{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.942382795085329, "eval_steps": 500, "global_step": 495000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 5.9442076668390486e-05, "grad_norm": 142.8204803466797, "learning_rate": 1.0699510200199725e-09, "loss": 3.738, "step": 10 }, { "epoch": 0.00011888415333678097, "grad_norm": 153.15045166015625, "learning_rate": 2.258785486708831e-09, "loss": 3.7609, "step": 20 }, { "epoch": 0.00017832623000517146, "grad_norm": 154.2900848388672, "learning_rate": 3.447619953397689e-09, "loss": 3.9563, "step": 30 }, { "epoch": 0.00023776830667356194, "grad_norm": 108.8991470336914, "learning_rate": 4.636454420086548e-09, "loss": 3.7018, "step": 40 }, { "epoch": 0.00029721038334195243, "grad_norm": 122.93909454345703, "learning_rate": 5.825288886775406e-09, "loss": 3.7964, "step": 50 }, { "epoch": 0.0003566524600103429, "grad_norm": 127.4955825805664, "learning_rate": 7.014123353464264e-09, "loss": 3.651, "step": 60 }, { "epoch": 0.0004160945366787334, "grad_norm": 126.6866226196289, "learning_rate": 8.202957820153123e-09, "loss": 3.8742, "step": 70 }, { "epoch": 0.0004755366133471239, "grad_norm": 110.9653549194336, "learning_rate": 9.39179228684198e-09, "loss": 3.7151, "step": 80 }, { "epoch": 0.0005349786900155144, "grad_norm": 138.6591033935547, "learning_rate": 1.0580626753530839e-08, "loss": 3.8349, "step": 90 }, { "epoch": 0.0005944207666839049, "grad_norm": 128.8533172607422, "learning_rate": 1.1769461220219698e-08, "loss": 3.6779, "step": 100 }, { "epoch": 0.0006538628433522954, "grad_norm": 139.779541015625, "learning_rate": 1.2958295686908556e-08, "loss": 3.8681, "step": 110 }, { "epoch": 0.0007133049200206858, "grad_norm": 116.91218566894531, "learning_rate": 1.4147130153597414e-08, "loss": 3.6415, "step": 120 }, { "epoch": 0.0007727469966890764, "grad_norm": 136.36407470703125, "learning_rate": 1.533596462028627e-08, "loss": 3.7366, "step": 130 }, { "epoch": 0.0008321890733574668, "grad_norm": 111.01805114746094, "learning_rate": 1.652479908697513e-08, "loss": 3.8076, "step": 140 }, { "epoch": 0.0008916311500258573, "grad_norm": 125.07760620117188, "learning_rate": 1.771363355366399e-08, "loss": 3.8268, "step": 150 }, { "epoch": 0.0009510732266942478, "grad_norm": 111.2386474609375, "learning_rate": 1.8902468020352848e-08, "loss": 3.5621, "step": 160 }, { "epoch": 0.0010105153033626382, "grad_norm": 114.46339416503906, "learning_rate": 2.0091302487041706e-08, "loss": 3.706, "step": 170 }, { "epoch": 0.0010699573800310289, "grad_norm": 137.96685791015625, "learning_rate": 2.1280136953730564e-08, "loss": 3.6157, "step": 180 }, { "epoch": 0.0011293994566994193, "grad_norm": 112.75586700439453, "learning_rate": 2.246897142041942e-08, "loss": 3.7094, "step": 190 }, { "epoch": 0.0011888415333678097, "grad_norm": 103.88154602050781, "learning_rate": 2.3657805887108283e-08, "loss": 3.484, "step": 200 }, { "epoch": 0.0012482836100362001, "grad_norm": 113.05964660644531, "learning_rate": 2.4846640353797137e-08, "loss": 3.6484, "step": 210 }, { "epoch": 0.0013077256867045908, "grad_norm": 117.55992126464844, "learning_rate": 2.6035474820486e-08, "loss": 3.7357, "step": 220 }, { "epoch": 0.0013671677633729812, "grad_norm": 114.67710876464844, "learning_rate": 2.7224309287174856e-08, "loss": 3.4386, "step": 230 }, { "epoch": 0.0014266098400413717, "grad_norm": 115.60771942138672, "learning_rate": 2.8413143753863714e-08, "loss": 3.4812, "step": 240 }, { "epoch": 0.001486051916709762, "grad_norm": 97.30168151855469, "learning_rate": 2.9601978220552575e-08, "loss": 3.4195, "step": 250 }, { "epoch": 0.0015454939933781527, "grad_norm": 114.11622619628906, "learning_rate": 3.079081268724143e-08, "loss": 3.5109, "step": 260 }, { "epoch": 0.0016049360700465432, "grad_norm": 113.13707733154297, "learning_rate": 3.1979647153930294e-08, "loss": 3.221, "step": 270 }, { "epoch": 0.0016643781467149336, "grad_norm": 96.0907974243164, "learning_rate": 3.316848162061915e-08, "loss": 3.3456, "step": 280 }, { "epoch": 0.001723820223383324, "grad_norm": 105.48980712890625, "learning_rate": 3.4357316087308e-08, "loss": 3.215, "step": 290 }, { "epoch": 0.0017832623000517147, "grad_norm": 104.56330108642578, "learning_rate": 3.5546150553996864e-08, "loss": 3.1982, "step": 300 }, { "epoch": 0.0018427043767201051, "grad_norm": 105.2012939453125, "learning_rate": 3.6734985020685725e-08, "loss": 3.1046, "step": 310 }, { "epoch": 0.0019021464533884955, "grad_norm": 88.62401580810547, "learning_rate": 3.792381948737458e-08, "loss": 3.1328, "step": 320 }, { "epoch": 0.001961588530056886, "grad_norm": 107.9185562133789, "learning_rate": 3.911265395406344e-08, "loss": 3.0531, "step": 330 }, { "epoch": 0.0020210306067252764, "grad_norm": 96.996337890625, "learning_rate": 4.03014884207523e-08, "loss": 2.8623, "step": 340 }, { "epoch": 0.002080472683393667, "grad_norm": 98.93458557128906, "learning_rate": 4.149032288744115e-08, "loss": 2.9403, "step": 350 }, { "epoch": 0.0021399147600620577, "grad_norm": 99.17608642578125, "learning_rate": 4.267915735413001e-08, "loss": 2.7797, "step": 360 }, { "epoch": 0.002199356836730448, "grad_norm": 104.47807312011719, "learning_rate": 4.386799182081887e-08, "loss": 2.686, "step": 370 }, { "epoch": 0.0022587989133988386, "grad_norm": 84.0674057006836, "learning_rate": 4.505682628750773e-08, "loss": 2.5373, "step": 380 }, { "epoch": 0.0023182409900672288, "grad_norm": 82.14847564697266, "learning_rate": 4.624566075419659e-08, "loss": 2.1917, "step": 390 }, { "epoch": 0.0023776830667356194, "grad_norm": 74.021240234375, "learning_rate": 4.743449522088545e-08, "loss": 2.2905, "step": 400 }, { "epoch": 0.00243712514340401, "grad_norm": 60.24504089355469, "learning_rate": 4.862332968757431e-08, "loss": 2.2268, "step": 410 }, { "epoch": 0.0024965672200724003, "grad_norm": 64.7810287475586, "learning_rate": 4.9812164154263165e-08, "loss": 2.1427, "step": 420 }, { "epoch": 0.002556009296740791, "grad_norm": 60.40483856201172, "learning_rate": 5.1000998620952026e-08, "loss": 2.1162, "step": 430 }, { "epoch": 0.0026154513734091816, "grad_norm": 61.14876174926758, "learning_rate": 5.218983308764089e-08, "loss": 2.0827, "step": 440 }, { "epoch": 0.002674893450077572, "grad_norm": 47.130008697509766, "learning_rate": 5.3378667554329735e-08, "loss": 1.9132, "step": 450 }, { "epoch": 0.0027343355267459625, "grad_norm": 48.96464538574219, "learning_rate": 5.4567502021018596e-08, "loss": 2.0112, "step": 460 }, { "epoch": 0.002793777603414353, "grad_norm": 47.480716705322266, "learning_rate": 5.575633648770746e-08, "loss": 1.9626, "step": 470 }, { "epoch": 0.0028532196800827433, "grad_norm": 60.5544548034668, "learning_rate": 5.694517095439631e-08, "loss": 1.9789, "step": 480 }, { "epoch": 0.002912661756751134, "grad_norm": 39.21125411987305, "learning_rate": 5.813400542108517e-08, "loss": 1.8061, "step": 490 }, { "epoch": 0.002972103833419524, "grad_norm": 39.745304107666016, "learning_rate": 5.9322839887774034e-08, "loss": 1.8608, "step": 500 }, { "epoch": 0.003031545910087915, "grad_norm": 36.55559158325195, "learning_rate": 6.051167435446288e-08, "loss": 1.7238, "step": 510 }, { "epoch": 0.0030909879867563055, "grad_norm": 30.57044219970703, "learning_rate": 6.170050882115174e-08, "loss": 1.8831, "step": 520 }, { "epoch": 0.0031504300634246957, "grad_norm": 36.26030731201172, "learning_rate": 6.28893432878406e-08, "loss": 1.7619, "step": 530 }, { "epoch": 0.0032098721400930863, "grad_norm": 33.17578125, "learning_rate": 6.407817775452947e-08, "loss": 1.6037, "step": 540 }, { "epoch": 0.003269314216761477, "grad_norm": 28.396364212036133, "learning_rate": 6.526701222121833e-08, "loss": 1.678, "step": 550 }, { "epoch": 0.003328756293429867, "grad_norm": 27.609539031982422, "learning_rate": 6.645584668790719e-08, "loss": 1.7237, "step": 560 }, { "epoch": 0.003388198370098258, "grad_norm": 32.41559982299805, "learning_rate": 6.764468115459605e-08, "loss": 1.7507, "step": 570 }, { "epoch": 0.003447640446766648, "grad_norm": 23.16154670715332, "learning_rate": 6.88335156212849e-08, "loss": 1.6398, "step": 580 }, { "epoch": 0.0035070825234350387, "grad_norm": 25.311086654663086, "learning_rate": 7.002235008797376e-08, "loss": 1.6741, "step": 590 }, { "epoch": 0.0035665246001034294, "grad_norm": 21.13146209716797, "learning_rate": 7.121118455466262e-08, "loss": 1.6215, "step": 600 }, { "epoch": 0.0036259666767718196, "grad_norm": 25.63249397277832, "learning_rate": 7.240001902135147e-08, "loss": 1.6226, "step": 610 }, { "epoch": 0.0036854087534402102, "grad_norm": 26.986520767211914, "learning_rate": 7.358885348804033e-08, "loss": 1.6677, "step": 620 }, { "epoch": 0.003744850830108601, "grad_norm": 29.49153709411621, "learning_rate": 7.477768795472919e-08, "loss": 1.6123, "step": 630 }, { "epoch": 0.003804292906776991, "grad_norm": 21.227563858032227, "learning_rate": 7.596652242141805e-08, "loss": 1.5763, "step": 640 }, { "epoch": 0.0038637349834453817, "grad_norm": 22.31380271911621, "learning_rate": 7.715535688810691e-08, "loss": 1.7628, "step": 650 }, { "epoch": 0.003923177060113772, "grad_norm": 32.52976608276367, "learning_rate": 7.834419135479577e-08, "loss": 1.4523, "step": 660 }, { "epoch": 0.003982619136782163, "grad_norm": 22.066234588623047, "learning_rate": 7.953302582148463e-08, "loss": 1.5481, "step": 670 }, { "epoch": 0.004042061213450553, "grad_norm": 29.661739349365234, "learning_rate": 8.072186028817348e-08, "loss": 1.661, "step": 680 }, { "epoch": 0.004101503290118944, "grad_norm": 26.46805763244629, "learning_rate": 8.191069475486233e-08, "loss": 1.6265, "step": 690 }, { "epoch": 0.004160945366787334, "grad_norm": 18.76072120666504, "learning_rate": 8.309952922155119e-08, "loss": 1.5786, "step": 700 }, { "epoch": 0.004220387443455724, "grad_norm": 21.77655601501465, "learning_rate": 8.428836368824005e-08, "loss": 1.5622, "step": 710 }, { "epoch": 0.004279829520124115, "grad_norm": 27.587722778320312, "learning_rate": 8.547719815492891e-08, "loss": 1.6622, "step": 720 }, { "epoch": 0.004339271596792506, "grad_norm": 21.74022102355957, "learning_rate": 8.666603262161777e-08, "loss": 1.5505, "step": 730 }, { "epoch": 0.004398713673460896, "grad_norm": 22.006620407104492, "learning_rate": 8.785486708830663e-08, "loss": 1.5329, "step": 740 }, { "epoch": 0.004458155750129287, "grad_norm": 20.711097717285156, "learning_rate": 8.90437015549955e-08, "loss": 1.5481, "step": 750 }, { "epoch": 0.004517597826797677, "grad_norm": 28.8737735748291, "learning_rate": 9.023253602168434e-08, "loss": 1.5805, "step": 760 }, { "epoch": 0.004577039903466067, "grad_norm": 20.881452560424805, "learning_rate": 9.14213704883732e-08, "loss": 1.6173, "step": 770 }, { "epoch": 0.0046364819801344576, "grad_norm": 22.550430297851562, "learning_rate": 9.261020495506207e-08, "loss": 1.495, "step": 780 }, { "epoch": 0.004695924056802849, "grad_norm": 22.484834671020508, "learning_rate": 9.379903942175093e-08, "loss": 1.5131, "step": 790 }, { "epoch": 0.004755366133471239, "grad_norm": 23.026416778564453, "learning_rate": 9.498787388843979e-08, "loss": 1.5662, "step": 800 }, { "epoch": 0.004814808210139629, "grad_norm": 16.993587493896484, "learning_rate": 9.617670835512865e-08, "loss": 1.5431, "step": 810 }, { "epoch": 0.00487425028680802, "grad_norm": 23.572917938232422, "learning_rate": 9.736554282181748e-08, "loss": 1.5333, "step": 820 }, { "epoch": 0.00493369236347641, "grad_norm": 22.71282196044922, "learning_rate": 9.855437728850635e-08, "loss": 1.626, "step": 830 }, { "epoch": 0.004993134440144801, "grad_norm": 20.586082458496094, "learning_rate": 9.97432117551952e-08, "loss": 1.6429, "step": 840 }, { "epoch": 0.005052576516813192, "grad_norm": 25.245033264160156, "learning_rate": 1.0093204622188407e-07, "loss": 1.543, "step": 850 }, { "epoch": 0.005112018593481582, "grad_norm": 25.446678161621094, "learning_rate": 1.0212088068857293e-07, "loss": 1.5229, "step": 860 }, { "epoch": 0.005171460670149972, "grad_norm": 24.73455810546875, "learning_rate": 1.0330971515526179e-07, "loss": 1.4813, "step": 870 }, { "epoch": 0.005230902746818363, "grad_norm": 18.370105743408203, "learning_rate": 1.0449854962195065e-07, "loss": 1.4618, "step": 880 }, { "epoch": 0.005290344823486753, "grad_norm": 20.508440017700195, "learning_rate": 1.056873840886395e-07, "loss": 1.4901, "step": 890 }, { "epoch": 0.005349786900155144, "grad_norm": 31.30401039123535, "learning_rate": 1.0687621855532836e-07, "loss": 1.5939, "step": 900 }, { "epoch": 0.005409228976823535, "grad_norm": 22.659048080444336, "learning_rate": 1.0806505302201722e-07, "loss": 1.6579, "step": 910 }, { "epoch": 0.005468671053491925, "grad_norm": 23.593046188354492, "learning_rate": 1.0925388748870608e-07, "loss": 1.5915, "step": 920 }, { "epoch": 0.005528113130160315, "grad_norm": 21.9558048248291, "learning_rate": 1.1044272195539494e-07, "loss": 1.4843, "step": 930 }, { "epoch": 0.005587555206828706, "grad_norm": 19.212968826293945, "learning_rate": 1.116315564220838e-07, "loss": 1.5815, "step": 940 }, { "epoch": 0.005646997283497096, "grad_norm": 22.45987319946289, "learning_rate": 1.1282039088877267e-07, "loss": 1.5167, "step": 950 }, { "epoch": 0.005706439360165487, "grad_norm": 20.059814453125, "learning_rate": 1.1400922535546151e-07, "loss": 1.4342, "step": 960 }, { "epoch": 0.005765881436833877, "grad_norm": 18.084604263305664, "learning_rate": 1.1519805982215037e-07, "loss": 1.5294, "step": 970 }, { "epoch": 0.005825323513502268, "grad_norm": 18.982830047607422, "learning_rate": 1.1638689428883924e-07, "loss": 1.4848, "step": 980 }, { "epoch": 0.005884765590170658, "grad_norm": 21.61163330078125, "learning_rate": 1.175757287555281e-07, "loss": 1.4369, "step": 990 }, { "epoch": 0.005944207666839048, "grad_norm": 24.843563079833984, "learning_rate": 1.1876456322221696e-07, "loss": 1.5007, "step": 1000 }, { "epoch": 0.0060036497435074394, "grad_norm": 23.25098419189453, "learning_rate": 1.1995339768890582e-07, "loss": 1.5392, "step": 1010 }, { "epoch": 0.00606309182017583, "grad_norm": 25.345609664916992, "learning_rate": 1.2114223215559467e-07, "loss": 1.5068, "step": 1020 }, { "epoch": 0.00612253389684422, "grad_norm": 18.804574966430664, "learning_rate": 1.2233106662228351e-07, "loss": 1.4414, "step": 1030 }, { "epoch": 0.006181975973512611, "grad_norm": 22.42491912841797, "learning_rate": 1.235199010889724e-07, "loss": 1.4805, "step": 1040 }, { "epoch": 0.006241418050181001, "grad_norm": 25.61677360534668, "learning_rate": 1.2470873555566124e-07, "loss": 1.439, "step": 1050 }, { "epoch": 0.006300860126849391, "grad_norm": 18.852542877197266, "learning_rate": 1.258975700223501e-07, "loss": 1.4462, "step": 1060 }, { "epoch": 0.0063603022035177825, "grad_norm": 19.345195770263672, "learning_rate": 1.2708640448903896e-07, "loss": 1.4516, "step": 1070 }, { "epoch": 0.006419744280186173, "grad_norm": 19.4258975982666, "learning_rate": 1.2827523895572783e-07, "loss": 1.458, "step": 1080 }, { "epoch": 0.006479186356854563, "grad_norm": 19.71558952331543, "learning_rate": 1.2946407342241665e-07, "loss": 1.4878, "step": 1090 }, { "epoch": 0.006538628433522954, "grad_norm": 18.586057662963867, "learning_rate": 1.3065290788910553e-07, "loss": 1.3585, "step": 1100 }, { "epoch": 0.006598070510191344, "grad_norm": 21.647172927856445, "learning_rate": 1.3184174235579438e-07, "loss": 1.5068, "step": 1110 }, { "epoch": 0.006657512586859734, "grad_norm": 23.60793685913086, "learning_rate": 1.3303057682248325e-07, "loss": 1.4351, "step": 1120 }, { "epoch": 0.006716954663528125, "grad_norm": 18.26819610595703, "learning_rate": 1.342194112891721e-07, "loss": 1.4808, "step": 1130 }, { "epoch": 0.006776396740196516, "grad_norm": 20.810312271118164, "learning_rate": 1.3540824575586097e-07, "loss": 1.4727, "step": 1140 }, { "epoch": 0.006835838816864906, "grad_norm": 16.851009368896484, "learning_rate": 1.3659708022254982e-07, "loss": 1.4228, "step": 1150 }, { "epoch": 0.006895280893533296, "grad_norm": 16.90770149230957, "learning_rate": 1.3778591468923867e-07, "loss": 1.4667, "step": 1160 }, { "epoch": 0.006954722970201687, "grad_norm": 19.7625675201416, "learning_rate": 1.3897474915592754e-07, "loss": 1.3464, "step": 1170 }, { "epoch": 0.007014165046870077, "grad_norm": 22.858238220214844, "learning_rate": 1.401635836226164e-07, "loss": 1.4451, "step": 1180 }, { "epoch": 0.007073607123538468, "grad_norm": 21.537090301513672, "learning_rate": 1.4135241808930527e-07, "loss": 1.506, "step": 1190 }, { "epoch": 0.007133049200206859, "grad_norm": 19.98550796508789, "learning_rate": 1.4254125255599411e-07, "loss": 1.5359, "step": 1200 }, { "epoch": 0.007192491276875249, "grad_norm": 18.627988815307617, "learning_rate": 1.43730087022683e-07, "loss": 1.4433, "step": 1210 }, { "epoch": 0.007251933353543639, "grad_norm": 17.521024703979492, "learning_rate": 1.4491892148937184e-07, "loss": 1.395, "step": 1220 }, { "epoch": 0.00731137543021203, "grad_norm": 23.037599563598633, "learning_rate": 1.4610775595606068e-07, "loss": 1.3897, "step": 1230 }, { "epoch": 0.0073708175068804204, "grad_norm": 20.76737403869629, "learning_rate": 1.4729659042274956e-07, "loss": 1.3718, "step": 1240 }, { "epoch": 0.007430259583548811, "grad_norm": 18.938125610351562, "learning_rate": 1.484854248894384e-07, "loss": 1.3431, "step": 1250 }, { "epoch": 0.007489701660217202, "grad_norm": 19.237403869628906, "learning_rate": 1.4967425935612728e-07, "loss": 1.41, "step": 1260 }, { "epoch": 0.007549143736885592, "grad_norm": 21.492952346801758, "learning_rate": 1.5086309382281613e-07, "loss": 1.4748, "step": 1270 }, { "epoch": 0.007608585813553982, "grad_norm": 18.916730880737305, "learning_rate": 1.5205192828950498e-07, "loss": 1.4097, "step": 1280 }, { "epoch": 0.007668027890222372, "grad_norm": 31.397336959838867, "learning_rate": 1.5324076275619382e-07, "loss": 1.451, "step": 1290 }, { "epoch": 0.0077274699668907635, "grad_norm": 21.82578468322754, "learning_rate": 1.544295972228827e-07, "loss": 1.4506, "step": 1300 }, { "epoch": 0.007786912043559154, "grad_norm": 16.137210845947266, "learning_rate": 1.5561843168957155e-07, "loss": 1.3593, "step": 1310 }, { "epoch": 0.007846354120227545, "grad_norm": 17.033477783203125, "learning_rate": 1.568072661562604e-07, "loss": 1.3327, "step": 1320 }, { "epoch": 0.007905796196895935, "grad_norm": 19.041601181030273, "learning_rate": 1.5799610062294927e-07, "loss": 1.4279, "step": 1330 }, { "epoch": 0.007965238273564325, "grad_norm": 24.064237594604492, "learning_rate": 1.5918493508963812e-07, "loss": 1.407, "step": 1340 }, { "epoch": 0.008024680350232715, "grad_norm": 13.883526802062988, "learning_rate": 1.60373769556327e-07, "loss": 1.378, "step": 1350 }, { "epoch": 0.008084122426901106, "grad_norm": 18.946311950683594, "learning_rate": 1.6156260402301584e-07, "loss": 1.3472, "step": 1360 }, { "epoch": 0.008143564503569498, "grad_norm": 18.99662208557129, "learning_rate": 1.6275143848970471e-07, "loss": 1.4673, "step": 1370 }, { "epoch": 0.008203006580237888, "grad_norm": 19.97707748413086, "learning_rate": 1.6394027295639356e-07, "loss": 1.3783, "step": 1380 }, { "epoch": 0.008262448656906278, "grad_norm": 20.736446380615234, "learning_rate": 1.6512910742308244e-07, "loss": 1.4188, "step": 1390 }, { "epoch": 0.008321890733574668, "grad_norm": 14.545549392700195, "learning_rate": 1.6631794188977128e-07, "loss": 1.3224, "step": 1400 }, { "epoch": 0.008381332810243058, "grad_norm": 20.700824737548828, "learning_rate": 1.6750677635646016e-07, "loss": 1.4069, "step": 1410 }, { "epoch": 0.008440774886911449, "grad_norm": 18.52537727355957, "learning_rate": 1.68695610823149e-07, "loss": 1.368, "step": 1420 }, { "epoch": 0.008500216963579839, "grad_norm": 24.041866302490234, "learning_rate": 1.6988444528983788e-07, "loss": 1.394, "step": 1430 }, { "epoch": 0.00855965904024823, "grad_norm": 19.720012664794922, "learning_rate": 1.7107327975652673e-07, "loss": 1.354, "step": 1440 }, { "epoch": 0.008619101116916621, "grad_norm": 19.089096069335938, "learning_rate": 1.7226211422321555e-07, "loss": 1.3488, "step": 1450 }, { "epoch": 0.008678543193585011, "grad_norm": 18.81599235534668, "learning_rate": 1.7345094868990442e-07, "loss": 1.3606, "step": 1460 }, { "epoch": 0.008737985270253401, "grad_norm": 15.38290786743164, "learning_rate": 1.7463978315659327e-07, "loss": 1.309, "step": 1470 }, { "epoch": 0.008797427346921792, "grad_norm": 20.672088623046875, "learning_rate": 1.7582861762328215e-07, "loss": 1.3928, "step": 1480 }, { "epoch": 0.008856869423590182, "grad_norm": 17.214942932128906, "learning_rate": 1.77017452089971e-07, "loss": 1.4077, "step": 1490 }, { "epoch": 0.008916311500258574, "grad_norm": 17.585832595825195, "learning_rate": 1.7820628655665987e-07, "loss": 1.354, "step": 1500 }, { "epoch": 0.008975753576926964, "grad_norm": 20.314302444458008, "learning_rate": 1.7939512102334872e-07, "loss": 1.3169, "step": 1510 }, { "epoch": 0.009035195653595354, "grad_norm": 20.30255699157715, "learning_rate": 1.805839554900376e-07, "loss": 1.3903, "step": 1520 }, { "epoch": 0.009094637730263744, "grad_norm": 21.01532554626465, "learning_rate": 1.8177278995672644e-07, "loss": 1.2965, "step": 1530 }, { "epoch": 0.009154079806932135, "grad_norm": 21.063505172729492, "learning_rate": 1.829616244234153e-07, "loss": 1.3785, "step": 1540 }, { "epoch": 0.009213521883600525, "grad_norm": 16.34746551513672, "learning_rate": 1.8415045889010416e-07, "loss": 1.3523, "step": 1550 }, { "epoch": 0.009272963960268915, "grad_norm": 18.715604782104492, "learning_rate": 1.8533929335679304e-07, "loss": 1.3724, "step": 1560 }, { "epoch": 0.009332406036937307, "grad_norm": 19.077892303466797, "learning_rate": 1.8652812782348188e-07, "loss": 1.3733, "step": 1570 }, { "epoch": 0.009391848113605697, "grad_norm": 21.954431533813477, "learning_rate": 1.877169622901707e-07, "loss": 1.3239, "step": 1580 }, { "epoch": 0.009451290190274087, "grad_norm": 17.090776443481445, "learning_rate": 1.8890579675685958e-07, "loss": 1.3594, "step": 1590 }, { "epoch": 0.009510732266942478, "grad_norm": 22.086397171020508, "learning_rate": 1.9009463122354843e-07, "loss": 1.2588, "step": 1600 }, { "epoch": 0.009570174343610868, "grad_norm": 20.473947525024414, "learning_rate": 1.912834656902373e-07, "loss": 1.3144, "step": 1610 }, { "epoch": 0.009629616420279258, "grad_norm": 14.533893585205078, "learning_rate": 1.9247230015692615e-07, "loss": 1.298, "step": 1620 }, { "epoch": 0.00968905849694765, "grad_norm": 21.011661529541016, "learning_rate": 1.9366113462361502e-07, "loss": 1.3135, "step": 1630 }, { "epoch": 0.00974850057361604, "grad_norm": 15.744470596313477, "learning_rate": 1.9484996909030387e-07, "loss": 1.2219, "step": 1640 }, { "epoch": 0.00980794265028443, "grad_norm": 18.017230987548828, "learning_rate": 1.9603880355699275e-07, "loss": 1.3297, "step": 1650 }, { "epoch": 0.00986738472695282, "grad_norm": 13.59457015991211, "learning_rate": 1.972276380236816e-07, "loss": 1.3757, "step": 1660 }, { "epoch": 0.009926826803621211, "grad_norm": 18.09391212463379, "learning_rate": 1.9841647249037047e-07, "loss": 1.321, "step": 1670 }, { "epoch": 0.009986268880289601, "grad_norm": 21.585641860961914, "learning_rate": 1.9960530695705932e-07, "loss": 1.3194, "step": 1680 }, { "epoch": 0.010045710956957993, "grad_norm": 22.948410034179688, "learning_rate": 2.007941414237482e-07, "loss": 1.3366, "step": 1690 }, { "epoch": 0.010105153033626383, "grad_norm": 18.838281631469727, "learning_rate": 2.0198297589043704e-07, "loss": 1.2935, "step": 1700 }, { "epoch": 0.010164595110294774, "grad_norm": 24.80682373046875, "learning_rate": 2.0317181035712589e-07, "loss": 1.3203, "step": 1710 }, { "epoch": 0.010224037186963164, "grad_norm": 15.833219528198242, "learning_rate": 2.0436064482381473e-07, "loss": 1.328, "step": 1720 }, { "epoch": 0.010283479263631554, "grad_norm": 20.291078567504883, "learning_rate": 2.055494792905036e-07, "loss": 1.3237, "step": 1730 }, { "epoch": 0.010342921340299944, "grad_norm": 20.075071334838867, "learning_rate": 2.0673831375719246e-07, "loss": 1.2875, "step": 1740 }, { "epoch": 0.010402363416968334, "grad_norm": 22.968372344970703, "learning_rate": 2.0792714822388133e-07, "loss": 1.3541, "step": 1750 }, { "epoch": 0.010461805493636726, "grad_norm": 16.901681900024414, "learning_rate": 2.0911598269057018e-07, "loss": 1.3578, "step": 1760 }, { "epoch": 0.010521247570305117, "grad_norm": 16.027311325073242, "learning_rate": 2.1030481715725905e-07, "loss": 1.2871, "step": 1770 }, { "epoch": 0.010580689646973507, "grad_norm": 21.43961524963379, "learning_rate": 2.114936516239479e-07, "loss": 1.3278, "step": 1780 }, { "epoch": 0.010640131723641897, "grad_norm": 19.064624786376953, "learning_rate": 2.1268248609063677e-07, "loss": 1.2864, "step": 1790 }, { "epoch": 0.010699573800310287, "grad_norm": 21.735164642333984, "learning_rate": 2.1387132055732562e-07, "loss": 1.3458, "step": 1800 }, { "epoch": 0.010759015876978677, "grad_norm": 18.099445343017578, "learning_rate": 2.150601550240145e-07, "loss": 1.336, "step": 1810 }, { "epoch": 0.01081845795364707, "grad_norm": 16.138845443725586, "learning_rate": 2.1624898949070334e-07, "loss": 1.2583, "step": 1820 }, { "epoch": 0.01087790003031546, "grad_norm": 16.871862411499023, "learning_rate": 2.1743782395739222e-07, "loss": 1.2394, "step": 1830 }, { "epoch": 0.01093734210698385, "grad_norm": 18.16187286376953, "learning_rate": 2.1862665842408104e-07, "loss": 1.1952, "step": 1840 }, { "epoch": 0.01099678418365224, "grad_norm": 22.97513771057129, "learning_rate": 2.198154928907699e-07, "loss": 1.3372, "step": 1850 }, { "epoch": 0.01105622626032063, "grad_norm": 19.569843292236328, "learning_rate": 2.2100432735745876e-07, "loss": 1.3118, "step": 1860 }, { "epoch": 0.01111566833698902, "grad_norm": 21.27242660522461, "learning_rate": 2.221931618241476e-07, "loss": 1.3752, "step": 1870 }, { "epoch": 0.011175110413657412, "grad_norm": 17.89333152770996, "learning_rate": 2.2338199629083649e-07, "loss": 1.3348, "step": 1880 }, { "epoch": 0.011234552490325803, "grad_norm": 17.545726776123047, "learning_rate": 2.2457083075752533e-07, "loss": 1.2274, "step": 1890 }, { "epoch": 0.011293994566994193, "grad_norm": 21.060157775878906, "learning_rate": 2.257596652242142e-07, "loss": 1.3284, "step": 1900 }, { "epoch": 0.011353436643662583, "grad_norm": 17.806838989257812, "learning_rate": 2.2694849969090306e-07, "loss": 1.2463, "step": 1910 }, { "epoch": 0.011412878720330973, "grad_norm": 19.51150894165039, "learning_rate": 2.2813733415759193e-07, "loss": 1.2388, "step": 1920 }, { "epoch": 0.011472320796999363, "grad_norm": 19.389543533325195, "learning_rate": 2.2932616862428078e-07, "loss": 1.2727, "step": 1930 }, { "epoch": 0.011531762873667754, "grad_norm": 20.359148025512695, "learning_rate": 2.3051500309096965e-07, "loss": 1.2396, "step": 1940 }, { "epoch": 0.011591204950336146, "grad_norm": 17.298683166503906, "learning_rate": 2.317038375576585e-07, "loss": 1.2792, "step": 1950 }, { "epoch": 0.011650647027004536, "grad_norm": 17.550142288208008, "learning_rate": 2.3289267202434737e-07, "loss": 1.2494, "step": 1960 }, { "epoch": 0.011710089103672926, "grad_norm": 16.455577850341797, "learning_rate": 2.340815064910362e-07, "loss": 1.2353, "step": 1970 }, { "epoch": 0.011769531180341316, "grad_norm": 20.76070785522461, "learning_rate": 2.3527034095772504e-07, "loss": 1.2916, "step": 1980 }, { "epoch": 0.011828973257009706, "grad_norm": 17.456588745117188, "learning_rate": 2.3645917542441392e-07, "loss": 1.277, "step": 1990 }, { "epoch": 0.011888415333678097, "grad_norm": 17.562145233154297, "learning_rate": 2.3764800989110277e-07, "loss": 1.2763, "step": 2000 }, { "epoch": 0.011947857410346489, "grad_norm": 16.343036651611328, "learning_rate": 2.388368443577916e-07, "loss": 1.2785, "step": 2010 }, { "epoch": 0.012007299487014879, "grad_norm": 21.982229232788086, "learning_rate": 2.400256788244805e-07, "loss": 1.1566, "step": 2020 }, { "epoch": 0.012066741563683269, "grad_norm": 20.859201431274414, "learning_rate": 2.4121451329116936e-07, "loss": 1.1882, "step": 2030 }, { "epoch": 0.01212618364035166, "grad_norm": 17.00811004638672, "learning_rate": 2.4240334775785824e-07, "loss": 1.2306, "step": 2040 }, { "epoch": 0.01218562571702005, "grad_norm": 15.392210960388184, "learning_rate": 2.4359218222454706e-07, "loss": 1.2427, "step": 2050 }, { "epoch": 0.01224506779368844, "grad_norm": 17.207990646362305, "learning_rate": 2.4478101669123593e-07, "loss": 1.2666, "step": 2060 }, { "epoch": 0.01230450987035683, "grad_norm": 16.48379898071289, "learning_rate": 2.459698511579248e-07, "loss": 1.2852, "step": 2070 }, { "epoch": 0.012363951947025222, "grad_norm": 18.824119567871094, "learning_rate": 2.471586856246137e-07, "loss": 1.2267, "step": 2080 }, { "epoch": 0.012423394023693612, "grad_norm": 15.689943313598633, "learning_rate": 2.483475200913025e-07, "loss": 1.2004, "step": 2090 }, { "epoch": 0.012482836100362002, "grad_norm": 22.152910232543945, "learning_rate": 2.495363545579913e-07, "loss": 1.2997, "step": 2100 }, { "epoch": 0.012542278177030393, "grad_norm": 17.10980224609375, "learning_rate": 2.507251890246802e-07, "loss": 1.2757, "step": 2110 }, { "epoch": 0.012601720253698783, "grad_norm": 20.45684242248535, "learning_rate": 2.5191402349136907e-07, "loss": 1.286, "step": 2120 }, { "epoch": 0.012661162330367173, "grad_norm": 16.058500289916992, "learning_rate": 2.5310285795805795e-07, "loss": 1.2928, "step": 2130 }, { "epoch": 0.012720604407035565, "grad_norm": 15.345049858093262, "learning_rate": 2.5429169242474677e-07, "loss": 1.2069, "step": 2140 }, { "epoch": 0.012780046483703955, "grad_norm": 16.456327438354492, "learning_rate": 2.5548052689143564e-07, "loss": 1.3096, "step": 2150 }, { "epoch": 0.012839488560372345, "grad_norm": 18.84521484375, "learning_rate": 2.566693613581245e-07, "loss": 1.2402, "step": 2160 }, { "epoch": 0.012898930637040736, "grad_norm": 24.64852523803711, "learning_rate": 2.578581958248134e-07, "loss": 1.2406, "step": 2170 }, { "epoch": 0.012958372713709126, "grad_norm": 19.37799835205078, "learning_rate": 2.590470302915022e-07, "loss": 1.2359, "step": 2180 }, { "epoch": 0.013017814790377516, "grad_norm": 17.10253143310547, "learning_rate": 2.602358647581911e-07, "loss": 1.2846, "step": 2190 }, { "epoch": 0.013077256867045908, "grad_norm": 15.017139434814453, "learning_rate": 2.6142469922487996e-07, "loss": 1.1735, "step": 2200 }, { "epoch": 0.013136698943714298, "grad_norm": 19.67150115966797, "learning_rate": 2.6261353369156884e-07, "loss": 1.2097, "step": 2210 }, { "epoch": 0.013196141020382688, "grad_norm": 22.321420669555664, "learning_rate": 2.6380236815825766e-07, "loss": 1.1829, "step": 2220 }, { "epoch": 0.013255583097051079, "grad_norm": 16.23740577697754, "learning_rate": 2.6499120262494653e-07, "loss": 1.2239, "step": 2230 }, { "epoch": 0.013315025173719469, "grad_norm": 17.244110107421875, "learning_rate": 2.6618003709163535e-07, "loss": 1.1895, "step": 2240 }, { "epoch": 0.013374467250387859, "grad_norm": 16.879161834716797, "learning_rate": 2.6736887155832423e-07, "loss": 1.1623, "step": 2250 }, { "epoch": 0.01343390932705625, "grad_norm": 19.58763313293457, "learning_rate": 2.685577060250131e-07, "loss": 1.2237, "step": 2260 }, { "epoch": 0.013493351403724641, "grad_norm": 15.648295402526855, "learning_rate": 2.69746540491702e-07, "loss": 1.194, "step": 2270 }, { "epoch": 0.013552793480393031, "grad_norm": 22.292816162109375, "learning_rate": 2.709353749583908e-07, "loss": 1.3244, "step": 2280 }, { "epoch": 0.013612235557061422, "grad_norm": 18.384429931640625, "learning_rate": 2.7212420942507967e-07, "loss": 1.2602, "step": 2290 }, { "epoch": 0.013671677633729812, "grad_norm": 19.61041831970215, "learning_rate": 2.7331304389176855e-07, "loss": 1.2018, "step": 2300 }, { "epoch": 0.013731119710398202, "grad_norm": 18.517574310302734, "learning_rate": 2.745018783584574e-07, "loss": 1.1565, "step": 2310 }, { "epoch": 0.013790561787066592, "grad_norm": 24.6839542388916, "learning_rate": 2.7569071282514624e-07, "loss": 1.2868, "step": 2320 }, { "epoch": 0.013850003863734984, "grad_norm": 16.39267921447754, "learning_rate": 2.768795472918351e-07, "loss": 1.2252, "step": 2330 }, { "epoch": 0.013909445940403374, "grad_norm": 15.766027450561523, "learning_rate": 2.78068381758524e-07, "loss": 1.1785, "step": 2340 }, { "epoch": 0.013968888017071765, "grad_norm": 16.932952880859375, "learning_rate": 2.7925721622521287e-07, "loss": 1.1907, "step": 2350 }, { "epoch": 0.014028330093740155, "grad_norm": 15.728399276733398, "learning_rate": 2.804460506919017e-07, "loss": 1.1827, "step": 2360 }, { "epoch": 0.014087772170408545, "grad_norm": 18.61570167541504, "learning_rate": 2.816348851585905e-07, "loss": 1.1921, "step": 2370 }, { "epoch": 0.014147214247076935, "grad_norm": 20.070589065551758, "learning_rate": 2.828237196252794e-07, "loss": 1.1646, "step": 2380 }, { "epoch": 0.014206656323745327, "grad_norm": 14.780390739440918, "learning_rate": 2.8401255409196826e-07, "loss": 1.2657, "step": 2390 }, { "epoch": 0.014266098400413717, "grad_norm": 21.359405517578125, "learning_rate": 2.8520138855865713e-07, "loss": 1.2283, "step": 2400 }, { "epoch": 0.014325540477082108, "grad_norm": 16.16600799560547, "learning_rate": 2.8639022302534595e-07, "loss": 1.2796, "step": 2410 }, { "epoch": 0.014384982553750498, "grad_norm": 18.725557327270508, "learning_rate": 2.8757905749203483e-07, "loss": 1.2233, "step": 2420 }, { "epoch": 0.014444424630418888, "grad_norm": 14.538203239440918, "learning_rate": 2.887678919587237e-07, "loss": 1.2625, "step": 2430 }, { "epoch": 0.014503866707087278, "grad_norm": 15.281079292297363, "learning_rate": 2.899567264254126e-07, "loss": 1.1722, "step": 2440 }, { "epoch": 0.014563308783755669, "grad_norm": 15.156546592712402, "learning_rate": 2.911455608921014e-07, "loss": 1.1612, "step": 2450 }, { "epoch": 0.01462275086042406, "grad_norm": 16.161012649536133, "learning_rate": 2.9233439535879027e-07, "loss": 1.1172, "step": 2460 }, { "epoch": 0.01468219293709245, "grad_norm": 19.53667449951172, "learning_rate": 2.9352322982547915e-07, "loss": 1.1517, "step": 2470 }, { "epoch": 0.014741635013760841, "grad_norm": 21.974117279052734, "learning_rate": 2.94712064292168e-07, "loss": 1.1971, "step": 2480 }, { "epoch": 0.014801077090429231, "grad_norm": 20.818056106567383, "learning_rate": 2.9590089875885684e-07, "loss": 1.3008, "step": 2490 }, { "epoch": 0.014860519167097621, "grad_norm": 14.946151733398438, "learning_rate": 2.9708973322554566e-07, "loss": 1.2189, "step": 2500 }, { "epoch": 0.014919961243766012, "grad_norm": 18.564496994018555, "learning_rate": 2.9827856769223454e-07, "loss": 1.2218, "step": 2510 }, { "epoch": 0.014979403320434403, "grad_norm": 15.526782035827637, "learning_rate": 2.994674021589234e-07, "loss": 1.2095, "step": 2520 }, { "epoch": 0.015038845397102794, "grad_norm": 14.394434928894043, "learning_rate": 3.006562366256123e-07, "loss": 1.1631, "step": 2530 }, { "epoch": 0.015098287473771184, "grad_norm": 16.596900939941406, "learning_rate": 3.018450710923011e-07, "loss": 1.1596, "step": 2540 }, { "epoch": 0.015157729550439574, "grad_norm": 20.212078094482422, "learning_rate": 3.0303390555899e-07, "loss": 1.225, "step": 2550 }, { "epoch": 0.015217171627107964, "grad_norm": 20.668567657470703, "learning_rate": 3.0422274002567886e-07, "loss": 1.2503, "step": 2560 }, { "epoch": 0.015276613703776355, "grad_norm": 14.743304252624512, "learning_rate": 3.0541157449236773e-07, "loss": 1.1825, "step": 2570 }, { "epoch": 0.015336055780444745, "grad_norm": 21.97252655029297, "learning_rate": 3.0660040895905655e-07, "loss": 1.1865, "step": 2580 }, { "epoch": 0.015395497857113137, "grad_norm": 15.549202919006348, "learning_rate": 3.077892434257454e-07, "loss": 1.1282, "step": 2590 }, { "epoch": 0.015454939933781527, "grad_norm": 18.190990447998047, "learning_rate": 3.089780778924343e-07, "loss": 1.1935, "step": 2600 }, { "epoch": 0.015514382010449917, "grad_norm": 19.320322036743164, "learning_rate": 3.101669123591232e-07, "loss": 1.1899, "step": 2610 }, { "epoch": 0.015573824087118307, "grad_norm": 13.524117469787598, "learning_rate": 3.11355746825812e-07, "loss": 1.1515, "step": 2620 }, { "epoch": 0.0156332661637867, "grad_norm": 16.983749389648438, "learning_rate": 3.125445812925008e-07, "loss": 1.1442, "step": 2630 }, { "epoch": 0.01569270824045509, "grad_norm": 20.59708595275879, "learning_rate": 3.1373341575918975e-07, "loss": 1.2013, "step": 2640 }, { "epoch": 0.01575215031712348, "grad_norm": 17.333049774169922, "learning_rate": 3.1492225022587857e-07, "loss": 1.2264, "step": 2650 }, { "epoch": 0.01581159239379187, "grad_norm": 16.24986457824707, "learning_rate": 3.1611108469256744e-07, "loss": 1.1949, "step": 2660 }, { "epoch": 0.01587103447046026, "grad_norm": 15.802569389343262, "learning_rate": 3.1729991915925626e-07, "loss": 1.1764, "step": 2670 }, { "epoch": 0.01593047654712865, "grad_norm": 16.74067497253418, "learning_rate": 3.184887536259452e-07, "loss": 1.2345, "step": 2680 }, { "epoch": 0.01598991862379704, "grad_norm": 17.063261032104492, "learning_rate": 3.19677588092634e-07, "loss": 1.0868, "step": 2690 }, { "epoch": 0.01604936070046543, "grad_norm": 21.800209045410156, "learning_rate": 3.2086642255932283e-07, "loss": 1.1957, "step": 2700 }, { "epoch": 0.01610880277713382, "grad_norm": 15.871210098266602, "learning_rate": 3.220552570260117e-07, "loss": 1.114, "step": 2710 }, { "epoch": 0.01616824485380221, "grad_norm": 22.31130599975586, "learning_rate": 3.232440914927006e-07, "loss": 1.2346, "step": 2720 }, { "epoch": 0.0162276869304706, "grad_norm": 15.240211486816406, "learning_rate": 3.2443292595938946e-07, "loss": 1.0974, "step": 2730 }, { "epoch": 0.016287129007138995, "grad_norm": 15.052156448364258, "learning_rate": 3.256217604260783e-07, "loss": 1.1346, "step": 2740 }, { "epoch": 0.016346571083807385, "grad_norm": 16.094287872314453, "learning_rate": 3.2681059489276715e-07, "loss": 1.1177, "step": 2750 }, { "epoch": 0.016406013160475776, "grad_norm": 17.89839744567871, "learning_rate": 3.27999429359456e-07, "loss": 1.1521, "step": 2760 }, { "epoch": 0.016465455237144166, "grad_norm": 19.661712646484375, "learning_rate": 3.291882638261449e-07, "loss": 1.1576, "step": 2770 }, { "epoch": 0.016524897313812556, "grad_norm": 16.383609771728516, "learning_rate": 3.303770982928337e-07, "loss": 1.1369, "step": 2780 }, { "epoch": 0.016584339390480946, "grad_norm": 19.64452362060547, "learning_rate": 3.315659327595226e-07, "loss": 1.1756, "step": 2790 }, { "epoch": 0.016643781467149336, "grad_norm": 20.185192108154297, "learning_rate": 3.3275476722621147e-07, "loss": 1.1964, "step": 2800 }, { "epoch": 0.016703223543817727, "grad_norm": 16.611305236816406, "learning_rate": 3.3394360169290034e-07, "loss": 1.1354, "step": 2810 }, { "epoch": 0.016762665620486117, "grad_norm": 17.04556655883789, "learning_rate": 3.3513243615958917e-07, "loss": 1.1009, "step": 2820 }, { "epoch": 0.016822107697154507, "grad_norm": 17.270780563354492, "learning_rate": 3.36321270626278e-07, "loss": 1.2324, "step": 2830 }, { "epoch": 0.016881549773822897, "grad_norm": 13.458934783935547, "learning_rate": 3.375101050929669e-07, "loss": 1.151, "step": 2840 }, { "epoch": 0.016940991850491288, "grad_norm": 17.17865562438965, "learning_rate": 3.3869893955965574e-07, "loss": 1.1137, "step": 2850 }, { "epoch": 0.017000433927159678, "grad_norm": 15.50258731842041, "learning_rate": 3.398877740263446e-07, "loss": 1.1395, "step": 2860 }, { "epoch": 0.01705987600382807, "grad_norm": 15.353231430053711, "learning_rate": 3.4107660849303343e-07, "loss": 1.1996, "step": 2870 }, { "epoch": 0.01711931808049646, "grad_norm": 16.51226806640625, "learning_rate": 3.422654429597223e-07, "loss": 1.0514, "step": 2880 }, { "epoch": 0.017178760157164852, "grad_norm": 15.87351131439209, "learning_rate": 3.434542774264112e-07, "loss": 1.1494, "step": 2890 }, { "epoch": 0.017238202233833242, "grad_norm": 16.165164947509766, "learning_rate": 3.4464311189310006e-07, "loss": 1.1132, "step": 2900 }, { "epoch": 0.017297644310501632, "grad_norm": 19.047008514404297, "learning_rate": 3.458319463597889e-07, "loss": 1.1432, "step": 2910 }, { "epoch": 0.017357086387170022, "grad_norm": 13.411001205444336, "learning_rate": 3.4702078082647775e-07, "loss": 1.1253, "step": 2920 }, { "epoch": 0.017416528463838413, "grad_norm": 16.846309661865234, "learning_rate": 3.482096152931666e-07, "loss": 1.1122, "step": 2930 }, { "epoch": 0.017475970540506803, "grad_norm": 13.708964347839355, "learning_rate": 3.493984497598555e-07, "loss": 1.143, "step": 2940 }, { "epoch": 0.017535412617175193, "grad_norm": 15.229162216186523, "learning_rate": 3.505872842265443e-07, "loss": 1.1557, "step": 2950 }, { "epoch": 0.017594854693843583, "grad_norm": 14.997661590576172, "learning_rate": 3.5177611869323314e-07, "loss": 1.1054, "step": 2960 }, { "epoch": 0.017654296770511974, "grad_norm": 17.326072692871094, "learning_rate": 3.5296495315992207e-07, "loss": 1.1315, "step": 2970 }, { "epoch": 0.017713738847180364, "grad_norm": 17.473464965820312, "learning_rate": 3.541537876266109e-07, "loss": 1.1628, "step": 2980 }, { "epoch": 0.017773180923848754, "grad_norm": 18.656997680664062, "learning_rate": 3.5534262209329977e-07, "loss": 1.1863, "step": 2990 }, { "epoch": 0.017832623000517148, "grad_norm": 14.14770221710205, "learning_rate": 3.565314565599886e-07, "loss": 1.0918, "step": 3000 }, { "epoch": 0.017892065077185538, "grad_norm": 16.580535888671875, "learning_rate": 3.577202910266775e-07, "loss": 1.1217, "step": 3010 }, { "epoch": 0.017951507153853928, "grad_norm": 13.98845100402832, "learning_rate": 3.5890912549336634e-07, "loss": 1.0636, "step": 3020 }, { "epoch": 0.01801094923052232, "grad_norm": 15.963601112365723, "learning_rate": 3.600979599600552e-07, "loss": 1.1786, "step": 3030 }, { "epoch": 0.01807039130719071, "grad_norm": 19.178691864013672, "learning_rate": 3.6128679442674403e-07, "loss": 1.1668, "step": 3040 }, { "epoch": 0.0181298333838591, "grad_norm": 20.065092086791992, "learning_rate": 3.6247562889343296e-07, "loss": 1.1213, "step": 3050 }, { "epoch": 0.01818927546052749, "grad_norm": 16.63050079345703, "learning_rate": 3.636644633601218e-07, "loss": 1.1284, "step": 3060 }, { "epoch": 0.01824871753719588, "grad_norm": 16.74932098388672, "learning_rate": 3.6485329782681065e-07, "loss": 1.1447, "step": 3070 }, { "epoch": 0.01830815961386427, "grad_norm": 15.900634765625, "learning_rate": 3.660421322934995e-07, "loss": 1.1919, "step": 3080 }, { "epoch": 0.01836760169053266, "grad_norm": 20.256481170654297, "learning_rate": 3.672309667601883e-07, "loss": 1.1163, "step": 3090 }, { "epoch": 0.01842704376720105, "grad_norm": 13.858315467834473, "learning_rate": 3.684198012268772e-07, "loss": 1.0902, "step": 3100 }, { "epoch": 0.01848648584386944, "grad_norm": 18.80283546447754, "learning_rate": 3.6960863569356605e-07, "loss": 1.0696, "step": 3110 }, { "epoch": 0.01854592792053783, "grad_norm": 14.932467460632324, "learning_rate": 3.707974701602549e-07, "loss": 1.106, "step": 3120 }, { "epoch": 0.018605369997206224, "grad_norm": 13.79568862915039, "learning_rate": 3.7198630462694374e-07, "loss": 1.145, "step": 3130 }, { "epoch": 0.018664812073874614, "grad_norm": 17.25339126586914, "learning_rate": 3.7317513909363267e-07, "loss": 1.1096, "step": 3140 }, { "epoch": 0.018724254150543004, "grad_norm": 18.150419235229492, "learning_rate": 3.743639735603215e-07, "loss": 1.0259, "step": 3150 }, { "epoch": 0.018783696227211395, "grad_norm": 15.939449310302734, "learning_rate": 3.7555280802701036e-07, "loss": 1.1053, "step": 3160 }, { "epoch": 0.018843138303879785, "grad_norm": 13.929422378540039, "learning_rate": 3.767416424936992e-07, "loss": 1.0992, "step": 3170 }, { "epoch": 0.018902580380548175, "grad_norm": 15.322072982788086, "learning_rate": 3.779304769603881e-07, "loss": 1.1238, "step": 3180 }, { "epoch": 0.018962022457216565, "grad_norm": 18.588838577270508, "learning_rate": 3.7911931142707694e-07, "loss": 1.1541, "step": 3190 }, { "epoch": 0.019021464533884955, "grad_norm": 18.454280853271484, "learning_rate": 3.803081458937658e-07, "loss": 1.0695, "step": 3200 }, { "epoch": 0.019080906610553346, "grad_norm": 15.66434097290039, "learning_rate": 3.8149698036045463e-07, "loss": 1.0614, "step": 3210 }, { "epoch": 0.019140348687221736, "grad_norm": 15.375593185424805, "learning_rate": 3.8268581482714345e-07, "loss": 1.1246, "step": 3220 }, { "epoch": 0.019199790763890126, "grad_norm": 19.950489044189453, "learning_rate": 3.838746492938324e-07, "loss": 1.128, "step": 3230 }, { "epoch": 0.019259232840558516, "grad_norm": 18.7246036529541, "learning_rate": 3.850634837605212e-07, "loss": 1.1603, "step": 3240 }, { "epoch": 0.01931867491722691, "grad_norm": 14.652915954589844, "learning_rate": 3.862523182272101e-07, "loss": 1.1596, "step": 3250 }, { "epoch": 0.0193781169938953, "grad_norm": 12.839068412780762, "learning_rate": 3.874411526938989e-07, "loss": 1.1441, "step": 3260 }, { "epoch": 0.01943755907056369, "grad_norm": 17.167499542236328, "learning_rate": 3.886299871605878e-07, "loss": 1.0899, "step": 3270 }, { "epoch": 0.01949700114723208, "grad_norm": 13.157768249511719, "learning_rate": 3.8981882162727665e-07, "loss": 1.1719, "step": 3280 }, { "epoch": 0.01955644322390047, "grad_norm": 18.250394821166992, "learning_rate": 3.910076560939655e-07, "loss": 1.1192, "step": 3290 }, { "epoch": 0.01961588530056886, "grad_norm": 17.296804428100586, "learning_rate": 3.9219649056065434e-07, "loss": 1.0941, "step": 3300 }, { "epoch": 0.01967532737723725, "grad_norm": 15.613707542419434, "learning_rate": 3.9338532502734327e-07, "loss": 1.0548, "step": 3310 }, { "epoch": 0.01973476945390564, "grad_norm": 15.203030586242676, "learning_rate": 3.945741594940321e-07, "loss": 1.0757, "step": 3320 }, { "epoch": 0.01979421153057403, "grad_norm": 16.86480712890625, "learning_rate": 3.9576299396072096e-07, "loss": 1.0906, "step": 3330 }, { "epoch": 0.019853653607242422, "grad_norm": 14.087571144104004, "learning_rate": 3.969518284274098e-07, "loss": 1.0862, "step": 3340 }, { "epoch": 0.019913095683910812, "grad_norm": 19.48655128479004, "learning_rate": 3.981406628940986e-07, "loss": 1.0779, "step": 3350 }, { "epoch": 0.019972537760579202, "grad_norm": 14.882169723510742, "learning_rate": 3.9932949736078753e-07, "loss": 1.0783, "step": 3360 }, { "epoch": 0.020031979837247593, "grad_norm": 20.731443405151367, "learning_rate": 4.0051833182747636e-07, "loss": 1.1389, "step": 3370 }, { "epoch": 0.020091421913915986, "grad_norm": 14.319005012512207, "learning_rate": 4.0170716629416523e-07, "loss": 1.1343, "step": 3380 }, { "epoch": 0.020150863990584376, "grad_norm": 14.113414764404297, "learning_rate": 4.0289600076085405e-07, "loss": 1.0273, "step": 3390 }, { "epoch": 0.020210306067252767, "grad_norm": 12.798348426818848, "learning_rate": 4.04084835227543e-07, "loss": 1.0703, "step": 3400 }, { "epoch": 0.020269748143921157, "grad_norm": 16.377426147460938, "learning_rate": 4.052736696942318e-07, "loss": 1.0165, "step": 3410 }, { "epoch": 0.020329190220589547, "grad_norm": 19.998058319091797, "learning_rate": 4.064625041609207e-07, "loss": 1.112, "step": 3420 }, { "epoch": 0.020388632297257937, "grad_norm": 16.568767547607422, "learning_rate": 4.076513386276095e-07, "loss": 1.0726, "step": 3430 }, { "epoch": 0.020448074373926328, "grad_norm": 17.237720489501953, "learning_rate": 4.088401730942984e-07, "loss": 1.0909, "step": 3440 }, { "epoch": 0.020507516450594718, "grad_norm": 17.469839096069336, "learning_rate": 4.1002900756098724e-07, "loss": 1.1609, "step": 3450 }, { "epoch": 0.020566958527263108, "grad_norm": 18.483156204223633, "learning_rate": 4.112178420276761e-07, "loss": 1.1076, "step": 3460 }, { "epoch": 0.020626400603931498, "grad_norm": 13.361639976501465, "learning_rate": 4.1240667649436494e-07, "loss": 1.0993, "step": 3470 }, { "epoch": 0.02068584268059989, "grad_norm": 14.394006729125977, "learning_rate": 4.1359551096105376e-07, "loss": 1.0891, "step": 3480 }, { "epoch": 0.02074528475726828, "grad_norm": 12.34019947052002, "learning_rate": 4.147843454277427e-07, "loss": 1.0152, "step": 3490 }, { "epoch": 0.02080472683393667, "grad_norm": 15.676482200622559, "learning_rate": 4.159731798944315e-07, "loss": 1.0878, "step": 3500 }, { "epoch": 0.020864168910605062, "grad_norm": 17.318195343017578, "learning_rate": 4.171620143611204e-07, "loss": 1.0907, "step": 3510 }, { "epoch": 0.020923610987273453, "grad_norm": 18.499187469482422, "learning_rate": 4.183508488278092e-07, "loss": 1.0025, "step": 3520 }, { "epoch": 0.020983053063941843, "grad_norm": 13.838471412658691, "learning_rate": 4.1953968329449813e-07, "loss": 1.1, "step": 3530 }, { "epoch": 0.021042495140610233, "grad_norm": 14.029010772705078, "learning_rate": 4.2072851776118696e-07, "loss": 1.0758, "step": 3540 }, { "epoch": 0.021101937217278623, "grad_norm": 17.345842361450195, "learning_rate": 4.2191735222787583e-07, "loss": 1.0662, "step": 3550 }, { "epoch": 0.021161379293947014, "grad_norm": 17.528535842895508, "learning_rate": 4.2310618669456465e-07, "loss": 1.1334, "step": 3560 }, { "epoch": 0.021220821370615404, "grad_norm": 16.125062942504883, "learning_rate": 4.242950211612536e-07, "loss": 1.1852, "step": 3570 }, { "epoch": 0.021280263447283794, "grad_norm": 15.201292991638184, "learning_rate": 4.254838556279424e-07, "loss": 1.0666, "step": 3580 }, { "epoch": 0.021339705523952184, "grad_norm": 14.299886703491211, "learning_rate": 4.266726900946313e-07, "loss": 1.0811, "step": 3590 }, { "epoch": 0.021399147600620574, "grad_norm": 16.652599334716797, "learning_rate": 4.278615245613201e-07, "loss": 1.0826, "step": 3600 }, { "epoch": 0.021458589677288965, "grad_norm": 12.66284465789795, "learning_rate": 4.290503590280089e-07, "loss": 1.0105, "step": 3610 }, { "epoch": 0.021518031753957355, "grad_norm": 15.197101593017578, "learning_rate": 4.3023919349469784e-07, "loss": 1.1305, "step": 3620 }, { "epoch": 0.021577473830625745, "grad_norm": 15.091727256774902, "learning_rate": 4.3142802796138667e-07, "loss": 1.0407, "step": 3630 }, { "epoch": 0.02163691590729414, "grad_norm": 16.9069881439209, "learning_rate": 4.3261686242807554e-07, "loss": 1.0576, "step": 3640 }, { "epoch": 0.02169635798396253, "grad_norm": 23.517000198364258, "learning_rate": 4.3380569689476436e-07, "loss": 1.0755, "step": 3650 }, { "epoch": 0.02175580006063092, "grad_norm": 19.25669288635254, "learning_rate": 4.349945313614533e-07, "loss": 1.0394, "step": 3660 }, { "epoch": 0.02181524213729931, "grad_norm": 16.41619873046875, "learning_rate": 4.361833658281421e-07, "loss": 1.0952, "step": 3670 }, { "epoch": 0.0218746842139677, "grad_norm": 14.691576957702637, "learning_rate": 4.37372200294831e-07, "loss": 1.1584, "step": 3680 }, { "epoch": 0.02193412629063609, "grad_norm": 15.432097434997559, "learning_rate": 4.385610347615198e-07, "loss": 1.0191, "step": 3690 }, { "epoch": 0.02199356836730448, "grad_norm": 15.87136173248291, "learning_rate": 4.3974986922820873e-07, "loss": 0.9969, "step": 3700 }, { "epoch": 0.02205301044397287, "grad_norm": 17.128416061401367, "learning_rate": 4.4093870369489755e-07, "loss": 1.1561, "step": 3710 }, { "epoch": 0.02211245252064126, "grad_norm": 19.178306579589844, "learning_rate": 4.4212753816158643e-07, "loss": 1.0907, "step": 3720 }, { "epoch": 0.02217189459730965, "grad_norm": 18.638185501098633, "learning_rate": 4.4331637262827525e-07, "loss": 1.0371, "step": 3730 }, { "epoch": 0.02223133667397804, "grad_norm": 16.498254776000977, "learning_rate": 4.445052070949641e-07, "loss": 1.0648, "step": 3740 }, { "epoch": 0.02229077875064643, "grad_norm": 12.643105506896973, "learning_rate": 4.45694041561653e-07, "loss": 1.0716, "step": 3750 }, { "epoch": 0.022350220827314825, "grad_norm": 17.74782371520996, "learning_rate": 4.468828760283418e-07, "loss": 1.0312, "step": 3760 }, { "epoch": 0.022409662903983215, "grad_norm": 18.565458297729492, "learning_rate": 4.480717104950307e-07, "loss": 1.0108, "step": 3770 }, { "epoch": 0.022469104980651605, "grad_norm": 16.94544792175293, "learning_rate": 4.4926054496171957e-07, "loss": 1.1317, "step": 3780 }, { "epoch": 0.022528547057319995, "grad_norm": 16.08000946044922, "learning_rate": 4.5044937942840844e-07, "loss": 1.038, "step": 3790 }, { "epoch": 0.022587989133988386, "grad_norm": 14.209247589111328, "learning_rate": 4.5163821389509727e-07, "loss": 1.0547, "step": 3800 }, { "epoch": 0.022647431210656776, "grad_norm": 14.87589168548584, "learning_rate": 4.5282704836178614e-07, "loss": 1.0641, "step": 3810 }, { "epoch": 0.022706873287325166, "grad_norm": 17.428749084472656, "learning_rate": 4.54015882828475e-07, "loss": 1.0256, "step": 3820 }, { "epoch": 0.022766315363993556, "grad_norm": 17.383028030395508, "learning_rate": 4.552047172951639e-07, "loss": 1.0182, "step": 3830 }, { "epoch": 0.022825757440661947, "grad_norm": 12.612896919250488, "learning_rate": 4.563935517618527e-07, "loss": 1.0702, "step": 3840 }, { "epoch": 0.022885199517330337, "grad_norm": 19.30036163330078, "learning_rate": 4.575823862285416e-07, "loss": 1.0631, "step": 3850 }, { "epoch": 0.022944641593998727, "grad_norm": 21.44646644592285, "learning_rate": 4.5877122069523046e-07, "loss": 1.036, "step": 3860 }, { "epoch": 0.023004083670667117, "grad_norm": 21.78565788269043, "learning_rate": 4.599600551619193e-07, "loss": 1.0509, "step": 3870 }, { "epoch": 0.023063525747335507, "grad_norm": 19.198091506958008, "learning_rate": 4.6114888962860815e-07, "loss": 1.0813, "step": 3880 }, { "epoch": 0.0231229678240039, "grad_norm": 17.678991317749023, "learning_rate": 4.62337724095297e-07, "loss": 1.0177, "step": 3890 }, { "epoch": 0.02318240990067229, "grad_norm": 18.339202880859375, "learning_rate": 4.6352655856198585e-07, "loss": 1.0982, "step": 3900 }, { "epoch": 0.02324185197734068, "grad_norm": 17.258346557617188, "learning_rate": 4.647153930286747e-07, "loss": 1.1014, "step": 3910 }, { "epoch": 0.02330129405400907, "grad_norm": 15.711326599121094, "learning_rate": 4.659042274953636e-07, "loss": 1.0175, "step": 3920 }, { "epoch": 0.023360736130677462, "grad_norm": 14.054784774780273, "learning_rate": 4.670930619620524e-07, "loss": 1.1407, "step": 3930 }, { "epoch": 0.023420178207345852, "grad_norm": 19.53343963623047, "learning_rate": 4.682818964287413e-07, "loss": 1.0579, "step": 3940 }, { "epoch": 0.023479620284014242, "grad_norm": 15.913159370422363, "learning_rate": 4.6947073089543017e-07, "loss": 1.0691, "step": 3950 }, { "epoch": 0.023539062360682633, "grad_norm": 16.599584579467773, "learning_rate": 4.7065956536211904e-07, "loss": 1.0254, "step": 3960 }, { "epoch": 0.023598504437351023, "grad_norm": 13.808609962463379, "learning_rate": 4.7184839982880786e-07, "loss": 1.0512, "step": 3970 }, { "epoch": 0.023657946514019413, "grad_norm": 12.595415115356445, "learning_rate": 4.7303723429549674e-07, "loss": 1.0417, "step": 3980 }, { "epoch": 0.023717388590687803, "grad_norm": 14.716597557067871, "learning_rate": 4.742260687621856e-07, "loss": 1.0809, "step": 3990 }, { "epoch": 0.023776830667356193, "grad_norm": 16.54854965209961, "learning_rate": 4.7541490322887443e-07, "loss": 0.9989, "step": 4000 }, { "epoch": 0.023836272744024584, "grad_norm": 15.478425979614258, "learning_rate": 4.766037376955633e-07, "loss": 1.0354, "step": 4010 }, { "epoch": 0.023895714820692977, "grad_norm": 17.19384002685547, "learning_rate": 4.777925721622522e-07, "loss": 0.9999, "step": 4020 }, { "epoch": 0.023955156897361368, "grad_norm": 15.038084030151367, "learning_rate": 4.78981406628941e-07, "loss": 1.0606, "step": 4030 }, { "epoch": 0.024014598974029758, "grad_norm": 14.240291595458984, "learning_rate": 4.801702410956298e-07, "loss": 0.9505, "step": 4040 }, { "epoch": 0.024074041050698148, "grad_norm": 18.55312728881836, "learning_rate": 4.813590755623188e-07, "loss": 1.0662, "step": 4050 }, { "epoch": 0.024133483127366538, "grad_norm": 19.355388641357422, "learning_rate": 4.825479100290076e-07, "loss": 1.0946, "step": 4060 }, { "epoch": 0.02419292520403493, "grad_norm": 16.140396118164062, "learning_rate": 4.837367444956965e-07, "loss": 0.9551, "step": 4070 }, { "epoch": 0.02425236728070332, "grad_norm": 16.497087478637695, "learning_rate": 4.849255789623853e-07, "loss": 1.0807, "step": 4080 }, { "epoch": 0.02431180935737171, "grad_norm": 17.833032608032227, "learning_rate": 4.861144134290743e-07, "loss": 1.081, "step": 4090 }, { "epoch": 0.0243712514340401, "grad_norm": 17.10344886779785, "learning_rate": 4.873032478957631e-07, "loss": 1.0132, "step": 4100 }, { "epoch": 0.02443069351070849, "grad_norm": 15.56428337097168, "learning_rate": 4.884920823624519e-07, "loss": 1.0075, "step": 4110 }, { "epoch": 0.02449013558737688, "grad_norm": 19.64569091796875, "learning_rate": 4.896809168291407e-07, "loss": 1.0394, "step": 4120 }, { "epoch": 0.02454957766404527, "grad_norm": 15.346323013305664, "learning_rate": 4.908697512958295e-07, "loss": 0.9567, "step": 4130 }, { "epoch": 0.02460901974071366, "grad_norm": 14.529317855834961, "learning_rate": 4.920585857625185e-07, "loss": 1.0227, "step": 4140 }, { "epoch": 0.024668461817382054, "grad_norm": 16.056283950805664, "learning_rate": 4.932474202292073e-07, "loss": 1.043, "step": 4150 }, { "epoch": 0.024727903894050444, "grad_norm": 16.101961135864258, "learning_rate": 4.944362546958962e-07, "loss": 1.0148, "step": 4160 }, { "epoch": 0.024787345970718834, "grad_norm": 20.18683624267578, "learning_rate": 4.95625089162585e-07, "loss": 1.0584, "step": 4170 }, { "epoch": 0.024846788047387224, "grad_norm": 11.277809143066406, "learning_rate": 4.96813923629274e-07, "loss": 1.0259, "step": 4180 }, { "epoch": 0.024906230124055614, "grad_norm": 17.541431427001953, "learning_rate": 4.980027580959628e-07, "loss": 1.024, "step": 4190 }, { "epoch": 0.024965672200724005, "grad_norm": 15.671330451965332, "learning_rate": 4.991915925626516e-07, "loss": 1.0763, "step": 4200 }, { "epoch": 0.025025114277392395, "grad_norm": 15.538743019104004, "learning_rate": 5.003804270293404e-07, "loss": 1.0222, "step": 4210 }, { "epoch": 0.025084556354060785, "grad_norm": 16.262495040893555, "learning_rate": 5.015692614960294e-07, "loss": 1.0219, "step": 4220 }, { "epoch": 0.025143998430729175, "grad_norm": 15.264937400817871, "learning_rate": 5.027580959627182e-07, "loss": 0.9593, "step": 4230 }, { "epoch": 0.025203440507397566, "grad_norm": 12.713869094848633, "learning_rate": 5.039469304294071e-07, "loss": 1.0147, "step": 4240 }, { "epoch": 0.025262882584065956, "grad_norm": 17.377229690551758, "learning_rate": 5.051357648960959e-07, "loss": 1.0384, "step": 4250 }, { "epoch": 0.025322324660734346, "grad_norm": 13.967991828918457, "learning_rate": 5.063245993627847e-07, "loss": 0.9895, "step": 4260 }, { "epoch": 0.02538176673740274, "grad_norm": 23.24956703186035, "learning_rate": 5.075134338294737e-07, "loss": 1.0544, "step": 4270 }, { "epoch": 0.02544120881407113, "grad_norm": 15.662755966186523, "learning_rate": 5.087022682961625e-07, "loss": 1.0588, "step": 4280 }, { "epoch": 0.02550065089073952, "grad_norm": 15.36386775970459, "learning_rate": 5.098911027628513e-07, "loss": 1.0375, "step": 4290 }, { "epoch": 0.02556009296740791, "grad_norm": 15.752704620361328, "learning_rate": 5.110799372295401e-07, "loss": 1.0161, "step": 4300 }, { "epoch": 0.0256195350440763, "grad_norm": 13.965620040893555, "learning_rate": 5.122687716962291e-07, "loss": 1.036, "step": 4310 }, { "epoch": 0.02567897712074469, "grad_norm": 14.251752853393555, "learning_rate": 5.134576061629179e-07, "loss": 1.0472, "step": 4320 }, { "epoch": 0.02573841919741308, "grad_norm": 17.911460876464844, "learning_rate": 5.146464406296068e-07, "loss": 1.0404, "step": 4330 }, { "epoch": 0.02579786127408147, "grad_norm": 15.714332580566406, "learning_rate": 5.158352750962956e-07, "loss": 0.9688, "step": 4340 }, { "epoch": 0.02585730335074986, "grad_norm": 16.08953857421875, "learning_rate": 5.170241095629846e-07, "loss": 1.0491, "step": 4350 }, { "epoch": 0.02591674542741825, "grad_norm": 13.73912525177002, "learning_rate": 5.182129440296734e-07, "loss": 1.0315, "step": 4360 }, { "epoch": 0.025976187504086642, "grad_norm": 15.790587425231934, "learning_rate": 5.194017784963622e-07, "loss": 1.0441, "step": 4370 }, { "epoch": 0.026035629580755032, "grad_norm": 15.382577896118164, "learning_rate": 5.20590612963051e-07, "loss": 0.991, "step": 4380 }, { "epoch": 0.026095071657423422, "grad_norm": 18.545974731445312, "learning_rate": 5.2177944742974e-07, "loss": 1.1049, "step": 4390 }, { "epoch": 0.026154513734091816, "grad_norm": 18.074983596801758, "learning_rate": 5.229682818964288e-07, "loss": 1.025, "step": 4400 }, { "epoch": 0.026213955810760206, "grad_norm": 19.221405029296875, "learning_rate": 5.241571163631176e-07, "loss": 1.0297, "step": 4410 }, { "epoch": 0.026273397887428596, "grad_norm": 15.153637886047363, "learning_rate": 5.253459508298065e-07, "loss": 0.963, "step": 4420 }, { "epoch": 0.026332839964096987, "grad_norm": 13.76234245300293, "learning_rate": 5.265347852964953e-07, "loss": 1.0782, "step": 4430 }, { "epoch": 0.026392282040765377, "grad_norm": 23.675128936767578, "learning_rate": 5.277236197631843e-07, "loss": 0.9613, "step": 4440 }, { "epoch": 0.026451724117433767, "grad_norm": 15.363752365112305, "learning_rate": 5.289124542298731e-07, "loss": 1.0307, "step": 4450 }, { "epoch": 0.026511166194102157, "grad_norm": 15.158602714538574, "learning_rate": 5.301012886965619e-07, "loss": 1.0082, "step": 4460 }, { "epoch": 0.026570608270770547, "grad_norm": 14.502652168273926, "learning_rate": 5.312901231632507e-07, "loss": 0.9933, "step": 4470 }, { "epoch": 0.026630050347438938, "grad_norm": 13.195229530334473, "learning_rate": 5.324789576299397e-07, "loss": 1.0256, "step": 4480 }, { "epoch": 0.026689492424107328, "grad_norm": 13.603482246398926, "learning_rate": 5.336677920966285e-07, "loss": 0.9611, "step": 4490 }, { "epoch": 0.026748934500775718, "grad_norm": 15.116276741027832, "learning_rate": 5.348566265633174e-07, "loss": 1.0036, "step": 4500 }, { "epoch": 0.026808376577444108, "grad_norm": 15.196722984313965, "learning_rate": 5.360454610300062e-07, "loss": 1.0353, "step": 4510 }, { "epoch": 0.0268678186541125, "grad_norm": 13.565038681030273, "learning_rate": 5.372342954966952e-07, "loss": 0.9609, "step": 4520 }, { "epoch": 0.026927260730780892, "grad_norm": 19.074501037597656, "learning_rate": 5.38423129963384e-07, "loss": 1.0056, "step": 4530 }, { "epoch": 0.026986702807449282, "grad_norm": 15.133832931518555, "learning_rate": 5.396119644300728e-07, "loss": 0.9921, "step": 4540 }, { "epoch": 0.027046144884117673, "grad_norm": 13.125186920166016, "learning_rate": 5.408007988967616e-07, "loss": 1.0055, "step": 4550 }, { "epoch": 0.027105586960786063, "grad_norm": 16.279077529907227, "learning_rate": 5.419896333634504e-07, "loss": 0.9799, "step": 4560 }, { "epoch": 0.027165029037454453, "grad_norm": 15.17044734954834, "learning_rate": 5.431784678301394e-07, "loss": 1.0656, "step": 4570 }, { "epoch": 0.027224471114122843, "grad_norm": 15.030183792114258, "learning_rate": 5.443673022968282e-07, "loss": 0.9983, "step": 4580 }, { "epoch": 0.027283913190791233, "grad_norm": 13.367537498474121, "learning_rate": 5.455561367635171e-07, "loss": 1.0141, "step": 4590 }, { "epoch": 0.027343355267459624, "grad_norm": 17.192665100097656, "learning_rate": 5.467449712302059e-07, "loss": 1.0311, "step": 4600 }, { "epoch": 0.027402797344128014, "grad_norm": 15.1950044631958, "learning_rate": 5.479338056968949e-07, "loss": 1.0863, "step": 4610 }, { "epoch": 0.027462239420796404, "grad_norm": 15.847233772277832, "learning_rate": 5.491226401635837e-07, "loss": 1.012, "step": 4620 }, { "epoch": 0.027521681497464794, "grad_norm": 19.34232521057129, "learning_rate": 5.503114746302725e-07, "loss": 0.9813, "step": 4630 }, { "epoch": 0.027581123574133184, "grad_norm": 15.357650756835938, "learning_rate": 5.515003090969613e-07, "loss": 0.9872, "step": 4640 }, { "epoch": 0.027640565650801575, "grad_norm": 11.738371849060059, "learning_rate": 5.526891435636503e-07, "loss": 0.9754, "step": 4650 }, { "epoch": 0.02770000772746997, "grad_norm": 18.53949546813965, "learning_rate": 5.538779780303391e-07, "loss": 1.0422, "step": 4660 }, { "epoch": 0.02775944980413836, "grad_norm": 14.080986976623535, "learning_rate": 5.550668124970279e-07, "loss": 1.0397, "step": 4670 }, { "epoch": 0.02781889188080675, "grad_norm": 17.322731018066406, "learning_rate": 5.562556469637168e-07, "loss": 1.0439, "step": 4680 }, { "epoch": 0.02787833395747514, "grad_norm": 14.949540138244629, "learning_rate": 5.574444814304057e-07, "loss": 1.0095, "step": 4690 }, { "epoch": 0.02793777603414353, "grad_norm": 13.398080825805664, "learning_rate": 5.586333158970946e-07, "loss": 1.0022, "step": 4700 }, { "epoch": 0.02799721811081192, "grad_norm": 12.344393730163574, "learning_rate": 5.598221503637834e-07, "loss": 0.9492, "step": 4710 }, { "epoch": 0.02805666018748031, "grad_norm": 14.002189636230469, "learning_rate": 5.610109848304722e-07, "loss": 0.9149, "step": 4720 }, { "epoch": 0.0281161022641487, "grad_norm": 17.124242782592773, "learning_rate": 5.62199819297161e-07, "loss": 1.0884, "step": 4730 }, { "epoch": 0.02817554434081709, "grad_norm": 18.075469970703125, "learning_rate": 5.6338865376385e-07, "loss": 0.9299, "step": 4740 }, { "epoch": 0.02823498641748548, "grad_norm": 17.288537979125977, "learning_rate": 5.645774882305388e-07, "loss": 1.0095, "step": 4750 }, { "epoch": 0.02829442849415387, "grad_norm": 12.62472915649414, "learning_rate": 5.657663226972277e-07, "loss": 0.9425, "step": 4760 }, { "epoch": 0.02835387057082226, "grad_norm": 16.05240821838379, "learning_rate": 5.669551571639165e-07, "loss": 0.9652, "step": 4770 }, { "epoch": 0.028413312647490654, "grad_norm": 12.528807640075684, "learning_rate": 5.681439916306055e-07, "loss": 0.9517, "step": 4780 }, { "epoch": 0.028472754724159045, "grad_norm": 15.430176734924316, "learning_rate": 5.693328260972943e-07, "loss": 1.0245, "step": 4790 }, { "epoch": 0.028532196800827435, "grad_norm": 16.071590423583984, "learning_rate": 5.705216605639831e-07, "loss": 0.9649, "step": 4800 }, { "epoch": 0.028591638877495825, "grad_norm": 14.675535202026367, "learning_rate": 5.717104950306719e-07, "loss": 0.9383, "step": 4810 }, { "epoch": 0.028651080954164215, "grad_norm": 14.75767707824707, "learning_rate": 5.728993294973609e-07, "loss": 0.974, "step": 4820 }, { "epoch": 0.028710523030832606, "grad_norm": 15.366301536560059, "learning_rate": 5.740881639640497e-07, "loss": 0.9542, "step": 4830 }, { "epoch": 0.028769965107500996, "grad_norm": 16.212451934814453, "learning_rate": 5.752769984307385e-07, "loss": 0.9341, "step": 4840 }, { "epoch": 0.028829407184169386, "grad_norm": 20.77583122253418, "learning_rate": 5.764658328974274e-07, "loss": 0.9828, "step": 4850 }, { "epoch": 0.028888849260837776, "grad_norm": 14.808025360107422, "learning_rate": 5.776546673641163e-07, "loss": 1.0051, "step": 4860 }, { "epoch": 0.028948291337506166, "grad_norm": 10.841477394104004, "learning_rate": 5.788435018308052e-07, "loss": 0.9671, "step": 4870 }, { "epoch": 0.029007733414174557, "grad_norm": 13.713773727416992, "learning_rate": 5.80032336297494e-07, "loss": 0.9246, "step": 4880 }, { "epoch": 0.029067175490842947, "grad_norm": 15.403968811035156, "learning_rate": 5.812211707641828e-07, "loss": 1.1194, "step": 4890 }, { "epoch": 0.029126617567511337, "grad_norm": 13.294910430908203, "learning_rate": 5.824100052308716e-07, "loss": 0.9686, "step": 4900 }, { "epoch": 0.02918605964417973, "grad_norm": 14.457573890686035, "learning_rate": 5.835988396975606e-07, "loss": 0.966, "step": 4910 }, { "epoch": 0.02924550172084812, "grad_norm": 15.434859275817871, "learning_rate": 5.847876741642494e-07, "loss": 0.8985, "step": 4920 }, { "epoch": 0.02930494379751651, "grad_norm": 13.227372169494629, "learning_rate": 5.859765086309382e-07, "loss": 0.9809, "step": 4930 }, { "epoch": 0.0293643858741849, "grad_norm": 17.982282638549805, "learning_rate": 5.871653430976271e-07, "loss": 0.9914, "step": 4940 }, { "epoch": 0.02942382795085329, "grad_norm": 17.040367126464844, "learning_rate": 5.88354177564316e-07, "loss": 0.9509, "step": 4950 }, { "epoch": 0.029483270027521682, "grad_norm": 12.190671920776367, "learning_rate": 5.895430120310049e-07, "loss": 0.9101, "step": 4960 }, { "epoch": 0.029542712104190072, "grad_norm": 13.171815872192383, "learning_rate": 5.907318464976937e-07, "loss": 0.9555, "step": 4970 }, { "epoch": 0.029602154180858462, "grad_norm": 14.861910820007324, "learning_rate": 5.919206809643825e-07, "loss": 1.0697, "step": 4980 }, { "epoch": 0.029661596257526852, "grad_norm": 15.059122085571289, "learning_rate": 5.931095154310715e-07, "loss": 1.0281, "step": 4990 }, { "epoch": 0.029721038334195243, "grad_norm": 12.951057434082031, "learning_rate": 5.942983498977603e-07, "loss": 0.9439, "step": 5000 }, { "epoch": 0.029780480410863633, "grad_norm": 15.364362716674805, "learning_rate": 5.954871843644491e-07, "loss": 0.9216, "step": 5010 }, { "epoch": 0.029839922487532023, "grad_norm": 14.448518753051758, "learning_rate": 5.96676018831138e-07, "loss": 0.9193, "step": 5020 }, { "epoch": 0.029899364564200413, "grad_norm": 13.835928916931152, "learning_rate": 5.978648532978269e-07, "loss": 0.8921, "step": 5030 }, { "epoch": 0.029958806640868807, "grad_norm": 14.009196281433105, "learning_rate": 5.990536877645158e-07, "loss": 1.0104, "step": 5040 }, { "epoch": 0.030018248717537197, "grad_norm": 15.180490493774414, "learning_rate": 6.002425222312046e-07, "loss": 0.9749, "step": 5050 }, { "epoch": 0.030077690794205587, "grad_norm": 18.035354614257812, "learning_rate": 6.014313566978934e-07, "loss": 1.0009, "step": 5060 }, { "epoch": 0.030137132870873978, "grad_norm": 13.34045696258545, "learning_rate": 6.026201911645823e-07, "loss": 0.9939, "step": 5070 }, { "epoch": 0.030196574947542368, "grad_norm": 12.880219459533691, "learning_rate": 6.038090256312712e-07, "loss": 0.908, "step": 5080 }, { "epoch": 0.030256017024210758, "grad_norm": 16.449710845947266, "learning_rate": 6.0499786009796e-07, "loss": 0.9724, "step": 5090 }, { "epoch": 0.030315459100879148, "grad_norm": 13.83980655670166, "learning_rate": 6.061866945646488e-07, "loss": 0.9902, "step": 5100 }, { "epoch": 0.03037490117754754, "grad_norm": 14.63952350616455, "learning_rate": 6.073755290313377e-07, "loss": 1.0231, "step": 5110 }, { "epoch": 0.03043434325421593, "grad_norm": 15.958183288574219, "learning_rate": 6.085643634980266e-07, "loss": 1.0326, "step": 5120 }, { "epoch": 0.03049378533088432, "grad_norm": 14.39486026763916, "learning_rate": 6.097531979647155e-07, "loss": 1.0151, "step": 5130 }, { "epoch": 0.03055322740755271, "grad_norm": 14.891345024108887, "learning_rate": 6.109420324314043e-07, "loss": 0.923, "step": 5140 }, { "epoch": 0.0306126694842211, "grad_norm": 12.085200309753418, "learning_rate": 6.121308668980932e-07, "loss": 0.9856, "step": 5150 }, { "epoch": 0.03067211156088949, "grad_norm": 18.597440719604492, "learning_rate": 6.133197013647821e-07, "loss": 0.8992, "step": 5160 }, { "epoch": 0.030731553637557883, "grad_norm": 15.44304370880127, "learning_rate": 6.145085358314709e-07, "loss": 1.0285, "step": 5170 }, { "epoch": 0.030790995714226273, "grad_norm": 17.039409637451172, "learning_rate": 6.156973702981597e-07, "loss": 1.0, "step": 5180 }, { "epoch": 0.030850437790894664, "grad_norm": 16.859392166137695, "learning_rate": 6.168862047648485e-07, "loss": 0.9705, "step": 5190 }, { "epoch": 0.030909879867563054, "grad_norm": 14.261958122253418, "learning_rate": 6.180750392315375e-07, "loss": 0.9381, "step": 5200 }, { "epoch": 0.030969321944231444, "grad_norm": 13.826448440551758, "learning_rate": 6.192638736982263e-07, "loss": 0.9487, "step": 5210 }, { "epoch": 0.031028764020899834, "grad_norm": 12.787317276000977, "learning_rate": 6.204527081649152e-07, "loss": 0.9752, "step": 5220 }, { "epoch": 0.031088206097568225, "grad_norm": 14.494080543518066, "learning_rate": 6.21641542631604e-07, "loss": 0.9915, "step": 5230 }, { "epoch": 0.031147648174236615, "grad_norm": 13.81155014038086, "learning_rate": 6.22830377098293e-07, "loss": 0.985, "step": 5240 }, { "epoch": 0.031207090250905005, "grad_norm": 10.74521255493164, "learning_rate": 6.240192115649818e-07, "loss": 0.9303, "step": 5250 }, { "epoch": 0.0312665323275734, "grad_norm": 14.668874740600586, "learning_rate": 6.252080460316706e-07, "loss": 0.8968, "step": 5260 }, { "epoch": 0.031325974404241785, "grad_norm": 16.678970336914062, "learning_rate": 6.263968804983594e-07, "loss": 0.9547, "step": 5270 }, { "epoch": 0.03138541648091018, "grad_norm": 13.289460182189941, "learning_rate": 6.275857149650482e-07, "loss": 0.9288, "step": 5280 }, { "epoch": 0.031444858557578566, "grad_norm": 17.149959564208984, "learning_rate": 6.287745494317373e-07, "loss": 0.9678, "step": 5290 }, { "epoch": 0.03150430063424696, "grad_norm": 12.400434494018555, "learning_rate": 6.299633838984261e-07, "loss": 0.93, "step": 5300 }, { "epoch": 0.031563742710915346, "grad_norm": 13.559633255004883, "learning_rate": 6.311522183651149e-07, "loss": 0.9443, "step": 5310 }, { "epoch": 0.03162318478758374, "grad_norm": 16.179424285888672, "learning_rate": 6.323410528318037e-07, "loss": 1.0381, "step": 5320 }, { "epoch": 0.03168262686425213, "grad_norm": 16.612855911254883, "learning_rate": 6.335298872984926e-07, "loss": 0.9637, "step": 5330 }, { "epoch": 0.03174206894092052, "grad_norm": 14.25296401977539, "learning_rate": 6.347187217651815e-07, "loss": 0.9574, "step": 5340 }, { "epoch": 0.03180151101758891, "grad_norm": 12.978344917297363, "learning_rate": 6.359075562318703e-07, "loss": 0.9341, "step": 5350 }, { "epoch": 0.0318609530942573, "grad_norm": 12.755537033081055, "learning_rate": 6.370963906985591e-07, "loss": 1.0133, "step": 5360 }, { "epoch": 0.031920395170925694, "grad_norm": 11.505270004272461, "learning_rate": 6.382852251652479e-07, "loss": 0.9739, "step": 5370 }, { "epoch": 0.03197983724759408, "grad_norm": 12.719076156616211, "learning_rate": 6.39474059631937e-07, "loss": 0.9565, "step": 5380 }, { "epoch": 0.032039279324262475, "grad_norm": 14.615232467651367, "learning_rate": 6.406628940986258e-07, "loss": 0.9622, "step": 5390 }, { "epoch": 0.03209872140093086, "grad_norm": 17.64462661743164, "learning_rate": 6.418517285653146e-07, "loss": 1.0063, "step": 5400 }, { "epoch": 0.032158163477599255, "grad_norm": 11.602812767028809, "learning_rate": 6.430405630320034e-07, "loss": 0.9616, "step": 5410 }, { "epoch": 0.03221760555426764, "grad_norm": 11.293414115905762, "learning_rate": 6.442293974986924e-07, "loss": 1.0059, "step": 5420 }, { "epoch": 0.032277047630936036, "grad_norm": 17.892004013061523, "learning_rate": 6.454182319653812e-07, "loss": 0.9336, "step": 5430 }, { "epoch": 0.03233648970760442, "grad_norm": 14.483888626098633, "learning_rate": 6.4660706643207e-07, "loss": 0.9493, "step": 5440 }, { "epoch": 0.032395931784272816, "grad_norm": 13.057292938232422, "learning_rate": 6.477959008987588e-07, "loss": 0.921, "step": 5450 }, { "epoch": 0.0324553738609412, "grad_norm": 13.965662002563477, "learning_rate": 6.489847353654477e-07, "loss": 0.8972, "step": 5460 }, { "epoch": 0.0325148159376096, "grad_norm": 15.197046279907227, "learning_rate": 6.501735698321367e-07, "loss": 0.9258, "step": 5470 }, { "epoch": 0.03257425801427799, "grad_norm": 19.671152114868164, "learning_rate": 6.513624042988255e-07, "loss": 1.0047, "step": 5480 }, { "epoch": 0.03263370009094638, "grad_norm": 13.909819602966309, "learning_rate": 6.525512387655143e-07, "loss": 0.9905, "step": 5490 }, { "epoch": 0.03269314216761477, "grad_norm": 13.052181243896484, "learning_rate": 6.537400732322032e-07, "loss": 0.9041, "step": 5500 }, { "epoch": 0.03275258424428316, "grad_norm": 15.208722114562988, "learning_rate": 6.549289076988921e-07, "loss": 0.9235, "step": 5510 }, { "epoch": 0.03281202632095155, "grad_norm": 12.037775993347168, "learning_rate": 6.561177421655809e-07, "loss": 0.9139, "step": 5520 }, { "epoch": 0.03287146839761994, "grad_norm": 14.324605941772461, "learning_rate": 6.573065766322697e-07, "loss": 0.9304, "step": 5530 }, { "epoch": 0.03293091047428833, "grad_norm": 15.419778823852539, "learning_rate": 6.584954110989585e-07, "loss": 0.9109, "step": 5540 }, { "epoch": 0.03299035255095672, "grad_norm": 11.112311363220215, "learning_rate": 6.596842455656476e-07, "loss": 0.9857, "step": 5550 }, { "epoch": 0.03304979462762511, "grad_norm": 15.295819282531738, "learning_rate": 6.608730800323364e-07, "loss": 0.9916, "step": 5560 }, { "epoch": 0.0331092367042935, "grad_norm": 14.571450233459473, "learning_rate": 6.620619144990252e-07, "loss": 0.9818, "step": 5570 }, { "epoch": 0.03316867878096189, "grad_norm": 13.920228958129883, "learning_rate": 6.63250748965714e-07, "loss": 0.8826, "step": 5580 }, { "epoch": 0.03322812085763028, "grad_norm": 15.65060043334961, "learning_rate": 6.644395834324029e-07, "loss": 0.952, "step": 5590 }, { "epoch": 0.03328756293429867, "grad_norm": 14.32390308380127, "learning_rate": 6.656284178990918e-07, "loss": 0.9653, "step": 5600 }, { "epoch": 0.03334700501096707, "grad_norm": 17.314455032348633, "learning_rate": 6.668172523657806e-07, "loss": 0.8721, "step": 5610 }, { "epoch": 0.03340644708763545, "grad_norm": 20.853870391845703, "learning_rate": 6.680060868324694e-07, "loss": 0.9681, "step": 5620 }, { "epoch": 0.03346588916430385, "grad_norm": 17.324487686157227, "learning_rate": 6.691949212991583e-07, "loss": 0.9571, "step": 5630 }, { "epoch": 0.033525331240972234, "grad_norm": 23.44059944152832, "learning_rate": 6.703837557658473e-07, "loss": 0.9195, "step": 5640 }, { "epoch": 0.03358477331764063, "grad_norm": 13.861607551574707, "learning_rate": 6.715725902325361e-07, "loss": 1.0241, "step": 5650 }, { "epoch": 0.033644215394309014, "grad_norm": 17.04478645324707, "learning_rate": 6.727614246992249e-07, "loss": 0.9401, "step": 5660 }, { "epoch": 0.03370365747097741, "grad_norm": 15.704061508178711, "learning_rate": 6.739502591659138e-07, "loss": 0.9891, "step": 5670 }, { "epoch": 0.033763099547645795, "grad_norm": 17.229122161865234, "learning_rate": 6.751390936326027e-07, "loss": 0.9583, "step": 5680 }, { "epoch": 0.03382254162431419, "grad_norm": 12.130043029785156, "learning_rate": 6.763279280992915e-07, "loss": 1.0442, "step": 5690 }, { "epoch": 0.033881983700982575, "grad_norm": 15.002455711364746, "learning_rate": 6.775167625659803e-07, "loss": 0.9388, "step": 5700 }, { "epoch": 0.03394142577765097, "grad_norm": 15.29825210571289, "learning_rate": 6.787055970326691e-07, "loss": 0.9265, "step": 5710 }, { "epoch": 0.034000867854319355, "grad_norm": 17.078813552856445, "learning_rate": 6.798944314993581e-07, "loss": 1.0001, "step": 5720 }, { "epoch": 0.03406030993098775, "grad_norm": 14.653853416442871, "learning_rate": 6.81083265966047e-07, "loss": 0.9538, "step": 5730 }, { "epoch": 0.03411975200765614, "grad_norm": 14.796028137207031, "learning_rate": 6.822721004327358e-07, "loss": 0.8501, "step": 5740 }, { "epoch": 0.03417919408432453, "grad_norm": 14.634885787963867, "learning_rate": 6.834609348994246e-07, "loss": 0.9281, "step": 5750 }, { "epoch": 0.03423863616099292, "grad_norm": 14.925270080566406, "learning_rate": 6.846497693661135e-07, "loss": 0.9766, "step": 5760 }, { "epoch": 0.03429807823766131, "grad_norm": 16.716379165649414, "learning_rate": 6.858386038328024e-07, "loss": 1.0227, "step": 5770 }, { "epoch": 0.034357520314329704, "grad_norm": 12.871150016784668, "learning_rate": 6.870274382994912e-07, "loss": 0.8995, "step": 5780 }, { "epoch": 0.03441696239099809, "grad_norm": 12.875082969665527, "learning_rate": 6.8821627276618e-07, "loss": 0.8851, "step": 5790 }, { "epoch": 0.034476404467666484, "grad_norm": 14.936026573181152, "learning_rate": 6.89405107232869e-07, "loss": 0.8741, "step": 5800 }, { "epoch": 0.03453584654433487, "grad_norm": 18.846952438354492, "learning_rate": 6.905939416995579e-07, "loss": 0.9643, "step": 5810 }, { "epoch": 0.034595288621003265, "grad_norm": 13.96923542022705, "learning_rate": 6.917827761662467e-07, "loss": 0.8814, "step": 5820 }, { "epoch": 0.03465473069767165, "grad_norm": 11.93293285369873, "learning_rate": 6.929716106329355e-07, "loss": 0.9279, "step": 5830 }, { "epoch": 0.034714172774340045, "grad_norm": 14.946527481079102, "learning_rate": 6.941604450996244e-07, "loss": 0.9402, "step": 5840 }, { "epoch": 0.03477361485100843, "grad_norm": 16.547863006591797, "learning_rate": 6.953492795663132e-07, "loss": 0.9079, "step": 5850 }, { "epoch": 0.034833056927676825, "grad_norm": 14.497818946838379, "learning_rate": 6.965381140330021e-07, "loss": 0.9688, "step": 5860 }, { "epoch": 0.03489249900434522, "grad_norm": 12.930692672729492, "learning_rate": 6.977269484996909e-07, "loss": 0.906, "step": 5870 }, { "epoch": 0.034951941081013606, "grad_norm": 11.867204666137695, "learning_rate": 6.989157829663797e-07, "loss": 0.9353, "step": 5880 }, { "epoch": 0.035011383157682, "grad_norm": 17.613521575927734, "learning_rate": 7.001046174330687e-07, "loss": 0.9293, "step": 5890 }, { "epoch": 0.035070825234350386, "grad_norm": 15.949312210083008, "learning_rate": 7.012934518997576e-07, "loss": 1.011, "step": 5900 }, { "epoch": 0.03513026731101878, "grad_norm": 14.969141006469727, "learning_rate": 7.024822863664464e-07, "loss": 0.9016, "step": 5910 }, { "epoch": 0.03518970938768717, "grad_norm": 15.594213485717773, "learning_rate": 7.036711208331352e-07, "loss": 0.9264, "step": 5920 }, { "epoch": 0.03524915146435556, "grad_norm": 13.83730697631836, "learning_rate": 7.048599552998241e-07, "loss": 0.9522, "step": 5930 }, { "epoch": 0.03530859354102395, "grad_norm": 14.452203750610352, "learning_rate": 7.06048789766513e-07, "loss": 0.9247, "step": 5940 }, { "epoch": 0.03536803561769234, "grad_norm": 12.365726470947266, "learning_rate": 7.072376242332018e-07, "loss": 0.9101, "step": 5950 }, { "epoch": 0.03542747769436073, "grad_norm": 16.839561462402344, "learning_rate": 7.084264586998906e-07, "loss": 0.9564, "step": 5960 }, { "epoch": 0.03548691977102912, "grad_norm": 11.216434478759766, "learning_rate": 7.096152931665796e-07, "loss": 0.9522, "step": 5970 }, { "epoch": 0.03554636184769751, "grad_norm": 12.834052085876465, "learning_rate": 7.108041276332684e-07, "loss": 0.8668, "step": 5980 }, { "epoch": 0.0356058039243659, "grad_norm": 15.482625961303711, "learning_rate": 7.119929620999573e-07, "loss": 0.9655, "step": 5990 }, { "epoch": 0.035665246001034295, "grad_norm": 14.60342788696289, "learning_rate": 7.131817965666461e-07, "loss": 0.8753, "step": 6000 }, { "epoch": 0.03572468807770268, "grad_norm": 13.865643501281738, "learning_rate": 7.14370631033335e-07, "loss": 0.915, "step": 6010 }, { "epoch": 0.035784130154371076, "grad_norm": 12.550415992736816, "learning_rate": 7.155594655000238e-07, "loss": 0.8571, "step": 6020 }, { "epoch": 0.03584357223103946, "grad_norm": 14.853391647338867, "learning_rate": 7.167482999667127e-07, "loss": 0.9673, "step": 6030 }, { "epoch": 0.035903014307707856, "grad_norm": 19.871845245361328, "learning_rate": 7.179371344334015e-07, "loss": 1.0115, "step": 6040 }, { "epoch": 0.03596245638437624, "grad_norm": 13.04587173461914, "learning_rate": 7.191259689000904e-07, "loss": 0.8729, "step": 6050 }, { "epoch": 0.03602189846104464, "grad_norm": 12.944914817810059, "learning_rate": 7.203148033667793e-07, "loss": 0.9032, "step": 6060 }, { "epoch": 0.03608134053771302, "grad_norm": 14.035593032836914, "learning_rate": 7.215036378334682e-07, "loss": 0.9054, "step": 6070 }, { "epoch": 0.03614078261438142, "grad_norm": 16.339481353759766, "learning_rate": 7.22692472300157e-07, "loss": 0.9285, "step": 6080 }, { "epoch": 0.036200224691049804, "grad_norm": 11.407753944396973, "learning_rate": 7.238813067668458e-07, "loss": 0.9764, "step": 6090 }, { "epoch": 0.0362596667677182, "grad_norm": 16.217784881591797, "learning_rate": 7.250701412335347e-07, "loss": 0.9717, "step": 6100 }, { "epoch": 0.036319108844386584, "grad_norm": 12.64461898803711, "learning_rate": 7.262589757002235e-07, "loss": 0.9404, "step": 6110 }, { "epoch": 0.03637855092105498, "grad_norm": 13.227155685424805, "learning_rate": 7.274478101669124e-07, "loss": 0.9678, "step": 6120 }, { "epoch": 0.03643799299772337, "grad_norm": 16.77825355529785, "learning_rate": 7.286366446336013e-07, "loss": 0.8798, "step": 6130 }, { "epoch": 0.03649743507439176, "grad_norm": 17.225448608398438, "learning_rate": 7.298254791002902e-07, "loss": 0.9601, "step": 6140 }, { "epoch": 0.03655687715106015, "grad_norm": 15.10741138458252, "learning_rate": 7.31014313566979e-07, "loss": 0.799, "step": 6150 }, { "epoch": 0.03661631922772854, "grad_norm": 12.35098934173584, "learning_rate": 7.322031480336679e-07, "loss": 0.8626, "step": 6160 }, { "epoch": 0.03667576130439693, "grad_norm": 14.757904052734375, "learning_rate": 7.333919825003567e-07, "loss": 0.957, "step": 6170 }, { "epoch": 0.03673520338106532, "grad_norm": 16.91635513305664, "learning_rate": 7.345808169670456e-07, "loss": 0.9998, "step": 6180 }, { "epoch": 0.03679464545773371, "grad_norm": 17.816911697387695, "learning_rate": 7.357696514337344e-07, "loss": 0.9143, "step": 6190 }, { "epoch": 0.0368540875344021, "grad_norm": 13.510675430297852, "learning_rate": 7.369584859004233e-07, "loss": 0.9372, "step": 6200 }, { "epoch": 0.03691352961107049, "grad_norm": 13.987162590026855, "learning_rate": 7.381473203671122e-07, "loss": 0.9746, "step": 6210 }, { "epoch": 0.03697297168773888, "grad_norm": 12.52872085571289, "learning_rate": 7.39336154833801e-07, "loss": 0.9087, "step": 6220 }, { "epoch": 0.037032413764407274, "grad_norm": 13.91893482208252, "learning_rate": 7.405249893004899e-07, "loss": 0.9279, "step": 6230 }, { "epoch": 0.03709185584107566, "grad_norm": 16.46114158630371, "learning_rate": 7.417138237671787e-07, "loss": 0.9303, "step": 6240 }, { "epoch": 0.037151297917744054, "grad_norm": 13.512332916259766, "learning_rate": 7.429026582338676e-07, "loss": 0.9066, "step": 6250 }, { "epoch": 0.03721073999441245, "grad_norm": 12.063403129577637, "learning_rate": 7.440914927005564e-07, "loss": 0.9332, "step": 6260 }, { "epoch": 0.037270182071080835, "grad_norm": 14.589612007141113, "learning_rate": 7.452803271672453e-07, "loss": 0.9574, "step": 6270 }, { "epoch": 0.03732962414774923, "grad_norm": 15.76040267944336, "learning_rate": 7.464691616339341e-07, "loss": 0.9064, "step": 6280 }, { "epoch": 0.037389066224417615, "grad_norm": 12.918754577636719, "learning_rate": 7.47657996100623e-07, "loss": 0.9105, "step": 6290 }, { "epoch": 0.03744850830108601, "grad_norm": 14.354513168334961, "learning_rate": 7.488468305673119e-07, "loss": 0.8836, "step": 6300 }, { "epoch": 0.037507950377754395, "grad_norm": 14.515230178833008, "learning_rate": 7.500356650340008e-07, "loss": 0.9269, "step": 6310 }, { "epoch": 0.03756739245442279, "grad_norm": 10.69520378112793, "learning_rate": 7.512244995006896e-07, "loss": 0.9087, "step": 6320 }, { "epoch": 0.037626834531091176, "grad_norm": 13.936694145202637, "learning_rate": 7.524133339673785e-07, "loss": 0.9078, "step": 6330 }, { "epoch": 0.03768627660775957, "grad_norm": 12.774474143981934, "learning_rate": 7.536021684340673e-07, "loss": 0.844, "step": 6340 }, { "epoch": 0.037745718684427956, "grad_norm": 13.68652057647705, "learning_rate": 7.547910029007562e-07, "loss": 0.9573, "step": 6350 }, { "epoch": 0.03780516076109635, "grad_norm": 13.0460844039917, "learning_rate": 7.55979837367445e-07, "loss": 0.9243, "step": 6360 }, { "epoch": 0.03786460283776474, "grad_norm": 17.087282180786133, "learning_rate": 7.571686718341338e-07, "loss": 0.9456, "step": 6370 }, { "epoch": 0.03792404491443313, "grad_norm": 11.086421012878418, "learning_rate": 7.583575063008228e-07, "loss": 0.9305, "step": 6380 }, { "epoch": 0.037983486991101524, "grad_norm": 12.987096786499023, "learning_rate": 7.595463407675116e-07, "loss": 0.9273, "step": 6390 }, { "epoch": 0.03804292906776991, "grad_norm": 18.308446884155273, "learning_rate": 7.607351752342005e-07, "loss": 0.8709, "step": 6400 }, { "epoch": 0.038102371144438305, "grad_norm": 12.098690032958984, "learning_rate": 7.619240097008893e-07, "loss": 0.8623, "step": 6410 }, { "epoch": 0.03816181322110669, "grad_norm": 14.564652442932129, "learning_rate": 7.631128441675782e-07, "loss": 0.9261, "step": 6420 }, { "epoch": 0.038221255297775085, "grad_norm": 14.511013984680176, "learning_rate": 7.64301678634267e-07, "loss": 0.9434, "step": 6430 }, { "epoch": 0.03828069737444347, "grad_norm": 13.176535606384277, "learning_rate": 7.654905131009559e-07, "loss": 0.9331, "step": 6440 }, { "epoch": 0.038340139451111865, "grad_norm": 16.466957092285156, "learning_rate": 7.666793475676447e-07, "loss": 0.9436, "step": 6450 }, { "epoch": 0.03839958152778025, "grad_norm": 15.785340309143066, "learning_rate": 7.678681820343337e-07, "loss": 0.8873, "step": 6460 }, { "epoch": 0.038459023604448646, "grad_norm": 14.199332237243652, "learning_rate": 7.690570165010225e-07, "loss": 0.9098, "step": 6470 }, { "epoch": 0.03851846568111703, "grad_norm": 14.731393814086914, "learning_rate": 7.702458509677114e-07, "loss": 0.9155, "step": 6480 }, { "epoch": 0.038577907757785426, "grad_norm": 12.482071876525879, "learning_rate": 7.714346854344002e-07, "loss": 0.8424, "step": 6490 }, { "epoch": 0.03863734983445382, "grad_norm": 12.44694709777832, "learning_rate": 7.72623519901089e-07, "loss": 0.9136, "step": 6500 }, { "epoch": 0.03869679191112221, "grad_norm": 15.243185997009277, "learning_rate": 7.738123543677779e-07, "loss": 0.9068, "step": 6510 }, { "epoch": 0.0387562339877906, "grad_norm": 9.859786033630371, "learning_rate": 7.750011888344667e-07, "loss": 0.91, "step": 6520 }, { "epoch": 0.03881567606445899, "grad_norm": 14.43821907043457, "learning_rate": 7.761900233011556e-07, "loss": 0.8826, "step": 6530 }, { "epoch": 0.03887511814112738, "grad_norm": 14.980059623718262, "learning_rate": 7.773788577678444e-07, "loss": 0.8617, "step": 6540 }, { "epoch": 0.03893456021779577, "grad_norm": 17.584409713745117, "learning_rate": 7.785676922345334e-07, "loss": 0.8623, "step": 6550 }, { "epoch": 0.03899400229446416, "grad_norm": 15.84716796875, "learning_rate": 7.797565267012222e-07, "loss": 0.9096, "step": 6560 }, { "epoch": 0.03905344437113255, "grad_norm": 15.370832443237305, "learning_rate": 7.809453611679111e-07, "loss": 1.0086, "step": 6570 }, { "epoch": 0.03911288644780094, "grad_norm": 11.313169479370117, "learning_rate": 7.821341956345999e-07, "loss": 0.8975, "step": 6580 }, { "epoch": 0.03917232852446933, "grad_norm": 13.557329177856445, "learning_rate": 7.833230301012888e-07, "loss": 0.8991, "step": 6590 }, { "epoch": 0.03923177060113772, "grad_norm": 14.35503101348877, "learning_rate": 7.845118645679776e-07, "loss": 0.9133, "step": 6600 }, { "epoch": 0.03929121267780611, "grad_norm": 14.961325645446777, "learning_rate": 7.857006990346665e-07, "loss": 0.8551, "step": 6610 }, { "epoch": 0.0393506547544745, "grad_norm": 15.177433013916016, "learning_rate": 7.868895335013553e-07, "loss": 0.905, "step": 6620 }, { "epoch": 0.039410096831142896, "grad_norm": 15.206299781799316, "learning_rate": 7.880783679680441e-07, "loss": 0.9103, "step": 6630 }, { "epoch": 0.03946953890781128, "grad_norm": 15.905479431152344, "learning_rate": 7.892672024347331e-07, "loss": 0.9056, "step": 6640 }, { "epoch": 0.03952898098447968, "grad_norm": 12.956162452697754, "learning_rate": 7.90456036901422e-07, "loss": 0.878, "step": 6650 }, { "epoch": 0.03958842306114806, "grad_norm": 13.65804672241211, "learning_rate": 7.916448713681108e-07, "loss": 0.9374, "step": 6660 }, { "epoch": 0.03964786513781646, "grad_norm": 16.256505966186523, "learning_rate": 7.928337058347996e-07, "loss": 0.8947, "step": 6670 }, { "epoch": 0.039707307214484844, "grad_norm": 15.022581100463867, "learning_rate": 7.940225403014885e-07, "loss": 0.9308, "step": 6680 }, { "epoch": 0.03976674929115324, "grad_norm": 11.944849014282227, "learning_rate": 7.952113747681773e-07, "loss": 0.8716, "step": 6690 }, { "epoch": 0.039826191367821624, "grad_norm": 10.810630798339844, "learning_rate": 7.964002092348662e-07, "loss": 0.8648, "step": 6700 }, { "epoch": 0.03988563344449002, "grad_norm": 19.40348243713379, "learning_rate": 7.97589043701555e-07, "loss": 0.8993, "step": 6710 }, { "epoch": 0.039945075521158405, "grad_norm": 11.494009971618652, "learning_rate": 7.98777878168244e-07, "loss": 0.96, "step": 6720 }, { "epoch": 0.0400045175978268, "grad_norm": 14.55797004699707, "learning_rate": 7.999667126349328e-07, "loss": 0.9499, "step": 6730 }, { "epoch": 0.040063959674495185, "grad_norm": 13.031116485595703, "learning_rate": 8.011555471016217e-07, "loss": 0.857, "step": 6740 }, { "epoch": 0.04012340175116358, "grad_norm": 11.695353507995605, "learning_rate": 8.023443815683105e-07, "loss": 0.8438, "step": 6750 }, { "epoch": 0.04018284382783197, "grad_norm": 12.375985145568848, "learning_rate": 8.035332160349993e-07, "loss": 0.8862, "step": 6760 }, { "epoch": 0.04024228590450036, "grad_norm": 14.599203109741211, "learning_rate": 8.047220505016882e-07, "loss": 0.9619, "step": 6770 }, { "epoch": 0.04030172798116875, "grad_norm": 15.360979080200195, "learning_rate": 8.059108849683771e-07, "loss": 0.8639, "step": 6780 }, { "epoch": 0.04036117005783714, "grad_norm": 14.009888648986816, "learning_rate": 8.070997194350659e-07, "loss": 0.9219, "step": 6790 }, { "epoch": 0.04042061213450553, "grad_norm": 16.16040802001953, "learning_rate": 8.082885539017547e-07, "loss": 0.9495, "step": 6800 }, { "epoch": 0.04048005421117392, "grad_norm": 16.408409118652344, "learning_rate": 8.094773883684437e-07, "loss": 0.8927, "step": 6810 }, { "epoch": 0.040539496287842314, "grad_norm": 14.092609405517578, "learning_rate": 8.106662228351326e-07, "loss": 0.9667, "step": 6820 }, { "epoch": 0.0405989383645107, "grad_norm": 11.786656379699707, "learning_rate": 8.118550573018214e-07, "loss": 0.9421, "step": 6830 }, { "epoch": 0.040658380441179094, "grad_norm": 14.434854507446289, "learning_rate": 8.130438917685102e-07, "loss": 0.9347, "step": 6840 }, { "epoch": 0.04071782251784748, "grad_norm": 13.089107513427734, "learning_rate": 8.142327262351991e-07, "loss": 0.9101, "step": 6850 }, { "epoch": 0.040777264594515875, "grad_norm": 13.078761100769043, "learning_rate": 8.15421560701888e-07, "loss": 0.8837, "step": 6860 }, { "epoch": 0.04083670667118426, "grad_norm": 11.22556209564209, "learning_rate": 8.166103951685768e-07, "loss": 0.8785, "step": 6870 }, { "epoch": 0.040896148747852655, "grad_norm": 13.187580108642578, "learning_rate": 8.177992296352656e-07, "loss": 0.8882, "step": 6880 }, { "epoch": 0.04095559082452105, "grad_norm": 12.123298645019531, "learning_rate": 8.189880641019544e-07, "loss": 0.854, "step": 6890 }, { "epoch": 0.041015032901189435, "grad_norm": 14.415519714355469, "learning_rate": 8.201768985686434e-07, "loss": 0.8842, "step": 6900 }, { "epoch": 0.04107447497785783, "grad_norm": 15.828551292419434, "learning_rate": 8.213657330353323e-07, "loss": 0.8894, "step": 6910 }, { "epoch": 0.041133917054526216, "grad_norm": 13.29734992980957, "learning_rate": 8.225545675020211e-07, "loss": 0.9121, "step": 6920 }, { "epoch": 0.04119335913119461, "grad_norm": 14.190268516540527, "learning_rate": 8.237434019687099e-07, "loss": 0.9457, "step": 6930 }, { "epoch": 0.041252801207862996, "grad_norm": 12.070000648498535, "learning_rate": 8.249322364353988e-07, "loss": 0.924, "step": 6940 }, { "epoch": 0.04131224328453139, "grad_norm": 13.769734382629395, "learning_rate": 8.261210709020877e-07, "loss": 0.9046, "step": 6950 }, { "epoch": 0.04137168536119978, "grad_norm": 14.200173377990723, "learning_rate": 8.273099053687765e-07, "loss": 0.9078, "step": 6960 }, { "epoch": 0.04143112743786817, "grad_norm": 13.168584823608398, "learning_rate": 8.284987398354653e-07, "loss": 0.956, "step": 6970 }, { "epoch": 0.04149056951453656, "grad_norm": 18.169172286987305, "learning_rate": 8.296875743021543e-07, "loss": 0.9142, "step": 6980 }, { "epoch": 0.04155001159120495, "grad_norm": 13.764129638671875, "learning_rate": 8.308764087688432e-07, "loss": 0.9169, "step": 6990 }, { "epoch": 0.04160945366787334, "grad_norm": 14.571249961853027, "learning_rate": 8.32065243235532e-07, "loss": 0.9094, "step": 7000 }, { "epoch": 0.04166889574454173, "grad_norm": 12.938974380493164, "learning_rate": 8.332540777022208e-07, "loss": 0.8712, "step": 7010 }, { "epoch": 0.041728337821210125, "grad_norm": 11.277999877929688, "learning_rate": 8.344429121689096e-07, "loss": 0.8324, "step": 7020 }, { "epoch": 0.04178777989787851, "grad_norm": 15.108384132385254, "learning_rate": 8.356317466355985e-07, "loss": 0.7726, "step": 7030 }, { "epoch": 0.041847221974546905, "grad_norm": 13.80821704864502, "learning_rate": 8.368205811022874e-07, "loss": 0.9297, "step": 7040 }, { "epoch": 0.04190666405121529, "grad_norm": 16.467857360839844, "learning_rate": 8.380094155689762e-07, "loss": 0.9406, "step": 7050 }, { "epoch": 0.041966106127883686, "grad_norm": 14.872773170471191, "learning_rate": 8.39198250035665e-07, "loss": 0.9096, "step": 7060 }, { "epoch": 0.04202554820455207, "grad_norm": 12.188511848449707, "learning_rate": 8.40387084502354e-07, "loss": 0.8838, "step": 7070 }, { "epoch": 0.042084990281220466, "grad_norm": 14.411291122436523, "learning_rate": 8.415759189690429e-07, "loss": 0.9237, "step": 7080 }, { "epoch": 0.04214443235788885, "grad_norm": 13.59569263458252, "learning_rate": 8.427647534357317e-07, "loss": 0.8172, "step": 7090 }, { "epoch": 0.04220387443455725, "grad_norm": 14.929292678833008, "learning_rate": 8.439535879024205e-07, "loss": 0.8357, "step": 7100 }, { "epoch": 0.04226331651122563, "grad_norm": 13.894465446472168, "learning_rate": 8.451424223691094e-07, "loss": 0.9174, "step": 7110 }, { "epoch": 0.04232275858789403, "grad_norm": 14.383899688720703, "learning_rate": 8.463312568357983e-07, "loss": 0.892, "step": 7120 }, { "epoch": 0.042382200664562414, "grad_norm": 14.42060661315918, "learning_rate": 8.475200913024871e-07, "loss": 0.8912, "step": 7130 }, { "epoch": 0.04244164274123081, "grad_norm": 13.146641731262207, "learning_rate": 8.487089257691759e-07, "loss": 0.8634, "step": 7140 }, { "epoch": 0.0425010848178992, "grad_norm": 12.244363784790039, "learning_rate": 8.498977602358647e-07, "loss": 0.9211, "step": 7150 }, { "epoch": 0.04256052689456759, "grad_norm": 14.910319328308105, "learning_rate": 8.510865947025538e-07, "loss": 0.8303, "step": 7160 }, { "epoch": 0.04261996897123598, "grad_norm": 13.22525691986084, "learning_rate": 8.522754291692426e-07, "loss": 0.9473, "step": 7170 }, { "epoch": 0.04267941104790437, "grad_norm": 15.423989295959473, "learning_rate": 8.534642636359314e-07, "loss": 0.8546, "step": 7180 }, { "epoch": 0.04273885312457276, "grad_norm": 12.946588516235352, "learning_rate": 8.546530981026202e-07, "loss": 0.8941, "step": 7190 }, { "epoch": 0.04279829520124115, "grad_norm": 11.188512802124023, "learning_rate": 8.558419325693091e-07, "loss": 0.8705, "step": 7200 }, { "epoch": 0.04285773727790954, "grad_norm": 15.623007774353027, "learning_rate": 8.57030767035998e-07, "loss": 0.868, "step": 7210 }, { "epoch": 0.04291717935457793, "grad_norm": 13.615960121154785, "learning_rate": 8.582196015026868e-07, "loss": 0.8476, "step": 7220 }, { "epoch": 0.04297662143124632, "grad_norm": 12.103989601135254, "learning_rate": 8.594084359693756e-07, "loss": 0.9197, "step": 7230 }, { "epoch": 0.04303606350791471, "grad_norm": 14.07780647277832, "learning_rate": 8.605972704360646e-07, "loss": 0.8818, "step": 7240 }, { "epoch": 0.0430955055845831, "grad_norm": 11.644572257995605, "learning_rate": 8.617861049027535e-07, "loss": 0.851, "step": 7250 }, { "epoch": 0.04315494766125149, "grad_norm": 16.000768661499023, "learning_rate": 8.629749393694423e-07, "loss": 0.8876, "step": 7260 }, { "epoch": 0.043214389737919884, "grad_norm": 18.904869079589844, "learning_rate": 8.641637738361311e-07, "loss": 0.8681, "step": 7270 }, { "epoch": 0.04327383181458828, "grad_norm": 12.486712455749512, "learning_rate": 8.653526083028199e-07, "loss": 0.8798, "step": 7280 }, { "epoch": 0.043333273891256664, "grad_norm": 11.795580863952637, "learning_rate": 8.665414427695089e-07, "loss": 0.9211, "step": 7290 }, { "epoch": 0.04339271596792506, "grad_norm": 12.209380149841309, "learning_rate": 8.677302772361977e-07, "loss": 0.8892, "step": 7300 }, { "epoch": 0.043452158044593445, "grad_norm": 13.287320137023926, "learning_rate": 8.689191117028865e-07, "loss": 0.8875, "step": 7310 }, { "epoch": 0.04351160012126184, "grad_norm": 14.346420288085938, "learning_rate": 8.701079461695753e-07, "loss": 0.9, "step": 7320 }, { "epoch": 0.043571042197930225, "grad_norm": 11.268707275390625, "learning_rate": 8.712967806362644e-07, "loss": 0.8701, "step": 7330 }, { "epoch": 0.04363048427459862, "grad_norm": 14.955479621887207, "learning_rate": 8.724856151029532e-07, "loss": 0.8197, "step": 7340 }, { "epoch": 0.043689926351267006, "grad_norm": 12.243165016174316, "learning_rate": 8.73674449569642e-07, "loss": 0.9444, "step": 7350 }, { "epoch": 0.0437493684279354, "grad_norm": 13.090694427490234, "learning_rate": 8.748632840363308e-07, "loss": 0.853, "step": 7360 }, { "epoch": 0.043808810504603786, "grad_norm": 13.40572738647461, "learning_rate": 8.760521185030197e-07, "loss": 0.8681, "step": 7370 }, { "epoch": 0.04386825258127218, "grad_norm": 11.968605995178223, "learning_rate": 8.772409529697086e-07, "loss": 0.8537, "step": 7380 }, { "epoch": 0.043927694657940566, "grad_norm": 11.513921737670898, "learning_rate": 8.784297874363974e-07, "loss": 0.8368, "step": 7390 }, { "epoch": 0.04398713673460896, "grad_norm": 14.553796768188477, "learning_rate": 8.796186219030862e-07, "loss": 0.8383, "step": 7400 }, { "epoch": 0.044046578811277354, "grad_norm": 13.40360164642334, "learning_rate": 8.80807456369775e-07, "loss": 0.8909, "step": 7410 }, { "epoch": 0.04410602088794574, "grad_norm": 11.687704086303711, "learning_rate": 8.819962908364641e-07, "loss": 0.8251, "step": 7420 }, { "epoch": 0.044165462964614134, "grad_norm": 13.280289649963379, "learning_rate": 8.831851253031529e-07, "loss": 0.8938, "step": 7430 }, { "epoch": 0.04422490504128252, "grad_norm": 12.26142692565918, "learning_rate": 8.843739597698417e-07, "loss": 0.8552, "step": 7440 }, { "epoch": 0.044284347117950915, "grad_norm": 14.087265968322754, "learning_rate": 8.855627942365305e-07, "loss": 0.9366, "step": 7450 }, { "epoch": 0.0443437891946193, "grad_norm": 11.884214401245117, "learning_rate": 8.867516287032195e-07, "loss": 0.8349, "step": 7460 }, { "epoch": 0.044403231271287695, "grad_norm": 15.16382122039795, "learning_rate": 8.879404631699083e-07, "loss": 0.8957, "step": 7470 }, { "epoch": 0.04446267334795608, "grad_norm": 12.955678939819336, "learning_rate": 8.891292976365971e-07, "loss": 0.8787, "step": 7480 }, { "epoch": 0.044522115424624475, "grad_norm": 17.708187103271484, "learning_rate": 8.903181321032859e-07, "loss": 0.8669, "step": 7490 }, { "epoch": 0.04458155750129286, "grad_norm": 10.186606407165527, "learning_rate": 8.91506966569975e-07, "loss": 0.8258, "step": 7500 }, { "epoch": 0.044640999577961256, "grad_norm": 14.970291137695312, "learning_rate": 8.926958010366638e-07, "loss": 0.9263, "step": 7510 }, { "epoch": 0.04470044165462965, "grad_norm": 14.479269981384277, "learning_rate": 8.938846355033526e-07, "loss": 0.9725, "step": 7520 }, { "epoch": 0.044759883731298036, "grad_norm": 13.611574172973633, "learning_rate": 8.950734699700414e-07, "loss": 0.8427, "step": 7530 }, { "epoch": 0.04481932580796643, "grad_norm": 14.632983207702637, "learning_rate": 8.962623044367302e-07, "loss": 0.9248, "step": 7540 }, { "epoch": 0.04487876788463482, "grad_norm": 14.661948204040527, "learning_rate": 8.974511389034192e-07, "loss": 0.9564, "step": 7550 }, { "epoch": 0.04493820996130321, "grad_norm": 14.74832820892334, "learning_rate": 8.98639973370108e-07, "loss": 0.8431, "step": 7560 }, { "epoch": 0.0449976520379716, "grad_norm": 11.665297508239746, "learning_rate": 8.998288078367968e-07, "loss": 0.7963, "step": 7570 }, { "epoch": 0.04505709411463999, "grad_norm": 15.357734680175781, "learning_rate": 9.010176423034856e-07, "loss": 0.89, "step": 7580 }, { "epoch": 0.04511653619130838, "grad_norm": 11.452557563781738, "learning_rate": 9.022064767701747e-07, "loss": 0.9251, "step": 7590 }, { "epoch": 0.04517597826797677, "grad_norm": 14.129788398742676, "learning_rate": 9.033953112368635e-07, "loss": 0.8692, "step": 7600 }, { "epoch": 0.04523542034464516, "grad_norm": 14.910880088806152, "learning_rate": 9.045841457035523e-07, "loss": 0.9013, "step": 7610 }, { "epoch": 0.04529486242131355, "grad_norm": 14.297821998596191, "learning_rate": 9.057729801702411e-07, "loss": 0.8146, "step": 7620 }, { "epoch": 0.04535430449798194, "grad_norm": 12.847522735595703, "learning_rate": 9.069618146369301e-07, "loss": 0.8382, "step": 7630 }, { "epoch": 0.04541374657465033, "grad_norm": 13.72578239440918, "learning_rate": 9.081506491036189e-07, "loss": 0.9309, "step": 7640 }, { "epoch": 0.045473188651318726, "grad_norm": 13.753473281860352, "learning_rate": 9.093394835703077e-07, "loss": 0.9161, "step": 7650 }, { "epoch": 0.04553263072798711, "grad_norm": 17.06543731689453, "learning_rate": 9.105283180369965e-07, "loss": 0.9471, "step": 7660 }, { "epoch": 0.045592072804655506, "grad_norm": 13.36284351348877, "learning_rate": 9.117171525036853e-07, "loss": 0.9215, "step": 7670 }, { "epoch": 0.04565151488132389, "grad_norm": 14.092970848083496, "learning_rate": 9.129059869703744e-07, "loss": 0.9222, "step": 7680 }, { "epoch": 0.04571095695799229, "grad_norm": 13.550718307495117, "learning_rate": 9.140948214370632e-07, "loss": 0.8391, "step": 7690 }, { "epoch": 0.04577039903466067, "grad_norm": 14.237711906433105, "learning_rate": 9.15283655903752e-07, "loss": 0.873, "step": 7700 }, { "epoch": 0.04582984111132907, "grad_norm": 12.807031631469727, "learning_rate": 9.164724903704408e-07, "loss": 0.8351, "step": 7710 }, { "epoch": 0.045889283187997454, "grad_norm": 11.686655044555664, "learning_rate": 9.176613248371298e-07, "loss": 0.9044, "step": 7720 }, { "epoch": 0.04594872526466585, "grad_norm": 13.910802841186523, "learning_rate": 9.188501593038186e-07, "loss": 0.8922, "step": 7730 }, { "epoch": 0.046008167341334234, "grad_norm": 14.908682823181152, "learning_rate": 9.200389937705074e-07, "loss": 0.9194, "step": 7740 }, { "epoch": 0.04606760941800263, "grad_norm": 11.924745559692383, "learning_rate": 9.212278282371962e-07, "loss": 0.9238, "step": 7750 }, { "epoch": 0.046127051494671015, "grad_norm": 11.314780235290527, "learning_rate": 9.224166627038853e-07, "loss": 0.8852, "step": 7760 }, { "epoch": 0.04618649357133941, "grad_norm": 13.279783248901367, "learning_rate": 9.236054971705741e-07, "loss": 0.8316, "step": 7770 }, { "epoch": 0.0462459356480078, "grad_norm": 13.2514066696167, "learning_rate": 9.247943316372629e-07, "loss": 0.8762, "step": 7780 }, { "epoch": 0.04630537772467619, "grad_norm": 16.0834903717041, "learning_rate": 9.259831661039517e-07, "loss": 0.8893, "step": 7790 }, { "epoch": 0.04636481980134458, "grad_norm": 14.181654930114746, "learning_rate": 9.271720005706406e-07, "loss": 0.8698, "step": 7800 }, { "epoch": 0.04642426187801297, "grad_norm": 11.704133033752441, "learning_rate": 9.283608350373295e-07, "loss": 0.8708, "step": 7810 }, { "epoch": 0.04648370395468136, "grad_norm": 12.250384330749512, "learning_rate": 9.295496695040183e-07, "loss": 0.8766, "step": 7820 }, { "epoch": 0.04654314603134975, "grad_norm": 15.33023452758789, "learning_rate": 9.307385039707071e-07, "loss": 0.8847, "step": 7830 }, { "epoch": 0.04660258810801814, "grad_norm": 10.393710136413574, "learning_rate": 9.31927338437396e-07, "loss": 0.9288, "step": 7840 }, { "epoch": 0.04666203018468653, "grad_norm": 12.823506355285645, "learning_rate": 9.33116172904085e-07, "loss": 0.8612, "step": 7850 }, { "epoch": 0.046721472261354924, "grad_norm": 16.62482261657715, "learning_rate": 9.343050073707738e-07, "loss": 0.8355, "step": 7860 }, { "epoch": 0.04678091433802331, "grad_norm": 11.219054222106934, "learning_rate": 9.354938418374626e-07, "loss": 0.9042, "step": 7870 }, { "epoch": 0.046840356414691704, "grad_norm": 14.046527862548828, "learning_rate": 9.366826763041514e-07, "loss": 0.9178, "step": 7880 }, { "epoch": 0.04689979849136009, "grad_norm": 16.379056930541992, "learning_rate": 9.378715107708404e-07, "loss": 0.8942, "step": 7890 }, { "epoch": 0.046959240568028485, "grad_norm": 14.234624862670898, "learning_rate": 9.390603452375292e-07, "loss": 0.9551, "step": 7900 }, { "epoch": 0.04701868264469688, "grad_norm": 13.123522758483887, "learning_rate": 9.40249179704218e-07, "loss": 0.918, "step": 7910 }, { "epoch": 0.047078124721365265, "grad_norm": 19.338708877563477, "learning_rate": 9.414380141709068e-07, "loss": 0.8991, "step": 7920 }, { "epoch": 0.04713756679803366, "grad_norm": 14.252067565917969, "learning_rate": 9.426268486375958e-07, "loss": 0.8623, "step": 7930 }, { "epoch": 0.047197008874702046, "grad_norm": 14.431915283203125, "learning_rate": 9.438156831042847e-07, "loss": 0.881, "step": 7940 }, { "epoch": 0.04725645095137044, "grad_norm": 13.535296440124512, "learning_rate": 9.450045175709735e-07, "loss": 0.8424, "step": 7950 }, { "epoch": 0.047315893028038826, "grad_norm": 13.248963356018066, "learning_rate": 9.461933520376623e-07, "loss": 0.8825, "step": 7960 }, { "epoch": 0.04737533510470722, "grad_norm": 12.170658111572266, "learning_rate": 9.473821865043511e-07, "loss": 0.8829, "step": 7970 }, { "epoch": 0.047434777181375606, "grad_norm": 15.047066688537598, "learning_rate": 9.485710209710401e-07, "loss": 0.8487, "step": 7980 }, { "epoch": 0.047494219258044, "grad_norm": 14.383503913879395, "learning_rate": 9.497598554377289e-07, "loss": 0.8669, "step": 7990 }, { "epoch": 0.04755366133471239, "grad_norm": 11.806044578552246, "learning_rate": 9.509486899044177e-07, "loss": 0.8855, "step": 8000 }, { "epoch": 0.04761310341138078, "grad_norm": 12.967793464660645, "learning_rate": 9.521375243711066e-07, "loss": 0.9049, "step": 8010 }, { "epoch": 0.04767254548804917, "grad_norm": 14.85243034362793, "learning_rate": 9.533263588377956e-07, "loss": 0.828, "step": 8020 }, { "epoch": 0.04773198756471756, "grad_norm": 15.216012001037598, "learning_rate": 9.545151933044843e-07, "loss": 0.866, "step": 8030 }, { "epoch": 0.047791429641385955, "grad_norm": 14.329832077026367, "learning_rate": 9.557040277711732e-07, "loss": 0.8594, "step": 8040 }, { "epoch": 0.04785087171805434, "grad_norm": 16.45084571838379, "learning_rate": 9.568928622378621e-07, "loss": 0.8907, "step": 8050 }, { "epoch": 0.047910313794722735, "grad_norm": 15.738965034484863, "learning_rate": 9.580816967045509e-07, "loss": 0.863, "step": 8060 }, { "epoch": 0.04796975587139112, "grad_norm": 12.043344497680664, "learning_rate": 9.592705311712398e-07, "loss": 0.8489, "step": 8070 }, { "epoch": 0.048029197948059515, "grad_norm": 11.682623863220215, "learning_rate": 9.604593656379287e-07, "loss": 0.8681, "step": 8080 }, { "epoch": 0.0480886400247279, "grad_norm": 12.652693748474121, "learning_rate": 9.616482001046174e-07, "loss": 0.8962, "step": 8090 }, { "epoch": 0.048148082101396296, "grad_norm": 11.84345531463623, "learning_rate": 9.628370345713064e-07, "loss": 0.8632, "step": 8100 }, { "epoch": 0.04820752417806468, "grad_norm": 13.043266296386719, "learning_rate": 9.640258690379953e-07, "loss": 0.9029, "step": 8110 }, { "epoch": 0.048266966254733076, "grad_norm": 13.88195514678955, "learning_rate": 9.65214703504684e-07, "loss": 0.9688, "step": 8120 }, { "epoch": 0.04832640833140146, "grad_norm": 11.69231128692627, "learning_rate": 9.66403537971373e-07, "loss": 0.9343, "step": 8130 }, { "epoch": 0.04838585040806986, "grad_norm": 13.044601440429688, "learning_rate": 9.675923724380619e-07, "loss": 0.9005, "step": 8140 }, { "epoch": 0.048445292484738244, "grad_norm": 14.988592147827148, "learning_rate": 9.687812069047508e-07, "loss": 0.9004, "step": 8150 }, { "epoch": 0.04850473456140664, "grad_norm": 15.07021713256836, "learning_rate": 9.699700413714395e-07, "loss": 0.8577, "step": 8160 }, { "epoch": 0.04856417663807503, "grad_norm": 13.3386812210083, "learning_rate": 9.711588758381284e-07, "loss": 0.8522, "step": 8170 }, { "epoch": 0.04862361871474342, "grad_norm": 12.825810432434082, "learning_rate": 9.723477103048171e-07, "loss": 0.9351, "step": 8180 }, { "epoch": 0.04868306079141181, "grad_norm": 17.162940979003906, "learning_rate": 9.73536544771506e-07, "loss": 0.8445, "step": 8190 }, { "epoch": 0.0487425028680802, "grad_norm": 13.821793556213379, "learning_rate": 9.74725379238195e-07, "loss": 0.862, "step": 8200 }, { "epoch": 0.04880194494474859, "grad_norm": 12.497443199157715, "learning_rate": 9.75914213704884e-07, "loss": 0.8823, "step": 8210 }, { "epoch": 0.04886138702141698, "grad_norm": 14.600653648376465, "learning_rate": 9.771030481715726e-07, "loss": 0.8772, "step": 8220 }, { "epoch": 0.04892082909808537, "grad_norm": 15.670380592346191, "learning_rate": 9.782918826382616e-07, "loss": 0.8386, "step": 8230 }, { "epoch": 0.04898027117475376, "grad_norm": 12.065094947814941, "learning_rate": 9.794807171049505e-07, "loss": 0.8743, "step": 8240 }, { "epoch": 0.04903971325142215, "grad_norm": 13.515213966369629, "learning_rate": 9.806695515716392e-07, "loss": 0.8216, "step": 8250 }, { "epoch": 0.04909915532809054, "grad_norm": 13.535135269165039, "learning_rate": 9.818583860383281e-07, "loss": 0.8474, "step": 8260 }, { "epoch": 0.04915859740475893, "grad_norm": 13.156176567077637, "learning_rate": 9.830472205050169e-07, "loss": 0.817, "step": 8270 }, { "epoch": 0.04921803948142732, "grad_norm": 14.222620010375977, "learning_rate": 9.842360549717058e-07, "loss": 0.9006, "step": 8280 }, { "epoch": 0.04927748155809571, "grad_norm": 11.098945617675781, "learning_rate": 9.854248894383947e-07, "loss": 0.7918, "step": 8290 }, { "epoch": 0.04933692363476411, "grad_norm": 14.355676651000977, "learning_rate": 9.866137239050836e-07, "loss": 0.8773, "step": 8300 }, { "epoch": 0.049396365711432494, "grad_norm": 12.80979061126709, "learning_rate": 9.878025583717723e-07, "loss": 0.7908, "step": 8310 }, { "epoch": 0.04945580778810089, "grad_norm": 11.73548412322998, "learning_rate": 9.889913928384613e-07, "loss": 0.8422, "step": 8320 }, { "epoch": 0.049515249864769274, "grad_norm": 12.533585548400879, "learning_rate": 9.901802273051502e-07, "loss": 0.8562, "step": 8330 }, { "epoch": 0.04957469194143767, "grad_norm": 12.209805488586426, "learning_rate": 9.91369061771839e-07, "loss": 0.9195, "step": 8340 }, { "epoch": 0.049634134018106055, "grad_norm": 12.68521499633789, "learning_rate": 9.925578962385278e-07, "loss": 0.8344, "step": 8350 }, { "epoch": 0.04969357609477445, "grad_norm": 14.067608833312988, "learning_rate": 9.937467307052166e-07, "loss": 0.7869, "step": 8360 }, { "epoch": 0.049753018171442835, "grad_norm": 16.489627838134766, "learning_rate": 9.949355651719055e-07, "loss": 0.9044, "step": 8370 }, { "epoch": 0.04981246024811123, "grad_norm": 12.904126167297363, "learning_rate": 9.961243996385944e-07, "loss": 0.8715, "step": 8380 }, { "epoch": 0.049871902324779616, "grad_norm": 14.122010231018066, "learning_rate": 9.973132341052833e-07, "loss": 0.8629, "step": 8390 }, { "epoch": 0.04993134440144801, "grad_norm": 13.632431030273438, "learning_rate": 9.98502068571972e-07, "loss": 0.8768, "step": 8400 }, { "epoch": 0.049990786478116396, "grad_norm": 12.670510292053223, "learning_rate": 9.99690903038661e-07, "loss": 0.8342, "step": 8410 }, { "epoch": 0.05005022855478479, "grad_norm": 14.10214900970459, "learning_rate": 1.00087973750535e-06, "loss": 0.8645, "step": 8420 }, { "epoch": 0.05010967063145318, "grad_norm": 14.960762023925781, "learning_rate": 1.0020685719720386e-06, "loss": 0.8217, "step": 8430 }, { "epoch": 0.05016911270812157, "grad_norm": 14.082088470458984, "learning_rate": 1.0032574064387276e-06, "loss": 0.959, "step": 8440 }, { "epoch": 0.050228554784789964, "grad_norm": 12.224638938903809, "learning_rate": 1.0044462409054165e-06, "loss": 0.8554, "step": 8450 }, { "epoch": 0.05028799686145835, "grad_norm": 13.335592269897461, "learning_rate": 1.0056350753721054e-06, "loss": 0.8142, "step": 8460 }, { "epoch": 0.050347438938126744, "grad_norm": 15.147937774658203, "learning_rate": 1.0068239098387941e-06, "loss": 0.8483, "step": 8470 }, { "epoch": 0.05040688101479513, "grad_norm": 14.75755500793457, "learning_rate": 1.008012744305483e-06, "loss": 0.8971, "step": 8480 }, { "epoch": 0.050466323091463525, "grad_norm": 16.301288604736328, "learning_rate": 1.0092015787721718e-06, "loss": 0.8202, "step": 8490 }, { "epoch": 0.05052576516813191, "grad_norm": 13.937798500061035, "learning_rate": 1.0103904132388607e-06, "loss": 0.845, "step": 8500 }, { "epoch": 0.050585207244800305, "grad_norm": 10.830706596374512, "learning_rate": 1.0115792477055496e-06, "loss": 0.8754, "step": 8510 }, { "epoch": 0.05064464932146869, "grad_norm": 11.880721092224121, "learning_rate": 1.0127680821722383e-06, "loss": 0.8868, "step": 8520 }, { "epoch": 0.050704091398137086, "grad_norm": 14.224678993225098, "learning_rate": 1.0139569166389273e-06, "loss": 0.8627, "step": 8530 }, { "epoch": 0.05076353347480548, "grad_norm": 11.842604637145996, "learning_rate": 1.0151457511056162e-06, "loss": 0.8371, "step": 8540 }, { "epoch": 0.050822975551473866, "grad_norm": 11.75127124786377, "learning_rate": 1.0163345855723051e-06, "loss": 0.9415, "step": 8550 }, { "epoch": 0.05088241762814226, "grad_norm": 12.001378059387207, "learning_rate": 1.0175234200389938e-06, "loss": 0.8227, "step": 8560 }, { "epoch": 0.050941859704810646, "grad_norm": 15.152139663696289, "learning_rate": 1.0187122545056828e-06, "loss": 0.9051, "step": 8570 }, { "epoch": 0.05100130178147904, "grad_norm": 11.423553466796875, "learning_rate": 1.0199010889723717e-06, "loss": 0.8023, "step": 8580 }, { "epoch": 0.05106074385814743, "grad_norm": 12.895233154296875, "learning_rate": 1.0210899234390604e-06, "loss": 0.8227, "step": 8590 }, { "epoch": 0.05112018593481582, "grad_norm": 16.737943649291992, "learning_rate": 1.0222787579057493e-06, "loss": 0.8728, "step": 8600 }, { "epoch": 0.05117962801148421, "grad_norm": 12.85289478302002, "learning_rate": 1.023467592372438e-06, "loss": 0.8559, "step": 8610 }, { "epoch": 0.0512390700881526, "grad_norm": 11.567727088928223, "learning_rate": 1.024656426839127e-06, "loss": 0.8188, "step": 8620 }, { "epoch": 0.05129851216482099, "grad_norm": 15.533815383911133, "learning_rate": 1.025845261305816e-06, "loss": 0.8881, "step": 8630 }, { "epoch": 0.05135795424148938, "grad_norm": 13.564342498779297, "learning_rate": 1.0270340957725048e-06, "loss": 0.8306, "step": 8640 }, { "epoch": 0.05141739631815777, "grad_norm": 12.133722305297852, "learning_rate": 1.0282229302391935e-06, "loss": 0.8613, "step": 8650 }, { "epoch": 0.05147683839482616, "grad_norm": 13.398317337036133, "learning_rate": 1.0294117647058825e-06, "loss": 0.8784, "step": 8660 }, { "epoch": 0.051536280471494555, "grad_norm": 12.030670166015625, "learning_rate": 1.0306005991725714e-06, "loss": 0.7933, "step": 8670 }, { "epoch": 0.05159572254816294, "grad_norm": 12.967865943908691, "learning_rate": 1.0317894336392601e-06, "loss": 0.9329, "step": 8680 }, { "epoch": 0.051655164624831336, "grad_norm": 11.749702453613281, "learning_rate": 1.032978268105949e-06, "loss": 0.8539, "step": 8690 }, { "epoch": 0.05171460670149972, "grad_norm": 10.641284942626953, "learning_rate": 1.0341671025726378e-06, "loss": 0.84, "step": 8700 }, { "epoch": 0.051774048778168116, "grad_norm": 11.258675575256348, "learning_rate": 1.035355937039327e-06, "loss": 0.8021, "step": 8710 }, { "epoch": 0.0518334908548365, "grad_norm": 10.062700271606445, "learning_rate": 1.0365447715060156e-06, "loss": 0.8633, "step": 8720 }, { "epoch": 0.0518929329315049, "grad_norm": 16.425111770629883, "learning_rate": 1.0377336059727045e-06, "loss": 0.8424, "step": 8730 }, { "epoch": 0.051952375008173284, "grad_norm": 12.670790672302246, "learning_rate": 1.0389224404393933e-06, "loss": 0.8022, "step": 8740 }, { "epoch": 0.05201181708484168, "grad_norm": 12.966934204101562, "learning_rate": 1.0401112749060822e-06, "loss": 0.8913, "step": 8750 }, { "epoch": 0.052071259161510064, "grad_norm": 15.415121078491211, "learning_rate": 1.0413001093727711e-06, "loss": 0.8242, "step": 8760 }, { "epoch": 0.05213070123817846, "grad_norm": 10.847929954528809, "learning_rate": 1.0424889438394598e-06, "loss": 0.8451, "step": 8770 }, { "epoch": 0.052190143314846844, "grad_norm": 14.349445343017578, "learning_rate": 1.0436777783061488e-06, "loss": 0.9412, "step": 8780 }, { "epoch": 0.05224958539151524, "grad_norm": 10.435626983642578, "learning_rate": 1.0448666127728375e-06, "loss": 0.901, "step": 8790 }, { "epoch": 0.05230902746818363, "grad_norm": 13.937889099121094, "learning_rate": 1.0460554472395266e-06, "loss": 0.8404, "step": 8800 }, { "epoch": 0.05236846954485202, "grad_norm": 14.351264953613281, "learning_rate": 1.0472442817062153e-06, "loss": 0.8494, "step": 8810 }, { "epoch": 0.05242791162152041, "grad_norm": 12.327260971069336, "learning_rate": 1.0484331161729043e-06, "loss": 0.8399, "step": 8820 }, { "epoch": 0.0524873536981888, "grad_norm": 10.754250526428223, "learning_rate": 1.049621950639593e-06, "loss": 0.8458, "step": 8830 }, { "epoch": 0.05254679577485719, "grad_norm": 10.128637313842773, "learning_rate": 1.050810785106282e-06, "loss": 0.8903, "step": 8840 }, { "epoch": 0.05260623785152558, "grad_norm": 11.683186531066895, "learning_rate": 1.0519996195729708e-06, "loss": 0.8383, "step": 8850 }, { "epoch": 0.05266567992819397, "grad_norm": 23.554943084716797, "learning_rate": 1.0531884540396595e-06, "loss": 0.8325, "step": 8860 }, { "epoch": 0.05272512200486236, "grad_norm": 14.389045715332031, "learning_rate": 1.0543772885063485e-06, "loss": 0.8569, "step": 8870 }, { "epoch": 0.05278456408153075, "grad_norm": 14.671850204467773, "learning_rate": 1.0555661229730372e-06, "loss": 0.8002, "step": 8880 }, { "epoch": 0.05284400615819914, "grad_norm": 12.178509712219238, "learning_rate": 1.0567549574397263e-06, "loss": 0.8809, "step": 8890 }, { "epoch": 0.052903448234867534, "grad_norm": 14.000237464904785, "learning_rate": 1.057943791906415e-06, "loss": 0.8432, "step": 8900 }, { "epoch": 0.05296289031153592, "grad_norm": 12.31035041809082, "learning_rate": 1.059132626373104e-06, "loss": 0.83, "step": 8910 }, { "epoch": 0.053022332388204314, "grad_norm": 14.078315734863281, "learning_rate": 1.0603214608397927e-06, "loss": 0.8424, "step": 8920 }, { "epoch": 0.05308177446487271, "grad_norm": 14.122145652770996, "learning_rate": 1.0615102953064816e-06, "loss": 0.8351, "step": 8930 }, { "epoch": 0.053141216541541095, "grad_norm": 15.480386734008789, "learning_rate": 1.0626991297731705e-06, "loss": 0.9391, "step": 8940 }, { "epoch": 0.05320065861820949, "grad_norm": 13.94628620147705, "learning_rate": 1.0638879642398592e-06, "loss": 0.8462, "step": 8950 }, { "epoch": 0.053260100694877875, "grad_norm": 13.247913360595703, "learning_rate": 1.0650767987065482e-06, "loss": 0.854, "step": 8960 }, { "epoch": 0.05331954277154627, "grad_norm": 13.225895881652832, "learning_rate": 1.066265633173237e-06, "loss": 0.846, "step": 8970 }, { "epoch": 0.053378984848214656, "grad_norm": 13.642792701721191, "learning_rate": 1.067454467639926e-06, "loss": 0.8124, "step": 8980 }, { "epoch": 0.05343842692488305, "grad_norm": 13.748318672180176, "learning_rate": 1.0686433021066147e-06, "loss": 0.8257, "step": 8990 }, { "epoch": 0.053497869001551436, "grad_norm": 11.673078536987305, "learning_rate": 1.0698321365733037e-06, "loss": 0.8484, "step": 9000 }, { "epoch": 0.05355731107821983, "grad_norm": 15.084066390991211, "learning_rate": 1.0710209710399924e-06, "loss": 0.8136, "step": 9010 }, { "epoch": 0.053616753154888216, "grad_norm": 14.007458686828613, "learning_rate": 1.0722098055066813e-06, "loss": 0.8624, "step": 9020 }, { "epoch": 0.05367619523155661, "grad_norm": 10.76686954498291, "learning_rate": 1.0733986399733702e-06, "loss": 0.7835, "step": 9030 }, { "epoch": 0.053735637308225, "grad_norm": 14.068657875061035, "learning_rate": 1.074587474440059e-06, "loss": 0.8583, "step": 9040 }, { "epoch": 0.05379507938489339, "grad_norm": 11.927251815795898, "learning_rate": 1.0757763089067479e-06, "loss": 0.8169, "step": 9050 }, { "epoch": 0.053854521461561784, "grad_norm": 12.261096954345703, "learning_rate": 1.0769651433734368e-06, "loss": 0.7721, "step": 9060 }, { "epoch": 0.05391396353823017, "grad_norm": 11.45304012298584, "learning_rate": 1.0781539778401257e-06, "loss": 0.7921, "step": 9070 }, { "epoch": 0.053973405614898565, "grad_norm": 14.725486755371094, "learning_rate": 1.0793428123068145e-06, "loss": 0.8289, "step": 9080 }, { "epoch": 0.05403284769156695, "grad_norm": 11.607462882995605, "learning_rate": 1.0805316467735034e-06, "loss": 0.8234, "step": 9090 }, { "epoch": 0.054092289768235345, "grad_norm": 13.13769817352295, "learning_rate": 1.0817204812401923e-06, "loss": 0.923, "step": 9100 }, { "epoch": 0.05415173184490373, "grad_norm": 10.828725814819336, "learning_rate": 1.082909315706881e-06, "loss": 0.8205, "step": 9110 }, { "epoch": 0.054211173921572126, "grad_norm": 10.892972946166992, "learning_rate": 1.08409815017357e-06, "loss": 0.8592, "step": 9120 }, { "epoch": 0.05427061599824051, "grad_norm": 12.756085395812988, "learning_rate": 1.0852869846402587e-06, "loss": 0.8487, "step": 9130 }, { "epoch": 0.054330058074908906, "grad_norm": 15.859238624572754, "learning_rate": 1.0864758191069476e-06, "loss": 0.7967, "step": 9140 }, { "epoch": 0.05438950015157729, "grad_norm": 12.96708869934082, "learning_rate": 1.0876646535736365e-06, "loss": 0.8285, "step": 9150 }, { "epoch": 0.054448942228245686, "grad_norm": 11.206202507019043, "learning_rate": 1.0888534880403255e-06, "loss": 0.9209, "step": 9160 }, { "epoch": 0.05450838430491407, "grad_norm": 13.619339942932129, "learning_rate": 1.0900423225070142e-06, "loss": 0.8009, "step": 9170 }, { "epoch": 0.05456782638158247, "grad_norm": 13.13149642944336, "learning_rate": 1.091231156973703e-06, "loss": 0.8357, "step": 9180 }, { "epoch": 0.05462726845825086, "grad_norm": 14.077763557434082, "learning_rate": 1.092419991440392e-06, "loss": 0.8581, "step": 9190 }, { "epoch": 0.05468671053491925, "grad_norm": 10.176247596740723, "learning_rate": 1.0936088259070807e-06, "loss": 0.8501, "step": 9200 }, { "epoch": 0.05474615261158764, "grad_norm": 14.174952507019043, "learning_rate": 1.0947976603737697e-06, "loss": 0.7922, "step": 9210 }, { "epoch": 0.05480559468825603, "grad_norm": 11.848437309265137, "learning_rate": 1.0959864948404584e-06, "loss": 0.8489, "step": 9220 }, { "epoch": 0.05486503676492442, "grad_norm": 12.95998764038086, "learning_rate": 1.0971753293071475e-06, "loss": 0.8712, "step": 9230 }, { "epoch": 0.05492447884159281, "grad_norm": 13.29025936126709, "learning_rate": 1.0983641637738362e-06, "loss": 0.8236, "step": 9240 }, { "epoch": 0.0549839209182612, "grad_norm": 13.844599723815918, "learning_rate": 1.0995529982405252e-06, "loss": 0.8373, "step": 9250 }, { "epoch": 0.05504336299492959, "grad_norm": 13.948598861694336, "learning_rate": 1.1007418327072139e-06, "loss": 0.8499, "step": 9260 }, { "epoch": 0.05510280507159798, "grad_norm": 13.770792007446289, "learning_rate": 1.1019306671739028e-06, "loss": 0.8301, "step": 9270 }, { "epoch": 0.05516224714826637, "grad_norm": 11.093753814697266, "learning_rate": 1.1031195016405917e-06, "loss": 0.8002, "step": 9280 }, { "epoch": 0.05522168922493476, "grad_norm": 15.132713317871094, "learning_rate": 1.1043083361072804e-06, "loss": 0.8411, "step": 9290 }, { "epoch": 0.05528113130160315, "grad_norm": 14.1788911819458, "learning_rate": 1.1054971705739694e-06, "loss": 0.8737, "step": 9300 }, { "epoch": 0.05534057337827154, "grad_norm": 12.276477813720703, "learning_rate": 1.106686005040658e-06, "loss": 0.7832, "step": 9310 }, { "epoch": 0.05540001545493994, "grad_norm": 14.931450843811035, "learning_rate": 1.1078748395073472e-06, "loss": 0.8241, "step": 9320 }, { "epoch": 0.055459457531608324, "grad_norm": 13.705852508544922, "learning_rate": 1.109063673974036e-06, "loss": 0.7963, "step": 9330 }, { "epoch": 0.05551889960827672, "grad_norm": 11.412717819213867, "learning_rate": 1.1102525084407249e-06, "loss": 0.8332, "step": 9340 }, { "epoch": 0.055578341684945104, "grad_norm": 11.470624923706055, "learning_rate": 1.1114413429074136e-06, "loss": 0.8473, "step": 9350 }, { "epoch": 0.0556377837616135, "grad_norm": 11.252670288085938, "learning_rate": 1.1126301773741025e-06, "loss": 0.8903, "step": 9360 }, { "epoch": 0.055697225838281884, "grad_norm": 11.361811637878418, "learning_rate": 1.1138190118407914e-06, "loss": 0.8728, "step": 9370 }, { "epoch": 0.05575666791495028, "grad_norm": 13.338932991027832, "learning_rate": 1.1150078463074802e-06, "loss": 0.8473, "step": 9380 }, { "epoch": 0.055816109991618665, "grad_norm": 10.670090675354004, "learning_rate": 1.116196680774169e-06, "loss": 0.8389, "step": 9390 }, { "epoch": 0.05587555206828706, "grad_norm": 14.578882217407227, "learning_rate": 1.1173855152408578e-06, "loss": 0.875, "step": 9400 }, { "epoch": 0.055934994144955445, "grad_norm": 13.664794921875, "learning_rate": 1.118574349707547e-06, "loss": 0.85, "step": 9410 }, { "epoch": 0.05599443622162384, "grad_norm": 12.000296592712402, "learning_rate": 1.1197631841742357e-06, "loss": 0.8414, "step": 9420 }, { "epoch": 0.056053878298292226, "grad_norm": 14.453004837036133, "learning_rate": 1.1209520186409246e-06, "loss": 0.8634, "step": 9430 }, { "epoch": 0.05611332037496062, "grad_norm": 13.502605438232422, "learning_rate": 1.1221408531076133e-06, "loss": 0.8319, "step": 9440 }, { "epoch": 0.05617276245162901, "grad_norm": 11.199379920959473, "learning_rate": 1.1233296875743022e-06, "loss": 0.8378, "step": 9450 }, { "epoch": 0.0562322045282974, "grad_norm": 13.195068359375, "learning_rate": 1.1245185220409912e-06, "loss": 0.8333, "step": 9460 }, { "epoch": 0.056291646604965793, "grad_norm": 11.35023021697998, "learning_rate": 1.1257073565076799e-06, "loss": 0.8072, "step": 9470 }, { "epoch": 0.05635108868163418, "grad_norm": 13.35723876953125, "learning_rate": 1.1268961909743688e-06, "loss": 0.8119, "step": 9480 }, { "epoch": 0.056410530758302574, "grad_norm": 9.334541320800781, "learning_rate": 1.1280850254410577e-06, "loss": 0.8722, "step": 9490 }, { "epoch": 0.05646997283497096, "grad_norm": 9.177295684814453, "learning_rate": 1.1292738599077467e-06, "loss": 0.785, "step": 9500 }, { "epoch": 0.056529414911639354, "grad_norm": 12.188294410705566, "learning_rate": 1.1304626943744354e-06, "loss": 0.8341, "step": 9510 }, { "epoch": 0.05658885698830774, "grad_norm": 11.678556442260742, "learning_rate": 1.1316515288411243e-06, "loss": 0.8345, "step": 9520 }, { "epoch": 0.056648299064976135, "grad_norm": 13.137556076049805, "learning_rate": 1.132840363307813e-06, "loss": 0.8915, "step": 9530 }, { "epoch": 0.05670774114164452, "grad_norm": 12.46286392211914, "learning_rate": 1.134029197774502e-06, "loss": 0.8668, "step": 9540 }, { "epoch": 0.056767183218312915, "grad_norm": 13.828850746154785, "learning_rate": 1.1352180322411909e-06, "loss": 0.8777, "step": 9550 }, { "epoch": 0.05682662529498131, "grad_norm": 11.534441947937012, "learning_rate": 1.1364068667078796e-06, "loss": 0.8859, "step": 9560 }, { "epoch": 0.056886067371649696, "grad_norm": 13.383157730102539, "learning_rate": 1.1375957011745685e-06, "loss": 0.8227, "step": 9570 }, { "epoch": 0.05694550944831809, "grad_norm": 13.955657958984375, "learning_rate": 1.1387845356412574e-06, "loss": 0.8436, "step": 9580 }, { "epoch": 0.057004951524986476, "grad_norm": 15.595137596130371, "learning_rate": 1.1399733701079464e-06, "loss": 0.8072, "step": 9590 }, { "epoch": 0.05706439360165487, "grad_norm": 10.807039260864258, "learning_rate": 1.141162204574635e-06, "loss": 0.8837, "step": 9600 }, { "epoch": 0.057123835678323256, "grad_norm": 13.98992919921875, "learning_rate": 1.142351039041324e-06, "loss": 0.7924, "step": 9610 }, { "epoch": 0.05718327775499165, "grad_norm": 11.959308624267578, "learning_rate": 1.143539873508013e-06, "loss": 0.8382, "step": 9620 }, { "epoch": 0.05724271983166004, "grad_norm": 13.800528526306152, "learning_rate": 1.1447287079747016e-06, "loss": 0.8603, "step": 9630 }, { "epoch": 0.05730216190832843, "grad_norm": 11.792130470275879, "learning_rate": 1.1459175424413906e-06, "loss": 0.7989, "step": 9640 }, { "epoch": 0.05736160398499682, "grad_norm": 12.139822959899902, "learning_rate": 1.1471063769080793e-06, "loss": 0.8493, "step": 9650 }, { "epoch": 0.05742104606166521, "grad_norm": 16.535655975341797, "learning_rate": 1.1482952113747682e-06, "loss": 0.7681, "step": 9660 }, { "epoch": 0.0574804881383336, "grad_norm": 12.537009239196777, "learning_rate": 1.1494840458414571e-06, "loss": 0.8212, "step": 9670 }, { "epoch": 0.05753993021500199, "grad_norm": 12.984241485595703, "learning_rate": 1.150672880308146e-06, "loss": 0.8669, "step": 9680 }, { "epoch": 0.057599372291670385, "grad_norm": 11.643621444702148, "learning_rate": 1.1518617147748348e-06, "loss": 0.8245, "step": 9690 }, { "epoch": 0.05765881436833877, "grad_norm": 13.955134391784668, "learning_rate": 1.1530505492415237e-06, "loss": 0.8422, "step": 9700 }, { "epoch": 0.057718256445007166, "grad_norm": 14.443718910217285, "learning_rate": 1.1542393837082126e-06, "loss": 0.8022, "step": 9710 }, { "epoch": 0.05777769852167555, "grad_norm": 13.283137321472168, "learning_rate": 1.1554282181749014e-06, "loss": 0.8252, "step": 9720 }, { "epoch": 0.057837140598343946, "grad_norm": 12.702139854431152, "learning_rate": 1.1566170526415903e-06, "loss": 0.8788, "step": 9730 }, { "epoch": 0.05789658267501233, "grad_norm": 11.55078411102295, "learning_rate": 1.157805887108279e-06, "loss": 0.8656, "step": 9740 }, { "epoch": 0.057956024751680726, "grad_norm": 11.294085502624512, "learning_rate": 1.1589947215749681e-06, "loss": 0.7976, "step": 9750 }, { "epoch": 0.05801546682834911, "grad_norm": 12.867133140563965, "learning_rate": 1.1601835560416569e-06, "loss": 0.8141, "step": 9760 }, { "epoch": 0.05807490890501751, "grad_norm": 13.377500534057617, "learning_rate": 1.1613723905083458e-06, "loss": 0.8695, "step": 9770 }, { "epoch": 0.058134350981685894, "grad_norm": 12.991968154907227, "learning_rate": 1.1625612249750345e-06, "loss": 0.8289, "step": 9780 }, { "epoch": 0.05819379305835429, "grad_norm": 15.503032684326172, "learning_rate": 1.1637500594417234e-06, "loss": 0.8267, "step": 9790 }, { "epoch": 0.058253235135022674, "grad_norm": 12.584747314453125, "learning_rate": 1.1649388939084124e-06, "loss": 0.8665, "step": 9800 }, { "epoch": 0.05831267721169107, "grad_norm": 13.058677673339844, "learning_rate": 1.166127728375101e-06, "loss": 0.7916, "step": 9810 }, { "epoch": 0.05837211928835946, "grad_norm": 14.890420913696289, "learning_rate": 1.16731656284179e-06, "loss": 0.878, "step": 9820 }, { "epoch": 0.05843156136502785, "grad_norm": 10.39245319366455, "learning_rate": 1.1685053973084787e-06, "loss": 0.7801, "step": 9830 }, { "epoch": 0.05849100344169624, "grad_norm": 14.43747329711914, "learning_rate": 1.1696942317751678e-06, "loss": 0.8676, "step": 9840 }, { "epoch": 0.05855044551836463, "grad_norm": 11.36274242401123, "learning_rate": 1.1708830662418566e-06, "loss": 0.8161, "step": 9850 }, { "epoch": 0.05860988759503302, "grad_norm": 16.920061111450195, "learning_rate": 1.1720719007085455e-06, "loss": 0.8494, "step": 9860 }, { "epoch": 0.05866932967170141, "grad_norm": 11.800202369689941, "learning_rate": 1.1732607351752342e-06, "loss": 0.8321, "step": 9870 }, { "epoch": 0.0587287717483698, "grad_norm": 11.790192604064941, "learning_rate": 1.1744495696419231e-06, "loss": 0.8061, "step": 9880 }, { "epoch": 0.05878821382503819, "grad_norm": 12.963678359985352, "learning_rate": 1.175638404108612e-06, "loss": 0.8146, "step": 9890 }, { "epoch": 0.05884765590170658, "grad_norm": 12.656018257141113, "learning_rate": 1.1768272385753008e-06, "loss": 0.8621, "step": 9900 }, { "epoch": 0.05890709797837497, "grad_norm": 12.689330101013184, "learning_rate": 1.1780160730419897e-06, "loss": 0.8028, "step": 9910 }, { "epoch": 0.058966540055043364, "grad_norm": 11.091711044311523, "learning_rate": 1.1792049075086784e-06, "loss": 0.7933, "step": 9920 }, { "epoch": 0.05902598213171175, "grad_norm": 11.009235382080078, "learning_rate": 1.1803937419753676e-06, "loss": 0.8423, "step": 9930 }, { "epoch": 0.059085424208380144, "grad_norm": 14.291234970092773, "learning_rate": 1.1815825764420563e-06, "loss": 0.8348, "step": 9940 }, { "epoch": 0.05914486628504854, "grad_norm": 11.883554458618164, "learning_rate": 1.1827714109087452e-06, "loss": 0.7539, "step": 9950 }, { "epoch": 0.059204308361716924, "grad_norm": 14.706549644470215, "learning_rate": 1.183960245375434e-06, "loss": 0.9023, "step": 9960 }, { "epoch": 0.05926375043838532, "grad_norm": 12.559306144714355, "learning_rate": 1.1851490798421228e-06, "loss": 0.8589, "step": 9970 }, { "epoch": 0.059323192515053705, "grad_norm": 16.367467880249023, "learning_rate": 1.1863379143088118e-06, "loss": 0.8635, "step": 9980 }, { "epoch": 0.0593826345917221, "grad_norm": 14.461675643920898, "learning_rate": 1.1875267487755005e-06, "loss": 0.8265, "step": 9990 }, { "epoch": 0.059442076668390485, "grad_norm": 11.20926284790039, "learning_rate": 1.1887155832421894e-06, "loss": 0.785, "step": 10000 }, { "epoch": 0.05950151874505888, "grad_norm": 13.71251392364502, "learning_rate": 1.1899044177088783e-06, "loss": 0.8102, "step": 10010 }, { "epoch": 0.059560960821727266, "grad_norm": 12.393121719360352, "learning_rate": 1.1910932521755673e-06, "loss": 0.8159, "step": 10020 }, { "epoch": 0.05962040289839566, "grad_norm": 9.749998092651367, "learning_rate": 1.192282086642256e-06, "loss": 0.8021, "step": 10030 }, { "epoch": 0.059679844975064046, "grad_norm": 11.930752754211426, "learning_rate": 1.193470921108945e-06, "loss": 0.8161, "step": 10040 }, { "epoch": 0.05973928705173244, "grad_norm": 10.812040328979492, "learning_rate": 1.1946597555756336e-06, "loss": 0.8369, "step": 10050 }, { "epoch": 0.05979872912840083, "grad_norm": 15.352206230163574, "learning_rate": 1.1958485900423226e-06, "loss": 0.8282, "step": 10060 }, { "epoch": 0.05985817120506922, "grad_norm": 12.561606407165527, "learning_rate": 1.1970374245090115e-06, "loss": 0.797, "step": 10070 }, { "epoch": 0.059917613281737614, "grad_norm": 11.450719833374023, "learning_rate": 1.1982262589757002e-06, "loss": 0.8151, "step": 10080 }, { "epoch": 0.059977055358406, "grad_norm": 12.904302597045898, "learning_rate": 1.1994150934423891e-06, "loss": 0.852, "step": 10090 }, { "epoch": 0.060036497435074394, "grad_norm": 12.697124481201172, "learning_rate": 1.200603927909078e-06, "loss": 0.8227, "step": 10100 }, { "epoch": 0.06009593951174278, "grad_norm": 15.532610893249512, "learning_rate": 1.201792762375767e-06, "loss": 0.8094, "step": 10110 }, { "epoch": 0.060155381588411175, "grad_norm": 12.011183738708496, "learning_rate": 1.2029815968424557e-06, "loss": 0.8004, "step": 10120 }, { "epoch": 0.06021482366507956, "grad_norm": 11.761407852172852, "learning_rate": 1.2041704313091446e-06, "loss": 0.8045, "step": 10130 }, { "epoch": 0.060274265741747955, "grad_norm": 12.266241073608398, "learning_rate": 1.2053592657758336e-06, "loss": 0.7996, "step": 10140 }, { "epoch": 0.06033370781841634, "grad_norm": 12.660880088806152, "learning_rate": 1.2065481002425223e-06, "loss": 0.8155, "step": 10150 }, { "epoch": 0.060393149895084736, "grad_norm": 12.64638614654541, "learning_rate": 1.2077369347092112e-06, "loss": 0.7838, "step": 10160 }, { "epoch": 0.06045259197175312, "grad_norm": 16.64212417602539, "learning_rate": 1.2089257691759001e-06, "loss": 0.8839, "step": 10170 }, { "epoch": 0.060512034048421516, "grad_norm": 10.237722396850586, "learning_rate": 1.2101146036425888e-06, "loss": 0.8271, "step": 10180 }, { "epoch": 0.0605714761250899, "grad_norm": 11.843329429626465, "learning_rate": 1.2113034381092778e-06, "loss": 0.8787, "step": 10190 }, { "epoch": 0.060630918201758296, "grad_norm": 12.377961158752441, "learning_rate": 1.2124922725759667e-06, "loss": 0.8211, "step": 10200 }, { "epoch": 0.06069036027842669, "grad_norm": 13.661269187927246, "learning_rate": 1.2136811070426554e-06, "loss": 0.8119, "step": 10210 }, { "epoch": 0.06074980235509508, "grad_norm": 11.013115882873535, "learning_rate": 1.2148699415093443e-06, "loss": 0.7852, "step": 10220 }, { "epoch": 0.06080924443176347, "grad_norm": 14.324472427368164, "learning_rate": 1.2160587759760333e-06, "loss": 0.8512, "step": 10230 }, { "epoch": 0.06086868650843186, "grad_norm": 13.27772331237793, "learning_rate": 1.217247610442722e-06, "loss": 0.8185, "step": 10240 }, { "epoch": 0.06092812858510025, "grad_norm": 10.33281421661377, "learning_rate": 1.218436444909411e-06, "loss": 0.824, "step": 10250 }, { "epoch": 0.06098757066176864, "grad_norm": 12.512171745300293, "learning_rate": 1.2196252793760998e-06, "loss": 0.8202, "step": 10260 }, { "epoch": 0.06104701273843703, "grad_norm": 11.463690757751465, "learning_rate": 1.2208141138427888e-06, "loss": 0.8339, "step": 10270 }, { "epoch": 0.06110645481510542, "grad_norm": 10.55505084991455, "learning_rate": 1.2220029483094775e-06, "loss": 0.8089, "step": 10280 }, { "epoch": 0.06116589689177381, "grad_norm": 12.893736839294434, "learning_rate": 1.2231917827761664e-06, "loss": 0.8033, "step": 10290 }, { "epoch": 0.0612253389684422, "grad_norm": 13.51602554321289, "learning_rate": 1.2243806172428551e-06, "loss": 0.8455, "step": 10300 }, { "epoch": 0.06128478104511059, "grad_norm": 11.198286056518555, "learning_rate": 1.225569451709544e-06, "loss": 0.831, "step": 10310 }, { "epoch": 0.06134422312177898, "grad_norm": 14.183733940124512, "learning_rate": 1.226758286176233e-06, "loss": 0.8933, "step": 10320 }, { "epoch": 0.06140366519844737, "grad_norm": 11.298421859741211, "learning_rate": 1.2279471206429217e-06, "loss": 0.8107, "step": 10330 }, { "epoch": 0.061463107275115766, "grad_norm": 11.489372253417969, "learning_rate": 1.2291359551096106e-06, "loss": 0.8242, "step": 10340 }, { "epoch": 0.06152254935178415, "grad_norm": 15.837382316589355, "learning_rate": 1.2303247895762995e-06, "loss": 0.8377, "step": 10350 }, { "epoch": 0.06158199142845255, "grad_norm": 13.458110809326172, "learning_rate": 1.2315136240429885e-06, "loss": 0.8542, "step": 10360 }, { "epoch": 0.061641433505120934, "grad_norm": 13.440303802490234, "learning_rate": 1.2327024585096772e-06, "loss": 0.8303, "step": 10370 }, { "epoch": 0.06170087558178933, "grad_norm": 10.502853393554688, "learning_rate": 1.2338912929763661e-06, "loss": 0.838, "step": 10380 }, { "epoch": 0.061760317658457714, "grad_norm": 12.957016944885254, "learning_rate": 1.2350801274430548e-06, "loss": 0.778, "step": 10390 }, { "epoch": 0.06181975973512611, "grad_norm": 12.319786071777344, "learning_rate": 1.2362689619097438e-06, "loss": 0.8398, "step": 10400 }, { "epoch": 0.061879201811794494, "grad_norm": 23.223020553588867, "learning_rate": 1.2374577963764327e-06, "loss": 0.8067, "step": 10410 }, { "epoch": 0.06193864388846289, "grad_norm": 9.703057289123535, "learning_rate": 1.2386466308431216e-06, "loss": 0.7895, "step": 10420 }, { "epoch": 0.061998085965131275, "grad_norm": 13.824427604675293, "learning_rate": 1.2398354653098103e-06, "loss": 0.7889, "step": 10430 }, { "epoch": 0.06205752804179967, "grad_norm": 9.559964179992676, "learning_rate": 1.2410242997764993e-06, "loss": 0.8939, "step": 10440 }, { "epoch": 0.06211697011846806, "grad_norm": 13.773104667663574, "learning_rate": 1.2422131342431882e-06, "loss": 0.8391, "step": 10450 }, { "epoch": 0.06217641219513645, "grad_norm": 11.991318702697754, "learning_rate": 1.243401968709877e-06, "loss": 0.8091, "step": 10460 }, { "epoch": 0.06223585427180484, "grad_norm": 12.255025863647461, "learning_rate": 1.2445908031765658e-06, "loss": 0.8312, "step": 10470 }, { "epoch": 0.06229529634847323, "grad_norm": 10.805763244628906, "learning_rate": 1.2457796376432545e-06, "loss": 0.8047, "step": 10480 }, { "epoch": 0.06235473842514162, "grad_norm": 10.063760757446289, "learning_rate": 1.2469684721099435e-06, "loss": 0.8329, "step": 10490 }, { "epoch": 0.06241418050181001, "grad_norm": 12.193222999572754, "learning_rate": 1.2481573065766324e-06, "loss": 0.836, "step": 10500 }, { "epoch": 0.062473622578478404, "grad_norm": 11.56080436706543, "learning_rate": 1.2493461410433213e-06, "loss": 0.8583, "step": 10510 }, { "epoch": 0.0625330646551468, "grad_norm": 14.240971565246582, "learning_rate": 1.2505349755100102e-06, "loss": 0.8356, "step": 10520 }, { "epoch": 0.06259250673181518, "grad_norm": 9.15177059173584, "learning_rate": 1.251723809976699e-06, "loss": 0.8192, "step": 10530 }, { "epoch": 0.06265194880848357, "grad_norm": 12.80333137512207, "learning_rate": 1.2529126444433879e-06, "loss": 0.8417, "step": 10540 }, { "epoch": 0.06271139088515196, "grad_norm": 16.021007537841797, "learning_rate": 1.2541014789100766e-06, "loss": 0.8155, "step": 10550 }, { "epoch": 0.06277083296182036, "grad_norm": 12.738916397094727, "learning_rate": 1.2552903133767655e-06, "loss": 0.8394, "step": 10560 }, { "epoch": 0.06283027503848874, "grad_norm": 11.617696762084961, "learning_rate": 1.2564791478434542e-06, "loss": 0.8364, "step": 10570 }, { "epoch": 0.06288971711515713, "grad_norm": 11.955669403076172, "learning_rate": 1.2576679823101432e-06, "loss": 0.8601, "step": 10580 }, { "epoch": 0.06294915919182553, "grad_norm": 13.630983352661133, "learning_rate": 1.2588568167768319e-06, "loss": 0.7668, "step": 10590 }, { "epoch": 0.06300860126849392, "grad_norm": 10.937896728515625, "learning_rate": 1.260045651243521e-06, "loss": 0.7988, "step": 10600 }, { "epoch": 0.0630680433451623, "grad_norm": 9.909902572631836, "learning_rate": 1.26123448571021e-06, "loss": 0.7511, "step": 10610 }, { "epoch": 0.06312748542183069, "grad_norm": 14.950300216674805, "learning_rate": 1.2624233201768987e-06, "loss": 0.9052, "step": 10620 }, { "epoch": 0.0631869274984991, "grad_norm": 17.075515747070312, "learning_rate": 1.2636121546435876e-06, "loss": 0.8776, "step": 10630 }, { "epoch": 0.06324636957516748, "grad_norm": 13.175007820129395, "learning_rate": 1.2648009891102763e-06, "loss": 0.8518, "step": 10640 }, { "epoch": 0.06330581165183587, "grad_norm": 12.034863471984863, "learning_rate": 1.2659898235769652e-06, "loss": 0.8288, "step": 10650 }, { "epoch": 0.06336525372850425, "grad_norm": 12.300374031066895, "learning_rate": 1.267178658043654e-06, "loss": 0.8481, "step": 10660 }, { "epoch": 0.06342469580517265, "grad_norm": 14.161849975585938, "learning_rate": 1.2683674925103429e-06, "loss": 0.7921, "step": 10670 }, { "epoch": 0.06348413788184104, "grad_norm": 16.359458923339844, "learning_rate": 1.2695563269770316e-06, "loss": 0.8444, "step": 10680 }, { "epoch": 0.06354357995850943, "grad_norm": 9.840282440185547, "learning_rate": 1.2707451614437207e-06, "loss": 0.8088, "step": 10690 }, { "epoch": 0.06360302203517781, "grad_norm": 11.763943672180176, "learning_rate": 1.2719339959104097e-06, "loss": 0.784, "step": 10700 }, { "epoch": 0.06366246411184621, "grad_norm": 13.358327865600586, "learning_rate": 1.2731228303770984e-06, "loss": 0.8092, "step": 10710 }, { "epoch": 0.0637219061885146, "grad_norm": 12.981003761291504, "learning_rate": 1.2743116648437873e-06, "loss": 0.8731, "step": 10720 }, { "epoch": 0.06378134826518299, "grad_norm": 11.14144515991211, "learning_rate": 1.275500499310476e-06, "loss": 0.8525, "step": 10730 }, { "epoch": 0.06384079034185139, "grad_norm": 15.35460376739502, "learning_rate": 1.276689333777165e-06, "loss": 0.8294, "step": 10740 }, { "epoch": 0.06390023241851978, "grad_norm": 12.376595497131348, "learning_rate": 1.2778781682438537e-06, "loss": 0.7969, "step": 10750 }, { "epoch": 0.06395967449518816, "grad_norm": 14.622307777404785, "learning_rate": 1.2790670027105426e-06, "loss": 0.835, "step": 10760 }, { "epoch": 0.06401911657185655, "grad_norm": 12.697535514831543, "learning_rate": 1.2802558371772317e-06, "loss": 0.841, "step": 10770 }, { "epoch": 0.06407855864852495, "grad_norm": 10.911067008972168, "learning_rate": 1.2814446716439205e-06, "loss": 0.8374, "step": 10780 }, { "epoch": 0.06413800072519334, "grad_norm": 11.500226020812988, "learning_rate": 1.2826335061106094e-06, "loss": 0.8313, "step": 10790 }, { "epoch": 0.06419744280186172, "grad_norm": 12.776739120483398, "learning_rate": 1.283822340577298e-06, "loss": 0.7353, "step": 10800 }, { "epoch": 0.06425688487853011, "grad_norm": 11.005033493041992, "learning_rate": 1.285011175043987e-06, "loss": 0.8352, "step": 10810 }, { "epoch": 0.06431632695519851, "grad_norm": 12.155729293823242, "learning_rate": 1.2862000095106757e-06, "loss": 0.8461, "step": 10820 }, { "epoch": 0.0643757690318669, "grad_norm": 16.582855224609375, "learning_rate": 1.2873888439773647e-06, "loss": 0.8531, "step": 10830 }, { "epoch": 0.06443521110853528, "grad_norm": 13.187297821044922, "learning_rate": 1.2885776784440534e-06, "loss": 0.7465, "step": 10840 }, { "epoch": 0.06449465318520368, "grad_norm": 12.73694133758545, "learning_rate": 1.2897665129107423e-06, "loss": 0.9073, "step": 10850 }, { "epoch": 0.06455409526187207, "grad_norm": 10.005401611328125, "learning_rate": 1.2909553473774314e-06, "loss": 0.7923, "step": 10860 }, { "epoch": 0.06461353733854046, "grad_norm": 12.630088806152344, "learning_rate": 1.2921441818441202e-06, "loss": 0.8692, "step": 10870 }, { "epoch": 0.06467297941520884, "grad_norm": 9.675738334655762, "learning_rate": 1.293333016310809e-06, "loss": 0.8351, "step": 10880 }, { "epoch": 0.06473242149187725, "grad_norm": 9.559700965881348, "learning_rate": 1.2945218507774978e-06, "loss": 0.7785, "step": 10890 }, { "epoch": 0.06479186356854563, "grad_norm": 13.01687240600586, "learning_rate": 1.2957106852441867e-06, "loss": 0.8517, "step": 10900 }, { "epoch": 0.06485130564521402, "grad_norm": 13.31812858581543, "learning_rate": 1.2968995197108754e-06, "loss": 0.856, "step": 10910 }, { "epoch": 0.0649107477218824, "grad_norm": 14.826569557189941, "learning_rate": 1.2980883541775644e-06, "loss": 0.8457, "step": 10920 }, { "epoch": 0.0649701897985508, "grad_norm": 14.084064483642578, "learning_rate": 1.299277188644253e-06, "loss": 0.782, "step": 10930 }, { "epoch": 0.0650296318752192, "grad_norm": 12.073341369628906, "learning_rate": 1.3004660231109422e-06, "loss": 0.7697, "step": 10940 }, { "epoch": 0.06508907395188758, "grad_norm": 11.072007179260254, "learning_rate": 1.3016548575776312e-06, "loss": 0.7576, "step": 10950 }, { "epoch": 0.06514851602855598, "grad_norm": 10.032220840454102, "learning_rate": 1.3028436920443199e-06, "loss": 0.7636, "step": 10960 }, { "epoch": 0.06520795810522437, "grad_norm": 14.005084991455078, "learning_rate": 1.3040325265110088e-06, "loss": 0.88, "step": 10970 }, { "epoch": 0.06526740018189275, "grad_norm": 10.981843948364258, "learning_rate": 1.3052213609776975e-06, "loss": 0.7878, "step": 10980 }, { "epoch": 0.06532684225856114, "grad_norm": 12.33231258392334, "learning_rate": 1.3064101954443864e-06, "loss": 0.8072, "step": 10990 }, { "epoch": 0.06538628433522954, "grad_norm": 10.240822792053223, "learning_rate": 1.3075990299110752e-06, "loss": 0.7982, "step": 11000 }, { "epoch": 0.06544572641189793, "grad_norm": 14.083847045898438, "learning_rate": 1.308787864377764e-06, "loss": 0.7991, "step": 11010 }, { "epoch": 0.06550516848856631, "grad_norm": 9.617681503295898, "learning_rate": 1.3099766988444528e-06, "loss": 0.8088, "step": 11020 }, { "epoch": 0.0655646105652347, "grad_norm": 10.617887496948242, "learning_rate": 1.311165533311142e-06, "loss": 0.7827, "step": 11030 }, { "epoch": 0.0656240526419031, "grad_norm": 13.750103950500488, "learning_rate": 1.3123543677778309e-06, "loss": 0.7831, "step": 11040 }, { "epoch": 0.06568349471857149, "grad_norm": 11.40219497680664, "learning_rate": 1.3135432022445196e-06, "loss": 0.837, "step": 11050 }, { "epoch": 0.06574293679523988, "grad_norm": 12.126897811889648, "learning_rate": 1.3147320367112085e-06, "loss": 0.8195, "step": 11060 }, { "epoch": 0.06580237887190826, "grad_norm": 16.88665008544922, "learning_rate": 1.3159208711778972e-06, "loss": 0.8289, "step": 11070 }, { "epoch": 0.06586182094857666, "grad_norm": 11.43383502960205, "learning_rate": 1.3171097056445862e-06, "loss": 0.7725, "step": 11080 }, { "epoch": 0.06592126302524505, "grad_norm": 13.136238098144531, "learning_rate": 1.3182985401112749e-06, "loss": 0.8148, "step": 11090 }, { "epoch": 0.06598070510191344, "grad_norm": 13.634702682495117, "learning_rate": 1.3194873745779638e-06, "loss": 0.8283, "step": 11100 }, { "epoch": 0.06604014717858184, "grad_norm": 15.857647895812988, "learning_rate": 1.3206762090446525e-06, "loss": 0.7903, "step": 11110 }, { "epoch": 0.06609958925525022, "grad_norm": 11.122328758239746, "learning_rate": 1.3218650435113416e-06, "loss": 0.8097, "step": 11120 }, { "epoch": 0.06615903133191861, "grad_norm": 12.292963981628418, "learning_rate": 1.3230538779780306e-06, "loss": 0.7907, "step": 11130 }, { "epoch": 0.066218473408587, "grad_norm": 11.200057983398438, "learning_rate": 1.3242427124447193e-06, "loss": 0.827, "step": 11140 }, { "epoch": 0.0662779154852554, "grad_norm": 12.362607955932617, "learning_rate": 1.3254315469114082e-06, "loss": 0.8205, "step": 11150 }, { "epoch": 0.06633735756192378, "grad_norm": 12.81845760345459, "learning_rate": 1.326620381378097e-06, "loss": 0.8664, "step": 11160 }, { "epoch": 0.06639679963859217, "grad_norm": 9.417350769042969, "learning_rate": 1.3278092158447859e-06, "loss": 0.8539, "step": 11170 }, { "epoch": 0.06645624171526056, "grad_norm": 14.204809188842773, "learning_rate": 1.3289980503114746e-06, "loss": 0.8472, "step": 11180 }, { "epoch": 0.06651568379192896, "grad_norm": 10.82331657409668, "learning_rate": 1.3301868847781635e-06, "loss": 0.7367, "step": 11190 }, { "epoch": 0.06657512586859735, "grad_norm": 12.393436431884766, "learning_rate": 1.3313757192448526e-06, "loss": 0.8394, "step": 11200 }, { "epoch": 0.06663456794526573, "grad_norm": 11.9735107421875, "learning_rate": 1.3325645537115414e-06, "loss": 0.8316, "step": 11210 }, { "epoch": 0.06669401002193413, "grad_norm": 12.514251708984375, "learning_rate": 1.3337533881782303e-06, "loss": 0.8355, "step": 11220 }, { "epoch": 0.06675345209860252, "grad_norm": 10.44293212890625, "learning_rate": 1.334942222644919e-06, "loss": 0.8118, "step": 11230 }, { "epoch": 0.0668128941752709, "grad_norm": 13.523613929748535, "learning_rate": 1.336131057111608e-06, "loss": 0.7773, "step": 11240 }, { "epoch": 0.0668723362519393, "grad_norm": 14.958667755126953, "learning_rate": 1.3373198915782966e-06, "loss": 0.8158, "step": 11250 }, { "epoch": 0.0669317783286077, "grad_norm": 11.606523513793945, "learning_rate": 1.3385087260449856e-06, "loss": 0.9309, "step": 11260 }, { "epoch": 0.06699122040527608, "grad_norm": 12.027214050292969, "learning_rate": 1.3396975605116743e-06, "loss": 0.7703, "step": 11270 }, { "epoch": 0.06705066248194447, "grad_norm": 11.581665992736816, "learning_rate": 1.3408863949783632e-06, "loss": 0.7682, "step": 11280 }, { "epoch": 0.06711010455861285, "grad_norm": 11.83003044128418, "learning_rate": 1.3420752294450524e-06, "loss": 0.811, "step": 11290 }, { "epoch": 0.06716954663528125, "grad_norm": 11.551553726196289, "learning_rate": 1.343264063911741e-06, "loss": 0.7974, "step": 11300 }, { "epoch": 0.06722898871194964, "grad_norm": 11.335556030273438, "learning_rate": 1.34445289837843e-06, "loss": 0.7785, "step": 11310 }, { "epoch": 0.06728843078861803, "grad_norm": 12.817081451416016, "learning_rate": 1.3456417328451187e-06, "loss": 0.8179, "step": 11320 }, { "epoch": 0.06734787286528642, "grad_norm": 10.149189949035645, "learning_rate": 1.3468305673118076e-06, "loss": 0.7947, "step": 11330 }, { "epoch": 0.06740731494195482, "grad_norm": 15.709944725036621, "learning_rate": 1.3480194017784964e-06, "loss": 0.8607, "step": 11340 }, { "epoch": 0.0674667570186232, "grad_norm": 15.270918846130371, "learning_rate": 1.3492082362451853e-06, "loss": 0.8067, "step": 11350 }, { "epoch": 0.06752619909529159, "grad_norm": 11.436166763305664, "learning_rate": 1.350397070711874e-06, "loss": 0.7714, "step": 11360 }, { "epoch": 0.06758564117195999, "grad_norm": 10.822673797607422, "learning_rate": 1.351585905178563e-06, "loss": 0.7901, "step": 11370 }, { "epoch": 0.06764508324862838, "grad_norm": 12.373019218444824, "learning_rate": 1.352774739645252e-06, "loss": 0.7955, "step": 11380 }, { "epoch": 0.06770452532529676, "grad_norm": 12.724396705627441, "learning_rate": 1.3539635741119408e-06, "loss": 0.8691, "step": 11390 }, { "epoch": 0.06776396740196515, "grad_norm": 13.7724027633667, "learning_rate": 1.3551524085786297e-06, "loss": 0.7732, "step": 11400 }, { "epoch": 0.06782340947863355, "grad_norm": 12.270148277282715, "learning_rate": 1.3563412430453184e-06, "loss": 0.801, "step": 11410 }, { "epoch": 0.06788285155530194, "grad_norm": 9.870043754577637, "learning_rate": 1.3575300775120074e-06, "loss": 0.7288, "step": 11420 }, { "epoch": 0.06794229363197032, "grad_norm": 11.900505065917969, "learning_rate": 1.358718911978696e-06, "loss": 0.8111, "step": 11430 }, { "epoch": 0.06800173570863871, "grad_norm": 13.82835578918457, "learning_rate": 1.359907746445385e-06, "loss": 0.8752, "step": 11440 }, { "epoch": 0.06806117778530711, "grad_norm": 13.017951011657715, "learning_rate": 1.3610965809120737e-06, "loss": 0.7855, "step": 11450 }, { "epoch": 0.0681206198619755, "grad_norm": 12.898061752319336, "learning_rate": 1.3622854153787628e-06, "loss": 0.7889, "step": 11460 }, { "epoch": 0.06818006193864388, "grad_norm": 10.801190376281738, "learning_rate": 1.3634742498454518e-06, "loss": 0.7718, "step": 11470 }, { "epoch": 0.06823950401531229, "grad_norm": 9.348177909851074, "learning_rate": 1.3646630843121405e-06, "loss": 0.7962, "step": 11480 }, { "epoch": 0.06829894609198067, "grad_norm": 11.280695915222168, "learning_rate": 1.3658519187788294e-06, "loss": 0.8438, "step": 11490 }, { "epoch": 0.06835838816864906, "grad_norm": 8.681928634643555, "learning_rate": 1.3670407532455181e-06, "loss": 0.8876, "step": 11500 }, { "epoch": 0.06841783024531745, "grad_norm": 11.06479549407959, "learning_rate": 1.368229587712207e-06, "loss": 0.7923, "step": 11510 }, { "epoch": 0.06847727232198585, "grad_norm": 13.787932395935059, "learning_rate": 1.3694184221788958e-06, "loss": 0.7697, "step": 11520 }, { "epoch": 0.06853671439865423, "grad_norm": 12.465194702148438, "learning_rate": 1.3706072566455847e-06, "loss": 0.815, "step": 11530 }, { "epoch": 0.06859615647532262, "grad_norm": 10.815028190612793, "learning_rate": 1.3717960911122734e-06, "loss": 0.7547, "step": 11540 }, { "epoch": 0.068655598551991, "grad_norm": 11.784387588500977, "learning_rate": 1.3729849255789626e-06, "loss": 0.8561, "step": 11550 }, { "epoch": 0.06871504062865941, "grad_norm": 12.751490592956543, "learning_rate": 1.3741737600456515e-06, "loss": 0.7899, "step": 11560 }, { "epoch": 0.0687744827053278, "grad_norm": 13.427349090576172, "learning_rate": 1.3753625945123402e-06, "loss": 0.8351, "step": 11570 }, { "epoch": 0.06883392478199618, "grad_norm": 11.207574844360352, "learning_rate": 1.3765514289790291e-06, "loss": 0.8173, "step": 11580 }, { "epoch": 0.06889336685866457, "grad_norm": 12.056352615356445, "learning_rate": 1.3777402634457178e-06, "loss": 0.8341, "step": 11590 }, { "epoch": 0.06895280893533297, "grad_norm": 11.304752349853516, "learning_rate": 1.3789290979124068e-06, "loss": 0.8412, "step": 11600 }, { "epoch": 0.06901225101200135, "grad_norm": 11.209239959716797, "learning_rate": 1.3801179323790955e-06, "loss": 0.7866, "step": 11610 }, { "epoch": 0.06907169308866974, "grad_norm": 11.540257453918457, "learning_rate": 1.3813067668457844e-06, "loss": 0.7792, "step": 11620 }, { "epoch": 0.06913113516533814, "grad_norm": 10.00740909576416, "learning_rate": 1.3824956013124731e-06, "loss": 0.8471, "step": 11630 }, { "epoch": 0.06919057724200653, "grad_norm": 10.469199180603027, "learning_rate": 1.3836844357791623e-06, "loss": 0.869, "step": 11640 }, { "epoch": 0.06925001931867492, "grad_norm": 13.567861557006836, "learning_rate": 1.3848732702458512e-06, "loss": 0.8269, "step": 11650 }, { "epoch": 0.0693094613953433, "grad_norm": 14.633094787597656, "learning_rate": 1.38606210471254e-06, "loss": 0.7747, "step": 11660 }, { "epoch": 0.0693689034720117, "grad_norm": 10.64389705657959, "learning_rate": 1.3872509391792288e-06, "loss": 0.8053, "step": 11670 }, { "epoch": 0.06942834554868009, "grad_norm": 11.01866340637207, "learning_rate": 1.3884397736459176e-06, "loss": 0.7494, "step": 11680 }, { "epoch": 0.06948778762534848, "grad_norm": 12.459944725036621, "learning_rate": 1.3896286081126065e-06, "loss": 0.7671, "step": 11690 }, { "epoch": 0.06954722970201686, "grad_norm": 11.975092887878418, "learning_rate": 1.3908174425792952e-06, "loss": 0.7569, "step": 11700 }, { "epoch": 0.06960667177868526, "grad_norm": 13.119733810424805, "learning_rate": 1.3920062770459841e-06, "loss": 0.7948, "step": 11710 }, { "epoch": 0.06966611385535365, "grad_norm": 13.892199516296387, "learning_rate": 1.3931951115126733e-06, "loss": 0.8516, "step": 11720 }, { "epoch": 0.06972555593202204, "grad_norm": 11.743642807006836, "learning_rate": 1.394383945979362e-06, "loss": 0.7782, "step": 11730 }, { "epoch": 0.06978499800869044, "grad_norm": 10.584781646728516, "learning_rate": 1.395572780446051e-06, "loss": 0.8118, "step": 11740 }, { "epoch": 0.06984444008535882, "grad_norm": 11.7501802444458, "learning_rate": 1.3967616149127396e-06, "loss": 0.7441, "step": 11750 }, { "epoch": 0.06990388216202721, "grad_norm": 11.408631324768066, "learning_rate": 1.3979504493794285e-06, "loss": 0.7626, "step": 11760 }, { "epoch": 0.0699633242386956, "grad_norm": 10.392009735107422, "learning_rate": 1.3991392838461173e-06, "loss": 0.8027, "step": 11770 }, { "epoch": 0.070022766315364, "grad_norm": 11.300745010375977, "learning_rate": 1.4003281183128062e-06, "loss": 0.7548, "step": 11780 }, { "epoch": 0.07008220839203239, "grad_norm": 12.243111610412598, "learning_rate": 1.401516952779495e-06, "loss": 0.7611, "step": 11790 }, { "epoch": 0.07014165046870077, "grad_norm": 12.171266555786133, "learning_rate": 1.4027057872461838e-06, "loss": 0.7884, "step": 11800 }, { "epoch": 0.07020109254536916, "grad_norm": 12.11938762664795, "learning_rate": 1.403894621712873e-06, "loss": 0.8425, "step": 11810 }, { "epoch": 0.07026053462203756, "grad_norm": 11.795694351196289, "learning_rate": 1.4050834561795617e-06, "loss": 0.8315, "step": 11820 }, { "epoch": 0.07031997669870595, "grad_norm": 10.211243629455566, "learning_rate": 1.4062722906462506e-06, "loss": 0.8057, "step": 11830 }, { "epoch": 0.07037941877537433, "grad_norm": 13.127457618713379, "learning_rate": 1.4074611251129393e-06, "loss": 0.7833, "step": 11840 }, { "epoch": 0.07043886085204272, "grad_norm": 12.192931175231934, "learning_rate": 1.4086499595796283e-06, "loss": 0.7585, "step": 11850 }, { "epoch": 0.07049830292871112, "grad_norm": 13.29451847076416, "learning_rate": 1.409838794046317e-06, "loss": 0.8727, "step": 11860 }, { "epoch": 0.07055774500537951, "grad_norm": 13.11087703704834, "learning_rate": 1.411027628513006e-06, "loss": 0.7942, "step": 11870 }, { "epoch": 0.0706171870820479, "grad_norm": 10.887699127197266, "learning_rate": 1.4122164629796948e-06, "loss": 0.8092, "step": 11880 }, { "epoch": 0.0706766291587163, "grad_norm": 10.769807815551758, "learning_rate": 1.4134052974463835e-06, "loss": 0.8361, "step": 11890 }, { "epoch": 0.07073607123538468, "grad_norm": 11.106294631958008, "learning_rate": 1.4145941319130727e-06, "loss": 0.8387, "step": 11900 }, { "epoch": 0.07079551331205307, "grad_norm": 16.543432235717773, "learning_rate": 1.4157829663797614e-06, "loss": 0.8147, "step": 11910 }, { "epoch": 0.07085495538872146, "grad_norm": 13.697129249572754, "learning_rate": 1.4169718008464503e-06, "loss": 0.8223, "step": 11920 }, { "epoch": 0.07091439746538986, "grad_norm": 14.331768989562988, "learning_rate": 1.418160635313139e-06, "loss": 0.8217, "step": 11930 }, { "epoch": 0.07097383954205824, "grad_norm": 10.14820671081543, "learning_rate": 1.419349469779828e-06, "loss": 0.7976, "step": 11940 }, { "epoch": 0.07103328161872663, "grad_norm": 11.438363075256348, "learning_rate": 1.4205383042465167e-06, "loss": 0.7827, "step": 11950 }, { "epoch": 0.07109272369539502, "grad_norm": 10.84823989868164, "learning_rate": 1.4217271387132056e-06, "loss": 0.7469, "step": 11960 }, { "epoch": 0.07115216577206342, "grad_norm": 11.02966022491455, "learning_rate": 1.4229159731798945e-06, "loss": 0.8526, "step": 11970 }, { "epoch": 0.0712116078487318, "grad_norm": 10.860745429992676, "learning_rate": 1.4241048076465835e-06, "loss": 0.7869, "step": 11980 }, { "epoch": 0.07127104992540019, "grad_norm": 12.662668228149414, "learning_rate": 1.4252936421132724e-06, "loss": 0.791, "step": 11990 }, { "epoch": 0.07133049200206859, "grad_norm": 12.087835311889648, "learning_rate": 1.4264824765799611e-06, "loss": 0.8394, "step": 12000 }, { "epoch": 0.07138993407873698, "grad_norm": 12.02946949005127, "learning_rate": 1.42767131104665e-06, "loss": 0.8069, "step": 12010 }, { "epoch": 0.07144937615540536, "grad_norm": 14.347474098205566, "learning_rate": 1.4288601455133388e-06, "loss": 0.8295, "step": 12020 }, { "epoch": 0.07150881823207375, "grad_norm": 13.493051528930664, "learning_rate": 1.4300489799800277e-06, "loss": 0.864, "step": 12030 }, { "epoch": 0.07156826030874215, "grad_norm": 11.628366470336914, "learning_rate": 1.4312378144467164e-06, "loss": 0.7762, "step": 12040 }, { "epoch": 0.07162770238541054, "grad_norm": 10.963496208190918, "learning_rate": 1.4324266489134053e-06, "loss": 0.803, "step": 12050 }, { "epoch": 0.07168714446207892, "grad_norm": 12.504317283630371, "learning_rate": 1.4336154833800943e-06, "loss": 0.8241, "step": 12060 }, { "epoch": 0.07174658653874731, "grad_norm": 13.062060356140137, "learning_rate": 1.4348043178467832e-06, "loss": 0.8263, "step": 12070 }, { "epoch": 0.07180602861541571, "grad_norm": 12.827967643737793, "learning_rate": 1.435993152313472e-06, "loss": 0.7595, "step": 12080 }, { "epoch": 0.0718654706920841, "grad_norm": 11.485897064208984, "learning_rate": 1.4371819867801608e-06, "loss": 0.8125, "step": 12090 }, { "epoch": 0.07192491276875249, "grad_norm": 11.963912010192871, "learning_rate": 1.4383708212468497e-06, "loss": 0.8296, "step": 12100 }, { "epoch": 0.07198435484542089, "grad_norm": 10.856389999389648, "learning_rate": 1.4395596557135385e-06, "loss": 0.824, "step": 12110 }, { "epoch": 0.07204379692208927, "grad_norm": 11.443009376525879, "learning_rate": 1.4407484901802274e-06, "loss": 0.8013, "step": 12120 }, { "epoch": 0.07210323899875766, "grad_norm": 12.14259147644043, "learning_rate": 1.4419373246469163e-06, "loss": 0.8567, "step": 12130 }, { "epoch": 0.07216268107542605, "grad_norm": 15.277798652648926, "learning_rate": 1.443126159113605e-06, "loss": 0.8077, "step": 12140 }, { "epoch": 0.07222212315209445, "grad_norm": 13.667448043823242, "learning_rate": 1.444314993580294e-06, "loss": 0.7985, "step": 12150 }, { "epoch": 0.07228156522876283, "grad_norm": 11.996969223022461, "learning_rate": 1.4455038280469829e-06, "loss": 0.7945, "step": 12160 }, { "epoch": 0.07234100730543122, "grad_norm": 16.943092346191406, "learning_rate": 1.4466926625136718e-06, "loss": 0.8234, "step": 12170 }, { "epoch": 0.07240044938209961, "grad_norm": 11.944931983947754, "learning_rate": 1.4478814969803605e-06, "loss": 0.7573, "step": 12180 }, { "epoch": 0.07245989145876801, "grad_norm": 12.254921913146973, "learning_rate": 1.4490703314470495e-06, "loss": 0.8295, "step": 12190 }, { "epoch": 0.0725193335354364, "grad_norm": 10.709857940673828, "learning_rate": 1.4502591659137382e-06, "loss": 0.8901, "step": 12200 }, { "epoch": 0.07257877561210478, "grad_norm": 12.129971504211426, "learning_rate": 1.451448000380427e-06, "loss": 0.753, "step": 12210 }, { "epoch": 0.07263821768877317, "grad_norm": 12.056553840637207, "learning_rate": 1.452636834847116e-06, "loss": 0.7907, "step": 12220 }, { "epoch": 0.07269765976544157, "grad_norm": 12.296195030212402, "learning_rate": 1.4538256693138047e-06, "loss": 0.7783, "step": 12230 }, { "epoch": 0.07275710184210996, "grad_norm": 12.341902732849121, "learning_rate": 1.4550145037804939e-06, "loss": 0.8309, "step": 12240 }, { "epoch": 0.07281654391877834, "grad_norm": 11.33187484741211, "learning_rate": 1.4562033382471826e-06, "loss": 0.7808, "step": 12250 }, { "epoch": 0.07287598599544674, "grad_norm": 10.610494613647461, "learning_rate": 1.4573921727138715e-06, "loss": 0.7636, "step": 12260 }, { "epoch": 0.07293542807211513, "grad_norm": 13.542511940002441, "learning_rate": 1.4585810071805602e-06, "loss": 0.7597, "step": 12270 }, { "epoch": 0.07299487014878352, "grad_norm": 12.218446731567383, "learning_rate": 1.4597698416472492e-06, "loss": 0.7877, "step": 12280 }, { "epoch": 0.0730543122254519, "grad_norm": 10.841349601745605, "learning_rate": 1.4609586761139379e-06, "loss": 0.825, "step": 12290 }, { "epoch": 0.0731137543021203, "grad_norm": 12.836223602294922, "learning_rate": 1.4621475105806268e-06, "loss": 0.8042, "step": 12300 }, { "epoch": 0.07317319637878869, "grad_norm": 13.424779891967773, "learning_rate": 1.4633363450473157e-06, "loss": 0.7902, "step": 12310 }, { "epoch": 0.07323263845545708, "grad_norm": 13.034708023071289, "learning_rate": 1.4645251795140045e-06, "loss": 0.7739, "step": 12320 }, { "epoch": 0.07329208053212546, "grad_norm": 11.471393585205078, "learning_rate": 1.4657140139806936e-06, "loss": 0.8362, "step": 12330 }, { "epoch": 0.07335152260879386, "grad_norm": 12.449387550354004, "learning_rate": 1.4669028484473823e-06, "loss": 0.767, "step": 12340 }, { "epoch": 0.07341096468546225, "grad_norm": 13.144729614257812, "learning_rate": 1.4680916829140712e-06, "loss": 0.8261, "step": 12350 }, { "epoch": 0.07347040676213064, "grad_norm": 11.123151779174805, "learning_rate": 1.46928051738076e-06, "loss": 0.8502, "step": 12360 }, { "epoch": 0.07352984883879904, "grad_norm": 12.060873985290527, "learning_rate": 1.4704693518474489e-06, "loss": 0.8188, "step": 12370 }, { "epoch": 0.07358929091546743, "grad_norm": 10.584884643554688, "learning_rate": 1.4716581863141378e-06, "loss": 0.78, "step": 12380 }, { "epoch": 0.07364873299213581, "grad_norm": 11.348241806030273, "learning_rate": 1.4728470207808265e-06, "loss": 0.8027, "step": 12390 }, { "epoch": 0.0737081750688042, "grad_norm": 12.445581436157227, "learning_rate": 1.4740358552475154e-06, "loss": 0.8161, "step": 12400 }, { "epoch": 0.0737676171454726, "grad_norm": 12.308743476867676, "learning_rate": 1.4752246897142042e-06, "loss": 0.7547, "step": 12410 }, { "epoch": 0.07382705922214099, "grad_norm": 13.282023429870605, "learning_rate": 1.4764135241808933e-06, "loss": 0.8036, "step": 12420 }, { "epoch": 0.07388650129880937, "grad_norm": 14.51623821258545, "learning_rate": 1.477602358647582e-06, "loss": 0.823, "step": 12430 }, { "epoch": 0.07394594337547776, "grad_norm": 12.984891891479492, "learning_rate": 1.478791193114271e-06, "loss": 0.8074, "step": 12440 }, { "epoch": 0.07400538545214616, "grad_norm": 10.865882873535156, "learning_rate": 1.4799800275809597e-06, "loss": 0.7984, "step": 12450 }, { "epoch": 0.07406482752881455, "grad_norm": 10.607894897460938, "learning_rate": 1.4811688620476486e-06, "loss": 0.7805, "step": 12460 }, { "epoch": 0.07412426960548293, "grad_norm": 13.542830467224121, "learning_rate": 1.4823576965143375e-06, "loss": 0.8402, "step": 12470 }, { "epoch": 0.07418371168215132, "grad_norm": 12.898717880249023, "learning_rate": 1.4835465309810262e-06, "loss": 0.8034, "step": 12480 }, { "epoch": 0.07424315375881972, "grad_norm": 12.943243980407715, "learning_rate": 1.4847353654477152e-06, "loss": 0.8412, "step": 12490 }, { "epoch": 0.07430259583548811, "grad_norm": 9.858495712280273, "learning_rate": 1.485924199914404e-06, "loss": 0.7366, "step": 12500 }, { "epoch": 0.0743620379121565, "grad_norm": 13.549115180969238, "learning_rate": 1.487113034381093e-06, "loss": 0.7183, "step": 12510 }, { "epoch": 0.0744214799888249, "grad_norm": 12.93809700012207, "learning_rate": 1.4883018688477817e-06, "loss": 0.8417, "step": 12520 }, { "epoch": 0.07448092206549328, "grad_norm": 11.62938404083252, "learning_rate": 1.4894907033144707e-06, "loss": 0.8439, "step": 12530 }, { "epoch": 0.07454036414216167, "grad_norm": 9.811042785644531, "learning_rate": 1.4906795377811596e-06, "loss": 0.8103, "step": 12540 }, { "epoch": 0.07459980621883006, "grad_norm": 12.128422737121582, "learning_rate": 1.4918683722478483e-06, "loss": 0.8181, "step": 12550 }, { "epoch": 0.07465924829549846, "grad_norm": 8.89682674407959, "learning_rate": 1.4930572067145372e-06, "loss": 0.7235, "step": 12560 }, { "epoch": 0.07471869037216684, "grad_norm": 10.702823638916016, "learning_rate": 1.494246041181226e-06, "loss": 0.8422, "step": 12570 }, { "epoch": 0.07477813244883523, "grad_norm": 8.37074089050293, "learning_rate": 1.4954348756479149e-06, "loss": 0.7524, "step": 12580 }, { "epoch": 0.07483757452550362, "grad_norm": 12.439291954040527, "learning_rate": 1.4966237101146038e-06, "loss": 0.7729, "step": 12590 }, { "epoch": 0.07489701660217202, "grad_norm": 10.267914772033691, "learning_rate": 1.4978125445812927e-06, "loss": 0.8377, "step": 12600 }, { "epoch": 0.0749564586788404, "grad_norm": 11.115825653076172, "learning_rate": 1.4990013790479814e-06, "loss": 0.787, "step": 12610 }, { "epoch": 0.07501590075550879, "grad_norm": 10.238913536071777, "learning_rate": 1.5001902135146704e-06, "loss": 0.7586, "step": 12620 }, { "epoch": 0.07507534283217719, "grad_norm": 12.938736915588379, "learning_rate": 1.5013790479813593e-06, "loss": 0.7684, "step": 12630 }, { "epoch": 0.07513478490884558, "grad_norm": 12.143329620361328, "learning_rate": 1.502567882448048e-06, "loss": 0.816, "step": 12640 }, { "epoch": 0.07519422698551397, "grad_norm": 12.617818832397461, "learning_rate": 1.503756716914737e-06, "loss": 0.8295, "step": 12650 }, { "epoch": 0.07525366906218235, "grad_norm": 9.909658432006836, "learning_rate": 1.5049455513814257e-06, "loss": 0.7054, "step": 12660 }, { "epoch": 0.07531311113885075, "grad_norm": 10.451879501342773, "learning_rate": 1.5061343858481146e-06, "loss": 0.8029, "step": 12670 }, { "epoch": 0.07537255321551914, "grad_norm": 12.582000732421875, "learning_rate": 1.5073232203148035e-06, "loss": 0.8301, "step": 12680 }, { "epoch": 0.07543199529218753, "grad_norm": 11.840057373046875, "learning_rate": 1.5085120547814924e-06, "loss": 0.8163, "step": 12690 }, { "epoch": 0.07549143736885591, "grad_norm": 12.22679328918457, "learning_rate": 1.5097008892481812e-06, "loss": 0.8153, "step": 12700 }, { "epoch": 0.07555087944552431, "grad_norm": 17.221054077148438, "learning_rate": 1.51088972371487e-06, "loss": 0.8385, "step": 12710 }, { "epoch": 0.0756103215221927, "grad_norm": 14.191585540771484, "learning_rate": 1.512078558181559e-06, "loss": 0.7719, "step": 12720 }, { "epoch": 0.07566976359886109, "grad_norm": 11.459639549255371, "learning_rate": 1.5132673926482477e-06, "loss": 0.7566, "step": 12730 }, { "epoch": 0.07572920567552947, "grad_norm": 10.84196949005127, "learning_rate": 1.5144562271149366e-06, "loss": 0.742, "step": 12740 }, { "epoch": 0.07578864775219787, "grad_norm": 12.713876724243164, "learning_rate": 1.5156450615816254e-06, "loss": 0.8173, "step": 12750 }, { "epoch": 0.07584808982886626, "grad_norm": 11.774238586425781, "learning_rate": 1.5168338960483145e-06, "loss": 0.7822, "step": 12760 }, { "epoch": 0.07590753190553465, "grad_norm": 11.659507751464844, "learning_rate": 1.5180227305150032e-06, "loss": 0.7996, "step": 12770 }, { "epoch": 0.07596697398220305, "grad_norm": 12.0324068069458, "learning_rate": 1.5192115649816921e-06, "loss": 0.8125, "step": 12780 }, { "epoch": 0.07602641605887143, "grad_norm": 11.979753494262695, "learning_rate": 1.520400399448381e-06, "loss": 0.791, "step": 12790 }, { "epoch": 0.07608585813553982, "grad_norm": 14.129213333129883, "learning_rate": 1.5215892339150698e-06, "loss": 0.7428, "step": 12800 }, { "epoch": 0.07614530021220821, "grad_norm": 10.625951766967773, "learning_rate": 1.5227780683817587e-06, "loss": 0.7873, "step": 12810 }, { "epoch": 0.07620474228887661, "grad_norm": 10.909356117248535, "learning_rate": 1.5239669028484474e-06, "loss": 0.8032, "step": 12820 }, { "epoch": 0.076264184365545, "grad_norm": 11.201271057128906, "learning_rate": 1.5251557373151364e-06, "loss": 0.7769, "step": 12830 }, { "epoch": 0.07632362644221338, "grad_norm": 10.478955268859863, "learning_rate": 1.526344571781825e-06, "loss": 0.7969, "step": 12840 }, { "epoch": 0.07638306851888177, "grad_norm": 9.787850379943848, "learning_rate": 1.5275334062485142e-06, "loss": 0.7464, "step": 12850 }, { "epoch": 0.07644251059555017, "grad_norm": 9.388394355773926, "learning_rate": 1.528722240715203e-06, "loss": 0.7874, "step": 12860 }, { "epoch": 0.07650195267221856, "grad_norm": 11.845803260803223, "learning_rate": 1.5299110751818919e-06, "loss": 0.7823, "step": 12870 }, { "epoch": 0.07656139474888694, "grad_norm": 12.33059310913086, "learning_rate": 1.5310999096485808e-06, "loss": 0.7312, "step": 12880 }, { "epoch": 0.07662083682555534, "grad_norm": 10.048501014709473, "learning_rate": 1.5322887441152695e-06, "loss": 0.8254, "step": 12890 }, { "epoch": 0.07668027890222373, "grad_norm": 11.84573745727539, "learning_rate": 1.5334775785819584e-06, "loss": 0.8492, "step": 12900 }, { "epoch": 0.07673972097889212, "grad_norm": 10.978038787841797, "learning_rate": 1.5346664130486471e-06, "loss": 0.857, "step": 12910 }, { "epoch": 0.0767991630555605, "grad_norm": 12.051226615905762, "learning_rate": 1.535855247515336e-06, "loss": 0.8314, "step": 12920 }, { "epoch": 0.0768586051322289, "grad_norm": 12.466090202331543, "learning_rate": 1.5370440819820248e-06, "loss": 0.8039, "step": 12930 }, { "epoch": 0.07691804720889729, "grad_norm": 9.344343185424805, "learning_rate": 1.538232916448714e-06, "loss": 0.8306, "step": 12940 }, { "epoch": 0.07697748928556568, "grad_norm": 12.410852432250977, "learning_rate": 1.5394217509154029e-06, "loss": 0.7809, "step": 12950 }, { "epoch": 0.07703693136223407, "grad_norm": 11.860428810119629, "learning_rate": 1.5406105853820916e-06, "loss": 0.7615, "step": 12960 }, { "epoch": 0.07709637343890247, "grad_norm": 12.1337308883667, "learning_rate": 1.5417994198487805e-06, "loss": 0.7471, "step": 12970 }, { "epoch": 0.07715581551557085, "grad_norm": 10.724246978759766, "learning_rate": 1.5429882543154692e-06, "loss": 0.77, "step": 12980 }, { "epoch": 0.07721525759223924, "grad_norm": 12.767303466796875, "learning_rate": 1.5441770887821581e-06, "loss": 0.811, "step": 12990 }, { "epoch": 0.07727469966890764, "grad_norm": 11.00566577911377, "learning_rate": 1.5453659232488469e-06, "loss": 0.8378, "step": 13000 }, { "epoch": 0.07733414174557603, "grad_norm": 10.773049354553223, "learning_rate": 1.5465547577155358e-06, "loss": 0.8236, "step": 13010 }, { "epoch": 0.07739358382224441, "grad_norm": 14.157041549682617, "learning_rate": 1.5477435921822247e-06, "loss": 0.7945, "step": 13020 }, { "epoch": 0.0774530258989128, "grad_norm": 14.239787101745605, "learning_rate": 1.5489324266489136e-06, "loss": 0.7933, "step": 13030 }, { "epoch": 0.0775124679755812, "grad_norm": 13.85063362121582, "learning_rate": 1.5501212611156026e-06, "loss": 0.7775, "step": 13040 }, { "epoch": 0.07757191005224959, "grad_norm": 10.278871536254883, "learning_rate": 1.5513100955822913e-06, "loss": 0.8372, "step": 13050 }, { "epoch": 0.07763135212891797, "grad_norm": 12.734865188598633, "learning_rate": 1.5524989300489802e-06, "loss": 0.7594, "step": 13060 }, { "epoch": 0.07769079420558636, "grad_norm": 13.624369621276855, "learning_rate": 1.553687764515669e-06, "loss": 0.7624, "step": 13070 }, { "epoch": 0.07775023628225476, "grad_norm": 11.88975715637207, "learning_rate": 1.5548765989823578e-06, "loss": 0.7842, "step": 13080 }, { "epoch": 0.07780967835892315, "grad_norm": 11.644332885742188, "learning_rate": 1.5560654334490466e-06, "loss": 0.8183, "step": 13090 }, { "epoch": 0.07786912043559154, "grad_norm": 10.995460510253906, "learning_rate": 1.5572542679157355e-06, "loss": 0.8086, "step": 13100 }, { "epoch": 0.07792856251225992, "grad_norm": 10.276745796203613, "learning_rate": 1.5584431023824244e-06, "loss": 0.7462, "step": 13110 }, { "epoch": 0.07798800458892832, "grad_norm": 11.486322402954102, "learning_rate": 1.5596319368491133e-06, "loss": 0.7872, "step": 13120 }, { "epoch": 0.07804744666559671, "grad_norm": 11.908306121826172, "learning_rate": 1.5608207713158023e-06, "loss": 0.8245, "step": 13130 }, { "epoch": 0.0781068887422651, "grad_norm": 11.67347240447998, "learning_rate": 1.562009605782491e-06, "loss": 0.8389, "step": 13140 }, { "epoch": 0.0781663308189335, "grad_norm": 9.809680938720703, "learning_rate": 1.56319844024918e-06, "loss": 0.8439, "step": 13150 }, { "epoch": 0.07822577289560188, "grad_norm": 12.720868110656738, "learning_rate": 1.5643872747158686e-06, "loss": 0.7819, "step": 13160 }, { "epoch": 0.07828521497227027, "grad_norm": 11.901812553405762, "learning_rate": 1.5655761091825576e-06, "loss": 0.7601, "step": 13170 }, { "epoch": 0.07834465704893866, "grad_norm": 11.235091209411621, "learning_rate": 1.5667649436492463e-06, "loss": 0.7829, "step": 13180 }, { "epoch": 0.07840409912560706, "grad_norm": 12.522520065307617, "learning_rate": 1.5679537781159352e-06, "loss": 0.7466, "step": 13190 }, { "epoch": 0.07846354120227544, "grad_norm": 9.696846008300781, "learning_rate": 1.5691426125826243e-06, "loss": 0.8088, "step": 13200 }, { "epoch": 0.07852298327894383, "grad_norm": 14.032525062561035, "learning_rate": 1.570331447049313e-06, "loss": 0.7676, "step": 13210 }, { "epoch": 0.07858242535561222, "grad_norm": 11.507668495178223, "learning_rate": 1.571520281516002e-06, "loss": 0.7487, "step": 13220 }, { "epoch": 0.07864186743228062, "grad_norm": 13.564802169799805, "learning_rate": 1.5727091159826907e-06, "loss": 0.8396, "step": 13230 }, { "epoch": 0.078701309508949, "grad_norm": 11.321965217590332, "learning_rate": 1.5738979504493796e-06, "loss": 0.8226, "step": 13240 }, { "epoch": 0.07876075158561739, "grad_norm": 11.143828392028809, "learning_rate": 1.5750867849160683e-06, "loss": 0.7821, "step": 13250 }, { "epoch": 0.07882019366228579, "grad_norm": 14.449970245361328, "learning_rate": 1.5762756193827573e-06, "loss": 0.8393, "step": 13260 }, { "epoch": 0.07887963573895418, "grad_norm": 11.111254692077637, "learning_rate": 1.577464453849446e-06, "loss": 0.753, "step": 13270 }, { "epoch": 0.07893907781562257, "grad_norm": 10.981485366821289, "learning_rate": 1.5786532883161351e-06, "loss": 0.7896, "step": 13280 }, { "epoch": 0.07899851989229095, "grad_norm": 12.429183959960938, "learning_rate": 1.579842122782824e-06, "loss": 0.8129, "step": 13290 }, { "epoch": 0.07905796196895935, "grad_norm": 11.675193786621094, "learning_rate": 1.5810309572495128e-06, "loss": 0.7975, "step": 13300 }, { "epoch": 0.07911740404562774, "grad_norm": 11.459994316101074, "learning_rate": 1.5822197917162017e-06, "loss": 0.7813, "step": 13310 }, { "epoch": 0.07917684612229613, "grad_norm": 10.674562454223633, "learning_rate": 1.5834086261828904e-06, "loss": 0.759, "step": 13320 }, { "epoch": 0.07923628819896451, "grad_norm": 13.84610652923584, "learning_rate": 1.5845974606495793e-06, "loss": 0.8116, "step": 13330 }, { "epoch": 0.07929573027563291, "grad_norm": 11.709120750427246, "learning_rate": 1.585786295116268e-06, "loss": 0.7822, "step": 13340 }, { "epoch": 0.0793551723523013, "grad_norm": 11.524577140808105, "learning_rate": 1.586975129582957e-06, "loss": 0.7871, "step": 13350 }, { "epoch": 0.07941461442896969, "grad_norm": 11.728659629821777, "learning_rate": 1.5881639640496457e-06, "loss": 0.7811, "step": 13360 }, { "epoch": 0.07947405650563807, "grad_norm": 11.610160827636719, "learning_rate": 1.5893527985163348e-06, "loss": 0.7742, "step": 13370 }, { "epoch": 0.07953349858230647, "grad_norm": 12.383152961730957, "learning_rate": 1.5905416329830238e-06, "loss": 0.8078, "step": 13380 }, { "epoch": 0.07959294065897486, "grad_norm": 7.233918190002441, "learning_rate": 1.5917304674497125e-06, "loss": 0.8036, "step": 13390 }, { "epoch": 0.07965238273564325, "grad_norm": 10.294981956481934, "learning_rate": 1.5929193019164014e-06, "loss": 0.729, "step": 13400 }, { "epoch": 0.07971182481231165, "grad_norm": 12.09391975402832, "learning_rate": 1.5941081363830901e-06, "loss": 0.7027, "step": 13410 }, { "epoch": 0.07977126688898004, "grad_norm": 11.50623893737793, "learning_rate": 1.595296970849779e-06, "loss": 0.7528, "step": 13420 }, { "epoch": 0.07983070896564842, "grad_norm": 10.499835014343262, "learning_rate": 1.5964858053164678e-06, "loss": 0.7316, "step": 13430 }, { "epoch": 0.07989015104231681, "grad_norm": 13.265364646911621, "learning_rate": 1.5976746397831567e-06, "loss": 0.7993, "step": 13440 }, { "epoch": 0.07994959311898521, "grad_norm": 13.294588088989258, "learning_rate": 1.5988634742498454e-06, "loss": 0.7925, "step": 13450 }, { "epoch": 0.0800090351956536, "grad_norm": 11.518074035644531, "learning_rate": 1.6000523087165345e-06, "loss": 0.6968, "step": 13460 }, { "epoch": 0.08006847727232198, "grad_norm": 9.754471778869629, "learning_rate": 1.6012411431832235e-06, "loss": 0.752, "step": 13470 }, { "epoch": 0.08012791934899037, "grad_norm": 10.404516220092773, "learning_rate": 1.6024299776499122e-06, "loss": 0.7476, "step": 13480 }, { "epoch": 0.08018736142565877, "grad_norm": 13.570210456848145, "learning_rate": 1.6036188121166011e-06, "loss": 0.7472, "step": 13490 }, { "epoch": 0.08024680350232716, "grad_norm": 11.887450218200684, "learning_rate": 1.6048076465832898e-06, "loss": 0.7882, "step": 13500 }, { "epoch": 0.08030624557899554, "grad_norm": 13.991671562194824, "learning_rate": 1.6059964810499788e-06, "loss": 0.8358, "step": 13510 }, { "epoch": 0.08036568765566394, "grad_norm": 10.07304859161377, "learning_rate": 1.6071853155166675e-06, "loss": 0.7759, "step": 13520 }, { "epoch": 0.08042512973233233, "grad_norm": 8.710701942443848, "learning_rate": 1.6083741499833564e-06, "loss": 0.7569, "step": 13530 }, { "epoch": 0.08048457180900072, "grad_norm": 12.991869926452637, "learning_rate": 1.6095629844500455e-06, "loss": 0.7462, "step": 13540 }, { "epoch": 0.0805440138856691, "grad_norm": 11.289995193481445, "learning_rate": 1.6107518189167343e-06, "loss": 0.8003, "step": 13550 }, { "epoch": 0.0806034559623375, "grad_norm": 11.681629180908203, "learning_rate": 1.6119406533834232e-06, "loss": 0.7632, "step": 13560 }, { "epoch": 0.08066289803900589, "grad_norm": 12.243337631225586, "learning_rate": 1.613129487850112e-06, "loss": 0.8179, "step": 13570 }, { "epoch": 0.08072234011567428, "grad_norm": 13.072166442871094, "learning_rate": 1.6143183223168008e-06, "loss": 0.782, "step": 13580 }, { "epoch": 0.08078178219234267, "grad_norm": 11.229256629943848, "learning_rate": 1.6155071567834895e-06, "loss": 0.8257, "step": 13590 }, { "epoch": 0.08084122426901107, "grad_norm": 10.187057495117188, "learning_rate": 1.6166959912501785e-06, "loss": 0.7301, "step": 13600 }, { "epoch": 0.08090066634567945, "grad_norm": 13.43366813659668, "learning_rate": 1.6178848257168672e-06, "loss": 0.7764, "step": 13610 }, { "epoch": 0.08096010842234784, "grad_norm": 12.55942440032959, "learning_rate": 1.6190736601835561e-06, "loss": 0.792, "step": 13620 }, { "epoch": 0.08101955049901623, "grad_norm": 11.428966522216797, "learning_rate": 1.6202624946502452e-06, "loss": 0.8002, "step": 13630 }, { "epoch": 0.08107899257568463, "grad_norm": 12.340574264526367, "learning_rate": 1.621451329116934e-06, "loss": 0.7984, "step": 13640 }, { "epoch": 0.08113843465235301, "grad_norm": 10.782598495483398, "learning_rate": 1.6226401635836229e-06, "loss": 0.7764, "step": 13650 }, { "epoch": 0.0811978767290214, "grad_norm": 14.277568817138672, "learning_rate": 1.6238289980503116e-06, "loss": 0.8001, "step": 13660 }, { "epoch": 0.0812573188056898, "grad_norm": 11.760961532592773, "learning_rate": 1.6250178325170005e-06, "loss": 0.8431, "step": 13670 }, { "epoch": 0.08131676088235819, "grad_norm": 11.557663917541504, "learning_rate": 1.6262066669836893e-06, "loss": 0.7823, "step": 13680 }, { "epoch": 0.08137620295902658, "grad_norm": 14.47928524017334, "learning_rate": 1.6273955014503782e-06, "loss": 0.839, "step": 13690 }, { "epoch": 0.08143564503569496, "grad_norm": 9.627591133117676, "learning_rate": 1.6285843359170669e-06, "loss": 0.7746, "step": 13700 }, { "epoch": 0.08149508711236336, "grad_norm": 10.725645065307617, "learning_rate": 1.6297731703837558e-06, "loss": 0.7337, "step": 13710 }, { "epoch": 0.08155452918903175, "grad_norm": 12.263080596923828, "learning_rate": 1.630962004850445e-06, "loss": 0.8102, "step": 13720 }, { "epoch": 0.08161397126570014, "grad_norm": 10.649020195007324, "learning_rate": 1.6321508393171337e-06, "loss": 0.8192, "step": 13730 }, { "epoch": 0.08167341334236852, "grad_norm": 13.137411117553711, "learning_rate": 1.6333396737838226e-06, "loss": 0.7711, "step": 13740 }, { "epoch": 0.08173285541903692, "grad_norm": 13.84856128692627, "learning_rate": 1.6345285082505113e-06, "loss": 0.7542, "step": 13750 }, { "epoch": 0.08179229749570531, "grad_norm": 10.591042518615723, "learning_rate": 1.6357173427172002e-06, "loss": 0.752, "step": 13760 }, { "epoch": 0.0818517395723737, "grad_norm": 13.492911338806152, "learning_rate": 1.636906177183889e-06, "loss": 0.7377, "step": 13770 }, { "epoch": 0.0819111816490421, "grad_norm": 12.776778221130371, "learning_rate": 1.6380950116505779e-06, "loss": 0.8444, "step": 13780 }, { "epoch": 0.08197062372571048, "grad_norm": 12.044317245483398, "learning_rate": 1.6392838461172666e-06, "loss": 0.8555, "step": 13790 }, { "epoch": 0.08203006580237887, "grad_norm": 11.125826835632324, "learning_rate": 1.6404726805839557e-06, "loss": 0.7548, "step": 13800 }, { "epoch": 0.08208950787904726, "grad_norm": 11.250465393066406, "learning_rate": 1.6416615150506447e-06, "loss": 0.7619, "step": 13810 }, { "epoch": 0.08214894995571566, "grad_norm": 12.61746883392334, "learning_rate": 1.6428503495173334e-06, "loss": 0.863, "step": 13820 }, { "epoch": 0.08220839203238405, "grad_norm": 10.050077438354492, "learning_rate": 1.6440391839840223e-06, "loss": 0.7542, "step": 13830 }, { "epoch": 0.08226783410905243, "grad_norm": 12.785294532775879, "learning_rate": 1.645228018450711e-06, "loss": 0.8695, "step": 13840 }, { "epoch": 0.08232727618572082, "grad_norm": 13.056014060974121, "learning_rate": 1.6464168529174e-06, "loss": 0.7949, "step": 13850 }, { "epoch": 0.08238671826238922, "grad_norm": 10.701173782348633, "learning_rate": 1.6476056873840887e-06, "loss": 0.783, "step": 13860 }, { "epoch": 0.0824461603390576, "grad_norm": 9.855057716369629, "learning_rate": 1.6487945218507776e-06, "loss": 0.7738, "step": 13870 }, { "epoch": 0.08250560241572599, "grad_norm": 10.405400276184082, "learning_rate": 1.6499833563174663e-06, "loss": 0.8029, "step": 13880 }, { "epoch": 0.08256504449239438, "grad_norm": 10.930192947387695, "learning_rate": 1.6511721907841555e-06, "loss": 0.8417, "step": 13890 }, { "epoch": 0.08262448656906278, "grad_norm": 11.528788566589355, "learning_rate": 1.6523610252508444e-06, "loss": 0.8215, "step": 13900 }, { "epoch": 0.08268392864573117, "grad_norm": 12.0082368850708, "learning_rate": 1.653549859717533e-06, "loss": 0.747, "step": 13910 }, { "epoch": 0.08274337072239955, "grad_norm": 10.945305824279785, "learning_rate": 1.654738694184222e-06, "loss": 0.7817, "step": 13920 }, { "epoch": 0.08280281279906795, "grad_norm": 11.072347640991211, "learning_rate": 1.6559275286509107e-06, "loss": 0.7689, "step": 13930 }, { "epoch": 0.08286225487573634, "grad_norm": 12.364192962646484, "learning_rate": 1.6571163631175997e-06, "loss": 0.7654, "step": 13940 }, { "epoch": 0.08292169695240473, "grad_norm": 14.000555992126465, "learning_rate": 1.6583051975842884e-06, "loss": 0.8334, "step": 13950 }, { "epoch": 0.08298113902907311, "grad_norm": 12.9542236328125, "learning_rate": 1.6594940320509773e-06, "loss": 0.7415, "step": 13960 }, { "epoch": 0.08304058110574151, "grad_norm": 10.937744140625, "learning_rate": 1.660682866517666e-06, "loss": 0.7756, "step": 13970 }, { "epoch": 0.0831000231824099, "grad_norm": 11.179614067077637, "learning_rate": 1.6618717009843552e-06, "loss": 0.7561, "step": 13980 }, { "epoch": 0.08315946525907829, "grad_norm": 10.62086009979248, "learning_rate": 1.663060535451044e-06, "loss": 0.7617, "step": 13990 }, { "epoch": 0.08321890733574668, "grad_norm": 12.664519309997559, "learning_rate": 1.6642493699177328e-06, "loss": 0.8057, "step": 14000 }, { "epoch": 0.08327834941241508, "grad_norm": 13.58411979675293, "learning_rate": 1.6654382043844217e-06, "loss": 0.787, "step": 14010 }, { "epoch": 0.08333779148908346, "grad_norm": 10.05341625213623, "learning_rate": 1.6666270388511104e-06, "loss": 0.7432, "step": 14020 }, { "epoch": 0.08339723356575185, "grad_norm": 10.301777839660645, "learning_rate": 1.6678158733177994e-06, "loss": 0.7929, "step": 14030 }, { "epoch": 0.08345667564242025, "grad_norm": 15.634195327758789, "learning_rate": 1.669004707784488e-06, "loss": 0.8054, "step": 14040 }, { "epoch": 0.08351611771908864, "grad_norm": 9.811269760131836, "learning_rate": 1.670193542251177e-06, "loss": 0.7691, "step": 14050 }, { "epoch": 0.08357555979575702, "grad_norm": 10.701887130737305, "learning_rate": 1.6713823767178662e-06, "loss": 0.7602, "step": 14060 }, { "epoch": 0.08363500187242541, "grad_norm": 10.521705627441406, "learning_rate": 1.6725712111845549e-06, "loss": 0.7648, "step": 14070 }, { "epoch": 0.08369444394909381, "grad_norm": 9.152605056762695, "learning_rate": 1.6737600456512438e-06, "loss": 0.8041, "step": 14080 }, { "epoch": 0.0837538860257622, "grad_norm": 14.506190299987793, "learning_rate": 1.6749488801179325e-06, "loss": 0.7916, "step": 14090 }, { "epoch": 0.08381332810243058, "grad_norm": 10.461630821228027, "learning_rate": 1.6761377145846214e-06, "loss": 0.8206, "step": 14100 }, { "epoch": 0.08387277017909897, "grad_norm": 10.343401908874512, "learning_rate": 1.6773265490513102e-06, "loss": 0.7741, "step": 14110 }, { "epoch": 0.08393221225576737, "grad_norm": 10.2490816116333, "learning_rate": 1.678515383517999e-06, "loss": 0.7906, "step": 14120 }, { "epoch": 0.08399165433243576, "grad_norm": 12.14596939086914, "learning_rate": 1.6797042179846878e-06, "loss": 0.7477, "step": 14130 }, { "epoch": 0.08405109640910415, "grad_norm": 13.880727767944336, "learning_rate": 1.6808930524513767e-06, "loss": 0.7439, "step": 14140 }, { "epoch": 0.08411053848577255, "grad_norm": 8.844191551208496, "learning_rate": 1.6820818869180659e-06, "loss": 0.7339, "step": 14150 }, { "epoch": 0.08416998056244093, "grad_norm": 9.679712295532227, "learning_rate": 1.6832707213847546e-06, "loss": 0.7791, "step": 14160 }, { "epoch": 0.08422942263910932, "grad_norm": 10.0789155960083, "learning_rate": 1.6844595558514435e-06, "loss": 0.768, "step": 14170 }, { "epoch": 0.0842888647157777, "grad_norm": 12.162219047546387, "learning_rate": 1.6856483903181322e-06, "loss": 0.7961, "step": 14180 }, { "epoch": 0.0843483067924461, "grad_norm": 13.645319938659668, "learning_rate": 1.6868372247848212e-06, "loss": 0.7906, "step": 14190 }, { "epoch": 0.0844077488691145, "grad_norm": 10.588838577270508, "learning_rate": 1.6880260592515099e-06, "loss": 0.7682, "step": 14200 }, { "epoch": 0.08446719094578288, "grad_norm": 11.596434593200684, "learning_rate": 1.6892148937181988e-06, "loss": 0.7584, "step": 14210 }, { "epoch": 0.08452663302245127, "grad_norm": 11.373031616210938, "learning_rate": 1.6904037281848875e-06, "loss": 0.7865, "step": 14220 }, { "epoch": 0.08458607509911967, "grad_norm": 11.11433219909668, "learning_rate": 1.6915925626515764e-06, "loss": 0.7972, "step": 14230 }, { "epoch": 0.08464551717578805, "grad_norm": 9.913386344909668, "learning_rate": 1.6927813971182656e-06, "loss": 0.8029, "step": 14240 }, { "epoch": 0.08470495925245644, "grad_norm": 10.18487548828125, "learning_rate": 1.6939702315849543e-06, "loss": 0.7665, "step": 14250 }, { "epoch": 0.08476440132912483, "grad_norm": 9.093873023986816, "learning_rate": 1.6951590660516432e-06, "loss": 0.778, "step": 14260 }, { "epoch": 0.08482384340579323, "grad_norm": 12.793203353881836, "learning_rate": 1.696347900518332e-06, "loss": 0.7772, "step": 14270 }, { "epoch": 0.08488328548246162, "grad_norm": 11.553447723388672, "learning_rate": 1.6975367349850209e-06, "loss": 0.8015, "step": 14280 }, { "epoch": 0.08494272755913, "grad_norm": 10.097282409667969, "learning_rate": 1.6987255694517096e-06, "loss": 0.7707, "step": 14290 }, { "epoch": 0.0850021696357984, "grad_norm": 12.811330795288086, "learning_rate": 1.6999144039183985e-06, "loss": 0.7961, "step": 14300 }, { "epoch": 0.08506161171246679, "grad_norm": 10.369321823120117, "learning_rate": 1.7011032383850872e-06, "loss": 0.7781, "step": 14310 }, { "epoch": 0.08512105378913518, "grad_norm": 12.296733856201172, "learning_rate": 1.7022920728517764e-06, "loss": 0.7702, "step": 14320 }, { "epoch": 0.08518049586580356, "grad_norm": 12.546914100646973, "learning_rate": 1.7034809073184653e-06, "loss": 0.8076, "step": 14330 }, { "epoch": 0.08523993794247196, "grad_norm": 10.344931602478027, "learning_rate": 1.704669741785154e-06, "loss": 0.744, "step": 14340 }, { "epoch": 0.08529938001914035, "grad_norm": 10.802827835083008, "learning_rate": 1.705858576251843e-06, "loss": 0.6984, "step": 14350 }, { "epoch": 0.08535882209580874, "grad_norm": 12.527350425720215, "learning_rate": 1.7070474107185316e-06, "loss": 0.7664, "step": 14360 }, { "epoch": 0.08541826417247712, "grad_norm": 15.75926399230957, "learning_rate": 1.7082362451852206e-06, "loss": 0.8395, "step": 14370 }, { "epoch": 0.08547770624914552, "grad_norm": 10.80655574798584, "learning_rate": 1.7094250796519093e-06, "loss": 0.7758, "step": 14380 }, { "epoch": 0.08553714832581391, "grad_norm": 12.81830883026123, "learning_rate": 1.7106139141185982e-06, "loss": 0.7557, "step": 14390 }, { "epoch": 0.0855965904024823, "grad_norm": 11.79189682006836, "learning_rate": 1.711802748585287e-06, "loss": 0.8174, "step": 14400 }, { "epoch": 0.0856560324791507, "grad_norm": 12.05527114868164, "learning_rate": 1.712991583051976e-06, "loss": 0.83, "step": 14410 }, { "epoch": 0.08571547455581909, "grad_norm": 10.850086212158203, "learning_rate": 1.714180417518665e-06, "loss": 0.7775, "step": 14420 }, { "epoch": 0.08577491663248747, "grad_norm": 12.6838960647583, "learning_rate": 1.7153692519853537e-06, "loss": 0.7556, "step": 14430 }, { "epoch": 0.08583435870915586, "grad_norm": 13.200310707092285, "learning_rate": 1.7165580864520426e-06, "loss": 0.7602, "step": 14440 }, { "epoch": 0.08589380078582426, "grad_norm": 9.555450439453125, "learning_rate": 1.7177469209187314e-06, "loss": 0.7474, "step": 14450 }, { "epoch": 0.08595324286249265, "grad_norm": 10.752902030944824, "learning_rate": 1.7189357553854203e-06, "loss": 0.7179, "step": 14460 }, { "epoch": 0.08601268493916103, "grad_norm": 11.07979679107666, "learning_rate": 1.720124589852109e-06, "loss": 0.7833, "step": 14470 }, { "epoch": 0.08607212701582942, "grad_norm": 12.80048656463623, "learning_rate": 1.721313424318798e-06, "loss": 0.7743, "step": 14480 }, { "epoch": 0.08613156909249782, "grad_norm": 9.6346435546875, "learning_rate": 1.7225022587854866e-06, "loss": 0.8081, "step": 14490 }, { "epoch": 0.0861910111691662, "grad_norm": 12.549264907836914, "learning_rate": 1.7236910932521758e-06, "loss": 0.8174, "step": 14500 }, { "epoch": 0.0862504532458346, "grad_norm": 12.2106294631958, "learning_rate": 1.7248799277188647e-06, "loss": 0.8318, "step": 14510 }, { "epoch": 0.08630989532250298, "grad_norm": 13.941780090332031, "learning_rate": 1.7260687621855534e-06, "loss": 0.7519, "step": 14520 }, { "epoch": 0.08636933739917138, "grad_norm": 10.466163635253906, "learning_rate": 1.7272575966522424e-06, "loss": 0.837, "step": 14530 }, { "epoch": 0.08642877947583977, "grad_norm": 10.07260513305664, "learning_rate": 1.728446431118931e-06, "loss": 0.7402, "step": 14540 }, { "epoch": 0.08648822155250815, "grad_norm": 12.318418502807617, "learning_rate": 1.72963526558562e-06, "loss": 0.745, "step": 14550 }, { "epoch": 0.08654766362917655, "grad_norm": 9.777962684631348, "learning_rate": 1.7308241000523087e-06, "loss": 0.8133, "step": 14560 }, { "epoch": 0.08660710570584494, "grad_norm": 13.977726936340332, "learning_rate": 1.7320129345189976e-06, "loss": 0.7899, "step": 14570 }, { "epoch": 0.08666654778251333, "grad_norm": 11.950127601623535, "learning_rate": 1.7332017689856868e-06, "loss": 0.7608, "step": 14580 }, { "epoch": 0.08672598985918172, "grad_norm": 13.43210506439209, "learning_rate": 1.7343906034523755e-06, "loss": 0.7759, "step": 14590 }, { "epoch": 0.08678543193585012, "grad_norm": 12.126444816589355, "learning_rate": 1.7355794379190644e-06, "loss": 0.7691, "step": 14600 }, { "epoch": 0.0868448740125185, "grad_norm": 11.762543678283691, "learning_rate": 1.7367682723857531e-06, "loss": 0.8025, "step": 14610 }, { "epoch": 0.08690431608918689, "grad_norm": 12.379828453063965, "learning_rate": 1.737957106852442e-06, "loss": 0.8026, "step": 14620 }, { "epoch": 0.08696375816585528, "grad_norm": 10.08994197845459, "learning_rate": 1.7391459413191308e-06, "loss": 0.8014, "step": 14630 }, { "epoch": 0.08702320024252368, "grad_norm": 10.3969087600708, "learning_rate": 1.7403347757858197e-06, "loss": 0.7603, "step": 14640 }, { "epoch": 0.08708264231919206, "grad_norm": 10.316617012023926, "learning_rate": 1.7415236102525084e-06, "loss": 0.7209, "step": 14650 }, { "epoch": 0.08714208439586045, "grad_norm": 10.667734146118164, "learning_rate": 1.7427124447191973e-06, "loss": 0.7319, "step": 14660 }, { "epoch": 0.08720152647252885, "grad_norm": 12.550695419311523, "learning_rate": 1.7439012791858865e-06, "loss": 0.7578, "step": 14670 }, { "epoch": 0.08726096854919724, "grad_norm": 9.59916877746582, "learning_rate": 1.7450901136525752e-06, "loss": 0.743, "step": 14680 }, { "epoch": 0.08732041062586562, "grad_norm": 10.239401817321777, "learning_rate": 1.7462789481192641e-06, "loss": 0.7864, "step": 14690 }, { "epoch": 0.08737985270253401, "grad_norm": 9.404511451721191, "learning_rate": 1.7474677825859528e-06, "loss": 0.6782, "step": 14700 }, { "epoch": 0.08743929477920241, "grad_norm": 9.475048065185547, "learning_rate": 1.7486566170526418e-06, "loss": 0.8131, "step": 14710 }, { "epoch": 0.0874987368558708, "grad_norm": 13.129536628723145, "learning_rate": 1.7498454515193305e-06, "loss": 0.755, "step": 14720 }, { "epoch": 0.08755817893253919, "grad_norm": 11.70603084564209, "learning_rate": 1.7510342859860194e-06, "loss": 0.7657, "step": 14730 }, { "epoch": 0.08761762100920757, "grad_norm": 12.177865028381348, "learning_rate": 1.7522231204527081e-06, "loss": 0.8591, "step": 14740 }, { "epoch": 0.08767706308587597, "grad_norm": 8.853347778320312, "learning_rate": 1.753411954919397e-06, "loss": 0.7922, "step": 14750 }, { "epoch": 0.08773650516254436, "grad_norm": 12.794513702392578, "learning_rate": 1.7546007893860862e-06, "loss": 0.7905, "step": 14760 }, { "epoch": 0.08779594723921275, "grad_norm": 10.192272186279297, "learning_rate": 1.755789623852775e-06, "loss": 0.7585, "step": 14770 }, { "epoch": 0.08785538931588113, "grad_norm": 9.671026229858398, "learning_rate": 1.7569784583194638e-06, "loss": 0.7887, "step": 14780 }, { "epoch": 0.08791483139254953, "grad_norm": 13.71580982208252, "learning_rate": 1.7581672927861526e-06, "loss": 0.8276, "step": 14790 }, { "epoch": 0.08797427346921792, "grad_norm": 15.697680473327637, "learning_rate": 1.7593561272528415e-06, "loss": 0.7417, "step": 14800 }, { "epoch": 0.0880337155458863, "grad_norm": 11.250605583190918, "learning_rate": 1.7605449617195302e-06, "loss": 0.7788, "step": 14810 }, { "epoch": 0.08809315762255471, "grad_norm": 10.087682723999023, "learning_rate": 1.7617337961862191e-06, "loss": 0.7266, "step": 14820 }, { "epoch": 0.0881525996992231, "grad_norm": 9.361371040344238, "learning_rate": 1.7629226306529078e-06, "loss": 0.7688, "step": 14830 }, { "epoch": 0.08821204177589148, "grad_norm": 9.536412239074707, "learning_rate": 1.764111465119597e-06, "loss": 0.7677, "step": 14840 }, { "epoch": 0.08827148385255987, "grad_norm": 14.597783088684082, "learning_rate": 1.765300299586286e-06, "loss": 0.8495, "step": 14850 }, { "epoch": 0.08833092592922827, "grad_norm": 10.705538749694824, "learning_rate": 1.7664891340529746e-06, "loss": 0.7365, "step": 14860 }, { "epoch": 0.08839036800589666, "grad_norm": 11.94982624053955, "learning_rate": 1.7676779685196636e-06, "loss": 0.7973, "step": 14870 }, { "epoch": 0.08844981008256504, "grad_norm": 12.990252494812012, "learning_rate": 1.7688668029863523e-06, "loss": 0.7913, "step": 14880 }, { "epoch": 0.08850925215923343, "grad_norm": 12.556386947631836, "learning_rate": 1.7700556374530412e-06, "loss": 0.8077, "step": 14890 }, { "epoch": 0.08856869423590183, "grad_norm": 10.895331382751465, "learning_rate": 1.77124447191973e-06, "loss": 0.7337, "step": 14900 }, { "epoch": 0.08862813631257022, "grad_norm": 10.389021873474121, "learning_rate": 1.7724333063864188e-06, "loss": 0.7392, "step": 14910 }, { "epoch": 0.0886875783892386, "grad_norm": 12.914708137512207, "learning_rate": 1.7736221408531076e-06, "loss": 0.7906, "step": 14920 }, { "epoch": 0.088747020465907, "grad_norm": 12.807823181152344, "learning_rate": 1.7748109753197967e-06, "loss": 0.7357, "step": 14930 }, { "epoch": 0.08880646254257539, "grad_norm": 10.269474029541016, "learning_rate": 1.7759998097864856e-06, "loss": 0.774, "step": 14940 }, { "epoch": 0.08886590461924378, "grad_norm": 11.93210506439209, "learning_rate": 1.7771886442531743e-06, "loss": 0.7658, "step": 14950 }, { "epoch": 0.08892534669591216, "grad_norm": 11.313928604125977, "learning_rate": 1.7783774787198633e-06, "loss": 0.8165, "step": 14960 }, { "epoch": 0.08898478877258056, "grad_norm": 12.684525489807129, "learning_rate": 1.779566313186552e-06, "loss": 0.7495, "step": 14970 }, { "epoch": 0.08904423084924895, "grad_norm": 10.326858520507812, "learning_rate": 1.780755147653241e-06, "loss": 0.7655, "step": 14980 }, { "epoch": 0.08910367292591734, "grad_norm": 13.657709121704102, "learning_rate": 1.7819439821199296e-06, "loss": 0.8328, "step": 14990 }, { "epoch": 0.08916311500258572, "grad_norm": 13.135890007019043, "learning_rate": 1.7831328165866185e-06, "loss": 0.7978, "step": 15000 }, { "epoch": 0.08922255707925413, "grad_norm": 16.957761764526367, "learning_rate": 1.7843216510533073e-06, "loss": 0.775, "step": 15010 }, { "epoch": 0.08928199915592251, "grad_norm": 11.79295825958252, "learning_rate": 1.7855104855199964e-06, "loss": 0.7808, "step": 15020 }, { "epoch": 0.0893414412325909, "grad_norm": 11.932239532470703, "learning_rate": 1.7866993199866853e-06, "loss": 0.81, "step": 15030 }, { "epoch": 0.0894008833092593, "grad_norm": 12.900446891784668, "learning_rate": 1.787888154453374e-06, "loss": 0.6824, "step": 15040 }, { "epoch": 0.08946032538592769, "grad_norm": 10.313693046569824, "learning_rate": 1.789076988920063e-06, "loss": 0.7918, "step": 15050 }, { "epoch": 0.08951976746259607, "grad_norm": 11.296995162963867, "learning_rate": 1.7902658233867517e-06, "loss": 0.802, "step": 15060 }, { "epoch": 0.08957920953926446, "grad_norm": 10.661556243896484, "learning_rate": 1.7914546578534406e-06, "loss": 0.7638, "step": 15070 }, { "epoch": 0.08963865161593286, "grad_norm": 10.052525520324707, "learning_rate": 1.7926434923201293e-06, "loss": 0.772, "step": 15080 }, { "epoch": 0.08969809369260125, "grad_norm": 11.287456512451172, "learning_rate": 1.7938323267868183e-06, "loss": 0.7394, "step": 15090 }, { "epoch": 0.08975753576926963, "grad_norm": 11.126108169555664, "learning_rate": 1.7950211612535074e-06, "loss": 0.7741, "step": 15100 }, { "epoch": 0.08981697784593802, "grad_norm": 11.848618507385254, "learning_rate": 1.7962099957201961e-06, "loss": 0.7538, "step": 15110 }, { "epoch": 0.08987641992260642, "grad_norm": 9.902985572814941, "learning_rate": 1.797398830186885e-06, "loss": 0.7723, "step": 15120 }, { "epoch": 0.08993586199927481, "grad_norm": 9.701628684997559, "learning_rate": 1.7985876646535738e-06, "loss": 0.742, "step": 15130 }, { "epoch": 0.0899953040759432, "grad_norm": 10.775663375854492, "learning_rate": 1.7997764991202627e-06, "loss": 0.7504, "step": 15140 }, { "epoch": 0.09005474615261158, "grad_norm": 10.54541301727295, "learning_rate": 1.8009653335869514e-06, "loss": 0.7297, "step": 15150 }, { "epoch": 0.09011418822927998, "grad_norm": 15.118012428283691, "learning_rate": 1.8021541680536403e-06, "loss": 0.7448, "step": 15160 }, { "epoch": 0.09017363030594837, "grad_norm": 12.435696601867676, "learning_rate": 1.803343002520329e-06, "loss": 0.7663, "step": 15170 }, { "epoch": 0.09023307238261676, "grad_norm": 12.279809951782227, "learning_rate": 1.804531836987018e-06, "loss": 0.6691, "step": 15180 }, { "epoch": 0.09029251445928516, "grad_norm": 11.502384185791016, "learning_rate": 1.8057206714537071e-06, "loss": 0.7963, "step": 15190 }, { "epoch": 0.09035195653595354, "grad_norm": 13.030075073242188, "learning_rate": 1.8069095059203958e-06, "loss": 0.67, "step": 15200 }, { "epoch": 0.09041139861262193, "grad_norm": 11.468759536743164, "learning_rate": 1.8080983403870848e-06, "loss": 0.7528, "step": 15210 }, { "epoch": 0.09047084068929032, "grad_norm": 12.834478378295898, "learning_rate": 1.8092871748537735e-06, "loss": 0.7738, "step": 15220 }, { "epoch": 0.09053028276595872, "grad_norm": 10.776698112487793, "learning_rate": 1.8104760093204624e-06, "loss": 0.7578, "step": 15230 }, { "epoch": 0.0905897248426271, "grad_norm": 15.094568252563477, "learning_rate": 1.8116648437871511e-06, "loss": 0.7896, "step": 15240 }, { "epoch": 0.09064916691929549, "grad_norm": 10.090636253356934, "learning_rate": 1.81285367825384e-06, "loss": 0.7493, "step": 15250 }, { "epoch": 0.09070860899596388, "grad_norm": 10.201869010925293, "learning_rate": 1.8140425127205288e-06, "loss": 0.729, "step": 15260 }, { "epoch": 0.09076805107263228, "grad_norm": 12.609916687011719, "learning_rate": 1.8152313471872177e-06, "loss": 0.7401, "step": 15270 }, { "epoch": 0.09082749314930066, "grad_norm": 11.59206771850586, "learning_rate": 1.8164201816539068e-06, "loss": 0.7921, "step": 15280 }, { "epoch": 0.09088693522596905, "grad_norm": 11.652632713317871, "learning_rate": 1.8176090161205955e-06, "loss": 0.8217, "step": 15290 }, { "epoch": 0.09094637730263745, "grad_norm": 10.433274269104004, "learning_rate": 1.8187978505872845e-06, "loss": 0.7948, "step": 15300 }, { "epoch": 0.09100581937930584, "grad_norm": 9.800179481506348, "learning_rate": 1.8199866850539732e-06, "loss": 0.7988, "step": 15310 }, { "epoch": 0.09106526145597423, "grad_norm": 11.20567512512207, "learning_rate": 1.821175519520662e-06, "loss": 0.8064, "step": 15320 }, { "epoch": 0.09112470353264261, "grad_norm": 14.506969451904297, "learning_rate": 1.8223643539873508e-06, "loss": 0.7466, "step": 15330 }, { "epoch": 0.09118414560931101, "grad_norm": 16.104345321655273, "learning_rate": 1.8235531884540397e-06, "loss": 0.8195, "step": 15340 }, { "epoch": 0.0912435876859794, "grad_norm": 11.272391319274902, "learning_rate": 1.8247420229207285e-06, "loss": 0.7651, "step": 15350 }, { "epoch": 0.09130302976264779, "grad_norm": 11.389668464660645, "learning_rate": 1.8259308573874176e-06, "loss": 0.8429, "step": 15360 }, { "epoch": 0.09136247183931617, "grad_norm": 10.587027549743652, "learning_rate": 1.8271196918541065e-06, "loss": 0.8134, "step": 15370 }, { "epoch": 0.09142191391598457, "grad_norm": 9.689268112182617, "learning_rate": 1.8283085263207952e-06, "loss": 0.7606, "step": 15380 }, { "epoch": 0.09148135599265296, "grad_norm": 9.350110054016113, "learning_rate": 1.8294973607874842e-06, "loss": 0.7089, "step": 15390 }, { "epoch": 0.09154079806932135, "grad_norm": 8.980340003967285, "learning_rate": 1.8306861952541729e-06, "loss": 0.7484, "step": 15400 }, { "epoch": 0.09160024014598973, "grad_norm": 10.557442665100098, "learning_rate": 1.8318750297208618e-06, "loss": 0.729, "step": 15410 }, { "epoch": 0.09165968222265813, "grad_norm": 12.230502128601074, "learning_rate": 1.8330638641875505e-06, "loss": 0.7347, "step": 15420 }, { "epoch": 0.09171912429932652, "grad_norm": 9.11086654663086, "learning_rate": 1.8342526986542395e-06, "loss": 0.7243, "step": 15430 }, { "epoch": 0.09177856637599491, "grad_norm": 10.918340682983398, "learning_rate": 1.8354415331209282e-06, "loss": 0.7638, "step": 15440 }, { "epoch": 0.09183800845266331, "grad_norm": 9.259678840637207, "learning_rate": 1.8366303675876173e-06, "loss": 0.7135, "step": 15450 }, { "epoch": 0.0918974505293317, "grad_norm": 10.630754470825195, "learning_rate": 1.8378192020543062e-06, "loss": 0.7849, "step": 15460 }, { "epoch": 0.09195689260600008, "grad_norm": 13.518301963806152, "learning_rate": 1.839008036520995e-06, "loss": 0.7354, "step": 15470 }, { "epoch": 0.09201633468266847, "grad_norm": 11.010512351989746, "learning_rate": 1.8401968709876839e-06, "loss": 0.7808, "step": 15480 }, { "epoch": 0.09207577675933687, "grad_norm": 11.50546646118164, "learning_rate": 1.8413857054543726e-06, "loss": 0.7348, "step": 15490 }, { "epoch": 0.09213521883600526, "grad_norm": 12.471473693847656, "learning_rate": 1.8425745399210615e-06, "loss": 0.7783, "step": 15500 }, { "epoch": 0.09219466091267364, "grad_norm": 11.385897636413574, "learning_rate": 1.8437633743877502e-06, "loss": 0.7883, "step": 15510 }, { "epoch": 0.09225410298934203, "grad_norm": 9.739250183105469, "learning_rate": 1.8449522088544392e-06, "loss": 0.7624, "step": 15520 }, { "epoch": 0.09231354506601043, "grad_norm": 9.021108627319336, "learning_rate": 1.8461410433211279e-06, "loss": 0.7623, "step": 15530 }, { "epoch": 0.09237298714267882, "grad_norm": 9.940319061279297, "learning_rate": 1.847329877787817e-06, "loss": 0.7359, "step": 15540 }, { "epoch": 0.0924324292193472, "grad_norm": 11.976123809814453, "learning_rate": 1.848518712254506e-06, "loss": 0.752, "step": 15550 }, { "epoch": 0.0924918712960156, "grad_norm": 11.82483196258545, "learning_rate": 1.8497075467211947e-06, "loss": 0.7117, "step": 15560 }, { "epoch": 0.09255131337268399, "grad_norm": 9.542798042297363, "learning_rate": 1.8508963811878836e-06, "loss": 0.7999, "step": 15570 }, { "epoch": 0.09261075544935238, "grad_norm": 12.008803367614746, "learning_rate": 1.8520852156545723e-06, "loss": 0.8048, "step": 15580 }, { "epoch": 0.09267019752602076, "grad_norm": 10.345024108886719, "learning_rate": 1.8532740501212612e-06, "loss": 0.7829, "step": 15590 }, { "epoch": 0.09272963960268917, "grad_norm": 12.003652572631836, "learning_rate": 1.85446288458795e-06, "loss": 0.7481, "step": 15600 }, { "epoch": 0.09278908167935755, "grad_norm": 9.066556930541992, "learning_rate": 1.8556517190546389e-06, "loss": 0.7551, "step": 15610 }, { "epoch": 0.09284852375602594, "grad_norm": 10.7752046585083, "learning_rate": 1.856840553521328e-06, "loss": 0.7747, "step": 15620 }, { "epoch": 0.09290796583269433, "grad_norm": 15.428093910217285, "learning_rate": 1.8580293879880167e-06, "loss": 0.8407, "step": 15630 }, { "epoch": 0.09296740790936273, "grad_norm": 10.960113525390625, "learning_rate": 1.8592182224547057e-06, "loss": 0.7576, "step": 15640 }, { "epoch": 0.09302684998603111, "grad_norm": 9.166380882263184, "learning_rate": 1.8604070569213944e-06, "loss": 0.7866, "step": 15650 }, { "epoch": 0.0930862920626995, "grad_norm": 11.424773216247559, "learning_rate": 1.8615958913880833e-06, "loss": 0.7769, "step": 15660 }, { "epoch": 0.09314573413936789, "grad_norm": 8.5575532913208, "learning_rate": 1.862784725854772e-06, "loss": 0.7343, "step": 15670 }, { "epoch": 0.09320517621603629, "grad_norm": 11.247143745422363, "learning_rate": 1.863973560321461e-06, "loss": 0.7331, "step": 15680 }, { "epoch": 0.09326461829270467, "grad_norm": 11.01723575592041, "learning_rate": 1.8651623947881497e-06, "loss": 0.7252, "step": 15690 }, { "epoch": 0.09332406036937306, "grad_norm": 12.53671646118164, "learning_rate": 1.8663512292548386e-06, "loss": 0.7484, "step": 15700 }, { "epoch": 0.09338350244604146, "grad_norm": 9.962635040283203, "learning_rate": 1.8675400637215277e-06, "loss": 0.7859, "step": 15710 }, { "epoch": 0.09344294452270985, "grad_norm": 8.593125343322754, "learning_rate": 1.8687288981882164e-06, "loss": 0.7073, "step": 15720 }, { "epoch": 0.09350238659937823, "grad_norm": 13.276656150817871, "learning_rate": 1.8699177326549054e-06, "loss": 0.7621, "step": 15730 }, { "epoch": 0.09356182867604662, "grad_norm": 10.8980073928833, "learning_rate": 1.871106567121594e-06, "loss": 0.7355, "step": 15740 }, { "epoch": 0.09362127075271502, "grad_norm": 9.512916564941406, "learning_rate": 1.872295401588283e-06, "loss": 0.7766, "step": 15750 }, { "epoch": 0.09368071282938341, "grad_norm": 9.86349105834961, "learning_rate": 1.8734842360549717e-06, "loss": 0.7728, "step": 15760 }, { "epoch": 0.0937401549060518, "grad_norm": 11.011736869812012, "learning_rate": 1.8746730705216607e-06, "loss": 0.7284, "step": 15770 }, { "epoch": 0.09379959698272018, "grad_norm": 11.583871841430664, "learning_rate": 1.8758619049883494e-06, "loss": 0.7783, "step": 15780 }, { "epoch": 0.09385903905938858, "grad_norm": 10.636818885803223, "learning_rate": 1.8770507394550383e-06, "loss": 0.7818, "step": 15790 }, { "epoch": 0.09391848113605697, "grad_norm": 11.599443435668945, "learning_rate": 1.8782395739217274e-06, "loss": 0.7742, "step": 15800 }, { "epoch": 0.09397792321272536, "grad_norm": 14.114367485046387, "learning_rate": 1.8794284083884162e-06, "loss": 0.8071, "step": 15810 }, { "epoch": 0.09403736528939376, "grad_norm": 10.304261207580566, "learning_rate": 1.880617242855105e-06, "loss": 0.7346, "step": 15820 }, { "epoch": 0.09409680736606214, "grad_norm": 10.656582832336426, "learning_rate": 1.8818060773217938e-06, "loss": 0.7136, "step": 15830 }, { "epoch": 0.09415624944273053, "grad_norm": 12.205449104309082, "learning_rate": 1.8829949117884827e-06, "loss": 0.7748, "step": 15840 }, { "epoch": 0.09421569151939892, "grad_norm": 10.355284690856934, "learning_rate": 1.8841837462551714e-06, "loss": 0.7555, "step": 15850 }, { "epoch": 0.09427513359606732, "grad_norm": 14.247593879699707, "learning_rate": 1.8853725807218604e-06, "loss": 0.857, "step": 15860 }, { "epoch": 0.0943345756727357, "grad_norm": 12.26431655883789, "learning_rate": 1.886561415188549e-06, "loss": 0.7055, "step": 15870 }, { "epoch": 0.09439401774940409, "grad_norm": 11.967516899108887, "learning_rate": 1.8877502496552382e-06, "loss": 0.7523, "step": 15880 }, { "epoch": 0.09445345982607248, "grad_norm": 12.322455406188965, "learning_rate": 1.8889390841219271e-06, "loss": 0.761, "step": 15890 }, { "epoch": 0.09451290190274088, "grad_norm": 11.03388500213623, "learning_rate": 1.8901279185886159e-06, "loss": 0.7484, "step": 15900 }, { "epoch": 0.09457234397940927, "grad_norm": 12.317305564880371, "learning_rate": 1.8913167530553048e-06, "loss": 0.7622, "step": 15910 }, { "epoch": 0.09463178605607765, "grad_norm": 10.450308799743652, "learning_rate": 1.8925055875219935e-06, "loss": 0.8077, "step": 15920 }, { "epoch": 0.09469122813274605, "grad_norm": 10.292119979858398, "learning_rate": 1.8936944219886824e-06, "loss": 0.6991, "step": 15930 }, { "epoch": 0.09475067020941444, "grad_norm": 10.693581581115723, "learning_rate": 1.8948832564553711e-06, "loss": 0.8184, "step": 15940 }, { "epoch": 0.09481011228608283, "grad_norm": 10.970196723937988, "learning_rate": 1.89607209092206e-06, "loss": 0.7236, "step": 15950 }, { "epoch": 0.09486955436275121, "grad_norm": 10.053481101989746, "learning_rate": 1.8972609253887488e-06, "loss": 0.7325, "step": 15960 }, { "epoch": 0.09492899643941961, "grad_norm": 12.412151336669922, "learning_rate": 1.898449759855438e-06, "loss": 0.7681, "step": 15970 }, { "epoch": 0.094988438516088, "grad_norm": 10.313483238220215, "learning_rate": 1.8996385943221269e-06, "loss": 0.7397, "step": 15980 }, { "epoch": 0.09504788059275639, "grad_norm": 13.454781532287598, "learning_rate": 1.9008274287888156e-06, "loss": 0.7292, "step": 15990 }, { "epoch": 0.09510732266942477, "grad_norm": 8.731609344482422, "learning_rate": 1.9020162632555045e-06, "loss": 0.7146, "step": 16000 }, { "epoch": 0.09516676474609317, "grad_norm": 13.904805183410645, "learning_rate": 1.9032050977221932e-06, "loss": 0.8071, "step": 16010 }, { "epoch": 0.09522620682276156, "grad_norm": 12.081254959106445, "learning_rate": 1.9043939321888821e-06, "loss": 0.7596, "step": 16020 }, { "epoch": 0.09528564889942995, "grad_norm": 8.941866874694824, "learning_rate": 1.9055827666555709e-06, "loss": 0.7509, "step": 16030 }, { "epoch": 0.09534509097609833, "grad_norm": 8.431451797485352, "learning_rate": 1.9067716011222598e-06, "loss": 0.7607, "step": 16040 }, { "epoch": 0.09540453305276674, "grad_norm": 10.45102596282959, "learning_rate": 1.9079604355889487e-06, "loss": 0.7695, "step": 16050 }, { "epoch": 0.09546397512943512, "grad_norm": 11.663875579833984, "learning_rate": 1.9091492700556376e-06, "loss": 0.7016, "step": 16060 }, { "epoch": 0.09552341720610351, "grad_norm": 14.485006332397461, "learning_rate": 1.9103381045223266e-06, "loss": 0.7297, "step": 16070 }, { "epoch": 0.09558285928277191, "grad_norm": 11.590396881103516, "learning_rate": 1.9115269389890155e-06, "loss": 0.6949, "step": 16080 }, { "epoch": 0.0956423013594403, "grad_norm": 9.093029022216797, "learning_rate": 1.912715773455704e-06, "loss": 0.752, "step": 16090 }, { "epoch": 0.09570174343610868, "grad_norm": 10.547531127929688, "learning_rate": 1.913904607922393e-06, "loss": 0.7296, "step": 16100 }, { "epoch": 0.09576118551277707, "grad_norm": 12.01712417602539, "learning_rate": 1.915093442389082e-06, "loss": 0.8135, "step": 16110 }, { "epoch": 0.09582062758944547, "grad_norm": 10.250673294067383, "learning_rate": 1.9162822768557708e-06, "loss": 0.7618, "step": 16120 }, { "epoch": 0.09588006966611386, "grad_norm": 12.558009147644043, "learning_rate": 1.9174711113224597e-06, "loss": 0.764, "step": 16130 }, { "epoch": 0.09593951174278224, "grad_norm": 10.515929222106934, "learning_rate": 1.9186599457891486e-06, "loss": 0.7162, "step": 16140 }, { "epoch": 0.09599895381945063, "grad_norm": 13.778438568115234, "learning_rate": 1.9198487802558376e-06, "loss": 0.8733, "step": 16150 }, { "epoch": 0.09605839589611903, "grad_norm": 11.260208129882812, "learning_rate": 1.921037614722526e-06, "loss": 0.7157, "step": 16160 }, { "epoch": 0.09611783797278742, "grad_norm": 11.135340690612793, "learning_rate": 1.922226449189215e-06, "loss": 0.6975, "step": 16170 }, { "epoch": 0.0961772800494558, "grad_norm": 10.648784637451172, "learning_rate": 1.923415283655904e-06, "loss": 0.7031, "step": 16180 }, { "epoch": 0.0962367221261242, "grad_norm": 10.271978378295898, "learning_rate": 1.924604118122593e-06, "loss": 0.7513, "step": 16190 }, { "epoch": 0.09629616420279259, "grad_norm": 9.791420936584473, "learning_rate": 1.9257929525892814e-06, "loss": 0.7542, "step": 16200 }, { "epoch": 0.09635560627946098, "grad_norm": 9.773073196411133, "learning_rate": 1.9269817870559703e-06, "loss": 0.7878, "step": 16210 }, { "epoch": 0.09641504835612937, "grad_norm": 11.126112937927246, "learning_rate": 1.928170621522659e-06, "loss": 0.8344, "step": 16220 }, { "epoch": 0.09647449043279777, "grad_norm": 11.30628776550293, "learning_rate": 1.929359455989348e-06, "loss": 0.735, "step": 16230 }, { "epoch": 0.09653393250946615, "grad_norm": 12.871871948242188, "learning_rate": 1.930548290456037e-06, "loss": 0.7295, "step": 16240 }, { "epoch": 0.09659337458613454, "grad_norm": 9.621228218078613, "learning_rate": 1.931737124922726e-06, "loss": 0.7956, "step": 16250 }, { "epoch": 0.09665281666280293, "grad_norm": 12.217138290405273, "learning_rate": 1.932925959389415e-06, "loss": 0.7832, "step": 16260 }, { "epoch": 0.09671225873947133, "grad_norm": 11.044775009155273, "learning_rate": 1.9341147938561034e-06, "loss": 0.7631, "step": 16270 }, { "epoch": 0.09677170081613971, "grad_norm": 10.85247802734375, "learning_rate": 1.9353036283227923e-06, "loss": 0.6658, "step": 16280 }, { "epoch": 0.0968311428928081, "grad_norm": 11.477239608764648, "learning_rate": 1.9364924627894813e-06, "loss": 0.7915, "step": 16290 }, { "epoch": 0.09689058496947649, "grad_norm": 9.734100341796875, "learning_rate": 1.93768129725617e-06, "loss": 0.7846, "step": 16300 }, { "epoch": 0.09695002704614489, "grad_norm": 11.042430877685547, "learning_rate": 1.938870131722859e-06, "loss": 0.7273, "step": 16310 }, { "epoch": 0.09700946912281327, "grad_norm": 11.979689598083496, "learning_rate": 1.940058966189548e-06, "loss": 0.6965, "step": 16320 }, { "epoch": 0.09706891119948166, "grad_norm": 11.063773155212402, "learning_rate": 1.941247800656237e-06, "loss": 0.7891, "step": 16330 }, { "epoch": 0.09712835327615006, "grad_norm": 10.915897369384766, "learning_rate": 1.9424366351229255e-06, "loss": 0.7566, "step": 16340 }, { "epoch": 0.09718779535281845, "grad_norm": 10.098666191101074, "learning_rate": 1.9436254695896144e-06, "loss": 0.8157, "step": 16350 }, { "epoch": 0.09724723742948684, "grad_norm": 12.21407699584961, "learning_rate": 1.9448143040563033e-06, "loss": 0.7631, "step": 16360 }, { "epoch": 0.09730667950615522, "grad_norm": 13.127087593078613, "learning_rate": 1.9460031385229923e-06, "loss": 0.7581, "step": 16370 }, { "epoch": 0.09736612158282362, "grad_norm": 11.431747436523438, "learning_rate": 1.947191972989681e-06, "loss": 0.718, "step": 16380 }, { "epoch": 0.09742556365949201, "grad_norm": 10.58029842376709, "learning_rate": 1.9483808074563697e-06, "loss": 0.8083, "step": 16390 }, { "epoch": 0.0974850057361604, "grad_norm": 10.976991653442383, "learning_rate": 1.949569641923059e-06, "loss": 0.7866, "step": 16400 }, { "epoch": 0.09754444781282878, "grad_norm": 10.3513765335083, "learning_rate": 1.9507584763897476e-06, "loss": 0.7669, "step": 16410 }, { "epoch": 0.09760388988949718, "grad_norm": 13.556199073791504, "learning_rate": 1.9519473108564365e-06, "loss": 0.7373, "step": 16420 }, { "epoch": 0.09766333196616557, "grad_norm": 9.999956130981445, "learning_rate": 1.9531361453231254e-06, "loss": 0.7482, "step": 16430 }, { "epoch": 0.09772277404283396, "grad_norm": 11.59538745880127, "learning_rate": 1.9543249797898143e-06, "loss": 0.7706, "step": 16440 }, { "epoch": 0.09778221611950236, "grad_norm": 8.893181800842285, "learning_rate": 1.955513814256503e-06, "loss": 0.7857, "step": 16450 }, { "epoch": 0.09784165819617074, "grad_norm": 10.688750267028809, "learning_rate": 1.9567026487231918e-06, "loss": 0.7633, "step": 16460 }, { "epoch": 0.09790110027283913, "grad_norm": 11.21458625793457, "learning_rate": 1.9578914831898807e-06, "loss": 0.7874, "step": 16470 }, { "epoch": 0.09796054234950752, "grad_norm": 11.843908309936523, "learning_rate": 1.9590803176565696e-06, "loss": 0.794, "step": 16480 }, { "epoch": 0.09801998442617592, "grad_norm": 10.666094779968262, "learning_rate": 1.9602691521232586e-06, "loss": 0.6977, "step": 16490 }, { "epoch": 0.0980794265028443, "grad_norm": 10.725217819213867, "learning_rate": 1.9614579865899475e-06, "loss": 0.7266, "step": 16500 }, { "epoch": 0.09813886857951269, "grad_norm": 8.67044448852539, "learning_rate": 1.9626468210566364e-06, "loss": 0.7396, "step": 16510 }, { "epoch": 0.09819831065618108, "grad_norm": 8.641218185424805, "learning_rate": 1.963835655523325e-06, "loss": 0.784, "step": 16520 }, { "epoch": 0.09825775273284948, "grad_norm": 10.298503875732422, "learning_rate": 1.965024489990014e-06, "loss": 0.7194, "step": 16530 }, { "epoch": 0.09831719480951787, "grad_norm": 11.665681838989258, "learning_rate": 1.9662133244567028e-06, "loss": 0.8395, "step": 16540 }, { "epoch": 0.09837663688618625, "grad_norm": 8.155681610107422, "learning_rate": 1.9674021589233917e-06, "loss": 0.7693, "step": 16550 }, { "epoch": 0.09843607896285464, "grad_norm": 9.053243637084961, "learning_rate": 1.9685909933900806e-06, "loss": 0.7366, "step": 16560 }, { "epoch": 0.09849552103952304, "grad_norm": 8.096250534057617, "learning_rate": 1.9697798278567695e-06, "loss": 0.6797, "step": 16570 }, { "epoch": 0.09855496311619143, "grad_norm": 11.175585746765137, "learning_rate": 1.9709686623234585e-06, "loss": 0.7474, "step": 16580 }, { "epoch": 0.09861440519285981, "grad_norm": 9.962509155273438, "learning_rate": 1.972157496790147e-06, "loss": 0.7353, "step": 16590 }, { "epoch": 0.09867384726952821, "grad_norm": 10.38405704498291, "learning_rate": 1.973346331256836e-06, "loss": 0.781, "step": 16600 }, { "epoch": 0.0987332893461966, "grad_norm": 10.383072853088379, "learning_rate": 1.974535165723525e-06, "loss": 0.7473, "step": 16610 }, { "epoch": 0.09879273142286499, "grad_norm": 8.888578414916992, "learning_rate": 1.9757240001902138e-06, "loss": 0.7634, "step": 16620 }, { "epoch": 0.09885217349953337, "grad_norm": 9.690168380737305, "learning_rate": 1.9769128346569027e-06, "loss": 0.7987, "step": 16630 }, { "epoch": 0.09891161557620178, "grad_norm": 11.200581550598145, "learning_rate": 1.978101669123591e-06, "loss": 0.8128, "step": 16640 }, { "epoch": 0.09897105765287016, "grad_norm": 10.145116806030273, "learning_rate": 1.97929050359028e-06, "loss": 0.7694, "step": 16650 }, { "epoch": 0.09903049972953855, "grad_norm": 9.551946640014648, "learning_rate": 1.980479338056969e-06, "loss": 0.754, "step": 16660 }, { "epoch": 0.09908994180620694, "grad_norm": 8.535236358642578, "learning_rate": 1.981668172523658e-06, "loss": 0.6777, "step": 16670 }, { "epoch": 0.09914938388287534, "grad_norm": 9.574967384338379, "learning_rate": 1.982857006990347e-06, "loss": 0.7378, "step": 16680 }, { "epoch": 0.09920882595954372, "grad_norm": 9.209604263305664, "learning_rate": 1.984045841457036e-06, "loss": 0.7198, "step": 16690 }, { "epoch": 0.09926826803621211, "grad_norm": 8.299932479858398, "learning_rate": 1.9852346759237243e-06, "loss": 0.7495, "step": 16700 }, { "epoch": 0.09932771011288051, "grad_norm": 10.961230278015137, "learning_rate": 1.9864235103904133e-06, "loss": 0.7634, "step": 16710 }, { "epoch": 0.0993871521895489, "grad_norm": 10.769335746765137, "learning_rate": 1.987612344857102e-06, "loss": 0.8067, "step": 16720 }, { "epoch": 0.09944659426621728, "grad_norm": 8.702043533325195, "learning_rate": 1.988801179323791e-06, "loss": 0.764, "step": 16730 }, { "epoch": 0.09950603634288567, "grad_norm": 12.487387657165527, "learning_rate": 1.98999001379048e-06, "loss": 0.8078, "step": 16740 }, { "epoch": 0.09956547841955407, "grad_norm": 10.690108299255371, "learning_rate": 1.991178848257169e-06, "loss": 0.7326, "step": 16750 }, { "epoch": 0.09962492049622246, "grad_norm": 9.723703384399414, "learning_rate": 1.992367682723858e-06, "loss": 0.7857, "step": 16760 }, { "epoch": 0.09968436257289084, "grad_norm": 11.64887809753418, "learning_rate": 1.9935565171905464e-06, "loss": 0.7888, "step": 16770 }, { "epoch": 0.09974380464955923, "grad_norm": 12.322816848754883, "learning_rate": 1.9947453516572353e-06, "loss": 0.7522, "step": 16780 }, { "epoch": 0.09980324672622763, "grad_norm": 11.760116577148438, "learning_rate": 1.9959341861239243e-06, "loss": 0.7362, "step": 16790 }, { "epoch": 0.09986268880289602, "grad_norm": 12.505452156066895, "learning_rate": 1.997123020590613e-06, "loss": 0.7163, "step": 16800 }, { "epoch": 0.0999221308795644, "grad_norm": 11.264154434204102, "learning_rate": 1.998311855057302e-06, "loss": 0.7475, "step": 16810 }, { "epoch": 0.09998157295623279, "grad_norm": 13.833085060119629, "learning_rate": 1.9995006895239906e-06, "loss": 0.7502, "step": 16820 }, { "epoch": 0.10004101503290119, "grad_norm": 10.539326667785645, "learning_rate": 2.00068952399068e-06, "loss": 0.7375, "step": 16830 }, { "epoch": 0.10010045710956958, "grad_norm": 12.645694732666016, "learning_rate": 2.0018783584573685e-06, "loss": 0.7931, "step": 16840 }, { "epoch": 0.10015989918623797, "grad_norm": 9.724732398986816, "learning_rate": 2.0030671929240574e-06, "loss": 0.7164, "step": 16850 }, { "epoch": 0.10021934126290637, "grad_norm": 12.657097816467285, "learning_rate": 2.0042560273907463e-06, "loss": 0.7981, "step": 16860 }, { "epoch": 0.10027878333957475, "grad_norm": 9.458022117614746, "learning_rate": 2.0054448618574352e-06, "loss": 0.7894, "step": 16870 }, { "epoch": 0.10033822541624314, "grad_norm": 12.86501407623291, "learning_rate": 2.006633696324124e-06, "loss": 0.7809, "step": 16880 }, { "epoch": 0.10039766749291153, "grad_norm": 11.348372459411621, "learning_rate": 2.0078225307908127e-06, "loss": 0.8356, "step": 16890 }, { "epoch": 0.10045710956957993, "grad_norm": 10.766072273254395, "learning_rate": 2.0090113652575016e-06, "loss": 0.7548, "step": 16900 }, { "epoch": 0.10051655164624831, "grad_norm": 12.977812767028809, "learning_rate": 2.0102001997241905e-06, "loss": 0.7284, "step": 16910 }, { "epoch": 0.1005759937229167, "grad_norm": 10.316990852355957, "learning_rate": 2.0113890341908795e-06, "loss": 0.7653, "step": 16920 }, { "epoch": 0.10063543579958509, "grad_norm": 9.218330383300781, "learning_rate": 2.0125778686575684e-06, "loss": 0.7293, "step": 16930 }, { "epoch": 0.10069487787625349, "grad_norm": 8.146860122680664, "learning_rate": 2.0137667031242573e-06, "loss": 0.7032, "step": 16940 }, { "epoch": 0.10075431995292188, "grad_norm": 10.483516693115234, "learning_rate": 2.0149555375909462e-06, "loss": 0.6895, "step": 16950 }, { "epoch": 0.10081376202959026, "grad_norm": 13.628631591796875, "learning_rate": 2.0161443720576347e-06, "loss": 0.797, "step": 16960 }, { "epoch": 0.10087320410625866, "grad_norm": 11.014937400817871, "learning_rate": 2.0173332065243237e-06, "loss": 0.7705, "step": 16970 }, { "epoch": 0.10093264618292705, "grad_norm": 12.87528133392334, "learning_rate": 2.0185220409910126e-06, "loss": 0.7561, "step": 16980 }, { "epoch": 0.10099208825959544, "grad_norm": 12.362678527832031, "learning_rate": 2.0197108754577015e-06, "loss": 0.7442, "step": 16990 }, { "epoch": 0.10105153033626382, "grad_norm": 9.870333671569824, "learning_rate": 2.02089970992439e-06, "loss": 0.717, "step": 17000 }, { "epoch": 0.10111097241293222, "grad_norm": 9.596346855163574, "learning_rate": 2.0220885443910794e-06, "loss": 0.7404, "step": 17010 }, { "epoch": 0.10117041448960061, "grad_norm": 11.020434379577637, "learning_rate": 2.023277378857768e-06, "loss": 0.7559, "step": 17020 }, { "epoch": 0.101229856566269, "grad_norm": 9.689000129699707, "learning_rate": 2.024466213324457e-06, "loss": 0.7197, "step": 17030 }, { "epoch": 0.10128929864293738, "grad_norm": 10.417816162109375, "learning_rate": 2.0256550477911457e-06, "loss": 0.8026, "step": 17040 }, { "epoch": 0.10134874071960578, "grad_norm": 11.456572532653809, "learning_rate": 2.0268438822578347e-06, "loss": 0.7077, "step": 17050 }, { "epoch": 0.10140818279627417, "grad_norm": 14.588096618652344, "learning_rate": 2.0280327167245236e-06, "loss": 0.7735, "step": 17060 }, { "epoch": 0.10146762487294256, "grad_norm": 11.006251335144043, "learning_rate": 2.029221551191212e-06, "loss": 0.7338, "step": 17070 }, { "epoch": 0.10152706694961096, "grad_norm": 10.451055526733398, "learning_rate": 2.030410385657901e-06, "loss": 0.7452, "step": 17080 }, { "epoch": 0.10158650902627935, "grad_norm": 9.92750072479248, "learning_rate": 2.03159922012459e-06, "loss": 0.6616, "step": 17090 }, { "epoch": 0.10164595110294773, "grad_norm": 9.952754020690918, "learning_rate": 2.032788054591279e-06, "loss": 0.766, "step": 17100 }, { "epoch": 0.10170539317961612, "grad_norm": 9.754246711730957, "learning_rate": 2.033976889057968e-06, "loss": 0.7647, "step": 17110 }, { "epoch": 0.10176483525628452, "grad_norm": 10.858220100402832, "learning_rate": 2.0351657235246567e-06, "loss": 0.7203, "step": 17120 }, { "epoch": 0.1018242773329529, "grad_norm": 11.362920761108398, "learning_rate": 2.0363545579913457e-06, "loss": 0.7953, "step": 17130 }, { "epoch": 0.10188371940962129, "grad_norm": 9.685192108154297, "learning_rate": 2.037543392458034e-06, "loss": 0.736, "step": 17140 }, { "epoch": 0.10194316148628968, "grad_norm": 9.38544750213623, "learning_rate": 2.038732226924723e-06, "loss": 0.6982, "step": 17150 }, { "epoch": 0.10200260356295808, "grad_norm": 9.728601455688477, "learning_rate": 2.039921061391412e-06, "loss": 0.7583, "step": 17160 }, { "epoch": 0.10206204563962647, "grad_norm": 8.077019691467285, "learning_rate": 2.041109895858101e-06, "loss": 0.7685, "step": 17170 }, { "epoch": 0.10212148771629485, "grad_norm": 10.762063026428223, "learning_rate": 2.04229873032479e-06, "loss": 0.7922, "step": 17180 }, { "epoch": 0.10218092979296324, "grad_norm": 9.517860412597656, "learning_rate": 2.043487564791479e-06, "loss": 0.7643, "step": 17190 }, { "epoch": 0.10224037186963164, "grad_norm": 8.51367473602295, "learning_rate": 2.0446763992581677e-06, "loss": 0.7151, "step": 17200 }, { "epoch": 0.10229981394630003, "grad_norm": 13.25008487701416, "learning_rate": 2.0458652337248562e-06, "loss": 0.7383, "step": 17210 }, { "epoch": 0.10235925602296841, "grad_norm": 10.010632514953613, "learning_rate": 2.047054068191545e-06, "loss": 0.8051, "step": 17220 }, { "epoch": 0.10241869809963682, "grad_norm": 13.460597038269043, "learning_rate": 2.048242902658234e-06, "loss": 0.739, "step": 17230 }, { "epoch": 0.1024781401763052, "grad_norm": 9.870842933654785, "learning_rate": 2.049431737124923e-06, "loss": 0.7805, "step": 17240 }, { "epoch": 0.10253758225297359, "grad_norm": 11.286738395690918, "learning_rate": 2.0506205715916115e-06, "loss": 0.7811, "step": 17250 }, { "epoch": 0.10259702432964198, "grad_norm": 9.920714378356934, "learning_rate": 2.0518094060583004e-06, "loss": 0.7808, "step": 17260 }, { "epoch": 0.10265646640631038, "grad_norm": 9.114487648010254, "learning_rate": 2.0529982405249894e-06, "loss": 0.768, "step": 17270 }, { "epoch": 0.10271590848297876, "grad_norm": 9.886725425720215, "learning_rate": 2.0541870749916783e-06, "loss": 0.7503, "step": 17280 }, { "epoch": 0.10277535055964715, "grad_norm": 13.040617942810059, "learning_rate": 2.0553759094583672e-06, "loss": 0.8033, "step": 17290 }, { "epoch": 0.10283479263631554, "grad_norm": 8.517128944396973, "learning_rate": 2.056564743925056e-06, "loss": 0.6707, "step": 17300 }, { "epoch": 0.10289423471298394, "grad_norm": 8.76494026184082, "learning_rate": 2.057753578391745e-06, "loss": 0.7272, "step": 17310 }, { "epoch": 0.10295367678965232, "grad_norm": 9.980447769165039, "learning_rate": 2.0589424128584336e-06, "loss": 0.7693, "step": 17320 }, { "epoch": 0.10301311886632071, "grad_norm": 11.817176818847656, "learning_rate": 2.0601312473251225e-06, "loss": 0.7239, "step": 17330 }, { "epoch": 0.10307256094298911, "grad_norm": 12.098893165588379, "learning_rate": 2.0613200817918114e-06, "loss": 0.7561, "step": 17340 }, { "epoch": 0.1031320030196575, "grad_norm": 8.566449165344238, "learning_rate": 2.0625089162585004e-06, "loss": 0.7536, "step": 17350 }, { "epoch": 0.10319144509632588, "grad_norm": 10.820157051086426, "learning_rate": 2.0636977507251893e-06, "loss": 0.7497, "step": 17360 }, { "epoch": 0.10325088717299427, "grad_norm": 10.587133407592773, "learning_rate": 2.0648865851918782e-06, "loss": 0.6698, "step": 17370 }, { "epoch": 0.10331032924966267, "grad_norm": 10.688446998596191, "learning_rate": 2.066075419658567e-06, "loss": 0.7833, "step": 17380 }, { "epoch": 0.10336977132633106, "grad_norm": 10.256271362304688, "learning_rate": 2.0672642541252557e-06, "loss": 0.7908, "step": 17390 }, { "epoch": 0.10342921340299945, "grad_norm": 11.947494506835938, "learning_rate": 2.0684530885919446e-06, "loss": 0.7822, "step": 17400 }, { "epoch": 0.10348865547966783, "grad_norm": 9.293892860412598, "learning_rate": 2.0696419230586335e-06, "loss": 0.7719, "step": 17410 }, { "epoch": 0.10354809755633623, "grad_norm": 9.793558120727539, "learning_rate": 2.0708307575253224e-06, "loss": 0.7582, "step": 17420 }, { "epoch": 0.10360753963300462, "grad_norm": 10.41965389251709, "learning_rate": 2.072019591992011e-06, "loss": 0.7533, "step": 17430 }, { "epoch": 0.103666981709673, "grad_norm": 11.404095649719238, "learning_rate": 2.0732084264587003e-06, "loss": 0.7997, "step": 17440 }, { "epoch": 0.10372642378634139, "grad_norm": 10.559000968933105, "learning_rate": 2.0743972609253892e-06, "loss": 0.7508, "step": 17450 }, { "epoch": 0.1037858658630098, "grad_norm": 13.05065631866455, "learning_rate": 2.0755860953920777e-06, "loss": 0.7774, "step": 17460 }, { "epoch": 0.10384530793967818, "grad_norm": 11.67325496673584, "learning_rate": 2.0767749298587667e-06, "loss": 0.7628, "step": 17470 }, { "epoch": 0.10390475001634657, "grad_norm": 11.26274299621582, "learning_rate": 2.0779637643254556e-06, "loss": 0.7636, "step": 17480 }, { "epoch": 0.10396419209301497, "grad_norm": 10.85408878326416, "learning_rate": 2.0791525987921445e-06, "loss": 0.7236, "step": 17490 }, { "epoch": 0.10402363416968335, "grad_norm": 9.581521987915039, "learning_rate": 2.080341433258833e-06, "loss": 0.7739, "step": 17500 }, { "epoch": 0.10408307624635174, "grad_norm": 10.612286567687988, "learning_rate": 2.081530267725522e-06, "loss": 0.7058, "step": 17510 }, { "epoch": 0.10414251832302013, "grad_norm": 10.078804016113281, "learning_rate": 2.082719102192211e-06, "loss": 0.7605, "step": 17520 }, { "epoch": 0.10420196039968853, "grad_norm": 15.312239646911621, "learning_rate": 2.0839079366589e-06, "loss": 0.8447, "step": 17530 }, { "epoch": 0.10426140247635692, "grad_norm": 14.170583724975586, "learning_rate": 2.0850967711255887e-06, "loss": 0.7962, "step": 17540 }, { "epoch": 0.1043208445530253, "grad_norm": 11.243409156799316, "learning_rate": 2.0862856055922776e-06, "loss": 0.8457, "step": 17550 }, { "epoch": 0.10438028662969369, "grad_norm": 10.997483253479004, "learning_rate": 2.0874744400589666e-06, "loss": 0.8097, "step": 17560 }, { "epoch": 0.10443972870636209, "grad_norm": 12.675244331359863, "learning_rate": 2.088663274525655e-06, "loss": 0.8053, "step": 17570 }, { "epoch": 0.10449917078303048, "grad_norm": 11.769153594970703, "learning_rate": 2.089852108992344e-06, "loss": 0.7132, "step": 17580 }, { "epoch": 0.10455861285969886, "grad_norm": 10.45942211151123, "learning_rate": 2.091040943459033e-06, "loss": 0.734, "step": 17590 }, { "epoch": 0.10461805493636726, "grad_norm": 9.207300186157227, "learning_rate": 2.092229777925722e-06, "loss": 0.7532, "step": 17600 }, { "epoch": 0.10467749701303565, "grad_norm": 9.1074800491333, "learning_rate": 2.0934186123924108e-06, "loss": 0.6921, "step": 17610 }, { "epoch": 0.10473693908970404, "grad_norm": 12.562270164489746, "learning_rate": 2.0946074468590997e-06, "loss": 0.7527, "step": 17620 }, { "epoch": 0.10479638116637242, "grad_norm": 11.152753829956055, "learning_rate": 2.0957962813257886e-06, "loss": 0.6511, "step": 17630 }, { "epoch": 0.10485582324304082, "grad_norm": 10.805837631225586, "learning_rate": 2.096985115792477e-06, "loss": 0.7291, "step": 17640 }, { "epoch": 0.10491526531970921, "grad_norm": 11.70364761352539, "learning_rate": 2.098173950259166e-06, "loss": 0.7908, "step": 17650 }, { "epoch": 0.1049747073963776, "grad_norm": 11.292640686035156, "learning_rate": 2.099362784725855e-06, "loss": 0.71, "step": 17660 }, { "epoch": 0.10503414947304598, "grad_norm": 10.403047561645508, "learning_rate": 2.100551619192544e-06, "loss": 0.7814, "step": 17670 }, { "epoch": 0.10509359154971439, "grad_norm": 10.897653579711914, "learning_rate": 2.1017404536592324e-06, "loss": 0.7787, "step": 17680 }, { "epoch": 0.10515303362638277, "grad_norm": 8.999744415283203, "learning_rate": 2.1029292881259214e-06, "loss": 0.6489, "step": 17690 }, { "epoch": 0.10521247570305116, "grad_norm": 12.14113998413086, "learning_rate": 2.1041181225926107e-06, "loss": 0.7173, "step": 17700 }, { "epoch": 0.10527191777971955, "grad_norm": 12.385700225830078, "learning_rate": 2.105306957059299e-06, "loss": 0.7829, "step": 17710 }, { "epoch": 0.10533135985638795, "grad_norm": 11.093170166015625, "learning_rate": 2.106495791525988e-06, "loss": 0.742, "step": 17720 }, { "epoch": 0.10539080193305633, "grad_norm": 11.596714973449707, "learning_rate": 2.107684625992677e-06, "loss": 0.7409, "step": 17730 }, { "epoch": 0.10545024400972472, "grad_norm": 8.429838180541992, "learning_rate": 2.108873460459366e-06, "loss": 0.6963, "step": 17740 }, { "epoch": 0.10550968608639312, "grad_norm": 9.264322280883789, "learning_rate": 2.1100622949260545e-06, "loss": 0.7596, "step": 17750 }, { "epoch": 0.1055691281630615, "grad_norm": 8.882568359375, "learning_rate": 2.1112511293927434e-06, "loss": 0.7749, "step": 17760 }, { "epoch": 0.1056285702397299, "grad_norm": 12.350900650024414, "learning_rate": 2.1124399638594324e-06, "loss": 0.8085, "step": 17770 }, { "epoch": 0.10568801231639828, "grad_norm": 11.570781707763672, "learning_rate": 2.1136287983261213e-06, "loss": 0.6991, "step": 17780 }, { "epoch": 0.10574745439306668, "grad_norm": 9.276108741760254, "learning_rate": 2.11481763279281e-06, "loss": 0.7482, "step": 17790 }, { "epoch": 0.10580689646973507, "grad_norm": 9.877376556396484, "learning_rate": 2.116006467259499e-06, "loss": 0.7941, "step": 17800 }, { "epoch": 0.10586633854640345, "grad_norm": 12.91211223602295, "learning_rate": 2.117195301726188e-06, "loss": 0.8037, "step": 17810 }, { "epoch": 0.10592578062307184, "grad_norm": 11.298558235168457, "learning_rate": 2.1183841361928766e-06, "loss": 0.6871, "step": 17820 }, { "epoch": 0.10598522269974024, "grad_norm": 12.093796730041504, "learning_rate": 2.1195729706595655e-06, "loss": 0.6814, "step": 17830 }, { "epoch": 0.10604466477640863, "grad_norm": 12.196523666381836, "learning_rate": 2.1207618051262544e-06, "loss": 0.7459, "step": 17840 }, { "epoch": 0.10610410685307702, "grad_norm": 10.116848945617676, "learning_rate": 2.1219506395929433e-06, "loss": 0.7769, "step": 17850 }, { "epoch": 0.10616354892974542, "grad_norm": 10.360147476196289, "learning_rate": 2.123139474059632e-06, "loss": 0.7664, "step": 17860 }, { "epoch": 0.1062229910064138, "grad_norm": 10.095897674560547, "learning_rate": 2.124328308526321e-06, "loss": 0.7561, "step": 17870 }, { "epoch": 0.10628243308308219, "grad_norm": 9.415559768676758, "learning_rate": 2.12551714299301e-06, "loss": 0.6995, "step": 17880 }, { "epoch": 0.10634187515975058, "grad_norm": 12.968849182128906, "learning_rate": 2.1267059774596986e-06, "loss": 0.783, "step": 17890 }, { "epoch": 0.10640131723641898, "grad_norm": 13.044649124145508, "learning_rate": 2.1278948119263876e-06, "loss": 0.7401, "step": 17900 }, { "epoch": 0.10646075931308736, "grad_norm": 9.787032127380371, "learning_rate": 2.1290836463930765e-06, "loss": 0.7714, "step": 17910 }, { "epoch": 0.10652020138975575, "grad_norm": 11.592789649963379, "learning_rate": 2.1302724808597654e-06, "loss": 0.8041, "step": 17920 }, { "epoch": 0.10657964346642414, "grad_norm": 11.499961853027344, "learning_rate": 2.131461315326454e-06, "loss": 0.7127, "step": 17930 }, { "epoch": 0.10663908554309254, "grad_norm": 10.853729248046875, "learning_rate": 2.132650149793143e-06, "loss": 0.7904, "step": 17940 }, { "epoch": 0.10669852761976092, "grad_norm": 10.562909126281738, "learning_rate": 2.1338389842598318e-06, "loss": 0.7172, "step": 17950 }, { "epoch": 0.10675796969642931, "grad_norm": 10.553800582885742, "learning_rate": 2.1350278187265207e-06, "loss": 0.7995, "step": 17960 }, { "epoch": 0.10681741177309771, "grad_norm": 9.356748580932617, "learning_rate": 2.1362166531932096e-06, "loss": 0.7486, "step": 17970 }, { "epoch": 0.1068768538497661, "grad_norm": 12.746908187866211, "learning_rate": 2.1374054876598986e-06, "loss": 0.7993, "step": 17980 }, { "epoch": 0.10693629592643449, "grad_norm": 11.02595043182373, "learning_rate": 2.1385943221265875e-06, "loss": 0.7856, "step": 17990 }, { "epoch": 0.10699573800310287, "grad_norm": 8.544249534606934, "learning_rate": 2.139783156593276e-06, "loss": 0.7358, "step": 18000 }, { "epoch": 0.10705518007977127, "grad_norm": 10.648174285888672, "learning_rate": 2.140971991059965e-06, "loss": 0.739, "step": 18010 }, { "epoch": 0.10711462215643966, "grad_norm": 9.946576118469238, "learning_rate": 2.142160825526654e-06, "loss": 0.7409, "step": 18020 }, { "epoch": 0.10717406423310805, "grad_norm": 8.561016082763672, "learning_rate": 2.1433496599933428e-06, "loss": 0.7137, "step": 18030 }, { "epoch": 0.10723350630977643, "grad_norm": 14.880345344543457, "learning_rate": 2.1445384944600313e-06, "loss": 0.7942, "step": 18040 }, { "epoch": 0.10729294838644483, "grad_norm": 10.800291061401367, "learning_rate": 2.1457273289267206e-06, "loss": 0.7683, "step": 18050 }, { "epoch": 0.10735239046311322, "grad_norm": 9.968802452087402, "learning_rate": 2.1469161633934095e-06, "loss": 0.7702, "step": 18060 }, { "epoch": 0.10741183253978161, "grad_norm": 7.821796894073486, "learning_rate": 2.148104997860098e-06, "loss": 0.7836, "step": 18070 }, { "epoch": 0.10747127461645, "grad_norm": 12.348113059997559, "learning_rate": 2.149293832326787e-06, "loss": 0.7468, "step": 18080 }, { "epoch": 0.1075307166931184, "grad_norm": 14.050555229187012, "learning_rate": 2.150482666793476e-06, "loss": 0.7624, "step": 18090 }, { "epoch": 0.10759015876978678, "grad_norm": 10.143348693847656, "learning_rate": 2.151671501260165e-06, "loss": 0.7681, "step": 18100 }, { "epoch": 0.10764960084645517, "grad_norm": 11.202975273132324, "learning_rate": 2.1528603357268533e-06, "loss": 0.745, "step": 18110 }, { "epoch": 0.10770904292312357, "grad_norm": 10.797491073608398, "learning_rate": 2.1540491701935423e-06, "loss": 0.7237, "step": 18120 }, { "epoch": 0.10776848499979196, "grad_norm": 10.87301254272461, "learning_rate": 2.1552380046602316e-06, "loss": 0.6777, "step": 18130 }, { "epoch": 0.10782792707646034, "grad_norm": 8.182631492614746, "learning_rate": 2.15642683912692e-06, "loss": 0.7074, "step": 18140 }, { "epoch": 0.10788736915312873, "grad_norm": 10.436033248901367, "learning_rate": 2.157615673593609e-06, "loss": 0.6984, "step": 18150 }, { "epoch": 0.10794681122979713, "grad_norm": 10.529823303222656, "learning_rate": 2.158804508060298e-06, "loss": 0.7296, "step": 18160 }, { "epoch": 0.10800625330646552, "grad_norm": 11.20511531829834, "learning_rate": 2.159993342526987e-06, "loss": 0.7733, "step": 18170 }, { "epoch": 0.1080656953831339, "grad_norm": 9.20083999633789, "learning_rate": 2.1611821769936754e-06, "loss": 0.7086, "step": 18180 }, { "epoch": 0.10812513745980229, "grad_norm": 9.988897323608398, "learning_rate": 2.1623710114603643e-06, "loss": 0.7193, "step": 18190 }, { "epoch": 0.10818457953647069, "grad_norm": 9.91787052154541, "learning_rate": 2.1635598459270533e-06, "loss": 0.7062, "step": 18200 }, { "epoch": 0.10824402161313908, "grad_norm": 13.502981185913086, "learning_rate": 2.164748680393742e-06, "loss": 0.7602, "step": 18210 }, { "epoch": 0.10830346368980746, "grad_norm": 11.24836540222168, "learning_rate": 2.165937514860431e-06, "loss": 0.7438, "step": 18220 }, { "epoch": 0.10836290576647586, "grad_norm": 9.867267608642578, "learning_rate": 2.16712634932712e-06, "loss": 0.7364, "step": 18230 }, { "epoch": 0.10842234784314425, "grad_norm": 8.39268970489502, "learning_rate": 2.168315183793809e-06, "loss": 0.6952, "step": 18240 }, { "epoch": 0.10848178991981264, "grad_norm": 8.803580284118652, "learning_rate": 2.1695040182604975e-06, "loss": 0.692, "step": 18250 }, { "epoch": 0.10854123199648102, "grad_norm": 10.139150619506836, "learning_rate": 2.1706928527271864e-06, "loss": 0.7232, "step": 18260 }, { "epoch": 0.10860067407314943, "grad_norm": 8.927245140075684, "learning_rate": 2.1718816871938753e-06, "loss": 0.7805, "step": 18270 }, { "epoch": 0.10866011614981781, "grad_norm": 9.930002212524414, "learning_rate": 2.1730705216605643e-06, "loss": 0.7468, "step": 18280 }, { "epoch": 0.1087195582264862, "grad_norm": 8.646323204040527, "learning_rate": 2.1742593561272528e-06, "loss": 0.7479, "step": 18290 }, { "epoch": 0.10877900030315459, "grad_norm": 9.39854907989502, "learning_rate": 2.1754481905939417e-06, "loss": 0.7243, "step": 18300 }, { "epoch": 0.10883844237982299, "grad_norm": 10.965150833129883, "learning_rate": 2.176637025060631e-06, "loss": 0.7726, "step": 18310 }, { "epoch": 0.10889788445649137, "grad_norm": 12.2196044921875, "learning_rate": 2.1778258595273195e-06, "loss": 0.7702, "step": 18320 }, { "epoch": 0.10895732653315976, "grad_norm": 10.2701416015625, "learning_rate": 2.1790146939940085e-06, "loss": 0.6962, "step": 18330 }, { "epoch": 0.10901676860982815, "grad_norm": 7.442998886108398, "learning_rate": 2.1802035284606974e-06, "loss": 0.7287, "step": 18340 }, { "epoch": 0.10907621068649655, "grad_norm": 9.52354907989502, "learning_rate": 2.1813923629273863e-06, "loss": 0.7581, "step": 18350 }, { "epoch": 0.10913565276316493, "grad_norm": 12.335363388061523, "learning_rate": 2.182581197394075e-06, "loss": 0.7484, "step": 18360 }, { "epoch": 0.10919509483983332, "grad_norm": 9.854231834411621, "learning_rate": 2.1837700318607638e-06, "loss": 0.7512, "step": 18370 }, { "epoch": 0.10925453691650172, "grad_norm": 9.634353637695312, "learning_rate": 2.1849588663274527e-06, "loss": 0.7923, "step": 18380 }, { "epoch": 0.10931397899317011, "grad_norm": 10.328507423400879, "learning_rate": 2.1861477007941416e-06, "loss": 0.716, "step": 18390 }, { "epoch": 0.1093734210698385, "grad_norm": 13.964932441711426, "learning_rate": 2.1873365352608305e-06, "loss": 0.7504, "step": 18400 }, { "epoch": 0.10943286314650688, "grad_norm": 13.084938049316406, "learning_rate": 2.1885253697275195e-06, "loss": 0.7896, "step": 18410 }, { "epoch": 0.10949230522317528, "grad_norm": 9.407565116882324, "learning_rate": 2.1897142041942084e-06, "loss": 0.7181, "step": 18420 }, { "epoch": 0.10955174729984367, "grad_norm": 11.520950317382812, "learning_rate": 2.190903038660897e-06, "loss": 0.7445, "step": 18430 }, { "epoch": 0.10961118937651206, "grad_norm": 9.407510757446289, "learning_rate": 2.192091873127586e-06, "loss": 0.7524, "step": 18440 }, { "epoch": 0.10967063145318044, "grad_norm": 9.800614356994629, "learning_rate": 2.1932807075942747e-06, "loss": 0.7174, "step": 18450 }, { "epoch": 0.10973007352984884, "grad_norm": 9.599642753601074, "learning_rate": 2.1944695420609637e-06, "loss": 0.6951, "step": 18460 }, { "epoch": 0.10978951560651723, "grad_norm": 8.379483222961426, "learning_rate": 2.195658376527652e-06, "loss": 0.7484, "step": 18470 }, { "epoch": 0.10984895768318562, "grad_norm": 12.386651039123535, "learning_rate": 2.1968472109943415e-06, "loss": 0.7443, "step": 18480 }, { "epoch": 0.10990839975985402, "grad_norm": 11.647781372070312, "learning_rate": 2.1980360454610305e-06, "loss": 0.7226, "step": 18490 }, { "epoch": 0.1099678418365224, "grad_norm": 11.309982299804688, "learning_rate": 2.199224879927719e-06, "loss": 0.7438, "step": 18500 }, { "epoch": 0.11002728391319079, "grad_norm": 8.883115768432617, "learning_rate": 2.200413714394408e-06, "loss": 0.8187, "step": 18510 }, { "epoch": 0.11008672598985918, "grad_norm": 11.579144477844238, "learning_rate": 2.201602548861097e-06, "loss": 0.8465, "step": 18520 }, { "epoch": 0.11014616806652758, "grad_norm": 11.408599853515625, "learning_rate": 2.2027913833277857e-06, "loss": 0.6775, "step": 18530 }, { "epoch": 0.11020561014319596, "grad_norm": 10.339399337768555, "learning_rate": 2.2039802177944742e-06, "loss": 0.7617, "step": 18540 }, { "epoch": 0.11026505221986435, "grad_norm": 12.182334899902344, "learning_rate": 2.205169052261163e-06, "loss": 0.7781, "step": 18550 }, { "epoch": 0.11032449429653274, "grad_norm": 12.490960121154785, "learning_rate": 2.206357886727852e-06, "loss": 0.7365, "step": 18560 }, { "epoch": 0.11038393637320114, "grad_norm": 12.409377098083496, "learning_rate": 2.207546721194541e-06, "loss": 0.7501, "step": 18570 }, { "epoch": 0.11044337844986953, "grad_norm": 11.25017261505127, "learning_rate": 2.20873555566123e-06, "loss": 0.7118, "step": 18580 }, { "epoch": 0.11050282052653791, "grad_norm": 12.152484893798828, "learning_rate": 2.209924390127919e-06, "loss": 0.7232, "step": 18590 }, { "epoch": 0.1105622626032063, "grad_norm": 12.295985221862793, "learning_rate": 2.211113224594608e-06, "loss": 0.7362, "step": 18600 }, { "epoch": 0.1106217046798747, "grad_norm": 8.61794662475586, "learning_rate": 2.2123020590612963e-06, "loss": 0.7001, "step": 18610 }, { "epoch": 0.11068114675654309, "grad_norm": 8.509894371032715, "learning_rate": 2.2134908935279852e-06, "loss": 0.7009, "step": 18620 }, { "epoch": 0.11074058883321147, "grad_norm": 11.862300872802734, "learning_rate": 2.214679727994674e-06, "loss": 0.7525, "step": 18630 }, { "epoch": 0.11080003090987987, "grad_norm": 10.638354301452637, "learning_rate": 2.215868562461363e-06, "loss": 0.7316, "step": 18640 }, { "epoch": 0.11085947298654826, "grad_norm": 10.578339576721191, "learning_rate": 2.217057396928052e-06, "loss": 0.7456, "step": 18650 }, { "epoch": 0.11091891506321665, "grad_norm": 8.502289772033691, "learning_rate": 2.218246231394741e-06, "loss": 0.7198, "step": 18660 }, { "epoch": 0.11097835713988503, "grad_norm": 12.356983184814453, "learning_rate": 2.21943506586143e-06, "loss": 0.7781, "step": 18670 }, { "epoch": 0.11103779921655343, "grad_norm": 9.149943351745605, "learning_rate": 2.2206239003281184e-06, "loss": 0.7412, "step": 18680 }, { "epoch": 0.11109724129322182, "grad_norm": 12.502336502075195, "learning_rate": 2.2218127347948073e-06, "loss": 0.7596, "step": 18690 }, { "epoch": 0.11115668336989021, "grad_norm": 16.033504486083984, "learning_rate": 2.2230015692614962e-06, "loss": 0.7186, "step": 18700 }, { "epoch": 0.1112161254465586, "grad_norm": 11.340635299682617, "learning_rate": 2.224190403728185e-06, "loss": 0.7824, "step": 18710 }, { "epoch": 0.111275567523227, "grad_norm": 10.997785568237305, "learning_rate": 2.2253792381948737e-06, "loss": 0.7073, "step": 18720 }, { "epoch": 0.11133500959989538, "grad_norm": 9.157291412353516, "learning_rate": 2.2265680726615626e-06, "loss": 0.7074, "step": 18730 }, { "epoch": 0.11139445167656377, "grad_norm": 10.022640228271484, "learning_rate": 2.227756907128252e-06, "loss": 0.7319, "step": 18740 }, { "epoch": 0.11145389375323217, "grad_norm": 10.14691162109375, "learning_rate": 2.2289457415949405e-06, "loss": 0.794, "step": 18750 }, { "epoch": 0.11151333582990056, "grad_norm": 11.629241943359375, "learning_rate": 2.2301345760616294e-06, "loss": 0.7494, "step": 18760 }, { "epoch": 0.11157277790656894, "grad_norm": 10.490216255187988, "learning_rate": 2.2313234105283183e-06, "loss": 0.7016, "step": 18770 }, { "epoch": 0.11163221998323733, "grad_norm": 12.64957046508789, "learning_rate": 2.2325122449950072e-06, "loss": 0.7488, "step": 18780 }, { "epoch": 0.11169166205990573, "grad_norm": 13.694518089294434, "learning_rate": 2.2337010794616957e-06, "loss": 0.7105, "step": 18790 }, { "epoch": 0.11175110413657412, "grad_norm": 11.317032814025879, "learning_rate": 2.2348899139283847e-06, "loss": 0.7649, "step": 18800 }, { "epoch": 0.1118105462132425, "grad_norm": 10.042064666748047, "learning_rate": 2.2360787483950736e-06, "loss": 0.7139, "step": 18810 }, { "epoch": 0.11186998828991089, "grad_norm": 8.655282020568848, "learning_rate": 2.2372675828617625e-06, "loss": 0.7175, "step": 18820 }, { "epoch": 0.11192943036657929, "grad_norm": 8.145418167114258, "learning_rate": 2.2384564173284514e-06, "loss": 0.7287, "step": 18830 }, { "epoch": 0.11198887244324768, "grad_norm": 9.205953598022461, "learning_rate": 2.2396452517951404e-06, "loss": 0.7565, "step": 18840 }, { "epoch": 0.11204831451991606, "grad_norm": 10.561574935913086, "learning_rate": 2.2408340862618293e-06, "loss": 0.7669, "step": 18850 }, { "epoch": 0.11210775659658445, "grad_norm": 12.46120548248291, "learning_rate": 2.242022920728518e-06, "loss": 0.7666, "step": 18860 }, { "epoch": 0.11216719867325285, "grad_norm": 11.523921966552734, "learning_rate": 2.2432117551952067e-06, "loss": 0.7934, "step": 18870 }, { "epoch": 0.11222664074992124, "grad_norm": 10.561534881591797, "learning_rate": 2.2444005896618957e-06, "loss": 0.7094, "step": 18880 }, { "epoch": 0.11228608282658963, "grad_norm": 11.917798042297363, "learning_rate": 2.2455894241285846e-06, "loss": 0.7442, "step": 18890 }, { "epoch": 0.11234552490325803, "grad_norm": 10.851532936096191, "learning_rate": 2.246778258595273e-06, "loss": 0.6764, "step": 18900 }, { "epoch": 0.11240496697992641, "grad_norm": 14.27524185180664, "learning_rate": 2.2479670930619624e-06, "loss": 0.8032, "step": 18910 }, { "epoch": 0.1124644090565948, "grad_norm": 9.805289268493652, "learning_rate": 2.2491559275286514e-06, "loss": 0.788, "step": 18920 }, { "epoch": 0.11252385113326319, "grad_norm": 10.360474586486816, "learning_rate": 2.25034476199534e-06, "loss": 0.742, "step": 18930 }, { "epoch": 0.11258329320993159, "grad_norm": 10.001185417175293, "learning_rate": 2.251533596462029e-06, "loss": 0.7412, "step": 18940 }, { "epoch": 0.11264273528659997, "grad_norm": 9.313411712646484, "learning_rate": 2.2527224309287177e-06, "loss": 0.7489, "step": 18950 }, { "epoch": 0.11270217736326836, "grad_norm": 13.321013450622559, "learning_rate": 2.2539112653954067e-06, "loss": 0.7445, "step": 18960 }, { "epoch": 0.11276161943993675, "grad_norm": 9.99083137512207, "learning_rate": 2.255100099862095e-06, "loss": 0.7103, "step": 18970 }, { "epoch": 0.11282106151660515, "grad_norm": 8.619643211364746, "learning_rate": 2.256288934328784e-06, "loss": 0.7312, "step": 18980 }, { "epoch": 0.11288050359327353, "grad_norm": 9.042521476745605, "learning_rate": 2.257477768795473e-06, "loss": 0.7143, "step": 18990 }, { "epoch": 0.11293994566994192, "grad_norm": 9.28960132598877, "learning_rate": 2.258666603262162e-06, "loss": 0.7126, "step": 19000 }, { "epoch": 0.11299938774661032, "grad_norm": 10.25299072265625, "learning_rate": 2.259855437728851e-06, "loss": 0.7635, "step": 19010 }, { "epoch": 0.11305882982327871, "grad_norm": 10.151208877563477, "learning_rate": 2.26104427219554e-06, "loss": 0.7116, "step": 19020 }, { "epoch": 0.1131182718999471, "grad_norm": 9.405250549316406, "learning_rate": 2.2622331066622287e-06, "loss": 0.7425, "step": 19030 }, { "epoch": 0.11317771397661548, "grad_norm": 10.370013236999512, "learning_rate": 2.2634219411289172e-06, "loss": 0.7514, "step": 19040 }, { "epoch": 0.11323715605328388, "grad_norm": 10.594955444335938, "learning_rate": 2.264610775595606e-06, "loss": 0.7997, "step": 19050 }, { "epoch": 0.11329659812995227, "grad_norm": 9.926047325134277, "learning_rate": 2.265799610062295e-06, "loss": 0.7115, "step": 19060 }, { "epoch": 0.11335604020662066, "grad_norm": 10.08304214477539, "learning_rate": 2.266988444528984e-06, "loss": 0.7317, "step": 19070 }, { "epoch": 0.11341548228328904, "grad_norm": 10.706631660461426, "learning_rate": 2.2681772789956725e-06, "loss": 0.7575, "step": 19080 }, { "epoch": 0.11347492435995744, "grad_norm": 8.160979270935059, "learning_rate": 2.269366113462362e-06, "loss": 0.6771, "step": 19090 }, { "epoch": 0.11353436643662583, "grad_norm": 12.796857833862305, "learning_rate": 2.270554947929051e-06, "loss": 0.7767, "step": 19100 }, { "epoch": 0.11359380851329422, "grad_norm": 10.499809265136719, "learning_rate": 2.2717437823957393e-06, "loss": 0.7907, "step": 19110 }, { "epoch": 0.11365325058996262, "grad_norm": 15.45193099975586, "learning_rate": 2.2729326168624282e-06, "loss": 0.7284, "step": 19120 }, { "epoch": 0.113712692666631, "grad_norm": 10.254090309143066, "learning_rate": 2.274121451329117e-06, "loss": 0.6904, "step": 19130 }, { "epoch": 0.11377213474329939, "grad_norm": 10.181249618530273, "learning_rate": 2.275310285795806e-06, "loss": 0.665, "step": 19140 }, { "epoch": 0.11383157681996778, "grad_norm": 11.06908893585205, "learning_rate": 2.2764991202624946e-06, "loss": 0.762, "step": 19150 }, { "epoch": 0.11389101889663618, "grad_norm": 11.209521293640137, "learning_rate": 2.2776879547291835e-06, "loss": 0.7543, "step": 19160 }, { "epoch": 0.11395046097330457, "grad_norm": 10.464264869689941, "learning_rate": 2.278876789195873e-06, "loss": 0.7278, "step": 19170 }, { "epoch": 0.11400990304997295, "grad_norm": 11.289196014404297, "learning_rate": 2.2800656236625614e-06, "loss": 0.7749, "step": 19180 }, { "epoch": 0.11406934512664134, "grad_norm": 9.923087120056152, "learning_rate": 2.2812544581292503e-06, "loss": 0.6867, "step": 19190 }, { "epoch": 0.11412878720330974, "grad_norm": 11.098031044006348, "learning_rate": 2.2824432925959392e-06, "loss": 0.7863, "step": 19200 }, { "epoch": 0.11418822927997813, "grad_norm": 12.081482887268066, "learning_rate": 2.283632127062628e-06, "loss": 0.8526, "step": 19210 }, { "epoch": 0.11424767135664651, "grad_norm": 10.18440055847168, "learning_rate": 2.2848209615293166e-06, "loss": 0.7513, "step": 19220 }, { "epoch": 0.1143071134333149, "grad_norm": 11.206341743469238, "learning_rate": 2.2860097959960056e-06, "loss": 0.8405, "step": 19230 }, { "epoch": 0.1143665555099833, "grad_norm": 8.15249252319336, "learning_rate": 2.2871986304626945e-06, "loss": 0.778, "step": 19240 }, { "epoch": 0.11442599758665169, "grad_norm": 9.832229614257812, "learning_rate": 2.2883874649293834e-06, "loss": 0.7513, "step": 19250 }, { "epoch": 0.11448543966332007, "grad_norm": 8.446015357971191, "learning_rate": 2.2895762993960724e-06, "loss": 0.7345, "step": 19260 }, { "epoch": 0.11454488173998847, "grad_norm": 10.991095542907715, "learning_rate": 2.2907651338627613e-06, "loss": 0.751, "step": 19270 }, { "epoch": 0.11460432381665686, "grad_norm": 12.109160423278809, "learning_rate": 2.29195396832945e-06, "loss": 0.7438, "step": 19280 }, { "epoch": 0.11466376589332525, "grad_norm": 9.958946228027344, "learning_rate": 2.2931428027961387e-06, "loss": 0.7439, "step": 19290 }, { "epoch": 0.11472320796999363, "grad_norm": 14.242471694946289, "learning_rate": 2.2943316372628276e-06, "loss": 0.8299, "step": 19300 }, { "epoch": 0.11478265004666204, "grad_norm": 11.521811485290527, "learning_rate": 2.2955204717295166e-06, "loss": 0.7329, "step": 19310 }, { "epoch": 0.11484209212333042, "grad_norm": 8.084778785705566, "learning_rate": 2.2967093061962055e-06, "loss": 0.7904, "step": 19320 }, { "epoch": 0.11490153419999881, "grad_norm": 10.073846817016602, "learning_rate": 2.297898140662894e-06, "loss": 0.7151, "step": 19330 }, { "epoch": 0.1149609762766672, "grad_norm": 10.020644187927246, "learning_rate": 2.299086975129583e-06, "loss": 0.709, "step": 19340 }, { "epoch": 0.1150204183533356, "grad_norm": 9.729480743408203, "learning_rate": 2.3002758095962723e-06, "loss": 0.7388, "step": 19350 }, { "epoch": 0.11507986043000398, "grad_norm": 10.795310974121094, "learning_rate": 2.3014646440629608e-06, "loss": 0.7516, "step": 19360 }, { "epoch": 0.11513930250667237, "grad_norm": 9.460122108459473, "learning_rate": 2.3026534785296497e-06, "loss": 0.7326, "step": 19370 }, { "epoch": 0.11519874458334077, "grad_norm": 9.547384262084961, "learning_rate": 2.3038423129963386e-06, "loss": 0.7925, "step": 19380 }, { "epoch": 0.11525818666000916, "grad_norm": 9.555450439453125, "learning_rate": 2.3050311474630276e-06, "loss": 0.7576, "step": 19390 }, { "epoch": 0.11531762873667754, "grad_norm": 11.07591724395752, "learning_rate": 2.306219981929716e-06, "loss": 0.784, "step": 19400 }, { "epoch": 0.11537707081334593, "grad_norm": 11.903983116149902, "learning_rate": 2.307408816396405e-06, "loss": 0.7177, "step": 19410 }, { "epoch": 0.11543651289001433, "grad_norm": 11.959920883178711, "learning_rate": 2.308597650863094e-06, "loss": 0.7758, "step": 19420 }, { "epoch": 0.11549595496668272, "grad_norm": 10.302084922790527, "learning_rate": 2.309786485329783e-06, "loss": 0.7676, "step": 19430 }, { "epoch": 0.1155553970433511, "grad_norm": 11.002155303955078, "learning_rate": 2.3109753197964718e-06, "loss": 0.7358, "step": 19440 }, { "epoch": 0.11561483912001949, "grad_norm": 10.88048267364502, "learning_rate": 2.3121641542631607e-06, "loss": 0.72, "step": 19450 }, { "epoch": 0.11567428119668789, "grad_norm": 9.261578559875488, "learning_rate": 2.3133529887298496e-06, "loss": 0.7768, "step": 19460 }, { "epoch": 0.11573372327335628, "grad_norm": 9.174830436706543, "learning_rate": 2.314541823196538e-06, "loss": 0.7135, "step": 19470 }, { "epoch": 0.11579316535002467, "grad_norm": 10.374068260192871, "learning_rate": 2.315730657663227e-06, "loss": 0.7773, "step": 19480 }, { "epoch": 0.11585260742669305, "grad_norm": 9.16313362121582, "learning_rate": 2.316919492129916e-06, "loss": 0.7633, "step": 19490 }, { "epoch": 0.11591204950336145, "grad_norm": 9.829988479614258, "learning_rate": 2.318108326596605e-06, "loss": 0.7257, "step": 19500 }, { "epoch": 0.11597149158002984, "grad_norm": 10.683561325073242, "learning_rate": 2.3192971610632934e-06, "loss": 0.7581, "step": 19510 }, { "epoch": 0.11603093365669823, "grad_norm": 10.809450149536133, "learning_rate": 2.3204859955299828e-06, "loss": 0.7025, "step": 19520 }, { "epoch": 0.11609037573336663, "grad_norm": 10.457356452941895, "learning_rate": 2.3216748299966717e-06, "loss": 0.7754, "step": 19530 }, { "epoch": 0.11614981781003501, "grad_norm": 6.61993408203125, "learning_rate": 2.32286366446336e-06, "loss": 0.7809, "step": 19540 }, { "epoch": 0.1162092598867034, "grad_norm": 13.675915718078613, "learning_rate": 2.324052498930049e-06, "loss": 0.8013, "step": 19550 }, { "epoch": 0.11626870196337179, "grad_norm": 9.318984031677246, "learning_rate": 2.325241333396738e-06, "loss": 0.7435, "step": 19560 }, { "epoch": 0.11632814404004019, "grad_norm": 11.087221145629883, "learning_rate": 2.326430167863427e-06, "loss": 0.793, "step": 19570 }, { "epoch": 0.11638758611670857, "grad_norm": 10.822392463684082, "learning_rate": 2.3276190023301155e-06, "loss": 0.714, "step": 19580 }, { "epoch": 0.11644702819337696, "grad_norm": 8.720022201538086, "learning_rate": 2.3288078367968044e-06, "loss": 0.7091, "step": 19590 }, { "epoch": 0.11650647027004535, "grad_norm": 11.397394180297852, "learning_rate": 2.3299966712634933e-06, "loss": 0.7523, "step": 19600 }, { "epoch": 0.11656591234671375, "grad_norm": 10.804701805114746, "learning_rate": 2.3311855057301823e-06, "loss": 0.7944, "step": 19610 }, { "epoch": 0.11662535442338214, "grad_norm": 9.524548530578613, "learning_rate": 2.332374340196871e-06, "loss": 0.7204, "step": 19620 }, { "epoch": 0.11668479650005052, "grad_norm": 9.551750183105469, "learning_rate": 2.33356317466356e-06, "loss": 0.7572, "step": 19630 }, { "epoch": 0.11674423857671892, "grad_norm": 7.777661323547363, "learning_rate": 2.334752009130249e-06, "loss": 0.7452, "step": 19640 }, { "epoch": 0.11680368065338731, "grad_norm": 15.99449348449707, "learning_rate": 2.3359408435969376e-06, "loss": 0.7003, "step": 19650 }, { "epoch": 0.1168631227300557, "grad_norm": 12.77258014678955, "learning_rate": 2.3371296780636265e-06, "loss": 0.7509, "step": 19660 }, { "epoch": 0.11692256480672408, "grad_norm": 9.250615119934082, "learning_rate": 2.3383185125303154e-06, "loss": 0.6829, "step": 19670 }, { "epoch": 0.11698200688339248, "grad_norm": 10.205180168151855, "learning_rate": 2.3395073469970043e-06, "loss": 0.7325, "step": 19680 }, { "epoch": 0.11704144896006087, "grad_norm": 12.316105842590332, "learning_rate": 2.3406961814636933e-06, "loss": 0.7276, "step": 19690 }, { "epoch": 0.11710089103672926, "grad_norm": 13.919585227966309, "learning_rate": 2.341885015930382e-06, "loss": 0.7924, "step": 19700 }, { "epoch": 0.11716033311339764, "grad_norm": 9.233663558959961, "learning_rate": 2.343073850397071e-06, "loss": 0.693, "step": 19710 }, { "epoch": 0.11721977519006604, "grad_norm": 11.10633659362793, "learning_rate": 2.3442626848637596e-06, "loss": 0.7848, "step": 19720 }, { "epoch": 0.11727921726673443, "grad_norm": 11.526371002197266, "learning_rate": 2.3454515193304485e-06, "loss": 0.7525, "step": 19730 }, { "epoch": 0.11733865934340282, "grad_norm": 10.679190635681152, "learning_rate": 2.3466403537971375e-06, "loss": 0.7061, "step": 19740 }, { "epoch": 0.1173981014200712, "grad_norm": 9.362171173095703, "learning_rate": 2.3478291882638264e-06, "loss": 0.7452, "step": 19750 }, { "epoch": 0.1174575434967396, "grad_norm": 10.503307342529297, "learning_rate": 2.349018022730515e-06, "loss": 0.6998, "step": 19760 }, { "epoch": 0.11751698557340799, "grad_norm": 11.607556343078613, "learning_rate": 2.350206857197204e-06, "loss": 0.6908, "step": 19770 }, { "epoch": 0.11757642765007638, "grad_norm": 10.932255744934082, "learning_rate": 2.351395691663893e-06, "loss": 0.806, "step": 19780 }, { "epoch": 0.11763586972674478, "grad_norm": 8.967738151550293, "learning_rate": 2.3525845261305817e-06, "loss": 0.7335, "step": 19790 }, { "epoch": 0.11769531180341317, "grad_norm": 9.640236854553223, "learning_rate": 2.3537733605972706e-06, "loss": 0.7323, "step": 19800 }, { "epoch": 0.11775475388008155, "grad_norm": 10.009994506835938, "learning_rate": 2.3549621950639595e-06, "loss": 0.6833, "step": 19810 }, { "epoch": 0.11781419595674994, "grad_norm": 8.509797096252441, "learning_rate": 2.3561510295306485e-06, "loss": 0.7136, "step": 19820 }, { "epoch": 0.11787363803341834, "grad_norm": 9.861165046691895, "learning_rate": 2.357339863997337e-06, "loss": 0.7816, "step": 19830 }, { "epoch": 0.11793308011008673, "grad_norm": 9.53489875793457, "learning_rate": 2.358528698464026e-06, "loss": 0.7498, "step": 19840 }, { "epoch": 0.11799252218675511, "grad_norm": 11.170737266540527, "learning_rate": 2.359717532930715e-06, "loss": 0.7285, "step": 19850 }, { "epoch": 0.1180519642634235, "grad_norm": 11.449254989624023, "learning_rate": 2.3609063673974038e-06, "loss": 0.7206, "step": 19860 }, { "epoch": 0.1181114063400919, "grad_norm": 11.218877792358398, "learning_rate": 2.3620952018640927e-06, "loss": 0.7376, "step": 19870 }, { "epoch": 0.11817084841676029, "grad_norm": 9.767921447753906, "learning_rate": 2.3632840363307816e-06, "loss": 0.7517, "step": 19880 }, { "epoch": 0.11823029049342867, "grad_norm": 8.034088134765625, "learning_rate": 2.3644728707974705e-06, "loss": 0.7428, "step": 19890 }, { "epoch": 0.11828973257009708, "grad_norm": 11.118066787719727, "learning_rate": 2.365661705264159e-06, "loss": 0.7734, "step": 19900 }, { "epoch": 0.11834917464676546, "grad_norm": 8.283231735229492, "learning_rate": 2.366850539730848e-06, "loss": 0.7112, "step": 19910 }, { "epoch": 0.11840861672343385, "grad_norm": 13.795270919799805, "learning_rate": 2.368039374197537e-06, "loss": 0.7348, "step": 19920 }, { "epoch": 0.11846805880010224, "grad_norm": 10.286552429199219, "learning_rate": 2.369228208664226e-06, "loss": 0.759, "step": 19930 }, { "epoch": 0.11852750087677064, "grad_norm": 7.799432277679443, "learning_rate": 2.3704170431309143e-06, "loss": 0.7183, "step": 19940 }, { "epoch": 0.11858694295343902, "grad_norm": 9.735130310058594, "learning_rate": 2.3716058775976037e-06, "loss": 0.7839, "step": 19950 }, { "epoch": 0.11864638503010741, "grad_norm": 8.358479499816895, "learning_rate": 2.3727947120642926e-06, "loss": 0.7756, "step": 19960 }, { "epoch": 0.1187058271067758, "grad_norm": 9.02099323272705, "learning_rate": 2.373983546530981e-06, "loss": 0.7449, "step": 19970 }, { "epoch": 0.1187652691834442, "grad_norm": 7.311549663543701, "learning_rate": 2.37517238099767e-06, "loss": 0.7489, "step": 19980 }, { "epoch": 0.11882471126011258, "grad_norm": 10.984029769897461, "learning_rate": 2.376361215464359e-06, "loss": 0.7522, "step": 19990 }, { "epoch": 0.11888415333678097, "grad_norm": 9.818493843078613, "learning_rate": 2.377550049931048e-06, "loss": 0.7214, "step": 20000 }, { "epoch": 0.11894359541344937, "grad_norm": 7.858526706695557, "learning_rate": 2.3787388843977364e-06, "loss": 0.7756, "step": 20010 }, { "epoch": 0.11900303749011776, "grad_norm": 8.794800758361816, "learning_rate": 2.3799277188644253e-06, "loss": 0.7791, "step": 20020 }, { "epoch": 0.11906247956678614, "grad_norm": 11.125844955444336, "learning_rate": 2.3811165533311143e-06, "loss": 0.7626, "step": 20030 }, { "epoch": 0.11912192164345453, "grad_norm": 9.388290405273438, "learning_rate": 2.382305387797803e-06, "loss": 0.7431, "step": 20040 }, { "epoch": 0.11918136372012293, "grad_norm": 13.408848762512207, "learning_rate": 2.383494222264492e-06, "loss": 0.7725, "step": 20050 }, { "epoch": 0.11924080579679132, "grad_norm": 9.587197303771973, "learning_rate": 2.384683056731181e-06, "loss": 0.7158, "step": 20060 }, { "epoch": 0.1193002478734597, "grad_norm": 9.78915786743164, "learning_rate": 2.38587189119787e-06, "loss": 0.7411, "step": 20070 }, { "epoch": 0.11935968995012809, "grad_norm": 10.297094345092773, "learning_rate": 2.3870607256645585e-06, "loss": 0.6933, "step": 20080 }, { "epoch": 0.11941913202679649, "grad_norm": 9.604270935058594, "learning_rate": 2.3882495601312474e-06, "loss": 0.7471, "step": 20090 }, { "epoch": 0.11947857410346488, "grad_norm": 13.669504165649414, "learning_rate": 2.3894383945979363e-06, "loss": 0.7612, "step": 20100 }, { "epoch": 0.11953801618013327, "grad_norm": 10.518573760986328, "learning_rate": 2.3906272290646252e-06, "loss": 0.6563, "step": 20110 }, { "epoch": 0.11959745825680165, "grad_norm": 11.14846420288086, "learning_rate": 2.3918160635313137e-06, "loss": 0.7808, "step": 20120 }, { "epoch": 0.11965690033347005, "grad_norm": 8.813318252563477, "learning_rate": 2.393004897998003e-06, "loss": 0.7981, "step": 20130 }, { "epoch": 0.11971634241013844, "grad_norm": 9.554290771484375, "learning_rate": 2.394193732464692e-06, "loss": 0.7733, "step": 20140 }, { "epoch": 0.11977578448680683, "grad_norm": 10.580777168273926, "learning_rate": 2.3953825669313805e-06, "loss": 0.6779, "step": 20150 }, { "epoch": 0.11983522656347523, "grad_norm": 9.67061710357666, "learning_rate": 2.3965714013980695e-06, "loss": 0.6463, "step": 20160 }, { "epoch": 0.11989466864014361, "grad_norm": 10.738544464111328, "learning_rate": 2.3977602358647584e-06, "loss": 0.7051, "step": 20170 }, { "epoch": 0.119954110716812, "grad_norm": 9.70752239227295, "learning_rate": 2.3989490703314473e-06, "loss": 0.7529, "step": 20180 }, { "epoch": 0.12001355279348039, "grad_norm": 14.198569297790527, "learning_rate": 2.400137904798136e-06, "loss": 0.7555, "step": 20190 }, { "epoch": 0.12007299487014879, "grad_norm": 14.306402206420898, "learning_rate": 2.4013267392648247e-06, "loss": 0.643, "step": 20200 }, { "epoch": 0.12013243694681718, "grad_norm": 8.286920547485352, "learning_rate": 2.402515573731514e-06, "loss": 0.7146, "step": 20210 }, { "epoch": 0.12019187902348556, "grad_norm": 10.08791446685791, "learning_rate": 2.4037044081982026e-06, "loss": 0.6924, "step": 20220 }, { "epoch": 0.12025132110015395, "grad_norm": 10.265974044799805, "learning_rate": 2.4048932426648915e-06, "loss": 0.751, "step": 20230 }, { "epoch": 0.12031076317682235, "grad_norm": 11.260598182678223, "learning_rate": 2.4060820771315805e-06, "loss": 0.7045, "step": 20240 }, { "epoch": 0.12037020525349074, "grad_norm": 11.616212844848633, "learning_rate": 2.4072709115982694e-06, "loss": 0.7638, "step": 20250 }, { "epoch": 0.12042964733015912, "grad_norm": 10.826952934265137, "learning_rate": 2.408459746064958e-06, "loss": 0.7163, "step": 20260 }, { "epoch": 0.12048908940682752, "grad_norm": 10.249253273010254, "learning_rate": 2.409648580531647e-06, "loss": 0.7501, "step": 20270 }, { "epoch": 0.12054853148349591, "grad_norm": 9.34146785736084, "learning_rate": 2.4108374149983357e-06, "loss": 0.7549, "step": 20280 }, { "epoch": 0.1206079735601643, "grad_norm": 12.560925483703613, "learning_rate": 2.4120262494650247e-06, "loss": 0.7506, "step": 20290 }, { "epoch": 0.12066741563683268, "grad_norm": 11.179549217224121, "learning_rate": 2.4132150839317136e-06, "loss": 0.7611, "step": 20300 }, { "epoch": 0.12072685771350108, "grad_norm": 12.500338554382324, "learning_rate": 2.4144039183984025e-06, "loss": 0.8215, "step": 20310 }, { "epoch": 0.12078629979016947, "grad_norm": 11.613183975219727, "learning_rate": 2.4155927528650914e-06, "loss": 0.8086, "step": 20320 }, { "epoch": 0.12084574186683786, "grad_norm": 11.862555503845215, "learning_rate": 2.41678158733178e-06, "loss": 0.7386, "step": 20330 }, { "epoch": 0.12090518394350624, "grad_norm": 8.238309860229492, "learning_rate": 2.417970421798469e-06, "loss": 0.7422, "step": 20340 }, { "epoch": 0.12096462602017465, "grad_norm": 9.615273475646973, "learning_rate": 2.419159256265158e-06, "loss": 0.7963, "step": 20350 }, { "epoch": 0.12102406809684303, "grad_norm": 12.85990047454834, "learning_rate": 2.4203480907318467e-06, "loss": 0.7278, "step": 20360 }, { "epoch": 0.12108351017351142, "grad_norm": 8.915894508361816, "learning_rate": 2.4215369251985352e-06, "loss": 0.7611, "step": 20370 }, { "epoch": 0.1211429522501798, "grad_norm": 11.8903169631958, "learning_rate": 2.422725759665224e-06, "loss": 0.7275, "step": 20380 }, { "epoch": 0.1212023943268482, "grad_norm": 10.56702709197998, "learning_rate": 2.4239145941319135e-06, "loss": 0.6817, "step": 20390 }, { "epoch": 0.12126183640351659, "grad_norm": 10.078579902648926, "learning_rate": 2.425103428598602e-06, "loss": 0.6696, "step": 20400 }, { "epoch": 0.12132127848018498, "grad_norm": 11.536145210266113, "learning_rate": 2.426292263065291e-06, "loss": 0.7512, "step": 20410 }, { "epoch": 0.12138072055685338, "grad_norm": 9.602632522583008, "learning_rate": 2.42748109753198e-06, "loss": 0.6731, "step": 20420 }, { "epoch": 0.12144016263352177, "grad_norm": 9.482731819152832, "learning_rate": 2.428669931998669e-06, "loss": 0.7532, "step": 20430 }, { "epoch": 0.12149960471019015, "grad_norm": 9.693387031555176, "learning_rate": 2.4298587664653573e-06, "loss": 0.7365, "step": 20440 }, { "epoch": 0.12155904678685854, "grad_norm": 13.009820938110352, "learning_rate": 2.4310476009320462e-06, "loss": 0.7129, "step": 20450 }, { "epoch": 0.12161848886352694, "grad_norm": 10.463454246520996, "learning_rate": 2.432236435398735e-06, "loss": 0.7119, "step": 20460 }, { "epoch": 0.12167793094019533, "grad_norm": 9.227978706359863, "learning_rate": 2.433425269865424e-06, "loss": 0.7385, "step": 20470 }, { "epoch": 0.12173737301686371, "grad_norm": 12.18502140045166, "learning_rate": 2.434614104332113e-06, "loss": 0.6766, "step": 20480 }, { "epoch": 0.1217968150935321, "grad_norm": 10.414739608764648, "learning_rate": 2.435802938798802e-06, "loss": 0.784, "step": 20490 }, { "epoch": 0.1218562571702005, "grad_norm": 10.758281707763672, "learning_rate": 2.436991773265491e-06, "loss": 0.7566, "step": 20500 }, { "epoch": 0.12191569924686889, "grad_norm": 12.866153717041016, "learning_rate": 2.4381806077321794e-06, "loss": 0.671, "step": 20510 }, { "epoch": 0.12197514132353728, "grad_norm": 10.34404468536377, "learning_rate": 2.4393694421988683e-06, "loss": 0.6952, "step": 20520 }, { "epoch": 0.12203458340020568, "grad_norm": 10.661930084228516, "learning_rate": 2.4405582766655572e-06, "loss": 0.7551, "step": 20530 }, { "epoch": 0.12209402547687406, "grad_norm": 11.326569557189941, "learning_rate": 2.441747111132246e-06, "loss": 0.7486, "step": 20540 }, { "epoch": 0.12215346755354245, "grad_norm": 11.30756664276123, "learning_rate": 2.442935945598935e-06, "loss": 0.7256, "step": 20550 }, { "epoch": 0.12221290963021084, "grad_norm": 7.389161109924316, "learning_rate": 2.444124780065624e-06, "loss": 0.7234, "step": 20560 }, { "epoch": 0.12227235170687924, "grad_norm": 9.227178573608398, "learning_rate": 2.445313614532313e-06, "loss": 0.781, "step": 20570 }, { "epoch": 0.12233179378354762, "grad_norm": 9.833588600158691, "learning_rate": 2.4465024489990014e-06, "loss": 0.6979, "step": 20580 }, { "epoch": 0.12239123586021601, "grad_norm": 12.10598373413086, "learning_rate": 2.4476912834656904e-06, "loss": 0.7125, "step": 20590 }, { "epoch": 0.1224506779368844, "grad_norm": 11.39078426361084, "learning_rate": 2.4488801179323793e-06, "loss": 0.794, "step": 20600 }, { "epoch": 0.1225101200135528, "grad_norm": 10.85903263092041, "learning_rate": 2.4500689523990682e-06, "loss": 0.7203, "step": 20610 }, { "epoch": 0.12256956209022118, "grad_norm": 11.312616348266602, "learning_rate": 2.451257786865757e-06, "loss": 0.8119, "step": 20620 }, { "epoch": 0.12262900416688957, "grad_norm": 9.336411476135254, "learning_rate": 2.4524466213324457e-06, "loss": 0.786, "step": 20630 }, { "epoch": 0.12268844624355796, "grad_norm": 9.93996810913086, "learning_rate": 2.4536354557991346e-06, "loss": 0.7809, "step": 20640 }, { "epoch": 0.12274788832022636, "grad_norm": 13.934783935546875, "learning_rate": 2.4548242902658235e-06, "loss": 0.7336, "step": 20650 }, { "epoch": 0.12280733039689475, "grad_norm": 12.301294326782227, "learning_rate": 2.4560131247325124e-06, "loss": 0.737, "step": 20660 }, { "epoch": 0.12286677247356313, "grad_norm": 12.738704681396484, "learning_rate": 2.4572019591992014e-06, "loss": 0.7225, "step": 20670 }, { "epoch": 0.12292621455023153, "grad_norm": 11.830351829528809, "learning_rate": 2.4583907936658903e-06, "loss": 0.7703, "step": 20680 }, { "epoch": 0.12298565662689992, "grad_norm": 13.922600746154785, "learning_rate": 2.459579628132579e-06, "loss": 0.7889, "step": 20690 }, { "epoch": 0.1230450987035683, "grad_norm": 12.31393051147461, "learning_rate": 2.4607684625992677e-06, "loss": 0.7808, "step": 20700 }, { "epoch": 0.1231045407802367, "grad_norm": 11.482257843017578, "learning_rate": 2.4619572970659566e-06, "loss": 0.7338, "step": 20710 }, { "epoch": 0.1231639828569051, "grad_norm": 10.943024635314941, "learning_rate": 2.4631461315326456e-06, "loss": 0.72, "step": 20720 }, { "epoch": 0.12322342493357348, "grad_norm": 11.334720611572266, "learning_rate": 2.4643349659993345e-06, "loss": 0.8024, "step": 20730 }, { "epoch": 0.12328286701024187, "grad_norm": 10.643075942993164, "learning_rate": 2.4655238004660234e-06, "loss": 0.6896, "step": 20740 }, { "epoch": 0.12334230908691025, "grad_norm": 11.755781173706055, "learning_rate": 2.4667126349327124e-06, "loss": 0.752, "step": 20750 }, { "epoch": 0.12340175116357865, "grad_norm": 8.471485137939453, "learning_rate": 2.467901469399401e-06, "loss": 0.6932, "step": 20760 }, { "epoch": 0.12346119324024704, "grad_norm": 10.668071746826172, "learning_rate": 2.46909030386609e-06, "loss": 0.6776, "step": 20770 }, { "epoch": 0.12352063531691543, "grad_norm": 10.055404663085938, "learning_rate": 2.4702791383327787e-06, "loss": 0.7338, "step": 20780 }, { "epoch": 0.12358007739358383, "grad_norm": 9.268574714660645, "learning_rate": 2.4714679727994676e-06, "loss": 0.7374, "step": 20790 }, { "epoch": 0.12363951947025222, "grad_norm": 12.212139129638672, "learning_rate": 2.4726568072661566e-06, "loss": 0.7342, "step": 20800 }, { "epoch": 0.1236989615469206, "grad_norm": 11.669689178466797, "learning_rate": 2.473845641732845e-06, "loss": 0.7753, "step": 20810 }, { "epoch": 0.12375840362358899, "grad_norm": 12.452719688415527, "learning_rate": 2.4750344761995344e-06, "loss": 0.7302, "step": 20820 }, { "epoch": 0.12381784570025739, "grad_norm": 9.510246276855469, "learning_rate": 2.476223310666223e-06, "loss": 0.7437, "step": 20830 }, { "epoch": 0.12387728777692578, "grad_norm": 9.687705993652344, "learning_rate": 2.477412145132912e-06, "loss": 0.7568, "step": 20840 }, { "epoch": 0.12393672985359416, "grad_norm": 9.687287330627441, "learning_rate": 2.4786009795996008e-06, "loss": 0.749, "step": 20850 }, { "epoch": 0.12399617193026255, "grad_norm": 8.770587921142578, "learning_rate": 2.4797898140662897e-06, "loss": 0.7315, "step": 20860 }, { "epoch": 0.12405561400693095, "grad_norm": 12.141663551330566, "learning_rate": 2.4809786485329786e-06, "loss": 0.7504, "step": 20870 }, { "epoch": 0.12411505608359934, "grad_norm": 11.554132461547852, "learning_rate": 2.482167482999667e-06, "loss": 0.6781, "step": 20880 }, { "epoch": 0.12417449816026772, "grad_norm": 8.545482635498047, "learning_rate": 2.483356317466356e-06, "loss": 0.7723, "step": 20890 }, { "epoch": 0.12423394023693612, "grad_norm": 9.389005661010742, "learning_rate": 2.484545151933045e-06, "loss": 0.7198, "step": 20900 }, { "epoch": 0.12429338231360451, "grad_norm": 12.690482139587402, "learning_rate": 2.485733986399734e-06, "loss": 0.6694, "step": 20910 }, { "epoch": 0.1243528243902729, "grad_norm": 9.046944618225098, "learning_rate": 2.486922820866423e-06, "loss": 0.7318, "step": 20920 }, { "epoch": 0.12441226646694128, "grad_norm": 10.442582130432129, "learning_rate": 2.4881116553331118e-06, "loss": 0.758, "step": 20930 }, { "epoch": 0.12447170854360969, "grad_norm": 8.792548179626465, "learning_rate": 2.4893004897998003e-06, "loss": 0.7236, "step": 20940 }, { "epoch": 0.12453115062027807, "grad_norm": 11.63840103149414, "learning_rate": 2.490489324266489e-06, "loss": 0.7481, "step": 20950 }, { "epoch": 0.12459059269694646, "grad_norm": 9.247041702270508, "learning_rate": 2.491678158733178e-06, "loss": 0.7775, "step": 20960 }, { "epoch": 0.12465003477361485, "grad_norm": 8.741565704345703, "learning_rate": 2.492866993199867e-06, "loss": 0.714, "step": 20970 }, { "epoch": 0.12470947685028325, "grad_norm": 11.290343284606934, "learning_rate": 2.494055827666556e-06, "loss": 0.7522, "step": 20980 }, { "epoch": 0.12476891892695163, "grad_norm": 10.390877723693848, "learning_rate": 2.495244662133245e-06, "loss": 0.7279, "step": 20990 }, { "epoch": 0.12482836100362002, "grad_norm": 10.524524688720703, "learning_rate": 2.496433496599934e-06, "loss": 0.7249, "step": 21000 }, { "epoch": 0.1248878030802884, "grad_norm": 10.097789764404297, "learning_rate": 2.4976223310666223e-06, "loss": 0.761, "step": 21010 }, { "epoch": 0.12494724515695681, "grad_norm": 10.08879566192627, "learning_rate": 2.4988111655333113e-06, "loss": 0.7522, "step": 21020 }, { "epoch": 0.1250066872336252, "grad_norm": 11.317011833190918, "learning_rate": 2.5e-06, "loss": 0.6606, "step": 21030 }, { "epoch": 0.1250661293102936, "grad_norm": 10.59632682800293, "learning_rate": 2.501188834466689e-06, "loss": 0.7325, "step": 21040 }, { "epoch": 0.12512557138696198, "grad_norm": 12.805241584777832, "learning_rate": 2.502377668933378e-06, "loss": 0.7042, "step": 21050 }, { "epoch": 0.12518501346363037, "grad_norm": 10.075139999389648, "learning_rate": 2.5035665034000666e-06, "loss": 0.6961, "step": 21060 }, { "epoch": 0.12524445554029875, "grad_norm": 12.291831970214844, "learning_rate": 2.5047553378667555e-06, "loss": 0.7248, "step": 21070 }, { "epoch": 0.12530389761696714, "grad_norm": 10.558645248413086, "learning_rate": 2.5059441723334444e-06, "loss": 0.7412, "step": 21080 }, { "epoch": 0.12536333969363553, "grad_norm": 9.622072219848633, "learning_rate": 2.5071330068001333e-06, "loss": 0.7303, "step": 21090 }, { "epoch": 0.12542278177030391, "grad_norm": 7.981234550476074, "learning_rate": 2.508321841266822e-06, "loss": 0.6872, "step": 21100 }, { "epoch": 0.12548222384697233, "grad_norm": 10.887287139892578, "learning_rate": 2.5095106757335108e-06, "loss": 0.7179, "step": 21110 }, { "epoch": 0.12554166592364072, "grad_norm": 12.033441543579102, "learning_rate": 2.5106995102002e-06, "loss": 0.7306, "step": 21120 }, { "epoch": 0.1256011080003091, "grad_norm": 11.638303756713867, "learning_rate": 2.511888344666889e-06, "loss": 0.7583, "step": 21130 }, { "epoch": 0.1256605500769775, "grad_norm": 9.81080150604248, "learning_rate": 2.513077179133578e-06, "loss": 0.7905, "step": 21140 }, { "epoch": 0.12571999215364588, "grad_norm": 9.922258377075195, "learning_rate": 2.5142660136002665e-06, "loss": 0.7391, "step": 21150 }, { "epoch": 0.12577943423031426, "grad_norm": 11.684652328491211, "learning_rate": 2.5154548480669554e-06, "loss": 0.7214, "step": 21160 }, { "epoch": 0.12583887630698265, "grad_norm": 11.158116340637207, "learning_rate": 2.5166436825336443e-06, "loss": 0.7497, "step": 21170 }, { "epoch": 0.12589831838365106, "grad_norm": 10.148369789123535, "learning_rate": 2.5178325170003333e-06, "loss": 0.693, "step": 21180 }, { "epoch": 0.12595776046031945, "grad_norm": 11.656291961669922, "learning_rate": 2.5190213514670218e-06, "loss": 0.7479, "step": 21190 }, { "epoch": 0.12601720253698784, "grad_norm": 9.007685661315918, "learning_rate": 2.5202101859337107e-06, "loss": 0.7641, "step": 21200 }, { "epoch": 0.12607664461365622, "grad_norm": 8.511935234069824, "learning_rate": 2.5213990204003996e-06, "loss": 0.7163, "step": 21210 }, { "epoch": 0.1261360866903246, "grad_norm": 11.02657413482666, "learning_rate": 2.5225878548670886e-06, "loss": 0.7394, "step": 21220 }, { "epoch": 0.126195528766993, "grad_norm": 11.851387023925781, "learning_rate": 2.5237766893337775e-06, "loss": 0.6798, "step": 21230 }, { "epoch": 0.12625497084366138, "grad_norm": 10.256532669067383, "learning_rate": 2.524965523800466e-06, "loss": 0.7789, "step": 21240 }, { "epoch": 0.12631441292032977, "grad_norm": 8.283706665039062, "learning_rate": 2.526154358267155e-06, "loss": 0.7032, "step": 21250 }, { "epoch": 0.1263738549969982, "grad_norm": 10.482571601867676, "learning_rate": 2.527343192733844e-06, "loss": 0.7299, "step": 21260 }, { "epoch": 0.12643329707366657, "grad_norm": 10.72247314453125, "learning_rate": 2.5285320272005328e-06, "loss": 0.7431, "step": 21270 }, { "epoch": 0.12649273915033496, "grad_norm": 11.033040046691895, "learning_rate": 2.5297208616672213e-06, "loss": 0.7435, "step": 21280 }, { "epoch": 0.12655218122700335, "grad_norm": 14.12530517578125, "learning_rate": 2.5309096961339106e-06, "loss": 0.7331, "step": 21290 }, { "epoch": 0.12661162330367173, "grad_norm": 12.293597221374512, "learning_rate": 2.5320985306005995e-06, "loss": 0.6941, "step": 21300 }, { "epoch": 0.12667106538034012, "grad_norm": 10.625541687011719, "learning_rate": 2.5332873650672885e-06, "loss": 0.7712, "step": 21310 }, { "epoch": 0.1267305074570085, "grad_norm": 11.645513534545898, "learning_rate": 2.5344761995339774e-06, "loss": 0.7179, "step": 21320 }, { "epoch": 0.12678994953367692, "grad_norm": 12.379578590393066, "learning_rate": 2.535665034000666e-06, "loss": 0.7033, "step": 21330 }, { "epoch": 0.1268493916103453, "grad_norm": 10.908802032470703, "learning_rate": 2.536853868467355e-06, "loss": 0.7726, "step": 21340 }, { "epoch": 0.1269088336870137, "grad_norm": 12.340346336364746, "learning_rate": 2.5380427029340438e-06, "loss": 0.776, "step": 21350 }, { "epoch": 0.12696827576368208, "grad_norm": 12.90170669555664, "learning_rate": 2.5392315374007327e-06, "loss": 0.7398, "step": 21360 }, { "epoch": 0.12702771784035047, "grad_norm": 11.56119441986084, "learning_rate": 2.5404203718674216e-06, "loss": 0.7452, "step": 21370 }, { "epoch": 0.12708715991701885, "grad_norm": 9.732586860656738, "learning_rate": 2.54160920633411e-06, "loss": 0.7263, "step": 21380 }, { "epoch": 0.12714660199368724, "grad_norm": 8.757609367370605, "learning_rate": 2.542798040800799e-06, "loss": 0.7372, "step": 21390 }, { "epoch": 0.12720604407035563, "grad_norm": 8.66322135925293, "learning_rate": 2.543986875267488e-06, "loss": 0.6974, "step": 21400 }, { "epoch": 0.12726548614702404, "grad_norm": 8.783111572265625, "learning_rate": 2.545175709734177e-06, "loss": 0.6438, "step": 21410 }, { "epoch": 0.12732492822369243, "grad_norm": 10.868886947631836, "learning_rate": 2.5463645442008654e-06, "loss": 0.7585, "step": 21420 }, { "epoch": 0.12738437030036082, "grad_norm": 8.861645698547363, "learning_rate": 2.5475533786675543e-06, "loss": 0.7051, "step": 21430 }, { "epoch": 0.1274438123770292, "grad_norm": 8.76865005493164, "learning_rate": 2.5487422131342433e-06, "loss": 0.7407, "step": 21440 }, { "epoch": 0.1275032544536976, "grad_norm": 10.477947235107422, "learning_rate": 2.549931047600932e-06, "loss": 0.773, "step": 21450 }, { "epoch": 0.12756269653036598, "grad_norm": 10.214149475097656, "learning_rate": 2.5511198820676207e-06, "loss": 0.7298, "step": 21460 }, { "epoch": 0.12762213860703436, "grad_norm": 9.650146484375, "learning_rate": 2.55230871653431e-06, "loss": 0.7451, "step": 21470 }, { "epoch": 0.12768158068370278, "grad_norm": 9.584380149841309, "learning_rate": 2.553497551000999e-06, "loss": 0.7396, "step": 21480 }, { "epoch": 0.12774102276037116, "grad_norm": 10.517803192138672, "learning_rate": 2.554686385467688e-06, "loss": 0.7347, "step": 21490 }, { "epoch": 0.12780046483703955, "grad_norm": 10.392784118652344, "learning_rate": 2.555875219934377e-06, "loss": 0.7629, "step": 21500 }, { "epoch": 0.12785990691370794, "grad_norm": 10.643362998962402, "learning_rate": 2.5570640544010653e-06, "loss": 0.7392, "step": 21510 }, { "epoch": 0.12791934899037632, "grad_norm": 13.144207000732422, "learning_rate": 2.5582528888677543e-06, "loss": 0.777, "step": 21520 }, { "epoch": 0.1279787910670447, "grad_norm": 11.016124725341797, "learning_rate": 2.559441723334443e-06, "loss": 0.6901, "step": 21530 }, { "epoch": 0.1280382331437131, "grad_norm": 9.189079284667969, "learning_rate": 2.560630557801132e-06, "loss": 0.6725, "step": 21540 }, { "epoch": 0.1280976752203815, "grad_norm": 12.46255111694336, "learning_rate": 2.561819392267821e-06, "loss": 0.7189, "step": 21550 }, { "epoch": 0.1281571172970499, "grad_norm": 9.229670524597168, "learning_rate": 2.5630082267345095e-06, "loss": 0.7395, "step": 21560 }, { "epoch": 0.1282165593737183, "grad_norm": 8.644103050231934, "learning_rate": 2.5641970612011985e-06, "loss": 0.7841, "step": 21570 }, { "epoch": 0.12827600145038667, "grad_norm": 10.418627738952637, "learning_rate": 2.5653858956678874e-06, "loss": 0.7002, "step": 21580 }, { "epoch": 0.12833544352705506, "grad_norm": 9.882868766784668, "learning_rate": 2.5665747301345763e-06, "loss": 0.7209, "step": 21590 }, { "epoch": 0.12839488560372345, "grad_norm": 10.029553413391113, "learning_rate": 2.567763564601265e-06, "loss": 0.7278, "step": 21600 }, { "epoch": 0.12845432768039183, "grad_norm": 11.449419021606445, "learning_rate": 2.5689523990679538e-06, "loss": 0.7344, "step": 21610 }, { "epoch": 0.12851376975706022, "grad_norm": 10.042455673217773, "learning_rate": 2.5701412335346427e-06, "loss": 0.7855, "step": 21620 }, { "epoch": 0.12857321183372863, "grad_norm": 9.148645401000977, "learning_rate": 2.5713300680013316e-06, "loss": 0.7648, "step": 21630 }, { "epoch": 0.12863265391039702, "grad_norm": 12.322070121765137, "learning_rate": 2.572518902468021e-06, "loss": 0.6876, "step": 21640 }, { "epoch": 0.1286920959870654, "grad_norm": 8.481167793273926, "learning_rate": 2.5737077369347095e-06, "loss": 0.6787, "step": 21650 }, { "epoch": 0.1287515380637338, "grad_norm": 8.889750480651855, "learning_rate": 2.5748965714013984e-06, "loss": 0.6635, "step": 21660 }, { "epoch": 0.12881098014040218, "grad_norm": 9.236285209655762, "learning_rate": 2.5760854058680873e-06, "loss": 0.7375, "step": 21670 }, { "epoch": 0.12887042221707057, "grad_norm": 11.815901756286621, "learning_rate": 2.5772742403347762e-06, "loss": 0.7022, "step": 21680 }, { "epoch": 0.12892986429373895, "grad_norm": 12.875205039978027, "learning_rate": 2.578463074801465e-06, "loss": 0.7666, "step": 21690 }, { "epoch": 0.12898930637040737, "grad_norm": 9.310833930969238, "learning_rate": 2.5796519092681537e-06, "loss": 0.6675, "step": 21700 }, { "epoch": 0.12904874844707576, "grad_norm": 10.251521110534668, "learning_rate": 2.5808407437348426e-06, "loss": 0.6951, "step": 21710 }, { "epoch": 0.12910819052374414, "grad_norm": 12.609493255615234, "learning_rate": 2.5820295782015315e-06, "loss": 0.6961, "step": 21720 }, { "epoch": 0.12916763260041253, "grad_norm": 10.859926223754883, "learning_rate": 2.5832184126682205e-06, "loss": 0.6888, "step": 21730 }, { "epoch": 0.12922707467708092, "grad_norm": 8.940655708312988, "learning_rate": 2.584407247134909e-06, "loss": 0.7063, "step": 21740 }, { "epoch": 0.1292865167537493, "grad_norm": 10.974164009094238, "learning_rate": 2.585596081601598e-06, "loss": 0.7948, "step": 21750 }, { "epoch": 0.1293459588304177, "grad_norm": 10.382270812988281, "learning_rate": 2.586784916068287e-06, "loss": 0.745, "step": 21760 }, { "epoch": 0.12940540090708608, "grad_norm": 7.943630695343018, "learning_rate": 2.5879737505349757e-06, "loss": 0.7665, "step": 21770 }, { "epoch": 0.1294648429837545, "grad_norm": 10.858562469482422, "learning_rate": 2.5891625850016642e-06, "loss": 0.7717, "step": 21780 }, { "epoch": 0.12952428506042288, "grad_norm": 9.6693696975708, "learning_rate": 2.590351419468353e-06, "loss": 0.7214, "step": 21790 }, { "epoch": 0.12958372713709126, "grad_norm": 10.556602478027344, "learning_rate": 2.591540253935042e-06, "loss": 0.7246, "step": 21800 }, { "epoch": 0.12964316921375965, "grad_norm": 9.035948753356934, "learning_rate": 2.5927290884017315e-06, "loss": 0.6874, "step": 21810 }, { "epoch": 0.12970261129042804, "grad_norm": 12.579333305358887, "learning_rate": 2.5939179228684204e-06, "loss": 0.6697, "step": 21820 }, { "epoch": 0.12976205336709642, "grad_norm": 12.183714866638184, "learning_rate": 2.595106757335109e-06, "loss": 0.7948, "step": 21830 }, { "epoch": 0.1298214954437648, "grad_norm": 8.614063262939453, "learning_rate": 2.596295591801798e-06, "loss": 0.7081, "step": 21840 }, { "epoch": 0.12988093752043323, "grad_norm": 10.418498992919922, "learning_rate": 2.5974844262684867e-06, "loss": 0.6922, "step": 21850 }, { "epoch": 0.1299403795971016, "grad_norm": 10.020303726196289, "learning_rate": 2.5986732607351757e-06, "loss": 0.7423, "step": 21860 }, { "epoch": 0.12999982167377, "grad_norm": 11.604884147644043, "learning_rate": 2.5998620952018646e-06, "loss": 0.6967, "step": 21870 }, { "epoch": 0.1300592637504384, "grad_norm": 12.607879638671875, "learning_rate": 2.601050929668553e-06, "loss": 0.7302, "step": 21880 }, { "epoch": 0.13011870582710677, "grad_norm": 8.477518081665039, "learning_rate": 2.602239764135242e-06, "loss": 0.7447, "step": 21890 }, { "epoch": 0.13017814790377516, "grad_norm": 10.727241516113281, "learning_rate": 2.603428598601931e-06, "loss": 0.7212, "step": 21900 }, { "epoch": 0.13023758998044355, "grad_norm": 10.041041374206543, "learning_rate": 2.60461743306862e-06, "loss": 0.7345, "step": 21910 }, { "epoch": 0.13029703205711196, "grad_norm": 9.69262981414795, "learning_rate": 2.6058062675353084e-06, "loss": 0.6984, "step": 21920 }, { "epoch": 0.13035647413378035, "grad_norm": 13.588970184326172, "learning_rate": 2.6069951020019973e-06, "loss": 0.7953, "step": 21930 }, { "epoch": 0.13041591621044873, "grad_norm": 9.672794342041016, "learning_rate": 2.6081839364686862e-06, "loss": 0.7531, "step": 21940 }, { "epoch": 0.13047535828711712, "grad_norm": 8.301836013793945, "learning_rate": 2.609372770935375e-06, "loss": 0.7097, "step": 21950 }, { "epoch": 0.1305348003637855, "grad_norm": 9.66336727142334, "learning_rate": 2.6105616054020637e-06, "loss": 0.7007, "step": 21960 }, { "epoch": 0.1305942424404539, "grad_norm": 8.642422676086426, "learning_rate": 2.6117504398687526e-06, "loss": 0.6695, "step": 21970 }, { "epoch": 0.13065368451712228, "grad_norm": 11.397762298583984, "learning_rate": 2.6129392743354415e-06, "loss": 0.741, "step": 21980 }, { "epoch": 0.13071312659379067, "grad_norm": 10.94677448272705, "learning_rate": 2.614128108802131e-06, "loss": 0.7364, "step": 21990 }, { "epoch": 0.13077256867045908, "grad_norm": 12.644342422485352, "learning_rate": 2.61531694326882e-06, "loss": 0.7363, "step": 22000 }, { "epoch": 0.13083201074712747, "grad_norm": 11.386004447937012, "learning_rate": 2.6165057777355083e-06, "loss": 0.7168, "step": 22010 }, { "epoch": 0.13089145282379586, "grad_norm": 8.425468444824219, "learning_rate": 2.6176946122021972e-06, "loss": 0.7044, "step": 22020 }, { "epoch": 0.13095089490046424, "grad_norm": 11.820697784423828, "learning_rate": 2.618883446668886e-06, "loss": 0.779, "step": 22030 }, { "epoch": 0.13101033697713263, "grad_norm": 9.278613090515137, "learning_rate": 2.620072281135575e-06, "loss": 0.7091, "step": 22040 }, { "epoch": 0.13106977905380102, "grad_norm": 9.85191535949707, "learning_rate": 2.621261115602264e-06, "loss": 0.776, "step": 22050 }, { "epoch": 0.1311292211304694, "grad_norm": 11.355777740478516, "learning_rate": 2.6224499500689525e-06, "loss": 0.7265, "step": 22060 }, { "epoch": 0.13118866320713782, "grad_norm": 12.712430953979492, "learning_rate": 2.6236387845356414e-06, "loss": 0.7343, "step": 22070 }, { "epoch": 0.1312481052838062, "grad_norm": 12.359796524047852, "learning_rate": 2.6248276190023304e-06, "loss": 0.7149, "step": 22080 }, { "epoch": 0.1313075473604746, "grad_norm": 9.746122360229492, "learning_rate": 2.6260164534690193e-06, "loss": 0.7302, "step": 22090 }, { "epoch": 0.13136698943714298, "grad_norm": 8.348703384399414, "learning_rate": 2.627205287935708e-06, "loss": 0.7722, "step": 22100 }, { "epoch": 0.13142643151381136, "grad_norm": 11.815434455871582, "learning_rate": 2.6283941224023967e-06, "loss": 0.7142, "step": 22110 }, { "epoch": 0.13148587359047975, "grad_norm": 10.35992431640625, "learning_rate": 2.6295829568690857e-06, "loss": 0.7201, "step": 22120 }, { "epoch": 0.13154531566714814, "grad_norm": 10.149950981140137, "learning_rate": 2.6307717913357746e-06, "loss": 0.7611, "step": 22130 }, { "epoch": 0.13160475774381653, "grad_norm": 9.167086601257324, "learning_rate": 2.631960625802463e-06, "loss": 0.7352, "step": 22140 }, { "epoch": 0.13166419982048494, "grad_norm": 10.368938446044922, "learning_rate": 2.633149460269152e-06, "loss": 0.7205, "step": 22150 }, { "epoch": 0.13172364189715333, "grad_norm": 7.9675612449646, "learning_rate": 2.6343382947358414e-06, "loss": 0.6758, "step": 22160 }, { "epoch": 0.1317830839738217, "grad_norm": 9.835183143615723, "learning_rate": 2.6355271292025303e-06, "loss": 0.7184, "step": 22170 }, { "epoch": 0.1318425260504901, "grad_norm": 8.45716667175293, "learning_rate": 2.6367159636692192e-06, "loss": 0.6884, "step": 22180 }, { "epoch": 0.1319019681271585, "grad_norm": 9.256110191345215, "learning_rate": 2.637904798135908e-06, "loss": 0.6681, "step": 22190 }, { "epoch": 0.13196141020382687, "grad_norm": 9.883691787719727, "learning_rate": 2.6390936326025967e-06, "loss": 0.7947, "step": 22200 }, { "epoch": 0.13202085228049526, "grad_norm": 9.788277626037598, "learning_rate": 2.6402824670692856e-06, "loss": 0.6974, "step": 22210 }, { "epoch": 0.13208029435716367, "grad_norm": 12.774209976196289, "learning_rate": 2.6414713015359745e-06, "loss": 0.7559, "step": 22220 }, { "epoch": 0.13213973643383206, "grad_norm": 11.727607727050781, "learning_rate": 2.6426601360026634e-06, "loss": 0.7692, "step": 22230 }, { "epoch": 0.13219917851050045, "grad_norm": 10.438346862792969, "learning_rate": 2.643848970469352e-06, "loss": 0.7131, "step": 22240 }, { "epoch": 0.13225862058716883, "grad_norm": 8.354214668273926, "learning_rate": 2.645037804936041e-06, "loss": 0.7325, "step": 22250 }, { "epoch": 0.13231806266383722, "grad_norm": 13.356922149658203, "learning_rate": 2.64622663940273e-06, "loss": 0.674, "step": 22260 }, { "epoch": 0.1323775047405056, "grad_norm": 11.741652488708496, "learning_rate": 2.6474154738694187e-06, "loss": 0.6968, "step": 22270 }, { "epoch": 0.132436946817174, "grad_norm": 9.370675086975098, "learning_rate": 2.6486043083361072e-06, "loss": 0.7123, "step": 22280 }, { "epoch": 0.13249638889384238, "grad_norm": 7.994650363922119, "learning_rate": 2.649793142802796e-06, "loss": 0.7133, "step": 22290 }, { "epoch": 0.1325558309705108, "grad_norm": 12.302090644836426, "learning_rate": 2.650981977269485e-06, "loss": 0.6872, "step": 22300 }, { "epoch": 0.13261527304717918, "grad_norm": 11.758499145507812, "learning_rate": 2.652170811736174e-06, "loss": 0.678, "step": 22310 }, { "epoch": 0.13267471512384757, "grad_norm": 9.613338470458984, "learning_rate": 2.6533596462028625e-06, "loss": 0.6948, "step": 22320 }, { "epoch": 0.13273415720051596, "grad_norm": 10.907720565795898, "learning_rate": 2.654548480669552e-06, "loss": 0.7289, "step": 22330 }, { "epoch": 0.13279359927718434, "grad_norm": 10.859482765197754, "learning_rate": 2.6557373151362408e-06, "loss": 0.7735, "step": 22340 }, { "epoch": 0.13285304135385273, "grad_norm": 11.932056427001953, "learning_rate": 2.6569261496029297e-06, "loss": 0.6892, "step": 22350 }, { "epoch": 0.13291248343052112, "grad_norm": 11.428009986877441, "learning_rate": 2.6581149840696186e-06, "loss": 0.7044, "step": 22360 }, { "epoch": 0.13297192550718953, "grad_norm": 10.590274810791016, "learning_rate": 2.6593038185363076e-06, "loss": 0.7544, "step": 22370 }, { "epoch": 0.13303136758385792, "grad_norm": 10.27192211151123, "learning_rate": 2.660492653002996e-06, "loss": 0.6821, "step": 22380 }, { "epoch": 0.1330908096605263, "grad_norm": 8.915820121765137, "learning_rate": 2.661681487469685e-06, "loss": 0.6937, "step": 22390 }, { "epoch": 0.1331502517371947, "grad_norm": 10.904925346374512, "learning_rate": 2.662870321936374e-06, "loss": 0.7549, "step": 22400 }, { "epoch": 0.13320969381386308, "grad_norm": 9.410794258117676, "learning_rate": 2.664059156403063e-06, "loss": 0.7055, "step": 22410 }, { "epoch": 0.13326913589053146, "grad_norm": 11.169334411621094, "learning_rate": 2.6652479908697514e-06, "loss": 0.6857, "step": 22420 }, { "epoch": 0.13332857796719985, "grad_norm": 10.851774215698242, "learning_rate": 2.6664368253364403e-06, "loss": 0.6724, "step": 22430 }, { "epoch": 0.13338802004386827, "grad_norm": 10.517533302307129, "learning_rate": 2.6676256598031292e-06, "loss": 0.6485, "step": 22440 }, { "epoch": 0.13344746212053665, "grad_norm": 11.828601837158203, "learning_rate": 2.668814494269818e-06, "loss": 0.7372, "step": 22450 }, { "epoch": 0.13350690419720504, "grad_norm": 10.919651985168457, "learning_rate": 2.6700033287365066e-06, "loss": 0.7298, "step": 22460 }, { "epoch": 0.13356634627387343, "grad_norm": 12.72048568725586, "learning_rate": 2.6711921632031956e-06, "loss": 0.7313, "step": 22470 }, { "epoch": 0.1336257883505418, "grad_norm": 10.444182395935059, "learning_rate": 2.6723809976698845e-06, "loss": 0.6697, "step": 22480 }, { "epoch": 0.1336852304272102, "grad_norm": 9.03892993927002, "learning_rate": 2.6735698321365734e-06, "loss": 0.7992, "step": 22490 }, { "epoch": 0.1337446725038786, "grad_norm": 9.07435417175293, "learning_rate": 2.674758666603262e-06, "loss": 0.675, "step": 22500 }, { "epoch": 0.13380411458054697, "grad_norm": 10.00862979888916, "learning_rate": 2.6759475010699513e-06, "loss": 0.7419, "step": 22510 }, { "epoch": 0.1338635566572154, "grad_norm": 11.905974388122559, "learning_rate": 2.67713633553664e-06, "loss": 0.8155, "step": 22520 }, { "epoch": 0.13392299873388377, "grad_norm": 9.108792304992676, "learning_rate": 2.678325170003329e-06, "loss": 0.6559, "step": 22530 }, { "epoch": 0.13398244081055216, "grad_norm": 10.785346984863281, "learning_rate": 2.679514004470018e-06, "loss": 0.7457, "step": 22540 }, { "epoch": 0.13404188288722055, "grad_norm": 11.890472412109375, "learning_rate": 2.680702838936707e-06, "loss": 0.7504, "step": 22550 }, { "epoch": 0.13410132496388893, "grad_norm": 10.104270935058594, "learning_rate": 2.6818916734033955e-06, "loss": 0.6802, "step": 22560 }, { "epoch": 0.13416076704055732, "grad_norm": 6.969433784484863, "learning_rate": 2.6830805078700844e-06, "loss": 0.7105, "step": 22570 }, { "epoch": 0.1342202091172257, "grad_norm": 7.64132833480835, "learning_rate": 2.6842693423367733e-06, "loss": 0.7024, "step": 22580 }, { "epoch": 0.13427965119389412, "grad_norm": 10.515558242797852, "learning_rate": 2.6854581768034623e-06, "loss": 0.7963, "step": 22590 }, { "epoch": 0.1343390932705625, "grad_norm": 11.225653648376465, "learning_rate": 2.6866470112701508e-06, "loss": 0.717, "step": 22600 }, { "epoch": 0.1343985353472309, "grad_norm": 8.573284149169922, "learning_rate": 2.6878358457368397e-06, "loss": 0.7088, "step": 22610 }, { "epoch": 0.13445797742389928, "grad_norm": 9.368093490600586, "learning_rate": 2.6890246802035286e-06, "loss": 0.7496, "step": 22620 }, { "epoch": 0.13451741950056767, "grad_norm": 12.495983123779297, "learning_rate": 2.6902135146702176e-06, "loss": 0.674, "step": 22630 }, { "epoch": 0.13457686157723606, "grad_norm": 8.873739242553711, "learning_rate": 2.691402349136906e-06, "loss": 0.7626, "step": 22640 }, { "epoch": 0.13463630365390444, "grad_norm": 10.452044486999512, "learning_rate": 2.692591183603595e-06, "loss": 0.7503, "step": 22650 }, { "epoch": 0.13469574573057283, "grad_norm": 10.4878568649292, "learning_rate": 2.693780018070284e-06, "loss": 0.7119, "step": 22660 }, { "epoch": 0.13475518780724124, "grad_norm": 9.037376403808594, "learning_rate": 2.694968852536973e-06, "loss": 0.7621, "step": 22670 }, { "epoch": 0.13481462988390963, "grad_norm": 10.774057388305664, "learning_rate": 2.696157687003662e-06, "loss": 0.8053, "step": 22680 }, { "epoch": 0.13487407196057802, "grad_norm": 9.501493453979492, "learning_rate": 2.697346521470351e-06, "loss": 0.7075, "step": 22690 }, { "epoch": 0.1349335140372464, "grad_norm": 10.911635398864746, "learning_rate": 2.6985353559370396e-06, "loss": 0.7358, "step": 22700 }, { "epoch": 0.1349929561139148, "grad_norm": 11.23774242401123, "learning_rate": 2.6997241904037286e-06, "loss": 0.6998, "step": 22710 }, { "epoch": 0.13505239819058318, "grad_norm": 9.430583953857422, "learning_rate": 2.7009130248704175e-06, "loss": 0.7107, "step": 22720 }, { "epoch": 0.13511184026725157, "grad_norm": 10.864099502563477, "learning_rate": 2.7021018593371064e-06, "loss": 0.7559, "step": 22730 }, { "epoch": 0.13517128234391998, "grad_norm": 8.72655200958252, "learning_rate": 2.703290693803795e-06, "loss": 0.7211, "step": 22740 }, { "epoch": 0.13523072442058837, "grad_norm": 11.777486801147461, "learning_rate": 2.704479528270484e-06, "loss": 0.7082, "step": 22750 }, { "epoch": 0.13529016649725675, "grad_norm": 11.018043518066406, "learning_rate": 2.7056683627371728e-06, "loss": 0.7563, "step": 22760 }, { "epoch": 0.13534960857392514, "grad_norm": 10.182976722717285, "learning_rate": 2.7068571972038617e-06, "loss": 0.7394, "step": 22770 }, { "epoch": 0.13540905065059353, "grad_norm": 8.679746627807617, "learning_rate": 2.70804603167055e-06, "loss": 0.7131, "step": 22780 }, { "epoch": 0.1354684927272619, "grad_norm": 11.942296028137207, "learning_rate": 2.709234866137239e-06, "loss": 0.7293, "step": 22790 }, { "epoch": 0.1355279348039303, "grad_norm": 9.721792221069336, "learning_rate": 2.710423700603928e-06, "loss": 0.7924, "step": 22800 }, { "epoch": 0.1355873768805987, "grad_norm": 9.489943504333496, "learning_rate": 2.711612535070617e-06, "loss": 0.7789, "step": 22810 }, { "epoch": 0.1356468189572671, "grad_norm": 9.846735954284668, "learning_rate": 2.7128013695373055e-06, "loss": 0.6715, "step": 22820 }, { "epoch": 0.1357062610339355, "grad_norm": 10.363472938537598, "learning_rate": 2.7139902040039944e-06, "loss": 0.7948, "step": 22830 }, { "epoch": 0.13576570311060387, "grad_norm": 9.071911811828613, "learning_rate": 2.7151790384706833e-06, "loss": 0.7547, "step": 22840 }, { "epoch": 0.13582514518727226, "grad_norm": 8.1084566116333, "learning_rate": 2.7163678729373727e-06, "loss": 0.6861, "step": 22850 }, { "epoch": 0.13588458726394065, "grad_norm": 10.001389503479004, "learning_rate": 2.7175567074040616e-06, "loss": 0.7204, "step": 22860 }, { "epoch": 0.13594402934060903, "grad_norm": 10.52790641784668, "learning_rate": 2.7187455418707505e-06, "loss": 0.7332, "step": 22870 }, { "epoch": 0.13600347141727742, "grad_norm": 9.680839538574219, "learning_rate": 2.719934376337439e-06, "loss": 0.6676, "step": 22880 }, { "epoch": 0.13606291349394584, "grad_norm": 9.120079040527344, "learning_rate": 2.721123210804128e-06, "loss": 0.746, "step": 22890 }, { "epoch": 0.13612235557061422, "grad_norm": 9.502809524536133, "learning_rate": 2.722312045270817e-06, "loss": 0.7173, "step": 22900 }, { "epoch": 0.1361817976472826, "grad_norm": 10.215734481811523, "learning_rate": 2.723500879737506e-06, "loss": 0.7504, "step": 22910 }, { "epoch": 0.136241239723951, "grad_norm": 10.546247482299805, "learning_rate": 2.7246897142041943e-06, "loss": 0.7167, "step": 22920 }, { "epoch": 0.13630068180061938, "grad_norm": 11.553093910217285, "learning_rate": 2.7258785486708833e-06, "loss": 0.7783, "step": 22930 }, { "epoch": 0.13636012387728777, "grad_norm": 9.767838478088379, "learning_rate": 2.727067383137572e-06, "loss": 0.7703, "step": 22940 }, { "epoch": 0.13641956595395616, "grad_norm": 13.047707557678223, "learning_rate": 2.728256217604261e-06, "loss": 0.7699, "step": 22950 }, { "epoch": 0.13647900803062457, "grad_norm": 8.143755912780762, "learning_rate": 2.7294450520709496e-06, "loss": 0.7693, "step": 22960 }, { "epoch": 0.13653845010729296, "grad_norm": 9.899504661560059, "learning_rate": 2.7306338865376385e-06, "loss": 0.6998, "step": 22970 }, { "epoch": 0.13659789218396134, "grad_norm": 11.050220489501953, "learning_rate": 2.7318227210043275e-06, "loss": 0.8072, "step": 22980 }, { "epoch": 0.13665733426062973, "grad_norm": 12.088776588439941, "learning_rate": 2.7330115554710164e-06, "loss": 0.6653, "step": 22990 }, { "epoch": 0.13671677633729812, "grad_norm": 9.139508247375488, "learning_rate": 2.734200389937705e-06, "loss": 0.6787, "step": 23000 }, { "epoch": 0.1367762184139665, "grad_norm": 9.32172679901123, "learning_rate": 2.735389224404394e-06, "loss": 0.7144, "step": 23010 }, { "epoch": 0.1368356604906349, "grad_norm": 12.73714828491211, "learning_rate": 2.7365780588710828e-06, "loss": 0.7524, "step": 23020 }, { "epoch": 0.13689510256730328, "grad_norm": 8.740728378295898, "learning_rate": 2.737766893337772e-06, "loss": 0.6786, "step": 23030 }, { "epoch": 0.1369545446439717, "grad_norm": 9.096017837524414, "learning_rate": 2.738955727804461e-06, "loss": 0.7057, "step": 23040 }, { "epoch": 0.13701398672064008, "grad_norm": 12.052210807800293, "learning_rate": 2.74014456227115e-06, "loss": 0.693, "step": 23050 }, { "epoch": 0.13707342879730847, "grad_norm": 9.952524185180664, "learning_rate": 2.7413333967378385e-06, "loss": 0.7899, "step": 23060 }, { "epoch": 0.13713287087397685, "grad_norm": 9.486660957336426, "learning_rate": 2.7425222312045274e-06, "loss": 0.7493, "step": 23070 }, { "epoch": 0.13719231295064524, "grad_norm": 8.803938865661621, "learning_rate": 2.7437110656712163e-06, "loss": 0.6742, "step": 23080 }, { "epoch": 0.13725175502731363, "grad_norm": 8.376604080200195, "learning_rate": 2.7448999001379053e-06, "loss": 0.7268, "step": 23090 }, { "epoch": 0.137311197103982, "grad_norm": 12.105114936828613, "learning_rate": 2.7460887346045938e-06, "loss": 0.7125, "step": 23100 }, { "epoch": 0.13737063918065043, "grad_norm": 8.525659561157227, "learning_rate": 2.7472775690712827e-06, "loss": 0.7114, "step": 23110 }, { "epoch": 0.13743008125731881, "grad_norm": 10.792997360229492, "learning_rate": 2.7484664035379716e-06, "loss": 0.7722, "step": 23120 }, { "epoch": 0.1374895233339872, "grad_norm": 9.342907905578613, "learning_rate": 2.7496552380046605e-06, "loss": 0.7662, "step": 23130 }, { "epoch": 0.1375489654106556, "grad_norm": 10.191617965698242, "learning_rate": 2.750844072471349e-06, "loss": 0.742, "step": 23140 }, { "epoch": 0.13760840748732397, "grad_norm": 7.971606254577637, "learning_rate": 2.752032906938038e-06, "loss": 0.7361, "step": 23150 }, { "epoch": 0.13766784956399236, "grad_norm": 11.056041717529297, "learning_rate": 2.753221741404727e-06, "loss": 0.7447, "step": 23160 }, { "epoch": 0.13772729164066075, "grad_norm": 10.018068313598633, "learning_rate": 2.754410575871416e-06, "loss": 0.7356, "step": 23170 }, { "epoch": 0.13778673371732914, "grad_norm": 9.117827415466309, "learning_rate": 2.7555994103381043e-06, "loss": 0.6742, "step": 23180 }, { "epoch": 0.13784617579399755, "grad_norm": 10.332147598266602, "learning_rate": 2.7567882448047933e-06, "loss": 0.7425, "step": 23190 }, { "epoch": 0.13790561787066594, "grad_norm": 8.864712715148926, "learning_rate": 2.7579770792714826e-06, "loss": 0.6761, "step": 23200 }, { "epoch": 0.13796505994733432, "grad_norm": 9.513376235961914, "learning_rate": 2.7591659137381715e-06, "loss": 0.6794, "step": 23210 }, { "epoch": 0.1380245020240027, "grad_norm": 10.82409954071045, "learning_rate": 2.7603547482048605e-06, "loss": 0.7671, "step": 23220 }, { "epoch": 0.1380839441006711, "grad_norm": 12.5211181640625, "learning_rate": 2.7615435826715494e-06, "loss": 0.71, "step": 23230 }, { "epoch": 0.13814338617733948, "grad_norm": 9.810903549194336, "learning_rate": 2.762732417138238e-06, "loss": 0.6715, "step": 23240 }, { "epoch": 0.13820282825400787, "grad_norm": 10.246296882629395, "learning_rate": 2.763921251604927e-06, "loss": 0.6941, "step": 23250 }, { "epoch": 0.13826227033067628, "grad_norm": 9.618487358093262, "learning_rate": 2.7651100860716157e-06, "loss": 0.6992, "step": 23260 }, { "epoch": 0.13832171240734467, "grad_norm": 9.446678161621094, "learning_rate": 2.7662989205383047e-06, "loss": 0.7139, "step": 23270 }, { "epoch": 0.13838115448401306, "grad_norm": 11.846753120422363, "learning_rate": 2.767487755004993e-06, "loss": 0.76, "step": 23280 }, { "epoch": 0.13844059656068144, "grad_norm": 10.125497817993164, "learning_rate": 2.768676589471682e-06, "loss": 0.7745, "step": 23290 }, { "epoch": 0.13850003863734983, "grad_norm": 10.45361328125, "learning_rate": 2.769865423938371e-06, "loss": 0.7603, "step": 23300 }, { "epoch": 0.13855948071401822, "grad_norm": 13.827971458435059, "learning_rate": 2.77105425840506e-06, "loss": 0.7563, "step": 23310 }, { "epoch": 0.1386189227906866, "grad_norm": 8.980340957641602, "learning_rate": 2.7722430928717485e-06, "loss": 0.7075, "step": 23320 }, { "epoch": 0.13867836486735502, "grad_norm": 10.209285736083984, "learning_rate": 2.7734319273384374e-06, "loss": 0.7937, "step": 23330 }, { "epoch": 0.1387378069440234, "grad_norm": 8.327031135559082, "learning_rate": 2.7746207618051263e-06, "loss": 0.7522, "step": 23340 }, { "epoch": 0.1387972490206918, "grad_norm": 8.986191749572754, "learning_rate": 2.7758095962718152e-06, "loss": 0.678, "step": 23350 }, { "epoch": 0.13885669109736018, "grad_norm": 9.645258903503418, "learning_rate": 2.7769984307385037e-06, "loss": 0.6913, "step": 23360 }, { "epoch": 0.13891613317402857, "grad_norm": 11.057543754577637, "learning_rate": 2.7781872652051935e-06, "loss": 0.7191, "step": 23370 }, { "epoch": 0.13897557525069695, "grad_norm": 9.639272689819336, "learning_rate": 2.779376099671882e-06, "loss": 0.73, "step": 23380 }, { "epoch": 0.13903501732736534, "grad_norm": 12.756237983703613, "learning_rate": 2.780564934138571e-06, "loss": 0.7986, "step": 23390 }, { "epoch": 0.13909445940403373, "grad_norm": 7.652557373046875, "learning_rate": 2.78175376860526e-06, "loss": 0.7337, "step": 23400 }, { "epoch": 0.13915390148070214, "grad_norm": 8.729286193847656, "learning_rate": 2.782942603071949e-06, "loss": 0.734, "step": 23410 }, { "epoch": 0.13921334355737053, "grad_norm": 9.362884521484375, "learning_rate": 2.7841314375386373e-06, "loss": 0.7251, "step": 23420 }, { "epoch": 0.13927278563403891, "grad_norm": 11.732951164245605, "learning_rate": 2.7853202720053262e-06, "loss": 0.7295, "step": 23430 }, { "epoch": 0.1393322277107073, "grad_norm": 9.354694366455078, "learning_rate": 2.786509106472015e-06, "loss": 0.6623, "step": 23440 }, { "epoch": 0.1393916697873757, "grad_norm": 9.962743759155273, "learning_rate": 2.787697940938704e-06, "loss": 0.7634, "step": 23450 }, { "epoch": 0.13945111186404407, "grad_norm": 8.949201583862305, "learning_rate": 2.7888867754053926e-06, "loss": 0.7633, "step": 23460 }, { "epoch": 0.13951055394071246, "grad_norm": 8.399755477905273, "learning_rate": 2.7900756098720815e-06, "loss": 0.6967, "step": 23470 }, { "epoch": 0.13956999601738088, "grad_norm": 8.226006507873535, "learning_rate": 2.7912644443387705e-06, "loss": 0.7692, "step": 23480 }, { "epoch": 0.13962943809404926, "grad_norm": 11.018777847290039, "learning_rate": 2.7924532788054594e-06, "loss": 0.8049, "step": 23490 }, { "epoch": 0.13968888017071765, "grad_norm": 8.902328491210938, "learning_rate": 2.793642113272148e-06, "loss": 0.6898, "step": 23500 }, { "epoch": 0.13974832224738604, "grad_norm": 11.25449275970459, "learning_rate": 2.794830947738837e-06, "loss": 0.728, "step": 23510 }, { "epoch": 0.13980776432405442, "grad_norm": 9.582500457763672, "learning_rate": 2.7960197822055257e-06, "loss": 0.7045, "step": 23520 }, { "epoch": 0.1398672064007228, "grad_norm": 8.519488334655762, "learning_rate": 2.7972086166722147e-06, "loss": 0.7045, "step": 23530 }, { "epoch": 0.1399266484773912, "grad_norm": 9.986931800842285, "learning_rate": 2.798397451138903e-06, "loss": 0.7396, "step": 23540 }, { "epoch": 0.13998609055405958, "grad_norm": 7.845890998840332, "learning_rate": 2.799586285605593e-06, "loss": 0.719, "step": 23550 }, { "epoch": 0.140045532630728, "grad_norm": 7.7375006675720215, "learning_rate": 2.8007751200722814e-06, "loss": 0.6654, "step": 23560 }, { "epoch": 0.14010497470739638, "grad_norm": 7.562743663787842, "learning_rate": 2.8019639545389704e-06, "loss": 0.6508, "step": 23570 }, { "epoch": 0.14016441678406477, "grad_norm": 9.115564346313477, "learning_rate": 2.8031527890056593e-06, "loss": 0.7618, "step": 23580 }, { "epoch": 0.14022385886073316, "grad_norm": 9.698111534118652, "learning_rate": 2.8043416234723482e-06, "loss": 0.7104, "step": 23590 }, { "epoch": 0.14028330093740154, "grad_norm": 9.297735214233398, "learning_rate": 2.8055304579390367e-06, "loss": 0.7464, "step": 23600 }, { "epoch": 0.14034274301406993, "grad_norm": 10.898578643798828, "learning_rate": 2.8067192924057257e-06, "loss": 0.742, "step": 23610 }, { "epoch": 0.14040218509073832, "grad_norm": 8.817962646484375, "learning_rate": 2.8079081268724146e-06, "loss": 0.6703, "step": 23620 }, { "epoch": 0.14046162716740673, "grad_norm": 10.511042594909668, "learning_rate": 2.8090969613391035e-06, "loss": 0.7061, "step": 23630 }, { "epoch": 0.14052106924407512, "grad_norm": 11.338579177856445, "learning_rate": 2.810285795805792e-06, "loss": 0.7381, "step": 23640 }, { "epoch": 0.1405805113207435, "grad_norm": 10.429936408996582, "learning_rate": 2.811474630272481e-06, "loss": 0.7599, "step": 23650 }, { "epoch": 0.1406399533974119, "grad_norm": 8.992417335510254, "learning_rate": 2.81266346473917e-06, "loss": 0.6901, "step": 23660 }, { "epoch": 0.14069939547408028, "grad_norm": 8.531044960021973, "learning_rate": 2.813852299205859e-06, "loss": 0.7051, "step": 23670 }, { "epoch": 0.14075883755074867, "grad_norm": 10.167252540588379, "learning_rate": 2.8150411336725473e-06, "loss": 0.7129, "step": 23680 }, { "epoch": 0.14081827962741705, "grad_norm": 9.056034088134766, "learning_rate": 2.8162299681392362e-06, "loss": 0.7617, "step": 23690 }, { "epoch": 0.14087772170408544, "grad_norm": 10.289331436157227, "learning_rate": 2.817418802605925e-06, "loss": 0.6997, "step": 23700 }, { "epoch": 0.14093716378075385, "grad_norm": 11.130887985229492, "learning_rate": 2.818607637072614e-06, "loss": 0.732, "step": 23710 }, { "epoch": 0.14099660585742224, "grad_norm": 9.107584953308105, "learning_rate": 2.8197964715393034e-06, "loss": 0.7442, "step": 23720 }, { "epoch": 0.14105604793409063, "grad_norm": 8.858990669250488, "learning_rate": 2.8209853060059924e-06, "loss": 0.7223, "step": 23730 }, { "epoch": 0.14111549001075901, "grad_norm": 11.07327651977539, "learning_rate": 2.822174140472681e-06, "loss": 0.7628, "step": 23740 }, { "epoch": 0.1411749320874274, "grad_norm": 10.281743049621582, "learning_rate": 2.82336297493937e-06, "loss": 0.7569, "step": 23750 }, { "epoch": 0.1412343741640958, "grad_norm": 10.943135261535645, "learning_rate": 2.8245518094060587e-06, "loss": 0.7283, "step": 23760 }, { "epoch": 0.14129381624076418, "grad_norm": 9.832005500793457, "learning_rate": 2.8257406438727476e-06, "loss": 0.695, "step": 23770 }, { "epoch": 0.1413532583174326, "grad_norm": 8.99422836303711, "learning_rate": 2.826929478339436e-06, "loss": 0.7456, "step": 23780 }, { "epoch": 0.14141270039410098, "grad_norm": 7.275639057159424, "learning_rate": 2.828118312806125e-06, "loss": 0.7313, "step": 23790 }, { "epoch": 0.14147214247076936, "grad_norm": 9.794456481933594, "learning_rate": 2.829307147272814e-06, "loss": 0.7054, "step": 23800 }, { "epoch": 0.14153158454743775, "grad_norm": 8.928378105163574, "learning_rate": 2.830495981739503e-06, "loss": 0.7723, "step": 23810 }, { "epoch": 0.14159102662410614, "grad_norm": 10.843429565429688, "learning_rate": 2.8316848162061914e-06, "loss": 0.7539, "step": 23820 }, { "epoch": 0.14165046870077452, "grad_norm": 9.144158363342285, "learning_rate": 2.8328736506728804e-06, "loss": 0.7056, "step": 23830 }, { "epoch": 0.1417099107774429, "grad_norm": 9.359353065490723, "learning_rate": 2.8340624851395693e-06, "loss": 0.751, "step": 23840 }, { "epoch": 0.14176935285411132, "grad_norm": 10.089884757995605, "learning_rate": 2.8352513196062582e-06, "loss": 0.7855, "step": 23850 }, { "epoch": 0.1418287949307797, "grad_norm": 10.274927139282227, "learning_rate": 2.8364401540729467e-06, "loss": 0.6665, "step": 23860 }, { "epoch": 0.1418882370074481, "grad_norm": 9.535508155822754, "learning_rate": 2.8376289885396357e-06, "loss": 0.6962, "step": 23870 }, { "epoch": 0.14194767908411648, "grad_norm": 11.41601276397705, "learning_rate": 2.8388178230063246e-06, "loss": 0.7418, "step": 23880 }, { "epoch": 0.14200712116078487, "grad_norm": 9.567750930786133, "learning_rate": 2.840006657473014e-06, "loss": 0.7275, "step": 23890 }, { "epoch": 0.14206656323745326, "grad_norm": 8.681595802307129, "learning_rate": 2.841195491939703e-06, "loss": 0.7173, "step": 23900 }, { "epoch": 0.14212600531412165, "grad_norm": 9.80040454864502, "learning_rate": 2.8423843264063918e-06, "loss": 0.7297, "step": 23910 }, { "epoch": 0.14218544739079003, "grad_norm": 9.303585052490234, "learning_rate": 2.8435731608730803e-06, "loss": 0.7146, "step": 23920 }, { "epoch": 0.14224488946745845, "grad_norm": 8.119450569152832, "learning_rate": 2.8447619953397692e-06, "loss": 0.6776, "step": 23930 }, { "epoch": 0.14230433154412683, "grad_norm": 9.245762825012207, "learning_rate": 2.845950829806458e-06, "loss": 0.7338, "step": 23940 }, { "epoch": 0.14236377362079522, "grad_norm": 11.401512145996094, "learning_rate": 2.847139664273147e-06, "loss": 0.7723, "step": 23950 }, { "epoch": 0.1424232156974636, "grad_norm": 9.314669609069824, "learning_rate": 2.8483284987398356e-06, "loss": 0.723, "step": 23960 }, { "epoch": 0.142482657774132, "grad_norm": 10.14944076538086, "learning_rate": 2.8495173332065245e-06, "loss": 0.6908, "step": 23970 }, { "epoch": 0.14254209985080038, "grad_norm": 10.721872329711914, "learning_rate": 2.8507061676732134e-06, "loss": 0.7075, "step": 23980 }, { "epoch": 0.14260154192746877, "grad_norm": 9.379276275634766, "learning_rate": 2.8518950021399024e-06, "loss": 0.7948, "step": 23990 }, { "epoch": 0.14266098400413718, "grad_norm": 7.567738056182861, "learning_rate": 2.853083836606591e-06, "loss": 0.7245, "step": 24000 }, { "epoch": 0.14272042608080557, "grad_norm": 9.345239639282227, "learning_rate": 2.8542726710732798e-06, "loss": 0.799, "step": 24010 }, { "epoch": 0.14277986815747395, "grad_norm": 9.599331855773926, "learning_rate": 2.8554615055399687e-06, "loss": 0.732, "step": 24020 }, { "epoch": 0.14283931023414234, "grad_norm": 7.802347183227539, "learning_rate": 2.8566503400066576e-06, "loss": 0.6714, "step": 24030 }, { "epoch": 0.14289875231081073, "grad_norm": 10.102877616882324, "learning_rate": 2.857839174473346e-06, "loss": 0.7182, "step": 24040 }, { "epoch": 0.14295819438747912, "grad_norm": 7.640513896942139, "learning_rate": 2.859028008940035e-06, "loss": 0.652, "step": 24050 }, { "epoch": 0.1430176364641475, "grad_norm": 9.58145523071289, "learning_rate": 2.860216843406724e-06, "loss": 0.7306, "step": 24060 }, { "epoch": 0.1430770785408159, "grad_norm": 11.081226348876953, "learning_rate": 2.8614056778734134e-06, "loss": 0.8332, "step": 24070 }, { "epoch": 0.1431365206174843, "grad_norm": 9.018420219421387, "learning_rate": 2.8625945123401023e-06, "loss": 0.721, "step": 24080 }, { "epoch": 0.1431959626941527, "grad_norm": 11.104393005371094, "learning_rate": 2.863783346806791e-06, "loss": 0.6864, "step": 24090 }, { "epoch": 0.14325540477082108, "grad_norm": 9.15414810180664, "learning_rate": 2.8649721812734797e-06, "loss": 0.7142, "step": 24100 }, { "epoch": 0.14331484684748946, "grad_norm": 9.986834526062012, "learning_rate": 2.8661610157401686e-06, "loss": 0.7372, "step": 24110 }, { "epoch": 0.14337428892415785, "grad_norm": 9.702848434448242, "learning_rate": 2.8673498502068576e-06, "loss": 0.7324, "step": 24120 }, { "epoch": 0.14343373100082624, "grad_norm": 11.452770233154297, "learning_rate": 2.8685386846735465e-06, "loss": 0.8062, "step": 24130 }, { "epoch": 0.14349317307749462, "grad_norm": 11.180307388305664, "learning_rate": 2.869727519140235e-06, "loss": 0.726, "step": 24140 }, { "epoch": 0.14355261515416304, "grad_norm": 9.311229705810547, "learning_rate": 2.870916353606924e-06, "loss": 0.6885, "step": 24150 }, { "epoch": 0.14361205723083142, "grad_norm": 9.978654861450195, "learning_rate": 2.872105188073613e-06, "loss": 0.7143, "step": 24160 }, { "epoch": 0.1436714993074998, "grad_norm": 7.605387210845947, "learning_rate": 2.8732940225403018e-06, "loss": 0.7035, "step": 24170 }, { "epoch": 0.1437309413841682, "grad_norm": 9.317566871643066, "learning_rate": 2.8744828570069903e-06, "loss": 0.715, "step": 24180 }, { "epoch": 0.14379038346083658, "grad_norm": 8.307605743408203, "learning_rate": 2.875671691473679e-06, "loss": 0.6726, "step": 24190 }, { "epoch": 0.14384982553750497, "grad_norm": 9.912699699401855, "learning_rate": 2.876860525940368e-06, "loss": 0.777, "step": 24200 }, { "epoch": 0.14390926761417336, "grad_norm": 8.53706169128418, "learning_rate": 2.878049360407057e-06, "loss": 0.6852, "step": 24210 }, { "epoch": 0.14396870969084177, "grad_norm": 9.772998809814453, "learning_rate": 2.879238194873746e-06, "loss": 0.6973, "step": 24220 }, { "epoch": 0.14402815176751016, "grad_norm": 12.708968162536621, "learning_rate": 2.8804270293404345e-06, "loss": 0.6934, "step": 24230 }, { "epoch": 0.14408759384417855, "grad_norm": 12.13929271697998, "learning_rate": 2.881615863807124e-06, "loss": 0.667, "step": 24240 }, { "epoch": 0.14414703592084693, "grad_norm": 11.003640174865723, "learning_rate": 2.8828046982738128e-06, "loss": 0.7539, "step": 24250 }, { "epoch": 0.14420647799751532, "grad_norm": 8.029396057128906, "learning_rate": 2.8839935327405017e-06, "loss": 0.7672, "step": 24260 }, { "epoch": 0.1442659200741837, "grad_norm": 12.368839263916016, "learning_rate": 2.8851823672071906e-06, "loss": 0.7613, "step": 24270 }, { "epoch": 0.1443253621508521, "grad_norm": 10.948413848876953, "learning_rate": 2.886371201673879e-06, "loss": 0.6948, "step": 24280 }, { "epoch": 0.14438480422752048, "grad_norm": 8.640356063842773, "learning_rate": 2.887560036140568e-06, "loss": 0.7377, "step": 24290 }, { "epoch": 0.1444442463041889, "grad_norm": 9.833303451538086, "learning_rate": 2.888748870607257e-06, "loss": 0.746, "step": 24300 }, { "epoch": 0.14450368838085728, "grad_norm": 9.860204696655273, "learning_rate": 2.889937705073946e-06, "loss": 0.6865, "step": 24310 }, { "epoch": 0.14456313045752567, "grad_norm": 9.032759666442871, "learning_rate": 2.8911265395406344e-06, "loss": 0.6592, "step": 24320 }, { "epoch": 0.14462257253419405, "grad_norm": 6.717288017272949, "learning_rate": 2.8923153740073233e-06, "loss": 0.7399, "step": 24330 }, { "epoch": 0.14468201461086244, "grad_norm": 11.817818641662598, "learning_rate": 2.8935042084740123e-06, "loss": 0.7518, "step": 24340 }, { "epoch": 0.14474145668753083, "grad_norm": 8.965615272521973, "learning_rate": 2.894693042940701e-06, "loss": 0.6459, "step": 24350 }, { "epoch": 0.14480089876419922, "grad_norm": 9.494490623474121, "learning_rate": 2.8958818774073897e-06, "loss": 0.7632, "step": 24360 }, { "epoch": 0.14486034084086763, "grad_norm": 10.809196472167969, "learning_rate": 2.8970707118740786e-06, "loss": 0.7158, "step": 24370 }, { "epoch": 0.14491978291753602, "grad_norm": 13.679283142089844, "learning_rate": 2.8982595463407676e-06, "loss": 0.7736, "step": 24380 }, { "epoch": 0.1449792249942044, "grad_norm": 9.964676856994629, "learning_rate": 2.8994483808074565e-06, "loss": 0.734, "step": 24390 }, { "epoch": 0.1450386670708728, "grad_norm": 10.348066329956055, "learning_rate": 2.9006372152741454e-06, "loss": 0.7252, "step": 24400 }, { "epoch": 0.14509810914754118, "grad_norm": 11.169856071472168, "learning_rate": 2.9018260497408348e-06, "loss": 0.7473, "step": 24410 }, { "epoch": 0.14515755122420956, "grad_norm": 8.251875877380371, "learning_rate": 2.9030148842075233e-06, "loss": 0.674, "step": 24420 }, { "epoch": 0.14521699330087795, "grad_norm": 10.711884498596191, "learning_rate": 2.904203718674212e-06, "loss": 0.6877, "step": 24430 }, { "epoch": 0.14527643537754634, "grad_norm": 11.207534790039062, "learning_rate": 2.905392553140901e-06, "loss": 0.7328, "step": 24440 }, { "epoch": 0.14533587745421475, "grad_norm": 10.017882347106934, "learning_rate": 2.90658138760759e-06, "loss": 0.7009, "step": 24450 }, { "epoch": 0.14539531953088314, "grad_norm": 9.124810218811035, "learning_rate": 2.9077702220742786e-06, "loss": 0.7457, "step": 24460 }, { "epoch": 0.14545476160755152, "grad_norm": 7.640619277954102, "learning_rate": 2.9089590565409675e-06, "loss": 0.7454, "step": 24470 }, { "epoch": 0.1455142036842199, "grad_norm": 9.644009590148926, "learning_rate": 2.9101478910076564e-06, "loss": 0.7254, "step": 24480 }, { "epoch": 0.1455736457608883, "grad_norm": 8.398078918457031, "learning_rate": 2.9113367254743453e-06, "loss": 0.7698, "step": 24490 }, { "epoch": 0.14563308783755669, "grad_norm": 9.384159088134766, "learning_rate": 2.912525559941034e-06, "loss": 0.7596, "step": 24500 }, { "epoch": 0.14569252991422507, "grad_norm": 9.565109252929688, "learning_rate": 2.9137143944077228e-06, "loss": 0.6885, "step": 24510 }, { "epoch": 0.1457519719908935, "grad_norm": 11.337008476257324, "learning_rate": 2.9149032288744117e-06, "loss": 0.678, "step": 24520 }, { "epoch": 0.14581141406756187, "grad_norm": 9.57529067993164, "learning_rate": 2.9160920633411006e-06, "loss": 0.6607, "step": 24530 }, { "epoch": 0.14587085614423026, "grad_norm": 9.875778198242188, "learning_rate": 2.9172808978077895e-06, "loss": 0.7469, "step": 24540 }, { "epoch": 0.14593029822089865, "grad_norm": 11.554302215576172, "learning_rate": 2.918469732274478e-06, "loss": 0.7643, "step": 24550 }, { "epoch": 0.14598974029756703, "grad_norm": 8.604129791259766, "learning_rate": 2.919658566741167e-06, "loss": 0.6864, "step": 24560 }, { "epoch": 0.14604918237423542, "grad_norm": 9.667366981506348, "learning_rate": 2.920847401207856e-06, "loss": 0.6778, "step": 24570 }, { "epoch": 0.1461086244509038, "grad_norm": 9.649164199829102, "learning_rate": 2.922036235674545e-06, "loss": 0.7197, "step": 24580 }, { "epoch": 0.1461680665275722, "grad_norm": 11.946945190429688, "learning_rate": 2.923225070141234e-06, "loss": 0.762, "step": 24590 }, { "epoch": 0.1462275086042406, "grad_norm": 8.806982040405273, "learning_rate": 2.9244139046079227e-06, "loss": 0.7433, "step": 24600 }, { "epoch": 0.146286950680909, "grad_norm": 11.594438552856445, "learning_rate": 2.9256027390746116e-06, "loss": 0.7402, "step": 24610 }, { "epoch": 0.14634639275757738, "grad_norm": 8.779601097106934, "learning_rate": 2.9267915735413005e-06, "loss": 0.758, "step": 24620 }, { "epoch": 0.14640583483424577, "grad_norm": 9.079570770263672, "learning_rate": 2.9279804080079895e-06, "loss": 0.7102, "step": 24630 }, { "epoch": 0.14646527691091416, "grad_norm": 8.765316009521484, "learning_rate": 2.929169242474678e-06, "loss": 0.675, "step": 24640 }, { "epoch": 0.14652471898758254, "grad_norm": 7.40397834777832, "learning_rate": 2.930358076941367e-06, "loss": 0.7093, "step": 24650 }, { "epoch": 0.14658416106425093, "grad_norm": 9.350418090820312, "learning_rate": 2.931546911408056e-06, "loss": 0.7279, "step": 24660 }, { "epoch": 0.14664360314091934, "grad_norm": 9.342791557312012, "learning_rate": 2.9327357458747448e-06, "loss": 0.7142, "step": 24670 }, { "epoch": 0.14670304521758773, "grad_norm": 9.758598327636719, "learning_rate": 2.9339245803414333e-06, "loss": 0.7332, "step": 24680 }, { "epoch": 0.14676248729425612, "grad_norm": 11.19659423828125, "learning_rate": 2.935113414808122e-06, "loss": 0.7266, "step": 24690 }, { "epoch": 0.1468219293709245, "grad_norm": 9.16870403289795, "learning_rate": 2.936302249274811e-06, "loss": 0.6788, "step": 24700 }, { "epoch": 0.1468813714475929, "grad_norm": 9.447781562805176, "learning_rate": 2.9374910837415e-06, "loss": 0.699, "step": 24710 }, { "epoch": 0.14694081352426128, "grad_norm": 9.227916717529297, "learning_rate": 2.938679918208189e-06, "loss": 0.7006, "step": 24720 }, { "epoch": 0.14700025560092966, "grad_norm": 8.828307151794434, "learning_rate": 2.9398687526748775e-06, "loss": 0.7423, "step": 24730 }, { "epoch": 0.14705969767759808, "grad_norm": 8.973493576049805, "learning_rate": 2.9410575871415664e-06, "loss": 0.684, "step": 24740 }, { "epoch": 0.14711913975426646, "grad_norm": 8.972518920898438, "learning_rate": 2.9422464216082553e-06, "loss": 0.7005, "step": 24750 }, { "epoch": 0.14717858183093485, "grad_norm": 10.306690216064453, "learning_rate": 2.9434352560749447e-06, "loss": 0.6931, "step": 24760 }, { "epoch": 0.14723802390760324, "grad_norm": 9.049233436584473, "learning_rate": 2.9446240905416336e-06, "loss": 0.7312, "step": 24770 }, { "epoch": 0.14729746598427162, "grad_norm": 9.215888023376465, "learning_rate": 2.945812925008322e-06, "loss": 0.6798, "step": 24780 }, { "epoch": 0.14735690806094, "grad_norm": 8.52889347076416, "learning_rate": 2.947001759475011e-06, "loss": 0.7029, "step": 24790 }, { "epoch": 0.1474163501376084, "grad_norm": 8.983657836914062, "learning_rate": 2.9481905939417e-06, "loss": 0.7602, "step": 24800 }, { "epoch": 0.14747579221427679, "grad_norm": 8.133355140686035, "learning_rate": 2.949379428408389e-06, "loss": 0.7507, "step": 24810 }, { "epoch": 0.1475352342909452, "grad_norm": 10.981107711791992, "learning_rate": 2.9505682628750774e-06, "loss": 0.752, "step": 24820 }, { "epoch": 0.1475946763676136, "grad_norm": 8.12620735168457, "learning_rate": 2.9517570973417663e-06, "loss": 0.7202, "step": 24830 }, { "epoch": 0.14765411844428197, "grad_norm": 10.518827438354492, "learning_rate": 2.9529459318084552e-06, "loss": 0.7578, "step": 24840 }, { "epoch": 0.14771356052095036, "grad_norm": 9.923151016235352, "learning_rate": 2.954134766275144e-06, "loss": 0.7531, "step": 24850 }, { "epoch": 0.14777300259761875, "grad_norm": 11.939285278320312, "learning_rate": 2.9553236007418327e-06, "loss": 0.7676, "step": 24860 }, { "epoch": 0.14783244467428713, "grad_norm": 8.179567337036133, "learning_rate": 2.9565124352085216e-06, "loss": 0.687, "step": 24870 }, { "epoch": 0.14789188675095552, "grad_norm": 9.743636131286621, "learning_rate": 2.9577012696752105e-06, "loss": 0.7405, "step": 24880 }, { "epoch": 0.14795132882762393, "grad_norm": 11.100442886352539, "learning_rate": 2.9588901041418995e-06, "loss": 0.7112, "step": 24890 }, { "epoch": 0.14801077090429232, "grad_norm": 10.615334510803223, "learning_rate": 2.9600789386085884e-06, "loss": 0.797, "step": 24900 }, { "epoch": 0.1480702129809607, "grad_norm": 10.450061798095703, "learning_rate": 2.961267773075277e-06, "loss": 0.7065, "step": 24910 }, { "epoch": 0.1481296550576291, "grad_norm": 9.446578979492188, "learning_rate": 2.962456607541966e-06, "loss": 0.7526, "step": 24920 }, { "epoch": 0.14818909713429748, "grad_norm": 10.42667007446289, "learning_rate": 2.963645442008655e-06, "loss": 0.7324, "step": 24930 }, { "epoch": 0.14824853921096587, "grad_norm": 8.40521240234375, "learning_rate": 2.964834276475344e-06, "loss": 0.7086, "step": 24940 }, { "epoch": 0.14830798128763426, "grad_norm": 10.013951301574707, "learning_rate": 2.966023110942033e-06, "loss": 0.7102, "step": 24950 }, { "epoch": 0.14836742336430264, "grad_norm": 10.835878372192383, "learning_rate": 2.9672119454087215e-06, "loss": 0.6842, "step": 24960 }, { "epoch": 0.14842686544097106, "grad_norm": 11.177253723144531, "learning_rate": 2.9684007798754105e-06, "loss": 0.6481, "step": 24970 }, { "epoch": 0.14848630751763944, "grad_norm": 12.162168502807617, "learning_rate": 2.9695896143420994e-06, "loss": 0.7846, "step": 24980 }, { "epoch": 0.14854574959430783, "grad_norm": 10.787837028503418, "learning_rate": 2.9707784488087883e-06, "loss": 0.6906, "step": 24990 }, { "epoch": 0.14860519167097622, "grad_norm": 10.033075332641602, "learning_rate": 2.971967283275477e-06, "loss": 0.6995, "step": 25000 }, { "epoch": 0.1486646337476446, "grad_norm": 10.810420989990234, "learning_rate": 2.9731561177421657e-06, "loss": 0.6951, "step": 25010 }, { "epoch": 0.148724075824313, "grad_norm": 9.460221290588379, "learning_rate": 2.9743449522088547e-06, "loss": 0.7075, "step": 25020 }, { "epoch": 0.14878351790098138, "grad_norm": 11.087631225585938, "learning_rate": 2.9755337866755436e-06, "loss": 0.7652, "step": 25030 }, { "epoch": 0.1488429599776498, "grad_norm": 6.948972702026367, "learning_rate": 2.9767226211422325e-06, "loss": 0.6976, "step": 25040 }, { "epoch": 0.14890240205431818, "grad_norm": 10.24422550201416, "learning_rate": 2.977911455608921e-06, "loss": 0.7481, "step": 25050 }, { "epoch": 0.14896184413098656, "grad_norm": 10.747560501098633, "learning_rate": 2.97910029007561e-06, "loss": 0.7132, "step": 25060 }, { "epoch": 0.14902128620765495, "grad_norm": 10.00326919555664, "learning_rate": 2.980289124542299e-06, "loss": 0.7481, "step": 25070 }, { "epoch": 0.14908072828432334, "grad_norm": 9.715179443359375, "learning_rate": 2.981477959008988e-06, "loss": 0.6826, "step": 25080 }, { "epoch": 0.14914017036099173, "grad_norm": 10.229256629943848, "learning_rate": 2.9826667934756763e-06, "loss": 0.714, "step": 25090 }, { "epoch": 0.1491996124376601, "grad_norm": 9.719515800476074, "learning_rate": 2.9838556279423652e-06, "loss": 0.6502, "step": 25100 }, { "epoch": 0.14925905451432853, "grad_norm": 9.4329195022583, "learning_rate": 2.9850444624090546e-06, "loss": 0.7389, "step": 25110 }, { "epoch": 0.1493184965909969, "grad_norm": 8.65362548828125, "learning_rate": 2.9862332968757435e-06, "loss": 0.6453, "step": 25120 }, { "epoch": 0.1493779386676653, "grad_norm": 10.774035453796387, "learning_rate": 2.9874221313424324e-06, "loss": 0.7418, "step": 25130 }, { "epoch": 0.1494373807443337, "grad_norm": 10.267230987548828, "learning_rate": 2.988610965809121e-06, "loss": 0.7905, "step": 25140 }, { "epoch": 0.14949682282100207, "grad_norm": 11.00089168548584, "learning_rate": 2.98979980027581e-06, "loss": 0.7107, "step": 25150 }, { "epoch": 0.14955626489767046, "grad_norm": 9.966320037841797, "learning_rate": 2.990988634742499e-06, "loss": 0.6968, "step": 25160 }, { "epoch": 0.14961570697433885, "grad_norm": 8.526150703430176, "learning_rate": 2.9921774692091877e-06, "loss": 0.724, "step": 25170 }, { "epoch": 0.14967514905100723, "grad_norm": 10.479116439819336, "learning_rate": 2.9933663036758762e-06, "loss": 0.704, "step": 25180 }, { "epoch": 0.14973459112767565, "grad_norm": 10.59709358215332, "learning_rate": 2.994555138142565e-06, "loss": 0.6778, "step": 25190 }, { "epoch": 0.14979403320434403, "grad_norm": 9.23696231842041, "learning_rate": 2.995743972609254e-06, "loss": 0.7601, "step": 25200 }, { "epoch": 0.14985347528101242, "grad_norm": 9.38515853881836, "learning_rate": 2.996932807075943e-06, "loss": 0.7189, "step": 25210 }, { "epoch": 0.1499129173576808, "grad_norm": 9.502211570739746, "learning_rate": 2.998121641542632e-06, "loss": 0.6951, "step": 25220 }, { "epoch": 0.1499723594343492, "grad_norm": 9.411215782165527, "learning_rate": 2.9993104760093204e-06, "loss": 0.6777, "step": 25230 }, { "epoch": 0.15003180151101758, "grad_norm": 9.890499114990234, "learning_rate": 3.0004993104760094e-06, "loss": 0.7058, "step": 25240 }, { "epoch": 0.15009124358768597, "grad_norm": 9.732481002807617, "learning_rate": 3.0016881449426983e-06, "loss": 0.7508, "step": 25250 }, { "epoch": 0.15015068566435438, "grad_norm": 12.655434608459473, "learning_rate": 3.0028769794093872e-06, "loss": 0.745, "step": 25260 }, { "epoch": 0.15021012774102277, "grad_norm": 10.134230613708496, "learning_rate": 3.0040658138760757e-06, "loss": 0.7244, "step": 25270 }, { "epoch": 0.15026956981769116, "grad_norm": 8.450704574584961, "learning_rate": 3.005254648342765e-06, "loss": 0.7145, "step": 25280 }, { "epoch": 0.15032901189435954, "grad_norm": 7.789989471435547, "learning_rate": 3.006443482809454e-06, "loss": 0.7931, "step": 25290 }, { "epoch": 0.15038845397102793, "grad_norm": 10.95936393737793, "learning_rate": 3.007632317276143e-06, "loss": 0.7253, "step": 25300 }, { "epoch": 0.15044789604769632, "grad_norm": 10.489068984985352, "learning_rate": 3.008821151742832e-06, "loss": 0.7132, "step": 25310 }, { "epoch": 0.1505073381243647, "grad_norm": 8.379778861999512, "learning_rate": 3.0100099862095204e-06, "loss": 0.6907, "step": 25320 }, { "epoch": 0.1505667802010331, "grad_norm": 9.990204811096191, "learning_rate": 3.0111988206762093e-06, "loss": 0.7686, "step": 25330 }, { "epoch": 0.1506262222777015, "grad_norm": 10.717948913574219, "learning_rate": 3.0123876551428982e-06, "loss": 0.6815, "step": 25340 }, { "epoch": 0.1506856643543699, "grad_norm": 9.71837043762207, "learning_rate": 3.013576489609587e-06, "loss": 0.6708, "step": 25350 }, { "epoch": 0.15074510643103828, "grad_norm": 10.648045539855957, "learning_rate": 3.014765324076276e-06, "loss": 0.6795, "step": 25360 }, { "epoch": 0.15080454850770666, "grad_norm": 10.959820747375488, "learning_rate": 3.0159541585429646e-06, "loss": 0.7201, "step": 25370 }, { "epoch": 0.15086399058437505, "grad_norm": 10.509831428527832, "learning_rate": 3.0171429930096535e-06, "loss": 0.7141, "step": 25380 }, { "epoch": 0.15092343266104344, "grad_norm": 9.821182250976562, "learning_rate": 3.0183318274763424e-06, "loss": 0.6953, "step": 25390 }, { "epoch": 0.15098287473771183, "grad_norm": 11.394097328186035, "learning_rate": 3.0195206619430314e-06, "loss": 0.714, "step": 25400 }, { "epoch": 0.15104231681438024, "grad_norm": 9.609843254089355, "learning_rate": 3.02070949640972e-06, "loss": 0.7218, "step": 25410 }, { "epoch": 0.15110175889104863, "grad_norm": 9.042610168457031, "learning_rate": 3.021898330876409e-06, "loss": 0.7216, "step": 25420 }, { "epoch": 0.151161200967717, "grad_norm": 8.68135929107666, "learning_rate": 3.0230871653430977e-06, "loss": 0.6967, "step": 25430 }, { "epoch": 0.1512206430443854, "grad_norm": 7.290036201477051, "learning_rate": 3.0242759998097867e-06, "loss": 0.6486, "step": 25440 }, { "epoch": 0.1512800851210538, "grad_norm": 7.959737300872803, "learning_rate": 3.025464834276476e-06, "loss": 0.6734, "step": 25450 }, { "epoch": 0.15133952719772217, "grad_norm": 8.995018005371094, "learning_rate": 3.0266536687431645e-06, "loss": 0.7018, "step": 25460 }, { "epoch": 0.15139896927439056, "grad_norm": 10.048550605773926, "learning_rate": 3.0278425032098534e-06, "loss": 0.7063, "step": 25470 }, { "epoch": 0.15145841135105895, "grad_norm": 9.293588638305664, "learning_rate": 3.0290313376765424e-06, "loss": 0.6992, "step": 25480 }, { "epoch": 0.15151785342772736, "grad_norm": 11.85992431640625, "learning_rate": 3.0302201721432313e-06, "loss": 0.6841, "step": 25490 }, { "epoch": 0.15157729550439575, "grad_norm": 9.795784950256348, "learning_rate": 3.03140900660992e-06, "loss": 0.7568, "step": 25500 }, { "epoch": 0.15163673758106413, "grad_norm": 10.092931747436523, "learning_rate": 3.0325978410766087e-06, "loss": 0.6803, "step": 25510 }, { "epoch": 0.15169617965773252, "grad_norm": 9.849778175354004, "learning_rate": 3.0337866755432976e-06, "loss": 0.7119, "step": 25520 }, { "epoch": 0.1517556217344009, "grad_norm": 9.733824729919434, "learning_rate": 3.0349755100099866e-06, "loss": 0.7046, "step": 25530 }, { "epoch": 0.1518150638110693, "grad_norm": 7.751812934875488, "learning_rate": 3.0361643444766755e-06, "loss": 0.6865, "step": 25540 }, { "epoch": 0.15187450588773768, "grad_norm": 9.809257507324219, "learning_rate": 3.037353178943364e-06, "loss": 0.711, "step": 25550 }, { "epoch": 0.1519339479644061, "grad_norm": 9.83141040802002, "learning_rate": 3.038542013410053e-06, "loss": 0.6621, "step": 25560 }, { "epoch": 0.15199339004107448, "grad_norm": 9.598670959472656, "learning_rate": 3.039730847876742e-06, "loss": 0.7528, "step": 25570 }, { "epoch": 0.15205283211774287, "grad_norm": 10.071137428283691, "learning_rate": 3.0409196823434308e-06, "loss": 0.7353, "step": 25580 }, { "epoch": 0.15211227419441126, "grad_norm": 8.130788803100586, "learning_rate": 3.0421085168101193e-06, "loss": 0.7211, "step": 25590 }, { "epoch": 0.15217171627107964, "grad_norm": 9.097517013549805, "learning_rate": 3.0432973512768082e-06, "loss": 0.758, "step": 25600 }, { "epoch": 0.15223115834774803, "grad_norm": 8.395975112915039, "learning_rate": 3.044486185743497e-06, "loss": 0.6686, "step": 25610 }, { "epoch": 0.15229060042441642, "grad_norm": 10.50407886505127, "learning_rate": 3.045675020210186e-06, "loss": 0.7303, "step": 25620 }, { "epoch": 0.15235004250108483, "grad_norm": 8.04475212097168, "learning_rate": 3.0468638546768754e-06, "loss": 0.7014, "step": 25630 }, { "epoch": 0.15240948457775322, "grad_norm": 14.265249252319336, "learning_rate": 3.048052689143564e-06, "loss": 0.7879, "step": 25640 }, { "epoch": 0.1524689266544216, "grad_norm": 8.534071922302246, "learning_rate": 3.049241523610253e-06, "loss": 0.7298, "step": 25650 }, { "epoch": 0.15252836873109, "grad_norm": 10.647603034973145, "learning_rate": 3.0504303580769418e-06, "loss": 0.6927, "step": 25660 }, { "epoch": 0.15258781080775838, "grad_norm": 9.383515357971191, "learning_rate": 3.0516191925436307e-06, "loss": 0.7144, "step": 25670 }, { "epoch": 0.15264725288442677, "grad_norm": 9.667879104614258, "learning_rate": 3.052808027010319e-06, "loss": 0.6994, "step": 25680 }, { "epoch": 0.15270669496109515, "grad_norm": 10.419921875, "learning_rate": 3.053996861477008e-06, "loss": 0.7307, "step": 25690 }, { "epoch": 0.15276613703776354, "grad_norm": 10.214123725891113, "learning_rate": 3.055185695943697e-06, "loss": 0.7207, "step": 25700 }, { "epoch": 0.15282557911443195, "grad_norm": 10.768149375915527, "learning_rate": 3.056374530410386e-06, "loss": 0.7076, "step": 25710 }, { "epoch": 0.15288502119110034, "grad_norm": 11.904010772705078, "learning_rate": 3.057563364877075e-06, "loss": 0.7152, "step": 25720 }, { "epoch": 0.15294446326776873, "grad_norm": 6.389805316925049, "learning_rate": 3.0587521993437634e-06, "loss": 0.6897, "step": 25730 }, { "epoch": 0.1530039053444371, "grad_norm": 9.132770538330078, "learning_rate": 3.0599410338104524e-06, "loss": 0.6875, "step": 25740 }, { "epoch": 0.1530633474211055, "grad_norm": 8.512628555297852, "learning_rate": 3.0611298682771413e-06, "loss": 0.6907, "step": 25750 }, { "epoch": 0.1531227894977739, "grad_norm": 9.301660537719727, "learning_rate": 3.06231870274383e-06, "loss": 0.6984, "step": 25760 }, { "epoch": 0.15318223157444227, "grad_norm": 10.869705200195312, "learning_rate": 3.0635075372105187e-06, "loss": 0.7389, "step": 25770 }, { "epoch": 0.1532416736511107, "grad_norm": 8.605184555053711, "learning_rate": 3.0646963716772076e-06, "loss": 0.7534, "step": 25780 }, { "epoch": 0.15330111572777907, "grad_norm": 10.890801429748535, "learning_rate": 3.0658852061438966e-06, "loss": 0.7217, "step": 25790 }, { "epoch": 0.15336055780444746, "grad_norm": 8.584189414978027, "learning_rate": 3.067074040610586e-06, "loss": 0.6903, "step": 25800 }, { "epoch": 0.15341999988111585, "grad_norm": 8.195144653320312, "learning_rate": 3.068262875077275e-06, "loss": 0.7161, "step": 25810 }, { "epoch": 0.15347944195778424, "grad_norm": 11.394451141357422, "learning_rate": 3.0694517095439633e-06, "loss": 0.7187, "step": 25820 }, { "epoch": 0.15353888403445262, "grad_norm": 10.1049165725708, "learning_rate": 3.0706405440106523e-06, "loss": 0.7323, "step": 25830 }, { "epoch": 0.153598326111121, "grad_norm": 9.671968460083008, "learning_rate": 3.071829378477341e-06, "loss": 0.7096, "step": 25840 }, { "epoch": 0.1536577681877894, "grad_norm": 9.176618576049805, "learning_rate": 3.07301821294403e-06, "loss": 0.8181, "step": 25850 }, { "epoch": 0.1537172102644578, "grad_norm": 11.346219062805176, "learning_rate": 3.074207047410719e-06, "loss": 0.7328, "step": 25860 }, { "epoch": 0.1537766523411262, "grad_norm": 9.3463134765625, "learning_rate": 3.0753958818774076e-06, "loss": 0.7181, "step": 25870 }, { "epoch": 0.15383609441779458, "grad_norm": 10.331206321716309, "learning_rate": 3.0765847163440965e-06, "loss": 0.7523, "step": 25880 }, { "epoch": 0.15389553649446297, "grad_norm": 12.521062850952148, "learning_rate": 3.0777735508107854e-06, "loss": 0.711, "step": 25890 }, { "epoch": 0.15395497857113136, "grad_norm": 9.847697257995605, "learning_rate": 3.0789623852774743e-06, "loss": 0.708, "step": 25900 }, { "epoch": 0.15401442064779974, "grad_norm": 10.162883758544922, "learning_rate": 3.080151219744163e-06, "loss": 0.7339, "step": 25910 }, { "epoch": 0.15407386272446813, "grad_norm": 10.212610244750977, "learning_rate": 3.0813400542108518e-06, "loss": 0.697, "step": 25920 }, { "epoch": 0.15413330480113654, "grad_norm": 11.43034553527832, "learning_rate": 3.0825288886775407e-06, "loss": 0.7204, "step": 25930 }, { "epoch": 0.15419274687780493, "grad_norm": 11.288551330566406, "learning_rate": 3.0837177231442296e-06, "loss": 0.6953, "step": 25940 }, { "epoch": 0.15425218895447332, "grad_norm": 9.54840087890625, "learning_rate": 3.084906557610918e-06, "loss": 0.7393, "step": 25950 }, { "epoch": 0.1543116310311417, "grad_norm": 9.373539924621582, "learning_rate": 3.086095392077607e-06, "loss": 0.7264, "step": 25960 }, { "epoch": 0.1543710731078101, "grad_norm": 8.22435188293457, "learning_rate": 3.0872842265442964e-06, "loss": 0.7004, "step": 25970 }, { "epoch": 0.15443051518447848, "grad_norm": 9.047392845153809, "learning_rate": 3.0884730610109853e-06, "loss": 0.7437, "step": 25980 }, { "epoch": 0.15448995726114687, "grad_norm": 10.500576972961426, "learning_rate": 3.0896618954776743e-06, "loss": 0.7227, "step": 25990 }, { "epoch": 0.15454939933781528, "grad_norm": 10.173849105834961, "learning_rate": 3.0908507299443628e-06, "loss": 0.7348, "step": 26000 }, { "epoch": 0.15460884141448367, "grad_norm": 9.387625694274902, "learning_rate": 3.0920395644110517e-06, "loss": 0.698, "step": 26010 }, { "epoch": 0.15466828349115205, "grad_norm": 9.156950950622559, "learning_rate": 3.0932283988777406e-06, "loss": 0.7329, "step": 26020 }, { "epoch": 0.15472772556782044, "grad_norm": 9.140256881713867, "learning_rate": 3.0944172333444295e-06, "loss": 0.7113, "step": 26030 }, { "epoch": 0.15478716764448883, "grad_norm": 9.584809303283691, "learning_rate": 3.0956060678111185e-06, "loss": 0.6962, "step": 26040 }, { "epoch": 0.1548466097211572, "grad_norm": 10.051003456115723, "learning_rate": 3.096794902277807e-06, "loss": 0.7101, "step": 26050 }, { "epoch": 0.1549060517978256, "grad_norm": 7.330073356628418, "learning_rate": 3.097983736744496e-06, "loss": 0.6407, "step": 26060 }, { "epoch": 0.154965493874494, "grad_norm": 9.36936092376709, "learning_rate": 3.099172571211185e-06, "loss": 0.688, "step": 26070 }, { "epoch": 0.1550249359511624, "grad_norm": 11.930962562561035, "learning_rate": 3.1003614056778738e-06, "loss": 0.7733, "step": 26080 }, { "epoch": 0.1550843780278308, "grad_norm": 9.213875770568848, "learning_rate": 3.1015502401445623e-06, "loss": 0.7589, "step": 26090 }, { "epoch": 0.15514382010449917, "grad_norm": 9.657447814941406, "learning_rate": 3.102739074611251e-06, "loss": 0.7486, "step": 26100 }, { "epoch": 0.15520326218116756, "grad_norm": 8.697869300842285, "learning_rate": 3.10392790907794e-06, "loss": 0.7017, "step": 26110 }, { "epoch": 0.15526270425783595, "grad_norm": 8.506448745727539, "learning_rate": 3.105116743544629e-06, "loss": 0.6816, "step": 26120 }, { "epoch": 0.15532214633450434, "grad_norm": 10.3690185546875, "learning_rate": 3.1063055780113176e-06, "loss": 0.731, "step": 26130 }, { "epoch": 0.15538158841117272, "grad_norm": 14.592077255249023, "learning_rate": 3.1074944124780065e-06, "loss": 0.7144, "step": 26140 }, { "epoch": 0.15544103048784114, "grad_norm": 10.262422561645508, "learning_rate": 3.108683246944696e-06, "loss": 0.7664, "step": 26150 }, { "epoch": 0.15550047256450952, "grad_norm": 7.871021270751953, "learning_rate": 3.1098720814113848e-06, "loss": 0.66, "step": 26160 }, { "epoch": 0.1555599146411779, "grad_norm": 10.670528411865234, "learning_rate": 3.1110609158780737e-06, "loss": 0.7655, "step": 26170 }, { "epoch": 0.1556193567178463, "grad_norm": 9.565608024597168, "learning_rate": 3.112249750344762e-06, "loss": 0.6802, "step": 26180 }, { "epoch": 0.15567879879451468, "grad_norm": 9.909097671508789, "learning_rate": 3.113438584811451e-06, "loss": 0.6386, "step": 26190 }, { "epoch": 0.15573824087118307, "grad_norm": 8.518914222717285, "learning_rate": 3.11462741927814e-06, "loss": 0.6843, "step": 26200 }, { "epoch": 0.15579768294785146, "grad_norm": 10.272909164428711, "learning_rate": 3.115816253744829e-06, "loss": 0.709, "step": 26210 }, { "epoch": 0.15585712502451984, "grad_norm": 9.189414024353027, "learning_rate": 3.117005088211518e-06, "loss": 0.6774, "step": 26220 }, { "epoch": 0.15591656710118826, "grad_norm": 9.781046867370605, "learning_rate": 3.1181939226782064e-06, "loss": 0.7128, "step": 26230 }, { "epoch": 0.15597600917785664, "grad_norm": 8.716327667236328, "learning_rate": 3.1193827571448953e-06, "loss": 0.7053, "step": 26240 }, { "epoch": 0.15603545125452503, "grad_norm": 9.488153457641602, "learning_rate": 3.1205715916115843e-06, "loss": 0.7242, "step": 26250 }, { "epoch": 0.15609489333119342, "grad_norm": 11.570638656616211, "learning_rate": 3.121760426078273e-06, "loss": 0.6912, "step": 26260 }, { "epoch": 0.1561543354078618, "grad_norm": 9.432194709777832, "learning_rate": 3.1229492605449617e-06, "loss": 0.7091, "step": 26270 }, { "epoch": 0.1562137774845302, "grad_norm": 8.273931503295898, "learning_rate": 3.1241380950116506e-06, "loss": 0.6827, "step": 26280 }, { "epoch": 0.15627321956119858, "grad_norm": 6.010356426239014, "learning_rate": 3.1253269294783395e-06, "loss": 0.7207, "step": 26290 }, { "epoch": 0.156332661637867, "grad_norm": 7.232822895050049, "learning_rate": 3.1265157639450285e-06, "loss": 0.6566, "step": 26300 }, { "epoch": 0.15639210371453538, "grad_norm": 12.825555801391602, "learning_rate": 3.127704598411717e-06, "loss": 0.714, "step": 26310 }, { "epoch": 0.15645154579120377, "grad_norm": 9.669034957885742, "learning_rate": 3.1288934328784063e-06, "loss": 0.7545, "step": 26320 }, { "epoch": 0.15651098786787215, "grad_norm": 9.226587295532227, "learning_rate": 3.1300822673450953e-06, "loss": 0.6586, "step": 26330 }, { "epoch": 0.15657042994454054, "grad_norm": 10.361146926879883, "learning_rate": 3.131271101811784e-06, "loss": 0.7379, "step": 26340 }, { "epoch": 0.15662987202120893, "grad_norm": 9.74270248413086, "learning_rate": 3.132459936278473e-06, "loss": 0.6798, "step": 26350 }, { "epoch": 0.1566893140978773, "grad_norm": 10.79576301574707, "learning_rate": 3.133648770745162e-06, "loss": 0.7235, "step": 26360 }, { "epoch": 0.1567487561745457, "grad_norm": 12.283300399780273, "learning_rate": 3.1348376052118505e-06, "loss": 0.7487, "step": 26370 }, { "epoch": 0.15680819825121411, "grad_norm": 10.18255615234375, "learning_rate": 3.1360264396785395e-06, "loss": 0.7632, "step": 26380 }, { "epoch": 0.1568676403278825, "grad_norm": 7.793044090270996, "learning_rate": 3.1372152741452284e-06, "loss": 0.7108, "step": 26390 }, { "epoch": 0.1569270824045509, "grad_norm": 8.091751098632812, "learning_rate": 3.1384041086119173e-06, "loss": 0.6665, "step": 26400 }, { "epoch": 0.15698652448121928, "grad_norm": 10.70695972442627, "learning_rate": 3.139592943078606e-06, "loss": 0.673, "step": 26410 }, { "epoch": 0.15704596655788766, "grad_norm": 9.637777328491211, "learning_rate": 3.1407817775452947e-06, "loss": 0.7481, "step": 26420 }, { "epoch": 0.15710540863455605, "grad_norm": 9.844574928283691, "learning_rate": 3.1419706120119837e-06, "loss": 0.7039, "step": 26430 }, { "epoch": 0.15716485071122444, "grad_norm": 9.305840492248535, "learning_rate": 3.1431594464786726e-06, "loss": 0.7306, "step": 26440 }, { "epoch": 0.15722429278789285, "grad_norm": 9.761767387390137, "learning_rate": 3.144348280945361e-06, "loss": 0.7247, "step": 26450 }, { "epoch": 0.15728373486456124, "grad_norm": 9.392053604125977, "learning_rate": 3.14553711541205e-06, "loss": 0.7701, "step": 26460 }, { "epoch": 0.15734317694122962, "grad_norm": 8.27408504486084, "learning_rate": 3.146725949878739e-06, "loss": 0.7408, "step": 26470 }, { "epoch": 0.157402619017898, "grad_norm": 8.675843238830566, "learning_rate": 3.147914784345428e-06, "loss": 0.7091, "step": 26480 }, { "epoch": 0.1574620610945664, "grad_norm": 8.861357688903809, "learning_rate": 3.1491036188121172e-06, "loss": 0.7539, "step": 26490 }, { "epoch": 0.15752150317123478, "grad_norm": 9.6594877243042, "learning_rate": 3.1502924532788057e-06, "loss": 0.7072, "step": 26500 }, { "epoch": 0.15758094524790317, "grad_norm": 8.589942932128906, "learning_rate": 3.1514812877454947e-06, "loss": 0.712, "step": 26510 }, { "epoch": 0.15764038732457158, "grad_norm": 9.336694717407227, "learning_rate": 3.1526701222121836e-06, "loss": 0.7337, "step": 26520 }, { "epoch": 0.15769982940123997, "grad_norm": 6.515997409820557, "learning_rate": 3.1538589566788725e-06, "loss": 0.709, "step": 26530 }, { "epoch": 0.15775927147790836, "grad_norm": 10.39264965057373, "learning_rate": 3.1550477911455615e-06, "loss": 0.6772, "step": 26540 }, { "epoch": 0.15781871355457674, "grad_norm": 9.797950744628906, "learning_rate": 3.15623662561225e-06, "loss": 0.7072, "step": 26550 }, { "epoch": 0.15787815563124513, "grad_norm": 9.296330451965332, "learning_rate": 3.157425460078939e-06, "loss": 0.7245, "step": 26560 }, { "epoch": 0.15793759770791352, "grad_norm": 11.929142951965332, "learning_rate": 3.158614294545628e-06, "loss": 0.6929, "step": 26570 }, { "epoch": 0.1579970397845819, "grad_norm": 9.859905242919922, "learning_rate": 3.1598031290123167e-06, "loss": 0.7256, "step": 26580 }, { "epoch": 0.1580564818612503, "grad_norm": 10.43394947052002, "learning_rate": 3.1609919634790052e-06, "loss": 0.6884, "step": 26590 }, { "epoch": 0.1581159239379187, "grad_norm": 11.2462739944458, "learning_rate": 3.162180797945694e-06, "loss": 0.6702, "step": 26600 }, { "epoch": 0.1581753660145871, "grad_norm": 9.76578140258789, "learning_rate": 3.163369632412383e-06, "loss": 0.7444, "step": 26610 }, { "epoch": 0.15823480809125548, "grad_norm": 8.654352188110352, "learning_rate": 3.164558466879072e-06, "loss": 0.6781, "step": 26620 }, { "epoch": 0.15829425016792387, "grad_norm": 9.611918449401855, "learning_rate": 3.1657473013457605e-06, "loss": 0.7118, "step": 26630 }, { "epoch": 0.15835369224459225, "grad_norm": 8.006318092346191, "learning_rate": 3.1669361358124495e-06, "loss": 0.7492, "step": 26640 }, { "epoch": 0.15841313432126064, "grad_norm": 8.576445579528809, "learning_rate": 3.1681249702791384e-06, "loss": 0.747, "step": 26650 }, { "epoch": 0.15847257639792903, "grad_norm": 9.95175552368164, "learning_rate": 3.1693138047458277e-06, "loss": 0.6657, "step": 26660 }, { "epoch": 0.15853201847459744, "grad_norm": 8.482441902160645, "learning_rate": 3.1705026392125167e-06, "loss": 0.6637, "step": 26670 }, { "epoch": 0.15859146055126583, "grad_norm": 7.339302062988281, "learning_rate": 3.1716914736792056e-06, "loss": 0.7359, "step": 26680 }, { "epoch": 0.15865090262793421, "grad_norm": 9.883079528808594, "learning_rate": 3.172880308145894e-06, "loss": 0.724, "step": 26690 }, { "epoch": 0.1587103447046026, "grad_norm": 8.347724914550781, "learning_rate": 3.174069142612583e-06, "loss": 0.7746, "step": 26700 }, { "epoch": 0.158769786781271, "grad_norm": 12.448429107666016, "learning_rate": 3.175257977079272e-06, "loss": 0.7939, "step": 26710 }, { "epoch": 0.15882922885793938, "grad_norm": 8.075862884521484, "learning_rate": 3.176446811545961e-06, "loss": 0.744, "step": 26720 }, { "epoch": 0.15888867093460776, "grad_norm": 9.305415153503418, "learning_rate": 3.1776356460126494e-06, "loss": 0.7461, "step": 26730 }, { "epoch": 0.15894811301127615, "grad_norm": 9.585576057434082, "learning_rate": 3.1788244804793383e-06, "loss": 0.6676, "step": 26740 }, { "epoch": 0.15900755508794456, "grad_norm": 9.799528121948242, "learning_rate": 3.1800133149460272e-06, "loss": 0.7386, "step": 26750 }, { "epoch": 0.15906699716461295, "grad_norm": 9.934209823608398, "learning_rate": 3.181202149412716e-06, "loss": 0.7645, "step": 26760 }, { "epoch": 0.15912643924128134, "grad_norm": 8.550503730773926, "learning_rate": 3.1823909838794047e-06, "loss": 0.7658, "step": 26770 }, { "epoch": 0.15918588131794972, "grad_norm": 9.58188533782959, "learning_rate": 3.1835798183460936e-06, "loss": 0.6793, "step": 26780 }, { "epoch": 0.1592453233946181, "grad_norm": 10.735698699951172, "learning_rate": 3.1847686528127825e-06, "loss": 0.745, "step": 26790 }, { "epoch": 0.1593047654712865, "grad_norm": 10.37348747253418, "learning_rate": 3.1859574872794714e-06, "loss": 0.7571, "step": 26800 }, { "epoch": 0.15936420754795488, "grad_norm": 7.630402088165283, "learning_rate": 3.18714632174616e-06, "loss": 0.6849, "step": 26810 }, { "epoch": 0.1594236496246233, "grad_norm": 8.341531753540039, "learning_rate": 3.188335156212849e-06, "loss": 0.6373, "step": 26820 }, { "epoch": 0.15948309170129168, "grad_norm": 9.504051208496094, "learning_rate": 3.189523990679538e-06, "loss": 0.6953, "step": 26830 }, { "epoch": 0.15954253377796007, "grad_norm": 9.621261596679688, "learning_rate": 3.190712825146227e-06, "loss": 0.684, "step": 26840 }, { "epoch": 0.15960197585462846, "grad_norm": 9.727191925048828, "learning_rate": 3.191901659612916e-06, "loss": 0.7477, "step": 26850 }, { "epoch": 0.15966141793129685, "grad_norm": 9.130806922912598, "learning_rate": 3.193090494079605e-06, "loss": 0.7301, "step": 26860 }, { "epoch": 0.15972086000796523, "grad_norm": 8.863360404968262, "learning_rate": 3.1942793285462935e-06, "loss": 0.6953, "step": 26870 }, { "epoch": 0.15978030208463362, "grad_norm": 8.593162536621094, "learning_rate": 3.1954681630129824e-06, "loss": 0.7668, "step": 26880 }, { "epoch": 0.15983974416130203, "grad_norm": 7.860769748687744, "learning_rate": 3.1966569974796714e-06, "loss": 0.6895, "step": 26890 }, { "epoch": 0.15989918623797042, "grad_norm": 11.32089900970459, "learning_rate": 3.1978458319463603e-06, "loss": 0.7106, "step": 26900 }, { "epoch": 0.1599586283146388, "grad_norm": 9.821538925170898, "learning_rate": 3.199034666413049e-06, "loss": 0.7578, "step": 26910 }, { "epoch": 0.1600180703913072, "grad_norm": 9.806883811950684, "learning_rate": 3.2002235008797377e-06, "loss": 0.7779, "step": 26920 }, { "epoch": 0.16007751246797558, "grad_norm": 8.252294540405273, "learning_rate": 3.2014123353464267e-06, "loss": 0.6841, "step": 26930 }, { "epoch": 0.16013695454464397, "grad_norm": 9.053248405456543, "learning_rate": 3.2026011698131156e-06, "loss": 0.7359, "step": 26940 }, { "epoch": 0.16019639662131235, "grad_norm": 9.905721664428711, "learning_rate": 3.203790004279804e-06, "loss": 0.7262, "step": 26950 }, { "epoch": 0.16025583869798074, "grad_norm": 10.31993579864502, "learning_rate": 3.204978838746493e-06, "loss": 0.7103, "step": 26960 }, { "epoch": 0.16031528077464915, "grad_norm": 9.807029724121094, "learning_rate": 3.206167673213182e-06, "loss": 0.7376, "step": 26970 }, { "epoch": 0.16037472285131754, "grad_norm": 9.108232498168945, "learning_rate": 3.207356507679871e-06, "loss": 0.7296, "step": 26980 }, { "epoch": 0.16043416492798593, "grad_norm": 11.33566665649414, "learning_rate": 3.2085453421465594e-06, "loss": 0.7446, "step": 26990 }, { "epoch": 0.16049360700465432, "grad_norm": 10.621233940124512, "learning_rate": 3.2097341766132483e-06, "loss": 0.6827, "step": 27000 }, { "epoch": 0.1605530490813227, "grad_norm": 11.724295616149902, "learning_rate": 3.2109230110799376e-06, "loss": 0.6601, "step": 27010 }, { "epoch": 0.1606124911579911, "grad_norm": 10.147677421569824, "learning_rate": 3.2121118455466266e-06, "loss": 0.6909, "step": 27020 }, { "epoch": 0.16067193323465948, "grad_norm": 10.014878273010254, "learning_rate": 3.2133006800133155e-06, "loss": 0.7827, "step": 27030 }, { "epoch": 0.1607313753113279, "grad_norm": 8.737689971923828, "learning_rate": 3.2144895144800044e-06, "loss": 0.6599, "step": 27040 }, { "epoch": 0.16079081738799628, "grad_norm": 8.776886940002441, "learning_rate": 3.215678348946693e-06, "loss": 0.708, "step": 27050 }, { "epoch": 0.16085025946466466, "grad_norm": 9.17345142364502, "learning_rate": 3.216867183413382e-06, "loss": 0.6816, "step": 27060 }, { "epoch": 0.16090970154133305, "grad_norm": 9.149334907531738, "learning_rate": 3.218056017880071e-06, "loss": 0.642, "step": 27070 }, { "epoch": 0.16096914361800144, "grad_norm": 10.674690246582031, "learning_rate": 3.2192448523467597e-06, "loss": 0.6679, "step": 27080 }, { "epoch": 0.16102858569466982, "grad_norm": 9.35332202911377, "learning_rate": 3.2204336868134482e-06, "loss": 0.8033, "step": 27090 }, { "epoch": 0.1610880277713382, "grad_norm": 8.220952987670898, "learning_rate": 3.221622521280137e-06, "loss": 0.7147, "step": 27100 }, { "epoch": 0.1611474698480066, "grad_norm": 8.008143424987793, "learning_rate": 3.222811355746826e-06, "loss": 0.6236, "step": 27110 }, { "epoch": 0.161206911924675, "grad_norm": 8.773155212402344, "learning_rate": 3.224000190213515e-06, "loss": 0.7432, "step": 27120 }, { "epoch": 0.1612663540013434, "grad_norm": 10.179142951965332, "learning_rate": 3.2251890246802035e-06, "loss": 0.7616, "step": 27130 }, { "epoch": 0.16132579607801179, "grad_norm": 9.536530494689941, "learning_rate": 3.2263778591468924e-06, "loss": 0.7498, "step": 27140 }, { "epoch": 0.16138523815468017, "grad_norm": 9.155184745788574, "learning_rate": 3.2275666936135814e-06, "loss": 0.7278, "step": 27150 }, { "epoch": 0.16144468023134856, "grad_norm": 6.923765182495117, "learning_rate": 3.2287555280802703e-06, "loss": 0.6941, "step": 27160 }, { "epoch": 0.16150412230801695, "grad_norm": 9.812246322631836, "learning_rate": 3.229944362546959e-06, "loss": 0.7838, "step": 27170 }, { "epoch": 0.16156356438468533, "grad_norm": 9.444005012512207, "learning_rate": 3.2311331970136486e-06, "loss": 0.6961, "step": 27180 }, { "epoch": 0.16162300646135375, "grad_norm": 7.678750038146973, "learning_rate": 3.232322031480337e-06, "loss": 0.6931, "step": 27190 }, { "epoch": 0.16168244853802213, "grad_norm": 9.197786331176758, "learning_rate": 3.233510865947026e-06, "loss": 0.6961, "step": 27200 }, { "epoch": 0.16174189061469052, "grad_norm": 6.836978912353516, "learning_rate": 3.234699700413715e-06, "loss": 0.6777, "step": 27210 }, { "epoch": 0.1618013326913589, "grad_norm": 12.51136302947998, "learning_rate": 3.235888534880404e-06, "loss": 0.7136, "step": 27220 }, { "epoch": 0.1618607747680273, "grad_norm": 9.222277641296387, "learning_rate": 3.2370773693470924e-06, "loss": 0.6859, "step": 27230 }, { "epoch": 0.16192021684469568, "grad_norm": 9.155797958374023, "learning_rate": 3.2382662038137813e-06, "loss": 0.7138, "step": 27240 }, { "epoch": 0.16197965892136407, "grad_norm": 9.342368125915527, "learning_rate": 3.23945503828047e-06, "loss": 0.7199, "step": 27250 }, { "epoch": 0.16203910099803245, "grad_norm": 9.43715763092041, "learning_rate": 3.240643872747159e-06, "loss": 0.698, "step": 27260 }, { "epoch": 0.16209854307470087, "grad_norm": 10.076769828796387, "learning_rate": 3.2418327072138476e-06, "loss": 0.7236, "step": 27270 }, { "epoch": 0.16215798515136925, "grad_norm": 9.5925874710083, "learning_rate": 3.2430215416805366e-06, "loss": 0.6693, "step": 27280 }, { "epoch": 0.16221742722803764, "grad_norm": 8.674625396728516, "learning_rate": 3.2442103761472255e-06, "loss": 0.7417, "step": 27290 }, { "epoch": 0.16227686930470603, "grad_norm": 10.070259094238281, "learning_rate": 3.2453992106139144e-06, "loss": 0.705, "step": 27300 }, { "epoch": 0.16233631138137442, "grad_norm": 6.572895526885986, "learning_rate": 3.246588045080603e-06, "loss": 0.6905, "step": 27310 }, { "epoch": 0.1623957534580428, "grad_norm": 8.07747745513916, "learning_rate": 3.247776879547292e-06, "loss": 0.6906, "step": 27320 }, { "epoch": 0.1624551955347112, "grad_norm": 7.656247138977051, "learning_rate": 3.2489657140139808e-06, "loss": 0.6947, "step": 27330 }, { "epoch": 0.1625146376113796, "grad_norm": 8.327131271362305, "learning_rate": 3.2501545484806697e-06, "loss": 0.6696, "step": 27340 }, { "epoch": 0.162574079688048, "grad_norm": 9.853309631347656, "learning_rate": 3.251343382947358e-06, "loss": 0.7011, "step": 27350 }, { "epoch": 0.16263352176471638, "grad_norm": 9.16588020324707, "learning_rate": 3.252532217414048e-06, "loss": 0.7217, "step": 27360 }, { "epoch": 0.16269296384138476, "grad_norm": 10.65250015258789, "learning_rate": 3.2537210518807365e-06, "loss": 0.6413, "step": 27370 }, { "epoch": 0.16275240591805315, "grad_norm": 11.516823768615723, "learning_rate": 3.2549098863474254e-06, "loss": 0.6721, "step": 27380 }, { "epoch": 0.16281184799472154, "grad_norm": 8.74474048614502, "learning_rate": 3.2560987208141143e-06, "loss": 0.7181, "step": 27390 }, { "epoch": 0.16287129007138992, "grad_norm": 9.234025001525879, "learning_rate": 3.2572875552808033e-06, "loss": 0.6681, "step": 27400 }, { "epoch": 0.16293073214805834, "grad_norm": 9.246695518493652, "learning_rate": 3.2584763897474918e-06, "loss": 0.7346, "step": 27410 }, { "epoch": 0.16299017422472672, "grad_norm": 10.234726905822754, "learning_rate": 3.2596652242141807e-06, "loss": 0.696, "step": 27420 }, { "epoch": 0.1630496163013951, "grad_norm": 7.4114460945129395, "learning_rate": 3.2608540586808696e-06, "loss": 0.658, "step": 27430 }, { "epoch": 0.1631090583780635, "grad_norm": 9.950390815734863, "learning_rate": 3.2620428931475586e-06, "loss": 0.6918, "step": 27440 }, { "epoch": 0.16316850045473189, "grad_norm": 8.616393089294434, "learning_rate": 3.263231727614247e-06, "loss": 0.6594, "step": 27450 }, { "epoch": 0.16322794253140027, "grad_norm": 9.396389961242676, "learning_rate": 3.264420562080936e-06, "loss": 0.698, "step": 27460 }, { "epoch": 0.16328738460806866, "grad_norm": 9.888656616210938, "learning_rate": 3.265609396547625e-06, "loss": 0.6998, "step": 27470 }, { "epoch": 0.16334682668473705, "grad_norm": 9.522858619689941, "learning_rate": 3.266798231014314e-06, "loss": 0.7458, "step": 27480 }, { "epoch": 0.16340626876140546, "grad_norm": 10.590563774108887, "learning_rate": 3.2679870654810023e-06, "loss": 0.7627, "step": 27490 }, { "epoch": 0.16346571083807385, "grad_norm": 12.309420585632324, "learning_rate": 3.2691758999476913e-06, "loss": 0.7065, "step": 27500 }, { "epoch": 0.16352515291474223, "grad_norm": 8.715645790100098, "learning_rate": 3.27036473441438e-06, "loss": 0.6942, "step": 27510 }, { "epoch": 0.16358459499141062, "grad_norm": 8.753116607666016, "learning_rate": 3.271553568881069e-06, "loss": 0.6504, "step": 27520 }, { "epoch": 0.163644037068079, "grad_norm": 9.41297721862793, "learning_rate": 3.2727424033477585e-06, "loss": 0.7066, "step": 27530 }, { "epoch": 0.1637034791447474, "grad_norm": 9.79826545715332, "learning_rate": 3.2739312378144474e-06, "loss": 0.718, "step": 27540 }, { "epoch": 0.16376292122141578, "grad_norm": 10.082728385925293, "learning_rate": 3.275120072281136e-06, "loss": 0.7119, "step": 27550 }, { "epoch": 0.1638223632980842, "grad_norm": 9.256651878356934, "learning_rate": 3.276308906747825e-06, "loss": 0.7313, "step": 27560 }, { "epoch": 0.16388180537475258, "grad_norm": 9.222844123840332, "learning_rate": 3.2774977412145138e-06, "loss": 0.7203, "step": 27570 }, { "epoch": 0.16394124745142097, "grad_norm": 8.601070404052734, "learning_rate": 3.2786865756812027e-06, "loss": 0.742, "step": 27580 }, { "epoch": 0.16400068952808936, "grad_norm": 8.2283296585083, "learning_rate": 3.279875410147891e-06, "loss": 0.6983, "step": 27590 }, { "epoch": 0.16406013160475774, "grad_norm": 8.568656921386719, "learning_rate": 3.28106424461458e-06, "loss": 0.7326, "step": 27600 }, { "epoch": 0.16411957368142613, "grad_norm": 9.166116714477539, "learning_rate": 3.282253079081269e-06, "loss": 0.7079, "step": 27610 }, { "epoch": 0.16417901575809452, "grad_norm": 8.719990730285645, "learning_rate": 3.283441913547958e-06, "loss": 0.6776, "step": 27620 }, { "epoch": 0.1642384578347629, "grad_norm": 9.428205490112305, "learning_rate": 3.2846307480146465e-06, "loss": 0.7414, "step": 27630 }, { "epoch": 0.16429789991143132, "grad_norm": 8.649264335632324, "learning_rate": 3.2858195824813354e-06, "loss": 0.6524, "step": 27640 }, { "epoch": 0.1643573419880997, "grad_norm": 8.804245948791504, "learning_rate": 3.2870084169480243e-06, "loss": 0.6896, "step": 27650 }, { "epoch": 0.1644167840647681, "grad_norm": 12.447866439819336, "learning_rate": 3.2881972514147133e-06, "loss": 0.6813, "step": 27660 }, { "epoch": 0.16447622614143648, "grad_norm": 8.586045265197754, "learning_rate": 3.2893860858814018e-06, "loss": 0.7185, "step": 27670 }, { "epoch": 0.16453566821810486, "grad_norm": 8.642236709594727, "learning_rate": 3.2905749203480907e-06, "loss": 0.6608, "step": 27680 }, { "epoch": 0.16459511029477325, "grad_norm": 7.107551574707031, "learning_rate": 3.2917637548147796e-06, "loss": 0.7025, "step": 27690 }, { "epoch": 0.16465455237144164, "grad_norm": 7.500444412231445, "learning_rate": 3.292952589281469e-06, "loss": 0.733, "step": 27700 }, { "epoch": 0.16471399444811005, "grad_norm": 7.654803276062012, "learning_rate": 3.294141423748158e-06, "loss": 0.7399, "step": 27710 }, { "epoch": 0.16477343652477844, "grad_norm": 10.09238052368164, "learning_rate": 3.295330258214847e-06, "loss": 0.6603, "step": 27720 }, { "epoch": 0.16483287860144683, "grad_norm": 8.92031192779541, "learning_rate": 3.2965190926815353e-06, "loss": 0.7198, "step": 27730 }, { "epoch": 0.1648923206781152, "grad_norm": 9.257851600646973, "learning_rate": 3.2977079271482243e-06, "loss": 0.7152, "step": 27740 }, { "epoch": 0.1649517627547836, "grad_norm": 7.860546112060547, "learning_rate": 3.298896761614913e-06, "loss": 0.7026, "step": 27750 }, { "epoch": 0.16501120483145199, "grad_norm": 8.179781913757324, "learning_rate": 3.300085596081602e-06, "loss": 0.7644, "step": 27760 }, { "epoch": 0.16507064690812037, "grad_norm": 7.814944744110107, "learning_rate": 3.3012744305482906e-06, "loss": 0.6932, "step": 27770 }, { "epoch": 0.16513008898478876, "grad_norm": 10.131731033325195, "learning_rate": 3.3024632650149795e-06, "loss": 0.7083, "step": 27780 }, { "epoch": 0.16518953106145717, "grad_norm": 8.983440399169922, "learning_rate": 3.3036520994816685e-06, "loss": 0.6971, "step": 27790 }, { "epoch": 0.16524897313812556, "grad_norm": 8.611309051513672, "learning_rate": 3.3048409339483574e-06, "loss": 0.7659, "step": 27800 }, { "epoch": 0.16530841521479395, "grad_norm": 9.055342674255371, "learning_rate": 3.306029768415046e-06, "loss": 0.6959, "step": 27810 }, { "epoch": 0.16536785729146233, "grad_norm": 8.892983436584473, "learning_rate": 3.307218602881735e-06, "loss": 0.6794, "step": 27820 }, { "epoch": 0.16542729936813072, "grad_norm": 8.767232894897461, "learning_rate": 3.3084074373484238e-06, "loss": 0.7708, "step": 27830 }, { "epoch": 0.1654867414447991, "grad_norm": 10.60757064819336, "learning_rate": 3.3095962718151127e-06, "loss": 0.7083, "step": 27840 }, { "epoch": 0.1655461835214675, "grad_norm": 7.6198954582214355, "learning_rate": 3.310785106281801e-06, "loss": 0.6821, "step": 27850 }, { "epoch": 0.1656056255981359, "grad_norm": 10.071544647216797, "learning_rate": 3.31197394074849e-06, "loss": 0.7247, "step": 27860 }, { "epoch": 0.1656650676748043, "grad_norm": 8.827105522155762, "learning_rate": 3.313162775215179e-06, "loss": 0.7101, "step": 27870 }, { "epoch": 0.16572450975147268, "grad_norm": 10.823250770568848, "learning_rate": 3.3143516096818684e-06, "loss": 0.675, "step": 27880 }, { "epoch": 0.16578395182814107, "grad_norm": 9.757280349731445, "learning_rate": 3.3155404441485573e-06, "loss": 0.7188, "step": 27890 }, { "epoch": 0.16584339390480946, "grad_norm": 9.358123779296875, "learning_rate": 3.3167292786152462e-06, "loss": 0.7053, "step": 27900 }, { "epoch": 0.16590283598147784, "grad_norm": 8.183635711669922, "learning_rate": 3.3179181130819348e-06, "loss": 0.7486, "step": 27910 }, { "epoch": 0.16596227805814623, "grad_norm": 8.085572242736816, "learning_rate": 3.3191069475486237e-06, "loss": 0.7317, "step": 27920 }, { "epoch": 0.16602172013481464, "grad_norm": 8.480318069458008, "learning_rate": 3.3202957820153126e-06, "loss": 0.745, "step": 27930 }, { "epoch": 0.16608116221148303, "grad_norm": 9.256963729858398, "learning_rate": 3.3214846164820015e-06, "loss": 0.7366, "step": 27940 }, { "epoch": 0.16614060428815142, "grad_norm": 8.502470016479492, "learning_rate": 3.32267345094869e-06, "loss": 0.701, "step": 27950 }, { "epoch": 0.1662000463648198, "grad_norm": 6.825347900390625, "learning_rate": 3.323862285415379e-06, "loss": 0.7279, "step": 27960 }, { "epoch": 0.1662594884414882, "grad_norm": 11.303874969482422, "learning_rate": 3.325051119882068e-06, "loss": 0.7259, "step": 27970 }, { "epoch": 0.16631893051815658, "grad_norm": 7.45141077041626, "learning_rate": 3.326239954348757e-06, "loss": 0.6933, "step": 27980 }, { "epoch": 0.16637837259482496, "grad_norm": 9.616247177124023, "learning_rate": 3.3274287888154453e-06, "loss": 0.7343, "step": 27990 }, { "epoch": 0.16643781467149335, "grad_norm": 9.493148803710938, "learning_rate": 3.3286176232821343e-06, "loss": 0.7247, "step": 28000 }, { "epoch": 0.16649725674816176, "grad_norm": 10.685537338256836, "learning_rate": 3.329806457748823e-06, "loss": 0.7705, "step": 28010 }, { "epoch": 0.16655669882483015, "grad_norm": 10.800296783447266, "learning_rate": 3.330995292215512e-06, "loss": 0.6949, "step": 28020 }, { "epoch": 0.16661614090149854, "grad_norm": 9.17570686340332, "learning_rate": 3.3321841266822006e-06, "loss": 0.7491, "step": 28030 }, { "epoch": 0.16667558297816693, "grad_norm": 8.714815139770508, "learning_rate": 3.3333729611488895e-06, "loss": 0.6564, "step": 28040 }, { "epoch": 0.1667350250548353, "grad_norm": 10.008444786071777, "learning_rate": 3.334561795615579e-06, "loss": 0.6966, "step": 28050 }, { "epoch": 0.1667944671315037, "grad_norm": 10.060961723327637, "learning_rate": 3.335750630082268e-06, "loss": 0.7508, "step": 28060 }, { "epoch": 0.16685390920817209, "grad_norm": 8.054535865783691, "learning_rate": 3.3369394645489567e-06, "loss": 0.6782, "step": 28070 }, { "epoch": 0.1669133512848405, "grad_norm": 10.483177185058594, "learning_rate": 3.3381282990156457e-06, "loss": 0.7295, "step": 28080 }, { "epoch": 0.1669727933615089, "grad_norm": 10.506697654724121, "learning_rate": 3.339317133482334e-06, "loss": 0.7303, "step": 28090 }, { "epoch": 0.16703223543817727, "grad_norm": 11.306036949157715, "learning_rate": 3.340505967949023e-06, "loss": 0.7592, "step": 28100 }, { "epoch": 0.16709167751484566, "grad_norm": 8.606900215148926, "learning_rate": 3.341694802415712e-06, "loss": 0.7467, "step": 28110 }, { "epoch": 0.16715111959151405, "grad_norm": 8.607148170471191, "learning_rate": 3.342883636882401e-06, "loss": 0.6466, "step": 28120 }, { "epoch": 0.16721056166818243, "grad_norm": 8.50674057006836, "learning_rate": 3.3440724713490895e-06, "loss": 0.6642, "step": 28130 }, { "epoch": 0.16727000374485082, "grad_norm": 10.417282104492188, "learning_rate": 3.3452613058157784e-06, "loss": 0.7254, "step": 28140 }, { "epoch": 0.1673294458215192, "grad_norm": 9.092251777648926, "learning_rate": 3.3464501402824673e-06, "loss": 0.7291, "step": 28150 }, { "epoch": 0.16738888789818762, "grad_norm": 8.342838287353516, "learning_rate": 3.3476389747491562e-06, "loss": 0.805, "step": 28160 }, { "epoch": 0.167448329974856, "grad_norm": 9.198461532592773, "learning_rate": 3.3488278092158447e-06, "loss": 0.6861, "step": 28170 }, { "epoch": 0.1675077720515244, "grad_norm": 8.7530517578125, "learning_rate": 3.3500166436825337e-06, "loss": 0.7267, "step": 28180 }, { "epoch": 0.16756721412819278, "grad_norm": 10.002630233764648, "learning_rate": 3.3512054781492226e-06, "loss": 0.6473, "step": 28190 }, { "epoch": 0.16762665620486117, "grad_norm": 8.530363082885742, "learning_rate": 3.3523943126159115e-06, "loss": 0.7295, "step": 28200 }, { "epoch": 0.16768609828152956, "grad_norm": 9.785852432250977, "learning_rate": 3.3535831470826005e-06, "loss": 0.686, "step": 28210 }, { "epoch": 0.16774554035819794, "grad_norm": 10.377068519592285, "learning_rate": 3.35477198154929e-06, "loss": 0.7444, "step": 28220 }, { "epoch": 0.16780498243486636, "grad_norm": 6.114272117614746, "learning_rate": 3.3559608160159783e-06, "loss": 0.7271, "step": 28230 }, { "epoch": 0.16786442451153474, "grad_norm": 8.765732765197754, "learning_rate": 3.3571496504826672e-06, "loss": 0.6829, "step": 28240 }, { "epoch": 0.16792386658820313, "grad_norm": 8.870412826538086, "learning_rate": 3.358338484949356e-06, "loss": 0.7289, "step": 28250 }, { "epoch": 0.16798330866487152, "grad_norm": 8.838706016540527, "learning_rate": 3.359527319416045e-06, "loss": 0.7175, "step": 28260 }, { "epoch": 0.1680427507415399, "grad_norm": 9.319062232971191, "learning_rate": 3.3607161538827336e-06, "loss": 0.7034, "step": 28270 }, { "epoch": 0.1681021928182083, "grad_norm": 8.780986785888672, "learning_rate": 3.3619049883494225e-06, "loss": 0.7482, "step": 28280 }, { "epoch": 0.16816163489487668, "grad_norm": 7.5596232414245605, "learning_rate": 3.3630938228161114e-06, "loss": 0.714, "step": 28290 }, { "epoch": 0.1682210769715451, "grad_norm": 8.106339454650879, "learning_rate": 3.3642826572828004e-06, "loss": 0.6522, "step": 28300 }, { "epoch": 0.16828051904821348, "grad_norm": 8.636446952819824, "learning_rate": 3.365471491749489e-06, "loss": 0.7187, "step": 28310 }, { "epoch": 0.16833996112488187, "grad_norm": 9.95171070098877, "learning_rate": 3.366660326216178e-06, "loss": 0.7299, "step": 28320 }, { "epoch": 0.16839940320155025, "grad_norm": 10.56766414642334, "learning_rate": 3.3678491606828667e-06, "loss": 0.7303, "step": 28330 }, { "epoch": 0.16845884527821864, "grad_norm": 10.97714900970459, "learning_rate": 3.3690379951495557e-06, "loss": 0.7318, "step": 28340 }, { "epoch": 0.16851828735488703, "grad_norm": 7.9115214347839355, "learning_rate": 3.370226829616244e-06, "loss": 0.7078, "step": 28350 }, { "epoch": 0.1685777294315554, "grad_norm": 9.030988693237305, "learning_rate": 3.371415664082933e-06, "loss": 0.6828, "step": 28360 }, { "epoch": 0.1686371715082238, "grad_norm": 8.823648452758789, "learning_rate": 3.372604498549622e-06, "loss": 0.7331, "step": 28370 }, { "epoch": 0.1686966135848922, "grad_norm": 8.91190242767334, "learning_rate": 3.373793333016311e-06, "loss": 0.68, "step": 28380 }, { "epoch": 0.1687560556615606, "grad_norm": 11.940520286560059, "learning_rate": 3.374982167483e-06, "loss": 0.7492, "step": 28390 }, { "epoch": 0.168815497738229, "grad_norm": 9.52828598022461, "learning_rate": 3.3761710019496892e-06, "loss": 0.7253, "step": 28400 }, { "epoch": 0.16887493981489737, "grad_norm": 11.187126159667969, "learning_rate": 3.3773598364163777e-06, "loss": 0.6821, "step": 28410 }, { "epoch": 0.16893438189156576, "grad_norm": 8.106844902038574, "learning_rate": 3.3785486708830667e-06, "loss": 0.7101, "step": 28420 }, { "epoch": 0.16899382396823415, "grad_norm": 9.037158966064453, "learning_rate": 3.3797375053497556e-06, "loss": 0.666, "step": 28430 }, { "epoch": 0.16905326604490253, "grad_norm": 10.689309120178223, "learning_rate": 3.3809263398164445e-06, "loss": 0.7056, "step": 28440 }, { "epoch": 0.16911270812157095, "grad_norm": 9.747882843017578, "learning_rate": 3.382115174283133e-06, "loss": 0.7001, "step": 28450 }, { "epoch": 0.16917215019823933, "grad_norm": 8.498967170715332, "learning_rate": 3.383304008749822e-06, "loss": 0.7199, "step": 28460 }, { "epoch": 0.16923159227490772, "grad_norm": 9.316843032836914, "learning_rate": 3.384492843216511e-06, "loss": 0.6387, "step": 28470 }, { "epoch": 0.1692910343515761, "grad_norm": 11.639638900756836, "learning_rate": 3.3856816776832e-06, "loss": 0.6804, "step": 28480 }, { "epoch": 0.1693504764282445, "grad_norm": 9.322297096252441, "learning_rate": 3.3868705121498883e-06, "loss": 0.7457, "step": 28490 }, { "epoch": 0.16940991850491288, "grad_norm": 7.843297958374023, "learning_rate": 3.3880593466165772e-06, "loss": 0.7308, "step": 28500 }, { "epoch": 0.16946936058158127, "grad_norm": 7.9648542404174805, "learning_rate": 3.389248181083266e-06, "loss": 0.6643, "step": 28510 }, { "epoch": 0.16952880265824966, "grad_norm": 8.310012817382812, "learning_rate": 3.390437015549955e-06, "loss": 0.7497, "step": 28520 }, { "epoch": 0.16958824473491807, "grad_norm": 7.687912464141846, "learning_rate": 3.3916258500166436e-06, "loss": 0.7195, "step": 28530 }, { "epoch": 0.16964768681158646, "grad_norm": 8.625088691711426, "learning_rate": 3.3928146844833325e-06, "loss": 0.6763, "step": 28540 }, { "epoch": 0.16970712888825484, "grad_norm": 10.160578727722168, "learning_rate": 3.3940035189500214e-06, "loss": 0.7239, "step": 28550 }, { "epoch": 0.16976657096492323, "grad_norm": 9.383078575134277, "learning_rate": 3.3951923534167104e-06, "loss": 0.7581, "step": 28560 }, { "epoch": 0.16982601304159162, "grad_norm": 8.924152374267578, "learning_rate": 3.3963811878833997e-06, "loss": 0.6781, "step": 28570 }, { "epoch": 0.16988545511826, "grad_norm": 8.436341285705566, "learning_rate": 3.3975700223500886e-06, "loss": 0.7387, "step": 28580 }, { "epoch": 0.1699448971949284, "grad_norm": 9.341809272766113, "learning_rate": 3.398758856816777e-06, "loss": 0.7744, "step": 28590 }, { "epoch": 0.1700043392715968, "grad_norm": 7.867818832397461, "learning_rate": 3.399947691283466e-06, "loss": 0.7355, "step": 28600 }, { "epoch": 0.1700637813482652, "grad_norm": 10.776137351989746, "learning_rate": 3.401136525750155e-06, "loss": 0.6747, "step": 28610 }, { "epoch": 0.17012322342493358, "grad_norm": 8.581509590148926, "learning_rate": 3.402325360216844e-06, "loss": 0.6927, "step": 28620 }, { "epoch": 0.17018266550160197, "grad_norm": 10.878119468688965, "learning_rate": 3.4035141946835324e-06, "loss": 0.717, "step": 28630 }, { "epoch": 0.17024210757827035, "grad_norm": 7.864473819732666, "learning_rate": 3.4047030291502214e-06, "loss": 0.7454, "step": 28640 }, { "epoch": 0.17030154965493874, "grad_norm": 9.979877471923828, "learning_rate": 3.4058918636169103e-06, "loss": 0.7502, "step": 28650 }, { "epoch": 0.17036099173160713, "grad_norm": 12.661704063415527, "learning_rate": 3.4070806980835992e-06, "loss": 0.6853, "step": 28660 }, { "epoch": 0.1704204338082755, "grad_norm": 12.085550308227539, "learning_rate": 3.4082695325502877e-06, "loss": 0.7141, "step": 28670 }, { "epoch": 0.17047987588494393, "grad_norm": 7.6716437339782715, "learning_rate": 3.4094583670169766e-06, "loss": 0.7149, "step": 28680 }, { "epoch": 0.1705393179616123, "grad_norm": 8.353519439697266, "learning_rate": 3.4106472014836656e-06, "loss": 0.6883, "step": 28690 }, { "epoch": 0.1705987600382807, "grad_norm": 9.021119117736816, "learning_rate": 3.4118360359503545e-06, "loss": 0.6487, "step": 28700 }, { "epoch": 0.1706582021149491, "grad_norm": 7.377063751220703, "learning_rate": 3.4130248704170434e-06, "loss": 0.7135, "step": 28710 }, { "epoch": 0.17071764419161747, "grad_norm": 7.50419807434082, "learning_rate": 3.414213704883732e-06, "loss": 0.7055, "step": 28720 }, { "epoch": 0.17077708626828586, "grad_norm": 8.569140434265137, "learning_rate": 3.415402539350421e-06, "loss": 0.6831, "step": 28730 }, { "epoch": 0.17083652834495425, "grad_norm": 8.888151168823242, "learning_rate": 3.4165913738171102e-06, "loss": 0.6675, "step": 28740 }, { "epoch": 0.17089597042162266, "grad_norm": 9.884064674377441, "learning_rate": 3.417780208283799e-06, "loss": 0.7366, "step": 28750 }, { "epoch": 0.17095541249829105, "grad_norm": 8.642253875732422, "learning_rate": 3.418969042750488e-06, "loss": 0.7027, "step": 28760 }, { "epoch": 0.17101485457495944, "grad_norm": 9.508228302001953, "learning_rate": 3.4201578772171766e-06, "loss": 0.7037, "step": 28770 }, { "epoch": 0.17107429665162782, "grad_norm": 7.210699558258057, "learning_rate": 3.4213467116838655e-06, "loss": 0.7139, "step": 28780 }, { "epoch": 0.1711337387282962, "grad_norm": 8.811923027038574, "learning_rate": 3.4225355461505544e-06, "loss": 0.7734, "step": 28790 }, { "epoch": 0.1711931808049646, "grad_norm": 9.538995742797852, "learning_rate": 3.4237243806172434e-06, "loss": 0.7496, "step": 28800 }, { "epoch": 0.17125262288163298, "grad_norm": 9.920306205749512, "learning_rate": 3.424913215083932e-06, "loss": 0.7898, "step": 28810 }, { "epoch": 0.1713120649583014, "grad_norm": 9.030513763427734, "learning_rate": 3.4261020495506208e-06, "loss": 0.7054, "step": 28820 }, { "epoch": 0.17137150703496978, "grad_norm": 10.208345413208008, "learning_rate": 3.4272908840173097e-06, "loss": 0.7172, "step": 28830 }, { "epoch": 0.17143094911163817, "grad_norm": 7.870054721832275, "learning_rate": 3.4284797184839986e-06, "loss": 0.6812, "step": 28840 }, { "epoch": 0.17149039118830656, "grad_norm": 7.763667583465576, "learning_rate": 3.429668552950687e-06, "loss": 0.7029, "step": 28850 }, { "epoch": 0.17154983326497494, "grad_norm": 8.805774688720703, "learning_rate": 3.430857387417376e-06, "loss": 0.7398, "step": 28860 }, { "epoch": 0.17160927534164333, "grad_norm": 6.454999923706055, "learning_rate": 3.432046221884065e-06, "loss": 0.6518, "step": 28870 }, { "epoch": 0.17166871741831172, "grad_norm": 11.078325271606445, "learning_rate": 3.433235056350754e-06, "loss": 0.7086, "step": 28880 }, { "epoch": 0.1717281594949801, "grad_norm": 12.146306991577148, "learning_rate": 3.434423890817443e-06, "loss": 0.7475, "step": 28890 }, { "epoch": 0.17178760157164852, "grad_norm": 10.140192985534668, "learning_rate": 3.4356127252841314e-06, "loss": 0.7294, "step": 28900 }, { "epoch": 0.1718470436483169, "grad_norm": 9.135143280029297, "learning_rate": 3.4368015597508203e-06, "loss": 0.7668, "step": 28910 }, { "epoch": 0.1719064857249853, "grad_norm": 8.945372581481934, "learning_rate": 3.4379903942175096e-06, "loss": 0.7418, "step": 28920 }, { "epoch": 0.17196592780165368, "grad_norm": 9.723566055297852, "learning_rate": 3.4391792286841986e-06, "loss": 0.7684, "step": 28930 }, { "epoch": 0.17202536987832207, "grad_norm": 10.315414428710938, "learning_rate": 3.4403680631508875e-06, "loss": 0.7223, "step": 28940 }, { "epoch": 0.17208481195499045, "grad_norm": 9.029688835144043, "learning_rate": 3.441556897617576e-06, "loss": 0.7222, "step": 28950 }, { "epoch": 0.17214425403165884, "grad_norm": 8.471604347229004, "learning_rate": 3.442745732084265e-06, "loss": 0.7406, "step": 28960 }, { "epoch": 0.17220369610832725, "grad_norm": 9.924521446228027, "learning_rate": 3.443934566550954e-06, "loss": 0.7322, "step": 28970 }, { "epoch": 0.17226313818499564, "grad_norm": 8.387199401855469, "learning_rate": 3.4451234010176428e-06, "loss": 0.7603, "step": 28980 }, { "epoch": 0.17232258026166403, "grad_norm": 8.584385871887207, "learning_rate": 3.4463122354843313e-06, "loss": 0.7169, "step": 28990 }, { "epoch": 0.1723820223383324, "grad_norm": 9.800795555114746, "learning_rate": 3.44750106995102e-06, "loss": 0.6606, "step": 29000 }, { "epoch": 0.1724414644150008, "grad_norm": 10.15680980682373, "learning_rate": 3.448689904417709e-06, "loss": 0.7148, "step": 29010 }, { "epoch": 0.1725009064916692, "grad_norm": 12.707498550415039, "learning_rate": 3.449878738884398e-06, "loss": 0.6991, "step": 29020 }, { "epoch": 0.17256034856833757, "grad_norm": 8.526809692382812, "learning_rate": 3.451067573351087e-06, "loss": 0.6814, "step": 29030 }, { "epoch": 0.17261979064500596, "grad_norm": 9.93822956085205, "learning_rate": 3.4522564078177755e-06, "loss": 0.6883, "step": 29040 }, { "epoch": 0.17267923272167437, "grad_norm": 10.196455955505371, "learning_rate": 3.4534452422844644e-06, "loss": 0.6572, "step": 29050 }, { "epoch": 0.17273867479834276, "grad_norm": 10.523706436157227, "learning_rate": 3.4546340767511533e-06, "loss": 0.6898, "step": 29060 }, { "epoch": 0.17279811687501115, "grad_norm": 9.047889709472656, "learning_rate": 3.4558229112178423e-06, "loss": 0.7056, "step": 29070 }, { "epoch": 0.17285755895167954, "grad_norm": 8.969104766845703, "learning_rate": 3.4570117456845308e-06, "loss": 0.7482, "step": 29080 }, { "epoch": 0.17291700102834792, "grad_norm": 8.232423782348633, "learning_rate": 3.45820058015122e-06, "loss": 0.7404, "step": 29090 }, { "epoch": 0.1729764431050163, "grad_norm": 9.330423355102539, "learning_rate": 3.459389414617909e-06, "loss": 0.6829, "step": 29100 }, { "epoch": 0.1730358851816847, "grad_norm": 10.534520149230957, "learning_rate": 3.460578249084598e-06, "loss": 0.7205, "step": 29110 }, { "epoch": 0.1730953272583531, "grad_norm": 9.598567008972168, "learning_rate": 3.461767083551287e-06, "loss": 0.6854, "step": 29120 }, { "epoch": 0.1731547693350215, "grad_norm": 10.101316452026367, "learning_rate": 3.4629559180179754e-06, "loss": 0.7337, "step": 29130 }, { "epoch": 0.17321421141168988, "grad_norm": 7.905444622039795, "learning_rate": 3.4641447524846643e-06, "loss": 0.6828, "step": 29140 }, { "epoch": 0.17327365348835827, "grad_norm": 10.03570556640625, "learning_rate": 3.4653335869513533e-06, "loss": 0.6994, "step": 29150 }, { "epoch": 0.17333309556502666, "grad_norm": 9.598610877990723, "learning_rate": 3.466522421418042e-06, "loss": 0.6641, "step": 29160 }, { "epoch": 0.17339253764169504, "grad_norm": 10.47921085357666, "learning_rate": 3.4677112558847307e-06, "loss": 0.7113, "step": 29170 }, { "epoch": 0.17345197971836343, "grad_norm": 9.507686614990234, "learning_rate": 3.4689000903514196e-06, "loss": 0.7536, "step": 29180 }, { "epoch": 0.17351142179503184, "grad_norm": 9.463943481445312, "learning_rate": 3.4700889248181086e-06, "loss": 0.7182, "step": 29190 }, { "epoch": 0.17357086387170023, "grad_norm": 10.714239120483398, "learning_rate": 3.4712777592847975e-06, "loss": 0.6536, "step": 29200 }, { "epoch": 0.17363030594836862, "grad_norm": 8.768777847290039, "learning_rate": 3.4724665937514864e-06, "loss": 0.668, "step": 29210 }, { "epoch": 0.173689748025037, "grad_norm": 7.998528957366943, "learning_rate": 3.473655428218175e-06, "loss": 0.731, "step": 29220 }, { "epoch": 0.1737491901017054, "grad_norm": 9.333454132080078, "learning_rate": 3.474844262684864e-06, "loss": 0.6897, "step": 29230 }, { "epoch": 0.17380863217837378, "grad_norm": 11.412233352661133, "learning_rate": 3.4760330971515528e-06, "loss": 0.7197, "step": 29240 }, { "epoch": 0.17386807425504217, "grad_norm": 10.740804672241211, "learning_rate": 3.4772219316182417e-06, "loss": 0.6775, "step": 29250 }, { "epoch": 0.17392751633171055, "grad_norm": 9.001885414123535, "learning_rate": 3.478410766084931e-06, "loss": 0.7083, "step": 29260 }, { "epoch": 0.17398695840837897, "grad_norm": 9.503750801086426, "learning_rate": 3.4795996005516195e-06, "loss": 0.7179, "step": 29270 }, { "epoch": 0.17404640048504735, "grad_norm": 10.86433219909668, "learning_rate": 3.4807884350183085e-06, "loss": 0.7514, "step": 29280 }, { "epoch": 0.17410584256171574, "grad_norm": 8.358433723449707, "learning_rate": 3.4819772694849974e-06, "loss": 0.6792, "step": 29290 }, { "epoch": 0.17416528463838413, "grad_norm": 9.201623916625977, "learning_rate": 3.4831661039516863e-06, "loss": 0.721, "step": 29300 }, { "epoch": 0.1742247267150525, "grad_norm": 10.698673248291016, "learning_rate": 3.484354938418375e-06, "loss": 0.7098, "step": 29310 }, { "epoch": 0.1742841687917209, "grad_norm": 8.886138916015625, "learning_rate": 3.4855437728850638e-06, "loss": 0.7398, "step": 29320 }, { "epoch": 0.1743436108683893, "grad_norm": 12.098613739013672, "learning_rate": 3.4867326073517527e-06, "loss": 0.6939, "step": 29330 }, { "epoch": 0.1744030529450577, "grad_norm": 6.190783500671387, "learning_rate": 3.4879214418184416e-06, "loss": 0.6854, "step": 29340 }, { "epoch": 0.1744624950217261, "grad_norm": 9.265913963317871, "learning_rate": 3.48911027628513e-06, "loss": 0.6662, "step": 29350 }, { "epoch": 0.17452193709839448, "grad_norm": 10.857768058776855, "learning_rate": 3.490299110751819e-06, "loss": 0.7644, "step": 29360 }, { "epoch": 0.17458137917506286, "grad_norm": 9.096368789672852, "learning_rate": 3.491487945218508e-06, "loss": 0.6691, "step": 29370 }, { "epoch": 0.17464082125173125, "grad_norm": 8.115445137023926, "learning_rate": 3.492676779685197e-06, "loss": 0.7164, "step": 29380 }, { "epoch": 0.17470026332839964, "grad_norm": 8.644791603088379, "learning_rate": 3.493865614151886e-06, "loss": 0.6646, "step": 29390 }, { "epoch": 0.17475970540506802, "grad_norm": 9.185521125793457, "learning_rate": 3.4950544486185743e-06, "loss": 0.6874, "step": 29400 }, { "epoch": 0.1748191474817364, "grad_norm": 8.688775062561035, "learning_rate": 3.4962432830852633e-06, "loss": 0.6863, "step": 29410 }, { "epoch": 0.17487858955840482, "grad_norm": 6.925126552581787, "learning_rate": 3.497432117551952e-06, "loss": 0.6981, "step": 29420 }, { "epoch": 0.1749380316350732, "grad_norm": 7.811250686645508, "learning_rate": 3.498620952018641e-06, "loss": 0.7152, "step": 29430 }, { "epoch": 0.1749974737117416, "grad_norm": 12.74270248413086, "learning_rate": 3.4998097864853305e-06, "loss": 0.6967, "step": 29440 }, { "epoch": 0.17505691578840998, "grad_norm": 9.220479011535645, "learning_rate": 3.500998620952019e-06, "loss": 0.714, "step": 29450 }, { "epoch": 0.17511635786507837, "grad_norm": 9.223018646240234, "learning_rate": 3.502187455418708e-06, "loss": 0.7458, "step": 29460 }, { "epoch": 0.17517579994174676, "grad_norm": 10.689613342285156, "learning_rate": 3.503376289885397e-06, "loss": 0.6955, "step": 29470 }, { "epoch": 0.17523524201841514, "grad_norm": 12.585771560668945, "learning_rate": 3.5045651243520858e-06, "loss": 0.7224, "step": 29480 }, { "epoch": 0.17529468409508356, "grad_norm": 10.690445899963379, "learning_rate": 3.5057539588187743e-06, "loss": 0.7341, "step": 29490 }, { "epoch": 0.17535412617175195, "grad_norm": 9.4644775390625, "learning_rate": 3.506942793285463e-06, "loss": 0.7702, "step": 29500 }, { "epoch": 0.17541356824842033, "grad_norm": 11.433093070983887, "learning_rate": 3.508131627752152e-06, "loss": 0.7472, "step": 29510 }, { "epoch": 0.17547301032508872, "grad_norm": 10.934982299804688, "learning_rate": 3.509320462218841e-06, "loss": 0.6966, "step": 29520 }, { "epoch": 0.1755324524017571, "grad_norm": 5.807102203369141, "learning_rate": 3.51050929668553e-06, "loss": 0.6787, "step": 29530 }, { "epoch": 0.1755918944784255, "grad_norm": 8.748323440551758, "learning_rate": 3.5116981311522185e-06, "loss": 0.6854, "step": 29540 }, { "epoch": 0.17565133655509388, "grad_norm": 9.276779174804688, "learning_rate": 3.5128869656189074e-06, "loss": 0.7102, "step": 29550 }, { "epoch": 0.17571077863176227, "grad_norm": 9.439729690551758, "learning_rate": 3.5140758000855963e-06, "loss": 0.768, "step": 29560 }, { "epoch": 0.17577022070843068, "grad_norm": 7.858826160430908, "learning_rate": 3.5152646345522852e-06, "loss": 0.6708, "step": 29570 }, { "epoch": 0.17582966278509907, "grad_norm": 8.598773002624512, "learning_rate": 3.5164534690189738e-06, "loss": 0.7263, "step": 29580 }, { "epoch": 0.17588910486176745, "grad_norm": 10.756963729858398, "learning_rate": 3.5176423034856627e-06, "loss": 0.7664, "step": 29590 }, { "epoch": 0.17594854693843584, "grad_norm": 8.020337104797363, "learning_rate": 3.5188311379523516e-06, "loss": 0.6888, "step": 29600 }, { "epoch": 0.17600798901510423, "grad_norm": 8.552806854248047, "learning_rate": 3.520019972419041e-06, "loss": 0.7069, "step": 29610 }, { "epoch": 0.1760674310917726, "grad_norm": 9.17404842376709, "learning_rate": 3.52120880688573e-06, "loss": 0.6939, "step": 29620 }, { "epoch": 0.176126873168441, "grad_norm": 6.82900857925415, "learning_rate": 3.5223976413524184e-06, "loss": 0.736, "step": 29630 }, { "epoch": 0.17618631524510941, "grad_norm": 12.106202125549316, "learning_rate": 3.5235864758191073e-06, "loss": 0.7561, "step": 29640 }, { "epoch": 0.1762457573217778, "grad_norm": 7.996211528778076, "learning_rate": 3.5247753102857962e-06, "loss": 0.6658, "step": 29650 }, { "epoch": 0.1763051993984462, "grad_norm": 8.295933723449707, "learning_rate": 3.525964144752485e-06, "loss": 0.649, "step": 29660 }, { "epoch": 0.17636464147511458, "grad_norm": 9.545318603515625, "learning_rate": 3.5271529792191737e-06, "loss": 0.7453, "step": 29670 }, { "epoch": 0.17642408355178296, "grad_norm": 8.757882118225098, "learning_rate": 3.5283418136858626e-06, "loss": 0.7561, "step": 29680 }, { "epoch": 0.17648352562845135, "grad_norm": 9.711559295654297, "learning_rate": 3.5295306481525515e-06, "loss": 0.7242, "step": 29690 }, { "epoch": 0.17654296770511974, "grad_norm": 9.1085205078125, "learning_rate": 3.5307194826192405e-06, "loss": 0.6806, "step": 29700 }, { "epoch": 0.17660240978178815, "grad_norm": 7.190768718719482, "learning_rate": 3.5319083170859294e-06, "loss": 0.6599, "step": 29710 }, { "epoch": 0.17666185185845654, "grad_norm": 7.999634265899658, "learning_rate": 3.533097151552618e-06, "loss": 0.6475, "step": 29720 }, { "epoch": 0.17672129393512492, "grad_norm": 9.044113159179688, "learning_rate": 3.534285986019307e-06, "loss": 0.7087, "step": 29730 }, { "epoch": 0.1767807360117933, "grad_norm": 9.388344764709473, "learning_rate": 3.5354748204859957e-06, "loss": 0.754, "step": 29740 }, { "epoch": 0.1768401780884617, "grad_norm": 7.1465911865234375, "learning_rate": 3.5366636549526847e-06, "loss": 0.7074, "step": 29750 }, { "epoch": 0.17689962016513008, "grad_norm": 9.216703414916992, "learning_rate": 3.537852489419373e-06, "loss": 0.6862, "step": 29760 }, { "epoch": 0.17695906224179847, "grad_norm": 7.492683410644531, "learning_rate": 3.539041323886062e-06, "loss": 0.725, "step": 29770 }, { "epoch": 0.17701850431846686, "grad_norm": 8.113926887512207, "learning_rate": 3.5402301583527515e-06, "loss": 0.6439, "step": 29780 }, { "epoch": 0.17707794639513527, "grad_norm": 7.884520053863525, "learning_rate": 3.5414189928194404e-06, "loss": 0.7182, "step": 29790 }, { "epoch": 0.17713738847180366, "grad_norm": 8.774873733520508, "learning_rate": 3.5426078272861293e-06, "loss": 0.7416, "step": 29800 }, { "epoch": 0.17719683054847205, "grad_norm": 8.318490982055664, "learning_rate": 3.543796661752818e-06, "loss": 0.6999, "step": 29810 }, { "epoch": 0.17725627262514043, "grad_norm": 9.2515230178833, "learning_rate": 3.5449854962195067e-06, "loss": 0.7698, "step": 29820 }, { "epoch": 0.17731571470180882, "grad_norm": 9.5407075881958, "learning_rate": 3.5461743306861957e-06, "loss": 0.6936, "step": 29830 }, { "epoch": 0.1773751567784772, "grad_norm": 12.377289772033691, "learning_rate": 3.5473631651528846e-06, "loss": 0.6646, "step": 29840 }, { "epoch": 0.1774345988551456, "grad_norm": 9.798182487487793, "learning_rate": 3.548551999619573e-06, "loss": 0.6915, "step": 29850 }, { "epoch": 0.177494040931814, "grad_norm": 11.075895309448242, "learning_rate": 3.549740834086262e-06, "loss": 0.749, "step": 29860 }, { "epoch": 0.1775534830084824, "grad_norm": 7.89663553237915, "learning_rate": 3.550929668552951e-06, "loss": 0.6657, "step": 29870 }, { "epoch": 0.17761292508515078, "grad_norm": 8.329042434692383, "learning_rate": 3.55211850301964e-06, "loss": 0.723, "step": 29880 }, { "epoch": 0.17767236716181917, "grad_norm": 8.041542053222656, "learning_rate": 3.553307337486329e-06, "loss": 0.7191, "step": 29890 }, { "epoch": 0.17773180923848755, "grad_norm": 9.714990615844727, "learning_rate": 3.5544961719530173e-06, "loss": 0.7023, "step": 29900 }, { "epoch": 0.17779125131515594, "grad_norm": 10.117646217346191, "learning_rate": 3.5556850064197062e-06, "loss": 0.6723, "step": 29910 }, { "epoch": 0.17785069339182433, "grad_norm": 9.634259223937988, "learning_rate": 3.556873840886395e-06, "loss": 0.7364, "step": 29920 }, { "epoch": 0.1779101354684927, "grad_norm": 6.947412967681885, "learning_rate": 3.558062675353084e-06, "loss": 0.7215, "step": 29930 }, { "epoch": 0.17796957754516113, "grad_norm": 7.779854774475098, "learning_rate": 3.5592515098197726e-06, "loss": 0.7169, "step": 29940 }, { "epoch": 0.17802901962182952, "grad_norm": 7.351149082183838, "learning_rate": 3.5604403442864615e-06, "loss": 0.7227, "step": 29950 }, { "epoch": 0.1780884616984979, "grad_norm": 8.907554626464844, "learning_rate": 3.561629178753151e-06, "loss": 0.6594, "step": 29960 }, { "epoch": 0.1781479037751663, "grad_norm": 8.633209228515625, "learning_rate": 3.56281801321984e-06, "loss": 0.685, "step": 29970 }, { "epoch": 0.17820734585183468, "grad_norm": 9.413333892822266, "learning_rate": 3.5640068476865287e-06, "loss": 0.7601, "step": 29980 }, { "epoch": 0.17826678792850306, "grad_norm": 11.24775218963623, "learning_rate": 3.5651956821532172e-06, "loss": 0.7435, "step": 29990 }, { "epoch": 0.17832623000517145, "grad_norm": 9.089252471923828, "learning_rate": 3.566384516619906e-06, "loss": 0.7352, "step": 30000 }, { "epoch": 0.17838567208183986, "grad_norm": 8.036907196044922, "learning_rate": 3.567573351086595e-06, "loss": 0.694, "step": 30010 }, { "epoch": 0.17844511415850825, "grad_norm": 7.95893669128418, "learning_rate": 3.568762185553284e-06, "loss": 0.7123, "step": 30020 }, { "epoch": 0.17850455623517664, "grad_norm": 9.287343978881836, "learning_rate": 3.569951020019973e-06, "loss": 0.7033, "step": 30030 }, { "epoch": 0.17856399831184502, "grad_norm": 7.838469505310059, "learning_rate": 3.5711398544866614e-06, "loss": 0.7282, "step": 30040 }, { "epoch": 0.1786234403885134, "grad_norm": 8.561220169067383, "learning_rate": 3.5723286889533504e-06, "loss": 0.6487, "step": 30050 }, { "epoch": 0.1786828824651818, "grad_norm": 8.582417488098145, "learning_rate": 3.5735175234200393e-06, "loss": 0.6987, "step": 30060 }, { "epoch": 0.17874232454185018, "grad_norm": 9.346266746520996, "learning_rate": 3.5747063578867282e-06, "loss": 0.6989, "step": 30070 }, { "epoch": 0.1788017666185186, "grad_norm": 10.272439956665039, "learning_rate": 3.5758951923534167e-06, "loss": 0.685, "step": 30080 }, { "epoch": 0.17886120869518699, "grad_norm": 9.603679656982422, "learning_rate": 3.5770840268201057e-06, "loss": 0.7124, "step": 30090 }, { "epoch": 0.17892065077185537, "grad_norm": 8.3433837890625, "learning_rate": 3.5782728612867946e-06, "loss": 0.6931, "step": 30100 }, { "epoch": 0.17898009284852376, "grad_norm": 9.167723655700684, "learning_rate": 3.5794616957534835e-06, "loss": 0.6798, "step": 30110 }, { "epoch": 0.17903953492519215, "grad_norm": 9.879411697387695, "learning_rate": 3.580650530220172e-06, "loss": 0.6472, "step": 30120 }, { "epoch": 0.17909897700186053, "grad_norm": 8.673829078674316, "learning_rate": 3.5818393646868614e-06, "loss": 0.6638, "step": 30130 }, { "epoch": 0.17915841907852892, "grad_norm": 9.019554138183594, "learning_rate": 3.5830281991535503e-06, "loss": 0.6468, "step": 30140 }, { "epoch": 0.1792178611551973, "grad_norm": 8.648868560791016, "learning_rate": 3.5842170336202392e-06, "loss": 0.7092, "step": 30150 }, { "epoch": 0.17927730323186572, "grad_norm": 7.0895538330078125, "learning_rate": 3.585405868086928e-06, "loss": 0.6927, "step": 30160 }, { "epoch": 0.1793367453085341, "grad_norm": 10.996354103088379, "learning_rate": 3.5865947025536167e-06, "loss": 0.6997, "step": 30170 }, { "epoch": 0.1793961873852025, "grad_norm": 11.920550346374512, "learning_rate": 3.5877835370203056e-06, "loss": 0.7228, "step": 30180 }, { "epoch": 0.17945562946187088, "grad_norm": 10.001261711120605, "learning_rate": 3.5889723714869945e-06, "loss": 0.6702, "step": 30190 }, { "epoch": 0.17951507153853927, "grad_norm": 11.777985572814941, "learning_rate": 3.5901612059536834e-06, "loss": 0.6926, "step": 30200 }, { "epoch": 0.17957451361520765, "grad_norm": 8.484869003295898, "learning_rate": 3.5913500404203724e-06, "loss": 0.6645, "step": 30210 }, { "epoch": 0.17963395569187604, "grad_norm": 8.522357940673828, "learning_rate": 3.592538874887061e-06, "loss": 0.6852, "step": 30220 }, { "epoch": 0.17969339776854446, "grad_norm": 10.071882247924805, "learning_rate": 3.59372770935375e-06, "loss": 0.7472, "step": 30230 }, { "epoch": 0.17975283984521284, "grad_norm": 7.366944789886475, "learning_rate": 3.5949165438204387e-06, "loss": 0.6759, "step": 30240 }, { "epoch": 0.17981228192188123, "grad_norm": 10.692110061645508, "learning_rate": 3.5961053782871276e-06, "loss": 0.6462, "step": 30250 }, { "epoch": 0.17987172399854962, "grad_norm": 6.589519023895264, "learning_rate": 3.597294212753816e-06, "loss": 0.6731, "step": 30260 }, { "epoch": 0.179931166075218, "grad_norm": 9.094892501831055, "learning_rate": 3.598483047220505e-06, "loss": 0.6779, "step": 30270 }, { "epoch": 0.1799906081518864, "grad_norm": 7.680798053741455, "learning_rate": 3.599671881687194e-06, "loss": 0.7051, "step": 30280 }, { "epoch": 0.18005005022855478, "grad_norm": 6.9363555908203125, "learning_rate": 3.600860716153883e-06, "loss": 0.7494, "step": 30290 }, { "epoch": 0.18010949230522316, "grad_norm": 8.58604621887207, "learning_rate": 3.6020495506205723e-06, "loss": 0.6889, "step": 30300 }, { "epoch": 0.18016893438189158, "grad_norm": 10.234835624694824, "learning_rate": 3.6032383850872608e-06, "loss": 0.6853, "step": 30310 }, { "epoch": 0.18022837645855996, "grad_norm": 10.44558334350586, "learning_rate": 3.6044272195539497e-06, "loss": 0.7167, "step": 30320 }, { "epoch": 0.18028781853522835, "grad_norm": 9.905086517333984, "learning_rate": 3.6056160540206386e-06, "loss": 0.7178, "step": 30330 }, { "epoch": 0.18034726061189674, "grad_norm": 9.65156078338623, "learning_rate": 3.6068048884873276e-06, "loss": 0.7434, "step": 30340 }, { "epoch": 0.18040670268856512, "grad_norm": 9.399192810058594, "learning_rate": 3.6079937229540165e-06, "loss": 0.6947, "step": 30350 }, { "epoch": 0.1804661447652335, "grad_norm": 9.194676399230957, "learning_rate": 3.609182557420705e-06, "loss": 0.7509, "step": 30360 }, { "epoch": 0.1805255868419019, "grad_norm": 8.186552047729492, "learning_rate": 3.610371391887394e-06, "loss": 0.7081, "step": 30370 }, { "epoch": 0.1805850289185703, "grad_norm": 7.220071315765381, "learning_rate": 3.611560226354083e-06, "loss": 0.6206, "step": 30380 }, { "epoch": 0.1806444709952387, "grad_norm": 8.396461486816406, "learning_rate": 3.6127490608207718e-06, "loss": 0.6829, "step": 30390 }, { "epoch": 0.18070391307190709, "grad_norm": 11.284810066223145, "learning_rate": 3.6139378952874603e-06, "loss": 0.7432, "step": 30400 }, { "epoch": 0.18076335514857547, "grad_norm": 9.748208999633789, "learning_rate": 3.6151267297541492e-06, "loss": 0.7093, "step": 30410 }, { "epoch": 0.18082279722524386, "grad_norm": 9.002331733703613, "learning_rate": 3.616315564220838e-06, "loss": 0.7288, "step": 30420 }, { "epoch": 0.18088223930191225, "grad_norm": 9.735454559326172, "learning_rate": 3.617504398687527e-06, "loss": 0.7464, "step": 30430 }, { "epoch": 0.18094168137858063, "grad_norm": 8.448118209838867, "learning_rate": 3.6186932331542156e-06, "loss": 0.7128, "step": 30440 }, { "epoch": 0.18100112345524902, "grad_norm": 8.746816635131836, "learning_rate": 3.6198820676209045e-06, "loss": 0.6506, "step": 30450 }, { "epoch": 0.18106056553191743, "grad_norm": 7.530490398406982, "learning_rate": 3.6210709020875934e-06, "loss": 0.7042, "step": 30460 }, { "epoch": 0.18112000760858582, "grad_norm": 11.505478858947754, "learning_rate": 3.6222597365542824e-06, "loss": 0.7059, "step": 30470 }, { "epoch": 0.1811794496852542, "grad_norm": 9.762998580932617, "learning_rate": 3.6234485710209717e-06, "loss": 0.6969, "step": 30480 }, { "epoch": 0.1812388917619226, "grad_norm": 8.975255966186523, "learning_rate": 3.62463740548766e-06, "loss": 0.7044, "step": 30490 }, { "epoch": 0.18129833383859098, "grad_norm": 9.093987464904785, "learning_rate": 3.625826239954349e-06, "loss": 0.7193, "step": 30500 }, { "epoch": 0.18135777591525937, "grad_norm": 7.984532356262207, "learning_rate": 3.627015074421038e-06, "loss": 0.7547, "step": 30510 }, { "epoch": 0.18141721799192775, "grad_norm": 8.946504592895508, "learning_rate": 3.628203908887727e-06, "loss": 0.6506, "step": 30520 }, { "epoch": 0.18147666006859617, "grad_norm": 7.748435020446777, "learning_rate": 3.629392743354416e-06, "loss": 0.714, "step": 30530 }, { "epoch": 0.18153610214526456, "grad_norm": 8.072412490844727, "learning_rate": 3.6305815778211044e-06, "loss": 0.6598, "step": 30540 }, { "epoch": 0.18159554422193294, "grad_norm": 9.059621810913086, "learning_rate": 3.6317704122877933e-06, "loss": 0.7568, "step": 30550 }, { "epoch": 0.18165498629860133, "grad_norm": 9.230398178100586, "learning_rate": 3.6329592467544823e-06, "loss": 0.7092, "step": 30560 }, { "epoch": 0.18171442837526972, "grad_norm": 9.777868270874023, "learning_rate": 3.634148081221171e-06, "loss": 0.7424, "step": 30570 }, { "epoch": 0.1817738704519381, "grad_norm": 11.834431648254395, "learning_rate": 3.6353369156878597e-06, "loss": 0.6671, "step": 30580 }, { "epoch": 0.1818333125286065, "grad_norm": 7.399623394012451, "learning_rate": 3.6365257501545486e-06, "loss": 0.6988, "step": 30590 }, { "epoch": 0.1818927546052749, "grad_norm": 9.873939514160156, "learning_rate": 3.6377145846212376e-06, "loss": 0.7309, "step": 30600 }, { "epoch": 0.1819521966819433, "grad_norm": 10.491064071655273, "learning_rate": 3.6389034190879265e-06, "loss": 0.6767, "step": 30610 }, { "epoch": 0.18201163875861168, "grad_norm": 13.882436752319336, "learning_rate": 3.640092253554615e-06, "loss": 0.7331, "step": 30620 }, { "epoch": 0.18207108083528006, "grad_norm": 13.213724136352539, "learning_rate": 3.641281088021304e-06, "loss": 0.686, "step": 30630 }, { "epoch": 0.18213052291194845, "grad_norm": 8.716012954711914, "learning_rate": 3.642469922487993e-06, "loss": 0.7009, "step": 30640 }, { "epoch": 0.18218996498861684, "grad_norm": 9.234806060791016, "learning_rate": 3.643658756954682e-06, "loss": 0.7102, "step": 30650 }, { "epoch": 0.18224940706528522, "grad_norm": 10.887858390808105, "learning_rate": 3.644847591421371e-06, "loss": 0.7549, "step": 30660 }, { "epoch": 0.1823088491419536, "grad_norm": 9.369699478149414, "learning_rate": 3.6460364258880596e-06, "loss": 0.6797, "step": 30670 }, { "epoch": 0.18236829121862203, "grad_norm": 9.143756866455078, "learning_rate": 3.6472252603547486e-06, "loss": 0.6551, "step": 30680 }, { "epoch": 0.1824277332952904, "grad_norm": 10.548323631286621, "learning_rate": 3.6484140948214375e-06, "loss": 0.7138, "step": 30690 }, { "epoch": 0.1824871753719588, "grad_norm": 11.328750610351562, "learning_rate": 3.6496029292881264e-06, "loss": 0.6907, "step": 30700 }, { "epoch": 0.18254661744862719, "grad_norm": 8.327597618103027, "learning_rate": 3.6507917637548153e-06, "loss": 0.6359, "step": 30710 }, { "epoch": 0.18260605952529557, "grad_norm": 8.16358757019043, "learning_rate": 3.651980598221504e-06, "loss": 0.6909, "step": 30720 }, { "epoch": 0.18266550160196396, "grad_norm": 6.859496116638184, "learning_rate": 3.6531694326881928e-06, "loss": 0.6609, "step": 30730 }, { "epoch": 0.18272494367863235, "grad_norm": 9.785426139831543, "learning_rate": 3.6543582671548817e-06, "loss": 0.7574, "step": 30740 }, { "epoch": 0.18278438575530076, "grad_norm": 8.023999214172363, "learning_rate": 3.6555471016215706e-06, "loss": 0.7295, "step": 30750 }, { "epoch": 0.18284382783196915, "grad_norm": 9.278820991516113, "learning_rate": 3.656735936088259e-06, "loss": 0.7486, "step": 30760 }, { "epoch": 0.18290326990863753, "grad_norm": 9.885683059692383, "learning_rate": 3.657924770554948e-06, "loss": 0.7133, "step": 30770 }, { "epoch": 0.18296271198530592, "grad_norm": 8.60101318359375, "learning_rate": 3.659113605021637e-06, "loss": 0.7409, "step": 30780 }, { "epoch": 0.1830221540619743, "grad_norm": 9.030760765075684, "learning_rate": 3.660302439488326e-06, "loss": 0.7423, "step": 30790 }, { "epoch": 0.1830815961386427, "grad_norm": 8.709970474243164, "learning_rate": 3.6614912739550144e-06, "loss": 0.7101, "step": 30800 }, { "epoch": 0.18314103821531108, "grad_norm": 9.656760215759277, "learning_rate": 3.6626801084217033e-06, "loss": 0.7213, "step": 30810 }, { "epoch": 0.18320048029197947, "grad_norm": 9.053454399108887, "learning_rate": 3.6638689428883927e-06, "loss": 0.6958, "step": 30820 }, { "epoch": 0.18325992236864788, "grad_norm": 9.427628517150879, "learning_rate": 3.6650577773550816e-06, "loss": 0.7246, "step": 30830 }, { "epoch": 0.18331936444531627, "grad_norm": 9.550188064575195, "learning_rate": 3.6662466118217705e-06, "loss": 0.6996, "step": 30840 }, { "epoch": 0.18337880652198466, "grad_norm": 9.73727035522461, "learning_rate": 3.6674354462884595e-06, "loss": 0.7059, "step": 30850 }, { "epoch": 0.18343824859865304, "grad_norm": 8.762338638305664, "learning_rate": 3.668624280755148e-06, "loss": 0.6951, "step": 30860 }, { "epoch": 0.18349769067532143, "grad_norm": 7.479011535644531, "learning_rate": 3.669813115221837e-06, "loss": 0.6877, "step": 30870 }, { "epoch": 0.18355713275198982, "grad_norm": 7.88809061050415, "learning_rate": 3.671001949688526e-06, "loss": 0.616, "step": 30880 }, { "epoch": 0.1836165748286582, "grad_norm": 8.471709251403809, "learning_rate": 3.6721907841552148e-06, "loss": 0.6974, "step": 30890 }, { "epoch": 0.18367601690532662, "grad_norm": 7.965497970581055, "learning_rate": 3.6733796186219033e-06, "loss": 0.6729, "step": 30900 }, { "epoch": 0.183735458981995, "grad_norm": 10.000463485717773, "learning_rate": 3.674568453088592e-06, "loss": 0.7751, "step": 30910 }, { "epoch": 0.1837949010586634, "grad_norm": 8.985211372375488, "learning_rate": 3.675757287555281e-06, "loss": 0.7333, "step": 30920 }, { "epoch": 0.18385434313533178, "grad_norm": 9.452869415283203, "learning_rate": 3.67694612202197e-06, "loss": 0.7104, "step": 30930 }, { "epoch": 0.18391378521200016, "grad_norm": 9.395757675170898, "learning_rate": 3.6781349564886585e-06, "loss": 0.7154, "step": 30940 }, { "epoch": 0.18397322728866855, "grad_norm": 9.088179588317871, "learning_rate": 3.6793237909553475e-06, "loss": 0.7058, "step": 30950 }, { "epoch": 0.18403266936533694, "grad_norm": 10.483769416809082, "learning_rate": 3.6805126254220364e-06, "loss": 0.6492, "step": 30960 }, { "epoch": 0.18409211144200535, "grad_norm": 9.981019973754883, "learning_rate": 3.6817014598887253e-06, "loss": 0.738, "step": 30970 }, { "epoch": 0.18415155351867374, "grad_norm": 9.3612060546875, "learning_rate": 3.682890294355414e-06, "loss": 0.6447, "step": 30980 }, { "epoch": 0.18421099559534213, "grad_norm": 9.236991882324219, "learning_rate": 3.6840791288221028e-06, "loss": 0.7503, "step": 30990 }, { "epoch": 0.1842704376720105, "grad_norm": 8.68431568145752, "learning_rate": 3.685267963288792e-06, "loss": 0.652, "step": 31000 }, { "epoch": 0.1843298797486789, "grad_norm": 10.833248138427734, "learning_rate": 3.686456797755481e-06, "loss": 0.679, "step": 31010 }, { "epoch": 0.18438932182534729, "grad_norm": 8.663216590881348, "learning_rate": 3.68764563222217e-06, "loss": 0.688, "step": 31020 }, { "epoch": 0.18444876390201567, "grad_norm": 7.016636848449707, "learning_rate": 3.688834466688859e-06, "loss": 0.6342, "step": 31030 }, { "epoch": 0.18450820597868406, "grad_norm": 9.931483268737793, "learning_rate": 3.6900233011555474e-06, "loss": 0.7175, "step": 31040 }, { "epoch": 0.18456764805535247, "grad_norm": 8.334795951843262, "learning_rate": 3.6912121356222363e-06, "loss": 0.6857, "step": 31050 }, { "epoch": 0.18462709013202086, "grad_norm": 11.650758743286133, "learning_rate": 3.6924009700889253e-06, "loss": 0.6627, "step": 31060 }, { "epoch": 0.18468653220868925, "grad_norm": 9.394922256469727, "learning_rate": 3.693589804555614e-06, "loss": 0.7709, "step": 31070 }, { "epoch": 0.18474597428535763, "grad_norm": 8.130900382995605, "learning_rate": 3.6947786390223027e-06, "loss": 0.7428, "step": 31080 }, { "epoch": 0.18480541636202602, "grad_norm": 7.048293590545654, "learning_rate": 3.6959674734889916e-06, "loss": 0.7198, "step": 31090 }, { "epoch": 0.1848648584386944, "grad_norm": 9.023256301879883, "learning_rate": 3.6971563079556805e-06, "loss": 0.7101, "step": 31100 }, { "epoch": 0.1849243005153628, "grad_norm": 10.323360443115234, "learning_rate": 3.6983451424223695e-06, "loss": 0.6385, "step": 31110 }, { "epoch": 0.1849837425920312, "grad_norm": 9.327282905578613, "learning_rate": 3.699533976889058e-06, "loss": 0.7585, "step": 31120 }, { "epoch": 0.1850431846686996, "grad_norm": 10.67287540435791, "learning_rate": 3.700722811355747e-06, "loss": 0.6966, "step": 31130 }, { "epoch": 0.18510262674536798, "grad_norm": 11.24103832244873, "learning_rate": 3.701911645822436e-06, "loss": 0.7281, "step": 31140 }, { "epoch": 0.18516206882203637, "grad_norm": 9.59203052520752, "learning_rate": 3.7031004802891248e-06, "loss": 0.6586, "step": 31150 }, { "epoch": 0.18522151089870476, "grad_norm": 8.102813720703125, "learning_rate": 3.7042893147558133e-06, "loss": 0.6782, "step": 31160 }, { "epoch": 0.18528095297537314, "grad_norm": 7.7537360191345215, "learning_rate": 3.705478149222503e-06, "loss": 0.6833, "step": 31170 }, { "epoch": 0.18534039505204153, "grad_norm": 7.480576992034912, "learning_rate": 3.7066669836891915e-06, "loss": 0.7272, "step": 31180 }, { "epoch": 0.18539983712870992, "grad_norm": 7.883354187011719, "learning_rate": 3.7078558181558805e-06, "loss": 0.7127, "step": 31190 }, { "epoch": 0.18545927920537833, "grad_norm": 8.522168159484863, "learning_rate": 3.7090446526225694e-06, "loss": 0.7348, "step": 31200 }, { "epoch": 0.18551872128204672, "grad_norm": 11.60190200805664, "learning_rate": 3.7102334870892583e-06, "loss": 0.6954, "step": 31210 }, { "epoch": 0.1855781633587151, "grad_norm": 8.956317901611328, "learning_rate": 3.711422321555947e-06, "loss": 0.7863, "step": 31220 }, { "epoch": 0.1856376054353835, "grad_norm": 10.192968368530273, "learning_rate": 3.7126111560226357e-06, "loss": 0.7159, "step": 31230 }, { "epoch": 0.18569704751205188, "grad_norm": 12.333285331726074, "learning_rate": 3.7137999904893247e-06, "loss": 0.7295, "step": 31240 }, { "epoch": 0.18575648958872026, "grad_norm": 8.743748664855957, "learning_rate": 3.7149888249560136e-06, "loss": 0.6688, "step": 31250 }, { "epoch": 0.18581593166538865, "grad_norm": 8.237555503845215, "learning_rate": 3.716177659422702e-06, "loss": 0.7499, "step": 31260 }, { "epoch": 0.18587537374205707, "grad_norm": 12.104432106018066, "learning_rate": 3.717366493889391e-06, "loss": 0.6537, "step": 31270 }, { "epoch": 0.18593481581872545, "grad_norm": 9.090230941772461, "learning_rate": 3.71855532835608e-06, "loss": 0.6977, "step": 31280 }, { "epoch": 0.18599425789539384, "grad_norm": 8.079652786254883, "learning_rate": 3.719744162822769e-06, "loss": 0.6946, "step": 31290 }, { "epoch": 0.18605369997206223, "grad_norm": 7.684030055999756, "learning_rate": 3.7209329972894574e-06, "loss": 0.6798, "step": 31300 }, { "epoch": 0.1861131420487306, "grad_norm": 8.387255668640137, "learning_rate": 3.7221218317561463e-06, "loss": 0.6958, "step": 31310 }, { "epoch": 0.186172584125399, "grad_norm": 9.21215534210205, "learning_rate": 3.7233106662228352e-06, "loss": 0.744, "step": 31320 }, { "epoch": 0.18623202620206739, "grad_norm": 8.073915481567383, "learning_rate": 3.724499500689524e-06, "loss": 0.7534, "step": 31330 }, { "epoch": 0.18629146827873577, "grad_norm": 8.823683738708496, "learning_rate": 3.7256883351562135e-06, "loss": 0.695, "step": 31340 }, { "epoch": 0.1863509103554042, "grad_norm": 10.449981689453125, "learning_rate": 3.7268771696229024e-06, "loss": 0.7256, "step": 31350 }, { "epoch": 0.18641035243207257, "grad_norm": 8.060853958129883, "learning_rate": 3.728066004089591e-06, "loss": 0.7311, "step": 31360 }, { "epoch": 0.18646979450874096, "grad_norm": 9.399689674377441, "learning_rate": 3.72925483855628e-06, "loss": 0.7532, "step": 31370 }, { "epoch": 0.18652923658540935, "grad_norm": 8.54580020904541, "learning_rate": 3.730443673022969e-06, "loss": 0.6526, "step": 31380 }, { "epoch": 0.18658867866207773, "grad_norm": 8.37094783782959, "learning_rate": 3.7316325074896577e-06, "loss": 0.703, "step": 31390 }, { "epoch": 0.18664812073874612, "grad_norm": 8.829366683959961, "learning_rate": 3.7328213419563462e-06, "loss": 0.7311, "step": 31400 }, { "epoch": 0.1867075628154145, "grad_norm": 8.716174125671387, "learning_rate": 3.734010176423035e-06, "loss": 0.707, "step": 31410 }, { "epoch": 0.18676700489208292, "grad_norm": 7.828713417053223, "learning_rate": 3.735199010889724e-06, "loss": 0.7406, "step": 31420 }, { "epoch": 0.1868264469687513, "grad_norm": 9.030624389648438, "learning_rate": 3.736387845356413e-06, "loss": 0.7347, "step": 31430 }, { "epoch": 0.1868858890454197, "grad_norm": 8.742804527282715, "learning_rate": 3.7375766798231015e-06, "loss": 0.7204, "step": 31440 }, { "epoch": 0.18694533112208808, "grad_norm": 8.449186325073242, "learning_rate": 3.7387655142897905e-06, "loss": 0.6461, "step": 31450 }, { "epoch": 0.18700477319875647, "grad_norm": 7.7878828048706055, "learning_rate": 3.7399543487564794e-06, "loss": 0.6706, "step": 31460 }, { "epoch": 0.18706421527542486, "grad_norm": 7.731221675872803, "learning_rate": 3.7411431832231683e-06, "loss": 0.6544, "step": 31470 }, { "epoch": 0.18712365735209324, "grad_norm": 8.938770294189453, "learning_rate": 3.742332017689857e-06, "loss": 0.6847, "step": 31480 }, { "epoch": 0.18718309942876166, "grad_norm": 8.980140686035156, "learning_rate": 3.7435208521565457e-06, "loss": 0.6671, "step": 31490 }, { "epoch": 0.18724254150543004, "grad_norm": 10.232911109924316, "learning_rate": 3.7447096866232347e-06, "loss": 0.7374, "step": 31500 }, { "epoch": 0.18730198358209843, "grad_norm": 8.52359390258789, "learning_rate": 3.745898521089924e-06, "loss": 0.6626, "step": 31510 }, { "epoch": 0.18736142565876682, "grad_norm": 11.062967300415039, "learning_rate": 3.747087355556613e-06, "loss": 0.6999, "step": 31520 }, { "epoch": 0.1874208677354352, "grad_norm": 7.625763893127441, "learning_rate": 3.748276190023302e-06, "loss": 0.689, "step": 31530 }, { "epoch": 0.1874803098121036, "grad_norm": 7.308084011077881, "learning_rate": 3.7494650244899904e-06, "loss": 0.7113, "step": 31540 }, { "epoch": 0.18753975188877198, "grad_norm": 7.748908996582031, "learning_rate": 3.7506538589566793e-06, "loss": 0.6734, "step": 31550 }, { "epoch": 0.18759919396544036, "grad_norm": 10.370079040527344, "learning_rate": 3.7518426934233682e-06, "loss": 0.7459, "step": 31560 }, { "epoch": 0.18765863604210878, "grad_norm": 8.29053783416748, "learning_rate": 3.753031527890057e-06, "loss": 0.6712, "step": 31570 }, { "epoch": 0.18771807811877717, "grad_norm": 8.716296195983887, "learning_rate": 3.7542203623567457e-06, "loss": 0.6994, "step": 31580 }, { "epoch": 0.18777752019544555, "grad_norm": 7.896267890930176, "learning_rate": 3.7554091968234346e-06, "loss": 0.7526, "step": 31590 }, { "epoch": 0.18783696227211394, "grad_norm": 8.174710273742676, "learning_rate": 3.7565980312901235e-06, "loss": 0.6498, "step": 31600 }, { "epoch": 0.18789640434878233, "grad_norm": 7.3399338722229, "learning_rate": 3.7577868657568124e-06, "loss": 0.6367, "step": 31610 }, { "epoch": 0.1879558464254507, "grad_norm": 9.4536771774292, "learning_rate": 3.758975700223501e-06, "loss": 0.7305, "step": 31620 }, { "epoch": 0.1880152885021191, "grad_norm": 6.406767845153809, "learning_rate": 3.76016453469019e-06, "loss": 0.6685, "step": 31630 }, { "epoch": 0.1880747305787875, "grad_norm": 8.347261428833008, "learning_rate": 3.761353369156879e-06, "loss": 0.7586, "step": 31640 }, { "epoch": 0.1881341726554559, "grad_norm": 9.362931251525879, "learning_rate": 3.7625422036235677e-06, "loss": 0.7292, "step": 31650 }, { "epoch": 0.1881936147321243, "grad_norm": 8.58232307434082, "learning_rate": 3.7637310380902562e-06, "loss": 0.6683, "step": 31660 }, { "epoch": 0.18825305680879267, "grad_norm": 7.709244251251221, "learning_rate": 3.764919872556945e-06, "loss": 0.7183, "step": 31670 }, { "epoch": 0.18831249888546106, "grad_norm": 9.759336471557617, "learning_rate": 3.766108707023634e-06, "loss": 0.6985, "step": 31680 }, { "epoch": 0.18837194096212945, "grad_norm": 10.066618919372559, "learning_rate": 3.7672975414903234e-06, "loss": 0.6912, "step": 31690 }, { "epoch": 0.18843138303879783, "grad_norm": 7.839025020599365, "learning_rate": 3.7684863759570124e-06, "loss": 0.7106, "step": 31700 }, { "epoch": 0.18849082511546622, "grad_norm": 9.80006217956543, "learning_rate": 3.7696752104237013e-06, "loss": 0.7117, "step": 31710 }, { "epoch": 0.18855026719213464, "grad_norm": 9.526873588562012, "learning_rate": 3.77086404489039e-06, "loss": 0.7004, "step": 31720 }, { "epoch": 0.18860970926880302, "grad_norm": 10.9702787399292, "learning_rate": 3.7720528793570787e-06, "loss": 0.7084, "step": 31730 }, { "epoch": 0.1886691513454714, "grad_norm": 8.353678703308105, "learning_rate": 3.7732417138237676e-06, "loss": 0.7411, "step": 31740 }, { "epoch": 0.1887285934221398, "grad_norm": 8.648322105407715, "learning_rate": 3.7744305482904566e-06, "loss": 0.6754, "step": 31750 }, { "epoch": 0.18878803549880818, "grad_norm": 9.077717781066895, "learning_rate": 3.775619382757145e-06, "loss": 0.7054, "step": 31760 }, { "epoch": 0.18884747757547657, "grad_norm": 8.228690147399902, "learning_rate": 3.776808217223834e-06, "loss": 0.7056, "step": 31770 }, { "epoch": 0.18890691965214496, "grad_norm": 5.7122883796691895, "learning_rate": 3.777997051690523e-06, "loss": 0.6521, "step": 31780 }, { "epoch": 0.18896636172881337, "grad_norm": 11.107098579406738, "learning_rate": 3.779185886157212e-06, "loss": 0.7377, "step": 31790 }, { "epoch": 0.18902580380548176, "grad_norm": 8.873961448669434, "learning_rate": 3.7803747206239004e-06, "loss": 0.6369, "step": 31800 }, { "epoch": 0.18908524588215014, "grad_norm": 8.958666801452637, "learning_rate": 3.7815635550905893e-06, "loss": 0.6698, "step": 31810 }, { "epoch": 0.18914468795881853, "grad_norm": 8.971346855163574, "learning_rate": 3.7827523895572782e-06, "loss": 0.7007, "step": 31820 }, { "epoch": 0.18920413003548692, "grad_norm": 9.25671672821045, "learning_rate": 3.783941224023967e-06, "loss": 0.687, "step": 31830 }, { "epoch": 0.1892635721121553, "grad_norm": 9.777388572692871, "learning_rate": 3.7851300584906557e-06, "loss": 0.6788, "step": 31840 }, { "epoch": 0.1893230141888237, "grad_norm": 7.874712944030762, "learning_rate": 3.7863188929573446e-06, "loss": 0.6975, "step": 31850 }, { "epoch": 0.1893824562654921, "grad_norm": 10.332480430603027, "learning_rate": 3.787507727424034e-06, "loss": 0.6598, "step": 31860 }, { "epoch": 0.1894418983421605, "grad_norm": 10.191143035888672, "learning_rate": 3.788696561890723e-06, "loss": 0.6505, "step": 31870 }, { "epoch": 0.18950134041882888, "grad_norm": 12.92019271850586, "learning_rate": 3.7898853963574118e-06, "loss": 0.7129, "step": 31880 }, { "epoch": 0.18956078249549727, "grad_norm": 11.204296112060547, "learning_rate": 3.7910742308241007e-06, "loss": 0.7428, "step": 31890 }, { "epoch": 0.18962022457216565, "grad_norm": 8.93569564819336, "learning_rate": 3.7922630652907892e-06, "loss": 0.6804, "step": 31900 }, { "epoch": 0.18967966664883404, "grad_norm": 7.433150291442871, "learning_rate": 3.793451899757478e-06, "loss": 0.7752, "step": 31910 }, { "epoch": 0.18973910872550243, "grad_norm": 7.187443256378174, "learning_rate": 3.794640734224167e-06, "loss": 0.7179, "step": 31920 }, { "epoch": 0.1897985508021708, "grad_norm": 7.906430244445801, "learning_rate": 3.795829568690856e-06, "loss": 0.7573, "step": 31930 }, { "epoch": 0.18985799287883923, "grad_norm": 10.701239585876465, "learning_rate": 3.7970184031575445e-06, "loss": 0.7367, "step": 31940 }, { "epoch": 0.1899174349555076, "grad_norm": 8.132681846618652, "learning_rate": 3.7982072376242334e-06, "loss": 0.6619, "step": 31950 }, { "epoch": 0.189976877032176, "grad_norm": 7.233363151550293, "learning_rate": 3.7993960720909224e-06, "loss": 0.6479, "step": 31960 }, { "epoch": 0.1900363191088444, "grad_norm": 9.18132495880127, "learning_rate": 3.8005849065576113e-06, "loss": 0.6825, "step": 31970 }, { "epoch": 0.19009576118551277, "grad_norm": 9.678616523742676, "learning_rate": 3.8017737410242998e-06, "loss": 0.7213, "step": 31980 }, { "epoch": 0.19015520326218116, "grad_norm": 8.503226280212402, "learning_rate": 3.8029625754909887e-06, "loss": 0.663, "step": 31990 }, { "epoch": 0.19021464533884955, "grad_norm": 9.791777610778809, "learning_rate": 3.8041514099576776e-06, "loss": 0.7347, "step": 32000 }, { "epoch": 0.19027408741551796, "grad_norm": 8.071261405944824, "learning_rate": 3.8053402444243666e-06, "loss": 0.7193, "step": 32010 }, { "epoch": 0.19033352949218635, "grad_norm": 17.07296371459961, "learning_rate": 3.806529078891055e-06, "loss": 0.8151, "step": 32020 }, { "epoch": 0.19039297156885474, "grad_norm": 9.818171501159668, "learning_rate": 3.807717913357745e-06, "loss": 0.686, "step": 32030 }, { "epoch": 0.19045241364552312, "grad_norm": 9.220540046691895, "learning_rate": 3.8089067478244334e-06, "loss": 0.6178, "step": 32040 }, { "epoch": 0.1905118557221915, "grad_norm": 8.721087455749512, "learning_rate": 3.8100955822911223e-06, "loss": 0.7316, "step": 32050 }, { "epoch": 0.1905712977988599, "grad_norm": 8.496395111083984, "learning_rate": 3.811284416757811e-06, "loss": 0.6792, "step": 32060 }, { "epoch": 0.19063073987552828, "grad_norm": 10.09068775177002, "learning_rate": 3.8124732512245e-06, "loss": 0.6249, "step": 32070 }, { "epoch": 0.19069018195219667, "grad_norm": 9.919617652893066, "learning_rate": 3.8136620856911886e-06, "loss": 0.6851, "step": 32080 }, { "epoch": 0.19074962402886508, "grad_norm": 8.203512191772461, "learning_rate": 3.814850920157878e-06, "loss": 0.6602, "step": 32090 }, { "epoch": 0.19080906610553347, "grad_norm": 9.283435821533203, "learning_rate": 3.816039754624566e-06, "loss": 0.7316, "step": 32100 }, { "epoch": 0.19086850818220186, "grad_norm": 8.026893615722656, "learning_rate": 3.817228589091255e-06, "loss": 0.77, "step": 32110 }, { "epoch": 0.19092795025887024, "grad_norm": 9.187617301940918, "learning_rate": 3.818417423557944e-06, "loss": 0.6771, "step": 32120 }, { "epoch": 0.19098739233553863, "grad_norm": 8.254559516906738, "learning_rate": 3.819606258024633e-06, "loss": 0.7141, "step": 32130 }, { "epoch": 0.19104683441220702, "grad_norm": 10.503301620483398, "learning_rate": 3.820795092491322e-06, "loss": 0.6583, "step": 32140 }, { "epoch": 0.1911062764888754, "grad_norm": 8.194668769836426, "learning_rate": 3.821983926958011e-06, "loss": 0.7385, "step": 32150 }, { "epoch": 0.19116571856554382, "grad_norm": 8.463936805725098, "learning_rate": 3.8231727614247e-06, "loss": 0.6644, "step": 32160 }, { "epoch": 0.1912251606422122, "grad_norm": 7.014162540435791, "learning_rate": 3.8243615958913886e-06, "loss": 0.643, "step": 32170 }, { "epoch": 0.1912846027188806, "grad_norm": 7.155148983001709, "learning_rate": 3.825550430358077e-06, "loss": 0.656, "step": 32180 }, { "epoch": 0.19134404479554898, "grad_norm": 11.195910453796387, "learning_rate": 3.8267392648247656e-06, "loss": 0.7768, "step": 32190 }, { "epoch": 0.19140348687221737, "grad_norm": 7.671249866485596, "learning_rate": 3.8279280992914545e-06, "loss": 0.7211, "step": 32200 }, { "epoch": 0.19146292894888575, "grad_norm": 9.812368392944336, "learning_rate": 3.829116933758144e-06, "loss": 0.7279, "step": 32210 }, { "epoch": 0.19152237102555414, "grad_norm": 8.514851570129395, "learning_rate": 3.830305768224833e-06, "loss": 0.7292, "step": 32220 }, { "epoch": 0.19158181310222253, "grad_norm": 12.823416709899902, "learning_rate": 3.831494602691522e-06, "loss": 0.7113, "step": 32230 }, { "epoch": 0.19164125517889094, "grad_norm": 7.743124961853027, "learning_rate": 3.83268343715821e-06, "loss": 0.6906, "step": 32240 }, { "epoch": 0.19170069725555933, "grad_norm": 8.705475807189941, "learning_rate": 3.833872271624899e-06, "loss": 0.671, "step": 32250 }, { "epoch": 0.1917601393322277, "grad_norm": 8.146626472473145, "learning_rate": 3.835061106091588e-06, "loss": 0.7158, "step": 32260 }, { "epoch": 0.1918195814088961, "grad_norm": 9.134066581726074, "learning_rate": 3.836249940558277e-06, "loss": 0.6567, "step": 32270 }, { "epoch": 0.1918790234855645, "grad_norm": 10.833494186401367, "learning_rate": 3.837438775024966e-06, "loss": 0.7638, "step": 32280 }, { "epoch": 0.19193846556223287, "grad_norm": 7.2265801429748535, "learning_rate": 3.838627609491655e-06, "loss": 0.6449, "step": 32290 }, { "epoch": 0.19199790763890126, "grad_norm": 8.739754676818848, "learning_rate": 3.839816443958344e-06, "loss": 0.7288, "step": 32300 }, { "epoch": 0.19205734971556968, "grad_norm": 8.494255065917969, "learning_rate": 3.841005278425033e-06, "loss": 0.6459, "step": 32310 }, { "epoch": 0.19211679179223806, "grad_norm": 10.117305755615234, "learning_rate": 3.842194112891721e-06, "loss": 0.7413, "step": 32320 }, { "epoch": 0.19217623386890645, "grad_norm": 8.761819839477539, "learning_rate": 3.84338294735841e-06, "loss": 0.7018, "step": 32330 }, { "epoch": 0.19223567594557484, "grad_norm": 9.378445625305176, "learning_rate": 3.844571781825099e-06, "loss": 0.7175, "step": 32340 }, { "epoch": 0.19229511802224322, "grad_norm": 7.968320369720459, "learning_rate": 3.8457606162917876e-06, "loss": 0.6779, "step": 32350 }, { "epoch": 0.1923545600989116, "grad_norm": 7.1691765785217285, "learning_rate": 3.8469494507584765e-06, "loss": 0.6746, "step": 32360 }, { "epoch": 0.19241400217558, "grad_norm": 7.849954128265381, "learning_rate": 3.848138285225165e-06, "loss": 0.7411, "step": 32370 }, { "epoch": 0.1924734442522484, "grad_norm": 7.290887832641602, "learning_rate": 3.849327119691854e-06, "loss": 0.6741, "step": 32380 }, { "epoch": 0.1925328863289168, "grad_norm": 8.564090728759766, "learning_rate": 3.850515954158543e-06, "loss": 0.6823, "step": 32390 }, { "epoch": 0.19259232840558518, "grad_norm": 8.705382347106934, "learning_rate": 3.851704788625232e-06, "loss": 0.7011, "step": 32400 }, { "epoch": 0.19265177048225357, "grad_norm": 9.106612205505371, "learning_rate": 3.852893623091921e-06, "loss": 0.6952, "step": 32410 }, { "epoch": 0.19271121255892196, "grad_norm": 9.027007102966309, "learning_rate": 3.85408245755861e-06, "loss": 0.7165, "step": 32420 }, { "epoch": 0.19277065463559034, "grad_norm": 8.268179893493652, "learning_rate": 3.855271292025299e-06, "loss": 0.7225, "step": 32430 }, { "epoch": 0.19283009671225873, "grad_norm": 9.524975776672363, "learning_rate": 3.856460126491988e-06, "loss": 0.7535, "step": 32440 }, { "epoch": 0.19288953878892712, "grad_norm": 10.487936019897461, "learning_rate": 3.857648960958677e-06, "loss": 0.7063, "step": 32450 }, { "epoch": 0.19294898086559553, "grad_norm": 9.465418815612793, "learning_rate": 3.858837795425365e-06, "loss": 0.7723, "step": 32460 }, { "epoch": 0.19300842294226392, "grad_norm": 10.728971481323242, "learning_rate": 3.860026629892054e-06, "loss": 0.7106, "step": 32470 }, { "epoch": 0.1930678650189323, "grad_norm": 13.271103858947754, "learning_rate": 3.861215464358743e-06, "loss": 0.7457, "step": 32480 }, { "epoch": 0.1931273070956007, "grad_norm": 8.881031036376953, "learning_rate": 3.862404298825432e-06, "loss": 0.6912, "step": 32490 }, { "epoch": 0.19318674917226908, "grad_norm": 7.124368190765381, "learning_rate": 3.863593133292121e-06, "loss": 0.6798, "step": 32500 }, { "epoch": 0.19324619124893747, "grad_norm": 8.762406349182129, "learning_rate": 3.8647819677588095e-06, "loss": 0.709, "step": 32510 }, { "epoch": 0.19330563332560585, "grad_norm": 10.918904304504395, "learning_rate": 3.8659708022254985e-06, "loss": 0.696, "step": 32520 }, { "epoch": 0.19336507540227427, "grad_norm": 8.967394828796387, "learning_rate": 3.867159636692187e-06, "loss": 0.6765, "step": 32530 }, { "epoch": 0.19342451747894265, "grad_norm": 8.691397666931152, "learning_rate": 3.868348471158876e-06, "loss": 0.6723, "step": 32540 }, { "epoch": 0.19348395955561104, "grad_norm": 9.56843376159668, "learning_rate": 3.869537305625565e-06, "loss": 0.642, "step": 32550 }, { "epoch": 0.19354340163227943, "grad_norm": 11.673025131225586, "learning_rate": 3.870726140092254e-06, "loss": 0.7066, "step": 32560 }, { "epoch": 0.1936028437089478, "grad_norm": 8.059182167053223, "learning_rate": 3.871914974558943e-06, "loss": 0.7058, "step": 32570 }, { "epoch": 0.1936622857856162, "grad_norm": 7.644995212554932, "learning_rate": 3.873103809025632e-06, "loss": 0.7014, "step": 32580 }, { "epoch": 0.1937217278622846, "grad_norm": 8.875985145568848, "learning_rate": 3.874292643492321e-06, "loss": 0.7104, "step": 32590 }, { "epoch": 0.19378116993895297, "grad_norm": 8.189468383789062, "learning_rate": 3.875481477959009e-06, "loss": 0.6975, "step": 32600 }, { "epoch": 0.1938406120156214, "grad_norm": 9.150558471679688, "learning_rate": 3.876670312425698e-06, "loss": 0.7227, "step": 32610 }, { "epoch": 0.19390005409228978, "grad_norm": 9.223549842834473, "learning_rate": 3.877859146892387e-06, "loss": 0.6909, "step": 32620 }, { "epoch": 0.19395949616895816, "grad_norm": 9.8243989944458, "learning_rate": 3.879047981359076e-06, "loss": 0.7621, "step": 32630 }, { "epoch": 0.19401893824562655, "grad_norm": 7.579637050628662, "learning_rate": 3.880236815825765e-06, "loss": 0.6922, "step": 32640 }, { "epoch": 0.19407838032229494, "grad_norm": 7.349321365356445, "learning_rate": 3.881425650292454e-06, "loss": 0.7268, "step": 32650 }, { "epoch": 0.19413782239896332, "grad_norm": 7.5664286613464355, "learning_rate": 3.882614484759143e-06, "loss": 0.7126, "step": 32660 }, { "epoch": 0.1941972644756317, "grad_norm": 11.305269241333008, "learning_rate": 3.8838033192258315e-06, "loss": 0.689, "step": 32670 }, { "epoch": 0.19425670655230012, "grad_norm": 8.59545612335205, "learning_rate": 3.88499215369252e-06, "loss": 0.7059, "step": 32680 }, { "epoch": 0.1943161486289685, "grad_norm": 7.063940525054932, "learning_rate": 3.8861809881592085e-06, "loss": 0.6909, "step": 32690 }, { "epoch": 0.1943755907056369, "grad_norm": 8.684745788574219, "learning_rate": 3.8873698226258975e-06, "loss": 0.7289, "step": 32700 }, { "epoch": 0.19443503278230528, "grad_norm": 8.366338729858398, "learning_rate": 3.888558657092586e-06, "loss": 0.6635, "step": 32710 }, { "epoch": 0.19449447485897367, "grad_norm": 10.021639823913574, "learning_rate": 3.889747491559275e-06, "loss": 0.6348, "step": 32720 }, { "epoch": 0.19455391693564206, "grad_norm": 9.016538619995117, "learning_rate": 3.890936326025965e-06, "loss": 0.736, "step": 32730 }, { "epoch": 0.19461335901231044, "grad_norm": 8.221787452697754, "learning_rate": 3.892125160492653e-06, "loss": 0.7018, "step": 32740 }, { "epoch": 0.19467280108897883, "grad_norm": 6.724255084991455, "learning_rate": 3.893313994959342e-06, "loss": 0.7621, "step": 32750 }, { "epoch": 0.19473224316564725, "grad_norm": 8.9581937789917, "learning_rate": 3.894502829426031e-06, "loss": 0.6856, "step": 32760 }, { "epoch": 0.19479168524231563, "grad_norm": 9.705009460449219, "learning_rate": 3.89569166389272e-06, "loss": 0.6787, "step": 32770 }, { "epoch": 0.19485112731898402, "grad_norm": 11.063695907592773, "learning_rate": 3.896880498359409e-06, "loss": 0.73, "step": 32780 }, { "epoch": 0.1949105693956524, "grad_norm": 7.612262725830078, "learning_rate": 3.898069332826098e-06, "loss": 0.7211, "step": 32790 }, { "epoch": 0.1949700114723208, "grad_norm": 8.499868392944336, "learning_rate": 3.899258167292787e-06, "loss": 0.7503, "step": 32800 }, { "epoch": 0.19502945354898918, "grad_norm": 8.163908004760742, "learning_rate": 3.900447001759476e-06, "loss": 0.6067, "step": 32810 }, { "epoch": 0.19508889562565757, "grad_norm": 7.757305145263672, "learning_rate": 3.901635836226164e-06, "loss": 0.6703, "step": 32820 }, { "epoch": 0.19514833770232598, "grad_norm": 9.417570114135742, "learning_rate": 3.902824670692853e-06, "loss": 0.6754, "step": 32830 }, { "epoch": 0.19520777977899437, "grad_norm": 9.196999549865723, "learning_rate": 3.904013505159542e-06, "loss": 0.6847, "step": 32840 }, { "epoch": 0.19526722185566275, "grad_norm": 9.408474922180176, "learning_rate": 3.9052023396262305e-06, "loss": 0.6997, "step": 32850 }, { "epoch": 0.19532666393233114, "grad_norm": 10.003981590270996, "learning_rate": 3.9063911740929195e-06, "loss": 0.7043, "step": 32860 }, { "epoch": 0.19538610600899953, "grad_norm": 7.702734470367432, "learning_rate": 3.907580008559608e-06, "loss": 0.7236, "step": 32870 }, { "epoch": 0.19544554808566791, "grad_norm": 7.607001781463623, "learning_rate": 3.908768843026297e-06, "loss": 0.7213, "step": 32880 }, { "epoch": 0.1955049901623363, "grad_norm": 7.859462261199951, "learning_rate": 3.909957677492986e-06, "loss": 0.7017, "step": 32890 }, { "epoch": 0.19556443223900472, "grad_norm": 11.325111389160156, "learning_rate": 3.911146511959675e-06, "loss": 0.6683, "step": 32900 }, { "epoch": 0.1956238743156731, "grad_norm": 8.250402450561523, "learning_rate": 3.912335346426364e-06, "loss": 0.7087, "step": 32910 }, { "epoch": 0.1956833163923415, "grad_norm": 10.872331619262695, "learning_rate": 3.913524180893053e-06, "loss": 0.797, "step": 32920 }, { "epoch": 0.19574275846900988, "grad_norm": 11.2482271194458, "learning_rate": 3.914713015359742e-06, "loss": 0.7355, "step": 32930 }, { "epoch": 0.19580220054567826, "grad_norm": 10.494416236877441, "learning_rate": 3.915901849826431e-06, "loss": 0.6821, "step": 32940 }, { "epoch": 0.19586164262234665, "grad_norm": 7.6530375480651855, "learning_rate": 3.91709068429312e-06, "loss": 0.6614, "step": 32950 }, { "epoch": 0.19592108469901504, "grad_norm": 10.95326042175293, "learning_rate": 3.918279518759808e-06, "loss": 0.7555, "step": 32960 }, { "epoch": 0.19598052677568342, "grad_norm": 9.449058532714844, "learning_rate": 3.919468353226497e-06, "loss": 0.7116, "step": 32970 }, { "epoch": 0.19603996885235184, "grad_norm": 9.305719375610352, "learning_rate": 3.920657187693186e-06, "loss": 0.6743, "step": 32980 }, { "epoch": 0.19609941092902022, "grad_norm": 8.725049018859863, "learning_rate": 3.921846022159875e-06, "loss": 0.7243, "step": 32990 }, { "epoch": 0.1961588530056886, "grad_norm": 7.406217575073242, "learning_rate": 3.923034856626564e-06, "loss": 0.6425, "step": 33000 }, { "epoch": 0.196218295082357, "grad_norm": 11.981575012207031, "learning_rate": 3.9242236910932525e-06, "loss": 0.6937, "step": 33010 }, { "epoch": 0.19627773715902538, "grad_norm": 10.760305404663086, "learning_rate": 3.9254125255599415e-06, "loss": 0.7478, "step": 33020 }, { "epoch": 0.19633717923569377, "grad_norm": 10.024785041809082, "learning_rate": 3.92660136002663e-06, "loss": 0.7145, "step": 33030 }, { "epoch": 0.19639662131236216, "grad_norm": 8.39250659942627, "learning_rate": 3.927790194493319e-06, "loss": 0.6976, "step": 33040 }, { "epoch": 0.19645606338903057, "grad_norm": 7.875080108642578, "learning_rate": 3.928979028960007e-06, "loss": 0.7599, "step": 33050 }, { "epoch": 0.19651550546569896, "grad_norm": 8.749441146850586, "learning_rate": 3.930167863426696e-06, "loss": 0.7365, "step": 33060 }, { "epoch": 0.19657494754236735, "grad_norm": 9.6635103225708, "learning_rate": 3.931356697893386e-06, "loss": 0.7401, "step": 33070 }, { "epoch": 0.19663438961903573, "grad_norm": 7.160547256469727, "learning_rate": 3.932545532360075e-06, "loss": 0.6947, "step": 33080 }, { "epoch": 0.19669383169570412, "grad_norm": 7.448244094848633, "learning_rate": 3.933734366826764e-06, "loss": 0.6896, "step": 33090 }, { "epoch": 0.1967532737723725, "grad_norm": 8.192159652709961, "learning_rate": 3.934923201293452e-06, "loss": 0.6755, "step": 33100 }, { "epoch": 0.1968127158490409, "grad_norm": 8.665678024291992, "learning_rate": 3.936112035760141e-06, "loss": 0.6268, "step": 33110 }, { "epoch": 0.19687215792570928, "grad_norm": 11.753389358520508, "learning_rate": 3.93730087022683e-06, "loss": 0.7378, "step": 33120 }, { "epoch": 0.1969316000023777, "grad_norm": 9.302082061767578, "learning_rate": 3.938489704693519e-06, "loss": 0.6954, "step": 33130 }, { "epoch": 0.19699104207904608, "grad_norm": 11.204190254211426, "learning_rate": 3.939678539160208e-06, "loss": 0.7652, "step": 33140 }, { "epoch": 0.19705048415571447, "grad_norm": 9.585128784179688, "learning_rate": 3.940867373626897e-06, "loss": 0.7157, "step": 33150 }, { "epoch": 0.19710992623238285, "grad_norm": 7.266696453094482, "learning_rate": 3.942056208093586e-06, "loss": 0.6817, "step": 33160 }, { "epoch": 0.19716936830905124, "grad_norm": 9.011073112487793, "learning_rate": 3.9432450425602745e-06, "loss": 0.7284, "step": 33170 }, { "epoch": 0.19722881038571963, "grad_norm": 9.980193138122559, "learning_rate": 3.944433877026963e-06, "loss": 0.7342, "step": 33180 }, { "epoch": 0.19728825246238801, "grad_norm": 9.955926895141602, "learning_rate": 3.9456227114936515e-06, "loss": 0.7339, "step": 33190 }, { "epoch": 0.19734769453905643, "grad_norm": 9.265523910522461, "learning_rate": 3.9468115459603404e-06, "loss": 0.7183, "step": 33200 }, { "epoch": 0.19740713661572482, "grad_norm": 10.417880058288574, "learning_rate": 3.948000380427029e-06, "loss": 0.6836, "step": 33210 }, { "epoch": 0.1974665786923932, "grad_norm": 6.981001377105713, "learning_rate": 3.949189214893718e-06, "loss": 0.7327, "step": 33220 }, { "epoch": 0.1975260207690616, "grad_norm": 8.8616361618042, "learning_rate": 3.950378049360407e-06, "loss": 0.7074, "step": 33230 }, { "epoch": 0.19758546284572998, "grad_norm": 8.321972846984863, "learning_rate": 3.951566883827096e-06, "loss": 0.6929, "step": 33240 }, { "epoch": 0.19764490492239836, "grad_norm": 10.74821949005127, "learning_rate": 3.952755718293785e-06, "loss": 0.6863, "step": 33250 }, { "epoch": 0.19770434699906675, "grad_norm": 7.647782325744629, "learning_rate": 3.953944552760474e-06, "loss": 0.6533, "step": 33260 }, { "epoch": 0.19776378907573516, "grad_norm": 8.0728178024292, "learning_rate": 3.955133387227163e-06, "loss": 0.6978, "step": 33270 }, { "epoch": 0.19782323115240355, "grad_norm": 10.016740798950195, "learning_rate": 3.956322221693852e-06, "loss": 0.7099, "step": 33280 }, { "epoch": 0.19788267322907194, "grad_norm": 9.788859367370605, "learning_rate": 3.957511056160541e-06, "loss": 0.7191, "step": 33290 }, { "epoch": 0.19794211530574032, "grad_norm": 9.56966781616211, "learning_rate": 3.95869989062723e-06, "loss": 0.6794, "step": 33300 }, { "epoch": 0.1980015573824087, "grad_norm": 9.051356315612793, "learning_rate": 3.959888725093919e-06, "loss": 0.747, "step": 33310 }, { "epoch": 0.1980609994590771, "grad_norm": 11.335579872131348, "learning_rate": 3.961077559560607e-06, "loss": 0.6651, "step": 33320 }, { "epoch": 0.19812044153574548, "grad_norm": 9.715156555175781, "learning_rate": 3.962266394027296e-06, "loss": 0.6452, "step": 33330 }, { "epoch": 0.19817988361241387, "grad_norm": 8.242154121398926, "learning_rate": 3.963455228493985e-06, "loss": 0.6906, "step": 33340 }, { "epoch": 0.19823932568908229, "grad_norm": 9.973360061645508, "learning_rate": 3.9646440629606735e-06, "loss": 0.6988, "step": 33350 }, { "epoch": 0.19829876776575067, "grad_norm": 8.03307819366455, "learning_rate": 3.9658328974273624e-06, "loss": 0.7153, "step": 33360 }, { "epoch": 0.19835820984241906, "grad_norm": 10.82864761352539, "learning_rate": 3.967021731894051e-06, "loss": 0.6522, "step": 33370 }, { "epoch": 0.19841765191908745, "grad_norm": 9.130855560302734, "learning_rate": 3.96821056636074e-06, "loss": 0.6659, "step": 33380 }, { "epoch": 0.19847709399575583, "grad_norm": 8.529844284057617, "learning_rate": 3.969399400827429e-06, "loss": 0.7052, "step": 33390 }, { "epoch": 0.19853653607242422, "grad_norm": 9.066214561462402, "learning_rate": 3.970588235294118e-06, "loss": 0.7255, "step": 33400 }, { "epoch": 0.1985959781490926, "grad_norm": 8.423554420471191, "learning_rate": 3.971777069760806e-06, "loss": 0.6783, "step": 33410 }, { "epoch": 0.19865542022576102, "grad_norm": 9.485806465148926, "learning_rate": 3.972965904227496e-06, "loss": 0.7032, "step": 33420 }, { "epoch": 0.1987148623024294, "grad_norm": 6.974538326263428, "learning_rate": 3.974154738694185e-06, "loss": 0.6985, "step": 33430 }, { "epoch": 0.1987743043790978, "grad_norm": 7.832876205444336, "learning_rate": 3.975343573160874e-06, "loss": 0.7157, "step": 33440 }, { "epoch": 0.19883374645576618, "grad_norm": 8.62685775756836, "learning_rate": 3.976532407627563e-06, "loss": 0.7412, "step": 33450 }, { "epoch": 0.19889318853243457, "grad_norm": 8.379014015197754, "learning_rate": 3.977721242094251e-06, "loss": 0.6682, "step": 33460 }, { "epoch": 0.19895263060910295, "grad_norm": 6.2333807945251465, "learning_rate": 3.97891007656094e-06, "loss": 0.6832, "step": 33470 }, { "epoch": 0.19901207268577134, "grad_norm": 9.364651679992676, "learning_rate": 3.980098911027629e-06, "loss": 0.7035, "step": 33480 }, { "epoch": 0.19907151476243973, "grad_norm": 7.804926872253418, "learning_rate": 3.981287745494318e-06, "loss": 0.6878, "step": 33490 }, { "epoch": 0.19913095683910814, "grad_norm": 8.103164672851562, "learning_rate": 3.9824765799610066e-06, "loss": 0.7395, "step": 33500 }, { "epoch": 0.19919039891577653, "grad_norm": 11.33607006072998, "learning_rate": 3.9836654144276955e-06, "loss": 0.7321, "step": 33510 }, { "epoch": 0.19924984099244492, "grad_norm": 8.756144523620605, "learning_rate": 3.9848542488943844e-06, "loss": 0.6791, "step": 33520 }, { "epoch": 0.1993092830691133, "grad_norm": 6.8882222175598145, "learning_rate": 3.986043083361073e-06, "loss": 0.68, "step": 33530 }, { "epoch": 0.1993687251457817, "grad_norm": 7.557589530944824, "learning_rate": 3.987231917827762e-06, "loss": 0.6725, "step": 33540 }, { "epoch": 0.19942816722245008, "grad_norm": 10.558710098266602, "learning_rate": 3.98842075229445e-06, "loss": 0.7241, "step": 33550 }, { "epoch": 0.19948760929911846, "grad_norm": 11.19114875793457, "learning_rate": 3.989609586761139e-06, "loss": 0.7524, "step": 33560 }, { "epoch": 0.19954705137578688, "grad_norm": 9.137544631958008, "learning_rate": 3.990798421227828e-06, "loss": 0.7387, "step": 33570 }, { "epoch": 0.19960649345245526, "grad_norm": 8.468623161315918, "learning_rate": 3.991987255694517e-06, "loss": 0.6788, "step": 33580 }, { "epoch": 0.19966593552912365, "grad_norm": 8.780021667480469, "learning_rate": 3.993176090161207e-06, "loss": 0.7325, "step": 33590 }, { "epoch": 0.19972537760579204, "grad_norm": 8.174981117248535, "learning_rate": 3.994364924627895e-06, "loss": 0.7113, "step": 33600 }, { "epoch": 0.19978481968246042, "grad_norm": 7.4328293800354, "learning_rate": 3.995553759094584e-06, "loss": 0.6824, "step": 33610 }, { "epoch": 0.1998442617591288, "grad_norm": 7.067744255065918, "learning_rate": 3.996742593561273e-06, "loss": 0.7126, "step": 33620 }, { "epoch": 0.1999037038357972, "grad_norm": 9.223302841186523, "learning_rate": 3.997931428027962e-06, "loss": 0.6893, "step": 33630 }, { "epoch": 0.19996314591246558, "grad_norm": 9.453861236572266, "learning_rate": 3.999120262494651e-06, "loss": 0.7501, "step": 33640 }, { "epoch": 0.200022587989134, "grad_norm": 8.272347450256348, "learning_rate": 4.00030909696134e-06, "loss": 0.6667, "step": 33650 }, { "epoch": 0.20008203006580239, "grad_norm": 10.193009376525879, "learning_rate": 4.0014979314280286e-06, "loss": 0.7952, "step": 33660 }, { "epoch": 0.20014147214247077, "grad_norm": 7.114712238311768, "learning_rate": 4.0026867658947175e-06, "loss": 0.6906, "step": 33670 }, { "epoch": 0.20020091421913916, "grad_norm": 8.887825965881348, "learning_rate": 4.0038756003614056e-06, "loss": 0.719, "step": 33680 }, { "epoch": 0.20026035629580755, "grad_norm": 6.498325347900391, "learning_rate": 4.0050644348280945e-06, "loss": 0.6588, "step": 33690 }, { "epoch": 0.20031979837247593, "grad_norm": 7.937747478485107, "learning_rate": 4.0062532692947834e-06, "loss": 0.7005, "step": 33700 }, { "epoch": 0.20037924044914432, "grad_norm": 8.843337059020996, "learning_rate": 4.007442103761472e-06, "loss": 0.6935, "step": 33710 }, { "epoch": 0.20043868252581273, "grad_norm": 6.781526565551758, "learning_rate": 4.008630938228161e-06, "loss": 0.6929, "step": 33720 }, { "epoch": 0.20049812460248112, "grad_norm": 6.824899673461914, "learning_rate": 4.00981977269485e-06, "loss": 0.7093, "step": 33730 }, { "epoch": 0.2005575666791495, "grad_norm": 7.751281261444092, "learning_rate": 4.011008607161539e-06, "loss": 0.7011, "step": 33740 }, { "epoch": 0.2006170087558179, "grad_norm": 8.338398933410645, "learning_rate": 4.012197441628228e-06, "loss": 0.6816, "step": 33750 }, { "epoch": 0.20067645083248628, "grad_norm": 8.153964042663574, "learning_rate": 4.013386276094917e-06, "loss": 0.7492, "step": 33760 }, { "epoch": 0.20073589290915467, "grad_norm": 15.93930721282959, "learning_rate": 4.014575110561606e-06, "loss": 0.6806, "step": 33770 }, { "epoch": 0.20079533498582305, "grad_norm": 7.923072338104248, "learning_rate": 4.015763945028295e-06, "loss": 0.6941, "step": 33780 }, { "epoch": 0.20085477706249147, "grad_norm": 8.523859024047852, "learning_rate": 4.016952779494984e-06, "loss": 0.7027, "step": 33790 }, { "epoch": 0.20091421913915986, "grad_norm": 8.383435249328613, "learning_rate": 4.018141613961673e-06, "loss": 0.7008, "step": 33800 }, { "epoch": 0.20097366121582824, "grad_norm": 9.013989448547363, "learning_rate": 4.019330448428362e-06, "loss": 0.7168, "step": 33810 }, { "epoch": 0.20103310329249663, "grad_norm": 7.22147274017334, "learning_rate": 4.02051928289505e-06, "loss": 0.6769, "step": 33820 }, { "epoch": 0.20109254536916502, "grad_norm": 9.889615058898926, "learning_rate": 4.021708117361739e-06, "loss": 0.7405, "step": 33830 }, { "epoch": 0.2011519874458334, "grad_norm": 8.701622009277344, "learning_rate": 4.0228969518284276e-06, "loss": 0.6992, "step": 33840 }, { "epoch": 0.2012114295225018, "grad_norm": 8.108585357666016, "learning_rate": 4.0240857862951165e-06, "loss": 0.6243, "step": 33850 }, { "epoch": 0.20127087159917018, "grad_norm": 8.390313148498535, "learning_rate": 4.025274620761805e-06, "loss": 0.6564, "step": 33860 }, { "epoch": 0.2013303136758386, "grad_norm": 8.582276344299316, "learning_rate": 4.026463455228494e-06, "loss": 0.7097, "step": 33870 }, { "epoch": 0.20138975575250698, "grad_norm": 7.7202019691467285, "learning_rate": 4.027652289695183e-06, "loss": 0.6301, "step": 33880 }, { "epoch": 0.20144919782917536, "grad_norm": 8.362858772277832, "learning_rate": 4.028841124161872e-06, "loss": 0.6721, "step": 33890 }, { "epoch": 0.20150863990584375, "grad_norm": 7.3393049240112305, "learning_rate": 4.030029958628561e-06, "loss": 0.6938, "step": 33900 }, { "epoch": 0.20156808198251214, "grad_norm": 9.580904960632324, "learning_rate": 4.031218793095249e-06, "loss": 0.7109, "step": 33910 }, { "epoch": 0.20162752405918052, "grad_norm": 8.111339569091797, "learning_rate": 4.032407627561938e-06, "loss": 0.6355, "step": 33920 }, { "epoch": 0.2016869661358489, "grad_norm": 9.684379577636719, "learning_rate": 4.033596462028627e-06, "loss": 0.6826, "step": 33930 }, { "epoch": 0.20174640821251733, "grad_norm": 8.792448997497559, "learning_rate": 4.034785296495317e-06, "loss": 0.677, "step": 33940 }, { "epoch": 0.2018058502891857, "grad_norm": 6.988074779510498, "learning_rate": 4.035974130962006e-06, "loss": 0.6409, "step": 33950 }, { "epoch": 0.2018652923658541, "grad_norm": 9.762741088867188, "learning_rate": 4.037162965428694e-06, "loss": 0.7599, "step": 33960 }, { "epoch": 0.20192473444252249, "grad_norm": 9.431306838989258, "learning_rate": 4.038351799895383e-06, "loss": 0.7885, "step": 33970 }, { "epoch": 0.20198417651919087, "grad_norm": 7.011018753051758, "learning_rate": 4.039540634362072e-06, "loss": 0.6297, "step": 33980 }, { "epoch": 0.20204361859585926, "grad_norm": 7.664848327636719, "learning_rate": 4.040729468828761e-06, "loss": 0.6084, "step": 33990 }, { "epoch": 0.20210306067252765, "grad_norm": 8.751152992248535, "learning_rate": 4.0419183032954495e-06, "loss": 0.6849, "step": 34000 }, { "epoch": 0.20216250274919603, "grad_norm": 7.093806743621826, "learning_rate": 4.0431071377621385e-06, "loss": 0.6846, "step": 34010 }, { "epoch": 0.20222194482586445, "grad_norm": 6.979381561279297, "learning_rate": 4.044295972228827e-06, "loss": 0.6843, "step": 34020 }, { "epoch": 0.20228138690253283, "grad_norm": 8.3269624710083, "learning_rate": 4.045484806695516e-06, "loss": 0.6757, "step": 34030 }, { "epoch": 0.20234082897920122, "grad_norm": 9.691232681274414, "learning_rate": 4.046673641162205e-06, "loss": 0.7609, "step": 34040 }, { "epoch": 0.2024002710558696, "grad_norm": 7.88198184967041, "learning_rate": 4.047862475628893e-06, "loss": 0.7142, "step": 34050 }, { "epoch": 0.202459713132538, "grad_norm": 7.749554634094238, "learning_rate": 4.049051310095582e-06, "loss": 0.758, "step": 34060 }, { "epoch": 0.20251915520920638, "grad_norm": 8.309321403503418, "learning_rate": 4.050240144562271e-06, "loss": 0.622, "step": 34070 }, { "epoch": 0.20257859728587477, "grad_norm": 9.467142105102539, "learning_rate": 4.05142897902896e-06, "loss": 0.6789, "step": 34080 }, { "epoch": 0.20263803936254318, "grad_norm": 6.542807102203369, "learning_rate": 4.052617813495649e-06, "loss": 0.679, "step": 34090 }, { "epoch": 0.20269748143921157, "grad_norm": 8.996861457824707, "learning_rate": 4.053806647962338e-06, "loss": 0.6316, "step": 34100 }, { "epoch": 0.20275692351587996, "grad_norm": 9.69886589050293, "learning_rate": 4.054995482429027e-06, "loss": 0.687, "step": 34110 }, { "epoch": 0.20281636559254834, "grad_norm": 7.525026798248291, "learning_rate": 4.056184316895716e-06, "loss": 0.6962, "step": 34120 }, { "epoch": 0.20287580766921673, "grad_norm": 9.607638359069824, "learning_rate": 4.057373151362405e-06, "loss": 0.7877, "step": 34130 }, { "epoch": 0.20293524974588512, "grad_norm": 8.839820861816406, "learning_rate": 4.058561985829094e-06, "loss": 0.7614, "step": 34140 }, { "epoch": 0.2029946918225535, "grad_norm": 6.906440734863281, "learning_rate": 4.059750820295783e-06, "loss": 0.743, "step": 34150 }, { "epoch": 0.20305413389922192, "grad_norm": 6.221236705780029, "learning_rate": 4.0609396547624715e-06, "loss": 0.6943, "step": 34160 }, { "epoch": 0.2031135759758903, "grad_norm": 6.81355619430542, "learning_rate": 4.0621284892291605e-06, "loss": 0.7562, "step": 34170 }, { "epoch": 0.2031730180525587, "grad_norm": 7.43817138671875, "learning_rate": 4.0633173236958485e-06, "loss": 0.6857, "step": 34180 }, { "epoch": 0.20323246012922708, "grad_norm": 9.816444396972656, "learning_rate": 4.0645061581625375e-06, "loss": 0.6972, "step": 34190 }, { "epoch": 0.20329190220589546, "grad_norm": 9.23099422454834, "learning_rate": 4.065694992629226e-06, "loss": 0.7691, "step": 34200 }, { "epoch": 0.20335134428256385, "grad_norm": 9.359322547912598, "learning_rate": 4.066883827095915e-06, "loss": 0.6292, "step": 34210 }, { "epoch": 0.20341078635923224, "grad_norm": 8.535625457763672, "learning_rate": 4.068072661562604e-06, "loss": 0.7166, "step": 34220 }, { "epoch": 0.20347022843590062, "grad_norm": 7.432816982269287, "learning_rate": 4.069261496029293e-06, "loss": 0.7277, "step": 34230 }, { "epoch": 0.20352967051256904, "grad_norm": 8.63602352142334, "learning_rate": 4.070450330495982e-06, "loss": 0.709, "step": 34240 }, { "epoch": 0.20358911258923743, "grad_norm": 8.788467407226562, "learning_rate": 4.071639164962671e-06, "loss": 0.6687, "step": 34250 }, { "epoch": 0.2036485546659058, "grad_norm": 8.511774063110352, "learning_rate": 4.07282799942936e-06, "loss": 0.7645, "step": 34260 }, { "epoch": 0.2037079967425742, "grad_norm": 10.185627937316895, "learning_rate": 4.074016833896048e-06, "loss": 0.6602, "step": 34270 }, { "epoch": 0.20376743881924259, "grad_norm": 7.532369136810303, "learning_rate": 4.075205668362737e-06, "loss": 0.7144, "step": 34280 }, { "epoch": 0.20382688089591097, "grad_norm": 7.738708019256592, "learning_rate": 4.076394502829427e-06, "loss": 0.6334, "step": 34290 }, { "epoch": 0.20388632297257936, "grad_norm": 7.573779582977295, "learning_rate": 4.077583337296116e-06, "loss": 0.6833, "step": 34300 }, { "epoch": 0.20394576504924777, "grad_norm": 6.273871421813965, "learning_rate": 4.078772171762805e-06, "loss": 0.6224, "step": 34310 }, { "epoch": 0.20400520712591616, "grad_norm": 7.764865875244141, "learning_rate": 4.079961006229493e-06, "loss": 0.6681, "step": 34320 }, { "epoch": 0.20406464920258455, "grad_norm": 9.140647888183594, "learning_rate": 4.081149840696182e-06, "loss": 0.6562, "step": 34330 }, { "epoch": 0.20412409127925293, "grad_norm": 9.830698013305664, "learning_rate": 4.0823386751628705e-06, "loss": 0.7167, "step": 34340 }, { "epoch": 0.20418353335592132, "grad_norm": 11.273514747619629, "learning_rate": 4.0835275096295595e-06, "loss": 0.6927, "step": 34350 }, { "epoch": 0.2042429754325897, "grad_norm": 7.199577331542969, "learning_rate": 4.084716344096248e-06, "loss": 0.702, "step": 34360 }, { "epoch": 0.2043024175092581, "grad_norm": 8.061161041259766, "learning_rate": 4.085905178562937e-06, "loss": 0.6852, "step": 34370 }, { "epoch": 0.20436185958592648, "grad_norm": 8.228958129882812, "learning_rate": 4.087094013029626e-06, "loss": 0.6692, "step": 34380 }, { "epoch": 0.2044213016625949, "grad_norm": 12.138364791870117, "learning_rate": 4.088282847496315e-06, "loss": 0.6914, "step": 34390 }, { "epoch": 0.20448074373926328, "grad_norm": 8.82761287689209, "learning_rate": 4.089471681963004e-06, "loss": 0.676, "step": 34400 }, { "epoch": 0.20454018581593167, "grad_norm": 8.039216041564941, "learning_rate": 4.090660516429692e-06, "loss": 0.6684, "step": 34410 }, { "epoch": 0.20459962789260006, "grad_norm": 7.9197187423706055, "learning_rate": 4.091849350896381e-06, "loss": 0.7015, "step": 34420 }, { "epoch": 0.20465906996926844, "grad_norm": 9.725032806396484, "learning_rate": 4.09303818536307e-06, "loss": 0.7391, "step": 34430 }, { "epoch": 0.20471851204593683, "grad_norm": 9.766592025756836, "learning_rate": 4.094227019829759e-06, "loss": 0.7163, "step": 34440 }, { "epoch": 0.20477795412260522, "grad_norm": 7.523040294647217, "learning_rate": 4.095415854296448e-06, "loss": 0.6856, "step": 34450 }, { "epoch": 0.20483739619927363, "grad_norm": 7.8644795417785645, "learning_rate": 4.096604688763137e-06, "loss": 0.7061, "step": 34460 }, { "epoch": 0.20489683827594202, "grad_norm": 9.509513854980469, "learning_rate": 4.097793523229826e-06, "loss": 0.734, "step": 34470 }, { "epoch": 0.2049562803526104, "grad_norm": 8.446895599365234, "learning_rate": 4.098982357696515e-06, "loss": 0.7203, "step": 34480 }, { "epoch": 0.2050157224292788, "grad_norm": 11.013984680175781, "learning_rate": 4.100171192163204e-06, "loss": 0.6651, "step": 34490 }, { "epoch": 0.20507516450594718, "grad_norm": 8.622664451599121, "learning_rate": 4.1013600266298925e-06, "loss": 0.6535, "step": 34500 }, { "epoch": 0.20513460658261556, "grad_norm": 6.934000492095947, "learning_rate": 4.1025488610965815e-06, "loss": 0.6726, "step": 34510 }, { "epoch": 0.20519404865928395, "grad_norm": 10.004888534545898, "learning_rate": 4.10373769556327e-06, "loss": 0.7269, "step": 34520 }, { "epoch": 0.20525349073595234, "grad_norm": 9.307622909545898, "learning_rate": 4.104926530029959e-06, "loss": 0.7389, "step": 34530 }, { "epoch": 0.20531293281262075, "grad_norm": 12.616279602050781, "learning_rate": 4.106115364496648e-06, "loss": 0.7093, "step": 34540 }, { "epoch": 0.20537237488928914, "grad_norm": 9.405899047851562, "learning_rate": 4.107304198963336e-06, "loss": 0.7901, "step": 34550 }, { "epoch": 0.20543181696595753, "grad_norm": 7.630833148956299, "learning_rate": 4.108493033430025e-06, "loss": 0.6533, "step": 34560 }, { "epoch": 0.2054912590426259, "grad_norm": 10.408249855041504, "learning_rate": 4.109681867896714e-06, "loss": 0.7166, "step": 34570 }, { "epoch": 0.2055507011192943, "grad_norm": 9.700370788574219, "learning_rate": 4.110870702363403e-06, "loss": 0.7169, "step": 34580 }, { "epoch": 0.20561014319596269, "grad_norm": 8.953479766845703, "learning_rate": 4.112059536830092e-06, "loss": 0.6972, "step": 34590 }, { "epoch": 0.20566958527263107, "grad_norm": 8.003266334533691, "learning_rate": 4.113248371296781e-06, "loss": 0.7043, "step": 34600 }, { "epoch": 0.2057290273492995, "grad_norm": 10.026205062866211, "learning_rate": 4.11443720576347e-06, "loss": 0.6953, "step": 34610 }, { "epoch": 0.20578846942596787, "grad_norm": 6.958082675933838, "learning_rate": 4.115626040230159e-06, "loss": 0.6906, "step": 34620 }, { "epoch": 0.20584791150263626, "grad_norm": 11.105504989624023, "learning_rate": 4.116814874696848e-06, "loss": 0.7224, "step": 34630 }, { "epoch": 0.20590735357930465, "grad_norm": 8.081486701965332, "learning_rate": 4.118003709163537e-06, "loss": 0.6734, "step": 34640 }, { "epoch": 0.20596679565597303, "grad_norm": 8.53157901763916, "learning_rate": 4.119192543630226e-06, "loss": 0.6891, "step": 34650 }, { "epoch": 0.20602623773264142, "grad_norm": 8.580492973327637, "learning_rate": 4.1203813780969145e-06, "loss": 0.6825, "step": 34660 }, { "epoch": 0.2060856798093098, "grad_norm": 6.822723865509033, "learning_rate": 4.1215702125636034e-06, "loss": 0.7185, "step": 34670 }, { "epoch": 0.20614512188597822, "grad_norm": 6.853621959686279, "learning_rate": 4.122759047030292e-06, "loss": 0.6873, "step": 34680 }, { "epoch": 0.2062045639626466, "grad_norm": 9.626213073730469, "learning_rate": 4.1239478814969805e-06, "loss": 0.6724, "step": 34690 }, { "epoch": 0.206264006039315, "grad_norm": 8.077577590942383, "learning_rate": 4.125136715963669e-06, "loss": 0.7788, "step": 34700 }, { "epoch": 0.20632344811598338, "grad_norm": 9.556992530822754, "learning_rate": 4.126325550430358e-06, "loss": 0.6869, "step": 34710 }, { "epoch": 0.20638289019265177, "grad_norm": 8.85680103302002, "learning_rate": 4.127514384897047e-06, "loss": 0.692, "step": 34720 }, { "epoch": 0.20644233226932016, "grad_norm": 10.95805549621582, "learning_rate": 4.128703219363736e-06, "loss": 0.729, "step": 34730 }, { "epoch": 0.20650177434598854, "grad_norm": 8.916845321655273, "learning_rate": 4.129892053830425e-06, "loss": 0.6281, "step": 34740 }, { "epoch": 0.20656121642265693, "grad_norm": 9.621919631958008, "learning_rate": 4.131080888297114e-06, "loss": 0.7303, "step": 34750 }, { "epoch": 0.20662065849932534, "grad_norm": 7.044621467590332, "learning_rate": 4.132269722763803e-06, "loss": 0.6425, "step": 34760 }, { "epoch": 0.20668010057599373, "grad_norm": 9.47241497039795, "learning_rate": 4.133458557230491e-06, "loss": 0.7134, "step": 34770 }, { "epoch": 0.20673954265266212, "grad_norm": 9.416390419006348, "learning_rate": 4.13464739169718e-06, "loss": 0.7747, "step": 34780 }, { "epoch": 0.2067989847293305, "grad_norm": 6.5106658935546875, "learning_rate": 4.135836226163869e-06, "loss": 0.639, "step": 34790 }, { "epoch": 0.2068584268059989, "grad_norm": 9.062744140625, "learning_rate": 4.137025060630558e-06, "loss": 0.7178, "step": 34800 }, { "epoch": 0.20691786888266728, "grad_norm": 7.646801471710205, "learning_rate": 4.138213895097248e-06, "loss": 0.7683, "step": 34810 }, { "epoch": 0.20697731095933566, "grad_norm": 8.79794692993164, "learning_rate": 4.139402729563936e-06, "loss": 0.6969, "step": 34820 }, { "epoch": 0.20703675303600408, "grad_norm": 6.845938682556152, "learning_rate": 4.140591564030625e-06, "loss": 0.6622, "step": 34830 }, { "epoch": 0.20709619511267247, "grad_norm": 11.589818000793457, "learning_rate": 4.1417803984973135e-06, "loss": 0.7053, "step": 34840 }, { "epoch": 0.20715563718934085, "grad_norm": 9.250995635986328, "learning_rate": 4.1429692329640024e-06, "loss": 0.691, "step": 34850 }, { "epoch": 0.20721507926600924, "grad_norm": 6.774377822875977, "learning_rate": 4.144158067430691e-06, "loss": 0.6943, "step": 34860 }, { "epoch": 0.20727452134267763, "grad_norm": 10.421751976013184, "learning_rate": 4.14534690189738e-06, "loss": 0.678, "step": 34870 }, { "epoch": 0.207333963419346, "grad_norm": 7.6928582191467285, "learning_rate": 4.146535736364069e-06, "loss": 0.7122, "step": 34880 }, { "epoch": 0.2073934054960144, "grad_norm": 7.2862443923950195, "learning_rate": 4.147724570830758e-06, "loss": 0.6333, "step": 34890 }, { "epoch": 0.20745284757268279, "grad_norm": 9.160377502441406, "learning_rate": 4.148913405297447e-06, "loss": 0.6718, "step": 34900 }, { "epoch": 0.2075122896493512, "grad_norm": 7.058566570281982, "learning_rate": 4.150102239764135e-06, "loss": 0.7567, "step": 34910 }, { "epoch": 0.2075717317260196, "grad_norm": 7.713535785675049, "learning_rate": 4.151291074230824e-06, "loss": 0.7101, "step": 34920 }, { "epoch": 0.20763117380268797, "grad_norm": 7.04711389541626, "learning_rate": 4.152479908697513e-06, "loss": 0.6598, "step": 34930 }, { "epoch": 0.20769061587935636, "grad_norm": 9.944777488708496, "learning_rate": 4.153668743164202e-06, "loss": 0.7045, "step": 34940 }, { "epoch": 0.20775005795602475, "grad_norm": 9.014678001403809, "learning_rate": 4.154857577630891e-06, "loss": 0.6771, "step": 34950 }, { "epoch": 0.20780950003269313, "grad_norm": 7.717020511627197, "learning_rate": 4.15604641209758e-06, "loss": 0.6787, "step": 34960 }, { "epoch": 0.20786894210936152, "grad_norm": 8.828435897827148, "learning_rate": 4.157235246564269e-06, "loss": 0.6755, "step": 34970 }, { "epoch": 0.20792838418602994, "grad_norm": 8.95156478881836, "learning_rate": 4.158424081030958e-06, "loss": 0.6815, "step": 34980 }, { "epoch": 0.20798782626269832, "grad_norm": 8.277212142944336, "learning_rate": 4.1596129154976466e-06, "loss": 0.6715, "step": 34990 }, { "epoch": 0.2080472683393667, "grad_norm": 8.10573959350586, "learning_rate": 4.1608017499643355e-06, "loss": 0.7726, "step": 35000 }, { "epoch": 0.2081067104160351, "grad_norm": 8.019607543945312, "learning_rate": 4.1619905844310244e-06, "loss": 0.6301, "step": 35010 }, { "epoch": 0.20816615249270348, "grad_norm": 8.214742660522461, "learning_rate": 4.163179418897713e-06, "loss": 0.7678, "step": 35020 }, { "epoch": 0.20822559456937187, "grad_norm": 7.648585796356201, "learning_rate": 4.164368253364402e-06, "loss": 0.6803, "step": 35030 }, { "epoch": 0.20828503664604026, "grad_norm": 8.871567726135254, "learning_rate": 4.165557087831091e-06, "loss": 0.6856, "step": 35040 }, { "epoch": 0.20834447872270867, "grad_norm": 7.780210971832275, "learning_rate": 4.166745922297779e-06, "loss": 0.6761, "step": 35050 }, { "epoch": 0.20840392079937706, "grad_norm": 7.734394073486328, "learning_rate": 4.167934756764468e-06, "loss": 0.696, "step": 35060 }, { "epoch": 0.20846336287604544, "grad_norm": 7.439632892608643, "learning_rate": 4.169123591231157e-06, "loss": 0.6657, "step": 35070 }, { "epoch": 0.20852280495271383, "grad_norm": 7.753739356994629, "learning_rate": 4.170312425697846e-06, "loss": 0.6501, "step": 35080 }, { "epoch": 0.20858224702938222, "grad_norm": 6.897311687469482, "learning_rate": 4.171501260164535e-06, "loss": 0.694, "step": 35090 }, { "epoch": 0.2086416891060506, "grad_norm": 8.8767671585083, "learning_rate": 4.172690094631224e-06, "loss": 0.6708, "step": 35100 }, { "epoch": 0.208701131182719, "grad_norm": 8.518832206726074, "learning_rate": 4.173878929097913e-06, "loss": 0.7159, "step": 35110 }, { "epoch": 0.20876057325938738, "grad_norm": 7.333937168121338, "learning_rate": 4.175067763564602e-06, "loss": 0.7485, "step": 35120 }, { "epoch": 0.2088200153360558, "grad_norm": 8.752403259277344, "learning_rate": 4.17625659803129e-06, "loss": 0.6565, "step": 35130 }, { "epoch": 0.20887945741272418, "grad_norm": 8.46811294555664, "learning_rate": 4.177445432497979e-06, "loss": 0.637, "step": 35140 }, { "epoch": 0.20893889948939257, "grad_norm": 9.02456283569336, "learning_rate": 4.1786342669646686e-06, "loss": 0.7877, "step": 35150 }, { "epoch": 0.20899834156606095, "grad_norm": 8.355958938598633, "learning_rate": 4.1798231014313575e-06, "loss": 0.705, "step": 35160 }, { "epoch": 0.20905778364272934, "grad_norm": 9.97846508026123, "learning_rate": 4.181011935898046e-06, "loss": 0.6783, "step": 35170 }, { "epoch": 0.20911722571939773, "grad_norm": 8.737728118896484, "learning_rate": 4.182200770364735e-06, "loss": 0.6936, "step": 35180 }, { "epoch": 0.2091766677960661, "grad_norm": 8.552884101867676, "learning_rate": 4.1833896048314234e-06, "loss": 0.6885, "step": 35190 }, { "epoch": 0.20923610987273453, "grad_norm": 9.797846794128418, "learning_rate": 4.184578439298112e-06, "loss": 0.6834, "step": 35200 }, { "epoch": 0.2092955519494029, "grad_norm": 9.757831573486328, "learning_rate": 4.185767273764801e-06, "loss": 0.6989, "step": 35210 }, { "epoch": 0.2093549940260713, "grad_norm": 9.024600982666016, "learning_rate": 4.18695610823149e-06, "loss": 0.7308, "step": 35220 }, { "epoch": 0.2094144361027397, "grad_norm": 6.934474945068359, "learning_rate": 4.188144942698179e-06, "loss": 0.7113, "step": 35230 }, { "epoch": 0.20947387817940807, "grad_norm": 9.379105567932129, "learning_rate": 4.189333777164868e-06, "loss": 0.7541, "step": 35240 }, { "epoch": 0.20953332025607646, "grad_norm": 6.828279972076416, "learning_rate": 4.190522611631557e-06, "loss": 0.6517, "step": 35250 }, { "epoch": 0.20959276233274485, "grad_norm": 7.790382385253906, "learning_rate": 4.191711446098246e-06, "loss": 0.7219, "step": 35260 }, { "epoch": 0.20965220440941323, "grad_norm": 10.118006706237793, "learning_rate": 4.192900280564934e-06, "loss": 0.7266, "step": 35270 }, { "epoch": 0.20971164648608165, "grad_norm": 7.747463703155518, "learning_rate": 4.194089115031623e-06, "loss": 0.6713, "step": 35280 }, { "epoch": 0.20977108856275004, "grad_norm": 11.752084732055664, "learning_rate": 4.195277949498312e-06, "loss": 0.6889, "step": 35290 }, { "epoch": 0.20983053063941842, "grad_norm": 8.71568775177002, "learning_rate": 4.196466783965001e-06, "loss": 0.6534, "step": 35300 }, { "epoch": 0.2098899727160868, "grad_norm": 9.316811561584473, "learning_rate": 4.19765561843169e-06, "loss": 0.6712, "step": 35310 }, { "epoch": 0.2099494147927552, "grad_norm": 9.642010688781738, "learning_rate": 4.198844452898379e-06, "loss": 0.7341, "step": 35320 }, { "epoch": 0.21000885686942358, "grad_norm": 9.661382675170898, "learning_rate": 4.2000332873650676e-06, "loss": 0.731, "step": 35330 }, { "epoch": 0.21006829894609197, "grad_norm": 8.200263023376465, "learning_rate": 4.2012221218317565e-06, "loss": 0.6882, "step": 35340 }, { "epoch": 0.21012774102276038, "grad_norm": 8.778931617736816, "learning_rate": 4.202410956298445e-06, "loss": 0.6919, "step": 35350 }, { "epoch": 0.21018718309942877, "grad_norm": 10.392732620239258, "learning_rate": 4.203599790765134e-06, "loss": 0.7216, "step": 35360 }, { "epoch": 0.21024662517609716, "grad_norm": 9.649188995361328, "learning_rate": 4.204788625231823e-06, "loss": 0.6788, "step": 35370 }, { "epoch": 0.21030606725276554, "grad_norm": 8.425896644592285, "learning_rate": 4.205977459698512e-06, "loss": 0.7117, "step": 35380 }, { "epoch": 0.21036550932943393, "grad_norm": 7.162158012390137, "learning_rate": 4.207166294165201e-06, "loss": 0.6269, "step": 35390 }, { "epoch": 0.21042495140610232, "grad_norm": 8.223880767822266, "learning_rate": 4.20835512863189e-06, "loss": 0.7564, "step": 35400 }, { "epoch": 0.2104843934827707, "grad_norm": 11.185202598571777, "learning_rate": 4.209543963098578e-06, "loss": 0.7667, "step": 35410 }, { "epoch": 0.2105438355594391, "grad_norm": 8.714481353759766, "learning_rate": 4.210732797565267e-06, "loss": 0.7146, "step": 35420 }, { "epoch": 0.2106032776361075, "grad_norm": 7.10008430480957, "learning_rate": 4.211921632031956e-06, "loss": 0.6729, "step": 35430 }, { "epoch": 0.2106627197127759, "grad_norm": 8.743370056152344, "learning_rate": 4.213110466498645e-06, "loss": 0.7259, "step": 35440 }, { "epoch": 0.21072216178944428, "grad_norm": 7.2872443199157715, "learning_rate": 4.214299300965334e-06, "loss": 0.6417, "step": 35450 }, { "epoch": 0.21078160386611267, "grad_norm": 9.20079517364502, "learning_rate": 4.215488135432023e-06, "loss": 0.6484, "step": 35460 }, { "epoch": 0.21084104594278105, "grad_norm": 6.497705936431885, "learning_rate": 4.216676969898712e-06, "loss": 0.7, "step": 35470 }, { "epoch": 0.21090048801944944, "grad_norm": 9.045668601989746, "learning_rate": 4.217865804365401e-06, "loss": 0.6541, "step": 35480 }, { "epoch": 0.21095993009611783, "grad_norm": 9.170302391052246, "learning_rate": 4.219054638832089e-06, "loss": 0.6754, "step": 35490 }, { "epoch": 0.21101937217278624, "grad_norm": 8.284012794494629, "learning_rate": 4.2202434732987785e-06, "loss": 0.6878, "step": 35500 }, { "epoch": 0.21107881424945463, "grad_norm": 6.439717769622803, "learning_rate": 4.221432307765467e-06, "loss": 0.6151, "step": 35510 }, { "epoch": 0.211138256326123, "grad_norm": 8.661937713623047, "learning_rate": 4.222621142232156e-06, "loss": 0.6801, "step": 35520 }, { "epoch": 0.2111976984027914, "grad_norm": 8.6220064163208, "learning_rate": 4.223809976698845e-06, "loss": 0.5947, "step": 35530 }, { "epoch": 0.2112571404794598, "grad_norm": 8.693896293640137, "learning_rate": 4.224998811165534e-06, "loss": 0.7325, "step": 35540 }, { "epoch": 0.21131658255612817, "grad_norm": 9.29373836517334, "learning_rate": 4.226187645632222e-06, "loss": 0.6465, "step": 35550 }, { "epoch": 0.21137602463279656, "grad_norm": 9.240118980407715, "learning_rate": 4.227376480098911e-06, "loss": 0.7356, "step": 35560 }, { "epoch": 0.21143546670946498, "grad_norm": 7.413172721862793, "learning_rate": 4.2285653145656e-06, "loss": 0.7025, "step": 35570 }, { "epoch": 0.21149490878613336, "grad_norm": 8.206071853637695, "learning_rate": 4.229754149032289e-06, "loss": 0.6986, "step": 35580 }, { "epoch": 0.21155435086280175, "grad_norm": 8.479170799255371, "learning_rate": 4.230942983498978e-06, "loss": 0.7122, "step": 35590 }, { "epoch": 0.21161379293947014, "grad_norm": 6.965684413909912, "learning_rate": 4.232131817965667e-06, "loss": 0.69, "step": 35600 }, { "epoch": 0.21167323501613852, "grad_norm": 8.732539176940918, "learning_rate": 4.233320652432356e-06, "loss": 0.6633, "step": 35610 }, { "epoch": 0.2117326770928069, "grad_norm": 8.393752098083496, "learning_rate": 4.234509486899045e-06, "loss": 0.6512, "step": 35620 }, { "epoch": 0.2117921191694753, "grad_norm": 10.570051193237305, "learning_rate": 4.235698321365733e-06, "loss": 0.6848, "step": 35630 }, { "epoch": 0.21185156124614368, "grad_norm": 8.425925254821777, "learning_rate": 4.236887155832422e-06, "loss": 0.6872, "step": 35640 }, { "epoch": 0.2119110033228121, "grad_norm": 7.949840545654297, "learning_rate": 4.238075990299111e-06, "loss": 0.6677, "step": 35650 }, { "epoch": 0.21197044539948048, "grad_norm": 6.882760524749756, "learning_rate": 4.2392648247658e-06, "loss": 0.7067, "step": 35660 }, { "epoch": 0.21202988747614887, "grad_norm": 10.462780952453613, "learning_rate": 4.240453659232489e-06, "loss": 0.7811, "step": 35670 }, { "epoch": 0.21208932955281726, "grad_norm": 9.100469589233398, "learning_rate": 4.241642493699178e-06, "loss": 0.6834, "step": 35680 }, { "epoch": 0.21214877162948564, "grad_norm": 7.3068766593933105, "learning_rate": 4.242831328165866e-06, "loss": 0.7117, "step": 35690 }, { "epoch": 0.21220821370615403, "grad_norm": 8.16795825958252, "learning_rate": 4.244020162632555e-06, "loss": 0.6885, "step": 35700 }, { "epoch": 0.21226765578282242, "grad_norm": 9.112385749816895, "learning_rate": 4.245208997099244e-06, "loss": 0.6313, "step": 35710 }, { "epoch": 0.21232709785949083, "grad_norm": 11.335278511047363, "learning_rate": 4.246397831565933e-06, "loss": 0.7348, "step": 35720 }, { "epoch": 0.21238653993615922, "grad_norm": 7.218667507171631, "learning_rate": 4.247586666032622e-06, "loss": 0.7129, "step": 35730 }, { "epoch": 0.2124459820128276, "grad_norm": 7.577578067779541, "learning_rate": 4.248775500499311e-06, "loss": 0.6734, "step": 35740 }, { "epoch": 0.212505424089496, "grad_norm": 8.78688907623291, "learning_rate": 4.249964334966e-06, "loss": 0.6736, "step": 35750 }, { "epoch": 0.21256486616616438, "grad_norm": 8.035847663879395, "learning_rate": 4.251153169432689e-06, "loss": 0.6893, "step": 35760 }, { "epoch": 0.21262430824283277, "grad_norm": 7.475564479827881, "learning_rate": 4.252342003899377e-06, "loss": 0.698, "step": 35770 }, { "epoch": 0.21268375031950115, "grad_norm": 9.922664642333984, "learning_rate": 4.253530838366066e-06, "loss": 0.6374, "step": 35780 }, { "epoch": 0.21274319239616954, "grad_norm": 10.376965522766113, "learning_rate": 4.254719672832755e-06, "loss": 0.7517, "step": 35790 }, { "epoch": 0.21280263447283795, "grad_norm": 8.511107444763184, "learning_rate": 4.255908507299444e-06, "loss": 0.6922, "step": 35800 }, { "epoch": 0.21286207654950634, "grad_norm": 6.492507457733154, "learning_rate": 4.257097341766133e-06, "loss": 0.6545, "step": 35810 }, { "epoch": 0.21292151862617473, "grad_norm": 7.80963659286499, "learning_rate": 4.258286176232822e-06, "loss": 0.6923, "step": 35820 }, { "epoch": 0.21298096070284311, "grad_norm": 10.153646469116211, "learning_rate": 4.2594750106995105e-06, "loss": 0.7332, "step": 35830 }, { "epoch": 0.2130404027795115, "grad_norm": 8.662178993225098, "learning_rate": 4.2606638451661995e-06, "loss": 0.6951, "step": 35840 }, { "epoch": 0.2130998448561799, "grad_norm": 9.721137046813965, "learning_rate": 4.261852679632888e-06, "loss": 0.6842, "step": 35850 }, { "epoch": 0.21315928693284827, "grad_norm": 9.057190895080566, "learning_rate": 4.263041514099577e-06, "loss": 0.712, "step": 35860 }, { "epoch": 0.2132187290095167, "grad_norm": 9.174226760864258, "learning_rate": 4.264230348566266e-06, "loss": 0.7132, "step": 35870 }, { "epoch": 0.21327817108618508, "grad_norm": 8.14555549621582, "learning_rate": 4.265419183032955e-06, "loss": 0.711, "step": 35880 }, { "epoch": 0.21333761316285346, "grad_norm": 8.959129333496094, "learning_rate": 4.266608017499644e-06, "loss": 0.7468, "step": 35890 }, { "epoch": 0.21339705523952185, "grad_norm": 9.986123085021973, "learning_rate": 4.267796851966333e-06, "loss": 0.6598, "step": 35900 }, { "epoch": 0.21345649731619024, "grad_norm": 8.596148490905762, "learning_rate": 4.268985686433021e-06, "loss": 0.6953, "step": 35910 }, { "epoch": 0.21351593939285862, "grad_norm": 7.451037883758545, "learning_rate": 4.27017452089971e-06, "loss": 0.6071, "step": 35920 }, { "epoch": 0.213575381469527, "grad_norm": 8.29366683959961, "learning_rate": 4.271363355366399e-06, "loss": 0.695, "step": 35930 }, { "epoch": 0.21363482354619542, "grad_norm": 8.090673446655273, "learning_rate": 4.272552189833088e-06, "loss": 0.7168, "step": 35940 }, { "epoch": 0.2136942656228638, "grad_norm": 7.638631343841553, "learning_rate": 4.273741024299777e-06, "loss": 0.6971, "step": 35950 }, { "epoch": 0.2137537076995322, "grad_norm": 7.375389099121094, "learning_rate": 4.274929858766466e-06, "loss": 0.6704, "step": 35960 }, { "epoch": 0.21381314977620058, "grad_norm": 7.477006912231445, "learning_rate": 4.276118693233155e-06, "loss": 0.745, "step": 35970 }, { "epoch": 0.21387259185286897, "grad_norm": 9.317874908447266, "learning_rate": 4.277307527699844e-06, "loss": 0.6727, "step": 35980 }, { "epoch": 0.21393203392953736, "grad_norm": 7.109043598175049, "learning_rate": 4.278496362166532e-06, "loss": 0.6904, "step": 35990 }, { "epoch": 0.21399147600620574, "grad_norm": 8.535690307617188, "learning_rate": 4.279685196633221e-06, "loss": 0.6936, "step": 36000 }, { "epoch": 0.21405091808287413, "grad_norm": 7.646994113922119, "learning_rate": 4.2808740310999095e-06, "loss": 0.6974, "step": 36010 }, { "epoch": 0.21411036015954255, "grad_norm": 7.688228130340576, "learning_rate": 4.282062865566599e-06, "loss": 0.6541, "step": 36020 }, { "epoch": 0.21416980223621093, "grad_norm": 8.465219497680664, "learning_rate": 4.283251700033288e-06, "loss": 0.6941, "step": 36030 }, { "epoch": 0.21422924431287932, "grad_norm": 9.12566089630127, "learning_rate": 4.284440534499977e-06, "loss": 0.6922, "step": 36040 }, { "epoch": 0.2142886863895477, "grad_norm": 9.655292510986328, "learning_rate": 4.285629368966665e-06, "loss": 0.7109, "step": 36050 }, { "epoch": 0.2143481284662161, "grad_norm": 8.733342170715332, "learning_rate": 4.286818203433354e-06, "loss": 0.6693, "step": 36060 }, { "epoch": 0.21440757054288448, "grad_norm": 8.220255851745605, "learning_rate": 4.288007037900043e-06, "loss": 0.6818, "step": 36070 }, { "epoch": 0.21446701261955287, "grad_norm": 9.192594528198242, "learning_rate": 4.289195872366732e-06, "loss": 0.675, "step": 36080 }, { "epoch": 0.21452645469622128, "grad_norm": 7.942898750305176, "learning_rate": 4.290384706833421e-06, "loss": 0.6773, "step": 36090 }, { "epoch": 0.21458589677288967, "grad_norm": 9.4362211227417, "learning_rate": 4.29157354130011e-06, "loss": 0.6592, "step": 36100 }, { "epoch": 0.21464533884955805, "grad_norm": 7.992881774902344, "learning_rate": 4.292762375766799e-06, "loss": 0.7597, "step": 36110 }, { "epoch": 0.21470478092622644, "grad_norm": 8.267328262329102, "learning_rate": 4.293951210233488e-06, "loss": 0.7191, "step": 36120 }, { "epoch": 0.21476422300289483, "grad_norm": 7.358280181884766, "learning_rate": 4.295140044700176e-06, "loss": 0.7059, "step": 36130 }, { "epoch": 0.21482366507956321, "grad_norm": 7.051141738891602, "learning_rate": 4.296328879166865e-06, "loss": 0.6414, "step": 36140 }, { "epoch": 0.2148831071562316, "grad_norm": 8.828817367553711, "learning_rate": 4.297517713633554e-06, "loss": 0.6927, "step": 36150 }, { "epoch": 0.2149425492329, "grad_norm": 8.860917091369629, "learning_rate": 4.298706548100243e-06, "loss": 0.6902, "step": 36160 }, { "epoch": 0.2150019913095684, "grad_norm": 6.840452671051025, "learning_rate": 4.2998953825669315e-06, "loss": 0.6676, "step": 36170 }, { "epoch": 0.2150614333862368, "grad_norm": 8.09963321685791, "learning_rate": 4.3010842170336205e-06, "loss": 0.6563, "step": 36180 }, { "epoch": 0.21512087546290518, "grad_norm": 10.145075798034668, "learning_rate": 4.302273051500309e-06, "loss": 0.7119, "step": 36190 }, { "epoch": 0.21518031753957356, "grad_norm": 8.184700965881348, "learning_rate": 4.303461885966998e-06, "loss": 0.669, "step": 36200 }, { "epoch": 0.21523975961624195, "grad_norm": 7.692727565765381, "learning_rate": 4.304650720433687e-06, "loss": 0.7037, "step": 36210 }, { "epoch": 0.21529920169291034, "grad_norm": 7.640989303588867, "learning_rate": 4.305839554900376e-06, "loss": 0.6753, "step": 36220 }, { "epoch": 0.21535864376957872, "grad_norm": 7.209868431091309, "learning_rate": 4.307028389367065e-06, "loss": 0.6871, "step": 36230 }, { "epoch": 0.21541808584624714, "grad_norm": 7.740512847900391, "learning_rate": 4.308217223833754e-06, "loss": 0.6507, "step": 36240 }, { "epoch": 0.21547752792291552, "grad_norm": 8.207073211669922, "learning_rate": 4.309406058300443e-06, "loss": 0.6899, "step": 36250 }, { "epoch": 0.2155369699995839, "grad_norm": 8.98379898071289, "learning_rate": 4.310594892767132e-06, "loss": 0.6643, "step": 36260 }, { "epoch": 0.2155964120762523, "grad_norm": 9.293783187866211, "learning_rate": 4.31178372723382e-06, "loss": 0.7413, "step": 36270 }, { "epoch": 0.21565585415292068, "grad_norm": 7.592600345611572, "learning_rate": 4.312972561700509e-06, "loss": 0.7212, "step": 36280 }, { "epoch": 0.21571529622958907, "grad_norm": 8.551528930664062, "learning_rate": 4.314161396167198e-06, "loss": 0.6798, "step": 36290 }, { "epoch": 0.21577473830625746, "grad_norm": 8.75912857055664, "learning_rate": 4.315350230633887e-06, "loss": 0.6983, "step": 36300 }, { "epoch": 0.21583418038292584, "grad_norm": 8.230142593383789, "learning_rate": 4.316539065100576e-06, "loss": 0.6904, "step": 36310 }, { "epoch": 0.21589362245959426, "grad_norm": 8.864813804626465, "learning_rate": 4.317727899567265e-06, "loss": 0.7397, "step": 36320 }, { "epoch": 0.21595306453626265, "grad_norm": 9.308379173278809, "learning_rate": 4.3189167340339535e-06, "loss": 0.7448, "step": 36330 }, { "epoch": 0.21601250661293103, "grad_norm": 9.01162052154541, "learning_rate": 4.3201055685006424e-06, "loss": 0.6781, "step": 36340 }, { "epoch": 0.21607194868959942, "grad_norm": 8.583338737487793, "learning_rate": 4.3212944029673305e-06, "loss": 0.6983, "step": 36350 }, { "epoch": 0.2161313907662678, "grad_norm": 8.906699180603027, "learning_rate": 4.3224832374340195e-06, "loss": 0.7147, "step": 36360 }, { "epoch": 0.2161908328429362, "grad_norm": 9.538161277770996, "learning_rate": 4.323672071900709e-06, "loss": 0.7257, "step": 36370 }, { "epoch": 0.21625027491960458, "grad_norm": 9.303590774536133, "learning_rate": 4.324860906367398e-06, "loss": 0.7225, "step": 36380 }, { "epoch": 0.216309716996273, "grad_norm": 9.233503341674805, "learning_rate": 4.326049740834087e-06, "loss": 0.6501, "step": 36390 }, { "epoch": 0.21636915907294138, "grad_norm": 6.928799629211426, "learning_rate": 4.327238575300776e-06, "loss": 0.7204, "step": 36400 }, { "epoch": 0.21642860114960977, "grad_norm": 8.151749610900879, "learning_rate": 4.328427409767464e-06, "loss": 0.7554, "step": 36410 }, { "epoch": 0.21648804322627815, "grad_norm": 8.784375190734863, "learning_rate": 4.329616244234153e-06, "loss": 0.681, "step": 36420 }, { "epoch": 0.21654748530294654, "grad_norm": 7.010791778564453, "learning_rate": 4.330805078700842e-06, "loss": 0.7029, "step": 36430 }, { "epoch": 0.21660692737961493, "grad_norm": 7.075929641723633, "learning_rate": 4.331993913167531e-06, "loss": 0.7038, "step": 36440 }, { "epoch": 0.21666636945628331, "grad_norm": 9.385164260864258, "learning_rate": 4.33318274763422e-06, "loss": 0.7131, "step": 36450 }, { "epoch": 0.21672581153295173, "grad_norm": 11.426904678344727, "learning_rate": 4.334371582100909e-06, "loss": 0.7088, "step": 36460 }, { "epoch": 0.21678525360962012, "grad_norm": 8.226862907409668, "learning_rate": 4.335560416567598e-06, "loss": 0.6422, "step": 36470 }, { "epoch": 0.2168446956862885, "grad_norm": 9.357280731201172, "learning_rate": 4.336749251034287e-06, "loss": 0.7476, "step": 36480 }, { "epoch": 0.2169041377629569, "grad_norm": 6.5946807861328125, "learning_rate": 4.337938085500975e-06, "loss": 0.7575, "step": 36490 }, { "epoch": 0.21696357983962528, "grad_norm": 8.81957721710205, "learning_rate": 4.339126919967664e-06, "loss": 0.7464, "step": 36500 }, { "epoch": 0.21702302191629366, "grad_norm": 9.24905014038086, "learning_rate": 4.3403157544343525e-06, "loss": 0.7186, "step": 36510 }, { "epoch": 0.21708246399296205, "grad_norm": 8.48611068725586, "learning_rate": 4.3415045889010414e-06, "loss": 0.6202, "step": 36520 }, { "epoch": 0.21714190606963044, "grad_norm": 9.652534484863281, "learning_rate": 4.34269342336773e-06, "loss": 0.6847, "step": 36530 }, { "epoch": 0.21720134814629885, "grad_norm": 8.012351989746094, "learning_rate": 4.34388225783442e-06, "loss": 0.6885, "step": 36540 }, { "epoch": 0.21726079022296724, "grad_norm": 9.012405395507812, "learning_rate": 4.345071092301108e-06, "loss": 0.7399, "step": 36550 }, { "epoch": 0.21732023229963562, "grad_norm": 9.064499855041504, "learning_rate": 4.346259926767797e-06, "loss": 0.6635, "step": 36560 }, { "epoch": 0.217379674376304, "grad_norm": 8.738031387329102, "learning_rate": 4.347448761234486e-06, "loss": 0.6988, "step": 36570 }, { "epoch": 0.2174391164529724, "grad_norm": 7.926553249359131, "learning_rate": 4.348637595701175e-06, "loss": 0.6911, "step": 36580 }, { "epoch": 0.21749855852964078, "grad_norm": 9.984857559204102, "learning_rate": 4.349826430167864e-06, "loss": 0.7027, "step": 36590 }, { "epoch": 0.21755800060630917, "grad_norm": 8.385663986206055, "learning_rate": 4.351015264634553e-06, "loss": 0.7479, "step": 36600 }, { "epoch": 0.21761744268297759, "grad_norm": 8.493006706237793, "learning_rate": 4.352204099101242e-06, "loss": 0.6971, "step": 36610 }, { "epoch": 0.21767688475964597, "grad_norm": 7.901101589202881, "learning_rate": 4.353392933567931e-06, "loss": 0.6261, "step": 36620 }, { "epoch": 0.21773632683631436, "grad_norm": 8.66308879852295, "learning_rate": 4.354581768034619e-06, "loss": 0.6734, "step": 36630 }, { "epoch": 0.21779576891298275, "grad_norm": 8.435076713562012, "learning_rate": 4.355770602501308e-06, "loss": 0.7316, "step": 36640 }, { "epoch": 0.21785521098965113, "grad_norm": 12.470442771911621, "learning_rate": 4.356959436967997e-06, "loss": 0.6818, "step": 36650 }, { "epoch": 0.21791465306631952, "grad_norm": 9.128564834594727, "learning_rate": 4.3581482714346856e-06, "loss": 0.647, "step": 36660 }, { "epoch": 0.2179740951429879, "grad_norm": 9.269732475280762, "learning_rate": 4.3593371059013745e-06, "loss": 0.7297, "step": 36670 }, { "epoch": 0.2180335372196563, "grad_norm": 10.126591682434082, "learning_rate": 4.3605259403680634e-06, "loss": 0.741, "step": 36680 }, { "epoch": 0.2180929792963247, "grad_norm": 5.990062236785889, "learning_rate": 4.361714774834752e-06, "loss": 0.6411, "step": 36690 }, { "epoch": 0.2181524213729931, "grad_norm": 7.539611339569092, "learning_rate": 4.362903609301441e-06, "loss": 0.6648, "step": 36700 }, { "epoch": 0.21821186344966148, "grad_norm": 9.33444881439209, "learning_rate": 4.36409244376813e-06, "loss": 0.6927, "step": 36710 }, { "epoch": 0.21827130552632987, "grad_norm": 8.763957023620605, "learning_rate": 4.365281278234819e-06, "loss": 0.7174, "step": 36720 }, { "epoch": 0.21833074760299825, "grad_norm": 8.55978012084961, "learning_rate": 4.366470112701508e-06, "loss": 0.6616, "step": 36730 }, { "epoch": 0.21839018967966664, "grad_norm": 7.831992149353027, "learning_rate": 4.367658947168197e-06, "loss": 0.709, "step": 36740 }, { "epoch": 0.21844963175633503, "grad_norm": 7.930298805236816, "learning_rate": 4.368847781634886e-06, "loss": 0.6613, "step": 36750 }, { "epoch": 0.21850907383300344, "grad_norm": 6.625887870788574, "learning_rate": 4.370036616101575e-06, "loss": 0.6538, "step": 36760 }, { "epoch": 0.21856851590967183, "grad_norm": 7.933381080627441, "learning_rate": 4.371225450568263e-06, "loss": 0.665, "step": 36770 }, { "epoch": 0.21862795798634022, "grad_norm": 7.709587097167969, "learning_rate": 4.372414285034952e-06, "loss": 0.6868, "step": 36780 }, { "epoch": 0.2186874000630086, "grad_norm": 8.156760215759277, "learning_rate": 4.373603119501641e-06, "loss": 0.6093, "step": 36790 }, { "epoch": 0.218746842139677, "grad_norm": 7.5474653244018555, "learning_rate": 4.37479195396833e-06, "loss": 0.7126, "step": 36800 }, { "epoch": 0.21880628421634538, "grad_norm": 8.86422061920166, "learning_rate": 4.375980788435019e-06, "loss": 0.721, "step": 36810 }, { "epoch": 0.21886572629301376, "grad_norm": 7.742209434509277, "learning_rate": 4.3771696229017076e-06, "loss": 0.6975, "step": 36820 }, { "epoch": 0.21892516836968218, "grad_norm": 9.106441497802734, "learning_rate": 4.3783584573683965e-06, "loss": 0.7381, "step": 36830 }, { "epoch": 0.21898461044635056, "grad_norm": 8.07437515258789, "learning_rate": 4.379547291835085e-06, "loss": 0.6488, "step": 36840 }, { "epoch": 0.21904405252301895, "grad_norm": 9.559626579284668, "learning_rate": 4.3807361263017735e-06, "loss": 0.6909, "step": 36850 }, { "epoch": 0.21910349459968734, "grad_norm": 9.81507682800293, "learning_rate": 4.3819249607684624e-06, "loss": 0.7157, "step": 36860 }, { "epoch": 0.21916293667635572, "grad_norm": 8.932745933532715, "learning_rate": 4.383113795235151e-06, "loss": 0.6826, "step": 36870 }, { "epoch": 0.2192223787530241, "grad_norm": 9.669353485107422, "learning_rate": 4.384302629701841e-06, "loss": 0.6732, "step": 36880 }, { "epoch": 0.2192818208296925, "grad_norm": 10.218859672546387, "learning_rate": 4.38549146416853e-06, "loss": 0.7138, "step": 36890 }, { "epoch": 0.21934126290636088, "grad_norm": 11.16133975982666, "learning_rate": 4.386680298635219e-06, "loss": 0.7314, "step": 36900 }, { "epoch": 0.2194007049830293, "grad_norm": 7.606701374053955, "learning_rate": 4.387869133101907e-06, "loss": 0.6621, "step": 36910 }, { "epoch": 0.21946014705969769, "grad_norm": 10.302019119262695, "learning_rate": 4.389057967568596e-06, "loss": 0.6881, "step": 36920 }, { "epoch": 0.21951958913636607, "grad_norm": 7.825794696807861, "learning_rate": 4.390246802035285e-06, "loss": 0.6577, "step": 36930 }, { "epoch": 0.21957903121303446, "grad_norm": 9.057568550109863, "learning_rate": 4.391435636501974e-06, "loss": 0.6606, "step": 36940 }, { "epoch": 0.21963847328970285, "grad_norm": 12.173158645629883, "learning_rate": 4.392624470968663e-06, "loss": 0.6769, "step": 36950 }, { "epoch": 0.21969791536637123, "grad_norm": 10.001765251159668, "learning_rate": 4.393813305435352e-06, "loss": 0.6784, "step": 36960 }, { "epoch": 0.21975735744303962, "grad_norm": 8.99548053741455, "learning_rate": 4.395002139902041e-06, "loss": 0.6508, "step": 36970 }, { "epoch": 0.21981679951970803, "grad_norm": 8.515701293945312, "learning_rate": 4.3961909743687296e-06, "loss": 0.6604, "step": 36980 }, { "epoch": 0.21987624159637642, "grad_norm": 9.93763542175293, "learning_rate": 4.397379808835418e-06, "loss": 0.7071, "step": 36990 }, { "epoch": 0.2199356836730448, "grad_norm": 8.27446460723877, "learning_rate": 4.3985686433021066e-06, "loss": 0.7547, "step": 37000 }, { "epoch": 0.2199951257497132, "grad_norm": 8.450361251831055, "learning_rate": 4.3997574777687955e-06, "loss": 0.7144, "step": 37010 }, { "epoch": 0.22005456782638158, "grad_norm": 9.456183433532715, "learning_rate": 4.400946312235484e-06, "loss": 0.7113, "step": 37020 }, { "epoch": 0.22011400990304997, "grad_norm": 9.354228019714355, "learning_rate": 4.402135146702173e-06, "loss": 0.6887, "step": 37030 }, { "epoch": 0.22017345197971835, "grad_norm": 9.691353797912598, "learning_rate": 4.403323981168862e-06, "loss": 0.6459, "step": 37040 }, { "epoch": 0.22023289405638674, "grad_norm": 8.114908218383789, "learning_rate": 4.404512815635551e-06, "loss": 0.6818, "step": 37050 }, { "epoch": 0.22029233613305516, "grad_norm": 7.8051838874816895, "learning_rate": 4.40570165010224e-06, "loss": 0.703, "step": 37060 }, { "epoch": 0.22035177820972354, "grad_norm": 7.017024993896484, "learning_rate": 4.406890484568929e-06, "loss": 0.6551, "step": 37070 }, { "epoch": 0.22041122028639193, "grad_norm": 10.06733226776123, "learning_rate": 4.408079319035618e-06, "loss": 0.685, "step": 37080 }, { "epoch": 0.22047066236306032, "grad_norm": 9.254956245422363, "learning_rate": 4.409268153502307e-06, "loss": 0.6974, "step": 37090 }, { "epoch": 0.2205301044397287, "grad_norm": 8.563958168029785, "learning_rate": 4.410456987968996e-06, "loss": 0.6757, "step": 37100 }, { "epoch": 0.2205895465163971, "grad_norm": 9.2553071975708, "learning_rate": 4.411645822435685e-06, "loss": 0.6814, "step": 37110 }, { "epoch": 0.22064898859306548, "grad_norm": 7.547976493835449, "learning_rate": 4.412834656902374e-06, "loss": 0.6335, "step": 37120 }, { "epoch": 0.2207084306697339, "grad_norm": 8.330611228942871, "learning_rate": 4.414023491369062e-06, "loss": 0.6748, "step": 37130 }, { "epoch": 0.22076787274640228, "grad_norm": 6.510527610778809, "learning_rate": 4.415212325835751e-06, "loss": 0.7482, "step": 37140 }, { "epoch": 0.22082731482307066, "grad_norm": 9.636815071105957, "learning_rate": 4.41640116030244e-06, "loss": 0.706, "step": 37150 }, { "epoch": 0.22088675689973905, "grad_norm": 8.565629005432129, "learning_rate": 4.4175899947691286e-06, "loss": 0.6749, "step": 37160 }, { "epoch": 0.22094619897640744, "grad_norm": 9.057531356811523, "learning_rate": 4.4187788292358175e-06, "loss": 0.6963, "step": 37170 }, { "epoch": 0.22100564105307582, "grad_norm": 6.472077369689941, "learning_rate": 4.419967663702506e-06, "loss": 0.7232, "step": 37180 }, { "epoch": 0.2210650831297442, "grad_norm": 5.196903228759766, "learning_rate": 4.421156498169195e-06, "loss": 0.6972, "step": 37190 }, { "epoch": 0.2211245252064126, "grad_norm": 7.620884418487549, "learning_rate": 4.422345332635884e-06, "loss": 0.7427, "step": 37200 }, { "epoch": 0.221183967283081, "grad_norm": 9.51110553741455, "learning_rate": 4.423534167102573e-06, "loss": 0.7159, "step": 37210 }, { "epoch": 0.2212434093597494, "grad_norm": 8.78693962097168, "learning_rate": 4.424723001569261e-06, "loss": 0.6493, "step": 37220 }, { "epoch": 0.22130285143641779, "grad_norm": 7.779882431030273, "learning_rate": 4.425911836035951e-06, "loss": 0.674, "step": 37230 }, { "epoch": 0.22136229351308617, "grad_norm": 8.616762161254883, "learning_rate": 4.42710067050264e-06, "loss": 0.7364, "step": 37240 }, { "epoch": 0.22142173558975456, "grad_norm": 9.310775756835938, "learning_rate": 4.428289504969329e-06, "loss": 0.6594, "step": 37250 }, { "epoch": 0.22148117766642295, "grad_norm": 8.937012672424316, "learning_rate": 4.429478339436018e-06, "loss": 0.789, "step": 37260 }, { "epoch": 0.22154061974309133, "grad_norm": 7.164381980895996, "learning_rate": 4.430667173902706e-06, "loss": 0.6778, "step": 37270 }, { "epoch": 0.22160006181975975, "grad_norm": 8.679638862609863, "learning_rate": 4.431856008369395e-06, "loss": 0.6809, "step": 37280 }, { "epoch": 0.22165950389642813, "grad_norm": 7.689466953277588, "learning_rate": 4.433044842836084e-06, "loss": 0.6797, "step": 37290 }, { "epoch": 0.22171894597309652, "grad_norm": 8.355854988098145, "learning_rate": 4.434233677302773e-06, "loss": 0.6257, "step": 37300 }, { "epoch": 0.2217783880497649, "grad_norm": 9.336512565612793, "learning_rate": 4.435422511769462e-06, "loss": 0.7323, "step": 37310 }, { "epoch": 0.2218378301264333, "grad_norm": 7.621802806854248, "learning_rate": 4.4366113462361505e-06, "loss": 0.6861, "step": 37320 }, { "epoch": 0.22189727220310168, "grad_norm": 5.307818412780762, "learning_rate": 4.4378001807028395e-06, "loss": 0.6464, "step": 37330 }, { "epoch": 0.22195671427977007, "grad_norm": 7.849423885345459, "learning_rate": 4.438989015169528e-06, "loss": 0.6985, "step": 37340 }, { "epoch": 0.22201615635643848, "grad_norm": 9.679911613464355, "learning_rate": 4.4401778496362165e-06, "loss": 0.7285, "step": 37350 }, { "epoch": 0.22207559843310687, "grad_norm": 6.089513301849365, "learning_rate": 4.441366684102905e-06, "loss": 0.7627, "step": 37360 }, { "epoch": 0.22213504050977526, "grad_norm": 7.7702555656433105, "learning_rate": 4.442555518569594e-06, "loss": 0.7438, "step": 37370 }, { "epoch": 0.22219448258644364, "grad_norm": 8.146449089050293, "learning_rate": 4.443744353036283e-06, "loss": 0.7225, "step": 37380 }, { "epoch": 0.22225392466311203, "grad_norm": 8.850458145141602, "learning_rate": 4.444933187502972e-06, "loss": 0.6725, "step": 37390 }, { "epoch": 0.22231336673978042, "grad_norm": 10.774715423583984, "learning_rate": 4.446122021969662e-06, "loss": 0.6923, "step": 37400 }, { "epoch": 0.2223728088164488, "grad_norm": 7.795690536499023, "learning_rate": 4.44731085643635e-06, "loss": 0.6658, "step": 37410 }, { "epoch": 0.2224322508931172, "grad_norm": 9.242084503173828, "learning_rate": 4.448499690903039e-06, "loss": 0.6741, "step": 37420 }, { "epoch": 0.2224916929697856, "grad_norm": 9.62494945526123, "learning_rate": 4.449688525369728e-06, "loss": 0.7329, "step": 37430 }, { "epoch": 0.222551135046454, "grad_norm": 9.439166069030762, "learning_rate": 4.450877359836417e-06, "loss": 0.6555, "step": 37440 }, { "epoch": 0.22261057712312238, "grad_norm": 7.414083480834961, "learning_rate": 4.452066194303106e-06, "loss": 0.6889, "step": 37450 }, { "epoch": 0.22267001919979076, "grad_norm": 12.83752155303955, "learning_rate": 4.453255028769795e-06, "loss": 0.7397, "step": 37460 }, { "epoch": 0.22272946127645915, "grad_norm": 8.619912147521973, "learning_rate": 4.454443863236484e-06, "loss": 0.7572, "step": 37470 }, { "epoch": 0.22278890335312754, "grad_norm": 7.51567268371582, "learning_rate": 4.4556326977031725e-06, "loss": 0.6757, "step": 37480 }, { "epoch": 0.22284834542979592, "grad_norm": 8.623817443847656, "learning_rate": 4.456821532169861e-06, "loss": 0.6235, "step": 37490 }, { "epoch": 0.22290778750646434, "grad_norm": 9.120633125305176, "learning_rate": 4.4580103666365495e-06, "loss": 0.7075, "step": 37500 }, { "epoch": 0.22296722958313273, "grad_norm": 8.748888969421387, "learning_rate": 4.4591992011032385e-06, "loss": 0.7172, "step": 37510 }, { "epoch": 0.2230266716598011, "grad_norm": 7.171222686767578, "learning_rate": 4.460388035569927e-06, "loss": 0.7288, "step": 37520 }, { "epoch": 0.2230861137364695, "grad_norm": 10.251862525939941, "learning_rate": 4.461576870036616e-06, "loss": 0.7069, "step": 37530 }, { "epoch": 0.22314555581313789, "grad_norm": 7.477294445037842, "learning_rate": 4.462765704503305e-06, "loss": 0.7437, "step": 37540 }, { "epoch": 0.22320499788980627, "grad_norm": 7.879284381866455, "learning_rate": 4.463954538969994e-06, "loss": 0.6928, "step": 37550 }, { "epoch": 0.22326443996647466, "grad_norm": 9.726171493530273, "learning_rate": 4.465143373436683e-06, "loss": 0.6778, "step": 37560 }, { "epoch": 0.22332388204314305, "grad_norm": 8.325435638427734, "learning_rate": 4.466332207903372e-06, "loss": 0.7717, "step": 37570 }, { "epoch": 0.22338332411981146, "grad_norm": 7.844427108764648, "learning_rate": 4.467521042370061e-06, "loss": 0.664, "step": 37580 }, { "epoch": 0.22344276619647985, "grad_norm": 8.092524528503418, "learning_rate": 4.46870987683675e-06, "loss": 0.7212, "step": 37590 }, { "epoch": 0.22350220827314823, "grad_norm": 10.570451736450195, "learning_rate": 4.469898711303439e-06, "loss": 0.6874, "step": 37600 }, { "epoch": 0.22356165034981662, "grad_norm": 9.155230522155762, "learning_rate": 4.471087545770128e-06, "loss": 0.7712, "step": 37610 }, { "epoch": 0.223621092426485, "grad_norm": 8.460199356079102, "learning_rate": 4.472276380236817e-06, "loss": 0.7163, "step": 37620 }, { "epoch": 0.2236805345031534, "grad_norm": 7.9442949295043945, "learning_rate": 4.473465214703505e-06, "loss": 0.7524, "step": 37630 }, { "epoch": 0.22373997657982178, "grad_norm": 8.489664077758789, "learning_rate": 4.474654049170194e-06, "loss": 0.6684, "step": 37640 }, { "epoch": 0.2237994186564902, "grad_norm": 7.464197635650635, "learning_rate": 4.475842883636883e-06, "loss": 0.7445, "step": 37650 }, { "epoch": 0.22385886073315858, "grad_norm": 10.519353866577148, "learning_rate": 4.4770317181035715e-06, "loss": 0.7127, "step": 37660 }, { "epoch": 0.22391830280982697, "grad_norm": 8.421918869018555, "learning_rate": 4.4782205525702605e-06, "loss": 0.6799, "step": 37670 }, { "epoch": 0.22397774488649536, "grad_norm": 18.380828857421875, "learning_rate": 4.479409387036949e-06, "loss": 0.7289, "step": 37680 }, { "epoch": 0.22403718696316374, "grad_norm": 7.133054256439209, "learning_rate": 4.480598221503638e-06, "loss": 0.6514, "step": 37690 }, { "epoch": 0.22409662903983213, "grad_norm": 10.6790771484375, "learning_rate": 4.481787055970327e-06, "loss": 0.7373, "step": 37700 }, { "epoch": 0.22415607111650052, "grad_norm": 9.889119148254395, "learning_rate": 4.482975890437016e-06, "loss": 0.6716, "step": 37710 }, { "epoch": 0.2242155131931689, "grad_norm": 8.94252872467041, "learning_rate": 4.484164724903704e-06, "loss": 0.6663, "step": 37720 }, { "epoch": 0.22427495526983732, "grad_norm": 7.780611991882324, "learning_rate": 4.485353559370393e-06, "loss": 0.7228, "step": 37730 }, { "epoch": 0.2243343973465057, "grad_norm": 10.839017868041992, "learning_rate": 4.486542393837082e-06, "loss": 0.6667, "step": 37740 }, { "epoch": 0.2243938394231741, "grad_norm": 9.382420539855957, "learning_rate": 4.487731228303772e-06, "loss": 0.7499, "step": 37750 }, { "epoch": 0.22445328149984248, "grad_norm": 10.139371871948242, "learning_rate": 4.488920062770461e-06, "loss": 0.7602, "step": 37760 }, { "epoch": 0.22451272357651086, "grad_norm": 8.438748359680176, "learning_rate": 4.490108897237149e-06, "loss": 0.6813, "step": 37770 }, { "epoch": 0.22457216565317925, "grad_norm": 8.510374069213867, "learning_rate": 4.491297731703838e-06, "loss": 0.6625, "step": 37780 }, { "epoch": 0.22463160772984764, "grad_norm": 6.654143333435059, "learning_rate": 4.492486566170527e-06, "loss": 0.6596, "step": 37790 }, { "epoch": 0.22469104980651605, "grad_norm": 7.963039875030518, "learning_rate": 4.493675400637216e-06, "loss": 0.6844, "step": 37800 }, { "epoch": 0.22475049188318444, "grad_norm": 8.340085983276367, "learning_rate": 4.494864235103905e-06, "loss": 0.6727, "step": 37810 }, { "epoch": 0.22480993395985283, "grad_norm": 6.8653106689453125, "learning_rate": 4.4960530695705935e-06, "loss": 0.6256, "step": 37820 }, { "epoch": 0.2248693760365212, "grad_norm": 8.728891372680664, "learning_rate": 4.4972419040372824e-06, "loss": 0.6956, "step": 37830 }, { "epoch": 0.2249288181131896, "grad_norm": 9.48134708404541, "learning_rate": 4.498430738503971e-06, "loss": 0.6931, "step": 37840 }, { "epoch": 0.22498826018985799, "grad_norm": 9.076054573059082, "learning_rate": 4.4996195729706595e-06, "loss": 0.7219, "step": 37850 }, { "epoch": 0.22504770226652637, "grad_norm": 7.943304061889648, "learning_rate": 4.500808407437348e-06, "loss": 0.6946, "step": 37860 }, { "epoch": 0.2251071443431948, "grad_norm": 9.202675819396973, "learning_rate": 4.501997241904037e-06, "loss": 0.7409, "step": 37870 }, { "epoch": 0.22516658641986317, "grad_norm": 7.7369256019592285, "learning_rate": 4.503186076370726e-06, "loss": 0.6613, "step": 37880 }, { "epoch": 0.22522602849653156, "grad_norm": 9.055058479309082, "learning_rate": 4.504374910837415e-06, "loss": 0.7238, "step": 37890 }, { "epoch": 0.22528547057319995, "grad_norm": 7.34884786605835, "learning_rate": 4.505563745304104e-06, "loss": 0.7374, "step": 37900 }, { "epoch": 0.22534491264986833, "grad_norm": 6.557397365570068, "learning_rate": 4.506752579770793e-06, "loss": 0.6897, "step": 37910 }, { "epoch": 0.22540435472653672, "grad_norm": 10.154483795166016, "learning_rate": 4.507941414237482e-06, "loss": 0.6606, "step": 37920 }, { "epoch": 0.2254637968032051, "grad_norm": 9.459685325622559, "learning_rate": 4.509130248704171e-06, "loss": 0.6583, "step": 37930 }, { "epoch": 0.2255232388798735, "grad_norm": 6.900321960449219, "learning_rate": 4.51031908317086e-06, "loss": 0.6766, "step": 37940 }, { "epoch": 0.2255826809565419, "grad_norm": 7.510847091674805, "learning_rate": 4.511507917637549e-06, "loss": 0.7587, "step": 37950 }, { "epoch": 0.2256421230332103, "grad_norm": 8.205812454223633, "learning_rate": 4.512696752104238e-06, "loss": 0.6828, "step": 37960 }, { "epoch": 0.22570156510987868, "grad_norm": 8.684845924377441, "learning_rate": 4.513885586570927e-06, "loss": 0.7024, "step": 37970 }, { "epoch": 0.22576100718654707, "grad_norm": 8.661627769470215, "learning_rate": 4.5150744210376155e-06, "loss": 0.7002, "step": 37980 }, { "epoch": 0.22582044926321546, "grad_norm": 6.910728931427002, "learning_rate": 4.516263255504304e-06, "loss": 0.6435, "step": 37990 }, { "epoch": 0.22587989133988384, "grad_norm": 9.053297996520996, "learning_rate": 4.5174520899709925e-06, "loss": 0.6878, "step": 38000 }, { "epoch": 0.22593933341655223, "grad_norm": 9.776631355285645, "learning_rate": 4.5186409244376814e-06, "loss": 0.6817, "step": 38010 }, { "epoch": 0.22599877549322064, "grad_norm": 8.519208908081055, "learning_rate": 4.51982975890437e-06, "loss": 0.7137, "step": 38020 }, { "epoch": 0.22605821756988903, "grad_norm": 8.613984107971191, "learning_rate": 4.521018593371059e-06, "loss": 0.7188, "step": 38030 }, { "epoch": 0.22611765964655742, "grad_norm": 6.625540733337402, "learning_rate": 4.522207427837748e-06, "loss": 0.6871, "step": 38040 }, { "epoch": 0.2261771017232258, "grad_norm": 8.154424667358398, "learning_rate": 4.523396262304437e-06, "loss": 0.7016, "step": 38050 }, { "epoch": 0.2262365437998942, "grad_norm": 7.546502113342285, "learning_rate": 4.524585096771126e-06, "loss": 0.7357, "step": 38060 }, { "epoch": 0.22629598587656258, "grad_norm": 8.656229972839355, "learning_rate": 4.525773931237815e-06, "loss": 0.7461, "step": 38070 }, { "epoch": 0.22635542795323096, "grad_norm": 10.799324989318848, "learning_rate": 4.526962765704503e-06, "loss": 0.6906, "step": 38080 }, { "epoch": 0.22641487002989935, "grad_norm": 7.3555006980896, "learning_rate": 4.528151600171192e-06, "loss": 0.7194, "step": 38090 }, { "epoch": 0.22647431210656777, "grad_norm": 10.031246185302734, "learning_rate": 4.529340434637882e-06, "loss": 0.6928, "step": 38100 }, { "epoch": 0.22653375418323615, "grad_norm": 10.279217720031738, "learning_rate": 4.530529269104571e-06, "loss": 0.6986, "step": 38110 }, { "epoch": 0.22659319625990454, "grad_norm": 6.1378560066223145, "learning_rate": 4.53171810357126e-06, "loss": 0.693, "step": 38120 }, { "epoch": 0.22665263833657293, "grad_norm": 7.622157573699951, "learning_rate": 4.532906938037948e-06, "loss": 0.6853, "step": 38130 }, { "epoch": 0.2267120804132413, "grad_norm": 8.481618881225586, "learning_rate": 4.534095772504637e-06, "loss": 0.6768, "step": 38140 }, { "epoch": 0.2267715224899097, "grad_norm": 7.893089294433594, "learning_rate": 4.535284606971326e-06, "loss": 0.6861, "step": 38150 }, { "epoch": 0.22683096456657809, "grad_norm": 7.277538299560547, "learning_rate": 4.5364734414380145e-06, "loss": 0.6797, "step": 38160 }, { "epoch": 0.2268904066432465, "grad_norm": 8.177422523498535, "learning_rate": 4.5376622759047034e-06, "loss": 0.679, "step": 38170 }, { "epoch": 0.2269498487199149, "grad_norm": 8.265314102172852, "learning_rate": 4.538851110371392e-06, "loss": 0.7215, "step": 38180 }, { "epoch": 0.22700929079658327, "grad_norm": 9.285306930541992, "learning_rate": 4.540039944838081e-06, "loss": 0.6616, "step": 38190 }, { "epoch": 0.22706873287325166, "grad_norm": 8.413671493530273, "learning_rate": 4.54122877930477e-06, "loss": 0.688, "step": 38200 }, { "epoch": 0.22712817494992005, "grad_norm": 7.247154235839844, "learning_rate": 4.542417613771459e-06, "loss": 0.653, "step": 38210 }, { "epoch": 0.22718761702658843, "grad_norm": 8.704635620117188, "learning_rate": 4.543606448238147e-06, "loss": 0.673, "step": 38220 }, { "epoch": 0.22724705910325682, "grad_norm": 8.208245277404785, "learning_rate": 4.544795282704836e-06, "loss": 0.7073, "step": 38230 }, { "epoch": 0.22730650117992524, "grad_norm": 6.347534656524658, "learning_rate": 4.545984117171525e-06, "loss": 0.68, "step": 38240 }, { "epoch": 0.22736594325659362, "grad_norm": 8.565732955932617, "learning_rate": 4.547172951638214e-06, "loss": 0.7734, "step": 38250 }, { "epoch": 0.227425385333262, "grad_norm": 8.24436092376709, "learning_rate": 4.548361786104903e-06, "loss": 0.6626, "step": 38260 }, { "epoch": 0.2274848274099304, "grad_norm": 7.6415815353393555, "learning_rate": 4.549550620571592e-06, "loss": 0.7056, "step": 38270 }, { "epoch": 0.22754426948659878, "grad_norm": 7.3780694007873535, "learning_rate": 4.550739455038281e-06, "loss": 0.6986, "step": 38280 }, { "epoch": 0.22760371156326717, "grad_norm": 10.281756401062012, "learning_rate": 4.55192828950497e-06, "loss": 0.7236, "step": 38290 }, { "epoch": 0.22766315363993556, "grad_norm": 8.024797439575195, "learning_rate": 4.553117123971659e-06, "loss": 0.7272, "step": 38300 }, { "epoch": 0.22772259571660394, "grad_norm": 8.01915454864502, "learning_rate": 4.5543059584383476e-06, "loss": 0.7064, "step": 38310 }, { "epoch": 0.22778203779327236, "grad_norm": 8.247309684753418, "learning_rate": 4.5554947929050365e-06, "loss": 0.6969, "step": 38320 }, { "epoch": 0.22784147986994074, "grad_norm": 8.386565208435059, "learning_rate": 4.556683627371725e-06, "loss": 0.6971, "step": 38330 }, { "epoch": 0.22790092194660913, "grad_norm": 7.323107719421387, "learning_rate": 4.557872461838414e-06, "loss": 0.684, "step": 38340 }, { "epoch": 0.22796036402327752, "grad_norm": 8.564126968383789, "learning_rate": 4.559061296305103e-06, "loss": 0.7191, "step": 38350 }, { "epoch": 0.2280198060999459, "grad_norm": 7.917239189147949, "learning_rate": 4.560250130771791e-06, "loss": 0.6559, "step": 38360 }, { "epoch": 0.2280792481766143, "grad_norm": 10.983297348022461, "learning_rate": 4.56143896523848e-06, "loss": 0.7175, "step": 38370 }, { "epoch": 0.22813869025328268, "grad_norm": 10.255231857299805, "learning_rate": 4.562627799705169e-06, "loss": 0.7352, "step": 38380 }, { "epoch": 0.2281981323299511, "grad_norm": 6.959487438201904, "learning_rate": 4.563816634171858e-06, "loss": 0.7014, "step": 38390 }, { "epoch": 0.22825757440661948, "grad_norm": 7.633903503417969, "learning_rate": 4.565005468638547e-06, "loss": 0.6127, "step": 38400 }, { "epoch": 0.22831701648328787, "grad_norm": 8.058250427246094, "learning_rate": 4.566194303105236e-06, "loss": 0.6642, "step": 38410 }, { "epoch": 0.22837645855995625, "grad_norm": 9.019594192504883, "learning_rate": 4.567383137571925e-06, "loss": 0.6823, "step": 38420 }, { "epoch": 0.22843590063662464, "grad_norm": 8.481078147888184, "learning_rate": 4.568571972038614e-06, "loss": 0.6819, "step": 38430 }, { "epoch": 0.22849534271329303, "grad_norm": 8.551810264587402, "learning_rate": 4.569760806505303e-06, "loss": 0.7321, "step": 38440 }, { "epoch": 0.2285547847899614, "grad_norm": 8.545406341552734, "learning_rate": 4.570949640971992e-06, "loss": 0.748, "step": 38450 }, { "epoch": 0.2286142268666298, "grad_norm": 9.34431266784668, "learning_rate": 4.572138475438681e-06, "loss": 0.6644, "step": 38460 }, { "epoch": 0.22867366894329821, "grad_norm": 7.406508922576904, "learning_rate": 4.5733273099053696e-06, "loss": 0.6647, "step": 38470 }, { "epoch": 0.2287331110199666, "grad_norm": 8.433698654174805, "learning_rate": 4.5745161443720585e-06, "loss": 0.7434, "step": 38480 }, { "epoch": 0.228792553096635, "grad_norm": 8.354856491088867, "learning_rate": 4.5757049788387466e-06, "loss": 0.7255, "step": 38490 }, { "epoch": 0.22885199517330337, "grad_norm": 9.37910270690918, "learning_rate": 4.5768938133054355e-06, "loss": 0.7102, "step": 38500 }, { "epoch": 0.22891143724997176, "grad_norm": 8.353599548339844, "learning_rate": 4.578082647772124e-06, "loss": 0.6943, "step": 38510 }, { "epoch": 0.22897087932664015, "grad_norm": 7.0737433433532715, "learning_rate": 4.579271482238813e-06, "loss": 0.7006, "step": 38520 }, { "epoch": 0.22903032140330853, "grad_norm": 7.94521427154541, "learning_rate": 4.580460316705502e-06, "loss": 0.7178, "step": 38530 }, { "epoch": 0.22908976347997695, "grad_norm": 7.804477214813232, "learning_rate": 4.581649151172191e-06, "loss": 0.6726, "step": 38540 }, { "epoch": 0.22914920555664534, "grad_norm": 8.781293869018555, "learning_rate": 4.58283798563888e-06, "loss": 0.6618, "step": 38550 }, { "epoch": 0.22920864763331372, "grad_norm": 8.911231994628906, "learning_rate": 4.584026820105569e-06, "loss": 0.6986, "step": 38560 }, { "epoch": 0.2292680897099821, "grad_norm": 9.479604721069336, "learning_rate": 4.585215654572258e-06, "loss": 0.6875, "step": 38570 }, { "epoch": 0.2293275317866505, "grad_norm": 7.605013370513916, "learning_rate": 4.586404489038946e-06, "loss": 0.6591, "step": 38580 }, { "epoch": 0.22938697386331888, "grad_norm": 7.607852935791016, "learning_rate": 4.587593323505635e-06, "loss": 0.6742, "step": 38590 }, { "epoch": 0.22944641593998727, "grad_norm": 9.937321662902832, "learning_rate": 4.588782157972324e-06, "loss": 0.7443, "step": 38600 }, { "epoch": 0.22950585801665566, "grad_norm": 7.628820896148682, "learning_rate": 4.589970992439013e-06, "loss": 0.6458, "step": 38610 }, { "epoch": 0.22956530009332407, "grad_norm": 8.057891845703125, "learning_rate": 4.591159826905703e-06, "loss": 0.7062, "step": 38620 }, { "epoch": 0.22962474216999246, "grad_norm": 8.584589004516602, "learning_rate": 4.592348661372391e-06, "loss": 0.7445, "step": 38630 }, { "epoch": 0.22968418424666084, "grad_norm": 7.382524013519287, "learning_rate": 4.59353749583908e-06, "loss": 0.6791, "step": 38640 }, { "epoch": 0.22974362632332923, "grad_norm": 7.715440273284912, "learning_rate": 4.5947263303057686e-06, "loss": 0.7177, "step": 38650 }, { "epoch": 0.22980306839999762, "grad_norm": 7.55510950088501, "learning_rate": 4.5959151647724575e-06, "loss": 0.6921, "step": 38660 }, { "epoch": 0.229862510476666, "grad_norm": 7.291439533233643, "learning_rate": 4.597103999239146e-06, "loss": 0.712, "step": 38670 }, { "epoch": 0.2299219525533344, "grad_norm": 8.228468894958496, "learning_rate": 4.598292833705835e-06, "loss": 0.6128, "step": 38680 }, { "epoch": 0.2299813946300028, "grad_norm": 8.823992729187012, "learning_rate": 4.599481668172524e-06, "loss": 0.6928, "step": 38690 }, { "epoch": 0.2300408367066712, "grad_norm": 9.625330924987793, "learning_rate": 4.600670502639213e-06, "loss": 0.7099, "step": 38700 }, { "epoch": 0.23010027878333958, "grad_norm": 11.557609558105469, "learning_rate": 4.601859337105902e-06, "loss": 0.6609, "step": 38710 }, { "epoch": 0.23015972086000797, "grad_norm": 8.619593620300293, "learning_rate": 4.60304817157259e-06, "loss": 0.7391, "step": 38720 }, { "epoch": 0.23021916293667635, "grad_norm": 7.974786758422852, "learning_rate": 4.604237006039279e-06, "loss": 0.6901, "step": 38730 }, { "epoch": 0.23027860501334474, "grad_norm": 7.201611042022705, "learning_rate": 4.605425840505968e-06, "loss": 0.6229, "step": 38740 }, { "epoch": 0.23033804709001313, "grad_norm": 7.9569091796875, "learning_rate": 4.606614674972657e-06, "loss": 0.6936, "step": 38750 }, { "epoch": 0.23039748916668154, "grad_norm": 9.288722038269043, "learning_rate": 4.607803509439346e-06, "loss": 0.6896, "step": 38760 }, { "epoch": 0.23045693124334993, "grad_norm": 7.7223310470581055, "learning_rate": 4.608992343906035e-06, "loss": 0.6064, "step": 38770 }, { "epoch": 0.23051637332001831, "grad_norm": 8.237728118896484, "learning_rate": 4.610181178372724e-06, "loss": 0.681, "step": 38780 }, { "epoch": 0.2305758153966867, "grad_norm": 8.561017036437988, "learning_rate": 4.611370012839413e-06, "loss": 0.7294, "step": 38790 }, { "epoch": 0.2306352574733551, "grad_norm": 9.75402545928955, "learning_rate": 4.612558847306102e-06, "loss": 0.7194, "step": 38800 }, { "epoch": 0.23069469955002347, "grad_norm": 8.966198921203613, "learning_rate": 4.6137476817727905e-06, "loss": 0.6524, "step": 38810 }, { "epoch": 0.23075414162669186, "grad_norm": 8.749015808105469, "learning_rate": 4.6149365162394795e-06, "loss": 0.6635, "step": 38820 }, { "epoch": 0.23081358370336025, "grad_norm": 9.252405166625977, "learning_rate": 4.616125350706168e-06, "loss": 0.6764, "step": 38830 }, { "epoch": 0.23087302578002866, "grad_norm": 7.9425482749938965, "learning_rate": 4.617314185172857e-06, "loss": 0.7315, "step": 38840 }, { "epoch": 0.23093246785669705, "grad_norm": 9.101669311523438, "learning_rate": 4.618503019639546e-06, "loss": 0.7047, "step": 38850 }, { "epoch": 0.23099190993336544, "grad_norm": 8.43741226196289, "learning_rate": 4.619691854106234e-06, "loss": 0.6878, "step": 38860 }, { "epoch": 0.23105135201003382, "grad_norm": 7.90525484085083, "learning_rate": 4.620880688572923e-06, "loss": 0.6941, "step": 38870 }, { "epoch": 0.2311107940867022, "grad_norm": 6.646664142608643, "learning_rate": 4.622069523039612e-06, "loss": 0.633, "step": 38880 }, { "epoch": 0.2311702361633706, "grad_norm": 8.18752384185791, "learning_rate": 4.623258357506301e-06, "loss": 0.7077, "step": 38890 }, { "epoch": 0.23122967824003898, "grad_norm": 9.126336097717285, "learning_rate": 4.62444719197299e-06, "loss": 0.7259, "step": 38900 }, { "epoch": 0.2312891203167074, "grad_norm": 8.571087837219238, "learning_rate": 4.625636026439679e-06, "loss": 0.6289, "step": 38910 }, { "epoch": 0.23134856239337578, "grad_norm": 6.842051029205322, "learning_rate": 4.626824860906368e-06, "loss": 0.6478, "step": 38920 }, { "epoch": 0.23140800447004417, "grad_norm": 7.787590503692627, "learning_rate": 4.628013695373057e-06, "loss": 0.6838, "step": 38930 }, { "epoch": 0.23146744654671256, "grad_norm": 10.89023494720459, "learning_rate": 4.629202529839745e-06, "loss": 0.6616, "step": 38940 }, { "epoch": 0.23152688862338094, "grad_norm": 6.562757968902588, "learning_rate": 4.630391364306434e-06, "loss": 0.7464, "step": 38950 }, { "epoch": 0.23158633070004933, "grad_norm": 6.44589376449585, "learning_rate": 4.631580198773124e-06, "loss": 0.5969, "step": 38960 }, { "epoch": 0.23164577277671772, "grad_norm": 6.786981105804443, "learning_rate": 4.6327690332398125e-06, "loss": 0.7474, "step": 38970 }, { "epoch": 0.2317052148533861, "grad_norm": 8.617232322692871, "learning_rate": 4.6339578677065015e-06, "loss": 0.7057, "step": 38980 }, { "epoch": 0.23176465693005452, "grad_norm": 10.738865852355957, "learning_rate": 4.6351467021731895e-06, "loss": 0.7261, "step": 38990 }, { "epoch": 0.2318240990067229, "grad_norm": 8.465499877929688, "learning_rate": 4.6363355366398785e-06, "loss": 0.7062, "step": 39000 }, { "epoch": 0.2318835410833913, "grad_norm": 11.061320304870605, "learning_rate": 4.637524371106567e-06, "loss": 0.6987, "step": 39010 }, { "epoch": 0.23194298316005968, "grad_norm": 10.850637435913086, "learning_rate": 4.638713205573256e-06, "loss": 0.7062, "step": 39020 }, { "epoch": 0.23200242523672807, "grad_norm": 7.363103866577148, "learning_rate": 4.639902040039945e-06, "loss": 0.6943, "step": 39030 }, { "epoch": 0.23206186731339645, "grad_norm": 9.084160804748535, "learning_rate": 4.641090874506634e-06, "loss": 0.736, "step": 39040 }, { "epoch": 0.23212130939006484, "grad_norm": 8.435476303100586, "learning_rate": 4.642279708973323e-06, "loss": 0.7343, "step": 39050 }, { "epoch": 0.23218075146673325, "grad_norm": 10.321056365966797, "learning_rate": 4.643468543440012e-06, "loss": 0.6916, "step": 39060 }, { "epoch": 0.23224019354340164, "grad_norm": 7.492534160614014, "learning_rate": 4.644657377906701e-06, "loss": 0.6984, "step": 39070 }, { "epoch": 0.23229963562007003, "grad_norm": 8.4026460647583, "learning_rate": 4.645846212373389e-06, "loss": 0.711, "step": 39080 }, { "epoch": 0.23235907769673841, "grad_norm": 6.457662582397461, "learning_rate": 4.647035046840078e-06, "loss": 0.7069, "step": 39090 }, { "epoch": 0.2324185197734068, "grad_norm": 7.351002216339111, "learning_rate": 4.648223881306767e-06, "loss": 0.6223, "step": 39100 }, { "epoch": 0.2324779618500752, "grad_norm": 9.323783874511719, "learning_rate": 4.649412715773456e-06, "loss": 0.7299, "step": 39110 }, { "epoch": 0.23253740392674357, "grad_norm": 8.115191459655762, "learning_rate": 4.650601550240145e-06, "loss": 0.7102, "step": 39120 }, { "epoch": 0.232596846003412, "grad_norm": 6.652712821960449, "learning_rate": 4.651790384706834e-06, "loss": 0.6977, "step": 39130 }, { "epoch": 0.23265628808008038, "grad_norm": 6.949313640594482, "learning_rate": 4.652979219173523e-06, "loss": 0.6085, "step": 39140 }, { "epoch": 0.23271573015674876, "grad_norm": 8.280190467834473, "learning_rate": 4.6541680536402115e-06, "loss": 0.681, "step": 39150 }, { "epoch": 0.23277517223341715, "grad_norm": 7.141909599304199, "learning_rate": 4.6553568881069005e-06, "loss": 0.6982, "step": 39160 }, { "epoch": 0.23283461431008554, "grad_norm": 7.78299617767334, "learning_rate": 4.656545722573589e-06, "loss": 0.7462, "step": 39170 }, { "epoch": 0.23289405638675392, "grad_norm": 7.670844078063965, "learning_rate": 4.657734557040278e-06, "loss": 0.695, "step": 39180 }, { "epoch": 0.2329534984634223, "grad_norm": 9.957985877990723, "learning_rate": 4.658923391506967e-06, "loss": 0.6287, "step": 39190 }, { "epoch": 0.2330129405400907, "grad_norm": 8.243101119995117, "learning_rate": 4.660112225973656e-06, "loss": 0.6637, "step": 39200 }, { "epoch": 0.2330723826167591, "grad_norm": 7.6185503005981445, "learning_rate": 4.661301060440345e-06, "loss": 0.7184, "step": 39210 }, { "epoch": 0.2331318246934275, "grad_norm": 11.16602611541748, "learning_rate": 4.662489894907033e-06, "loss": 0.7324, "step": 39220 }, { "epoch": 0.23319126677009588, "grad_norm": 8.84933853149414, "learning_rate": 4.663678729373722e-06, "loss": 0.6725, "step": 39230 }, { "epoch": 0.23325070884676427, "grad_norm": 9.137585639953613, "learning_rate": 4.664867563840411e-06, "loss": 0.6765, "step": 39240 }, { "epoch": 0.23331015092343266, "grad_norm": 6.8804426193237305, "learning_rate": 4.6660563983071e-06, "loss": 0.7263, "step": 39250 }, { "epoch": 0.23336959300010104, "grad_norm": 9.431792259216309, "learning_rate": 4.667245232773789e-06, "loss": 0.7083, "step": 39260 }, { "epoch": 0.23342903507676943, "grad_norm": 7.504188060760498, "learning_rate": 4.668434067240478e-06, "loss": 0.696, "step": 39270 }, { "epoch": 0.23348847715343785, "grad_norm": 11.319623947143555, "learning_rate": 4.669622901707167e-06, "loss": 0.7169, "step": 39280 }, { "epoch": 0.23354791923010623, "grad_norm": 9.800562858581543, "learning_rate": 4.670811736173856e-06, "loss": 0.6751, "step": 39290 }, { "epoch": 0.23360736130677462, "grad_norm": 7.310897350311279, "learning_rate": 4.672000570640544e-06, "loss": 0.6816, "step": 39300 }, { "epoch": 0.233666803383443, "grad_norm": 8.797992706298828, "learning_rate": 4.6731894051072335e-06, "loss": 0.6926, "step": 39310 }, { "epoch": 0.2337262454601114, "grad_norm": 8.821455955505371, "learning_rate": 4.6743782395739224e-06, "loss": 0.7489, "step": 39320 }, { "epoch": 0.23378568753677978, "grad_norm": 8.684163093566895, "learning_rate": 4.675567074040611e-06, "loss": 0.6635, "step": 39330 }, { "epoch": 0.23384512961344817, "grad_norm": 9.406059265136719, "learning_rate": 4.6767559085073e-06, "loss": 0.6782, "step": 39340 }, { "epoch": 0.23390457169011655, "grad_norm": 9.963871002197266, "learning_rate": 4.677944742973989e-06, "loss": 0.7496, "step": 39350 }, { "epoch": 0.23396401376678497, "grad_norm": 8.282381057739258, "learning_rate": 4.679133577440677e-06, "loss": 0.698, "step": 39360 }, { "epoch": 0.23402345584345335, "grad_norm": 9.665694236755371, "learning_rate": 4.680322411907366e-06, "loss": 0.6712, "step": 39370 }, { "epoch": 0.23408289792012174, "grad_norm": 8.800019264221191, "learning_rate": 4.681511246374055e-06, "loss": 0.6947, "step": 39380 }, { "epoch": 0.23414233999679013, "grad_norm": 8.442732810974121, "learning_rate": 4.682700080840744e-06, "loss": 0.7432, "step": 39390 }, { "epoch": 0.23420178207345851, "grad_norm": 10.726802825927734, "learning_rate": 4.683888915307433e-06, "loss": 0.6622, "step": 39400 }, { "epoch": 0.2342612241501269, "grad_norm": 8.88416862487793, "learning_rate": 4.685077749774122e-06, "loss": 0.634, "step": 39410 }, { "epoch": 0.2343206662267953, "grad_norm": 7.540182590484619, "learning_rate": 4.686266584240811e-06, "loss": 0.6524, "step": 39420 }, { "epoch": 0.2343801083034637, "grad_norm": 6.939268589019775, "learning_rate": 4.6874554187075e-06, "loss": 0.69, "step": 39430 }, { "epoch": 0.2344395503801321, "grad_norm": 8.44094467163086, "learning_rate": 4.688644253174188e-06, "loss": 0.7319, "step": 39440 }, { "epoch": 0.23449899245680048, "grad_norm": 10.416045188903809, "learning_rate": 4.689833087640877e-06, "loss": 0.7488, "step": 39450 }, { "epoch": 0.23455843453346886, "grad_norm": 8.872047424316406, "learning_rate": 4.691021922107566e-06, "loss": 0.7061, "step": 39460 }, { "epoch": 0.23461787661013725, "grad_norm": 8.070011138916016, "learning_rate": 4.692210756574255e-06, "loss": 0.6811, "step": 39470 }, { "epoch": 0.23467731868680564, "grad_norm": 7.1841139793396, "learning_rate": 4.6933995910409444e-06, "loss": 0.6773, "step": 39480 }, { "epoch": 0.23473676076347402, "grad_norm": 9.018630027770996, "learning_rate": 4.6945884255076325e-06, "loss": 0.6341, "step": 39490 }, { "epoch": 0.2347962028401424, "grad_norm": 6.688952445983887, "learning_rate": 4.6957772599743214e-06, "loss": 0.6588, "step": 39500 }, { "epoch": 0.23485564491681082, "grad_norm": 6.988605499267578, "learning_rate": 4.69696609444101e-06, "loss": 0.657, "step": 39510 }, { "epoch": 0.2349150869934792, "grad_norm": 10.049209594726562, "learning_rate": 4.698154928907699e-06, "loss": 0.6926, "step": 39520 }, { "epoch": 0.2349745290701476, "grad_norm": 9.464401245117188, "learning_rate": 4.699343763374388e-06, "loss": 0.7005, "step": 39530 }, { "epoch": 0.23503397114681598, "grad_norm": 7.221979141235352, "learning_rate": 4.700532597841077e-06, "loss": 0.707, "step": 39540 }, { "epoch": 0.23509341322348437, "grad_norm": 7.214077949523926, "learning_rate": 4.701721432307766e-06, "loss": 0.6882, "step": 39550 }, { "epoch": 0.23515285530015276, "grad_norm": 6.571475505828857, "learning_rate": 4.702910266774455e-06, "loss": 0.6768, "step": 39560 }, { "epoch": 0.23521229737682114, "grad_norm": 7.977409839630127, "learning_rate": 4.704099101241144e-06, "loss": 0.7483, "step": 39570 }, { "epoch": 0.23527173945348956, "grad_norm": 9.16590404510498, "learning_rate": 4.705287935707832e-06, "loss": 0.7296, "step": 39580 }, { "epoch": 0.23533118153015795, "grad_norm": 9.026411056518555, "learning_rate": 4.706476770174521e-06, "loss": 0.6936, "step": 39590 }, { "epoch": 0.23539062360682633, "grad_norm": 8.96717357635498, "learning_rate": 4.70766560464121e-06, "loss": 0.7085, "step": 39600 }, { "epoch": 0.23545006568349472, "grad_norm": 7.281208038330078, "learning_rate": 4.708854439107899e-06, "loss": 0.6565, "step": 39610 }, { "epoch": 0.2355095077601631, "grad_norm": 7.441726207733154, "learning_rate": 4.710043273574588e-06, "loss": 0.707, "step": 39620 }, { "epoch": 0.2355689498368315, "grad_norm": 7.925706386566162, "learning_rate": 4.711232108041277e-06, "loss": 0.7085, "step": 39630 }, { "epoch": 0.23562839191349988, "grad_norm": 8.877025604248047, "learning_rate": 4.712420942507966e-06, "loss": 0.7162, "step": 39640 }, { "epoch": 0.2356878339901683, "grad_norm": 8.624472618103027, "learning_rate": 4.7136097769746545e-06, "loss": 0.6807, "step": 39650 }, { "epoch": 0.23574727606683668, "grad_norm": 7.770828723907471, "learning_rate": 4.7147986114413434e-06, "loss": 0.7084, "step": 39660 }, { "epoch": 0.23580671814350507, "grad_norm": 7.378594875335693, "learning_rate": 4.715987445908032e-06, "loss": 0.6293, "step": 39670 }, { "epoch": 0.23586616022017345, "grad_norm": 8.155723571777344, "learning_rate": 4.717176280374721e-06, "loss": 0.6712, "step": 39680 }, { "epoch": 0.23592560229684184, "grad_norm": 6.500396251678467, "learning_rate": 4.71836511484141e-06, "loss": 0.7472, "step": 39690 }, { "epoch": 0.23598504437351023, "grad_norm": 9.038901329040527, "learning_rate": 4.719553949308099e-06, "loss": 0.7252, "step": 39700 }, { "epoch": 0.23604448645017861, "grad_norm": 7.942330837249756, "learning_rate": 4.720742783774788e-06, "loss": 0.6911, "step": 39710 }, { "epoch": 0.236103928526847, "grad_norm": 7.7975754737854, "learning_rate": 4.721931618241476e-06, "loss": 0.6908, "step": 39720 }, { "epoch": 0.23616337060351542, "grad_norm": 9.17812728881836, "learning_rate": 4.723120452708165e-06, "loss": 0.6542, "step": 39730 }, { "epoch": 0.2362228126801838, "grad_norm": 9.030402183532715, "learning_rate": 4.724309287174854e-06, "loss": 0.6866, "step": 39740 }, { "epoch": 0.2362822547568522, "grad_norm": 7.9057135581970215, "learning_rate": 4.725498121641543e-06, "loss": 0.6425, "step": 39750 }, { "epoch": 0.23634169683352058, "grad_norm": 7.693286895751953, "learning_rate": 4.726686956108232e-06, "loss": 0.7101, "step": 39760 }, { "epoch": 0.23640113891018896, "grad_norm": 8.712886810302734, "learning_rate": 4.727875790574921e-06, "loss": 0.6899, "step": 39770 }, { "epoch": 0.23646058098685735, "grad_norm": 11.344573020935059, "learning_rate": 4.72906462504161e-06, "loss": 0.6484, "step": 39780 }, { "epoch": 0.23652002306352574, "grad_norm": 8.187777519226074, "learning_rate": 4.730253459508299e-06, "loss": 0.6431, "step": 39790 }, { "epoch": 0.23657946514019415, "grad_norm": 10.092537879943848, "learning_rate": 4.731442293974987e-06, "loss": 0.6892, "step": 39800 }, { "epoch": 0.23663890721686254, "grad_norm": 7.323877811431885, "learning_rate": 4.732631128441676e-06, "loss": 0.6946, "step": 39810 }, { "epoch": 0.23669834929353092, "grad_norm": 7.281973838806152, "learning_rate": 4.733819962908365e-06, "loss": 0.699, "step": 39820 }, { "epoch": 0.2367577913701993, "grad_norm": 7.1138763427734375, "learning_rate": 4.735008797375054e-06, "loss": 0.6978, "step": 39830 }, { "epoch": 0.2368172334468677, "grad_norm": 7.0192155838012695, "learning_rate": 4.736197631841743e-06, "loss": 0.7234, "step": 39840 }, { "epoch": 0.23687667552353608, "grad_norm": 8.048471450805664, "learning_rate": 4.737386466308432e-06, "loss": 0.7439, "step": 39850 }, { "epoch": 0.23693611760020447, "grad_norm": 10.534891128540039, "learning_rate": 4.73857530077512e-06, "loss": 0.7285, "step": 39860 }, { "epoch": 0.23699555967687286, "grad_norm": 8.832632064819336, "learning_rate": 4.739764135241809e-06, "loss": 0.6639, "step": 39870 }, { "epoch": 0.23705500175354127, "grad_norm": 8.30862808227539, "learning_rate": 4.740952969708498e-06, "loss": 0.6925, "step": 39880 }, { "epoch": 0.23711444383020966, "grad_norm": 7.0541558265686035, "learning_rate": 4.742141804175187e-06, "loss": 0.6475, "step": 39890 }, { "epoch": 0.23717388590687805, "grad_norm": 8.611016273498535, "learning_rate": 4.743330638641876e-06, "loss": 0.6624, "step": 39900 }, { "epoch": 0.23723332798354643, "grad_norm": 8.499411582946777, "learning_rate": 4.744519473108565e-06, "loss": 0.7295, "step": 39910 }, { "epoch": 0.23729277006021482, "grad_norm": 7.899993896484375, "learning_rate": 4.745708307575254e-06, "loss": 0.6582, "step": 39920 }, { "epoch": 0.2373522121368832, "grad_norm": 6.301386833190918, "learning_rate": 4.746897142041943e-06, "loss": 0.6617, "step": 39930 }, { "epoch": 0.2374116542135516, "grad_norm": 7.43750524520874, "learning_rate": 4.748085976508631e-06, "loss": 0.678, "step": 39940 }, { "epoch": 0.23747109629022, "grad_norm": 8.275153160095215, "learning_rate": 4.74927481097532e-06, "loss": 0.6078, "step": 39950 }, { "epoch": 0.2375305383668884, "grad_norm": 8.940865516662598, "learning_rate": 4.750463645442009e-06, "loss": 0.7435, "step": 39960 }, { "epoch": 0.23758998044355678, "grad_norm": 12.411236763000488, "learning_rate": 4.751652479908698e-06, "loss": 0.7292, "step": 39970 }, { "epoch": 0.23764942252022517, "grad_norm": 8.487198829650879, "learning_rate": 4.7528413143753866e-06, "loss": 0.7205, "step": 39980 }, { "epoch": 0.23770886459689355, "grad_norm": 7.215244770050049, "learning_rate": 4.7540301488420755e-06, "loss": 0.6957, "step": 39990 }, { "epoch": 0.23776830667356194, "grad_norm": 8.025849342346191, "learning_rate": 4.7552189833087644e-06, "loss": 0.6529, "step": 40000 }, { "epoch": 0.23782774875023033, "grad_norm": 8.06965160369873, "learning_rate": 4.756407817775453e-06, "loss": 0.6387, "step": 40010 }, { "epoch": 0.23788719082689874, "grad_norm": 9.59726333618164, "learning_rate": 4.757596652242142e-06, "loss": 0.7209, "step": 40020 }, { "epoch": 0.23794663290356713, "grad_norm": 8.770888328552246, "learning_rate": 4.758785486708831e-06, "loss": 0.6472, "step": 40030 }, { "epoch": 0.23800607498023552, "grad_norm": 9.839248657226562, "learning_rate": 4.75997432117552e-06, "loss": 0.7204, "step": 40040 }, { "epoch": 0.2380655170569039, "grad_norm": 7.671554088592529, "learning_rate": 4.761163155642209e-06, "loss": 0.6522, "step": 40050 }, { "epoch": 0.2381249591335723, "grad_norm": 9.25540542602539, "learning_rate": 4.762351990108898e-06, "loss": 0.7151, "step": 40060 }, { "epoch": 0.23818440121024068, "grad_norm": 8.5868501663208, "learning_rate": 4.763540824575587e-06, "loss": 0.7038, "step": 40070 }, { "epoch": 0.23824384328690906, "grad_norm": 7.827868938446045, "learning_rate": 4.764729659042275e-06, "loss": 0.654, "step": 40080 }, { "epoch": 0.23830328536357745, "grad_norm": 7.132890224456787, "learning_rate": 4.765918493508964e-06, "loss": 0.6956, "step": 40090 }, { "epoch": 0.23836272744024586, "grad_norm": 8.399782180786133, "learning_rate": 4.767107327975653e-06, "loss": 0.681, "step": 40100 }, { "epoch": 0.23842216951691425, "grad_norm": 8.258127212524414, "learning_rate": 4.768296162442342e-06, "loss": 0.6422, "step": 40110 }, { "epoch": 0.23848161159358264, "grad_norm": 8.387939453125, "learning_rate": 4.769484996909031e-06, "loss": 0.5925, "step": 40120 }, { "epoch": 0.23854105367025102, "grad_norm": 7.688933849334717, "learning_rate": 4.77067383137572e-06, "loss": 0.6969, "step": 40130 }, { "epoch": 0.2386004957469194, "grad_norm": 9.562301635742188, "learning_rate": 4.7718626658424086e-06, "loss": 0.7551, "step": 40140 }, { "epoch": 0.2386599378235878, "grad_norm": 7.881771087646484, "learning_rate": 4.7730515003090975e-06, "loss": 0.7066, "step": 40150 }, { "epoch": 0.23871937990025618, "grad_norm": 7.503481864929199, "learning_rate": 4.7742403347757856e-06, "loss": 0.701, "step": 40160 }, { "epoch": 0.2387788219769246, "grad_norm": 7.588264465332031, "learning_rate": 4.7754291692424745e-06, "loss": 0.6553, "step": 40170 }, { "epoch": 0.23883826405359299, "grad_norm": 7.176235675811768, "learning_rate": 4.776618003709164e-06, "loss": 0.6792, "step": 40180 }, { "epoch": 0.23889770613026137, "grad_norm": 8.841772079467773, "learning_rate": 4.777806838175853e-06, "loss": 0.7614, "step": 40190 }, { "epoch": 0.23895714820692976, "grad_norm": 9.1380033493042, "learning_rate": 4.778995672642542e-06, "loss": 0.6447, "step": 40200 }, { "epoch": 0.23901659028359815, "grad_norm": 6.82811164855957, "learning_rate": 4.780184507109231e-06, "loss": 0.6844, "step": 40210 }, { "epoch": 0.23907603236026653, "grad_norm": 6.797105312347412, "learning_rate": 4.781373341575919e-06, "loss": 0.6926, "step": 40220 }, { "epoch": 0.23913547443693492, "grad_norm": 8.116218566894531, "learning_rate": 4.782562176042608e-06, "loss": 0.7194, "step": 40230 }, { "epoch": 0.2391949165136033, "grad_norm": 9.103188514709473, "learning_rate": 4.783751010509297e-06, "loss": 0.6617, "step": 40240 }, { "epoch": 0.23925435859027172, "grad_norm": 11.97382926940918, "learning_rate": 4.784939844975986e-06, "loss": 0.699, "step": 40250 }, { "epoch": 0.2393138006669401, "grad_norm": 7.045953750610352, "learning_rate": 4.786128679442675e-06, "loss": 0.6323, "step": 40260 }, { "epoch": 0.2393732427436085, "grad_norm": 9.210890769958496, "learning_rate": 4.787317513909364e-06, "loss": 0.623, "step": 40270 }, { "epoch": 0.23943268482027688, "grad_norm": 6.665975570678711, "learning_rate": 4.788506348376053e-06, "loss": 0.6705, "step": 40280 }, { "epoch": 0.23949212689694527, "grad_norm": 9.037900924682617, "learning_rate": 4.789695182842742e-06, "loss": 0.6575, "step": 40290 }, { "epoch": 0.23955156897361365, "grad_norm": 8.41956615447998, "learning_rate": 4.79088401730943e-06, "loss": 0.6577, "step": 40300 }, { "epoch": 0.23961101105028204, "grad_norm": 8.405044555664062, "learning_rate": 4.792072851776119e-06, "loss": 0.7053, "step": 40310 }, { "epoch": 0.23967045312695046, "grad_norm": 7.426700115203857, "learning_rate": 4.7932616862428076e-06, "loss": 0.6961, "step": 40320 }, { "epoch": 0.23972989520361884, "grad_norm": 6.8523993492126465, "learning_rate": 4.7944505207094965e-06, "loss": 0.7235, "step": 40330 }, { "epoch": 0.23978933728028723, "grad_norm": 7.870833873748779, "learning_rate": 4.795639355176185e-06, "loss": 0.6966, "step": 40340 }, { "epoch": 0.23984877935695562, "grad_norm": 8.971553802490234, "learning_rate": 4.796828189642875e-06, "loss": 0.6247, "step": 40350 }, { "epoch": 0.239908221433624, "grad_norm": 10.918010711669922, "learning_rate": 4.798017024109563e-06, "loss": 0.6945, "step": 40360 }, { "epoch": 0.2399676635102924, "grad_norm": 7.9362616539001465, "learning_rate": 4.799205858576252e-06, "loss": 0.6705, "step": 40370 }, { "epoch": 0.24002710558696078, "grad_norm": 7.308572769165039, "learning_rate": 4.800394693042941e-06, "loss": 0.6679, "step": 40380 }, { "epoch": 0.24008654766362916, "grad_norm": 7.979241371154785, "learning_rate": 4.80158352750963e-06, "loss": 0.6953, "step": 40390 }, { "epoch": 0.24014598974029758, "grad_norm": 8.229225158691406, "learning_rate": 4.802772361976319e-06, "loss": 0.7142, "step": 40400 }, { "epoch": 0.24020543181696596, "grad_norm": 7.407681941986084, "learning_rate": 4.803961196443008e-06, "loss": 0.6717, "step": 40410 }, { "epoch": 0.24026487389363435, "grad_norm": 8.190877914428711, "learning_rate": 4.805150030909697e-06, "loss": 0.703, "step": 40420 }, { "epoch": 0.24032431597030274, "grad_norm": 7.961686134338379, "learning_rate": 4.806338865376386e-06, "loss": 0.6433, "step": 40430 }, { "epoch": 0.24038375804697112, "grad_norm": 6.679358005523682, "learning_rate": 4.807527699843074e-06, "loss": 0.6291, "step": 40440 }, { "epoch": 0.2404432001236395, "grad_norm": 9.14532470703125, "learning_rate": 4.808716534309763e-06, "loss": 0.6837, "step": 40450 }, { "epoch": 0.2405026422003079, "grad_norm": 9.264695167541504, "learning_rate": 4.809905368776452e-06, "loss": 0.6625, "step": 40460 }, { "epoch": 0.2405620842769763, "grad_norm": 8.44930648803711, "learning_rate": 4.811094203243141e-06, "loss": 0.668, "step": 40470 }, { "epoch": 0.2406215263536447, "grad_norm": 5.770140171051025, "learning_rate": 4.8122830377098295e-06, "loss": 0.6916, "step": 40480 }, { "epoch": 0.24068096843031309, "grad_norm": 9.364570617675781, "learning_rate": 4.8134718721765185e-06, "loss": 0.7265, "step": 40490 }, { "epoch": 0.24074041050698147, "grad_norm": 8.029061317443848, "learning_rate": 4.814660706643207e-06, "loss": 0.6688, "step": 40500 }, { "epoch": 0.24079985258364986, "grad_norm": 8.051020622253418, "learning_rate": 4.815849541109896e-06, "loss": 0.7277, "step": 40510 }, { "epoch": 0.24085929466031825, "grad_norm": 8.717728614807129, "learning_rate": 4.817038375576585e-06, "loss": 0.7089, "step": 40520 }, { "epoch": 0.24091873673698663, "grad_norm": 9.544220924377441, "learning_rate": 4.818227210043274e-06, "loss": 0.6571, "step": 40530 }, { "epoch": 0.24097817881365505, "grad_norm": 10.11707878112793, "learning_rate": 4.819416044509963e-06, "loss": 0.6465, "step": 40540 }, { "epoch": 0.24103762089032343, "grad_norm": 9.752285957336426, "learning_rate": 4.820604878976652e-06, "loss": 0.6982, "step": 40550 }, { "epoch": 0.24109706296699182, "grad_norm": 9.619688034057617, "learning_rate": 4.821793713443341e-06, "loss": 0.7058, "step": 40560 }, { "epoch": 0.2411565050436602, "grad_norm": 7.217605113983154, "learning_rate": 4.82298254791003e-06, "loss": 0.6556, "step": 40570 }, { "epoch": 0.2412159471203286, "grad_norm": 7.590317249298096, "learning_rate": 4.824171382376718e-06, "loss": 0.6941, "step": 40580 }, { "epoch": 0.24127538919699698, "grad_norm": 7.450369358062744, "learning_rate": 4.825360216843407e-06, "loss": 0.6712, "step": 40590 }, { "epoch": 0.24133483127366537, "grad_norm": 7.964020252227783, "learning_rate": 4.826549051310096e-06, "loss": 0.6255, "step": 40600 }, { "epoch": 0.24139427335033375, "grad_norm": 6.185774326324463, "learning_rate": 4.827737885776785e-06, "loss": 0.7047, "step": 40610 }, { "epoch": 0.24145371542700217, "grad_norm": 8.735979080200195, "learning_rate": 4.828926720243474e-06, "loss": 0.6599, "step": 40620 }, { "epoch": 0.24151315750367056, "grad_norm": 9.550806045532227, "learning_rate": 4.830115554710163e-06, "loss": 0.669, "step": 40630 }, { "epoch": 0.24157259958033894, "grad_norm": 8.943413734436035, "learning_rate": 4.8313043891768515e-06, "loss": 0.6977, "step": 40640 }, { "epoch": 0.24163204165700733, "grad_norm": 10.857257843017578, "learning_rate": 4.8324932236435405e-06, "loss": 0.7609, "step": 40650 }, { "epoch": 0.24169148373367572, "grad_norm": 8.230483055114746, "learning_rate": 4.8336820581102285e-06, "loss": 0.6738, "step": 40660 }, { "epoch": 0.2417509258103441, "grad_norm": 7.90330171585083, "learning_rate": 4.8348708925769175e-06, "loss": 0.7439, "step": 40670 }, { "epoch": 0.2418103678870125, "grad_norm": 9.671475410461426, "learning_rate": 4.836059727043606e-06, "loss": 0.6919, "step": 40680 }, { "epoch": 0.2418698099636809, "grad_norm": 9.094297409057617, "learning_rate": 4.837248561510295e-06, "loss": 0.6896, "step": 40690 }, { "epoch": 0.2419292520403493, "grad_norm": 7.916134357452393, "learning_rate": 4.838437395976985e-06, "loss": 0.6617, "step": 40700 }, { "epoch": 0.24198869411701768, "grad_norm": 9.556779861450195, "learning_rate": 4.839626230443674e-06, "loss": 0.7456, "step": 40710 }, { "epoch": 0.24204813619368606, "grad_norm": 7.625694751739502, "learning_rate": 4.840815064910362e-06, "loss": 0.6627, "step": 40720 }, { "epoch": 0.24210757827035445, "grad_norm": 8.715642929077148, "learning_rate": 4.842003899377051e-06, "loss": 0.7052, "step": 40730 }, { "epoch": 0.24216702034702284, "grad_norm": 7.413704872131348, "learning_rate": 4.84319273384374e-06, "loss": 0.6966, "step": 40740 }, { "epoch": 0.24222646242369122, "grad_norm": 8.660012245178223, "learning_rate": 4.844381568310429e-06, "loss": 0.7171, "step": 40750 }, { "epoch": 0.2422859045003596, "grad_norm": 7.672718048095703, "learning_rate": 4.845570402777118e-06, "loss": 0.6452, "step": 40760 }, { "epoch": 0.24234534657702803, "grad_norm": 7.491152763366699, "learning_rate": 4.846759237243807e-06, "loss": 0.668, "step": 40770 }, { "epoch": 0.2424047886536964, "grad_norm": 7.448856830596924, "learning_rate": 4.847948071710496e-06, "loss": 0.678, "step": 40780 }, { "epoch": 0.2424642307303648, "grad_norm": 7.09677791595459, "learning_rate": 4.849136906177185e-06, "loss": 0.6882, "step": 40790 }, { "epoch": 0.24252367280703319, "grad_norm": 7.352269172668457, "learning_rate": 4.850325740643873e-06, "loss": 0.7009, "step": 40800 }, { "epoch": 0.24258311488370157, "grad_norm": 8.613131523132324, "learning_rate": 4.851514575110562e-06, "loss": 0.7046, "step": 40810 }, { "epoch": 0.24264255696036996, "grad_norm": 6.695636749267578, "learning_rate": 4.8527034095772505e-06, "loss": 0.6853, "step": 40820 }, { "epoch": 0.24270199903703835, "grad_norm": 6.2300333976745605, "learning_rate": 4.8538922440439395e-06, "loss": 0.6928, "step": 40830 }, { "epoch": 0.24276144111370676, "grad_norm": 6.966772556304932, "learning_rate": 4.855081078510628e-06, "loss": 0.6741, "step": 40840 }, { "epoch": 0.24282088319037515, "grad_norm": 7.275430679321289, "learning_rate": 4.856269912977317e-06, "loss": 0.6337, "step": 40850 }, { "epoch": 0.24288032526704353, "grad_norm": 7.276293754577637, "learning_rate": 4.857458747444006e-06, "loss": 0.7045, "step": 40860 }, { "epoch": 0.24293976734371192, "grad_norm": 8.191446304321289, "learning_rate": 4.858647581910695e-06, "loss": 0.6274, "step": 40870 }, { "epoch": 0.2429992094203803, "grad_norm": 7.82895565032959, "learning_rate": 4.859836416377384e-06, "loss": 0.6982, "step": 40880 }, { "epoch": 0.2430586514970487, "grad_norm": 8.109854698181152, "learning_rate": 4.861025250844073e-06, "loss": 0.6599, "step": 40890 }, { "epoch": 0.24311809357371708, "grad_norm": 9.548364639282227, "learning_rate": 4.862214085310762e-06, "loss": 0.6628, "step": 40900 }, { "epoch": 0.2431775356503855, "grad_norm": 6.738118648529053, "learning_rate": 4.863402919777451e-06, "loss": 0.7688, "step": 40910 }, { "epoch": 0.24323697772705388, "grad_norm": 9.45572280883789, "learning_rate": 4.86459175424414e-06, "loss": 0.6504, "step": 40920 }, { "epoch": 0.24329641980372227, "grad_norm": 9.610782623291016, "learning_rate": 4.865780588710829e-06, "loss": 0.6807, "step": 40930 }, { "epoch": 0.24335586188039066, "grad_norm": 7.921723365783691, "learning_rate": 4.866969423177517e-06, "loss": 0.6427, "step": 40940 }, { "epoch": 0.24341530395705904, "grad_norm": 6.268793106079102, "learning_rate": 4.868158257644206e-06, "loss": 0.6586, "step": 40950 }, { "epoch": 0.24347474603372743, "grad_norm": 7.4328155517578125, "learning_rate": 4.869347092110895e-06, "loss": 0.6822, "step": 40960 }, { "epoch": 0.24353418811039582, "grad_norm": 7.408205986022949, "learning_rate": 4.870535926577584e-06, "loss": 0.6879, "step": 40970 }, { "epoch": 0.2435936301870642, "grad_norm": 9.826099395751953, "learning_rate": 4.8717247610442725e-06, "loss": 0.7292, "step": 40980 }, { "epoch": 0.24365307226373262, "grad_norm": 8.962030410766602, "learning_rate": 4.8729135955109614e-06, "loss": 0.7263, "step": 40990 }, { "epoch": 0.243712514340401, "grad_norm": 7.154322624206543, "learning_rate": 4.87410242997765e-06, "loss": 0.6605, "step": 41000 }, { "epoch": 0.2437719564170694, "grad_norm": 7.860566139221191, "learning_rate": 4.875291264444339e-06, "loss": 0.712, "step": 41010 }, { "epoch": 0.24383139849373778, "grad_norm": 8.157304763793945, "learning_rate": 4.876480098911027e-06, "loss": 0.6871, "step": 41020 }, { "epoch": 0.24389084057040616, "grad_norm": 7.454927444458008, "learning_rate": 4.877668933377716e-06, "loss": 0.6868, "step": 41030 }, { "epoch": 0.24395028264707455, "grad_norm": 9.569005966186523, "learning_rate": 4.878857767844406e-06, "loss": 0.6739, "step": 41040 }, { "epoch": 0.24400972472374294, "grad_norm": 8.578834533691406, "learning_rate": 4.880046602311095e-06, "loss": 0.7114, "step": 41050 }, { "epoch": 0.24406916680041135, "grad_norm": 8.388407707214355, "learning_rate": 4.881235436777784e-06, "loss": 0.6367, "step": 41060 }, { "epoch": 0.24412860887707974, "grad_norm": 8.514348983764648, "learning_rate": 4.882424271244473e-06, "loss": 0.6609, "step": 41070 }, { "epoch": 0.24418805095374813, "grad_norm": 7.839369773864746, "learning_rate": 4.883613105711161e-06, "loss": 0.6811, "step": 41080 }, { "epoch": 0.2442474930304165, "grad_norm": 8.607823371887207, "learning_rate": 4.88480194017785e-06, "loss": 0.7122, "step": 41090 }, { "epoch": 0.2443069351070849, "grad_norm": 9.026999473571777, "learning_rate": 4.885990774644539e-06, "loss": 0.6498, "step": 41100 }, { "epoch": 0.24436637718375329, "grad_norm": 9.861246109008789, "learning_rate": 4.887179609111228e-06, "loss": 0.6806, "step": 41110 }, { "epoch": 0.24442581926042167, "grad_norm": 7.646810054779053, "learning_rate": 4.888368443577917e-06, "loss": 0.6611, "step": 41120 }, { "epoch": 0.24448526133709006, "grad_norm": 8.0971040725708, "learning_rate": 4.889557278044606e-06, "loss": 0.7068, "step": 41130 }, { "epoch": 0.24454470341375847, "grad_norm": 6.771014213562012, "learning_rate": 4.8907461125112945e-06, "loss": 0.6354, "step": 41140 }, { "epoch": 0.24460414549042686, "grad_norm": 6.903726100921631, "learning_rate": 4.8919349469779834e-06, "loss": 0.6604, "step": 41150 }, { "epoch": 0.24466358756709525, "grad_norm": 10.606925964355469, "learning_rate": 4.8931237814446715e-06, "loss": 0.7429, "step": 41160 }, { "epoch": 0.24472302964376363, "grad_norm": 6.661558151245117, "learning_rate": 4.8943126159113604e-06, "loss": 0.6604, "step": 41170 }, { "epoch": 0.24478247172043202, "grad_norm": 7.774697303771973, "learning_rate": 4.895501450378049e-06, "loss": 0.6815, "step": 41180 }, { "epoch": 0.2448419137971004, "grad_norm": 8.57187557220459, "learning_rate": 4.896690284844738e-06, "loss": 0.7406, "step": 41190 }, { "epoch": 0.2449013558737688, "grad_norm": 7.500227451324463, "learning_rate": 4.897879119311427e-06, "loss": 0.6665, "step": 41200 }, { "epoch": 0.2449607979504372, "grad_norm": 9.268832206726074, "learning_rate": 4.899067953778116e-06, "loss": 0.6729, "step": 41210 }, { "epoch": 0.2450202400271056, "grad_norm": 9.414517402648926, "learning_rate": 4.900256788244805e-06, "loss": 0.6969, "step": 41220 }, { "epoch": 0.24507968210377398, "grad_norm": 6.710177898406982, "learning_rate": 4.901445622711494e-06, "loss": 0.6736, "step": 41230 }, { "epoch": 0.24513912418044237, "grad_norm": 6.856979846954346, "learning_rate": 4.902634457178183e-06, "loss": 0.6493, "step": 41240 }, { "epoch": 0.24519856625711076, "grad_norm": 8.536931991577148, "learning_rate": 4.903823291644872e-06, "loss": 0.684, "step": 41250 }, { "epoch": 0.24525800833377914, "grad_norm": 8.845723152160645, "learning_rate": 4.905012126111561e-06, "loss": 0.7194, "step": 41260 }, { "epoch": 0.24531745041044753, "grad_norm": 7.99968147277832, "learning_rate": 4.90620096057825e-06, "loss": 0.737, "step": 41270 }, { "epoch": 0.24537689248711592, "grad_norm": 8.091038703918457, "learning_rate": 4.907389795044939e-06, "loss": 0.6706, "step": 41280 }, { "epoch": 0.24543633456378433, "grad_norm": 6.925932884216309, "learning_rate": 4.9085786295116276e-06, "loss": 0.6484, "step": 41290 }, { "epoch": 0.24549577664045272, "grad_norm": 6.664511680603027, "learning_rate": 4.909767463978316e-06, "loss": 0.6528, "step": 41300 }, { "epoch": 0.2455552187171211, "grad_norm": 10.294514656066895, "learning_rate": 4.910956298445005e-06, "loss": 0.6988, "step": 41310 }, { "epoch": 0.2456146607937895, "grad_norm": 9.008273124694824, "learning_rate": 4.9121451329116935e-06, "loss": 0.7125, "step": 41320 }, { "epoch": 0.24567410287045788, "grad_norm": 7.88322114944458, "learning_rate": 4.9133339673783824e-06, "loss": 0.6365, "step": 41330 }, { "epoch": 0.24573354494712626, "grad_norm": 7.454652786254883, "learning_rate": 4.914522801845071e-06, "loss": 0.6842, "step": 41340 }, { "epoch": 0.24579298702379465, "grad_norm": 7.877349853515625, "learning_rate": 4.91571163631176e-06, "loss": 0.6885, "step": 41350 }, { "epoch": 0.24585242910046307, "grad_norm": 9.636589050292969, "learning_rate": 4.916900470778449e-06, "loss": 0.7036, "step": 41360 }, { "epoch": 0.24591187117713145, "grad_norm": 8.052104949951172, "learning_rate": 4.918089305245138e-06, "loss": 0.646, "step": 41370 }, { "epoch": 0.24597131325379984, "grad_norm": 10.024392127990723, "learning_rate": 4.919278139711827e-06, "loss": 0.6804, "step": 41380 }, { "epoch": 0.24603075533046823, "grad_norm": 7.24776554107666, "learning_rate": 4.920466974178516e-06, "loss": 0.6402, "step": 41390 }, { "epoch": 0.2460901974071366, "grad_norm": 7.902890682220459, "learning_rate": 4.921655808645205e-06, "loss": 0.6943, "step": 41400 }, { "epoch": 0.246149639483805, "grad_norm": 7.5415940284729, "learning_rate": 4.922844643111894e-06, "loss": 0.7189, "step": 41410 }, { "epoch": 0.2462090815604734, "grad_norm": 7.069546699523926, "learning_rate": 4.924033477578583e-06, "loss": 0.6732, "step": 41420 }, { "epoch": 0.2462685236371418, "grad_norm": 6.317422389984131, "learning_rate": 4.925222312045272e-06, "loss": 0.6623, "step": 41430 }, { "epoch": 0.2463279657138102, "grad_norm": 8.627345085144043, "learning_rate": 4.92641114651196e-06, "loss": 0.6451, "step": 41440 }, { "epoch": 0.24638740779047857, "grad_norm": 7.809504985809326, "learning_rate": 4.927599980978649e-06, "loss": 0.6952, "step": 41450 }, { "epoch": 0.24644684986714696, "grad_norm": 9.876922607421875, "learning_rate": 4.928788815445338e-06, "loss": 0.632, "step": 41460 }, { "epoch": 0.24650629194381535, "grad_norm": 11.25841999053955, "learning_rate": 4.9299776499120266e-06, "loss": 0.6874, "step": 41470 }, { "epoch": 0.24656573402048373, "grad_norm": 8.234097480773926, "learning_rate": 4.9311664843787155e-06, "loss": 0.702, "step": 41480 }, { "epoch": 0.24662517609715212, "grad_norm": 6.669618129730225, "learning_rate": 4.9323553188454044e-06, "loss": 0.6944, "step": 41490 }, { "epoch": 0.2466846181738205, "grad_norm": 8.814565658569336, "learning_rate": 4.933544153312093e-06, "loss": 0.6214, "step": 41500 }, { "epoch": 0.24674406025048892, "grad_norm": 11.027596473693848, "learning_rate": 4.934732987778782e-06, "loss": 0.7283, "step": 41510 }, { "epoch": 0.2468035023271573, "grad_norm": 8.86331844329834, "learning_rate": 4.93592182224547e-06, "loss": 0.6824, "step": 41520 }, { "epoch": 0.2468629444038257, "grad_norm": 8.989775657653809, "learning_rate": 4.937110656712159e-06, "loss": 0.6834, "step": 41530 }, { "epoch": 0.24692238648049408, "grad_norm": 7.8960747718811035, "learning_rate": 4.938299491178848e-06, "loss": 0.6909, "step": 41540 }, { "epoch": 0.24698182855716247, "grad_norm": 6.908358573913574, "learning_rate": 4.939488325645537e-06, "loss": 0.6732, "step": 41550 }, { "epoch": 0.24704127063383086, "grad_norm": 8.40920639038086, "learning_rate": 4.940677160112227e-06, "loss": 0.7712, "step": 41560 }, { "epoch": 0.24710071271049924, "grad_norm": 9.338091850280762, "learning_rate": 4.941865994578916e-06, "loss": 0.6558, "step": 41570 }, { "epoch": 0.24716015478716766, "grad_norm": 7.284027099609375, "learning_rate": 4.943054829045604e-06, "loss": 0.6848, "step": 41580 }, { "epoch": 0.24721959686383604, "grad_norm": 7.181175708770752, "learning_rate": 4.944243663512293e-06, "loss": 0.6314, "step": 41590 }, { "epoch": 0.24727903894050443, "grad_norm": 9.343761444091797, "learning_rate": 4.945432497978982e-06, "loss": 0.6952, "step": 41600 }, { "epoch": 0.24733848101717282, "grad_norm": 8.489775657653809, "learning_rate": 4.946621332445671e-06, "loss": 0.6765, "step": 41610 }, { "epoch": 0.2473979230938412, "grad_norm": 9.379925727844238, "learning_rate": 4.94781016691236e-06, "loss": 0.6782, "step": 41620 }, { "epoch": 0.2474573651705096, "grad_norm": 6.640322208404541, "learning_rate": 4.9489990013790486e-06, "loss": 0.6813, "step": 41630 }, { "epoch": 0.24751680724717798, "grad_norm": 6.907010555267334, "learning_rate": 4.9501878358457375e-06, "loss": 0.6756, "step": 41640 }, { "epoch": 0.24757624932384636, "grad_norm": 7.732799053192139, "learning_rate": 4.951376670312426e-06, "loss": 0.6722, "step": 41650 }, { "epoch": 0.24763569140051478, "grad_norm": 7.394322872161865, "learning_rate": 4.9525655047791145e-06, "loss": 0.6431, "step": 41660 }, { "epoch": 0.24769513347718317, "grad_norm": 8.447569847106934, "learning_rate": 4.9537543392458034e-06, "loss": 0.7289, "step": 41670 }, { "epoch": 0.24775457555385155, "grad_norm": 7.296041488647461, "learning_rate": 4.954943173712492e-06, "loss": 0.6049, "step": 41680 }, { "epoch": 0.24781401763051994, "grad_norm": 9.390064239501953, "learning_rate": 4.956132008179181e-06, "loss": 0.6823, "step": 41690 }, { "epoch": 0.24787345970718833, "grad_norm": 8.098352432250977, "learning_rate": 4.95732084264587e-06, "loss": 0.6752, "step": 41700 }, { "epoch": 0.2479329017838567, "grad_norm": 9.947330474853516, "learning_rate": 4.958509677112559e-06, "loss": 0.7499, "step": 41710 }, { "epoch": 0.2479923438605251, "grad_norm": 6.819488525390625, "learning_rate": 4.959698511579248e-06, "loss": 0.6418, "step": 41720 }, { "epoch": 0.24805178593719351, "grad_norm": 9.191808700561523, "learning_rate": 4.960887346045937e-06, "loss": 0.6947, "step": 41730 }, { "epoch": 0.2481112280138619, "grad_norm": 7.517646789550781, "learning_rate": 4.962076180512626e-06, "loss": 0.6823, "step": 41740 }, { "epoch": 0.2481706700905303, "grad_norm": 7.533071517944336, "learning_rate": 4.963265014979315e-06, "loss": 0.6794, "step": 41750 }, { "epoch": 0.24823011216719867, "grad_norm": 8.284029960632324, "learning_rate": 4.964453849446004e-06, "loss": 0.5762, "step": 41760 }, { "epoch": 0.24828955424386706, "grad_norm": 9.903374671936035, "learning_rate": 4.965642683912693e-06, "loss": 0.697, "step": 41770 }, { "epoch": 0.24834899632053545, "grad_norm": 8.053484916687012, "learning_rate": 4.966831518379382e-06, "loss": 0.6082, "step": 41780 }, { "epoch": 0.24840843839720383, "grad_norm": 9.116870880126953, "learning_rate": 4.9680203528460706e-06, "loss": 0.7259, "step": 41790 }, { "epoch": 0.24846788047387225, "grad_norm": 7.890688896179199, "learning_rate": 4.969209187312759e-06, "loss": 0.6871, "step": 41800 }, { "epoch": 0.24852732255054064, "grad_norm": 8.832538604736328, "learning_rate": 4.9703980217794476e-06, "loss": 0.6983, "step": 41810 }, { "epoch": 0.24858676462720902, "grad_norm": 10.461917877197266, "learning_rate": 4.9715868562461365e-06, "loss": 0.7213, "step": 41820 }, { "epoch": 0.2486462067038774, "grad_norm": 8.597090721130371, "learning_rate": 4.972775690712825e-06, "loss": 0.6926, "step": 41830 }, { "epoch": 0.2487056487805458, "grad_norm": 8.45469856262207, "learning_rate": 4.973964525179514e-06, "loss": 0.737, "step": 41840 }, { "epoch": 0.24876509085721418, "grad_norm": 8.13771915435791, "learning_rate": 4.975153359646203e-06, "loss": 0.7795, "step": 41850 }, { "epoch": 0.24882453293388257, "grad_norm": 7.200598239898682, "learning_rate": 4.976342194112892e-06, "loss": 0.6333, "step": 41860 }, { "epoch": 0.24888397501055096, "grad_norm": 11.786290168762207, "learning_rate": 4.977531028579581e-06, "loss": 0.6932, "step": 41870 }, { "epoch": 0.24894341708721937, "grad_norm": 8.398215293884277, "learning_rate": 4.97871986304627e-06, "loss": 0.6372, "step": 41880 }, { "epoch": 0.24900285916388776, "grad_norm": 7.41648530960083, "learning_rate": 4.979908697512958e-06, "loss": 0.6676, "step": 41890 }, { "epoch": 0.24906230124055614, "grad_norm": 9.063940048217773, "learning_rate": 4.981097531979647e-06, "loss": 0.659, "step": 41900 }, { "epoch": 0.24912174331722453, "grad_norm": 7.933515548706055, "learning_rate": 4.982286366446337e-06, "loss": 0.7099, "step": 41910 }, { "epoch": 0.24918118539389292, "grad_norm": 7.465493679046631, "learning_rate": 4.983475200913026e-06, "loss": 0.7575, "step": 41920 }, { "epoch": 0.2492406274705613, "grad_norm": 7.115086078643799, "learning_rate": 4.984664035379715e-06, "loss": 0.6615, "step": 41930 }, { "epoch": 0.2493000695472297, "grad_norm": 7.369222640991211, "learning_rate": 4.985852869846403e-06, "loss": 0.6827, "step": 41940 }, { "epoch": 0.2493595116238981, "grad_norm": 7.512193202972412, "learning_rate": 4.987041704313092e-06, "loss": 0.633, "step": 41950 }, { "epoch": 0.2494189537005665, "grad_norm": 6.952106952667236, "learning_rate": 4.988230538779781e-06, "loss": 0.7044, "step": 41960 }, { "epoch": 0.24947839577723488, "grad_norm": 7.668874740600586, "learning_rate": 4.9894193732464695e-06, "loss": 0.69, "step": 41970 }, { "epoch": 0.24953783785390327, "grad_norm": 7.626908302307129, "learning_rate": 4.9906082077131585e-06, "loss": 0.688, "step": 41980 }, { "epoch": 0.24959727993057165, "grad_norm": 10.714046478271484, "learning_rate": 4.991797042179847e-06, "loss": 0.7161, "step": 41990 }, { "epoch": 0.24965672200724004, "grad_norm": 7.820481777191162, "learning_rate": 4.992985876646536e-06, "loss": 0.6668, "step": 42000 }, { "epoch": 0.24971616408390843, "grad_norm": 7.931764602661133, "learning_rate": 4.994174711113225e-06, "loss": 0.7196, "step": 42010 }, { "epoch": 0.2497756061605768, "grad_norm": 9.188934326171875, "learning_rate": 4.995363545579914e-06, "loss": 0.7337, "step": 42020 }, { "epoch": 0.24983504823724523, "grad_norm": 10.159077644348145, "learning_rate": 4.996552380046602e-06, "loss": 0.6528, "step": 42030 }, { "epoch": 0.24989449031391361, "grad_norm": 9.619518280029297, "learning_rate": 4.997741214513291e-06, "loss": 0.6925, "step": 42040 }, { "epoch": 0.249953932390582, "grad_norm": 8.436078071594238, "learning_rate": 4.99893004897998e-06, "loss": 0.6423, "step": 42050 }, { "epoch": 0.2500133744672504, "grad_norm": 8.63472843170166, "learning_rate": 5.00011888344667e-06, "loss": 0.6456, "step": 42060 }, { "epoch": 0.2500728165439188, "grad_norm": 10.1780366897583, "learning_rate": 5.001307717913359e-06, "loss": 0.7463, "step": 42070 }, { "epoch": 0.2501322586205872, "grad_norm": 7.300711631774902, "learning_rate": 5.002496552380047e-06, "loss": 0.747, "step": 42080 }, { "epoch": 0.25019170069725555, "grad_norm": 7.241913795471191, "learning_rate": 5.003685386846736e-06, "loss": 0.6443, "step": 42090 }, { "epoch": 0.25025114277392396, "grad_norm": 6.3707146644592285, "learning_rate": 5.004874221313425e-06, "loss": 0.6534, "step": 42100 }, { "epoch": 0.2503105848505923, "grad_norm": 9.15242862701416, "learning_rate": 5.006063055780114e-06, "loss": 0.6674, "step": 42110 }, { "epoch": 0.25037002692726074, "grad_norm": 8.006054878234863, "learning_rate": 5.007251890246803e-06, "loss": 0.6832, "step": 42120 }, { "epoch": 0.2504294690039291, "grad_norm": 6.7583537101745605, "learning_rate": 5.0084407247134915e-06, "loss": 0.6579, "step": 42130 }, { "epoch": 0.2504889110805975, "grad_norm": 7.40920352935791, "learning_rate": 5.0096295591801805e-06, "loss": 0.688, "step": 42140 }, { "epoch": 0.2505483531572659, "grad_norm": 10.352882385253906, "learning_rate": 5.010818393646869e-06, "loss": 0.7473, "step": 42150 }, { "epoch": 0.2506077952339343, "grad_norm": 8.159391403198242, "learning_rate": 5.0120072281135575e-06, "loss": 0.6608, "step": 42160 }, { "epoch": 0.2506672373106027, "grad_norm": 8.425477027893066, "learning_rate": 5.013196062580246e-06, "loss": 0.6712, "step": 42170 }, { "epoch": 0.25072667938727106, "grad_norm": 8.933012962341309, "learning_rate": 5.014384897046935e-06, "loss": 0.773, "step": 42180 }, { "epoch": 0.25078612146393947, "grad_norm": 7.186531066894531, "learning_rate": 5.015573731513624e-06, "loss": 0.6692, "step": 42190 }, { "epoch": 0.25084556354060783, "grad_norm": 6.668489933013916, "learning_rate": 5.016762565980313e-06, "loss": 0.6921, "step": 42200 }, { "epoch": 0.25090500561727624, "grad_norm": 10.575875282287598, "learning_rate": 5.017951400447002e-06, "loss": 0.7013, "step": 42210 }, { "epoch": 0.25096444769394466, "grad_norm": 8.35234260559082, "learning_rate": 5.019140234913691e-06, "loss": 0.6687, "step": 42220 }, { "epoch": 0.251023889770613, "grad_norm": 7.430481433868408, "learning_rate": 5.02032906938038e-06, "loss": 0.7132, "step": 42230 }, { "epoch": 0.25108333184728143, "grad_norm": 7.40344762802124, "learning_rate": 5.021517903847069e-06, "loss": 0.6994, "step": 42240 }, { "epoch": 0.2511427739239498, "grad_norm": 7.60780668258667, "learning_rate": 5.022706738313757e-06, "loss": 0.6713, "step": 42250 }, { "epoch": 0.2512022160006182, "grad_norm": 6.626460075378418, "learning_rate": 5.023895572780446e-06, "loss": 0.6416, "step": 42260 }, { "epoch": 0.25126165807728656, "grad_norm": 8.051559448242188, "learning_rate": 5.025084407247135e-06, "loss": 0.7004, "step": 42270 }, { "epoch": 0.251321100153955, "grad_norm": 7.68793249130249, "learning_rate": 5.026273241713824e-06, "loss": 0.6915, "step": 42280 }, { "epoch": 0.2513805422306234, "grad_norm": 8.511919021606445, "learning_rate": 5.027462076180513e-06, "loss": 0.7047, "step": 42290 }, { "epoch": 0.25143998430729175, "grad_norm": 9.066224098205566, "learning_rate": 5.028650910647202e-06, "loss": 0.7469, "step": 42300 }, { "epoch": 0.25149942638396017, "grad_norm": 8.746491432189941, "learning_rate": 5.0298397451138905e-06, "loss": 0.6532, "step": 42310 }, { "epoch": 0.2515588684606285, "grad_norm": 10.296850204467773, "learning_rate": 5.0310285795805795e-06, "loss": 0.6631, "step": 42320 }, { "epoch": 0.25161831053729694, "grad_norm": 8.281643867492676, "learning_rate": 5.0322174140472675e-06, "loss": 0.7264, "step": 42330 }, { "epoch": 0.2516777526139653, "grad_norm": 11.851807594299316, "learning_rate": 5.033406248513958e-06, "loss": 0.677, "step": 42340 }, { "epoch": 0.2517371946906337, "grad_norm": 7.473225116729736, "learning_rate": 5.034595082980647e-06, "loss": 0.6792, "step": 42350 }, { "epoch": 0.25179663676730213, "grad_norm": 8.67015266418457, "learning_rate": 5.035783917447335e-06, "loss": 0.6404, "step": 42360 }, { "epoch": 0.2518560788439705, "grad_norm": 8.279181480407715, "learning_rate": 5.036972751914024e-06, "loss": 0.7039, "step": 42370 }, { "epoch": 0.2519155209206389, "grad_norm": 8.543474197387695, "learning_rate": 5.038161586380713e-06, "loss": 0.7212, "step": 42380 }, { "epoch": 0.25197496299730726, "grad_norm": 8.1812105178833, "learning_rate": 5.039350420847402e-06, "loss": 0.674, "step": 42390 }, { "epoch": 0.2520344050739757, "grad_norm": 7.566760063171387, "learning_rate": 5.040539255314091e-06, "loss": 0.7028, "step": 42400 }, { "epoch": 0.25209384715064403, "grad_norm": 7.85015869140625, "learning_rate": 5.04172808978078e-06, "loss": 0.6923, "step": 42410 }, { "epoch": 0.25215328922731245, "grad_norm": 7.949707984924316, "learning_rate": 5.042916924247469e-06, "loss": 0.685, "step": 42420 }, { "epoch": 0.2522127313039808, "grad_norm": 6.941634178161621, "learning_rate": 5.044105758714158e-06, "loss": 0.678, "step": 42430 }, { "epoch": 0.2522721733806492, "grad_norm": 9.83328628540039, "learning_rate": 5.045294593180846e-06, "loss": 0.6328, "step": 42440 }, { "epoch": 0.25233161545731764, "grad_norm": 7.769962787628174, "learning_rate": 5.046483427647535e-06, "loss": 0.6509, "step": 42450 }, { "epoch": 0.252391057533986, "grad_norm": 8.236639976501465, "learning_rate": 5.047672262114224e-06, "loss": 0.7157, "step": 42460 }, { "epoch": 0.2524504996106544, "grad_norm": 9.258164405822754, "learning_rate": 5.0488610965809125e-06, "loss": 0.692, "step": 42470 }, { "epoch": 0.25250994168732277, "grad_norm": 7.864295482635498, "learning_rate": 5.0500499310476015e-06, "loss": 0.656, "step": 42480 }, { "epoch": 0.2525693837639912, "grad_norm": 8.277337074279785, "learning_rate": 5.05123876551429e-06, "loss": 0.6763, "step": 42490 }, { "epoch": 0.25262882584065954, "grad_norm": 7.976498603820801, "learning_rate": 5.052427599980979e-06, "loss": 0.7547, "step": 42500 }, { "epoch": 0.25268826791732796, "grad_norm": 7.707981109619141, "learning_rate": 5.053616434447668e-06, "loss": 0.6485, "step": 42510 }, { "epoch": 0.2527477099939964, "grad_norm": 7.6667799949646, "learning_rate": 5.054805268914357e-06, "loss": 0.6781, "step": 42520 }, { "epoch": 0.25280715207066473, "grad_norm": 8.361586570739746, "learning_rate": 5.055994103381045e-06, "loss": 0.6608, "step": 42530 }, { "epoch": 0.25286659414733315, "grad_norm": 8.10392951965332, "learning_rate": 5.057182937847734e-06, "loss": 0.6365, "step": 42540 }, { "epoch": 0.2529260362240015, "grad_norm": 6.8465800285339355, "learning_rate": 5.058371772314423e-06, "loss": 0.7236, "step": 42550 }, { "epoch": 0.2529854783006699, "grad_norm": 7.522158145904541, "learning_rate": 5.059560606781112e-06, "loss": 0.7181, "step": 42560 }, { "epoch": 0.2530449203773383, "grad_norm": 7.814246654510498, "learning_rate": 5.060749441247801e-06, "loss": 0.6952, "step": 42570 }, { "epoch": 0.2531043624540067, "grad_norm": 8.998968124389648, "learning_rate": 5.06193827571449e-06, "loss": 0.731, "step": 42580 }, { "epoch": 0.2531638045306751, "grad_norm": 7.104181289672852, "learning_rate": 5.063127110181179e-06, "loss": 0.7004, "step": 42590 }, { "epoch": 0.25322324660734347, "grad_norm": 7.721538543701172, "learning_rate": 5.064315944647868e-06, "loss": 0.6599, "step": 42600 }, { "epoch": 0.2532826886840119, "grad_norm": 9.077413558959961, "learning_rate": 5.065504779114556e-06, "loss": 0.7412, "step": 42610 }, { "epoch": 0.25334213076068024, "grad_norm": 7.801019191741943, "learning_rate": 5.066693613581245e-06, "loss": 0.6682, "step": 42620 }, { "epoch": 0.25340157283734865, "grad_norm": 9.07323169708252, "learning_rate": 5.067882448047934e-06, "loss": 0.637, "step": 42630 }, { "epoch": 0.253461014914017, "grad_norm": 6.828350067138672, "learning_rate": 5.069071282514623e-06, "loss": 0.6901, "step": 42640 }, { "epoch": 0.2535204569906854, "grad_norm": 7.624663352966309, "learning_rate": 5.0702601169813115e-06, "loss": 0.6673, "step": 42650 }, { "epoch": 0.25357989906735384, "grad_norm": 8.303759574890137, "learning_rate": 5.0714489514480005e-06, "loss": 0.6442, "step": 42660 }, { "epoch": 0.2536393411440222, "grad_norm": 8.641511917114258, "learning_rate": 5.072637785914689e-06, "loss": 0.6482, "step": 42670 }, { "epoch": 0.2536987832206906, "grad_norm": 10.421133995056152, "learning_rate": 5.073826620381378e-06, "loss": 0.6456, "step": 42680 }, { "epoch": 0.253758225297359, "grad_norm": 7.474423408508301, "learning_rate": 5.075015454848068e-06, "loss": 0.6868, "step": 42690 }, { "epoch": 0.2538176673740274, "grad_norm": 8.344303131103516, "learning_rate": 5.076204289314757e-06, "loss": 0.6445, "step": 42700 }, { "epoch": 0.25387710945069575, "grad_norm": 8.731230735778809, "learning_rate": 5.077393123781446e-06, "loss": 0.6696, "step": 42710 }, { "epoch": 0.25393655152736416, "grad_norm": 10.21825122833252, "learning_rate": 5.078581958248134e-06, "loss": 0.668, "step": 42720 }, { "epoch": 0.2539959936040326, "grad_norm": 9.1846342086792, "learning_rate": 5.079770792714823e-06, "loss": 0.6919, "step": 42730 }, { "epoch": 0.25405543568070094, "grad_norm": 10.117499351501465, "learning_rate": 5.080959627181512e-06, "loss": 0.7341, "step": 42740 }, { "epoch": 0.25411487775736935, "grad_norm": 7.228919506072998, "learning_rate": 5.082148461648201e-06, "loss": 0.6296, "step": 42750 }, { "epoch": 0.2541743198340377, "grad_norm": 7.519451141357422, "learning_rate": 5.08333729611489e-06, "loss": 0.7296, "step": 42760 }, { "epoch": 0.2542337619107061, "grad_norm": 8.95444107055664, "learning_rate": 5.084526130581579e-06, "loss": 0.6241, "step": 42770 }, { "epoch": 0.2542932039873745, "grad_norm": 8.159181594848633, "learning_rate": 5.085714965048268e-06, "loss": 0.7105, "step": 42780 }, { "epoch": 0.2543526460640429, "grad_norm": 8.616338729858398, "learning_rate": 5.0869037995149565e-06, "loss": 0.6814, "step": 42790 }, { "epoch": 0.25441208814071126, "grad_norm": 7.308315277099609, "learning_rate": 5.088092633981645e-06, "loss": 0.6758, "step": 42800 }, { "epoch": 0.25447153021737967, "grad_norm": 7.161081790924072, "learning_rate": 5.0892814684483335e-06, "loss": 0.6787, "step": 42810 }, { "epoch": 0.2545309722940481, "grad_norm": 8.830571174621582, "learning_rate": 5.0904703029150224e-06, "loss": 0.7562, "step": 42820 }, { "epoch": 0.25459041437071644, "grad_norm": 5.695479393005371, "learning_rate": 5.091659137381711e-06, "loss": 0.5982, "step": 42830 }, { "epoch": 0.25464985644738486, "grad_norm": 8.151163101196289, "learning_rate": 5.0928479718484e-06, "loss": 0.6554, "step": 42840 }, { "epoch": 0.2547092985240532, "grad_norm": 7.426996231079102, "learning_rate": 5.094036806315089e-06, "loss": 0.6762, "step": 42850 }, { "epoch": 0.25476874060072163, "grad_norm": 8.044388771057129, "learning_rate": 5.095225640781778e-06, "loss": 0.6939, "step": 42860 }, { "epoch": 0.25482818267739, "grad_norm": 8.689539909362793, "learning_rate": 5.096414475248467e-06, "loss": 0.704, "step": 42870 }, { "epoch": 0.2548876247540584, "grad_norm": 8.379098892211914, "learning_rate": 5.097603309715156e-06, "loss": 0.6378, "step": 42880 }, { "epoch": 0.2549470668307268, "grad_norm": 9.932162284851074, "learning_rate": 5.098792144181844e-06, "loss": 0.6941, "step": 42890 }, { "epoch": 0.2550065089073952, "grad_norm": 7.354084014892578, "learning_rate": 5.099980978648533e-06, "loss": 0.6591, "step": 42900 }, { "epoch": 0.2550659509840636, "grad_norm": 9.113981246948242, "learning_rate": 5.101169813115222e-06, "loss": 0.6801, "step": 42910 }, { "epoch": 0.25512539306073195, "grad_norm": 7.495548725128174, "learning_rate": 5.102358647581911e-06, "loss": 0.6982, "step": 42920 }, { "epoch": 0.25518483513740037, "grad_norm": 7.817584991455078, "learning_rate": 5.1035474820486e-06, "loss": 0.6684, "step": 42930 }, { "epoch": 0.2552442772140687, "grad_norm": 7.019515514373779, "learning_rate": 5.104736316515289e-06, "loss": 0.7034, "step": 42940 }, { "epoch": 0.25530371929073714, "grad_norm": 8.910148620605469, "learning_rate": 5.105925150981978e-06, "loss": 0.7359, "step": 42950 }, { "epoch": 0.25536316136740556, "grad_norm": 7.886959552764893, "learning_rate": 5.1071139854486666e-06, "loss": 0.6792, "step": 42960 }, { "epoch": 0.2554226034440739, "grad_norm": 9.588842391967773, "learning_rate": 5.108302819915355e-06, "loss": 0.6609, "step": 42970 }, { "epoch": 0.25548204552074233, "grad_norm": 10.715677261352539, "learning_rate": 5.109491654382044e-06, "loss": 0.7161, "step": 42980 }, { "epoch": 0.2555414875974107, "grad_norm": 7.624488830566406, "learning_rate": 5.1106804888487325e-06, "loss": 0.6864, "step": 42990 }, { "epoch": 0.2556009296740791, "grad_norm": 9.571202278137207, "learning_rate": 5.1118693233154214e-06, "loss": 0.671, "step": 43000 }, { "epoch": 0.25566037175074746, "grad_norm": 6.948971271514893, "learning_rate": 5.11305815778211e-06, "loss": 0.7109, "step": 43010 }, { "epoch": 0.2557198138274159, "grad_norm": 8.403243064880371, "learning_rate": 5.114246992248799e-06, "loss": 0.671, "step": 43020 }, { "epoch": 0.2557792559040843, "grad_norm": 8.811762809753418, "learning_rate": 5.115435826715489e-06, "loss": 0.6951, "step": 43030 }, { "epoch": 0.25583869798075265, "grad_norm": 7.370610237121582, "learning_rate": 5.116624661182178e-06, "loss": 0.6653, "step": 43040 }, { "epoch": 0.25589814005742106, "grad_norm": 7.493834972381592, "learning_rate": 5.117813495648867e-06, "loss": 0.663, "step": 43050 }, { "epoch": 0.2559575821340894, "grad_norm": 8.617761611938477, "learning_rate": 5.119002330115556e-06, "loss": 0.6582, "step": 43060 }, { "epoch": 0.25601702421075784, "grad_norm": 8.691250801086426, "learning_rate": 5.120191164582245e-06, "loss": 0.699, "step": 43070 }, { "epoch": 0.2560764662874262, "grad_norm": 9.907308578491211, "learning_rate": 5.121379999048933e-06, "loss": 0.7614, "step": 43080 }, { "epoch": 0.2561359083640946, "grad_norm": 7.020335674285889, "learning_rate": 5.122568833515622e-06, "loss": 0.6974, "step": 43090 }, { "epoch": 0.256195350440763, "grad_norm": 7.2941670417785645, "learning_rate": 5.123757667982311e-06, "loss": 0.726, "step": 43100 }, { "epoch": 0.2562547925174314, "grad_norm": 7.814408779144287, "learning_rate": 5.124946502449e-06, "loss": 0.6729, "step": 43110 }, { "epoch": 0.2563142345940998, "grad_norm": 7.7519989013671875, "learning_rate": 5.1261353369156886e-06, "loss": 0.7751, "step": 43120 }, { "epoch": 0.25637367667076816, "grad_norm": 8.649907112121582, "learning_rate": 5.1273241713823775e-06, "loss": 0.7159, "step": 43130 }, { "epoch": 0.2564331187474366, "grad_norm": 7.746328353881836, "learning_rate": 5.128513005849066e-06, "loss": 0.6873, "step": 43140 }, { "epoch": 0.25649256082410493, "grad_norm": 6.2933349609375, "learning_rate": 5.129701840315755e-06, "loss": 0.6829, "step": 43150 }, { "epoch": 0.25655200290077335, "grad_norm": 7.869711399078369, "learning_rate": 5.1308906747824434e-06, "loss": 0.6495, "step": 43160 }, { "epoch": 0.2566114449774417, "grad_norm": 7.815090179443359, "learning_rate": 5.132079509249132e-06, "loss": 0.6671, "step": 43170 }, { "epoch": 0.2566708870541101, "grad_norm": 9.092263221740723, "learning_rate": 5.133268343715821e-06, "loss": 0.6614, "step": 43180 }, { "epoch": 0.25673032913077853, "grad_norm": 9.424602508544922, "learning_rate": 5.13445717818251e-06, "loss": 0.7183, "step": 43190 }, { "epoch": 0.2567897712074469, "grad_norm": 8.989652633666992, "learning_rate": 5.135646012649199e-06, "loss": 0.6085, "step": 43200 }, { "epoch": 0.2568492132841153, "grad_norm": 9.052350044250488, "learning_rate": 5.136834847115888e-06, "loss": 0.7467, "step": 43210 }, { "epoch": 0.25690865536078367, "grad_norm": 6.922346591949463, "learning_rate": 5.138023681582577e-06, "loss": 0.6173, "step": 43220 }, { "epoch": 0.2569680974374521, "grad_norm": 7.613600254058838, "learning_rate": 5.139212516049266e-06, "loss": 0.6327, "step": 43230 }, { "epoch": 0.25702753951412044, "grad_norm": 10.327995300292969, "learning_rate": 5.140401350515955e-06, "loss": 0.6645, "step": 43240 }, { "epoch": 0.25708698159078885, "grad_norm": 6.923701286315918, "learning_rate": 5.141590184982643e-06, "loss": 0.6618, "step": 43250 }, { "epoch": 0.25714642366745727, "grad_norm": 8.713475227355957, "learning_rate": 5.142779019449332e-06, "loss": 0.6947, "step": 43260 }, { "epoch": 0.25720586574412563, "grad_norm": 6.406060695648193, "learning_rate": 5.143967853916021e-06, "loss": 0.6693, "step": 43270 }, { "epoch": 0.25726530782079404, "grad_norm": 7.51275110244751, "learning_rate": 5.14515668838271e-06, "loss": 0.7414, "step": 43280 }, { "epoch": 0.2573247498974624, "grad_norm": 7.355441570281982, "learning_rate": 5.146345522849399e-06, "loss": 0.6518, "step": 43290 }, { "epoch": 0.2573841919741308, "grad_norm": 8.0355806350708, "learning_rate": 5.1475343573160876e-06, "loss": 0.6896, "step": 43300 }, { "epoch": 0.2574436340507992, "grad_norm": 8.76280689239502, "learning_rate": 5.1487231917827765e-06, "loss": 0.6587, "step": 43310 }, { "epoch": 0.2575030761274676, "grad_norm": 9.056510925292969, "learning_rate": 5.149912026249465e-06, "loss": 0.6791, "step": 43320 }, { "epoch": 0.257562518204136, "grad_norm": 8.893317222595215, "learning_rate": 5.1511008607161535e-06, "loss": 0.7563, "step": 43330 }, { "epoch": 0.25762196028080436, "grad_norm": 5.839430809020996, "learning_rate": 5.1522896951828424e-06, "loss": 0.6164, "step": 43340 }, { "epoch": 0.2576814023574728, "grad_norm": 8.014269828796387, "learning_rate": 5.153478529649531e-06, "loss": 0.6538, "step": 43350 }, { "epoch": 0.25774084443414114, "grad_norm": 9.224139213562012, "learning_rate": 5.15466736411622e-06, "loss": 0.6876, "step": 43360 }, { "epoch": 0.25780028651080955, "grad_norm": 6.528409004211426, "learning_rate": 5.155856198582909e-06, "loss": 0.6794, "step": 43370 }, { "epoch": 0.2578597285874779, "grad_norm": 8.357929229736328, "learning_rate": 5.157045033049599e-06, "loss": 0.6895, "step": 43380 }, { "epoch": 0.2579191706641463, "grad_norm": 8.485060691833496, "learning_rate": 5.158233867516288e-06, "loss": 0.698, "step": 43390 }, { "epoch": 0.25797861274081474, "grad_norm": 7.414381980895996, "learning_rate": 5.159422701982977e-06, "loss": 0.7049, "step": 43400 }, { "epoch": 0.2580380548174831, "grad_norm": 7.407853603363037, "learning_rate": 5.160611536449666e-06, "loss": 0.7143, "step": 43410 }, { "epoch": 0.2580974968941515, "grad_norm": 8.551958084106445, "learning_rate": 5.161800370916355e-06, "loss": 0.7162, "step": 43420 }, { "epoch": 0.25815693897081987, "grad_norm": 8.813652992248535, "learning_rate": 5.162989205383044e-06, "loss": 0.663, "step": 43430 }, { "epoch": 0.2582163810474883, "grad_norm": 7.615962982177734, "learning_rate": 5.164178039849732e-06, "loss": 0.7167, "step": 43440 }, { "epoch": 0.25827582312415664, "grad_norm": 7.791604042053223, "learning_rate": 5.165366874316421e-06, "loss": 0.6332, "step": 43450 }, { "epoch": 0.25833526520082506, "grad_norm": 7.925768852233887, "learning_rate": 5.1665557087831096e-06, "loss": 0.7006, "step": 43460 }, { "epoch": 0.2583947072774935, "grad_norm": 9.005796432495117, "learning_rate": 5.1677445432497985e-06, "loss": 0.6717, "step": 43470 }, { "epoch": 0.25845414935416183, "grad_norm": 7.852642059326172, "learning_rate": 5.168933377716487e-06, "loss": 0.6566, "step": 43480 }, { "epoch": 0.25851359143083025, "grad_norm": 7.660552978515625, "learning_rate": 5.170122212183176e-06, "loss": 0.6574, "step": 43490 }, { "epoch": 0.2585730335074986, "grad_norm": 7.297536849975586, "learning_rate": 5.171311046649865e-06, "loss": 0.7371, "step": 43500 }, { "epoch": 0.258632475584167, "grad_norm": 7.9223713874816895, "learning_rate": 5.172499881116554e-06, "loss": 0.6948, "step": 43510 }, { "epoch": 0.2586919176608354, "grad_norm": 6.869146823883057, "learning_rate": 5.173688715583243e-06, "loss": 0.6997, "step": 43520 }, { "epoch": 0.2587513597375038, "grad_norm": 8.750908851623535, "learning_rate": 5.174877550049931e-06, "loss": 0.6665, "step": 43530 }, { "epoch": 0.25881080181417215, "grad_norm": 8.652442932128906, "learning_rate": 5.17606638451662e-06, "loss": 0.6987, "step": 43540 }, { "epoch": 0.25887024389084057, "grad_norm": 6.422769069671631, "learning_rate": 5.177255218983309e-06, "loss": 0.6714, "step": 43550 }, { "epoch": 0.258929685967509, "grad_norm": 8.191340446472168, "learning_rate": 5.178444053449998e-06, "loss": 0.6678, "step": 43560 }, { "epoch": 0.25898912804417734, "grad_norm": 9.9712495803833, "learning_rate": 5.179632887916687e-06, "loss": 0.755, "step": 43570 }, { "epoch": 0.25904857012084576, "grad_norm": 9.140434265136719, "learning_rate": 5.180821722383376e-06, "loss": 0.7141, "step": 43580 }, { "epoch": 0.2591080121975141, "grad_norm": 6.947434425354004, "learning_rate": 5.182010556850065e-06, "loss": 0.7172, "step": 43590 }, { "epoch": 0.25916745427418253, "grad_norm": 9.281682968139648, "learning_rate": 5.183199391316754e-06, "loss": 0.7023, "step": 43600 }, { "epoch": 0.2592268963508509, "grad_norm": 7.504465579986572, "learning_rate": 5.184388225783442e-06, "loss": 0.6872, "step": 43610 }, { "epoch": 0.2592863384275193, "grad_norm": 9.069347381591797, "learning_rate": 5.185577060250131e-06, "loss": 0.6629, "step": 43620 }, { "epoch": 0.2593457805041877, "grad_norm": 6.15777587890625, "learning_rate": 5.18676589471682e-06, "loss": 0.6487, "step": 43630 }, { "epoch": 0.2594052225808561, "grad_norm": 7.867959022521973, "learning_rate": 5.1879547291835085e-06, "loss": 0.6409, "step": 43640 }, { "epoch": 0.2594646646575245, "grad_norm": 9.887344360351562, "learning_rate": 5.1891435636501975e-06, "loss": 0.6954, "step": 43650 }, { "epoch": 0.25952410673419285, "grad_norm": 7.5539350509643555, "learning_rate": 5.190332398116886e-06, "loss": 0.7132, "step": 43660 }, { "epoch": 0.25958354881086126, "grad_norm": 7.913524627685547, "learning_rate": 5.191521232583575e-06, "loss": 0.7726, "step": 43670 }, { "epoch": 0.2596429908875296, "grad_norm": 8.16351318359375, "learning_rate": 5.192710067050264e-06, "loss": 0.6766, "step": 43680 }, { "epoch": 0.25970243296419804, "grad_norm": 8.224042892456055, "learning_rate": 5.193898901516952e-06, "loss": 0.6636, "step": 43690 }, { "epoch": 0.25976187504086645, "grad_norm": 6.0145955085754395, "learning_rate": 5.195087735983641e-06, "loss": 0.7369, "step": 43700 }, { "epoch": 0.2598213171175348, "grad_norm": 9.392007827758789, "learning_rate": 5.19627657045033e-06, "loss": 0.7036, "step": 43710 }, { "epoch": 0.2598807591942032, "grad_norm": 8.474193572998047, "learning_rate": 5.197465404917019e-06, "loss": 0.7357, "step": 43720 }, { "epoch": 0.2599402012708716, "grad_norm": 7.131742477416992, "learning_rate": 5.198654239383709e-06, "loss": 0.6898, "step": 43730 }, { "epoch": 0.25999964334754, "grad_norm": 7.063658714294434, "learning_rate": 5.199843073850398e-06, "loss": 0.6622, "step": 43740 }, { "epoch": 0.26005908542420836, "grad_norm": 7.963455677032471, "learning_rate": 5.201031908317087e-06, "loss": 0.7078, "step": 43750 }, { "epoch": 0.2601185275008768, "grad_norm": 8.167149543762207, "learning_rate": 5.202220742783776e-06, "loss": 0.6849, "step": 43760 }, { "epoch": 0.2601779695775452, "grad_norm": 6.650067329406738, "learning_rate": 5.203409577250465e-06, "loss": 0.6748, "step": 43770 }, { "epoch": 0.26023741165421355, "grad_norm": 9.078686714172363, "learning_rate": 5.2045984117171535e-06, "loss": 0.7413, "step": 43780 }, { "epoch": 0.26029685373088196, "grad_norm": 7.1763105392456055, "learning_rate": 5.2057872461838425e-06, "loss": 0.6647, "step": 43790 }, { "epoch": 0.2603562958075503, "grad_norm": 8.735259056091309, "learning_rate": 5.2069760806505305e-06, "loss": 0.6555, "step": 43800 }, { "epoch": 0.26041573788421873, "grad_norm": 6.718266010284424, "learning_rate": 5.2081649151172195e-06, "loss": 0.6996, "step": 43810 }, { "epoch": 0.2604751799608871, "grad_norm": 7.319570541381836, "learning_rate": 5.209353749583908e-06, "loss": 0.6817, "step": 43820 }, { "epoch": 0.2605346220375555, "grad_norm": 5.929262161254883, "learning_rate": 5.210542584050597e-06, "loss": 0.6825, "step": 43830 }, { "epoch": 0.2605940641142239, "grad_norm": 6.001536846160889, "learning_rate": 5.211731418517286e-06, "loss": 0.6587, "step": 43840 }, { "epoch": 0.2606535061908923, "grad_norm": 9.040863990783691, "learning_rate": 5.212920252983975e-06, "loss": 0.7191, "step": 43850 }, { "epoch": 0.2607129482675607, "grad_norm": 8.642928123474121, "learning_rate": 5.214109087450664e-06, "loss": 0.7162, "step": 43860 }, { "epoch": 0.26077239034422905, "grad_norm": 8.030396461486816, "learning_rate": 5.215297921917353e-06, "loss": 0.6687, "step": 43870 }, { "epoch": 0.26083183242089747, "grad_norm": 14.953481674194336, "learning_rate": 5.216486756384042e-06, "loss": 0.711, "step": 43880 }, { "epoch": 0.26089127449756583, "grad_norm": 8.176806449890137, "learning_rate": 5.21767559085073e-06, "loss": 0.6671, "step": 43890 }, { "epoch": 0.26095071657423424, "grad_norm": 6.660223960876465, "learning_rate": 5.218864425317419e-06, "loss": 0.6948, "step": 43900 }, { "epoch": 0.2610101586509026, "grad_norm": 7.406108379364014, "learning_rate": 5.220053259784108e-06, "loss": 0.7281, "step": 43910 }, { "epoch": 0.261069600727571, "grad_norm": 6.540164470672607, "learning_rate": 5.221242094250797e-06, "loss": 0.6734, "step": 43920 }, { "epoch": 0.26112904280423943, "grad_norm": 8.18419361114502, "learning_rate": 5.222430928717486e-06, "loss": 0.6543, "step": 43930 }, { "epoch": 0.2611884848809078, "grad_norm": 7.806873798370361, "learning_rate": 5.223619763184175e-06, "loss": 0.7179, "step": 43940 }, { "epoch": 0.2612479269575762, "grad_norm": 8.214240074157715, "learning_rate": 5.224808597650864e-06, "loss": 0.6296, "step": 43950 }, { "epoch": 0.26130736903424456, "grad_norm": 8.34037971496582, "learning_rate": 5.2259974321175525e-06, "loss": 0.7009, "step": 43960 }, { "epoch": 0.261366811110913, "grad_norm": 6.45550012588501, "learning_rate": 5.227186266584241e-06, "loss": 0.6369, "step": 43970 }, { "epoch": 0.26142625318758134, "grad_norm": 8.724284172058105, "learning_rate": 5.2283751010509295e-06, "loss": 0.6663, "step": 43980 }, { "epoch": 0.26148569526424975, "grad_norm": 7.133067607879639, "learning_rate": 5.2295639355176185e-06, "loss": 0.686, "step": 43990 }, { "epoch": 0.26154513734091817, "grad_norm": 6.856593132019043, "learning_rate": 5.230752769984307e-06, "loss": 0.6722, "step": 44000 }, { "epoch": 0.2616045794175865, "grad_norm": 8.05527400970459, "learning_rate": 5.231941604450996e-06, "loss": 0.6579, "step": 44010 }, { "epoch": 0.26166402149425494, "grad_norm": 9.274141311645508, "learning_rate": 5.233130438917685e-06, "loss": 0.6203, "step": 44020 }, { "epoch": 0.2617234635709233, "grad_norm": 8.690025329589844, "learning_rate": 5.234319273384374e-06, "loss": 0.6955, "step": 44030 }, { "epoch": 0.2617829056475917, "grad_norm": 6.875942707061768, "learning_rate": 5.235508107851063e-06, "loss": 0.6445, "step": 44040 }, { "epoch": 0.26184234772426007, "grad_norm": 10.016517639160156, "learning_rate": 5.236696942317752e-06, "loss": 0.7091, "step": 44050 }, { "epoch": 0.2619017898009285, "grad_norm": 7.5893874168396, "learning_rate": 5.23788577678444e-06, "loss": 0.6916, "step": 44060 }, { "epoch": 0.2619612318775969, "grad_norm": 8.660499572753906, "learning_rate": 5.239074611251131e-06, "loss": 0.732, "step": 44070 }, { "epoch": 0.26202067395426526, "grad_norm": 6.499180793762207, "learning_rate": 5.240263445717819e-06, "loss": 0.6376, "step": 44080 }, { "epoch": 0.2620801160309337, "grad_norm": 8.521968841552734, "learning_rate": 5.241452280184508e-06, "loss": 0.678, "step": 44090 }, { "epoch": 0.26213955810760203, "grad_norm": 7.888593673706055, "learning_rate": 5.242641114651197e-06, "loss": 0.6498, "step": 44100 }, { "epoch": 0.26219900018427045, "grad_norm": 8.463997840881348, "learning_rate": 5.243829949117886e-06, "loss": 0.6829, "step": 44110 }, { "epoch": 0.2622584422609388, "grad_norm": 7.653379440307617, "learning_rate": 5.2450187835845745e-06, "loss": 0.6884, "step": 44120 }, { "epoch": 0.2623178843376072, "grad_norm": 7.507410049438477, "learning_rate": 5.2462076180512634e-06, "loss": 0.7141, "step": 44130 }, { "epoch": 0.26237732641427564, "grad_norm": 8.217045783996582, "learning_rate": 5.247396452517952e-06, "loss": 0.7018, "step": 44140 }, { "epoch": 0.262436768490944, "grad_norm": 7.3805131912231445, "learning_rate": 5.248585286984641e-06, "loss": 0.6657, "step": 44150 }, { "epoch": 0.2624962105676124, "grad_norm": 7.10269832611084, "learning_rate": 5.24977412145133e-06, "loss": 0.747, "step": 44160 }, { "epoch": 0.26255565264428077, "grad_norm": 8.947636604309082, "learning_rate": 5.250962955918018e-06, "loss": 0.6518, "step": 44170 }, { "epoch": 0.2626150947209492, "grad_norm": 8.656938552856445, "learning_rate": 5.252151790384707e-06, "loss": 0.6362, "step": 44180 }, { "epoch": 0.26267453679761754, "grad_norm": 9.255526542663574, "learning_rate": 5.253340624851396e-06, "loss": 0.6408, "step": 44190 }, { "epoch": 0.26273397887428596, "grad_norm": 7.384066104888916, "learning_rate": 5.254529459318085e-06, "loss": 0.7281, "step": 44200 }, { "epoch": 0.2627934209509543, "grad_norm": 10.122702598571777, "learning_rate": 5.255718293784774e-06, "loss": 0.7052, "step": 44210 }, { "epoch": 0.26285286302762273, "grad_norm": 10.28244400024414, "learning_rate": 5.256907128251463e-06, "loss": 0.6924, "step": 44220 }, { "epoch": 0.26291230510429114, "grad_norm": 7.201349258422852, "learning_rate": 5.258095962718152e-06, "loss": 0.6691, "step": 44230 }, { "epoch": 0.2629717471809595, "grad_norm": 9.161906242370605, "learning_rate": 5.259284797184841e-06, "loss": 0.7043, "step": 44240 }, { "epoch": 0.2630311892576279, "grad_norm": 6.468608856201172, "learning_rate": 5.260473631651529e-06, "loss": 0.6735, "step": 44250 }, { "epoch": 0.2630906313342963, "grad_norm": 7.762450695037842, "learning_rate": 5.261662466118218e-06, "loss": 0.6464, "step": 44260 }, { "epoch": 0.2631500734109647, "grad_norm": 8.680601119995117, "learning_rate": 5.262851300584907e-06, "loss": 0.6493, "step": 44270 }, { "epoch": 0.26320951548763305, "grad_norm": 8.600776672363281, "learning_rate": 5.264040135051596e-06, "loss": 0.6531, "step": 44280 }, { "epoch": 0.26326895756430146, "grad_norm": 8.44565486907959, "learning_rate": 5.265228969518285e-06, "loss": 0.6647, "step": 44290 }, { "epoch": 0.2633283996409699, "grad_norm": 7.483424186706543, "learning_rate": 5.2664178039849735e-06, "loss": 0.6616, "step": 44300 }, { "epoch": 0.26338784171763824, "grad_norm": 7.082796096801758, "learning_rate": 5.2676066384516624e-06, "loss": 0.6129, "step": 44310 }, { "epoch": 0.26344728379430665, "grad_norm": 7.612521171569824, "learning_rate": 5.268795472918351e-06, "loss": 0.6567, "step": 44320 }, { "epoch": 0.263506725870975, "grad_norm": 8.011632919311523, "learning_rate": 5.2699843073850395e-06, "loss": 0.606, "step": 44330 }, { "epoch": 0.2635661679476434, "grad_norm": 7.63215446472168, "learning_rate": 5.271173141851728e-06, "loss": 0.6918, "step": 44340 }, { "epoch": 0.2636256100243118, "grad_norm": 7.615808963775635, "learning_rate": 5.272361976318417e-06, "loss": 0.6955, "step": 44350 }, { "epoch": 0.2636850521009802, "grad_norm": 8.06999397277832, "learning_rate": 5.273550810785106e-06, "loss": 0.7224, "step": 44360 }, { "epoch": 0.2637444941776486, "grad_norm": 8.941339492797852, "learning_rate": 5.274739645251795e-06, "loss": 0.7129, "step": 44370 }, { "epoch": 0.263803936254317, "grad_norm": 8.027853965759277, "learning_rate": 5.275928479718484e-06, "loss": 0.6699, "step": 44380 }, { "epoch": 0.2638633783309854, "grad_norm": 9.492059707641602, "learning_rate": 5.277117314185173e-06, "loss": 0.6607, "step": 44390 }, { "epoch": 0.26392282040765375, "grad_norm": 7.140674114227295, "learning_rate": 5.278306148651862e-06, "loss": 0.6089, "step": 44400 }, { "epoch": 0.26398226248432216, "grad_norm": 7.592512130737305, "learning_rate": 5.279494983118551e-06, "loss": 0.6872, "step": 44410 }, { "epoch": 0.2640417045609905, "grad_norm": 6.666829586029053, "learning_rate": 5.280683817585241e-06, "loss": 0.6679, "step": 44420 }, { "epoch": 0.26410114663765893, "grad_norm": 6.6802287101745605, "learning_rate": 5.2818726520519296e-06, "loss": 0.7068, "step": 44430 }, { "epoch": 0.26416058871432735, "grad_norm": 6.603287220001221, "learning_rate": 5.283061486518618e-06, "loss": 0.6431, "step": 44440 }, { "epoch": 0.2642200307909957, "grad_norm": 7.629240036010742, "learning_rate": 5.284250320985307e-06, "loss": 0.6336, "step": 44450 }, { "epoch": 0.2642794728676641, "grad_norm": 8.017830848693848, "learning_rate": 5.2854391554519955e-06, "loss": 0.6491, "step": 44460 }, { "epoch": 0.2643389149443325, "grad_norm": 7.313087463378906, "learning_rate": 5.2866279899186844e-06, "loss": 0.7013, "step": 44470 }, { "epoch": 0.2643983570210009, "grad_norm": 7.43583345413208, "learning_rate": 5.287816824385373e-06, "loss": 0.7278, "step": 44480 }, { "epoch": 0.26445779909766925, "grad_norm": 7.095941543579102, "learning_rate": 5.289005658852062e-06, "loss": 0.6758, "step": 44490 }, { "epoch": 0.26451724117433767, "grad_norm": 8.13096809387207, "learning_rate": 5.290194493318751e-06, "loss": 0.6697, "step": 44500 }, { "epoch": 0.2645766832510061, "grad_norm": 8.443222999572754, "learning_rate": 5.29138332778544e-06, "loss": 0.7096, "step": 44510 }, { "epoch": 0.26463612532767444, "grad_norm": 9.179708480834961, "learning_rate": 5.292572162252129e-06, "loss": 0.7355, "step": 44520 }, { "epoch": 0.26469556740434286, "grad_norm": 7.458261966705322, "learning_rate": 5.293760996718817e-06, "loss": 0.6307, "step": 44530 }, { "epoch": 0.2647550094810112, "grad_norm": 8.772503852844238, "learning_rate": 5.294949831185506e-06, "loss": 0.6854, "step": 44540 }, { "epoch": 0.26481445155767963, "grad_norm": 8.829267501831055, "learning_rate": 5.296138665652195e-06, "loss": 0.7122, "step": 44550 }, { "epoch": 0.264873893634348, "grad_norm": 8.645195007324219, "learning_rate": 5.297327500118884e-06, "loss": 0.6615, "step": 44560 }, { "epoch": 0.2649333357110164, "grad_norm": 7.534760475158691, "learning_rate": 5.298516334585573e-06, "loss": 0.6575, "step": 44570 }, { "epoch": 0.26499277778768476, "grad_norm": 7.952970504760742, "learning_rate": 5.299705169052262e-06, "loss": 0.7116, "step": 44580 }, { "epoch": 0.2650522198643532, "grad_norm": 9.537023544311523, "learning_rate": 5.300894003518951e-06, "loss": 0.6606, "step": 44590 }, { "epoch": 0.2651116619410216, "grad_norm": 9.538995742797852, "learning_rate": 5.30208283798564e-06, "loss": 0.6237, "step": 44600 }, { "epoch": 0.26517110401768995, "grad_norm": 8.322189331054688, "learning_rate": 5.303271672452328e-06, "loss": 0.6947, "step": 44610 }, { "epoch": 0.26523054609435837, "grad_norm": 7.204923152923584, "learning_rate": 5.304460506919017e-06, "loss": 0.679, "step": 44620 }, { "epoch": 0.2652899881710267, "grad_norm": 8.34470272064209, "learning_rate": 5.3056493413857056e-06, "loss": 0.6832, "step": 44630 }, { "epoch": 0.26534943024769514, "grad_norm": 8.01718807220459, "learning_rate": 5.3068381758523945e-06, "loss": 0.7216, "step": 44640 }, { "epoch": 0.2654088723243635, "grad_norm": 7.971670150756836, "learning_rate": 5.3080270103190834e-06, "loss": 0.7032, "step": 44650 }, { "epoch": 0.2654683144010319, "grad_norm": 7.400705337524414, "learning_rate": 5.309215844785772e-06, "loss": 0.6502, "step": 44660 }, { "epoch": 0.2655277564777003, "grad_norm": 7.443565845489502, "learning_rate": 5.310404679252461e-06, "loss": 0.658, "step": 44670 }, { "epoch": 0.2655871985543687, "grad_norm": 7.069161891937256, "learning_rate": 5.31159351371915e-06, "loss": 0.7356, "step": 44680 }, { "epoch": 0.2656466406310371, "grad_norm": 8.440072059631348, "learning_rate": 5.312782348185838e-06, "loss": 0.7195, "step": 44690 }, { "epoch": 0.26570608270770546, "grad_norm": 7.686047077178955, "learning_rate": 5.313971182652527e-06, "loss": 0.6636, "step": 44700 }, { "epoch": 0.2657655247843739, "grad_norm": 9.38893985748291, "learning_rate": 5.315160017119216e-06, "loss": 0.7086, "step": 44710 }, { "epoch": 0.26582496686104223, "grad_norm": 13.084027290344238, "learning_rate": 5.316348851585905e-06, "loss": 0.6407, "step": 44720 }, { "epoch": 0.26588440893771065, "grad_norm": 7.311795711517334, "learning_rate": 5.317537686052594e-06, "loss": 0.6792, "step": 44730 }, { "epoch": 0.26594385101437906, "grad_norm": 7.997437477111816, "learning_rate": 5.318726520519283e-06, "loss": 0.6356, "step": 44740 }, { "epoch": 0.2660032930910474, "grad_norm": 7.103694915771484, "learning_rate": 5.319915354985972e-06, "loss": 0.6418, "step": 44750 }, { "epoch": 0.26606273516771584, "grad_norm": 6.730091571807861, "learning_rate": 5.321104189452661e-06, "loss": 0.6848, "step": 44760 }, { "epoch": 0.2661221772443842, "grad_norm": 5.782465934753418, "learning_rate": 5.3222930239193506e-06, "loss": 0.6801, "step": 44770 }, { "epoch": 0.2661816193210526, "grad_norm": 8.289017677307129, "learning_rate": 5.3234818583860395e-06, "loss": 0.6685, "step": 44780 }, { "epoch": 0.26624106139772097, "grad_norm": 6.746002674102783, "learning_rate": 5.324670692852728e-06, "loss": 0.7135, "step": 44790 }, { "epoch": 0.2663005034743894, "grad_norm": 6.74860954284668, "learning_rate": 5.3258595273194165e-06, "loss": 0.6415, "step": 44800 }, { "epoch": 0.2663599455510578, "grad_norm": 8.696287155151367, "learning_rate": 5.327048361786105e-06, "loss": 0.6509, "step": 44810 }, { "epoch": 0.26641938762772616, "grad_norm": 7.840359210968018, "learning_rate": 5.328237196252794e-06, "loss": 0.698, "step": 44820 }, { "epoch": 0.26647882970439457, "grad_norm": 5.706617832183838, "learning_rate": 5.329426030719483e-06, "loss": 0.6638, "step": 44830 }, { "epoch": 0.26653827178106293, "grad_norm": 7.454518795013428, "learning_rate": 5.330614865186172e-06, "loss": 0.6694, "step": 44840 }, { "epoch": 0.26659771385773134, "grad_norm": 7.706404685974121, "learning_rate": 5.331803699652861e-06, "loss": 0.6687, "step": 44850 }, { "epoch": 0.2666571559343997, "grad_norm": 7.756509780883789, "learning_rate": 5.33299253411955e-06, "loss": 0.5988, "step": 44860 }, { "epoch": 0.2667165980110681, "grad_norm": 7.544652462005615, "learning_rate": 5.334181368586239e-06, "loss": 0.7096, "step": 44870 }, { "epoch": 0.26677604008773653, "grad_norm": 7.291883945465088, "learning_rate": 5.335370203052928e-06, "loss": 0.7111, "step": 44880 }, { "epoch": 0.2668354821644049, "grad_norm": 7.624205589294434, "learning_rate": 5.336559037519616e-06, "loss": 0.7256, "step": 44890 }, { "epoch": 0.2668949242410733, "grad_norm": 6.973611831665039, "learning_rate": 5.337747871986305e-06, "loss": 0.7099, "step": 44900 }, { "epoch": 0.26695436631774166, "grad_norm": 7.250479221343994, "learning_rate": 5.338936706452994e-06, "loss": 0.6667, "step": 44910 }, { "epoch": 0.2670138083944101, "grad_norm": 6.953849792480469, "learning_rate": 5.340125540919683e-06, "loss": 0.608, "step": 44920 }, { "epoch": 0.26707325047107844, "grad_norm": 7.837576866149902, "learning_rate": 5.341314375386372e-06, "loss": 0.756, "step": 44930 }, { "epoch": 0.26713269254774685, "grad_norm": 6.253084182739258, "learning_rate": 5.342503209853061e-06, "loss": 0.6432, "step": 44940 }, { "epoch": 0.2671921346244152, "grad_norm": 6.975224018096924, "learning_rate": 5.3436920443197496e-06, "loss": 0.6498, "step": 44950 }, { "epoch": 0.2672515767010836, "grad_norm": 8.798545837402344, "learning_rate": 5.3448808787864385e-06, "loss": 0.6958, "step": 44960 }, { "epoch": 0.26731101877775204, "grad_norm": 8.180671691894531, "learning_rate": 5.3460697132531266e-06, "loss": 0.6534, "step": 44970 }, { "epoch": 0.2673704608544204, "grad_norm": 9.002205848693848, "learning_rate": 5.3472585477198155e-06, "loss": 0.6258, "step": 44980 }, { "epoch": 0.2674299029310888, "grad_norm": 12.42409610748291, "learning_rate": 5.348447382186504e-06, "loss": 0.7465, "step": 44990 }, { "epoch": 0.2674893450077572, "grad_norm": 9.766974449157715, "learning_rate": 5.349636216653193e-06, "loss": 0.66, "step": 45000 }, { "epoch": 0.2675487870844256, "grad_norm": 9.531630516052246, "learning_rate": 5.350825051119882e-06, "loss": 0.6697, "step": 45010 }, { "epoch": 0.26760822916109395, "grad_norm": 8.368926048278809, "learning_rate": 5.352013885586571e-06, "loss": 0.7305, "step": 45020 }, { "epoch": 0.26766767123776236, "grad_norm": 7.945440292358398, "learning_rate": 5.35320272005326e-06, "loss": 0.6854, "step": 45030 }, { "epoch": 0.2677271133144308, "grad_norm": 8.459779739379883, "learning_rate": 5.354391554519949e-06, "loss": 0.6383, "step": 45040 }, { "epoch": 0.26778655539109913, "grad_norm": 6.850159645080566, "learning_rate": 5.355580388986638e-06, "loss": 0.6607, "step": 45050 }, { "epoch": 0.26784599746776755, "grad_norm": 6.377674579620361, "learning_rate": 5.356769223453326e-06, "loss": 0.6864, "step": 45060 }, { "epoch": 0.2679054395444359, "grad_norm": 8.524633407592773, "learning_rate": 5.357958057920015e-06, "loss": 0.6398, "step": 45070 }, { "epoch": 0.2679648816211043, "grad_norm": 7.9928131103515625, "learning_rate": 5.359146892386704e-06, "loss": 0.6431, "step": 45080 }, { "epoch": 0.2680243236977727, "grad_norm": 7.914023399353027, "learning_rate": 5.360335726853393e-06, "loss": 0.7176, "step": 45090 }, { "epoch": 0.2680837657744411, "grad_norm": 6.697223663330078, "learning_rate": 5.361524561320082e-06, "loss": 0.6965, "step": 45100 }, { "epoch": 0.2681432078511095, "grad_norm": 6.739415645599365, "learning_rate": 5.3627133957867715e-06, "loss": 0.7093, "step": 45110 }, { "epoch": 0.26820264992777787, "grad_norm": 7.934973239898682, "learning_rate": 5.3639022302534605e-06, "loss": 0.7248, "step": 45120 }, { "epoch": 0.2682620920044463, "grad_norm": 6.091457366943359, "learning_rate": 5.365091064720149e-06, "loss": 0.6942, "step": 45130 }, { "epoch": 0.26832153408111464, "grad_norm": 8.718656539916992, "learning_rate": 5.366279899186838e-06, "loss": 0.6564, "step": 45140 }, { "epoch": 0.26838097615778306, "grad_norm": 9.621609687805176, "learning_rate": 5.367468733653527e-06, "loss": 0.6745, "step": 45150 }, { "epoch": 0.2684404182344514, "grad_norm": 7.488471031188965, "learning_rate": 5.368657568120216e-06, "loss": 0.7182, "step": 45160 }, { "epoch": 0.26849986031111983, "grad_norm": 8.258501052856445, "learning_rate": 5.369846402586904e-06, "loss": 0.6929, "step": 45170 }, { "epoch": 0.26855930238778825, "grad_norm": 8.050897598266602, "learning_rate": 5.371035237053593e-06, "loss": 0.7062, "step": 45180 }, { "epoch": 0.2686187444644566, "grad_norm": 9.638065338134766, "learning_rate": 5.372224071520282e-06, "loss": 0.6649, "step": 45190 }, { "epoch": 0.268678186541125, "grad_norm": 6.311649799346924, "learning_rate": 5.373412905986971e-06, "loss": 0.643, "step": 45200 }, { "epoch": 0.2687376286177934, "grad_norm": 9.512200355529785, "learning_rate": 5.37460174045366e-06, "loss": 0.6754, "step": 45210 }, { "epoch": 0.2687970706944618, "grad_norm": 8.115272521972656, "learning_rate": 5.375790574920349e-06, "loss": 0.6517, "step": 45220 }, { "epoch": 0.26885651277113015, "grad_norm": 7.9286699295043945, "learning_rate": 5.376979409387038e-06, "loss": 0.7076, "step": 45230 }, { "epoch": 0.26891595484779857, "grad_norm": 8.596823692321777, "learning_rate": 5.378168243853727e-06, "loss": 0.7188, "step": 45240 }, { "epoch": 0.268975396924467, "grad_norm": 7.591437339782715, "learning_rate": 5.379357078320415e-06, "loss": 0.5966, "step": 45250 }, { "epoch": 0.26903483900113534, "grad_norm": 11.0667085647583, "learning_rate": 5.380545912787104e-06, "loss": 0.7406, "step": 45260 }, { "epoch": 0.26909428107780375, "grad_norm": 8.976066589355469, "learning_rate": 5.381734747253793e-06, "loss": 0.6883, "step": 45270 }, { "epoch": 0.2691537231544721, "grad_norm": 8.038700103759766, "learning_rate": 5.382923581720482e-06, "loss": 0.6825, "step": 45280 }, { "epoch": 0.2692131652311405, "grad_norm": 7.17453670501709, "learning_rate": 5.3841124161871705e-06, "loss": 0.6254, "step": 45290 }, { "epoch": 0.2692726073078089, "grad_norm": 8.629732131958008, "learning_rate": 5.3853012506538595e-06, "loss": 0.7075, "step": 45300 }, { "epoch": 0.2693320493844773, "grad_norm": 9.066205978393555, "learning_rate": 5.386490085120548e-06, "loss": 0.6592, "step": 45310 }, { "epoch": 0.26939149146114566, "grad_norm": 6.94553279876709, "learning_rate": 5.387678919587237e-06, "loss": 0.7043, "step": 45320 }, { "epoch": 0.2694509335378141, "grad_norm": 8.313529014587402, "learning_rate": 5.388867754053925e-06, "loss": 0.674, "step": 45330 }, { "epoch": 0.2695103756144825, "grad_norm": 9.187012672424316, "learning_rate": 5.390056588520614e-06, "loss": 0.7313, "step": 45340 }, { "epoch": 0.26956981769115085, "grad_norm": 7.384885311126709, "learning_rate": 5.391245422987303e-06, "loss": 0.6734, "step": 45350 }, { "epoch": 0.26962925976781926, "grad_norm": 9.510638236999512, "learning_rate": 5.392434257453992e-06, "loss": 0.6845, "step": 45360 }, { "epoch": 0.2696887018444876, "grad_norm": 8.697367668151855, "learning_rate": 5.393623091920681e-06, "loss": 0.6712, "step": 45370 }, { "epoch": 0.26974814392115604, "grad_norm": 8.891432762145996, "learning_rate": 5.39481192638737e-06, "loss": 0.7342, "step": 45380 }, { "epoch": 0.2698075859978244, "grad_norm": 8.347870826721191, "learning_rate": 5.396000760854059e-06, "loss": 0.6491, "step": 45390 }, { "epoch": 0.2698670280744928, "grad_norm": 6.687046051025391, "learning_rate": 5.397189595320748e-06, "loss": 0.756, "step": 45400 }, { "epoch": 0.2699264701511612, "grad_norm": 7.773989677429199, "learning_rate": 5.398378429787437e-06, "loss": 0.7124, "step": 45410 }, { "epoch": 0.2699859122278296, "grad_norm": 5.962563514709473, "learning_rate": 5.399567264254125e-06, "loss": 0.6813, "step": 45420 }, { "epoch": 0.270045354304498, "grad_norm": 8.15491008758545, "learning_rate": 5.400756098720814e-06, "loss": 0.6438, "step": 45430 }, { "epoch": 0.27010479638116636, "grad_norm": 7.13918399810791, "learning_rate": 5.401944933187503e-06, "loss": 0.6546, "step": 45440 }, { "epoch": 0.27016423845783477, "grad_norm": 8.241045951843262, "learning_rate": 5.403133767654192e-06, "loss": 0.6975, "step": 45450 }, { "epoch": 0.27022368053450313, "grad_norm": 9.760238647460938, "learning_rate": 5.4043226021208815e-06, "loss": 0.6998, "step": 45460 }, { "epoch": 0.27028312261117154, "grad_norm": 7.535851001739502, "learning_rate": 5.40551143658757e-06, "loss": 0.7309, "step": 45470 }, { "epoch": 0.27034256468783996, "grad_norm": 7.9448089599609375, "learning_rate": 5.406700271054259e-06, "loss": 0.6886, "step": 45480 }, { "epoch": 0.2704020067645083, "grad_norm": 7.792659282684326, "learning_rate": 5.407889105520948e-06, "loss": 0.6297, "step": 45490 }, { "epoch": 0.27046144884117673, "grad_norm": 7.058905124664307, "learning_rate": 5.409077939987637e-06, "loss": 0.6753, "step": 45500 }, { "epoch": 0.2705208909178451, "grad_norm": 7.408458232879639, "learning_rate": 5.410266774454326e-06, "loss": 0.6998, "step": 45510 }, { "epoch": 0.2705803329945135, "grad_norm": 6.997800827026367, "learning_rate": 5.411455608921015e-06, "loss": 0.7062, "step": 45520 }, { "epoch": 0.27063977507118187, "grad_norm": 6.248412132263184, "learning_rate": 5.412644443387703e-06, "loss": 0.6908, "step": 45530 }, { "epoch": 0.2706992171478503, "grad_norm": 9.875322341918945, "learning_rate": 5.413833277854392e-06, "loss": 0.7243, "step": 45540 }, { "epoch": 0.2707586592245187, "grad_norm": 8.159231185913086, "learning_rate": 5.415022112321081e-06, "loss": 0.7185, "step": 45550 }, { "epoch": 0.27081810130118705, "grad_norm": 7.6634111404418945, "learning_rate": 5.41621094678777e-06, "loss": 0.6842, "step": 45560 }, { "epoch": 0.27087754337785547, "grad_norm": 7.417211532592773, "learning_rate": 5.417399781254459e-06, "loss": 0.6931, "step": 45570 }, { "epoch": 0.2709369854545238, "grad_norm": 7.711521625518799, "learning_rate": 5.418588615721148e-06, "loss": 0.662, "step": 45580 }, { "epoch": 0.27099642753119224, "grad_norm": 9.15463638305664, "learning_rate": 5.419777450187837e-06, "loss": 0.678, "step": 45590 }, { "epoch": 0.2710558696078606, "grad_norm": 7.233700752258301, "learning_rate": 5.420966284654526e-06, "loss": 0.6964, "step": 45600 }, { "epoch": 0.271115311684529, "grad_norm": 7.561696529388428, "learning_rate": 5.422155119121214e-06, "loss": 0.6798, "step": 45610 }, { "epoch": 0.2711747537611974, "grad_norm": 7.368495941162109, "learning_rate": 5.423343953587903e-06, "loss": 0.6988, "step": 45620 }, { "epoch": 0.2712341958378658, "grad_norm": 10.372930526733398, "learning_rate": 5.4245327880545915e-06, "loss": 0.669, "step": 45630 }, { "epoch": 0.2712936379145342, "grad_norm": 6.818122863769531, "learning_rate": 5.4257216225212805e-06, "loss": 0.7113, "step": 45640 }, { "epoch": 0.27135307999120256, "grad_norm": 7.640570640563965, "learning_rate": 5.426910456987969e-06, "loss": 0.7721, "step": 45650 }, { "epoch": 0.271412522067871, "grad_norm": 7.364006996154785, "learning_rate": 5.428099291454658e-06, "loss": 0.7034, "step": 45660 }, { "epoch": 0.27147196414453933, "grad_norm": 8.534713745117188, "learning_rate": 5.429288125921347e-06, "loss": 0.7267, "step": 45670 }, { "epoch": 0.27153140622120775, "grad_norm": 10.089886665344238, "learning_rate": 5.430476960388036e-06, "loss": 0.6803, "step": 45680 }, { "epoch": 0.2715908482978761, "grad_norm": 10.294794082641602, "learning_rate": 5.431665794854725e-06, "loss": 0.6446, "step": 45690 }, { "epoch": 0.2716502903745445, "grad_norm": 10.306446075439453, "learning_rate": 5.432854629321413e-06, "loss": 0.686, "step": 45700 }, { "epoch": 0.27170973245121294, "grad_norm": 9.097801208496094, "learning_rate": 5.434043463788102e-06, "loss": 0.6596, "step": 45710 }, { "epoch": 0.2717691745278813, "grad_norm": 7.0532989501953125, "learning_rate": 5.435232298254791e-06, "loss": 0.656, "step": 45720 }, { "epoch": 0.2718286166045497, "grad_norm": 7.348850727081299, "learning_rate": 5.43642113272148e-06, "loss": 0.7265, "step": 45730 }, { "epoch": 0.27188805868121807, "grad_norm": 7.7770256996154785, "learning_rate": 5.437609967188169e-06, "loss": 0.6804, "step": 45740 }, { "epoch": 0.2719475007578865, "grad_norm": 9.484162330627441, "learning_rate": 5.438798801654858e-06, "loss": 0.7272, "step": 45750 }, { "epoch": 0.27200694283455484, "grad_norm": 9.476085662841797, "learning_rate": 5.439987636121547e-06, "loss": 0.6876, "step": 45760 }, { "epoch": 0.27206638491122326, "grad_norm": 7.849891662597656, "learning_rate": 5.441176470588236e-06, "loss": 0.6832, "step": 45770 }, { "epoch": 0.2721258269878917, "grad_norm": 5.864670753479004, "learning_rate": 5.442365305054924e-06, "loss": 0.6523, "step": 45780 }, { "epoch": 0.27218526906456003, "grad_norm": 7.2029619216918945, "learning_rate": 5.443554139521613e-06, "loss": 0.7121, "step": 45790 }, { "epoch": 0.27224471114122845, "grad_norm": 9.032480239868164, "learning_rate": 5.444742973988302e-06, "loss": 0.6969, "step": 45800 }, { "epoch": 0.2723041532178968, "grad_norm": 8.447834968566895, "learning_rate": 5.445931808454991e-06, "loss": 0.662, "step": 45810 }, { "epoch": 0.2723635952945652, "grad_norm": 7.870088577270508, "learning_rate": 5.44712064292168e-06, "loss": 0.7086, "step": 45820 }, { "epoch": 0.2724230373712336, "grad_norm": 7.534472465515137, "learning_rate": 5.448309477388369e-06, "loss": 0.6553, "step": 45830 }, { "epoch": 0.272482479447902, "grad_norm": 6.436639308929443, "learning_rate": 5.449498311855058e-06, "loss": 0.6797, "step": 45840 }, { "epoch": 0.2725419215245704, "grad_norm": 8.091401100158691, "learning_rate": 5.450687146321747e-06, "loss": 0.7036, "step": 45850 }, { "epoch": 0.27260136360123877, "grad_norm": 8.88653564453125, "learning_rate": 5.451875980788436e-06, "loss": 0.6426, "step": 45860 }, { "epoch": 0.2726608056779072, "grad_norm": 8.230795860290527, "learning_rate": 5.453064815255125e-06, "loss": 0.6764, "step": 45870 }, { "epoch": 0.27272024775457554, "grad_norm": 7.6634955406188965, "learning_rate": 5.454253649721814e-06, "loss": 0.6454, "step": 45880 }, { "epoch": 0.27277968983124395, "grad_norm": 9.31783676147461, "learning_rate": 5.455442484188502e-06, "loss": 0.6692, "step": 45890 }, { "epoch": 0.2728391319079123, "grad_norm": 9.722148895263672, "learning_rate": 5.456631318655191e-06, "loss": 0.7067, "step": 45900 }, { "epoch": 0.27289857398458073, "grad_norm": 7.163999557495117, "learning_rate": 5.45782015312188e-06, "loss": 0.6383, "step": 45910 }, { "epoch": 0.27295801606124914, "grad_norm": 7.094244480133057, "learning_rate": 5.459008987588569e-06, "loss": 0.6735, "step": 45920 }, { "epoch": 0.2730174581379175, "grad_norm": 9.282800674438477, "learning_rate": 5.460197822055258e-06, "loss": 0.7103, "step": 45930 }, { "epoch": 0.2730769002145859, "grad_norm": 7.530489921569824, "learning_rate": 5.461386656521947e-06, "loss": 0.7265, "step": 45940 }, { "epoch": 0.2731363422912543, "grad_norm": 6.342896461486816, "learning_rate": 5.4625754909886355e-06, "loss": 0.6215, "step": 45950 }, { "epoch": 0.2731957843679227, "grad_norm": 6.432606220245361, "learning_rate": 5.4637643254553244e-06, "loss": 0.657, "step": 45960 }, { "epoch": 0.27325522644459105, "grad_norm": 6.1652140617370605, "learning_rate": 5.4649531599220125e-06, "loss": 0.641, "step": 45970 }, { "epoch": 0.27331466852125946, "grad_norm": 6.845427989959717, "learning_rate": 5.4661419943887014e-06, "loss": 0.6814, "step": 45980 }, { "epoch": 0.2733741105979278, "grad_norm": 10.894950866699219, "learning_rate": 5.46733082885539e-06, "loss": 0.6577, "step": 45990 }, { "epoch": 0.27343355267459624, "grad_norm": 8.17531681060791, "learning_rate": 5.468519663322079e-06, "loss": 0.7492, "step": 46000 }, { "epoch": 0.27349299475126465, "grad_norm": 6.472565174102783, "learning_rate": 5.469708497788768e-06, "loss": 0.6418, "step": 46010 }, { "epoch": 0.273552436827933, "grad_norm": 7.851308345794678, "learning_rate": 5.470897332255457e-06, "loss": 0.7478, "step": 46020 }, { "epoch": 0.2736118789046014, "grad_norm": 7.958942890167236, "learning_rate": 5.472086166722146e-06, "loss": 0.6368, "step": 46030 }, { "epoch": 0.2736713209812698, "grad_norm": 6.01207971572876, "learning_rate": 5.473275001188835e-06, "loss": 0.6388, "step": 46040 }, { "epoch": 0.2737307630579382, "grad_norm": 7.59238862991333, "learning_rate": 5.474463835655524e-06, "loss": 0.6093, "step": 46050 }, { "epoch": 0.27379020513460656, "grad_norm": 6.88129186630249, "learning_rate": 5.475652670122212e-06, "loss": 0.7259, "step": 46060 }, { "epoch": 0.27384964721127497, "grad_norm": 7.252191543579102, "learning_rate": 5.476841504588901e-06, "loss": 0.6657, "step": 46070 }, { "epoch": 0.2739090892879434, "grad_norm": 6.4667558670043945, "learning_rate": 5.47803033905559e-06, "loss": 0.6411, "step": 46080 }, { "epoch": 0.27396853136461174, "grad_norm": 8.967543601989746, "learning_rate": 5.479219173522279e-06, "loss": 0.6649, "step": 46090 }, { "epoch": 0.27402797344128016, "grad_norm": 6.997337341308594, "learning_rate": 5.480408007988968e-06, "loss": 0.6879, "step": 46100 }, { "epoch": 0.2740874155179485, "grad_norm": 7.375796794891357, "learning_rate": 5.481596842455657e-06, "loss": 0.7001, "step": 46110 }, { "epoch": 0.27414685759461693, "grad_norm": 8.304346084594727, "learning_rate": 5.482785676922346e-06, "loss": 0.7198, "step": 46120 }, { "epoch": 0.2742062996712853, "grad_norm": 7.58240270614624, "learning_rate": 5.4839745113890345e-06, "loss": 0.6996, "step": 46130 }, { "epoch": 0.2742657417479537, "grad_norm": 6.419028282165527, "learning_rate": 5.485163345855723e-06, "loss": 0.6446, "step": 46140 }, { "epoch": 0.2743251838246221, "grad_norm": 9.647520065307617, "learning_rate": 5.486352180322413e-06, "loss": 0.6932, "step": 46150 }, { "epoch": 0.2743846259012905, "grad_norm": 7.277462005615234, "learning_rate": 5.487541014789102e-06, "loss": 0.7527, "step": 46160 }, { "epoch": 0.2744440679779589, "grad_norm": 9.711889266967773, "learning_rate": 5.48872984925579e-06, "loss": 0.6767, "step": 46170 }, { "epoch": 0.27450351005462725, "grad_norm": 6.014809608459473, "learning_rate": 5.489918683722479e-06, "loss": 0.6253, "step": 46180 }, { "epoch": 0.27456295213129567, "grad_norm": 7.528846740722656, "learning_rate": 5.491107518189168e-06, "loss": 0.652, "step": 46190 }, { "epoch": 0.274622394207964, "grad_norm": 7.298125743865967, "learning_rate": 5.492296352655857e-06, "loss": 0.6636, "step": 46200 }, { "epoch": 0.27468183628463244, "grad_norm": 6.484012126922607, "learning_rate": 5.493485187122546e-06, "loss": 0.6124, "step": 46210 }, { "epoch": 0.27474127836130086, "grad_norm": 7.227214813232422, "learning_rate": 5.494674021589235e-06, "loss": 0.7359, "step": 46220 }, { "epoch": 0.2748007204379692, "grad_norm": 6.659952163696289, "learning_rate": 5.495862856055924e-06, "loss": 0.6709, "step": 46230 }, { "epoch": 0.27486016251463763, "grad_norm": 9.089527130126953, "learning_rate": 5.497051690522613e-06, "loss": 0.6426, "step": 46240 }, { "epoch": 0.274919604591306, "grad_norm": 8.507716178894043, "learning_rate": 5.498240524989301e-06, "loss": 0.7108, "step": 46250 }, { "epoch": 0.2749790466679744, "grad_norm": 8.27708911895752, "learning_rate": 5.49942935945599e-06, "loss": 0.6619, "step": 46260 }, { "epoch": 0.27503848874464276, "grad_norm": 8.298377990722656, "learning_rate": 5.500618193922679e-06, "loss": 0.7449, "step": 46270 }, { "epoch": 0.2750979308213112, "grad_norm": 7.05069637298584, "learning_rate": 5.5018070283893676e-06, "loss": 0.7424, "step": 46280 }, { "epoch": 0.2751573728979796, "grad_norm": 8.289318084716797, "learning_rate": 5.5029958628560565e-06, "loss": 0.6412, "step": 46290 }, { "epoch": 0.27521681497464795, "grad_norm": 8.276959419250488, "learning_rate": 5.504184697322745e-06, "loss": 0.748, "step": 46300 }, { "epoch": 0.27527625705131636, "grad_norm": 11.169378280639648, "learning_rate": 5.505373531789434e-06, "loss": 0.7725, "step": 46310 }, { "epoch": 0.2753356991279847, "grad_norm": 7.960766315460205, "learning_rate": 5.506562366256123e-06, "loss": 0.6571, "step": 46320 }, { "epoch": 0.27539514120465314, "grad_norm": 7.332955360412598, "learning_rate": 5.507751200722811e-06, "loss": 0.6589, "step": 46330 }, { "epoch": 0.2754545832813215, "grad_norm": 7.718024253845215, "learning_rate": 5.5089400351895e-06, "loss": 0.6573, "step": 46340 }, { "epoch": 0.2755140253579899, "grad_norm": 7.574776649475098, "learning_rate": 5.510128869656189e-06, "loss": 0.7163, "step": 46350 }, { "epoch": 0.27557346743465827, "grad_norm": 6.587515830993652, "learning_rate": 5.511317704122878e-06, "loss": 0.6182, "step": 46360 }, { "epoch": 0.2756329095113267, "grad_norm": 8.123135566711426, "learning_rate": 5.512506538589567e-06, "loss": 0.6685, "step": 46370 }, { "epoch": 0.2756923515879951, "grad_norm": 9.715811729431152, "learning_rate": 5.513695373056256e-06, "loss": 0.69, "step": 46380 }, { "epoch": 0.27575179366466346, "grad_norm": 7.10280179977417, "learning_rate": 5.514884207522945e-06, "loss": 0.6528, "step": 46390 }, { "epoch": 0.2758112357413319, "grad_norm": 9.553715705871582, "learning_rate": 5.516073041989634e-06, "loss": 0.652, "step": 46400 }, { "epoch": 0.27587067781800023, "grad_norm": 8.204078674316406, "learning_rate": 5.517261876456323e-06, "loss": 0.6884, "step": 46410 }, { "epoch": 0.27593011989466865, "grad_norm": 7.883337497711182, "learning_rate": 5.518450710923011e-06, "loss": 0.6801, "step": 46420 }, { "epoch": 0.275989561971337, "grad_norm": 6.617549896240234, "learning_rate": 5.5196395453897e-06, "loss": 0.6632, "step": 46430 }, { "epoch": 0.2760490040480054, "grad_norm": 7.309640407562256, "learning_rate": 5.520828379856389e-06, "loss": 0.6194, "step": 46440 }, { "epoch": 0.27610844612467383, "grad_norm": 6.498562335968018, "learning_rate": 5.522017214323078e-06, "loss": 0.7166, "step": 46450 }, { "epoch": 0.2761678882013422, "grad_norm": 9.502704620361328, "learning_rate": 5.5232060487897666e-06, "loss": 0.6552, "step": 46460 }, { "epoch": 0.2762273302780106, "grad_norm": 7.100829124450684, "learning_rate": 5.5243948832564555e-06, "loss": 0.6501, "step": 46470 }, { "epoch": 0.27628677235467897, "grad_norm": 7.436111927032471, "learning_rate": 5.525583717723144e-06, "loss": 0.6261, "step": 46480 }, { "epoch": 0.2763462144313474, "grad_norm": 7.1673994064331055, "learning_rate": 5.526772552189833e-06, "loss": 0.6833, "step": 46490 }, { "epoch": 0.27640565650801574, "grad_norm": 6.174238681793213, "learning_rate": 5.527961386656523e-06, "loss": 0.6258, "step": 46500 }, { "epoch": 0.27646509858468415, "grad_norm": 7.245450496673584, "learning_rate": 5.529150221123212e-06, "loss": 0.6719, "step": 46510 }, { "epoch": 0.27652454066135257, "grad_norm": 7.8789896965026855, "learning_rate": 5.530339055589901e-06, "loss": 0.6833, "step": 46520 }, { "epoch": 0.27658398273802093, "grad_norm": 6.782804012298584, "learning_rate": 5.531527890056589e-06, "loss": 0.6722, "step": 46530 }, { "epoch": 0.27664342481468934, "grad_norm": 7.0193023681640625, "learning_rate": 5.532716724523278e-06, "loss": 0.6791, "step": 46540 }, { "epoch": 0.2767028668913577, "grad_norm": 6.98908805847168, "learning_rate": 5.533905558989967e-06, "loss": 0.7324, "step": 46550 }, { "epoch": 0.2767623089680261, "grad_norm": 9.277322769165039, "learning_rate": 5.535094393456656e-06, "loss": 0.6892, "step": 46560 }, { "epoch": 0.2768217510446945, "grad_norm": 5.614167213439941, "learning_rate": 5.536283227923345e-06, "loss": 0.6837, "step": 46570 }, { "epoch": 0.2768811931213629, "grad_norm": 6.94979190826416, "learning_rate": 5.537472062390034e-06, "loss": 0.7307, "step": 46580 }, { "epoch": 0.2769406351980313, "grad_norm": 7.504753589630127, "learning_rate": 5.538660896856723e-06, "loss": 0.7101, "step": 46590 }, { "epoch": 0.27700007727469966, "grad_norm": 8.82227611541748, "learning_rate": 5.5398497313234115e-06, "loss": 0.6711, "step": 46600 }, { "epoch": 0.2770595193513681, "grad_norm": 7.885179042816162, "learning_rate": 5.5410385657901e-06, "loss": 0.6573, "step": 46610 }, { "epoch": 0.27711896142803644, "grad_norm": 8.106751441955566, "learning_rate": 5.5422274002567886e-06, "loss": 0.67, "step": 46620 }, { "epoch": 0.27717840350470485, "grad_norm": 7.135753154754639, "learning_rate": 5.5434162347234775e-06, "loss": 0.6893, "step": 46630 }, { "epoch": 0.2772378455813732, "grad_norm": 7.999807357788086, "learning_rate": 5.544605069190166e-06, "loss": 0.6693, "step": 46640 }, { "epoch": 0.2772972876580416, "grad_norm": 8.328404426574707, "learning_rate": 5.545793903656855e-06, "loss": 0.6738, "step": 46650 }, { "epoch": 0.27735672973471004, "grad_norm": 5.7563395500183105, "learning_rate": 5.546982738123544e-06, "loss": 0.667, "step": 46660 }, { "epoch": 0.2774161718113784, "grad_norm": 7.573461532592773, "learning_rate": 5.548171572590233e-06, "loss": 0.655, "step": 46670 }, { "epoch": 0.2774756138880468, "grad_norm": 7.375048637390137, "learning_rate": 5.549360407056922e-06, "loss": 0.6793, "step": 46680 }, { "epoch": 0.27753505596471517, "grad_norm": 6.673867702484131, "learning_rate": 5.550549241523611e-06, "loss": 0.601, "step": 46690 }, { "epoch": 0.2775944980413836, "grad_norm": 7.259864807128906, "learning_rate": 5.551738075990299e-06, "loss": 0.7204, "step": 46700 }, { "epoch": 0.27765394011805195, "grad_norm": 8.0640230178833, "learning_rate": 5.552926910456988e-06, "loss": 0.6443, "step": 46710 }, { "epoch": 0.27771338219472036, "grad_norm": 6.919740676879883, "learning_rate": 5.554115744923677e-06, "loss": 0.6687, "step": 46720 }, { "epoch": 0.2777728242713887, "grad_norm": 7.34213924407959, "learning_rate": 5.555304579390366e-06, "loss": 0.6546, "step": 46730 }, { "epoch": 0.27783226634805713, "grad_norm": 8.270387649536133, "learning_rate": 5.556493413857055e-06, "loss": 0.7028, "step": 46740 }, { "epoch": 0.27789170842472555, "grad_norm": 8.618910789489746, "learning_rate": 5.557682248323744e-06, "loss": 0.6636, "step": 46750 }, { "epoch": 0.2779511505013939, "grad_norm": 8.215911865234375, "learning_rate": 5.558871082790433e-06, "loss": 0.6522, "step": 46760 }, { "epoch": 0.2780105925780623, "grad_norm": 8.094217300415039, "learning_rate": 5.560059917257122e-06, "loss": 0.7042, "step": 46770 }, { "epoch": 0.2780700346547307, "grad_norm": 7.050860404968262, "learning_rate": 5.56124875172381e-06, "loss": 0.6448, "step": 46780 }, { "epoch": 0.2781294767313991, "grad_norm": 6.393898010253906, "learning_rate": 5.562437586190499e-06, "loss": 0.6994, "step": 46790 }, { "epoch": 0.27818891880806745, "grad_norm": 7.701679706573486, "learning_rate": 5.5636264206571876e-06, "loss": 0.6769, "step": 46800 }, { "epoch": 0.27824836088473587, "grad_norm": 6.938644886016846, "learning_rate": 5.5648152551238765e-06, "loss": 0.6479, "step": 46810 }, { "epoch": 0.2783078029614043, "grad_norm": 8.802908897399902, "learning_rate": 5.566004089590565e-06, "loss": 0.6285, "step": 46820 }, { "epoch": 0.27836724503807264, "grad_norm": 6.101093292236328, "learning_rate": 5.567192924057254e-06, "loss": 0.6752, "step": 46830 }, { "epoch": 0.27842668711474106, "grad_norm": 6.9995574951171875, "learning_rate": 5.568381758523944e-06, "loss": 0.6801, "step": 46840 }, { "epoch": 0.2784861291914094, "grad_norm": 7.6986565589904785, "learning_rate": 5.569570592990633e-06, "loss": 0.6718, "step": 46850 }, { "epoch": 0.27854557126807783, "grad_norm": 6.854060649871826, "learning_rate": 5.570759427457322e-06, "loss": 0.6347, "step": 46860 }, { "epoch": 0.2786050133447462, "grad_norm": 7.346990585327148, "learning_rate": 5.571948261924011e-06, "loss": 0.6824, "step": 46870 }, { "epoch": 0.2786644554214146, "grad_norm": 8.121085166931152, "learning_rate": 5.5731370963907e-06, "loss": 0.7423, "step": 46880 }, { "epoch": 0.278723897498083, "grad_norm": 7.039581298828125, "learning_rate": 5.574325930857388e-06, "loss": 0.6491, "step": 46890 }, { "epoch": 0.2787833395747514, "grad_norm": 6.975527286529541, "learning_rate": 5.575514765324077e-06, "loss": 0.7062, "step": 46900 }, { "epoch": 0.2788427816514198, "grad_norm": 6.239262104034424, "learning_rate": 5.576703599790766e-06, "loss": 0.6909, "step": 46910 }, { "epoch": 0.27890222372808815, "grad_norm": 7.110213756561279, "learning_rate": 5.577892434257455e-06, "loss": 0.6594, "step": 46920 }, { "epoch": 0.27896166580475656, "grad_norm": 7.470486164093018, "learning_rate": 5.579081268724144e-06, "loss": 0.6473, "step": 46930 }, { "epoch": 0.2790211078814249, "grad_norm": 7.363438129425049, "learning_rate": 5.5802701031908325e-06, "loss": 0.6867, "step": 46940 }, { "epoch": 0.27908054995809334, "grad_norm": 8.242691993713379, "learning_rate": 5.5814589376575215e-06, "loss": 0.6476, "step": 46950 }, { "epoch": 0.27913999203476175, "grad_norm": 7.105364799499512, "learning_rate": 5.58264777212421e-06, "loss": 0.6285, "step": 46960 }, { "epoch": 0.2791994341114301, "grad_norm": 7.015785217285156, "learning_rate": 5.5838366065908985e-06, "loss": 0.5964, "step": 46970 }, { "epoch": 0.2792588761880985, "grad_norm": 6.220466136932373, "learning_rate": 5.585025441057587e-06, "loss": 0.6948, "step": 46980 }, { "epoch": 0.2793183182647669, "grad_norm": 7.05961799621582, "learning_rate": 5.586214275524276e-06, "loss": 0.6558, "step": 46990 }, { "epoch": 0.2793777603414353, "grad_norm": 7.8008928298950195, "learning_rate": 5.587403109990965e-06, "loss": 0.634, "step": 47000 }, { "epoch": 0.27943720241810366, "grad_norm": 9.731731414794922, "learning_rate": 5.588591944457654e-06, "loss": 0.6639, "step": 47010 }, { "epoch": 0.2794966444947721, "grad_norm": 10.299239158630371, "learning_rate": 5.589780778924343e-06, "loss": 0.6955, "step": 47020 }, { "epoch": 0.2795560865714405, "grad_norm": 8.177932739257812, "learning_rate": 5.590969613391032e-06, "loss": 0.7444, "step": 47030 }, { "epoch": 0.27961552864810885, "grad_norm": 9.200438499450684, "learning_rate": 5.592158447857721e-06, "loss": 0.6871, "step": 47040 }, { "epoch": 0.27967497072477726, "grad_norm": 5.9858880043029785, "learning_rate": 5.59334728232441e-06, "loss": 0.6271, "step": 47050 }, { "epoch": 0.2797344128014456, "grad_norm": 7.664485454559326, "learning_rate": 5.594536116791098e-06, "loss": 0.7351, "step": 47060 }, { "epoch": 0.27979385487811403, "grad_norm": 6.298807621002197, "learning_rate": 5.595724951257787e-06, "loss": 0.6807, "step": 47070 }, { "epoch": 0.2798532969547824, "grad_norm": 7.081154823303223, "learning_rate": 5.596913785724476e-06, "loss": 0.6379, "step": 47080 }, { "epoch": 0.2799127390314508, "grad_norm": 6.2490739822387695, "learning_rate": 5.598102620191165e-06, "loss": 0.7018, "step": 47090 }, { "epoch": 0.27997218110811917, "grad_norm": 5.917389869689941, "learning_rate": 5.599291454657854e-06, "loss": 0.6078, "step": 47100 }, { "epoch": 0.2800316231847876, "grad_norm": 8.00234317779541, "learning_rate": 5.600480289124543e-06, "loss": 0.6762, "step": 47110 }, { "epoch": 0.280091065261456, "grad_norm": 7.770866394042969, "learning_rate": 5.6016691235912315e-06, "loss": 0.6397, "step": 47120 }, { "epoch": 0.28015050733812435, "grad_norm": 7.859930992126465, "learning_rate": 5.6028579580579205e-06, "loss": 0.6786, "step": 47130 }, { "epoch": 0.28020994941479277, "grad_norm": 8.438281059265137, "learning_rate": 5.6040467925246085e-06, "loss": 0.6683, "step": 47140 }, { "epoch": 0.28026939149146113, "grad_norm": 7.0754008293151855, "learning_rate": 5.6052356269912975e-06, "loss": 0.712, "step": 47150 }, { "epoch": 0.28032883356812954, "grad_norm": 6.172135353088379, "learning_rate": 5.606424461457986e-06, "loss": 0.6881, "step": 47160 }, { "epoch": 0.2803882756447979, "grad_norm": 10.458925247192383, "learning_rate": 5.607613295924675e-06, "loss": 0.6884, "step": 47170 }, { "epoch": 0.2804477177214663, "grad_norm": 6.725790500640869, "learning_rate": 5.608802130391364e-06, "loss": 0.7123, "step": 47180 }, { "epoch": 0.28050715979813473, "grad_norm": 8.738480567932129, "learning_rate": 5.609990964858054e-06, "loss": 0.6807, "step": 47190 }, { "epoch": 0.2805666018748031, "grad_norm": 8.920421600341797, "learning_rate": 5.611179799324743e-06, "loss": 0.5979, "step": 47200 }, { "epoch": 0.2806260439514715, "grad_norm": 5.918878078460693, "learning_rate": 5.612368633791432e-06, "loss": 0.6349, "step": 47210 }, { "epoch": 0.28068548602813986, "grad_norm": 7.6747822761535645, "learning_rate": 5.613557468258121e-06, "loss": 0.6423, "step": 47220 }, { "epoch": 0.2807449281048083, "grad_norm": 7.626388072967529, "learning_rate": 5.61474630272481e-06, "loss": 0.7434, "step": 47230 }, { "epoch": 0.28080437018147664, "grad_norm": 7.0598249435424805, "learning_rate": 5.615935137191499e-06, "loss": 0.7144, "step": 47240 }, { "epoch": 0.28086381225814505, "grad_norm": 8.06833267211914, "learning_rate": 5.617123971658187e-06, "loss": 0.6915, "step": 47250 }, { "epoch": 0.28092325433481347, "grad_norm": 7.396223068237305, "learning_rate": 5.618312806124876e-06, "loss": 0.6457, "step": 47260 }, { "epoch": 0.2809826964114818, "grad_norm": 7.490366458892822, "learning_rate": 5.619501640591565e-06, "loss": 0.6955, "step": 47270 }, { "epoch": 0.28104213848815024, "grad_norm": 7.613131999969482, "learning_rate": 5.6206904750582535e-06, "loss": 0.7064, "step": 47280 }, { "epoch": 0.2811015805648186, "grad_norm": 7.680102348327637, "learning_rate": 5.6218793095249424e-06, "loss": 0.6958, "step": 47290 }, { "epoch": 0.281161022641487, "grad_norm": 6.782398700714111, "learning_rate": 5.623068143991631e-06, "loss": 0.6749, "step": 47300 }, { "epoch": 0.28122046471815537, "grad_norm": 10.113062858581543, "learning_rate": 5.62425697845832e-06, "loss": 0.7338, "step": 47310 }, { "epoch": 0.2812799067948238, "grad_norm": 7.0123748779296875, "learning_rate": 5.625445812925009e-06, "loss": 0.6459, "step": 47320 }, { "epoch": 0.2813393488714922, "grad_norm": 9.04809856414795, "learning_rate": 5.626634647391697e-06, "loss": 0.7198, "step": 47330 }, { "epoch": 0.28139879094816056, "grad_norm": 7.775486946105957, "learning_rate": 5.627823481858386e-06, "loss": 0.6085, "step": 47340 }, { "epoch": 0.281458233024829, "grad_norm": 7.375660419464111, "learning_rate": 5.629012316325075e-06, "loss": 0.6421, "step": 47350 }, { "epoch": 0.28151767510149733, "grad_norm": 6.832334518432617, "learning_rate": 5.630201150791764e-06, "loss": 0.6166, "step": 47360 }, { "epoch": 0.28157711717816575, "grad_norm": 6.526517391204834, "learning_rate": 5.631389985258453e-06, "loss": 0.6496, "step": 47370 }, { "epoch": 0.2816365592548341, "grad_norm": 8.541300773620605, "learning_rate": 5.632578819725142e-06, "loss": 0.6191, "step": 47380 }, { "epoch": 0.2816960013315025, "grad_norm": 9.19733715057373, "learning_rate": 5.633767654191831e-06, "loss": 0.6727, "step": 47390 }, { "epoch": 0.2817554434081709, "grad_norm": 7.607360363006592, "learning_rate": 5.63495648865852e-06, "loss": 0.5985, "step": 47400 }, { "epoch": 0.2818148854848393, "grad_norm": 7.381308555603027, "learning_rate": 5.636145323125209e-06, "loss": 0.664, "step": 47410 }, { "epoch": 0.2818743275615077, "grad_norm": 8.643030166625977, "learning_rate": 5.637334157591897e-06, "loss": 0.6573, "step": 47420 }, { "epoch": 0.28193376963817607, "grad_norm": 6.650365829467773, "learning_rate": 5.638522992058586e-06, "loss": 0.6376, "step": 47430 }, { "epoch": 0.2819932117148445, "grad_norm": 8.694869995117188, "learning_rate": 5.639711826525275e-06, "loss": 0.6459, "step": 47440 }, { "epoch": 0.28205265379151284, "grad_norm": 8.108375549316406, "learning_rate": 5.640900660991964e-06, "loss": 0.7581, "step": 47450 }, { "epoch": 0.28211209586818126, "grad_norm": 8.611156463623047, "learning_rate": 5.6420894954586525e-06, "loss": 0.6455, "step": 47460 }, { "epoch": 0.2821715379448496, "grad_norm": 7.9216766357421875, "learning_rate": 5.6432783299253414e-06, "loss": 0.6294, "step": 47470 }, { "epoch": 0.28223098002151803, "grad_norm": 6.127382755279541, "learning_rate": 5.64446716439203e-06, "loss": 0.736, "step": 47480 }, { "epoch": 0.28229042209818644, "grad_norm": 8.656964302062988, "learning_rate": 5.645655998858719e-06, "loss": 0.7561, "step": 47490 }, { "epoch": 0.2823498641748548, "grad_norm": 7.095943927764893, "learning_rate": 5.646844833325407e-06, "loss": 0.7179, "step": 47500 }, { "epoch": 0.2824093062515232, "grad_norm": 6.714488506317139, "learning_rate": 5.648033667792096e-06, "loss": 0.7046, "step": 47510 }, { "epoch": 0.2824687483281916, "grad_norm": 7.625057220458984, "learning_rate": 5.649222502258785e-06, "loss": 0.6774, "step": 47520 }, { "epoch": 0.28252819040486, "grad_norm": 8.49294662475586, "learning_rate": 5.650411336725474e-06, "loss": 0.6548, "step": 47530 }, { "epoch": 0.28258763248152835, "grad_norm": 7.5361480712890625, "learning_rate": 5.651600171192164e-06, "loss": 0.7722, "step": 47540 }, { "epoch": 0.28264707455819676, "grad_norm": 7.794154167175293, "learning_rate": 5.652789005658853e-06, "loss": 0.7291, "step": 47550 }, { "epoch": 0.2827065166348652, "grad_norm": 7.948922634124756, "learning_rate": 5.653977840125542e-06, "loss": 0.7212, "step": 47560 }, { "epoch": 0.28276595871153354, "grad_norm": 8.003150939941406, "learning_rate": 5.655166674592231e-06, "loss": 0.6829, "step": 47570 }, { "epoch": 0.28282540078820195, "grad_norm": 6.611878871917725, "learning_rate": 5.65635550905892e-06, "loss": 0.6585, "step": 47580 }, { "epoch": 0.2828848428648703, "grad_norm": 9.221734046936035, "learning_rate": 5.6575443435256086e-06, "loss": 0.6866, "step": 47590 }, { "epoch": 0.2829442849415387, "grad_norm": 8.665172576904297, "learning_rate": 5.6587331779922975e-06, "loss": 0.6937, "step": 47600 }, { "epoch": 0.2830037270182071, "grad_norm": 6.559324741363525, "learning_rate": 5.659922012458986e-06, "loss": 0.6986, "step": 47610 }, { "epoch": 0.2830631690948755, "grad_norm": 6.0082244873046875, "learning_rate": 5.6611108469256745e-06, "loss": 0.6891, "step": 47620 }, { "epoch": 0.2831226111715439, "grad_norm": 8.43864917755127, "learning_rate": 5.6622996813923634e-06, "loss": 0.7447, "step": 47630 }, { "epoch": 0.2831820532482123, "grad_norm": 8.292046546936035, "learning_rate": 5.663488515859052e-06, "loss": 0.7258, "step": 47640 }, { "epoch": 0.2832414953248807, "grad_norm": 6.770456314086914, "learning_rate": 5.664677350325741e-06, "loss": 0.6707, "step": 47650 }, { "epoch": 0.28330093740154905, "grad_norm": 7.642361164093018, "learning_rate": 5.66586618479243e-06, "loss": 0.701, "step": 47660 }, { "epoch": 0.28336037947821746, "grad_norm": 8.286101341247559, "learning_rate": 5.667055019259119e-06, "loss": 0.6478, "step": 47670 }, { "epoch": 0.2834198215548858, "grad_norm": 7.080698013305664, "learning_rate": 5.668243853725808e-06, "loss": 0.6791, "step": 47680 }, { "epoch": 0.28347926363155423, "grad_norm": 9.489031791687012, "learning_rate": 5.669432688192497e-06, "loss": 0.7398, "step": 47690 }, { "epoch": 0.28353870570822265, "grad_norm": 8.262418746948242, "learning_rate": 5.670621522659185e-06, "loss": 0.67, "step": 47700 }, { "epoch": 0.283598147784891, "grad_norm": 7.834163188934326, "learning_rate": 5.671810357125874e-06, "loss": 0.7827, "step": 47710 }, { "epoch": 0.2836575898615594, "grad_norm": 8.555797576904297, "learning_rate": 5.672999191592563e-06, "loss": 0.7231, "step": 47720 }, { "epoch": 0.2837170319382278, "grad_norm": 11.220327377319336, "learning_rate": 5.674188026059252e-06, "loss": 0.6635, "step": 47730 }, { "epoch": 0.2837764740148962, "grad_norm": 8.473847389221191, "learning_rate": 5.675376860525941e-06, "loss": 0.6929, "step": 47740 }, { "epoch": 0.28383591609156456, "grad_norm": 7.72894811630249, "learning_rate": 5.67656569499263e-06, "loss": 0.6864, "step": 47750 }, { "epoch": 0.28389535816823297, "grad_norm": 6.326323986053467, "learning_rate": 5.677754529459319e-06, "loss": 0.6052, "step": 47760 }, { "epoch": 0.28395480024490133, "grad_norm": 10.128339767456055, "learning_rate": 5.6789433639260076e-06, "loss": 0.6988, "step": 47770 }, { "epoch": 0.28401424232156974, "grad_norm": 8.182151794433594, "learning_rate": 5.680132198392696e-06, "loss": 0.7388, "step": 47780 }, { "epoch": 0.28407368439823816, "grad_norm": 8.564067840576172, "learning_rate": 5.681321032859385e-06, "loss": 0.7193, "step": 47790 }, { "epoch": 0.2841331264749065, "grad_norm": 8.887124061584473, "learning_rate": 5.6825098673260735e-06, "loss": 0.6432, "step": 47800 }, { "epoch": 0.28419256855157493, "grad_norm": 8.623771667480469, "learning_rate": 5.6836987017927624e-06, "loss": 0.6686, "step": 47810 }, { "epoch": 0.2842520106282433, "grad_norm": 7.195326328277588, "learning_rate": 5.684887536259451e-06, "loss": 0.6716, "step": 47820 }, { "epoch": 0.2843114527049117, "grad_norm": 8.131985664367676, "learning_rate": 5.68607637072614e-06, "loss": 0.7051, "step": 47830 }, { "epoch": 0.28437089478158006, "grad_norm": 8.038650512695312, "learning_rate": 5.687265205192829e-06, "loss": 0.7314, "step": 47840 }, { "epoch": 0.2844303368582485, "grad_norm": 6.349982261657715, "learning_rate": 5.688454039659518e-06, "loss": 0.7699, "step": 47850 }, { "epoch": 0.2844897789349169, "grad_norm": 7.2867350578308105, "learning_rate": 5.689642874126206e-06, "loss": 0.6548, "step": 47860 }, { "epoch": 0.28454922101158525, "grad_norm": 7.6413774490356445, "learning_rate": 5.690831708592895e-06, "loss": 0.6598, "step": 47870 }, { "epoch": 0.28460866308825367, "grad_norm": 5.972405433654785, "learning_rate": 5.692020543059586e-06, "loss": 0.6472, "step": 47880 }, { "epoch": 0.284668105164922, "grad_norm": 6.699965000152588, "learning_rate": 5.693209377526274e-06, "loss": 0.6826, "step": 47890 }, { "epoch": 0.28472754724159044, "grad_norm": 6.757883071899414, "learning_rate": 5.694398211992963e-06, "loss": 0.6927, "step": 47900 }, { "epoch": 0.2847869893182588, "grad_norm": 8.311278343200684, "learning_rate": 5.695587046459652e-06, "loss": 0.6942, "step": 47910 }, { "epoch": 0.2848464313949272, "grad_norm": 7.170626163482666, "learning_rate": 5.696775880926341e-06, "loss": 0.6489, "step": 47920 }, { "epoch": 0.2849058734715956, "grad_norm": 5.694443225860596, "learning_rate": 5.6979647153930296e-06, "loss": 0.6969, "step": 47930 }, { "epoch": 0.284965315548264, "grad_norm": 6.551784038543701, "learning_rate": 5.6991535498597185e-06, "loss": 0.662, "step": 47940 }, { "epoch": 0.2850247576249324, "grad_norm": 8.158040046691895, "learning_rate": 5.700342384326407e-06, "loss": 0.6988, "step": 47950 }, { "epoch": 0.28508419970160076, "grad_norm": 12.989042282104492, "learning_rate": 5.701531218793096e-06, "loss": 0.747, "step": 47960 }, { "epoch": 0.2851436417782692, "grad_norm": 10.68509578704834, "learning_rate": 5.7027200532597844e-06, "loss": 0.7598, "step": 47970 }, { "epoch": 0.28520308385493753, "grad_norm": 9.397501945495605, "learning_rate": 5.703908887726473e-06, "loss": 0.6526, "step": 47980 }, { "epoch": 0.28526252593160595, "grad_norm": 7.9480671882629395, "learning_rate": 5.705097722193162e-06, "loss": 0.7594, "step": 47990 }, { "epoch": 0.28532196800827436, "grad_norm": 8.593791007995605, "learning_rate": 5.706286556659851e-06, "loss": 0.6467, "step": 48000 }, { "epoch": 0.2853814100849427, "grad_norm": 7.722458839416504, "learning_rate": 5.70747539112654e-06, "loss": 0.6303, "step": 48010 }, { "epoch": 0.28544085216161114, "grad_norm": 7.494832992553711, "learning_rate": 5.708664225593229e-06, "loss": 0.6882, "step": 48020 }, { "epoch": 0.2855002942382795, "grad_norm": 7.395149230957031, "learning_rate": 5.709853060059918e-06, "loss": 0.7019, "step": 48030 }, { "epoch": 0.2855597363149479, "grad_norm": 10.369439125061035, "learning_rate": 5.711041894526607e-06, "loss": 0.6803, "step": 48040 }, { "epoch": 0.28561917839161627, "grad_norm": 8.118073463439941, "learning_rate": 5.712230728993296e-06, "loss": 0.6592, "step": 48050 }, { "epoch": 0.2856786204682847, "grad_norm": 6.696142196655273, "learning_rate": 5.713419563459984e-06, "loss": 0.6483, "step": 48060 }, { "epoch": 0.2857380625449531, "grad_norm": 8.752333641052246, "learning_rate": 5.714608397926673e-06, "loss": 0.7358, "step": 48070 }, { "epoch": 0.28579750462162146, "grad_norm": 6.694373607635498, "learning_rate": 5.715797232393362e-06, "loss": 0.6409, "step": 48080 }, { "epoch": 0.28585694669828987, "grad_norm": 6.828175067901611, "learning_rate": 5.716986066860051e-06, "loss": 0.6228, "step": 48090 }, { "epoch": 0.28591638877495823, "grad_norm": 7.5117268562316895, "learning_rate": 5.71817490132674e-06, "loss": 0.7106, "step": 48100 }, { "epoch": 0.28597583085162664, "grad_norm": 9.138769149780273, "learning_rate": 5.7193637357934286e-06, "loss": 0.7158, "step": 48110 }, { "epoch": 0.286035272928295, "grad_norm": 6.899775505065918, "learning_rate": 5.7205525702601175e-06, "loss": 0.6737, "step": 48120 }, { "epoch": 0.2860947150049634, "grad_norm": 8.590336799621582, "learning_rate": 5.721741404726806e-06, "loss": 0.6783, "step": 48130 }, { "epoch": 0.2861541570816318, "grad_norm": 8.02679443359375, "learning_rate": 5.7229302391934945e-06, "loss": 0.7512, "step": 48140 }, { "epoch": 0.2862135991583002, "grad_norm": 8.055696487426758, "learning_rate": 5.724119073660183e-06, "loss": 0.6621, "step": 48150 }, { "epoch": 0.2862730412349686, "grad_norm": 8.111595153808594, "learning_rate": 5.725307908126872e-06, "loss": 0.66, "step": 48160 }, { "epoch": 0.28633248331163696, "grad_norm": 10.015058517456055, "learning_rate": 5.726496742593561e-06, "loss": 0.7921, "step": 48170 }, { "epoch": 0.2863919253883054, "grad_norm": 9.104640007019043, "learning_rate": 5.72768557706025e-06, "loss": 0.7168, "step": 48180 }, { "epoch": 0.28645136746497374, "grad_norm": 9.256814002990723, "learning_rate": 5.728874411526939e-06, "loss": 0.712, "step": 48190 }, { "epoch": 0.28651080954164215, "grad_norm": 8.831216812133789, "learning_rate": 5.730063245993628e-06, "loss": 0.7112, "step": 48200 }, { "epoch": 0.2865702516183105, "grad_norm": 7.86453104019165, "learning_rate": 5.731252080460317e-06, "loss": 0.6205, "step": 48210 }, { "epoch": 0.2866296936949789, "grad_norm": 7.734999179840088, "learning_rate": 5.732440914927006e-06, "loss": 0.6744, "step": 48220 }, { "epoch": 0.28668913577164734, "grad_norm": 6.5669474601745605, "learning_rate": 5.733629749393696e-06, "loss": 0.7339, "step": 48230 }, { "epoch": 0.2867485778483157, "grad_norm": 6.942696571350098, "learning_rate": 5.734818583860385e-06, "loss": 0.6608, "step": 48240 }, { "epoch": 0.2868080199249841, "grad_norm": 9.217588424682617, "learning_rate": 5.736007418327073e-06, "loss": 0.6533, "step": 48250 }, { "epoch": 0.2868674620016525, "grad_norm": 11.795207977294922, "learning_rate": 5.737196252793762e-06, "loss": 0.7501, "step": 48260 }, { "epoch": 0.2869269040783209, "grad_norm": 10.568758964538574, "learning_rate": 5.7383850872604505e-06, "loss": 0.6722, "step": 48270 }, { "epoch": 0.28698634615498925, "grad_norm": 7.86807107925415, "learning_rate": 5.7395739217271395e-06, "loss": 0.7505, "step": 48280 }, { "epoch": 0.28704578823165766, "grad_norm": 8.089953422546387, "learning_rate": 5.740762756193828e-06, "loss": 0.63, "step": 48290 }, { "epoch": 0.2871052303083261, "grad_norm": 7.46925687789917, "learning_rate": 5.741951590660517e-06, "loss": 0.7136, "step": 48300 }, { "epoch": 0.28716467238499443, "grad_norm": 7.171668529510498, "learning_rate": 5.743140425127206e-06, "loss": 0.6198, "step": 48310 }, { "epoch": 0.28722411446166285, "grad_norm": 9.668986320495605, "learning_rate": 5.744329259593895e-06, "loss": 0.6241, "step": 48320 }, { "epoch": 0.2872835565383312, "grad_norm": 7.810388565063477, "learning_rate": 5.745518094060584e-06, "loss": 0.6346, "step": 48330 }, { "epoch": 0.2873429986149996, "grad_norm": 7.298446178436279, "learning_rate": 5.746706928527272e-06, "loss": 0.6907, "step": 48340 }, { "epoch": 0.287402440691668, "grad_norm": 8.845354080200195, "learning_rate": 5.747895762993961e-06, "loss": 0.6788, "step": 48350 }, { "epoch": 0.2874618827683364, "grad_norm": 8.648597717285156, "learning_rate": 5.74908459746065e-06, "loss": 0.654, "step": 48360 }, { "epoch": 0.2875213248450048, "grad_norm": 6.840653896331787, "learning_rate": 5.750273431927339e-06, "loss": 0.7041, "step": 48370 }, { "epoch": 0.28758076692167317, "grad_norm": 7.387449741363525, "learning_rate": 5.751462266394028e-06, "loss": 0.6462, "step": 48380 }, { "epoch": 0.2876402089983416, "grad_norm": 7.383914947509766, "learning_rate": 5.752651100860717e-06, "loss": 0.6768, "step": 48390 }, { "epoch": 0.28769965107500994, "grad_norm": 7.374602317810059, "learning_rate": 5.753839935327406e-06, "loss": 0.6594, "step": 48400 }, { "epoch": 0.28775909315167836, "grad_norm": 7.27870512008667, "learning_rate": 5.755028769794095e-06, "loss": 0.6899, "step": 48410 }, { "epoch": 0.2878185352283467, "grad_norm": 6.9397149085998535, "learning_rate": 5.756217604260783e-06, "loss": 0.6528, "step": 48420 }, { "epoch": 0.28787797730501513, "grad_norm": 9.852336883544922, "learning_rate": 5.757406438727472e-06, "loss": 0.7231, "step": 48430 }, { "epoch": 0.28793741938168355, "grad_norm": 9.317079544067383, "learning_rate": 5.758595273194161e-06, "loss": 0.6433, "step": 48440 }, { "epoch": 0.2879968614583519, "grad_norm": 6.3958210945129395, "learning_rate": 5.7597841076608495e-06, "loss": 0.709, "step": 48450 }, { "epoch": 0.2880563035350203, "grad_norm": 8.201993942260742, "learning_rate": 5.7609729421275385e-06, "loss": 0.7204, "step": 48460 }, { "epoch": 0.2881157456116887, "grad_norm": 6.596734523773193, "learning_rate": 5.762161776594227e-06, "loss": 0.6798, "step": 48470 }, { "epoch": 0.2881751876883571, "grad_norm": 7.821037292480469, "learning_rate": 5.763350611060916e-06, "loss": 0.677, "step": 48480 }, { "epoch": 0.28823462976502545, "grad_norm": 6.504627704620361, "learning_rate": 5.764539445527605e-06, "loss": 0.6285, "step": 48490 }, { "epoch": 0.28829407184169387, "grad_norm": 7.772546291351318, "learning_rate": 5.765728279994293e-06, "loss": 0.7083, "step": 48500 }, { "epoch": 0.2883535139183622, "grad_norm": 8.339191436767578, "learning_rate": 5.766917114460982e-06, "loss": 0.7209, "step": 48510 }, { "epoch": 0.28841295599503064, "grad_norm": 7.284270763397217, "learning_rate": 5.768105948927671e-06, "loss": 0.7183, "step": 48520 }, { "epoch": 0.28847239807169905, "grad_norm": 7.8430633544921875, "learning_rate": 5.76929478339436e-06, "loss": 0.6491, "step": 48530 }, { "epoch": 0.2885318401483674, "grad_norm": 7.714245796203613, "learning_rate": 5.770483617861049e-06, "loss": 0.6989, "step": 48540 }, { "epoch": 0.28859128222503583, "grad_norm": 8.37602710723877, "learning_rate": 5.771672452327738e-06, "loss": 0.693, "step": 48550 }, { "epoch": 0.2886507243017042, "grad_norm": 5.8693037033081055, "learning_rate": 5.772861286794427e-06, "loss": 0.677, "step": 48560 }, { "epoch": 0.2887101663783726, "grad_norm": 8.173563003540039, "learning_rate": 5.774050121261116e-06, "loss": 0.661, "step": 48570 }, { "epoch": 0.28876960845504096, "grad_norm": 7.129357814788818, "learning_rate": 5.775238955727806e-06, "loss": 0.6826, "step": 48580 }, { "epoch": 0.2888290505317094, "grad_norm": 9.427834510803223, "learning_rate": 5.7764277901944945e-06, "loss": 0.6949, "step": 48590 }, { "epoch": 0.2888884926083778, "grad_norm": 7.820156574249268, "learning_rate": 5.7776166246611835e-06, "loss": 0.7198, "step": 48600 }, { "epoch": 0.28894793468504615, "grad_norm": 9.558876037597656, "learning_rate": 5.7788054591278715e-06, "loss": 0.6605, "step": 48610 }, { "epoch": 0.28900737676171456, "grad_norm": 8.035649299621582, "learning_rate": 5.7799942935945605e-06, "loss": 0.6434, "step": 48620 }, { "epoch": 0.2890668188383829, "grad_norm": 7.695864677429199, "learning_rate": 5.781183128061249e-06, "loss": 0.6766, "step": 48630 }, { "epoch": 0.28912626091505134, "grad_norm": 7.970606803894043, "learning_rate": 5.782371962527938e-06, "loss": 0.7339, "step": 48640 }, { "epoch": 0.2891857029917197, "grad_norm": 7.75347900390625, "learning_rate": 5.783560796994627e-06, "loss": 0.6443, "step": 48650 }, { "epoch": 0.2892451450683881, "grad_norm": 5.858358383178711, "learning_rate": 5.784749631461316e-06, "loss": 0.6248, "step": 48660 }, { "epoch": 0.2893045871450565, "grad_norm": 8.134833335876465, "learning_rate": 5.785938465928005e-06, "loss": 0.6958, "step": 48670 }, { "epoch": 0.2893640292217249, "grad_norm": 9.334992408752441, "learning_rate": 5.787127300394694e-06, "loss": 0.6948, "step": 48680 }, { "epoch": 0.2894234712983933, "grad_norm": 7.617613315582275, "learning_rate": 5.788316134861383e-06, "loss": 0.6342, "step": 48690 }, { "epoch": 0.28948291337506166, "grad_norm": 7.535745143890381, "learning_rate": 5.789504969328071e-06, "loss": 0.6581, "step": 48700 }, { "epoch": 0.28954235545173007, "grad_norm": 6.185076713562012, "learning_rate": 5.79069380379476e-06, "loss": 0.7245, "step": 48710 }, { "epoch": 0.28960179752839843, "grad_norm": 8.097185134887695, "learning_rate": 5.791882638261449e-06, "loss": 0.7118, "step": 48720 }, { "epoch": 0.28966123960506684, "grad_norm": 7.143008232116699, "learning_rate": 5.793071472728138e-06, "loss": 0.6894, "step": 48730 }, { "epoch": 0.28972068168173526, "grad_norm": 7.484911918640137, "learning_rate": 5.794260307194827e-06, "loss": 0.6791, "step": 48740 }, { "epoch": 0.2897801237584036, "grad_norm": 9.367953300476074, "learning_rate": 5.795449141661516e-06, "loss": 0.6926, "step": 48750 }, { "epoch": 0.28983956583507203, "grad_norm": 6.682576656341553, "learning_rate": 5.796637976128205e-06, "loss": 0.6537, "step": 48760 }, { "epoch": 0.2898990079117404, "grad_norm": 9.157439231872559, "learning_rate": 5.7978268105948935e-06, "loss": 0.7208, "step": 48770 }, { "epoch": 0.2899584499884088, "grad_norm": 6.836584091186523, "learning_rate": 5.799015645061582e-06, "loss": 0.5945, "step": 48780 }, { "epoch": 0.29001789206507717, "grad_norm": 7.665414333343506, "learning_rate": 5.8002044795282705e-06, "loss": 0.7085, "step": 48790 }, { "epoch": 0.2900773341417456, "grad_norm": 7.824750900268555, "learning_rate": 5.8013933139949595e-06, "loss": 0.688, "step": 48800 }, { "epoch": 0.290136776218414, "grad_norm": 6.594094753265381, "learning_rate": 5.802582148461648e-06, "loss": 0.721, "step": 48810 }, { "epoch": 0.29019621829508235, "grad_norm": 8.173532485961914, "learning_rate": 5.803770982928337e-06, "loss": 0.6693, "step": 48820 }, { "epoch": 0.29025566037175077, "grad_norm": 6.61078405380249, "learning_rate": 5.804959817395026e-06, "loss": 0.6546, "step": 48830 }, { "epoch": 0.2903151024484191, "grad_norm": 7.390625476837158, "learning_rate": 5.806148651861715e-06, "loss": 0.6682, "step": 48840 }, { "epoch": 0.29037454452508754, "grad_norm": 6.483569622039795, "learning_rate": 5.807337486328404e-06, "loss": 0.6547, "step": 48850 }, { "epoch": 0.2904339866017559, "grad_norm": 7.227931499481201, "learning_rate": 5.808526320795092e-06, "loss": 0.7466, "step": 48860 }, { "epoch": 0.2904934286784243, "grad_norm": 9.03416633605957, "learning_rate": 5.809715155261781e-06, "loss": 0.7208, "step": 48870 }, { "epoch": 0.2905528707550927, "grad_norm": 6.141229629516602, "learning_rate": 5.81090398972847e-06, "loss": 0.6781, "step": 48880 }, { "epoch": 0.2906123128317611, "grad_norm": 8.914545059204102, "learning_rate": 5.812092824195159e-06, "loss": 0.7451, "step": 48890 }, { "epoch": 0.2906717549084295, "grad_norm": 8.701762199401855, "learning_rate": 5.813281658661848e-06, "loss": 0.597, "step": 48900 }, { "epoch": 0.29073119698509786, "grad_norm": 7.481888771057129, "learning_rate": 5.814470493128537e-06, "loss": 0.6447, "step": 48910 }, { "epoch": 0.2907906390617663, "grad_norm": 6.384042263031006, "learning_rate": 5.815659327595227e-06, "loss": 0.6991, "step": 48920 }, { "epoch": 0.29085008113843464, "grad_norm": 8.773714065551758, "learning_rate": 5.8168481620619155e-06, "loss": 0.7029, "step": 48930 }, { "epoch": 0.29090952321510305, "grad_norm": 7.65154504776001, "learning_rate": 5.8180369965286044e-06, "loss": 0.6389, "step": 48940 }, { "epoch": 0.2909689652917714, "grad_norm": 8.821282386779785, "learning_rate": 5.819225830995293e-06, "loss": 0.6594, "step": 48950 }, { "epoch": 0.2910284073684398, "grad_norm": 7.6962504386901855, "learning_rate": 5.820414665461982e-06, "loss": 0.697, "step": 48960 }, { "epoch": 0.29108784944510824, "grad_norm": 7.653448581695557, "learning_rate": 5.82160349992867e-06, "loss": 0.6766, "step": 48970 }, { "epoch": 0.2911472915217766, "grad_norm": 8.640091896057129, "learning_rate": 5.822792334395359e-06, "loss": 0.6603, "step": 48980 }, { "epoch": 0.291206733598445, "grad_norm": 6.6591291427612305, "learning_rate": 5.823981168862048e-06, "loss": 0.6691, "step": 48990 }, { "epoch": 0.29126617567511337, "grad_norm": 7.248281002044678, "learning_rate": 5.825170003328737e-06, "loss": 0.6543, "step": 49000 }, { "epoch": 0.2913256177517818, "grad_norm": 7.049742698669434, "learning_rate": 5.826358837795426e-06, "loss": 0.7046, "step": 49010 }, { "epoch": 0.29138505982845014, "grad_norm": 6.638852596282959, "learning_rate": 5.827547672262115e-06, "loss": 0.6781, "step": 49020 }, { "epoch": 0.29144450190511856, "grad_norm": 9.452354431152344, "learning_rate": 5.828736506728804e-06, "loss": 0.6755, "step": 49030 }, { "epoch": 0.291503943981787, "grad_norm": 6.725903034210205, "learning_rate": 5.829925341195493e-06, "loss": 0.7131, "step": 49040 }, { "epoch": 0.29156338605845533, "grad_norm": 9.820365905761719, "learning_rate": 5.831114175662182e-06, "loss": 0.6417, "step": 49050 }, { "epoch": 0.29162282813512375, "grad_norm": 7.750011920928955, "learning_rate": 5.83230301012887e-06, "loss": 0.7032, "step": 49060 }, { "epoch": 0.2916822702117921, "grad_norm": 7.906347751617432, "learning_rate": 5.833491844595559e-06, "loss": 0.6729, "step": 49070 }, { "epoch": 0.2917417122884605, "grad_norm": 6.927288055419922, "learning_rate": 5.834680679062248e-06, "loss": 0.63, "step": 49080 }, { "epoch": 0.2918011543651289, "grad_norm": 6.704195022583008, "learning_rate": 5.835869513528937e-06, "loss": 0.654, "step": 49090 }, { "epoch": 0.2918605964417973, "grad_norm": 6.951728820800781, "learning_rate": 5.837058347995626e-06, "loss": 0.6381, "step": 49100 }, { "epoch": 0.2919200385184657, "grad_norm": 7.9146199226379395, "learning_rate": 5.8382471824623145e-06, "loss": 0.6656, "step": 49110 }, { "epoch": 0.29197948059513407, "grad_norm": 9.696331024169922, "learning_rate": 5.8394360169290034e-06, "loss": 0.6197, "step": 49120 }, { "epoch": 0.2920389226718025, "grad_norm": 8.881671905517578, "learning_rate": 5.840624851395692e-06, "loss": 0.6865, "step": 49130 }, { "epoch": 0.29209836474847084, "grad_norm": 8.19029426574707, "learning_rate": 5.8418136858623804e-06, "loss": 0.6877, "step": 49140 }, { "epoch": 0.29215780682513925, "grad_norm": 7.50982666015625, "learning_rate": 5.843002520329069e-06, "loss": 0.6972, "step": 49150 }, { "epoch": 0.2922172489018076, "grad_norm": 8.915328025817871, "learning_rate": 5.844191354795758e-06, "loss": 0.7015, "step": 49160 }, { "epoch": 0.29227669097847603, "grad_norm": 8.45576000213623, "learning_rate": 5.845380189262447e-06, "loss": 0.6333, "step": 49170 }, { "epoch": 0.2923361330551444, "grad_norm": 9.373254776000977, "learning_rate": 5.846569023729136e-06, "loss": 0.7673, "step": 49180 }, { "epoch": 0.2923955751318128, "grad_norm": 9.876579284667969, "learning_rate": 5.847757858195825e-06, "loss": 0.7119, "step": 49190 }, { "epoch": 0.2924550172084812, "grad_norm": 6.909745216369629, "learning_rate": 5.848946692662514e-06, "loss": 0.6973, "step": 49200 }, { "epoch": 0.2925144592851496, "grad_norm": 8.628888130187988, "learning_rate": 5.850135527129203e-06, "loss": 0.6944, "step": 49210 }, { "epoch": 0.292573901361818, "grad_norm": 7.539057731628418, "learning_rate": 5.851324361595892e-06, "loss": 0.6557, "step": 49220 }, { "epoch": 0.29263334343848635, "grad_norm": 6.621892929077148, "learning_rate": 5.85251319606258e-06, "loss": 0.6935, "step": 49230 }, { "epoch": 0.29269278551515476, "grad_norm": 8.331731796264648, "learning_rate": 5.853702030529269e-06, "loss": 0.6582, "step": 49240 }, { "epoch": 0.2927522275918231, "grad_norm": 6.835197925567627, "learning_rate": 5.854890864995958e-06, "loss": 0.6487, "step": 49250 }, { "epoch": 0.29281166966849154, "grad_norm": 7.9988112449646, "learning_rate": 5.856079699462647e-06, "loss": 0.7052, "step": 49260 }, { "epoch": 0.29287111174515995, "grad_norm": 8.909003257751465, "learning_rate": 5.8572685339293365e-06, "loss": 0.6813, "step": 49270 }, { "epoch": 0.2929305538218283, "grad_norm": 9.08167839050293, "learning_rate": 5.8584573683960254e-06, "loss": 0.6849, "step": 49280 }, { "epoch": 0.2929899958984967, "grad_norm": 8.547530174255371, "learning_rate": 5.859646202862714e-06, "loss": 0.6525, "step": 49290 }, { "epoch": 0.2930494379751651, "grad_norm": 9.13791275024414, "learning_rate": 5.860835037329403e-06, "loss": 0.7174, "step": 49300 }, { "epoch": 0.2931088800518335, "grad_norm": 6.522952079772949, "learning_rate": 5.862023871796092e-06, "loss": 0.6301, "step": 49310 }, { "epoch": 0.29316832212850186, "grad_norm": 9.150466918945312, "learning_rate": 5.863212706262781e-06, "loss": 0.7154, "step": 49320 }, { "epoch": 0.29322776420517027, "grad_norm": 8.554628372192383, "learning_rate": 5.86440154072947e-06, "loss": 0.7014, "step": 49330 }, { "epoch": 0.2932872062818387, "grad_norm": 7.923049449920654, "learning_rate": 5.865590375196158e-06, "loss": 0.6481, "step": 49340 }, { "epoch": 0.29334664835850705, "grad_norm": 8.78167724609375, "learning_rate": 5.866779209662847e-06, "loss": 0.6646, "step": 49350 }, { "epoch": 0.29340609043517546, "grad_norm": 6.894704818725586, "learning_rate": 5.867968044129536e-06, "loss": 0.7086, "step": 49360 }, { "epoch": 0.2934655325118438, "grad_norm": 9.846534729003906, "learning_rate": 5.869156878596225e-06, "loss": 0.6963, "step": 49370 }, { "epoch": 0.29352497458851223, "grad_norm": 7.306947708129883, "learning_rate": 5.870345713062914e-06, "loss": 0.7676, "step": 49380 }, { "epoch": 0.2935844166651806, "grad_norm": 7.220934867858887, "learning_rate": 5.871534547529603e-06, "loss": 0.6683, "step": 49390 }, { "epoch": 0.293643858741849, "grad_norm": 5.615740776062012, "learning_rate": 5.872723381996292e-06, "loss": 0.676, "step": 49400 }, { "epoch": 0.2937033008185174, "grad_norm": 8.818184852600098, "learning_rate": 5.873912216462981e-06, "loss": 0.6911, "step": 49410 }, { "epoch": 0.2937627428951858, "grad_norm": 6.085742950439453, "learning_rate": 5.875101050929669e-06, "loss": 0.7076, "step": 49420 }, { "epoch": 0.2938221849718542, "grad_norm": 6.839555740356445, "learning_rate": 5.876289885396358e-06, "loss": 0.5931, "step": 49430 }, { "epoch": 0.29388162704852255, "grad_norm": 6.935847759246826, "learning_rate": 5.8774787198630466e-06, "loss": 0.6363, "step": 49440 }, { "epoch": 0.29394106912519097, "grad_norm": 9.254481315612793, "learning_rate": 5.8786675543297355e-06, "loss": 0.6537, "step": 49450 }, { "epoch": 0.2940005112018593, "grad_norm": 7.6700615882873535, "learning_rate": 5.8798563887964244e-06, "loss": 0.6892, "step": 49460 }, { "epoch": 0.29405995327852774, "grad_norm": 8.581077575683594, "learning_rate": 5.881045223263113e-06, "loss": 0.7296, "step": 49470 }, { "epoch": 0.29411939535519616, "grad_norm": 8.337624549865723, "learning_rate": 5.882234057729802e-06, "loss": 0.6811, "step": 49480 }, { "epoch": 0.2941788374318645, "grad_norm": 8.525111198425293, "learning_rate": 5.883422892196491e-06, "loss": 0.6948, "step": 49490 }, { "epoch": 0.29423827950853293, "grad_norm": 6.488106727600098, "learning_rate": 5.884611726663179e-06, "loss": 0.6949, "step": 49500 }, { "epoch": 0.2942977215852013, "grad_norm": 8.066025733947754, "learning_rate": 5.885800561129868e-06, "loss": 0.7349, "step": 49510 }, { "epoch": 0.2943571636618697, "grad_norm": 6.906620502471924, "learning_rate": 5.886989395596557e-06, "loss": 0.6887, "step": 49520 }, { "epoch": 0.29441660573853806, "grad_norm": 10.365031242370605, "learning_rate": 5.888178230063246e-06, "loss": 0.7546, "step": 49530 }, { "epoch": 0.2944760478152065, "grad_norm": 7.165436744689941, "learning_rate": 5.889367064529935e-06, "loss": 0.6905, "step": 49540 }, { "epoch": 0.29453548989187484, "grad_norm": 7.371731281280518, "learning_rate": 5.890555898996624e-06, "loss": 0.6605, "step": 49550 }, { "epoch": 0.29459493196854325, "grad_norm": 8.426372528076172, "learning_rate": 5.891744733463313e-06, "loss": 0.6748, "step": 49560 }, { "epoch": 0.29465437404521166, "grad_norm": 7.465333938598633, "learning_rate": 5.892933567930002e-06, "loss": 0.672, "step": 49570 }, { "epoch": 0.29471381612188, "grad_norm": 7.686800479888916, "learning_rate": 5.894122402396691e-06, "loss": 0.6389, "step": 49580 }, { "epoch": 0.29477325819854844, "grad_norm": 8.481553077697754, "learning_rate": 5.895311236863379e-06, "loss": 0.6677, "step": 49590 }, { "epoch": 0.2948327002752168, "grad_norm": 8.462747573852539, "learning_rate": 5.896500071330068e-06, "loss": 0.6777, "step": 49600 }, { "epoch": 0.2948921423518852, "grad_norm": 8.621614456176758, "learning_rate": 5.897688905796757e-06, "loss": 0.7376, "step": 49610 }, { "epoch": 0.29495158442855357, "grad_norm": 8.902145385742188, "learning_rate": 5.898877740263446e-06, "loss": 0.6928, "step": 49620 }, { "epoch": 0.295011026505222, "grad_norm": 7.10695219039917, "learning_rate": 5.900066574730135e-06, "loss": 0.6562, "step": 49630 }, { "epoch": 0.2950704685818904, "grad_norm": 6.5391130447387695, "learning_rate": 5.901255409196824e-06, "loss": 0.6947, "step": 49640 }, { "epoch": 0.29512991065855876, "grad_norm": 9.984424591064453, "learning_rate": 5.902444243663513e-06, "loss": 0.6791, "step": 49650 }, { "epoch": 0.2951893527352272, "grad_norm": 8.07325553894043, "learning_rate": 5.903633078130202e-06, "loss": 0.6863, "step": 49660 }, { "epoch": 0.29524879481189553, "grad_norm": 8.174922943115234, "learning_rate": 5.904821912596891e-06, "loss": 0.6838, "step": 49670 }, { "epoch": 0.29530823688856395, "grad_norm": 6.402188301086426, "learning_rate": 5.90601074706358e-06, "loss": 0.6921, "step": 49680 }, { "epoch": 0.2953676789652323, "grad_norm": 8.553342819213867, "learning_rate": 5.907199581530269e-06, "loss": 0.6418, "step": 49690 }, { "epoch": 0.2954271210419007, "grad_norm": 9.394218444824219, "learning_rate": 5.908388415996957e-06, "loss": 0.6898, "step": 49700 }, { "epoch": 0.29548656311856913, "grad_norm": 8.648033142089844, "learning_rate": 5.909577250463646e-06, "loss": 0.6442, "step": 49710 }, { "epoch": 0.2955460051952375, "grad_norm": 11.333467483520508, "learning_rate": 5.910766084930335e-06, "loss": 0.7089, "step": 49720 }, { "epoch": 0.2956054472719059, "grad_norm": 8.974658012390137, "learning_rate": 5.911954919397024e-06, "loss": 0.679, "step": 49730 }, { "epoch": 0.29566488934857427, "grad_norm": 6.56845235824585, "learning_rate": 5.913143753863713e-06, "loss": 0.6903, "step": 49740 }, { "epoch": 0.2957243314252427, "grad_norm": 8.372864723205566, "learning_rate": 5.914332588330402e-06, "loss": 0.6776, "step": 49750 }, { "epoch": 0.29578377350191104, "grad_norm": 5.898775577545166, "learning_rate": 5.9155214227970906e-06, "loss": 0.6345, "step": 49760 }, { "epoch": 0.29584321557857945, "grad_norm": 7.698451519012451, "learning_rate": 5.9167102572637795e-06, "loss": 0.747, "step": 49770 }, { "epoch": 0.29590265765524787, "grad_norm": 6.550535678863525, "learning_rate": 5.9178990917304676e-06, "loss": 0.6528, "step": 49780 }, { "epoch": 0.29596209973191623, "grad_norm": 6.601836204528809, "learning_rate": 5.9190879261971565e-06, "loss": 0.7187, "step": 49790 }, { "epoch": 0.29602154180858464, "grad_norm": 7.948441028594971, "learning_rate": 5.920276760663845e-06, "loss": 0.7188, "step": 49800 }, { "epoch": 0.296080983885253, "grad_norm": 7.083670616149902, "learning_rate": 5.921465595130534e-06, "loss": 0.6725, "step": 49810 }, { "epoch": 0.2961404259619214, "grad_norm": 7.462772369384766, "learning_rate": 5.922654429597223e-06, "loss": 0.7173, "step": 49820 }, { "epoch": 0.2961998680385898, "grad_norm": 7.250545978546143, "learning_rate": 5.923843264063912e-06, "loss": 0.653, "step": 49830 }, { "epoch": 0.2962593101152582, "grad_norm": 9.040182113647461, "learning_rate": 5.925032098530601e-06, "loss": 0.6081, "step": 49840 }, { "epoch": 0.2963187521919266, "grad_norm": 7.0130510330200195, "learning_rate": 5.92622093299729e-06, "loss": 0.6605, "step": 49850 }, { "epoch": 0.29637819426859496, "grad_norm": 8.539756774902344, "learning_rate": 5.927409767463979e-06, "loss": 0.6927, "step": 49860 }, { "epoch": 0.2964376363452634, "grad_norm": 8.371710777282715, "learning_rate": 5.928598601930667e-06, "loss": 0.6876, "step": 49870 }, { "epoch": 0.29649707842193174, "grad_norm": 7.810273170471191, "learning_rate": 5.929787436397356e-06, "loss": 0.6662, "step": 49880 }, { "epoch": 0.29655652049860015, "grad_norm": 7.166548728942871, "learning_rate": 5.930976270864045e-06, "loss": 0.7095, "step": 49890 }, { "epoch": 0.2966159625752685, "grad_norm": 6.932495594024658, "learning_rate": 5.932165105330734e-06, "loss": 0.6429, "step": 49900 }, { "epoch": 0.2966754046519369, "grad_norm": 6.778052806854248, "learning_rate": 5.933353939797423e-06, "loss": 0.7241, "step": 49910 }, { "epoch": 0.2967348467286053, "grad_norm": 8.174882888793945, "learning_rate": 5.934542774264112e-06, "loss": 0.7177, "step": 49920 }, { "epoch": 0.2967942888052737, "grad_norm": 8.490127563476562, "learning_rate": 5.935731608730801e-06, "loss": 0.6894, "step": 49930 }, { "epoch": 0.2968537308819421, "grad_norm": 7.78882360458374, "learning_rate": 5.9369204431974895e-06, "loss": 0.652, "step": 49940 }, { "epoch": 0.29691317295861047, "grad_norm": 6.538112163543701, "learning_rate": 5.938109277664178e-06, "loss": 0.6487, "step": 49950 }, { "epoch": 0.2969726150352789, "grad_norm": 6.970437049865723, "learning_rate": 5.939298112130868e-06, "loss": 0.6504, "step": 49960 }, { "epoch": 0.29703205711194725, "grad_norm": 9.223081588745117, "learning_rate": 5.940486946597557e-06, "loss": 0.694, "step": 49970 }, { "epoch": 0.29709149918861566, "grad_norm": 7.926652431488037, "learning_rate": 5.941675781064245e-06, "loss": 0.6473, "step": 49980 }, { "epoch": 0.297150941265284, "grad_norm": 8.131919860839844, "learning_rate": 5.942864615530934e-06, "loss": 0.6224, "step": 49990 }, { "epoch": 0.29721038334195243, "grad_norm": 9.168152809143066, "learning_rate": 5.944053449997623e-06, "loss": 0.7111, "step": 50000 }, { "epoch": 0.29726982541862085, "grad_norm": 6.6520586013793945, "learning_rate": 5.945242284464312e-06, "loss": 0.6481, "step": 50010 }, { "epoch": 0.2973292674952892, "grad_norm": 6.7108025550842285, "learning_rate": 5.946431118931001e-06, "loss": 0.7298, "step": 50020 }, { "epoch": 0.2973887095719576, "grad_norm": 8.897520065307617, "learning_rate": 5.94761995339769e-06, "loss": 0.6452, "step": 50030 }, { "epoch": 0.297448151648626, "grad_norm": 8.235414505004883, "learning_rate": 5.948808787864379e-06, "loss": 0.7057, "step": 50040 }, { "epoch": 0.2975075937252944, "grad_norm": 7.063634395599365, "learning_rate": 5.949997622331068e-06, "loss": 0.7012, "step": 50050 }, { "epoch": 0.29756703580196275, "grad_norm": 7.379873752593994, "learning_rate": 5.951186456797756e-06, "loss": 0.6566, "step": 50060 }, { "epoch": 0.29762647787863117, "grad_norm": 8.959161758422852, "learning_rate": 5.952375291264445e-06, "loss": 0.6821, "step": 50070 }, { "epoch": 0.2976859199552996, "grad_norm": 10.395132064819336, "learning_rate": 5.953564125731134e-06, "loss": 0.6791, "step": 50080 }, { "epoch": 0.29774536203196794, "grad_norm": 10.091307640075684, "learning_rate": 5.954752960197823e-06, "loss": 0.6752, "step": 50090 }, { "epoch": 0.29780480410863636, "grad_norm": 7.255031585693359, "learning_rate": 5.9559417946645115e-06, "loss": 0.6986, "step": 50100 }, { "epoch": 0.2978642461853047, "grad_norm": 6.1692280769348145, "learning_rate": 5.9571306291312005e-06, "loss": 0.6336, "step": 50110 }, { "epoch": 0.29792368826197313, "grad_norm": 7.068656921386719, "learning_rate": 5.958319463597889e-06, "loss": 0.682, "step": 50120 }, { "epoch": 0.2979831303386415, "grad_norm": 8.019923210144043, "learning_rate": 5.959508298064578e-06, "loss": 0.7175, "step": 50130 }, { "epoch": 0.2980425724153099, "grad_norm": 10.23921012878418, "learning_rate": 5.960697132531266e-06, "loss": 0.7448, "step": 50140 }, { "epoch": 0.2981020144919783, "grad_norm": 6.6908721923828125, "learning_rate": 5.961885966997955e-06, "loss": 0.6741, "step": 50150 }, { "epoch": 0.2981614565686467, "grad_norm": 6.663179397583008, "learning_rate": 5.963074801464644e-06, "loss": 0.6457, "step": 50160 }, { "epoch": 0.2982208986453151, "grad_norm": 8.79240608215332, "learning_rate": 5.964263635931333e-06, "loss": 0.69, "step": 50170 }, { "epoch": 0.29828034072198345, "grad_norm": 8.346190452575684, "learning_rate": 5.965452470398022e-06, "loss": 0.7246, "step": 50180 }, { "epoch": 0.29833978279865186, "grad_norm": 8.513324737548828, "learning_rate": 5.966641304864711e-06, "loss": 0.6742, "step": 50190 }, { "epoch": 0.2983992248753202, "grad_norm": 8.000957489013672, "learning_rate": 5.9678301393314e-06, "loss": 0.7022, "step": 50200 }, { "epoch": 0.29845866695198864, "grad_norm": 8.207215309143066, "learning_rate": 5.969018973798089e-06, "loss": 0.6306, "step": 50210 }, { "epoch": 0.29851810902865705, "grad_norm": 4.5951924324035645, "learning_rate": 5.970207808264778e-06, "loss": 0.6577, "step": 50220 }, { "epoch": 0.2985775511053254, "grad_norm": 7.207422256469727, "learning_rate": 5.971396642731466e-06, "loss": 0.6538, "step": 50230 }, { "epoch": 0.2986369931819938, "grad_norm": 6.968116760253906, "learning_rate": 5.972585477198155e-06, "loss": 0.6327, "step": 50240 }, { "epoch": 0.2986964352586622, "grad_norm": 7.635105133056641, "learning_rate": 5.973774311664844e-06, "loss": 0.6884, "step": 50250 }, { "epoch": 0.2987558773353306, "grad_norm": 7.861950397491455, "learning_rate": 5.974963146131533e-06, "loss": 0.6574, "step": 50260 }, { "epoch": 0.29881531941199896, "grad_norm": 6.940739154815674, "learning_rate": 5.976151980598222e-06, "loss": 0.7049, "step": 50270 }, { "epoch": 0.2988747614886674, "grad_norm": 8.50637435913086, "learning_rate": 5.9773408150649105e-06, "loss": 0.7104, "step": 50280 }, { "epoch": 0.29893420356533573, "grad_norm": 7.059813499450684, "learning_rate": 5.9785296495315995e-06, "loss": 0.6965, "step": 50290 }, { "epoch": 0.29899364564200415, "grad_norm": 6.6384782791137695, "learning_rate": 5.979718483998288e-06, "loss": 0.6661, "step": 50300 }, { "epoch": 0.29905308771867256, "grad_norm": 12.395705223083496, "learning_rate": 5.980907318464978e-06, "loss": 0.664, "step": 50310 }, { "epoch": 0.2991125297953409, "grad_norm": 7.440957546234131, "learning_rate": 5.982096152931667e-06, "loss": 0.652, "step": 50320 }, { "epoch": 0.29917197187200933, "grad_norm": 7.1068010330200195, "learning_rate": 5.983284987398356e-06, "loss": 0.6878, "step": 50330 }, { "epoch": 0.2992314139486777, "grad_norm": 7.710545539855957, "learning_rate": 5.984473821865044e-06, "loss": 0.6402, "step": 50340 }, { "epoch": 0.2992908560253461, "grad_norm": 7.352733135223389, "learning_rate": 5.985662656331733e-06, "loss": 0.7064, "step": 50350 }, { "epoch": 0.29935029810201447, "grad_norm": 9.420605659484863, "learning_rate": 5.986851490798422e-06, "loss": 0.6909, "step": 50360 }, { "epoch": 0.2994097401786829, "grad_norm": 7.645858287811279, "learning_rate": 5.988040325265111e-06, "loss": 0.6775, "step": 50370 }, { "epoch": 0.2994691822553513, "grad_norm": 8.305408477783203, "learning_rate": 5.9892291597318e-06, "loss": 0.6936, "step": 50380 }, { "epoch": 0.29952862433201966, "grad_norm": 11.179654121398926, "learning_rate": 5.990417994198489e-06, "loss": 0.6762, "step": 50390 }, { "epoch": 0.29958806640868807, "grad_norm": 7.169746398925781, "learning_rate": 5.991606828665178e-06, "loss": 0.5901, "step": 50400 }, { "epoch": 0.29964750848535643, "grad_norm": 7.306872367858887, "learning_rate": 5.992795663131867e-06, "loss": 0.6964, "step": 50410 }, { "epoch": 0.29970695056202484, "grad_norm": 9.659628868103027, "learning_rate": 5.993984497598555e-06, "loss": 0.6371, "step": 50420 }, { "epoch": 0.2997663926386932, "grad_norm": 6.900927543640137, "learning_rate": 5.995173332065244e-06, "loss": 0.6963, "step": 50430 }, { "epoch": 0.2998258347153616, "grad_norm": 7.843333721160889, "learning_rate": 5.9963621665319325e-06, "loss": 0.6752, "step": 50440 }, { "epoch": 0.29988527679203003, "grad_norm": 8.724472045898438, "learning_rate": 5.9975510009986215e-06, "loss": 0.7375, "step": 50450 }, { "epoch": 0.2999447188686984, "grad_norm": 7.43227481842041, "learning_rate": 5.99873983546531e-06, "loss": 0.5941, "step": 50460 }, { "epoch": 0.3000041609453668, "grad_norm": 7.309012413024902, "learning_rate": 5.999928669931999e-06, "loss": 0.5999, "step": 50470 }, { "epoch": 0.30006360302203516, "grad_norm": 7.510194301605225, "learning_rate": 6.001117504398688e-06, "loss": 0.6407, "step": 50480 }, { "epoch": 0.3001230450987036, "grad_norm": 7.313812255859375, "learning_rate": 6.002306338865377e-06, "loss": 0.7025, "step": 50490 }, { "epoch": 0.30018248717537194, "grad_norm": 11.727547645568848, "learning_rate": 6.003495173332065e-06, "loss": 0.7238, "step": 50500 }, { "epoch": 0.30024192925204035, "grad_norm": 8.667947769165039, "learning_rate": 6.004684007798754e-06, "loss": 0.6929, "step": 50510 }, { "epoch": 0.30030137132870877, "grad_norm": 6.909906387329102, "learning_rate": 6.005872842265443e-06, "loss": 0.618, "step": 50520 }, { "epoch": 0.3003608134053771, "grad_norm": 6.663425922393799, "learning_rate": 6.007061676732132e-06, "loss": 0.6731, "step": 50530 }, { "epoch": 0.30042025548204554, "grad_norm": 7.435368061065674, "learning_rate": 6.008250511198821e-06, "loss": 0.6728, "step": 50540 }, { "epoch": 0.3004796975587139, "grad_norm": 8.440374374389648, "learning_rate": 6.00943934566551e-06, "loss": 0.6961, "step": 50550 }, { "epoch": 0.3005391396353823, "grad_norm": 7.248635292053223, "learning_rate": 6.010628180132199e-06, "loss": 0.664, "step": 50560 }, { "epoch": 0.30059858171205067, "grad_norm": 8.842635154724121, "learning_rate": 6.011817014598888e-06, "loss": 0.6506, "step": 50570 }, { "epoch": 0.3006580237887191, "grad_norm": 7.660337924957275, "learning_rate": 6.013005849065577e-06, "loss": 0.6547, "step": 50580 }, { "epoch": 0.30071746586538745, "grad_norm": 5.957102298736572, "learning_rate": 6.014194683532265e-06, "loss": 0.6512, "step": 50590 }, { "epoch": 0.30077690794205586, "grad_norm": 7.462443828582764, "learning_rate": 6.015383517998954e-06, "loss": 0.6988, "step": 50600 }, { "epoch": 0.3008363500187243, "grad_norm": 6.4484100341796875, "learning_rate": 6.016572352465643e-06, "loss": 0.6596, "step": 50610 }, { "epoch": 0.30089579209539263, "grad_norm": 8.207751274108887, "learning_rate": 6.0177611869323315e-06, "loss": 0.7072, "step": 50620 }, { "epoch": 0.30095523417206105, "grad_norm": 7.420409202575684, "learning_rate": 6.0189500213990205e-06, "loss": 0.7028, "step": 50630 }, { "epoch": 0.3010146762487294, "grad_norm": 7.230646133422852, "learning_rate": 6.020138855865709e-06, "loss": 0.736, "step": 50640 }, { "epoch": 0.3010741183253978, "grad_norm": 6.949833869934082, "learning_rate": 6.021327690332398e-06, "loss": 0.6553, "step": 50650 }, { "epoch": 0.3011335604020662, "grad_norm": 9.263751983642578, "learning_rate": 6.022516524799088e-06, "loss": 0.6429, "step": 50660 }, { "epoch": 0.3011930024787346, "grad_norm": 6.596306324005127, "learning_rate": 6.023705359265777e-06, "loss": 0.7185, "step": 50670 }, { "epoch": 0.301252444555403, "grad_norm": 8.0347318649292, "learning_rate": 6.024894193732466e-06, "loss": 0.6511, "step": 50680 }, { "epoch": 0.30131188663207137, "grad_norm": 8.444332122802734, "learning_rate": 6.026083028199155e-06, "loss": 0.718, "step": 50690 }, { "epoch": 0.3013713287087398, "grad_norm": 7.3823394775390625, "learning_rate": 6.027271862665843e-06, "loss": 0.6798, "step": 50700 }, { "epoch": 0.30143077078540814, "grad_norm": 7.5769877433776855, "learning_rate": 6.028460697132532e-06, "loss": 0.6997, "step": 50710 }, { "epoch": 0.30149021286207656, "grad_norm": 8.563908576965332, "learning_rate": 6.029649531599221e-06, "loss": 0.7402, "step": 50720 }, { "epoch": 0.3015496549387449, "grad_norm": 5.908865928649902, "learning_rate": 6.03083836606591e-06, "loss": 0.64, "step": 50730 }, { "epoch": 0.30160909701541333, "grad_norm": 8.250834465026855, "learning_rate": 6.032027200532599e-06, "loss": 0.7115, "step": 50740 }, { "epoch": 0.30166853909208174, "grad_norm": 8.837372779846191, "learning_rate": 6.033216034999288e-06, "loss": 0.6571, "step": 50750 }, { "epoch": 0.3017279811687501, "grad_norm": 12.965543746948242, "learning_rate": 6.0344048694659765e-06, "loss": 0.7138, "step": 50760 }, { "epoch": 0.3017874232454185, "grad_norm": 7.110495567321777, "learning_rate": 6.0355937039326654e-06, "loss": 0.6217, "step": 50770 }, { "epoch": 0.3018468653220869, "grad_norm": 7.082857608795166, "learning_rate": 6.0367825383993535e-06, "loss": 0.6522, "step": 50780 }, { "epoch": 0.3019063073987553, "grad_norm": 6.6859941482543945, "learning_rate": 6.0379713728660424e-06, "loss": 0.5865, "step": 50790 }, { "epoch": 0.30196574947542365, "grad_norm": 6.789063453674316, "learning_rate": 6.039160207332731e-06, "loss": 0.6537, "step": 50800 }, { "epoch": 0.30202519155209206, "grad_norm": 8.825140953063965, "learning_rate": 6.04034904179942e-06, "loss": 0.7224, "step": 50810 }, { "epoch": 0.3020846336287605, "grad_norm": 5.673745632171631, "learning_rate": 6.041537876266109e-06, "loss": 0.6636, "step": 50820 }, { "epoch": 0.30214407570542884, "grad_norm": 7.07623291015625, "learning_rate": 6.042726710732798e-06, "loss": 0.6975, "step": 50830 }, { "epoch": 0.30220351778209725, "grad_norm": 7.0686187744140625, "learning_rate": 6.043915545199487e-06, "loss": 0.7012, "step": 50840 }, { "epoch": 0.3022629598587656, "grad_norm": 6.916974067687988, "learning_rate": 6.045104379666176e-06, "loss": 0.6791, "step": 50850 }, { "epoch": 0.302322401935434, "grad_norm": 6.255972385406494, "learning_rate": 6.046293214132865e-06, "loss": 0.6435, "step": 50860 }, { "epoch": 0.3023818440121024, "grad_norm": 6.458662986755371, "learning_rate": 6.047482048599553e-06, "loss": 0.6999, "step": 50870 }, { "epoch": 0.3024412860887708, "grad_norm": 8.143043518066406, "learning_rate": 6.048670883066242e-06, "loss": 0.6892, "step": 50880 }, { "epoch": 0.3025007281654392, "grad_norm": 7.622605323791504, "learning_rate": 6.049859717532931e-06, "loss": 0.648, "step": 50890 }, { "epoch": 0.3025601702421076, "grad_norm": 6.861380100250244, "learning_rate": 6.05104855199962e-06, "loss": 0.6444, "step": 50900 }, { "epoch": 0.302619612318776, "grad_norm": 7.3069167137146, "learning_rate": 6.052237386466309e-06, "loss": 0.6949, "step": 50910 }, { "epoch": 0.30267905439544435, "grad_norm": 6.923299789428711, "learning_rate": 6.053426220932998e-06, "loss": 0.6829, "step": 50920 }, { "epoch": 0.30273849647211276, "grad_norm": 7.6846513748168945, "learning_rate": 6.0546150553996866e-06, "loss": 0.7615, "step": 50930 }, { "epoch": 0.3027979385487811, "grad_norm": 9.013240814208984, "learning_rate": 6.0558038898663755e-06, "loss": 0.6667, "step": 50940 }, { "epoch": 0.30285738062544953, "grad_norm": 7.757073879241943, "learning_rate": 6.056992724333064e-06, "loss": 0.6526, "step": 50950 }, { "epoch": 0.3029168227021179, "grad_norm": 7.346501350402832, "learning_rate": 6.0581815587997525e-06, "loss": 0.6818, "step": 50960 }, { "epoch": 0.3029762647787863, "grad_norm": 7.411142349243164, "learning_rate": 6.0593703932664414e-06, "loss": 0.7148, "step": 50970 }, { "epoch": 0.3030357068554547, "grad_norm": 10.670323371887207, "learning_rate": 6.06055922773313e-06, "loss": 0.7079, "step": 50980 }, { "epoch": 0.3030951489321231, "grad_norm": 7.572115421295166, "learning_rate": 6.061748062199819e-06, "loss": 0.6827, "step": 50990 }, { "epoch": 0.3031545910087915, "grad_norm": 7.6496758460998535, "learning_rate": 6.062936896666509e-06, "loss": 0.667, "step": 51000 }, { "epoch": 0.30321403308545986, "grad_norm": 7.962249279022217, "learning_rate": 6.064125731133198e-06, "loss": 0.6624, "step": 51010 }, { "epoch": 0.30327347516212827, "grad_norm": 6.947100639343262, "learning_rate": 6.065314565599887e-06, "loss": 0.6565, "step": 51020 }, { "epoch": 0.30333291723879663, "grad_norm": 7.090481281280518, "learning_rate": 6.066503400066576e-06, "loss": 0.6874, "step": 51030 }, { "epoch": 0.30339235931546504, "grad_norm": 7.54755163192749, "learning_rate": 6.067692234533265e-06, "loss": 0.6452, "step": 51040 }, { "epoch": 0.30345180139213346, "grad_norm": 7.926474094390869, "learning_rate": 6.068881068999954e-06, "loss": 0.6632, "step": 51050 }, { "epoch": 0.3035112434688018, "grad_norm": 9.719962120056152, "learning_rate": 6.070069903466642e-06, "loss": 0.6186, "step": 51060 }, { "epoch": 0.30357068554547023, "grad_norm": 7.730898380279541, "learning_rate": 6.071258737933331e-06, "loss": 0.6803, "step": 51070 }, { "epoch": 0.3036301276221386, "grad_norm": 11.414582252502441, "learning_rate": 6.07244757240002e-06, "loss": 0.7473, "step": 51080 }, { "epoch": 0.303689569698807, "grad_norm": 6.4377593994140625, "learning_rate": 6.0736364068667086e-06, "loss": 0.6951, "step": 51090 }, { "epoch": 0.30374901177547536, "grad_norm": 6.659473419189453, "learning_rate": 6.0748252413333975e-06, "loss": 0.6518, "step": 51100 }, { "epoch": 0.3038084538521438, "grad_norm": 8.506194114685059, "learning_rate": 6.076014075800086e-06, "loss": 0.6541, "step": 51110 }, { "epoch": 0.3038678959288122, "grad_norm": 8.018508911132812, "learning_rate": 6.077202910266775e-06, "loss": 0.6753, "step": 51120 }, { "epoch": 0.30392733800548055, "grad_norm": 6.7972187995910645, "learning_rate": 6.078391744733464e-06, "loss": 0.6313, "step": 51130 }, { "epoch": 0.30398678008214897, "grad_norm": 8.356203079223633, "learning_rate": 6.079580579200152e-06, "loss": 0.6535, "step": 51140 }, { "epoch": 0.3040462221588173, "grad_norm": 9.781089782714844, "learning_rate": 6.080769413666841e-06, "loss": 0.6649, "step": 51150 }, { "epoch": 0.30410566423548574, "grad_norm": 9.263895988464355, "learning_rate": 6.08195824813353e-06, "loss": 0.646, "step": 51160 }, { "epoch": 0.3041651063121541, "grad_norm": 9.779850006103516, "learning_rate": 6.083147082600219e-06, "loss": 0.6701, "step": 51170 }, { "epoch": 0.3042245483888225, "grad_norm": 7.492403507232666, "learning_rate": 6.084335917066908e-06, "loss": 0.713, "step": 51180 }, { "epoch": 0.30428399046549093, "grad_norm": 9.249069213867188, "learning_rate": 6.085524751533597e-06, "loss": 0.6734, "step": 51190 }, { "epoch": 0.3043434325421593, "grad_norm": 9.119695663452148, "learning_rate": 6.086713586000286e-06, "loss": 0.6931, "step": 51200 }, { "epoch": 0.3044028746188277, "grad_norm": 7.707710266113281, "learning_rate": 6.087902420466975e-06, "loss": 0.7252, "step": 51210 }, { "epoch": 0.30446231669549606, "grad_norm": 10.106579780578613, "learning_rate": 6.089091254933664e-06, "loss": 0.6726, "step": 51220 }, { "epoch": 0.3045217587721645, "grad_norm": 5.813324928283691, "learning_rate": 6.090280089400352e-06, "loss": 0.6931, "step": 51230 }, { "epoch": 0.30458120084883283, "grad_norm": 5.480446815490723, "learning_rate": 6.091468923867041e-06, "loss": 0.6556, "step": 51240 }, { "epoch": 0.30464064292550125, "grad_norm": 9.193164825439453, "learning_rate": 6.09265775833373e-06, "loss": 0.6692, "step": 51250 }, { "epoch": 0.30470008500216966, "grad_norm": 9.030402183532715, "learning_rate": 6.093846592800419e-06, "loss": 0.6808, "step": 51260 }, { "epoch": 0.304759527078838, "grad_norm": 9.794221878051758, "learning_rate": 6.0950354272671076e-06, "loss": 0.6959, "step": 51270 }, { "epoch": 0.30481896915550644, "grad_norm": 7.967519760131836, "learning_rate": 6.0962242617337965e-06, "loss": 0.7083, "step": 51280 }, { "epoch": 0.3048784112321748, "grad_norm": 7.065253257751465, "learning_rate": 6.097413096200485e-06, "loss": 0.6976, "step": 51290 }, { "epoch": 0.3049378533088432, "grad_norm": 8.277023315429688, "learning_rate": 6.098601930667174e-06, "loss": 0.6627, "step": 51300 }, { "epoch": 0.30499729538551157, "grad_norm": 10.975015640258789, "learning_rate": 6.0997907651338624e-06, "loss": 0.6388, "step": 51310 }, { "epoch": 0.30505673746218, "grad_norm": 7.920928001403809, "learning_rate": 6.100979599600551e-06, "loss": 0.6145, "step": 51320 }, { "epoch": 0.30511617953884834, "grad_norm": 7.567958831787109, "learning_rate": 6.10216843406724e-06, "loss": 0.6845, "step": 51330 }, { "epoch": 0.30517562161551676, "grad_norm": 7.110637664794922, "learning_rate": 6.103357268533929e-06, "loss": 0.6383, "step": 51340 }, { "epoch": 0.30523506369218517, "grad_norm": 10.544370651245117, "learning_rate": 6.104546103000619e-06, "loss": 0.6717, "step": 51350 }, { "epoch": 0.30529450576885353, "grad_norm": 7.692028045654297, "learning_rate": 6.105734937467308e-06, "loss": 0.6932, "step": 51360 }, { "epoch": 0.30535394784552194, "grad_norm": 7.163381099700928, "learning_rate": 6.106923771933997e-06, "loss": 0.6582, "step": 51370 }, { "epoch": 0.3054133899221903, "grad_norm": 6.775109767913818, "learning_rate": 6.108112606400686e-06, "loss": 0.6756, "step": 51380 }, { "epoch": 0.3054728319988587, "grad_norm": 7.32783842086792, "learning_rate": 6.109301440867375e-06, "loss": 0.7204, "step": 51390 }, { "epoch": 0.3055322740755271, "grad_norm": 7.1845927238464355, "learning_rate": 6.110490275334064e-06, "loss": 0.6572, "step": 51400 }, { "epoch": 0.3055917161521955, "grad_norm": 9.818960189819336, "learning_rate": 6.1116791098007525e-06, "loss": 0.6616, "step": 51410 }, { "epoch": 0.3056511582288639, "grad_norm": 7.954339027404785, "learning_rate": 6.112867944267441e-06, "loss": 0.7208, "step": 51420 }, { "epoch": 0.30571060030553227, "grad_norm": 7.556733131408691, "learning_rate": 6.1140567787341296e-06, "loss": 0.687, "step": 51430 }, { "epoch": 0.3057700423822007, "grad_norm": 7.39786434173584, "learning_rate": 6.1152456132008185e-06, "loss": 0.6635, "step": 51440 }, { "epoch": 0.30582948445886904, "grad_norm": 7.3469557762146, "learning_rate": 6.116434447667507e-06, "loss": 0.6531, "step": 51450 }, { "epoch": 0.30588892653553745, "grad_norm": 6.0723443031311035, "learning_rate": 6.117623282134196e-06, "loss": 0.7037, "step": 51460 }, { "epoch": 0.3059483686122058, "grad_norm": 8.314455032348633, "learning_rate": 6.118812116600885e-06, "loss": 0.697, "step": 51470 }, { "epoch": 0.3060078106888742, "grad_norm": 9.29924201965332, "learning_rate": 6.120000951067574e-06, "loss": 0.7139, "step": 51480 }, { "epoch": 0.30606725276554264, "grad_norm": 7.23459529876709, "learning_rate": 6.121189785534263e-06, "loss": 0.5974, "step": 51490 }, { "epoch": 0.306126694842211, "grad_norm": 6.420229434967041, "learning_rate": 6.122378620000952e-06, "loss": 0.6996, "step": 51500 }, { "epoch": 0.3061861369188794, "grad_norm": 7.840996742248535, "learning_rate": 6.12356745446764e-06, "loss": 0.7679, "step": 51510 }, { "epoch": 0.3062455789955478, "grad_norm": 10.352187156677246, "learning_rate": 6.124756288934329e-06, "loss": 0.6391, "step": 51520 }, { "epoch": 0.3063050210722162, "grad_norm": 9.584892272949219, "learning_rate": 6.125945123401018e-06, "loss": 0.7007, "step": 51530 }, { "epoch": 0.30636446314888455, "grad_norm": 5.564779758453369, "learning_rate": 6.127133957867707e-06, "loss": 0.6691, "step": 51540 }, { "epoch": 0.30642390522555296, "grad_norm": 6.040659427642822, "learning_rate": 6.128322792334396e-06, "loss": 0.6528, "step": 51550 }, { "epoch": 0.3064833473022214, "grad_norm": 8.459815979003906, "learning_rate": 6.129511626801085e-06, "loss": 0.6851, "step": 51560 }, { "epoch": 0.30654278937888974, "grad_norm": 6.541332721710205, "learning_rate": 6.130700461267774e-06, "loss": 0.648, "step": 51570 }, { "epoch": 0.30660223145555815, "grad_norm": 8.528664588928223, "learning_rate": 6.131889295734463e-06, "loss": 0.7209, "step": 51580 }, { "epoch": 0.3066616735322265, "grad_norm": 5.885403156280518, "learning_rate": 6.133078130201151e-06, "loss": 0.6861, "step": 51590 }, { "epoch": 0.3067211156088949, "grad_norm": 9.080140113830566, "learning_rate": 6.13426696466784e-06, "loss": 0.7444, "step": 51600 }, { "epoch": 0.3067805576855633, "grad_norm": 8.44349193572998, "learning_rate": 6.1354557991345285e-06, "loss": 0.7158, "step": 51610 }, { "epoch": 0.3068399997622317, "grad_norm": 6.569721221923828, "learning_rate": 6.1366446336012175e-06, "loss": 0.7036, "step": 51620 }, { "epoch": 0.3068994418389001, "grad_norm": 7.5745720863342285, "learning_rate": 6.137833468067906e-06, "loss": 0.6719, "step": 51630 }, { "epoch": 0.30695888391556847, "grad_norm": 10.605443954467773, "learning_rate": 6.139022302534595e-06, "loss": 0.7193, "step": 51640 }, { "epoch": 0.3070183259922369, "grad_norm": 7.478893756866455, "learning_rate": 6.140211137001284e-06, "loss": 0.7352, "step": 51650 }, { "epoch": 0.30707776806890524, "grad_norm": 7.706376075744629, "learning_rate": 6.141399971467973e-06, "loss": 0.6762, "step": 51660 }, { "epoch": 0.30713721014557366, "grad_norm": 10.205373764038086, "learning_rate": 6.142588805934661e-06, "loss": 0.6514, "step": 51670 }, { "epoch": 0.307196652222242, "grad_norm": 6.851731777191162, "learning_rate": 6.14377764040135e-06, "loss": 0.6982, "step": 51680 }, { "epoch": 0.30725609429891043, "grad_norm": 6.472565174102783, "learning_rate": 6.144966474868039e-06, "loss": 0.6446, "step": 51690 }, { "epoch": 0.3073155363755788, "grad_norm": 7.997514724731445, "learning_rate": 6.146155309334729e-06, "loss": 0.7022, "step": 51700 }, { "epoch": 0.3073749784522472, "grad_norm": 6.711469650268555, "learning_rate": 6.147344143801418e-06, "loss": 0.622, "step": 51710 }, { "epoch": 0.3074344205289156, "grad_norm": 6.884588718414307, "learning_rate": 6.148532978268107e-06, "loss": 0.6541, "step": 51720 }, { "epoch": 0.307493862605584, "grad_norm": 8.219667434692383, "learning_rate": 6.149721812734796e-06, "loss": 0.7294, "step": 51730 }, { "epoch": 0.3075533046822524, "grad_norm": 6.876370429992676, "learning_rate": 6.150910647201485e-06, "loss": 0.7218, "step": 51740 }, { "epoch": 0.30761274675892075, "grad_norm": 10.231059074401855, "learning_rate": 6.1520994816681735e-06, "loss": 0.6446, "step": 51750 }, { "epoch": 0.30767218883558917, "grad_norm": 6.548456192016602, "learning_rate": 6.1532883161348625e-06, "loss": 0.6907, "step": 51760 }, { "epoch": 0.3077316309122575, "grad_norm": 5.929643630981445, "learning_rate": 6.154477150601551e-06, "loss": 0.6485, "step": 51770 }, { "epoch": 0.30779107298892594, "grad_norm": 8.207151412963867, "learning_rate": 6.1556659850682395e-06, "loss": 0.689, "step": 51780 }, { "epoch": 0.30785051506559435, "grad_norm": 8.062686920166016, "learning_rate": 6.156854819534928e-06, "loss": 0.6519, "step": 51790 }, { "epoch": 0.3079099571422627, "grad_norm": 8.424144744873047, "learning_rate": 6.158043654001617e-06, "loss": 0.6984, "step": 51800 }, { "epoch": 0.30796939921893113, "grad_norm": 8.287912368774414, "learning_rate": 6.159232488468306e-06, "loss": 0.6935, "step": 51810 }, { "epoch": 0.3080288412955995, "grad_norm": 9.101788520812988, "learning_rate": 6.160421322934995e-06, "loss": 0.6648, "step": 51820 }, { "epoch": 0.3080882833722679, "grad_norm": 8.904223442077637, "learning_rate": 6.161610157401684e-06, "loss": 0.663, "step": 51830 }, { "epoch": 0.30814772544893626, "grad_norm": 8.050383567810059, "learning_rate": 6.162798991868373e-06, "loss": 0.6816, "step": 51840 }, { "epoch": 0.3082071675256047, "grad_norm": 7.202667236328125, "learning_rate": 6.163987826335062e-06, "loss": 0.6362, "step": 51850 }, { "epoch": 0.3082666096022731, "grad_norm": 8.204745292663574, "learning_rate": 6.165176660801751e-06, "loss": 0.6588, "step": 51860 }, { "epoch": 0.30832605167894145, "grad_norm": 8.268098831176758, "learning_rate": 6.166365495268439e-06, "loss": 0.6394, "step": 51870 }, { "epoch": 0.30838549375560986, "grad_norm": 7.283076763153076, "learning_rate": 6.167554329735128e-06, "loss": 0.7226, "step": 51880 }, { "epoch": 0.3084449358322782, "grad_norm": 5.7672648429870605, "learning_rate": 6.168743164201817e-06, "loss": 0.6853, "step": 51890 }, { "epoch": 0.30850437790894664, "grad_norm": 10.039145469665527, "learning_rate": 6.169931998668506e-06, "loss": 0.6818, "step": 51900 }, { "epoch": 0.308563819985615, "grad_norm": 7.31116247177124, "learning_rate": 6.171120833135195e-06, "loss": 0.6729, "step": 51910 }, { "epoch": 0.3086232620622834, "grad_norm": 7.737430572509766, "learning_rate": 6.172309667601884e-06, "loss": 0.6801, "step": 51920 }, { "epoch": 0.3086827041389518, "grad_norm": 7.197188854217529, "learning_rate": 6.1734985020685725e-06, "loss": 0.6648, "step": 51930 }, { "epoch": 0.3087421462156202, "grad_norm": 6.1181488037109375, "learning_rate": 6.1746873365352615e-06, "loss": 0.628, "step": 51940 }, { "epoch": 0.3088015882922886, "grad_norm": 6.202844142913818, "learning_rate": 6.1758761710019495e-06, "loss": 0.6829, "step": 51950 }, { "epoch": 0.30886103036895696, "grad_norm": 7.779996395111084, "learning_rate": 6.1770650054686385e-06, "loss": 0.6268, "step": 51960 }, { "epoch": 0.30892047244562537, "grad_norm": 6.428825378417969, "learning_rate": 6.178253839935327e-06, "loss": 0.679, "step": 51970 }, { "epoch": 0.30897991452229373, "grad_norm": 6.967233180999756, "learning_rate": 6.179442674402016e-06, "loss": 0.7106, "step": 51980 }, { "epoch": 0.30903935659896214, "grad_norm": 7.665321350097656, "learning_rate": 6.180631508868705e-06, "loss": 0.7131, "step": 51990 }, { "epoch": 0.30909879867563056, "grad_norm": 7.954941749572754, "learning_rate": 6.181820343335394e-06, "loss": 0.6793, "step": 52000 }, { "epoch": 0.3091582407522989, "grad_norm": 7.004082202911377, "learning_rate": 6.183009177802083e-06, "loss": 0.6666, "step": 52010 }, { "epoch": 0.30921768282896733, "grad_norm": 11.26098918914795, "learning_rate": 6.184198012268772e-06, "loss": 0.6934, "step": 52020 }, { "epoch": 0.3092771249056357, "grad_norm": 7.812504291534424, "learning_rate": 6.18538684673546e-06, "loss": 0.644, "step": 52030 }, { "epoch": 0.3093365669823041, "grad_norm": 7.043853759765625, "learning_rate": 6.186575681202151e-06, "loss": 0.697, "step": 52040 }, { "epoch": 0.30939600905897247, "grad_norm": 8.889982223510742, "learning_rate": 6.18776451566884e-06, "loss": 0.7175, "step": 52050 }, { "epoch": 0.3094554511356409, "grad_norm": 7.380760192871094, "learning_rate": 6.188953350135528e-06, "loss": 0.6499, "step": 52060 }, { "epoch": 0.30951489321230924, "grad_norm": 8.57030963897705, "learning_rate": 6.190142184602217e-06, "loss": 0.6502, "step": 52070 }, { "epoch": 0.30957433528897765, "grad_norm": 6.091801643371582, "learning_rate": 6.191331019068906e-06, "loss": 0.6519, "step": 52080 }, { "epoch": 0.30963377736564607, "grad_norm": 7.387086391448975, "learning_rate": 6.1925198535355945e-06, "loss": 0.6363, "step": 52090 }, { "epoch": 0.3096932194423144, "grad_norm": 9.766122817993164, "learning_rate": 6.1937086880022834e-06, "loss": 0.6801, "step": 52100 }, { "epoch": 0.30975266151898284, "grad_norm": 8.465816497802734, "learning_rate": 6.194897522468972e-06, "loss": 0.6348, "step": 52110 }, { "epoch": 0.3098121035956512, "grad_norm": 9.823504447937012, "learning_rate": 6.196086356935661e-06, "loss": 0.6609, "step": 52120 }, { "epoch": 0.3098715456723196, "grad_norm": 6.9824676513671875, "learning_rate": 6.19727519140235e-06, "loss": 0.6561, "step": 52130 }, { "epoch": 0.309930987748988, "grad_norm": 9.253151893615723, "learning_rate": 6.198464025869038e-06, "loss": 0.6748, "step": 52140 }, { "epoch": 0.3099904298256564, "grad_norm": 8.173291206359863, "learning_rate": 6.199652860335727e-06, "loss": 0.6715, "step": 52150 }, { "epoch": 0.3100498719023248, "grad_norm": 7.965002059936523, "learning_rate": 6.200841694802416e-06, "loss": 0.6465, "step": 52160 }, { "epoch": 0.31010931397899316, "grad_norm": 8.142014503479004, "learning_rate": 6.202030529269105e-06, "loss": 0.6365, "step": 52170 }, { "epoch": 0.3101687560556616, "grad_norm": 7.332850456237793, "learning_rate": 6.203219363735794e-06, "loss": 0.6972, "step": 52180 }, { "epoch": 0.31022819813232994, "grad_norm": 6.167456150054932, "learning_rate": 6.204408198202483e-06, "loss": 0.698, "step": 52190 }, { "epoch": 0.31028764020899835, "grad_norm": 8.67798137664795, "learning_rate": 6.205597032669172e-06, "loss": 0.6896, "step": 52200 }, { "epoch": 0.3103470822856667, "grad_norm": 7.124475002288818, "learning_rate": 6.206785867135861e-06, "loss": 0.6506, "step": 52210 }, { "epoch": 0.3104065243623351, "grad_norm": 9.042398452758789, "learning_rate": 6.20797470160255e-06, "loss": 0.6669, "step": 52220 }, { "epoch": 0.31046596643900354, "grad_norm": 10.221853256225586, "learning_rate": 6.209163536069238e-06, "loss": 0.7133, "step": 52230 }, { "epoch": 0.3105254085156719, "grad_norm": 7.041410446166992, "learning_rate": 6.210352370535927e-06, "loss": 0.7389, "step": 52240 }, { "epoch": 0.3105848505923403, "grad_norm": 8.387907028198242, "learning_rate": 6.211541205002616e-06, "loss": 0.705, "step": 52250 }, { "epoch": 0.31064429266900867, "grad_norm": 7.8416571617126465, "learning_rate": 6.212730039469305e-06, "loss": 0.6665, "step": 52260 }, { "epoch": 0.3107037347456771, "grad_norm": 6.189638137817383, "learning_rate": 6.2139188739359935e-06, "loss": 0.6635, "step": 52270 }, { "epoch": 0.31076317682234544, "grad_norm": 9.135403633117676, "learning_rate": 6.2151077084026824e-06, "loss": 0.691, "step": 52280 }, { "epoch": 0.31082261889901386, "grad_norm": 6.863343715667725, "learning_rate": 6.216296542869371e-06, "loss": 0.7061, "step": 52290 }, { "epoch": 0.3108820609756823, "grad_norm": 6.023168563842773, "learning_rate": 6.21748537733606e-06, "loss": 0.6491, "step": 52300 }, { "epoch": 0.31094150305235063, "grad_norm": 5.390264511108398, "learning_rate": 6.218674211802748e-06, "loss": 0.6792, "step": 52310 }, { "epoch": 0.31100094512901905, "grad_norm": 6.893768787384033, "learning_rate": 6.219863046269437e-06, "loss": 0.7682, "step": 52320 }, { "epoch": 0.3110603872056874, "grad_norm": 8.150076866149902, "learning_rate": 6.221051880736126e-06, "loss": 0.6556, "step": 52330 }, { "epoch": 0.3111198292823558, "grad_norm": 8.11268424987793, "learning_rate": 6.222240715202815e-06, "loss": 0.6823, "step": 52340 }, { "epoch": 0.3111792713590242, "grad_norm": 9.051348686218262, "learning_rate": 6.223429549669504e-06, "loss": 0.7153, "step": 52350 }, { "epoch": 0.3112387134356926, "grad_norm": 7.992583751678467, "learning_rate": 6.224618384136193e-06, "loss": 0.6614, "step": 52360 }, { "epoch": 0.31129815551236095, "grad_norm": 8.144694328308105, "learning_rate": 6.225807218602882e-06, "loss": 0.6745, "step": 52370 }, { "epoch": 0.31135759758902937, "grad_norm": 7.811404228210449, "learning_rate": 6.226996053069571e-06, "loss": 0.6322, "step": 52380 }, { "epoch": 0.3114170396656978, "grad_norm": 6.601069927215576, "learning_rate": 6.228184887536261e-06, "loss": 0.6927, "step": 52390 }, { "epoch": 0.31147648174236614, "grad_norm": 7.315621852874756, "learning_rate": 6.2293737220029496e-06, "loss": 0.6151, "step": 52400 }, { "epoch": 0.31153592381903455, "grad_norm": 7.232619762420654, "learning_rate": 6.2305625564696385e-06, "loss": 0.7, "step": 52410 }, { "epoch": 0.3115953658957029, "grad_norm": 6.455630779266357, "learning_rate": 6.231751390936327e-06, "loss": 0.6828, "step": 52420 }, { "epoch": 0.31165480797237133, "grad_norm": 9.474369049072266, "learning_rate": 6.2329402254030155e-06, "loss": 0.6866, "step": 52430 }, { "epoch": 0.3117142500490397, "grad_norm": 8.687631607055664, "learning_rate": 6.2341290598697044e-06, "loss": 0.7403, "step": 52440 }, { "epoch": 0.3117736921257081, "grad_norm": 6.469115257263184, "learning_rate": 6.235317894336393e-06, "loss": 0.674, "step": 52450 }, { "epoch": 0.3118331342023765, "grad_norm": 8.392568588256836, "learning_rate": 6.236506728803082e-06, "loss": 0.6952, "step": 52460 }, { "epoch": 0.3118925762790449, "grad_norm": 6.442373275756836, "learning_rate": 6.237695563269771e-06, "loss": 0.7323, "step": 52470 }, { "epoch": 0.3119520183557133, "grad_norm": 7.049505710601807, "learning_rate": 6.23888439773646e-06, "loss": 0.6789, "step": 52480 }, { "epoch": 0.31201146043238165, "grad_norm": 7.9529242515563965, "learning_rate": 6.240073232203149e-06, "loss": 0.6629, "step": 52490 }, { "epoch": 0.31207090250905006, "grad_norm": 8.938847541809082, "learning_rate": 6.241262066669838e-06, "loss": 0.6841, "step": 52500 }, { "epoch": 0.3121303445857184, "grad_norm": 7.2584228515625, "learning_rate": 6.242450901136526e-06, "loss": 0.6944, "step": 52510 }, { "epoch": 0.31218978666238684, "grad_norm": 7.830143451690674, "learning_rate": 6.243639735603215e-06, "loss": 0.6838, "step": 52520 }, { "epoch": 0.31224922873905525, "grad_norm": 7.303325176239014, "learning_rate": 6.244828570069904e-06, "loss": 0.6899, "step": 52530 }, { "epoch": 0.3123086708157236, "grad_norm": 6.606170177459717, "learning_rate": 6.246017404536593e-06, "loss": 0.6921, "step": 52540 }, { "epoch": 0.312368112892392, "grad_norm": 7.161068439483643, "learning_rate": 6.247206239003282e-06, "loss": 0.6668, "step": 52550 }, { "epoch": 0.3124275549690604, "grad_norm": 9.637336730957031, "learning_rate": 6.248395073469971e-06, "loss": 0.6833, "step": 52560 }, { "epoch": 0.3124869970457288, "grad_norm": 7.377725601196289, "learning_rate": 6.24958390793666e-06, "loss": 0.69, "step": 52570 }, { "epoch": 0.31254643912239716, "grad_norm": 7.303603649139404, "learning_rate": 6.2507727424033486e-06, "loss": 0.6196, "step": 52580 }, { "epoch": 0.31260588119906557, "grad_norm": 7.687225818634033, "learning_rate": 6.251961576870037e-06, "loss": 0.7107, "step": 52590 }, { "epoch": 0.312665323275734, "grad_norm": 8.611452102661133, "learning_rate": 6.2531504113367256e-06, "loss": 0.7182, "step": 52600 }, { "epoch": 0.31272476535240235, "grad_norm": 7.699504852294922, "learning_rate": 6.2543392458034145e-06, "loss": 0.726, "step": 52610 }, { "epoch": 0.31278420742907076, "grad_norm": 7.876297950744629, "learning_rate": 6.2555280802701034e-06, "loss": 0.7063, "step": 52620 }, { "epoch": 0.3128436495057391, "grad_norm": 7.813302040100098, "learning_rate": 6.256716914736792e-06, "loss": 0.6723, "step": 52630 }, { "epoch": 0.31290309158240753, "grad_norm": 8.014474868774414, "learning_rate": 6.257905749203481e-06, "loss": 0.6496, "step": 52640 }, { "epoch": 0.3129625336590759, "grad_norm": 8.343818664550781, "learning_rate": 6.25909458367017e-06, "loss": 0.6356, "step": 52650 }, { "epoch": 0.3130219757357443, "grad_norm": 7.2378692626953125, "learning_rate": 6.260283418136859e-06, "loss": 0.6889, "step": 52660 }, { "epoch": 0.3130814178124127, "grad_norm": 7.539041042327881, "learning_rate": 6.261472252603547e-06, "loss": 0.7453, "step": 52670 }, { "epoch": 0.3131408598890811, "grad_norm": 7.02149772644043, "learning_rate": 6.262661087070236e-06, "loss": 0.6843, "step": 52680 }, { "epoch": 0.3132003019657495, "grad_norm": 9.648740768432617, "learning_rate": 6.263849921536925e-06, "loss": 0.6188, "step": 52690 }, { "epoch": 0.31325974404241785, "grad_norm": 5.494281768798828, "learning_rate": 6.265038756003614e-06, "loss": 0.6614, "step": 52700 }, { "epoch": 0.31331918611908627, "grad_norm": 7.1728835105896, "learning_rate": 6.266227590470303e-06, "loss": 0.6524, "step": 52710 }, { "epoch": 0.3133786281957546, "grad_norm": 6.9201507568359375, "learning_rate": 6.267416424936992e-06, "loss": 0.6576, "step": 52720 }, { "epoch": 0.31343807027242304, "grad_norm": 7.0243425369262695, "learning_rate": 6.268605259403682e-06, "loss": 0.6738, "step": 52730 }, { "epoch": 0.3134975123490914, "grad_norm": 6.729084014892578, "learning_rate": 6.2697940938703706e-06, "loss": 0.6809, "step": 52740 }, { "epoch": 0.3135569544257598, "grad_norm": 6.398906230926514, "learning_rate": 6.2709829283370595e-06, "loss": 0.629, "step": 52750 }, { "epoch": 0.31361639650242823, "grad_norm": 7.335501670837402, "learning_rate": 6.272171762803748e-06, "loss": 0.6866, "step": 52760 }, { "epoch": 0.3136758385790966, "grad_norm": 9.250826835632324, "learning_rate": 6.273360597270437e-06, "loss": 0.7144, "step": 52770 }, { "epoch": 0.313735280655765, "grad_norm": 7.974028587341309, "learning_rate": 6.274549431737125e-06, "loss": 0.7086, "step": 52780 }, { "epoch": 0.31379472273243336, "grad_norm": 7.453603744506836, "learning_rate": 6.275738266203814e-06, "loss": 0.6195, "step": 52790 }, { "epoch": 0.3138541648091018, "grad_norm": 6.898205757141113, "learning_rate": 6.276927100670503e-06, "loss": 0.7074, "step": 52800 }, { "epoch": 0.31391360688577014, "grad_norm": 8.066850662231445, "learning_rate": 6.278115935137192e-06, "loss": 0.705, "step": 52810 }, { "epoch": 0.31397304896243855, "grad_norm": 6.96978759765625, "learning_rate": 6.279304769603881e-06, "loss": 0.7092, "step": 52820 }, { "epoch": 0.31403249103910696, "grad_norm": 7.2901387214660645, "learning_rate": 6.28049360407057e-06, "loss": 0.7032, "step": 52830 }, { "epoch": 0.3140919331157753, "grad_norm": 7.4889140129089355, "learning_rate": 6.281682438537259e-06, "loss": 0.6902, "step": 52840 }, { "epoch": 0.31415137519244374, "grad_norm": 9.108621597290039, "learning_rate": 6.282871273003948e-06, "loss": 0.6901, "step": 52850 }, { "epoch": 0.3142108172691121, "grad_norm": 6.3545074462890625, "learning_rate": 6.284060107470637e-06, "loss": 0.6837, "step": 52860 }, { "epoch": 0.3142702593457805, "grad_norm": 8.101494789123535, "learning_rate": 6.285248941937325e-06, "loss": 0.7126, "step": 52870 }, { "epoch": 0.31432970142244887, "grad_norm": 7.1173834800720215, "learning_rate": 6.286437776404014e-06, "loss": 0.6653, "step": 52880 }, { "epoch": 0.3143891434991173, "grad_norm": 9.055736541748047, "learning_rate": 6.287626610870703e-06, "loss": 0.6672, "step": 52890 }, { "epoch": 0.3144485855757857, "grad_norm": 10.231358528137207, "learning_rate": 6.288815445337392e-06, "loss": 0.6271, "step": 52900 }, { "epoch": 0.31450802765245406, "grad_norm": 8.128252029418945, "learning_rate": 6.290004279804081e-06, "loss": 0.6986, "step": 52910 }, { "epoch": 0.3145674697291225, "grad_norm": 8.00672721862793, "learning_rate": 6.2911931142707696e-06, "loss": 0.7172, "step": 52920 }, { "epoch": 0.31462691180579083, "grad_norm": 9.7763032913208, "learning_rate": 6.2923819487374585e-06, "loss": 0.6363, "step": 52930 }, { "epoch": 0.31468635388245925, "grad_norm": 8.8057861328125, "learning_rate": 6.293570783204147e-06, "loss": 0.7338, "step": 52940 }, { "epoch": 0.3147457959591276, "grad_norm": 7.080525875091553, "learning_rate": 6.2947596176708355e-06, "loss": 0.6787, "step": 52950 }, { "epoch": 0.314805238035796, "grad_norm": 8.431994438171387, "learning_rate": 6.295948452137524e-06, "loss": 0.673, "step": 52960 }, { "epoch": 0.31486468011246443, "grad_norm": 8.061548233032227, "learning_rate": 6.297137286604213e-06, "loss": 0.6725, "step": 52970 }, { "epoch": 0.3149241221891328, "grad_norm": 13.235400199890137, "learning_rate": 6.298326121070902e-06, "loss": 0.7279, "step": 52980 }, { "epoch": 0.3149835642658012, "grad_norm": 7.211691379547119, "learning_rate": 6.299514955537591e-06, "loss": 0.6061, "step": 52990 }, { "epoch": 0.31504300634246957, "grad_norm": 7.063532829284668, "learning_rate": 6.30070379000428e-06, "loss": 0.6826, "step": 53000 }, { "epoch": 0.315102448419138, "grad_norm": 6.970690727233887, "learning_rate": 6.301892624470969e-06, "loss": 0.6096, "step": 53010 }, { "epoch": 0.31516189049580634, "grad_norm": 7.280211925506592, "learning_rate": 6.303081458937658e-06, "loss": 0.7009, "step": 53020 }, { "epoch": 0.31522133257247476, "grad_norm": 7.087799549102783, "learning_rate": 6.304270293404347e-06, "loss": 0.6268, "step": 53030 }, { "epoch": 0.31528077464914317, "grad_norm": 6.184063911437988, "learning_rate": 6.305459127871035e-06, "loss": 0.5768, "step": 53040 }, { "epoch": 0.31534021672581153, "grad_norm": 7.307915210723877, "learning_rate": 6.306647962337724e-06, "loss": 0.6805, "step": 53050 }, { "epoch": 0.31539965880247994, "grad_norm": 8.118223190307617, "learning_rate": 6.307836796804413e-06, "loss": 0.7033, "step": 53060 }, { "epoch": 0.3154591008791483, "grad_norm": 6.870108604431152, "learning_rate": 6.309025631271102e-06, "loss": 0.665, "step": 53070 }, { "epoch": 0.3155185429558167, "grad_norm": 8.087347030639648, "learning_rate": 6.3102144657377915e-06, "loss": 0.6814, "step": 53080 }, { "epoch": 0.3155779850324851, "grad_norm": 7.84372615814209, "learning_rate": 6.3114033002044805e-06, "loss": 0.6632, "step": 53090 }, { "epoch": 0.3156374271091535, "grad_norm": 6.065549850463867, "learning_rate": 6.312592134671169e-06, "loss": 0.749, "step": 53100 }, { "epoch": 0.31569686918582185, "grad_norm": 5.99751615524292, "learning_rate": 6.313780969137858e-06, "loss": 0.6883, "step": 53110 }, { "epoch": 0.31575631126249026, "grad_norm": 8.257710456848145, "learning_rate": 6.314969803604547e-06, "loss": 0.6652, "step": 53120 }, { "epoch": 0.3158157533391587, "grad_norm": 9.546651840209961, "learning_rate": 6.316158638071236e-06, "loss": 0.6723, "step": 53130 }, { "epoch": 0.31587519541582704, "grad_norm": 6.622112274169922, "learning_rate": 6.317347472537925e-06, "loss": 0.7465, "step": 53140 }, { "epoch": 0.31593463749249545, "grad_norm": 7.790011405944824, "learning_rate": 6.318536307004613e-06, "loss": 0.6764, "step": 53150 }, { "epoch": 0.3159940795691638, "grad_norm": 9.040546417236328, "learning_rate": 6.319725141471302e-06, "loss": 0.7076, "step": 53160 }, { "epoch": 0.3160535216458322, "grad_norm": 7.934168338775635, "learning_rate": 6.320913975937991e-06, "loss": 0.6832, "step": 53170 }, { "epoch": 0.3161129637225006, "grad_norm": 7.624398231506348, "learning_rate": 6.32210281040468e-06, "loss": 0.633, "step": 53180 }, { "epoch": 0.316172405799169, "grad_norm": 7.514731407165527, "learning_rate": 6.323291644871369e-06, "loss": 0.6721, "step": 53190 }, { "epoch": 0.3162318478758374, "grad_norm": 5.966456413269043, "learning_rate": 6.324480479338058e-06, "loss": 0.6341, "step": 53200 }, { "epoch": 0.31629128995250577, "grad_norm": 6.9072065353393555, "learning_rate": 6.325669313804747e-06, "loss": 0.6742, "step": 53210 }, { "epoch": 0.3163507320291742, "grad_norm": 7.89675760269165, "learning_rate": 6.326858148271436e-06, "loss": 0.6839, "step": 53220 }, { "epoch": 0.31641017410584255, "grad_norm": 6.2434210777282715, "learning_rate": 6.328046982738124e-06, "loss": 0.667, "step": 53230 }, { "epoch": 0.31646961618251096, "grad_norm": 6.669775009155273, "learning_rate": 6.329235817204813e-06, "loss": 0.6611, "step": 53240 }, { "epoch": 0.3165290582591793, "grad_norm": 7.223986625671387, "learning_rate": 6.330424651671502e-06, "loss": 0.6967, "step": 53250 }, { "epoch": 0.31658850033584773, "grad_norm": 5.624832630157471, "learning_rate": 6.3316134861381905e-06, "loss": 0.6664, "step": 53260 }, { "epoch": 0.31664794241251615, "grad_norm": 6.301677703857422, "learning_rate": 6.3328023206048795e-06, "loss": 0.5953, "step": 53270 }, { "epoch": 0.3167073844891845, "grad_norm": 8.858051300048828, "learning_rate": 6.333991155071568e-06, "loss": 0.6506, "step": 53280 }, { "epoch": 0.3167668265658529, "grad_norm": 8.010664939880371, "learning_rate": 6.335179989538257e-06, "loss": 0.6987, "step": 53290 }, { "epoch": 0.3168262686425213, "grad_norm": 6.380995273590088, "learning_rate": 6.336368824004946e-06, "loss": 0.7018, "step": 53300 }, { "epoch": 0.3168857107191897, "grad_norm": 7.346230983734131, "learning_rate": 6.337557658471634e-06, "loss": 0.6565, "step": 53310 }, { "epoch": 0.31694515279585805, "grad_norm": 7.4018378257751465, "learning_rate": 6.338746492938323e-06, "loss": 0.6672, "step": 53320 }, { "epoch": 0.31700459487252647, "grad_norm": 6.95688533782959, "learning_rate": 6.339935327405012e-06, "loss": 0.6266, "step": 53330 }, { "epoch": 0.3170640369491949, "grad_norm": 8.12265396118164, "learning_rate": 6.341124161871701e-06, "loss": 0.6485, "step": 53340 }, { "epoch": 0.31712347902586324, "grad_norm": 8.004700660705566, "learning_rate": 6.34231299633839e-06, "loss": 0.704, "step": 53350 }, { "epoch": 0.31718292110253166, "grad_norm": 10.710126876831055, "learning_rate": 6.343501830805079e-06, "loss": 0.6726, "step": 53360 }, { "epoch": 0.3172423631792, "grad_norm": 8.149117469787598, "learning_rate": 6.344690665271768e-06, "loss": 0.6802, "step": 53370 }, { "epoch": 0.31730180525586843, "grad_norm": 6.804908275604248, "learning_rate": 6.345879499738457e-06, "loss": 0.6909, "step": 53380 }, { "epoch": 0.3173612473325368, "grad_norm": 8.538148880004883, "learning_rate": 6.347068334205146e-06, "loss": 0.6478, "step": 53390 }, { "epoch": 0.3174206894092052, "grad_norm": 7.583121299743652, "learning_rate": 6.348257168671834e-06, "loss": 0.7224, "step": 53400 }, { "epoch": 0.3174801314858736, "grad_norm": 6.747447490692139, "learning_rate": 6.349446003138523e-06, "loss": 0.6525, "step": 53410 }, { "epoch": 0.317539573562542, "grad_norm": 7.376529693603516, "learning_rate": 6.350634837605212e-06, "loss": 0.6815, "step": 53420 }, { "epoch": 0.3175990156392104, "grad_norm": 7.632517337799072, "learning_rate": 6.3518236720719015e-06, "loss": 0.6285, "step": 53430 }, { "epoch": 0.31765845771587875, "grad_norm": 7.642909049987793, "learning_rate": 6.35301250653859e-06, "loss": 0.658, "step": 53440 }, { "epoch": 0.31771789979254716, "grad_norm": 7.93338680267334, "learning_rate": 6.354201341005279e-06, "loss": 0.6877, "step": 53450 }, { "epoch": 0.3177773418692155, "grad_norm": 6.6083855628967285, "learning_rate": 6.355390175471968e-06, "loss": 0.6336, "step": 53460 }, { "epoch": 0.31783678394588394, "grad_norm": 6.053183555603027, "learning_rate": 6.356579009938657e-06, "loss": 0.6302, "step": 53470 }, { "epoch": 0.3178962260225523, "grad_norm": 7.947774410247803, "learning_rate": 6.357767844405346e-06, "loss": 0.6864, "step": 53480 }, { "epoch": 0.3179556680992207, "grad_norm": 6.344386100769043, "learning_rate": 6.358956678872035e-06, "loss": 0.6886, "step": 53490 }, { "epoch": 0.3180151101758891, "grad_norm": 7.662534713745117, "learning_rate": 6.360145513338724e-06, "loss": 0.7172, "step": 53500 }, { "epoch": 0.3180745522525575, "grad_norm": 7.110438346862793, "learning_rate": 6.361334347805412e-06, "loss": 0.6306, "step": 53510 }, { "epoch": 0.3181339943292259, "grad_norm": 18.90071678161621, "learning_rate": 6.362523182272101e-06, "loss": 0.6422, "step": 53520 }, { "epoch": 0.31819343640589426, "grad_norm": 7.927436351776123, "learning_rate": 6.36371201673879e-06, "loss": 0.6169, "step": 53530 }, { "epoch": 0.3182528784825627, "grad_norm": 8.187310218811035, "learning_rate": 6.364900851205479e-06, "loss": 0.6487, "step": 53540 }, { "epoch": 0.31831232055923103, "grad_norm": 7.11865758895874, "learning_rate": 6.366089685672168e-06, "loss": 0.6494, "step": 53550 }, { "epoch": 0.31837176263589945, "grad_norm": 8.14930534362793, "learning_rate": 6.367278520138857e-06, "loss": 0.626, "step": 53560 }, { "epoch": 0.31843120471256786, "grad_norm": 6.670527458190918, "learning_rate": 6.368467354605546e-06, "loss": 0.6758, "step": 53570 }, { "epoch": 0.3184906467892362, "grad_norm": 7.419982433319092, "learning_rate": 6.3696561890722345e-06, "loss": 0.6768, "step": 53580 }, { "epoch": 0.31855008886590463, "grad_norm": 8.575239181518555, "learning_rate": 6.370845023538923e-06, "loss": 0.6548, "step": 53590 }, { "epoch": 0.318609530942573, "grad_norm": 9.899005889892578, "learning_rate": 6.3720338580056115e-06, "loss": 0.6203, "step": 53600 }, { "epoch": 0.3186689730192414, "grad_norm": 6.573014259338379, "learning_rate": 6.3732226924723005e-06, "loss": 0.7211, "step": 53610 }, { "epoch": 0.31872841509590977, "grad_norm": 8.241350173950195, "learning_rate": 6.374411526938989e-06, "loss": 0.6255, "step": 53620 }, { "epoch": 0.3187878571725782, "grad_norm": 9.899347305297852, "learning_rate": 6.375600361405678e-06, "loss": 0.6804, "step": 53630 }, { "epoch": 0.3188472992492466, "grad_norm": 6.303333759307861, "learning_rate": 6.376789195872367e-06, "loss": 0.6506, "step": 53640 }, { "epoch": 0.31890674132591496, "grad_norm": 8.151313781738281, "learning_rate": 6.377978030339056e-06, "loss": 0.6675, "step": 53650 }, { "epoch": 0.31896618340258337, "grad_norm": 6.266362190246582, "learning_rate": 6.379166864805745e-06, "loss": 0.6507, "step": 53660 }, { "epoch": 0.31902562547925173, "grad_norm": 7.195468425750732, "learning_rate": 6.380355699272433e-06, "loss": 0.7448, "step": 53670 }, { "epoch": 0.31908506755592014, "grad_norm": 5.809182643890381, "learning_rate": 6.381544533739122e-06, "loss": 0.6558, "step": 53680 }, { "epoch": 0.3191445096325885, "grad_norm": 6.849842071533203, "learning_rate": 6.382733368205811e-06, "loss": 0.6834, "step": 53690 }, { "epoch": 0.3192039517092569, "grad_norm": 6.046648025512695, "learning_rate": 6.3839222026725e-06, "loss": 0.6941, "step": 53700 }, { "epoch": 0.31926339378592533, "grad_norm": 7.151211738586426, "learning_rate": 6.385111037139189e-06, "loss": 0.6532, "step": 53710 }, { "epoch": 0.3193228358625937, "grad_norm": 7.057249546051025, "learning_rate": 6.386299871605878e-06, "loss": 0.6746, "step": 53720 }, { "epoch": 0.3193822779392621, "grad_norm": 6.542566299438477, "learning_rate": 6.387488706072567e-06, "loss": 0.6255, "step": 53730 }, { "epoch": 0.31944172001593046, "grad_norm": 8.456645011901855, "learning_rate": 6.388677540539256e-06, "loss": 0.6556, "step": 53740 }, { "epoch": 0.3195011620925989, "grad_norm": 5.734355926513672, "learning_rate": 6.389866375005945e-06, "loss": 0.6691, "step": 53750 }, { "epoch": 0.31956060416926724, "grad_norm": 7.080077648162842, "learning_rate": 6.391055209472633e-06, "loss": 0.6749, "step": 53760 }, { "epoch": 0.31962004624593565, "grad_norm": 9.673330307006836, "learning_rate": 6.392244043939323e-06, "loss": 0.6862, "step": 53770 }, { "epoch": 0.31967948832260407, "grad_norm": 6.470915794372559, "learning_rate": 6.393432878406011e-06, "loss": 0.6495, "step": 53780 }, { "epoch": 0.3197389303992724, "grad_norm": 6.980404853820801, "learning_rate": 6.3946217128727e-06, "loss": 0.6679, "step": 53790 }, { "epoch": 0.31979837247594084, "grad_norm": 8.223881721496582, "learning_rate": 6.395810547339389e-06, "loss": 0.6786, "step": 53800 }, { "epoch": 0.3198578145526092, "grad_norm": 6.1134467124938965, "learning_rate": 6.396999381806078e-06, "loss": 0.6664, "step": 53810 }, { "epoch": 0.3199172566292776, "grad_norm": 8.549805641174316, "learning_rate": 6.398188216272767e-06, "loss": 0.6974, "step": 53820 }, { "epoch": 0.31997669870594597, "grad_norm": 6.893213748931885, "learning_rate": 6.399377050739456e-06, "loss": 0.7025, "step": 53830 }, { "epoch": 0.3200361407826144, "grad_norm": 9.367573738098145, "learning_rate": 6.400565885206145e-06, "loss": 0.7109, "step": 53840 }, { "epoch": 0.32009558285928275, "grad_norm": 7.349329471588135, "learning_rate": 6.401754719672834e-06, "loss": 0.732, "step": 53850 }, { "epoch": 0.32015502493595116, "grad_norm": 7.155288219451904, "learning_rate": 6.402943554139523e-06, "loss": 0.6893, "step": 53860 }, { "epoch": 0.3202144670126196, "grad_norm": 7.0131611824035645, "learning_rate": 6.404132388606211e-06, "loss": 0.6499, "step": 53870 }, { "epoch": 0.32027390908928793, "grad_norm": 7.345284461975098, "learning_rate": 6.4053212230729e-06, "loss": 0.6685, "step": 53880 }, { "epoch": 0.32033335116595635, "grad_norm": 7.598894119262695, "learning_rate": 6.406510057539589e-06, "loss": 0.7438, "step": 53890 }, { "epoch": 0.3203927932426247, "grad_norm": 6.9004716873168945, "learning_rate": 6.407698892006278e-06, "loss": 0.7097, "step": 53900 }, { "epoch": 0.3204522353192931, "grad_norm": 7.316343784332275, "learning_rate": 6.408887726472967e-06, "loss": 0.717, "step": 53910 }, { "epoch": 0.3205116773959615, "grad_norm": 6.669167518615723, "learning_rate": 6.4100765609396555e-06, "loss": 0.7033, "step": 53920 }, { "epoch": 0.3205711194726299, "grad_norm": 5.602115154266357, "learning_rate": 6.4112653954063444e-06, "loss": 0.6347, "step": 53930 }, { "epoch": 0.3206305615492983, "grad_norm": 7.277981758117676, "learning_rate": 6.412454229873033e-06, "loss": 0.6537, "step": 53940 }, { "epoch": 0.32069000362596667, "grad_norm": 6.554614067077637, "learning_rate": 6.4136430643397214e-06, "loss": 0.7346, "step": 53950 }, { "epoch": 0.3207494457026351, "grad_norm": 9.119048118591309, "learning_rate": 6.41483189880641e-06, "loss": 0.7124, "step": 53960 }, { "epoch": 0.32080888777930344, "grad_norm": 6.336175918579102, "learning_rate": 6.416020733273099e-06, "loss": 0.6421, "step": 53970 }, { "epoch": 0.32086832985597186, "grad_norm": 5.74924373626709, "learning_rate": 6.417209567739788e-06, "loss": 0.6264, "step": 53980 }, { "epoch": 0.3209277719326402, "grad_norm": 7.673155307769775, "learning_rate": 6.418398402206477e-06, "loss": 0.7179, "step": 53990 }, { "epoch": 0.32098721400930863, "grad_norm": 7.183198928833008, "learning_rate": 6.419587236673166e-06, "loss": 0.6842, "step": 54000 }, { "epoch": 0.32104665608597704, "grad_norm": 7.990849494934082, "learning_rate": 6.420776071139855e-06, "loss": 0.6718, "step": 54010 }, { "epoch": 0.3211060981626454, "grad_norm": 6.402245998382568, "learning_rate": 6.421964905606544e-06, "loss": 0.6799, "step": 54020 }, { "epoch": 0.3211655402393138, "grad_norm": 9.416587829589844, "learning_rate": 6.423153740073233e-06, "loss": 0.7763, "step": 54030 }, { "epoch": 0.3212249823159822, "grad_norm": 8.237781524658203, "learning_rate": 6.424342574539921e-06, "loss": 0.6452, "step": 54040 }, { "epoch": 0.3212844243926506, "grad_norm": 7.948083400726318, "learning_rate": 6.42553140900661e-06, "loss": 0.6869, "step": 54050 }, { "epoch": 0.32134386646931895, "grad_norm": 7.504975318908691, "learning_rate": 6.426720243473299e-06, "loss": 0.6823, "step": 54060 }, { "epoch": 0.32140330854598737, "grad_norm": 10.01414966583252, "learning_rate": 6.427909077939988e-06, "loss": 0.6972, "step": 54070 }, { "epoch": 0.3214627506226558, "grad_norm": 8.487509727478027, "learning_rate": 6.429097912406677e-06, "loss": 0.669, "step": 54080 }, { "epoch": 0.32152219269932414, "grad_norm": 7.683483123779297, "learning_rate": 6.430286746873366e-06, "loss": 0.6446, "step": 54090 }, { "epoch": 0.32158163477599255, "grad_norm": 6.613327503204346, "learning_rate": 6.4314755813400545e-06, "loss": 0.6685, "step": 54100 }, { "epoch": 0.3216410768526609, "grad_norm": 7.878462791442871, "learning_rate": 6.4326644158067434e-06, "loss": 0.6481, "step": 54110 }, { "epoch": 0.3217005189293293, "grad_norm": 7.1674275398254395, "learning_rate": 6.433853250273433e-06, "loss": 0.6479, "step": 54120 }, { "epoch": 0.3217599610059977, "grad_norm": 8.937071800231934, "learning_rate": 6.435042084740122e-06, "loss": 0.6903, "step": 54130 }, { "epoch": 0.3218194030826661, "grad_norm": 9.797513008117676, "learning_rate": 6.436230919206811e-06, "loss": 0.6867, "step": 54140 }, { "epoch": 0.32187884515933446, "grad_norm": 8.402485847473145, "learning_rate": 6.437419753673499e-06, "loss": 0.6967, "step": 54150 }, { "epoch": 0.3219382872360029, "grad_norm": 8.420064926147461, "learning_rate": 6.438608588140188e-06, "loss": 0.6097, "step": 54160 }, { "epoch": 0.3219977293126713, "grad_norm": 7.229795455932617, "learning_rate": 6.439797422606877e-06, "loss": 0.7075, "step": 54170 }, { "epoch": 0.32205717138933965, "grad_norm": 7.329394340515137, "learning_rate": 6.440986257073566e-06, "loss": 0.7152, "step": 54180 }, { "epoch": 0.32211661346600806, "grad_norm": 9.208099365234375, "learning_rate": 6.442175091540255e-06, "loss": 0.7229, "step": 54190 }, { "epoch": 0.3221760555426764, "grad_norm": 6.203446388244629, "learning_rate": 6.443363926006944e-06, "loss": 0.6924, "step": 54200 }, { "epoch": 0.32223549761934484, "grad_norm": 7.426292896270752, "learning_rate": 6.444552760473633e-06, "loss": 0.6692, "step": 54210 }, { "epoch": 0.3222949396960132, "grad_norm": 7.033263206481934, "learning_rate": 6.445741594940322e-06, "loss": 0.6909, "step": 54220 }, { "epoch": 0.3223543817726816, "grad_norm": 8.301148414611816, "learning_rate": 6.44693042940701e-06, "loss": 0.7018, "step": 54230 }, { "epoch": 0.32241382384935, "grad_norm": 7.61688756942749, "learning_rate": 6.448119263873699e-06, "loss": 0.6045, "step": 54240 }, { "epoch": 0.3224732659260184, "grad_norm": 8.08407974243164, "learning_rate": 6.4493080983403876e-06, "loss": 0.6413, "step": 54250 }, { "epoch": 0.3225327080026868, "grad_norm": 7.0288405418396, "learning_rate": 6.4504969328070765e-06, "loss": 0.6809, "step": 54260 }, { "epoch": 0.32259215007935516, "grad_norm": 5.932160377502441, "learning_rate": 6.451685767273765e-06, "loss": 0.6575, "step": 54270 }, { "epoch": 0.32265159215602357, "grad_norm": 8.629257202148438, "learning_rate": 6.452874601740454e-06, "loss": 0.7034, "step": 54280 }, { "epoch": 0.32271103423269193, "grad_norm": 12.32968521118164, "learning_rate": 6.454063436207143e-06, "loss": 0.6465, "step": 54290 }, { "epoch": 0.32277047630936034, "grad_norm": 7.258068084716797, "learning_rate": 6.455252270673832e-06, "loss": 0.6829, "step": 54300 }, { "epoch": 0.32282991838602876, "grad_norm": 9.921926498413086, "learning_rate": 6.45644110514052e-06, "loss": 0.6988, "step": 54310 }, { "epoch": 0.3228893604626971, "grad_norm": 8.95742416381836, "learning_rate": 6.457629939607209e-06, "loss": 0.7378, "step": 54320 }, { "epoch": 0.32294880253936553, "grad_norm": 6.116515636444092, "learning_rate": 6.458818774073898e-06, "loss": 0.6291, "step": 54330 }, { "epoch": 0.3230082446160339, "grad_norm": 9.023958206176758, "learning_rate": 6.460007608540587e-06, "loss": 0.6763, "step": 54340 }, { "epoch": 0.3230676866927023, "grad_norm": 7.108117580413818, "learning_rate": 6.461196443007276e-06, "loss": 0.6358, "step": 54350 }, { "epoch": 0.32312712876937066, "grad_norm": 9.064827919006348, "learning_rate": 6.462385277473965e-06, "loss": 0.715, "step": 54360 }, { "epoch": 0.3231865708460391, "grad_norm": 7.648988723754883, "learning_rate": 6.463574111940654e-06, "loss": 0.5964, "step": 54370 }, { "epoch": 0.3232460129227075, "grad_norm": 7.115005016326904, "learning_rate": 6.464762946407343e-06, "loss": 0.6736, "step": 54380 }, { "epoch": 0.32330545499937585, "grad_norm": 5.7585768699646, "learning_rate": 6.465951780874032e-06, "loss": 0.7001, "step": 54390 }, { "epoch": 0.32336489707604427, "grad_norm": 7.990955352783203, "learning_rate": 6.46714061534072e-06, "loss": 0.632, "step": 54400 }, { "epoch": 0.3234243391527126, "grad_norm": 7.429307460784912, "learning_rate": 6.468329449807409e-06, "loss": 0.6915, "step": 54410 }, { "epoch": 0.32348378122938104, "grad_norm": 9.951362609863281, "learning_rate": 6.469518284274098e-06, "loss": 0.6917, "step": 54420 }, { "epoch": 0.3235432233060494, "grad_norm": 8.478729248046875, "learning_rate": 6.4707071187407866e-06, "loss": 0.6755, "step": 54430 }, { "epoch": 0.3236026653827178, "grad_norm": 5.451696395874023, "learning_rate": 6.4718959532074755e-06, "loss": 0.6537, "step": 54440 }, { "epoch": 0.32366210745938623, "grad_norm": 7.617074012756348, "learning_rate": 6.473084787674164e-06, "loss": 0.7136, "step": 54450 }, { "epoch": 0.3237215495360546, "grad_norm": 5.507357597351074, "learning_rate": 6.474273622140853e-06, "loss": 0.7019, "step": 54460 }, { "epoch": 0.323780991612723, "grad_norm": 10.065805435180664, "learning_rate": 6.475462456607543e-06, "loss": 0.6565, "step": 54470 }, { "epoch": 0.32384043368939136, "grad_norm": 8.356416702270508, "learning_rate": 6.476651291074232e-06, "loss": 0.6576, "step": 54480 }, { "epoch": 0.3238998757660598, "grad_norm": 6.9307780265808105, "learning_rate": 6.477840125540921e-06, "loss": 0.6197, "step": 54490 }, { "epoch": 0.32395931784272813, "grad_norm": 7.322155475616455, "learning_rate": 6.47902896000761e-06, "loss": 0.7449, "step": 54500 }, { "epoch": 0.32401875991939655, "grad_norm": 8.2047700881958, "learning_rate": 6.480217794474298e-06, "loss": 0.7104, "step": 54510 }, { "epoch": 0.3240782019960649, "grad_norm": 7.574635028839111, "learning_rate": 6.481406628940987e-06, "loss": 0.7137, "step": 54520 }, { "epoch": 0.3241376440727333, "grad_norm": 7.8834967613220215, "learning_rate": 6.482595463407676e-06, "loss": 0.6971, "step": 54530 }, { "epoch": 0.32419708614940174, "grad_norm": 7.970318794250488, "learning_rate": 6.483784297874365e-06, "loss": 0.6889, "step": 54540 }, { "epoch": 0.3242565282260701, "grad_norm": 7.605724811553955, "learning_rate": 6.484973132341054e-06, "loss": 0.6695, "step": 54550 }, { "epoch": 0.3243159703027385, "grad_norm": 7.722544193267822, "learning_rate": 6.486161966807743e-06, "loss": 0.6725, "step": 54560 }, { "epoch": 0.32437541237940687, "grad_norm": 5.8573527336120605, "learning_rate": 6.4873508012744315e-06, "loss": 0.6239, "step": 54570 }, { "epoch": 0.3244348544560753, "grad_norm": 8.111255645751953, "learning_rate": 6.4885396357411205e-06, "loss": 0.7286, "step": 54580 }, { "epoch": 0.32449429653274364, "grad_norm": 8.083390235900879, "learning_rate": 6.4897284702078086e-06, "loss": 0.6612, "step": 54590 }, { "epoch": 0.32455373860941206, "grad_norm": 6.870424747467041, "learning_rate": 6.4909173046744975e-06, "loss": 0.7121, "step": 54600 }, { "epoch": 0.32461318068608047, "grad_norm": 8.217817306518555, "learning_rate": 6.492106139141186e-06, "loss": 0.6665, "step": 54610 }, { "epoch": 0.32467262276274883, "grad_norm": 7.353602409362793, "learning_rate": 6.493294973607875e-06, "loss": 0.6704, "step": 54620 }, { "epoch": 0.32473206483941724, "grad_norm": 7.3919677734375, "learning_rate": 6.494483808074564e-06, "loss": 0.7576, "step": 54630 }, { "epoch": 0.3247915069160856, "grad_norm": 6.641342639923096, "learning_rate": 6.495672642541253e-06, "loss": 0.6929, "step": 54640 }, { "epoch": 0.324850948992754, "grad_norm": 7.7111382484436035, "learning_rate": 6.496861477007942e-06, "loss": 0.7248, "step": 54650 }, { "epoch": 0.3249103910694224, "grad_norm": 7.493943691253662, "learning_rate": 6.498050311474631e-06, "loss": 0.6779, "step": 54660 }, { "epoch": 0.3249698331460908, "grad_norm": 7.4690470695495605, "learning_rate": 6.499239145941319e-06, "loss": 0.6753, "step": 54670 }, { "epoch": 0.3250292752227592, "grad_norm": 9.334907531738281, "learning_rate": 6.500427980408008e-06, "loss": 0.7053, "step": 54680 }, { "epoch": 0.32508871729942757, "grad_norm": 7.3653564453125, "learning_rate": 6.501616814874697e-06, "loss": 0.6843, "step": 54690 }, { "epoch": 0.325148159376096, "grad_norm": 9.429868698120117, "learning_rate": 6.502805649341386e-06, "loss": 0.7486, "step": 54700 }, { "epoch": 0.32520760145276434, "grad_norm": 6.416204452514648, "learning_rate": 6.503994483808075e-06, "loss": 0.7083, "step": 54710 }, { "epoch": 0.32526704352943275, "grad_norm": 8.039185523986816, "learning_rate": 6.505183318274764e-06, "loss": 0.6426, "step": 54720 }, { "epoch": 0.3253264856061011, "grad_norm": 7.822439193725586, "learning_rate": 6.506372152741453e-06, "loss": 0.6921, "step": 54730 }, { "epoch": 0.3253859276827695, "grad_norm": 8.128791809082031, "learning_rate": 6.507560987208142e-06, "loss": 0.6975, "step": 54740 }, { "epoch": 0.32544536975943794, "grad_norm": 6.405643939971924, "learning_rate": 6.5087498216748305e-06, "loss": 0.6125, "step": 54750 }, { "epoch": 0.3255048118361063, "grad_norm": 8.243352890014648, "learning_rate": 6.509938656141519e-06, "loss": 0.6429, "step": 54760 }, { "epoch": 0.3255642539127747, "grad_norm": 7.214993476867676, "learning_rate": 6.5111274906082076e-06, "loss": 0.6405, "step": 54770 }, { "epoch": 0.3256236959894431, "grad_norm": 8.216503143310547, "learning_rate": 6.5123163250748965e-06, "loss": 0.6814, "step": 54780 }, { "epoch": 0.3256831380661115, "grad_norm": 8.963249206542969, "learning_rate": 6.513505159541585e-06, "loss": 0.6577, "step": 54790 }, { "epoch": 0.32574258014277985, "grad_norm": 9.625618934631348, "learning_rate": 6.514693994008274e-06, "loss": 0.7042, "step": 54800 }, { "epoch": 0.32580202221944826, "grad_norm": 6.720005035400391, "learning_rate": 6.515882828474964e-06, "loss": 0.6323, "step": 54810 }, { "epoch": 0.3258614642961167, "grad_norm": 7.662306308746338, "learning_rate": 6.517071662941653e-06, "loss": 0.707, "step": 54820 }, { "epoch": 0.32592090637278504, "grad_norm": 7.404867649078369, "learning_rate": 6.518260497408342e-06, "loss": 0.675, "step": 54830 }, { "epoch": 0.32598034844945345, "grad_norm": 8.0424165725708, "learning_rate": 6.519449331875031e-06, "loss": 0.7236, "step": 54840 }, { "epoch": 0.3260397905261218, "grad_norm": 6.552777290344238, "learning_rate": 6.52063816634172e-06, "loss": 0.7577, "step": 54850 }, { "epoch": 0.3260992326027902, "grad_norm": 6.672557353973389, "learning_rate": 6.521827000808409e-06, "loss": 0.6637, "step": 54860 }, { "epoch": 0.3261586746794586, "grad_norm": 6.108875274658203, "learning_rate": 6.523015835275097e-06, "loss": 0.6132, "step": 54870 }, { "epoch": 0.326218116756127, "grad_norm": 8.039822578430176, "learning_rate": 6.524204669741786e-06, "loss": 0.6917, "step": 54880 }, { "epoch": 0.32627755883279536, "grad_norm": 6.112070560455322, "learning_rate": 6.525393504208475e-06, "loss": 0.6958, "step": 54890 }, { "epoch": 0.32633700090946377, "grad_norm": 6.125458240509033, "learning_rate": 6.526582338675164e-06, "loss": 0.6405, "step": 54900 }, { "epoch": 0.3263964429861322, "grad_norm": 6.579002857208252, "learning_rate": 6.5277711731418525e-06, "loss": 0.6583, "step": 54910 }, { "epoch": 0.32645588506280054, "grad_norm": 7.365475177764893, "learning_rate": 6.5289600076085415e-06, "loss": 0.6151, "step": 54920 }, { "epoch": 0.32651532713946896, "grad_norm": 6.719675540924072, "learning_rate": 6.53014884207523e-06, "loss": 0.6878, "step": 54930 }, { "epoch": 0.3265747692161373, "grad_norm": 7.085590839385986, "learning_rate": 6.531337676541919e-06, "loss": 0.6289, "step": 54940 }, { "epoch": 0.32663421129280573, "grad_norm": 5.63346529006958, "learning_rate": 6.532526511008607e-06, "loss": 0.6035, "step": 54950 }, { "epoch": 0.3266936533694741, "grad_norm": 7.362595081329346, "learning_rate": 6.533715345475296e-06, "loss": 0.7087, "step": 54960 }, { "epoch": 0.3267530954461425, "grad_norm": 7.696303367614746, "learning_rate": 6.534904179941985e-06, "loss": 0.6578, "step": 54970 }, { "epoch": 0.3268125375228109, "grad_norm": 9.892166137695312, "learning_rate": 6.536093014408674e-06, "loss": 0.714, "step": 54980 }, { "epoch": 0.3268719795994793, "grad_norm": 6.880801677703857, "learning_rate": 6.537281848875363e-06, "loss": 0.6766, "step": 54990 }, { "epoch": 0.3269314216761477, "grad_norm": 7.716665744781494, "learning_rate": 6.538470683342052e-06, "loss": 0.6847, "step": 55000 }, { "epoch": 0.32699086375281605, "grad_norm": 7.931092262268066, "learning_rate": 6.539659517808741e-06, "loss": 0.6924, "step": 55010 }, { "epoch": 0.32705030582948447, "grad_norm": 7.375547409057617, "learning_rate": 6.54084835227543e-06, "loss": 0.666, "step": 55020 }, { "epoch": 0.3271097479061528, "grad_norm": 6.910726070404053, "learning_rate": 6.542037186742119e-06, "loss": 0.6793, "step": 55030 }, { "epoch": 0.32716918998282124, "grad_norm": 6.910910129547119, "learning_rate": 6.543226021208807e-06, "loss": 0.6381, "step": 55040 }, { "epoch": 0.32722863205948965, "grad_norm": 6.725684642791748, "learning_rate": 6.544414855675496e-06, "loss": 0.6854, "step": 55050 }, { "epoch": 0.327288074136158, "grad_norm": 5.68640661239624, "learning_rate": 6.545603690142185e-06, "loss": 0.6877, "step": 55060 }, { "epoch": 0.32734751621282643, "grad_norm": 5.644995212554932, "learning_rate": 6.546792524608874e-06, "loss": 0.647, "step": 55070 }, { "epoch": 0.3274069582894948, "grad_norm": 7.986626148223877, "learning_rate": 6.547981359075563e-06, "loss": 0.7394, "step": 55080 }, { "epoch": 0.3274664003661632, "grad_norm": 7.658464431762695, "learning_rate": 6.5491701935422515e-06, "loss": 0.7116, "step": 55090 }, { "epoch": 0.32752584244283156, "grad_norm": 5.951320171356201, "learning_rate": 6.5503590280089405e-06, "loss": 0.6685, "step": 55100 }, { "epoch": 0.3275852845195, "grad_norm": 7.640185356140137, "learning_rate": 6.551547862475629e-06, "loss": 0.6431, "step": 55110 }, { "epoch": 0.3276447265961684, "grad_norm": 8.51895809173584, "learning_rate": 6.5527366969423175e-06, "loss": 0.6776, "step": 55120 }, { "epoch": 0.32770416867283675, "grad_norm": 6.287353038787842, "learning_rate": 6.553925531409006e-06, "loss": 0.6561, "step": 55130 }, { "epoch": 0.32776361074950516, "grad_norm": 7.51896333694458, "learning_rate": 6.555114365875695e-06, "loss": 0.7007, "step": 55140 }, { "epoch": 0.3278230528261735, "grad_norm": 7.269864559173584, "learning_rate": 6.556303200342384e-06, "loss": 0.7075, "step": 55150 }, { "epoch": 0.32788249490284194, "grad_norm": 8.428244590759277, "learning_rate": 6.557492034809074e-06, "loss": 0.7111, "step": 55160 }, { "epoch": 0.3279419369795103, "grad_norm": 6.280513286590576, "learning_rate": 6.558680869275763e-06, "loss": 0.6818, "step": 55170 }, { "epoch": 0.3280013790561787, "grad_norm": 7.33920955657959, "learning_rate": 6.559869703742452e-06, "loss": 0.6646, "step": 55180 }, { "epoch": 0.3280608211328471, "grad_norm": 6.884674549102783, "learning_rate": 6.561058538209141e-06, "loss": 0.6766, "step": 55190 }, { "epoch": 0.3281202632095155, "grad_norm": 7.64570951461792, "learning_rate": 6.56224737267583e-06, "loss": 0.6951, "step": 55200 }, { "epoch": 0.3281797052861839, "grad_norm": 7.398130416870117, "learning_rate": 6.563436207142519e-06, "loss": 0.7274, "step": 55210 }, { "epoch": 0.32823914736285226, "grad_norm": 7.222010135650635, "learning_rate": 6.564625041609208e-06, "loss": 0.6135, "step": 55220 }, { "epoch": 0.32829858943952067, "grad_norm": 7.886098384857178, "learning_rate": 6.565813876075896e-06, "loss": 0.6686, "step": 55230 }, { "epoch": 0.32835803151618903, "grad_norm": 11.117839813232422, "learning_rate": 6.567002710542585e-06, "loss": 0.6451, "step": 55240 }, { "epoch": 0.32841747359285745, "grad_norm": 5.571619510650635, "learning_rate": 6.5681915450092735e-06, "loss": 0.6912, "step": 55250 }, { "epoch": 0.3284769156695258, "grad_norm": 9.12081527709961, "learning_rate": 6.5693803794759624e-06, "loss": 0.7079, "step": 55260 }, { "epoch": 0.3285363577461942, "grad_norm": 7.187351703643799, "learning_rate": 6.570569213942651e-06, "loss": 0.6878, "step": 55270 }, { "epoch": 0.32859579982286263, "grad_norm": 8.066701889038086, "learning_rate": 6.57175804840934e-06, "loss": 0.6424, "step": 55280 }, { "epoch": 0.328655241899531, "grad_norm": 7.410744667053223, "learning_rate": 6.572946882876029e-06, "loss": 0.6774, "step": 55290 }, { "epoch": 0.3287146839761994, "grad_norm": 8.269052505493164, "learning_rate": 6.574135717342718e-06, "loss": 0.7414, "step": 55300 }, { "epoch": 0.32877412605286777, "grad_norm": 5.384002208709717, "learning_rate": 6.575324551809406e-06, "loss": 0.6221, "step": 55310 }, { "epoch": 0.3288335681295362, "grad_norm": 7.035462379455566, "learning_rate": 6.576513386276095e-06, "loss": 0.6652, "step": 55320 }, { "epoch": 0.32889301020620454, "grad_norm": 7.223564147949219, "learning_rate": 6.577702220742784e-06, "loss": 0.7097, "step": 55330 }, { "epoch": 0.32895245228287295, "grad_norm": 7.298291206359863, "learning_rate": 6.578891055209473e-06, "loss": 0.653, "step": 55340 }, { "epoch": 0.32901189435954137, "grad_norm": 8.668503761291504, "learning_rate": 6.580079889676162e-06, "loss": 0.6873, "step": 55350 }, { "epoch": 0.3290713364362097, "grad_norm": 7.188662528991699, "learning_rate": 6.581268724142851e-06, "loss": 0.679, "step": 55360 }, { "epoch": 0.32913077851287814, "grad_norm": 9.299300193786621, "learning_rate": 6.58245755860954e-06, "loss": 0.6508, "step": 55370 }, { "epoch": 0.3291902205895465, "grad_norm": 7.871000289916992, "learning_rate": 6.583646393076229e-06, "loss": 0.7429, "step": 55380 }, { "epoch": 0.3292496626662149, "grad_norm": 7.748521327972412, "learning_rate": 6.584835227542918e-06, "loss": 0.7373, "step": 55390 }, { "epoch": 0.3293091047428833, "grad_norm": 5.442319393157959, "learning_rate": 6.586024062009606e-06, "loss": 0.625, "step": 55400 }, { "epoch": 0.3293685468195517, "grad_norm": 7.707277297973633, "learning_rate": 6.587212896476295e-06, "loss": 0.6752, "step": 55410 }, { "epoch": 0.3294279888962201, "grad_norm": 7.528285503387451, "learning_rate": 6.588401730942984e-06, "loss": 0.6585, "step": 55420 }, { "epoch": 0.32948743097288846, "grad_norm": 7.13952112197876, "learning_rate": 6.5895905654096725e-06, "loss": 0.6742, "step": 55430 }, { "epoch": 0.3295468730495569, "grad_norm": 8.047208786010742, "learning_rate": 6.5907793998763614e-06, "loss": 0.669, "step": 55440 }, { "epoch": 0.32960631512622524, "grad_norm": 7.050887584686279, "learning_rate": 6.59196823434305e-06, "loss": 0.6812, "step": 55450 }, { "epoch": 0.32966575720289365, "grad_norm": 8.234235763549805, "learning_rate": 6.593157068809739e-06, "loss": 0.7277, "step": 55460 }, { "epoch": 0.329725199279562, "grad_norm": 7.073772430419922, "learning_rate": 6.594345903276428e-06, "loss": 0.6988, "step": 55470 }, { "epoch": 0.3297846413562304, "grad_norm": 7.499094486236572, "learning_rate": 6.595534737743116e-06, "loss": 0.7106, "step": 55480 }, { "epoch": 0.32984408343289884, "grad_norm": 6.518066883087158, "learning_rate": 6.596723572209805e-06, "loss": 0.6602, "step": 55490 }, { "epoch": 0.3299035255095672, "grad_norm": 7.803760528564453, "learning_rate": 6.597912406676494e-06, "loss": 0.6551, "step": 55500 }, { "epoch": 0.3299629675862356, "grad_norm": 8.154313087463379, "learning_rate": 6.599101241143184e-06, "loss": 0.6764, "step": 55510 }, { "epoch": 0.33002240966290397, "grad_norm": 8.764715194702148, "learning_rate": 6.600290075609873e-06, "loss": 0.7027, "step": 55520 }, { "epoch": 0.3300818517395724, "grad_norm": 8.387361526489258, "learning_rate": 6.601478910076562e-06, "loss": 0.6782, "step": 55530 }, { "epoch": 0.33014129381624074, "grad_norm": 7.289266109466553, "learning_rate": 6.602667744543251e-06, "loss": 0.6797, "step": 55540 }, { "epoch": 0.33020073589290916, "grad_norm": 7.992855072021484, "learning_rate": 6.60385657900994e-06, "loss": 0.6509, "step": 55550 }, { "epoch": 0.3302601779695775, "grad_norm": 9.266128540039062, "learning_rate": 6.6050454134766286e-06, "loss": 0.6596, "step": 55560 }, { "epoch": 0.33031962004624593, "grad_norm": 7.593703746795654, "learning_rate": 6.6062342479433175e-06, "loss": 0.6487, "step": 55570 }, { "epoch": 0.33037906212291435, "grad_norm": 8.218533515930176, "learning_rate": 6.6074230824100064e-06, "loss": 0.7179, "step": 55580 }, { "epoch": 0.3304385041995827, "grad_norm": 7.205780029296875, "learning_rate": 6.6086119168766945e-06, "loss": 0.6877, "step": 55590 }, { "epoch": 0.3304979462762511, "grad_norm": 7.146509647369385, "learning_rate": 6.6098007513433834e-06, "loss": 0.7207, "step": 55600 }, { "epoch": 0.3305573883529195, "grad_norm": 6.948129653930664, "learning_rate": 6.610989585810072e-06, "loss": 0.6393, "step": 55610 }, { "epoch": 0.3306168304295879, "grad_norm": 8.121764183044434, "learning_rate": 6.612178420276761e-06, "loss": 0.736, "step": 55620 }, { "epoch": 0.33067627250625625, "grad_norm": 6.202374458312988, "learning_rate": 6.61336725474345e-06, "loss": 0.7414, "step": 55630 }, { "epoch": 0.33073571458292467, "grad_norm": 7.127035140991211, "learning_rate": 6.614556089210139e-06, "loss": 0.6477, "step": 55640 }, { "epoch": 0.3307951566595931, "grad_norm": 7.343145847320557, "learning_rate": 6.615744923676828e-06, "loss": 0.7231, "step": 55650 }, { "epoch": 0.33085459873626144, "grad_norm": 6.557448863983154, "learning_rate": 6.616933758143517e-06, "loss": 0.7189, "step": 55660 }, { "epoch": 0.33091404081292985, "grad_norm": 6.501395225524902, "learning_rate": 6.618122592610206e-06, "loss": 0.6612, "step": 55670 }, { "epoch": 0.3309734828895982, "grad_norm": 6.825870990753174, "learning_rate": 6.619311427076894e-06, "loss": 0.6451, "step": 55680 }, { "epoch": 0.33103292496626663, "grad_norm": 8.185675621032715, "learning_rate": 6.620500261543583e-06, "loss": 0.6668, "step": 55690 }, { "epoch": 0.331092367042935, "grad_norm": 6.466078281402588, "learning_rate": 6.621689096010272e-06, "loss": 0.6684, "step": 55700 }, { "epoch": 0.3311518091196034, "grad_norm": 9.236323356628418, "learning_rate": 6.622877930476961e-06, "loss": 0.6977, "step": 55710 }, { "epoch": 0.3312112511962718, "grad_norm": 8.908807754516602, "learning_rate": 6.62406676494365e-06, "loss": 0.6612, "step": 55720 }, { "epoch": 0.3312706932729402, "grad_norm": 7.850989818572998, "learning_rate": 6.625255599410339e-06, "loss": 0.6671, "step": 55730 }, { "epoch": 0.3313301353496086, "grad_norm": 8.910260200500488, "learning_rate": 6.6264444338770276e-06, "loss": 0.6262, "step": 55740 }, { "epoch": 0.33138957742627695, "grad_norm": 7.251793384552002, "learning_rate": 6.6276332683437165e-06, "loss": 0.677, "step": 55750 }, { "epoch": 0.33144901950294536, "grad_norm": 8.27029800415039, "learning_rate": 6.628822102810405e-06, "loss": 0.6643, "step": 55760 }, { "epoch": 0.3315084615796137, "grad_norm": 9.011828422546387, "learning_rate": 6.6300109372770935e-06, "loss": 0.7025, "step": 55770 }, { "epoch": 0.33156790365628214, "grad_norm": 8.471031188964844, "learning_rate": 6.6311997717437824e-06, "loss": 0.7206, "step": 55780 }, { "epoch": 0.33162734573295055, "grad_norm": 6.3714141845703125, "learning_rate": 6.632388606210471e-06, "loss": 0.6749, "step": 55790 }, { "epoch": 0.3316867878096189, "grad_norm": 9.086118698120117, "learning_rate": 6.63357744067716e-06, "loss": 0.7405, "step": 55800 }, { "epoch": 0.3317462298862873, "grad_norm": 9.017414093017578, "learning_rate": 6.634766275143849e-06, "loss": 0.7327, "step": 55810 }, { "epoch": 0.3318056719629557, "grad_norm": 8.207877159118652, "learning_rate": 6.635955109610538e-06, "loss": 0.7438, "step": 55820 }, { "epoch": 0.3318651140396241, "grad_norm": 8.039908409118652, "learning_rate": 6.637143944077227e-06, "loss": 0.6951, "step": 55830 }, { "epoch": 0.33192455611629246, "grad_norm": 9.44509506225586, "learning_rate": 6.638332778543915e-06, "loss": 0.6855, "step": 55840 }, { "epoch": 0.33198399819296087, "grad_norm": 7.160015106201172, "learning_rate": 6.639521613010606e-06, "loss": 0.6621, "step": 55850 }, { "epoch": 0.3320434402696293, "grad_norm": 9.061519622802734, "learning_rate": 6.640710447477295e-06, "loss": 0.6967, "step": 55860 }, { "epoch": 0.33210288234629765, "grad_norm": 6.944122314453125, "learning_rate": 6.641899281943983e-06, "loss": 0.6481, "step": 55870 }, { "epoch": 0.33216232442296606, "grad_norm": 7.71314811706543, "learning_rate": 6.643088116410672e-06, "loss": 0.7299, "step": 55880 }, { "epoch": 0.3322217664996344, "grad_norm": 9.386540412902832, "learning_rate": 6.644276950877361e-06, "loss": 0.6777, "step": 55890 }, { "epoch": 0.33228120857630283, "grad_norm": 10.490800857543945, "learning_rate": 6.6454657853440496e-06, "loss": 0.6983, "step": 55900 }, { "epoch": 0.3323406506529712, "grad_norm": 7.81874942779541, "learning_rate": 6.6466546198107385e-06, "loss": 0.6338, "step": 55910 }, { "epoch": 0.3324000927296396, "grad_norm": 7.349178791046143, "learning_rate": 6.647843454277427e-06, "loss": 0.6712, "step": 55920 }, { "epoch": 0.33245953480630797, "grad_norm": 6.108060359954834, "learning_rate": 6.649032288744116e-06, "loss": 0.7528, "step": 55930 }, { "epoch": 0.3325189768829764, "grad_norm": 7.6602349281311035, "learning_rate": 6.650221123210805e-06, "loss": 0.6352, "step": 55940 }, { "epoch": 0.3325784189596448, "grad_norm": 8.966760635375977, "learning_rate": 6.651409957677493e-06, "loss": 0.748, "step": 55950 }, { "epoch": 0.33263786103631315, "grad_norm": 8.010917663574219, "learning_rate": 6.652598792144182e-06, "loss": 0.6494, "step": 55960 }, { "epoch": 0.33269730311298157, "grad_norm": 7.300709247589111, "learning_rate": 6.653787626610871e-06, "loss": 0.6997, "step": 55970 }, { "epoch": 0.3327567451896499, "grad_norm": 7.072935104370117, "learning_rate": 6.65497646107756e-06, "loss": 0.7104, "step": 55980 }, { "epoch": 0.33281618726631834, "grad_norm": 7.708122253417969, "learning_rate": 6.656165295544249e-06, "loss": 0.6603, "step": 55990 }, { "epoch": 0.3328756293429867, "grad_norm": 8.023869514465332, "learning_rate": 6.657354130010938e-06, "loss": 0.6655, "step": 56000 }, { "epoch": 0.3329350714196551, "grad_norm": 8.057361602783203, "learning_rate": 6.658542964477627e-06, "loss": 0.6734, "step": 56010 }, { "epoch": 0.33299451349632353, "grad_norm": 6.894680976867676, "learning_rate": 6.659731798944316e-06, "loss": 0.6476, "step": 56020 }, { "epoch": 0.3330539555729919, "grad_norm": 8.10702133178711, "learning_rate": 6.660920633411005e-06, "loss": 0.7055, "step": 56030 }, { "epoch": 0.3331133976496603, "grad_norm": 11.27449893951416, "learning_rate": 6.662109467877693e-06, "loss": 0.672, "step": 56040 }, { "epoch": 0.33317283972632866, "grad_norm": 7.598610877990723, "learning_rate": 6.663298302344382e-06, "loss": 0.6474, "step": 56050 }, { "epoch": 0.3332322818029971, "grad_norm": 7.41264009475708, "learning_rate": 6.664487136811071e-06, "loss": 0.6742, "step": 56060 }, { "epoch": 0.33329172387966544, "grad_norm": 6.752431392669678, "learning_rate": 6.66567597127776e-06, "loss": 0.6411, "step": 56070 }, { "epoch": 0.33335116595633385, "grad_norm": 7.192349433898926, "learning_rate": 6.6668648057444486e-06, "loss": 0.7, "step": 56080 }, { "epoch": 0.33341060803300226, "grad_norm": 5.8139519691467285, "learning_rate": 6.6680536402111375e-06, "loss": 0.566, "step": 56090 }, { "epoch": 0.3334700501096706, "grad_norm": 7.583320617675781, "learning_rate": 6.669242474677826e-06, "loss": 0.6595, "step": 56100 }, { "epoch": 0.33352949218633904, "grad_norm": 5.685576915740967, "learning_rate": 6.670431309144515e-06, "loss": 0.6382, "step": 56110 }, { "epoch": 0.3335889342630074, "grad_norm": 7.904288291931152, "learning_rate": 6.671620143611203e-06, "loss": 0.6563, "step": 56120 }, { "epoch": 0.3336483763396758, "grad_norm": 11.02417278289795, "learning_rate": 6.672808978077892e-06, "loss": 0.6329, "step": 56130 }, { "epoch": 0.33370781841634417, "grad_norm": 11.464038848876953, "learning_rate": 6.673997812544581e-06, "loss": 0.6893, "step": 56140 }, { "epoch": 0.3337672604930126, "grad_norm": 6.466429710388184, "learning_rate": 6.67518664701127e-06, "loss": 0.6418, "step": 56150 }, { "epoch": 0.333826702569681, "grad_norm": 6.615159034729004, "learning_rate": 6.676375481477959e-06, "loss": 0.6492, "step": 56160 }, { "epoch": 0.33388614464634936, "grad_norm": 5.941587448120117, "learning_rate": 6.677564315944648e-06, "loss": 0.7244, "step": 56170 }, { "epoch": 0.3339455867230178, "grad_norm": 8.91396713256836, "learning_rate": 6.678753150411337e-06, "loss": 0.6903, "step": 56180 }, { "epoch": 0.33400502879968613, "grad_norm": 8.318748474121094, "learning_rate": 6.679941984878026e-06, "loss": 0.6907, "step": 56190 }, { "epoch": 0.33406447087635455, "grad_norm": 6.753679275512695, "learning_rate": 6.681130819344716e-06, "loss": 0.6513, "step": 56200 }, { "epoch": 0.3341239129530229, "grad_norm": 6.187944412231445, "learning_rate": 6.682319653811405e-06, "loss": 0.687, "step": 56210 }, { "epoch": 0.3341833550296913, "grad_norm": 7.4207282066345215, "learning_rate": 6.6835084882780935e-06, "loss": 0.6788, "step": 56220 }, { "epoch": 0.33424279710635973, "grad_norm": 7.006216526031494, "learning_rate": 6.684697322744782e-06, "loss": 0.6974, "step": 56230 }, { "epoch": 0.3343022391830281, "grad_norm": 6.820779800415039, "learning_rate": 6.6858861572114705e-06, "loss": 0.6833, "step": 56240 }, { "epoch": 0.3343616812596965, "grad_norm": 8.612761497497559, "learning_rate": 6.6870749916781595e-06, "loss": 0.659, "step": 56250 }, { "epoch": 0.33442112333636487, "grad_norm": 6.194437026977539, "learning_rate": 6.688263826144848e-06, "loss": 0.7169, "step": 56260 }, { "epoch": 0.3344805654130333, "grad_norm": 7.6817731857299805, "learning_rate": 6.689452660611537e-06, "loss": 0.6896, "step": 56270 }, { "epoch": 0.33454000748970164, "grad_norm": 8.145000457763672, "learning_rate": 6.690641495078226e-06, "loss": 0.6624, "step": 56280 }, { "epoch": 0.33459944956637006, "grad_norm": 7.471441268920898, "learning_rate": 6.691830329544915e-06, "loss": 0.7194, "step": 56290 }, { "epoch": 0.3346588916430384, "grad_norm": 6.0717597007751465, "learning_rate": 6.693019164011604e-06, "loss": 0.6651, "step": 56300 }, { "epoch": 0.33471833371970683, "grad_norm": 9.954329490661621, "learning_rate": 6.694207998478292e-06, "loss": 0.7008, "step": 56310 }, { "epoch": 0.33477777579637524, "grad_norm": 7.211699485778809, "learning_rate": 6.695396832944981e-06, "loss": 0.7408, "step": 56320 }, { "epoch": 0.3348372178730436, "grad_norm": 9.431145668029785, "learning_rate": 6.69658566741167e-06, "loss": 0.6864, "step": 56330 }, { "epoch": 0.334896659949712, "grad_norm": 8.292067527770996, "learning_rate": 6.697774501878359e-06, "loss": 0.6731, "step": 56340 }, { "epoch": 0.3349561020263804, "grad_norm": 7.8698506355285645, "learning_rate": 6.698963336345048e-06, "loss": 0.736, "step": 56350 }, { "epoch": 0.3350155441030488, "grad_norm": 8.151616096496582, "learning_rate": 6.700152170811737e-06, "loss": 0.6856, "step": 56360 }, { "epoch": 0.33507498617971715, "grad_norm": 8.787837982177734, "learning_rate": 6.701341005278426e-06, "loss": 0.6955, "step": 56370 }, { "epoch": 0.33513442825638556, "grad_norm": 7.230212688446045, "learning_rate": 6.702529839745115e-06, "loss": 0.6302, "step": 56380 }, { "epoch": 0.335193870333054, "grad_norm": 6.0868024826049805, "learning_rate": 6.703718674211804e-06, "loss": 0.6805, "step": 56390 }, { "epoch": 0.33525331240972234, "grad_norm": 8.634474754333496, "learning_rate": 6.704907508678492e-06, "loss": 0.628, "step": 56400 }, { "epoch": 0.33531275448639075, "grad_norm": 8.88361930847168, "learning_rate": 6.706096343145181e-06, "loss": 0.6725, "step": 56410 }, { "epoch": 0.3353721965630591, "grad_norm": 6.834282398223877, "learning_rate": 6.7072851776118695e-06, "loss": 0.6688, "step": 56420 }, { "epoch": 0.3354316386397275, "grad_norm": 7.527622699737549, "learning_rate": 6.7084740120785585e-06, "loss": 0.6982, "step": 56430 }, { "epoch": 0.3354910807163959, "grad_norm": 8.367133140563965, "learning_rate": 6.709662846545247e-06, "loss": 0.6817, "step": 56440 }, { "epoch": 0.3355505227930643, "grad_norm": 6.004155158996582, "learning_rate": 6.710851681011936e-06, "loss": 0.647, "step": 56450 }, { "epoch": 0.3356099648697327, "grad_norm": 7.207417964935303, "learning_rate": 6.712040515478625e-06, "loss": 0.6617, "step": 56460 }, { "epoch": 0.33566940694640107, "grad_norm": 6.730082035064697, "learning_rate": 6.713229349945314e-06, "loss": 0.6117, "step": 56470 }, { "epoch": 0.3357288490230695, "grad_norm": 8.117535591125488, "learning_rate": 6.714418184412002e-06, "loss": 0.6706, "step": 56480 }, { "epoch": 0.33578829109973785, "grad_norm": 7.197324752807617, "learning_rate": 6.715607018878691e-06, "loss": 0.6854, "step": 56490 }, { "epoch": 0.33584773317640626, "grad_norm": 7.327024936676025, "learning_rate": 6.71679585334538e-06, "loss": 0.6547, "step": 56500 }, { "epoch": 0.3359071752530746, "grad_norm": 7.927649974822998, "learning_rate": 6.717984687812069e-06, "loss": 0.6937, "step": 56510 }, { "epoch": 0.33596661732974303, "grad_norm": 9.13616943359375, "learning_rate": 6.719173522278758e-06, "loss": 0.6767, "step": 56520 }, { "epoch": 0.33602605940641145, "grad_norm": 7.708957672119141, "learning_rate": 6.720362356745447e-06, "loss": 0.6274, "step": 56530 }, { "epoch": 0.3360855014830798, "grad_norm": 6.702049255371094, "learning_rate": 6.721551191212136e-06, "loss": 0.6127, "step": 56540 }, { "epoch": 0.3361449435597482, "grad_norm": 6.032739639282227, "learning_rate": 6.722740025678826e-06, "loss": 0.6234, "step": 56550 }, { "epoch": 0.3362043856364166, "grad_norm": 7.739144325256348, "learning_rate": 6.7239288601455145e-06, "loss": 0.6676, "step": 56560 }, { "epoch": 0.336263827713085, "grad_norm": 6.804757118225098, "learning_rate": 6.7251176946122035e-06, "loss": 0.6694, "step": 56570 }, { "epoch": 0.33632326978975335, "grad_norm": 6.384220600128174, "learning_rate": 6.726306529078892e-06, "loss": 0.6845, "step": 56580 }, { "epoch": 0.33638271186642177, "grad_norm": 7.453074932098389, "learning_rate": 6.7274953635455805e-06, "loss": 0.6485, "step": 56590 }, { "epoch": 0.3364421539430902, "grad_norm": 8.21355152130127, "learning_rate": 6.728684198012269e-06, "loss": 0.625, "step": 56600 }, { "epoch": 0.33650159601975854, "grad_norm": 6.778653621673584, "learning_rate": 6.729873032478958e-06, "loss": 0.7294, "step": 56610 }, { "epoch": 0.33656103809642696, "grad_norm": 6.62414026260376, "learning_rate": 6.731061866945647e-06, "loss": 0.6017, "step": 56620 }, { "epoch": 0.3366204801730953, "grad_norm": 7.275478363037109, "learning_rate": 6.732250701412336e-06, "loss": 0.6366, "step": 56630 }, { "epoch": 0.33667992224976373, "grad_norm": 7.640888214111328, "learning_rate": 6.733439535879025e-06, "loss": 0.7589, "step": 56640 }, { "epoch": 0.3367393643264321, "grad_norm": 7.145191669464111, "learning_rate": 6.734628370345714e-06, "loss": 0.6925, "step": 56650 }, { "epoch": 0.3367988064031005, "grad_norm": 5.935949325561523, "learning_rate": 6.735817204812403e-06, "loss": 0.6242, "step": 56660 }, { "epoch": 0.33685824847976886, "grad_norm": 9.625882148742676, "learning_rate": 6.737006039279092e-06, "loss": 0.6947, "step": 56670 }, { "epoch": 0.3369176905564373, "grad_norm": 6.955763339996338, "learning_rate": 6.73819487374578e-06, "loss": 0.689, "step": 56680 }, { "epoch": 0.3369771326331057, "grad_norm": 7.974530220031738, "learning_rate": 6.739383708212469e-06, "loss": 0.6303, "step": 56690 }, { "epoch": 0.33703657470977405, "grad_norm": 8.328377723693848, "learning_rate": 6.740572542679158e-06, "loss": 0.7039, "step": 56700 }, { "epoch": 0.33709601678644247, "grad_norm": 7.083028793334961, "learning_rate": 6.741761377145847e-06, "loss": 0.7339, "step": 56710 }, { "epoch": 0.3371554588631108, "grad_norm": 5.777589321136475, "learning_rate": 6.742950211612536e-06, "loss": 0.7429, "step": 56720 }, { "epoch": 0.33721490093977924, "grad_norm": 8.152335166931152, "learning_rate": 6.744139046079225e-06, "loss": 0.7029, "step": 56730 }, { "epoch": 0.3372743430164476, "grad_norm": 6.8595380783081055, "learning_rate": 6.7453278805459135e-06, "loss": 0.6916, "step": 56740 }, { "epoch": 0.337333785093116, "grad_norm": 6.607511520385742, "learning_rate": 6.7465167150126025e-06, "loss": 0.6501, "step": 56750 }, { "epoch": 0.3373932271697844, "grad_norm": 5.758155822753906, "learning_rate": 6.7477055494792905e-06, "loss": 0.6144, "step": 56760 }, { "epoch": 0.3374526692464528, "grad_norm": 8.082775115966797, "learning_rate": 6.7488943839459795e-06, "loss": 0.6511, "step": 56770 }, { "epoch": 0.3375121113231212, "grad_norm": 6.021356105804443, "learning_rate": 6.750083218412668e-06, "loss": 0.6203, "step": 56780 }, { "epoch": 0.33757155339978956, "grad_norm": 7.103692531585693, "learning_rate": 6.751272052879357e-06, "loss": 0.6247, "step": 56790 }, { "epoch": 0.337630995476458, "grad_norm": 6.587562561035156, "learning_rate": 6.752460887346046e-06, "loss": 0.5485, "step": 56800 }, { "epoch": 0.33769043755312633, "grad_norm": 8.371405601501465, "learning_rate": 6.753649721812735e-06, "loss": 0.6748, "step": 56810 }, { "epoch": 0.33774987962979475, "grad_norm": 7.430412769317627, "learning_rate": 6.754838556279424e-06, "loss": 0.6946, "step": 56820 }, { "epoch": 0.33780932170646316, "grad_norm": 7.117074489593506, "learning_rate": 6.756027390746113e-06, "loss": 0.5953, "step": 56830 }, { "epoch": 0.3378687637831315, "grad_norm": 8.196074485778809, "learning_rate": 6.757216225212801e-06, "loss": 0.634, "step": 56840 }, { "epoch": 0.33792820585979993, "grad_norm": 6.191762447357178, "learning_rate": 6.75840505967949e-06, "loss": 0.7043, "step": 56850 }, { "epoch": 0.3379876479364683, "grad_norm": 7.847630023956299, "learning_rate": 6.759593894146179e-06, "loss": 0.7041, "step": 56860 }, { "epoch": 0.3380470900131367, "grad_norm": 7.262864589691162, "learning_rate": 6.760782728612868e-06, "loss": 0.7069, "step": 56870 }, { "epoch": 0.33810653208980507, "grad_norm": 9.398336410522461, "learning_rate": 6.761971563079557e-06, "loss": 0.6782, "step": 56880 }, { "epoch": 0.3381659741664735, "grad_norm": 8.489412307739258, "learning_rate": 6.763160397546247e-06, "loss": 0.7196, "step": 56890 }, { "epoch": 0.3382254162431419, "grad_norm": 7.7320709228515625, "learning_rate": 6.7643492320129355e-06, "loss": 0.6375, "step": 56900 }, { "epoch": 0.33828485831981026, "grad_norm": 7.930347919464111, "learning_rate": 6.7655380664796244e-06, "loss": 0.7533, "step": 56910 }, { "epoch": 0.33834430039647867, "grad_norm": 7.512118339538574, "learning_rate": 6.766726900946313e-06, "loss": 0.7447, "step": 56920 }, { "epoch": 0.33840374247314703, "grad_norm": 9.48533821105957, "learning_rate": 6.767915735413002e-06, "loss": 0.5991, "step": 56930 }, { "epoch": 0.33846318454981544, "grad_norm": 6.293146133422852, "learning_rate": 6.769104569879691e-06, "loss": 0.6865, "step": 56940 }, { "epoch": 0.3385226266264838, "grad_norm": 7.014721393585205, "learning_rate": 6.770293404346379e-06, "loss": 0.6606, "step": 56950 }, { "epoch": 0.3385820687031522, "grad_norm": 7.035148620605469, "learning_rate": 6.771482238813068e-06, "loss": 0.6112, "step": 56960 }, { "epoch": 0.33864151077982063, "grad_norm": 7.117325782775879, "learning_rate": 6.772671073279757e-06, "loss": 0.6435, "step": 56970 }, { "epoch": 0.338700952856489, "grad_norm": 6.785826206207275, "learning_rate": 6.773859907746446e-06, "loss": 0.5913, "step": 56980 }, { "epoch": 0.3387603949331574, "grad_norm": 6.746488094329834, "learning_rate": 6.775048742213135e-06, "loss": 0.689, "step": 56990 }, { "epoch": 0.33881983700982576, "grad_norm": 6.359283447265625, "learning_rate": 6.776237576679824e-06, "loss": 0.7134, "step": 57000 }, { "epoch": 0.3388792790864942, "grad_norm": 8.457808494567871, "learning_rate": 6.777426411146513e-06, "loss": 0.699, "step": 57010 }, { "epoch": 0.33893872116316254, "grad_norm": 6.690552234649658, "learning_rate": 6.778615245613202e-06, "loss": 0.677, "step": 57020 }, { "epoch": 0.33899816323983095, "grad_norm": 7.511740684509277, "learning_rate": 6.779804080079891e-06, "loss": 0.6888, "step": 57030 }, { "epoch": 0.3390576053164993, "grad_norm": 8.197761535644531, "learning_rate": 6.780992914546579e-06, "loss": 0.6957, "step": 57040 }, { "epoch": 0.3391170473931677, "grad_norm": 7.743282318115234, "learning_rate": 6.782181749013268e-06, "loss": 0.7386, "step": 57050 }, { "epoch": 0.33917648946983614, "grad_norm": 7.3287200927734375, "learning_rate": 6.783370583479957e-06, "loss": 0.6657, "step": 57060 }, { "epoch": 0.3392359315465045, "grad_norm": 7.158382892608643, "learning_rate": 6.784559417946646e-06, "loss": 0.6329, "step": 57070 }, { "epoch": 0.3392953736231729, "grad_norm": 6.871903896331787, "learning_rate": 6.7857482524133345e-06, "loss": 0.6882, "step": 57080 }, { "epoch": 0.3393548156998413, "grad_norm": 7.139777183532715, "learning_rate": 6.7869370868800234e-06, "loss": 0.7087, "step": 57090 }, { "epoch": 0.3394142577765097, "grad_norm": 6.582157135009766, "learning_rate": 6.788125921346712e-06, "loss": 0.6736, "step": 57100 }, { "epoch": 0.33947369985317805, "grad_norm": 8.668994903564453, "learning_rate": 6.789314755813401e-06, "loss": 0.6204, "step": 57110 }, { "epoch": 0.33953314192984646, "grad_norm": 6.738704204559326, "learning_rate": 6.790503590280089e-06, "loss": 0.6218, "step": 57120 }, { "epoch": 0.3395925840065149, "grad_norm": 6.328585147857666, "learning_rate": 6.791692424746778e-06, "loss": 0.6667, "step": 57130 }, { "epoch": 0.33965202608318323, "grad_norm": 7.329050064086914, "learning_rate": 6.792881259213467e-06, "loss": 0.6343, "step": 57140 }, { "epoch": 0.33971146815985165, "grad_norm": 7.445071697235107, "learning_rate": 6.794070093680156e-06, "loss": 0.6478, "step": 57150 }, { "epoch": 0.33977091023652, "grad_norm": 6.360080718994141, "learning_rate": 6.795258928146845e-06, "loss": 0.7116, "step": 57160 }, { "epoch": 0.3398303523131884, "grad_norm": 8.620990753173828, "learning_rate": 6.796447762613534e-06, "loss": 0.6689, "step": 57170 }, { "epoch": 0.3398897943898568, "grad_norm": 9.33945083618164, "learning_rate": 6.797636597080223e-06, "loss": 0.6447, "step": 57180 }, { "epoch": 0.3399492364665252, "grad_norm": 7.354372501373291, "learning_rate": 6.798825431546912e-06, "loss": 0.69, "step": 57190 }, { "epoch": 0.3400086785431936, "grad_norm": 6.940502166748047, "learning_rate": 6.800014266013601e-06, "loss": 0.6802, "step": 57200 }, { "epoch": 0.34006812061986197, "grad_norm": 7.2100629806518555, "learning_rate": 6.801203100480289e-06, "loss": 0.6628, "step": 57210 }, { "epoch": 0.3401275626965304, "grad_norm": 9.600310325622559, "learning_rate": 6.802391934946978e-06, "loss": 0.7061, "step": 57220 }, { "epoch": 0.34018700477319874, "grad_norm": 6.12650728225708, "learning_rate": 6.803580769413667e-06, "loss": 0.6165, "step": 57230 }, { "epoch": 0.34024644684986716, "grad_norm": 7.559661388397217, "learning_rate": 6.8047696038803565e-06, "loss": 0.6975, "step": 57240 }, { "epoch": 0.3403058889265355, "grad_norm": 6.860607624053955, "learning_rate": 6.8059584383470454e-06, "loss": 0.6579, "step": 57250 }, { "epoch": 0.34036533100320393, "grad_norm": 7.941122055053711, "learning_rate": 6.807147272813734e-06, "loss": 0.6528, "step": 57260 }, { "epoch": 0.34042477307987234, "grad_norm": 9.433107376098633, "learning_rate": 6.808336107280423e-06, "loss": 0.7172, "step": 57270 }, { "epoch": 0.3404842151565407, "grad_norm": 7.118969917297363, "learning_rate": 6.809524941747112e-06, "loss": 0.7016, "step": 57280 }, { "epoch": 0.3405436572332091, "grad_norm": 8.449174880981445, "learning_rate": 6.810713776213801e-06, "loss": 0.6816, "step": 57290 }, { "epoch": 0.3406030993098775, "grad_norm": 7.640788555145264, "learning_rate": 6.81190261068049e-06, "loss": 0.6525, "step": 57300 }, { "epoch": 0.3406625413865459, "grad_norm": 6.595924377441406, "learning_rate": 6.813091445147179e-06, "loss": 0.6794, "step": 57310 }, { "epoch": 0.34072198346321425, "grad_norm": 8.342432022094727, "learning_rate": 6.814280279613867e-06, "loss": 0.6457, "step": 57320 }, { "epoch": 0.34078142553988267, "grad_norm": 9.25377368927002, "learning_rate": 6.815469114080556e-06, "loss": 0.6713, "step": 57330 }, { "epoch": 0.340840867616551, "grad_norm": 7.804261207580566, "learning_rate": 6.816657948547245e-06, "loss": 0.6643, "step": 57340 }, { "epoch": 0.34090030969321944, "grad_norm": 9.532093048095703, "learning_rate": 6.817846783013934e-06, "loss": 0.665, "step": 57350 }, { "epoch": 0.34095975176988785, "grad_norm": 5.5035223960876465, "learning_rate": 6.819035617480623e-06, "loss": 0.6827, "step": 57360 }, { "epoch": 0.3410191938465562, "grad_norm": 9.173977851867676, "learning_rate": 6.820224451947312e-06, "loss": 0.7271, "step": 57370 }, { "epoch": 0.3410786359232246, "grad_norm": 6.704573631286621, "learning_rate": 6.821413286414001e-06, "loss": 0.6748, "step": 57380 }, { "epoch": 0.341138077999893, "grad_norm": 8.439611434936523, "learning_rate": 6.8226021208806896e-06, "loss": 0.6682, "step": 57390 }, { "epoch": 0.3411975200765614, "grad_norm": 10.634245872497559, "learning_rate": 6.823790955347378e-06, "loss": 0.7558, "step": 57400 }, { "epoch": 0.34125696215322976, "grad_norm": 7.9926981925964355, "learning_rate": 6.8249797898140666e-06, "loss": 0.7322, "step": 57410 }, { "epoch": 0.3413164042298982, "grad_norm": 8.899417877197266, "learning_rate": 6.8261686242807555e-06, "loss": 0.7197, "step": 57420 }, { "epoch": 0.3413758463065666, "grad_norm": 6.735103607177734, "learning_rate": 6.8273574587474444e-06, "loss": 0.6442, "step": 57430 }, { "epoch": 0.34143528838323495, "grad_norm": 7.135866641998291, "learning_rate": 6.828546293214133e-06, "loss": 0.679, "step": 57440 }, { "epoch": 0.34149473045990336, "grad_norm": 7.474750995635986, "learning_rate": 6.829735127680822e-06, "loss": 0.6398, "step": 57450 }, { "epoch": 0.3415541725365717, "grad_norm": 5.960321426391602, "learning_rate": 6.830923962147511e-06, "loss": 0.6725, "step": 57460 }, { "epoch": 0.34161361461324014, "grad_norm": 6.917253494262695, "learning_rate": 6.8321127966142e-06, "loss": 0.6783, "step": 57470 }, { "epoch": 0.3416730566899085, "grad_norm": 5.682460308074951, "learning_rate": 6.833301631080888e-06, "loss": 0.7047, "step": 57480 }, { "epoch": 0.3417324987665769, "grad_norm": 5.30830192565918, "learning_rate": 6.834490465547577e-06, "loss": 0.6441, "step": 57490 }, { "epoch": 0.3417919408432453, "grad_norm": 7.517263412475586, "learning_rate": 6.835679300014266e-06, "loss": 0.6164, "step": 57500 }, { "epoch": 0.3418513829199137, "grad_norm": 5.121023654937744, "learning_rate": 6.836868134480955e-06, "loss": 0.6638, "step": 57510 }, { "epoch": 0.3419108249965821, "grad_norm": 8.177702903747559, "learning_rate": 6.838056968947644e-06, "loss": 0.6743, "step": 57520 }, { "epoch": 0.34197026707325046, "grad_norm": 6.040180683135986, "learning_rate": 6.839245803414333e-06, "loss": 0.6445, "step": 57530 }, { "epoch": 0.34202970914991887, "grad_norm": 7.550654888153076, "learning_rate": 6.840434637881022e-06, "loss": 0.6742, "step": 57540 }, { "epoch": 0.34208915122658723, "grad_norm": 6.9467244148254395, "learning_rate": 6.841623472347711e-06, "loss": 0.7131, "step": 57550 }, { "epoch": 0.34214859330325564, "grad_norm": 9.349326133728027, "learning_rate": 6.8428123068144e-06, "loss": 0.6413, "step": 57560 }, { "epoch": 0.34220803537992406, "grad_norm": 9.773967742919922, "learning_rate": 6.844001141281088e-06, "loss": 0.6771, "step": 57570 }, { "epoch": 0.3422674774565924, "grad_norm": 5.914219379425049, "learning_rate": 6.845189975747778e-06, "loss": 0.6938, "step": 57580 }, { "epoch": 0.34232691953326083, "grad_norm": 7.673995018005371, "learning_rate": 6.846378810214466e-06, "loss": 0.6318, "step": 57590 }, { "epoch": 0.3423863616099292, "grad_norm": 7.693935394287109, "learning_rate": 6.847567644681155e-06, "loss": 0.6015, "step": 57600 }, { "epoch": 0.3424458036865976, "grad_norm": 6.251101016998291, "learning_rate": 6.848756479147844e-06, "loss": 0.7323, "step": 57610 }, { "epoch": 0.34250524576326596, "grad_norm": 6.897518634796143, "learning_rate": 6.849945313614533e-06, "loss": 0.6496, "step": 57620 }, { "epoch": 0.3425646878399344, "grad_norm": 7.893486499786377, "learning_rate": 6.851134148081222e-06, "loss": 0.6786, "step": 57630 }, { "epoch": 0.3426241299166028, "grad_norm": 6.808710098266602, "learning_rate": 6.852322982547911e-06, "loss": 0.6405, "step": 57640 }, { "epoch": 0.34268357199327115, "grad_norm": 6.36691951751709, "learning_rate": 6.8535118170146e-06, "loss": 0.6472, "step": 57650 }, { "epoch": 0.34274301406993957, "grad_norm": 12.25001335144043, "learning_rate": 6.854700651481289e-06, "loss": 0.6844, "step": 57660 }, { "epoch": 0.3428024561466079, "grad_norm": 5.938592910766602, "learning_rate": 6.855889485947978e-06, "loss": 0.6694, "step": 57670 }, { "epoch": 0.34286189822327634, "grad_norm": 7.212258338928223, "learning_rate": 6.857078320414666e-06, "loss": 0.6793, "step": 57680 }, { "epoch": 0.3429213402999447, "grad_norm": 6.74998140335083, "learning_rate": 6.858267154881355e-06, "loss": 0.651, "step": 57690 }, { "epoch": 0.3429807823766131, "grad_norm": 6.59468936920166, "learning_rate": 6.859455989348044e-06, "loss": 0.7206, "step": 57700 }, { "epoch": 0.3430402244532815, "grad_norm": 6.580994129180908, "learning_rate": 6.860644823814733e-06, "loss": 0.6229, "step": 57710 }, { "epoch": 0.3430996665299499, "grad_norm": 7.996562957763672, "learning_rate": 6.861833658281422e-06, "loss": 0.6653, "step": 57720 }, { "epoch": 0.3431591086066183, "grad_norm": 5.922355651855469, "learning_rate": 6.8630224927481106e-06, "loss": 0.6558, "step": 57730 }, { "epoch": 0.34321855068328666, "grad_norm": 7.138921737670898, "learning_rate": 6.8642113272147995e-06, "loss": 0.6783, "step": 57740 }, { "epoch": 0.3432779927599551, "grad_norm": 6.3398847579956055, "learning_rate": 6.865400161681488e-06, "loss": 0.6358, "step": 57750 }, { "epoch": 0.34333743483662343, "grad_norm": 7.269989490509033, "learning_rate": 6.8665889961481765e-06, "loss": 0.627, "step": 57760 }, { "epoch": 0.34339687691329185, "grad_norm": 7.1374945640563965, "learning_rate": 6.867777830614865e-06, "loss": 0.6889, "step": 57770 }, { "epoch": 0.3434563189899602, "grad_norm": 8.1377534866333, "learning_rate": 6.868966665081554e-06, "loss": 0.6797, "step": 57780 }, { "epoch": 0.3435157610666286, "grad_norm": 7.639877796173096, "learning_rate": 6.870155499548243e-06, "loss": 0.6967, "step": 57790 }, { "epoch": 0.34357520314329704, "grad_norm": 7.187984943389893, "learning_rate": 6.871344334014932e-06, "loss": 0.6757, "step": 57800 }, { "epoch": 0.3436346452199654, "grad_norm": 7.046812057495117, "learning_rate": 6.872533168481621e-06, "loss": 0.6774, "step": 57810 }, { "epoch": 0.3436940872966338, "grad_norm": 7.737131595611572, "learning_rate": 6.87372200294831e-06, "loss": 0.6628, "step": 57820 }, { "epoch": 0.34375352937330217, "grad_norm": 6.175776481628418, "learning_rate": 6.874910837414999e-06, "loss": 0.6746, "step": 57830 }, { "epoch": 0.3438129714499706, "grad_norm": 7.538344383239746, "learning_rate": 6.876099671881687e-06, "loss": 0.6548, "step": 57840 }, { "epoch": 0.34387241352663894, "grad_norm": 6.454115867614746, "learning_rate": 6.877288506348376e-06, "loss": 0.6328, "step": 57850 }, { "epoch": 0.34393185560330736, "grad_norm": 7.612452030181885, "learning_rate": 6.878477340815065e-06, "loss": 0.7127, "step": 57860 }, { "epoch": 0.34399129767997577, "grad_norm": 7.210085868835449, "learning_rate": 6.879666175281754e-06, "loss": 0.6475, "step": 57870 }, { "epoch": 0.34405073975664413, "grad_norm": 7.864797592163086, "learning_rate": 6.880855009748443e-06, "loss": 0.6868, "step": 57880 }, { "epoch": 0.34411018183331255, "grad_norm": 7.899564266204834, "learning_rate": 6.882043844215132e-06, "loss": 0.6567, "step": 57890 }, { "epoch": 0.3441696239099809, "grad_norm": 8.105463981628418, "learning_rate": 6.883232678681821e-06, "loss": 0.6912, "step": 57900 }, { "epoch": 0.3442290659866493, "grad_norm": 6.23427152633667, "learning_rate": 6.8844215131485095e-06, "loss": 0.5893, "step": 57910 }, { "epoch": 0.3442885080633177, "grad_norm": 7.761551856994629, "learning_rate": 6.8856103476151985e-06, "loss": 0.638, "step": 57920 }, { "epoch": 0.3443479501399861, "grad_norm": 9.220441818237305, "learning_rate": 6.886799182081888e-06, "loss": 0.6685, "step": 57930 }, { "epoch": 0.3444073922166545, "grad_norm": 7.39107608795166, "learning_rate": 6.887988016548577e-06, "loss": 0.7247, "step": 57940 }, { "epoch": 0.34446683429332287, "grad_norm": 9.255189895629883, "learning_rate": 6.889176851015265e-06, "loss": 0.7295, "step": 57950 }, { "epoch": 0.3445262763699913, "grad_norm": 7.8734517097473145, "learning_rate": 6.890365685481954e-06, "loss": 0.6392, "step": 57960 }, { "epoch": 0.34458571844665964, "grad_norm": 6.7861714363098145, "learning_rate": 6.891554519948643e-06, "loss": 0.6683, "step": 57970 }, { "epoch": 0.34464516052332805, "grad_norm": 6.49234676361084, "learning_rate": 6.892743354415332e-06, "loss": 0.7072, "step": 57980 }, { "epoch": 0.3447046025999964, "grad_norm": 6.420360565185547, "learning_rate": 6.893932188882021e-06, "loss": 0.7254, "step": 57990 }, { "epoch": 0.3447640446766648, "grad_norm": 7.891556739807129, "learning_rate": 6.89512102334871e-06, "loss": 0.6696, "step": 58000 }, { "epoch": 0.34482348675333324, "grad_norm": 7.1804633140563965, "learning_rate": 6.896309857815399e-06, "loss": 0.625, "step": 58010 }, { "epoch": 0.3448829288300016, "grad_norm": 7.75827693939209, "learning_rate": 6.897498692282088e-06, "loss": 0.6905, "step": 58020 }, { "epoch": 0.34494237090667, "grad_norm": 8.981779098510742, "learning_rate": 6.898687526748777e-06, "loss": 0.7062, "step": 58030 }, { "epoch": 0.3450018129833384, "grad_norm": 8.684755325317383, "learning_rate": 6.899876361215465e-06, "loss": 0.6791, "step": 58040 }, { "epoch": 0.3450612550600068, "grad_norm": 6.156134605407715, "learning_rate": 6.901065195682154e-06, "loss": 0.6926, "step": 58050 }, { "epoch": 0.34512069713667515, "grad_norm": 6.640804767608643, "learning_rate": 6.902254030148843e-06, "loss": 0.6679, "step": 58060 }, { "epoch": 0.34518013921334356, "grad_norm": 7.3253397941589355, "learning_rate": 6.9034428646155315e-06, "loss": 0.6345, "step": 58070 }, { "epoch": 0.3452395812900119, "grad_norm": 6.755415439605713, "learning_rate": 6.9046316990822205e-06, "loss": 0.6964, "step": 58080 }, { "epoch": 0.34529902336668034, "grad_norm": 7.36685848236084, "learning_rate": 6.905820533548909e-06, "loss": 0.6414, "step": 58090 }, { "epoch": 0.34535846544334875, "grad_norm": 8.404984474182129, "learning_rate": 6.907009368015598e-06, "loss": 0.6298, "step": 58100 }, { "epoch": 0.3454179075200171, "grad_norm": 9.39901351928711, "learning_rate": 6.908198202482287e-06, "loss": 0.7006, "step": 58110 }, { "epoch": 0.3454773495966855, "grad_norm": 7.745965003967285, "learning_rate": 6.909387036948975e-06, "loss": 0.7299, "step": 58120 }, { "epoch": 0.3455367916733539, "grad_norm": 6.611536502838135, "learning_rate": 6.910575871415664e-06, "loss": 0.6937, "step": 58130 }, { "epoch": 0.3455962337500223, "grad_norm": 6.367999076843262, "learning_rate": 6.911764705882353e-06, "loss": 0.6723, "step": 58140 }, { "epoch": 0.34565567582669066, "grad_norm": 7.497800350189209, "learning_rate": 6.912953540349042e-06, "loss": 0.6837, "step": 58150 }, { "epoch": 0.34571511790335907, "grad_norm": 7.075344562530518, "learning_rate": 6.914142374815731e-06, "loss": 0.6537, "step": 58160 }, { "epoch": 0.3457745599800275, "grad_norm": 8.912128448486328, "learning_rate": 6.91533120928242e-06, "loss": 0.7182, "step": 58170 }, { "epoch": 0.34583400205669584, "grad_norm": 8.024968147277832, "learning_rate": 6.916520043749109e-06, "loss": 0.6152, "step": 58180 }, { "epoch": 0.34589344413336426, "grad_norm": 6.847134113311768, "learning_rate": 6.917708878215798e-06, "loss": 0.6345, "step": 58190 }, { "epoch": 0.3459528862100326, "grad_norm": 8.887229919433594, "learning_rate": 6.918897712682487e-06, "loss": 0.6831, "step": 58200 }, { "epoch": 0.34601232828670103, "grad_norm": 6.485573768615723, "learning_rate": 6.920086547149175e-06, "loss": 0.6597, "step": 58210 }, { "epoch": 0.3460717703633694, "grad_norm": 7.5141401290893555, "learning_rate": 6.921275381615864e-06, "loss": 0.6515, "step": 58220 }, { "epoch": 0.3461312124400378, "grad_norm": 9.771343231201172, "learning_rate": 6.922464216082553e-06, "loss": 0.7235, "step": 58230 }, { "epoch": 0.3461906545167062, "grad_norm": 8.693085670471191, "learning_rate": 6.923653050549242e-06, "loss": 0.7071, "step": 58240 }, { "epoch": 0.3462500965933746, "grad_norm": 9.01245403289795, "learning_rate": 6.9248418850159305e-06, "loss": 0.6678, "step": 58250 }, { "epoch": 0.346309538670043, "grad_norm": 9.072498321533203, "learning_rate": 6.9260307194826195e-06, "loss": 0.691, "step": 58260 }, { "epoch": 0.34636898074671135, "grad_norm": 13.062499046325684, "learning_rate": 6.927219553949308e-06, "loss": 0.6648, "step": 58270 }, { "epoch": 0.34642842282337977, "grad_norm": 8.419644355773926, "learning_rate": 6.928408388415998e-06, "loss": 0.7043, "step": 58280 }, { "epoch": 0.3464878649000481, "grad_norm": 7.6055989265441895, "learning_rate": 6.929597222882687e-06, "loss": 0.663, "step": 58290 }, { "epoch": 0.34654730697671654, "grad_norm": 8.906893730163574, "learning_rate": 6.930786057349376e-06, "loss": 0.7449, "step": 58300 }, { "epoch": 0.34660674905338495, "grad_norm": 7.051520347595215, "learning_rate": 6.931974891816065e-06, "loss": 0.6703, "step": 58310 }, { "epoch": 0.3466661911300533, "grad_norm": 6.6761155128479, "learning_rate": 6.933163726282753e-06, "loss": 0.6339, "step": 58320 }, { "epoch": 0.34672563320672173, "grad_norm": 6.4619011878967285, "learning_rate": 6.934352560749442e-06, "loss": 0.7117, "step": 58330 }, { "epoch": 0.3467850752833901, "grad_norm": 5.189659595489502, "learning_rate": 6.935541395216131e-06, "loss": 0.6955, "step": 58340 }, { "epoch": 0.3468445173600585, "grad_norm": 7.158729553222656, "learning_rate": 6.93673022968282e-06, "loss": 0.6923, "step": 58350 }, { "epoch": 0.34690395943672686, "grad_norm": 9.01844596862793, "learning_rate": 6.937919064149509e-06, "loss": 0.7079, "step": 58360 }, { "epoch": 0.3469634015133953, "grad_norm": 7.415041923522949, "learning_rate": 6.939107898616198e-06, "loss": 0.6905, "step": 58370 }, { "epoch": 0.3470228435900637, "grad_norm": 9.48447322845459, "learning_rate": 6.940296733082887e-06, "loss": 0.7318, "step": 58380 }, { "epoch": 0.34708228566673205, "grad_norm": 7.185640811920166, "learning_rate": 6.9414855675495755e-06, "loss": 0.7544, "step": 58390 }, { "epoch": 0.34714172774340046, "grad_norm": 6.853324890136719, "learning_rate": 6.942674402016264e-06, "loss": 0.7092, "step": 58400 }, { "epoch": 0.3472011698200688, "grad_norm": 8.33914566040039, "learning_rate": 6.9438632364829525e-06, "loss": 0.6788, "step": 58410 }, { "epoch": 0.34726061189673724, "grad_norm": 8.564101219177246, "learning_rate": 6.9450520709496415e-06, "loss": 0.7056, "step": 58420 }, { "epoch": 0.3473200539734056, "grad_norm": 7.009925842285156, "learning_rate": 6.94624090541633e-06, "loss": 0.7009, "step": 58430 }, { "epoch": 0.347379496050074, "grad_norm": 7.231043815612793, "learning_rate": 6.947429739883019e-06, "loss": 0.6729, "step": 58440 }, { "epoch": 0.34743893812674237, "grad_norm": 8.531400680541992, "learning_rate": 6.948618574349708e-06, "loss": 0.6758, "step": 58450 }, { "epoch": 0.3474983802034108, "grad_norm": 8.601822853088379, "learning_rate": 6.949807408816397e-06, "loss": 0.6308, "step": 58460 }, { "epoch": 0.3475578222800792, "grad_norm": 7.814830780029297, "learning_rate": 6.950996243283086e-06, "loss": 0.572, "step": 58470 }, { "epoch": 0.34761726435674756, "grad_norm": 8.364737510681152, "learning_rate": 6.952185077749774e-06, "loss": 0.6174, "step": 58480 }, { "epoch": 0.34767670643341597, "grad_norm": 8.739397048950195, "learning_rate": 6.953373912216463e-06, "loss": 0.6241, "step": 58490 }, { "epoch": 0.34773614851008433, "grad_norm": 12.82900619506836, "learning_rate": 6.954562746683152e-06, "loss": 0.6616, "step": 58500 }, { "epoch": 0.34779559058675275, "grad_norm": 7.963827133178711, "learning_rate": 6.955751581149841e-06, "loss": 0.7387, "step": 58510 }, { "epoch": 0.3478550326634211, "grad_norm": 8.005260467529297, "learning_rate": 6.95694041561653e-06, "loss": 0.6792, "step": 58520 }, { "epoch": 0.3479144747400895, "grad_norm": 6.886417865753174, "learning_rate": 6.958129250083219e-06, "loss": 0.6517, "step": 58530 }, { "epoch": 0.34797391681675793, "grad_norm": 6.6159515380859375, "learning_rate": 6.959318084549908e-06, "loss": 0.6975, "step": 58540 }, { "epoch": 0.3480333588934263, "grad_norm": 8.73597526550293, "learning_rate": 6.960506919016597e-06, "loss": 0.6805, "step": 58550 }, { "epoch": 0.3480928009700947, "grad_norm": 6.184619426727295, "learning_rate": 6.961695753483286e-06, "loss": 0.6429, "step": 58560 }, { "epoch": 0.34815224304676307, "grad_norm": 7.560014724731445, "learning_rate": 6.962884587949974e-06, "loss": 0.7185, "step": 58570 }, { "epoch": 0.3482116851234315, "grad_norm": 7.206940174102783, "learning_rate": 6.964073422416663e-06, "loss": 0.6686, "step": 58580 }, { "epoch": 0.34827112720009984, "grad_norm": 7.197397708892822, "learning_rate": 6.9652622568833515e-06, "loss": 0.6447, "step": 58590 }, { "epoch": 0.34833056927676825, "grad_norm": 8.15577220916748, "learning_rate": 6.9664510913500405e-06, "loss": 0.6624, "step": 58600 }, { "epoch": 0.34839001135343667, "grad_norm": 6.0893964767456055, "learning_rate": 6.967639925816729e-06, "loss": 0.6274, "step": 58610 }, { "epoch": 0.348449453430105, "grad_norm": 9.76128101348877, "learning_rate": 6.968828760283419e-06, "loss": 0.652, "step": 58620 }, { "epoch": 0.34850889550677344, "grad_norm": 7.376707553863525, "learning_rate": 6.970017594750108e-06, "loss": 0.6217, "step": 58630 }, { "epoch": 0.3485683375834418, "grad_norm": 6.991664886474609, "learning_rate": 6.971206429216797e-06, "loss": 0.688, "step": 58640 }, { "epoch": 0.3486277796601102, "grad_norm": 8.432703971862793, "learning_rate": 6.972395263683486e-06, "loss": 0.6632, "step": 58650 }, { "epoch": 0.3486872217367786, "grad_norm": 8.098828315734863, "learning_rate": 6.973584098150175e-06, "loss": 0.7167, "step": 58660 }, { "epoch": 0.348746663813447, "grad_norm": 6.624015808105469, "learning_rate": 6.974772932616864e-06, "loss": 0.6487, "step": 58670 }, { "epoch": 0.3488061058901154, "grad_norm": 9.376477241516113, "learning_rate": 6.975961767083552e-06, "loss": 0.6828, "step": 58680 }, { "epoch": 0.34886554796678376, "grad_norm": 7.016996383666992, "learning_rate": 6.977150601550241e-06, "loss": 0.6755, "step": 58690 }, { "epoch": 0.3489249900434522, "grad_norm": 5.4415717124938965, "learning_rate": 6.97833943601693e-06, "loss": 0.6659, "step": 58700 }, { "epoch": 0.34898443212012054, "grad_norm": 10.30411434173584, "learning_rate": 6.979528270483619e-06, "loss": 0.6685, "step": 58710 }, { "epoch": 0.34904387419678895, "grad_norm": 7.0569915771484375, "learning_rate": 6.980717104950308e-06, "loss": 0.6503, "step": 58720 }, { "epoch": 0.3491033162734573, "grad_norm": 6.304102897644043, "learning_rate": 6.9819059394169965e-06, "loss": 0.6841, "step": 58730 }, { "epoch": 0.3491627583501257, "grad_norm": 6.386341094970703, "learning_rate": 6.9830947738836854e-06, "loss": 0.6586, "step": 58740 }, { "epoch": 0.34922220042679414, "grad_norm": 5.490294933319092, "learning_rate": 6.984283608350374e-06, "loss": 0.7142, "step": 58750 }, { "epoch": 0.3492816425034625, "grad_norm": 8.20820140838623, "learning_rate": 6.9854724428170624e-06, "loss": 0.6744, "step": 58760 }, { "epoch": 0.3493410845801309, "grad_norm": 7.548982620239258, "learning_rate": 6.986661277283751e-06, "loss": 0.645, "step": 58770 }, { "epoch": 0.34940052665679927, "grad_norm": 7.079231262207031, "learning_rate": 6.98785011175044e-06, "loss": 0.726, "step": 58780 }, { "epoch": 0.3494599687334677, "grad_norm": 7.480058193206787, "learning_rate": 6.989038946217129e-06, "loss": 0.6852, "step": 58790 }, { "epoch": 0.34951941081013604, "grad_norm": 7.788693904876709, "learning_rate": 6.990227780683818e-06, "loss": 0.7129, "step": 58800 }, { "epoch": 0.34957885288680446, "grad_norm": 6.687897205352783, "learning_rate": 6.991416615150507e-06, "loss": 0.683, "step": 58810 }, { "epoch": 0.3496382949634728, "grad_norm": 7.253815174102783, "learning_rate": 6.992605449617196e-06, "loss": 0.6544, "step": 58820 }, { "epoch": 0.34969773704014123, "grad_norm": 6.459000110626221, "learning_rate": 6.993794284083885e-06, "loss": 0.6998, "step": 58830 }, { "epoch": 0.34975717911680965, "grad_norm": 7.737158298492432, "learning_rate": 6.994983118550574e-06, "loss": 0.635, "step": 58840 }, { "epoch": 0.349816621193478, "grad_norm": 7.3884758949279785, "learning_rate": 6.996171953017262e-06, "loss": 0.6667, "step": 58850 }, { "epoch": 0.3498760632701464, "grad_norm": 8.07961654663086, "learning_rate": 6.997360787483951e-06, "loss": 0.7175, "step": 58860 }, { "epoch": 0.3499355053468148, "grad_norm": 6.873500347137451, "learning_rate": 6.99854962195064e-06, "loss": 0.7222, "step": 58870 }, { "epoch": 0.3499949474234832, "grad_norm": 6.20527458190918, "learning_rate": 6.999738456417329e-06, "loss": 0.6854, "step": 58880 }, { "epoch": 0.35005438950015155, "grad_norm": 7.801220417022705, "learning_rate": 7.000927290884018e-06, "loss": 0.6835, "step": 58890 }, { "epoch": 0.35011383157681997, "grad_norm": 9.12128734588623, "learning_rate": 7.0021161253507066e-06, "loss": 0.6663, "step": 58900 }, { "epoch": 0.3501732736534884, "grad_norm": 7.828243732452393, "learning_rate": 7.0033049598173955e-06, "loss": 0.7065, "step": 58910 }, { "epoch": 0.35023271573015674, "grad_norm": 4.455307483673096, "learning_rate": 7.0044937942840844e-06, "loss": 0.6002, "step": 58920 }, { "epoch": 0.35029215780682516, "grad_norm": 6.450066089630127, "learning_rate": 7.0056826287507725e-06, "loss": 0.647, "step": 58930 }, { "epoch": 0.3503515998834935, "grad_norm": 5.339776039123535, "learning_rate": 7.0068714632174614e-06, "loss": 0.6897, "step": 58940 }, { "epoch": 0.35041104196016193, "grad_norm": 7.102275371551514, "learning_rate": 7.00806029768415e-06, "loss": 0.7036, "step": 58950 }, { "epoch": 0.3504704840368303, "grad_norm": 6.068695068359375, "learning_rate": 7.009249132150839e-06, "loss": 0.6749, "step": 58960 }, { "epoch": 0.3505299261134987, "grad_norm": 5.9515886306762695, "learning_rate": 7.010437966617529e-06, "loss": 0.6317, "step": 58970 }, { "epoch": 0.3505893681901671, "grad_norm": 6.7322845458984375, "learning_rate": 7.011626801084218e-06, "loss": 0.689, "step": 58980 }, { "epoch": 0.3506488102668355, "grad_norm": 6.191427707672119, "learning_rate": 7.012815635550907e-06, "loss": 0.67, "step": 58990 }, { "epoch": 0.3507082523435039, "grad_norm": 6.848652362823486, "learning_rate": 7.014004470017596e-06, "loss": 0.6579, "step": 59000 }, { "epoch": 0.35076769442017225, "grad_norm": 7.7055559158325195, "learning_rate": 7.015193304484285e-06, "loss": 0.6568, "step": 59010 }, { "epoch": 0.35082713649684066, "grad_norm": 6.614133834838867, "learning_rate": 7.016382138950974e-06, "loss": 0.6681, "step": 59020 }, { "epoch": 0.350886578573509, "grad_norm": 7.15792989730835, "learning_rate": 7.017570973417663e-06, "loss": 0.626, "step": 59030 }, { "epoch": 0.35094602065017744, "grad_norm": 6.603055953979492, "learning_rate": 7.018759807884351e-06, "loss": 0.7395, "step": 59040 }, { "epoch": 0.35100546272684585, "grad_norm": 5.854493618011475, "learning_rate": 7.01994864235104e-06, "loss": 0.6514, "step": 59050 }, { "epoch": 0.3510649048035142, "grad_norm": 7.089650630950928, "learning_rate": 7.0211374768177286e-06, "loss": 0.686, "step": 59060 }, { "epoch": 0.3511243468801826, "grad_norm": 8.944235801696777, "learning_rate": 7.0223263112844175e-06, "loss": 0.6685, "step": 59070 }, { "epoch": 0.351183788956851, "grad_norm": 7.198959827423096, "learning_rate": 7.023515145751106e-06, "loss": 0.6624, "step": 59080 }, { "epoch": 0.3512432310335194, "grad_norm": 7.047282695770264, "learning_rate": 7.024703980217795e-06, "loss": 0.6961, "step": 59090 }, { "epoch": 0.35130267311018776, "grad_norm": 7.9083991050720215, "learning_rate": 7.025892814684484e-06, "loss": 0.6557, "step": 59100 }, { "epoch": 0.35136211518685617, "grad_norm": 5.955259323120117, "learning_rate": 7.027081649151173e-06, "loss": 0.6712, "step": 59110 }, { "epoch": 0.35142155726352453, "grad_norm": 7.25373649597168, "learning_rate": 7.028270483617861e-06, "loss": 0.6521, "step": 59120 }, { "epoch": 0.35148099934019295, "grad_norm": 6.459040641784668, "learning_rate": 7.02945931808455e-06, "loss": 0.6602, "step": 59130 }, { "epoch": 0.35154044141686136, "grad_norm": 6.917877674102783, "learning_rate": 7.030648152551239e-06, "loss": 0.6504, "step": 59140 }, { "epoch": 0.3515998834935297, "grad_norm": 7.578078746795654, "learning_rate": 7.031836987017928e-06, "loss": 0.6486, "step": 59150 }, { "epoch": 0.35165932557019813, "grad_norm": 7.484202861785889, "learning_rate": 7.033025821484617e-06, "loss": 0.644, "step": 59160 }, { "epoch": 0.3517187676468665, "grad_norm": 7.939330577850342, "learning_rate": 7.034214655951306e-06, "loss": 0.705, "step": 59170 }, { "epoch": 0.3517782097235349, "grad_norm": 7.669501304626465, "learning_rate": 7.035403490417995e-06, "loss": 0.7048, "step": 59180 }, { "epoch": 0.35183765180020327, "grad_norm": 6.785141468048096, "learning_rate": 7.036592324884684e-06, "loss": 0.6142, "step": 59190 }, { "epoch": 0.3518970938768717, "grad_norm": 6.255385398864746, "learning_rate": 7.037781159351373e-06, "loss": 0.6584, "step": 59200 }, { "epoch": 0.3519565359535401, "grad_norm": 7.408738613128662, "learning_rate": 7.038969993818061e-06, "loss": 0.667, "step": 59210 }, { "epoch": 0.35201597803020845, "grad_norm": 6.512973308563232, "learning_rate": 7.04015882828475e-06, "loss": 0.683, "step": 59220 }, { "epoch": 0.35207542010687687, "grad_norm": 6.146213054656982, "learning_rate": 7.041347662751439e-06, "loss": 0.7167, "step": 59230 }, { "epoch": 0.3521348621835452, "grad_norm": 8.71969985961914, "learning_rate": 7.0425364972181276e-06, "loss": 0.7195, "step": 59240 }, { "epoch": 0.35219430426021364, "grad_norm": 8.303421020507812, "learning_rate": 7.0437253316848165e-06, "loss": 0.7255, "step": 59250 }, { "epoch": 0.352253746336882, "grad_norm": 6.551144599914551, "learning_rate": 7.044914166151505e-06, "loss": 0.6253, "step": 59260 }, { "epoch": 0.3523131884135504, "grad_norm": 7.556514739990234, "learning_rate": 7.046103000618194e-06, "loss": 0.6607, "step": 59270 }, { "epoch": 0.35237263049021883, "grad_norm": 8.446005821228027, "learning_rate": 7.047291835084883e-06, "loss": 0.6642, "step": 59280 }, { "epoch": 0.3524320725668872, "grad_norm": 8.692310333251953, "learning_rate": 7.048480669551571e-06, "loss": 0.6621, "step": 59290 }, { "epoch": 0.3524915146435556, "grad_norm": 7.0807929039001465, "learning_rate": 7.04966950401826e-06, "loss": 0.648, "step": 59300 }, { "epoch": 0.35255095672022396, "grad_norm": 7.961857795715332, "learning_rate": 7.050858338484949e-06, "loss": 0.7278, "step": 59310 }, { "epoch": 0.3526103987968924, "grad_norm": 6.65981912612915, "learning_rate": 7.052047172951639e-06, "loss": 0.6904, "step": 59320 }, { "epoch": 0.35266984087356074, "grad_norm": 9.098088264465332, "learning_rate": 7.053236007418328e-06, "loss": 0.6782, "step": 59330 }, { "epoch": 0.35272928295022915, "grad_norm": 6.284566879272461, "learning_rate": 7.054424841885017e-06, "loss": 0.6739, "step": 59340 }, { "epoch": 0.35278872502689756, "grad_norm": 6.583765029907227, "learning_rate": 7.055613676351706e-06, "loss": 0.6666, "step": 59350 }, { "epoch": 0.3528481671035659, "grad_norm": 8.145833969116211, "learning_rate": 7.056802510818395e-06, "loss": 0.664, "step": 59360 }, { "epoch": 0.35290760918023434, "grad_norm": 9.07191276550293, "learning_rate": 7.057991345285084e-06, "loss": 0.6704, "step": 59370 }, { "epoch": 0.3529670512569027, "grad_norm": 7.8821940422058105, "learning_rate": 7.0591801797517725e-06, "loss": 0.6155, "step": 59380 }, { "epoch": 0.3530264933335711, "grad_norm": 6.237671375274658, "learning_rate": 7.0603690142184615e-06, "loss": 0.6462, "step": 59390 }, { "epoch": 0.35308593541023947, "grad_norm": 6.76324462890625, "learning_rate": 7.0615578486851496e-06, "loss": 0.6785, "step": 59400 }, { "epoch": 0.3531453774869079, "grad_norm": 8.867293357849121, "learning_rate": 7.0627466831518385e-06, "loss": 0.7109, "step": 59410 }, { "epoch": 0.3532048195635763, "grad_norm": 6.916703224182129, "learning_rate": 7.063935517618527e-06, "loss": 0.6497, "step": 59420 }, { "epoch": 0.35326426164024466, "grad_norm": 7.527314186096191, "learning_rate": 7.065124352085216e-06, "loss": 0.6557, "step": 59430 }, { "epoch": 0.3533237037169131, "grad_norm": 6.365954875946045, "learning_rate": 7.066313186551905e-06, "loss": 0.6958, "step": 59440 }, { "epoch": 0.35338314579358143, "grad_norm": 7.4872212409973145, "learning_rate": 7.067502021018594e-06, "loss": 0.6357, "step": 59450 }, { "epoch": 0.35344258787024985, "grad_norm": 5.504444122314453, "learning_rate": 7.068690855485283e-06, "loss": 0.7287, "step": 59460 }, { "epoch": 0.3535020299469182, "grad_norm": 5.07773494720459, "learning_rate": 7.069879689951972e-06, "loss": 0.6937, "step": 59470 }, { "epoch": 0.3535614720235866, "grad_norm": 9.143431663513184, "learning_rate": 7.07106852441866e-06, "loss": 0.6358, "step": 59480 }, { "epoch": 0.353620914100255, "grad_norm": 6.837437629699707, "learning_rate": 7.072257358885349e-06, "loss": 0.6874, "step": 59490 }, { "epoch": 0.3536803561769234, "grad_norm": 7.466889381408691, "learning_rate": 7.073446193352038e-06, "loss": 0.694, "step": 59500 }, { "epoch": 0.3537397982535918, "grad_norm": 8.304865837097168, "learning_rate": 7.074635027818727e-06, "loss": 0.6909, "step": 59510 }, { "epoch": 0.35379924033026017, "grad_norm": 6.502818584442139, "learning_rate": 7.075823862285416e-06, "loss": 0.6844, "step": 59520 }, { "epoch": 0.3538586824069286, "grad_norm": 7.134632587432861, "learning_rate": 7.077012696752105e-06, "loss": 0.6852, "step": 59530 }, { "epoch": 0.35391812448359694, "grad_norm": 6.686942100524902, "learning_rate": 7.078201531218794e-06, "loss": 0.6048, "step": 59540 }, { "epoch": 0.35397756656026536, "grad_norm": 7.215157985687256, "learning_rate": 7.079390365685483e-06, "loss": 0.6918, "step": 59550 }, { "epoch": 0.3540370086369337, "grad_norm": 8.677751541137695, "learning_rate": 7.0805792001521715e-06, "loss": 0.7141, "step": 59560 }, { "epoch": 0.35409645071360213, "grad_norm": 7.075430393218994, "learning_rate": 7.08176803461886e-06, "loss": 0.7411, "step": 59570 }, { "epoch": 0.35415589279027054, "grad_norm": 5.998088359832764, "learning_rate": 7.0829568690855485e-06, "loss": 0.6753, "step": 59580 }, { "epoch": 0.3542153348669389, "grad_norm": 6.116525650024414, "learning_rate": 7.0841457035522375e-06, "loss": 0.7421, "step": 59590 }, { "epoch": 0.3542747769436073, "grad_norm": 8.541250228881836, "learning_rate": 7.085334538018926e-06, "loss": 0.6212, "step": 59600 }, { "epoch": 0.3543342190202757, "grad_norm": 6.835093021392822, "learning_rate": 7.086523372485615e-06, "loss": 0.64, "step": 59610 }, { "epoch": 0.3543936610969441, "grad_norm": 6.9139251708984375, "learning_rate": 7.087712206952304e-06, "loss": 0.6276, "step": 59620 }, { "epoch": 0.35445310317361245, "grad_norm": 8.488981246948242, "learning_rate": 7.088901041418993e-06, "loss": 0.6749, "step": 59630 }, { "epoch": 0.35451254525028086, "grad_norm": 7.946937084197998, "learning_rate": 7.090089875885682e-06, "loss": 0.6947, "step": 59640 }, { "epoch": 0.3545719873269493, "grad_norm": 6.385880470275879, "learning_rate": 7.09127871035237e-06, "loss": 0.6245, "step": 59650 }, { "epoch": 0.35463142940361764, "grad_norm": 7.301753520965576, "learning_rate": 7.092467544819061e-06, "loss": 0.7094, "step": 59660 }, { "epoch": 0.35469087148028605, "grad_norm": 6.710920333862305, "learning_rate": 7.09365637928575e-06, "loss": 0.6343, "step": 59670 }, { "epoch": 0.3547503135569544, "grad_norm": 6.462040424346924, "learning_rate": 7.094845213752438e-06, "loss": 0.6509, "step": 59680 }, { "epoch": 0.3548097556336228, "grad_norm": 9.46875, "learning_rate": 7.096034048219127e-06, "loss": 0.6935, "step": 59690 }, { "epoch": 0.3548691977102912, "grad_norm": 7.74576473236084, "learning_rate": 7.097222882685816e-06, "loss": 0.6779, "step": 59700 }, { "epoch": 0.3549286397869596, "grad_norm": 6.043257236480713, "learning_rate": 7.098411717152505e-06, "loss": 0.674, "step": 59710 }, { "epoch": 0.354988081863628, "grad_norm": 7.577503204345703, "learning_rate": 7.0996005516191935e-06, "loss": 0.6549, "step": 59720 }, { "epoch": 0.3550475239402964, "grad_norm": 6.920313835144043, "learning_rate": 7.1007893860858825e-06, "loss": 0.6929, "step": 59730 }, { "epoch": 0.3551069660169648, "grad_norm": 6.420840740203857, "learning_rate": 7.101978220552571e-06, "loss": 0.6681, "step": 59740 }, { "epoch": 0.35516640809363315, "grad_norm": 6.6951727867126465, "learning_rate": 7.10316705501926e-06, "loss": 0.6989, "step": 59750 }, { "epoch": 0.35522585017030156, "grad_norm": 9.028219223022461, "learning_rate": 7.104355889485948e-06, "loss": 0.6874, "step": 59760 }, { "epoch": 0.3552852922469699, "grad_norm": 7.479817867279053, "learning_rate": 7.105544723952637e-06, "loss": 0.6524, "step": 59770 }, { "epoch": 0.35534473432363833, "grad_norm": 6.656954288482666, "learning_rate": 7.106733558419326e-06, "loss": 0.6378, "step": 59780 }, { "epoch": 0.35540417640030675, "grad_norm": 5.559581756591797, "learning_rate": 7.107922392886015e-06, "loss": 0.6685, "step": 59790 }, { "epoch": 0.3554636184769751, "grad_norm": 7.817626953125, "learning_rate": 7.109111227352704e-06, "loss": 0.6601, "step": 59800 }, { "epoch": 0.3555230605536435, "grad_norm": 6.632432460784912, "learning_rate": 7.110300061819393e-06, "loss": 0.6343, "step": 59810 }, { "epoch": 0.3555825026303119, "grad_norm": 10.714292526245117, "learning_rate": 7.111488896286082e-06, "loss": 0.6976, "step": 59820 }, { "epoch": 0.3556419447069803, "grad_norm": 6.321791172027588, "learning_rate": 7.112677730752771e-06, "loss": 0.6547, "step": 59830 }, { "epoch": 0.35570138678364865, "grad_norm": 7.475124835968018, "learning_rate": 7.11386656521946e-06, "loss": 0.6816, "step": 59840 }, { "epoch": 0.35576082886031707, "grad_norm": 6.984487056732178, "learning_rate": 7.115055399686148e-06, "loss": 0.706, "step": 59850 }, { "epoch": 0.3558202709369854, "grad_norm": 7.59009313583374, "learning_rate": 7.116244234152837e-06, "loss": 0.7082, "step": 59860 }, { "epoch": 0.35587971301365384, "grad_norm": 7.726337909698486, "learning_rate": 7.117433068619526e-06, "loss": 0.6756, "step": 59870 }, { "epoch": 0.35593915509032226, "grad_norm": 7.111377716064453, "learning_rate": 7.118621903086215e-06, "loss": 0.6881, "step": 59880 }, { "epoch": 0.3559985971669906, "grad_norm": 6.557517051696777, "learning_rate": 7.119810737552904e-06, "loss": 0.62, "step": 59890 }, { "epoch": 0.35605803924365903, "grad_norm": 6.834316730499268, "learning_rate": 7.1209995720195925e-06, "loss": 0.6982, "step": 59900 }, { "epoch": 0.3561174813203274, "grad_norm": 7.1802754402160645, "learning_rate": 7.1221884064862815e-06, "loss": 0.666, "step": 59910 }, { "epoch": 0.3561769233969958, "grad_norm": 7.515376567840576, "learning_rate": 7.12337724095297e-06, "loss": 0.6761, "step": 59920 }, { "epoch": 0.35623636547366416, "grad_norm": 7.677549362182617, "learning_rate": 7.1245660754196585e-06, "loss": 0.6851, "step": 59930 }, { "epoch": 0.3562958075503326, "grad_norm": 7.439283847808838, "learning_rate": 7.125754909886347e-06, "loss": 0.6313, "step": 59940 }, { "epoch": 0.356355249627001, "grad_norm": 5.8570556640625, "learning_rate": 7.126943744353036e-06, "loss": 0.6952, "step": 59950 }, { "epoch": 0.35641469170366935, "grad_norm": 8.054023742675781, "learning_rate": 7.128132578819725e-06, "loss": 0.7406, "step": 59960 }, { "epoch": 0.35647413378033777, "grad_norm": 9.164702415466309, "learning_rate": 7.129321413286414e-06, "loss": 0.6954, "step": 59970 }, { "epoch": 0.3565335758570061, "grad_norm": 9.001582145690918, "learning_rate": 7.130510247753103e-06, "loss": 0.616, "step": 59980 }, { "epoch": 0.35659301793367454, "grad_norm": 7.098996639251709, "learning_rate": 7.131699082219792e-06, "loss": 0.7223, "step": 59990 }, { "epoch": 0.3566524600103429, "grad_norm": 7.132050037384033, "learning_rate": 7.132887916686481e-06, "loss": 0.6843, "step": 60000 }, { "epoch": 0.3567119020870113, "grad_norm": 6.2727556228637695, "learning_rate": 7.134076751153171e-06, "loss": 0.6597, "step": 60010 }, { "epoch": 0.3567713441636797, "grad_norm": 7.003865718841553, "learning_rate": 7.13526558561986e-06, "loss": 0.6504, "step": 60020 }, { "epoch": 0.3568307862403481, "grad_norm": 9.272538185119629, "learning_rate": 7.136454420086549e-06, "loss": 0.6708, "step": 60030 }, { "epoch": 0.3568902283170165, "grad_norm": 6.441112041473389, "learning_rate": 7.137643254553237e-06, "loss": 0.655, "step": 60040 }, { "epoch": 0.35694967039368486, "grad_norm": 8.163422584533691, "learning_rate": 7.138832089019926e-06, "loss": 0.6466, "step": 60050 }, { "epoch": 0.3570091124703533, "grad_norm": 7.194360256195068, "learning_rate": 7.1400209234866145e-06, "loss": 0.6144, "step": 60060 }, { "epoch": 0.35706855454702163, "grad_norm": 7.097851276397705, "learning_rate": 7.1412097579533034e-06, "loss": 0.694, "step": 60070 }, { "epoch": 0.35712799662369005, "grad_norm": 8.685938835144043, "learning_rate": 7.142398592419992e-06, "loss": 0.6483, "step": 60080 }, { "epoch": 0.35718743870035846, "grad_norm": 5.482404708862305, "learning_rate": 7.143587426886681e-06, "loss": 0.6655, "step": 60090 }, { "epoch": 0.3572468807770268, "grad_norm": 7.16487455368042, "learning_rate": 7.14477626135337e-06, "loss": 0.6508, "step": 60100 }, { "epoch": 0.35730632285369524, "grad_norm": 6.110315799713135, "learning_rate": 7.145965095820059e-06, "loss": 0.7231, "step": 60110 }, { "epoch": 0.3573657649303636, "grad_norm": 6.821094512939453, "learning_rate": 7.147153930286747e-06, "loss": 0.6569, "step": 60120 }, { "epoch": 0.357425207007032, "grad_norm": 6.677943229675293, "learning_rate": 7.148342764753436e-06, "loss": 0.6641, "step": 60130 }, { "epoch": 0.35748464908370037, "grad_norm": 7.231551170349121, "learning_rate": 7.149531599220125e-06, "loss": 0.695, "step": 60140 }, { "epoch": 0.3575440911603688, "grad_norm": 6.194827079772949, "learning_rate": 7.150720433686814e-06, "loss": 0.6416, "step": 60150 }, { "epoch": 0.3576035332370372, "grad_norm": 8.057914733886719, "learning_rate": 7.151909268153503e-06, "loss": 0.6545, "step": 60160 }, { "epoch": 0.35766297531370556, "grad_norm": 7.918520927429199, "learning_rate": 7.153098102620192e-06, "loss": 0.6789, "step": 60170 }, { "epoch": 0.35772241739037397, "grad_norm": 7.6095733642578125, "learning_rate": 7.154286937086881e-06, "loss": 0.6928, "step": 60180 }, { "epoch": 0.35778185946704233, "grad_norm": 5.9186930656433105, "learning_rate": 7.15547577155357e-06, "loss": 0.6506, "step": 60190 }, { "epoch": 0.35784130154371074, "grad_norm": 7.916441440582275, "learning_rate": 7.156664606020259e-06, "loss": 0.7593, "step": 60200 }, { "epoch": 0.3579007436203791, "grad_norm": 6.37631893157959, "learning_rate": 7.157853440486947e-06, "loss": 0.6272, "step": 60210 }, { "epoch": 0.3579601856970475, "grad_norm": 6.946138858795166, "learning_rate": 7.159042274953636e-06, "loss": 0.7182, "step": 60220 }, { "epoch": 0.3580196277737159, "grad_norm": 7.894063472747803, "learning_rate": 7.160231109420325e-06, "loss": 0.7402, "step": 60230 }, { "epoch": 0.3580790698503843, "grad_norm": 6.885450839996338, "learning_rate": 7.1614199438870135e-06, "loss": 0.6217, "step": 60240 }, { "epoch": 0.3581385119270527, "grad_norm": 6.002718448638916, "learning_rate": 7.1626087783537024e-06, "loss": 0.7065, "step": 60250 }, { "epoch": 0.35819795400372106, "grad_norm": 7.385887622833252, "learning_rate": 7.163797612820391e-06, "loss": 0.6475, "step": 60260 }, { "epoch": 0.3582573960803895, "grad_norm": 6.203579902648926, "learning_rate": 7.16498644728708e-06, "loss": 0.7192, "step": 60270 }, { "epoch": 0.35831683815705784, "grad_norm": 7.868098258972168, "learning_rate": 7.166175281753769e-06, "loss": 0.6958, "step": 60280 }, { "epoch": 0.35837628023372625, "grad_norm": 6.428063869476318, "learning_rate": 7.167364116220457e-06, "loss": 0.6732, "step": 60290 }, { "epoch": 0.3584357223103946, "grad_norm": 6.573486804962158, "learning_rate": 7.168552950687146e-06, "loss": 0.6229, "step": 60300 }, { "epoch": 0.358495164387063, "grad_norm": 6.593954086303711, "learning_rate": 7.169741785153835e-06, "loss": 0.679, "step": 60310 }, { "epoch": 0.35855460646373144, "grad_norm": 8.011434555053711, "learning_rate": 7.170930619620524e-06, "loss": 0.7007, "step": 60320 }, { "epoch": 0.3586140485403998, "grad_norm": 5.19580078125, "learning_rate": 7.172119454087213e-06, "loss": 0.6317, "step": 60330 }, { "epoch": 0.3586734906170682, "grad_norm": 7.86259651184082, "learning_rate": 7.173308288553902e-06, "loss": 0.6526, "step": 60340 }, { "epoch": 0.3587329326937366, "grad_norm": 8.800312995910645, "learning_rate": 7.174497123020591e-06, "loss": 0.6327, "step": 60350 }, { "epoch": 0.358792374770405, "grad_norm": 6.302817344665527, "learning_rate": 7.175685957487281e-06, "loss": 0.6791, "step": 60360 }, { "epoch": 0.35885181684707335, "grad_norm": 7.0393853187561035, "learning_rate": 7.1768747919539696e-06, "loss": 0.682, "step": 60370 }, { "epoch": 0.35891125892374176, "grad_norm": 5.837539196014404, "learning_rate": 7.1780636264206585e-06, "loss": 0.6888, "step": 60380 }, { "epoch": 0.3589707010004102, "grad_norm": 7.263901710510254, "learning_rate": 7.1792524608873474e-06, "loss": 0.7377, "step": 60390 }, { "epoch": 0.35903014307707853, "grad_norm": 6.537192344665527, "learning_rate": 7.1804412953540355e-06, "loss": 0.613, "step": 60400 }, { "epoch": 0.35908958515374695, "grad_norm": 6.953106880187988, "learning_rate": 7.1816301298207244e-06, "loss": 0.6756, "step": 60410 }, { "epoch": 0.3591490272304153, "grad_norm": 6.444104194641113, "learning_rate": 7.182818964287413e-06, "loss": 0.6361, "step": 60420 }, { "epoch": 0.3592084693070837, "grad_norm": 8.363810539245605, "learning_rate": 7.184007798754102e-06, "loss": 0.6319, "step": 60430 }, { "epoch": 0.3592679113837521, "grad_norm": 7.290626049041748, "learning_rate": 7.185196633220791e-06, "loss": 0.6169, "step": 60440 }, { "epoch": 0.3593273534604205, "grad_norm": 5.774276256561279, "learning_rate": 7.18638546768748e-06, "loss": 0.6597, "step": 60450 }, { "epoch": 0.3593867955370889, "grad_norm": 8.763481140136719, "learning_rate": 7.187574302154169e-06, "loss": 0.6746, "step": 60460 }, { "epoch": 0.35944623761375727, "grad_norm": 6.1514997482299805, "learning_rate": 7.188763136620858e-06, "loss": 0.7281, "step": 60470 }, { "epoch": 0.3595056796904257, "grad_norm": 8.528721809387207, "learning_rate": 7.189951971087546e-06, "loss": 0.6922, "step": 60480 }, { "epoch": 0.35956512176709404, "grad_norm": 6.7550554275512695, "learning_rate": 7.191140805554235e-06, "loss": 0.6874, "step": 60490 }, { "epoch": 0.35962456384376246, "grad_norm": 9.021811485290527, "learning_rate": 7.192329640020924e-06, "loss": 0.6664, "step": 60500 }, { "epoch": 0.3596840059204308, "grad_norm": 6.811624050140381, "learning_rate": 7.193518474487613e-06, "loss": 0.6566, "step": 60510 }, { "epoch": 0.35974344799709923, "grad_norm": 8.44073486328125, "learning_rate": 7.194707308954302e-06, "loss": 0.6804, "step": 60520 }, { "epoch": 0.3598028900737676, "grad_norm": 6.356027603149414, "learning_rate": 7.195896143420991e-06, "loss": 0.6984, "step": 60530 }, { "epoch": 0.359862332150436, "grad_norm": 5.929091453552246, "learning_rate": 7.19708497788768e-06, "loss": 0.6827, "step": 60540 }, { "epoch": 0.3599217742271044, "grad_norm": 8.364922523498535, "learning_rate": 7.1982738123543686e-06, "loss": 0.6562, "step": 60550 }, { "epoch": 0.3599812163037728, "grad_norm": 8.426825523376465, "learning_rate": 7.1994626468210575e-06, "loss": 0.7532, "step": 60560 }, { "epoch": 0.3600406583804412, "grad_norm": 7.2133283615112305, "learning_rate": 7.2006514812877456e-06, "loss": 0.7288, "step": 60570 }, { "epoch": 0.36010010045710955, "grad_norm": 6.337513446807861, "learning_rate": 7.2018403157544345e-06, "loss": 0.6641, "step": 60580 }, { "epoch": 0.36015954253377797, "grad_norm": 6.479971408843994, "learning_rate": 7.2030291502211234e-06, "loss": 0.7187, "step": 60590 }, { "epoch": 0.3602189846104463, "grad_norm": 6.877072334289551, "learning_rate": 7.204217984687812e-06, "loss": 0.672, "step": 60600 }, { "epoch": 0.36027842668711474, "grad_norm": 6.895296573638916, "learning_rate": 7.205406819154501e-06, "loss": 0.6279, "step": 60610 }, { "epoch": 0.36033786876378315, "grad_norm": 6.204087257385254, "learning_rate": 7.20659565362119e-06, "loss": 0.662, "step": 60620 }, { "epoch": 0.3603973108404515, "grad_norm": 11.854084014892578, "learning_rate": 7.207784488087879e-06, "loss": 0.6841, "step": 60630 }, { "epoch": 0.3604567529171199, "grad_norm": 7.617619037628174, "learning_rate": 7.208973322554568e-06, "loss": 0.656, "step": 60640 }, { "epoch": 0.3605161949937883, "grad_norm": 6.292283058166504, "learning_rate": 7.210162157021256e-06, "loss": 0.6589, "step": 60650 }, { "epoch": 0.3605756370704567, "grad_norm": 5.841055393218994, "learning_rate": 7.211350991487945e-06, "loss": 0.6425, "step": 60660 }, { "epoch": 0.36063507914712506, "grad_norm": 6.009586334228516, "learning_rate": 7.212539825954634e-06, "loss": 0.626, "step": 60670 }, { "epoch": 0.3606945212237935, "grad_norm": 10.024130821228027, "learning_rate": 7.213728660421323e-06, "loss": 0.6898, "step": 60680 }, { "epoch": 0.3607539633004619, "grad_norm": 8.57839584350586, "learning_rate": 7.214917494888012e-06, "loss": 0.717, "step": 60690 }, { "epoch": 0.36081340537713025, "grad_norm": 8.179291725158691, "learning_rate": 7.216106329354702e-06, "loss": 0.7339, "step": 60700 }, { "epoch": 0.36087284745379866, "grad_norm": 7.732719898223877, "learning_rate": 7.2172951638213906e-06, "loss": 0.6559, "step": 60710 }, { "epoch": 0.360932289530467, "grad_norm": 6.012283802032471, "learning_rate": 7.2184839982880795e-06, "loss": 0.5913, "step": 60720 }, { "epoch": 0.36099173160713544, "grad_norm": 8.118945121765137, "learning_rate": 7.219672832754768e-06, "loss": 0.6363, "step": 60730 }, { "epoch": 0.3610511736838038, "grad_norm": 7.453428268432617, "learning_rate": 7.220861667221457e-06, "loss": 0.649, "step": 60740 }, { "epoch": 0.3611106157604722, "grad_norm": 5.046575546264648, "learning_rate": 7.222050501688146e-06, "loss": 0.6278, "step": 60750 }, { "epoch": 0.3611700578371406, "grad_norm": 7.3713483810424805, "learning_rate": 7.223239336154834e-06, "loss": 0.683, "step": 60760 }, { "epoch": 0.361229499913809, "grad_norm": 6.782461643218994, "learning_rate": 7.224428170621523e-06, "loss": 0.666, "step": 60770 }, { "epoch": 0.3612889419904774, "grad_norm": 7.919223308563232, "learning_rate": 7.225617005088212e-06, "loss": 0.6652, "step": 60780 }, { "epoch": 0.36134838406714576, "grad_norm": 6.011120319366455, "learning_rate": 7.226805839554901e-06, "loss": 0.6542, "step": 60790 }, { "epoch": 0.36140782614381417, "grad_norm": 7.276324272155762, "learning_rate": 7.22799467402159e-06, "loss": 0.6862, "step": 60800 }, { "epoch": 0.36146726822048253, "grad_norm": 7.141219139099121, "learning_rate": 7.229183508488279e-06, "loss": 0.616, "step": 60810 }, { "epoch": 0.36152671029715094, "grad_norm": 6.029600620269775, "learning_rate": 7.230372342954968e-06, "loss": 0.7051, "step": 60820 }, { "epoch": 0.36158615237381936, "grad_norm": 7.330658912658691, "learning_rate": 7.231561177421657e-06, "loss": 0.6848, "step": 60830 }, { "epoch": 0.3616455944504877, "grad_norm": 6.469597339630127, "learning_rate": 7.232750011888346e-06, "loss": 0.7034, "step": 60840 }, { "epoch": 0.36170503652715613, "grad_norm": 6.7671613693237305, "learning_rate": 7.233938846355034e-06, "loss": 0.6774, "step": 60850 }, { "epoch": 0.3617644786038245, "grad_norm": 6.622925281524658, "learning_rate": 7.235127680821723e-06, "loss": 0.6718, "step": 60860 }, { "epoch": 0.3618239206804929, "grad_norm": 7.960891246795654, "learning_rate": 7.236316515288412e-06, "loss": 0.633, "step": 60870 }, { "epoch": 0.36188336275716126, "grad_norm": 7.463769435882568, "learning_rate": 7.237505349755101e-06, "loss": 0.6776, "step": 60880 }, { "epoch": 0.3619428048338297, "grad_norm": 6.758595943450928, "learning_rate": 7.2386941842217896e-06, "loss": 0.6609, "step": 60890 }, { "epoch": 0.36200224691049804, "grad_norm": 6.355757236480713, "learning_rate": 7.2398830186884785e-06, "loss": 0.6492, "step": 60900 }, { "epoch": 0.36206168898716645, "grad_norm": 7.176692008972168, "learning_rate": 7.241071853155167e-06, "loss": 0.7111, "step": 60910 }, { "epoch": 0.36212113106383487, "grad_norm": 5.881647109985352, "learning_rate": 7.242260687621856e-06, "loss": 0.6502, "step": 60920 }, { "epoch": 0.3621805731405032, "grad_norm": 9.261960983276367, "learning_rate": 7.243449522088544e-06, "loss": 0.7491, "step": 60930 }, { "epoch": 0.36224001521717164, "grad_norm": 9.441330909729004, "learning_rate": 7.244638356555233e-06, "loss": 0.7179, "step": 60940 }, { "epoch": 0.36229945729384, "grad_norm": 6.28530740737915, "learning_rate": 7.245827191021922e-06, "loss": 0.6396, "step": 60950 }, { "epoch": 0.3623588993705084, "grad_norm": 7.011582374572754, "learning_rate": 7.247016025488611e-06, "loss": 0.6996, "step": 60960 }, { "epoch": 0.3624183414471768, "grad_norm": 7.889839172363281, "learning_rate": 7.2482048599553e-06, "loss": 0.7432, "step": 60970 }, { "epoch": 0.3624777835238452, "grad_norm": 7.363003253936768, "learning_rate": 7.249393694421989e-06, "loss": 0.6912, "step": 60980 }, { "epoch": 0.3625372256005136, "grad_norm": 7.088108539581299, "learning_rate": 7.250582528888678e-06, "loss": 0.7324, "step": 60990 }, { "epoch": 0.36259666767718196, "grad_norm": 7.08341646194458, "learning_rate": 7.251771363355367e-06, "loss": 0.6151, "step": 61000 }, { "epoch": 0.3626561097538504, "grad_norm": 7.180142402648926, "learning_rate": 7.252960197822055e-06, "loss": 0.6487, "step": 61010 }, { "epoch": 0.36271555183051873, "grad_norm": 8.099591255187988, "learning_rate": 7.254149032288744e-06, "loss": 0.6474, "step": 61020 }, { "epoch": 0.36277499390718715, "grad_norm": 6.811564922332764, "learning_rate": 7.255337866755433e-06, "loss": 0.7447, "step": 61030 }, { "epoch": 0.3628344359838555, "grad_norm": 6.699242115020752, "learning_rate": 7.256526701222122e-06, "loss": 0.6243, "step": 61040 }, { "epoch": 0.3628938780605239, "grad_norm": 7.620849609375, "learning_rate": 7.2577155356888115e-06, "loss": 0.6329, "step": 61050 }, { "epoch": 0.36295332013719234, "grad_norm": 8.817030906677246, "learning_rate": 7.2589043701555005e-06, "loss": 0.7479, "step": 61060 }, { "epoch": 0.3630127622138607, "grad_norm": 6.773131847381592, "learning_rate": 7.260093204622189e-06, "loss": 0.6541, "step": 61070 }, { "epoch": 0.3630722042905291, "grad_norm": 6.540299892425537, "learning_rate": 7.261282039088878e-06, "loss": 0.6542, "step": 61080 }, { "epoch": 0.36313164636719747, "grad_norm": 6.558642864227295, "learning_rate": 7.262470873555567e-06, "loss": 0.6439, "step": 61090 }, { "epoch": 0.3631910884438659, "grad_norm": 4.837015628814697, "learning_rate": 7.263659708022256e-06, "loss": 0.7237, "step": 61100 }, { "epoch": 0.36325053052053424, "grad_norm": 7.592412948608398, "learning_rate": 7.264848542488945e-06, "loss": 0.6633, "step": 61110 }, { "epoch": 0.36330997259720266, "grad_norm": 7.968875885009766, "learning_rate": 7.266037376955633e-06, "loss": 0.7006, "step": 61120 }, { "epoch": 0.36336941467387107, "grad_norm": 8.219648361206055, "learning_rate": 7.267226211422322e-06, "loss": 0.6834, "step": 61130 }, { "epoch": 0.36342885675053943, "grad_norm": 6.6546406745910645, "learning_rate": 7.268415045889011e-06, "loss": 0.6521, "step": 61140 }, { "epoch": 0.36348829882720785, "grad_norm": 8.72294807434082, "learning_rate": 7.2696038803557e-06, "loss": 0.6944, "step": 61150 }, { "epoch": 0.3635477409038762, "grad_norm": 9.06756591796875, "learning_rate": 7.270792714822389e-06, "loss": 0.6963, "step": 61160 }, { "epoch": 0.3636071829805446, "grad_norm": 6.77645206451416, "learning_rate": 7.271981549289078e-06, "loss": 0.6536, "step": 61170 }, { "epoch": 0.363666625057213, "grad_norm": 5.9604973793029785, "learning_rate": 7.273170383755767e-06, "loss": 0.6388, "step": 61180 }, { "epoch": 0.3637260671338814, "grad_norm": 8.526357650756836, "learning_rate": 7.274359218222456e-06, "loss": 0.7246, "step": 61190 }, { "epoch": 0.3637855092105498, "grad_norm": 6.9035210609436035, "learning_rate": 7.275548052689145e-06, "loss": 0.6622, "step": 61200 }, { "epoch": 0.36384495128721817, "grad_norm": 6.689362049102783, "learning_rate": 7.276736887155833e-06, "loss": 0.6808, "step": 61210 }, { "epoch": 0.3639043933638866, "grad_norm": 5.785634994506836, "learning_rate": 7.277925721622522e-06, "loss": 0.6841, "step": 61220 }, { "epoch": 0.36396383544055494, "grad_norm": 6.930198669433594, "learning_rate": 7.2791145560892105e-06, "loss": 0.7431, "step": 61230 }, { "epoch": 0.36402327751722335, "grad_norm": 7.552850723266602, "learning_rate": 7.2803033905558995e-06, "loss": 0.6982, "step": 61240 }, { "epoch": 0.3640827195938917, "grad_norm": 5.782651901245117, "learning_rate": 7.281492225022588e-06, "loss": 0.625, "step": 61250 }, { "epoch": 0.3641421616705601, "grad_norm": 7.402403831481934, "learning_rate": 7.282681059489277e-06, "loss": 0.642, "step": 61260 }, { "epoch": 0.3642016037472285, "grad_norm": 5.921965599060059, "learning_rate": 7.283869893955966e-06, "loss": 0.6895, "step": 61270 }, { "epoch": 0.3642610458238969, "grad_norm": 8.771703720092773, "learning_rate": 7.285058728422655e-06, "loss": 0.7094, "step": 61280 }, { "epoch": 0.3643204879005653, "grad_norm": 5.911479473114014, "learning_rate": 7.286247562889343e-06, "loss": 0.6921, "step": 61290 }, { "epoch": 0.3643799299772337, "grad_norm": 8.450213432312012, "learning_rate": 7.287436397356032e-06, "loss": 0.629, "step": 61300 }, { "epoch": 0.3644393720539021, "grad_norm": 6.003356456756592, "learning_rate": 7.288625231822721e-06, "loss": 0.699, "step": 61310 }, { "epoch": 0.36449881413057045, "grad_norm": 6.6088666915893555, "learning_rate": 7.28981406628941e-06, "loss": 0.6779, "step": 61320 }, { "epoch": 0.36455825620723886, "grad_norm": 7.725157260894775, "learning_rate": 7.291002900756099e-06, "loss": 0.655, "step": 61330 }, { "epoch": 0.3646176982839072, "grad_norm": 5.961034774780273, "learning_rate": 7.292191735222788e-06, "loss": 0.647, "step": 61340 }, { "epoch": 0.36467714036057564, "grad_norm": 7.335671424865723, "learning_rate": 7.293380569689477e-06, "loss": 0.662, "step": 61350 }, { "epoch": 0.36473658243724405, "grad_norm": 5.525866985321045, "learning_rate": 7.294569404156166e-06, "loss": 0.6798, "step": 61360 }, { "epoch": 0.3647960245139124, "grad_norm": 7.021664619445801, "learning_rate": 7.295758238622855e-06, "loss": 0.6785, "step": 61370 }, { "epoch": 0.3648554665905808, "grad_norm": 7.6462297439575195, "learning_rate": 7.296947073089543e-06, "loss": 0.6727, "step": 61380 }, { "epoch": 0.3649149086672492, "grad_norm": 7.83948278427124, "learning_rate": 7.298135907556232e-06, "loss": 0.6914, "step": 61390 }, { "epoch": 0.3649743507439176, "grad_norm": 6.693809986114502, "learning_rate": 7.2993247420229215e-06, "loss": 0.6763, "step": 61400 }, { "epoch": 0.36503379282058596, "grad_norm": 8.750537872314453, "learning_rate": 7.30051357648961e-06, "loss": 0.664, "step": 61410 }, { "epoch": 0.36509323489725437, "grad_norm": 7.4083123207092285, "learning_rate": 7.301702410956299e-06, "loss": 0.6531, "step": 61420 }, { "epoch": 0.3651526769739228, "grad_norm": 5.46384859085083, "learning_rate": 7.302891245422988e-06, "loss": 0.6957, "step": 61430 }, { "epoch": 0.36521211905059114, "grad_norm": 5.340207576751709, "learning_rate": 7.304080079889677e-06, "loss": 0.6333, "step": 61440 }, { "epoch": 0.36527156112725956, "grad_norm": 5.781149864196777, "learning_rate": 7.305268914356366e-06, "loss": 0.6909, "step": 61450 }, { "epoch": 0.3653310032039279, "grad_norm": 6.701364994049072, "learning_rate": 7.306457748823055e-06, "loss": 0.6439, "step": 61460 }, { "epoch": 0.36539044528059633, "grad_norm": 6.859449863433838, "learning_rate": 7.307646583289744e-06, "loss": 0.6205, "step": 61470 }, { "epoch": 0.3654498873572647, "grad_norm": 6.209927082061768, "learning_rate": 7.308835417756433e-06, "loss": 0.665, "step": 61480 }, { "epoch": 0.3655093294339331, "grad_norm": 6.295090675354004, "learning_rate": 7.310024252223121e-06, "loss": 0.6905, "step": 61490 }, { "epoch": 0.3655687715106015, "grad_norm": 6.923551082611084, "learning_rate": 7.31121308668981e-06, "loss": 0.6721, "step": 61500 }, { "epoch": 0.3656282135872699, "grad_norm": 7.1628007888793945, "learning_rate": 7.312401921156499e-06, "loss": 0.6558, "step": 61510 }, { "epoch": 0.3656876556639383, "grad_norm": 8.94719123840332, "learning_rate": 7.313590755623188e-06, "loss": 0.6514, "step": 61520 }, { "epoch": 0.36574709774060665, "grad_norm": 6.477673053741455, "learning_rate": 7.314779590089877e-06, "loss": 0.6355, "step": 61530 }, { "epoch": 0.36580653981727507, "grad_norm": 8.378755569458008, "learning_rate": 7.315968424556566e-06, "loss": 0.64, "step": 61540 }, { "epoch": 0.3658659818939434, "grad_norm": 7.219935894012451, "learning_rate": 7.3171572590232545e-06, "loss": 0.657, "step": 61550 }, { "epoch": 0.36592542397061184, "grad_norm": 6.277156829833984, "learning_rate": 7.3183460934899434e-06, "loss": 0.6464, "step": 61560 }, { "epoch": 0.36598486604728026, "grad_norm": 6.077559471130371, "learning_rate": 7.3195349279566315e-06, "loss": 0.6511, "step": 61570 }, { "epoch": 0.3660443081239486, "grad_norm": 6.204452037811279, "learning_rate": 7.3207237624233205e-06, "loss": 0.6299, "step": 61580 }, { "epoch": 0.36610375020061703, "grad_norm": 6.517602920532227, "learning_rate": 7.321912596890009e-06, "loss": 0.6506, "step": 61590 }, { "epoch": 0.3661631922772854, "grad_norm": 7.266207218170166, "learning_rate": 7.323101431356698e-06, "loss": 0.6645, "step": 61600 }, { "epoch": 0.3662226343539538, "grad_norm": 5.82637882232666, "learning_rate": 7.324290265823387e-06, "loss": 0.6525, "step": 61610 }, { "epoch": 0.36628207643062216, "grad_norm": 6.942275047302246, "learning_rate": 7.325479100290076e-06, "loss": 0.6707, "step": 61620 }, { "epoch": 0.3663415185072906, "grad_norm": 5.809150695800781, "learning_rate": 7.326667934756765e-06, "loss": 0.6839, "step": 61630 }, { "epoch": 0.36640096058395893, "grad_norm": 8.574132919311523, "learning_rate": 7.327856769223454e-06, "loss": 0.6398, "step": 61640 }, { "epoch": 0.36646040266062735, "grad_norm": 7.7057294845581055, "learning_rate": 7.329045603690142e-06, "loss": 0.7195, "step": 61650 }, { "epoch": 0.36651984473729576, "grad_norm": 7.2409563064575195, "learning_rate": 7.330234438156831e-06, "loss": 0.6857, "step": 61660 }, { "epoch": 0.3665792868139641, "grad_norm": 8.014628410339355, "learning_rate": 7.33142327262352e-06, "loss": 0.6875, "step": 61670 }, { "epoch": 0.36663872889063254, "grad_norm": 5.160014629364014, "learning_rate": 7.332612107090209e-06, "loss": 0.689, "step": 61680 }, { "epoch": 0.3666981709673009, "grad_norm": 7.092066287994385, "learning_rate": 7.333800941556898e-06, "loss": 0.6612, "step": 61690 }, { "epoch": 0.3667576130439693, "grad_norm": 7.347506523132324, "learning_rate": 7.334989776023587e-06, "loss": 0.6939, "step": 61700 }, { "epoch": 0.36681705512063767, "grad_norm": 5.435917854309082, "learning_rate": 7.336178610490276e-06, "loss": 0.6796, "step": 61710 }, { "epoch": 0.3668764971973061, "grad_norm": 10.155716896057129, "learning_rate": 7.337367444956965e-06, "loss": 0.5923, "step": 61720 }, { "epoch": 0.3669359392739745, "grad_norm": 6.503073215484619, "learning_rate": 7.3385562794236535e-06, "loss": 0.6846, "step": 61730 }, { "epoch": 0.36699538135064286, "grad_norm": 5.6976542472839355, "learning_rate": 7.339745113890343e-06, "loss": 0.6833, "step": 61740 }, { "epoch": 0.36705482342731127, "grad_norm": 5.518984794616699, "learning_rate": 7.340933948357032e-06, "loss": 0.6119, "step": 61750 }, { "epoch": 0.36711426550397963, "grad_norm": 6.096558094024658, "learning_rate": 7.34212278282372e-06, "loss": 0.7074, "step": 61760 }, { "epoch": 0.36717370758064805, "grad_norm": 6.373722076416016, "learning_rate": 7.343311617290409e-06, "loss": 0.6551, "step": 61770 }, { "epoch": 0.3672331496573164, "grad_norm": 8.328110694885254, "learning_rate": 7.344500451757098e-06, "loss": 0.7223, "step": 61780 }, { "epoch": 0.3672925917339848, "grad_norm": 6.048532485961914, "learning_rate": 7.345689286223787e-06, "loss": 0.6393, "step": 61790 }, { "epoch": 0.36735203381065323, "grad_norm": 7.855030536651611, "learning_rate": 7.346878120690476e-06, "loss": 0.7191, "step": 61800 }, { "epoch": 0.3674114758873216, "grad_norm": 6.205132007598877, "learning_rate": 7.348066955157165e-06, "loss": 0.6492, "step": 61810 }, { "epoch": 0.36747091796399, "grad_norm": 6.561104774475098, "learning_rate": 7.349255789623854e-06, "loss": 0.6751, "step": 61820 }, { "epoch": 0.36753036004065837, "grad_norm": 9.547619819641113, "learning_rate": 7.350444624090543e-06, "loss": 0.6391, "step": 61830 }, { "epoch": 0.3675898021173268, "grad_norm": 6.315819263458252, "learning_rate": 7.351633458557232e-06, "loss": 0.6981, "step": 61840 }, { "epoch": 0.36764924419399514, "grad_norm": 7.584170341491699, "learning_rate": 7.35282229302392e-06, "loss": 0.6821, "step": 61850 }, { "epoch": 0.36770868627066355, "grad_norm": 6.427555561065674, "learning_rate": 7.354011127490609e-06, "loss": 0.6524, "step": 61860 }, { "epoch": 0.36776812834733197, "grad_norm": 6.10536003112793, "learning_rate": 7.355199961957298e-06, "loss": 0.6703, "step": 61870 }, { "epoch": 0.3678275704240003, "grad_norm": 7.985753059387207, "learning_rate": 7.356388796423987e-06, "loss": 0.7147, "step": 61880 }, { "epoch": 0.36788701250066874, "grad_norm": 6.946117877960205, "learning_rate": 7.3575776308906755e-06, "loss": 0.6806, "step": 61890 }, { "epoch": 0.3679464545773371, "grad_norm": 7.288563251495361, "learning_rate": 7.3587664653573644e-06, "loss": 0.712, "step": 61900 }, { "epoch": 0.3680058966540055, "grad_norm": 5.557861328125, "learning_rate": 7.359955299824053e-06, "loss": 0.6283, "step": 61910 }, { "epoch": 0.3680653387306739, "grad_norm": 6.3760199546813965, "learning_rate": 7.361144134290742e-06, "loss": 0.6864, "step": 61920 }, { "epoch": 0.3681247808073423, "grad_norm": 7.663755893707275, "learning_rate": 7.36233296875743e-06, "loss": 0.6925, "step": 61930 }, { "epoch": 0.3681842228840107, "grad_norm": 8.665730476379395, "learning_rate": 7.363521803224119e-06, "loss": 0.6823, "step": 61940 }, { "epoch": 0.36824366496067906, "grad_norm": 7.6086506843566895, "learning_rate": 7.364710637690808e-06, "loss": 0.6544, "step": 61950 }, { "epoch": 0.3683031070373475, "grad_norm": 6.146407127380371, "learning_rate": 7.365899472157497e-06, "loss": 0.6333, "step": 61960 }, { "epoch": 0.36836254911401584, "grad_norm": 7.9628753662109375, "learning_rate": 7.367088306624186e-06, "loss": 0.711, "step": 61970 }, { "epoch": 0.36842199119068425, "grad_norm": 7.600957870483398, "learning_rate": 7.368277141090875e-06, "loss": 0.6718, "step": 61980 }, { "epoch": 0.3684814332673526, "grad_norm": 7.369095802307129, "learning_rate": 7.369465975557564e-06, "loss": 0.7206, "step": 61990 }, { "epoch": 0.368540875344021, "grad_norm": 6.9215545654296875, "learning_rate": 7.370654810024253e-06, "loss": 0.6562, "step": 62000 }, { "epoch": 0.3686003174206894, "grad_norm": 6.110723972320557, "learning_rate": 7.371843644490941e-06, "loss": 0.6728, "step": 62010 }, { "epoch": 0.3686597594973578, "grad_norm": 5.913436412811279, "learning_rate": 7.37303247895763e-06, "loss": 0.6279, "step": 62020 }, { "epoch": 0.3687192015740262, "grad_norm": 4.9919819831848145, "learning_rate": 7.374221313424319e-06, "loss": 0.6919, "step": 62030 }, { "epoch": 0.36877864365069457, "grad_norm": 8.061366081237793, "learning_rate": 7.375410147891008e-06, "loss": 0.693, "step": 62040 }, { "epoch": 0.368838085727363, "grad_norm": 7.267429351806641, "learning_rate": 7.376598982357697e-06, "loss": 0.6807, "step": 62050 }, { "epoch": 0.36889752780403134, "grad_norm": 9.350224494934082, "learning_rate": 7.377787816824386e-06, "loss": 0.6487, "step": 62060 }, { "epoch": 0.36895696988069976, "grad_norm": 12.415308952331543, "learning_rate": 7.3789766512910745e-06, "loss": 0.7105, "step": 62070 }, { "epoch": 0.3690164119573681, "grad_norm": 5.8692450523376465, "learning_rate": 7.3801654857577634e-06, "loss": 0.7025, "step": 62080 }, { "epoch": 0.36907585403403653, "grad_norm": 8.826480865478516, "learning_rate": 7.381354320224453e-06, "loss": 0.6324, "step": 62090 }, { "epoch": 0.36913529611070495, "grad_norm": 7.022326469421387, "learning_rate": 7.382543154691142e-06, "loss": 0.6162, "step": 62100 }, { "epoch": 0.3691947381873733, "grad_norm": 7.569515705108643, "learning_rate": 7.383731989157831e-06, "loss": 0.6489, "step": 62110 }, { "epoch": 0.3692541802640417, "grad_norm": 7.597387313842773, "learning_rate": 7.384920823624519e-06, "loss": 0.7282, "step": 62120 }, { "epoch": 0.3693136223407101, "grad_norm": 6.02822208404541, "learning_rate": 7.386109658091208e-06, "loss": 0.6417, "step": 62130 }, { "epoch": 0.3693730644173785, "grad_norm": 6.7792534828186035, "learning_rate": 7.387298492557897e-06, "loss": 0.6435, "step": 62140 }, { "epoch": 0.36943250649404685, "grad_norm": 6.476219177246094, "learning_rate": 7.388487327024586e-06, "loss": 0.6629, "step": 62150 }, { "epoch": 0.36949194857071527, "grad_norm": 6.026455879211426, "learning_rate": 7.389676161491275e-06, "loss": 0.7141, "step": 62160 }, { "epoch": 0.3695513906473837, "grad_norm": 7.620339870452881, "learning_rate": 7.390864995957964e-06, "loss": 0.6394, "step": 62170 }, { "epoch": 0.36961083272405204, "grad_norm": 8.675995826721191, "learning_rate": 7.392053830424653e-06, "loss": 0.6586, "step": 62180 }, { "epoch": 0.36967027480072046, "grad_norm": 5.780959129333496, "learning_rate": 7.393242664891342e-06, "loss": 0.6069, "step": 62190 }, { "epoch": 0.3697297168773888, "grad_norm": 8.470986366271973, "learning_rate": 7.3944314993580306e-06, "loss": 0.6655, "step": 62200 }, { "epoch": 0.36978915895405723, "grad_norm": 6.9085869789123535, "learning_rate": 7.395620333824719e-06, "loss": 0.6992, "step": 62210 }, { "epoch": 0.3698486010307256, "grad_norm": 6.674558639526367, "learning_rate": 7.3968091682914076e-06, "loss": 0.6098, "step": 62220 }, { "epoch": 0.369908043107394, "grad_norm": 6.867491245269775, "learning_rate": 7.3979980027580965e-06, "loss": 0.679, "step": 62230 }, { "epoch": 0.3699674851840624, "grad_norm": 6.6378984451293945, "learning_rate": 7.399186837224785e-06, "loss": 0.7079, "step": 62240 }, { "epoch": 0.3700269272607308, "grad_norm": 9.719364166259766, "learning_rate": 7.400375671691474e-06, "loss": 0.7061, "step": 62250 }, { "epoch": 0.3700863693373992, "grad_norm": 6.383602619171143, "learning_rate": 7.401564506158163e-06, "loss": 0.673, "step": 62260 }, { "epoch": 0.37014581141406755, "grad_norm": 8.022258758544922, "learning_rate": 7.402753340624852e-06, "loss": 0.6541, "step": 62270 }, { "epoch": 0.37020525349073596, "grad_norm": 7.320321559906006, "learning_rate": 7.403942175091541e-06, "loss": 0.6488, "step": 62280 }, { "epoch": 0.3702646955674043, "grad_norm": 6.59034538269043, "learning_rate": 7.405131009558229e-06, "loss": 0.6859, "step": 62290 }, { "epoch": 0.37032413764407274, "grad_norm": 7.0362443923950195, "learning_rate": 7.406319844024918e-06, "loss": 0.7206, "step": 62300 }, { "epoch": 0.3703835797207411, "grad_norm": 7.705956935882568, "learning_rate": 7.407508678491607e-06, "loss": 0.6888, "step": 62310 }, { "epoch": 0.3704430217974095, "grad_norm": 6.080370903015137, "learning_rate": 7.408697512958296e-06, "loss": 0.6699, "step": 62320 }, { "epoch": 0.3705024638740779, "grad_norm": 6.712950706481934, "learning_rate": 7.409886347424985e-06, "loss": 0.6582, "step": 62330 }, { "epoch": 0.3705619059507463, "grad_norm": 6.5232744216918945, "learning_rate": 7.411075181891674e-06, "loss": 0.6086, "step": 62340 }, { "epoch": 0.3706213480274147, "grad_norm": 7.686833381652832, "learning_rate": 7.412264016358363e-06, "loss": 0.5947, "step": 62350 }, { "epoch": 0.37068079010408306, "grad_norm": 6.844560146331787, "learning_rate": 7.413452850825052e-06, "loss": 0.6674, "step": 62360 }, { "epoch": 0.37074023218075147, "grad_norm": 5.412622451782227, "learning_rate": 7.414641685291741e-06, "loss": 0.6382, "step": 62370 }, { "epoch": 0.37079967425741983, "grad_norm": 7.434873580932617, "learning_rate": 7.415830519758429e-06, "loss": 0.7164, "step": 62380 }, { "epoch": 0.37085911633408825, "grad_norm": 8.07301139831543, "learning_rate": 7.417019354225118e-06, "loss": 0.6865, "step": 62390 }, { "epoch": 0.37091855841075666, "grad_norm": 5.038872718811035, "learning_rate": 7.4182081886918066e-06, "loss": 0.7461, "step": 62400 }, { "epoch": 0.370978000487425, "grad_norm": 5.873074531555176, "learning_rate": 7.4193970231584955e-06, "loss": 0.6262, "step": 62410 }, { "epoch": 0.37103744256409343, "grad_norm": 5.685459136962891, "learning_rate": 7.420585857625184e-06, "loss": 0.6347, "step": 62420 }, { "epoch": 0.3710968846407618, "grad_norm": 6.885818958282471, "learning_rate": 7.421774692091874e-06, "loss": 0.7273, "step": 62430 }, { "epoch": 0.3711563267174302, "grad_norm": 7.850383758544922, "learning_rate": 7.422963526558563e-06, "loss": 0.7049, "step": 62440 }, { "epoch": 0.37121576879409857, "grad_norm": 7.70864200592041, "learning_rate": 7.424152361025252e-06, "loss": 0.6592, "step": 62450 }, { "epoch": 0.371275210870767, "grad_norm": 7.722525119781494, "learning_rate": 7.425341195491941e-06, "loss": 0.6928, "step": 62460 }, { "epoch": 0.3713346529474354, "grad_norm": 7.0593485832214355, "learning_rate": 7.42653002995863e-06, "loss": 0.6437, "step": 62470 }, { "epoch": 0.37139409502410375, "grad_norm": 8.218832015991211, "learning_rate": 7.427718864425319e-06, "loss": 0.6114, "step": 62480 }, { "epoch": 0.37145353710077217, "grad_norm": 6.955883502960205, "learning_rate": 7.428907698892007e-06, "loss": 0.6747, "step": 62490 }, { "epoch": 0.3715129791774405, "grad_norm": 8.65207290649414, "learning_rate": 7.430096533358696e-06, "loss": 0.689, "step": 62500 }, { "epoch": 0.37157242125410894, "grad_norm": 7.371278285980225, "learning_rate": 7.431285367825385e-06, "loss": 0.7078, "step": 62510 }, { "epoch": 0.3716318633307773, "grad_norm": 7.329126358032227, "learning_rate": 7.432474202292074e-06, "loss": 0.6299, "step": 62520 }, { "epoch": 0.3716913054074457, "grad_norm": 8.05182933807373, "learning_rate": 7.433663036758763e-06, "loss": 0.6534, "step": 62530 }, { "epoch": 0.37175074748411413, "grad_norm": 6.2591142654418945, "learning_rate": 7.4348518712254515e-06, "loss": 0.6504, "step": 62540 }, { "epoch": 0.3718101895607825, "grad_norm": 5.618216037750244, "learning_rate": 7.4360407056921405e-06, "loss": 0.635, "step": 62550 }, { "epoch": 0.3718696316374509, "grad_norm": 6.570060729980469, "learning_rate": 7.437229540158829e-06, "loss": 0.6964, "step": 62560 }, { "epoch": 0.37192907371411926, "grad_norm": 8.981861114501953, "learning_rate": 7.4384183746255175e-06, "loss": 0.714, "step": 62570 }, { "epoch": 0.3719885157907877, "grad_norm": 7.687071323394775, "learning_rate": 7.439607209092206e-06, "loss": 0.5995, "step": 62580 }, { "epoch": 0.37204795786745604, "grad_norm": 7.725870609283447, "learning_rate": 7.440796043558895e-06, "loss": 0.7096, "step": 62590 }, { "epoch": 0.37210739994412445, "grad_norm": 6.971829414367676, "learning_rate": 7.441984878025584e-06, "loss": 0.7118, "step": 62600 }, { "epoch": 0.37216684202079287, "grad_norm": 8.999492645263672, "learning_rate": 7.443173712492273e-06, "loss": 0.6521, "step": 62610 }, { "epoch": 0.3722262840974612, "grad_norm": 5.635056972503662, "learning_rate": 7.444362546958962e-06, "loss": 0.6574, "step": 62620 }, { "epoch": 0.37228572617412964, "grad_norm": 4.843135356903076, "learning_rate": 7.445551381425651e-06, "loss": 0.6684, "step": 62630 }, { "epoch": 0.372345168250798, "grad_norm": 6.3231306076049805, "learning_rate": 7.44674021589234e-06, "loss": 0.7161, "step": 62640 }, { "epoch": 0.3724046103274664, "grad_norm": 9.075636863708496, "learning_rate": 7.447929050359028e-06, "loss": 0.7083, "step": 62650 }, { "epoch": 0.37246405240413477, "grad_norm": 8.497537612915039, "learning_rate": 7.449117884825717e-06, "loss": 0.6491, "step": 62660 }, { "epoch": 0.3725234944808032, "grad_norm": 6.217485427856445, "learning_rate": 7.450306719292406e-06, "loss": 0.6672, "step": 62670 }, { "epoch": 0.37258293655747154, "grad_norm": 6.105146884918213, "learning_rate": 7.451495553759095e-06, "loss": 0.6172, "step": 62680 }, { "epoch": 0.37264237863413996, "grad_norm": 6.324077606201172, "learning_rate": 7.452684388225784e-06, "loss": 0.6518, "step": 62690 }, { "epoch": 0.3727018207108084, "grad_norm": 6.599857807159424, "learning_rate": 7.453873222692473e-06, "loss": 0.6083, "step": 62700 }, { "epoch": 0.37276126278747673, "grad_norm": 7.334114074707031, "learning_rate": 7.455062057159162e-06, "loss": 0.7156, "step": 62710 }, { "epoch": 0.37282070486414515, "grad_norm": 6.29185676574707, "learning_rate": 7.4562508916258505e-06, "loss": 0.6616, "step": 62720 }, { "epoch": 0.3728801469408135, "grad_norm": 9.26622200012207, "learning_rate": 7.4574397260925395e-06, "loss": 0.6731, "step": 62730 }, { "epoch": 0.3729395890174819, "grad_norm": 7.2524189949035645, "learning_rate": 7.4586285605592276e-06, "loss": 0.6751, "step": 62740 }, { "epoch": 0.3729990310941503, "grad_norm": 6.240423202514648, "learning_rate": 7.4598173950259165e-06, "loss": 0.6572, "step": 62750 }, { "epoch": 0.3730584731708187, "grad_norm": 7.8103437423706055, "learning_rate": 7.461006229492605e-06, "loss": 0.6921, "step": 62760 }, { "epoch": 0.3731179152474871, "grad_norm": 8.039277076721191, "learning_rate": 7.462195063959294e-06, "loss": 0.6282, "step": 62770 }, { "epoch": 0.37317735732415547, "grad_norm": 7.228726863861084, "learning_rate": 7.463383898425984e-06, "loss": 0.7138, "step": 62780 }, { "epoch": 0.3732367994008239, "grad_norm": 6.777085304260254, "learning_rate": 7.464572732892673e-06, "loss": 0.6605, "step": 62790 }, { "epoch": 0.37329624147749224, "grad_norm": 8.823535919189453, "learning_rate": 7.465761567359362e-06, "loss": 0.7326, "step": 62800 }, { "epoch": 0.37335568355416066, "grad_norm": 5.028769016265869, "learning_rate": 7.466950401826051e-06, "loss": 0.6393, "step": 62810 }, { "epoch": 0.373415125630829, "grad_norm": 6.717541217803955, "learning_rate": 7.46813923629274e-06, "loss": 0.7078, "step": 62820 }, { "epoch": 0.37347456770749743, "grad_norm": 9.568498611450195, "learning_rate": 7.469328070759429e-06, "loss": 0.6347, "step": 62830 }, { "epoch": 0.37353400978416584, "grad_norm": 8.142986297607422, "learning_rate": 7.470516905226118e-06, "loss": 0.6612, "step": 62840 }, { "epoch": 0.3735934518608342, "grad_norm": 7.399893283843994, "learning_rate": 7.471705739692806e-06, "loss": 0.6403, "step": 62850 }, { "epoch": 0.3736528939375026, "grad_norm": 7.042550086975098, "learning_rate": 7.472894574159495e-06, "loss": 0.6701, "step": 62860 }, { "epoch": 0.373712336014171, "grad_norm": 6.6819167137146, "learning_rate": 7.474083408626184e-06, "loss": 0.6883, "step": 62870 }, { "epoch": 0.3737717780908394, "grad_norm": 8.521492958068848, "learning_rate": 7.4752722430928725e-06, "loss": 0.6546, "step": 62880 }, { "epoch": 0.37383122016750775, "grad_norm": 6.619858264923096, "learning_rate": 7.4764610775595615e-06, "loss": 0.6483, "step": 62890 }, { "epoch": 0.37389066224417616, "grad_norm": 8.514763832092285, "learning_rate": 7.47764991202625e-06, "loss": 0.6612, "step": 62900 }, { "epoch": 0.3739501043208446, "grad_norm": 4.933910846710205, "learning_rate": 7.478838746492939e-06, "loss": 0.6369, "step": 62910 }, { "epoch": 0.37400954639751294, "grad_norm": 7.153903484344482, "learning_rate": 7.480027580959628e-06, "loss": 0.7641, "step": 62920 }, { "epoch": 0.37406898847418135, "grad_norm": 6.942675590515137, "learning_rate": 7.481216415426316e-06, "loss": 0.7089, "step": 62930 }, { "epoch": 0.3741284305508497, "grad_norm": 8.60743236541748, "learning_rate": 7.482405249893005e-06, "loss": 0.7075, "step": 62940 }, { "epoch": 0.3741878726275181, "grad_norm": 6.461180686950684, "learning_rate": 7.483594084359694e-06, "loss": 0.6341, "step": 62950 }, { "epoch": 0.3742473147041865, "grad_norm": 6.083613395690918, "learning_rate": 7.484782918826383e-06, "loss": 0.6353, "step": 62960 }, { "epoch": 0.3743067567808549, "grad_norm": 7.753663539886475, "learning_rate": 7.485971753293072e-06, "loss": 0.679, "step": 62970 }, { "epoch": 0.3743661988575233, "grad_norm": 8.193198204040527, "learning_rate": 7.487160587759761e-06, "loss": 0.6344, "step": 62980 }, { "epoch": 0.3744256409341917, "grad_norm": 6.782601833343506, "learning_rate": 7.48834942222645e-06, "loss": 0.673, "step": 62990 }, { "epoch": 0.3744850830108601, "grad_norm": 5.52543306350708, "learning_rate": 7.489538256693139e-06, "loss": 0.6742, "step": 63000 }, { "epoch": 0.37454452508752845, "grad_norm": 8.046936988830566, "learning_rate": 7.490727091159828e-06, "loss": 0.7169, "step": 63010 }, { "epoch": 0.37460396716419686, "grad_norm": 6.520707607269287, "learning_rate": 7.491915925626516e-06, "loss": 0.6818, "step": 63020 }, { "epoch": 0.3746634092408652, "grad_norm": 6.387032985687256, "learning_rate": 7.493104760093205e-06, "loss": 0.6975, "step": 63030 }, { "epoch": 0.37472285131753363, "grad_norm": 7.902590751647949, "learning_rate": 7.494293594559894e-06, "loss": 0.6189, "step": 63040 }, { "epoch": 0.374782293394202, "grad_norm": 6.55189847946167, "learning_rate": 7.495482429026583e-06, "loss": 0.6453, "step": 63050 }, { "epoch": 0.3748417354708704, "grad_norm": 7.052852153778076, "learning_rate": 7.4966712634932715e-06, "loss": 0.6648, "step": 63060 }, { "epoch": 0.3749011775475388, "grad_norm": 7.050893783569336, "learning_rate": 7.4978600979599605e-06, "loss": 0.7163, "step": 63070 }, { "epoch": 0.3749606196242072, "grad_norm": 7.441524505615234, "learning_rate": 7.499048932426649e-06, "loss": 0.6252, "step": 63080 }, { "epoch": 0.3750200617008756, "grad_norm": 7.977750778198242, "learning_rate": 7.500237766893338e-06, "loss": 0.6829, "step": 63090 }, { "epoch": 0.37507950377754395, "grad_norm": 5.19637393951416, "learning_rate": 7.501426601360026e-06, "loss": 0.6659, "step": 63100 }, { "epoch": 0.37513894585421237, "grad_norm": 5.305551052093506, "learning_rate": 7.502615435826715e-06, "loss": 0.669, "step": 63110 }, { "epoch": 0.37519838793088073, "grad_norm": 7.612033367156982, "learning_rate": 7.503804270293404e-06, "loss": 0.6431, "step": 63120 }, { "epoch": 0.37525783000754914, "grad_norm": 5.289547443389893, "learning_rate": 7.504993104760094e-06, "loss": 0.6196, "step": 63130 }, { "epoch": 0.37531727208421756, "grad_norm": 6.478472709655762, "learning_rate": 7.506181939226783e-06, "loss": 0.6396, "step": 63140 }, { "epoch": 0.3753767141608859, "grad_norm": 7.149261951446533, "learning_rate": 7.507370773693472e-06, "loss": 0.6286, "step": 63150 }, { "epoch": 0.37543615623755433, "grad_norm": 6.940727710723877, "learning_rate": 7.508559608160161e-06, "loss": 0.7366, "step": 63160 }, { "epoch": 0.3754955983142227, "grad_norm": 6.799251079559326, "learning_rate": 7.50974844262685e-06, "loss": 0.6721, "step": 63170 }, { "epoch": 0.3755550403908911, "grad_norm": 6.416903495788574, "learning_rate": 7.510937277093539e-06, "loss": 0.7104, "step": 63180 }, { "epoch": 0.37561448246755946, "grad_norm": 6.982035160064697, "learning_rate": 7.512126111560228e-06, "loss": 0.6909, "step": 63190 }, { "epoch": 0.3756739245442279, "grad_norm": 7.722108840942383, "learning_rate": 7.5133149460269165e-06, "loss": 0.6459, "step": 63200 }, { "epoch": 0.3757333666208963, "grad_norm": 6.138113021850586, "learning_rate": 7.514503780493605e-06, "loss": 0.6337, "step": 63210 }, { "epoch": 0.37579280869756465, "grad_norm": 5.644100666046143, "learning_rate": 7.5156926149602935e-06, "loss": 0.5807, "step": 63220 }, { "epoch": 0.37585225077423307, "grad_norm": 8.679364204406738, "learning_rate": 7.5168814494269824e-06, "loss": 0.6932, "step": 63230 }, { "epoch": 0.3759116928509014, "grad_norm": 7.299994945526123, "learning_rate": 7.518070283893671e-06, "loss": 0.6988, "step": 63240 }, { "epoch": 0.37597113492756984, "grad_norm": 6.852879524230957, "learning_rate": 7.51925911836036e-06, "loss": 0.6878, "step": 63250 }, { "epoch": 0.3760305770042382, "grad_norm": 6.0881733894348145, "learning_rate": 7.520447952827049e-06, "loss": 0.6185, "step": 63260 }, { "epoch": 0.3760900190809066, "grad_norm": 6.164853572845459, "learning_rate": 7.521636787293738e-06, "loss": 0.7414, "step": 63270 }, { "epoch": 0.376149461157575, "grad_norm": 5.5720367431640625, "learning_rate": 7.522825621760427e-06, "loss": 0.6577, "step": 63280 }, { "epoch": 0.3762089032342434, "grad_norm": 7.477311134338379, "learning_rate": 7.524014456227115e-06, "loss": 0.668, "step": 63290 }, { "epoch": 0.3762683453109118, "grad_norm": 6.070793151855469, "learning_rate": 7.525203290693804e-06, "loss": 0.6387, "step": 63300 }, { "epoch": 0.37632778738758016, "grad_norm": 8.580142974853516, "learning_rate": 7.526392125160493e-06, "loss": 0.6852, "step": 63310 }, { "epoch": 0.3763872294642486, "grad_norm": 6.8522210121154785, "learning_rate": 7.527580959627182e-06, "loss": 0.6792, "step": 63320 }, { "epoch": 0.37644667154091693, "grad_norm": 6.259378433227539, "learning_rate": 7.528769794093871e-06, "loss": 0.6655, "step": 63330 }, { "epoch": 0.37650611361758535, "grad_norm": 7.435727119445801, "learning_rate": 7.52995862856056e-06, "loss": 0.6765, "step": 63340 }, { "epoch": 0.37656555569425376, "grad_norm": 6.929378509521484, "learning_rate": 7.531147463027249e-06, "loss": 0.6684, "step": 63350 }, { "epoch": 0.3766249977709221, "grad_norm": 7.296632289886475, "learning_rate": 7.532336297493938e-06, "loss": 0.6882, "step": 63360 }, { "epoch": 0.37668443984759054, "grad_norm": 5.228114604949951, "learning_rate": 7.533525131960627e-06, "loss": 0.6553, "step": 63370 }, { "epoch": 0.3767438819242589, "grad_norm": 8.586894989013672, "learning_rate": 7.534713966427315e-06, "loss": 0.6757, "step": 63380 }, { "epoch": 0.3768033240009273, "grad_norm": 7.377218723297119, "learning_rate": 7.535902800894004e-06, "loss": 0.7063, "step": 63390 }, { "epoch": 0.37686276607759567, "grad_norm": 7.627302646636963, "learning_rate": 7.5370916353606925e-06, "loss": 0.6803, "step": 63400 }, { "epoch": 0.3769222081542641, "grad_norm": 7.5504584312438965, "learning_rate": 7.5382804698273814e-06, "loss": 0.6947, "step": 63410 }, { "epoch": 0.37698165023093244, "grad_norm": 6.605515003204346, "learning_rate": 7.53946930429407e-06, "loss": 0.6803, "step": 63420 }, { "epoch": 0.37704109230760086, "grad_norm": 8.019031524658203, "learning_rate": 7.540658138760759e-06, "loss": 0.7286, "step": 63430 }, { "epoch": 0.37710053438426927, "grad_norm": 7.405026435852051, "learning_rate": 7.541846973227448e-06, "loss": 0.6903, "step": 63440 }, { "epoch": 0.37715997646093763, "grad_norm": 7.631004810333252, "learning_rate": 7.543035807694137e-06, "loss": 0.6387, "step": 63450 }, { "epoch": 0.37721941853760604, "grad_norm": 7.895637035369873, "learning_rate": 7.544224642160825e-06, "loss": 0.6818, "step": 63460 }, { "epoch": 0.3772788606142744, "grad_norm": 7.539006233215332, "learning_rate": 7.545413476627516e-06, "loss": 0.7034, "step": 63470 }, { "epoch": 0.3773383026909428, "grad_norm": 6.723056793212891, "learning_rate": 7.546602311094205e-06, "loss": 0.6833, "step": 63480 }, { "epoch": 0.3773977447676112, "grad_norm": 7.108145236968994, "learning_rate": 7.547791145560893e-06, "loss": 0.7397, "step": 63490 }, { "epoch": 0.3774571868442796, "grad_norm": 6.300246238708496, "learning_rate": 7.548979980027582e-06, "loss": 0.6501, "step": 63500 }, { "epoch": 0.377516628920948, "grad_norm": 6.34375524520874, "learning_rate": 7.550168814494271e-06, "loss": 0.6552, "step": 63510 }, { "epoch": 0.37757607099761636, "grad_norm": 7.152360916137695, "learning_rate": 7.55135764896096e-06, "loss": 0.6205, "step": 63520 }, { "epoch": 0.3776355130742848, "grad_norm": 6.8140153884887695, "learning_rate": 7.5525464834276486e-06, "loss": 0.7242, "step": 63530 }, { "epoch": 0.37769495515095314, "grad_norm": 7.385557174682617, "learning_rate": 7.5537353178943375e-06, "loss": 0.6725, "step": 63540 }, { "epoch": 0.37775439722762155, "grad_norm": 7.713106155395508, "learning_rate": 7.5549241523610264e-06, "loss": 0.6392, "step": 63550 }, { "epoch": 0.3778138393042899, "grad_norm": 8.78921890258789, "learning_rate": 7.556112986827715e-06, "loss": 0.6794, "step": 63560 }, { "epoch": 0.3778732813809583, "grad_norm": 5.922053337097168, "learning_rate": 7.5573018212944034e-06, "loss": 0.6807, "step": 63570 }, { "epoch": 0.37793272345762674, "grad_norm": 7.366967678070068, "learning_rate": 7.558490655761092e-06, "loss": 0.6234, "step": 63580 }, { "epoch": 0.3779921655342951, "grad_norm": 7.051302433013916, "learning_rate": 7.559679490227781e-06, "loss": 0.6849, "step": 63590 }, { "epoch": 0.3780516076109635, "grad_norm": 8.05551815032959, "learning_rate": 7.56086832469447e-06, "loss": 0.6727, "step": 63600 }, { "epoch": 0.3781110496876319, "grad_norm": 7.3562235832214355, "learning_rate": 7.562057159161159e-06, "loss": 0.6676, "step": 63610 }, { "epoch": 0.3781704917643003, "grad_norm": 9.70752239227295, "learning_rate": 7.563245993627848e-06, "loss": 0.6767, "step": 63620 }, { "epoch": 0.37822993384096865, "grad_norm": 6.4405670166015625, "learning_rate": 7.564434828094537e-06, "loss": 0.6811, "step": 63630 }, { "epoch": 0.37828937591763706, "grad_norm": 5.918156147003174, "learning_rate": 7.565623662561226e-06, "loss": 0.6403, "step": 63640 }, { "epoch": 0.3783488179943055, "grad_norm": 7.428493499755859, "learning_rate": 7.566812497027914e-06, "loss": 0.64, "step": 63650 }, { "epoch": 0.37840826007097383, "grad_norm": 6.067039966583252, "learning_rate": 7.568001331494603e-06, "loss": 0.6461, "step": 63660 }, { "epoch": 0.37846770214764225, "grad_norm": 6.259022235870361, "learning_rate": 7.569190165961292e-06, "loss": 0.6023, "step": 63670 }, { "epoch": 0.3785271442243106, "grad_norm": 7.690794944763184, "learning_rate": 7.570379000427981e-06, "loss": 0.6373, "step": 63680 }, { "epoch": 0.378586586300979, "grad_norm": 6.701255798339844, "learning_rate": 7.57156783489467e-06, "loss": 0.7161, "step": 63690 }, { "epoch": 0.3786460283776474, "grad_norm": 8.702580451965332, "learning_rate": 7.572756669361359e-06, "loss": 0.682, "step": 63700 }, { "epoch": 0.3787054704543158, "grad_norm": 6.290747165679932, "learning_rate": 7.5739455038280476e-06, "loss": 0.6737, "step": 63710 }, { "epoch": 0.3787649125309842, "grad_norm": 8.772561073303223, "learning_rate": 7.5751343382947365e-06, "loss": 0.6724, "step": 63720 }, { "epoch": 0.37882435460765257, "grad_norm": 7.668498992919922, "learning_rate": 7.5763231727614254e-06, "loss": 0.7069, "step": 63730 }, { "epoch": 0.378883796684321, "grad_norm": 6.3880791664123535, "learning_rate": 7.5775120072281135e-06, "loss": 0.6741, "step": 63740 }, { "epoch": 0.37894323876098934, "grad_norm": 7.095588684082031, "learning_rate": 7.5787008416948024e-06, "loss": 0.6374, "step": 63750 }, { "epoch": 0.37900268083765776, "grad_norm": 6.8871870040893555, "learning_rate": 7.579889676161491e-06, "loss": 0.7043, "step": 63760 }, { "epoch": 0.3790621229143261, "grad_norm": 7.7423200607299805, "learning_rate": 7.58107851062818e-06, "loss": 0.7126, "step": 63770 }, { "epoch": 0.37912156499099453, "grad_norm": 6.46107292175293, "learning_rate": 7.582267345094869e-06, "loss": 0.6737, "step": 63780 }, { "epoch": 0.3791810070676629, "grad_norm": 6.975653171539307, "learning_rate": 7.583456179561558e-06, "loss": 0.6464, "step": 63790 }, { "epoch": 0.3792404491443313, "grad_norm": 8.21686840057373, "learning_rate": 7.584645014028247e-06, "loss": 0.6605, "step": 63800 }, { "epoch": 0.3792998912209997, "grad_norm": 6.56003475189209, "learning_rate": 7.585833848494936e-06, "loss": 0.7133, "step": 63810 }, { "epoch": 0.3793593332976681, "grad_norm": 6.732232093811035, "learning_rate": 7.587022682961626e-06, "loss": 0.7254, "step": 63820 }, { "epoch": 0.3794187753743365, "grad_norm": 5.094970703125, "learning_rate": 7.588211517428315e-06, "loss": 0.682, "step": 63830 }, { "epoch": 0.37947821745100485, "grad_norm": 5.302011966705322, "learning_rate": 7.589400351895004e-06, "loss": 0.7198, "step": 63840 }, { "epoch": 0.37953765952767327, "grad_norm": 8.879732131958008, "learning_rate": 7.590589186361692e-06, "loss": 0.752, "step": 63850 }, { "epoch": 0.3795971016043416, "grad_norm": 6.986988067626953, "learning_rate": 7.591778020828381e-06, "loss": 0.7051, "step": 63860 }, { "epoch": 0.37965654368101004, "grad_norm": 8.048441886901855, "learning_rate": 7.5929668552950696e-06, "loss": 0.6981, "step": 63870 }, { "epoch": 0.37971598575767845, "grad_norm": 7.778933525085449, "learning_rate": 7.5941556897617585e-06, "loss": 0.6996, "step": 63880 }, { "epoch": 0.3797754278343468, "grad_norm": 6.903643608093262, "learning_rate": 7.595344524228447e-06, "loss": 0.6578, "step": 63890 }, { "epoch": 0.3798348699110152, "grad_norm": 6.5580034255981445, "learning_rate": 7.596533358695136e-06, "loss": 0.7282, "step": 63900 }, { "epoch": 0.3798943119876836, "grad_norm": 7.201333522796631, "learning_rate": 7.597722193161825e-06, "loss": 0.66, "step": 63910 }, { "epoch": 0.379953754064352, "grad_norm": 7.034831523895264, "learning_rate": 7.598911027628514e-06, "loss": 0.6745, "step": 63920 }, { "epoch": 0.38001319614102036, "grad_norm": 7.5062384605407715, "learning_rate": 7.600099862095202e-06, "loss": 0.7022, "step": 63930 }, { "epoch": 0.3800726382176888, "grad_norm": 6.53004789352417, "learning_rate": 7.601288696561891e-06, "loss": 0.6123, "step": 63940 }, { "epoch": 0.3801320802943572, "grad_norm": 6.483151435852051, "learning_rate": 7.60247753102858e-06, "loss": 0.6484, "step": 63950 }, { "epoch": 0.38019152237102555, "grad_norm": 6.00191068649292, "learning_rate": 7.603666365495269e-06, "loss": 0.6405, "step": 63960 }, { "epoch": 0.38025096444769396, "grad_norm": 6.533327102661133, "learning_rate": 7.604855199961958e-06, "loss": 0.7298, "step": 63970 }, { "epoch": 0.3803104065243623, "grad_norm": 6.895530700683594, "learning_rate": 7.606044034428647e-06, "loss": 0.6246, "step": 63980 }, { "epoch": 0.38036984860103074, "grad_norm": 6.143913269042969, "learning_rate": 7.607232868895336e-06, "loss": 0.6921, "step": 63990 }, { "epoch": 0.3804292906776991, "grad_norm": 8.647001266479492, "learning_rate": 7.608421703362025e-06, "loss": 0.6785, "step": 64000 }, { "epoch": 0.3804887327543675, "grad_norm": 6.2790846824646, "learning_rate": 7.609610537828714e-06, "loss": 0.6736, "step": 64010 }, { "epoch": 0.3805481748310359, "grad_norm": 6.073958873748779, "learning_rate": 7.610799372295402e-06, "loss": 0.6459, "step": 64020 }, { "epoch": 0.3806076169077043, "grad_norm": 7.887350082397461, "learning_rate": 7.611988206762091e-06, "loss": 0.6705, "step": 64030 }, { "epoch": 0.3806670589843727, "grad_norm": 6.459274768829346, "learning_rate": 7.61317704122878e-06, "loss": 0.6679, "step": 64040 }, { "epoch": 0.38072650106104106, "grad_norm": 6.355174541473389, "learning_rate": 7.6143658756954686e-06, "loss": 0.6698, "step": 64050 }, { "epoch": 0.38078594313770947, "grad_norm": 7.581762790679932, "learning_rate": 7.6155547101621575e-06, "loss": 0.7016, "step": 64060 }, { "epoch": 0.38084538521437783, "grad_norm": 6.62344217300415, "learning_rate": 7.616743544628846e-06, "loss": 0.6534, "step": 64070 }, { "epoch": 0.38090482729104624, "grad_norm": 7.299133777618408, "learning_rate": 7.617932379095535e-06, "loss": 0.6793, "step": 64080 }, { "epoch": 0.3809642693677146, "grad_norm": 6.016238689422607, "learning_rate": 7.619121213562224e-06, "loss": 0.6249, "step": 64090 }, { "epoch": 0.381023711444383, "grad_norm": 6.436698913574219, "learning_rate": 7.620310048028912e-06, "loss": 0.7064, "step": 64100 }, { "epoch": 0.38108315352105143, "grad_norm": 5.936018466949463, "learning_rate": 7.621498882495601e-06, "loss": 0.6321, "step": 64110 }, { "epoch": 0.3811425955977198, "grad_norm": 8.386691093444824, "learning_rate": 7.62268771696229e-06, "loss": 0.6891, "step": 64120 }, { "epoch": 0.3812020376743882, "grad_norm": 8.195155143737793, "learning_rate": 7.623876551428979e-06, "loss": 0.7176, "step": 64130 }, { "epoch": 0.38126147975105656, "grad_norm": 7.043425559997559, "learning_rate": 7.625065385895668e-06, "loss": 0.6796, "step": 64140 }, { "epoch": 0.381320921827725, "grad_norm": 7.81962776184082, "learning_rate": 7.626254220362357e-06, "loss": 0.6886, "step": 64150 }, { "epoch": 0.38138036390439334, "grad_norm": 8.06002426147461, "learning_rate": 7.627443054829046e-06, "loss": 0.6573, "step": 64160 }, { "epoch": 0.38143980598106175, "grad_norm": 7.783552169799805, "learning_rate": 7.628631889295736e-06, "loss": 0.6958, "step": 64170 }, { "epoch": 0.38149924805773017, "grad_norm": 6.6984148025512695, "learning_rate": 7.629820723762424e-06, "loss": 0.6688, "step": 64180 }, { "epoch": 0.3815586901343985, "grad_norm": 6.188668251037598, "learning_rate": 7.631009558229114e-06, "loss": 0.6741, "step": 64190 }, { "epoch": 0.38161813221106694, "grad_norm": 7.06067419052124, "learning_rate": 7.632198392695802e-06, "loss": 0.6718, "step": 64200 }, { "epoch": 0.3816775742877353, "grad_norm": 6.4833455085754395, "learning_rate": 7.633387227162491e-06, "loss": 0.6857, "step": 64210 }, { "epoch": 0.3817370163644037, "grad_norm": 9.234427452087402, "learning_rate": 7.63457606162918e-06, "loss": 0.7509, "step": 64220 }, { "epoch": 0.3817964584410721, "grad_norm": 9.618196487426758, "learning_rate": 7.63576489609587e-06, "loss": 0.7198, "step": 64230 }, { "epoch": 0.3818559005177405, "grad_norm": 7.085322856903076, "learning_rate": 7.636953730562557e-06, "loss": 0.7123, "step": 64240 }, { "epoch": 0.3819153425944089, "grad_norm": 8.002376556396484, "learning_rate": 7.638142565029245e-06, "loss": 0.6377, "step": 64250 }, { "epoch": 0.38197478467107726, "grad_norm": 5.680410385131836, "learning_rate": 7.639331399495935e-06, "loss": 0.6661, "step": 64260 }, { "epoch": 0.3820342267477457, "grad_norm": 7.864584445953369, "learning_rate": 7.640520233962623e-06, "loss": 0.6391, "step": 64270 }, { "epoch": 0.38209366882441403, "grad_norm": 6.592117786407471, "learning_rate": 7.641709068429313e-06, "loss": 0.6786, "step": 64280 }, { "epoch": 0.38215311090108245, "grad_norm": 5.8193583488464355, "learning_rate": 7.642897902896001e-06, "loss": 0.6473, "step": 64290 }, { "epoch": 0.3822125529777508, "grad_norm": 6.997290134429932, "learning_rate": 7.644086737362691e-06, "loss": 0.6559, "step": 64300 }, { "epoch": 0.3822719950544192, "grad_norm": 7.506450176239014, "learning_rate": 7.645275571829379e-06, "loss": 0.6869, "step": 64310 }, { "epoch": 0.38233143713108764, "grad_norm": 8.117345809936523, "learning_rate": 7.646464406296069e-06, "loss": 0.6444, "step": 64320 }, { "epoch": 0.382390879207756, "grad_norm": 6.469443321228027, "learning_rate": 7.647653240762757e-06, "loss": 0.7651, "step": 64330 }, { "epoch": 0.3824503212844244, "grad_norm": 6.913247108459473, "learning_rate": 7.648842075229445e-06, "loss": 0.7225, "step": 64340 }, { "epoch": 0.38250976336109277, "grad_norm": 6.386889934539795, "learning_rate": 7.650030909696135e-06, "loss": 0.6889, "step": 64350 }, { "epoch": 0.3825692054377612, "grad_norm": 8.458029747009277, "learning_rate": 7.651219744162823e-06, "loss": 0.678, "step": 64360 }, { "epoch": 0.38262864751442954, "grad_norm": 7.7985968589782715, "learning_rate": 7.652408578629513e-06, "loss": 0.6625, "step": 64370 }, { "epoch": 0.38268808959109796, "grad_norm": 8.379363059997559, "learning_rate": 7.6535974130962e-06, "loss": 0.6988, "step": 64380 }, { "epoch": 0.38274753166776637, "grad_norm": 8.096495628356934, "learning_rate": 7.65478624756289e-06, "loss": 0.6938, "step": 64390 }, { "epoch": 0.38280697374443473, "grad_norm": 6.233551502227783, "learning_rate": 7.655975082029578e-06, "loss": 0.683, "step": 64400 }, { "epoch": 0.38286641582110315, "grad_norm": 5.514639377593994, "learning_rate": 7.657163916496268e-06, "loss": 0.6614, "step": 64410 }, { "epoch": 0.3829258578977715, "grad_norm": 7.830990791320801, "learning_rate": 7.658352750962956e-06, "loss": 0.6464, "step": 64420 }, { "epoch": 0.3829852999744399, "grad_norm": 7.18186092376709, "learning_rate": 7.659541585429644e-06, "loss": 0.597, "step": 64430 }, { "epoch": 0.3830447420511083, "grad_norm": 7.056440830230713, "learning_rate": 7.660730419896334e-06, "loss": 0.7152, "step": 64440 }, { "epoch": 0.3831041841277767, "grad_norm": 6.041445255279541, "learning_rate": 7.661919254363022e-06, "loss": 0.6413, "step": 64450 }, { "epoch": 0.38316362620444505, "grad_norm": 8.140332221984863, "learning_rate": 7.663108088829712e-06, "loss": 0.6696, "step": 64460 }, { "epoch": 0.38322306828111347, "grad_norm": 8.933276176452637, "learning_rate": 7.6642969232964e-06, "loss": 0.6838, "step": 64470 }, { "epoch": 0.3832825103577819, "grad_norm": 6.869129180908203, "learning_rate": 7.66548575776309e-06, "loss": 0.5779, "step": 64480 }, { "epoch": 0.38334195243445024, "grad_norm": 12.26811695098877, "learning_rate": 7.666674592229778e-06, "loss": 0.6718, "step": 64490 }, { "epoch": 0.38340139451111865, "grad_norm": 5.505508899688721, "learning_rate": 7.667863426696466e-06, "loss": 0.6509, "step": 64500 }, { "epoch": 0.383460836587787, "grad_norm": 7.905383110046387, "learning_rate": 7.669052261163158e-06, "loss": 0.6766, "step": 64510 }, { "epoch": 0.3835202786644554, "grad_norm": 7.896125793457031, "learning_rate": 7.670241095629846e-06, "loss": 0.697, "step": 64520 }, { "epoch": 0.3835797207411238, "grad_norm": 5.646209239959717, "learning_rate": 7.671429930096534e-06, "loss": 0.6417, "step": 64530 }, { "epoch": 0.3836391628177922, "grad_norm": 8.613846778869629, "learning_rate": 7.672618764563223e-06, "loss": 0.6968, "step": 64540 }, { "epoch": 0.3836986048944606, "grad_norm": 6.626773834228516, "learning_rate": 7.673807599029912e-06, "loss": 0.6692, "step": 64550 }, { "epoch": 0.383758046971129, "grad_norm": 9.563569068908691, "learning_rate": 7.674996433496601e-06, "loss": 0.6781, "step": 64560 }, { "epoch": 0.3838174890477974, "grad_norm": 8.376808166503906, "learning_rate": 7.67618526796329e-06, "loss": 0.6595, "step": 64570 }, { "epoch": 0.38387693112446575, "grad_norm": 6.383952617645264, "learning_rate": 7.67737410242998e-06, "loss": 0.6627, "step": 64580 }, { "epoch": 0.38393637320113416, "grad_norm": 8.932674407958984, "learning_rate": 7.678562936896667e-06, "loss": 0.6976, "step": 64590 }, { "epoch": 0.3839958152778025, "grad_norm": 8.554130554199219, "learning_rate": 7.679751771363357e-06, "loss": 0.684, "step": 64600 }, { "epoch": 0.38405525735447094, "grad_norm": 8.138982772827148, "learning_rate": 7.680940605830045e-06, "loss": 0.6344, "step": 64610 }, { "epoch": 0.38411469943113935, "grad_norm": 7.0900349617004395, "learning_rate": 7.682129440296733e-06, "loss": 0.6806, "step": 64620 }, { "epoch": 0.3841741415078077, "grad_norm": 8.10208511352539, "learning_rate": 7.683318274763423e-06, "loss": 0.6393, "step": 64630 }, { "epoch": 0.3842335835844761, "grad_norm": 7.820028305053711, "learning_rate": 7.684507109230111e-06, "loss": 0.6507, "step": 64640 }, { "epoch": 0.3842930256611445, "grad_norm": 6.502901554107666, "learning_rate": 7.6856959436968e-06, "loss": 0.6888, "step": 64650 }, { "epoch": 0.3843524677378129, "grad_norm": 7.317135810852051, "learning_rate": 7.686884778163489e-06, "loss": 0.6258, "step": 64660 }, { "epoch": 0.38441190981448126, "grad_norm": 6.9604597091674805, "learning_rate": 7.688073612630179e-06, "loss": 0.6462, "step": 64670 }, { "epoch": 0.38447135189114967, "grad_norm": 6.090808868408203, "learning_rate": 7.689262447096867e-06, "loss": 0.6937, "step": 64680 }, { "epoch": 0.3845307939678181, "grad_norm": 8.046893119812012, "learning_rate": 7.690451281563557e-06, "loss": 0.689, "step": 64690 }, { "epoch": 0.38459023604448644, "grad_norm": 7.670743465423584, "learning_rate": 7.691640116030245e-06, "loss": 0.6693, "step": 64700 }, { "epoch": 0.38464967812115486, "grad_norm": 7.116189956665039, "learning_rate": 7.692828950496933e-06, "loss": 0.7571, "step": 64710 }, { "epoch": 0.3847091201978232, "grad_norm": 5.509309768676758, "learning_rate": 7.694017784963622e-06, "loss": 0.6797, "step": 64720 }, { "epoch": 0.38476856227449163, "grad_norm": 8.272589683532715, "learning_rate": 7.69520661943031e-06, "loss": 0.6897, "step": 64730 }, { "epoch": 0.38482800435116, "grad_norm": 9.028044700622559, "learning_rate": 7.696395453897e-06, "loss": 0.6825, "step": 64740 }, { "epoch": 0.3848874464278284, "grad_norm": 9.558308601379395, "learning_rate": 7.697584288363688e-06, "loss": 0.6978, "step": 64750 }, { "epoch": 0.3849468885044968, "grad_norm": 7.905342102050781, "learning_rate": 7.698773122830378e-06, "loss": 0.7027, "step": 64760 }, { "epoch": 0.3850063305811652, "grad_norm": 7.045358180999756, "learning_rate": 7.699961957297066e-06, "loss": 0.7118, "step": 64770 }, { "epoch": 0.3850657726578336, "grad_norm": 6.185836315155029, "learning_rate": 7.701150791763754e-06, "loss": 0.6758, "step": 64780 }, { "epoch": 0.38512521473450195, "grad_norm": 8.395771980285645, "learning_rate": 7.702339626230444e-06, "loss": 0.7032, "step": 64790 }, { "epoch": 0.38518465681117037, "grad_norm": 7.820644855499268, "learning_rate": 7.703528460697132e-06, "loss": 0.6789, "step": 64800 }, { "epoch": 0.3852440988878387, "grad_norm": 7.501001834869385, "learning_rate": 7.704717295163822e-06, "loss": 0.6538, "step": 64810 }, { "epoch": 0.38530354096450714, "grad_norm": 5.776500701904297, "learning_rate": 7.70590612963051e-06, "loss": 0.6242, "step": 64820 }, { "epoch": 0.3853629830411755, "grad_norm": 7.125505447387695, "learning_rate": 7.7070949640972e-06, "loss": 0.7366, "step": 64830 }, { "epoch": 0.3854224251178439, "grad_norm": 7.016703128814697, "learning_rate": 7.708283798563888e-06, "loss": 0.6605, "step": 64840 }, { "epoch": 0.38548186719451233, "grad_norm": 7.893683433532715, "learning_rate": 7.709472633030578e-06, "loss": 0.7376, "step": 64850 }, { "epoch": 0.3855413092711807, "grad_norm": 7.527474880218506, "learning_rate": 7.710661467497267e-06, "loss": 0.6386, "step": 64860 }, { "epoch": 0.3856007513478491, "grad_norm": 8.03039836883545, "learning_rate": 7.711850301963956e-06, "loss": 0.7602, "step": 64870 }, { "epoch": 0.38566019342451746, "grad_norm": 6.940331935882568, "learning_rate": 7.713039136430645e-06, "loss": 0.7156, "step": 64880 }, { "epoch": 0.3857196355011859, "grad_norm": 6.516562461853027, "learning_rate": 7.714227970897333e-06, "loss": 0.6261, "step": 64890 }, { "epoch": 0.38577907757785423, "grad_norm": 6.8416242599487305, "learning_rate": 7.715416805364021e-06, "loss": 0.7082, "step": 64900 }, { "epoch": 0.38583851965452265, "grad_norm": 4.956649303436279, "learning_rate": 7.716605639830711e-06, "loss": 0.6661, "step": 64910 }, { "epoch": 0.38589796173119106, "grad_norm": 7.150187015533447, "learning_rate": 7.7177944742974e-06, "loss": 0.759, "step": 64920 }, { "epoch": 0.3859574038078594, "grad_norm": 6.597815990447998, "learning_rate": 7.718983308764089e-06, "loss": 0.717, "step": 64930 }, { "epoch": 0.38601684588452784, "grad_norm": 7.547084331512451, "learning_rate": 7.720172143230777e-06, "loss": 0.6394, "step": 64940 }, { "epoch": 0.3860762879611962, "grad_norm": 5.8842267990112305, "learning_rate": 7.721360977697467e-06, "loss": 0.7708, "step": 64950 }, { "epoch": 0.3861357300378646, "grad_norm": 7.364229679107666, "learning_rate": 7.722549812164155e-06, "loss": 0.7223, "step": 64960 }, { "epoch": 0.38619517211453297, "grad_norm": 7.517314910888672, "learning_rate": 7.723738646630843e-06, "loss": 0.6476, "step": 64970 }, { "epoch": 0.3862546141912014, "grad_norm": 6.997931480407715, "learning_rate": 7.724927481097533e-06, "loss": 0.6644, "step": 64980 }, { "epoch": 0.3863140562678698, "grad_norm": 6.72908353805542, "learning_rate": 7.726116315564221e-06, "loss": 0.6396, "step": 64990 }, { "epoch": 0.38637349834453816, "grad_norm": 8.696756362915039, "learning_rate": 7.72730515003091e-06, "loss": 0.7116, "step": 65000 }, { "epoch": 0.38643294042120657, "grad_norm": 6.593536376953125, "learning_rate": 7.728493984497599e-06, "loss": 0.6334, "step": 65010 }, { "epoch": 0.38649238249787493, "grad_norm": 11.261576652526855, "learning_rate": 7.729682818964289e-06, "loss": 0.6651, "step": 65020 }, { "epoch": 0.38655182457454335, "grad_norm": 6.872671604156494, "learning_rate": 7.730871653430977e-06, "loss": 0.6873, "step": 65030 }, { "epoch": 0.3866112666512117, "grad_norm": 9.340130805969238, "learning_rate": 7.732060487897666e-06, "loss": 0.7177, "step": 65040 }, { "epoch": 0.3866707087278801, "grad_norm": 7.582176685333252, "learning_rate": 7.733249322364355e-06, "loss": 0.6711, "step": 65050 }, { "epoch": 0.38673015080454853, "grad_norm": 9.02163028717041, "learning_rate": 7.734438156831043e-06, "loss": 0.6861, "step": 65060 }, { "epoch": 0.3867895928812169, "grad_norm": 5.720432281494141, "learning_rate": 7.735626991297732e-06, "loss": 0.711, "step": 65070 }, { "epoch": 0.3868490349578853, "grad_norm": 6.055485248565674, "learning_rate": 7.73681582576442e-06, "loss": 0.6413, "step": 65080 }, { "epoch": 0.38690847703455367, "grad_norm": 7.007908344268799, "learning_rate": 7.73800466023111e-06, "loss": 0.6839, "step": 65090 }, { "epoch": 0.3869679191112221, "grad_norm": 7.086925983428955, "learning_rate": 7.739193494697798e-06, "loss": 0.762, "step": 65100 }, { "epoch": 0.38702736118789044, "grad_norm": 5.242605686187744, "learning_rate": 7.740382329164488e-06, "loss": 0.5965, "step": 65110 }, { "epoch": 0.38708680326455885, "grad_norm": 6.194953441619873, "learning_rate": 7.741571163631176e-06, "loss": 0.7128, "step": 65120 }, { "epoch": 0.38714624534122727, "grad_norm": 7.164479732513428, "learning_rate": 7.742759998097866e-06, "loss": 0.7261, "step": 65130 }, { "epoch": 0.3872056874178956, "grad_norm": 6.570443630218506, "learning_rate": 7.743948832564554e-06, "loss": 0.6337, "step": 65140 }, { "epoch": 0.38726512949456404, "grad_norm": 6.222640037536621, "learning_rate": 7.745137667031242e-06, "loss": 0.6708, "step": 65150 }, { "epoch": 0.3873245715712324, "grad_norm": 6.676182746887207, "learning_rate": 7.746326501497932e-06, "loss": 0.5987, "step": 65160 }, { "epoch": 0.3873840136479008, "grad_norm": 5.775805950164795, "learning_rate": 7.74751533596462e-06, "loss": 0.6248, "step": 65170 }, { "epoch": 0.3874434557245692, "grad_norm": 6.398735523223877, "learning_rate": 7.74870417043131e-06, "loss": 0.6356, "step": 65180 }, { "epoch": 0.3875028978012376, "grad_norm": 6.513252258300781, "learning_rate": 7.749893004897998e-06, "loss": 0.6752, "step": 65190 }, { "epoch": 0.38756233987790595, "grad_norm": 6.866364002227783, "learning_rate": 7.751081839364688e-06, "loss": 0.6319, "step": 65200 }, { "epoch": 0.38762178195457436, "grad_norm": 7.869295597076416, "learning_rate": 7.752270673831377e-06, "loss": 0.7708, "step": 65210 }, { "epoch": 0.3876812240312428, "grad_norm": 7.0928263664245605, "learning_rate": 7.753459508298065e-06, "loss": 0.6759, "step": 65220 }, { "epoch": 0.38774066610791114, "grad_norm": 7.356008529663086, "learning_rate": 7.754648342764755e-06, "loss": 0.6498, "step": 65230 }, { "epoch": 0.38780010818457955, "grad_norm": 6.153585433959961, "learning_rate": 7.755837177231443e-06, "loss": 0.6678, "step": 65240 }, { "epoch": 0.3878595502612479, "grad_norm": 7.607061386108398, "learning_rate": 7.757026011698131e-06, "loss": 0.6675, "step": 65250 }, { "epoch": 0.3879189923379163, "grad_norm": 8.000999450683594, "learning_rate": 7.758214846164821e-06, "loss": 0.6534, "step": 65260 }, { "epoch": 0.3879784344145847, "grad_norm": 9.06045150756836, "learning_rate": 7.75940368063151e-06, "loss": 0.6905, "step": 65270 }, { "epoch": 0.3880378764912531, "grad_norm": 6.655391216278076, "learning_rate": 7.760592515098199e-06, "loss": 0.6391, "step": 65280 }, { "epoch": 0.3880973185679215, "grad_norm": 5.216149806976318, "learning_rate": 7.761781349564887e-06, "loss": 0.7241, "step": 65290 }, { "epoch": 0.38815676064458987, "grad_norm": 6.077950477600098, "learning_rate": 7.762970184031577e-06, "loss": 0.6765, "step": 65300 }, { "epoch": 0.3882162027212583, "grad_norm": 6.733191967010498, "learning_rate": 7.764159018498265e-06, "loss": 0.6237, "step": 65310 }, { "epoch": 0.38827564479792664, "grad_norm": 6.448060035705566, "learning_rate": 7.765347852964955e-06, "loss": 0.6407, "step": 65320 }, { "epoch": 0.38833508687459506, "grad_norm": 9.118364334106445, "learning_rate": 7.766536687431643e-06, "loss": 0.7575, "step": 65330 }, { "epoch": 0.3883945289512634, "grad_norm": 7.936451435089111, "learning_rate": 7.767725521898331e-06, "loss": 0.6253, "step": 65340 }, { "epoch": 0.38845397102793183, "grad_norm": 6.866815090179443, "learning_rate": 7.76891435636502e-06, "loss": 0.6405, "step": 65350 }, { "epoch": 0.38851341310460025, "grad_norm": 5.469892978668213, "learning_rate": 7.770103190831709e-06, "loss": 0.6255, "step": 65360 }, { "epoch": 0.3885728551812686, "grad_norm": 6.746588706970215, "learning_rate": 7.771292025298398e-06, "loss": 0.6857, "step": 65370 }, { "epoch": 0.388632297257937, "grad_norm": 6.933884143829346, "learning_rate": 7.772480859765087e-06, "loss": 0.6949, "step": 65380 }, { "epoch": 0.3886917393346054, "grad_norm": 6.5308003425598145, "learning_rate": 7.773669694231776e-06, "loss": 0.6478, "step": 65390 }, { "epoch": 0.3887511814112738, "grad_norm": 7.742141246795654, "learning_rate": 7.774858528698464e-06, "loss": 0.7062, "step": 65400 }, { "epoch": 0.38881062348794215, "grad_norm": 6.81341028213501, "learning_rate": 7.776047363165154e-06, "loss": 0.6701, "step": 65410 }, { "epoch": 0.38887006556461057, "grad_norm": 8.424622535705566, "learning_rate": 7.777236197631842e-06, "loss": 0.712, "step": 65420 }, { "epoch": 0.388929507641279, "grad_norm": 6.927221298217773, "learning_rate": 7.77842503209853e-06, "loss": 0.6253, "step": 65430 }, { "epoch": 0.38898894971794734, "grad_norm": 6.366405963897705, "learning_rate": 7.77961386656522e-06, "loss": 0.7176, "step": 65440 }, { "epoch": 0.38904839179461576, "grad_norm": 7.763174533843994, "learning_rate": 7.780802701031908e-06, "loss": 0.7237, "step": 65450 }, { "epoch": 0.3891078338712841, "grad_norm": 7.1995015144348145, "learning_rate": 7.781991535498598e-06, "loss": 0.648, "step": 65460 }, { "epoch": 0.38916727594795253, "grad_norm": 8.675396919250488, "learning_rate": 7.783180369965286e-06, "loss": 0.6945, "step": 65470 }, { "epoch": 0.3892267180246209, "grad_norm": 9.04526424407959, "learning_rate": 7.784369204431976e-06, "loss": 0.6638, "step": 65480 }, { "epoch": 0.3892861601012893, "grad_norm": 8.134322166442871, "learning_rate": 7.785558038898664e-06, "loss": 0.6409, "step": 65490 }, { "epoch": 0.38934560217795766, "grad_norm": 7.5339741706848145, "learning_rate": 7.786746873365352e-06, "loss": 0.7242, "step": 65500 }, { "epoch": 0.3894050442546261, "grad_norm": 5.36116361618042, "learning_rate": 7.787935707832042e-06, "loss": 0.6413, "step": 65510 }, { "epoch": 0.3894644863312945, "grad_norm": 7.446684837341309, "learning_rate": 7.78912454229873e-06, "loss": 0.6804, "step": 65520 }, { "epoch": 0.38952392840796285, "grad_norm": 5.264781475067139, "learning_rate": 7.79031337676542e-06, "loss": 0.6681, "step": 65530 }, { "epoch": 0.38958337048463126, "grad_norm": 7.2037177085876465, "learning_rate": 7.791502211232108e-06, "loss": 0.7027, "step": 65540 }, { "epoch": 0.3896428125612996, "grad_norm": 6.372846603393555, "learning_rate": 7.792691045698797e-06, "loss": 0.7071, "step": 65550 }, { "epoch": 0.38970225463796804, "grad_norm": 6.6965813636779785, "learning_rate": 7.793879880165487e-06, "loss": 0.6653, "step": 65560 }, { "epoch": 0.3897616967146364, "grad_norm": 9.809760093688965, "learning_rate": 7.795068714632175e-06, "loss": 0.6453, "step": 65570 }, { "epoch": 0.3898211387913048, "grad_norm": 8.32446575164795, "learning_rate": 7.796257549098865e-06, "loss": 0.6824, "step": 65580 }, { "epoch": 0.3898805808679732, "grad_norm": 7.46854829788208, "learning_rate": 7.797446383565553e-06, "loss": 0.7016, "step": 65590 }, { "epoch": 0.3899400229446416, "grad_norm": 7.83219575881958, "learning_rate": 7.798635218032243e-06, "loss": 0.6294, "step": 65600 }, { "epoch": 0.38999946502131, "grad_norm": 7.501832962036133, "learning_rate": 7.799824052498931e-06, "loss": 0.7083, "step": 65610 }, { "epoch": 0.39005890709797836, "grad_norm": 6.249277114868164, "learning_rate": 7.801012886965619e-06, "loss": 0.6742, "step": 65620 }, { "epoch": 0.3901183491746468, "grad_norm": 8.490776062011719, "learning_rate": 7.802201721432309e-06, "loss": 0.7557, "step": 65630 }, { "epoch": 0.39017779125131513, "grad_norm": 8.36448860168457, "learning_rate": 7.803390555898997e-06, "loss": 0.6607, "step": 65640 }, { "epoch": 0.39023723332798355, "grad_norm": 7.046745300292969, "learning_rate": 7.804579390365687e-06, "loss": 0.7009, "step": 65650 }, { "epoch": 0.39029667540465196, "grad_norm": 8.185569763183594, "learning_rate": 7.805768224832375e-06, "loss": 0.6948, "step": 65660 }, { "epoch": 0.3903561174813203, "grad_norm": 6.477779865264893, "learning_rate": 7.806957059299065e-06, "loss": 0.6597, "step": 65670 }, { "epoch": 0.39041555955798873, "grad_norm": 5.347764492034912, "learning_rate": 7.808145893765753e-06, "loss": 0.6837, "step": 65680 }, { "epoch": 0.3904750016346571, "grad_norm": 5.454985618591309, "learning_rate": 7.809334728232442e-06, "loss": 0.6708, "step": 65690 }, { "epoch": 0.3905344437113255, "grad_norm": 5.4345383644104, "learning_rate": 7.81052356269913e-06, "loss": 0.6695, "step": 65700 }, { "epoch": 0.39059388578799387, "grad_norm": 7.930487632751465, "learning_rate": 7.811712397165819e-06, "loss": 0.703, "step": 65710 }, { "epoch": 0.3906533278646623, "grad_norm": 5.676406383514404, "learning_rate": 7.812901231632508e-06, "loss": 0.6748, "step": 65720 }, { "epoch": 0.3907127699413307, "grad_norm": 6.337421894073486, "learning_rate": 7.814090066099196e-06, "loss": 0.6112, "step": 65730 }, { "epoch": 0.39077221201799905, "grad_norm": 5.383986473083496, "learning_rate": 7.815278900565886e-06, "loss": 0.6796, "step": 65740 }, { "epoch": 0.39083165409466747, "grad_norm": 6.408059597015381, "learning_rate": 7.816467735032574e-06, "loss": 0.6635, "step": 65750 }, { "epoch": 0.39089109617133583, "grad_norm": 6.273205280303955, "learning_rate": 7.817656569499264e-06, "loss": 0.6518, "step": 65760 }, { "epoch": 0.39095053824800424, "grad_norm": 8.309998512268066, "learning_rate": 7.818845403965952e-06, "loss": 0.662, "step": 65770 }, { "epoch": 0.3910099803246726, "grad_norm": 6.488157272338867, "learning_rate": 7.82003423843264e-06, "loss": 0.6504, "step": 65780 }, { "epoch": 0.391069422401341, "grad_norm": 6.3718581199646, "learning_rate": 7.82122307289933e-06, "loss": 0.628, "step": 65790 }, { "epoch": 0.39112886447800943, "grad_norm": 5.581108093261719, "learning_rate": 7.822411907366018e-06, "loss": 0.6504, "step": 65800 }, { "epoch": 0.3911883065546778, "grad_norm": 7.604467868804932, "learning_rate": 7.823600741832708e-06, "loss": 0.7021, "step": 65810 }, { "epoch": 0.3912477486313462, "grad_norm": 5.76404333114624, "learning_rate": 7.824789576299396e-06, "loss": 0.6409, "step": 65820 }, { "epoch": 0.39130719070801456, "grad_norm": 6.63088321685791, "learning_rate": 7.825978410766086e-06, "loss": 0.6287, "step": 65830 }, { "epoch": 0.391366632784683, "grad_norm": 8.7731294631958, "learning_rate": 7.827167245232774e-06, "loss": 0.6732, "step": 65840 }, { "epoch": 0.39142607486135134, "grad_norm": 6.636263370513916, "learning_rate": 7.828356079699464e-06, "loss": 0.6512, "step": 65850 }, { "epoch": 0.39148551693801975, "grad_norm": 6.68448543548584, "learning_rate": 7.829544914166152e-06, "loss": 0.6241, "step": 65860 }, { "epoch": 0.3915449590146881, "grad_norm": 7.056999683380127, "learning_rate": 7.83073374863284e-06, "loss": 0.7286, "step": 65870 }, { "epoch": 0.3916044010913565, "grad_norm": 5.778980255126953, "learning_rate": 7.83192258309953e-06, "loss": 0.6802, "step": 65880 }, { "epoch": 0.39166384316802494, "grad_norm": 5.491927146911621, "learning_rate": 7.833111417566218e-06, "loss": 0.6092, "step": 65890 }, { "epoch": 0.3917232852446933, "grad_norm": 6.986663818359375, "learning_rate": 7.834300252032907e-06, "loss": 0.6393, "step": 65900 }, { "epoch": 0.3917827273213617, "grad_norm": 6.313230037689209, "learning_rate": 7.835489086499597e-06, "loss": 0.689, "step": 65910 }, { "epoch": 0.39184216939803007, "grad_norm": 8.897303581237793, "learning_rate": 7.836677920966285e-06, "loss": 0.5807, "step": 65920 }, { "epoch": 0.3919016114746985, "grad_norm": 7.341970443725586, "learning_rate": 7.837866755432975e-06, "loss": 0.6146, "step": 65930 }, { "epoch": 0.39196105355136684, "grad_norm": 5.246347904205322, "learning_rate": 7.839055589899663e-06, "loss": 0.6641, "step": 65940 }, { "epoch": 0.39202049562803526, "grad_norm": 5.6236891746521, "learning_rate": 7.840244424366353e-06, "loss": 0.6533, "step": 65950 }, { "epoch": 0.3920799377047037, "grad_norm": 7.688324451446533, "learning_rate": 7.841433258833041e-06, "loss": 0.6514, "step": 65960 }, { "epoch": 0.39213937978137203, "grad_norm": 8.169371604919434, "learning_rate": 7.84262209329973e-06, "loss": 0.7276, "step": 65970 }, { "epoch": 0.39219882185804045, "grad_norm": 7.179712772369385, "learning_rate": 7.843810927766419e-06, "loss": 0.6144, "step": 65980 }, { "epoch": 0.3922582639347088, "grad_norm": 6.8908820152282715, "learning_rate": 7.844999762233107e-06, "loss": 0.6594, "step": 65990 }, { "epoch": 0.3923177060113772, "grad_norm": 6.421389579772949, "learning_rate": 7.846188596699797e-06, "loss": 0.6418, "step": 66000 }, { "epoch": 0.3923771480880456, "grad_norm": 7.932403087615967, "learning_rate": 7.847377431166485e-06, "loss": 0.6667, "step": 66010 }, { "epoch": 0.392436590164714, "grad_norm": 7.957874298095703, "learning_rate": 7.848566265633175e-06, "loss": 0.6806, "step": 66020 }, { "epoch": 0.3924960322413824, "grad_norm": 5.959568977355957, "learning_rate": 7.849755100099863e-06, "loss": 0.6943, "step": 66030 }, { "epoch": 0.39255547431805077, "grad_norm": 7.379978656768799, "learning_rate": 7.850943934566552e-06, "loss": 0.6742, "step": 66040 }, { "epoch": 0.3926149163947192, "grad_norm": 6.8597869873046875, "learning_rate": 7.85213276903324e-06, "loss": 0.7232, "step": 66050 }, { "epoch": 0.39267435847138754, "grad_norm": 9.196307182312012, "learning_rate": 7.853321603499929e-06, "loss": 0.6621, "step": 66060 }, { "epoch": 0.39273380054805596, "grad_norm": 5.90652322769165, "learning_rate": 7.854510437966618e-06, "loss": 0.6361, "step": 66070 }, { "epoch": 0.3927932426247243, "grad_norm": 7.503965377807617, "learning_rate": 7.855699272433306e-06, "loss": 0.649, "step": 66080 }, { "epoch": 0.39285268470139273, "grad_norm": 5.737601280212402, "learning_rate": 7.856888106899996e-06, "loss": 0.6164, "step": 66090 }, { "epoch": 0.39291212677806114, "grad_norm": 6.772765636444092, "learning_rate": 7.858076941366684e-06, "loss": 0.7226, "step": 66100 }, { "epoch": 0.3929715688547295, "grad_norm": 7.777299404144287, "learning_rate": 7.859265775833374e-06, "loss": 0.697, "step": 66110 }, { "epoch": 0.3930310109313979, "grad_norm": 9.063918113708496, "learning_rate": 7.860454610300062e-06, "loss": 0.6751, "step": 66120 }, { "epoch": 0.3930904530080663, "grad_norm": 6.523985862731934, "learning_rate": 7.861643444766752e-06, "loss": 0.6218, "step": 66130 }, { "epoch": 0.3931498950847347, "grad_norm": 5.799078941345215, "learning_rate": 7.86283227923344e-06, "loss": 0.7142, "step": 66140 }, { "epoch": 0.39320933716140305, "grad_norm": 8.617501258850098, "learning_rate": 7.864021113700128e-06, "loss": 0.6455, "step": 66150 }, { "epoch": 0.39326877923807146, "grad_norm": 7.760235786437988, "learning_rate": 7.865209948166818e-06, "loss": 0.6878, "step": 66160 }, { "epoch": 0.3933282213147399, "grad_norm": 7.475615978240967, "learning_rate": 7.866398782633506e-06, "loss": 0.6108, "step": 66170 }, { "epoch": 0.39338766339140824, "grad_norm": 6.416930675506592, "learning_rate": 7.867587617100196e-06, "loss": 0.6659, "step": 66180 }, { "epoch": 0.39344710546807665, "grad_norm": 8.537521362304688, "learning_rate": 7.868776451566884e-06, "loss": 0.6568, "step": 66190 }, { "epoch": 0.393506547544745, "grad_norm": 7.394586086273193, "learning_rate": 7.869965286033574e-06, "loss": 0.6822, "step": 66200 }, { "epoch": 0.3935659896214134, "grad_norm": 8.532434463500977, "learning_rate": 7.871154120500262e-06, "loss": 0.6614, "step": 66210 }, { "epoch": 0.3936254316980818, "grad_norm": 5.954714775085449, "learning_rate": 7.872342954966951e-06, "loss": 0.6776, "step": 66220 }, { "epoch": 0.3936848737747502, "grad_norm": 8.242729187011719, "learning_rate": 7.87353178943364e-06, "loss": 0.7096, "step": 66230 }, { "epoch": 0.39374431585141856, "grad_norm": 7.035641193389893, "learning_rate": 7.874720623900328e-06, "loss": 0.6891, "step": 66240 }, { "epoch": 0.393803757928087, "grad_norm": 7.953495025634766, "learning_rate": 7.875909458367017e-06, "loss": 0.626, "step": 66250 }, { "epoch": 0.3938632000047554, "grad_norm": 6.6267900466918945, "learning_rate": 7.877098292833707e-06, "loss": 0.6273, "step": 66260 }, { "epoch": 0.39392264208142375, "grad_norm": 7.121242523193359, "learning_rate": 7.878287127300395e-06, "loss": 0.6225, "step": 66270 }, { "epoch": 0.39398208415809216, "grad_norm": 9.055559158325195, "learning_rate": 7.879475961767085e-06, "loss": 0.6453, "step": 66280 }, { "epoch": 0.3940415262347605, "grad_norm": 7.117584228515625, "learning_rate": 7.880664796233773e-06, "loss": 0.6666, "step": 66290 }, { "epoch": 0.39410096831142893, "grad_norm": 7.022729873657227, "learning_rate": 7.881853630700463e-06, "loss": 0.679, "step": 66300 }, { "epoch": 0.3941604103880973, "grad_norm": 7.500030040740967, "learning_rate": 7.883042465167151e-06, "loss": 0.662, "step": 66310 }, { "epoch": 0.3942198524647657, "grad_norm": 6.371372699737549, "learning_rate": 7.88423129963384e-06, "loss": 0.6519, "step": 66320 }, { "epoch": 0.3942792945414341, "grad_norm": 7.1105122566223145, "learning_rate": 7.885420134100529e-06, "loss": 0.7247, "step": 66330 }, { "epoch": 0.3943387366181025, "grad_norm": 7.734414100646973, "learning_rate": 7.886608968567217e-06, "loss": 0.7511, "step": 66340 }, { "epoch": 0.3943981786947709, "grad_norm": 5.0940632820129395, "learning_rate": 7.887797803033907e-06, "loss": 0.6294, "step": 66350 }, { "epoch": 0.39445762077143925, "grad_norm": 6.798617362976074, "learning_rate": 7.888986637500595e-06, "loss": 0.6827, "step": 66360 }, { "epoch": 0.39451706284810767, "grad_norm": 6.285091400146484, "learning_rate": 7.890175471967284e-06, "loss": 0.6855, "step": 66370 }, { "epoch": 0.39457650492477603, "grad_norm": 6.474798679351807, "learning_rate": 7.891364306433973e-06, "loss": 0.7013, "step": 66380 }, { "epoch": 0.39463594700144444, "grad_norm": 9.82478141784668, "learning_rate": 7.892553140900662e-06, "loss": 0.6345, "step": 66390 }, { "epoch": 0.39469538907811286, "grad_norm": 6.697125434875488, "learning_rate": 7.89374197536735e-06, "loss": 0.6734, "step": 66400 }, { "epoch": 0.3947548311547812, "grad_norm": 6.723103046417236, "learning_rate": 7.89493080983404e-06, "loss": 0.6795, "step": 66410 }, { "epoch": 0.39481427323144963, "grad_norm": 5.904140472412109, "learning_rate": 7.896119644300728e-06, "loss": 0.6551, "step": 66420 }, { "epoch": 0.394873715308118, "grad_norm": 6.349091529846191, "learning_rate": 7.897308478767416e-06, "loss": 0.6603, "step": 66430 }, { "epoch": 0.3949331573847864, "grad_norm": 6.882076263427734, "learning_rate": 7.898497313234106e-06, "loss": 0.7051, "step": 66440 }, { "epoch": 0.39499259946145476, "grad_norm": 7.445014476776123, "learning_rate": 7.899686147700794e-06, "loss": 0.6751, "step": 66450 }, { "epoch": 0.3950520415381232, "grad_norm": 6.002669811248779, "learning_rate": 7.900874982167484e-06, "loss": 0.6439, "step": 66460 }, { "epoch": 0.3951114836147916, "grad_norm": 8.15588092803955, "learning_rate": 7.902063816634172e-06, "loss": 0.6866, "step": 66470 }, { "epoch": 0.39517092569145995, "grad_norm": 5.573763847351074, "learning_rate": 7.903252651100862e-06, "loss": 0.6753, "step": 66480 }, { "epoch": 0.39523036776812837, "grad_norm": 6.963930130004883, "learning_rate": 7.90444148556755e-06, "loss": 0.7274, "step": 66490 }, { "epoch": 0.3952898098447967, "grad_norm": 5.5053935050964355, "learning_rate": 7.905630320034238e-06, "loss": 0.7212, "step": 66500 }, { "epoch": 0.39534925192146514, "grad_norm": 8.06839656829834, "learning_rate": 7.906819154500928e-06, "loss": 0.721, "step": 66510 }, { "epoch": 0.3954086939981335, "grad_norm": 5.666802883148193, "learning_rate": 7.908007988967616e-06, "loss": 0.6837, "step": 66520 }, { "epoch": 0.3954681360748019, "grad_norm": 6.60348653793335, "learning_rate": 7.909196823434306e-06, "loss": 0.6806, "step": 66530 }, { "epoch": 0.3955275781514703, "grad_norm": 6.074188232421875, "learning_rate": 7.910385657900994e-06, "loss": 0.6885, "step": 66540 }, { "epoch": 0.3955870202281387, "grad_norm": 7.6333088874816895, "learning_rate": 7.911574492367683e-06, "loss": 0.7037, "step": 66550 }, { "epoch": 0.3956464623048071, "grad_norm": 8.950122833251953, "learning_rate": 7.912763326834372e-06, "loss": 0.6628, "step": 66560 }, { "epoch": 0.39570590438147546, "grad_norm": 7.946433067321777, "learning_rate": 7.913952161301061e-06, "loss": 0.6654, "step": 66570 }, { "epoch": 0.3957653464581439, "grad_norm": 4.982107639312744, "learning_rate": 7.91514099576775e-06, "loss": 0.7061, "step": 66580 }, { "epoch": 0.39582478853481223, "grad_norm": 8.42110538482666, "learning_rate": 7.916329830234439e-06, "loss": 0.6176, "step": 66590 }, { "epoch": 0.39588423061148065, "grad_norm": 8.480632781982422, "learning_rate": 7.917518664701129e-06, "loss": 0.6851, "step": 66600 }, { "epoch": 0.395943672688149, "grad_norm": 6.700743675231934, "learning_rate": 7.918707499167817e-06, "loss": 0.6481, "step": 66610 }, { "epoch": 0.3960031147648174, "grad_norm": 4.878586292266846, "learning_rate": 7.919896333634505e-06, "loss": 0.6146, "step": 66620 }, { "epoch": 0.39606255684148584, "grad_norm": 6.656617164611816, "learning_rate": 7.921085168101195e-06, "loss": 0.6498, "step": 66630 }, { "epoch": 0.3961219989181542, "grad_norm": 8.351034164428711, "learning_rate": 7.922274002567883e-06, "loss": 0.7129, "step": 66640 }, { "epoch": 0.3961814409948226, "grad_norm": 5.211717128753662, "learning_rate": 7.923462837034573e-06, "loss": 0.6272, "step": 66650 }, { "epoch": 0.39624088307149097, "grad_norm": 8.136482238769531, "learning_rate": 7.92465167150126e-06, "loss": 0.6923, "step": 66660 }, { "epoch": 0.3963003251481594, "grad_norm": 6.060859203338623, "learning_rate": 7.92584050596795e-06, "loss": 0.6362, "step": 66670 }, { "epoch": 0.39635976722482774, "grad_norm": 6.703184127807617, "learning_rate": 7.927029340434639e-06, "loss": 0.6228, "step": 66680 }, { "epoch": 0.39641920930149616, "grad_norm": 6.6438398361206055, "learning_rate": 7.928218174901328e-06, "loss": 0.6853, "step": 66690 }, { "epoch": 0.39647865137816457, "grad_norm": 8.272573471069336, "learning_rate": 7.929407009368017e-06, "loss": 0.7102, "step": 66700 }, { "epoch": 0.39653809345483293, "grad_norm": 7.206843376159668, "learning_rate": 7.930595843834705e-06, "loss": 0.6628, "step": 66710 }, { "epoch": 0.39659753553150134, "grad_norm": 8.762284278869629, "learning_rate": 7.931784678301394e-06, "loss": 0.6856, "step": 66720 }, { "epoch": 0.3966569776081697, "grad_norm": 6.716054439544678, "learning_rate": 7.932973512768082e-06, "loss": 0.7262, "step": 66730 }, { "epoch": 0.3967164196848381, "grad_norm": 7.13997220993042, "learning_rate": 7.934162347234772e-06, "loss": 0.6423, "step": 66740 }, { "epoch": 0.3967758617615065, "grad_norm": 7.615416526794434, "learning_rate": 7.93535118170146e-06, "loss": 0.7514, "step": 66750 }, { "epoch": 0.3968353038381749, "grad_norm": 6.9864888191223145, "learning_rate": 7.93654001616815e-06, "loss": 0.68, "step": 66760 }, { "epoch": 0.3968947459148433, "grad_norm": 7.23307991027832, "learning_rate": 7.937728850634838e-06, "loss": 0.6055, "step": 66770 }, { "epoch": 0.39695418799151166, "grad_norm": 7.67175817489624, "learning_rate": 7.938917685101526e-06, "loss": 0.6133, "step": 66780 }, { "epoch": 0.3970136300681801, "grad_norm": 5.6593780517578125, "learning_rate": 7.940106519568216e-06, "loss": 0.6978, "step": 66790 }, { "epoch": 0.39707307214484844, "grad_norm": 5.552867412567139, "learning_rate": 7.941295354034904e-06, "loss": 0.6926, "step": 66800 }, { "epoch": 0.39713251422151685, "grad_norm": 6.053122043609619, "learning_rate": 7.942484188501594e-06, "loss": 0.6964, "step": 66810 }, { "epoch": 0.3971919562981852, "grad_norm": 7.074714660644531, "learning_rate": 7.943673022968282e-06, "loss": 0.6251, "step": 66820 }, { "epoch": 0.3972513983748536, "grad_norm": 8.08027458190918, "learning_rate": 7.944861857434972e-06, "loss": 0.6731, "step": 66830 }, { "epoch": 0.39731084045152204, "grad_norm": 8.798540115356445, "learning_rate": 7.94605069190166e-06, "loss": 0.6643, "step": 66840 }, { "epoch": 0.3973702825281904, "grad_norm": 5.456212043762207, "learning_rate": 7.94723952636835e-06, "loss": 0.6806, "step": 66850 }, { "epoch": 0.3974297246048588, "grad_norm": 6.308099269866943, "learning_rate": 7.948428360835038e-06, "loss": 0.6222, "step": 66860 }, { "epoch": 0.3974891666815272, "grad_norm": 6.295259475708008, "learning_rate": 7.949617195301726e-06, "loss": 0.745, "step": 66870 }, { "epoch": 0.3975486087581956, "grad_norm": 7.57911491394043, "learning_rate": 7.950806029768416e-06, "loss": 0.6773, "step": 66880 }, { "epoch": 0.39760805083486395, "grad_norm": 6.675576210021973, "learning_rate": 7.951994864235104e-06, "loss": 0.6229, "step": 66890 }, { "epoch": 0.39766749291153236, "grad_norm": 8.253314971923828, "learning_rate": 7.953183698701793e-06, "loss": 0.6494, "step": 66900 }, { "epoch": 0.3977269349882008, "grad_norm": 6.603490352630615, "learning_rate": 7.954372533168481e-06, "loss": 0.7049, "step": 66910 }, { "epoch": 0.39778637706486913, "grad_norm": 6.2169575691223145, "learning_rate": 7.955561367635171e-06, "loss": 0.7328, "step": 66920 }, { "epoch": 0.39784581914153755, "grad_norm": 6.982265949249268, "learning_rate": 7.95675020210186e-06, "loss": 0.6264, "step": 66930 }, { "epoch": 0.3979052612182059, "grad_norm": 6.7962236404418945, "learning_rate": 7.957939036568549e-06, "loss": 0.6813, "step": 66940 }, { "epoch": 0.3979647032948743, "grad_norm": 6.43799352645874, "learning_rate": 7.959127871035239e-06, "loss": 0.6689, "step": 66950 }, { "epoch": 0.3980241453715427, "grad_norm": 7.3040995597839355, "learning_rate": 7.960316705501927e-06, "loss": 0.6524, "step": 66960 }, { "epoch": 0.3980835874482111, "grad_norm": 5.991987705230713, "learning_rate": 7.961505539968617e-06, "loss": 0.6717, "step": 66970 }, { "epoch": 0.39814302952487945, "grad_norm": 6.027195453643799, "learning_rate": 7.962694374435305e-06, "loss": 0.6981, "step": 66980 }, { "epoch": 0.39820247160154787, "grad_norm": 7.463229179382324, "learning_rate": 7.963883208901993e-06, "loss": 0.7264, "step": 66990 }, { "epoch": 0.3982619136782163, "grad_norm": 6.766777038574219, "learning_rate": 7.965072043368683e-06, "loss": 0.6764, "step": 67000 }, { "epoch": 0.39832135575488464, "grad_norm": 4.5959153175354, "learning_rate": 7.96626087783537e-06, "loss": 0.6414, "step": 67010 }, { "epoch": 0.39838079783155306, "grad_norm": 6.189843654632568, "learning_rate": 7.96744971230206e-06, "loss": 0.6324, "step": 67020 }, { "epoch": 0.3984402399082214, "grad_norm": 6.927804946899414, "learning_rate": 7.968638546768749e-06, "loss": 0.6486, "step": 67030 }, { "epoch": 0.39849968198488983, "grad_norm": 7.191527366638184, "learning_rate": 7.969827381235438e-06, "loss": 0.6605, "step": 67040 }, { "epoch": 0.3985591240615582, "grad_norm": 8.325790405273438, "learning_rate": 7.971016215702126e-06, "loss": 0.6486, "step": 67050 }, { "epoch": 0.3986185661382266, "grad_norm": 7.848541259765625, "learning_rate": 7.972205050168814e-06, "loss": 0.6758, "step": 67060 }, { "epoch": 0.398678008214895, "grad_norm": 6.528576850891113, "learning_rate": 7.973393884635504e-06, "loss": 0.6042, "step": 67070 }, { "epoch": 0.3987374502915634, "grad_norm": 6.158679962158203, "learning_rate": 7.974582719102192e-06, "loss": 0.6374, "step": 67080 }, { "epoch": 0.3987968923682318, "grad_norm": 7.293173789978027, "learning_rate": 7.975771553568882e-06, "loss": 0.7083, "step": 67090 }, { "epoch": 0.39885633444490015, "grad_norm": 7.848047733306885, "learning_rate": 7.97696038803557e-06, "loss": 0.6593, "step": 67100 }, { "epoch": 0.39891577652156857, "grad_norm": 7.785264492034912, "learning_rate": 7.97814922250226e-06, "loss": 0.7026, "step": 67110 }, { "epoch": 0.3989752185982369, "grad_norm": 7.698094367980957, "learning_rate": 7.979338056968948e-06, "loss": 0.7079, "step": 67120 }, { "epoch": 0.39903466067490534, "grad_norm": 7.785542964935303, "learning_rate": 7.980526891435638e-06, "loss": 0.6309, "step": 67130 }, { "epoch": 0.39909410275157375, "grad_norm": 8.37553882598877, "learning_rate": 7.981715725902326e-06, "loss": 0.672, "step": 67140 }, { "epoch": 0.3991535448282421, "grad_norm": 5.465203762054443, "learning_rate": 7.982904560369014e-06, "loss": 0.6751, "step": 67150 }, { "epoch": 0.3992129869049105, "grad_norm": 6.968344688415527, "learning_rate": 7.984093394835704e-06, "loss": 0.6194, "step": 67160 }, { "epoch": 0.3992724289815789, "grad_norm": 6.297965049743652, "learning_rate": 7.985282229302392e-06, "loss": 0.6112, "step": 67170 }, { "epoch": 0.3993318710582473, "grad_norm": 6.803535461425781, "learning_rate": 7.986471063769082e-06, "loss": 0.6793, "step": 67180 }, { "epoch": 0.39939131313491566, "grad_norm": 7.4528961181640625, "learning_rate": 7.98765989823577e-06, "loss": 0.6579, "step": 67190 }, { "epoch": 0.3994507552115841, "grad_norm": 7.9337239265441895, "learning_rate": 7.98884873270246e-06, "loss": 0.6326, "step": 67200 }, { "epoch": 0.3995101972882525, "grad_norm": 5.757076263427734, "learning_rate": 7.990037567169148e-06, "loss": 0.6827, "step": 67210 }, { "epoch": 0.39956963936492085, "grad_norm": 6.345499515533447, "learning_rate": 7.991226401635837e-06, "loss": 0.704, "step": 67220 }, { "epoch": 0.39962908144158926, "grad_norm": 5.661081790924072, "learning_rate": 7.992415236102525e-06, "loss": 0.6822, "step": 67230 }, { "epoch": 0.3996885235182576, "grad_norm": 5.85995626449585, "learning_rate": 7.993604070569213e-06, "loss": 0.6745, "step": 67240 }, { "epoch": 0.39974796559492604, "grad_norm": 6.774482727050781, "learning_rate": 7.994792905035903e-06, "loss": 0.6041, "step": 67250 }, { "epoch": 0.3998074076715944, "grad_norm": 6.696380615234375, "learning_rate": 7.995981739502591e-06, "loss": 0.7043, "step": 67260 }, { "epoch": 0.3998668497482628, "grad_norm": 8.001910209655762, "learning_rate": 7.997170573969281e-06, "loss": 0.6178, "step": 67270 }, { "epoch": 0.39992629182493117, "grad_norm": 8.422918319702148, "learning_rate": 7.998359408435971e-06, "loss": 0.7312, "step": 67280 }, { "epoch": 0.3999857339015996, "grad_norm": 6.735565662384033, "learning_rate": 7.999548242902659e-06, "loss": 0.6245, "step": 67290 }, { "epoch": 0.400045175978268, "grad_norm": 8.931511878967285, "learning_rate": 8.000737077369349e-06, "loss": 0.7043, "step": 67300 }, { "epoch": 0.40010461805493636, "grad_norm": 7.594855308532715, "learning_rate": 8.001925911836037e-06, "loss": 0.6802, "step": 67310 }, { "epoch": 0.40016406013160477, "grad_norm": 6.2290940284729, "learning_rate": 8.003114746302727e-06, "loss": 0.6531, "step": 67320 }, { "epoch": 0.40022350220827313, "grad_norm": 6.4764251708984375, "learning_rate": 8.004303580769415e-06, "loss": 0.6549, "step": 67330 }, { "epoch": 0.40028294428494154, "grad_norm": 7.020751476287842, "learning_rate": 8.005492415236103e-06, "loss": 0.6345, "step": 67340 }, { "epoch": 0.4003423863616099, "grad_norm": 6.644069194793701, "learning_rate": 8.006681249702793e-06, "loss": 0.6604, "step": 67350 }, { "epoch": 0.4004018284382783, "grad_norm": 5.420085906982422, "learning_rate": 8.00787008416948e-06, "loss": 0.6309, "step": 67360 }, { "epoch": 0.40046127051494673, "grad_norm": 5.575357913970947, "learning_rate": 8.00905891863617e-06, "loss": 0.6527, "step": 67370 }, { "epoch": 0.4005207125916151, "grad_norm": 7.639486789703369, "learning_rate": 8.010247753102858e-06, "loss": 0.6723, "step": 67380 }, { "epoch": 0.4005801546682835, "grad_norm": 5.924095630645752, "learning_rate": 8.011436587569548e-06, "loss": 0.629, "step": 67390 }, { "epoch": 0.40063959674495186, "grad_norm": 5.197519779205322, "learning_rate": 8.012625422036236e-06, "loss": 0.6747, "step": 67400 }, { "epoch": 0.4006990388216203, "grad_norm": 6.4914164543151855, "learning_rate": 8.013814256502926e-06, "loss": 0.6747, "step": 67410 }, { "epoch": 0.40075848089828864, "grad_norm": 7.066996097564697, "learning_rate": 8.015003090969614e-06, "loss": 0.6512, "step": 67420 }, { "epoch": 0.40081792297495705, "grad_norm": 5.670310974121094, "learning_rate": 8.016191925436302e-06, "loss": 0.6324, "step": 67430 }, { "epoch": 0.40087736505162547, "grad_norm": 5.673819541931152, "learning_rate": 8.017380759902992e-06, "loss": 0.6447, "step": 67440 }, { "epoch": 0.4009368071282938, "grad_norm": 5.405659198760986, "learning_rate": 8.01856959436968e-06, "loss": 0.6436, "step": 67450 }, { "epoch": 0.40099624920496224, "grad_norm": 7.42711067199707, "learning_rate": 8.01975842883637e-06, "loss": 0.6797, "step": 67460 }, { "epoch": 0.4010556912816306, "grad_norm": 6.986669063568115, "learning_rate": 8.020947263303058e-06, "loss": 0.69, "step": 67470 }, { "epoch": 0.401115133358299, "grad_norm": 7.010237216949463, "learning_rate": 8.022136097769748e-06, "loss": 0.7445, "step": 67480 }, { "epoch": 0.4011745754349674, "grad_norm": 7.399928092956543, "learning_rate": 8.023324932236436e-06, "loss": 0.6643, "step": 67490 }, { "epoch": 0.4012340175116358, "grad_norm": 5.271075248718262, "learning_rate": 8.024513766703126e-06, "loss": 0.6078, "step": 67500 }, { "epoch": 0.4012934595883042, "grad_norm": 6.491949081420898, "learning_rate": 8.025702601169814e-06, "loss": 0.7536, "step": 67510 }, { "epoch": 0.40135290166497256, "grad_norm": 7.774203777313232, "learning_rate": 8.026891435636502e-06, "loss": 0.7021, "step": 67520 }, { "epoch": 0.401412343741641, "grad_norm": 6.919190883636475, "learning_rate": 8.028080270103192e-06, "loss": 0.6372, "step": 67530 }, { "epoch": 0.40147178581830933, "grad_norm": 5.699517250061035, "learning_rate": 8.02926910456988e-06, "loss": 0.6441, "step": 67540 }, { "epoch": 0.40153122789497775, "grad_norm": 9.54498291015625, "learning_rate": 8.03045793903657e-06, "loss": 0.6331, "step": 67550 }, { "epoch": 0.4015906699716461, "grad_norm": 6.295149803161621, "learning_rate": 8.031646773503257e-06, "loss": 0.685, "step": 67560 }, { "epoch": 0.4016501120483145, "grad_norm": 6.60134744644165, "learning_rate": 8.032835607969947e-06, "loss": 0.6705, "step": 67570 }, { "epoch": 0.40170955412498294, "grad_norm": 7.503045558929443, "learning_rate": 8.034024442436635e-06, "loss": 0.6075, "step": 67580 }, { "epoch": 0.4017689962016513, "grad_norm": 6.060418605804443, "learning_rate": 8.035213276903323e-06, "loss": 0.654, "step": 67590 }, { "epoch": 0.4018284382783197, "grad_norm": 7.993011951446533, "learning_rate": 8.036402111370013e-06, "loss": 0.6946, "step": 67600 }, { "epoch": 0.40188788035498807, "grad_norm": 7.34912109375, "learning_rate": 8.037590945836701e-06, "loss": 0.628, "step": 67610 }, { "epoch": 0.4019473224316565, "grad_norm": 6.0931572914123535, "learning_rate": 8.038779780303391e-06, "loss": 0.6457, "step": 67620 }, { "epoch": 0.40200676450832484, "grad_norm": 7.370641231536865, "learning_rate": 8.03996861477008e-06, "loss": 0.6487, "step": 67630 }, { "epoch": 0.40206620658499326, "grad_norm": 6.0317254066467285, "learning_rate": 8.041157449236769e-06, "loss": 0.6747, "step": 67640 }, { "epoch": 0.4021256486616616, "grad_norm": 6.2974772453308105, "learning_rate": 8.042346283703459e-06, "loss": 0.653, "step": 67650 }, { "epoch": 0.40218509073833003, "grad_norm": 5.855116367340088, "learning_rate": 8.043535118170147e-06, "loss": 0.6765, "step": 67660 }, { "epoch": 0.40224453281499845, "grad_norm": 7.197633743286133, "learning_rate": 8.044723952636837e-06, "loss": 0.6608, "step": 67670 }, { "epoch": 0.4023039748916668, "grad_norm": 7.5150651931762695, "learning_rate": 8.045912787103525e-06, "loss": 0.6872, "step": 67680 }, { "epoch": 0.4023634169683352, "grad_norm": 7.423029899597168, "learning_rate": 8.047101621570214e-06, "loss": 0.6824, "step": 67690 }, { "epoch": 0.4024228590450036, "grad_norm": 6.939175605773926, "learning_rate": 8.048290456036902e-06, "loss": 0.6888, "step": 67700 }, { "epoch": 0.402482301121672, "grad_norm": 6.514861583709717, "learning_rate": 8.04947929050359e-06, "loss": 0.6499, "step": 67710 }, { "epoch": 0.40254174319834035, "grad_norm": 7.143412113189697, "learning_rate": 8.05066812497028e-06, "loss": 0.6871, "step": 67720 }, { "epoch": 0.40260118527500877, "grad_norm": 5.177175045013428, "learning_rate": 8.051856959436968e-06, "loss": 0.7181, "step": 67730 }, { "epoch": 0.4026606273516772, "grad_norm": 8.630334854125977, "learning_rate": 8.053045793903658e-06, "loss": 0.6643, "step": 67740 }, { "epoch": 0.40272006942834554, "grad_norm": 7.322482109069824, "learning_rate": 8.054234628370346e-06, "loss": 0.6095, "step": 67750 }, { "epoch": 0.40277951150501395, "grad_norm": 8.127939224243164, "learning_rate": 8.055423462837036e-06, "loss": 0.7438, "step": 67760 }, { "epoch": 0.4028389535816823, "grad_norm": 8.026801109313965, "learning_rate": 8.056612297303724e-06, "loss": 0.6293, "step": 67770 }, { "epoch": 0.4028983956583507, "grad_norm": 6.963572025299072, "learning_rate": 8.057801131770412e-06, "loss": 0.6413, "step": 67780 }, { "epoch": 0.4029578377350191, "grad_norm": 7.123520851135254, "learning_rate": 8.058989966237102e-06, "loss": 0.6786, "step": 67790 }, { "epoch": 0.4030172798116875, "grad_norm": 9.245949745178223, "learning_rate": 8.06017880070379e-06, "loss": 0.6415, "step": 67800 }, { "epoch": 0.4030767218883559, "grad_norm": 7.304440498352051, "learning_rate": 8.06136763517048e-06, "loss": 0.6996, "step": 67810 }, { "epoch": 0.4031361639650243, "grad_norm": 6.815701961517334, "learning_rate": 8.062556469637168e-06, "loss": 0.7255, "step": 67820 }, { "epoch": 0.4031956060416927, "grad_norm": 6.079727649688721, "learning_rate": 8.063745304103858e-06, "loss": 0.6783, "step": 67830 }, { "epoch": 0.40325504811836105, "grad_norm": 6.522583484649658, "learning_rate": 8.064934138570546e-06, "loss": 0.7105, "step": 67840 }, { "epoch": 0.40331449019502946, "grad_norm": 6.259696006774902, "learning_rate": 8.066122973037236e-06, "loss": 0.6546, "step": 67850 }, { "epoch": 0.4033739322716978, "grad_norm": 7.87870454788208, "learning_rate": 8.067311807503924e-06, "loss": 0.6789, "step": 67860 }, { "epoch": 0.40343337434836624, "grad_norm": 8.89218521118164, "learning_rate": 8.068500641970612e-06, "loss": 0.6939, "step": 67870 }, { "epoch": 0.40349281642503465, "grad_norm": 6.549317836761475, "learning_rate": 8.069689476437301e-06, "loss": 0.7115, "step": 67880 }, { "epoch": 0.403552258501703, "grad_norm": 6.779016017913818, "learning_rate": 8.07087831090399e-06, "loss": 0.6334, "step": 67890 }, { "epoch": 0.4036117005783714, "grad_norm": 8.130401611328125, "learning_rate": 8.07206714537068e-06, "loss": 0.6863, "step": 67900 }, { "epoch": 0.4036711426550398, "grad_norm": 8.164462089538574, "learning_rate": 8.073255979837367e-06, "loss": 0.6827, "step": 67910 }, { "epoch": 0.4037305847317082, "grad_norm": 6.3538408279418945, "learning_rate": 8.074444814304057e-06, "loss": 0.6653, "step": 67920 }, { "epoch": 0.40379002680837656, "grad_norm": 6.905200958251953, "learning_rate": 8.075633648770745e-06, "loss": 0.6802, "step": 67930 }, { "epoch": 0.40384946888504497, "grad_norm": 7.657583713531494, "learning_rate": 8.076822483237435e-06, "loss": 0.6506, "step": 67940 }, { "epoch": 0.4039089109617134, "grad_norm": 6.4212117195129395, "learning_rate": 8.078011317704123e-06, "loss": 0.6707, "step": 67950 }, { "epoch": 0.40396835303838174, "grad_norm": 8.415179252624512, "learning_rate": 8.079200152170811e-06, "loss": 0.6769, "step": 67960 }, { "epoch": 0.40402779511505016, "grad_norm": 6.299097537994385, "learning_rate": 8.080388986637501e-06, "loss": 0.6816, "step": 67970 }, { "epoch": 0.4040872371917185, "grad_norm": 9.584699630737305, "learning_rate": 8.08157782110419e-06, "loss": 0.6756, "step": 67980 }, { "epoch": 0.40414667926838693, "grad_norm": 6.145240783691406, "learning_rate": 8.082766655570879e-06, "loss": 0.6813, "step": 67990 }, { "epoch": 0.4042061213450553, "grad_norm": 6.117302894592285, "learning_rate": 8.083955490037569e-06, "loss": 0.6424, "step": 68000 }, { "epoch": 0.4042655634217237, "grad_norm": 8.39163875579834, "learning_rate": 8.085144324504257e-06, "loss": 0.6509, "step": 68010 }, { "epoch": 0.40432500549839206, "grad_norm": 6.727294445037842, "learning_rate": 8.086333158970946e-06, "loss": 0.6765, "step": 68020 }, { "epoch": 0.4043844475750605, "grad_norm": 7.206623077392578, "learning_rate": 8.087521993437635e-06, "loss": 0.6316, "step": 68030 }, { "epoch": 0.4044438896517289, "grad_norm": 4.954370021820068, "learning_rate": 8.088710827904324e-06, "loss": 0.6151, "step": 68040 }, { "epoch": 0.40450333172839725, "grad_norm": 6.046481132507324, "learning_rate": 8.089899662371012e-06, "loss": 0.5915, "step": 68050 }, { "epoch": 0.40456277380506567, "grad_norm": 7.022267818450928, "learning_rate": 8.0910884968377e-06, "loss": 0.6628, "step": 68060 }, { "epoch": 0.404622215881734, "grad_norm": 5.8727946281433105, "learning_rate": 8.09227733130439e-06, "loss": 0.6578, "step": 68070 }, { "epoch": 0.40468165795840244, "grad_norm": 7.850301265716553, "learning_rate": 8.093466165771078e-06, "loss": 0.6924, "step": 68080 }, { "epoch": 0.4047411000350708, "grad_norm": 5.956300735473633, "learning_rate": 8.094655000237768e-06, "loss": 0.7377, "step": 68090 }, { "epoch": 0.4048005421117392, "grad_norm": 7.065411567687988, "learning_rate": 8.095843834704456e-06, "loss": 0.7164, "step": 68100 }, { "epoch": 0.40485998418840763, "grad_norm": 7.0518693923950195, "learning_rate": 8.097032669171146e-06, "loss": 0.675, "step": 68110 }, { "epoch": 0.404919426265076, "grad_norm": 8.018739700317383, "learning_rate": 8.098221503637834e-06, "loss": 0.6903, "step": 68120 }, { "epoch": 0.4049788683417444, "grad_norm": 6.528355598449707, "learning_rate": 8.099410338104524e-06, "loss": 0.6786, "step": 68130 }, { "epoch": 0.40503831041841276, "grad_norm": 5.883639335632324, "learning_rate": 8.100599172571212e-06, "loss": 0.6583, "step": 68140 }, { "epoch": 0.4050977524950812, "grad_norm": 6.152071952819824, "learning_rate": 8.1017880070379e-06, "loss": 0.6744, "step": 68150 }, { "epoch": 0.40515719457174953, "grad_norm": 6.8872809410095215, "learning_rate": 8.10297684150459e-06, "loss": 0.6584, "step": 68160 }, { "epoch": 0.40521663664841795, "grad_norm": 5.413899898529053, "learning_rate": 8.104165675971278e-06, "loss": 0.7024, "step": 68170 }, { "epoch": 0.40527607872508636, "grad_norm": 4.868410587310791, "learning_rate": 8.105354510437968e-06, "loss": 0.7137, "step": 68180 }, { "epoch": 0.4053355208017547, "grad_norm": 7.1609392166137695, "learning_rate": 8.106543344904656e-06, "loss": 0.7151, "step": 68190 }, { "epoch": 0.40539496287842314, "grad_norm": 5.77379035949707, "learning_rate": 8.107732179371345e-06, "loss": 0.7238, "step": 68200 }, { "epoch": 0.4054544049550915, "grad_norm": 5.832620620727539, "learning_rate": 8.108921013838034e-06, "loss": 0.6585, "step": 68210 }, { "epoch": 0.4055138470317599, "grad_norm": 7.825527667999268, "learning_rate": 8.110109848304723e-06, "loss": 0.6834, "step": 68220 }, { "epoch": 0.40557328910842827, "grad_norm": 8.018308639526367, "learning_rate": 8.111298682771411e-06, "loss": 0.6506, "step": 68230 }, { "epoch": 0.4056327311850967, "grad_norm": 6.016313552856445, "learning_rate": 8.1124875172381e-06, "loss": 0.6701, "step": 68240 }, { "epoch": 0.4056921732617651, "grad_norm": 7.928445339202881, "learning_rate": 8.11367635170479e-06, "loss": 0.6259, "step": 68250 }, { "epoch": 0.40575161533843346, "grad_norm": 5.687241554260254, "learning_rate": 8.114865186171477e-06, "loss": 0.609, "step": 68260 }, { "epoch": 0.4058110574151019, "grad_norm": 7.025479316711426, "learning_rate": 8.116054020638167e-06, "loss": 0.7106, "step": 68270 }, { "epoch": 0.40587049949177023, "grad_norm": 6.051693439483643, "learning_rate": 8.117242855104855e-06, "loss": 0.6474, "step": 68280 }, { "epoch": 0.40592994156843865, "grad_norm": 6.460355758666992, "learning_rate": 8.118431689571545e-06, "loss": 0.6603, "step": 68290 }, { "epoch": 0.405989383645107, "grad_norm": 5.937077045440674, "learning_rate": 8.119620524038233e-06, "loss": 0.6655, "step": 68300 }, { "epoch": 0.4060488257217754, "grad_norm": 7.518810749053955, "learning_rate": 8.120809358504921e-06, "loss": 0.6267, "step": 68310 }, { "epoch": 0.40610826779844383, "grad_norm": 8.13245677947998, "learning_rate": 8.121998192971613e-06, "loss": 0.7107, "step": 68320 }, { "epoch": 0.4061677098751122, "grad_norm": 7.341948986053467, "learning_rate": 8.1231870274383e-06, "loss": 0.645, "step": 68330 }, { "epoch": 0.4062271519517806, "grad_norm": 7.894535064697266, "learning_rate": 8.124375861904989e-06, "loss": 0.6525, "step": 68340 }, { "epoch": 0.40628659402844897, "grad_norm": 6.912683963775635, "learning_rate": 8.125564696371678e-06, "loss": 0.6815, "step": 68350 }, { "epoch": 0.4063460361051174, "grad_norm": 8.313326835632324, "learning_rate": 8.126753530838367e-06, "loss": 0.6786, "step": 68360 }, { "epoch": 0.40640547818178574, "grad_norm": 6.995736122131348, "learning_rate": 8.127942365305056e-06, "loss": 0.6942, "step": 68370 }, { "epoch": 0.40646492025845415, "grad_norm": 6.315192699432373, "learning_rate": 8.129131199771744e-06, "loss": 0.7276, "step": 68380 }, { "epoch": 0.4065243623351225, "grad_norm": 7.0395612716674805, "learning_rate": 8.130320034238434e-06, "loss": 0.7047, "step": 68390 }, { "epoch": 0.40658380441179093, "grad_norm": 6.56497049331665, "learning_rate": 8.131508868705122e-06, "loss": 0.6908, "step": 68400 }, { "epoch": 0.40664324648845934, "grad_norm": 7.652003765106201, "learning_rate": 8.132697703171812e-06, "loss": 0.7007, "step": 68410 }, { "epoch": 0.4067026885651277, "grad_norm": 6.683058738708496, "learning_rate": 8.1338865376385e-06, "loss": 0.6754, "step": 68420 }, { "epoch": 0.4067621306417961, "grad_norm": 7.537511825561523, "learning_rate": 8.135075372105188e-06, "loss": 0.6552, "step": 68430 }, { "epoch": 0.4068215727184645, "grad_norm": 7.41231632232666, "learning_rate": 8.136264206571878e-06, "loss": 0.6027, "step": 68440 }, { "epoch": 0.4068810147951329, "grad_norm": 6.504142761230469, "learning_rate": 8.137453041038566e-06, "loss": 0.6372, "step": 68450 }, { "epoch": 0.40694045687180125, "grad_norm": 7.992889881134033, "learning_rate": 8.138641875505256e-06, "loss": 0.6772, "step": 68460 }, { "epoch": 0.40699989894846966, "grad_norm": 6.195249557495117, "learning_rate": 8.139830709971944e-06, "loss": 0.697, "step": 68470 }, { "epoch": 0.4070593410251381, "grad_norm": 7.181275844573975, "learning_rate": 8.141019544438634e-06, "loss": 0.635, "step": 68480 }, { "epoch": 0.40711878310180644, "grad_norm": 6.313637733459473, "learning_rate": 8.142208378905322e-06, "loss": 0.6478, "step": 68490 }, { "epoch": 0.40717822517847485, "grad_norm": 6.872747421264648, "learning_rate": 8.143397213372012e-06, "loss": 0.6289, "step": 68500 }, { "epoch": 0.4072376672551432, "grad_norm": 8.477531433105469, "learning_rate": 8.1445860478387e-06, "loss": 0.6646, "step": 68510 }, { "epoch": 0.4072971093318116, "grad_norm": 8.865950584411621, "learning_rate": 8.145774882305388e-06, "loss": 0.643, "step": 68520 }, { "epoch": 0.40735655140848, "grad_norm": 6.484926700592041, "learning_rate": 8.146963716772077e-06, "loss": 0.6914, "step": 68530 }, { "epoch": 0.4074159934851484, "grad_norm": 7.294343948364258, "learning_rate": 8.148152551238766e-06, "loss": 0.632, "step": 68540 }, { "epoch": 0.4074754355618168, "grad_norm": 4.868592739105225, "learning_rate": 8.149341385705455e-06, "loss": 0.6515, "step": 68550 }, { "epoch": 0.40753487763848517, "grad_norm": 6.952846527099609, "learning_rate": 8.150530220172143e-06, "loss": 0.5895, "step": 68560 }, { "epoch": 0.4075943197151536, "grad_norm": 7.32137393951416, "learning_rate": 8.151719054638833e-06, "loss": 0.7378, "step": 68570 }, { "epoch": 0.40765376179182194, "grad_norm": 10.721399307250977, "learning_rate": 8.152907889105521e-06, "loss": 0.6613, "step": 68580 }, { "epoch": 0.40771320386849036, "grad_norm": 6.629125118255615, "learning_rate": 8.15409672357221e-06, "loss": 0.6408, "step": 68590 }, { "epoch": 0.4077726459451587, "grad_norm": 6.886807441711426, "learning_rate": 8.155285558038899e-06, "loss": 0.6722, "step": 68600 }, { "epoch": 0.40783208802182713, "grad_norm": 7.0825371742248535, "learning_rate": 8.156474392505587e-06, "loss": 0.6767, "step": 68610 }, { "epoch": 0.40789153009849555, "grad_norm": 8.707897186279297, "learning_rate": 8.157663226972277e-06, "loss": 0.7182, "step": 68620 }, { "epoch": 0.4079509721751639, "grad_norm": 7.300644874572754, "learning_rate": 8.158852061438965e-06, "loss": 0.6566, "step": 68630 }, { "epoch": 0.4080104142518323, "grad_norm": 5.88929557800293, "learning_rate": 8.160040895905655e-06, "loss": 0.6679, "step": 68640 }, { "epoch": 0.4080698563285007, "grad_norm": 6.290867328643799, "learning_rate": 8.161229730372343e-06, "loss": 0.6225, "step": 68650 }, { "epoch": 0.4081292984051691, "grad_norm": 7.360879421234131, "learning_rate": 8.162418564839033e-06, "loss": 0.6146, "step": 68660 }, { "epoch": 0.40818874048183745, "grad_norm": 5.925520420074463, "learning_rate": 8.163607399305722e-06, "loss": 0.641, "step": 68670 }, { "epoch": 0.40824818255850587, "grad_norm": 5.866004467010498, "learning_rate": 8.16479623377241e-06, "loss": 0.6132, "step": 68680 }, { "epoch": 0.4083076246351743, "grad_norm": 7.686215877532959, "learning_rate": 8.1659850682391e-06, "loss": 0.6812, "step": 68690 }, { "epoch": 0.40836706671184264, "grad_norm": 7.197736740112305, "learning_rate": 8.167173902705788e-06, "loss": 0.6748, "step": 68700 }, { "epoch": 0.40842650878851106, "grad_norm": 6.570836544036865, "learning_rate": 8.168362737172476e-06, "loss": 0.6688, "step": 68710 }, { "epoch": 0.4084859508651794, "grad_norm": 6.05321741104126, "learning_rate": 8.169551571639166e-06, "loss": 0.6555, "step": 68720 }, { "epoch": 0.40854539294184783, "grad_norm": 7.664514064788818, "learning_rate": 8.170740406105854e-06, "loss": 0.6892, "step": 68730 }, { "epoch": 0.4086048350185162, "grad_norm": 6.353972434997559, "learning_rate": 8.171929240572544e-06, "loss": 0.7, "step": 68740 }, { "epoch": 0.4086642770951846, "grad_norm": 7.827902793884277, "learning_rate": 8.173118075039232e-06, "loss": 0.6145, "step": 68750 }, { "epoch": 0.40872371917185296, "grad_norm": 6.805201053619385, "learning_rate": 8.174306909505922e-06, "loss": 0.6318, "step": 68760 }, { "epoch": 0.4087831612485214, "grad_norm": 4.940573692321777, "learning_rate": 8.17549574397261e-06, "loss": 0.6061, "step": 68770 }, { "epoch": 0.4088426033251898, "grad_norm": 6.64068078994751, "learning_rate": 8.176684578439298e-06, "loss": 0.6298, "step": 68780 }, { "epoch": 0.40890204540185815, "grad_norm": 8.603415489196777, "learning_rate": 8.177873412905988e-06, "loss": 0.7207, "step": 68790 }, { "epoch": 0.40896148747852656, "grad_norm": 6.005021095275879, "learning_rate": 8.179062247372676e-06, "loss": 0.6241, "step": 68800 }, { "epoch": 0.4090209295551949, "grad_norm": 7.081853866577148, "learning_rate": 8.180251081839366e-06, "loss": 0.6543, "step": 68810 }, { "epoch": 0.40908037163186334, "grad_norm": 7.833479881286621, "learning_rate": 8.181439916306054e-06, "loss": 0.6865, "step": 68820 }, { "epoch": 0.4091398137085317, "grad_norm": 5.314047813415527, "learning_rate": 8.182628750772744e-06, "loss": 0.6097, "step": 68830 }, { "epoch": 0.4091992557852001, "grad_norm": 7.7885260581970215, "learning_rate": 8.183817585239432e-06, "loss": 0.7015, "step": 68840 }, { "epoch": 0.4092586978618685, "grad_norm": 11.121850967407227, "learning_rate": 8.185006419706121e-06, "loss": 0.6907, "step": 68850 }, { "epoch": 0.4093181399385369, "grad_norm": 6.363918304443359, "learning_rate": 8.18619525417281e-06, "loss": 0.6844, "step": 68860 }, { "epoch": 0.4093775820152053, "grad_norm": 8.671557426452637, "learning_rate": 8.187384088639498e-06, "loss": 0.6936, "step": 68870 }, { "epoch": 0.40943702409187366, "grad_norm": 7.712821006774902, "learning_rate": 8.188572923106187e-06, "loss": 0.6659, "step": 68880 }, { "epoch": 0.4094964661685421, "grad_norm": 7.040086269378662, "learning_rate": 8.189761757572875e-06, "loss": 0.6631, "step": 68890 }, { "epoch": 0.40955590824521043, "grad_norm": 6.166328430175781, "learning_rate": 8.190950592039565e-06, "loss": 0.6748, "step": 68900 }, { "epoch": 0.40961535032187885, "grad_norm": 7.300423622131348, "learning_rate": 8.192139426506253e-06, "loss": 0.6888, "step": 68910 }, { "epoch": 0.40967479239854726, "grad_norm": 7.562082767486572, "learning_rate": 8.193328260972943e-06, "loss": 0.6896, "step": 68920 }, { "epoch": 0.4097342344752156, "grad_norm": 8.590982437133789, "learning_rate": 8.194517095439631e-06, "loss": 0.6301, "step": 68930 }, { "epoch": 0.40979367655188403, "grad_norm": 7.361490726470947, "learning_rate": 8.195705929906321e-06, "loss": 0.62, "step": 68940 }, { "epoch": 0.4098531186285524, "grad_norm": 6.127954006195068, "learning_rate": 8.196894764373009e-06, "loss": 0.6867, "step": 68950 }, { "epoch": 0.4099125607052208, "grad_norm": 7.179299831390381, "learning_rate": 8.198083598839697e-06, "loss": 0.7172, "step": 68960 }, { "epoch": 0.40997200278188917, "grad_norm": 6.0775861740112305, "learning_rate": 8.199272433306387e-06, "loss": 0.6834, "step": 68970 }, { "epoch": 0.4100314448585576, "grad_norm": 6.727396488189697, "learning_rate": 8.200461267773075e-06, "loss": 0.613, "step": 68980 }, { "epoch": 0.410090886935226, "grad_norm": 7.278382778167725, "learning_rate": 8.201650102239765e-06, "loss": 0.6201, "step": 68990 }, { "epoch": 0.41015032901189435, "grad_norm": 7.2108378410339355, "learning_rate": 8.202838936706453e-06, "loss": 0.7077, "step": 69000 }, { "epoch": 0.41020977108856277, "grad_norm": 8.97732162475586, "learning_rate": 8.204027771173143e-06, "loss": 0.6722, "step": 69010 }, { "epoch": 0.41026921316523113, "grad_norm": 6.940165996551514, "learning_rate": 8.205216605639832e-06, "loss": 0.6398, "step": 69020 }, { "epoch": 0.41032865524189954, "grad_norm": 8.258284568786621, "learning_rate": 8.20640544010652e-06, "loss": 0.667, "step": 69030 }, { "epoch": 0.4103880973185679, "grad_norm": 7.171750545501709, "learning_rate": 8.20759427457321e-06, "loss": 0.6931, "step": 69040 }, { "epoch": 0.4104475393952363, "grad_norm": 6.832279205322266, "learning_rate": 8.208783109039898e-06, "loss": 0.6592, "step": 69050 }, { "epoch": 0.4105069814719047, "grad_norm": 5.945559978485107, "learning_rate": 8.209971943506586e-06, "loss": 0.6515, "step": 69060 }, { "epoch": 0.4105664235485731, "grad_norm": 4.870020389556885, "learning_rate": 8.211160777973276e-06, "loss": 0.6572, "step": 69070 }, { "epoch": 0.4106258656252415, "grad_norm": 6.596096038818359, "learning_rate": 8.212349612439964e-06, "loss": 0.6423, "step": 69080 }, { "epoch": 0.41068530770190986, "grad_norm": 5.112392425537109, "learning_rate": 8.213538446906654e-06, "loss": 0.643, "step": 69090 }, { "epoch": 0.4107447497785783, "grad_norm": 8.510865211486816, "learning_rate": 8.214727281373342e-06, "loss": 0.6999, "step": 69100 }, { "epoch": 0.41080419185524664, "grad_norm": 6.659651279449463, "learning_rate": 8.215916115840032e-06, "loss": 0.6541, "step": 69110 }, { "epoch": 0.41086363393191505, "grad_norm": 6.044216156005859, "learning_rate": 8.21710495030672e-06, "loss": 0.6763, "step": 69120 }, { "epoch": 0.4109230760085834, "grad_norm": 7.8809967041015625, "learning_rate": 8.21829378477341e-06, "loss": 0.7069, "step": 69130 }, { "epoch": 0.4109825180852518, "grad_norm": 7.396500587463379, "learning_rate": 8.219482619240098e-06, "loss": 0.7377, "step": 69140 }, { "epoch": 0.41104196016192024, "grad_norm": 7.343302249908447, "learning_rate": 8.220671453706786e-06, "loss": 0.7229, "step": 69150 }, { "epoch": 0.4111014022385886, "grad_norm": 5.6266560554504395, "learning_rate": 8.221860288173476e-06, "loss": 0.7051, "step": 69160 }, { "epoch": 0.411160844315257, "grad_norm": 6.760825157165527, "learning_rate": 8.223049122640164e-06, "loss": 0.6799, "step": 69170 }, { "epoch": 0.41122028639192537, "grad_norm": 6.0905914306640625, "learning_rate": 8.224237957106854e-06, "loss": 0.7108, "step": 69180 }, { "epoch": 0.4112797284685938, "grad_norm": 7.496442794799805, "learning_rate": 8.225426791573542e-06, "loss": 0.6704, "step": 69190 }, { "epoch": 0.41133917054526214, "grad_norm": 7.914169788360596, "learning_rate": 8.226615626040231e-06, "loss": 0.6889, "step": 69200 }, { "epoch": 0.41139861262193056, "grad_norm": 8.71681022644043, "learning_rate": 8.22780446050692e-06, "loss": 0.7006, "step": 69210 }, { "epoch": 0.411458054698599, "grad_norm": 7.1278862953186035, "learning_rate": 8.22899329497361e-06, "loss": 0.7179, "step": 69220 }, { "epoch": 0.41151749677526733, "grad_norm": 7.787039756774902, "learning_rate": 8.230182129440297e-06, "loss": 0.7072, "step": 69230 }, { "epoch": 0.41157693885193575, "grad_norm": 7.768682956695557, "learning_rate": 8.231370963906985e-06, "loss": 0.7286, "step": 69240 }, { "epoch": 0.4116363809286041, "grad_norm": 6.9691548347473145, "learning_rate": 8.232559798373675e-06, "loss": 0.6712, "step": 69250 }, { "epoch": 0.4116958230052725, "grad_norm": 5.224923610687256, "learning_rate": 8.233748632840363e-06, "loss": 0.6481, "step": 69260 }, { "epoch": 0.4117552650819409, "grad_norm": 6.9257893562316895, "learning_rate": 8.234937467307053e-06, "loss": 0.6167, "step": 69270 }, { "epoch": 0.4118147071586093, "grad_norm": 7.232560157775879, "learning_rate": 8.236126301773741e-06, "loss": 0.6642, "step": 69280 }, { "epoch": 0.4118741492352777, "grad_norm": 7.862437725067139, "learning_rate": 8.237315136240431e-06, "loss": 0.6934, "step": 69290 }, { "epoch": 0.41193359131194607, "grad_norm": 8.550267219543457, "learning_rate": 8.238503970707119e-06, "loss": 0.7183, "step": 69300 }, { "epoch": 0.4119930333886145, "grad_norm": 7.422458171844482, "learning_rate": 8.239692805173807e-06, "loss": 0.7578, "step": 69310 }, { "epoch": 0.41205247546528284, "grad_norm": 6.421939849853516, "learning_rate": 8.240881639640497e-06, "loss": 0.6545, "step": 69320 }, { "epoch": 0.41211191754195126, "grad_norm": 6.071089267730713, "learning_rate": 8.242070474107185e-06, "loss": 0.671, "step": 69330 }, { "epoch": 0.4121713596186196, "grad_norm": 5.341770648956299, "learning_rate": 8.243259308573875e-06, "loss": 0.6952, "step": 69340 }, { "epoch": 0.41223080169528803, "grad_norm": 6.316440582275391, "learning_rate": 8.244448143040563e-06, "loss": 0.6559, "step": 69350 }, { "epoch": 0.41229024377195644, "grad_norm": 5.815812110900879, "learning_rate": 8.245636977507253e-06, "loss": 0.6324, "step": 69360 }, { "epoch": 0.4123496858486248, "grad_norm": 7.173856258392334, "learning_rate": 8.246825811973942e-06, "loss": 0.5976, "step": 69370 }, { "epoch": 0.4124091279252932, "grad_norm": 6.583034038543701, "learning_rate": 8.24801464644063e-06, "loss": 0.6306, "step": 69380 }, { "epoch": 0.4124685700019616, "grad_norm": 5.715179443359375, "learning_rate": 8.24920348090732e-06, "loss": 0.6913, "step": 69390 }, { "epoch": 0.41252801207863, "grad_norm": 7.658084392547607, "learning_rate": 8.250392315374008e-06, "loss": 0.6804, "step": 69400 }, { "epoch": 0.41258745415529835, "grad_norm": 6.968790054321289, "learning_rate": 8.251581149840698e-06, "loss": 0.6631, "step": 69410 }, { "epoch": 0.41264689623196676, "grad_norm": 9.214428901672363, "learning_rate": 8.252769984307386e-06, "loss": 0.7164, "step": 69420 }, { "epoch": 0.4127063383086351, "grad_norm": 7.356113910675049, "learning_rate": 8.253958818774074e-06, "loss": 0.6842, "step": 69430 }, { "epoch": 0.41276578038530354, "grad_norm": 8.312335968017578, "learning_rate": 8.255147653240764e-06, "loss": 0.7251, "step": 69440 }, { "epoch": 0.41282522246197195, "grad_norm": 6.316954612731934, "learning_rate": 8.256336487707452e-06, "loss": 0.6708, "step": 69450 }, { "epoch": 0.4128846645386403, "grad_norm": 5.402197360992432, "learning_rate": 8.257525322174142e-06, "loss": 0.6726, "step": 69460 }, { "epoch": 0.4129441066153087, "grad_norm": 6.511620044708252, "learning_rate": 8.25871415664083e-06, "loss": 0.7136, "step": 69470 }, { "epoch": 0.4130035486919771, "grad_norm": 6.05623197555542, "learning_rate": 8.25990299110752e-06, "loss": 0.6306, "step": 69480 }, { "epoch": 0.4130629907686455, "grad_norm": 7.875879287719727, "learning_rate": 8.261091825574208e-06, "loss": 0.7409, "step": 69490 }, { "epoch": 0.41312243284531386, "grad_norm": 6.208570957183838, "learning_rate": 8.262280660040898e-06, "loss": 0.7337, "step": 69500 }, { "epoch": 0.4131818749219823, "grad_norm": 5.888752460479736, "learning_rate": 8.263469494507586e-06, "loss": 0.6835, "step": 69510 }, { "epoch": 0.4132413169986507, "grad_norm": 7.615411281585693, "learning_rate": 8.264658328974274e-06, "loss": 0.6839, "step": 69520 }, { "epoch": 0.41330075907531905, "grad_norm": 6.815091609954834, "learning_rate": 8.265847163440963e-06, "loss": 0.6459, "step": 69530 }, { "epoch": 0.41336020115198746, "grad_norm": 5.543855667114258, "learning_rate": 8.267035997907652e-06, "loss": 0.6726, "step": 69540 }, { "epoch": 0.4134196432286558, "grad_norm": 6.6442952156066895, "learning_rate": 8.268224832374341e-06, "loss": 0.6011, "step": 69550 }, { "epoch": 0.41347908530532423, "grad_norm": 7.830672264099121, "learning_rate": 8.26941366684103e-06, "loss": 0.6734, "step": 69560 }, { "epoch": 0.4135385273819926, "grad_norm": 9.312487602233887, "learning_rate": 8.27060250130772e-06, "loss": 0.6891, "step": 69570 }, { "epoch": 0.413597969458661, "grad_norm": 7.380489349365234, "learning_rate": 8.271791335774407e-06, "loss": 0.6522, "step": 69580 }, { "epoch": 0.4136574115353294, "grad_norm": 8.490952491760254, "learning_rate": 8.272980170241095e-06, "loss": 0.7128, "step": 69590 }, { "epoch": 0.4137168536119978, "grad_norm": 6.7202558517456055, "learning_rate": 8.274169004707785e-06, "loss": 0.7036, "step": 69600 }, { "epoch": 0.4137762956886662, "grad_norm": 5.734074115753174, "learning_rate": 8.275357839174473e-06, "loss": 0.681, "step": 69610 }, { "epoch": 0.41383573776533455, "grad_norm": 6.332306385040283, "learning_rate": 8.276546673641163e-06, "loss": 0.6431, "step": 69620 }, { "epoch": 0.41389517984200297, "grad_norm": 6.548084735870361, "learning_rate": 8.277735508107851e-06, "loss": 0.6724, "step": 69630 }, { "epoch": 0.41395462191867133, "grad_norm": 6.519715785980225, "learning_rate": 8.27892434257454e-06, "loss": 0.6392, "step": 69640 }, { "epoch": 0.41401406399533974, "grad_norm": 8.00912857055664, "learning_rate": 8.280113177041229e-06, "loss": 0.6764, "step": 69650 }, { "epoch": 0.41407350607200816, "grad_norm": 6.340163230895996, "learning_rate": 8.281302011507919e-06, "loss": 0.6757, "step": 69660 }, { "epoch": 0.4141329481486765, "grad_norm": 7.518279075622559, "learning_rate": 8.282490845974607e-06, "loss": 0.7242, "step": 69670 }, { "epoch": 0.41419239022534493, "grad_norm": 7.58978271484375, "learning_rate": 8.283679680441295e-06, "loss": 0.6397, "step": 69680 }, { "epoch": 0.4142518323020133, "grad_norm": 5.956188678741455, "learning_rate": 8.284868514907985e-06, "loss": 0.6125, "step": 69690 }, { "epoch": 0.4143112743786817, "grad_norm": 6.899079322814941, "learning_rate": 8.286057349374673e-06, "loss": 0.7004, "step": 69700 }, { "epoch": 0.41437071645535006, "grad_norm": 6.37280797958374, "learning_rate": 8.287246183841362e-06, "loss": 0.7045, "step": 69710 }, { "epoch": 0.4144301585320185, "grad_norm": 7.548154830932617, "learning_rate": 8.288435018308052e-06, "loss": 0.6956, "step": 69720 }, { "epoch": 0.4144896006086869, "grad_norm": 5.889989852905273, "learning_rate": 8.28962385277474e-06, "loss": 0.6793, "step": 69730 }, { "epoch": 0.41454904268535525, "grad_norm": 6.593671798706055, "learning_rate": 8.29081268724143e-06, "loss": 0.6809, "step": 69740 }, { "epoch": 0.41460848476202367, "grad_norm": 6.063546180725098, "learning_rate": 8.292001521708118e-06, "loss": 0.6343, "step": 69750 }, { "epoch": 0.414667926838692, "grad_norm": 6.701039791107178, "learning_rate": 8.293190356174808e-06, "loss": 0.6912, "step": 69760 }, { "epoch": 0.41472736891536044, "grad_norm": 6.305469989776611, "learning_rate": 8.294379190641496e-06, "loss": 0.6326, "step": 69770 }, { "epoch": 0.4147868109920288, "grad_norm": 6.367061614990234, "learning_rate": 8.295568025108184e-06, "loss": 0.6773, "step": 69780 }, { "epoch": 0.4148462530686972, "grad_norm": 7.193323135375977, "learning_rate": 8.296756859574874e-06, "loss": 0.6978, "step": 69790 }, { "epoch": 0.41490569514536557, "grad_norm": 6.610983371734619, "learning_rate": 8.297945694041562e-06, "loss": 0.6736, "step": 69800 }, { "epoch": 0.414965137222034, "grad_norm": 6.093362331390381, "learning_rate": 8.299134528508252e-06, "loss": 0.6413, "step": 69810 }, { "epoch": 0.4150245792987024, "grad_norm": 6.8765058517456055, "learning_rate": 8.30032336297494e-06, "loss": 0.6803, "step": 69820 }, { "epoch": 0.41508402137537076, "grad_norm": 5.7483954429626465, "learning_rate": 8.30151219744163e-06, "loss": 0.6889, "step": 69830 }, { "epoch": 0.4151434634520392, "grad_norm": 6.687528610229492, "learning_rate": 8.302701031908318e-06, "loss": 0.6181, "step": 69840 }, { "epoch": 0.41520290552870753, "grad_norm": 6.71911096572876, "learning_rate": 8.303889866375007e-06, "loss": 0.6889, "step": 69850 }, { "epoch": 0.41526234760537595, "grad_norm": 5.26820182800293, "learning_rate": 8.305078700841696e-06, "loss": 0.6199, "step": 69860 }, { "epoch": 0.4153217896820443, "grad_norm": 5.912913799285889, "learning_rate": 8.306267535308384e-06, "loss": 0.6337, "step": 69870 }, { "epoch": 0.4153812317587127, "grad_norm": 5.40774393081665, "learning_rate": 8.307456369775073e-06, "loss": 0.6687, "step": 69880 }, { "epoch": 0.41544067383538114, "grad_norm": 7.7188615798950195, "learning_rate": 8.308645204241761e-06, "loss": 0.7524, "step": 69890 }, { "epoch": 0.4155001159120495, "grad_norm": 7.026173114776611, "learning_rate": 8.309834038708451e-06, "loss": 0.6519, "step": 69900 }, { "epoch": 0.4155595579887179, "grad_norm": 6.502613544464111, "learning_rate": 8.31102287317514e-06, "loss": 0.6836, "step": 69910 }, { "epoch": 0.41561900006538627, "grad_norm": 5.876067161560059, "learning_rate": 8.312211707641829e-06, "loss": 0.6608, "step": 69920 }, { "epoch": 0.4156784421420547, "grad_norm": 5.463468551635742, "learning_rate": 8.313400542108517e-06, "loss": 0.5719, "step": 69930 }, { "epoch": 0.41573788421872304, "grad_norm": 6.5357866287231445, "learning_rate": 8.314589376575207e-06, "loss": 0.7101, "step": 69940 }, { "epoch": 0.41579732629539146, "grad_norm": 7.664540767669678, "learning_rate": 8.315778211041895e-06, "loss": 0.6673, "step": 69950 }, { "epoch": 0.41585676837205987, "grad_norm": 8.708184242248535, "learning_rate": 8.316967045508583e-06, "loss": 0.7376, "step": 69960 }, { "epoch": 0.41591621044872823, "grad_norm": 6.6789350509643555, "learning_rate": 8.318155879975273e-06, "loss": 0.6832, "step": 69970 }, { "epoch": 0.41597565252539664, "grad_norm": 6.386125564575195, "learning_rate": 8.319344714441961e-06, "loss": 0.7427, "step": 69980 }, { "epoch": 0.416035094602065, "grad_norm": 7.5171895027160645, "learning_rate": 8.32053354890865e-06, "loss": 0.6717, "step": 69990 }, { "epoch": 0.4160945366787334, "grad_norm": 5.86421012878418, "learning_rate": 8.321722383375339e-06, "loss": 0.6293, "step": 70000 }, { "epoch": 0.4161539787554018, "grad_norm": 6.21876859664917, "learning_rate": 8.322911217842029e-06, "loss": 0.6712, "step": 70010 }, { "epoch": 0.4162134208320702, "grad_norm": 5.785694122314453, "learning_rate": 8.324100052308717e-06, "loss": 0.651, "step": 70020 }, { "epoch": 0.4162728629087386, "grad_norm": 7.952736854553223, "learning_rate": 8.325288886775406e-06, "loss": 0.6566, "step": 70030 }, { "epoch": 0.41633230498540696, "grad_norm": 5.189696788787842, "learning_rate": 8.326477721242095e-06, "loss": 0.6415, "step": 70040 }, { "epoch": 0.4163917470620754, "grad_norm": 5.910279750823975, "learning_rate": 8.327666555708783e-06, "loss": 0.6661, "step": 70050 }, { "epoch": 0.41645118913874374, "grad_norm": 6.538419723510742, "learning_rate": 8.328855390175472e-06, "loss": 0.6288, "step": 70060 }, { "epoch": 0.41651063121541215, "grad_norm": 5.166141986846924, "learning_rate": 8.330044224642162e-06, "loss": 0.6758, "step": 70070 }, { "epoch": 0.4165700732920805, "grad_norm": 5.162074089050293, "learning_rate": 8.33123305910885e-06, "loss": 0.615, "step": 70080 }, { "epoch": 0.4166295153687489, "grad_norm": 7.477092266082764, "learning_rate": 8.33242189357554e-06, "loss": 0.6602, "step": 70090 }, { "epoch": 0.41668895744541734, "grad_norm": 6.875611305236816, "learning_rate": 8.333610728042228e-06, "loss": 0.6798, "step": 70100 }, { "epoch": 0.4167483995220857, "grad_norm": 7.133883476257324, "learning_rate": 8.334799562508918e-06, "loss": 0.639, "step": 70110 }, { "epoch": 0.4168078415987541, "grad_norm": 6.4549665451049805, "learning_rate": 8.335988396975606e-06, "loss": 0.6987, "step": 70120 }, { "epoch": 0.4168672836754225, "grad_norm": 5.905495643615723, "learning_rate": 8.337177231442296e-06, "loss": 0.624, "step": 70130 }, { "epoch": 0.4169267257520909, "grad_norm": 8.087959289550781, "learning_rate": 8.338366065908984e-06, "loss": 0.7247, "step": 70140 }, { "epoch": 0.41698616782875925, "grad_norm": 5.615830421447754, "learning_rate": 8.339554900375672e-06, "loss": 0.6714, "step": 70150 }, { "epoch": 0.41704560990542766, "grad_norm": 7.552428245544434, "learning_rate": 8.340743734842362e-06, "loss": 0.6914, "step": 70160 }, { "epoch": 0.417105051982096, "grad_norm": 5.065493106842041, "learning_rate": 8.34193256930905e-06, "loss": 0.6196, "step": 70170 }, { "epoch": 0.41716449405876443, "grad_norm": 8.446308135986328, "learning_rate": 8.34312140377574e-06, "loss": 0.6497, "step": 70180 }, { "epoch": 0.41722393613543285, "grad_norm": 7.823807716369629, "learning_rate": 8.344310238242428e-06, "loss": 0.6735, "step": 70190 }, { "epoch": 0.4172833782121012, "grad_norm": 6.529909133911133, "learning_rate": 8.345499072709117e-06, "loss": 0.7012, "step": 70200 }, { "epoch": 0.4173428202887696, "grad_norm": 6.062841892242432, "learning_rate": 8.346687907175805e-06, "loss": 0.6305, "step": 70210 }, { "epoch": 0.417402262365438, "grad_norm": 7.608251571655273, "learning_rate": 8.347876741642495e-06, "loss": 0.6421, "step": 70220 }, { "epoch": 0.4174617044421064, "grad_norm": 8.493772506713867, "learning_rate": 8.349065576109183e-06, "loss": 0.6689, "step": 70230 }, { "epoch": 0.41752114651877476, "grad_norm": 4.172319412231445, "learning_rate": 8.350254410575871e-06, "loss": 0.6281, "step": 70240 }, { "epoch": 0.41758058859544317, "grad_norm": 5.665768623352051, "learning_rate": 8.351443245042561e-06, "loss": 0.666, "step": 70250 }, { "epoch": 0.4176400306721116, "grad_norm": 8.777885437011719, "learning_rate": 8.35263207950925e-06, "loss": 0.6726, "step": 70260 }, { "epoch": 0.41769947274877994, "grad_norm": 7.8135528564453125, "learning_rate": 8.353820913975939e-06, "loss": 0.6391, "step": 70270 }, { "epoch": 0.41775891482544836, "grad_norm": 6.577381610870361, "learning_rate": 8.355009748442627e-06, "loss": 0.66, "step": 70280 }, { "epoch": 0.4178183569021167, "grad_norm": 6.561980247497559, "learning_rate": 8.356198582909317e-06, "loss": 0.6875, "step": 70290 }, { "epoch": 0.41787779897878513, "grad_norm": 7.215855121612549, "learning_rate": 8.357387417376005e-06, "loss": 0.6488, "step": 70300 }, { "epoch": 0.4179372410554535, "grad_norm": 6.9553070068359375, "learning_rate": 8.358576251842693e-06, "loss": 0.6735, "step": 70310 }, { "epoch": 0.4179966831321219, "grad_norm": 7.642405986785889, "learning_rate": 8.359765086309383e-06, "loss": 0.6914, "step": 70320 }, { "epoch": 0.4180561252087903, "grad_norm": 8.955638885498047, "learning_rate": 8.360953920776071e-06, "loss": 0.7023, "step": 70330 }, { "epoch": 0.4181155672854587, "grad_norm": 7.934467315673828, "learning_rate": 8.36214275524276e-06, "loss": 0.6764, "step": 70340 }, { "epoch": 0.4181750093621271, "grad_norm": 5.4096503257751465, "learning_rate": 8.363331589709449e-06, "loss": 0.6304, "step": 70350 }, { "epoch": 0.41823445143879545, "grad_norm": 7.260209560394287, "learning_rate": 8.364520424176138e-06, "loss": 0.6755, "step": 70360 }, { "epoch": 0.41829389351546387, "grad_norm": 8.612629890441895, "learning_rate": 8.365709258642827e-06, "loss": 0.7021, "step": 70370 }, { "epoch": 0.4183533355921322, "grad_norm": 7.249020576477051, "learning_rate": 8.366898093109516e-06, "loss": 0.6465, "step": 70380 }, { "epoch": 0.41841277766880064, "grad_norm": 7.610889911651611, "learning_rate": 8.368086927576204e-06, "loss": 0.707, "step": 70390 }, { "epoch": 0.41847221974546905, "grad_norm": 8.574034690856934, "learning_rate": 8.369275762042894e-06, "loss": 0.6302, "step": 70400 }, { "epoch": 0.4185316618221374, "grad_norm": 8.222990036010742, "learning_rate": 8.370464596509584e-06, "loss": 0.6378, "step": 70410 }, { "epoch": 0.4185911038988058, "grad_norm": 5.524648189544678, "learning_rate": 8.371653430976272e-06, "loss": 0.6108, "step": 70420 }, { "epoch": 0.4186505459754742, "grad_norm": 8.298617362976074, "learning_rate": 8.37284226544296e-06, "loss": 0.7194, "step": 70430 }, { "epoch": 0.4187099880521426, "grad_norm": 6.635116100311279, "learning_rate": 8.37403109990965e-06, "loss": 0.6551, "step": 70440 }, { "epoch": 0.41876943012881096, "grad_norm": 5.859543800354004, "learning_rate": 8.375219934376338e-06, "loss": 0.6528, "step": 70450 }, { "epoch": 0.4188288722054794, "grad_norm": 6.725942134857178, "learning_rate": 8.376408768843028e-06, "loss": 0.6648, "step": 70460 }, { "epoch": 0.41888831428214773, "grad_norm": 6.780520439147949, "learning_rate": 8.377597603309716e-06, "loss": 0.7035, "step": 70470 }, { "epoch": 0.41894775635881615, "grad_norm": 6.420753479003906, "learning_rate": 8.378786437776406e-06, "loss": 0.6615, "step": 70480 }, { "epoch": 0.41900719843548456, "grad_norm": 5.394585609436035, "learning_rate": 8.379975272243094e-06, "loss": 0.6598, "step": 70490 }, { "epoch": 0.4190666405121529, "grad_norm": 6.853890419006348, "learning_rate": 8.381164106709783e-06, "loss": 0.6319, "step": 70500 }, { "epoch": 0.41912608258882134, "grad_norm": 7.030099391937256, "learning_rate": 8.382352941176472e-06, "loss": 0.6342, "step": 70510 }, { "epoch": 0.4191855246654897, "grad_norm": 7.067277908325195, "learning_rate": 8.38354177564316e-06, "loss": 0.6755, "step": 70520 }, { "epoch": 0.4192449667421581, "grad_norm": 5.970037460327148, "learning_rate": 8.38473061010985e-06, "loss": 0.6767, "step": 70530 }, { "epoch": 0.41930440881882647, "grad_norm": 6.662237644195557, "learning_rate": 8.385919444576537e-06, "loss": 0.6272, "step": 70540 }, { "epoch": 0.4193638508954949, "grad_norm": 9.187134742736816, "learning_rate": 8.387108279043227e-06, "loss": 0.6842, "step": 70550 }, { "epoch": 0.4194232929721633, "grad_norm": 6.6949615478515625, "learning_rate": 8.388297113509915e-06, "loss": 0.6806, "step": 70560 }, { "epoch": 0.41948273504883166, "grad_norm": 7.3677496910095215, "learning_rate": 8.389485947976605e-06, "loss": 0.7031, "step": 70570 }, { "epoch": 0.41954217712550007, "grad_norm": 8.854146003723145, "learning_rate": 8.390674782443293e-06, "loss": 0.629, "step": 70580 }, { "epoch": 0.41960161920216843, "grad_norm": 6.139310359954834, "learning_rate": 8.391863616909981e-06, "loss": 0.6077, "step": 70590 }, { "epoch": 0.41966106127883684, "grad_norm": 8.567008018493652, "learning_rate": 8.393052451376671e-06, "loss": 0.648, "step": 70600 }, { "epoch": 0.4197205033555052, "grad_norm": 6.811201095581055, "learning_rate": 8.394241285843359e-06, "loss": 0.6704, "step": 70610 }, { "epoch": 0.4197799454321736, "grad_norm": 6.335256576538086, "learning_rate": 8.395430120310049e-06, "loss": 0.6889, "step": 70620 }, { "epoch": 0.41983938750884203, "grad_norm": 7.307129383087158, "learning_rate": 8.396618954776737e-06, "loss": 0.6798, "step": 70630 }, { "epoch": 0.4198988295855104, "grad_norm": 6.518694877624512, "learning_rate": 8.397807789243427e-06, "loss": 0.6247, "step": 70640 }, { "epoch": 0.4199582716621788, "grad_norm": 5.628597736358643, "learning_rate": 8.398996623710115e-06, "loss": 0.6364, "step": 70650 }, { "epoch": 0.42001771373884716, "grad_norm": 7.365832328796387, "learning_rate": 8.400185458176805e-06, "loss": 0.671, "step": 70660 }, { "epoch": 0.4200771558155156, "grad_norm": 5.8029327392578125, "learning_rate": 8.401374292643493e-06, "loss": 0.6641, "step": 70670 }, { "epoch": 0.42013659789218394, "grad_norm": 6.69342041015625, "learning_rate": 8.40256312711018e-06, "loss": 0.7096, "step": 70680 }, { "epoch": 0.42019603996885235, "grad_norm": 6.6653594970703125, "learning_rate": 8.40375196157687e-06, "loss": 0.6831, "step": 70690 }, { "epoch": 0.42025548204552077, "grad_norm": 8.211860656738281, "learning_rate": 8.404940796043559e-06, "loss": 0.6872, "step": 70700 }, { "epoch": 0.4203149241221891, "grad_norm": 7.997014999389648, "learning_rate": 8.406129630510248e-06, "loss": 0.653, "step": 70710 }, { "epoch": 0.42037436619885754, "grad_norm": 10.158110618591309, "learning_rate": 8.407318464976936e-06, "loss": 0.6557, "step": 70720 }, { "epoch": 0.4204338082755259, "grad_norm": 8.545060157775879, "learning_rate": 8.408507299443626e-06, "loss": 0.6665, "step": 70730 }, { "epoch": 0.4204932503521943, "grad_norm": 6.905304431915283, "learning_rate": 8.409696133910314e-06, "loss": 0.6469, "step": 70740 }, { "epoch": 0.4205526924288627, "grad_norm": 6.505527019500732, "learning_rate": 8.410884968377004e-06, "loss": 0.6717, "step": 70750 }, { "epoch": 0.4206121345055311, "grad_norm": 7.763614654541016, "learning_rate": 8.412073802843694e-06, "loss": 0.695, "step": 70760 }, { "epoch": 0.4206715765821995, "grad_norm": 5.870845794677734, "learning_rate": 8.413262637310382e-06, "loss": 0.6787, "step": 70770 }, { "epoch": 0.42073101865886786, "grad_norm": 5.904623031616211, "learning_rate": 8.41445147177707e-06, "loss": 0.6659, "step": 70780 }, { "epoch": 0.4207904607355363, "grad_norm": 7.4585466384887695, "learning_rate": 8.41564030624376e-06, "loss": 0.7051, "step": 70790 }, { "epoch": 0.42084990281220463, "grad_norm": 6.68740701675415, "learning_rate": 8.416829140710448e-06, "loss": 0.6326, "step": 70800 }, { "epoch": 0.42090934488887305, "grad_norm": 6.754053592681885, "learning_rate": 8.418017975177138e-06, "loss": 0.7067, "step": 70810 }, { "epoch": 0.4209687869655414, "grad_norm": 6.925811290740967, "learning_rate": 8.419206809643826e-06, "loss": 0.6641, "step": 70820 }, { "epoch": 0.4210282290422098, "grad_norm": 7.405847549438477, "learning_rate": 8.420395644110516e-06, "loss": 0.6715, "step": 70830 }, { "epoch": 0.4210876711188782, "grad_norm": 6.817007064819336, "learning_rate": 8.421584478577204e-06, "loss": 0.6184, "step": 70840 }, { "epoch": 0.4211471131955466, "grad_norm": 5.454831600189209, "learning_rate": 8.422773313043893e-06, "loss": 0.6406, "step": 70850 }, { "epoch": 0.421206555272215, "grad_norm": 9.592133522033691, "learning_rate": 8.423962147510581e-06, "loss": 0.658, "step": 70860 }, { "epoch": 0.42126599734888337, "grad_norm": 6.5972514152526855, "learning_rate": 8.42515098197727e-06, "loss": 0.6437, "step": 70870 }, { "epoch": 0.4213254394255518, "grad_norm": 6.85763692855835, "learning_rate": 8.42633981644396e-06, "loss": 0.6699, "step": 70880 }, { "epoch": 0.42138488150222014, "grad_norm": 4.68134880065918, "learning_rate": 8.427528650910647e-06, "loss": 0.6901, "step": 70890 }, { "epoch": 0.42144432357888856, "grad_norm": 8.523396492004395, "learning_rate": 8.428717485377337e-06, "loss": 0.6253, "step": 70900 }, { "epoch": 0.4215037656555569, "grad_norm": 6.142244815826416, "learning_rate": 8.429906319844025e-06, "loss": 0.6665, "step": 70910 }, { "epoch": 0.42156320773222533, "grad_norm": 7.342384338378906, "learning_rate": 8.431095154310715e-06, "loss": 0.7001, "step": 70920 }, { "epoch": 0.42162264980889375, "grad_norm": 7.896244525909424, "learning_rate": 8.432283988777403e-06, "loss": 0.7237, "step": 70930 }, { "epoch": 0.4216820918855621, "grad_norm": 8.160876274108887, "learning_rate": 8.433472823244093e-06, "loss": 0.6948, "step": 70940 }, { "epoch": 0.4217415339622305, "grad_norm": 7.21224308013916, "learning_rate": 8.434661657710781e-06, "loss": 0.705, "step": 70950 }, { "epoch": 0.4218009760388989, "grad_norm": 7.584956645965576, "learning_rate": 8.435850492177469e-06, "loss": 0.7095, "step": 70960 }, { "epoch": 0.4218604181155673, "grad_norm": 6.259731292724609, "learning_rate": 8.437039326644159e-06, "loss": 0.6511, "step": 70970 }, { "epoch": 0.42191986019223565, "grad_norm": 7.948729991912842, "learning_rate": 8.438228161110847e-06, "loss": 0.734, "step": 70980 }, { "epoch": 0.42197930226890407, "grad_norm": 6.916747570037842, "learning_rate": 8.439416995577537e-06, "loss": 0.6508, "step": 70990 }, { "epoch": 0.4220387443455725, "grad_norm": 5.7629475593566895, "learning_rate": 8.440605830044225e-06, "loss": 0.6711, "step": 71000 }, { "epoch": 0.42209818642224084, "grad_norm": 7.022830009460449, "learning_rate": 8.441794664510915e-06, "loss": 0.6317, "step": 71010 }, { "epoch": 0.42215762849890925, "grad_norm": 6.507001876831055, "learning_rate": 8.442983498977603e-06, "loss": 0.7043, "step": 71020 }, { "epoch": 0.4222170705755776, "grad_norm": 8.314640045166016, "learning_rate": 8.444172333444292e-06, "loss": 0.7151, "step": 71030 }, { "epoch": 0.422276512652246, "grad_norm": 6.687885761260986, "learning_rate": 8.44536116791098e-06, "loss": 0.6847, "step": 71040 }, { "epoch": 0.4223359547289144, "grad_norm": 5.54752779006958, "learning_rate": 8.446550002377669e-06, "loss": 0.6858, "step": 71050 }, { "epoch": 0.4223953968055828, "grad_norm": 5.730616569519043, "learning_rate": 8.447738836844358e-06, "loss": 0.6952, "step": 71060 }, { "epoch": 0.4224548388822512, "grad_norm": 5.206586837768555, "learning_rate": 8.448927671311046e-06, "loss": 0.5998, "step": 71070 }, { "epoch": 0.4225142809589196, "grad_norm": 7.5992302894592285, "learning_rate": 8.450116505777736e-06, "loss": 0.7375, "step": 71080 }, { "epoch": 0.422573723035588, "grad_norm": 7.216397285461426, "learning_rate": 8.451305340244424e-06, "loss": 0.6844, "step": 71090 }, { "epoch": 0.42263316511225635, "grad_norm": 6.1264777183532715, "learning_rate": 8.452494174711114e-06, "loss": 0.6145, "step": 71100 }, { "epoch": 0.42269260718892476, "grad_norm": 7.045971870422363, "learning_rate": 8.453683009177804e-06, "loss": 0.636, "step": 71110 }, { "epoch": 0.4227520492655931, "grad_norm": 7.534406661987305, "learning_rate": 8.454871843644492e-06, "loss": 0.6702, "step": 71120 }, { "epoch": 0.42281149134226154, "grad_norm": 6.116482734680176, "learning_rate": 8.456060678111182e-06, "loss": 0.7028, "step": 71130 }, { "epoch": 0.42287093341892995, "grad_norm": 6.409487724304199, "learning_rate": 8.45724951257787e-06, "loss": 0.6592, "step": 71140 }, { "epoch": 0.4229303754955983, "grad_norm": 6.590381622314453, "learning_rate": 8.458438347044558e-06, "loss": 0.6653, "step": 71150 }, { "epoch": 0.4229898175722667, "grad_norm": 6.4966325759887695, "learning_rate": 8.459627181511248e-06, "loss": 0.614, "step": 71160 }, { "epoch": 0.4230492596489351, "grad_norm": 8.38973617553711, "learning_rate": 8.460816015977936e-06, "loss": 0.6976, "step": 71170 }, { "epoch": 0.4231087017256035, "grad_norm": 5.706364631652832, "learning_rate": 8.462004850444625e-06, "loss": 0.7032, "step": 71180 }, { "epoch": 0.42316814380227186, "grad_norm": 5.9120330810546875, "learning_rate": 8.463193684911314e-06, "loss": 0.6794, "step": 71190 }, { "epoch": 0.42322758587894027, "grad_norm": 5.938004970550537, "learning_rate": 8.464382519378003e-06, "loss": 0.6801, "step": 71200 }, { "epoch": 0.42328702795560863, "grad_norm": 6.679101943969727, "learning_rate": 8.465571353844691e-06, "loss": 0.6764, "step": 71210 }, { "epoch": 0.42334647003227704, "grad_norm": 6.155025005340576, "learning_rate": 8.466760188311381e-06, "loss": 0.6733, "step": 71220 }, { "epoch": 0.42340591210894546, "grad_norm": 4.764571666717529, "learning_rate": 8.46794902277807e-06, "loss": 0.6435, "step": 71230 }, { "epoch": 0.4234653541856138, "grad_norm": 5.176661968231201, "learning_rate": 8.469137857244757e-06, "loss": 0.6931, "step": 71240 }, { "epoch": 0.42352479626228223, "grad_norm": 7.1639580726623535, "learning_rate": 8.470326691711447e-06, "loss": 0.6927, "step": 71250 }, { "epoch": 0.4235842383389506, "grad_norm": 5.712227821350098, "learning_rate": 8.471515526178135e-06, "loss": 0.6233, "step": 71260 }, { "epoch": 0.423643680415619, "grad_norm": 6.5306715965271, "learning_rate": 8.472704360644825e-06, "loss": 0.6437, "step": 71270 }, { "epoch": 0.42370312249228737, "grad_norm": 7.518237590789795, "learning_rate": 8.473893195111513e-06, "loss": 0.6427, "step": 71280 }, { "epoch": 0.4237625645689558, "grad_norm": 6.325992584228516, "learning_rate": 8.475082029578203e-06, "loss": 0.6307, "step": 71290 }, { "epoch": 0.4238220066456242, "grad_norm": 6.577536582946777, "learning_rate": 8.476270864044891e-06, "loss": 0.6728, "step": 71300 }, { "epoch": 0.42388144872229255, "grad_norm": 8.253292083740234, "learning_rate": 8.477459698511579e-06, "loss": 0.6776, "step": 71310 }, { "epoch": 0.42394089079896097, "grad_norm": 5.837774753570557, "learning_rate": 8.478648532978269e-06, "loss": 0.6349, "step": 71320 }, { "epoch": 0.4240003328756293, "grad_norm": 6.369851589202881, "learning_rate": 8.479837367444957e-06, "loss": 0.6376, "step": 71330 }, { "epoch": 0.42405977495229774, "grad_norm": 6.769288539886475, "learning_rate": 8.481026201911647e-06, "loss": 0.6841, "step": 71340 }, { "epoch": 0.4241192170289661, "grad_norm": 5.223916053771973, "learning_rate": 8.482215036378335e-06, "loss": 0.6298, "step": 71350 }, { "epoch": 0.4241786591056345, "grad_norm": 6.61077356338501, "learning_rate": 8.483403870845024e-06, "loss": 0.6719, "step": 71360 }, { "epoch": 0.42423810118230293, "grad_norm": 5.983278751373291, "learning_rate": 8.484592705311713e-06, "loss": 0.6815, "step": 71370 }, { "epoch": 0.4242975432589713, "grad_norm": 7.6232099533081055, "learning_rate": 8.485781539778402e-06, "loss": 0.6676, "step": 71380 }, { "epoch": 0.4243569853356397, "grad_norm": 5.259697437286377, "learning_rate": 8.48697037424509e-06, "loss": 0.6228, "step": 71390 }, { "epoch": 0.42441642741230806, "grad_norm": 5.646589279174805, "learning_rate": 8.488159208711778e-06, "loss": 0.6453, "step": 71400 }, { "epoch": 0.4244758694889765, "grad_norm": 6.1379618644714355, "learning_rate": 8.489348043178468e-06, "loss": 0.6697, "step": 71410 }, { "epoch": 0.42453531156564484, "grad_norm": 5.770814895629883, "learning_rate": 8.490536877645156e-06, "loss": 0.6552, "step": 71420 }, { "epoch": 0.42459475364231325, "grad_norm": 7.578111171722412, "learning_rate": 8.491725712111846e-06, "loss": 0.6506, "step": 71430 }, { "epoch": 0.42465419571898166, "grad_norm": 10.76242733001709, "learning_rate": 8.492914546578536e-06, "loss": 0.7071, "step": 71440 }, { "epoch": 0.42471363779565, "grad_norm": 5.01242208480835, "learning_rate": 8.494103381045224e-06, "loss": 0.6575, "step": 71450 }, { "epoch": 0.42477307987231844, "grad_norm": 6.140070915222168, "learning_rate": 8.495292215511914e-06, "loss": 0.6821, "step": 71460 }, { "epoch": 0.4248325219489868, "grad_norm": 6.970886707305908, "learning_rate": 8.496481049978602e-06, "loss": 0.6902, "step": 71470 }, { "epoch": 0.4248919640256552, "grad_norm": 6.995615005493164, "learning_rate": 8.497669884445292e-06, "loss": 0.6186, "step": 71480 }, { "epoch": 0.42495140610232357, "grad_norm": 6.234586238861084, "learning_rate": 8.49885871891198e-06, "loss": 0.6817, "step": 71490 }, { "epoch": 0.425010848178992, "grad_norm": 5.963807582855225, "learning_rate": 8.50004755337867e-06, "loss": 0.6584, "step": 71500 }, { "epoch": 0.4250702902556604, "grad_norm": 6.254988193511963, "learning_rate": 8.501236387845358e-06, "loss": 0.6861, "step": 71510 }, { "epoch": 0.42512973233232876, "grad_norm": 7.327966690063477, "learning_rate": 8.502425222312046e-06, "loss": 0.6678, "step": 71520 }, { "epoch": 0.4251891744089972, "grad_norm": 6.544789791107178, "learning_rate": 8.503614056778735e-06, "loss": 0.6984, "step": 71530 }, { "epoch": 0.42524861648566553, "grad_norm": 5.722736835479736, "learning_rate": 8.504802891245423e-06, "loss": 0.6598, "step": 71540 }, { "epoch": 0.42530805856233395, "grad_norm": 8.551485061645508, "learning_rate": 8.505991725712113e-06, "loss": 0.6266, "step": 71550 }, { "epoch": 0.4253675006390023, "grad_norm": 6.6239705085754395, "learning_rate": 8.507180560178801e-06, "loss": 0.6188, "step": 71560 }, { "epoch": 0.4254269427156707, "grad_norm": 6.3390069007873535, "learning_rate": 8.508369394645491e-06, "loss": 0.6243, "step": 71570 }, { "epoch": 0.4254863847923391, "grad_norm": 6.277769088745117, "learning_rate": 8.509558229112179e-06, "loss": 0.6918, "step": 71580 }, { "epoch": 0.4255458268690075, "grad_norm": 8.034972190856934, "learning_rate": 8.510747063578867e-06, "loss": 0.6552, "step": 71590 }, { "epoch": 0.4256052689456759, "grad_norm": 6.615458011627197, "learning_rate": 8.511935898045557e-06, "loss": 0.6987, "step": 71600 }, { "epoch": 0.42566471102234427, "grad_norm": 10.867222785949707, "learning_rate": 8.513124732512245e-06, "loss": 0.6471, "step": 71610 }, { "epoch": 0.4257241530990127, "grad_norm": 7.623551845550537, "learning_rate": 8.514313566978935e-06, "loss": 0.6744, "step": 71620 }, { "epoch": 0.42578359517568104, "grad_norm": 6.19302225112915, "learning_rate": 8.515502401445623e-06, "loss": 0.6562, "step": 71630 }, { "epoch": 0.42584303725234945, "grad_norm": 6.671669960021973, "learning_rate": 8.516691235912313e-06, "loss": 0.6337, "step": 71640 }, { "epoch": 0.4259024793290178, "grad_norm": 7.084167957305908, "learning_rate": 8.517880070379e-06, "loss": 0.6529, "step": 71650 }, { "epoch": 0.42596192140568623, "grad_norm": 5.894939422607422, "learning_rate": 8.51906890484569e-06, "loss": 0.6098, "step": 71660 }, { "epoch": 0.42602136348235464, "grad_norm": 6.010521411895752, "learning_rate": 8.520257739312379e-06, "loss": 0.6487, "step": 71670 }, { "epoch": 0.426080805559023, "grad_norm": 7.4823808670043945, "learning_rate": 8.521446573779067e-06, "loss": 0.6489, "step": 71680 }, { "epoch": 0.4261402476356914, "grad_norm": 6.264029502868652, "learning_rate": 8.522635408245756e-06, "loss": 0.6163, "step": 71690 }, { "epoch": 0.4261996897123598, "grad_norm": 7.19455099105835, "learning_rate": 8.523824242712445e-06, "loss": 0.6891, "step": 71700 }, { "epoch": 0.4262591317890282, "grad_norm": 6.180829048156738, "learning_rate": 8.525013077179134e-06, "loss": 0.7032, "step": 71710 }, { "epoch": 0.42631857386569655, "grad_norm": 7.2457756996154785, "learning_rate": 8.526201911645822e-06, "loss": 0.674, "step": 71720 }, { "epoch": 0.42637801594236496, "grad_norm": 8.03934383392334, "learning_rate": 8.527390746112512e-06, "loss": 0.7165, "step": 71730 }, { "epoch": 0.4264374580190334, "grad_norm": 7.4122490882873535, "learning_rate": 8.5285795805792e-06, "loss": 0.6573, "step": 71740 }, { "epoch": 0.42649690009570174, "grad_norm": 6.440217018127441, "learning_rate": 8.52976841504589e-06, "loss": 0.6024, "step": 71750 }, { "epoch": 0.42655634217237015, "grad_norm": 7.116626739501953, "learning_rate": 8.530957249512578e-06, "loss": 0.7053, "step": 71760 }, { "epoch": 0.4266157842490385, "grad_norm": 7.400623321533203, "learning_rate": 8.532146083979266e-06, "loss": 0.6332, "step": 71770 }, { "epoch": 0.4266752263257069, "grad_norm": 6.563995838165283, "learning_rate": 8.533334918445956e-06, "loss": 0.6009, "step": 71780 }, { "epoch": 0.4267346684023753, "grad_norm": 8.003507614135742, "learning_rate": 8.534523752912646e-06, "loss": 0.6885, "step": 71790 }, { "epoch": 0.4267941104790437, "grad_norm": 7.20847225189209, "learning_rate": 8.535712587379334e-06, "loss": 0.6499, "step": 71800 }, { "epoch": 0.4268535525557121, "grad_norm": 7.91506290435791, "learning_rate": 8.536901421846024e-06, "loss": 0.6595, "step": 71810 }, { "epoch": 0.42691299463238047, "grad_norm": 7.331436634063721, "learning_rate": 8.538090256312712e-06, "loss": 0.6831, "step": 71820 }, { "epoch": 0.4269724367090489, "grad_norm": 5.54398250579834, "learning_rate": 8.539279090779401e-06, "loss": 0.629, "step": 71830 }, { "epoch": 0.42703187878571724, "grad_norm": 6.4813055992126465, "learning_rate": 8.54046792524609e-06, "loss": 0.6539, "step": 71840 }, { "epoch": 0.42709132086238566, "grad_norm": 4.930761337280273, "learning_rate": 8.54165675971278e-06, "loss": 0.6567, "step": 71850 }, { "epoch": 0.427150762939054, "grad_norm": 7.933840751647949, "learning_rate": 8.542845594179467e-06, "loss": 0.658, "step": 71860 }, { "epoch": 0.42721020501572243, "grad_norm": 6.799178600311279, "learning_rate": 8.544034428646155e-06, "loss": 0.71, "step": 71870 }, { "epoch": 0.42726964709239085, "grad_norm": 6.430097579956055, "learning_rate": 8.545223263112845e-06, "loss": 0.6152, "step": 71880 }, { "epoch": 0.4273290891690592, "grad_norm": 7.059713840484619, "learning_rate": 8.546412097579533e-06, "loss": 0.6956, "step": 71890 }, { "epoch": 0.4273885312457276, "grad_norm": 6.999697208404541, "learning_rate": 8.547600932046223e-06, "loss": 0.6782, "step": 71900 }, { "epoch": 0.427447973322396, "grad_norm": 5.91595983505249, "learning_rate": 8.548789766512911e-06, "loss": 0.6919, "step": 71910 }, { "epoch": 0.4275074153990644, "grad_norm": 5.4084320068359375, "learning_rate": 8.549978600979601e-06, "loss": 0.6529, "step": 71920 }, { "epoch": 0.42756685747573275, "grad_norm": 9.976936340332031, "learning_rate": 8.551167435446289e-06, "loss": 0.6124, "step": 71930 }, { "epoch": 0.42762629955240117, "grad_norm": 8.678250312805176, "learning_rate": 8.552356269912979e-06, "loss": 0.7278, "step": 71940 }, { "epoch": 0.4276857416290695, "grad_norm": 8.390751838684082, "learning_rate": 8.553545104379667e-06, "loss": 0.657, "step": 71950 }, { "epoch": 0.42774518370573794, "grad_norm": 8.231980323791504, "learning_rate": 8.554733938846355e-06, "loss": 0.6459, "step": 71960 }, { "epoch": 0.42780462578240636, "grad_norm": 8.80346393585205, "learning_rate": 8.555922773313045e-06, "loss": 0.6797, "step": 71970 }, { "epoch": 0.4278640678590747, "grad_norm": 5.372321128845215, "learning_rate": 8.557111607779733e-06, "loss": 0.6631, "step": 71980 }, { "epoch": 0.42792350993574313, "grad_norm": 6.413244724273682, "learning_rate": 8.558300442246423e-06, "loss": 0.6254, "step": 71990 }, { "epoch": 0.4279829520124115, "grad_norm": 5.208328723907471, "learning_rate": 8.55948927671311e-06, "loss": 0.6142, "step": 72000 }, { "epoch": 0.4280423940890799, "grad_norm": 6.387248516082764, "learning_rate": 8.5606781111798e-06, "loss": 0.6508, "step": 72010 }, { "epoch": 0.42810183616574826, "grad_norm": 5.905082702636719, "learning_rate": 8.561866945646489e-06, "loss": 0.708, "step": 72020 }, { "epoch": 0.4281612782424167, "grad_norm": 8.993672370910645, "learning_rate": 8.563055780113178e-06, "loss": 0.6691, "step": 72030 }, { "epoch": 0.4282207203190851, "grad_norm": 5.694072723388672, "learning_rate": 8.564244614579866e-06, "loss": 0.6766, "step": 72040 }, { "epoch": 0.42828016239575345, "grad_norm": 6.441798210144043, "learning_rate": 8.565433449046554e-06, "loss": 0.7074, "step": 72050 }, { "epoch": 0.42833960447242186, "grad_norm": 8.202341079711914, "learning_rate": 8.566622283513244e-06, "loss": 0.6354, "step": 72060 }, { "epoch": 0.4283990465490902, "grad_norm": 4.945024013519287, "learning_rate": 8.567811117979932e-06, "loss": 0.6989, "step": 72070 }, { "epoch": 0.42845848862575864, "grad_norm": 8.92018985748291, "learning_rate": 8.568999952446622e-06, "loss": 0.6916, "step": 72080 }, { "epoch": 0.428517930702427, "grad_norm": 5.549878120422363, "learning_rate": 8.57018878691331e-06, "loss": 0.6934, "step": 72090 }, { "epoch": 0.4285773727790954, "grad_norm": 5.543521881103516, "learning_rate": 8.57137762138e-06, "loss": 0.7193, "step": 72100 }, { "epoch": 0.4286368148557638, "grad_norm": 6.308708190917969, "learning_rate": 8.572566455846688e-06, "loss": 0.7341, "step": 72110 }, { "epoch": 0.4286962569324322, "grad_norm": 5.151744842529297, "learning_rate": 8.573755290313376e-06, "loss": 0.6622, "step": 72120 }, { "epoch": 0.4287556990091006, "grad_norm": 7.085180759429932, "learning_rate": 8.574944124780066e-06, "loss": 0.7083, "step": 72130 }, { "epoch": 0.42881514108576896, "grad_norm": 6.806415557861328, "learning_rate": 8.576132959246756e-06, "loss": 0.6546, "step": 72140 }, { "epoch": 0.4288745831624374, "grad_norm": 7.086450576782227, "learning_rate": 8.577321793713444e-06, "loss": 0.6815, "step": 72150 }, { "epoch": 0.42893402523910573, "grad_norm": 6.720328330993652, "learning_rate": 8.578510628180134e-06, "loss": 0.6977, "step": 72160 }, { "epoch": 0.42899346731577415, "grad_norm": 6.238938808441162, "learning_rate": 8.579699462646822e-06, "loss": 0.6676, "step": 72170 }, { "epoch": 0.42905290939244256, "grad_norm": 5.679529190063477, "learning_rate": 8.580888297113511e-06, "loss": 0.6528, "step": 72180 }, { "epoch": 0.4291123514691109, "grad_norm": 6.509592533111572, "learning_rate": 8.5820771315802e-06, "loss": 0.6203, "step": 72190 }, { "epoch": 0.42917179354577933, "grad_norm": 8.077041625976562, "learning_rate": 8.58326596604689e-06, "loss": 0.7003, "step": 72200 }, { "epoch": 0.4292312356224477, "grad_norm": 7.302243709564209, "learning_rate": 8.584454800513577e-06, "loss": 0.6701, "step": 72210 }, { "epoch": 0.4292906776991161, "grad_norm": 6.3996148109436035, "learning_rate": 8.585643634980267e-06, "loss": 0.6937, "step": 72220 }, { "epoch": 0.42935011977578447, "grad_norm": 6.596985340118408, "learning_rate": 8.586832469446955e-06, "loss": 0.6288, "step": 72230 }, { "epoch": 0.4294095618524529, "grad_norm": 6.248697757720947, "learning_rate": 8.588021303913643e-06, "loss": 0.6891, "step": 72240 }, { "epoch": 0.42946900392912124, "grad_norm": 5.03511381149292, "learning_rate": 8.589210138380333e-06, "loss": 0.6147, "step": 72250 }, { "epoch": 0.42952844600578965, "grad_norm": 6.3792405128479, "learning_rate": 8.590398972847021e-06, "loss": 0.6252, "step": 72260 }, { "epoch": 0.42958788808245807, "grad_norm": 7.325278282165527, "learning_rate": 8.591587807313711e-06, "loss": 0.7132, "step": 72270 }, { "epoch": 0.42964733015912643, "grad_norm": 7.536390781402588, "learning_rate": 8.592776641780399e-06, "loss": 0.6766, "step": 72280 }, { "epoch": 0.42970677223579484, "grad_norm": 5.625842094421387, "learning_rate": 8.593965476247089e-06, "loss": 0.6106, "step": 72290 }, { "epoch": 0.4297662143124632, "grad_norm": 7.503968238830566, "learning_rate": 8.595154310713777e-06, "loss": 0.691, "step": 72300 }, { "epoch": 0.4298256563891316, "grad_norm": 6.1938581466674805, "learning_rate": 8.596343145180465e-06, "loss": 0.669, "step": 72310 }, { "epoch": 0.4298850984658, "grad_norm": 8.075360298156738, "learning_rate": 8.597531979647155e-06, "loss": 0.687, "step": 72320 }, { "epoch": 0.4299445405424684, "grad_norm": 5.62905216217041, "learning_rate": 8.598720814113843e-06, "loss": 0.6172, "step": 72330 }, { "epoch": 0.4300039826191368, "grad_norm": 7.699478626251221, "learning_rate": 8.599909648580533e-06, "loss": 0.6635, "step": 72340 }, { "epoch": 0.43006342469580516, "grad_norm": 11.156318664550781, "learning_rate": 8.60109848304722e-06, "loss": 0.7062, "step": 72350 }, { "epoch": 0.4301228667724736, "grad_norm": 5.341465473175049, "learning_rate": 8.60228731751391e-06, "loss": 0.69, "step": 72360 }, { "epoch": 0.43018230884914194, "grad_norm": 8.775274276733398, "learning_rate": 8.603476151980598e-06, "loss": 0.6642, "step": 72370 }, { "epoch": 0.43024175092581035, "grad_norm": 5.519753932952881, "learning_rate": 8.604664986447288e-06, "loss": 0.6075, "step": 72380 }, { "epoch": 0.4303011930024787, "grad_norm": 7.548849582672119, "learning_rate": 8.605853820913976e-06, "loss": 0.6973, "step": 72390 }, { "epoch": 0.4303606350791471, "grad_norm": 7.422238349914551, "learning_rate": 8.607042655380664e-06, "loss": 0.6885, "step": 72400 }, { "epoch": 0.43042007715581554, "grad_norm": 6.603741645812988, "learning_rate": 8.608231489847354e-06, "loss": 0.6853, "step": 72410 }, { "epoch": 0.4304795192324839, "grad_norm": 5.913071632385254, "learning_rate": 8.609420324314042e-06, "loss": 0.6136, "step": 72420 }, { "epoch": 0.4305389613091523, "grad_norm": 5.455380439758301, "learning_rate": 8.610609158780732e-06, "loss": 0.7295, "step": 72430 }, { "epoch": 0.43059840338582067, "grad_norm": 5.717381477355957, "learning_rate": 8.61179799324742e-06, "loss": 0.7049, "step": 72440 }, { "epoch": 0.4306578454624891, "grad_norm": 5.318582534790039, "learning_rate": 8.61298682771411e-06, "loss": 0.6056, "step": 72450 }, { "epoch": 0.43071728753915745, "grad_norm": 6.234194278717041, "learning_rate": 8.614175662180798e-06, "loss": 0.7107, "step": 72460 }, { "epoch": 0.43077672961582586, "grad_norm": 5.500920295715332, "learning_rate": 8.615364496647488e-06, "loss": 0.6684, "step": 72470 }, { "epoch": 0.4308361716924943, "grad_norm": 6.415113925933838, "learning_rate": 8.616553331114178e-06, "loss": 0.6732, "step": 72480 }, { "epoch": 0.43089561376916263, "grad_norm": 6.222908973693848, "learning_rate": 8.617742165580866e-06, "loss": 0.7075, "step": 72490 }, { "epoch": 0.43095505584583105, "grad_norm": 7.561635971069336, "learning_rate": 8.618931000047555e-06, "loss": 0.6737, "step": 72500 }, { "epoch": 0.4310144979224994, "grad_norm": 6.017731666564941, "learning_rate": 8.620119834514243e-06, "loss": 0.6709, "step": 72510 }, { "epoch": 0.4310739399991678, "grad_norm": 7.592020034790039, "learning_rate": 8.621308668980932e-06, "loss": 0.6676, "step": 72520 }, { "epoch": 0.4311333820758362, "grad_norm": 6.985941410064697, "learning_rate": 8.622497503447621e-06, "loss": 0.6801, "step": 72530 }, { "epoch": 0.4311928241525046, "grad_norm": 6.45932674407959, "learning_rate": 8.62368633791431e-06, "loss": 0.662, "step": 72540 }, { "epoch": 0.431252266229173, "grad_norm": 6.025689125061035, "learning_rate": 8.624875172381e-06, "loss": 0.6758, "step": 72550 }, { "epoch": 0.43131170830584137, "grad_norm": 7.439220905303955, "learning_rate": 8.626064006847687e-06, "loss": 0.689, "step": 72560 }, { "epoch": 0.4313711503825098, "grad_norm": 7.790263652801514, "learning_rate": 8.627252841314377e-06, "loss": 0.6771, "step": 72570 }, { "epoch": 0.43143059245917814, "grad_norm": 6.646677017211914, "learning_rate": 8.628441675781065e-06, "loss": 0.6653, "step": 72580 }, { "epoch": 0.43149003453584656, "grad_norm": 6.937010288238525, "learning_rate": 8.629630510247753e-06, "loss": 0.7141, "step": 72590 }, { "epoch": 0.4315494766125149, "grad_norm": 6.8892669677734375, "learning_rate": 8.630819344714443e-06, "loss": 0.6126, "step": 72600 }, { "epoch": 0.43160891868918333, "grad_norm": 6.175618648529053, "learning_rate": 8.632008179181131e-06, "loss": 0.6909, "step": 72610 }, { "epoch": 0.4316683607658517, "grad_norm": 5.229466438293457, "learning_rate": 8.63319701364782e-06, "loss": 0.6618, "step": 72620 }, { "epoch": 0.4317278028425201, "grad_norm": 5.292284965515137, "learning_rate": 8.634385848114509e-06, "loss": 0.5788, "step": 72630 }, { "epoch": 0.4317872449191885, "grad_norm": 7.1349921226501465, "learning_rate": 8.635574682581199e-06, "loss": 0.6934, "step": 72640 }, { "epoch": 0.4318466869958569, "grad_norm": 6.088608741760254, "learning_rate": 8.636763517047887e-06, "loss": 0.6562, "step": 72650 }, { "epoch": 0.4319061290725253, "grad_norm": 6.609200477600098, "learning_rate": 8.637952351514577e-06, "loss": 0.6487, "step": 72660 }, { "epoch": 0.43196557114919365, "grad_norm": 5.562213897705078, "learning_rate": 8.639141185981265e-06, "loss": 0.6946, "step": 72670 }, { "epoch": 0.43202501322586206, "grad_norm": 6.865569114685059, "learning_rate": 8.640330020447953e-06, "loss": 0.6924, "step": 72680 }, { "epoch": 0.4320844553025304, "grad_norm": 7.102028846740723, "learning_rate": 8.641518854914642e-06, "loss": 0.6439, "step": 72690 }, { "epoch": 0.43214389737919884, "grad_norm": 8.898271560668945, "learning_rate": 8.64270768938133e-06, "loss": 0.6972, "step": 72700 }, { "epoch": 0.43220333945586725, "grad_norm": 8.219655990600586, "learning_rate": 8.64389652384802e-06, "loss": 0.6782, "step": 72710 }, { "epoch": 0.4322627815325356, "grad_norm": 7.059630870819092, "learning_rate": 8.645085358314708e-06, "loss": 0.6436, "step": 72720 }, { "epoch": 0.432322223609204, "grad_norm": 6.67811393737793, "learning_rate": 8.646274192781398e-06, "loss": 0.6931, "step": 72730 }, { "epoch": 0.4323816656858724, "grad_norm": 8.672051429748535, "learning_rate": 8.647463027248086e-06, "loss": 0.6585, "step": 72740 }, { "epoch": 0.4324411077625408, "grad_norm": 5.769606113433838, "learning_rate": 8.648651861714776e-06, "loss": 0.6118, "step": 72750 }, { "epoch": 0.43250054983920916, "grad_norm": 6.233929634094238, "learning_rate": 8.649840696181464e-06, "loss": 0.6654, "step": 72760 }, { "epoch": 0.4325599919158776, "grad_norm": 9.57918930053711, "learning_rate": 8.651029530648152e-06, "loss": 0.7527, "step": 72770 }, { "epoch": 0.432619433992546, "grad_norm": 6.960631847381592, "learning_rate": 8.652218365114842e-06, "loss": 0.6647, "step": 72780 }, { "epoch": 0.43267887606921435, "grad_norm": 6.74650239944458, "learning_rate": 8.65340719958153e-06, "loss": 0.6449, "step": 72790 }, { "epoch": 0.43273831814588276, "grad_norm": 4.744426250457764, "learning_rate": 8.65459603404822e-06, "loss": 0.6863, "step": 72800 }, { "epoch": 0.4327977602225511, "grad_norm": 7.316227436065674, "learning_rate": 8.655784868514908e-06, "loss": 0.6816, "step": 72810 }, { "epoch": 0.43285720229921953, "grad_norm": 6.484461784362793, "learning_rate": 8.656973702981598e-06, "loss": 0.7032, "step": 72820 }, { "epoch": 0.4329166443758879, "grad_norm": 6.668844699859619, "learning_rate": 8.658162537448287e-06, "loss": 0.6298, "step": 72830 }, { "epoch": 0.4329760864525563, "grad_norm": 7.618772029876709, "learning_rate": 8.659351371914976e-06, "loss": 0.7167, "step": 72840 }, { "epoch": 0.4330355285292247, "grad_norm": 5.323375701904297, "learning_rate": 8.660540206381665e-06, "loss": 0.6455, "step": 72850 }, { "epoch": 0.4330949706058931, "grad_norm": 5.820523738861084, "learning_rate": 8.661729040848353e-06, "loss": 0.642, "step": 72860 }, { "epoch": 0.4331544126825615, "grad_norm": 6.912765026092529, "learning_rate": 8.662917875315041e-06, "loss": 0.6654, "step": 72870 }, { "epoch": 0.43321385475922985, "grad_norm": 6.377467155456543, "learning_rate": 8.664106709781731e-06, "loss": 0.747, "step": 72880 }, { "epoch": 0.43327329683589827, "grad_norm": 7.5233154296875, "learning_rate": 8.66529554424842e-06, "loss": 0.6948, "step": 72890 }, { "epoch": 0.43333273891256663, "grad_norm": 7.196402072906494, "learning_rate": 8.666484378715109e-06, "loss": 0.6956, "step": 72900 }, { "epoch": 0.43339218098923504, "grad_norm": 7.640596389770508, "learning_rate": 8.667673213181797e-06, "loss": 0.7095, "step": 72910 }, { "epoch": 0.43345162306590346, "grad_norm": 7.103802680969238, "learning_rate": 8.668862047648487e-06, "loss": 0.6754, "step": 72920 }, { "epoch": 0.4335110651425718, "grad_norm": 7.51900053024292, "learning_rate": 8.670050882115175e-06, "loss": 0.6854, "step": 72930 }, { "epoch": 0.43357050721924023, "grad_norm": 6.091118812561035, "learning_rate": 8.671239716581865e-06, "loss": 0.6108, "step": 72940 }, { "epoch": 0.4336299492959086, "grad_norm": 7.210407257080078, "learning_rate": 8.672428551048553e-06, "loss": 0.6471, "step": 72950 }, { "epoch": 0.433689391372577, "grad_norm": 6.321583271026611, "learning_rate": 8.673617385515241e-06, "loss": 0.6367, "step": 72960 }, { "epoch": 0.43374883344924536, "grad_norm": 7.496806621551514, "learning_rate": 8.67480621998193e-06, "loss": 0.6509, "step": 72970 }, { "epoch": 0.4338082755259138, "grad_norm": 7.2131805419921875, "learning_rate": 8.675995054448619e-06, "loss": 0.6926, "step": 72980 }, { "epoch": 0.43386771760258214, "grad_norm": 6.212956428527832, "learning_rate": 8.677183888915309e-06, "loss": 0.6569, "step": 72990 }, { "epoch": 0.43392715967925055, "grad_norm": 6.943314552307129, "learning_rate": 8.678372723381997e-06, "loss": 0.6688, "step": 73000 }, { "epoch": 0.43398660175591897, "grad_norm": 5.830716609954834, "learning_rate": 8.679561557848686e-06, "loss": 0.6469, "step": 73010 }, { "epoch": 0.4340460438325873, "grad_norm": 6.216409206390381, "learning_rate": 8.680750392315375e-06, "loss": 0.6995, "step": 73020 }, { "epoch": 0.43410548590925574, "grad_norm": 6.176988124847412, "learning_rate": 8.681939226782064e-06, "loss": 0.6701, "step": 73030 }, { "epoch": 0.4341649279859241, "grad_norm": 6.72585391998291, "learning_rate": 8.683128061248752e-06, "loss": 0.5968, "step": 73040 }, { "epoch": 0.4342243700625925, "grad_norm": 7.5731964111328125, "learning_rate": 8.68431689571544e-06, "loss": 0.6583, "step": 73050 }, { "epoch": 0.43428381213926087, "grad_norm": 9.83312702178955, "learning_rate": 8.68550573018213e-06, "loss": 0.6528, "step": 73060 }, { "epoch": 0.4343432542159293, "grad_norm": 6.865245342254639, "learning_rate": 8.686694564648818e-06, "loss": 0.6382, "step": 73070 }, { "epoch": 0.4344026962925977, "grad_norm": 6.895721912384033, "learning_rate": 8.687883399115508e-06, "loss": 0.6254, "step": 73080 }, { "epoch": 0.43446213836926606, "grad_norm": 7.469246864318848, "learning_rate": 8.689072233582196e-06, "loss": 0.6548, "step": 73090 }, { "epoch": 0.4345215804459345, "grad_norm": 5.728461265563965, "learning_rate": 8.690261068048886e-06, "loss": 0.6664, "step": 73100 }, { "epoch": 0.43458102252260283, "grad_norm": 7.55601167678833, "learning_rate": 8.691449902515574e-06, "loss": 0.6986, "step": 73110 }, { "epoch": 0.43464046459927125, "grad_norm": 8.316906929016113, "learning_rate": 8.692638736982262e-06, "loss": 0.5968, "step": 73120 }, { "epoch": 0.4346999066759396, "grad_norm": 5.655428886413574, "learning_rate": 8.693827571448952e-06, "loss": 0.6278, "step": 73130 }, { "epoch": 0.434759348752608, "grad_norm": 8.125527381896973, "learning_rate": 8.69501640591564e-06, "loss": 0.7168, "step": 73140 }, { "epoch": 0.43481879082927644, "grad_norm": 6.125168800354004, "learning_rate": 8.69620524038233e-06, "loss": 0.6553, "step": 73150 }, { "epoch": 0.4348782329059448, "grad_norm": 7.292118072509766, "learning_rate": 8.697394074849018e-06, "loss": 0.6266, "step": 73160 }, { "epoch": 0.4349376749826132, "grad_norm": 6.582515716552734, "learning_rate": 8.698582909315708e-06, "loss": 0.6241, "step": 73170 }, { "epoch": 0.43499711705928157, "grad_norm": 7.037762641906738, "learning_rate": 8.699771743782397e-06, "loss": 0.6388, "step": 73180 }, { "epoch": 0.43505655913595, "grad_norm": 5.52203369140625, "learning_rate": 8.700960578249085e-06, "loss": 0.6547, "step": 73190 }, { "epoch": 0.43511600121261834, "grad_norm": 7.602455139160156, "learning_rate": 8.702149412715775e-06, "loss": 0.6763, "step": 73200 }, { "epoch": 0.43517544328928676, "grad_norm": 7.347790718078613, "learning_rate": 8.703338247182463e-06, "loss": 0.6838, "step": 73210 }, { "epoch": 0.43523488536595517, "grad_norm": 6.230788230895996, "learning_rate": 8.704527081649153e-06, "loss": 0.6736, "step": 73220 }, { "epoch": 0.43529432744262353, "grad_norm": 8.017318725585938, "learning_rate": 8.705715916115841e-06, "loss": 0.6143, "step": 73230 }, { "epoch": 0.43535376951929194, "grad_norm": 8.423469543457031, "learning_rate": 8.70690475058253e-06, "loss": 0.6813, "step": 73240 }, { "epoch": 0.4354132115959603, "grad_norm": 7.003426551818848, "learning_rate": 8.708093585049219e-06, "loss": 0.7231, "step": 73250 }, { "epoch": 0.4354726536726287, "grad_norm": 10.606449127197266, "learning_rate": 8.709282419515907e-06, "loss": 0.6649, "step": 73260 }, { "epoch": 0.4355320957492971, "grad_norm": 4.442371845245361, "learning_rate": 8.710471253982597e-06, "loss": 0.6582, "step": 73270 }, { "epoch": 0.4355915378259655, "grad_norm": 6.414071559906006, "learning_rate": 8.711660088449285e-06, "loss": 0.6371, "step": 73280 }, { "epoch": 0.4356509799026339, "grad_norm": 6.06547212600708, "learning_rate": 8.712848922915975e-06, "loss": 0.6591, "step": 73290 }, { "epoch": 0.43571042197930226, "grad_norm": 5.96421480178833, "learning_rate": 8.714037757382663e-06, "loss": 0.6406, "step": 73300 }, { "epoch": 0.4357698640559707, "grad_norm": 8.855364799499512, "learning_rate": 8.715226591849353e-06, "loss": 0.6727, "step": 73310 }, { "epoch": 0.43582930613263904, "grad_norm": 5.810962200164795, "learning_rate": 8.71641542631604e-06, "loss": 0.6694, "step": 73320 }, { "epoch": 0.43588874820930745, "grad_norm": 7.120486736297607, "learning_rate": 8.717604260782729e-06, "loss": 0.6568, "step": 73330 }, { "epoch": 0.4359481902859758, "grad_norm": 6.72280216217041, "learning_rate": 8.718793095249418e-06, "loss": 0.6292, "step": 73340 }, { "epoch": 0.4360076323626442, "grad_norm": 5.757401943206787, "learning_rate": 8.719981929716107e-06, "loss": 0.6486, "step": 73350 }, { "epoch": 0.4360670744393126, "grad_norm": 6.071904182434082, "learning_rate": 8.721170764182796e-06, "loss": 0.6858, "step": 73360 }, { "epoch": 0.436126516515981, "grad_norm": 6.2425456047058105, "learning_rate": 8.722359598649484e-06, "loss": 0.6835, "step": 73370 }, { "epoch": 0.4361859585926494, "grad_norm": 7.279109001159668, "learning_rate": 8.723548433116174e-06, "loss": 0.6673, "step": 73380 }, { "epoch": 0.4362454006693178, "grad_norm": 7.342784881591797, "learning_rate": 8.724737267582862e-06, "loss": 0.653, "step": 73390 }, { "epoch": 0.4363048427459862, "grad_norm": 6.374239921569824, "learning_rate": 8.72592610204955e-06, "loss": 0.6308, "step": 73400 }, { "epoch": 0.43636428482265455, "grad_norm": 7.308119297027588, "learning_rate": 8.72711493651624e-06, "loss": 0.6746, "step": 73410 }, { "epoch": 0.43642372689932296, "grad_norm": 8.350481033325195, "learning_rate": 8.728303770982928e-06, "loss": 0.6447, "step": 73420 }, { "epoch": 0.4364831689759913, "grad_norm": 6.68271541595459, "learning_rate": 8.729492605449618e-06, "loss": 0.5994, "step": 73430 }, { "epoch": 0.43654261105265973, "grad_norm": 5.513530254364014, "learning_rate": 8.730681439916306e-06, "loss": 0.6833, "step": 73440 }, { "epoch": 0.43660205312932815, "grad_norm": 5.864377975463867, "learning_rate": 8.731870274382996e-06, "loss": 0.688, "step": 73450 }, { "epoch": 0.4366614952059965, "grad_norm": 5.263421058654785, "learning_rate": 8.733059108849684e-06, "loss": 0.6458, "step": 73460 }, { "epoch": 0.4367209372826649, "grad_norm": 6.995429992675781, "learning_rate": 8.734247943316374e-06, "loss": 0.6866, "step": 73470 }, { "epoch": 0.4367803793593333, "grad_norm": 7.433459758758545, "learning_rate": 8.735436777783062e-06, "loss": 0.6316, "step": 73480 }, { "epoch": 0.4368398214360017, "grad_norm": 8.605134963989258, "learning_rate": 8.73662561224975e-06, "loss": 0.6582, "step": 73490 }, { "epoch": 0.43689926351267006, "grad_norm": 8.027388572692871, "learning_rate": 8.73781444671644e-06, "loss": 0.7908, "step": 73500 }, { "epoch": 0.43695870558933847, "grad_norm": 6.39098596572876, "learning_rate": 8.739003281183128e-06, "loss": 0.6633, "step": 73510 }, { "epoch": 0.4370181476660069, "grad_norm": 6.346308708190918, "learning_rate": 8.740192115649817e-06, "loss": 0.6305, "step": 73520 }, { "epoch": 0.43707758974267524, "grad_norm": 6.0584940910339355, "learning_rate": 8.741380950116507e-06, "loss": 0.6424, "step": 73530 }, { "epoch": 0.43713703181934366, "grad_norm": 8.214942932128906, "learning_rate": 8.742569784583195e-06, "loss": 0.6685, "step": 73540 }, { "epoch": 0.437196473896012, "grad_norm": 5.522099018096924, "learning_rate": 8.743758619049885e-06, "loss": 0.6081, "step": 73550 }, { "epoch": 0.43725591597268043, "grad_norm": 6.660984992980957, "learning_rate": 8.744947453516573e-06, "loss": 0.6247, "step": 73560 }, { "epoch": 0.4373153580493488, "grad_norm": 6.671211242675781, "learning_rate": 8.746136287983263e-06, "loss": 0.6871, "step": 73570 }, { "epoch": 0.4373748001260172, "grad_norm": 9.118867874145508, "learning_rate": 8.747325122449951e-06, "loss": 0.7389, "step": 73580 }, { "epoch": 0.4374342422026856, "grad_norm": 6.773948669433594, "learning_rate": 8.748513956916639e-06, "loss": 0.6619, "step": 73590 }, { "epoch": 0.437493684279354, "grad_norm": 7.834418773651123, "learning_rate": 8.749702791383329e-06, "loss": 0.6552, "step": 73600 }, { "epoch": 0.4375531263560224, "grad_norm": 8.309257507324219, "learning_rate": 8.750891625850017e-06, "loss": 0.6597, "step": 73610 }, { "epoch": 0.43761256843269075, "grad_norm": 5.595779895782471, "learning_rate": 8.752080460316707e-06, "loss": 0.6633, "step": 73620 }, { "epoch": 0.43767201050935917, "grad_norm": 7.031576633453369, "learning_rate": 8.753269294783395e-06, "loss": 0.6563, "step": 73630 }, { "epoch": 0.4377314525860275, "grad_norm": 11.555731773376465, "learning_rate": 8.754458129250085e-06, "loss": 0.6774, "step": 73640 }, { "epoch": 0.43779089466269594, "grad_norm": 6.614107131958008, "learning_rate": 8.755646963716773e-06, "loss": 0.6696, "step": 73650 }, { "epoch": 0.43785033673936435, "grad_norm": 14.222797393798828, "learning_rate": 8.756835798183462e-06, "loss": 0.658, "step": 73660 }, { "epoch": 0.4379097788160327, "grad_norm": 6.940225601196289, "learning_rate": 8.75802463265015e-06, "loss": 0.6632, "step": 73670 }, { "epoch": 0.4379692208927011, "grad_norm": 7.60427188873291, "learning_rate": 8.759213467116839e-06, "loss": 0.6491, "step": 73680 }, { "epoch": 0.4380286629693695, "grad_norm": 6.631263256072998, "learning_rate": 8.760402301583528e-06, "loss": 0.7111, "step": 73690 }, { "epoch": 0.4380881050460379, "grad_norm": 7.79203462600708, "learning_rate": 8.761591136050216e-06, "loss": 0.6639, "step": 73700 }, { "epoch": 0.43814754712270626, "grad_norm": 6.994173526763916, "learning_rate": 8.762779970516906e-06, "loss": 0.6761, "step": 73710 }, { "epoch": 0.4382069891993747, "grad_norm": 6.779202461242676, "learning_rate": 8.763968804983594e-06, "loss": 0.6538, "step": 73720 }, { "epoch": 0.43826643127604303, "grad_norm": 5.39190149307251, "learning_rate": 8.765157639450284e-06, "loss": 0.6717, "step": 73730 }, { "epoch": 0.43832587335271145, "grad_norm": 6.4078593254089355, "learning_rate": 8.766346473916972e-06, "loss": 0.6713, "step": 73740 }, { "epoch": 0.43838531542937986, "grad_norm": 5.799434185028076, "learning_rate": 8.767535308383662e-06, "loss": 0.702, "step": 73750 }, { "epoch": 0.4384447575060482, "grad_norm": 7.695962429046631, "learning_rate": 8.76872414285035e-06, "loss": 0.6793, "step": 73760 }, { "epoch": 0.43850419958271664, "grad_norm": 7.450405597686768, "learning_rate": 8.769912977317038e-06, "loss": 0.6411, "step": 73770 }, { "epoch": 0.438563641659385, "grad_norm": 7.276194095611572, "learning_rate": 8.771101811783728e-06, "loss": 0.6738, "step": 73780 }, { "epoch": 0.4386230837360534, "grad_norm": 7.653909683227539, "learning_rate": 8.772290646250416e-06, "loss": 0.6142, "step": 73790 }, { "epoch": 0.43868252581272177, "grad_norm": 7.903341293334961, "learning_rate": 8.773479480717106e-06, "loss": 0.712, "step": 73800 }, { "epoch": 0.4387419678893902, "grad_norm": 6.657853126525879, "learning_rate": 8.774668315183794e-06, "loss": 0.7024, "step": 73810 }, { "epoch": 0.4388014099660586, "grad_norm": 8.309399604797363, "learning_rate": 8.775857149650484e-06, "loss": 0.6691, "step": 73820 }, { "epoch": 0.43886085204272696, "grad_norm": 6.098923683166504, "learning_rate": 8.777045984117172e-06, "loss": 0.6885, "step": 73830 }, { "epoch": 0.43892029411939537, "grad_norm": 6.536869525909424, "learning_rate": 8.77823481858386e-06, "loss": 0.6284, "step": 73840 }, { "epoch": 0.43897973619606373, "grad_norm": 7.693339824676514, "learning_rate": 8.77942365305055e-06, "loss": 0.6337, "step": 73850 }, { "epoch": 0.43903917827273214, "grad_norm": 6.067306041717529, "learning_rate": 8.780612487517238e-06, "loss": 0.7331, "step": 73860 }, { "epoch": 0.4390986203494005, "grad_norm": 5.903402805328369, "learning_rate": 8.781801321983927e-06, "loss": 0.6453, "step": 73870 }, { "epoch": 0.4391580624260689, "grad_norm": 6.586577415466309, "learning_rate": 8.782990156450617e-06, "loss": 0.7349, "step": 73880 }, { "epoch": 0.43921750450273733, "grad_norm": 5.955443382263184, "learning_rate": 8.784178990917305e-06, "loss": 0.6839, "step": 73890 }, { "epoch": 0.4392769465794057, "grad_norm": 5.604674339294434, "learning_rate": 8.785367825383995e-06, "loss": 0.6416, "step": 73900 }, { "epoch": 0.4393363886560741, "grad_norm": 7.66032600402832, "learning_rate": 8.786556659850683e-06, "loss": 0.6791, "step": 73910 }, { "epoch": 0.43939583073274247, "grad_norm": 6.70977783203125, "learning_rate": 8.787745494317373e-06, "loss": 0.6537, "step": 73920 }, { "epoch": 0.4394552728094109, "grad_norm": 5.8454508781433105, "learning_rate": 8.788934328784061e-06, "loss": 0.6275, "step": 73930 }, { "epoch": 0.43951471488607924, "grad_norm": 7.121846675872803, "learning_rate": 8.79012316325075e-06, "loss": 0.6539, "step": 73940 }, { "epoch": 0.43957415696274765, "grad_norm": 7.499277591705322, "learning_rate": 8.791311997717439e-06, "loss": 0.6735, "step": 73950 }, { "epoch": 0.43963359903941607, "grad_norm": 6.843170642852783, "learning_rate": 8.792500832184127e-06, "loss": 0.6247, "step": 73960 }, { "epoch": 0.4396930411160844, "grad_norm": 5.921866416931152, "learning_rate": 8.793689666650817e-06, "loss": 0.6429, "step": 73970 }, { "epoch": 0.43975248319275284, "grad_norm": 8.152487754821777, "learning_rate": 8.794878501117505e-06, "loss": 0.6828, "step": 73980 }, { "epoch": 0.4398119252694212, "grad_norm": 5.611508846282959, "learning_rate": 8.796067335584195e-06, "loss": 0.609, "step": 73990 }, { "epoch": 0.4398713673460896, "grad_norm": 6.861639976501465, "learning_rate": 8.797256170050883e-06, "loss": 0.6956, "step": 74000 }, { "epoch": 0.439930809422758, "grad_norm": 8.166783332824707, "learning_rate": 8.798445004517572e-06, "loss": 0.674, "step": 74010 }, { "epoch": 0.4399902514994264, "grad_norm": 7.946821689605713, "learning_rate": 8.79963383898426e-06, "loss": 0.6306, "step": 74020 }, { "epoch": 0.44004969357609475, "grad_norm": 5.569235324859619, "learning_rate": 8.80082267345095e-06, "loss": 0.6457, "step": 74030 }, { "epoch": 0.44010913565276316, "grad_norm": 7.656210899353027, "learning_rate": 8.802011507917638e-06, "loss": 0.6644, "step": 74040 }, { "epoch": 0.4401685777294316, "grad_norm": 6.517065048217773, "learning_rate": 8.803200342384326e-06, "loss": 0.6836, "step": 74050 }, { "epoch": 0.44022801980609993, "grad_norm": 7.580687522888184, "learning_rate": 8.804389176851016e-06, "loss": 0.6893, "step": 74060 }, { "epoch": 0.44028746188276835, "grad_norm": 8.051018714904785, "learning_rate": 8.805578011317704e-06, "loss": 0.6583, "step": 74070 }, { "epoch": 0.4403469039594367, "grad_norm": 6.07833194732666, "learning_rate": 8.806766845784394e-06, "loss": 0.7148, "step": 74080 }, { "epoch": 0.4404063460361051, "grad_norm": 7.021483898162842, "learning_rate": 8.807955680251082e-06, "loss": 0.7032, "step": 74090 }, { "epoch": 0.4404657881127735, "grad_norm": 6.05959939956665, "learning_rate": 8.809144514717772e-06, "loss": 0.6859, "step": 74100 }, { "epoch": 0.4405252301894419, "grad_norm": 6.345950603485107, "learning_rate": 8.81033334918446e-06, "loss": 0.6338, "step": 74110 }, { "epoch": 0.4405846722661103, "grad_norm": 7.8951311111450195, "learning_rate": 8.811522183651148e-06, "loss": 0.6731, "step": 74120 }, { "epoch": 0.44064411434277867, "grad_norm": 5.766531944274902, "learning_rate": 8.812711018117838e-06, "loss": 0.6564, "step": 74130 }, { "epoch": 0.4407035564194471, "grad_norm": 7.987969398498535, "learning_rate": 8.813899852584526e-06, "loss": 0.7045, "step": 74140 }, { "epoch": 0.44076299849611544, "grad_norm": 6.99547815322876, "learning_rate": 8.815088687051216e-06, "loss": 0.6404, "step": 74150 }, { "epoch": 0.44082244057278386, "grad_norm": 6.855571746826172, "learning_rate": 8.816277521517904e-06, "loss": 0.6695, "step": 74160 }, { "epoch": 0.4408818826494522, "grad_norm": 7.211769104003906, "learning_rate": 8.817466355984594e-06, "loss": 0.6551, "step": 74170 }, { "epoch": 0.44094132472612063, "grad_norm": 6.737572193145752, "learning_rate": 8.818655190451282e-06, "loss": 0.6171, "step": 74180 }, { "epoch": 0.44100076680278905, "grad_norm": 6.249999523162842, "learning_rate": 8.819844024917971e-06, "loss": 0.7117, "step": 74190 }, { "epoch": 0.4410602088794574, "grad_norm": 5.2015581130981445, "learning_rate": 8.82103285938466e-06, "loss": 0.7132, "step": 74200 }, { "epoch": 0.4411196509561258, "grad_norm": 7.9362616539001465, "learning_rate": 8.82222169385135e-06, "loss": 0.6368, "step": 74210 }, { "epoch": 0.4411790930327942, "grad_norm": 5.400200366973877, "learning_rate": 8.823410528318039e-06, "loss": 0.6871, "step": 74220 }, { "epoch": 0.4412385351094626, "grad_norm": 6.079804420471191, "learning_rate": 8.824599362784727e-06, "loss": 0.6356, "step": 74230 }, { "epoch": 0.44129797718613095, "grad_norm": 7.479583263397217, "learning_rate": 8.825788197251415e-06, "loss": 0.6071, "step": 74240 }, { "epoch": 0.44135741926279937, "grad_norm": 5.976236820220947, "learning_rate": 8.826977031718105e-06, "loss": 0.6243, "step": 74250 }, { "epoch": 0.4414168613394678, "grad_norm": 8.283864974975586, "learning_rate": 8.828165866184793e-06, "loss": 0.6131, "step": 74260 }, { "epoch": 0.44147630341613614, "grad_norm": 6.004528999328613, "learning_rate": 8.829354700651483e-06, "loss": 0.6396, "step": 74270 }, { "epoch": 0.44153574549280455, "grad_norm": 5.407139778137207, "learning_rate": 8.830543535118171e-06, "loss": 0.6997, "step": 74280 }, { "epoch": 0.4415951875694729, "grad_norm": 8.241677284240723, "learning_rate": 8.83173236958486e-06, "loss": 0.689, "step": 74290 }, { "epoch": 0.44165462964614133, "grad_norm": 6.5278778076171875, "learning_rate": 8.832921204051549e-06, "loss": 0.6917, "step": 74300 }, { "epoch": 0.4417140717228097, "grad_norm": 8.079375267028809, "learning_rate": 8.834110038518239e-06, "loss": 0.7314, "step": 74310 }, { "epoch": 0.4417735137994781, "grad_norm": 7.096177577972412, "learning_rate": 8.835298872984927e-06, "loss": 0.6778, "step": 74320 }, { "epoch": 0.4418329558761465, "grad_norm": 7.252387523651123, "learning_rate": 8.836487707451615e-06, "loss": 0.674, "step": 74330 }, { "epoch": 0.4418923979528149, "grad_norm": 6.9390716552734375, "learning_rate": 8.837676541918304e-06, "loss": 0.5977, "step": 74340 }, { "epoch": 0.4419518400294833, "grad_norm": 5.630265712738037, "learning_rate": 8.838865376384993e-06, "loss": 0.688, "step": 74350 }, { "epoch": 0.44201128210615165, "grad_norm": 9.0673189163208, "learning_rate": 8.840054210851682e-06, "loss": 0.7373, "step": 74360 }, { "epoch": 0.44207072418282006, "grad_norm": 5.195168495178223, "learning_rate": 8.84124304531837e-06, "loss": 0.6799, "step": 74370 }, { "epoch": 0.4421301662594884, "grad_norm": 6.671123027801514, "learning_rate": 8.84243187978506e-06, "loss": 0.7211, "step": 74380 }, { "epoch": 0.44218960833615684, "grad_norm": 6.957724094390869, "learning_rate": 8.843620714251748e-06, "loss": 0.6407, "step": 74390 }, { "epoch": 0.4422490504128252, "grad_norm": 6.820651054382324, "learning_rate": 8.844809548718436e-06, "loss": 0.6614, "step": 74400 }, { "epoch": 0.4423084924894936, "grad_norm": 6.188808917999268, "learning_rate": 8.845998383185126e-06, "loss": 0.6355, "step": 74410 }, { "epoch": 0.442367934566162, "grad_norm": 6.583442687988281, "learning_rate": 8.847187217651814e-06, "loss": 0.7032, "step": 74420 }, { "epoch": 0.4424273766428304, "grad_norm": 7.906095027923584, "learning_rate": 8.848376052118504e-06, "loss": 0.689, "step": 74430 }, { "epoch": 0.4424868187194988, "grad_norm": 7.085721492767334, "learning_rate": 8.849564886585192e-06, "loss": 0.6543, "step": 74440 }, { "epoch": 0.44254626079616716, "grad_norm": 6.713000774383545, "learning_rate": 8.850753721051882e-06, "loss": 0.7314, "step": 74450 }, { "epoch": 0.44260570287283557, "grad_norm": 11.223139762878418, "learning_rate": 8.85194255551857e-06, "loss": 0.6681, "step": 74460 }, { "epoch": 0.44266514494950393, "grad_norm": 6.673531532287598, "learning_rate": 8.85313138998526e-06, "loss": 0.6447, "step": 74470 }, { "epoch": 0.44272458702617234, "grad_norm": 9.064204216003418, "learning_rate": 8.854320224451948e-06, "loss": 0.677, "step": 74480 }, { "epoch": 0.44278402910284076, "grad_norm": 6.681271076202393, "learning_rate": 8.855509058918636e-06, "loss": 0.6298, "step": 74490 }, { "epoch": 0.4428434711795091, "grad_norm": 5.8155622482299805, "learning_rate": 8.856697893385326e-06, "loss": 0.6445, "step": 74500 }, { "epoch": 0.44290291325617753, "grad_norm": 6.370505332946777, "learning_rate": 8.857886727852014e-06, "loss": 0.6224, "step": 74510 }, { "epoch": 0.4429623553328459, "grad_norm": 6.707084655761719, "learning_rate": 8.859075562318703e-06, "loss": 0.6526, "step": 74520 }, { "epoch": 0.4430217974095143, "grad_norm": 8.464041709899902, "learning_rate": 8.860264396785392e-06, "loss": 0.5989, "step": 74530 }, { "epoch": 0.44308123948618267, "grad_norm": 5.796733379364014, "learning_rate": 8.861453231252081e-06, "loss": 0.6154, "step": 74540 }, { "epoch": 0.4431406815628511, "grad_norm": 5.396122455596924, "learning_rate": 8.86264206571877e-06, "loss": 0.6507, "step": 74550 }, { "epoch": 0.4432001236395195, "grad_norm": 7.005738258361816, "learning_rate": 8.863830900185459e-06, "loss": 0.6402, "step": 74560 }, { "epoch": 0.44325956571618785, "grad_norm": 6.336482524871826, "learning_rate": 8.865019734652149e-06, "loss": 0.6264, "step": 74570 }, { "epoch": 0.44331900779285627, "grad_norm": 5.005435943603516, "learning_rate": 8.866208569118837e-06, "loss": 0.698, "step": 74580 }, { "epoch": 0.4433784498695246, "grad_norm": 6.9227166175842285, "learning_rate": 8.867397403585525e-06, "loss": 0.6499, "step": 74590 }, { "epoch": 0.44343789194619304, "grad_norm": 5.1005539894104, "learning_rate": 8.868586238052215e-06, "loss": 0.6983, "step": 74600 }, { "epoch": 0.4434973340228614, "grad_norm": 6.4847917556762695, "learning_rate": 8.869775072518903e-06, "loss": 0.6784, "step": 74610 }, { "epoch": 0.4435567760995298, "grad_norm": 5.417508125305176, "learning_rate": 8.870963906985593e-06, "loss": 0.6488, "step": 74620 }, { "epoch": 0.44361621817619823, "grad_norm": 6.848699569702148, "learning_rate": 8.87215274145228e-06, "loss": 0.7145, "step": 74630 }, { "epoch": 0.4436756602528666, "grad_norm": 7.665206432342529, "learning_rate": 8.87334157591897e-06, "loss": 0.6747, "step": 74640 }, { "epoch": 0.443735102329535, "grad_norm": 7.6275858879089355, "learning_rate": 8.874530410385659e-06, "loss": 0.6761, "step": 74650 }, { "epoch": 0.44379454440620336, "grad_norm": 6.007904052734375, "learning_rate": 8.875719244852348e-06, "loss": 0.6928, "step": 74660 }, { "epoch": 0.4438539864828718, "grad_norm": 6.825649738311768, "learning_rate": 8.876908079319037e-06, "loss": 0.7244, "step": 74670 }, { "epoch": 0.44391342855954014, "grad_norm": 7.481020927429199, "learning_rate": 8.878096913785725e-06, "loss": 0.718, "step": 74680 }, { "epoch": 0.44397287063620855, "grad_norm": 6.291934490203857, "learning_rate": 8.879285748252414e-06, "loss": 0.664, "step": 74690 }, { "epoch": 0.44403231271287696, "grad_norm": 8.061962127685547, "learning_rate": 8.880474582719102e-06, "loss": 0.6481, "step": 74700 }, { "epoch": 0.4440917547895453, "grad_norm": 8.326680183410645, "learning_rate": 8.881663417185792e-06, "loss": 0.7073, "step": 74710 }, { "epoch": 0.44415119686621374, "grad_norm": 7.244720935821533, "learning_rate": 8.88285225165248e-06, "loss": 0.6513, "step": 74720 }, { "epoch": 0.4442106389428821, "grad_norm": 7.419360637664795, "learning_rate": 8.88404108611917e-06, "loss": 0.6792, "step": 74730 }, { "epoch": 0.4442700810195505, "grad_norm": 5.943136215209961, "learning_rate": 8.885229920585858e-06, "loss": 0.6547, "step": 74740 }, { "epoch": 0.44432952309621887, "grad_norm": 5.657949924468994, "learning_rate": 8.886418755052548e-06, "loss": 0.649, "step": 74750 }, { "epoch": 0.4443889651728873, "grad_norm": 6.414536952972412, "learning_rate": 8.887607589519236e-06, "loss": 0.6531, "step": 74760 }, { "epoch": 0.44444840724955564, "grad_norm": 6.203615665435791, "learning_rate": 8.888796423985924e-06, "loss": 0.6923, "step": 74770 }, { "epoch": 0.44450784932622406, "grad_norm": 5.808067798614502, "learning_rate": 8.889985258452614e-06, "loss": 0.6579, "step": 74780 }, { "epoch": 0.4445672914028925, "grad_norm": 6.9607954025268555, "learning_rate": 8.891174092919302e-06, "loss": 0.7003, "step": 74790 }, { "epoch": 0.44462673347956083, "grad_norm": 9.392731666564941, "learning_rate": 8.892362927385992e-06, "loss": 0.6773, "step": 74800 }, { "epoch": 0.44468617555622925, "grad_norm": 7.442906379699707, "learning_rate": 8.89355176185268e-06, "loss": 0.6886, "step": 74810 }, { "epoch": 0.4447456176328976, "grad_norm": 5.858150482177734, "learning_rate": 8.89474059631937e-06, "loss": 0.7056, "step": 74820 }, { "epoch": 0.444805059709566, "grad_norm": 6.175341606140137, "learning_rate": 8.895929430786058e-06, "loss": 0.6933, "step": 74830 }, { "epoch": 0.4448645017862344, "grad_norm": 5.853357791900635, "learning_rate": 8.897118265252747e-06, "loss": 0.6814, "step": 74840 }, { "epoch": 0.4449239438629028, "grad_norm": 10.188029289245605, "learning_rate": 8.898307099719436e-06, "loss": 0.6706, "step": 74850 }, { "epoch": 0.4449833859395712, "grad_norm": 7.046229839324951, "learning_rate": 8.899495934186124e-06, "loss": 0.6964, "step": 74860 }, { "epoch": 0.44504282801623957, "grad_norm": 6.623928546905518, "learning_rate": 8.900684768652813e-06, "loss": 0.6823, "step": 74870 }, { "epoch": 0.445102270092908, "grad_norm": 6.091728210449219, "learning_rate": 8.901873603119501e-06, "loss": 0.7015, "step": 74880 }, { "epoch": 0.44516171216957634, "grad_norm": 6.550639629364014, "learning_rate": 8.903062437586191e-06, "loss": 0.654, "step": 74890 }, { "epoch": 0.44522115424624475, "grad_norm": 7.069737434387207, "learning_rate": 8.90425127205288e-06, "loss": 0.6267, "step": 74900 }, { "epoch": 0.4452805963229131, "grad_norm": 7.570486068725586, "learning_rate": 8.905440106519569e-06, "loss": 0.6793, "step": 74910 }, { "epoch": 0.44534003839958153, "grad_norm": 8.562134742736816, "learning_rate": 8.906628940986259e-06, "loss": 0.7068, "step": 74920 }, { "epoch": 0.44539948047624994, "grad_norm": 7.482991695404053, "learning_rate": 8.907817775452947e-06, "loss": 0.6349, "step": 74930 }, { "epoch": 0.4454589225529183, "grad_norm": 5.541501522064209, "learning_rate": 8.909006609919637e-06, "loss": 0.5749, "step": 74940 }, { "epoch": 0.4455183646295867, "grad_norm": 7.1769700050354, "learning_rate": 8.910195444386325e-06, "loss": 0.6477, "step": 74950 }, { "epoch": 0.4455778067062551, "grad_norm": 6.899251461029053, "learning_rate": 8.911384278853013e-06, "loss": 0.6903, "step": 74960 }, { "epoch": 0.4456372487829235, "grad_norm": 5.742701053619385, "learning_rate": 8.912573113319703e-06, "loss": 0.6469, "step": 74970 }, { "epoch": 0.44569669085959185, "grad_norm": 7.226464748382568, "learning_rate": 8.91376194778639e-06, "loss": 0.6371, "step": 74980 }, { "epoch": 0.44575613293626026, "grad_norm": 6.603813171386719, "learning_rate": 8.91495078225308e-06, "loss": 0.7139, "step": 74990 }, { "epoch": 0.4458155750129287, "grad_norm": 9.903709411621094, "learning_rate": 8.916139616719769e-06, "loss": 0.7085, "step": 75000 }, { "epoch": 0.44587501708959704, "grad_norm": 6.225055694580078, "learning_rate": 8.917328451186458e-06, "loss": 0.6887, "step": 75010 }, { "epoch": 0.44593445916626545, "grad_norm": 7.104851722717285, "learning_rate": 8.918517285653146e-06, "loss": 0.6737, "step": 75020 }, { "epoch": 0.4459939012429338, "grad_norm": 6.75056791305542, "learning_rate": 8.919706120119836e-06, "loss": 0.6351, "step": 75030 }, { "epoch": 0.4460533433196022, "grad_norm": 6.096226692199707, "learning_rate": 8.920894954586524e-06, "loss": 0.6792, "step": 75040 }, { "epoch": 0.4461127853962706, "grad_norm": 6.887120723724365, "learning_rate": 8.922083789053212e-06, "loss": 0.7416, "step": 75050 }, { "epoch": 0.446172227472939, "grad_norm": 6.382397174835205, "learning_rate": 8.923272623519902e-06, "loss": 0.6936, "step": 75060 }, { "epoch": 0.4462316695496074, "grad_norm": 9.683271408081055, "learning_rate": 8.92446145798659e-06, "loss": 0.7208, "step": 75070 }, { "epoch": 0.44629111162627577, "grad_norm": 6.360548973083496, "learning_rate": 8.92565029245328e-06, "loss": 0.5793, "step": 75080 }, { "epoch": 0.4463505537029442, "grad_norm": 6.9607086181640625, "learning_rate": 8.926839126919968e-06, "loss": 0.6498, "step": 75090 }, { "epoch": 0.44640999577961255, "grad_norm": 7.947779178619385, "learning_rate": 8.928027961386658e-06, "loss": 0.7488, "step": 75100 }, { "epoch": 0.44646943785628096, "grad_norm": 7.476940631866455, "learning_rate": 8.929216795853346e-06, "loss": 0.7185, "step": 75110 }, { "epoch": 0.4465288799329493, "grad_norm": 5.177277565002441, "learning_rate": 8.930405630320034e-06, "loss": 0.699, "step": 75120 }, { "epoch": 0.44658832200961773, "grad_norm": 6.134194850921631, "learning_rate": 8.931594464786724e-06, "loss": 0.6134, "step": 75130 }, { "epoch": 0.4466477640862861, "grad_norm": 6.419766902923584, "learning_rate": 8.932783299253412e-06, "loss": 0.6069, "step": 75140 }, { "epoch": 0.4467072061629545, "grad_norm": 7.56420373916626, "learning_rate": 8.933972133720102e-06, "loss": 0.6541, "step": 75150 }, { "epoch": 0.4467666482396229, "grad_norm": 6.509567737579346, "learning_rate": 8.93516096818679e-06, "loss": 0.6847, "step": 75160 }, { "epoch": 0.4468260903162913, "grad_norm": 6.920163154602051, "learning_rate": 8.93634980265348e-06, "loss": 0.6679, "step": 75170 }, { "epoch": 0.4468855323929597, "grad_norm": 6.904421806335449, "learning_rate": 8.937538637120168e-06, "loss": 0.6685, "step": 75180 }, { "epoch": 0.44694497446962805, "grad_norm": 7.457043170928955, "learning_rate": 8.938727471586857e-06, "loss": 0.6267, "step": 75190 }, { "epoch": 0.44700441654629647, "grad_norm": 6.988376140594482, "learning_rate": 8.939916306053545e-06, "loss": 0.709, "step": 75200 }, { "epoch": 0.4470638586229648, "grad_norm": 7.235383987426758, "learning_rate": 8.941105140520233e-06, "loss": 0.6971, "step": 75210 }, { "epoch": 0.44712330069963324, "grad_norm": 6.720969200134277, "learning_rate": 8.942293974986923e-06, "loss": 0.67, "step": 75220 }, { "epoch": 0.44718274277630166, "grad_norm": 6.612768650054932, "learning_rate": 8.943482809453611e-06, "loss": 0.6314, "step": 75230 }, { "epoch": 0.44724218485297, "grad_norm": 6.8317155838012695, "learning_rate": 8.944671643920301e-06, "loss": 0.6447, "step": 75240 }, { "epoch": 0.44730162692963843, "grad_norm": 6.629560947418213, "learning_rate": 8.945860478386991e-06, "loss": 0.6747, "step": 75250 }, { "epoch": 0.4473610690063068, "grad_norm": 7.8313679695129395, "learning_rate": 8.947049312853679e-06, "loss": 0.6607, "step": 75260 }, { "epoch": 0.4474205110829752, "grad_norm": 6.775033473968506, "learning_rate": 8.948238147320369e-06, "loss": 0.6852, "step": 75270 }, { "epoch": 0.44747995315964356, "grad_norm": 6.124312877655029, "learning_rate": 8.949426981787057e-06, "loss": 0.6373, "step": 75280 }, { "epoch": 0.447539395236312, "grad_norm": 7.156580924987793, "learning_rate": 8.950615816253747e-06, "loss": 0.6354, "step": 75290 }, { "epoch": 0.4475988373129804, "grad_norm": 6.455387592315674, "learning_rate": 8.951804650720435e-06, "loss": 0.6635, "step": 75300 }, { "epoch": 0.44765827938964875, "grad_norm": 8.895745277404785, "learning_rate": 8.952993485187124e-06, "loss": 0.6837, "step": 75310 }, { "epoch": 0.44771772146631716, "grad_norm": 9.654086112976074, "learning_rate": 8.954182319653813e-06, "loss": 0.6027, "step": 75320 }, { "epoch": 0.4477771635429855, "grad_norm": 6.23878288269043, "learning_rate": 8.9553711541205e-06, "loss": 0.7072, "step": 75330 }, { "epoch": 0.44783660561965394, "grad_norm": 6.14970064163208, "learning_rate": 8.95655998858719e-06, "loss": 0.6501, "step": 75340 }, { "epoch": 0.4478960476963223, "grad_norm": 8.519063949584961, "learning_rate": 8.957748823053878e-06, "loss": 0.7515, "step": 75350 }, { "epoch": 0.4479554897729907, "grad_norm": 8.180415153503418, "learning_rate": 8.958937657520568e-06, "loss": 0.7246, "step": 75360 }, { "epoch": 0.4480149318496591, "grad_norm": 5.968411445617676, "learning_rate": 8.960126491987256e-06, "loss": 0.6489, "step": 75370 }, { "epoch": 0.4480743739263275, "grad_norm": 7.283722400665283, "learning_rate": 8.961315326453946e-06, "loss": 0.6343, "step": 75380 }, { "epoch": 0.4481338160029959, "grad_norm": 6.103301048278809, "learning_rate": 8.962504160920634e-06, "loss": 0.693, "step": 75390 }, { "epoch": 0.44819325807966426, "grad_norm": 5.632181167602539, "learning_rate": 8.963692995387322e-06, "loss": 0.6448, "step": 75400 }, { "epoch": 0.4482527001563327, "grad_norm": 6.929780006408691, "learning_rate": 8.964881829854012e-06, "loss": 0.6745, "step": 75410 }, { "epoch": 0.44831214223300103, "grad_norm": 5.659232139587402, "learning_rate": 8.9660706643207e-06, "loss": 0.6116, "step": 75420 }, { "epoch": 0.44837158430966945, "grad_norm": 5.369657039642334, "learning_rate": 8.96725949878739e-06, "loss": 0.6542, "step": 75430 }, { "epoch": 0.4484310263863378, "grad_norm": 6.874993801116943, "learning_rate": 8.968448333254078e-06, "loss": 0.7038, "step": 75440 }, { "epoch": 0.4484904684630062, "grad_norm": 6.441052436828613, "learning_rate": 8.969637167720768e-06, "loss": 0.7116, "step": 75450 }, { "epoch": 0.44854991053967463, "grad_norm": 6.504663467407227, "learning_rate": 8.970826002187456e-06, "loss": 0.7108, "step": 75460 }, { "epoch": 0.448609352616343, "grad_norm": 7.2071428298950195, "learning_rate": 8.972014836654146e-06, "loss": 0.7214, "step": 75470 }, { "epoch": 0.4486687946930114, "grad_norm": 9.623905181884766, "learning_rate": 8.973203671120834e-06, "loss": 0.628, "step": 75480 }, { "epoch": 0.44872823676967977, "grad_norm": 5.887877941131592, "learning_rate": 8.974392505587522e-06, "loss": 0.6666, "step": 75490 }, { "epoch": 0.4487876788463482, "grad_norm": 6.760704517364502, "learning_rate": 8.975581340054212e-06, "loss": 0.6881, "step": 75500 }, { "epoch": 0.44884712092301654, "grad_norm": 7.839815616607666, "learning_rate": 8.9767701745209e-06, "loss": 0.6363, "step": 75510 }, { "epoch": 0.44890656299968495, "grad_norm": 6.94171142578125, "learning_rate": 8.97795900898759e-06, "loss": 0.6039, "step": 75520 }, { "epoch": 0.44896600507635337, "grad_norm": 5.0927252769470215, "learning_rate": 8.979147843454277e-06, "loss": 0.6535, "step": 75530 }, { "epoch": 0.44902544715302173, "grad_norm": 7.930209636688232, "learning_rate": 8.980336677920967e-06, "loss": 0.6292, "step": 75540 }, { "epoch": 0.44908488922969014, "grad_norm": 4.540642738342285, "learning_rate": 8.981525512387655e-06, "loss": 0.605, "step": 75550 }, { "epoch": 0.4491443313063585, "grad_norm": 5.004389762878418, "learning_rate": 8.982714346854345e-06, "loss": 0.6363, "step": 75560 }, { "epoch": 0.4492037733830269, "grad_norm": 5.940126895904541, "learning_rate": 8.983903181321033e-06, "loss": 0.7008, "step": 75570 }, { "epoch": 0.4492632154596953, "grad_norm": 6.463993072509766, "learning_rate": 8.985092015787721e-06, "loss": 0.6679, "step": 75580 }, { "epoch": 0.4493226575363637, "grad_norm": 6.396550178527832, "learning_rate": 8.986280850254411e-06, "loss": 0.6111, "step": 75590 }, { "epoch": 0.4493820996130321, "grad_norm": 7.315058708190918, "learning_rate": 8.9874696847211e-06, "loss": 0.6547, "step": 75600 }, { "epoch": 0.44944154168970046, "grad_norm": 7.080069541931152, "learning_rate": 8.988658519187789e-06, "loss": 0.632, "step": 75610 }, { "epoch": 0.4495009837663689, "grad_norm": 5.977339267730713, "learning_rate": 8.989847353654479e-06, "loss": 0.6512, "step": 75620 }, { "epoch": 0.44956042584303724, "grad_norm": 6.332647323608398, "learning_rate": 8.991036188121167e-06, "loss": 0.6452, "step": 75630 }, { "epoch": 0.44961986791970565, "grad_norm": 6.8475470542907715, "learning_rate": 8.992225022587857e-06, "loss": 0.6383, "step": 75640 }, { "epoch": 0.449679309996374, "grad_norm": 5.581772804260254, "learning_rate": 8.993413857054545e-06, "loss": 0.6869, "step": 75650 }, { "epoch": 0.4497387520730424, "grad_norm": 7.12214469909668, "learning_rate": 8.994602691521234e-06, "loss": 0.6834, "step": 75660 }, { "epoch": 0.44979819414971084, "grad_norm": 7.430858612060547, "learning_rate": 8.995791525987922e-06, "loss": 0.6582, "step": 75670 }, { "epoch": 0.4498576362263792, "grad_norm": 5.839894771575928, "learning_rate": 8.99698036045461e-06, "loss": 0.6382, "step": 75680 }, { "epoch": 0.4499170783030476, "grad_norm": 5.744927406311035, "learning_rate": 8.9981691949213e-06, "loss": 0.6807, "step": 75690 }, { "epoch": 0.44997652037971597, "grad_norm": 5.965359210968018, "learning_rate": 8.999358029387988e-06, "loss": 0.6828, "step": 75700 }, { "epoch": 0.4500359624563844, "grad_norm": 5.266628265380859, "learning_rate": 9.000546863854678e-06, "loss": 0.6379, "step": 75710 }, { "epoch": 0.45009540453305275, "grad_norm": 4.5361714363098145, "learning_rate": 9.001735698321366e-06, "loss": 0.6826, "step": 75720 }, { "epoch": 0.45015484660972116, "grad_norm": 7.973202228546143, "learning_rate": 9.002924532788056e-06, "loss": 0.6617, "step": 75730 }, { "epoch": 0.4502142886863896, "grad_norm": 6.659485340118408, "learning_rate": 9.004113367254744e-06, "loss": 0.6786, "step": 75740 }, { "epoch": 0.45027373076305793, "grad_norm": 5.216318130493164, "learning_rate": 9.005302201721434e-06, "loss": 0.7017, "step": 75750 }, { "epoch": 0.45033317283972635, "grad_norm": 7.414309024810791, "learning_rate": 9.006491036188122e-06, "loss": 0.6811, "step": 75760 }, { "epoch": 0.4503926149163947, "grad_norm": 8.274720191955566, "learning_rate": 9.00767987065481e-06, "loss": 0.7012, "step": 75770 }, { "epoch": 0.4504520569930631, "grad_norm": 8.300697326660156, "learning_rate": 9.0088687051215e-06, "loss": 0.6776, "step": 75780 }, { "epoch": 0.4505114990697315, "grad_norm": 6.409397602081299, "learning_rate": 9.010057539588188e-06, "loss": 0.6993, "step": 75790 }, { "epoch": 0.4505709411463999, "grad_norm": 6.940723896026611, "learning_rate": 9.011246374054878e-06, "loss": 0.7034, "step": 75800 }, { "epoch": 0.45063038322306825, "grad_norm": 6.68126106262207, "learning_rate": 9.012435208521566e-06, "loss": 0.7434, "step": 75810 }, { "epoch": 0.45068982529973667, "grad_norm": 6.93993616104126, "learning_rate": 9.013624042988256e-06, "loss": 0.6458, "step": 75820 }, { "epoch": 0.4507492673764051, "grad_norm": 5.5183820724487305, "learning_rate": 9.014812877454944e-06, "loss": 0.598, "step": 75830 }, { "epoch": 0.45080870945307344, "grad_norm": 7.547334671020508, "learning_rate": 9.016001711921633e-06, "loss": 0.6739, "step": 75840 }, { "epoch": 0.45086815152974186, "grad_norm": 6.623092174530029, "learning_rate": 9.017190546388321e-06, "loss": 0.6099, "step": 75850 }, { "epoch": 0.4509275936064102, "grad_norm": 5.605875015258789, "learning_rate": 9.01837938085501e-06, "loss": 0.6709, "step": 75860 }, { "epoch": 0.45098703568307863, "grad_norm": 7.46129035949707, "learning_rate": 9.0195682153217e-06, "loss": 0.7628, "step": 75870 }, { "epoch": 0.451046477759747, "grad_norm": 6.495907306671143, "learning_rate": 9.020757049788387e-06, "loss": 0.6094, "step": 75880 }, { "epoch": 0.4511059198364154, "grad_norm": 6.011394023895264, "learning_rate": 9.021945884255077e-06, "loss": 0.6737, "step": 75890 }, { "epoch": 0.4511653619130838, "grad_norm": 6.791207790374756, "learning_rate": 9.023134718721765e-06, "loss": 0.652, "step": 75900 }, { "epoch": 0.4512248039897522, "grad_norm": 6.015217304229736, "learning_rate": 9.024323553188455e-06, "loss": 0.6545, "step": 75910 }, { "epoch": 0.4512842460664206, "grad_norm": 4.705957412719727, "learning_rate": 9.025512387655143e-06, "loss": 0.6275, "step": 75920 }, { "epoch": 0.45134368814308895, "grad_norm": 9.128430366516113, "learning_rate": 9.026701222121831e-06, "loss": 0.7188, "step": 75930 }, { "epoch": 0.45140313021975736, "grad_norm": 6.774396896362305, "learning_rate": 9.027890056588521e-06, "loss": 0.6333, "step": 75940 }, { "epoch": 0.4514625722964257, "grad_norm": 5.917651653289795, "learning_rate": 9.02907889105521e-06, "loss": 0.6203, "step": 75950 }, { "epoch": 0.45152201437309414, "grad_norm": 7.080188274383545, "learning_rate": 9.030267725521899e-06, "loss": 0.6946, "step": 75960 }, { "epoch": 0.45158145644976255, "grad_norm": 7.924782752990723, "learning_rate": 9.031456559988589e-06, "loss": 0.7017, "step": 75970 }, { "epoch": 0.4516408985264309, "grad_norm": 7.524853706359863, "learning_rate": 9.032645394455277e-06, "loss": 0.6861, "step": 75980 }, { "epoch": 0.4517003406030993, "grad_norm": 5.446958541870117, "learning_rate": 9.033834228921966e-06, "loss": 0.637, "step": 75990 }, { "epoch": 0.4517597826797677, "grad_norm": 6.408275604248047, "learning_rate": 9.035023063388655e-06, "loss": 0.6904, "step": 76000 }, { "epoch": 0.4518192247564361, "grad_norm": 5.341508865356445, "learning_rate": 9.036211897855344e-06, "loss": 0.6398, "step": 76010 }, { "epoch": 0.45187866683310446, "grad_norm": 6.897553443908691, "learning_rate": 9.037400732322032e-06, "loss": 0.6839, "step": 76020 }, { "epoch": 0.4519381089097729, "grad_norm": 6.678037643432617, "learning_rate": 9.038589566788722e-06, "loss": 0.6318, "step": 76030 }, { "epoch": 0.4519975509864413, "grad_norm": 6.971332550048828, "learning_rate": 9.03977840125541e-06, "loss": 0.6893, "step": 76040 }, { "epoch": 0.45205699306310965, "grad_norm": 7.381845474243164, "learning_rate": 9.040967235722098e-06, "loss": 0.6719, "step": 76050 }, { "epoch": 0.45211643513977806, "grad_norm": 6.401989936828613, "learning_rate": 9.042156070188788e-06, "loss": 0.7069, "step": 76060 }, { "epoch": 0.4521758772164464, "grad_norm": 7.085028648376465, "learning_rate": 9.043344904655476e-06, "loss": 0.6844, "step": 76070 }, { "epoch": 0.45223531929311483, "grad_norm": 4.93873929977417, "learning_rate": 9.044533739122166e-06, "loss": 0.647, "step": 76080 }, { "epoch": 0.4522947613697832, "grad_norm": 6.637571334838867, "learning_rate": 9.045722573588854e-06, "loss": 0.6866, "step": 76090 }, { "epoch": 0.4523542034464516, "grad_norm": 7.654886722564697, "learning_rate": 9.046911408055544e-06, "loss": 0.6438, "step": 76100 }, { "epoch": 0.45241364552312, "grad_norm": 7.0093865394592285, "learning_rate": 9.048100242522232e-06, "loss": 0.6435, "step": 76110 }, { "epoch": 0.4524730875997884, "grad_norm": 6.851591110229492, "learning_rate": 9.04928907698892e-06, "loss": 0.7036, "step": 76120 }, { "epoch": 0.4525325296764568, "grad_norm": 6.191941261291504, "learning_rate": 9.05047791145561e-06, "loss": 0.6995, "step": 76130 }, { "epoch": 0.45259197175312516, "grad_norm": 6.857656478881836, "learning_rate": 9.051666745922298e-06, "loss": 0.617, "step": 76140 }, { "epoch": 0.45265141382979357, "grad_norm": 6.497076511383057, "learning_rate": 9.052855580388988e-06, "loss": 0.6626, "step": 76150 }, { "epoch": 0.45271085590646193, "grad_norm": 6.825998306274414, "learning_rate": 9.054044414855676e-06, "loss": 0.7056, "step": 76160 }, { "epoch": 0.45277029798313034, "grad_norm": 5.033896446228027, "learning_rate": 9.055233249322365e-06, "loss": 0.6209, "step": 76170 }, { "epoch": 0.4528297400597987, "grad_norm": 6.702474117279053, "learning_rate": 9.056422083789054e-06, "loss": 0.6449, "step": 76180 }, { "epoch": 0.4528891821364671, "grad_norm": 5.424020767211914, "learning_rate": 9.057610918255743e-06, "loss": 0.6275, "step": 76190 }, { "epoch": 0.45294862421313553, "grad_norm": 6.815247058868408, "learning_rate": 9.058799752722431e-06, "loss": 0.686, "step": 76200 }, { "epoch": 0.4530080662898039, "grad_norm": 6.21303653717041, "learning_rate": 9.05998858718912e-06, "loss": 0.6406, "step": 76210 }, { "epoch": 0.4530675083664723, "grad_norm": 6.210756778717041, "learning_rate": 9.06117742165581e-06, "loss": 0.658, "step": 76220 }, { "epoch": 0.45312695044314066, "grad_norm": 6.078588008880615, "learning_rate": 9.062366256122497e-06, "loss": 0.6311, "step": 76230 }, { "epoch": 0.4531863925198091, "grad_norm": 5.562142848968506, "learning_rate": 9.063555090589187e-06, "loss": 0.6773, "step": 76240 }, { "epoch": 0.45324583459647744, "grad_norm": 6.4312944412231445, "learning_rate": 9.064743925055875e-06, "loss": 0.6594, "step": 76250 }, { "epoch": 0.45330527667314585, "grad_norm": 6.66578483581543, "learning_rate": 9.065932759522565e-06, "loss": 0.606, "step": 76260 }, { "epoch": 0.45336471874981427, "grad_norm": 7.644845485687256, "learning_rate": 9.067121593989253e-06, "loss": 0.6971, "step": 76270 }, { "epoch": 0.4534241608264826, "grad_norm": 6.229249477386475, "learning_rate": 9.068310428455943e-06, "loss": 0.6472, "step": 76280 }, { "epoch": 0.45348360290315104, "grad_norm": 7.367645263671875, "learning_rate": 9.069499262922633e-06, "loss": 0.7028, "step": 76290 }, { "epoch": 0.4535430449798194, "grad_norm": 7.051235675811768, "learning_rate": 9.07068809738932e-06, "loss": 0.6801, "step": 76300 }, { "epoch": 0.4536024870564878, "grad_norm": 7.18280029296875, "learning_rate": 9.07187693185601e-06, "loss": 0.6501, "step": 76310 }, { "epoch": 0.45366192913315617, "grad_norm": 5.625842094421387, "learning_rate": 9.073065766322698e-06, "loss": 0.6611, "step": 76320 }, { "epoch": 0.4537213712098246, "grad_norm": 6.557631492614746, "learning_rate": 9.074254600789387e-06, "loss": 0.6056, "step": 76330 }, { "epoch": 0.453780813286493, "grad_norm": 7.248301982879639, "learning_rate": 9.075443435256076e-06, "loss": 0.6418, "step": 76340 }, { "epoch": 0.45384025536316136, "grad_norm": 7.719903945922852, "learning_rate": 9.076632269722764e-06, "loss": 0.6474, "step": 76350 }, { "epoch": 0.4538996974398298, "grad_norm": 6.585725784301758, "learning_rate": 9.077821104189454e-06, "loss": 0.6804, "step": 76360 }, { "epoch": 0.45395913951649813, "grad_norm": 7.473418712615967, "learning_rate": 9.079009938656142e-06, "loss": 0.6515, "step": 76370 }, { "epoch": 0.45401858159316655, "grad_norm": 6.550360202789307, "learning_rate": 9.080198773122832e-06, "loss": 0.6912, "step": 76380 }, { "epoch": 0.4540780236698349, "grad_norm": 5.551916599273682, "learning_rate": 9.08138760758952e-06, "loss": 0.7215, "step": 76390 }, { "epoch": 0.4541374657465033, "grad_norm": 7.080807209014893, "learning_rate": 9.082576442056208e-06, "loss": 0.6349, "step": 76400 }, { "epoch": 0.45419690782317174, "grad_norm": 5.141012191772461, "learning_rate": 9.083765276522898e-06, "loss": 0.6219, "step": 76410 }, { "epoch": 0.4542563498998401, "grad_norm": 7.843348503112793, "learning_rate": 9.084954110989586e-06, "loss": 0.7139, "step": 76420 }, { "epoch": 0.4543157919765085, "grad_norm": 7.243085861206055, "learning_rate": 9.086142945456276e-06, "loss": 0.6117, "step": 76430 }, { "epoch": 0.45437523405317687, "grad_norm": 6.067996501922607, "learning_rate": 9.087331779922964e-06, "loss": 0.7225, "step": 76440 }, { "epoch": 0.4544346761298453, "grad_norm": 6.745630264282227, "learning_rate": 9.088520614389654e-06, "loss": 0.6414, "step": 76450 }, { "epoch": 0.45449411820651364, "grad_norm": 5.875047206878662, "learning_rate": 9.089709448856342e-06, "loss": 0.6461, "step": 76460 }, { "epoch": 0.45455356028318206, "grad_norm": 6.572959899902344, "learning_rate": 9.090898283323032e-06, "loss": 0.6747, "step": 76470 }, { "epoch": 0.45461300235985047, "grad_norm": 5.415676116943359, "learning_rate": 9.09208711778972e-06, "loss": 0.6254, "step": 76480 }, { "epoch": 0.45467244443651883, "grad_norm": 5.987212181091309, "learning_rate": 9.093275952256408e-06, "loss": 0.7084, "step": 76490 }, { "epoch": 0.45473188651318724, "grad_norm": 6.088192939758301, "learning_rate": 9.094464786723097e-06, "loss": 0.6967, "step": 76500 }, { "epoch": 0.4547913285898556, "grad_norm": 4.551311016082764, "learning_rate": 9.095653621189786e-06, "loss": 0.6112, "step": 76510 }, { "epoch": 0.454850770666524, "grad_norm": 6.3519978523254395, "learning_rate": 9.096842455656475e-06, "loss": 0.7137, "step": 76520 }, { "epoch": 0.4549102127431924, "grad_norm": 5.6008076667785645, "learning_rate": 9.098031290123163e-06, "loss": 0.6175, "step": 76530 }, { "epoch": 0.4549696548198608, "grad_norm": 7.102921009063721, "learning_rate": 9.099220124589853e-06, "loss": 0.6766, "step": 76540 }, { "epoch": 0.45502909689652915, "grad_norm": 5.678130149841309, "learning_rate": 9.100408959056541e-06, "loss": 0.6751, "step": 76550 }, { "epoch": 0.45508853897319756, "grad_norm": 5.486498832702637, "learning_rate": 9.101597793523231e-06, "loss": 0.6296, "step": 76560 }, { "epoch": 0.455147981049866, "grad_norm": 5.589200019836426, "learning_rate": 9.102786627989919e-06, "loss": 0.6016, "step": 76570 }, { "epoch": 0.45520742312653434, "grad_norm": 7.534696578979492, "learning_rate": 9.103975462456607e-06, "loss": 0.7081, "step": 76580 }, { "epoch": 0.45526686520320275, "grad_norm": 6.410637855529785, "learning_rate": 9.105164296923297e-06, "loss": 0.6276, "step": 76590 }, { "epoch": 0.4553263072798711, "grad_norm": 8.42332649230957, "learning_rate": 9.106353131389985e-06, "loss": 0.627, "step": 76600 }, { "epoch": 0.4553857493565395, "grad_norm": 6.768967628479004, "learning_rate": 9.107541965856675e-06, "loss": 0.6927, "step": 76610 }, { "epoch": 0.4554451914332079, "grad_norm": 8.467917442321777, "learning_rate": 9.108730800323363e-06, "loss": 0.6591, "step": 76620 }, { "epoch": 0.4555046335098763, "grad_norm": 6.105226993560791, "learning_rate": 9.109919634790053e-06, "loss": 0.6594, "step": 76630 }, { "epoch": 0.4555640755865447, "grad_norm": 5.906549453735352, "learning_rate": 9.111108469256742e-06, "loss": 0.6152, "step": 76640 }, { "epoch": 0.4556235176632131, "grad_norm": 6.230103969573975, "learning_rate": 9.11229730372343e-06, "loss": 0.638, "step": 76650 }, { "epoch": 0.4556829597398815, "grad_norm": 6.815834045410156, "learning_rate": 9.11348613819012e-06, "loss": 0.6506, "step": 76660 }, { "epoch": 0.45574240181654985, "grad_norm": 5.716736316680908, "learning_rate": 9.114674972656808e-06, "loss": 0.6482, "step": 76670 }, { "epoch": 0.45580184389321826, "grad_norm": 6.899417400360107, "learning_rate": 9.115863807123496e-06, "loss": 0.6568, "step": 76680 }, { "epoch": 0.4558612859698866, "grad_norm": 6.020744800567627, "learning_rate": 9.117052641590186e-06, "loss": 0.6864, "step": 76690 }, { "epoch": 0.45592072804655503, "grad_norm": 6.582108974456787, "learning_rate": 9.118241476056874e-06, "loss": 0.6297, "step": 76700 }, { "epoch": 0.45598017012322345, "grad_norm": 6.919405460357666, "learning_rate": 9.119430310523564e-06, "loss": 0.7086, "step": 76710 }, { "epoch": 0.4560396121998918, "grad_norm": 5.877347946166992, "learning_rate": 9.120619144990252e-06, "loss": 0.596, "step": 76720 }, { "epoch": 0.4560990542765602, "grad_norm": 7.688486576080322, "learning_rate": 9.121807979456942e-06, "loss": 0.6994, "step": 76730 }, { "epoch": 0.4561584963532286, "grad_norm": 5.421590805053711, "learning_rate": 9.12299681392363e-06, "loss": 0.6414, "step": 76740 }, { "epoch": 0.456217938429897, "grad_norm": 6.129435062408447, "learning_rate": 9.12418564839032e-06, "loss": 0.6353, "step": 76750 }, { "epoch": 0.45627738050656536, "grad_norm": 5.637160778045654, "learning_rate": 9.125374482857008e-06, "loss": 0.6337, "step": 76760 }, { "epoch": 0.45633682258323377, "grad_norm": 8.653487205505371, "learning_rate": 9.126563317323696e-06, "loss": 0.6559, "step": 76770 }, { "epoch": 0.4563962646599022, "grad_norm": 5.178403854370117, "learning_rate": 9.127752151790386e-06, "loss": 0.5901, "step": 76780 }, { "epoch": 0.45645570673657054, "grad_norm": 6.259398937225342, "learning_rate": 9.128940986257074e-06, "loss": 0.6753, "step": 76790 }, { "epoch": 0.45651514881323896, "grad_norm": 7.020312786102295, "learning_rate": 9.130129820723764e-06, "loss": 0.5959, "step": 76800 }, { "epoch": 0.4565745908899073, "grad_norm": 6.642989635467529, "learning_rate": 9.131318655190452e-06, "loss": 0.6556, "step": 76810 }, { "epoch": 0.45663403296657573, "grad_norm": 5.330639839172363, "learning_rate": 9.132507489657141e-06, "loss": 0.7433, "step": 76820 }, { "epoch": 0.4566934750432441, "grad_norm": 6.631131649017334, "learning_rate": 9.13369632412383e-06, "loss": 0.6998, "step": 76830 }, { "epoch": 0.4567529171199125, "grad_norm": 5.015929222106934, "learning_rate": 9.13488515859052e-06, "loss": 0.6571, "step": 76840 }, { "epoch": 0.4568123591965809, "grad_norm": 6.437453746795654, "learning_rate": 9.136073993057207e-06, "loss": 0.6463, "step": 76850 }, { "epoch": 0.4568718012732493, "grad_norm": 7.338480472564697, "learning_rate": 9.137262827523895e-06, "loss": 0.5975, "step": 76860 }, { "epoch": 0.4569312433499177, "grad_norm": 6.558801174163818, "learning_rate": 9.138451661990585e-06, "loss": 0.7008, "step": 76870 }, { "epoch": 0.45699068542658605, "grad_norm": 5.811878681182861, "learning_rate": 9.139640496457273e-06, "loss": 0.6483, "step": 76880 }, { "epoch": 0.45705012750325447, "grad_norm": 7.9664692878723145, "learning_rate": 9.140829330923963e-06, "loss": 0.7335, "step": 76890 }, { "epoch": 0.4571095695799228, "grad_norm": 6.155126094818115, "learning_rate": 9.142018165390651e-06, "loss": 0.6242, "step": 76900 }, { "epoch": 0.45716901165659124, "grad_norm": 5.834628582000732, "learning_rate": 9.143206999857341e-06, "loss": 0.6416, "step": 76910 }, { "epoch": 0.4572284537332596, "grad_norm": 6.722159385681152, "learning_rate": 9.144395834324029e-06, "loss": 0.666, "step": 76920 }, { "epoch": 0.457287895809928, "grad_norm": 7.852204322814941, "learning_rate": 9.145584668790717e-06, "loss": 0.672, "step": 76930 }, { "epoch": 0.45734733788659643, "grad_norm": 6.8362250328063965, "learning_rate": 9.146773503257407e-06, "loss": 0.6787, "step": 76940 }, { "epoch": 0.4574067799632648, "grad_norm": 8.059475898742676, "learning_rate": 9.147962337724095e-06, "loss": 0.7075, "step": 76950 }, { "epoch": 0.4574662220399332, "grad_norm": 7.721909523010254, "learning_rate": 9.149151172190785e-06, "loss": 0.6344, "step": 76960 }, { "epoch": 0.45752566411660156, "grad_norm": 6.741988182067871, "learning_rate": 9.150340006657473e-06, "loss": 0.7382, "step": 76970 }, { "epoch": 0.45758510619327, "grad_norm": 6.097555637359619, "learning_rate": 9.151528841124163e-06, "loss": 0.6926, "step": 76980 }, { "epoch": 0.45764454826993833, "grad_norm": 5.796341419219971, "learning_rate": 9.152717675590852e-06, "loss": 0.7266, "step": 76990 }, { "epoch": 0.45770399034660675, "grad_norm": 6.228029727935791, "learning_rate": 9.15390651005754e-06, "loss": 0.6369, "step": 77000 }, { "epoch": 0.45776343242327516, "grad_norm": 7.349531173706055, "learning_rate": 9.15509534452423e-06, "loss": 0.7036, "step": 77010 }, { "epoch": 0.4578228744999435, "grad_norm": 5.441590785980225, "learning_rate": 9.156284178990918e-06, "loss": 0.6391, "step": 77020 }, { "epoch": 0.45788231657661194, "grad_norm": 7.937963485717773, "learning_rate": 9.157473013457608e-06, "loss": 0.646, "step": 77030 }, { "epoch": 0.4579417586532803, "grad_norm": 6.551909923553467, "learning_rate": 9.158661847924296e-06, "loss": 0.6637, "step": 77040 }, { "epoch": 0.4580012007299487, "grad_norm": 5.709066390991211, "learning_rate": 9.159850682390984e-06, "loss": 0.6379, "step": 77050 }, { "epoch": 0.45806064280661707, "grad_norm": 8.169622421264648, "learning_rate": 9.161039516857674e-06, "loss": 0.7277, "step": 77060 }, { "epoch": 0.4581200848832855, "grad_norm": 4.721119403839111, "learning_rate": 9.162228351324362e-06, "loss": 0.6546, "step": 77070 }, { "epoch": 0.4581795269599539, "grad_norm": 6.966242790222168, "learning_rate": 9.163417185791052e-06, "loss": 0.6737, "step": 77080 }, { "epoch": 0.45823896903662226, "grad_norm": 6.424386024475098, "learning_rate": 9.16460602025774e-06, "loss": 0.7036, "step": 77090 }, { "epoch": 0.45829841111329067, "grad_norm": 4.6261372566223145, "learning_rate": 9.16579485472443e-06, "loss": 0.6591, "step": 77100 }, { "epoch": 0.45835785318995903, "grad_norm": 6.993212699890137, "learning_rate": 9.166983689191118e-06, "loss": 0.6376, "step": 77110 }, { "epoch": 0.45841729526662744, "grad_norm": 5.449942588806152, "learning_rate": 9.168172523657806e-06, "loss": 0.6956, "step": 77120 }, { "epoch": 0.4584767373432958, "grad_norm": 6.9910688400268555, "learning_rate": 9.169361358124496e-06, "loss": 0.6482, "step": 77130 }, { "epoch": 0.4585361794199642, "grad_norm": 6.323582649230957, "learning_rate": 9.170550192591184e-06, "loss": 0.6452, "step": 77140 }, { "epoch": 0.45859562149663263, "grad_norm": 7.77969217300415, "learning_rate": 9.171739027057874e-06, "loss": 0.7485, "step": 77150 }, { "epoch": 0.458655063573301, "grad_norm": 5.254807472229004, "learning_rate": 9.172927861524562e-06, "loss": 0.6851, "step": 77160 }, { "epoch": 0.4587145056499694, "grad_norm": 6.582294940948486, "learning_rate": 9.174116695991251e-06, "loss": 0.6481, "step": 77170 }, { "epoch": 0.45877394772663777, "grad_norm": 6.760571002960205, "learning_rate": 9.17530553045794e-06, "loss": 0.6828, "step": 77180 }, { "epoch": 0.4588333898033062, "grad_norm": 9.499313354492188, "learning_rate": 9.17649436492463e-06, "loss": 0.666, "step": 77190 }, { "epoch": 0.45889283187997454, "grad_norm": 7.593170166015625, "learning_rate": 9.177683199391317e-06, "loss": 0.6959, "step": 77200 }, { "epoch": 0.45895227395664295, "grad_norm": 5.877760410308838, "learning_rate": 9.178872033858005e-06, "loss": 0.6685, "step": 77210 }, { "epoch": 0.4590117160333113, "grad_norm": 7.262501239776611, "learning_rate": 9.180060868324695e-06, "loss": 0.6777, "step": 77220 }, { "epoch": 0.4590711581099797, "grad_norm": 6.057307720184326, "learning_rate": 9.181249702791383e-06, "loss": 0.6575, "step": 77230 }, { "epoch": 0.45913060018664814, "grad_norm": 7.3607869148254395, "learning_rate": 9.182438537258073e-06, "loss": 0.6342, "step": 77240 }, { "epoch": 0.4591900422633165, "grad_norm": 8.037813186645508, "learning_rate": 9.183627371724761e-06, "loss": 0.6646, "step": 77250 }, { "epoch": 0.4592494843399849, "grad_norm": 5.232204914093018, "learning_rate": 9.184816206191451e-06, "loss": 0.5893, "step": 77260 }, { "epoch": 0.4593089264166533, "grad_norm": 6.153507232666016, "learning_rate": 9.186005040658139e-06, "loss": 0.6929, "step": 77270 }, { "epoch": 0.4593683684933217, "grad_norm": 5.801969528198242, "learning_rate": 9.187193875124829e-06, "loss": 0.6792, "step": 77280 }, { "epoch": 0.45942781056999005, "grad_norm": 6.649779796600342, "learning_rate": 9.188382709591517e-06, "loss": 0.622, "step": 77290 }, { "epoch": 0.45948725264665846, "grad_norm": 6.669031620025635, "learning_rate": 9.189571544058205e-06, "loss": 0.7502, "step": 77300 }, { "epoch": 0.4595466947233269, "grad_norm": 7.9026780128479, "learning_rate": 9.190760378524895e-06, "loss": 0.6818, "step": 77310 }, { "epoch": 0.45960613679999524, "grad_norm": 6.715615749359131, "learning_rate": 9.191949212991583e-06, "loss": 0.6454, "step": 77320 }, { "epoch": 0.45966557887666365, "grad_norm": 7.486239433288574, "learning_rate": 9.193138047458273e-06, "loss": 0.7103, "step": 77330 }, { "epoch": 0.459725020953332, "grad_norm": 5.8479084968566895, "learning_rate": 9.194326881924962e-06, "loss": 0.6616, "step": 77340 }, { "epoch": 0.4597844630300004, "grad_norm": 6.1584696769714355, "learning_rate": 9.19551571639165e-06, "loss": 0.6254, "step": 77350 }, { "epoch": 0.4598439051066688, "grad_norm": 6.592458724975586, "learning_rate": 9.19670455085834e-06, "loss": 0.6145, "step": 77360 }, { "epoch": 0.4599033471833372, "grad_norm": 6.83198881149292, "learning_rate": 9.197893385325028e-06, "loss": 0.6663, "step": 77370 }, { "epoch": 0.4599627892600056, "grad_norm": 6.889009475708008, "learning_rate": 9.199082219791718e-06, "loss": 0.6192, "step": 77380 }, { "epoch": 0.46002223133667397, "grad_norm": 5.6371750831604, "learning_rate": 9.200271054258406e-06, "loss": 0.644, "step": 77390 }, { "epoch": 0.4600816734133424, "grad_norm": 8.8798828125, "learning_rate": 9.201459888725094e-06, "loss": 0.6609, "step": 77400 }, { "epoch": 0.46014111549001074, "grad_norm": 6.121500492095947, "learning_rate": 9.202648723191784e-06, "loss": 0.6347, "step": 77410 }, { "epoch": 0.46020055756667916, "grad_norm": 6.018222332000732, "learning_rate": 9.203837557658472e-06, "loss": 0.6385, "step": 77420 }, { "epoch": 0.4602599996433475, "grad_norm": 6.924169540405273, "learning_rate": 9.205026392125162e-06, "loss": 0.7103, "step": 77430 }, { "epoch": 0.46031944172001593, "grad_norm": 6.349998474121094, "learning_rate": 9.20621522659185e-06, "loss": 0.6672, "step": 77440 }, { "epoch": 0.46037888379668435, "grad_norm": 6.065174102783203, "learning_rate": 9.20740406105854e-06, "loss": 0.6642, "step": 77450 }, { "epoch": 0.4604383258733527, "grad_norm": 6.371179580688477, "learning_rate": 9.208592895525228e-06, "loss": 0.6463, "step": 77460 }, { "epoch": 0.4604977679500211, "grad_norm": 6.714743137359619, "learning_rate": 9.209781729991918e-06, "loss": 0.6835, "step": 77470 }, { "epoch": 0.4605572100266895, "grad_norm": 9.981566429138184, "learning_rate": 9.210970564458606e-06, "loss": 0.7, "step": 77480 }, { "epoch": 0.4606166521033579, "grad_norm": 6.418209552764893, "learning_rate": 9.212159398925294e-06, "loss": 0.7079, "step": 77490 }, { "epoch": 0.46067609418002625, "grad_norm": 7.920497417449951, "learning_rate": 9.213348233391983e-06, "loss": 0.6567, "step": 77500 }, { "epoch": 0.46073553625669467, "grad_norm": 5.804906845092773, "learning_rate": 9.214537067858672e-06, "loss": 0.6692, "step": 77510 }, { "epoch": 0.4607949783333631, "grad_norm": 6.263747692108154, "learning_rate": 9.215725902325361e-06, "loss": 0.7348, "step": 77520 }, { "epoch": 0.46085442041003144, "grad_norm": 7.182906150817871, "learning_rate": 9.21691473679205e-06, "loss": 0.6646, "step": 77530 }, { "epoch": 0.46091386248669985, "grad_norm": 6.926245212554932, "learning_rate": 9.21810357125874e-06, "loss": 0.6963, "step": 77540 }, { "epoch": 0.4609733045633682, "grad_norm": 6.3727707862854, "learning_rate": 9.219292405725427e-06, "loss": 0.6397, "step": 77550 }, { "epoch": 0.46103274664003663, "grad_norm": 7.886233806610107, "learning_rate": 9.220481240192117e-06, "loss": 0.686, "step": 77560 }, { "epoch": 0.461092188716705, "grad_norm": 6.096900939941406, "learning_rate": 9.221670074658805e-06, "loss": 0.6158, "step": 77570 }, { "epoch": 0.4611516307933734, "grad_norm": 5.069120407104492, "learning_rate": 9.222858909125493e-06, "loss": 0.6351, "step": 77580 }, { "epoch": 0.46121107287004176, "grad_norm": 7.597465991973877, "learning_rate": 9.224047743592183e-06, "loss": 0.7169, "step": 77590 }, { "epoch": 0.4612705149467102, "grad_norm": 7.087285995483398, "learning_rate": 9.225236578058871e-06, "loss": 0.6699, "step": 77600 }, { "epoch": 0.4613299570233786, "grad_norm": 5.478869438171387, "learning_rate": 9.22642541252556e-06, "loss": 0.6184, "step": 77610 }, { "epoch": 0.46138939910004695, "grad_norm": 5.74464750289917, "learning_rate": 9.227614246992249e-06, "loss": 0.6753, "step": 77620 }, { "epoch": 0.46144884117671536, "grad_norm": 6.802388668060303, "learning_rate": 9.228803081458939e-06, "loss": 0.6109, "step": 77630 }, { "epoch": 0.4615082832533837, "grad_norm": 7.112473487854004, "learning_rate": 9.229991915925627e-06, "loss": 0.7012, "step": 77640 }, { "epoch": 0.46156772533005214, "grad_norm": 7.307410717010498, "learning_rate": 9.231180750392315e-06, "loss": 0.7668, "step": 77650 }, { "epoch": 0.4616271674067205, "grad_norm": 5.329954624176025, "learning_rate": 9.232369584859005e-06, "loss": 0.6611, "step": 77660 }, { "epoch": 0.4616866094833889, "grad_norm": 6.959246635437012, "learning_rate": 9.233558419325693e-06, "loss": 0.659, "step": 77670 }, { "epoch": 0.4617460515600573, "grad_norm": 7.159523010253906, "learning_rate": 9.234747253792382e-06, "loss": 0.6679, "step": 77680 }, { "epoch": 0.4618054936367257, "grad_norm": 6.267401695251465, "learning_rate": 9.235936088259072e-06, "loss": 0.6786, "step": 77690 }, { "epoch": 0.4618649357133941, "grad_norm": 5.524451732635498, "learning_rate": 9.23712492272576e-06, "loss": 0.6297, "step": 77700 }, { "epoch": 0.46192437779006246, "grad_norm": 5.074220657348633, "learning_rate": 9.23831375719245e-06, "loss": 0.7305, "step": 77710 }, { "epoch": 0.46198381986673087, "grad_norm": 5.564805030822754, "learning_rate": 9.239502591659138e-06, "loss": 0.6463, "step": 77720 }, { "epoch": 0.46204326194339923, "grad_norm": 6.275689601898193, "learning_rate": 9.240691426125828e-06, "loss": 0.735, "step": 77730 }, { "epoch": 0.46210270402006765, "grad_norm": 5.947780609130859, "learning_rate": 9.241880260592516e-06, "loss": 0.6779, "step": 77740 }, { "epoch": 0.46216214609673606, "grad_norm": 8.172407150268555, "learning_rate": 9.243069095059206e-06, "loss": 0.6633, "step": 77750 }, { "epoch": 0.4622215881734044, "grad_norm": 7.43377685546875, "learning_rate": 9.244257929525894e-06, "loss": 0.6196, "step": 77760 }, { "epoch": 0.46228103025007283, "grad_norm": 6.50416898727417, "learning_rate": 9.245446763992582e-06, "loss": 0.6688, "step": 77770 }, { "epoch": 0.4623404723267412, "grad_norm": 5.183718204498291, "learning_rate": 9.246635598459272e-06, "loss": 0.6454, "step": 77780 }, { "epoch": 0.4623999144034096, "grad_norm": 7.869822025299072, "learning_rate": 9.24782443292596e-06, "loss": 0.6837, "step": 77790 }, { "epoch": 0.46245935648007797, "grad_norm": 8.155889511108398, "learning_rate": 9.24901326739265e-06, "loss": 0.7035, "step": 77800 }, { "epoch": 0.4625187985567464, "grad_norm": 6.022740840911865, "learning_rate": 9.250202101859338e-06, "loss": 0.6566, "step": 77810 }, { "epoch": 0.4625782406334148, "grad_norm": 6.485979080200195, "learning_rate": 9.251390936326027e-06, "loss": 0.6535, "step": 77820 }, { "epoch": 0.46263768271008315, "grad_norm": 6.104022979736328, "learning_rate": 9.252579770792716e-06, "loss": 0.6378, "step": 77830 }, { "epoch": 0.46269712478675157, "grad_norm": 7.122978687286377, "learning_rate": 9.253768605259405e-06, "loss": 0.6586, "step": 77840 }, { "epoch": 0.4627565668634199, "grad_norm": 5.667379379272461, "learning_rate": 9.254957439726093e-06, "loss": 0.6476, "step": 77850 }, { "epoch": 0.46281600894008834, "grad_norm": 7.421945571899414, "learning_rate": 9.256146274192781e-06, "loss": 0.5984, "step": 77860 }, { "epoch": 0.4628754510167567, "grad_norm": 5.822820663452148, "learning_rate": 9.257335108659471e-06, "loss": 0.6462, "step": 77870 }, { "epoch": 0.4629348930934251, "grad_norm": 6.204785346984863, "learning_rate": 9.25852394312616e-06, "loss": 0.6493, "step": 77880 }, { "epoch": 0.46299433517009353, "grad_norm": 7.445077419281006, "learning_rate": 9.259712777592849e-06, "loss": 0.6247, "step": 77890 }, { "epoch": 0.4630537772467619, "grad_norm": 6.165831089019775, "learning_rate": 9.260901612059537e-06, "loss": 0.6916, "step": 77900 }, { "epoch": 0.4631132193234303, "grad_norm": 5.393557548522949, "learning_rate": 9.262090446526227e-06, "loss": 0.6877, "step": 77910 }, { "epoch": 0.46317266140009866, "grad_norm": 8.80803394317627, "learning_rate": 9.263279280992915e-06, "loss": 0.6963, "step": 77920 }, { "epoch": 0.4632321034767671, "grad_norm": 6.012783050537109, "learning_rate": 9.264468115459603e-06, "loss": 0.6773, "step": 77930 }, { "epoch": 0.46329154555343544, "grad_norm": 7.546211242675781, "learning_rate": 9.265656949926293e-06, "loss": 0.658, "step": 77940 }, { "epoch": 0.46335098763010385, "grad_norm": 5.614367485046387, "learning_rate": 9.266845784392981e-06, "loss": 0.6265, "step": 77950 }, { "epoch": 0.4634104297067722, "grad_norm": 4.269496440887451, "learning_rate": 9.26803461885967e-06, "loss": 0.5945, "step": 77960 }, { "epoch": 0.4634698717834406, "grad_norm": 7.238442420959473, "learning_rate": 9.269223453326359e-06, "loss": 0.7414, "step": 77970 }, { "epoch": 0.46352931386010904, "grad_norm": 6.120416641235352, "learning_rate": 9.270412287793049e-06, "loss": 0.6218, "step": 77980 }, { "epoch": 0.4635887559367774, "grad_norm": 6.692828178405762, "learning_rate": 9.271601122259737e-06, "loss": 0.6543, "step": 77990 }, { "epoch": 0.4636481980134458, "grad_norm": 5.803424835205078, "learning_rate": 9.272789956726426e-06, "loss": 0.6692, "step": 78000 }, { "epoch": 0.46370764009011417, "grad_norm": 5.9618635177612305, "learning_rate": 9.273978791193115e-06, "loss": 0.6164, "step": 78010 }, { "epoch": 0.4637670821667826, "grad_norm": 6.047726154327393, "learning_rate": 9.275167625659804e-06, "loss": 0.7631, "step": 78020 }, { "epoch": 0.46382652424345094, "grad_norm": 6.296925067901611, "learning_rate": 9.276356460126494e-06, "loss": 0.6957, "step": 78030 }, { "epoch": 0.46388596632011936, "grad_norm": 6.801367282867432, "learning_rate": 9.277545294593182e-06, "loss": 0.6033, "step": 78040 }, { "epoch": 0.4639454083967878, "grad_norm": 6.695398330688477, "learning_rate": 9.27873412905987e-06, "loss": 0.6461, "step": 78050 }, { "epoch": 0.46400485047345613, "grad_norm": 7.248834609985352, "learning_rate": 9.27992296352656e-06, "loss": 0.7269, "step": 78060 }, { "epoch": 0.46406429255012455, "grad_norm": 7.043853759765625, "learning_rate": 9.281111797993248e-06, "loss": 0.6643, "step": 78070 }, { "epoch": 0.4641237346267929, "grad_norm": 5.8363823890686035, "learning_rate": 9.282300632459938e-06, "loss": 0.6563, "step": 78080 }, { "epoch": 0.4641831767034613, "grad_norm": 6.116473197937012, "learning_rate": 9.283489466926626e-06, "loss": 0.6546, "step": 78090 }, { "epoch": 0.4642426187801297, "grad_norm": 6.3532795906066895, "learning_rate": 9.284678301393316e-06, "loss": 0.7217, "step": 78100 }, { "epoch": 0.4643020608567981, "grad_norm": 7.797634601593018, "learning_rate": 9.285867135860004e-06, "loss": 0.7392, "step": 78110 }, { "epoch": 0.4643615029334665, "grad_norm": 5.875141620635986, "learning_rate": 9.287055970326692e-06, "loss": 0.6072, "step": 78120 }, { "epoch": 0.46442094501013487, "grad_norm": 6.056731700897217, "learning_rate": 9.288244804793382e-06, "loss": 0.6536, "step": 78130 }, { "epoch": 0.4644803870868033, "grad_norm": 6.662208080291748, "learning_rate": 9.28943363926007e-06, "loss": 0.6567, "step": 78140 }, { "epoch": 0.46453982916347164, "grad_norm": 6.053958415985107, "learning_rate": 9.29062247372676e-06, "loss": 0.6462, "step": 78150 }, { "epoch": 0.46459927124014005, "grad_norm": 5.062098026275635, "learning_rate": 9.291811308193448e-06, "loss": 0.6498, "step": 78160 }, { "epoch": 0.4646587133168084, "grad_norm": 7.540463447570801, "learning_rate": 9.293000142660137e-06, "loss": 0.6137, "step": 78170 }, { "epoch": 0.46471815539347683, "grad_norm": 7.189377307891846, "learning_rate": 9.294188977126825e-06, "loss": 0.6447, "step": 78180 }, { "epoch": 0.46477759747014524, "grad_norm": 6.463738441467285, "learning_rate": 9.295377811593515e-06, "loss": 0.6907, "step": 78190 }, { "epoch": 0.4648370395468136, "grad_norm": 8.243762969970703, "learning_rate": 9.296566646060203e-06, "loss": 0.7103, "step": 78200 }, { "epoch": 0.464896481623482, "grad_norm": 7.667708396911621, "learning_rate": 9.297755480526891e-06, "loss": 0.7002, "step": 78210 }, { "epoch": 0.4649559237001504, "grad_norm": 6.6860151290893555, "learning_rate": 9.298944314993581e-06, "loss": 0.7087, "step": 78220 }, { "epoch": 0.4650153657768188, "grad_norm": 6.347833633422852, "learning_rate": 9.30013314946027e-06, "loss": 0.648, "step": 78230 }, { "epoch": 0.46507480785348715, "grad_norm": 6.112733364105225, "learning_rate": 9.301321983926959e-06, "loss": 0.6962, "step": 78240 }, { "epoch": 0.46513424993015556, "grad_norm": 7.307295322418213, "learning_rate": 9.302510818393647e-06, "loss": 0.702, "step": 78250 }, { "epoch": 0.465193692006824, "grad_norm": 6.337612628936768, "learning_rate": 9.303699652860337e-06, "loss": 0.7018, "step": 78260 }, { "epoch": 0.46525313408349234, "grad_norm": 5.78258752822876, "learning_rate": 9.304888487327025e-06, "loss": 0.7351, "step": 78270 }, { "epoch": 0.46531257616016075, "grad_norm": 10.968578338623047, "learning_rate": 9.306077321793715e-06, "loss": 0.659, "step": 78280 }, { "epoch": 0.4653720182368291, "grad_norm": 5.68865966796875, "learning_rate": 9.307266156260403e-06, "loss": 0.6555, "step": 78290 }, { "epoch": 0.4654314603134975, "grad_norm": 5.34506893157959, "learning_rate": 9.308454990727091e-06, "loss": 0.6888, "step": 78300 }, { "epoch": 0.4654909023901659, "grad_norm": 5.964168548583984, "learning_rate": 9.30964382519378e-06, "loss": 0.678, "step": 78310 }, { "epoch": 0.4655503444668343, "grad_norm": 4.835787773132324, "learning_rate": 9.310832659660469e-06, "loss": 0.6943, "step": 78320 }, { "epoch": 0.46560978654350266, "grad_norm": 6.286238193511963, "learning_rate": 9.312021494127158e-06, "loss": 0.6682, "step": 78330 }, { "epoch": 0.46566922862017107, "grad_norm": 5.587996959686279, "learning_rate": 9.313210328593847e-06, "loss": 0.6188, "step": 78340 }, { "epoch": 0.4657286706968395, "grad_norm": 6.021639823913574, "learning_rate": 9.314399163060536e-06, "loss": 0.6234, "step": 78350 }, { "epoch": 0.46578811277350785, "grad_norm": 6.223687171936035, "learning_rate": 9.315587997527224e-06, "loss": 0.6485, "step": 78360 }, { "epoch": 0.46584755485017626, "grad_norm": 7.242730617523193, "learning_rate": 9.316776831993914e-06, "loss": 0.6993, "step": 78370 }, { "epoch": 0.4659069969268446, "grad_norm": 8.189202308654785, "learning_rate": 9.317965666460604e-06, "loss": 0.6779, "step": 78380 }, { "epoch": 0.46596643900351303, "grad_norm": 7.38387393951416, "learning_rate": 9.319154500927292e-06, "loss": 0.6407, "step": 78390 }, { "epoch": 0.4660258810801814, "grad_norm": 7.661506652832031, "learning_rate": 9.32034333539398e-06, "loss": 0.6827, "step": 78400 }, { "epoch": 0.4660853231568498, "grad_norm": 6.6324238777160645, "learning_rate": 9.32153216986067e-06, "loss": 0.6891, "step": 78410 }, { "epoch": 0.4661447652335182, "grad_norm": 6.318421840667725, "learning_rate": 9.322721004327358e-06, "loss": 0.6812, "step": 78420 }, { "epoch": 0.4662042073101866, "grad_norm": 6.29276180267334, "learning_rate": 9.323909838794048e-06, "loss": 0.6833, "step": 78430 }, { "epoch": 0.466263649386855, "grad_norm": 6.4586334228515625, "learning_rate": 9.325098673260736e-06, "loss": 0.6266, "step": 78440 }, { "epoch": 0.46632309146352335, "grad_norm": 5.58499002456665, "learning_rate": 9.326287507727426e-06, "loss": 0.6109, "step": 78450 }, { "epoch": 0.46638253354019177, "grad_norm": 6.103875160217285, "learning_rate": 9.327476342194114e-06, "loss": 0.7256, "step": 78460 }, { "epoch": 0.4664419756168601, "grad_norm": 6.638479709625244, "learning_rate": 9.328665176660803e-06, "loss": 0.6718, "step": 78470 }, { "epoch": 0.46650141769352854, "grad_norm": 7.6300740242004395, "learning_rate": 9.329854011127492e-06, "loss": 0.643, "step": 78480 }, { "epoch": 0.46656085977019696, "grad_norm": 7.832047462463379, "learning_rate": 9.33104284559418e-06, "loss": 0.6553, "step": 78490 }, { "epoch": 0.4666203018468653, "grad_norm": 6.152992248535156, "learning_rate": 9.33223168006087e-06, "loss": 0.6664, "step": 78500 }, { "epoch": 0.46667974392353373, "grad_norm": 5.958270072937012, "learning_rate": 9.333420514527557e-06, "loss": 0.6689, "step": 78510 }, { "epoch": 0.4667391860002021, "grad_norm": 6.979074001312256, "learning_rate": 9.334609348994247e-06, "loss": 0.682, "step": 78520 }, { "epoch": 0.4667986280768705, "grad_norm": 6.651379108428955, "learning_rate": 9.335798183460935e-06, "loss": 0.6922, "step": 78530 }, { "epoch": 0.46685807015353886, "grad_norm": 7.264256954193115, "learning_rate": 9.336987017927625e-06, "loss": 0.6742, "step": 78540 }, { "epoch": 0.4669175122302073, "grad_norm": 5.320949554443359, "learning_rate": 9.338175852394313e-06, "loss": 0.6395, "step": 78550 }, { "epoch": 0.4669769543068757, "grad_norm": 5.644838333129883, "learning_rate": 9.339364686861003e-06, "loss": 0.6292, "step": 78560 }, { "epoch": 0.46703639638354405, "grad_norm": 5.64687442779541, "learning_rate": 9.340553521327691e-06, "loss": 0.6767, "step": 78570 }, { "epoch": 0.46709583846021246, "grad_norm": 7.463013648986816, "learning_rate": 9.341742355794379e-06, "loss": 0.7011, "step": 78580 }, { "epoch": 0.4671552805368808, "grad_norm": 8.564202308654785, "learning_rate": 9.342931190261069e-06, "loss": 0.7354, "step": 78590 }, { "epoch": 0.46721472261354924, "grad_norm": 6.361778736114502, "learning_rate": 9.344120024727757e-06, "loss": 0.6706, "step": 78600 }, { "epoch": 0.4672741646902176, "grad_norm": 6.2866291999816895, "learning_rate": 9.345308859194447e-06, "loss": 0.6811, "step": 78610 }, { "epoch": 0.467333606766886, "grad_norm": 7.538201332092285, "learning_rate": 9.346497693661135e-06, "loss": 0.6399, "step": 78620 }, { "epoch": 0.4673930488435544, "grad_norm": 8.199175834655762, "learning_rate": 9.347686528127825e-06, "loss": 0.6841, "step": 78630 }, { "epoch": 0.4674524909202228, "grad_norm": 7.018321990966797, "learning_rate": 9.348875362594513e-06, "loss": 0.6867, "step": 78640 }, { "epoch": 0.4675119329968912, "grad_norm": 6.660616874694824, "learning_rate": 9.3500641970612e-06, "loss": 0.7105, "step": 78650 }, { "epoch": 0.46757137507355956, "grad_norm": 6.950106143951416, "learning_rate": 9.35125303152789e-06, "loss": 0.6746, "step": 78660 }, { "epoch": 0.467630817150228, "grad_norm": 6.316814422607422, "learning_rate": 9.352441865994579e-06, "loss": 0.6443, "step": 78670 }, { "epoch": 0.46769025922689633, "grad_norm": 6.800322532653809, "learning_rate": 9.353630700461268e-06, "loss": 0.6974, "step": 78680 }, { "epoch": 0.46774970130356475, "grad_norm": 6.90787935256958, "learning_rate": 9.354819534927956e-06, "loss": 0.6212, "step": 78690 }, { "epoch": 0.4678091433802331, "grad_norm": 5.237826824188232, "learning_rate": 9.356008369394646e-06, "loss": 0.6157, "step": 78700 }, { "epoch": 0.4678685854569015, "grad_norm": 6.59812068939209, "learning_rate": 9.357197203861334e-06, "loss": 0.6601, "step": 78710 }, { "epoch": 0.46792802753356993, "grad_norm": 7.078827381134033, "learning_rate": 9.358386038328024e-06, "loss": 0.663, "step": 78720 }, { "epoch": 0.4679874696102383, "grad_norm": 3.996203660964966, "learning_rate": 9.359574872794714e-06, "loss": 0.6362, "step": 78730 }, { "epoch": 0.4680469116869067, "grad_norm": 5.24669075012207, "learning_rate": 9.360763707261402e-06, "loss": 0.6575, "step": 78740 }, { "epoch": 0.46810635376357507, "grad_norm": 7.769439697265625, "learning_rate": 9.361952541728092e-06, "loss": 0.6748, "step": 78750 }, { "epoch": 0.4681657958402435, "grad_norm": 6.680315017700195, "learning_rate": 9.36314137619478e-06, "loss": 0.681, "step": 78760 }, { "epoch": 0.46822523791691184, "grad_norm": 8.531156539916992, "learning_rate": 9.364330210661468e-06, "loss": 0.6479, "step": 78770 }, { "epoch": 0.46828467999358026, "grad_norm": 6.875247955322266, "learning_rate": 9.365519045128158e-06, "loss": 0.6369, "step": 78780 }, { "epoch": 0.46834412207024867, "grad_norm": 6.866582870483398, "learning_rate": 9.366707879594846e-06, "loss": 0.6287, "step": 78790 }, { "epoch": 0.46840356414691703, "grad_norm": 6.160236835479736, "learning_rate": 9.367896714061536e-06, "loss": 0.6959, "step": 78800 }, { "epoch": 0.46846300622358544, "grad_norm": 8.567934036254883, "learning_rate": 9.369085548528224e-06, "loss": 0.6566, "step": 78810 }, { "epoch": 0.4685224483002538, "grad_norm": 6.03765344619751, "learning_rate": 9.370274382994913e-06, "loss": 0.6037, "step": 78820 }, { "epoch": 0.4685818903769222, "grad_norm": 7.585249423980713, "learning_rate": 9.371463217461601e-06, "loss": 0.6715, "step": 78830 }, { "epoch": 0.4686413324535906, "grad_norm": 6.083920478820801, "learning_rate": 9.372652051928291e-06, "loss": 0.6569, "step": 78840 }, { "epoch": 0.468700774530259, "grad_norm": 7.829534530639648, "learning_rate": 9.37384088639498e-06, "loss": 0.7133, "step": 78850 }, { "epoch": 0.4687602166069274, "grad_norm": 5.814343452453613, "learning_rate": 9.375029720861667e-06, "loss": 0.6469, "step": 78860 }, { "epoch": 0.46881965868359576, "grad_norm": 7.610784530639648, "learning_rate": 9.376218555328357e-06, "loss": 0.6452, "step": 78870 }, { "epoch": 0.4688791007602642, "grad_norm": 6.481327056884766, "learning_rate": 9.377407389795045e-06, "loss": 0.6192, "step": 78880 }, { "epoch": 0.46893854283693254, "grad_norm": 9.174946784973145, "learning_rate": 9.378596224261735e-06, "loss": 0.7257, "step": 78890 }, { "epoch": 0.46899798491360095, "grad_norm": 5.882408618927002, "learning_rate": 9.379785058728423e-06, "loss": 0.6409, "step": 78900 }, { "epoch": 0.4690574269902693, "grad_norm": 7.658963680267334, "learning_rate": 9.380973893195113e-06, "loss": 0.6563, "step": 78910 }, { "epoch": 0.4691168690669377, "grad_norm": 5.9245452880859375, "learning_rate": 9.382162727661801e-06, "loss": 0.624, "step": 78920 }, { "epoch": 0.46917631114360614, "grad_norm": 4.566784858703613, "learning_rate": 9.383351562128489e-06, "loss": 0.6479, "step": 78930 }, { "epoch": 0.4692357532202745, "grad_norm": 7.965250015258789, "learning_rate": 9.384540396595179e-06, "loss": 0.6916, "step": 78940 }, { "epoch": 0.4692951952969429, "grad_norm": 7.8464813232421875, "learning_rate": 9.385729231061867e-06, "loss": 0.6785, "step": 78950 }, { "epoch": 0.46935463737361127, "grad_norm": 6.263859272003174, "learning_rate": 9.386918065528557e-06, "loss": 0.7135, "step": 78960 }, { "epoch": 0.4694140794502797, "grad_norm": 8.0955810546875, "learning_rate": 9.388106899995245e-06, "loss": 0.6517, "step": 78970 }, { "epoch": 0.46947352152694805, "grad_norm": 5.741605281829834, "learning_rate": 9.389295734461935e-06, "loss": 0.6313, "step": 78980 }, { "epoch": 0.46953296360361646, "grad_norm": 6.753697395324707, "learning_rate": 9.390484568928623e-06, "loss": 0.6899, "step": 78990 }, { "epoch": 0.4695924056802848, "grad_norm": 5.871591091156006, "learning_rate": 9.391673403395312e-06, "loss": 0.6684, "step": 79000 }, { "epoch": 0.46965184775695323, "grad_norm": 7.086082935333252, "learning_rate": 9.392862237862e-06, "loss": 0.622, "step": 79010 }, { "epoch": 0.46971128983362165, "grad_norm": 6.7975335121154785, "learning_rate": 9.394051072328689e-06, "loss": 0.6995, "step": 79020 }, { "epoch": 0.46977073191029, "grad_norm": 6.7945756912231445, "learning_rate": 9.395239906795378e-06, "loss": 0.7069, "step": 79030 }, { "epoch": 0.4698301739869584, "grad_norm": 7.789133071899414, "learning_rate": 9.396428741262066e-06, "loss": 0.7524, "step": 79040 }, { "epoch": 0.4698896160636268, "grad_norm": 6.48601770401001, "learning_rate": 9.397617575728756e-06, "loss": 0.642, "step": 79050 }, { "epoch": 0.4699490581402952, "grad_norm": 6.122044563293457, "learning_rate": 9.398806410195446e-06, "loss": 0.6882, "step": 79060 }, { "epoch": 0.47000850021696355, "grad_norm": 7.572000503540039, "learning_rate": 9.399995244662134e-06, "loss": 0.7289, "step": 79070 }, { "epoch": 0.47006794229363197, "grad_norm": 5.464245319366455, "learning_rate": 9.401184079128824e-06, "loss": 0.6304, "step": 79080 }, { "epoch": 0.4701273843703004, "grad_norm": 5.991231918334961, "learning_rate": 9.402372913595512e-06, "loss": 0.6897, "step": 79090 }, { "epoch": 0.47018682644696874, "grad_norm": 6.696152687072754, "learning_rate": 9.403561748062202e-06, "loss": 0.6771, "step": 79100 }, { "epoch": 0.47024626852363716, "grad_norm": 8.315828323364258, "learning_rate": 9.40475058252889e-06, "loss": 0.7209, "step": 79110 }, { "epoch": 0.4703057106003055, "grad_norm": 9.036596298217773, "learning_rate": 9.40593941699558e-06, "loss": 0.6887, "step": 79120 }, { "epoch": 0.47036515267697393, "grad_norm": 5.2953948974609375, "learning_rate": 9.407128251462268e-06, "loss": 0.6309, "step": 79130 }, { "epoch": 0.4704245947536423, "grad_norm": 6.8384809494018555, "learning_rate": 9.408317085928956e-06, "loss": 0.6223, "step": 79140 }, { "epoch": 0.4704840368303107, "grad_norm": 7.995258331298828, "learning_rate": 9.409505920395645e-06, "loss": 0.7064, "step": 79150 }, { "epoch": 0.4705434789069791, "grad_norm": 5.696664333343506, "learning_rate": 9.410694754862334e-06, "loss": 0.6819, "step": 79160 }, { "epoch": 0.4706029209836475, "grad_norm": 5.989282608032227, "learning_rate": 9.411883589329023e-06, "loss": 0.6774, "step": 79170 }, { "epoch": 0.4706623630603159, "grad_norm": 8.794655799865723, "learning_rate": 9.413072423795711e-06, "loss": 0.6303, "step": 79180 }, { "epoch": 0.47072180513698425, "grad_norm": 6.277843952178955, "learning_rate": 9.414261258262401e-06, "loss": 0.6397, "step": 79190 }, { "epoch": 0.47078124721365266, "grad_norm": 5.4772162437438965, "learning_rate": 9.41545009272909e-06, "loss": 0.6641, "step": 79200 }, { "epoch": 0.470840689290321, "grad_norm": 5.092068195343018, "learning_rate": 9.416638927195777e-06, "loss": 0.6624, "step": 79210 }, { "epoch": 0.47090013136698944, "grad_norm": 6.323348045349121, "learning_rate": 9.417827761662467e-06, "loss": 0.671, "step": 79220 }, { "epoch": 0.47095957344365785, "grad_norm": 7.280632495880127, "learning_rate": 9.419016596129155e-06, "loss": 0.6801, "step": 79230 }, { "epoch": 0.4710190155203262, "grad_norm": 6.465822219848633, "learning_rate": 9.420205430595845e-06, "loss": 0.6721, "step": 79240 }, { "epoch": 0.4710784575969946, "grad_norm": 4.810003280639648, "learning_rate": 9.421394265062533e-06, "loss": 0.6726, "step": 79250 }, { "epoch": 0.471137899673663, "grad_norm": 6.305915355682373, "learning_rate": 9.422583099529223e-06, "loss": 0.704, "step": 79260 }, { "epoch": 0.4711973417503314, "grad_norm": 6.10941743850708, "learning_rate": 9.423771933995911e-06, "loss": 0.664, "step": 79270 }, { "epoch": 0.47125678382699976, "grad_norm": 6.571669578552246, "learning_rate": 9.4249607684626e-06, "loss": 0.6554, "step": 79280 }, { "epoch": 0.4713162259036682, "grad_norm": 6.465336799621582, "learning_rate": 9.426149602929289e-06, "loss": 0.5902, "step": 79290 }, { "epoch": 0.4713756679803366, "grad_norm": 5.6779375076293945, "learning_rate": 9.427338437395977e-06, "loss": 0.6654, "step": 79300 }, { "epoch": 0.47143511005700495, "grad_norm": 4.675652503967285, "learning_rate": 9.428527271862667e-06, "loss": 0.6747, "step": 79310 }, { "epoch": 0.47149455213367336, "grad_norm": 6.858121395111084, "learning_rate": 9.429716106329355e-06, "loss": 0.6531, "step": 79320 }, { "epoch": 0.4715539942103417, "grad_norm": 6.531341552734375, "learning_rate": 9.430904940796044e-06, "loss": 0.6549, "step": 79330 }, { "epoch": 0.47161343628701013, "grad_norm": 6.9189133644104, "learning_rate": 9.432093775262733e-06, "loss": 0.6689, "step": 79340 }, { "epoch": 0.4716728783636785, "grad_norm": 6.916913032531738, "learning_rate": 9.433282609729422e-06, "loss": 0.6479, "step": 79350 }, { "epoch": 0.4717323204403469, "grad_norm": 7.015546798706055, "learning_rate": 9.43447144419611e-06, "loss": 0.6649, "step": 79360 }, { "epoch": 0.47179176251701527, "grad_norm": 5.291987419128418, "learning_rate": 9.4356602786628e-06, "loss": 0.6712, "step": 79370 }, { "epoch": 0.4718512045936837, "grad_norm": 7.574358940124512, "learning_rate": 9.436849113129488e-06, "loss": 0.689, "step": 79380 }, { "epoch": 0.4719106466703521, "grad_norm": 7.546397686004639, "learning_rate": 9.438037947596176e-06, "loss": 0.6862, "step": 79390 }, { "epoch": 0.47197008874702046, "grad_norm": 6.681143283843994, "learning_rate": 9.439226782062866e-06, "loss": 0.6615, "step": 79400 }, { "epoch": 0.47202953082368887, "grad_norm": 6.0285563468933105, "learning_rate": 9.440415616529556e-06, "loss": 0.6077, "step": 79410 }, { "epoch": 0.47208897290035723, "grad_norm": 6.583674907684326, "learning_rate": 9.441604450996244e-06, "loss": 0.6831, "step": 79420 }, { "epoch": 0.47214841497702564, "grad_norm": 7.019399166107178, "learning_rate": 9.442793285462934e-06, "loss": 0.6825, "step": 79430 }, { "epoch": 0.472207857053694, "grad_norm": 6.103275775909424, "learning_rate": 9.443982119929622e-06, "loss": 0.6804, "step": 79440 }, { "epoch": 0.4722672991303624, "grad_norm": 5.77339506149292, "learning_rate": 9.445170954396312e-06, "loss": 0.6151, "step": 79450 }, { "epoch": 0.47232674120703083, "grad_norm": 6.444944858551025, "learning_rate": 9.446359788863e-06, "loss": 0.7304, "step": 79460 }, { "epoch": 0.4723861832836992, "grad_norm": 5.9437713623046875, "learning_rate": 9.44754862332969e-06, "loss": 0.617, "step": 79470 }, { "epoch": 0.4724456253603676, "grad_norm": 6.43808650970459, "learning_rate": 9.448737457796378e-06, "loss": 0.6821, "step": 79480 }, { "epoch": 0.47250506743703596, "grad_norm": 7.33821964263916, "learning_rate": 9.449926292263066e-06, "loss": 0.695, "step": 79490 }, { "epoch": 0.4725645095137044, "grad_norm": 5.76728630065918, "learning_rate": 9.451115126729755e-06, "loss": 0.7114, "step": 79500 }, { "epoch": 0.47262395159037274, "grad_norm": 6.773256301879883, "learning_rate": 9.452303961196443e-06, "loss": 0.671, "step": 79510 }, { "epoch": 0.47268339366704115, "grad_norm": 5.826435089111328, "learning_rate": 9.453492795663133e-06, "loss": 0.634, "step": 79520 }, { "epoch": 0.47274283574370957, "grad_norm": 5.39320707321167, "learning_rate": 9.454681630129821e-06, "loss": 0.6759, "step": 79530 }, { "epoch": 0.4728022778203779, "grad_norm": 7.063964366912842, "learning_rate": 9.455870464596511e-06, "loss": 0.7162, "step": 79540 }, { "epoch": 0.47286171989704634, "grad_norm": 5.7873125076293945, "learning_rate": 9.457059299063199e-06, "loss": 0.6711, "step": 79550 }, { "epoch": 0.4729211619737147, "grad_norm": 6.196030139923096, "learning_rate": 9.458248133529889e-06, "loss": 0.6867, "step": 79560 }, { "epoch": 0.4729806040503831, "grad_norm": 6.875596523284912, "learning_rate": 9.459436967996577e-06, "loss": 0.6698, "step": 79570 }, { "epoch": 0.4730400461270515, "grad_norm": 5.72266960144043, "learning_rate": 9.460625802463265e-06, "loss": 0.6976, "step": 79580 }, { "epoch": 0.4730994882037199, "grad_norm": 4.921801567077637, "learning_rate": 9.461814636929955e-06, "loss": 0.6183, "step": 79590 }, { "epoch": 0.4731589302803883, "grad_norm": 7.3019328117370605, "learning_rate": 9.463003471396643e-06, "loss": 0.7674, "step": 79600 }, { "epoch": 0.47321837235705666, "grad_norm": 6.146425247192383, "learning_rate": 9.464192305863333e-06, "loss": 0.64, "step": 79610 }, { "epoch": 0.4732778144337251, "grad_norm": 5.9766669273376465, "learning_rate": 9.46538114033002e-06, "loss": 0.607, "step": 79620 }, { "epoch": 0.47333725651039343, "grad_norm": 5.654773235321045, "learning_rate": 9.46656997479671e-06, "loss": 0.6052, "step": 79630 }, { "epoch": 0.47339669858706185, "grad_norm": 5.459315776824951, "learning_rate": 9.467758809263399e-06, "loss": 0.6556, "step": 79640 }, { "epoch": 0.4734561406637302, "grad_norm": 8.135194778442383, "learning_rate": 9.468947643730087e-06, "loss": 0.6647, "step": 79650 }, { "epoch": 0.4735155827403986, "grad_norm": 6.19094181060791, "learning_rate": 9.470136478196776e-06, "loss": 0.6313, "step": 79660 }, { "epoch": 0.47357502481706704, "grad_norm": 6.965641498565674, "learning_rate": 9.471325312663465e-06, "loss": 0.6027, "step": 79670 }, { "epoch": 0.4736344668937354, "grad_norm": 5.506251811981201, "learning_rate": 9.472514147130154e-06, "loss": 0.5885, "step": 79680 }, { "epoch": 0.4736939089704038, "grad_norm": 7.217526912689209, "learning_rate": 9.473702981596842e-06, "loss": 0.6271, "step": 79690 }, { "epoch": 0.47375335104707217, "grad_norm": 5.675677299499512, "learning_rate": 9.474891816063532e-06, "loss": 0.6698, "step": 79700 }, { "epoch": 0.4738127931237406, "grad_norm": 6.0587005615234375, "learning_rate": 9.47608065053022e-06, "loss": 0.6661, "step": 79710 }, { "epoch": 0.47387223520040894, "grad_norm": 7.050085067749023, "learning_rate": 9.47726948499691e-06, "loss": 0.6581, "step": 79720 }, { "epoch": 0.47393167727707736, "grad_norm": 7.025428295135498, "learning_rate": 9.478458319463598e-06, "loss": 0.7084, "step": 79730 }, { "epoch": 0.4739911193537457, "grad_norm": 5.5695037841796875, "learning_rate": 9.479647153930286e-06, "loss": 0.6131, "step": 79740 }, { "epoch": 0.47405056143041413, "grad_norm": 8.24987506866455, "learning_rate": 9.480835988396976e-06, "loss": 0.6833, "step": 79750 }, { "epoch": 0.47411000350708254, "grad_norm": 5.400609016418457, "learning_rate": 9.482024822863666e-06, "loss": 0.7224, "step": 79760 }, { "epoch": 0.4741694455837509, "grad_norm": 6.613250732421875, "learning_rate": 9.483213657330354e-06, "loss": 0.7055, "step": 79770 }, { "epoch": 0.4742288876604193, "grad_norm": 6.22952938079834, "learning_rate": 9.484402491797044e-06, "loss": 0.6971, "step": 79780 }, { "epoch": 0.4742883297370877, "grad_norm": 7.738218784332275, "learning_rate": 9.485591326263732e-06, "loss": 0.6478, "step": 79790 }, { "epoch": 0.4743477718137561, "grad_norm": 6.8442912101745605, "learning_rate": 9.486780160730421e-06, "loss": 0.6759, "step": 79800 }, { "epoch": 0.47440721389042445, "grad_norm": 6.22291898727417, "learning_rate": 9.48796899519711e-06, "loss": 0.6453, "step": 79810 }, { "epoch": 0.47446665596709287, "grad_norm": 4.998405933380127, "learning_rate": 9.4891578296638e-06, "loss": 0.6187, "step": 79820 }, { "epoch": 0.4745260980437613, "grad_norm": 6.851417064666748, "learning_rate": 9.490346664130487e-06, "loss": 0.671, "step": 79830 }, { "epoch": 0.47458554012042964, "grad_norm": 7.348687648773193, "learning_rate": 9.491535498597177e-06, "loss": 0.6232, "step": 79840 }, { "epoch": 0.47464498219709805, "grad_norm": 7.0354814529418945, "learning_rate": 9.492724333063865e-06, "loss": 0.6341, "step": 79850 }, { "epoch": 0.4747044242737664, "grad_norm": 7.211173057556152, "learning_rate": 9.493913167530553e-06, "loss": 0.6699, "step": 79860 }, { "epoch": 0.4747638663504348, "grad_norm": 6.220938682556152, "learning_rate": 9.495102001997243e-06, "loss": 0.6356, "step": 79870 }, { "epoch": 0.4748233084271032, "grad_norm": 6.391544818878174, "learning_rate": 9.496290836463931e-06, "loss": 0.6751, "step": 79880 }, { "epoch": 0.4748827505037716, "grad_norm": 7.304368019104004, "learning_rate": 9.497479670930621e-06, "loss": 0.6622, "step": 79890 }, { "epoch": 0.47494219258044, "grad_norm": 5.632272243499756, "learning_rate": 9.498668505397309e-06, "loss": 0.6737, "step": 79900 }, { "epoch": 0.4750016346571084, "grad_norm": 6.011661529541016, "learning_rate": 9.499857339863999e-06, "loss": 0.6503, "step": 79910 }, { "epoch": 0.4750610767337768, "grad_norm": 5.671870231628418, "learning_rate": 9.501046174330687e-06, "loss": 0.7012, "step": 79920 }, { "epoch": 0.47512051881044515, "grad_norm": 6.400897979736328, "learning_rate": 9.502235008797375e-06, "loss": 0.714, "step": 79930 }, { "epoch": 0.47517996088711356, "grad_norm": 5.822732925415039, "learning_rate": 9.503423843264065e-06, "loss": 0.6779, "step": 79940 }, { "epoch": 0.4752394029637819, "grad_norm": 8.379261016845703, "learning_rate": 9.504612677730753e-06, "loss": 0.6331, "step": 79950 }, { "epoch": 0.47529884504045034, "grad_norm": 6.123934745788574, "learning_rate": 9.505801512197443e-06, "loss": 0.6271, "step": 79960 }, { "epoch": 0.47535828711711875, "grad_norm": 6.541983604431152, "learning_rate": 9.50699034666413e-06, "loss": 0.5725, "step": 79970 }, { "epoch": 0.4754177291937871, "grad_norm": 8.650106430053711, "learning_rate": 9.50817918113082e-06, "loss": 0.7191, "step": 79980 }, { "epoch": 0.4754771712704555, "grad_norm": 5.922388553619385, "learning_rate": 9.509368015597509e-06, "loss": 0.6906, "step": 79990 }, { "epoch": 0.4755366133471239, "grad_norm": 5.3991546630859375, "learning_rate": 9.510556850064198e-06, "loss": 0.6313, "step": 80000 }, { "epoch": 0.4755960554237923, "grad_norm": 5.895317077636719, "learning_rate": 9.511745684530886e-06, "loss": 0.6495, "step": 80010 }, { "epoch": 0.47565549750046066, "grad_norm": 6.956501483917236, "learning_rate": 9.512934518997574e-06, "loss": 0.6627, "step": 80020 }, { "epoch": 0.47571493957712907, "grad_norm": 7.9016265869140625, "learning_rate": 9.514123353464264e-06, "loss": 0.6612, "step": 80030 }, { "epoch": 0.4757743816537975, "grad_norm": 5.134500026702881, "learning_rate": 9.515312187930952e-06, "loss": 0.6318, "step": 80040 }, { "epoch": 0.47583382373046584, "grad_norm": 5.522911071777344, "learning_rate": 9.516501022397642e-06, "loss": 0.7084, "step": 80050 }, { "epoch": 0.47589326580713426, "grad_norm": 6.170519828796387, "learning_rate": 9.51768985686433e-06, "loss": 0.6373, "step": 80060 }, { "epoch": 0.4759527078838026, "grad_norm": 6.479826927185059, "learning_rate": 9.51887869133102e-06, "loss": 0.7321, "step": 80070 }, { "epoch": 0.47601214996047103, "grad_norm": 7.2302422523498535, "learning_rate": 9.520067525797708e-06, "loss": 0.6712, "step": 80080 }, { "epoch": 0.4760715920371394, "grad_norm": 6.9341630935668945, "learning_rate": 9.521256360264398e-06, "loss": 0.6436, "step": 80090 }, { "epoch": 0.4761310341138078, "grad_norm": 5.0815510749816895, "learning_rate": 9.522445194731088e-06, "loss": 0.6064, "step": 80100 }, { "epoch": 0.47619047619047616, "grad_norm": 6.0815019607543945, "learning_rate": 9.523634029197776e-06, "loss": 0.6961, "step": 80110 }, { "epoch": 0.4762499182671446, "grad_norm": 6.021258354187012, "learning_rate": 9.524822863664465e-06, "loss": 0.614, "step": 80120 }, { "epoch": 0.476309360343813, "grad_norm": 6.04732084274292, "learning_rate": 9.526011698131154e-06, "loss": 0.6589, "step": 80130 }, { "epoch": 0.47636880242048135, "grad_norm": 6.867527484893799, "learning_rate": 9.527200532597842e-06, "loss": 0.6948, "step": 80140 }, { "epoch": 0.47642824449714977, "grad_norm": 6.875587463378906, "learning_rate": 9.528389367064531e-06, "loss": 0.5933, "step": 80150 }, { "epoch": 0.4764876865738181, "grad_norm": 6.726171016693115, "learning_rate": 9.52957820153122e-06, "loss": 0.7391, "step": 80160 }, { "epoch": 0.47654712865048654, "grad_norm": 6.807812690734863, "learning_rate": 9.53076703599791e-06, "loss": 0.6716, "step": 80170 }, { "epoch": 0.4766065707271549, "grad_norm": 6.388938903808594, "learning_rate": 9.531955870464597e-06, "loss": 0.6658, "step": 80180 }, { "epoch": 0.4766660128038233, "grad_norm": 9.196694374084473, "learning_rate": 9.533144704931287e-06, "loss": 0.6711, "step": 80190 }, { "epoch": 0.47672545488049173, "grad_norm": 5.603017330169678, "learning_rate": 9.534333539397975e-06, "loss": 0.6439, "step": 80200 }, { "epoch": 0.4767848969571601, "grad_norm": 7.015561580657959, "learning_rate": 9.535522373864663e-06, "loss": 0.6718, "step": 80210 }, { "epoch": 0.4768443390338285, "grad_norm": 6.816786766052246, "learning_rate": 9.536711208331353e-06, "loss": 0.6193, "step": 80220 }, { "epoch": 0.47690378111049686, "grad_norm": 7.315941333770752, "learning_rate": 9.537900042798041e-06, "loss": 0.6273, "step": 80230 }, { "epoch": 0.4769632231871653, "grad_norm": 6.2466230392456055, "learning_rate": 9.539088877264731e-06, "loss": 0.6452, "step": 80240 }, { "epoch": 0.47702266526383363, "grad_norm": 5.228134632110596, "learning_rate": 9.540277711731419e-06, "loss": 0.6916, "step": 80250 }, { "epoch": 0.47708210734050205, "grad_norm": 6.066285610198975, "learning_rate": 9.541466546198109e-06, "loss": 0.6316, "step": 80260 }, { "epoch": 0.47714154941717046, "grad_norm": 7.997734546661377, "learning_rate": 9.542655380664797e-06, "loss": 0.6254, "step": 80270 }, { "epoch": 0.4772009914938388, "grad_norm": 5.852583408355713, "learning_rate": 9.543844215131487e-06, "loss": 0.7021, "step": 80280 }, { "epoch": 0.47726043357050724, "grad_norm": 8.232184410095215, "learning_rate": 9.545033049598175e-06, "loss": 0.6534, "step": 80290 }, { "epoch": 0.4773198756471756, "grad_norm": 5.988216876983643, "learning_rate": 9.546221884064863e-06, "loss": 0.6876, "step": 80300 }, { "epoch": 0.477379317723844, "grad_norm": 7.022348403930664, "learning_rate": 9.547410718531553e-06, "loss": 0.7041, "step": 80310 }, { "epoch": 0.47743875980051237, "grad_norm": 6.945344924926758, "learning_rate": 9.54859955299824e-06, "loss": 0.6148, "step": 80320 }, { "epoch": 0.4774982018771808, "grad_norm": 8.7095947265625, "learning_rate": 9.54978838746493e-06, "loss": 0.7045, "step": 80330 }, { "epoch": 0.4775576439538492, "grad_norm": 5.755751132965088, "learning_rate": 9.550977221931618e-06, "loss": 0.6936, "step": 80340 }, { "epoch": 0.47761708603051756, "grad_norm": 8.221076011657715, "learning_rate": 9.552166056398308e-06, "loss": 0.7121, "step": 80350 }, { "epoch": 0.47767652810718597, "grad_norm": 6.794980525970459, "learning_rate": 9.553354890864996e-06, "loss": 0.6024, "step": 80360 }, { "epoch": 0.47773597018385433, "grad_norm": 6.246383190155029, "learning_rate": 9.554543725331686e-06, "loss": 0.6046, "step": 80370 }, { "epoch": 0.47779541226052274, "grad_norm": 6.990926265716553, "learning_rate": 9.555732559798374e-06, "loss": 0.6093, "step": 80380 }, { "epoch": 0.4778548543371911, "grad_norm": 5.427981853485107, "learning_rate": 9.556921394265062e-06, "loss": 0.6196, "step": 80390 }, { "epoch": 0.4779142964138595, "grad_norm": 7.258939743041992, "learning_rate": 9.558110228731752e-06, "loss": 0.6598, "step": 80400 }, { "epoch": 0.4779737384905279, "grad_norm": 7.283360958099365, "learning_rate": 9.55929906319844e-06, "loss": 0.6645, "step": 80410 }, { "epoch": 0.4780331805671963, "grad_norm": 7.275586128234863, "learning_rate": 9.56048789766513e-06, "loss": 0.6729, "step": 80420 }, { "epoch": 0.4780926226438647, "grad_norm": 7.242471218109131, "learning_rate": 9.561676732131818e-06, "loss": 0.6317, "step": 80430 }, { "epoch": 0.47815206472053307, "grad_norm": 8.054726600646973, "learning_rate": 9.562865566598508e-06, "loss": 0.656, "step": 80440 }, { "epoch": 0.4782115067972015, "grad_norm": 7.02058744430542, "learning_rate": 9.564054401065198e-06, "loss": 0.7399, "step": 80450 }, { "epoch": 0.47827094887386984, "grad_norm": 7.247493743896484, "learning_rate": 9.565243235531886e-06, "loss": 0.6817, "step": 80460 }, { "epoch": 0.47833039095053825, "grad_norm": 5.516508102416992, "learning_rate": 9.566432069998575e-06, "loss": 0.6085, "step": 80470 }, { "epoch": 0.4783898330272066, "grad_norm": 7.219381332397461, "learning_rate": 9.567620904465263e-06, "loss": 0.674, "step": 80480 }, { "epoch": 0.478449275103875, "grad_norm": 6.346508502960205, "learning_rate": 9.568809738931952e-06, "loss": 0.7, "step": 80490 }, { "epoch": 0.47850871718054344, "grad_norm": 6.5700483322143555, "learning_rate": 9.569998573398641e-06, "loss": 0.6239, "step": 80500 }, { "epoch": 0.4785681592572118, "grad_norm": 8.943975448608398, "learning_rate": 9.57118740786533e-06, "loss": 0.7402, "step": 80510 }, { "epoch": 0.4786276013338802, "grad_norm": 6.477943420410156, "learning_rate": 9.57237624233202e-06, "loss": 0.6674, "step": 80520 }, { "epoch": 0.4786870434105486, "grad_norm": 9.42761516571045, "learning_rate": 9.573565076798707e-06, "loss": 0.7027, "step": 80530 }, { "epoch": 0.478746485487217, "grad_norm": 6.369147300720215, "learning_rate": 9.574753911265397e-06, "loss": 0.6752, "step": 80540 }, { "epoch": 0.47880592756388535, "grad_norm": 5.601567268371582, "learning_rate": 9.575942745732085e-06, "loss": 0.6758, "step": 80550 }, { "epoch": 0.47886536964055376, "grad_norm": 6.41525936126709, "learning_rate": 9.577131580198775e-06, "loss": 0.7027, "step": 80560 }, { "epoch": 0.4789248117172222, "grad_norm": 6.457181453704834, "learning_rate": 9.578320414665463e-06, "loss": 0.6193, "step": 80570 }, { "epoch": 0.47898425379389054, "grad_norm": 7.301100730895996, "learning_rate": 9.579509249132151e-06, "loss": 0.6526, "step": 80580 }, { "epoch": 0.47904369587055895, "grad_norm": 6.36059045791626, "learning_rate": 9.58069808359884e-06, "loss": 0.7098, "step": 80590 }, { "epoch": 0.4791031379472273, "grad_norm": 7.539323806762695, "learning_rate": 9.581886918065529e-06, "loss": 0.7279, "step": 80600 }, { "epoch": 0.4791625800238957, "grad_norm": 7.33396577835083, "learning_rate": 9.583075752532219e-06, "loss": 0.6975, "step": 80610 }, { "epoch": 0.4792220221005641, "grad_norm": 6.5646281242370605, "learning_rate": 9.584264586998907e-06, "loss": 0.7071, "step": 80620 }, { "epoch": 0.4792814641772325, "grad_norm": 6.699151992797852, "learning_rate": 9.585453421465597e-06, "loss": 0.663, "step": 80630 }, { "epoch": 0.4793409062539009, "grad_norm": 8.23794174194336, "learning_rate": 9.586642255932285e-06, "loss": 0.6861, "step": 80640 }, { "epoch": 0.47940034833056927, "grad_norm": 5.65800142288208, "learning_rate": 9.587831090398974e-06, "loss": 0.682, "step": 80650 }, { "epoch": 0.4794597904072377, "grad_norm": 6.134451866149902, "learning_rate": 9.589019924865662e-06, "loss": 0.5937, "step": 80660 }, { "epoch": 0.47951923248390604, "grad_norm": 5.904418468475342, "learning_rate": 9.59020875933235e-06, "loss": 0.6452, "step": 80670 }, { "epoch": 0.47957867456057446, "grad_norm": 5.035539627075195, "learning_rate": 9.59139759379904e-06, "loss": 0.6602, "step": 80680 }, { "epoch": 0.4796381166372428, "grad_norm": 7.112253189086914, "learning_rate": 9.592586428265728e-06, "loss": 0.7125, "step": 80690 }, { "epoch": 0.47969755871391123, "grad_norm": 5.601362228393555, "learning_rate": 9.593775262732418e-06, "loss": 0.6602, "step": 80700 }, { "epoch": 0.47975700079057965, "grad_norm": 6.821929454803467, "learning_rate": 9.594964097199106e-06, "loss": 0.6944, "step": 80710 }, { "epoch": 0.479816442867248, "grad_norm": 7.666476726531982, "learning_rate": 9.596152931665796e-06, "loss": 0.7256, "step": 80720 }, { "epoch": 0.4798758849439164, "grad_norm": 7.899775505065918, "learning_rate": 9.597341766132484e-06, "loss": 0.5829, "step": 80730 }, { "epoch": 0.4799353270205848, "grad_norm": 5.838381767272949, "learning_rate": 9.598530600599172e-06, "loss": 0.7077, "step": 80740 }, { "epoch": 0.4799947690972532, "grad_norm": 7.682896137237549, "learning_rate": 9.599719435065862e-06, "loss": 0.7087, "step": 80750 }, { "epoch": 0.48005421117392155, "grad_norm": 4.785912990570068, "learning_rate": 9.60090826953255e-06, "loss": 0.6383, "step": 80760 }, { "epoch": 0.48011365325058997, "grad_norm": 5.050724506378174, "learning_rate": 9.60209710399924e-06, "loss": 0.6662, "step": 80770 }, { "epoch": 0.4801730953272583, "grad_norm": 6.978930473327637, "learning_rate": 9.603285938465928e-06, "loss": 0.6949, "step": 80780 }, { "epoch": 0.48023253740392674, "grad_norm": 4.596231460571289, "learning_rate": 9.604474772932618e-06, "loss": 0.6561, "step": 80790 }, { "epoch": 0.48029197948059515, "grad_norm": 6.719038009643555, "learning_rate": 9.605663607399307e-06, "loss": 0.6934, "step": 80800 }, { "epoch": 0.4803514215572635, "grad_norm": 6.689402103424072, "learning_rate": 9.606852441865996e-06, "loss": 0.6535, "step": 80810 }, { "epoch": 0.48041086363393193, "grad_norm": 7.011491775512695, "learning_rate": 9.608041276332685e-06, "loss": 0.5976, "step": 80820 }, { "epoch": 0.4804703057106003, "grad_norm": 5.5298614501953125, "learning_rate": 9.609230110799373e-06, "loss": 0.6156, "step": 80830 }, { "epoch": 0.4805297477872687, "grad_norm": 6.28648567199707, "learning_rate": 9.610418945266063e-06, "loss": 0.6298, "step": 80840 }, { "epoch": 0.48058918986393706, "grad_norm": 5.580835342407227, "learning_rate": 9.611607779732751e-06, "loss": 0.7047, "step": 80850 }, { "epoch": 0.4806486319406055, "grad_norm": 6.476491451263428, "learning_rate": 9.61279661419944e-06, "loss": 0.64, "step": 80860 }, { "epoch": 0.4807080740172739, "grad_norm": 5.268359184265137, "learning_rate": 9.613985448666129e-06, "loss": 0.6439, "step": 80870 }, { "epoch": 0.48076751609394225, "grad_norm": 6.7593889236450195, "learning_rate": 9.615174283132817e-06, "loss": 0.6336, "step": 80880 }, { "epoch": 0.48082695817061066, "grad_norm": 6.956604957580566, "learning_rate": 9.616363117599507e-06, "loss": 0.6327, "step": 80890 }, { "epoch": 0.480886400247279, "grad_norm": 7.012474536895752, "learning_rate": 9.617551952066195e-06, "loss": 0.6761, "step": 80900 }, { "epoch": 0.48094584232394744, "grad_norm": 7.791656970977783, "learning_rate": 9.618740786532885e-06, "loss": 0.6448, "step": 80910 }, { "epoch": 0.4810052844006158, "grad_norm": 6.895848751068115, "learning_rate": 9.619929620999573e-06, "loss": 0.6929, "step": 80920 }, { "epoch": 0.4810647264772842, "grad_norm": 5.65308141708374, "learning_rate": 9.621118455466261e-06, "loss": 0.5973, "step": 80930 }, { "epoch": 0.4811241685539526, "grad_norm": 7.61182165145874, "learning_rate": 9.62230728993295e-06, "loss": 0.6745, "step": 80940 }, { "epoch": 0.481183610630621, "grad_norm": 5.798967361450195, "learning_rate": 9.623496124399639e-06, "loss": 0.6744, "step": 80950 }, { "epoch": 0.4812430527072894, "grad_norm": 6.5252556800842285, "learning_rate": 9.624684958866329e-06, "loss": 0.7319, "step": 80960 }, { "epoch": 0.48130249478395776, "grad_norm": 6.572885036468506, "learning_rate": 9.625873793333017e-06, "loss": 0.6357, "step": 80970 }, { "epoch": 0.48136193686062617, "grad_norm": 6.479306697845459, "learning_rate": 9.627062627799706e-06, "loss": 0.631, "step": 80980 }, { "epoch": 0.48142137893729453, "grad_norm": 7.153050899505615, "learning_rate": 9.628251462266395e-06, "loss": 0.6325, "step": 80990 }, { "epoch": 0.48148082101396295, "grad_norm": 6.4015374183654785, "learning_rate": 9.629440296733084e-06, "loss": 0.6554, "step": 81000 }, { "epoch": 0.48154026309063136, "grad_norm": 5.162465572357178, "learning_rate": 9.630629131199772e-06, "loss": 0.6683, "step": 81010 }, { "epoch": 0.4815997051672997, "grad_norm": 7.024859428405762, "learning_rate": 9.63181796566646e-06, "loss": 0.7031, "step": 81020 }, { "epoch": 0.48165914724396813, "grad_norm": 7.243033409118652, "learning_rate": 9.63300680013315e-06, "loss": 0.6445, "step": 81030 }, { "epoch": 0.4817185893206365, "grad_norm": 7.071094036102295, "learning_rate": 9.634195634599838e-06, "loss": 0.6315, "step": 81040 }, { "epoch": 0.4817780313973049, "grad_norm": 5.152705192565918, "learning_rate": 9.635384469066528e-06, "loss": 0.6831, "step": 81050 }, { "epoch": 0.48183747347397327, "grad_norm": 6.116007328033447, "learning_rate": 9.636573303533216e-06, "loss": 0.6718, "step": 81060 }, { "epoch": 0.4818969155506417, "grad_norm": 5.215890407562256, "learning_rate": 9.637762137999906e-06, "loss": 0.6147, "step": 81070 }, { "epoch": 0.4819563576273101, "grad_norm": 6.495160102844238, "learning_rate": 9.638950972466594e-06, "loss": 0.7161, "step": 81080 }, { "epoch": 0.48201579970397845, "grad_norm": 5.804023742675781, "learning_rate": 9.640139806933284e-06, "loss": 0.6668, "step": 81090 }, { "epoch": 0.48207524178064687, "grad_norm": 6.610464096069336, "learning_rate": 9.641328641399972e-06, "loss": 0.6118, "step": 81100 }, { "epoch": 0.4821346838573152, "grad_norm": 5.958880424499512, "learning_rate": 9.64251747586666e-06, "loss": 0.6626, "step": 81110 }, { "epoch": 0.48219412593398364, "grad_norm": 7.232680797576904, "learning_rate": 9.64370631033335e-06, "loss": 0.6225, "step": 81120 }, { "epoch": 0.482253568010652, "grad_norm": 6.82258415222168, "learning_rate": 9.644895144800038e-06, "loss": 0.6379, "step": 81130 }, { "epoch": 0.4823130100873204, "grad_norm": 8.860878944396973, "learning_rate": 9.646083979266728e-06, "loss": 0.7113, "step": 81140 }, { "epoch": 0.4823724521639888, "grad_norm": 6.1197333335876465, "learning_rate": 9.647272813733417e-06, "loss": 0.6137, "step": 81150 }, { "epoch": 0.4824318942406572, "grad_norm": 5.4150800704956055, "learning_rate": 9.648461648200105e-06, "loss": 0.6252, "step": 81160 }, { "epoch": 0.4824913363173256, "grad_norm": 5.7893853187561035, "learning_rate": 9.649650482666795e-06, "loss": 0.5992, "step": 81170 }, { "epoch": 0.48255077839399396, "grad_norm": 5.3606648445129395, "learning_rate": 9.650839317133483e-06, "loss": 0.6851, "step": 81180 }, { "epoch": 0.4826102204706624, "grad_norm": 6.261192321777344, "learning_rate": 9.652028151600173e-06, "loss": 0.6572, "step": 81190 }, { "epoch": 0.48266966254733074, "grad_norm": 7.213563919067383, "learning_rate": 9.653216986066861e-06, "loss": 0.5963, "step": 81200 }, { "epoch": 0.48272910462399915, "grad_norm": 5.2238616943359375, "learning_rate": 9.65440582053355e-06, "loss": 0.6697, "step": 81210 }, { "epoch": 0.4827885467006675, "grad_norm": 7.663530349731445, "learning_rate": 9.655594655000239e-06, "loss": 0.6447, "step": 81220 }, { "epoch": 0.4828479887773359, "grad_norm": 9.192935943603516, "learning_rate": 9.656783489466927e-06, "loss": 0.6416, "step": 81230 }, { "epoch": 0.48290743085400434, "grad_norm": 6.481053829193115, "learning_rate": 9.657972323933617e-06, "loss": 0.6206, "step": 81240 }, { "epoch": 0.4829668729306727, "grad_norm": 6.9810004234313965, "learning_rate": 9.659161158400305e-06, "loss": 0.6665, "step": 81250 }, { "epoch": 0.4830263150073411, "grad_norm": 7.12851095199585, "learning_rate": 9.660349992866995e-06, "loss": 0.6711, "step": 81260 }, { "epoch": 0.48308575708400947, "grad_norm": 6.23936128616333, "learning_rate": 9.661538827333683e-06, "loss": 0.6295, "step": 81270 }, { "epoch": 0.4831451991606779, "grad_norm": 6.159334182739258, "learning_rate": 9.662727661800373e-06, "loss": 0.6461, "step": 81280 }, { "epoch": 0.48320464123734624, "grad_norm": 6.181614875793457, "learning_rate": 9.66391649626706e-06, "loss": 0.6691, "step": 81290 }, { "epoch": 0.48326408331401466, "grad_norm": 6.583080768585205, "learning_rate": 9.665105330733749e-06, "loss": 0.6814, "step": 81300 }, { "epoch": 0.4833235253906831, "grad_norm": 5.9299774169921875, "learning_rate": 9.666294165200438e-06, "loss": 0.6303, "step": 81310 }, { "epoch": 0.48338296746735143, "grad_norm": 5.634057998657227, "learning_rate": 9.667482999667127e-06, "loss": 0.6597, "step": 81320 }, { "epoch": 0.48344240954401985, "grad_norm": 6.43207311630249, "learning_rate": 9.668671834133816e-06, "loss": 0.6026, "step": 81330 }, { "epoch": 0.4835018516206882, "grad_norm": 7.134096145629883, "learning_rate": 9.669860668600504e-06, "loss": 0.7211, "step": 81340 }, { "epoch": 0.4835612936973566, "grad_norm": 7.5006232261657715, "learning_rate": 9.671049503067194e-06, "loss": 0.6769, "step": 81350 }, { "epoch": 0.483620735774025, "grad_norm": 6.963491439819336, "learning_rate": 9.672238337533882e-06, "loss": 0.6526, "step": 81360 }, { "epoch": 0.4836801778506934, "grad_norm": 6.849167346954346, "learning_rate": 9.673427172000572e-06, "loss": 0.6574, "step": 81370 }, { "epoch": 0.4837396199273618, "grad_norm": 6.964752674102783, "learning_rate": 9.67461600646726e-06, "loss": 0.6584, "step": 81380 }, { "epoch": 0.48379906200403017, "grad_norm": 5.3753662109375, "learning_rate": 9.675804840933948e-06, "loss": 0.6037, "step": 81390 }, { "epoch": 0.4838585040806986, "grad_norm": 5.721824645996094, "learning_rate": 9.676993675400638e-06, "loss": 0.6266, "step": 81400 }, { "epoch": 0.48391794615736694, "grad_norm": 5.562796115875244, "learning_rate": 9.678182509867326e-06, "loss": 0.688, "step": 81410 }, { "epoch": 0.48397738823403536, "grad_norm": 7.020729064941406, "learning_rate": 9.679371344334016e-06, "loss": 0.6784, "step": 81420 }, { "epoch": 0.4840368303107037, "grad_norm": 8.274943351745605, "learning_rate": 9.680560178800704e-06, "loss": 0.6928, "step": 81430 }, { "epoch": 0.48409627238737213, "grad_norm": 5.971276760101318, "learning_rate": 9.681749013267394e-06, "loss": 0.6417, "step": 81440 }, { "epoch": 0.48415571446404054, "grad_norm": 6.453246116638184, "learning_rate": 9.682937847734082e-06, "loss": 0.6637, "step": 81450 }, { "epoch": 0.4842151565407089, "grad_norm": 7.625722408294678, "learning_rate": 9.68412668220077e-06, "loss": 0.6409, "step": 81460 }, { "epoch": 0.4842745986173773, "grad_norm": 5.465906620025635, "learning_rate": 9.68531551666746e-06, "loss": 0.6543, "step": 81470 }, { "epoch": 0.4843340406940457, "grad_norm": 7.336770534515381, "learning_rate": 9.686504351134148e-06, "loss": 0.6966, "step": 81480 }, { "epoch": 0.4843934827707141, "grad_norm": 6.933722972869873, "learning_rate": 9.687693185600837e-06, "loss": 0.6303, "step": 81490 }, { "epoch": 0.48445292484738245, "grad_norm": 5.143670082092285, "learning_rate": 9.688882020067527e-06, "loss": 0.6008, "step": 81500 }, { "epoch": 0.48451236692405086, "grad_norm": 6.416069030761719, "learning_rate": 9.690070854534215e-06, "loss": 0.6928, "step": 81510 }, { "epoch": 0.4845718090007192, "grad_norm": 6.431657314300537, "learning_rate": 9.691259689000905e-06, "loss": 0.6934, "step": 81520 }, { "epoch": 0.48463125107738764, "grad_norm": 6.625137805938721, "learning_rate": 9.692448523467593e-06, "loss": 0.6249, "step": 81530 }, { "epoch": 0.48469069315405605, "grad_norm": 5.588761329650879, "learning_rate": 9.693637357934283e-06, "loss": 0.6243, "step": 81540 }, { "epoch": 0.4847501352307244, "grad_norm": 8.094861030578613, "learning_rate": 9.694826192400971e-06, "loss": 0.6856, "step": 81550 }, { "epoch": 0.4848095773073928, "grad_norm": 6.071892738342285, "learning_rate": 9.69601502686766e-06, "loss": 0.7069, "step": 81560 }, { "epoch": 0.4848690193840612, "grad_norm": 6.236958980560303, "learning_rate": 9.697203861334349e-06, "loss": 0.6952, "step": 81570 }, { "epoch": 0.4849284614607296, "grad_norm": 7.327212810516357, "learning_rate": 9.698392695801037e-06, "loss": 0.718, "step": 81580 }, { "epoch": 0.48498790353739796, "grad_norm": 6.374941825866699, "learning_rate": 9.699581530267727e-06, "loss": 0.6232, "step": 81590 }, { "epoch": 0.48504734561406637, "grad_norm": 5.651794910430908, "learning_rate": 9.700770364734415e-06, "loss": 0.6321, "step": 81600 }, { "epoch": 0.4851067876907348, "grad_norm": 6.1985368728637695, "learning_rate": 9.701959199201105e-06, "loss": 0.6794, "step": 81610 }, { "epoch": 0.48516622976740315, "grad_norm": 6.147755146026611, "learning_rate": 9.703148033667793e-06, "loss": 0.6876, "step": 81620 }, { "epoch": 0.48522567184407156, "grad_norm": 7.601790428161621, "learning_rate": 9.704336868134482e-06, "loss": 0.6325, "step": 81630 }, { "epoch": 0.4852851139207399, "grad_norm": 7.1755051612854, "learning_rate": 9.70552570260117e-06, "loss": 0.625, "step": 81640 }, { "epoch": 0.48534455599740833, "grad_norm": 4.667304039001465, "learning_rate": 9.70671453706786e-06, "loss": 0.5928, "step": 81650 }, { "epoch": 0.4854039980740767, "grad_norm": 6.789130687713623, "learning_rate": 9.707903371534548e-06, "loss": 0.6679, "step": 81660 }, { "epoch": 0.4854634401507451, "grad_norm": 5.271190166473389, "learning_rate": 9.709092206001236e-06, "loss": 0.6633, "step": 81670 }, { "epoch": 0.4855228822274135, "grad_norm": 5.551085472106934, "learning_rate": 9.710281040467926e-06, "loss": 0.6822, "step": 81680 }, { "epoch": 0.4855823243040819, "grad_norm": 7.9842448234558105, "learning_rate": 9.711469874934614e-06, "loss": 0.6458, "step": 81690 }, { "epoch": 0.4856417663807503, "grad_norm": 5.861042022705078, "learning_rate": 9.712658709401304e-06, "loss": 0.6432, "step": 81700 }, { "epoch": 0.48570120845741865, "grad_norm": 6.293740749359131, "learning_rate": 9.713847543867992e-06, "loss": 0.6316, "step": 81710 }, { "epoch": 0.48576065053408707, "grad_norm": 5.817561149597168, "learning_rate": 9.715036378334682e-06, "loss": 0.7385, "step": 81720 }, { "epoch": 0.4858200926107554, "grad_norm": 6.513543128967285, "learning_rate": 9.71622521280137e-06, "loss": 0.671, "step": 81730 }, { "epoch": 0.48587953468742384, "grad_norm": 6.418208122253418, "learning_rate": 9.717414047268058e-06, "loss": 0.6042, "step": 81740 }, { "epoch": 0.48593897676409226, "grad_norm": 6.092909812927246, "learning_rate": 9.718602881734748e-06, "loss": 0.6624, "step": 81750 }, { "epoch": 0.4859984188407606, "grad_norm": 5.316202163696289, "learning_rate": 9.719791716201436e-06, "loss": 0.6159, "step": 81760 }, { "epoch": 0.48605786091742903, "grad_norm": 5.753871917724609, "learning_rate": 9.720980550668126e-06, "loss": 0.6482, "step": 81770 }, { "epoch": 0.4861173029940974, "grad_norm": 7.269242286682129, "learning_rate": 9.722169385134814e-06, "loss": 0.6903, "step": 81780 }, { "epoch": 0.4861767450707658, "grad_norm": 6.078527450561523, "learning_rate": 9.723358219601504e-06, "loss": 0.6483, "step": 81790 }, { "epoch": 0.48623618714743416, "grad_norm": 7.661471843719482, "learning_rate": 9.724547054068192e-06, "loss": 0.6679, "step": 81800 }, { "epoch": 0.4862956292241026, "grad_norm": 6.384618759155273, "learning_rate": 9.725735888534881e-06, "loss": 0.6327, "step": 81810 }, { "epoch": 0.486355071300771, "grad_norm": 6.640885353088379, "learning_rate": 9.72692472300157e-06, "loss": 0.6799, "step": 81820 }, { "epoch": 0.48641451337743935, "grad_norm": 6.744338512420654, "learning_rate": 9.728113557468258e-06, "loss": 0.6344, "step": 81830 }, { "epoch": 0.48647395545410776, "grad_norm": 6.7647199630737305, "learning_rate": 9.729302391934949e-06, "loss": 0.6741, "step": 81840 }, { "epoch": 0.4865333975307761, "grad_norm": 6.693859100341797, "learning_rate": 9.730491226401637e-06, "loss": 0.6904, "step": 81850 }, { "epoch": 0.48659283960744454, "grad_norm": 9.074257850646973, "learning_rate": 9.731680060868325e-06, "loss": 0.683, "step": 81860 }, { "epoch": 0.4866522816841129, "grad_norm": 5.168705463409424, "learning_rate": 9.732868895335015e-06, "loss": 0.6432, "step": 81870 }, { "epoch": 0.4867117237607813, "grad_norm": 6.498003959655762, "learning_rate": 9.734057729801703e-06, "loss": 0.6823, "step": 81880 }, { "epoch": 0.48677116583744967, "grad_norm": 5.539515972137451, "learning_rate": 9.735246564268393e-06, "loss": 0.7155, "step": 81890 }, { "epoch": 0.4868306079141181, "grad_norm": 6.2140421867370605, "learning_rate": 9.736435398735081e-06, "loss": 0.5948, "step": 81900 }, { "epoch": 0.4868900499907865, "grad_norm": 7.9482831954956055, "learning_rate": 9.73762423320177e-06, "loss": 0.732, "step": 81910 }, { "epoch": 0.48694949206745486, "grad_norm": 5.444460391998291, "learning_rate": 9.738813067668459e-06, "loss": 0.6698, "step": 81920 }, { "epoch": 0.4870089341441233, "grad_norm": 5.746925354003906, "learning_rate": 9.740001902135147e-06, "loss": 0.6502, "step": 81930 }, { "epoch": 0.48706837622079163, "grad_norm": 7.1076579093933105, "learning_rate": 9.741190736601837e-06, "loss": 0.6639, "step": 81940 }, { "epoch": 0.48712781829746005, "grad_norm": 5.120535373687744, "learning_rate": 9.742379571068525e-06, "loss": 0.6304, "step": 81950 }, { "epoch": 0.4871872603741284, "grad_norm": 6.551523685455322, "learning_rate": 9.743568405535215e-06, "loss": 0.7022, "step": 81960 }, { "epoch": 0.4872467024507968, "grad_norm": 7.194361209869385, "learning_rate": 9.744757240001903e-06, "loss": 0.6332, "step": 81970 }, { "epoch": 0.48730614452746523, "grad_norm": 5.627385139465332, "learning_rate": 9.745946074468592e-06, "loss": 0.6484, "step": 81980 }, { "epoch": 0.4873655866041336, "grad_norm": 6.186037540435791, "learning_rate": 9.74713490893528e-06, "loss": 0.6053, "step": 81990 }, { "epoch": 0.487425028680802, "grad_norm": 5.929022312164307, "learning_rate": 9.74832374340197e-06, "loss": 0.6308, "step": 82000 }, { "epoch": 0.48748447075747037, "grad_norm": 5.675205230712891, "learning_rate": 9.749512577868658e-06, "loss": 0.6581, "step": 82010 }, { "epoch": 0.4875439128341388, "grad_norm": 5.767733097076416, "learning_rate": 9.750701412335346e-06, "loss": 0.5878, "step": 82020 }, { "epoch": 0.48760335491080714, "grad_norm": 6.765783309936523, "learning_rate": 9.751890246802036e-06, "loss": 0.6562, "step": 82030 }, { "epoch": 0.48766279698747556, "grad_norm": 5.288885593414307, "learning_rate": 9.753079081268724e-06, "loss": 0.695, "step": 82040 }, { "epoch": 0.48772223906414397, "grad_norm": 6.1504645347595215, "learning_rate": 9.754267915735414e-06, "loss": 0.644, "step": 82050 }, { "epoch": 0.48778168114081233, "grad_norm": 7.577245712280273, "learning_rate": 9.755456750202102e-06, "loss": 0.6959, "step": 82060 }, { "epoch": 0.48784112321748074, "grad_norm": 6.056215286254883, "learning_rate": 9.756645584668792e-06, "loss": 0.591, "step": 82070 }, { "epoch": 0.4879005652941491, "grad_norm": 7.258533477783203, "learning_rate": 9.75783441913548e-06, "loss": 0.717, "step": 82080 }, { "epoch": 0.4879600073708175, "grad_norm": 5.851816654205322, "learning_rate": 9.75902325360217e-06, "loss": 0.6944, "step": 82090 }, { "epoch": 0.4880194494474859, "grad_norm": 6.120872497558594, "learning_rate": 9.760212088068858e-06, "loss": 0.6613, "step": 82100 }, { "epoch": 0.4880788915241543, "grad_norm": 6.578627586364746, "learning_rate": 9.761400922535546e-06, "loss": 0.6473, "step": 82110 }, { "epoch": 0.4881383336008227, "grad_norm": 6.708157539367676, "learning_rate": 9.762589757002236e-06, "loss": 0.6397, "step": 82120 }, { "epoch": 0.48819777567749106, "grad_norm": 15.101837158203125, "learning_rate": 9.763778591468924e-06, "loss": 0.6602, "step": 82130 }, { "epoch": 0.4882572177541595, "grad_norm": 6.493697643280029, "learning_rate": 9.764967425935614e-06, "loss": 0.668, "step": 82140 }, { "epoch": 0.48831665983082784, "grad_norm": 6.667887210845947, "learning_rate": 9.766156260402302e-06, "loss": 0.7028, "step": 82150 }, { "epoch": 0.48837610190749625, "grad_norm": 6.676427364349365, "learning_rate": 9.767345094868991e-06, "loss": 0.6002, "step": 82160 }, { "epoch": 0.4884355439841646, "grad_norm": 5.624166965484619, "learning_rate": 9.76853392933568e-06, "loss": 0.6514, "step": 82170 }, { "epoch": 0.488494986060833, "grad_norm": 7.615426063537598, "learning_rate": 9.76972276380237e-06, "loss": 0.6065, "step": 82180 }, { "epoch": 0.4885544281375014, "grad_norm": 5.1662702560424805, "learning_rate": 9.770911598269059e-06, "loss": 0.6212, "step": 82190 }, { "epoch": 0.4886138702141698, "grad_norm": 5.4195876121521, "learning_rate": 9.772100432735747e-06, "loss": 0.6243, "step": 82200 }, { "epoch": 0.4886733122908382, "grad_norm": 6.751683235168457, "learning_rate": 9.773289267202435e-06, "loss": 0.6556, "step": 82210 }, { "epoch": 0.48873275436750657, "grad_norm": 4.938257694244385, "learning_rate": 9.774478101669125e-06, "loss": 0.6589, "step": 82220 }, { "epoch": 0.488792196444175, "grad_norm": 6.01409387588501, "learning_rate": 9.775666936135813e-06, "loss": 0.6747, "step": 82230 }, { "epoch": 0.48885163852084335, "grad_norm": 7.5868377685546875, "learning_rate": 9.776855770602503e-06, "loss": 0.6815, "step": 82240 }, { "epoch": 0.48891108059751176, "grad_norm": 7.263936519622803, "learning_rate": 9.778044605069191e-06, "loss": 0.6587, "step": 82250 }, { "epoch": 0.4889705226741801, "grad_norm": 6.015460014343262, "learning_rate": 9.77923343953588e-06, "loss": 0.6955, "step": 82260 }, { "epoch": 0.48902996475084853, "grad_norm": 5.637630939483643, "learning_rate": 9.780422274002569e-06, "loss": 0.6197, "step": 82270 }, { "epoch": 0.48908940682751695, "grad_norm": 7.323543548583984, "learning_rate": 9.781611108469259e-06, "loss": 0.6905, "step": 82280 }, { "epoch": 0.4891488489041853, "grad_norm": 5.692507743835449, "learning_rate": 9.782799942935947e-06, "loss": 0.7288, "step": 82290 }, { "epoch": 0.4892082909808537, "grad_norm": 6.969900131225586, "learning_rate": 9.783988777402635e-06, "loss": 0.6354, "step": 82300 }, { "epoch": 0.4892677330575221, "grad_norm": 6.5671844482421875, "learning_rate": 9.785177611869324e-06, "loss": 0.6559, "step": 82310 }, { "epoch": 0.4893271751341905, "grad_norm": 7.251287937164307, "learning_rate": 9.786366446336013e-06, "loss": 0.6526, "step": 82320 }, { "epoch": 0.48938661721085885, "grad_norm": 5.343450546264648, "learning_rate": 9.787555280802702e-06, "loss": 0.6707, "step": 82330 }, { "epoch": 0.48944605928752727, "grad_norm": 5.202780246734619, "learning_rate": 9.78874411526939e-06, "loss": 0.6749, "step": 82340 }, { "epoch": 0.4895055013641957, "grad_norm": 6.359274387359619, "learning_rate": 9.78993294973608e-06, "loss": 0.6445, "step": 82350 }, { "epoch": 0.48956494344086404, "grad_norm": 12.9049711227417, "learning_rate": 9.791121784202768e-06, "loss": 0.72, "step": 82360 }, { "epoch": 0.48962438551753246, "grad_norm": 6.4402384757995605, "learning_rate": 9.792310618669458e-06, "loss": 0.6098, "step": 82370 }, { "epoch": 0.4896838275942008, "grad_norm": 6.731945991516113, "learning_rate": 9.793499453136146e-06, "loss": 0.6482, "step": 82380 }, { "epoch": 0.48974326967086923, "grad_norm": 6.198009014129639, "learning_rate": 9.794688287602834e-06, "loss": 0.6676, "step": 82390 }, { "epoch": 0.4898027117475376, "grad_norm": 5.961428642272949, "learning_rate": 9.795877122069524e-06, "loss": 0.6499, "step": 82400 }, { "epoch": 0.489862153824206, "grad_norm": 6.093484401702881, "learning_rate": 9.797065956536212e-06, "loss": 0.6171, "step": 82410 }, { "epoch": 0.4899215959008744, "grad_norm": 7.160477638244629, "learning_rate": 9.798254791002902e-06, "loss": 0.6476, "step": 82420 }, { "epoch": 0.4899810379775428, "grad_norm": 6.081991195678711, "learning_rate": 9.79944362546959e-06, "loss": 0.6951, "step": 82430 }, { "epoch": 0.4900404800542112, "grad_norm": 6.050755500793457, "learning_rate": 9.80063245993628e-06, "loss": 0.7445, "step": 82440 }, { "epoch": 0.49009992213087955, "grad_norm": 8.085663795471191, "learning_rate": 9.801821294402968e-06, "loss": 0.6977, "step": 82450 }, { "epoch": 0.49015936420754797, "grad_norm": 7.362257480621338, "learning_rate": 9.803010128869656e-06, "loss": 0.6531, "step": 82460 }, { "epoch": 0.4902188062842163, "grad_norm": 6.049673557281494, "learning_rate": 9.804198963336346e-06, "loss": 0.6294, "step": 82470 }, { "epoch": 0.49027824836088474, "grad_norm": 6.80681848526001, "learning_rate": 9.805387797803034e-06, "loss": 0.6532, "step": 82480 }, { "epoch": 0.49033769043755315, "grad_norm": 7.728469371795654, "learning_rate": 9.806576632269723e-06, "loss": 0.6572, "step": 82490 }, { "epoch": 0.4903971325142215, "grad_norm": 6.74275541305542, "learning_rate": 9.807765466736412e-06, "loss": 0.6771, "step": 82500 }, { "epoch": 0.4904565745908899, "grad_norm": 5.429522514343262, "learning_rate": 9.808954301203101e-06, "loss": 0.6685, "step": 82510 }, { "epoch": 0.4905160166675583, "grad_norm": 8.147085189819336, "learning_rate": 9.81014313566979e-06, "loss": 0.6956, "step": 82520 }, { "epoch": 0.4905754587442267, "grad_norm": 7.375156402587891, "learning_rate": 9.811331970136479e-06, "loss": 0.6911, "step": 82530 }, { "epoch": 0.49063490082089506, "grad_norm": 7.344637870788574, "learning_rate": 9.812520804603169e-06, "loss": 0.6509, "step": 82540 }, { "epoch": 0.4906943428975635, "grad_norm": 5.638616561889648, "learning_rate": 9.813709639069857e-06, "loss": 0.6417, "step": 82550 }, { "epoch": 0.49075378497423183, "grad_norm": 6.933021545410156, "learning_rate": 9.814898473536547e-06, "loss": 0.6539, "step": 82560 }, { "epoch": 0.49081322705090025, "grad_norm": 6.135198593139648, "learning_rate": 9.816087308003235e-06, "loss": 0.6107, "step": 82570 }, { "epoch": 0.49087266912756866, "grad_norm": 5.668496131896973, "learning_rate": 9.817276142469923e-06, "loss": 0.7142, "step": 82580 }, { "epoch": 0.490932111204237, "grad_norm": 7.975473880767822, "learning_rate": 9.818464976936613e-06, "loss": 0.7338, "step": 82590 }, { "epoch": 0.49099155328090544, "grad_norm": 6.087267875671387, "learning_rate": 9.8196538114033e-06, "loss": 0.7216, "step": 82600 }, { "epoch": 0.4910509953575738, "grad_norm": 6.588095664978027, "learning_rate": 9.82084264586999e-06, "loss": 0.6711, "step": 82610 }, { "epoch": 0.4911104374342422, "grad_norm": 7.447058200836182, "learning_rate": 9.822031480336679e-06, "loss": 0.6371, "step": 82620 }, { "epoch": 0.49116987951091057, "grad_norm": 6.537687301635742, "learning_rate": 9.823220314803368e-06, "loss": 0.6745, "step": 82630 }, { "epoch": 0.491229321587579, "grad_norm": 5.620654106140137, "learning_rate": 9.824409149270057e-06, "loss": 0.6566, "step": 82640 }, { "epoch": 0.4912887636642474, "grad_norm": 6.142683506011963, "learning_rate": 9.825597983736746e-06, "loss": 0.6411, "step": 82650 }, { "epoch": 0.49134820574091576, "grad_norm": 5.389021396636963, "learning_rate": 9.826786818203434e-06, "loss": 0.6537, "step": 82660 }, { "epoch": 0.49140764781758417, "grad_norm": 6.642673015594482, "learning_rate": 9.827975652670122e-06, "loss": 0.6743, "step": 82670 }, { "epoch": 0.49146708989425253, "grad_norm": 5.032475471496582, "learning_rate": 9.829164487136812e-06, "loss": 0.588, "step": 82680 }, { "epoch": 0.49152653197092094, "grad_norm": 6.238739967346191, "learning_rate": 9.8303533216035e-06, "loss": 0.7074, "step": 82690 }, { "epoch": 0.4915859740475893, "grad_norm": 5.557187557220459, "learning_rate": 9.83154215607019e-06, "loss": 0.6084, "step": 82700 }, { "epoch": 0.4916454161242577, "grad_norm": 5.818065643310547, "learning_rate": 9.832730990536878e-06, "loss": 0.639, "step": 82710 }, { "epoch": 0.49170485820092613, "grad_norm": 5.699596881866455, "learning_rate": 9.833919825003568e-06, "loss": 0.7006, "step": 82720 }, { "epoch": 0.4917643002775945, "grad_norm": 7.046352386474609, "learning_rate": 9.835108659470256e-06, "loss": 0.6886, "step": 82730 }, { "epoch": 0.4918237423542629, "grad_norm": 6.452984809875488, "learning_rate": 9.836297493936944e-06, "loss": 0.725, "step": 82740 }, { "epoch": 0.49188318443093126, "grad_norm": 5.71824836730957, "learning_rate": 9.837486328403634e-06, "loss": 0.6529, "step": 82750 }, { "epoch": 0.4919426265075997, "grad_norm": 5.801234245300293, "learning_rate": 9.838675162870322e-06, "loss": 0.6827, "step": 82760 }, { "epoch": 0.49200206858426804, "grad_norm": 6.332769870758057, "learning_rate": 9.839863997337012e-06, "loss": 0.6704, "step": 82770 }, { "epoch": 0.49206151066093645, "grad_norm": 6.818410396575928, "learning_rate": 9.8410528318037e-06, "loss": 0.7081, "step": 82780 }, { "epoch": 0.49212095273760487, "grad_norm": 6.936781883239746, "learning_rate": 9.84224166627039e-06, "loss": 0.6843, "step": 82790 }, { "epoch": 0.4921803948142732, "grad_norm": 6.261674880981445, "learning_rate": 9.843430500737078e-06, "loss": 0.6797, "step": 82800 }, { "epoch": 0.49223983689094164, "grad_norm": 6.69978141784668, "learning_rate": 9.844619335203767e-06, "loss": 0.6781, "step": 82810 }, { "epoch": 0.49229927896761, "grad_norm": 6.7831573486328125, "learning_rate": 9.845808169670456e-06, "loss": 0.6887, "step": 82820 }, { "epoch": 0.4923587210442784, "grad_norm": 6.287409782409668, "learning_rate": 9.846997004137144e-06, "loss": 0.6327, "step": 82830 }, { "epoch": 0.4924181631209468, "grad_norm": 16.092063903808594, "learning_rate": 9.848185838603833e-06, "loss": 0.6228, "step": 82840 }, { "epoch": 0.4924776051976152, "grad_norm": 8.663736343383789, "learning_rate": 9.849374673070521e-06, "loss": 0.6565, "step": 82850 }, { "epoch": 0.4925370472742836, "grad_norm": 5.0604119300842285, "learning_rate": 9.850563507537211e-06, "loss": 0.6167, "step": 82860 }, { "epoch": 0.49259648935095196, "grad_norm": 6.916421890258789, "learning_rate": 9.851752342003901e-06, "loss": 0.7398, "step": 82870 }, { "epoch": 0.4926559314276204, "grad_norm": 7.076774597167969, "learning_rate": 9.852941176470589e-06, "loss": 0.6929, "step": 82880 }, { "epoch": 0.49271537350428873, "grad_norm": 7.295823574066162, "learning_rate": 9.854130010937279e-06, "loss": 0.6672, "step": 82890 }, { "epoch": 0.49277481558095715, "grad_norm": 4.792212963104248, "learning_rate": 9.855318845403967e-06, "loss": 0.6276, "step": 82900 }, { "epoch": 0.4928342576576255, "grad_norm": 7.289877891540527, "learning_rate": 9.856507679870657e-06, "loss": 0.6393, "step": 82910 }, { "epoch": 0.4928936997342939, "grad_norm": 6.141971588134766, "learning_rate": 9.857696514337345e-06, "loss": 0.6518, "step": 82920 }, { "epoch": 0.4929531418109623, "grad_norm": 7.0487542152404785, "learning_rate": 9.858885348804033e-06, "loss": 0.6273, "step": 82930 }, { "epoch": 0.4930125838876307, "grad_norm": 7.0772504806518555, "learning_rate": 9.860074183270723e-06, "loss": 0.6537, "step": 82940 }, { "epoch": 0.4930720259642991, "grad_norm": 5.662999153137207, "learning_rate": 9.86126301773741e-06, "loss": 0.6547, "step": 82950 }, { "epoch": 0.49313146804096747, "grad_norm": 6.750820636749268, "learning_rate": 9.8624518522041e-06, "loss": 0.6984, "step": 82960 }, { "epoch": 0.4931909101176359, "grad_norm": 8.945001602172852, "learning_rate": 9.863640686670789e-06, "loss": 0.6892, "step": 82970 }, { "epoch": 0.49325035219430424, "grad_norm": 8.176473617553711, "learning_rate": 9.864829521137478e-06, "loss": 0.7308, "step": 82980 }, { "epoch": 0.49330979427097266, "grad_norm": 7.5815582275390625, "learning_rate": 9.866018355604166e-06, "loss": 0.6515, "step": 82990 }, { "epoch": 0.493369236347641, "grad_norm": 5.817582130432129, "learning_rate": 9.867207190070856e-06, "loss": 0.615, "step": 83000 }, { "epoch": 0.49342867842430943, "grad_norm": 5.632277488708496, "learning_rate": 9.868396024537544e-06, "loss": 0.6832, "step": 83010 }, { "epoch": 0.49348812050097784, "grad_norm": 6.6815338134765625, "learning_rate": 9.869584859004232e-06, "loss": 0.6487, "step": 83020 }, { "epoch": 0.4935475625776462, "grad_norm": 5.226871967315674, "learning_rate": 9.870773693470922e-06, "loss": 0.7251, "step": 83030 }, { "epoch": 0.4936070046543146, "grad_norm": 5.267257213592529, "learning_rate": 9.87196252793761e-06, "loss": 0.6499, "step": 83040 }, { "epoch": 0.493666446730983, "grad_norm": 6.3855390548706055, "learning_rate": 9.8731513624043e-06, "loss": 0.6354, "step": 83050 }, { "epoch": 0.4937258888076514, "grad_norm": 5.670156478881836, "learning_rate": 9.874340196870988e-06, "loss": 0.6776, "step": 83060 }, { "epoch": 0.49378533088431975, "grad_norm": 6.240212440490723, "learning_rate": 9.875529031337678e-06, "loss": 0.6329, "step": 83070 }, { "epoch": 0.49384477296098817, "grad_norm": 6.387711524963379, "learning_rate": 9.876717865804366e-06, "loss": 0.6875, "step": 83080 }, { "epoch": 0.4939042150376566, "grad_norm": 6.335089206695557, "learning_rate": 9.877906700271056e-06, "loss": 0.671, "step": 83090 }, { "epoch": 0.49396365711432494, "grad_norm": 8.744318962097168, "learning_rate": 9.879095534737744e-06, "loss": 0.7086, "step": 83100 }, { "epoch": 0.49402309919099335, "grad_norm": 8.016066551208496, "learning_rate": 9.880284369204432e-06, "loss": 0.6609, "step": 83110 }, { "epoch": 0.4940825412676617, "grad_norm": 7.9081950187683105, "learning_rate": 9.881473203671122e-06, "loss": 0.6507, "step": 83120 }, { "epoch": 0.4941419833443301, "grad_norm": 6.063310623168945, "learning_rate": 9.88266203813781e-06, "loss": 0.6179, "step": 83130 }, { "epoch": 0.4942014254209985, "grad_norm": 5.8690314292907715, "learning_rate": 9.8838508726045e-06, "loss": 0.7362, "step": 83140 }, { "epoch": 0.4942608674976669, "grad_norm": 6.1392292976379395, "learning_rate": 9.885039707071188e-06, "loss": 0.6279, "step": 83150 }, { "epoch": 0.4943203095743353, "grad_norm": 6.4515604972839355, "learning_rate": 9.886228541537877e-06, "loss": 0.6522, "step": 83160 }, { "epoch": 0.4943797516510037, "grad_norm": 10.7725248336792, "learning_rate": 9.887417376004565e-06, "loss": 0.6356, "step": 83170 }, { "epoch": 0.4944391937276721, "grad_norm": 5.389807224273682, "learning_rate": 9.888606210471255e-06, "loss": 0.6185, "step": 83180 }, { "epoch": 0.49449863580434045, "grad_norm": 7.149299621582031, "learning_rate": 9.889795044937943e-06, "loss": 0.6959, "step": 83190 }, { "epoch": 0.49455807788100886, "grad_norm": 8.272927284240723, "learning_rate": 9.890983879404631e-06, "loss": 0.693, "step": 83200 }, { "epoch": 0.4946175199576772, "grad_norm": 4.678206443786621, "learning_rate": 9.892172713871321e-06, "loss": 0.6349, "step": 83210 }, { "epoch": 0.49467696203434564, "grad_norm": 6.774806976318359, "learning_rate": 9.893361548338011e-06, "loss": 0.7238, "step": 83220 }, { "epoch": 0.49473640411101405, "grad_norm": 7.193617820739746, "learning_rate": 9.894550382804699e-06, "loss": 0.6502, "step": 83230 }, { "epoch": 0.4947958461876824, "grad_norm": 6.394774436950684, "learning_rate": 9.895739217271389e-06, "loss": 0.6498, "step": 83240 }, { "epoch": 0.4948552882643508, "grad_norm": 7.923679828643799, "learning_rate": 9.896928051738077e-06, "loss": 0.6462, "step": 83250 }, { "epoch": 0.4949147303410192, "grad_norm": 4.211844444274902, "learning_rate": 9.898116886204767e-06, "loss": 0.6671, "step": 83260 }, { "epoch": 0.4949741724176876, "grad_norm": 7.175637722015381, "learning_rate": 9.899305720671455e-06, "loss": 0.6791, "step": 83270 }, { "epoch": 0.49503361449435596, "grad_norm": 6.119096755981445, "learning_rate": 9.900494555138144e-06, "loss": 0.6744, "step": 83280 }, { "epoch": 0.49509305657102437, "grad_norm": 6.82510232925415, "learning_rate": 9.901683389604833e-06, "loss": 0.7168, "step": 83290 }, { "epoch": 0.49515249864769273, "grad_norm": 6.908417701721191, "learning_rate": 9.90287222407152e-06, "loss": 0.6416, "step": 83300 }, { "epoch": 0.49521194072436114, "grad_norm": 8.677485466003418, "learning_rate": 9.90406105853821e-06, "loss": 0.7185, "step": 83310 }, { "epoch": 0.49527138280102956, "grad_norm": 4.841448783874512, "learning_rate": 9.905249893004898e-06, "loss": 0.6635, "step": 83320 }, { "epoch": 0.4953308248776979, "grad_norm": 5.376482963562012, "learning_rate": 9.906438727471588e-06, "loss": 0.6409, "step": 83330 }, { "epoch": 0.49539026695436633, "grad_norm": 7.175192832946777, "learning_rate": 9.907627561938276e-06, "loss": 0.7057, "step": 83340 }, { "epoch": 0.4954497090310347, "grad_norm": 6.677656173706055, "learning_rate": 9.908816396404966e-06, "loss": 0.5823, "step": 83350 }, { "epoch": 0.4955091511077031, "grad_norm": 6.246877193450928, "learning_rate": 9.910005230871654e-06, "loss": 0.6171, "step": 83360 }, { "epoch": 0.49556859318437146, "grad_norm": 5.818798542022705, "learning_rate": 9.911194065338344e-06, "loss": 0.673, "step": 83370 }, { "epoch": 0.4956280352610399, "grad_norm": 5.1990485191345215, "learning_rate": 9.912382899805032e-06, "loss": 0.6516, "step": 83380 }, { "epoch": 0.4956874773377083, "grad_norm": 5.274138927459717, "learning_rate": 9.91357173427172e-06, "loss": 0.6749, "step": 83390 }, { "epoch": 0.49574691941437665, "grad_norm": 4.896373748779297, "learning_rate": 9.91476056873841e-06, "loss": 0.6169, "step": 83400 }, { "epoch": 0.49580636149104507, "grad_norm": 5.273285388946533, "learning_rate": 9.915949403205098e-06, "loss": 0.6692, "step": 83410 }, { "epoch": 0.4958658035677134, "grad_norm": 5.102421283721924, "learning_rate": 9.917138237671788e-06, "loss": 0.6674, "step": 83420 }, { "epoch": 0.49592524564438184, "grad_norm": 6.912082672119141, "learning_rate": 9.918327072138476e-06, "loss": 0.6601, "step": 83430 }, { "epoch": 0.4959846877210502, "grad_norm": 6.5940351486206055, "learning_rate": 9.919515906605166e-06, "loss": 0.7323, "step": 83440 }, { "epoch": 0.4960441297977186, "grad_norm": 7.259110450744629, "learning_rate": 9.920704741071854e-06, "loss": 0.6692, "step": 83450 }, { "epoch": 0.49610357187438703, "grad_norm": 6.586407661437988, "learning_rate": 9.921893575538542e-06, "loss": 0.6445, "step": 83460 }, { "epoch": 0.4961630139510554, "grad_norm": 6.7062506675720215, "learning_rate": 9.923082410005232e-06, "loss": 0.6619, "step": 83470 }, { "epoch": 0.4962224560277238, "grad_norm": 6.2451887130737305, "learning_rate": 9.92427124447192e-06, "loss": 0.6729, "step": 83480 }, { "epoch": 0.49628189810439216, "grad_norm": 9.24456787109375, "learning_rate": 9.92546007893861e-06, "loss": 0.6762, "step": 83490 }, { "epoch": 0.4963413401810606, "grad_norm": 5.8358283042907715, "learning_rate": 9.926648913405297e-06, "loss": 0.6497, "step": 83500 }, { "epoch": 0.49640078225772893, "grad_norm": 6.853814125061035, "learning_rate": 9.927837747871987e-06, "loss": 0.6681, "step": 83510 }, { "epoch": 0.49646022433439735, "grad_norm": 7.826071262359619, "learning_rate": 9.929026582338675e-06, "loss": 0.6936, "step": 83520 }, { "epoch": 0.49651966641106576, "grad_norm": 6.1214213371276855, "learning_rate": 9.930215416805365e-06, "loss": 0.6639, "step": 83530 }, { "epoch": 0.4965791084877341, "grad_norm": 7.573901176452637, "learning_rate": 9.931404251272053e-06, "loss": 0.6799, "step": 83540 }, { "epoch": 0.49663855056440254, "grad_norm": 5.410409927368164, "learning_rate": 9.932593085738741e-06, "loss": 0.6338, "step": 83550 }, { "epoch": 0.4966979926410709, "grad_norm": 7.4210100173950195, "learning_rate": 9.933781920205431e-06, "loss": 0.6444, "step": 83560 }, { "epoch": 0.4967574347177393, "grad_norm": 5.501652717590332, "learning_rate": 9.93497075467212e-06, "loss": 0.6041, "step": 83570 }, { "epoch": 0.49681687679440767, "grad_norm": 5.459356307983398, "learning_rate": 9.936159589138809e-06, "loss": 0.6656, "step": 83580 }, { "epoch": 0.4968763188710761, "grad_norm": 6.512086391448975, "learning_rate": 9.937348423605499e-06, "loss": 0.6534, "step": 83590 }, { "epoch": 0.4969357609477445, "grad_norm": 5.100944995880127, "learning_rate": 9.938537258072187e-06, "loss": 0.6858, "step": 83600 }, { "epoch": 0.49699520302441286, "grad_norm": 6.705860137939453, "learning_rate": 9.939726092538877e-06, "loss": 0.7013, "step": 83610 }, { "epoch": 0.49705464510108127, "grad_norm": 5.710700511932373, "learning_rate": 9.940914927005565e-06, "loss": 0.7023, "step": 83620 }, { "epoch": 0.49711408717774963, "grad_norm": 6.471194267272949, "learning_rate": 9.942103761472254e-06, "loss": 0.6826, "step": 83630 }, { "epoch": 0.49717352925441805, "grad_norm": 6.369243144989014, "learning_rate": 9.943292595938942e-06, "loss": 0.6377, "step": 83640 }, { "epoch": 0.4972329713310864, "grad_norm": 5.762360095977783, "learning_rate": 9.944481430405632e-06, "loss": 0.635, "step": 83650 }, { "epoch": 0.4972924134077548, "grad_norm": 5.125802040100098, "learning_rate": 9.94567026487232e-06, "loss": 0.6395, "step": 83660 }, { "epoch": 0.4973518554844232, "grad_norm": 7.394868850708008, "learning_rate": 9.946859099339008e-06, "loss": 0.6447, "step": 83670 }, { "epoch": 0.4974112975610916, "grad_norm": 5.43049955368042, "learning_rate": 9.948047933805698e-06, "loss": 0.633, "step": 83680 }, { "epoch": 0.49747073963776, "grad_norm": 6.415698051452637, "learning_rate": 9.949236768272386e-06, "loss": 0.6772, "step": 83690 }, { "epoch": 0.49753018171442837, "grad_norm": 4.88566780090332, "learning_rate": 9.950425602739076e-06, "loss": 0.5753, "step": 83700 }, { "epoch": 0.4975896237910968, "grad_norm": 7.249288558959961, "learning_rate": 9.951614437205764e-06, "loss": 0.6587, "step": 83710 }, { "epoch": 0.49764906586776514, "grad_norm": 6.035197734832764, "learning_rate": 9.952803271672454e-06, "loss": 0.6803, "step": 83720 }, { "epoch": 0.49770850794443355, "grad_norm": 6.3404459953308105, "learning_rate": 9.953992106139142e-06, "loss": 0.6417, "step": 83730 }, { "epoch": 0.4977679500211019, "grad_norm": 6.224413871765137, "learning_rate": 9.95518094060583e-06, "loss": 0.6067, "step": 83740 }, { "epoch": 0.4978273920977703, "grad_norm": 4.87706184387207, "learning_rate": 9.95636977507252e-06, "loss": 0.6683, "step": 83750 }, { "epoch": 0.49788683417443874, "grad_norm": 7.985183238983154, "learning_rate": 9.957558609539208e-06, "loss": 0.6851, "step": 83760 }, { "epoch": 0.4979462762511071, "grad_norm": 6.799784183502197, "learning_rate": 9.958747444005898e-06, "loss": 0.6735, "step": 83770 }, { "epoch": 0.4980057183277755, "grad_norm": 6.595041275024414, "learning_rate": 9.959936278472586e-06, "loss": 0.659, "step": 83780 }, { "epoch": 0.4980651604044439, "grad_norm": 5.146371841430664, "learning_rate": 9.961125112939276e-06, "loss": 0.633, "step": 83790 }, { "epoch": 0.4981246024811123, "grad_norm": 6.262129783630371, "learning_rate": 9.962313947405964e-06, "loss": 0.6366, "step": 83800 }, { "epoch": 0.49818404455778065, "grad_norm": 5.984340667724609, "learning_rate": 9.963502781872653e-06, "loss": 0.6055, "step": 83810 }, { "epoch": 0.49824348663444906, "grad_norm": 4.820476531982422, "learning_rate": 9.964691616339341e-06, "loss": 0.6324, "step": 83820 }, { "epoch": 0.4983029287111175, "grad_norm": 7.213980197906494, "learning_rate": 9.96588045080603e-06, "loss": 0.6879, "step": 83830 }, { "epoch": 0.49836237078778584, "grad_norm": 5.969233989715576, "learning_rate": 9.96706928527272e-06, "loss": 0.6493, "step": 83840 }, { "epoch": 0.49842181286445425, "grad_norm": 4.838981628417969, "learning_rate": 9.968258119739407e-06, "loss": 0.6447, "step": 83850 }, { "epoch": 0.4984812549411226, "grad_norm": 6.087754726409912, "learning_rate": 9.969446954206097e-06, "loss": 0.6401, "step": 83860 }, { "epoch": 0.498540697017791, "grad_norm": 7.446411609649658, "learning_rate": 9.970635788672785e-06, "loss": 0.6501, "step": 83870 }, { "epoch": 0.4986001390944594, "grad_norm": 7.010624408721924, "learning_rate": 9.971824623139475e-06, "loss": 0.6542, "step": 83880 }, { "epoch": 0.4986595811711278, "grad_norm": 8.014859199523926, "learning_rate": 9.973013457606163e-06, "loss": 0.6726, "step": 83890 }, { "epoch": 0.4987190232477962, "grad_norm": 7.974025249481201, "learning_rate": 9.974202292072853e-06, "loss": 0.7073, "step": 83900 }, { "epoch": 0.49877846532446457, "grad_norm": 8.375631332397461, "learning_rate": 9.975391126539543e-06, "loss": 0.7018, "step": 83910 }, { "epoch": 0.498837907401133, "grad_norm": 4.488844394683838, "learning_rate": 9.97657996100623e-06, "loss": 0.6211, "step": 83920 }, { "epoch": 0.49889734947780134, "grad_norm": 7.007473468780518, "learning_rate": 9.977768795472919e-06, "loss": 0.6596, "step": 83930 }, { "epoch": 0.49895679155446976, "grad_norm": 6.686946868896484, "learning_rate": 9.978957629939609e-06, "loss": 0.6519, "step": 83940 }, { "epoch": 0.4990162336311381, "grad_norm": 6.697200298309326, "learning_rate": 9.980146464406297e-06, "loss": 0.683, "step": 83950 }, { "epoch": 0.49907567570780653, "grad_norm": 6.01992654800415, "learning_rate": 9.981335298872986e-06, "loss": 0.5921, "step": 83960 }, { "epoch": 0.4991351177844749, "grad_norm": 6.695648193359375, "learning_rate": 9.982524133339675e-06, "loss": 0.6583, "step": 83970 }, { "epoch": 0.4991945598611433, "grad_norm": 5.625626087188721, "learning_rate": 9.983712967806364e-06, "loss": 0.6674, "step": 83980 }, { "epoch": 0.4992540019378117, "grad_norm": 6.832422733306885, "learning_rate": 9.984901802273052e-06, "loss": 0.676, "step": 83990 }, { "epoch": 0.4993134440144801, "grad_norm": 5.518428802490234, "learning_rate": 9.986090636739742e-06, "loss": 0.5916, "step": 84000 }, { "epoch": 0.4993728860911485, "grad_norm": 7.062250137329102, "learning_rate": 9.98727947120643e-06, "loss": 0.7195, "step": 84010 }, { "epoch": 0.49943232816781685, "grad_norm": 7.486304759979248, "learning_rate": 9.988468305673118e-06, "loss": 0.7071, "step": 84020 }, { "epoch": 0.49949177024448527, "grad_norm": 6.179344177246094, "learning_rate": 9.989657140139808e-06, "loss": 0.7135, "step": 84030 }, { "epoch": 0.4995512123211536, "grad_norm": 6.286109447479248, "learning_rate": 9.990845974606496e-06, "loss": 0.675, "step": 84040 }, { "epoch": 0.49961065439782204, "grad_norm": 5.981088161468506, "learning_rate": 9.992034809073186e-06, "loss": 0.6, "step": 84050 }, { "epoch": 0.49967009647449045, "grad_norm": 6.674267768859863, "learning_rate": 9.993223643539874e-06, "loss": 0.6215, "step": 84060 }, { "epoch": 0.4997295385511588, "grad_norm": 8.295292854309082, "learning_rate": 9.994412478006564e-06, "loss": 0.7209, "step": 84070 }, { "epoch": 0.49978898062782723, "grad_norm": 4.9177327156066895, "learning_rate": 9.995601312473252e-06, "loss": 0.6788, "step": 84080 }, { "epoch": 0.4998484227044956, "grad_norm": 5.504469871520996, "learning_rate": 9.996790146939942e-06, "loss": 0.687, "step": 84090 }, { "epoch": 0.499907864781164, "grad_norm": 5.074760437011719, "learning_rate": 9.99797898140663e-06, "loss": 0.6476, "step": 84100 }, { "epoch": 0.49996730685783236, "grad_norm": 5.71006965637207, "learning_rate": 9.999167815873318e-06, "loss": 0.6471, "step": 84110 }, { "epoch": 0.5000267489345008, "grad_norm": 6.830169677734375, "learning_rate": 9.999999999612524e-06, "loss": 0.6629, "step": 84120 }, { "epoch": 0.5000861910111691, "grad_norm": 6.541669845581055, "learning_rate": 9.999999992724047e-06, "loss": 0.6676, "step": 84130 }, { "epoch": 0.5001456330878375, "grad_norm": 6.390436172485352, "learning_rate": 9.999999977224972e-06, "loss": 0.6426, "step": 84140 }, { "epoch": 0.500205075164506, "grad_norm": 6.244609355926514, "learning_rate": 9.999999953115302e-06, "loss": 0.6632, "step": 84150 }, { "epoch": 0.5002645172411744, "grad_norm": 6.832422733306885, "learning_rate": 9.999999920395036e-06, "loss": 0.6758, "step": 84160 }, { "epoch": 0.5003239593178427, "grad_norm": 6.137463569641113, "learning_rate": 9.999999879064172e-06, "loss": 0.6443, "step": 84170 }, { "epoch": 0.5003834013945111, "grad_norm": 7.370883941650391, "learning_rate": 9.999999829122713e-06, "loss": 0.701, "step": 84180 }, { "epoch": 0.5004428434711795, "grad_norm": 7.023953437805176, "learning_rate": 9.999999770570656e-06, "loss": 0.6299, "step": 84190 }, { "epoch": 0.5005022855478479, "grad_norm": 7.094869613647461, "learning_rate": 9.999999703408004e-06, "loss": 0.6911, "step": 84200 }, { "epoch": 0.5005617276245163, "grad_norm": 7.26815938949585, "learning_rate": 9.999999627634756e-06, "loss": 0.6358, "step": 84210 }, { "epoch": 0.5006211697011846, "grad_norm": 6.761755466461182, "learning_rate": 9.999999543250911e-06, "loss": 0.6201, "step": 84220 }, { "epoch": 0.5006806117778531, "grad_norm": 7.134903907775879, "learning_rate": 9.999999450256472e-06, "loss": 0.6342, "step": 84230 }, { "epoch": 0.5007400538545215, "grad_norm": 5.367661476135254, "learning_rate": 9.999999348651436e-06, "loss": 0.6961, "step": 84240 }, { "epoch": 0.5007994959311899, "grad_norm": 5.848089218139648, "learning_rate": 9.999999238435805e-06, "loss": 0.654, "step": 84250 }, { "epoch": 0.5008589380078582, "grad_norm": 5.8332648277282715, "learning_rate": 9.999999119609578e-06, "loss": 0.6763, "step": 84260 }, { "epoch": 0.5009183800845266, "grad_norm": 6.379673480987549, "learning_rate": 9.999998992172756e-06, "loss": 0.6523, "step": 84270 }, { "epoch": 0.500977822161195, "grad_norm": 6.5390119552612305, "learning_rate": 9.99999885612534e-06, "loss": 0.6688, "step": 84280 }, { "epoch": 0.5010372642378634, "grad_norm": 5.192727088928223, "learning_rate": 9.999998711467328e-06, "loss": 0.6502, "step": 84290 }, { "epoch": 0.5010967063145318, "grad_norm": 6.665623664855957, "learning_rate": 9.999998558198724e-06, "loss": 0.6185, "step": 84300 }, { "epoch": 0.5011561483912002, "grad_norm": 7.4273529052734375, "learning_rate": 9.999998396319525e-06, "loss": 0.6156, "step": 84310 }, { "epoch": 0.5012155904678686, "grad_norm": 5.5824456214904785, "learning_rate": 9.999998225829731e-06, "loss": 0.6802, "step": 84320 }, { "epoch": 0.501275032544537, "grad_norm": 7.657700061798096, "learning_rate": 9.999998046729344e-06, "loss": 0.6228, "step": 84330 }, { "epoch": 0.5013344746212054, "grad_norm": 5.854706287384033, "learning_rate": 9.999997859018364e-06, "loss": 0.6231, "step": 84340 }, { "epoch": 0.5013939166978738, "grad_norm": 7.863148212432861, "learning_rate": 9.999997662696791e-06, "loss": 0.6777, "step": 84350 }, { "epoch": 0.5014533587745421, "grad_norm": 5.276150226593018, "learning_rate": 9.999997457764625e-06, "loss": 0.6515, "step": 84360 }, { "epoch": 0.5015128008512105, "grad_norm": 6.073353290557861, "learning_rate": 9.999997244221868e-06, "loss": 0.6301, "step": 84370 }, { "epoch": 0.5015722429278789, "grad_norm": 6.667793273925781, "learning_rate": 9.999997022068518e-06, "loss": 0.7336, "step": 84380 }, { "epoch": 0.5016316850045474, "grad_norm": 6.3631815910339355, "learning_rate": 9.999996791304578e-06, "loss": 0.6295, "step": 84390 }, { "epoch": 0.5016911270812157, "grad_norm": 4.847299575805664, "learning_rate": 9.999996551930045e-06, "loss": 0.6926, "step": 84400 }, { "epoch": 0.5017505691578841, "grad_norm": 5.385976314544678, "learning_rate": 9.999996303944922e-06, "loss": 0.6491, "step": 84410 }, { "epoch": 0.5018100112345525, "grad_norm": 6.335087776184082, "learning_rate": 9.99999604734921e-06, "loss": 0.6481, "step": 84420 }, { "epoch": 0.5018694533112209, "grad_norm": 5.469869136810303, "learning_rate": 9.999995782142906e-06, "loss": 0.6573, "step": 84430 }, { "epoch": 0.5019288953878893, "grad_norm": 4.748903751373291, "learning_rate": 9.999995508326016e-06, "loss": 0.6586, "step": 84440 }, { "epoch": 0.5019883374645576, "grad_norm": 5.4150471687316895, "learning_rate": 9.999995225898534e-06, "loss": 0.7464, "step": 84450 }, { "epoch": 0.502047779541226, "grad_norm": 6.267858982086182, "learning_rate": 9.999994934860465e-06, "loss": 0.6806, "step": 84460 }, { "epoch": 0.5021072216178945, "grad_norm": 5.730658054351807, "learning_rate": 9.999994635211807e-06, "loss": 0.6456, "step": 84470 }, { "epoch": 0.5021666636945629, "grad_norm": 6.8703179359436035, "learning_rate": 9.999994326952562e-06, "loss": 0.6648, "step": 84480 }, { "epoch": 0.5022261057712312, "grad_norm": 5.4989399909973145, "learning_rate": 9.99999401008273e-06, "loss": 0.7298, "step": 84490 }, { "epoch": 0.5022855478478996, "grad_norm": 6.1941328048706055, "learning_rate": 9.999993684602314e-06, "loss": 0.626, "step": 84500 }, { "epoch": 0.502344989924568, "grad_norm": 6.250699520111084, "learning_rate": 9.99999335051131e-06, "loss": 0.6448, "step": 84510 }, { "epoch": 0.5024044320012364, "grad_norm": 6.9411420822143555, "learning_rate": 9.99999300780972e-06, "loss": 0.6812, "step": 84520 }, { "epoch": 0.5024638740779048, "grad_norm": 6.308449745178223, "learning_rate": 9.999992656497548e-06, "loss": 0.5782, "step": 84530 }, { "epoch": 0.5025233161545731, "grad_norm": 5.790609359741211, "learning_rate": 9.999992296574792e-06, "loss": 0.6197, "step": 84540 }, { "epoch": 0.5025827582312415, "grad_norm": 6.4385085105896, "learning_rate": 9.99999192804145e-06, "loss": 0.6735, "step": 84550 }, { "epoch": 0.50264220030791, "grad_norm": 5.704237937927246, "learning_rate": 9.999991550897528e-06, "loss": 0.6283, "step": 84560 }, { "epoch": 0.5027016423845784, "grad_norm": 6.8090362548828125, "learning_rate": 9.999991165143023e-06, "loss": 0.6646, "step": 84570 }, { "epoch": 0.5027610844612468, "grad_norm": 6.599387168884277, "learning_rate": 9.999990770777937e-06, "loss": 0.6952, "step": 84580 }, { "epoch": 0.5028205265379151, "grad_norm": 5.456277847290039, "learning_rate": 9.999990367802268e-06, "loss": 0.6647, "step": 84590 }, { "epoch": 0.5028799686145835, "grad_norm": 6.143670558929443, "learning_rate": 9.999989956216023e-06, "loss": 0.6796, "step": 84600 }, { "epoch": 0.5029394106912519, "grad_norm": 6.856143474578857, "learning_rate": 9.999989536019196e-06, "loss": 0.6472, "step": 84610 }, { "epoch": 0.5029988527679203, "grad_norm": 6.951711177825928, "learning_rate": 9.999989107211792e-06, "loss": 0.5912, "step": 84620 }, { "epoch": 0.5030582948445886, "grad_norm": 6.393762588500977, "learning_rate": 9.999988669793808e-06, "loss": 0.7586, "step": 84630 }, { "epoch": 0.503117736921257, "grad_norm": 7.559940338134766, "learning_rate": 9.999988223765249e-06, "loss": 0.6206, "step": 84640 }, { "epoch": 0.5031771789979255, "grad_norm": 6.189993381500244, "learning_rate": 9.999987769126111e-06, "loss": 0.6486, "step": 84650 }, { "epoch": 0.5032366210745939, "grad_norm": 5.9595561027526855, "learning_rate": 9.9999873058764e-06, "loss": 0.6485, "step": 84660 }, { "epoch": 0.5032960631512623, "grad_norm": 6.055398464202881, "learning_rate": 9.999986834016113e-06, "loss": 0.632, "step": 84670 }, { "epoch": 0.5033555052279306, "grad_norm": 5.30441951751709, "learning_rate": 9.999986353545253e-06, "loss": 0.6482, "step": 84680 }, { "epoch": 0.503414947304599, "grad_norm": 4.370688438415527, "learning_rate": 9.99998586446382e-06, "loss": 0.6103, "step": 84690 }, { "epoch": 0.5034743893812674, "grad_norm": 6.145939350128174, "learning_rate": 9.999985366771813e-06, "loss": 0.6581, "step": 84700 }, { "epoch": 0.5035338314579358, "grad_norm": 6.859685897827148, "learning_rate": 9.999984860469236e-06, "loss": 0.7066, "step": 84710 }, { "epoch": 0.5035932735346043, "grad_norm": 6.803988456726074, "learning_rate": 9.999984345556088e-06, "loss": 0.6078, "step": 84720 }, { "epoch": 0.5036527156112726, "grad_norm": 6.988133907318115, "learning_rate": 9.999983822032373e-06, "loss": 0.7649, "step": 84730 }, { "epoch": 0.503712157687941, "grad_norm": 5.345570087432861, "learning_rate": 9.999983289898086e-06, "loss": 0.6584, "step": 84740 }, { "epoch": 0.5037715997646094, "grad_norm": 6.370718479156494, "learning_rate": 9.999982749153232e-06, "loss": 0.6737, "step": 84750 }, { "epoch": 0.5038310418412778, "grad_norm": 7.1075053215026855, "learning_rate": 9.999982199797811e-06, "loss": 0.656, "step": 84760 }, { "epoch": 0.5038904839179461, "grad_norm": 5.024484157562256, "learning_rate": 9.999981641831825e-06, "loss": 0.6576, "step": 84770 }, { "epoch": 0.5039499259946145, "grad_norm": 7.43843412399292, "learning_rate": 9.999981075255275e-06, "loss": 0.6411, "step": 84780 }, { "epoch": 0.5040093680712829, "grad_norm": 4.463050365447998, "learning_rate": 9.999980500068158e-06, "loss": 0.5961, "step": 84790 }, { "epoch": 0.5040688101479514, "grad_norm": 6.460302829742432, "learning_rate": 9.99997991627048e-06, "loss": 0.6515, "step": 84800 }, { "epoch": 0.5041282522246198, "grad_norm": 7.236147880554199, "learning_rate": 9.99997932386224e-06, "loss": 0.627, "step": 84810 }, { "epoch": 0.5041876943012881, "grad_norm": 5.924220085144043, "learning_rate": 9.999978722843437e-06, "loss": 0.6388, "step": 84820 }, { "epoch": 0.5042471363779565, "grad_norm": 7.220795631408691, "learning_rate": 9.999978113214075e-06, "loss": 0.6437, "step": 84830 }, { "epoch": 0.5043065784546249, "grad_norm": 6.4942755699157715, "learning_rate": 9.999977494974156e-06, "loss": 0.7299, "step": 84840 }, { "epoch": 0.5043660205312933, "grad_norm": 6.8202972412109375, "learning_rate": 9.999976868123678e-06, "loss": 0.7097, "step": 84850 }, { "epoch": 0.5044254626079616, "grad_norm": 6.672962188720703, "learning_rate": 9.99997623266264e-06, "loss": 0.6953, "step": 84860 }, { "epoch": 0.50448490468463, "grad_norm": 5.023457050323486, "learning_rate": 9.999975588591051e-06, "loss": 0.6349, "step": 84870 }, { "epoch": 0.5045443467612984, "grad_norm": 6.832350730895996, "learning_rate": 9.999974935908906e-06, "loss": 0.7424, "step": 84880 }, { "epoch": 0.5046037888379669, "grad_norm": 5.5989789962768555, "learning_rate": 9.999974274616206e-06, "loss": 0.6108, "step": 84890 }, { "epoch": 0.5046632309146353, "grad_norm": 7.6519341468811035, "learning_rate": 9.999973604712956e-06, "loss": 0.6557, "step": 84900 }, { "epoch": 0.5047226729913036, "grad_norm": 6.596933364868164, "learning_rate": 9.999972926199155e-06, "loss": 0.6512, "step": 84910 }, { "epoch": 0.504782115067972, "grad_norm": 7.6389479637146, "learning_rate": 9.999972239074803e-06, "loss": 0.6322, "step": 84920 }, { "epoch": 0.5048415571446404, "grad_norm": 5.670670509338379, "learning_rate": 9.999971543339902e-06, "loss": 0.609, "step": 84930 }, { "epoch": 0.5049009992213088, "grad_norm": 6.947554588317871, "learning_rate": 9.999970838994453e-06, "loss": 0.6542, "step": 84940 }, { "epoch": 0.5049604412979772, "grad_norm": 7.172328472137451, "learning_rate": 9.999970126038459e-06, "loss": 0.6668, "step": 84950 }, { "epoch": 0.5050198833746455, "grad_norm": 8.269596099853516, "learning_rate": 9.999969404471918e-06, "loss": 0.6442, "step": 84960 }, { "epoch": 0.505079325451314, "grad_norm": 4.764717102050781, "learning_rate": 9.999968674294835e-06, "loss": 0.6468, "step": 84970 }, { "epoch": 0.5051387675279824, "grad_norm": 5.418494701385498, "learning_rate": 9.999967935507208e-06, "loss": 0.6317, "step": 84980 }, { "epoch": 0.5051982096046508, "grad_norm": 6.036594867706299, "learning_rate": 9.99996718810904e-06, "loss": 0.7187, "step": 84990 }, { "epoch": 0.5052576516813191, "grad_norm": 7.075933456420898, "learning_rate": 9.999966432100332e-06, "loss": 0.6875, "step": 85000 }, { "epoch": 0.5053170937579875, "grad_norm": 6.778639793395996, "learning_rate": 9.999965667481085e-06, "loss": 0.7192, "step": 85010 }, { "epoch": 0.5053765358346559, "grad_norm": 6.330985069274902, "learning_rate": 9.999964894251301e-06, "loss": 0.6871, "step": 85020 }, { "epoch": 0.5054359779113243, "grad_norm": 6.724589824676514, "learning_rate": 9.99996411241098e-06, "loss": 0.6436, "step": 85030 }, { "epoch": 0.5054954199879927, "grad_norm": 8.450078964233398, "learning_rate": 9.999963321960125e-06, "loss": 0.6204, "step": 85040 }, { "epoch": 0.505554862064661, "grad_norm": 6.159121036529541, "learning_rate": 9.999962522898736e-06, "loss": 0.6271, "step": 85050 }, { "epoch": 0.5056143041413295, "grad_norm": 6.080120086669922, "learning_rate": 9.999961715226815e-06, "loss": 0.6358, "step": 85060 }, { "epoch": 0.5056737462179979, "grad_norm": 8.276439666748047, "learning_rate": 9.999960898944366e-06, "loss": 0.6188, "step": 85070 }, { "epoch": 0.5057331882946663, "grad_norm": 5.994047164916992, "learning_rate": 9.999960074051384e-06, "loss": 0.6393, "step": 85080 }, { "epoch": 0.5057926303713347, "grad_norm": 5.191788196563721, "learning_rate": 9.999959240547876e-06, "loss": 0.5616, "step": 85090 }, { "epoch": 0.505852072448003, "grad_norm": 5.490097999572754, "learning_rate": 9.999958398433842e-06, "loss": 0.7219, "step": 85100 }, { "epoch": 0.5059115145246714, "grad_norm": 7.077917098999023, "learning_rate": 9.999957547709283e-06, "loss": 0.7105, "step": 85110 }, { "epoch": 0.5059709566013398, "grad_norm": 7.25222110748291, "learning_rate": 9.9999566883742e-06, "loss": 0.6706, "step": 85120 }, { "epoch": 0.5060303986780083, "grad_norm": 5.798532962799072, "learning_rate": 9.999955820428592e-06, "loss": 0.5763, "step": 85130 }, { "epoch": 0.5060898407546766, "grad_norm": 8.008513450622559, "learning_rate": 9.999954943872467e-06, "loss": 0.6174, "step": 85140 }, { "epoch": 0.506149282831345, "grad_norm": 5.624660015106201, "learning_rate": 9.999954058705822e-06, "loss": 0.6598, "step": 85150 }, { "epoch": 0.5062087249080134, "grad_norm": 5.1929497718811035, "learning_rate": 9.999953164928662e-06, "loss": 0.6627, "step": 85160 }, { "epoch": 0.5062681669846818, "grad_norm": 5.393129348754883, "learning_rate": 9.999952262540984e-06, "loss": 0.6604, "step": 85170 }, { "epoch": 0.5063276090613502, "grad_norm": 5.425515174865723, "learning_rate": 9.99995135154279e-06, "loss": 0.6242, "step": 85180 }, { "epoch": 0.5063870511380185, "grad_norm": 6.919704914093018, "learning_rate": 9.999950431934084e-06, "loss": 0.654, "step": 85190 }, { "epoch": 0.5064464932146869, "grad_norm": 6.372419834136963, "learning_rate": 9.999949503714869e-06, "loss": 0.6408, "step": 85200 }, { "epoch": 0.5065059352913553, "grad_norm": 5.875975608825684, "learning_rate": 9.999948566885142e-06, "loss": 0.6626, "step": 85210 }, { "epoch": 0.5065653773680238, "grad_norm": 8.522607803344727, "learning_rate": 9.999947621444908e-06, "loss": 0.6756, "step": 85220 }, { "epoch": 0.5066248194446921, "grad_norm": 6.490500450134277, "learning_rate": 9.999946667394167e-06, "loss": 0.6534, "step": 85230 }, { "epoch": 0.5066842615213605, "grad_norm": 8.57013988494873, "learning_rate": 9.999945704732924e-06, "loss": 0.6493, "step": 85240 }, { "epoch": 0.5067437035980289, "grad_norm": 4.457779407501221, "learning_rate": 9.999944733461175e-06, "loss": 0.7056, "step": 85250 }, { "epoch": 0.5068031456746973, "grad_norm": 7.091638565063477, "learning_rate": 9.999943753578925e-06, "loss": 0.6356, "step": 85260 }, { "epoch": 0.5068625877513657, "grad_norm": 6.397207260131836, "learning_rate": 9.999942765086174e-06, "loss": 0.6576, "step": 85270 }, { "epoch": 0.506922029828034, "grad_norm": 8.451712608337402, "learning_rate": 9.999941767982928e-06, "loss": 0.7092, "step": 85280 }, { "epoch": 0.5069814719047024, "grad_norm": 6.28164529800415, "learning_rate": 9.999940762269183e-06, "loss": 0.6962, "step": 85290 }, { "epoch": 0.5070409139813709, "grad_norm": 5.57074499130249, "learning_rate": 9.999939747944945e-06, "loss": 0.6655, "step": 85300 }, { "epoch": 0.5071003560580393, "grad_norm": 8.149489402770996, "learning_rate": 9.999938725010214e-06, "loss": 0.7038, "step": 85310 }, { "epoch": 0.5071597981347077, "grad_norm": 4.940733432769775, "learning_rate": 9.999937693464991e-06, "loss": 0.622, "step": 85320 }, { "epoch": 0.507219240211376, "grad_norm": 6.047234058380127, "learning_rate": 9.99993665330928e-06, "loss": 0.6371, "step": 85330 }, { "epoch": 0.5072786822880444, "grad_norm": 6.161717891693115, "learning_rate": 9.99993560454308e-06, "loss": 0.6837, "step": 85340 }, { "epoch": 0.5073381243647128, "grad_norm": 6.519249439239502, "learning_rate": 9.999934547166396e-06, "loss": 0.6335, "step": 85350 }, { "epoch": 0.5073975664413812, "grad_norm": 5.563343048095703, "learning_rate": 9.999933481179227e-06, "loss": 0.6759, "step": 85360 }, { "epoch": 0.5074570085180495, "grad_norm": 7.799072265625, "learning_rate": 9.999932406581576e-06, "loss": 0.6712, "step": 85370 }, { "epoch": 0.507516450594718, "grad_norm": 4.649264812469482, "learning_rate": 9.999931323373446e-06, "loss": 0.6524, "step": 85380 }, { "epoch": 0.5075758926713864, "grad_norm": 6.022584915161133, "learning_rate": 9.999930231554838e-06, "loss": 0.591, "step": 85390 }, { "epoch": 0.5076353347480548, "grad_norm": 5.556870460510254, "learning_rate": 9.999929131125752e-06, "loss": 0.6418, "step": 85400 }, { "epoch": 0.5076947768247232, "grad_norm": 7.645210266113281, "learning_rate": 9.999928022086192e-06, "loss": 0.6336, "step": 85410 }, { "epoch": 0.5077542189013915, "grad_norm": 6.549848556518555, "learning_rate": 9.999926904436158e-06, "loss": 0.6737, "step": 85420 }, { "epoch": 0.5078136609780599, "grad_norm": 5.319747447967529, "learning_rate": 9.999925778175654e-06, "loss": 0.6596, "step": 85430 }, { "epoch": 0.5078731030547283, "grad_norm": 4.975977897644043, "learning_rate": 9.999924643304682e-06, "loss": 0.6513, "step": 85440 }, { "epoch": 0.5079325451313967, "grad_norm": 6.121123313903809, "learning_rate": 9.999923499823243e-06, "loss": 0.6403, "step": 85450 }, { "epoch": 0.5079919872080652, "grad_norm": 6.332797050476074, "learning_rate": 9.999922347731339e-06, "loss": 0.6532, "step": 85460 }, { "epoch": 0.5080514292847335, "grad_norm": 8.461273193359375, "learning_rate": 9.999921187028972e-06, "loss": 0.6639, "step": 85470 }, { "epoch": 0.5081108713614019, "grad_norm": 6.666859149932861, "learning_rate": 9.999920017716145e-06, "loss": 0.631, "step": 85480 }, { "epoch": 0.5081703134380703, "grad_norm": 6.73469877243042, "learning_rate": 9.999918839792858e-06, "loss": 0.7489, "step": 85490 }, { "epoch": 0.5082297555147387, "grad_norm": 7.053150653839111, "learning_rate": 9.999917653259114e-06, "loss": 0.6267, "step": 85500 }, { "epoch": 0.508289197591407, "grad_norm": 5.3505473136901855, "learning_rate": 9.999916458114916e-06, "loss": 0.674, "step": 85510 }, { "epoch": 0.5083486396680754, "grad_norm": 5.352789402008057, "learning_rate": 9.999915254360265e-06, "loss": 0.6033, "step": 85520 }, { "epoch": 0.5084080817447438, "grad_norm": 5.498100757598877, "learning_rate": 9.999914041995164e-06, "loss": 0.6435, "step": 85530 }, { "epoch": 0.5084675238214122, "grad_norm": 6.0038743019104, "learning_rate": 9.999912821019613e-06, "loss": 0.7006, "step": 85540 }, { "epoch": 0.5085269658980807, "grad_norm": 6.223905563354492, "learning_rate": 9.999911591433617e-06, "loss": 0.6383, "step": 85550 }, { "epoch": 0.508586407974749, "grad_norm": 6.055228233337402, "learning_rate": 9.999910353237177e-06, "loss": 0.6432, "step": 85560 }, { "epoch": 0.5086458500514174, "grad_norm": 5.625679969787598, "learning_rate": 9.999909106430293e-06, "loss": 0.6507, "step": 85570 }, { "epoch": 0.5087052921280858, "grad_norm": 6.315508842468262, "learning_rate": 9.999907851012972e-06, "loss": 0.7485, "step": 85580 }, { "epoch": 0.5087647342047542, "grad_norm": 5.157961368560791, "learning_rate": 9.999906586985208e-06, "loss": 0.6316, "step": 85590 }, { "epoch": 0.5088241762814225, "grad_norm": 5.947519302368164, "learning_rate": 9.999905314347013e-06, "loss": 0.6159, "step": 85600 }, { "epoch": 0.5088836183580909, "grad_norm": 8.58438491821289, "learning_rate": 9.999904033098381e-06, "loss": 0.6669, "step": 85610 }, { "epoch": 0.5089430604347593, "grad_norm": 7.871592998504639, "learning_rate": 9.99990274323932e-06, "loss": 0.693, "step": 85620 }, { "epoch": 0.5090025025114278, "grad_norm": 5.395000457763672, "learning_rate": 9.999901444769831e-06, "loss": 0.6024, "step": 85630 }, { "epoch": 0.5090619445880962, "grad_norm": 7.282154083251953, "learning_rate": 9.999900137689912e-06, "loss": 0.648, "step": 85640 }, { "epoch": 0.5091213866647645, "grad_norm": 6.240625381469727, "learning_rate": 9.99989882199957e-06, "loss": 0.6646, "step": 85650 }, { "epoch": 0.5091808287414329, "grad_norm": 7.3776116371154785, "learning_rate": 9.999897497698805e-06, "loss": 0.6222, "step": 85660 }, { "epoch": 0.5092402708181013, "grad_norm": 6.388224124908447, "learning_rate": 9.999896164787622e-06, "loss": 0.6826, "step": 85670 }, { "epoch": 0.5092997128947697, "grad_norm": 5.520059108734131, "learning_rate": 9.999894823266018e-06, "loss": 0.6339, "step": 85680 }, { "epoch": 0.5093591549714381, "grad_norm": 6.702661037445068, "learning_rate": 9.999893473134e-06, "loss": 0.6854, "step": 85690 }, { "epoch": 0.5094185970481064, "grad_norm": 4.43917989730835, "learning_rate": 9.99989211439157e-06, "loss": 0.6225, "step": 85700 }, { "epoch": 0.5094780391247749, "grad_norm": 5.725971698760986, "learning_rate": 9.999890747038727e-06, "loss": 0.6208, "step": 85710 }, { "epoch": 0.5095374812014433, "grad_norm": 5.140366077423096, "learning_rate": 9.999889371075477e-06, "loss": 0.6834, "step": 85720 }, { "epoch": 0.5095969232781117, "grad_norm": 7.427639961242676, "learning_rate": 9.999887986501821e-06, "loss": 0.7196, "step": 85730 }, { "epoch": 0.50965636535478, "grad_norm": 6.066412448883057, "learning_rate": 9.99988659331776e-06, "loss": 0.6837, "step": 85740 }, { "epoch": 0.5097158074314484, "grad_norm": 5.126642227172852, "learning_rate": 9.9998851915233e-06, "loss": 0.6605, "step": 85750 }, { "epoch": 0.5097752495081168, "grad_norm": 7.112844944000244, "learning_rate": 9.99988378111844e-06, "loss": 0.666, "step": 85760 }, { "epoch": 0.5098346915847852, "grad_norm": 8.218783378601074, "learning_rate": 9.999882362103183e-06, "loss": 0.7371, "step": 85770 }, { "epoch": 0.5098941336614536, "grad_norm": 5.1575164794921875, "learning_rate": 9.999880934477533e-06, "loss": 0.612, "step": 85780 }, { "epoch": 0.509953575738122, "grad_norm": 8.115638732910156, "learning_rate": 9.99987949824149e-06, "loss": 0.7037, "step": 85790 }, { "epoch": 0.5100130178147904, "grad_norm": 4.947749614715576, "learning_rate": 9.999878053395058e-06, "loss": 0.6258, "step": 85800 }, { "epoch": 0.5100724598914588, "grad_norm": 6.7490105628967285, "learning_rate": 9.99987659993824e-06, "loss": 0.7166, "step": 85810 }, { "epoch": 0.5101319019681272, "grad_norm": 7.509594917297363, "learning_rate": 9.999875137871038e-06, "loss": 0.6741, "step": 85820 }, { "epoch": 0.5101913440447956, "grad_norm": 12.015443801879883, "learning_rate": 9.999873667193456e-06, "loss": 0.6847, "step": 85830 }, { "epoch": 0.5102507861214639, "grad_norm": 5.6098737716674805, "learning_rate": 9.999872187905493e-06, "loss": 0.6645, "step": 85840 }, { "epoch": 0.5103102281981323, "grad_norm": 6.93056583404541, "learning_rate": 9.999870700007156e-06, "loss": 0.6665, "step": 85850 }, { "epoch": 0.5103696702748007, "grad_norm": 4.958549499511719, "learning_rate": 9.999869203498442e-06, "loss": 0.6474, "step": 85860 }, { "epoch": 0.5104291123514691, "grad_norm": 6.381000995635986, "learning_rate": 9.999867698379358e-06, "loss": 0.6644, "step": 85870 }, { "epoch": 0.5104885544281375, "grad_norm": 7.396195888519287, "learning_rate": 9.999866184649904e-06, "loss": 0.6641, "step": 85880 }, { "epoch": 0.5105479965048059, "grad_norm": 7.600681304931641, "learning_rate": 9.999864662310085e-06, "loss": 0.6505, "step": 85890 }, { "epoch": 0.5106074385814743, "grad_norm": 5.563087463378906, "learning_rate": 9.999863131359902e-06, "loss": 0.6492, "step": 85900 }, { "epoch": 0.5106668806581427, "grad_norm": 7.077616214752197, "learning_rate": 9.999861591799358e-06, "loss": 0.6957, "step": 85910 }, { "epoch": 0.5107263227348111, "grad_norm": 4.640929222106934, "learning_rate": 9.999860043628458e-06, "loss": 0.6767, "step": 85920 }, { "epoch": 0.5107857648114794, "grad_norm": 8.828850746154785, "learning_rate": 9.9998584868472e-06, "loss": 0.7302, "step": 85930 }, { "epoch": 0.5108452068881478, "grad_norm": 7.372699737548828, "learning_rate": 9.999856921455588e-06, "loss": 0.6308, "step": 85940 }, { "epoch": 0.5109046489648162, "grad_norm": 5.797974586486816, "learning_rate": 9.999855347453629e-06, "loss": 0.638, "step": 85950 }, { "epoch": 0.5109640910414847, "grad_norm": 5.653578281402588, "learning_rate": 9.99985376484132e-06, "loss": 0.648, "step": 85960 }, { "epoch": 0.511023533118153, "grad_norm": 5.543034553527832, "learning_rate": 9.999852173618668e-06, "loss": 0.6584, "step": 85970 }, { "epoch": 0.5110829751948214, "grad_norm": 6.244519233703613, "learning_rate": 9.999850573785674e-06, "loss": 0.6308, "step": 85980 }, { "epoch": 0.5111424172714898, "grad_norm": 8.951181411743164, "learning_rate": 9.99984896534234e-06, "loss": 0.6049, "step": 85990 }, { "epoch": 0.5112018593481582, "grad_norm": 6.160316467285156, "learning_rate": 9.99984734828867e-06, "loss": 0.6912, "step": 86000 }, { "epoch": 0.5112613014248266, "grad_norm": 6.191921710968018, "learning_rate": 9.999845722624665e-06, "loss": 0.6065, "step": 86010 }, { "epoch": 0.5113207435014949, "grad_norm": 5.968383312225342, "learning_rate": 9.99984408835033e-06, "loss": 0.6147, "step": 86020 }, { "epoch": 0.5113801855781633, "grad_norm": 6.263051986694336, "learning_rate": 9.999842445465666e-06, "loss": 0.6892, "step": 86030 }, { "epoch": 0.5114396276548318, "grad_norm": 5.313663482666016, "learning_rate": 9.999840793970678e-06, "loss": 0.7253, "step": 86040 }, { "epoch": 0.5114990697315002, "grad_norm": 7.921733856201172, "learning_rate": 9.999839133865369e-06, "loss": 0.7531, "step": 86050 }, { "epoch": 0.5115585118081686, "grad_norm": 5.273768424987793, "learning_rate": 9.999837465149737e-06, "loss": 0.6848, "step": 86060 }, { "epoch": 0.5116179538848369, "grad_norm": 8.796849250793457, "learning_rate": 9.99983578782379e-06, "loss": 0.6174, "step": 86070 }, { "epoch": 0.5116773959615053, "grad_norm": 7.077398300170898, "learning_rate": 9.999834101887528e-06, "loss": 0.6342, "step": 86080 }, { "epoch": 0.5117368380381737, "grad_norm": 7.76985502243042, "learning_rate": 9.999832407340958e-06, "loss": 0.6966, "step": 86090 }, { "epoch": 0.5117962801148421, "grad_norm": 4.887265205383301, "learning_rate": 9.999830704184077e-06, "loss": 0.6547, "step": 86100 }, { "epoch": 0.5118557221915104, "grad_norm": 7.875155925750732, "learning_rate": 9.999828992416893e-06, "loss": 0.6742, "step": 86110 }, { "epoch": 0.5119151642681788, "grad_norm": 6.692873001098633, "learning_rate": 9.999827272039406e-06, "loss": 0.6671, "step": 86120 }, { "epoch": 0.5119746063448473, "grad_norm": 6.868161678314209, "learning_rate": 9.99982554305162e-06, "loss": 0.7129, "step": 86130 }, { "epoch": 0.5120340484215157, "grad_norm": 7.201001167297363, "learning_rate": 9.999823805453538e-06, "loss": 0.6722, "step": 86140 }, { "epoch": 0.5120934904981841, "grad_norm": 6.311941623687744, "learning_rate": 9.999822059245163e-06, "loss": 0.7306, "step": 86150 }, { "epoch": 0.5121529325748524, "grad_norm": 6.075799465179443, "learning_rate": 9.999820304426498e-06, "loss": 0.5783, "step": 86160 }, { "epoch": 0.5122123746515208, "grad_norm": 7.182110786437988, "learning_rate": 9.999818540997544e-06, "loss": 0.6634, "step": 86170 }, { "epoch": 0.5122718167281892, "grad_norm": 5.926368236541748, "learning_rate": 9.999816768958308e-06, "loss": 0.6933, "step": 86180 }, { "epoch": 0.5123312588048576, "grad_norm": 6.404565334320068, "learning_rate": 9.999814988308789e-06, "loss": 0.7093, "step": 86190 }, { "epoch": 0.512390700881526, "grad_norm": 5.24104118347168, "learning_rate": 9.999813199048995e-06, "loss": 0.7123, "step": 86200 }, { "epoch": 0.5124501429581944, "grad_norm": 7.199121952056885, "learning_rate": 9.999811401178923e-06, "loss": 0.7176, "step": 86210 }, { "epoch": 0.5125095850348628, "grad_norm": 5.308219909667969, "learning_rate": 9.999809594698581e-06, "loss": 0.6978, "step": 86220 }, { "epoch": 0.5125690271115312, "grad_norm": 8.085484504699707, "learning_rate": 9.99980777960797e-06, "loss": 0.6979, "step": 86230 }, { "epoch": 0.5126284691881996, "grad_norm": 8.398662567138672, "learning_rate": 9.999805955907094e-06, "loss": 0.6939, "step": 86240 }, { "epoch": 0.5126879112648679, "grad_norm": 5.790586948394775, "learning_rate": 9.999804123595954e-06, "loss": 0.663, "step": 86250 }, { "epoch": 0.5127473533415363, "grad_norm": 6.102132797241211, "learning_rate": 9.999802282674555e-06, "loss": 0.617, "step": 86260 }, { "epoch": 0.5128067954182047, "grad_norm": 6.016666889190674, "learning_rate": 9.999800433142902e-06, "loss": 0.6804, "step": 86270 }, { "epoch": 0.5128662374948731, "grad_norm": 5.819239139556885, "learning_rate": 9.999798575000994e-06, "loss": 0.6998, "step": 86280 }, { "epoch": 0.5129256795715416, "grad_norm": 4.795059680938721, "learning_rate": 9.999796708248836e-06, "loss": 0.6459, "step": 86290 }, { "epoch": 0.5129851216482099, "grad_norm": 6.3840131759643555, "learning_rate": 9.999794832886434e-06, "loss": 0.6717, "step": 86300 }, { "epoch": 0.5130445637248783, "grad_norm": 5.403756141662598, "learning_rate": 9.999792948913787e-06, "loss": 0.6768, "step": 86310 }, { "epoch": 0.5131040058015467, "grad_norm": 5.383014678955078, "learning_rate": 9.999791056330899e-06, "loss": 0.7336, "step": 86320 }, { "epoch": 0.5131634478782151, "grad_norm": 6.256131172180176, "learning_rate": 9.999789155137776e-06, "loss": 0.6274, "step": 86330 }, { "epoch": 0.5132228899548834, "grad_norm": 6.934757709503174, "learning_rate": 9.999787245334418e-06, "loss": 0.6833, "step": 86340 }, { "epoch": 0.5132823320315518, "grad_norm": 6.36164665222168, "learning_rate": 9.99978532692083e-06, "loss": 0.6575, "step": 86350 }, { "epoch": 0.5133417741082202, "grad_norm": 4.84840726852417, "learning_rate": 9.999783399897018e-06, "loss": 0.6442, "step": 86360 }, { "epoch": 0.5134012161848887, "grad_norm": 8.245545387268066, "learning_rate": 9.999781464262978e-06, "loss": 0.7466, "step": 86370 }, { "epoch": 0.5134606582615571, "grad_norm": 7.219018459320068, "learning_rate": 9.999779520018722e-06, "loss": 0.6512, "step": 86380 }, { "epoch": 0.5135201003382254, "grad_norm": 5.948031902313232, "learning_rate": 9.999777567164246e-06, "loss": 0.6811, "step": 86390 }, { "epoch": 0.5135795424148938, "grad_norm": 5.883020877838135, "learning_rate": 9.999775605699558e-06, "loss": 0.7037, "step": 86400 }, { "epoch": 0.5136389844915622, "grad_norm": 5.509884834289551, "learning_rate": 9.999773635624659e-06, "loss": 0.6376, "step": 86410 }, { "epoch": 0.5136984265682306, "grad_norm": 6.756677150726318, "learning_rate": 9.999771656939554e-06, "loss": 0.6938, "step": 86420 }, { "epoch": 0.513757868644899, "grad_norm": 7.129633903503418, "learning_rate": 9.999769669644245e-06, "loss": 0.6693, "step": 86430 }, { "epoch": 0.5138173107215673, "grad_norm": 5.952179908752441, "learning_rate": 9.999767673738736e-06, "loss": 0.6875, "step": 86440 }, { "epoch": 0.5138767527982357, "grad_norm": 6.4605817794799805, "learning_rate": 9.999765669223032e-06, "loss": 0.6338, "step": 86450 }, { "epoch": 0.5139361948749042, "grad_norm": 4.6068596839904785, "learning_rate": 9.999763656097132e-06, "loss": 0.5995, "step": 86460 }, { "epoch": 0.5139956369515726, "grad_norm": 7.448176860809326, "learning_rate": 9.999761634361045e-06, "loss": 0.714, "step": 86470 }, { "epoch": 0.5140550790282409, "grad_norm": 6.102273464202881, "learning_rate": 9.999759604014771e-06, "loss": 0.6357, "step": 86480 }, { "epoch": 0.5141145211049093, "grad_norm": 6.515843391418457, "learning_rate": 9.999757565058314e-06, "loss": 0.6538, "step": 86490 }, { "epoch": 0.5141739631815777, "grad_norm": 4.669656276702881, "learning_rate": 9.999755517491678e-06, "loss": 0.64, "step": 86500 }, { "epoch": 0.5142334052582461, "grad_norm": 5.822813987731934, "learning_rate": 9.999753461314867e-06, "loss": 0.6535, "step": 86510 }, { "epoch": 0.5142928473349145, "grad_norm": 5.752321720123291, "learning_rate": 9.999751396527884e-06, "loss": 0.5959, "step": 86520 }, { "epoch": 0.5143522894115828, "grad_norm": 5.693675994873047, "learning_rate": 9.999749323130732e-06, "loss": 0.599, "step": 86530 }, { "epoch": 0.5144117314882513, "grad_norm": 6.565455913543701, "learning_rate": 9.999747241123416e-06, "loss": 0.6268, "step": 86540 }, { "epoch": 0.5144711735649197, "grad_norm": 5.864940166473389, "learning_rate": 9.999745150505939e-06, "loss": 0.6404, "step": 86550 }, { "epoch": 0.5145306156415881, "grad_norm": 6.200035095214844, "learning_rate": 9.999743051278303e-06, "loss": 0.657, "step": 86560 }, { "epoch": 0.5145900577182565, "grad_norm": 6.450654983520508, "learning_rate": 9.999740943440512e-06, "loss": 0.6725, "step": 86570 }, { "epoch": 0.5146494997949248, "grad_norm": 5.73250150680542, "learning_rate": 9.999738826992574e-06, "loss": 0.7015, "step": 86580 }, { "epoch": 0.5147089418715932, "grad_norm": 6.21470832824707, "learning_rate": 9.999736701934486e-06, "loss": 0.7378, "step": 86590 }, { "epoch": 0.5147683839482616, "grad_norm": 6.777984619140625, "learning_rate": 9.999734568266256e-06, "loss": 0.7079, "step": 86600 }, { "epoch": 0.51482782602493, "grad_norm": 5.8780598640441895, "learning_rate": 9.999732425987886e-06, "loss": 0.6333, "step": 86610 }, { "epoch": 0.5148872681015983, "grad_norm": 5.352272987365723, "learning_rate": 9.999730275099382e-06, "loss": 0.6393, "step": 86620 }, { "epoch": 0.5149467101782668, "grad_norm": 6.194581985473633, "learning_rate": 9.999728115600744e-06, "loss": 0.5958, "step": 86630 }, { "epoch": 0.5150061522549352, "grad_norm": 4.943586826324463, "learning_rate": 9.999725947491978e-06, "loss": 0.676, "step": 86640 }, { "epoch": 0.5150655943316036, "grad_norm": 6.69726037979126, "learning_rate": 9.999723770773087e-06, "loss": 0.6817, "step": 86650 }, { "epoch": 0.515125036408272, "grad_norm": 5.788121700286865, "learning_rate": 9.999721585444075e-06, "loss": 0.6726, "step": 86660 }, { "epoch": 0.5151844784849403, "grad_norm": 7.204792022705078, "learning_rate": 9.999719391504948e-06, "loss": 0.6285, "step": 86670 }, { "epoch": 0.5152439205616087, "grad_norm": 5.377730846405029, "learning_rate": 9.999717188955705e-06, "loss": 0.6631, "step": 86680 }, { "epoch": 0.5153033626382771, "grad_norm": 5.121041774749756, "learning_rate": 9.999714977796354e-06, "loss": 0.6165, "step": 86690 }, { "epoch": 0.5153628047149456, "grad_norm": 6.78948974609375, "learning_rate": 9.999712758026896e-06, "loss": 0.7134, "step": 86700 }, { "epoch": 0.5154222467916139, "grad_norm": 7.690204620361328, "learning_rate": 9.999710529647338e-06, "loss": 0.6829, "step": 86710 }, { "epoch": 0.5154816888682823, "grad_norm": 6.768449783325195, "learning_rate": 9.99970829265768e-06, "loss": 0.6724, "step": 86720 }, { "epoch": 0.5155411309449507, "grad_norm": 5.983243942260742, "learning_rate": 9.999706047057928e-06, "loss": 0.6319, "step": 86730 }, { "epoch": 0.5156005730216191, "grad_norm": 7.171071529388428, "learning_rate": 9.999703792848087e-06, "loss": 0.6546, "step": 86740 }, { "epoch": 0.5156600150982875, "grad_norm": 5.575808048248291, "learning_rate": 9.99970153002816e-06, "loss": 0.6273, "step": 86750 }, { "epoch": 0.5157194571749558, "grad_norm": 5.655938148498535, "learning_rate": 9.999699258598148e-06, "loss": 0.6478, "step": 86760 }, { "epoch": 0.5157788992516242, "grad_norm": 5.220553398132324, "learning_rate": 9.999696978558057e-06, "loss": 0.6292, "step": 86770 }, { "epoch": 0.5158383413282926, "grad_norm": 5.9129157066345215, "learning_rate": 9.999694689907895e-06, "loss": 0.6664, "step": 86780 }, { "epoch": 0.5158977834049611, "grad_norm": 8.385555267333984, "learning_rate": 9.999692392647659e-06, "loss": 0.6754, "step": 86790 }, { "epoch": 0.5159572254816295, "grad_norm": 6.944606781005859, "learning_rate": 9.999690086777358e-06, "loss": 0.646, "step": 86800 }, { "epoch": 0.5160166675582978, "grad_norm": 7.523311614990234, "learning_rate": 9.999687772296994e-06, "loss": 0.661, "step": 86810 }, { "epoch": 0.5160761096349662, "grad_norm": 5.861142158508301, "learning_rate": 9.999685449206569e-06, "loss": 0.6229, "step": 86820 }, { "epoch": 0.5161355517116346, "grad_norm": 7.417023181915283, "learning_rate": 9.99968311750609e-06, "loss": 0.583, "step": 86830 }, { "epoch": 0.516194993788303, "grad_norm": 6.6364827156066895, "learning_rate": 9.99968077719556e-06, "loss": 0.6295, "step": 86840 }, { "epoch": 0.5162544358649713, "grad_norm": 4.3966755867004395, "learning_rate": 9.999678428274984e-06, "loss": 0.6351, "step": 86850 }, { "epoch": 0.5163138779416397, "grad_norm": 4.967351913452148, "learning_rate": 9.999676070744366e-06, "loss": 0.6071, "step": 86860 }, { "epoch": 0.5163733200183082, "grad_norm": 6.4600982666015625, "learning_rate": 9.999673704603708e-06, "loss": 0.7084, "step": 86870 }, { "epoch": 0.5164327620949766, "grad_norm": 5.674574851989746, "learning_rate": 9.999671329853015e-06, "loss": 0.7146, "step": 86880 }, { "epoch": 0.516492204171645, "grad_norm": 6.172444820404053, "learning_rate": 9.999668946492292e-06, "loss": 0.6488, "step": 86890 }, { "epoch": 0.5165516462483133, "grad_norm": 4.783778667449951, "learning_rate": 9.99966655452154e-06, "loss": 0.5912, "step": 86900 }, { "epoch": 0.5166110883249817, "grad_norm": 5.822784423828125, "learning_rate": 9.999664153940769e-06, "loss": 0.7294, "step": 86910 }, { "epoch": 0.5166705304016501, "grad_norm": 6.981160640716553, "learning_rate": 9.99966174474998e-06, "loss": 0.6508, "step": 86920 }, { "epoch": 0.5167299724783185, "grad_norm": 7.780837059020996, "learning_rate": 9.999659326949176e-06, "loss": 0.6566, "step": 86930 }, { "epoch": 0.516789414554987, "grad_norm": 6.5842084884643555, "learning_rate": 9.999656900538362e-06, "loss": 0.6417, "step": 86940 }, { "epoch": 0.5168488566316553, "grad_norm": 7.091904640197754, "learning_rate": 9.99965446551754e-06, "loss": 0.6875, "step": 86950 }, { "epoch": 0.5169082987083237, "grad_norm": 7.341227054595947, "learning_rate": 9.999652021886719e-06, "loss": 0.6925, "step": 86960 }, { "epoch": 0.5169677407849921, "grad_norm": 8.053455352783203, "learning_rate": 9.9996495696459e-06, "loss": 0.7081, "step": 86970 }, { "epoch": 0.5170271828616605, "grad_norm": 7.172236919403076, "learning_rate": 9.999647108795089e-06, "loss": 0.6498, "step": 86980 }, { "epoch": 0.5170866249383288, "grad_norm": 5.472411155700684, "learning_rate": 9.999644639334289e-06, "loss": 0.6745, "step": 86990 }, { "epoch": 0.5171460670149972, "grad_norm": 8.464822769165039, "learning_rate": 9.999642161263503e-06, "loss": 0.6396, "step": 87000 }, { "epoch": 0.5172055090916656, "grad_norm": 5.953294277191162, "learning_rate": 9.999639674582738e-06, "loss": 0.6378, "step": 87010 }, { "epoch": 0.517264951168334, "grad_norm": 6.977242469787598, "learning_rate": 9.999637179291994e-06, "loss": 0.6874, "step": 87020 }, { "epoch": 0.5173243932450025, "grad_norm": 5.769624710083008, "learning_rate": 9.999634675391281e-06, "loss": 0.6415, "step": 87030 }, { "epoch": 0.5173838353216708, "grad_norm": 7.996596336364746, "learning_rate": 9.9996321628806e-06, "loss": 0.6659, "step": 87040 }, { "epoch": 0.5174432773983392, "grad_norm": 5.817689418792725, "learning_rate": 9.999629641759956e-06, "loss": 0.633, "step": 87050 }, { "epoch": 0.5175027194750076, "grad_norm": 4.980345726013184, "learning_rate": 9.999627112029352e-06, "loss": 0.6147, "step": 87060 }, { "epoch": 0.517562161551676, "grad_norm": 7.497429847717285, "learning_rate": 9.999624573688795e-06, "loss": 0.7386, "step": 87070 }, { "epoch": 0.5176216036283443, "grad_norm": 7.696252346038818, "learning_rate": 9.99962202673829e-06, "loss": 0.6815, "step": 87080 }, { "epoch": 0.5176810457050127, "grad_norm": 6.373612403869629, "learning_rate": 9.999619471177835e-06, "loss": 0.6288, "step": 87090 }, { "epoch": 0.5177404877816811, "grad_norm": 5.975512981414795, "learning_rate": 9.99961690700744e-06, "loss": 0.6833, "step": 87100 }, { "epoch": 0.5177999298583496, "grad_norm": 5.720632553100586, "learning_rate": 9.99961433422711e-06, "loss": 0.6361, "step": 87110 }, { "epoch": 0.517859371935018, "grad_norm": 6.5417327880859375, "learning_rate": 9.999611752836846e-06, "loss": 0.6162, "step": 87120 }, { "epoch": 0.5179188140116863, "grad_norm": 6.75970458984375, "learning_rate": 9.999609162836654e-06, "loss": 0.6238, "step": 87130 }, { "epoch": 0.5179782560883547, "grad_norm": 6.400010585784912, "learning_rate": 9.999606564226539e-06, "loss": 0.6644, "step": 87140 }, { "epoch": 0.5180376981650231, "grad_norm": 6.62124490737915, "learning_rate": 9.999603957006506e-06, "loss": 0.699, "step": 87150 }, { "epoch": 0.5180971402416915, "grad_norm": 7.352272033691406, "learning_rate": 9.999601341176558e-06, "loss": 0.6617, "step": 87160 }, { "epoch": 0.5181565823183599, "grad_norm": 6.444881439208984, "learning_rate": 9.999598716736698e-06, "loss": 0.5813, "step": 87170 }, { "epoch": 0.5182160243950282, "grad_norm": 6.548019886016846, "learning_rate": 9.999596083686934e-06, "loss": 0.6839, "step": 87180 }, { "epoch": 0.5182754664716966, "grad_norm": 6.5971550941467285, "learning_rate": 9.999593442027266e-06, "loss": 0.673, "step": 87190 }, { "epoch": 0.5183349085483651, "grad_norm": 7.133932113647461, "learning_rate": 9.999590791757706e-06, "loss": 0.6546, "step": 87200 }, { "epoch": 0.5183943506250335, "grad_norm": 5.355165958404541, "learning_rate": 9.999588132878252e-06, "loss": 0.6798, "step": 87210 }, { "epoch": 0.5184537927017018, "grad_norm": 5.541378498077393, "learning_rate": 9.999585465388911e-06, "loss": 0.6978, "step": 87220 }, { "epoch": 0.5185132347783702, "grad_norm": 6.997859001159668, "learning_rate": 9.999582789289689e-06, "loss": 0.6689, "step": 87230 }, { "epoch": 0.5185726768550386, "grad_norm": 6.042844295501709, "learning_rate": 9.999580104580585e-06, "loss": 0.6794, "step": 87240 }, { "epoch": 0.518632118931707, "grad_norm": 8.259515762329102, "learning_rate": 9.99957741126161e-06, "loss": 0.6679, "step": 87250 }, { "epoch": 0.5186915610083754, "grad_norm": 5.40059232711792, "learning_rate": 9.999574709332767e-06, "loss": 0.6866, "step": 87260 }, { "epoch": 0.5187510030850437, "grad_norm": 7.798188209533691, "learning_rate": 9.999571998794057e-06, "loss": 0.6263, "step": 87270 }, { "epoch": 0.5188104451617122, "grad_norm": 6.630947589874268, "learning_rate": 9.999569279645488e-06, "loss": 0.6523, "step": 87280 }, { "epoch": 0.5188698872383806, "grad_norm": 5.22068452835083, "learning_rate": 9.999566551887068e-06, "loss": 0.7024, "step": 87290 }, { "epoch": 0.518929329315049, "grad_norm": 6.835229873657227, "learning_rate": 9.999563815518794e-06, "loss": 0.6987, "step": 87300 }, { "epoch": 0.5189887713917174, "grad_norm": 6.635012149810791, "learning_rate": 9.999561070540675e-06, "loss": 0.6467, "step": 87310 }, { "epoch": 0.5190482134683857, "grad_norm": 6.322562217712402, "learning_rate": 9.999558316952717e-06, "loss": 0.6812, "step": 87320 }, { "epoch": 0.5191076555450541, "grad_norm": 8.585686683654785, "learning_rate": 9.999555554754922e-06, "loss": 0.6564, "step": 87330 }, { "epoch": 0.5191670976217225, "grad_norm": 5.7673115730285645, "learning_rate": 9.999552783947296e-06, "loss": 0.6954, "step": 87340 }, { "epoch": 0.5192265396983909, "grad_norm": 7.043034076690674, "learning_rate": 9.999550004529844e-06, "loss": 0.6243, "step": 87350 }, { "epoch": 0.5192859817750592, "grad_norm": 5.875267505645752, "learning_rate": 9.999547216502568e-06, "loss": 0.6268, "step": 87360 }, { "epoch": 0.5193454238517277, "grad_norm": 4.623525142669678, "learning_rate": 9.999544419865477e-06, "loss": 0.6476, "step": 87370 }, { "epoch": 0.5194048659283961, "grad_norm": 7.536306381225586, "learning_rate": 9.999541614618576e-06, "loss": 0.6532, "step": 87380 }, { "epoch": 0.5194643080050645, "grad_norm": 6.851833820343018, "learning_rate": 9.999538800761864e-06, "loss": 0.6833, "step": 87390 }, { "epoch": 0.5195237500817329, "grad_norm": 7.552525520324707, "learning_rate": 9.999535978295351e-06, "loss": 0.6808, "step": 87400 }, { "epoch": 0.5195831921584012, "grad_norm": 6.752445697784424, "learning_rate": 9.99953314721904e-06, "loss": 0.6565, "step": 87410 }, { "epoch": 0.5196426342350696, "grad_norm": 6.418951988220215, "learning_rate": 9.999530307532938e-06, "loss": 0.6276, "step": 87420 }, { "epoch": 0.519702076311738, "grad_norm": 6.836908340454102, "learning_rate": 9.999527459237048e-06, "loss": 0.7305, "step": 87430 }, { "epoch": 0.5197615183884065, "grad_norm": 4.952465534210205, "learning_rate": 9.999524602331375e-06, "loss": 0.6901, "step": 87440 }, { "epoch": 0.5198209604650748, "grad_norm": 6.493949890136719, "learning_rate": 9.999521736815925e-06, "loss": 0.6467, "step": 87450 }, { "epoch": 0.5198804025417432, "grad_norm": 5.429200172424316, "learning_rate": 9.999518862690701e-06, "loss": 0.7023, "step": 87460 }, { "epoch": 0.5199398446184116, "grad_norm": 5.854303359985352, "learning_rate": 9.999515979955707e-06, "loss": 0.6428, "step": 87470 }, { "epoch": 0.51999928669508, "grad_norm": 4.83526086807251, "learning_rate": 9.999513088610953e-06, "loss": 0.6854, "step": 87480 }, { "epoch": 0.5200587287717484, "grad_norm": 5.772276878356934, "learning_rate": 9.99951018865644e-06, "loss": 0.6376, "step": 87490 }, { "epoch": 0.5201181708484167, "grad_norm": 6.0425872802734375, "learning_rate": 9.999507280092173e-06, "loss": 0.6789, "step": 87500 }, { "epoch": 0.5201776129250851, "grad_norm": 6.350477695465088, "learning_rate": 9.999504362918158e-06, "loss": 0.6629, "step": 87510 }, { "epoch": 0.5202370550017535, "grad_norm": 5.259464263916016, "learning_rate": 9.999501437134401e-06, "loss": 0.7166, "step": 87520 }, { "epoch": 0.520296497078422, "grad_norm": 6.786543846130371, "learning_rate": 9.999498502740906e-06, "loss": 0.7055, "step": 87530 }, { "epoch": 0.5203559391550904, "grad_norm": 5.817312717437744, "learning_rate": 9.999495559737677e-06, "loss": 0.6577, "step": 87540 }, { "epoch": 0.5204153812317587, "grad_norm": 7.376838684082031, "learning_rate": 9.99949260812472e-06, "loss": 0.6498, "step": 87550 }, { "epoch": 0.5204748233084271, "grad_norm": 5.209750652313232, "learning_rate": 9.99948964790204e-06, "loss": 0.6107, "step": 87560 }, { "epoch": 0.5205342653850955, "grad_norm": 6.580801963806152, "learning_rate": 9.999486679069646e-06, "loss": 0.6654, "step": 87570 }, { "epoch": 0.5205937074617639, "grad_norm": 6.265560626983643, "learning_rate": 9.999483701627534e-06, "loss": 0.6281, "step": 87580 }, { "epoch": 0.5206531495384322, "grad_norm": 6.434943199157715, "learning_rate": 9.999480715575717e-06, "loss": 0.668, "step": 87590 }, { "epoch": 0.5207125916151006, "grad_norm": 7.208659648895264, "learning_rate": 9.999477720914199e-06, "loss": 0.5773, "step": 87600 }, { "epoch": 0.520772033691769, "grad_norm": 8.110438346862793, "learning_rate": 9.999474717642983e-06, "loss": 0.709, "step": 87610 }, { "epoch": 0.5208314757684375, "grad_norm": 6.169797897338867, "learning_rate": 9.999471705762075e-06, "loss": 0.6569, "step": 87620 }, { "epoch": 0.5208909178451059, "grad_norm": 5.575732231140137, "learning_rate": 9.99946868527148e-06, "loss": 0.715, "step": 87630 }, { "epoch": 0.5209503599217742, "grad_norm": 5.685898303985596, "learning_rate": 9.999465656171204e-06, "loss": 0.618, "step": 87640 }, { "epoch": 0.5210098019984426, "grad_norm": 5.70930290222168, "learning_rate": 9.99946261846125e-06, "loss": 0.6855, "step": 87650 }, { "epoch": 0.521069244075111, "grad_norm": 8.156326293945312, "learning_rate": 9.999459572141626e-06, "loss": 0.6426, "step": 87660 }, { "epoch": 0.5211286861517794, "grad_norm": 5.993760585784912, "learning_rate": 9.999456517212335e-06, "loss": 0.6987, "step": 87670 }, { "epoch": 0.5211881282284478, "grad_norm": 5.684959888458252, "learning_rate": 9.999453453673384e-06, "loss": 0.6663, "step": 87680 }, { "epoch": 0.5212475703051161, "grad_norm": 6.445173263549805, "learning_rate": 9.999450381524778e-06, "loss": 0.6307, "step": 87690 }, { "epoch": 0.5213070123817846, "grad_norm": 5.872885227203369, "learning_rate": 9.999447300766522e-06, "loss": 0.7233, "step": 87700 }, { "epoch": 0.521366454458453, "grad_norm": 7.3356194496154785, "learning_rate": 9.99944421139862e-06, "loss": 0.7035, "step": 87710 }, { "epoch": 0.5214258965351214, "grad_norm": 5.5975141525268555, "learning_rate": 9.99944111342108e-06, "loss": 0.642, "step": 87720 }, { "epoch": 0.5214853386117897, "grad_norm": 6.911133766174316, "learning_rate": 9.999438006833906e-06, "loss": 0.7033, "step": 87730 }, { "epoch": 0.5215447806884581, "grad_norm": 7.14321231842041, "learning_rate": 9.999434891637102e-06, "loss": 0.6767, "step": 87740 }, { "epoch": 0.5216042227651265, "grad_norm": 5.642901420593262, "learning_rate": 9.999431767830675e-06, "loss": 0.6358, "step": 87750 }, { "epoch": 0.5216636648417949, "grad_norm": 7.217860221862793, "learning_rate": 9.99942863541463e-06, "loss": 0.616, "step": 87760 }, { "epoch": 0.5217231069184634, "grad_norm": 7.913313865661621, "learning_rate": 9.999425494388972e-06, "loss": 0.6161, "step": 87770 }, { "epoch": 0.5217825489951317, "grad_norm": 5.712798595428467, "learning_rate": 9.999422344753709e-06, "loss": 0.5997, "step": 87780 }, { "epoch": 0.5218419910718001, "grad_norm": 5.859251022338867, "learning_rate": 9.999419186508842e-06, "loss": 0.7284, "step": 87790 }, { "epoch": 0.5219014331484685, "grad_norm": 6.480631351470947, "learning_rate": 9.999416019654378e-06, "loss": 0.6831, "step": 87800 }, { "epoch": 0.5219608752251369, "grad_norm": 6.974902153015137, "learning_rate": 9.999412844190326e-06, "loss": 0.6211, "step": 87810 }, { "epoch": 0.5220203173018052, "grad_norm": 6.096645355224609, "learning_rate": 9.999409660116685e-06, "loss": 0.6657, "step": 87820 }, { "epoch": 0.5220797593784736, "grad_norm": 5.286731719970703, "learning_rate": 9.999406467433468e-06, "loss": 0.6478, "step": 87830 }, { "epoch": 0.522139201455142, "grad_norm": 4.417885780334473, "learning_rate": 9.999403266140672e-06, "loss": 0.7125, "step": 87840 }, { "epoch": 0.5221986435318104, "grad_norm": 6.646852016448975, "learning_rate": 9.999400056238312e-06, "loss": 0.6812, "step": 87850 }, { "epoch": 0.5222580856084789, "grad_norm": 7.1963791847229, "learning_rate": 9.999396837726385e-06, "loss": 0.6685, "step": 87860 }, { "epoch": 0.5223175276851472, "grad_norm": 6.627187252044678, "learning_rate": 9.9993936106049e-06, "loss": 0.6261, "step": 87870 }, { "epoch": 0.5223769697618156, "grad_norm": 7.442579746246338, "learning_rate": 9.999390374873866e-06, "loss": 0.657, "step": 87880 }, { "epoch": 0.522436411838484, "grad_norm": 7.775545120239258, "learning_rate": 9.999387130533282e-06, "loss": 0.7183, "step": 87890 }, { "epoch": 0.5224958539151524, "grad_norm": 7.448786735534668, "learning_rate": 9.999383877583157e-06, "loss": 0.6482, "step": 87900 }, { "epoch": 0.5225552959918208, "grad_norm": 7.434360027313232, "learning_rate": 9.999380616023498e-06, "loss": 0.6883, "step": 87910 }, { "epoch": 0.5226147380684891, "grad_norm": 7.601406574249268, "learning_rate": 9.999377345854308e-06, "loss": 0.6608, "step": 87920 }, { "epoch": 0.5226741801451575, "grad_norm": 5.654662132263184, "learning_rate": 9.999374067075594e-06, "loss": 0.6457, "step": 87930 }, { "epoch": 0.522733622221826, "grad_norm": 6.8004302978515625, "learning_rate": 9.999370779687362e-06, "loss": 0.6551, "step": 87940 }, { "epoch": 0.5227930642984944, "grad_norm": 7.2460455894470215, "learning_rate": 9.999367483689617e-06, "loss": 0.6293, "step": 87950 }, { "epoch": 0.5228525063751627, "grad_norm": 4.247305870056152, "learning_rate": 9.999364179082363e-06, "loss": 0.5769, "step": 87960 }, { "epoch": 0.5229119484518311, "grad_norm": 7.00842809677124, "learning_rate": 9.999360865865609e-06, "loss": 0.6428, "step": 87970 }, { "epoch": 0.5229713905284995, "grad_norm": 6.816786766052246, "learning_rate": 9.999357544039359e-06, "loss": 0.6676, "step": 87980 }, { "epoch": 0.5230308326051679, "grad_norm": 6.28997278213501, "learning_rate": 9.999354213603619e-06, "loss": 0.69, "step": 87990 }, { "epoch": 0.5230902746818363, "grad_norm": 5.704636573791504, "learning_rate": 9.999350874558394e-06, "loss": 0.6813, "step": 88000 }, { "epoch": 0.5231497167585046, "grad_norm": 6.765188217163086, "learning_rate": 9.999347526903688e-06, "loss": 0.664, "step": 88010 }, { "epoch": 0.523209158835173, "grad_norm": 6.149447917938232, "learning_rate": 9.999344170639512e-06, "loss": 0.6532, "step": 88020 }, { "epoch": 0.5232686009118415, "grad_norm": 5.839378833770752, "learning_rate": 9.999340805765868e-06, "loss": 0.6444, "step": 88030 }, { "epoch": 0.5233280429885099, "grad_norm": 5.496829986572266, "learning_rate": 9.999337432282764e-06, "loss": 0.6083, "step": 88040 }, { "epoch": 0.5233874850651782, "grad_norm": 5.396059989929199, "learning_rate": 9.999334050190203e-06, "loss": 0.7453, "step": 88050 }, { "epoch": 0.5234469271418466, "grad_norm": 6.073200702667236, "learning_rate": 9.99933065948819e-06, "loss": 0.6423, "step": 88060 }, { "epoch": 0.523506369218515, "grad_norm": 5.258842468261719, "learning_rate": 9.999327260176737e-06, "loss": 0.6028, "step": 88070 }, { "epoch": 0.5235658112951834, "grad_norm": 5.842090606689453, "learning_rate": 9.999323852255844e-06, "loss": 0.6447, "step": 88080 }, { "epoch": 0.5236252533718518, "grad_norm": 5.829769134521484, "learning_rate": 9.999320435725519e-06, "loss": 0.6872, "step": 88090 }, { "epoch": 0.5236846954485201, "grad_norm": 6.855634689331055, "learning_rate": 9.99931701058577e-06, "loss": 0.7787, "step": 88100 }, { "epoch": 0.5237441375251886, "grad_norm": 5.747531890869141, "learning_rate": 9.999313576836598e-06, "loss": 0.6784, "step": 88110 }, { "epoch": 0.523803579601857, "grad_norm": 6.816727638244629, "learning_rate": 9.99931013447801e-06, "loss": 0.6858, "step": 88120 }, { "epoch": 0.5238630216785254, "grad_norm": 5.329685688018799, "learning_rate": 9.999306683510017e-06, "loss": 0.6117, "step": 88130 }, { "epoch": 0.5239224637551938, "grad_norm": 5.029708385467529, "learning_rate": 9.999303223932618e-06, "loss": 0.6839, "step": 88140 }, { "epoch": 0.5239819058318621, "grad_norm": 4.764667987823486, "learning_rate": 9.999299755745826e-06, "loss": 0.6432, "step": 88150 }, { "epoch": 0.5240413479085305, "grad_norm": 6.699309349060059, "learning_rate": 9.999296278949642e-06, "loss": 0.7445, "step": 88160 }, { "epoch": 0.5241007899851989, "grad_norm": 7.008945941925049, "learning_rate": 9.999292793544073e-06, "loss": 0.684, "step": 88170 }, { "epoch": 0.5241602320618673, "grad_norm": 7.258458137512207, "learning_rate": 9.999289299529125e-06, "loss": 0.6616, "step": 88180 }, { "epoch": 0.5242196741385357, "grad_norm": 6.324769020080566, "learning_rate": 9.999285796904804e-06, "loss": 0.6086, "step": 88190 }, { "epoch": 0.5242791162152041, "grad_norm": 5.820074081420898, "learning_rate": 9.999282285671116e-06, "loss": 0.5885, "step": 88200 }, { "epoch": 0.5243385582918725, "grad_norm": 6.572638034820557, "learning_rate": 9.999278765828069e-06, "loss": 0.6707, "step": 88210 }, { "epoch": 0.5243980003685409, "grad_norm": 6.986239433288574, "learning_rate": 9.999275237375667e-06, "loss": 0.6495, "step": 88220 }, { "epoch": 0.5244574424452093, "grad_norm": 6.42889404296875, "learning_rate": 9.999271700313917e-06, "loss": 0.6607, "step": 88230 }, { "epoch": 0.5245168845218776, "grad_norm": 5.4420695304870605, "learning_rate": 9.999268154642822e-06, "loss": 0.6631, "step": 88240 }, { "epoch": 0.524576326598546, "grad_norm": 4.696458339691162, "learning_rate": 9.999264600362393e-06, "loss": 0.6839, "step": 88250 }, { "epoch": 0.5246357686752144, "grad_norm": 5.5812578201293945, "learning_rate": 9.999261037472634e-06, "loss": 0.6165, "step": 88260 }, { "epoch": 0.5246952107518829, "grad_norm": 6.515533447265625, "learning_rate": 9.999257465973551e-06, "loss": 0.6616, "step": 88270 }, { "epoch": 0.5247546528285513, "grad_norm": 7.147517681121826, "learning_rate": 9.999253885865148e-06, "loss": 0.6167, "step": 88280 }, { "epoch": 0.5248140949052196, "grad_norm": 6.292388916015625, "learning_rate": 9.999250297147436e-06, "loss": 0.6468, "step": 88290 }, { "epoch": 0.524873536981888, "grad_norm": 5.138951301574707, "learning_rate": 9.999246699820417e-06, "loss": 0.57, "step": 88300 }, { "epoch": 0.5249329790585564, "grad_norm": 6.135882377624512, "learning_rate": 9.999243093884099e-06, "loss": 0.7099, "step": 88310 }, { "epoch": 0.5249924211352248, "grad_norm": 6.875471591949463, "learning_rate": 9.999239479338487e-06, "loss": 0.7194, "step": 88320 }, { "epoch": 0.5250518632118931, "grad_norm": 7.511774063110352, "learning_rate": 9.99923585618359e-06, "loss": 0.6988, "step": 88330 }, { "epoch": 0.5251113052885615, "grad_norm": 6.800789833068848, "learning_rate": 9.99923222441941e-06, "loss": 0.6432, "step": 88340 }, { "epoch": 0.52517074736523, "grad_norm": 6.03558349609375, "learning_rate": 9.999228584045959e-06, "loss": 0.6391, "step": 88350 }, { "epoch": 0.5252301894418984, "grad_norm": 5.01719856262207, "learning_rate": 9.999224935063236e-06, "loss": 0.626, "step": 88360 }, { "epoch": 0.5252896315185668, "grad_norm": 6.893282890319824, "learning_rate": 9.999221277471254e-06, "loss": 0.6578, "step": 88370 }, { "epoch": 0.5253490735952351, "grad_norm": 4.284614086151123, "learning_rate": 9.999217611270016e-06, "loss": 0.6595, "step": 88380 }, { "epoch": 0.5254085156719035, "grad_norm": 6.73093318939209, "learning_rate": 9.99921393645953e-06, "loss": 0.6984, "step": 88390 }, { "epoch": 0.5254679577485719, "grad_norm": 5.456006050109863, "learning_rate": 9.999210253039797e-06, "loss": 0.6692, "step": 88400 }, { "epoch": 0.5255273998252403, "grad_norm": 6.026888370513916, "learning_rate": 9.99920656101083e-06, "loss": 0.6591, "step": 88410 }, { "epoch": 0.5255868419019086, "grad_norm": 6.947513580322266, "learning_rate": 9.999202860372633e-06, "loss": 0.6092, "step": 88420 }, { "epoch": 0.525646283978577, "grad_norm": 4.774637699127197, "learning_rate": 9.999199151125213e-06, "loss": 0.6423, "step": 88430 }, { "epoch": 0.5257057260552455, "grad_norm": 5.9539079666137695, "learning_rate": 9.999195433268574e-06, "loss": 0.6456, "step": 88440 }, { "epoch": 0.5257651681319139, "grad_norm": 7.673277854919434, "learning_rate": 9.999191706802724e-06, "loss": 0.6712, "step": 88450 }, { "epoch": 0.5258246102085823, "grad_norm": 6.383263111114502, "learning_rate": 9.99918797172767e-06, "loss": 0.627, "step": 88460 }, { "epoch": 0.5258840522852506, "grad_norm": 5.804069995880127, "learning_rate": 9.999184228043416e-06, "loss": 0.6663, "step": 88470 }, { "epoch": 0.525943494361919, "grad_norm": 5.226040840148926, "learning_rate": 9.999180475749973e-06, "loss": 0.6772, "step": 88480 }, { "epoch": 0.5260029364385874, "grad_norm": 5.971251487731934, "learning_rate": 9.999176714847342e-06, "loss": 0.6582, "step": 88490 }, { "epoch": 0.5260623785152558, "grad_norm": 5.977982044219971, "learning_rate": 9.999172945335536e-06, "loss": 0.64, "step": 88500 }, { "epoch": 0.5261218205919242, "grad_norm": 5.266085147857666, "learning_rate": 9.999169167214556e-06, "loss": 0.6024, "step": 88510 }, { "epoch": 0.5261812626685926, "grad_norm": 6.015181064605713, "learning_rate": 9.999165380484408e-06, "loss": 0.6693, "step": 88520 }, { "epoch": 0.526240704745261, "grad_norm": 6.132333755493164, "learning_rate": 9.999161585145102e-06, "loss": 0.6414, "step": 88530 }, { "epoch": 0.5263001468219294, "grad_norm": 6.129706382751465, "learning_rate": 9.999157781196644e-06, "loss": 0.6607, "step": 88540 }, { "epoch": 0.5263595888985978, "grad_norm": 4.610426902770996, "learning_rate": 9.999153968639039e-06, "loss": 0.6006, "step": 88550 }, { "epoch": 0.5264190309752661, "grad_norm": 5.350101947784424, "learning_rate": 9.999150147472296e-06, "loss": 0.6657, "step": 88560 }, { "epoch": 0.5264784730519345, "grad_norm": 5.8723320960998535, "learning_rate": 9.999146317696419e-06, "loss": 0.6367, "step": 88570 }, { "epoch": 0.5265379151286029, "grad_norm": 5.900508403778076, "learning_rate": 9.999142479311415e-06, "loss": 0.6533, "step": 88580 }, { "epoch": 0.5265973572052713, "grad_norm": 6.809835910797119, "learning_rate": 9.999138632317291e-06, "loss": 0.6682, "step": 88590 }, { "epoch": 0.5266567992819398, "grad_norm": 7.2271504402160645, "learning_rate": 9.999134776714054e-06, "loss": 0.6817, "step": 88600 }, { "epoch": 0.5267162413586081, "grad_norm": 5.462915420532227, "learning_rate": 9.99913091250171e-06, "loss": 0.6596, "step": 88610 }, { "epoch": 0.5267756834352765, "grad_norm": 5.751974105834961, "learning_rate": 9.999127039680267e-06, "loss": 0.7162, "step": 88620 }, { "epoch": 0.5268351255119449, "grad_norm": 5.503764629364014, "learning_rate": 9.999123158249732e-06, "loss": 0.6753, "step": 88630 }, { "epoch": 0.5268945675886133, "grad_norm": 8.632447242736816, "learning_rate": 9.999119268210109e-06, "loss": 0.6631, "step": 88640 }, { "epoch": 0.5269540096652817, "grad_norm": 5.692374229431152, "learning_rate": 9.999115369561407e-06, "loss": 0.6949, "step": 88650 }, { "epoch": 0.52701345174195, "grad_norm": 6.4151482582092285, "learning_rate": 9.99911146230363e-06, "loss": 0.6637, "step": 88660 }, { "epoch": 0.5270728938186184, "grad_norm": 5.167194843292236, "learning_rate": 9.999107546436788e-06, "loss": 0.6137, "step": 88670 }, { "epoch": 0.5271323358952869, "grad_norm": 6.305172920227051, "learning_rate": 9.999103621960886e-06, "loss": 0.6389, "step": 88680 }, { "epoch": 0.5271917779719553, "grad_norm": 5.928149223327637, "learning_rate": 9.99909968887593e-06, "loss": 0.6961, "step": 88690 }, { "epoch": 0.5272512200486236, "grad_norm": 6.288830280303955, "learning_rate": 9.999095747181929e-06, "loss": 0.6796, "step": 88700 }, { "epoch": 0.527310662125292, "grad_norm": 5.549842357635498, "learning_rate": 9.999091796878887e-06, "loss": 0.6213, "step": 88710 }, { "epoch": 0.5273701042019604, "grad_norm": 5.4557204246521, "learning_rate": 9.999087837966815e-06, "loss": 0.662, "step": 88720 }, { "epoch": 0.5274295462786288, "grad_norm": 5.497659683227539, "learning_rate": 9.999083870445716e-06, "loss": 0.6743, "step": 88730 }, { "epoch": 0.5274889883552972, "grad_norm": 6.115538597106934, "learning_rate": 9.9990798943156e-06, "loss": 0.6141, "step": 88740 }, { "epoch": 0.5275484304319655, "grad_norm": 5.959605693817139, "learning_rate": 9.99907590957647e-06, "loss": 0.6946, "step": 88750 }, { "epoch": 0.527607872508634, "grad_norm": 5.122288227081299, "learning_rate": 9.999071916228334e-06, "loss": 0.6654, "step": 88760 }, { "epoch": 0.5276673145853024, "grad_norm": 6.352167129516602, "learning_rate": 9.9990679142712e-06, "loss": 0.6709, "step": 88770 }, { "epoch": 0.5277267566619708, "grad_norm": 5.722436428070068, "learning_rate": 9.999063903705077e-06, "loss": 0.6309, "step": 88780 }, { "epoch": 0.5277861987386391, "grad_norm": 5.759188175201416, "learning_rate": 9.999059884529968e-06, "loss": 0.6205, "step": 88790 }, { "epoch": 0.5278456408153075, "grad_norm": 5.763101577758789, "learning_rate": 9.99905585674588e-06, "loss": 0.6404, "step": 88800 }, { "epoch": 0.5279050828919759, "grad_norm": 4.5423736572265625, "learning_rate": 9.999051820352824e-06, "loss": 0.6406, "step": 88810 }, { "epoch": 0.5279645249686443, "grad_norm": 5.741302013397217, "learning_rate": 9.999047775350801e-06, "loss": 0.6715, "step": 88820 }, { "epoch": 0.5280239670453127, "grad_norm": 6.668240070343018, "learning_rate": 9.999043721739823e-06, "loss": 0.6467, "step": 88830 }, { "epoch": 0.528083409121981, "grad_norm": 6.638060569763184, "learning_rate": 9.999039659519896e-06, "loss": 0.6298, "step": 88840 }, { "epoch": 0.5281428511986495, "grad_norm": 7.3015899658203125, "learning_rate": 9.999035588691025e-06, "loss": 0.6534, "step": 88850 }, { "epoch": 0.5282022932753179, "grad_norm": 6.574460506439209, "learning_rate": 9.999031509253218e-06, "loss": 0.672, "step": 88860 }, { "epoch": 0.5282617353519863, "grad_norm": 8.223166465759277, "learning_rate": 9.999027421206483e-06, "loss": 0.6943, "step": 88870 }, { "epoch": 0.5283211774286547, "grad_norm": 7.578537940979004, "learning_rate": 9.999023324550828e-06, "loss": 0.6852, "step": 88880 }, { "epoch": 0.528380619505323, "grad_norm": 5.646496772766113, "learning_rate": 9.999019219286256e-06, "loss": 0.662, "step": 88890 }, { "epoch": 0.5284400615819914, "grad_norm": 7.349708080291748, "learning_rate": 9.999015105412777e-06, "loss": 0.6551, "step": 88900 }, { "epoch": 0.5284995036586598, "grad_norm": 6.249640941619873, "learning_rate": 9.999010982930398e-06, "loss": 0.6802, "step": 88910 }, { "epoch": 0.5285589457353282, "grad_norm": 7.078072547912598, "learning_rate": 9.999006851839124e-06, "loss": 0.7515, "step": 88920 }, { "epoch": 0.5286183878119965, "grad_norm": 5.336918830871582, "learning_rate": 9.999002712138965e-06, "loss": 0.6377, "step": 88930 }, { "epoch": 0.528677829888665, "grad_norm": 5.941865921020508, "learning_rate": 9.998998563829927e-06, "loss": 0.6796, "step": 88940 }, { "epoch": 0.5287372719653334, "grad_norm": 6.255648612976074, "learning_rate": 9.998994406912018e-06, "loss": 0.546, "step": 88950 }, { "epoch": 0.5287967140420018, "grad_norm": 6.346546649932861, "learning_rate": 9.998990241385243e-06, "loss": 0.6967, "step": 88960 }, { "epoch": 0.5288561561186702, "grad_norm": 6.527777194976807, "learning_rate": 9.99898606724961e-06, "loss": 0.6683, "step": 88970 }, { "epoch": 0.5289155981953385, "grad_norm": 5.866338729858398, "learning_rate": 9.998981884505126e-06, "loss": 0.6535, "step": 88980 }, { "epoch": 0.5289750402720069, "grad_norm": 4.820654392242432, "learning_rate": 9.9989776931518e-06, "loss": 0.6359, "step": 88990 }, { "epoch": 0.5290344823486753, "grad_norm": 3.8951873779296875, "learning_rate": 9.998973493189638e-06, "loss": 0.5953, "step": 89000 }, { "epoch": 0.5290939244253438, "grad_norm": 7.37809944152832, "learning_rate": 9.998969284618648e-06, "loss": 0.6718, "step": 89010 }, { "epoch": 0.5291533665020122, "grad_norm": 5.274678707122803, "learning_rate": 9.998965067438833e-06, "loss": 0.6473, "step": 89020 }, { "epoch": 0.5292128085786805, "grad_norm": 6.382397651672363, "learning_rate": 9.998960841650206e-06, "loss": 0.6642, "step": 89030 }, { "epoch": 0.5292722506553489, "grad_norm": 7.051104545593262, "learning_rate": 9.998956607252772e-06, "loss": 0.6582, "step": 89040 }, { "epoch": 0.5293316927320173, "grad_norm": 5.915846824645996, "learning_rate": 9.998952364246538e-06, "loss": 0.6442, "step": 89050 }, { "epoch": 0.5293911348086857, "grad_norm": 8.215310096740723, "learning_rate": 9.99894811263151e-06, "loss": 0.6757, "step": 89060 }, { "epoch": 0.529450576885354, "grad_norm": 5.317139625549316, "learning_rate": 9.9989438524077e-06, "loss": 0.6075, "step": 89070 }, { "epoch": 0.5295100189620224, "grad_norm": 6.702080726623535, "learning_rate": 9.998939583575111e-06, "loss": 0.6605, "step": 89080 }, { "epoch": 0.5295694610386908, "grad_norm": 6.309675216674805, "learning_rate": 9.99893530613375e-06, "loss": 0.6354, "step": 89090 }, { "epoch": 0.5296289031153593, "grad_norm": 5.521829128265381, "learning_rate": 9.998931020083629e-06, "loss": 0.6306, "step": 89100 }, { "epoch": 0.5296883451920277, "grad_norm": 5.764070510864258, "learning_rate": 9.998926725424748e-06, "loss": 0.7524, "step": 89110 }, { "epoch": 0.529747787268696, "grad_norm": 6.2106428146362305, "learning_rate": 9.998922422157122e-06, "loss": 0.6762, "step": 89120 }, { "epoch": 0.5298072293453644, "grad_norm": 7.207508087158203, "learning_rate": 9.998918110280755e-06, "loss": 0.7516, "step": 89130 }, { "epoch": 0.5298666714220328, "grad_norm": 6.5137434005737305, "learning_rate": 9.998913789795655e-06, "loss": 0.6951, "step": 89140 }, { "epoch": 0.5299261134987012, "grad_norm": 6.197117805480957, "learning_rate": 9.998909460701826e-06, "loss": 0.6428, "step": 89150 }, { "epoch": 0.5299855555753695, "grad_norm": 7.149480819702148, "learning_rate": 9.998905122999281e-06, "loss": 0.6732, "step": 89160 }, { "epoch": 0.5300449976520379, "grad_norm": 4.89646577835083, "learning_rate": 9.998900776688025e-06, "loss": 0.6086, "step": 89170 }, { "epoch": 0.5301044397287064, "grad_norm": 7.073007106781006, "learning_rate": 9.998896421768065e-06, "loss": 0.6307, "step": 89180 }, { "epoch": 0.5301638818053748, "grad_norm": 8.056865692138672, "learning_rate": 9.998892058239407e-06, "loss": 0.6539, "step": 89190 }, { "epoch": 0.5302233238820432, "grad_norm": 5.525273323059082, "learning_rate": 9.998887686102064e-06, "loss": 0.6734, "step": 89200 }, { "epoch": 0.5302827659587115, "grad_norm": 8.13155746459961, "learning_rate": 9.998883305356037e-06, "loss": 0.674, "step": 89210 }, { "epoch": 0.5303422080353799, "grad_norm": 5.767692565917969, "learning_rate": 9.998878916001338e-06, "loss": 0.6266, "step": 89220 }, { "epoch": 0.5304016501120483, "grad_norm": 5.24382209777832, "learning_rate": 9.99887451803797e-06, "loss": 0.6649, "step": 89230 }, { "epoch": 0.5304610921887167, "grad_norm": 6.72992467880249, "learning_rate": 9.998870111465948e-06, "loss": 0.6285, "step": 89240 }, { "epoch": 0.5305205342653851, "grad_norm": 6.169005393981934, "learning_rate": 9.998865696285273e-06, "loss": 0.6261, "step": 89250 }, { "epoch": 0.5305799763420534, "grad_norm": 6.360091686248779, "learning_rate": 9.998861272495956e-06, "loss": 0.6661, "step": 89260 }, { "epoch": 0.5306394184187219, "grad_norm": 4.702826499938965, "learning_rate": 9.998856840098002e-06, "loss": 0.6924, "step": 89270 }, { "epoch": 0.5306988604953903, "grad_norm": 5.997927665710449, "learning_rate": 9.998852399091422e-06, "loss": 0.5889, "step": 89280 }, { "epoch": 0.5307583025720587, "grad_norm": 6.18195915222168, "learning_rate": 9.998847949476217e-06, "loss": 0.5828, "step": 89290 }, { "epoch": 0.530817744648727, "grad_norm": 6.111851692199707, "learning_rate": 9.998843491252405e-06, "loss": 0.6716, "step": 89300 }, { "epoch": 0.5308771867253954, "grad_norm": 5.729130744934082, "learning_rate": 9.998839024419987e-06, "loss": 0.6539, "step": 89310 }, { "epoch": 0.5309366288020638, "grad_norm": 4.5200653076171875, "learning_rate": 9.998834548978968e-06, "loss": 0.6645, "step": 89320 }, { "epoch": 0.5309960708787322, "grad_norm": 7.854791641235352, "learning_rate": 9.998830064929363e-06, "loss": 0.6784, "step": 89330 }, { "epoch": 0.5310555129554007, "grad_norm": 6.42114782333374, "learning_rate": 9.998825572271175e-06, "loss": 0.6668, "step": 89340 }, { "epoch": 0.531114955032069, "grad_norm": 6.594789028167725, "learning_rate": 9.998821071004413e-06, "loss": 0.6205, "step": 89350 }, { "epoch": 0.5311743971087374, "grad_norm": 6.117474555969238, "learning_rate": 9.998816561129085e-06, "loss": 0.5909, "step": 89360 }, { "epoch": 0.5312338391854058, "grad_norm": 5.680733680725098, "learning_rate": 9.998812042645198e-06, "loss": 0.6736, "step": 89370 }, { "epoch": 0.5312932812620742, "grad_norm": 6.846314907073975, "learning_rate": 9.99880751555276e-06, "loss": 0.7183, "step": 89380 }, { "epoch": 0.5313527233387426, "grad_norm": 7.439428329467773, "learning_rate": 9.998802979851781e-06, "loss": 0.6356, "step": 89390 }, { "epoch": 0.5314121654154109, "grad_norm": 4.89759635925293, "learning_rate": 9.998798435542264e-06, "loss": 0.6604, "step": 89400 }, { "epoch": 0.5314716074920793, "grad_norm": 5.456508159637451, "learning_rate": 9.99879388262422e-06, "loss": 0.6374, "step": 89410 }, { "epoch": 0.5315310495687477, "grad_norm": 5.01165771484375, "learning_rate": 9.998789321097659e-06, "loss": 0.6602, "step": 89420 }, { "epoch": 0.5315904916454162, "grad_norm": 6.940420150756836, "learning_rate": 9.998784750962585e-06, "loss": 0.668, "step": 89430 }, { "epoch": 0.5316499337220845, "grad_norm": 4.644498825073242, "learning_rate": 9.998780172219007e-06, "loss": 0.6211, "step": 89440 }, { "epoch": 0.5317093757987529, "grad_norm": 5.846010684967041, "learning_rate": 9.998775584866933e-06, "loss": 0.6402, "step": 89450 }, { "epoch": 0.5317688178754213, "grad_norm": 6.430578708648682, "learning_rate": 9.99877098890637e-06, "loss": 0.69, "step": 89460 }, { "epoch": 0.5318282599520897, "grad_norm": 5.56915283203125, "learning_rate": 9.998766384337329e-06, "loss": 0.5967, "step": 89470 }, { "epoch": 0.5318877020287581, "grad_norm": 6.2668609619140625, "learning_rate": 9.998761771159813e-06, "loss": 0.6745, "step": 89480 }, { "epoch": 0.5319471441054264, "grad_norm": 5.818253517150879, "learning_rate": 9.998757149373836e-06, "loss": 0.6479, "step": 89490 }, { "epoch": 0.5320065861820948, "grad_norm": 6.808155059814453, "learning_rate": 9.9987525189794e-06, "loss": 0.6292, "step": 89500 }, { "epoch": 0.5320660282587633, "grad_norm": 6.6472883224487305, "learning_rate": 9.998747879976518e-06, "loss": 0.6759, "step": 89510 }, { "epoch": 0.5321254703354317, "grad_norm": 6.054803848266602, "learning_rate": 9.998743232365194e-06, "loss": 0.6473, "step": 89520 }, { "epoch": 0.5321849124121, "grad_norm": 6.727517604827881, "learning_rate": 9.99873857614544e-06, "loss": 0.667, "step": 89530 }, { "epoch": 0.5322443544887684, "grad_norm": 4.947707653045654, "learning_rate": 9.998733911317259e-06, "loss": 0.6177, "step": 89540 }, { "epoch": 0.5323037965654368, "grad_norm": 8.003433227539062, "learning_rate": 9.998729237880664e-06, "loss": 0.7461, "step": 89550 }, { "epoch": 0.5323632386421052, "grad_norm": 6.29383659362793, "learning_rate": 9.99872455583566e-06, "loss": 0.6558, "step": 89560 }, { "epoch": 0.5324226807187736, "grad_norm": 4.900174140930176, "learning_rate": 9.998719865182254e-06, "loss": 0.6098, "step": 89570 }, { "epoch": 0.5324821227954419, "grad_norm": 5.567128658294678, "learning_rate": 9.998715165920458e-06, "loss": 0.6787, "step": 89580 }, { "epoch": 0.5325415648721104, "grad_norm": 5.982906818389893, "learning_rate": 9.998710458050278e-06, "loss": 0.6246, "step": 89590 }, { "epoch": 0.5326010069487788, "grad_norm": 6.408695697784424, "learning_rate": 9.998705741571721e-06, "loss": 0.6672, "step": 89600 }, { "epoch": 0.5326604490254472, "grad_norm": 6.778281211853027, "learning_rate": 9.998701016484797e-06, "loss": 0.5946, "step": 89610 }, { "epoch": 0.5327198911021156, "grad_norm": 5.892683506011963, "learning_rate": 9.998696282789514e-06, "loss": 0.7003, "step": 89620 }, { "epoch": 0.5327793331787839, "grad_norm": 7.827899932861328, "learning_rate": 9.99869154048588e-06, "loss": 0.5901, "step": 89630 }, { "epoch": 0.5328387752554523, "grad_norm": 7.357729911804199, "learning_rate": 9.998686789573901e-06, "loss": 0.6687, "step": 89640 }, { "epoch": 0.5328982173321207, "grad_norm": 7.317878723144531, "learning_rate": 9.998682030053588e-06, "loss": 0.666, "step": 89650 }, { "epoch": 0.5329576594087891, "grad_norm": 4.364193916320801, "learning_rate": 9.998677261924947e-06, "loss": 0.6364, "step": 89660 }, { "epoch": 0.5330171014854574, "grad_norm": 6.034687042236328, "learning_rate": 9.998672485187988e-06, "loss": 0.682, "step": 89670 }, { "epoch": 0.5330765435621259, "grad_norm": 6.164761066436768, "learning_rate": 9.998667699842718e-06, "loss": 0.6939, "step": 89680 }, { "epoch": 0.5331359856387943, "grad_norm": 7.583156585693359, "learning_rate": 9.998662905889148e-06, "loss": 0.6658, "step": 89690 }, { "epoch": 0.5331954277154627, "grad_norm": 5.766927719116211, "learning_rate": 9.998658103327282e-06, "loss": 0.611, "step": 89700 }, { "epoch": 0.5332548697921311, "grad_norm": 8.710026741027832, "learning_rate": 9.998653292157131e-06, "loss": 0.6967, "step": 89710 }, { "epoch": 0.5333143118687994, "grad_norm": 8.371312141418457, "learning_rate": 9.998648472378703e-06, "loss": 0.6236, "step": 89720 }, { "epoch": 0.5333737539454678, "grad_norm": 5.817660331726074, "learning_rate": 9.998643643992005e-06, "loss": 0.7061, "step": 89730 }, { "epoch": 0.5334331960221362, "grad_norm": 6.303402900695801, "learning_rate": 9.998638806997046e-06, "loss": 0.6051, "step": 89740 }, { "epoch": 0.5334926380988047, "grad_norm": 6.1458845138549805, "learning_rate": 9.998633961393835e-06, "loss": 0.6852, "step": 89750 }, { "epoch": 0.5335520801754731, "grad_norm": 6.0857415199279785, "learning_rate": 9.99862910718238e-06, "loss": 0.659, "step": 89760 }, { "epoch": 0.5336115222521414, "grad_norm": 6.999699592590332, "learning_rate": 9.99862424436269e-06, "loss": 0.6379, "step": 89770 }, { "epoch": 0.5336709643288098, "grad_norm": 6.856013298034668, "learning_rate": 9.998619372934773e-06, "loss": 0.6743, "step": 89780 }, { "epoch": 0.5337304064054782, "grad_norm": 6.365406513214111, "learning_rate": 9.998614492898636e-06, "loss": 0.676, "step": 89790 }, { "epoch": 0.5337898484821466, "grad_norm": 5.2893829345703125, "learning_rate": 9.998609604254286e-06, "loss": 0.611, "step": 89800 }, { "epoch": 0.5338492905588149, "grad_norm": 6.124707221984863, "learning_rate": 9.998604707001739e-06, "loss": 0.5956, "step": 89810 }, { "epoch": 0.5339087326354833, "grad_norm": 7.278392314910889, "learning_rate": 9.998599801140994e-06, "loss": 0.6483, "step": 89820 }, { "epoch": 0.5339681747121517, "grad_norm": 6.56134033203125, "learning_rate": 9.998594886672064e-06, "loss": 0.625, "step": 89830 }, { "epoch": 0.5340276167888202, "grad_norm": 5.2594757080078125, "learning_rate": 9.99858996359496e-06, "loss": 0.6585, "step": 89840 }, { "epoch": 0.5340870588654886, "grad_norm": 5.959470272064209, "learning_rate": 9.998585031909684e-06, "loss": 0.6529, "step": 89850 }, { "epoch": 0.5341465009421569, "grad_norm": 5.318614482879639, "learning_rate": 9.99858009161625e-06, "loss": 0.6569, "step": 89860 }, { "epoch": 0.5342059430188253, "grad_norm": 6.4831061363220215, "learning_rate": 9.998575142714666e-06, "loss": 0.6711, "step": 89870 }, { "epoch": 0.5342653850954937, "grad_norm": 4.653023719787598, "learning_rate": 9.998570185204937e-06, "loss": 0.5812, "step": 89880 }, { "epoch": 0.5343248271721621, "grad_norm": 5.545416355133057, "learning_rate": 9.998565219087075e-06, "loss": 0.6442, "step": 89890 }, { "epoch": 0.5343842692488304, "grad_norm": 5.134228706359863, "learning_rate": 9.998560244361087e-06, "loss": 0.6528, "step": 89900 }, { "epoch": 0.5344437113254988, "grad_norm": 5.977547645568848, "learning_rate": 9.998555261026982e-06, "loss": 0.6517, "step": 89910 }, { "epoch": 0.5345031534021673, "grad_norm": 5.337206840515137, "learning_rate": 9.998550269084769e-06, "loss": 0.5799, "step": 89920 }, { "epoch": 0.5345625954788357, "grad_norm": 6.841330528259277, "learning_rate": 9.998545268534454e-06, "loss": 0.6993, "step": 89930 }, { "epoch": 0.5346220375555041, "grad_norm": 5.566958904266357, "learning_rate": 9.99854025937605e-06, "loss": 0.6895, "step": 89940 }, { "epoch": 0.5346814796321724, "grad_norm": 7.157717704772949, "learning_rate": 9.998535241609562e-06, "loss": 0.6542, "step": 89950 }, { "epoch": 0.5347409217088408, "grad_norm": 6.7978081703186035, "learning_rate": 9.998530215235e-06, "loss": 0.6647, "step": 89960 }, { "epoch": 0.5348003637855092, "grad_norm": 4.923657417297363, "learning_rate": 9.998525180252371e-06, "loss": 0.6446, "step": 89970 }, { "epoch": 0.5348598058621776, "grad_norm": 6.931030750274658, "learning_rate": 9.998520136661687e-06, "loss": 0.6354, "step": 89980 }, { "epoch": 0.534919247938846, "grad_norm": 6.3565826416015625, "learning_rate": 9.998515084462956e-06, "loss": 0.6773, "step": 89990 }, { "epoch": 0.5349786900155143, "grad_norm": 6.1923699378967285, "learning_rate": 9.998510023656185e-06, "loss": 0.6777, "step": 90000 }, { "epoch": 0.5350381320921828, "grad_norm": 6.579319477081299, "learning_rate": 9.99850495424138e-06, "loss": 0.6856, "step": 90010 }, { "epoch": 0.5350975741688512, "grad_norm": 5.688928127288818, "learning_rate": 9.998499876218557e-06, "loss": 0.5641, "step": 90020 }, { "epoch": 0.5351570162455196, "grad_norm": 10.431617736816406, "learning_rate": 9.998494789587721e-06, "loss": 0.6874, "step": 90030 }, { "epoch": 0.5352164583221879, "grad_norm": 8.132762908935547, "learning_rate": 9.998489694348878e-06, "loss": 0.6611, "step": 90040 }, { "epoch": 0.5352759003988563, "grad_norm": 6.1058430671691895, "learning_rate": 9.99848459050204e-06, "loss": 0.6496, "step": 90050 }, { "epoch": 0.5353353424755247, "grad_norm": 6.293845176696777, "learning_rate": 9.998479478047217e-06, "loss": 0.6921, "step": 90060 }, { "epoch": 0.5353947845521931, "grad_norm": 5.596902370452881, "learning_rate": 9.998474356984414e-06, "loss": 0.6355, "step": 90070 }, { "epoch": 0.5354542266288616, "grad_norm": 6.640941619873047, "learning_rate": 9.998469227313642e-06, "loss": 0.6618, "step": 90080 }, { "epoch": 0.5355136687055299, "grad_norm": 6.529218673706055, "learning_rate": 9.99846408903491e-06, "loss": 0.6911, "step": 90090 }, { "epoch": 0.5355731107821983, "grad_norm": 6.658089637756348, "learning_rate": 9.998458942148226e-06, "loss": 0.616, "step": 90100 }, { "epoch": 0.5356325528588667, "grad_norm": 6.562439441680908, "learning_rate": 9.998453786653599e-06, "loss": 0.6885, "step": 90110 }, { "epoch": 0.5356919949355351, "grad_norm": 4.387874603271484, "learning_rate": 9.99844862255104e-06, "loss": 0.6443, "step": 90120 }, { "epoch": 0.5357514370122035, "grad_norm": 6.377562999725342, "learning_rate": 9.998443449840553e-06, "loss": 0.6941, "step": 90130 }, { "epoch": 0.5358108790888718, "grad_norm": 5.892446994781494, "learning_rate": 9.998438268522153e-06, "loss": 0.6387, "step": 90140 }, { "epoch": 0.5358703211655402, "grad_norm": 6.850239276885986, "learning_rate": 9.998433078595844e-06, "loss": 0.699, "step": 90150 }, { "epoch": 0.5359297632422086, "grad_norm": 6.346656322479248, "learning_rate": 9.998427880061638e-06, "loss": 0.6804, "step": 90160 }, { "epoch": 0.5359892053188771, "grad_norm": 7.037796974182129, "learning_rate": 9.998422672919542e-06, "loss": 0.672, "step": 90170 }, { "epoch": 0.5360486473955454, "grad_norm": 5.351733684539795, "learning_rate": 9.998417457169567e-06, "loss": 0.6798, "step": 90180 }, { "epoch": 0.5361080894722138, "grad_norm": 7.023879051208496, "learning_rate": 9.998412232811719e-06, "loss": 0.6194, "step": 90190 }, { "epoch": 0.5361675315488822, "grad_norm": 4.747602939605713, "learning_rate": 9.99840699984601e-06, "loss": 0.6654, "step": 90200 }, { "epoch": 0.5362269736255506, "grad_norm": 5.8188066482543945, "learning_rate": 9.998401758272446e-06, "loss": 0.6698, "step": 90210 }, { "epoch": 0.536286415702219, "grad_norm": 7.522272109985352, "learning_rate": 9.99839650809104e-06, "loss": 0.6583, "step": 90220 }, { "epoch": 0.5363458577788873, "grad_norm": 5.611865997314453, "learning_rate": 9.998391249301798e-06, "loss": 0.6153, "step": 90230 }, { "epoch": 0.5364052998555557, "grad_norm": 8.005613327026367, "learning_rate": 9.99838598190473e-06, "loss": 0.6587, "step": 90240 }, { "epoch": 0.5364647419322242, "grad_norm": 5.494767189025879, "learning_rate": 9.998380705899844e-06, "loss": 0.6938, "step": 90250 }, { "epoch": 0.5365241840088926, "grad_norm": 6.580685138702393, "learning_rate": 9.998375421287151e-06, "loss": 0.5911, "step": 90260 }, { "epoch": 0.5365836260855609, "grad_norm": 8.596732139587402, "learning_rate": 9.998370128066659e-06, "loss": 0.6192, "step": 90270 }, { "epoch": 0.5366430681622293, "grad_norm": 5.805352687835693, "learning_rate": 9.998364826238375e-06, "loss": 0.645, "step": 90280 }, { "epoch": 0.5367025102388977, "grad_norm": 6.8027143478393555, "learning_rate": 9.998359515802314e-06, "loss": 0.6395, "step": 90290 }, { "epoch": 0.5367619523155661, "grad_norm": 7.331318378448486, "learning_rate": 9.99835419675848e-06, "loss": 0.6394, "step": 90300 }, { "epoch": 0.5368213943922345, "grad_norm": 5.361776828765869, "learning_rate": 9.998348869106883e-06, "loss": 0.6615, "step": 90310 }, { "epoch": 0.5368808364689028, "grad_norm": 5.834944725036621, "learning_rate": 9.998343532847534e-06, "loss": 0.6155, "step": 90320 }, { "epoch": 0.5369402785455712, "grad_norm": 7.766480445861816, "learning_rate": 9.99833818798044e-06, "loss": 0.6214, "step": 90330 }, { "epoch": 0.5369997206222397, "grad_norm": 6.0471272468566895, "learning_rate": 9.998332834505613e-06, "loss": 0.6675, "step": 90340 }, { "epoch": 0.5370591626989081, "grad_norm": 6.654177188873291, "learning_rate": 9.998327472423058e-06, "loss": 0.5987, "step": 90350 }, { "epoch": 0.5371186047755765, "grad_norm": 5.2139482498168945, "learning_rate": 9.99832210173279e-06, "loss": 0.6629, "step": 90360 }, { "epoch": 0.5371780468522448, "grad_norm": 7.8399128913879395, "learning_rate": 9.998316722434812e-06, "loss": 0.6422, "step": 90370 }, { "epoch": 0.5372374889289132, "grad_norm": 6.176286220550537, "learning_rate": 9.998311334529136e-06, "loss": 0.6255, "step": 90380 }, { "epoch": 0.5372969310055816, "grad_norm": 9.171524047851562, "learning_rate": 9.998305938015772e-06, "loss": 0.6642, "step": 90390 }, { "epoch": 0.53735637308225, "grad_norm": 4.506168365478516, "learning_rate": 9.99830053289473e-06, "loss": 0.6101, "step": 90400 }, { "epoch": 0.5374158151589183, "grad_norm": 7.824740886688232, "learning_rate": 9.998295119166018e-06, "loss": 0.6714, "step": 90410 }, { "epoch": 0.5374752572355868, "grad_norm": 7.095089912414551, "learning_rate": 9.998289696829645e-06, "loss": 0.6254, "step": 90420 }, { "epoch": 0.5375346993122552, "grad_norm": 7.20598030090332, "learning_rate": 9.998284265885621e-06, "loss": 0.6682, "step": 90430 }, { "epoch": 0.5375941413889236, "grad_norm": 6.793844699859619, "learning_rate": 9.998278826333954e-06, "loss": 0.744, "step": 90440 }, { "epoch": 0.537653583465592, "grad_norm": 8.073932647705078, "learning_rate": 9.998273378174656e-06, "loss": 0.651, "step": 90450 }, { "epoch": 0.5377130255422603, "grad_norm": 6.64376974105835, "learning_rate": 9.998267921407734e-06, "loss": 0.694, "step": 90460 }, { "epoch": 0.5377724676189287, "grad_norm": 7.01642370223999, "learning_rate": 9.998262456033198e-06, "loss": 0.6682, "step": 90470 }, { "epoch": 0.5378319096955971, "grad_norm": 8.496886253356934, "learning_rate": 9.998256982051058e-06, "loss": 0.6531, "step": 90480 }, { "epoch": 0.5378913517722655, "grad_norm": 6.71493673324585, "learning_rate": 9.998251499461322e-06, "loss": 0.6482, "step": 90490 }, { "epoch": 0.537950793848934, "grad_norm": 5.089929103851318, "learning_rate": 9.998246008264004e-06, "loss": 0.5923, "step": 90500 }, { "epoch": 0.5380102359256023, "grad_norm": 5.003241539001465, "learning_rate": 9.998240508459106e-06, "loss": 0.6253, "step": 90510 }, { "epoch": 0.5380696780022707, "grad_norm": 6.040494441986084, "learning_rate": 9.998235000046644e-06, "loss": 0.6331, "step": 90520 }, { "epoch": 0.5381291200789391, "grad_norm": 5.700848579406738, "learning_rate": 9.998229483026623e-06, "loss": 0.7408, "step": 90530 }, { "epoch": 0.5381885621556075, "grad_norm": 6.763760566711426, "learning_rate": 9.998223957399057e-06, "loss": 0.7413, "step": 90540 }, { "epoch": 0.5382480042322758, "grad_norm": 5.57858943939209, "learning_rate": 9.99821842316395e-06, "loss": 0.6218, "step": 90550 }, { "epoch": 0.5383074463089442, "grad_norm": 6.707859516143799, "learning_rate": 9.998212880321316e-06, "loss": 0.6981, "step": 90560 }, { "epoch": 0.5383668883856126, "grad_norm": 6.018420696258545, "learning_rate": 9.998207328871163e-06, "loss": 0.639, "step": 90570 }, { "epoch": 0.538426330462281, "grad_norm": 4.682357311248779, "learning_rate": 9.9982017688135e-06, "loss": 0.6908, "step": 90580 }, { "epoch": 0.5384857725389495, "grad_norm": 5.778611183166504, "learning_rate": 9.998196200148338e-06, "loss": 0.6469, "step": 90590 }, { "epoch": 0.5385452146156178, "grad_norm": 7.272310733795166, "learning_rate": 9.998190622875686e-06, "loss": 0.6543, "step": 90600 }, { "epoch": 0.5386046566922862, "grad_norm": 7.22000789642334, "learning_rate": 9.998185036995554e-06, "loss": 0.6821, "step": 90610 }, { "epoch": 0.5386640987689546, "grad_norm": 6.551736354827881, "learning_rate": 9.99817944250795e-06, "loss": 0.5888, "step": 90620 }, { "epoch": 0.538723540845623, "grad_norm": 5.927796840667725, "learning_rate": 9.998173839412883e-06, "loss": 0.6478, "step": 90630 }, { "epoch": 0.5387829829222913, "grad_norm": 6.223718643188477, "learning_rate": 9.998168227710367e-06, "loss": 0.666, "step": 90640 }, { "epoch": 0.5388424249989597, "grad_norm": 7.138001918792725, "learning_rate": 9.998162607400408e-06, "loss": 0.7211, "step": 90650 }, { "epoch": 0.5389018670756281, "grad_norm": 6.693113327026367, "learning_rate": 9.998156978483016e-06, "loss": 0.6562, "step": 90660 }, { "epoch": 0.5389613091522966, "grad_norm": 5.328072547912598, "learning_rate": 9.998151340958201e-06, "loss": 0.6353, "step": 90670 }, { "epoch": 0.539020751228965, "grad_norm": 4.3625874519348145, "learning_rate": 9.998145694825973e-06, "loss": 0.7174, "step": 90680 }, { "epoch": 0.5390801933056333, "grad_norm": 6.5555243492126465, "learning_rate": 9.998140040086344e-06, "loss": 0.6463, "step": 90690 }, { "epoch": 0.5391396353823017, "grad_norm": 6.3869948387146, "learning_rate": 9.99813437673932e-06, "loss": 0.6722, "step": 90700 }, { "epoch": 0.5391990774589701, "grad_norm": 6.475704193115234, "learning_rate": 9.998128704784912e-06, "loss": 0.677, "step": 90710 }, { "epoch": 0.5392585195356385, "grad_norm": 5.533226013183594, "learning_rate": 9.99812302422313e-06, "loss": 0.6443, "step": 90720 }, { "epoch": 0.5393179616123069, "grad_norm": 5.983123779296875, "learning_rate": 9.998117335053984e-06, "loss": 0.6252, "step": 90730 }, { "epoch": 0.5393774036889752, "grad_norm": 5.698659896850586, "learning_rate": 9.998111637277483e-06, "loss": 0.6239, "step": 90740 }, { "epoch": 0.5394368457656437, "grad_norm": 5.976487636566162, "learning_rate": 9.998105930893638e-06, "loss": 0.6338, "step": 90750 }, { "epoch": 0.5394962878423121, "grad_norm": 6.46155309677124, "learning_rate": 9.998100215902459e-06, "loss": 0.6745, "step": 90760 }, { "epoch": 0.5395557299189805, "grad_norm": 5.928250312805176, "learning_rate": 9.998094492303954e-06, "loss": 0.6522, "step": 90770 }, { "epoch": 0.5396151719956488, "grad_norm": 6.7919535636901855, "learning_rate": 9.998088760098135e-06, "loss": 0.6227, "step": 90780 }, { "epoch": 0.5396746140723172, "grad_norm": 4.518336772918701, "learning_rate": 9.99808301928501e-06, "loss": 0.6095, "step": 90790 }, { "epoch": 0.5397340561489856, "grad_norm": 5.751503944396973, "learning_rate": 9.998077269864587e-06, "loss": 0.6646, "step": 90800 }, { "epoch": 0.539793498225654, "grad_norm": 5.185876369476318, "learning_rate": 9.998071511836883e-06, "loss": 0.5992, "step": 90810 }, { "epoch": 0.5398529403023224, "grad_norm": 5.6509809494018555, "learning_rate": 9.998065745201902e-06, "loss": 0.6294, "step": 90820 }, { "epoch": 0.5399123823789908, "grad_norm": 6.502552509307861, "learning_rate": 9.998059969959655e-06, "loss": 0.6513, "step": 90830 }, { "epoch": 0.5399718244556592, "grad_norm": 7.197525978088379, "learning_rate": 9.998054186110153e-06, "loss": 0.634, "step": 90840 }, { "epoch": 0.5400312665323276, "grad_norm": 6.080662727355957, "learning_rate": 9.998048393653403e-06, "loss": 0.5941, "step": 90850 }, { "epoch": 0.540090708608996, "grad_norm": 7.396804332733154, "learning_rate": 9.998042592589422e-06, "loss": 0.5802, "step": 90860 }, { "epoch": 0.5401501506856644, "grad_norm": 6.507374286651611, "learning_rate": 9.99803678291821e-06, "loss": 0.6946, "step": 90870 }, { "epoch": 0.5402095927623327, "grad_norm": 4.7284698486328125, "learning_rate": 9.998030964639786e-06, "loss": 0.6761, "step": 90880 }, { "epoch": 0.5402690348390011, "grad_norm": 5.651952266693115, "learning_rate": 9.998025137754156e-06, "loss": 0.6505, "step": 90890 }, { "epoch": 0.5403284769156695, "grad_norm": 7.160943508148193, "learning_rate": 9.998019302261329e-06, "loss": 0.6794, "step": 90900 }, { "epoch": 0.540387918992338, "grad_norm": 7.654560089111328, "learning_rate": 9.998013458161316e-06, "loss": 0.6785, "step": 90910 }, { "epoch": 0.5404473610690063, "grad_norm": 5.733213424682617, "learning_rate": 9.998007605454127e-06, "loss": 0.6558, "step": 90920 }, { "epoch": 0.5405068031456747, "grad_norm": 9.801177024841309, "learning_rate": 9.998001744139775e-06, "loss": 0.7379, "step": 90930 }, { "epoch": 0.5405662452223431, "grad_norm": 6.0263872146606445, "learning_rate": 9.997995874218268e-06, "loss": 0.6836, "step": 90940 }, { "epoch": 0.5406256872990115, "grad_norm": 5.515758037567139, "learning_rate": 9.997989995689613e-06, "loss": 0.65, "step": 90950 }, { "epoch": 0.5406851293756799, "grad_norm": 6.082840919494629, "learning_rate": 9.997984108553824e-06, "loss": 0.6615, "step": 90960 }, { "epoch": 0.5407445714523482, "grad_norm": 6.81723165512085, "learning_rate": 9.99797821281091e-06, "loss": 0.6538, "step": 90970 }, { "epoch": 0.5408040135290166, "grad_norm": 5.890774250030518, "learning_rate": 9.997972308460881e-06, "loss": 0.6267, "step": 90980 }, { "epoch": 0.540863455605685, "grad_norm": 5.270114421844482, "learning_rate": 9.997966395503749e-06, "loss": 0.6522, "step": 90990 }, { "epoch": 0.5409228976823535, "grad_norm": 5.679741859436035, "learning_rate": 9.99796047393952e-06, "loss": 0.7134, "step": 91000 }, { "epoch": 0.5409823397590218, "grad_norm": 6.5772929191589355, "learning_rate": 9.997954543768209e-06, "loss": 0.6517, "step": 91010 }, { "epoch": 0.5410417818356902, "grad_norm": 7.039292335510254, "learning_rate": 9.997948604989823e-06, "loss": 0.6197, "step": 91020 }, { "epoch": 0.5411012239123586, "grad_norm": 8.312034606933594, "learning_rate": 9.997942657604372e-06, "loss": 0.6383, "step": 91030 }, { "epoch": 0.541160665989027, "grad_norm": 6.193332672119141, "learning_rate": 9.997936701611867e-06, "loss": 0.6331, "step": 91040 }, { "epoch": 0.5412201080656954, "grad_norm": 6.180484771728516, "learning_rate": 9.99793073701232e-06, "loss": 0.6265, "step": 91050 }, { "epoch": 0.5412795501423637, "grad_norm": 6.63462495803833, "learning_rate": 9.997924763805742e-06, "loss": 0.6727, "step": 91060 }, { "epoch": 0.5413389922190321, "grad_norm": 5.780036926269531, "learning_rate": 9.997918781992139e-06, "loss": 0.6635, "step": 91070 }, { "epoch": 0.5413984342957006, "grad_norm": 6.886265277862549, "learning_rate": 9.997912791571523e-06, "loss": 0.682, "step": 91080 }, { "epoch": 0.541457876372369, "grad_norm": 5.992372512817383, "learning_rate": 9.997906792543905e-06, "loss": 0.6351, "step": 91090 }, { "epoch": 0.5415173184490374, "grad_norm": 7.256642818450928, "learning_rate": 9.997900784909296e-06, "loss": 0.6936, "step": 91100 }, { "epoch": 0.5415767605257057, "grad_norm": 8.232839584350586, "learning_rate": 9.997894768667707e-06, "loss": 0.6831, "step": 91110 }, { "epoch": 0.5416362026023741, "grad_norm": 7.593976020812988, "learning_rate": 9.997888743819143e-06, "loss": 0.6833, "step": 91120 }, { "epoch": 0.5416956446790425, "grad_norm": 7.8385491371154785, "learning_rate": 9.997882710363621e-06, "loss": 0.701, "step": 91130 }, { "epoch": 0.5417550867557109, "grad_norm": 5.89643669128418, "learning_rate": 9.997876668301147e-06, "loss": 0.6575, "step": 91140 }, { "epoch": 0.5418145288323792, "grad_norm": 6.531380653381348, "learning_rate": 9.997870617631735e-06, "loss": 0.6571, "step": 91150 }, { "epoch": 0.5418739709090477, "grad_norm": 6.545494079589844, "learning_rate": 9.997864558355392e-06, "loss": 0.596, "step": 91160 }, { "epoch": 0.5419334129857161, "grad_norm": 6.286602973937988, "learning_rate": 9.99785849047213e-06, "loss": 0.6457, "step": 91170 }, { "epoch": 0.5419928550623845, "grad_norm": 5.488047122955322, "learning_rate": 9.99785241398196e-06, "loss": 0.673, "step": 91180 }, { "epoch": 0.5420522971390529, "grad_norm": 5.040625095367432, "learning_rate": 9.997846328884893e-06, "loss": 0.6467, "step": 91190 }, { "epoch": 0.5421117392157212, "grad_norm": 6.533397197723389, "learning_rate": 9.997840235180936e-06, "loss": 0.6675, "step": 91200 }, { "epoch": 0.5421711812923896, "grad_norm": 6.976399898529053, "learning_rate": 9.997834132870102e-06, "loss": 0.6151, "step": 91210 }, { "epoch": 0.542230623369058, "grad_norm": 6.086567401885986, "learning_rate": 9.997828021952403e-06, "loss": 0.6583, "step": 91220 }, { "epoch": 0.5422900654457264, "grad_norm": 7.002323627471924, "learning_rate": 9.997821902427847e-06, "loss": 0.664, "step": 91230 }, { "epoch": 0.5423495075223947, "grad_norm": 5.813946723937988, "learning_rate": 9.997815774296445e-06, "loss": 0.7035, "step": 91240 }, { "epoch": 0.5424089495990632, "grad_norm": 5.880717754364014, "learning_rate": 9.997809637558207e-06, "loss": 0.6829, "step": 91250 }, { "epoch": 0.5424683916757316, "grad_norm": 6.276265621185303, "learning_rate": 9.997803492213145e-06, "loss": 0.6504, "step": 91260 }, { "epoch": 0.5425278337524, "grad_norm": 7.173864364624023, "learning_rate": 9.99779733826127e-06, "loss": 0.7265, "step": 91270 }, { "epoch": 0.5425872758290684, "grad_norm": 6.141860008239746, "learning_rate": 9.997791175702592e-06, "loss": 0.6621, "step": 91280 }, { "epoch": 0.5426467179057367, "grad_norm": 7.637052536010742, "learning_rate": 9.99778500453712e-06, "loss": 0.7173, "step": 91290 }, { "epoch": 0.5427061599824051, "grad_norm": 6.399600028991699, "learning_rate": 9.997778824764865e-06, "loss": 0.6818, "step": 91300 }, { "epoch": 0.5427656020590735, "grad_norm": 5.932467937469482, "learning_rate": 9.997772636385841e-06, "loss": 0.6445, "step": 91310 }, { "epoch": 0.542825044135742, "grad_norm": 6.004920959472656, "learning_rate": 9.997766439400054e-06, "loss": 0.6106, "step": 91320 }, { "epoch": 0.5428844862124104, "grad_norm": 8.394164085388184, "learning_rate": 9.997760233807519e-06, "loss": 0.6665, "step": 91330 }, { "epoch": 0.5429439282890787, "grad_norm": 6.441202163696289, "learning_rate": 9.997754019608244e-06, "loss": 0.6053, "step": 91340 }, { "epoch": 0.5430033703657471, "grad_norm": 7.058652877807617, "learning_rate": 9.997747796802238e-06, "loss": 0.6791, "step": 91350 }, { "epoch": 0.5430628124424155, "grad_norm": 5.90024471282959, "learning_rate": 9.997741565389516e-06, "loss": 0.6298, "step": 91360 }, { "epoch": 0.5431222545190839, "grad_norm": 5.330049991607666, "learning_rate": 9.997735325370087e-06, "loss": 0.6461, "step": 91370 }, { "epoch": 0.5431816965957522, "grad_norm": 5.801743030548096, "learning_rate": 9.99772907674396e-06, "loss": 0.6341, "step": 91380 }, { "epoch": 0.5432411386724206, "grad_norm": 6.560720443725586, "learning_rate": 9.997722819511149e-06, "loss": 0.6931, "step": 91390 }, { "epoch": 0.543300580749089, "grad_norm": 7.335829257965088, "learning_rate": 9.997716553671661e-06, "loss": 0.6525, "step": 91400 }, { "epoch": 0.5433600228257575, "grad_norm": 6.950683116912842, "learning_rate": 9.99771027922551e-06, "loss": 0.6018, "step": 91410 }, { "epoch": 0.5434194649024259, "grad_norm": 7.396005153656006, "learning_rate": 9.997703996172705e-06, "loss": 0.6567, "step": 91420 }, { "epoch": 0.5434789069790942, "grad_norm": 5.734148025512695, "learning_rate": 9.997697704513258e-06, "loss": 0.6631, "step": 91430 }, { "epoch": 0.5435383490557626, "grad_norm": 6.581025123596191, "learning_rate": 9.99769140424718e-06, "loss": 0.6606, "step": 91440 }, { "epoch": 0.543597791132431, "grad_norm": 6.662840366363525, "learning_rate": 9.99768509537448e-06, "loss": 0.6694, "step": 91450 }, { "epoch": 0.5436572332090994, "grad_norm": 9.536935806274414, "learning_rate": 9.99767877789517e-06, "loss": 0.6386, "step": 91460 }, { "epoch": 0.5437166752857678, "grad_norm": 5.851511478424072, "learning_rate": 9.99767245180926e-06, "loss": 0.6887, "step": 91470 }, { "epoch": 0.5437761173624361, "grad_norm": 6.078502178192139, "learning_rate": 9.997666117116763e-06, "loss": 0.6859, "step": 91480 }, { "epoch": 0.5438355594391046, "grad_norm": 6.237645149230957, "learning_rate": 9.997659773817688e-06, "loss": 0.6976, "step": 91490 }, { "epoch": 0.543895001515773, "grad_norm": 5.745992660522461, "learning_rate": 9.997653421912048e-06, "loss": 0.6365, "step": 91500 }, { "epoch": 0.5439544435924414, "grad_norm": 9.564861297607422, "learning_rate": 9.99764706139985e-06, "loss": 0.6323, "step": 91510 }, { "epoch": 0.5440138856691097, "grad_norm": 7.07289981842041, "learning_rate": 9.99764069228111e-06, "loss": 0.6627, "step": 91520 }, { "epoch": 0.5440733277457781, "grad_norm": 6.259512901306152, "learning_rate": 9.997634314555834e-06, "loss": 0.7271, "step": 91530 }, { "epoch": 0.5441327698224465, "grad_norm": 5.325141906738281, "learning_rate": 9.997627928224036e-06, "loss": 0.7123, "step": 91540 }, { "epoch": 0.5441922118991149, "grad_norm": 5.51387357711792, "learning_rate": 9.997621533285728e-06, "loss": 0.648, "step": 91550 }, { "epoch": 0.5442516539757833, "grad_norm": 5.150206089019775, "learning_rate": 9.997615129740919e-06, "loss": 0.6543, "step": 91560 }, { "epoch": 0.5443110960524516, "grad_norm": 5.385709285736084, "learning_rate": 9.99760871758962e-06, "loss": 0.6902, "step": 91570 }, { "epoch": 0.5443705381291201, "grad_norm": 6.232475280761719, "learning_rate": 9.99760229683184e-06, "loss": 0.6672, "step": 91580 }, { "epoch": 0.5444299802057885, "grad_norm": 5.592775821685791, "learning_rate": 9.997595867467597e-06, "loss": 0.661, "step": 91590 }, { "epoch": 0.5444894222824569, "grad_norm": 5.956155300140381, "learning_rate": 9.997589429496894e-06, "loss": 0.6869, "step": 91600 }, { "epoch": 0.5445488643591252, "grad_norm": 6.404047966003418, "learning_rate": 9.997582982919747e-06, "loss": 0.6512, "step": 91610 }, { "epoch": 0.5446083064357936, "grad_norm": 5.171703338623047, "learning_rate": 9.997576527736166e-06, "loss": 0.6076, "step": 91620 }, { "epoch": 0.544667748512462, "grad_norm": 6.082269668579102, "learning_rate": 9.997570063946163e-06, "loss": 0.7088, "step": 91630 }, { "epoch": 0.5447271905891304, "grad_norm": 6.584683418273926, "learning_rate": 9.997563591549748e-06, "loss": 0.5982, "step": 91640 }, { "epoch": 0.5447866326657989, "grad_norm": 6.956489562988281, "learning_rate": 9.997557110546929e-06, "loss": 0.688, "step": 91650 }, { "epoch": 0.5448460747424672, "grad_norm": 5.915832042694092, "learning_rate": 9.997550620937725e-06, "loss": 0.6842, "step": 91660 }, { "epoch": 0.5449055168191356, "grad_norm": 5.8660149574279785, "learning_rate": 9.997544122722139e-06, "loss": 0.6565, "step": 91670 }, { "epoch": 0.544964958895804, "grad_norm": 5.828631401062012, "learning_rate": 9.997537615900185e-06, "loss": 0.6365, "step": 91680 }, { "epoch": 0.5450244009724724, "grad_norm": 5.5042829513549805, "learning_rate": 9.997531100471877e-06, "loss": 0.6392, "step": 91690 }, { "epoch": 0.5450838430491408, "grad_norm": 6.006296157836914, "learning_rate": 9.997524576437225e-06, "loss": 0.6458, "step": 91700 }, { "epoch": 0.5451432851258091, "grad_norm": 5.543455123901367, "learning_rate": 9.997518043796238e-06, "loss": 0.6159, "step": 91710 }, { "epoch": 0.5452027272024775, "grad_norm": 7.174450874328613, "learning_rate": 9.997511502548929e-06, "loss": 0.6651, "step": 91720 }, { "epoch": 0.545262169279146, "grad_norm": 5.194799423217773, "learning_rate": 9.99750495269531e-06, "loss": 0.712, "step": 91730 }, { "epoch": 0.5453216113558144, "grad_norm": 8.113526344299316, "learning_rate": 9.997498394235388e-06, "loss": 0.6768, "step": 91740 }, { "epoch": 0.5453810534324827, "grad_norm": 6.17117166519165, "learning_rate": 9.99749182716918e-06, "loss": 0.6116, "step": 91750 }, { "epoch": 0.5454404955091511, "grad_norm": 7.334513187408447, "learning_rate": 9.997485251496695e-06, "loss": 0.6827, "step": 91760 }, { "epoch": 0.5454999375858195, "grad_norm": 5.731266975402832, "learning_rate": 9.997478667217943e-06, "loss": 0.637, "step": 91770 }, { "epoch": 0.5455593796624879, "grad_norm": 5.558216571807861, "learning_rate": 9.997472074332937e-06, "loss": 0.6513, "step": 91780 }, { "epoch": 0.5456188217391563, "grad_norm": 7.803369045257568, "learning_rate": 9.997465472841687e-06, "loss": 0.6165, "step": 91790 }, { "epoch": 0.5456782638158246, "grad_norm": 5.984776496887207, "learning_rate": 9.997458862744204e-06, "loss": 0.6353, "step": 91800 }, { "epoch": 0.545737705892493, "grad_norm": 7.478011131286621, "learning_rate": 9.997452244040505e-06, "loss": 0.6428, "step": 91810 }, { "epoch": 0.5457971479691615, "grad_norm": 6.363237380981445, "learning_rate": 9.997445616730593e-06, "loss": 0.6636, "step": 91820 }, { "epoch": 0.5458565900458299, "grad_norm": 5.601438045501709, "learning_rate": 9.997438980814484e-06, "loss": 0.6491, "step": 91830 }, { "epoch": 0.5459160321224983, "grad_norm": 4.769707679748535, "learning_rate": 9.99743233629219e-06, "loss": 0.646, "step": 91840 }, { "epoch": 0.5459754741991666, "grad_norm": 4.783902168273926, "learning_rate": 9.99742568316372e-06, "loss": 0.6587, "step": 91850 }, { "epoch": 0.546034916275835, "grad_norm": 6.03143835067749, "learning_rate": 9.997419021429087e-06, "loss": 0.6551, "step": 91860 }, { "epoch": 0.5460943583525034, "grad_norm": 5.148185729980469, "learning_rate": 9.997412351088302e-06, "loss": 0.6902, "step": 91870 }, { "epoch": 0.5461538004291718, "grad_norm": 5.875600814819336, "learning_rate": 9.997405672141378e-06, "loss": 0.6297, "step": 91880 }, { "epoch": 0.5462132425058401, "grad_norm": 5.9734344482421875, "learning_rate": 9.997398984588324e-06, "loss": 0.6375, "step": 91890 }, { "epoch": 0.5462726845825085, "grad_norm": 7.305273056030273, "learning_rate": 9.997392288429154e-06, "loss": 0.6167, "step": 91900 }, { "epoch": 0.546332126659177, "grad_norm": 5.727531433105469, "learning_rate": 9.997385583663877e-06, "loss": 0.5544, "step": 91910 }, { "epoch": 0.5463915687358454, "grad_norm": 7.752143859863281, "learning_rate": 9.997378870292506e-06, "loss": 0.7109, "step": 91920 }, { "epoch": 0.5464510108125138, "grad_norm": 4.835732460021973, "learning_rate": 9.997372148315053e-06, "loss": 0.6593, "step": 91930 }, { "epoch": 0.5465104528891821, "grad_norm": 6.458043575286865, "learning_rate": 9.997365417731526e-06, "loss": 0.6302, "step": 91940 }, { "epoch": 0.5465698949658505, "grad_norm": 4.477285385131836, "learning_rate": 9.997358678541941e-06, "loss": 0.6564, "step": 91950 }, { "epoch": 0.5466293370425189, "grad_norm": 6.7963714599609375, "learning_rate": 9.997351930746309e-06, "loss": 0.6399, "step": 91960 }, { "epoch": 0.5466887791191873, "grad_norm": 5.804567813873291, "learning_rate": 9.997345174344642e-06, "loss": 0.6283, "step": 91970 }, { "epoch": 0.5467482211958556, "grad_norm": 6.794025897979736, "learning_rate": 9.997338409336948e-06, "loss": 0.6046, "step": 91980 }, { "epoch": 0.5468076632725241, "grad_norm": 6.146598815917969, "learning_rate": 9.997331635723241e-06, "loss": 0.634, "step": 91990 }, { "epoch": 0.5468671053491925, "grad_norm": 9.286639213562012, "learning_rate": 9.997324853503534e-06, "loss": 0.7589, "step": 92000 }, { "epoch": 0.5469265474258609, "grad_norm": 5.949222087860107, "learning_rate": 9.997318062677837e-06, "loss": 0.6548, "step": 92010 }, { "epoch": 0.5469859895025293, "grad_norm": 5.5876569747924805, "learning_rate": 9.997311263246161e-06, "loss": 0.6296, "step": 92020 }, { "epoch": 0.5470454315791976, "grad_norm": 5.443439483642578, "learning_rate": 9.997304455208519e-06, "loss": 0.6567, "step": 92030 }, { "epoch": 0.547104873655866, "grad_norm": 5.466349124908447, "learning_rate": 9.997297638564924e-06, "loss": 0.6315, "step": 92040 }, { "epoch": 0.5471643157325344, "grad_norm": 5.247799873352051, "learning_rate": 9.997290813315384e-06, "loss": 0.6196, "step": 92050 }, { "epoch": 0.5472237578092028, "grad_norm": 7.124579906463623, "learning_rate": 9.997283979459915e-06, "loss": 0.6541, "step": 92060 }, { "epoch": 0.5472831998858713, "grad_norm": 7.388149738311768, "learning_rate": 9.997277136998525e-06, "loss": 0.6517, "step": 92070 }, { "epoch": 0.5473426419625396, "grad_norm": 5.380115509033203, "learning_rate": 9.99727028593123e-06, "loss": 0.6548, "step": 92080 }, { "epoch": 0.547402084039208, "grad_norm": 5.687150478363037, "learning_rate": 9.997263426258035e-06, "loss": 0.6524, "step": 92090 }, { "epoch": 0.5474615261158764, "grad_norm": 6.036008358001709, "learning_rate": 9.997256557978959e-06, "loss": 0.6745, "step": 92100 }, { "epoch": 0.5475209681925448, "grad_norm": 4.768182754516602, "learning_rate": 9.99724968109401e-06, "loss": 0.6727, "step": 92110 }, { "epoch": 0.5475804102692131, "grad_norm": 5.483591079711914, "learning_rate": 9.997242795603202e-06, "loss": 0.5966, "step": 92120 }, { "epoch": 0.5476398523458815, "grad_norm": 7.328811168670654, "learning_rate": 9.997235901506546e-06, "loss": 0.6662, "step": 92130 }, { "epoch": 0.5476992944225499, "grad_norm": 6.420589923858643, "learning_rate": 9.997228998804051e-06, "loss": 0.6574, "step": 92140 }, { "epoch": 0.5477587364992184, "grad_norm": 6.534322738647461, "learning_rate": 9.997222087495734e-06, "loss": 0.6484, "step": 92150 }, { "epoch": 0.5478181785758868, "grad_norm": 7.071312427520752, "learning_rate": 9.997215167581604e-06, "loss": 0.6217, "step": 92160 }, { "epoch": 0.5478776206525551, "grad_norm": 5.590417385101318, "learning_rate": 9.997208239061671e-06, "loss": 0.6547, "step": 92170 }, { "epoch": 0.5479370627292235, "grad_norm": 4.310460567474365, "learning_rate": 9.99720130193595e-06, "loss": 0.5966, "step": 92180 }, { "epoch": 0.5479965048058919, "grad_norm": 5.195341110229492, "learning_rate": 9.997194356204454e-06, "loss": 0.6506, "step": 92190 }, { "epoch": 0.5480559468825603, "grad_norm": 7.6769118309021, "learning_rate": 9.997187401867192e-06, "loss": 0.6789, "step": 92200 }, { "epoch": 0.5481153889592287, "grad_norm": 5.987537384033203, "learning_rate": 9.997180438924177e-06, "loss": 0.6023, "step": 92210 }, { "epoch": 0.548174831035897, "grad_norm": 6.570108413696289, "learning_rate": 9.99717346737542e-06, "loss": 0.6431, "step": 92220 }, { "epoch": 0.5482342731125655, "grad_norm": 5.719540119171143, "learning_rate": 9.997166487220936e-06, "loss": 0.5819, "step": 92230 }, { "epoch": 0.5482937151892339, "grad_norm": 6.186970233917236, "learning_rate": 9.997159498460733e-06, "loss": 0.6998, "step": 92240 }, { "epoch": 0.5483531572659023, "grad_norm": 5.782939434051514, "learning_rate": 9.997152501094827e-06, "loss": 0.6742, "step": 92250 }, { "epoch": 0.5484125993425706, "grad_norm": 5.784806728363037, "learning_rate": 9.997145495123225e-06, "loss": 0.6688, "step": 92260 }, { "epoch": 0.548472041419239, "grad_norm": 5.737752437591553, "learning_rate": 9.997138480545945e-06, "loss": 0.7434, "step": 92270 }, { "epoch": 0.5485314834959074, "grad_norm": 6.134668827056885, "learning_rate": 9.997131457362996e-06, "loss": 0.6861, "step": 92280 }, { "epoch": 0.5485909255725758, "grad_norm": 5.294857025146484, "learning_rate": 9.997124425574391e-06, "loss": 0.6483, "step": 92290 }, { "epoch": 0.5486503676492442, "grad_norm": 4.748249053955078, "learning_rate": 9.99711738518014e-06, "loss": 0.6181, "step": 92300 }, { "epoch": 0.5487098097259125, "grad_norm": 4.742798328399658, "learning_rate": 9.997110336180257e-06, "loss": 0.6851, "step": 92310 }, { "epoch": 0.548769251802581, "grad_norm": 5.830080509185791, "learning_rate": 9.997103278574753e-06, "loss": 0.7154, "step": 92320 }, { "epoch": 0.5488286938792494, "grad_norm": 6.837980270385742, "learning_rate": 9.997096212363642e-06, "loss": 0.6266, "step": 92330 }, { "epoch": 0.5488881359559178, "grad_norm": 5.849221706390381, "learning_rate": 9.997089137546935e-06, "loss": 0.6035, "step": 92340 }, { "epoch": 0.5489475780325861, "grad_norm": 7.151184558868408, "learning_rate": 9.997082054124645e-06, "loss": 0.7061, "step": 92350 }, { "epoch": 0.5490070201092545, "grad_norm": 6.249497890472412, "learning_rate": 9.997074962096783e-06, "loss": 0.6944, "step": 92360 }, { "epoch": 0.5490664621859229, "grad_norm": 7.152031421661377, "learning_rate": 9.99706786146336e-06, "loss": 0.636, "step": 92370 }, { "epoch": 0.5491259042625913, "grad_norm": 6.6305012702941895, "learning_rate": 9.997060752224392e-06, "loss": 0.6559, "step": 92380 }, { "epoch": 0.5491853463392598, "grad_norm": 5.674271106719971, "learning_rate": 9.997053634379889e-06, "loss": 0.6662, "step": 92390 }, { "epoch": 0.549244788415928, "grad_norm": 6.760499000549316, "learning_rate": 9.997046507929861e-06, "loss": 0.6839, "step": 92400 }, { "epoch": 0.5493042304925965, "grad_norm": 4.262292861938477, "learning_rate": 9.997039372874325e-06, "loss": 0.638, "step": 92410 }, { "epoch": 0.5493636725692649, "grad_norm": 5.490090847015381, "learning_rate": 9.99703222921329e-06, "loss": 0.6224, "step": 92420 }, { "epoch": 0.5494231146459333, "grad_norm": 5.6189680099487305, "learning_rate": 9.99702507694677e-06, "loss": 0.6879, "step": 92430 }, { "epoch": 0.5494825567226017, "grad_norm": 5.66510009765625, "learning_rate": 9.997017916074776e-06, "loss": 0.6122, "step": 92440 }, { "epoch": 0.54954199879927, "grad_norm": 5.768721103668213, "learning_rate": 9.997010746597322e-06, "loss": 0.6744, "step": 92450 }, { "epoch": 0.5496014408759384, "grad_norm": 6.008178234100342, "learning_rate": 9.997003568514419e-06, "loss": 0.6654, "step": 92460 }, { "epoch": 0.5496608829526068, "grad_norm": 5.164417266845703, "learning_rate": 9.996996381826078e-06, "loss": 0.6476, "step": 92470 }, { "epoch": 0.5497203250292753, "grad_norm": 7.163695812225342, "learning_rate": 9.996989186532314e-06, "loss": 0.6326, "step": 92480 }, { "epoch": 0.5497797671059436, "grad_norm": 7.498879909515381, "learning_rate": 9.996981982633138e-06, "loss": 0.678, "step": 92490 }, { "epoch": 0.549839209182612, "grad_norm": 6.046376705169678, "learning_rate": 9.996974770128564e-06, "loss": 0.6134, "step": 92500 }, { "epoch": 0.5498986512592804, "grad_norm": 7.085604667663574, "learning_rate": 9.996967549018602e-06, "loss": 0.5803, "step": 92510 }, { "epoch": 0.5499580933359488, "grad_norm": 5.815680027008057, "learning_rate": 9.996960319303266e-06, "loss": 0.6562, "step": 92520 }, { "epoch": 0.5500175354126172, "grad_norm": 3.964920997619629, "learning_rate": 9.99695308098257e-06, "loss": 0.644, "step": 92530 }, { "epoch": 0.5500769774892855, "grad_norm": 5.59137487411499, "learning_rate": 9.996945834056522e-06, "loss": 0.6916, "step": 92540 }, { "epoch": 0.5501364195659539, "grad_norm": 5.2209553718566895, "learning_rate": 9.996938578525137e-06, "loss": 0.6456, "step": 92550 }, { "epoch": 0.5501958616426224, "grad_norm": 5.567060470581055, "learning_rate": 9.996931314388429e-06, "loss": 0.6382, "step": 92560 }, { "epoch": 0.5502553037192908, "grad_norm": 5.2699809074401855, "learning_rate": 9.996924041646407e-06, "loss": 0.6175, "step": 92570 }, { "epoch": 0.5503147457959592, "grad_norm": 7.796109199523926, "learning_rate": 9.996916760299089e-06, "loss": 0.6709, "step": 92580 }, { "epoch": 0.5503741878726275, "grad_norm": 6.325104236602783, "learning_rate": 9.996909470346481e-06, "loss": 0.6496, "step": 92590 }, { "epoch": 0.5504336299492959, "grad_norm": 5.974628448486328, "learning_rate": 9.9969021717886e-06, "loss": 0.5898, "step": 92600 }, { "epoch": 0.5504930720259643, "grad_norm": 6.185365200042725, "learning_rate": 9.996894864625457e-06, "loss": 0.6494, "step": 92610 }, { "epoch": 0.5505525141026327, "grad_norm": 5.377599239349365, "learning_rate": 9.996887548857065e-06, "loss": 0.6337, "step": 92620 }, { "epoch": 0.550611956179301, "grad_norm": 5.916174411773682, "learning_rate": 9.996880224483436e-06, "loss": 0.63, "step": 92630 }, { "epoch": 0.5506713982559694, "grad_norm": 4.947421550750732, "learning_rate": 9.996872891504583e-06, "loss": 0.6348, "step": 92640 }, { "epoch": 0.5507308403326379, "grad_norm": 4.449533462524414, "learning_rate": 9.996865549920518e-06, "loss": 0.6437, "step": 92650 }, { "epoch": 0.5507902824093063, "grad_norm": 4.4853339195251465, "learning_rate": 9.996858199731256e-06, "loss": 0.6214, "step": 92660 }, { "epoch": 0.5508497244859747, "grad_norm": 5.040434837341309, "learning_rate": 9.996850840936808e-06, "loss": 0.6231, "step": 92670 }, { "epoch": 0.550909166562643, "grad_norm": 5.182754993438721, "learning_rate": 9.996843473537186e-06, "loss": 0.6707, "step": 92680 }, { "epoch": 0.5509686086393114, "grad_norm": 7.105546474456787, "learning_rate": 9.996836097532402e-06, "loss": 0.6552, "step": 92690 }, { "epoch": 0.5510280507159798, "grad_norm": 5.667532920837402, "learning_rate": 9.996828712922474e-06, "loss": 0.6255, "step": 92700 }, { "epoch": 0.5510874927926482, "grad_norm": 6.479531764984131, "learning_rate": 9.996821319707405e-06, "loss": 0.6543, "step": 92710 }, { "epoch": 0.5511469348693165, "grad_norm": 5.721616268157959, "learning_rate": 9.996813917887219e-06, "loss": 0.6728, "step": 92720 }, { "epoch": 0.551206376945985, "grad_norm": 5.901236057281494, "learning_rate": 9.99680650746192e-06, "loss": 0.6331, "step": 92730 }, { "epoch": 0.5512658190226534, "grad_norm": 5.73207426071167, "learning_rate": 9.996799088431523e-06, "loss": 0.6848, "step": 92740 }, { "epoch": 0.5513252610993218, "grad_norm": 5.051036834716797, "learning_rate": 9.996791660796043e-06, "loss": 0.6285, "step": 92750 }, { "epoch": 0.5513847031759902, "grad_norm": 5.701741695404053, "learning_rate": 9.996784224555494e-06, "loss": 0.5771, "step": 92760 }, { "epoch": 0.5514441452526585, "grad_norm": 6.928024768829346, "learning_rate": 9.996776779709884e-06, "loss": 0.674, "step": 92770 }, { "epoch": 0.5515035873293269, "grad_norm": 7.070103168487549, "learning_rate": 9.996769326259228e-06, "loss": 0.6529, "step": 92780 }, { "epoch": 0.5515630294059953, "grad_norm": 7.2303619384765625, "learning_rate": 9.996761864203539e-06, "loss": 0.7362, "step": 92790 }, { "epoch": 0.5516224714826637, "grad_norm": 5.8549981117248535, "learning_rate": 9.996754393542832e-06, "loss": 0.6616, "step": 92800 }, { "epoch": 0.5516819135593322, "grad_norm": 6.830708026885986, "learning_rate": 9.996746914277115e-06, "loss": 0.6384, "step": 92810 }, { "epoch": 0.5517413556360005, "grad_norm": 6.498725891113281, "learning_rate": 9.996739426406405e-06, "loss": 0.6855, "step": 92820 }, { "epoch": 0.5518007977126689, "grad_norm": 7.028653621673584, "learning_rate": 9.996731929930713e-06, "loss": 0.72, "step": 92830 }, { "epoch": 0.5518602397893373, "grad_norm": 8.095261573791504, "learning_rate": 9.996724424850053e-06, "loss": 0.6656, "step": 92840 }, { "epoch": 0.5519196818660057, "grad_norm": 5.574692249298096, "learning_rate": 9.996716911164437e-06, "loss": 0.6672, "step": 92850 }, { "epoch": 0.551979123942674, "grad_norm": 6.919304847717285, "learning_rate": 9.996709388873878e-06, "loss": 0.6576, "step": 92860 }, { "epoch": 0.5520385660193424, "grad_norm": 5.914813041687012, "learning_rate": 9.99670185797839e-06, "loss": 0.6419, "step": 92870 }, { "epoch": 0.5520980080960108, "grad_norm": 6.35125207901001, "learning_rate": 9.996694318477984e-06, "loss": 0.6331, "step": 92880 }, { "epoch": 0.5521574501726793, "grad_norm": 6.36091423034668, "learning_rate": 9.996686770372675e-06, "loss": 0.6222, "step": 92890 }, { "epoch": 0.5522168922493477, "grad_norm": 8.622232437133789, "learning_rate": 9.996679213662475e-06, "loss": 0.6859, "step": 92900 }, { "epoch": 0.552276334326016, "grad_norm": 4.497962474822998, "learning_rate": 9.996671648347396e-06, "loss": 0.6232, "step": 92910 }, { "epoch": 0.5523357764026844, "grad_norm": 6.161526679992676, "learning_rate": 9.996664074427454e-06, "loss": 0.6119, "step": 92920 }, { "epoch": 0.5523952184793528, "grad_norm": 7.876333236694336, "learning_rate": 9.996656491902661e-06, "loss": 0.6561, "step": 92930 }, { "epoch": 0.5524546605560212, "grad_norm": 6.487942218780518, "learning_rate": 9.996648900773027e-06, "loss": 0.6803, "step": 92940 }, { "epoch": 0.5525141026326896, "grad_norm": 7.116919040679932, "learning_rate": 9.99664130103857e-06, "loss": 0.6514, "step": 92950 }, { "epoch": 0.5525735447093579, "grad_norm": 5.596679210662842, "learning_rate": 9.996633692699298e-06, "loss": 0.6485, "step": 92960 }, { "epoch": 0.5526329867860263, "grad_norm": 6.500000953674316, "learning_rate": 9.996626075755226e-06, "loss": 0.6085, "step": 92970 }, { "epoch": 0.5526924288626948, "grad_norm": 5.049543857574463, "learning_rate": 9.99661845020637e-06, "loss": 0.644, "step": 92980 }, { "epoch": 0.5527518709393632, "grad_norm": 5.140178203582764, "learning_rate": 9.99661081605274e-06, "loss": 0.6618, "step": 92990 }, { "epoch": 0.5528113130160315, "grad_norm": 6.708329200744629, "learning_rate": 9.996603173294352e-06, "loss": 0.6369, "step": 93000 }, { "epoch": 0.5528707550926999, "grad_norm": 5.108354091644287, "learning_rate": 9.996595521931214e-06, "loss": 0.6567, "step": 93010 }, { "epoch": 0.5529301971693683, "grad_norm": 5.6769256591796875, "learning_rate": 9.996587861963344e-06, "loss": 0.6438, "step": 93020 }, { "epoch": 0.5529896392460367, "grad_norm": 6.311227798461914, "learning_rate": 9.996580193390753e-06, "loss": 0.6526, "step": 93030 }, { "epoch": 0.5530490813227051, "grad_norm": 6.393005847930908, "learning_rate": 9.996572516213456e-06, "loss": 0.6118, "step": 93040 }, { "epoch": 0.5531085233993734, "grad_norm": 7.5890302658081055, "learning_rate": 9.996564830431464e-06, "loss": 0.6673, "step": 93050 }, { "epoch": 0.5531679654760419, "grad_norm": 5.5045270919799805, "learning_rate": 9.99655713604479e-06, "loss": 0.6248, "step": 93060 }, { "epoch": 0.5532274075527103, "grad_norm": 6.07085657119751, "learning_rate": 9.996549433053449e-06, "loss": 0.6113, "step": 93070 }, { "epoch": 0.5532868496293787, "grad_norm": 6.190689563751221, "learning_rate": 9.996541721457454e-06, "loss": 0.6244, "step": 93080 }, { "epoch": 0.553346291706047, "grad_norm": 4.366013050079346, "learning_rate": 9.996534001256819e-06, "loss": 0.6031, "step": 93090 }, { "epoch": 0.5534057337827154, "grad_norm": 5.102683067321777, "learning_rate": 9.996526272451554e-06, "loss": 0.6343, "step": 93100 }, { "epoch": 0.5534651758593838, "grad_norm": 6.522731781005859, "learning_rate": 9.996518535041677e-06, "loss": 0.6668, "step": 93110 }, { "epoch": 0.5535246179360522, "grad_norm": 6.856027126312256, "learning_rate": 9.996510789027198e-06, "loss": 0.6785, "step": 93120 }, { "epoch": 0.5535840600127206, "grad_norm": 6.231472015380859, "learning_rate": 9.99650303440813e-06, "loss": 0.6207, "step": 93130 }, { "epoch": 0.553643502089389, "grad_norm": 5.15627908706665, "learning_rate": 9.996495271184489e-06, "loss": 0.6407, "step": 93140 }, { "epoch": 0.5537029441660574, "grad_norm": 6.7405924797058105, "learning_rate": 9.996487499356286e-06, "loss": 0.6449, "step": 93150 }, { "epoch": 0.5537623862427258, "grad_norm": 4.879334926605225, "learning_rate": 9.996479718923538e-06, "loss": 0.6622, "step": 93160 }, { "epoch": 0.5538218283193942, "grad_norm": 4.398200511932373, "learning_rate": 9.996471929886253e-06, "loss": 0.6347, "step": 93170 }, { "epoch": 0.5538812703960626, "grad_norm": 6.8133344650268555, "learning_rate": 9.996464132244448e-06, "loss": 0.6964, "step": 93180 }, { "epoch": 0.5539407124727309, "grad_norm": 5.702037334442139, "learning_rate": 9.996456325998136e-06, "loss": 0.7053, "step": 93190 }, { "epoch": 0.5540001545493993, "grad_norm": 6.580686092376709, "learning_rate": 9.99644851114733e-06, "loss": 0.6139, "step": 93200 }, { "epoch": 0.5540595966260677, "grad_norm": 5.398643493652344, "learning_rate": 9.996440687692042e-06, "loss": 0.6867, "step": 93210 }, { "epoch": 0.5541190387027362, "grad_norm": 6.908047676086426, "learning_rate": 9.996432855632287e-06, "loss": 0.6504, "step": 93220 }, { "epoch": 0.5541784807794045, "grad_norm": 4.461968898773193, "learning_rate": 9.996425014968082e-06, "loss": 0.613, "step": 93230 }, { "epoch": 0.5542379228560729, "grad_norm": 8.300826072692871, "learning_rate": 9.996417165699432e-06, "loss": 0.6805, "step": 93240 }, { "epoch": 0.5542973649327413, "grad_norm": 6.324769496917725, "learning_rate": 9.996409307826358e-06, "loss": 0.6152, "step": 93250 }, { "epoch": 0.5543568070094097, "grad_norm": 4.568146228790283, "learning_rate": 9.996401441348873e-06, "loss": 0.6124, "step": 93260 }, { "epoch": 0.5544162490860781, "grad_norm": 7.036540985107422, "learning_rate": 9.996393566266986e-06, "loss": 0.644, "step": 93270 }, { "epoch": 0.5544756911627464, "grad_norm": 5.4899516105651855, "learning_rate": 9.996385682580713e-06, "loss": 0.6951, "step": 93280 }, { "epoch": 0.5545351332394148, "grad_norm": 7.435302257537842, "learning_rate": 9.996377790290068e-06, "loss": 0.6858, "step": 93290 }, { "epoch": 0.5545945753160832, "grad_norm": 5.460637092590332, "learning_rate": 9.996369889395066e-06, "loss": 0.6642, "step": 93300 }, { "epoch": 0.5546540173927517, "grad_norm": 5.507162094116211, "learning_rate": 9.996361979895716e-06, "loss": 0.6533, "step": 93310 }, { "epoch": 0.5547134594694201, "grad_norm": 5.255807876586914, "learning_rate": 9.996354061792037e-06, "loss": 0.5921, "step": 93320 }, { "epoch": 0.5547729015460884, "grad_norm": 5.756307601928711, "learning_rate": 9.996346135084039e-06, "loss": 0.6397, "step": 93330 }, { "epoch": 0.5548323436227568, "grad_norm": 5.826145172119141, "learning_rate": 9.996338199771736e-06, "loss": 0.6124, "step": 93340 }, { "epoch": 0.5548917856994252, "grad_norm": 5.927133560180664, "learning_rate": 9.996330255855145e-06, "loss": 0.7016, "step": 93350 }, { "epoch": 0.5549512277760936, "grad_norm": 4.978100299835205, "learning_rate": 9.996322303334275e-06, "loss": 0.6467, "step": 93360 }, { "epoch": 0.5550106698527619, "grad_norm": 5.755706787109375, "learning_rate": 9.996314342209142e-06, "loss": 0.6231, "step": 93370 }, { "epoch": 0.5550701119294303, "grad_norm": 7.2522172927856445, "learning_rate": 9.99630637247976e-06, "loss": 0.6228, "step": 93380 }, { "epoch": 0.5551295540060988, "grad_norm": 5.443708419799805, "learning_rate": 9.996298394146142e-06, "loss": 0.6702, "step": 93390 }, { "epoch": 0.5551889960827672, "grad_norm": 5.804594039916992, "learning_rate": 9.996290407208301e-06, "loss": 0.6531, "step": 93400 }, { "epoch": 0.5552484381594356, "grad_norm": 6.693827152252197, "learning_rate": 9.996282411666254e-06, "loss": 0.667, "step": 93410 }, { "epoch": 0.5553078802361039, "grad_norm": 5.7392578125, "learning_rate": 9.996274407520013e-06, "loss": 0.6489, "step": 93420 }, { "epoch": 0.5553673223127723, "grad_norm": 5.917210102081299, "learning_rate": 9.99626639476959e-06, "loss": 0.674, "step": 93430 }, { "epoch": 0.5554267643894407, "grad_norm": 6.221844673156738, "learning_rate": 9.996258373415e-06, "loss": 0.7081, "step": 93440 }, { "epoch": 0.5554862064661091, "grad_norm": 6.0824384689331055, "learning_rate": 9.996250343456257e-06, "loss": 0.6068, "step": 93450 }, { "epoch": 0.5555456485427774, "grad_norm": 4.83043098449707, "learning_rate": 9.996242304893373e-06, "loss": 0.6413, "step": 93460 }, { "epoch": 0.5556050906194459, "grad_norm": 5.469661235809326, "learning_rate": 9.996234257726367e-06, "loss": 0.652, "step": 93470 }, { "epoch": 0.5556645326961143, "grad_norm": 5.132917881011963, "learning_rate": 9.996226201955247e-06, "loss": 0.6571, "step": 93480 }, { "epoch": 0.5557239747727827, "grad_norm": 6.297934532165527, "learning_rate": 9.99621813758003e-06, "loss": 0.6177, "step": 93490 }, { "epoch": 0.5557834168494511, "grad_norm": 7.232526779174805, "learning_rate": 9.99621006460073e-06, "loss": 0.6562, "step": 93500 }, { "epoch": 0.5558428589261194, "grad_norm": 4.387760162353516, "learning_rate": 9.99620198301736e-06, "loss": 0.6455, "step": 93510 }, { "epoch": 0.5559023010027878, "grad_norm": 6.10421085357666, "learning_rate": 9.996193892829933e-06, "loss": 0.6224, "step": 93520 }, { "epoch": 0.5559617430794562, "grad_norm": 6.5319719314575195, "learning_rate": 9.996185794038465e-06, "loss": 0.5991, "step": 93530 }, { "epoch": 0.5560211851561246, "grad_norm": 7.473339557647705, "learning_rate": 9.996177686642967e-06, "loss": 0.6767, "step": 93540 }, { "epoch": 0.5560806272327931, "grad_norm": 7.623781681060791, "learning_rate": 9.996169570643457e-06, "loss": 0.6546, "step": 93550 }, { "epoch": 0.5561400693094614, "grad_norm": 5.567912578582764, "learning_rate": 9.996161446039946e-06, "loss": 0.6517, "step": 93560 }, { "epoch": 0.5561995113861298, "grad_norm": 5.884302616119385, "learning_rate": 9.99615331283245e-06, "loss": 0.6649, "step": 93570 }, { "epoch": 0.5562589534627982, "grad_norm": 12.358954429626465, "learning_rate": 9.99614517102098e-06, "loss": 0.6262, "step": 93580 }, { "epoch": 0.5563183955394666, "grad_norm": 5.307149887084961, "learning_rate": 9.996137020605552e-06, "loss": 0.6569, "step": 93590 }, { "epoch": 0.5563778376161349, "grad_norm": 8.130023956298828, "learning_rate": 9.996128861586182e-06, "loss": 0.6164, "step": 93600 }, { "epoch": 0.5564372796928033, "grad_norm": 5.748544692993164, "learning_rate": 9.996120693962881e-06, "loss": 0.6619, "step": 93610 }, { "epoch": 0.5564967217694717, "grad_norm": 7.213871955871582, "learning_rate": 9.996112517735664e-06, "loss": 0.6589, "step": 93620 }, { "epoch": 0.5565561638461402, "grad_norm": 5.449212551116943, "learning_rate": 9.996104332904543e-06, "loss": 0.6179, "step": 93630 }, { "epoch": 0.5566156059228086, "grad_norm": 5.553671836853027, "learning_rate": 9.996096139469538e-06, "loss": 0.6451, "step": 93640 }, { "epoch": 0.5566750479994769, "grad_norm": 6.593356132507324, "learning_rate": 9.996087937430657e-06, "loss": 0.6505, "step": 93650 }, { "epoch": 0.5567344900761453, "grad_norm": 6.686363220214844, "learning_rate": 9.996079726787918e-06, "loss": 0.6567, "step": 93660 }, { "epoch": 0.5567939321528137, "grad_norm": 7.287062644958496, "learning_rate": 9.996071507541332e-06, "loss": 0.5954, "step": 93670 }, { "epoch": 0.5568533742294821, "grad_norm": 7.300545692443848, "learning_rate": 9.996063279690916e-06, "loss": 0.6616, "step": 93680 }, { "epoch": 0.5569128163061505, "grad_norm": 6.205718517303467, "learning_rate": 9.996055043236681e-06, "loss": 0.6773, "step": 93690 }, { "epoch": 0.5569722583828188, "grad_norm": 5.225699424743652, "learning_rate": 9.996046798178643e-06, "loss": 0.6475, "step": 93700 }, { "epoch": 0.5570317004594872, "grad_norm": 5.312929630279541, "learning_rate": 9.996038544516819e-06, "loss": 0.612, "step": 93710 }, { "epoch": 0.5570911425361557, "grad_norm": 8.970766067504883, "learning_rate": 9.996030282251218e-06, "loss": 0.6696, "step": 93720 }, { "epoch": 0.5571505846128241, "grad_norm": 6.988366603851318, "learning_rate": 9.996022011381859e-06, "loss": 0.6531, "step": 93730 }, { "epoch": 0.5572100266894924, "grad_norm": 6.400490760803223, "learning_rate": 9.996013731908752e-06, "loss": 0.6827, "step": 93740 }, { "epoch": 0.5572694687661608, "grad_norm": 5.503246784210205, "learning_rate": 9.996005443831913e-06, "loss": 0.6219, "step": 93750 }, { "epoch": 0.5573289108428292, "grad_norm": 6.177849769592285, "learning_rate": 9.995997147151358e-06, "loss": 0.6754, "step": 93760 }, { "epoch": 0.5573883529194976, "grad_norm": 5.520779132843018, "learning_rate": 9.9959888418671e-06, "loss": 0.675, "step": 93770 }, { "epoch": 0.557447794996166, "grad_norm": 5.498279094696045, "learning_rate": 9.995980527979152e-06, "loss": 0.6168, "step": 93780 }, { "epoch": 0.5575072370728343, "grad_norm": 7.18221378326416, "learning_rate": 9.995972205487529e-06, "loss": 0.6187, "step": 93790 }, { "epoch": 0.5575666791495028, "grad_norm": 8.51817798614502, "learning_rate": 9.995963874392248e-06, "loss": 0.6904, "step": 93800 }, { "epoch": 0.5576261212261712, "grad_norm": 5.823480129241943, "learning_rate": 9.99595553469332e-06, "loss": 0.7164, "step": 93810 }, { "epoch": 0.5576855633028396, "grad_norm": 6.443156719207764, "learning_rate": 9.99594718639076e-06, "loss": 0.676, "step": 93820 }, { "epoch": 0.5577450053795079, "grad_norm": 4.91984224319458, "learning_rate": 9.995938829484582e-06, "loss": 0.703, "step": 93830 }, { "epoch": 0.5578044474561763, "grad_norm": 5.736345291137695, "learning_rate": 9.995930463974801e-06, "loss": 0.662, "step": 93840 }, { "epoch": 0.5578638895328447, "grad_norm": 5.61842155456543, "learning_rate": 9.995922089861434e-06, "loss": 0.6278, "step": 93850 }, { "epoch": 0.5579233316095131, "grad_norm": 7.451732635498047, "learning_rate": 9.995913707144491e-06, "loss": 0.687, "step": 93860 }, { "epoch": 0.5579827736861815, "grad_norm": 8.175816535949707, "learning_rate": 9.99590531582399e-06, "loss": 0.676, "step": 93870 }, { "epoch": 0.5580422157628498, "grad_norm": 7.649691104888916, "learning_rate": 9.995896915899942e-06, "loss": 0.7068, "step": 93880 }, { "epoch": 0.5581016578395183, "grad_norm": 7.070799350738525, "learning_rate": 9.995888507372367e-06, "loss": 0.6557, "step": 93890 }, { "epoch": 0.5581610999161867, "grad_norm": 6.477227210998535, "learning_rate": 9.995880090241273e-06, "loss": 0.5887, "step": 93900 }, { "epoch": 0.5582205419928551, "grad_norm": 5.619953155517578, "learning_rate": 9.995871664506677e-06, "loss": 0.628, "step": 93910 }, { "epoch": 0.5582799840695235, "grad_norm": 5.537370681762695, "learning_rate": 9.995863230168595e-06, "loss": 0.6397, "step": 93920 }, { "epoch": 0.5583394261461918, "grad_norm": 5.863030910491943, "learning_rate": 9.995854787227042e-06, "loss": 0.6637, "step": 93930 }, { "epoch": 0.5583988682228602, "grad_norm": 5.5234174728393555, "learning_rate": 9.99584633568203e-06, "loss": 0.6971, "step": 93940 }, { "epoch": 0.5584583102995286, "grad_norm": 5.479284763336182, "learning_rate": 9.995837875533571e-06, "loss": 0.5893, "step": 93950 }, { "epoch": 0.558517752376197, "grad_norm": 8.83757209777832, "learning_rate": 9.995829406781687e-06, "loss": 0.6258, "step": 93960 }, { "epoch": 0.5585771944528654, "grad_norm": 4.4314141273498535, "learning_rate": 9.995820929426388e-06, "loss": 0.6976, "step": 93970 }, { "epoch": 0.5586366365295338, "grad_norm": 5.880820274353027, "learning_rate": 9.995812443467689e-06, "loss": 0.6856, "step": 93980 }, { "epoch": 0.5586960786062022, "grad_norm": 6.2595014572143555, "learning_rate": 9.995803948905605e-06, "loss": 0.6237, "step": 93990 }, { "epoch": 0.5587555206828706, "grad_norm": 6.384173393249512, "learning_rate": 9.995795445740148e-06, "loss": 0.6079, "step": 94000 }, { "epoch": 0.558814962759539, "grad_norm": 5.347092151641846, "learning_rate": 9.995786933971338e-06, "loss": 0.6229, "step": 94010 }, { "epoch": 0.5588744048362073, "grad_norm": 5.73559045791626, "learning_rate": 9.995778413599186e-06, "loss": 0.5921, "step": 94020 }, { "epoch": 0.5589338469128757, "grad_norm": 4.980114936828613, "learning_rate": 9.995769884623709e-06, "loss": 0.6133, "step": 94030 }, { "epoch": 0.5589932889895441, "grad_norm": 7.266225814819336, "learning_rate": 9.99576134704492e-06, "loss": 0.6849, "step": 94040 }, { "epoch": 0.5590527310662126, "grad_norm": 7.32794713973999, "learning_rate": 9.99575280086283e-06, "loss": 0.6619, "step": 94050 }, { "epoch": 0.559112173142881, "grad_norm": 6.563753128051758, "learning_rate": 9.99574424607746e-06, "loss": 0.6665, "step": 94060 }, { "epoch": 0.5591716152195493, "grad_norm": 6.408531665802002, "learning_rate": 9.995735682688824e-06, "loss": 0.6052, "step": 94070 }, { "epoch": 0.5592310572962177, "grad_norm": 5.134250640869141, "learning_rate": 9.995727110696934e-06, "loss": 0.68, "step": 94080 }, { "epoch": 0.5592904993728861, "grad_norm": 6.979190826416016, "learning_rate": 9.995718530101805e-06, "loss": 0.6548, "step": 94090 }, { "epoch": 0.5593499414495545, "grad_norm": 7.436643123626709, "learning_rate": 9.995709940903454e-06, "loss": 0.5728, "step": 94100 }, { "epoch": 0.5594093835262228, "grad_norm": 8.283896446228027, "learning_rate": 9.995701343101894e-06, "loss": 0.6634, "step": 94110 }, { "epoch": 0.5594688256028912, "grad_norm": 6.275669097900391, "learning_rate": 9.995692736697138e-06, "loss": 0.6138, "step": 94120 }, { "epoch": 0.5595282676795597, "grad_norm": 5.365473747253418, "learning_rate": 9.995684121689205e-06, "loss": 0.5776, "step": 94130 }, { "epoch": 0.5595877097562281, "grad_norm": 6.166501045227051, "learning_rate": 9.995675498078107e-06, "loss": 0.6746, "step": 94140 }, { "epoch": 0.5596471518328965, "grad_norm": 6.987907409667969, "learning_rate": 9.99566686586386e-06, "loss": 0.6222, "step": 94150 }, { "epoch": 0.5597065939095648, "grad_norm": 7.1377081871032715, "learning_rate": 9.995658225046481e-06, "loss": 0.644, "step": 94160 }, { "epoch": 0.5597660359862332, "grad_norm": 6.206311225891113, "learning_rate": 9.99564957562598e-06, "loss": 0.6314, "step": 94170 }, { "epoch": 0.5598254780629016, "grad_norm": 8.271599769592285, "learning_rate": 9.995640917602373e-06, "loss": 0.6302, "step": 94180 }, { "epoch": 0.55988492013957, "grad_norm": 8.32730484008789, "learning_rate": 9.99563225097568e-06, "loss": 0.6434, "step": 94190 }, { "epoch": 0.5599443622162383, "grad_norm": 6.298348903656006, "learning_rate": 9.99562357574591e-06, "loss": 0.6655, "step": 94200 }, { "epoch": 0.5600038042929067, "grad_norm": 5.731908321380615, "learning_rate": 9.99561489191308e-06, "loss": 0.6343, "step": 94210 }, { "epoch": 0.5600632463695752, "grad_norm": 6.768074035644531, "learning_rate": 9.995606199477205e-06, "loss": 0.688, "step": 94220 }, { "epoch": 0.5601226884462436, "grad_norm": 6.3361101150512695, "learning_rate": 9.995597498438301e-06, "loss": 0.6838, "step": 94230 }, { "epoch": 0.560182130522912, "grad_norm": 7.228473663330078, "learning_rate": 9.995588788796381e-06, "loss": 0.6226, "step": 94240 }, { "epoch": 0.5602415725995803, "grad_norm": 5.835903644561768, "learning_rate": 9.995580070551463e-06, "loss": 0.6747, "step": 94250 }, { "epoch": 0.5603010146762487, "grad_norm": 5.992377758026123, "learning_rate": 9.995571343703558e-06, "loss": 0.6557, "step": 94260 }, { "epoch": 0.5603604567529171, "grad_norm": 5.380112171173096, "learning_rate": 9.995562608252685e-06, "loss": 0.6581, "step": 94270 }, { "epoch": 0.5604198988295855, "grad_norm": 4.797529220581055, "learning_rate": 9.995553864198855e-06, "loss": 0.6285, "step": 94280 }, { "epoch": 0.560479340906254, "grad_norm": 8.435080528259277, "learning_rate": 9.995545111542087e-06, "loss": 0.6888, "step": 94290 }, { "epoch": 0.5605387829829223, "grad_norm": 5.498457908630371, "learning_rate": 9.995536350282393e-06, "loss": 0.6846, "step": 94300 }, { "epoch": 0.5605982250595907, "grad_norm": 5.756411552429199, "learning_rate": 9.995527580419788e-06, "loss": 0.702, "step": 94310 }, { "epoch": 0.5606576671362591, "grad_norm": 5.514199733734131, "learning_rate": 9.995518801954291e-06, "loss": 0.6449, "step": 94320 }, { "epoch": 0.5607171092129275, "grad_norm": 5.068922519683838, "learning_rate": 9.995510014885915e-06, "loss": 0.598, "step": 94330 }, { "epoch": 0.5607765512895958, "grad_norm": 7.7851152420043945, "learning_rate": 9.995501219214672e-06, "loss": 0.6628, "step": 94340 }, { "epoch": 0.5608359933662642, "grad_norm": 8.096430778503418, "learning_rate": 9.995492414940581e-06, "loss": 0.6069, "step": 94350 }, { "epoch": 0.5608954354429326, "grad_norm": 6.10686731338501, "learning_rate": 9.995483602063656e-06, "loss": 0.6455, "step": 94360 }, { "epoch": 0.560954877519601, "grad_norm": 7.1860761642456055, "learning_rate": 9.995474780583914e-06, "loss": 0.6385, "step": 94370 }, { "epoch": 0.5610143195962695, "grad_norm": 5.459937572479248, "learning_rate": 9.995465950501366e-06, "loss": 0.6535, "step": 94380 }, { "epoch": 0.5610737616729378, "grad_norm": 5.910522937774658, "learning_rate": 9.99545711181603e-06, "loss": 0.6931, "step": 94390 }, { "epoch": 0.5611332037496062, "grad_norm": 6.356944561004639, "learning_rate": 9.99544826452792e-06, "loss": 0.6354, "step": 94400 }, { "epoch": 0.5611926458262746, "grad_norm": 7.671533107757568, "learning_rate": 9.995439408637055e-06, "loss": 0.6057, "step": 94410 }, { "epoch": 0.561252087902943, "grad_norm": 6.407003879547119, "learning_rate": 9.995430544143445e-06, "loss": 0.5983, "step": 94420 }, { "epoch": 0.5613115299796113, "grad_norm": 5.557145118713379, "learning_rate": 9.995421671047107e-06, "loss": 0.6607, "step": 94430 }, { "epoch": 0.5613709720562797, "grad_norm": 6.16974401473999, "learning_rate": 9.995412789348059e-06, "loss": 0.655, "step": 94440 }, { "epoch": 0.5614304141329481, "grad_norm": 4.817338466644287, "learning_rate": 9.995403899046314e-06, "loss": 0.5738, "step": 94450 }, { "epoch": 0.5614898562096166, "grad_norm": 5.483131408691406, "learning_rate": 9.995395000141885e-06, "loss": 0.6115, "step": 94460 }, { "epoch": 0.561549298286285, "grad_norm": 7.076809406280518, "learning_rate": 9.995386092634792e-06, "loss": 0.6223, "step": 94470 }, { "epoch": 0.5616087403629533, "grad_norm": 6.045350074768066, "learning_rate": 9.995377176525047e-06, "loss": 0.7154, "step": 94480 }, { "epoch": 0.5616681824396217, "grad_norm": 7.204217433929443, "learning_rate": 9.995368251812666e-06, "loss": 0.6283, "step": 94490 }, { "epoch": 0.5617276245162901, "grad_norm": 6.317557334899902, "learning_rate": 9.995359318497667e-06, "loss": 0.6261, "step": 94500 }, { "epoch": 0.5617870665929585, "grad_norm": 6.496512413024902, "learning_rate": 9.995350376580061e-06, "loss": 0.6414, "step": 94510 }, { "epoch": 0.5618465086696269, "grad_norm": 6.684624195098877, "learning_rate": 9.995341426059867e-06, "loss": 0.6479, "step": 94520 }, { "epoch": 0.5619059507462952, "grad_norm": 5.3135576248168945, "learning_rate": 9.995332466937098e-06, "loss": 0.5991, "step": 94530 }, { "epoch": 0.5619653928229636, "grad_norm": 5.358985424041748, "learning_rate": 9.995323499211771e-06, "loss": 0.6248, "step": 94540 }, { "epoch": 0.5620248348996321, "grad_norm": 8.096842765808105, "learning_rate": 9.995314522883902e-06, "loss": 0.7268, "step": 94550 }, { "epoch": 0.5620842769763005, "grad_norm": 4.924219131469727, "learning_rate": 9.995305537953504e-06, "loss": 0.6086, "step": 94560 }, { "epoch": 0.5621437190529688, "grad_norm": 5.136836051940918, "learning_rate": 9.995296544420594e-06, "loss": 0.6296, "step": 94570 }, { "epoch": 0.5622031611296372, "grad_norm": 5.920175552368164, "learning_rate": 9.995287542285187e-06, "loss": 0.6074, "step": 94580 }, { "epoch": 0.5622626032063056, "grad_norm": 6.469550609588623, "learning_rate": 9.9952785315473e-06, "loss": 0.6132, "step": 94590 }, { "epoch": 0.562322045282974, "grad_norm": 3.6132211685180664, "learning_rate": 9.995269512206946e-06, "loss": 0.6153, "step": 94600 }, { "epoch": 0.5623814873596424, "grad_norm": 5.115083694458008, "learning_rate": 9.995260484264141e-06, "loss": 0.6025, "step": 94610 }, { "epoch": 0.5624409294363107, "grad_norm": 6.744874477386475, "learning_rate": 9.995251447718905e-06, "loss": 0.6682, "step": 94620 }, { "epoch": 0.5625003715129792, "grad_norm": 5.353576183319092, "learning_rate": 9.995242402571248e-06, "loss": 0.602, "step": 94630 }, { "epoch": 0.5625598135896476, "grad_norm": 5.208189010620117, "learning_rate": 9.995233348821187e-06, "loss": 0.6974, "step": 94640 }, { "epoch": 0.562619255666316, "grad_norm": 4.630125999450684, "learning_rate": 9.99522428646874e-06, "loss": 0.6611, "step": 94650 }, { "epoch": 0.5626786977429844, "grad_norm": 4.604584693908691, "learning_rate": 9.995215215513918e-06, "loss": 0.6211, "step": 94660 }, { "epoch": 0.5627381398196527, "grad_norm": 6.755589008331299, "learning_rate": 9.99520613595674e-06, "loss": 0.6138, "step": 94670 }, { "epoch": 0.5627975818963211, "grad_norm": 5.498048782348633, "learning_rate": 9.995197047797223e-06, "loss": 0.5927, "step": 94680 }, { "epoch": 0.5628570239729895, "grad_norm": 6.977177619934082, "learning_rate": 9.99518795103538e-06, "loss": 0.6224, "step": 94690 }, { "epoch": 0.562916466049658, "grad_norm": 6.049653053283691, "learning_rate": 9.995178845671225e-06, "loss": 0.6489, "step": 94700 }, { "epoch": 0.5629759081263263, "grad_norm": 5.725908279418945, "learning_rate": 9.995169731704777e-06, "loss": 0.6133, "step": 94710 }, { "epoch": 0.5630353502029947, "grad_norm": 7.003481388092041, "learning_rate": 9.995160609136052e-06, "loss": 0.6625, "step": 94720 }, { "epoch": 0.5630947922796631, "grad_norm": 5.91043758392334, "learning_rate": 9.995151477965064e-06, "loss": 0.6169, "step": 94730 }, { "epoch": 0.5631542343563315, "grad_norm": 6.64687442779541, "learning_rate": 9.99514233819183e-06, "loss": 0.6355, "step": 94740 }, { "epoch": 0.5632136764329999, "grad_norm": 8.021881103515625, "learning_rate": 9.995133189816364e-06, "loss": 0.6387, "step": 94750 }, { "epoch": 0.5632731185096682, "grad_norm": 6.855124473571777, "learning_rate": 9.995124032838682e-06, "loss": 0.6341, "step": 94760 }, { "epoch": 0.5633325605863366, "grad_norm": 5.675424098968506, "learning_rate": 9.995114867258802e-06, "loss": 0.6612, "step": 94770 }, { "epoch": 0.563392002663005, "grad_norm": 6.708489418029785, "learning_rate": 9.995105693076736e-06, "loss": 0.6744, "step": 94780 }, { "epoch": 0.5634514447396735, "grad_norm": 7.24795389175415, "learning_rate": 9.995096510292503e-06, "loss": 0.5962, "step": 94790 }, { "epoch": 0.5635108868163418, "grad_norm": 5.802769660949707, "learning_rate": 9.995087318906119e-06, "loss": 0.6454, "step": 94800 }, { "epoch": 0.5635703288930102, "grad_norm": 6.512217044830322, "learning_rate": 9.995078118917597e-06, "loss": 0.6654, "step": 94810 }, { "epoch": 0.5636297709696786, "grad_norm": 5.34784460067749, "learning_rate": 9.995068910326955e-06, "loss": 0.618, "step": 94820 }, { "epoch": 0.563689213046347, "grad_norm": 6.4500041007995605, "learning_rate": 9.995059693134208e-06, "loss": 0.7025, "step": 94830 }, { "epoch": 0.5637486551230154, "grad_norm": 9.067484855651855, "learning_rate": 9.995050467339373e-06, "loss": 0.6386, "step": 94840 }, { "epoch": 0.5638080971996837, "grad_norm": 6.429315090179443, "learning_rate": 9.995041232942464e-06, "loss": 0.6326, "step": 94850 }, { "epoch": 0.5638675392763521, "grad_norm": 7.173898696899414, "learning_rate": 9.995031989943499e-06, "loss": 0.6697, "step": 94860 }, { "epoch": 0.5639269813530206, "grad_norm": 7.658665180206299, "learning_rate": 9.995022738342493e-06, "loss": 0.6308, "step": 94870 }, { "epoch": 0.563986423429689, "grad_norm": 5.55384635925293, "learning_rate": 9.995013478139462e-06, "loss": 0.5908, "step": 94880 }, { "epoch": 0.5640458655063574, "grad_norm": 6.238055229187012, "learning_rate": 9.99500420933442e-06, "loss": 0.6333, "step": 94890 }, { "epoch": 0.5641053075830257, "grad_norm": 5.584852695465088, "learning_rate": 9.994994931927387e-06, "loss": 0.646, "step": 94900 }, { "epoch": 0.5641647496596941, "grad_norm": 5.882166862487793, "learning_rate": 9.994985645918375e-06, "loss": 0.6626, "step": 94910 }, { "epoch": 0.5642241917363625, "grad_norm": 4.520073890686035, "learning_rate": 9.994976351307402e-06, "loss": 0.6418, "step": 94920 }, { "epoch": 0.5642836338130309, "grad_norm": 6.145786285400391, "learning_rate": 9.994967048094483e-06, "loss": 0.6584, "step": 94930 }, { "epoch": 0.5643430758896992, "grad_norm": 7.484580039978027, "learning_rate": 9.994957736279638e-06, "loss": 0.6732, "step": 94940 }, { "epoch": 0.5644025179663676, "grad_norm": 7.334992408752441, "learning_rate": 9.994948415862878e-06, "loss": 0.6965, "step": 94950 }, { "epoch": 0.5644619600430361, "grad_norm": 5.378310203552246, "learning_rate": 9.99493908684422e-06, "loss": 0.6331, "step": 94960 }, { "epoch": 0.5645214021197045, "grad_norm": 5.538460731506348, "learning_rate": 9.99492974922368e-06, "loss": 0.6648, "step": 94970 }, { "epoch": 0.5645808441963729, "grad_norm": 5.9702887535095215, "learning_rate": 9.994920403001278e-06, "loss": 0.6051, "step": 94980 }, { "epoch": 0.5646402862730412, "grad_norm": 6.445460319519043, "learning_rate": 9.994911048177025e-06, "loss": 0.6215, "step": 94990 }, { "epoch": 0.5646997283497096, "grad_norm": 6.1167755126953125, "learning_rate": 9.99490168475094e-06, "loss": 0.7041, "step": 95000 }, { "epoch": 0.564759170426378, "grad_norm": 5.503498554229736, "learning_rate": 9.994892312723037e-06, "loss": 0.6769, "step": 95010 }, { "epoch": 0.5648186125030464, "grad_norm": 5.39628267288208, "learning_rate": 9.994882932093335e-06, "loss": 0.7074, "step": 95020 }, { "epoch": 0.5648780545797149, "grad_norm": 5.584778785705566, "learning_rate": 9.99487354286185e-06, "loss": 0.6478, "step": 95030 }, { "epoch": 0.5649374966563832, "grad_norm": 5.186327934265137, "learning_rate": 9.994864145028593e-06, "loss": 0.6682, "step": 95040 }, { "epoch": 0.5649969387330516, "grad_norm": 5.597187519073486, "learning_rate": 9.994854738593586e-06, "loss": 0.6295, "step": 95050 }, { "epoch": 0.56505638080972, "grad_norm": 6.44888162612915, "learning_rate": 9.994845323556843e-06, "loss": 0.6016, "step": 95060 }, { "epoch": 0.5651158228863884, "grad_norm": 7.076030731201172, "learning_rate": 9.99483589991838e-06, "loss": 0.6385, "step": 95070 }, { "epoch": 0.5651752649630567, "grad_norm": 7.672482490539551, "learning_rate": 9.994826467678214e-06, "loss": 0.6474, "step": 95080 }, { "epoch": 0.5652347070397251, "grad_norm": 4.917576313018799, "learning_rate": 9.994817026836361e-06, "loss": 0.6134, "step": 95090 }, { "epoch": 0.5652941491163935, "grad_norm": 6.583615303039551, "learning_rate": 9.994807577392838e-06, "loss": 0.6485, "step": 95100 }, { "epoch": 0.5653535911930619, "grad_norm": 7.63597297668457, "learning_rate": 9.99479811934766e-06, "loss": 0.5836, "step": 95110 }, { "epoch": 0.5654130332697304, "grad_norm": 4.463778018951416, "learning_rate": 9.994788652700841e-06, "loss": 0.6253, "step": 95120 }, { "epoch": 0.5654724753463987, "grad_norm": 7.988798141479492, "learning_rate": 9.994779177452403e-06, "loss": 0.7421, "step": 95130 }, { "epoch": 0.5655319174230671, "grad_norm": 6.7971882820129395, "learning_rate": 9.994769693602358e-06, "loss": 0.6632, "step": 95140 }, { "epoch": 0.5655913594997355, "grad_norm": 7.63637113571167, "learning_rate": 9.994760201150723e-06, "loss": 0.6541, "step": 95150 }, { "epoch": 0.5656508015764039, "grad_norm": 5.532737731933594, "learning_rate": 9.994750700097518e-06, "loss": 0.6857, "step": 95160 }, { "epoch": 0.5657102436530722, "grad_norm": 6.3509721755981445, "learning_rate": 9.994741190442754e-06, "loss": 0.6503, "step": 95170 }, { "epoch": 0.5657696857297406, "grad_norm": 5.328527450561523, "learning_rate": 9.994731672186449e-06, "loss": 0.6422, "step": 95180 }, { "epoch": 0.565829127806409, "grad_norm": 7.449191570281982, "learning_rate": 9.994722145328622e-06, "loss": 0.6687, "step": 95190 }, { "epoch": 0.5658885698830775, "grad_norm": 7.159709930419922, "learning_rate": 9.994712609869286e-06, "loss": 0.6501, "step": 95200 }, { "epoch": 0.5659480119597459, "grad_norm": 7.354939937591553, "learning_rate": 9.99470306580846e-06, "loss": 0.6299, "step": 95210 }, { "epoch": 0.5660074540364142, "grad_norm": 6.458502769470215, "learning_rate": 9.994693513146158e-06, "loss": 0.6406, "step": 95220 }, { "epoch": 0.5660668961130826, "grad_norm": 6.1124701499938965, "learning_rate": 9.994683951882398e-06, "loss": 0.669, "step": 95230 }, { "epoch": 0.566126338189751, "grad_norm": 6.6707892417907715, "learning_rate": 9.994674382017197e-06, "loss": 0.5908, "step": 95240 }, { "epoch": 0.5661857802664194, "grad_norm": 6.188236236572266, "learning_rate": 9.994664803550571e-06, "loss": 0.6197, "step": 95250 }, { "epoch": 0.5662452223430878, "grad_norm": 6.5261712074279785, "learning_rate": 9.994655216482536e-06, "loss": 0.6039, "step": 95260 }, { "epoch": 0.5663046644197561, "grad_norm": 6.046762943267822, "learning_rate": 9.994645620813107e-06, "loss": 0.638, "step": 95270 }, { "epoch": 0.5663641064964245, "grad_norm": 5.956239223480225, "learning_rate": 9.994636016542305e-06, "loss": 0.6762, "step": 95280 }, { "epoch": 0.566423548573093, "grad_norm": 7.2394537925720215, "learning_rate": 9.994626403670143e-06, "loss": 0.6589, "step": 95290 }, { "epoch": 0.5664829906497614, "grad_norm": 5.373859405517578, "learning_rate": 9.994616782196637e-06, "loss": 0.6179, "step": 95300 }, { "epoch": 0.5665424327264297, "grad_norm": 5.6872735023498535, "learning_rate": 9.994607152121806e-06, "loss": 0.6265, "step": 95310 }, { "epoch": 0.5666018748030981, "grad_norm": 6.285894393920898, "learning_rate": 9.994597513445668e-06, "loss": 0.6887, "step": 95320 }, { "epoch": 0.5666613168797665, "grad_norm": 5.616921424865723, "learning_rate": 9.994587866168233e-06, "loss": 0.66, "step": 95330 }, { "epoch": 0.5667207589564349, "grad_norm": 6.497405529022217, "learning_rate": 9.994578210289525e-06, "loss": 0.6515, "step": 95340 }, { "epoch": 0.5667802010331033, "grad_norm": 5.691802501678467, "learning_rate": 9.994568545809556e-06, "loss": 0.678, "step": 95350 }, { "epoch": 0.5668396431097716, "grad_norm": 7.156195640563965, "learning_rate": 9.994558872728343e-06, "loss": 0.6079, "step": 95360 }, { "epoch": 0.56689908518644, "grad_norm": 5.691164493560791, "learning_rate": 9.994549191045906e-06, "loss": 0.6127, "step": 95370 }, { "epoch": 0.5669585272631085, "grad_norm": 5.60107946395874, "learning_rate": 9.994539500762257e-06, "loss": 0.6578, "step": 95380 }, { "epoch": 0.5670179693397769, "grad_norm": 4.813929080963135, "learning_rate": 9.994529801877416e-06, "loss": 0.697, "step": 95390 }, { "epoch": 0.5670774114164453, "grad_norm": 6.503457069396973, "learning_rate": 9.994520094391399e-06, "loss": 0.6652, "step": 95400 }, { "epoch": 0.5671368534931136, "grad_norm": 6.47452974319458, "learning_rate": 9.994510378304221e-06, "loss": 0.6921, "step": 95410 }, { "epoch": 0.567196295569782, "grad_norm": 7.320038318634033, "learning_rate": 9.994500653615903e-06, "loss": 0.6278, "step": 95420 }, { "epoch": 0.5672557376464504, "grad_norm": 5.809699058532715, "learning_rate": 9.994490920326456e-06, "loss": 0.5944, "step": 95430 }, { "epoch": 0.5673151797231188, "grad_norm": 7.079831123352051, "learning_rate": 9.994481178435902e-06, "loss": 0.6416, "step": 95440 }, { "epoch": 0.5673746217997871, "grad_norm": 6.265363693237305, "learning_rate": 9.994471427944255e-06, "loss": 0.6543, "step": 95450 }, { "epoch": 0.5674340638764556, "grad_norm": 5.9947991371154785, "learning_rate": 9.994461668851532e-06, "loss": 0.5968, "step": 95460 }, { "epoch": 0.567493505953124, "grad_norm": 5.55979585647583, "learning_rate": 9.99445190115775e-06, "loss": 0.6533, "step": 95470 }, { "epoch": 0.5675529480297924, "grad_norm": 8.603970527648926, "learning_rate": 9.994442124862924e-06, "loss": 0.6242, "step": 95480 }, { "epoch": 0.5676123901064608, "grad_norm": 5.178145408630371, "learning_rate": 9.994432339967075e-06, "loss": 0.684, "step": 95490 }, { "epoch": 0.5676718321831291, "grad_norm": 6.623927116394043, "learning_rate": 9.994422546470217e-06, "loss": 0.6087, "step": 95500 }, { "epoch": 0.5677312742597975, "grad_norm": 6.247601509094238, "learning_rate": 9.994412744372368e-06, "loss": 0.6192, "step": 95510 }, { "epoch": 0.5677907163364659, "grad_norm": 6.100387096405029, "learning_rate": 9.994402933673544e-06, "loss": 0.6229, "step": 95520 }, { "epoch": 0.5678501584131344, "grad_norm": 7.309830665588379, "learning_rate": 9.994393114373762e-06, "loss": 0.6033, "step": 95530 }, { "epoch": 0.5679096004898027, "grad_norm": 9.160547256469727, "learning_rate": 9.99438328647304e-06, "loss": 0.7329, "step": 95540 }, { "epoch": 0.5679690425664711, "grad_norm": 7.126837730407715, "learning_rate": 9.994373449971393e-06, "loss": 0.6722, "step": 95550 }, { "epoch": 0.5680284846431395, "grad_norm": 6.557849884033203, "learning_rate": 9.994363604868839e-06, "loss": 0.6343, "step": 95560 }, { "epoch": 0.5680879267198079, "grad_norm": 7.581981182098389, "learning_rate": 9.994353751165396e-06, "loss": 0.6119, "step": 95570 }, { "epoch": 0.5681473687964763, "grad_norm": 7.1479811668396, "learning_rate": 9.994343888861079e-06, "loss": 0.6831, "step": 95580 }, { "epoch": 0.5682068108731446, "grad_norm": 6.907763481140137, "learning_rate": 9.994334017955906e-06, "loss": 0.6461, "step": 95590 }, { "epoch": 0.568266252949813, "grad_norm": 5.158790111541748, "learning_rate": 9.994324138449894e-06, "loss": 0.7239, "step": 95600 }, { "epoch": 0.5683256950264814, "grad_norm": 5.108853816986084, "learning_rate": 9.99431425034306e-06, "loss": 0.5864, "step": 95610 }, { "epoch": 0.5683851371031499, "grad_norm": 5.652943134307861, "learning_rate": 9.99430435363542e-06, "loss": 0.6592, "step": 95620 }, { "epoch": 0.5684445791798183, "grad_norm": 7.154426574707031, "learning_rate": 9.994294448326994e-06, "loss": 0.6543, "step": 95630 }, { "epoch": 0.5685040212564866, "grad_norm": 5.7041120529174805, "learning_rate": 9.994284534417796e-06, "loss": 0.6653, "step": 95640 }, { "epoch": 0.568563463333155, "grad_norm": 7.3182525634765625, "learning_rate": 9.994274611907844e-06, "loss": 0.6558, "step": 95650 }, { "epoch": 0.5686229054098234, "grad_norm": 7.104432106018066, "learning_rate": 9.994264680797155e-06, "loss": 0.6782, "step": 95660 }, { "epoch": 0.5686823474864918, "grad_norm": 5.433227062225342, "learning_rate": 9.994254741085745e-06, "loss": 0.7104, "step": 95670 }, { "epoch": 0.5687417895631601, "grad_norm": 5.559617519378662, "learning_rate": 9.994244792773635e-06, "loss": 0.5662, "step": 95680 }, { "epoch": 0.5688012316398285, "grad_norm": 6.465529918670654, "learning_rate": 9.994234835860838e-06, "loss": 0.7259, "step": 95690 }, { "epoch": 0.568860673716497, "grad_norm": 5.127262115478516, "learning_rate": 9.994224870347374e-06, "loss": 0.6268, "step": 95700 }, { "epoch": 0.5689201157931654, "grad_norm": 6.7355523109436035, "learning_rate": 9.994214896233259e-06, "loss": 0.6366, "step": 95710 }, { "epoch": 0.5689795578698338, "grad_norm": 6.586452007293701, "learning_rate": 9.994204913518509e-06, "loss": 0.6604, "step": 95720 }, { "epoch": 0.5690389999465021, "grad_norm": 5.280021667480469, "learning_rate": 9.994194922203142e-06, "loss": 0.6438, "step": 95730 }, { "epoch": 0.5690984420231705, "grad_norm": 5.744117259979248, "learning_rate": 9.994184922287176e-06, "loss": 0.6356, "step": 95740 }, { "epoch": 0.5691578840998389, "grad_norm": 5.545392990112305, "learning_rate": 9.994174913770626e-06, "loss": 0.6616, "step": 95750 }, { "epoch": 0.5692173261765073, "grad_norm": 6.664196014404297, "learning_rate": 9.994164896653513e-06, "loss": 0.6652, "step": 95760 }, { "epoch": 0.5692767682531757, "grad_norm": 6.419988632202148, "learning_rate": 9.994154870935852e-06, "loss": 0.6493, "step": 95770 }, { "epoch": 0.569336210329844, "grad_norm": 6.735497951507568, "learning_rate": 9.99414483661766e-06, "loss": 0.5951, "step": 95780 }, { "epoch": 0.5693956524065125, "grad_norm": 4.944335460662842, "learning_rate": 9.994134793698955e-06, "loss": 0.6308, "step": 95790 }, { "epoch": 0.5694550944831809, "grad_norm": 5.785835266113281, "learning_rate": 9.994124742179754e-06, "loss": 0.6395, "step": 95800 }, { "epoch": 0.5695145365598493, "grad_norm": 6.6094512939453125, "learning_rate": 9.994114682060074e-06, "loss": 0.6233, "step": 95810 }, { "epoch": 0.5695739786365176, "grad_norm": 5.995298862457275, "learning_rate": 9.994104613339932e-06, "loss": 0.629, "step": 95820 }, { "epoch": 0.569633420713186, "grad_norm": 5.294627666473389, "learning_rate": 9.994094536019347e-06, "loss": 0.6429, "step": 95830 }, { "epoch": 0.5696928627898544, "grad_norm": 5.765560626983643, "learning_rate": 9.994084450098335e-06, "loss": 0.6851, "step": 95840 }, { "epoch": 0.5697523048665228, "grad_norm": 5.752369403839111, "learning_rate": 9.994074355576913e-06, "loss": 0.5648, "step": 95850 }, { "epoch": 0.5698117469431913, "grad_norm": 5.018920421600342, "learning_rate": 9.9940642524551e-06, "loss": 0.6643, "step": 95860 }, { "epoch": 0.5698711890198596, "grad_norm": 6.064081192016602, "learning_rate": 9.994054140732912e-06, "loss": 0.6564, "step": 95870 }, { "epoch": 0.569930631096528, "grad_norm": 6.324159145355225, "learning_rate": 9.994044020410367e-06, "loss": 0.6911, "step": 95880 }, { "epoch": 0.5699900731731964, "grad_norm": 4.749186992645264, "learning_rate": 9.994033891487482e-06, "loss": 0.6517, "step": 95890 }, { "epoch": 0.5700495152498648, "grad_norm": 5.072579383850098, "learning_rate": 9.994023753964276e-06, "loss": 0.5791, "step": 95900 }, { "epoch": 0.5701089573265331, "grad_norm": 7.10426139831543, "learning_rate": 9.994013607840765e-06, "loss": 0.635, "step": 95910 }, { "epoch": 0.5701683994032015, "grad_norm": 6.788243293762207, "learning_rate": 9.994003453116964e-06, "loss": 0.6508, "step": 95920 }, { "epoch": 0.5702278414798699, "grad_norm": 6.260799884796143, "learning_rate": 9.993993289792896e-06, "loss": 0.6589, "step": 95930 }, { "epoch": 0.5702872835565383, "grad_norm": 5.676963806152344, "learning_rate": 9.993983117868575e-06, "loss": 0.6761, "step": 95940 }, { "epoch": 0.5703467256332068, "grad_norm": 7.547080039978027, "learning_rate": 9.99397293734402e-06, "loss": 0.66, "step": 95950 }, { "epoch": 0.5704061677098751, "grad_norm": 7.303390026092529, "learning_rate": 9.993962748219246e-06, "loss": 0.6931, "step": 95960 }, { "epoch": 0.5704656097865435, "grad_norm": 4.884469032287598, "learning_rate": 9.993952550494273e-06, "loss": 0.7272, "step": 95970 }, { "epoch": 0.5705250518632119, "grad_norm": 5.394156455993652, "learning_rate": 9.993942344169118e-06, "loss": 0.6881, "step": 95980 }, { "epoch": 0.5705844939398803, "grad_norm": 4.451899528503418, "learning_rate": 9.993932129243799e-06, "loss": 0.6828, "step": 95990 }, { "epoch": 0.5706439360165487, "grad_norm": 5.888331413269043, "learning_rate": 9.993921905718333e-06, "loss": 0.5907, "step": 96000 }, { "epoch": 0.570703378093217, "grad_norm": 7.254409313201904, "learning_rate": 9.993911673592735e-06, "loss": 0.6863, "step": 96010 }, { "epoch": 0.5707628201698854, "grad_norm": 5.902284145355225, "learning_rate": 9.993901432867028e-06, "loss": 0.616, "step": 96020 }, { "epoch": 0.5708222622465539, "grad_norm": 4.953709602355957, "learning_rate": 9.993891183541226e-06, "loss": 0.562, "step": 96030 }, { "epoch": 0.5708817043232223, "grad_norm": 8.252349853515625, "learning_rate": 9.993880925615348e-06, "loss": 0.6933, "step": 96040 }, { "epoch": 0.5709411463998906, "grad_norm": 7.353553295135498, "learning_rate": 9.99387065908941e-06, "loss": 0.6764, "step": 96050 }, { "epoch": 0.571000588476559, "grad_norm": 6.213604927062988, "learning_rate": 9.993860383963433e-06, "loss": 0.6366, "step": 96060 }, { "epoch": 0.5710600305532274, "grad_norm": 4.7166266441345215, "learning_rate": 9.993850100237431e-06, "loss": 0.6851, "step": 96070 }, { "epoch": 0.5711194726298958, "grad_norm": 5.074277877807617, "learning_rate": 9.993839807911424e-06, "loss": 0.6227, "step": 96080 }, { "epoch": 0.5711789147065642, "grad_norm": 5.065418243408203, "learning_rate": 9.993829506985428e-06, "loss": 0.613, "step": 96090 }, { "epoch": 0.5712383567832325, "grad_norm": 6.12542724609375, "learning_rate": 9.993819197459463e-06, "loss": 0.6378, "step": 96100 }, { "epoch": 0.571297798859901, "grad_norm": 5.467984199523926, "learning_rate": 9.993808879333543e-06, "loss": 0.6368, "step": 96110 }, { "epoch": 0.5713572409365694, "grad_norm": 7.388486385345459, "learning_rate": 9.99379855260769e-06, "loss": 0.6272, "step": 96120 }, { "epoch": 0.5714166830132378, "grad_norm": 5.182911396026611, "learning_rate": 9.993788217281921e-06, "loss": 0.6486, "step": 96130 }, { "epoch": 0.5714761250899062, "grad_norm": 5.885222434997559, "learning_rate": 9.993777873356252e-06, "loss": 0.6416, "step": 96140 }, { "epoch": 0.5715355671665745, "grad_norm": 7.024434566497803, "learning_rate": 9.993767520830702e-06, "loss": 0.6472, "step": 96150 }, { "epoch": 0.5715950092432429, "grad_norm": 6.861886024475098, "learning_rate": 9.993757159705287e-06, "loss": 0.6268, "step": 96160 }, { "epoch": 0.5716544513199113, "grad_norm": 5.974925994873047, "learning_rate": 9.993746789980028e-06, "loss": 0.7223, "step": 96170 }, { "epoch": 0.5717138933965797, "grad_norm": 5.713862419128418, "learning_rate": 9.99373641165494e-06, "loss": 0.657, "step": 96180 }, { "epoch": 0.571773335473248, "grad_norm": 5.764531135559082, "learning_rate": 9.993726024730043e-06, "loss": 0.6396, "step": 96190 }, { "epoch": 0.5718327775499165, "grad_norm": 5.878087520599365, "learning_rate": 9.993715629205353e-06, "loss": 0.6389, "step": 96200 }, { "epoch": 0.5718922196265849, "grad_norm": 7.001363754272461, "learning_rate": 9.99370522508089e-06, "loss": 0.5923, "step": 96210 }, { "epoch": 0.5719516617032533, "grad_norm": 5.127111911773682, "learning_rate": 9.99369481235667e-06, "loss": 0.693, "step": 96220 }, { "epoch": 0.5720111037799217, "grad_norm": 8.12193775177002, "learning_rate": 9.993684391032711e-06, "loss": 0.6564, "step": 96230 }, { "epoch": 0.57207054585659, "grad_norm": 5.470776081085205, "learning_rate": 9.993673961109034e-06, "loss": 0.6383, "step": 96240 }, { "epoch": 0.5721299879332584, "grad_norm": 6.546728610992432, "learning_rate": 9.993663522585653e-06, "loss": 0.6014, "step": 96250 }, { "epoch": 0.5721894300099268, "grad_norm": 5.295273780822754, "learning_rate": 9.993653075462586e-06, "loss": 0.6261, "step": 96260 }, { "epoch": 0.5722488720865953, "grad_norm": 5.017698287963867, "learning_rate": 9.993642619739855e-06, "loss": 0.5932, "step": 96270 }, { "epoch": 0.5723083141632636, "grad_norm": 6.435331344604492, "learning_rate": 9.993632155417474e-06, "loss": 0.643, "step": 96280 }, { "epoch": 0.572367756239932, "grad_norm": 7.359363555908203, "learning_rate": 9.993621682495465e-06, "loss": 0.7295, "step": 96290 }, { "epoch": 0.5724271983166004, "grad_norm": 6.678773880004883, "learning_rate": 9.993611200973841e-06, "loss": 0.6495, "step": 96300 }, { "epoch": 0.5724866403932688, "grad_norm": 6.221201419830322, "learning_rate": 9.993600710852625e-06, "loss": 0.5776, "step": 96310 }, { "epoch": 0.5725460824699372, "grad_norm": 6.6477813720703125, "learning_rate": 9.993590212131829e-06, "loss": 0.5531, "step": 96320 }, { "epoch": 0.5726055245466055, "grad_norm": 6.754690170288086, "learning_rate": 9.993579704811478e-06, "loss": 0.6321, "step": 96330 }, { "epoch": 0.5726649666232739, "grad_norm": 4.487700939178467, "learning_rate": 9.993569188891587e-06, "loss": 0.6183, "step": 96340 }, { "epoch": 0.5727244086999423, "grad_norm": 7.100532531738281, "learning_rate": 9.993558664372173e-06, "loss": 0.5918, "step": 96350 }, { "epoch": 0.5727838507766108, "grad_norm": 5.91844367980957, "learning_rate": 9.993548131253256e-06, "loss": 0.7173, "step": 96360 }, { "epoch": 0.5728432928532792, "grad_norm": 5.841189384460449, "learning_rate": 9.993537589534851e-06, "loss": 0.6303, "step": 96370 }, { "epoch": 0.5729027349299475, "grad_norm": 5.549258232116699, "learning_rate": 9.99352703921698e-06, "loss": 0.6586, "step": 96380 }, { "epoch": 0.5729621770066159, "grad_norm": 6.622868537902832, "learning_rate": 9.99351648029966e-06, "loss": 0.6324, "step": 96390 }, { "epoch": 0.5730216190832843, "grad_norm": 5.677699565887451, "learning_rate": 9.99350591278291e-06, "loss": 0.6171, "step": 96400 }, { "epoch": 0.5730810611599527, "grad_norm": 5.363292217254639, "learning_rate": 9.993495336666745e-06, "loss": 0.6111, "step": 96410 }, { "epoch": 0.573140503236621, "grad_norm": 7.730836391448975, "learning_rate": 9.993484751951186e-06, "loss": 0.6305, "step": 96420 }, { "epoch": 0.5731999453132894, "grad_norm": 4.818337440490723, "learning_rate": 9.993474158636251e-06, "loss": 0.5921, "step": 96430 }, { "epoch": 0.5732593873899579, "grad_norm": 4.934404373168945, "learning_rate": 9.993463556721956e-06, "loss": 0.5937, "step": 96440 }, { "epoch": 0.5733188294666263, "grad_norm": 6.185809135437012, "learning_rate": 9.993452946208322e-06, "loss": 0.6351, "step": 96450 }, { "epoch": 0.5733782715432947, "grad_norm": 8.236863136291504, "learning_rate": 9.993442327095366e-06, "loss": 0.6357, "step": 96460 }, { "epoch": 0.573437713619963, "grad_norm": 6.506206035614014, "learning_rate": 9.993431699383107e-06, "loss": 0.6505, "step": 96470 }, { "epoch": 0.5734971556966314, "grad_norm": 5.542377471923828, "learning_rate": 9.993421063071563e-06, "loss": 0.6197, "step": 96480 }, { "epoch": 0.5735565977732998, "grad_norm": 5.28079891204834, "learning_rate": 9.993410418160751e-06, "loss": 0.645, "step": 96490 }, { "epoch": 0.5736160398499682, "grad_norm": 5.356032848358154, "learning_rate": 9.993399764650691e-06, "loss": 0.6305, "step": 96500 }, { "epoch": 0.5736754819266366, "grad_norm": 7.9504008293151855, "learning_rate": 9.9933891025414e-06, "loss": 0.6484, "step": 96510 }, { "epoch": 0.573734924003305, "grad_norm": 6.461442947387695, "learning_rate": 9.993378431832899e-06, "loss": 0.5821, "step": 96520 }, { "epoch": 0.5737943660799734, "grad_norm": 6.155354976654053, "learning_rate": 9.993367752525203e-06, "loss": 0.66, "step": 96530 }, { "epoch": 0.5738538081566418, "grad_norm": 8.401570320129395, "learning_rate": 9.993357064618332e-06, "loss": 0.6658, "step": 96540 }, { "epoch": 0.5739132502333102, "grad_norm": 5.622500896453857, "learning_rate": 9.993346368112305e-06, "loss": 0.6096, "step": 96550 }, { "epoch": 0.5739726923099785, "grad_norm": 6.10387659072876, "learning_rate": 9.99333566300714e-06, "loss": 0.6589, "step": 96560 }, { "epoch": 0.5740321343866469, "grad_norm": 7.029983043670654, "learning_rate": 9.993324949302854e-06, "loss": 0.6159, "step": 96570 }, { "epoch": 0.5740915764633153, "grad_norm": 6.402816295623779, "learning_rate": 9.993314226999468e-06, "loss": 0.6487, "step": 96580 }, { "epoch": 0.5741510185399837, "grad_norm": 5.155173301696777, "learning_rate": 9.993303496096998e-06, "loss": 0.6983, "step": 96590 }, { "epoch": 0.5742104606166522, "grad_norm": 6.213963508605957, "learning_rate": 9.993292756595464e-06, "loss": 0.6867, "step": 96600 }, { "epoch": 0.5742699026933205, "grad_norm": 6.1481146812438965, "learning_rate": 9.993282008494884e-06, "loss": 0.6759, "step": 96610 }, { "epoch": 0.5743293447699889, "grad_norm": 6.50733757019043, "learning_rate": 9.993271251795277e-06, "loss": 0.669, "step": 96620 }, { "epoch": 0.5743887868466573, "grad_norm": 5.541251182556152, "learning_rate": 9.993260486496662e-06, "loss": 0.6144, "step": 96630 }, { "epoch": 0.5744482289233257, "grad_norm": 6.241091251373291, "learning_rate": 9.993249712599054e-06, "loss": 0.6149, "step": 96640 }, { "epoch": 0.574507670999994, "grad_norm": 6.543890953063965, "learning_rate": 9.993238930102476e-06, "loss": 0.6492, "step": 96650 }, { "epoch": 0.5745671130766624, "grad_norm": 6.854434013366699, "learning_rate": 9.993228139006946e-06, "loss": 0.6405, "step": 96660 }, { "epoch": 0.5746265551533308, "grad_norm": 5.071944713592529, "learning_rate": 9.993217339312479e-06, "loss": 0.5642, "step": 96670 }, { "epoch": 0.5746859972299992, "grad_norm": 6.602550983428955, "learning_rate": 9.993206531019096e-06, "loss": 0.6221, "step": 96680 }, { "epoch": 0.5747454393066677, "grad_norm": 5.675112724304199, "learning_rate": 9.993195714126816e-06, "loss": 0.649, "step": 96690 }, { "epoch": 0.574804881383336, "grad_norm": 5.728182792663574, "learning_rate": 9.993184888635659e-06, "loss": 0.6303, "step": 96700 }, { "epoch": 0.5748643234600044, "grad_norm": 7.26362419128418, "learning_rate": 9.99317405454564e-06, "loss": 0.6391, "step": 96710 }, { "epoch": 0.5749237655366728, "grad_norm": 5.597651958465576, "learning_rate": 9.99316321185678e-06, "loss": 0.6423, "step": 96720 }, { "epoch": 0.5749832076133412, "grad_norm": 6.29329252243042, "learning_rate": 9.993152360569096e-06, "loss": 0.5928, "step": 96730 }, { "epoch": 0.5750426496900096, "grad_norm": 7.648956298828125, "learning_rate": 9.99314150068261e-06, "loss": 0.6669, "step": 96740 }, { "epoch": 0.5751020917666779, "grad_norm": 3.7789788246154785, "learning_rate": 9.993130632197338e-06, "loss": 0.6482, "step": 96750 }, { "epoch": 0.5751615338433463, "grad_norm": 5.851273536682129, "learning_rate": 9.993119755113299e-06, "loss": 0.6237, "step": 96760 }, { "epoch": 0.5752209759200148, "grad_norm": 6.499790668487549, "learning_rate": 9.99310886943051e-06, "loss": 0.6869, "step": 96770 }, { "epoch": 0.5752804179966832, "grad_norm": 5.347308158874512, "learning_rate": 9.993097975148996e-06, "loss": 0.6196, "step": 96780 }, { "epoch": 0.5753398600733515, "grad_norm": 5.665165424346924, "learning_rate": 9.993087072268768e-06, "loss": 0.5942, "step": 96790 }, { "epoch": 0.5753993021500199, "grad_norm": 6.414246082305908, "learning_rate": 9.993076160789849e-06, "loss": 0.6094, "step": 96800 }, { "epoch": 0.5754587442266883, "grad_norm": 6.065403938293457, "learning_rate": 9.993065240712258e-06, "loss": 0.6503, "step": 96810 }, { "epoch": 0.5755181863033567, "grad_norm": 4.733086585998535, "learning_rate": 9.993054312036013e-06, "loss": 0.6862, "step": 96820 }, { "epoch": 0.5755776283800251, "grad_norm": 5.357417106628418, "learning_rate": 9.993043374761132e-06, "loss": 0.6701, "step": 96830 }, { "epoch": 0.5756370704566934, "grad_norm": 4.120630264282227, "learning_rate": 9.993032428887633e-06, "loss": 0.6393, "step": 96840 }, { "epoch": 0.5756965125333618, "grad_norm": 6.629913806915283, "learning_rate": 9.993021474415539e-06, "loss": 0.6707, "step": 96850 }, { "epoch": 0.5757559546100303, "grad_norm": 6.36771821975708, "learning_rate": 9.993010511344866e-06, "loss": 0.6856, "step": 96860 }, { "epoch": 0.5758153966866987, "grad_norm": 5.556203842163086, "learning_rate": 9.992999539675632e-06, "loss": 0.6063, "step": 96870 }, { "epoch": 0.5758748387633671, "grad_norm": 5.168201923370361, "learning_rate": 9.992988559407856e-06, "loss": 0.6478, "step": 96880 }, { "epoch": 0.5759342808400354, "grad_norm": 7.857617378234863, "learning_rate": 9.99297757054156e-06, "loss": 0.6517, "step": 96890 }, { "epoch": 0.5759937229167038, "grad_norm": 5.980612754821777, "learning_rate": 9.99296657307676e-06, "loss": 0.6605, "step": 96900 }, { "epoch": 0.5760531649933722, "grad_norm": 8.342341423034668, "learning_rate": 9.992955567013476e-06, "loss": 0.6657, "step": 96910 }, { "epoch": 0.5761126070700406, "grad_norm": 5.851853847503662, "learning_rate": 9.992944552351727e-06, "loss": 0.6198, "step": 96920 }, { "epoch": 0.5761720491467089, "grad_norm": 4.769518852233887, "learning_rate": 9.992933529091533e-06, "loss": 0.6057, "step": 96930 }, { "epoch": 0.5762314912233774, "grad_norm": 6.0751118659973145, "learning_rate": 9.99292249723291e-06, "loss": 0.6743, "step": 96940 }, { "epoch": 0.5762909333000458, "grad_norm": 5.802958965301514, "learning_rate": 9.992911456775878e-06, "loss": 0.6515, "step": 96950 }, { "epoch": 0.5763503753767142, "grad_norm": 5.798611164093018, "learning_rate": 9.992900407720458e-06, "loss": 0.6449, "step": 96960 }, { "epoch": 0.5764098174533826, "grad_norm": 5.13034725189209, "learning_rate": 9.992889350066668e-06, "loss": 0.6212, "step": 96970 }, { "epoch": 0.5764692595300509, "grad_norm": 6.190924644470215, "learning_rate": 9.992878283814527e-06, "loss": 0.6088, "step": 96980 }, { "epoch": 0.5765287016067193, "grad_norm": 6.22494649887085, "learning_rate": 9.992867208964052e-06, "loss": 0.6457, "step": 96990 }, { "epoch": 0.5765881436833877, "grad_norm": 4.914314270019531, "learning_rate": 9.992856125515265e-06, "loss": 0.6085, "step": 97000 }, { "epoch": 0.5766475857600561, "grad_norm": 5.0896220207214355, "learning_rate": 9.992845033468184e-06, "loss": 0.6551, "step": 97010 }, { "epoch": 0.5767070278367245, "grad_norm": 5.70431661605835, "learning_rate": 9.99283393282283e-06, "loss": 0.6514, "step": 97020 }, { "epoch": 0.5767664699133929, "grad_norm": 5.8296918869018555, "learning_rate": 9.992822823579219e-06, "loss": 0.7208, "step": 97030 }, { "epoch": 0.5768259119900613, "grad_norm": 5.948971271514893, "learning_rate": 9.992811705737369e-06, "loss": 0.6369, "step": 97040 }, { "epoch": 0.5768853540667297, "grad_norm": 6.656450271606445, "learning_rate": 9.992800579297303e-06, "loss": 0.683, "step": 97050 }, { "epoch": 0.5769447961433981, "grad_norm": 4.507289409637451, "learning_rate": 9.992789444259038e-06, "loss": 0.6516, "step": 97060 }, { "epoch": 0.5770042382200664, "grad_norm": 5.921982765197754, "learning_rate": 9.992778300622596e-06, "loss": 0.637, "step": 97070 }, { "epoch": 0.5770636802967348, "grad_norm": 4.777430057525635, "learning_rate": 9.992767148387994e-06, "loss": 0.6605, "step": 97080 }, { "epoch": 0.5771231223734032, "grad_norm": 5.214144229888916, "learning_rate": 9.99275598755525e-06, "loss": 0.6322, "step": 97090 }, { "epoch": 0.5771825644500717, "grad_norm": 7.141290664672852, "learning_rate": 9.992744818124384e-06, "loss": 0.6125, "step": 97100 }, { "epoch": 0.5772420065267401, "grad_norm": 6.838293552398682, "learning_rate": 9.992733640095416e-06, "loss": 0.6362, "step": 97110 }, { "epoch": 0.5773014486034084, "grad_norm": 4.961694240570068, "learning_rate": 9.992722453468367e-06, "loss": 0.5978, "step": 97120 }, { "epoch": 0.5773608906800768, "grad_norm": 6.828451633453369, "learning_rate": 9.992711258243251e-06, "loss": 0.6836, "step": 97130 }, { "epoch": 0.5774203327567452, "grad_norm": 5.87019681930542, "learning_rate": 9.992700054420093e-06, "loss": 0.5947, "step": 97140 }, { "epoch": 0.5774797748334136, "grad_norm": 6.0079474449157715, "learning_rate": 9.992688841998907e-06, "loss": 0.6472, "step": 97150 }, { "epoch": 0.5775392169100819, "grad_norm": 7.032303333282471, "learning_rate": 9.992677620979719e-06, "loss": 0.6439, "step": 97160 }, { "epoch": 0.5775986589867503, "grad_norm": 6.500199794769287, "learning_rate": 9.992666391362541e-06, "loss": 0.6331, "step": 97170 }, { "epoch": 0.5776581010634187, "grad_norm": 5.80659818649292, "learning_rate": 9.992655153147398e-06, "loss": 0.6146, "step": 97180 }, { "epoch": 0.5777175431400872, "grad_norm": 5.482794761657715, "learning_rate": 9.992643906334306e-06, "loss": 0.6463, "step": 97190 }, { "epoch": 0.5777769852167556, "grad_norm": 5.103768348693848, "learning_rate": 9.992632650923284e-06, "loss": 0.6659, "step": 97200 }, { "epoch": 0.5778364272934239, "grad_norm": 6.521722793579102, "learning_rate": 9.992621386914354e-06, "loss": 0.6787, "step": 97210 }, { "epoch": 0.5778958693700923, "grad_norm": 6.106356143951416, "learning_rate": 9.992610114307536e-06, "loss": 0.6822, "step": 97220 }, { "epoch": 0.5779553114467607, "grad_norm": 6.936004638671875, "learning_rate": 9.992598833102846e-06, "loss": 0.6858, "step": 97230 }, { "epoch": 0.5780147535234291, "grad_norm": 8.019547462463379, "learning_rate": 9.992587543300305e-06, "loss": 0.6768, "step": 97240 }, { "epoch": 0.5780741956000975, "grad_norm": 6.687987327575684, "learning_rate": 9.992576244899935e-06, "loss": 0.6681, "step": 97250 }, { "epoch": 0.5781336376767658, "grad_norm": 6.9621758460998535, "learning_rate": 9.99256493790175e-06, "loss": 0.6148, "step": 97260 }, { "epoch": 0.5781930797534343, "grad_norm": 6.703548431396484, "learning_rate": 9.992553622305773e-06, "loss": 0.6874, "step": 97270 }, { "epoch": 0.5782525218301027, "grad_norm": 5.974234580993652, "learning_rate": 9.992542298112024e-06, "loss": 0.6331, "step": 97280 }, { "epoch": 0.5783119639067711, "grad_norm": 6.402970314025879, "learning_rate": 9.992530965320522e-06, "loss": 0.6281, "step": 97290 }, { "epoch": 0.5783714059834394, "grad_norm": 5.577551364898682, "learning_rate": 9.992519623931284e-06, "loss": 0.611, "step": 97300 }, { "epoch": 0.5784308480601078, "grad_norm": 5.7362494468688965, "learning_rate": 9.992508273944333e-06, "loss": 0.6228, "step": 97310 }, { "epoch": 0.5784902901367762, "grad_norm": 5.693157196044922, "learning_rate": 9.992496915359687e-06, "loss": 0.6069, "step": 97320 }, { "epoch": 0.5785497322134446, "grad_norm": 5.283364772796631, "learning_rate": 9.992485548177364e-06, "loss": 0.65, "step": 97330 }, { "epoch": 0.578609174290113, "grad_norm": 6.000251770019531, "learning_rate": 9.992474172397387e-06, "loss": 0.6409, "step": 97340 }, { "epoch": 0.5786686163667814, "grad_norm": 6.84769344329834, "learning_rate": 9.992462788019773e-06, "loss": 0.6124, "step": 97350 }, { "epoch": 0.5787280584434498, "grad_norm": 4.883835315704346, "learning_rate": 9.992451395044543e-06, "loss": 0.6155, "step": 97360 }, { "epoch": 0.5787875005201182, "grad_norm": 6.7746100425720215, "learning_rate": 9.992439993471714e-06, "loss": 0.6836, "step": 97370 }, { "epoch": 0.5788469425967866, "grad_norm": 5.89482307434082, "learning_rate": 9.99242858330131e-06, "loss": 0.5905, "step": 97380 }, { "epoch": 0.5789063846734549, "grad_norm": 7.916278839111328, "learning_rate": 9.992417164533347e-06, "loss": 0.6403, "step": 97390 }, { "epoch": 0.5789658267501233, "grad_norm": 5.96843147277832, "learning_rate": 9.992405737167846e-06, "loss": 0.6066, "step": 97400 }, { "epoch": 0.5790252688267917, "grad_norm": 7.7686686515808105, "learning_rate": 9.992394301204828e-06, "loss": 0.6845, "step": 97410 }, { "epoch": 0.5790847109034601, "grad_norm": 5.32803201675415, "learning_rate": 9.99238285664431e-06, "loss": 0.6784, "step": 97420 }, { "epoch": 0.5791441529801286, "grad_norm": 5.678235054016113, "learning_rate": 9.992371403486313e-06, "loss": 0.6017, "step": 97430 }, { "epoch": 0.5792035950567969, "grad_norm": 5.354465484619141, "learning_rate": 9.992359941730857e-06, "loss": 0.6275, "step": 97440 }, { "epoch": 0.5792630371334653, "grad_norm": 5.322080612182617, "learning_rate": 9.992348471377962e-06, "loss": 0.6718, "step": 97450 }, { "epoch": 0.5793224792101337, "grad_norm": 5.398351669311523, "learning_rate": 9.992336992427646e-06, "loss": 0.6303, "step": 97460 }, { "epoch": 0.5793819212868021, "grad_norm": 6.3920369148254395, "learning_rate": 9.992325504879932e-06, "loss": 0.6438, "step": 97470 }, { "epoch": 0.5794413633634705, "grad_norm": 5.244722366333008, "learning_rate": 9.992314008734835e-06, "loss": 0.6249, "step": 97480 }, { "epoch": 0.5795008054401388, "grad_norm": 5.198000431060791, "learning_rate": 9.99230250399238e-06, "loss": 0.7115, "step": 97490 }, { "epoch": 0.5795602475168072, "grad_norm": 6.388227462768555, "learning_rate": 9.992290990652584e-06, "loss": 0.6294, "step": 97500 }, { "epoch": 0.5796196895934757, "grad_norm": 6.024518013000488, "learning_rate": 9.992279468715466e-06, "loss": 0.6767, "step": 97510 }, { "epoch": 0.5796791316701441, "grad_norm": 5.6681671142578125, "learning_rate": 9.992267938181049e-06, "loss": 0.646, "step": 97520 }, { "epoch": 0.5797385737468124, "grad_norm": 5.522818565368652, "learning_rate": 9.99225639904935e-06, "loss": 0.6467, "step": 97530 }, { "epoch": 0.5797980158234808, "grad_norm": 5.999849319458008, "learning_rate": 9.99224485132039e-06, "loss": 0.6478, "step": 97540 }, { "epoch": 0.5798574579001492, "grad_norm": 5.921759128570557, "learning_rate": 9.992233294994188e-06, "loss": 0.6697, "step": 97550 }, { "epoch": 0.5799168999768176, "grad_norm": 4.97662353515625, "learning_rate": 9.992221730070765e-06, "loss": 0.6473, "step": 97560 }, { "epoch": 0.579976342053486, "grad_norm": 5.754209041595459, "learning_rate": 9.992210156550142e-06, "loss": 0.6344, "step": 97570 }, { "epoch": 0.5800357841301543, "grad_norm": 4.994938850402832, "learning_rate": 9.992198574432336e-06, "loss": 0.6486, "step": 97580 }, { "epoch": 0.5800952262068227, "grad_norm": 7.46288537979126, "learning_rate": 9.992186983717369e-06, "loss": 0.7034, "step": 97590 }, { "epoch": 0.5801546682834912, "grad_norm": 5.850627422332764, "learning_rate": 9.99217538440526e-06, "loss": 0.6312, "step": 97600 }, { "epoch": 0.5802141103601596, "grad_norm": 6.257199764251709, "learning_rate": 9.992163776496029e-06, "loss": 0.6478, "step": 97610 }, { "epoch": 0.580273552436828, "grad_norm": 5.210930347442627, "learning_rate": 9.992152159989697e-06, "loss": 0.6147, "step": 97620 }, { "epoch": 0.5803329945134963, "grad_norm": 4.922537803649902, "learning_rate": 9.992140534886281e-06, "loss": 0.6125, "step": 97630 }, { "epoch": 0.5803924365901647, "grad_norm": 5.629409313201904, "learning_rate": 9.992128901185805e-06, "loss": 0.6492, "step": 97640 }, { "epoch": 0.5804518786668331, "grad_norm": 5.241480827331543, "learning_rate": 9.992117258888289e-06, "loss": 0.5828, "step": 97650 }, { "epoch": 0.5805113207435015, "grad_norm": 5.163851261138916, "learning_rate": 9.99210560799375e-06, "loss": 0.6364, "step": 97660 }, { "epoch": 0.5805707628201698, "grad_norm": 4.620802402496338, "learning_rate": 9.992093948502208e-06, "loss": 0.5776, "step": 97670 }, { "epoch": 0.5806302048968383, "grad_norm": 5.75425910949707, "learning_rate": 9.992082280413685e-06, "loss": 0.6278, "step": 97680 }, { "epoch": 0.5806896469735067, "grad_norm": 5.693973541259766, "learning_rate": 9.992070603728203e-06, "loss": 0.6193, "step": 97690 }, { "epoch": 0.5807490890501751, "grad_norm": 5.684383869171143, "learning_rate": 9.992058918445779e-06, "loss": 0.6129, "step": 97700 }, { "epoch": 0.5808085311268435, "grad_norm": 5.685906887054443, "learning_rate": 9.992047224566434e-06, "loss": 0.6294, "step": 97710 }, { "epoch": 0.5808679732035118, "grad_norm": 6.024167537689209, "learning_rate": 9.992035522090186e-06, "loss": 0.6148, "step": 97720 }, { "epoch": 0.5809274152801802, "grad_norm": 4.551430702209473, "learning_rate": 9.99202381101706e-06, "loss": 0.5969, "step": 97730 }, { "epoch": 0.5809868573568486, "grad_norm": 5.869468688964844, "learning_rate": 9.992012091347072e-06, "loss": 0.6466, "step": 97740 }, { "epoch": 0.581046299433517, "grad_norm": 4.9037766456604, "learning_rate": 9.992000363080243e-06, "loss": 0.6329, "step": 97750 }, { "epoch": 0.5811057415101853, "grad_norm": 5.863574981689453, "learning_rate": 9.991988626216595e-06, "loss": 0.6417, "step": 97760 }, { "epoch": 0.5811651835868538, "grad_norm": 7.071874618530273, "learning_rate": 9.991976880756147e-06, "loss": 0.6688, "step": 97770 }, { "epoch": 0.5812246256635222, "grad_norm": 6.197445392608643, "learning_rate": 9.991965126698917e-06, "loss": 0.6132, "step": 97780 }, { "epoch": 0.5812840677401906, "grad_norm": 6.448992729187012, "learning_rate": 9.991953364044928e-06, "loss": 0.6752, "step": 97790 }, { "epoch": 0.581343509816859, "grad_norm": 6.960779666900635, "learning_rate": 9.991941592794201e-06, "loss": 0.6285, "step": 97800 }, { "epoch": 0.5814029518935273, "grad_norm": 6.923895835876465, "learning_rate": 9.991929812946755e-06, "loss": 0.5915, "step": 97810 }, { "epoch": 0.5814623939701957, "grad_norm": 6.37771463394165, "learning_rate": 9.99191802450261e-06, "loss": 0.5879, "step": 97820 }, { "epoch": 0.5815218360468641, "grad_norm": 6.054518699645996, "learning_rate": 9.991906227461787e-06, "loss": 0.6521, "step": 97830 }, { "epoch": 0.5815812781235326, "grad_norm": 7.501851558685303, "learning_rate": 9.991894421824304e-06, "loss": 0.6167, "step": 97840 }, { "epoch": 0.581640720200201, "grad_norm": 5.29835319519043, "learning_rate": 9.991882607590185e-06, "loss": 0.5801, "step": 97850 }, { "epoch": 0.5817001622768693, "grad_norm": 5.879125118255615, "learning_rate": 9.991870784759447e-06, "loss": 0.6849, "step": 97860 }, { "epoch": 0.5817596043535377, "grad_norm": 6.858876705169678, "learning_rate": 9.991858953332113e-06, "loss": 0.6412, "step": 97870 }, { "epoch": 0.5818190464302061, "grad_norm": 5.856077671051025, "learning_rate": 9.991847113308202e-06, "loss": 0.6404, "step": 97880 }, { "epoch": 0.5818784885068745, "grad_norm": 6.274583339691162, "learning_rate": 9.991835264687735e-06, "loss": 0.5826, "step": 97890 }, { "epoch": 0.5819379305835428, "grad_norm": 6.445981502532959, "learning_rate": 9.991823407470731e-06, "loss": 0.7009, "step": 97900 }, { "epoch": 0.5819973726602112, "grad_norm": 6.175530433654785, "learning_rate": 9.991811541657212e-06, "loss": 0.6603, "step": 97910 }, { "epoch": 0.5820568147368796, "grad_norm": 6.405066013336182, "learning_rate": 9.991799667247198e-06, "loss": 0.6229, "step": 97920 }, { "epoch": 0.5821162568135481, "grad_norm": 5.1008429527282715, "learning_rate": 9.99178778424071e-06, "loss": 0.6544, "step": 97930 }, { "epoch": 0.5821756988902165, "grad_norm": 6.94518518447876, "learning_rate": 9.991775892637767e-06, "loss": 0.642, "step": 97940 }, { "epoch": 0.5822351409668848, "grad_norm": 6.547281742095947, "learning_rate": 9.99176399243839e-06, "loss": 0.6534, "step": 97950 }, { "epoch": 0.5822945830435532, "grad_norm": 5.317800521850586, "learning_rate": 9.991752083642601e-06, "loss": 0.6295, "step": 97960 }, { "epoch": 0.5823540251202216, "grad_norm": 4.79497766494751, "learning_rate": 9.991740166250418e-06, "loss": 0.5934, "step": 97970 }, { "epoch": 0.58241346719689, "grad_norm": 5.302137851715088, "learning_rate": 9.991728240261864e-06, "loss": 0.6285, "step": 97980 }, { "epoch": 0.5824729092735583, "grad_norm": 5.465054988861084, "learning_rate": 9.991716305676957e-06, "loss": 0.646, "step": 97990 }, { "epoch": 0.5825323513502267, "grad_norm": 5.4119873046875, "learning_rate": 9.99170436249572e-06, "loss": 0.6249, "step": 98000 }, { "epoch": 0.5825917934268952, "grad_norm": 5.395386695861816, "learning_rate": 9.991692410718173e-06, "loss": 0.6315, "step": 98010 }, { "epoch": 0.5826512355035636, "grad_norm": 6.634637355804443, "learning_rate": 9.991680450344335e-06, "loss": 0.6544, "step": 98020 }, { "epoch": 0.582710677580232, "grad_norm": 6.058325290679932, "learning_rate": 9.991668481374228e-06, "loss": 0.5879, "step": 98030 }, { "epoch": 0.5827701196569003, "grad_norm": 6.951851844787598, "learning_rate": 9.991656503807871e-06, "loss": 0.6597, "step": 98040 }, { "epoch": 0.5828295617335687, "grad_norm": 5.507787227630615, "learning_rate": 9.99164451764529e-06, "loss": 0.6106, "step": 98050 }, { "epoch": 0.5828890038102371, "grad_norm": 4.664574146270752, "learning_rate": 9.991632522886498e-06, "loss": 0.6139, "step": 98060 }, { "epoch": 0.5829484458869055, "grad_norm": 6.917599678039551, "learning_rate": 9.99162051953152e-06, "loss": 0.6006, "step": 98070 }, { "epoch": 0.583007887963574, "grad_norm": 6.485892295837402, "learning_rate": 9.991608507580375e-06, "loss": 0.6015, "step": 98080 }, { "epoch": 0.5830673300402422, "grad_norm": 6.171868801116943, "learning_rate": 9.991596487033086e-06, "loss": 0.6316, "step": 98090 }, { "epoch": 0.5831267721169107, "grad_norm": 5.791971683502197, "learning_rate": 9.991584457889671e-06, "loss": 0.5873, "step": 98100 }, { "epoch": 0.5831862141935791, "grad_norm": 5.337850093841553, "learning_rate": 9.991572420150152e-06, "loss": 0.6206, "step": 98110 }, { "epoch": 0.5832456562702475, "grad_norm": 5.727653980255127, "learning_rate": 9.99156037381455e-06, "loss": 0.609, "step": 98120 }, { "epoch": 0.5833050983469158, "grad_norm": 5.943316459655762, "learning_rate": 9.991548318882887e-06, "loss": 0.6158, "step": 98130 }, { "epoch": 0.5833645404235842, "grad_norm": 5.6238298416137695, "learning_rate": 9.991536255355181e-06, "loss": 0.6005, "step": 98140 }, { "epoch": 0.5834239825002526, "grad_norm": 6.475635528564453, "learning_rate": 9.991524183231453e-06, "loss": 0.6014, "step": 98150 }, { "epoch": 0.583483424576921, "grad_norm": 6.02802038192749, "learning_rate": 9.991512102511727e-06, "loss": 0.674, "step": 98160 }, { "epoch": 0.5835428666535895, "grad_norm": 5.465724945068359, "learning_rate": 9.991500013196019e-06, "loss": 0.6352, "step": 98170 }, { "epoch": 0.5836023087302578, "grad_norm": 6.268215179443359, "learning_rate": 9.991487915284355e-06, "loss": 0.6445, "step": 98180 }, { "epoch": 0.5836617508069262, "grad_norm": 7.446732997894287, "learning_rate": 9.991475808776752e-06, "loss": 0.6566, "step": 98190 }, { "epoch": 0.5837211928835946, "grad_norm": 5.497768878936768, "learning_rate": 9.99146369367323e-06, "loss": 0.6448, "step": 98200 }, { "epoch": 0.583780634960263, "grad_norm": 7.691399097442627, "learning_rate": 9.991451569973815e-06, "loss": 0.6244, "step": 98210 }, { "epoch": 0.5838400770369314, "grad_norm": 5.29119873046875, "learning_rate": 9.991439437678525e-06, "loss": 0.648, "step": 98220 }, { "epoch": 0.5838995191135997, "grad_norm": 7.920933723449707, "learning_rate": 9.991427296787378e-06, "loss": 0.7167, "step": 98230 }, { "epoch": 0.5839589611902681, "grad_norm": 6.6272149085998535, "learning_rate": 9.9914151473004e-06, "loss": 0.617, "step": 98240 }, { "epoch": 0.5840184032669365, "grad_norm": 4.403860569000244, "learning_rate": 9.991402989217608e-06, "loss": 0.6408, "step": 98250 }, { "epoch": 0.584077845343605, "grad_norm": 6.7450666427612305, "learning_rate": 9.991390822539026e-06, "loss": 0.5891, "step": 98260 }, { "epoch": 0.5841372874202733, "grad_norm": 5.886392593383789, "learning_rate": 9.991378647264672e-06, "loss": 0.6706, "step": 98270 }, { "epoch": 0.5841967294969417, "grad_norm": 6.54303503036499, "learning_rate": 9.991366463394569e-06, "loss": 0.6231, "step": 98280 }, { "epoch": 0.5842561715736101, "grad_norm": 5.986405372619629, "learning_rate": 9.991354270928738e-06, "loss": 0.6944, "step": 98290 }, { "epoch": 0.5843156136502785, "grad_norm": 4.822733402252197, "learning_rate": 9.991342069867198e-06, "loss": 0.6196, "step": 98300 }, { "epoch": 0.5843750557269469, "grad_norm": 6.82276725769043, "learning_rate": 9.991329860209973e-06, "loss": 0.6834, "step": 98310 }, { "epoch": 0.5844344978036152, "grad_norm": 6.984139442443848, "learning_rate": 9.99131764195708e-06, "loss": 0.6802, "step": 98320 }, { "epoch": 0.5844939398802836, "grad_norm": 7.303985118865967, "learning_rate": 9.991305415108546e-06, "loss": 0.6284, "step": 98330 }, { "epoch": 0.5845533819569521, "grad_norm": 6.626253604888916, "learning_rate": 9.991293179664385e-06, "loss": 0.5957, "step": 98340 }, { "epoch": 0.5846128240336205, "grad_norm": 5.7823262214660645, "learning_rate": 9.991280935624624e-06, "loss": 0.6401, "step": 98350 }, { "epoch": 0.5846722661102888, "grad_norm": 5.033567428588867, "learning_rate": 9.991268682989282e-06, "loss": 0.6826, "step": 98360 }, { "epoch": 0.5847317081869572, "grad_norm": 5.244707107543945, "learning_rate": 9.991256421758377e-06, "loss": 0.6317, "step": 98370 }, { "epoch": 0.5847911502636256, "grad_norm": 5.7645463943481445, "learning_rate": 9.991244151931936e-06, "loss": 0.6579, "step": 98380 }, { "epoch": 0.584850592340294, "grad_norm": 5.9094743728637695, "learning_rate": 9.991231873509974e-06, "loss": 0.601, "step": 98390 }, { "epoch": 0.5849100344169624, "grad_norm": 6.8032917976379395, "learning_rate": 9.991219586492518e-06, "loss": 0.645, "step": 98400 }, { "epoch": 0.5849694764936307, "grad_norm": 7.850750923156738, "learning_rate": 9.991207290879585e-06, "loss": 0.652, "step": 98410 }, { "epoch": 0.5850289185702992, "grad_norm": 4.955120086669922, "learning_rate": 9.991194986671198e-06, "loss": 0.5896, "step": 98420 }, { "epoch": 0.5850883606469676, "grad_norm": 6.053214073181152, "learning_rate": 9.991182673867377e-06, "loss": 0.6174, "step": 98430 }, { "epoch": 0.585147802723636, "grad_norm": 4.731318473815918, "learning_rate": 9.991170352468144e-06, "loss": 0.6609, "step": 98440 }, { "epoch": 0.5852072448003044, "grad_norm": 6.023171901702881, "learning_rate": 9.99115802247352e-06, "loss": 0.6725, "step": 98450 }, { "epoch": 0.5852666868769727, "grad_norm": 5.961103916168213, "learning_rate": 9.991145683883527e-06, "loss": 0.6694, "step": 98460 }, { "epoch": 0.5853261289536411, "grad_norm": 6.012643814086914, "learning_rate": 9.991133336698184e-06, "loss": 0.6128, "step": 98470 }, { "epoch": 0.5853855710303095, "grad_norm": 6.56734561920166, "learning_rate": 9.991120980917517e-06, "loss": 0.686, "step": 98480 }, { "epoch": 0.5854450131069779, "grad_norm": 5.4586181640625, "learning_rate": 9.991108616541542e-06, "loss": 0.5916, "step": 98490 }, { "epoch": 0.5855044551836462, "grad_norm": 6.937361240386963, "learning_rate": 9.991096243570283e-06, "loss": 0.6414, "step": 98500 }, { "epoch": 0.5855638972603147, "grad_norm": 6.129397392272949, "learning_rate": 9.99108386200376e-06, "loss": 0.6248, "step": 98510 }, { "epoch": 0.5856233393369831, "grad_norm": 6.066634654998779, "learning_rate": 9.991071471841996e-06, "loss": 0.6311, "step": 98520 }, { "epoch": 0.5856827814136515, "grad_norm": 5.2596755027771, "learning_rate": 9.991059073085009e-06, "loss": 0.6922, "step": 98530 }, { "epoch": 0.5857422234903199, "grad_norm": 6.925660610198975, "learning_rate": 9.991046665732827e-06, "loss": 0.647, "step": 98540 }, { "epoch": 0.5858016655669882, "grad_norm": 6.268363952636719, "learning_rate": 9.991034249785464e-06, "loss": 0.6489, "step": 98550 }, { "epoch": 0.5858611076436566, "grad_norm": 5.318767070770264, "learning_rate": 9.991021825242944e-06, "loss": 0.529, "step": 98560 }, { "epoch": 0.585920549720325, "grad_norm": 4.486879825592041, "learning_rate": 9.991009392105291e-06, "loss": 0.5854, "step": 98570 }, { "epoch": 0.5859799917969934, "grad_norm": 7.330524921417236, "learning_rate": 9.990996950372524e-06, "loss": 0.6363, "step": 98580 }, { "epoch": 0.5860394338736619, "grad_norm": 5.634793758392334, "learning_rate": 9.990984500044663e-06, "loss": 0.633, "step": 98590 }, { "epoch": 0.5860988759503302, "grad_norm": 6.2124762535095215, "learning_rate": 9.990972041121733e-06, "loss": 0.6141, "step": 98600 }, { "epoch": 0.5861583180269986, "grad_norm": 6.054547309875488, "learning_rate": 9.990959573603754e-06, "loss": 0.6215, "step": 98610 }, { "epoch": 0.586217760103667, "grad_norm": 5.355025291442871, "learning_rate": 9.990947097490746e-06, "loss": 0.5898, "step": 98620 }, { "epoch": 0.5862772021803354, "grad_norm": 4.7170023918151855, "learning_rate": 9.99093461278273e-06, "loss": 0.6024, "step": 98630 }, { "epoch": 0.5863366442570037, "grad_norm": 6.064617156982422, "learning_rate": 9.990922119479731e-06, "loss": 0.6052, "step": 98640 }, { "epoch": 0.5863960863336721, "grad_norm": 5.86468505859375, "learning_rate": 9.99090961758177e-06, "loss": 0.5943, "step": 98650 }, { "epoch": 0.5864555284103405, "grad_norm": 5.386343955993652, "learning_rate": 9.990897107088864e-06, "loss": 0.6029, "step": 98660 }, { "epoch": 0.586514970487009, "grad_norm": 6.932507514953613, "learning_rate": 9.99088458800104e-06, "loss": 0.5928, "step": 98670 }, { "epoch": 0.5865744125636774, "grad_norm": 5.287940502166748, "learning_rate": 9.990872060318317e-06, "loss": 0.6117, "step": 98680 }, { "epoch": 0.5866338546403457, "grad_norm": 7.0567731857299805, "learning_rate": 9.990859524040717e-06, "loss": 0.6534, "step": 98690 }, { "epoch": 0.5866932967170141, "grad_norm": 6.336987495422363, "learning_rate": 9.99084697916826e-06, "loss": 0.5957, "step": 98700 }, { "epoch": 0.5867527387936825, "grad_norm": 5.736527442932129, "learning_rate": 9.990834425700969e-06, "loss": 0.5924, "step": 98710 }, { "epoch": 0.5868121808703509, "grad_norm": 5.344428539276123, "learning_rate": 9.990821863638867e-06, "loss": 0.6326, "step": 98720 }, { "epoch": 0.5868716229470192, "grad_norm": 4.599025249481201, "learning_rate": 9.990809292981973e-06, "loss": 0.564, "step": 98730 }, { "epoch": 0.5869310650236876, "grad_norm": 6.299681186676025, "learning_rate": 9.99079671373031e-06, "loss": 0.6435, "step": 98740 }, { "epoch": 0.586990507100356, "grad_norm": 9.552112579345703, "learning_rate": 9.9907841258839e-06, "loss": 0.6574, "step": 98750 }, { "epoch": 0.5870499491770245, "grad_norm": 6.018455982208252, "learning_rate": 9.990771529442765e-06, "loss": 0.6304, "step": 98760 }, { "epoch": 0.5871093912536929, "grad_norm": 5.623745441436768, "learning_rate": 9.990758924406925e-06, "loss": 0.6509, "step": 98770 }, { "epoch": 0.5871688333303612, "grad_norm": 7.032788276672363, "learning_rate": 9.990746310776402e-06, "loss": 0.6889, "step": 98780 }, { "epoch": 0.5872282754070296, "grad_norm": 7.86833381652832, "learning_rate": 9.99073368855122e-06, "loss": 0.618, "step": 98790 }, { "epoch": 0.587287717483698, "grad_norm": 5.600659370422363, "learning_rate": 9.990721057731399e-06, "loss": 0.6404, "step": 98800 }, { "epoch": 0.5873471595603664, "grad_norm": 6.665111541748047, "learning_rate": 9.99070841831696e-06, "loss": 0.6529, "step": 98810 }, { "epoch": 0.5874066016370348, "grad_norm": 7.610862731933594, "learning_rate": 9.990695770307926e-06, "loss": 0.7031, "step": 98820 }, { "epoch": 0.5874660437137031, "grad_norm": 4.932118892669678, "learning_rate": 9.990683113704316e-06, "loss": 0.5639, "step": 98830 }, { "epoch": 0.5875254857903716, "grad_norm": 5.272798538208008, "learning_rate": 9.990670448506158e-06, "loss": 0.659, "step": 98840 }, { "epoch": 0.58758492786704, "grad_norm": 6.397696018218994, "learning_rate": 9.990657774713469e-06, "loss": 0.6553, "step": 98850 }, { "epoch": 0.5876443699437084, "grad_norm": 5.076019287109375, "learning_rate": 9.99064509232627e-06, "loss": 0.5812, "step": 98860 }, { "epoch": 0.5877038120203767, "grad_norm": 6.508388042449951, "learning_rate": 9.990632401344586e-06, "loss": 0.6178, "step": 98870 }, { "epoch": 0.5877632540970451, "grad_norm": 6.573127746582031, "learning_rate": 9.990619701768438e-06, "loss": 0.7021, "step": 98880 }, { "epoch": 0.5878226961737135, "grad_norm": 5.048924446105957, "learning_rate": 9.990606993597847e-06, "loss": 0.6533, "step": 98890 }, { "epoch": 0.5878821382503819, "grad_norm": 6.80389404296875, "learning_rate": 9.990594276832835e-06, "loss": 0.6779, "step": 98900 }, { "epoch": 0.5879415803270504, "grad_norm": 6.358548164367676, "learning_rate": 9.990581551473425e-06, "loss": 0.7163, "step": 98910 }, { "epoch": 0.5880010224037187, "grad_norm": 7.018893241882324, "learning_rate": 9.990568817519637e-06, "loss": 0.581, "step": 98920 }, { "epoch": 0.5880604644803871, "grad_norm": 5.939783096313477, "learning_rate": 9.990556074971493e-06, "loss": 0.5713, "step": 98930 }, { "epoch": 0.5881199065570555, "grad_norm": 6.19826602935791, "learning_rate": 9.990543323829018e-06, "loss": 0.6237, "step": 98940 }, { "epoch": 0.5881793486337239, "grad_norm": 6.203308582305908, "learning_rate": 9.99053056409223e-06, "loss": 0.5817, "step": 98950 }, { "epoch": 0.5882387907103923, "grad_norm": 5.559086322784424, "learning_rate": 9.990517795761157e-06, "loss": 0.6694, "step": 98960 }, { "epoch": 0.5882982327870606, "grad_norm": 5.510158061981201, "learning_rate": 9.990505018835813e-06, "loss": 0.6475, "step": 98970 }, { "epoch": 0.588357674863729, "grad_norm": 7.337371826171875, "learning_rate": 9.990492233316225e-06, "loss": 0.6772, "step": 98980 }, { "epoch": 0.5884171169403974, "grad_norm": 5.233780384063721, "learning_rate": 9.990479439202414e-06, "loss": 0.6117, "step": 98990 }, { "epoch": 0.5884765590170659, "grad_norm": 5.563384056091309, "learning_rate": 9.990466636494403e-06, "loss": 0.6132, "step": 99000 }, { "epoch": 0.5885360010937342, "grad_norm": 5.408181190490723, "learning_rate": 9.990453825192211e-06, "loss": 0.6396, "step": 99010 }, { "epoch": 0.5885954431704026, "grad_norm": 6.384740352630615, "learning_rate": 9.990441005295864e-06, "loss": 0.6613, "step": 99020 }, { "epoch": 0.588654885247071, "grad_norm": 5.385287761688232, "learning_rate": 9.99042817680538e-06, "loss": 0.5726, "step": 99030 }, { "epoch": 0.5887143273237394, "grad_norm": 8.60931396484375, "learning_rate": 9.990415339720784e-06, "loss": 0.676, "step": 99040 }, { "epoch": 0.5887737694004078, "grad_norm": 6.412038326263428, "learning_rate": 9.9904024940421e-06, "loss": 0.5947, "step": 99050 }, { "epoch": 0.5888332114770761, "grad_norm": 5.687252044677734, "learning_rate": 9.990389639769343e-06, "loss": 0.6537, "step": 99060 }, { "epoch": 0.5888926535537445, "grad_norm": 4.57726526260376, "learning_rate": 9.990376776902542e-06, "loss": 0.6317, "step": 99070 }, { "epoch": 0.588952095630413, "grad_norm": 4.166868686676025, "learning_rate": 9.990363905441717e-06, "loss": 0.5639, "step": 99080 }, { "epoch": 0.5890115377070814, "grad_norm": 5.845983982086182, "learning_rate": 9.990351025386888e-06, "loss": 0.6097, "step": 99090 }, { "epoch": 0.5890709797837497, "grad_norm": 7.646772861480713, "learning_rate": 9.990338136738083e-06, "loss": 0.5988, "step": 99100 }, { "epoch": 0.5891304218604181, "grad_norm": 7.015842914581299, "learning_rate": 9.990325239495317e-06, "loss": 0.6595, "step": 99110 }, { "epoch": 0.5891898639370865, "grad_norm": 5.729663372039795, "learning_rate": 9.990312333658617e-06, "loss": 0.6746, "step": 99120 }, { "epoch": 0.5892493060137549, "grad_norm": 6.0929083824157715, "learning_rate": 9.990299419228002e-06, "loss": 0.6079, "step": 99130 }, { "epoch": 0.5893087480904233, "grad_norm": 6.485352516174316, "learning_rate": 9.990286496203496e-06, "loss": 0.6255, "step": 99140 }, { "epoch": 0.5893681901670916, "grad_norm": 6.0171051025390625, "learning_rate": 9.990273564585123e-06, "loss": 0.6677, "step": 99150 }, { "epoch": 0.58942763224376, "grad_norm": 6.778461933135986, "learning_rate": 9.990260624372902e-06, "loss": 0.6656, "step": 99160 }, { "epoch": 0.5894870743204285, "grad_norm": 6.9947991371154785, "learning_rate": 9.990247675566858e-06, "loss": 0.6759, "step": 99170 }, { "epoch": 0.5895465163970969, "grad_norm": 5.471008777618408, "learning_rate": 9.99023471816701e-06, "loss": 0.6267, "step": 99180 }, { "epoch": 0.5896059584737653, "grad_norm": 6.005807399749756, "learning_rate": 9.990221752173386e-06, "loss": 0.6388, "step": 99190 }, { "epoch": 0.5896654005504336, "grad_norm": 5.3956451416015625, "learning_rate": 9.990208777586002e-06, "loss": 0.6419, "step": 99200 }, { "epoch": 0.589724842627102, "grad_norm": 5.586304187774658, "learning_rate": 9.990195794404884e-06, "loss": 0.6224, "step": 99210 }, { "epoch": 0.5897842847037704, "grad_norm": 6.537334442138672, "learning_rate": 9.990182802630052e-06, "loss": 0.6344, "step": 99220 }, { "epoch": 0.5898437267804388, "grad_norm": 6.659136772155762, "learning_rate": 9.990169802261532e-06, "loss": 0.6494, "step": 99230 }, { "epoch": 0.5899031688571071, "grad_norm": 5.717402935028076, "learning_rate": 9.990156793299343e-06, "loss": 0.6944, "step": 99240 }, { "epoch": 0.5899626109337756, "grad_norm": 5.698772430419922, "learning_rate": 9.990143775743509e-06, "loss": 0.6337, "step": 99250 }, { "epoch": 0.590022053010444, "grad_norm": 7.838168621063232, "learning_rate": 9.990130749594051e-06, "loss": 0.6833, "step": 99260 }, { "epoch": 0.5900814950871124, "grad_norm": 5.880972862243652, "learning_rate": 9.990117714850994e-06, "loss": 0.715, "step": 99270 }, { "epoch": 0.5901409371637808, "grad_norm": 6.50526237487793, "learning_rate": 9.990104671514358e-06, "loss": 0.62, "step": 99280 }, { "epoch": 0.5902003792404491, "grad_norm": 6.246013641357422, "learning_rate": 9.990091619584167e-06, "loss": 0.6107, "step": 99290 }, { "epoch": 0.5902598213171175, "grad_norm": 5.119030952453613, "learning_rate": 9.990078559060442e-06, "loss": 0.6546, "step": 99300 }, { "epoch": 0.5903192633937859, "grad_norm": 7.693793296813965, "learning_rate": 9.990065489943207e-06, "loss": 0.6203, "step": 99310 }, { "epoch": 0.5903787054704543, "grad_norm": 5.39010763168335, "learning_rate": 9.990052412232483e-06, "loss": 0.6128, "step": 99320 }, { "epoch": 0.5904381475471228, "grad_norm": 5.394947528839111, "learning_rate": 9.990039325928294e-06, "loss": 0.6121, "step": 99330 }, { "epoch": 0.5904975896237911, "grad_norm": 6.047872066497803, "learning_rate": 9.990026231030661e-06, "loss": 0.6267, "step": 99340 }, { "epoch": 0.5905570317004595, "grad_norm": 5.970547676086426, "learning_rate": 9.990013127539609e-06, "loss": 0.6555, "step": 99350 }, { "epoch": 0.5906164737771279, "grad_norm": 6.509753704071045, "learning_rate": 9.990000015455157e-06, "loss": 0.6102, "step": 99360 }, { "epoch": 0.5906759158537963, "grad_norm": 7.753188610076904, "learning_rate": 9.98998689477733e-06, "loss": 0.6307, "step": 99370 }, { "epoch": 0.5907353579304646, "grad_norm": 6.33657693862915, "learning_rate": 9.989973765506152e-06, "loss": 0.6156, "step": 99380 }, { "epoch": 0.590794800007133, "grad_norm": 6.1802473068237305, "learning_rate": 9.989960627641642e-06, "loss": 0.6361, "step": 99390 }, { "epoch": 0.5908542420838014, "grad_norm": 5.459270477294922, "learning_rate": 9.989947481183826e-06, "loss": 0.6262, "step": 99400 }, { "epoch": 0.5909136841604699, "grad_norm": 4.577476501464844, "learning_rate": 9.989934326132723e-06, "loss": 0.6113, "step": 99410 }, { "epoch": 0.5909731262371383, "grad_norm": 4.684741020202637, "learning_rate": 9.989921162488358e-06, "loss": 0.648, "step": 99420 }, { "epoch": 0.5910325683138066, "grad_norm": 5.271511077880859, "learning_rate": 9.989907990250755e-06, "loss": 0.6256, "step": 99430 }, { "epoch": 0.591092010390475, "grad_norm": 6.4939141273498535, "learning_rate": 9.989894809419933e-06, "loss": 0.6132, "step": 99440 }, { "epoch": 0.5911514524671434, "grad_norm": 6.18724250793457, "learning_rate": 9.989881619995919e-06, "loss": 0.6051, "step": 99450 }, { "epoch": 0.5912108945438118, "grad_norm": 5.015764236450195, "learning_rate": 9.989868421978733e-06, "loss": 0.6349, "step": 99460 }, { "epoch": 0.5912703366204801, "grad_norm": 5.276461601257324, "learning_rate": 9.989855215368397e-06, "loss": 0.6636, "step": 99470 }, { "epoch": 0.5913297786971485, "grad_norm": 6.048335552215576, "learning_rate": 9.989842000164935e-06, "loss": 0.5989, "step": 99480 }, { "epoch": 0.591389220773817, "grad_norm": 5.265303611755371, "learning_rate": 9.98982877636837e-06, "loss": 0.6391, "step": 99490 }, { "epoch": 0.5914486628504854, "grad_norm": 6.789035320281982, "learning_rate": 9.989815543978724e-06, "loss": 0.6862, "step": 99500 }, { "epoch": 0.5915081049271538, "grad_norm": 5.103466033935547, "learning_rate": 9.989802302996022e-06, "loss": 0.6481, "step": 99510 }, { "epoch": 0.5915675470038221, "grad_norm": 5.965867042541504, "learning_rate": 9.989789053420285e-06, "loss": 0.6302, "step": 99520 }, { "epoch": 0.5916269890804905, "grad_norm": 5.251582145690918, "learning_rate": 9.989775795251533e-06, "loss": 0.6155, "step": 99530 }, { "epoch": 0.5916864311571589, "grad_norm": 4.846222400665283, "learning_rate": 9.989762528489795e-06, "loss": 0.6506, "step": 99540 }, { "epoch": 0.5917458732338273, "grad_norm": 6.464168548583984, "learning_rate": 9.989749253135087e-06, "loss": 0.6385, "step": 99550 }, { "epoch": 0.5918053153104957, "grad_norm": 7.611341953277588, "learning_rate": 9.989735969187439e-06, "loss": 0.6029, "step": 99560 }, { "epoch": 0.591864757387164, "grad_norm": 5.730255603790283, "learning_rate": 9.98972267664687e-06, "loss": 0.6505, "step": 99570 }, { "epoch": 0.5919241994638325, "grad_norm": 5.5950164794921875, "learning_rate": 9.989709375513402e-06, "loss": 0.6085, "step": 99580 }, { "epoch": 0.5919836415405009, "grad_norm": 5.292847156524658, "learning_rate": 9.989696065787058e-06, "loss": 0.6495, "step": 99590 }, { "epoch": 0.5920430836171693, "grad_norm": 5.908982753753662, "learning_rate": 9.989682747467864e-06, "loss": 0.6503, "step": 99600 }, { "epoch": 0.5921025256938376, "grad_norm": 6.704179286956787, "learning_rate": 9.989669420555838e-06, "loss": 0.6518, "step": 99610 }, { "epoch": 0.592161967770506, "grad_norm": 6.305273056030273, "learning_rate": 9.98965608505101e-06, "loss": 0.6704, "step": 99620 }, { "epoch": 0.5922214098471744, "grad_norm": 3.7891881465911865, "learning_rate": 9.989642740953395e-06, "loss": 0.5707, "step": 99630 }, { "epoch": 0.5922808519238428, "grad_norm": 4.38496208190918, "learning_rate": 9.989629388263023e-06, "loss": 0.656, "step": 99640 }, { "epoch": 0.5923402940005112, "grad_norm": 7.250280857086182, "learning_rate": 9.989616026979912e-06, "loss": 0.6699, "step": 99650 }, { "epoch": 0.5923997360771796, "grad_norm": 5.698645114898682, "learning_rate": 9.989602657104087e-06, "loss": 0.6424, "step": 99660 }, { "epoch": 0.592459178153848, "grad_norm": 7.197325706481934, "learning_rate": 9.989589278635572e-06, "loss": 0.6384, "step": 99670 }, { "epoch": 0.5925186202305164, "grad_norm": 5.449397563934326, "learning_rate": 9.989575891574388e-06, "loss": 0.6579, "step": 99680 }, { "epoch": 0.5925780623071848, "grad_norm": 5.819902420043945, "learning_rate": 9.98956249592056e-06, "loss": 0.6719, "step": 99690 }, { "epoch": 0.5926375043838532, "grad_norm": 5.879879951477051, "learning_rate": 9.989549091674109e-06, "loss": 0.6254, "step": 99700 }, { "epoch": 0.5926969464605215, "grad_norm": 4.4446821212768555, "learning_rate": 9.989535678835059e-06, "loss": 0.603, "step": 99710 }, { "epoch": 0.5927563885371899, "grad_norm": 5.749183654785156, "learning_rate": 9.989522257403433e-06, "loss": 0.6399, "step": 99720 }, { "epoch": 0.5928158306138583, "grad_norm": 5.464807987213135, "learning_rate": 9.989508827379255e-06, "loss": 0.5908, "step": 99730 }, { "epoch": 0.5928752726905268, "grad_norm": 4.695187568664551, "learning_rate": 9.989495388762547e-06, "loss": 0.6441, "step": 99740 }, { "epoch": 0.5929347147671951, "grad_norm": 5.414461135864258, "learning_rate": 9.989481941553335e-06, "loss": 0.6357, "step": 99750 }, { "epoch": 0.5929941568438635, "grad_norm": 5.717350959777832, "learning_rate": 9.989468485751637e-06, "loss": 0.6181, "step": 99760 }, { "epoch": 0.5930535989205319, "grad_norm": 5.546239852905273, "learning_rate": 9.989455021357478e-06, "loss": 0.6514, "step": 99770 }, { "epoch": 0.5931130409972003, "grad_norm": 6.65181303024292, "learning_rate": 9.989441548370884e-06, "loss": 0.6765, "step": 99780 }, { "epoch": 0.5931724830738687, "grad_norm": 7.294747352600098, "learning_rate": 9.989428066791876e-06, "loss": 0.6378, "step": 99790 }, { "epoch": 0.593231925150537, "grad_norm": 5.1886372566223145, "learning_rate": 9.989414576620477e-06, "loss": 0.6555, "step": 99800 }, { "epoch": 0.5932913672272054, "grad_norm": 5.7007551193237305, "learning_rate": 9.989401077856713e-06, "loss": 0.593, "step": 99810 }, { "epoch": 0.5933508093038738, "grad_norm": 6.408595085144043, "learning_rate": 9.989387570500602e-06, "loss": 0.5998, "step": 99820 }, { "epoch": 0.5934102513805423, "grad_norm": 5.555942535400391, "learning_rate": 9.989374054552173e-06, "loss": 0.6484, "step": 99830 }, { "epoch": 0.5934696934572106, "grad_norm": 5.442827224731445, "learning_rate": 9.989360530011444e-06, "loss": 0.6343, "step": 99840 }, { "epoch": 0.593529135533879, "grad_norm": 7.5852251052856445, "learning_rate": 9.989346996878443e-06, "loss": 0.6245, "step": 99850 }, { "epoch": 0.5935885776105474, "grad_norm": 5.756849765777588, "learning_rate": 9.98933345515319e-06, "loss": 0.5985, "step": 99860 }, { "epoch": 0.5936480196872158, "grad_norm": 5.380086898803711, "learning_rate": 9.98931990483571e-06, "loss": 0.6094, "step": 99870 }, { "epoch": 0.5937074617638842, "grad_norm": 6.65819787979126, "learning_rate": 9.989306345926024e-06, "loss": 0.6162, "step": 99880 }, { "epoch": 0.5937669038405525, "grad_norm": 4.691191673278809, "learning_rate": 9.98929277842416e-06, "loss": 0.5788, "step": 99890 }, { "epoch": 0.5938263459172209, "grad_norm": 4.676144123077393, "learning_rate": 9.989279202330137e-06, "loss": 0.6116, "step": 99900 }, { "epoch": 0.5938857879938894, "grad_norm": 5.280275344848633, "learning_rate": 9.98926561764398e-06, "loss": 0.5776, "step": 99910 }, { "epoch": 0.5939452300705578, "grad_norm": 6.502641201019287, "learning_rate": 9.989252024365712e-06, "loss": 0.5948, "step": 99920 }, { "epoch": 0.5940046721472262, "grad_norm": 5.828780174255371, "learning_rate": 9.989238422495358e-06, "loss": 0.6242, "step": 99930 }, { "epoch": 0.5940641142238945, "grad_norm": 6.4457106590271, "learning_rate": 9.989224812032938e-06, "loss": 0.6189, "step": 99940 }, { "epoch": 0.5941235563005629, "grad_norm": 5.554558753967285, "learning_rate": 9.989211192978479e-06, "loss": 0.6395, "step": 99950 }, { "epoch": 0.5941829983772313, "grad_norm": 4.329082489013672, "learning_rate": 9.989197565332003e-06, "loss": 0.6171, "step": 99960 }, { "epoch": 0.5942424404538997, "grad_norm": 5.6123785972595215, "learning_rate": 9.989183929093534e-06, "loss": 0.6484, "step": 99970 }, { "epoch": 0.594301882530568, "grad_norm": 6.194461345672607, "learning_rate": 9.989170284263094e-06, "loss": 0.656, "step": 99980 }, { "epoch": 0.5943613246072365, "grad_norm": 6.610239028930664, "learning_rate": 9.989156630840707e-06, "loss": 0.6204, "step": 99990 }, { "epoch": 0.5944207666839049, "grad_norm": 5.618467807769775, "learning_rate": 9.989142968826397e-06, "loss": 0.6657, "step": 100000 }, { "epoch": 0.5944802087605733, "grad_norm": 5.088164806365967, "learning_rate": 9.989129298220189e-06, "loss": 0.6034, "step": 100010 }, { "epoch": 0.5945396508372417, "grad_norm": 6.570371627807617, "learning_rate": 9.989115619022105e-06, "loss": 0.623, "step": 100020 }, { "epoch": 0.59459909291391, "grad_norm": 5.527661323547363, "learning_rate": 9.989101931232168e-06, "loss": 0.6183, "step": 100030 }, { "epoch": 0.5946585349905784, "grad_norm": 6.135694980621338, "learning_rate": 9.9890882348504e-06, "loss": 0.6454, "step": 100040 }, { "epoch": 0.5947179770672468, "grad_norm": 5.484290599822998, "learning_rate": 9.98907452987683e-06, "loss": 0.625, "step": 100050 }, { "epoch": 0.5947774191439152, "grad_norm": 7.013748645782471, "learning_rate": 9.989060816311479e-06, "loss": 0.6442, "step": 100060 }, { "epoch": 0.5948368612205837, "grad_norm": 6.861962795257568, "learning_rate": 9.989047094154367e-06, "loss": 0.6832, "step": 100070 }, { "epoch": 0.594896303297252, "grad_norm": 5.356868743896484, "learning_rate": 9.989033363405523e-06, "loss": 0.596, "step": 100080 }, { "epoch": 0.5949557453739204, "grad_norm": 8.305867195129395, "learning_rate": 9.989019624064965e-06, "loss": 0.6301, "step": 100090 }, { "epoch": 0.5950151874505888, "grad_norm": 6.525692462921143, "learning_rate": 9.989005876132723e-06, "loss": 0.6009, "step": 100100 }, { "epoch": 0.5950746295272572, "grad_norm": 7.556565761566162, "learning_rate": 9.988992119608816e-06, "loss": 0.5744, "step": 100110 }, { "epoch": 0.5951340716039255, "grad_norm": 6.592773914337158, "learning_rate": 9.98897835449327e-06, "loss": 0.6762, "step": 100120 }, { "epoch": 0.5951935136805939, "grad_norm": 6.747041702270508, "learning_rate": 9.98896458078611e-06, "loss": 0.6364, "step": 100130 }, { "epoch": 0.5952529557572623, "grad_norm": 6.069563865661621, "learning_rate": 9.988950798487353e-06, "loss": 0.7051, "step": 100140 }, { "epoch": 0.5953123978339308, "grad_norm": 5.673901557922363, "learning_rate": 9.988937007597031e-06, "loss": 0.6383, "step": 100150 }, { "epoch": 0.5953718399105992, "grad_norm": 6.217284679412842, "learning_rate": 9.988923208115165e-06, "loss": 0.6606, "step": 100160 }, { "epoch": 0.5954312819872675, "grad_norm": 6.500821113586426, "learning_rate": 9.988909400041775e-06, "loss": 0.6225, "step": 100170 }, { "epoch": 0.5954907240639359, "grad_norm": 5.172035217285156, "learning_rate": 9.98889558337689e-06, "loss": 0.6763, "step": 100180 }, { "epoch": 0.5955501661406043, "grad_norm": 7.326503753662109, "learning_rate": 9.98888175812053e-06, "loss": 0.6535, "step": 100190 }, { "epoch": 0.5956096082172727, "grad_norm": 4.59843111038208, "learning_rate": 9.988867924272721e-06, "loss": 0.6169, "step": 100200 }, { "epoch": 0.595669050293941, "grad_norm": 7.003017425537109, "learning_rate": 9.988854081833485e-06, "loss": 0.6388, "step": 100210 }, { "epoch": 0.5957284923706094, "grad_norm": 6.008425712585449, "learning_rate": 9.988840230802849e-06, "loss": 0.6026, "step": 100220 }, { "epoch": 0.5957879344472778, "grad_norm": 7.554389953613281, "learning_rate": 9.988826371180833e-06, "loss": 0.6284, "step": 100230 }, { "epoch": 0.5958473765239463, "grad_norm": 5.893665313720703, "learning_rate": 9.988812502967464e-06, "loss": 0.6549, "step": 100240 }, { "epoch": 0.5959068186006147, "grad_norm": 5.499917984008789, "learning_rate": 9.988798626162765e-06, "loss": 0.6338, "step": 100250 }, { "epoch": 0.595966260677283, "grad_norm": 6.711421489715576, "learning_rate": 9.988784740766758e-06, "loss": 0.6299, "step": 100260 }, { "epoch": 0.5960257027539514, "grad_norm": 4.85727596282959, "learning_rate": 9.98877084677947e-06, "loss": 0.6357, "step": 100270 }, { "epoch": 0.5960851448306198, "grad_norm": 5.747499465942383, "learning_rate": 9.988756944200921e-06, "loss": 0.6883, "step": 100280 }, { "epoch": 0.5961445869072882, "grad_norm": 5.990118980407715, "learning_rate": 9.988743033031141e-06, "loss": 0.6503, "step": 100290 }, { "epoch": 0.5962040289839566, "grad_norm": 5.691728115081787, "learning_rate": 9.988729113270147e-06, "loss": 0.6235, "step": 100300 }, { "epoch": 0.5962634710606249, "grad_norm": 6.6767988204956055, "learning_rate": 9.988715184917968e-06, "loss": 0.6725, "step": 100310 }, { "epoch": 0.5963229131372934, "grad_norm": 4.787817478179932, "learning_rate": 9.988701247974625e-06, "loss": 0.6365, "step": 100320 }, { "epoch": 0.5963823552139618, "grad_norm": 6.6452813148498535, "learning_rate": 9.988687302440143e-06, "loss": 0.5966, "step": 100330 }, { "epoch": 0.5964417972906302, "grad_norm": 5.798073768615723, "learning_rate": 9.988673348314548e-06, "loss": 0.6075, "step": 100340 }, { "epoch": 0.5965012393672985, "grad_norm": 5.480766773223877, "learning_rate": 9.98865938559786e-06, "loss": 0.6245, "step": 100350 }, { "epoch": 0.5965606814439669, "grad_norm": 5.437358379364014, "learning_rate": 9.988645414290107e-06, "loss": 0.6245, "step": 100360 }, { "epoch": 0.5966201235206353, "grad_norm": 5.118480682373047, "learning_rate": 9.988631434391312e-06, "loss": 0.6541, "step": 100370 }, { "epoch": 0.5966795655973037, "grad_norm": 5.605292797088623, "learning_rate": 9.988617445901496e-06, "loss": 0.6438, "step": 100380 }, { "epoch": 0.5967390076739721, "grad_norm": 5.046172142028809, "learning_rate": 9.988603448820688e-06, "loss": 0.603, "step": 100390 }, { "epoch": 0.5967984497506404, "grad_norm": 6.449732303619385, "learning_rate": 9.988589443148908e-06, "loss": 0.6113, "step": 100400 }, { "epoch": 0.5968578918273089, "grad_norm": 5.9045844078063965, "learning_rate": 9.988575428886183e-06, "loss": 0.6008, "step": 100410 }, { "epoch": 0.5969173339039773, "grad_norm": 4.931790351867676, "learning_rate": 9.988561406032536e-06, "loss": 0.6901, "step": 100420 }, { "epoch": 0.5969767759806457, "grad_norm": 5.0135393142700195, "learning_rate": 9.98854737458799e-06, "loss": 0.5864, "step": 100430 }, { "epoch": 0.5970362180573141, "grad_norm": 7.354618549346924, "learning_rate": 9.988533334552569e-06, "loss": 0.6508, "step": 100440 }, { "epoch": 0.5970956601339824, "grad_norm": 6.5211334228515625, "learning_rate": 9.9885192859263e-06, "loss": 0.6343, "step": 100450 }, { "epoch": 0.5971551022106508, "grad_norm": 5.150487899780273, "learning_rate": 9.988505228709206e-06, "loss": 0.6045, "step": 100460 }, { "epoch": 0.5972145442873192, "grad_norm": 7.121685028076172, "learning_rate": 9.98849116290131e-06, "loss": 0.6055, "step": 100470 }, { "epoch": 0.5972739863639877, "grad_norm": 4.961627960205078, "learning_rate": 9.988477088502637e-06, "loss": 0.688, "step": 100480 }, { "epoch": 0.597333428440656, "grad_norm": 8.497371673583984, "learning_rate": 9.988463005513212e-06, "loss": 0.5608, "step": 100490 }, { "epoch": 0.5973928705173244, "grad_norm": 6.895928859710693, "learning_rate": 9.988448913933057e-06, "loss": 0.5968, "step": 100500 }, { "epoch": 0.5974523125939928, "grad_norm": 6.816167831420898, "learning_rate": 9.988434813762198e-06, "loss": 0.6451, "step": 100510 }, { "epoch": 0.5975117546706612, "grad_norm": 6.7913384437561035, "learning_rate": 9.98842070500066e-06, "loss": 0.6077, "step": 100520 }, { "epoch": 0.5975711967473296, "grad_norm": 5.621081352233887, "learning_rate": 9.988406587648466e-06, "loss": 0.6107, "step": 100530 }, { "epoch": 0.5976306388239979, "grad_norm": 6.407163143157959, "learning_rate": 9.98839246170564e-06, "loss": 0.6518, "step": 100540 }, { "epoch": 0.5976900809006663, "grad_norm": 5.846452713012695, "learning_rate": 9.988378327172208e-06, "loss": 0.6075, "step": 100550 }, { "epoch": 0.5977495229773347, "grad_norm": 6.676877975463867, "learning_rate": 9.988364184048193e-06, "loss": 0.6405, "step": 100560 }, { "epoch": 0.5978089650540032, "grad_norm": 6.840043544769287, "learning_rate": 9.98835003233362e-06, "loss": 0.6249, "step": 100570 }, { "epoch": 0.5978684071306715, "grad_norm": 6.150567531585693, "learning_rate": 9.988335872028511e-06, "loss": 0.6185, "step": 100580 }, { "epoch": 0.5979278492073399, "grad_norm": 4.324588298797607, "learning_rate": 9.988321703132895e-06, "loss": 0.6515, "step": 100590 }, { "epoch": 0.5979872912840083, "grad_norm": 4.971510887145996, "learning_rate": 9.988307525646793e-06, "loss": 0.6333, "step": 100600 }, { "epoch": 0.5980467333606767, "grad_norm": 5.577528953552246, "learning_rate": 9.98829333957023e-06, "loss": 0.6287, "step": 100610 }, { "epoch": 0.5981061754373451, "grad_norm": 6.485509395599365, "learning_rate": 9.98827914490323e-06, "loss": 0.6011, "step": 100620 }, { "epoch": 0.5981656175140134, "grad_norm": 5.035886287689209, "learning_rate": 9.98826494164582e-06, "loss": 0.5514, "step": 100630 }, { "epoch": 0.5982250595906818, "grad_norm": 6.112386226654053, "learning_rate": 9.988250729798021e-06, "loss": 0.7246, "step": 100640 }, { "epoch": 0.5982845016673503, "grad_norm": 5.882339954376221, "learning_rate": 9.98823650935986e-06, "loss": 0.7165, "step": 100650 }, { "epoch": 0.5983439437440187, "grad_norm": 5.505018711090088, "learning_rate": 9.98822228033136e-06, "loss": 0.642, "step": 100660 }, { "epoch": 0.5984033858206871, "grad_norm": 6.054222106933594, "learning_rate": 9.988208042712547e-06, "loss": 0.6061, "step": 100670 }, { "epoch": 0.5984628278973554, "grad_norm": 6.511922836303711, "learning_rate": 9.988193796503442e-06, "loss": 0.6826, "step": 100680 }, { "epoch": 0.5985222699740238, "grad_norm": 4.635082721710205, "learning_rate": 9.988179541704075e-06, "loss": 0.5779, "step": 100690 }, { "epoch": 0.5985817120506922, "grad_norm": 6.167707443237305, "learning_rate": 9.988165278314465e-06, "loss": 0.6166, "step": 100700 }, { "epoch": 0.5986411541273606, "grad_norm": 5.044960021972656, "learning_rate": 9.988151006334642e-06, "loss": 0.627, "step": 100710 }, { "epoch": 0.5987005962040289, "grad_norm": 5.464679718017578, "learning_rate": 9.988136725764626e-06, "loss": 0.6333, "step": 100720 }, { "epoch": 0.5987600382806973, "grad_norm": 5.146831512451172, "learning_rate": 9.988122436604444e-06, "loss": 0.6584, "step": 100730 }, { "epoch": 0.5988194803573658, "grad_norm": 6.417478561401367, "learning_rate": 9.98810813885412e-06, "loss": 0.6449, "step": 100740 }, { "epoch": 0.5988789224340342, "grad_norm": 4.380627155303955, "learning_rate": 9.988093832513679e-06, "loss": 0.5744, "step": 100750 }, { "epoch": 0.5989383645107026, "grad_norm": 4.688436508178711, "learning_rate": 9.988079517583144e-06, "loss": 0.6242, "step": 100760 }, { "epoch": 0.5989978065873709, "grad_norm": 6.236227989196777, "learning_rate": 9.988065194062542e-06, "loss": 0.6284, "step": 100770 }, { "epoch": 0.5990572486640393, "grad_norm": 4.448929309844971, "learning_rate": 9.988050861951896e-06, "loss": 0.6359, "step": 100780 }, { "epoch": 0.5991166907407077, "grad_norm": 5.7047319412231445, "learning_rate": 9.988036521251231e-06, "loss": 0.5896, "step": 100790 }, { "epoch": 0.5991761328173761, "grad_norm": 6.101257801055908, "learning_rate": 9.988022171960573e-06, "loss": 0.555, "step": 100800 }, { "epoch": 0.5992355748940446, "grad_norm": 6.698291778564453, "learning_rate": 9.988007814079946e-06, "loss": 0.5696, "step": 100810 }, { "epoch": 0.5992950169707129, "grad_norm": 5.95236873626709, "learning_rate": 9.987993447609373e-06, "loss": 0.6712, "step": 100820 }, { "epoch": 0.5993544590473813, "grad_norm": 4.213291645050049, "learning_rate": 9.98797907254888e-06, "loss": 0.6786, "step": 100830 }, { "epoch": 0.5994139011240497, "grad_norm": 7.091657638549805, "learning_rate": 9.987964688898492e-06, "loss": 0.6814, "step": 100840 }, { "epoch": 0.5994733432007181, "grad_norm": 5.363035202026367, "learning_rate": 9.987950296658234e-06, "loss": 0.6271, "step": 100850 }, { "epoch": 0.5995327852773864, "grad_norm": 4.814249038696289, "learning_rate": 9.98793589582813e-06, "loss": 0.6598, "step": 100860 }, { "epoch": 0.5995922273540548, "grad_norm": 6.032206058502197, "learning_rate": 9.987921486408206e-06, "loss": 0.6723, "step": 100870 }, { "epoch": 0.5996516694307232, "grad_norm": 4.592721462249756, "learning_rate": 9.987907068398485e-06, "loss": 0.6628, "step": 100880 }, { "epoch": 0.5997111115073916, "grad_norm": 5.452884674072266, "learning_rate": 9.987892641798995e-06, "loss": 0.703, "step": 100890 }, { "epoch": 0.5997705535840601, "grad_norm": 5.463126182556152, "learning_rate": 9.987878206609758e-06, "loss": 0.6406, "step": 100900 }, { "epoch": 0.5998299956607284, "grad_norm": 5.256371974945068, "learning_rate": 9.987863762830798e-06, "loss": 0.6419, "step": 100910 }, { "epoch": 0.5998894377373968, "grad_norm": 4.964287757873535, "learning_rate": 9.987849310462143e-06, "loss": 0.5926, "step": 100920 }, { "epoch": 0.5999488798140652, "grad_norm": 5.122011661529541, "learning_rate": 9.987834849503816e-06, "loss": 0.6969, "step": 100930 }, { "epoch": 0.6000083218907336, "grad_norm": 6.149473667144775, "learning_rate": 9.987820379955842e-06, "loss": 0.5679, "step": 100940 }, { "epoch": 0.6000677639674019, "grad_norm": 5.042130470275879, "learning_rate": 9.987805901818245e-06, "loss": 0.6403, "step": 100950 }, { "epoch": 0.6001272060440703, "grad_norm": 5.864450931549072, "learning_rate": 9.987791415091052e-06, "loss": 0.6612, "step": 100960 }, { "epoch": 0.6001866481207387, "grad_norm": 4.126506805419922, "learning_rate": 9.987776919774287e-06, "loss": 0.6161, "step": 100970 }, { "epoch": 0.6002460901974072, "grad_norm": 5.872923851013184, "learning_rate": 9.987762415867977e-06, "loss": 0.6761, "step": 100980 }, { "epoch": 0.6003055322740756, "grad_norm": 7.348912239074707, "learning_rate": 9.987747903372144e-06, "loss": 0.601, "step": 100990 }, { "epoch": 0.6003649743507439, "grad_norm": 5.137937068939209, "learning_rate": 9.987733382286812e-06, "loss": 0.6143, "step": 101000 }, { "epoch": 0.6004244164274123, "grad_norm": 6.282083034515381, "learning_rate": 9.98771885261201e-06, "loss": 0.5797, "step": 101010 }, { "epoch": 0.6004838585040807, "grad_norm": 5.6130290031433105, "learning_rate": 9.98770431434776e-06, "loss": 0.5958, "step": 101020 }, { "epoch": 0.6005433005807491, "grad_norm": 5.7243876457214355, "learning_rate": 9.98768976749409e-06, "loss": 0.6683, "step": 101030 }, { "epoch": 0.6006027426574175, "grad_norm": 5.713284015655518, "learning_rate": 9.98767521205102e-06, "loss": 0.5827, "step": 101040 }, { "epoch": 0.6006621847340858, "grad_norm": 5.411228179931641, "learning_rate": 9.98766064801858e-06, "loss": 0.6307, "step": 101050 }, { "epoch": 0.6007216268107543, "grad_norm": 6.3703389167785645, "learning_rate": 9.987646075396793e-06, "loss": 0.644, "step": 101060 }, { "epoch": 0.6007810688874227, "grad_norm": 5.614932537078857, "learning_rate": 9.987631494185685e-06, "loss": 0.611, "step": 101070 }, { "epoch": 0.6008405109640911, "grad_norm": 5.319632530212402, "learning_rate": 9.987616904385278e-06, "loss": 0.6197, "step": 101080 }, { "epoch": 0.6008999530407594, "grad_norm": 5.52080774307251, "learning_rate": 9.987602305995603e-06, "loss": 0.6647, "step": 101090 }, { "epoch": 0.6009593951174278, "grad_norm": 5.31962251663208, "learning_rate": 9.98758769901668e-06, "loss": 0.6403, "step": 101100 }, { "epoch": 0.6010188371940962, "grad_norm": 5.208271026611328, "learning_rate": 9.987573083448536e-06, "loss": 0.6463, "step": 101110 }, { "epoch": 0.6010782792707646, "grad_norm": 4.09279203414917, "learning_rate": 9.987558459291196e-06, "loss": 0.5898, "step": 101120 }, { "epoch": 0.601137721347433, "grad_norm": 5.397765636444092, "learning_rate": 9.987543826544684e-06, "loss": 0.6002, "step": 101130 }, { "epoch": 0.6011971634241013, "grad_norm": 6.550975799560547, "learning_rate": 9.987529185209029e-06, "loss": 0.6429, "step": 101140 }, { "epoch": 0.6012566055007698, "grad_norm": 6.180010795593262, "learning_rate": 9.98751453528425e-06, "loss": 0.6343, "step": 101150 }, { "epoch": 0.6013160475774382, "grad_norm": 5.151527404785156, "learning_rate": 9.98749987677038e-06, "loss": 0.6461, "step": 101160 }, { "epoch": 0.6013754896541066, "grad_norm": 6.798721790313721, "learning_rate": 9.987485209667439e-06, "loss": 0.6115, "step": 101170 }, { "epoch": 0.6014349317307749, "grad_norm": 6.7129011154174805, "learning_rate": 9.98747053397545e-06, "loss": 0.6403, "step": 101180 }, { "epoch": 0.6014943738074433, "grad_norm": 5.94084358215332, "learning_rate": 9.987455849694446e-06, "loss": 0.6156, "step": 101190 }, { "epoch": 0.6015538158841117, "grad_norm": 4.362821578979492, "learning_rate": 9.987441156824444e-06, "loss": 0.5744, "step": 101200 }, { "epoch": 0.6016132579607801, "grad_norm": 5.466649055480957, "learning_rate": 9.987426455365476e-06, "loss": 0.7092, "step": 101210 }, { "epoch": 0.6016727000374485, "grad_norm": 4.840116500854492, "learning_rate": 9.987411745317564e-06, "loss": 0.6244, "step": 101220 }, { "epoch": 0.6017321421141169, "grad_norm": 4.189892768859863, "learning_rate": 9.987397026680734e-06, "loss": 0.5794, "step": 101230 }, { "epoch": 0.6017915841907853, "grad_norm": 5.838967800140381, "learning_rate": 9.987382299455011e-06, "loss": 0.6128, "step": 101240 }, { "epoch": 0.6018510262674537, "grad_norm": 4.837996482849121, "learning_rate": 9.987367563640421e-06, "loss": 0.6136, "step": 101250 }, { "epoch": 0.6019104683441221, "grad_norm": 5.4679694175720215, "learning_rate": 9.98735281923699e-06, "loss": 0.58, "step": 101260 }, { "epoch": 0.6019699104207905, "grad_norm": 5.316766738891602, "learning_rate": 9.98733806624474e-06, "loss": 0.6367, "step": 101270 }, { "epoch": 0.6020293524974588, "grad_norm": 6.988853454589844, "learning_rate": 9.987323304663699e-06, "loss": 0.6128, "step": 101280 }, { "epoch": 0.6020887945741272, "grad_norm": 6.131892681121826, "learning_rate": 9.987308534493894e-06, "loss": 0.609, "step": 101290 }, { "epoch": 0.6021482366507956, "grad_norm": 5.990248203277588, "learning_rate": 9.987293755735348e-06, "loss": 0.6405, "step": 101300 }, { "epoch": 0.6022076787274641, "grad_norm": 6.77119779586792, "learning_rate": 9.987278968388086e-06, "loss": 0.6582, "step": 101310 }, { "epoch": 0.6022671208041324, "grad_norm": 5.285444736480713, "learning_rate": 9.987264172452135e-06, "loss": 0.658, "step": 101320 }, { "epoch": 0.6023265628808008, "grad_norm": 9.480340003967285, "learning_rate": 9.987249367927521e-06, "loss": 0.6734, "step": 101330 }, { "epoch": 0.6023860049574692, "grad_norm": 5.446859359741211, "learning_rate": 9.987234554814268e-06, "loss": 0.5827, "step": 101340 }, { "epoch": 0.6024454470341376, "grad_norm": 5.7491536140441895, "learning_rate": 9.987219733112401e-06, "loss": 0.6164, "step": 101350 }, { "epoch": 0.602504889110806, "grad_norm": 6.17291784286499, "learning_rate": 9.987204902821948e-06, "loss": 0.6601, "step": 101360 }, { "epoch": 0.6025643311874743, "grad_norm": 6.617524147033691, "learning_rate": 9.987190063942931e-06, "loss": 0.6931, "step": 101370 }, { "epoch": 0.6026237732641427, "grad_norm": 6.142501354217529, "learning_rate": 9.98717521647538e-06, "loss": 0.6138, "step": 101380 }, { "epoch": 0.6026832153408112, "grad_norm": 4.011977672576904, "learning_rate": 9.987160360419316e-06, "loss": 0.6205, "step": 101390 }, { "epoch": 0.6027426574174796, "grad_norm": 5.799420356750488, "learning_rate": 9.987145495774768e-06, "loss": 0.6133, "step": 101400 }, { "epoch": 0.602802099494148, "grad_norm": 6.081080913543701, "learning_rate": 9.98713062254176e-06, "loss": 0.6045, "step": 101410 }, { "epoch": 0.6028615415708163, "grad_norm": 5.574568748474121, "learning_rate": 9.98711574072032e-06, "loss": 0.6129, "step": 101420 }, { "epoch": 0.6029209836474847, "grad_norm": 4.722722053527832, "learning_rate": 9.98710085031047e-06, "loss": 0.6186, "step": 101430 }, { "epoch": 0.6029804257241531, "grad_norm": 5.878485679626465, "learning_rate": 9.987085951312238e-06, "loss": 0.6772, "step": 101440 }, { "epoch": 0.6030398678008215, "grad_norm": 5.129376411437988, "learning_rate": 9.987071043725649e-06, "loss": 0.6163, "step": 101450 }, { "epoch": 0.6030993098774898, "grad_norm": 5.2530646324157715, "learning_rate": 9.987056127550727e-06, "loss": 0.6591, "step": 101460 }, { "epoch": 0.6031587519541582, "grad_norm": 5.448721885681152, "learning_rate": 9.987041202787499e-06, "loss": 0.6452, "step": 101470 }, { "epoch": 0.6032181940308267, "grad_norm": 5.424075126647949, "learning_rate": 9.987026269435994e-06, "loss": 0.6164, "step": 101480 }, { "epoch": 0.6032776361074951, "grad_norm": 6.1276535987854, "learning_rate": 9.987011327496232e-06, "loss": 0.6423, "step": 101490 }, { "epoch": 0.6033370781841635, "grad_norm": 6.103361129760742, "learning_rate": 9.986996376968244e-06, "loss": 0.6686, "step": 101500 }, { "epoch": 0.6033965202608318, "grad_norm": 3.997537136077881, "learning_rate": 9.98698141785205e-06, "loss": 0.6308, "step": 101510 }, { "epoch": 0.6034559623375002, "grad_norm": 6.014942169189453, "learning_rate": 9.986966450147682e-06, "loss": 0.633, "step": 101520 }, { "epoch": 0.6035154044141686, "grad_norm": 6.382344722747803, "learning_rate": 9.98695147385516e-06, "loss": 0.633, "step": 101530 }, { "epoch": 0.603574846490837, "grad_norm": 4.876914024353027, "learning_rate": 9.986936488974515e-06, "loss": 0.5959, "step": 101540 }, { "epoch": 0.6036342885675053, "grad_norm": 4.526305198669434, "learning_rate": 9.986921495505768e-06, "loss": 0.6199, "step": 101550 }, { "epoch": 0.6036937306441738, "grad_norm": 6.423187255859375, "learning_rate": 9.98690649344895e-06, "loss": 0.6373, "step": 101560 }, { "epoch": 0.6037531727208422, "grad_norm": 6.964501857757568, "learning_rate": 9.986891482804082e-06, "loss": 0.639, "step": 101570 }, { "epoch": 0.6038126147975106, "grad_norm": 5.407958030700684, "learning_rate": 9.986876463571191e-06, "loss": 0.6299, "step": 101580 }, { "epoch": 0.603872056874179, "grad_norm": 5.166740894317627, "learning_rate": 9.986861435750305e-06, "loss": 0.6175, "step": 101590 }, { "epoch": 0.6039314989508473, "grad_norm": 5.487851142883301, "learning_rate": 9.986846399341448e-06, "loss": 0.6311, "step": 101600 }, { "epoch": 0.6039909410275157, "grad_norm": 4.405905246734619, "learning_rate": 9.986831354344648e-06, "loss": 0.6689, "step": 101610 }, { "epoch": 0.6040503831041841, "grad_norm": 4.599606990814209, "learning_rate": 9.986816300759928e-06, "loss": 0.626, "step": 101620 }, { "epoch": 0.6041098251808525, "grad_norm": 5.785004615783691, "learning_rate": 9.986801238587316e-06, "loss": 0.6339, "step": 101630 }, { "epoch": 0.604169267257521, "grad_norm": 7.1912522315979, "learning_rate": 9.986786167826836e-06, "loss": 0.617, "step": 101640 }, { "epoch": 0.6042287093341893, "grad_norm": 6.5738091468811035, "learning_rate": 9.986771088478517e-06, "loss": 0.6294, "step": 101650 }, { "epoch": 0.6042881514108577, "grad_norm": 7.191515922546387, "learning_rate": 9.986756000542383e-06, "loss": 0.6567, "step": 101660 }, { "epoch": 0.6043475934875261, "grad_norm": 6.512572765350342, "learning_rate": 9.986740904018459e-06, "loss": 0.634, "step": 101670 }, { "epoch": 0.6044070355641945, "grad_norm": 6.162146091461182, "learning_rate": 9.986725798906772e-06, "loss": 0.6519, "step": 101680 }, { "epoch": 0.6044664776408628, "grad_norm": 5.21544885635376, "learning_rate": 9.98671068520735e-06, "loss": 0.5984, "step": 101690 }, { "epoch": 0.6045259197175312, "grad_norm": 5.032631874084473, "learning_rate": 9.986695562920216e-06, "loss": 0.6201, "step": 101700 }, { "epoch": 0.6045853617941996, "grad_norm": 7.269071102142334, "learning_rate": 9.986680432045397e-06, "loss": 0.6296, "step": 101710 }, { "epoch": 0.604644803870868, "grad_norm": 4.597109317779541, "learning_rate": 9.986665292582918e-06, "loss": 0.6002, "step": 101720 }, { "epoch": 0.6047042459475365, "grad_norm": 6.204324245452881, "learning_rate": 9.986650144532808e-06, "loss": 0.6097, "step": 101730 }, { "epoch": 0.6047636880242048, "grad_norm": 7.77573823928833, "learning_rate": 9.986634987895092e-06, "loss": 0.6545, "step": 101740 }, { "epoch": 0.6048231301008732, "grad_norm": 6.628633975982666, "learning_rate": 9.986619822669795e-06, "loss": 0.6053, "step": 101750 }, { "epoch": 0.6048825721775416, "grad_norm": 5.525581359863281, "learning_rate": 9.986604648856944e-06, "loss": 0.578, "step": 101760 }, { "epoch": 0.60494201425421, "grad_norm": 6.08671236038208, "learning_rate": 9.986589466456565e-06, "loss": 0.582, "step": 101770 }, { "epoch": 0.6050014563308784, "grad_norm": 5.412531852722168, "learning_rate": 9.986574275468683e-06, "loss": 0.6371, "step": 101780 }, { "epoch": 0.6050608984075467, "grad_norm": 6.921152114868164, "learning_rate": 9.986559075893325e-06, "loss": 0.6202, "step": 101790 }, { "epoch": 0.6051203404842151, "grad_norm": 5.573012351989746, "learning_rate": 9.986543867730518e-06, "loss": 0.5968, "step": 101800 }, { "epoch": 0.6051797825608836, "grad_norm": 5.789003372192383, "learning_rate": 9.986528650980287e-06, "loss": 0.6062, "step": 101810 }, { "epoch": 0.605239224637552, "grad_norm": 5.914379119873047, "learning_rate": 9.986513425642659e-06, "loss": 0.5969, "step": 101820 }, { "epoch": 0.6052986667142203, "grad_norm": 5.6961283683776855, "learning_rate": 9.986498191717659e-06, "loss": 0.6233, "step": 101830 }, { "epoch": 0.6053581087908887, "grad_norm": 7.0968146324157715, "learning_rate": 9.986482949205316e-06, "loss": 0.652, "step": 101840 }, { "epoch": 0.6054175508675571, "grad_norm": 6.258886337280273, "learning_rate": 9.986467698105652e-06, "loss": 0.6277, "step": 101850 }, { "epoch": 0.6054769929442255, "grad_norm": 5.185266971588135, "learning_rate": 9.986452438418697e-06, "loss": 0.6747, "step": 101860 }, { "epoch": 0.6055364350208939, "grad_norm": 5.643945217132568, "learning_rate": 9.986437170144476e-06, "loss": 0.6549, "step": 101870 }, { "epoch": 0.6055958770975622, "grad_norm": 5.218884468078613, "learning_rate": 9.986421893283015e-06, "loss": 0.5848, "step": 101880 }, { "epoch": 0.6056553191742307, "grad_norm": 4.246869087219238, "learning_rate": 9.98640660783434e-06, "loss": 0.6212, "step": 101890 }, { "epoch": 0.6057147612508991, "grad_norm": 5.294912338256836, "learning_rate": 9.98639131379848e-06, "loss": 0.5823, "step": 101900 }, { "epoch": 0.6057742033275675, "grad_norm": 6.077358722686768, "learning_rate": 9.986376011175459e-06, "loss": 0.626, "step": 101910 }, { "epoch": 0.6058336454042358, "grad_norm": 5.714359760284424, "learning_rate": 9.9863606999653e-06, "loss": 0.5925, "step": 101920 }, { "epoch": 0.6058930874809042, "grad_norm": 5.064691543579102, "learning_rate": 9.986345380168037e-06, "loss": 0.6283, "step": 101930 }, { "epoch": 0.6059525295575726, "grad_norm": 6.344997406005859, "learning_rate": 9.98633005178369e-06, "loss": 0.6997, "step": 101940 }, { "epoch": 0.606011971634241, "grad_norm": 6.205801010131836, "learning_rate": 9.986314714812288e-06, "loss": 0.5885, "step": 101950 }, { "epoch": 0.6060714137109094, "grad_norm": 6.055455684661865, "learning_rate": 9.986299369253856e-06, "loss": 0.6102, "step": 101960 }, { "epoch": 0.6061308557875777, "grad_norm": 6.796172618865967, "learning_rate": 9.986284015108422e-06, "loss": 0.6868, "step": 101970 }, { "epoch": 0.6061902978642462, "grad_norm": 5.328732013702393, "learning_rate": 9.986268652376015e-06, "loss": 0.6384, "step": 101980 }, { "epoch": 0.6062497399409146, "grad_norm": 4.917402744293213, "learning_rate": 9.986253281056654e-06, "loss": 0.6126, "step": 101990 }, { "epoch": 0.606309182017583, "grad_norm": 4.676713466644287, "learning_rate": 9.986237901150372e-06, "loss": 0.5675, "step": 102000 }, { "epoch": 0.6063686240942514, "grad_norm": 7.401403427124023, "learning_rate": 9.986222512657194e-06, "loss": 0.6058, "step": 102010 }, { "epoch": 0.6064280661709197, "grad_norm": 4.267059326171875, "learning_rate": 9.986207115577146e-06, "loss": 0.6506, "step": 102020 }, { "epoch": 0.6064875082475881, "grad_norm": 5.509174346923828, "learning_rate": 9.986191709910253e-06, "loss": 0.6053, "step": 102030 }, { "epoch": 0.6065469503242565, "grad_norm": 5.620136737823486, "learning_rate": 9.986176295656544e-06, "loss": 0.6562, "step": 102040 }, { "epoch": 0.606606392400925, "grad_norm": 5.41069221496582, "learning_rate": 9.986160872816044e-06, "loss": 0.6371, "step": 102050 }, { "epoch": 0.6066658344775933, "grad_norm": 5.52559757232666, "learning_rate": 9.98614544138878e-06, "loss": 0.6261, "step": 102060 }, { "epoch": 0.6067252765542617, "grad_norm": 6.1239752769470215, "learning_rate": 9.986130001374778e-06, "loss": 0.6091, "step": 102070 }, { "epoch": 0.6067847186309301, "grad_norm": 6.367615222930908, "learning_rate": 9.986114552774066e-06, "loss": 0.6581, "step": 102080 }, { "epoch": 0.6068441607075985, "grad_norm": 5.470183849334717, "learning_rate": 9.986099095586672e-06, "loss": 0.6019, "step": 102090 }, { "epoch": 0.6069036027842669, "grad_norm": 5.759047985076904, "learning_rate": 9.986083629812618e-06, "loss": 0.5969, "step": 102100 }, { "epoch": 0.6069630448609352, "grad_norm": 4.876461982727051, "learning_rate": 9.986068155451932e-06, "loss": 0.5753, "step": 102110 }, { "epoch": 0.6070224869376036, "grad_norm": 6.812601089477539, "learning_rate": 9.986052672504644e-06, "loss": 0.6229, "step": 102120 }, { "epoch": 0.607081929014272, "grad_norm": 5.236188888549805, "learning_rate": 9.986037180970776e-06, "loss": 0.585, "step": 102130 }, { "epoch": 0.6071413710909405, "grad_norm": 5.5610809326171875, "learning_rate": 9.98602168085036e-06, "loss": 0.5656, "step": 102140 }, { "epoch": 0.6072008131676089, "grad_norm": 5.595671653747559, "learning_rate": 9.986006172143418e-06, "loss": 0.6043, "step": 102150 }, { "epoch": 0.6072602552442772, "grad_norm": 3.899214744567871, "learning_rate": 9.985990654849977e-06, "loss": 0.5583, "step": 102160 }, { "epoch": 0.6073196973209456, "grad_norm": 4.994856834411621, "learning_rate": 9.985975128970067e-06, "loss": 0.5698, "step": 102170 }, { "epoch": 0.607379139397614, "grad_norm": 5.896746635437012, "learning_rate": 9.985959594503713e-06, "loss": 0.6388, "step": 102180 }, { "epoch": 0.6074385814742824, "grad_norm": 6.27500057220459, "learning_rate": 9.985944051450942e-06, "loss": 0.6463, "step": 102190 }, { "epoch": 0.6074980235509507, "grad_norm": 5.689280033111572, "learning_rate": 9.985928499811779e-06, "loss": 0.6485, "step": 102200 }, { "epoch": 0.6075574656276191, "grad_norm": 4.605701923370361, "learning_rate": 9.985912939586254e-06, "loss": 0.5891, "step": 102210 }, { "epoch": 0.6076169077042876, "grad_norm": 5.71912956237793, "learning_rate": 9.98589737077439e-06, "loss": 0.5683, "step": 102220 }, { "epoch": 0.607676349780956, "grad_norm": 7.030201435089111, "learning_rate": 9.985881793376217e-06, "loss": 0.6415, "step": 102230 }, { "epoch": 0.6077357918576244, "grad_norm": 6.709014892578125, "learning_rate": 9.98586620739176e-06, "loss": 0.6271, "step": 102240 }, { "epoch": 0.6077952339342927, "grad_norm": 5.982733726501465, "learning_rate": 9.985850612821048e-06, "loss": 0.6396, "step": 102250 }, { "epoch": 0.6078546760109611, "grad_norm": 6.652006149291992, "learning_rate": 9.985835009664105e-06, "loss": 0.6312, "step": 102260 }, { "epoch": 0.6079141180876295, "grad_norm": 5.297867298126221, "learning_rate": 9.98581939792096e-06, "loss": 0.5975, "step": 102270 }, { "epoch": 0.6079735601642979, "grad_norm": 8.02967357635498, "learning_rate": 9.985803777591638e-06, "loss": 0.6849, "step": 102280 }, { "epoch": 0.6080330022409662, "grad_norm": 7.542800426483154, "learning_rate": 9.985788148676167e-06, "loss": 0.6398, "step": 102290 }, { "epoch": 0.6080924443176347, "grad_norm": 5.612089157104492, "learning_rate": 9.985772511174575e-06, "loss": 0.6936, "step": 102300 }, { "epoch": 0.6081518863943031, "grad_norm": 9.385994911193848, "learning_rate": 9.985756865086889e-06, "loss": 0.6673, "step": 102310 }, { "epoch": 0.6082113284709715, "grad_norm": 5.953537940979004, "learning_rate": 9.985741210413132e-06, "loss": 0.6059, "step": 102320 }, { "epoch": 0.6082707705476399, "grad_norm": 5.731365203857422, "learning_rate": 9.985725547153336e-06, "loss": 0.5995, "step": 102330 }, { "epoch": 0.6083302126243082, "grad_norm": 7.155888557434082, "learning_rate": 9.985709875307523e-06, "loss": 0.6702, "step": 102340 }, { "epoch": 0.6083896547009766, "grad_norm": 7.645044803619385, "learning_rate": 9.985694194875725e-06, "loss": 0.6383, "step": 102350 }, { "epoch": 0.608449096777645, "grad_norm": 5.528262615203857, "learning_rate": 9.985678505857966e-06, "loss": 0.5964, "step": 102360 }, { "epoch": 0.6085085388543134, "grad_norm": 5.831299781799316, "learning_rate": 9.985662808254272e-06, "loss": 0.5656, "step": 102370 }, { "epoch": 0.6085679809309819, "grad_norm": 5.360072612762451, "learning_rate": 9.985647102064675e-06, "loss": 0.5881, "step": 102380 }, { "epoch": 0.6086274230076502, "grad_norm": 7.054256916046143, "learning_rate": 9.985631387289198e-06, "loss": 0.6768, "step": 102390 }, { "epoch": 0.6086868650843186, "grad_norm": 5.233694076538086, "learning_rate": 9.985615663927867e-06, "loss": 0.5897, "step": 102400 }, { "epoch": 0.608746307160987, "grad_norm": 5.9073872566223145, "learning_rate": 9.985599931980713e-06, "loss": 0.6269, "step": 102410 }, { "epoch": 0.6088057492376554, "grad_norm": 5.8952131271362305, "learning_rate": 9.98558419144776e-06, "loss": 0.6468, "step": 102420 }, { "epoch": 0.6088651913143237, "grad_norm": 5.296147346496582, "learning_rate": 9.985568442329037e-06, "loss": 0.6088, "step": 102430 }, { "epoch": 0.6089246333909921, "grad_norm": 5.101701259613037, "learning_rate": 9.98555268462457e-06, "loss": 0.6333, "step": 102440 }, { "epoch": 0.6089840754676605, "grad_norm": 5.228238105773926, "learning_rate": 9.985536918334385e-06, "loss": 0.5946, "step": 102450 }, { "epoch": 0.609043517544329, "grad_norm": 5.791334629058838, "learning_rate": 9.985521143458511e-06, "loss": 0.6221, "step": 102460 }, { "epoch": 0.6091029596209974, "grad_norm": 5.155012130737305, "learning_rate": 9.985505359996976e-06, "loss": 0.5504, "step": 102470 }, { "epoch": 0.6091624016976657, "grad_norm": 5.754598617553711, "learning_rate": 9.985489567949805e-06, "loss": 0.6653, "step": 102480 }, { "epoch": 0.6092218437743341, "grad_norm": 5.905770778656006, "learning_rate": 9.985473767317027e-06, "loss": 0.5941, "step": 102490 }, { "epoch": 0.6092812858510025, "grad_norm": 5.882931232452393, "learning_rate": 9.985457958098667e-06, "loss": 0.6355, "step": 102500 }, { "epoch": 0.6093407279276709, "grad_norm": 6.715810775756836, "learning_rate": 9.985442140294754e-06, "loss": 0.6782, "step": 102510 }, { "epoch": 0.6094001700043393, "grad_norm": 6.871814727783203, "learning_rate": 9.985426313905315e-06, "loss": 0.6228, "step": 102520 }, { "epoch": 0.6094596120810076, "grad_norm": 5.278127670288086, "learning_rate": 9.985410478930377e-06, "loss": 0.6569, "step": 102530 }, { "epoch": 0.609519054157676, "grad_norm": 5.835147380828857, "learning_rate": 9.985394635369969e-06, "loss": 0.593, "step": 102540 }, { "epoch": 0.6095784962343445, "grad_norm": 7.328494071960449, "learning_rate": 9.985378783224113e-06, "loss": 0.6122, "step": 102550 }, { "epoch": 0.6096379383110129, "grad_norm": 4.7045159339904785, "learning_rate": 9.985362922492843e-06, "loss": 0.6238, "step": 102560 }, { "epoch": 0.6096973803876812, "grad_norm": 4.794034481048584, "learning_rate": 9.985347053176182e-06, "loss": 0.5702, "step": 102570 }, { "epoch": 0.6097568224643496, "grad_norm": 4.765240669250488, "learning_rate": 9.985331175274158e-06, "loss": 0.6265, "step": 102580 }, { "epoch": 0.609816264541018, "grad_norm": 5.736549377441406, "learning_rate": 9.9853152887868e-06, "loss": 0.619, "step": 102590 }, { "epoch": 0.6098757066176864, "grad_norm": 6.285592555999756, "learning_rate": 9.985299393714134e-06, "loss": 0.6373, "step": 102600 }, { "epoch": 0.6099351486943548, "grad_norm": 6.273279190063477, "learning_rate": 9.985283490056186e-06, "loss": 0.7127, "step": 102610 }, { "epoch": 0.6099945907710231, "grad_norm": 5.608137130737305, "learning_rate": 9.985267577812987e-06, "loss": 0.6818, "step": 102620 }, { "epoch": 0.6100540328476916, "grad_norm": 4.344483375549316, "learning_rate": 9.985251656984561e-06, "loss": 0.6386, "step": 102630 }, { "epoch": 0.61011347492436, "grad_norm": 5.924511909484863, "learning_rate": 9.985235727570939e-06, "loss": 0.6208, "step": 102640 }, { "epoch": 0.6101729170010284, "grad_norm": 4.787839889526367, "learning_rate": 9.985219789572144e-06, "loss": 0.6732, "step": 102650 }, { "epoch": 0.6102323590776967, "grad_norm": 5.130187511444092, "learning_rate": 9.985203842988208e-06, "loss": 0.5585, "step": 102660 }, { "epoch": 0.6102918011543651, "grad_norm": 6.681412696838379, "learning_rate": 9.985187887819152e-06, "loss": 0.6016, "step": 102670 }, { "epoch": 0.6103512432310335, "grad_norm": 4.881252765655518, "learning_rate": 9.985171924065011e-06, "loss": 0.6086, "step": 102680 }, { "epoch": 0.6104106853077019, "grad_norm": 5.088699817657471, "learning_rate": 9.985155951725809e-06, "loss": 0.5892, "step": 102690 }, { "epoch": 0.6104701273843703, "grad_norm": 6.9531331062316895, "learning_rate": 9.985139970801571e-06, "loss": 0.6192, "step": 102700 }, { "epoch": 0.6105295694610386, "grad_norm": 6.799391746520996, "learning_rate": 9.985123981292331e-06, "loss": 0.626, "step": 102710 }, { "epoch": 0.6105890115377071, "grad_norm": 4.302150726318359, "learning_rate": 9.98510798319811e-06, "loss": 0.6291, "step": 102720 }, { "epoch": 0.6106484536143755, "grad_norm": 6.323037147521973, "learning_rate": 9.985091976518939e-06, "loss": 0.6806, "step": 102730 }, { "epoch": 0.6107078956910439, "grad_norm": 5.713170528411865, "learning_rate": 9.985075961254846e-06, "loss": 0.602, "step": 102740 }, { "epoch": 0.6107673377677123, "grad_norm": 7.045531272888184, "learning_rate": 9.985059937405855e-06, "loss": 0.591, "step": 102750 }, { "epoch": 0.6108267798443806, "grad_norm": 4.654245853424072, "learning_rate": 9.985043904971998e-06, "loss": 0.6281, "step": 102760 }, { "epoch": 0.610886221921049, "grad_norm": 5.142643928527832, "learning_rate": 9.9850278639533e-06, "loss": 0.5041, "step": 102770 }, { "epoch": 0.6109456639977174, "grad_norm": 6.041194438934326, "learning_rate": 9.985011814349788e-06, "loss": 0.622, "step": 102780 }, { "epoch": 0.6110051060743859, "grad_norm": 8.07946491241455, "learning_rate": 9.984995756161492e-06, "loss": 0.6368, "step": 102790 }, { "epoch": 0.6110645481510542, "grad_norm": 6.126634120941162, "learning_rate": 9.98497968938844e-06, "loss": 0.6561, "step": 102800 }, { "epoch": 0.6111239902277226, "grad_norm": 4.478740215301514, "learning_rate": 9.984963614030655e-06, "loss": 0.5899, "step": 102810 }, { "epoch": 0.611183432304391, "grad_norm": 6.231561660766602, "learning_rate": 9.984947530088169e-06, "loss": 0.608, "step": 102820 }, { "epoch": 0.6112428743810594, "grad_norm": 4.54019021987915, "learning_rate": 9.98493143756101e-06, "loss": 0.5808, "step": 102830 }, { "epoch": 0.6113023164577278, "grad_norm": 6.732424736022949, "learning_rate": 9.984915336449204e-06, "loss": 0.6641, "step": 102840 }, { "epoch": 0.6113617585343961, "grad_norm": 8.07730770111084, "learning_rate": 9.984899226752777e-06, "loss": 0.6144, "step": 102850 }, { "epoch": 0.6114212006110645, "grad_norm": 5.961628437042236, "learning_rate": 9.984883108471761e-06, "loss": 0.6781, "step": 102860 }, { "epoch": 0.611480642687733, "grad_norm": 6.192864418029785, "learning_rate": 9.984866981606181e-06, "loss": 0.5981, "step": 102870 }, { "epoch": 0.6115400847644014, "grad_norm": 5.534070014953613, "learning_rate": 9.984850846156065e-06, "loss": 0.647, "step": 102880 }, { "epoch": 0.6115995268410698, "grad_norm": 7.369373321533203, "learning_rate": 9.98483470212144e-06, "loss": 0.637, "step": 102890 }, { "epoch": 0.6116589689177381, "grad_norm": 7.052985668182373, "learning_rate": 9.984818549502335e-06, "loss": 0.6486, "step": 102900 }, { "epoch": 0.6117184109944065, "grad_norm": 7.288912773132324, "learning_rate": 9.984802388298778e-06, "loss": 0.6053, "step": 102910 }, { "epoch": 0.6117778530710749, "grad_norm": 5.7805609703063965, "learning_rate": 9.984786218510798e-06, "loss": 0.6278, "step": 102920 }, { "epoch": 0.6118372951477433, "grad_norm": 4.872736930847168, "learning_rate": 9.98477004013842e-06, "loss": 0.6343, "step": 102930 }, { "epoch": 0.6118967372244116, "grad_norm": 6.1627960205078125, "learning_rate": 9.984753853181674e-06, "loss": 0.5797, "step": 102940 }, { "epoch": 0.61195617930108, "grad_norm": 5.646349906921387, "learning_rate": 9.984737657640586e-06, "loss": 0.6551, "step": 102950 }, { "epoch": 0.6120156213777485, "grad_norm": 6.207452774047852, "learning_rate": 9.984721453515184e-06, "loss": 0.663, "step": 102960 }, { "epoch": 0.6120750634544169, "grad_norm": 6.7002387046813965, "learning_rate": 9.9847052408055e-06, "loss": 0.6571, "step": 102970 }, { "epoch": 0.6121345055310853, "grad_norm": 4.95011568069458, "learning_rate": 9.984689019511557e-06, "loss": 0.6347, "step": 102980 }, { "epoch": 0.6121939476077536, "grad_norm": 5.764283657073975, "learning_rate": 9.984672789633385e-06, "loss": 0.644, "step": 102990 }, { "epoch": 0.612253389684422, "grad_norm": 6.486791610717773, "learning_rate": 9.984656551171012e-06, "loss": 0.6095, "step": 103000 }, { "epoch": 0.6123128317610904, "grad_norm": 6.278594493865967, "learning_rate": 9.984640304124464e-06, "loss": 0.6355, "step": 103010 }, { "epoch": 0.6123722738377588, "grad_norm": 5.509466648101807, "learning_rate": 9.984624048493773e-06, "loss": 0.5991, "step": 103020 }, { "epoch": 0.6124317159144271, "grad_norm": 5.176985263824463, "learning_rate": 9.984607784278963e-06, "loss": 0.644, "step": 103030 }, { "epoch": 0.6124911579910955, "grad_norm": 7.429661750793457, "learning_rate": 9.984591511480066e-06, "loss": 0.651, "step": 103040 }, { "epoch": 0.612550600067764, "grad_norm": 7.250710487365723, "learning_rate": 9.984575230097104e-06, "loss": 0.6249, "step": 103050 }, { "epoch": 0.6126100421444324, "grad_norm": 5.545299530029297, "learning_rate": 9.98455894013011e-06, "loss": 0.6302, "step": 103060 }, { "epoch": 0.6126694842211008, "grad_norm": 6.7516913414001465, "learning_rate": 9.984542641579113e-06, "loss": 0.6466, "step": 103070 }, { "epoch": 0.6127289262977691, "grad_norm": 8.679277420043945, "learning_rate": 9.984526334444137e-06, "loss": 0.6588, "step": 103080 }, { "epoch": 0.6127883683744375, "grad_norm": 5.261463642120361, "learning_rate": 9.984510018725213e-06, "loss": 0.6899, "step": 103090 }, { "epoch": 0.6128478104511059, "grad_norm": 5.07248067855835, "learning_rate": 9.984493694422365e-06, "loss": 0.6172, "step": 103100 }, { "epoch": 0.6129072525277743, "grad_norm": 5.476681232452393, "learning_rate": 9.984477361535627e-06, "loss": 0.6548, "step": 103110 }, { "epoch": 0.6129666946044428, "grad_norm": 6.12742280960083, "learning_rate": 9.984461020065024e-06, "loss": 0.6243, "step": 103120 }, { "epoch": 0.6130261366811111, "grad_norm": 5.612421989440918, "learning_rate": 9.984444670010584e-06, "loss": 0.5925, "step": 103130 }, { "epoch": 0.6130855787577795, "grad_norm": 6.025481224060059, "learning_rate": 9.984428311372336e-06, "loss": 0.6212, "step": 103140 }, { "epoch": 0.6131450208344479, "grad_norm": 5.881380558013916, "learning_rate": 9.984411944150307e-06, "loss": 0.6578, "step": 103150 }, { "epoch": 0.6132044629111163, "grad_norm": 4.8278422355651855, "learning_rate": 9.984395568344525e-06, "loss": 0.6872, "step": 103160 }, { "epoch": 0.6132639049877846, "grad_norm": 6.076930522918701, "learning_rate": 9.98437918395502e-06, "loss": 0.6542, "step": 103170 }, { "epoch": 0.613323347064453, "grad_norm": 6.3418755531311035, "learning_rate": 9.984362790981821e-06, "loss": 0.572, "step": 103180 }, { "epoch": 0.6133827891411214, "grad_norm": 6.825544357299805, "learning_rate": 9.984346389424952e-06, "loss": 0.6211, "step": 103190 }, { "epoch": 0.6134422312177898, "grad_norm": 5.444540023803711, "learning_rate": 9.984329979284445e-06, "loss": 0.6131, "step": 103200 }, { "epoch": 0.6135016732944583, "grad_norm": 5.736475944519043, "learning_rate": 9.984313560560327e-06, "loss": 0.7159, "step": 103210 }, { "epoch": 0.6135611153711266, "grad_norm": 5.379498481750488, "learning_rate": 9.984297133252627e-06, "loss": 0.6026, "step": 103220 }, { "epoch": 0.613620557447795, "grad_norm": 6.272295951843262, "learning_rate": 9.98428069736137e-06, "loss": 0.6252, "step": 103230 }, { "epoch": 0.6136799995244634, "grad_norm": 6.18802547454834, "learning_rate": 9.98426425288659e-06, "loss": 0.5907, "step": 103240 }, { "epoch": 0.6137394416011318, "grad_norm": 4.43536901473999, "learning_rate": 9.984247799828311e-06, "loss": 0.5319, "step": 103250 }, { "epoch": 0.6137988836778002, "grad_norm": 6.871216297149658, "learning_rate": 9.984231338186562e-06, "loss": 0.6088, "step": 103260 }, { "epoch": 0.6138583257544685, "grad_norm": 6.039707183837891, "learning_rate": 9.984214867961373e-06, "loss": 0.6453, "step": 103270 }, { "epoch": 0.6139177678311369, "grad_norm": 7.26181697845459, "learning_rate": 9.98419838915277e-06, "loss": 0.6218, "step": 103280 }, { "epoch": 0.6139772099078054, "grad_norm": 4.656338691711426, "learning_rate": 9.984181901760782e-06, "loss": 0.6351, "step": 103290 }, { "epoch": 0.6140366519844738, "grad_norm": 5.999635219573975, "learning_rate": 9.984165405785442e-06, "loss": 0.5686, "step": 103300 }, { "epoch": 0.6140960940611421, "grad_norm": 5.572809219360352, "learning_rate": 9.984148901226772e-06, "loss": 0.6651, "step": 103310 }, { "epoch": 0.6141555361378105, "grad_norm": 6.152799606323242, "learning_rate": 9.984132388084802e-06, "loss": 0.6727, "step": 103320 }, { "epoch": 0.6142149782144789, "grad_norm": 5.923182964324951, "learning_rate": 9.984115866359563e-06, "loss": 0.5724, "step": 103330 }, { "epoch": 0.6142744202911473, "grad_norm": 5.463747501373291, "learning_rate": 9.984099336051081e-06, "loss": 0.6211, "step": 103340 }, { "epoch": 0.6143338623678157, "grad_norm": 5.499240398406982, "learning_rate": 9.984082797159385e-06, "loss": 0.657, "step": 103350 }, { "epoch": 0.614393304444484, "grad_norm": 5.195369243621826, "learning_rate": 9.984066249684503e-06, "loss": 0.6152, "step": 103360 }, { "epoch": 0.6144527465211524, "grad_norm": 4.552777290344238, "learning_rate": 9.984049693626465e-06, "loss": 0.6079, "step": 103370 }, { "epoch": 0.6145121885978209, "grad_norm": 7.276620864868164, "learning_rate": 9.9840331289853e-06, "loss": 0.6147, "step": 103380 }, { "epoch": 0.6145716306744893, "grad_norm": 5.552495002746582, "learning_rate": 9.984016555761034e-06, "loss": 0.5977, "step": 103390 }, { "epoch": 0.6146310727511576, "grad_norm": 6.484208106994629, "learning_rate": 9.983999973953698e-06, "loss": 0.584, "step": 103400 }, { "epoch": 0.614690514827826, "grad_norm": 5.977903366088867, "learning_rate": 9.983983383563317e-06, "loss": 0.6325, "step": 103410 }, { "epoch": 0.6147499569044944, "grad_norm": 6.619582176208496, "learning_rate": 9.983966784589924e-06, "loss": 0.6099, "step": 103420 }, { "epoch": 0.6148093989811628, "grad_norm": 4.737175941467285, "learning_rate": 9.983950177033545e-06, "loss": 0.6626, "step": 103430 }, { "epoch": 0.6148688410578312, "grad_norm": 6.109138488769531, "learning_rate": 9.983933560894208e-06, "loss": 0.6636, "step": 103440 }, { "epoch": 0.6149282831344995, "grad_norm": 5.0217695236206055, "learning_rate": 9.983916936171945e-06, "loss": 0.6294, "step": 103450 }, { "epoch": 0.614987725211168, "grad_norm": 5.94701623916626, "learning_rate": 9.98390030286678e-06, "loss": 0.6469, "step": 103460 }, { "epoch": 0.6150471672878364, "grad_norm": 6.54905366897583, "learning_rate": 9.983883660978746e-06, "loss": 0.7086, "step": 103470 }, { "epoch": 0.6151066093645048, "grad_norm": 5.01705265045166, "learning_rate": 9.983867010507868e-06, "loss": 0.5615, "step": 103480 }, { "epoch": 0.6151660514411732, "grad_norm": 4.6856889724731445, "learning_rate": 9.983850351454176e-06, "loss": 0.5775, "step": 103490 }, { "epoch": 0.6152254935178415, "grad_norm": 4.900535583496094, "learning_rate": 9.9838336838177e-06, "loss": 0.5851, "step": 103500 }, { "epoch": 0.6152849355945099, "grad_norm": 5.207355976104736, "learning_rate": 9.983817007598469e-06, "loss": 0.5914, "step": 103510 }, { "epoch": 0.6153443776711783, "grad_norm": 6.714083671569824, "learning_rate": 9.983800322796508e-06, "loss": 0.6235, "step": 103520 }, { "epoch": 0.6154038197478467, "grad_norm": 7.326455593109131, "learning_rate": 9.983783629411851e-06, "loss": 0.6378, "step": 103530 }, { "epoch": 0.615463261824515, "grad_norm": 6.048735618591309, "learning_rate": 9.983766927444522e-06, "loss": 0.5854, "step": 103540 }, { "epoch": 0.6155227039011835, "grad_norm": 5.628660202026367, "learning_rate": 9.983750216894552e-06, "loss": 0.6501, "step": 103550 }, { "epoch": 0.6155821459778519, "grad_norm": 6.195587635040283, "learning_rate": 9.983733497761968e-06, "loss": 0.6987, "step": 103560 }, { "epoch": 0.6156415880545203, "grad_norm": 6.985151767730713, "learning_rate": 9.983716770046803e-06, "loss": 0.6582, "step": 103570 }, { "epoch": 0.6157010301311887, "grad_norm": 6.502877235412598, "learning_rate": 9.983700033749081e-06, "loss": 0.6954, "step": 103580 }, { "epoch": 0.615760472207857, "grad_norm": 5.881327152252197, "learning_rate": 9.983683288868836e-06, "loss": 0.6265, "step": 103590 }, { "epoch": 0.6158199142845254, "grad_norm": 5.02777624130249, "learning_rate": 9.983666535406091e-06, "loss": 0.6253, "step": 103600 }, { "epoch": 0.6158793563611938, "grad_norm": 5.770804405212402, "learning_rate": 9.983649773360877e-06, "loss": 0.6002, "step": 103610 }, { "epoch": 0.6159387984378623, "grad_norm": 6.217721939086914, "learning_rate": 9.983633002733227e-06, "loss": 0.6012, "step": 103620 }, { "epoch": 0.6159982405145307, "grad_norm": 4.656691551208496, "learning_rate": 9.983616223523163e-06, "loss": 0.6856, "step": 103630 }, { "epoch": 0.616057682591199, "grad_norm": 5.209225177764893, "learning_rate": 9.983599435730717e-06, "loss": 0.6902, "step": 103640 }, { "epoch": 0.6161171246678674, "grad_norm": 5.62375020980835, "learning_rate": 9.98358263935592e-06, "loss": 0.588, "step": 103650 }, { "epoch": 0.6161765667445358, "grad_norm": 5.285583019256592, "learning_rate": 9.983565834398798e-06, "loss": 0.5828, "step": 103660 }, { "epoch": 0.6162360088212042, "grad_norm": 5.20048189163208, "learning_rate": 9.983549020859382e-06, "loss": 0.6034, "step": 103670 }, { "epoch": 0.6162954508978725, "grad_norm": 7.317502975463867, "learning_rate": 9.983532198737698e-06, "loss": 0.6083, "step": 103680 }, { "epoch": 0.6163548929745409, "grad_norm": 6.689414978027344, "learning_rate": 9.983515368033779e-06, "loss": 0.6174, "step": 103690 }, { "epoch": 0.6164143350512093, "grad_norm": 4.424289703369141, "learning_rate": 9.983498528747652e-06, "loss": 0.5797, "step": 103700 }, { "epoch": 0.6164737771278778, "grad_norm": 7.357278823852539, "learning_rate": 9.983481680879344e-06, "loss": 0.6813, "step": 103710 }, { "epoch": 0.6165332192045462, "grad_norm": 7.070124626159668, "learning_rate": 9.983464824428887e-06, "loss": 0.6456, "step": 103720 }, { "epoch": 0.6165926612812145, "grad_norm": 6.707645893096924, "learning_rate": 9.98344795939631e-06, "loss": 0.6226, "step": 103730 }, { "epoch": 0.6166521033578829, "grad_norm": 4.952690124511719, "learning_rate": 9.983431085781639e-06, "loss": 0.5973, "step": 103740 }, { "epoch": 0.6167115454345513, "grad_norm": 7.062809467315674, "learning_rate": 9.983414203584908e-06, "loss": 0.6466, "step": 103750 }, { "epoch": 0.6167709875112197, "grad_norm": 5.207234859466553, "learning_rate": 9.98339731280614e-06, "loss": 0.6408, "step": 103760 }, { "epoch": 0.616830429587888, "grad_norm": 4.8332343101501465, "learning_rate": 9.983380413445367e-06, "loss": 0.5822, "step": 103770 }, { "epoch": 0.6168898716645564, "grad_norm": 6.677162170410156, "learning_rate": 9.983363505502621e-06, "loss": 0.6318, "step": 103780 }, { "epoch": 0.6169493137412249, "grad_norm": 4.143420219421387, "learning_rate": 9.983346588977926e-06, "loss": 0.6179, "step": 103790 }, { "epoch": 0.6170087558178933, "grad_norm": 5.2744460105896, "learning_rate": 9.983329663871314e-06, "loss": 0.6489, "step": 103800 }, { "epoch": 0.6170681978945617, "grad_norm": 6.036886215209961, "learning_rate": 9.983312730182815e-06, "loss": 0.6248, "step": 103810 }, { "epoch": 0.61712763997123, "grad_norm": 5.17777681350708, "learning_rate": 9.983295787912458e-06, "loss": 0.6282, "step": 103820 }, { "epoch": 0.6171870820478984, "grad_norm": 6.048397064208984, "learning_rate": 9.983278837060269e-06, "loss": 0.59, "step": 103830 }, { "epoch": 0.6172465241245668, "grad_norm": 6.354878902435303, "learning_rate": 9.98326187762628e-06, "loss": 0.6103, "step": 103840 }, { "epoch": 0.6173059662012352, "grad_norm": 6.676244735717773, "learning_rate": 9.983244909610518e-06, "loss": 0.5967, "step": 103850 }, { "epoch": 0.6173654082779036, "grad_norm": 5.740631580352783, "learning_rate": 9.983227933013014e-06, "loss": 0.5895, "step": 103860 }, { "epoch": 0.617424850354572, "grad_norm": 6.723110198974609, "learning_rate": 9.983210947833798e-06, "loss": 0.6433, "step": 103870 }, { "epoch": 0.6174842924312404, "grad_norm": 5.885701656341553, "learning_rate": 9.983193954072898e-06, "loss": 0.617, "step": 103880 }, { "epoch": 0.6175437345079088, "grad_norm": 6.3382344245910645, "learning_rate": 9.983176951730343e-06, "loss": 0.6513, "step": 103890 }, { "epoch": 0.6176031765845772, "grad_norm": 5.083317756652832, "learning_rate": 9.983159940806163e-06, "loss": 0.6423, "step": 103900 }, { "epoch": 0.6176626186612455, "grad_norm": 5.38686990737915, "learning_rate": 9.983142921300387e-06, "loss": 0.6032, "step": 103910 }, { "epoch": 0.6177220607379139, "grad_norm": 6.470499515533447, "learning_rate": 9.983125893213044e-06, "loss": 0.6256, "step": 103920 }, { "epoch": 0.6177815028145823, "grad_norm": 5.437058925628662, "learning_rate": 9.983108856544163e-06, "loss": 0.6976, "step": 103930 }, { "epoch": 0.6178409448912507, "grad_norm": 6.119895935058594, "learning_rate": 9.983091811293776e-06, "loss": 0.6246, "step": 103940 }, { "epoch": 0.6179003869679192, "grad_norm": 5.330191135406494, "learning_rate": 9.98307475746191e-06, "loss": 0.6196, "step": 103950 }, { "epoch": 0.6179598290445875, "grad_norm": 6.766231536865234, "learning_rate": 9.983057695048592e-06, "loss": 0.6568, "step": 103960 }, { "epoch": 0.6180192711212559, "grad_norm": 7.570234775543213, "learning_rate": 9.983040624053857e-06, "loss": 0.6097, "step": 103970 }, { "epoch": 0.6180787131979243, "grad_norm": 5.192192554473877, "learning_rate": 9.98302354447773e-06, "loss": 0.6205, "step": 103980 }, { "epoch": 0.6181381552745927, "grad_norm": 7.011606693267822, "learning_rate": 9.983006456320244e-06, "loss": 0.6297, "step": 103990 }, { "epoch": 0.6181975973512611, "grad_norm": 5.691694259643555, "learning_rate": 9.982989359581423e-06, "loss": 0.6537, "step": 104000 }, { "epoch": 0.6182570394279294, "grad_norm": 4.301705360412598, "learning_rate": 9.982972254261302e-06, "loss": 0.5902, "step": 104010 }, { "epoch": 0.6183164815045978, "grad_norm": 8.315963745117188, "learning_rate": 9.982955140359906e-06, "loss": 0.6405, "step": 104020 }, { "epoch": 0.6183759235812663, "grad_norm": 6.022561550140381, "learning_rate": 9.98293801787727e-06, "loss": 0.706, "step": 104030 }, { "epoch": 0.6184353656579347, "grad_norm": 6.313185691833496, "learning_rate": 9.982920886813418e-06, "loss": 0.6244, "step": 104040 }, { "epoch": 0.618494807734603, "grad_norm": 7.713545799255371, "learning_rate": 9.982903747168382e-06, "loss": 0.6336, "step": 104050 }, { "epoch": 0.6185542498112714, "grad_norm": 5.583432197570801, "learning_rate": 9.982886598942192e-06, "loss": 0.6382, "step": 104060 }, { "epoch": 0.6186136918879398, "grad_norm": 5.48049783706665, "learning_rate": 9.982869442134875e-06, "loss": 0.5888, "step": 104070 }, { "epoch": 0.6186731339646082, "grad_norm": 7.6374359130859375, "learning_rate": 9.982852276746465e-06, "loss": 0.6809, "step": 104080 }, { "epoch": 0.6187325760412766, "grad_norm": 7.259922027587891, "learning_rate": 9.982835102776987e-06, "loss": 0.6334, "step": 104090 }, { "epoch": 0.6187920181179449, "grad_norm": 5.677525043487549, "learning_rate": 9.982817920226472e-06, "loss": 0.6502, "step": 104100 }, { "epoch": 0.6188514601946133, "grad_norm": 6.779747009277344, "learning_rate": 9.98280072909495e-06, "loss": 0.6103, "step": 104110 }, { "epoch": 0.6189109022712818, "grad_norm": 5.927526950836182, "learning_rate": 9.982783529382452e-06, "loss": 0.6095, "step": 104120 }, { "epoch": 0.6189703443479502, "grad_norm": 5.246748924255371, "learning_rate": 9.982766321089005e-06, "loss": 0.6235, "step": 104130 }, { "epoch": 0.6190297864246185, "grad_norm": 7.437148571014404, "learning_rate": 9.98274910421464e-06, "loss": 0.6017, "step": 104140 }, { "epoch": 0.6190892285012869, "grad_norm": 5.881190299987793, "learning_rate": 9.982731878759386e-06, "loss": 0.6878, "step": 104150 }, { "epoch": 0.6191486705779553, "grad_norm": 6.983330249786377, "learning_rate": 9.982714644723275e-06, "loss": 0.6373, "step": 104160 }, { "epoch": 0.6192081126546237, "grad_norm": 5.954294204711914, "learning_rate": 9.982697402106334e-06, "loss": 0.61, "step": 104170 }, { "epoch": 0.6192675547312921, "grad_norm": 7.846405029296875, "learning_rate": 9.982680150908593e-06, "loss": 0.6646, "step": 104180 }, { "epoch": 0.6193269968079604, "grad_norm": 4.050088405609131, "learning_rate": 9.982662891130083e-06, "loss": 0.6068, "step": 104190 }, { "epoch": 0.6193864388846289, "grad_norm": 5.606965065002441, "learning_rate": 9.982645622770832e-06, "loss": 0.5662, "step": 104200 }, { "epoch": 0.6194458809612973, "grad_norm": 5.163144588470459, "learning_rate": 9.982628345830872e-06, "loss": 0.5779, "step": 104210 }, { "epoch": 0.6195053230379657, "grad_norm": 5.828151702880859, "learning_rate": 9.98261106031023e-06, "loss": 0.6787, "step": 104220 }, { "epoch": 0.6195647651146341, "grad_norm": 6.406561851501465, "learning_rate": 9.982593766208939e-06, "loss": 0.6625, "step": 104230 }, { "epoch": 0.6196242071913024, "grad_norm": 5.320804119110107, "learning_rate": 9.982576463527026e-06, "loss": 0.6445, "step": 104240 }, { "epoch": 0.6196836492679708, "grad_norm": 3.9888229370117188, "learning_rate": 9.98255915226452e-06, "loss": 0.6044, "step": 104250 }, { "epoch": 0.6197430913446392, "grad_norm": 7.601878643035889, "learning_rate": 9.982541832421456e-06, "loss": 0.6537, "step": 104260 }, { "epoch": 0.6198025334213076, "grad_norm": 7.062252521514893, "learning_rate": 9.982524503997858e-06, "loss": 0.601, "step": 104270 }, { "epoch": 0.619861975497976, "grad_norm": 6.674842834472656, "learning_rate": 9.98250716699376e-06, "loss": 0.6558, "step": 104280 }, { "epoch": 0.6199214175746444, "grad_norm": 5.97565221786499, "learning_rate": 9.982489821409189e-06, "loss": 0.5682, "step": 104290 }, { "epoch": 0.6199808596513128, "grad_norm": 5.069336891174316, "learning_rate": 9.982472467244178e-06, "loss": 0.5844, "step": 104300 }, { "epoch": 0.6200403017279812, "grad_norm": 4.319859981536865, "learning_rate": 9.982455104498753e-06, "loss": 0.5486, "step": 104310 }, { "epoch": 0.6200997438046496, "grad_norm": 5.654777526855469, "learning_rate": 9.982437733172946e-06, "loss": 0.6019, "step": 104320 }, { "epoch": 0.6201591858813179, "grad_norm": 6.553703784942627, "learning_rate": 9.982420353266786e-06, "loss": 0.6418, "step": 104330 }, { "epoch": 0.6202186279579863, "grad_norm": 4.291654586791992, "learning_rate": 9.982402964780305e-06, "loss": 0.6471, "step": 104340 }, { "epoch": 0.6202780700346547, "grad_norm": 7.489222049713135, "learning_rate": 9.982385567713531e-06, "loss": 0.636, "step": 104350 }, { "epoch": 0.6203375121113232, "grad_norm": 5.907451629638672, "learning_rate": 9.982368162066495e-06, "loss": 0.6464, "step": 104360 }, { "epoch": 0.6203969541879915, "grad_norm": 6.0122904777526855, "learning_rate": 9.982350747839227e-06, "loss": 0.5952, "step": 104370 }, { "epoch": 0.6204563962646599, "grad_norm": 5.558310031890869, "learning_rate": 9.982333325031756e-06, "loss": 0.6245, "step": 104380 }, { "epoch": 0.6205158383413283, "grad_norm": 6.505064010620117, "learning_rate": 9.982315893644112e-06, "loss": 0.5967, "step": 104390 }, { "epoch": 0.6205752804179967, "grad_norm": 5.220304489135742, "learning_rate": 9.982298453676326e-06, "loss": 0.68, "step": 104400 }, { "epoch": 0.6206347224946651, "grad_norm": 4.943277359008789, "learning_rate": 9.982281005128428e-06, "loss": 0.6556, "step": 104410 }, { "epoch": 0.6206941645713334, "grad_norm": 5.004648208618164, "learning_rate": 9.982263548000445e-06, "loss": 0.6631, "step": 104420 }, { "epoch": 0.6207536066480018, "grad_norm": 6.442225456237793, "learning_rate": 9.982246082292414e-06, "loss": 0.6522, "step": 104430 }, { "epoch": 0.6208130487246702, "grad_norm": 5.849793434143066, "learning_rate": 9.982228608004358e-06, "loss": 0.6099, "step": 104440 }, { "epoch": 0.6208724908013387, "grad_norm": 5.616092681884766, "learning_rate": 9.98221112513631e-06, "loss": 0.6263, "step": 104450 }, { "epoch": 0.6209319328780071, "grad_norm": 7.1766276359558105, "learning_rate": 9.9821936336883e-06, "loss": 0.7175, "step": 104460 }, { "epoch": 0.6209913749546754, "grad_norm": 5.4475603103637695, "learning_rate": 9.98217613366036e-06, "loss": 0.6543, "step": 104470 }, { "epoch": 0.6210508170313438, "grad_norm": 5.471447944641113, "learning_rate": 9.982158625052516e-06, "loss": 0.6287, "step": 104480 }, { "epoch": 0.6211102591080122, "grad_norm": 5.690091133117676, "learning_rate": 9.982141107864802e-06, "loss": 0.5806, "step": 104490 }, { "epoch": 0.6211697011846806, "grad_norm": 6.090812683105469, "learning_rate": 9.982123582097245e-06, "loss": 0.6353, "step": 104500 }, { "epoch": 0.6212291432613489, "grad_norm": 4.909254550933838, "learning_rate": 9.982106047749878e-06, "loss": 0.6173, "step": 104510 }, { "epoch": 0.6212885853380173, "grad_norm": 4.594000339508057, "learning_rate": 9.982088504822729e-06, "loss": 0.6495, "step": 104520 }, { "epoch": 0.6213480274146858, "grad_norm": 4.384310722351074, "learning_rate": 9.98207095331583e-06, "loss": 0.5651, "step": 104530 }, { "epoch": 0.6214074694913542, "grad_norm": 5.523557186126709, "learning_rate": 9.98205339322921e-06, "loss": 0.6742, "step": 104540 }, { "epoch": 0.6214669115680226, "grad_norm": 7.328199863433838, "learning_rate": 9.982035824562899e-06, "loss": 0.5936, "step": 104550 }, { "epoch": 0.6215263536446909, "grad_norm": 4.762375831604004, "learning_rate": 9.982018247316927e-06, "loss": 0.604, "step": 104560 }, { "epoch": 0.6215857957213593, "grad_norm": 5.748345375061035, "learning_rate": 9.982000661491327e-06, "loss": 0.6418, "step": 104570 }, { "epoch": 0.6216452377980277, "grad_norm": 5.390133857727051, "learning_rate": 9.981983067086128e-06, "loss": 0.6308, "step": 104580 }, { "epoch": 0.6217046798746961, "grad_norm": 6.196570873260498, "learning_rate": 9.981965464101357e-06, "loss": 0.5931, "step": 104590 }, { "epoch": 0.6217641219513645, "grad_norm": 4.611701488494873, "learning_rate": 9.981947852537049e-06, "loss": 0.5969, "step": 104600 }, { "epoch": 0.6218235640280328, "grad_norm": 5.435802459716797, "learning_rate": 9.981930232393232e-06, "loss": 0.6321, "step": 104610 }, { "epoch": 0.6218830061047013, "grad_norm": 4.926249027252197, "learning_rate": 9.981912603669937e-06, "loss": 0.5982, "step": 104620 }, { "epoch": 0.6219424481813697, "grad_norm": 6.50648307800293, "learning_rate": 9.981894966367195e-06, "loss": 0.6754, "step": 104630 }, { "epoch": 0.6220018902580381, "grad_norm": 5.75665283203125, "learning_rate": 9.981877320485033e-06, "loss": 0.6678, "step": 104640 }, { "epoch": 0.6220613323347064, "grad_norm": 6.57921028137207, "learning_rate": 9.981859666023485e-06, "loss": 0.6278, "step": 104650 }, { "epoch": 0.6221207744113748, "grad_norm": 6.893941879272461, "learning_rate": 9.98184200298258e-06, "loss": 0.6722, "step": 104660 }, { "epoch": 0.6221802164880432, "grad_norm": 5.5227460861206055, "learning_rate": 9.981824331362349e-06, "loss": 0.6099, "step": 104670 }, { "epoch": 0.6222396585647116, "grad_norm": 5.232972621917725, "learning_rate": 9.981806651162822e-06, "loss": 0.6453, "step": 104680 }, { "epoch": 0.62229910064138, "grad_norm": 4.378932952880859, "learning_rate": 9.981788962384029e-06, "loss": 0.6079, "step": 104690 }, { "epoch": 0.6223585427180484, "grad_norm": 5.909550666809082, "learning_rate": 9.981771265026002e-06, "loss": 0.618, "step": 104700 }, { "epoch": 0.6224179847947168, "grad_norm": 5.450029373168945, "learning_rate": 9.98175355908877e-06, "loss": 0.6568, "step": 104710 }, { "epoch": 0.6224774268713852, "grad_norm": 5.857154369354248, "learning_rate": 9.981735844572364e-06, "loss": 0.6937, "step": 104720 }, { "epoch": 0.6225368689480536, "grad_norm": 5.864311218261719, "learning_rate": 9.981718121476814e-06, "loss": 0.6521, "step": 104730 }, { "epoch": 0.6225963110247219, "grad_norm": 5.7974443435668945, "learning_rate": 9.981700389802151e-06, "loss": 0.6802, "step": 104740 }, { "epoch": 0.6226557531013903, "grad_norm": 5.158265113830566, "learning_rate": 9.981682649548407e-06, "loss": 0.5897, "step": 104750 }, { "epoch": 0.6227151951780587, "grad_norm": 4.589440822601318, "learning_rate": 9.98166490071561e-06, "loss": 0.6281, "step": 104760 }, { "epoch": 0.6227746372547271, "grad_norm": 6.654864311218262, "learning_rate": 9.981647143303792e-06, "loss": 0.6329, "step": 104770 }, { "epoch": 0.6228340793313956, "grad_norm": 5.549475193023682, "learning_rate": 9.981629377312982e-06, "loss": 0.6343, "step": 104780 }, { "epoch": 0.6228935214080639, "grad_norm": 5.831879615783691, "learning_rate": 9.981611602743214e-06, "loss": 0.5911, "step": 104790 }, { "epoch": 0.6229529634847323, "grad_norm": 6.6370158195495605, "learning_rate": 9.981593819594515e-06, "loss": 0.6007, "step": 104800 }, { "epoch": 0.6230124055614007, "grad_norm": 6.370924949645996, "learning_rate": 9.981576027866917e-06, "loss": 0.6817, "step": 104810 }, { "epoch": 0.6230718476380691, "grad_norm": 7.022256851196289, "learning_rate": 9.98155822756045e-06, "loss": 0.5635, "step": 104820 }, { "epoch": 0.6231312897147375, "grad_norm": 5.776543617248535, "learning_rate": 9.981540418675147e-06, "loss": 0.5549, "step": 104830 }, { "epoch": 0.6231907317914058, "grad_norm": 4.724227428436279, "learning_rate": 9.981522601211036e-06, "loss": 0.5846, "step": 104840 }, { "epoch": 0.6232501738680742, "grad_norm": 5.382113456726074, "learning_rate": 9.981504775168148e-06, "loss": 0.6258, "step": 104850 }, { "epoch": 0.6233096159447427, "grad_norm": 6.92141580581665, "learning_rate": 9.981486940546516e-06, "loss": 0.6737, "step": 104860 }, { "epoch": 0.6233690580214111, "grad_norm": 5.667037487030029, "learning_rate": 9.981469097346169e-06, "loss": 0.6221, "step": 104870 }, { "epoch": 0.6234285000980794, "grad_norm": 6.6957268714904785, "learning_rate": 9.981451245567135e-06, "loss": 0.6339, "step": 104880 }, { "epoch": 0.6234879421747478, "grad_norm": 5.744668960571289, "learning_rate": 9.981433385209452e-06, "loss": 0.5845, "step": 104890 }, { "epoch": 0.6235473842514162, "grad_norm": 6.136152267456055, "learning_rate": 9.981415516273143e-06, "loss": 0.573, "step": 104900 }, { "epoch": 0.6236068263280846, "grad_norm": 5.835000514984131, "learning_rate": 9.981397638758243e-06, "loss": 0.6328, "step": 104910 }, { "epoch": 0.623666268404753, "grad_norm": 5.303699016571045, "learning_rate": 9.981379752664781e-06, "loss": 0.6358, "step": 104920 }, { "epoch": 0.6237257104814213, "grad_norm": 5.706857204437256, "learning_rate": 9.98136185799279e-06, "loss": 0.6178, "step": 104930 }, { "epoch": 0.6237851525580898, "grad_norm": 4.884284973144531, "learning_rate": 9.9813439547423e-06, "loss": 0.6421, "step": 104940 }, { "epoch": 0.6238445946347582, "grad_norm": 6.127472877502441, "learning_rate": 9.98132604291334e-06, "loss": 0.6173, "step": 104950 }, { "epoch": 0.6239040367114266, "grad_norm": 5.710742950439453, "learning_rate": 9.981308122505944e-06, "loss": 0.65, "step": 104960 }, { "epoch": 0.623963478788095, "grad_norm": 4.762284278869629, "learning_rate": 9.981290193520138e-06, "loss": 0.5814, "step": 104970 }, { "epoch": 0.6240229208647633, "grad_norm": 7.451798439025879, "learning_rate": 9.981272255955959e-06, "loss": 0.6585, "step": 104980 }, { "epoch": 0.6240823629414317, "grad_norm": 4.678433418273926, "learning_rate": 9.981254309813433e-06, "loss": 0.6219, "step": 104990 }, { "epoch": 0.6241418050181001, "grad_norm": 6.322281837463379, "learning_rate": 9.981236355092594e-06, "loss": 0.6718, "step": 105000 }, { "epoch": 0.6242012470947685, "grad_norm": 5.878047943115234, "learning_rate": 9.981218391793473e-06, "loss": 0.6483, "step": 105010 }, { "epoch": 0.6242606891714368, "grad_norm": 4.882571220397949, "learning_rate": 9.981200419916096e-06, "loss": 0.5776, "step": 105020 }, { "epoch": 0.6243201312481053, "grad_norm": 4.9399333000183105, "learning_rate": 9.9811824394605e-06, "loss": 0.6421, "step": 105030 }, { "epoch": 0.6243795733247737, "grad_norm": 5.964629650115967, "learning_rate": 9.981164450426712e-06, "loss": 0.5825, "step": 105040 }, { "epoch": 0.6244390154014421, "grad_norm": 7.023165702819824, "learning_rate": 9.981146452814765e-06, "loss": 0.6271, "step": 105050 }, { "epoch": 0.6244984574781105, "grad_norm": 6.016304016113281, "learning_rate": 9.981128446624691e-06, "loss": 0.5998, "step": 105060 }, { "epoch": 0.6245578995547788, "grad_norm": 4.936277389526367, "learning_rate": 9.981110431856517e-06, "loss": 0.5817, "step": 105070 }, { "epoch": 0.6246173416314472, "grad_norm": 4.779891014099121, "learning_rate": 9.981092408510279e-06, "loss": 0.6564, "step": 105080 }, { "epoch": 0.6246767837081156, "grad_norm": 5.882176876068115, "learning_rate": 9.981074376586002e-06, "loss": 0.5924, "step": 105090 }, { "epoch": 0.624736225784784, "grad_norm": 5.753646373748779, "learning_rate": 9.981056336083723e-06, "loss": 0.6604, "step": 105100 }, { "epoch": 0.6247956678614524, "grad_norm": 6.655770778656006, "learning_rate": 9.98103828700347e-06, "loss": 0.6935, "step": 105110 }, { "epoch": 0.6248551099381208, "grad_norm": 5.083384990692139, "learning_rate": 9.981020229345275e-06, "loss": 0.5951, "step": 105120 }, { "epoch": 0.6249145520147892, "grad_norm": 6.516794681549072, "learning_rate": 9.98100216310917e-06, "loss": 0.618, "step": 105130 }, { "epoch": 0.6249739940914576, "grad_norm": 5.487086296081543, "learning_rate": 9.980984088295183e-06, "loss": 0.5848, "step": 105140 }, { "epoch": 0.625033436168126, "grad_norm": 5.607294082641602, "learning_rate": 9.980966004903349e-06, "loss": 0.6745, "step": 105150 }, { "epoch": 0.6250928782447943, "grad_norm": 5.4018402099609375, "learning_rate": 9.980947912933696e-06, "loss": 0.6215, "step": 105160 }, { "epoch": 0.6251523203214627, "grad_norm": 5.256643295288086, "learning_rate": 9.980929812386256e-06, "loss": 0.6292, "step": 105170 }, { "epoch": 0.6252117623981311, "grad_norm": 5.918033123016357, "learning_rate": 9.980911703261061e-06, "loss": 0.6472, "step": 105180 }, { "epoch": 0.6252712044747996, "grad_norm": 7.53726053237915, "learning_rate": 9.980893585558143e-06, "loss": 0.6147, "step": 105190 }, { "epoch": 0.625330646551468, "grad_norm": 5.5735955238342285, "learning_rate": 9.98087545927753e-06, "loss": 0.5929, "step": 105200 }, { "epoch": 0.6253900886281363, "grad_norm": 6.416255950927734, "learning_rate": 9.980857324419255e-06, "loss": 0.5901, "step": 105210 }, { "epoch": 0.6254495307048047, "grad_norm": 7.01912784576416, "learning_rate": 9.98083918098335e-06, "loss": 0.6398, "step": 105220 }, { "epoch": 0.6255089727814731, "grad_norm": 5.520614147186279, "learning_rate": 9.980821028969847e-06, "loss": 0.6089, "step": 105230 }, { "epoch": 0.6255684148581415, "grad_norm": 6.336270809173584, "learning_rate": 9.980802868378775e-06, "loss": 0.5723, "step": 105240 }, { "epoch": 0.6256278569348098, "grad_norm": 5.343658924102783, "learning_rate": 9.980784699210166e-06, "loss": 0.7059, "step": 105250 }, { "epoch": 0.6256872990114782, "grad_norm": 6.439780235290527, "learning_rate": 9.980766521464051e-06, "loss": 0.6109, "step": 105260 }, { "epoch": 0.6257467410881467, "grad_norm": 5.1366987228393555, "learning_rate": 9.980748335140461e-06, "loss": 0.6159, "step": 105270 }, { "epoch": 0.6258061831648151, "grad_norm": 4.763728141784668, "learning_rate": 9.980730140239431e-06, "loss": 0.5854, "step": 105280 }, { "epoch": 0.6258656252414835, "grad_norm": 4.930583953857422, "learning_rate": 9.980711936760988e-06, "loss": 0.6074, "step": 105290 }, { "epoch": 0.6259250673181518, "grad_norm": 6.377885341644287, "learning_rate": 9.980693724705164e-06, "loss": 0.6125, "step": 105300 }, { "epoch": 0.6259845093948202, "grad_norm": 6.216416835784912, "learning_rate": 9.980675504071991e-06, "loss": 0.572, "step": 105310 }, { "epoch": 0.6260439514714886, "grad_norm": 5.712876796722412, "learning_rate": 9.9806572748615e-06, "loss": 0.5587, "step": 105320 }, { "epoch": 0.626103393548157, "grad_norm": 4.333693027496338, "learning_rate": 9.980639037073725e-06, "loss": 0.5536, "step": 105330 }, { "epoch": 0.6261628356248254, "grad_norm": 6.7946696281433105, "learning_rate": 9.980620790708696e-06, "loss": 0.6979, "step": 105340 }, { "epoch": 0.6262222777014937, "grad_norm": 4.883781909942627, "learning_rate": 9.98060253576644e-06, "loss": 0.6349, "step": 105350 }, { "epoch": 0.6262817197781622, "grad_norm": 4.17426872253418, "learning_rate": 9.980584272246994e-06, "loss": 0.6173, "step": 105360 }, { "epoch": 0.6263411618548306, "grad_norm": 4.774658679962158, "learning_rate": 9.980566000150388e-06, "loss": 0.5713, "step": 105370 }, { "epoch": 0.626400603931499, "grad_norm": 6.222894191741943, "learning_rate": 9.980547719476654e-06, "loss": 0.6462, "step": 105380 }, { "epoch": 0.6264600460081673, "grad_norm": 5.400210380554199, "learning_rate": 9.98052943022582e-06, "loss": 0.6395, "step": 105390 }, { "epoch": 0.6265194880848357, "grad_norm": 5.600523948669434, "learning_rate": 9.980511132397921e-06, "loss": 0.6384, "step": 105400 }, { "epoch": 0.6265789301615041, "grad_norm": 5.20663595199585, "learning_rate": 9.98049282599299e-06, "loss": 0.6365, "step": 105410 }, { "epoch": 0.6266383722381725, "grad_norm": 4.124410629272461, "learning_rate": 9.980474511011053e-06, "loss": 0.6334, "step": 105420 }, { "epoch": 0.626697814314841, "grad_norm": 6.953976631164551, "learning_rate": 9.980456187452145e-06, "loss": 0.6296, "step": 105430 }, { "epoch": 0.6267572563915093, "grad_norm": 5.163334846496582, "learning_rate": 9.980437855316299e-06, "loss": 0.6164, "step": 105440 }, { "epoch": 0.6268166984681777, "grad_norm": 6.732915878295898, "learning_rate": 9.980419514603543e-06, "loss": 0.662, "step": 105450 }, { "epoch": 0.6268761405448461, "grad_norm": 6.362082004547119, "learning_rate": 9.98040116531391e-06, "loss": 0.5798, "step": 105460 }, { "epoch": 0.6269355826215145, "grad_norm": 6.216188430786133, "learning_rate": 9.980382807447433e-06, "loss": 0.564, "step": 105470 }, { "epoch": 0.6269950246981828, "grad_norm": 6.415894031524658, "learning_rate": 9.980364441004143e-06, "loss": 0.5946, "step": 105480 }, { "epoch": 0.6270544667748512, "grad_norm": 6.9008612632751465, "learning_rate": 9.98034606598407e-06, "loss": 0.6628, "step": 105490 }, { "epoch": 0.6271139088515196, "grad_norm": 5.248439788818359, "learning_rate": 9.98032768238725e-06, "loss": 0.6402, "step": 105500 }, { "epoch": 0.627173350928188, "grad_norm": 6.583890914916992, "learning_rate": 9.980309290213708e-06, "loss": 0.6616, "step": 105510 }, { "epoch": 0.6272327930048565, "grad_norm": 5.561219692230225, "learning_rate": 9.98029088946348e-06, "loss": 0.657, "step": 105520 }, { "epoch": 0.6272922350815248, "grad_norm": 6.440610408782959, "learning_rate": 9.980272480136598e-06, "loss": 0.6032, "step": 105530 }, { "epoch": 0.6273516771581932, "grad_norm": 5.33005952835083, "learning_rate": 9.98025406223309e-06, "loss": 0.6221, "step": 105540 }, { "epoch": 0.6274111192348616, "grad_norm": 7.251823425292969, "learning_rate": 9.980235635752991e-06, "loss": 0.6339, "step": 105550 }, { "epoch": 0.62747056131153, "grad_norm": 5.995894432067871, "learning_rate": 9.980217200696333e-06, "loss": 0.5956, "step": 105560 }, { "epoch": 0.6275300033881984, "grad_norm": 6.093740463256836, "learning_rate": 9.980198757063147e-06, "loss": 0.6099, "step": 105570 }, { "epoch": 0.6275894454648667, "grad_norm": 6.8541388511657715, "learning_rate": 9.980180304853465e-06, "loss": 0.5876, "step": 105580 }, { "epoch": 0.6276488875415351, "grad_norm": 5.873053550720215, "learning_rate": 9.980161844067317e-06, "loss": 0.6216, "step": 105590 }, { "epoch": 0.6277083296182036, "grad_norm": 5.354783058166504, "learning_rate": 9.980143374704737e-06, "loss": 0.6479, "step": 105600 }, { "epoch": 0.627767771694872, "grad_norm": 5.760961055755615, "learning_rate": 9.980124896765755e-06, "loss": 0.648, "step": 105610 }, { "epoch": 0.6278272137715403, "grad_norm": 6.225383758544922, "learning_rate": 9.980106410250404e-06, "loss": 0.6462, "step": 105620 }, { "epoch": 0.6278866558482087, "grad_norm": 7.407678604125977, "learning_rate": 9.980087915158715e-06, "loss": 0.6586, "step": 105630 }, { "epoch": 0.6279460979248771, "grad_norm": 6.754825592041016, "learning_rate": 9.98006941149072e-06, "loss": 0.5834, "step": 105640 }, { "epoch": 0.6280055400015455, "grad_norm": 6.246831893920898, "learning_rate": 9.980050899246455e-06, "loss": 0.6318, "step": 105650 }, { "epoch": 0.6280649820782139, "grad_norm": 5.2655158042907715, "learning_rate": 9.980032378425944e-06, "loss": 0.6688, "step": 105660 }, { "epoch": 0.6281244241548822, "grad_norm": 6.710519790649414, "learning_rate": 9.980013849029224e-06, "loss": 0.6621, "step": 105670 }, { "epoch": 0.6281838662315506, "grad_norm": 6.090789318084717, "learning_rate": 9.979995311056327e-06, "loss": 0.569, "step": 105680 }, { "epoch": 0.6282433083082191, "grad_norm": 4.4513325691223145, "learning_rate": 9.979976764507281e-06, "loss": 0.6193, "step": 105690 }, { "epoch": 0.6283027503848875, "grad_norm": 4.7442827224731445, "learning_rate": 9.979958209382124e-06, "loss": 0.6441, "step": 105700 }, { "epoch": 0.6283621924615559, "grad_norm": 6.4687724113464355, "learning_rate": 9.979939645680885e-06, "loss": 0.6194, "step": 105710 }, { "epoch": 0.6284216345382242, "grad_norm": 5.4862589836120605, "learning_rate": 9.979921073403594e-06, "loss": 0.6454, "step": 105720 }, { "epoch": 0.6284810766148926, "grad_norm": 6.058127403259277, "learning_rate": 9.979902492550285e-06, "loss": 0.5641, "step": 105730 }, { "epoch": 0.628540518691561, "grad_norm": 6.933063983917236, "learning_rate": 9.97988390312099e-06, "loss": 0.6135, "step": 105740 }, { "epoch": 0.6285999607682294, "grad_norm": 5.524310111999512, "learning_rate": 9.979865305115742e-06, "loss": 0.6039, "step": 105750 }, { "epoch": 0.6286594028448977, "grad_norm": 6.74131965637207, "learning_rate": 9.97984669853457e-06, "loss": 0.6108, "step": 105760 }, { "epoch": 0.6287188449215662, "grad_norm": 6.181065082550049, "learning_rate": 9.979828083377507e-06, "loss": 0.5874, "step": 105770 }, { "epoch": 0.6287782869982346, "grad_norm": 6.609583854675293, "learning_rate": 9.979809459644587e-06, "loss": 0.6467, "step": 105780 }, { "epoch": 0.628837729074903, "grad_norm": 5.626551151275635, "learning_rate": 9.979790827335843e-06, "loss": 0.6912, "step": 105790 }, { "epoch": 0.6288971711515714, "grad_norm": 5.668352127075195, "learning_rate": 9.979772186451302e-06, "loss": 0.6823, "step": 105800 }, { "epoch": 0.6289566132282397, "grad_norm": 6.701026916503906, "learning_rate": 9.979753536991001e-06, "loss": 0.6732, "step": 105810 }, { "epoch": 0.6290160553049081, "grad_norm": 4.933660984039307, "learning_rate": 9.979734878954968e-06, "loss": 0.6046, "step": 105820 }, { "epoch": 0.6290754973815765, "grad_norm": 6.763099193572998, "learning_rate": 9.97971621234324e-06, "loss": 0.6272, "step": 105830 }, { "epoch": 0.629134939458245, "grad_norm": 6.5139312744140625, "learning_rate": 9.979697537155844e-06, "loss": 0.6976, "step": 105840 }, { "epoch": 0.6291943815349132, "grad_norm": 6.137484073638916, "learning_rate": 9.979678853392816e-06, "loss": 0.6201, "step": 105850 }, { "epoch": 0.6292538236115817, "grad_norm": 4.465192794799805, "learning_rate": 9.979660161054188e-06, "loss": 0.6129, "step": 105860 }, { "epoch": 0.6293132656882501, "grad_norm": 5.968835830688477, "learning_rate": 9.97964146013999e-06, "loss": 0.6334, "step": 105870 }, { "epoch": 0.6293727077649185, "grad_norm": 5.662139892578125, "learning_rate": 9.979622750650256e-06, "loss": 0.6578, "step": 105880 }, { "epoch": 0.6294321498415869, "grad_norm": 5.012927532196045, "learning_rate": 9.979604032585015e-06, "loss": 0.6351, "step": 105890 }, { "epoch": 0.6294915919182552, "grad_norm": 6.336772441864014, "learning_rate": 9.979585305944303e-06, "loss": 0.6466, "step": 105900 }, { "epoch": 0.6295510339949236, "grad_norm": 5.296614170074463, "learning_rate": 9.979566570728152e-06, "loss": 0.6756, "step": 105910 }, { "epoch": 0.629610476071592, "grad_norm": 5.039676189422607, "learning_rate": 9.979547826936593e-06, "loss": 0.6344, "step": 105920 }, { "epoch": 0.6296699181482605, "grad_norm": 5.426785469055176, "learning_rate": 9.979529074569656e-06, "loss": 0.5374, "step": 105930 }, { "epoch": 0.6297293602249289, "grad_norm": 6.15880012512207, "learning_rate": 9.979510313627378e-06, "loss": 0.6314, "step": 105940 }, { "epoch": 0.6297888023015972, "grad_norm": 5.6264801025390625, "learning_rate": 9.97949154410979e-06, "loss": 0.59, "step": 105950 }, { "epoch": 0.6298482443782656, "grad_norm": 6.330776214599609, "learning_rate": 9.979472766016922e-06, "loss": 0.6694, "step": 105960 }, { "epoch": 0.629907686454934, "grad_norm": 6.643864154815674, "learning_rate": 9.979453979348807e-06, "loss": 0.6249, "step": 105970 }, { "epoch": 0.6299671285316024, "grad_norm": 4.620664596557617, "learning_rate": 9.97943518410548e-06, "loss": 0.5832, "step": 105980 }, { "epoch": 0.6300265706082707, "grad_norm": 4.85066032409668, "learning_rate": 9.97941638028697e-06, "loss": 0.6075, "step": 105990 }, { "epoch": 0.6300860126849391, "grad_norm": 5.288669109344482, "learning_rate": 9.979397567893312e-06, "loss": 0.5958, "step": 106000 }, { "epoch": 0.6301454547616075, "grad_norm": 4.94804573059082, "learning_rate": 9.979378746924537e-06, "loss": 0.6311, "step": 106010 }, { "epoch": 0.630204896838276, "grad_norm": 6.2581987380981445, "learning_rate": 9.979359917380676e-06, "loss": 0.5567, "step": 106020 }, { "epoch": 0.6302643389149444, "grad_norm": 5.0203657150268555, "learning_rate": 9.979341079261765e-06, "loss": 0.5931, "step": 106030 }, { "epoch": 0.6303237809916127, "grad_norm": 6.098850250244141, "learning_rate": 9.979322232567834e-06, "loss": 0.6157, "step": 106040 }, { "epoch": 0.6303832230682811, "grad_norm": 5.768810749053955, "learning_rate": 9.979303377298916e-06, "loss": 0.6257, "step": 106050 }, { "epoch": 0.6304426651449495, "grad_norm": 4.860631465911865, "learning_rate": 9.979284513455043e-06, "loss": 0.5942, "step": 106060 }, { "epoch": 0.6305021072216179, "grad_norm": 5.513487815856934, "learning_rate": 9.97926564103625e-06, "loss": 0.644, "step": 106070 }, { "epoch": 0.6305615492982863, "grad_norm": 7.092472553253174, "learning_rate": 9.979246760042565e-06, "loss": 0.5991, "step": 106080 }, { "epoch": 0.6306209913749546, "grad_norm": 5.317892551422119, "learning_rate": 9.979227870474025e-06, "loss": 0.5902, "step": 106090 }, { "epoch": 0.6306804334516231, "grad_norm": 5.2291178703308105, "learning_rate": 9.979208972330658e-06, "loss": 0.6332, "step": 106100 }, { "epoch": 0.6307398755282915, "grad_norm": 5.183244705200195, "learning_rate": 9.9791900656125e-06, "loss": 0.5759, "step": 106110 }, { "epoch": 0.6307993176049599, "grad_norm": 5.314004421234131, "learning_rate": 9.979171150319583e-06, "loss": 0.6272, "step": 106120 }, { "epoch": 0.6308587596816282, "grad_norm": 5.114297866821289, "learning_rate": 9.979152226451939e-06, "loss": 0.6982, "step": 106130 }, { "epoch": 0.6309182017582966, "grad_norm": 5.454130172729492, "learning_rate": 9.979133294009601e-06, "loss": 0.7189, "step": 106140 }, { "epoch": 0.630977643834965, "grad_norm": 7.165747165679932, "learning_rate": 9.979114352992601e-06, "loss": 0.6182, "step": 106150 }, { "epoch": 0.6310370859116334, "grad_norm": 5.45667028427124, "learning_rate": 9.979095403400973e-06, "loss": 0.6609, "step": 106160 }, { "epoch": 0.6310965279883018, "grad_norm": 4.585353374481201, "learning_rate": 9.979076445234747e-06, "loss": 0.6218, "step": 106170 }, { "epoch": 0.6311559700649702, "grad_norm": 5.282566070556641, "learning_rate": 9.979057478493958e-06, "loss": 0.59, "step": 106180 }, { "epoch": 0.6312154121416386, "grad_norm": 5.430933475494385, "learning_rate": 9.97903850317864e-06, "loss": 0.6109, "step": 106190 }, { "epoch": 0.631274854218307, "grad_norm": 5.2982587814331055, "learning_rate": 9.97901951928882e-06, "loss": 0.572, "step": 106200 }, { "epoch": 0.6313342962949754, "grad_norm": 5.522170543670654, "learning_rate": 9.979000526824536e-06, "loss": 0.616, "step": 106210 }, { "epoch": 0.6313937383716437, "grad_norm": 5.343688488006592, "learning_rate": 9.978981525785819e-06, "loss": 0.645, "step": 106220 }, { "epoch": 0.6314531804483121, "grad_norm": 5.838047981262207, "learning_rate": 9.978962516172701e-06, "loss": 0.6678, "step": 106230 }, { "epoch": 0.6315126225249805, "grad_norm": 5.758113384246826, "learning_rate": 9.978943497985216e-06, "loss": 0.6459, "step": 106240 }, { "epoch": 0.6315720646016489, "grad_norm": 6.545628547668457, "learning_rate": 9.978924471223396e-06, "loss": 0.6503, "step": 106250 }, { "epoch": 0.6316315066783174, "grad_norm": 6.133461952209473, "learning_rate": 9.978905435887277e-06, "loss": 0.5742, "step": 106260 }, { "epoch": 0.6316909487549857, "grad_norm": 4.956084728240967, "learning_rate": 9.978886391976885e-06, "loss": 0.601, "step": 106270 }, { "epoch": 0.6317503908316541, "grad_norm": 4.444786548614502, "learning_rate": 9.978867339492257e-06, "loss": 0.6224, "step": 106280 }, { "epoch": 0.6318098329083225, "grad_norm": 5.8096604347229, "learning_rate": 9.978848278433426e-06, "loss": 0.6148, "step": 106290 }, { "epoch": 0.6318692749849909, "grad_norm": 5.049651145935059, "learning_rate": 9.978829208800424e-06, "loss": 0.6245, "step": 106300 }, { "epoch": 0.6319287170616593, "grad_norm": 5.78395938873291, "learning_rate": 9.978810130593286e-06, "loss": 0.6281, "step": 106310 }, { "epoch": 0.6319881591383276, "grad_norm": 5.414617538452148, "learning_rate": 9.97879104381204e-06, "loss": 0.6056, "step": 106320 }, { "epoch": 0.632047601214996, "grad_norm": 5.009098529815674, "learning_rate": 9.978771948456722e-06, "loss": 0.5275, "step": 106330 }, { "epoch": 0.6321070432916644, "grad_norm": 5.995777606964111, "learning_rate": 9.978752844527367e-06, "loss": 0.6798, "step": 106340 }, { "epoch": 0.6321664853683329, "grad_norm": 5.493337154388428, "learning_rate": 9.978733732024005e-06, "loss": 0.6456, "step": 106350 }, { "epoch": 0.6322259274450012, "grad_norm": 5.368880748748779, "learning_rate": 9.978714610946667e-06, "loss": 0.641, "step": 106360 }, { "epoch": 0.6322853695216696, "grad_norm": 4.7865400314331055, "learning_rate": 9.97869548129539e-06, "loss": 0.6437, "step": 106370 }, { "epoch": 0.632344811598338, "grad_norm": 6.255101680755615, "learning_rate": 9.978676343070206e-06, "loss": 0.5954, "step": 106380 }, { "epoch": 0.6324042536750064, "grad_norm": 5.047627925872803, "learning_rate": 9.978657196271146e-06, "loss": 0.5888, "step": 106390 }, { "epoch": 0.6324636957516748, "grad_norm": 6.546783924102783, "learning_rate": 9.978638040898246e-06, "loss": 0.6267, "step": 106400 }, { "epoch": 0.6325231378283431, "grad_norm": 5.95205545425415, "learning_rate": 9.978618876951536e-06, "loss": 0.5828, "step": 106410 }, { "epoch": 0.6325825799050115, "grad_norm": 4.456981182098389, "learning_rate": 9.97859970443105e-06, "loss": 0.6608, "step": 106420 }, { "epoch": 0.63264202198168, "grad_norm": 6.782797336578369, "learning_rate": 9.978580523336821e-06, "loss": 0.6569, "step": 106430 }, { "epoch": 0.6327014640583484, "grad_norm": 6.0965471267700195, "learning_rate": 9.978561333668883e-06, "loss": 0.6451, "step": 106440 }, { "epoch": 0.6327609061350168, "grad_norm": 6.133284568786621, "learning_rate": 9.978542135427269e-06, "loss": 0.6535, "step": 106450 }, { "epoch": 0.6328203482116851, "grad_norm": 5.879361152648926, "learning_rate": 9.978522928612011e-06, "loss": 0.6512, "step": 106460 }, { "epoch": 0.6328797902883535, "grad_norm": 6.068449974060059, "learning_rate": 9.978503713223142e-06, "loss": 0.6339, "step": 106470 }, { "epoch": 0.6329392323650219, "grad_norm": 7.027317047119141, "learning_rate": 9.978484489260697e-06, "loss": 0.6643, "step": 106480 }, { "epoch": 0.6329986744416903, "grad_norm": 5.6165690422058105, "learning_rate": 9.978465256724706e-06, "loss": 0.5995, "step": 106490 }, { "epoch": 0.6330581165183586, "grad_norm": 5.239746570587158, "learning_rate": 9.978446015615205e-06, "loss": 0.6151, "step": 106500 }, { "epoch": 0.633117558595027, "grad_norm": 4.665889263153076, "learning_rate": 9.978426765932223e-06, "loss": 0.5863, "step": 106510 }, { "epoch": 0.6331770006716955, "grad_norm": 4.4528608322143555, "learning_rate": 9.978407507675799e-06, "loss": 0.5719, "step": 106520 }, { "epoch": 0.6332364427483639, "grad_norm": 7.017210006713867, "learning_rate": 9.978388240845961e-06, "loss": 0.6368, "step": 106530 }, { "epoch": 0.6332958848250323, "grad_norm": 6.367758274078369, "learning_rate": 9.978368965442748e-06, "loss": 0.6064, "step": 106540 }, { "epoch": 0.6333553269017006, "grad_norm": 6.184370517730713, "learning_rate": 9.978349681466187e-06, "loss": 0.5747, "step": 106550 }, { "epoch": 0.633414768978369, "grad_norm": 4.62633752822876, "learning_rate": 9.978330388916316e-06, "loss": 0.589, "step": 106560 }, { "epoch": 0.6334742110550374, "grad_norm": 4.5886735916137695, "learning_rate": 9.978311087793163e-06, "loss": 0.5439, "step": 106570 }, { "epoch": 0.6335336531317058, "grad_norm": 5.408941745758057, "learning_rate": 9.978291778096765e-06, "loss": 0.5534, "step": 106580 }, { "epoch": 0.6335930952083741, "grad_norm": 5.39730167388916, "learning_rate": 9.978272459827156e-06, "loss": 0.6005, "step": 106590 }, { "epoch": 0.6336525372850426, "grad_norm": 4.932214736938477, "learning_rate": 9.978253132984368e-06, "loss": 0.628, "step": 106600 }, { "epoch": 0.633711979361711, "grad_norm": 7.061305046081543, "learning_rate": 9.978233797568433e-06, "loss": 0.6698, "step": 106610 }, { "epoch": 0.6337714214383794, "grad_norm": 4.754322052001953, "learning_rate": 9.978214453579386e-06, "loss": 0.5446, "step": 106620 }, { "epoch": 0.6338308635150478, "grad_norm": 6.4749016761779785, "learning_rate": 9.97819510101726e-06, "loss": 0.6374, "step": 106630 }, { "epoch": 0.6338903055917161, "grad_norm": 5.991771697998047, "learning_rate": 9.978175739882087e-06, "loss": 0.6164, "step": 106640 }, { "epoch": 0.6339497476683845, "grad_norm": 6.4409403800964355, "learning_rate": 9.978156370173901e-06, "loss": 0.6219, "step": 106650 }, { "epoch": 0.6340091897450529, "grad_norm": 5.977010726928711, "learning_rate": 9.978136991892737e-06, "loss": 0.5764, "step": 106660 }, { "epoch": 0.6340686318217214, "grad_norm": 5.630352020263672, "learning_rate": 9.978117605038628e-06, "loss": 0.6706, "step": 106670 }, { "epoch": 0.6341280738983898, "grad_norm": 6.038960933685303, "learning_rate": 9.978098209611604e-06, "loss": 0.5593, "step": 106680 }, { "epoch": 0.6341875159750581, "grad_norm": 7.600830078125, "learning_rate": 9.978078805611703e-06, "loss": 0.6422, "step": 106690 }, { "epoch": 0.6342469580517265, "grad_norm": 5.182281970977783, "learning_rate": 9.978059393038954e-06, "loss": 0.5881, "step": 106700 }, { "epoch": 0.6343064001283949, "grad_norm": 3.887343168258667, "learning_rate": 9.978039971893396e-06, "loss": 0.5525, "step": 106710 }, { "epoch": 0.6343658422050633, "grad_norm": 6.363793849945068, "learning_rate": 9.978020542175057e-06, "loss": 0.5823, "step": 106720 }, { "epoch": 0.6344252842817316, "grad_norm": 4.810550212860107, "learning_rate": 9.978001103883972e-06, "loss": 0.5835, "step": 106730 }, { "epoch": 0.6344847263584, "grad_norm": 5.752195835113525, "learning_rate": 9.977981657020177e-06, "loss": 0.6301, "step": 106740 }, { "epoch": 0.6345441684350684, "grad_norm": 6.248998165130615, "learning_rate": 9.977962201583704e-06, "loss": 0.6296, "step": 106750 }, { "epoch": 0.6346036105117369, "grad_norm": 5.836334228515625, "learning_rate": 9.977942737574584e-06, "loss": 0.672, "step": 106760 }, { "epoch": 0.6346630525884053, "grad_norm": 5.335607051849365, "learning_rate": 9.977923264992854e-06, "loss": 0.5849, "step": 106770 }, { "epoch": 0.6347224946650736, "grad_norm": 5.2346577644348145, "learning_rate": 9.977903783838546e-06, "loss": 0.6481, "step": 106780 }, { "epoch": 0.634781936741742, "grad_norm": 6.341142177581787, "learning_rate": 9.977884294111694e-06, "loss": 0.6207, "step": 106790 }, { "epoch": 0.6348413788184104, "grad_norm": 6.249934673309326, "learning_rate": 9.977864795812331e-06, "loss": 0.58, "step": 106800 }, { "epoch": 0.6349008208950788, "grad_norm": 5.749218463897705, "learning_rate": 9.977845288940492e-06, "loss": 0.6752, "step": 106810 }, { "epoch": 0.6349602629717472, "grad_norm": 5.753408432006836, "learning_rate": 9.977825773496206e-06, "loss": 0.61, "step": 106820 }, { "epoch": 0.6350197050484155, "grad_norm": 4.23784065246582, "learning_rate": 9.977806249479512e-06, "loss": 0.5874, "step": 106830 }, { "epoch": 0.635079147125084, "grad_norm": 5.4729180335998535, "learning_rate": 9.977786716890443e-06, "loss": 0.5993, "step": 106840 }, { "epoch": 0.6351385892017524, "grad_norm": 5.951456069946289, "learning_rate": 9.977767175729029e-06, "loss": 0.6654, "step": 106850 }, { "epoch": 0.6351980312784208, "grad_norm": 6.795041561126709, "learning_rate": 9.977747625995308e-06, "loss": 0.59, "step": 106860 }, { "epoch": 0.6352574733550891, "grad_norm": 6.719552993774414, "learning_rate": 9.977728067689313e-06, "loss": 0.6193, "step": 106870 }, { "epoch": 0.6353169154317575, "grad_norm": 4.665699481964111, "learning_rate": 9.977708500811072e-06, "loss": 0.6059, "step": 106880 }, { "epoch": 0.6353763575084259, "grad_norm": 4.495233058929443, "learning_rate": 9.977688925360627e-06, "loss": 0.5785, "step": 106890 }, { "epoch": 0.6354357995850943, "grad_norm": 8.113975524902344, "learning_rate": 9.977669341338006e-06, "loss": 0.6623, "step": 106900 }, { "epoch": 0.6354952416617627, "grad_norm": 7.2921905517578125, "learning_rate": 9.977649748743244e-06, "loss": 0.5901, "step": 106910 }, { "epoch": 0.635554683738431, "grad_norm": 5.064891815185547, "learning_rate": 9.977630147576376e-06, "loss": 0.6206, "step": 106920 }, { "epoch": 0.6356141258150995, "grad_norm": 5.672162055969238, "learning_rate": 9.977610537837434e-06, "loss": 0.5976, "step": 106930 }, { "epoch": 0.6356735678917679, "grad_norm": 5.834056854248047, "learning_rate": 9.977590919526454e-06, "loss": 0.5635, "step": 106940 }, { "epoch": 0.6357330099684363, "grad_norm": 6.244807243347168, "learning_rate": 9.977571292643466e-06, "loss": 0.6768, "step": 106950 }, { "epoch": 0.6357924520451046, "grad_norm": 4.8251633644104, "learning_rate": 9.977551657188508e-06, "loss": 0.6603, "step": 106960 }, { "epoch": 0.635851894121773, "grad_norm": 5.831441879272461, "learning_rate": 9.977532013161614e-06, "loss": 0.607, "step": 106970 }, { "epoch": 0.6359113361984414, "grad_norm": 6.134137153625488, "learning_rate": 9.977512360562815e-06, "loss": 0.6861, "step": 106980 }, { "epoch": 0.6359707782751098, "grad_norm": 6.445952415466309, "learning_rate": 9.977492699392144e-06, "loss": 0.6571, "step": 106990 }, { "epoch": 0.6360302203517783, "grad_norm": 7.324282646179199, "learning_rate": 9.977473029649638e-06, "loss": 0.6037, "step": 107000 }, { "epoch": 0.6360896624284466, "grad_norm": 6.231629371643066, "learning_rate": 9.97745335133533e-06, "loss": 0.669, "step": 107010 }, { "epoch": 0.636149104505115, "grad_norm": 6.136749744415283, "learning_rate": 9.977433664449252e-06, "loss": 0.6373, "step": 107020 }, { "epoch": 0.6362085465817834, "grad_norm": 5.487641334533691, "learning_rate": 9.97741396899144e-06, "loss": 0.6079, "step": 107030 }, { "epoch": 0.6362679886584518, "grad_norm": 5.953439712524414, "learning_rate": 9.977394264961929e-06, "loss": 0.6306, "step": 107040 }, { "epoch": 0.6363274307351202, "grad_norm": 5.582308769226074, "learning_rate": 9.977374552360748e-06, "loss": 0.6425, "step": 107050 }, { "epoch": 0.6363868728117885, "grad_norm": 6.167198181152344, "learning_rate": 9.977354831187937e-06, "loss": 0.6449, "step": 107060 }, { "epoch": 0.6364463148884569, "grad_norm": 6.425410270690918, "learning_rate": 9.977335101443526e-06, "loss": 0.5925, "step": 107070 }, { "epoch": 0.6365057569651253, "grad_norm": 4.956577301025391, "learning_rate": 9.977315363127549e-06, "loss": 0.6294, "step": 107080 }, { "epoch": 0.6365651990417938, "grad_norm": 6.6479034423828125, "learning_rate": 9.977295616240042e-06, "loss": 0.6222, "step": 107090 }, { "epoch": 0.6366246411184621, "grad_norm": 8.795347213745117, "learning_rate": 9.977275860781037e-06, "loss": 0.6107, "step": 107100 }, { "epoch": 0.6366840831951305, "grad_norm": 5.457775592803955, "learning_rate": 9.977256096750571e-06, "loss": 0.659, "step": 107110 }, { "epoch": 0.6367435252717989, "grad_norm": 5.8175764083862305, "learning_rate": 9.977236324148675e-06, "loss": 0.606, "step": 107120 }, { "epoch": 0.6368029673484673, "grad_norm": 4.8057379722595215, "learning_rate": 9.977216542975386e-06, "loss": 0.5887, "step": 107130 }, { "epoch": 0.6368624094251357, "grad_norm": 6.41703987121582, "learning_rate": 9.977196753230734e-06, "loss": 0.5841, "step": 107140 }, { "epoch": 0.636921851501804, "grad_norm": 5.466228008270264, "learning_rate": 9.977176954914756e-06, "loss": 0.5888, "step": 107150 }, { "epoch": 0.6369812935784724, "grad_norm": 6.955883026123047, "learning_rate": 9.977157148027485e-06, "loss": 0.5953, "step": 107160 }, { "epoch": 0.6370407356551409, "grad_norm": 5.663442134857178, "learning_rate": 9.977137332568956e-06, "loss": 0.6407, "step": 107170 }, { "epoch": 0.6371001777318093, "grad_norm": 5.819221019744873, "learning_rate": 9.977117508539203e-06, "loss": 0.6337, "step": 107180 }, { "epoch": 0.6371596198084777, "grad_norm": 4.81059455871582, "learning_rate": 9.977097675938258e-06, "loss": 0.6017, "step": 107190 }, { "epoch": 0.637219061885146, "grad_norm": 6.073078632354736, "learning_rate": 9.977077834766159e-06, "loss": 0.5784, "step": 107200 }, { "epoch": 0.6372785039618144, "grad_norm": 6.416568756103516, "learning_rate": 9.977057985022938e-06, "loss": 0.5757, "step": 107210 }, { "epoch": 0.6373379460384828, "grad_norm": 7.628349781036377, "learning_rate": 9.977038126708628e-06, "loss": 0.6007, "step": 107220 }, { "epoch": 0.6373973881151512, "grad_norm": 5.722072601318359, "learning_rate": 9.977018259823266e-06, "loss": 0.6063, "step": 107230 }, { "epoch": 0.6374568301918195, "grad_norm": 5.480625152587891, "learning_rate": 9.976998384366883e-06, "loss": 0.6854, "step": 107240 }, { "epoch": 0.637516272268488, "grad_norm": 5.328851699829102, "learning_rate": 9.976978500339515e-06, "loss": 0.6551, "step": 107250 }, { "epoch": 0.6375757143451564, "grad_norm": 5.207551956176758, "learning_rate": 9.976958607741198e-06, "loss": 0.6138, "step": 107260 }, { "epoch": 0.6376351564218248, "grad_norm": 5.094025611877441, "learning_rate": 9.976938706571964e-06, "loss": 0.6151, "step": 107270 }, { "epoch": 0.6376945984984932, "grad_norm": 5.49714994430542, "learning_rate": 9.976918796831847e-06, "loss": 0.594, "step": 107280 }, { "epoch": 0.6377540405751615, "grad_norm": 7.564488887786865, "learning_rate": 9.976898878520883e-06, "loss": 0.5824, "step": 107290 }, { "epoch": 0.6378134826518299, "grad_norm": 6.221602916717529, "learning_rate": 9.976878951639105e-06, "loss": 0.672, "step": 107300 }, { "epoch": 0.6378729247284983, "grad_norm": 5.098645210266113, "learning_rate": 9.976859016186546e-06, "loss": 0.6011, "step": 107310 }, { "epoch": 0.6379323668051667, "grad_norm": 6.373966693878174, "learning_rate": 9.976839072163242e-06, "loss": 0.6753, "step": 107320 }, { "epoch": 0.637991808881835, "grad_norm": 5.001589298248291, "learning_rate": 9.976819119569229e-06, "loss": 0.5643, "step": 107330 }, { "epoch": 0.6380512509585035, "grad_norm": 6.424357891082764, "learning_rate": 9.97679915840454e-06, "loss": 0.5982, "step": 107340 }, { "epoch": 0.6381106930351719, "grad_norm": 6.087834358215332, "learning_rate": 9.976779188669206e-06, "loss": 0.6755, "step": 107350 }, { "epoch": 0.6381701351118403, "grad_norm": 8.153183937072754, "learning_rate": 9.976759210363267e-06, "loss": 0.5985, "step": 107360 }, { "epoch": 0.6382295771885087, "grad_norm": 6.140818119049072, "learning_rate": 9.976739223486754e-06, "loss": 0.6227, "step": 107370 }, { "epoch": 0.638289019265177, "grad_norm": 6.058974266052246, "learning_rate": 9.976719228039702e-06, "loss": 0.5927, "step": 107380 }, { "epoch": 0.6383484613418454, "grad_norm": 5.177453994750977, "learning_rate": 9.976699224022147e-06, "loss": 0.6353, "step": 107390 }, { "epoch": 0.6384079034185138, "grad_norm": 7.300627708435059, "learning_rate": 9.976679211434121e-06, "loss": 0.5951, "step": 107400 }, { "epoch": 0.6384673454951822, "grad_norm": 5.436773777008057, "learning_rate": 9.976659190275659e-06, "loss": 0.5782, "step": 107410 }, { "epoch": 0.6385267875718507, "grad_norm": 5.364504814147949, "learning_rate": 9.976639160546798e-06, "loss": 0.6536, "step": 107420 }, { "epoch": 0.638586229648519, "grad_norm": 5.745981693267822, "learning_rate": 9.97661912224757e-06, "loss": 0.5919, "step": 107430 }, { "epoch": 0.6386456717251874, "grad_norm": 5.139535903930664, "learning_rate": 9.976599075378008e-06, "loss": 0.5722, "step": 107440 }, { "epoch": 0.6387051138018558, "grad_norm": 6.2679219245910645, "learning_rate": 9.97657901993815e-06, "loss": 0.6451, "step": 107450 }, { "epoch": 0.6387645558785242, "grad_norm": 5.777028560638428, "learning_rate": 9.97655895592803e-06, "loss": 0.6461, "step": 107460 }, { "epoch": 0.6388239979551925, "grad_norm": 5.576754093170166, "learning_rate": 9.976538883347681e-06, "loss": 0.5542, "step": 107470 }, { "epoch": 0.6388834400318609, "grad_norm": 5.15777063369751, "learning_rate": 9.97651880219714e-06, "loss": 0.5962, "step": 107480 }, { "epoch": 0.6389428821085293, "grad_norm": 6.367732048034668, "learning_rate": 9.976498712476437e-06, "loss": 0.6683, "step": 107490 }, { "epoch": 0.6390023241851978, "grad_norm": 4.925444602966309, "learning_rate": 9.97647861418561e-06, "loss": 0.5975, "step": 107500 }, { "epoch": 0.6390617662618662, "grad_norm": 5.815918445587158, "learning_rate": 9.976458507324694e-06, "loss": 0.6989, "step": 107510 }, { "epoch": 0.6391212083385345, "grad_norm": 5.8974690437316895, "learning_rate": 9.97643839189372e-06, "loss": 0.596, "step": 107520 }, { "epoch": 0.6391806504152029, "grad_norm": 6.349067687988281, "learning_rate": 9.976418267892729e-06, "loss": 0.6533, "step": 107530 }, { "epoch": 0.6392400924918713, "grad_norm": 5.500750541687012, "learning_rate": 9.976398135321751e-06, "loss": 0.6445, "step": 107540 }, { "epoch": 0.6392995345685397, "grad_norm": 6.507531642913818, "learning_rate": 9.97637799418082e-06, "loss": 0.6401, "step": 107550 }, { "epoch": 0.6393589766452081, "grad_norm": 5.979669094085693, "learning_rate": 9.976357844469975e-06, "loss": 0.6328, "step": 107560 }, { "epoch": 0.6394184187218764, "grad_norm": 4.711731910705566, "learning_rate": 9.976337686189245e-06, "loss": 0.6242, "step": 107570 }, { "epoch": 0.6394778607985449, "grad_norm": 4.456487655639648, "learning_rate": 9.97631751933867e-06, "loss": 0.6118, "step": 107580 }, { "epoch": 0.6395373028752133, "grad_norm": 4.1590375900268555, "learning_rate": 9.976297343918282e-06, "loss": 0.6234, "step": 107590 }, { "epoch": 0.6395967449518817, "grad_norm": 6.302249908447266, "learning_rate": 9.976277159928116e-06, "loss": 0.6274, "step": 107600 }, { "epoch": 0.63965618702855, "grad_norm": 5.315098762512207, "learning_rate": 9.976256967368207e-06, "loss": 0.6004, "step": 107610 }, { "epoch": 0.6397156291052184, "grad_norm": 6.1184821128845215, "learning_rate": 9.976236766238589e-06, "loss": 0.6254, "step": 107620 }, { "epoch": 0.6397750711818868, "grad_norm": 5.17858362197876, "learning_rate": 9.976216556539298e-06, "loss": 0.5777, "step": 107630 }, { "epoch": 0.6398345132585552, "grad_norm": 5.9637274742126465, "learning_rate": 9.976196338270368e-06, "loss": 0.6498, "step": 107640 }, { "epoch": 0.6398939553352236, "grad_norm": 4.241140842437744, "learning_rate": 9.976176111431835e-06, "loss": 0.6194, "step": 107650 }, { "epoch": 0.6399533974118919, "grad_norm": 5.599837779998779, "learning_rate": 9.976155876023734e-06, "loss": 0.6288, "step": 107660 }, { "epoch": 0.6400128394885604, "grad_norm": 5.430278301239014, "learning_rate": 9.976135632046095e-06, "loss": 0.5696, "step": 107670 }, { "epoch": 0.6400722815652288, "grad_norm": 4.665288925170898, "learning_rate": 9.97611537949896e-06, "loss": 0.6461, "step": 107680 }, { "epoch": 0.6401317236418972, "grad_norm": 6.164339542388916, "learning_rate": 9.97609511838236e-06, "loss": 0.6177, "step": 107690 }, { "epoch": 0.6401911657185655, "grad_norm": 4.27117919921875, "learning_rate": 9.976074848696332e-06, "loss": 0.6684, "step": 107700 }, { "epoch": 0.6402506077952339, "grad_norm": 5.23110818862915, "learning_rate": 9.976054570440906e-06, "loss": 0.5683, "step": 107710 }, { "epoch": 0.6403100498719023, "grad_norm": 6.470372200012207, "learning_rate": 9.976034283616121e-06, "loss": 0.6266, "step": 107720 }, { "epoch": 0.6403694919485707, "grad_norm": 5.284073352813721, "learning_rate": 9.976013988222013e-06, "loss": 0.6243, "step": 107730 }, { "epoch": 0.6404289340252391, "grad_norm": 4.729809284210205, "learning_rate": 9.975993684258614e-06, "loss": 0.5475, "step": 107740 }, { "epoch": 0.6404883761019075, "grad_norm": 6.250574588775635, "learning_rate": 9.97597337172596e-06, "loss": 0.6342, "step": 107750 }, { "epoch": 0.6405478181785759, "grad_norm": 5.945402145385742, "learning_rate": 9.975953050624088e-06, "loss": 0.6418, "step": 107760 }, { "epoch": 0.6406072602552443, "grad_norm": 6.016529560089111, "learning_rate": 9.97593272095303e-06, "loss": 0.6179, "step": 107770 }, { "epoch": 0.6406667023319127, "grad_norm": 4.23896598815918, "learning_rate": 9.97591238271282e-06, "loss": 0.5946, "step": 107780 }, { "epoch": 0.6407261444085811, "grad_norm": 5.191461563110352, "learning_rate": 9.975892035903498e-06, "loss": 0.6446, "step": 107790 }, { "epoch": 0.6407855864852494, "grad_norm": 4.465017795562744, "learning_rate": 9.975871680525095e-06, "loss": 0.5624, "step": 107800 }, { "epoch": 0.6408450285619178, "grad_norm": 6.463846683502197, "learning_rate": 9.975851316577647e-06, "loss": 0.63, "step": 107810 }, { "epoch": 0.6409044706385862, "grad_norm": 4.22607946395874, "learning_rate": 9.97583094406119e-06, "loss": 0.6676, "step": 107820 }, { "epoch": 0.6409639127152547, "grad_norm": 5.926822185516357, "learning_rate": 9.975810562975758e-06, "loss": 0.6137, "step": 107830 }, { "epoch": 0.641023354791923, "grad_norm": 6.121705055236816, "learning_rate": 9.975790173321387e-06, "loss": 0.5659, "step": 107840 }, { "epoch": 0.6410827968685914, "grad_norm": 6.2972283363342285, "learning_rate": 9.975769775098112e-06, "loss": 0.6515, "step": 107850 }, { "epoch": 0.6411422389452598, "grad_norm": 4.488190650939941, "learning_rate": 9.975749368305967e-06, "loss": 0.6184, "step": 107860 }, { "epoch": 0.6412016810219282, "grad_norm": 5.5414557456970215, "learning_rate": 9.975728952944988e-06, "loss": 0.5816, "step": 107870 }, { "epoch": 0.6412611230985966, "grad_norm": 7.2673516273498535, "learning_rate": 9.975708529015208e-06, "loss": 0.6236, "step": 107880 }, { "epoch": 0.6413205651752649, "grad_norm": 6.7213921546936035, "learning_rate": 9.975688096516667e-06, "loss": 0.6592, "step": 107890 }, { "epoch": 0.6413800072519333, "grad_norm": 4.7352705001831055, "learning_rate": 9.975667655449397e-06, "loss": 0.6091, "step": 107900 }, { "epoch": 0.6414394493286018, "grad_norm": 4.821191310882568, "learning_rate": 9.975647205813433e-06, "loss": 0.603, "step": 107910 }, { "epoch": 0.6414988914052702, "grad_norm": 5.142399311065674, "learning_rate": 9.97562674760881e-06, "loss": 0.6087, "step": 107920 }, { "epoch": 0.6415583334819385, "grad_norm": 5.766722679138184, "learning_rate": 9.975606280835566e-06, "loss": 0.6534, "step": 107930 }, { "epoch": 0.6416177755586069, "grad_norm": 5.16287899017334, "learning_rate": 9.975585805493734e-06, "loss": 0.6492, "step": 107940 }, { "epoch": 0.6416772176352753, "grad_norm": 7.587519645690918, "learning_rate": 9.975565321583349e-06, "loss": 0.5552, "step": 107950 }, { "epoch": 0.6417366597119437, "grad_norm": 6.693356990814209, "learning_rate": 9.975544829104446e-06, "loss": 0.5588, "step": 107960 }, { "epoch": 0.6417961017886121, "grad_norm": 4.504642486572266, "learning_rate": 9.975524328057062e-06, "loss": 0.6004, "step": 107970 }, { "epoch": 0.6418555438652804, "grad_norm": 6.395887851715088, "learning_rate": 9.975503818441233e-06, "loss": 0.6384, "step": 107980 }, { "epoch": 0.6419149859419488, "grad_norm": 7.043254852294922, "learning_rate": 9.97548330025699e-06, "loss": 0.6084, "step": 107990 }, { "epoch": 0.6419744280186173, "grad_norm": 5.433444976806641, "learning_rate": 9.975462773504373e-06, "loss": 0.6283, "step": 108000 }, { "epoch": 0.6420338700952857, "grad_norm": 4.948623180389404, "learning_rate": 9.975442238183414e-06, "loss": 0.5906, "step": 108010 }, { "epoch": 0.6420933121719541, "grad_norm": 5.850859642028809, "learning_rate": 9.97542169429415e-06, "loss": 0.6443, "step": 108020 }, { "epoch": 0.6421527542486224, "grad_norm": 6.883115291595459, "learning_rate": 9.975401141836616e-06, "loss": 0.6248, "step": 108030 }, { "epoch": 0.6422121963252908, "grad_norm": 4.982518196105957, "learning_rate": 9.975380580810849e-06, "loss": 0.6057, "step": 108040 }, { "epoch": 0.6422716384019592, "grad_norm": 6.30012845993042, "learning_rate": 9.975360011216883e-06, "loss": 0.5996, "step": 108050 }, { "epoch": 0.6423310804786276, "grad_norm": 5.248291969299316, "learning_rate": 9.975339433054752e-06, "loss": 0.6105, "step": 108060 }, { "epoch": 0.6423905225552959, "grad_norm": 6.730161190032959, "learning_rate": 9.975318846324492e-06, "loss": 0.6918, "step": 108070 }, { "epoch": 0.6424499646319644, "grad_norm": 6.688573360443115, "learning_rate": 9.975298251026143e-06, "loss": 0.6174, "step": 108080 }, { "epoch": 0.6425094067086328, "grad_norm": 5.393538951873779, "learning_rate": 9.975277647159734e-06, "loss": 0.6414, "step": 108090 }, { "epoch": 0.6425688487853012, "grad_norm": 6.057791709899902, "learning_rate": 9.975257034725303e-06, "loss": 0.6139, "step": 108100 }, { "epoch": 0.6426282908619696, "grad_norm": 4.420462131500244, "learning_rate": 9.975236413722888e-06, "loss": 0.5759, "step": 108110 }, { "epoch": 0.6426877329386379, "grad_norm": 5.043269634246826, "learning_rate": 9.975215784152521e-06, "loss": 0.6244, "step": 108120 }, { "epoch": 0.6427471750153063, "grad_norm": 6.650594711303711, "learning_rate": 9.975195146014238e-06, "loss": 0.6316, "step": 108130 }, { "epoch": 0.6428066170919747, "grad_norm": 5.151389122009277, "learning_rate": 9.975174499308075e-06, "loss": 0.5917, "step": 108140 }, { "epoch": 0.6428660591686431, "grad_norm": 7.7442545890808105, "learning_rate": 9.975153844034068e-06, "loss": 0.6091, "step": 108150 }, { "epoch": 0.6429255012453116, "grad_norm": 6.9343695640563965, "learning_rate": 9.975133180192255e-06, "loss": 0.6024, "step": 108160 }, { "epoch": 0.6429849433219799, "grad_norm": 6.6825337409973145, "learning_rate": 9.975112507782667e-06, "loss": 0.6126, "step": 108170 }, { "epoch": 0.6430443853986483, "grad_norm": 6.4932732582092285, "learning_rate": 9.975091826805342e-06, "loss": 0.6199, "step": 108180 }, { "epoch": 0.6431038274753167, "grad_norm": 5.553630352020264, "learning_rate": 9.975071137260315e-06, "loss": 0.5614, "step": 108190 }, { "epoch": 0.6431632695519851, "grad_norm": 9.187067985534668, "learning_rate": 9.975050439147622e-06, "loss": 0.6321, "step": 108200 }, { "epoch": 0.6432227116286534, "grad_norm": 5.249214172363281, "learning_rate": 9.975029732467299e-06, "loss": 0.6513, "step": 108210 }, { "epoch": 0.6432821537053218, "grad_norm": 7.850127696990967, "learning_rate": 9.975009017219382e-06, "loss": 0.5504, "step": 108220 }, { "epoch": 0.6433415957819902, "grad_norm": 5.518561840057373, "learning_rate": 9.974988293403904e-06, "loss": 0.6165, "step": 108230 }, { "epoch": 0.6434010378586587, "grad_norm": 5.448699951171875, "learning_rate": 9.974967561020904e-06, "loss": 0.5993, "step": 108240 }, { "epoch": 0.6434604799353271, "grad_norm": 4.646036148071289, "learning_rate": 9.974946820070416e-06, "loss": 0.6063, "step": 108250 }, { "epoch": 0.6435199220119954, "grad_norm": 6.156940460205078, "learning_rate": 9.974926070552474e-06, "loss": 0.622, "step": 108260 }, { "epoch": 0.6435793640886638, "grad_norm": 5.6973347663879395, "learning_rate": 9.974905312467117e-06, "loss": 0.5807, "step": 108270 }, { "epoch": 0.6436388061653322, "grad_norm": 4.259112358093262, "learning_rate": 9.97488454581438e-06, "loss": 0.6192, "step": 108280 }, { "epoch": 0.6436982482420006, "grad_norm": 6.731112480163574, "learning_rate": 9.974863770594297e-06, "loss": 0.5929, "step": 108290 }, { "epoch": 0.6437576903186689, "grad_norm": 5.441840648651123, "learning_rate": 9.974842986806907e-06, "loss": 0.5797, "step": 108300 }, { "epoch": 0.6438171323953373, "grad_norm": 6.356419563293457, "learning_rate": 9.974822194452242e-06, "loss": 0.6657, "step": 108310 }, { "epoch": 0.6438765744720057, "grad_norm": 4.686530113220215, "learning_rate": 9.97480139353034e-06, "loss": 0.6028, "step": 108320 }, { "epoch": 0.6439360165486742, "grad_norm": 7.106842041015625, "learning_rate": 9.974780584041237e-06, "loss": 0.6556, "step": 108330 }, { "epoch": 0.6439954586253426, "grad_norm": 6.232601642608643, "learning_rate": 9.974759765984967e-06, "loss": 0.5745, "step": 108340 }, { "epoch": 0.6440549007020109, "grad_norm": 5.588386058807373, "learning_rate": 9.974738939361568e-06, "loss": 0.5847, "step": 108350 }, { "epoch": 0.6441143427786793, "grad_norm": 5.234714031219482, "learning_rate": 9.974718104171075e-06, "loss": 0.568, "step": 108360 }, { "epoch": 0.6441737848553477, "grad_norm": 5.379143238067627, "learning_rate": 9.974697260413523e-06, "loss": 0.6151, "step": 108370 }, { "epoch": 0.6442332269320161, "grad_norm": 4.220949172973633, "learning_rate": 9.974676408088952e-06, "loss": 0.6189, "step": 108380 }, { "epoch": 0.6442926690086845, "grad_norm": 5.291706562042236, "learning_rate": 9.974655547197392e-06, "loss": 0.6827, "step": 108390 }, { "epoch": 0.6443521110853528, "grad_norm": 4.994335174560547, "learning_rate": 9.974634677738882e-06, "loss": 0.6247, "step": 108400 }, { "epoch": 0.6444115531620213, "grad_norm": 7.227522373199463, "learning_rate": 9.974613799713457e-06, "loss": 0.5609, "step": 108410 }, { "epoch": 0.6444709952386897, "grad_norm": 6.643775463104248, "learning_rate": 9.974592913121152e-06, "loss": 0.6384, "step": 108420 }, { "epoch": 0.6445304373153581, "grad_norm": 5.973942279815674, "learning_rate": 9.974572017962007e-06, "loss": 0.6558, "step": 108430 }, { "epoch": 0.6445898793920264, "grad_norm": 5.32966423034668, "learning_rate": 9.974551114236056e-06, "loss": 0.6531, "step": 108440 }, { "epoch": 0.6446493214686948, "grad_norm": 5.6672868728637695, "learning_rate": 9.974530201943332e-06, "loss": 0.6397, "step": 108450 }, { "epoch": 0.6447087635453632, "grad_norm": 6.061098098754883, "learning_rate": 9.974509281083876e-06, "loss": 0.6294, "step": 108460 }, { "epoch": 0.6447682056220316, "grad_norm": 6.104444980621338, "learning_rate": 9.974488351657718e-06, "loss": 0.6143, "step": 108470 }, { "epoch": 0.6448276476987, "grad_norm": 6.299942493438721, "learning_rate": 9.974467413664902e-06, "loss": 0.6337, "step": 108480 }, { "epoch": 0.6448870897753683, "grad_norm": 6.051207542419434, "learning_rate": 9.974446467105455e-06, "loss": 0.6167, "step": 108490 }, { "epoch": 0.6449465318520368, "grad_norm": 5.91170597076416, "learning_rate": 9.97442551197942e-06, "loss": 0.6298, "step": 108500 }, { "epoch": 0.6450059739287052, "grad_norm": 5.230356216430664, "learning_rate": 9.97440454828683e-06, "loss": 0.5789, "step": 108510 }, { "epoch": 0.6450654160053736, "grad_norm": 6.449604511260986, "learning_rate": 9.974383576027723e-06, "loss": 0.6371, "step": 108520 }, { "epoch": 0.645124858082042, "grad_norm": 7.013922214508057, "learning_rate": 9.974362595202134e-06, "loss": 0.6103, "step": 108530 }, { "epoch": 0.6451843001587103, "grad_norm": 6.552127361297607, "learning_rate": 9.974341605810098e-06, "loss": 0.6526, "step": 108540 }, { "epoch": 0.6452437422353787, "grad_norm": 4.701624870300293, "learning_rate": 9.974320607851651e-06, "loss": 0.5913, "step": 108550 }, { "epoch": 0.6453031843120471, "grad_norm": 6.390176773071289, "learning_rate": 9.974299601326834e-06, "loss": 0.5687, "step": 108560 }, { "epoch": 0.6453626263887156, "grad_norm": 5.070361614227295, "learning_rate": 9.974278586235677e-06, "loss": 0.6424, "step": 108570 }, { "epoch": 0.6454220684653839, "grad_norm": 7.969666481018066, "learning_rate": 9.974257562578219e-06, "loss": 0.668, "step": 108580 }, { "epoch": 0.6454815105420523, "grad_norm": 5.132351398468018, "learning_rate": 9.974236530354495e-06, "loss": 0.6075, "step": 108590 }, { "epoch": 0.6455409526187207, "grad_norm": 6.812358379364014, "learning_rate": 9.974215489564545e-06, "loss": 0.631, "step": 108600 }, { "epoch": 0.6456003946953891, "grad_norm": 6.5088653564453125, "learning_rate": 9.9741944402084e-06, "loss": 0.66, "step": 108610 }, { "epoch": 0.6456598367720575, "grad_norm": 5.669508934020996, "learning_rate": 9.9741733822861e-06, "loss": 0.5517, "step": 108620 }, { "epoch": 0.6457192788487258, "grad_norm": 7.50004243850708, "learning_rate": 9.97415231579768e-06, "loss": 0.6565, "step": 108630 }, { "epoch": 0.6457787209253942, "grad_norm": 4.81680965423584, "learning_rate": 9.974131240743174e-06, "loss": 0.6196, "step": 108640 }, { "epoch": 0.6458381630020626, "grad_norm": 6.042427062988281, "learning_rate": 9.974110157122624e-06, "loss": 0.6118, "step": 108650 }, { "epoch": 0.6458976050787311, "grad_norm": 4.915243625640869, "learning_rate": 9.97408906493606e-06, "loss": 0.6062, "step": 108660 }, { "epoch": 0.6459570471553994, "grad_norm": 5.016646862030029, "learning_rate": 9.974067964183523e-06, "loss": 0.5753, "step": 108670 }, { "epoch": 0.6460164892320678, "grad_norm": 6.2379150390625, "learning_rate": 9.974046854865045e-06, "loss": 0.6236, "step": 108680 }, { "epoch": 0.6460759313087362, "grad_norm": 4.458433628082275, "learning_rate": 9.974025736980667e-06, "loss": 0.6627, "step": 108690 }, { "epoch": 0.6461353733854046, "grad_norm": 5.7617926597595215, "learning_rate": 9.974004610530422e-06, "loss": 0.5966, "step": 108700 }, { "epoch": 0.646194815462073, "grad_norm": 4.687971591949463, "learning_rate": 9.973983475514349e-06, "loss": 0.6061, "step": 108710 }, { "epoch": 0.6462542575387413, "grad_norm": 4.995506763458252, "learning_rate": 9.97396233193248e-06, "loss": 0.5964, "step": 108720 }, { "epoch": 0.6463136996154097, "grad_norm": 6.097875118255615, "learning_rate": 9.973941179784859e-06, "loss": 0.6142, "step": 108730 }, { "epoch": 0.6463731416920782, "grad_norm": 6.614978790283203, "learning_rate": 9.973920019071515e-06, "loss": 0.6629, "step": 108740 }, { "epoch": 0.6464325837687466, "grad_norm": 5.987681865692139, "learning_rate": 9.973898849792486e-06, "loss": 0.6431, "step": 108750 }, { "epoch": 0.646492025845415, "grad_norm": 5.961376667022705, "learning_rate": 9.973877671947812e-06, "loss": 0.6008, "step": 108760 }, { "epoch": 0.6465514679220833, "grad_norm": 7.371917724609375, "learning_rate": 9.973856485537526e-06, "loss": 0.5798, "step": 108770 }, { "epoch": 0.6466109099987517, "grad_norm": 6.989495754241943, "learning_rate": 9.973835290561666e-06, "loss": 0.6299, "step": 108780 }, { "epoch": 0.6466703520754201, "grad_norm": 7.1696343421936035, "learning_rate": 9.973814087020268e-06, "loss": 0.6574, "step": 108790 }, { "epoch": 0.6467297941520885, "grad_norm": 5.120508193969727, "learning_rate": 9.97379287491337e-06, "loss": 0.584, "step": 108800 }, { "epoch": 0.6467892362287568, "grad_norm": 6.114433765411377, "learning_rate": 9.973771654241006e-06, "loss": 0.621, "step": 108810 }, { "epoch": 0.6468486783054253, "grad_norm": 7.961668014526367, "learning_rate": 9.973750425003212e-06, "loss": 0.6398, "step": 108820 }, { "epoch": 0.6469081203820937, "grad_norm": 6.9505414962768555, "learning_rate": 9.97372918720003e-06, "loss": 0.6553, "step": 108830 }, { "epoch": 0.6469675624587621, "grad_norm": 5.949306488037109, "learning_rate": 9.97370794083149e-06, "loss": 0.5533, "step": 108840 }, { "epoch": 0.6470270045354305, "grad_norm": 6.394228935241699, "learning_rate": 9.973686685897632e-06, "loss": 0.6183, "step": 108850 }, { "epoch": 0.6470864466120988, "grad_norm": 6.855344295501709, "learning_rate": 9.973665422398493e-06, "loss": 0.608, "step": 108860 }, { "epoch": 0.6471458886887672, "grad_norm": 5.858620643615723, "learning_rate": 9.973644150334109e-06, "loss": 0.6104, "step": 108870 }, { "epoch": 0.6472053307654356, "grad_norm": 7.357481002807617, "learning_rate": 9.973622869704515e-06, "loss": 0.6089, "step": 108880 }, { "epoch": 0.647264772842104, "grad_norm": 5.402819633483887, "learning_rate": 9.973601580509751e-06, "loss": 0.5964, "step": 108890 }, { "epoch": 0.6473242149187725, "grad_norm": 7.073955059051514, "learning_rate": 9.973580282749848e-06, "loss": 0.6231, "step": 108900 }, { "epoch": 0.6473836569954408, "grad_norm": 7.4668755531311035, "learning_rate": 9.97355897642485e-06, "loss": 0.6417, "step": 108910 }, { "epoch": 0.6474430990721092, "grad_norm": 6.34226655960083, "learning_rate": 9.973537661534788e-06, "loss": 0.6124, "step": 108920 }, { "epoch": 0.6475025411487776, "grad_norm": 4.888415336608887, "learning_rate": 9.973516338079702e-06, "loss": 0.6213, "step": 108930 }, { "epoch": 0.647561983225446, "grad_norm": 6.882092475891113, "learning_rate": 9.973495006059626e-06, "loss": 0.6056, "step": 108940 }, { "epoch": 0.6476214253021143, "grad_norm": 6.501294136047363, "learning_rate": 9.9734736654746e-06, "loss": 0.6379, "step": 108950 }, { "epoch": 0.6476808673787827, "grad_norm": 4.621378421783447, "learning_rate": 9.973452316324656e-06, "loss": 0.5951, "step": 108960 }, { "epoch": 0.6477403094554511, "grad_norm": 6.690181732177734, "learning_rate": 9.973430958609837e-06, "loss": 0.6218, "step": 108970 }, { "epoch": 0.6477997515321195, "grad_norm": 7.194764137268066, "learning_rate": 9.973409592330174e-06, "loss": 0.5874, "step": 108980 }, { "epoch": 0.647859193608788, "grad_norm": 6.107264995574951, "learning_rate": 9.973388217485708e-06, "loss": 0.6128, "step": 108990 }, { "epoch": 0.6479186356854563, "grad_norm": 6.1557207107543945, "learning_rate": 9.973366834076473e-06, "loss": 0.6311, "step": 109000 }, { "epoch": 0.6479780777621247, "grad_norm": 5.172791481018066, "learning_rate": 9.973345442102507e-06, "loss": 0.5906, "step": 109010 }, { "epoch": 0.6480375198387931, "grad_norm": 6.969376564025879, "learning_rate": 9.973324041563848e-06, "loss": 0.6258, "step": 109020 }, { "epoch": 0.6480969619154615, "grad_norm": 6.089844703674316, "learning_rate": 9.973302632460529e-06, "loss": 0.6011, "step": 109030 }, { "epoch": 0.6481564039921298, "grad_norm": 6.182820796966553, "learning_rate": 9.973281214792591e-06, "loss": 0.5932, "step": 109040 }, { "epoch": 0.6482158460687982, "grad_norm": 4.848046779632568, "learning_rate": 9.97325978856007e-06, "loss": 0.629, "step": 109050 }, { "epoch": 0.6482752881454666, "grad_norm": 5.608248710632324, "learning_rate": 9.973238353763002e-06, "loss": 0.6075, "step": 109060 }, { "epoch": 0.6483347302221351, "grad_norm": 5.211050510406494, "learning_rate": 9.973216910401424e-06, "loss": 0.5751, "step": 109070 }, { "epoch": 0.6483941722988035, "grad_norm": 6.3562092781066895, "learning_rate": 9.973195458475373e-06, "loss": 0.589, "step": 109080 }, { "epoch": 0.6484536143754718, "grad_norm": 8.37463092803955, "learning_rate": 9.973173997984883e-06, "loss": 0.6865, "step": 109090 }, { "epoch": 0.6485130564521402, "grad_norm": 5.768848896026611, "learning_rate": 9.973152528929998e-06, "loss": 0.6253, "step": 109100 }, { "epoch": 0.6485724985288086, "grad_norm": 4.1043219566345215, "learning_rate": 9.97313105131075e-06, "loss": 0.6103, "step": 109110 }, { "epoch": 0.648631940605477, "grad_norm": 6.218943119049072, "learning_rate": 9.973109565127176e-06, "loss": 0.6466, "step": 109120 }, { "epoch": 0.6486913826821454, "grad_norm": 6.00140380859375, "learning_rate": 9.973088070379315e-06, "loss": 0.6321, "step": 109130 }, { "epoch": 0.6487508247588137, "grad_norm": 5.90802001953125, "learning_rate": 9.973066567067203e-06, "loss": 0.6197, "step": 109140 }, { "epoch": 0.6488102668354822, "grad_norm": 6.891462802886963, "learning_rate": 9.973045055190877e-06, "loss": 0.6116, "step": 109150 }, { "epoch": 0.6488697089121506, "grad_norm": 5.635502338409424, "learning_rate": 9.973023534750374e-06, "loss": 0.6566, "step": 109160 }, { "epoch": 0.648929150988819, "grad_norm": 4.2492170333862305, "learning_rate": 9.97300200574573e-06, "loss": 0.655, "step": 109170 }, { "epoch": 0.6489885930654873, "grad_norm": 5.055135726928711, "learning_rate": 9.972980468176985e-06, "loss": 0.5698, "step": 109180 }, { "epoch": 0.6490480351421557, "grad_norm": 6.139005184173584, "learning_rate": 9.972958922044172e-06, "loss": 0.6648, "step": 109190 }, { "epoch": 0.6491074772188241, "grad_norm": 5.7153754234313965, "learning_rate": 9.972937367347332e-06, "loss": 0.6387, "step": 109200 }, { "epoch": 0.6491669192954925, "grad_norm": 5.508600234985352, "learning_rate": 9.9729158040865e-06, "loss": 0.6423, "step": 109210 }, { "epoch": 0.6492263613721609, "grad_norm": 4.994969367980957, "learning_rate": 9.972894232261714e-06, "loss": 0.569, "step": 109220 }, { "epoch": 0.6492858034488292, "grad_norm": 5.144043922424316, "learning_rate": 9.972872651873011e-06, "loss": 0.6455, "step": 109230 }, { "epoch": 0.6493452455254977, "grad_norm": 12.39045524597168, "learning_rate": 9.972851062920426e-06, "loss": 0.6511, "step": 109240 }, { "epoch": 0.6494046876021661, "grad_norm": 5.208439350128174, "learning_rate": 9.972829465404001e-06, "loss": 0.5628, "step": 109250 }, { "epoch": 0.6494641296788345, "grad_norm": 6.534775733947754, "learning_rate": 9.972807859323768e-06, "loss": 0.5674, "step": 109260 }, { "epoch": 0.6495235717555029, "grad_norm": 6.301655292510986, "learning_rate": 9.972786244679769e-06, "loss": 0.6996, "step": 109270 }, { "epoch": 0.6495830138321712, "grad_norm": 6.105518817901611, "learning_rate": 9.972764621472034e-06, "loss": 0.6427, "step": 109280 }, { "epoch": 0.6496424559088396, "grad_norm": 5.79006290435791, "learning_rate": 9.97274298970061e-06, "loss": 0.6442, "step": 109290 }, { "epoch": 0.649701897985508, "grad_norm": 5.080008029937744, "learning_rate": 9.972721349365527e-06, "loss": 0.5764, "step": 109300 }, { "epoch": 0.6497613400621765, "grad_norm": 6.547328948974609, "learning_rate": 9.972699700466826e-06, "loss": 0.6432, "step": 109310 }, { "epoch": 0.6498207821388448, "grad_norm": 5.839320659637451, "learning_rate": 9.97267804300454e-06, "loss": 0.6193, "step": 109320 }, { "epoch": 0.6498802242155132, "grad_norm": 4.987525939941406, "learning_rate": 9.972656376978711e-06, "loss": 0.5836, "step": 109330 }, { "epoch": 0.6499396662921816, "grad_norm": 6.493414402008057, "learning_rate": 9.972634702389374e-06, "loss": 0.6651, "step": 109340 }, { "epoch": 0.64999910836885, "grad_norm": 6.195946216583252, "learning_rate": 9.972613019236568e-06, "loss": 0.6522, "step": 109350 }, { "epoch": 0.6500585504455184, "grad_norm": 8.103215217590332, "learning_rate": 9.972591327520326e-06, "loss": 0.6323, "step": 109360 }, { "epoch": 0.6501179925221867, "grad_norm": 5.7612786293029785, "learning_rate": 9.972569627240691e-06, "loss": 0.6644, "step": 109370 }, { "epoch": 0.6501774345988551, "grad_norm": 4.976672649383545, "learning_rate": 9.972547918397697e-06, "loss": 0.5599, "step": 109380 }, { "epoch": 0.6502368766755235, "grad_norm": 6.897282123565674, "learning_rate": 9.972526200991382e-06, "loss": 0.5915, "step": 109390 }, { "epoch": 0.650296318752192, "grad_norm": 5.481313705444336, "learning_rate": 9.972504475021785e-06, "loss": 0.608, "step": 109400 }, { "epoch": 0.6503557608288603, "grad_norm": 5.781213760375977, "learning_rate": 9.97248274048894e-06, "loss": 0.5524, "step": 109410 }, { "epoch": 0.6504152029055287, "grad_norm": 4.773552894592285, "learning_rate": 9.972460997392888e-06, "loss": 0.5863, "step": 109420 }, { "epoch": 0.6504746449821971, "grad_norm": 6.756135940551758, "learning_rate": 9.972439245733663e-06, "loss": 0.6075, "step": 109430 }, { "epoch": 0.6505340870588655, "grad_norm": 4.3245720863342285, "learning_rate": 9.972417485511306e-06, "loss": 0.6089, "step": 109440 }, { "epoch": 0.6505935291355339, "grad_norm": 5.699244022369385, "learning_rate": 9.972395716725852e-06, "loss": 0.62, "step": 109450 }, { "epoch": 0.6506529712122022, "grad_norm": 7.500112056732178, "learning_rate": 9.97237393937734e-06, "loss": 0.6365, "step": 109460 }, { "epoch": 0.6507124132888706, "grad_norm": 6.738619327545166, "learning_rate": 9.972352153465805e-06, "loss": 0.6665, "step": 109470 }, { "epoch": 0.650771855365539, "grad_norm": 5.224715709686279, "learning_rate": 9.972330358991289e-06, "loss": 0.6474, "step": 109480 }, { "epoch": 0.6508312974422075, "grad_norm": 5.435254096984863, "learning_rate": 9.972308555953825e-06, "loss": 0.6047, "step": 109490 }, { "epoch": 0.6508907395188759, "grad_norm": 5.181103706359863, "learning_rate": 9.972286744353453e-06, "loss": 0.6091, "step": 109500 }, { "epoch": 0.6509501815955442, "grad_norm": 5.518545150756836, "learning_rate": 9.97226492419021e-06, "loss": 0.6091, "step": 109510 }, { "epoch": 0.6510096236722126, "grad_norm": 5.212100028991699, "learning_rate": 9.972243095464132e-06, "loss": 0.6689, "step": 109520 }, { "epoch": 0.651069065748881, "grad_norm": 4.350553512573242, "learning_rate": 9.97222125817526e-06, "loss": 0.596, "step": 109530 }, { "epoch": 0.6511285078255494, "grad_norm": 6.417434215545654, "learning_rate": 9.97219941232363e-06, "loss": 0.596, "step": 109540 }, { "epoch": 0.6511879499022177, "grad_norm": 6.721778869628906, "learning_rate": 9.972177557909277e-06, "loss": 0.5853, "step": 109550 }, { "epoch": 0.6512473919788861, "grad_norm": 5.2875657081604, "learning_rate": 9.972155694932242e-06, "loss": 0.6264, "step": 109560 }, { "epoch": 0.6513068340555546, "grad_norm": 6.047140121459961, "learning_rate": 9.972133823392562e-06, "loss": 0.5544, "step": 109570 }, { "epoch": 0.651366276132223, "grad_norm": 5.555693626403809, "learning_rate": 9.972111943290275e-06, "loss": 0.5982, "step": 109580 }, { "epoch": 0.6514257182088914, "grad_norm": 4.729365825653076, "learning_rate": 9.972090054625416e-06, "loss": 0.6057, "step": 109590 }, { "epoch": 0.6514851602855597, "grad_norm": 5.909259796142578, "learning_rate": 9.972068157398027e-06, "loss": 0.5791, "step": 109600 }, { "epoch": 0.6515446023622281, "grad_norm": 5.480055332183838, "learning_rate": 9.972046251608143e-06, "loss": 0.6049, "step": 109610 }, { "epoch": 0.6516040444388965, "grad_norm": 4.333907604217529, "learning_rate": 9.972024337255801e-06, "loss": 0.5825, "step": 109620 }, { "epoch": 0.6516634865155649, "grad_norm": 5.943378925323486, "learning_rate": 9.97200241434104e-06, "loss": 0.6083, "step": 109630 }, { "epoch": 0.6517229285922334, "grad_norm": 5.930875778198242, "learning_rate": 9.971980482863897e-06, "loss": 0.7067, "step": 109640 }, { "epoch": 0.6517823706689017, "grad_norm": 5.398935317993164, "learning_rate": 9.971958542824412e-06, "loss": 0.6145, "step": 109650 }, { "epoch": 0.6518418127455701, "grad_norm": 7.070586681365967, "learning_rate": 9.97193659422262e-06, "loss": 0.6229, "step": 109660 }, { "epoch": 0.6519012548222385, "grad_norm": 6.056182861328125, "learning_rate": 9.97191463705856e-06, "loss": 0.6072, "step": 109670 }, { "epoch": 0.6519606968989069, "grad_norm": 5.913290977478027, "learning_rate": 9.971892671332271e-06, "loss": 0.6406, "step": 109680 }, { "epoch": 0.6520201389755752, "grad_norm": 6.250667572021484, "learning_rate": 9.971870697043788e-06, "loss": 0.6169, "step": 109690 }, { "epoch": 0.6520795810522436, "grad_norm": 7.798532962799072, "learning_rate": 9.971848714193151e-06, "loss": 0.6055, "step": 109700 }, { "epoch": 0.652139023128912, "grad_norm": 5.141538619995117, "learning_rate": 9.971826722780398e-06, "loss": 0.5545, "step": 109710 }, { "epoch": 0.6521984652055804, "grad_norm": 4.75859260559082, "learning_rate": 9.971804722805565e-06, "loss": 0.6676, "step": 109720 }, { "epoch": 0.6522579072822489, "grad_norm": 6.490810871124268, "learning_rate": 9.971782714268692e-06, "loss": 0.6243, "step": 109730 }, { "epoch": 0.6523173493589172, "grad_norm": 5.729179382324219, "learning_rate": 9.971760697169814e-06, "loss": 0.5798, "step": 109740 }, { "epoch": 0.6523767914355856, "grad_norm": 5.644791603088379, "learning_rate": 9.971738671508973e-06, "loss": 0.7269, "step": 109750 }, { "epoch": 0.652436233512254, "grad_norm": 5.643774032592773, "learning_rate": 9.971716637286204e-06, "loss": 0.6108, "step": 109760 }, { "epoch": 0.6524956755889224, "grad_norm": 5.000288486480713, "learning_rate": 9.971694594501546e-06, "loss": 0.619, "step": 109770 }, { "epoch": 0.6525551176655907, "grad_norm": 5.908170700073242, "learning_rate": 9.971672543155037e-06, "loss": 0.6098, "step": 109780 }, { "epoch": 0.6526145597422591, "grad_norm": 7.919151782989502, "learning_rate": 9.971650483246713e-06, "loss": 0.5981, "step": 109790 }, { "epoch": 0.6526740018189275, "grad_norm": 7.248544692993164, "learning_rate": 9.971628414776614e-06, "loss": 0.6275, "step": 109800 }, { "epoch": 0.652733443895596, "grad_norm": 4.691642761230469, "learning_rate": 9.97160633774478e-06, "loss": 0.6868, "step": 109810 }, { "epoch": 0.6527928859722644, "grad_norm": 6.421988010406494, "learning_rate": 9.971584252151245e-06, "loss": 0.6249, "step": 109820 }, { "epoch": 0.6528523280489327, "grad_norm": 5.990609169006348, "learning_rate": 9.971562157996048e-06, "loss": 0.6075, "step": 109830 }, { "epoch": 0.6529117701256011, "grad_norm": 5.618633270263672, "learning_rate": 9.971540055279229e-06, "loss": 0.5692, "step": 109840 }, { "epoch": 0.6529712122022695, "grad_norm": 6.012698173522949, "learning_rate": 9.971517944000826e-06, "loss": 0.6355, "step": 109850 }, { "epoch": 0.6530306542789379, "grad_norm": 7.562668323516846, "learning_rate": 9.971495824160875e-06, "loss": 0.6769, "step": 109860 }, { "epoch": 0.6530900963556063, "grad_norm": 3.689432382583618, "learning_rate": 9.971473695759413e-06, "loss": 0.635, "step": 109870 }, { "epoch": 0.6531495384322746, "grad_norm": 5.401052474975586, "learning_rate": 9.97145155879648e-06, "loss": 0.5734, "step": 109880 }, { "epoch": 0.653208980508943, "grad_norm": 7.034392833709717, "learning_rate": 9.971429413272118e-06, "loss": 0.6023, "step": 109890 }, { "epoch": 0.6532684225856115, "grad_norm": 5.7785964012146, "learning_rate": 9.97140725918636e-06, "loss": 0.6285, "step": 109900 }, { "epoch": 0.6533278646622799, "grad_norm": 6.507995128631592, "learning_rate": 9.971385096539243e-06, "loss": 0.6537, "step": 109910 }, { "epoch": 0.6533873067389482, "grad_norm": 6.07236909866333, "learning_rate": 9.97136292533081e-06, "loss": 0.6083, "step": 109920 }, { "epoch": 0.6534467488156166, "grad_norm": 6.170456409454346, "learning_rate": 9.971340745561095e-06, "loss": 0.7082, "step": 109930 }, { "epoch": 0.653506190892285, "grad_norm": 5.206078052520752, "learning_rate": 9.971318557230141e-06, "loss": 0.6175, "step": 109940 }, { "epoch": 0.6535656329689534, "grad_norm": 5.776861190795898, "learning_rate": 9.971296360337981e-06, "loss": 0.6268, "step": 109950 }, { "epoch": 0.6536250750456218, "grad_norm": 5.471405982971191, "learning_rate": 9.971274154884656e-06, "loss": 0.6344, "step": 109960 }, { "epoch": 0.6536845171222901, "grad_norm": 4.801515579223633, "learning_rate": 9.971251940870203e-06, "loss": 0.6568, "step": 109970 }, { "epoch": 0.6537439591989586, "grad_norm": 5.150103569030762, "learning_rate": 9.971229718294662e-06, "loss": 0.6576, "step": 109980 }, { "epoch": 0.653803401275627, "grad_norm": 5.701922416687012, "learning_rate": 9.97120748715807e-06, "loss": 0.5968, "step": 109990 }, { "epoch": 0.6538628433522954, "grad_norm": 4.202035427093506, "learning_rate": 9.971185247460466e-06, "loss": 0.5858, "step": 110000 }, { "epoch": 0.6539222854289638, "grad_norm": 5.035439968109131, "learning_rate": 9.971162999201887e-06, "loss": 0.5913, "step": 110010 }, { "epoch": 0.6539817275056321, "grad_norm": 8.213074684143066, "learning_rate": 9.971140742382373e-06, "loss": 0.6059, "step": 110020 }, { "epoch": 0.6540411695823005, "grad_norm": 4.771699905395508, "learning_rate": 9.971118477001962e-06, "loss": 0.6249, "step": 110030 }, { "epoch": 0.6541006116589689, "grad_norm": 4.53513765335083, "learning_rate": 9.97109620306069e-06, "loss": 0.5919, "step": 110040 }, { "epoch": 0.6541600537356373, "grad_norm": 5.4839677810668945, "learning_rate": 9.971073920558598e-06, "loss": 0.6485, "step": 110050 }, { "epoch": 0.6542194958123057, "grad_norm": 4.646981239318848, "learning_rate": 9.971051629495724e-06, "loss": 0.5686, "step": 110060 }, { "epoch": 0.6542789378889741, "grad_norm": 5.098920822143555, "learning_rate": 9.971029329872107e-06, "loss": 0.5678, "step": 110070 }, { "epoch": 0.6543383799656425, "grad_norm": 6.840834617614746, "learning_rate": 9.971007021687781e-06, "loss": 0.6267, "step": 110080 }, { "epoch": 0.6543978220423109, "grad_norm": 4.605380058288574, "learning_rate": 9.97098470494279e-06, "loss": 0.5364, "step": 110090 }, { "epoch": 0.6544572641189793, "grad_norm": 7.202561855316162, "learning_rate": 9.970962379637171e-06, "loss": 0.6128, "step": 110100 }, { "epoch": 0.6545167061956476, "grad_norm": 8.153602600097656, "learning_rate": 9.970940045770961e-06, "loss": 0.6055, "step": 110110 }, { "epoch": 0.654576148272316, "grad_norm": 5.535349369049072, "learning_rate": 9.970917703344199e-06, "loss": 0.6877, "step": 110120 }, { "epoch": 0.6546355903489844, "grad_norm": 6.29263162612915, "learning_rate": 9.970895352356923e-06, "loss": 0.6265, "step": 110130 }, { "epoch": 0.6546950324256529, "grad_norm": 4.8441033363342285, "learning_rate": 9.970872992809172e-06, "loss": 0.6452, "step": 110140 }, { "epoch": 0.6547544745023212, "grad_norm": 6.135265350341797, "learning_rate": 9.970850624700984e-06, "loss": 0.6766, "step": 110150 }, { "epoch": 0.6548139165789896, "grad_norm": 5.804435729980469, "learning_rate": 9.9708282480324e-06, "loss": 0.5932, "step": 110160 }, { "epoch": 0.654873358655658, "grad_norm": 5.131272315979004, "learning_rate": 9.970805862803457e-06, "loss": 0.6718, "step": 110170 }, { "epoch": 0.6549328007323264, "grad_norm": 4.8163557052612305, "learning_rate": 9.97078346901419e-06, "loss": 0.602, "step": 110180 }, { "epoch": 0.6549922428089948, "grad_norm": 6.596747398376465, "learning_rate": 9.970761066664645e-06, "loss": 0.6202, "step": 110190 }, { "epoch": 0.6550516848856631, "grad_norm": 5.897409439086914, "learning_rate": 9.970738655754854e-06, "loss": 0.6242, "step": 110200 }, { "epoch": 0.6551111269623315, "grad_norm": 6.907264232635498, "learning_rate": 9.970716236284858e-06, "loss": 0.6767, "step": 110210 }, { "epoch": 0.655170569039, "grad_norm": 7.5263824462890625, "learning_rate": 9.970693808254695e-06, "loss": 0.6039, "step": 110220 }, { "epoch": 0.6552300111156684, "grad_norm": 5.519317150115967, "learning_rate": 9.970671371664405e-06, "loss": 0.6007, "step": 110230 }, { "epoch": 0.6552894531923368, "grad_norm": 4.568705081939697, "learning_rate": 9.970648926514027e-06, "loss": 0.5967, "step": 110240 }, { "epoch": 0.6553488952690051, "grad_norm": 6.388246536254883, "learning_rate": 9.970626472803595e-06, "loss": 0.6258, "step": 110250 }, { "epoch": 0.6554083373456735, "grad_norm": 4.65129280090332, "learning_rate": 9.970604010533153e-06, "loss": 0.6108, "step": 110260 }, { "epoch": 0.6554677794223419, "grad_norm": 6.138166904449463, "learning_rate": 9.97058153970274e-06, "loss": 0.6421, "step": 110270 }, { "epoch": 0.6555272214990103, "grad_norm": 5.151634216308594, "learning_rate": 9.97055906031239e-06, "loss": 0.591, "step": 110280 }, { "epoch": 0.6555866635756786, "grad_norm": 5.027600288391113, "learning_rate": 9.970536572362144e-06, "loss": 0.5546, "step": 110290 }, { "epoch": 0.655646105652347, "grad_norm": 6.495736598968506, "learning_rate": 9.970514075852043e-06, "loss": 0.6698, "step": 110300 }, { "epoch": 0.6557055477290155, "grad_norm": 4.911847114562988, "learning_rate": 9.97049157078212e-06, "loss": 0.5797, "step": 110310 }, { "epoch": 0.6557649898056839, "grad_norm": 4.514397144317627, "learning_rate": 9.97046905715242e-06, "loss": 0.6315, "step": 110320 }, { "epoch": 0.6558244318823523, "grad_norm": 5.9401044845581055, "learning_rate": 9.970446534962981e-06, "loss": 0.5875, "step": 110330 }, { "epoch": 0.6558838739590206, "grad_norm": 5.148166179656982, "learning_rate": 9.970424004213837e-06, "loss": 0.5597, "step": 110340 }, { "epoch": 0.655943316035689, "grad_norm": 4.355703830718994, "learning_rate": 9.97040146490503e-06, "loss": 0.5983, "step": 110350 }, { "epoch": 0.6560027581123574, "grad_norm": 5.080856800079346, "learning_rate": 9.9703789170366e-06, "loss": 0.5943, "step": 110360 }, { "epoch": 0.6560622001890258, "grad_norm": 6.551064968109131, "learning_rate": 9.970356360608583e-06, "loss": 0.5933, "step": 110370 }, { "epoch": 0.6561216422656942, "grad_norm": 6.883527755737305, "learning_rate": 9.97033379562102e-06, "loss": 0.6523, "step": 110380 }, { "epoch": 0.6561810843423626, "grad_norm": 5.8182454109191895, "learning_rate": 9.970311222073951e-06, "loss": 0.6562, "step": 110390 }, { "epoch": 0.656240526419031, "grad_norm": 6.0058817863464355, "learning_rate": 9.97028863996741e-06, "loss": 0.639, "step": 110400 }, { "epoch": 0.6562999684956994, "grad_norm": 5.268051624298096, "learning_rate": 9.970266049301443e-06, "loss": 0.6491, "step": 110410 }, { "epoch": 0.6563594105723678, "grad_norm": 7.159703254699707, "learning_rate": 9.97024345007608e-06, "loss": 0.6552, "step": 110420 }, { "epoch": 0.6564188526490361, "grad_norm": 5.633424758911133, "learning_rate": 9.970220842291366e-06, "loss": 0.6021, "step": 110430 }, { "epoch": 0.6564782947257045, "grad_norm": 5.8231520652771, "learning_rate": 9.97019822594734e-06, "loss": 0.6268, "step": 110440 }, { "epoch": 0.6565377368023729, "grad_norm": 5.451920509338379, "learning_rate": 9.97017560104404e-06, "loss": 0.5888, "step": 110450 }, { "epoch": 0.6565971788790413, "grad_norm": 5.909743785858154, "learning_rate": 9.970152967581504e-06, "loss": 0.6111, "step": 110460 }, { "epoch": 0.6566566209557098, "grad_norm": 5.056497097015381, "learning_rate": 9.970130325559771e-06, "loss": 0.5544, "step": 110470 }, { "epoch": 0.6567160630323781, "grad_norm": 7.401382923126221, "learning_rate": 9.970107674978882e-06, "loss": 0.6242, "step": 110480 }, { "epoch": 0.6567755051090465, "grad_norm": 5.357784271240234, "learning_rate": 9.970085015838873e-06, "loss": 0.6046, "step": 110490 }, { "epoch": 0.6568349471857149, "grad_norm": 5.432180404663086, "learning_rate": 9.970062348139785e-06, "loss": 0.5823, "step": 110500 }, { "epoch": 0.6568943892623833, "grad_norm": 6.236274242401123, "learning_rate": 9.970039671881658e-06, "loss": 0.5707, "step": 110510 }, { "epoch": 0.6569538313390516, "grad_norm": 4.352803707122803, "learning_rate": 9.970016987064527e-06, "loss": 0.5928, "step": 110520 }, { "epoch": 0.65701327341572, "grad_norm": 5.141051769256592, "learning_rate": 9.969994293688433e-06, "loss": 0.6324, "step": 110530 }, { "epoch": 0.6570727154923884, "grad_norm": 7.938961505889893, "learning_rate": 9.96997159175342e-06, "loss": 0.5882, "step": 110540 }, { "epoch": 0.6571321575690569, "grad_norm": 4.734531402587891, "learning_rate": 9.96994888125952e-06, "loss": 0.588, "step": 110550 }, { "epoch": 0.6571915996457253, "grad_norm": 6.524964809417725, "learning_rate": 9.969926162206776e-06, "loss": 0.5927, "step": 110560 }, { "epoch": 0.6572510417223936, "grad_norm": 5.619988441467285, "learning_rate": 9.969903434595227e-06, "loss": 0.6526, "step": 110570 }, { "epoch": 0.657310483799062, "grad_norm": 5.41898250579834, "learning_rate": 9.969880698424909e-06, "loss": 0.6174, "step": 110580 }, { "epoch": 0.6573699258757304, "grad_norm": 5.835234642028809, "learning_rate": 9.969857953695866e-06, "loss": 0.614, "step": 110590 }, { "epoch": 0.6574293679523988, "grad_norm": 5.421665668487549, "learning_rate": 9.969835200408132e-06, "loss": 0.5868, "step": 110600 }, { "epoch": 0.6574888100290672, "grad_norm": 4.84585428237915, "learning_rate": 9.96981243856175e-06, "loss": 0.6315, "step": 110610 }, { "epoch": 0.6575482521057355, "grad_norm": 5.853179931640625, "learning_rate": 9.969789668156757e-06, "loss": 0.6432, "step": 110620 }, { "epoch": 0.657607694182404, "grad_norm": 5.815738201141357, "learning_rate": 9.969766889193195e-06, "loss": 0.6088, "step": 110630 }, { "epoch": 0.6576671362590724, "grad_norm": 6.247623443603516, "learning_rate": 9.969744101671102e-06, "loss": 0.6262, "step": 110640 }, { "epoch": 0.6577265783357408, "grad_norm": 5.336240768432617, "learning_rate": 9.969721305590513e-06, "loss": 0.5958, "step": 110650 }, { "epoch": 0.6577860204124091, "grad_norm": 5.17204475402832, "learning_rate": 9.969698500951475e-06, "loss": 0.6291, "step": 110660 }, { "epoch": 0.6578454624890775, "grad_norm": 6.125463485717773, "learning_rate": 9.969675687754021e-06, "loss": 0.6384, "step": 110670 }, { "epoch": 0.6579049045657459, "grad_norm": 4.476799011230469, "learning_rate": 9.969652865998194e-06, "loss": 0.6039, "step": 110680 }, { "epoch": 0.6579643466424143, "grad_norm": 6.187459945678711, "learning_rate": 9.96963003568403e-06, "loss": 0.6281, "step": 110690 }, { "epoch": 0.6580237887190827, "grad_norm": 4.802095413208008, "learning_rate": 9.96960719681157e-06, "loss": 0.6078, "step": 110700 }, { "epoch": 0.658083230795751, "grad_norm": 4.86876106262207, "learning_rate": 9.969584349380855e-06, "loss": 0.5959, "step": 110710 }, { "epoch": 0.6581426728724195, "grad_norm": 4.200981140136719, "learning_rate": 9.969561493391923e-06, "loss": 0.5881, "step": 110720 }, { "epoch": 0.6582021149490879, "grad_norm": 5.868791580200195, "learning_rate": 9.969538628844811e-06, "loss": 0.6133, "step": 110730 }, { "epoch": 0.6582615570257563, "grad_norm": 5.433309078216553, "learning_rate": 9.969515755739563e-06, "loss": 0.6379, "step": 110740 }, { "epoch": 0.6583209991024247, "grad_norm": 6.082018852233887, "learning_rate": 9.969492874076214e-06, "loss": 0.6497, "step": 110750 }, { "epoch": 0.658380441179093, "grad_norm": 6.07759952545166, "learning_rate": 9.969469983854806e-06, "loss": 0.6223, "step": 110760 }, { "epoch": 0.6584398832557614, "grad_norm": 5.799922466278076, "learning_rate": 9.96944708507538e-06, "loss": 0.6085, "step": 110770 }, { "epoch": 0.6584993253324298, "grad_norm": 5.173950672149658, "learning_rate": 9.96942417773797e-06, "loss": 0.6119, "step": 110780 }, { "epoch": 0.6585587674090982, "grad_norm": 5.314573287963867, "learning_rate": 9.96940126184262e-06, "loss": 0.6597, "step": 110790 }, { "epoch": 0.6586182094857665, "grad_norm": 5.11307430267334, "learning_rate": 9.969378337389365e-06, "loss": 0.5795, "step": 110800 }, { "epoch": 0.658677651562435, "grad_norm": 5.8633503913879395, "learning_rate": 9.969355404378252e-06, "loss": 0.6361, "step": 110810 }, { "epoch": 0.6587370936391034, "grad_norm": 8.952168464660645, "learning_rate": 9.969332462809314e-06, "loss": 0.5762, "step": 110820 }, { "epoch": 0.6587965357157718, "grad_norm": 5.872329235076904, "learning_rate": 9.969309512682593e-06, "loss": 0.6121, "step": 110830 }, { "epoch": 0.6588559777924402, "grad_norm": 7.87643575668335, "learning_rate": 9.969286553998128e-06, "loss": 0.6172, "step": 110840 }, { "epoch": 0.6589154198691085, "grad_norm": 5.26023006439209, "learning_rate": 9.969263586755959e-06, "loss": 0.5821, "step": 110850 }, { "epoch": 0.6589748619457769, "grad_norm": 6.585247039794922, "learning_rate": 9.969240610956124e-06, "loss": 0.5902, "step": 110860 }, { "epoch": 0.6590343040224453, "grad_norm": 5.114499568939209, "learning_rate": 9.969217626598665e-06, "loss": 0.6335, "step": 110870 }, { "epoch": 0.6590937460991138, "grad_norm": 6.586660385131836, "learning_rate": 9.969194633683618e-06, "loss": 0.6336, "step": 110880 }, { "epoch": 0.6591531881757821, "grad_norm": 6.2494916915893555, "learning_rate": 9.969171632211028e-06, "loss": 0.6124, "step": 110890 }, { "epoch": 0.6592126302524505, "grad_norm": 4.064722061157227, "learning_rate": 9.96914862218093e-06, "loss": 0.5983, "step": 110900 }, { "epoch": 0.6592720723291189, "grad_norm": 4.275795936584473, "learning_rate": 9.969125603593367e-06, "loss": 0.6229, "step": 110910 }, { "epoch": 0.6593315144057873, "grad_norm": 4.722816467285156, "learning_rate": 9.969102576448374e-06, "loss": 0.6036, "step": 110920 }, { "epoch": 0.6593909564824557, "grad_norm": 7.181658744812012, "learning_rate": 9.969079540745994e-06, "loss": 0.629, "step": 110930 }, { "epoch": 0.659450398559124, "grad_norm": 5.420351982116699, "learning_rate": 9.969056496486269e-06, "loss": 0.5572, "step": 110940 }, { "epoch": 0.6595098406357924, "grad_norm": 4.529914855957031, "learning_rate": 9.969033443669233e-06, "loss": 0.5706, "step": 110950 }, { "epoch": 0.6595692827124608, "grad_norm": 5.470584869384766, "learning_rate": 9.969010382294929e-06, "loss": 0.6063, "step": 110960 }, { "epoch": 0.6596287247891293, "grad_norm": 7.329765319824219, "learning_rate": 9.968987312363396e-06, "loss": 0.6755, "step": 110970 }, { "epoch": 0.6596881668657977, "grad_norm": 5.532111644744873, "learning_rate": 9.968964233874674e-06, "loss": 0.5806, "step": 110980 }, { "epoch": 0.659747608942466, "grad_norm": 6.376952171325684, "learning_rate": 9.968941146828803e-06, "loss": 0.6321, "step": 110990 }, { "epoch": 0.6598070510191344, "grad_norm": 5.406958103179932, "learning_rate": 9.968918051225823e-06, "loss": 0.6178, "step": 111000 }, { "epoch": 0.6598664930958028, "grad_norm": 5.912361145019531, "learning_rate": 9.968894947065772e-06, "loss": 0.6318, "step": 111010 }, { "epoch": 0.6599259351724712, "grad_norm": 5.30311393737793, "learning_rate": 9.968871834348693e-06, "loss": 0.5964, "step": 111020 }, { "epoch": 0.6599853772491395, "grad_norm": 5.502988338470459, "learning_rate": 9.968848713074622e-06, "loss": 0.6275, "step": 111030 }, { "epoch": 0.6600448193258079, "grad_norm": 5.196026802062988, "learning_rate": 9.968825583243603e-06, "loss": 0.6059, "step": 111040 }, { "epoch": 0.6601042614024764, "grad_norm": 5.9134202003479, "learning_rate": 9.96880244485567e-06, "loss": 0.5967, "step": 111050 }, { "epoch": 0.6601637034791448, "grad_norm": 6.834819793701172, "learning_rate": 9.968779297910869e-06, "loss": 0.6133, "step": 111060 }, { "epoch": 0.6602231455558132, "grad_norm": 6.486676216125488, "learning_rate": 9.968756142409235e-06, "loss": 0.6181, "step": 111070 }, { "epoch": 0.6602825876324815, "grad_norm": 5.7105841636657715, "learning_rate": 9.968732978350812e-06, "loss": 0.5707, "step": 111080 }, { "epoch": 0.6603420297091499, "grad_norm": 4.8482890129089355, "learning_rate": 9.968709805735637e-06, "loss": 0.6903, "step": 111090 }, { "epoch": 0.6604014717858183, "grad_norm": 3.9732561111450195, "learning_rate": 9.968686624563752e-06, "loss": 0.6099, "step": 111100 }, { "epoch": 0.6604609138624867, "grad_norm": 5.9044694900512695, "learning_rate": 9.968663434835194e-06, "loss": 0.6242, "step": 111110 }, { "epoch": 0.660520355939155, "grad_norm": 5.49585485458374, "learning_rate": 9.968640236550006e-06, "loss": 0.6064, "step": 111120 }, { "epoch": 0.6605797980158234, "grad_norm": 5.779322147369385, "learning_rate": 9.968617029708227e-06, "loss": 0.5475, "step": 111130 }, { "epoch": 0.6606392400924919, "grad_norm": 7.259478569030762, "learning_rate": 9.968593814309895e-06, "loss": 0.6289, "step": 111140 }, { "epoch": 0.6606986821691603, "grad_norm": 5.798027038574219, "learning_rate": 9.968570590355053e-06, "loss": 0.6105, "step": 111150 }, { "epoch": 0.6607581242458287, "grad_norm": 5.9542155265808105, "learning_rate": 9.968547357843739e-06, "loss": 0.6752, "step": 111160 }, { "epoch": 0.660817566322497, "grad_norm": 6.507562637329102, "learning_rate": 9.968524116775992e-06, "loss": 0.5869, "step": 111170 }, { "epoch": 0.6608770083991654, "grad_norm": 6.234691143035889, "learning_rate": 9.968500867151856e-06, "loss": 0.5539, "step": 111180 }, { "epoch": 0.6609364504758338, "grad_norm": 6.234212398529053, "learning_rate": 9.96847760897137e-06, "loss": 0.679, "step": 111190 }, { "epoch": 0.6609958925525022, "grad_norm": 4.924152851104736, "learning_rate": 9.96845434223457e-06, "loss": 0.6057, "step": 111200 }, { "epoch": 0.6610553346291707, "grad_norm": 5.328561305999756, "learning_rate": 9.968431066941499e-06, "loss": 0.6572, "step": 111210 }, { "epoch": 0.661114776705839, "grad_norm": 4.855401992797852, "learning_rate": 9.968407783092197e-06, "loss": 0.5527, "step": 111220 }, { "epoch": 0.6611742187825074, "grad_norm": 5.788839340209961, "learning_rate": 9.968384490686705e-06, "loss": 0.639, "step": 111230 }, { "epoch": 0.6612336608591758, "grad_norm": 5.692809104919434, "learning_rate": 9.968361189725063e-06, "loss": 0.6169, "step": 111240 }, { "epoch": 0.6612931029358442, "grad_norm": 6.081601619720459, "learning_rate": 9.968337880207308e-06, "loss": 0.5759, "step": 111250 }, { "epoch": 0.6613525450125125, "grad_norm": 5.299072265625, "learning_rate": 9.968314562133484e-06, "loss": 0.5916, "step": 111260 }, { "epoch": 0.6614119870891809, "grad_norm": 5.1355509757995605, "learning_rate": 9.968291235503626e-06, "loss": 0.6117, "step": 111270 }, { "epoch": 0.6614714291658493, "grad_norm": 5.153439044952393, "learning_rate": 9.968267900317781e-06, "loss": 0.6052, "step": 111280 }, { "epoch": 0.6615308712425177, "grad_norm": 6.078189849853516, "learning_rate": 9.968244556575986e-06, "loss": 0.6215, "step": 111290 }, { "epoch": 0.6615903133191862, "grad_norm": 5.462852954864502, "learning_rate": 9.968221204278278e-06, "loss": 0.5907, "step": 111300 }, { "epoch": 0.6616497553958545, "grad_norm": 5.778624057769775, "learning_rate": 9.968197843424704e-06, "loss": 0.6191, "step": 111310 }, { "epoch": 0.6617091974725229, "grad_norm": 5.72660493850708, "learning_rate": 9.9681744740153e-06, "loss": 0.5524, "step": 111320 }, { "epoch": 0.6617686395491913, "grad_norm": 7.353921413421631, "learning_rate": 9.968151096050106e-06, "loss": 0.6695, "step": 111330 }, { "epoch": 0.6618280816258597, "grad_norm": 6.498431205749512, "learning_rate": 9.968127709529162e-06, "loss": 0.5984, "step": 111340 }, { "epoch": 0.6618875237025281, "grad_norm": 5.076620578765869, "learning_rate": 9.96810431445251e-06, "loss": 0.5743, "step": 111350 }, { "epoch": 0.6619469657791964, "grad_norm": 6.181628704071045, "learning_rate": 9.96808091082019e-06, "loss": 0.5618, "step": 111360 }, { "epoch": 0.6620064078558648, "grad_norm": 6.129388809204102, "learning_rate": 9.96805749863224e-06, "loss": 0.6244, "step": 111370 }, { "epoch": 0.6620658499325333, "grad_norm": 6.870126724243164, "learning_rate": 9.968034077888704e-06, "loss": 0.6071, "step": 111380 }, { "epoch": 0.6621252920092017, "grad_norm": 5.4895548820495605, "learning_rate": 9.96801064858962e-06, "loss": 0.5837, "step": 111390 }, { "epoch": 0.66218473408587, "grad_norm": 5.421417713165283, "learning_rate": 9.96798721073503e-06, "loss": 0.5325, "step": 111400 }, { "epoch": 0.6622441761625384, "grad_norm": 5.413483142852783, "learning_rate": 9.967963764324973e-06, "loss": 0.5168, "step": 111410 }, { "epoch": 0.6623036182392068, "grad_norm": 4.569538116455078, "learning_rate": 9.96794030935949e-06, "loss": 0.6709, "step": 111420 }, { "epoch": 0.6623630603158752, "grad_norm": 6.326834678649902, "learning_rate": 9.96791684583862e-06, "loss": 0.6172, "step": 111430 }, { "epoch": 0.6624225023925436, "grad_norm": 5.658957004547119, "learning_rate": 9.967893373762404e-06, "loss": 0.6263, "step": 111440 }, { "epoch": 0.6624819444692119, "grad_norm": 4.772400379180908, "learning_rate": 9.967869893130884e-06, "loss": 0.6323, "step": 111450 }, { "epoch": 0.6625413865458804, "grad_norm": 5.316635608673096, "learning_rate": 9.967846403944097e-06, "loss": 0.6527, "step": 111460 }, { "epoch": 0.6626008286225488, "grad_norm": 6.968079566955566, "learning_rate": 9.967822906202088e-06, "loss": 0.6406, "step": 111470 }, { "epoch": 0.6626602706992172, "grad_norm": 5.74743127822876, "learning_rate": 9.967799399904895e-06, "loss": 0.6193, "step": 111480 }, { "epoch": 0.6627197127758855, "grad_norm": 6.626004695892334, "learning_rate": 9.967775885052558e-06, "loss": 0.6808, "step": 111490 }, { "epoch": 0.6627791548525539, "grad_norm": 6.729206562042236, "learning_rate": 9.967752361645118e-06, "loss": 0.6243, "step": 111500 }, { "epoch": 0.6628385969292223, "grad_norm": 5.7341628074646, "learning_rate": 9.967728829682617e-06, "loss": 0.5852, "step": 111510 }, { "epoch": 0.6628980390058907, "grad_norm": 4.949308395385742, "learning_rate": 9.967705289165093e-06, "loss": 0.5666, "step": 111520 }, { "epoch": 0.6629574810825591, "grad_norm": 6.3171706199646, "learning_rate": 9.967681740092589e-06, "loss": 0.5878, "step": 111530 }, { "epoch": 0.6630169231592274, "grad_norm": 4.413089752197266, "learning_rate": 9.967658182465143e-06, "loss": 0.6054, "step": 111540 }, { "epoch": 0.6630763652358959, "grad_norm": 5.473221778869629, "learning_rate": 9.967634616282797e-06, "loss": 0.5483, "step": 111550 }, { "epoch": 0.6631358073125643, "grad_norm": 5.394063949584961, "learning_rate": 9.967611041545593e-06, "loss": 0.6643, "step": 111560 }, { "epoch": 0.6631952493892327, "grad_norm": 6.582179069519043, "learning_rate": 9.967587458253568e-06, "loss": 0.6089, "step": 111570 }, { "epoch": 0.6632546914659011, "grad_norm": 6.063692092895508, "learning_rate": 9.967563866406766e-06, "loss": 0.6577, "step": 111580 }, { "epoch": 0.6633141335425694, "grad_norm": 6.431196212768555, "learning_rate": 9.967540266005225e-06, "loss": 0.6585, "step": 111590 }, { "epoch": 0.6633735756192378, "grad_norm": 5.716935634613037, "learning_rate": 9.967516657048988e-06, "loss": 0.563, "step": 111600 }, { "epoch": 0.6634330176959062, "grad_norm": 5.080094814300537, "learning_rate": 9.967493039538093e-06, "loss": 0.6074, "step": 111610 }, { "epoch": 0.6634924597725746, "grad_norm": 4.361317157745361, "learning_rate": 9.967469413472587e-06, "loss": 0.608, "step": 111620 }, { "epoch": 0.663551901849243, "grad_norm": 5.376885890960693, "learning_rate": 9.967445778852501e-06, "loss": 0.5596, "step": 111630 }, { "epoch": 0.6636113439259114, "grad_norm": 4.546639919281006, "learning_rate": 9.967422135677882e-06, "loss": 0.5818, "step": 111640 }, { "epoch": 0.6636707860025798, "grad_norm": 5.740834712982178, "learning_rate": 9.967398483948771e-06, "loss": 0.6325, "step": 111650 }, { "epoch": 0.6637302280792482, "grad_norm": 4.916011333465576, "learning_rate": 9.967374823665205e-06, "loss": 0.5622, "step": 111660 }, { "epoch": 0.6637896701559166, "grad_norm": 6.217895984649658, "learning_rate": 9.967351154827228e-06, "loss": 0.6393, "step": 111670 }, { "epoch": 0.6638491122325849, "grad_norm": 5.688941955566406, "learning_rate": 9.967327477434878e-06, "loss": 0.553, "step": 111680 }, { "epoch": 0.6639085543092533, "grad_norm": 5.947262763977051, "learning_rate": 9.9673037914882e-06, "loss": 0.6219, "step": 111690 }, { "epoch": 0.6639679963859217, "grad_norm": 5.096282005310059, "learning_rate": 9.967280096987231e-06, "loss": 0.6214, "step": 111700 }, { "epoch": 0.6640274384625902, "grad_norm": 4.39030647277832, "learning_rate": 9.967256393932011e-06, "loss": 0.6154, "step": 111710 }, { "epoch": 0.6640868805392586, "grad_norm": 5.66798210144043, "learning_rate": 9.967232682322586e-06, "loss": 0.619, "step": 111720 }, { "epoch": 0.6641463226159269, "grad_norm": 7.274421691894531, "learning_rate": 9.967208962158992e-06, "loss": 0.6353, "step": 111730 }, { "epoch": 0.6642057646925953, "grad_norm": 7.142889976501465, "learning_rate": 9.967185233441273e-06, "loss": 0.6135, "step": 111740 }, { "epoch": 0.6642652067692637, "grad_norm": 4.886538982391357, "learning_rate": 9.967161496169466e-06, "loss": 0.5754, "step": 111750 }, { "epoch": 0.6643246488459321, "grad_norm": 6.792051792144775, "learning_rate": 9.967137750343616e-06, "loss": 0.6648, "step": 111760 }, { "epoch": 0.6643840909226004, "grad_norm": 5.710819721221924, "learning_rate": 9.96711399596376e-06, "loss": 0.6021, "step": 111770 }, { "epoch": 0.6644435329992688, "grad_norm": 4.6007208824157715, "learning_rate": 9.967090233029944e-06, "loss": 0.5884, "step": 111780 }, { "epoch": 0.6645029750759373, "grad_norm": 5.922353744506836, "learning_rate": 9.967066461542204e-06, "loss": 0.5715, "step": 111790 }, { "epoch": 0.6645624171526057, "grad_norm": 6.307055950164795, "learning_rate": 9.967042681500583e-06, "loss": 0.6611, "step": 111800 }, { "epoch": 0.6646218592292741, "grad_norm": 6.351180076599121, "learning_rate": 9.967018892905123e-06, "loss": 0.5903, "step": 111810 }, { "epoch": 0.6646813013059424, "grad_norm": 5.70904016494751, "learning_rate": 9.966995095755863e-06, "loss": 0.5819, "step": 111820 }, { "epoch": 0.6647407433826108, "grad_norm": 5.449990749359131, "learning_rate": 9.966971290052845e-06, "loss": 0.5607, "step": 111830 }, { "epoch": 0.6648001854592792, "grad_norm": 5.306847095489502, "learning_rate": 9.966947475796109e-06, "loss": 0.6426, "step": 111840 }, { "epoch": 0.6648596275359476, "grad_norm": 5.8275299072265625, "learning_rate": 9.966923652985697e-06, "loss": 0.6647, "step": 111850 }, { "epoch": 0.6649190696126159, "grad_norm": 5.959535121917725, "learning_rate": 9.96689982162165e-06, "loss": 0.54, "step": 111860 }, { "epoch": 0.6649785116892843, "grad_norm": 5.998234748840332, "learning_rate": 9.966875981704009e-06, "loss": 0.6071, "step": 111870 }, { "epoch": 0.6650379537659528, "grad_norm": 5.0705366134643555, "learning_rate": 9.966852133232816e-06, "loss": 0.603, "step": 111880 }, { "epoch": 0.6650973958426212, "grad_norm": 4.458307266235352, "learning_rate": 9.966828276208109e-06, "loss": 0.6218, "step": 111890 }, { "epoch": 0.6651568379192896, "grad_norm": 5.138757228851318, "learning_rate": 9.966804410629933e-06, "loss": 0.5936, "step": 111900 }, { "epoch": 0.6652162799959579, "grad_norm": 4.777797698974609, "learning_rate": 9.966780536498325e-06, "loss": 0.641, "step": 111910 }, { "epoch": 0.6652757220726263, "grad_norm": 5.339453220367432, "learning_rate": 9.96675665381333e-06, "loss": 0.5948, "step": 111920 }, { "epoch": 0.6653351641492947, "grad_norm": 5.58540678024292, "learning_rate": 9.966732762574987e-06, "loss": 0.5649, "step": 111930 }, { "epoch": 0.6653946062259631, "grad_norm": 5.627737522125244, "learning_rate": 9.96670886278334e-06, "loss": 0.6352, "step": 111940 }, { "epoch": 0.6654540483026316, "grad_norm": 4.371352672576904, "learning_rate": 9.966684954438424e-06, "loss": 0.5656, "step": 111950 }, { "epoch": 0.6655134903792999, "grad_norm": 6.894509792327881, "learning_rate": 9.966661037540284e-06, "loss": 0.6534, "step": 111960 }, { "epoch": 0.6655729324559683, "grad_norm": 4.935898303985596, "learning_rate": 9.966637112088963e-06, "loss": 0.6401, "step": 111970 }, { "epoch": 0.6656323745326367, "grad_norm": 5.411357402801514, "learning_rate": 9.966613178084499e-06, "loss": 0.5861, "step": 111980 }, { "epoch": 0.6656918166093051, "grad_norm": 5.02267599105835, "learning_rate": 9.966589235526935e-06, "loss": 0.5833, "step": 111990 }, { "epoch": 0.6657512586859734, "grad_norm": 5.748440265655518, "learning_rate": 9.966565284416311e-06, "loss": 0.6065, "step": 112000 }, { "epoch": 0.6658107007626418, "grad_norm": 6.189662456512451, "learning_rate": 9.96654132475267e-06, "loss": 0.5897, "step": 112010 }, { "epoch": 0.6658701428393102, "grad_norm": 6.032506942749023, "learning_rate": 9.966517356536052e-06, "loss": 0.6706, "step": 112020 }, { "epoch": 0.6659295849159786, "grad_norm": 4.4059953689575195, "learning_rate": 9.966493379766498e-06, "loss": 0.6037, "step": 112030 }, { "epoch": 0.6659890269926471, "grad_norm": 5.184632301330566, "learning_rate": 9.966469394444052e-06, "loss": 0.5863, "step": 112040 }, { "epoch": 0.6660484690693154, "grad_norm": 4.956153392791748, "learning_rate": 9.96644540056875e-06, "loss": 0.55, "step": 112050 }, { "epoch": 0.6661079111459838, "grad_norm": 6.231771469116211, "learning_rate": 9.966421398140638e-06, "loss": 0.6479, "step": 112060 }, { "epoch": 0.6661673532226522, "grad_norm": 5.628050804138184, "learning_rate": 9.966397387159756e-06, "loss": 0.5802, "step": 112070 }, { "epoch": 0.6662267952993206, "grad_norm": 3.811253786087036, "learning_rate": 9.966373367626146e-06, "loss": 0.6274, "step": 112080 }, { "epoch": 0.666286237375989, "grad_norm": 4.628293514251709, "learning_rate": 9.966349339539846e-06, "loss": 0.6116, "step": 112090 }, { "epoch": 0.6663456794526573, "grad_norm": 5.361119270324707, "learning_rate": 9.966325302900901e-06, "loss": 0.5433, "step": 112100 }, { "epoch": 0.6664051215293257, "grad_norm": 5.505573749542236, "learning_rate": 9.966301257709352e-06, "loss": 0.6286, "step": 112110 }, { "epoch": 0.6664645636059942, "grad_norm": 5.439931869506836, "learning_rate": 9.966277203965237e-06, "loss": 0.6308, "step": 112120 }, { "epoch": 0.6665240056826626, "grad_norm": 4.609290599822998, "learning_rate": 9.966253141668603e-06, "loss": 0.6241, "step": 112130 }, { "epoch": 0.6665834477593309, "grad_norm": 4.792095184326172, "learning_rate": 9.966229070819488e-06, "loss": 0.6387, "step": 112140 }, { "epoch": 0.6666428898359993, "grad_norm": 4.516178607940674, "learning_rate": 9.966204991417933e-06, "loss": 0.5565, "step": 112150 }, { "epoch": 0.6667023319126677, "grad_norm": 5.648319244384766, "learning_rate": 9.966180903463983e-06, "loss": 0.6032, "step": 112160 }, { "epoch": 0.6667617739893361, "grad_norm": 5.065413951873779, "learning_rate": 9.966156806957675e-06, "loss": 0.6326, "step": 112170 }, { "epoch": 0.6668212160660045, "grad_norm": 5.996620178222656, "learning_rate": 9.966132701899051e-06, "loss": 0.5545, "step": 112180 }, { "epoch": 0.6668806581426728, "grad_norm": 7.439845085144043, "learning_rate": 9.966108588288154e-06, "loss": 0.6599, "step": 112190 }, { "epoch": 0.6669401002193412, "grad_norm": 5.6114068031311035, "learning_rate": 9.966084466125028e-06, "loss": 0.5964, "step": 112200 }, { "epoch": 0.6669995422960097, "grad_norm": 5.376272201538086, "learning_rate": 9.96606033540971e-06, "loss": 0.6252, "step": 112210 }, { "epoch": 0.6670589843726781, "grad_norm": 3.735917806625366, "learning_rate": 9.966036196142245e-06, "loss": 0.6126, "step": 112220 }, { "epoch": 0.6671184264493464, "grad_norm": 5.3193840980529785, "learning_rate": 9.966012048322673e-06, "loss": 0.6173, "step": 112230 }, { "epoch": 0.6671778685260148, "grad_norm": 5.225269794464111, "learning_rate": 9.965987891951035e-06, "loss": 0.5842, "step": 112240 }, { "epoch": 0.6672373106026832, "grad_norm": 5.65363883972168, "learning_rate": 9.965963727027372e-06, "loss": 0.5904, "step": 112250 }, { "epoch": 0.6672967526793516, "grad_norm": 5.832566738128662, "learning_rate": 9.965939553551729e-06, "loss": 0.617, "step": 112260 }, { "epoch": 0.66735619475602, "grad_norm": 5.545039176940918, "learning_rate": 9.965915371524146e-06, "loss": 0.6022, "step": 112270 }, { "epoch": 0.6674156368326883, "grad_norm": 5.571981430053711, "learning_rate": 9.965891180944663e-06, "loss": 0.6575, "step": 112280 }, { "epoch": 0.6674750789093568, "grad_norm": 5.34677791595459, "learning_rate": 9.965866981813324e-06, "loss": 0.61, "step": 112290 }, { "epoch": 0.6675345209860252, "grad_norm": 6.754549980163574, "learning_rate": 9.965842774130169e-06, "loss": 0.6406, "step": 112300 }, { "epoch": 0.6675939630626936, "grad_norm": 5.503811836242676, "learning_rate": 9.965818557895238e-06, "loss": 0.6489, "step": 112310 }, { "epoch": 0.667653405139362, "grad_norm": 3.960200071334839, "learning_rate": 9.965794333108577e-06, "loss": 0.5899, "step": 112320 }, { "epoch": 0.6677128472160303, "grad_norm": 5.611517906188965, "learning_rate": 9.965770099770225e-06, "loss": 0.6481, "step": 112330 }, { "epoch": 0.6677722892926987, "grad_norm": 6.124845027923584, "learning_rate": 9.965745857880224e-06, "loss": 0.6111, "step": 112340 }, { "epoch": 0.6678317313693671, "grad_norm": 5.78780460357666, "learning_rate": 9.965721607438619e-06, "loss": 0.5839, "step": 112350 }, { "epoch": 0.6678911734460355, "grad_norm": 6.005615711212158, "learning_rate": 9.965697348445446e-06, "loss": 0.5357, "step": 112360 }, { "epoch": 0.6679506155227038, "grad_norm": 6.149956226348877, "learning_rate": 9.96567308090075e-06, "loss": 0.655, "step": 112370 }, { "epoch": 0.6680100575993723, "grad_norm": 5.480423927307129, "learning_rate": 9.965648804804573e-06, "loss": 0.6034, "step": 112380 }, { "epoch": 0.6680694996760407, "grad_norm": 4.234494209289551, "learning_rate": 9.965624520156957e-06, "loss": 0.6167, "step": 112390 }, { "epoch": 0.6681289417527091, "grad_norm": 5.180927753448486, "learning_rate": 9.965600226957941e-06, "loss": 0.6135, "step": 112400 }, { "epoch": 0.6681883838293775, "grad_norm": 5.8481855392456055, "learning_rate": 9.965575925207571e-06, "loss": 0.6706, "step": 112410 }, { "epoch": 0.6682478259060458, "grad_norm": 7.1344404220581055, "learning_rate": 9.965551614905886e-06, "loss": 0.6072, "step": 112420 }, { "epoch": 0.6683072679827142, "grad_norm": 7.200658321380615, "learning_rate": 9.96552729605293e-06, "loss": 0.6481, "step": 112430 }, { "epoch": 0.6683667100593826, "grad_norm": 4.803049564361572, "learning_rate": 9.965502968648742e-06, "loss": 0.6103, "step": 112440 }, { "epoch": 0.668426152136051, "grad_norm": 5.903746128082275, "learning_rate": 9.965478632693365e-06, "loss": 0.6344, "step": 112450 }, { "epoch": 0.6684855942127195, "grad_norm": 5.819178581237793, "learning_rate": 9.965454288186842e-06, "loss": 0.582, "step": 112460 }, { "epoch": 0.6685450362893878, "grad_norm": 5.602541446685791, "learning_rate": 9.965429935129214e-06, "loss": 0.631, "step": 112470 }, { "epoch": 0.6686044783660562, "grad_norm": 5.732863903045654, "learning_rate": 9.965405573520523e-06, "loss": 0.6449, "step": 112480 }, { "epoch": 0.6686639204427246, "grad_norm": 5.8651652336120605, "learning_rate": 9.96538120336081e-06, "loss": 0.5703, "step": 112490 }, { "epoch": 0.668723362519393, "grad_norm": 6.851578235626221, "learning_rate": 9.965356824650121e-06, "loss": 0.577, "step": 112500 }, { "epoch": 0.6687828045960613, "grad_norm": 5.54791784286499, "learning_rate": 9.965332437388493e-06, "loss": 0.6692, "step": 112510 }, { "epoch": 0.6688422466727297, "grad_norm": 5.790605545043945, "learning_rate": 9.965308041575971e-06, "loss": 0.5636, "step": 112520 }, { "epoch": 0.6689016887493981, "grad_norm": 5.299190998077393, "learning_rate": 9.965283637212598e-06, "loss": 0.585, "step": 112530 }, { "epoch": 0.6689611308260666, "grad_norm": 6.149190425872803, "learning_rate": 9.965259224298411e-06, "loss": 0.6012, "step": 112540 }, { "epoch": 0.669020572902735, "grad_norm": 4.456584453582764, "learning_rate": 9.965234802833457e-06, "loss": 0.6236, "step": 112550 }, { "epoch": 0.6690800149794033, "grad_norm": 5.562141418457031, "learning_rate": 9.965210372817774e-06, "loss": 0.607, "step": 112560 }, { "epoch": 0.6691394570560717, "grad_norm": 5.294075965881348, "learning_rate": 9.965185934251408e-06, "loss": 0.6159, "step": 112570 }, { "epoch": 0.6691988991327401, "grad_norm": 5.948101043701172, "learning_rate": 9.965161487134398e-06, "loss": 0.618, "step": 112580 }, { "epoch": 0.6692583412094085, "grad_norm": 5.990289688110352, "learning_rate": 9.96513703146679e-06, "loss": 0.6264, "step": 112590 }, { "epoch": 0.6693177832860768, "grad_norm": 4.982272148132324, "learning_rate": 9.965112567248622e-06, "loss": 0.5761, "step": 112600 }, { "epoch": 0.6693772253627452, "grad_norm": 5.321253299713135, "learning_rate": 9.965088094479938e-06, "loss": 0.6386, "step": 112610 }, { "epoch": 0.6694366674394137, "grad_norm": 4.867166519165039, "learning_rate": 9.965063613160778e-06, "loss": 0.6901, "step": 112620 }, { "epoch": 0.6694961095160821, "grad_norm": 7.5856733322143555, "learning_rate": 9.965039123291189e-06, "loss": 0.67, "step": 112630 }, { "epoch": 0.6695555515927505, "grad_norm": 5.689006328582764, "learning_rate": 9.96501462487121e-06, "loss": 0.661, "step": 112640 }, { "epoch": 0.6696149936694188, "grad_norm": 6.209369659423828, "learning_rate": 9.96499011790088e-06, "loss": 0.553, "step": 112650 }, { "epoch": 0.6696744357460872, "grad_norm": 6.640990257263184, "learning_rate": 9.964965602380248e-06, "loss": 0.6468, "step": 112660 }, { "epoch": 0.6697338778227556, "grad_norm": 5.606818199157715, "learning_rate": 9.964941078309352e-06, "loss": 0.5891, "step": 112670 }, { "epoch": 0.669793319899424, "grad_norm": 4.212412357330322, "learning_rate": 9.964916545688236e-06, "loss": 0.6351, "step": 112680 }, { "epoch": 0.6698527619760924, "grad_norm": 5.307495594024658, "learning_rate": 9.96489200451694e-06, "loss": 0.6182, "step": 112690 }, { "epoch": 0.6699122040527608, "grad_norm": 5.985754013061523, "learning_rate": 9.964867454795508e-06, "loss": 0.5712, "step": 112700 }, { "epoch": 0.6699716461294292, "grad_norm": 6.595291614532471, "learning_rate": 9.964842896523981e-06, "loss": 0.6535, "step": 112710 }, { "epoch": 0.6700310882060976, "grad_norm": 5.722355365753174, "learning_rate": 9.964818329702404e-06, "loss": 0.6112, "step": 112720 }, { "epoch": 0.670090530282766, "grad_norm": 4.897449970245361, "learning_rate": 9.964793754330815e-06, "loss": 0.6348, "step": 112730 }, { "epoch": 0.6701499723594343, "grad_norm": 5.847928524017334, "learning_rate": 9.964769170409261e-06, "loss": 0.5854, "step": 112740 }, { "epoch": 0.6702094144361027, "grad_norm": 5.131692886352539, "learning_rate": 9.96474457793778e-06, "loss": 0.647, "step": 112750 }, { "epoch": 0.6702688565127711, "grad_norm": 5.468133449554443, "learning_rate": 9.964719976916417e-06, "loss": 0.628, "step": 112760 }, { "epoch": 0.6703282985894395, "grad_norm": 6.2211761474609375, "learning_rate": 9.964695367345215e-06, "loss": 0.571, "step": 112770 }, { "epoch": 0.670387740666108, "grad_norm": 5.514440059661865, "learning_rate": 9.964670749224214e-06, "loss": 0.5613, "step": 112780 }, { "epoch": 0.6704471827427763, "grad_norm": 6.71244478225708, "learning_rate": 9.964646122553459e-06, "loss": 0.645, "step": 112790 }, { "epoch": 0.6705066248194447, "grad_norm": 4.911792755126953, "learning_rate": 9.96462148733299e-06, "loss": 0.5522, "step": 112800 }, { "epoch": 0.6705660668961131, "grad_norm": 4.926910400390625, "learning_rate": 9.96459684356285e-06, "loss": 0.5749, "step": 112810 }, { "epoch": 0.6706255089727815, "grad_norm": 5.746405601501465, "learning_rate": 9.964572191243083e-06, "loss": 0.6631, "step": 112820 }, { "epoch": 0.6706849510494499, "grad_norm": 5.436049938201904, "learning_rate": 9.96454753037373e-06, "loss": 0.6596, "step": 112830 }, { "epoch": 0.6707443931261182, "grad_norm": 5.620995998382568, "learning_rate": 9.964522860954833e-06, "loss": 0.6148, "step": 112840 }, { "epoch": 0.6708038352027866, "grad_norm": 3.564271926879883, "learning_rate": 9.964498182986436e-06, "loss": 0.6131, "step": 112850 }, { "epoch": 0.670863277279455, "grad_norm": 5.286680698394775, "learning_rate": 9.96447349646858e-06, "loss": 0.5796, "step": 112860 }, { "epoch": 0.6709227193561235, "grad_norm": 5.28498649597168, "learning_rate": 9.964448801401309e-06, "loss": 0.618, "step": 112870 }, { "epoch": 0.6709821614327918, "grad_norm": 5.267701625823975, "learning_rate": 9.964424097784665e-06, "loss": 0.63, "step": 112880 }, { "epoch": 0.6710416035094602, "grad_norm": 5.287825107574463, "learning_rate": 9.964399385618691e-06, "loss": 0.6447, "step": 112890 }, { "epoch": 0.6711010455861286, "grad_norm": 6.094335079193115, "learning_rate": 9.964374664903426e-06, "loss": 0.6229, "step": 112900 }, { "epoch": 0.671160487662797, "grad_norm": 5.870147228240967, "learning_rate": 9.964349935638919e-06, "loss": 0.6144, "step": 112910 }, { "epoch": 0.6712199297394654, "grad_norm": 5.095637321472168, "learning_rate": 9.964325197825208e-06, "loss": 0.5625, "step": 112920 }, { "epoch": 0.6712793718161337, "grad_norm": 6.747746467590332, "learning_rate": 9.964300451462336e-06, "loss": 0.5937, "step": 112930 }, { "epoch": 0.6713388138928021, "grad_norm": 5.38145637512207, "learning_rate": 9.964275696550346e-06, "loss": 0.5629, "step": 112940 }, { "epoch": 0.6713982559694706, "grad_norm": 4.543099403381348, "learning_rate": 9.964250933089281e-06, "loss": 0.6544, "step": 112950 }, { "epoch": 0.671457698046139, "grad_norm": 5.720210075378418, "learning_rate": 9.964226161079185e-06, "loss": 0.585, "step": 112960 }, { "epoch": 0.6715171401228073, "grad_norm": 4.862365245819092, "learning_rate": 9.964201380520098e-06, "loss": 0.64, "step": 112970 }, { "epoch": 0.6715765821994757, "grad_norm": 6.059146404266357, "learning_rate": 9.964176591412064e-06, "loss": 0.587, "step": 112980 }, { "epoch": 0.6716360242761441, "grad_norm": 6.412910461425781, "learning_rate": 9.964151793755125e-06, "loss": 0.5448, "step": 112990 }, { "epoch": 0.6716954663528125, "grad_norm": 6.4707136154174805, "learning_rate": 9.964126987549324e-06, "loss": 0.6019, "step": 113000 }, { "epoch": 0.6717549084294809, "grad_norm": 6.78708553314209, "learning_rate": 9.964102172794708e-06, "loss": 0.6545, "step": 113010 }, { "epoch": 0.6718143505061492, "grad_norm": 7.108610153198242, "learning_rate": 9.964077349491312e-06, "loss": 0.6128, "step": 113020 }, { "epoch": 0.6718737925828177, "grad_norm": 6.2108283042907715, "learning_rate": 9.964052517639182e-06, "loss": 0.587, "step": 113030 }, { "epoch": 0.6719332346594861, "grad_norm": 6.121997833251953, "learning_rate": 9.964027677238365e-06, "loss": 0.6296, "step": 113040 }, { "epoch": 0.6719926767361545, "grad_norm": 4.499560356140137, "learning_rate": 9.964002828288896e-06, "loss": 0.5955, "step": 113050 }, { "epoch": 0.6720521188128229, "grad_norm": 4.713888645172119, "learning_rate": 9.963977970790824e-06, "loss": 0.6115, "step": 113060 }, { "epoch": 0.6721115608894912, "grad_norm": 6.456462860107422, "learning_rate": 9.963953104744189e-06, "loss": 0.6291, "step": 113070 }, { "epoch": 0.6721710029661596, "grad_norm": 6.4461164474487305, "learning_rate": 9.963928230149034e-06, "loss": 0.5633, "step": 113080 }, { "epoch": 0.672230445042828, "grad_norm": 6.376308441162109, "learning_rate": 9.963903347005403e-06, "loss": 0.6284, "step": 113090 }, { "epoch": 0.6722898871194964, "grad_norm": 5.048759937286377, "learning_rate": 9.963878455313338e-06, "loss": 0.5796, "step": 113100 }, { "epoch": 0.6723493291961647, "grad_norm": 7.985109329223633, "learning_rate": 9.963853555072882e-06, "loss": 0.5565, "step": 113110 }, { "epoch": 0.6724087712728332, "grad_norm": 4.9601054191589355, "learning_rate": 9.963828646284076e-06, "loss": 0.6322, "step": 113120 }, { "epoch": 0.6724682133495016, "grad_norm": 4.971939563751221, "learning_rate": 9.963803728946969e-06, "loss": 0.6332, "step": 113130 }, { "epoch": 0.67252765542617, "grad_norm": 8.047317504882812, "learning_rate": 9.963778803061596e-06, "loss": 0.6446, "step": 113140 }, { "epoch": 0.6725870975028384, "grad_norm": 6.206531047821045, "learning_rate": 9.963753868628006e-06, "loss": 0.601, "step": 113150 }, { "epoch": 0.6726465395795067, "grad_norm": 6.097037315368652, "learning_rate": 9.963728925646238e-06, "loss": 0.5965, "step": 113160 }, { "epoch": 0.6727059816561751, "grad_norm": 6.379848480224609, "learning_rate": 9.963703974116339e-06, "loss": 0.5898, "step": 113170 }, { "epoch": 0.6727654237328435, "grad_norm": 4.745769023895264, "learning_rate": 9.963679014038346e-06, "loss": 0.6169, "step": 113180 }, { "epoch": 0.672824865809512, "grad_norm": 5.044617176055908, "learning_rate": 9.963654045412308e-06, "loss": 0.5595, "step": 113190 }, { "epoch": 0.6728843078861804, "grad_norm": 5.215405464172363, "learning_rate": 9.963629068238263e-06, "loss": 0.63, "step": 113200 }, { "epoch": 0.6729437499628487, "grad_norm": 6.867655277252197, "learning_rate": 9.963604082516259e-06, "loss": 0.5808, "step": 113210 }, { "epoch": 0.6730031920395171, "grad_norm": 5.933141231536865, "learning_rate": 9.963579088246335e-06, "loss": 0.6181, "step": 113220 }, { "epoch": 0.6730626341161855, "grad_norm": 5.473865032196045, "learning_rate": 9.963554085428538e-06, "loss": 0.6426, "step": 113230 }, { "epoch": 0.6731220761928539, "grad_norm": 6.245189189910889, "learning_rate": 9.963529074062906e-06, "loss": 0.6527, "step": 113240 }, { "epoch": 0.6731815182695222, "grad_norm": 5.751919746398926, "learning_rate": 9.963504054149486e-06, "loss": 0.6499, "step": 113250 }, { "epoch": 0.6732409603461906, "grad_norm": 6.492424488067627, "learning_rate": 9.963479025688318e-06, "loss": 0.6802, "step": 113260 }, { "epoch": 0.673300402422859, "grad_norm": 4.1382527351379395, "learning_rate": 9.963453988679448e-06, "loss": 0.5934, "step": 113270 }, { "epoch": 0.6733598444995275, "grad_norm": 5.1678853034973145, "learning_rate": 9.96342894312292e-06, "loss": 0.6027, "step": 113280 }, { "epoch": 0.6734192865761959, "grad_norm": 4.938029766082764, "learning_rate": 9.963403889018773e-06, "loss": 0.5487, "step": 113290 }, { "epoch": 0.6734787286528642, "grad_norm": 7.314818859100342, "learning_rate": 9.963378826367051e-06, "loss": 0.6912, "step": 113300 }, { "epoch": 0.6735381707295326, "grad_norm": 6.0162272453308105, "learning_rate": 9.963353755167801e-06, "loss": 0.6444, "step": 113310 }, { "epoch": 0.673597612806201, "grad_norm": 7.794460773468018, "learning_rate": 9.963328675421062e-06, "loss": 0.6437, "step": 113320 }, { "epoch": 0.6736570548828694, "grad_norm": 4.756523132324219, "learning_rate": 9.96330358712688e-06, "loss": 0.5405, "step": 113330 }, { "epoch": 0.6737164969595377, "grad_norm": 5.113330364227295, "learning_rate": 9.963278490285297e-06, "loss": 0.6008, "step": 113340 }, { "epoch": 0.6737759390362061, "grad_norm": 5.082225322723389, "learning_rate": 9.963253384896357e-06, "loss": 0.5926, "step": 113350 }, { "epoch": 0.6738353811128746, "grad_norm": 4.015984058380127, "learning_rate": 9.963228270960098e-06, "loss": 0.6041, "step": 113360 }, { "epoch": 0.673894823189543, "grad_norm": 6.660640716552734, "learning_rate": 9.963203148476573e-06, "loss": 0.5378, "step": 113370 }, { "epoch": 0.6739542652662114, "grad_norm": 6.190114498138428, "learning_rate": 9.963178017445819e-06, "loss": 0.594, "step": 113380 }, { "epoch": 0.6740137073428797, "grad_norm": 7.043298244476318, "learning_rate": 9.963152877867877e-06, "loss": 0.6296, "step": 113390 }, { "epoch": 0.6740731494195481, "grad_norm": 7.750344276428223, "learning_rate": 9.963127729742796e-06, "loss": 0.6442, "step": 113400 }, { "epoch": 0.6741325914962165, "grad_norm": 6.1638946533203125, "learning_rate": 9.963102573070617e-06, "loss": 0.5794, "step": 113410 }, { "epoch": 0.6741920335728849, "grad_norm": 5.327728271484375, "learning_rate": 9.963077407851382e-06, "loss": 0.5682, "step": 113420 }, { "epoch": 0.6742514756495533, "grad_norm": 4.839265823364258, "learning_rate": 9.963052234085136e-06, "loss": 0.5923, "step": 113430 }, { "epoch": 0.6743109177262216, "grad_norm": 5.330441474914551, "learning_rate": 9.963027051771922e-06, "loss": 0.6074, "step": 113440 }, { "epoch": 0.6743703598028901, "grad_norm": 5.613630771636963, "learning_rate": 9.963001860911784e-06, "loss": 0.6063, "step": 113450 }, { "epoch": 0.6744298018795585, "grad_norm": 6.500948905944824, "learning_rate": 9.962976661504765e-06, "loss": 0.6338, "step": 113460 }, { "epoch": 0.6744892439562269, "grad_norm": 8.296586036682129, "learning_rate": 9.962951453550907e-06, "loss": 0.662, "step": 113470 }, { "epoch": 0.6745486860328952, "grad_norm": 6.289194583892822, "learning_rate": 9.962926237050253e-06, "loss": 0.6407, "step": 113480 }, { "epoch": 0.6746081281095636, "grad_norm": 5.159368515014648, "learning_rate": 9.96290101200285e-06, "loss": 0.6433, "step": 113490 }, { "epoch": 0.674667570186232, "grad_norm": 4.499574661254883, "learning_rate": 9.962875778408737e-06, "loss": 0.6658, "step": 113500 }, { "epoch": 0.6747270122629004, "grad_norm": 5.705770015716553, "learning_rate": 9.962850536267962e-06, "loss": 0.6074, "step": 113510 }, { "epoch": 0.6747864543395689, "grad_norm": 5.453055381774902, "learning_rate": 9.962825285580566e-06, "loss": 0.586, "step": 113520 }, { "epoch": 0.6748458964162372, "grad_norm": 4.994008541107178, "learning_rate": 9.962800026346593e-06, "loss": 0.5974, "step": 113530 }, { "epoch": 0.6749053384929056, "grad_norm": 5.3788323402404785, "learning_rate": 9.962774758566085e-06, "loss": 0.5662, "step": 113540 }, { "epoch": 0.674964780569574, "grad_norm": 5.679376602172852, "learning_rate": 9.962749482239087e-06, "loss": 0.6251, "step": 113550 }, { "epoch": 0.6750242226462424, "grad_norm": 5.065828323364258, "learning_rate": 9.962724197365644e-06, "loss": 0.5889, "step": 113560 }, { "epoch": 0.6750836647229108, "grad_norm": 5.539783000946045, "learning_rate": 9.962698903945794e-06, "loss": 0.6623, "step": 113570 }, { "epoch": 0.6751431067995791, "grad_norm": 5.146625995635986, "learning_rate": 9.962673601979587e-06, "loss": 0.5973, "step": 113580 }, { "epoch": 0.6752025488762475, "grad_norm": 5.8231635093688965, "learning_rate": 9.962648291467063e-06, "loss": 0.622, "step": 113590 }, { "epoch": 0.675261990952916, "grad_norm": 5.426234245300293, "learning_rate": 9.962622972408267e-06, "loss": 0.5782, "step": 113600 }, { "epoch": 0.6753214330295844, "grad_norm": 5.336690425872803, "learning_rate": 9.962597644803242e-06, "loss": 0.6337, "step": 113610 }, { "epoch": 0.6753808751062527, "grad_norm": 5.155646800994873, "learning_rate": 9.962572308652032e-06, "loss": 0.5799, "step": 113620 }, { "epoch": 0.6754403171829211, "grad_norm": 6.235117435455322, "learning_rate": 9.96254696395468e-06, "loss": 0.6578, "step": 113630 }, { "epoch": 0.6754997592595895, "grad_norm": 5.552792549133301, "learning_rate": 9.962521610711232e-06, "loss": 0.6063, "step": 113640 }, { "epoch": 0.6755592013362579, "grad_norm": 6.7250518798828125, "learning_rate": 9.962496248921727e-06, "loss": 0.5886, "step": 113650 }, { "epoch": 0.6756186434129263, "grad_norm": 5.074028968811035, "learning_rate": 9.962470878586212e-06, "loss": 0.5804, "step": 113660 }, { "epoch": 0.6756780854895946, "grad_norm": 4.2630391120910645, "learning_rate": 9.962445499704729e-06, "loss": 0.5721, "step": 113670 }, { "epoch": 0.675737527566263, "grad_norm": 5.76242208480835, "learning_rate": 9.962420112277325e-06, "loss": 0.6069, "step": 113680 }, { "epoch": 0.6757969696429315, "grad_norm": 4.887130260467529, "learning_rate": 9.96239471630404e-06, "loss": 0.6546, "step": 113690 }, { "epoch": 0.6758564117195999, "grad_norm": 4.776150226593018, "learning_rate": 9.96236931178492e-06, "loss": 0.5854, "step": 113700 }, { "epoch": 0.6759158537962682, "grad_norm": 5.310485363006592, "learning_rate": 9.962343898720008e-06, "loss": 0.5529, "step": 113710 }, { "epoch": 0.6759752958729366, "grad_norm": 6.530803680419922, "learning_rate": 9.962318477109348e-06, "loss": 0.6383, "step": 113720 }, { "epoch": 0.676034737949605, "grad_norm": 5.970546722412109, "learning_rate": 9.962293046952981e-06, "loss": 0.6709, "step": 113730 }, { "epoch": 0.6760941800262734, "grad_norm": 5.5892181396484375, "learning_rate": 9.962267608250955e-06, "loss": 0.5844, "step": 113740 }, { "epoch": 0.6761536221029418, "grad_norm": 5.966219425201416, "learning_rate": 9.962242161003312e-06, "loss": 0.6427, "step": 113750 }, { "epoch": 0.6762130641796101, "grad_norm": 4.961429119110107, "learning_rate": 9.962216705210097e-06, "loss": 0.6217, "step": 113760 }, { "epoch": 0.6762725062562785, "grad_norm": 6.158301830291748, "learning_rate": 9.96219124087135e-06, "loss": 0.6946, "step": 113770 }, { "epoch": 0.676331948332947, "grad_norm": 4.594485759735107, "learning_rate": 9.962165767987121e-06, "loss": 0.5814, "step": 113780 }, { "epoch": 0.6763913904096154, "grad_norm": 4.266491889953613, "learning_rate": 9.96214028655745e-06, "loss": 0.5855, "step": 113790 }, { "epoch": 0.6764508324862838, "grad_norm": 5.15012788772583, "learning_rate": 9.962114796582378e-06, "loss": 0.6428, "step": 113800 }, { "epoch": 0.6765102745629521, "grad_norm": 4.373055934906006, "learning_rate": 9.962089298061955e-06, "loss": 0.5307, "step": 113810 }, { "epoch": 0.6765697166396205, "grad_norm": 6.007108211517334, "learning_rate": 9.962063790996222e-06, "loss": 0.634, "step": 113820 }, { "epoch": 0.6766291587162889, "grad_norm": 6.221463680267334, "learning_rate": 9.962038275385224e-06, "loss": 0.6271, "step": 113830 }, { "epoch": 0.6766886007929573, "grad_norm": 5.428189277648926, "learning_rate": 9.962012751229003e-06, "loss": 0.6066, "step": 113840 }, { "epoch": 0.6767480428696256, "grad_norm": 5.791386127471924, "learning_rate": 9.961987218527602e-06, "loss": 0.6553, "step": 113850 }, { "epoch": 0.6768074849462941, "grad_norm": 5.292335033416748, "learning_rate": 9.961961677281069e-06, "loss": 0.5951, "step": 113860 }, { "epoch": 0.6768669270229625, "grad_norm": 5.924658298492432, "learning_rate": 9.961936127489445e-06, "loss": 0.6613, "step": 113870 }, { "epoch": 0.6769263690996309, "grad_norm": 4.177394866943359, "learning_rate": 9.961910569152777e-06, "loss": 0.5754, "step": 113880 }, { "epoch": 0.6769858111762993, "grad_norm": 5.40127420425415, "learning_rate": 9.961885002271105e-06, "loss": 0.5869, "step": 113890 }, { "epoch": 0.6770452532529676, "grad_norm": 5.800424575805664, "learning_rate": 9.961859426844476e-06, "loss": 0.5636, "step": 113900 }, { "epoch": 0.677104695329636, "grad_norm": 6.498126029968262, "learning_rate": 9.961833842872932e-06, "loss": 0.6033, "step": 113910 }, { "epoch": 0.6771641374063044, "grad_norm": 4.694949626922607, "learning_rate": 9.961808250356519e-06, "loss": 0.565, "step": 113920 }, { "epoch": 0.6772235794829728, "grad_norm": 4.684945583343506, "learning_rate": 9.96178264929528e-06, "loss": 0.589, "step": 113930 }, { "epoch": 0.6772830215596413, "grad_norm": 6.993597984313965, "learning_rate": 9.961757039689258e-06, "loss": 0.6128, "step": 113940 }, { "epoch": 0.6773424636363096, "grad_norm": 5.647791862487793, "learning_rate": 9.961731421538499e-06, "loss": 0.6468, "step": 113950 }, { "epoch": 0.677401905712978, "grad_norm": 5.6274895668029785, "learning_rate": 9.961705794843048e-06, "loss": 0.5906, "step": 113960 }, { "epoch": 0.6774613477896464, "grad_norm": 5.160347938537598, "learning_rate": 9.961680159602946e-06, "loss": 0.6054, "step": 113970 }, { "epoch": 0.6775207898663148, "grad_norm": 5.945274829864502, "learning_rate": 9.961654515818239e-06, "loss": 0.5907, "step": 113980 }, { "epoch": 0.6775802319429831, "grad_norm": 4.729109764099121, "learning_rate": 9.96162886348897e-06, "loss": 0.6826, "step": 113990 }, { "epoch": 0.6776396740196515, "grad_norm": 4.494281768798828, "learning_rate": 9.961603202615186e-06, "loss": 0.6164, "step": 114000 }, { "epoch": 0.6776991160963199, "grad_norm": 5.925613880157471, "learning_rate": 9.961577533196929e-06, "loss": 0.6271, "step": 114010 }, { "epoch": 0.6777585581729884, "grad_norm": 6.629741191864014, "learning_rate": 9.961551855234243e-06, "loss": 0.616, "step": 114020 }, { "epoch": 0.6778180002496568, "grad_norm": 5.366472244262695, "learning_rate": 9.961526168727171e-06, "loss": 0.5806, "step": 114030 }, { "epoch": 0.6778774423263251, "grad_norm": 7.382959365844727, "learning_rate": 9.961500473675762e-06, "loss": 0.6275, "step": 114040 }, { "epoch": 0.6779368844029935, "grad_norm": 7.377974987030029, "learning_rate": 9.961474770080055e-06, "loss": 0.6041, "step": 114050 }, { "epoch": 0.6779963264796619, "grad_norm": 10.847550392150879, "learning_rate": 9.961449057940098e-06, "loss": 0.5973, "step": 114060 }, { "epoch": 0.6780557685563303, "grad_norm": 5.677419662475586, "learning_rate": 9.961423337255933e-06, "loss": 0.5452, "step": 114070 }, { "epoch": 0.6781152106329986, "grad_norm": 5.493436336517334, "learning_rate": 9.961397608027605e-06, "loss": 0.5819, "step": 114080 }, { "epoch": 0.678174652709667, "grad_norm": 6.082860469818115, "learning_rate": 9.961371870255158e-06, "loss": 0.5376, "step": 114090 }, { "epoch": 0.6782340947863355, "grad_norm": 6.196935176849365, "learning_rate": 9.961346123938638e-06, "loss": 0.6345, "step": 114100 }, { "epoch": 0.6782935368630039, "grad_norm": 5.805092811584473, "learning_rate": 9.961320369078085e-06, "loss": 0.5958, "step": 114110 }, { "epoch": 0.6783529789396723, "grad_norm": 7.176531791687012, "learning_rate": 9.96129460567355e-06, "loss": 0.6089, "step": 114120 }, { "epoch": 0.6784124210163406, "grad_norm": 6.221773624420166, "learning_rate": 9.96126883372507e-06, "loss": 0.5937, "step": 114130 }, { "epoch": 0.678471863093009, "grad_norm": 5.1437177658081055, "learning_rate": 9.961243053232697e-06, "loss": 0.6308, "step": 114140 }, { "epoch": 0.6785313051696774, "grad_norm": 5.685975074768066, "learning_rate": 9.96121726419647e-06, "loss": 0.6, "step": 114150 }, { "epoch": 0.6785907472463458, "grad_norm": 4.799402713775635, "learning_rate": 9.961191466616433e-06, "loss": 0.5826, "step": 114160 }, { "epoch": 0.6786501893230142, "grad_norm": 4.972311496734619, "learning_rate": 9.961165660492634e-06, "loss": 0.6088, "step": 114170 }, { "epoch": 0.6787096313996825, "grad_norm": 5.699368476867676, "learning_rate": 9.961139845825116e-06, "loss": 0.6094, "step": 114180 }, { "epoch": 0.678769073476351, "grad_norm": 5.538949012756348, "learning_rate": 9.961114022613923e-06, "loss": 0.6513, "step": 114190 }, { "epoch": 0.6788285155530194, "grad_norm": 6.188854217529297, "learning_rate": 9.961088190859099e-06, "loss": 0.5861, "step": 114200 }, { "epoch": 0.6788879576296878, "grad_norm": 6.995932579040527, "learning_rate": 9.96106235056069e-06, "loss": 0.6126, "step": 114210 }, { "epoch": 0.6789473997063561, "grad_norm": 5.431447505950928, "learning_rate": 9.96103650171874e-06, "loss": 0.6298, "step": 114220 }, { "epoch": 0.6790068417830245, "grad_norm": 5.876989841461182, "learning_rate": 9.961010644333293e-06, "loss": 0.6064, "step": 114230 }, { "epoch": 0.6790662838596929, "grad_norm": 5.563825607299805, "learning_rate": 9.960984778404393e-06, "loss": 0.616, "step": 114240 }, { "epoch": 0.6791257259363613, "grad_norm": 4.5771284103393555, "learning_rate": 9.960958903932086e-06, "loss": 0.614, "step": 114250 }, { "epoch": 0.6791851680130297, "grad_norm": 5.889124393463135, "learning_rate": 9.960933020916415e-06, "loss": 0.665, "step": 114260 }, { "epoch": 0.679244610089698, "grad_norm": 4.881392002105713, "learning_rate": 9.960907129357427e-06, "loss": 0.5478, "step": 114270 }, { "epoch": 0.6793040521663665, "grad_norm": 5.080090522766113, "learning_rate": 9.960881229255162e-06, "loss": 0.5493, "step": 114280 }, { "epoch": 0.6793634942430349, "grad_norm": 6.357468128204346, "learning_rate": 9.96085532060967e-06, "loss": 0.6807, "step": 114290 }, { "epoch": 0.6794229363197033, "grad_norm": 7.413365364074707, "learning_rate": 9.960829403420994e-06, "loss": 0.6033, "step": 114300 }, { "epoch": 0.6794823783963716, "grad_norm": 7.242222785949707, "learning_rate": 9.960803477689177e-06, "loss": 0.6096, "step": 114310 }, { "epoch": 0.67954182047304, "grad_norm": 4.394933223724365, "learning_rate": 9.960777543414263e-06, "loss": 0.6395, "step": 114320 }, { "epoch": 0.6796012625497084, "grad_norm": 4.812204360961914, "learning_rate": 9.9607516005963e-06, "loss": 0.624, "step": 114330 }, { "epoch": 0.6796607046263768, "grad_norm": 4.966134071350098, "learning_rate": 9.96072564923533e-06, "loss": 0.5629, "step": 114340 }, { "epoch": 0.6797201467030453, "grad_norm": 4.96307897567749, "learning_rate": 9.960699689331398e-06, "loss": 0.5869, "step": 114350 }, { "epoch": 0.6797795887797136, "grad_norm": 5.954005241394043, "learning_rate": 9.96067372088455e-06, "loss": 0.5839, "step": 114360 }, { "epoch": 0.679839030856382, "grad_norm": 5.96129846572876, "learning_rate": 9.960647743894829e-06, "loss": 0.6687, "step": 114370 }, { "epoch": 0.6798984729330504, "grad_norm": 7.43756103515625, "learning_rate": 9.96062175836228e-06, "loss": 0.6591, "step": 114380 }, { "epoch": 0.6799579150097188, "grad_norm": 4.958880424499512, "learning_rate": 9.960595764286951e-06, "loss": 0.6045, "step": 114390 }, { "epoch": 0.6800173570863872, "grad_norm": 6.120213508605957, "learning_rate": 9.960569761668883e-06, "loss": 0.6013, "step": 114400 }, { "epoch": 0.6800767991630555, "grad_norm": 5.345414638519287, "learning_rate": 9.960543750508122e-06, "loss": 0.6525, "step": 114410 }, { "epoch": 0.6801362412397239, "grad_norm": 4.722380638122559, "learning_rate": 9.960517730804715e-06, "loss": 0.6148, "step": 114420 }, { "epoch": 0.6801956833163924, "grad_norm": 5.5669074058532715, "learning_rate": 9.9604917025587e-06, "loss": 0.5981, "step": 114430 }, { "epoch": 0.6802551253930608, "grad_norm": 5.282907009124756, "learning_rate": 9.960465665770131e-06, "loss": 0.6248, "step": 114440 }, { "epoch": 0.6803145674697291, "grad_norm": 6.7320380210876465, "learning_rate": 9.960439620439046e-06, "loss": 0.6461, "step": 114450 }, { "epoch": 0.6803740095463975, "grad_norm": 6.23256254196167, "learning_rate": 9.960413566565493e-06, "loss": 0.5851, "step": 114460 }, { "epoch": 0.6804334516230659, "grad_norm": 5.527684688568115, "learning_rate": 9.960387504149514e-06, "loss": 0.5588, "step": 114470 }, { "epoch": 0.6804928936997343, "grad_norm": 5.463128089904785, "learning_rate": 9.960361433191157e-06, "loss": 0.5974, "step": 114480 }, { "epoch": 0.6805523357764027, "grad_norm": 4.951424598693848, "learning_rate": 9.960335353690467e-06, "loss": 0.5971, "step": 114490 }, { "epoch": 0.680611777853071, "grad_norm": 4.778226375579834, "learning_rate": 9.960309265647486e-06, "loss": 0.6061, "step": 114500 }, { "epoch": 0.6806712199297394, "grad_norm": 3.97214412689209, "learning_rate": 9.96028316906226e-06, "loss": 0.5578, "step": 114510 }, { "epoch": 0.6807306620064079, "grad_norm": 5.934713363647461, "learning_rate": 9.960257063934835e-06, "loss": 0.5153, "step": 114520 }, { "epoch": 0.6807901040830763, "grad_norm": 5.281449794769287, "learning_rate": 9.960230950265257e-06, "loss": 0.5986, "step": 114530 }, { "epoch": 0.6808495461597447, "grad_norm": 4.617093563079834, "learning_rate": 9.960204828053567e-06, "loss": 0.6042, "step": 114540 }, { "epoch": 0.680908988236413, "grad_norm": 4.744372844696045, "learning_rate": 9.960178697299816e-06, "loss": 0.614, "step": 114550 }, { "epoch": 0.6809684303130814, "grad_norm": 6.513713836669922, "learning_rate": 9.960152558004044e-06, "loss": 0.5939, "step": 114560 }, { "epoch": 0.6810278723897498, "grad_norm": 5.795781135559082, "learning_rate": 9.960126410166295e-06, "loss": 0.5995, "step": 114570 }, { "epoch": 0.6810873144664182, "grad_norm": 4.70766019821167, "learning_rate": 9.96010025378662e-06, "loss": 0.5736, "step": 114580 }, { "epoch": 0.6811467565430865, "grad_norm": 5.284221649169922, "learning_rate": 9.960074088865058e-06, "loss": 0.6136, "step": 114590 }, { "epoch": 0.681206198619755, "grad_norm": 5.241771221160889, "learning_rate": 9.960047915401659e-06, "loss": 0.6285, "step": 114600 }, { "epoch": 0.6812656406964234, "grad_norm": 6.844364166259766, "learning_rate": 9.960021733396463e-06, "loss": 0.574, "step": 114610 }, { "epoch": 0.6813250827730918, "grad_norm": 5.366330146789551, "learning_rate": 9.959995542849519e-06, "loss": 0.5969, "step": 114620 }, { "epoch": 0.6813845248497602, "grad_norm": 6.379650592803955, "learning_rate": 9.959969343760871e-06, "loss": 0.5989, "step": 114630 }, { "epoch": 0.6814439669264285, "grad_norm": 5.361098766326904, "learning_rate": 9.959943136130563e-06, "loss": 0.6132, "step": 114640 }, { "epoch": 0.6815034090030969, "grad_norm": 5.591732501983643, "learning_rate": 9.959916919958643e-06, "loss": 0.6384, "step": 114650 }, { "epoch": 0.6815628510797653, "grad_norm": 5.639347553253174, "learning_rate": 9.959890695245152e-06, "loss": 0.6223, "step": 114660 }, { "epoch": 0.6816222931564337, "grad_norm": 4.646635055541992, "learning_rate": 9.959864461990139e-06, "loss": 0.6384, "step": 114670 }, { "epoch": 0.681681735233102, "grad_norm": 6.476751804351807, "learning_rate": 9.959838220193648e-06, "loss": 0.6624, "step": 114680 }, { "epoch": 0.6817411773097705, "grad_norm": 5.078221797943115, "learning_rate": 9.959811969855722e-06, "loss": 0.628, "step": 114690 }, { "epoch": 0.6818006193864389, "grad_norm": 5.201532363891602, "learning_rate": 9.959785710976408e-06, "loss": 0.5673, "step": 114700 }, { "epoch": 0.6818600614631073, "grad_norm": 6.7885966300964355, "learning_rate": 9.959759443555754e-06, "loss": 0.6468, "step": 114710 }, { "epoch": 0.6819195035397757, "grad_norm": 5.0607757568359375, "learning_rate": 9.9597331675938e-06, "loss": 0.64, "step": 114720 }, { "epoch": 0.681978945616444, "grad_norm": 5.787022113800049, "learning_rate": 9.959706883090595e-06, "loss": 0.6293, "step": 114730 }, { "epoch": 0.6820383876931124, "grad_norm": 5.470417022705078, "learning_rate": 9.959680590046181e-06, "loss": 0.569, "step": 114740 }, { "epoch": 0.6820978297697808, "grad_norm": 5.8209123611450195, "learning_rate": 9.959654288460607e-06, "loss": 0.5469, "step": 114750 }, { "epoch": 0.6821572718464493, "grad_norm": 6.924323081970215, "learning_rate": 9.959627978333917e-06, "loss": 0.6724, "step": 114760 }, { "epoch": 0.6822167139231177, "grad_norm": 6.399467468261719, "learning_rate": 9.959601659666154e-06, "loss": 0.5846, "step": 114770 }, { "epoch": 0.682276155999786, "grad_norm": 5.355036735534668, "learning_rate": 9.959575332457366e-06, "loss": 0.5935, "step": 114780 }, { "epoch": 0.6823355980764544, "grad_norm": 6.589049339294434, "learning_rate": 9.959548996707597e-06, "loss": 0.6782, "step": 114790 }, { "epoch": 0.6823950401531228, "grad_norm": 5.62214469909668, "learning_rate": 9.959522652416894e-06, "loss": 0.5932, "step": 114800 }, { "epoch": 0.6824544822297912, "grad_norm": 4.796596527099609, "learning_rate": 9.9594962995853e-06, "loss": 0.5425, "step": 114810 }, { "epoch": 0.6825139243064595, "grad_norm": 7.440911769866943, "learning_rate": 9.959469938212863e-06, "loss": 0.578, "step": 114820 }, { "epoch": 0.6825733663831279, "grad_norm": 5.160447597503662, "learning_rate": 9.959443568299626e-06, "loss": 0.5772, "step": 114830 }, { "epoch": 0.6826328084597963, "grad_norm": 4.648860454559326, "learning_rate": 9.959417189845636e-06, "loss": 0.6283, "step": 114840 }, { "epoch": 0.6826922505364648, "grad_norm": 6.695168495178223, "learning_rate": 9.959390802850937e-06, "loss": 0.6257, "step": 114850 }, { "epoch": 0.6827516926131332, "grad_norm": 4.9512038230896, "learning_rate": 9.959364407315577e-06, "loss": 0.6166, "step": 114860 }, { "epoch": 0.6828111346898015, "grad_norm": 4.783190727233887, "learning_rate": 9.959338003239598e-06, "loss": 0.6198, "step": 114870 }, { "epoch": 0.6828705767664699, "grad_norm": 6.3553876876831055, "learning_rate": 9.959311590623048e-06, "loss": 0.5967, "step": 114880 }, { "epoch": 0.6829300188431383, "grad_norm": 5.875858783721924, "learning_rate": 9.95928516946597e-06, "loss": 0.5938, "step": 114890 }, { "epoch": 0.6829894609198067, "grad_norm": 5.895968914031982, "learning_rate": 9.959258739768413e-06, "loss": 0.6154, "step": 114900 }, { "epoch": 0.6830489029964751, "grad_norm": 5.1333441734313965, "learning_rate": 9.959232301530421e-06, "loss": 0.5991, "step": 114910 }, { "epoch": 0.6831083450731434, "grad_norm": 5.935365200042725, "learning_rate": 9.959205854752038e-06, "loss": 0.6091, "step": 114920 }, { "epoch": 0.6831677871498119, "grad_norm": 4.749085426330566, "learning_rate": 9.959179399433313e-06, "loss": 0.596, "step": 114930 }, { "epoch": 0.6832272292264803, "grad_norm": 5.247063636779785, "learning_rate": 9.959152935574287e-06, "loss": 0.6649, "step": 114940 }, { "epoch": 0.6832866713031487, "grad_norm": 5.7924089431762695, "learning_rate": 9.959126463175009e-06, "loss": 0.6339, "step": 114950 }, { "epoch": 0.683346113379817, "grad_norm": 4.8216753005981445, "learning_rate": 9.959099982235525e-06, "loss": 0.6546, "step": 114960 }, { "epoch": 0.6834055554564854, "grad_norm": 6.959636688232422, "learning_rate": 9.959073492755876e-06, "loss": 0.6606, "step": 114970 }, { "epoch": 0.6834649975331538, "grad_norm": 6.342580318450928, "learning_rate": 9.959046994736113e-06, "loss": 0.635, "step": 114980 }, { "epoch": 0.6835244396098222, "grad_norm": 4.40194034576416, "learning_rate": 9.959020488176279e-06, "loss": 0.5687, "step": 114990 }, { "epoch": 0.6835838816864906, "grad_norm": 5.846367359161377, "learning_rate": 9.958993973076418e-06, "loss": 0.6027, "step": 115000 }, { "epoch": 0.683643323763159, "grad_norm": 5.146602153778076, "learning_rate": 9.95896744943658e-06, "loss": 0.6407, "step": 115010 }, { "epoch": 0.6837027658398274, "grad_norm": 5.4572434425354, "learning_rate": 9.958940917256808e-06, "loss": 0.6302, "step": 115020 }, { "epoch": 0.6837622079164958, "grad_norm": 5.090849876403809, "learning_rate": 9.958914376537147e-06, "loss": 0.5766, "step": 115030 }, { "epoch": 0.6838216499931642, "grad_norm": 6.018245697021484, "learning_rate": 9.958887827277645e-06, "loss": 0.5987, "step": 115040 }, { "epoch": 0.6838810920698325, "grad_norm": 5.014506816864014, "learning_rate": 9.958861269478345e-06, "loss": 0.605, "step": 115050 }, { "epoch": 0.6839405341465009, "grad_norm": 6.405581474304199, "learning_rate": 9.958834703139295e-06, "loss": 0.6488, "step": 115060 }, { "epoch": 0.6839999762231693, "grad_norm": 5.158786773681641, "learning_rate": 9.95880812826054e-06, "loss": 0.5562, "step": 115070 }, { "epoch": 0.6840594182998377, "grad_norm": 5.815329074859619, "learning_rate": 9.958781544842127e-06, "loss": 0.6226, "step": 115080 }, { "epoch": 0.6841188603765062, "grad_norm": 4.001725673675537, "learning_rate": 9.9587549528841e-06, "loss": 0.544, "step": 115090 }, { "epoch": 0.6841783024531745, "grad_norm": 4.632465839385986, "learning_rate": 9.958728352386502e-06, "loss": 0.6313, "step": 115100 }, { "epoch": 0.6842377445298429, "grad_norm": 5.64350700378418, "learning_rate": 9.958701743349387e-06, "loss": 0.6092, "step": 115110 }, { "epoch": 0.6842971866065113, "grad_norm": 4.041754245758057, "learning_rate": 9.958675125772792e-06, "loss": 0.5563, "step": 115120 }, { "epoch": 0.6843566286831797, "grad_norm": 5.709334373474121, "learning_rate": 9.95864849965677e-06, "loss": 0.6672, "step": 115130 }, { "epoch": 0.6844160707598481, "grad_norm": 5.340804576873779, "learning_rate": 9.958621865001361e-06, "loss": 0.6641, "step": 115140 }, { "epoch": 0.6844755128365164, "grad_norm": 6.526797294616699, "learning_rate": 9.958595221806615e-06, "loss": 0.659, "step": 115150 }, { "epoch": 0.6845349549131848, "grad_norm": 3.903622627258301, "learning_rate": 9.958568570072575e-06, "loss": 0.5792, "step": 115160 }, { "epoch": 0.6845943969898532, "grad_norm": 6.5480475425720215, "learning_rate": 9.95854190979929e-06, "loss": 0.6187, "step": 115170 }, { "epoch": 0.6846538390665217, "grad_norm": 5.726294994354248, "learning_rate": 9.958515240986803e-06, "loss": 0.6522, "step": 115180 }, { "epoch": 0.68471328114319, "grad_norm": 6.284199237823486, "learning_rate": 9.958488563635161e-06, "loss": 0.6292, "step": 115190 }, { "epoch": 0.6847727232198584, "grad_norm": 5.608715534210205, "learning_rate": 9.958461877744412e-06, "loss": 0.6163, "step": 115200 }, { "epoch": 0.6848321652965268, "grad_norm": 5.223081588745117, "learning_rate": 9.958435183314598e-06, "loss": 0.6409, "step": 115210 }, { "epoch": 0.6848916073731952, "grad_norm": 4.292306423187256, "learning_rate": 9.958408480345767e-06, "loss": 0.5911, "step": 115220 }, { "epoch": 0.6849510494498636, "grad_norm": 4.918951511383057, "learning_rate": 9.958381768837966e-06, "loss": 0.6336, "step": 115230 }, { "epoch": 0.6850104915265319, "grad_norm": 6.477453708648682, "learning_rate": 9.958355048791239e-06, "loss": 0.6368, "step": 115240 }, { "epoch": 0.6850699336032003, "grad_norm": 6.401150226593018, "learning_rate": 9.958328320205633e-06, "loss": 0.5857, "step": 115250 }, { "epoch": 0.6851293756798688, "grad_norm": 5.259132385253906, "learning_rate": 9.958301583081196e-06, "loss": 0.5525, "step": 115260 }, { "epoch": 0.6851888177565372, "grad_norm": 5.2065887451171875, "learning_rate": 9.95827483741797e-06, "loss": 0.5832, "step": 115270 }, { "epoch": 0.6852482598332056, "grad_norm": 5.181210517883301, "learning_rate": 9.958248083216003e-06, "loss": 0.6146, "step": 115280 }, { "epoch": 0.6853077019098739, "grad_norm": 3.9400100708007812, "learning_rate": 9.958221320475342e-06, "loss": 0.6207, "step": 115290 }, { "epoch": 0.6853671439865423, "grad_norm": 5.820122241973877, "learning_rate": 9.958194549196032e-06, "loss": 0.6204, "step": 115300 }, { "epoch": 0.6854265860632107, "grad_norm": 4.841937065124512, "learning_rate": 9.958167769378119e-06, "loss": 0.5752, "step": 115310 }, { "epoch": 0.6854860281398791, "grad_norm": 6.324956893920898, "learning_rate": 9.958140981021652e-06, "loss": 0.682, "step": 115320 }, { "epoch": 0.6855454702165474, "grad_norm": 5.482596397399902, "learning_rate": 9.958114184126672e-06, "loss": 0.6157, "step": 115330 }, { "epoch": 0.6856049122932159, "grad_norm": 6.415208339691162, "learning_rate": 9.958087378693228e-06, "loss": 0.5901, "step": 115340 }, { "epoch": 0.6856643543698843, "grad_norm": 5.337253093719482, "learning_rate": 9.958060564721366e-06, "loss": 0.6028, "step": 115350 }, { "epoch": 0.6857237964465527, "grad_norm": 5.894495487213135, "learning_rate": 9.958033742211133e-06, "loss": 0.6009, "step": 115360 }, { "epoch": 0.6857832385232211, "grad_norm": 5.948359489440918, "learning_rate": 9.958006911162574e-06, "loss": 0.6595, "step": 115370 }, { "epoch": 0.6858426805998894, "grad_norm": 5.115494251251221, "learning_rate": 9.957980071575735e-06, "loss": 0.6049, "step": 115380 }, { "epoch": 0.6859021226765578, "grad_norm": 5.909792423248291, "learning_rate": 9.957953223450663e-06, "loss": 0.6281, "step": 115390 }, { "epoch": 0.6859615647532262, "grad_norm": 5.079214572906494, "learning_rate": 9.957926366787405e-06, "loss": 0.5545, "step": 115400 }, { "epoch": 0.6860210068298946, "grad_norm": 6.6312360763549805, "learning_rate": 9.957899501586003e-06, "loss": 0.6091, "step": 115410 }, { "epoch": 0.686080448906563, "grad_norm": 6.43118143081665, "learning_rate": 9.95787262784651e-06, "loss": 0.659, "step": 115420 }, { "epoch": 0.6861398909832314, "grad_norm": 4.543292999267578, "learning_rate": 9.957845745568967e-06, "loss": 0.5993, "step": 115430 }, { "epoch": 0.6861993330598998, "grad_norm": 6.262753486633301, "learning_rate": 9.957818854753423e-06, "loss": 0.5955, "step": 115440 }, { "epoch": 0.6862587751365682, "grad_norm": 4.552673816680908, "learning_rate": 9.957791955399922e-06, "loss": 0.562, "step": 115450 }, { "epoch": 0.6863182172132366, "grad_norm": 6.962562561035156, "learning_rate": 9.957765047508513e-06, "loss": 0.6288, "step": 115460 }, { "epoch": 0.6863776592899049, "grad_norm": 7.003486633300781, "learning_rate": 9.957738131079242e-06, "loss": 0.6429, "step": 115470 }, { "epoch": 0.6864371013665733, "grad_norm": 4.570470809936523, "learning_rate": 9.957711206112152e-06, "loss": 0.6453, "step": 115480 }, { "epoch": 0.6864965434432417, "grad_norm": 6.491382598876953, "learning_rate": 9.957684272607294e-06, "loss": 0.5826, "step": 115490 }, { "epoch": 0.6865559855199102, "grad_norm": 5.301136016845703, "learning_rate": 9.957657330564711e-06, "loss": 0.6083, "step": 115500 }, { "epoch": 0.6866154275965786, "grad_norm": 5.122293472290039, "learning_rate": 9.957630379984452e-06, "loss": 0.5984, "step": 115510 }, { "epoch": 0.6866748696732469, "grad_norm": 4.842255592346191, "learning_rate": 9.957603420866559e-06, "loss": 0.6339, "step": 115520 }, { "epoch": 0.6867343117499153, "grad_norm": 4.63966178894043, "learning_rate": 9.957576453211083e-06, "loss": 0.6069, "step": 115530 }, { "epoch": 0.6867937538265837, "grad_norm": 4.787319183349609, "learning_rate": 9.957549477018068e-06, "loss": 0.5935, "step": 115540 }, { "epoch": 0.6868531959032521, "grad_norm": 6.233270168304443, "learning_rate": 9.957522492287562e-06, "loss": 0.6148, "step": 115550 }, { "epoch": 0.6869126379799204, "grad_norm": 4.414029121398926, "learning_rate": 9.957495499019612e-06, "loss": 0.6117, "step": 115560 }, { "epoch": 0.6869720800565888, "grad_norm": 7.426120758056641, "learning_rate": 9.95746849721426e-06, "loss": 0.6364, "step": 115570 }, { "epoch": 0.6870315221332572, "grad_norm": 5.874342441558838, "learning_rate": 9.95744148687156e-06, "loss": 0.5047, "step": 115580 }, { "epoch": 0.6870909642099257, "grad_norm": 5.030777454376221, "learning_rate": 9.95741446799155e-06, "loss": 0.6142, "step": 115590 }, { "epoch": 0.6871504062865941, "grad_norm": 6.659278869628906, "learning_rate": 9.957387440574284e-06, "loss": 0.6436, "step": 115600 }, { "epoch": 0.6872098483632624, "grad_norm": 5.3478779792785645, "learning_rate": 9.957360404619802e-06, "loss": 0.5791, "step": 115610 }, { "epoch": 0.6872692904399308, "grad_norm": 6.049409866333008, "learning_rate": 9.957333360128157e-06, "loss": 0.6251, "step": 115620 }, { "epoch": 0.6873287325165992, "grad_norm": 7.4580159187316895, "learning_rate": 9.957306307099391e-06, "loss": 0.596, "step": 115630 }, { "epoch": 0.6873881745932676, "grad_norm": 4.356368541717529, "learning_rate": 9.957279245533553e-06, "loss": 0.6313, "step": 115640 }, { "epoch": 0.687447616669936, "grad_norm": 6.443855285644531, "learning_rate": 9.957252175430687e-06, "loss": 0.6512, "step": 115650 }, { "epoch": 0.6875070587466043, "grad_norm": 5.678430557250977, "learning_rate": 9.957225096790843e-06, "loss": 0.5978, "step": 115660 }, { "epoch": 0.6875665008232728, "grad_norm": 5.6885085105896, "learning_rate": 9.957198009614066e-06, "loss": 0.5768, "step": 115670 }, { "epoch": 0.6876259428999412, "grad_norm": 4.769429683685303, "learning_rate": 9.957170913900401e-06, "loss": 0.6107, "step": 115680 }, { "epoch": 0.6876853849766096, "grad_norm": 6.542490482330322, "learning_rate": 9.957143809649898e-06, "loss": 0.6163, "step": 115690 }, { "epoch": 0.6877448270532779, "grad_norm": 5.847188472747803, "learning_rate": 9.957116696862602e-06, "loss": 0.5576, "step": 115700 }, { "epoch": 0.6878042691299463, "grad_norm": 6.250483989715576, "learning_rate": 9.957089575538557e-06, "loss": 0.6495, "step": 115710 }, { "epoch": 0.6878637112066147, "grad_norm": 6.686094284057617, "learning_rate": 9.957062445677813e-06, "loss": 0.6206, "step": 115720 }, { "epoch": 0.6879231532832831, "grad_norm": 6.4312310218811035, "learning_rate": 9.957035307280418e-06, "loss": 0.6484, "step": 115730 }, { "epoch": 0.6879825953599515, "grad_norm": 5.802048206329346, "learning_rate": 9.957008160346415e-06, "loss": 0.6366, "step": 115740 }, { "epoch": 0.6880420374366198, "grad_norm": 5.5716166496276855, "learning_rate": 9.956981004875851e-06, "loss": 0.6094, "step": 115750 }, { "epoch": 0.6881014795132883, "grad_norm": 6.219053745269775, "learning_rate": 9.956953840868778e-06, "loss": 0.6104, "step": 115760 }, { "epoch": 0.6881609215899567, "grad_norm": 5.055274486541748, "learning_rate": 9.956926668325237e-06, "loss": 0.5287, "step": 115770 }, { "epoch": 0.6882203636666251, "grad_norm": 4.508154392242432, "learning_rate": 9.956899487245278e-06, "loss": 0.6069, "step": 115780 }, { "epoch": 0.6882798057432934, "grad_norm": 6.435368061065674, "learning_rate": 9.956872297628944e-06, "loss": 0.6023, "step": 115790 }, { "epoch": 0.6883392478199618, "grad_norm": 4.636332988739014, "learning_rate": 9.956845099476287e-06, "loss": 0.5836, "step": 115800 }, { "epoch": 0.6883986898966302, "grad_norm": 6.1211466789245605, "learning_rate": 9.956817892787349e-06, "loss": 0.5996, "step": 115810 }, { "epoch": 0.6884581319732986, "grad_norm": 5.687148094177246, "learning_rate": 9.956790677562182e-06, "loss": 0.6482, "step": 115820 }, { "epoch": 0.688517574049967, "grad_norm": 5.6541571617126465, "learning_rate": 9.956763453800829e-06, "loss": 0.6325, "step": 115830 }, { "epoch": 0.6885770161266354, "grad_norm": 5.365921974182129, "learning_rate": 9.956736221503337e-06, "loss": 0.6185, "step": 115840 }, { "epoch": 0.6886364582033038, "grad_norm": 5.498068809509277, "learning_rate": 9.956708980669753e-06, "loss": 0.6049, "step": 115850 }, { "epoch": 0.6886959002799722, "grad_norm": 6.644711971282959, "learning_rate": 9.956681731300126e-06, "loss": 0.5658, "step": 115860 }, { "epoch": 0.6887553423566406, "grad_norm": 5.2991204261779785, "learning_rate": 9.956654473394503e-06, "loss": 0.6296, "step": 115870 }, { "epoch": 0.688814784433309, "grad_norm": 6.599851131439209, "learning_rate": 9.956627206952928e-06, "loss": 0.6085, "step": 115880 }, { "epoch": 0.6888742265099773, "grad_norm": 6.853374481201172, "learning_rate": 9.95659993197545e-06, "loss": 0.6733, "step": 115890 }, { "epoch": 0.6889336685866457, "grad_norm": 5.960117816925049, "learning_rate": 9.956572648462114e-06, "loss": 0.6093, "step": 115900 }, { "epoch": 0.6889931106633141, "grad_norm": 5.535553455352783, "learning_rate": 9.95654535641297e-06, "loss": 0.619, "step": 115910 }, { "epoch": 0.6890525527399826, "grad_norm": 5.037399768829346, "learning_rate": 9.956518055828063e-06, "loss": 0.6061, "step": 115920 }, { "epoch": 0.6891119948166509, "grad_norm": 6.066760063171387, "learning_rate": 9.95649074670744e-06, "loss": 0.6871, "step": 115930 }, { "epoch": 0.6891714368933193, "grad_norm": 7.03123140335083, "learning_rate": 9.95646342905115e-06, "loss": 0.612, "step": 115940 }, { "epoch": 0.6892308789699877, "grad_norm": 3.920078754425049, "learning_rate": 9.95643610285924e-06, "loss": 0.619, "step": 115950 }, { "epoch": 0.6892903210466561, "grad_norm": 5.300558090209961, "learning_rate": 9.956408768131752e-06, "loss": 0.599, "step": 115960 }, { "epoch": 0.6893497631233245, "grad_norm": 5.353231430053711, "learning_rate": 9.956381424868738e-06, "loss": 0.6275, "step": 115970 }, { "epoch": 0.6894092051999928, "grad_norm": 5.166824817657471, "learning_rate": 9.956354073070245e-06, "loss": 0.5986, "step": 115980 }, { "epoch": 0.6894686472766612, "grad_norm": 6.873976230621338, "learning_rate": 9.956326712736317e-06, "loss": 0.657, "step": 115990 }, { "epoch": 0.6895280893533297, "grad_norm": 4.730854511260986, "learning_rate": 9.956299343867005e-06, "loss": 0.5992, "step": 116000 }, { "epoch": 0.6895875314299981, "grad_norm": 5.80190896987915, "learning_rate": 9.956271966462352e-06, "loss": 0.5579, "step": 116010 }, { "epoch": 0.6896469735066665, "grad_norm": 4.3175811767578125, "learning_rate": 9.95624458052241e-06, "loss": 0.6001, "step": 116020 }, { "epoch": 0.6897064155833348, "grad_norm": 5.718766212463379, "learning_rate": 9.956217186047222e-06, "loss": 0.6336, "step": 116030 }, { "epoch": 0.6897658576600032, "grad_norm": 5.571310997009277, "learning_rate": 9.956189783036836e-06, "loss": 0.5885, "step": 116040 }, { "epoch": 0.6898252997366716, "grad_norm": 6.993130683898926, "learning_rate": 9.9561623714913e-06, "loss": 0.6629, "step": 116050 }, { "epoch": 0.68988474181334, "grad_norm": 4.671098232269287, "learning_rate": 9.956134951410662e-06, "loss": 0.5927, "step": 116060 }, { "epoch": 0.6899441838900083, "grad_norm": 3.9492428302764893, "learning_rate": 9.956107522794966e-06, "loss": 0.612, "step": 116070 }, { "epoch": 0.6900036259666767, "grad_norm": 5.788619518280029, "learning_rate": 9.956080085644263e-06, "loss": 0.6215, "step": 116080 }, { "epoch": 0.6900630680433452, "grad_norm": 4.891834259033203, "learning_rate": 9.956052639958599e-06, "loss": 0.569, "step": 116090 }, { "epoch": 0.6901225101200136, "grad_norm": 6.527020454406738, "learning_rate": 9.956025185738021e-06, "loss": 0.6118, "step": 116100 }, { "epoch": 0.690181952196682, "grad_norm": 4.6433868408203125, "learning_rate": 9.955997722982576e-06, "loss": 0.5572, "step": 116110 }, { "epoch": 0.6902413942733503, "grad_norm": 6.13136625289917, "learning_rate": 9.955970251692314e-06, "loss": 0.5523, "step": 116120 }, { "epoch": 0.6903008363500187, "grad_norm": 4.965950012207031, "learning_rate": 9.955942771867275e-06, "loss": 0.6257, "step": 116130 }, { "epoch": 0.6903602784266871, "grad_norm": 5.683428764343262, "learning_rate": 9.955915283507515e-06, "loss": 0.6539, "step": 116140 }, { "epoch": 0.6904197205033555, "grad_norm": 5.381644248962402, "learning_rate": 9.955887786613076e-06, "loss": 0.5542, "step": 116150 }, { "epoch": 0.6904791625800238, "grad_norm": 6.446463108062744, "learning_rate": 9.955860281184008e-06, "loss": 0.5848, "step": 116160 }, { "epoch": 0.6905386046566923, "grad_norm": 7.323342323303223, "learning_rate": 9.955832767220356e-06, "loss": 0.6264, "step": 116170 }, { "epoch": 0.6905980467333607, "grad_norm": 6.286180019378662, "learning_rate": 9.95580524472217e-06, "loss": 0.5699, "step": 116180 }, { "epoch": 0.6906574888100291, "grad_norm": 5.822721481323242, "learning_rate": 9.955777713689495e-06, "loss": 0.6527, "step": 116190 }, { "epoch": 0.6907169308866975, "grad_norm": 5.642880916595459, "learning_rate": 9.95575017412238e-06, "loss": 0.6617, "step": 116200 }, { "epoch": 0.6907763729633658, "grad_norm": 6.205544471740723, "learning_rate": 9.955722626020873e-06, "loss": 0.6433, "step": 116210 }, { "epoch": 0.6908358150400342, "grad_norm": 4.485045909881592, "learning_rate": 9.955695069385015e-06, "loss": 0.5855, "step": 116220 }, { "epoch": 0.6908952571167026, "grad_norm": 6.178461074829102, "learning_rate": 9.955667504214866e-06, "loss": 0.6132, "step": 116230 }, { "epoch": 0.690954699193371, "grad_norm": 7.3712077140808105, "learning_rate": 9.955639930510462e-06, "loss": 0.6343, "step": 116240 }, { "epoch": 0.6910141412700395, "grad_norm": 5.28848123550415, "learning_rate": 9.955612348271855e-06, "loss": 0.6075, "step": 116250 }, { "epoch": 0.6910735833467078, "grad_norm": 6.383042812347412, "learning_rate": 9.955584757499093e-06, "loss": 0.5737, "step": 116260 }, { "epoch": 0.6911330254233762, "grad_norm": 5.413561820983887, "learning_rate": 9.955557158192225e-06, "loss": 0.6215, "step": 116270 }, { "epoch": 0.6911924675000446, "grad_norm": 4.259909629821777, "learning_rate": 9.955529550351293e-06, "loss": 0.5613, "step": 116280 }, { "epoch": 0.691251909576713, "grad_norm": 7.120368957519531, "learning_rate": 9.955501933976349e-06, "loss": 0.6387, "step": 116290 }, { "epoch": 0.6913113516533813, "grad_norm": 5.276406288146973, "learning_rate": 9.955474309067439e-06, "loss": 0.6038, "step": 116300 }, { "epoch": 0.6913707937300497, "grad_norm": 5.700647830963135, "learning_rate": 9.955446675624611e-06, "loss": 0.6341, "step": 116310 }, { "epoch": 0.6914302358067181, "grad_norm": 5.080302715301514, "learning_rate": 9.955419033647913e-06, "loss": 0.5765, "step": 116320 }, { "epoch": 0.6914896778833866, "grad_norm": 6.203439235687256, "learning_rate": 9.955391383137391e-06, "loss": 0.627, "step": 116330 }, { "epoch": 0.691549119960055, "grad_norm": 5.1249213218688965, "learning_rate": 9.955363724093095e-06, "loss": 0.6306, "step": 116340 }, { "epoch": 0.6916085620367233, "grad_norm": 5.894515514373779, "learning_rate": 9.955336056515071e-06, "loss": 0.6358, "step": 116350 }, { "epoch": 0.6916680041133917, "grad_norm": 5.4505414962768555, "learning_rate": 9.955308380403369e-06, "loss": 0.612, "step": 116360 }, { "epoch": 0.6917274461900601, "grad_norm": 4.937717914581299, "learning_rate": 9.955280695758031e-06, "loss": 0.6091, "step": 116370 }, { "epoch": 0.6917868882667285, "grad_norm": 6.944799423217773, "learning_rate": 9.955253002579111e-06, "loss": 0.6162, "step": 116380 }, { "epoch": 0.6918463303433969, "grad_norm": 5.271234512329102, "learning_rate": 9.955225300866653e-06, "loss": 0.6302, "step": 116390 }, { "epoch": 0.6919057724200652, "grad_norm": 5.583357334136963, "learning_rate": 9.955197590620705e-06, "loss": 0.5511, "step": 116400 }, { "epoch": 0.6919652144967336, "grad_norm": 6.251719951629639, "learning_rate": 9.955169871841317e-06, "loss": 0.6147, "step": 116410 }, { "epoch": 0.6920246565734021, "grad_norm": 5.392712593078613, "learning_rate": 9.955142144528536e-06, "loss": 0.628, "step": 116420 }, { "epoch": 0.6920840986500705, "grad_norm": 5.516847610473633, "learning_rate": 9.955114408682407e-06, "loss": 0.5762, "step": 116430 }, { "epoch": 0.6921435407267388, "grad_norm": 7.209638595581055, "learning_rate": 9.955086664302979e-06, "loss": 0.5902, "step": 116440 }, { "epoch": 0.6922029828034072, "grad_norm": 7.40476655960083, "learning_rate": 9.955058911390303e-06, "loss": 0.6667, "step": 116450 }, { "epoch": 0.6922624248800756, "grad_norm": 5.452874183654785, "learning_rate": 9.955031149944424e-06, "loss": 0.6109, "step": 116460 }, { "epoch": 0.692321866956744, "grad_norm": 4.773163318634033, "learning_rate": 9.955003379965389e-06, "loss": 0.5702, "step": 116470 }, { "epoch": 0.6923813090334124, "grad_norm": 4.042447090148926, "learning_rate": 9.954975601453248e-06, "loss": 0.5987, "step": 116480 }, { "epoch": 0.6924407511100807, "grad_norm": 5.60899019241333, "learning_rate": 9.954947814408047e-06, "loss": 0.5951, "step": 116490 }, { "epoch": 0.6925001931867492, "grad_norm": 6.466978549957275, "learning_rate": 9.954920018829835e-06, "loss": 0.6165, "step": 116500 }, { "epoch": 0.6925596352634176, "grad_norm": 6.776852607727051, "learning_rate": 9.95489221471866e-06, "loss": 0.5973, "step": 116510 }, { "epoch": 0.692619077340086, "grad_norm": 6.281510353088379, "learning_rate": 9.954864402074568e-06, "loss": 0.5611, "step": 116520 }, { "epoch": 0.6926785194167543, "grad_norm": 4.840120315551758, "learning_rate": 9.95483658089761e-06, "loss": 0.5729, "step": 116530 }, { "epoch": 0.6927379614934227, "grad_norm": 4.767500877380371, "learning_rate": 9.954808751187832e-06, "loss": 0.6351, "step": 116540 }, { "epoch": 0.6927974035700911, "grad_norm": 5.478232383728027, "learning_rate": 9.95478091294528e-06, "loss": 0.6226, "step": 116550 }, { "epoch": 0.6928568456467595, "grad_norm": 5.545114994049072, "learning_rate": 9.954753066170007e-06, "loss": 0.614, "step": 116560 }, { "epoch": 0.692916287723428, "grad_norm": 5.476491451263428, "learning_rate": 9.954725210862055e-06, "loss": 0.5959, "step": 116570 }, { "epoch": 0.6929757298000963, "grad_norm": 7.009273529052734, "learning_rate": 9.954697347021479e-06, "loss": 0.6121, "step": 116580 }, { "epoch": 0.6930351718767647, "grad_norm": 7.135878562927246, "learning_rate": 9.95466947464832e-06, "loss": 0.6082, "step": 116590 }, { "epoch": 0.6930946139534331, "grad_norm": 4.972355365753174, "learning_rate": 9.954641593742628e-06, "loss": 0.5917, "step": 116600 }, { "epoch": 0.6931540560301015, "grad_norm": 6.3265700340271, "learning_rate": 9.954613704304455e-06, "loss": 0.6016, "step": 116610 }, { "epoch": 0.6932134981067699, "grad_norm": 4.459381580352783, "learning_rate": 9.954585806333844e-06, "loss": 0.5783, "step": 116620 }, { "epoch": 0.6932729401834382, "grad_norm": 6.138101577758789, "learning_rate": 9.954557899830846e-06, "loss": 0.6169, "step": 116630 }, { "epoch": 0.6933323822601066, "grad_norm": 5.1025896072387695, "learning_rate": 9.954529984795508e-06, "loss": 0.6024, "step": 116640 }, { "epoch": 0.693391824336775, "grad_norm": 6.0261335372924805, "learning_rate": 9.954502061227878e-06, "loss": 0.5946, "step": 116650 }, { "epoch": 0.6934512664134435, "grad_norm": 4.74804162979126, "learning_rate": 9.954474129128004e-06, "loss": 0.6242, "step": 116660 }, { "epoch": 0.6935107084901118, "grad_norm": 7.184767723083496, "learning_rate": 9.954446188495934e-06, "loss": 0.5971, "step": 116670 }, { "epoch": 0.6935701505667802, "grad_norm": 6.096103668212891, "learning_rate": 9.954418239331717e-06, "loss": 0.5848, "step": 116680 }, { "epoch": 0.6936295926434486, "grad_norm": 5.520172119140625, "learning_rate": 9.954390281635402e-06, "loss": 0.5932, "step": 116690 }, { "epoch": 0.693689034720117, "grad_norm": 6.253137588500977, "learning_rate": 9.954362315407035e-06, "loss": 0.5971, "step": 116700 }, { "epoch": 0.6937484767967854, "grad_norm": 4.3611040115356445, "learning_rate": 9.954334340646665e-06, "loss": 0.619, "step": 116710 }, { "epoch": 0.6938079188734537, "grad_norm": 6.944643020629883, "learning_rate": 9.954306357354339e-06, "loss": 0.6101, "step": 116720 }, { "epoch": 0.6938673609501221, "grad_norm": 6.198135852813721, "learning_rate": 9.954278365530106e-06, "loss": 0.6121, "step": 116730 }, { "epoch": 0.6939268030267906, "grad_norm": 5.692262172698975, "learning_rate": 9.954250365174017e-06, "loss": 0.5997, "step": 116740 }, { "epoch": 0.693986245103459, "grad_norm": 6.012276649475098, "learning_rate": 9.954222356286116e-06, "loss": 0.5867, "step": 116750 }, { "epoch": 0.6940456871801274, "grad_norm": 5.298896312713623, "learning_rate": 9.954194338866453e-06, "loss": 0.5971, "step": 116760 }, { "epoch": 0.6941051292567957, "grad_norm": 4.875983238220215, "learning_rate": 9.954166312915076e-06, "loss": 0.5849, "step": 116770 }, { "epoch": 0.6941645713334641, "grad_norm": 4.793602466583252, "learning_rate": 9.954138278432035e-06, "loss": 0.6219, "step": 116780 }, { "epoch": 0.6942240134101325, "grad_norm": 4.541556358337402, "learning_rate": 9.954110235417376e-06, "loss": 0.5284, "step": 116790 }, { "epoch": 0.6942834554868009, "grad_norm": 4.584210395812988, "learning_rate": 9.954082183871148e-06, "loss": 0.5759, "step": 116800 }, { "epoch": 0.6943428975634692, "grad_norm": 6.013545989990234, "learning_rate": 9.954054123793397e-06, "loss": 0.5774, "step": 116810 }, { "epoch": 0.6944023396401376, "grad_norm": 6.80170202255249, "learning_rate": 9.954026055184176e-06, "loss": 0.635, "step": 116820 }, { "epoch": 0.6944617817168061, "grad_norm": 6.298415184020996, "learning_rate": 9.953997978043533e-06, "loss": 0.6288, "step": 116830 }, { "epoch": 0.6945212237934745, "grad_norm": 4.412294387817383, "learning_rate": 9.95396989237151e-06, "loss": 0.6433, "step": 116840 }, { "epoch": 0.6945806658701429, "grad_norm": 4.593419551849365, "learning_rate": 9.953941798168162e-06, "loss": 0.6026, "step": 116850 }, { "epoch": 0.6946401079468112, "grad_norm": 5.314663410186768, "learning_rate": 9.953913695433537e-06, "loss": 0.5699, "step": 116860 }, { "epoch": 0.6946995500234796, "grad_norm": 5.64887809753418, "learning_rate": 9.95388558416768e-06, "loss": 0.4794, "step": 116870 }, { "epoch": 0.694758992100148, "grad_norm": 5.199235439300537, "learning_rate": 9.95385746437064e-06, "loss": 0.6025, "step": 116880 }, { "epoch": 0.6948184341768164, "grad_norm": 6.008244037628174, "learning_rate": 9.953829336042467e-06, "loss": 0.6078, "step": 116890 }, { "epoch": 0.6948778762534847, "grad_norm": 5.404937744140625, "learning_rate": 9.953801199183208e-06, "loss": 0.5791, "step": 116900 }, { "epoch": 0.6949373183301532, "grad_norm": 6.69124174118042, "learning_rate": 9.953773053792913e-06, "loss": 0.5851, "step": 116910 }, { "epoch": 0.6949967604068216, "grad_norm": 6.026043891906738, "learning_rate": 9.95374489987163e-06, "loss": 0.653, "step": 116920 }, { "epoch": 0.69505620248349, "grad_norm": 6.1483235359191895, "learning_rate": 9.953716737419408e-06, "loss": 0.5572, "step": 116930 }, { "epoch": 0.6951156445601584, "grad_norm": 6.6332221031188965, "learning_rate": 9.953688566436292e-06, "loss": 0.6371, "step": 116940 }, { "epoch": 0.6951750866368267, "grad_norm": 6.818544864654541, "learning_rate": 9.953660386922334e-06, "loss": 0.6098, "step": 116950 }, { "epoch": 0.6952345287134951, "grad_norm": 4.274814128875732, "learning_rate": 9.953632198877585e-06, "loss": 0.6051, "step": 116960 }, { "epoch": 0.6952939707901635, "grad_norm": 10.786822319030762, "learning_rate": 9.953604002302086e-06, "loss": 0.5721, "step": 116970 }, { "epoch": 0.6953534128668319, "grad_norm": 7.226019382476807, "learning_rate": 9.953575797195894e-06, "loss": 0.6184, "step": 116980 }, { "epoch": 0.6954128549435004, "grad_norm": 6.166903495788574, "learning_rate": 9.95354758355905e-06, "loss": 0.6078, "step": 116990 }, { "epoch": 0.6954722970201687, "grad_norm": 5.6024274826049805, "learning_rate": 9.953519361391609e-06, "loss": 0.6031, "step": 117000 }, { "epoch": 0.6955317390968371, "grad_norm": 5.653028964996338, "learning_rate": 9.953491130693614e-06, "loss": 0.6186, "step": 117010 }, { "epoch": 0.6955911811735055, "grad_norm": 5.483268737792969, "learning_rate": 9.953462891465116e-06, "loss": 0.6473, "step": 117020 }, { "epoch": 0.6956506232501739, "grad_norm": 4.150645732879639, "learning_rate": 9.953434643706166e-06, "loss": 0.5695, "step": 117030 }, { "epoch": 0.6957100653268422, "grad_norm": 5.406848907470703, "learning_rate": 9.953406387416809e-06, "loss": 0.6389, "step": 117040 }, { "epoch": 0.6957695074035106, "grad_norm": 5.095012664794922, "learning_rate": 9.953378122597094e-06, "loss": 0.5389, "step": 117050 }, { "epoch": 0.695828949480179, "grad_norm": 5.593101501464844, "learning_rate": 9.953349849247074e-06, "loss": 0.5902, "step": 117060 }, { "epoch": 0.6958883915568475, "grad_norm": 5.501826763153076, "learning_rate": 9.953321567366792e-06, "loss": 0.593, "step": 117070 }, { "epoch": 0.6959478336335159, "grad_norm": 5.78411865234375, "learning_rate": 9.953293276956302e-06, "loss": 0.5311, "step": 117080 }, { "epoch": 0.6960072757101842, "grad_norm": 6.002748966217041, "learning_rate": 9.953264978015647e-06, "loss": 0.6054, "step": 117090 }, { "epoch": 0.6960667177868526, "grad_norm": 4.585798740386963, "learning_rate": 9.95323667054488e-06, "loss": 0.6134, "step": 117100 }, { "epoch": 0.696126159863521, "grad_norm": 5.105319976806641, "learning_rate": 9.953208354544048e-06, "loss": 0.6083, "step": 117110 }, { "epoch": 0.6961856019401894, "grad_norm": 5.093053817749023, "learning_rate": 9.953180030013201e-06, "loss": 0.6349, "step": 117120 }, { "epoch": 0.6962450440168578, "grad_norm": 6.281243324279785, "learning_rate": 9.953151696952386e-06, "loss": 0.6296, "step": 117130 }, { "epoch": 0.6963044860935261, "grad_norm": 3.781078338623047, "learning_rate": 9.953123355361654e-06, "loss": 0.6347, "step": 117140 }, { "epoch": 0.6963639281701945, "grad_norm": 5.362545967102051, "learning_rate": 9.953095005241051e-06, "loss": 0.6088, "step": 117150 }, { "epoch": 0.696423370246863, "grad_norm": 4.510318756103516, "learning_rate": 9.953066646590628e-06, "loss": 0.6243, "step": 117160 }, { "epoch": 0.6964828123235314, "grad_norm": 6.095571994781494, "learning_rate": 9.953038279410435e-06, "loss": 0.5923, "step": 117170 }, { "epoch": 0.6965422544001997, "grad_norm": 6.090559482574463, "learning_rate": 9.953009903700516e-06, "loss": 0.5445, "step": 117180 }, { "epoch": 0.6966016964768681, "grad_norm": 7.056549549102783, "learning_rate": 9.952981519460926e-06, "loss": 0.5749, "step": 117190 }, { "epoch": 0.6966611385535365, "grad_norm": 5.850179672241211, "learning_rate": 9.95295312669171e-06, "loss": 0.6107, "step": 117200 }, { "epoch": 0.6967205806302049, "grad_norm": 6.224116802215576, "learning_rate": 9.952924725392916e-06, "loss": 0.6161, "step": 117210 }, { "epoch": 0.6967800227068733, "grad_norm": 4.4425225257873535, "learning_rate": 9.952896315564596e-06, "loss": 0.618, "step": 117220 }, { "epoch": 0.6968394647835416, "grad_norm": 6.0503764152526855, "learning_rate": 9.952867897206797e-06, "loss": 0.5724, "step": 117230 }, { "epoch": 0.69689890686021, "grad_norm": 7.703425884246826, "learning_rate": 9.95283947031957e-06, "loss": 0.6257, "step": 117240 }, { "epoch": 0.6969583489368785, "grad_norm": 5.958699703216553, "learning_rate": 9.95281103490296e-06, "loss": 0.67, "step": 117250 }, { "epoch": 0.6970177910135469, "grad_norm": 4.8360137939453125, "learning_rate": 9.952782590957021e-06, "loss": 0.6157, "step": 117260 }, { "epoch": 0.6970772330902152, "grad_norm": 6.527133464813232, "learning_rate": 9.952754138481798e-06, "loss": 0.6063, "step": 117270 }, { "epoch": 0.6971366751668836, "grad_norm": 6.481176853179932, "learning_rate": 9.952725677477341e-06, "loss": 0.5733, "step": 117280 }, { "epoch": 0.697196117243552, "grad_norm": 5.672860145568848, "learning_rate": 9.9526972079437e-06, "loss": 0.5354, "step": 117290 }, { "epoch": 0.6972555593202204, "grad_norm": 8.438852310180664, "learning_rate": 9.952668729880924e-06, "loss": 0.6583, "step": 117300 }, { "epoch": 0.6973150013968888, "grad_norm": 4.748280048370361, "learning_rate": 9.952640243289062e-06, "loss": 0.5454, "step": 117310 }, { "epoch": 0.6973744434735571, "grad_norm": 5.267867088317871, "learning_rate": 9.952611748168162e-06, "loss": 0.6121, "step": 117320 }, { "epoch": 0.6974338855502256, "grad_norm": 4.858084201812744, "learning_rate": 9.952583244518273e-06, "loss": 0.5908, "step": 117330 }, { "epoch": 0.697493327626894, "grad_norm": 5.455605983734131, "learning_rate": 9.952554732339444e-06, "loss": 0.6047, "step": 117340 }, { "epoch": 0.6975527697035624, "grad_norm": 5.326888084411621, "learning_rate": 9.952526211631725e-06, "loss": 0.5739, "step": 117350 }, { "epoch": 0.6976122117802308, "grad_norm": 6.426736354827881, "learning_rate": 9.952497682395167e-06, "loss": 0.6055, "step": 117360 }, { "epoch": 0.6976716538568991, "grad_norm": 6.530728816986084, "learning_rate": 9.952469144629815e-06, "loss": 0.5838, "step": 117370 }, { "epoch": 0.6977310959335675, "grad_norm": 6.500513076782227, "learning_rate": 9.952440598335721e-06, "loss": 0.5981, "step": 117380 }, { "epoch": 0.6977905380102359, "grad_norm": 5.469862461090088, "learning_rate": 9.952412043512934e-06, "loss": 0.5806, "step": 117390 }, { "epoch": 0.6978499800869044, "grad_norm": 6.591990947723389, "learning_rate": 9.952383480161502e-06, "loss": 0.6044, "step": 117400 }, { "epoch": 0.6979094221635727, "grad_norm": 5.9458489418029785, "learning_rate": 9.952354908281475e-06, "loss": 0.63, "step": 117410 }, { "epoch": 0.6979688642402411, "grad_norm": 5.600346565246582, "learning_rate": 9.9523263278729e-06, "loss": 0.6209, "step": 117420 }, { "epoch": 0.6980283063169095, "grad_norm": 4.796946048736572, "learning_rate": 9.952297738935832e-06, "loss": 0.5824, "step": 117430 }, { "epoch": 0.6980877483935779, "grad_norm": 6.623029708862305, "learning_rate": 9.952269141470314e-06, "loss": 0.5788, "step": 117440 }, { "epoch": 0.6981471904702463, "grad_norm": 6.169703483581543, "learning_rate": 9.952240535476398e-06, "loss": 0.63, "step": 117450 }, { "epoch": 0.6982066325469146, "grad_norm": 3.587066650390625, "learning_rate": 9.952211920954132e-06, "loss": 0.6248, "step": 117460 }, { "epoch": 0.698266074623583, "grad_norm": 6.683403015136719, "learning_rate": 9.952183297903567e-06, "loss": 0.5916, "step": 117470 }, { "epoch": 0.6983255167002514, "grad_norm": 4.759318828582764, "learning_rate": 9.952154666324751e-06, "loss": 0.5756, "step": 117480 }, { "epoch": 0.6983849587769199, "grad_norm": 4.77947473526001, "learning_rate": 9.952126026217735e-06, "loss": 0.6018, "step": 117490 }, { "epoch": 0.6984444008535883, "grad_norm": 4.837392807006836, "learning_rate": 9.952097377582566e-06, "loss": 0.603, "step": 117500 }, { "epoch": 0.6985038429302566, "grad_norm": 5.91621208190918, "learning_rate": 9.952068720419294e-06, "loss": 0.5494, "step": 117510 }, { "epoch": 0.698563285006925, "grad_norm": 5.963316917419434, "learning_rate": 9.952040054727971e-06, "loss": 0.5843, "step": 117520 }, { "epoch": 0.6986227270835934, "grad_norm": 5.505779266357422, "learning_rate": 9.952011380508642e-06, "loss": 0.5653, "step": 117530 }, { "epoch": 0.6986821691602618, "grad_norm": 4.8865885734558105, "learning_rate": 9.95198269776136e-06, "loss": 0.5966, "step": 117540 }, { "epoch": 0.6987416112369301, "grad_norm": 4.921319007873535, "learning_rate": 9.951954006486171e-06, "loss": 0.5599, "step": 117550 }, { "epoch": 0.6988010533135985, "grad_norm": 7.66825532913208, "learning_rate": 9.951925306683127e-06, "loss": 0.6983, "step": 117560 }, { "epoch": 0.698860495390267, "grad_norm": 6.402407646179199, "learning_rate": 9.951896598352278e-06, "loss": 0.5872, "step": 117570 }, { "epoch": 0.6989199374669354, "grad_norm": 6.412156581878662, "learning_rate": 9.951867881493671e-06, "loss": 0.5993, "step": 117580 }, { "epoch": 0.6989793795436038, "grad_norm": 6.847114086151123, "learning_rate": 9.951839156107358e-06, "loss": 0.5898, "step": 117590 }, { "epoch": 0.6990388216202721, "grad_norm": 5.257971286773682, "learning_rate": 9.951810422193387e-06, "loss": 0.6118, "step": 117600 }, { "epoch": 0.6990982636969405, "grad_norm": 6.9678215980529785, "learning_rate": 9.951781679751806e-06, "loss": 0.5712, "step": 117610 }, { "epoch": 0.6991577057736089, "grad_norm": 5.482632160186768, "learning_rate": 9.951752928782667e-06, "loss": 0.6645, "step": 117620 }, { "epoch": 0.6992171478502773, "grad_norm": 5.902327060699463, "learning_rate": 9.951724169286018e-06, "loss": 0.6568, "step": 117630 }, { "epoch": 0.6992765899269456, "grad_norm": 5.415063381195068, "learning_rate": 9.95169540126191e-06, "loss": 0.5756, "step": 117640 }, { "epoch": 0.699336032003614, "grad_norm": 4.10426139831543, "learning_rate": 9.951666624710392e-06, "loss": 0.5922, "step": 117650 }, { "epoch": 0.6993954740802825, "grad_norm": 5.363125324249268, "learning_rate": 9.951637839631512e-06, "loss": 0.6171, "step": 117660 }, { "epoch": 0.6994549161569509, "grad_norm": 7.095608711242676, "learning_rate": 9.951609046025322e-06, "loss": 0.6546, "step": 117670 }, { "epoch": 0.6995143582336193, "grad_norm": 4.826108455657959, "learning_rate": 9.95158024389187e-06, "loss": 0.6141, "step": 117680 }, { "epoch": 0.6995738003102876, "grad_norm": 5.875664710998535, "learning_rate": 9.951551433231205e-06, "loss": 0.5794, "step": 117690 }, { "epoch": 0.699633242386956, "grad_norm": 5.821698188781738, "learning_rate": 9.95152261404338e-06, "loss": 0.5882, "step": 117700 }, { "epoch": 0.6996926844636244, "grad_norm": 5.285254955291748, "learning_rate": 9.95149378632844e-06, "loss": 0.6228, "step": 117710 }, { "epoch": 0.6997521265402928, "grad_norm": 4.83151388168335, "learning_rate": 9.951464950086438e-06, "loss": 0.5779, "step": 117720 }, { "epoch": 0.6998115686169613, "grad_norm": 6.409112453460693, "learning_rate": 9.951436105317423e-06, "loss": 0.6364, "step": 117730 }, { "epoch": 0.6998710106936296, "grad_norm": 6.141982078552246, "learning_rate": 9.951407252021443e-06, "loss": 0.6545, "step": 117740 }, { "epoch": 0.699930452770298, "grad_norm": 6.860451698303223, "learning_rate": 9.951378390198549e-06, "loss": 0.5951, "step": 117750 }, { "epoch": 0.6999898948469664, "grad_norm": 6.786374092102051, "learning_rate": 9.95134951984879e-06, "loss": 0.6062, "step": 117760 }, { "epoch": 0.7000493369236348, "grad_norm": 5.994568347930908, "learning_rate": 9.951320640972219e-06, "loss": 0.6657, "step": 117770 }, { "epoch": 0.7001087790003031, "grad_norm": 6.222893714904785, "learning_rate": 9.951291753568882e-06, "loss": 0.5934, "step": 117780 }, { "epoch": 0.7001682210769715, "grad_norm": 4.235804080963135, "learning_rate": 9.951262857638828e-06, "loss": 0.5837, "step": 117790 }, { "epoch": 0.7002276631536399, "grad_norm": 5.1533684730529785, "learning_rate": 9.95123395318211e-06, "loss": 0.6643, "step": 117800 }, { "epoch": 0.7002871052303083, "grad_norm": 6.108511924743652, "learning_rate": 9.951205040198777e-06, "loss": 0.6177, "step": 117810 }, { "epoch": 0.7003465473069768, "grad_norm": 7.804254531860352, "learning_rate": 9.951176118688877e-06, "loss": 0.6605, "step": 117820 }, { "epoch": 0.7004059893836451, "grad_norm": 5.501894950866699, "learning_rate": 9.951147188652461e-06, "loss": 0.584, "step": 117830 }, { "epoch": 0.7004654314603135, "grad_norm": 5.666378974914551, "learning_rate": 9.951118250089579e-06, "loss": 0.6223, "step": 117840 }, { "epoch": 0.7005248735369819, "grad_norm": 4.282071113586426, "learning_rate": 9.95108930300028e-06, "loss": 0.6168, "step": 117850 }, { "epoch": 0.7005843156136503, "grad_norm": 5.061386585235596, "learning_rate": 9.951060347384616e-06, "loss": 0.6081, "step": 117860 }, { "epoch": 0.7006437576903186, "grad_norm": 5.405356407165527, "learning_rate": 9.951031383242635e-06, "loss": 0.5428, "step": 117870 }, { "epoch": 0.700703199766987, "grad_norm": 4.806442737579346, "learning_rate": 9.951002410574387e-06, "loss": 0.574, "step": 117880 }, { "epoch": 0.7007626418436554, "grad_norm": 5.405361652374268, "learning_rate": 9.950973429379922e-06, "loss": 0.6307, "step": 117890 }, { "epoch": 0.7008220839203239, "grad_norm": 5.641584396362305, "learning_rate": 9.950944439659289e-06, "loss": 0.6087, "step": 117900 }, { "epoch": 0.7008815259969923, "grad_norm": 5.660401344299316, "learning_rate": 9.95091544141254e-06, "loss": 0.5868, "step": 117910 }, { "epoch": 0.7009409680736606, "grad_norm": 5.164703845977783, "learning_rate": 9.950886434639724e-06, "loss": 0.6543, "step": 117920 }, { "epoch": 0.701000410150329, "grad_norm": 4.860469818115234, "learning_rate": 9.95085741934089e-06, "loss": 0.565, "step": 117930 }, { "epoch": 0.7010598522269974, "grad_norm": 5.716123580932617, "learning_rate": 9.95082839551609e-06, "loss": 0.6029, "step": 117940 }, { "epoch": 0.7011192943036658, "grad_norm": 4.776937961578369, "learning_rate": 9.950799363165371e-06, "loss": 0.6378, "step": 117950 }, { "epoch": 0.7011787363803342, "grad_norm": 5.439753532409668, "learning_rate": 9.950770322288787e-06, "loss": 0.6184, "step": 117960 }, { "epoch": 0.7012381784570025, "grad_norm": 5.690314769744873, "learning_rate": 9.950741272886384e-06, "loss": 0.5654, "step": 117970 }, { "epoch": 0.701297620533671, "grad_norm": 6.187021732330322, "learning_rate": 9.950712214958214e-06, "loss": 0.5456, "step": 117980 }, { "epoch": 0.7013570626103394, "grad_norm": 6.156766891479492, "learning_rate": 9.950683148504328e-06, "loss": 0.6088, "step": 117990 }, { "epoch": 0.7014165046870078, "grad_norm": 4.611959457397461, "learning_rate": 9.950654073524774e-06, "loss": 0.6168, "step": 118000 }, { "epoch": 0.7014759467636761, "grad_norm": 5.291233539581299, "learning_rate": 9.950624990019603e-06, "loss": 0.5757, "step": 118010 }, { "epoch": 0.7015353888403445, "grad_norm": 5.635416030883789, "learning_rate": 9.950595897988864e-06, "loss": 0.614, "step": 118020 }, { "epoch": 0.7015948309170129, "grad_norm": 5.8361616134643555, "learning_rate": 9.95056679743261e-06, "loss": 0.6254, "step": 118030 }, { "epoch": 0.7016542729936813, "grad_norm": 4.642217636108398, "learning_rate": 9.95053768835089e-06, "loss": 0.537, "step": 118040 }, { "epoch": 0.7017137150703497, "grad_norm": 6.788146495819092, "learning_rate": 9.95050857074375e-06, "loss": 0.6763, "step": 118050 }, { "epoch": 0.701773157147018, "grad_norm": 5.839121341705322, "learning_rate": 9.950479444611248e-06, "loss": 0.5966, "step": 118060 }, { "epoch": 0.7018325992236865, "grad_norm": 5.957152843475342, "learning_rate": 9.950450309953427e-06, "loss": 0.5455, "step": 118070 }, { "epoch": 0.7018920413003549, "grad_norm": 4.609519958496094, "learning_rate": 9.95042116677034e-06, "loss": 0.5891, "step": 118080 }, { "epoch": 0.7019514833770233, "grad_norm": 6.181214809417725, "learning_rate": 9.950392015062038e-06, "loss": 0.5893, "step": 118090 }, { "epoch": 0.7020109254536917, "grad_norm": 4.810393810272217, "learning_rate": 9.950362854828569e-06, "loss": 0.5959, "step": 118100 }, { "epoch": 0.70207036753036, "grad_norm": 6.599164009094238, "learning_rate": 9.950333686069984e-06, "loss": 0.5892, "step": 118110 }, { "epoch": 0.7021298096070284, "grad_norm": 5.248654365539551, "learning_rate": 9.950304508786336e-06, "loss": 0.6054, "step": 118120 }, { "epoch": 0.7021892516836968, "grad_norm": 5.6090407371521, "learning_rate": 9.950275322977671e-06, "loss": 0.5884, "step": 118130 }, { "epoch": 0.7022486937603653, "grad_norm": 6.264339447021484, "learning_rate": 9.950246128644043e-06, "loss": 0.6124, "step": 118140 }, { "epoch": 0.7023081358370336, "grad_norm": 5.188425064086914, "learning_rate": 9.950216925785499e-06, "loss": 0.5939, "step": 118150 }, { "epoch": 0.702367577913702, "grad_norm": 4.867543697357178, "learning_rate": 9.950187714402092e-06, "loss": 0.5767, "step": 118160 }, { "epoch": 0.7024270199903704, "grad_norm": 5.485116481781006, "learning_rate": 9.95015849449387e-06, "loss": 0.6498, "step": 118170 }, { "epoch": 0.7024864620670388, "grad_norm": 5.766441345214844, "learning_rate": 9.950129266060886e-06, "loss": 0.6175, "step": 118180 }, { "epoch": 0.7025459041437072, "grad_norm": 5.512009143829346, "learning_rate": 9.950100029103186e-06, "loss": 0.5976, "step": 118190 }, { "epoch": 0.7026053462203755, "grad_norm": 6.100971698760986, "learning_rate": 9.950070783620826e-06, "loss": 0.6147, "step": 118200 }, { "epoch": 0.7026647882970439, "grad_norm": 7.074961185455322, "learning_rate": 9.950041529613852e-06, "loss": 0.6226, "step": 118210 }, { "epoch": 0.7027242303737123, "grad_norm": 7.383684158325195, "learning_rate": 9.950012267082317e-06, "loss": 0.6579, "step": 118220 }, { "epoch": 0.7027836724503808, "grad_norm": 4.570912837982178, "learning_rate": 9.949982996026268e-06, "loss": 0.595, "step": 118230 }, { "epoch": 0.7028431145270491, "grad_norm": 5.676358222961426, "learning_rate": 9.949953716445759e-06, "loss": 0.6104, "step": 118240 }, { "epoch": 0.7029025566037175, "grad_norm": 6.659567356109619, "learning_rate": 9.94992442834084e-06, "loss": 0.6061, "step": 118250 }, { "epoch": 0.7029619986803859, "grad_norm": 4.850844860076904, "learning_rate": 9.94989513171156e-06, "loss": 0.5671, "step": 118260 }, { "epoch": 0.7030214407570543, "grad_norm": 4.3625993728637695, "learning_rate": 9.949865826557969e-06, "loss": 0.5886, "step": 118270 }, { "epoch": 0.7030808828337227, "grad_norm": 5.247674465179443, "learning_rate": 9.94983651288012e-06, "loss": 0.6884, "step": 118280 }, { "epoch": 0.703140324910391, "grad_norm": 5.305817604064941, "learning_rate": 9.94980719067806e-06, "loss": 0.6206, "step": 118290 }, { "epoch": 0.7031997669870594, "grad_norm": 5.491408348083496, "learning_rate": 9.949777859951844e-06, "loss": 0.5906, "step": 118300 }, { "epoch": 0.7032592090637279, "grad_norm": 7.163569450378418, "learning_rate": 9.949748520701516e-06, "loss": 0.6424, "step": 118310 }, { "epoch": 0.7033186511403963, "grad_norm": 6.197561264038086, "learning_rate": 9.949719172927135e-06, "loss": 0.5789, "step": 118320 }, { "epoch": 0.7033780932170647, "grad_norm": 6.7553205490112305, "learning_rate": 9.949689816628744e-06, "loss": 0.5898, "step": 118330 }, { "epoch": 0.703437535293733, "grad_norm": 5.102497100830078, "learning_rate": 9.949660451806398e-06, "loss": 0.6082, "step": 118340 }, { "epoch": 0.7034969773704014, "grad_norm": 4.9465484619140625, "learning_rate": 9.949631078460145e-06, "loss": 0.6026, "step": 118350 }, { "epoch": 0.7035564194470698, "grad_norm": 6.223184585571289, "learning_rate": 9.949601696590036e-06, "loss": 0.5947, "step": 118360 }, { "epoch": 0.7036158615237382, "grad_norm": 4.734385013580322, "learning_rate": 9.949572306196124e-06, "loss": 0.5477, "step": 118370 }, { "epoch": 0.7036753036004065, "grad_norm": 5.866186618804932, "learning_rate": 9.949542907278457e-06, "loss": 0.6104, "step": 118380 }, { "epoch": 0.703734745677075, "grad_norm": 8.722067832946777, "learning_rate": 9.949513499837087e-06, "loss": 0.6626, "step": 118390 }, { "epoch": 0.7037941877537434, "grad_norm": 5.436227798461914, "learning_rate": 9.949484083872065e-06, "loss": 0.6119, "step": 118400 }, { "epoch": 0.7038536298304118, "grad_norm": 4.981762886047363, "learning_rate": 9.94945465938344e-06, "loss": 0.5922, "step": 118410 }, { "epoch": 0.7039130719070802, "grad_norm": 6.427058219909668, "learning_rate": 9.949425226371263e-06, "loss": 0.6056, "step": 118420 }, { "epoch": 0.7039725139837485, "grad_norm": 4.713447570800781, "learning_rate": 9.949395784835585e-06, "loss": 0.5561, "step": 118430 }, { "epoch": 0.7040319560604169, "grad_norm": 7.109884262084961, "learning_rate": 9.949366334776457e-06, "loss": 0.6287, "step": 118440 }, { "epoch": 0.7040913981370853, "grad_norm": 5.741493225097656, "learning_rate": 9.949336876193932e-06, "loss": 0.583, "step": 118450 }, { "epoch": 0.7041508402137537, "grad_norm": 5.232570648193359, "learning_rate": 9.949307409088056e-06, "loss": 0.638, "step": 118460 }, { "epoch": 0.7042102822904222, "grad_norm": 5.281953811645508, "learning_rate": 9.949277933458884e-06, "loss": 0.6176, "step": 118470 }, { "epoch": 0.7042697243670905, "grad_norm": 3.8854644298553467, "learning_rate": 9.949248449306463e-06, "loss": 0.5595, "step": 118480 }, { "epoch": 0.7043291664437589, "grad_norm": 4.4138383865356445, "learning_rate": 9.949218956630846e-06, "loss": 0.6104, "step": 118490 }, { "epoch": 0.7043886085204273, "grad_norm": 8.350399017333984, "learning_rate": 9.949189455432082e-06, "loss": 0.6661, "step": 118500 }, { "epoch": 0.7044480505970957, "grad_norm": 5.5447001457214355, "learning_rate": 9.949159945710225e-06, "loss": 0.6212, "step": 118510 }, { "epoch": 0.704507492673764, "grad_norm": 5.205136775970459, "learning_rate": 9.949130427465324e-06, "loss": 0.6219, "step": 118520 }, { "epoch": 0.7045669347504324, "grad_norm": 4.621368408203125, "learning_rate": 9.94910090069743e-06, "loss": 0.61, "step": 118530 }, { "epoch": 0.7046263768271008, "grad_norm": 5.164165496826172, "learning_rate": 9.949071365406595e-06, "loss": 0.7066, "step": 118540 }, { "epoch": 0.7046858189037692, "grad_norm": 7.465908527374268, "learning_rate": 9.949041821592866e-06, "loss": 0.5949, "step": 118550 }, { "epoch": 0.7047452609804377, "grad_norm": 5.211514472961426, "learning_rate": 9.949012269256297e-06, "loss": 0.6217, "step": 118560 }, { "epoch": 0.704804703057106, "grad_norm": 4.56003475189209, "learning_rate": 9.948982708396939e-06, "loss": 0.6054, "step": 118570 }, { "epoch": 0.7048641451337744, "grad_norm": 7.379837512969971, "learning_rate": 9.948953139014843e-06, "loss": 0.5603, "step": 118580 }, { "epoch": 0.7049235872104428, "grad_norm": 4.999023914337158, "learning_rate": 9.948923561110057e-06, "loss": 0.5753, "step": 118590 }, { "epoch": 0.7049830292871112, "grad_norm": 5.3761067390441895, "learning_rate": 9.948893974682637e-06, "loss": 0.577, "step": 118600 }, { "epoch": 0.7050424713637795, "grad_norm": 5.181305408477783, "learning_rate": 9.94886437973263e-06, "loss": 0.6161, "step": 118610 }, { "epoch": 0.7051019134404479, "grad_norm": 6.173873424530029, "learning_rate": 9.948834776260087e-06, "loss": 0.5667, "step": 118620 }, { "epoch": 0.7051613555171163, "grad_norm": 5.260474681854248, "learning_rate": 9.948805164265061e-06, "loss": 0.583, "step": 118630 }, { "epoch": 0.7052207975937848, "grad_norm": 5.66130256652832, "learning_rate": 9.9487755437476e-06, "loss": 0.5827, "step": 118640 }, { "epoch": 0.7052802396704532, "grad_norm": 4.420062065124512, "learning_rate": 9.948745914707761e-06, "loss": 0.6172, "step": 118650 }, { "epoch": 0.7053396817471215, "grad_norm": 6.102666854858398, "learning_rate": 9.948716277145588e-06, "loss": 0.638, "step": 118660 }, { "epoch": 0.7053991238237899, "grad_norm": 5.344996452331543, "learning_rate": 9.948686631061135e-06, "loss": 0.6067, "step": 118670 }, { "epoch": 0.7054585659004583, "grad_norm": 5.868450164794922, "learning_rate": 9.948656976454453e-06, "loss": 0.5842, "step": 118680 }, { "epoch": 0.7055180079771267, "grad_norm": 6.396327495574951, "learning_rate": 9.948627313325595e-06, "loss": 0.5558, "step": 118690 }, { "epoch": 0.7055774500537951, "grad_norm": 6.093506336212158, "learning_rate": 9.94859764167461e-06, "loss": 0.5913, "step": 118700 }, { "epoch": 0.7056368921304634, "grad_norm": 5.2022294998168945, "learning_rate": 9.94856796150155e-06, "loss": 0.5901, "step": 118710 }, { "epoch": 0.7056963342071318, "grad_norm": 4.778100967407227, "learning_rate": 9.948538272806463e-06, "loss": 0.5777, "step": 118720 }, { "epoch": 0.7057557762838003, "grad_norm": 5.762612342834473, "learning_rate": 9.948508575589404e-06, "loss": 0.656, "step": 118730 }, { "epoch": 0.7058152183604687, "grad_norm": 4.072711944580078, "learning_rate": 9.948478869850424e-06, "loss": 0.6467, "step": 118740 }, { "epoch": 0.705874660437137, "grad_norm": 5.85042667388916, "learning_rate": 9.948449155589573e-06, "loss": 0.594, "step": 118750 }, { "epoch": 0.7059341025138054, "grad_norm": 4.657471179962158, "learning_rate": 9.9484194328069e-06, "loss": 0.5561, "step": 118760 }, { "epoch": 0.7059935445904738, "grad_norm": 5.196849346160889, "learning_rate": 9.94838970150246e-06, "loss": 0.5378, "step": 118770 }, { "epoch": 0.7060529866671422, "grad_norm": 7.355266094207764, "learning_rate": 9.948359961676301e-06, "loss": 0.6085, "step": 118780 }, { "epoch": 0.7061124287438106, "grad_norm": 6.702010631561279, "learning_rate": 9.948330213328476e-06, "loss": 0.573, "step": 118790 }, { "epoch": 0.7061718708204789, "grad_norm": 6.528067588806152, "learning_rate": 9.948300456459036e-06, "loss": 0.5971, "step": 118800 }, { "epoch": 0.7062313128971474, "grad_norm": 6.036724090576172, "learning_rate": 9.948270691068034e-06, "loss": 0.6613, "step": 118810 }, { "epoch": 0.7062907549738158, "grad_norm": 5.040498733520508, "learning_rate": 9.948240917155517e-06, "loss": 0.6249, "step": 118820 }, { "epoch": 0.7063501970504842, "grad_norm": 5.797585487365723, "learning_rate": 9.94821113472154e-06, "loss": 0.5519, "step": 118830 }, { "epoch": 0.7064096391271526, "grad_norm": 4.0447821617126465, "learning_rate": 9.948181343766152e-06, "loss": 0.5683, "step": 118840 }, { "epoch": 0.7064690812038209, "grad_norm": 4.695302963256836, "learning_rate": 9.948151544289408e-06, "loss": 0.6109, "step": 118850 }, { "epoch": 0.7065285232804893, "grad_norm": 4.3195881843566895, "learning_rate": 9.948121736291355e-06, "loss": 0.6146, "step": 118860 }, { "epoch": 0.7065879653571577, "grad_norm": 5.174589157104492, "learning_rate": 9.948091919772045e-06, "loss": 0.608, "step": 118870 }, { "epoch": 0.7066474074338261, "grad_norm": 5.029322147369385, "learning_rate": 9.948062094731531e-06, "loss": 0.6147, "step": 118880 }, { "epoch": 0.7067068495104945, "grad_norm": 4.589627742767334, "learning_rate": 9.948032261169864e-06, "loss": 0.575, "step": 118890 }, { "epoch": 0.7067662915871629, "grad_norm": 6.293944835662842, "learning_rate": 9.948002419087095e-06, "loss": 0.593, "step": 118900 }, { "epoch": 0.7068257336638313, "grad_norm": 4.9160847663879395, "learning_rate": 9.947972568483275e-06, "loss": 0.6192, "step": 118910 }, { "epoch": 0.7068851757404997, "grad_norm": 7.078332901000977, "learning_rate": 9.947942709358455e-06, "loss": 0.5359, "step": 118920 }, { "epoch": 0.7069446178171681, "grad_norm": 6.063965797424316, "learning_rate": 9.947912841712689e-06, "loss": 0.6129, "step": 118930 }, { "epoch": 0.7070040598938364, "grad_norm": 4.965657711029053, "learning_rate": 9.947882965546027e-06, "loss": 0.581, "step": 118940 }, { "epoch": 0.7070635019705048, "grad_norm": 5.403347492218018, "learning_rate": 9.947853080858519e-06, "loss": 0.5691, "step": 118950 }, { "epoch": 0.7071229440471732, "grad_norm": 5.272994041442871, "learning_rate": 9.947823187650217e-06, "loss": 0.5158, "step": 118960 }, { "epoch": 0.7071823861238417, "grad_norm": 4.704090118408203, "learning_rate": 9.947793285921175e-06, "loss": 0.6259, "step": 118970 }, { "epoch": 0.70724182820051, "grad_norm": 6.278738975524902, "learning_rate": 9.94776337567144e-06, "loss": 0.5994, "step": 118980 }, { "epoch": 0.7073012702771784, "grad_norm": 5.118983745574951, "learning_rate": 9.94773345690107e-06, "loss": 0.5626, "step": 118990 }, { "epoch": 0.7073607123538468, "grad_norm": 5.287269592285156, "learning_rate": 9.94770352961011e-06, "loss": 0.5522, "step": 119000 }, { "epoch": 0.7074201544305152, "grad_norm": 5.341771125793457, "learning_rate": 9.947673593798613e-06, "loss": 0.5708, "step": 119010 }, { "epoch": 0.7074795965071836, "grad_norm": 5.14694881439209, "learning_rate": 9.947643649466634e-06, "loss": 0.6209, "step": 119020 }, { "epoch": 0.7075390385838519, "grad_norm": 5.434774398803711, "learning_rate": 9.94761369661422e-06, "loss": 0.624, "step": 119030 }, { "epoch": 0.7075984806605203, "grad_norm": 5.915399074554443, "learning_rate": 9.947583735241428e-06, "loss": 0.6058, "step": 119040 }, { "epoch": 0.7076579227371887, "grad_norm": 5.123208999633789, "learning_rate": 9.947553765348304e-06, "loss": 0.5913, "step": 119050 }, { "epoch": 0.7077173648138572, "grad_norm": 7.168871879577637, "learning_rate": 9.947523786934903e-06, "loss": 0.637, "step": 119060 }, { "epoch": 0.7077768068905256, "grad_norm": 4.982846736907959, "learning_rate": 9.947493800001275e-06, "loss": 0.5993, "step": 119070 }, { "epoch": 0.7078362489671939, "grad_norm": 7.608461856842041, "learning_rate": 9.947463804547475e-06, "loss": 0.5986, "step": 119080 }, { "epoch": 0.7078956910438623, "grad_norm": 4.735343933105469, "learning_rate": 9.94743380057355e-06, "loss": 0.6518, "step": 119090 }, { "epoch": 0.7079551331205307, "grad_norm": 5.827682971954346, "learning_rate": 9.947403788079553e-06, "loss": 0.615, "step": 119100 }, { "epoch": 0.7080145751971991, "grad_norm": 5.136571884155273, "learning_rate": 9.947373767065538e-06, "loss": 0.6442, "step": 119110 }, { "epoch": 0.7080740172738674, "grad_norm": 5.433895111083984, "learning_rate": 9.947343737531553e-06, "loss": 0.5667, "step": 119120 }, { "epoch": 0.7081334593505358, "grad_norm": 4.658423900604248, "learning_rate": 9.947313699477652e-06, "loss": 0.609, "step": 119130 }, { "epoch": 0.7081929014272043, "grad_norm": 4.8366193771362305, "learning_rate": 9.94728365290389e-06, "loss": 0.5715, "step": 119140 }, { "epoch": 0.7082523435038727, "grad_norm": 5.556482315063477, "learning_rate": 9.947253597810311e-06, "loss": 0.5718, "step": 119150 }, { "epoch": 0.7083117855805411, "grad_norm": 4.926833152770996, "learning_rate": 9.947223534196973e-06, "loss": 0.578, "step": 119160 }, { "epoch": 0.7083712276572094, "grad_norm": 7.146880149841309, "learning_rate": 9.947193462063924e-06, "loss": 0.6569, "step": 119170 }, { "epoch": 0.7084306697338778, "grad_norm": 4.663202285766602, "learning_rate": 9.94716338141122e-06, "loss": 0.5989, "step": 119180 }, { "epoch": 0.7084901118105462, "grad_norm": 6.010702610015869, "learning_rate": 9.94713329223891e-06, "loss": 0.5844, "step": 119190 }, { "epoch": 0.7085495538872146, "grad_norm": 5.449317932128906, "learning_rate": 9.947103194547046e-06, "loss": 0.6082, "step": 119200 }, { "epoch": 0.708608995963883, "grad_norm": 6.5667033195495605, "learning_rate": 9.94707308833568e-06, "loss": 0.6048, "step": 119210 }, { "epoch": 0.7086684380405514, "grad_norm": 5.435492038726807, "learning_rate": 9.947042973604862e-06, "loss": 0.6578, "step": 119220 }, { "epoch": 0.7087278801172198, "grad_norm": 5.2208943367004395, "learning_rate": 9.947012850354647e-06, "loss": 0.6185, "step": 119230 }, { "epoch": 0.7087873221938882, "grad_norm": 5.834866523742676, "learning_rate": 9.946982718585085e-06, "loss": 0.6228, "step": 119240 }, { "epoch": 0.7088467642705566, "grad_norm": 6.247522830963135, "learning_rate": 9.94695257829623e-06, "loss": 0.6085, "step": 119250 }, { "epoch": 0.7089062063472249, "grad_norm": 5.426856994628906, "learning_rate": 9.946922429488134e-06, "loss": 0.6426, "step": 119260 }, { "epoch": 0.7089656484238933, "grad_norm": 5.490389823913574, "learning_rate": 9.946892272160843e-06, "loss": 0.6497, "step": 119270 }, { "epoch": 0.7090250905005617, "grad_norm": 5.063872814178467, "learning_rate": 9.946862106314416e-06, "loss": 0.5856, "step": 119280 }, { "epoch": 0.7090845325772301, "grad_norm": 4.54449987411499, "learning_rate": 9.946831931948902e-06, "loss": 0.5722, "step": 119290 }, { "epoch": 0.7091439746538986, "grad_norm": 4.759948253631592, "learning_rate": 9.946801749064351e-06, "loss": 0.5788, "step": 119300 }, { "epoch": 0.7092034167305669, "grad_norm": 5.6913743019104, "learning_rate": 9.946771557660819e-06, "loss": 0.5746, "step": 119310 }, { "epoch": 0.7092628588072353, "grad_norm": 8.777510643005371, "learning_rate": 9.946741357738356e-06, "loss": 0.636, "step": 119320 }, { "epoch": 0.7093223008839037, "grad_norm": 5.798901081085205, "learning_rate": 9.946711149297015e-06, "loss": 0.6164, "step": 119330 }, { "epoch": 0.7093817429605721, "grad_norm": 6.62512731552124, "learning_rate": 9.946680932336845e-06, "loss": 0.6197, "step": 119340 }, { "epoch": 0.7094411850372404, "grad_norm": 5.27426815032959, "learning_rate": 9.946650706857903e-06, "loss": 0.5799, "step": 119350 }, { "epoch": 0.7095006271139088, "grad_norm": 6.585377216339111, "learning_rate": 9.946620472860236e-06, "loss": 0.5708, "step": 119360 }, { "epoch": 0.7095600691905772, "grad_norm": 6.666507244110107, "learning_rate": 9.946590230343898e-06, "loss": 0.6746, "step": 119370 }, { "epoch": 0.7096195112672457, "grad_norm": 5.266573905944824, "learning_rate": 9.946559979308943e-06, "loss": 0.5435, "step": 119380 }, { "epoch": 0.7096789533439141, "grad_norm": 4.787078857421875, "learning_rate": 9.946529719755422e-06, "loss": 0.5985, "step": 119390 }, { "epoch": 0.7097383954205824, "grad_norm": 5.284474849700928, "learning_rate": 9.946499451683385e-06, "loss": 0.5796, "step": 119400 }, { "epoch": 0.7097978374972508, "grad_norm": 6.135540008544922, "learning_rate": 9.946469175092885e-06, "loss": 0.6068, "step": 119410 }, { "epoch": 0.7098572795739192, "grad_norm": 5.942248344421387, "learning_rate": 9.946438889983976e-06, "loss": 0.6051, "step": 119420 }, { "epoch": 0.7099167216505876, "grad_norm": 5.310551166534424, "learning_rate": 9.94640859635671e-06, "loss": 0.5889, "step": 119430 }, { "epoch": 0.709976163727256, "grad_norm": 4.950703144073486, "learning_rate": 9.946378294211138e-06, "loss": 0.6008, "step": 119440 }, { "epoch": 0.7100356058039243, "grad_norm": 6.863443374633789, "learning_rate": 9.946347983547311e-06, "loss": 0.6079, "step": 119450 }, { "epoch": 0.7100950478805927, "grad_norm": 6.21259880065918, "learning_rate": 9.946317664365284e-06, "loss": 0.5904, "step": 119460 }, { "epoch": 0.7101544899572612, "grad_norm": 5.528943061828613, "learning_rate": 9.946287336665106e-06, "loss": 0.5554, "step": 119470 }, { "epoch": 0.7102139320339296, "grad_norm": 5.74036169052124, "learning_rate": 9.946257000446833e-06, "loss": 0.6483, "step": 119480 }, { "epoch": 0.7102733741105979, "grad_norm": 5.113955020904541, "learning_rate": 9.946226655710515e-06, "loss": 0.6304, "step": 119490 }, { "epoch": 0.7103328161872663, "grad_norm": 4.853128910064697, "learning_rate": 9.946196302456204e-06, "loss": 0.5989, "step": 119500 }, { "epoch": 0.7103922582639347, "grad_norm": 5.506591796875, "learning_rate": 9.946165940683951e-06, "loss": 0.6294, "step": 119510 }, { "epoch": 0.7104517003406031, "grad_norm": 5.696303844451904, "learning_rate": 9.946135570393813e-06, "loss": 0.5764, "step": 119520 }, { "epoch": 0.7105111424172715, "grad_norm": 4.837765216827393, "learning_rate": 9.946105191585837e-06, "loss": 0.6555, "step": 119530 }, { "epoch": 0.7105705844939398, "grad_norm": 4.899135112762451, "learning_rate": 9.946074804260079e-06, "loss": 0.569, "step": 119540 }, { "epoch": 0.7106300265706083, "grad_norm": 5.0335893630981445, "learning_rate": 9.946044408416591e-06, "loss": 0.6122, "step": 119550 }, { "epoch": 0.7106894686472767, "grad_norm": 6.612356662750244, "learning_rate": 9.946014004055424e-06, "loss": 0.6116, "step": 119560 }, { "epoch": 0.7107489107239451, "grad_norm": 5.192322254180908, "learning_rate": 9.94598359117663e-06, "loss": 0.6144, "step": 119570 }, { "epoch": 0.7108083528006135, "grad_norm": 4.997071266174316, "learning_rate": 9.945953169780262e-06, "loss": 0.5713, "step": 119580 }, { "epoch": 0.7108677948772818, "grad_norm": 6.5293049812316895, "learning_rate": 9.945922739866372e-06, "loss": 0.5986, "step": 119590 }, { "epoch": 0.7109272369539502, "grad_norm": 5.8219075202941895, "learning_rate": 9.945892301435013e-06, "loss": 0.5886, "step": 119600 }, { "epoch": 0.7109866790306186, "grad_norm": 5.8868536949157715, "learning_rate": 9.945861854486238e-06, "loss": 0.6456, "step": 119610 }, { "epoch": 0.711046121107287, "grad_norm": 6.014644145965576, "learning_rate": 9.9458313990201e-06, "loss": 0.5806, "step": 119620 }, { "epoch": 0.7111055631839553, "grad_norm": 6.147177696228027, "learning_rate": 9.945800935036649e-06, "loss": 0.6688, "step": 119630 }, { "epoch": 0.7111650052606238, "grad_norm": 4.572376728057861, "learning_rate": 9.945770462535938e-06, "loss": 0.6577, "step": 119640 }, { "epoch": 0.7112244473372922, "grad_norm": 5.800933361053467, "learning_rate": 9.94573998151802e-06, "loss": 0.643, "step": 119650 }, { "epoch": 0.7112838894139606, "grad_norm": 5.790275573730469, "learning_rate": 9.94570949198295e-06, "loss": 0.5284, "step": 119660 }, { "epoch": 0.711343331490629, "grad_norm": 4.949270725250244, "learning_rate": 9.945678993930776e-06, "loss": 0.5749, "step": 119670 }, { "epoch": 0.7114027735672973, "grad_norm": 6.160675048828125, "learning_rate": 9.945648487361553e-06, "loss": 0.6753, "step": 119680 }, { "epoch": 0.7114622156439657, "grad_norm": 9.82024097442627, "learning_rate": 9.945617972275334e-06, "loss": 0.6779, "step": 119690 }, { "epoch": 0.7115216577206341, "grad_norm": 8.353219032287598, "learning_rate": 9.94558744867217e-06, "loss": 0.5822, "step": 119700 }, { "epoch": 0.7115810997973026, "grad_norm": 5.931252479553223, "learning_rate": 9.945556916552114e-06, "loss": 0.6046, "step": 119710 }, { "epoch": 0.7116405418739709, "grad_norm": 4.9167304039001465, "learning_rate": 9.945526375915219e-06, "loss": 0.5718, "step": 119720 }, { "epoch": 0.7116999839506393, "grad_norm": 3.514960527420044, "learning_rate": 9.945495826761537e-06, "loss": 0.6158, "step": 119730 }, { "epoch": 0.7117594260273077, "grad_norm": 5.05731725692749, "learning_rate": 9.945465269091123e-06, "loss": 0.6302, "step": 119740 }, { "epoch": 0.7118188681039761, "grad_norm": 7.396440505981445, "learning_rate": 9.945434702904026e-06, "loss": 0.6565, "step": 119750 }, { "epoch": 0.7118783101806445, "grad_norm": 5.7745866775512695, "learning_rate": 9.9454041282003e-06, "loss": 0.6149, "step": 119760 }, { "epoch": 0.7119377522573128, "grad_norm": 5.6510114669799805, "learning_rate": 9.94537354498e-06, "loss": 0.5892, "step": 119770 }, { "epoch": 0.7119971943339812, "grad_norm": 5.937443256378174, "learning_rate": 9.945342953243175e-06, "loss": 0.6304, "step": 119780 }, { "epoch": 0.7120566364106496, "grad_norm": 4.546088218688965, "learning_rate": 9.94531235298988e-06, "loss": 0.5748, "step": 119790 }, { "epoch": 0.7121160784873181, "grad_norm": 5.1157917976379395, "learning_rate": 9.945281744220167e-06, "loss": 0.5757, "step": 119800 }, { "epoch": 0.7121755205639865, "grad_norm": 4.174813270568848, "learning_rate": 9.94525112693409e-06, "loss": 0.5905, "step": 119810 }, { "epoch": 0.7122349626406548, "grad_norm": 5.819005966186523, "learning_rate": 9.945220501131699e-06, "loss": 0.5835, "step": 119820 }, { "epoch": 0.7122944047173232, "grad_norm": 7.105286121368408, "learning_rate": 9.945189866813048e-06, "loss": 0.5895, "step": 119830 }, { "epoch": 0.7123538467939916, "grad_norm": 4.0922651290893555, "learning_rate": 9.945159223978192e-06, "loss": 0.5399, "step": 119840 }, { "epoch": 0.71241328887066, "grad_norm": 6.40294885635376, "learning_rate": 9.94512857262718e-06, "loss": 0.6018, "step": 119850 }, { "epoch": 0.7124727309473283, "grad_norm": 5.255063056945801, "learning_rate": 9.945097912760067e-06, "loss": 0.6577, "step": 119860 }, { "epoch": 0.7125321730239967, "grad_norm": 5.264367580413818, "learning_rate": 9.945067244376905e-06, "loss": 0.623, "step": 119870 }, { "epoch": 0.7125916151006652, "grad_norm": 4.6088995933532715, "learning_rate": 9.945036567477747e-06, "loss": 0.6107, "step": 119880 }, { "epoch": 0.7126510571773336, "grad_norm": 5.858384609222412, "learning_rate": 9.945005882062646e-06, "loss": 0.5298, "step": 119890 }, { "epoch": 0.712710499254002, "grad_norm": 4.356720924377441, "learning_rate": 9.944975188131656e-06, "loss": 0.5822, "step": 119900 }, { "epoch": 0.7127699413306703, "grad_norm": 4.224957466125488, "learning_rate": 9.944944485684828e-06, "loss": 0.6267, "step": 119910 }, { "epoch": 0.7128293834073387, "grad_norm": 5.8883233070373535, "learning_rate": 9.944913774722216e-06, "loss": 0.6547, "step": 119920 }, { "epoch": 0.7128888254840071, "grad_norm": 7.128195285797119, "learning_rate": 9.944883055243872e-06, "loss": 0.5895, "step": 119930 }, { "epoch": 0.7129482675606755, "grad_norm": 5.260448455810547, "learning_rate": 9.94485232724985e-06, "loss": 0.5609, "step": 119940 }, { "epoch": 0.713007709637344, "grad_norm": 5.2318878173828125, "learning_rate": 9.9448215907402e-06, "loss": 0.6192, "step": 119950 }, { "epoch": 0.7130671517140122, "grad_norm": 6.280428409576416, "learning_rate": 9.94479084571498e-06, "loss": 0.6258, "step": 119960 }, { "epoch": 0.7131265937906807, "grad_norm": 5.446034908294678, "learning_rate": 9.94476009217424e-06, "loss": 0.6442, "step": 119970 }, { "epoch": 0.7131860358673491, "grad_norm": 6.16963005065918, "learning_rate": 9.94472933011803e-06, "loss": 0.638, "step": 119980 }, { "epoch": 0.7132454779440175, "grad_norm": 8.310441017150879, "learning_rate": 9.944698559546408e-06, "loss": 0.5302, "step": 119990 }, { "epoch": 0.7133049200206858, "grad_norm": 4.524028301239014, "learning_rate": 9.944667780459427e-06, "loss": 0.5882, "step": 120000 }, { "epoch": 0.7133643620973542, "grad_norm": 8.45053482055664, "learning_rate": 9.944636992857136e-06, "loss": 0.6675, "step": 120010 }, { "epoch": 0.7134238041740226, "grad_norm": 4.2016167640686035, "learning_rate": 9.94460619673959e-06, "loss": 0.6287, "step": 120020 }, { "epoch": 0.713483246250691, "grad_norm": 4.757966041564941, "learning_rate": 9.944575392106843e-06, "loss": 0.6393, "step": 120030 }, { "epoch": 0.7135426883273595, "grad_norm": 6.336212158203125, "learning_rate": 9.944544578958947e-06, "loss": 0.6213, "step": 120040 }, { "epoch": 0.7136021304040278, "grad_norm": 7.003971099853516, "learning_rate": 9.944513757295954e-06, "loss": 0.6071, "step": 120050 }, { "epoch": 0.7136615724806962, "grad_norm": 4.903209209442139, "learning_rate": 9.94448292711792e-06, "loss": 0.5993, "step": 120060 }, { "epoch": 0.7137210145573646, "grad_norm": 5.086216926574707, "learning_rate": 9.944452088424896e-06, "loss": 0.5702, "step": 120070 }, { "epoch": 0.713780456634033, "grad_norm": 5.270774841308594, "learning_rate": 9.944421241216936e-06, "loss": 0.6655, "step": 120080 }, { "epoch": 0.7138398987107013, "grad_norm": 5.280155181884766, "learning_rate": 9.944390385494093e-06, "loss": 0.6593, "step": 120090 }, { "epoch": 0.7138993407873697, "grad_norm": 5.1047797203063965, "learning_rate": 9.944359521256419e-06, "loss": 0.6592, "step": 120100 }, { "epoch": 0.7139587828640381, "grad_norm": 5.521175861358643, "learning_rate": 9.944328648503966e-06, "loss": 0.5566, "step": 120110 }, { "epoch": 0.7140182249407065, "grad_norm": 6.561683177947998, "learning_rate": 9.944297767236793e-06, "loss": 0.6505, "step": 120120 }, { "epoch": 0.714077667017375, "grad_norm": 6.416489124298096, "learning_rate": 9.944266877454946e-06, "loss": 0.5907, "step": 120130 }, { "epoch": 0.7141371090940433, "grad_norm": 7.300679683685303, "learning_rate": 9.944235979158484e-06, "loss": 0.6186, "step": 120140 }, { "epoch": 0.7141965511707117, "grad_norm": 6.5845627784729, "learning_rate": 9.944205072347457e-06, "loss": 0.5695, "step": 120150 }, { "epoch": 0.7142559932473801, "grad_norm": 6.368984699249268, "learning_rate": 9.944174157021917e-06, "loss": 0.5969, "step": 120160 }, { "epoch": 0.7143154353240485, "grad_norm": 5.020556449890137, "learning_rate": 9.944143233181922e-06, "loss": 0.66, "step": 120170 }, { "epoch": 0.7143748774007169, "grad_norm": 6.83208703994751, "learning_rate": 9.94411230082752e-06, "loss": 0.5863, "step": 120180 }, { "epoch": 0.7144343194773852, "grad_norm": 6.803879261016846, "learning_rate": 9.944081359958768e-06, "loss": 0.5965, "step": 120190 }, { "epoch": 0.7144937615540536, "grad_norm": 6.184258937835693, "learning_rate": 9.944050410575718e-06, "loss": 0.5858, "step": 120200 }, { "epoch": 0.7145532036307221, "grad_norm": 4.755484104156494, "learning_rate": 9.944019452678422e-06, "loss": 0.5996, "step": 120210 }, { "epoch": 0.7146126457073905, "grad_norm": 4.532552719116211, "learning_rate": 9.943988486266936e-06, "loss": 0.5697, "step": 120220 }, { "epoch": 0.7146720877840588, "grad_norm": 4.792726993560791, "learning_rate": 9.943957511341312e-06, "loss": 0.5778, "step": 120230 }, { "epoch": 0.7147315298607272, "grad_norm": 5.727295875549316, "learning_rate": 9.943926527901603e-06, "loss": 0.5777, "step": 120240 }, { "epoch": 0.7147909719373956, "grad_norm": 6.256960868835449, "learning_rate": 9.943895535947862e-06, "loss": 0.5804, "step": 120250 }, { "epoch": 0.714850414014064, "grad_norm": 4.175143718719482, "learning_rate": 9.943864535480143e-06, "loss": 0.5717, "step": 120260 }, { "epoch": 0.7149098560907324, "grad_norm": 6.635653972625732, "learning_rate": 9.9438335264985e-06, "loss": 0.5796, "step": 120270 }, { "epoch": 0.7149692981674007, "grad_norm": 5.121653079986572, "learning_rate": 9.943802509002986e-06, "loss": 0.608, "step": 120280 }, { "epoch": 0.7150287402440691, "grad_norm": 5.560980319976807, "learning_rate": 9.943771482993654e-06, "loss": 0.5914, "step": 120290 }, { "epoch": 0.7150881823207376, "grad_norm": 4.796256065368652, "learning_rate": 9.943740448470558e-06, "loss": 0.6222, "step": 120300 }, { "epoch": 0.715147624397406, "grad_norm": 3.6186654567718506, "learning_rate": 9.94370940543375e-06, "loss": 0.5493, "step": 120310 }, { "epoch": 0.7152070664740744, "grad_norm": 5.471951007843018, "learning_rate": 9.943678353883285e-06, "loss": 0.5978, "step": 120320 }, { "epoch": 0.7152665085507427, "grad_norm": 6.808755874633789, "learning_rate": 9.943647293819217e-06, "loss": 0.5109, "step": 120330 }, { "epoch": 0.7153259506274111, "grad_norm": 6.409741401672363, "learning_rate": 9.943616225241597e-06, "loss": 0.6296, "step": 120340 }, { "epoch": 0.7153853927040795, "grad_norm": 5.3758769035339355, "learning_rate": 9.94358514815048e-06, "loss": 0.6088, "step": 120350 }, { "epoch": 0.7154448347807479, "grad_norm": 4.645007610321045, "learning_rate": 9.943554062545919e-06, "loss": 0.642, "step": 120360 }, { "epoch": 0.7155042768574162, "grad_norm": 6.347116470336914, "learning_rate": 9.94352296842797e-06, "loss": 0.6206, "step": 120370 }, { "epoch": 0.7155637189340847, "grad_norm": 4.6401262283325195, "learning_rate": 9.943491865796685e-06, "loss": 0.6094, "step": 120380 }, { "epoch": 0.7156231610107531, "grad_norm": 4.5002899169921875, "learning_rate": 9.943460754652115e-06, "loss": 0.573, "step": 120390 }, { "epoch": 0.7156826030874215, "grad_norm": 7.526070594787598, "learning_rate": 9.943429634994317e-06, "loss": 0.6085, "step": 120400 }, { "epoch": 0.7157420451640899, "grad_norm": 4.802032470703125, "learning_rate": 9.943398506823341e-06, "loss": 0.58, "step": 120410 }, { "epoch": 0.7158014872407582, "grad_norm": 6.741115570068359, "learning_rate": 9.943367370139246e-06, "loss": 0.5974, "step": 120420 }, { "epoch": 0.7158609293174266, "grad_norm": 5.4181904792785645, "learning_rate": 9.943336224942081e-06, "loss": 0.5753, "step": 120430 }, { "epoch": 0.715920371394095, "grad_norm": 7.5253214836120605, "learning_rate": 9.943305071231902e-06, "loss": 0.646, "step": 120440 }, { "epoch": 0.7159798134707634, "grad_norm": 5.397779941558838, "learning_rate": 9.943273909008762e-06, "loss": 0.6484, "step": 120450 }, { "epoch": 0.7160392555474318, "grad_norm": 6.372776508331299, "learning_rate": 9.943242738272712e-06, "loss": 0.6293, "step": 120460 }, { "epoch": 0.7160986976241002, "grad_norm": 5.0579376220703125, "learning_rate": 9.94321155902381e-06, "loss": 0.5476, "step": 120470 }, { "epoch": 0.7161581397007686, "grad_norm": 5.302478313446045, "learning_rate": 9.943180371262108e-06, "loss": 0.5755, "step": 120480 }, { "epoch": 0.716217581777437, "grad_norm": 4.964478015899658, "learning_rate": 9.943149174987661e-06, "loss": 0.5722, "step": 120490 }, { "epoch": 0.7162770238541054, "grad_norm": 6.513331413269043, "learning_rate": 9.94311797020052e-06, "loss": 0.5917, "step": 120500 }, { "epoch": 0.7163364659307737, "grad_norm": 5.245136737823486, "learning_rate": 9.943086756900739e-06, "loss": 0.5811, "step": 120510 }, { "epoch": 0.7163959080074421, "grad_norm": 5.874998092651367, "learning_rate": 9.943055535088373e-06, "loss": 0.6165, "step": 120520 }, { "epoch": 0.7164553500841105, "grad_norm": 4.016444683074951, "learning_rate": 9.943024304763478e-06, "loss": 0.5834, "step": 120530 }, { "epoch": 0.716514792160779, "grad_norm": 6.217469215393066, "learning_rate": 9.942993065926103e-06, "loss": 0.5979, "step": 120540 }, { "epoch": 0.7165742342374474, "grad_norm": 6.493566989898682, "learning_rate": 9.942961818576304e-06, "loss": 0.5721, "step": 120550 }, { "epoch": 0.7166336763141157, "grad_norm": 6.290493965148926, "learning_rate": 9.942930562714138e-06, "loss": 0.6038, "step": 120560 }, { "epoch": 0.7166931183907841, "grad_norm": 4.739989280700684, "learning_rate": 9.942899298339652e-06, "loss": 0.5737, "step": 120570 }, { "epoch": 0.7167525604674525, "grad_norm": 4.763123989105225, "learning_rate": 9.942868025452905e-06, "loss": 0.6037, "step": 120580 }, { "epoch": 0.7168120025441209, "grad_norm": 5.956110000610352, "learning_rate": 9.94283674405395e-06, "loss": 0.619, "step": 120590 }, { "epoch": 0.7168714446207892, "grad_norm": 4.906968593597412, "learning_rate": 9.94280545414284e-06, "loss": 0.5834, "step": 120600 }, { "epoch": 0.7169308866974576, "grad_norm": 4.475165843963623, "learning_rate": 9.94277415571963e-06, "loss": 0.5663, "step": 120610 }, { "epoch": 0.716990328774126, "grad_norm": 4.640063285827637, "learning_rate": 9.942742848784371e-06, "loss": 0.6016, "step": 120620 }, { "epoch": 0.7170497708507945, "grad_norm": 5.409645080566406, "learning_rate": 9.942711533337122e-06, "loss": 0.6001, "step": 120630 }, { "epoch": 0.7171092129274629, "grad_norm": 5.545951843261719, "learning_rate": 9.942680209377931e-06, "loss": 0.5923, "step": 120640 }, { "epoch": 0.7171686550041312, "grad_norm": 5.992654800415039, "learning_rate": 9.942648876906857e-06, "loss": 0.5604, "step": 120650 }, { "epoch": 0.7172280970807996, "grad_norm": 5.662594795227051, "learning_rate": 9.942617535923951e-06, "loss": 0.5244, "step": 120660 }, { "epoch": 0.717287539157468, "grad_norm": 4.258274555206299, "learning_rate": 9.942586186429269e-06, "loss": 0.604, "step": 120670 }, { "epoch": 0.7173469812341364, "grad_norm": 6.060463905334473, "learning_rate": 9.942554828422862e-06, "loss": 0.5727, "step": 120680 }, { "epoch": 0.7174064233108048, "grad_norm": 4.554074764251709, "learning_rate": 9.942523461904787e-06, "loss": 0.5873, "step": 120690 }, { "epoch": 0.7174658653874731, "grad_norm": 5.3129963874816895, "learning_rate": 9.942492086875097e-06, "loss": 0.5696, "step": 120700 }, { "epoch": 0.7175253074641416, "grad_norm": 7.053829669952393, "learning_rate": 9.942460703333846e-06, "loss": 0.64, "step": 120710 }, { "epoch": 0.71758474954081, "grad_norm": 7.251506805419922, "learning_rate": 9.942429311281087e-06, "loss": 0.6458, "step": 120720 }, { "epoch": 0.7176441916174784, "grad_norm": 5.855252265930176, "learning_rate": 9.942397910716875e-06, "loss": 0.582, "step": 120730 }, { "epoch": 0.7177036336941467, "grad_norm": 4.7855730056762695, "learning_rate": 9.942366501641265e-06, "loss": 0.5819, "step": 120740 }, { "epoch": 0.7177630757708151, "grad_norm": 5.9122843742370605, "learning_rate": 9.94233508405431e-06, "loss": 0.5828, "step": 120750 }, { "epoch": 0.7178225178474835, "grad_norm": 4.74506950378418, "learning_rate": 9.942303657956064e-06, "loss": 0.6149, "step": 120760 }, { "epoch": 0.7178819599241519, "grad_norm": 5.130927562713623, "learning_rate": 9.94227222334658e-06, "loss": 0.6264, "step": 120770 }, { "epoch": 0.7179414020008204, "grad_norm": 4.925718307495117, "learning_rate": 9.942240780225916e-06, "loss": 0.6023, "step": 120780 }, { "epoch": 0.7180008440774887, "grad_norm": 5.705073833465576, "learning_rate": 9.942209328594124e-06, "loss": 0.612, "step": 120790 }, { "epoch": 0.7180602861541571, "grad_norm": 5.630373954772949, "learning_rate": 9.942177868451254e-06, "loss": 0.5539, "step": 120800 }, { "epoch": 0.7181197282308255, "grad_norm": 5.384754180908203, "learning_rate": 9.942146399797368e-06, "loss": 0.5943, "step": 120810 }, { "epoch": 0.7181791703074939, "grad_norm": 4.515512943267822, "learning_rate": 9.942114922632516e-06, "loss": 0.6333, "step": 120820 }, { "epoch": 0.7182386123841622, "grad_norm": 5.603518009185791, "learning_rate": 9.942083436956751e-06, "loss": 0.5561, "step": 120830 }, { "epoch": 0.7182980544608306, "grad_norm": 5.798369407653809, "learning_rate": 9.942051942770127e-06, "loss": 0.6599, "step": 120840 }, { "epoch": 0.718357496537499, "grad_norm": 5.677881240844727, "learning_rate": 9.942020440072702e-06, "loss": 0.6355, "step": 120850 }, { "epoch": 0.7184169386141674, "grad_norm": 5.410180568695068, "learning_rate": 9.941988928864527e-06, "loss": 0.5871, "step": 120860 }, { "epoch": 0.7184763806908359, "grad_norm": 5.77741003036499, "learning_rate": 9.94195740914566e-06, "loss": 0.554, "step": 120870 }, { "epoch": 0.7185358227675042, "grad_norm": 4.839695453643799, "learning_rate": 9.94192588091615e-06, "loss": 0.6359, "step": 120880 }, { "epoch": 0.7185952648441726, "grad_norm": 6.145448684692383, "learning_rate": 9.941894344176055e-06, "loss": 0.6231, "step": 120890 }, { "epoch": 0.718654706920841, "grad_norm": 7.291370391845703, "learning_rate": 9.941862798925428e-06, "loss": 0.632, "step": 120900 }, { "epoch": 0.7187141489975094, "grad_norm": 5.766559600830078, "learning_rate": 9.941831245164324e-06, "loss": 0.6364, "step": 120910 }, { "epoch": 0.7187735910741778, "grad_norm": 5.747551918029785, "learning_rate": 9.941799682892796e-06, "loss": 0.5723, "step": 120920 }, { "epoch": 0.7188330331508461, "grad_norm": 3.9992387294769287, "learning_rate": 9.941768112110902e-06, "loss": 0.5953, "step": 120930 }, { "epoch": 0.7188924752275145, "grad_norm": 4.093221664428711, "learning_rate": 9.941736532818691e-06, "loss": 0.5847, "step": 120940 }, { "epoch": 0.718951917304183, "grad_norm": 5.823267936706543, "learning_rate": 9.94170494501622e-06, "loss": 0.613, "step": 120950 }, { "epoch": 0.7190113593808514, "grad_norm": 4.977066516876221, "learning_rate": 9.941673348703545e-06, "loss": 0.5573, "step": 120960 }, { "epoch": 0.7190708014575197, "grad_norm": 5.243015766143799, "learning_rate": 9.941641743880718e-06, "loss": 0.5499, "step": 120970 }, { "epoch": 0.7191302435341881, "grad_norm": 5.906090259552002, "learning_rate": 9.941610130547795e-06, "loss": 0.6047, "step": 120980 }, { "epoch": 0.7191896856108565, "grad_norm": 4.857832431793213, "learning_rate": 9.941578508704828e-06, "loss": 0.6498, "step": 120990 }, { "epoch": 0.7192491276875249, "grad_norm": 7.1901021003723145, "learning_rate": 9.941546878351874e-06, "loss": 0.6214, "step": 121000 }, { "epoch": 0.7193085697641933, "grad_norm": 5.406002521514893, "learning_rate": 9.941515239488987e-06, "loss": 0.58, "step": 121010 }, { "epoch": 0.7193680118408616, "grad_norm": 6.575573921203613, "learning_rate": 9.941483592116222e-06, "loss": 0.6521, "step": 121020 }, { "epoch": 0.71942745391753, "grad_norm": 5.519839286804199, "learning_rate": 9.94145193623363e-06, "loss": 0.5745, "step": 121030 }, { "epoch": 0.7194868959941985, "grad_norm": 4.349879741668701, "learning_rate": 9.941420271841271e-06, "loss": 0.5719, "step": 121040 }, { "epoch": 0.7195463380708669, "grad_norm": 4.7699971199035645, "learning_rate": 9.941388598939194e-06, "loss": 0.6459, "step": 121050 }, { "epoch": 0.7196057801475352, "grad_norm": 3.8663887977600098, "learning_rate": 9.941356917527458e-06, "loss": 0.5657, "step": 121060 }, { "epoch": 0.7196652222242036, "grad_norm": 6.402524471282959, "learning_rate": 9.941325227606117e-06, "loss": 0.626, "step": 121070 }, { "epoch": 0.719724664300872, "grad_norm": 4.15580940246582, "learning_rate": 9.941293529175223e-06, "loss": 0.5258, "step": 121080 }, { "epoch": 0.7197841063775404, "grad_norm": 5.828126907348633, "learning_rate": 9.94126182223483e-06, "loss": 0.5989, "step": 121090 }, { "epoch": 0.7198435484542088, "grad_norm": 5.160006523132324, "learning_rate": 9.941230106784997e-06, "loss": 0.622, "step": 121100 }, { "epoch": 0.7199029905308771, "grad_norm": 5.185040473937988, "learning_rate": 9.941198382825777e-06, "loss": 0.5707, "step": 121110 }, { "epoch": 0.7199624326075456, "grad_norm": 5.555423259735107, "learning_rate": 9.94116665035722e-06, "loss": 0.5632, "step": 121120 }, { "epoch": 0.720021874684214, "grad_norm": 5.041816711425781, "learning_rate": 9.941134909379388e-06, "loss": 0.584, "step": 121130 }, { "epoch": 0.7200813167608824, "grad_norm": 5.716215133666992, "learning_rate": 9.941103159892331e-06, "loss": 0.5654, "step": 121140 }, { "epoch": 0.7201407588375508, "grad_norm": 5.055391311645508, "learning_rate": 9.941071401896104e-06, "loss": 0.6099, "step": 121150 }, { "epoch": 0.7202002009142191, "grad_norm": 4.969122886657715, "learning_rate": 9.941039635390766e-06, "loss": 0.5624, "step": 121160 }, { "epoch": 0.7202596429908875, "grad_norm": 5.658868312835693, "learning_rate": 9.941007860376365e-06, "loss": 0.5555, "step": 121170 }, { "epoch": 0.7203190850675559, "grad_norm": 5.156554698944092, "learning_rate": 9.940976076852959e-06, "loss": 0.5869, "step": 121180 }, { "epoch": 0.7203785271442243, "grad_norm": 6.777749538421631, "learning_rate": 9.940944284820604e-06, "loss": 0.6263, "step": 121190 }, { "epoch": 0.7204379692208926, "grad_norm": 4.963367938995361, "learning_rate": 9.94091248427935e-06, "loss": 0.5569, "step": 121200 }, { "epoch": 0.7204974112975611, "grad_norm": 6.417836666107178, "learning_rate": 9.940880675229258e-06, "loss": 0.5952, "step": 121210 }, { "epoch": 0.7205568533742295, "grad_norm": 6.810146808624268, "learning_rate": 9.940848857670381e-06, "loss": 0.5916, "step": 121220 }, { "epoch": 0.7206162954508979, "grad_norm": 5.625193119049072, "learning_rate": 9.940817031602772e-06, "loss": 0.5951, "step": 121230 }, { "epoch": 0.7206757375275663, "grad_norm": 7.072225570678711, "learning_rate": 9.940785197026486e-06, "loss": 0.5914, "step": 121240 }, { "epoch": 0.7207351796042346, "grad_norm": 5.500085830688477, "learning_rate": 9.940753353941576e-06, "loss": 0.566, "step": 121250 }, { "epoch": 0.720794621680903, "grad_norm": 5.986014366149902, "learning_rate": 9.940721502348102e-06, "loss": 0.5726, "step": 121260 }, { "epoch": 0.7208540637575714, "grad_norm": 5.763195514678955, "learning_rate": 9.940689642246115e-06, "loss": 0.6411, "step": 121270 }, { "epoch": 0.7209135058342399, "grad_norm": 7.019708633422852, "learning_rate": 9.940657773635672e-06, "loss": 0.575, "step": 121280 }, { "epoch": 0.7209729479109083, "grad_norm": 6.4962053298950195, "learning_rate": 9.940625896516827e-06, "loss": 0.5879, "step": 121290 }, { "epoch": 0.7210323899875766, "grad_norm": 5.944789409637451, "learning_rate": 9.940594010889633e-06, "loss": 0.633, "step": 121300 }, { "epoch": 0.721091832064245, "grad_norm": 4.325430393218994, "learning_rate": 9.94056211675415e-06, "loss": 0.6086, "step": 121310 }, { "epoch": 0.7211512741409134, "grad_norm": 6.256422996520996, "learning_rate": 9.940530214110425e-06, "loss": 0.5502, "step": 121320 }, { "epoch": 0.7212107162175818, "grad_norm": 5.231033802032471, "learning_rate": 9.940498302958519e-06, "loss": 0.6013, "step": 121330 }, { "epoch": 0.7212701582942501, "grad_norm": 7.0527825355529785, "learning_rate": 9.940466383298486e-06, "loss": 0.6279, "step": 121340 }, { "epoch": 0.7213296003709185, "grad_norm": 6.337546348571777, "learning_rate": 9.940434455130381e-06, "loss": 0.6292, "step": 121350 }, { "epoch": 0.721389042447587, "grad_norm": 4.892557621002197, "learning_rate": 9.940402518454257e-06, "loss": 0.6384, "step": 121360 }, { "epoch": 0.7214484845242554, "grad_norm": 6.231236934661865, "learning_rate": 9.940370573270171e-06, "loss": 0.6283, "step": 121370 }, { "epoch": 0.7215079266009238, "grad_norm": 5.123525142669678, "learning_rate": 9.940338619578178e-06, "loss": 0.5693, "step": 121380 }, { "epoch": 0.7215673686775921, "grad_norm": 4.712652683258057, "learning_rate": 9.940306657378332e-06, "loss": 0.5684, "step": 121390 }, { "epoch": 0.7216268107542605, "grad_norm": 6.602420330047607, "learning_rate": 9.940274686670689e-06, "loss": 0.5667, "step": 121400 }, { "epoch": 0.7216862528309289, "grad_norm": 4.421201705932617, "learning_rate": 9.940242707455302e-06, "loss": 0.566, "step": 121410 }, { "epoch": 0.7217456949075973, "grad_norm": 4.54189395904541, "learning_rate": 9.94021071973223e-06, "loss": 0.5703, "step": 121420 }, { "epoch": 0.7218051369842656, "grad_norm": 5.40300989151001, "learning_rate": 9.940178723501523e-06, "loss": 0.6018, "step": 121430 }, { "epoch": 0.721864579060934, "grad_norm": 4.647572040557861, "learning_rate": 9.94014671876324e-06, "loss": 0.5717, "step": 121440 }, { "epoch": 0.7219240211376025, "grad_norm": 4.854693412780762, "learning_rate": 9.940114705517435e-06, "loss": 0.6097, "step": 121450 }, { "epoch": 0.7219834632142709, "grad_norm": 5.572443962097168, "learning_rate": 9.940082683764163e-06, "loss": 0.6187, "step": 121460 }, { "epoch": 0.7220429052909393, "grad_norm": 4.636115074157715, "learning_rate": 9.94005065350348e-06, "loss": 0.6178, "step": 121470 }, { "epoch": 0.7221023473676076, "grad_norm": 7.331130027770996, "learning_rate": 9.940018614735438e-06, "loss": 0.5455, "step": 121480 }, { "epoch": 0.722161789444276, "grad_norm": 7.428775787353516, "learning_rate": 9.939986567460097e-06, "loss": 0.6343, "step": 121490 }, { "epoch": 0.7222212315209444, "grad_norm": 5.648992538452148, "learning_rate": 9.939954511677508e-06, "loss": 0.5942, "step": 121500 }, { "epoch": 0.7222806735976128, "grad_norm": 4.702269077301025, "learning_rate": 9.939922447387729e-06, "loss": 0.5834, "step": 121510 }, { "epoch": 0.7223401156742812, "grad_norm": 5.464945316314697, "learning_rate": 9.939890374590814e-06, "loss": 0.5894, "step": 121520 }, { "epoch": 0.7223995577509496, "grad_norm": 6.5270609855651855, "learning_rate": 9.939858293286818e-06, "loss": 0.6937, "step": 121530 }, { "epoch": 0.722458999827618, "grad_norm": 7.005713939666748, "learning_rate": 9.939826203475797e-06, "loss": 0.6264, "step": 121540 }, { "epoch": 0.7225184419042864, "grad_norm": 6.230196952819824, "learning_rate": 9.939794105157805e-06, "loss": 0.6406, "step": 121550 }, { "epoch": 0.7225778839809548, "grad_norm": 7.504317283630371, "learning_rate": 9.939761998332899e-06, "loss": 0.5949, "step": 121560 }, { "epoch": 0.7226373260576231, "grad_norm": 6.537773609161377, "learning_rate": 9.939729883001132e-06, "loss": 0.629, "step": 121570 }, { "epoch": 0.7226967681342915, "grad_norm": 6.6072306632995605, "learning_rate": 9.939697759162563e-06, "loss": 0.6, "step": 121580 }, { "epoch": 0.7227562102109599, "grad_norm": 6.967056751251221, "learning_rate": 9.939665626817242e-06, "loss": 0.5839, "step": 121590 }, { "epoch": 0.7228156522876283, "grad_norm": 7.355018615722656, "learning_rate": 9.93963348596523e-06, "loss": 0.5881, "step": 121600 }, { "epoch": 0.7228750943642968, "grad_norm": 4.974176406860352, "learning_rate": 9.939601336606578e-06, "loss": 0.6292, "step": 121610 }, { "epoch": 0.7229345364409651, "grad_norm": 5.719559192657471, "learning_rate": 9.939569178741346e-06, "loss": 0.5796, "step": 121620 }, { "epoch": 0.7229939785176335, "grad_norm": 6.4801177978515625, "learning_rate": 9.939537012369584e-06, "loss": 0.6421, "step": 121630 }, { "epoch": 0.7230534205943019, "grad_norm": 4.805165767669678, "learning_rate": 9.939504837491351e-06, "loss": 0.604, "step": 121640 }, { "epoch": 0.7231128626709703, "grad_norm": 4.959681034088135, "learning_rate": 9.939472654106701e-06, "loss": 0.5788, "step": 121650 }, { "epoch": 0.7231723047476387, "grad_norm": 5.329817295074463, "learning_rate": 9.93944046221569e-06, "loss": 0.5431, "step": 121660 }, { "epoch": 0.723231746824307, "grad_norm": 5.161690711975098, "learning_rate": 9.939408261818372e-06, "loss": 0.5835, "step": 121670 }, { "epoch": 0.7232911889009754, "grad_norm": 5.319878578186035, "learning_rate": 9.939376052914805e-06, "loss": 0.5903, "step": 121680 }, { "epoch": 0.7233506309776438, "grad_norm": 5.857443809509277, "learning_rate": 9.939343835505041e-06, "loss": 0.5861, "step": 121690 }, { "epoch": 0.7234100730543123, "grad_norm": 6.300393581390381, "learning_rate": 9.93931160958914e-06, "loss": 0.5585, "step": 121700 }, { "epoch": 0.7234695151309806, "grad_norm": 6.481513023376465, "learning_rate": 9.939279375167154e-06, "loss": 0.6045, "step": 121710 }, { "epoch": 0.723528957207649, "grad_norm": 7.2974700927734375, "learning_rate": 9.939247132239141e-06, "loss": 0.5913, "step": 121720 }, { "epoch": 0.7235883992843174, "grad_norm": 6.37963342666626, "learning_rate": 9.939214880805153e-06, "loss": 0.6728, "step": 121730 }, { "epoch": 0.7236478413609858, "grad_norm": 4.358035087585449, "learning_rate": 9.939182620865249e-06, "loss": 0.615, "step": 121740 }, { "epoch": 0.7237072834376542, "grad_norm": 4.717121601104736, "learning_rate": 9.939150352419482e-06, "loss": 0.5151, "step": 121750 }, { "epoch": 0.7237667255143225, "grad_norm": 5.121646404266357, "learning_rate": 9.939118075467908e-06, "loss": 0.6052, "step": 121760 }, { "epoch": 0.7238261675909909, "grad_norm": 5.767355442047119, "learning_rate": 9.939085790010586e-06, "loss": 0.6114, "step": 121770 }, { "epoch": 0.7238856096676594, "grad_norm": 5.4968485832214355, "learning_rate": 9.939053496047567e-06, "loss": 0.6362, "step": 121780 }, { "epoch": 0.7239450517443278, "grad_norm": 4.593817234039307, "learning_rate": 9.939021193578909e-06, "loss": 0.6014, "step": 121790 }, { "epoch": 0.7240044938209961, "grad_norm": 6.494775295257568, "learning_rate": 9.938988882604668e-06, "loss": 0.6702, "step": 121800 }, { "epoch": 0.7240639358976645, "grad_norm": 5.105477809906006, "learning_rate": 9.938956563124897e-06, "loss": 0.6308, "step": 121810 }, { "epoch": 0.7241233779743329, "grad_norm": 5.194107532501221, "learning_rate": 9.938924235139656e-06, "loss": 0.5447, "step": 121820 }, { "epoch": 0.7241828200510013, "grad_norm": 5.547020435333252, "learning_rate": 9.938891898648997e-06, "loss": 0.585, "step": 121830 }, { "epoch": 0.7242422621276697, "grad_norm": 5.001153469085693, "learning_rate": 9.938859553652976e-06, "loss": 0.5828, "step": 121840 }, { "epoch": 0.724301704204338, "grad_norm": 6.126274108886719, "learning_rate": 9.93882720015165e-06, "loss": 0.6187, "step": 121850 }, { "epoch": 0.7243611462810065, "grad_norm": 5.309957504272461, "learning_rate": 9.938794838145075e-06, "loss": 0.5775, "step": 121860 }, { "epoch": 0.7244205883576749, "grad_norm": 6.355445384979248, "learning_rate": 9.938762467633305e-06, "loss": 0.5744, "step": 121870 }, { "epoch": 0.7244800304343433, "grad_norm": 5.040470600128174, "learning_rate": 9.938730088616398e-06, "loss": 0.5544, "step": 121880 }, { "epoch": 0.7245394725110117, "grad_norm": 5.952947616577148, "learning_rate": 9.938697701094407e-06, "loss": 0.5273, "step": 121890 }, { "epoch": 0.72459891458768, "grad_norm": 6.830714225769043, "learning_rate": 9.938665305067389e-06, "loss": 0.6627, "step": 121900 }, { "epoch": 0.7246583566643484, "grad_norm": 6.736434459686279, "learning_rate": 9.938632900535403e-06, "loss": 0.6199, "step": 121910 }, { "epoch": 0.7247177987410168, "grad_norm": 3.8522191047668457, "learning_rate": 9.9386004874985e-06, "loss": 0.5948, "step": 121920 }, { "epoch": 0.7247772408176852, "grad_norm": 5.244298934936523, "learning_rate": 9.938568065956737e-06, "loss": 0.5808, "step": 121930 }, { "epoch": 0.7248366828943535, "grad_norm": 4.646168231964111, "learning_rate": 9.938535635910172e-06, "loss": 0.5914, "step": 121940 }, { "epoch": 0.724896124971022, "grad_norm": 6.298002243041992, "learning_rate": 9.93850319735886e-06, "loss": 0.6013, "step": 121950 }, { "epoch": 0.7249555670476904, "grad_norm": 5.789496898651123, "learning_rate": 9.938470750302853e-06, "loss": 0.5316, "step": 121960 }, { "epoch": 0.7250150091243588, "grad_norm": 5.077027797698975, "learning_rate": 9.938438294742212e-06, "loss": 0.5813, "step": 121970 }, { "epoch": 0.7250744512010272, "grad_norm": 5.703787326812744, "learning_rate": 9.938405830676992e-06, "loss": 0.6016, "step": 121980 }, { "epoch": 0.7251338932776955, "grad_norm": 5.189069747924805, "learning_rate": 9.938373358107247e-06, "loss": 0.5848, "step": 121990 }, { "epoch": 0.7251933353543639, "grad_norm": 5.016958713531494, "learning_rate": 9.938340877033032e-06, "loss": 0.6105, "step": 122000 }, { "epoch": 0.7252527774310323, "grad_norm": 4.689422130584717, "learning_rate": 9.938308387454408e-06, "loss": 0.542, "step": 122010 }, { "epoch": 0.7253122195077008, "grad_norm": 5.175803184509277, "learning_rate": 9.938275889371426e-06, "loss": 0.5397, "step": 122020 }, { "epoch": 0.7253716615843692, "grad_norm": 4.236936569213867, "learning_rate": 9.938243382784143e-06, "loss": 0.5126, "step": 122030 }, { "epoch": 0.7254311036610375, "grad_norm": 5.995157241821289, "learning_rate": 9.938210867692618e-06, "loss": 0.624, "step": 122040 }, { "epoch": 0.7254905457377059, "grad_norm": 4.551569938659668, "learning_rate": 9.938178344096903e-06, "loss": 0.6053, "step": 122050 }, { "epoch": 0.7255499878143743, "grad_norm": 5.858679294586182, "learning_rate": 9.938145811997056e-06, "loss": 0.6225, "step": 122060 }, { "epoch": 0.7256094298910427, "grad_norm": 4.5006914138793945, "learning_rate": 9.938113271393134e-06, "loss": 0.5857, "step": 122070 }, { "epoch": 0.725668871967711, "grad_norm": 5.694699764251709, "learning_rate": 9.938080722285188e-06, "loss": 0.5653, "step": 122080 }, { "epoch": 0.7257283140443794, "grad_norm": 5.584743499755859, "learning_rate": 9.938048164673281e-06, "loss": 0.6415, "step": 122090 }, { "epoch": 0.7257877561210478, "grad_norm": 4.202884674072266, "learning_rate": 9.938015598557465e-06, "loss": 0.6343, "step": 122100 }, { "epoch": 0.7258471981977163, "grad_norm": 5.458786964416504, "learning_rate": 9.937983023937795e-06, "loss": 0.6005, "step": 122110 }, { "epoch": 0.7259066402743847, "grad_norm": 7.102841854095459, "learning_rate": 9.937950440814332e-06, "loss": 0.6386, "step": 122120 }, { "epoch": 0.725966082351053, "grad_norm": 6.006950378417969, "learning_rate": 9.937917849187128e-06, "loss": 0.6153, "step": 122130 }, { "epoch": 0.7260255244277214, "grad_norm": 6.08576774597168, "learning_rate": 9.93788524905624e-06, "loss": 0.6571, "step": 122140 }, { "epoch": 0.7260849665043898, "grad_norm": 5.227309703826904, "learning_rate": 9.937852640421727e-06, "loss": 0.584, "step": 122150 }, { "epoch": 0.7261444085810582, "grad_norm": 5.394858360290527, "learning_rate": 9.93782002328364e-06, "loss": 0.6096, "step": 122160 }, { "epoch": 0.7262038506577265, "grad_norm": 6.461264133453369, "learning_rate": 9.937787397642037e-06, "loss": 0.5729, "step": 122170 }, { "epoch": 0.7262632927343949, "grad_norm": 6.340538024902344, "learning_rate": 9.937754763496977e-06, "loss": 0.6558, "step": 122180 }, { "epoch": 0.7263227348110634, "grad_norm": 6.6481122970581055, "learning_rate": 9.937722120848515e-06, "loss": 0.6252, "step": 122190 }, { "epoch": 0.7263821768877318, "grad_norm": 5.554187297821045, "learning_rate": 9.937689469696703e-06, "loss": 0.6205, "step": 122200 }, { "epoch": 0.7264416189644002, "grad_norm": 5.919582366943359, "learning_rate": 9.937656810041603e-06, "loss": 0.5977, "step": 122210 }, { "epoch": 0.7265010610410685, "grad_norm": 4.16116189956665, "learning_rate": 9.937624141883267e-06, "loss": 0.5217, "step": 122220 }, { "epoch": 0.7265605031177369, "grad_norm": 5.168192386627197, "learning_rate": 9.937591465221753e-06, "loss": 0.568, "step": 122230 }, { "epoch": 0.7266199451944053, "grad_norm": 4.609928607940674, "learning_rate": 9.93755878005712e-06, "loss": 0.5666, "step": 122240 }, { "epoch": 0.7266793872710737, "grad_norm": 6.9529852867126465, "learning_rate": 9.937526086389421e-06, "loss": 0.5696, "step": 122250 }, { "epoch": 0.7267388293477421, "grad_norm": 4.981476783752441, "learning_rate": 9.937493384218712e-06, "loss": 0.6024, "step": 122260 }, { "epoch": 0.7267982714244104, "grad_norm": 3.9788825511932373, "learning_rate": 9.93746067354505e-06, "loss": 0.5971, "step": 122270 }, { "epoch": 0.7268577135010789, "grad_norm": 6.440140247344971, "learning_rate": 9.937427954368493e-06, "loss": 0.6477, "step": 122280 }, { "epoch": 0.7269171555777473, "grad_norm": 5.05930233001709, "learning_rate": 9.937395226689094e-06, "loss": 0.5932, "step": 122290 }, { "epoch": 0.7269765976544157, "grad_norm": 5.717249870300293, "learning_rate": 9.937362490506912e-06, "loss": 0.5274, "step": 122300 }, { "epoch": 0.727036039731084, "grad_norm": 6.199481010437012, "learning_rate": 9.937329745822002e-06, "loss": 0.5933, "step": 122310 }, { "epoch": 0.7270954818077524, "grad_norm": 6.018484115600586, "learning_rate": 9.937296992634422e-06, "loss": 0.6148, "step": 122320 }, { "epoch": 0.7271549238844208, "grad_norm": 5.369441032409668, "learning_rate": 9.937264230944228e-06, "loss": 0.563, "step": 122330 }, { "epoch": 0.7272143659610892, "grad_norm": 6.302911281585693, "learning_rate": 9.937231460751475e-06, "loss": 0.6431, "step": 122340 }, { "epoch": 0.7272738080377577, "grad_norm": 6.521419525146484, "learning_rate": 9.937198682056221e-06, "loss": 0.6054, "step": 122350 }, { "epoch": 0.727333250114426, "grad_norm": 5.2624430656433105, "learning_rate": 9.937165894858521e-06, "loss": 0.5113, "step": 122360 }, { "epoch": 0.7273926921910944, "grad_norm": 5.841209888458252, "learning_rate": 9.937133099158434e-06, "loss": 0.5461, "step": 122370 }, { "epoch": 0.7274521342677628, "grad_norm": 4.770752906799316, "learning_rate": 9.937100294956012e-06, "loss": 0.6092, "step": 122380 }, { "epoch": 0.7275115763444312, "grad_norm": 6.421264171600342, "learning_rate": 9.937067482251315e-06, "loss": 0.5562, "step": 122390 }, { "epoch": 0.7275710184210996, "grad_norm": 5.592643737792969, "learning_rate": 9.9370346610444e-06, "loss": 0.6026, "step": 122400 }, { "epoch": 0.7276304604977679, "grad_norm": 5.481582164764404, "learning_rate": 9.93700183133532e-06, "loss": 0.595, "step": 122410 }, { "epoch": 0.7276899025744363, "grad_norm": 6.9201178550720215, "learning_rate": 9.936968993124136e-06, "loss": 0.6014, "step": 122420 }, { "epoch": 0.7277493446511047, "grad_norm": 5.0792717933654785, "learning_rate": 9.936936146410903e-06, "loss": 0.6315, "step": 122430 }, { "epoch": 0.7278087867277732, "grad_norm": 6.168881416320801, "learning_rate": 9.936903291195675e-06, "loss": 0.5875, "step": 122440 }, { "epoch": 0.7278682288044415, "grad_norm": 5.517513751983643, "learning_rate": 9.936870427478512e-06, "loss": 0.5796, "step": 122450 }, { "epoch": 0.7279276708811099, "grad_norm": 5.951292514801025, "learning_rate": 9.936837555259466e-06, "loss": 0.5784, "step": 122460 }, { "epoch": 0.7279871129577783, "grad_norm": 6.090101718902588, "learning_rate": 9.9368046745386e-06, "loss": 0.554, "step": 122470 }, { "epoch": 0.7280465550344467, "grad_norm": 4.431838512420654, "learning_rate": 9.936771785315965e-06, "loss": 0.5876, "step": 122480 }, { "epoch": 0.7281059971111151, "grad_norm": 5.255745887756348, "learning_rate": 9.936738887591622e-06, "loss": 0.6387, "step": 122490 }, { "epoch": 0.7281654391877834, "grad_norm": 5.992136478424072, "learning_rate": 9.936705981365625e-06, "loss": 0.6055, "step": 122500 }, { "epoch": 0.7282248812644518, "grad_norm": 4.775704860687256, "learning_rate": 9.936673066638029e-06, "loss": 0.5863, "step": 122510 }, { "epoch": 0.7282843233411203, "grad_norm": 4.688058853149414, "learning_rate": 9.936640143408895e-06, "loss": 0.5897, "step": 122520 }, { "epoch": 0.7283437654177887, "grad_norm": 4.395565032958984, "learning_rate": 9.936607211678277e-06, "loss": 0.6526, "step": 122530 }, { "epoch": 0.728403207494457, "grad_norm": 5.55527400970459, "learning_rate": 9.936574271446232e-06, "loss": 0.6706, "step": 122540 }, { "epoch": 0.7284626495711254, "grad_norm": 6.689132213592529, "learning_rate": 9.936541322712818e-06, "loss": 0.6645, "step": 122550 }, { "epoch": 0.7285220916477938, "grad_norm": 5.1244096755981445, "learning_rate": 9.936508365478092e-06, "loss": 0.5785, "step": 122560 }, { "epoch": 0.7285815337244622, "grad_norm": 6.057937145233154, "learning_rate": 9.936475399742107e-06, "loss": 0.5733, "step": 122570 }, { "epoch": 0.7286409758011306, "grad_norm": 4.893211364746094, "learning_rate": 9.936442425504924e-06, "loss": 0.6326, "step": 122580 }, { "epoch": 0.7287004178777989, "grad_norm": 4.683748722076416, "learning_rate": 9.936409442766598e-06, "loss": 0.6137, "step": 122590 }, { "epoch": 0.7287598599544673, "grad_norm": 5.2702813148498535, "learning_rate": 9.936376451527185e-06, "loss": 0.619, "step": 122600 }, { "epoch": 0.7288193020311358, "grad_norm": 4.4926652908325195, "learning_rate": 9.936343451786745e-06, "loss": 0.5789, "step": 122610 }, { "epoch": 0.7288787441078042, "grad_norm": 5.496962547302246, "learning_rate": 9.936310443545329e-06, "loss": 0.55, "step": 122620 }, { "epoch": 0.7289381861844726, "grad_norm": 5.790345191955566, "learning_rate": 9.936277426803001e-06, "loss": 0.5897, "step": 122630 }, { "epoch": 0.7289976282611409, "grad_norm": 5.576432704925537, "learning_rate": 9.936244401559811e-06, "loss": 0.6063, "step": 122640 }, { "epoch": 0.7290570703378093, "grad_norm": 6.083622455596924, "learning_rate": 9.936211367815822e-06, "loss": 0.6609, "step": 122650 }, { "epoch": 0.7291165124144777, "grad_norm": 4.655603408813477, "learning_rate": 9.936178325571086e-06, "loss": 0.5561, "step": 122660 }, { "epoch": 0.7291759544911461, "grad_norm": 4.432088375091553, "learning_rate": 9.936145274825663e-06, "loss": 0.6079, "step": 122670 }, { "epoch": 0.7292353965678144, "grad_norm": 6.66403341293335, "learning_rate": 9.93611221557961e-06, "loss": 0.5681, "step": 122680 }, { "epoch": 0.7292948386444829, "grad_norm": 4.274041652679443, "learning_rate": 9.93607914783298e-06, "loss": 0.6438, "step": 122690 }, { "epoch": 0.7293542807211513, "grad_norm": 4.8115692138671875, "learning_rate": 9.936046071585834e-06, "loss": 0.5539, "step": 122700 }, { "epoch": 0.7294137227978197, "grad_norm": 4.307724952697754, "learning_rate": 9.936012986838228e-06, "loss": 0.5747, "step": 122710 }, { "epoch": 0.7294731648744881, "grad_norm": 6.092049598693848, "learning_rate": 9.93597989359022e-06, "loss": 0.5174, "step": 122720 }, { "epoch": 0.7295326069511564, "grad_norm": 4.612218856811523, "learning_rate": 9.935946791841864e-06, "loss": 0.5475, "step": 122730 }, { "epoch": 0.7295920490278248, "grad_norm": 5.37391471862793, "learning_rate": 9.93591368159322e-06, "loss": 0.5516, "step": 122740 }, { "epoch": 0.7296514911044932, "grad_norm": 6.5391340255737305, "learning_rate": 9.935880562844342e-06, "loss": 0.6504, "step": 122750 }, { "epoch": 0.7297109331811616, "grad_norm": 7.180395126342773, "learning_rate": 9.935847435595288e-06, "loss": 0.6208, "step": 122760 }, { "epoch": 0.7297703752578301, "grad_norm": 4.307478427886963, "learning_rate": 9.935814299846118e-06, "loss": 0.572, "step": 122770 }, { "epoch": 0.7298298173344984, "grad_norm": 4.989099025726318, "learning_rate": 9.935781155596886e-06, "loss": 0.5073, "step": 122780 }, { "epoch": 0.7298892594111668, "grad_norm": 4.671706676483154, "learning_rate": 9.935748002847649e-06, "loss": 0.5617, "step": 122790 }, { "epoch": 0.7299487014878352, "grad_norm": 4.357733726501465, "learning_rate": 9.935714841598467e-06, "loss": 0.561, "step": 122800 }, { "epoch": 0.7300081435645036, "grad_norm": 5.414099216461182, "learning_rate": 9.935681671849393e-06, "loss": 0.6449, "step": 122810 }, { "epoch": 0.7300675856411719, "grad_norm": 6.01871395111084, "learning_rate": 9.935648493600488e-06, "loss": 0.6171, "step": 122820 }, { "epoch": 0.7301270277178403, "grad_norm": 5.583134174346924, "learning_rate": 9.935615306851806e-06, "loss": 0.6504, "step": 122830 }, { "epoch": 0.7301864697945087, "grad_norm": 5.200270175933838, "learning_rate": 9.935582111603407e-06, "loss": 0.5929, "step": 122840 }, { "epoch": 0.7302459118711772, "grad_norm": 6.584720611572266, "learning_rate": 9.935548907855345e-06, "loss": 0.6343, "step": 122850 }, { "epoch": 0.7303053539478456, "grad_norm": 4.5713701248168945, "learning_rate": 9.93551569560768e-06, "loss": 0.5499, "step": 122860 }, { "epoch": 0.7303647960245139, "grad_norm": 6.349349498748779, "learning_rate": 9.93548247486047e-06, "loss": 0.5924, "step": 122870 }, { "epoch": 0.7304242381011823, "grad_norm": 3.8770759105682373, "learning_rate": 9.935449245613766e-06, "loss": 0.6037, "step": 122880 }, { "epoch": 0.7304836801778507, "grad_norm": 5.80454683303833, "learning_rate": 9.935416007867632e-06, "loss": 0.5919, "step": 122890 }, { "epoch": 0.7305431222545191, "grad_norm": 5.08671236038208, "learning_rate": 9.935382761622123e-06, "loss": 0.5408, "step": 122900 }, { "epoch": 0.7306025643311874, "grad_norm": 5.979892730712891, "learning_rate": 9.935349506877296e-06, "loss": 0.6609, "step": 122910 }, { "epoch": 0.7306620064078558, "grad_norm": 4.833609580993652, "learning_rate": 9.935316243633206e-06, "loss": 0.6138, "step": 122920 }, { "epoch": 0.7307214484845242, "grad_norm": 6.155007839202881, "learning_rate": 9.935282971889915e-06, "loss": 0.5955, "step": 122930 }, { "epoch": 0.7307808905611927, "grad_norm": 5.182412624359131, "learning_rate": 9.935249691647477e-06, "loss": 0.5376, "step": 122940 }, { "epoch": 0.7308403326378611, "grad_norm": 5.201549053192139, "learning_rate": 9.935216402905951e-06, "loss": 0.5442, "step": 122950 }, { "epoch": 0.7308997747145294, "grad_norm": 6.951038837432861, "learning_rate": 9.935183105665393e-06, "loss": 0.6491, "step": 122960 }, { "epoch": 0.7309592167911978, "grad_norm": 7.018446445465088, "learning_rate": 9.93514979992586e-06, "loss": 0.5981, "step": 122970 }, { "epoch": 0.7310186588678662, "grad_norm": 6.328890800476074, "learning_rate": 9.93511648568741e-06, "loss": 0.6151, "step": 122980 }, { "epoch": 0.7310781009445346, "grad_norm": 4.263268947601318, "learning_rate": 9.935083162950102e-06, "loss": 0.5982, "step": 122990 }, { "epoch": 0.731137543021203, "grad_norm": 4.840855121612549, "learning_rate": 9.935049831713992e-06, "loss": 0.6476, "step": 123000 }, { "epoch": 0.7311969850978713, "grad_norm": 5.500837802886963, "learning_rate": 9.935016491979136e-06, "loss": 0.5254, "step": 123010 }, { "epoch": 0.7312564271745398, "grad_norm": 4.976322174072266, "learning_rate": 9.934983143745593e-06, "loss": 0.5769, "step": 123020 }, { "epoch": 0.7313158692512082, "grad_norm": 7.66305685043335, "learning_rate": 9.934949787013422e-06, "loss": 0.6154, "step": 123030 }, { "epoch": 0.7313753113278766, "grad_norm": 5.572312831878662, "learning_rate": 9.934916421782676e-06, "loss": 0.5824, "step": 123040 }, { "epoch": 0.7314347534045449, "grad_norm": 6.019616603851318, "learning_rate": 9.934883048053416e-06, "loss": 0.5537, "step": 123050 }, { "epoch": 0.7314941954812133, "grad_norm": 6.84144401550293, "learning_rate": 9.9348496658257e-06, "loss": 0.5744, "step": 123060 }, { "epoch": 0.7315536375578817, "grad_norm": 6.110470771789551, "learning_rate": 9.934816275099583e-06, "loss": 0.5735, "step": 123070 }, { "epoch": 0.7316130796345501, "grad_norm": 5.212736129760742, "learning_rate": 9.934782875875123e-06, "loss": 0.5649, "step": 123080 }, { "epoch": 0.7316725217112185, "grad_norm": 4.859770774841309, "learning_rate": 9.934749468152378e-06, "loss": 0.5557, "step": 123090 }, { "epoch": 0.7317319637878869, "grad_norm": 6.127948760986328, "learning_rate": 9.934716051931407e-06, "loss": 0.6064, "step": 123100 }, { "epoch": 0.7317914058645553, "grad_norm": 5.245126247406006, "learning_rate": 9.934682627212265e-06, "loss": 0.5557, "step": 123110 }, { "epoch": 0.7318508479412237, "grad_norm": 6.069908618927002, "learning_rate": 9.934649193995011e-06, "loss": 0.5996, "step": 123120 }, { "epoch": 0.7319102900178921, "grad_norm": 4.926019191741943, "learning_rate": 9.934615752279704e-06, "loss": 0.6004, "step": 123130 }, { "epoch": 0.7319697320945605, "grad_norm": 6.661478519439697, "learning_rate": 9.934582302066398e-06, "loss": 0.5989, "step": 123140 }, { "epoch": 0.7320291741712288, "grad_norm": 4.8503522872924805, "learning_rate": 9.934548843355151e-06, "loss": 0.5189, "step": 123150 }, { "epoch": 0.7320886162478972, "grad_norm": 6.001729488372803, "learning_rate": 9.934515376146026e-06, "loss": 0.6115, "step": 123160 }, { "epoch": 0.7321480583245656, "grad_norm": 5.965721607208252, "learning_rate": 9.934481900439073e-06, "loss": 0.6645, "step": 123170 }, { "epoch": 0.7322075004012341, "grad_norm": 5.938693523406982, "learning_rate": 9.934448416234356e-06, "loss": 0.6161, "step": 123180 }, { "epoch": 0.7322669424779024, "grad_norm": 4.531064987182617, "learning_rate": 9.93441492353193e-06, "loss": 0.6096, "step": 123190 }, { "epoch": 0.7323263845545708, "grad_norm": 5.897034168243408, "learning_rate": 9.934381422331851e-06, "loss": 0.594, "step": 123200 }, { "epoch": 0.7323858266312392, "grad_norm": 5.2581377029418945, "learning_rate": 9.93434791263418e-06, "loss": 0.536, "step": 123210 }, { "epoch": 0.7324452687079076, "grad_norm": 5.454728126525879, "learning_rate": 9.934314394438972e-06, "loss": 0.5226, "step": 123220 }, { "epoch": 0.732504710784576, "grad_norm": 5.0261688232421875, "learning_rate": 9.934280867746285e-06, "loss": 0.679, "step": 123230 }, { "epoch": 0.7325641528612443, "grad_norm": 5.580170154571533, "learning_rate": 9.93424733255618e-06, "loss": 0.6364, "step": 123240 }, { "epoch": 0.7326235949379127, "grad_norm": 4.188467979431152, "learning_rate": 9.93421378886871e-06, "loss": 0.5721, "step": 123250 }, { "epoch": 0.7326830370145812, "grad_norm": 6.862946510314941, "learning_rate": 9.934180236683937e-06, "loss": 0.5439, "step": 123260 }, { "epoch": 0.7327424790912496, "grad_norm": 4.946316719055176, "learning_rate": 9.934146676001917e-06, "loss": 0.5673, "step": 123270 }, { "epoch": 0.7328019211679179, "grad_norm": 5.534757614135742, "learning_rate": 9.934113106822706e-06, "loss": 0.5845, "step": 123280 }, { "epoch": 0.7328613632445863, "grad_norm": 5.148434162139893, "learning_rate": 9.934079529146364e-06, "loss": 0.5932, "step": 123290 }, { "epoch": 0.7329208053212547, "grad_norm": 5.836190223693848, "learning_rate": 9.93404594297295e-06, "loss": 0.5411, "step": 123300 }, { "epoch": 0.7329802473979231, "grad_norm": 6.564736843109131, "learning_rate": 9.934012348302517e-06, "loss": 0.6025, "step": 123310 }, { "epoch": 0.7330396894745915, "grad_norm": 6.383846282958984, "learning_rate": 9.93397874513513e-06, "loss": 0.6143, "step": 123320 }, { "epoch": 0.7330991315512598, "grad_norm": 5.702801704406738, "learning_rate": 9.933945133470839e-06, "loss": 0.573, "step": 123330 }, { "epoch": 0.7331585736279282, "grad_norm": 6.561952590942383, "learning_rate": 9.933911513309708e-06, "loss": 0.5757, "step": 123340 }, { "epoch": 0.7332180157045967, "grad_norm": 5.782435894012451, "learning_rate": 9.933877884651793e-06, "loss": 0.5575, "step": 123350 }, { "epoch": 0.7332774577812651, "grad_norm": 5.3877034187316895, "learning_rate": 9.93384424749715e-06, "loss": 0.5887, "step": 123360 }, { "epoch": 0.7333368998579335, "grad_norm": 5.410846710205078, "learning_rate": 9.933810601845839e-06, "loss": 0.5864, "step": 123370 }, { "epoch": 0.7333963419346018, "grad_norm": 5.115307807922363, "learning_rate": 9.933776947697918e-06, "loss": 0.631, "step": 123380 }, { "epoch": 0.7334557840112702, "grad_norm": 5.836025714874268, "learning_rate": 9.933743285053445e-06, "loss": 0.5971, "step": 123390 }, { "epoch": 0.7335152260879386, "grad_norm": 6.563345909118652, "learning_rate": 9.933709613912476e-06, "loss": 0.5838, "step": 123400 }, { "epoch": 0.733574668164607, "grad_norm": 5.100523471832275, "learning_rate": 9.933675934275072e-06, "loss": 0.6282, "step": 123410 }, { "epoch": 0.7336341102412753, "grad_norm": 5.51095724105835, "learning_rate": 9.933642246141289e-06, "loss": 0.6496, "step": 123420 }, { "epoch": 0.7336935523179438, "grad_norm": 4.040805816650391, "learning_rate": 9.933608549511184e-06, "loss": 0.5602, "step": 123430 }, { "epoch": 0.7337529943946122, "grad_norm": 6.429738998413086, "learning_rate": 9.933574844384817e-06, "loss": 0.6232, "step": 123440 }, { "epoch": 0.7338124364712806, "grad_norm": 4.84857702255249, "learning_rate": 9.933541130762246e-06, "loss": 0.5709, "step": 123450 }, { "epoch": 0.733871878547949, "grad_norm": 5.968264102935791, "learning_rate": 9.933507408643527e-06, "loss": 0.6212, "step": 123460 }, { "epoch": 0.7339313206246173, "grad_norm": 6.592448711395264, "learning_rate": 9.93347367802872e-06, "loss": 0.5954, "step": 123470 }, { "epoch": 0.7339907627012857, "grad_norm": 5.444122314453125, "learning_rate": 9.933439938917884e-06, "loss": 0.6325, "step": 123480 }, { "epoch": 0.7340502047779541, "grad_norm": 5.470407962799072, "learning_rate": 9.933406191311075e-06, "loss": 0.5807, "step": 123490 }, { "epoch": 0.7341096468546225, "grad_norm": 5.392466068267822, "learning_rate": 9.933372435208353e-06, "loss": 0.5745, "step": 123500 }, { "epoch": 0.734169088931291, "grad_norm": 5.062298774719238, "learning_rate": 9.933338670609773e-06, "loss": 0.5728, "step": 123510 }, { "epoch": 0.7342285310079593, "grad_norm": 3.9597833156585693, "learning_rate": 9.933304897515397e-06, "loss": 0.623, "step": 123520 }, { "epoch": 0.7342879730846277, "grad_norm": 6.058506011962891, "learning_rate": 9.93327111592528e-06, "loss": 0.5737, "step": 123530 }, { "epoch": 0.7343474151612961, "grad_norm": 4.890567779541016, "learning_rate": 9.933237325839481e-06, "loss": 0.5696, "step": 123540 }, { "epoch": 0.7344068572379645, "grad_norm": 5.281702995300293, "learning_rate": 9.93320352725806e-06, "loss": 0.5625, "step": 123550 }, { "epoch": 0.7344662993146328, "grad_norm": 5.026179790496826, "learning_rate": 9.933169720181075e-06, "loss": 0.5856, "step": 123560 }, { "epoch": 0.7345257413913012, "grad_norm": 4.5799784660339355, "learning_rate": 9.933135904608583e-06, "loss": 0.5487, "step": 123570 }, { "epoch": 0.7345851834679696, "grad_norm": 5.163883686065674, "learning_rate": 9.93310208054064e-06, "loss": 0.5759, "step": 123580 }, { "epoch": 0.734644625544638, "grad_norm": 4.912829399108887, "learning_rate": 9.933068247977307e-06, "loss": 0.5493, "step": 123590 }, { "epoch": 0.7347040676213065, "grad_norm": 5.907691955566406, "learning_rate": 9.933034406918642e-06, "loss": 0.6196, "step": 123600 }, { "epoch": 0.7347635096979748, "grad_norm": 5.281006813049316, "learning_rate": 9.933000557364704e-06, "loss": 0.6045, "step": 123610 }, { "epoch": 0.7348229517746432, "grad_norm": 5.839773178100586, "learning_rate": 9.932966699315551e-06, "loss": 0.5613, "step": 123620 }, { "epoch": 0.7348823938513116, "grad_norm": 6.557152271270752, "learning_rate": 9.932932832771239e-06, "loss": 0.5874, "step": 123630 }, { "epoch": 0.73494183592798, "grad_norm": 7.374322891235352, "learning_rate": 9.93289895773183e-06, "loss": 0.6216, "step": 123640 }, { "epoch": 0.7350012780046483, "grad_norm": 5.908902645111084, "learning_rate": 9.93286507419738e-06, "loss": 0.6445, "step": 123650 }, { "epoch": 0.7350607200813167, "grad_norm": 4.68514347076416, "learning_rate": 9.932831182167946e-06, "loss": 0.5747, "step": 123660 }, { "epoch": 0.7351201621579851, "grad_norm": 5.028558731079102, "learning_rate": 9.932797281643589e-06, "loss": 0.5967, "step": 123670 }, { "epoch": 0.7351796042346536, "grad_norm": 5.532138347625732, "learning_rate": 9.932763372624367e-06, "loss": 0.5724, "step": 123680 }, { "epoch": 0.735239046311322, "grad_norm": 6.103938579559326, "learning_rate": 9.932729455110338e-06, "loss": 0.6218, "step": 123690 }, { "epoch": 0.7352984883879903, "grad_norm": 5.259481906890869, "learning_rate": 9.93269552910156e-06, "loss": 0.5998, "step": 123700 }, { "epoch": 0.7353579304646587, "grad_norm": 5.378479480743408, "learning_rate": 9.932661594598092e-06, "loss": 0.5799, "step": 123710 }, { "epoch": 0.7354173725413271, "grad_norm": 4.610556602478027, "learning_rate": 9.932627651599992e-06, "loss": 0.5863, "step": 123720 }, { "epoch": 0.7354768146179955, "grad_norm": 6.18565559387207, "learning_rate": 9.932593700107318e-06, "loss": 0.6867, "step": 123730 }, { "epoch": 0.7355362566946639, "grad_norm": 4.824469089508057, "learning_rate": 9.93255974012013e-06, "loss": 0.6552, "step": 123740 }, { "epoch": 0.7355956987713322, "grad_norm": 5.625382423400879, "learning_rate": 9.932525771638486e-06, "loss": 0.5748, "step": 123750 }, { "epoch": 0.7356551408480007, "grad_norm": 6.2145256996154785, "learning_rate": 9.932491794662442e-06, "loss": 0.5852, "step": 123760 }, { "epoch": 0.7357145829246691, "grad_norm": 5.845094680786133, "learning_rate": 9.932457809192061e-06, "loss": 0.5773, "step": 123770 }, { "epoch": 0.7357740250013375, "grad_norm": 6.349800109863281, "learning_rate": 9.932423815227398e-06, "loss": 0.603, "step": 123780 }, { "epoch": 0.7358334670780058, "grad_norm": 5.321209907531738, "learning_rate": 9.932389812768513e-06, "loss": 0.5716, "step": 123790 }, { "epoch": 0.7358929091546742, "grad_norm": 5.673820495605469, "learning_rate": 9.932355801815462e-06, "loss": 0.5898, "step": 123800 }, { "epoch": 0.7359523512313426, "grad_norm": 6.002816677093506, "learning_rate": 9.93232178236831e-06, "loss": 0.5844, "step": 123810 }, { "epoch": 0.736011793308011, "grad_norm": 7.498780727386475, "learning_rate": 9.932287754427109e-06, "loss": 0.6279, "step": 123820 }, { "epoch": 0.7360712353846794, "grad_norm": 5.62369966506958, "learning_rate": 9.932253717991919e-06, "loss": 0.5933, "step": 123830 }, { "epoch": 0.7361306774613477, "grad_norm": 5.061366558074951, "learning_rate": 9.932219673062802e-06, "loss": 0.5461, "step": 123840 }, { "epoch": 0.7361901195380162, "grad_norm": 5.5278706550598145, "learning_rate": 9.932185619639812e-06, "loss": 0.573, "step": 123850 }, { "epoch": 0.7362495616146846, "grad_norm": 4.962532043457031, "learning_rate": 9.93215155772301e-06, "loss": 0.6026, "step": 123860 }, { "epoch": 0.736309003691353, "grad_norm": 6.60775899887085, "learning_rate": 9.932117487312457e-06, "loss": 0.6546, "step": 123870 }, { "epoch": 0.7363684457680214, "grad_norm": 5.5189104080200195, "learning_rate": 9.932083408408206e-06, "loss": 0.6243, "step": 123880 }, { "epoch": 0.7364278878446897, "grad_norm": 5.871453762054443, "learning_rate": 9.932049321010322e-06, "loss": 0.5594, "step": 123890 }, { "epoch": 0.7364873299213581, "grad_norm": 4.599820613861084, "learning_rate": 9.932015225118859e-06, "loss": 0.551, "step": 123900 }, { "epoch": 0.7365467719980265, "grad_norm": 5.308798789978027, "learning_rate": 9.931981120733876e-06, "loss": 0.5915, "step": 123910 }, { "epoch": 0.736606214074695, "grad_norm": 4.541236877441406, "learning_rate": 9.931947007855435e-06, "loss": 0.5833, "step": 123920 }, { "epoch": 0.7366656561513633, "grad_norm": 5.666430950164795, "learning_rate": 9.931912886483592e-06, "loss": 0.5404, "step": 123930 }, { "epoch": 0.7367250982280317, "grad_norm": 5.4770588874816895, "learning_rate": 9.931878756618408e-06, "loss": 0.6247, "step": 123940 }, { "epoch": 0.7367845403047001, "grad_norm": 4.205284595489502, "learning_rate": 9.931844618259939e-06, "loss": 0.5411, "step": 123950 }, { "epoch": 0.7368439823813685, "grad_norm": 5.28166389465332, "learning_rate": 9.931810471408243e-06, "loss": 0.5654, "step": 123960 }, { "epoch": 0.7369034244580369, "grad_norm": 5.705763339996338, "learning_rate": 9.931776316063385e-06, "loss": 0.5958, "step": 123970 }, { "epoch": 0.7369628665347052, "grad_norm": 5.978829860687256, "learning_rate": 9.931742152225417e-06, "loss": 0.6308, "step": 123980 }, { "epoch": 0.7370223086113736, "grad_norm": 5.439725875854492, "learning_rate": 9.931707979894401e-06, "loss": 0.566, "step": 123990 }, { "epoch": 0.737081750688042, "grad_norm": 4.949009418487549, "learning_rate": 9.931673799070396e-06, "loss": 0.5723, "step": 124000 }, { "epoch": 0.7371411927647105, "grad_norm": 4.616329669952393, "learning_rate": 9.93163960975346e-06, "loss": 0.5936, "step": 124010 }, { "epoch": 0.7372006348413788, "grad_norm": 7.216563701629639, "learning_rate": 9.931605411943652e-06, "loss": 0.6443, "step": 124020 }, { "epoch": 0.7372600769180472, "grad_norm": 5.149827480316162, "learning_rate": 9.931571205641032e-06, "loss": 0.5468, "step": 124030 }, { "epoch": 0.7373195189947156, "grad_norm": 6.622114181518555, "learning_rate": 9.931536990845657e-06, "loss": 0.6037, "step": 124040 }, { "epoch": 0.737378961071384, "grad_norm": 4.434114933013916, "learning_rate": 9.931502767557586e-06, "loss": 0.5653, "step": 124050 }, { "epoch": 0.7374384031480524, "grad_norm": 5.600687503814697, "learning_rate": 9.93146853577688e-06, "loss": 0.5876, "step": 124060 }, { "epoch": 0.7374978452247207, "grad_norm": 8.215641021728516, "learning_rate": 9.931434295503597e-06, "loss": 0.6525, "step": 124070 }, { "epoch": 0.7375572873013891, "grad_norm": 5.707557201385498, "learning_rate": 9.931400046737795e-06, "loss": 0.5477, "step": 124080 }, { "epoch": 0.7376167293780576, "grad_norm": 4.784551620483398, "learning_rate": 9.931365789479534e-06, "loss": 0.5978, "step": 124090 }, { "epoch": 0.737676171454726, "grad_norm": 8.44273567199707, "learning_rate": 9.931331523728873e-06, "loss": 0.5761, "step": 124100 }, { "epoch": 0.7377356135313944, "grad_norm": 3.839367389678955, "learning_rate": 9.93129724948587e-06, "loss": 0.5969, "step": 124110 }, { "epoch": 0.7377950556080627, "grad_norm": 4.958954334259033, "learning_rate": 9.931262966750585e-06, "loss": 0.6127, "step": 124120 }, { "epoch": 0.7378544976847311, "grad_norm": 6.063644886016846, "learning_rate": 9.931228675523077e-06, "loss": 0.6115, "step": 124130 }, { "epoch": 0.7379139397613995, "grad_norm": 5.903787612915039, "learning_rate": 9.931194375803405e-06, "loss": 0.6047, "step": 124140 }, { "epoch": 0.7379733818380679, "grad_norm": 5.572918891906738, "learning_rate": 9.931160067591628e-06, "loss": 0.5984, "step": 124150 }, { "epoch": 0.7380328239147362, "grad_norm": 6.952361106872559, "learning_rate": 9.931125750887805e-06, "loss": 0.5465, "step": 124160 }, { "epoch": 0.7380922659914047, "grad_norm": 6.049593448638916, "learning_rate": 9.931091425691994e-06, "loss": 0.5973, "step": 124170 }, { "epoch": 0.7381517080680731, "grad_norm": 4.6387939453125, "learning_rate": 9.931057092004257e-06, "loss": 0.6078, "step": 124180 }, { "epoch": 0.7382111501447415, "grad_norm": 5.139676094055176, "learning_rate": 9.93102274982465e-06, "loss": 0.5612, "step": 124190 }, { "epoch": 0.7382705922214099, "grad_norm": 4.359354019165039, "learning_rate": 9.930988399153234e-06, "loss": 0.574, "step": 124200 }, { "epoch": 0.7383300342980782, "grad_norm": 6.544614315032959, "learning_rate": 9.930954039990066e-06, "loss": 0.6003, "step": 124210 }, { "epoch": 0.7383894763747466, "grad_norm": 4.571346759796143, "learning_rate": 9.93091967233521e-06, "loss": 0.5634, "step": 124220 }, { "epoch": 0.738448918451415, "grad_norm": 5.0542378425598145, "learning_rate": 9.93088529618872e-06, "loss": 0.5861, "step": 124230 }, { "epoch": 0.7385083605280834, "grad_norm": 5.4979095458984375, "learning_rate": 9.930850911550657e-06, "loss": 0.6034, "step": 124240 }, { "epoch": 0.7385678026047517, "grad_norm": 6.202853679656982, "learning_rate": 9.930816518421081e-06, "loss": 0.6323, "step": 124250 }, { "epoch": 0.7386272446814202, "grad_norm": 5.044500827789307, "learning_rate": 9.93078211680005e-06, "loss": 0.561, "step": 124260 }, { "epoch": 0.7386866867580886, "grad_norm": 5.083564758300781, "learning_rate": 9.930747706687624e-06, "loss": 0.6017, "step": 124270 }, { "epoch": 0.738746128834757, "grad_norm": 5.366347789764404, "learning_rate": 9.930713288083863e-06, "loss": 0.5055, "step": 124280 }, { "epoch": 0.7388055709114254, "grad_norm": 5.917933940887451, "learning_rate": 9.930678860988824e-06, "loss": 0.6349, "step": 124290 }, { "epoch": 0.7388650129880937, "grad_norm": 4.59070348739624, "learning_rate": 9.930644425402568e-06, "loss": 0.5774, "step": 124300 }, { "epoch": 0.7389244550647621, "grad_norm": 6.011617660522461, "learning_rate": 9.930609981325156e-06, "loss": 0.5522, "step": 124310 }, { "epoch": 0.7389838971414305, "grad_norm": 6.465473175048828, "learning_rate": 9.930575528756642e-06, "loss": 0.6238, "step": 124320 }, { "epoch": 0.739043339218099, "grad_norm": 7.464424133300781, "learning_rate": 9.930541067697092e-06, "loss": 0.6302, "step": 124330 }, { "epoch": 0.7391027812947674, "grad_norm": 7.224989414215088, "learning_rate": 9.930506598146562e-06, "loss": 0.6026, "step": 124340 }, { "epoch": 0.7391622233714357, "grad_norm": 6.03540563583374, "learning_rate": 9.930472120105107e-06, "loss": 0.5782, "step": 124350 }, { "epoch": 0.7392216654481041, "grad_norm": 4.460999965667725, "learning_rate": 9.930437633572794e-06, "loss": 0.608, "step": 124360 }, { "epoch": 0.7392811075247725, "grad_norm": 4.425499439239502, "learning_rate": 9.93040313854968e-06, "loss": 0.575, "step": 124370 }, { "epoch": 0.7393405496014409, "grad_norm": 4.115947723388672, "learning_rate": 9.930368635035822e-06, "loss": 0.5607, "step": 124380 }, { "epoch": 0.7393999916781092, "grad_norm": 4.44147253036499, "learning_rate": 9.93033412303128e-06, "loss": 0.5809, "step": 124390 }, { "epoch": 0.7394594337547776, "grad_norm": 7.562868118286133, "learning_rate": 9.930299602536116e-06, "loss": 0.5976, "step": 124400 }, { "epoch": 0.739518875831446, "grad_norm": 4.061300277709961, "learning_rate": 9.930265073550386e-06, "loss": 0.5307, "step": 124410 }, { "epoch": 0.7395783179081145, "grad_norm": 4.21248197555542, "learning_rate": 9.930230536074153e-06, "loss": 0.5693, "step": 124420 }, { "epoch": 0.7396377599847829, "grad_norm": 5.113915920257568, "learning_rate": 9.930195990107474e-06, "loss": 0.6314, "step": 124430 }, { "epoch": 0.7396972020614512, "grad_norm": 4.702304840087891, "learning_rate": 9.930161435650409e-06, "loss": 0.5859, "step": 124440 }, { "epoch": 0.7397566441381196, "grad_norm": 4.675283432006836, "learning_rate": 9.930126872703019e-06, "loss": 0.6294, "step": 124450 }, { "epoch": 0.739816086214788, "grad_norm": 7.515303611755371, "learning_rate": 9.930092301265362e-06, "loss": 0.6428, "step": 124460 }, { "epoch": 0.7398755282914564, "grad_norm": 4.564538478851318, "learning_rate": 9.930057721337495e-06, "loss": 0.6011, "step": 124470 }, { "epoch": 0.7399349703681248, "grad_norm": 4.7431817054748535, "learning_rate": 9.930023132919484e-06, "loss": 0.5806, "step": 124480 }, { "epoch": 0.7399944124447931, "grad_norm": 6.6937336921691895, "learning_rate": 9.929988536011384e-06, "loss": 0.5713, "step": 124490 }, { "epoch": 0.7400538545214616, "grad_norm": 4.144561767578125, "learning_rate": 9.929953930613254e-06, "loss": 0.5856, "step": 124500 }, { "epoch": 0.74011329659813, "grad_norm": 7.121674537658691, "learning_rate": 9.929919316725157e-06, "loss": 0.567, "step": 124510 }, { "epoch": 0.7401727386747984, "grad_norm": 6.424840927124023, "learning_rate": 9.92988469434715e-06, "loss": 0.6329, "step": 124520 }, { "epoch": 0.7402321807514667, "grad_norm": 6.453451156616211, "learning_rate": 9.929850063479291e-06, "loss": 0.5907, "step": 124530 }, { "epoch": 0.7402916228281351, "grad_norm": 6.425178527832031, "learning_rate": 9.929815424121645e-06, "loss": 0.6317, "step": 124540 }, { "epoch": 0.7403510649048035, "grad_norm": 4.557557106018066, "learning_rate": 9.929780776274267e-06, "loss": 0.6178, "step": 124550 }, { "epoch": 0.7404105069814719, "grad_norm": 4.382744789123535, "learning_rate": 9.929746119937221e-06, "loss": 0.5748, "step": 124560 }, { "epoch": 0.7404699490581403, "grad_norm": 4.134012699127197, "learning_rate": 9.929711455110561e-06, "loss": 0.5641, "step": 124570 }, { "epoch": 0.7405293911348086, "grad_norm": 5.740563869476318, "learning_rate": 9.929676781794351e-06, "loss": 0.6574, "step": 124580 }, { "epoch": 0.7405888332114771, "grad_norm": 6.018849849700928, "learning_rate": 9.929642099988649e-06, "loss": 0.6147, "step": 124590 }, { "epoch": 0.7406482752881455, "grad_norm": 5.902477741241455, "learning_rate": 9.929607409693516e-06, "loss": 0.5343, "step": 124600 }, { "epoch": 0.7407077173648139, "grad_norm": 5.572268009185791, "learning_rate": 9.92957271090901e-06, "loss": 0.5666, "step": 124610 }, { "epoch": 0.7407671594414822, "grad_norm": 4.497888088226318, "learning_rate": 9.92953800363519e-06, "loss": 0.5371, "step": 124620 }, { "epoch": 0.7408266015181506, "grad_norm": 4.288162708282471, "learning_rate": 9.92950328787212e-06, "loss": 0.5503, "step": 124630 }, { "epoch": 0.740886043594819, "grad_norm": 5.85766077041626, "learning_rate": 9.929468563619856e-06, "loss": 0.6345, "step": 124640 }, { "epoch": 0.7409454856714874, "grad_norm": 6.638078689575195, "learning_rate": 9.929433830878459e-06, "loss": 0.6543, "step": 124650 }, { "epoch": 0.7410049277481559, "grad_norm": 4.781486511230469, "learning_rate": 9.92939908964799e-06, "loss": 0.5828, "step": 124660 }, { "epoch": 0.7410643698248242, "grad_norm": 7.783756732940674, "learning_rate": 9.929364339928506e-06, "loss": 0.6392, "step": 124670 }, { "epoch": 0.7411238119014926, "grad_norm": 4.915807723999023, "learning_rate": 9.929329581720069e-06, "loss": 0.5548, "step": 124680 }, { "epoch": 0.741183253978161, "grad_norm": 6.298892498016357, "learning_rate": 9.929294815022737e-06, "loss": 0.6115, "step": 124690 }, { "epoch": 0.7412426960548294, "grad_norm": 6.057033538818359, "learning_rate": 9.929260039836572e-06, "loss": 0.5918, "step": 124700 }, { "epoch": 0.7413021381314978, "grad_norm": 5.403359413146973, "learning_rate": 9.929225256161635e-06, "loss": 0.5432, "step": 124710 }, { "epoch": 0.7413615802081661, "grad_norm": 5.5514140129089355, "learning_rate": 9.929190463997981e-06, "loss": 0.6063, "step": 124720 }, { "epoch": 0.7414210222848345, "grad_norm": 4.547759056091309, "learning_rate": 9.929155663345675e-06, "loss": 0.6383, "step": 124730 }, { "epoch": 0.7414804643615029, "grad_norm": 5.983952045440674, "learning_rate": 9.929120854204774e-06, "loss": 0.6343, "step": 124740 }, { "epoch": 0.7415399064381714, "grad_norm": 6.124752521514893, "learning_rate": 9.92908603657534e-06, "loss": 0.6133, "step": 124750 }, { "epoch": 0.7415993485148397, "grad_norm": 5.37155294418335, "learning_rate": 9.92905121045743e-06, "loss": 0.6434, "step": 124760 }, { "epoch": 0.7416587905915081, "grad_norm": 5.064988613128662, "learning_rate": 9.929016375851105e-06, "loss": 0.6038, "step": 124770 }, { "epoch": 0.7417182326681765, "grad_norm": 5.688252925872803, "learning_rate": 9.928981532756428e-06, "loss": 0.5793, "step": 124780 }, { "epoch": 0.7417776747448449, "grad_norm": 5.375814437866211, "learning_rate": 9.928946681173456e-06, "loss": 0.607, "step": 124790 }, { "epoch": 0.7418371168215133, "grad_norm": 5.971941947937012, "learning_rate": 9.928911821102249e-06, "loss": 0.5817, "step": 124800 }, { "epoch": 0.7418965588981816, "grad_norm": 6.131629943847656, "learning_rate": 9.928876952542868e-06, "loss": 0.5907, "step": 124810 }, { "epoch": 0.74195600097485, "grad_norm": 5.410150527954102, "learning_rate": 9.928842075495373e-06, "loss": 0.6345, "step": 124820 }, { "epoch": 0.7420154430515185, "grad_norm": 5.384705543518066, "learning_rate": 9.928807189959823e-06, "loss": 0.5551, "step": 124830 }, { "epoch": 0.7420748851281869, "grad_norm": 5.26861572265625, "learning_rate": 9.92877229593628e-06, "loss": 0.6101, "step": 124840 }, { "epoch": 0.7421343272048553, "grad_norm": 6.379942417144775, "learning_rate": 9.928737393424803e-06, "loss": 0.5187, "step": 124850 }, { "epoch": 0.7421937692815236, "grad_norm": 5.164498805999756, "learning_rate": 9.928702482425453e-06, "loss": 0.6639, "step": 124860 }, { "epoch": 0.742253211358192, "grad_norm": 5.471946716308594, "learning_rate": 9.928667562938288e-06, "loss": 0.6213, "step": 124870 }, { "epoch": 0.7423126534348604, "grad_norm": 6.529283046722412, "learning_rate": 9.92863263496337e-06, "loss": 0.6032, "step": 124880 }, { "epoch": 0.7423720955115288, "grad_norm": 5.060291767120361, "learning_rate": 9.928597698500757e-06, "loss": 0.586, "step": 124890 }, { "epoch": 0.7424315375881971, "grad_norm": 6.1665215492248535, "learning_rate": 9.928562753550511e-06, "loss": 0.6042, "step": 124900 }, { "epoch": 0.7424909796648655, "grad_norm": 7.168229579925537, "learning_rate": 9.928527800112693e-06, "loss": 0.6747, "step": 124910 }, { "epoch": 0.742550421741534, "grad_norm": 5.450458526611328, "learning_rate": 9.928492838187362e-06, "loss": 0.5847, "step": 124920 }, { "epoch": 0.7426098638182024, "grad_norm": 4.643941879272461, "learning_rate": 9.928457867774577e-06, "loss": 0.6191, "step": 124930 }, { "epoch": 0.7426693058948708, "grad_norm": 6.045415878295898, "learning_rate": 9.928422888874401e-06, "loss": 0.5976, "step": 124940 }, { "epoch": 0.7427287479715391, "grad_norm": 5.573117733001709, "learning_rate": 9.92838790148689e-06, "loss": 0.5864, "step": 124950 }, { "epoch": 0.7427881900482075, "grad_norm": 4.8228302001953125, "learning_rate": 9.928352905612111e-06, "loss": 0.6434, "step": 124960 }, { "epoch": 0.7428476321248759, "grad_norm": 6.250340461730957, "learning_rate": 9.928317901250118e-06, "loss": 0.6013, "step": 124970 }, { "epoch": 0.7429070742015443, "grad_norm": 5.395069122314453, "learning_rate": 9.928282888400973e-06, "loss": 0.6085, "step": 124980 }, { "epoch": 0.7429665162782126, "grad_norm": 5.025514125823975, "learning_rate": 9.928247867064739e-06, "loss": 0.5748, "step": 124990 }, { "epoch": 0.743025958354881, "grad_norm": 5.282172203063965, "learning_rate": 9.928212837241472e-06, "loss": 0.5943, "step": 125000 }, { "epoch": 0.7430854004315495, "grad_norm": 5.678548336029053, "learning_rate": 9.928177798931235e-06, "loss": 0.5269, "step": 125010 }, { "epoch": 0.7431448425082179, "grad_norm": 5.11516809463501, "learning_rate": 9.928142752134089e-06, "loss": 0.6031, "step": 125020 }, { "epoch": 0.7432042845848863, "grad_norm": 5.635387897491455, "learning_rate": 9.928107696850092e-06, "loss": 0.5625, "step": 125030 }, { "epoch": 0.7432637266615546, "grad_norm": 5.2536773681640625, "learning_rate": 9.928072633079307e-06, "loss": 0.5797, "step": 125040 }, { "epoch": 0.743323168738223, "grad_norm": 6.091724395751953, "learning_rate": 9.92803756082179e-06, "loss": 0.5538, "step": 125050 }, { "epoch": 0.7433826108148914, "grad_norm": 5.659095764160156, "learning_rate": 9.928002480077606e-06, "loss": 0.5698, "step": 125060 }, { "epoch": 0.7434420528915598, "grad_norm": 6.425268650054932, "learning_rate": 9.927967390846815e-06, "loss": 0.5874, "step": 125070 }, { "epoch": 0.7435014949682283, "grad_norm": 4.559959411621094, "learning_rate": 9.927932293129474e-06, "loss": 0.604, "step": 125080 }, { "epoch": 0.7435609370448966, "grad_norm": 5.838688850402832, "learning_rate": 9.927897186925647e-06, "loss": 0.5878, "step": 125090 }, { "epoch": 0.743620379121565, "grad_norm": 7.533369541168213, "learning_rate": 9.927862072235393e-06, "loss": 0.6167, "step": 125100 }, { "epoch": 0.7436798211982334, "grad_norm": 6.866273403167725, "learning_rate": 9.927826949058772e-06, "loss": 0.6127, "step": 125110 }, { "epoch": 0.7437392632749018, "grad_norm": 5.9218339920043945, "learning_rate": 9.927791817395844e-06, "loss": 0.5993, "step": 125120 }, { "epoch": 0.7437987053515701, "grad_norm": 4.416904926300049, "learning_rate": 9.927756677246672e-06, "loss": 0.5463, "step": 125130 }, { "epoch": 0.7438581474282385, "grad_norm": 4.999172687530518, "learning_rate": 9.927721528611315e-06, "loss": 0.5705, "step": 125140 }, { "epoch": 0.7439175895049069, "grad_norm": 4.758988380432129, "learning_rate": 9.927686371489833e-06, "loss": 0.5931, "step": 125150 }, { "epoch": 0.7439770315815754, "grad_norm": 6.7913899421691895, "learning_rate": 9.927651205882287e-06, "loss": 0.5618, "step": 125160 }, { "epoch": 0.7440364736582438, "grad_norm": 5.501103401184082, "learning_rate": 9.927616031788738e-06, "loss": 0.5916, "step": 125170 }, { "epoch": 0.7440959157349121, "grad_norm": 5.1726226806640625, "learning_rate": 9.927580849209246e-06, "loss": 0.6209, "step": 125180 }, { "epoch": 0.7441553578115805, "grad_norm": 6.456695079803467, "learning_rate": 9.927545658143874e-06, "loss": 0.6327, "step": 125190 }, { "epoch": 0.7442147998882489, "grad_norm": 5.914093494415283, "learning_rate": 9.927510458592677e-06, "loss": 0.5714, "step": 125200 }, { "epoch": 0.7442742419649173, "grad_norm": 6.696132183074951, "learning_rate": 9.92747525055572e-06, "loss": 0.5895, "step": 125210 }, { "epoch": 0.7443336840415857, "grad_norm": 4.847030162811279, "learning_rate": 9.927440034033064e-06, "loss": 0.5718, "step": 125220 }, { "epoch": 0.744393126118254, "grad_norm": 5.6949782371521, "learning_rate": 9.927404809024768e-06, "loss": 0.5681, "step": 125230 }, { "epoch": 0.7444525681949224, "grad_norm": 4.925583362579346, "learning_rate": 9.927369575530893e-06, "loss": 0.6626, "step": 125240 }, { "epoch": 0.7445120102715909, "grad_norm": 6.1694560050964355, "learning_rate": 9.927334333551499e-06, "loss": 0.6388, "step": 125250 }, { "epoch": 0.7445714523482593, "grad_norm": 5.842013835906982, "learning_rate": 9.927299083086647e-06, "loss": 0.5448, "step": 125260 }, { "epoch": 0.7446308944249276, "grad_norm": 7.742687702178955, "learning_rate": 9.9272638241364e-06, "loss": 0.6955, "step": 125270 }, { "epoch": 0.744690336501596, "grad_norm": 5.367014408111572, "learning_rate": 9.927228556700814e-06, "loss": 0.5572, "step": 125280 }, { "epoch": 0.7447497785782644, "grad_norm": 5.27766227722168, "learning_rate": 9.927193280779954e-06, "loss": 0.6252, "step": 125290 }, { "epoch": 0.7448092206549328, "grad_norm": 6.089711666107178, "learning_rate": 9.92715799637388e-06, "loss": 0.5706, "step": 125300 }, { "epoch": 0.7448686627316012, "grad_norm": 4.674880504608154, "learning_rate": 9.92712270348265e-06, "loss": 0.5818, "step": 125310 }, { "epoch": 0.7449281048082695, "grad_norm": 5.8600592613220215, "learning_rate": 9.92708740210633e-06, "loss": 0.6219, "step": 125320 }, { "epoch": 0.744987546884938, "grad_norm": 4.404027462005615, "learning_rate": 9.927052092244973e-06, "loss": 0.4872, "step": 125330 }, { "epoch": 0.7450469889616064, "grad_norm": 6.026607513427734, "learning_rate": 9.927016773898647e-06, "loss": 0.564, "step": 125340 }, { "epoch": 0.7451064310382748, "grad_norm": 6.272491455078125, "learning_rate": 9.926981447067411e-06, "loss": 0.6144, "step": 125350 }, { "epoch": 0.7451658731149431, "grad_norm": 3.9448184967041016, "learning_rate": 9.926946111751326e-06, "loss": 0.5384, "step": 125360 }, { "epoch": 0.7452253151916115, "grad_norm": 6.304316520690918, "learning_rate": 9.92691076795045e-06, "loss": 0.5645, "step": 125370 }, { "epoch": 0.7452847572682799, "grad_norm": 4.240718364715576, "learning_rate": 9.926875415664846e-06, "loss": 0.5755, "step": 125380 }, { "epoch": 0.7453441993449483, "grad_norm": 4.799270153045654, "learning_rate": 9.926840054894575e-06, "loss": 0.5938, "step": 125390 }, { "epoch": 0.7454036414216167, "grad_norm": 6.276944160461426, "learning_rate": 9.926804685639697e-06, "loss": 0.6188, "step": 125400 }, { "epoch": 0.745463083498285, "grad_norm": 6.894591331481934, "learning_rate": 9.926769307900274e-06, "loss": 0.6225, "step": 125410 }, { "epoch": 0.7455225255749535, "grad_norm": 5.166548728942871, "learning_rate": 9.926733921676365e-06, "loss": 0.6092, "step": 125420 }, { "epoch": 0.7455819676516219, "grad_norm": 5.320168495178223, "learning_rate": 9.926698526968035e-06, "loss": 0.6335, "step": 125430 }, { "epoch": 0.7456414097282903, "grad_norm": 4.9949774742126465, "learning_rate": 9.92666312377534e-06, "loss": 0.5732, "step": 125440 }, { "epoch": 0.7457008518049587, "grad_norm": 5.24801778793335, "learning_rate": 9.926627712098345e-06, "loss": 0.5866, "step": 125450 }, { "epoch": 0.745760293881627, "grad_norm": 4.5945820808410645, "learning_rate": 9.926592291937107e-06, "loss": 0.6269, "step": 125460 }, { "epoch": 0.7458197359582954, "grad_norm": 5.347451210021973, "learning_rate": 9.926556863291691e-06, "loss": 0.5801, "step": 125470 }, { "epoch": 0.7458791780349638, "grad_norm": 3.4367666244506836, "learning_rate": 9.926521426162155e-06, "loss": 0.5598, "step": 125480 }, { "epoch": 0.7459386201116323, "grad_norm": 5.267631530761719, "learning_rate": 9.926485980548563e-06, "loss": 0.6322, "step": 125490 }, { "epoch": 0.7459980621883006, "grad_norm": 4.300849437713623, "learning_rate": 9.926450526450974e-06, "loss": 0.6215, "step": 125500 }, { "epoch": 0.746057504264969, "grad_norm": 5.916428089141846, "learning_rate": 9.926415063869448e-06, "loss": 0.604, "step": 125510 }, { "epoch": 0.7461169463416374, "grad_norm": 6.7592902183532715, "learning_rate": 9.926379592804048e-06, "loss": 0.6604, "step": 125520 }, { "epoch": 0.7461763884183058, "grad_norm": 6.994091987609863, "learning_rate": 9.926344113254836e-06, "loss": 0.6382, "step": 125530 }, { "epoch": 0.7462358304949742, "grad_norm": 4.636123180389404, "learning_rate": 9.92630862522187e-06, "loss": 0.634, "step": 125540 }, { "epoch": 0.7462952725716425, "grad_norm": 4.8302693367004395, "learning_rate": 9.926273128705213e-06, "loss": 0.5824, "step": 125550 }, { "epoch": 0.7463547146483109, "grad_norm": 4.245323181152344, "learning_rate": 9.926237623704926e-06, "loss": 0.5377, "step": 125560 }, { "epoch": 0.7464141567249793, "grad_norm": 6.685159683227539, "learning_rate": 9.92620211022107e-06, "loss": 0.574, "step": 125570 }, { "epoch": 0.7464735988016478, "grad_norm": 5.222741603851318, "learning_rate": 9.926166588253706e-06, "loss": 0.5742, "step": 125580 }, { "epoch": 0.7465330408783162, "grad_norm": 6.13270902633667, "learning_rate": 9.926131057802895e-06, "loss": 0.6197, "step": 125590 }, { "epoch": 0.7465924829549845, "grad_norm": 5.36391019821167, "learning_rate": 9.9260955188687e-06, "loss": 0.5573, "step": 125600 }, { "epoch": 0.7466519250316529, "grad_norm": 5.473021507263184, "learning_rate": 9.92605997145118e-06, "loss": 0.5994, "step": 125610 }, { "epoch": 0.7467113671083213, "grad_norm": 4.983264923095703, "learning_rate": 9.926024415550397e-06, "loss": 0.6364, "step": 125620 }, { "epoch": 0.7467708091849897, "grad_norm": 7.1736016273498535, "learning_rate": 9.925988851166412e-06, "loss": 0.6707, "step": 125630 }, { "epoch": 0.746830251261658, "grad_norm": 6.0144219398498535, "learning_rate": 9.925953278299286e-06, "loss": 0.5595, "step": 125640 }, { "epoch": 0.7468896933383264, "grad_norm": 4.345180988311768, "learning_rate": 9.925917696949081e-06, "loss": 0.5724, "step": 125650 }, { "epoch": 0.7469491354149949, "grad_norm": 5.099003314971924, "learning_rate": 9.925882107115858e-06, "loss": 0.6518, "step": 125660 }, { "epoch": 0.7470085774916633, "grad_norm": 4.869301795959473, "learning_rate": 9.92584650879968e-06, "loss": 0.5686, "step": 125670 }, { "epoch": 0.7470680195683317, "grad_norm": 5.243727207183838, "learning_rate": 9.925810902000605e-06, "loss": 0.552, "step": 125680 }, { "epoch": 0.747127461645, "grad_norm": 5.955513000488281, "learning_rate": 9.925775286718695e-06, "loss": 0.5815, "step": 125690 }, { "epoch": 0.7471869037216684, "grad_norm": 5.156310081481934, "learning_rate": 9.925739662954013e-06, "loss": 0.6359, "step": 125700 }, { "epoch": 0.7472463457983368, "grad_norm": 5.990457534790039, "learning_rate": 9.92570403070662e-06, "loss": 0.6113, "step": 125710 }, { "epoch": 0.7473057878750052, "grad_norm": 5.212836265563965, "learning_rate": 9.925668389976577e-06, "loss": 0.6333, "step": 125720 }, { "epoch": 0.7473652299516735, "grad_norm": 4.7192816734313965, "learning_rate": 9.925632740763944e-06, "loss": 0.6186, "step": 125730 }, { "epoch": 0.747424672028342, "grad_norm": 4.402820587158203, "learning_rate": 9.925597083068786e-06, "loss": 0.5353, "step": 125740 }, { "epoch": 0.7474841141050104, "grad_norm": 5.223971843719482, "learning_rate": 9.92556141689116e-06, "loss": 0.5543, "step": 125750 }, { "epoch": 0.7475435561816788, "grad_norm": 5.697620391845703, "learning_rate": 9.92552574223113e-06, "loss": 0.6219, "step": 125760 }, { "epoch": 0.7476029982583472, "grad_norm": 5.598494529724121, "learning_rate": 9.925490059088759e-06, "loss": 0.5542, "step": 125770 }, { "epoch": 0.7476624403350155, "grad_norm": 6.204827308654785, "learning_rate": 9.925454367464103e-06, "loss": 0.575, "step": 125780 }, { "epoch": 0.7477218824116839, "grad_norm": 4.1865620613098145, "learning_rate": 9.92541866735723e-06, "loss": 0.5466, "step": 125790 }, { "epoch": 0.7477813244883523, "grad_norm": 5.609714508056641, "learning_rate": 9.925382958768195e-06, "loss": 0.5575, "step": 125800 }, { "epoch": 0.7478407665650207, "grad_norm": 7.182584762573242, "learning_rate": 9.925347241697065e-06, "loss": 0.5651, "step": 125810 }, { "epoch": 0.7479002086416892, "grad_norm": 5.251044750213623, "learning_rate": 9.9253115161439e-06, "loss": 0.6432, "step": 125820 }, { "epoch": 0.7479596507183575, "grad_norm": 6.103891849517822, "learning_rate": 9.925275782108759e-06, "loss": 0.5799, "step": 125830 }, { "epoch": 0.7480190927950259, "grad_norm": 5.52300500869751, "learning_rate": 9.925240039591706e-06, "loss": 0.5707, "step": 125840 }, { "epoch": 0.7480785348716943, "grad_norm": 7.174369812011719, "learning_rate": 9.925204288592804e-06, "loss": 0.6467, "step": 125850 }, { "epoch": 0.7481379769483627, "grad_norm": 5.636801719665527, "learning_rate": 9.92516852911211e-06, "loss": 0.5864, "step": 125860 }, { "epoch": 0.748197419025031, "grad_norm": 5.048994064331055, "learning_rate": 9.92513276114969e-06, "loss": 0.6018, "step": 125870 }, { "epoch": 0.7482568611016994, "grad_norm": 6.884496212005615, "learning_rate": 9.925096984705601e-06, "loss": 0.5923, "step": 125880 }, { "epoch": 0.7483163031783678, "grad_norm": 5.182538032531738, "learning_rate": 9.925061199779911e-06, "loss": 0.5612, "step": 125890 }, { "epoch": 0.7483757452550363, "grad_norm": 5.58030366897583, "learning_rate": 9.925025406372677e-06, "loss": 0.5863, "step": 125900 }, { "epoch": 0.7484351873317047, "grad_norm": 3.829477548599243, "learning_rate": 9.924989604483959e-06, "loss": 0.5785, "step": 125910 }, { "epoch": 0.748494629408373, "grad_norm": 5.889901161193848, "learning_rate": 9.924953794113822e-06, "loss": 0.5692, "step": 125920 }, { "epoch": 0.7485540714850414, "grad_norm": 4.997252464294434, "learning_rate": 9.92491797526233e-06, "loss": 0.5678, "step": 125930 }, { "epoch": 0.7486135135617098, "grad_norm": 5.438869476318359, "learning_rate": 9.924882147929538e-06, "loss": 0.5824, "step": 125940 }, { "epoch": 0.7486729556383782, "grad_norm": 5.460720062255859, "learning_rate": 9.924846312115513e-06, "loss": 0.6259, "step": 125950 }, { "epoch": 0.7487323977150466, "grad_norm": 6.404957294464111, "learning_rate": 9.924810467820316e-06, "loss": 0.598, "step": 125960 }, { "epoch": 0.7487918397917149, "grad_norm": 5.229592800140381, "learning_rate": 9.924774615044005e-06, "loss": 0.5585, "step": 125970 }, { "epoch": 0.7488512818683833, "grad_norm": 6.000767230987549, "learning_rate": 9.924738753786647e-06, "loss": 0.5992, "step": 125980 }, { "epoch": 0.7489107239450518, "grad_norm": 4.956062316894531, "learning_rate": 9.924702884048301e-06, "loss": 0.5982, "step": 125990 }, { "epoch": 0.7489701660217202, "grad_norm": 5.593714237213135, "learning_rate": 9.924667005829028e-06, "loss": 0.5711, "step": 126000 }, { "epoch": 0.7490296080983885, "grad_norm": 5.32870626449585, "learning_rate": 9.924631119128892e-06, "loss": 0.6039, "step": 126010 }, { "epoch": 0.7490890501750569, "grad_norm": 6.785646915435791, "learning_rate": 9.924595223947952e-06, "loss": 0.5868, "step": 126020 }, { "epoch": 0.7491484922517253, "grad_norm": 6.833606719970703, "learning_rate": 9.924559320286274e-06, "loss": 0.5547, "step": 126030 }, { "epoch": 0.7492079343283937, "grad_norm": 5.750124931335449, "learning_rate": 9.924523408143914e-06, "loss": 0.6505, "step": 126040 }, { "epoch": 0.7492673764050621, "grad_norm": 6.681103229522705, "learning_rate": 9.92448748752094e-06, "loss": 0.6424, "step": 126050 }, { "epoch": 0.7493268184817304, "grad_norm": 7.139169216156006, "learning_rate": 9.92445155841741e-06, "loss": 0.6046, "step": 126060 }, { "epoch": 0.7493862605583989, "grad_norm": 4.536197662353516, "learning_rate": 9.924415620833385e-06, "loss": 0.5687, "step": 126070 }, { "epoch": 0.7494457026350673, "grad_norm": 4.875258445739746, "learning_rate": 9.92437967476893e-06, "loss": 0.5764, "step": 126080 }, { "epoch": 0.7495051447117357, "grad_norm": 4.233938694000244, "learning_rate": 9.924343720224106e-06, "loss": 0.5705, "step": 126090 }, { "epoch": 0.749564586788404, "grad_norm": 5.589890480041504, "learning_rate": 9.924307757198974e-06, "loss": 0.5567, "step": 126100 }, { "epoch": 0.7496240288650724, "grad_norm": 5.007523059844971, "learning_rate": 9.924271785693598e-06, "loss": 0.5675, "step": 126110 }, { "epoch": 0.7496834709417408, "grad_norm": 5.611507892608643, "learning_rate": 9.924235805708037e-06, "loss": 0.5778, "step": 126120 }, { "epoch": 0.7497429130184092, "grad_norm": 6.977959156036377, "learning_rate": 9.924199817242354e-06, "loss": 0.6103, "step": 126130 }, { "epoch": 0.7498023550950776, "grad_norm": 5.165938377380371, "learning_rate": 9.924163820296613e-06, "loss": 0.5879, "step": 126140 }, { "epoch": 0.749861797171746, "grad_norm": 4.471109867095947, "learning_rate": 9.924127814870873e-06, "loss": 0.5643, "step": 126150 }, { "epoch": 0.7499212392484144, "grad_norm": 5.536948204040527, "learning_rate": 9.924091800965198e-06, "loss": 0.5789, "step": 126160 }, { "epoch": 0.7499806813250828, "grad_norm": 4.254806995391846, "learning_rate": 9.924055778579648e-06, "loss": 0.5356, "step": 126170 }, { "epoch": 0.7500401234017512, "grad_norm": 5.942818641662598, "learning_rate": 9.92401974771429e-06, "loss": 0.5801, "step": 126180 }, { "epoch": 0.7500995654784196, "grad_norm": 5.021689414978027, "learning_rate": 9.923983708369178e-06, "loss": 0.6001, "step": 126190 }, { "epoch": 0.7501590075550879, "grad_norm": 5.874293327331543, "learning_rate": 9.923947660544382e-06, "loss": 0.5466, "step": 126200 }, { "epoch": 0.7502184496317563, "grad_norm": 6.790459632873535, "learning_rate": 9.923911604239959e-06, "loss": 0.5789, "step": 126210 }, { "epoch": 0.7502778917084247, "grad_norm": 5.960313320159912, "learning_rate": 9.923875539455973e-06, "loss": 0.5455, "step": 126220 }, { "epoch": 0.7503373337850932, "grad_norm": 6.202679634094238, "learning_rate": 9.923839466192485e-06, "loss": 0.6028, "step": 126230 }, { "epoch": 0.7503967758617615, "grad_norm": 4.024397850036621, "learning_rate": 9.92380338444956e-06, "loss": 0.6214, "step": 126240 }, { "epoch": 0.7504562179384299, "grad_norm": 5.36429500579834, "learning_rate": 9.923767294227256e-06, "loss": 0.6327, "step": 126250 }, { "epoch": 0.7505156600150983, "grad_norm": 5.887821674346924, "learning_rate": 9.923731195525637e-06, "loss": 0.5566, "step": 126260 }, { "epoch": 0.7505751020917667, "grad_norm": 5.7871174812316895, "learning_rate": 9.923695088344766e-06, "loss": 0.6044, "step": 126270 }, { "epoch": 0.7506345441684351, "grad_norm": 4.749139308929443, "learning_rate": 9.923658972684706e-06, "loss": 0.5215, "step": 126280 }, { "epoch": 0.7506939862451034, "grad_norm": 6.1383233070373535, "learning_rate": 9.923622848545517e-06, "loss": 0.6285, "step": 126290 }, { "epoch": 0.7507534283217718, "grad_norm": 6.602361679077148, "learning_rate": 9.923586715927261e-06, "loss": 0.5901, "step": 126300 }, { "epoch": 0.7508128703984402, "grad_norm": 4.910768985748291, "learning_rate": 9.923550574830001e-06, "loss": 0.6683, "step": 126310 }, { "epoch": 0.7508723124751087, "grad_norm": 4.816612243652344, "learning_rate": 9.923514425253802e-06, "loss": 0.5959, "step": 126320 }, { "epoch": 0.7509317545517771, "grad_norm": 4.756734848022461, "learning_rate": 9.923478267198722e-06, "loss": 0.5428, "step": 126330 }, { "epoch": 0.7509911966284454, "grad_norm": 5.276986598968506, "learning_rate": 9.923442100664825e-06, "loss": 0.5928, "step": 126340 }, { "epoch": 0.7510506387051138, "grad_norm": 7.793828010559082, "learning_rate": 9.923405925652171e-06, "loss": 0.5703, "step": 126350 }, { "epoch": 0.7511100807817822, "grad_norm": 5.984077453613281, "learning_rate": 9.923369742160828e-06, "loss": 0.6283, "step": 126360 }, { "epoch": 0.7511695228584506, "grad_norm": 4.442134857177734, "learning_rate": 9.923333550190855e-06, "loss": 0.5979, "step": 126370 }, { "epoch": 0.7512289649351189, "grad_norm": 5.303300857543945, "learning_rate": 9.923297349742312e-06, "loss": 0.5398, "step": 126380 }, { "epoch": 0.7512884070117873, "grad_norm": 5.521609306335449, "learning_rate": 9.923261140815264e-06, "loss": 0.5883, "step": 126390 }, { "epoch": 0.7513478490884558, "grad_norm": 4.531427383422852, "learning_rate": 9.923224923409773e-06, "loss": 0.5849, "step": 126400 }, { "epoch": 0.7514072911651242, "grad_norm": 5.834505081176758, "learning_rate": 9.923188697525902e-06, "loss": 0.5766, "step": 126410 }, { "epoch": 0.7514667332417926, "grad_norm": 5.720329761505127, "learning_rate": 9.923152463163713e-06, "loss": 0.6166, "step": 126420 }, { "epoch": 0.7515261753184609, "grad_norm": 4.539501190185547, "learning_rate": 9.923116220323265e-06, "loss": 0.6038, "step": 126430 }, { "epoch": 0.7515856173951293, "grad_norm": 3.558410406112671, "learning_rate": 9.923079969004627e-06, "loss": 0.5943, "step": 126440 }, { "epoch": 0.7516450594717977, "grad_norm": 5.7096710205078125, "learning_rate": 9.923043709207857e-06, "loss": 0.5589, "step": 126450 }, { "epoch": 0.7517045015484661, "grad_norm": 4.973905563354492, "learning_rate": 9.923007440933017e-06, "loss": 0.5554, "step": 126460 }, { "epoch": 0.7517639436251344, "grad_norm": 6.353511810302734, "learning_rate": 9.922971164180171e-06, "loss": 0.5384, "step": 126470 }, { "epoch": 0.7518233857018028, "grad_norm": 5.162437915802002, "learning_rate": 9.922934878949382e-06, "loss": 0.6219, "step": 126480 }, { "epoch": 0.7518828277784713, "grad_norm": 7.014318466186523, "learning_rate": 9.922898585240712e-06, "loss": 0.6169, "step": 126490 }, { "epoch": 0.7519422698551397, "grad_norm": 5.872997283935547, "learning_rate": 9.922862283054224e-06, "loss": 0.5841, "step": 126500 }, { "epoch": 0.7520017119318081, "grad_norm": 5.942905426025391, "learning_rate": 9.922825972389977e-06, "loss": 0.5668, "step": 126510 }, { "epoch": 0.7520611540084764, "grad_norm": 4.873554706573486, "learning_rate": 9.922789653248039e-06, "loss": 0.6202, "step": 126520 }, { "epoch": 0.7521205960851448, "grad_norm": 5.421109199523926, "learning_rate": 9.922753325628468e-06, "loss": 0.5874, "step": 126530 }, { "epoch": 0.7521800381618132, "grad_norm": 4.619955062866211, "learning_rate": 9.922716989531329e-06, "loss": 0.5981, "step": 126540 }, { "epoch": 0.7522394802384816, "grad_norm": 4.699152946472168, "learning_rate": 9.922680644956684e-06, "loss": 0.5893, "step": 126550 }, { "epoch": 0.75229892231515, "grad_norm": 5.397169589996338, "learning_rate": 9.922644291904597e-06, "loss": 0.5658, "step": 126560 }, { "epoch": 0.7523583643918184, "grad_norm": 4.499934196472168, "learning_rate": 9.922607930375127e-06, "loss": 0.574, "step": 126570 }, { "epoch": 0.7524178064684868, "grad_norm": 4.729133129119873, "learning_rate": 9.922571560368339e-06, "loss": 0.5567, "step": 126580 }, { "epoch": 0.7524772485451552, "grad_norm": 6.148603916168213, "learning_rate": 9.922535181884296e-06, "loss": 0.5956, "step": 126590 }, { "epoch": 0.7525366906218236, "grad_norm": 4.959571838378906, "learning_rate": 9.922498794923062e-06, "loss": 0.6144, "step": 126600 }, { "epoch": 0.7525961326984919, "grad_norm": 5.505373001098633, "learning_rate": 9.922462399484695e-06, "loss": 0.6207, "step": 126610 }, { "epoch": 0.7526555747751603, "grad_norm": 5.980072498321533, "learning_rate": 9.92242599556926e-06, "loss": 0.5598, "step": 126620 }, { "epoch": 0.7527150168518287, "grad_norm": 5.330149173736572, "learning_rate": 9.922389583176822e-06, "loss": 0.5439, "step": 126630 }, { "epoch": 0.7527744589284971, "grad_norm": 5.2939887046813965, "learning_rate": 9.92235316230744e-06, "loss": 0.5464, "step": 126640 }, { "epoch": 0.7528339010051656, "grad_norm": 5.143381118774414, "learning_rate": 9.92231673296118e-06, "loss": 0.5717, "step": 126650 }, { "epoch": 0.7528933430818339, "grad_norm": 5.572955131530762, "learning_rate": 9.922280295138105e-06, "loss": 0.5935, "step": 126660 }, { "epoch": 0.7529527851585023, "grad_norm": 4.628007888793945, "learning_rate": 9.922243848838273e-06, "loss": 0.5618, "step": 126670 }, { "epoch": 0.7530122272351707, "grad_norm": 6.661113739013672, "learning_rate": 9.922207394061752e-06, "loss": 0.6034, "step": 126680 }, { "epoch": 0.7530716693118391, "grad_norm": 5.6306047439575195, "learning_rate": 9.9221709308086e-06, "loss": 0.5361, "step": 126690 }, { "epoch": 0.7531311113885075, "grad_norm": 6.222886562347412, "learning_rate": 9.922134459078883e-06, "loss": 0.5425, "step": 126700 }, { "epoch": 0.7531905534651758, "grad_norm": 5.4179911613464355, "learning_rate": 9.922097978872665e-06, "loss": 0.5721, "step": 126710 }, { "epoch": 0.7532499955418442, "grad_norm": 5.615050315856934, "learning_rate": 9.922061490190004e-06, "loss": 0.5584, "step": 126720 }, { "epoch": 0.7533094376185127, "grad_norm": 5.01718807220459, "learning_rate": 9.92202499303097e-06, "loss": 0.5927, "step": 126730 }, { "epoch": 0.7533688796951811, "grad_norm": 6.412703990936279, "learning_rate": 9.921988487395619e-06, "loss": 0.6088, "step": 126740 }, { "epoch": 0.7534283217718494, "grad_norm": 3.4713385105133057, "learning_rate": 9.921951973284016e-06, "loss": 0.5468, "step": 126750 }, { "epoch": 0.7534877638485178, "grad_norm": 3.912825345993042, "learning_rate": 9.921915450696226e-06, "loss": 0.5328, "step": 126760 }, { "epoch": 0.7535472059251862, "grad_norm": 4.00393009185791, "learning_rate": 9.921878919632308e-06, "loss": 0.5291, "step": 126770 }, { "epoch": 0.7536066480018546, "grad_norm": 5.903862476348877, "learning_rate": 9.92184238009233e-06, "loss": 0.5004, "step": 126780 }, { "epoch": 0.753666090078523, "grad_norm": 6.252321720123291, "learning_rate": 9.92180583207635e-06, "loss": 0.602, "step": 126790 }, { "epoch": 0.7537255321551913, "grad_norm": 6.179806232452393, "learning_rate": 9.921769275584435e-06, "loss": 0.6173, "step": 126800 }, { "epoch": 0.7537849742318598, "grad_norm": 4.57712984085083, "learning_rate": 9.921732710616646e-06, "loss": 0.5625, "step": 126810 }, { "epoch": 0.7538444163085282, "grad_norm": 6.163084506988525, "learning_rate": 9.921696137173045e-06, "loss": 0.5432, "step": 126820 }, { "epoch": 0.7539038583851966, "grad_norm": 4.924975395202637, "learning_rate": 9.921659555253695e-06, "loss": 0.5472, "step": 126830 }, { "epoch": 0.7539633004618649, "grad_norm": 6.23842716217041, "learning_rate": 9.921622964858661e-06, "loss": 0.5874, "step": 126840 }, { "epoch": 0.7540227425385333, "grad_norm": 7.414211750030518, "learning_rate": 9.921586365988005e-06, "loss": 0.619, "step": 126850 }, { "epoch": 0.7540821846152017, "grad_norm": 5.0963029861450195, "learning_rate": 9.92154975864179e-06, "loss": 0.5135, "step": 126860 }, { "epoch": 0.7541416266918701, "grad_norm": 5.21645450592041, "learning_rate": 9.92151314282008e-06, "loss": 0.5873, "step": 126870 }, { "epoch": 0.7542010687685385, "grad_norm": 5.865634918212891, "learning_rate": 9.921476518522937e-06, "loss": 0.582, "step": 126880 }, { "epoch": 0.7542605108452068, "grad_norm": 4.403388023376465, "learning_rate": 9.921439885750423e-06, "loss": 0.6281, "step": 126890 }, { "epoch": 0.7543199529218753, "grad_norm": 4.75334358215332, "learning_rate": 9.921403244502604e-06, "loss": 0.5474, "step": 126900 }, { "epoch": 0.7543793949985437, "grad_norm": 5.290737628936768, "learning_rate": 9.92136659477954e-06, "loss": 0.6265, "step": 126910 }, { "epoch": 0.7544388370752121, "grad_norm": 6.18166971206665, "learning_rate": 9.921329936581296e-06, "loss": 0.6138, "step": 126920 }, { "epoch": 0.7544982791518805, "grad_norm": 6.419443607330322, "learning_rate": 9.921293269907935e-06, "loss": 0.6159, "step": 126930 }, { "epoch": 0.7545577212285488, "grad_norm": 5.245830535888672, "learning_rate": 9.92125659475952e-06, "loss": 0.6263, "step": 126940 }, { "epoch": 0.7546171633052172, "grad_norm": 5.847192287445068, "learning_rate": 9.921219911136112e-06, "loss": 0.6561, "step": 126950 }, { "epoch": 0.7546766053818856, "grad_norm": 4.672938823699951, "learning_rate": 9.921183219037778e-06, "loss": 0.5815, "step": 126960 }, { "epoch": 0.754736047458554, "grad_norm": 6.362044811248779, "learning_rate": 9.921146518464577e-06, "loss": 0.6228, "step": 126970 }, { "epoch": 0.7547954895352224, "grad_norm": 6.393876075744629, "learning_rate": 9.921109809416577e-06, "loss": 0.6104, "step": 126980 }, { "epoch": 0.7548549316118908, "grad_norm": 4.926130294799805, "learning_rate": 9.921073091893839e-06, "loss": 0.5748, "step": 126990 }, { "epoch": 0.7549143736885592, "grad_norm": 5.820058345794678, "learning_rate": 9.921036365896424e-06, "loss": 0.574, "step": 127000 }, { "epoch": 0.7549738157652276, "grad_norm": 5.163205623626709, "learning_rate": 9.920999631424398e-06, "loss": 0.6011, "step": 127010 }, { "epoch": 0.755033257841896, "grad_norm": 4.33715295791626, "learning_rate": 9.920962888477824e-06, "loss": 0.5983, "step": 127020 }, { "epoch": 0.7550926999185643, "grad_norm": 6.88842248916626, "learning_rate": 9.920926137056763e-06, "loss": 0.5799, "step": 127030 }, { "epoch": 0.7551521419952327, "grad_norm": 6.163808822631836, "learning_rate": 9.920889377161283e-06, "loss": 0.6399, "step": 127040 }, { "epoch": 0.7552115840719011, "grad_norm": 3.7817578315734863, "learning_rate": 9.920852608791443e-06, "loss": 0.5066, "step": 127050 }, { "epoch": 0.7552710261485696, "grad_norm": 5.2692975997924805, "learning_rate": 9.920815831947305e-06, "loss": 0.5368, "step": 127060 }, { "epoch": 0.755330468225238, "grad_norm": 5.010973930358887, "learning_rate": 9.92077904662894e-06, "loss": 0.5754, "step": 127070 }, { "epoch": 0.7553899103019063, "grad_norm": 6.212983131408691, "learning_rate": 9.920742252836404e-06, "loss": 0.5529, "step": 127080 }, { "epoch": 0.7554493523785747, "grad_norm": 5.786299705505371, "learning_rate": 9.92070545056976e-06, "loss": 0.6172, "step": 127090 }, { "epoch": 0.7555087944552431, "grad_norm": 5.72837495803833, "learning_rate": 9.920668639829077e-06, "loss": 0.6088, "step": 127100 }, { "epoch": 0.7555682365319115, "grad_norm": 5.514241695404053, "learning_rate": 9.920631820614416e-06, "loss": 0.6098, "step": 127110 }, { "epoch": 0.7556276786085798, "grad_norm": 6.188965797424316, "learning_rate": 9.920594992925837e-06, "loss": 0.5798, "step": 127120 }, { "epoch": 0.7556871206852482, "grad_norm": 5.709939002990723, "learning_rate": 9.92055815676341e-06, "loss": 0.6248, "step": 127130 }, { "epoch": 0.7557465627619167, "grad_norm": 4.578564643859863, "learning_rate": 9.920521312127193e-06, "loss": 0.6037, "step": 127140 }, { "epoch": 0.7558060048385851, "grad_norm": 5.60401725769043, "learning_rate": 9.92048445901725e-06, "loss": 0.5437, "step": 127150 }, { "epoch": 0.7558654469152535, "grad_norm": 4.689869403839111, "learning_rate": 9.920447597433647e-06, "loss": 0.5151, "step": 127160 }, { "epoch": 0.7559248889919218, "grad_norm": 4.43503999710083, "learning_rate": 9.920410727376446e-06, "loss": 0.5559, "step": 127170 }, { "epoch": 0.7559843310685902, "grad_norm": 5.561022758483887, "learning_rate": 9.92037384884571e-06, "loss": 0.5743, "step": 127180 }, { "epoch": 0.7560437731452586, "grad_norm": 6.118234634399414, "learning_rate": 9.920336961841505e-06, "loss": 0.6176, "step": 127190 }, { "epoch": 0.756103215221927, "grad_norm": 5.682711124420166, "learning_rate": 9.92030006636389e-06, "loss": 0.6167, "step": 127200 }, { "epoch": 0.7561626572985953, "grad_norm": 6.870240688323975, "learning_rate": 9.920263162412932e-06, "loss": 0.6145, "step": 127210 }, { "epoch": 0.7562220993752637, "grad_norm": 6.114035606384277, "learning_rate": 9.920226249988696e-06, "loss": 0.5288, "step": 127220 }, { "epoch": 0.7562815414519322, "grad_norm": 5.884645938873291, "learning_rate": 9.920189329091242e-06, "loss": 0.551, "step": 127230 }, { "epoch": 0.7563409835286006, "grad_norm": 5.026208877563477, "learning_rate": 9.920152399720634e-06, "loss": 0.603, "step": 127240 }, { "epoch": 0.756400425605269, "grad_norm": 5.96954870223999, "learning_rate": 9.920115461876937e-06, "loss": 0.5988, "step": 127250 }, { "epoch": 0.7564598676819373, "grad_norm": 6.4192728996276855, "learning_rate": 9.920078515560213e-06, "loss": 0.5699, "step": 127260 }, { "epoch": 0.7565193097586057, "grad_norm": 4.934479713439941, "learning_rate": 9.92004156077053e-06, "loss": 0.5797, "step": 127270 }, { "epoch": 0.7565787518352741, "grad_norm": 4.9585137367248535, "learning_rate": 9.920004597507947e-06, "loss": 0.5577, "step": 127280 }, { "epoch": 0.7566381939119425, "grad_norm": 5.897540092468262, "learning_rate": 9.919967625772527e-06, "loss": 0.5385, "step": 127290 }, { "epoch": 0.756697635988611, "grad_norm": 4.267693519592285, "learning_rate": 9.919930645564338e-06, "loss": 0.6286, "step": 127300 }, { "epoch": 0.7567570780652793, "grad_norm": 6.6425909996032715, "learning_rate": 9.91989365688344e-06, "loss": 0.6471, "step": 127310 }, { "epoch": 0.7568165201419477, "grad_norm": 6.261905670166016, "learning_rate": 9.919856659729898e-06, "loss": 0.5826, "step": 127320 }, { "epoch": 0.7568759622186161, "grad_norm": 5.494193077087402, "learning_rate": 9.919819654103777e-06, "loss": 0.5612, "step": 127330 }, { "epoch": 0.7569354042952845, "grad_norm": 7.107697010040283, "learning_rate": 9.919782640005137e-06, "loss": 0.6638, "step": 127340 }, { "epoch": 0.7569948463719528, "grad_norm": 4.767420291900635, "learning_rate": 9.919745617434047e-06, "loss": 0.6214, "step": 127350 }, { "epoch": 0.7570542884486212, "grad_norm": 4.297771453857422, "learning_rate": 9.919708586390567e-06, "loss": 0.5507, "step": 127360 }, { "epoch": 0.7571137305252896, "grad_norm": 5.641933917999268, "learning_rate": 9.919671546874762e-06, "loss": 0.6066, "step": 127370 }, { "epoch": 0.757173172601958, "grad_norm": 5.254654884338379, "learning_rate": 9.919634498886697e-06, "loss": 0.6027, "step": 127380 }, { "epoch": 0.7572326146786265, "grad_norm": 5.371861934661865, "learning_rate": 9.919597442426432e-06, "loss": 0.5928, "step": 127390 }, { "epoch": 0.7572920567552948, "grad_norm": 5.9352617263793945, "learning_rate": 9.919560377494034e-06, "loss": 0.6285, "step": 127400 }, { "epoch": 0.7573514988319632, "grad_norm": 7.037664890289307, "learning_rate": 9.919523304089566e-06, "loss": 0.6146, "step": 127410 }, { "epoch": 0.7574109409086316, "grad_norm": 4.010471343994141, "learning_rate": 9.919486222213092e-06, "loss": 0.5851, "step": 127420 }, { "epoch": 0.7574703829853, "grad_norm": 6.486856937408447, "learning_rate": 9.919449131864676e-06, "loss": 0.5602, "step": 127430 }, { "epoch": 0.7575298250619684, "grad_norm": 6.277341365814209, "learning_rate": 9.919412033044381e-06, "loss": 0.5682, "step": 127440 }, { "epoch": 0.7575892671386367, "grad_norm": 4.246798038482666, "learning_rate": 9.919374925752272e-06, "loss": 0.6253, "step": 127450 }, { "epoch": 0.7576487092153051, "grad_norm": 6.082113742828369, "learning_rate": 9.919337809988413e-06, "loss": 0.5865, "step": 127460 }, { "epoch": 0.7577081512919736, "grad_norm": 5.697659969329834, "learning_rate": 9.919300685752866e-06, "loss": 0.5815, "step": 127470 }, { "epoch": 0.757767593368642, "grad_norm": 4.23397970199585, "learning_rate": 9.919263553045698e-06, "loss": 0.5584, "step": 127480 }, { "epoch": 0.7578270354453103, "grad_norm": 5.468072891235352, "learning_rate": 9.91922641186697e-06, "loss": 0.5917, "step": 127490 }, { "epoch": 0.7578864775219787, "grad_norm": 5.199236869812012, "learning_rate": 9.919189262216746e-06, "loss": 0.5638, "step": 127500 }, { "epoch": 0.7579459195986471, "grad_norm": 5.747253894805908, "learning_rate": 9.919152104095093e-06, "loss": 0.5777, "step": 127510 }, { "epoch": 0.7580053616753155, "grad_norm": 4.966122627258301, "learning_rate": 9.919114937502073e-06, "loss": 0.5975, "step": 127520 }, { "epoch": 0.7580648037519839, "grad_norm": 5.715847015380859, "learning_rate": 9.91907776243775e-06, "loss": 0.5803, "step": 127530 }, { "epoch": 0.7581242458286522, "grad_norm": 6.148674011230469, "learning_rate": 9.919040578902188e-06, "loss": 0.601, "step": 127540 }, { "epoch": 0.7581836879053206, "grad_norm": 4.5663018226623535, "learning_rate": 9.91900338689545e-06, "loss": 0.5677, "step": 127550 }, { "epoch": 0.7582431299819891, "grad_norm": 4.827038764953613, "learning_rate": 9.918966186417603e-06, "loss": 0.5442, "step": 127560 }, { "epoch": 0.7583025720586575, "grad_norm": 5.381016254425049, "learning_rate": 9.918928977468709e-06, "loss": 0.5811, "step": 127570 }, { "epoch": 0.7583620141353258, "grad_norm": 5.0795769691467285, "learning_rate": 9.918891760048833e-06, "loss": 0.5784, "step": 127580 }, { "epoch": 0.7584214562119942, "grad_norm": 5.477707386016846, "learning_rate": 9.918854534158035e-06, "loss": 0.5897, "step": 127590 }, { "epoch": 0.7584808982886626, "grad_norm": 5.515103816986084, "learning_rate": 9.918817299796385e-06, "loss": 0.6084, "step": 127600 }, { "epoch": 0.758540340365331, "grad_norm": 7.0395121574401855, "learning_rate": 9.918780056963946e-06, "loss": 0.6021, "step": 127610 }, { "epoch": 0.7585997824419994, "grad_norm": 6.209924697875977, "learning_rate": 9.918742805660779e-06, "loss": 0.6369, "step": 127620 }, { "epoch": 0.7586592245186677, "grad_norm": 5.6259894371032715, "learning_rate": 9.918705545886952e-06, "loss": 0.6265, "step": 127630 }, { "epoch": 0.7587186665953362, "grad_norm": 4.619355201721191, "learning_rate": 9.918668277642524e-06, "loss": 0.5894, "step": 127640 }, { "epoch": 0.7587781086720046, "grad_norm": 4.155982494354248, "learning_rate": 9.918631000927565e-06, "loss": 0.6501, "step": 127650 }, { "epoch": 0.758837550748673, "grad_norm": 4.485395908355713, "learning_rate": 9.918593715742135e-06, "loss": 0.5749, "step": 127660 }, { "epoch": 0.7588969928253414, "grad_norm": 6.719273567199707, "learning_rate": 9.9185564220863e-06, "loss": 0.5382, "step": 127670 }, { "epoch": 0.7589564349020097, "grad_norm": 5.346680164337158, "learning_rate": 9.918519119960127e-06, "loss": 0.6189, "step": 127680 }, { "epoch": 0.7590158769786781, "grad_norm": 5.4756999015808105, "learning_rate": 9.918481809363674e-06, "loss": 0.5564, "step": 127690 }, { "epoch": 0.7590753190553465, "grad_norm": 7.093712329864502, "learning_rate": 9.918444490297007e-06, "loss": 0.6259, "step": 127700 }, { "epoch": 0.759134761132015, "grad_norm": 4.981087684631348, "learning_rate": 9.918407162760195e-06, "loss": 0.5587, "step": 127710 }, { "epoch": 0.7591942032086832, "grad_norm": 5.0264997482299805, "learning_rate": 9.918369826753298e-06, "loss": 0.6081, "step": 127720 }, { "epoch": 0.7592536452853517, "grad_norm": 5.368193626403809, "learning_rate": 9.918332482276381e-06, "loss": 0.5548, "step": 127730 }, { "epoch": 0.7593130873620201, "grad_norm": 6.091809272766113, "learning_rate": 9.918295129329508e-06, "loss": 0.594, "step": 127740 }, { "epoch": 0.7593725294386885, "grad_norm": 5.044655799865723, "learning_rate": 9.918257767912745e-06, "loss": 0.6234, "step": 127750 }, { "epoch": 0.7594319715153569, "grad_norm": 5.99934720993042, "learning_rate": 9.918220398026155e-06, "loss": 0.654, "step": 127760 }, { "epoch": 0.7594914135920252, "grad_norm": 5.413564205169678, "learning_rate": 9.918183019669802e-06, "loss": 0.6171, "step": 127770 }, { "epoch": 0.7595508556686936, "grad_norm": 4.791066646575928, "learning_rate": 9.918145632843752e-06, "loss": 0.6096, "step": 127780 }, { "epoch": 0.759610297745362, "grad_norm": 5.055550575256348, "learning_rate": 9.918108237548067e-06, "loss": 0.5802, "step": 127790 }, { "epoch": 0.7596697398220305, "grad_norm": 7.45349645614624, "learning_rate": 9.918070833782815e-06, "loss": 0.5537, "step": 127800 }, { "epoch": 0.7597291818986988, "grad_norm": 4.396838188171387, "learning_rate": 9.918033421548056e-06, "loss": 0.5268, "step": 127810 }, { "epoch": 0.7597886239753672, "grad_norm": 5.832483291625977, "learning_rate": 9.917996000843858e-06, "loss": 0.5749, "step": 127820 }, { "epoch": 0.7598480660520356, "grad_norm": 5.722085952758789, "learning_rate": 9.917958571670284e-06, "loss": 0.5967, "step": 127830 }, { "epoch": 0.759907508128704, "grad_norm": 4.517643451690674, "learning_rate": 9.917921134027398e-06, "loss": 0.5648, "step": 127840 }, { "epoch": 0.7599669502053724, "grad_norm": 5.5959014892578125, "learning_rate": 9.917883687915266e-06, "loss": 0.6186, "step": 127850 }, { "epoch": 0.7600263922820407, "grad_norm": 4.823673725128174, "learning_rate": 9.917846233333949e-06, "loss": 0.5991, "step": 127860 }, { "epoch": 0.7600858343587091, "grad_norm": 5.9982123374938965, "learning_rate": 9.917808770283518e-06, "loss": 0.5858, "step": 127870 }, { "epoch": 0.7601452764353775, "grad_norm": 7.342423439025879, "learning_rate": 9.917771298764029e-06, "loss": 0.6106, "step": 127880 }, { "epoch": 0.760204718512046, "grad_norm": 5.258310317993164, "learning_rate": 9.917733818775554e-06, "loss": 0.5383, "step": 127890 }, { "epoch": 0.7602641605887144, "grad_norm": 4.946552276611328, "learning_rate": 9.917696330318154e-06, "loss": 0.5213, "step": 127900 }, { "epoch": 0.7603236026653827, "grad_norm": 5.190947532653809, "learning_rate": 9.917658833391895e-06, "loss": 0.5865, "step": 127910 }, { "epoch": 0.7603830447420511, "grad_norm": 5.294413089752197, "learning_rate": 9.91762132799684e-06, "loss": 0.5549, "step": 127920 }, { "epoch": 0.7604424868187195, "grad_norm": 5.69550895690918, "learning_rate": 9.917583814133054e-06, "loss": 0.6037, "step": 127930 }, { "epoch": 0.7605019288953879, "grad_norm": 6.3183159828186035, "learning_rate": 9.917546291800601e-06, "loss": 0.5675, "step": 127940 }, { "epoch": 0.7605613709720562, "grad_norm": 6.061624526977539, "learning_rate": 9.917508760999548e-06, "loss": 0.6073, "step": 127950 }, { "epoch": 0.7606208130487246, "grad_norm": 4.804202556610107, "learning_rate": 9.917471221729958e-06, "loss": 0.5185, "step": 127960 }, { "epoch": 0.7606802551253931, "grad_norm": 4.801854610443115, "learning_rate": 9.917433673991895e-06, "loss": 0.5858, "step": 127970 }, { "epoch": 0.7607396972020615, "grad_norm": 5.676353931427002, "learning_rate": 9.917396117785425e-06, "loss": 0.6096, "step": 127980 }, { "epoch": 0.7607991392787299, "grad_norm": 4.6108479499816895, "learning_rate": 9.917358553110612e-06, "loss": 0.6266, "step": 127990 }, { "epoch": 0.7608585813553982, "grad_norm": 5.304515838623047, "learning_rate": 9.917320979967522e-06, "loss": 0.5681, "step": 128000 }, { "epoch": 0.7609180234320666, "grad_norm": 3.8365230560302734, "learning_rate": 9.917283398356216e-06, "loss": 0.5079, "step": 128010 }, { "epoch": 0.760977465508735, "grad_norm": 4.97826623916626, "learning_rate": 9.917245808276764e-06, "loss": 0.5888, "step": 128020 }, { "epoch": 0.7610369075854034, "grad_norm": 6.308183193206787, "learning_rate": 9.917208209729226e-06, "loss": 0.6263, "step": 128030 }, { "epoch": 0.7610963496620718, "grad_norm": 4.186238765716553, "learning_rate": 9.91717060271367e-06, "loss": 0.6464, "step": 128040 }, { "epoch": 0.7611557917387402, "grad_norm": 5.63791036605835, "learning_rate": 9.917132987230157e-06, "loss": 0.5454, "step": 128050 }, { "epoch": 0.7612152338154086, "grad_norm": 6.228992938995361, "learning_rate": 9.917095363278758e-06, "loss": 0.6163, "step": 128060 }, { "epoch": 0.761274675892077, "grad_norm": 5.88775634765625, "learning_rate": 9.917057730859532e-06, "loss": 0.6125, "step": 128070 }, { "epoch": 0.7613341179687454, "grad_norm": 5.455084323883057, "learning_rate": 9.917020089972546e-06, "loss": 0.5844, "step": 128080 }, { "epoch": 0.7613935600454137, "grad_norm": 6.013805866241455, "learning_rate": 9.916982440617866e-06, "loss": 0.5585, "step": 128090 }, { "epoch": 0.7614530021220821, "grad_norm": 6.106876373291016, "learning_rate": 9.916944782795554e-06, "loss": 0.5752, "step": 128100 }, { "epoch": 0.7615124441987505, "grad_norm": 5.554610252380371, "learning_rate": 9.916907116505678e-06, "loss": 0.5491, "step": 128110 }, { "epoch": 0.7615718862754189, "grad_norm": 4.055346488952637, "learning_rate": 9.9168694417483e-06, "loss": 0.5741, "step": 128120 }, { "epoch": 0.7616313283520874, "grad_norm": 6.189751148223877, "learning_rate": 9.916831758523486e-06, "loss": 0.5883, "step": 128130 }, { "epoch": 0.7616907704287557, "grad_norm": 5.029386043548584, "learning_rate": 9.916794066831301e-06, "loss": 0.613, "step": 128140 }, { "epoch": 0.7617502125054241, "grad_norm": 5.606083869934082, "learning_rate": 9.91675636667181e-06, "loss": 0.5419, "step": 128150 }, { "epoch": 0.7618096545820925, "grad_norm": 6.366152286529541, "learning_rate": 9.916718658045079e-06, "loss": 0.5622, "step": 128160 }, { "epoch": 0.7618690966587609, "grad_norm": 5.308034420013428, "learning_rate": 9.91668094095117e-06, "loss": 0.5846, "step": 128170 }, { "epoch": 0.7619285387354292, "grad_norm": 8.322742462158203, "learning_rate": 9.916643215390152e-06, "loss": 0.5854, "step": 128180 }, { "epoch": 0.7619879808120976, "grad_norm": 5.072364330291748, "learning_rate": 9.916605481362088e-06, "loss": 0.6385, "step": 128190 }, { "epoch": 0.762047422888766, "grad_norm": 5.0332417488098145, "learning_rate": 9.91656773886704e-06, "loss": 0.6193, "step": 128200 }, { "epoch": 0.7621068649654344, "grad_norm": 4.332768440246582, "learning_rate": 9.916529987905077e-06, "loss": 0.5749, "step": 128210 }, { "epoch": 0.7621663070421029, "grad_norm": 7.603175640106201, "learning_rate": 9.916492228476264e-06, "loss": 0.601, "step": 128220 }, { "epoch": 0.7622257491187712, "grad_norm": 4.7032551765441895, "learning_rate": 9.916454460580662e-06, "loss": 0.5826, "step": 128230 }, { "epoch": 0.7622851911954396, "grad_norm": 4.069822788238525, "learning_rate": 9.916416684218342e-06, "loss": 0.5664, "step": 128240 }, { "epoch": 0.762344633272108, "grad_norm": 5.646529197692871, "learning_rate": 9.916378899389364e-06, "loss": 0.5956, "step": 128250 }, { "epoch": 0.7624040753487764, "grad_norm": 4.47431755065918, "learning_rate": 9.916341106093795e-06, "loss": 0.5944, "step": 128260 }, { "epoch": 0.7624635174254448, "grad_norm": 4.359421730041504, "learning_rate": 9.916303304331701e-06, "loss": 0.5483, "step": 128270 }, { "epoch": 0.7625229595021131, "grad_norm": 6.512763977050781, "learning_rate": 9.916265494103144e-06, "loss": 0.6188, "step": 128280 }, { "epoch": 0.7625824015787815, "grad_norm": 5.854681491851807, "learning_rate": 9.916227675408193e-06, "loss": 0.6462, "step": 128290 }, { "epoch": 0.76264184365545, "grad_norm": 5.254304885864258, "learning_rate": 9.91618984824691e-06, "loss": 0.6243, "step": 128300 }, { "epoch": 0.7627012857321184, "grad_norm": 5.244870185852051, "learning_rate": 9.916152012619362e-06, "loss": 0.5916, "step": 128310 }, { "epoch": 0.7627607278087867, "grad_norm": 5.369816780090332, "learning_rate": 9.916114168525614e-06, "loss": 0.5863, "step": 128320 }, { "epoch": 0.7628201698854551, "grad_norm": 6.0921454429626465, "learning_rate": 9.91607631596573e-06, "loss": 0.5933, "step": 128330 }, { "epoch": 0.7628796119621235, "grad_norm": 4.177156448364258, "learning_rate": 9.916038454939778e-06, "loss": 0.5982, "step": 128340 }, { "epoch": 0.7629390540387919, "grad_norm": 5.345561504364014, "learning_rate": 9.91600058544782e-06, "loss": 0.5266, "step": 128350 }, { "epoch": 0.7629984961154603, "grad_norm": 5.068589687347412, "learning_rate": 9.915962707489923e-06, "loss": 0.5876, "step": 128360 }, { "epoch": 0.7630579381921286, "grad_norm": 6.1964802742004395, "learning_rate": 9.91592482106615e-06, "loss": 0.5731, "step": 128370 }, { "epoch": 0.763117380268797, "grad_norm": 5.0239434242248535, "learning_rate": 9.91588692617657e-06, "loss": 0.5653, "step": 128380 }, { "epoch": 0.7631768223454655, "grad_norm": 6.033409118652344, "learning_rate": 9.915849022821244e-06, "loss": 0.5642, "step": 128390 }, { "epoch": 0.7632362644221339, "grad_norm": 6.206507205963135, "learning_rate": 9.915811111000242e-06, "loss": 0.6035, "step": 128400 }, { "epoch": 0.7632957064988023, "grad_norm": 4.569718837738037, "learning_rate": 9.915773190713624e-06, "loss": 0.552, "step": 128410 }, { "epoch": 0.7633551485754706, "grad_norm": 5.652894496917725, "learning_rate": 9.91573526196146e-06, "loss": 0.5717, "step": 128420 }, { "epoch": 0.763414590652139, "grad_norm": 4.085958480834961, "learning_rate": 9.915697324743812e-06, "loss": 0.5824, "step": 128430 }, { "epoch": 0.7634740327288074, "grad_norm": 5.183709144592285, "learning_rate": 9.915659379060747e-06, "loss": 0.603, "step": 128440 }, { "epoch": 0.7635334748054758, "grad_norm": 5.65665864944458, "learning_rate": 9.915621424912331e-06, "loss": 0.5925, "step": 128450 }, { "epoch": 0.7635929168821441, "grad_norm": 6.046846389770508, "learning_rate": 9.915583462298628e-06, "loss": 0.616, "step": 128460 }, { "epoch": 0.7636523589588126, "grad_norm": 5.987410068511963, "learning_rate": 9.915545491219702e-06, "loss": 0.6008, "step": 128470 }, { "epoch": 0.763711801035481, "grad_norm": 5.656081676483154, "learning_rate": 9.915507511675623e-06, "loss": 0.6094, "step": 128480 }, { "epoch": 0.7637712431121494, "grad_norm": 4.300198078155518, "learning_rate": 9.915469523666453e-06, "loss": 0.585, "step": 128490 }, { "epoch": 0.7638306851888178, "grad_norm": 5.372154235839844, "learning_rate": 9.915431527192256e-06, "loss": 0.5588, "step": 128500 }, { "epoch": 0.7638901272654861, "grad_norm": 6.607896327972412, "learning_rate": 9.915393522253101e-06, "loss": 0.5984, "step": 128510 }, { "epoch": 0.7639495693421545, "grad_norm": 4.007928371429443, "learning_rate": 9.915355508849051e-06, "loss": 0.5496, "step": 128520 }, { "epoch": 0.7640090114188229, "grad_norm": 4.905040264129639, "learning_rate": 9.915317486980173e-06, "loss": 0.53, "step": 128530 }, { "epoch": 0.7640684534954914, "grad_norm": 5.845368385314941, "learning_rate": 9.915279456646532e-06, "loss": 0.6117, "step": 128540 }, { "epoch": 0.7641278955721597, "grad_norm": 6.782641410827637, "learning_rate": 9.915241417848192e-06, "loss": 0.5459, "step": 128550 }, { "epoch": 0.7641873376488281, "grad_norm": 7.542677879333496, "learning_rate": 9.91520337058522e-06, "loss": 0.6291, "step": 128560 }, { "epoch": 0.7642467797254965, "grad_norm": 6.241104602813721, "learning_rate": 9.915165314857682e-06, "loss": 0.5412, "step": 128570 }, { "epoch": 0.7643062218021649, "grad_norm": 4.5726141929626465, "learning_rate": 9.915127250665643e-06, "loss": 0.5289, "step": 128580 }, { "epoch": 0.7643656638788333, "grad_norm": 5.62125301361084, "learning_rate": 9.915089178009169e-06, "loss": 0.6028, "step": 128590 }, { "epoch": 0.7644251059555016, "grad_norm": 5.271373271942139, "learning_rate": 9.915051096888325e-06, "loss": 0.6314, "step": 128600 }, { "epoch": 0.76448454803217, "grad_norm": 6.11711311340332, "learning_rate": 9.915013007303175e-06, "loss": 0.5483, "step": 128610 }, { "epoch": 0.7645439901088384, "grad_norm": 5.119591236114502, "learning_rate": 9.914974909253787e-06, "loss": 0.5247, "step": 128620 }, { "epoch": 0.7646034321855069, "grad_norm": 5.070590496063232, "learning_rate": 9.914936802740225e-06, "loss": 0.593, "step": 128630 }, { "epoch": 0.7646628742621753, "grad_norm": 7.600163459777832, "learning_rate": 9.914898687762556e-06, "loss": 0.5411, "step": 128640 }, { "epoch": 0.7647223163388436, "grad_norm": 5.990108489990234, "learning_rate": 9.914860564320845e-06, "loss": 0.6176, "step": 128650 }, { "epoch": 0.764781758415512, "grad_norm": 5.182631492614746, "learning_rate": 9.914822432415158e-06, "loss": 0.5292, "step": 128660 }, { "epoch": 0.7648412004921804, "grad_norm": 5.292636394500732, "learning_rate": 9.91478429204556e-06, "loss": 0.5061, "step": 128670 }, { "epoch": 0.7649006425688488, "grad_norm": 5.878368854522705, "learning_rate": 9.914746143212117e-06, "loss": 0.66, "step": 128680 }, { "epoch": 0.7649600846455171, "grad_norm": 4.767308235168457, "learning_rate": 9.914707985914896e-06, "loss": 0.5688, "step": 128690 }, { "epoch": 0.7650195267221855, "grad_norm": 5.657899856567383, "learning_rate": 9.91466982015396e-06, "loss": 0.5856, "step": 128700 }, { "epoch": 0.765078968798854, "grad_norm": 5.16156530380249, "learning_rate": 9.914631645929375e-06, "loss": 0.5425, "step": 128710 }, { "epoch": 0.7651384108755224, "grad_norm": 6.170549392700195, "learning_rate": 9.914593463241212e-06, "loss": 0.5465, "step": 128720 }, { "epoch": 0.7651978529521908, "grad_norm": 4.878409385681152, "learning_rate": 9.914555272089529e-06, "loss": 0.5848, "step": 128730 }, { "epoch": 0.7652572950288591, "grad_norm": 5.029153347015381, "learning_rate": 9.914517072474397e-06, "loss": 0.5871, "step": 128740 }, { "epoch": 0.7653167371055275, "grad_norm": 6.143655776977539, "learning_rate": 9.914478864395879e-06, "loss": 0.5582, "step": 128750 }, { "epoch": 0.7653761791821959, "grad_norm": 5.689878463745117, "learning_rate": 9.914440647854043e-06, "loss": 0.6195, "step": 128760 }, { "epoch": 0.7654356212588643, "grad_norm": 4.335695743560791, "learning_rate": 9.914402422848954e-06, "loss": 0.5473, "step": 128770 }, { "epoch": 0.7654950633355327, "grad_norm": 7.581140995025635, "learning_rate": 9.914364189380676e-06, "loss": 0.5456, "step": 128780 }, { "epoch": 0.765554505412201, "grad_norm": 6.117726802825928, "learning_rate": 9.914325947449277e-06, "loss": 0.5669, "step": 128790 }, { "epoch": 0.7656139474888695, "grad_norm": 4.969337463378906, "learning_rate": 9.914287697054822e-06, "loss": 0.5793, "step": 128800 }, { "epoch": 0.7656733895655379, "grad_norm": 6.316833019256592, "learning_rate": 9.91424943819738e-06, "loss": 0.6287, "step": 128810 }, { "epoch": 0.7657328316422063, "grad_norm": 4.95894193649292, "learning_rate": 9.914211170877012e-06, "loss": 0.5823, "step": 128820 }, { "epoch": 0.7657922737188746, "grad_norm": 3.5199930667877197, "learning_rate": 9.914172895093787e-06, "loss": 0.5531, "step": 128830 }, { "epoch": 0.765851715795543, "grad_norm": 6.548641204833984, "learning_rate": 9.91413461084777e-06, "loss": 0.5647, "step": 128840 }, { "epoch": 0.7659111578722114, "grad_norm": 3.9841575622558594, "learning_rate": 9.914096318139025e-06, "loss": 0.5854, "step": 128850 }, { "epoch": 0.7659705999488798, "grad_norm": 5.869324684143066, "learning_rate": 9.91405801696762e-06, "loss": 0.579, "step": 128860 }, { "epoch": 0.7660300420255483, "grad_norm": 6.421248912811279, "learning_rate": 9.914019707333622e-06, "loss": 0.5286, "step": 128870 }, { "epoch": 0.7660894841022166, "grad_norm": 5.9048004150390625, "learning_rate": 9.913981389237096e-06, "loss": 0.5722, "step": 128880 }, { "epoch": 0.766148926178885, "grad_norm": 5.607983589172363, "learning_rate": 9.913943062678106e-06, "loss": 0.5668, "step": 128890 }, { "epoch": 0.7662083682555534, "grad_norm": 3.9254753589630127, "learning_rate": 9.913904727656722e-06, "loss": 0.5694, "step": 128900 }, { "epoch": 0.7662678103322218, "grad_norm": 6.830235004425049, "learning_rate": 9.913866384173007e-06, "loss": 0.644, "step": 128910 }, { "epoch": 0.7663272524088901, "grad_norm": 3.9273173809051514, "learning_rate": 9.913828032227027e-06, "loss": 0.5844, "step": 128920 }, { "epoch": 0.7663866944855585, "grad_norm": 4.596420764923096, "learning_rate": 9.913789671818849e-06, "loss": 0.5953, "step": 128930 }, { "epoch": 0.7664461365622269, "grad_norm": 4.379814624786377, "learning_rate": 9.91375130294854e-06, "loss": 0.5766, "step": 128940 }, { "epoch": 0.7665055786388953, "grad_norm": 5.8253493309021, "learning_rate": 9.913712925616164e-06, "loss": 0.5811, "step": 128950 }, { "epoch": 0.7665650207155638, "grad_norm": 6.701991081237793, "learning_rate": 9.913674539821787e-06, "loss": 0.6245, "step": 128960 }, { "epoch": 0.7666244627922321, "grad_norm": 7.684719085693359, "learning_rate": 9.913636145565478e-06, "loss": 0.565, "step": 128970 }, { "epoch": 0.7666839048689005, "grad_norm": 5.803584575653076, "learning_rate": 9.913597742847301e-06, "loss": 0.6375, "step": 128980 }, { "epoch": 0.7667433469455689, "grad_norm": 4.5177226066589355, "learning_rate": 9.91355933166732e-06, "loss": 0.5951, "step": 128990 }, { "epoch": 0.7668027890222373, "grad_norm": 5.343668460845947, "learning_rate": 9.913520912025606e-06, "loss": 0.5579, "step": 129000 }, { "epoch": 0.7668622310989057, "grad_norm": 4.710687160491943, "learning_rate": 9.913482483922223e-06, "loss": 0.5413, "step": 129010 }, { "epoch": 0.766921673175574, "grad_norm": 4.628380298614502, "learning_rate": 9.913444047357235e-06, "loss": 0.5564, "step": 129020 }, { "epoch": 0.7669811152522424, "grad_norm": 5.018571376800537, "learning_rate": 9.913405602330712e-06, "loss": 0.6149, "step": 129030 }, { "epoch": 0.7670405573289109, "grad_norm": 5.549525260925293, "learning_rate": 9.913367148842717e-06, "loss": 0.6427, "step": 129040 }, { "epoch": 0.7670999994055793, "grad_norm": 5.605025768280029, "learning_rate": 9.913328686893317e-06, "loss": 0.6209, "step": 129050 }, { "epoch": 0.7671594414822476, "grad_norm": 4.574085712432861, "learning_rate": 9.91329021648258e-06, "loss": 0.5436, "step": 129060 }, { "epoch": 0.767218883558916, "grad_norm": 6.639124870300293, "learning_rate": 9.913251737610571e-06, "loss": 0.6242, "step": 129070 }, { "epoch": 0.7672783256355844, "grad_norm": 6.29777717590332, "learning_rate": 9.913213250277356e-06, "loss": 0.6053, "step": 129080 }, { "epoch": 0.7673377677122528, "grad_norm": 5.963226318359375, "learning_rate": 9.913174754483001e-06, "loss": 0.566, "step": 129090 }, { "epoch": 0.7673972097889212, "grad_norm": 4.8034162521362305, "learning_rate": 9.913136250227575e-06, "loss": 0.5753, "step": 129100 }, { "epoch": 0.7674566518655895, "grad_norm": 5.0669989585876465, "learning_rate": 9.91309773751114e-06, "loss": 0.5099, "step": 129110 }, { "epoch": 0.767516093942258, "grad_norm": 4.675234317779541, "learning_rate": 9.913059216333764e-06, "loss": 0.5931, "step": 129120 }, { "epoch": 0.7675755360189264, "grad_norm": 3.6905808448791504, "learning_rate": 9.913020686695515e-06, "loss": 0.5718, "step": 129130 }, { "epoch": 0.7676349780955948, "grad_norm": 4.478488445281982, "learning_rate": 9.91298214859646e-06, "loss": 0.5984, "step": 129140 }, { "epoch": 0.7676944201722632, "grad_norm": 4.491474628448486, "learning_rate": 9.91294360203666e-06, "loss": 0.516, "step": 129150 }, { "epoch": 0.7677538622489315, "grad_norm": 5.406974792480469, "learning_rate": 9.912905047016187e-06, "loss": 0.5586, "step": 129160 }, { "epoch": 0.7678133043255999, "grad_norm": 5.348690032958984, "learning_rate": 9.912866483535104e-06, "loss": 0.6071, "step": 129170 }, { "epoch": 0.7678727464022683, "grad_norm": 6.612454414367676, "learning_rate": 9.91282791159348e-06, "loss": 0.5668, "step": 129180 }, { "epoch": 0.7679321884789367, "grad_norm": 4.4920477867126465, "learning_rate": 9.91278933119138e-06, "loss": 0.58, "step": 129190 }, { "epoch": 0.767991630555605, "grad_norm": 5.309528350830078, "learning_rate": 9.91275074232887e-06, "loss": 0.6291, "step": 129200 }, { "epoch": 0.7680510726322735, "grad_norm": 5.505432605743408, "learning_rate": 9.912712145006017e-06, "loss": 0.5041, "step": 129210 }, { "epoch": 0.7681105147089419, "grad_norm": 5.916388988494873, "learning_rate": 9.912673539222887e-06, "loss": 0.5999, "step": 129220 }, { "epoch": 0.7681699567856103, "grad_norm": 8.001189231872559, "learning_rate": 9.912634924979549e-06, "loss": 0.5708, "step": 129230 }, { "epoch": 0.7682293988622787, "grad_norm": 5.911001682281494, "learning_rate": 9.912596302276065e-06, "loss": 0.5124, "step": 129240 }, { "epoch": 0.768288840938947, "grad_norm": 5.303294658660889, "learning_rate": 9.912557671112506e-06, "loss": 0.6113, "step": 129250 }, { "epoch": 0.7683482830156154, "grad_norm": 5.328345775604248, "learning_rate": 9.912519031488937e-06, "loss": 0.6122, "step": 129260 }, { "epoch": 0.7684077250922838, "grad_norm": 7.043512344360352, "learning_rate": 9.912480383405422e-06, "loss": 0.6116, "step": 129270 }, { "epoch": 0.7684671671689522, "grad_norm": 5.04516077041626, "learning_rate": 9.91244172686203e-06, "loss": 0.6069, "step": 129280 }, { "epoch": 0.7685266092456206, "grad_norm": 5.158627986907959, "learning_rate": 9.912403061858828e-06, "loss": 0.6014, "step": 129290 }, { "epoch": 0.768586051322289, "grad_norm": 4.4345703125, "learning_rate": 9.91236438839588e-06, "loss": 0.5915, "step": 129300 }, { "epoch": 0.7686454933989574, "grad_norm": 5.543216705322266, "learning_rate": 9.912325706473257e-06, "loss": 0.5469, "step": 129310 }, { "epoch": 0.7687049354756258, "grad_norm": 5.904104232788086, "learning_rate": 9.912287016091022e-06, "loss": 0.5558, "step": 129320 }, { "epoch": 0.7687643775522942, "grad_norm": 4.825098514556885, "learning_rate": 9.912248317249242e-06, "loss": 0.5877, "step": 129330 }, { "epoch": 0.7688238196289625, "grad_norm": 4.762852668762207, "learning_rate": 9.912209609947984e-06, "loss": 0.5859, "step": 129340 }, { "epoch": 0.7688832617056309, "grad_norm": 5.963717937469482, "learning_rate": 9.912170894187318e-06, "loss": 0.6146, "step": 129350 }, { "epoch": 0.7689427037822993, "grad_norm": 6.478973388671875, "learning_rate": 9.912132169967305e-06, "loss": 0.5844, "step": 129360 }, { "epoch": 0.7690021458589678, "grad_norm": 5.252246379852295, "learning_rate": 9.912093437288013e-06, "loss": 0.5831, "step": 129370 }, { "epoch": 0.7690615879356362, "grad_norm": 6.389599800109863, "learning_rate": 9.912054696149514e-06, "loss": 0.6236, "step": 129380 }, { "epoch": 0.7691210300123045, "grad_norm": 3.89350962638855, "learning_rate": 9.912015946551867e-06, "loss": 0.5919, "step": 129390 }, { "epoch": 0.7691804720889729, "grad_norm": 4.644191265106201, "learning_rate": 9.911977188495142e-06, "loss": 0.5282, "step": 129400 }, { "epoch": 0.7692399141656413, "grad_norm": 5.976040840148926, "learning_rate": 9.91193842197941e-06, "loss": 0.5778, "step": 129410 }, { "epoch": 0.7692993562423097, "grad_norm": 3.952669382095337, "learning_rate": 9.911899647004732e-06, "loss": 0.5712, "step": 129420 }, { "epoch": 0.769358798318978, "grad_norm": 5.750949859619141, "learning_rate": 9.911860863571177e-06, "loss": 0.5531, "step": 129430 }, { "epoch": 0.7694182403956464, "grad_norm": 5.74146842956543, "learning_rate": 9.91182207167881e-06, "loss": 0.5599, "step": 129440 }, { "epoch": 0.7694776824723149, "grad_norm": 4.161533355712891, "learning_rate": 9.911783271327701e-06, "loss": 0.602, "step": 129450 }, { "epoch": 0.7695371245489833, "grad_norm": 6.526094436645508, "learning_rate": 9.911744462517915e-06, "loss": 0.581, "step": 129460 }, { "epoch": 0.7695965666256517, "grad_norm": 5.961822509765625, "learning_rate": 9.911705645249518e-06, "loss": 0.5563, "step": 129470 }, { "epoch": 0.76965600870232, "grad_norm": 5.999925136566162, "learning_rate": 9.911666819522578e-06, "loss": 0.6214, "step": 129480 }, { "epoch": 0.7697154507789884, "grad_norm": 4.515625476837158, "learning_rate": 9.911627985337163e-06, "loss": 0.5423, "step": 129490 }, { "epoch": 0.7697748928556568, "grad_norm": 6.803085803985596, "learning_rate": 9.911589142693339e-06, "loss": 0.5884, "step": 129500 }, { "epoch": 0.7698343349323252, "grad_norm": 4.480772972106934, "learning_rate": 9.91155029159117e-06, "loss": 0.5836, "step": 129510 }, { "epoch": 0.7698937770089936, "grad_norm": 5.192431926727295, "learning_rate": 9.911511432030727e-06, "loss": 0.558, "step": 129520 }, { "epoch": 0.7699532190856619, "grad_norm": 6.347080707550049, "learning_rate": 9.911472564012075e-06, "loss": 0.6148, "step": 129530 }, { "epoch": 0.7700126611623304, "grad_norm": 5.47247314453125, "learning_rate": 9.91143368753528e-06, "loss": 0.5958, "step": 129540 }, { "epoch": 0.7700721032389988, "grad_norm": 5.104357719421387, "learning_rate": 9.911394802600411e-06, "loss": 0.6126, "step": 129550 }, { "epoch": 0.7701315453156672, "grad_norm": 5.530714511871338, "learning_rate": 9.911355909207534e-06, "loss": 0.5635, "step": 129560 }, { "epoch": 0.7701909873923355, "grad_norm": 7.295135974884033, "learning_rate": 9.911317007356718e-06, "loss": 0.5849, "step": 129570 }, { "epoch": 0.7702504294690039, "grad_norm": 5.123217582702637, "learning_rate": 9.911278097048027e-06, "loss": 0.5251, "step": 129580 }, { "epoch": 0.7703098715456723, "grad_norm": 5.375669002532959, "learning_rate": 9.911239178281527e-06, "loss": 0.6077, "step": 129590 }, { "epoch": 0.7703693136223407, "grad_norm": 4.707248210906982, "learning_rate": 9.911200251057288e-06, "loss": 0.6009, "step": 129600 }, { "epoch": 0.7704287556990091, "grad_norm": 6.233954429626465, "learning_rate": 9.911161315375378e-06, "loss": 0.6108, "step": 129610 }, { "epoch": 0.7704881977756775, "grad_norm": 4.603982448577881, "learning_rate": 9.911122371235861e-06, "loss": 0.5901, "step": 129620 }, { "epoch": 0.7705476398523459, "grad_norm": 5.035426139831543, "learning_rate": 9.911083418638806e-06, "loss": 0.5919, "step": 129630 }, { "epoch": 0.7706070819290143, "grad_norm": 4.6923723220825195, "learning_rate": 9.911044457584279e-06, "loss": 0.496, "step": 129640 }, { "epoch": 0.7706665240056827, "grad_norm": 6.176929950714111, "learning_rate": 9.911005488072347e-06, "loss": 0.5628, "step": 129650 }, { "epoch": 0.770725966082351, "grad_norm": 4.507157802581787, "learning_rate": 9.910966510103077e-06, "loss": 0.5566, "step": 129660 }, { "epoch": 0.7707854081590194, "grad_norm": 5.367611408233643, "learning_rate": 9.910927523676538e-06, "loss": 0.5752, "step": 129670 }, { "epoch": 0.7708448502356878, "grad_norm": 7.638058185577393, "learning_rate": 9.910888528792795e-06, "loss": 0.5995, "step": 129680 }, { "epoch": 0.7709042923123562, "grad_norm": 5.979987621307373, "learning_rate": 9.910849525451918e-06, "loss": 0.5816, "step": 129690 }, { "epoch": 0.7709637343890247, "grad_norm": 6.030496597290039, "learning_rate": 9.91081051365397e-06, "loss": 0.5418, "step": 129700 }, { "epoch": 0.771023176465693, "grad_norm": 6.316947937011719, "learning_rate": 9.91077149339902e-06, "loss": 0.5261, "step": 129710 }, { "epoch": 0.7710826185423614, "grad_norm": 4.649977207183838, "learning_rate": 9.910732464687138e-06, "loss": 0.5719, "step": 129720 }, { "epoch": 0.7711420606190298, "grad_norm": 5.91312837600708, "learning_rate": 9.910693427518387e-06, "loss": 0.4922, "step": 129730 }, { "epoch": 0.7712015026956982, "grad_norm": 4.668306350708008, "learning_rate": 9.910654381892837e-06, "loss": 0.5233, "step": 129740 }, { "epoch": 0.7712609447723666, "grad_norm": 5.409908771514893, "learning_rate": 9.910615327810552e-06, "loss": 0.5546, "step": 129750 }, { "epoch": 0.7713203868490349, "grad_norm": 5.59613037109375, "learning_rate": 9.910576265271604e-06, "loss": 0.5536, "step": 129760 }, { "epoch": 0.7713798289257033, "grad_norm": 4.403682231903076, "learning_rate": 9.910537194276055e-06, "loss": 0.5786, "step": 129770 }, { "epoch": 0.7714392710023718, "grad_norm": 6.094002723693848, "learning_rate": 9.910498114823978e-06, "loss": 0.553, "step": 129780 }, { "epoch": 0.7714987130790402, "grad_norm": 6.420748710632324, "learning_rate": 9.910459026915435e-06, "loss": 0.5668, "step": 129790 }, { "epoch": 0.7715581551557085, "grad_norm": 7.531881809234619, "learning_rate": 9.910419930550497e-06, "loss": 0.6138, "step": 129800 }, { "epoch": 0.7716175972323769, "grad_norm": 4.789866924285889, "learning_rate": 9.91038082572923e-06, "loss": 0.5835, "step": 129810 }, { "epoch": 0.7716770393090453, "grad_norm": 5.658304691314697, "learning_rate": 9.9103417124517e-06, "loss": 0.6762, "step": 129820 }, { "epoch": 0.7717364813857137, "grad_norm": 5.2395243644714355, "learning_rate": 9.910302590717977e-06, "loss": 0.5806, "step": 129830 }, { "epoch": 0.7717959234623821, "grad_norm": 5.899226188659668, "learning_rate": 9.910263460528127e-06, "loss": 0.5683, "step": 129840 }, { "epoch": 0.7718553655390504, "grad_norm": 5.259716987609863, "learning_rate": 9.910224321882218e-06, "loss": 0.5694, "step": 129850 }, { "epoch": 0.7719148076157188, "grad_norm": 6.448437213897705, "learning_rate": 9.910185174780315e-06, "loss": 0.5711, "step": 129860 }, { "epoch": 0.7719742496923873, "grad_norm": 5.901859760284424, "learning_rate": 9.910146019222489e-06, "loss": 0.6038, "step": 129870 }, { "epoch": 0.7720336917690557, "grad_norm": 5.000924587249756, "learning_rate": 9.910106855208806e-06, "loss": 0.5845, "step": 129880 }, { "epoch": 0.7720931338457241, "grad_norm": 6.679036617279053, "learning_rate": 9.91006768273933e-06, "loss": 0.6145, "step": 129890 }, { "epoch": 0.7721525759223924, "grad_norm": 4.625461578369141, "learning_rate": 9.910028501814136e-06, "loss": 0.6006, "step": 129900 }, { "epoch": 0.7722120179990608, "grad_norm": 4.569849491119385, "learning_rate": 9.909989312433283e-06, "loss": 0.6206, "step": 129910 }, { "epoch": 0.7722714600757292, "grad_norm": 4.7682929039001465, "learning_rate": 9.909950114596844e-06, "loss": 0.6016, "step": 129920 }, { "epoch": 0.7723309021523976, "grad_norm": 6.265868663787842, "learning_rate": 9.909910908304887e-06, "loss": 0.5506, "step": 129930 }, { "epoch": 0.7723903442290659, "grad_norm": 5.809301853179932, "learning_rate": 9.909871693557476e-06, "loss": 0.5567, "step": 129940 }, { "epoch": 0.7724497863057344, "grad_norm": 6.874795436859131, "learning_rate": 9.909832470354679e-06, "loss": 0.5674, "step": 129950 }, { "epoch": 0.7725092283824028, "grad_norm": 4.45604944229126, "learning_rate": 9.909793238696565e-06, "loss": 0.5696, "step": 129960 }, { "epoch": 0.7725686704590712, "grad_norm": 6.590252876281738, "learning_rate": 9.909753998583202e-06, "loss": 0.5934, "step": 129970 }, { "epoch": 0.7726281125357396, "grad_norm": 5.660629749298096, "learning_rate": 9.909714750014657e-06, "loss": 0.61, "step": 129980 }, { "epoch": 0.7726875546124079, "grad_norm": 5.5164899826049805, "learning_rate": 9.909675492990998e-06, "loss": 0.5943, "step": 129990 }, { "epoch": 0.7727469966890763, "grad_norm": 5.201293468475342, "learning_rate": 9.90963622751229e-06, "loss": 0.5723, "step": 130000 }, { "epoch": 0.7728064387657447, "grad_norm": 5.033498287200928, "learning_rate": 9.909596953578604e-06, "loss": 0.5466, "step": 130010 }, { "epoch": 0.7728658808424131, "grad_norm": 6.060461044311523, "learning_rate": 9.909557671190007e-06, "loss": 0.5933, "step": 130020 }, { "epoch": 0.7729253229190814, "grad_norm": 4.7457051277160645, "learning_rate": 9.909518380346563e-06, "loss": 0.5954, "step": 130030 }, { "epoch": 0.7729847649957499, "grad_norm": 4.424848556518555, "learning_rate": 9.909479081048346e-06, "loss": 0.5838, "step": 130040 }, { "epoch": 0.7730442070724183, "grad_norm": 5.464179039001465, "learning_rate": 9.909439773295418e-06, "loss": 0.649, "step": 130050 }, { "epoch": 0.7731036491490867, "grad_norm": 5.263704776763916, "learning_rate": 9.90940045708785e-06, "loss": 0.5305, "step": 130060 }, { "epoch": 0.7731630912257551, "grad_norm": 6.3459367752075195, "learning_rate": 9.909361132425707e-06, "loss": 0.5788, "step": 130070 }, { "epoch": 0.7732225333024234, "grad_norm": 3.693852424621582, "learning_rate": 9.909321799309059e-06, "loss": 0.5929, "step": 130080 }, { "epoch": 0.7732819753790918, "grad_norm": 5.447342872619629, "learning_rate": 9.909282457737974e-06, "loss": 0.547, "step": 130090 }, { "epoch": 0.7733414174557602, "grad_norm": 5.5854716300964355, "learning_rate": 9.909243107712519e-06, "loss": 0.5924, "step": 130100 }, { "epoch": 0.7734008595324287, "grad_norm": 4.639673233032227, "learning_rate": 9.909203749232761e-06, "loss": 0.5543, "step": 130110 }, { "epoch": 0.7734603016090971, "grad_norm": 4.764833450317383, "learning_rate": 9.909164382298768e-06, "loss": 0.6491, "step": 130120 }, { "epoch": 0.7735197436857654, "grad_norm": 4.158556938171387, "learning_rate": 9.90912500691061e-06, "loss": 0.5675, "step": 130130 }, { "epoch": 0.7735791857624338, "grad_norm": 7.583756923675537, "learning_rate": 9.909085623068351e-06, "loss": 0.6321, "step": 130140 }, { "epoch": 0.7736386278391022, "grad_norm": 6.957985877990723, "learning_rate": 9.909046230772062e-06, "loss": 0.5579, "step": 130150 }, { "epoch": 0.7736980699157706, "grad_norm": 5.8327956199646, "learning_rate": 9.909006830021808e-06, "loss": 0.6444, "step": 130160 }, { "epoch": 0.7737575119924389, "grad_norm": 5.044689178466797, "learning_rate": 9.908967420817658e-06, "loss": 0.5381, "step": 130170 }, { "epoch": 0.7738169540691073, "grad_norm": 4.468857765197754, "learning_rate": 9.908928003159683e-06, "loss": 0.5386, "step": 130180 }, { "epoch": 0.7738763961457757, "grad_norm": 5.87141227722168, "learning_rate": 9.908888577047948e-06, "loss": 0.6336, "step": 130190 }, { "epoch": 0.7739358382224442, "grad_norm": 5.816827297210693, "learning_rate": 9.908849142482519e-06, "loss": 0.6302, "step": 130200 }, { "epoch": 0.7739952802991126, "grad_norm": 6.0615668296813965, "learning_rate": 9.908809699463469e-06, "loss": 0.5661, "step": 130210 }, { "epoch": 0.7740547223757809, "grad_norm": 5.286759376525879, "learning_rate": 9.908770247990861e-06, "loss": 0.5782, "step": 130220 }, { "epoch": 0.7741141644524493, "grad_norm": 5.554325103759766, "learning_rate": 9.908730788064766e-06, "loss": 0.5952, "step": 130230 }, { "epoch": 0.7741736065291177, "grad_norm": 3.980083465576172, "learning_rate": 9.90869131968525e-06, "loss": 0.5425, "step": 130240 }, { "epoch": 0.7742330486057861, "grad_norm": 5.564845085144043, "learning_rate": 9.908651842852382e-06, "loss": 0.5839, "step": 130250 }, { "epoch": 0.7742924906824545, "grad_norm": 6.892285346984863, "learning_rate": 9.908612357566229e-06, "loss": 0.562, "step": 130260 }, { "epoch": 0.7743519327591228, "grad_norm": 6.576438903808594, "learning_rate": 9.908572863826862e-06, "loss": 0.5396, "step": 130270 }, { "epoch": 0.7744113748357913, "grad_norm": 6.28294563293457, "learning_rate": 9.908533361634344e-06, "loss": 0.6179, "step": 130280 }, { "epoch": 0.7744708169124597, "grad_norm": 5.379392623901367, "learning_rate": 9.908493850988748e-06, "loss": 0.5573, "step": 130290 }, { "epoch": 0.7745302589891281, "grad_norm": 6.147831439971924, "learning_rate": 9.90845433189014e-06, "loss": 0.6547, "step": 130300 }, { "epoch": 0.7745897010657964, "grad_norm": 4.807375907897949, "learning_rate": 9.908414804338587e-06, "loss": 0.561, "step": 130310 }, { "epoch": 0.7746491431424648, "grad_norm": 4.472952365875244, "learning_rate": 9.908375268334159e-06, "loss": 0.5519, "step": 130320 }, { "epoch": 0.7747085852191332, "grad_norm": 5.221214771270752, "learning_rate": 9.908335723876922e-06, "loss": 0.6418, "step": 130330 }, { "epoch": 0.7747680272958016, "grad_norm": 5.352381229400635, "learning_rate": 9.908296170966945e-06, "loss": 0.6219, "step": 130340 }, { "epoch": 0.77482746937247, "grad_norm": 5.6736907958984375, "learning_rate": 9.908256609604297e-06, "loss": 0.5978, "step": 130350 }, { "epoch": 0.7748869114491383, "grad_norm": 5.913435935974121, "learning_rate": 9.908217039789047e-06, "loss": 0.6385, "step": 130360 }, { "epoch": 0.7749463535258068, "grad_norm": 5.418887138366699, "learning_rate": 9.90817746152126e-06, "loss": 0.5394, "step": 130370 }, { "epoch": 0.7750057956024752, "grad_norm": 6.0075273513793945, "learning_rate": 9.908137874801005e-06, "loss": 0.5768, "step": 130380 }, { "epoch": 0.7750652376791436, "grad_norm": 4.230859756469727, "learning_rate": 9.908098279628353e-06, "loss": 0.5819, "step": 130390 }, { "epoch": 0.7751246797558119, "grad_norm": 5.016305923461914, "learning_rate": 9.908058676003369e-06, "loss": 0.634, "step": 130400 }, { "epoch": 0.7751841218324803, "grad_norm": 5.118729591369629, "learning_rate": 9.908019063926121e-06, "loss": 0.6076, "step": 130410 }, { "epoch": 0.7752435639091487, "grad_norm": 5.014538288116455, "learning_rate": 9.90797944339668e-06, "loss": 0.5844, "step": 130420 }, { "epoch": 0.7753030059858171, "grad_norm": 4.8957719802856445, "learning_rate": 9.907939814415113e-06, "loss": 0.5707, "step": 130430 }, { "epoch": 0.7753624480624856, "grad_norm": 5.076035976409912, "learning_rate": 9.907900176981489e-06, "loss": 0.6054, "step": 130440 }, { "epoch": 0.7754218901391539, "grad_norm": 4.783014297485352, "learning_rate": 9.907860531095875e-06, "loss": 0.5828, "step": 130450 }, { "epoch": 0.7754813322158223, "grad_norm": 4.259759902954102, "learning_rate": 9.907820876758337e-06, "loss": 0.5484, "step": 130460 }, { "epoch": 0.7755407742924907, "grad_norm": 5.457671642303467, "learning_rate": 9.907781213968947e-06, "loss": 0.5948, "step": 130470 }, { "epoch": 0.7756002163691591, "grad_norm": 5.558635711669922, "learning_rate": 9.907741542727774e-06, "loss": 0.6075, "step": 130480 }, { "epoch": 0.7756596584458275, "grad_norm": 6.4300713539123535, "learning_rate": 9.907701863034881e-06, "loss": 0.5705, "step": 130490 }, { "epoch": 0.7757191005224958, "grad_norm": 5.701992988586426, "learning_rate": 9.907662174890343e-06, "loss": 0.56, "step": 130500 }, { "epoch": 0.7757785425991642, "grad_norm": 5.77962064743042, "learning_rate": 9.907622478294225e-06, "loss": 0.6075, "step": 130510 }, { "epoch": 0.7758379846758326, "grad_norm": 4.051197528839111, "learning_rate": 9.907582773246593e-06, "loss": 0.5498, "step": 130520 }, { "epoch": 0.7758974267525011, "grad_norm": 5.332832336425781, "learning_rate": 9.907543059747521e-06, "loss": 0.6058, "step": 130530 }, { "epoch": 0.7759568688291694, "grad_norm": 5.396032810211182, "learning_rate": 9.907503337797073e-06, "loss": 0.6637, "step": 130540 }, { "epoch": 0.7760163109058378, "grad_norm": 4.578145980834961, "learning_rate": 9.907463607395317e-06, "loss": 0.5447, "step": 130550 }, { "epoch": 0.7760757529825062, "grad_norm": 6.91329288482666, "learning_rate": 9.907423868542325e-06, "loss": 0.5913, "step": 130560 }, { "epoch": 0.7761351950591746, "grad_norm": 5.715715408325195, "learning_rate": 9.907384121238164e-06, "loss": 0.6419, "step": 130570 }, { "epoch": 0.776194637135843, "grad_norm": 4.6617751121521, "learning_rate": 9.9073443654829e-06, "loss": 0.5373, "step": 130580 }, { "epoch": 0.7762540792125113, "grad_norm": 5.226877689361572, "learning_rate": 9.907304601276605e-06, "loss": 0.6266, "step": 130590 }, { "epoch": 0.7763135212891797, "grad_norm": 5.382115364074707, "learning_rate": 9.907264828619346e-06, "loss": 0.6023, "step": 130600 }, { "epoch": 0.7763729633658482, "grad_norm": 6.810177803039551, "learning_rate": 9.907225047511192e-06, "loss": 0.5515, "step": 130610 }, { "epoch": 0.7764324054425166, "grad_norm": 6.6211347579956055, "learning_rate": 9.90718525795221e-06, "loss": 0.5987, "step": 130620 }, { "epoch": 0.776491847519185, "grad_norm": 4.773151874542236, "learning_rate": 9.907145459942468e-06, "loss": 0.5635, "step": 130630 }, { "epoch": 0.7765512895958533, "grad_norm": 4.308084964752197, "learning_rate": 9.907105653482038e-06, "loss": 0.5563, "step": 130640 }, { "epoch": 0.7766107316725217, "grad_norm": 7.731364727020264, "learning_rate": 9.907065838570986e-06, "loss": 0.5648, "step": 130650 }, { "epoch": 0.7766701737491901, "grad_norm": 5.271153926849365, "learning_rate": 9.907026015209383e-06, "loss": 0.6277, "step": 130660 }, { "epoch": 0.7767296158258585, "grad_norm": 5.220041751861572, "learning_rate": 9.906986183397292e-06, "loss": 0.5989, "step": 130670 }, { "epoch": 0.7767890579025268, "grad_norm": 8.062966346740723, "learning_rate": 9.906946343134788e-06, "loss": 0.5857, "step": 130680 }, { "epoch": 0.7768484999791953, "grad_norm": 5.440650939941406, "learning_rate": 9.906906494421937e-06, "loss": 0.5602, "step": 130690 }, { "epoch": 0.7769079420558637, "grad_norm": 4.675986289978027, "learning_rate": 9.906866637258806e-06, "loss": 0.5546, "step": 130700 }, { "epoch": 0.7769673841325321, "grad_norm": 6.416824817657471, "learning_rate": 9.906826771645466e-06, "loss": 0.6523, "step": 130710 }, { "epoch": 0.7770268262092005, "grad_norm": 4.604033946990967, "learning_rate": 9.906786897581984e-06, "loss": 0.6218, "step": 130720 }, { "epoch": 0.7770862682858688, "grad_norm": 5.723568916320801, "learning_rate": 9.90674701506843e-06, "loss": 0.5849, "step": 130730 }, { "epoch": 0.7771457103625372, "grad_norm": 6.094781398773193, "learning_rate": 9.906707124104872e-06, "loss": 0.6249, "step": 130740 }, { "epoch": 0.7772051524392056, "grad_norm": 6.845878601074219, "learning_rate": 9.90666722469138e-06, "loss": 0.5826, "step": 130750 }, { "epoch": 0.777264594515874, "grad_norm": 5.097360134124756, "learning_rate": 9.90662731682802e-06, "loss": 0.5557, "step": 130760 }, { "epoch": 0.7773240365925423, "grad_norm": 6.359551906585693, "learning_rate": 9.906587400514862e-06, "loss": 0.6458, "step": 130770 }, { "epoch": 0.7773834786692108, "grad_norm": 6.471862316131592, "learning_rate": 9.906547475751977e-06, "loss": 0.5771, "step": 130780 }, { "epoch": 0.7774429207458792, "grad_norm": 6.965073585510254, "learning_rate": 9.906507542539432e-06, "loss": 0.5218, "step": 130790 }, { "epoch": 0.7775023628225476, "grad_norm": 5.687336444854736, "learning_rate": 9.906467600877294e-06, "loss": 0.5843, "step": 130800 }, { "epoch": 0.777561804899216, "grad_norm": 4.855950832366943, "learning_rate": 9.906427650765633e-06, "loss": 0.6223, "step": 130810 }, { "epoch": 0.7776212469758843, "grad_norm": 5.184460639953613, "learning_rate": 9.90638769220452e-06, "loss": 0.6059, "step": 130820 }, { "epoch": 0.7776806890525527, "grad_norm": 4.800637722015381, "learning_rate": 9.906347725194021e-06, "loss": 0.6379, "step": 130830 }, { "epoch": 0.7777401311292211, "grad_norm": 5.224064826965332, "learning_rate": 9.906307749734206e-06, "loss": 0.6012, "step": 130840 }, { "epoch": 0.7777995732058895, "grad_norm": 5.945676326751709, "learning_rate": 9.906267765825144e-06, "loss": 0.5662, "step": 130850 }, { "epoch": 0.777859015282558, "grad_norm": 5.456455707550049, "learning_rate": 9.906227773466901e-06, "loss": 0.5346, "step": 130860 }, { "epoch": 0.7779184573592263, "grad_norm": 4.512068271636963, "learning_rate": 9.906187772659551e-06, "loss": 0.5254, "step": 130870 }, { "epoch": 0.7779778994358947, "grad_norm": 5.0761823654174805, "learning_rate": 9.90614776340316e-06, "loss": 0.5948, "step": 130880 }, { "epoch": 0.7780373415125631, "grad_norm": 6.035763740539551, "learning_rate": 9.906107745697797e-06, "loss": 0.5253, "step": 130890 }, { "epoch": 0.7780967835892315, "grad_norm": 4.3048505783081055, "learning_rate": 9.906067719543531e-06, "loss": 0.5713, "step": 130900 }, { "epoch": 0.7781562256658998, "grad_norm": 4.150659561157227, "learning_rate": 9.90602768494043e-06, "loss": 0.5582, "step": 130910 }, { "epoch": 0.7782156677425682, "grad_norm": 3.8647046089172363, "learning_rate": 9.905987641888565e-06, "loss": 0.5511, "step": 130920 }, { "epoch": 0.7782751098192366, "grad_norm": 4.232579708099365, "learning_rate": 9.905947590388003e-06, "loss": 0.6084, "step": 130930 }, { "epoch": 0.7783345518959051, "grad_norm": 5.520262241363525, "learning_rate": 9.905907530438815e-06, "loss": 0.5069, "step": 130940 }, { "epoch": 0.7783939939725735, "grad_norm": 6.363152980804443, "learning_rate": 9.90586746204107e-06, "loss": 0.6475, "step": 130950 }, { "epoch": 0.7784534360492418, "grad_norm": 6.787142753601074, "learning_rate": 9.905827385194833e-06, "loss": 0.5658, "step": 130960 }, { "epoch": 0.7785128781259102, "grad_norm": 4.5678582191467285, "learning_rate": 9.905787299900177e-06, "loss": 0.5997, "step": 130970 }, { "epoch": 0.7785723202025786, "grad_norm": 4.8187055587768555, "learning_rate": 9.90574720615717e-06, "loss": 0.5319, "step": 130980 }, { "epoch": 0.778631762279247, "grad_norm": 6.418127059936523, "learning_rate": 9.905707103965881e-06, "loss": 0.5775, "step": 130990 }, { "epoch": 0.7786912043559153, "grad_norm": 5.553906440734863, "learning_rate": 9.905666993326379e-06, "loss": 0.5708, "step": 131000 }, { "epoch": 0.7787506464325837, "grad_norm": 4.68253231048584, "learning_rate": 9.905626874238734e-06, "loss": 0.5751, "step": 131010 }, { "epoch": 0.7788100885092522, "grad_norm": 5.268126964569092, "learning_rate": 9.905586746703013e-06, "loss": 0.6062, "step": 131020 }, { "epoch": 0.7788695305859206, "grad_norm": 5.33479118347168, "learning_rate": 9.905546610719287e-06, "loss": 0.5668, "step": 131030 }, { "epoch": 0.778928972662589, "grad_norm": 4.8329644203186035, "learning_rate": 9.905506466287624e-06, "loss": 0.5552, "step": 131040 }, { "epoch": 0.7789884147392573, "grad_norm": 4.90134859085083, "learning_rate": 9.905466313408095e-06, "loss": 0.5681, "step": 131050 }, { "epoch": 0.7790478568159257, "grad_norm": 5.871248245239258, "learning_rate": 9.905426152080766e-06, "loss": 0.5701, "step": 131060 }, { "epoch": 0.7791072988925941, "grad_norm": 4.617182731628418, "learning_rate": 9.905385982305707e-06, "loss": 0.6257, "step": 131070 }, { "epoch": 0.7791667409692625, "grad_norm": 4.730215072631836, "learning_rate": 9.90534580408299e-06, "loss": 0.5393, "step": 131080 }, { "epoch": 0.7792261830459309, "grad_norm": 4.514323711395264, "learning_rate": 9.90530561741268e-06, "loss": 0.5781, "step": 131090 }, { "epoch": 0.7792856251225992, "grad_norm": 5.345319747924805, "learning_rate": 9.905265422294851e-06, "loss": 0.5962, "step": 131100 }, { "epoch": 0.7793450671992677, "grad_norm": 5.3352227210998535, "learning_rate": 9.905225218729568e-06, "loss": 0.6226, "step": 131110 }, { "epoch": 0.7794045092759361, "grad_norm": 5.1758809089660645, "learning_rate": 9.905185006716902e-06, "loss": 0.5115, "step": 131120 }, { "epoch": 0.7794639513526045, "grad_norm": 6.7724151611328125, "learning_rate": 9.905144786256924e-06, "loss": 0.6435, "step": 131130 }, { "epoch": 0.7795233934292728, "grad_norm": 4.828315734863281, "learning_rate": 9.905104557349699e-06, "loss": 0.5713, "step": 131140 }, { "epoch": 0.7795828355059412, "grad_norm": 6.153955459594727, "learning_rate": 9.9050643199953e-06, "loss": 0.5824, "step": 131150 }, { "epoch": 0.7796422775826096, "grad_norm": 4.438149452209473, "learning_rate": 9.905024074193794e-06, "loss": 0.5706, "step": 131160 }, { "epoch": 0.779701719659278, "grad_norm": 4.740310192108154, "learning_rate": 9.904983819945253e-06, "loss": 0.6041, "step": 131170 }, { "epoch": 0.7797611617359465, "grad_norm": 4.21955680847168, "learning_rate": 9.904943557249744e-06, "loss": 0.5964, "step": 131180 }, { "epoch": 0.7798206038126148, "grad_norm": 4.167425155639648, "learning_rate": 9.904903286107335e-06, "loss": 0.5444, "step": 131190 }, { "epoch": 0.7798800458892832, "grad_norm": 6.780086517333984, "learning_rate": 9.9048630065181e-06, "loss": 0.5565, "step": 131200 }, { "epoch": 0.7799394879659516, "grad_norm": 6.015445232391357, "learning_rate": 9.904822718482103e-06, "loss": 0.6116, "step": 131210 }, { "epoch": 0.77999893004262, "grad_norm": 5.282679557800293, "learning_rate": 9.904782421999419e-06, "loss": 0.5973, "step": 131220 }, { "epoch": 0.7800583721192884, "grad_norm": 5.507437229156494, "learning_rate": 9.904742117070113e-06, "loss": 0.5753, "step": 131230 }, { "epoch": 0.7801178141959567, "grad_norm": 5.170536994934082, "learning_rate": 9.904701803694254e-06, "loss": 0.5854, "step": 131240 }, { "epoch": 0.7801772562726251, "grad_norm": 5.7985520362854, "learning_rate": 9.904661481871916e-06, "loss": 0.5673, "step": 131250 }, { "epoch": 0.7802366983492935, "grad_norm": 4.193015098571777, "learning_rate": 9.904621151603164e-06, "loss": 0.6117, "step": 131260 }, { "epoch": 0.780296140425962, "grad_norm": 6.283864498138428, "learning_rate": 9.904580812888072e-06, "loss": 0.6293, "step": 131270 }, { "epoch": 0.7803555825026303, "grad_norm": 5.349395275115967, "learning_rate": 9.904540465726705e-06, "loss": 0.5881, "step": 131280 }, { "epoch": 0.7804150245792987, "grad_norm": 6.841040134429932, "learning_rate": 9.904500110119133e-06, "loss": 0.5896, "step": 131290 }, { "epoch": 0.7804744666559671, "grad_norm": 5.283173561096191, "learning_rate": 9.904459746065427e-06, "loss": 0.609, "step": 131300 }, { "epoch": 0.7805339087326355, "grad_norm": 6.411281585693359, "learning_rate": 9.904419373565657e-06, "loss": 0.6212, "step": 131310 }, { "epoch": 0.7805933508093039, "grad_norm": 5.048676013946533, "learning_rate": 9.90437899261989e-06, "loss": 0.61, "step": 131320 }, { "epoch": 0.7806527928859722, "grad_norm": 5.739118576049805, "learning_rate": 9.904338603228198e-06, "loss": 0.5844, "step": 131330 }, { "epoch": 0.7807122349626406, "grad_norm": 4.070899486541748, "learning_rate": 9.90429820539065e-06, "loss": 0.5731, "step": 131340 }, { "epoch": 0.780771677039309, "grad_norm": 5.843418598175049, "learning_rate": 9.904257799107315e-06, "loss": 0.6055, "step": 131350 }, { "epoch": 0.7808311191159775, "grad_norm": 4.270909786224365, "learning_rate": 9.904217384378263e-06, "loss": 0.5029, "step": 131360 }, { "epoch": 0.7808905611926458, "grad_norm": 6.437560081481934, "learning_rate": 9.904176961203565e-06, "loss": 0.6132, "step": 131370 }, { "epoch": 0.7809500032693142, "grad_norm": 5.935853004455566, "learning_rate": 9.904136529583289e-06, "loss": 0.5697, "step": 131380 }, { "epoch": 0.7810094453459826, "grad_norm": 5.172301769256592, "learning_rate": 9.904096089517503e-06, "loss": 0.5896, "step": 131390 }, { "epoch": 0.781068887422651, "grad_norm": 5.610812187194824, "learning_rate": 9.904055641006278e-06, "loss": 0.5686, "step": 131400 }, { "epoch": 0.7811283294993194, "grad_norm": 4.494260311126709, "learning_rate": 9.904015184049685e-06, "loss": 0.5566, "step": 131410 }, { "epoch": 0.7811877715759877, "grad_norm": 6.486403942108154, "learning_rate": 9.903974718647793e-06, "loss": 0.6446, "step": 131420 }, { "epoch": 0.7812472136526561, "grad_norm": 5.218194961547852, "learning_rate": 9.903934244800672e-06, "loss": 0.5413, "step": 131430 }, { "epoch": 0.7813066557293246, "grad_norm": 5.061139106750488, "learning_rate": 9.90389376250839e-06, "loss": 0.6064, "step": 131440 }, { "epoch": 0.781366097805993, "grad_norm": 4.81942081451416, "learning_rate": 9.903853271771017e-06, "loss": 0.5815, "step": 131450 }, { "epoch": 0.7814255398826614, "grad_norm": 5.830207347869873, "learning_rate": 9.903812772588625e-06, "loss": 0.5242, "step": 131460 }, { "epoch": 0.7814849819593297, "grad_norm": 5.1577558517456055, "learning_rate": 9.903772264961283e-06, "loss": 0.5944, "step": 131470 }, { "epoch": 0.7815444240359981, "grad_norm": 4.020676136016846, "learning_rate": 9.903731748889059e-06, "loss": 0.5403, "step": 131480 }, { "epoch": 0.7816038661126665, "grad_norm": 4.6546101570129395, "learning_rate": 9.903691224372023e-06, "loss": 0.5668, "step": 131490 }, { "epoch": 0.7816633081893349, "grad_norm": 6.674149990081787, "learning_rate": 9.903650691410247e-06, "loss": 0.6106, "step": 131500 }, { "epoch": 0.7817227502660032, "grad_norm": 6.3346428871154785, "learning_rate": 9.903610150003799e-06, "loss": 0.5813, "step": 131510 }, { "epoch": 0.7817821923426717, "grad_norm": 5.872952938079834, "learning_rate": 9.90356960015275e-06, "loss": 0.6212, "step": 131520 }, { "epoch": 0.7818416344193401, "grad_norm": 4.760234355926514, "learning_rate": 9.903529041857167e-06, "loss": 0.6034, "step": 131530 }, { "epoch": 0.7819010764960085, "grad_norm": 6.640575408935547, "learning_rate": 9.903488475117123e-06, "loss": 0.6029, "step": 131540 }, { "epoch": 0.7819605185726769, "grad_norm": 5.077091217041016, "learning_rate": 9.903447899932687e-06, "loss": 0.649, "step": 131550 }, { "epoch": 0.7820199606493452, "grad_norm": 5.557311534881592, "learning_rate": 9.903407316303929e-06, "loss": 0.577, "step": 131560 }, { "epoch": 0.7820794027260136, "grad_norm": 4.8785786628723145, "learning_rate": 9.903366724230918e-06, "loss": 0.5373, "step": 131570 }, { "epoch": 0.782138844802682, "grad_norm": 4.839318752288818, "learning_rate": 9.903326123713724e-06, "loss": 0.6274, "step": 131580 }, { "epoch": 0.7821982868793504, "grad_norm": 4.726618766784668, "learning_rate": 9.903285514752418e-06, "loss": 0.5941, "step": 131590 }, { "epoch": 0.7822577289560189, "grad_norm": 5.461227893829346, "learning_rate": 9.90324489734707e-06, "loss": 0.5725, "step": 131600 }, { "epoch": 0.7823171710326872, "grad_norm": 4.4181647300720215, "learning_rate": 9.903204271497747e-06, "loss": 0.6168, "step": 131610 }, { "epoch": 0.7823766131093556, "grad_norm": 6.241905689239502, "learning_rate": 9.903163637204523e-06, "loss": 0.5514, "step": 131620 }, { "epoch": 0.782436055186024, "grad_norm": 7.115208148956299, "learning_rate": 9.903122994467465e-06, "loss": 0.6199, "step": 131630 }, { "epoch": 0.7824954972626924, "grad_norm": 4.998143196105957, "learning_rate": 9.903082343286645e-06, "loss": 0.5711, "step": 131640 }, { "epoch": 0.7825549393393607, "grad_norm": 5.626170635223389, "learning_rate": 9.903041683662132e-06, "loss": 0.5726, "step": 131650 }, { "epoch": 0.7826143814160291, "grad_norm": 5.094216823577881, "learning_rate": 9.903001015593996e-06, "loss": 0.5683, "step": 131660 }, { "epoch": 0.7826738234926975, "grad_norm": 7.535447120666504, "learning_rate": 9.902960339082309e-06, "loss": 0.5718, "step": 131670 }, { "epoch": 0.782733265569366, "grad_norm": 5.1485419273376465, "learning_rate": 9.902919654127136e-06, "loss": 0.5132, "step": 131680 }, { "epoch": 0.7827927076460344, "grad_norm": 4.667311191558838, "learning_rate": 9.902878960728553e-06, "loss": 0.6275, "step": 131690 }, { "epoch": 0.7828521497227027, "grad_norm": 4.844417572021484, "learning_rate": 9.902838258886627e-06, "loss": 0.5891, "step": 131700 }, { "epoch": 0.7829115917993711, "grad_norm": 4.93527364730835, "learning_rate": 9.902797548601428e-06, "loss": 0.6185, "step": 131710 }, { "epoch": 0.7829710338760395, "grad_norm": 5.342678546905518, "learning_rate": 9.902756829873026e-06, "loss": 0.6183, "step": 131720 }, { "epoch": 0.7830304759527079, "grad_norm": 8.055941581726074, "learning_rate": 9.902716102701493e-06, "loss": 0.544, "step": 131730 }, { "epoch": 0.7830899180293762, "grad_norm": 5.307920932769775, "learning_rate": 9.902675367086897e-06, "loss": 0.5648, "step": 131740 }, { "epoch": 0.7831493601060446, "grad_norm": 6.526426315307617, "learning_rate": 9.90263462302931e-06, "loss": 0.6015, "step": 131750 }, { "epoch": 0.783208802182713, "grad_norm": 5.7297139167785645, "learning_rate": 9.9025938705288e-06, "loss": 0.6171, "step": 131760 }, { "epoch": 0.7832682442593815, "grad_norm": 4.828771114349365, "learning_rate": 9.90255310958544e-06, "loss": 0.6237, "step": 131770 }, { "epoch": 0.7833276863360499, "grad_norm": 5.651264190673828, "learning_rate": 9.902512340199297e-06, "loss": 0.6306, "step": 131780 }, { "epoch": 0.7833871284127182, "grad_norm": 5.129904747009277, "learning_rate": 9.902471562370444e-06, "loss": 0.5351, "step": 131790 }, { "epoch": 0.7834465704893866, "grad_norm": 6.389941692352295, "learning_rate": 9.902430776098948e-06, "loss": 0.5203, "step": 131800 }, { "epoch": 0.783506012566055, "grad_norm": 5.574001789093018, "learning_rate": 9.902389981384884e-06, "loss": 0.5425, "step": 131810 }, { "epoch": 0.7835654546427234, "grad_norm": 4.875288963317871, "learning_rate": 9.902349178228318e-06, "loss": 0.5294, "step": 131820 }, { "epoch": 0.7836248967193918, "grad_norm": 6.201134204864502, "learning_rate": 9.902308366629321e-06, "loss": 0.5755, "step": 131830 }, { "epoch": 0.7836843387960601, "grad_norm": 5.2481794357299805, "learning_rate": 9.902267546587965e-06, "loss": 0.6455, "step": 131840 }, { "epoch": 0.7837437808727286, "grad_norm": 5.918222904205322, "learning_rate": 9.90222671810432e-06, "loss": 0.562, "step": 131850 }, { "epoch": 0.783803222949397, "grad_norm": 6.441712379455566, "learning_rate": 9.902185881178455e-06, "loss": 0.5592, "step": 131860 }, { "epoch": 0.7838626650260654, "grad_norm": 5.739235877990723, "learning_rate": 9.902145035810442e-06, "loss": 0.6097, "step": 131870 }, { "epoch": 0.7839221071027337, "grad_norm": 4.821364879608154, "learning_rate": 9.902104182000349e-06, "loss": 0.5304, "step": 131880 }, { "epoch": 0.7839815491794021, "grad_norm": 4.9787211418151855, "learning_rate": 9.902063319748248e-06, "loss": 0.5335, "step": 131890 }, { "epoch": 0.7840409912560705, "grad_norm": 4.830524921417236, "learning_rate": 9.902022449054208e-06, "loss": 0.5459, "step": 131900 }, { "epoch": 0.7841004333327389, "grad_norm": 5.501667022705078, "learning_rate": 9.901981569918301e-06, "loss": 0.5751, "step": 131910 }, { "epoch": 0.7841598754094073, "grad_norm": 5.61460542678833, "learning_rate": 9.901940682340598e-06, "loss": 0.5953, "step": 131920 }, { "epoch": 0.7842193174860757, "grad_norm": 5.407215595245361, "learning_rate": 9.901899786321168e-06, "loss": 0.4993, "step": 131930 }, { "epoch": 0.7842787595627441, "grad_norm": 4.2718186378479, "learning_rate": 9.901858881860082e-06, "loss": 0.5874, "step": 131940 }, { "epoch": 0.7843382016394125, "grad_norm": 6.562806606292725, "learning_rate": 9.901817968957408e-06, "loss": 0.5719, "step": 131950 }, { "epoch": 0.7843976437160809, "grad_norm": 5.03495454788208, "learning_rate": 9.90177704761322e-06, "loss": 0.6028, "step": 131960 }, { "epoch": 0.7844570857927493, "grad_norm": 4.726801872253418, "learning_rate": 9.901736117827588e-06, "loss": 0.5336, "step": 131970 }, { "epoch": 0.7845165278694176, "grad_norm": 5.834537029266357, "learning_rate": 9.90169517960058e-06, "loss": 0.6229, "step": 131980 }, { "epoch": 0.784575969946086, "grad_norm": 6.172570705413818, "learning_rate": 9.90165423293227e-06, "loss": 0.5398, "step": 131990 }, { "epoch": 0.7846354120227544, "grad_norm": 5.678491115570068, "learning_rate": 9.901613277822723e-06, "loss": 0.591, "step": 132000 }, { "epoch": 0.7846948540994229, "grad_norm": 5.8557538986206055, "learning_rate": 9.901572314272017e-06, "loss": 0.6115, "step": 132010 }, { "epoch": 0.7847542961760912, "grad_norm": 5.680944919586182, "learning_rate": 9.901531342280217e-06, "loss": 0.5701, "step": 132020 }, { "epoch": 0.7848137382527596, "grad_norm": 5.207362651824951, "learning_rate": 9.901490361847394e-06, "loss": 0.5767, "step": 132030 }, { "epoch": 0.784873180329428, "grad_norm": 7.019620895385742, "learning_rate": 9.901449372973622e-06, "loss": 0.5993, "step": 132040 }, { "epoch": 0.7849326224060964, "grad_norm": 5.465630531311035, "learning_rate": 9.901408375658968e-06, "loss": 0.5683, "step": 132050 }, { "epoch": 0.7849920644827648, "grad_norm": 4.147370338439941, "learning_rate": 9.901367369903502e-06, "loss": 0.5712, "step": 132060 }, { "epoch": 0.7850515065594331, "grad_norm": 5.344624996185303, "learning_rate": 9.901326355707301e-06, "loss": 0.5377, "step": 132070 }, { "epoch": 0.7851109486361015, "grad_norm": 4.739679336547852, "learning_rate": 9.901285333070428e-06, "loss": 0.5691, "step": 132080 }, { "epoch": 0.78517039071277, "grad_norm": 4.8525190353393555, "learning_rate": 9.901244301992958e-06, "loss": 0.5908, "step": 132090 }, { "epoch": 0.7852298327894384, "grad_norm": 5.678048133850098, "learning_rate": 9.90120326247496e-06, "loss": 0.5888, "step": 132100 }, { "epoch": 0.7852892748661067, "grad_norm": 4.749370574951172, "learning_rate": 9.901162214516507e-06, "loss": 0.5439, "step": 132110 }, { "epoch": 0.7853487169427751, "grad_norm": 4.816689968109131, "learning_rate": 9.901121158117666e-06, "loss": 0.5267, "step": 132120 }, { "epoch": 0.7854081590194435, "grad_norm": 5.293038845062256, "learning_rate": 9.901080093278508e-06, "loss": 0.6147, "step": 132130 }, { "epoch": 0.7854676010961119, "grad_norm": 5.331036567687988, "learning_rate": 9.901039019999107e-06, "loss": 0.5976, "step": 132140 }, { "epoch": 0.7855270431727803, "grad_norm": 5.159549236297607, "learning_rate": 9.900997938279533e-06, "loss": 0.6087, "step": 132150 }, { "epoch": 0.7855864852494486, "grad_norm": 7.1559062004089355, "learning_rate": 9.900956848119857e-06, "loss": 0.6421, "step": 132160 }, { "epoch": 0.785645927326117, "grad_norm": 5.601371765136719, "learning_rate": 9.900915749520146e-06, "loss": 0.5944, "step": 132170 }, { "epoch": 0.7857053694027855, "grad_norm": 6.550121307373047, "learning_rate": 9.900874642480473e-06, "loss": 0.6033, "step": 132180 }, { "epoch": 0.7857648114794539, "grad_norm": 4.550769329071045, "learning_rate": 9.90083352700091e-06, "loss": 0.5689, "step": 132190 }, { "epoch": 0.7858242535561223, "grad_norm": 6.069299221038818, "learning_rate": 9.900792403081528e-06, "loss": 0.5548, "step": 132200 }, { "epoch": 0.7858836956327906, "grad_norm": 5.653645992279053, "learning_rate": 9.900751270722394e-06, "loss": 0.5513, "step": 132210 }, { "epoch": 0.785943137709459, "grad_norm": 4.979473114013672, "learning_rate": 9.900710129923582e-06, "loss": 0.5022, "step": 132220 }, { "epoch": 0.7860025797861274, "grad_norm": 5.249393463134766, "learning_rate": 9.900668980685164e-06, "loss": 0.5629, "step": 132230 }, { "epoch": 0.7860620218627958, "grad_norm": 5.046542644500732, "learning_rate": 9.90062782300721e-06, "loss": 0.5742, "step": 132240 }, { "epoch": 0.7861214639394641, "grad_norm": 4.817580699920654, "learning_rate": 9.900586656889788e-06, "loss": 0.5833, "step": 132250 }, { "epoch": 0.7861809060161326, "grad_norm": 4.597620964050293, "learning_rate": 9.900545482332972e-06, "loss": 0.5296, "step": 132260 }, { "epoch": 0.786240348092801, "grad_norm": 5.249903678894043, "learning_rate": 9.900504299336833e-06, "loss": 0.5512, "step": 132270 }, { "epoch": 0.7862997901694694, "grad_norm": 5.548689365386963, "learning_rate": 9.900463107901438e-06, "loss": 0.5831, "step": 132280 }, { "epoch": 0.7863592322461378, "grad_norm": 5.225461006164551, "learning_rate": 9.900421908026865e-06, "loss": 0.5559, "step": 132290 }, { "epoch": 0.7864186743228061, "grad_norm": 4.798996448516846, "learning_rate": 9.900380699713179e-06, "loss": 0.5691, "step": 132300 }, { "epoch": 0.7864781163994745, "grad_norm": 4.776273250579834, "learning_rate": 9.90033948296045e-06, "loss": 0.6072, "step": 132310 }, { "epoch": 0.7865375584761429, "grad_norm": 4.284087181091309, "learning_rate": 9.900298257768755e-06, "loss": 0.5589, "step": 132320 }, { "epoch": 0.7865970005528113, "grad_norm": 5.451280117034912, "learning_rate": 9.90025702413816e-06, "loss": 0.53, "step": 132330 }, { "epoch": 0.7866564426294798, "grad_norm": 5.697982311248779, "learning_rate": 9.900215782068739e-06, "loss": 0.5648, "step": 132340 }, { "epoch": 0.7867158847061481, "grad_norm": 5.993253231048584, "learning_rate": 9.90017453156056e-06, "loss": 0.5837, "step": 132350 }, { "epoch": 0.7867753267828165, "grad_norm": 5.371397018432617, "learning_rate": 9.900133272613697e-06, "loss": 0.5471, "step": 132360 }, { "epoch": 0.7868347688594849, "grad_norm": 5.328430652618408, "learning_rate": 9.90009200522822e-06, "loss": 0.6154, "step": 132370 }, { "epoch": 0.7868942109361533, "grad_norm": 6.128949165344238, "learning_rate": 9.9000507294042e-06, "loss": 0.5943, "step": 132380 }, { "epoch": 0.7869536530128216, "grad_norm": 4.567552089691162, "learning_rate": 9.900009445141707e-06, "loss": 0.5596, "step": 132390 }, { "epoch": 0.78701309508949, "grad_norm": 5.148468017578125, "learning_rate": 9.899968152440813e-06, "loss": 0.5558, "step": 132400 }, { "epoch": 0.7870725371661584, "grad_norm": 6.040750503540039, "learning_rate": 9.899926851301591e-06, "loss": 0.5779, "step": 132410 }, { "epoch": 0.7871319792428269, "grad_norm": 6.673519134521484, "learning_rate": 9.89988554172411e-06, "loss": 0.6123, "step": 132420 }, { "epoch": 0.7871914213194953, "grad_norm": 4.0754899978637695, "learning_rate": 9.899844223708439e-06, "loss": 0.5881, "step": 132430 }, { "epoch": 0.7872508633961636, "grad_norm": 4.595318794250488, "learning_rate": 9.899802897254654e-06, "loss": 0.5814, "step": 132440 }, { "epoch": 0.787310305472832, "grad_norm": 6.164649963378906, "learning_rate": 9.899761562362822e-06, "loss": 0.6268, "step": 132450 }, { "epoch": 0.7873697475495004, "grad_norm": 3.930323839187622, "learning_rate": 9.899720219033017e-06, "loss": 0.5651, "step": 132460 }, { "epoch": 0.7874291896261688, "grad_norm": 4.88713264465332, "learning_rate": 9.89967886726531e-06, "loss": 0.5723, "step": 132470 }, { "epoch": 0.7874886317028371, "grad_norm": 5.949432849884033, "learning_rate": 9.899637507059769e-06, "loss": 0.5504, "step": 132480 }, { "epoch": 0.7875480737795055, "grad_norm": 6.4702582359313965, "learning_rate": 9.89959613841647e-06, "loss": 0.5997, "step": 132490 }, { "epoch": 0.787607515856174, "grad_norm": 5.743702411651611, "learning_rate": 9.899554761335482e-06, "loss": 0.6057, "step": 132500 }, { "epoch": 0.7876669579328424, "grad_norm": 7.435150146484375, "learning_rate": 9.899513375816873e-06, "loss": 0.5884, "step": 132510 }, { "epoch": 0.7877264000095108, "grad_norm": 4.90018892288208, "learning_rate": 9.89947198186072e-06, "loss": 0.5222, "step": 132520 }, { "epoch": 0.7877858420861791, "grad_norm": 5.360644340515137, "learning_rate": 9.89943057946709e-06, "loss": 0.5815, "step": 132530 }, { "epoch": 0.7878452841628475, "grad_norm": 5.075810432434082, "learning_rate": 9.899389168636057e-06, "loss": 0.6181, "step": 132540 }, { "epoch": 0.7879047262395159, "grad_norm": 4.760584354400635, "learning_rate": 9.899347749367692e-06, "loss": 0.5671, "step": 132550 }, { "epoch": 0.7879641683161843, "grad_norm": 5.600975513458252, "learning_rate": 9.899306321662066e-06, "loss": 0.615, "step": 132560 }, { "epoch": 0.7880236103928527, "grad_norm": 6.518486499786377, "learning_rate": 9.899264885519248e-06, "loss": 0.5879, "step": 132570 }, { "epoch": 0.788083052469521, "grad_norm": 6.451964855194092, "learning_rate": 9.899223440939312e-06, "loss": 0.554, "step": 132580 }, { "epoch": 0.7881424945461895, "grad_norm": 4.394638538360596, "learning_rate": 9.899181987922329e-06, "loss": 0.5718, "step": 132590 }, { "epoch": 0.7882019366228579, "grad_norm": 5.642224311828613, "learning_rate": 9.899140526468369e-06, "loss": 0.5726, "step": 132600 }, { "epoch": 0.7882613786995263, "grad_norm": 4.776514053344727, "learning_rate": 9.899099056577505e-06, "loss": 0.5534, "step": 132610 }, { "epoch": 0.7883208207761946, "grad_norm": 4.9761152267456055, "learning_rate": 9.899057578249809e-06, "loss": 0.5739, "step": 132620 }, { "epoch": 0.788380262852863, "grad_norm": 4.785003662109375, "learning_rate": 9.899016091485349e-06, "loss": 0.5477, "step": 132630 }, { "epoch": 0.7884397049295314, "grad_norm": 5.555785655975342, "learning_rate": 9.898974596284202e-06, "loss": 0.5996, "step": 132640 }, { "epoch": 0.7884991470061998, "grad_norm": 6.9392924308776855, "learning_rate": 9.898933092646434e-06, "loss": 0.5219, "step": 132650 }, { "epoch": 0.7885585890828682, "grad_norm": 4.209167003631592, "learning_rate": 9.898891580572118e-06, "loss": 0.5879, "step": 132660 }, { "epoch": 0.7886180311595365, "grad_norm": 4.9300456047058105, "learning_rate": 9.898850060061328e-06, "loss": 0.6212, "step": 132670 }, { "epoch": 0.788677473236205, "grad_norm": 5.543954849243164, "learning_rate": 9.898808531114133e-06, "loss": 0.6064, "step": 132680 }, { "epoch": 0.7887369153128734, "grad_norm": 5.293562889099121, "learning_rate": 9.898766993730605e-06, "loss": 0.6166, "step": 132690 }, { "epoch": 0.7887963573895418, "grad_norm": 7.257370471954346, "learning_rate": 9.898725447910815e-06, "loss": 0.6003, "step": 132700 }, { "epoch": 0.7888557994662102, "grad_norm": 4.912843227386475, "learning_rate": 9.898683893654837e-06, "loss": 0.6289, "step": 132710 }, { "epoch": 0.7889152415428785, "grad_norm": 7.144356727600098, "learning_rate": 9.89864233096274e-06, "loss": 0.5582, "step": 132720 }, { "epoch": 0.7889746836195469, "grad_norm": 4.497884273529053, "learning_rate": 9.898600759834595e-06, "loss": 0.5952, "step": 132730 }, { "epoch": 0.7890341256962153, "grad_norm": 4.24840784072876, "learning_rate": 9.898559180270478e-06, "loss": 0.5992, "step": 132740 }, { "epoch": 0.7890935677728838, "grad_norm": 5.0164642333984375, "learning_rate": 9.898517592270456e-06, "loss": 0.5749, "step": 132750 }, { "epoch": 0.7891530098495521, "grad_norm": 4.63386869430542, "learning_rate": 9.898475995834601e-06, "loss": 0.5709, "step": 132760 }, { "epoch": 0.7892124519262205, "grad_norm": 6.053628921508789, "learning_rate": 9.898434390962988e-06, "loss": 0.5623, "step": 132770 }, { "epoch": 0.7892718940028889, "grad_norm": 6.746346950531006, "learning_rate": 9.898392777655685e-06, "loss": 0.5534, "step": 132780 }, { "epoch": 0.7893313360795573, "grad_norm": 4.820019721984863, "learning_rate": 9.898351155912766e-06, "loss": 0.5469, "step": 132790 }, { "epoch": 0.7893907781562257, "grad_norm": 4.5466814041137695, "learning_rate": 9.898309525734302e-06, "loss": 0.5982, "step": 132800 }, { "epoch": 0.789450220232894, "grad_norm": 5.09480619430542, "learning_rate": 9.898267887120363e-06, "loss": 0.568, "step": 132810 }, { "epoch": 0.7895096623095624, "grad_norm": 6.302886009216309, "learning_rate": 9.898226240071024e-06, "loss": 0.5307, "step": 132820 }, { "epoch": 0.7895691043862308, "grad_norm": 4.788043022155762, "learning_rate": 9.898184584586354e-06, "loss": 0.5718, "step": 132830 }, { "epoch": 0.7896285464628993, "grad_norm": 4.9862141609191895, "learning_rate": 9.898142920666425e-06, "loss": 0.5345, "step": 132840 }, { "epoch": 0.7896879885395676, "grad_norm": 4.225673198699951, "learning_rate": 9.898101248311312e-06, "loss": 0.4914, "step": 132850 }, { "epoch": 0.789747430616236, "grad_norm": 5.607939720153809, "learning_rate": 9.898059567521083e-06, "loss": 0.6022, "step": 132860 }, { "epoch": 0.7898068726929044, "grad_norm": 4.240025520324707, "learning_rate": 9.898017878295809e-06, "loss": 0.5973, "step": 132870 }, { "epoch": 0.7898663147695728, "grad_norm": 6.260303020477295, "learning_rate": 9.897976180635566e-06, "loss": 0.5481, "step": 132880 }, { "epoch": 0.7899257568462412, "grad_norm": 5.243452072143555, "learning_rate": 9.897934474540422e-06, "loss": 0.6026, "step": 132890 }, { "epoch": 0.7899851989229095, "grad_norm": 5.330357551574707, "learning_rate": 9.897892760010453e-06, "loss": 0.5507, "step": 132900 }, { "epoch": 0.7900446409995779, "grad_norm": 5.52642297744751, "learning_rate": 9.897851037045728e-06, "loss": 0.5525, "step": 132910 }, { "epoch": 0.7901040830762464, "grad_norm": 6.725949287414551, "learning_rate": 9.897809305646315e-06, "loss": 0.5385, "step": 132920 }, { "epoch": 0.7901635251529148, "grad_norm": 5.636306285858154, "learning_rate": 9.897767565812295e-06, "loss": 0.5386, "step": 132930 }, { "epoch": 0.7902229672295832, "grad_norm": 6.185558795928955, "learning_rate": 9.897725817543733e-06, "loss": 0.5819, "step": 132940 }, { "epoch": 0.7902824093062515, "grad_norm": 5.7854323387146, "learning_rate": 9.897684060840701e-06, "loss": 0.554, "step": 132950 }, { "epoch": 0.7903418513829199, "grad_norm": 5.93609094619751, "learning_rate": 9.897642295703274e-06, "loss": 0.592, "step": 132960 }, { "epoch": 0.7904012934595883, "grad_norm": 4.84157657623291, "learning_rate": 9.897600522131524e-06, "loss": 0.5786, "step": 132970 }, { "epoch": 0.7904607355362567, "grad_norm": 6.16087007522583, "learning_rate": 9.897558740125519e-06, "loss": 0.4949, "step": 132980 }, { "epoch": 0.790520177612925, "grad_norm": 6.27855110168457, "learning_rate": 9.897516949685334e-06, "loss": 0.6166, "step": 132990 }, { "epoch": 0.7905796196895934, "grad_norm": 7.2680559158325195, "learning_rate": 9.897475150811043e-06, "loss": 0.6387, "step": 133000 }, { "epoch": 0.7906390617662619, "grad_norm": 5.829344749450684, "learning_rate": 9.897433343502712e-06, "loss": 0.5758, "step": 133010 }, { "epoch": 0.7906985038429303, "grad_norm": 5.1220550537109375, "learning_rate": 9.897391527760418e-06, "loss": 0.6448, "step": 133020 }, { "epoch": 0.7907579459195987, "grad_norm": 7.1018524169921875, "learning_rate": 9.897349703584231e-06, "loss": 0.6123, "step": 133030 }, { "epoch": 0.790817387996267, "grad_norm": 5.1935248374938965, "learning_rate": 9.897307870974223e-06, "loss": 0.5707, "step": 133040 }, { "epoch": 0.7908768300729354, "grad_norm": 4.7808074951171875, "learning_rate": 9.89726602993047e-06, "loss": 0.5736, "step": 133050 }, { "epoch": 0.7909362721496038, "grad_norm": 5.055670261383057, "learning_rate": 9.897224180453037e-06, "loss": 0.5525, "step": 133060 }, { "epoch": 0.7909957142262722, "grad_norm": 4.773233413696289, "learning_rate": 9.897182322542001e-06, "loss": 0.5833, "step": 133070 }, { "epoch": 0.7910551563029407, "grad_norm": 5.172013282775879, "learning_rate": 9.897140456197432e-06, "loss": 0.5466, "step": 133080 }, { "epoch": 0.791114598379609, "grad_norm": 7.659753322601318, "learning_rate": 9.897098581419404e-06, "loss": 0.6252, "step": 133090 }, { "epoch": 0.7911740404562774, "grad_norm": 5.834721565246582, "learning_rate": 9.897056698207988e-06, "loss": 0.5787, "step": 133100 }, { "epoch": 0.7912334825329458, "grad_norm": 4.893795013427734, "learning_rate": 9.897014806563255e-06, "loss": 0.5653, "step": 133110 }, { "epoch": 0.7912929246096142, "grad_norm": 9.153363227844238, "learning_rate": 9.896972906485277e-06, "loss": 0.5667, "step": 133120 }, { "epoch": 0.7913523666862825, "grad_norm": 6.086821556091309, "learning_rate": 9.896930997974129e-06, "loss": 0.6226, "step": 133130 }, { "epoch": 0.7914118087629509, "grad_norm": 7.994099140167236, "learning_rate": 9.89688908102988e-06, "loss": 0.5577, "step": 133140 }, { "epoch": 0.7914712508396193, "grad_norm": 8.439798355102539, "learning_rate": 9.896847155652607e-06, "loss": 0.5704, "step": 133150 }, { "epoch": 0.7915306929162877, "grad_norm": 6.055182456970215, "learning_rate": 9.896805221842376e-06, "loss": 0.6173, "step": 133160 }, { "epoch": 0.7915901349929562, "grad_norm": 4.807943344116211, "learning_rate": 9.896763279599262e-06, "loss": 0.528, "step": 133170 }, { "epoch": 0.7916495770696245, "grad_norm": 7.594061374664307, "learning_rate": 9.89672132892334e-06, "loss": 0.499, "step": 133180 }, { "epoch": 0.7917090191462929, "grad_norm": 7.345741271972656, "learning_rate": 9.896679369814677e-06, "loss": 0.5863, "step": 133190 }, { "epoch": 0.7917684612229613, "grad_norm": 7.074425220489502, "learning_rate": 9.896637402273349e-06, "loss": 0.5791, "step": 133200 }, { "epoch": 0.7918279032996297, "grad_norm": 5.406142234802246, "learning_rate": 9.896595426299427e-06, "loss": 0.5888, "step": 133210 }, { "epoch": 0.791887345376298, "grad_norm": 6.056880950927734, "learning_rate": 9.896553441892985e-06, "loss": 0.5948, "step": 133220 }, { "epoch": 0.7919467874529664, "grad_norm": 5.7656168937683105, "learning_rate": 9.896511449054091e-06, "loss": 0.5892, "step": 133230 }, { "epoch": 0.7920062295296348, "grad_norm": 6.239385604858398, "learning_rate": 9.896469447782822e-06, "loss": 0.5159, "step": 133240 }, { "epoch": 0.7920656716063033, "grad_norm": 5.160098552703857, "learning_rate": 9.896427438079246e-06, "loss": 0.5538, "step": 133250 }, { "epoch": 0.7921251136829717, "grad_norm": 4.0548834800720215, "learning_rate": 9.89638541994344e-06, "loss": 0.5579, "step": 133260 }, { "epoch": 0.79218455575964, "grad_norm": 6.374545097351074, "learning_rate": 9.896343393375473e-06, "loss": 0.5926, "step": 133270 }, { "epoch": 0.7922439978363084, "grad_norm": 5.674246788024902, "learning_rate": 9.89630135837542e-06, "loss": 0.6012, "step": 133280 }, { "epoch": 0.7923034399129768, "grad_norm": 5.454733848571777, "learning_rate": 9.89625931494335e-06, "loss": 0.5679, "step": 133290 }, { "epoch": 0.7923628819896452, "grad_norm": 5.9290571212768555, "learning_rate": 9.896217263079338e-06, "loss": 0.5602, "step": 133300 }, { "epoch": 0.7924223240663136, "grad_norm": 5.263319969177246, "learning_rate": 9.896175202783455e-06, "loss": 0.5827, "step": 133310 }, { "epoch": 0.7924817661429819, "grad_norm": 4.415370941162109, "learning_rate": 9.896133134055775e-06, "loss": 0.5238, "step": 133320 }, { "epoch": 0.7925412082196504, "grad_norm": 5.820106506347656, "learning_rate": 9.896091056896369e-06, "loss": 0.5219, "step": 133330 }, { "epoch": 0.7926006502963188, "grad_norm": 5.738714694976807, "learning_rate": 9.89604897130531e-06, "loss": 0.5848, "step": 133340 }, { "epoch": 0.7926600923729872, "grad_norm": 4.886856555938721, "learning_rate": 9.896006877282672e-06, "loss": 0.5753, "step": 133350 }, { "epoch": 0.7927195344496555, "grad_norm": 6.069926738739014, "learning_rate": 9.895964774828523e-06, "loss": 0.5569, "step": 133360 }, { "epoch": 0.7927789765263239, "grad_norm": 3.747215747833252, "learning_rate": 9.89592266394294e-06, "loss": 0.4815, "step": 133370 }, { "epoch": 0.7928384186029923, "grad_norm": 5.799022197723389, "learning_rate": 9.895880544625995e-06, "loss": 0.5876, "step": 133380 }, { "epoch": 0.7928978606796607, "grad_norm": 6.132145881652832, "learning_rate": 9.895838416877758e-06, "loss": 0.6218, "step": 133390 }, { "epoch": 0.7929573027563291, "grad_norm": 7.961910247802734, "learning_rate": 9.895796280698304e-06, "loss": 0.6013, "step": 133400 }, { "epoch": 0.7930167448329974, "grad_norm": 5.460785865783691, "learning_rate": 9.895754136087705e-06, "loss": 0.5808, "step": 133410 }, { "epoch": 0.7930761869096659, "grad_norm": 4.664674758911133, "learning_rate": 9.895711983046033e-06, "loss": 0.5709, "step": 133420 }, { "epoch": 0.7931356289863343, "grad_norm": 4.577496528625488, "learning_rate": 9.895669821573359e-06, "loss": 0.588, "step": 133430 }, { "epoch": 0.7931950710630027, "grad_norm": 6.375049591064453, "learning_rate": 9.89562765166976e-06, "loss": 0.5386, "step": 133440 }, { "epoch": 0.7932545131396711, "grad_norm": 6.16157865524292, "learning_rate": 9.895585473335306e-06, "loss": 0.5488, "step": 133450 }, { "epoch": 0.7933139552163394, "grad_norm": 4.499420166015625, "learning_rate": 9.895543286570067e-06, "loss": 0.5622, "step": 133460 }, { "epoch": 0.7933733972930078, "grad_norm": 6.522755146026611, "learning_rate": 9.89550109137412e-06, "loss": 0.5663, "step": 133470 }, { "epoch": 0.7934328393696762, "grad_norm": 6.362279891967773, "learning_rate": 9.895458887747536e-06, "loss": 0.5959, "step": 133480 }, { "epoch": 0.7934922814463446, "grad_norm": 5.5470170974731445, "learning_rate": 9.895416675690388e-06, "loss": 0.6068, "step": 133490 }, { "epoch": 0.793551723523013, "grad_norm": 4.39854621887207, "learning_rate": 9.895374455202747e-06, "loss": 0.5577, "step": 133500 }, { "epoch": 0.7936111655996814, "grad_norm": 7.774876594543457, "learning_rate": 9.895332226284688e-06, "loss": 0.5932, "step": 133510 }, { "epoch": 0.7936706076763498, "grad_norm": 6.426985740661621, "learning_rate": 9.895289988936284e-06, "loss": 0.5117, "step": 133520 }, { "epoch": 0.7937300497530182, "grad_norm": 6.105930805206299, "learning_rate": 9.895247743157606e-06, "loss": 0.5008, "step": 133530 }, { "epoch": 0.7937894918296866, "grad_norm": 4.460692882537842, "learning_rate": 9.895205488948725e-06, "loss": 0.5984, "step": 133540 }, { "epoch": 0.7938489339063549, "grad_norm": 7.009487628936768, "learning_rate": 9.89516322630972e-06, "loss": 0.5719, "step": 133550 }, { "epoch": 0.7939083759830233, "grad_norm": 5.736208915710449, "learning_rate": 9.895120955240655e-06, "loss": 0.5776, "step": 133560 }, { "epoch": 0.7939678180596917, "grad_norm": 5.084164142608643, "learning_rate": 9.895078675741612e-06, "loss": 0.5305, "step": 133570 }, { "epoch": 0.7940272601363602, "grad_norm": 6.67404842376709, "learning_rate": 9.895036387812657e-06, "loss": 0.6083, "step": 133580 }, { "epoch": 0.7940867022130285, "grad_norm": 4.696199417114258, "learning_rate": 9.894994091453867e-06, "loss": 0.592, "step": 133590 }, { "epoch": 0.7941461442896969, "grad_norm": 5.91365385055542, "learning_rate": 9.894951786665311e-06, "loss": 0.6083, "step": 133600 }, { "epoch": 0.7942055863663653, "grad_norm": 6.285846710205078, "learning_rate": 9.894909473447066e-06, "loss": 0.6373, "step": 133610 }, { "epoch": 0.7942650284430337, "grad_norm": 4.974860191345215, "learning_rate": 9.894867151799201e-06, "loss": 0.5576, "step": 133620 }, { "epoch": 0.7943244705197021, "grad_norm": 4.744220733642578, "learning_rate": 9.894824821721791e-06, "loss": 0.5862, "step": 133630 }, { "epoch": 0.7943839125963704, "grad_norm": 3.887791156768799, "learning_rate": 9.894782483214912e-06, "loss": 0.5783, "step": 133640 }, { "epoch": 0.7944433546730388, "grad_norm": 5.180498123168945, "learning_rate": 9.89474013627863e-06, "loss": 0.6163, "step": 133650 }, { "epoch": 0.7945027967497073, "grad_norm": 5.778491497039795, "learning_rate": 9.89469778091302e-06, "loss": 0.5383, "step": 133660 }, { "epoch": 0.7945622388263757, "grad_norm": 6.629914283752441, "learning_rate": 9.89465541711816e-06, "loss": 0.5818, "step": 133670 }, { "epoch": 0.7946216809030441, "grad_norm": 5.127594470977783, "learning_rate": 9.894613044894117e-06, "loss": 0.5647, "step": 133680 }, { "epoch": 0.7946811229797124, "grad_norm": 5.713950157165527, "learning_rate": 9.894570664240969e-06, "loss": 0.5599, "step": 133690 }, { "epoch": 0.7947405650563808, "grad_norm": 5.147129535675049, "learning_rate": 9.894528275158783e-06, "loss": 0.609, "step": 133700 }, { "epoch": 0.7948000071330492, "grad_norm": 4.836853981018066, "learning_rate": 9.894485877647637e-06, "loss": 0.5546, "step": 133710 }, { "epoch": 0.7948594492097176, "grad_norm": 5.034651279449463, "learning_rate": 9.894443471707602e-06, "loss": 0.6003, "step": 133720 }, { "epoch": 0.7949188912863859, "grad_norm": 7.393876075744629, "learning_rate": 9.894401057338751e-06, "loss": 0.5313, "step": 133730 }, { "epoch": 0.7949783333630543, "grad_norm": 4.058244228363037, "learning_rate": 9.89435863454116e-06, "loss": 0.5503, "step": 133740 }, { "epoch": 0.7950377754397228, "grad_norm": 4.824611663818359, "learning_rate": 9.894316203314897e-06, "loss": 0.5556, "step": 133750 }, { "epoch": 0.7950972175163912, "grad_norm": 4.62073278427124, "learning_rate": 9.894273763660037e-06, "loss": 0.5995, "step": 133760 }, { "epoch": 0.7951566595930596, "grad_norm": 5.328721523284912, "learning_rate": 9.894231315576655e-06, "loss": 0.5653, "step": 133770 }, { "epoch": 0.7952161016697279, "grad_norm": 5.272821426391602, "learning_rate": 9.894188859064821e-06, "loss": 0.6087, "step": 133780 }, { "epoch": 0.7952755437463963, "grad_norm": 5.685754776000977, "learning_rate": 9.894146394124613e-06, "loss": 0.6014, "step": 133790 }, { "epoch": 0.7953349858230647, "grad_norm": 5.267647743225098, "learning_rate": 9.894103920756099e-06, "loss": 0.5924, "step": 133800 }, { "epoch": 0.7953944278997331, "grad_norm": 5.566092014312744, "learning_rate": 9.894061438959352e-06, "loss": 0.5408, "step": 133810 }, { "epoch": 0.7954538699764016, "grad_norm": 4.716017246246338, "learning_rate": 9.894018948734451e-06, "loss": 0.5196, "step": 133820 }, { "epoch": 0.7955133120530699, "grad_norm": 4.614237308502197, "learning_rate": 9.893976450081465e-06, "loss": 0.514, "step": 133830 }, { "epoch": 0.7955727541297383, "grad_norm": 5.125120639801025, "learning_rate": 9.893933943000464e-06, "loss": 0.5671, "step": 133840 }, { "epoch": 0.7956321962064067, "grad_norm": 6.3234710693359375, "learning_rate": 9.893891427491529e-06, "loss": 0.5374, "step": 133850 }, { "epoch": 0.7956916382830751, "grad_norm": 5.461728096008301, "learning_rate": 9.893848903554725e-06, "loss": 0.5791, "step": 133860 }, { "epoch": 0.7957510803597434, "grad_norm": 6.08573055267334, "learning_rate": 9.893806371190134e-06, "loss": 0.6842, "step": 133870 }, { "epoch": 0.7958105224364118, "grad_norm": 5.436750411987305, "learning_rate": 9.89376383039782e-06, "loss": 0.5806, "step": 133880 }, { "epoch": 0.7958699645130802, "grad_norm": 6.318727493286133, "learning_rate": 9.893721281177864e-06, "loss": 0.5497, "step": 133890 }, { "epoch": 0.7959294065897486, "grad_norm": 4.871037483215332, "learning_rate": 9.893678723530334e-06, "loss": 0.5075, "step": 133900 }, { "epoch": 0.7959888486664171, "grad_norm": 5.51014518737793, "learning_rate": 9.893636157455307e-06, "loss": 0.6295, "step": 133910 }, { "epoch": 0.7960482907430854, "grad_norm": 5.292398452758789, "learning_rate": 9.893593582952854e-06, "loss": 0.5796, "step": 133920 }, { "epoch": 0.7961077328197538, "grad_norm": 5.3203125, "learning_rate": 9.893551000023047e-06, "loss": 0.5861, "step": 133930 }, { "epoch": 0.7961671748964222, "grad_norm": 6.887281894683838, "learning_rate": 9.893508408665965e-06, "loss": 0.5785, "step": 133940 }, { "epoch": 0.7962266169730906, "grad_norm": 5.693187713623047, "learning_rate": 9.893465808881676e-06, "loss": 0.5777, "step": 133950 }, { "epoch": 0.7962860590497589, "grad_norm": 4.321072101593018, "learning_rate": 9.893423200670254e-06, "loss": 0.5409, "step": 133960 }, { "epoch": 0.7963455011264273, "grad_norm": 4.85567045211792, "learning_rate": 9.893380584031773e-06, "loss": 0.5682, "step": 133970 }, { "epoch": 0.7964049432030957, "grad_norm": 5.534080505371094, "learning_rate": 9.893337958966308e-06, "loss": 0.5767, "step": 133980 }, { "epoch": 0.7964643852797642, "grad_norm": 4.220834255218506, "learning_rate": 9.89329532547393e-06, "loss": 0.5869, "step": 133990 }, { "epoch": 0.7965238273564326, "grad_norm": 5.069340705871582, "learning_rate": 9.893252683554715e-06, "loss": 0.5773, "step": 134000 }, { "epoch": 0.7965832694331009, "grad_norm": 5.150753021240234, "learning_rate": 9.893210033208736e-06, "loss": 0.5731, "step": 134010 }, { "epoch": 0.7966427115097693, "grad_norm": 5.529787540435791, "learning_rate": 9.893167374436063e-06, "loss": 0.6392, "step": 134020 }, { "epoch": 0.7967021535864377, "grad_norm": 5.6582512855529785, "learning_rate": 9.893124707236774e-06, "loss": 0.5843, "step": 134030 }, { "epoch": 0.7967615956631061, "grad_norm": 6.782361030578613, "learning_rate": 9.893082031610939e-06, "loss": 0.6265, "step": 134040 }, { "epoch": 0.7968210377397745, "grad_norm": 4.570282459259033, "learning_rate": 9.893039347558633e-06, "loss": 0.5379, "step": 134050 }, { "epoch": 0.7968804798164428, "grad_norm": 7.247523784637451, "learning_rate": 9.892996655079929e-06, "loss": 0.5269, "step": 134060 }, { "epoch": 0.7969399218931112, "grad_norm": 5.862392425537109, "learning_rate": 9.892953954174902e-06, "loss": 0.5557, "step": 134070 }, { "epoch": 0.7969993639697797, "grad_norm": 7.325405120849609, "learning_rate": 9.892911244843625e-06, "loss": 0.5776, "step": 134080 }, { "epoch": 0.7970588060464481, "grad_norm": 4.211498260498047, "learning_rate": 9.89286852708617e-06, "loss": 0.6302, "step": 134090 }, { "epoch": 0.7971182481231164, "grad_norm": 6.393407344818115, "learning_rate": 9.892825800902613e-06, "loss": 0.6451, "step": 134100 }, { "epoch": 0.7971776901997848, "grad_norm": 5.473699569702148, "learning_rate": 9.892783066293023e-06, "loss": 0.5718, "step": 134110 }, { "epoch": 0.7972371322764532, "grad_norm": 6.500445365905762, "learning_rate": 9.892740323257479e-06, "loss": 0.5993, "step": 134120 }, { "epoch": 0.7972965743531216, "grad_norm": 7.262885093688965, "learning_rate": 9.892697571796053e-06, "loss": 0.6607, "step": 134130 }, { "epoch": 0.79735601642979, "grad_norm": 4.5488600730896, "learning_rate": 9.892654811908817e-06, "loss": 0.5894, "step": 134140 }, { "epoch": 0.7974154585064583, "grad_norm": 6.411552906036377, "learning_rate": 9.892612043595846e-06, "loss": 0.6146, "step": 134150 }, { "epoch": 0.7974749005831268, "grad_norm": 6.264464855194092, "learning_rate": 9.892569266857213e-06, "loss": 0.564, "step": 134160 }, { "epoch": 0.7975343426597952, "grad_norm": 4.979916572570801, "learning_rate": 9.892526481692992e-06, "loss": 0.5431, "step": 134170 }, { "epoch": 0.7975937847364636, "grad_norm": 5.129332065582275, "learning_rate": 9.892483688103257e-06, "loss": 0.6242, "step": 134180 }, { "epoch": 0.7976532268131319, "grad_norm": 5.496772289276123, "learning_rate": 9.89244088608808e-06, "loss": 0.583, "step": 134190 }, { "epoch": 0.7977126688898003, "grad_norm": 5.095900535583496, "learning_rate": 9.892398075647535e-06, "loss": 0.6069, "step": 134200 }, { "epoch": 0.7977721109664687, "grad_norm": 5.596645355224609, "learning_rate": 9.892355256781701e-06, "loss": 0.5795, "step": 134210 }, { "epoch": 0.7978315530431371, "grad_norm": 5.5439629554748535, "learning_rate": 9.892312429490644e-06, "loss": 0.6362, "step": 134220 }, { "epoch": 0.7978909951198055, "grad_norm": 7.639863014221191, "learning_rate": 9.892269593774443e-06, "loss": 0.5648, "step": 134230 }, { "epoch": 0.7979504371964738, "grad_norm": 7.377743721008301, "learning_rate": 9.892226749633168e-06, "loss": 0.5657, "step": 134240 }, { "epoch": 0.7980098792731423, "grad_norm": 7.130714416503906, "learning_rate": 9.892183897066899e-06, "loss": 0.5875, "step": 134250 }, { "epoch": 0.7980693213498107, "grad_norm": 4.998489856719971, "learning_rate": 9.892141036075703e-06, "loss": 0.5525, "step": 134260 }, { "epoch": 0.7981287634264791, "grad_norm": 5.2933244705200195, "learning_rate": 9.892098166659654e-06, "loss": 0.6055, "step": 134270 }, { "epoch": 0.7981882055031475, "grad_norm": 4.738934516906738, "learning_rate": 9.892055288818831e-06, "loss": 0.6057, "step": 134280 }, { "epoch": 0.7982476475798158, "grad_norm": 4.054811477661133, "learning_rate": 9.892012402553305e-06, "loss": 0.5547, "step": 134290 }, { "epoch": 0.7983070896564842, "grad_norm": 4.972741603851318, "learning_rate": 9.89196950786315e-06, "loss": 0.5972, "step": 134300 }, { "epoch": 0.7983665317331526, "grad_norm": 4.611745357513428, "learning_rate": 9.891926604748438e-06, "loss": 0.5174, "step": 134310 }, { "epoch": 0.798425973809821, "grad_norm": 4.642037868499756, "learning_rate": 9.891883693209246e-06, "loss": 0.5998, "step": 134320 }, { "epoch": 0.7984854158864894, "grad_norm": 4.319244861602783, "learning_rate": 9.891840773245647e-06, "loss": 0.5537, "step": 134330 }, { "epoch": 0.7985448579631578, "grad_norm": 5.045460224151611, "learning_rate": 9.891797844857715e-06, "loss": 0.5425, "step": 134340 }, { "epoch": 0.7986043000398262, "grad_norm": 5.506371974945068, "learning_rate": 9.891754908045521e-06, "loss": 0.527, "step": 134350 }, { "epoch": 0.7986637421164946, "grad_norm": 4.925751209259033, "learning_rate": 9.891711962809145e-06, "loss": 0.5627, "step": 134360 }, { "epoch": 0.798723184193163, "grad_norm": 4.868113040924072, "learning_rate": 9.891669009148655e-06, "loss": 0.4957, "step": 134370 }, { "epoch": 0.7987826262698313, "grad_norm": 4.351255893707275, "learning_rate": 9.891626047064127e-06, "loss": 0.54, "step": 134380 }, { "epoch": 0.7988420683464997, "grad_norm": 4.1102752685546875, "learning_rate": 9.891583076555636e-06, "loss": 0.5596, "step": 134390 }, { "epoch": 0.7989015104231681, "grad_norm": 7.858325004577637, "learning_rate": 9.891540097623255e-06, "loss": 0.5202, "step": 134400 }, { "epoch": 0.7989609524998366, "grad_norm": 6.918457984924316, "learning_rate": 9.89149711026706e-06, "loss": 0.5511, "step": 134410 }, { "epoch": 0.799020394576505, "grad_norm": 4.70428991317749, "learning_rate": 9.89145411448712e-06, "loss": 0.5545, "step": 134420 }, { "epoch": 0.7990798366531733, "grad_norm": 4.681218147277832, "learning_rate": 9.891411110283514e-06, "loss": 0.5908, "step": 134430 }, { "epoch": 0.7991392787298417, "grad_norm": 5.223114967346191, "learning_rate": 9.891368097656315e-06, "loss": 0.6005, "step": 134440 }, { "epoch": 0.7991987208065101, "grad_norm": 5.278073787689209, "learning_rate": 9.891325076605595e-06, "loss": 0.6335, "step": 134450 }, { "epoch": 0.7992581628831785, "grad_norm": 5.683401584625244, "learning_rate": 9.891282047131433e-06, "loss": 0.5747, "step": 134460 }, { "epoch": 0.7993176049598468, "grad_norm": 5.568023681640625, "learning_rate": 9.891239009233897e-06, "loss": 0.5512, "step": 134470 }, { "epoch": 0.7993770470365152, "grad_norm": 5.288794040679932, "learning_rate": 9.891195962913062e-06, "loss": 0.5642, "step": 134480 }, { "epoch": 0.7994364891131837, "grad_norm": 5.291967391967773, "learning_rate": 9.891152908169009e-06, "loss": 0.6226, "step": 134490 }, { "epoch": 0.7994959311898521, "grad_norm": 4.8904829025268555, "learning_rate": 9.891109845001803e-06, "loss": 0.5876, "step": 134500 }, { "epoch": 0.7995553732665205, "grad_norm": 4.625677585601807, "learning_rate": 9.891066773411525e-06, "loss": 0.5172, "step": 134510 }, { "epoch": 0.7996148153431888, "grad_norm": 6.638794898986816, "learning_rate": 9.891023693398244e-06, "loss": 0.595, "step": 134520 }, { "epoch": 0.7996742574198572, "grad_norm": 6.137500762939453, "learning_rate": 9.890980604962037e-06, "loss": 0.5534, "step": 134530 }, { "epoch": 0.7997336994965256, "grad_norm": 4.312750816345215, "learning_rate": 9.890937508102978e-06, "loss": 0.5545, "step": 134540 }, { "epoch": 0.799793141573194, "grad_norm": 4.961591720581055, "learning_rate": 9.890894402821142e-06, "loss": 0.5539, "step": 134550 }, { "epoch": 0.7998525836498623, "grad_norm": 4.919668197631836, "learning_rate": 9.8908512891166e-06, "loss": 0.5161, "step": 134560 }, { "epoch": 0.7999120257265308, "grad_norm": 6.361592769622803, "learning_rate": 9.890808166989432e-06, "loss": 0.5698, "step": 134570 }, { "epoch": 0.7999714678031992, "grad_norm": 6.570765495300293, "learning_rate": 9.890765036439708e-06, "loss": 0.5905, "step": 134580 }, { "epoch": 0.8000309098798676, "grad_norm": 5.424375057220459, "learning_rate": 9.8907218974675e-06, "loss": 0.5264, "step": 134590 }, { "epoch": 0.800090351956536, "grad_norm": 5.659548759460449, "learning_rate": 9.890678750072889e-06, "loss": 0.5943, "step": 134600 }, { "epoch": 0.8001497940332043, "grad_norm": 6.236843109130859, "learning_rate": 9.890635594255943e-06, "loss": 0.5983, "step": 134610 }, { "epoch": 0.8002092361098727, "grad_norm": 4.958367824554443, "learning_rate": 9.89059243001674e-06, "loss": 0.5757, "step": 134620 }, { "epoch": 0.8002686781865411, "grad_norm": 5.763314723968506, "learning_rate": 9.890549257355352e-06, "loss": 0.5859, "step": 134630 }, { "epoch": 0.8003281202632095, "grad_norm": 6.2602081298828125, "learning_rate": 9.890506076271857e-06, "loss": 0.5719, "step": 134640 }, { "epoch": 0.800387562339878, "grad_norm": 4.007691860198975, "learning_rate": 9.890462886766325e-06, "loss": 0.5265, "step": 134650 }, { "epoch": 0.8004470044165463, "grad_norm": 6.817234516143799, "learning_rate": 9.890419688838834e-06, "loss": 0.6327, "step": 134660 }, { "epoch": 0.8005064464932147, "grad_norm": 5.069633960723877, "learning_rate": 9.890376482489457e-06, "loss": 0.5611, "step": 134670 }, { "epoch": 0.8005658885698831, "grad_norm": 7.1441874504089355, "learning_rate": 9.890333267718266e-06, "loss": 0.6126, "step": 134680 }, { "epoch": 0.8006253306465515, "grad_norm": 4.986593723297119, "learning_rate": 9.890290044525339e-06, "loss": 0.5879, "step": 134690 }, { "epoch": 0.8006847727232198, "grad_norm": 5.946467399597168, "learning_rate": 9.890246812910748e-06, "loss": 0.6592, "step": 134700 }, { "epoch": 0.8007442147998882, "grad_norm": 5.404718399047852, "learning_rate": 9.890203572874571e-06, "loss": 0.6369, "step": 134710 }, { "epoch": 0.8008036568765566, "grad_norm": 3.7554454803466797, "learning_rate": 9.890160324416878e-06, "loss": 0.5544, "step": 134720 }, { "epoch": 0.800863098953225, "grad_norm": 4.642646789550781, "learning_rate": 9.890117067537745e-06, "loss": 0.5284, "step": 134730 }, { "epoch": 0.8009225410298935, "grad_norm": 6.419517517089844, "learning_rate": 9.890073802237247e-06, "loss": 0.5876, "step": 134740 }, { "epoch": 0.8009819831065618, "grad_norm": 7.389650344848633, "learning_rate": 9.890030528515461e-06, "loss": 0.6219, "step": 134750 }, { "epoch": 0.8010414251832302, "grad_norm": 4.885295391082764, "learning_rate": 9.889987246372456e-06, "loss": 0.6135, "step": 134760 }, { "epoch": 0.8011008672598986, "grad_norm": 4.250075340270996, "learning_rate": 9.889943955808311e-06, "loss": 0.638, "step": 134770 }, { "epoch": 0.801160309336567, "grad_norm": 7.282486915588379, "learning_rate": 9.8899006568231e-06, "loss": 0.5736, "step": 134780 }, { "epoch": 0.8012197514132354, "grad_norm": 5.304444789886475, "learning_rate": 9.889857349416894e-06, "loss": 0.5332, "step": 134790 }, { "epoch": 0.8012791934899037, "grad_norm": 6.175676345825195, "learning_rate": 9.889814033589772e-06, "loss": 0.5726, "step": 134800 }, { "epoch": 0.8013386355665721, "grad_norm": 4.952022552490234, "learning_rate": 9.889770709341807e-06, "loss": 0.5473, "step": 134810 }, { "epoch": 0.8013980776432406, "grad_norm": 3.557487726211548, "learning_rate": 9.889727376673072e-06, "loss": 0.5664, "step": 134820 }, { "epoch": 0.801457519719909, "grad_norm": 6.215297698974609, "learning_rate": 9.889684035583643e-06, "loss": 0.5618, "step": 134830 }, { "epoch": 0.8015169617965773, "grad_norm": 4.007184982299805, "learning_rate": 9.889640686073596e-06, "loss": 0.6224, "step": 134840 }, { "epoch": 0.8015764038732457, "grad_norm": 4.114196300506592, "learning_rate": 9.889597328143004e-06, "loss": 0.565, "step": 134850 }, { "epoch": 0.8016358459499141, "grad_norm": 6.204270362854004, "learning_rate": 9.889553961791941e-06, "loss": 0.5728, "step": 134860 }, { "epoch": 0.8016952880265825, "grad_norm": 3.3238699436187744, "learning_rate": 9.889510587020483e-06, "loss": 0.5724, "step": 134870 }, { "epoch": 0.8017547301032509, "grad_norm": 5.396657466888428, "learning_rate": 9.889467203828706e-06, "loss": 0.5351, "step": 134880 }, { "epoch": 0.8018141721799192, "grad_norm": 4.341648578643799, "learning_rate": 9.889423812216681e-06, "loss": 0.575, "step": 134890 }, { "epoch": 0.8018736142565877, "grad_norm": 5.7605438232421875, "learning_rate": 9.889380412184487e-06, "loss": 0.5746, "step": 134900 }, { "epoch": 0.8019330563332561, "grad_norm": 5.908626556396484, "learning_rate": 9.889337003732193e-06, "loss": 0.5689, "step": 134910 }, { "epoch": 0.8019924984099245, "grad_norm": 4.42026424407959, "learning_rate": 9.88929358685988e-06, "loss": 0.498, "step": 134920 }, { "epoch": 0.8020519404865928, "grad_norm": 4.609550476074219, "learning_rate": 9.88925016156762e-06, "loss": 0.5667, "step": 134930 }, { "epoch": 0.8021113825632612, "grad_norm": 6.095520496368408, "learning_rate": 9.889206727855488e-06, "loss": 0.5128, "step": 134940 }, { "epoch": 0.8021708246399296, "grad_norm": 5.112333297729492, "learning_rate": 9.889163285723557e-06, "loss": 0.5767, "step": 134950 }, { "epoch": 0.802230266716598, "grad_norm": 5.817440986633301, "learning_rate": 9.889119835171904e-06, "loss": 0.5875, "step": 134960 }, { "epoch": 0.8022897087932664, "grad_norm": 5.169270992279053, "learning_rate": 9.889076376200604e-06, "loss": 0.5522, "step": 134970 }, { "epoch": 0.8023491508699347, "grad_norm": 5.19378137588501, "learning_rate": 9.88903290880973e-06, "loss": 0.6169, "step": 134980 }, { "epoch": 0.8024085929466032, "grad_norm": 6.841124057769775, "learning_rate": 9.88898943299936e-06, "loss": 0.6108, "step": 134990 }, { "epoch": 0.8024680350232716, "grad_norm": 5.324463367462158, "learning_rate": 9.888945948769566e-06, "loss": 0.5516, "step": 135000 }, { "epoch": 0.80252747709994, "grad_norm": 4.230968952178955, "learning_rate": 9.888902456120422e-06, "loss": 0.5684, "step": 135010 }, { "epoch": 0.8025869191766084, "grad_norm": 6.774110317230225, "learning_rate": 9.888858955052006e-06, "loss": 0.5714, "step": 135020 }, { "epoch": 0.8026463612532767, "grad_norm": 5.610909461975098, "learning_rate": 9.888815445564393e-06, "loss": 0.6246, "step": 135030 }, { "epoch": 0.8027058033299451, "grad_norm": 5.347479820251465, "learning_rate": 9.888771927657655e-06, "loss": 0.5559, "step": 135040 }, { "epoch": 0.8027652454066135, "grad_norm": 4.014423370361328, "learning_rate": 9.888728401331868e-06, "loss": 0.6024, "step": 135050 }, { "epoch": 0.802824687483282, "grad_norm": 5.343925952911377, "learning_rate": 9.888684866587108e-06, "loss": 0.5461, "step": 135060 }, { "epoch": 0.8028841295599503, "grad_norm": 5.639646530151367, "learning_rate": 9.888641323423448e-06, "loss": 0.5929, "step": 135070 }, { "epoch": 0.8029435716366187, "grad_norm": 5.319673538208008, "learning_rate": 9.888597771840966e-06, "loss": 0.5796, "step": 135080 }, { "epoch": 0.8030030137132871, "grad_norm": 6.57603120803833, "learning_rate": 9.888554211839735e-06, "loss": 0.6138, "step": 135090 }, { "epoch": 0.8030624557899555, "grad_norm": 5.257688999176025, "learning_rate": 9.888510643419831e-06, "loss": 0.6005, "step": 135100 }, { "epoch": 0.8031218978666239, "grad_norm": 5.8890180587768555, "learning_rate": 9.888467066581326e-06, "loss": 0.59, "step": 135110 }, { "epoch": 0.8031813399432922, "grad_norm": 4.857152462005615, "learning_rate": 9.8884234813243e-06, "loss": 0.5304, "step": 135120 }, { "epoch": 0.8032407820199606, "grad_norm": 6.195734977722168, "learning_rate": 9.888379887648825e-06, "loss": 0.5577, "step": 135130 }, { "epoch": 0.803300224096629, "grad_norm": 5.587347030639648, "learning_rate": 9.888336285554976e-06, "loss": 0.5943, "step": 135140 }, { "epoch": 0.8033596661732975, "grad_norm": 5.032729148864746, "learning_rate": 9.888292675042827e-06, "loss": 0.5842, "step": 135150 }, { "epoch": 0.8034191082499659, "grad_norm": 5.604557037353516, "learning_rate": 9.888249056112459e-06, "loss": 0.5533, "step": 135160 }, { "epoch": 0.8034785503266342, "grad_norm": 4.701924800872803, "learning_rate": 9.88820542876394e-06, "loss": 0.578, "step": 135170 }, { "epoch": 0.8035379924033026, "grad_norm": 5.834263801574707, "learning_rate": 9.888161792997349e-06, "loss": 0.5667, "step": 135180 }, { "epoch": 0.803597434479971, "grad_norm": 5.2621941566467285, "learning_rate": 9.888118148812757e-06, "loss": 0.5773, "step": 135190 }, { "epoch": 0.8036568765566394, "grad_norm": 7.7054619789123535, "learning_rate": 9.888074496210245e-06, "loss": 0.4959, "step": 135200 }, { "epoch": 0.8037163186333077, "grad_norm": 4.800273418426514, "learning_rate": 9.888030835189886e-06, "loss": 0.515, "step": 135210 }, { "epoch": 0.8037757607099761, "grad_norm": 5.805969715118408, "learning_rate": 9.887987165751753e-06, "loss": 0.5736, "step": 135220 }, { "epoch": 0.8038352027866446, "grad_norm": 4.915350914001465, "learning_rate": 9.887943487895926e-06, "loss": 0.567, "step": 135230 }, { "epoch": 0.803894644863313, "grad_norm": 7.332318305969238, "learning_rate": 9.887899801622474e-06, "loss": 0.5473, "step": 135240 }, { "epoch": 0.8039540869399814, "grad_norm": 4.020536422729492, "learning_rate": 9.887856106931476e-06, "loss": 0.5347, "step": 135250 }, { "epoch": 0.8040135290166497, "grad_norm": 3.945998430252075, "learning_rate": 9.887812403823007e-06, "loss": 0.55, "step": 135260 }, { "epoch": 0.8040729710933181, "grad_norm": 6.163313388824463, "learning_rate": 9.887768692297142e-06, "loss": 0.5547, "step": 135270 }, { "epoch": 0.8041324131699865, "grad_norm": 5.14685583114624, "learning_rate": 9.887724972353956e-06, "loss": 0.5872, "step": 135280 }, { "epoch": 0.8041918552466549, "grad_norm": 5.245833873748779, "learning_rate": 9.887681243993524e-06, "loss": 0.5754, "step": 135290 }, { "epoch": 0.8042512973233232, "grad_norm": 4.999716758728027, "learning_rate": 9.887637507215922e-06, "loss": 0.5712, "step": 135300 }, { "epoch": 0.8043107393999916, "grad_norm": 5.202338218688965, "learning_rate": 9.887593762021225e-06, "loss": 0.5175, "step": 135310 }, { "epoch": 0.8043701814766601, "grad_norm": 6.53018856048584, "learning_rate": 9.887550008409507e-06, "loss": 0.5726, "step": 135320 }, { "epoch": 0.8044296235533285, "grad_norm": 6.769774913787842, "learning_rate": 9.887506246380847e-06, "loss": 0.5928, "step": 135330 }, { "epoch": 0.8044890656299969, "grad_norm": 5.528888702392578, "learning_rate": 9.887462475935317e-06, "loss": 0.6047, "step": 135340 }, { "epoch": 0.8045485077066652, "grad_norm": 3.8113889694213867, "learning_rate": 9.887418697072993e-06, "loss": 0.5659, "step": 135350 }, { "epoch": 0.8046079497833336, "grad_norm": 5.876123428344727, "learning_rate": 9.887374909793952e-06, "loss": 0.59, "step": 135360 }, { "epoch": 0.804667391860002, "grad_norm": 3.8364579677581787, "learning_rate": 9.887331114098268e-06, "loss": 0.5194, "step": 135370 }, { "epoch": 0.8047268339366704, "grad_norm": 3.926222801208496, "learning_rate": 9.887287309986016e-06, "loss": 0.4917, "step": 135380 }, { "epoch": 0.8047862760133389, "grad_norm": 7.233058929443359, "learning_rate": 9.887243497457273e-06, "loss": 0.589, "step": 135390 }, { "epoch": 0.8048457180900072, "grad_norm": 5.153792381286621, "learning_rate": 9.887199676512113e-06, "loss": 0.5447, "step": 135400 }, { "epoch": 0.8049051601666756, "grad_norm": 4.963693618774414, "learning_rate": 9.887155847150611e-06, "loss": 0.6345, "step": 135410 }, { "epoch": 0.804964602243344, "grad_norm": 4.274922847747803, "learning_rate": 9.887112009372845e-06, "loss": 0.5315, "step": 135420 }, { "epoch": 0.8050240443200124, "grad_norm": 6.009897232055664, "learning_rate": 9.887068163178888e-06, "loss": 0.5715, "step": 135430 }, { "epoch": 0.8050834863966807, "grad_norm": 5.861987590789795, "learning_rate": 9.887024308568818e-06, "loss": 0.5654, "step": 135440 }, { "epoch": 0.8051429284733491, "grad_norm": 4.912967681884766, "learning_rate": 9.886980445542707e-06, "loss": 0.5435, "step": 135450 }, { "epoch": 0.8052023705500175, "grad_norm": 5.4990458488464355, "learning_rate": 9.886936574100634e-06, "loss": 0.5888, "step": 135460 }, { "epoch": 0.805261812626686, "grad_norm": 4.663074016571045, "learning_rate": 9.886892694242674e-06, "loss": 0.5824, "step": 135470 }, { "epoch": 0.8053212547033544, "grad_norm": 5.429101943969727, "learning_rate": 9.8868488059689e-06, "loss": 0.5881, "step": 135480 }, { "epoch": 0.8053806967800227, "grad_norm": 5.722078800201416, "learning_rate": 9.886804909279389e-06, "loss": 0.5683, "step": 135490 }, { "epoch": 0.8054401388566911, "grad_norm": 5.3507537841796875, "learning_rate": 9.886761004174217e-06, "loss": 0.5696, "step": 135500 }, { "epoch": 0.8054995809333595, "grad_norm": 5.625245094299316, "learning_rate": 9.88671709065346e-06, "loss": 0.4955, "step": 135510 }, { "epoch": 0.8055590230100279, "grad_norm": 4.336530685424805, "learning_rate": 9.886673168717194e-06, "loss": 0.5367, "step": 135520 }, { "epoch": 0.8056184650866963, "grad_norm": 5.048245429992676, "learning_rate": 9.886629238365492e-06, "loss": 0.582, "step": 135530 }, { "epoch": 0.8056779071633646, "grad_norm": 8.221426010131836, "learning_rate": 9.886585299598432e-06, "loss": 0.5901, "step": 135540 }, { "epoch": 0.805737349240033, "grad_norm": 4.486806869506836, "learning_rate": 9.88654135241609e-06, "loss": 0.5672, "step": 135550 }, { "epoch": 0.8057967913167015, "grad_norm": 6.359824180603027, "learning_rate": 9.88649739681854e-06, "loss": 0.5933, "step": 135560 }, { "epoch": 0.8058562333933699, "grad_norm": 5.856042861938477, "learning_rate": 9.886453432805858e-06, "loss": 0.5564, "step": 135570 }, { "epoch": 0.8059156754700382, "grad_norm": 4.954226493835449, "learning_rate": 9.886409460378121e-06, "loss": 0.6009, "step": 135580 }, { "epoch": 0.8059751175467066, "grad_norm": 6.502778053283691, "learning_rate": 9.886365479535404e-06, "loss": 0.5413, "step": 135590 }, { "epoch": 0.806034559623375, "grad_norm": 4.909675598144531, "learning_rate": 9.886321490277782e-06, "loss": 0.5272, "step": 135600 }, { "epoch": 0.8060940017000434, "grad_norm": 6.459304332733154, "learning_rate": 9.886277492605332e-06, "loss": 0.6239, "step": 135610 }, { "epoch": 0.8061534437767118, "grad_norm": 5.327929973602295, "learning_rate": 9.88623348651813e-06, "loss": 0.5927, "step": 135620 }, { "epoch": 0.8062128858533801, "grad_norm": 6.132627010345459, "learning_rate": 9.886189472016247e-06, "loss": 0.6066, "step": 135630 }, { "epoch": 0.8062723279300485, "grad_norm": 5.627363204956055, "learning_rate": 9.886145449099767e-06, "loss": 0.5847, "step": 135640 }, { "epoch": 0.806331770006717, "grad_norm": 4.531738758087158, "learning_rate": 9.886101417768758e-06, "loss": 0.5894, "step": 135650 }, { "epoch": 0.8063912120833854, "grad_norm": 5.048727035522461, "learning_rate": 9.886057378023302e-06, "loss": 0.5257, "step": 135660 }, { "epoch": 0.8064506541600537, "grad_norm": 6.077936172485352, "learning_rate": 9.886013329863472e-06, "loss": 0.5828, "step": 135670 }, { "epoch": 0.8065100962367221, "grad_norm": 6.233675956726074, "learning_rate": 9.885969273289343e-06, "loss": 0.5641, "step": 135680 }, { "epoch": 0.8065695383133905, "grad_norm": 4.623218059539795, "learning_rate": 9.885925208300992e-06, "loss": 0.4727, "step": 135690 }, { "epoch": 0.8066289803900589, "grad_norm": 5.729067325592041, "learning_rate": 9.885881134898495e-06, "loss": 0.5824, "step": 135700 }, { "epoch": 0.8066884224667273, "grad_norm": 4.498605728149414, "learning_rate": 9.885837053081927e-06, "loss": 0.5659, "step": 135710 }, { "epoch": 0.8067478645433956, "grad_norm": 5.930912971496582, "learning_rate": 9.885792962851366e-06, "loss": 0.5533, "step": 135720 }, { "epoch": 0.8068073066200641, "grad_norm": 4.204169750213623, "learning_rate": 9.885748864206886e-06, "loss": 0.5539, "step": 135730 }, { "epoch": 0.8068667486967325, "grad_norm": 4.766912460327148, "learning_rate": 9.885704757148564e-06, "loss": 0.5364, "step": 135740 }, { "epoch": 0.8069261907734009, "grad_norm": 6.507949352264404, "learning_rate": 9.885660641676475e-06, "loss": 0.603, "step": 135750 }, { "epoch": 0.8069856328500693, "grad_norm": 5.089588165283203, "learning_rate": 9.885616517790695e-06, "loss": 0.5303, "step": 135760 }, { "epoch": 0.8070450749267376, "grad_norm": 5.588123798370361, "learning_rate": 9.8855723854913e-06, "loss": 0.6087, "step": 135770 }, { "epoch": 0.807104517003406, "grad_norm": 5.623385429382324, "learning_rate": 9.885528244778368e-06, "loss": 0.5494, "step": 135780 }, { "epoch": 0.8071639590800744, "grad_norm": 6.119558811187744, "learning_rate": 9.885484095651973e-06, "loss": 0.5824, "step": 135790 }, { "epoch": 0.8072234011567428, "grad_norm": 9.831512451171875, "learning_rate": 9.885439938112191e-06, "loss": 0.5637, "step": 135800 }, { "epoch": 0.8072828432334112, "grad_norm": 5.547098636627197, "learning_rate": 9.885395772159099e-06, "loss": 0.5435, "step": 135810 }, { "epoch": 0.8073422853100796, "grad_norm": 5.3773298263549805, "learning_rate": 9.885351597792772e-06, "loss": 0.6163, "step": 135820 }, { "epoch": 0.807401727386748, "grad_norm": 5.436036586761475, "learning_rate": 9.885307415013287e-06, "loss": 0.5283, "step": 135830 }, { "epoch": 0.8074611694634164, "grad_norm": 8.884136199951172, "learning_rate": 9.88526322382072e-06, "loss": 0.6142, "step": 135840 }, { "epoch": 0.8075206115400848, "grad_norm": 5.242298126220703, "learning_rate": 9.885219024215146e-06, "loss": 0.5904, "step": 135850 }, { "epoch": 0.8075800536167531, "grad_norm": 4.914892673492432, "learning_rate": 9.885174816196642e-06, "loss": 0.5694, "step": 135860 }, { "epoch": 0.8076394956934215, "grad_norm": 5.351632118225098, "learning_rate": 9.885130599765285e-06, "loss": 0.638, "step": 135870 }, { "epoch": 0.8076989377700899, "grad_norm": 4.11721658706665, "learning_rate": 9.88508637492115e-06, "loss": 0.5261, "step": 135880 }, { "epoch": 0.8077583798467584, "grad_norm": 6.93848991394043, "learning_rate": 9.885042141664312e-06, "loss": 0.595, "step": 135890 }, { "epoch": 0.8078178219234268, "grad_norm": 5.3313703536987305, "learning_rate": 9.88499789999485e-06, "loss": 0.6368, "step": 135900 }, { "epoch": 0.8078772640000951, "grad_norm": 4.983724117279053, "learning_rate": 9.884953649912838e-06, "loss": 0.547, "step": 135910 }, { "epoch": 0.8079367060767635, "grad_norm": 5.475899696350098, "learning_rate": 9.884909391418354e-06, "loss": 0.644, "step": 135920 }, { "epoch": 0.8079961481534319, "grad_norm": 4.909550666809082, "learning_rate": 9.884865124511472e-06, "loss": 0.6216, "step": 135930 }, { "epoch": 0.8080555902301003, "grad_norm": 5.459690570831299, "learning_rate": 9.88482084919227e-06, "loss": 0.6236, "step": 135940 }, { "epoch": 0.8081150323067686, "grad_norm": 5.330881595611572, "learning_rate": 9.884776565460823e-06, "loss": 0.6198, "step": 135950 }, { "epoch": 0.808174474383437, "grad_norm": 5.050907611846924, "learning_rate": 9.88473227331721e-06, "loss": 0.6025, "step": 135960 }, { "epoch": 0.8082339164601055, "grad_norm": 4.487912178039551, "learning_rate": 9.884687972761502e-06, "loss": 0.5541, "step": 135970 }, { "epoch": 0.8082933585367739, "grad_norm": 6.316932678222656, "learning_rate": 9.88464366379378e-06, "loss": 0.6248, "step": 135980 }, { "epoch": 0.8083528006134423, "grad_norm": 4.616720676422119, "learning_rate": 9.884599346414118e-06, "loss": 0.5959, "step": 135990 }, { "epoch": 0.8084122426901106, "grad_norm": 5.092848777770996, "learning_rate": 9.884555020622595e-06, "loss": 0.5431, "step": 136000 }, { "epoch": 0.808471684766779, "grad_norm": 6.390397548675537, "learning_rate": 9.884510686419284e-06, "loss": 0.5904, "step": 136010 }, { "epoch": 0.8085311268434474, "grad_norm": 4.576024532318115, "learning_rate": 9.884466343804265e-06, "loss": 0.5287, "step": 136020 }, { "epoch": 0.8085905689201158, "grad_norm": 6.310572147369385, "learning_rate": 9.88442199277761e-06, "loss": 0.5386, "step": 136030 }, { "epoch": 0.8086500109967841, "grad_norm": 5.621561527252197, "learning_rate": 9.884377633339398e-06, "loss": 0.5897, "step": 136040 }, { "epoch": 0.8087094530734525, "grad_norm": 6.055961608886719, "learning_rate": 9.884333265489704e-06, "loss": 0.6336, "step": 136050 }, { "epoch": 0.808768895150121, "grad_norm": 4.793979167938232, "learning_rate": 9.884288889228607e-06, "loss": 0.5805, "step": 136060 }, { "epoch": 0.8088283372267894, "grad_norm": 4.740217208862305, "learning_rate": 9.88424450455618e-06, "loss": 0.5827, "step": 136070 }, { "epoch": 0.8088877793034578, "grad_norm": 4.446837425231934, "learning_rate": 9.884200111472501e-06, "loss": 0.5478, "step": 136080 }, { "epoch": 0.8089472213801261, "grad_norm": 9.42291259765625, "learning_rate": 9.884155709977649e-06, "loss": 0.5251, "step": 136090 }, { "epoch": 0.8090066634567945, "grad_norm": 5.406976222991943, "learning_rate": 9.884111300071697e-06, "loss": 0.5413, "step": 136100 }, { "epoch": 0.8090661055334629, "grad_norm": 5.107410430908203, "learning_rate": 9.884066881754721e-06, "loss": 0.5477, "step": 136110 }, { "epoch": 0.8091255476101313, "grad_norm": 5.157021522521973, "learning_rate": 9.884022455026801e-06, "loss": 0.5877, "step": 136120 }, { "epoch": 0.8091849896867997, "grad_norm": 6.340076446533203, "learning_rate": 9.883978019888012e-06, "loss": 0.538, "step": 136130 }, { "epoch": 0.809244431763468, "grad_norm": 6.647017478942871, "learning_rate": 9.88393357633843e-06, "loss": 0.585, "step": 136140 }, { "epoch": 0.8093038738401365, "grad_norm": 4.862433910369873, "learning_rate": 9.88388912437813e-06, "loss": 0.5925, "step": 136150 }, { "epoch": 0.8093633159168049, "grad_norm": 5.816691875457764, "learning_rate": 9.88384466400719e-06, "loss": 0.5566, "step": 136160 }, { "epoch": 0.8094227579934733, "grad_norm": 5.6523637771606445, "learning_rate": 9.883800195225689e-06, "loss": 0.6023, "step": 136170 }, { "epoch": 0.8094822000701416, "grad_norm": 5.371788501739502, "learning_rate": 9.883755718033699e-06, "loss": 0.5232, "step": 136180 }, { "epoch": 0.80954164214681, "grad_norm": 4.601634979248047, "learning_rate": 9.8837112324313e-06, "loss": 0.5246, "step": 136190 }, { "epoch": 0.8096010842234784, "grad_norm": 5.1287922859191895, "learning_rate": 9.883666738418567e-06, "loss": 0.5495, "step": 136200 }, { "epoch": 0.8096605263001468, "grad_norm": 5.978926658630371, "learning_rate": 9.883622235995578e-06, "loss": 0.5602, "step": 136210 }, { "epoch": 0.8097199683768153, "grad_norm": 4.6544318199157715, "learning_rate": 9.88357772516241e-06, "loss": 0.5772, "step": 136220 }, { "epoch": 0.8097794104534836, "grad_norm": 5.612091064453125, "learning_rate": 9.883533205919135e-06, "loss": 0.5779, "step": 136230 }, { "epoch": 0.809838852530152, "grad_norm": 7.470937728881836, "learning_rate": 9.883488678265835e-06, "loss": 0.5743, "step": 136240 }, { "epoch": 0.8098982946068204, "grad_norm": 6.507812976837158, "learning_rate": 9.883444142202586e-06, "loss": 0.6002, "step": 136250 }, { "epoch": 0.8099577366834888, "grad_norm": 4.696846008300781, "learning_rate": 9.883399597729462e-06, "loss": 0.5786, "step": 136260 }, { "epoch": 0.8100171787601572, "grad_norm": 5.159421920776367, "learning_rate": 9.883355044846542e-06, "loss": 0.5189, "step": 136270 }, { "epoch": 0.8100766208368255, "grad_norm": 3.3604488372802734, "learning_rate": 9.883310483553901e-06, "loss": 0.5693, "step": 136280 }, { "epoch": 0.8101360629134939, "grad_norm": 6.722754001617432, "learning_rate": 9.883265913851619e-06, "loss": 0.5489, "step": 136290 }, { "epoch": 0.8101955049901624, "grad_norm": 3.6028459072113037, "learning_rate": 9.883221335739767e-06, "loss": 0.6287, "step": 136300 }, { "epoch": 0.8102549470668308, "grad_norm": 3.5667121410369873, "learning_rate": 9.883176749218428e-06, "loss": 0.5682, "step": 136310 }, { "epoch": 0.8103143891434991, "grad_norm": 4.837098598480225, "learning_rate": 9.883132154287674e-06, "loss": 0.5586, "step": 136320 }, { "epoch": 0.8103738312201675, "grad_norm": 4.166265487670898, "learning_rate": 9.883087550947586e-06, "loss": 0.5626, "step": 136330 }, { "epoch": 0.8104332732968359, "grad_norm": 5.265351295471191, "learning_rate": 9.883042939198236e-06, "loss": 0.5183, "step": 136340 }, { "epoch": 0.8104927153735043, "grad_norm": 4.409289360046387, "learning_rate": 9.882998319039704e-06, "loss": 0.5639, "step": 136350 }, { "epoch": 0.8105521574501727, "grad_norm": 6.005374908447266, "learning_rate": 9.882953690472068e-06, "loss": 0.5124, "step": 136360 }, { "epoch": 0.810611599526841, "grad_norm": 4.684690952301025, "learning_rate": 9.882909053495402e-06, "loss": 0.555, "step": 136370 }, { "epoch": 0.8106710416035094, "grad_norm": 5.2763214111328125, "learning_rate": 9.882864408109784e-06, "loss": 0.5472, "step": 136380 }, { "epoch": 0.8107304836801779, "grad_norm": 5.213430404663086, "learning_rate": 9.882819754315291e-06, "loss": 0.5944, "step": 136390 }, { "epoch": 0.8107899257568463, "grad_norm": 6.652453422546387, "learning_rate": 9.882775092112e-06, "loss": 0.5277, "step": 136400 }, { "epoch": 0.8108493678335146, "grad_norm": 4.8787922859191895, "learning_rate": 9.882730421499986e-06, "loss": 0.5888, "step": 136410 }, { "epoch": 0.810908809910183, "grad_norm": 5.36710262298584, "learning_rate": 9.88268574247933e-06, "loss": 0.6173, "step": 136420 }, { "epoch": 0.8109682519868514, "grad_norm": 5.460622310638428, "learning_rate": 9.882641055050106e-06, "loss": 0.6035, "step": 136430 }, { "epoch": 0.8110276940635198, "grad_norm": 6.932449817657471, "learning_rate": 9.88259635921239e-06, "loss": 0.5157, "step": 136440 }, { "epoch": 0.8110871361401882, "grad_norm": 4.988986492156982, "learning_rate": 9.882551654966262e-06, "loss": 0.554, "step": 136450 }, { "epoch": 0.8111465782168565, "grad_norm": 5.190855979919434, "learning_rate": 9.882506942311798e-06, "loss": 0.6055, "step": 136460 }, { "epoch": 0.811206020293525, "grad_norm": 6.391462802886963, "learning_rate": 9.882462221249073e-06, "loss": 0.6038, "step": 136470 }, { "epoch": 0.8112654623701934, "grad_norm": 4.8736162185668945, "learning_rate": 9.882417491778166e-06, "loss": 0.5483, "step": 136480 }, { "epoch": 0.8113249044468618, "grad_norm": 5.002980709075928, "learning_rate": 9.882372753899153e-06, "loss": 0.4845, "step": 136490 }, { "epoch": 0.8113843465235302, "grad_norm": 6.446780204772949, "learning_rate": 9.882328007612112e-06, "loss": 0.5575, "step": 136500 }, { "epoch": 0.8114437886001985, "grad_norm": 4.6291890144348145, "learning_rate": 9.88228325291712e-06, "loss": 0.6078, "step": 136510 }, { "epoch": 0.8115032306768669, "grad_norm": 5.345966815948486, "learning_rate": 9.882238489814253e-06, "loss": 0.5621, "step": 136520 }, { "epoch": 0.8115626727535353, "grad_norm": 6.422412872314453, "learning_rate": 9.88219371830359e-06, "loss": 0.5918, "step": 136530 }, { "epoch": 0.8116221148302037, "grad_norm": 5.789909839630127, "learning_rate": 9.882148938385206e-06, "loss": 0.5689, "step": 136540 }, { "epoch": 0.811681556906872, "grad_norm": 4.9684038162231445, "learning_rate": 9.882104150059179e-06, "loss": 0.549, "step": 136550 }, { "epoch": 0.8117409989835405, "grad_norm": 4.83962345123291, "learning_rate": 9.882059353325587e-06, "loss": 0.5721, "step": 136560 }, { "epoch": 0.8118004410602089, "grad_norm": 5.760237693786621, "learning_rate": 9.882014548184504e-06, "loss": 0.6141, "step": 136570 }, { "epoch": 0.8118598831368773, "grad_norm": 5.441377639770508, "learning_rate": 9.881969734636012e-06, "loss": 0.5691, "step": 136580 }, { "epoch": 0.8119193252135457, "grad_norm": 4.246641635894775, "learning_rate": 9.881924912680183e-06, "loss": 0.5883, "step": 136590 }, { "epoch": 0.811978767290214, "grad_norm": 5.3784074783325195, "learning_rate": 9.8818800823171e-06, "loss": 0.5267, "step": 136600 }, { "epoch": 0.8120382093668824, "grad_norm": 6.252878665924072, "learning_rate": 9.881835243546834e-06, "loss": 0.5942, "step": 136610 }, { "epoch": 0.8120976514435508, "grad_norm": 5.297617435455322, "learning_rate": 9.881790396369466e-06, "loss": 0.5174, "step": 136620 }, { "epoch": 0.8121570935202193, "grad_norm": 6.504044532775879, "learning_rate": 9.881745540785074e-06, "loss": 0.5983, "step": 136630 }, { "epoch": 0.8122165355968877, "grad_norm": 5.328329563140869, "learning_rate": 9.881700676793733e-06, "loss": 0.5984, "step": 136640 }, { "epoch": 0.812275977673556, "grad_norm": 6.414858818054199, "learning_rate": 9.88165580439552e-06, "loss": 0.589, "step": 136650 }, { "epoch": 0.8123354197502244, "grad_norm": 4.391646385192871, "learning_rate": 9.881610923590515e-06, "loss": 0.6188, "step": 136660 }, { "epoch": 0.8123948618268928, "grad_norm": 5.695939064025879, "learning_rate": 9.881566034378791e-06, "loss": 0.5702, "step": 136670 }, { "epoch": 0.8124543039035612, "grad_norm": 6.2293701171875, "learning_rate": 9.88152113676043e-06, "loss": 0.5718, "step": 136680 }, { "epoch": 0.8125137459802295, "grad_norm": 4.5746541023254395, "learning_rate": 9.881476230735506e-06, "loss": 0.5355, "step": 136690 }, { "epoch": 0.8125731880568979, "grad_norm": 6.0415825843811035, "learning_rate": 9.881431316304098e-06, "loss": 0.5688, "step": 136700 }, { "epoch": 0.8126326301335663, "grad_norm": 6.310608386993408, "learning_rate": 9.881386393466284e-06, "loss": 0.5584, "step": 136710 }, { "epoch": 0.8126920722102348, "grad_norm": 5.272611141204834, "learning_rate": 9.881341462222137e-06, "loss": 0.6097, "step": 136720 }, { "epoch": 0.8127515142869032, "grad_norm": 6.014400959014893, "learning_rate": 9.88129652257174e-06, "loss": 0.5531, "step": 136730 }, { "epoch": 0.8128109563635715, "grad_norm": 6.9314374923706055, "learning_rate": 9.881251574515168e-06, "loss": 0.5937, "step": 136740 }, { "epoch": 0.8128703984402399, "grad_norm": 5.405694484710693, "learning_rate": 9.881206618052497e-06, "loss": 0.5894, "step": 136750 }, { "epoch": 0.8129298405169083, "grad_norm": 6.172604084014893, "learning_rate": 9.881161653183805e-06, "loss": 0.5318, "step": 136760 }, { "epoch": 0.8129892825935767, "grad_norm": 7.241273403167725, "learning_rate": 9.881116679909172e-06, "loss": 0.6072, "step": 136770 }, { "epoch": 0.813048724670245, "grad_norm": 4.769460678100586, "learning_rate": 9.881071698228674e-06, "loss": 0.5916, "step": 136780 }, { "epoch": 0.8131081667469134, "grad_norm": 5.050736427307129, "learning_rate": 9.881026708142389e-06, "loss": 0.5386, "step": 136790 }, { "epoch": 0.8131676088235819, "grad_norm": 5.481645584106445, "learning_rate": 9.880981709650392e-06, "loss": 0.5863, "step": 136800 }, { "epoch": 0.8132270509002503, "grad_norm": 5.3702263832092285, "learning_rate": 9.880936702752762e-06, "loss": 0.5553, "step": 136810 }, { "epoch": 0.8132864929769187, "grad_norm": 5.580539226531982, "learning_rate": 9.880891687449576e-06, "loss": 0.583, "step": 136820 }, { "epoch": 0.813345935053587, "grad_norm": 7.064637660980225, "learning_rate": 9.880846663740916e-06, "loss": 0.5836, "step": 136830 }, { "epoch": 0.8134053771302554, "grad_norm": 6.818353652954102, "learning_rate": 9.880801631626851e-06, "loss": 0.5734, "step": 136840 }, { "epoch": 0.8134648192069238, "grad_norm": 7.061399459838867, "learning_rate": 9.880756591107465e-06, "loss": 0.616, "step": 136850 }, { "epoch": 0.8135242612835922, "grad_norm": 5.9447855949401855, "learning_rate": 9.880711542182834e-06, "loss": 0.5884, "step": 136860 }, { "epoch": 0.8135837033602606, "grad_norm": 4.477806568145752, "learning_rate": 9.880666484853033e-06, "loss": 0.561, "step": 136870 }, { "epoch": 0.813643145436929, "grad_norm": 5.386229991912842, "learning_rate": 9.880621419118146e-06, "loss": 0.6275, "step": 136880 }, { "epoch": 0.8137025875135974, "grad_norm": 5.204235076904297, "learning_rate": 9.880576344978245e-06, "loss": 0.5739, "step": 136890 }, { "epoch": 0.8137620295902658, "grad_norm": 5.4004130363464355, "learning_rate": 9.880531262433409e-06, "loss": 0.5357, "step": 136900 }, { "epoch": 0.8138214716669342, "grad_norm": 4.228012561798096, "learning_rate": 9.880486171483716e-06, "loss": 0.6064, "step": 136910 }, { "epoch": 0.8138809137436025, "grad_norm": 5.6909403800964355, "learning_rate": 9.880441072129241e-06, "loss": 0.5809, "step": 136920 }, { "epoch": 0.8139403558202709, "grad_norm": 5.1762776374816895, "learning_rate": 9.880395964370067e-06, "loss": 0.5363, "step": 136930 }, { "epoch": 0.8139997978969393, "grad_norm": 5.60626745223999, "learning_rate": 9.880350848206268e-06, "loss": 0.5825, "step": 136940 }, { "epoch": 0.8140592399736077, "grad_norm": 4.937563419342041, "learning_rate": 9.880305723637924e-06, "loss": 0.5798, "step": 136950 }, { "epoch": 0.8141186820502762, "grad_norm": 7.989765644073486, "learning_rate": 9.88026059066511e-06, "loss": 0.5703, "step": 136960 }, { "epoch": 0.8141781241269445, "grad_norm": 5.511378765106201, "learning_rate": 9.880215449287905e-06, "loss": 0.5467, "step": 136970 }, { "epoch": 0.8142375662036129, "grad_norm": 5.285229206085205, "learning_rate": 9.880170299506387e-06, "loss": 0.6007, "step": 136980 }, { "epoch": 0.8142970082802813, "grad_norm": 4.040841102600098, "learning_rate": 9.880125141320631e-06, "loss": 0.4869, "step": 136990 }, { "epoch": 0.8143564503569497, "grad_norm": 6.44985294342041, "learning_rate": 9.880079974730721e-06, "loss": 0.658, "step": 137000 }, { "epoch": 0.8144158924336181, "grad_norm": 5.375583171844482, "learning_rate": 9.880034799736728e-06, "loss": 0.6024, "step": 137010 }, { "epoch": 0.8144753345102864, "grad_norm": 4.57972526550293, "learning_rate": 9.879989616338735e-06, "loss": 0.5658, "step": 137020 }, { "epoch": 0.8145347765869548, "grad_norm": 5.269078731536865, "learning_rate": 9.879944424536817e-06, "loss": 0.5977, "step": 137030 }, { "epoch": 0.8145942186636232, "grad_norm": 5.446975231170654, "learning_rate": 9.87989922433105e-06, "loss": 0.5584, "step": 137040 }, { "epoch": 0.8146536607402917, "grad_norm": 6.5904622077941895, "learning_rate": 9.879854015721517e-06, "loss": 0.5663, "step": 137050 }, { "epoch": 0.81471310281696, "grad_norm": 5.275439262390137, "learning_rate": 9.879808798708293e-06, "loss": 0.6186, "step": 137060 }, { "epoch": 0.8147725448936284, "grad_norm": 5.26283597946167, "learning_rate": 9.879763573291455e-06, "loss": 0.5835, "step": 137070 }, { "epoch": 0.8148319869702968, "grad_norm": 4.852020740509033, "learning_rate": 9.879718339471083e-06, "loss": 0.6105, "step": 137080 }, { "epoch": 0.8148914290469652, "grad_norm": 6.832128524780273, "learning_rate": 9.879673097247254e-06, "loss": 0.5719, "step": 137090 }, { "epoch": 0.8149508711236336, "grad_norm": 5.168064117431641, "learning_rate": 9.879627846620044e-06, "loss": 0.5664, "step": 137100 }, { "epoch": 0.8150103132003019, "grad_norm": 5.986385822296143, "learning_rate": 9.879582587589534e-06, "loss": 0.5903, "step": 137110 }, { "epoch": 0.8150697552769703, "grad_norm": 6.004674434661865, "learning_rate": 9.879537320155798e-06, "loss": 0.5359, "step": 137120 }, { "epoch": 0.8151291973536388, "grad_norm": 5.9002156257629395, "learning_rate": 9.87949204431892e-06, "loss": 0.6526, "step": 137130 }, { "epoch": 0.8151886394303072, "grad_norm": 4.466027736663818, "learning_rate": 9.879446760078972e-06, "loss": 0.5351, "step": 137140 }, { "epoch": 0.8152480815069755, "grad_norm": 5.3899102210998535, "learning_rate": 9.879401467436037e-06, "loss": 0.5482, "step": 137150 }, { "epoch": 0.8153075235836439, "grad_norm": 4.913086414337158, "learning_rate": 9.879356166390189e-06, "loss": 0.5332, "step": 137160 }, { "epoch": 0.8153669656603123, "grad_norm": 4.982133865356445, "learning_rate": 9.879310856941506e-06, "loss": 0.5686, "step": 137170 }, { "epoch": 0.8154264077369807, "grad_norm": 5.488265037536621, "learning_rate": 9.87926553909007e-06, "loss": 0.5977, "step": 137180 }, { "epoch": 0.8154858498136491, "grad_norm": 6.0075483322143555, "learning_rate": 9.879220212835956e-06, "loss": 0.5401, "step": 137190 }, { "epoch": 0.8155452918903174, "grad_norm": 4.4683990478515625, "learning_rate": 9.87917487817924e-06, "loss": 0.5776, "step": 137200 }, { "epoch": 0.8156047339669859, "grad_norm": 5.119934558868408, "learning_rate": 9.879129535120006e-06, "loss": 0.5813, "step": 137210 }, { "epoch": 0.8156641760436543, "grad_norm": 5.426567077636719, "learning_rate": 9.879084183658327e-06, "loss": 0.6015, "step": 137220 }, { "epoch": 0.8157236181203227, "grad_norm": 5.556721210479736, "learning_rate": 9.879038823794285e-06, "loss": 0.5092, "step": 137230 }, { "epoch": 0.8157830601969911, "grad_norm": 4.280309200286865, "learning_rate": 9.878993455527955e-06, "loss": 0.5639, "step": 137240 }, { "epoch": 0.8158425022736594, "grad_norm": 5.415189266204834, "learning_rate": 9.878948078859414e-06, "loss": 0.5972, "step": 137250 }, { "epoch": 0.8159019443503278, "grad_norm": 4.062056541442871, "learning_rate": 9.878902693788743e-06, "loss": 0.5149, "step": 137260 }, { "epoch": 0.8159613864269962, "grad_norm": 5.972129821777344, "learning_rate": 9.878857300316021e-06, "loss": 0.549, "step": 137270 }, { "epoch": 0.8160208285036646, "grad_norm": 5.900569438934326, "learning_rate": 9.878811898441324e-06, "loss": 0.5392, "step": 137280 }, { "epoch": 0.816080270580333, "grad_norm": 4.8155293464660645, "learning_rate": 9.87876648816473e-06, "loss": 0.5592, "step": 137290 }, { "epoch": 0.8161397126570014, "grad_norm": 4.876294136047363, "learning_rate": 9.878721069486319e-06, "loss": 0.5941, "step": 137300 }, { "epoch": 0.8161991547336698, "grad_norm": 5.92655611038208, "learning_rate": 9.878675642406168e-06, "loss": 0.5994, "step": 137310 }, { "epoch": 0.8162585968103382, "grad_norm": 5.274437427520752, "learning_rate": 9.878630206924356e-06, "loss": 0.5004, "step": 137320 }, { "epoch": 0.8163180388870066, "grad_norm": 5.300673484802246, "learning_rate": 9.878584763040959e-06, "loss": 0.5784, "step": 137330 }, { "epoch": 0.8163774809636749, "grad_norm": 4.305332660675049, "learning_rate": 9.878539310756058e-06, "loss": 0.6169, "step": 137340 }, { "epoch": 0.8164369230403433, "grad_norm": 5.340900897979736, "learning_rate": 9.878493850069731e-06, "loss": 0.5564, "step": 137350 }, { "epoch": 0.8164963651170117, "grad_norm": 5.7235307693481445, "learning_rate": 9.878448380982055e-06, "loss": 0.5631, "step": 137360 }, { "epoch": 0.8165558071936801, "grad_norm": 6.433511734008789, "learning_rate": 9.878402903493108e-06, "loss": 0.5764, "step": 137370 }, { "epoch": 0.8166152492703486, "grad_norm": 3.8653414249420166, "learning_rate": 9.878357417602968e-06, "loss": 0.5176, "step": 137380 }, { "epoch": 0.8166746913470169, "grad_norm": 5.67161226272583, "learning_rate": 9.878311923311717e-06, "loss": 0.5694, "step": 137390 }, { "epoch": 0.8167341334236853, "grad_norm": 6.6919779777526855, "learning_rate": 9.87826642061943e-06, "loss": 0.5658, "step": 137400 }, { "epoch": 0.8167935755003537, "grad_norm": 5.70257043838501, "learning_rate": 9.878220909526185e-06, "loss": 0.5635, "step": 137410 }, { "epoch": 0.8168530175770221, "grad_norm": 4.381252288818359, "learning_rate": 9.878175390032063e-06, "loss": 0.5413, "step": 137420 }, { "epoch": 0.8169124596536904, "grad_norm": 5.113359451293945, "learning_rate": 9.878129862137141e-06, "loss": 0.5686, "step": 137430 }, { "epoch": 0.8169719017303588, "grad_norm": 5.5867018699646, "learning_rate": 9.878084325841495e-06, "loss": 0.5672, "step": 137440 }, { "epoch": 0.8170313438070272, "grad_norm": 5.1111578941345215, "learning_rate": 9.878038781145209e-06, "loss": 0.5461, "step": 137450 }, { "epoch": 0.8170907858836957, "grad_norm": 5.879188060760498, "learning_rate": 9.877993228048356e-06, "loss": 0.5554, "step": 137460 }, { "epoch": 0.8171502279603641, "grad_norm": 6.7294697761535645, "learning_rate": 9.877947666551018e-06, "loss": 0.5989, "step": 137470 }, { "epoch": 0.8172096700370324, "grad_norm": 6.526155948638916, "learning_rate": 9.87790209665327e-06, "loss": 0.5678, "step": 137480 }, { "epoch": 0.8172691121137008, "grad_norm": 4.998789310455322, "learning_rate": 9.877856518355194e-06, "loss": 0.647, "step": 137490 }, { "epoch": 0.8173285541903692, "grad_norm": 3.870689630508423, "learning_rate": 9.877810931656868e-06, "loss": 0.5277, "step": 137500 }, { "epoch": 0.8173879962670376, "grad_norm": 5.01876974105835, "learning_rate": 9.877765336558369e-06, "loss": 0.5456, "step": 137510 }, { "epoch": 0.8174474383437059, "grad_norm": 4.808292865753174, "learning_rate": 9.877719733059774e-06, "loss": 0.5544, "step": 137520 }, { "epoch": 0.8175068804203743, "grad_norm": 5.316290378570557, "learning_rate": 9.877674121161166e-06, "loss": 0.535, "step": 137530 }, { "epoch": 0.8175663224970428, "grad_norm": 4.849152565002441, "learning_rate": 9.87762850086262e-06, "loss": 0.5769, "step": 137540 }, { "epoch": 0.8176257645737112, "grad_norm": 5.327989101409912, "learning_rate": 9.877582872164216e-06, "loss": 0.5883, "step": 137550 }, { "epoch": 0.8176852066503796, "grad_norm": 5.7283477783203125, "learning_rate": 9.877537235066033e-06, "loss": 0.5073, "step": 137560 }, { "epoch": 0.8177446487270479, "grad_norm": 5.361584663391113, "learning_rate": 9.877491589568147e-06, "loss": 0.5677, "step": 137570 }, { "epoch": 0.8178040908037163, "grad_norm": 5.13957405090332, "learning_rate": 9.877445935670642e-06, "loss": 0.5433, "step": 137580 }, { "epoch": 0.8178635328803847, "grad_norm": 5.088983058929443, "learning_rate": 9.87740027337359e-06, "loss": 0.6375, "step": 137590 }, { "epoch": 0.8179229749570531, "grad_norm": 4.859096527099609, "learning_rate": 9.877354602677073e-06, "loss": 0.587, "step": 137600 }, { "epoch": 0.8179824170337215, "grad_norm": 5.9645891189575195, "learning_rate": 9.877308923581171e-06, "loss": 0.579, "step": 137610 }, { "epoch": 0.8180418591103898, "grad_norm": 4.426970481872559, "learning_rate": 9.87726323608596e-06, "loss": 0.6186, "step": 137620 }, { "epoch": 0.8181013011870583, "grad_norm": 5.326412677764893, "learning_rate": 9.877217540191519e-06, "loss": 0.5889, "step": 137630 }, { "epoch": 0.8181607432637267, "grad_norm": 4.295756816864014, "learning_rate": 9.87717183589793e-06, "loss": 0.5064, "step": 137640 }, { "epoch": 0.8182201853403951, "grad_norm": 5.566556930541992, "learning_rate": 9.877126123205267e-06, "loss": 0.5531, "step": 137650 }, { "epoch": 0.8182796274170634, "grad_norm": 4.646954536437988, "learning_rate": 9.877080402113612e-06, "loss": 0.5488, "step": 137660 }, { "epoch": 0.8183390694937318, "grad_norm": 4.828364849090576, "learning_rate": 9.877034672623041e-06, "loss": 0.5178, "step": 137670 }, { "epoch": 0.8183985115704002, "grad_norm": 5.3826470375061035, "learning_rate": 9.876988934733635e-06, "loss": 0.5661, "step": 137680 }, { "epoch": 0.8184579536470686, "grad_norm": 6.156007766723633, "learning_rate": 9.876943188445474e-06, "loss": 0.5183, "step": 137690 }, { "epoch": 0.818517395723737, "grad_norm": 5.726503849029541, "learning_rate": 9.876897433758634e-06, "loss": 0.5394, "step": 137700 }, { "epoch": 0.8185768378004054, "grad_norm": 5.020536422729492, "learning_rate": 9.876851670673193e-06, "loss": 0.551, "step": 137710 }, { "epoch": 0.8186362798770738, "grad_norm": 4.497796058654785, "learning_rate": 9.876805899189233e-06, "loss": 0.6058, "step": 137720 }, { "epoch": 0.8186957219537422, "grad_norm": 5.505661487579346, "learning_rate": 9.876760119306832e-06, "loss": 0.5987, "step": 137730 }, { "epoch": 0.8187551640304106, "grad_norm": 5.070384502410889, "learning_rate": 9.876714331026068e-06, "loss": 0.5611, "step": 137740 }, { "epoch": 0.8188146061070789, "grad_norm": 5.259372711181641, "learning_rate": 9.876668534347019e-06, "loss": 0.6201, "step": 137750 }, { "epoch": 0.8188740481837473, "grad_norm": 4.382380962371826, "learning_rate": 9.876622729269765e-06, "loss": 0.5794, "step": 137760 }, { "epoch": 0.8189334902604157, "grad_norm": 5.012469291687012, "learning_rate": 9.876576915794385e-06, "loss": 0.5934, "step": 137770 }, { "epoch": 0.8189929323370841, "grad_norm": 6.051428318023682, "learning_rate": 9.876531093920957e-06, "loss": 0.6214, "step": 137780 }, { "epoch": 0.8190523744137526, "grad_norm": 6.46685266494751, "learning_rate": 9.876485263649562e-06, "loss": 0.5443, "step": 137790 }, { "epoch": 0.8191118164904209, "grad_norm": 5.625246524810791, "learning_rate": 9.876439424980278e-06, "loss": 0.5558, "step": 137800 }, { "epoch": 0.8191712585670893, "grad_norm": 4.806268215179443, "learning_rate": 9.876393577913182e-06, "loss": 0.5768, "step": 137810 }, { "epoch": 0.8192307006437577, "grad_norm": 4.80463171005249, "learning_rate": 9.876347722448354e-06, "loss": 0.5693, "step": 137820 }, { "epoch": 0.8192901427204261, "grad_norm": 4.580077171325684, "learning_rate": 9.876301858585875e-06, "loss": 0.5267, "step": 137830 }, { "epoch": 0.8193495847970945, "grad_norm": 5.201976776123047, "learning_rate": 9.87625598632582e-06, "loss": 0.5493, "step": 137840 }, { "epoch": 0.8194090268737628, "grad_norm": 8.683501243591309, "learning_rate": 9.876210105668274e-06, "loss": 0.5859, "step": 137850 }, { "epoch": 0.8194684689504312, "grad_norm": 6.633343696594238, "learning_rate": 9.876164216613308e-06, "loss": 0.6253, "step": 137860 }, { "epoch": 0.8195279110270997, "grad_norm": 4.259479999542236, "learning_rate": 9.87611831916101e-06, "loss": 0.5948, "step": 137870 }, { "epoch": 0.8195873531037681, "grad_norm": 4.170869827270508, "learning_rate": 9.87607241331145e-06, "loss": 0.5384, "step": 137880 }, { "epoch": 0.8196467951804364, "grad_norm": 6.498324394226074, "learning_rate": 9.876026499064715e-06, "loss": 0.64, "step": 137890 }, { "epoch": 0.8197062372571048, "grad_norm": 4.838881492614746, "learning_rate": 9.875980576420878e-06, "loss": 0.5908, "step": 137900 }, { "epoch": 0.8197656793337732, "grad_norm": 5.740767478942871, "learning_rate": 9.875934645380023e-06, "loss": 0.5357, "step": 137910 }, { "epoch": 0.8198251214104416, "grad_norm": 5.2512969970703125, "learning_rate": 9.875888705942226e-06, "loss": 0.5605, "step": 137920 }, { "epoch": 0.81988456348711, "grad_norm": 6.098399639129639, "learning_rate": 9.875842758107565e-06, "loss": 0.5539, "step": 137930 }, { "epoch": 0.8199440055637783, "grad_norm": 6.458829879760742, "learning_rate": 9.875796801876124e-06, "loss": 0.5909, "step": 137940 }, { "epoch": 0.8200034476404467, "grad_norm": 4.240612983703613, "learning_rate": 9.875750837247976e-06, "loss": 0.5463, "step": 137950 }, { "epoch": 0.8200628897171152, "grad_norm": 5.54543924331665, "learning_rate": 9.875704864223205e-06, "loss": 0.5391, "step": 137960 }, { "epoch": 0.8201223317937836, "grad_norm": 5.129420757293701, "learning_rate": 9.875658882801888e-06, "loss": 0.529, "step": 137970 }, { "epoch": 0.820181773870452, "grad_norm": 4.472910404205322, "learning_rate": 9.875612892984105e-06, "loss": 0.5943, "step": 137980 }, { "epoch": 0.8202412159471203, "grad_norm": 6.075134754180908, "learning_rate": 9.875566894769936e-06, "loss": 0.5838, "step": 137990 }, { "epoch": 0.8203006580237887, "grad_norm": 5.343713760375977, "learning_rate": 9.875520888159458e-06, "loss": 0.5425, "step": 138000 }, { "epoch": 0.8203601001004571, "grad_norm": 5.3956828117370605, "learning_rate": 9.875474873152751e-06, "loss": 0.5562, "step": 138010 }, { "epoch": 0.8204195421771255, "grad_norm": 5.873652458190918, "learning_rate": 9.875428849749895e-06, "loss": 0.6075, "step": 138020 }, { "epoch": 0.8204789842537938, "grad_norm": 6.799346923828125, "learning_rate": 9.87538281795097e-06, "loss": 0.5883, "step": 138030 }, { "epoch": 0.8205384263304623, "grad_norm": 4.890025615692139, "learning_rate": 9.875336777756052e-06, "loss": 0.6286, "step": 138040 }, { "epoch": 0.8205978684071307, "grad_norm": 4.824512004852295, "learning_rate": 9.875290729165222e-06, "loss": 0.5484, "step": 138050 }, { "epoch": 0.8206573104837991, "grad_norm": 4.810391426086426, "learning_rate": 9.87524467217856e-06, "loss": 0.5532, "step": 138060 }, { "epoch": 0.8207167525604675, "grad_norm": 7.356302261352539, "learning_rate": 9.875198606796146e-06, "loss": 0.6046, "step": 138070 }, { "epoch": 0.8207761946371358, "grad_norm": 5.593438625335693, "learning_rate": 9.87515253301806e-06, "loss": 0.5781, "step": 138080 }, { "epoch": 0.8208356367138042, "grad_norm": 4.461397171020508, "learning_rate": 9.875106450844377e-06, "loss": 0.5089, "step": 138090 }, { "epoch": 0.8208950787904726, "grad_norm": 4.960699081420898, "learning_rate": 9.87506036027518e-06, "loss": 0.5363, "step": 138100 }, { "epoch": 0.820954520867141, "grad_norm": 3.999417304992676, "learning_rate": 9.875014261310545e-06, "loss": 0.5006, "step": 138110 }, { "epoch": 0.8210139629438094, "grad_norm": 7.0316877365112305, "learning_rate": 9.874968153950556e-06, "loss": 0.5892, "step": 138120 }, { "epoch": 0.8210734050204778, "grad_norm": 6.674045562744141, "learning_rate": 9.87492203819529e-06, "loss": 0.5312, "step": 138130 }, { "epoch": 0.8211328470971462, "grad_norm": 5.8606085777282715, "learning_rate": 9.874875914044826e-06, "loss": 0.5469, "step": 138140 }, { "epoch": 0.8211922891738146, "grad_norm": 5.351170539855957, "learning_rate": 9.874829781499245e-06, "loss": 0.5147, "step": 138150 }, { "epoch": 0.821251731250483, "grad_norm": 4.979024887084961, "learning_rate": 9.874783640558625e-06, "loss": 0.6032, "step": 138160 }, { "epoch": 0.8213111733271513, "grad_norm": 5.219152927398682, "learning_rate": 9.874737491223046e-06, "loss": 0.5515, "step": 138170 }, { "epoch": 0.8213706154038197, "grad_norm": 5.1905436515808105, "learning_rate": 9.874691333492588e-06, "loss": 0.5618, "step": 138180 }, { "epoch": 0.8214300574804881, "grad_norm": 4.49343729019165, "learning_rate": 9.874645167367329e-06, "loss": 0.5918, "step": 138190 }, { "epoch": 0.8214894995571566, "grad_norm": 4.358523368835449, "learning_rate": 9.874598992847348e-06, "loss": 0.5187, "step": 138200 }, { "epoch": 0.821548941633825, "grad_norm": 5.08973503112793, "learning_rate": 9.874552809932729e-06, "loss": 0.5629, "step": 138210 }, { "epoch": 0.8216083837104933, "grad_norm": 5.571782112121582, "learning_rate": 9.874506618623547e-06, "loss": 0.5381, "step": 138220 }, { "epoch": 0.8216678257871617, "grad_norm": 5.16501522064209, "learning_rate": 9.874460418919882e-06, "loss": 0.5923, "step": 138230 }, { "epoch": 0.8217272678638301, "grad_norm": 6.00128173828125, "learning_rate": 9.874414210821815e-06, "loss": 0.6082, "step": 138240 }, { "epoch": 0.8217867099404985, "grad_norm": 5.154923915863037, "learning_rate": 9.874367994329425e-06, "loss": 0.5281, "step": 138250 }, { "epoch": 0.8218461520171668, "grad_norm": 6.794065952301025, "learning_rate": 9.874321769442793e-06, "loss": 0.5767, "step": 138260 }, { "epoch": 0.8219055940938352, "grad_norm": 4.750563144683838, "learning_rate": 9.874275536161997e-06, "loss": 0.5498, "step": 138270 }, { "epoch": 0.8219650361705036, "grad_norm": 5.913952827453613, "learning_rate": 9.874229294487117e-06, "loss": 0.569, "step": 138280 }, { "epoch": 0.8220244782471721, "grad_norm": 5.048503398895264, "learning_rate": 9.874183044418231e-06, "loss": 0.6108, "step": 138290 }, { "epoch": 0.8220839203238405, "grad_norm": 4.185325622558594, "learning_rate": 9.874136785955422e-06, "loss": 0.6161, "step": 138300 }, { "epoch": 0.8221433624005088, "grad_norm": 5.31449556350708, "learning_rate": 9.874090519098767e-06, "loss": 0.5765, "step": 138310 }, { "epoch": 0.8222028044771772, "grad_norm": 6.637697219848633, "learning_rate": 9.874044243848347e-06, "loss": 0.5746, "step": 138320 }, { "epoch": 0.8222622465538456, "grad_norm": 5.401435852050781, "learning_rate": 9.873997960204241e-06, "loss": 0.6219, "step": 138330 }, { "epoch": 0.822321688630514, "grad_norm": 5.106415271759033, "learning_rate": 9.873951668166528e-06, "loss": 0.5567, "step": 138340 }, { "epoch": 0.8223811307071824, "grad_norm": 5.654816627502441, "learning_rate": 9.87390536773529e-06, "loss": 0.5388, "step": 138350 }, { "epoch": 0.8224405727838507, "grad_norm": 5.135834693908691, "learning_rate": 9.873859058910604e-06, "loss": 0.5336, "step": 138360 }, { "epoch": 0.8225000148605192, "grad_norm": 5.614598274230957, "learning_rate": 9.873812741692552e-06, "loss": 0.5737, "step": 138370 }, { "epoch": 0.8225594569371876, "grad_norm": 5.26285457611084, "learning_rate": 9.873766416081214e-06, "loss": 0.5954, "step": 138380 }, { "epoch": 0.822618899013856, "grad_norm": 5.408117294311523, "learning_rate": 9.873720082076667e-06, "loss": 0.5523, "step": 138390 }, { "epoch": 0.8226783410905243, "grad_norm": 5.374773025512695, "learning_rate": 9.873673739678993e-06, "loss": 0.5637, "step": 138400 }, { "epoch": 0.8227377831671927, "grad_norm": 5.3467698097229, "learning_rate": 9.873627388888273e-06, "loss": 0.5447, "step": 138410 }, { "epoch": 0.8227972252438611, "grad_norm": 4.938349723815918, "learning_rate": 9.873581029704584e-06, "loss": 0.5417, "step": 138420 }, { "epoch": 0.8228566673205295, "grad_norm": 5.093120098114014, "learning_rate": 9.873534662128005e-06, "loss": 0.5286, "step": 138430 }, { "epoch": 0.822916109397198, "grad_norm": 7.159423828125, "learning_rate": 9.873488286158621e-06, "loss": 0.5752, "step": 138440 }, { "epoch": 0.8229755514738663, "grad_norm": 6.6836256980896, "learning_rate": 9.873441901796507e-06, "loss": 0.5817, "step": 138450 }, { "epoch": 0.8230349935505347, "grad_norm": 4.994614601135254, "learning_rate": 9.873395509041745e-06, "loss": 0.6199, "step": 138460 }, { "epoch": 0.8230944356272031, "grad_norm": 5.373444080352783, "learning_rate": 9.873349107894415e-06, "loss": 0.5664, "step": 138470 }, { "epoch": 0.8231538777038715, "grad_norm": 4.750175952911377, "learning_rate": 9.873302698354594e-06, "loss": 0.5535, "step": 138480 }, { "epoch": 0.8232133197805398, "grad_norm": 4.527864933013916, "learning_rate": 9.873256280422365e-06, "loss": 0.4891, "step": 138490 }, { "epoch": 0.8232727618572082, "grad_norm": 6.058883190155029, "learning_rate": 9.873209854097809e-06, "loss": 0.6217, "step": 138500 }, { "epoch": 0.8233322039338766, "grad_norm": 4.131893634796143, "learning_rate": 9.873163419381004e-06, "loss": 0.5444, "step": 138510 }, { "epoch": 0.823391646010545, "grad_norm": 5.672878265380859, "learning_rate": 9.873116976272027e-06, "loss": 0.5581, "step": 138520 }, { "epoch": 0.8234510880872135, "grad_norm": 3.5973668098449707, "learning_rate": 9.873070524770965e-06, "loss": 0.5923, "step": 138530 }, { "epoch": 0.8235105301638818, "grad_norm": 6.88780403137207, "learning_rate": 9.873024064877891e-06, "loss": 0.6407, "step": 138540 }, { "epoch": 0.8235699722405502, "grad_norm": 6.872379302978516, "learning_rate": 9.872977596592892e-06, "loss": 0.5514, "step": 138550 }, { "epoch": 0.8236294143172186, "grad_norm": 4.955690860748291, "learning_rate": 9.87293111991604e-06, "loss": 0.5892, "step": 138560 }, { "epoch": 0.823688856393887, "grad_norm": 5.435438632965088, "learning_rate": 9.872884634847422e-06, "loss": 0.592, "step": 138570 }, { "epoch": 0.8237482984705554, "grad_norm": 6.636936664581299, "learning_rate": 9.872838141387114e-06, "loss": 0.5266, "step": 138580 }, { "epoch": 0.8238077405472237, "grad_norm": 5.004429817199707, "learning_rate": 9.872791639535198e-06, "loss": 0.5809, "step": 138590 }, { "epoch": 0.8238671826238921, "grad_norm": 5.318117618560791, "learning_rate": 9.872745129291754e-06, "loss": 0.5506, "step": 138600 }, { "epoch": 0.8239266247005606, "grad_norm": 5.697288513183594, "learning_rate": 9.872698610656859e-06, "loss": 0.5519, "step": 138610 }, { "epoch": 0.823986066777229, "grad_norm": 5.499963283538818, "learning_rate": 9.872652083630597e-06, "loss": 0.6156, "step": 138620 }, { "epoch": 0.8240455088538973, "grad_norm": 6.063545227050781, "learning_rate": 9.872605548213049e-06, "loss": 0.5588, "step": 138630 }, { "epoch": 0.8241049509305657, "grad_norm": 5.19291877746582, "learning_rate": 9.872559004404289e-06, "loss": 0.5528, "step": 138640 }, { "epoch": 0.8241643930072341, "grad_norm": 4.213617324829102, "learning_rate": 9.872512452204402e-06, "loss": 0.54, "step": 138650 }, { "epoch": 0.8242238350839025, "grad_norm": 5.309075355529785, "learning_rate": 9.872465891613467e-06, "loss": 0.5228, "step": 138660 }, { "epoch": 0.8242832771605709, "grad_norm": 4.69064998626709, "learning_rate": 9.872419322631566e-06, "loss": 0.5708, "step": 138670 }, { "epoch": 0.8243427192372392, "grad_norm": 5.1492509841918945, "learning_rate": 9.872372745258776e-06, "loss": 0.5231, "step": 138680 }, { "epoch": 0.8244021613139076, "grad_norm": 6.836983680725098, "learning_rate": 9.87232615949518e-06, "loss": 0.5399, "step": 138690 }, { "epoch": 0.8244616033905761, "grad_norm": 8.123869895935059, "learning_rate": 9.872279565340856e-06, "loss": 0.6185, "step": 138700 }, { "epoch": 0.8245210454672445, "grad_norm": 4.354748249053955, "learning_rate": 9.872232962795887e-06, "loss": 0.5553, "step": 138710 }, { "epoch": 0.8245804875439129, "grad_norm": 5.442108154296875, "learning_rate": 9.87218635186035e-06, "loss": 0.5465, "step": 138720 }, { "epoch": 0.8246399296205812, "grad_norm": 5.0710577964782715, "learning_rate": 9.872139732534327e-06, "loss": 0.5602, "step": 138730 }, { "epoch": 0.8246993716972496, "grad_norm": 4.695618152618408, "learning_rate": 9.872093104817897e-06, "loss": 0.5888, "step": 138740 }, { "epoch": 0.824758813773918, "grad_norm": 7.278223991394043, "learning_rate": 9.872046468711144e-06, "loss": 0.615, "step": 138750 }, { "epoch": 0.8248182558505864, "grad_norm": 5.527707576751709, "learning_rate": 9.871999824214143e-06, "loss": 0.5759, "step": 138760 }, { "epoch": 0.8248776979272547, "grad_norm": 6.883047580718994, "learning_rate": 9.871953171326979e-06, "loss": 0.5661, "step": 138770 }, { "epoch": 0.8249371400039232, "grad_norm": 6.405431270599365, "learning_rate": 9.87190651004973e-06, "loss": 0.5991, "step": 138780 }, { "epoch": 0.8249965820805916, "grad_norm": 4.935258388519287, "learning_rate": 9.871859840382474e-06, "loss": 0.6082, "step": 138790 }, { "epoch": 0.82505602415726, "grad_norm": 5.935269355773926, "learning_rate": 9.871813162325297e-06, "loss": 0.522, "step": 138800 }, { "epoch": 0.8251154662339284, "grad_norm": 5.36349630355835, "learning_rate": 9.871766475878275e-06, "loss": 0.5787, "step": 138810 }, { "epoch": 0.8251749083105967, "grad_norm": 5.234419822692871, "learning_rate": 9.87171978104149e-06, "loss": 0.5649, "step": 138820 }, { "epoch": 0.8252343503872651, "grad_norm": 6.141711711883545, "learning_rate": 9.871673077815023e-06, "loss": 0.6024, "step": 138830 }, { "epoch": 0.8252937924639335, "grad_norm": 4.906523704528809, "learning_rate": 9.871626366198953e-06, "loss": 0.5824, "step": 138840 }, { "epoch": 0.8253532345406019, "grad_norm": 5.325459957122803, "learning_rate": 9.871579646193361e-06, "loss": 0.5672, "step": 138850 }, { "epoch": 0.8254126766172702, "grad_norm": 7.789960861206055, "learning_rate": 9.871532917798328e-06, "loss": 0.5821, "step": 138860 }, { "epoch": 0.8254721186939387, "grad_norm": 5.525932788848877, "learning_rate": 9.871486181013935e-06, "loss": 0.5336, "step": 138870 }, { "epoch": 0.8255315607706071, "grad_norm": 5.938265323638916, "learning_rate": 9.87143943584026e-06, "loss": 0.5426, "step": 138880 }, { "epoch": 0.8255910028472755, "grad_norm": 4.771040439605713, "learning_rate": 9.871392682277385e-06, "loss": 0.5664, "step": 138890 }, { "epoch": 0.8256504449239439, "grad_norm": 5.8062520027160645, "learning_rate": 9.871345920325393e-06, "loss": 0.5681, "step": 138900 }, { "epoch": 0.8257098870006122, "grad_norm": 7.002932548522949, "learning_rate": 9.87129914998436e-06, "loss": 0.5929, "step": 138910 }, { "epoch": 0.8257693290772806, "grad_norm": 5.955644607543945, "learning_rate": 9.871252371254366e-06, "loss": 0.5692, "step": 138920 }, { "epoch": 0.825828771153949, "grad_norm": 4.242761135101318, "learning_rate": 9.8712055841355e-06, "loss": 0.526, "step": 138930 }, { "epoch": 0.8258882132306175, "grad_norm": 4.681084156036377, "learning_rate": 9.871158788627833e-06, "loss": 0.5441, "step": 138940 }, { "epoch": 0.8259476553072859, "grad_norm": 6.269952774047852, "learning_rate": 9.871111984731449e-06, "loss": 0.5931, "step": 138950 }, { "epoch": 0.8260070973839542, "grad_norm": 4.768547534942627, "learning_rate": 9.871065172446432e-06, "loss": 0.5406, "step": 138960 }, { "epoch": 0.8260665394606226, "grad_norm": 4.738699436187744, "learning_rate": 9.871018351772856e-06, "loss": 0.5791, "step": 138970 }, { "epoch": 0.826125981537291, "grad_norm": 5.2793426513671875, "learning_rate": 9.870971522710808e-06, "loss": 0.6011, "step": 138980 }, { "epoch": 0.8261854236139594, "grad_norm": 5.957254886627197, "learning_rate": 9.870924685260364e-06, "loss": 0.5479, "step": 138990 }, { "epoch": 0.8262448656906277, "grad_norm": 5.107353687286377, "learning_rate": 9.870877839421607e-06, "loss": 0.6061, "step": 139000 }, { "epoch": 0.8263043077672961, "grad_norm": 5.818260669708252, "learning_rate": 9.870830985194618e-06, "loss": 0.5839, "step": 139010 }, { "epoch": 0.8263637498439645, "grad_norm": 5.396698951721191, "learning_rate": 9.870784122579476e-06, "loss": 0.4972, "step": 139020 }, { "epoch": 0.826423191920633, "grad_norm": 6.057635307312012, "learning_rate": 9.870737251576263e-06, "loss": 0.5445, "step": 139030 }, { "epoch": 0.8264826339973014, "grad_norm": 3.825916290283203, "learning_rate": 9.870690372185059e-06, "loss": 0.5531, "step": 139040 }, { "epoch": 0.8265420760739697, "grad_norm": 5.732265949249268, "learning_rate": 9.870643484405946e-06, "loss": 0.5732, "step": 139050 }, { "epoch": 0.8266015181506381, "grad_norm": 5.9360575675964355, "learning_rate": 9.870596588239004e-06, "loss": 0.6238, "step": 139060 }, { "epoch": 0.8266609602273065, "grad_norm": 5.622489929199219, "learning_rate": 9.87054968368431e-06, "loss": 0.5497, "step": 139070 }, { "epoch": 0.8267204023039749, "grad_norm": 5.337497711181641, "learning_rate": 9.870502770741952e-06, "loss": 0.5576, "step": 139080 }, { "epoch": 0.8267798443806433, "grad_norm": 6.343019962310791, "learning_rate": 9.870455849412007e-06, "loss": 0.5841, "step": 139090 }, { "epoch": 0.8268392864573116, "grad_norm": 5.774151802062988, "learning_rate": 9.870408919694554e-06, "loss": 0.5814, "step": 139100 }, { "epoch": 0.82689872853398, "grad_norm": 5.308922290802002, "learning_rate": 9.870361981589675e-06, "loss": 0.552, "step": 139110 }, { "epoch": 0.8269581706106485, "grad_norm": 5.976704120635986, "learning_rate": 9.870315035097453e-06, "loss": 0.5608, "step": 139120 }, { "epoch": 0.8270176126873169, "grad_norm": 5.447536468505859, "learning_rate": 9.870268080217969e-06, "loss": 0.5425, "step": 139130 }, { "epoch": 0.8270770547639852, "grad_norm": 6.237841606140137, "learning_rate": 9.8702211169513e-06, "loss": 0.5511, "step": 139140 }, { "epoch": 0.8271364968406536, "grad_norm": 4.534210205078125, "learning_rate": 9.87017414529753e-06, "loss": 0.5498, "step": 139150 }, { "epoch": 0.827195938917322, "grad_norm": 6.0984110832214355, "learning_rate": 9.870127165256737e-06, "loss": 0.6046, "step": 139160 }, { "epoch": 0.8272553809939904, "grad_norm": 5.629466533660889, "learning_rate": 9.870080176829006e-06, "loss": 0.6137, "step": 139170 }, { "epoch": 0.8273148230706588, "grad_norm": 4.773107051849365, "learning_rate": 9.870033180014417e-06, "loss": 0.6045, "step": 139180 }, { "epoch": 0.8273742651473271, "grad_norm": 6.770414352416992, "learning_rate": 9.869986174813047e-06, "loss": 0.6204, "step": 139190 }, { "epoch": 0.8274337072239956, "grad_norm": 6.751035690307617, "learning_rate": 9.869939161224981e-06, "loss": 0.6109, "step": 139200 }, { "epoch": 0.827493149300664, "grad_norm": 3.9704625606536865, "learning_rate": 9.869892139250299e-06, "loss": 0.5337, "step": 139210 }, { "epoch": 0.8275525913773324, "grad_norm": 4.898076057434082, "learning_rate": 9.869845108889082e-06, "loss": 0.6052, "step": 139220 }, { "epoch": 0.8276120334540007, "grad_norm": 6.1095757484436035, "learning_rate": 9.86979807014141e-06, "loss": 0.5505, "step": 139230 }, { "epoch": 0.8276714755306691, "grad_norm": 5.465587615966797, "learning_rate": 9.869751023007366e-06, "loss": 0.5214, "step": 139240 }, { "epoch": 0.8277309176073375, "grad_norm": 5.737135410308838, "learning_rate": 9.869703967487027e-06, "loss": 0.5878, "step": 139250 }, { "epoch": 0.8277903596840059, "grad_norm": 5.8712477684021, "learning_rate": 9.869656903580478e-06, "loss": 0.5861, "step": 139260 }, { "epoch": 0.8278498017606744, "grad_norm": 5.5255818367004395, "learning_rate": 9.8696098312878e-06, "loss": 0.5414, "step": 139270 }, { "epoch": 0.8279092438373427, "grad_norm": 5.125819206237793, "learning_rate": 9.869562750609072e-06, "loss": 0.5732, "step": 139280 }, { "epoch": 0.8279686859140111, "grad_norm": 6.354130268096924, "learning_rate": 9.869515661544375e-06, "loss": 0.5525, "step": 139290 }, { "epoch": 0.8280281279906795, "grad_norm": 6.411966800689697, "learning_rate": 9.869468564093792e-06, "loss": 0.6123, "step": 139300 }, { "epoch": 0.8280875700673479, "grad_norm": 5.494078636169434, "learning_rate": 9.869421458257403e-06, "loss": 0.5808, "step": 139310 }, { "epoch": 0.8281470121440163, "grad_norm": 5.076481819152832, "learning_rate": 9.869374344035289e-06, "loss": 0.5508, "step": 139320 }, { "epoch": 0.8282064542206846, "grad_norm": 5.875858306884766, "learning_rate": 9.869327221427532e-06, "loss": 0.5461, "step": 139330 }, { "epoch": 0.828265896297353, "grad_norm": 5.645112037658691, "learning_rate": 9.869280090434212e-06, "loss": 0.5525, "step": 139340 }, { "epoch": 0.8283253383740214, "grad_norm": 5.858134746551514, "learning_rate": 9.86923295105541e-06, "loss": 0.5771, "step": 139350 }, { "epoch": 0.8283847804506899, "grad_norm": 4.681911468505859, "learning_rate": 9.869185803291208e-06, "loss": 0.6023, "step": 139360 }, { "epoch": 0.8284442225273582, "grad_norm": 5.818098545074463, "learning_rate": 9.869138647141687e-06, "loss": 0.6067, "step": 139370 }, { "epoch": 0.8285036646040266, "grad_norm": 5.192920207977295, "learning_rate": 9.869091482606929e-06, "loss": 0.539, "step": 139380 }, { "epoch": 0.828563106680695, "grad_norm": 5.286325454711914, "learning_rate": 9.869044309687014e-06, "loss": 0.5555, "step": 139390 }, { "epoch": 0.8286225487573634, "grad_norm": 6.442921161651611, "learning_rate": 9.868997128382026e-06, "loss": 0.5676, "step": 139400 }, { "epoch": 0.8286819908340318, "grad_norm": 6.440704345703125, "learning_rate": 9.868949938692041e-06, "loss": 0.5692, "step": 139410 }, { "epoch": 0.8287414329107001, "grad_norm": 6.480502128601074, "learning_rate": 9.868902740617144e-06, "loss": 0.6268, "step": 139420 }, { "epoch": 0.8288008749873685, "grad_norm": 5.672893047332764, "learning_rate": 9.868855534157416e-06, "loss": 0.4865, "step": 139430 }, { "epoch": 0.828860317064037, "grad_norm": 5.432044506072998, "learning_rate": 9.868808319312939e-06, "loss": 0.5245, "step": 139440 }, { "epoch": 0.8289197591407054, "grad_norm": 5.686212062835693, "learning_rate": 9.868761096083792e-06, "loss": 0.5746, "step": 139450 }, { "epoch": 0.8289792012173738, "grad_norm": 5.324772357940674, "learning_rate": 9.868713864470057e-06, "loss": 0.571, "step": 139460 }, { "epoch": 0.8290386432940421, "grad_norm": 5.490170955657959, "learning_rate": 9.868666624471816e-06, "loss": 0.5534, "step": 139470 }, { "epoch": 0.8290980853707105, "grad_norm": 5.7009172439575195, "learning_rate": 9.86861937608915e-06, "loss": 0.5995, "step": 139480 }, { "epoch": 0.8291575274473789, "grad_norm": 6.556796550750732, "learning_rate": 9.86857211932214e-06, "loss": 0.5975, "step": 139490 }, { "epoch": 0.8292169695240473, "grad_norm": 6.31593656539917, "learning_rate": 9.86852485417087e-06, "loss": 0.5757, "step": 139500 }, { "epoch": 0.8292764116007156, "grad_norm": 5.210354328155518, "learning_rate": 9.868477580635418e-06, "loss": 0.5821, "step": 139510 }, { "epoch": 0.829335853677384, "grad_norm": 5.592891693115234, "learning_rate": 9.868430298715865e-06, "loss": 0.6072, "step": 139520 }, { "epoch": 0.8293952957540525, "grad_norm": 4.2738871574401855, "learning_rate": 9.868383008412296e-06, "loss": 0.519, "step": 139530 }, { "epoch": 0.8294547378307209, "grad_norm": 4.044011116027832, "learning_rate": 9.86833570972479e-06, "loss": 0.6176, "step": 139540 }, { "epoch": 0.8295141799073893, "grad_norm": 6.436260223388672, "learning_rate": 9.86828840265343e-06, "loss": 0.5214, "step": 139550 }, { "epoch": 0.8295736219840576, "grad_norm": 4.395249843597412, "learning_rate": 9.868241087198297e-06, "loss": 0.5781, "step": 139560 }, { "epoch": 0.829633064060726, "grad_norm": 5.304525852203369, "learning_rate": 9.86819376335947e-06, "loss": 0.5096, "step": 139570 }, { "epoch": 0.8296925061373944, "grad_norm": 4.483747959136963, "learning_rate": 9.868146431137033e-06, "loss": 0.5867, "step": 139580 }, { "epoch": 0.8297519482140628, "grad_norm": 6.08120059967041, "learning_rate": 9.868099090531068e-06, "loss": 0.5745, "step": 139590 }, { "epoch": 0.8298113902907311, "grad_norm": 5.092260360717773, "learning_rate": 9.868051741541655e-06, "loss": 0.5409, "step": 139600 }, { "epoch": 0.8298708323673996, "grad_norm": 5.633925914764404, "learning_rate": 9.868004384168876e-06, "loss": 0.612, "step": 139610 }, { "epoch": 0.829930274444068, "grad_norm": 5.932518005371094, "learning_rate": 9.867957018412812e-06, "loss": 0.5326, "step": 139620 }, { "epoch": 0.8299897165207364, "grad_norm": 5.575985431671143, "learning_rate": 9.867909644273545e-06, "loss": 0.6133, "step": 139630 }, { "epoch": 0.8300491585974048, "grad_norm": 5.248621463775635, "learning_rate": 9.867862261751158e-06, "loss": 0.5282, "step": 139640 }, { "epoch": 0.8301086006740731, "grad_norm": 7.206493377685547, "learning_rate": 9.86781487084573e-06, "loss": 0.6221, "step": 139650 }, { "epoch": 0.8301680427507415, "grad_norm": 5.92046594619751, "learning_rate": 9.867767471557345e-06, "loss": 0.5523, "step": 139660 }, { "epoch": 0.8302274848274099, "grad_norm": 5.706782817840576, "learning_rate": 9.867720063886085e-06, "loss": 0.5927, "step": 139670 }, { "epoch": 0.8302869269040783, "grad_norm": 5.916398525238037, "learning_rate": 9.867672647832029e-06, "loss": 0.5589, "step": 139680 }, { "epoch": 0.8303463689807468, "grad_norm": 6.258889675140381, "learning_rate": 9.867625223395258e-06, "loss": 0.5843, "step": 139690 }, { "epoch": 0.8304058110574151, "grad_norm": 4.766593933105469, "learning_rate": 9.867577790575857e-06, "loss": 0.5374, "step": 139700 }, { "epoch": 0.8304652531340835, "grad_norm": 5.165547847747803, "learning_rate": 9.867530349373906e-06, "loss": 0.6065, "step": 139710 }, { "epoch": 0.8305246952107519, "grad_norm": 4.854689121246338, "learning_rate": 9.867482899789489e-06, "loss": 0.6098, "step": 139720 }, { "epoch": 0.8305841372874203, "grad_norm": 6.687388896942139, "learning_rate": 9.867435441822684e-06, "loss": 0.536, "step": 139730 }, { "epoch": 0.8306435793640886, "grad_norm": 5.185444355010986, "learning_rate": 9.867387975473575e-06, "loss": 0.5734, "step": 139740 }, { "epoch": 0.830703021440757, "grad_norm": 5.425928115844727, "learning_rate": 9.867340500742242e-06, "loss": 0.5332, "step": 139750 }, { "epoch": 0.8307624635174254, "grad_norm": 6.234283447265625, "learning_rate": 9.867293017628767e-06, "loss": 0.6052, "step": 139760 }, { "epoch": 0.8308219055940939, "grad_norm": 5.269410610198975, "learning_rate": 9.867245526133235e-06, "loss": 0.5372, "step": 139770 }, { "epoch": 0.8308813476707623, "grad_norm": 5.221168518066406, "learning_rate": 9.867198026255725e-06, "loss": 0.5605, "step": 139780 }, { "epoch": 0.8309407897474306, "grad_norm": 4.426608562469482, "learning_rate": 9.867150517996318e-06, "loss": 0.5, "step": 139790 }, { "epoch": 0.831000231824099, "grad_norm": 6.493476390838623, "learning_rate": 9.867103001355098e-06, "loss": 0.5741, "step": 139800 }, { "epoch": 0.8310596739007674, "grad_norm": 7.2553839683532715, "learning_rate": 9.867055476332145e-06, "loss": 0.642, "step": 139810 }, { "epoch": 0.8311191159774358, "grad_norm": 4.4525909423828125, "learning_rate": 9.867007942927544e-06, "loss": 0.5242, "step": 139820 }, { "epoch": 0.8311785580541042, "grad_norm": 6.349503040313721, "learning_rate": 9.866960401141373e-06, "loss": 0.5384, "step": 139830 }, { "epoch": 0.8312380001307725, "grad_norm": 5.637461185455322, "learning_rate": 9.866912850973715e-06, "loss": 0.5596, "step": 139840 }, { "epoch": 0.831297442207441, "grad_norm": 4.970902442932129, "learning_rate": 9.866865292424653e-06, "loss": 0.5608, "step": 139850 }, { "epoch": 0.8313568842841094, "grad_norm": 4.398055076599121, "learning_rate": 9.866817725494268e-06, "loss": 0.5689, "step": 139860 }, { "epoch": 0.8314163263607778, "grad_norm": 4.726629257202148, "learning_rate": 9.866770150182643e-06, "loss": 0.5307, "step": 139870 }, { "epoch": 0.8314757684374461, "grad_norm": 5.710153102874756, "learning_rate": 9.866722566489858e-06, "loss": 0.5371, "step": 139880 }, { "epoch": 0.8315352105141145, "grad_norm": 6.897692680358887, "learning_rate": 9.866674974415996e-06, "loss": 0.5351, "step": 139890 }, { "epoch": 0.8315946525907829, "grad_norm": 5.387877941131592, "learning_rate": 9.86662737396114e-06, "loss": 0.5441, "step": 139900 }, { "epoch": 0.8316540946674513, "grad_norm": 6.0561418533325195, "learning_rate": 9.866579765125372e-06, "loss": 0.6414, "step": 139910 }, { "epoch": 0.8317135367441197, "grad_norm": 5.897068977355957, "learning_rate": 9.86653214790877e-06, "loss": 0.5966, "step": 139920 }, { "epoch": 0.831772978820788, "grad_norm": 4.574558258056641, "learning_rate": 9.86648452231142e-06, "loss": 0.5505, "step": 139930 }, { "epoch": 0.8318324208974565, "grad_norm": 4.065009593963623, "learning_rate": 9.866436888333404e-06, "loss": 0.5766, "step": 139940 }, { "epoch": 0.8318918629741249, "grad_norm": 5.5836873054504395, "learning_rate": 9.866389245974803e-06, "loss": 0.5415, "step": 139950 }, { "epoch": 0.8319513050507933, "grad_norm": 5.153914928436279, "learning_rate": 9.8663415952357e-06, "loss": 0.615, "step": 139960 }, { "epoch": 0.8320107471274616, "grad_norm": 5.395197868347168, "learning_rate": 9.866293936116173e-06, "loss": 0.5785, "step": 139970 }, { "epoch": 0.83207018920413, "grad_norm": 3.7494094371795654, "learning_rate": 9.866246268616309e-06, "loss": 0.5201, "step": 139980 }, { "epoch": 0.8321296312807984, "grad_norm": 4.4106292724609375, "learning_rate": 9.866198592736189e-06, "loss": 0.5499, "step": 139990 }, { "epoch": 0.8321890733574668, "grad_norm": 4.25979471206665, "learning_rate": 9.866150908475893e-06, "loss": 0.5674, "step": 140000 }, { "epoch": 0.8322485154341352, "grad_norm": 5.10243034362793, "learning_rate": 9.866103215835505e-06, "loss": 0.5938, "step": 140010 }, { "epoch": 0.8323079575108036, "grad_norm": 5.292422294616699, "learning_rate": 9.866055514815108e-06, "loss": 0.4832, "step": 140020 }, { "epoch": 0.832367399587472, "grad_norm": 5.780993461608887, "learning_rate": 9.86600780541478e-06, "loss": 0.5118, "step": 140030 }, { "epoch": 0.8324268416641404, "grad_norm": 5.85142707824707, "learning_rate": 9.865960087634609e-06, "loss": 0.5511, "step": 140040 }, { "epoch": 0.8324862837408088, "grad_norm": 4.566312313079834, "learning_rate": 9.865912361474672e-06, "loss": 0.5343, "step": 140050 }, { "epoch": 0.8325457258174772, "grad_norm": 6.875716209411621, "learning_rate": 9.865864626935054e-06, "loss": 0.5077, "step": 140060 }, { "epoch": 0.8326051678941455, "grad_norm": 5.4390692710876465, "learning_rate": 9.865816884015836e-06, "loss": 0.5499, "step": 140070 }, { "epoch": 0.8326646099708139, "grad_norm": 4.5500030517578125, "learning_rate": 9.865769132717103e-06, "loss": 0.5725, "step": 140080 }, { "epoch": 0.8327240520474823, "grad_norm": 5.9266581535339355, "learning_rate": 9.865721373038933e-06, "loss": 0.52, "step": 140090 }, { "epoch": 0.8327834941241508, "grad_norm": 4.73687744140625, "learning_rate": 9.86567360498141e-06, "loss": 0.6015, "step": 140100 }, { "epoch": 0.8328429362008191, "grad_norm": 5.208380222320557, "learning_rate": 9.865625828544616e-06, "loss": 0.5525, "step": 140110 }, { "epoch": 0.8329023782774875, "grad_norm": 5.458993911743164, "learning_rate": 9.865578043728636e-06, "loss": 0.6289, "step": 140120 }, { "epoch": 0.8329618203541559, "grad_norm": 6.871418476104736, "learning_rate": 9.865530250533548e-06, "loss": 0.5752, "step": 140130 }, { "epoch": 0.8330212624308243, "grad_norm": 4.9249267578125, "learning_rate": 9.865482448959437e-06, "loss": 0.5643, "step": 140140 }, { "epoch": 0.8330807045074927, "grad_norm": 4.707098007202148, "learning_rate": 9.865434639006385e-06, "loss": 0.5533, "step": 140150 }, { "epoch": 0.833140146584161, "grad_norm": 4.625877857208252, "learning_rate": 9.865386820674473e-06, "loss": 0.5597, "step": 140160 }, { "epoch": 0.8331995886608294, "grad_norm": 5.449014186859131, "learning_rate": 9.865338993963786e-06, "loss": 0.6304, "step": 140170 }, { "epoch": 0.8332590307374979, "grad_norm": 5.274393558502197, "learning_rate": 9.865291158874405e-06, "loss": 0.591, "step": 140180 }, { "epoch": 0.8333184728141663, "grad_norm": 5.803737163543701, "learning_rate": 9.86524331540641e-06, "loss": 0.5859, "step": 140190 }, { "epoch": 0.8333779148908347, "grad_norm": 5.777645111083984, "learning_rate": 9.865195463559886e-06, "loss": 0.5201, "step": 140200 }, { "epoch": 0.833437356967503, "grad_norm": 6.929107666015625, "learning_rate": 9.865147603334916e-06, "loss": 0.5767, "step": 140210 }, { "epoch": 0.8334967990441714, "grad_norm": 4.924494743347168, "learning_rate": 9.86509973473158e-06, "loss": 0.5642, "step": 140220 }, { "epoch": 0.8335562411208398, "grad_norm": 5.369465351104736, "learning_rate": 9.865051857749963e-06, "loss": 0.5266, "step": 140230 }, { "epoch": 0.8336156831975082, "grad_norm": 5.002237796783447, "learning_rate": 9.865003972390145e-06, "loss": 0.5393, "step": 140240 }, { "epoch": 0.8336751252741765, "grad_norm": 4.665630340576172, "learning_rate": 9.86495607865221e-06, "loss": 0.5284, "step": 140250 }, { "epoch": 0.833734567350845, "grad_norm": 4.689031600952148, "learning_rate": 9.864908176536242e-06, "loss": 0.5319, "step": 140260 }, { "epoch": 0.8337940094275134, "grad_norm": 5.061739444732666, "learning_rate": 9.86486026604232e-06, "loss": 0.554, "step": 140270 }, { "epoch": 0.8338534515041818, "grad_norm": 7.066031455993652, "learning_rate": 9.86481234717053e-06, "loss": 0.5188, "step": 140280 }, { "epoch": 0.8339128935808502, "grad_norm": 6.502208232879639, "learning_rate": 9.86476441992095e-06, "loss": 0.5542, "step": 140290 }, { "epoch": 0.8339723356575185, "grad_norm": 6.122706890106201, "learning_rate": 9.864716484293665e-06, "loss": 0.6367, "step": 140300 }, { "epoch": 0.8340317777341869, "grad_norm": 5.401340961456299, "learning_rate": 9.864668540288759e-06, "loss": 0.5553, "step": 140310 }, { "epoch": 0.8340912198108553, "grad_norm": 4.903665065765381, "learning_rate": 9.864620587906316e-06, "loss": 0.5547, "step": 140320 }, { "epoch": 0.8341506618875237, "grad_norm": 7.792570114135742, "learning_rate": 9.864572627146412e-06, "loss": 0.6069, "step": 140330 }, { "epoch": 0.834210103964192, "grad_norm": 6.602968215942383, "learning_rate": 9.864524658009135e-06, "loss": 0.5622, "step": 140340 }, { "epoch": 0.8342695460408605, "grad_norm": 5.11869478225708, "learning_rate": 9.864476680494565e-06, "loss": 0.5532, "step": 140350 }, { "epoch": 0.8343289881175289, "grad_norm": 4.659264087677002, "learning_rate": 9.864428694602787e-06, "loss": 0.5576, "step": 140360 }, { "epoch": 0.8343884301941973, "grad_norm": 5.2178192138671875, "learning_rate": 9.864380700333882e-06, "loss": 0.5433, "step": 140370 }, { "epoch": 0.8344478722708657, "grad_norm": 5.890316009521484, "learning_rate": 9.864332697687932e-06, "loss": 0.5808, "step": 140380 }, { "epoch": 0.834507314347534, "grad_norm": 6.085322380065918, "learning_rate": 9.864284686665022e-06, "loss": 0.5444, "step": 140390 }, { "epoch": 0.8345667564242024, "grad_norm": 4.56008243560791, "learning_rate": 9.864236667265235e-06, "loss": 0.5951, "step": 140400 }, { "epoch": 0.8346261985008708, "grad_norm": 4.7221784591674805, "learning_rate": 9.86418863948865e-06, "loss": 0.6151, "step": 140410 }, { "epoch": 0.8346856405775392, "grad_norm": 3.549649238586426, "learning_rate": 9.86414060333535e-06, "loss": 0.5419, "step": 140420 }, { "epoch": 0.8347450826542077, "grad_norm": 4.252392292022705, "learning_rate": 9.864092558805422e-06, "loss": 0.5101, "step": 140430 }, { "epoch": 0.834804524730876, "grad_norm": 4.403762340545654, "learning_rate": 9.864044505898947e-06, "loss": 0.5733, "step": 140440 }, { "epoch": 0.8348639668075444, "grad_norm": 6.212571144104004, "learning_rate": 9.863996444616005e-06, "loss": 0.5655, "step": 140450 }, { "epoch": 0.8349234088842128, "grad_norm": 5.829111099243164, "learning_rate": 9.863948374956681e-06, "loss": 0.6041, "step": 140460 }, { "epoch": 0.8349828509608812, "grad_norm": 5.60336971282959, "learning_rate": 9.863900296921058e-06, "loss": 0.5572, "step": 140470 }, { "epoch": 0.8350422930375495, "grad_norm": 5.588433742523193, "learning_rate": 9.86385221050922e-06, "loss": 0.5543, "step": 140480 }, { "epoch": 0.8351017351142179, "grad_norm": 4.024060249328613, "learning_rate": 9.863804115721244e-06, "loss": 0.5634, "step": 140490 }, { "epoch": 0.8351611771908863, "grad_norm": 6.072021961212158, "learning_rate": 9.863756012557221e-06, "loss": 0.5663, "step": 140500 }, { "epoch": 0.8352206192675548, "grad_norm": 5.300121784210205, "learning_rate": 9.863707901017228e-06, "loss": 0.528, "step": 140510 }, { "epoch": 0.8352800613442232, "grad_norm": 5.129803657531738, "learning_rate": 9.863659781101349e-06, "loss": 0.6093, "step": 140520 }, { "epoch": 0.8353395034208915, "grad_norm": 4.888493061065674, "learning_rate": 9.86361165280967e-06, "loss": 0.5739, "step": 140530 }, { "epoch": 0.8353989454975599, "grad_norm": 4.234374046325684, "learning_rate": 9.86356351614227e-06, "loss": 0.5979, "step": 140540 }, { "epoch": 0.8354583875742283, "grad_norm": 5.848487377166748, "learning_rate": 9.863515371099233e-06, "loss": 0.5954, "step": 140550 }, { "epoch": 0.8355178296508967, "grad_norm": 6.601240158081055, "learning_rate": 9.863467217680643e-06, "loss": 0.6335, "step": 140560 }, { "epoch": 0.8355772717275651, "grad_norm": 5.883572578430176, "learning_rate": 9.86341905588658e-06, "loss": 0.5807, "step": 140570 }, { "epoch": 0.8356367138042334, "grad_norm": 4.7911696434021, "learning_rate": 9.863370885717132e-06, "loss": 0.5737, "step": 140580 }, { "epoch": 0.8356961558809018, "grad_norm": 7.3321685791015625, "learning_rate": 9.863322707172378e-06, "loss": 0.6463, "step": 140590 }, { "epoch": 0.8357555979575703, "grad_norm": 8.441248893737793, "learning_rate": 9.8632745202524e-06, "loss": 0.5613, "step": 140600 }, { "epoch": 0.8358150400342387, "grad_norm": 5.201437950134277, "learning_rate": 9.863226324957285e-06, "loss": 0.5599, "step": 140610 }, { "epoch": 0.835874482110907, "grad_norm": 6.337574481964111, "learning_rate": 9.863178121287114e-06, "loss": 0.562, "step": 140620 }, { "epoch": 0.8359339241875754, "grad_norm": 5.276636123657227, "learning_rate": 9.863129909241969e-06, "loss": 0.5056, "step": 140630 }, { "epoch": 0.8359933662642438, "grad_norm": 5.352782726287842, "learning_rate": 9.863081688821936e-06, "loss": 0.5925, "step": 140640 }, { "epoch": 0.8360528083409122, "grad_norm": 4.747646331787109, "learning_rate": 9.863033460027094e-06, "loss": 0.5563, "step": 140650 }, { "epoch": 0.8361122504175806, "grad_norm": 4.628938674926758, "learning_rate": 9.862985222857529e-06, "loss": 0.5356, "step": 140660 }, { "epoch": 0.8361716924942489, "grad_norm": 5.010149002075195, "learning_rate": 9.862936977313323e-06, "loss": 0.5857, "step": 140670 }, { "epoch": 0.8362311345709174, "grad_norm": 5.599335670471191, "learning_rate": 9.862888723394559e-06, "loss": 0.5945, "step": 140680 }, { "epoch": 0.8362905766475858, "grad_norm": 4.32138204574585, "learning_rate": 9.862840461101322e-06, "loss": 0.6002, "step": 140690 }, { "epoch": 0.8363500187242542, "grad_norm": 5.714219093322754, "learning_rate": 9.862792190433692e-06, "loss": 0.583, "step": 140700 }, { "epoch": 0.8364094608009225, "grad_norm": 5.674745559692383, "learning_rate": 9.862743911391755e-06, "loss": 0.5658, "step": 140710 }, { "epoch": 0.8364689028775909, "grad_norm": 4.302738666534424, "learning_rate": 9.862695623975592e-06, "loss": 0.5576, "step": 140720 }, { "epoch": 0.8365283449542593, "grad_norm": 4.972498416900635, "learning_rate": 9.862647328185287e-06, "loss": 0.6575, "step": 140730 }, { "epoch": 0.8365877870309277, "grad_norm": 5.669658660888672, "learning_rate": 9.862599024020921e-06, "loss": 0.5842, "step": 140740 }, { "epoch": 0.8366472291075961, "grad_norm": 6.536921977996826, "learning_rate": 9.86255071148258e-06, "loss": 0.5759, "step": 140750 }, { "epoch": 0.8367066711842644, "grad_norm": 6.0463972091674805, "learning_rate": 9.86250239057035e-06, "loss": 0.5459, "step": 140760 }, { "epoch": 0.8367661132609329, "grad_norm": 6.817288398742676, "learning_rate": 9.862454061284308e-06, "loss": 0.5833, "step": 140770 }, { "epoch": 0.8368255553376013, "grad_norm": 4.2370686531066895, "learning_rate": 9.862405723624539e-06, "loss": 0.4884, "step": 140780 }, { "epoch": 0.8368849974142697, "grad_norm": 6.463216304779053, "learning_rate": 9.862357377591128e-06, "loss": 0.5203, "step": 140790 }, { "epoch": 0.8369444394909381, "grad_norm": 6.123533725738525, "learning_rate": 9.862309023184157e-06, "loss": 0.5539, "step": 140800 }, { "epoch": 0.8370038815676064, "grad_norm": 4.950366973876953, "learning_rate": 9.862260660403712e-06, "loss": 0.5193, "step": 140810 }, { "epoch": 0.8370633236442748, "grad_norm": 5.029819488525391, "learning_rate": 9.862212289249872e-06, "loss": 0.5898, "step": 140820 }, { "epoch": 0.8371227657209432, "grad_norm": 4.990902900695801, "learning_rate": 9.862163909722724e-06, "loss": 0.5676, "step": 140830 }, { "epoch": 0.8371822077976117, "grad_norm": 5.2505903244018555, "learning_rate": 9.862115521822348e-06, "loss": 0.591, "step": 140840 }, { "epoch": 0.83724164987428, "grad_norm": 4.905167102813721, "learning_rate": 9.862067125548829e-06, "loss": 0.5338, "step": 140850 }, { "epoch": 0.8373010919509484, "grad_norm": 7.488189220428467, "learning_rate": 9.862018720902251e-06, "loss": 0.5327, "step": 140860 }, { "epoch": 0.8373605340276168, "grad_norm": 5.87450647354126, "learning_rate": 9.861970307882696e-06, "loss": 0.5727, "step": 140870 }, { "epoch": 0.8374199761042852, "grad_norm": 5.677415370941162, "learning_rate": 9.86192188649025e-06, "loss": 0.5296, "step": 140880 }, { "epoch": 0.8374794181809536, "grad_norm": 5.051105976104736, "learning_rate": 9.86187345672499e-06, "loss": 0.5902, "step": 140890 }, { "epoch": 0.8375388602576219, "grad_norm": 5.378671646118164, "learning_rate": 9.861825018587007e-06, "loss": 0.5413, "step": 140900 }, { "epoch": 0.8375983023342903, "grad_norm": 6.575228691101074, "learning_rate": 9.86177657207638e-06, "loss": 0.6456, "step": 140910 }, { "epoch": 0.8376577444109587, "grad_norm": 3.3941292762756348, "learning_rate": 9.861728117193194e-06, "loss": 0.5753, "step": 140920 }, { "epoch": 0.8377171864876272, "grad_norm": 5.3502326011657715, "learning_rate": 9.861679653937533e-06, "loss": 0.5449, "step": 140930 }, { "epoch": 0.8377766285642955, "grad_norm": 4.955514430999756, "learning_rate": 9.861631182309478e-06, "loss": 0.5394, "step": 140940 }, { "epoch": 0.8378360706409639, "grad_norm": 6.752377986907959, "learning_rate": 9.861582702309116e-06, "loss": 0.6207, "step": 140950 }, { "epoch": 0.8378955127176323, "grad_norm": 5.270097732543945, "learning_rate": 9.861534213936528e-06, "loss": 0.5421, "step": 140960 }, { "epoch": 0.8379549547943007, "grad_norm": 4.943042755126953, "learning_rate": 9.861485717191796e-06, "loss": 0.5734, "step": 140970 }, { "epoch": 0.8380143968709691, "grad_norm": 4.825284481048584, "learning_rate": 9.861437212075008e-06, "loss": 0.563, "step": 140980 }, { "epoch": 0.8380738389476374, "grad_norm": 4.328440189361572, "learning_rate": 9.861388698586245e-06, "loss": 0.608, "step": 140990 }, { "epoch": 0.8381332810243058, "grad_norm": 4.662580966949463, "learning_rate": 9.861340176725589e-06, "loss": 0.5771, "step": 141000 }, { "epoch": 0.8381927231009743, "grad_norm": 5.513913154602051, "learning_rate": 9.861291646493125e-06, "loss": 0.6014, "step": 141010 }, { "epoch": 0.8382521651776427, "grad_norm": 6.373872756958008, "learning_rate": 9.861243107888939e-06, "loss": 0.5681, "step": 141020 }, { "epoch": 0.8383116072543111, "grad_norm": 4.451208114624023, "learning_rate": 9.86119456091311e-06, "loss": 0.5661, "step": 141030 }, { "epoch": 0.8383710493309794, "grad_norm": 5.590818405151367, "learning_rate": 9.861146005565725e-06, "loss": 0.5437, "step": 141040 }, { "epoch": 0.8384304914076478, "grad_norm": 5.412818908691406, "learning_rate": 9.861097441846866e-06, "loss": 0.5838, "step": 141050 }, { "epoch": 0.8384899334843162, "grad_norm": 5.1923346519470215, "learning_rate": 9.861048869756618e-06, "loss": 0.5928, "step": 141060 }, { "epoch": 0.8385493755609846, "grad_norm": 6.500234603881836, "learning_rate": 9.861000289295065e-06, "loss": 0.5873, "step": 141070 }, { "epoch": 0.8386088176376529, "grad_norm": 4.631768226623535, "learning_rate": 9.860951700462287e-06, "loss": 0.5522, "step": 141080 }, { "epoch": 0.8386682597143214, "grad_norm": 6.061596393585205, "learning_rate": 9.86090310325837e-06, "loss": 0.5792, "step": 141090 }, { "epoch": 0.8387277017909898, "grad_norm": 5.373746395111084, "learning_rate": 9.8608544976834e-06, "loss": 0.5528, "step": 141100 }, { "epoch": 0.8387871438676582, "grad_norm": 6.287784576416016, "learning_rate": 9.860805883737457e-06, "loss": 0.5872, "step": 141110 }, { "epoch": 0.8388465859443266, "grad_norm": 5.965386867523193, "learning_rate": 9.860757261420627e-06, "loss": 0.5728, "step": 141120 }, { "epoch": 0.8389060280209949, "grad_norm": 6.028388023376465, "learning_rate": 9.860708630732993e-06, "loss": 0.5714, "step": 141130 }, { "epoch": 0.8389654700976633, "grad_norm": 6.369855880737305, "learning_rate": 9.860659991674638e-06, "loss": 0.5765, "step": 141140 }, { "epoch": 0.8390249121743317, "grad_norm": 3.9330811500549316, "learning_rate": 9.860611344245647e-06, "loss": 0.5753, "step": 141150 }, { "epoch": 0.8390843542510001, "grad_norm": 5.483523368835449, "learning_rate": 9.860562688446105e-06, "loss": 0.5354, "step": 141160 }, { "epoch": 0.8391437963276686, "grad_norm": 5.520583629608154, "learning_rate": 9.860514024276091e-06, "loss": 0.5629, "step": 141170 }, { "epoch": 0.8392032384043369, "grad_norm": 5.765271186828613, "learning_rate": 9.860465351735694e-06, "loss": 0.5588, "step": 141180 }, { "epoch": 0.8392626804810053, "grad_norm": 4.37895393371582, "learning_rate": 9.860416670824995e-06, "loss": 0.5112, "step": 141190 }, { "epoch": 0.8393221225576737, "grad_norm": 6.474937438964844, "learning_rate": 9.86036798154408e-06, "loss": 0.5443, "step": 141200 }, { "epoch": 0.8393815646343421, "grad_norm": 4.274741172790527, "learning_rate": 9.86031928389303e-06, "loss": 0.5865, "step": 141210 }, { "epoch": 0.8394410067110104, "grad_norm": 4.033744812011719, "learning_rate": 9.860270577871929e-06, "loss": 0.5909, "step": 141220 }, { "epoch": 0.8395004487876788, "grad_norm": 5.907057762145996, "learning_rate": 9.860221863480863e-06, "loss": 0.53, "step": 141230 }, { "epoch": 0.8395598908643472, "grad_norm": 5.227073669433594, "learning_rate": 9.860173140719917e-06, "loss": 0.536, "step": 141240 }, { "epoch": 0.8396193329410157, "grad_norm": 5.384438514709473, "learning_rate": 9.860124409589171e-06, "loss": 0.5648, "step": 141250 }, { "epoch": 0.8396787750176841, "grad_norm": 6.515398025512695, "learning_rate": 9.86007567008871e-06, "loss": 0.58, "step": 141260 }, { "epoch": 0.8397382170943524, "grad_norm": 4.566325664520264, "learning_rate": 9.860026922218622e-06, "loss": 0.5709, "step": 141270 }, { "epoch": 0.8397976591710208, "grad_norm": 5.255915641784668, "learning_rate": 9.859978165978985e-06, "loss": 0.5573, "step": 141280 }, { "epoch": 0.8398571012476892, "grad_norm": 4.988643169403076, "learning_rate": 9.859929401369887e-06, "loss": 0.5278, "step": 141290 }, { "epoch": 0.8399165433243576, "grad_norm": 5.055700778961182, "learning_rate": 9.859880628391411e-06, "loss": 0.4981, "step": 141300 }, { "epoch": 0.8399759854010259, "grad_norm": 4.733333110809326, "learning_rate": 9.85983184704364e-06, "loss": 0.566, "step": 141310 }, { "epoch": 0.8400354274776943, "grad_norm": 4.690618991851807, "learning_rate": 9.859783057326658e-06, "loss": 0.5616, "step": 141320 }, { "epoch": 0.8400948695543627, "grad_norm": 5.755675792694092, "learning_rate": 9.85973425924055e-06, "loss": 0.5601, "step": 141330 }, { "epoch": 0.8401543116310312, "grad_norm": 5.200656414031982, "learning_rate": 9.859685452785401e-06, "loss": 0.6119, "step": 141340 }, { "epoch": 0.8402137537076996, "grad_norm": 5.583456993103027, "learning_rate": 9.859636637961294e-06, "loss": 0.5175, "step": 141350 }, { "epoch": 0.8402731957843679, "grad_norm": 6.189671039581299, "learning_rate": 9.859587814768311e-06, "loss": 0.5151, "step": 141360 }, { "epoch": 0.8403326378610363, "grad_norm": 5.003722667694092, "learning_rate": 9.85953898320654e-06, "loss": 0.5989, "step": 141370 }, { "epoch": 0.8403920799377047, "grad_norm": 4.65822696685791, "learning_rate": 9.85949014327606e-06, "loss": 0.5507, "step": 141380 }, { "epoch": 0.8404515220143731, "grad_norm": 5.222862720489502, "learning_rate": 9.859441294976962e-06, "loss": 0.5614, "step": 141390 }, { "epoch": 0.8405109640910415, "grad_norm": 5.89447546005249, "learning_rate": 9.859392438309324e-06, "loss": 0.5384, "step": 141400 }, { "epoch": 0.8405704061677098, "grad_norm": 6.546347618103027, "learning_rate": 9.859343573273232e-06, "loss": 0.5884, "step": 141410 }, { "epoch": 0.8406298482443783, "grad_norm": 5.872066974639893, "learning_rate": 9.859294699868771e-06, "loss": 0.4873, "step": 141420 }, { "epoch": 0.8406892903210467, "grad_norm": 4.35972785949707, "learning_rate": 9.859245818096025e-06, "loss": 0.5573, "step": 141430 }, { "epoch": 0.8407487323977151, "grad_norm": 5.378326416015625, "learning_rate": 9.859196927955078e-06, "loss": 0.5715, "step": 141440 }, { "epoch": 0.8408081744743834, "grad_norm": 6.061943054199219, "learning_rate": 9.859148029446014e-06, "loss": 0.5418, "step": 141450 }, { "epoch": 0.8408676165510518, "grad_norm": 6.703784942626953, "learning_rate": 9.859099122568917e-06, "loss": 0.5681, "step": 141460 }, { "epoch": 0.8409270586277202, "grad_norm": 5.193583965301514, "learning_rate": 9.859050207323872e-06, "loss": 0.581, "step": 141470 }, { "epoch": 0.8409865007043886, "grad_norm": 5.174554824829102, "learning_rate": 9.859001283710963e-06, "loss": 0.6007, "step": 141480 }, { "epoch": 0.841045942781057, "grad_norm": 4.825377464294434, "learning_rate": 9.858952351730272e-06, "loss": 0.6015, "step": 141490 }, { "epoch": 0.8411053848577253, "grad_norm": 4.352663993835449, "learning_rate": 9.858903411381888e-06, "loss": 0.5199, "step": 141500 }, { "epoch": 0.8411648269343938, "grad_norm": 5.889575958251953, "learning_rate": 9.858854462665892e-06, "loss": 0.5918, "step": 141510 }, { "epoch": 0.8412242690110622, "grad_norm": 3.816673755645752, "learning_rate": 9.858805505582367e-06, "loss": 0.5559, "step": 141520 }, { "epoch": 0.8412837110877306, "grad_norm": 5.161763668060303, "learning_rate": 9.858756540131402e-06, "loss": 0.5123, "step": 141530 }, { "epoch": 0.841343153164399, "grad_norm": 5.3514862060546875, "learning_rate": 9.858707566313078e-06, "loss": 0.5824, "step": 141540 }, { "epoch": 0.8414025952410673, "grad_norm": 5.8951849937438965, "learning_rate": 9.858658584127477e-06, "loss": 0.5592, "step": 141550 }, { "epoch": 0.8414620373177357, "grad_norm": 5.220582962036133, "learning_rate": 9.858609593574688e-06, "loss": 0.567, "step": 141560 }, { "epoch": 0.8415214793944041, "grad_norm": 4.522314071655273, "learning_rate": 9.858560594654793e-06, "loss": 0.5138, "step": 141570 }, { "epoch": 0.8415809214710726, "grad_norm": 5.600509166717529, "learning_rate": 9.858511587367878e-06, "loss": 0.5551, "step": 141580 }, { "epoch": 0.8416403635477409, "grad_norm": 5.041569232940674, "learning_rate": 9.858462571714027e-06, "loss": 0.536, "step": 141590 }, { "epoch": 0.8416998056244093, "grad_norm": 5.747132778167725, "learning_rate": 9.858413547693322e-06, "loss": 0.5479, "step": 141600 }, { "epoch": 0.8417592477010777, "grad_norm": 6.107666492462158, "learning_rate": 9.85836451530585e-06, "loss": 0.4876, "step": 141610 }, { "epoch": 0.8418186897777461, "grad_norm": 6.203664779663086, "learning_rate": 9.858315474551694e-06, "loss": 0.5864, "step": 141620 }, { "epoch": 0.8418781318544145, "grad_norm": 5.061368465423584, "learning_rate": 9.85826642543094e-06, "loss": 0.5095, "step": 141630 }, { "epoch": 0.8419375739310828, "grad_norm": 6.9246320724487305, "learning_rate": 9.858217367943672e-06, "loss": 0.5826, "step": 141640 }, { "epoch": 0.8419970160077512, "grad_norm": 5.516688823699951, "learning_rate": 9.858168302089971e-06, "loss": 0.5419, "step": 141650 }, { "epoch": 0.8420564580844196, "grad_norm": 5.347561359405518, "learning_rate": 9.858119227869928e-06, "loss": 0.529, "step": 141660 }, { "epoch": 0.8421159001610881, "grad_norm": 6.063991069793701, "learning_rate": 9.858070145283622e-06, "loss": 0.5908, "step": 141670 }, { "epoch": 0.8421753422377564, "grad_norm": 5.061859607696533, "learning_rate": 9.85802105433114e-06, "loss": 0.5048, "step": 141680 }, { "epoch": 0.8422347843144248, "grad_norm": 4.586423873901367, "learning_rate": 9.857971955012567e-06, "loss": 0.5519, "step": 141690 }, { "epoch": 0.8422942263910932, "grad_norm": 5.411754608154297, "learning_rate": 9.857922847327985e-06, "loss": 0.5407, "step": 141700 }, { "epoch": 0.8423536684677616, "grad_norm": 4.770437240600586, "learning_rate": 9.857873731277483e-06, "loss": 0.5426, "step": 141710 }, { "epoch": 0.84241311054443, "grad_norm": 4.873641490936279, "learning_rate": 9.857824606861139e-06, "loss": 0.5925, "step": 141720 }, { "epoch": 0.8424725526210983, "grad_norm": 5.3898210525512695, "learning_rate": 9.857775474079044e-06, "loss": 0.5829, "step": 141730 }, { "epoch": 0.8425319946977667, "grad_norm": 5.846620082855225, "learning_rate": 9.857726332931279e-06, "loss": 0.5604, "step": 141740 }, { "epoch": 0.8425914367744352, "grad_norm": 5.208150863647461, "learning_rate": 9.857677183417932e-06, "loss": 0.5605, "step": 141750 }, { "epoch": 0.8426508788511036, "grad_norm": 4.540682315826416, "learning_rate": 9.85762802553908e-06, "loss": 0.5667, "step": 141760 }, { "epoch": 0.842710320927772, "grad_norm": 4.935737609863281, "learning_rate": 9.857578859294818e-06, "loss": 0.5279, "step": 141770 }, { "epoch": 0.8427697630044403, "grad_norm": 5.1736884117126465, "learning_rate": 9.857529684685223e-06, "loss": 0.5372, "step": 141780 }, { "epoch": 0.8428292050811087, "grad_norm": 5.2241058349609375, "learning_rate": 9.857480501710383e-06, "loss": 0.549, "step": 141790 }, { "epoch": 0.8428886471577771, "grad_norm": 4.307036399841309, "learning_rate": 9.857431310370383e-06, "loss": 0.5951, "step": 141800 }, { "epoch": 0.8429480892344455, "grad_norm": 6.842812538146973, "learning_rate": 9.857382110665306e-06, "loss": 0.5667, "step": 141810 }, { "epoch": 0.8430075313111138, "grad_norm": 4.839095115661621, "learning_rate": 9.857332902595236e-06, "loss": 0.5006, "step": 141820 }, { "epoch": 0.8430669733877822, "grad_norm": 6.045256614685059, "learning_rate": 9.857283686160262e-06, "loss": 0.5408, "step": 141830 }, { "epoch": 0.8431264154644507, "grad_norm": 5.320218086242676, "learning_rate": 9.857234461360463e-06, "loss": 0.5232, "step": 141840 }, { "epoch": 0.8431858575411191, "grad_norm": 5.186717987060547, "learning_rate": 9.85718522819593e-06, "loss": 0.4994, "step": 141850 }, { "epoch": 0.8432452996177875, "grad_norm": 4.793790817260742, "learning_rate": 9.857135986666742e-06, "loss": 0.5453, "step": 141860 }, { "epoch": 0.8433047416944558, "grad_norm": 5.290330410003662, "learning_rate": 9.857086736772986e-06, "loss": 0.5078, "step": 141870 }, { "epoch": 0.8433641837711242, "grad_norm": 6.717342376708984, "learning_rate": 9.857037478514748e-06, "loss": 0.597, "step": 141880 }, { "epoch": 0.8434236258477926, "grad_norm": 5.946513652801514, "learning_rate": 9.856988211892112e-06, "loss": 0.6096, "step": 141890 }, { "epoch": 0.843483067924461, "grad_norm": 4.976568222045898, "learning_rate": 9.856938936905163e-06, "loss": 0.5592, "step": 141900 }, { "epoch": 0.8435425100011295, "grad_norm": 4.673635959625244, "learning_rate": 9.856889653553985e-06, "loss": 0.6205, "step": 141910 }, { "epoch": 0.8436019520777978, "grad_norm": 4.951547145843506, "learning_rate": 9.856840361838663e-06, "loss": 0.5563, "step": 141920 }, { "epoch": 0.8436613941544662, "grad_norm": 4.832885265350342, "learning_rate": 9.856791061759284e-06, "loss": 0.5019, "step": 141930 }, { "epoch": 0.8437208362311346, "grad_norm": 5.0173492431640625, "learning_rate": 9.85674175331593e-06, "loss": 0.5519, "step": 141940 }, { "epoch": 0.843780278307803, "grad_norm": 4.36136531829834, "learning_rate": 9.856692436508688e-06, "loss": 0.5467, "step": 141950 }, { "epoch": 0.8438397203844713, "grad_norm": 4.505043029785156, "learning_rate": 9.85664311133764e-06, "loss": 0.4954, "step": 141960 }, { "epoch": 0.8438991624611397, "grad_norm": 9.117058753967285, "learning_rate": 9.856593777802877e-06, "loss": 0.5865, "step": 141970 }, { "epoch": 0.8439586045378081, "grad_norm": 6.580024242401123, "learning_rate": 9.856544435904476e-06, "loss": 0.5996, "step": 141980 }, { "epoch": 0.8440180466144765, "grad_norm": 5.49820613861084, "learning_rate": 9.856495085642528e-06, "loss": 0.579, "step": 141990 }, { "epoch": 0.844077488691145, "grad_norm": 6.00567102432251, "learning_rate": 9.856445727017116e-06, "loss": 0.5231, "step": 142000 }, { "epoch": 0.8441369307678133, "grad_norm": 5.125672817230225, "learning_rate": 9.856396360028325e-06, "loss": 0.566, "step": 142010 }, { "epoch": 0.8441963728444817, "grad_norm": 5.759651184082031, "learning_rate": 9.85634698467624e-06, "loss": 0.5522, "step": 142020 }, { "epoch": 0.8442558149211501, "grad_norm": 8.15746021270752, "learning_rate": 9.856297600960948e-06, "loss": 0.585, "step": 142030 }, { "epoch": 0.8443152569978185, "grad_norm": 5.212609767913818, "learning_rate": 9.856248208882528e-06, "loss": 0.5768, "step": 142040 }, { "epoch": 0.8443746990744868, "grad_norm": 5.895015239715576, "learning_rate": 9.856198808441071e-06, "loss": 0.5628, "step": 142050 }, { "epoch": 0.8444341411511552, "grad_norm": 5.379417419433594, "learning_rate": 9.856149399636661e-06, "loss": 0.5715, "step": 142060 }, { "epoch": 0.8444935832278236, "grad_norm": 4.321889877319336, "learning_rate": 9.856099982469381e-06, "loss": 0.5501, "step": 142070 }, { "epoch": 0.844553025304492, "grad_norm": 5.264270305633545, "learning_rate": 9.856050556939318e-06, "loss": 0.6165, "step": 142080 }, { "epoch": 0.8446124673811605, "grad_norm": 4.4645562171936035, "learning_rate": 9.856001123046556e-06, "loss": 0.5447, "step": 142090 }, { "epoch": 0.8446719094578288, "grad_norm": 6.109877586364746, "learning_rate": 9.855951680791182e-06, "loss": 0.5702, "step": 142100 }, { "epoch": 0.8447313515344972, "grad_norm": 6.217797756195068, "learning_rate": 9.85590223017328e-06, "loss": 0.5849, "step": 142110 }, { "epoch": 0.8447907936111656, "grad_norm": 5.185847759246826, "learning_rate": 9.855852771192933e-06, "loss": 0.5706, "step": 142120 }, { "epoch": 0.844850235687834, "grad_norm": 5.413631916046143, "learning_rate": 9.85580330385023e-06, "loss": 0.5794, "step": 142130 }, { "epoch": 0.8449096777645024, "grad_norm": 5.190606117248535, "learning_rate": 9.855753828145254e-06, "loss": 0.537, "step": 142140 }, { "epoch": 0.8449691198411707, "grad_norm": 5.357807636260986, "learning_rate": 9.85570434407809e-06, "loss": 0.5427, "step": 142150 }, { "epoch": 0.8450285619178391, "grad_norm": 4.725886344909668, "learning_rate": 9.855654851648823e-06, "loss": 0.5735, "step": 142160 }, { "epoch": 0.8450880039945076, "grad_norm": 4.1126790046691895, "learning_rate": 9.85560535085754e-06, "loss": 0.5733, "step": 142170 }, { "epoch": 0.845147446071176, "grad_norm": 5.15375280380249, "learning_rate": 9.855555841704325e-06, "loss": 0.5326, "step": 142180 }, { "epoch": 0.8452068881478443, "grad_norm": 5.105565547943115, "learning_rate": 9.855506324189264e-06, "loss": 0.5482, "step": 142190 }, { "epoch": 0.8452663302245127, "grad_norm": 4.438439846038818, "learning_rate": 9.855456798312441e-06, "loss": 0.619, "step": 142200 }, { "epoch": 0.8453257723011811, "grad_norm": 5.665146827697754, "learning_rate": 9.855407264073942e-06, "loss": 0.5682, "step": 142210 }, { "epoch": 0.8453852143778495, "grad_norm": 6.0326151847839355, "learning_rate": 9.855357721473853e-06, "loss": 0.5526, "step": 142220 }, { "epoch": 0.8454446564545179, "grad_norm": 5.466877460479736, "learning_rate": 9.855308170512258e-06, "loss": 0.5891, "step": 142230 }, { "epoch": 0.8455040985311862, "grad_norm": 4.8484110832214355, "learning_rate": 9.855258611189243e-06, "loss": 0.5313, "step": 142240 }, { "epoch": 0.8455635406078547, "grad_norm": 4.832625865936279, "learning_rate": 9.855209043504894e-06, "loss": 0.536, "step": 142250 }, { "epoch": 0.8456229826845231, "grad_norm": 6.3178277015686035, "learning_rate": 9.855159467459294e-06, "loss": 0.5516, "step": 142260 }, { "epoch": 0.8456824247611915, "grad_norm": 6.889586448669434, "learning_rate": 9.855109883052533e-06, "loss": 0.5765, "step": 142270 }, { "epoch": 0.8457418668378599, "grad_norm": 5.579178333282471, "learning_rate": 9.855060290284692e-06, "loss": 0.6, "step": 142280 }, { "epoch": 0.8458013089145282, "grad_norm": 5.046529769897461, "learning_rate": 9.855010689155857e-06, "loss": 0.5441, "step": 142290 }, { "epoch": 0.8458607509911966, "grad_norm": 5.955338478088379, "learning_rate": 9.854961079666115e-06, "loss": 0.5436, "step": 142300 }, { "epoch": 0.845920193067865, "grad_norm": 5.621807098388672, "learning_rate": 9.85491146181555e-06, "loss": 0.5959, "step": 142310 }, { "epoch": 0.8459796351445334, "grad_norm": 4.580657958984375, "learning_rate": 9.85486183560425e-06, "loss": 0.5403, "step": 142320 }, { "epoch": 0.8460390772212018, "grad_norm": 4.425333499908447, "learning_rate": 9.854812201032298e-06, "loss": 0.5288, "step": 142330 }, { "epoch": 0.8460985192978702, "grad_norm": 5.926555633544922, "learning_rate": 9.85476255809978e-06, "loss": 0.5372, "step": 142340 }, { "epoch": 0.8461579613745386, "grad_norm": 4.676711082458496, "learning_rate": 9.854712906806782e-06, "loss": 0.5688, "step": 142350 }, { "epoch": 0.846217403451207, "grad_norm": 5.426421165466309, "learning_rate": 9.854663247153388e-06, "loss": 0.572, "step": 142360 }, { "epoch": 0.8462768455278754, "grad_norm": 6.710277080535889, "learning_rate": 9.854613579139685e-06, "loss": 0.5369, "step": 142370 }, { "epoch": 0.8463362876045437, "grad_norm": 4.4245476722717285, "learning_rate": 9.85456390276576e-06, "loss": 0.529, "step": 142380 }, { "epoch": 0.8463957296812121, "grad_norm": 7.4722723960876465, "learning_rate": 9.854514218031693e-06, "loss": 0.5776, "step": 142390 }, { "epoch": 0.8464551717578805, "grad_norm": 5.087586402893066, "learning_rate": 9.854464524937576e-06, "loss": 0.5308, "step": 142400 }, { "epoch": 0.846514613834549, "grad_norm": 5.038326740264893, "learning_rate": 9.854414823483492e-06, "loss": 0.5924, "step": 142410 }, { "epoch": 0.8465740559112173, "grad_norm": 6.855976581573486, "learning_rate": 9.854365113669524e-06, "loss": 0.5825, "step": 142420 }, { "epoch": 0.8466334979878857, "grad_norm": 3.746408224105835, "learning_rate": 9.854315395495762e-06, "loss": 0.4855, "step": 142430 }, { "epoch": 0.8466929400645541, "grad_norm": 4.77482795715332, "learning_rate": 9.85426566896229e-06, "loss": 0.5224, "step": 142440 }, { "epoch": 0.8467523821412225, "grad_norm": 4.876230239868164, "learning_rate": 9.854215934069193e-06, "loss": 0.5882, "step": 142450 }, { "epoch": 0.8468118242178909, "grad_norm": 5.793522357940674, "learning_rate": 9.854166190816557e-06, "loss": 0.5456, "step": 142460 }, { "epoch": 0.8468712662945592, "grad_norm": 5.511387348175049, "learning_rate": 9.854116439204466e-06, "loss": 0.5865, "step": 142470 }, { "epoch": 0.8469307083712276, "grad_norm": 5.676822185516357, "learning_rate": 9.85406667923301e-06, "loss": 0.5691, "step": 142480 }, { "epoch": 0.846990150447896, "grad_norm": 4.546668529510498, "learning_rate": 9.85401691090227e-06, "loss": 0.55, "step": 142490 }, { "epoch": 0.8470495925245645, "grad_norm": 6.302399158477783, "learning_rate": 9.853967134212334e-06, "loss": 0.581, "step": 142500 }, { "epoch": 0.8471090346012329, "grad_norm": 4.454656600952148, "learning_rate": 9.853917349163288e-06, "loss": 0.5563, "step": 142510 }, { "epoch": 0.8471684766779012, "grad_norm": 4.861727237701416, "learning_rate": 9.853867555755217e-06, "loss": 0.6099, "step": 142520 }, { "epoch": 0.8472279187545696, "grad_norm": 5.211047172546387, "learning_rate": 9.853817753988206e-06, "loss": 0.5062, "step": 142530 }, { "epoch": 0.847287360831238, "grad_norm": 4.875923156738281, "learning_rate": 9.853767943862344e-06, "loss": 0.5519, "step": 142540 }, { "epoch": 0.8473468029079064, "grad_norm": 4.524112224578857, "learning_rate": 9.853718125377713e-06, "loss": 0.5542, "step": 142550 }, { "epoch": 0.8474062449845747, "grad_norm": 5.7734880447387695, "learning_rate": 9.8536682985344e-06, "loss": 0.5844, "step": 142560 }, { "epoch": 0.8474656870612431, "grad_norm": 5.862663745880127, "learning_rate": 9.85361846333249e-06, "loss": 0.5685, "step": 142570 }, { "epoch": 0.8475251291379116, "grad_norm": 5.214438438415527, "learning_rate": 9.853568619772072e-06, "loss": 0.5337, "step": 142580 }, { "epoch": 0.84758457121458, "grad_norm": 5.952310085296631, "learning_rate": 9.85351876785323e-06, "loss": 0.5416, "step": 142590 }, { "epoch": 0.8476440132912484, "grad_norm": 5.197134017944336, "learning_rate": 9.853468907576047e-06, "loss": 0.5032, "step": 142600 }, { "epoch": 0.8477034553679167, "grad_norm": 5.146749019622803, "learning_rate": 9.853419038940613e-06, "loss": 0.538, "step": 142610 }, { "epoch": 0.8477628974445851, "grad_norm": 6.790847301483154, "learning_rate": 9.853369161947012e-06, "loss": 0.582, "step": 142620 }, { "epoch": 0.8478223395212535, "grad_norm": 3.70151424407959, "learning_rate": 9.85331927659533e-06, "loss": 0.5731, "step": 142630 }, { "epoch": 0.8478817815979219, "grad_norm": 4.763280868530273, "learning_rate": 9.853269382885655e-06, "loss": 0.5197, "step": 142640 }, { "epoch": 0.8479412236745903, "grad_norm": 4.33982515335083, "learning_rate": 9.85321948081807e-06, "loss": 0.5472, "step": 142650 }, { "epoch": 0.8480006657512587, "grad_norm": 5.36690092086792, "learning_rate": 9.853169570392662e-06, "loss": 0.5792, "step": 142660 }, { "epoch": 0.8480601078279271, "grad_norm": 5.331746578216553, "learning_rate": 9.853119651609515e-06, "loss": 0.6128, "step": 142670 }, { "epoch": 0.8481195499045955, "grad_norm": 5.274771213531494, "learning_rate": 9.853069724468719e-06, "loss": 0.6017, "step": 142680 }, { "epoch": 0.8481789919812639, "grad_norm": 5.925686836242676, "learning_rate": 9.853019788970357e-06, "loss": 0.5265, "step": 142690 }, { "epoch": 0.8482384340579322, "grad_norm": 4.595158576965332, "learning_rate": 9.852969845114516e-06, "loss": 0.5841, "step": 142700 }, { "epoch": 0.8482978761346006, "grad_norm": 6.113717555999756, "learning_rate": 9.852919892901283e-06, "loss": 0.5241, "step": 142710 }, { "epoch": 0.848357318211269, "grad_norm": 4.800102710723877, "learning_rate": 9.852869932330743e-06, "loss": 0.5741, "step": 142720 }, { "epoch": 0.8484167602879374, "grad_norm": 4.158102989196777, "learning_rate": 9.852819963402979e-06, "loss": 0.5552, "step": 142730 }, { "epoch": 0.8484762023646059, "grad_norm": 5.806606769561768, "learning_rate": 9.852769986118083e-06, "loss": 0.601, "step": 142740 }, { "epoch": 0.8485356444412742, "grad_norm": 3.8712806701660156, "learning_rate": 9.852720000476135e-06, "loss": 0.5571, "step": 142750 }, { "epoch": 0.8485950865179426, "grad_norm": 6.019539833068848, "learning_rate": 9.852670006477228e-06, "loss": 0.5577, "step": 142760 }, { "epoch": 0.848654528594611, "grad_norm": 4.606399059295654, "learning_rate": 9.852620004121441e-06, "loss": 0.4869, "step": 142770 }, { "epoch": 0.8487139706712794, "grad_norm": 6.094393730163574, "learning_rate": 9.852569993408865e-06, "loss": 0.4921, "step": 142780 }, { "epoch": 0.8487734127479477, "grad_norm": 3.9429798126220703, "learning_rate": 9.852519974339585e-06, "loss": 0.5825, "step": 142790 }, { "epoch": 0.8488328548246161, "grad_norm": 5.451361179351807, "learning_rate": 9.852469946913686e-06, "loss": 0.5825, "step": 142800 }, { "epoch": 0.8488922969012845, "grad_norm": 5.758976936340332, "learning_rate": 9.852419911131253e-06, "loss": 0.5176, "step": 142810 }, { "epoch": 0.848951738977953, "grad_norm": 5.106110572814941, "learning_rate": 9.852369866992377e-06, "loss": 0.5591, "step": 142820 }, { "epoch": 0.8490111810546214, "grad_norm": 5.293451309204102, "learning_rate": 9.852319814497137e-06, "loss": 0.6054, "step": 142830 }, { "epoch": 0.8490706231312897, "grad_norm": 6.304245948791504, "learning_rate": 9.852269753645628e-06, "loss": 0.5465, "step": 142840 }, { "epoch": 0.8491300652079581, "grad_norm": 5.464313507080078, "learning_rate": 9.85221968443793e-06, "loss": 0.5049, "step": 142850 }, { "epoch": 0.8491895072846265, "grad_norm": 5.474896430969238, "learning_rate": 9.852169606874128e-06, "loss": 0.5968, "step": 142860 }, { "epoch": 0.8492489493612949, "grad_norm": 4.621715068817139, "learning_rate": 9.852119520954314e-06, "loss": 0.5482, "step": 142870 }, { "epoch": 0.8493083914379633, "grad_norm": 5.5138349533081055, "learning_rate": 9.85206942667857e-06, "loss": 0.5643, "step": 142880 }, { "epoch": 0.8493678335146316, "grad_norm": 4.791072368621826, "learning_rate": 9.852019324046984e-06, "loss": 0.5153, "step": 142890 }, { "epoch": 0.8494272755913, "grad_norm": 5.829113960266113, "learning_rate": 9.851969213059642e-06, "loss": 0.5398, "step": 142900 }, { "epoch": 0.8494867176679685, "grad_norm": 5.72302770614624, "learning_rate": 9.85191909371663e-06, "loss": 0.5732, "step": 142910 }, { "epoch": 0.8495461597446369, "grad_norm": 5.524179935455322, "learning_rate": 9.851868966018034e-06, "loss": 0.5297, "step": 142920 }, { "epoch": 0.8496056018213052, "grad_norm": 4.143937110900879, "learning_rate": 9.851818829963941e-06, "loss": 0.5042, "step": 142930 }, { "epoch": 0.8496650438979736, "grad_norm": 3.90934681892395, "learning_rate": 9.851768685554437e-06, "loss": 0.5578, "step": 142940 }, { "epoch": 0.849724485974642, "grad_norm": 5.630867004394531, "learning_rate": 9.851718532789607e-06, "loss": 0.5182, "step": 142950 }, { "epoch": 0.8497839280513104, "grad_norm": 5.803237438201904, "learning_rate": 9.851668371669541e-06, "loss": 0.5621, "step": 142960 }, { "epoch": 0.8498433701279788, "grad_norm": 4.648175239562988, "learning_rate": 9.851618202194322e-06, "loss": 0.5662, "step": 142970 }, { "epoch": 0.8499028122046471, "grad_norm": 5.6604509353637695, "learning_rate": 9.851568024364037e-06, "loss": 0.5445, "step": 142980 }, { "epoch": 0.8499622542813156, "grad_norm": 4.739546775817871, "learning_rate": 9.851517838178775e-06, "loss": 0.5258, "step": 142990 }, { "epoch": 0.850021696357984, "grad_norm": 4.193034648895264, "learning_rate": 9.851467643638619e-06, "loss": 0.5804, "step": 143000 }, { "epoch": 0.8500811384346524, "grad_norm": 4.634267330169678, "learning_rate": 9.851417440743658e-06, "loss": 0.5573, "step": 143010 }, { "epoch": 0.8501405805113208, "grad_norm": 5.449896335601807, "learning_rate": 9.851367229493975e-06, "loss": 0.565, "step": 143020 }, { "epoch": 0.8502000225879891, "grad_norm": 4.120992183685303, "learning_rate": 9.85131700988966e-06, "loss": 0.5695, "step": 143030 }, { "epoch": 0.8502594646646575, "grad_norm": 6.294850826263428, "learning_rate": 9.8512667819308e-06, "loss": 0.5309, "step": 143040 }, { "epoch": 0.8503189067413259, "grad_norm": 6.2946343421936035, "learning_rate": 9.851216545617478e-06, "loss": 0.5436, "step": 143050 }, { "epoch": 0.8503783488179943, "grad_norm": 4.700998783111572, "learning_rate": 9.851166300949781e-06, "loss": 0.5205, "step": 143060 }, { "epoch": 0.8504377908946626, "grad_norm": 6.337244510650635, "learning_rate": 9.8511160479278e-06, "loss": 0.5966, "step": 143070 }, { "epoch": 0.8504972329713311, "grad_norm": 5.686306476593018, "learning_rate": 9.851065786551617e-06, "loss": 0.5513, "step": 143080 }, { "epoch": 0.8505566750479995, "grad_norm": 5.505003452301025, "learning_rate": 9.851015516821319e-06, "loss": 0.5057, "step": 143090 }, { "epoch": 0.8506161171246679, "grad_norm": 4.743448734283447, "learning_rate": 9.850965238736994e-06, "loss": 0.5503, "step": 143100 }, { "epoch": 0.8506755592013363, "grad_norm": 5.181585788726807, "learning_rate": 9.850914952298727e-06, "loss": 0.5566, "step": 143110 }, { "epoch": 0.8507350012780046, "grad_norm": 5.968530654907227, "learning_rate": 9.850864657506607e-06, "loss": 0.5746, "step": 143120 }, { "epoch": 0.850794443354673, "grad_norm": 5.550162315368652, "learning_rate": 9.85081435436072e-06, "loss": 0.5659, "step": 143130 }, { "epoch": 0.8508538854313414, "grad_norm": 4.4228620529174805, "learning_rate": 9.85076404286115e-06, "loss": 0.5246, "step": 143140 }, { "epoch": 0.8509133275080099, "grad_norm": 5.825507164001465, "learning_rate": 9.850713723007987e-06, "loss": 0.5553, "step": 143150 }, { "epoch": 0.8509727695846782, "grad_norm": 5.360423564910889, "learning_rate": 9.850663394801316e-06, "loss": 0.5506, "step": 143160 }, { "epoch": 0.8510322116613466, "grad_norm": 6.1923747062683105, "learning_rate": 9.850613058241222e-06, "loss": 0.5954, "step": 143170 }, { "epoch": 0.851091653738015, "grad_norm": 4.408834934234619, "learning_rate": 9.850562713327797e-06, "loss": 0.5011, "step": 143180 }, { "epoch": 0.8511510958146834, "grad_norm": 4.486638069152832, "learning_rate": 9.85051236006112e-06, "loss": 0.5713, "step": 143190 }, { "epoch": 0.8512105378913518, "grad_norm": 5.039750099182129, "learning_rate": 9.850461998441286e-06, "loss": 0.6125, "step": 143200 }, { "epoch": 0.8512699799680201, "grad_norm": 4.233029842376709, "learning_rate": 9.850411628468375e-06, "loss": 0.5114, "step": 143210 }, { "epoch": 0.8513294220446885, "grad_norm": 4.084397792816162, "learning_rate": 9.850361250142476e-06, "loss": 0.5422, "step": 143220 }, { "epoch": 0.851388864121357, "grad_norm": 7.722986698150635, "learning_rate": 9.850310863463679e-06, "loss": 0.5997, "step": 143230 }, { "epoch": 0.8514483061980254, "grad_norm": 4.146054267883301, "learning_rate": 9.850260468432066e-06, "loss": 0.566, "step": 143240 }, { "epoch": 0.8515077482746938, "grad_norm": 6.094162464141846, "learning_rate": 9.850210065047726e-06, "loss": 0.5651, "step": 143250 }, { "epoch": 0.8515671903513621, "grad_norm": 5.372693061828613, "learning_rate": 9.850159653310746e-06, "loss": 0.5795, "step": 143260 }, { "epoch": 0.8516266324280305, "grad_norm": 4.779378890991211, "learning_rate": 9.850109233221212e-06, "loss": 0.5798, "step": 143270 }, { "epoch": 0.8516860745046989, "grad_norm": 6.40433406829834, "learning_rate": 9.850058804779213e-06, "loss": 0.5765, "step": 143280 }, { "epoch": 0.8517455165813673, "grad_norm": 5.5523762702941895, "learning_rate": 9.850008367984832e-06, "loss": 0.5664, "step": 143290 }, { "epoch": 0.8518049586580356, "grad_norm": 6.400053977966309, "learning_rate": 9.849957922838157e-06, "loss": 0.5411, "step": 143300 }, { "epoch": 0.851864400734704, "grad_norm": 5.435807228088379, "learning_rate": 9.849907469339277e-06, "loss": 0.5409, "step": 143310 }, { "epoch": 0.8519238428113725, "grad_norm": 5.156802654266357, "learning_rate": 9.849857007488277e-06, "loss": 0.5616, "step": 143320 }, { "epoch": 0.8519832848880409, "grad_norm": 4.527974605560303, "learning_rate": 9.849806537285246e-06, "loss": 0.5689, "step": 143330 }, { "epoch": 0.8520427269647093, "grad_norm": 5.7280659675598145, "learning_rate": 9.84975605873027e-06, "loss": 0.554, "step": 143340 }, { "epoch": 0.8521021690413776, "grad_norm": 5.347686767578125, "learning_rate": 9.849705571823434e-06, "loss": 0.5142, "step": 143350 }, { "epoch": 0.852161611118046, "grad_norm": 5.781463623046875, "learning_rate": 9.849655076564826e-06, "loss": 0.5655, "step": 143360 }, { "epoch": 0.8522210531947144, "grad_norm": 5.982684135437012, "learning_rate": 9.849604572954533e-06, "loss": 0.5777, "step": 143370 }, { "epoch": 0.8522804952713828, "grad_norm": 5.713161945343018, "learning_rate": 9.849554060992642e-06, "loss": 0.5547, "step": 143380 }, { "epoch": 0.8523399373480512, "grad_norm": 5.055454254150391, "learning_rate": 9.849503540679243e-06, "loss": 0.5926, "step": 143390 }, { "epoch": 0.8523993794247195, "grad_norm": 4.162219524383545, "learning_rate": 9.849453012014418e-06, "loss": 0.5209, "step": 143400 }, { "epoch": 0.852458821501388, "grad_norm": 5.429047584533691, "learning_rate": 9.849402474998258e-06, "loss": 0.5657, "step": 143410 }, { "epoch": 0.8525182635780564, "grad_norm": 6.377645492553711, "learning_rate": 9.849351929630845e-06, "loss": 0.5907, "step": 143420 }, { "epoch": 0.8525777056547248, "grad_norm": 3.193744659423828, "learning_rate": 9.849301375912272e-06, "loss": 0.6117, "step": 143430 }, { "epoch": 0.8526371477313931, "grad_norm": 4.744518756866455, "learning_rate": 9.849250813842624e-06, "loss": 0.5279, "step": 143440 }, { "epoch": 0.8526965898080615, "grad_norm": 8.615757942199707, "learning_rate": 9.849200243421986e-06, "loss": 0.5532, "step": 143450 }, { "epoch": 0.8527560318847299, "grad_norm": 5.686349391937256, "learning_rate": 9.849149664650448e-06, "loss": 0.6137, "step": 143460 }, { "epoch": 0.8528154739613983, "grad_norm": 5.033318519592285, "learning_rate": 9.849099077528095e-06, "loss": 0.6284, "step": 143470 }, { "epoch": 0.8528749160380668, "grad_norm": 6.6584296226501465, "learning_rate": 9.849048482055013e-06, "loss": 0.5488, "step": 143480 }, { "epoch": 0.8529343581147351, "grad_norm": 5.240087509155273, "learning_rate": 9.848997878231294e-06, "loss": 0.5243, "step": 143490 }, { "epoch": 0.8529938001914035, "grad_norm": 4.093656539916992, "learning_rate": 9.84894726605702e-06, "loss": 0.5688, "step": 143500 }, { "epoch": 0.8530532422680719, "grad_norm": 5.960449695587158, "learning_rate": 9.84889664553228e-06, "loss": 0.5274, "step": 143510 }, { "epoch": 0.8531126843447403, "grad_norm": 6.847845554351807, "learning_rate": 9.848846016657163e-06, "loss": 0.5445, "step": 143520 }, { "epoch": 0.8531721264214086, "grad_norm": 5.586961269378662, "learning_rate": 9.848795379431754e-06, "loss": 0.5386, "step": 143530 }, { "epoch": 0.853231568498077, "grad_norm": 5.810605049133301, "learning_rate": 9.84874473385614e-06, "loss": 0.5177, "step": 143540 }, { "epoch": 0.8532910105747454, "grad_norm": 5.448703289031982, "learning_rate": 9.84869407993041e-06, "loss": 0.5701, "step": 143550 }, { "epoch": 0.8533504526514138, "grad_norm": 5.922944068908691, "learning_rate": 9.84864341765465e-06, "loss": 0.5756, "step": 143560 }, { "epoch": 0.8534098947280823, "grad_norm": 3.771709680557251, "learning_rate": 9.848592747028947e-06, "loss": 0.5276, "step": 143570 }, { "epoch": 0.8534693368047506, "grad_norm": 6.313287734985352, "learning_rate": 9.848542068053389e-06, "loss": 0.5362, "step": 143580 }, { "epoch": 0.853528778881419, "grad_norm": 5.187442302703857, "learning_rate": 9.848491380728063e-06, "loss": 0.5644, "step": 143590 }, { "epoch": 0.8535882209580874, "grad_norm": 5.366920471191406, "learning_rate": 9.848440685053058e-06, "loss": 0.5634, "step": 143600 }, { "epoch": 0.8536476630347558, "grad_norm": 4.544966697692871, "learning_rate": 9.848389981028457e-06, "loss": 0.5583, "step": 143610 }, { "epoch": 0.8537071051114242, "grad_norm": 6.2455573081970215, "learning_rate": 9.848339268654352e-06, "loss": 0.5719, "step": 143620 }, { "epoch": 0.8537665471880925, "grad_norm": 4.517636299133301, "learning_rate": 9.848288547930827e-06, "loss": 0.6242, "step": 143630 }, { "epoch": 0.8538259892647609, "grad_norm": 4.88145112991333, "learning_rate": 9.848237818857971e-06, "loss": 0.5521, "step": 143640 }, { "epoch": 0.8538854313414294, "grad_norm": 4.440915107727051, "learning_rate": 9.848187081435871e-06, "loss": 0.5151, "step": 143650 }, { "epoch": 0.8539448734180978, "grad_norm": 4.853416442871094, "learning_rate": 9.848136335664615e-06, "loss": 0.5277, "step": 143660 }, { "epoch": 0.8540043154947661, "grad_norm": 6.5681257247924805, "learning_rate": 9.848085581544289e-06, "loss": 0.5222, "step": 143670 }, { "epoch": 0.8540637575714345, "grad_norm": 5.719358444213867, "learning_rate": 9.84803481907498e-06, "loss": 0.5603, "step": 143680 }, { "epoch": 0.8541231996481029, "grad_norm": 4.8782453536987305, "learning_rate": 9.847984048256779e-06, "loss": 0.5689, "step": 143690 }, { "epoch": 0.8541826417247713, "grad_norm": 4.66285514831543, "learning_rate": 9.84793326908977e-06, "loss": 0.5629, "step": 143700 }, { "epoch": 0.8542420838014397, "grad_norm": 5.485621452331543, "learning_rate": 9.847882481574041e-06, "loss": 0.5717, "step": 143710 }, { "epoch": 0.854301525878108, "grad_norm": 5.648228645324707, "learning_rate": 9.847831685709682e-06, "loss": 0.6051, "step": 143720 }, { "epoch": 0.8543609679547765, "grad_norm": 4.175764083862305, "learning_rate": 9.847780881496776e-06, "loss": 0.5458, "step": 143730 }, { "epoch": 0.8544204100314449, "grad_norm": 5.012580871582031, "learning_rate": 9.847730068935413e-06, "loss": 0.595, "step": 143740 }, { "epoch": 0.8544798521081133, "grad_norm": 5.146087646484375, "learning_rate": 9.847679248025682e-06, "loss": 0.5943, "step": 143750 }, { "epoch": 0.8545392941847817, "grad_norm": 6.647322654724121, "learning_rate": 9.847628418767667e-06, "loss": 0.5906, "step": 143760 }, { "epoch": 0.85459873626145, "grad_norm": 5.894828796386719, "learning_rate": 9.847577581161457e-06, "loss": 0.5909, "step": 143770 }, { "epoch": 0.8546581783381184, "grad_norm": 5.867687225341797, "learning_rate": 9.847526735207142e-06, "loss": 0.5507, "step": 143780 }, { "epoch": 0.8547176204147868, "grad_norm": 4.540122985839844, "learning_rate": 9.847475880904809e-06, "loss": 0.5316, "step": 143790 }, { "epoch": 0.8547770624914552, "grad_norm": 4.360832214355469, "learning_rate": 9.847425018254541e-06, "loss": 0.5363, "step": 143800 }, { "epoch": 0.8548365045681235, "grad_norm": 4.716236114501953, "learning_rate": 9.84737414725643e-06, "loss": 0.5449, "step": 143810 }, { "epoch": 0.854895946644792, "grad_norm": 5.150199890136719, "learning_rate": 9.847323267910562e-06, "loss": 0.5603, "step": 143820 }, { "epoch": 0.8549553887214604, "grad_norm": 6.506077766418457, "learning_rate": 9.847272380217025e-06, "loss": 0.5899, "step": 143830 }, { "epoch": 0.8550148307981288, "grad_norm": 5.179149627685547, "learning_rate": 9.847221484175907e-06, "loss": 0.5411, "step": 143840 }, { "epoch": 0.8550742728747972, "grad_norm": 4.191945552825928, "learning_rate": 9.847170579787296e-06, "loss": 0.6182, "step": 143850 }, { "epoch": 0.8551337149514655, "grad_norm": 5.785017490386963, "learning_rate": 9.847119667051276e-06, "loss": 0.6288, "step": 143860 }, { "epoch": 0.8551931570281339, "grad_norm": 4.846682071685791, "learning_rate": 9.84706874596794e-06, "loss": 0.5174, "step": 143870 }, { "epoch": 0.8552525991048023, "grad_norm": 4.189547061920166, "learning_rate": 9.847017816537373e-06, "loss": 0.5938, "step": 143880 }, { "epoch": 0.8553120411814708, "grad_norm": 6.960559844970703, "learning_rate": 9.846966878759663e-06, "loss": 0.5471, "step": 143890 }, { "epoch": 0.855371483258139, "grad_norm": 4.924726963043213, "learning_rate": 9.846915932634898e-06, "loss": 0.5504, "step": 143900 }, { "epoch": 0.8554309253348075, "grad_norm": 5.185710906982422, "learning_rate": 9.846864978163163e-06, "loss": 0.5664, "step": 143910 }, { "epoch": 0.8554903674114759, "grad_norm": 4.987305641174316, "learning_rate": 9.846814015344551e-06, "loss": 0.5306, "step": 143920 }, { "epoch": 0.8555498094881443, "grad_norm": 6.084049701690674, "learning_rate": 9.846763044179145e-06, "loss": 0.5854, "step": 143930 }, { "epoch": 0.8556092515648127, "grad_norm": 5.846210956573486, "learning_rate": 9.846712064667037e-06, "loss": 0.5581, "step": 143940 }, { "epoch": 0.855668693641481, "grad_norm": 5.3603196144104, "learning_rate": 9.84666107680831e-06, "loss": 0.6371, "step": 143950 }, { "epoch": 0.8557281357181494, "grad_norm": 5.218846797943115, "learning_rate": 9.846610080603058e-06, "loss": 0.5449, "step": 143960 }, { "epoch": 0.8557875777948178, "grad_norm": 5.152364253997803, "learning_rate": 9.846559076051362e-06, "loss": 0.5407, "step": 143970 }, { "epoch": 0.8558470198714863, "grad_norm": 5.611238956451416, "learning_rate": 9.846508063153314e-06, "loss": 0.6095, "step": 143980 }, { "epoch": 0.8559064619481547, "grad_norm": 5.662067890167236, "learning_rate": 9.846457041909e-06, "loss": 0.5312, "step": 143990 }, { "epoch": 0.855965904024823, "grad_norm": 3.2027454376220703, "learning_rate": 9.84640601231851e-06, "loss": 0.5036, "step": 144000 }, { "epoch": 0.8560253461014914, "grad_norm": 7.423748970031738, "learning_rate": 9.846354974381929e-06, "loss": 0.629, "step": 144010 }, { "epoch": 0.8560847881781598, "grad_norm": 5.226931571960449, "learning_rate": 9.846303928099348e-06, "loss": 0.5584, "step": 144020 }, { "epoch": 0.8561442302548282, "grad_norm": 6.164569854736328, "learning_rate": 9.846252873470853e-06, "loss": 0.628, "step": 144030 }, { "epoch": 0.8562036723314965, "grad_norm": 6.264813423156738, "learning_rate": 9.846201810496532e-06, "loss": 0.5849, "step": 144040 }, { "epoch": 0.8562631144081649, "grad_norm": 5.878156661987305, "learning_rate": 9.846150739176472e-06, "loss": 0.5522, "step": 144050 }, { "epoch": 0.8563225564848334, "grad_norm": 5.012882232666016, "learning_rate": 9.846099659510764e-06, "loss": 0.5245, "step": 144060 }, { "epoch": 0.8563819985615018, "grad_norm": 6.153093338012695, "learning_rate": 9.846048571499494e-06, "loss": 0.5771, "step": 144070 }, { "epoch": 0.8564414406381702, "grad_norm": 3.9953622817993164, "learning_rate": 9.84599747514275e-06, "loss": 0.5758, "step": 144080 }, { "epoch": 0.8565008827148385, "grad_norm": 5.163275241851807, "learning_rate": 9.84594637044062e-06, "loss": 0.5408, "step": 144090 }, { "epoch": 0.8565603247915069, "grad_norm": 3.9830188751220703, "learning_rate": 9.845895257393192e-06, "loss": 0.5346, "step": 144100 }, { "epoch": 0.8566197668681753, "grad_norm": 4.789117336273193, "learning_rate": 9.845844136000554e-06, "loss": 0.6148, "step": 144110 }, { "epoch": 0.8566792089448437, "grad_norm": 5.576879501342773, "learning_rate": 9.845793006262795e-06, "loss": 0.5539, "step": 144120 }, { "epoch": 0.856738651021512, "grad_norm": 5.882312297821045, "learning_rate": 9.84574186818e-06, "loss": 0.5492, "step": 144130 }, { "epoch": 0.8567980930981804, "grad_norm": 4.782002925872803, "learning_rate": 9.845690721752262e-06, "loss": 0.5404, "step": 144140 }, { "epoch": 0.8568575351748489, "grad_norm": 6.221885681152344, "learning_rate": 9.845639566979666e-06, "loss": 0.5711, "step": 144150 }, { "epoch": 0.8569169772515173, "grad_norm": 4.785511016845703, "learning_rate": 9.845588403862299e-06, "loss": 0.5987, "step": 144160 }, { "epoch": 0.8569764193281857, "grad_norm": 3.829005241394043, "learning_rate": 9.845537232400252e-06, "loss": 0.5801, "step": 144170 }, { "epoch": 0.857035861404854, "grad_norm": 5.89675760269165, "learning_rate": 9.845486052593612e-06, "loss": 0.5657, "step": 144180 }, { "epoch": 0.8570953034815224, "grad_norm": 5.507602691650391, "learning_rate": 9.845434864442465e-06, "loss": 0.5894, "step": 144190 }, { "epoch": 0.8571547455581908, "grad_norm": 5.066368579864502, "learning_rate": 9.845383667946901e-06, "loss": 0.5764, "step": 144200 }, { "epoch": 0.8572141876348592, "grad_norm": 6.0973124504089355, "learning_rate": 9.845332463107012e-06, "loss": 0.5434, "step": 144210 }, { "epoch": 0.8572736297115277, "grad_norm": 4.85703706741333, "learning_rate": 9.845281249922878e-06, "loss": 0.5378, "step": 144220 }, { "epoch": 0.857333071788196, "grad_norm": 3.696463108062744, "learning_rate": 9.845230028394593e-06, "loss": 0.5616, "step": 144230 }, { "epoch": 0.8573925138648644, "grad_norm": 4.460974216461182, "learning_rate": 9.845178798522244e-06, "loss": 0.5754, "step": 144240 }, { "epoch": 0.8574519559415328, "grad_norm": 4.777985572814941, "learning_rate": 9.845127560305919e-06, "loss": 0.5732, "step": 144250 }, { "epoch": 0.8575113980182012, "grad_norm": 4.294107437133789, "learning_rate": 9.845076313745707e-06, "loss": 0.5436, "step": 144260 }, { "epoch": 0.8575708400948695, "grad_norm": 5.92710018157959, "learning_rate": 9.845025058841695e-06, "loss": 0.6134, "step": 144270 }, { "epoch": 0.8576302821715379, "grad_norm": 6.081030368804932, "learning_rate": 9.84497379559397e-06, "loss": 0.5261, "step": 144280 }, { "epoch": 0.8576897242482063, "grad_norm": 7.6016106605529785, "learning_rate": 9.844922524002624e-06, "loss": 0.6066, "step": 144290 }, { "epoch": 0.8577491663248747, "grad_norm": 4.178324222564697, "learning_rate": 9.844871244067743e-06, "loss": 0.5202, "step": 144300 }, { "epoch": 0.8578086084015432, "grad_norm": 5.115005970001221, "learning_rate": 9.844819955789416e-06, "loss": 0.5049, "step": 144310 }, { "epoch": 0.8578680504782115, "grad_norm": 5.3076090812683105, "learning_rate": 9.84476865916773e-06, "loss": 0.5192, "step": 144320 }, { "epoch": 0.8579274925548799, "grad_norm": 5.314327716827393, "learning_rate": 9.844717354202774e-06, "loss": 0.568, "step": 144330 }, { "epoch": 0.8579869346315483, "grad_norm": 6.620693683624268, "learning_rate": 9.844666040894637e-06, "loss": 0.558, "step": 144340 }, { "epoch": 0.8580463767082167, "grad_norm": 5.128243446350098, "learning_rate": 9.844614719243408e-06, "loss": 0.6331, "step": 144350 }, { "epoch": 0.8581058187848851, "grad_norm": 3.9586148262023926, "learning_rate": 9.844563389249174e-06, "loss": 0.5269, "step": 144360 }, { "epoch": 0.8581652608615534, "grad_norm": 5.161381721496582, "learning_rate": 9.844512050912023e-06, "loss": 0.5635, "step": 144370 }, { "epoch": 0.8582247029382218, "grad_norm": 5.012048721313477, "learning_rate": 9.844460704232045e-06, "loss": 0.5208, "step": 144380 }, { "epoch": 0.8582841450148903, "grad_norm": 5.529964923858643, "learning_rate": 9.844409349209327e-06, "loss": 0.5561, "step": 144390 }, { "epoch": 0.8583435870915587, "grad_norm": 5.090838432312012, "learning_rate": 9.844357985843959e-06, "loss": 0.5601, "step": 144400 }, { "epoch": 0.858403029168227, "grad_norm": 4.383176326751709, "learning_rate": 9.844306614136027e-06, "loss": 0.5308, "step": 144410 }, { "epoch": 0.8584624712448954, "grad_norm": 6.218502044677734, "learning_rate": 9.844255234085622e-06, "loss": 0.5561, "step": 144420 }, { "epoch": 0.8585219133215638, "grad_norm": 6.249056339263916, "learning_rate": 9.844203845692832e-06, "loss": 0.5923, "step": 144430 }, { "epoch": 0.8585813553982322, "grad_norm": 5.014588832855225, "learning_rate": 9.844152448957745e-06, "loss": 0.605, "step": 144440 }, { "epoch": 0.8586407974749006, "grad_norm": 7.157752513885498, "learning_rate": 9.84410104388045e-06, "loss": 0.5545, "step": 144450 }, { "epoch": 0.8587002395515689, "grad_norm": 4.922757148742676, "learning_rate": 9.844049630461032e-06, "loss": 0.5453, "step": 144460 }, { "epoch": 0.8587596816282373, "grad_norm": 4.662738800048828, "learning_rate": 9.843998208699586e-06, "loss": 0.57, "step": 144470 }, { "epoch": 0.8588191237049058, "grad_norm": 5.303786754608154, "learning_rate": 9.843946778596195e-06, "loss": 0.5645, "step": 144480 }, { "epoch": 0.8588785657815742, "grad_norm": 4.8341264724731445, "learning_rate": 9.843895340150951e-06, "loss": 0.5476, "step": 144490 }, { "epoch": 0.8589380078582425, "grad_norm": 5.351149559020996, "learning_rate": 9.84384389336394e-06, "loss": 0.5663, "step": 144500 }, { "epoch": 0.8589974499349109, "grad_norm": 5.491687774658203, "learning_rate": 9.843792438235252e-06, "loss": 0.5847, "step": 144510 }, { "epoch": 0.8590568920115793, "grad_norm": 5.306157112121582, "learning_rate": 9.843740974764977e-06, "loss": 0.5063, "step": 144520 }, { "epoch": 0.8591163340882477, "grad_norm": 5.212216854095459, "learning_rate": 9.8436895029532e-06, "loss": 0.5933, "step": 144530 }, { "epoch": 0.8591757761649161, "grad_norm": 5.893089294433594, "learning_rate": 9.843638022800013e-06, "loss": 0.562, "step": 144540 }, { "epoch": 0.8592352182415844, "grad_norm": 4.978602886199951, "learning_rate": 9.843586534305503e-06, "loss": 0.5909, "step": 144550 }, { "epoch": 0.8592946603182529, "grad_norm": 6.394346714019775, "learning_rate": 9.843535037469758e-06, "loss": 0.6268, "step": 144560 }, { "epoch": 0.8593541023949213, "grad_norm": 6.198157787322998, "learning_rate": 9.84348353229287e-06, "loss": 0.6282, "step": 144570 }, { "epoch": 0.8594135444715897, "grad_norm": 5.349098205566406, "learning_rate": 9.843432018774925e-06, "loss": 0.5268, "step": 144580 }, { "epoch": 0.8594729865482581, "grad_norm": 6.22477388381958, "learning_rate": 9.84338049691601e-06, "loss": 0.5401, "step": 144590 }, { "epoch": 0.8595324286249264, "grad_norm": 4.420384407043457, "learning_rate": 9.843328966716219e-06, "loss": 0.5944, "step": 144600 }, { "epoch": 0.8595918707015948, "grad_norm": 5.523121356964111, "learning_rate": 9.843277428175634e-06, "loss": 0.5288, "step": 144610 }, { "epoch": 0.8596513127782632, "grad_norm": 4.713231563568115, "learning_rate": 9.84322588129435e-06, "loss": 0.5589, "step": 144620 }, { "epoch": 0.8597107548549316, "grad_norm": 5.621306419372559, "learning_rate": 9.843174326072453e-06, "loss": 0.5322, "step": 144630 }, { "epoch": 0.8597701969316, "grad_norm": 7.639866828918457, "learning_rate": 9.84312276251003e-06, "loss": 0.614, "step": 144640 }, { "epoch": 0.8598296390082684, "grad_norm": 5.467151641845703, "learning_rate": 9.843071190607173e-06, "loss": 0.5088, "step": 144650 }, { "epoch": 0.8598890810849368, "grad_norm": 4.123764514923096, "learning_rate": 9.843019610363972e-06, "loss": 0.4978, "step": 144660 }, { "epoch": 0.8599485231616052, "grad_norm": 5.339616775512695, "learning_rate": 9.84296802178051e-06, "loss": 0.5747, "step": 144670 }, { "epoch": 0.8600079652382736, "grad_norm": 5.255781173706055, "learning_rate": 9.84291642485688e-06, "loss": 0.5517, "step": 144680 }, { "epoch": 0.8600674073149419, "grad_norm": 5.507282257080078, "learning_rate": 9.842864819593173e-06, "loss": 0.586, "step": 144690 }, { "epoch": 0.8601268493916103, "grad_norm": 3.6855547428131104, "learning_rate": 9.84281320598947e-06, "loss": 0.5751, "step": 144700 }, { "epoch": 0.8601862914682787, "grad_norm": 4.63223123550415, "learning_rate": 9.842761584045868e-06, "loss": 0.515, "step": 144710 }, { "epoch": 0.8602457335449472, "grad_norm": 6.255539894104004, "learning_rate": 9.842709953762452e-06, "loss": 0.5409, "step": 144720 }, { "epoch": 0.8603051756216156, "grad_norm": 4.017138957977295, "learning_rate": 9.842658315139311e-06, "loss": 0.5462, "step": 144730 }, { "epoch": 0.8603646176982839, "grad_norm": 4.748617172241211, "learning_rate": 9.842606668176536e-06, "loss": 0.573, "step": 144740 }, { "epoch": 0.8604240597749523, "grad_norm": 4.516412734985352, "learning_rate": 9.842555012874213e-06, "loss": 0.533, "step": 144750 }, { "epoch": 0.8604835018516207, "grad_norm": 5.964169502258301, "learning_rate": 9.842503349232432e-06, "loss": 0.593, "step": 144760 }, { "epoch": 0.8605429439282891, "grad_norm": 5.993570804595947, "learning_rate": 9.842451677251285e-06, "loss": 0.508, "step": 144770 }, { "epoch": 0.8606023860049574, "grad_norm": 4.385745525360107, "learning_rate": 9.842399996930857e-06, "loss": 0.5791, "step": 144780 }, { "epoch": 0.8606618280816258, "grad_norm": 5.445666790008545, "learning_rate": 9.842348308271238e-06, "loss": 0.5318, "step": 144790 }, { "epoch": 0.8607212701582942, "grad_norm": 6.701709747314453, "learning_rate": 9.842296611272517e-06, "loss": 0.5601, "step": 144800 }, { "epoch": 0.8607807122349627, "grad_norm": 4.8364129066467285, "learning_rate": 9.842244905934786e-06, "loss": 0.5632, "step": 144810 }, { "epoch": 0.8608401543116311, "grad_norm": 5.204108715057373, "learning_rate": 9.842193192258128e-06, "loss": 0.5628, "step": 144820 }, { "epoch": 0.8608995963882994, "grad_norm": 5.200026512145996, "learning_rate": 9.842141470242639e-06, "loss": 0.5485, "step": 144830 }, { "epoch": 0.8609590384649678, "grad_norm": 4.398519039154053, "learning_rate": 9.842089739888402e-06, "loss": 0.582, "step": 144840 }, { "epoch": 0.8610184805416362, "grad_norm": 4.705197811126709, "learning_rate": 9.84203800119551e-06, "loss": 0.5466, "step": 144850 }, { "epoch": 0.8610779226183046, "grad_norm": 8.174111366271973, "learning_rate": 9.84198625416405e-06, "loss": 0.5392, "step": 144860 }, { "epoch": 0.8611373646949729, "grad_norm": 6.280666828155518, "learning_rate": 9.841934498794112e-06, "loss": 0.5451, "step": 144870 }, { "epoch": 0.8611968067716413, "grad_norm": 5.825228214263916, "learning_rate": 9.841882735085785e-06, "loss": 0.577, "step": 144880 }, { "epoch": 0.8612562488483098, "grad_norm": 4.150783061981201, "learning_rate": 9.84183096303916e-06, "loss": 0.5327, "step": 144890 }, { "epoch": 0.8613156909249782, "grad_norm": 7.573642253875732, "learning_rate": 9.841779182654322e-06, "loss": 0.6062, "step": 144900 }, { "epoch": 0.8613751330016466, "grad_norm": 5.0460920333862305, "learning_rate": 9.841727393931364e-06, "loss": 0.5531, "step": 144910 }, { "epoch": 0.8614345750783149, "grad_norm": 6.256337642669678, "learning_rate": 9.841675596870373e-06, "loss": 0.5007, "step": 144920 }, { "epoch": 0.8614940171549833, "grad_norm": 7.216140270233154, "learning_rate": 9.84162379147144e-06, "loss": 0.5648, "step": 144930 }, { "epoch": 0.8615534592316517, "grad_norm": 5.820903778076172, "learning_rate": 9.841571977734652e-06, "loss": 0.5162, "step": 144940 }, { "epoch": 0.8616129013083201, "grad_norm": 5.182005405426025, "learning_rate": 9.8415201556601e-06, "loss": 0.5464, "step": 144950 }, { "epoch": 0.8616723433849885, "grad_norm": 5.7086687088012695, "learning_rate": 9.841468325247871e-06, "loss": 0.5759, "step": 144960 }, { "epoch": 0.8617317854616569, "grad_norm": 5.008962154388428, "learning_rate": 9.841416486498058e-06, "loss": 0.557, "step": 144970 }, { "epoch": 0.8617912275383253, "grad_norm": 5.479324817657471, "learning_rate": 9.841364639410747e-06, "loss": 0.508, "step": 144980 }, { "epoch": 0.8618506696149937, "grad_norm": 6.279472827911377, "learning_rate": 9.84131278398603e-06, "loss": 0.5825, "step": 144990 }, { "epoch": 0.8619101116916621, "grad_norm": 6.172258377075195, "learning_rate": 9.841260920223993e-06, "loss": 0.5833, "step": 145000 }, { "epoch": 0.8619695537683304, "grad_norm": 6.681211948394775, "learning_rate": 9.841209048124727e-06, "loss": 0.5611, "step": 145010 }, { "epoch": 0.8620289958449988, "grad_norm": 4.730298042297363, "learning_rate": 9.841157167688323e-06, "loss": 0.619, "step": 145020 }, { "epoch": 0.8620884379216672, "grad_norm": 4.807677745819092, "learning_rate": 9.841105278914866e-06, "loss": 0.5768, "step": 145030 }, { "epoch": 0.8621478799983356, "grad_norm": 3.8052144050598145, "learning_rate": 9.84105338180445e-06, "loss": 0.5503, "step": 145040 }, { "epoch": 0.8622073220750041, "grad_norm": 4.051599979400635, "learning_rate": 9.841001476357164e-06, "loss": 0.467, "step": 145050 }, { "epoch": 0.8622667641516724, "grad_norm": 5.035677433013916, "learning_rate": 9.840949562573092e-06, "loss": 0.5274, "step": 145060 }, { "epoch": 0.8623262062283408, "grad_norm": 5.985732078552246, "learning_rate": 9.84089764045233e-06, "loss": 0.5409, "step": 145070 }, { "epoch": 0.8623856483050092, "grad_norm": 5.204256534576416, "learning_rate": 9.840845709994963e-06, "loss": 0.4972, "step": 145080 }, { "epoch": 0.8624450903816776, "grad_norm": 4.404973030090332, "learning_rate": 9.840793771201084e-06, "loss": 0.5582, "step": 145090 }, { "epoch": 0.862504532458346, "grad_norm": 4.458644866943359, "learning_rate": 9.84074182407078e-06, "loss": 0.5553, "step": 145100 }, { "epoch": 0.8625639745350143, "grad_norm": 4.3176751136779785, "learning_rate": 9.840689868604141e-06, "loss": 0.515, "step": 145110 }, { "epoch": 0.8626234166116827, "grad_norm": 6.978654861450195, "learning_rate": 9.840637904801256e-06, "loss": 0.555, "step": 145120 }, { "epoch": 0.8626828586883512, "grad_norm": 6.822021007537842, "learning_rate": 9.840585932662214e-06, "loss": 0.5206, "step": 145130 }, { "epoch": 0.8627423007650196, "grad_norm": 4.273893356323242, "learning_rate": 9.840533952187107e-06, "loss": 0.5128, "step": 145140 }, { "epoch": 0.8628017428416879, "grad_norm": 5.539081573486328, "learning_rate": 9.840481963376022e-06, "loss": 0.5414, "step": 145150 }, { "epoch": 0.8628611849183563, "grad_norm": 4.994046211242676, "learning_rate": 9.84042996622905e-06, "loss": 0.5294, "step": 145160 }, { "epoch": 0.8629206269950247, "grad_norm": 6.030055046081543, "learning_rate": 9.840377960746279e-06, "loss": 0.6148, "step": 145170 }, { "epoch": 0.8629800690716931, "grad_norm": 5.27782678604126, "learning_rate": 9.840325946927801e-06, "loss": 0.5359, "step": 145180 }, { "epoch": 0.8630395111483615, "grad_norm": 4.628001689910889, "learning_rate": 9.840273924773705e-06, "loss": 0.5525, "step": 145190 }, { "epoch": 0.8630989532250298, "grad_norm": 5.719109058380127, "learning_rate": 9.840221894284077e-06, "loss": 0.5556, "step": 145200 }, { "epoch": 0.8631583953016982, "grad_norm": 4.123603343963623, "learning_rate": 9.840169855459012e-06, "loss": 0.5122, "step": 145210 }, { "epoch": 0.8632178373783667, "grad_norm": 5.445262432098389, "learning_rate": 9.840117808298595e-06, "loss": 0.5692, "step": 145220 }, { "epoch": 0.8632772794550351, "grad_norm": 7.570029258728027, "learning_rate": 9.840065752802919e-06, "loss": 0.4891, "step": 145230 }, { "epoch": 0.8633367215317034, "grad_norm": 6.215342044830322, "learning_rate": 9.840013688972072e-06, "loss": 0.5281, "step": 145240 }, { "epoch": 0.8633961636083718, "grad_norm": 4.683341026306152, "learning_rate": 9.839961616806144e-06, "loss": 0.5554, "step": 145250 }, { "epoch": 0.8634556056850402, "grad_norm": 6.043978214263916, "learning_rate": 9.839909536305223e-06, "loss": 0.5641, "step": 145260 }, { "epoch": 0.8635150477617086, "grad_norm": 5.3563313484191895, "learning_rate": 9.839857447469403e-06, "loss": 0.5772, "step": 145270 }, { "epoch": 0.863574489838377, "grad_norm": 4.44666051864624, "learning_rate": 9.839805350298768e-06, "loss": 0.5809, "step": 145280 }, { "epoch": 0.8636339319150453, "grad_norm": 4.90261697769165, "learning_rate": 9.839753244793413e-06, "loss": 0.5416, "step": 145290 }, { "epoch": 0.8636933739917138, "grad_norm": 3.7596147060394287, "learning_rate": 9.839701130953424e-06, "loss": 0.5745, "step": 145300 }, { "epoch": 0.8637528160683822, "grad_norm": 5.289587020874023, "learning_rate": 9.839649008778894e-06, "loss": 0.561, "step": 145310 }, { "epoch": 0.8638122581450506, "grad_norm": 4.934596061706543, "learning_rate": 9.839596878269908e-06, "loss": 0.5723, "step": 145320 }, { "epoch": 0.863871700221719, "grad_norm": 5.142461776733398, "learning_rate": 9.839544739426561e-06, "loss": 0.5517, "step": 145330 }, { "epoch": 0.8639311422983873, "grad_norm": 6.788911819458008, "learning_rate": 9.839492592248941e-06, "loss": 0.5793, "step": 145340 }, { "epoch": 0.8639905843750557, "grad_norm": 4.467984199523926, "learning_rate": 9.839440436737135e-06, "loss": 0.5326, "step": 145350 }, { "epoch": 0.8640500264517241, "grad_norm": 5.0595903396606445, "learning_rate": 9.839388272891237e-06, "loss": 0.5247, "step": 145360 }, { "epoch": 0.8641094685283925, "grad_norm": 6.165850639343262, "learning_rate": 9.839336100711334e-06, "loss": 0.6339, "step": 145370 }, { "epoch": 0.8641689106050608, "grad_norm": 5.278501987457275, "learning_rate": 9.839283920197518e-06, "loss": 0.5225, "step": 145380 }, { "epoch": 0.8642283526817293, "grad_norm": 4.939935207366943, "learning_rate": 9.839231731349877e-06, "loss": 0.5627, "step": 145390 }, { "epoch": 0.8642877947583977, "grad_norm": 4.03830623626709, "learning_rate": 9.839179534168502e-06, "loss": 0.5489, "step": 145400 }, { "epoch": 0.8643472368350661, "grad_norm": 4.7938432693481445, "learning_rate": 9.839127328653482e-06, "loss": 0.5245, "step": 145410 }, { "epoch": 0.8644066789117345, "grad_norm": 5.508123874664307, "learning_rate": 9.839075114804906e-06, "loss": 0.6451, "step": 145420 }, { "epoch": 0.8644661209884028, "grad_norm": 5.60803747177124, "learning_rate": 9.839022892622866e-06, "loss": 0.5334, "step": 145430 }, { "epoch": 0.8645255630650712, "grad_norm": 5.894223213195801, "learning_rate": 9.838970662107454e-06, "loss": 0.5225, "step": 145440 }, { "epoch": 0.8645850051417396, "grad_norm": 4.771638870239258, "learning_rate": 9.838918423258755e-06, "loss": 0.5237, "step": 145450 }, { "epoch": 0.864644447218408, "grad_norm": 4.78906774520874, "learning_rate": 9.83886617607686e-06, "loss": 0.5575, "step": 145460 }, { "epoch": 0.8647038892950765, "grad_norm": 5.1293768882751465, "learning_rate": 9.838813920561862e-06, "loss": 0.5282, "step": 145470 }, { "epoch": 0.8647633313717448, "grad_norm": 5.290762901306152, "learning_rate": 9.838761656713848e-06, "loss": 0.6407, "step": 145480 }, { "epoch": 0.8648227734484132, "grad_norm": 5.923292636871338, "learning_rate": 9.83870938453291e-06, "loss": 0.5826, "step": 145490 }, { "epoch": 0.8648822155250816, "grad_norm": 5.7417426109313965, "learning_rate": 9.838657104019136e-06, "loss": 0.5602, "step": 145500 }, { "epoch": 0.86494165760175, "grad_norm": 5.409689426422119, "learning_rate": 9.838604815172616e-06, "loss": 0.5224, "step": 145510 }, { "epoch": 0.8650010996784183, "grad_norm": 5.706667423248291, "learning_rate": 9.838552517993442e-06, "loss": 0.5841, "step": 145520 }, { "epoch": 0.8650605417550867, "grad_norm": 5.290996551513672, "learning_rate": 9.838500212481705e-06, "loss": 0.5469, "step": 145530 }, { "epoch": 0.8651199838317551, "grad_norm": 5.198927402496338, "learning_rate": 9.838447898637492e-06, "loss": 0.5554, "step": 145540 }, { "epoch": 0.8651794259084236, "grad_norm": 5.408169746398926, "learning_rate": 9.838395576460895e-06, "loss": 0.5491, "step": 145550 }, { "epoch": 0.865238867985092, "grad_norm": 5.319103717803955, "learning_rate": 9.838343245952003e-06, "loss": 0.5573, "step": 145560 }, { "epoch": 0.8652983100617603, "grad_norm": 6.669665813446045, "learning_rate": 9.838290907110907e-06, "loss": 0.5721, "step": 145570 }, { "epoch": 0.8653577521384287, "grad_norm": 6.648360252380371, "learning_rate": 9.838238559937697e-06, "loss": 0.5773, "step": 145580 }, { "epoch": 0.8654171942150971, "grad_norm": 5.325689792633057, "learning_rate": 9.838186204432462e-06, "loss": 0.537, "step": 145590 }, { "epoch": 0.8654766362917655, "grad_norm": 4.433980941772461, "learning_rate": 9.838133840595294e-06, "loss": 0.5698, "step": 145600 }, { "epoch": 0.8655360783684338, "grad_norm": 6.9355902671813965, "learning_rate": 9.838081468426282e-06, "loss": 0.5319, "step": 145610 }, { "epoch": 0.8655955204451022, "grad_norm": 6.395230770111084, "learning_rate": 9.838029087925515e-06, "loss": 0.6034, "step": 145620 }, { "epoch": 0.8656549625217707, "grad_norm": 4.934289455413818, "learning_rate": 9.837976699093085e-06, "loss": 0.5595, "step": 145630 }, { "epoch": 0.8657144045984391, "grad_norm": 5.075862407684326, "learning_rate": 9.837924301929084e-06, "loss": 0.5624, "step": 145640 }, { "epoch": 0.8657738466751075, "grad_norm": 4.704731464385986, "learning_rate": 9.837871896433598e-06, "loss": 0.5435, "step": 145650 }, { "epoch": 0.8658332887517758, "grad_norm": 4.722975730895996, "learning_rate": 9.837819482606721e-06, "loss": 0.632, "step": 145660 }, { "epoch": 0.8658927308284442, "grad_norm": 4.94602108001709, "learning_rate": 9.837767060448539e-06, "loss": 0.5861, "step": 145670 }, { "epoch": 0.8659521729051126, "grad_norm": 4.500233173370361, "learning_rate": 9.837714629959147e-06, "loss": 0.5081, "step": 145680 }, { "epoch": 0.866011614981781, "grad_norm": 4.8674635887146, "learning_rate": 9.837662191138634e-06, "loss": 0.4883, "step": 145690 }, { "epoch": 0.8660710570584494, "grad_norm": 5.703642845153809, "learning_rate": 9.837609743987088e-06, "loss": 0.5612, "step": 145700 }, { "epoch": 0.8661304991351177, "grad_norm": 6.034767150878906, "learning_rate": 9.837557288504602e-06, "loss": 0.5496, "step": 145710 }, { "epoch": 0.8661899412117862, "grad_norm": 5.333572864532471, "learning_rate": 9.837504824691264e-06, "loss": 0.6222, "step": 145720 }, { "epoch": 0.8662493832884546, "grad_norm": 4.2903547286987305, "learning_rate": 9.837452352547165e-06, "loss": 0.5618, "step": 145730 }, { "epoch": 0.866308825365123, "grad_norm": 4.488297939300537, "learning_rate": 9.837399872072397e-06, "loss": 0.5325, "step": 145740 }, { "epoch": 0.8663682674417913, "grad_norm": 5.784707069396973, "learning_rate": 9.837347383267049e-06, "loss": 0.4867, "step": 145750 }, { "epoch": 0.8664277095184597, "grad_norm": 4.806609153747559, "learning_rate": 9.83729488613121e-06, "loss": 0.5528, "step": 145760 }, { "epoch": 0.8664871515951281, "grad_norm": 5.5563788414001465, "learning_rate": 9.837242380664975e-06, "loss": 0.5523, "step": 145770 }, { "epoch": 0.8665465936717965, "grad_norm": 4.797661781311035, "learning_rate": 9.837189866868429e-06, "loss": 0.5734, "step": 145780 }, { "epoch": 0.866606035748465, "grad_norm": 7.2805938720703125, "learning_rate": 9.837137344741666e-06, "loss": 0.6017, "step": 145790 }, { "epoch": 0.8666654778251333, "grad_norm": 4.933959484100342, "learning_rate": 9.837084814284775e-06, "loss": 0.541, "step": 145800 }, { "epoch": 0.8667249199018017, "grad_norm": 5.388898849487305, "learning_rate": 9.837032275497846e-06, "loss": 0.5862, "step": 145810 }, { "epoch": 0.8667843619784701, "grad_norm": 6.290766716003418, "learning_rate": 9.836979728380974e-06, "loss": 0.5338, "step": 145820 }, { "epoch": 0.8668438040551385, "grad_norm": 4.965735912322998, "learning_rate": 9.83692717293424e-06, "loss": 0.5599, "step": 145830 }, { "epoch": 0.8669032461318069, "grad_norm": 4.856445789337158, "learning_rate": 9.836874609157745e-06, "loss": 0.5627, "step": 145840 }, { "epoch": 0.8669626882084752, "grad_norm": 5.130528926849365, "learning_rate": 9.836822037051571e-06, "loss": 0.5472, "step": 145850 }, { "epoch": 0.8670221302851436, "grad_norm": 7.0355682373046875, "learning_rate": 9.836769456615816e-06, "loss": 0.5664, "step": 145860 }, { "epoch": 0.867081572361812, "grad_norm": 5.5696234703063965, "learning_rate": 9.836716867850565e-06, "loss": 0.5259, "step": 145870 }, { "epoch": 0.8671410144384805, "grad_norm": 4.655803203582764, "learning_rate": 9.836664270755911e-06, "loss": 0.6331, "step": 145880 }, { "epoch": 0.8672004565151488, "grad_norm": 5.175261497497559, "learning_rate": 9.836611665331944e-06, "loss": 0.546, "step": 145890 }, { "epoch": 0.8672598985918172, "grad_norm": 6.993221282958984, "learning_rate": 9.836559051578753e-06, "loss": 0.5666, "step": 145900 }, { "epoch": 0.8673193406684856, "grad_norm": 7.057526111602783, "learning_rate": 9.836506429496433e-06, "loss": 0.5704, "step": 145910 }, { "epoch": 0.867378782745154, "grad_norm": 6.191926956176758, "learning_rate": 9.836453799085071e-06, "loss": 0.5442, "step": 145920 }, { "epoch": 0.8674382248218224, "grad_norm": 5.993137836456299, "learning_rate": 9.836401160344757e-06, "loss": 0.5872, "step": 145930 }, { "epoch": 0.8674976668984907, "grad_norm": 4.897031784057617, "learning_rate": 9.836348513275585e-06, "loss": 0.58, "step": 145940 }, { "epoch": 0.8675571089751591, "grad_norm": 5.2526984214782715, "learning_rate": 9.836295857877643e-06, "loss": 0.5198, "step": 145950 }, { "epoch": 0.8676165510518276, "grad_norm": 5.923435211181641, "learning_rate": 9.83624319415102e-06, "loss": 0.5513, "step": 145960 }, { "epoch": 0.867675993128496, "grad_norm": 5.735751152038574, "learning_rate": 9.836190522095811e-06, "loss": 0.5732, "step": 145970 }, { "epoch": 0.8677354352051643, "grad_norm": 5.300854206085205, "learning_rate": 9.836137841712108e-06, "loss": 0.5527, "step": 145980 }, { "epoch": 0.8677948772818327, "grad_norm": 5.947693347930908, "learning_rate": 9.836085152999994e-06, "loss": 0.5855, "step": 145990 }, { "epoch": 0.8678543193585011, "grad_norm": 5.1644392013549805, "learning_rate": 9.836032455959568e-06, "loss": 0.5848, "step": 146000 }, { "epoch": 0.8679137614351695, "grad_norm": 5.577908992767334, "learning_rate": 9.835979750590916e-06, "loss": 0.5453, "step": 146010 }, { "epoch": 0.8679732035118379, "grad_norm": 5.857237339019775, "learning_rate": 9.835927036894128e-06, "loss": 0.5528, "step": 146020 }, { "epoch": 0.8680326455885062, "grad_norm": 5.151085376739502, "learning_rate": 9.835874314869298e-06, "loss": 0.5544, "step": 146030 }, { "epoch": 0.8680920876651746, "grad_norm": 4.7374587059021, "learning_rate": 9.835821584516514e-06, "loss": 0.6058, "step": 146040 }, { "epoch": 0.8681515297418431, "grad_norm": 5.0989990234375, "learning_rate": 9.835768845835872e-06, "loss": 0.5731, "step": 146050 }, { "epoch": 0.8682109718185115, "grad_norm": 4.585633277893066, "learning_rate": 9.835716098827454e-06, "loss": 0.5512, "step": 146060 }, { "epoch": 0.8682704138951799, "grad_norm": 5.101203441619873, "learning_rate": 9.835663343491359e-06, "loss": 0.5553, "step": 146070 }, { "epoch": 0.8683298559718482, "grad_norm": 5.898246765136719, "learning_rate": 9.835610579827675e-06, "loss": 0.5168, "step": 146080 }, { "epoch": 0.8683892980485166, "grad_norm": 5.993166446685791, "learning_rate": 9.835557807836491e-06, "loss": 0.551, "step": 146090 }, { "epoch": 0.868448740125185, "grad_norm": 4.645866394042969, "learning_rate": 9.835505027517901e-06, "loss": 0.5563, "step": 146100 }, { "epoch": 0.8685081822018534, "grad_norm": 6.288686275482178, "learning_rate": 9.835452238871995e-06, "loss": 0.5622, "step": 146110 }, { "epoch": 0.8685676242785217, "grad_norm": 5.498887062072754, "learning_rate": 9.83539944189886e-06, "loss": 0.5017, "step": 146120 }, { "epoch": 0.8686270663551902, "grad_norm": 4.227637767791748, "learning_rate": 9.835346636598592e-06, "loss": 0.5099, "step": 146130 }, { "epoch": 0.8686865084318586, "grad_norm": 4.613760471343994, "learning_rate": 9.835293822971282e-06, "loss": 0.5852, "step": 146140 }, { "epoch": 0.868745950508527, "grad_norm": 5.046850681304932, "learning_rate": 9.835241001017018e-06, "loss": 0.5542, "step": 146150 }, { "epoch": 0.8688053925851954, "grad_norm": 5.230708122253418, "learning_rate": 9.83518817073589e-06, "loss": 0.5876, "step": 146160 }, { "epoch": 0.8688648346618637, "grad_norm": 5.304328918457031, "learning_rate": 9.835135332127993e-06, "loss": 0.6086, "step": 146170 }, { "epoch": 0.8689242767385321, "grad_norm": 5.356247901916504, "learning_rate": 9.835082485193414e-06, "loss": 0.5872, "step": 146180 }, { "epoch": 0.8689837188152005, "grad_norm": 5.540698051452637, "learning_rate": 9.83502962993225e-06, "loss": 0.5165, "step": 146190 }, { "epoch": 0.869043160891869, "grad_norm": 7.416429042816162, "learning_rate": 9.834976766344585e-06, "loss": 0.5537, "step": 146200 }, { "epoch": 0.8691026029685374, "grad_norm": 4.636764049530029, "learning_rate": 9.834923894430513e-06, "loss": 0.5608, "step": 146210 }, { "epoch": 0.8691620450452057, "grad_norm": 7.078000068664551, "learning_rate": 9.834871014190126e-06, "loss": 0.5817, "step": 146220 }, { "epoch": 0.8692214871218741, "grad_norm": 5.417577266693115, "learning_rate": 9.834818125623514e-06, "loss": 0.5394, "step": 146230 }, { "epoch": 0.8692809291985425, "grad_norm": 4.61501932144165, "learning_rate": 9.83476522873077e-06, "loss": 0.508, "step": 146240 }, { "epoch": 0.8693403712752109, "grad_norm": 6.886743068695068, "learning_rate": 9.834712323511981e-06, "loss": 0.5652, "step": 146250 }, { "epoch": 0.8693998133518792, "grad_norm": 5.025422096252441, "learning_rate": 9.834659409967242e-06, "loss": 0.5898, "step": 146260 }, { "epoch": 0.8694592554285476, "grad_norm": 4.560698509216309, "learning_rate": 9.834606488096641e-06, "loss": 0.5519, "step": 146270 }, { "epoch": 0.869518697505216, "grad_norm": 3.84140944480896, "learning_rate": 9.834553557900272e-06, "loss": 0.6187, "step": 146280 }, { "epoch": 0.8695781395818845, "grad_norm": 4.332596778869629, "learning_rate": 9.834500619378225e-06, "loss": 0.5045, "step": 146290 }, { "epoch": 0.8696375816585529, "grad_norm": 5.265625953674316, "learning_rate": 9.834447672530591e-06, "loss": 0.5513, "step": 146300 }, { "epoch": 0.8696970237352212, "grad_norm": 5.025752544403076, "learning_rate": 9.83439471735746e-06, "loss": 0.526, "step": 146310 }, { "epoch": 0.8697564658118896, "grad_norm": 5.411162376403809, "learning_rate": 9.834341753858925e-06, "loss": 0.5634, "step": 146320 }, { "epoch": 0.869815907888558, "grad_norm": 6.952544689178467, "learning_rate": 9.834288782035078e-06, "loss": 0.594, "step": 146330 }, { "epoch": 0.8698753499652264, "grad_norm": 4.480604648590088, "learning_rate": 9.834235801886009e-06, "loss": 0.6083, "step": 146340 }, { "epoch": 0.8699347920418947, "grad_norm": 6.112517833709717, "learning_rate": 9.834182813411808e-06, "loss": 0.5118, "step": 146350 }, { "epoch": 0.8699942341185631, "grad_norm": 6.185659885406494, "learning_rate": 9.834129816612568e-06, "loss": 0.5469, "step": 146360 }, { "epoch": 0.8700536761952316, "grad_norm": 4.685466289520264, "learning_rate": 9.834076811488379e-06, "loss": 0.5221, "step": 146370 }, { "epoch": 0.8701131182719, "grad_norm": 4.716620445251465, "learning_rate": 9.834023798039332e-06, "loss": 0.5661, "step": 146380 }, { "epoch": 0.8701725603485684, "grad_norm": 4.483123302459717, "learning_rate": 9.833970776265522e-06, "loss": 0.5588, "step": 146390 }, { "epoch": 0.8702320024252367, "grad_norm": 6.093503475189209, "learning_rate": 9.833917746167035e-06, "loss": 0.5256, "step": 146400 }, { "epoch": 0.8702914445019051, "grad_norm": 4.056224822998047, "learning_rate": 9.833864707743967e-06, "loss": 0.535, "step": 146410 }, { "epoch": 0.8703508865785735, "grad_norm": 4.155842304229736, "learning_rate": 9.833811660996406e-06, "loss": 0.559, "step": 146420 }, { "epoch": 0.8704103286552419, "grad_norm": 4.572882175445557, "learning_rate": 9.833758605924444e-06, "loss": 0.538, "step": 146430 }, { "epoch": 0.8704697707319103, "grad_norm": 5.3091325759887695, "learning_rate": 9.833705542528173e-06, "loss": 0.5603, "step": 146440 }, { "epoch": 0.8705292128085786, "grad_norm": 5.536938190460205, "learning_rate": 9.833652470807686e-06, "loss": 0.5479, "step": 146450 }, { "epoch": 0.8705886548852471, "grad_norm": 4.546315670013428, "learning_rate": 9.83359939076307e-06, "loss": 0.4944, "step": 146460 }, { "epoch": 0.8706480969619155, "grad_norm": 4.428872108459473, "learning_rate": 9.83354630239442e-06, "loss": 0.5431, "step": 146470 }, { "epoch": 0.8707075390385839, "grad_norm": 5.837034702301025, "learning_rate": 9.83349320570183e-06, "loss": 0.5123, "step": 146480 }, { "epoch": 0.8707669811152522, "grad_norm": 5.704622745513916, "learning_rate": 9.833440100685384e-06, "loss": 0.5178, "step": 146490 }, { "epoch": 0.8708264231919206, "grad_norm": 5.135775566101074, "learning_rate": 9.83338698734518e-06, "loss": 0.5414, "step": 146500 }, { "epoch": 0.870885865268589, "grad_norm": 6.005744457244873, "learning_rate": 9.833333865681304e-06, "loss": 0.6441, "step": 146510 }, { "epoch": 0.8709453073452574, "grad_norm": 4.456592559814453, "learning_rate": 9.833280735693853e-06, "loss": 0.5253, "step": 146520 }, { "epoch": 0.8710047494219259, "grad_norm": 4.511957168579102, "learning_rate": 9.833227597382915e-06, "loss": 0.5251, "step": 146530 }, { "epoch": 0.8710641914985942, "grad_norm": 5.268991947174072, "learning_rate": 9.833174450748581e-06, "loss": 0.5617, "step": 146540 }, { "epoch": 0.8711236335752626, "grad_norm": 3.9938225746154785, "learning_rate": 9.833121295790946e-06, "loss": 0.5173, "step": 146550 }, { "epoch": 0.871183075651931, "grad_norm": 6.8362956047058105, "learning_rate": 9.833068132510097e-06, "loss": 0.5703, "step": 146560 }, { "epoch": 0.8712425177285994, "grad_norm": 4.60405969619751, "learning_rate": 9.833014960906131e-06, "loss": 0.5261, "step": 146570 }, { "epoch": 0.8713019598052678, "grad_norm": 5.834680557250977, "learning_rate": 9.832961780979135e-06, "loss": 0.5591, "step": 146580 }, { "epoch": 0.8713614018819361, "grad_norm": 7.0191450119018555, "learning_rate": 9.832908592729202e-06, "loss": 0.5428, "step": 146590 }, { "epoch": 0.8714208439586045, "grad_norm": 6.25032901763916, "learning_rate": 9.832855396156424e-06, "loss": 0.5389, "step": 146600 }, { "epoch": 0.8714802860352729, "grad_norm": 6.3989434242248535, "learning_rate": 9.832802191260892e-06, "loss": 0.5872, "step": 146610 }, { "epoch": 0.8715397281119414, "grad_norm": 5.1227898597717285, "learning_rate": 9.8327489780427e-06, "loss": 0.573, "step": 146620 }, { "epoch": 0.8715991701886097, "grad_norm": 5.667021751403809, "learning_rate": 9.832695756501935e-06, "loss": 0.5994, "step": 146630 }, { "epoch": 0.8716586122652781, "grad_norm": 5.770585536956787, "learning_rate": 9.83264252663869e-06, "loss": 0.5811, "step": 146640 }, { "epoch": 0.8717180543419465, "grad_norm": 4.8259663581848145, "learning_rate": 9.832589288453063e-06, "loss": 0.5219, "step": 146650 }, { "epoch": 0.8717774964186149, "grad_norm": 4.126195907592773, "learning_rate": 9.832536041945137e-06, "loss": 0.5025, "step": 146660 }, { "epoch": 0.8718369384952833, "grad_norm": 5.005263328552246, "learning_rate": 9.832482787115009e-06, "loss": 0.5494, "step": 146670 }, { "epoch": 0.8718963805719516, "grad_norm": 4.563182353973389, "learning_rate": 9.832429523962767e-06, "loss": 0.5718, "step": 146680 }, { "epoch": 0.87195582264862, "grad_norm": 5.289781093597412, "learning_rate": 9.832376252488508e-06, "loss": 0.5657, "step": 146690 }, { "epoch": 0.8720152647252885, "grad_norm": 6.066571235656738, "learning_rate": 9.832322972692317e-06, "loss": 0.5342, "step": 146700 }, { "epoch": 0.8720747068019569, "grad_norm": 4.8721160888671875, "learning_rate": 9.832269684574292e-06, "loss": 0.5615, "step": 146710 }, { "epoch": 0.8721341488786252, "grad_norm": 4.756249904632568, "learning_rate": 9.83221638813452e-06, "loss": 0.5741, "step": 146720 }, { "epoch": 0.8721935909552936, "grad_norm": 5.638157367706299, "learning_rate": 9.832163083373095e-06, "loss": 0.56, "step": 146730 }, { "epoch": 0.872253033031962, "grad_norm": 7.405819416046143, "learning_rate": 9.832109770290109e-06, "loss": 0.6125, "step": 146740 }, { "epoch": 0.8723124751086304, "grad_norm": 5.929219722747803, "learning_rate": 9.832056448885654e-06, "loss": 0.596, "step": 146750 }, { "epoch": 0.8723719171852988, "grad_norm": 4.6606125831604, "learning_rate": 9.83200311915982e-06, "loss": 0.5808, "step": 146760 }, { "epoch": 0.8724313592619671, "grad_norm": 5.497472763061523, "learning_rate": 9.831949781112702e-06, "loss": 0.5294, "step": 146770 }, { "epoch": 0.8724908013386355, "grad_norm": 5.8569746017456055, "learning_rate": 9.831896434744387e-06, "loss": 0.5164, "step": 146780 }, { "epoch": 0.872550243415304, "grad_norm": 4.9957475662231445, "learning_rate": 9.831843080054972e-06, "loss": 0.5248, "step": 146790 }, { "epoch": 0.8726096854919724, "grad_norm": 5.314120769500732, "learning_rate": 9.831789717044548e-06, "loss": 0.5196, "step": 146800 }, { "epoch": 0.8726691275686408, "grad_norm": 6.086597442626953, "learning_rate": 9.831736345713204e-06, "loss": 0.5226, "step": 146810 }, { "epoch": 0.8727285696453091, "grad_norm": 4.586098670959473, "learning_rate": 9.831682966061034e-06, "loss": 0.57, "step": 146820 }, { "epoch": 0.8727880117219775, "grad_norm": 6.395828723907471, "learning_rate": 9.831629578088128e-06, "loss": 0.5993, "step": 146830 }, { "epoch": 0.8728474537986459, "grad_norm": 4.65627384185791, "learning_rate": 9.83157618179458e-06, "loss": 0.5881, "step": 146840 }, { "epoch": 0.8729068958753143, "grad_norm": 4.458983898162842, "learning_rate": 9.831522777180482e-06, "loss": 0.5598, "step": 146850 }, { "epoch": 0.8729663379519826, "grad_norm": 5.918619632720947, "learning_rate": 9.831469364245925e-06, "loss": 0.5148, "step": 146860 }, { "epoch": 0.873025780028651, "grad_norm": 7.003139019012451, "learning_rate": 9.831415942991e-06, "loss": 0.5925, "step": 146870 }, { "epoch": 0.8730852221053195, "grad_norm": 4.628484725952148, "learning_rate": 9.831362513415802e-06, "loss": 0.5669, "step": 146880 }, { "epoch": 0.8731446641819879, "grad_norm": 5.419529438018799, "learning_rate": 9.83130907552042e-06, "loss": 0.5861, "step": 146890 }, { "epoch": 0.8732041062586563, "grad_norm": 5.965444087982178, "learning_rate": 9.831255629304948e-06, "loss": 0.6144, "step": 146900 }, { "epoch": 0.8732635483353246, "grad_norm": 4.993257999420166, "learning_rate": 9.831202174769479e-06, "loss": 0.5201, "step": 146910 }, { "epoch": 0.873322990411993, "grad_norm": 5.077903747558594, "learning_rate": 9.8311487119141e-06, "loss": 0.5867, "step": 146920 }, { "epoch": 0.8733824324886614, "grad_norm": 3.9229319095611572, "learning_rate": 9.83109524073891e-06, "loss": 0.5628, "step": 146930 }, { "epoch": 0.8734418745653298, "grad_norm": 4.3751220703125, "learning_rate": 9.831041761243995e-06, "loss": 0.525, "step": 146940 }, { "epoch": 0.8735013166419983, "grad_norm": 5.850712776184082, "learning_rate": 9.83098827342945e-06, "loss": 0.597, "step": 146950 }, { "epoch": 0.8735607587186666, "grad_norm": 4.210411548614502, "learning_rate": 9.830934777295368e-06, "loss": 0.5737, "step": 146960 }, { "epoch": 0.873620200795335, "grad_norm": 4.826153755187988, "learning_rate": 9.830881272841839e-06, "loss": 0.5336, "step": 146970 }, { "epoch": 0.8736796428720034, "grad_norm": 4.420137882232666, "learning_rate": 9.830827760068957e-06, "loss": 0.5915, "step": 146980 }, { "epoch": 0.8737390849486718, "grad_norm": 4.236599922180176, "learning_rate": 9.830774238976812e-06, "loss": 0.5575, "step": 146990 }, { "epoch": 0.8737985270253401, "grad_norm": 5.216229438781738, "learning_rate": 9.830720709565497e-06, "loss": 0.5349, "step": 147000 }, { "epoch": 0.8738579691020085, "grad_norm": 7.952681541442871, "learning_rate": 9.830667171835104e-06, "loss": 0.5991, "step": 147010 }, { "epoch": 0.8739174111786769, "grad_norm": 5.649197101593018, "learning_rate": 9.830613625785728e-06, "loss": 0.5148, "step": 147020 }, { "epoch": 0.8739768532553454, "grad_norm": 5.214046478271484, "learning_rate": 9.830560071417459e-06, "loss": 0.5912, "step": 147030 }, { "epoch": 0.8740362953320138, "grad_norm": 3.5768320560455322, "learning_rate": 9.830506508730387e-06, "loss": 0.5204, "step": 147040 }, { "epoch": 0.8740957374086821, "grad_norm": 5.504701137542725, "learning_rate": 9.830452937724608e-06, "loss": 0.5099, "step": 147050 }, { "epoch": 0.8741551794853505, "grad_norm": 5.610150337219238, "learning_rate": 9.830399358400212e-06, "loss": 0.5516, "step": 147060 }, { "epoch": 0.8742146215620189, "grad_norm": 5.5856099128723145, "learning_rate": 9.830345770757293e-06, "loss": 0.5456, "step": 147070 }, { "epoch": 0.8742740636386873, "grad_norm": 6.756175994873047, "learning_rate": 9.830292174795941e-06, "loss": 0.5982, "step": 147080 }, { "epoch": 0.8743335057153556, "grad_norm": 5.180019855499268, "learning_rate": 9.83023857051625e-06, "loss": 0.5498, "step": 147090 }, { "epoch": 0.874392947792024, "grad_norm": 7.313236713409424, "learning_rate": 9.830184957918312e-06, "loss": 0.5822, "step": 147100 }, { "epoch": 0.8744523898686924, "grad_norm": 5.372086048126221, "learning_rate": 9.830131337002218e-06, "loss": 0.5729, "step": 147110 }, { "epoch": 0.8745118319453609, "grad_norm": 5.343249797821045, "learning_rate": 9.830077707768062e-06, "loss": 0.5406, "step": 147120 }, { "epoch": 0.8745712740220293, "grad_norm": 5.225307941436768, "learning_rate": 9.830024070215938e-06, "loss": 0.526, "step": 147130 }, { "epoch": 0.8746307160986976, "grad_norm": 5.982619762420654, "learning_rate": 9.829970424345934e-06, "loss": 0.6129, "step": 147140 }, { "epoch": 0.874690158175366, "grad_norm": 5.523396968841553, "learning_rate": 9.829916770158145e-06, "loss": 0.6133, "step": 147150 }, { "epoch": 0.8747496002520344, "grad_norm": 5.178576946258545, "learning_rate": 9.829863107652664e-06, "loss": 0.5601, "step": 147160 }, { "epoch": 0.8748090423287028, "grad_norm": 5.277705669403076, "learning_rate": 9.82980943682958e-06, "loss": 0.5572, "step": 147170 }, { "epoch": 0.8748684844053712, "grad_norm": 4.875988006591797, "learning_rate": 9.82975575768899e-06, "loss": 0.5667, "step": 147180 }, { "epoch": 0.8749279264820395, "grad_norm": 5.248012542724609, "learning_rate": 9.829702070230984e-06, "loss": 0.5863, "step": 147190 }, { "epoch": 0.874987368558708, "grad_norm": 4.9711127281188965, "learning_rate": 9.829648374455654e-06, "loss": 0.5702, "step": 147200 }, { "epoch": 0.8750468106353764, "grad_norm": 4.342791557312012, "learning_rate": 9.829594670363094e-06, "loss": 0.5345, "step": 147210 }, { "epoch": 0.8751062527120448, "grad_norm": 4.671769618988037, "learning_rate": 9.829540957953396e-06, "loss": 0.5433, "step": 147220 }, { "epoch": 0.8751656947887131, "grad_norm": 6.3513946533203125, "learning_rate": 9.829487237226653e-06, "loss": 0.5544, "step": 147230 }, { "epoch": 0.8752251368653815, "grad_norm": 4.6966681480407715, "learning_rate": 9.829433508182954e-06, "loss": 0.5739, "step": 147240 }, { "epoch": 0.8752845789420499, "grad_norm": 6.394379138946533, "learning_rate": 9.829379770822397e-06, "loss": 0.5965, "step": 147250 }, { "epoch": 0.8753440210187183, "grad_norm": 4.210884094238281, "learning_rate": 9.82932602514507e-06, "loss": 0.5444, "step": 147260 }, { "epoch": 0.8754034630953867, "grad_norm": 5.819697856903076, "learning_rate": 9.829272271151068e-06, "loss": 0.5971, "step": 147270 }, { "epoch": 0.875462905172055, "grad_norm": 5.1042680740356445, "learning_rate": 9.829218508840484e-06, "loss": 0.5142, "step": 147280 }, { "epoch": 0.8755223472487235, "grad_norm": 5.025984287261963, "learning_rate": 9.829164738213409e-06, "loss": 0.5152, "step": 147290 }, { "epoch": 0.8755817893253919, "grad_norm": 5.866403102874756, "learning_rate": 9.829110959269933e-06, "loss": 0.5322, "step": 147300 }, { "epoch": 0.8756412314020603, "grad_norm": 4.725893020629883, "learning_rate": 9.829057172010155e-06, "loss": 0.535, "step": 147310 }, { "epoch": 0.8757006734787287, "grad_norm": 5.483148574829102, "learning_rate": 9.829003376434164e-06, "loss": 0.5529, "step": 147320 }, { "epoch": 0.875760115555397, "grad_norm": 5.42016077041626, "learning_rate": 9.828949572542052e-06, "loss": 0.5203, "step": 147330 }, { "epoch": 0.8758195576320654, "grad_norm": 4.260247707366943, "learning_rate": 9.828895760333914e-06, "loss": 0.5334, "step": 147340 }, { "epoch": 0.8758789997087338, "grad_norm": 5.220900058746338, "learning_rate": 9.828841939809842e-06, "loss": 0.5997, "step": 147350 }, { "epoch": 0.8759384417854023, "grad_norm": 5.846731662750244, "learning_rate": 9.828788110969924e-06, "loss": 0.5618, "step": 147360 }, { "epoch": 0.8759978838620706, "grad_norm": 5.4082159996032715, "learning_rate": 9.82873427381426e-06, "loss": 0.5555, "step": 147370 }, { "epoch": 0.876057325938739, "grad_norm": 5.6547136306762695, "learning_rate": 9.828680428342938e-06, "loss": 0.5832, "step": 147380 }, { "epoch": 0.8761167680154074, "grad_norm": 4.785144329071045, "learning_rate": 9.828626574556054e-06, "loss": 0.571, "step": 147390 }, { "epoch": 0.8761762100920758, "grad_norm": 6.788151264190674, "learning_rate": 9.828572712453697e-06, "loss": 0.5151, "step": 147400 }, { "epoch": 0.8762356521687442, "grad_norm": 4.458653926849365, "learning_rate": 9.828518842035963e-06, "loss": 0.5324, "step": 147410 }, { "epoch": 0.8762950942454125, "grad_norm": 6.409814834594727, "learning_rate": 9.828464963302943e-06, "loss": 0.6132, "step": 147420 }, { "epoch": 0.8763545363220809, "grad_norm": 4.925586700439453, "learning_rate": 9.82841107625473e-06, "loss": 0.5323, "step": 147430 }, { "epoch": 0.8764139783987493, "grad_norm": 5.393535614013672, "learning_rate": 9.828357180891417e-06, "loss": 0.5825, "step": 147440 }, { "epoch": 0.8764734204754178, "grad_norm": 5.037115573883057, "learning_rate": 9.828303277213098e-06, "loss": 0.5793, "step": 147450 }, { "epoch": 0.8765328625520861, "grad_norm": 5.630278587341309, "learning_rate": 9.828249365219862e-06, "loss": 0.5345, "step": 147460 }, { "epoch": 0.8765923046287545, "grad_norm": 4.423090934753418, "learning_rate": 9.828195444911807e-06, "loss": 0.5695, "step": 147470 }, { "epoch": 0.8766517467054229, "grad_norm": 6.152012348175049, "learning_rate": 9.828141516289023e-06, "loss": 0.5833, "step": 147480 }, { "epoch": 0.8767111887820913, "grad_norm": 5.498879432678223, "learning_rate": 9.828087579351602e-06, "loss": 0.5448, "step": 147490 }, { "epoch": 0.8767706308587597, "grad_norm": 4.924192428588867, "learning_rate": 9.828033634099639e-06, "loss": 0.5726, "step": 147500 }, { "epoch": 0.876830072935428, "grad_norm": 4.7798285484313965, "learning_rate": 9.827979680533225e-06, "loss": 0.5043, "step": 147510 }, { "epoch": 0.8768895150120964, "grad_norm": 5.885209560394287, "learning_rate": 9.827925718652454e-06, "loss": 0.5843, "step": 147520 }, { "epoch": 0.8769489570887649, "grad_norm": 5.682708263397217, "learning_rate": 9.82787174845742e-06, "loss": 0.5499, "step": 147530 }, { "epoch": 0.8770083991654333, "grad_norm": 5.234753608703613, "learning_rate": 9.827817769948215e-06, "loss": 0.5596, "step": 147540 }, { "epoch": 0.8770678412421017, "grad_norm": 5.32633638381958, "learning_rate": 9.827763783124931e-06, "loss": 0.5144, "step": 147550 }, { "epoch": 0.87712728331877, "grad_norm": 6.5906267166137695, "learning_rate": 9.827709787987662e-06, "loss": 0.558, "step": 147560 }, { "epoch": 0.8771867253954384, "grad_norm": 5.30059814453125, "learning_rate": 9.827655784536501e-06, "loss": 0.5467, "step": 147570 }, { "epoch": 0.8772461674721068, "grad_norm": 5.158295631408691, "learning_rate": 9.82760177277154e-06, "loss": 0.5311, "step": 147580 }, { "epoch": 0.8773056095487752, "grad_norm": 5.638327598571777, "learning_rate": 9.827547752692871e-06, "loss": 0.5204, "step": 147590 }, { "epoch": 0.8773650516254435, "grad_norm": 4.150705337524414, "learning_rate": 9.827493724300592e-06, "loss": 0.5291, "step": 147600 }, { "epoch": 0.877424493702112, "grad_norm": 5.218410968780518, "learning_rate": 9.82743968759479e-06, "loss": 0.5559, "step": 147610 }, { "epoch": 0.8774839357787804, "grad_norm": 6.949764728546143, "learning_rate": 9.827385642575564e-06, "loss": 0.536, "step": 147620 }, { "epoch": 0.8775433778554488, "grad_norm": 4.4424896240234375, "learning_rate": 9.827331589243003e-06, "loss": 0.5838, "step": 147630 }, { "epoch": 0.8776028199321172, "grad_norm": 5.109268665313721, "learning_rate": 9.827277527597199e-06, "loss": 0.5522, "step": 147640 }, { "epoch": 0.8776622620087855, "grad_norm": 6.382142066955566, "learning_rate": 9.827223457638248e-06, "loss": 0.572, "step": 147650 }, { "epoch": 0.8777217040854539, "grad_norm": 7.837779521942139, "learning_rate": 9.827169379366243e-06, "loss": 0.5258, "step": 147660 }, { "epoch": 0.8777811461621223, "grad_norm": 4.386338233947754, "learning_rate": 9.827115292781277e-06, "loss": 0.5782, "step": 147670 }, { "epoch": 0.8778405882387907, "grad_norm": 5.355757236480713, "learning_rate": 9.82706119788344e-06, "loss": 0.5572, "step": 147680 }, { "epoch": 0.877900030315459, "grad_norm": 5.700122833251953, "learning_rate": 9.82700709467283e-06, "loss": 0.5515, "step": 147690 }, { "epoch": 0.8779594723921275, "grad_norm": 4.5719804763793945, "learning_rate": 9.826952983149537e-06, "loss": 0.5147, "step": 147700 }, { "epoch": 0.8780189144687959, "grad_norm": 4.832572937011719, "learning_rate": 9.826898863313656e-06, "loss": 0.5388, "step": 147710 }, { "epoch": 0.8780783565454643, "grad_norm": 5.444093704223633, "learning_rate": 9.826844735165278e-06, "loss": 0.6034, "step": 147720 }, { "epoch": 0.8781377986221327, "grad_norm": 5.96447229385376, "learning_rate": 9.826790598704498e-06, "loss": 0.5546, "step": 147730 }, { "epoch": 0.878197240698801, "grad_norm": 4.959447383880615, "learning_rate": 9.826736453931408e-06, "loss": 0.5822, "step": 147740 }, { "epoch": 0.8782566827754694, "grad_norm": 4.136561393737793, "learning_rate": 9.826682300846102e-06, "loss": 0.5251, "step": 147750 }, { "epoch": 0.8783161248521378, "grad_norm": 4.68977165222168, "learning_rate": 9.826628139448672e-06, "loss": 0.538, "step": 147760 }, { "epoch": 0.8783755669288063, "grad_norm": 5.1647772789001465, "learning_rate": 9.826573969739215e-06, "loss": 0.5509, "step": 147770 }, { "epoch": 0.8784350090054747, "grad_norm": 4.86673641204834, "learning_rate": 9.826519791717822e-06, "loss": 0.5512, "step": 147780 }, { "epoch": 0.878494451082143, "grad_norm": 4.630079746246338, "learning_rate": 9.826465605384584e-06, "loss": 0.5352, "step": 147790 }, { "epoch": 0.8785538931588114, "grad_norm": 5.948570728302002, "learning_rate": 9.826411410739596e-06, "loss": 0.5118, "step": 147800 }, { "epoch": 0.8786133352354798, "grad_norm": 5.910449504852295, "learning_rate": 9.826357207782952e-06, "loss": 0.5684, "step": 147810 }, { "epoch": 0.8786727773121482, "grad_norm": 5.122046947479248, "learning_rate": 9.826302996514747e-06, "loss": 0.6317, "step": 147820 }, { "epoch": 0.8787322193888165, "grad_norm": 5.700651168823242, "learning_rate": 9.826248776935071e-06, "loss": 0.546, "step": 147830 }, { "epoch": 0.8787916614654849, "grad_norm": 5.78652286529541, "learning_rate": 9.82619454904402e-06, "loss": 0.6154, "step": 147840 }, { "epoch": 0.8788511035421533, "grad_norm": 4.629688739776611, "learning_rate": 9.826140312841683e-06, "loss": 0.551, "step": 147850 }, { "epoch": 0.8789105456188218, "grad_norm": 5.695550441741943, "learning_rate": 9.82608606832816e-06, "loss": 0.5332, "step": 147860 }, { "epoch": 0.8789699876954902, "grad_norm": 5.577589988708496, "learning_rate": 9.826031815503539e-06, "loss": 0.5274, "step": 147870 }, { "epoch": 0.8790294297721585, "grad_norm": 3.879610300064087, "learning_rate": 9.825977554367917e-06, "loss": 0.4957, "step": 147880 }, { "epoch": 0.8790888718488269, "grad_norm": 4.823766231536865, "learning_rate": 9.825923284921383e-06, "loss": 0.6069, "step": 147890 }, { "epoch": 0.8791483139254953, "grad_norm": 5.2354817390441895, "learning_rate": 9.825869007164036e-06, "loss": 0.5248, "step": 147900 }, { "epoch": 0.8792077560021637, "grad_norm": 4.502877235412598, "learning_rate": 9.825814721095965e-06, "loss": 0.5056, "step": 147910 }, { "epoch": 0.8792671980788321, "grad_norm": 5.577055931091309, "learning_rate": 9.825760426717266e-06, "loss": 0.5514, "step": 147920 }, { "epoch": 0.8793266401555004, "grad_norm": 4.511715888977051, "learning_rate": 9.825706124028032e-06, "loss": 0.5243, "step": 147930 }, { "epoch": 0.8793860822321689, "grad_norm": 6.509666442871094, "learning_rate": 9.825651813028355e-06, "loss": 0.5641, "step": 147940 }, { "epoch": 0.8794455243088373, "grad_norm": 6.217338562011719, "learning_rate": 9.82559749371833e-06, "loss": 0.5615, "step": 147950 }, { "epoch": 0.8795049663855057, "grad_norm": 3.903594970703125, "learning_rate": 9.825543166098052e-06, "loss": 0.5523, "step": 147960 }, { "epoch": 0.879564408462174, "grad_norm": 5.116336345672607, "learning_rate": 9.825488830167611e-06, "loss": 0.5344, "step": 147970 }, { "epoch": 0.8796238505388424, "grad_norm": 7.075730323791504, "learning_rate": 9.825434485927103e-06, "loss": 0.559, "step": 147980 }, { "epoch": 0.8796832926155108, "grad_norm": 5.512423038482666, "learning_rate": 9.825380133376623e-06, "loss": 0.5729, "step": 147990 }, { "epoch": 0.8797427346921792, "grad_norm": 6.489266395568848, "learning_rate": 9.825325772516261e-06, "loss": 0.6267, "step": 148000 }, { "epoch": 0.8798021767688476, "grad_norm": 5.013201713562012, "learning_rate": 9.825271403346113e-06, "loss": 0.5502, "step": 148010 }, { "epoch": 0.879861618845516, "grad_norm": 6.7103657722473145, "learning_rate": 9.82521702586627e-06, "loss": 0.585, "step": 148020 }, { "epoch": 0.8799210609221844, "grad_norm": 5.279613971710205, "learning_rate": 9.825162640076828e-06, "loss": 0.571, "step": 148030 }, { "epoch": 0.8799805029988528, "grad_norm": 5.333020210266113, "learning_rate": 9.825108245977882e-06, "loss": 0.5271, "step": 148040 }, { "epoch": 0.8800399450755212, "grad_norm": 4.637148857116699, "learning_rate": 9.825053843569523e-06, "loss": 0.5708, "step": 148050 }, { "epoch": 0.8800993871521895, "grad_norm": 5.272571563720703, "learning_rate": 9.824999432851845e-06, "loss": 0.543, "step": 148060 }, { "epoch": 0.8801588292288579, "grad_norm": 6.481191635131836, "learning_rate": 9.824945013824944e-06, "loss": 0.6012, "step": 148070 }, { "epoch": 0.8802182713055263, "grad_norm": 4.631932735443115, "learning_rate": 9.82489058648891e-06, "loss": 0.536, "step": 148080 }, { "epoch": 0.8802777133821947, "grad_norm": 4.907370090484619, "learning_rate": 9.82483615084384e-06, "loss": 0.5575, "step": 148090 }, { "epoch": 0.8803371554588632, "grad_norm": 5.207948207855225, "learning_rate": 9.824781706889826e-06, "loss": 0.5961, "step": 148100 }, { "epoch": 0.8803965975355315, "grad_norm": 5.346268177032471, "learning_rate": 9.824727254626962e-06, "loss": 0.523, "step": 148110 }, { "epoch": 0.8804560396121999, "grad_norm": 5.205221176147461, "learning_rate": 9.82467279405534e-06, "loss": 0.5408, "step": 148120 }, { "epoch": 0.8805154816888683, "grad_norm": 5.438679218292236, "learning_rate": 9.824618325175059e-06, "loss": 0.5578, "step": 148130 }, { "epoch": 0.8805749237655367, "grad_norm": 4.968533992767334, "learning_rate": 9.824563847986208e-06, "loss": 0.5445, "step": 148140 }, { "epoch": 0.8806343658422051, "grad_norm": 5.986963748931885, "learning_rate": 9.824509362488883e-06, "loss": 0.5348, "step": 148150 }, { "epoch": 0.8806938079188734, "grad_norm": 4.99776029586792, "learning_rate": 9.824454868683177e-06, "loss": 0.5673, "step": 148160 }, { "epoch": 0.8807532499955418, "grad_norm": 4.555417537689209, "learning_rate": 9.824400366569185e-06, "loss": 0.5311, "step": 148170 }, { "epoch": 0.8808126920722102, "grad_norm": 6.124667167663574, "learning_rate": 9.824345856147e-06, "loss": 0.5778, "step": 148180 }, { "epoch": 0.8808721341488787, "grad_norm": 4.690305709838867, "learning_rate": 9.824291337416713e-06, "loss": 0.5373, "step": 148190 }, { "epoch": 0.880931576225547, "grad_norm": 4.7143940925598145, "learning_rate": 9.824236810378423e-06, "loss": 0.525, "step": 148200 }, { "epoch": 0.8809910183022154, "grad_norm": 4.030735015869141, "learning_rate": 9.824182275032222e-06, "loss": 0.4864, "step": 148210 }, { "epoch": 0.8810504603788838, "grad_norm": 6.772838592529297, "learning_rate": 9.824127731378203e-06, "loss": 0.5732, "step": 148220 }, { "epoch": 0.8811099024555522, "grad_norm": 4.9192609786987305, "learning_rate": 9.82407317941646e-06, "loss": 0.5345, "step": 148230 }, { "epoch": 0.8811693445322206, "grad_norm": 4.925363540649414, "learning_rate": 9.824018619147087e-06, "loss": 0.5657, "step": 148240 }, { "epoch": 0.8812287866088889, "grad_norm": 6.401480197906494, "learning_rate": 9.823964050570179e-06, "loss": 0.5401, "step": 148250 }, { "epoch": 0.8812882286855573, "grad_norm": 5.39916467666626, "learning_rate": 9.823909473685829e-06, "loss": 0.5885, "step": 148260 }, { "epoch": 0.8813476707622258, "grad_norm": 4.606634140014648, "learning_rate": 9.823854888494131e-06, "loss": 0.5097, "step": 148270 }, { "epoch": 0.8814071128388942, "grad_norm": 4.240490913391113, "learning_rate": 9.823800294995181e-06, "loss": 0.544, "step": 148280 }, { "epoch": 0.8814665549155626, "grad_norm": 5.1237616539001465, "learning_rate": 9.823745693189069e-06, "loss": 0.5686, "step": 148290 }, { "epoch": 0.8815259969922309, "grad_norm": 6.193714618682861, "learning_rate": 9.823691083075893e-06, "loss": 0.5397, "step": 148300 }, { "epoch": 0.8815854390688993, "grad_norm": 5.784638404846191, "learning_rate": 9.823636464655745e-06, "loss": 0.5898, "step": 148310 }, { "epoch": 0.8816448811455677, "grad_norm": 5.780955791473389, "learning_rate": 9.82358183792872e-06, "loss": 0.6059, "step": 148320 }, { "epoch": 0.8817043232222361, "grad_norm": 6.714574337005615, "learning_rate": 9.82352720289491e-06, "loss": 0.6188, "step": 148330 }, { "epoch": 0.8817637652989044, "grad_norm": 5.891255855560303, "learning_rate": 9.823472559554412e-06, "loss": 0.5853, "step": 148340 }, { "epoch": 0.8818232073755728, "grad_norm": 5.111268043518066, "learning_rate": 9.823417907907318e-06, "loss": 0.5822, "step": 148350 }, { "epoch": 0.8818826494522413, "grad_norm": 5.594841957092285, "learning_rate": 9.823363247953724e-06, "loss": 0.5373, "step": 148360 }, { "epoch": 0.8819420915289097, "grad_norm": 6.607085227966309, "learning_rate": 9.823308579693721e-06, "loss": 0.5174, "step": 148370 }, { "epoch": 0.8820015336055781, "grad_norm": 5.177018165588379, "learning_rate": 9.823253903127405e-06, "loss": 0.5512, "step": 148380 }, { "epoch": 0.8820609756822464, "grad_norm": 5.617403507232666, "learning_rate": 9.823199218254873e-06, "loss": 0.5443, "step": 148390 }, { "epoch": 0.8821204177589148, "grad_norm": 6.461555004119873, "learning_rate": 9.823144525076215e-06, "loss": 0.5711, "step": 148400 }, { "epoch": 0.8821798598355832, "grad_norm": 4.957306385040283, "learning_rate": 9.823089823591525e-06, "loss": 0.521, "step": 148410 }, { "epoch": 0.8822393019122516, "grad_norm": 4.048593044281006, "learning_rate": 9.8230351138009e-06, "loss": 0.5591, "step": 148420 }, { "epoch": 0.8822987439889199, "grad_norm": 4.55755090713501, "learning_rate": 9.822980395704434e-06, "loss": 0.5155, "step": 148430 }, { "epoch": 0.8823581860655884, "grad_norm": 4.688945293426514, "learning_rate": 9.822925669302222e-06, "loss": 0.5579, "step": 148440 }, { "epoch": 0.8824176281422568, "grad_norm": 4.737189292907715, "learning_rate": 9.822870934594353e-06, "loss": 0.5784, "step": 148450 }, { "epoch": 0.8824770702189252, "grad_norm": 5.139988422393799, "learning_rate": 9.822816191580927e-06, "loss": 0.5378, "step": 148460 }, { "epoch": 0.8825365122955936, "grad_norm": 5.997811317443848, "learning_rate": 9.822761440262034e-06, "loss": 0.6205, "step": 148470 }, { "epoch": 0.8825959543722619, "grad_norm": 5.308451175689697, "learning_rate": 9.822706680637771e-06, "loss": 0.5408, "step": 148480 }, { "epoch": 0.8826553964489303, "grad_norm": 3.959036111831665, "learning_rate": 9.822651912708232e-06, "loss": 0.5334, "step": 148490 }, { "epoch": 0.8827148385255987, "grad_norm": 4.876224040985107, "learning_rate": 9.822597136473511e-06, "loss": 0.536, "step": 148500 }, { "epoch": 0.8827742806022671, "grad_norm": 5.47806978225708, "learning_rate": 9.822542351933703e-06, "loss": 0.6012, "step": 148510 }, { "epoch": 0.8828337226789356, "grad_norm": 5.627123832702637, "learning_rate": 9.822487559088902e-06, "loss": 0.5209, "step": 148520 }, { "epoch": 0.8828931647556039, "grad_norm": 5.399669170379639, "learning_rate": 9.8224327579392e-06, "loss": 0.56, "step": 148530 }, { "epoch": 0.8829526068322723, "grad_norm": 6.068525791168213, "learning_rate": 9.822377948484695e-06, "loss": 0.5827, "step": 148540 }, { "epoch": 0.8830120489089407, "grad_norm": 5.111570358276367, "learning_rate": 9.82232313072548e-06, "loss": 0.6298, "step": 148550 }, { "epoch": 0.8830714909856091, "grad_norm": 5.020221710205078, "learning_rate": 9.822268304661647e-06, "loss": 0.5251, "step": 148560 }, { "epoch": 0.8831309330622774, "grad_norm": 4.982009410858154, "learning_rate": 9.822213470293293e-06, "loss": 0.5858, "step": 148570 }, { "epoch": 0.8831903751389458, "grad_norm": 4.890346527099609, "learning_rate": 9.822158627620515e-06, "loss": 0.5369, "step": 148580 }, { "epoch": 0.8832498172156142, "grad_norm": 4.44143533706665, "learning_rate": 9.822103776643402e-06, "loss": 0.5339, "step": 148590 }, { "epoch": 0.8833092592922827, "grad_norm": 5.022220134735107, "learning_rate": 9.822048917362052e-06, "loss": 0.5332, "step": 148600 }, { "epoch": 0.8833687013689511, "grad_norm": 6.198999881744385, "learning_rate": 9.821994049776557e-06, "loss": 0.5343, "step": 148610 }, { "epoch": 0.8834281434456194, "grad_norm": 7.363947868347168, "learning_rate": 9.821939173887014e-06, "loss": 0.5593, "step": 148620 }, { "epoch": 0.8834875855222878, "grad_norm": 5.398934364318848, "learning_rate": 9.821884289693516e-06, "loss": 0.5831, "step": 148630 }, { "epoch": 0.8835470275989562, "grad_norm": 4.226471424102783, "learning_rate": 9.821829397196159e-06, "loss": 0.5168, "step": 148640 }, { "epoch": 0.8836064696756246, "grad_norm": 4.326310157775879, "learning_rate": 9.821774496395035e-06, "loss": 0.5683, "step": 148650 }, { "epoch": 0.883665911752293, "grad_norm": 5.220345973968506, "learning_rate": 9.821719587290241e-06, "loss": 0.5613, "step": 148660 }, { "epoch": 0.8837253538289613, "grad_norm": 5.0841064453125, "learning_rate": 9.821664669881869e-06, "loss": 0.4988, "step": 148670 }, { "epoch": 0.8837847959056297, "grad_norm": 5.921458721160889, "learning_rate": 9.821609744170017e-06, "loss": 0.6337, "step": 148680 }, { "epoch": 0.8838442379822982, "grad_norm": 5.755265712738037, "learning_rate": 9.821554810154776e-06, "loss": 0.5692, "step": 148690 }, { "epoch": 0.8839036800589666, "grad_norm": 6.132410049438477, "learning_rate": 9.821499867836244e-06, "loss": 0.544, "step": 148700 }, { "epoch": 0.8839631221356349, "grad_norm": 4.215624809265137, "learning_rate": 9.821444917214514e-06, "loss": 0.5257, "step": 148710 }, { "epoch": 0.8840225642123033, "grad_norm": 5.141581058502197, "learning_rate": 9.821389958289678e-06, "loss": 0.5551, "step": 148720 }, { "epoch": 0.8840820062889717, "grad_norm": 6.183439254760742, "learning_rate": 9.821334991061835e-06, "loss": 0.6053, "step": 148730 }, { "epoch": 0.8841414483656401, "grad_norm": 5.607532978057861, "learning_rate": 9.821280015531078e-06, "loss": 0.529, "step": 148740 }, { "epoch": 0.8842008904423085, "grad_norm": 4.88939094543457, "learning_rate": 9.821225031697501e-06, "loss": 0.4748, "step": 148750 }, { "epoch": 0.8842603325189768, "grad_norm": 5.268960475921631, "learning_rate": 9.8211700395612e-06, "loss": 0.5247, "step": 148760 }, { "epoch": 0.8843197745956453, "grad_norm": 7.6657304763793945, "learning_rate": 9.821115039122269e-06, "loss": 0.5565, "step": 148770 }, { "epoch": 0.8843792166723137, "grad_norm": 4.563809871673584, "learning_rate": 9.821060030380802e-06, "loss": 0.5428, "step": 148780 }, { "epoch": 0.8844386587489821, "grad_norm": 4.211553573608398, "learning_rate": 9.821005013336895e-06, "loss": 0.4921, "step": 148790 }, { "epoch": 0.8844981008256504, "grad_norm": 4.6467814445495605, "learning_rate": 9.820949987990641e-06, "loss": 0.5379, "step": 148800 }, { "epoch": 0.8845575429023188, "grad_norm": 5.542223930358887, "learning_rate": 9.820894954342136e-06, "loss": 0.6642, "step": 148810 }, { "epoch": 0.8846169849789872, "grad_norm": 5.179402828216553, "learning_rate": 9.820839912391476e-06, "loss": 0.5263, "step": 148820 }, { "epoch": 0.8846764270556556, "grad_norm": 5.182949542999268, "learning_rate": 9.820784862138754e-06, "loss": 0.5539, "step": 148830 }, { "epoch": 0.884735869132324, "grad_norm": 6.36884069442749, "learning_rate": 9.820729803584065e-06, "loss": 0.5958, "step": 148840 }, { "epoch": 0.8847953112089924, "grad_norm": 4.041249752044678, "learning_rate": 9.820674736727504e-06, "loss": 0.579, "step": 148850 }, { "epoch": 0.8848547532856608, "grad_norm": 4.946176528930664, "learning_rate": 9.820619661569167e-06, "loss": 0.5997, "step": 148860 }, { "epoch": 0.8849141953623292, "grad_norm": 6.057585716247559, "learning_rate": 9.820564578109147e-06, "loss": 0.5464, "step": 148870 }, { "epoch": 0.8849736374389976, "grad_norm": 5.752082824707031, "learning_rate": 9.820509486347538e-06, "loss": 0.5068, "step": 148880 }, { "epoch": 0.885033079515666, "grad_norm": 5.327538013458252, "learning_rate": 9.820454386284437e-06, "loss": 0.5388, "step": 148890 }, { "epoch": 0.8850925215923343, "grad_norm": 4.857779026031494, "learning_rate": 9.82039927791994e-06, "loss": 0.5253, "step": 148900 }, { "epoch": 0.8851519636690027, "grad_norm": 4.383437156677246, "learning_rate": 9.82034416125414e-06, "loss": 0.5707, "step": 148910 }, { "epoch": 0.8852114057456711, "grad_norm": 4.034538269042969, "learning_rate": 9.820289036287132e-06, "loss": 0.5564, "step": 148920 }, { "epoch": 0.8852708478223396, "grad_norm": 6.325368404388428, "learning_rate": 9.82023390301901e-06, "loss": 0.5864, "step": 148930 }, { "epoch": 0.8853302898990079, "grad_norm": 6.481029033660889, "learning_rate": 9.820178761449871e-06, "loss": 0.5498, "step": 148940 }, { "epoch": 0.8853897319756763, "grad_norm": 4.935981273651123, "learning_rate": 9.820123611579808e-06, "loss": 0.5618, "step": 148950 }, { "epoch": 0.8854491740523447, "grad_norm": 6.485429286956787, "learning_rate": 9.820068453408919e-06, "loss": 0.56, "step": 148960 }, { "epoch": 0.8855086161290131, "grad_norm": 6.286943435668945, "learning_rate": 9.820013286937296e-06, "loss": 0.5837, "step": 148970 }, { "epoch": 0.8855680582056815, "grad_norm": 4.636739253997803, "learning_rate": 9.819958112165036e-06, "loss": 0.5318, "step": 148980 }, { "epoch": 0.8856275002823498, "grad_norm": 4.774165630340576, "learning_rate": 9.819902929092231e-06, "loss": 0.5412, "step": 148990 }, { "epoch": 0.8856869423590182, "grad_norm": 6.052639484405518, "learning_rate": 9.819847737718979e-06, "loss": 0.5277, "step": 149000 }, { "epoch": 0.8857463844356867, "grad_norm": 5.914793968200684, "learning_rate": 9.819792538045374e-06, "loss": 0.5764, "step": 149010 }, { "epoch": 0.8858058265123551, "grad_norm": 5.706271171569824, "learning_rate": 9.81973733007151e-06, "loss": 0.5544, "step": 149020 }, { "epoch": 0.8858652685890235, "grad_norm": 4.716098308563232, "learning_rate": 9.819682113797487e-06, "loss": 0.5528, "step": 149030 }, { "epoch": 0.8859247106656918, "grad_norm": 4.98408317565918, "learning_rate": 9.819626889223392e-06, "loss": 0.5155, "step": 149040 }, { "epoch": 0.8859841527423602, "grad_norm": 4.790374279022217, "learning_rate": 9.819571656349328e-06, "loss": 0.5503, "step": 149050 }, { "epoch": 0.8860435948190286, "grad_norm": 6.238276958465576, "learning_rate": 9.819516415175383e-06, "loss": 0.5398, "step": 149060 }, { "epoch": 0.886103036895697, "grad_norm": 6.441043376922607, "learning_rate": 9.819461165701659e-06, "loss": 0.5903, "step": 149070 }, { "epoch": 0.8861624789723653, "grad_norm": 6.325348854064941, "learning_rate": 9.819405907928246e-06, "loss": 0.5999, "step": 149080 }, { "epoch": 0.8862219210490337, "grad_norm": 5.004297733306885, "learning_rate": 9.819350641855241e-06, "loss": 0.5592, "step": 149090 }, { "epoch": 0.8862813631257022, "grad_norm": 5.730884552001953, "learning_rate": 9.81929536748274e-06, "loss": 0.5791, "step": 149100 }, { "epoch": 0.8863408052023706, "grad_norm": 4.392956733703613, "learning_rate": 9.819240084810838e-06, "loss": 0.5411, "step": 149110 }, { "epoch": 0.886400247279039, "grad_norm": 5.970017433166504, "learning_rate": 9.819184793839627e-06, "loss": 0.5513, "step": 149120 }, { "epoch": 0.8864596893557073, "grad_norm": 5.699639320373535, "learning_rate": 9.819129494569205e-06, "loss": 0.5683, "step": 149130 }, { "epoch": 0.8865191314323757, "grad_norm": 5.236640930175781, "learning_rate": 9.819074186999668e-06, "loss": 0.536, "step": 149140 }, { "epoch": 0.8865785735090441, "grad_norm": 5.857048511505127, "learning_rate": 9.819018871131112e-06, "loss": 0.5536, "step": 149150 }, { "epoch": 0.8866380155857125, "grad_norm": 5.879269599914551, "learning_rate": 9.818963546963629e-06, "loss": 0.5215, "step": 149160 }, { "epoch": 0.8866974576623808, "grad_norm": 7.091357707977295, "learning_rate": 9.818908214497316e-06, "loss": 0.6205, "step": 149170 }, { "epoch": 0.8867568997390493, "grad_norm": 4.894418239593506, "learning_rate": 9.818852873732268e-06, "loss": 0.5438, "step": 149180 }, { "epoch": 0.8868163418157177, "grad_norm": 5.671748638153076, "learning_rate": 9.818797524668579e-06, "loss": 0.5271, "step": 149190 }, { "epoch": 0.8868757838923861, "grad_norm": 5.768880844116211, "learning_rate": 9.818742167306347e-06, "loss": 0.4957, "step": 149200 }, { "epoch": 0.8869352259690545, "grad_norm": 5.664865493774414, "learning_rate": 9.818686801645666e-06, "loss": 0.5594, "step": 149210 }, { "epoch": 0.8869946680457228, "grad_norm": 5.786452770233154, "learning_rate": 9.818631427686631e-06, "loss": 0.5812, "step": 149220 }, { "epoch": 0.8870541101223912, "grad_norm": 5.532378196716309, "learning_rate": 9.818576045429337e-06, "loss": 0.5626, "step": 149230 }, { "epoch": 0.8871135521990596, "grad_norm": 5.870285511016846, "learning_rate": 9.818520654873883e-06, "loss": 0.5997, "step": 149240 }, { "epoch": 0.887172994275728, "grad_norm": 4.822188854217529, "learning_rate": 9.818465256020359e-06, "loss": 0.5376, "step": 149250 }, { "epoch": 0.8872324363523965, "grad_norm": 5.330673694610596, "learning_rate": 9.818409848868863e-06, "loss": 0.5463, "step": 149260 }, { "epoch": 0.8872918784290648, "grad_norm": 4.405959606170654, "learning_rate": 9.81835443341949e-06, "loss": 0.5554, "step": 149270 }, { "epoch": 0.8873513205057332, "grad_norm": 4.766488075256348, "learning_rate": 9.818299009672338e-06, "loss": 0.5746, "step": 149280 }, { "epoch": 0.8874107625824016, "grad_norm": 4.025339603424072, "learning_rate": 9.818243577627498e-06, "loss": 0.56, "step": 149290 }, { "epoch": 0.88747020465907, "grad_norm": 5.766830921173096, "learning_rate": 9.818188137285068e-06, "loss": 0.6071, "step": 149300 }, { "epoch": 0.8875296467357383, "grad_norm": 5.643318176269531, "learning_rate": 9.818132688645143e-06, "loss": 0.5496, "step": 149310 }, { "epoch": 0.8875890888124067, "grad_norm": 5.918227195739746, "learning_rate": 9.818077231707822e-06, "loss": 0.5338, "step": 149320 }, { "epoch": 0.8876485308890751, "grad_norm": 4.144550323486328, "learning_rate": 9.818021766473193e-06, "loss": 0.5494, "step": 149330 }, { "epoch": 0.8877079729657436, "grad_norm": 6.386114597320557, "learning_rate": 9.817966292941356e-06, "loss": 0.5994, "step": 149340 }, { "epoch": 0.887767415042412, "grad_norm": 6.19142484664917, "learning_rate": 9.817910811112408e-06, "loss": 0.5196, "step": 149350 }, { "epoch": 0.8878268571190803, "grad_norm": 5.217175006866455, "learning_rate": 9.817855320986442e-06, "loss": 0.5806, "step": 149360 }, { "epoch": 0.8878862991957487, "grad_norm": 5.206979751586914, "learning_rate": 9.817799822563555e-06, "loss": 0.5125, "step": 149370 }, { "epoch": 0.8879457412724171, "grad_norm": 5.126906394958496, "learning_rate": 9.817744315843839e-06, "loss": 0.5597, "step": 149380 }, { "epoch": 0.8880051833490855, "grad_norm": 7.452216148376465, "learning_rate": 9.817688800827395e-06, "loss": 0.6218, "step": 149390 }, { "epoch": 0.8880646254257539, "grad_norm": 5.051304340362549, "learning_rate": 9.817633277514315e-06, "loss": 0.5269, "step": 149400 }, { "epoch": 0.8881240675024222, "grad_norm": 5.399843692779541, "learning_rate": 9.817577745904695e-06, "loss": 0.5623, "step": 149410 }, { "epoch": 0.8881835095790906, "grad_norm": 6.325344085693359, "learning_rate": 9.817522205998634e-06, "loss": 0.5672, "step": 149420 }, { "epoch": 0.8882429516557591, "grad_norm": 6.186856746673584, "learning_rate": 9.817466657796223e-06, "loss": 0.5386, "step": 149430 }, { "epoch": 0.8883023937324275, "grad_norm": 5.2871623039245605, "learning_rate": 9.81741110129756e-06, "loss": 0.5651, "step": 149440 }, { "epoch": 0.8883618358090958, "grad_norm": 3.7934763431549072, "learning_rate": 9.81735553650274e-06, "loss": 0.5425, "step": 149450 }, { "epoch": 0.8884212778857642, "grad_norm": 5.499454498291016, "learning_rate": 9.81729996341186e-06, "loss": 0.5807, "step": 149460 }, { "epoch": 0.8884807199624326, "grad_norm": 6.223113536834717, "learning_rate": 9.817244382025014e-06, "loss": 0.5866, "step": 149470 }, { "epoch": 0.888540162039101, "grad_norm": 3.864093780517578, "learning_rate": 9.817188792342299e-06, "loss": 0.5324, "step": 149480 }, { "epoch": 0.8885996041157694, "grad_norm": 6.437406539916992, "learning_rate": 9.817133194363809e-06, "loss": 0.5161, "step": 149490 }, { "epoch": 0.8886590461924377, "grad_norm": 4.9296793937683105, "learning_rate": 9.81707758808964e-06, "loss": 0.5971, "step": 149500 }, { "epoch": 0.8887184882691062, "grad_norm": 4.917675971984863, "learning_rate": 9.81702197351989e-06, "loss": 0.5475, "step": 149510 }, { "epoch": 0.8887779303457746, "grad_norm": 4.743838310241699, "learning_rate": 9.816966350654653e-06, "loss": 0.5381, "step": 149520 }, { "epoch": 0.888837372422443, "grad_norm": 6.707273960113525, "learning_rate": 9.816910719494026e-06, "loss": 0.6125, "step": 149530 }, { "epoch": 0.8888968144991113, "grad_norm": 4.860872268676758, "learning_rate": 9.816855080038104e-06, "loss": 0.5557, "step": 149540 }, { "epoch": 0.8889562565757797, "grad_norm": 5.132925987243652, "learning_rate": 9.816799432286981e-06, "loss": 0.5484, "step": 149550 }, { "epoch": 0.8890156986524481, "grad_norm": 5.3389811515808105, "learning_rate": 9.816743776240756e-06, "loss": 0.5518, "step": 149560 }, { "epoch": 0.8890751407291165, "grad_norm": 4.675455570220947, "learning_rate": 9.816688111899525e-06, "loss": 0.5704, "step": 149570 }, { "epoch": 0.889134582805785, "grad_norm": 4.750624179840088, "learning_rate": 9.81663243926338e-06, "loss": 0.5704, "step": 149580 }, { "epoch": 0.8891940248824532, "grad_norm": 4.606636047363281, "learning_rate": 9.816576758332419e-06, "loss": 0.5371, "step": 149590 }, { "epoch": 0.8892534669591217, "grad_norm": 4.909409999847412, "learning_rate": 9.816521069106739e-06, "loss": 0.5809, "step": 149600 }, { "epoch": 0.8893129090357901, "grad_norm": 4.935207366943359, "learning_rate": 9.816465371586436e-06, "loss": 0.4928, "step": 149610 }, { "epoch": 0.8893723511124585, "grad_norm": 4.494928359985352, "learning_rate": 9.816409665771604e-06, "loss": 0.5324, "step": 149620 }, { "epoch": 0.8894317931891269, "grad_norm": 5.534696102142334, "learning_rate": 9.81635395166234e-06, "loss": 0.5448, "step": 149630 }, { "epoch": 0.8894912352657952, "grad_norm": 5.062885761260986, "learning_rate": 9.81629822925874e-06, "loss": 0.5832, "step": 149640 }, { "epoch": 0.8895506773424636, "grad_norm": 5.474401950836182, "learning_rate": 9.8162424985609e-06, "loss": 0.5801, "step": 149650 }, { "epoch": 0.889610119419132, "grad_norm": 4.642507553100586, "learning_rate": 9.816186759568914e-06, "loss": 0.551, "step": 149660 }, { "epoch": 0.8896695614958005, "grad_norm": 5.43602180480957, "learning_rate": 9.816131012282881e-06, "loss": 0.5214, "step": 149670 }, { "epoch": 0.8897290035724688, "grad_norm": 5.003681659698486, "learning_rate": 9.816075256702897e-06, "loss": 0.5454, "step": 149680 }, { "epoch": 0.8897884456491372, "grad_norm": 5.397134780883789, "learning_rate": 9.816019492829054e-06, "loss": 0.5066, "step": 149690 }, { "epoch": 0.8898478877258056, "grad_norm": 6.58709716796875, "learning_rate": 9.815963720661452e-06, "loss": 0.5823, "step": 149700 }, { "epoch": 0.889907329802474, "grad_norm": 6.554378032684326, "learning_rate": 9.815907940200186e-06, "loss": 0.5747, "step": 149710 }, { "epoch": 0.8899667718791424, "grad_norm": 6.190345287322998, "learning_rate": 9.815852151445353e-06, "loss": 0.546, "step": 149720 }, { "epoch": 0.8900262139558107, "grad_norm": 6.549203872680664, "learning_rate": 9.815796354397048e-06, "loss": 0.5943, "step": 149730 }, { "epoch": 0.8900856560324791, "grad_norm": 6.686974048614502, "learning_rate": 9.815740549055367e-06, "loss": 0.5447, "step": 149740 }, { "epoch": 0.8901450981091475, "grad_norm": 4.4679856300354, "learning_rate": 9.815684735420403e-06, "loss": 0.5576, "step": 149750 }, { "epoch": 0.890204540185816, "grad_norm": 6.218266487121582, "learning_rate": 9.815628913492258e-06, "loss": 0.5603, "step": 149760 }, { "epoch": 0.8902639822624844, "grad_norm": 5.727335453033447, "learning_rate": 9.815573083271026e-06, "loss": 0.574, "step": 149770 }, { "epoch": 0.8903234243391527, "grad_norm": 5.69075870513916, "learning_rate": 9.8155172447568e-06, "loss": 0.5723, "step": 149780 }, { "epoch": 0.8903828664158211, "grad_norm": 4.142236232757568, "learning_rate": 9.815461397949681e-06, "loss": 0.5442, "step": 149790 }, { "epoch": 0.8904423084924895, "grad_norm": 4.498445987701416, "learning_rate": 9.815405542849763e-06, "loss": 0.5409, "step": 149800 }, { "epoch": 0.8905017505691579, "grad_norm": 7.302796363830566, "learning_rate": 9.81534967945714e-06, "loss": 0.5787, "step": 149810 }, { "epoch": 0.8905611926458262, "grad_norm": 3.8178865909576416, "learning_rate": 9.815293807771913e-06, "loss": 0.5371, "step": 149820 }, { "epoch": 0.8906206347224946, "grad_norm": 4.0109405517578125, "learning_rate": 9.815237927794173e-06, "loss": 0.5173, "step": 149830 }, { "epoch": 0.8906800767991631, "grad_norm": 4.806354999542236, "learning_rate": 9.81518203952402e-06, "loss": 0.5216, "step": 149840 }, { "epoch": 0.8907395188758315, "grad_norm": 3.754392147064209, "learning_rate": 9.815126142961548e-06, "loss": 0.58, "step": 149850 }, { "epoch": 0.8907989609524999, "grad_norm": 6.684070110321045, "learning_rate": 9.815070238106857e-06, "loss": 0.5296, "step": 149860 }, { "epoch": 0.8908584030291682, "grad_norm": 4.801387786865234, "learning_rate": 9.815014324960036e-06, "loss": 0.5166, "step": 149870 }, { "epoch": 0.8909178451058366, "grad_norm": 5.629728317260742, "learning_rate": 9.81495840352119e-06, "loss": 0.5317, "step": 149880 }, { "epoch": 0.890977287182505, "grad_norm": 4.416749477386475, "learning_rate": 9.81490247379041e-06, "loss": 0.5594, "step": 149890 }, { "epoch": 0.8910367292591734, "grad_norm": 4.948446273803711, "learning_rate": 9.814846535767793e-06, "loss": 0.5672, "step": 149900 }, { "epoch": 0.8910961713358417, "grad_norm": 4.565764427185059, "learning_rate": 9.814790589453435e-06, "loss": 0.6023, "step": 149910 }, { "epoch": 0.8911556134125102, "grad_norm": 5.1593756675720215, "learning_rate": 9.814734634847434e-06, "loss": 0.5739, "step": 149920 }, { "epoch": 0.8912150554891786, "grad_norm": 5.713431358337402, "learning_rate": 9.814678671949886e-06, "loss": 0.5393, "step": 149930 }, { "epoch": 0.891274497565847, "grad_norm": 5.1019062995910645, "learning_rate": 9.814622700760885e-06, "loss": 0.5869, "step": 149940 }, { "epoch": 0.8913339396425154, "grad_norm": 4.481391906738281, "learning_rate": 9.814566721280531e-06, "loss": 0.5686, "step": 149950 }, { "epoch": 0.8913933817191837, "grad_norm": 4.076284885406494, "learning_rate": 9.814510733508917e-06, "loss": 0.4963, "step": 149960 }, { "epoch": 0.8914528237958521, "grad_norm": 5.994776248931885, "learning_rate": 9.814454737446144e-06, "loss": 0.5098, "step": 149970 }, { "epoch": 0.8915122658725205, "grad_norm": 7.028245449066162, "learning_rate": 9.814398733092303e-06, "loss": 0.6342, "step": 149980 }, { "epoch": 0.8915717079491889, "grad_norm": 6.725870609283447, "learning_rate": 9.814342720447494e-06, "loss": 0.5086, "step": 149990 }, { "epoch": 0.8916311500258574, "grad_norm": 4.315743446350098, "learning_rate": 9.81428669951181e-06, "loss": 0.5557, "step": 150000 }, { "epoch": 0.8916905921025257, "grad_norm": 4.549576759338379, "learning_rate": 9.814230670285352e-06, "loss": 0.5243, "step": 150010 }, { "epoch": 0.8917500341791941, "grad_norm": 4.694796562194824, "learning_rate": 9.814174632768215e-06, "loss": 0.5413, "step": 150020 }, { "epoch": 0.8918094762558625, "grad_norm": 4.932648658752441, "learning_rate": 9.814118586960496e-06, "loss": 0.5177, "step": 150030 }, { "epoch": 0.8918689183325309, "grad_norm": 6.278600215911865, "learning_rate": 9.814062532862287e-06, "loss": 0.5849, "step": 150040 }, { "epoch": 0.8919283604091992, "grad_norm": 4.714922904968262, "learning_rate": 9.814006470473689e-06, "loss": 0.4842, "step": 150050 }, { "epoch": 0.8919878024858676, "grad_norm": 7.631807327270508, "learning_rate": 9.813950399794799e-06, "loss": 0.5467, "step": 150060 }, { "epoch": 0.892047244562536, "grad_norm": 4.6499857902526855, "learning_rate": 9.81389432082571e-06, "loss": 0.506, "step": 150070 }, { "epoch": 0.8921066866392044, "grad_norm": 5.551033973693848, "learning_rate": 9.813838233566521e-06, "loss": 0.5484, "step": 150080 }, { "epoch": 0.8921661287158729, "grad_norm": 4.733603000640869, "learning_rate": 9.813782138017329e-06, "loss": 0.5844, "step": 150090 }, { "epoch": 0.8922255707925412, "grad_norm": 6.364182472229004, "learning_rate": 9.813726034178228e-06, "loss": 0.519, "step": 150100 }, { "epoch": 0.8922850128692096, "grad_norm": 5.0179924964904785, "learning_rate": 9.813669922049318e-06, "loss": 0.5104, "step": 150110 }, { "epoch": 0.892344454945878, "grad_norm": 6.5654144287109375, "learning_rate": 9.813613801630695e-06, "loss": 0.5336, "step": 150120 }, { "epoch": 0.8924038970225464, "grad_norm": 4.9514079093933105, "learning_rate": 9.813557672922453e-06, "loss": 0.5462, "step": 150130 }, { "epoch": 0.8924633390992148, "grad_norm": 5.000059127807617, "learning_rate": 9.813501535924691e-06, "loss": 0.5153, "step": 150140 }, { "epoch": 0.8925227811758831, "grad_norm": 4.7490997314453125, "learning_rate": 9.813445390637505e-06, "loss": 0.5815, "step": 150150 }, { "epoch": 0.8925822232525515, "grad_norm": 5.033891201019287, "learning_rate": 9.813389237060991e-06, "loss": 0.5276, "step": 150160 }, { "epoch": 0.89264166532922, "grad_norm": 5.432115077972412, "learning_rate": 9.813333075195247e-06, "loss": 0.5909, "step": 150170 }, { "epoch": 0.8927011074058884, "grad_norm": 4.647775173187256, "learning_rate": 9.81327690504037e-06, "loss": 0.5455, "step": 150180 }, { "epoch": 0.8927605494825567, "grad_norm": 4.734989166259766, "learning_rate": 9.813220726596454e-06, "loss": 0.5174, "step": 150190 }, { "epoch": 0.8928199915592251, "grad_norm": 6.653308391571045, "learning_rate": 9.813164539863599e-06, "loss": 0.504, "step": 150200 }, { "epoch": 0.8928794336358935, "grad_norm": 3.64726185798645, "learning_rate": 9.8131083448419e-06, "loss": 0.5233, "step": 150210 }, { "epoch": 0.8929388757125619, "grad_norm": 4.942028522491455, "learning_rate": 9.813052141531453e-06, "loss": 0.5582, "step": 150220 }, { "epoch": 0.8929983177892303, "grad_norm": 5.790942192077637, "learning_rate": 9.812995929932359e-06, "loss": 0.5316, "step": 150230 }, { "epoch": 0.8930577598658986, "grad_norm": 5.400855541229248, "learning_rate": 9.812939710044708e-06, "loss": 0.5635, "step": 150240 }, { "epoch": 0.893117201942567, "grad_norm": 4.907247066497803, "learning_rate": 9.812883481868603e-06, "loss": 0.5611, "step": 150250 }, { "epoch": 0.8931766440192355, "grad_norm": 5.767126083374023, "learning_rate": 9.812827245404138e-06, "loss": 0.5975, "step": 150260 }, { "epoch": 0.8932360860959039, "grad_norm": 4.639215469360352, "learning_rate": 9.812771000651408e-06, "loss": 0.4895, "step": 150270 }, { "epoch": 0.8932955281725722, "grad_norm": 6.543116092681885, "learning_rate": 9.812714747610515e-06, "loss": 0.5841, "step": 150280 }, { "epoch": 0.8933549702492406, "grad_norm": 4.9638590812683105, "learning_rate": 9.812658486281553e-06, "loss": 0.5378, "step": 150290 }, { "epoch": 0.893414412325909, "grad_norm": 4.958891868591309, "learning_rate": 9.812602216664618e-06, "loss": 0.5127, "step": 150300 }, { "epoch": 0.8934738544025774, "grad_norm": 5.492853164672852, "learning_rate": 9.812545938759806e-06, "loss": 0.5183, "step": 150310 }, { "epoch": 0.8935332964792458, "grad_norm": 7.04963493347168, "learning_rate": 9.812489652567218e-06, "loss": 0.5556, "step": 150320 }, { "epoch": 0.8935927385559141, "grad_norm": 8.325193405151367, "learning_rate": 9.812433358086947e-06, "loss": 0.5321, "step": 150330 }, { "epoch": 0.8936521806325826, "grad_norm": 6.096137523651123, "learning_rate": 9.812377055319093e-06, "loss": 0.6048, "step": 150340 }, { "epoch": 0.893711622709251, "grad_norm": 6.006742000579834, "learning_rate": 9.81232074426375e-06, "loss": 0.5561, "step": 150350 }, { "epoch": 0.8937710647859194, "grad_norm": 5.9484076499938965, "learning_rate": 9.81226442492102e-06, "loss": 0.5836, "step": 150360 }, { "epoch": 0.8938305068625878, "grad_norm": 6.110958099365234, "learning_rate": 9.812208097290991e-06, "loss": 0.5651, "step": 150370 }, { "epoch": 0.8938899489392561, "grad_norm": 5.468544006347656, "learning_rate": 9.812151761373769e-06, "loss": 0.5849, "step": 150380 }, { "epoch": 0.8939493910159245, "grad_norm": 7.173828601837158, "learning_rate": 9.812095417169447e-06, "loss": 0.5451, "step": 150390 }, { "epoch": 0.8940088330925929, "grad_norm": 5.408042907714844, "learning_rate": 9.812039064678123e-06, "loss": 0.5791, "step": 150400 }, { "epoch": 0.8940682751692614, "grad_norm": 4.4521589279174805, "learning_rate": 9.811982703899891e-06, "loss": 0.5532, "step": 150410 }, { "epoch": 0.8941277172459297, "grad_norm": 4.439380168914795, "learning_rate": 9.811926334834854e-06, "loss": 0.5566, "step": 150420 }, { "epoch": 0.8941871593225981, "grad_norm": 5.798713684082031, "learning_rate": 9.811869957483105e-06, "loss": 0.559, "step": 150430 }, { "epoch": 0.8942466013992665, "grad_norm": 3.4025180339813232, "learning_rate": 9.81181357184474e-06, "loss": 0.5285, "step": 150440 }, { "epoch": 0.8943060434759349, "grad_norm": 4.301690578460693, "learning_rate": 9.811757177919859e-06, "loss": 0.5246, "step": 150450 }, { "epoch": 0.8943654855526033, "grad_norm": 4.736515045166016, "learning_rate": 9.811700775708556e-06, "loss": 0.5146, "step": 150460 }, { "epoch": 0.8944249276292716, "grad_norm": 5.066375255584717, "learning_rate": 9.811644365210933e-06, "loss": 0.5377, "step": 150470 }, { "epoch": 0.89448436970594, "grad_norm": 5.933926582336426, "learning_rate": 9.811587946427084e-06, "loss": 0.5256, "step": 150480 }, { "epoch": 0.8945438117826084, "grad_norm": 4.309086799621582, "learning_rate": 9.811531519357105e-06, "loss": 0.5354, "step": 150490 }, { "epoch": 0.8946032538592769, "grad_norm": 5.199381351470947, "learning_rate": 9.811475084001097e-06, "loss": 0.5287, "step": 150500 }, { "epoch": 0.8946626959359453, "grad_norm": 4.717782974243164, "learning_rate": 9.811418640359151e-06, "loss": 0.5491, "step": 150510 }, { "epoch": 0.8947221380126136, "grad_norm": 5.645658016204834, "learning_rate": 9.811362188431371e-06, "loss": 0.5663, "step": 150520 }, { "epoch": 0.894781580089282, "grad_norm": 5.334587574005127, "learning_rate": 9.811305728217851e-06, "loss": 0.4988, "step": 150530 }, { "epoch": 0.8948410221659504, "grad_norm": 4.886922836303711, "learning_rate": 9.811249259718688e-06, "loss": 0.5815, "step": 150540 }, { "epoch": 0.8949004642426188, "grad_norm": 3.978070020675659, "learning_rate": 9.81119278293398e-06, "loss": 0.4888, "step": 150550 }, { "epoch": 0.8949599063192871, "grad_norm": 6.269534111022949, "learning_rate": 9.811136297863823e-06, "loss": 0.6357, "step": 150560 }, { "epoch": 0.8950193483959555, "grad_norm": 5.833506107330322, "learning_rate": 9.811079804508316e-06, "loss": 0.5406, "step": 150570 }, { "epoch": 0.895078790472624, "grad_norm": 5.562765598297119, "learning_rate": 9.811023302867555e-06, "loss": 0.5515, "step": 150580 }, { "epoch": 0.8951382325492924, "grad_norm": 6.088839530944824, "learning_rate": 9.810966792941638e-06, "loss": 0.5621, "step": 150590 }, { "epoch": 0.8951976746259608, "grad_norm": 5.742054462432861, "learning_rate": 9.810910274730663e-06, "loss": 0.5705, "step": 150600 }, { "epoch": 0.8952571167026291, "grad_norm": 5.49147891998291, "learning_rate": 9.810853748234725e-06, "loss": 0.5708, "step": 150610 }, { "epoch": 0.8953165587792975, "grad_norm": 4.987177848815918, "learning_rate": 9.810797213453925e-06, "loss": 0.5197, "step": 150620 }, { "epoch": 0.8953760008559659, "grad_norm": 6.314734935760498, "learning_rate": 9.810740670388356e-06, "loss": 0.5214, "step": 150630 }, { "epoch": 0.8954354429326343, "grad_norm": 5.115633487701416, "learning_rate": 9.810684119038118e-06, "loss": 0.51, "step": 150640 }, { "epoch": 0.8954948850093026, "grad_norm": 5.919622421264648, "learning_rate": 9.810627559403309e-06, "loss": 0.5697, "step": 150650 }, { "epoch": 0.895554327085971, "grad_norm": 6.0783867835998535, "learning_rate": 9.810570991484023e-06, "loss": 0.5245, "step": 150660 }, { "epoch": 0.8956137691626395, "grad_norm": 5.4574995040893555, "learning_rate": 9.810514415280363e-06, "loss": 0.5815, "step": 150670 }, { "epoch": 0.8956732112393079, "grad_norm": 6.002155303955078, "learning_rate": 9.810457830792421e-06, "loss": 0.5225, "step": 150680 }, { "epoch": 0.8957326533159763, "grad_norm": 4.854674339294434, "learning_rate": 9.810401238020298e-06, "loss": 0.5338, "step": 150690 }, { "epoch": 0.8957920953926446, "grad_norm": 6.375366687774658, "learning_rate": 9.810344636964089e-06, "loss": 0.5101, "step": 150700 }, { "epoch": 0.895851537469313, "grad_norm": 5.183946132659912, "learning_rate": 9.810288027623893e-06, "loss": 0.5151, "step": 150710 }, { "epoch": 0.8959109795459814, "grad_norm": 4.063128471374512, "learning_rate": 9.810231409999806e-06, "loss": 0.5365, "step": 150720 }, { "epoch": 0.8959704216226498, "grad_norm": 5.14018440246582, "learning_rate": 9.810174784091928e-06, "loss": 0.5365, "step": 150730 }, { "epoch": 0.8960298636993183, "grad_norm": 4.3791728019714355, "learning_rate": 9.810118149900354e-06, "loss": 0.4941, "step": 150740 }, { "epoch": 0.8960893057759866, "grad_norm": 4.9014363288879395, "learning_rate": 9.810061507425183e-06, "loss": 0.5477, "step": 150750 }, { "epoch": 0.896148747852655, "grad_norm": 6.747228145599365, "learning_rate": 9.810004856666512e-06, "loss": 0.5181, "step": 150760 }, { "epoch": 0.8962081899293234, "grad_norm": 6.61210298538208, "learning_rate": 9.80994819762444e-06, "loss": 0.52, "step": 150770 }, { "epoch": 0.8962676320059918, "grad_norm": 5.907810211181641, "learning_rate": 9.809891530299062e-06, "loss": 0.5452, "step": 150780 }, { "epoch": 0.8963270740826601, "grad_norm": 5.748007774353027, "learning_rate": 9.80983485469048e-06, "loss": 0.5611, "step": 150790 }, { "epoch": 0.8963865161593285, "grad_norm": 5.594954013824463, "learning_rate": 9.809778170798785e-06, "loss": 0.5627, "step": 150800 }, { "epoch": 0.8964459582359969, "grad_norm": 5.680445671081543, "learning_rate": 9.809721478624077e-06, "loss": 0.4961, "step": 150810 }, { "epoch": 0.8965054003126653, "grad_norm": 6.132003307342529, "learning_rate": 9.809664778166458e-06, "loss": 0.5004, "step": 150820 }, { "epoch": 0.8965648423893338, "grad_norm": 4.488533020019531, "learning_rate": 9.809608069426019e-06, "loss": 0.5234, "step": 150830 }, { "epoch": 0.8966242844660021, "grad_norm": 4.768092155456543, "learning_rate": 9.809551352402865e-06, "loss": 0.5325, "step": 150840 }, { "epoch": 0.8966837265426705, "grad_norm": 4.817016124725342, "learning_rate": 9.809494627097087e-06, "loss": 0.5214, "step": 150850 }, { "epoch": 0.8967431686193389, "grad_norm": 4.427452087402344, "learning_rate": 9.809437893508787e-06, "loss": 0.5239, "step": 150860 }, { "epoch": 0.8968026106960073, "grad_norm": 5.4013447761535645, "learning_rate": 9.80938115163806e-06, "loss": 0.536, "step": 150870 }, { "epoch": 0.8968620527726756, "grad_norm": 6.548637390136719, "learning_rate": 9.809324401485006e-06, "loss": 0.5468, "step": 150880 }, { "epoch": 0.896921494849344, "grad_norm": 6.362120151519775, "learning_rate": 9.80926764304972e-06, "loss": 0.4918, "step": 150890 }, { "epoch": 0.8969809369260124, "grad_norm": 4.464531898498535, "learning_rate": 9.8092108763323e-06, "loss": 0.5072, "step": 150900 }, { "epoch": 0.8970403790026809, "grad_norm": 4.9667487144470215, "learning_rate": 9.809154101332847e-06, "loss": 0.5357, "step": 150910 }, { "epoch": 0.8970998210793493, "grad_norm": 5.531484603881836, "learning_rate": 9.809097318051457e-06, "loss": 0.545, "step": 150920 }, { "epoch": 0.8971592631560176, "grad_norm": 4.633179187774658, "learning_rate": 9.809040526488228e-06, "loss": 0.5218, "step": 150930 }, { "epoch": 0.897218705232686, "grad_norm": 5.934075355529785, "learning_rate": 9.808983726643257e-06, "loss": 0.499, "step": 150940 }, { "epoch": 0.8972781473093544, "grad_norm": 4.93733024597168, "learning_rate": 9.80892691851664e-06, "loss": 0.5427, "step": 150950 }, { "epoch": 0.8973375893860228, "grad_norm": 5.350579261779785, "learning_rate": 9.808870102108482e-06, "loss": 0.5696, "step": 150960 }, { "epoch": 0.8973970314626912, "grad_norm": 4.828092575073242, "learning_rate": 9.808813277418871e-06, "loss": 0.5341, "step": 150970 }, { "epoch": 0.8974564735393595, "grad_norm": 5.547663688659668, "learning_rate": 9.808756444447911e-06, "loss": 0.5742, "step": 150980 }, { "epoch": 0.897515915616028, "grad_norm": 5.796342849731445, "learning_rate": 9.8086996031957e-06, "loss": 0.573, "step": 150990 }, { "epoch": 0.8975753576926964, "grad_norm": 4.607232570648193, "learning_rate": 9.808642753662335e-06, "loss": 0.534, "step": 151000 }, { "epoch": 0.8976347997693648, "grad_norm": 5.892222881317139, "learning_rate": 9.80858589584791e-06, "loss": 0.5379, "step": 151010 }, { "epoch": 0.8976942418460331, "grad_norm": 5.52708101272583, "learning_rate": 9.808529029752529e-06, "loss": 0.5217, "step": 151020 }, { "epoch": 0.8977536839227015, "grad_norm": 4.984521389007568, "learning_rate": 9.808472155376288e-06, "loss": 0.5302, "step": 151030 }, { "epoch": 0.8978131259993699, "grad_norm": 5.651052951812744, "learning_rate": 9.808415272719283e-06, "loss": 0.6138, "step": 151040 }, { "epoch": 0.8978725680760383, "grad_norm": 4.357119560241699, "learning_rate": 9.808358381781613e-06, "loss": 0.4878, "step": 151050 }, { "epoch": 0.8979320101527067, "grad_norm": 5.663274765014648, "learning_rate": 9.808301482563376e-06, "loss": 0.5221, "step": 151060 }, { "epoch": 0.897991452229375, "grad_norm": 4.338893890380859, "learning_rate": 9.80824457506467e-06, "loss": 0.562, "step": 151070 }, { "epoch": 0.8980508943060435, "grad_norm": 6.4897966384887695, "learning_rate": 9.808187659285594e-06, "loss": 0.5597, "step": 151080 }, { "epoch": 0.8981103363827119, "grad_norm": 5.713807106018066, "learning_rate": 9.808130735226244e-06, "loss": 0.5597, "step": 151090 }, { "epoch": 0.8981697784593803, "grad_norm": 5.914429664611816, "learning_rate": 9.808073802886721e-06, "loss": 0.5191, "step": 151100 }, { "epoch": 0.8982292205360487, "grad_norm": 6.599626064300537, "learning_rate": 9.80801686226712e-06, "loss": 0.5253, "step": 151110 }, { "epoch": 0.898288662612717, "grad_norm": 4.080700397491455, "learning_rate": 9.807959913367539e-06, "loss": 0.4735, "step": 151120 }, { "epoch": 0.8983481046893854, "grad_norm": 5.924915313720703, "learning_rate": 9.80790295618808e-06, "loss": 0.6103, "step": 151130 }, { "epoch": 0.8984075467660538, "grad_norm": 5.6033735275268555, "learning_rate": 9.807845990728837e-06, "loss": 0.5603, "step": 151140 }, { "epoch": 0.8984669888427222, "grad_norm": 4.896594524383545, "learning_rate": 9.80778901698991e-06, "loss": 0.5301, "step": 151150 }, { "epoch": 0.8985264309193906, "grad_norm": 5.402749538421631, "learning_rate": 9.807732034971395e-06, "loss": 0.5732, "step": 151160 }, { "epoch": 0.898585872996059, "grad_norm": 5.77551794052124, "learning_rate": 9.807675044673394e-06, "loss": 0.5468, "step": 151170 }, { "epoch": 0.8986453150727274, "grad_norm": 5.031773567199707, "learning_rate": 9.807618046096004e-06, "loss": 0.5655, "step": 151180 }, { "epoch": 0.8987047571493958, "grad_norm": 5.944486618041992, "learning_rate": 9.807561039239319e-06, "loss": 0.5626, "step": 151190 }, { "epoch": 0.8987641992260642, "grad_norm": 5.596644878387451, "learning_rate": 9.807504024103442e-06, "loss": 0.5326, "step": 151200 }, { "epoch": 0.8988236413027325, "grad_norm": 3.9220023155212402, "learning_rate": 9.807447000688469e-06, "loss": 0.5171, "step": 151210 }, { "epoch": 0.8988830833794009, "grad_norm": 4.854577541351318, "learning_rate": 9.8073899689945e-06, "loss": 0.5576, "step": 151220 }, { "epoch": 0.8989425254560693, "grad_norm": 5.287553787231445, "learning_rate": 9.80733292902163e-06, "loss": 0.5723, "step": 151230 }, { "epoch": 0.8990019675327378, "grad_norm": 5.832406997680664, "learning_rate": 9.807275880769958e-06, "loss": 0.5158, "step": 151240 }, { "epoch": 0.8990614096094061, "grad_norm": 5.595988750457764, "learning_rate": 9.807218824239585e-06, "loss": 0.5713, "step": 151250 }, { "epoch": 0.8991208516860745, "grad_norm": 5.485952854156494, "learning_rate": 9.807161759430608e-06, "loss": 0.5437, "step": 151260 }, { "epoch": 0.8991802937627429, "grad_norm": 4.671315670013428, "learning_rate": 9.807104686343124e-06, "loss": 0.606, "step": 151270 }, { "epoch": 0.8992397358394113, "grad_norm": 5.882564067840576, "learning_rate": 9.807047604977233e-06, "loss": 0.5431, "step": 151280 }, { "epoch": 0.8992991779160797, "grad_norm": 6.039010524749756, "learning_rate": 9.80699051533303e-06, "loss": 0.5848, "step": 151290 }, { "epoch": 0.899358619992748, "grad_norm": 5.13293981552124, "learning_rate": 9.806933417410617e-06, "loss": 0.582, "step": 151300 }, { "epoch": 0.8994180620694164, "grad_norm": 4.571009159088135, "learning_rate": 9.806876311210093e-06, "loss": 0.5506, "step": 151310 }, { "epoch": 0.8994775041460848, "grad_norm": 7.325878143310547, "learning_rate": 9.806819196731555e-06, "loss": 0.5804, "step": 151320 }, { "epoch": 0.8995369462227533, "grad_norm": 4.653319835662842, "learning_rate": 9.806762073975097e-06, "loss": 0.543, "step": 151330 }, { "epoch": 0.8995963882994217, "grad_norm": 5.817037105560303, "learning_rate": 9.806704942940824e-06, "loss": 0.5652, "step": 151340 }, { "epoch": 0.89965583037609, "grad_norm": 4.418299674987793, "learning_rate": 9.80664780362883e-06, "loss": 0.5266, "step": 151350 }, { "epoch": 0.8997152724527584, "grad_norm": 6.204012870788574, "learning_rate": 9.806590656039216e-06, "loss": 0.5549, "step": 151360 }, { "epoch": 0.8997747145294268, "grad_norm": 4.615514278411865, "learning_rate": 9.80653350017208e-06, "loss": 0.5479, "step": 151370 }, { "epoch": 0.8998341566060952, "grad_norm": 5.193258762359619, "learning_rate": 9.806476336027519e-06, "loss": 0.5684, "step": 151380 }, { "epoch": 0.8998935986827635, "grad_norm": 4.649117469787598, "learning_rate": 9.806419163605632e-06, "loss": 0.5677, "step": 151390 }, { "epoch": 0.8999530407594319, "grad_norm": 5.703932285308838, "learning_rate": 9.806361982906519e-06, "loss": 0.5208, "step": 151400 }, { "epoch": 0.9000124828361004, "grad_norm": 4.2617878913879395, "learning_rate": 9.806304793930275e-06, "loss": 0.5207, "step": 151410 }, { "epoch": 0.9000719249127688, "grad_norm": 5.59315299987793, "learning_rate": 9.806247596677001e-06, "loss": 0.5883, "step": 151420 }, { "epoch": 0.9001313669894372, "grad_norm": 5.520360946655273, "learning_rate": 9.806190391146797e-06, "loss": 0.5696, "step": 151430 }, { "epoch": 0.9001908090661055, "grad_norm": 6.276073455810547, "learning_rate": 9.806133177339759e-06, "loss": 0.5714, "step": 151440 }, { "epoch": 0.9002502511427739, "grad_norm": 5.614859580993652, "learning_rate": 9.806075955255985e-06, "loss": 0.5981, "step": 151450 }, { "epoch": 0.9003096932194423, "grad_norm": 5.545125961303711, "learning_rate": 9.806018724895577e-06, "loss": 0.5617, "step": 151460 }, { "epoch": 0.9003691352961107, "grad_norm": 5.348405361175537, "learning_rate": 9.805961486258629e-06, "loss": 0.6194, "step": 151470 }, { "epoch": 0.9004285773727791, "grad_norm": 6.309213638305664, "learning_rate": 9.805904239345242e-06, "loss": 0.5997, "step": 151480 }, { "epoch": 0.9004880194494475, "grad_norm": 4.760606288909912, "learning_rate": 9.805846984155516e-06, "loss": 0.5739, "step": 151490 }, { "epoch": 0.9005474615261159, "grad_norm": 5.154390811920166, "learning_rate": 9.805789720689547e-06, "loss": 0.5894, "step": 151500 }, { "epoch": 0.9006069036027843, "grad_norm": 4.6843695640563965, "learning_rate": 9.805732448947434e-06, "loss": 0.5454, "step": 151510 }, { "epoch": 0.9006663456794527, "grad_norm": 5.996720314025879, "learning_rate": 9.805675168929278e-06, "loss": 0.5217, "step": 151520 }, { "epoch": 0.900725787756121, "grad_norm": 4.78909158706665, "learning_rate": 9.805617880635176e-06, "loss": 0.5387, "step": 151530 }, { "epoch": 0.9007852298327894, "grad_norm": 3.908742904663086, "learning_rate": 9.805560584065227e-06, "loss": 0.5124, "step": 151540 }, { "epoch": 0.9008446719094578, "grad_norm": 4.792494773864746, "learning_rate": 9.805503279219526e-06, "loss": 0.5302, "step": 151550 }, { "epoch": 0.9009041139861262, "grad_norm": 6.749497413635254, "learning_rate": 9.805445966098177e-06, "loss": 0.5655, "step": 151560 }, { "epoch": 0.9009635560627947, "grad_norm": 4.500912666320801, "learning_rate": 9.805388644701277e-06, "loss": 0.4619, "step": 151570 }, { "epoch": 0.901022998139463, "grad_norm": 4.3652472496032715, "learning_rate": 9.805331315028925e-06, "loss": 0.5675, "step": 151580 }, { "epoch": 0.9010824402161314, "grad_norm": 6.626880645751953, "learning_rate": 9.805273977081218e-06, "loss": 0.5784, "step": 151590 }, { "epoch": 0.9011418822927998, "grad_norm": 7.549239158630371, "learning_rate": 9.805216630858256e-06, "loss": 0.5663, "step": 151600 }, { "epoch": 0.9012013243694682, "grad_norm": 4.890283584594727, "learning_rate": 9.805159276360137e-06, "loss": 0.5642, "step": 151610 }, { "epoch": 0.9012607664461365, "grad_norm": 5.218945503234863, "learning_rate": 9.805101913586962e-06, "loss": 0.5557, "step": 151620 }, { "epoch": 0.9013202085228049, "grad_norm": 5.750073432922363, "learning_rate": 9.805044542538827e-06, "loss": 0.5394, "step": 151630 }, { "epoch": 0.9013796505994733, "grad_norm": 5.127356052398682, "learning_rate": 9.804987163215832e-06, "loss": 0.5123, "step": 151640 }, { "epoch": 0.9014390926761418, "grad_norm": 3.6420481204986572, "learning_rate": 9.804929775618077e-06, "loss": 0.4895, "step": 151650 }, { "epoch": 0.9014985347528102, "grad_norm": 4.367786884307861, "learning_rate": 9.804872379745658e-06, "loss": 0.5588, "step": 151660 }, { "epoch": 0.9015579768294785, "grad_norm": 4.043205261230469, "learning_rate": 9.804814975598677e-06, "loss": 0.471, "step": 151670 }, { "epoch": 0.9016174189061469, "grad_norm": 4.924774646759033, "learning_rate": 9.80475756317723e-06, "loss": 0.5713, "step": 151680 }, { "epoch": 0.9016768609828153, "grad_norm": 5.068702220916748, "learning_rate": 9.804700142481417e-06, "loss": 0.5775, "step": 151690 }, { "epoch": 0.9017363030594837, "grad_norm": 6.518830299377441, "learning_rate": 9.804642713511338e-06, "loss": 0.5468, "step": 151700 }, { "epoch": 0.9017957451361521, "grad_norm": 6.492704391479492, "learning_rate": 9.804585276267092e-06, "loss": 0.5571, "step": 151710 }, { "epoch": 0.9018551872128204, "grad_norm": 6.564002513885498, "learning_rate": 9.804527830748774e-06, "loss": 0.5258, "step": 151720 }, { "epoch": 0.9019146292894888, "grad_norm": 8.523576736450195, "learning_rate": 9.804470376956487e-06, "loss": 0.5737, "step": 151730 }, { "epoch": 0.9019740713661573, "grad_norm": 5.620739936828613, "learning_rate": 9.804412914890329e-06, "loss": 0.5508, "step": 151740 }, { "epoch": 0.9020335134428257, "grad_norm": 4.025676727294922, "learning_rate": 9.8043554445504e-06, "loss": 0.5417, "step": 151750 }, { "epoch": 0.902092955519494, "grad_norm": 6.879443168640137, "learning_rate": 9.804297965936795e-06, "loss": 0.5675, "step": 151760 }, { "epoch": 0.9021523975961624, "grad_norm": 6.117177486419678, "learning_rate": 9.804240479049618e-06, "loss": 0.49, "step": 151770 }, { "epoch": 0.9022118396728308, "grad_norm": 5.281018257141113, "learning_rate": 9.804182983888966e-06, "loss": 0.5727, "step": 151780 }, { "epoch": 0.9022712817494992, "grad_norm": 6.1224212646484375, "learning_rate": 9.804125480454936e-06, "loss": 0.5264, "step": 151790 }, { "epoch": 0.9023307238261676, "grad_norm": 5.4449615478515625, "learning_rate": 9.804067968747627e-06, "loss": 0.5826, "step": 151800 }, { "epoch": 0.9023901659028359, "grad_norm": 5.346331596374512, "learning_rate": 9.804010448767143e-06, "loss": 0.5858, "step": 151810 }, { "epoch": 0.9024496079795044, "grad_norm": 5.515729904174805, "learning_rate": 9.803952920513579e-06, "loss": 0.5546, "step": 151820 }, { "epoch": 0.9025090500561728, "grad_norm": 5.719308376312256, "learning_rate": 9.803895383987034e-06, "loss": 0.625, "step": 151830 }, { "epoch": 0.9025684921328412, "grad_norm": 4.258579730987549, "learning_rate": 9.803837839187608e-06, "loss": 0.559, "step": 151840 }, { "epoch": 0.9026279342095096, "grad_norm": 7.082790374755859, "learning_rate": 9.803780286115401e-06, "loss": 0.5628, "step": 151850 }, { "epoch": 0.9026873762861779, "grad_norm": 5.43408727645874, "learning_rate": 9.803722724770512e-06, "loss": 0.5754, "step": 151860 }, { "epoch": 0.9027468183628463, "grad_norm": 6.082940101623535, "learning_rate": 9.803665155153037e-06, "loss": 0.569, "step": 151870 }, { "epoch": 0.9028062604395147, "grad_norm": 6.473887920379639, "learning_rate": 9.803607577263079e-06, "loss": 0.5611, "step": 151880 }, { "epoch": 0.9028657025161831, "grad_norm": 5.958363056182861, "learning_rate": 9.803549991100735e-06, "loss": 0.5881, "step": 151890 }, { "epoch": 0.9029251445928514, "grad_norm": 4.438996315002441, "learning_rate": 9.803492396666105e-06, "loss": 0.532, "step": 151900 }, { "epoch": 0.9029845866695199, "grad_norm": 5.156550407409668, "learning_rate": 9.803434793959287e-06, "loss": 0.5784, "step": 151910 }, { "epoch": 0.9030440287461883, "grad_norm": 4.7777485847473145, "learning_rate": 9.803377182980383e-06, "loss": 0.5816, "step": 151920 }, { "epoch": 0.9031034708228567, "grad_norm": 4.182342052459717, "learning_rate": 9.80331956372949e-06, "loss": 0.5678, "step": 151930 }, { "epoch": 0.9031629128995251, "grad_norm": 5.327591896057129, "learning_rate": 9.803261936206707e-06, "loss": 0.5769, "step": 151940 }, { "epoch": 0.9032223549761934, "grad_norm": 6.190918922424316, "learning_rate": 9.803204300412133e-06, "loss": 0.5549, "step": 151950 }, { "epoch": 0.9032817970528618, "grad_norm": 6.3464131355285645, "learning_rate": 9.803146656345868e-06, "loss": 0.5496, "step": 151960 }, { "epoch": 0.9033412391295302, "grad_norm": 4.0457444190979, "learning_rate": 9.803089004008013e-06, "loss": 0.5413, "step": 151970 }, { "epoch": 0.9034006812061987, "grad_norm": 4.463491916656494, "learning_rate": 9.803031343398665e-06, "loss": 0.5041, "step": 151980 }, { "epoch": 0.903460123282867, "grad_norm": 4.625268936157227, "learning_rate": 9.802973674517923e-06, "loss": 0.61, "step": 151990 }, { "epoch": 0.9035195653595354, "grad_norm": 3.5912668704986572, "learning_rate": 9.80291599736589e-06, "loss": 0.4765, "step": 152000 }, { "epoch": 0.9035790074362038, "grad_norm": 4.784034252166748, "learning_rate": 9.80285831194266e-06, "loss": 0.5465, "step": 152010 }, { "epoch": 0.9036384495128722, "grad_norm": 5.54799747467041, "learning_rate": 9.802800618248336e-06, "loss": 0.5581, "step": 152020 }, { "epoch": 0.9036978915895406, "grad_norm": 5.189938068389893, "learning_rate": 9.802742916283015e-06, "loss": 0.5338, "step": 152030 }, { "epoch": 0.9037573336662089, "grad_norm": 6.805205821990967, "learning_rate": 9.802685206046798e-06, "loss": 0.5763, "step": 152040 }, { "epoch": 0.9038167757428773, "grad_norm": 5.841213226318359, "learning_rate": 9.802627487539785e-06, "loss": 0.5886, "step": 152050 }, { "epoch": 0.9038762178195457, "grad_norm": 5.986044406890869, "learning_rate": 9.802569760762073e-06, "loss": 0.5208, "step": 152060 }, { "epoch": 0.9039356598962142, "grad_norm": 4.980932235717773, "learning_rate": 9.802512025713765e-06, "loss": 0.5721, "step": 152070 }, { "epoch": 0.9039951019728826, "grad_norm": 5.094608306884766, "learning_rate": 9.802454282394956e-06, "loss": 0.5186, "step": 152080 }, { "epoch": 0.9040545440495509, "grad_norm": 6.450168132781982, "learning_rate": 9.80239653080575e-06, "loss": 0.5583, "step": 152090 }, { "epoch": 0.9041139861262193, "grad_norm": 5.059006214141846, "learning_rate": 9.802338770946242e-06, "loss": 0.5804, "step": 152100 }, { "epoch": 0.9041734282028877, "grad_norm": 6.240843296051025, "learning_rate": 9.802281002816534e-06, "loss": 0.5024, "step": 152110 }, { "epoch": 0.9042328702795561, "grad_norm": 4.541959285736084, "learning_rate": 9.802223226416727e-06, "loss": 0.568, "step": 152120 }, { "epoch": 0.9042923123562244, "grad_norm": 4.721518039703369, "learning_rate": 9.802165441746916e-06, "loss": 0.5585, "step": 152130 }, { "epoch": 0.9043517544328928, "grad_norm": 4.2135396003723145, "learning_rate": 9.802107648807205e-06, "loss": 0.5733, "step": 152140 }, { "epoch": 0.9044111965095613, "grad_norm": 5.046696662902832, "learning_rate": 9.80204984759769e-06, "loss": 0.593, "step": 152150 }, { "epoch": 0.9044706385862297, "grad_norm": 5.342343807220459, "learning_rate": 9.801992038118473e-06, "loss": 0.5091, "step": 152160 }, { "epoch": 0.9045300806628981, "grad_norm": 4.336856365203857, "learning_rate": 9.801934220369653e-06, "loss": 0.491, "step": 152170 }, { "epoch": 0.9045895227395664, "grad_norm": 6.131468296051025, "learning_rate": 9.801876394351331e-06, "loss": 0.5362, "step": 152180 }, { "epoch": 0.9046489648162348, "grad_norm": 5.934706687927246, "learning_rate": 9.801818560063603e-06, "loss": 0.4776, "step": 152190 }, { "epoch": 0.9047084068929032, "grad_norm": 6.873320579528809, "learning_rate": 9.80176071750657e-06, "loss": 0.5215, "step": 152200 }, { "epoch": 0.9047678489695716, "grad_norm": 6.870969772338867, "learning_rate": 9.801702866680332e-06, "loss": 0.6057, "step": 152210 }, { "epoch": 0.90482729104624, "grad_norm": 5.575634479522705, "learning_rate": 9.80164500758499e-06, "loss": 0.5665, "step": 152220 }, { "epoch": 0.9048867331229083, "grad_norm": 6.6903581619262695, "learning_rate": 9.801587140220642e-06, "loss": 0.5824, "step": 152230 }, { "epoch": 0.9049461751995768, "grad_norm": 5.2758002281188965, "learning_rate": 9.801529264587389e-06, "loss": 0.5002, "step": 152240 }, { "epoch": 0.9050056172762452, "grad_norm": 3.6973888874053955, "learning_rate": 9.801471380685328e-06, "loss": 0.5993, "step": 152250 }, { "epoch": 0.9050650593529136, "grad_norm": 3.8171565532684326, "learning_rate": 9.801413488514561e-06, "loss": 0.5141, "step": 152260 }, { "epoch": 0.9051245014295819, "grad_norm": 4.475920677185059, "learning_rate": 9.801355588075186e-06, "loss": 0.5568, "step": 152270 }, { "epoch": 0.9051839435062503, "grad_norm": 5.882094860076904, "learning_rate": 9.801297679367306e-06, "loss": 0.5791, "step": 152280 }, { "epoch": 0.9052433855829187, "grad_norm": 4.681731700897217, "learning_rate": 9.801239762391017e-06, "loss": 0.6019, "step": 152290 }, { "epoch": 0.9053028276595871, "grad_norm": 5.339008808135986, "learning_rate": 9.801181837146421e-06, "loss": 0.5653, "step": 152300 }, { "epoch": 0.9053622697362556, "grad_norm": 5.0027666091918945, "learning_rate": 9.801123903633616e-06, "loss": 0.5209, "step": 152310 }, { "epoch": 0.9054217118129239, "grad_norm": 5.660977840423584, "learning_rate": 9.801065961852703e-06, "loss": 0.5258, "step": 152320 }, { "epoch": 0.9054811538895923, "grad_norm": 4.586493015289307, "learning_rate": 9.801008011803784e-06, "loss": 0.5363, "step": 152330 }, { "epoch": 0.9055405959662607, "grad_norm": 4.269877910614014, "learning_rate": 9.800950053486952e-06, "loss": 0.5188, "step": 152340 }, { "epoch": 0.9056000380429291, "grad_norm": 5.395516872406006, "learning_rate": 9.800892086902314e-06, "loss": 0.5461, "step": 152350 }, { "epoch": 0.9056594801195974, "grad_norm": 6.292414665222168, "learning_rate": 9.800834112049966e-06, "loss": 0.6424, "step": 152360 }, { "epoch": 0.9057189221962658, "grad_norm": 6.017983436584473, "learning_rate": 9.80077612893001e-06, "loss": 0.6133, "step": 152370 }, { "epoch": 0.9057783642729342, "grad_norm": 3.487700939178467, "learning_rate": 9.800718137542545e-06, "loss": 0.5562, "step": 152380 }, { "epoch": 0.9058378063496026, "grad_norm": 7.024343013763428, "learning_rate": 9.800660137887668e-06, "loss": 0.5625, "step": 152390 }, { "epoch": 0.9058972484262711, "grad_norm": 4.331881046295166, "learning_rate": 9.800602129965484e-06, "loss": 0.5573, "step": 152400 }, { "epoch": 0.9059566905029394, "grad_norm": 7.465022087097168, "learning_rate": 9.800544113776089e-06, "loss": 0.5809, "step": 152410 }, { "epoch": 0.9060161325796078, "grad_norm": 4.702131271362305, "learning_rate": 9.800486089319584e-06, "loss": 0.5826, "step": 152420 }, { "epoch": 0.9060755746562762, "grad_norm": 5.765346527099609, "learning_rate": 9.80042805659607e-06, "loss": 0.5105, "step": 152430 }, { "epoch": 0.9061350167329446, "grad_norm": 6.085493087768555, "learning_rate": 9.800370015605645e-06, "loss": 0.548, "step": 152440 }, { "epoch": 0.906194458809613, "grad_norm": 5.251640796661377, "learning_rate": 9.800311966348412e-06, "loss": 0.5641, "step": 152450 }, { "epoch": 0.9062539008862813, "grad_norm": 6.671815872192383, "learning_rate": 9.800253908824468e-06, "loss": 0.5461, "step": 152460 }, { "epoch": 0.9063133429629497, "grad_norm": 5.310115337371826, "learning_rate": 9.800195843033914e-06, "loss": 0.5426, "step": 152470 }, { "epoch": 0.9063727850396182, "grad_norm": 4.575645923614502, "learning_rate": 9.80013776897685e-06, "loss": 0.5291, "step": 152480 }, { "epoch": 0.9064322271162866, "grad_norm": 5.8782548904418945, "learning_rate": 9.800079686653375e-06, "loss": 0.556, "step": 152490 }, { "epoch": 0.9064916691929549, "grad_norm": 5.739622116088867, "learning_rate": 9.800021596063592e-06, "loss": 0.5785, "step": 152500 }, { "epoch": 0.9065511112696233, "grad_norm": 5.378220558166504, "learning_rate": 9.799963497207598e-06, "loss": 0.5274, "step": 152510 }, { "epoch": 0.9066105533462917, "grad_norm": 5.888133525848389, "learning_rate": 9.799905390085494e-06, "loss": 0.5416, "step": 152520 }, { "epoch": 0.9066699954229601, "grad_norm": 4.856215000152588, "learning_rate": 9.79984727469738e-06, "loss": 0.5522, "step": 152530 }, { "epoch": 0.9067294374996285, "grad_norm": 6.768131256103516, "learning_rate": 9.799789151043358e-06, "loss": 0.5565, "step": 152540 }, { "epoch": 0.9067888795762968, "grad_norm": 4.071508884429932, "learning_rate": 9.799731019123524e-06, "loss": 0.512, "step": 152550 }, { "epoch": 0.9068483216529653, "grad_norm": 5.96903657913208, "learning_rate": 9.799672878937982e-06, "loss": 0.5259, "step": 152560 }, { "epoch": 0.9069077637296337, "grad_norm": 5.111140251159668, "learning_rate": 9.799614730486831e-06, "loss": 0.5201, "step": 152570 }, { "epoch": 0.9069672058063021, "grad_norm": 4.161737442016602, "learning_rate": 9.799556573770169e-06, "loss": 0.5055, "step": 152580 }, { "epoch": 0.9070266478829705, "grad_norm": 5.344963073730469, "learning_rate": 9.7994984087881e-06, "loss": 0.4942, "step": 152590 }, { "epoch": 0.9070860899596388, "grad_norm": 5.661318302154541, "learning_rate": 9.79944023554072e-06, "loss": 0.5677, "step": 152600 }, { "epoch": 0.9071455320363072, "grad_norm": 4.932550430297852, "learning_rate": 9.799382054028133e-06, "loss": 0.5304, "step": 152610 }, { "epoch": 0.9072049741129756, "grad_norm": 5.111485004425049, "learning_rate": 9.799323864250436e-06, "loss": 0.5158, "step": 152620 }, { "epoch": 0.907264416189644, "grad_norm": 5.313878059387207, "learning_rate": 9.79926566620773e-06, "loss": 0.5474, "step": 152630 }, { "epoch": 0.9073238582663123, "grad_norm": 4.295982360839844, "learning_rate": 9.799207459900117e-06, "loss": 0.547, "step": 152640 }, { "epoch": 0.9073833003429808, "grad_norm": 6.300440311431885, "learning_rate": 9.799149245327697e-06, "loss": 0.4678, "step": 152650 }, { "epoch": 0.9074427424196492, "grad_norm": 7.669718265533447, "learning_rate": 9.799091022490569e-06, "loss": 0.6174, "step": 152660 }, { "epoch": 0.9075021844963176, "grad_norm": 5.023245334625244, "learning_rate": 9.799032791388834e-06, "loss": 0.5354, "step": 152670 }, { "epoch": 0.907561626572986, "grad_norm": 5.3720808029174805, "learning_rate": 9.798974552022591e-06, "loss": 0.5509, "step": 152680 }, { "epoch": 0.9076210686496543, "grad_norm": 5.382167339324951, "learning_rate": 9.798916304391941e-06, "loss": 0.5048, "step": 152690 }, { "epoch": 0.9076805107263227, "grad_norm": 4.84277868270874, "learning_rate": 9.798858048496985e-06, "loss": 0.5124, "step": 152700 }, { "epoch": 0.9077399528029911, "grad_norm": 6.64228630065918, "learning_rate": 9.798799784337822e-06, "loss": 0.5401, "step": 152710 }, { "epoch": 0.9077993948796595, "grad_norm": 4.72766637802124, "learning_rate": 9.798741511914555e-06, "loss": 0.4844, "step": 152720 }, { "epoch": 0.9078588369563279, "grad_norm": 4.8849992752075195, "learning_rate": 9.798683231227282e-06, "loss": 0.5325, "step": 152730 }, { "epoch": 0.9079182790329963, "grad_norm": 4.554732322692871, "learning_rate": 9.798624942276102e-06, "loss": 0.4833, "step": 152740 }, { "epoch": 0.9079777211096647, "grad_norm": 5.3213725090026855, "learning_rate": 9.79856664506112e-06, "loss": 0.5175, "step": 152750 }, { "epoch": 0.9080371631863331, "grad_norm": 5.075101852416992, "learning_rate": 9.798508339582432e-06, "loss": 0.5245, "step": 152760 }, { "epoch": 0.9080966052630015, "grad_norm": 4.008822917938232, "learning_rate": 9.79845002584014e-06, "loss": 0.5364, "step": 152770 }, { "epoch": 0.9081560473396698, "grad_norm": 5.3947672843933105, "learning_rate": 9.798391703834346e-06, "loss": 0.558, "step": 152780 }, { "epoch": 0.9082154894163382, "grad_norm": 4.5510945320129395, "learning_rate": 9.798333373565148e-06, "loss": 0.5169, "step": 152790 }, { "epoch": 0.9082749314930066, "grad_norm": 6.208351135253906, "learning_rate": 9.798275035032646e-06, "loss": 0.5481, "step": 152800 }, { "epoch": 0.9083343735696751, "grad_norm": 3.7165582180023193, "learning_rate": 9.798216688236944e-06, "loss": 0.4893, "step": 152810 }, { "epoch": 0.9083938156463435, "grad_norm": 4.974275588989258, "learning_rate": 9.79815833317814e-06, "loss": 0.5677, "step": 152820 }, { "epoch": 0.9084532577230118, "grad_norm": 4.324452877044678, "learning_rate": 9.798099969856334e-06, "loss": 0.4719, "step": 152830 }, { "epoch": 0.9085126997996802, "grad_norm": 4.9125494956970215, "learning_rate": 9.798041598271628e-06, "loss": 0.5718, "step": 152840 }, { "epoch": 0.9085721418763486, "grad_norm": 4.368024826049805, "learning_rate": 9.797983218424122e-06, "loss": 0.4984, "step": 152850 }, { "epoch": 0.908631583953017, "grad_norm": 6.008042335510254, "learning_rate": 9.797924830313917e-06, "loss": 0.5616, "step": 152860 }, { "epoch": 0.9086910260296853, "grad_norm": 4.3494462966918945, "learning_rate": 9.797866433941112e-06, "loss": 0.5638, "step": 152870 }, { "epoch": 0.9087504681063537, "grad_norm": 4.756183624267578, "learning_rate": 9.797808029305808e-06, "loss": 0.5288, "step": 152880 }, { "epoch": 0.9088099101830222, "grad_norm": 5.069556713104248, "learning_rate": 9.797749616408107e-06, "loss": 0.539, "step": 152890 }, { "epoch": 0.9088693522596906, "grad_norm": 5.681711673736572, "learning_rate": 9.797691195248108e-06, "loss": 0.6097, "step": 152900 }, { "epoch": 0.908928794336359, "grad_norm": 5.401992321014404, "learning_rate": 9.797632765825913e-06, "loss": 0.5368, "step": 152910 }, { "epoch": 0.9089882364130273, "grad_norm": 5.426665782928467, "learning_rate": 9.79757432814162e-06, "loss": 0.5757, "step": 152920 }, { "epoch": 0.9090476784896957, "grad_norm": 4.633518695831299, "learning_rate": 9.797515882195335e-06, "loss": 0.5523, "step": 152930 }, { "epoch": 0.9091071205663641, "grad_norm": 6.3867926597595215, "learning_rate": 9.797457427987154e-06, "loss": 0.5715, "step": 152940 }, { "epoch": 0.9091665626430325, "grad_norm": 6.41160774230957, "learning_rate": 9.797398965517178e-06, "loss": 0.5855, "step": 152950 }, { "epoch": 0.9092260047197009, "grad_norm": 4.504526138305664, "learning_rate": 9.797340494785507e-06, "loss": 0.5553, "step": 152960 }, { "epoch": 0.9092854467963692, "grad_norm": 3.963999032974243, "learning_rate": 9.797282015792246e-06, "loss": 0.537, "step": 152970 }, { "epoch": 0.9093448888730377, "grad_norm": 4.3607330322265625, "learning_rate": 9.797223528537491e-06, "loss": 0.5137, "step": 152980 }, { "epoch": 0.9094043309497061, "grad_norm": 5.073071479797363, "learning_rate": 9.797165033021348e-06, "loss": 0.5299, "step": 152990 }, { "epoch": 0.9094637730263745, "grad_norm": 5.313183784484863, "learning_rate": 9.797106529243912e-06, "loss": 0.5704, "step": 153000 }, { "epoch": 0.9095232151030428, "grad_norm": 5.157062530517578, "learning_rate": 9.797048017205286e-06, "loss": 0.5092, "step": 153010 }, { "epoch": 0.9095826571797112, "grad_norm": 5.1217732429504395, "learning_rate": 9.796989496905571e-06, "loss": 0.5649, "step": 153020 }, { "epoch": 0.9096420992563796, "grad_norm": 5.133478164672852, "learning_rate": 9.796930968344868e-06, "loss": 0.5424, "step": 153030 }, { "epoch": 0.909701541333048, "grad_norm": 6.5465898513793945, "learning_rate": 9.796872431523277e-06, "loss": 0.544, "step": 153040 }, { "epoch": 0.9097609834097165, "grad_norm": 4.681596279144287, "learning_rate": 9.7968138864409e-06, "loss": 0.5547, "step": 153050 }, { "epoch": 0.9098204254863848, "grad_norm": 5.619202613830566, "learning_rate": 9.796755333097839e-06, "loss": 0.5631, "step": 153060 }, { "epoch": 0.9098798675630532, "grad_norm": 5.602602005004883, "learning_rate": 9.79669677149419e-06, "loss": 0.5404, "step": 153070 }, { "epoch": 0.9099393096397216, "grad_norm": 7.8090362548828125, "learning_rate": 9.796638201630058e-06, "loss": 0.5884, "step": 153080 }, { "epoch": 0.90999875171639, "grad_norm": 5.836178779602051, "learning_rate": 9.796579623505543e-06, "loss": 0.5494, "step": 153090 }, { "epoch": 0.9100581937930583, "grad_norm": 5.781849384307861, "learning_rate": 9.796521037120744e-06, "loss": 0.5564, "step": 153100 }, { "epoch": 0.9101176358697267, "grad_norm": 5.568938732147217, "learning_rate": 9.796462442475764e-06, "loss": 0.53, "step": 153110 }, { "epoch": 0.9101770779463951, "grad_norm": 6.904991149902344, "learning_rate": 9.796403839570705e-06, "loss": 0.517, "step": 153120 }, { "epoch": 0.9102365200230635, "grad_norm": 3.753251791000366, "learning_rate": 9.796345228405664e-06, "loss": 0.5196, "step": 153130 }, { "epoch": 0.910295962099732, "grad_norm": 6.7459893226623535, "learning_rate": 9.796286608980746e-06, "loss": 0.513, "step": 153140 }, { "epoch": 0.9103554041764003, "grad_norm": 3.6860389709472656, "learning_rate": 9.79622798129605e-06, "loss": 0.5353, "step": 153150 }, { "epoch": 0.9104148462530687, "grad_norm": 6.188278675079346, "learning_rate": 9.796169345351677e-06, "loss": 0.5753, "step": 153160 }, { "epoch": 0.9104742883297371, "grad_norm": 4.5954270362854, "learning_rate": 9.796110701147727e-06, "loss": 0.5614, "step": 153170 }, { "epoch": 0.9105337304064055, "grad_norm": 6.724665641784668, "learning_rate": 9.796052048684304e-06, "loss": 0.5904, "step": 153180 }, { "epoch": 0.9105931724830739, "grad_norm": 4.618716716766357, "learning_rate": 9.795993387961507e-06, "loss": 0.5771, "step": 153190 }, { "epoch": 0.9106526145597422, "grad_norm": 5.341822624206543, "learning_rate": 9.795934718979435e-06, "loss": 0.525, "step": 153200 }, { "epoch": 0.9107120566364106, "grad_norm": 5.686802864074707, "learning_rate": 9.795876041738192e-06, "loss": 0.5357, "step": 153210 }, { "epoch": 0.910771498713079, "grad_norm": 5.110594272613525, "learning_rate": 9.795817356237878e-06, "loss": 0.4989, "step": 153220 }, { "epoch": 0.9108309407897475, "grad_norm": 6.051837921142578, "learning_rate": 9.795758662478595e-06, "loss": 0.498, "step": 153230 }, { "epoch": 0.9108903828664158, "grad_norm": 6.347487449645996, "learning_rate": 9.795699960460445e-06, "loss": 0.5919, "step": 153240 }, { "epoch": 0.9109498249430842, "grad_norm": 4.751217365264893, "learning_rate": 9.795641250183526e-06, "loss": 0.5294, "step": 153250 }, { "epoch": 0.9110092670197526, "grad_norm": 4.876871585845947, "learning_rate": 9.79558253164794e-06, "loss": 0.5085, "step": 153260 }, { "epoch": 0.911068709096421, "grad_norm": 4.771887302398682, "learning_rate": 9.795523804853789e-06, "loss": 0.5468, "step": 153270 }, { "epoch": 0.9111281511730894, "grad_norm": 5.547818183898926, "learning_rate": 9.795465069801174e-06, "loss": 0.5422, "step": 153280 }, { "epoch": 0.9111875932497577, "grad_norm": 3.841181755065918, "learning_rate": 9.795406326490195e-06, "loss": 0.5356, "step": 153290 }, { "epoch": 0.9112470353264261, "grad_norm": 5.694373607635498, "learning_rate": 9.795347574920954e-06, "loss": 0.5481, "step": 153300 }, { "epoch": 0.9113064774030946, "grad_norm": 6.171507835388184, "learning_rate": 9.795288815093554e-06, "loss": 0.5614, "step": 153310 }, { "epoch": 0.911365919479763, "grad_norm": 4.0125956535339355, "learning_rate": 9.795230047008093e-06, "loss": 0.535, "step": 153320 }, { "epoch": 0.9114253615564314, "grad_norm": 5.663427829742432, "learning_rate": 9.795171270664675e-06, "loss": 0.5139, "step": 153330 }, { "epoch": 0.9114848036330997, "grad_norm": 4.29884147644043, "learning_rate": 9.795112486063399e-06, "loss": 0.5986, "step": 153340 }, { "epoch": 0.9115442457097681, "grad_norm": 3.7225446701049805, "learning_rate": 9.795053693204368e-06, "loss": 0.5423, "step": 153350 }, { "epoch": 0.9116036877864365, "grad_norm": 3.961092710494995, "learning_rate": 9.794994892087682e-06, "loss": 0.5811, "step": 153360 }, { "epoch": 0.9116631298631049, "grad_norm": 7.061392784118652, "learning_rate": 9.794936082713442e-06, "loss": 0.4864, "step": 153370 }, { "epoch": 0.9117225719397732, "grad_norm": 5.6477251052856445, "learning_rate": 9.79487726508175e-06, "loss": 0.5486, "step": 153380 }, { "epoch": 0.9117820140164417, "grad_norm": 5.126380443572998, "learning_rate": 9.794818439192708e-06, "loss": 0.5289, "step": 153390 }, { "epoch": 0.9118414560931101, "grad_norm": 5.237285137176514, "learning_rate": 9.794759605046416e-06, "loss": 0.4877, "step": 153400 }, { "epoch": 0.9119008981697785, "grad_norm": 5.342039108276367, "learning_rate": 9.794700762642976e-06, "loss": 0.5095, "step": 153410 }, { "epoch": 0.9119603402464469, "grad_norm": 5.331326961517334, "learning_rate": 9.79464191198249e-06, "loss": 0.5388, "step": 153420 }, { "epoch": 0.9120197823231152, "grad_norm": 5.4571309089660645, "learning_rate": 9.794583053065059e-06, "loss": 0.5778, "step": 153430 }, { "epoch": 0.9120792243997836, "grad_norm": 7.02392053604126, "learning_rate": 9.794524185890782e-06, "loss": 0.5661, "step": 153440 }, { "epoch": 0.912138666476452, "grad_norm": 5.32477331161499, "learning_rate": 9.794465310459762e-06, "loss": 0.5585, "step": 153450 }, { "epoch": 0.9121981085531204, "grad_norm": 5.353257656097412, "learning_rate": 9.794406426772103e-06, "loss": 0.5349, "step": 153460 }, { "epoch": 0.9122575506297887, "grad_norm": 5.999858379364014, "learning_rate": 9.794347534827901e-06, "loss": 0.5917, "step": 153470 }, { "epoch": 0.9123169927064572, "grad_norm": 6.92247200012207, "learning_rate": 9.794288634627263e-06, "loss": 0.6066, "step": 153480 }, { "epoch": 0.9123764347831256, "grad_norm": 5.375573635101318, "learning_rate": 9.794229726170288e-06, "loss": 0.5947, "step": 153490 }, { "epoch": 0.912435876859794, "grad_norm": 6.621278285980225, "learning_rate": 9.794170809457076e-06, "loss": 0.5145, "step": 153500 }, { "epoch": 0.9124953189364624, "grad_norm": 5.404041290283203, "learning_rate": 9.794111884487731e-06, "loss": 0.5738, "step": 153510 }, { "epoch": 0.9125547610131307, "grad_norm": 5.417558193206787, "learning_rate": 9.794052951262352e-06, "loss": 0.5144, "step": 153520 }, { "epoch": 0.9126142030897991, "grad_norm": 4.895094871520996, "learning_rate": 9.793994009781042e-06, "loss": 0.5081, "step": 153530 }, { "epoch": 0.9126736451664675, "grad_norm": 5.22170877456665, "learning_rate": 9.793935060043904e-06, "loss": 0.4935, "step": 153540 }, { "epoch": 0.912733087243136, "grad_norm": 5.674210548400879, "learning_rate": 9.793876102051037e-06, "loss": 0.5465, "step": 153550 }, { "epoch": 0.9127925293198044, "grad_norm": 4.637469291687012, "learning_rate": 9.793817135802542e-06, "loss": 0.5014, "step": 153560 }, { "epoch": 0.9128519713964727, "grad_norm": 4.813833236694336, "learning_rate": 9.793758161298524e-06, "loss": 0.5565, "step": 153570 }, { "epoch": 0.9129114134731411, "grad_norm": 4.640462398529053, "learning_rate": 9.79369917853908e-06, "loss": 0.5648, "step": 153580 }, { "epoch": 0.9129708555498095, "grad_norm": 7.827014446258545, "learning_rate": 9.793640187524316e-06, "loss": 0.5684, "step": 153590 }, { "epoch": 0.9130302976264779, "grad_norm": 4.244923114776611, "learning_rate": 9.793581188254331e-06, "loss": 0.5364, "step": 153600 }, { "epoch": 0.9130897397031462, "grad_norm": 4.397096633911133, "learning_rate": 9.793522180729227e-06, "loss": 0.4946, "step": 153610 }, { "epoch": 0.9131491817798146, "grad_norm": 5.664374351501465, "learning_rate": 9.793463164949106e-06, "loss": 0.5317, "step": 153620 }, { "epoch": 0.913208623856483, "grad_norm": 5.642665863037109, "learning_rate": 9.79340414091407e-06, "loss": 0.5632, "step": 153630 }, { "epoch": 0.9132680659331515, "grad_norm": 6.205702781677246, "learning_rate": 9.79334510862422e-06, "loss": 0.4932, "step": 153640 }, { "epoch": 0.9133275080098199, "grad_norm": 5.296565532684326, "learning_rate": 9.793286068079656e-06, "loss": 0.5635, "step": 153650 }, { "epoch": 0.9133869500864882, "grad_norm": 4.372284412384033, "learning_rate": 9.793227019280484e-06, "loss": 0.5822, "step": 153660 }, { "epoch": 0.9134463921631566, "grad_norm": 5.931901931762695, "learning_rate": 9.793167962226802e-06, "loss": 0.5641, "step": 153670 }, { "epoch": 0.913505834239825, "grad_norm": 5.006103038787842, "learning_rate": 9.793108896918714e-06, "loss": 0.5372, "step": 153680 }, { "epoch": 0.9135652763164934, "grad_norm": 4.780394554138184, "learning_rate": 9.793049823356318e-06, "loss": 0.5512, "step": 153690 }, { "epoch": 0.9136247183931618, "grad_norm": 6.579757213592529, "learning_rate": 9.79299074153972e-06, "loss": 0.5289, "step": 153700 }, { "epoch": 0.9136841604698301, "grad_norm": 5.026787281036377, "learning_rate": 9.79293165146902e-06, "loss": 0.5229, "step": 153710 }, { "epoch": 0.9137436025464986, "grad_norm": 4.20314359664917, "learning_rate": 9.79287255314432e-06, "loss": 0.5216, "step": 153720 }, { "epoch": 0.913803044623167, "grad_norm": 4.677957534790039, "learning_rate": 9.792813446565722e-06, "loss": 0.5544, "step": 153730 }, { "epoch": 0.9138624866998354, "grad_norm": 5.870119571685791, "learning_rate": 9.792754331733327e-06, "loss": 0.5506, "step": 153740 }, { "epoch": 0.9139219287765037, "grad_norm": 5.493557929992676, "learning_rate": 9.792695208647235e-06, "loss": 0.5661, "step": 153750 }, { "epoch": 0.9139813708531721, "grad_norm": 6.531311511993408, "learning_rate": 9.792636077307554e-06, "loss": 0.5646, "step": 153760 }, { "epoch": 0.9140408129298405, "grad_norm": 5.253365516662598, "learning_rate": 9.79257693771438e-06, "loss": 0.5614, "step": 153770 }, { "epoch": 0.9141002550065089, "grad_norm": 5.269918441772461, "learning_rate": 9.792517789867815e-06, "loss": 0.5737, "step": 153780 }, { "epoch": 0.9141596970831773, "grad_norm": 5.287973403930664, "learning_rate": 9.792458633767966e-06, "loss": 0.489, "step": 153790 }, { "epoch": 0.9142191391598457, "grad_norm": 5.991862773895264, "learning_rate": 9.792399469414928e-06, "loss": 0.5615, "step": 153800 }, { "epoch": 0.9142785812365141, "grad_norm": 4.44514799118042, "learning_rate": 9.792340296808807e-06, "loss": 0.4938, "step": 153810 }, { "epoch": 0.9143380233131825, "grad_norm": 5.691298961639404, "learning_rate": 9.792281115949704e-06, "loss": 0.5362, "step": 153820 }, { "epoch": 0.9143974653898509, "grad_norm": 5.512846946716309, "learning_rate": 9.792221926837723e-06, "loss": 0.554, "step": 153830 }, { "epoch": 0.9144569074665192, "grad_norm": 6.054573059082031, "learning_rate": 9.792162729472962e-06, "loss": 0.5202, "step": 153840 }, { "epoch": 0.9145163495431876, "grad_norm": 4.819584369659424, "learning_rate": 9.792103523855528e-06, "loss": 0.5162, "step": 153850 }, { "epoch": 0.914575791619856, "grad_norm": 5.286035060882568, "learning_rate": 9.792044309985516e-06, "loss": 0.4983, "step": 153860 }, { "epoch": 0.9146352336965244, "grad_norm": 5.363562107086182, "learning_rate": 9.791985087863034e-06, "loss": 0.5399, "step": 153870 }, { "epoch": 0.9146946757731929, "grad_norm": 4.810680866241455, "learning_rate": 9.791925857488182e-06, "loss": 0.5382, "step": 153880 }, { "epoch": 0.9147541178498612, "grad_norm": 4.458757400512695, "learning_rate": 9.79186661886106e-06, "loss": 0.5618, "step": 153890 }, { "epoch": 0.9148135599265296, "grad_norm": 4.145017147064209, "learning_rate": 9.791807371981777e-06, "loss": 0.5334, "step": 153900 }, { "epoch": 0.914873002003198, "grad_norm": 4.809042930603027, "learning_rate": 9.791748116850426e-06, "loss": 0.551, "step": 153910 }, { "epoch": 0.9149324440798664, "grad_norm": 5.52305793762207, "learning_rate": 9.791688853467111e-06, "loss": 0.5667, "step": 153920 }, { "epoch": 0.9149918861565348, "grad_norm": 5.274203777313232, "learning_rate": 9.791629581831941e-06, "loss": 0.5595, "step": 153930 }, { "epoch": 0.9150513282332031, "grad_norm": 6.719152450561523, "learning_rate": 9.79157030194501e-06, "loss": 0.5343, "step": 153940 }, { "epoch": 0.9151107703098715, "grad_norm": 5.5044474601745605, "learning_rate": 9.791511013806425e-06, "loss": 0.5535, "step": 153950 }, { "epoch": 0.91517021238654, "grad_norm": 4.642958164215088, "learning_rate": 9.791451717416285e-06, "loss": 0.5254, "step": 153960 }, { "epoch": 0.9152296544632084, "grad_norm": 4.731935977935791, "learning_rate": 9.791392412774692e-06, "loss": 0.5015, "step": 153970 }, { "epoch": 0.9152890965398767, "grad_norm": 5.0260820388793945, "learning_rate": 9.791333099881752e-06, "loss": 0.5223, "step": 153980 }, { "epoch": 0.9153485386165451, "grad_norm": 4.793334484100342, "learning_rate": 9.791273778737565e-06, "loss": 0.535, "step": 153990 }, { "epoch": 0.9154079806932135, "grad_norm": 6.014333724975586, "learning_rate": 9.79121444934223e-06, "loss": 0.546, "step": 154000 }, { "epoch": 0.9154674227698819, "grad_norm": 8.379653930664062, "learning_rate": 9.791155111695855e-06, "loss": 0.5845, "step": 154010 }, { "epoch": 0.9155268648465503, "grad_norm": 5.297939300537109, "learning_rate": 9.791095765798537e-06, "loss": 0.5133, "step": 154020 }, { "epoch": 0.9155863069232186, "grad_norm": 6.050172328948975, "learning_rate": 9.791036411650382e-06, "loss": 0.58, "step": 154030 }, { "epoch": 0.915645748999887, "grad_norm": 5.237155914306641, "learning_rate": 9.790977049251492e-06, "loss": 0.5371, "step": 154040 }, { "epoch": 0.9157051910765555, "grad_norm": 4.778243064880371, "learning_rate": 9.790917678601965e-06, "loss": 0.5158, "step": 154050 }, { "epoch": 0.9157646331532239, "grad_norm": 5.669491767883301, "learning_rate": 9.790858299701907e-06, "loss": 0.5575, "step": 154060 }, { "epoch": 0.9158240752298922, "grad_norm": 4.485523223876953, "learning_rate": 9.790798912551419e-06, "loss": 0.5608, "step": 154070 }, { "epoch": 0.9158835173065606, "grad_norm": 4.732245445251465, "learning_rate": 9.790739517150605e-06, "loss": 0.5135, "step": 154080 }, { "epoch": 0.915942959383229, "grad_norm": 4.414743423461914, "learning_rate": 9.790680113499565e-06, "loss": 0.5627, "step": 154090 }, { "epoch": 0.9160024014598974, "grad_norm": 5.1318440437316895, "learning_rate": 9.7906207015984e-06, "loss": 0.4958, "step": 154100 }, { "epoch": 0.9160618435365658, "grad_norm": 5.9374098777771, "learning_rate": 9.790561281447218e-06, "loss": 0.5676, "step": 154110 }, { "epoch": 0.9161212856132341, "grad_norm": 6.437150955200195, "learning_rate": 9.790501853046117e-06, "loss": 0.5453, "step": 154120 }, { "epoch": 0.9161807276899026, "grad_norm": 5.100123405456543, "learning_rate": 9.7904424163952e-06, "loss": 0.5581, "step": 154130 }, { "epoch": 0.916240169766571, "grad_norm": 6.32744836807251, "learning_rate": 9.79038297149457e-06, "loss": 0.5567, "step": 154140 }, { "epoch": 0.9162996118432394, "grad_norm": 5.96811580657959, "learning_rate": 9.790323518344329e-06, "loss": 0.5156, "step": 154150 }, { "epoch": 0.9163590539199078, "grad_norm": 5.1918182373046875, "learning_rate": 9.790264056944578e-06, "loss": 0.5349, "step": 154160 }, { "epoch": 0.9164184959965761, "grad_norm": 5.4013991355896, "learning_rate": 9.790204587295423e-06, "loss": 0.5279, "step": 154170 }, { "epoch": 0.9164779380732445, "grad_norm": 3.8899238109588623, "learning_rate": 9.790145109396961e-06, "loss": 0.4792, "step": 154180 }, { "epoch": 0.9165373801499129, "grad_norm": 6.764660835266113, "learning_rate": 9.7900856232493e-06, "loss": 0.5083, "step": 154190 }, { "epoch": 0.9165968222265813, "grad_norm": 4.809520244598389, "learning_rate": 9.79002612885254e-06, "loss": 0.5087, "step": 154200 }, { "epoch": 0.9166562643032496, "grad_norm": 4.334292411804199, "learning_rate": 9.789966626206782e-06, "loss": 0.5051, "step": 154210 }, { "epoch": 0.9167157063799181, "grad_norm": 6.3340559005737305, "learning_rate": 9.78990711531213e-06, "loss": 0.5982, "step": 154220 }, { "epoch": 0.9167751484565865, "grad_norm": 4.275753974914551, "learning_rate": 9.789847596168686e-06, "loss": 0.5273, "step": 154230 }, { "epoch": 0.9168345905332549, "grad_norm": 5.68566370010376, "learning_rate": 9.789788068776556e-06, "loss": 0.5702, "step": 154240 }, { "epoch": 0.9168940326099233, "grad_norm": 6.062187671661377, "learning_rate": 9.789728533135836e-06, "loss": 0.5604, "step": 154250 }, { "epoch": 0.9169534746865916, "grad_norm": 5.167864799499512, "learning_rate": 9.789668989246635e-06, "loss": 0.5328, "step": 154260 }, { "epoch": 0.91701291676326, "grad_norm": 5.095098495483398, "learning_rate": 9.78960943710905e-06, "loss": 0.545, "step": 154270 }, { "epoch": 0.9170723588399284, "grad_norm": 6.13797664642334, "learning_rate": 9.789549876723188e-06, "loss": 0.5968, "step": 154280 }, { "epoch": 0.9171318009165969, "grad_norm": 6.454320430755615, "learning_rate": 9.789490308089149e-06, "loss": 0.5284, "step": 154290 }, { "epoch": 0.9171912429932653, "grad_norm": 3.8119330406188965, "learning_rate": 9.789430731207035e-06, "loss": 0.5922, "step": 154300 }, { "epoch": 0.9172506850699336, "grad_norm": 4.243805408477783, "learning_rate": 9.78937114607695e-06, "loss": 0.5369, "step": 154310 }, { "epoch": 0.917310127146602, "grad_norm": 4.059361457824707, "learning_rate": 9.789311552698996e-06, "loss": 0.5472, "step": 154320 }, { "epoch": 0.9173695692232704, "grad_norm": 5.197723865509033, "learning_rate": 9.789251951073278e-06, "loss": 0.5262, "step": 154330 }, { "epoch": 0.9174290112999388, "grad_norm": 6.067904949188232, "learning_rate": 9.789192341199895e-06, "loss": 0.5344, "step": 154340 }, { "epoch": 0.9174884533766071, "grad_norm": 5.104953289031982, "learning_rate": 9.789132723078954e-06, "loss": 0.5423, "step": 154350 }, { "epoch": 0.9175478954532755, "grad_norm": 5.62569522857666, "learning_rate": 9.789073096710553e-06, "loss": 0.5436, "step": 154360 }, { "epoch": 0.917607337529944, "grad_norm": 5.618872165679932, "learning_rate": 9.789013462094797e-06, "loss": 0.5965, "step": 154370 }, { "epoch": 0.9176667796066124, "grad_norm": 5.431947708129883, "learning_rate": 9.788953819231788e-06, "loss": 0.5746, "step": 154380 }, { "epoch": 0.9177262216832808, "grad_norm": 5.950973987579346, "learning_rate": 9.78889416812163e-06, "loss": 0.6139, "step": 154390 }, { "epoch": 0.9177856637599491, "grad_norm": 4.85639762878418, "learning_rate": 9.788834508764424e-06, "loss": 0.5388, "step": 154400 }, { "epoch": 0.9178451058366175, "grad_norm": 5.929401397705078, "learning_rate": 9.788774841160274e-06, "loss": 0.5612, "step": 154410 }, { "epoch": 0.9179045479132859, "grad_norm": 6.795945167541504, "learning_rate": 9.788715165309282e-06, "loss": 0.6411, "step": 154420 }, { "epoch": 0.9179639899899543, "grad_norm": 6.481729984283447, "learning_rate": 9.78865548121155e-06, "loss": 0.5817, "step": 154430 }, { "epoch": 0.9180234320666226, "grad_norm": 5.588684558868408, "learning_rate": 9.788595788867184e-06, "loss": 0.5746, "step": 154440 }, { "epoch": 0.918082874143291, "grad_norm": 4.817615032196045, "learning_rate": 9.788536088276284e-06, "loss": 0.6245, "step": 154450 }, { "epoch": 0.9181423162199595, "grad_norm": 4.312469482421875, "learning_rate": 9.788476379438953e-06, "loss": 0.6006, "step": 154460 }, { "epoch": 0.9182017582966279, "grad_norm": 4.43255615234375, "learning_rate": 9.788416662355295e-06, "loss": 0.5666, "step": 154470 }, { "epoch": 0.9182612003732963, "grad_norm": 4.236185550689697, "learning_rate": 9.788356937025411e-06, "loss": 0.5419, "step": 154480 }, { "epoch": 0.9183206424499646, "grad_norm": 4.119817733764648, "learning_rate": 9.788297203449407e-06, "loss": 0.5788, "step": 154490 }, { "epoch": 0.918380084526633, "grad_norm": 4.677333354949951, "learning_rate": 9.788237461627383e-06, "loss": 0.5419, "step": 154500 }, { "epoch": 0.9184395266033014, "grad_norm": 6.146794319152832, "learning_rate": 9.788177711559442e-06, "loss": 0.5241, "step": 154510 }, { "epoch": 0.9184989686799698, "grad_norm": 4.742762565612793, "learning_rate": 9.788117953245688e-06, "loss": 0.5374, "step": 154520 }, { "epoch": 0.9185584107566382, "grad_norm": 4.331442356109619, "learning_rate": 9.788058186686225e-06, "loss": 0.533, "step": 154530 }, { "epoch": 0.9186178528333065, "grad_norm": 3.981031894683838, "learning_rate": 9.787998411881153e-06, "loss": 0.5862, "step": 154540 }, { "epoch": 0.918677294909975, "grad_norm": 4.293241500854492, "learning_rate": 9.787938628830576e-06, "loss": 0.5492, "step": 154550 }, { "epoch": 0.9187367369866434, "grad_norm": 4.918233394622803, "learning_rate": 9.787878837534597e-06, "loss": 0.5294, "step": 154560 }, { "epoch": 0.9187961790633118, "grad_norm": 4.9019365310668945, "learning_rate": 9.78781903799332e-06, "loss": 0.5412, "step": 154570 }, { "epoch": 0.9188556211399801, "grad_norm": 5.555536270141602, "learning_rate": 9.787759230206849e-06, "loss": 0.525, "step": 154580 }, { "epoch": 0.9189150632166485, "grad_norm": 3.7725467681884766, "learning_rate": 9.787699414175284e-06, "loss": 0.5251, "step": 154590 }, { "epoch": 0.9189745052933169, "grad_norm": 6.631123065948486, "learning_rate": 9.78763958989873e-06, "loss": 0.5562, "step": 154600 }, { "epoch": 0.9190339473699853, "grad_norm": 3.7967097759246826, "learning_rate": 9.787579757377288e-06, "loss": 0.4923, "step": 154610 }, { "epoch": 0.9190933894466538, "grad_norm": 5.652354717254639, "learning_rate": 9.787519916611064e-06, "loss": 0.5189, "step": 154620 }, { "epoch": 0.9191528315233221, "grad_norm": 5.1583476066589355, "learning_rate": 9.78746006760016e-06, "loss": 0.5459, "step": 154630 }, { "epoch": 0.9192122735999905, "grad_norm": 4.506136894226074, "learning_rate": 9.787400210344677e-06, "loss": 0.5517, "step": 154640 }, { "epoch": 0.9192717156766589, "grad_norm": 4.149965286254883, "learning_rate": 9.787340344844719e-06, "loss": 0.5385, "step": 154650 }, { "epoch": 0.9193311577533273, "grad_norm": 7.176028251647949, "learning_rate": 9.787280471100391e-06, "loss": 0.6075, "step": 154660 }, { "epoch": 0.9193905998299957, "grad_norm": 4.507037162780762, "learning_rate": 9.787220589111794e-06, "loss": 0.514, "step": 154670 }, { "epoch": 0.919450041906664, "grad_norm": 5.529505729675293, "learning_rate": 9.787160698879032e-06, "loss": 0.596, "step": 154680 }, { "epoch": 0.9195094839833324, "grad_norm": 5.143714427947998, "learning_rate": 9.78710080040221e-06, "loss": 0.5288, "step": 154690 }, { "epoch": 0.9195689260600008, "grad_norm": 4.792510986328125, "learning_rate": 9.787040893681426e-06, "loss": 0.5173, "step": 154700 }, { "epoch": 0.9196283681366693, "grad_norm": 4.598857402801514, "learning_rate": 9.786980978716789e-06, "loss": 0.5611, "step": 154710 }, { "epoch": 0.9196878102133376, "grad_norm": 4.957344055175781, "learning_rate": 9.786921055508399e-06, "loss": 0.559, "step": 154720 }, { "epoch": 0.919747252290006, "grad_norm": 4.501481533050537, "learning_rate": 9.78686112405636e-06, "loss": 0.5503, "step": 154730 }, { "epoch": 0.9198066943666744, "grad_norm": 5.225369453430176, "learning_rate": 9.786801184360772e-06, "loss": 0.5651, "step": 154740 }, { "epoch": 0.9198661364433428, "grad_norm": 5.901028156280518, "learning_rate": 9.786741236421745e-06, "loss": 0.581, "step": 154750 }, { "epoch": 0.9199255785200112, "grad_norm": 5.208202362060547, "learning_rate": 9.786681280239375e-06, "loss": 0.5406, "step": 154760 }, { "epoch": 0.9199850205966795, "grad_norm": 6.881080627441406, "learning_rate": 9.786621315813772e-06, "loss": 0.5472, "step": 154770 }, { "epoch": 0.9200444626733479, "grad_norm": 5.479737281799316, "learning_rate": 9.786561343145036e-06, "loss": 0.5587, "step": 154780 }, { "epoch": 0.9201039047500164, "grad_norm": 4.244783878326416, "learning_rate": 9.786501362233269e-06, "loss": 0.5336, "step": 154790 }, { "epoch": 0.9201633468266848, "grad_norm": 2.8375415802001953, "learning_rate": 9.786441373078574e-06, "loss": 0.4691, "step": 154800 }, { "epoch": 0.9202227889033531, "grad_norm": 4.731136798858643, "learning_rate": 9.786381375681058e-06, "loss": 0.539, "step": 154810 }, { "epoch": 0.9202822309800215, "grad_norm": 5.463838577270508, "learning_rate": 9.786321370040821e-06, "loss": 0.5342, "step": 154820 }, { "epoch": 0.9203416730566899, "grad_norm": 5.878426551818848, "learning_rate": 9.786261356157969e-06, "loss": 0.5096, "step": 154830 }, { "epoch": 0.9204011151333583, "grad_norm": 5.6414265632629395, "learning_rate": 9.786201334032604e-06, "loss": 0.5221, "step": 154840 }, { "epoch": 0.9204605572100267, "grad_norm": 5.006345272064209, "learning_rate": 9.786141303664827e-06, "loss": 0.5478, "step": 154850 }, { "epoch": 0.920519999286695, "grad_norm": 4.473919868469238, "learning_rate": 9.786081265054745e-06, "loss": 0.5503, "step": 154860 }, { "epoch": 0.9205794413633634, "grad_norm": 5.6999664306640625, "learning_rate": 9.78602121820246e-06, "loss": 0.5294, "step": 154870 }, { "epoch": 0.9206388834400319, "grad_norm": 5.660661697387695, "learning_rate": 9.785961163108075e-06, "loss": 0.542, "step": 154880 }, { "epoch": 0.9206983255167003, "grad_norm": 6.952625751495361, "learning_rate": 9.785901099771692e-06, "loss": 0.5339, "step": 154890 }, { "epoch": 0.9207577675933687, "grad_norm": 5.3170695304870605, "learning_rate": 9.78584102819342e-06, "loss": 0.5399, "step": 154900 }, { "epoch": 0.920817209670037, "grad_norm": 5.168205261230469, "learning_rate": 9.785780948373357e-06, "loss": 0.575, "step": 154910 }, { "epoch": 0.9208766517467054, "grad_norm": 6.050646781921387, "learning_rate": 9.785720860311607e-06, "loss": 0.5735, "step": 154920 }, { "epoch": 0.9209360938233738, "grad_norm": 5.794130802154541, "learning_rate": 9.785660764008276e-06, "loss": 0.547, "step": 154930 }, { "epoch": 0.9209955359000422, "grad_norm": 5.386066436767578, "learning_rate": 9.785600659463466e-06, "loss": 0.4993, "step": 154940 }, { "epoch": 0.9210549779767105, "grad_norm": 6.279947280883789, "learning_rate": 9.78554054667728e-06, "loss": 0.5653, "step": 154950 }, { "epoch": 0.921114420053379, "grad_norm": 5.70569372177124, "learning_rate": 9.785480425649824e-06, "loss": 0.5524, "step": 154960 }, { "epoch": 0.9211738621300474, "grad_norm": 4.981595516204834, "learning_rate": 9.785420296381198e-06, "loss": 0.5787, "step": 154970 }, { "epoch": 0.9212333042067158, "grad_norm": 5.740420818328857, "learning_rate": 9.785360158871509e-06, "loss": 0.5628, "step": 154980 }, { "epoch": 0.9212927462833842, "grad_norm": 5.253604888916016, "learning_rate": 9.785300013120856e-06, "loss": 0.5675, "step": 154990 }, { "epoch": 0.9213521883600525, "grad_norm": 4.582910537719727, "learning_rate": 9.785239859129348e-06, "loss": 0.5303, "step": 155000 }, { "epoch": 0.9214116304367209, "grad_norm": 5.169837474822998, "learning_rate": 9.785179696897084e-06, "loss": 0.5176, "step": 155010 }, { "epoch": 0.9214710725133893, "grad_norm": 5.373472213745117, "learning_rate": 9.78511952642417e-06, "loss": 0.5459, "step": 155020 }, { "epoch": 0.9215305145900577, "grad_norm": 5.820476531982422, "learning_rate": 9.78505934771071e-06, "loss": 0.5655, "step": 155030 }, { "epoch": 0.9215899566667262, "grad_norm": 4.836723327636719, "learning_rate": 9.784999160756807e-06, "loss": 0.51, "step": 155040 }, { "epoch": 0.9216493987433945, "grad_norm": 5.928134918212891, "learning_rate": 9.784938965562564e-06, "loss": 0.4942, "step": 155050 }, { "epoch": 0.9217088408200629, "grad_norm": 5.777445316314697, "learning_rate": 9.784878762128086e-06, "loss": 0.5584, "step": 155060 }, { "epoch": 0.9217682828967313, "grad_norm": 3.97192120552063, "learning_rate": 9.784818550453474e-06, "loss": 0.5079, "step": 155070 }, { "epoch": 0.9218277249733997, "grad_norm": 6.234985828399658, "learning_rate": 9.784758330538834e-06, "loss": 0.564, "step": 155080 }, { "epoch": 0.921887167050068, "grad_norm": 5.358774185180664, "learning_rate": 9.784698102384272e-06, "loss": 0.5352, "step": 155090 }, { "epoch": 0.9219466091267364, "grad_norm": 6.336329936981201, "learning_rate": 9.784637865989886e-06, "loss": 0.5824, "step": 155100 }, { "epoch": 0.9220060512034048, "grad_norm": 5.946921348571777, "learning_rate": 9.784577621355784e-06, "loss": 0.5897, "step": 155110 }, { "epoch": 0.9220654932800733, "grad_norm": 5.30377197265625, "learning_rate": 9.784517368482069e-06, "loss": 0.5259, "step": 155120 }, { "epoch": 0.9221249353567417, "grad_norm": 6.014214515686035, "learning_rate": 9.784457107368843e-06, "loss": 0.5407, "step": 155130 }, { "epoch": 0.92218437743341, "grad_norm": 4.761815071105957, "learning_rate": 9.78439683801621e-06, "loss": 0.5562, "step": 155140 }, { "epoch": 0.9222438195100784, "grad_norm": 5.629698276519775, "learning_rate": 9.784336560424276e-06, "loss": 0.5736, "step": 155150 }, { "epoch": 0.9223032615867468, "grad_norm": 4.716803550720215, "learning_rate": 9.784276274593145e-06, "loss": 0.4921, "step": 155160 }, { "epoch": 0.9223627036634152, "grad_norm": 3.930133104324341, "learning_rate": 9.784215980522917e-06, "loss": 0.5583, "step": 155170 }, { "epoch": 0.9224221457400835, "grad_norm": 4.677027225494385, "learning_rate": 9.784155678213701e-06, "loss": 0.5746, "step": 155180 }, { "epoch": 0.9224815878167519, "grad_norm": 4.374353408813477, "learning_rate": 9.784095367665594e-06, "loss": 0.5597, "step": 155190 }, { "epoch": 0.9225410298934204, "grad_norm": 3.722595691680908, "learning_rate": 9.784035048878708e-06, "loss": 0.5797, "step": 155200 }, { "epoch": 0.9226004719700888, "grad_norm": 5.2695088386535645, "learning_rate": 9.78397472185314e-06, "loss": 0.5631, "step": 155210 }, { "epoch": 0.9226599140467572, "grad_norm": 4.149725437164307, "learning_rate": 9.783914386588998e-06, "loss": 0.4726, "step": 155220 }, { "epoch": 0.9227193561234255, "grad_norm": 4.47675085067749, "learning_rate": 9.783854043086385e-06, "loss": 0.5385, "step": 155230 }, { "epoch": 0.9227787982000939, "grad_norm": 5.617494106292725, "learning_rate": 9.783793691345405e-06, "loss": 0.5442, "step": 155240 }, { "epoch": 0.9228382402767623, "grad_norm": 5.0206618309021, "learning_rate": 9.783733331366158e-06, "loss": 0.59, "step": 155250 }, { "epoch": 0.9228976823534307, "grad_norm": 5.46312952041626, "learning_rate": 9.783672963148756e-06, "loss": 0.5348, "step": 155260 }, { "epoch": 0.9229571244300991, "grad_norm": 5.690946102142334, "learning_rate": 9.783612586693295e-06, "loss": 0.5615, "step": 155270 }, { "epoch": 0.9230165665067674, "grad_norm": 4.068392753601074, "learning_rate": 9.783552201999885e-06, "loss": 0.523, "step": 155280 }, { "epoch": 0.9230760085834359, "grad_norm": 4.518979549407959, "learning_rate": 9.783491809068625e-06, "loss": 0.5717, "step": 155290 }, { "epoch": 0.9231354506601043, "grad_norm": 4.398841857910156, "learning_rate": 9.783431407899622e-06, "loss": 0.5263, "step": 155300 }, { "epoch": 0.9231948927367727, "grad_norm": 4.131725788116455, "learning_rate": 9.78337099849298e-06, "loss": 0.5497, "step": 155310 }, { "epoch": 0.923254334813441, "grad_norm": 5.775221347808838, "learning_rate": 9.783310580848802e-06, "loss": 0.5465, "step": 155320 }, { "epoch": 0.9233137768901094, "grad_norm": 5.900579929351807, "learning_rate": 9.783250154967192e-06, "loss": 0.5562, "step": 155330 }, { "epoch": 0.9233732189667778, "grad_norm": 4.7422990798950195, "learning_rate": 9.783189720848257e-06, "loss": 0.5478, "step": 155340 }, { "epoch": 0.9234326610434462, "grad_norm": 5.4263410568237305, "learning_rate": 9.783129278492096e-06, "loss": 0.568, "step": 155350 }, { "epoch": 0.9234921031201146, "grad_norm": 5.6055121421813965, "learning_rate": 9.783068827898816e-06, "loss": 0.5728, "step": 155360 }, { "epoch": 0.923551545196783, "grad_norm": 6.490273952484131, "learning_rate": 9.783008369068521e-06, "loss": 0.5328, "step": 155370 }, { "epoch": 0.9236109872734514, "grad_norm": 4.7469305992126465, "learning_rate": 9.782947902001314e-06, "loss": 0.5344, "step": 155380 }, { "epoch": 0.9236704293501198, "grad_norm": 4.300612449645996, "learning_rate": 9.782887426697301e-06, "loss": 0.5172, "step": 155390 }, { "epoch": 0.9237298714267882, "grad_norm": 5.7049455642700195, "learning_rate": 9.782826943156586e-06, "loss": 0.5257, "step": 155400 }, { "epoch": 0.9237893135034566, "grad_norm": 5.511412143707275, "learning_rate": 9.782766451379271e-06, "loss": 0.5482, "step": 155410 }, { "epoch": 0.9238487555801249, "grad_norm": 5.062959671020508, "learning_rate": 9.782705951365462e-06, "loss": 0.4823, "step": 155420 }, { "epoch": 0.9239081976567933, "grad_norm": 6.10247278213501, "learning_rate": 9.782645443115262e-06, "loss": 0.569, "step": 155430 }, { "epoch": 0.9239676397334617, "grad_norm": 4.168781280517578, "learning_rate": 9.782584926628777e-06, "loss": 0.522, "step": 155440 }, { "epoch": 0.9240270818101302, "grad_norm": 5.134174823760986, "learning_rate": 9.78252440190611e-06, "loss": 0.5911, "step": 155450 }, { "epoch": 0.9240865238867985, "grad_norm": 4.4865593910217285, "learning_rate": 9.782463868947365e-06, "loss": 0.5358, "step": 155460 }, { "epoch": 0.9241459659634669, "grad_norm": 5.020624160766602, "learning_rate": 9.782403327752646e-06, "loss": 0.498, "step": 155470 }, { "epoch": 0.9242054080401353, "grad_norm": 4.751144886016846, "learning_rate": 9.782342778322057e-06, "loss": 0.5338, "step": 155480 }, { "epoch": 0.9242648501168037, "grad_norm": 4.704749584197998, "learning_rate": 9.782282220655705e-06, "loss": 0.5096, "step": 155490 }, { "epoch": 0.9243242921934721, "grad_norm": 4.456507682800293, "learning_rate": 9.782221654753693e-06, "loss": 0.5802, "step": 155500 }, { "epoch": 0.9243837342701404, "grad_norm": 6.864528179168701, "learning_rate": 9.782161080616125e-06, "loss": 0.5398, "step": 155510 }, { "epoch": 0.9244431763468088, "grad_norm": 5.041809558868408, "learning_rate": 9.782100498243102e-06, "loss": 0.5563, "step": 155520 }, { "epoch": 0.9245026184234773, "grad_norm": 4.8387298583984375, "learning_rate": 9.782039907634733e-06, "loss": 0.588, "step": 155530 }, { "epoch": 0.9245620605001457, "grad_norm": 4.419632911682129, "learning_rate": 9.78197930879112e-06, "loss": 0.5107, "step": 155540 }, { "epoch": 0.924621502576814, "grad_norm": 5.6845574378967285, "learning_rate": 9.78191870171237e-06, "loss": 0.5236, "step": 155550 }, { "epoch": 0.9246809446534824, "grad_norm": 4.671404838562012, "learning_rate": 9.781858086398584e-06, "loss": 0.5572, "step": 155560 }, { "epoch": 0.9247403867301508, "grad_norm": 6.142971038818359, "learning_rate": 9.781797462849868e-06, "loss": 0.5627, "step": 155570 }, { "epoch": 0.9247998288068192, "grad_norm": 3.238938331604004, "learning_rate": 9.781736831066327e-06, "loss": 0.5088, "step": 155580 }, { "epoch": 0.9248592708834876, "grad_norm": 4.834305286407471, "learning_rate": 9.781676191048064e-06, "loss": 0.5714, "step": 155590 }, { "epoch": 0.9249187129601559, "grad_norm": 8.120965957641602, "learning_rate": 9.781615542795183e-06, "loss": 0.5849, "step": 155600 }, { "epoch": 0.9249781550368243, "grad_norm": 5.6654205322265625, "learning_rate": 9.78155488630779e-06, "loss": 0.565, "step": 155610 }, { "epoch": 0.9250375971134928, "grad_norm": 4.473883152008057, "learning_rate": 9.78149422158599e-06, "loss": 0.4767, "step": 155620 }, { "epoch": 0.9250970391901612, "grad_norm": 4.7934041023254395, "learning_rate": 9.781433548629887e-06, "loss": 0.5613, "step": 155630 }, { "epoch": 0.9251564812668296, "grad_norm": 4.732892990112305, "learning_rate": 9.781372867439583e-06, "loss": 0.5656, "step": 155640 }, { "epoch": 0.9252159233434979, "grad_norm": 6.184305667877197, "learning_rate": 9.781312178015184e-06, "loss": 0.6, "step": 155650 }, { "epoch": 0.9252753654201663, "grad_norm": 4.782754421234131, "learning_rate": 9.781251480356797e-06, "loss": 0.4927, "step": 155660 }, { "epoch": 0.9253348074968347, "grad_norm": 5.676344394683838, "learning_rate": 9.781190774464522e-06, "loss": 0.5466, "step": 155670 }, { "epoch": 0.9253942495735031, "grad_norm": 5.1249542236328125, "learning_rate": 9.781130060338469e-06, "loss": 0.5081, "step": 155680 }, { "epoch": 0.9254536916501714, "grad_norm": 4.29714298248291, "learning_rate": 9.781069337978737e-06, "loss": 0.4979, "step": 155690 }, { "epoch": 0.9255131337268399, "grad_norm": 3.8382694721221924, "learning_rate": 9.781008607385434e-06, "loss": 0.5458, "step": 155700 }, { "epoch": 0.9255725758035083, "grad_norm": 5.942328929901123, "learning_rate": 9.780947868558665e-06, "loss": 0.5404, "step": 155710 }, { "epoch": 0.9256320178801767, "grad_norm": 4.355686187744141, "learning_rate": 9.780887121498532e-06, "loss": 0.4874, "step": 155720 }, { "epoch": 0.9256914599568451, "grad_norm": 5.283820629119873, "learning_rate": 9.780826366205141e-06, "loss": 0.5358, "step": 155730 }, { "epoch": 0.9257509020335134, "grad_norm": 5.208607196807861, "learning_rate": 9.780765602678596e-06, "loss": 0.5461, "step": 155740 }, { "epoch": 0.9258103441101818, "grad_norm": 5.575547695159912, "learning_rate": 9.780704830919003e-06, "loss": 0.5163, "step": 155750 }, { "epoch": 0.9258697861868502, "grad_norm": 6.37974739074707, "learning_rate": 9.780644050926466e-06, "loss": 0.5901, "step": 155760 }, { "epoch": 0.9259292282635186, "grad_norm": 5.264151573181152, "learning_rate": 9.78058326270109e-06, "loss": 0.496, "step": 155770 }, { "epoch": 0.9259886703401871, "grad_norm": 6.004997253417969, "learning_rate": 9.780522466242978e-06, "loss": 0.595, "step": 155780 }, { "epoch": 0.9260481124168554, "grad_norm": 4.392457008361816, "learning_rate": 9.780461661552236e-06, "loss": 0.5586, "step": 155790 }, { "epoch": 0.9261075544935238, "grad_norm": 3.706627607345581, "learning_rate": 9.78040084862897e-06, "loss": 0.526, "step": 155800 }, { "epoch": 0.9261669965701922, "grad_norm": 5.784615516662598, "learning_rate": 9.780340027473283e-06, "loss": 0.5756, "step": 155810 }, { "epoch": 0.9262264386468606, "grad_norm": 4.2190985679626465, "learning_rate": 9.780279198085278e-06, "loss": 0.5762, "step": 155820 }, { "epoch": 0.9262858807235289, "grad_norm": 4.337052822113037, "learning_rate": 9.780218360465063e-06, "loss": 0.5291, "step": 155830 }, { "epoch": 0.9263453228001973, "grad_norm": 5.883533000946045, "learning_rate": 9.780157514612742e-06, "loss": 0.5268, "step": 155840 }, { "epoch": 0.9264047648768657, "grad_norm": 6.464971542358398, "learning_rate": 9.78009666052842e-06, "loss": 0.57, "step": 155850 }, { "epoch": 0.9264642069535342, "grad_norm": 4.3271379470825195, "learning_rate": 9.780035798212201e-06, "loss": 0.4858, "step": 155860 }, { "epoch": 0.9265236490302026, "grad_norm": 4.644778251647949, "learning_rate": 9.77997492766419e-06, "loss": 0.5104, "step": 155870 }, { "epoch": 0.9265830911068709, "grad_norm": 4.400226593017578, "learning_rate": 9.779914048884492e-06, "loss": 0.6033, "step": 155880 }, { "epoch": 0.9266425331835393, "grad_norm": 4.714730262756348, "learning_rate": 9.77985316187321e-06, "loss": 0.5686, "step": 155890 }, { "epoch": 0.9267019752602077, "grad_norm": 5.505336284637451, "learning_rate": 9.779792266630453e-06, "loss": 0.4955, "step": 155900 }, { "epoch": 0.9267614173368761, "grad_norm": 6.02268648147583, "learning_rate": 9.779731363156322e-06, "loss": 0.5166, "step": 155910 }, { "epoch": 0.9268208594135444, "grad_norm": 4.655578136444092, "learning_rate": 9.779670451450922e-06, "loss": 0.4799, "step": 155920 }, { "epoch": 0.9268803014902128, "grad_norm": 3.450110673904419, "learning_rate": 9.77960953151436e-06, "loss": 0.5281, "step": 155930 }, { "epoch": 0.9269397435668812, "grad_norm": 4.947356224060059, "learning_rate": 9.779548603346742e-06, "loss": 0.5558, "step": 155940 }, { "epoch": 0.9269991856435497, "grad_norm": 5.914042949676514, "learning_rate": 9.779487666948169e-06, "loss": 0.5323, "step": 155950 }, { "epoch": 0.9270586277202181, "grad_norm": 4.514901161193848, "learning_rate": 9.77942672231875e-06, "loss": 0.5648, "step": 155960 }, { "epoch": 0.9271180697968864, "grad_norm": 5.349325656890869, "learning_rate": 9.779365769458586e-06, "loss": 0.6353, "step": 155970 }, { "epoch": 0.9271775118735548, "grad_norm": 5.926581859588623, "learning_rate": 9.779304808367783e-06, "loss": 0.4945, "step": 155980 }, { "epoch": 0.9272369539502232, "grad_norm": 6.201294422149658, "learning_rate": 9.779243839046449e-06, "loss": 0.6486, "step": 155990 }, { "epoch": 0.9272963960268916, "grad_norm": 5.953846454620361, "learning_rate": 9.779182861494687e-06, "loss": 0.5206, "step": 156000 }, { "epoch": 0.92735583810356, "grad_norm": 5.53176736831665, "learning_rate": 9.7791218757126e-06, "loss": 0.5432, "step": 156010 }, { "epoch": 0.9274152801802283, "grad_norm": 3.6702868938446045, "learning_rate": 9.779060881700295e-06, "loss": 0.528, "step": 156020 }, { "epoch": 0.9274747222568968, "grad_norm": 4.894172191619873, "learning_rate": 9.778999879457878e-06, "loss": 0.5471, "step": 156030 }, { "epoch": 0.9275341643335652, "grad_norm": 4.182613849639893, "learning_rate": 9.778938868985452e-06, "loss": 0.5037, "step": 156040 }, { "epoch": 0.9275936064102336, "grad_norm": 6.005924701690674, "learning_rate": 9.778877850283125e-06, "loss": 0.5593, "step": 156050 }, { "epoch": 0.9276530484869019, "grad_norm": 4.339221477508545, "learning_rate": 9.778816823350998e-06, "loss": 0.5299, "step": 156060 }, { "epoch": 0.9277124905635703, "grad_norm": 5.404135227203369, "learning_rate": 9.778755788189181e-06, "loss": 0.5346, "step": 156070 }, { "epoch": 0.9277719326402387, "grad_norm": 4.870142459869385, "learning_rate": 9.778694744797775e-06, "loss": 0.5298, "step": 156080 }, { "epoch": 0.9278313747169071, "grad_norm": 5.583333969116211, "learning_rate": 9.778633693176885e-06, "loss": 0.5583, "step": 156090 }, { "epoch": 0.9278908167935755, "grad_norm": 6.298835277557373, "learning_rate": 9.778572633326618e-06, "loss": 0.5628, "step": 156100 }, { "epoch": 0.9279502588702438, "grad_norm": 5.3694844245910645, "learning_rate": 9.77851156524708e-06, "loss": 0.5203, "step": 156110 }, { "epoch": 0.9280097009469123, "grad_norm": 6.702441215515137, "learning_rate": 9.778450488938374e-06, "loss": 0.5756, "step": 156120 }, { "epoch": 0.9280691430235807, "grad_norm": 5.249423503875732, "learning_rate": 9.778389404400606e-06, "loss": 0.5961, "step": 156130 }, { "epoch": 0.9281285851002491, "grad_norm": 4.589869022369385, "learning_rate": 9.778328311633883e-06, "loss": 0.5644, "step": 156140 }, { "epoch": 0.9281880271769175, "grad_norm": 4.121560096740723, "learning_rate": 9.778267210638306e-06, "loss": 0.5116, "step": 156150 }, { "epoch": 0.9282474692535858, "grad_norm": 6.385961055755615, "learning_rate": 9.778206101413985e-06, "loss": 0.5774, "step": 156160 }, { "epoch": 0.9283069113302542, "grad_norm": 5.276050567626953, "learning_rate": 9.778144983961021e-06, "loss": 0.5302, "step": 156170 }, { "epoch": 0.9283663534069226, "grad_norm": 4.265945911407471, "learning_rate": 9.778083858279521e-06, "loss": 0.4961, "step": 156180 }, { "epoch": 0.928425795483591, "grad_norm": 6.360283851623535, "learning_rate": 9.778022724369592e-06, "loss": 0.5572, "step": 156190 }, { "epoch": 0.9284852375602594, "grad_norm": 4.498717784881592, "learning_rate": 9.777961582231337e-06, "loss": 0.5274, "step": 156200 }, { "epoch": 0.9285446796369278, "grad_norm": 7.6406145095825195, "learning_rate": 9.777900431864864e-06, "loss": 0.5581, "step": 156210 }, { "epoch": 0.9286041217135962, "grad_norm": 5.993702411651611, "learning_rate": 9.777839273270274e-06, "loss": 0.5893, "step": 156220 }, { "epoch": 0.9286635637902646, "grad_norm": 4.17869234085083, "learning_rate": 9.777778106447675e-06, "loss": 0.5431, "step": 156230 }, { "epoch": 0.928723005866933, "grad_norm": 6.289430141448975, "learning_rate": 9.777716931397173e-06, "loss": 0.5248, "step": 156240 }, { "epoch": 0.9287824479436013, "grad_norm": 5.765906810760498, "learning_rate": 9.777655748118872e-06, "loss": 0.5859, "step": 156250 }, { "epoch": 0.9288418900202697, "grad_norm": 4.754824161529541, "learning_rate": 9.777594556612878e-06, "loss": 0.5525, "step": 156260 }, { "epoch": 0.9289013320969381, "grad_norm": 5.207819938659668, "learning_rate": 9.777533356879295e-06, "loss": 0.4814, "step": 156270 }, { "epoch": 0.9289607741736066, "grad_norm": 7.0383429527282715, "learning_rate": 9.77747214891823e-06, "loss": 0.5823, "step": 156280 }, { "epoch": 0.9290202162502749, "grad_norm": 5.641908168792725, "learning_rate": 9.77741093272979e-06, "loss": 0.584, "step": 156290 }, { "epoch": 0.9290796583269433, "grad_norm": 5.401878833770752, "learning_rate": 9.777349708314075e-06, "loss": 0.5662, "step": 156300 }, { "epoch": 0.9291391004036117, "grad_norm": 5.6734795570373535, "learning_rate": 9.777288475671197e-06, "loss": 0.5295, "step": 156310 }, { "epoch": 0.9291985424802801, "grad_norm": 4.845814228057861, "learning_rate": 9.777227234801254e-06, "loss": 0.5689, "step": 156320 }, { "epoch": 0.9292579845569485, "grad_norm": 6.16146183013916, "learning_rate": 9.77716598570436e-06, "loss": 0.5173, "step": 156330 }, { "epoch": 0.9293174266336168, "grad_norm": 5.647387981414795, "learning_rate": 9.777104728380614e-06, "loss": 0.5629, "step": 156340 }, { "epoch": 0.9293768687102852, "grad_norm": 4.785926818847656, "learning_rate": 9.777043462830123e-06, "loss": 0.5469, "step": 156350 }, { "epoch": 0.9294363107869537, "grad_norm": 5.268525123596191, "learning_rate": 9.776982189052994e-06, "loss": 0.5354, "step": 156360 }, { "epoch": 0.9294957528636221, "grad_norm": 5.419295787811279, "learning_rate": 9.776920907049332e-06, "loss": 0.5387, "step": 156370 }, { "epoch": 0.9295551949402905, "grad_norm": 5.335047721862793, "learning_rate": 9.776859616819244e-06, "loss": 0.5342, "step": 156380 }, { "epoch": 0.9296146370169588, "grad_norm": 6.696209907531738, "learning_rate": 9.77679831836283e-06, "loss": 0.5643, "step": 156390 }, { "epoch": 0.9296740790936272, "grad_norm": 5.898860454559326, "learning_rate": 9.776737011680202e-06, "loss": 0.5407, "step": 156400 }, { "epoch": 0.9297335211702956, "grad_norm": 4.550318717956543, "learning_rate": 9.776675696771463e-06, "loss": 0.5673, "step": 156410 }, { "epoch": 0.929792963246964, "grad_norm": 6.202436923980713, "learning_rate": 9.776614373636716e-06, "loss": 0.5204, "step": 156420 }, { "epoch": 0.9298524053236323, "grad_norm": 5.445906639099121, "learning_rate": 9.776553042276072e-06, "loss": 0.5639, "step": 156430 }, { "epoch": 0.9299118474003008, "grad_norm": 4.986405849456787, "learning_rate": 9.776491702689631e-06, "loss": 0.5331, "step": 156440 }, { "epoch": 0.9299712894769692, "grad_norm": 4.230278015136719, "learning_rate": 9.776430354877505e-06, "loss": 0.5152, "step": 156450 }, { "epoch": 0.9300307315536376, "grad_norm": 4.999203205108643, "learning_rate": 9.776368998839792e-06, "loss": 0.5204, "step": 156460 }, { "epoch": 0.930090173630306, "grad_norm": 5.634947299957275, "learning_rate": 9.776307634576605e-06, "loss": 0.5275, "step": 156470 }, { "epoch": 0.9301496157069743, "grad_norm": 5.178610324859619, "learning_rate": 9.776246262088046e-06, "loss": 0.5333, "step": 156480 }, { "epoch": 0.9302090577836427, "grad_norm": 4.607019424438477, "learning_rate": 9.776184881374219e-06, "loss": 0.4844, "step": 156490 }, { "epoch": 0.9302684998603111, "grad_norm": 5.7449493408203125, "learning_rate": 9.776123492435232e-06, "loss": 0.5788, "step": 156500 }, { "epoch": 0.9303279419369795, "grad_norm": 5.848467826843262, "learning_rate": 9.77606209527119e-06, "loss": 0.5042, "step": 156510 }, { "epoch": 0.930387384013648, "grad_norm": 5.436458110809326, "learning_rate": 9.776000689882202e-06, "loss": 0.5666, "step": 156520 }, { "epoch": 0.9304468260903163, "grad_norm": 4.081239223480225, "learning_rate": 9.775939276268368e-06, "loss": 0.467, "step": 156530 }, { "epoch": 0.9305062681669847, "grad_norm": 4.694332599639893, "learning_rate": 9.775877854429799e-06, "loss": 0.6051, "step": 156540 }, { "epoch": 0.9305657102436531, "grad_norm": 5.8849287033081055, "learning_rate": 9.775816424366597e-06, "loss": 0.5342, "step": 156550 }, { "epoch": 0.9306251523203215, "grad_norm": 6.463379859924316, "learning_rate": 9.775754986078869e-06, "loss": 0.5481, "step": 156560 }, { "epoch": 0.9306845943969898, "grad_norm": 5.9336018562316895, "learning_rate": 9.775693539566722e-06, "loss": 0.6464, "step": 156570 }, { "epoch": 0.9307440364736582, "grad_norm": 3.2883548736572266, "learning_rate": 9.775632084830263e-06, "loss": 0.4959, "step": 156580 }, { "epoch": 0.9308034785503266, "grad_norm": 3.9271509647369385, "learning_rate": 9.775570621869592e-06, "loss": 0.499, "step": 156590 }, { "epoch": 0.930862920626995, "grad_norm": 4.9734320640563965, "learning_rate": 9.775509150684821e-06, "loss": 0.5156, "step": 156600 }, { "epoch": 0.9309223627036635, "grad_norm": 6.931487083435059, "learning_rate": 9.775447671276052e-06, "loss": 0.5176, "step": 156610 }, { "epoch": 0.9309818047803318, "grad_norm": 3.898576021194458, "learning_rate": 9.775386183643394e-06, "loss": 0.5218, "step": 156620 }, { "epoch": 0.9310412468570002, "grad_norm": 7.406222820281982, "learning_rate": 9.775324687786948e-06, "loss": 0.5879, "step": 156630 }, { "epoch": 0.9311006889336686, "grad_norm": 6.091938495635986, "learning_rate": 9.775263183706826e-06, "loss": 0.5548, "step": 156640 }, { "epoch": 0.931160131010337, "grad_norm": 5.1613383293151855, "learning_rate": 9.775201671403129e-06, "loss": 0.4631, "step": 156650 }, { "epoch": 0.9312195730870053, "grad_norm": 5.144381999969482, "learning_rate": 9.775140150875967e-06, "loss": 0.5318, "step": 156660 }, { "epoch": 0.9312790151636737, "grad_norm": 5.417644023895264, "learning_rate": 9.775078622125443e-06, "loss": 0.5798, "step": 156670 }, { "epoch": 0.9313384572403421, "grad_norm": 6.086341381072998, "learning_rate": 9.775017085151663e-06, "loss": 0.567, "step": 156680 }, { "epoch": 0.9313978993170106, "grad_norm": 4.985076904296875, "learning_rate": 9.774955539954736e-06, "loss": 0.5532, "step": 156690 }, { "epoch": 0.931457341393679, "grad_norm": 4.118649482727051, "learning_rate": 9.774893986534763e-06, "loss": 0.5373, "step": 156700 }, { "epoch": 0.9315167834703473, "grad_norm": 4.539434909820557, "learning_rate": 9.774832424891856e-06, "loss": 0.5485, "step": 156710 }, { "epoch": 0.9315762255470157, "grad_norm": 4.48375129699707, "learning_rate": 9.774770855026116e-06, "loss": 0.529, "step": 156720 }, { "epoch": 0.9316356676236841, "grad_norm": 6.326328754425049, "learning_rate": 9.77470927693765e-06, "loss": 0.5357, "step": 156730 }, { "epoch": 0.9316951097003525, "grad_norm": 4.80820369720459, "learning_rate": 9.774647690626567e-06, "loss": 0.5264, "step": 156740 }, { "epoch": 0.9317545517770209, "grad_norm": 4.1342620849609375, "learning_rate": 9.77458609609297e-06, "loss": 0.4774, "step": 156750 }, { "epoch": 0.9318139938536892, "grad_norm": 4.839138031005859, "learning_rate": 9.774524493336966e-06, "loss": 0.5202, "step": 156760 }, { "epoch": 0.9318734359303577, "grad_norm": 5.536588668823242, "learning_rate": 9.77446288235866e-06, "loss": 0.5007, "step": 156770 }, { "epoch": 0.9319328780070261, "grad_norm": 5.876941204071045, "learning_rate": 9.774401263158161e-06, "loss": 0.5767, "step": 156780 }, { "epoch": 0.9319923200836945, "grad_norm": 5.2847900390625, "learning_rate": 9.774339635735573e-06, "loss": 0.5049, "step": 156790 }, { "epoch": 0.9320517621603628, "grad_norm": 7.565343856811523, "learning_rate": 9.774278000091002e-06, "loss": 0.582, "step": 156800 }, { "epoch": 0.9321112042370312, "grad_norm": 4.817460536956787, "learning_rate": 9.774216356224555e-06, "loss": 0.5267, "step": 156810 }, { "epoch": 0.9321706463136996, "grad_norm": 7.1078715324401855, "learning_rate": 9.774154704136339e-06, "loss": 0.5551, "step": 156820 }, { "epoch": 0.932230088390368, "grad_norm": 5.849852085113525, "learning_rate": 9.774093043826456e-06, "loss": 0.4995, "step": 156830 }, { "epoch": 0.9322895304670364, "grad_norm": 5.248189926147461, "learning_rate": 9.774031375295016e-06, "loss": 0.5815, "step": 156840 }, { "epoch": 0.9323489725437047, "grad_norm": 4.385653495788574, "learning_rate": 9.773969698542126e-06, "loss": 0.4878, "step": 156850 }, { "epoch": 0.9324084146203732, "grad_norm": 4.125000953674316, "learning_rate": 9.77390801356789e-06, "loss": 0.5252, "step": 156860 }, { "epoch": 0.9324678566970416, "grad_norm": 5.436126708984375, "learning_rate": 9.773846320372413e-06, "loss": 0.5679, "step": 156870 }, { "epoch": 0.93252729877371, "grad_norm": 6.385647296905518, "learning_rate": 9.773784618955807e-06, "loss": 0.5624, "step": 156880 }, { "epoch": 0.9325867408503784, "grad_norm": 5.644941329956055, "learning_rate": 9.773722909318171e-06, "loss": 0.5298, "step": 156890 }, { "epoch": 0.9326461829270467, "grad_norm": 5.467074394226074, "learning_rate": 9.773661191459615e-06, "loss": 0.5434, "step": 156900 }, { "epoch": 0.9327056250037151, "grad_norm": 7.225625514984131, "learning_rate": 9.773599465380245e-06, "loss": 0.5381, "step": 156910 }, { "epoch": 0.9327650670803835, "grad_norm": 5.324105262756348, "learning_rate": 9.773537731080168e-06, "loss": 0.5341, "step": 156920 }, { "epoch": 0.932824509157052, "grad_norm": 5.142611503601074, "learning_rate": 9.773475988559488e-06, "loss": 0.5691, "step": 156930 }, { "epoch": 0.9328839512337203, "grad_norm": 5.735933780670166, "learning_rate": 9.773414237818312e-06, "loss": 0.5266, "step": 156940 }, { "epoch": 0.9329433933103887, "grad_norm": 5.164784908294678, "learning_rate": 9.77335247885675e-06, "loss": 0.5279, "step": 156950 }, { "epoch": 0.9330028353870571, "grad_norm": 5.015453338623047, "learning_rate": 9.773290711674903e-06, "loss": 0.5421, "step": 156960 }, { "epoch": 0.9330622774637255, "grad_norm": 5.908632755279541, "learning_rate": 9.77322893627288e-06, "loss": 0.5494, "step": 156970 }, { "epoch": 0.9331217195403939, "grad_norm": 4.968687057495117, "learning_rate": 9.77316715265079e-06, "loss": 0.5203, "step": 156980 }, { "epoch": 0.9331811616170622, "grad_norm": 6.191081523895264, "learning_rate": 9.773105360808734e-06, "loss": 0.5289, "step": 156990 }, { "epoch": 0.9332406036937306, "grad_norm": 4.937692165374756, "learning_rate": 9.773043560746823e-06, "loss": 0.579, "step": 157000 }, { "epoch": 0.933300045770399, "grad_norm": 3.7710821628570557, "learning_rate": 9.77298175246516e-06, "loss": 0.5543, "step": 157010 }, { "epoch": 0.9333594878470675, "grad_norm": 5.597348690032959, "learning_rate": 9.772919935963854e-06, "loss": 0.5469, "step": 157020 }, { "epoch": 0.9334189299237358, "grad_norm": 6.070703506469727, "learning_rate": 9.772858111243008e-06, "loss": 0.56, "step": 157030 }, { "epoch": 0.9334783720004042, "grad_norm": 5.661516189575195, "learning_rate": 9.772796278302734e-06, "loss": 0.5525, "step": 157040 }, { "epoch": 0.9335378140770726, "grad_norm": 6.314260005950928, "learning_rate": 9.772734437143135e-06, "loss": 0.5279, "step": 157050 }, { "epoch": 0.933597256153741, "grad_norm": 5.091513156890869, "learning_rate": 9.772672587764316e-06, "loss": 0.5197, "step": 157060 }, { "epoch": 0.9336566982304094, "grad_norm": 5.427825450897217, "learning_rate": 9.772610730166386e-06, "loss": 0.462, "step": 157070 }, { "epoch": 0.9337161403070777, "grad_norm": 4.923829555511475, "learning_rate": 9.77254886434945e-06, "loss": 0.5624, "step": 157080 }, { "epoch": 0.9337755823837461, "grad_norm": 4.405542850494385, "learning_rate": 9.772486990313617e-06, "loss": 0.5427, "step": 157090 }, { "epoch": 0.9338350244604146, "grad_norm": 5.867160797119141, "learning_rate": 9.77242510805899e-06, "loss": 0.5188, "step": 157100 }, { "epoch": 0.933894466537083, "grad_norm": 5.6549153327941895, "learning_rate": 9.77236321758568e-06, "loss": 0.5759, "step": 157110 }, { "epoch": 0.9339539086137514, "grad_norm": 4.072176456451416, "learning_rate": 9.772301318893789e-06, "loss": 0.4861, "step": 157120 }, { "epoch": 0.9340133506904197, "grad_norm": 5.853249549865723, "learning_rate": 9.772239411983427e-06, "loss": 0.5418, "step": 157130 }, { "epoch": 0.9340727927670881, "grad_norm": 5.815901756286621, "learning_rate": 9.772177496854698e-06, "loss": 0.5029, "step": 157140 }, { "epoch": 0.9341322348437565, "grad_norm": 6.143062114715576, "learning_rate": 9.772115573507713e-06, "loss": 0.5022, "step": 157150 }, { "epoch": 0.9341916769204249, "grad_norm": 4.432927131652832, "learning_rate": 9.772053641942571e-06, "loss": 0.5437, "step": 157160 }, { "epoch": 0.9342511189970932, "grad_norm": 5.768055438995361, "learning_rate": 9.771991702159387e-06, "loss": 0.5219, "step": 157170 }, { "epoch": 0.9343105610737616, "grad_norm": 5.847385406494141, "learning_rate": 9.771929754158263e-06, "loss": 0.5744, "step": 157180 }, { "epoch": 0.9343700031504301, "grad_norm": 4.5477495193481445, "learning_rate": 9.771867797939306e-06, "loss": 0.5417, "step": 157190 }, { "epoch": 0.9344294452270985, "grad_norm": 4.55650520324707, "learning_rate": 9.771805833502623e-06, "loss": 0.5322, "step": 157200 }, { "epoch": 0.9344888873037669, "grad_norm": 4.712454319000244, "learning_rate": 9.771743860848322e-06, "loss": 0.5334, "step": 157210 }, { "epoch": 0.9345483293804352, "grad_norm": 4.995208740234375, "learning_rate": 9.771681879976508e-06, "loss": 0.5563, "step": 157220 }, { "epoch": 0.9346077714571036, "grad_norm": 4.8056640625, "learning_rate": 9.771619890887289e-06, "loss": 0.4891, "step": 157230 }, { "epoch": 0.934667213533772, "grad_norm": 5.854203701019287, "learning_rate": 9.77155789358077e-06, "loss": 0.5118, "step": 157240 }, { "epoch": 0.9347266556104404, "grad_norm": 4.947234153747559, "learning_rate": 9.77149588805706e-06, "loss": 0.5369, "step": 157250 }, { "epoch": 0.9347860976871089, "grad_norm": 5.686943054199219, "learning_rate": 9.771433874316264e-06, "loss": 0.5757, "step": 157260 }, { "epoch": 0.9348455397637772, "grad_norm": 5.420093059539795, "learning_rate": 9.77137185235849e-06, "loss": 0.4989, "step": 157270 }, { "epoch": 0.9349049818404456, "grad_norm": 5.157562255859375, "learning_rate": 9.771309822183845e-06, "loss": 0.5637, "step": 157280 }, { "epoch": 0.934964423917114, "grad_norm": 4.970663070678711, "learning_rate": 9.771247783792435e-06, "loss": 0.544, "step": 157290 }, { "epoch": 0.9350238659937824, "grad_norm": 5.786707401275635, "learning_rate": 9.771185737184366e-06, "loss": 0.4962, "step": 157300 }, { "epoch": 0.9350833080704507, "grad_norm": 3.5239601135253906, "learning_rate": 9.771123682359747e-06, "loss": 0.5624, "step": 157310 }, { "epoch": 0.9351427501471191, "grad_norm": 4.807792663574219, "learning_rate": 9.771061619318682e-06, "loss": 0.5746, "step": 157320 }, { "epoch": 0.9352021922237875, "grad_norm": 5.091519832611084, "learning_rate": 9.770999548061282e-06, "loss": 0.6231, "step": 157330 }, { "epoch": 0.935261634300456, "grad_norm": 5.524658203125, "learning_rate": 9.770937468587652e-06, "loss": 0.5458, "step": 157340 }, { "epoch": 0.9353210763771244, "grad_norm": 5.70798921585083, "learning_rate": 9.770875380897896e-06, "loss": 0.5773, "step": 157350 }, { "epoch": 0.9353805184537927, "grad_norm": 5.214469909667969, "learning_rate": 9.770813284992123e-06, "loss": 0.5389, "step": 157360 }, { "epoch": 0.9354399605304611, "grad_norm": 7.150290489196777, "learning_rate": 9.77075118087044e-06, "loss": 0.5866, "step": 157370 }, { "epoch": 0.9354994026071295, "grad_norm": 4.844553470611572, "learning_rate": 9.770689068532957e-06, "loss": 0.5387, "step": 157380 }, { "epoch": 0.9355588446837979, "grad_norm": 5.937662124633789, "learning_rate": 9.770626947979778e-06, "loss": 0.5581, "step": 157390 }, { "epoch": 0.9356182867604662, "grad_norm": 4.946098804473877, "learning_rate": 9.770564819211007e-06, "loss": 0.5025, "step": 157400 }, { "epoch": 0.9356777288371346, "grad_norm": 5.544974327087402, "learning_rate": 9.770502682226758e-06, "loss": 0.5083, "step": 157410 }, { "epoch": 0.935737170913803, "grad_norm": 5.727783203125, "learning_rate": 9.770440537027133e-06, "loss": 0.5543, "step": 157420 }, { "epoch": 0.9357966129904715, "grad_norm": 3.93001127243042, "learning_rate": 9.770378383612239e-06, "loss": 0.5635, "step": 157430 }, { "epoch": 0.9358560550671399, "grad_norm": 4.749018669128418, "learning_rate": 9.770316221982184e-06, "loss": 0.5353, "step": 157440 }, { "epoch": 0.9359154971438082, "grad_norm": 5.4343485832214355, "learning_rate": 9.770254052137076e-06, "loss": 0.532, "step": 157450 }, { "epoch": 0.9359749392204766, "grad_norm": 6.598933219909668, "learning_rate": 9.770191874077022e-06, "loss": 0.588, "step": 157460 }, { "epoch": 0.936034381297145, "grad_norm": 5.695801258087158, "learning_rate": 9.770129687802128e-06, "loss": 0.5007, "step": 157470 }, { "epoch": 0.9360938233738134, "grad_norm": 6.282686233520508, "learning_rate": 9.770067493312501e-06, "loss": 0.5651, "step": 157480 }, { "epoch": 0.9361532654504818, "grad_norm": 4.875092029571533, "learning_rate": 9.77000529060825e-06, "loss": 0.5438, "step": 157490 }, { "epoch": 0.9362127075271501, "grad_norm": 7.226460933685303, "learning_rate": 9.769943079689478e-06, "loss": 0.5834, "step": 157500 }, { "epoch": 0.9362721496038185, "grad_norm": 6.880227565765381, "learning_rate": 9.769880860556297e-06, "loss": 0.5977, "step": 157510 }, { "epoch": 0.936331591680487, "grad_norm": 5.504742622375488, "learning_rate": 9.769818633208812e-06, "loss": 0.5539, "step": 157520 }, { "epoch": 0.9363910337571554, "grad_norm": 5.036601543426514, "learning_rate": 9.769756397647129e-06, "loss": 0.5186, "step": 157530 }, { "epoch": 0.9364504758338237, "grad_norm": 3.830245018005371, "learning_rate": 9.769694153871359e-06, "loss": 0.5439, "step": 157540 }, { "epoch": 0.9365099179104921, "grad_norm": 6.7072224617004395, "learning_rate": 9.769631901881604e-06, "loss": 0.635, "step": 157550 }, { "epoch": 0.9365693599871605, "grad_norm": 4.61298131942749, "learning_rate": 9.769569641677974e-06, "loss": 0.4982, "step": 157560 }, { "epoch": 0.9366288020638289, "grad_norm": 7.1037726402282715, "learning_rate": 9.769507373260577e-06, "loss": 0.581, "step": 157570 }, { "epoch": 0.9366882441404973, "grad_norm": 4.853912830352783, "learning_rate": 9.769445096629518e-06, "loss": 0.5727, "step": 157580 }, { "epoch": 0.9367476862171656, "grad_norm": 5.666954517364502, "learning_rate": 9.769382811784907e-06, "loss": 0.5779, "step": 157590 }, { "epoch": 0.9368071282938341, "grad_norm": 6.887120246887207, "learning_rate": 9.769320518726847e-06, "loss": 0.5527, "step": 157600 }, { "epoch": 0.9368665703705025, "grad_norm": 6.245810508728027, "learning_rate": 9.769258217455451e-06, "loss": 0.5257, "step": 157610 }, { "epoch": 0.9369260124471709, "grad_norm": 5.3903632164001465, "learning_rate": 9.769195907970823e-06, "loss": 0.5219, "step": 157620 }, { "epoch": 0.9369854545238392, "grad_norm": 5.341495990753174, "learning_rate": 9.76913359027307e-06, "loss": 0.574, "step": 157630 }, { "epoch": 0.9370448966005076, "grad_norm": 4.4195556640625, "learning_rate": 9.7690712643623e-06, "loss": 0.4864, "step": 157640 }, { "epoch": 0.937104338677176, "grad_norm": 4.320705890655518, "learning_rate": 9.76900893023862e-06, "loss": 0.5689, "step": 157650 }, { "epoch": 0.9371637807538444, "grad_norm": 5.566338539123535, "learning_rate": 9.768946587902138e-06, "loss": 0.503, "step": 157660 }, { "epoch": 0.9372232228305128, "grad_norm": 5.00880241394043, "learning_rate": 9.768884237352959e-06, "loss": 0.5732, "step": 157670 }, { "epoch": 0.9372826649071812, "grad_norm": 4.007083415985107, "learning_rate": 9.768821878591195e-06, "loss": 0.5156, "step": 157680 }, { "epoch": 0.9373421069838496, "grad_norm": 5.223971366882324, "learning_rate": 9.768759511616948e-06, "loss": 0.5534, "step": 157690 }, { "epoch": 0.937401549060518, "grad_norm": 6.544863224029541, "learning_rate": 9.76869713643033e-06, "loss": 0.5664, "step": 157700 }, { "epoch": 0.9374609911371864, "grad_norm": 7.093938827514648, "learning_rate": 9.768634753031446e-06, "loss": 0.5285, "step": 157710 }, { "epoch": 0.9375204332138548, "grad_norm": 4.37667179107666, "learning_rate": 9.768572361420405e-06, "loss": 0.5499, "step": 157720 }, { "epoch": 0.9375798752905231, "grad_norm": 5.392961025238037, "learning_rate": 9.768509961597312e-06, "loss": 0.5567, "step": 157730 }, { "epoch": 0.9376393173671915, "grad_norm": 5.889958381652832, "learning_rate": 9.768447553562277e-06, "loss": 0.5364, "step": 157740 }, { "epoch": 0.9376987594438599, "grad_norm": 5.46966028213501, "learning_rate": 9.768385137315406e-06, "loss": 0.523, "step": 157750 }, { "epoch": 0.9377582015205284, "grad_norm": 5.958393096923828, "learning_rate": 9.768322712856806e-06, "loss": 0.5956, "step": 157760 }, { "epoch": 0.9378176435971967, "grad_norm": 4.961654186248779, "learning_rate": 9.768260280186586e-06, "loss": 0.5507, "step": 157770 }, { "epoch": 0.9378770856738651, "grad_norm": 4.474269866943359, "learning_rate": 9.768197839304853e-06, "loss": 0.5245, "step": 157780 }, { "epoch": 0.9379365277505335, "grad_norm": 5.3451948165893555, "learning_rate": 9.768135390211715e-06, "loss": 0.5472, "step": 157790 }, { "epoch": 0.9379959698272019, "grad_norm": 6.719992637634277, "learning_rate": 9.768072932907278e-06, "loss": 0.6061, "step": 157800 }, { "epoch": 0.9380554119038703, "grad_norm": 5.078988552093506, "learning_rate": 9.76801046739165e-06, "loss": 0.5607, "step": 157810 }, { "epoch": 0.9381148539805386, "grad_norm": 5.540809631347656, "learning_rate": 9.767947993664939e-06, "loss": 0.5715, "step": 157820 }, { "epoch": 0.938174296057207, "grad_norm": 7.180622100830078, "learning_rate": 9.767885511727255e-06, "loss": 0.5631, "step": 157830 }, { "epoch": 0.9382337381338755, "grad_norm": 4.113763332366943, "learning_rate": 9.7678230215787e-06, "loss": 0.5314, "step": 157840 }, { "epoch": 0.9382931802105439, "grad_norm": 5.202958106994629, "learning_rate": 9.767760523219387e-06, "loss": 0.5445, "step": 157850 }, { "epoch": 0.9383526222872123, "grad_norm": 5.990345001220703, "learning_rate": 9.767698016649421e-06, "loss": 0.564, "step": 157860 }, { "epoch": 0.9384120643638806, "grad_norm": 5.420602321624756, "learning_rate": 9.76763550186891e-06, "loss": 0.5338, "step": 157870 }, { "epoch": 0.938471506440549, "grad_norm": 6.660966396331787, "learning_rate": 9.767572978877962e-06, "loss": 0.5368, "step": 157880 }, { "epoch": 0.9385309485172174, "grad_norm": 5.814388275146484, "learning_rate": 9.767510447676684e-06, "loss": 0.5551, "step": 157890 }, { "epoch": 0.9385903905938858, "grad_norm": 5.2142486572265625, "learning_rate": 9.767447908265185e-06, "loss": 0.515, "step": 157900 }, { "epoch": 0.9386498326705541, "grad_norm": 5.043885707855225, "learning_rate": 9.767385360643572e-06, "loss": 0.5528, "step": 157910 }, { "epoch": 0.9387092747472225, "grad_norm": 6.597118854522705, "learning_rate": 9.767322804811952e-06, "loss": 0.5331, "step": 157920 }, { "epoch": 0.938768716823891, "grad_norm": 5.362523555755615, "learning_rate": 9.767260240770433e-06, "loss": 0.5812, "step": 157930 }, { "epoch": 0.9388281589005594, "grad_norm": 5.842498779296875, "learning_rate": 9.767197668519124e-06, "loss": 0.5318, "step": 157940 }, { "epoch": 0.9388876009772278, "grad_norm": 5.950606346130371, "learning_rate": 9.76713508805813e-06, "loss": 0.5572, "step": 157950 }, { "epoch": 0.9389470430538961, "grad_norm": 4.977675437927246, "learning_rate": 9.767072499387563e-06, "loss": 0.5634, "step": 157960 }, { "epoch": 0.9390064851305645, "grad_norm": 5.700417518615723, "learning_rate": 9.767009902507526e-06, "loss": 0.5641, "step": 157970 }, { "epoch": 0.9390659272072329, "grad_norm": 5.710047721862793, "learning_rate": 9.76694729741813e-06, "loss": 0.5109, "step": 157980 }, { "epoch": 0.9391253692839013, "grad_norm": 5.228566646575928, "learning_rate": 9.766884684119483e-06, "loss": 0.5393, "step": 157990 }, { "epoch": 0.9391848113605696, "grad_norm": 4.244149208068848, "learning_rate": 9.766822062611692e-06, "loss": 0.5669, "step": 158000 }, { "epoch": 0.939244253437238, "grad_norm": 4.263321876525879, "learning_rate": 9.766759432894864e-06, "loss": 0.5404, "step": 158010 }, { "epoch": 0.9393036955139065, "grad_norm": 5.942138195037842, "learning_rate": 9.766696794969107e-06, "loss": 0.567, "step": 158020 }, { "epoch": 0.9393631375905749, "grad_norm": 5.565075874328613, "learning_rate": 9.766634148834528e-06, "loss": 0.5291, "step": 158030 }, { "epoch": 0.9394225796672433, "grad_norm": 4.993972301483154, "learning_rate": 9.766571494491238e-06, "loss": 0.5345, "step": 158040 }, { "epoch": 0.9394820217439116, "grad_norm": 5.396513938903809, "learning_rate": 9.766508831939343e-06, "loss": 0.5361, "step": 158050 }, { "epoch": 0.93954146382058, "grad_norm": 5.9059882164001465, "learning_rate": 9.766446161178951e-06, "loss": 0.5399, "step": 158060 }, { "epoch": 0.9396009058972484, "grad_norm": 4.015119552612305, "learning_rate": 9.76638348221017e-06, "loss": 0.5048, "step": 158070 }, { "epoch": 0.9396603479739168, "grad_norm": 6.480324745178223, "learning_rate": 9.766320795033108e-06, "loss": 0.5767, "step": 158080 }, { "epoch": 0.9397197900505853, "grad_norm": 4.170800685882568, "learning_rate": 9.766258099647872e-06, "loss": 0.4961, "step": 158090 }, { "epoch": 0.9397792321272536, "grad_norm": 3.9575905799865723, "learning_rate": 9.766195396054572e-06, "loss": 0.4887, "step": 158100 }, { "epoch": 0.939838674203922, "grad_norm": 4.437910556793213, "learning_rate": 9.766132684253315e-06, "loss": 0.5633, "step": 158110 }, { "epoch": 0.9398981162805904, "grad_norm": 5.679886341094971, "learning_rate": 9.766069964244208e-06, "loss": 0.591, "step": 158120 }, { "epoch": 0.9399575583572588, "grad_norm": 4.848203182220459, "learning_rate": 9.766007236027359e-06, "loss": 0.5248, "step": 158130 }, { "epoch": 0.9400170004339271, "grad_norm": 5.5104475021362305, "learning_rate": 9.76594449960288e-06, "loss": 0.5267, "step": 158140 }, { "epoch": 0.9400764425105955, "grad_norm": 4.803684234619141, "learning_rate": 9.765881754970873e-06, "loss": 0.5329, "step": 158150 }, { "epoch": 0.9401358845872639, "grad_norm": 7.424907684326172, "learning_rate": 9.765819002131451e-06, "loss": 0.5431, "step": 158160 }, { "epoch": 0.9401953266639324, "grad_norm": 4.536755084991455, "learning_rate": 9.765756241084718e-06, "loss": 0.5268, "step": 158170 }, { "epoch": 0.9402547687406008, "grad_norm": 4.78821325302124, "learning_rate": 9.765693471830785e-06, "loss": 0.5614, "step": 158180 }, { "epoch": 0.9403142108172691, "grad_norm": 4.292352676391602, "learning_rate": 9.765630694369759e-06, "loss": 0.5042, "step": 158190 }, { "epoch": 0.9403736528939375, "grad_norm": 5.810112476348877, "learning_rate": 9.765567908701748e-06, "loss": 0.5115, "step": 158200 }, { "epoch": 0.9404330949706059, "grad_norm": 4.732001304626465, "learning_rate": 9.765505114826861e-06, "loss": 0.5343, "step": 158210 }, { "epoch": 0.9404925370472743, "grad_norm": 6.804202079772949, "learning_rate": 9.765442312745206e-06, "loss": 0.5685, "step": 158220 }, { "epoch": 0.9405519791239427, "grad_norm": 5.34971809387207, "learning_rate": 9.76537950245689e-06, "loss": 0.5303, "step": 158230 }, { "epoch": 0.940611421200611, "grad_norm": 4.392396450042725, "learning_rate": 9.765316683962024e-06, "loss": 0.5216, "step": 158240 }, { "epoch": 0.9406708632772794, "grad_norm": 4.8531389236450195, "learning_rate": 9.76525385726071e-06, "loss": 0.5646, "step": 158250 }, { "epoch": 0.9407303053539479, "grad_norm": 6.3763909339904785, "learning_rate": 9.765191022353064e-06, "loss": 0.5736, "step": 158260 }, { "epoch": 0.9407897474306163, "grad_norm": 5.042423248291016, "learning_rate": 9.765128179239189e-06, "loss": 0.5594, "step": 158270 }, { "epoch": 0.9408491895072846, "grad_norm": 4.418608665466309, "learning_rate": 9.765065327919195e-06, "loss": 0.4582, "step": 158280 }, { "epoch": 0.940908631583953, "grad_norm": 5.4911346435546875, "learning_rate": 9.76500246839319e-06, "loss": 0.6133, "step": 158290 }, { "epoch": 0.9409680736606214, "grad_norm": 5.7447967529296875, "learning_rate": 9.76493960066128e-06, "loss": 0.5265, "step": 158300 }, { "epoch": 0.9410275157372898, "grad_norm": 5.683437824249268, "learning_rate": 9.764876724723578e-06, "loss": 0.4946, "step": 158310 }, { "epoch": 0.9410869578139582, "grad_norm": 4.7041544914245605, "learning_rate": 9.76481384058019e-06, "loss": 0.5781, "step": 158320 }, { "epoch": 0.9411463998906265, "grad_norm": 5.588200569152832, "learning_rate": 9.764750948231223e-06, "loss": 0.5103, "step": 158330 }, { "epoch": 0.941205841967295, "grad_norm": 5.2841691970825195, "learning_rate": 9.764688047676786e-06, "loss": 0.4769, "step": 158340 }, { "epoch": 0.9412652840439634, "grad_norm": 5.189261436462402, "learning_rate": 9.764625138916988e-06, "loss": 0.5645, "step": 158350 }, { "epoch": 0.9413247261206318, "grad_norm": 4.85029935836792, "learning_rate": 9.764562221951937e-06, "loss": 0.4966, "step": 158360 }, { "epoch": 0.9413841681973001, "grad_norm": 6.705236911773682, "learning_rate": 9.764499296781742e-06, "loss": 0.5586, "step": 158370 }, { "epoch": 0.9414436102739685, "grad_norm": 5.891135215759277, "learning_rate": 9.76443636340651e-06, "loss": 0.5896, "step": 158380 }, { "epoch": 0.9415030523506369, "grad_norm": 5.238736152648926, "learning_rate": 9.76437342182635e-06, "loss": 0.5873, "step": 158390 }, { "epoch": 0.9415624944273053, "grad_norm": 7.501045227050781, "learning_rate": 9.764310472041371e-06, "loss": 0.5903, "step": 158400 }, { "epoch": 0.9416219365039737, "grad_norm": 7.1500725746154785, "learning_rate": 9.76424751405168e-06, "loss": 0.5355, "step": 158410 }, { "epoch": 0.941681378580642, "grad_norm": 6.010628700256348, "learning_rate": 9.764184547857388e-06, "loss": 0.5263, "step": 158420 }, { "epoch": 0.9417408206573105, "grad_norm": 6.6127119064331055, "learning_rate": 9.764121573458601e-06, "loss": 0.5411, "step": 158430 }, { "epoch": 0.9418002627339789, "grad_norm": 5.193183898925781, "learning_rate": 9.764058590855427e-06, "loss": 0.6318, "step": 158440 }, { "epoch": 0.9418597048106473, "grad_norm": 5.332497596740723, "learning_rate": 9.763995600047977e-06, "loss": 0.569, "step": 158450 }, { "epoch": 0.9419191468873157, "grad_norm": 5.2261271476745605, "learning_rate": 9.763932601036359e-06, "loss": 0.5448, "step": 158460 }, { "epoch": 0.941978588963984, "grad_norm": 4.435274124145508, "learning_rate": 9.763869593820679e-06, "loss": 0.5508, "step": 158470 }, { "epoch": 0.9420380310406524, "grad_norm": 6.119592666625977, "learning_rate": 9.763806578401047e-06, "loss": 0.4912, "step": 158480 }, { "epoch": 0.9420974731173208, "grad_norm": 5.44588041305542, "learning_rate": 9.763743554777573e-06, "loss": 0.6322, "step": 158490 }, { "epoch": 0.9421569151939893, "grad_norm": 4.066866874694824, "learning_rate": 9.763680522950364e-06, "loss": 0.5444, "step": 158500 }, { "epoch": 0.9422163572706576, "grad_norm": 4.994811058044434, "learning_rate": 9.763617482919527e-06, "loss": 0.5354, "step": 158510 }, { "epoch": 0.942275799347326, "grad_norm": 4.111949920654297, "learning_rate": 9.763554434685174e-06, "loss": 0.5279, "step": 158520 }, { "epoch": 0.9423352414239944, "grad_norm": 4.8145575523376465, "learning_rate": 9.763491378247412e-06, "loss": 0.5358, "step": 158530 }, { "epoch": 0.9423946835006628, "grad_norm": 4.417898178100586, "learning_rate": 9.76342831360635e-06, "loss": 0.5427, "step": 158540 }, { "epoch": 0.9424541255773312, "grad_norm": 5.049687385559082, "learning_rate": 9.763365240762093e-06, "loss": 0.5483, "step": 158550 }, { "epoch": 0.9425135676539995, "grad_norm": 4.182201862335205, "learning_rate": 9.763302159714756e-06, "loss": 0.5364, "step": 158560 }, { "epoch": 0.9425730097306679, "grad_norm": 4.196596145629883, "learning_rate": 9.763239070464444e-06, "loss": 0.577, "step": 158570 }, { "epoch": 0.9426324518073363, "grad_norm": 5.5695672035217285, "learning_rate": 9.763175973011263e-06, "loss": 0.5827, "step": 158580 }, { "epoch": 0.9426918938840048, "grad_norm": 4.251981735229492, "learning_rate": 9.763112867355327e-06, "loss": 0.5296, "step": 158590 }, { "epoch": 0.9427513359606732, "grad_norm": 4.87748908996582, "learning_rate": 9.763049753496742e-06, "loss": 0.5225, "step": 158600 }, { "epoch": 0.9428107780373415, "grad_norm": 4.730001926422119, "learning_rate": 9.762986631435616e-06, "loss": 0.5373, "step": 158610 }, { "epoch": 0.9428702201140099, "grad_norm": 4.869072437286377, "learning_rate": 9.762923501172062e-06, "loss": 0.5355, "step": 158620 }, { "epoch": 0.9429296621906783, "grad_norm": 7.0775017738342285, "learning_rate": 9.76286036270618e-06, "loss": 0.5713, "step": 158630 }, { "epoch": 0.9429891042673467, "grad_norm": 4.494077682495117, "learning_rate": 9.762797216038089e-06, "loss": 0.5477, "step": 158640 }, { "epoch": 0.943048546344015, "grad_norm": 3.6982786655426025, "learning_rate": 9.762734061167892e-06, "loss": 0.5232, "step": 158650 }, { "epoch": 0.9431079884206834, "grad_norm": 6.374871253967285, "learning_rate": 9.762670898095697e-06, "loss": 0.5483, "step": 158660 }, { "epoch": 0.9431674304973519, "grad_norm": 3.6853065490722656, "learning_rate": 9.762607726821616e-06, "loss": 0.5517, "step": 158670 }, { "epoch": 0.9432268725740203, "grad_norm": 6.045068740844727, "learning_rate": 9.762544547345756e-06, "loss": 0.5657, "step": 158680 }, { "epoch": 0.9432863146506887, "grad_norm": 6.102776050567627, "learning_rate": 9.762481359668224e-06, "loss": 0.5104, "step": 158690 }, { "epoch": 0.943345756727357, "grad_norm": 4.692934513092041, "learning_rate": 9.762418163789132e-06, "loss": 0.4929, "step": 158700 }, { "epoch": 0.9434051988040254, "grad_norm": 5.302958965301514, "learning_rate": 9.76235495970859e-06, "loss": 0.5848, "step": 158710 }, { "epoch": 0.9434646408806938, "grad_norm": 4.64976692199707, "learning_rate": 9.762291747426703e-06, "loss": 0.536, "step": 158720 }, { "epoch": 0.9435240829573622, "grad_norm": 5.806651592254639, "learning_rate": 9.762228526943578e-06, "loss": 0.5999, "step": 158730 }, { "epoch": 0.9435835250340305, "grad_norm": 5.6298980712890625, "learning_rate": 9.762165298259332e-06, "loss": 0.5592, "step": 158740 }, { "epoch": 0.943642967110699, "grad_norm": 5.0581207275390625, "learning_rate": 9.762102061374067e-06, "loss": 0.5513, "step": 158750 }, { "epoch": 0.9437024091873674, "grad_norm": 5.636331081390381, "learning_rate": 9.762038816287894e-06, "loss": 0.5191, "step": 158760 }, { "epoch": 0.9437618512640358, "grad_norm": 5.387300968170166, "learning_rate": 9.761975563000924e-06, "loss": 0.5521, "step": 158770 }, { "epoch": 0.9438212933407042, "grad_norm": 4.70656156539917, "learning_rate": 9.761912301513261e-06, "loss": 0.55, "step": 158780 }, { "epoch": 0.9438807354173725, "grad_norm": 6.37386417388916, "learning_rate": 9.761849031825018e-06, "loss": 0.572, "step": 158790 }, { "epoch": 0.9439401774940409, "grad_norm": 5.056736469268799, "learning_rate": 9.761785753936304e-06, "loss": 0.554, "step": 158800 }, { "epoch": 0.9439996195707093, "grad_norm": 4.100982189178467, "learning_rate": 9.761722467847224e-06, "loss": 0.5544, "step": 158810 }, { "epoch": 0.9440590616473777, "grad_norm": 5.159456253051758, "learning_rate": 9.76165917355789e-06, "loss": 0.5869, "step": 158820 }, { "epoch": 0.9441185037240462, "grad_norm": 5.228684902191162, "learning_rate": 9.761595871068415e-06, "loss": 0.5497, "step": 158830 }, { "epoch": 0.9441779458007145, "grad_norm": 6.150053977966309, "learning_rate": 9.7615325603789e-06, "loss": 0.4956, "step": 158840 }, { "epoch": 0.9442373878773829, "grad_norm": 5.99741792678833, "learning_rate": 9.761469241489459e-06, "loss": 0.5263, "step": 158850 }, { "epoch": 0.9442968299540513, "grad_norm": 4.932938575744629, "learning_rate": 9.7614059144002e-06, "loss": 0.5374, "step": 158860 }, { "epoch": 0.9443562720307197, "grad_norm": 5.864940643310547, "learning_rate": 9.761342579111231e-06, "loss": 0.5538, "step": 158870 }, { "epoch": 0.944415714107388, "grad_norm": 6.065982341766357, "learning_rate": 9.761279235622663e-06, "loss": 0.5306, "step": 158880 }, { "epoch": 0.9444751561840564, "grad_norm": 5.6912922859191895, "learning_rate": 9.761215883934603e-06, "loss": 0.5303, "step": 158890 }, { "epoch": 0.9445345982607248, "grad_norm": 4.967931270599365, "learning_rate": 9.761152524047161e-06, "loss": 0.5269, "step": 158900 }, { "epoch": 0.9445940403373932, "grad_norm": 6.53393030166626, "learning_rate": 9.761089155960447e-06, "loss": 0.5545, "step": 158910 }, { "epoch": 0.9446534824140617, "grad_norm": 5.300317287445068, "learning_rate": 9.761025779674568e-06, "loss": 0.5405, "step": 158920 }, { "epoch": 0.94471292449073, "grad_norm": 5.950881004333496, "learning_rate": 9.760962395189637e-06, "loss": 0.5287, "step": 158930 }, { "epoch": 0.9447723665673984, "grad_norm": 5.197969436645508, "learning_rate": 9.76089900250576e-06, "loss": 0.5257, "step": 158940 }, { "epoch": 0.9448318086440668, "grad_norm": 4.269737720489502, "learning_rate": 9.760835601623046e-06, "loss": 0.5363, "step": 158950 }, { "epoch": 0.9448912507207352, "grad_norm": 4.669903755187988, "learning_rate": 9.760772192541605e-06, "loss": 0.4989, "step": 158960 }, { "epoch": 0.9449506927974036, "grad_norm": 5.483562469482422, "learning_rate": 9.760708775261547e-06, "loss": 0.6012, "step": 158970 }, { "epoch": 0.9450101348740719, "grad_norm": 4.7641425132751465, "learning_rate": 9.76064534978298e-06, "loss": 0.5273, "step": 158980 }, { "epoch": 0.9450695769507403, "grad_norm": 5.2548017501831055, "learning_rate": 9.760581916106013e-06, "loss": 0.5442, "step": 158990 }, { "epoch": 0.9451290190274088, "grad_norm": 5.2193098068237305, "learning_rate": 9.760518474230759e-06, "loss": 0.5754, "step": 159000 }, { "epoch": 0.9451884611040772, "grad_norm": 4.5240583419799805, "learning_rate": 9.76045502415732e-06, "loss": 0.5244, "step": 159010 }, { "epoch": 0.9452479031807455, "grad_norm": 4.416763782501221, "learning_rate": 9.760391565885811e-06, "loss": 0.5189, "step": 159020 }, { "epoch": 0.9453073452574139, "grad_norm": 4.136495590209961, "learning_rate": 9.76032809941634e-06, "loss": 0.5592, "step": 159030 }, { "epoch": 0.9453667873340823, "grad_norm": 4.397975921630859, "learning_rate": 9.760264624749017e-06, "loss": 0.5461, "step": 159040 }, { "epoch": 0.9454262294107507, "grad_norm": 4.0711164474487305, "learning_rate": 9.760201141883949e-06, "loss": 0.5508, "step": 159050 }, { "epoch": 0.9454856714874191, "grad_norm": 5.475410461425781, "learning_rate": 9.760137650821246e-06, "loss": 0.5549, "step": 159060 }, { "epoch": 0.9455451135640874, "grad_norm": 6.3437652587890625, "learning_rate": 9.76007415156102e-06, "loss": 0.5541, "step": 159070 }, { "epoch": 0.9456045556407559, "grad_norm": 5.128387451171875, "learning_rate": 9.760010644103378e-06, "loss": 0.5811, "step": 159080 }, { "epoch": 0.9456639977174243, "grad_norm": 4.506556510925293, "learning_rate": 9.759947128448428e-06, "loss": 0.5504, "step": 159090 }, { "epoch": 0.9457234397940927, "grad_norm": 6.862583160400391, "learning_rate": 9.759883604596283e-06, "loss": 0.5465, "step": 159100 }, { "epoch": 0.945782881870761, "grad_norm": 4.646481990814209, "learning_rate": 9.75982007254705e-06, "loss": 0.5135, "step": 159110 }, { "epoch": 0.9458423239474294, "grad_norm": 5.117646217346191, "learning_rate": 9.759756532300838e-06, "loss": 0.5167, "step": 159120 }, { "epoch": 0.9459017660240978, "grad_norm": 4.18489933013916, "learning_rate": 9.759692983857758e-06, "loss": 0.5268, "step": 159130 }, { "epoch": 0.9459612081007662, "grad_norm": 4.139490127563477, "learning_rate": 9.759629427217918e-06, "loss": 0.534, "step": 159140 }, { "epoch": 0.9460206501774346, "grad_norm": 4.9488725662231445, "learning_rate": 9.75956586238143e-06, "loss": 0.5409, "step": 159150 }, { "epoch": 0.946080092254103, "grad_norm": 5.484956741333008, "learning_rate": 9.759502289348399e-06, "loss": 0.5308, "step": 159160 }, { "epoch": 0.9461395343307714, "grad_norm": 5.6371941566467285, "learning_rate": 9.75943870811894e-06, "loss": 0.5332, "step": 159170 }, { "epoch": 0.9461989764074398, "grad_norm": 5.10162878036499, "learning_rate": 9.759375118693157e-06, "loss": 0.5069, "step": 159180 }, { "epoch": 0.9462584184841082, "grad_norm": 4.0133185386657715, "learning_rate": 9.759311521071164e-06, "loss": 0.5246, "step": 159190 }, { "epoch": 0.9463178605607766, "grad_norm": 4.61566686630249, "learning_rate": 9.759247915253069e-06, "loss": 0.5878, "step": 159200 }, { "epoch": 0.9463773026374449, "grad_norm": 6.166536331176758, "learning_rate": 9.75918430123898e-06, "loss": 0.5599, "step": 159210 }, { "epoch": 0.9464367447141133, "grad_norm": 5.8814616203308105, "learning_rate": 9.759120679029008e-06, "loss": 0.5188, "step": 159220 }, { "epoch": 0.9464961867907817, "grad_norm": 5.015344619750977, "learning_rate": 9.759057048623262e-06, "loss": 0.5288, "step": 159230 }, { "epoch": 0.9465556288674501, "grad_norm": 5.495943069458008, "learning_rate": 9.758993410021853e-06, "loss": 0.4875, "step": 159240 }, { "epoch": 0.9466150709441185, "grad_norm": 5.6695709228515625, "learning_rate": 9.758929763224888e-06, "loss": 0.5227, "step": 159250 }, { "epoch": 0.9466745130207869, "grad_norm": 4.589025497436523, "learning_rate": 9.75886610823248e-06, "loss": 0.4949, "step": 159260 }, { "epoch": 0.9467339550974553, "grad_norm": 4.673686504364014, "learning_rate": 9.758802445044737e-06, "loss": 0.5388, "step": 159270 }, { "epoch": 0.9467933971741237, "grad_norm": 4.689493656158447, "learning_rate": 9.758738773661767e-06, "loss": 0.5033, "step": 159280 }, { "epoch": 0.9468528392507921, "grad_norm": 6.398561000823975, "learning_rate": 9.75867509408368e-06, "loss": 0.5553, "step": 159290 }, { "epoch": 0.9469122813274604, "grad_norm": 4.95973539352417, "learning_rate": 9.758611406310588e-06, "loss": 0.524, "step": 159300 }, { "epoch": 0.9469717234041288, "grad_norm": 4.411568641662598, "learning_rate": 9.7585477103426e-06, "loss": 0.5116, "step": 159310 }, { "epoch": 0.9470311654807972, "grad_norm": 7.714052677154541, "learning_rate": 9.758484006179825e-06, "loss": 0.5766, "step": 159320 }, { "epoch": 0.9470906075574657, "grad_norm": 3.192331314086914, "learning_rate": 9.758420293822371e-06, "loss": 0.5184, "step": 159330 }, { "epoch": 0.9471500496341341, "grad_norm": 5.4638848304748535, "learning_rate": 9.758356573270351e-06, "loss": 0.5403, "step": 159340 }, { "epoch": 0.9472094917108024, "grad_norm": 6.26917839050293, "learning_rate": 9.758292844523874e-06, "loss": 0.5431, "step": 159350 }, { "epoch": 0.9472689337874708, "grad_norm": 5.613458156585693, "learning_rate": 9.758229107583047e-06, "loss": 0.5638, "step": 159360 }, { "epoch": 0.9473283758641392, "grad_norm": 5.114073276519775, "learning_rate": 9.758165362447982e-06, "loss": 0.4806, "step": 159370 }, { "epoch": 0.9473878179408076, "grad_norm": 4.454090118408203, "learning_rate": 9.75810160911879e-06, "loss": 0.4855, "step": 159380 }, { "epoch": 0.9474472600174759, "grad_norm": 5.944161415100098, "learning_rate": 9.758037847595579e-06, "loss": 0.5293, "step": 159390 }, { "epoch": 0.9475067020941443, "grad_norm": 3.8501267433166504, "learning_rate": 9.757974077878458e-06, "loss": 0.5364, "step": 159400 }, { "epoch": 0.9475661441708128, "grad_norm": 4.176366806030273, "learning_rate": 9.757910299967537e-06, "loss": 0.5341, "step": 159410 }, { "epoch": 0.9476255862474812, "grad_norm": 6.64692497253418, "learning_rate": 9.75784651386293e-06, "loss": 0.5573, "step": 159420 }, { "epoch": 0.9476850283241496, "grad_norm": 5.002485275268555, "learning_rate": 9.757782719564742e-06, "loss": 0.5269, "step": 159430 }, { "epoch": 0.9477444704008179, "grad_norm": 4.703385353088379, "learning_rate": 9.757718917073084e-06, "loss": 0.5786, "step": 159440 }, { "epoch": 0.9478039124774863, "grad_norm": 5.000678062438965, "learning_rate": 9.757655106388067e-06, "loss": 0.5352, "step": 159450 }, { "epoch": 0.9478633545541547, "grad_norm": 5.339877128601074, "learning_rate": 9.7575912875098e-06, "loss": 0.5155, "step": 159460 }, { "epoch": 0.9479227966308231, "grad_norm": 3.8016695976257324, "learning_rate": 9.757527460438392e-06, "loss": 0.554, "step": 159470 }, { "epoch": 0.9479822387074914, "grad_norm": 5.482686519622803, "learning_rate": 9.757463625173956e-06, "loss": 0.5121, "step": 159480 }, { "epoch": 0.9480416807841598, "grad_norm": 5.7613420486450195, "learning_rate": 9.757399781716598e-06, "loss": 0.6204, "step": 159490 }, { "epoch": 0.9481011228608283, "grad_norm": 4.780327796936035, "learning_rate": 9.757335930066431e-06, "loss": 0.5728, "step": 159500 }, { "epoch": 0.9481605649374967, "grad_norm": 5.22382116317749, "learning_rate": 9.757272070223564e-06, "loss": 0.4847, "step": 159510 }, { "epoch": 0.9482200070141651, "grad_norm": 5.9664459228515625, "learning_rate": 9.757208202188107e-06, "loss": 0.5502, "step": 159520 }, { "epoch": 0.9482794490908334, "grad_norm": 3.837799072265625, "learning_rate": 9.757144325960168e-06, "loss": 0.5127, "step": 159530 }, { "epoch": 0.9483388911675018, "grad_norm": 5.213733196258545, "learning_rate": 9.757080441539861e-06, "loss": 0.522, "step": 159540 }, { "epoch": 0.9483983332441702, "grad_norm": 9.128089904785156, "learning_rate": 9.757016548927295e-06, "loss": 0.5637, "step": 159550 }, { "epoch": 0.9484577753208386, "grad_norm": 5.64396333694458, "learning_rate": 9.756952648122576e-06, "loss": 0.5449, "step": 159560 }, { "epoch": 0.948517217397507, "grad_norm": 4.976240634918213, "learning_rate": 9.756888739125819e-06, "loss": 0.5593, "step": 159570 }, { "epoch": 0.9485766594741754, "grad_norm": 5.0148186683654785, "learning_rate": 9.75682482193713e-06, "loss": 0.5347, "step": 159580 }, { "epoch": 0.9486361015508438, "grad_norm": 4.46071195602417, "learning_rate": 9.756760896556623e-06, "loss": 0.5751, "step": 159590 }, { "epoch": 0.9486955436275122, "grad_norm": 5.888238906860352, "learning_rate": 9.756696962984404e-06, "loss": 0.5134, "step": 159600 }, { "epoch": 0.9487549857041806, "grad_norm": 4.3603949546813965, "learning_rate": 9.756633021220587e-06, "loss": 0.4581, "step": 159610 }, { "epoch": 0.9488144277808489, "grad_norm": 5.0164475440979, "learning_rate": 9.75656907126528e-06, "loss": 0.4768, "step": 159620 }, { "epoch": 0.9488738698575173, "grad_norm": 4.888012886047363, "learning_rate": 9.756505113118595e-06, "loss": 0.607, "step": 159630 }, { "epoch": 0.9489333119341857, "grad_norm": 4.824927806854248, "learning_rate": 9.756441146780638e-06, "loss": 0.5547, "step": 159640 }, { "epoch": 0.9489927540108541, "grad_norm": 4.972911357879639, "learning_rate": 9.756377172251523e-06, "loss": 0.5644, "step": 159650 }, { "epoch": 0.9490521960875226, "grad_norm": 5.3849406242370605, "learning_rate": 9.75631318953136e-06, "loss": 0.5147, "step": 159660 }, { "epoch": 0.9491116381641909, "grad_norm": 6.652231216430664, "learning_rate": 9.756249198620257e-06, "loss": 0.562, "step": 159670 }, { "epoch": 0.9491710802408593, "grad_norm": 6.95232629776001, "learning_rate": 9.756185199518325e-06, "loss": 0.5022, "step": 159680 }, { "epoch": 0.9492305223175277, "grad_norm": 4.674924373626709, "learning_rate": 9.756121192225676e-06, "loss": 0.5143, "step": 159690 }, { "epoch": 0.9492899643941961, "grad_norm": 5.109325885772705, "learning_rate": 9.756057176742417e-06, "loss": 0.4801, "step": 159700 }, { "epoch": 0.9493494064708645, "grad_norm": 5.742983818054199, "learning_rate": 9.75599315306866e-06, "loss": 0.4616, "step": 159710 }, { "epoch": 0.9494088485475328, "grad_norm": 5.749996185302734, "learning_rate": 9.755929121204516e-06, "loss": 0.5299, "step": 159720 }, { "epoch": 0.9494682906242012, "grad_norm": 5.228163719177246, "learning_rate": 9.755865081150097e-06, "loss": 0.5521, "step": 159730 }, { "epoch": 0.9495277327008697, "grad_norm": 4.4439473152160645, "learning_rate": 9.755801032905509e-06, "loss": 0.5406, "step": 159740 }, { "epoch": 0.9495871747775381, "grad_norm": 6.915992259979248, "learning_rate": 9.755736976470865e-06, "loss": 0.5411, "step": 159750 }, { "epoch": 0.9496466168542064, "grad_norm": 4.236067295074463, "learning_rate": 9.755672911846272e-06, "loss": 0.5298, "step": 159760 }, { "epoch": 0.9497060589308748, "grad_norm": 5.360805034637451, "learning_rate": 9.755608839031846e-06, "loss": 0.5689, "step": 159770 }, { "epoch": 0.9497655010075432, "grad_norm": 6.289094924926758, "learning_rate": 9.755544758027691e-06, "loss": 0.5111, "step": 159780 }, { "epoch": 0.9498249430842116, "grad_norm": 5.776357173919678, "learning_rate": 9.75548066883392e-06, "loss": 0.5138, "step": 159790 }, { "epoch": 0.94988438516088, "grad_norm": 4.117271423339844, "learning_rate": 9.755416571450646e-06, "loss": 0.46, "step": 159800 }, { "epoch": 0.9499438272375483, "grad_norm": 5.209562301635742, "learning_rate": 9.755352465877979e-06, "loss": 0.5524, "step": 159810 }, { "epoch": 0.9500032693142167, "grad_norm": 5.757050037384033, "learning_rate": 9.755288352116026e-06, "loss": 0.5709, "step": 159820 }, { "epoch": 0.9500627113908852, "grad_norm": 4.570702075958252, "learning_rate": 9.755224230164898e-06, "loss": 0.5225, "step": 159830 }, { "epoch": 0.9501221534675536, "grad_norm": 6.016123294830322, "learning_rate": 9.755160100024708e-06, "loss": 0.5225, "step": 159840 }, { "epoch": 0.9501815955442219, "grad_norm": 4.904011249542236, "learning_rate": 9.755095961695562e-06, "loss": 0.5229, "step": 159850 }, { "epoch": 0.9502410376208903, "grad_norm": 5.290437698364258, "learning_rate": 9.755031815177577e-06, "loss": 0.5588, "step": 159860 }, { "epoch": 0.9503004796975587, "grad_norm": 4.964663028717041, "learning_rate": 9.754967660470858e-06, "loss": 0.5065, "step": 159870 }, { "epoch": 0.9503599217742271, "grad_norm": 5.51555061340332, "learning_rate": 9.754903497575519e-06, "loss": 0.5575, "step": 159880 }, { "epoch": 0.9504193638508955, "grad_norm": 4.571879863739014, "learning_rate": 9.754839326491667e-06, "loss": 0.5434, "step": 159890 }, { "epoch": 0.9504788059275638, "grad_norm": 5.2481865882873535, "learning_rate": 9.754775147219415e-06, "loss": 0.55, "step": 159900 }, { "epoch": 0.9505382480042323, "grad_norm": 5.000560760498047, "learning_rate": 9.754710959758873e-06, "loss": 0.5171, "step": 159910 }, { "epoch": 0.9505976900809007, "grad_norm": 5.573334693908691, "learning_rate": 9.75464676411015e-06, "loss": 0.5541, "step": 159920 }, { "epoch": 0.9506571321575691, "grad_norm": 6.655348300933838, "learning_rate": 9.75458256027336e-06, "loss": 0.5602, "step": 159930 }, { "epoch": 0.9507165742342375, "grad_norm": 6.3418426513671875, "learning_rate": 9.754518348248611e-06, "loss": 0.5462, "step": 159940 }, { "epoch": 0.9507760163109058, "grad_norm": 4.752144813537598, "learning_rate": 9.754454128036013e-06, "loss": 0.5064, "step": 159950 }, { "epoch": 0.9508354583875742, "grad_norm": 4.471329212188721, "learning_rate": 9.75438989963568e-06, "loss": 0.4945, "step": 159960 }, { "epoch": 0.9508949004642426, "grad_norm": 4.979227542877197, "learning_rate": 9.754325663047717e-06, "loss": 0.5319, "step": 159970 }, { "epoch": 0.950954342540911, "grad_norm": 3.6722962856292725, "learning_rate": 9.754261418272241e-06, "loss": 0.5224, "step": 159980 }, { "epoch": 0.9510137846175793, "grad_norm": 4.44071626663208, "learning_rate": 9.754197165309358e-06, "loss": 0.5756, "step": 159990 }, { "epoch": 0.9510732266942478, "grad_norm": 5.516607761383057, "learning_rate": 9.75413290415918e-06, "loss": 0.5927, "step": 160000 }, { "epoch": 0.9511326687709162, "grad_norm": 6.485620498657227, "learning_rate": 9.754068634821818e-06, "loss": 0.5979, "step": 160010 }, { "epoch": 0.9511921108475846, "grad_norm": 4.1509857177734375, "learning_rate": 9.754004357297384e-06, "loss": 0.4689, "step": 160020 }, { "epoch": 0.951251552924253, "grad_norm": 5.391861915588379, "learning_rate": 9.753940071585986e-06, "loss": 0.5226, "step": 160030 }, { "epoch": 0.9513109950009213, "grad_norm": 5.265078544616699, "learning_rate": 9.753875777687735e-06, "loss": 0.5093, "step": 160040 }, { "epoch": 0.9513704370775897, "grad_norm": 6.836659908294678, "learning_rate": 9.753811475602745e-06, "loss": 0.5805, "step": 160050 }, { "epoch": 0.9514298791542581, "grad_norm": 5.277588844299316, "learning_rate": 9.753747165331124e-06, "loss": 0.538, "step": 160060 }, { "epoch": 0.9514893212309266, "grad_norm": 4.507002830505371, "learning_rate": 9.753682846872982e-06, "loss": 0.5048, "step": 160070 }, { "epoch": 0.951548763307595, "grad_norm": 4.470691680908203, "learning_rate": 9.753618520228432e-06, "loss": 0.5118, "step": 160080 }, { "epoch": 0.9516082053842633, "grad_norm": 7.402441024780273, "learning_rate": 9.753554185397582e-06, "loss": 0.6455, "step": 160090 }, { "epoch": 0.9516676474609317, "grad_norm": 4.981527805328369, "learning_rate": 9.753489842380547e-06, "loss": 0.5041, "step": 160100 }, { "epoch": 0.9517270895376001, "grad_norm": 4.9657673835754395, "learning_rate": 9.753425491177432e-06, "loss": 0.5062, "step": 160110 }, { "epoch": 0.9517865316142685, "grad_norm": 4.408777236938477, "learning_rate": 9.753361131788354e-06, "loss": 0.5262, "step": 160120 }, { "epoch": 0.9518459736909368, "grad_norm": 6.183601379394531, "learning_rate": 9.753296764213421e-06, "loss": 0.5247, "step": 160130 }, { "epoch": 0.9519054157676052, "grad_norm": 4.04600715637207, "learning_rate": 9.753232388452743e-06, "loss": 0.5112, "step": 160140 }, { "epoch": 0.9519648578442736, "grad_norm": 5.153517723083496, "learning_rate": 9.75316800450643e-06, "loss": 0.583, "step": 160150 }, { "epoch": 0.9520242999209421, "grad_norm": 4.540863037109375, "learning_rate": 9.753103612374597e-06, "loss": 0.4933, "step": 160160 }, { "epoch": 0.9520837419976105, "grad_norm": 4.3551836013793945, "learning_rate": 9.753039212057351e-06, "loss": 0.5202, "step": 160170 }, { "epoch": 0.9521431840742788, "grad_norm": 5.829957962036133, "learning_rate": 9.752974803554804e-06, "loss": 0.5325, "step": 160180 }, { "epoch": 0.9522026261509472, "grad_norm": 5.918376922607422, "learning_rate": 9.752910386867069e-06, "loss": 0.4808, "step": 160190 }, { "epoch": 0.9522620682276156, "grad_norm": 5.066843032836914, "learning_rate": 9.752845961994255e-06, "loss": 0.5005, "step": 160200 }, { "epoch": 0.952321510304284, "grad_norm": 5.654855251312256, "learning_rate": 9.752781528936472e-06, "loss": 0.6036, "step": 160210 }, { "epoch": 0.9523809523809523, "grad_norm": 5.939509391784668, "learning_rate": 9.752717087693833e-06, "loss": 0.5204, "step": 160220 }, { "epoch": 0.9524403944576207, "grad_norm": 4.675164222717285, "learning_rate": 9.752652638266447e-06, "loss": 0.4907, "step": 160230 }, { "epoch": 0.9524998365342892, "grad_norm": 5.193286895751953, "learning_rate": 9.752588180654427e-06, "loss": 0.5783, "step": 160240 }, { "epoch": 0.9525592786109576, "grad_norm": 4.595460414886475, "learning_rate": 9.752523714857884e-06, "loss": 0.5222, "step": 160250 }, { "epoch": 0.952618720687626, "grad_norm": 5.031471252441406, "learning_rate": 9.752459240876925e-06, "loss": 0.5455, "step": 160260 }, { "epoch": 0.9526781627642943, "grad_norm": 6.720789909362793, "learning_rate": 9.752394758711667e-06, "loss": 0.593, "step": 160270 }, { "epoch": 0.9527376048409627, "grad_norm": 5.061563491821289, "learning_rate": 9.752330268362218e-06, "loss": 0.5498, "step": 160280 }, { "epoch": 0.9527970469176311, "grad_norm": 6.331490516662598, "learning_rate": 9.752265769828688e-06, "loss": 0.5436, "step": 160290 }, { "epoch": 0.9528564889942995, "grad_norm": 4.907327651977539, "learning_rate": 9.75220126311119e-06, "loss": 0.4989, "step": 160300 }, { "epoch": 0.952915931070968, "grad_norm": 4.246514797210693, "learning_rate": 9.752136748209835e-06, "loss": 0.5318, "step": 160310 }, { "epoch": 0.9529753731476363, "grad_norm": 4.668359756469727, "learning_rate": 9.752072225124733e-06, "loss": 0.5454, "step": 160320 }, { "epoch": 0.9530348152243047, "grad_norm": 5.381132125854492, "learning_rate": 9.752007693855995e-06, "loss": 0.5655, "step": 160330 }, { "epoch": 0.9530942573009731, "grad_norm": 5.073999404907227, "learning_rate": 9.751943154403733e-06, "loss": 0.53, "step": 160340 }, { "epoch": 0.9531536993776415, "grad_norm": 5.971153736114502, "learning_rate": 9.751878606768058e-06, "loss": 0.5052, "step": 160350 }, { "epoch": 0.9532131414543098, "grad_norm": 5.287255764007568, "learning_rate": 9.751814050949083e-06, "loss": 0.494, "step": 160360 }, { "epoch": 0.9532725835309782, "grad_norm": 5.304891109466553, "learning_rate": 9.751749486946913e-06, "loss": 0.5118, "step": 160370 }, { "epoch": 0.9533320256076466, "grad_norm": 5.934450626373291, "learning_rate": 9.751684914761666e-06, "loss": 0.5555, "step": 160380 }, { "epoch": 0.953391467684315, "grad_norm": 4.577095031738281, "learning_rate": 9.75162033439345e-06, "loss": 0.5014, "step": 160390 }, { "epoch": 0.9534509097609835, "grad_norm": 7.638519763946533, "learning_rate": 9.751555745842378e-06, "loss": 0.5174, "step": 160400 }, { "epoch": 0.9535103518376518, "grad_norm": 5.564723491668701, "learning_rate": 9.75149114910856e-06, "loss": 0.5498, "step": 160410 }, { "epoch": 0.9535697939143202, "grad_norm": 5.475414752960205, "learning_rate": 9.751426544192106e-06, "loss": 0.5489, "step": 160420 }, { "epoch": 0.9536292359909886, "grad_norm": 4.894266605377197, "learning_rate": 9.751361931093128e-06, "loss": 0.5029, "step": 160430 }, { "epoch": 0.953688678067657, "grad_norm": 4.633095741271973, "learning_rate": 9.751297309811741e-06, "loss": 0.5092, "step": 160440 }, { "epoch": 0.9537481201443254, "grad_norm": 4.910750865936279, "learning_rate": 9.75123268034805e-06, "loss": 0.5347, "step": 160450 }, { "epoch": 0.9538075622209937, "grad_norm": 5.521677494049072, "learning_rate": 9.75116804270217e-06, "loss": 0.5214, "step": 160460 }, { "epoch": 0.9538670042976621, "grad_norm": 6.718277454376221, "learning_rate": 9.751103396874213e-06, "loss": 0.5386, "step": 160470 }, { "epoch": 0.9539264463743305, "grad_norm": 7.03882360458374, "learning_rate": 9.751038742864287e-06, "loss": 0.4935, "step": 160480 }, { "epoch": 0.953985888450999, "grad_norm": 4.452469825744629, "learning_rate": 9.750974080672508e-06, "loss": 0.4963, "step": 160490 }, { "epoch": 0.9540453305276673, "grad_norm": 4.650513648986816, "learning_rate": 9.750909410298983e-06, "loss": 0.509, "step": 160500 }, { "epoch": 0.9541047726043357, "grad_norm": 5.953397274017334, "learning_rate": 9.750844731743825e-06, "loss": 0.5535, "step": 160510 }, { "epoch": 0.9541642146810041, "grad_norm": 4.835494518280029, "learning_rate": 9.750780045007147e-06, "loss": 0.5134, "step": 160520 }, { "epoch": 0.9542236567576725, "grad_norm": 5.320271968841553, "learning_rate": 9.750715350089057e-06, "loss": 0.5692, "step": 160530 }, { "epoch": 0.9542830988343409, "grad_norm": 5.749963283538818, "learning_rate": 9.75065064698967e-06, "loss": 0.5437, "step": 160540 }, { "epoch": 0.9543425409110092, "grad_norm": 5.025167942047119, "learning_rate": 9.750585935709094e-06, "loss": 0.5263, "step": 160550 }, { "epoch": 0.9544019829876776, "grad_norm": 5.027648448944092, "learning_rate": 9.750521216247444e-06, "loss": 0.5019, "step": 160560 }, { "epoch": 0.9544614250643461, "grad_norm": 4.690250873565674, "learning_rate": 9.750456488604829e-06, "loss": 0.521, "step": 160570 }, { "epoch": 0.9545208671410145, "grad_norm": 4.698124408721924, "learning_rate": 9.750391752781361e-06, "loss": 0.5456, "step": 160580 }, { "epoch": 0.9545803092176828, "grad_norm": 5.480786323547363, "learning_rate": 9.750327008777151e-06, "loss": 0.548, "step": 160590 }, { "epoch": 0.9546397512943512, "grad_norm": 3.8678998947143555, "learning_rate": 9.750262256592312e-06, "loss": 0.5125, "step": 160600 }, { "epoch": 0.9546991933710196, "grad_norm": 5.326278209686279, "learning_rate": 9.750197496226955e-06, "loss": 0.533, "step": 160610 }, { "epoch": 0.954758635447688, "grad_norm": 6.340811729431152, "learning_rate": 9.75013272768119e-06, "loss": 0.5525, "step": 160620 }, { "epoch": 0.9548180775243564, "grad_norm": 4.357433319091797, "learning_rate": 9.75006795095513e-06, "loss": 0.5376, "step": 160630 }, { "epoch": 0.9548775196010247, "grad_norm": 5.814069747924805, "learning_rate": 9.750003166048886e-06, "loss": 0.5014, "step": 160640 }, { "epoch": 0.9549369616776932, "grad_norm": 5.282066345214844, "learning_rate": 9.749938372962571e-06, "loss": 0.5062, "step": 160650 }, { "epoch": 0.9549964037543616, "grad_norm": 3.960263967514038, "learning_rate": 9.749873571696293e-06, "loss": 0.5492, "step": 160660 }, { "epoch": 0.95505584583103, "grad_norm": 3.9317846298217773, "learning_rate": 9.749808762250168e-06, "loss": 0.5441, "step": 160670 }, { "epoch": 0.9551152879076984, "grad_norm": 6.159253120422363, "learning_rate": 9.749743944624306e-06, "loss": 0.5244, "step": 160680 }, { "epoch": 0.9551747299843667, "grad_norm": 6.418298244476318, "learning_rate": 9.749679118818817e-06, "loss": 0.5543, "step": 160690 }, { "epoch": 0.9552341720610351, "grad_norm": 4.371139049530029, "learning_rate": 9.749614284833815e-06, "loss": 0.4591, "step": 160700 }, { "epoch": 0.9552936141377035, "grad_norm": 6.190708637237549, "learning_rate": 9.749549442669408e-06, "loss": 0.4952, "step": 160710 }, { "epoch": 0.9553530562143719, "grad_norm": 5.240231037139893, "learning_rate": 9.749484592325712e-06, "loss": 0.5723, "step": 160720 }, { "epoch": 0.9554124982910402, "grad_norm": 6.868916034698486, "learning_rate": 9.749419733802837e-06, "loss": 0.5182, "step": 160730 }, { "epoch": 0.9554719403677087, "grad_norm": 3.4157156944274902, "learning_rate": 9.749354867100894e-06, "loss": 0.5599, "step": 160740 }, { "epoch": 0.9555313824443771, "grad_norm": 5.319408416748047, "learning_rate": 9.749289992219995e-06, "loss": 0.5218, "step": 160750 }, { "epoch": 0.9555908245210455, "grad_norm": 5.0886054039001465, "learning_rate": 9.749225109160251e-06, "loss": 0.5611, "step": 160760 }, { "epoch": 0.9556502665977139, "grad_norm": 4.10982084274292, "learning_rate": 9.749160217921776e-06, "loss": 0.5267, "step": 160770 }, { "epoch": 0.9557097086743822, "grad_norm": 4.110552787780762, "learning_rate": 9.74909531850468e-06, "loss": 0.4715, "step": 160780 }, { "epoch": 0.9557691507510506, "grad_norm": 4.775029182434082, "learning_rate": 9.749030410909077e-06, "loss": 0.5089, "step": 160790 }, { "epoch": 0.955828592827719, "grad_norm": 4.8368611335754395, "learning_rate": 9.748965495135075e-06, "loss": 0.5288, "step": 160800 }, { "epoch": 0.9558880349043875, "grad_norm": 6.524309158325195, "learning_rate": 9.74890057118279e-06, "loss": 0.5183, "step": 160810 }, { "epoch": 0.9559474769810558, "grad_norm": 7.054985523223877, "learning_rate": 9.748835639052328e-06, "loss": 0.6123, "step": 160820 }, { "epoch": 0.9560069190577242, "grad_norm": 6.592526912689209, "learning_rate": 9.748770698743806e-06, "loss": 0.5749, "step": 160830 }, { "epoch": 0.9560663611343926, "grad_norm": 4.302757740020752, "learning_rate": 9.748705750257335e-06, "loss": 0.5365, "step": 160840 }, { "epoch": 0.956125803211061, "grad_norm": 6.400927543640137, "learning_rate": 9.748640793593025e-06, "loss": 0.5105, "step": 160850 }, { "epoch": 0.9561852452877294, "grad_norm": 5.704959869384766, "learning_rate": 9.74857582875099e-06, "loss": 0.5633, "step": 160860 }, { "epoch": 0.9562446873643977, "grad_norm": 4.438212871551514, "learning_rate": 9.748510855731341e-06, "loss": 0.5574, "step": 160870 }, { "epoch": 0.9563041294410661, "grad_norm": 5.452084541320801, "learning_rate": 9.748445874534189e-06, "loss": 0.5158, "step": 160880 }, { "epoch": 0.9563635715177345, "grad_norm": 5.213133335113525, "learning_rate": 9.748380885159647e-06, "loss": 0.543, "step": 160890 }, { "epoch": 0.956423013594403, "grad_norm": 4.660371780395508, "learning_rate": 9.748315887607827e-06, "loss": 0.5338, "step": 160900 }, { "epoch": 0.9564824556710714, "grad_norm": 5.776437282562256, "learning_rate": 9.748250881878839e-06, "loss": 0.499, "step": 160910 }, { "epoch": 0.9565418977477397, "grad_norm": 4.706295490264893, "learning_rate": 9.748185867972798e-06, "loss": 0.5758, "step": 160920 }, { "epoch": 0.9566013398244081, "grad_norm": 4.859272003173828, "learning_rate": 9.748120845889812e-06, "loss": 0.5526, "step": 160930 }, { "epoch": 0.9566607819010765, "grad_norm": 5.3878655433654785, "learning_rate": 9.748055815629998e-06, "loss": 0.5246, "step": 160940 }, { "epoch": 0.9567202239777449, "grad_norm": 6.083380222320557, "learning_rate": 9.747990777193463e-06, "loss": 0.5657, "step": 160950 }, { "epoch": 0.9567796660544132, "grad_norm": 6.295664310455322, "learning_rate": 9.747925730580324e-06, "loss": 0.5362, "step": 160960 }, { "epoch": 0.9568391081310816, "grad_norm": 4.629615783691406, "learning_rate": 9.74786067579069e-06, "loss": 0.5489, "step": 160970 }, { "epoch": 0.95689855020775, "grad_norm": 4.93720817565918, "learning_rate": 9.747795612824671e-06, "loss": 0.5207, "step": 160980 }, { "epoch": 0.9569579922844185, "grad_norm": 4.859889507293701, "learning_rate": 9.747730541682383e-06, "loss": 0.5752, "step": 160990 }, { "epoch": 0.9570174343610869, "grad_norm": 4.2996506690979, "learning_rate": 9.747665462363938e-06, "loss": 0.5358, "step": 161000 }, { "epoch": 0.9570768764377552, "grad_norm": 4.9993391036987305, "learning_rate": 9.747600374869443e-06, "loss": 0.5714, "step": 161010 }, { "epoch": 0.9571363185144236, "grad_norm": 6.663004398345947, "learning_rate": 9.747535279199015e-06, "loss": 0.5307, "step": 161020 }, { "epoch": 0.957195760591092, "grad_norm": 5.429433822631836, "learning_rate": 9.747470175352767e-06, "loss": 0.5567, "step": 161030 }, { "epoch": 0.9572552026677604, "grad_norm": 5.232987403869629, "learning_rate": 9.747405063330808e-06, "loss": 0.5384, "step": 161040 }, { "epoch": 0.9573146447444288, "grad_norm": 6.582511901855469, "learning_rate": 9.74733994313325e-06, "loss": 0.5498, "step": 161050 }, { "epoch": 0.9573740868210971, "grad_norm": 5.035996913909912, "learning_rate": 9.747274814760207e-06, "loss": 0.5147, "step": 161060 }, { "epoch": 0.9574335288977656, "grad_norm": 5.9297332763671875, "learning_rate": 9.74720967821179e-06, "loss": 0.5548, "step": 161070 }, { "epoch": 0.957492970974434, "grad_norm": 5.346144676208496, "learning_rate": 9.74714453348811e-06, "loss": 0.4764, "step": 161080 }, { "epoch": 0.9575524130511024, "grad_norm": 4.118492603302002, "learning_rate": 9.747079380589284e-06, "loss": 0.5502, "step": 161090 }, { "epoch": 0.9576118551277707, "grad_norm": 4.460244655609131, "learning_rate": 9.747014219515419e-06, "loss": 0.513, "step": 161100 }, { "epoch": 0.9576712972044391, "grad_norm": 5.126188278198242, "learning_rate": 9.746949050266629e-06, "loss": 0.5536, "step": 161110 }, { "epoch": 0.9577307392811075, "grad_norm": 5.768235683441162, "learning_rate": 9.746883872843027e-06, "loss": 0.5141, "step": 161120 }, { "epoch": 0.9577901813577759, "grad_norm": 4.716616630554199, "learning_rate": 9.746818687244724e-06, "loss": 0.5225, "step": 161130 }, { "epoch": 0.9578496234344444, "grad_norm": 5.536182880401611, "learning_rate": 9.746753493471831e-06, "loss": 0.5518, "step": 161140 }, { "epoch": 0.9579090655111127, "grad_norm": 5.461860656738281, "learning_rate": 9.746688291524466e-06, "loss": 0.5463, "step": 161150 }, { "epoch": 0.9579685075877811, "grad_norm": 5.50862455368042, "learning_rate": 9.746623081402735e-06, "loss": 0.5598, "step": 161160 }, { "epoch": 0.9580279496644495, "grad_norm": 4.443567752838135, "learning_rate": 9.746557863106754e-06, "loss": 0.5276, "step": 161170 }, { "epoch": 0.9580873917411179, "grad_norm": 4.595762729644775, "learning_rate": 9.746492636636631e-06, "loss": 0.5145, "step": 161180 }, { "epoch": 0.9581468338177862, "grad_norm": 4.78054666519165, "learning_rate": 9.746427401992485e-06, "loss": 0.495, "step": 161190 }, { "epoch": 0.9582062758944546, "grad_norm": 4.075431823730469, "learning_rate": 9.746362159174423e-06, "loss": 0.5571, "step": 161200 }, { "epoch": 0.958265717971123, "grad_norm": 5.232294082641602, "learning_rate": 9.74629690818256e-06, "loss": 0.4867, "step": 161210 }, { "epoch": 0.9583251600477914, "grad_norm": 6.1649556159973145, "learning_rate": 9.746231649017007e-06, "loss": 0.5877, "step": 161220 }, { "epoch": 0.9583846021244599, "grad_norm": 6.619598865509033, "learning_rate": 9.746166381677874e-06, "loss": 0.5716, "step": 161230 }, { "epoch": 0.9584440442011282, "grad_norm": 7.02413272857666, "learning_rate": 9.746101106165279e-06, "loss": 0.5256, "step": 161240 }, { "epoch": 0.9585034862777966, "grad_norm": 4.855599403381348, "learning_rate": 9.746035822479331e-06, "loss": 0.5396, "step": 161250 }, { "epoch": 0.958562928354465, "grad_norm": 5.2129106521606445, "learning_rate": 9.745970530620143e-06, "loss": 0.5366, "step": 161260 }, { "epoch": 0.9586223704311334, "grad_norm": 5.164170742034912, "learning_rate": 9.745905230587828e-06, "loss": 0.4729, "step": 161270 }, { "epoch": 0.9586818125078018, "grad_norm": 5.422086238861084, "learning_rate": 9.745839922382499e-06, "loss": 0.5272, "step": 161280 }, { "epoch": 0.9587412545844701, "grad_norm": 5.143685340881348, "learning_rate": 9.745774606004265e-06, "loss": 0.509, "step": 161290 }, { "epoch": 0.9588006966611385, "grad_norm": 5.519279956817627, "learning_rate": 9.745709281453241e-06, "loss": 0.5444, "step": 161300 }, { "epoch": 0.958860138737807, "grad_norm": 5.7683587074279785, "learning_rate": 9.745643948729542e-06, "loss": 0.5459, "step": 161310 }, { "epoch": 0.9589195808144754, "grad_norm": 5.6137590408325195, "learning_rate": 9.745578607833274e-06, "loss": 0.5317, "step": 161320 }, { "epoch": 0.9589790228911437, "grad_norm": 4.450136661529541, "learning_rate": 9.745513258764556e-06, "loss": 0.5291, "step": 161330 }, { "epoch": 0.9590384649678121, "grad_norm": 4.44888162612915, "learning_rate": 9.745447901523498e-06, "loss": 0.5412, "step": 161340 }, { "epoch": 0.9590979070444805, "grad_norm": 5.573432922363281, "learning_rate": 9.745382536110213e-06, "loss": 0.5338, "step": 161350 }, { "epoch": 0.9591573491211489, "grad_norm": 5.481215000152588, "learning_rate": 9.745317162524812e-06, "loss": 0.5502, "step": 161360 }, { "epoch": 0.9592167911978173, "grad_norm": 5.050200939178467, "learning_rate": 9.745251780767409e-06, "loss": 0.531, "step": 161370 }, { "epoch": 0.9592762332744856, "grad_norm": 4.738494396209717, "learning_rate": 9.745186390838115e-06, "loss": 0.5332, "step": 161380 }, { "epoch": 0.959335675351154, "grad_norm": 4.5065107345581055, "learning_rate": 9.745120992737045e-06, "loss": 0.4949, "step": 161390 }, { "epoch": 0.9593951174278225, "grad_norm": 5.433006286621094, "learning_rate": 9.74505558646431e-06, "loss": 0.5883, "step": 161400 }, { "epoch": 0.9594545595044909, "grad_norm": 5.5086774826049805, "learning_rate": 9.744990172020023e-06, "loss": 0.6051, "step": 161410 }, { "epoch": 0.9595140015811593, "grad_norm": 5.352185249328613, "learning_rate": 9.744924749404297e-06, "loss": 0.5842, "step": 161420 }, { "epoch": 0.9595734436578276, "grad_norm": 4.220430850982666, "learning_rate": 9.744859318617245e-06, "loss": 0.566, "step": 161430 }, { "epoch": 0.959632885734496, "grad_norm": 6.029826641082764, "learning_rate": 9.744793879658979e-06, "loss": 0.5451, "step": 161440 }, { "epoch": 0.9596923278111644, "grad_norm": 5.792804718017578, "learning_rate": 9.74472843252961e-06, "loss": 0.5456, "step": 161450 }, { "epoch": 0.9597517698878328, "grad_norm": 4.3590617179870605, "learning_rate": 9.744662977229256e-06, "loss": 0.5713, "step": 161460 }, { "epoch": 0.9598112119645011, "grad_norm": 6.494757175445557, "learning_rate": 9.744597513758022e-06, "loss": 0.6117, "step": 161470 }, { "epoch": 0.9598706540411696, "grad_norm": 5.781566143035889, "learning_rate": 9.744532042116029e-06, "loss": 0.5118, "step": 161480 }, { "epoch": 0.959930096117838, "grad_norm": 4.739671230316162, "learning_rate": 9.744466562303383e-06, "loss": 0.5541, "step": 161490 }, { "epoch": 0.9599895381945064, "grad_norm": 5.622560977935791, "learning_rate": 9.7444010743202e-06, "loss": 0.5341, "step": 161500 }, { "epoch": 0.9600489802711748, "grad_norm": 4.685278415679932, "learning_rate": 9.744335578166592e-06, "loss": 0.5136, "step": 161510 }, { "epoch": 0.9601084223478431, "grad_norm": 6.1603851318359375, "learning_rate": 9.744270073842674e-06, "loss": 0.5087, "step": 161520 }, { "epoch": 0.9601678644245115, "grad_norm": 5.4256415367126465, "learning_rate": 9.744204561348555e-06, "loss": 0.5203, "step": 161530 }, { "epoch": 0.9602273065011799, "grad_norm": 5.384410858154297, "learning_rate": 9.74413904068435e-06, "loss": 0.497, "step": 161540 }, { "epoch": 0.9602867485778483, "grad_norm": 4.470432758331299, "learning_rate": 9.744073511850172e-06, "loss": 0.5177, "step": 161550 }, { "epoch": 0.9603461906545167, "grad_norm": 4.632514476776123, "learning_rate": 9.744007974846132e-06, "loss": 0.5324, "step": 161560 }, { "epoch": 0.9604056327311851, "grad_norm": 4.864816665649414, "learning_rate": 9.743942429672346e-06, "loss": 0.4738, "step": 161570 }, { "epoch": 0.9604650748078535, "grad_norm": 4.775942325592041, "learning_rate": 9.743876876328924e-06, "loss": 0.5557, "step": 161580 }, { "epoch": 0.9605245168845219, "grad_norm": 7.082208156585693, "learning_rate": 9.743811314815982e-06, "loss": 0.5506, "step": 161590 }, { "epoch": 0.9605839589611903, "grad_norm": 5.0258002281188965, "learning_rate": 9.743745745133628e-06, "loss": 0.516, "step": 161600 }, { "epoch": 0.9606434010378586, "grad_norm": 4.013000011444092, "learning_rate": 9.74368016728198e-06, "loss": 0.5282, "step": 161610 }, { "epoch": 0.960702843114527, "grad_norm": 6.501426696777344, "learning_rate": 9.743614581261147e-06, "loss": 0.5613, "step": 161620 }, { "epoch": 0.9607622851911954, "grad_norm": 4.37601900100708, "learning_rate": 9.743548987071245e-06, "loss": 0.5605, "step": 161630 }, { "epoch": 0.9608217272678639, "grad_norm": 4.642966270446777, "learning_rate": 9.743483384712384e-06, "loss": 0.5333, "step": 161640 }, { "epoch": 0.9608811693445323, "grad_norm": 5.557248115539551, "learning_rate": 9.74341777418468e-06, "loss": 0.4841, "step": 161650 }, { "epoch": 0.9609406114212006, "grad_norm": 6.286747932434082, "learning_rate": 9.743352155488243e-06, "loss": 0.5319, "step": 161660 }, { "epoch": 0.961000053497869, "grad_norm": 5.256180763244629, "learning_rate": 9.74328652862319e-06, "loss": 0.5711, "step": 161670 }, { "epoch": 0.9610594955745374, "grad_norm": 5.344332218170166, "learning_rate": 9.74322089358963e-06, "loss": 0.5029, "step": 161680 }, { "epoch": 0.9611189376512058, "grad_norm": 7.07951545715332, "learning_rate": 9.74315525038768e-06, "loss": 0.548, "step": 161690 }, { "epoch": 0.9611783797278741, "grad_norm": 4.738536834716797, "learning_rate": 9.743089599017448e-06, "loss": 0.5095, "step": 161700 }, { "epoch": 0.9612378218045425, "grad_norm": 5.021108627319336, "learning_rate": 9.74302393947905e-06, "loss": 0.5373, "step": 161710 }, { "epoch": 0.961297263881211, "grad_norm": 4.541232585906982, "learning_rate": 9.7429582717726e-06, "loss": 0.5152, "step": 161720 }, { "epoch": 0.9613567059578794, "grad_norm": 5.366559028625488, "learning_rate": 9.74289259589821e-06, "loss": 0.5132, "step": 161730 }, { "epoch": 0.9614161480345478, "grad_norm": 4.922304630279541, "learning_rate": 9.742826911855993e-06, "loss": 0.5216, "step": 161740 }, { "epoch": 0.9614755901112161, "grad_norm": 5.271638870239258, "learning_rate": 9.742761219646063e-06, "loss": 0.505, "step": 161750 }, { "epoch": 0.9615350321878845, "grad_norm": 4.019426345825195, "learning_rate": 9.742695519268531e-06, "loss": 0.4995, "step": 161760 }, { "epoch": 0.9615944742645529, "grad_norm": 4.674333095550537, "learning_rate": 9.742629810723511e-06, "loss": 0.5033, "step": 161770 }, { "epoch": 0.9616539163412213, "grad_norm": 6.021727085113525, "learning_rate": 9.742564094011117e-06, "loss": 0.6333, "step": 161780 }, { "epoch": 0.9617133584178897, "grad_norm": 4.231879234313965, "learning_rate": 9.742498369131461e-06, "loss": 0.566, "step": 161790 }, { "epoch": 0.961772800494558, "grad_norm": 4.3817315101623535, "learning_rate": 9.742432636084658e-06, "loss": 0.5158, "step": 161800 }, { "epoch": 0.9618322425712265, "grad_norm": 4.774889945983887, "learning_rate": 9.74236689487082e-06, "loss": 0.4915, "step": 161810 }, { "epoch": 0.9618916846478949, "grad_norm": 5.299223899841309, "learning_rate": 9.742301145490061e-06, "loss": 0.4813, "step": 161820 }, { "epoch": 0.9619511267245633, "grad_norm": 3.7855305671691895, "learning_rate": 9.742235387942491e-06, "loss": 0.5346, "step": 161830 }, { "epoch": 0.9620105688012316, "grad_norm": 5.191129207611084, "learning_rate": 9.742169622228228e-06, "loss": 0.6026, "step": 161840 }, { "epoch": 0.9620700108779, "grad_norm": 5.304945945739746, "learning_rate": 9.742103848347384e-06, "loss": 0.5393, "step": 161850 }, { "epoch": 0.9621294529545684, "grad_norm": 5.3055267333984375, "learning_rate": 9.74203806630007e-06, "loss": 0.5538, "step": 161860 }, { "epoch": 0.9621888950312368, "grad_norm": 6.519445896148682, "learning_rate": 9.7419722760864e-06, "loss": 0.5608, "step": 161870 }, { "epoch": 0.9622483371079052, "grad_norm": 4.858586311340332, "learning_rate": 9.74190647770649e-06, "loss": 0.562, "step": 161880 }, { "epoch": 0.9623077791845736, "grad_norm": 6.081412315368652, "learning_rate": 9.74184067116045e-06, "loss": 0.5149, "step": 161890 }, { "epoch": 0.962367221261242, "grad_norm": 4.72335958480835, "learning_rate": 9.741774856448394e-06, "loss": 0.5533, "step": 161900 }, { "epoch": 0.9624266633379104, "grad_norm": 5.638023853302002, "learning_rate": 9.741709033570436e-06, "loss": 0.5429, "step": 161910 }, { "epoch": 0.9624861054145788, "grad_norm": 5.117469787597656, "learning_rate": 9.74164320252669e-06, "loss": 0.5502, "step": 161920 }, { "epoch": 0.9625455474912471, "grad_norm": 4.255512237548828, "learning_rate": 9.741577363317267e-06, "loss": 0.5357, "step": 161930 }, { "epoch": 0.9626049895679155, "grad_norm": 5.850275039672852, "learning_rate": 9.741511515942285e-06, "loss": 0.5424, "step": 161940 }, { "epoch": 0.9626644316445839, "grad_norm": 5.193417072296143, "learning_rate": 9.74144566040185e-06, "loss": 0.4944, "step": 161950 }, { "epoch": 0.9627238737212523, "grad_norm": 6.045228481292725, "learning_rate": 9.741379796696084e-06, "loss": 0.5875, "step": 161960 }, { "epoch": 0.9627833157979208, "grad_norm": 6.027735710144043, "learning_rate": 9.741313924825095e-06, "loss": 0.5023, "step": 161970 }, { "epoch": 0.9628427578745891, "grad_norm": 6.120249271392822, "learning_rate": 9.741248044788999e-06, "loss": 0.528, "step": 161980 }, { "epoch": 0.9629021999512575, "grad_norm": 5.147069931030273, "learning_rate": 9.741182156587906e-06, "loss": 0.5864, "step": 161990 }, { "epoch": 0.9629616420279259, "grad_norm": 4.717486381530762, "learning_rate": 9.741116260221933e-06, "loss": 0.5525, "step": 162000 }, { "epoch": 0.9630210841045943, "grad_norm": 5.2440876960754395, "learning_rate": 9.74105035569119e-06, "loss": 0.5084, "step": 162010 }, { "epoch": 0.9630805261812627, "grad_norm": 6.290498733520508, "learning_rate": 9.740984442995795e-06, "loss": 0.5752, "step": 162020 }, { "epoch": 0.963139968257931, "grad_norm": 3.73921799659729, "learning_rate": 9.740918522135858e-06, "loss": 0.5511, "step": 162030 }, { "epoch": 0.9631994103345994, "grad_norm": 3.7481143474578857, "learning_rate": 9.740852593111495e-06, "loss": 0.5092, "step": 162040 }, { "epoch": 0.9632588524112679, "grad_norm": 4.215750694274902, "learning_rate": 9.740786655922816e-06, "loss": 0.5284, "step": 162050 }, { "epoch": 0.9633182944879363, "grad_norm": 6.620383262634277, "learning_rate": 9.740720710569937e-06, "loss": 0.5031, "step": 162060 }, { "epoch": 0.9633777365646046, "grad_norm": 4.576474666595459, "learning_rate": 9.740654757052972e-06, "loss": 0.5388, "step": 162070 }, { "epoch": 0.963437178641273, "grad_norm": 3.6104869842529297, "learning_rate": 9.740588795372035e-06, "loss": 0.5323, "step": 162080 }, { "epoch": 0.9634966207179414, "grad_norm": 4.257190227508545, "learning_rate": 9.740522825527236e-06, "loss": 0.5404, "step": 162090 }, { "epoch": 0.9635560627946098, "grad_norm": 5.878800868988037, "learning_rate": 9.740456847518694e-06, "loss": 0.5458, "step": 162100 }, { "epoch": 0.9636155048712782, "grad_norm": 5.465763092041016, "learning_rate": 9.740390861346517e-06, "loss": 0.6071, "step": 162110 }, { "epoch": 0.9636749469479465, "grad_norm": 5.535735130310059, "learning_rate": 9.740324867010822e-06, "loss": 0.5224, "step": 162120 }, { "epoch": 0.963734389024615, "grad_norm": 6.2301859855651855, "learning_rate": 9.740258864511722e-06, "loss": 0.5605, "step": 162130 }, { "epoch": 0.9637938311012834, "grad_norm": 5.328123569488525, "learning_rate": 9.74019285384933e-06, "loss": 0.4809, "step": 162140 }, { "epoch": 0.9638532731779518, "grad_norm": 4.912629127502441, "learning_rate": 9.740126835023763e-06, "loss": 0.5498, "step": 162150 }, { "epoch": 0.9639127152546202, "grad_norm": 4.968461513519287, "learning_rate": 9.74006080803513e-06, "loss": 0.5068, "step": 162160 }, { "epoch": 0.9639721573312885, "grad_norm": 6.172205448150635, "learning_rate": 9.739994772883548e-06, "loss": 0.5628, "step": 162170 }, { "epoch": 0.9640315994079569, "grad_norm": 4.683934688568115, "learning_rate": 9.739928729569127e-06, "loss": 0.5101, "step": 162180 }, { "epoch": 0.9640910414846253, "grad_norm": 4.278147220611572, "learning_rate": 9.739862678091984e-06, "loss": 0.5054, "step": 162190 }, { "epoch": 0.9641504835612937, "grad_norm": 5.035289764404297, "learning_rate": 9.739796618452233e-06, "loss": 0.5361, "step": 162200 }, { "epoch": 0.964209925637962, "grad_norm": 5.676385402679443, "learning_rate": 9.739730550649986e-06, "loss": 0.5482, "step": 162210 }, { "epoch": 0.9642693677146305, "grad_norm": 4.273874759674072, "learning_rate": 9.739664474685357e-06, "loss": 0.4737, "step": 162220 }, { "epoch": 0.9643288097912989, "grad_norm": 6.355058193206787, "learning_rate": 9.739598390558463e-06, "loss": 0.5148, "step": 162230 }, { "epoch": 0.9643882518679673, "grad_norm": 4.966240406036377, "learning_rate": 9.739532298269411e-06, "loss": 0.4864, "step": 162240 }, { "epoch": 0.9644476939446357, "grad_norm": 5.756657600402832, "learning_rate": 9.739466197818322e-06, "loss": 0.5264, "step": 162250 }, { "epoch": 0.964507136021304, "grad_norm": 7.338675022125244, "learning_rate": 9.739400089205306e-06, "loss": 0.5252, "step": 162260 }, { "epoch": 0.9645665780979724, "grad_norm": 4.928234577178955, "learning_rate": 9.739333972430477e-06, "loss": 0.5496, "step": 162270 }, { "epoch": 0.9646260201746408, "grad_norm": 7.008134841918945, "learning_rate": 9.73926784749395e-06, "loss": 0.6067, "step": 162280 }, { "epoch": 0.9646854622513092, "grad_norm": 4.131068229675293, "learning_rate": 9.739201714395835e-06, "loss": 0.4907, "step": 162290 }, { "epoch": 0.9647449043279775, "grad_norm": 5.60279655456543, "learning_rate": 9.739135573136254e-06, "loss": 0.5362, "step": 162300 }, { "epoch": 0.964804346404646, "grad_norm": 4.577507495880127, "learning_rate": 9.739069423715313e-06, "loss": 0.4983, "step": 162310 }, { "epoch": 0.9648637884813144, "grad_norm": 5.292187213897705, "learning_rate": 9.739003266133132e-06, "loss": 0.5375, "step": 162320 }, { "epoch": 0.9649232305579828, "grad_norm": 4.8090291023254395, "learning_rate": 9.738937100389818e-06, "loss": 0.5109, "step": 162330 }, { "epoch": 0.9649826726346512, "grad_norm": 5.809697151184082, "learning_rate": 9.73887092648549e-06, "loss": 0.5691, "step": 162340 }, { "epoch": 0.9650421147113195, "grad_norm": 4.621654987335205, "learning_rate": 9.738804744420262e-06, "loss": 0.5425, "step": 162350 }, { "epoch": 0.9651015567879879, "grad_norm": 6.068691730499268, "learning_rate": 9.738738554194246e-06, "loss": 0.516, "step": 162360 }, { "epoch": 0.9651609988646563, "grad_norm": 6.520534038543701, "learning_rate": 9.738672355807559e-06, "loss": 0.5763, "step": 162370 }, { "epoch": 0.9652204409413248, "grad_norm": 4.139304161071777, "learning_rate": 9.73860614926031e-06, "loss": 0.507, "step": 162380 }, { "epoch": 0.9652798830179932, "grad_norm": 4.476201057434082, "learning_rate": 9.738539934552618e-06, "loss": 0.4881, "step": 162390 }, { "epoch": 0.9653393250946615, "grad_norm": 4.077060222625732, "learning_rate": 9.738473711684593e-06, "loss": 0.4847, "step": 162400 }, { "epoch": 0.9653987671713299, "grad_norm": 4.9320759773254395, "learning_rate": 9.738407480656351e-06, "loss": 0.5483, "step": 162410 }, { "epoch": 0.9654582092479983, "grad_norm": 6.142446994781494, "learning_rate": 9.738341241468007e-06, "loss": 0.5376, "step": 162420 }, { "epoch": 0.9655176513246667, "grad_norm": 4.663604259490967, "learning_rate": 9.738274994119675e-06, "loss": 0.5092, "step": 162430 }, { "epoch": 0.965577093401335, "grad_norm": 6.155661582946777, "learning_rate": 9.738208738611466e-06, "loss": 0.5105, "step": 162440 }, { "epoch": 0.9656365354780034, "grad_norm": 5.750662803649902, "learning_rate": 9.738142474943495e-06, "loss": 0.5993, "step": 162450 }, { "epoch": 0.9656959775546718, "grad_norm": 5.655307292938232, "learning_rate": 9.73807620311588e-06, "loss": 0.4951, "step": 162460 }, { "epoch": 0.9657554196313403, "grad_norm": 7.015435218811035, "learning_rate": 9.738009923128732e-06, "loss": 0.5448, "step": 162470 }, { "epoch": 0.9658148617080087, "grad_norm": 4.754499912261963, "learning_rate": 9.737943634982165e-06, "loss": 0.5291, "step": 162480 }, { "epoch": 0.965874303784677, "grad_norm": 5.182012557983398, "learning_rate": 9.737877338676294e-06, "loss": 0.4679, "step": 162490 }, { "epoch": 0.9659337458613454, "grad_norm": 6.403426647186279, "learning_rate": 9.737811034211232e-06, "loss": 0.5365, "step": 162500 }, { "epoch": 0.9659931879380138, "grad_norm": 5.451597213745117, "learning_rate": 9.737744721587095e-06, "loss": 0.4876, "step": 162510 }, { "epoch": 0.9660526300146822, "grad_norm": 4.238886833190918, "learning_rate": 9.737678400803996e-06, "loss": 0.5132, "step": 162520 }, { "epoch": 0.9661120720913506, "grad_norm": 5.292115688323975, "learning_rate": 9.737612071862051e-06, "loss": 0.4994, "step": 162530 }, { "epoch": 0.9661715141680189, "grad_norm": 4.7863640785217285, "learning_rate": 9.73754573476137e-06, "loss": 0.4708, "step": 162540 }, { "epoch": 0.9662309562446874, "grad_norm": 4.729706764221191, "learning_rate": 9.737479389502072e-06, "loss": 0.5432, "step": 162550 }, { "epoch": 0.9662903983213558, "grad_norm": 5.259542942047119, "learning_rate": 9.73741303608427e-06, "loss": 0.5644, "step": 162560 }, { "epoch": 0.9663498403980242, "grad_norm": 4.827752113342285, "learning_rate": 9.737346674508075e-06, "loss": 0.532, "step": 162570 }, { "epoch": 0.9664092824746925, "grad_norm": 4.81196403503418, "learning_rate": 9.737280304773604e-06, "loss": 0.5379, "step": 162580 }, { "epoch": 0.9664687245513609, "grad_norm": 4.448273658752441, "learning_rate": 9.737213926880972e-06, "loss": 0.4819, "step": 162590 }, { "epoch": 0.9665281666280293, "grad_norm": 5.312381267547607, "learning_rate": 9.737147540830293e-06, "loss": 0.5769, "step": 162600 }, { "epoch": 0.9665876087046977, "grad_norm": 3.7037110328674316, "learning_rate": 9.737081146621681e-06, "loss": 0.5168, "step": 162610 }, { "epoch": 0.9666470507813661, "grad_norm": 4.474609375, "learning_rate": 9.737014744255249e-06, "loss": 0.5208, "step": 162620 }, { "epoch": 0.9667064928580344, "grad_norm": 4.396020412445068, "learning_rate": 9.736948333731111e-06, "loss": 0.5301, "step": 162630 }, { "epoch": 0.9667659349347029, "grad_norm": 4.251177787780762, "learning_rate": 9.736881915049386e-06, "loss": 0.5322, "step": 162640 }, { "epoch": 0.9668253770113713, "grad_norm": 5.965904712677002, "learning_rate": 9.736815488210183e-06, "loss": 0.5586, "step": 162650 }, { "epoch": 0.9668848190880397, "grad_norm": 4.290140628814697, "learning_rate": 9.736749053213619e-06, "loss": 0.5334, "step": 162660 }, { "epoch": 0.966944261164708, "grad_norm": 6.187709808349609, "learning_rate": 9.736682610059807e-06, "loss": 0.4778, "step": 162670 }, { "epoch": 0.9670037032413764, "grad_norm": 4.6816558837890625, "learning_rate": 9.736616158748863e-06, "loss": 0.4944, "step": 162680 }, { "epoch": 0.9670631453180448, "grad_norm": 4.48527717590332, "learning_rate": 9.736549699280902e-06, "loss": 0.5242, "step": 162690 }, { "epoch": 0.9671225873947132, "grad_norm": 4.8923516273498535, "learning_rate": 9.736483231656036e-06, "loss": 0.474, "step": 162700 }, { "epoch": 0.9671820294713817, "grad_norm": 4.734709739685059, "learning_rate": 9.73641675587438e-06, "loss": 0.5357, "step": 162710 }, { "epoch": 0.96724147154805, "grad_norm": 5.07932710647583, "learning_rate": 9.73635027193605e-06, "loss": 0.5679, "step": 162720 }, { "epoch": 0.9673009136247184, "grad_norm": 3.937246084213257, "learning_rate": 9.73628377984116e-06, "loss": 0.5504, "step": 162730 }, { "epoch": 0.9673603557013868, "grad_norm": 5.86993408203125, "learning_rate": 9.736217279589826e-06, "loss": 0.5373, "step": 162740 }, { "epoch": 0.9674197977780552, "grad_norm": 5.267848491668701, "learning_rate": 9.736150771182158e-06, "loss": 0.5269, "step": 162750 }, { "epoch": 0.9674792398547236, "grad_norm": 4.382950782775879, "learning_rate": 9.736084254618274e-06, "loss": 0.5407, "step": 162760 }, { "epoch": 0.9675386819313919, "grad_norm": 4.406292915344238, "learning_rate": 9.736017729898288e-06, "loss": 0.565, "step": 162770 }, { "epoch": 0.9675981240080603, "grad_norm": 4.556426048278809, "learning_rate": 9.735951197022315e-06, "loss": 0.5021, "step": 162780 }, { "epoch": 0.9676575660847287, "grad_norm": 5.011733531951904, "learning_rate": 9.735884655990469e-06, "loss": 0.5545, "step": 162790 }, { "epoch": 0.9677170081613972, "grad_norm": 4.71398401260376, "learning_rate": 9.735818106802864e-06, "loss": 0.504, "step": 162800 }, { "epoch": 0.9677764502380655, "grad_norm": 5.440993309020996, "learning_rate": 9.735751549459614e-06, "loss": 0.5707, "step": 162810 }, { "epoch": 0.9678358923147339, "grad_norm": 3.7150003910064697, "learning_rate": 9.735684983960836e-06, "loss": 0.5123, "step": 162820 }, { "epoch": 0.9678953343914023, "grad_norm": 6.77854061126709, "learning_rate": 9.735618410306642e-06, "loss": 0.5819, "step": 162830 }, { "epoch": 0.9679547764680707, "grad_norm": 6.4012131690979, "learning_rate": 9.735551828497149e-06, "loss": 0.5302, "step": 162840 }, { "epoch": 0.9680142185447391, "grad_norm": 4.810004711151123, "learning_rate": 9.735485238532471e-06, "loss": 0.5324, "step": 162850 }, { "epoch": 0.9680736606214074, "grad_norm": 5.321117877960205, "learning_rate": 9.735418640412723e-06, "loss": 0.5064, "step": 162860 }, { "epoch": 0.9681331026980758, "grad_norm": 4.010150909423828, "learning_rate": 9.735352034138018e-06, "loss": 0.5085, "step": 162870 }, { "epoch": 0.9681925447747443, "grad_norm": 4.755345821380615, "learning_rate": 9.735285419708473e-06, "loss": 0.5249, "step": 162880 }, { "epoch": 0.9682519868514127, "grad_norm": 6.830829620361328, "learning_rate": 9.735218797124201e-06, "loss": 0.5429, "step": 162890 }, { "epoch": 0.9683114289280811, "grad_norm": 4.862278461456299, "learning_rate": 9.735152166385316e-06, "loss": 0.5689, "step": 162900 }, { "epoch": 0.9683708710047494, "grad_norm": 4.837452411651611, "learning_rate": 9.735085527491935e-06, "loss": 0.5366, "step": 162910 }, { "epoch": 0.9684303130814178, "grad_norm": 5.9339776039123535, "learning_rate": 9.735018880444172e-06, "loss": 0.5271, "step": 162920 }, { "epoch": 0.9684897551580862, "grad_norm": 5.369884967803955, "learning_rate": 9.734952225242142e-06, "loss": 0.5559, "step": 162930 }, { "epoch": 0.9685491972347546, "grad_norm": 6.6771063804626465, "learning_rate": 9.734885561885958e-06, "loss": 0.5189, "step": 162940 }, { "epoch": 0.9686086393114229, "grad_norm": 4.972675323486328, "learning_rate": 9.734818890375736e-06, "loss": 0.5226, "step": 162950 }, { "epoch": 0.9686680813880914, "grad_norm": 6.440019607543945, "learning_rate": 9.734752210711591e-06, "loss": 0.5435, "step": 162960 }, { "epoch": 0.9687275234647598, "grad_norm": 5.143590927124023, "learning_rate": 9.73468552289364e-06, "loss": 0.5164, "step": 162970 }, { "epoch": 0.9687869655414282, "grad_norm": 3.785155773162842, "learning_rate": 9.734618826921994e-06, "loss": 0.4921, "step": 162980 }, { "epoch": 0.9688464076180966, "grad_norm": 3.910630464553833, "learning_rate": 9.734552122796767e-06, "loss": 0.5429, "step": 162990 }, { "epoch": 0.9689058496947649, "grad_norm": 5.0562639236450195, "learning_rate": 9.73448541051808e-06, "loss": 0.5158, "step": 163000 }, { "epoch": 0.9689652917714333, "grad_norm": 6.504130840301514, "learning_rate": 9.734418690086043e-06, "loss": 0.5262, "step": 163010 }, { "epoch": 0.9690247338481017, "grad_norm": 5.851837158203125, "learning_rate": 9.734351961500772e-06, "loss": 0.4434, "step": 163020 }, { "epoch": 0.9690841759247701, "grad_norm": 5.5824785232543945, "learning_rate": 9.734285224762381e-06, "loss": 0.563, "step": 163030 }, { "epoch": 0.9691436180014384, "grad_norm": 6.045867919921875, "learning_rate": 9.734218479870987e-06, "loss": 0.5146, "step": 163040 }, { "epoch": 0.9692030600781069, "grad_norm": 4.167243957519531, "learning_rate": 9.734151726826704e-06, "loss": 0.4955, "step": 163050 }, { "epoch": 0.9692625021547753, "grad_norm": 4.635542392730713, "learning_rate": 9.734084965629647e-06, "loss": 0.5165, "step": 163060 }, { "epoch": 0.9693219442314437, "grad_norm": 5.524980068206787, "learning_rate": 9.73401819627993e-06, "loss": 0.4985, "step": 163070 }, { "epoch": 0.9693813863081121, "grad_norm": 5.778831958770752, "learning_rate": 9.73395141877767e-06, "loss": 0.5598, "step": 163080 }, { "epoch": 0.9694408283847804, "grad_norm": 3.806011915206909, "learning_rate": 9.73388463312298e-06, "loss": 0.5334, "step": 163090 }, { "epoch": 0.9695002704614488, "grad_norm": 5.222670555114746, "learning_rate": 9.733817839315975e-06, "loss": 0.5152, "step": 163100 }, { "epoch": 0.9695597125381172, "grad_norm": 5.471297740936279, "learning_rate": 9.733751037356773e-06, "loss": 0.495, "step": 163110 }, { "epoch": 0.9696191546147856, "grad_norm": 5.108366012573242, "learning_rate": 9.733684227245486e-06, "loss": 0.5539, "step": 163120 }, { "epoch": 0.9696785966914541, "grad_norm": 4.322913646697998, "learning_rate": 9.73361740898223e-06, "loss": 0.4749, "step": 163130 }, { "epoch": 0.9697380387681224, "grad_norm": 4.428280353546143, "learning_rate": 9.733550582567119e-06, "loss": 0.5669, "step": 163140 }, { "epoch": 0.9697974808447908, "grad_norm": 4.079558372497559, "learning_rate": 9.73348374800027e-06, "loss": 0.5071, "step": 163150 }, { "epoch": 0.9698569229214592, "grad_norm": 5.471470355987549, "learning_rate": 9.733416905281797e-06, "loss": 0.5156, "step": 163160 }, { "epoch": 0.9699163649981276, "grad_norm": 5.397525310516357, "learning_rate": 9.733350054411815e-06, "loss": 0.5449, "step": 163170 }, { "epoch": 0.9699758070747959, "grad_norm": 4.298765659332275, "learning_rate": 9.733283195390439e-06, "loss": 0.4928, "step": 163180 }, { "epoch": 0.9700352491514643, "grad_norm": 5.155807971954346, "learning_rate": 9.733216328217787e-06, "loss": 0.5093, "step": 163190 }, { "epoch": 0.9700946912281327, "grad_norm": 4.197573661804199, "learning_rate": 9.733149452893969e-06, "loss": 0.5007, "step": 163200 }, { "epoch": 0.9701541333048012, "grad_norm": 6.080873489379883, "learning_rate": 9.733082569419104e-06, "loss": 0.5069, "step": 163210 }, { "epoch": 0.9702135753814696, "grad_norm": 4.992217063903809, "learning_rate": 9.733015677793305e-06, "loss": 0.4537, "step": 163220 }, { "epoch": 0.9702730174581379, "grad_norm": 6.161675930023193, "learning_rate": 9.73294877801669e-06, "loss": 0.5877, "step": 163230 }, { "epoch": 0.9703324595348063, "grad_norm": 5.742595195770264, "learning_rate": 9.732881870089373e-06, "loss": 0.5739, "step": 163240 }, { "epoch": 0.9703919016114747, "grad_norm": 5.121334552764893, "learning_rate": 9.732814954011466e-06, "loss": 0.554, "step": 163250 }, { "epoch": 0.9704513436881431, "grad_norm": 3.945068359375, "learning_rate": 9.732748029783088e-06, "loss": 0.5261, "step": 163260 }, { "epoch": 0.9705107857648115, "grad_norm": 4.016528606414795, "learning_rate": 9.732681097404354e-06, "loss": 0.5808, "step": 163270 }, { "epoch": 0.9705702278414798, "grad_norm": 6.416450023651123, "learning_rate": 9.732614156875378e-06, "loss": 0.5508, "step": 163280 }, { "epoch": 0.9706296699181483, "grad_norm": 4.588740825653076, "learning_rate": 9.732547208196278e-06, "loss": 0.5412, "step": 163290 }, { "epoch": 0.9706891119948167, "grad_norm": 4.38946008682251, "learning_rate": 9.732480251367162e-06, "loss": 0.5492, "step": 163300 }, { "epoch": 0.9707485540714851, "grad_norm": 4.2275710105896, "learning_rate": 9.732413286388154e-06, "loss": 0.5336, "step": 163310 }, { "epoch": 0.9708079961481534, "grad_norm": 5.542357444763184, "learning_rate": 9.732346313259365e-06, "loss": 0.5253, "step": 163320 }, { "epoch": 0.9708674382248218, "grad_norm": 4.685160160064697, "learning_rate": 9.73227933198091e-06, "loss": 0.5465, "step": 163330 }, { "epoch": 0.9709268803014902, "grad_norm": 4.069966793060303, "learning_rate": 9.732212342552907e-06, "loss": 0.5442, "step": 163340 }, { "epoch": 0.9709863223781586, "grad_norm": 5.102761268615723, "learning_rate": 9.732145344975468e-06, "loss": 0.5603, "step": 163350 }, { "epoch": 0.971045764454827, "grad_norm": 5.268767833709717, "learning_rate": 9.732078339248712e-06, "loss": 0.5438, "step": 163360 }, { "epoch": 0.9711052065314953, "grad_norm": 6.154078483581543, "learning_rate": 9.732011325372751e-06, "loss": 0.5462, "step": 163370 }, { "epoch": 0.9711646486081638, "grad_norm": 4.733826637268066, "learning_rate": 9.731944303347702e-06, "loss": 0.5031, "step": 163380 }, { "epoch": 0.9712240906848322, "grad_norm": 5.087372303009033, "learning_rate": 9.73187727317368e-06, "loss": 0.5687, "step": 163390 }, { "epoch": 0.9712835327615006, "grad_norm": 6.360274791717529, "learning_rate": 9.731810234850802e-06, "loss": 0.5568, "step": 163400 }, { "epoch": 0.9713429748381689, "grad_norm": 5.0515875816345215, "learning_rate": 9.731743188379182e-06, "loss": 0.5824, "step": 163410 }, { "epoch": 0.9714024169148373, "grad_norm": 5.885373115539551, "learning_rate": 9.731676133758933e-06, "loss": 0.5027, "step": 163420 }, { "epoch": 0.9714618589915057, "grad_norm": 3.922279119491577, "learning_rate": 9.731609070990177e-06, "loss": 0.517, "step": 163430 }, { "epoch": 0.9715213010681741, "grad_norm": 4.974620342254639, "learning_rate": 9.731542000073024e-06, "loss": 0.5383, "step": 163440 }, { "epoch": 0.9715807431448426, "grad_norm": 5.840025424957275, "learning_rate": 9.731474921007591e-06, "loss": 0.5477, "step": 163450 }, { "epoch": 0.9716401852215109, "grad_norm": 4.534658432006836, "learning_rate": 9.731407833793994e-06, "loss": 0.5903, "step": 163460 }, { "epoch": 0.9716996272981793, "grad_norm": 4.477681636810303, "learning_rate": 9.731340738432346e-06, "loss": 0.5109, "step": 163470 }, { "epoch": 0.9717590693748477, "grad_norm": 4.159285068511963, "learning_rate": 9.731273634922767e-06, "loss": 0.522, "step": 163480 }, { "epoch": 0.9718185114515161, "grad_norm": 4.4360175132751465, "learning_rate": 9.731206523265371e-06, "loss": 0.497, "step": 163490 }, { "epoch": 0.9718779535281845, "grad_norm": 6.353643417358398, "learning_rate": 9.73113940346027e-06, "loss": 0.4801, "step": 163500 }, { "epoch": 0.9719373956048528, "grad_norm": 6.192410469055176, "learning_rate": 9.731072275507586e-06, "loss": 0.5137, "step": 163510 }, { "epoch": 0.9719968376815212, "grad_norm": 4.6214680671691895, "learning_rate": 9.731005139407428e-06, "loss": 0.5296, "step": 163520 }, { "epoch": 0.9720562797581896, "grad_norm": 4.478835582733154, "learning_rate": 9.730937995159916e-06, "loss": 0.5473, "step": 163530 }, { "epoch": 0.9721157218348581, "grad_norm": 4.53252649307251, "learning_rate": 9.730870842765165e-06, "loss": 0.5415, "step": 163540 }, { "epoch": 0.9721751639115264, "grad_norm": 4.742921829223633, "learning_rate": 9.730803682223289e-06, "loss": 0.5503, "step": 163550 }, { "epoch": 0.9722346059881948, "grad_norm": 5.459769248962402, "learning_rate": 9.730736513534404e-06, "loss": 0.5482, "step": 163560 }, { "epoch": 0.9722940480648632, "grad_norm": 5.810924053192139, "learning_rate": 9.730669336698626e-06, "loss": 0.5103, "step": 163570 }, { "epoch": 0.9723534901415316, "grad_norm": 4.885672569274902, "learning_rate": 9.730602151716073e-06, "loss": 0.5054, "step": 163580 }, { "epoch": 0.9724129322182, "grad_norm": 4.362674236297607, "learning_rate": 9.730534958586857e-06, "loss": 0.5354, "step": 163590 }, { "epoch": 0.9724723742948683, "grad_norm": 4.558535099029541, "learning_rate": 9.730467757311095e-06, "loss": 0.5587, "step": 163600 }, { "epoch": 0.9725318163715367, "grad_norm": 4.218353748321533, "learning_rate": 9.730400547888904e-06, "loss": 0.5413, "step": 163610 }, { "epoch": 0.9725912584482052, "grad_norm": 5.110340118408203, "learning_rate": 9.730333330320399e-06, "loss": 0.5024, "step": 163620 }, { "epoch": 0.9726507005248736, "grad_norm": 4.217377662658691, "learning_rate": 9.730266104605695e-06, "loss": 0.5151, "step": 163630 }, { "epoch": 0.972710142601542, "grad_norm": 5.217257022857666, "learning_rate": 9.73019887074491e-06, "loss": 0.5393, "step": 163640 }, { "epoch": 0.9727695846782103, "grad_norm": 4.379227638244629, "learning_rate": 9.730131628738156e-06, "loss": 0.5352, "step": 163650 }, { "epoch": 0.9728290267548787, "grad_norm": 6.073167324066162, "learning_rate": 9.73006437858555e-06, "loss": 0.5811, "step": 163660 }, { "epoch": 0.9728884688315471, "grad_norm": 5.080599784851074, "learning_rate": 9.729997120287212e-06, "loss": 0.5335, "step": 163670 }, { "epoch": 0.9729479109082155, "grad_norm": 4.573111057281494, "learning_rate": 9.729929853843252e-06, "loss": 0.525, "step": 163680 }, { "epoch": 0.9730073529848838, "grad_norm": 6.15369176864624, "learning_rate": 9.72986257925379e-06, "loss": 0.5621, "step": 163690 }, { "epoch": 0.9730667950615522, "grad_norm": 5.293786525726318, "learning_rate": 9.729795296518941e-06, "loss": 0.4996, "step": 163700 }, { "epoch": 0.9731262371382207, "grad_norm": 7.352361679077148, "learning_rate": 9.72972800563882e-06, "loss": 0.6079, "step": 163710 }, { "epoch": 0.9731856792148891, "grad_norm": 4.001144886016846, "learning_rate": 9.729660706613541e-06, "loss": 0.5396, "step": 163720 }, { "epoch": 0.9732451212915575, "grad_norm": 5.662785530090332, "learning_rate": 9.729593399443223e-06, "loss": 0.5322, "step": 163730 }, { "epoch": 0.9733045633682258, "grad_norm": 5.780305862426758, "learning_rate": 9.72952608412798e-06, "loss": 0.5717, "step": 163740 }, { "epoch": 0.9733640054448942, "grad_norm": 6.019118785858154, "learning_rate": 9.729458760667929e-06, "loss": 0.5195, "step": 163750 }, { "epoch": 0.9734234475215626, "grad_norm": 5.436434745788574, "learning_rate": 9.729391429063187e-06, "loss": 0.4996, "step": 163760 }, { "epoch": 0.973482889598231, "grad_norm": 6.034422874450684, "learning_rate": 9.729324089313867e-06, "loss": 0.5165, "step": 163770 }, { "epoch": 0.9735423316748993, "grad_norm": 4.227256774902344, "learning_rate": 9.729256741420088e-06, "loss": 0.5304, "step": 163780 }, { "epoch": 0.9736017737515678, "grad_norm": 4.144526958465576, "learning_rate": 9.729189385381966e-06, "loss": 0.546, "step": 163790 }, { "epoch": 0.9736612158282362, "grad_norm": 5.5943403244018555, "learning_rate": 9.729122021199613e-06, "loss": 0.5186, "step": 163800 }, { "epoch": 0.9737206579049046, "grad_norm": 5.389439105987549, "learning_rate": 9.729054648873147e-06, "loss": 0.5676, "step": 163810 }, { "epoch": 0.973780099981573, "grad_norm": 3.791591167449951, "learning_rate": 9.728987268402687e-06, "loss": 0.5243, "step": 163820 }, { "epoch": 0.9738395420582413, "grad_norm": 3.7846717834472656, "learning_rate": 9.728919879788346e-06, "loss": 0.5192, "step": 163830 }, { "epoch": 0.9738989841349097, "grad_norm": 6.189380168914795, "learning_rate": 9.72885248303024e-06, "loss": 0.5727, "step": 163840 }, { "epoch": 0.9739584262115781, "grad_norm": 5.064491271972656, "learning_rate": 9.728785078128486e-06, "loss": 0.5403, "step": 163850 }, { "epoch": 0.9740178682882465, "grad_norm": 4.220115661621094, "learning_rate": 9.7287176650832e-06, "loss": 0.5124, "step": 163860 }, { "epoch": 0.974077310364915, "grad_norm": 4.653538227081299, "learning_rate": 9.728650243894498e-06, "loss": 0.5524, "step": 163870 }, { "epoch": 0.9741367524415833, "grad_norm": 5.190278053283691, "learning_rate": 9.728582814562494e-06, "loss": 0.5416, "step": 163880 }, { "epoch": 0.9741961945182517, "grad_norm": 6.224888324737549, "learning_rate": 9.728515377087309e-06, "loss": 0.5112, "step": 163890 }, { "epoch": 0.9742556365949201, "grad_norm": 4.730226516723633, "learning_rate": 9.728447931469056e-06, "loss": 0.5338, "step": 163900 }, { "epoch": 0.9743150786715885, "grad_norm": 4.704984664916992, "learning_rate": 9.728380477707851e-06, "loss": 0.5246, "step": 163910 }, { "epoch": 0.9743745207482568, "grad_norm": 8.569941520690918, "learning_rate": 9.72831301580381e-06, "loss": 0.5837, "step": 163920 }, { "epoch": 0.9744339628249252, "grad_norm": 4.869572639465332, "learning_rate": 9.72824554575705e-06, "loss": 0.5642, "step": 163930 }, { "epoch": 0.9744934049015936, "grad_norm": 5.657339572906494, "learning_rate": 9.728178067567689e-06, "loss": 0.5454, "step": 163940 }, { "epoch": 0.974552846978262, "grad_norm": 5.623809814453125, "learning_rate": 9.72811058123584e-06, "loss": 0.5211, "step": 163950 }, { "epoch": 0.9746122890549305, "grad_norm": 6.232571601867676, "learning_rate": 9.72804308676162e-06, "loss": 0.5382, "step": 163960 }, { "epoch": 0.9746717311315988, "grad_norm": 5.405698299407959, "learning_rate": 9.727975584145146e-06, "loss": 0.5587, "step": 163970 }, { "epoch": 0.9747311732082672, "grad_norm": 4.74399995803833, "learning_rate": 9.727908073386534e-06, "loss": 0.5197, "step": 163980 }, { "epoch": 0.9747906152849356, "grad_norm": 4.890955924987793, "learning_rate": 9.727840554485899e-06, "loss": 0.5032, "step": 163990 }, { "epoch": 0.974850057361604, "grad_norm": 5.6093244552612305, "learning_rate": 9.727773027443359e-06, "loss": 0.5078, "step": 164000 }, { "epoch": 0.9749094994382723, "grad_norm": 5.328607082366943, "learning_rate": 9.72770549225903e-06, "loss": 0.5401, "step": 164010 }, { "epoch": 0.9749689415149407, "grad_norm": 6.953178882598877, "learning_rate": 9.727637948933028e-06, "loss": 0.4888, "step": 164020 }, { "epoch": 0.9750283835916091, "grad_norm": 5.384453773498535, "learning_rate": 9.72757039746547e-06, "loss": 0.5395, "step": 164030 }, { "epoch": 0.9750878256682776, "grad_norm": 5.682949066162109, "learning_rate": 9.72750283785647e-06, "loss": 0.5502, "step": 164040 }, { "epoch": 0.975147267744946, "grad_norm": 4.512138843536377, "learning_rate": 9.727435270106147e-06, "loss": 0.5104, "step": 164050 }, { "epoch": 0.9752067098216143, "grad_norm": 4.493745803833008, "learning_rate": 9.727367694214618e-06, "loss": 0.4829, "step": 164060 }, { "epoch": 0.9752661518982827, "grad_norm": 5.604984283447266, "learning_rate": 9.727300110181996e-06, "loss": 0.5145, "step": 164070 }, { "epoch": 0.9753255939749511, "grad_norm": 4.875814914703369, "learning_rate": 9.727232518008401e-06, "loss": 0.5363, "step": 164080 }, { "epoch": 0.9753850360516195, "grad_norm": 5.851416110992432, "learning_rate": 9.727164917693946e-06, "loss": 0.5289, "step": 164090 }, { "epoch": 0.9754444781282879, "grad_norm": 4.117873191833496, "learning_rate": 9.727097309238748e-06, "loss": 0.5321, "step": 164100 }, { "epoch": 0.9755039202049562, "grad_norm": 7.9397358894348145, "learning_rate": 9.727029692642925e-06, "loss": 0.5787, "step": 164110 }, { "epoch": 0.9755633622816247, "grad_norm": 4.956264495849609, "learning_rate": 9.726962067906594e-06, "loss": 0.5263, "step": 164120 }, { "epoch": 0.9756228043582931, "grad_norm": 5.099874496459961, "learning_rate": 9.72689443502987e-06, "loss": 0.4953, "step": 164130 }, { "epoch": 0.9756822464349615, "grad_norm": 7.811008453369141, "learning_rate": 9.726826794012868e-06, "loss": 0.5713, "step": 164140 }, { "epoch": 0.9757416885116298, "grad_norm": 6.079753875732422, "learning_rate": 9.726759144855708e-06, "loss": 0.5637, "step": 164150 }, { "epoch": 0.9758011305882982, "grad_norm": 5.334713935852051, "learning_rate": 9.726691487558504e-06, "loss": 0.536, "step": 164160 }, { "epoch": 0.9758605726649666, "grad_norm": 4.770320892333984, "learning_rate": 9.726623822121375e-06, "loss": 0.5232, "step": 164170 }, { "epoch": 0.975920014741635, "grad_norm": 5.0795135498046875, "learning_rate": 9.726556148544435e-06, "loss": 0.5039, "step": 164180 }, { "epoch": 0.9759794568183034, "grad_norm": 4.939215183258057, "learning_rate": 9.726488466827799e-06, "loss": 0.5442, "step": 164190 }, { "epoch": 0.9760388988949718, "grad_norm": 5.717290878295898, "learning_rate": 9.726420776971588e-06, "loss": 0.5218, "step": 164200 }, { "epoch": 0.9760983409716402, "grad_norm": 5.540809631347656, "learning_rate": 9.726353078975916e-06, "loss": 0.5329, "step": 164210 }, { "epoch": 0.9761577830483086, "grad_norm": 5.2460713386535645, "learning_rate": 9.7262853728409e-06, "loss": 0.547, "step": 164220 }, { "epoch": 0.976217225124977, "grad_norm": 3.5197014808654785, "learning_rate": 9.726217658566658e-06, "loss": 0.4801, "step": 164230 }, { "epoch": 0.9762766672016454, "grad_norm": 7.68695068359375, "learning_rate": 9.726149936153304e-06, "loss": 0.5102, "step": 164240 }, { "epoch": 0.9763361092783137, "grad_norm": 5.126970291137695, "learning_rate": 9.726082205600957e-06, "loss": 0.551, "step": 164250 }, { "epoch": 0.9763955513549821, "grad_norm": 7.582056999206543, "learning_rate": 9.72601446690973e-06, "loss": 0.5733, "step": 164260 }, { "epoch": 0.9764549934316505, "grad_norm": 5.357242584228516, "learning_rate": 9.725946720079744e-06, "loss": 0.5805, "step": 164270 }, { "epoch": 0.976514435508319, "grad_norm": 5.8673505783081055, "learning_rate": 9.725878965111115e-06, "loss": 0.5051, "step": 164280 }, { "epoch": 0.9765738775849873, "grad_norm": 4.512568950653076, "learning_rate": 9.725811202003956e-06, "loss": 0.5822, "step": 164290 }, { "epoch": 0.9766333196616557, "grad_norm": 3.913534641265869, "learning_rate": 9.725743430758387e-06, "loss": 0.5399, "step": 164300 }, { "epoch": 0.9766927617383241, "grad_norm": 5.1799635887146, "learning_rate": 9.725675651374526e-06, "loss": 0.5513, "step": 164310 }, { "epoch": 0.9767522038149925, "grad_norm": 5.651913642883301, "learning_rate": 9.725607863852485e-06, "loss": 0.5389, "step": 164320 }, { "epoch": 0.9768116458916609, "grad_norm": 5.5749735832214355, "learning_rate": 9.725540068192384e-06, "loss": 0.559, "step": 164330 }, { "epoch": 0.9768710879683292, "grad_norm": 4.560405254364014, "learning_rate": 9.72547226439434e-06, "loss": 0.5523, "step": 164340 }, { "epoch": 0.9769305300449976, "grad_norm": 4.967276096343994, "learning_rate": 9.725404452458469e-06, "loss": 0.5278, "step": 164350 }, { "epoch": 0.976989972121666, "grad_norm": 4.706087589263916, "learning_rate": 9.725336632384888e-06, "loss": 0.546, "step": 164360 }, { "epoch": 0.9770494141983345, "grad_norm": 5.8969926834106445, "learning_rate": 9.725268804173713e-06, "loss": 0.5044, "step": 164370 }, { "epoch": 0.9771088562750028, "grad_norm": 6.531156539916992, "learning_rate": 9.72520096782506e-06, "loss": 0.4732, "step": 164380 }, { "epoch": 0.9771682983516712, "grad_norm": 4.06363582611084, "learning_rate": 9.725133123339047e-06, "loss": 0.4684, "step": 164390 }, { "epoch": 0.9772277404283396, "grad_norm": 5.622210502624512, "learning_rate": 9.725065270715793e-06, "loss": 0.4853, "step": 164400 }, { "epoch": 0.977287182505008, "grad_norm": 4.229562759399414, "learning_rate": 9.724997409955413e-06, "loss": 0.4861, "step": 164410 }, { "epoch": 0.9773466245816764, "grad_norm": 6.1785054206848145, "learning_rate": 9.724929541058023e-06, "loss": 0.5176, "step": 164420 }, { "epoch": 0.9774060666583447, "grad_norm": 5.101765155792236, "learning_rate": 9.72486166402374e-06, "loss": 0.5383, "step": 164430 }, { "epoch": 0.9774655087350131, "grad_norm": 5.14218807220459, "learning_rate": 9.724793778852682e-06, "loss": 0.5177, "step": 164440 }, { "epoch": 0.9775249508116816, "grad_norm": 5.498030662536621, "learning_rate": 9.724725885544964e-06, "loss": 0.5317, "step": 164450 }, { "epoch": 0.97758439288835, "grad_norm": 4.866833209991455, "learning_rate": 9.724657984100706e-06, "loss": 0.5117, "step": 164460 }, { "epoch": 0.9776438349650184, "grad_norm": 5.9399943351745605, "learning_rate": 9.724590074520022e-06, "loss": 0.4901, "step": 164470 }, { "epoch": 0.9777032770416867, "grad_norm": 4.3997907638549805, "learning_rate": 9.72452215680303e-06, "loss": 0.499, "step": 164480 }, { "epoch": 0.9777627191183551, "grad_norm": 4.702857971191406, "learning_rate": 9.72445423094985e-06, "loss": 0.5168, "step": 164490 }, { "epoch": 0.9778221611950235, "grad_norm": 5.804643630981445, "learning_rate": 9.724386296960593e-06, "loss": 0.5028, "step": 164500 }, { "epoch": 0.9778816032716919, "grad_norm": 5.095904350280762, "learning_rate": 9.72431835483538e-06, "loss": 0.5266, "step": 164510 }, { "epoch": 0.9779410453483602, "grad_norm": 6.439650535583496, "learning_rate": 9.724250404574328e-06, "loss": 0.5716, "step": 164520 }, { "epoch": 0.9780004874250287, "grad_norm": 5.342871189117432, "learning_rate": 9.724182446177551e-06, "loss": 0.4836, "step": 164530 }, { "epoch": 0.9780599295016971, "grad_norm": 5.391656875610352, "learning_rate": 9.72411447964517e-06, "loss": 0.5595, "step": 164540 }, { "epoch": 0.9781193715783655, "grad_norm": 4.174139976501465, "learning_rate": 9.724046504977299e-06, "loss": 0.5131, "step": 164550 }, { "epoch": 0.9781788136550339, "grad_norm": 6.225515365600586, "learning_rate": 9.723978522174057e-06, "loss": 0.5158, "step": 164560 }, { "epoch": 0.9782382557317022, "grad_norm": 5.392599582672119, "learning_rate": 9.72391053123556e-06, "loss": 0.5305, "step": 164570 }, { "epoch": 0.9782976978083706, "grad_norm": 8.252684593200684, "learning_rate": 9.723842532161925e-06, "loss": 0.5186, "step": 164580 }, { "epoch": 0.978357139885039, "grad_norm": 5.36835241317749, "learning_rate": 9.72377452495327e-06, "loss": 0.6028, "step": 164590 }, { "epoch": 0.9784165819617074, "grad_norm": 4.944255828857422, "learning_rate": 9.723706509609713e-06, "loss": 0.5652, "step": 164600 }, { "epoch": 0.9784760240383759, "grad_norm": 5.451896667480469, "learning_rate": 9.723638486131368e-06, "loss": 0.5325, "step": 164610 }, { "epoch": 0.9785354661150442, "grad_norm": 3.9524447917938232, "learning_rate": 9.723570454518355e-06, "loss": 0.4733, "step": 164620 }, { "epoch": 0.9785949081917126, "grad_norm": 6.580283164978027, "learning_rate": 9.723502414770789e-06, "loss": 0.5509, "step": 164630 }, { "epoch": 0.978654350268381, "grad_norm": 5.542332649230957, "learning_rate": 9.72343436688879e-06, "loss": 0.5464, "step": 164640 }, { "epoch": 0.9787137923450494, "grad_norm": 5.762517929077148, "learning_rate": 9.72336631087247e-06, "loss": 0.5206, "step": 164650 }, { "epoch": 0.9787732344217177, "grad_norm": 5.065352916717529, "learning_rate": 9.723298246721953e-06, "loss": 0.4885, "step": 164660 }, { "epoch": 0.9788326764983861, "grad_norm": 5.2246880531311035, "learning_rate": 9.723230174437351e-06, "loss": 0.5507, "step": 164670 }, { "epoch": 0.9788921185750545, "grad_norm": 4.602172374725342, "learning_rate": 9.723162094018783e-06, "loss": 0.4912, "step": 164680 }, { "epoch": 0.978951560651723, "grad_norm": 4.928413391113281, "learning_rate": 9.723094005466368e-06, "loss": 0.5141, "step": 164690 }, { "epoch": 0.9790110027283914, "grad_norm": 6.194728374481201, "learning_rate": 9.723025908780221e-06, "loss": 0.5274, "step": 164700 }, { "epoch": 0.9790704448050597, "grad_norm": 6.437801361083984, "learning_rate": 9.722957803960459e-06, "loss": 0.4995, "step": 164710 }, { "epoch": 0.9791298868817281, "grad_norm": 5.129175662994385, "learning_rate": 9.7228896910072e-06, "loss": 0.487, "step": 164720 }, { "epoch": 0.9791893289583965, "grad_norm": 5.144564628601074, "learning_rate": 9.722821569920562e-06, "loss": 0.606, "step": 164730 }, { "epoch": 0.9792487710350649, "grad_norm": 5.722412109375, "learning_rate": 9.722753440700662e-06, "loss": 0.5555, "step": 164740 }, { "epoch": 0.9793082131117332, "grad_norm": 5.3444390296936035, "learning_rate": 9.722685303347616e-06, "loss": 0.5068, "step": 164750 }, { "epoch": 0.9793676551884016, "grad_norm": 3.2762739658355713, "learning_rate": 9.722617157861544e-06, "loss": 0.5503, "step": 164760 }, { "epoch": 0.97942709726507, "grad_norm": 5.671566963195801, "learning_rate": 9.72254900424256e-06, "loss": 0.493, "step": 164770 }, { "epoch": 0.9794865393417385, "grad_norm": 5.020060062408447, "learning_rate": 9.722480842490786e-06, "loss": 0.519, "step": 164780 }, { "epoch": 0.9795459814184069, "grad_norm": 4.860074043273926, "learning_rate": 9.722412672606334e-06, "loss": 0.4633, "step": 164790 }, { "epoch": 0.9796054234950752, "grad_norm": 5.633119106292725, "learning_rate": 9.722344494589325e-06, "loss": 0.5232, "step": 164800 }, { "epoch": 0.9796648655717436, "grad_norm": 5.522932529449463, "learning_rate": 9.722276308439874e-06, "loss": 0.5041, "step": 164810 }, { "epoch": 0.979724307648412, "grad_norm": 5.239050388336182, "learning_rate": 9.7222081141581e-06, "loss": 0.5504, "step": 164820 }, { "epoch": 0.9797837497250804, "grad_norm": 6.078453063964844, "learning_rate": 9.722139911744121e-06, "loss": 0.547, "step": 164830 }, { "epoch": 0.9798431918017488, "grad_norm": 6.228521823883057, "learning_rate": 9.722071701198055e-06, "loss": 0.5119, "step": 164840 }, { "epoch": 0.9799026338784171, "grad_norm": 5.213631629943848, "learning_rate": 9.722003482520016e-06, "loss": 0.5371, "step": 164850 }, { "epoch": 0.9799620759550856, "grad_norm": 4.5160932540893555, "learning_rate": 9.721935255710124e-06, "loss": 0.5339, "step": 164860 }, { "epoch": 0.980021518031754, "grad_norm": 6.643525123596191, "learning_rate": 9.721867020768496e-06, "loss": 0.5075, "step": 164870 }, { "epoch": 0.9800809601084224, "grad_norm": 5.821133136749268, "learning_rate": 9.721798777695249e-06, "loss": 0.5766, "step": 164880 }, { "epoch": 0.9801404021850907, "grad_norm": 4.916841506958008, "learning_rate": 9.721730526490502e-06, "loss": 0.5341, "step": 164890 }, { "epoch": 0.9801998442617591, "grad_norm": 5.461383819580078, "learning_rate": 9.721662267154373e-06, "loss": 0.5108, "step": 164900 }, { "epoch": 0.9802592863384275, "grad_norm": 6.063787937164307, "learning_rate": 9.721593999686976e-06, "loss": 0.5469, "step": 164910 }, { "epoch": 0.9803187284150959, "grad_norm": 5.449458122253418, "learning_rate": 9.721525724088433e-06, "loss": 0.503, "step": 164920 }, { "epoch": 0.9803781704917643, "grad_norm": 4.8932647705078125, "learning_rate": 9.721457440358855e-06, "loss": 0.5196, "step": 164930 }, { "epoch": 0.9804376125684326, "grad_norm": 5.7911577224731445, "learning_rate": 9.721389148498369e-06, "loss": 0.5317, "step": 164940 }, { "epoch": 0.9804970546451011, "grad_norm": 4.18928337097168, "learning_rate": 9.721320848507084e-06, "loss": 0.5458, "step": 164950 }, { "epoch": 0.9805564967217695, "grad_norm": 4.919630527496338, "learning_rate": 9.721252540385123e-06, "loss": 0.5059, "step": 164960 }, { "epoch": 0.9806159387984379, "grad_norm": 4.726501941680908, "learning_rate": 9.721184224132601e-06, "loss": 0.5602, "step": 164970 }, { "epoch": 0.9806753808751063, "grad_norm": 6.668519020080566, "learning_rate": 9.721115899749635e-06, "loss": 0.4961, "step": 164980 }, { "epoch": 0.9807348229517746, "grad_norm": 5.606749534606934, "learning_rate": 9.721047567236348e-06, "loss": 0.521, "step": 164990 }, { "epoch": 0.980794265028443, "grad_norm": 4.245607852935791, "learning_rate": 9.72097922659285e-06, "loss": 0.5048, "step": 165000 }, { "epoch": 0.9808537071051114, "grad_norm": 4.164578914642334, "learning_rate": 9.720910877819265e-06, "loss": 0.4957, "step": 165010 }, { "epoch": 0.9809131491817799, "grad_norm": 4.392898082733154, "learning_rate": 9.720842520915708e-06, "loss": 0.5138, "step": 165020 }, { "epoch": 0.9809725912584482, "grad_norm": 5.2776103019714355, "learning_rate": 9.720774155882295e-06, "loss": 0.595, "step": 165030 }, { "epoch": 0.9810320333351166, "grad_norm": 5.327975749969482, "learning_rate": 9.720705782719147e-06, "loss": 0.4748, "step": 165040 }, { "epoch": 0.981091475411785, "grad_norm": 5.976655006408691, "learning_rate": 9.72063740142638e-06, "loss": 0.5287, "step": 165050 }, { "epoch": 0.9811509174884534, "grad_norm": 5.423290252685547, "learning_rate": 9.720569012004114e-06, "loss": 0.5009, "step": 165060 }, { "epoch": 0.9812103595651218, "grad_norm": 5.161001682281494, "learning_rate": 9.720500614452462e-06, "loss": 0.5796, "step": 165070 }, { "epoch": 0.9812698016417901, "grad_norm": 4.54904842376709, "learning_rate": 9.720432208771545e-06, "loss": 0.485, "step": 165080 }, { "epoch": 0.9813292437184585, "grad_norm": 4.275977611541748, "learning_rate": 9.720363794961481e-06, "loss": 0.5034, "step": 165090 }, { "epoch": 0.981388685795127, "grad_norm": 4.36382532119751, "learning_rate": 9.720295373022389e-06, "loss": 0.4861, "step": 165100 }, { "epoch": 0.9814481278717954, "grad_norm": 5.911175727844238, "learning_rate": 9.720226942954382e-06, "loss": 0.5023, "step": 165110 }, { "epoch": 0.9815075699484637, "grad_norm": 5.665727615356445, "learning_rate": 9.720158504757585e-06, "loss": 0.5586, "step": 165120 }, { "epoch": 0.9815670120251321, "grad_norm": 5.774144649505615, "learning_rate": 9.720090058432108e-06, "loss": 0.5168, "step": 165130 }, { "epoch": 0.9816264541018005, "grad_norm": 4.864193439483643, "learning_rate": 9.720021603978076e-06, "loss": 0.5093, "step": 165140 }, { "epoch": 0.9816858961784689, "grad_norm": 6.296143054962158, "learning_rate": 9.719953141395601e-06, "loss": 0.5304, "step": 165150 }, { "epoch": 0.9817453382551373, "grad_norm": 5.3247389793396, "learning_rate": 9.719884670684805e-06, "loss": 0.5303, "step": 165160 }, { "epoch": 0.9818047803318056, "grad_norm": 4.195146083831787, "learning_rate": 9.719816191845804e-06, "loss": 0.5015, "step": 165170 }, { "epoch": 0.981864222408474, "grad_norm": 5.712615013122559, "learning_rate": 9.719747704878716e-06, "loss": 0.5531, "step": 165180 }, { "epoch": 0.9819236644851425, "grad_norm": 5.256160259246826, "learning_rate": 9.71967920978366e-06, "loss": 0.5161, "step": 165190 }, { "epoch": 0.9819831065618109, "grad_norm": 4.9267706871032715, "learning_rate": 9.719610706560752e-06, "loss": 0.5178, "step": 165200 }, { "epoch": 0.9820425486384793, "grad_norm": 4.456559658050537, "learning_rate": 9.719542195210112e-06, "loss": 0.4623, "step": 165210 }, { "epoch": 0.9821019907151476, "grad_norm": 3.9762439727783203, "learning_rate": 9.719473675731859e-06, "loss": 0.4918, "step": 165220 }, { "epoch": 0.982161432791816, "grad_norm": 7.047631740570068, "learning_rate": 9.719405148126107e-06, "loss": 0.5285, "step": 165230 }, { "epoch": 0.9822208748684844, "grad_norm": 4.12355899810791, "learning_rate": 9.719336612392976e-06, "loss": 0.5053, "step": 165240 }, { "epoch": 0.9822803169451528, "grad_norm": 5.041971683502197, "learning_rate": 9.719268068532586e-06, "loss": 0.5534, "step": 165250 }, { "epoch": 0.9823397590218211, "grad_norm": 4.021071434020996, "learning_rate": 9.719199516545051e-06, "loss": 0.5454, "step": 165260 }, { "epoch": 0.9823992010984895, "grad_norm": 5.0854339599609375, "learning_rate": 9.719130956430493e-06, "loss": 0.5446, "step": 165270 }, { "epoch": 0.982458643175158, "grad_norm": 6.597497463226318, "learning_rate": 9.719062388189029e-06, "loss": 0.5165, "step": 165280 }, { "epoch": 0.9825180852518264, "grad_norm": 5.428037166595459, "learning_rate": 9.718993811820775e-06, "loss": 0.5239, "step": 165290 }, { "epoch": 0.9825775273284948, "grad_norm": 5.6103339195251465, "learning_rate": 9.71892522732585e-06, "loss": 0.5189, "step": 165300 }, { "epoch": 0.9826369694051631, "grad_norm": 4.616669654846191, "learning_rate": 9.718856634704375e-06, "loss": 0.5109, "step": 165310 }, { "epoch": 0.9826964114818315, "grad_norm": 5.968103885650635, "learning_rate": 9.718788033956465e-06, "loss": 0.507, "step": 165320 }, { "epoch": 0.9827558535584999, "grad_norm": 5.1835479736328125, "learning_rate": 9.718719425082239e-06, "loss": 0.5336, "step": 165330 }, { "epoch": 0.9828152956351683, "grad_norm": 5.027568340301514, "learning_rate": 9.718650808081814e-06, "loss": 0.4876, "step": 165340 }, { "epoch": 0.9828747377118368, "grad_norm": 5.847177505493164, "learning_rate": 9.71858218295531e-06, "loss": 0.5091, "step": 165350 }, { "epoch": 0.9829341797885051, "grad_norm": 5.216607570648193, "learning_rate": 9.718513549702845e-06, "loss": 0.523, "step": 165360 }, { "epoch": 0.9829936218651735, "grad_norm": 5.075173854827881, "learning_rate": 9.718444908324536e-06, "loss": 0.4866, "step": 165370 }, { "epoch": 0.9830530639418419, "grad_norm": 4.3433990478515625, "learning_rate": 9.718376258820501e-06, "loss": 0.5356, "step": 165380 }, { "epoch": 0.9831125060185103, "grad_norm": 4.53526496887207, "learning_rate": 9.718307601190862e-06, "loss": 0.538, "step": 165390 }, { "epoch": 0.9831719480951786, "grad_norm": 5.540998935699463, "learning_rate": 9.718238935435731e-06, "loss": 0.5001, "step": 165400 }, { "epoch": 0.983231390171847, "grad_norm": 5.542679309844971, "learning_rate": 9.718170261555232e-06, "loss": 0.5357, "step": 165410 }, { "epoch": 0.9832908322485154, "grad_norm": 4.486686706542969, "learning_rate": 9.718101579549479e-06, "loss": 0.5368, "step": 165420 }, { "epoch": 0.9833502743251838, "grad_norm": 6.231746673583984, "learning_rate": 9.718032889418595e-06, "loss": 0.4926, "step": 165430 }, { "epoch": 0.9834097164018523, "grad_norm": 4.578474998474121, "learning_rate": 9.717964191162692e-06, "loss": 0.5345, "step": 165440 }, { "epoch": 0.9834691584785206, "grad_norm": 4.862283706665039, "learning_rate": 9.717895484781894e-06, "loss": 0.492, "step": 165450 }, { "epoch": 0.983528600555189, "grad_norm": 5.638769149780273, "learning_rate": 9.717826770276316e-06, "loss": 0.5604, "step": 165460 }, { "epoch": 0.9835880426318574, "grad_norm": 6.037417411804199, "learning_rate": 9.717758047646078e-06, "loss": 0.5059, "step": 165470 }, { "epoch": 0.9836474847085258, "grad_norm": 4.718858242034912, "learning_rate": 9.717689316891297e-06, "loss": 0.5632, "step": 165480 }, { "epoch": 0.9837069267851941, "grad_norm": 4.182912826538086, "learning_rate": 9.717620578012093e-06, "loss": 0.5872, "step": 165490 }, { "epoch": 0.9837663688618625, "grad_norm": 5.909914970397949, "learning_rate": 9.717551831008582e-06, "loss": 0.5635, "step": 165500 }, { "epoch": 0.9838258109385309, "grad_norm": 5.207393646240234, "learning_rate": 9.717483075880884e-06, "loss": 0.5521, "step": 165510 }, { "epoch": 0.9838852530151994, "grad_norm": 5.007447719573975, "learning_rate": 9.717414312629118e-06, "loss": 0.5545, "step": 165520 }, { "epoch": 0.9839446950918678, "grad_norm": 4.314691543579102, "learning_rate": 9.717345541253402e-06, "loss": 0.5459, "step": 165530 }, { "epoch": 0.9840041371685361, "grad_norm": 5.950360298156738, "learning_rate": 9.717276761753855e-06, "loss": 0.492, "step": 165540 }, { "epoch": 0.9840635792452045, "grad_norm": 5.652115345001221, "learning_rate": 9.717207974130593e-06, "loss": 0.5161, "step": 165550 }, { "epoch": 0.9841230213218729, "grad_norm": 4.7855682373046875, "learning_rate": 9.717139178383737e-06, "loss": 0.5228, "step": 165560 }, { "epoch": 0.9841824633985413, "grad_norm": 4.044705867767334, "learning_rate": 9.717070374513404e-06, "loss": 0.457, "step": 165570 }, { "epoch": 0.9842419054752097, "grad_norm": 5.4627532958984375, "learning_rate": 9.717001562519713e-06, "loss": 0.5287, "step": 165580 }, { "epoch": 0.984301347551878, "grad_norm": 5.01500940322876, "learning_rate": 9.716932742402782e-06, "loss": 0.52, "step": 165590 }, { "epoch": 0.9843607896285465, "grad_norm": 5.188980579376221, "learning_rate": 9.716863914162731e-06, "loss": 0.4996, "step": 165600 }, { "epoch": 0.9844202317052149, "grad_norm": 4.658815383911133, "learning_rate": 9.716795077799676e-06, "loss": 0.5017, "step": 165610 }, { "epoch": 0.9844796737818833, "grad_norm": 4.41510009765625, "learning_rate": 9.716726233313739e-06, "loss": 0.536, "step": 165620 }, { "epoch": 0.9845391158585516, "grad_norm": 4.787298202514648, "learning_rate": 9.716657380705035e-06, "loss": 0.4747, "step": 165630 }, { "epoch": 0.98459855793522, "grad_norm": 6.079787731170654, "learning_rate": 9.716588519973684e-06, "loss": 0.4985, "step": 165640 }, { "epoch": 0.9846580000118884, "grad_norm": 4.96254825592041, "learning_rate": 9.716519651119806e-06, "loss": 0.538, "step": 165650 }, { "epoch": 0.9847174420885568, "grad_norm": 5.160402774810791, "learning_rate": 9.716450774143518e-06, "loss": 0.5038, "step": 165660 }, { "epoch": 0.9847768841652252, "grad_norm": 5.59893274307251, "learning_rate": 9.71638188904494e-06, "loss": 0.4988, "step": 165670 }, { "epoch": 0.9848363262418935, "grad_norm": 4.5505828857421875, "learning_rate": 9.716312995824188e-06, "loss": 0.571, "step": 165680 }, { "epoch": 0.984895768318562, "grad_norm": 3.9653263092041016, "learning_rate": 9.716244094481383e-06, "loss": 0.5779, "step": 165690 }, { "epoch": 0.9849552103952304, "grad_norm": 5.641097545623779, "learning_rate": 9.716175185016643e-06, "loss": 0.5646, "step": 165700 }, { "epoch": 0.9850146524718988, "grad_norm": 4.513152122497559, "learning_rate": 9.716106267430085e-06, "loss": 0.511, "step": 165710 }, { "epoch": 0.9850740945485672, "grad_norm": 5.104590892791748, "learning_rate": 9.716037341721832e-06, "loss": 0.5229, "step": 165720 }, { "epoch": 0.9851335366252355, "grad_norm": 4.501434326171875, "learning_rate": 9.715968407891998e-06, "loss": 0.5548, "step": 165730 }, { "epoch": 0.9851929787019039, "grad_norm": 5.291513919830322, "learning_rate": 9.715899465940705e-06, "loss": 0.5082, "step": 165740 }, { "epoch": 0.9852524207785723, "grad_norm": 4.669566631317139, "learning_rate": 9.715830515868069e-06, "loss": 0.5543, "step": 165750 }, { "epoch": 0.9853118628552407, "grad_norm": 4.136075019836426, "learning_rate": 9.715761557674213e-06, "loss": 0.4754, "step": 165760 }, { "epoch": 0.985371304931909, "grad_norm": 6.828907012939453, "learning_rate": 9.715692591359251e-06, "loss": 0.51, "step": 165770 }, { "epoch": 0.9854307470085775, "grad_norm": 3.579935073852539, "learning_rate": 9.715623616923303e-06, "loss": 0.5095, "step": 165780 }, { "epoch": 0.9854901890852459, "grad_norm": 4.8031697273254395, "learning_rate": 9.71555463436649e-06, "loss": 0.5009, "step": 165790 }, { "epoch": 0.9855496311619143, "grad_norm": 4.747518539428711, "learning_rate": 9.715485643688928e-06, "loss": 0.4682, "step": 165800 }, { "epoch": 0.9856090732385827, "grad_norm": 4.086328983306885, "learning_rate": 9.715416644890737e-06, "loss": 0.5011, "step": 165810 }, { "epoch": 0.985668515315251, "grad_norm": 4.205819606781006, "learning_rate": 9.715347637972036e-06, "loss": 0.4739, "step": 165820 }, { "epoch": 0.9857279573919194, "grad_norm": 6.289142608642578, "learning_rate": 9.715278622932944e-06, "loss": 0.544, "step": 165830 }, { "epoch": 0.9857873994685878, "grad_norm": 4.429252624511719, "learning_rate": 9.71520959977358e-06, "loss": 0.5506, "step": 165840 }, { "epoch": 0.9858468415452563, "grad_norm": 4.807927131652832, "learning_rate": 9.715140568494063e-06, "loss": 0.5127, "step": 165850 }, { "epoch": 0.9859062836219246, "grad_norm": 4.021930694580078, "learning_rate": 9.715071529094511e-06, "loss": 0.5198, "step": 165860 }, { "epoch": 0.985965725698593, "grad_norm": 5.673681259155273, "learning_rate": 9.715002481575042e-06, "loss": 0.6407, "step": 165870 }, { "epoch": 0.9860251677752614, "grad_norm": 5.271940231323242, "learning_rate": 9.714933425935777e-06, "loss": 0.5282, "step": 165880 }, { "epoch": 0.9860846098519298, "grad_norm": 5.7830681800842285, "learning_rate": 9.714864362176835e-06, "loss": 0.5399, "step": 165890 }, { "epoch": 0.9861440519285982, "grad_norm": 4.825063705444336, "learning_rate": 9.71479529029833e-06, "loss": 0.5614, "step": 165900 }, { "epoch": 0.9862034940052665, "grad_norm": 5.5602803230285645, "learning_rate": 9.71472621030039e-06, "loss": 0.531, "step": 165910 }, { "epoch": 0.9862629360819349, "grad_norm": 5.390475273132324, "learning_rate": 9.714657122183126e-06, "loss": 0.4877, "step": 165920 }, { "epoch": 0.9863223781586034, "grad_norm": 7.327747821807861, "learning_rate": 9.714588025946661e-06, "loss": 0.5575, "step": 165930 }, { "epoch": 0.9863818202352718, "grad_norm": 6.327244281768799, "learning_rate": 9.714518921591112e-06, "loss": 0.5902, "step": 165940 }, { "epoch": 0.9864412623119402, "grad_norm": 4.211122989654541, "learning_rate": 9.7144498091166e-06, "loss": 0.5416, "step": 165950 }, { "epoch": 0.9865007043886085, "grad_norm": 5.037861347198486, "learning_rate": 9.714380688523244e-06, "loss": 0.5306, "step": 165960 }, { "epoch": 0.9865601464652769, "grad_norm": 4.971309185028076, "learning_rate": 9.714311559811159e-06, "loss": 0.5611, "step": 165970 }, { "epoch": 0.9866195885419453, "grad_norm": 5.818213939666748, "learning_rate": 9.714242422980469e-06, "loss": 0.5479, "step": 165980 }, { "epoch": 0.9866790306186137, "grad_norm": 6.609898090362549, "learning_rate": 9.714173278031291e-06, "loss": 0.5638, "step": 165990 }, { "epoch": 0.986738472695282, "grad_norm": 4.099049091339111, "learning_rate": 9.714104124963743e-06, "loss": 0.5056, "step": 166000 }, { "epoch": 0.9867979147719504, "grad_norm": 5.952272891998291, "learning_rate": 9.714034963777945e-06, "loss": 0.5031, "step": 166010 }, { "epoch": 0.9868573568486189, "grad_norm": 6.771729469299316, "learning_rate": 9.713965794474017e-06, "loss": 0.5368, "step": 166020 }, { "epoch": 0.9869167989252873, "grad_norm": 4.6432414054870605, "learning_rate": 9.713896617052078e-06, "loss": 0.5138, "step": 166030 }, { "epoch": 0.9869762410019557, "grad_norm": 4.8015289306640625, "learning_rate": 9.713827431512247e-06, "loss": 0.5075, "step": 166040 }, { "epoch": 0.987035683078624, "grad_norm": 7.087864875793457, "learning_rate": 9.71375823785464e-06, "loss": 0.5351, "step": 166050 }, { "epoch": 0.9870951251552924, "grad_norm": 4.075740814208984, "learning_rate": 9.713689036079382e-06, "loss": 0.5117, "step": 166060 }, { "epoch": 0.9871545672319608, "grad_norm": 6.830697059631348, "learning_rate": 9.713619826186587e-06, "loss": 0.5324, "step": 166070 }, { "epoch": 0.9872140093086292, "grad_norm": 4.118206977844238, "learning_rate": 9.713550608176378e-06, "loss": 0.5581, "step": 166080 }, { "epoch": 0.9872734513852977, "grad_norm": 4.788209915161133, "learning_rate": 9.71348138204887e-06, "loss": 0.5171, "step": 166090 }, { "epoch": 0.987332893461966, "grad_norm": 5.013813495635986, "learning_rate": 9.713412147804187e-06, "loss": 0.4747, "step": 166100 }, { "epoch": 0.9873923355386344, "grad_norm": 5.022418975830078, "learning_rate": 9.713342905442444e-06, "loss": 0.5214, "step": 166110 }, { "epoch": 0.9874517776153028, "grad_norm": 6.039425849914551, "learning_rate": 9.713273654963764e-06, "loss": 0.5472, "step": 166120 }, { "epoch": 0.9875112196919712, "grad_norm": 6.443164825439453, "learning_rate": 9.713204396368263e-06, "loss": 0.4908, "step": 166130 }, { "epoch": 0.9875706617686395, "grad_norm": 5.181206226348877, "learning_rate": 9.713135129656063e-06, "loss": 0.535, "step": 166140 }, { "epoch": 0.9876301038453079, "grad_norm": 6.315786361694336, "learning_rate": 9.713065854827281e-06, "loss": 0.5683, "step": 166150 }, { "epoch": 0.9876895459219763, "grad_norm": 4.405048847198486, "learning_rate": 9.712996571882037e-06, "loss": 0.5429, "step": 166160 }, { "epoch": 0.9877489879986447, "grad_norm": 6.862001419067383, "learning_rate": 9.712927280820452e-06, "loss": 0.5886, "step": 166170 }, { "epoch": 0.9878084300753132, "grad_norm": 6.2237701416015625, "learning_rate": 9.712857981642641e-06, "loss": 0.4932, "step": 166180 }, { "epoch": 0.9878678721519815, "grad_norm": 5.593750953674316, "learning_rate": 9.712788674348728e-06, "loss": 0.5241, "step": 166190 }, { "epoch": 0.9879273142286499, "grad_norm": 5.299623012542725, "learning_rate": 9.712719358938832e-06, "loss": 0.4968, "step": 166200 }, { "epoch": 0.9879867563053183, "grad_norm": 4.1256818771362305, "learning_rate": 9.71265003541307e-06, "loss": 0.4935, "step": 166210 }, { "epoch": 0.9880461983819867, "grad_norm": 4.931533336639404, "learning_rate": 9.71258070377156e-06, "loss": 0.5189, "step": 166220 }, { "epoch": 0.988105640458655, "grad_norm": 5.10111665725708, "learning_rate": 9.712511364014426e-06, "loss": 0.5277, "step": 166230 }, { "epoch": 0.9881650825353234, "grad_norm": 5.45587158203125, "learning_rate": 9.712442016141785e-06, "loss": 0.561, "step": 166240 }, { "epoch": 0.9882245246119918, "grad_norm": 4.976071357727051, "learning_rate": 9.712372660153758e-06, "loss": 0.5153, "step": 166250 }, { "epoch": 0.9882839666886603, "grad_norm": 6.408998489379883, "learning_rate": 9.71230329605046e-06, "loss": 0.5755, "step": 166260 }, { "epoch": 0.9883434087653287, "grad_norm": 5.5247883796691895, "learning_rate": 9.712233923832015e-06, "loss": 0.5121, "step": 166270 }, { "epoch": 0.988402850841997, "grad_norm": 5.531370162963867, "learning_rate": 9.71216454349854e-06, "loss": 0.539, "step": 166280 }, { "epoch": 0.9884622929186654, "grad_norm": 3.838085651397705, "learning_rate": 9.712095155050156e-06, "loss": 0.5108, "step": 166290 }, { "epoch": 0.9885217349953338, "grad_norm": 5.607474327087402, "learning_rate": 9.712025758486982e-06, "loss": 0.5255, "step": 166300 }, { "epoch": 0.9885811770720022, "grad_norm": 4.996150970458984, "learning_rate": 9.711956353809137e-06, "loss": 0.511, "step": 166310 }, { "epoch": 0.9886406191486706, "grad_norm": 3.6338648796081543, "learning_rate": 9.711886941016741e-06, "loss": 0.572, "step": 166320 }, { "epoch": 0.9887000612253389, "grad_norm": 4.681203365325928, "learning_rate": 9.711817520109916e-06, "loss": 0.4864, "step": 166330 }, { "epoch": 0.9887595033020073, "grad_norm": 6.493775844573975, "learning_rate": 9.711748091088775e-06, "loss": 0.5024, "step": 166340 }, { "epoch": 0.9888189453786758, "grad_norm": 6.165163516998291, "learning_rate": 9.711678653953444e-06, "loss": 0.577, "step": 166350 }, { "epoch": 0.9888783874553442, "grad_norm": 4.012817859649658, "learning_rate": 9.711609208704041e-06, "loss": 0.6101, "step": 166360 }, { "epoch": 0.9889378295320125, "grad_norm": 5.447673320770264, "learning_rate": 9.711539755340682e-06, "loss": 0.4942, "step": 166370 }, { "epoch": 0.9889972716086809, "grad_norm": 6.456011772155762, "learning_rate": 9.711470293863491e-06, "loss": 0.5571, "step": 166380 }, { "epoch": 0.9890567136853493, "grad_norm": 5.930075645446777, "learning_rate": 9.711400824272586e-06, "loss": 0.4782, "step": 166390 }, { "epoch": 0.9891161557620177, "grad_norm": 5.804020881652832, "learning_rate": 9.711331346568087e-06, "loss": 0.5258, "step": 166400 }, { "epoch": 0.9891755978386861, "grad_norm": 7.269345760345459, "learning_rate": 9.711261860750112e-06, "loss": 0.5535, "step": 166410 }, { "epoch": 0.9892350399153544, "grad_norm": 5.627527713775635, "learning_rate": 9.711192366818783e-06, "loss": 0.5046, "step": 166420 }, { "epoch": 0.9892944819920229, "grad_norm": 4.315654277801514, "learning_rate": 9.711122864774218e-06, "loss": 0.5675, "step": 166430 }, { "epoch": 0.9893539240686913, "grad_norm": 5.58492374420166, "learning_rate": 9.711053354616538e-06, "loss": 0.5352, "step": 166440 }, { "epoch": 0.9894133661453597, "grad_norm": 5.240488052368164, "learning_rate": 9.71098383634586e-06, "loss": 0.4984, "step": 166450 }, { "epoch": 0.9894728082220281, "grad_norm": 5.902015209197998, "learning_rate": 9.710914309962309e-06, "loss": 0.5147, "step": 166460 }, { "epoch": 0.9895322502986964, "grad_norm": 4.998301982879639, "learning_rate": 9.710844775465999e-06, "loss": 0.5316, "step": 166470 }, { "epoch": 0.9895916923753648, "grad_norm": 4.752983093261719, "learning_rate": 9.710775232857052e-06, "loss": 0.5142, "step": 166480 }, { "epoch": 0.9896511344520332, "grad_norm": 5.405018329620361, "learning_rate": 9.71070568213559e-06, "loss": 0.5161, "step": 166490 }, { "epoch": 0.9897105765287016, "grad_norm": 4.130494117736816, "learning_rate": 9.710636123301729e-06, "loss": 0.5045, "step": 166500 }, { "epoch": 0.98977001860537, "grad_norm": 6.623335361480713, "learning_rate": 9.710566556355592e-06, "loss": 0.5448, "step": 166510 }, { "epoch": 0.9898294606820384, "grad_norm": 5.988609790802002, "learning_rate": 9.710496981297295e-06, "loss": 0.507, "step": 166520 }, { "epoch": 0.9898889027587068, "grad_norm": 3.981632709503174, "learning_rate": 9.710427398126962e-06, "loss": 0.5231, "step": 166530 }, { "epoch": 0.9899483448353752, "grad_norm": 6.148725509643555, "learning_rate": 9.710357806844712e-06, "loss": 0.601, "step": 166540 }, { "epoch": 0.9900077869120436, "grad_norm": 3.467313528060913, "learning_rate": 9.710288207450662e-06, "loss": 0.5221, "step": 166550 }, { "epoch": 0.9900672289887119, "grad_norm": 5.655488014221191, "learning_rate": 9.710218599944934e-06, "loss": 0.5179, "step": 166560 }, { "epoch": 0.9901266710653803, "grad_norm": 5.906493663787842, "learning_rate": 9.710148984327647e-06, "loss": 0.5285, "step": 166570 }, { "epoch": 0.9901861131420487, "grad_norm": 4.0280022621154785, "learning_rate": 9.710079360598924e-06, "loss": 0.5376, "step": 166580 }, { "epoch": 0.9902455552187172, "grad_norm": 5.048511505126953, "learning_rate": 9.71000972875888e-06, "loss": 0.5542, "step": 166590 }, { "epoch": 0.9903049972953855, "grad_norm": 5.241086959838867, "learning_rate": 9.709940088807636e-06, "loss": 0.5396, "step": 166600 }, { "epoch": 0.9903644393720539, "grad_norm": 4.959833145141602, "learning_rate": 9.709870440745316e-06, "loss": 0.4983, "step": 166610 }, { "epoch": 0.9904238814487223, "grad_norm": 5.2936110496521, "learning_rate": 9.709800784572036e-06, "loss": 0.6154, "step": 166620 }, { "epoch": 0.9904833235253907, "grad_norm": 6.898758888244629, "learning_rate": 9.709731120287917e-06, "loss": 0.6014, "step": 166630 }, { "epoch": 0.9905427656020591, "grad_norm": 3.831019639968872, "learning_rate": 9.70966144789308e-06, "loss": 0.4852, "step": 166640 }, { "epoch": 0.9906022076787274, "grad_norm": 5.322454452514648, "learning_rate": 9.709591767387643e-06, "loss": 0.5365, "step": 166650 }, { "epoch": 0.9906616497553958, "grad_norm": 3.0524258613586426, "learning_rate": 9.709522078771727e-06, "loss": 0.4883, "step": 166660 }, { "epoch": 0.9907210918320642, "grad_norm": 5.313485622406006, "learning_rate": 9.709452382045452e-06, "loss": 0.5546, "step": 166670 }, { "epoch": 0.9907805339087327, "grad_norm": 3.916637659072876, "learning_rate": 9.709382677208938e-06, "loss": 0.4808, "step": 166680 }, { "epoch": 0.9908399759854011, "grad_norm": 4.563535690307617, "learning_rate": 9.709312964262307e-06, "loss": 0.4751, "step": 166690 }, { "epoch": 0.9908994180620694, "grad_norm": 5.453240394592285, "learning_rate": 9.709243243205674e-06, "loss": 0.5165, "step": 166700 }, { "epoch": 0.9909588601387378, "grad_norm": 5.786228179931641, "learning_rate": 9.709173514039166e-06, "loss": 0.555, "step": 166710 }, { "epoch": 0.9910183022154062, "grad_norm": 5.579345226287842, "learning_rate": 9.709103776762896e-06, "loss": 0.5187, "step": 166720 }, { "epoch": 0.9910777442920746, "grad_norm": 5.532829761505127, "learning_rate": 9.70903403137699e-06, "loss": 0.4931, "step": 166730 }, { "epoch": 0.9911371863687429, "grad_norm": 6.082632541656494, "learning_rate": 9.708964277881564e-06, "loss": 0.5432, "step": 166740 }, { "epoch": 0.9911966284454113, "grad_norm": 6.210549831390381, "learning_rate": 9.708894516276739e-06, "loss": 0.5707, "step": 166750 }, { "epoch": 0.9912560705220798, "grad_norm": 6.164845943450928, "learning_rate": 9.708824746562636e-06, "loss": 0.5125, "step": 166760 }, { "epoch": 0.9913155125987482, "grad_norm": 6.484872817993164, "learning_rate": 9.708754968739376e-06, "loss": 0.5186, "step": 166770 }, { "epoch": 0.9913749546754166, "grad_norm": 3.493913412094116, "learning_rate": 9.708685182807079e-06, "loss": 0.5063, "step": 166780 }, { "epoch": 0.9914343967520849, "grad_norm": 5.625023365020752, "learning_rate": 9.708615388765863e-06, "loss": 0.5325, "step": 166790 }, { "epoch": 0.9914938388287533, "grad_norm": 6.233248233795166, "learning_rate": 9.708545586615847e-06, "loss": 0.5225, "step": 166800 }, { "epoch": 0.9915532809054217, "grad_norm": 4.488266468048096, "learning_rate": 9.708475776357157e-06, "loss": 0.5236, "step": 166810 }, { "epoch": 0.9916127229820901, "grad_norm": 6.349707126617432, "learning_rate": 9.70840595798991e-06, "loss": 0.5563, "step": 166820 }, { "epoch": 0.9916721650587585, "grad_norm": 4.846835613250732, "learning_rate": 9.708336131514225e-06, "loss": 0.5239, "step": 166830 }, { "epoch": 0.9917316071354269, "grad_norm": 5.167088031768799, "learning_rate": 9.708266296930222e-06, "loss": 0.5379, "step": 166840 }, { "epoch": 0.9917910492120953, "grad_norm": 5.316787242889404, "learning_rate": 9.708196454238025e-06, "loss": 0.5395, "step": 166850 }, { "epoch": 0.9918504912887637, "grad_norm": 5.563648700714111, "learning_rate": 9.708126603437751e-06, "loss": 0.4768, "step": 166860 }, { "epoch": 0.9919099333654321, "grad_norm": 5.631747722625732, "learning_rate": 9.708056744529522e-06, "loss": 0.5432, "step": 166870 }, { "epoch": 0.9919693754421004, "grad_norm": 4.332181930541992, "learning_rate": 9.707986877513456e-06, "loss": 0.5397, "step": 166880 }, { "epoch": 0.9920288175187688, "grad_norm": 5.901876449584961, "learning_rate": 9.707917002389677e-06, "loss": 0.5771, "step": 166890 }, { "epoch": 0.9920882595954372, "grad_norm": 5.178882598876953, "learning_rate": 9.707847119158302e-06, "loss": 0.5603, "step": 166900 }, { "epoch": 0.9921477016721056, "grad_norm": 4.123433589935303, "learning_rate": 9.707777227819451e-06, "loss": 0.4879, "step": 166910 }, { "epoch": 0.9922071437487741, "grad_norm": 5.172591209411621, "learning_rate": 9.707707328373248e-06, "loss": 0.5156, "step": 166920 }, { "epoch": 0.9922665858254424, "grad_norm": 7.108796119689941, "learning_rate": 9.707637420819812e-06, "loss": 0.5086, "step": 166930 }, { "epoch": 0.9923260279021108, "grad_norm": 5.235407829284668, "learning_rate": 9.70756750515926e-06, "loss": 0.5414, "step": 166940 }, { "epoch": 0.9923854699787792, "grad_norm": 4.8328046798706055, "learning_rate": 9.707497581391716e-06, "loss": 0.5365, "step": 166950 }, { "epoch": 0.9924449120554476, "grad_norm": 4.995754241943359, "learning_rate": 9.7074276495173e-06, "loss": 0.5079, "step": 166960 }, { "epoch": 0.9925043541321159, "grad_norm": 5.111922740936279, "learning_rate": 9.707357709536132e-06, "loss": 0.5091, "step": 166970 }, { "epoch": 0.9925637962087843, "grad_norm": 5.516139507293701, "learning_rate": 9.707287761448332e-06, "loss": 0.5547, "step": 166980 }, { "epoch": 0.9926232382854527, "grad_norm": 5.235785007476807, "learning_rate": 9.707217805254022e-06, "loss": 0.4979, "step": 166990 }, { "epoch": 0.9926826803621212, "grad_norm": 6.143444061279297, "learning_rate": 9.70714784095332e-06, "loss": 0.5537, "step": 167000 }, { "epoch": 0.9927421224387896, "grad_norm": 6.3726372718811035, "learning_rate": 9.707077868546347e-06, "loss": 0.5649, "step": 167010 }, { "epoch": 0.9928015645154579, "grad_norm": 6.288822650909424, "learning_rate": 9.707007888033224e-06, "loss": 0.5853, "step": 167020 }, { "epoch": 0.9928610065921263, "grad_norm": 6.697891712188721, "learning_rate": 9.706937899414074e-06, "loss": 0.5306, "step": 167030 }, { "epoch": 0.9929204486687947, "grad_norm": 4.578156471252441, "learning_rate": 9.706867902689014e-06, "loss": 0.5183, "step": 167040 }, { "epoch": 0.9929798907454631, "grad_norm": 4.307765483856201, "learning_rate": 9.706797897858167e-06, "loss": 0.5425, "step": 167050 }, { "epoch": 0.9930393328221315, "grad_norm": 5.20391321182251, "learning_rate": 9.706727884921651e-06, "loss": 0.55, "step": 167060 }, { "epoch": 0.9930987748987998, "grad_norm": 4.775437831878662, "learning_rate": 9.706657863879588e-06, "loss": 0.5089, "step": 167070 }, { "epoch": 0.9931582169754682, "grad_norm": 5.528058052062988, "learning_rate": 9.7065878347321e-06, "loss": 0.5525, "step": 167080 }, { "epoch": 0.9932176590521367, "grad_norm": 4.675293445587158, "learning_rate": 9.706517797479305e-06, "loss": 0.5294, "step": 167090 }, { "epoch": 0.9932771011288051, "grad_norm": 4.193027496337891, "learning_rate": 9.706447752121326e-06, "loss": 0.4948, "step": 167100 }, { "epoch": 0.9933365432054734, "grad_norm": 4.037309646606445, "learning_rate": 9.70637769865828e-06, "loss": 0.5066, "step": 167110 }, { "epoch": 0.9933959852821418, "grad_norm": 5.339713096618652, "learning_rate": 9.706307637090291e-06, "loss": 0.5501, "step": 167120 }, { "epoch": 0.9934554273588102, "grad_norm": 4.473651885986328, "learning_rate": 9.70623756741748e-06, "loss": 0.4667, "step": 167130 }, { "epoch": 0.9935148694354786, "grad_norm": 5.024068355560303, "learning_rate": 9.706167489639965e-06, "loss": 0.5216, "step": 167140 }, { "epoch": 0.993574311512147, "grad_norm": 5.1346564292907715, "learning_rate": 9.706097403757868e-06, "loss": 0.5468, "step": 167150 }, { "epoch": 0.9936337535888153, "grad_norm": 5.48983097076416, "learning_rate": 9.706027309771311e-06, "loss": 0.4605, "step": 167160 }, { "epoch": 0.9936931956654838, "grad_norm": 5.895615577697754, "learning_rate": 9.705957207680414e-06, "loss": 0.5906, "step": 167170 }, { "epoch": 0.9937526377421522, "grad_norm": 4.867450714111328, "learning_rate": 9.705887097485295e-06, "loss": 0.4916, "step": 167180 }, { "epoch": 0.9938120798188206, "grad_norm": 4.499131202697754, "learning_rate": 9.705816979186077e-06, "loss": 0.5281, "step": 167190 }, { "epoch": 0.993871521895489, "grad_norm": 4.328528881072998, "learning_rate": 9.705746852782883e-06, "loss": 0.5259, "step": 167200 }, { "epoch": 0.9939309639721573, "grad_norm": 4.78504753112793, "learning_rate": 9.70567671827583e-06, "loss": 0.5151, "step": 167210 }, { "epoch": 0.9939904060488257, "grad_norm": 4.847941875457764, "learning_rate": 9.70560657566504e-06, "loss": 0.5392, "step": 167220 }, { "epoch": 0.9940498481254941, "grad_norm": 6.36752462387085, "learning_rate": 9.705536424950635e-06, "loss": 0.5127, "step": 167230 }, { "epoch": 0.9941092902021625, "grad_norm": 4.679514408111572, "learning_rate": 9.705466266132735e-06, "loss": 0.5663, "step": 167240 }, { "epoch": 0.9941687322788308, "grad_norm": 4.791759014129639, "learning_rate": 9.705396099211459e-06, "loss": 0.5618, "step": 167250 }, { "epoch": 0.9942281743554993, "grad_norm": 5.4192399978637695, "learning_rate": 9.70532592418693e-06, "loss": 0.5341, "step": 167260 }, { "epoch": 0.9942876164321677, "grad_norm": 5.026913642883301, "learning_rate": 9.705255741059268e-06, "loss": 0.5304, "step": 167270 }, { "epoch": 0.9943470585088361, "grad_norm": 5.753339767456055, "learning_rate": 9.705185549828595e-06, "loss": 0.5236, "step": 167280 }, { "epoch": 0.9944065005855045, "grad_norm": 4.810277462005615, "learning_rate": 9.705115350495031e-06, "loss": 0.5783, "step": 167290 }, { "epoch": 0.9944659426621728, "grad_norm": 5.481945514678955, "learning_rate": 9.705045143058697e-06, "loss": 0.5875, "step": 167300 }, { "epoch": 0.9945253847388412, "grad_norm": 4.944277763366699, "learning_rate": 9.704974927519714e-06, "loss": 0.521, "step": 167310 }, { "epoch": 0.9945848268155096, "grad_norm": 4.433220863342285, "learning_rate": 9.704904703878201e-06, "loss": 0.4656, "step": 167320 }, { "epoch": 0.994644268892178, "grad_norm": 4.776860237121582, "learning_rate": 9.704834472134283e-06, "loss": 0.5159, "step": 167330 }, { "epoch": 0.9947037109688464, "grad_norm": 5.2577714920043945, "learning_rate": 9.704764232288078e-06, "loss": 0.5368, "step": 167340 }, { "epoch": 0.9947631530455148, "grad_norm": 5.237044811248779, "learning_rate": 9.704693984339708e-06, "loss": 0.4919, "step": 167350 }, { "epoch": 0.9948225951221832, "grad_norm": 5.107966899871826, "learning_rate": 9.704623728289294e-06, "loss": 0.5332, "step": 167360 }, { "epoch": 0.9948820371988516, "grad_norm": 6.952430248260498, "learning_rate": 9.704553464136955e-06, "loss": 0.4518, "step": 167370 }, { "epoch": 0.99494147927552, "grad_norm": 6.641974449157715, "learning_rate": 9.704483191882814e-06, "loss": 0.5451, "step": 167380 }, { "epoch": 0.9950009213521883, "grad_norm": 6.641927242279053, "learning_rate": 9.70441291152699e-06, "loss": 0.5566, "step": 167390 }, { "epoch": 0.9950603634288567, "grad_norm": 8.5365629196167, "learning_rate": 9.704342623069609e-06, "loss": 0.5158, "step": 167400 }, { "epoch": 0.9951198055055251, "grad_norm": 6.02372407913208, "learning_rate": 9.704272326510787e-06, "loss": 0.5603, "step": 167410 }, { "epoch": 0.9951792475821936, "grad_norm": 4.925414562225342, "learning_rate": 9.704202021850648e-06, "loss": 0.4958, "step": 167420 }, { "epoch": 0.995238689658862, "grad_norm": 5.883567810058594, "learning_rate": 9.704131709089311e-06, "loss": 0.5801, "step": 167430 }, { "epoch": 0.9952981317355303, "grad_norm": 4.410889148712158, "learning_rate": 9.704061388226897e-06, "loss": 0.5641, "step": 167440 }, { "epoch": 0.9953575738121987, "grad_norm": 4.408810615539551, "learning_rate": 9.703991059263529e-06, "loss": 0.54, "step": 167450 }, { "epoch": 0.9954170158888671, "grad_norm": 3.54471492767334, "learning_rate": 9.703920722199325e-06, "loss": 0.5344, "step": 167460 }, { "epoch": 0.9954764579655355, "grad_norm": 8.777256965637207, "learning_rate": 9.703850377034411e-06, "loss": 0.5122, "step": 167470 }, { "epoch": 0.9955359000422038, "grad_norm": 5.686981201171875, "learning_rate": 9.703780023768905e-06, "loss": 0.5227, "step": 167480 }, { "epoch": 0.9955953421188722, "grad_norm": 4.809759140014648, "learning_rate": 9.703709662402927e-06, "loss": 0.5097, "step": 167490 }, { "epoch": 0.9956547841955407, "grad_norm": 4.867867946624756, "learning_rate": 9.703639292936602e-06, "loss": 0.4766, "step": 167500 }, { "epoch": 0.9957142262722091, "grad_norm": 4.7313690185546875, "learning_rate": 9.703568915370048e-06, "loss": 0.5044, "step": 167510 }, { "epoch": 0.9957736683488775, "grad_norm": 5.013998508453369, "learning_rate": 9.703498529703386e-06, "loss": 0.4913, "step": 167520 }, { "epoch": 0.9958331104255458, "grad_norm": 4.420969486236572, "learning_rate": 9.703428135936739e-06, "loss": 0.5217, "step": 167530 }, { "epoch": 0.9958925525022142, "grad_norm": 4.96412467956543, "learning_rate": 9.703357734070228e-06, "loss": 0.5222, "step": 167540 }, { "epoch": 0.9959519945788826, "grad_norm": 4.515951156616211, "learning_rate": 9.703287324103974e-06, "loss": 0.5072, "step": 167550 }, { "epoch": 0.996011436655551, "grad_norm": 4.734899044036865, "learning_rate": 9.703216906038097e-06, "loss": 0.581, "step": 167560 }, { "epoch": 0.9960708787322193, "grad_norm": 5.0788493156433105, "learning_rate": 9.70314647987272e-06, "loss": 0.4982, "step": 167570 }, { "epoch": 0.9961303208088877, "grad_norm": 5.570511817932129, "learning_rate": 9.703076045607962e-06, "loss": 0.5367, "step": 167580 }, { "epoch": 0.9961897628855562, "grad_norm": 4.510562419891357, "learning_rate": 9.703005603243948e-06, "loss": 0.5252, "step": 167590 }, { "epoch": 0.9962492049622246, "grad_norm": 5.020924091339111, "learning_rate": 9.702935152780797e-06, "loss": 0.5003, "step": 167600 }, { "epoch": 0.996308647038893, "grad_norm": 6.229648113250732, "learning_rate": 9.70286469421863e-06, "loss": 0.5089, "step": 167610 }, { "epoch": 0.9963680891155613, "grad_norm": 5.876445293426514, "learning_rate": 9.702794227557568e-06, "loss": 0.5291, "step": 167620 }, { "epoch": 0.9964275311922297, "grad_norm": 4.095069408416748, "learning_rate": 9.702723752797734e-06, "loss": 0.5237, "step": 167630 }, { "epoch": 0.9964869732688981, "grad_norm": 5.28839111328125, "learning_rate": 9.702653269939249e-06, "loss": 0.5446, "step": 167640 }, { "epoch": 0.9965464153455665, "grad_norm": 6.48137903213501, "learning_rate": 9.702582778982232e-06, "loss": 0.539, "step": 167650 }, { "epoch": 0.996605857422235, "grad_norm": 4.23273229598999, "learning_rate": 9.702512279926808e-06, "loss": 0.5146, "step": 167660 }, { "epoch": 0.9966652994989033, "grad_norm": 4.65179443359375, "learning_rate": 9.702441772773099e-06, "loss": 0.5247, "step": 167670 }, { "epoch": 0.9967247415755717, "grad_norm": 3.6551036834716797, "learning_rate": 9.70237125752122e-06, "loss": 0.4834, "step": 167680 }, { "epoch": 0.9967841836522401, "grad_norm": 6.447919845581055, "learning_rate": 9.7023007341713e-06, "loss": 0.5306, "step": 167690 }, { "epoch": 0.9968436257289085, "grad_norm": 5.114877700805664, "learning_rate": 9.702230202723455e-06, "loss": 0.5322, "step": 167700 }, { "epoch": 0.9969030678055768, "grad_norm": 4.627752304077148, "learning_rate": 9.702159663177808e-06, "loss": 0.5125, "step": 167710 }, { "epoch": 0.9969625098822452, "grad_norm": 4.943511009216309, "learning_rate": 9.702089115534484e-06, "loss": 0.4772, "step": 167720 }, { "epoch": 0.9970219519589136, "grad_norm": 5.894960880279541, "learning_rate": 9.702018559793598e-06, "loss": 0.5148, "step": 167730 }, { "epoch": 0.997081394035582, "grad_norm": 5.455311298370361, "learning_rate": 9.701947995955276e-06, "loss": 0.5033, "step": 167740 }, { "epoch": 0.9971408361122505, "grad_norm": 6.619182586669922, "learning_rate": 9.70187742401964e-06, "loss": 0.5799, "step": 167750 }, { "epoch": 0.9972002781889188, "grad_norm": 5.204611778259277, "learning_rate": 9.701806843986809e-06, "loss": 0.5086, "step": 167760 }, { "epoch": 0.9972597202655872, "grad_norm": 3.9172537326812744, "learning_rate": 9.701736255856906e-06, "loss": 0.4898, "step": 167770 }, { "epoch": 0.9973191623422556, "grad_norm": 5.229626655578613, "learning_rate": 9.701665659630053e-06, "loss": 0.528, "step": 167780 }, { "epoch": 0.997378604418924, "grad_norm": 4.355742454528809, "learning_rate": 9.70159505530637e-06, "loss": 0.5001, "step": 167790 }, { "epoch": 0.9974380464955924, "grad_norm": 4.843315601348877, "learning_rate": 9.701524442885978e-06, "loss": 0.4843, "step": 167800 }, { "epoch": 0.9974974885722607, "grad_norm": 3.881646156311035, "learning_rate": 9.701453822369e-06, "loss": 0.4647, "step": 167810 }, { "epoch": 0.9975569306489291, "grad_norm": 4.45988655090332, "learning_rate": 9.70138319375556e-06, "loss": 0.4867, "step": 167820 }, { "epoch": 0.9976163727255976, "grad_norm": 5.125926971435547, "learning_rate": 9.701312557045774e-06, "loss": 0.5053, "step": 167830 }, { "epoch": 0.997675814802266, "grad_norm": 4.569118499755859, "learning_rate": 9.70124191223977e-06, "loss": 0.5162, "step": 167840 }, { "epoch": 0.9977352568789343, "grad_norm": 5.281820297241211, "learning_rate": 9.701171259337665e-06, "loss": 0.5695, "step": 167850 }, { "epoch": 0.9977946989556027, "grad_norm": 6.67470645904541, "learning_rate": 9.70110059833958e-06, "loss": 0.5786, "step": 167860 }, { "epoch": 0.9978541410322711, "grad_norm": 5.625531196594238, "learning_rate": 9.701029929245642e-06, "loss": 0.5454, "step": 167870 }, { "epoch": 0.9979135831089395, "grad_norm": 4.708464622497559, "learning_rate": 9.700959252055968e-06, "loss": 0.4562, "step": 167880 }, { "epoch": 0.9979730251856079, "grad_norm": 6.1379804611206055, "learning_rate": 9.700888566770683e-06, "loss": 0.4973, "step": 167890 }, { "epoch": 0.9980324672622762, "grad_norm": 3.939932346343994, "learning_rate": 9.700817873389906e-06, "loss": 0.5256, "step": 167900 }, { "epoch": 0.9980919093389446, "grad_norm": 4.241301536560059, "learning_rate": 9.70074717191376e-06, "loss": 0.5191, "step": 167910 }, { "epoch": 0.9981513514156131, "grad_norm": 4.950104236602783, "learning_rate": 9.700676462342364e-06, "loss": 0.5181, "step": 167920 }, { "epoch": 0.9982107934922815, "grad_norm": 4.159733295440674, "learning_rate": 9.700605744675845e-06, "loss": 0.4844, "step": 167930 }, { "epoch": 0.9982702355689498, "grad_norm": 6.521740436553955, "learning_rate": 9.70053501891432e-06, "loss": 0.5478, "step": 167940 }, { "epoch": 0.9983296776456182, "grad_norm": 4.47933292388916, "learning_rate": 9.700464285057916e-06, "loss": 0.5448, "step": 167950 }, { "epoch": 0.9983891197222866, "grad_norm": 5.1093430519104, "learning_rate": 9.70039354310675e-06, "loss": 0.5777, "step": 167960 }, { "epoch": 0.998448561798955, "grad_norm": 3.732917308807373, "learning_rate": 9.700322793060944e-06, "loss": 0.5325, "step": 167970 }, { "epoch": 0.9985080038756234, "grad_norm": 5.185561180114746, "learning_rate": 9.700252034920624e-06, "loss": 0.536, "step": 167980 }, { "epoch": 0.9985674459522917, "grad_norm": 3.7568507194519043, "learning_rate": 9.700181268685907e-06, "loss": 0.5308, "step": 167990 }, { "epoch": 0.9986268880289602, "grad_norm": 3.9289422035217285, "learning_rate": 9.700110494356918e-06, "loss": 0.5619, "step": 168000 }, { "epoch": 0.9986863301056286, "grad_norm": 6.783076286315918, "learning_rate": 9.700039711933778e-06, "loss": 0.5903, "step": 168010 }, { "epoch": 0.998745772182297, "grad_norm": 5.904669284820557, "learning_rate": 9.699968921416609e-06, "loss": 0.5463, "step": 168020 }, { "epoch": 0.9988052142589654, "grad_norm": 3.5912270545959473, "learning_rate": 9.699898122805532e-06, "loss": 0.4916, "step": 168030 }, { "epoch": 0.9988646563356337, "grad_norm": 5.120208740234375, "learning_rate": 9.69982731610067e-06, "loss": 0.5581, "step": 168040 }, { "epoch": 0.9989240984123021, "grad_norm": 6.975907325744629, "learning_rate": 9.699756501302145e-06, "loss": 0.5064, "step": 168050 }, { "epoch": 0.9989835404889705, "grad_norm": 5.018248558044434, "learning_rate": 9.699685678410077e-06, "loss": 0.5417, "step": 168060 }, { "epoch": 0.999042982565639, "grad_norm": 4.808533191680908, "learning_rate": 9.69961484742459e-06, "loss": 0.5554, "step": 168070 }, { "epoch": 0.9991024246423073, "grad_norm": 6.297017574310303, "learning_rate": 9.699544008345807e-06, "loss": 0.5026, "step": 168080 }, { "epoch": 0.9991618667189757, "grad_norm": 5.31704568862915, "learning_rate": 9.699473161173846e-06, "loss": 0.5242, "step": 168090 }, { "epoch": 0.9992213087956441, "grad_norm": 5.088026523590088, "learning_rate": 9.699402305908833e-06, "loss": 0.5358, "step": 168100 }, { "epoch": 0.9992807508723125, "grad_norm": 7.072042942047119, "learning_rate": 9.699331442550888e-06, "loss": 0.4944, "step": 168110 }, { "epoch": 0.9993401929489809, "grad_norm": 4.752172470092773, "learning_rate": 9.699260571100136e-06, "loss": 0.5449, "step": 168120 }, { "epoch": 0.9993996350256492, "grad_norm": 4.728978157043457, "learning_rate": 9.699189691556694e-06, "loss": 0.5178, "step": 168130 }, { "epoch": 0.9994590771023176, "grad_norm": 4.763184547424316, "learning_rate": 9.699118803920686e-06, "loss": 0.5236, "step": 168140 }, { "epoch": 0.999518519178986, "grad_norm": 4.127943515777588, "learning_rate": 9.699047908192236e-06, "loss": 0.5091, "step": 168150 }, { "epoch": 0.9995779612556545, "grad_norm": 4.864065170288086, "learning_rate": 9.698977004371466e-06, "loss": 0.5033, "step": 168160 }, { "epoch": 0.9996374033323229, "grad_norm": 6.786340236663818, "learning_rate": 9.698906092458496e-06, "loss": 0.5446, "step": 168170 }, { "epoch": 0.9996968454089912, "grad_norm": 4.361302375793457, "learning_rate": 9.698835172453448e-06, "loss": 0.4715, "step": 168180 }, { "epoch": 0.9997562874856596, "grad_norm": 6.375589370727539, "learning_rate": 9.698764244356446e-06, "loss": 0.502, "step": 168190 }, { "epoch": 0.999815729562328, "grad_norm": 5.614095687866211, "learning_rate": 9.698693308167612e-06, "loss": 0.4938, "step": 168200 }, { "epoch": 0.9998751716389964, "grad_norm": 6.306750774383545, "learning_rate": 9.698622363887068e-06, "loss": 0.5645, "step": 168210 }, { "epoch": 0.9999346137156647, "grad_norm": 4.877975940704346, "learning_rate": 9.698551411514933e-06, "loss": 0.604, "step": 168220 }, { "epoch": 0.9999940557923331, "grad_norm": 4.911200046539307, "learning_rate": 9.698480451051333e-06, "loss": 0.5446, "step": 168230 }, { "epoch": 1.0000534978690017, "grad_norm": 4.784056186676025, "learning_rate": 9.698409482496389e-06, "loss": 0.4448, "step": 168240 }, { "epoch": 1.0001129399456699, "grad_norm": 4.855278968811035, "learning_rate": 9.698338505850225e-06, "loss": 0.4123, "step": 168250 }, { "epoch": 1.0001723820223383, "grad_norm": 4.292034149169922, "learning_rate": 9.698267521112958e-06, "loss": 0.3847, "step": 168260 }, { "epoch": 1.0002318240990067, "grad_norm": 5.385091781616211, "learning_rate": 9.698196528284717e-06, "loss": 0.4075, "step": 168270 }, { "epoch": 1.000291266175675, "grad_norm": 4.666676998138428, "learning_rate": 9.69812552736562e-06, "loss": 0.4394, "step": 168280 }, { "epoch": 1.0003507082523435, "grad_norm": 4.882196426391602, "learning_rate": 9.69805451835579e-06, "loss": 0.3612, "step": 168290 }, { "epoch": 1.000410150329012, "grad_norm": 3.970276355743408, "learning_rate": 9.69798350125535e-06, "loss": 0.4156, "step": 168300 }, { "epoch": 1.0004695924056803, "grad_norm": 3.807265281677246, "learning_rate": 9.697912476064421e-06, "loss": 0.4537, "step": 168310 }, { "epoch": 1.0005290344823488, "grad_norm": 5.103819370269775, "learning_rate": 9.697841442783127e-06, "loss": 0.3905, "step": 168320 }, { "epoch": 1.0005884765590172, "grad_norm": 5.262711048126221, "learning_rate": 9.697770401411589e-06, "loss": 0.405, "step": 168330 }, { "epoch": 1.0006479186356854, "grad_norm": 5.450917720794678, "learning_rate": 9.697699351949929e-06, "loss": 0.4214, "step": 168340 }, { "epoch": 1.0007073607123538, "grad_norm": 3.5995426177978516, "learning_rate": 9.697628294398271e-06, "loss": 0.4057, "step": 168350 }, { "epoch": 1.0007668027890222, "grad_norm": 5.406432628631592, "learning_rate": 9.697557228756737e-06, "loss": 0.3793, "step": 168360 }, { "epoch": 1.0008262448656906, "grad_norm": 3.6693918704986572, "learning_rate": 9.697486155025449e-06, "loss": 0.378, "step": 168370 }, { "epoch": 1.000885686942359, "grad_norm": 3.6552114486694336, "learning_rate": 9.69741507320453e-06, "loss": 0.3703, "step": 168380 }, { "epoch": 1.0009451290190274, "grad_norm": 6.503447532653809, "learning_rate": 9.697343983294101e-06, "loss": 0.4831, "step": 168390 }, { "epoch": 1.0010045710956958, "grad_norm": 5.028473854064941, "learning_rate": 9.697272885294284e-06, "loss": 0.4401, "step": 168400 }, { "epoch": 1.0010640131723643, "grad_norm": 5.567596435546875, "learning_rate": 9.697201779205204e-06, "loss": 0.4098, "step": 168410 }, { "epoch": 1.0011234552490327, "grad_norm": 5.970292568206787, "learning_rate": 9.697130665026981e-06, "loss": 0.4503, "step": 168420 }, { "epoch": 1.0011828973257009, "grad_norm": 4.894518852233887, "learning_rate": 9.69705954275974e-06, "loss": 0.445, "step": 168430 }, { "epoch": 1.0012423394023693, "grad_norm": 5.95460844039917, "learning_rate": 9.6969884124036e-06, "loss": 0.422, "step": 168440 }, { "epoch": 1.0013017814790377, "grad_norm": 5.00449800491333, "learning_rate": 9.696917273958689e-06, "loss": 0.4447, "step": 168450 }, { "epoch": 1.0013612235557061, "grad_norm": 7.061890602111816, "learning_rate": 9.696846127425123e-06, "loss": 0.4213, "step": 168460 }, { "epoch": 1.0014206656323745, "grad_norm": 6.665890693664551, "learning_rate": 9.696774972803027e-06, "loss": 0.424, "step": 168470 }, { "epoch": 1.001480107709043, "grad_norm": 4.646472930908203, "learning_rate": 9.696703810092527e-06, "loss": 0.4174, "step": 168480 }, { "epoch": 1.0015395497857114, "grad_norm": 4.954578876495361, "learning_rate": 9.69663263929374e-06, "loss": 0.4049, "step": 168490 }, { "epoch": 1.0015989918623798, "grad_norm": 5.1226677894592285, "learning_rate": 9.696561460406793e-06, "loss": 0.4485, "step": 168500 }, { "epoch": 1.0016584339390482, "grad_norm": 5.123356819152832, "learning_rate": 9.696490273431807e-06, "loss": 0.435, "step": 168510 }, { "epoch": 1.0017178760157164, "grad_norm": 5.868847846984863, "learning_rate": 9.696419078368902e-06, "loss": 0.4368, "step": 168520 }, { "epoch": 1.0017773180923848, "grad_norm": 5.9967427253723145, "learning_rate": 9.696347875218205e-06, "loss": 0.3775, "step": 168530 }, { "epoch": 1.0018367601690532, "grad_norm": 3.2891619205474854, "learning_rate": 9.696276663979835e-06, "loss": 0.4116, "step": 168540 }, { "epoch": 1.0018962022457216, "grad_norm": 4.420901775360107, "learning_rate": 9.696205444653919e-06, "loss": 0.4039, "step": 168550 }, { "epoch": 1.00195564432239, "grad_norm": 5.235631465911865, "learning_rate": 9.696134217240574e-06, "loss": 0.4085, "step": 168560 }, { "epoch": 1.0020150863990585, "grad_norm": 5.105154991149902, "learning_rate": 9.696062981739927e-06, "loss": 0.4071, "step": 168570 }, { "epoch": 1.0020745284757269, "grad_norm": 6.463576316833496, "learning_rate": 9.6959917381521e-06, "loss": 0.4403, "step": 168580 }, { "epoch": 1.0021339705523953, "grad_norm": 6.308503150939941, "learning_rate": 9.695920486477213e-06, "loss": 0.4513, "step": 168590 }, { "epoch": 1.0021934126290637, "grad_norm": 4.111719608306885, "learning_rate": 9.695849226715392e-06, "loss": 0.4195, "step": 168600 }, { "epoch": 1.002252854705732, "grad_norm": 5.0323591232299805, "learning_rate": 9.695777958866756e-06, "loss": 0.4283, "step": 168610 }, { "epoch": 1.0023122967824003, "grad_norm": 4.724409103393555, "learning_rate": 9.695706682931433e-06, "loss": 0.3786, "step": 168620 }, { "epoch": 1.0023717388590687, "grad_norm": 5.346948146820068, "learning_rate": 9.695635398909541e-06, "loss": 0.4168, "step": 168630 }, { "epoch": 1.0024311809357371, "grad_norm": 5.855701923370361, "learning_rate": 9.695564106801206e-06, "loss": 0.4204, "step": 168640 }, { "epoch": 1.0024906230124055, "grad_norm": 4.299338340759277, "learning_rate": 9.695492806606549e-06, "loss": 0.4043, "step": 168650 }, { "epoch": 1.002550065089074, "grad_norm": 5.15525484085083, "learning_rate": 9.695421498325693e-06, "loss": 0.4255, "step": 168660 }, { "epoch": 1.0026095071657424, "grad_norm": 4.502389907836914, "learning_rate": 9.695350181958759e-06, "loss": 0.4179, "step": 168670 }, { "epoch": 1.0026689492424108, "grad_norm": 4.738492012023926, "learning_rate": 9.695278857505874e-06, "loss": 0.4103, "step": 168680 }, { "epoch": 1.0027283913190792, "grad_norm": 4.716820240020752, "learning_rate": 9.695207524967159e-06, "loss": 0.3844, "step": 168690 }, { "epoch": 1.0027878333957476, "grad_norm": 4.053496837615967, "learning_rate": 9.695136184342735e-06, "loss": 0.4353, "step": 168700 }, { "epoch": 1.0028472754724158, "grad_norm": 4.5708441734313965, "learning_rate": 9.695064835632725e-06, "loss": 0.4168, "step": 168710 }, { "epoch": 1.0029067175490842, "grad_norm": 5.58663272857666, "learning_rate": 9.694993478837256e-06, "loss": 0.4065, "step": 168720 }, { "epoch": 1.0029661596257526, "grad_norm": 4.357237339019775, "learning_rate": 9.694922113956446e-06, "loss": 0.4564, "step": 168730 }, { "epoch": 1.003025601702421, "grad_norm": 4.586606025695801, "learning_rate": 9.694850740990422e-06, "loss": 0.3977, "step": 168740 }, { "epoch": 1.0030850437790895, "grad_norm": 5.899142265319824, "learning_rate": 9.694779359939302e-06, "loss": 0.4628, "step": 168750 }, { "epoch": 1.0031444858557579, "grad_norm": 4.0264692306518555, "learning_rate": 9.694707970803214e-06, "loss": 0.373, "step": 168760 }, { "epoch": 1.0032039279324263, "grad_norm": 4.295001029968262, "learning_rate": 9.694636573582279e-06, "loss": 0.3755, "step": 168770 }, { "epoch": 1.0032633700090947, "grad_norm": 4.638996124267578, "learning_rate": 9.694565168276617e-06, "loss": 0.4017, "step": 168780 }, { "epoch": 1.0033228120857631, "grad_norm": 5.813442230224609, "learning_rate": 9.694493754886357e-06, "loss": 0.4465, "step": 168790 }, { "epoch": 1.0033822541624313, "grad_norm": 4.7463908195495605, "learning_rate": 9.694422333411616e-06, "loss": 0.4218, "step": 168800 }, { "epoch": 1.0034416962390997, "grad_norm": 6.608921527862549, "learning_rate": 9.69435090385252e-06, "loss": 0.3939, "step": 168810 }, { "epoch": 1.0035011383157681, "grad_norm": 5.0304460525512695, "learning_rate": 9.694279466209193e-06, "loss": 0.4226, "step": 168820 }, { "epoch": 1.0035605803924366, "grad_norm": 4.9709792137146, "learning_rate": 9.694208020481756e-06, "loss": 0.4067, "step": 168830 }, { "epoch": 1.003620022469105, "grad_norm": 4.53535795211792, "learning_rate": 9.694136566670332e-06, "loss": 0.4122, "step": 168840 }, { "epoch": 1.0036794645457734, "grad_norm": 6.35170316696167, "learning_rate": 9.694065104775045e-06, "loss": 0.4294, "step": 168850 }, { "epoch": 1.0037389066224418, "grad_norm": 5.162920951843262, "learning_rate": 9.69399363479602e-06, "loss": 0.4294, "step": 168860 }, { "epoch": 1.0037983486991102, "grad_norm": 4.181018829345703, "learning_rate": 9.693922156733375e-06, "loss": 0.4138, "step": 168870 }, { "epoch": 1.0038577907757786, "grad_norm": 4.622681140899658, "learning_rate": 9.693850670587237e-06, "loss": 0.4263, "step": 168880 }, { "epoch": 1.0039172328524468, "grad_norm": 6.1027350425720215, "learning_rate": 9.693779176357728e-06, "loss": 0.4772, "step": 168890 }, { "epoch": 1.0039766749291152, "grad_norm": 6.403615951538086, "learning_rate": 9.693707674044971e-06, "loss": 0.3905, "step": 168900 }, { "epoch": 1.0040361170057837, "grad_norm": 4.959907054901123, "learning_rate": 9.69363616364909e-06, "loss": 0.3925, "step": 168910 }, { "epoch": 1.004095559082452, "grad_norm": 3.993476629257202, "learning_rate": 9.693564645170206e-06, "loss": 0.3954, "step": 168920 }, { "epoch": 1.0041550011591205, "grad_norm": 5.905753135681152, "learning_rate": 9.693493118608445e-06, "loss": 0.4406, "step": 168930 }, { "epoch": 1.004214443235789, "grad_norm": 5.981962203979492, "learning_rate": 9.69342158396393e-06, "loss": 0.421, "step": 168940 }, { "epoch": 1.0042738853124573, "grad_norm": 4.170113563537598, "learning_rate": 9.69335004123678e-06, "loss": 0.3914, "step": 168950 }, { "epoch": 1.0043333273891257, "grad_norm": 4.34274435043335, "learning_rate": 9.693278490427122e-06, "loss": 0.422, "step": 168960 }, { "epoch": 1.0043927694657941, "grad_norm": 4.68470573425293, "learning_rate": 9.693206931535079e-06, "loss": 0.3965, "step": 168970 }, { "epoch": 1.0044522115424623, "grad_norm": 5.114506244659424, "learning_rate": 9.693135364560774e-06, "loss": 0.4325, "step": 168980 }, { "epoch": 1.0045116536191308, "grad_norm": 4.0511603355407715, "learning_rate": 9.69306378950433e-06, "loss": 0.435, "step": 168990 }, { "epoch": 1.0045710956957992, "grad_norm": 3.8607139587402344, "learning_rate": 9.692992206365871e-06, "loss": 0.4092, "step": 169000 }, { "epoch": 1.0046305377724676, "grad_norm": 6.0035400390625, "learning_rate": 9.692920615145518e-06, "loss": 0.4774, "step": 169010 }, { "epoch": 1.004689979849136, "grad_norm": 5.538366317749023, "learning_rate": 9.692849015843398e-06, "loss": 0.4373, "step": 169020 }, { "epoch": 1.0047494219258044, "grad_norm": 6.114858627319336, "learning_rate": 9.69277740845963e-06, "loss": 0.4298, "step": 169030 }, { "epoch": 1.0048088640024728, "grad_norm": 6.032451629638672, "learning_rate": 9.692705792994339e-06, "loss": 0.391, "step": 169040 }, { "epoch": 1.0048683060791412, "grad_norm": 5.973183631896973, "learning_rate": 9.69263416944765e-06, "loss": 0.3908, "step": 169050 }, { "epoch": 1.0049277481558097, "grad_norm": 6.276412010192871, "learning_rate": 9.692562537819682e-06, "loss": 0.4178, "step": 169060 }, { "epoch": 1.004987190232478, "grad_norm": 5.180270671844482, "learning_rate": 9.692490898110566e-06, "loss": 0.4019, "step": 169070 }, { "epoch": 1.0050466323091463, "grad_norm": 6.1226582527160645, "learning_rate": 9.692419250320419e-06, "loss": 0.4085, "step": 169080 }, { "epoch": 1.0051060743858147, "grad_norm": 3.79219913482666, "learning_rate": 9.692347594449365e-06, "loss": 0.4065, "step": 169090 }, { "epoch": 1.005165516462483, "grad_norm": 4.106218338012695, "learning_rate": 9.69227593049753e-06, "loss": 0.4073, "step": 169100 }, { "epoch": 1.0052249585391515, "grad_norm": 4.870107650756836, "learning_rate": 9.692204258465034e-06, "loss": 0.4001, "step": 169110 }, { "epoch": 1.00528440061582, "grad_norm": 6.070838928222656, "learning_rate": 9.692132578352005e-06, "loss": 0.4306, "step": 169120 }, { "epoch": 1.0053438426924883, "grad_norm": 7.101967811584473, "learning_rate": 9.692060890158561e-06, "loss": 0.3971, "step": 169130 }, { "epoch": 1.0054032847691567, "grad_norm": 4.116245746612549, "learning_rate": 9.69198919388483e-06, "loss": 0.3757, "step": 169140 }, { "epoch": 1.0054627268458252, "grad_norm": 5.981281757354736, "learning_rate": 9.691917489530934e-06, "loss": 0.4073, "step": 169150 }, { "epoch": 1.0055221689224936, "grad_norm": 4.397758483886719, "learning_rate": 9.691845777096995e-06, "loss": 0.4114, "step": 169160 }, { "epoch": 1.0055816109991618, "grad_norm": 4.7478766441345215, "learning_rate": 9.691774056583139e-06, "loss": 0.3808, "step": 169170 }, { "epoch": 1.0056410530758302, "grad_norm": 7.0104475021362305, "learning_rate": 9.691702327989488e-06, "loss": 0.3849, "step": 169180 }, { "epoch": 1.0057004951524986, "grad_norm": 4.334863185882568, "learning_rate": 9.691630591316166e-06, "loss": 0.4208, "step": 169190 }, { "epoch": 1.005759937229167, "grad_norm": 3.115457773208618, "learning_rate": 9.691558846563295e-06, "loss": 0.4071, "step": 169200 }, { "epoch": 1.0058193793058354, "grad_norm": 3.669715642929077, "learning_rate": 9.691487093731002e-06, "loss": 0.3718, "step": 169210 }, { "epoch": 1.0058788213825038, "grad_norm": 4.61080265045166, "learning_rate": 9.691415332819407e-06, "loss": 0.4085, "step": 169220 }, { "epoch": 1.0059382634591723, "grad_norm": 7.710692405700684, "learning_rate": 9.691343563828636e-06, "loss": 0.4408, "step": 169230 }, { "epoch": 1.0059977055358407, "grad_norm": 5.297008514404297, "learning_rate": 9.691271786758812e-06, "loss": 0.4267, "step": 169240 }, { "epoch": 1.006057147612509, "grad_norm": 5.856333255767822, "learning_rate": 9.691200001610057e-06, "loss": 0.4165, "step": 169250 }, { "epoch": 1.0061165896891773, "grad_norm": 6.056753635406494, "learning_rate": 9.691128208382495e-06, "loss": 0.4372, "step": 169260 }, { "epoch": 1.0061760317658457, "grad_norm": 4.377382755279541, "learning_rate": 9.691056407076251e-06, "loss": 0.4071, "step": 169270 }, { "epoch": 1.006235473842514, "grad_norm": 5.525555610656738, "learning_rate": 9.690984597691449e-06, "loss": 0.4355, "step": 169280 }, { "epoch": 1.0062949159191825, "grad_norm": 6.379185199737549, "learning_rate": 9.690912780228213e-06, "loss": 0.4524, "step": 169290 }, { "epoch": 1.006354357995851, "grad_norm": 5.415737628936768, "learning_rate": 9.690840954686662e-06, "loss": 0.4319, "step": 169300 }, { "epoch": 1.0064138000725193, "grad_norm": 6.057984828948975, "learning_rate": 9.690769121066925e-06, "loss": 0.3827, "step": 169310 }, { "epoch": 1.0064732421491878, "grad_norm": 7.687789440155029, "learning_rate": 9.690697279369125e-06, "loss": 0.382, "step": 169320 }, { "epoch": 1.0065326842258562, "grad_norm": 5.426748275756836, "learning_rate": 9.690625429593383e-06, "loss": 0.3808, "step": 169330 }, { "epoch": 1.0065921263025246, "grad_norm": 7.205572128295898, "learning_rate": 9.690553571739824e-06, "loss": 0.429, "step": 169340 }, { "epoch": 1.0066515683791928, "grad_norm": 3.6477372646331787, "learning_rate": 9.690481705808575e-06, "loss": 0.4207, "step": 169350 }, { "epoch": 1.0067110104558612, "grad_norm": 5.4576921463012695, "learning_rate": 9.690409831799753e-06, "loss": 0.4363, "step": 169360 }, { "epoch": 1.0067704525325296, "grad_norm": 4.814467430114746, "learning_rate": 9.690337949713489e-06, "loss": 0.4379, "step": 169370 }, { "epoch": 1.006829894609198, "grad_norm": 5.304887771606445, "learning_rate": 9.690266059549902e-06, "loss": 0.4069, "step": 169380 }, { "epoch": 1.0068893366858664, "grad_norm": 4.264599323272705, "learning_rate": 9.690194161309117e-06, "loss": 0.3961, "step": 169390 }, { "epoch": 1.0069487787625349, "grad_norm": 5.642967700958252, "learning_rate": 9.690122254991258e-06, "loss": 0.3864, "step": 169400 }, { "epoch": 1.0070082208392033, "grad_norm": 4.72330904006958, "learning_rate": 9.690050340596448e-06, "loss": 0.4483, "step": 169410 }, { "epoch": 1.0070676629158717, "grad_norm": 5.108604907989502, "learning_rate": 9.689978418124814e-06, "loss": 0.4429, "step": 169420 }, { "epoch": 1.00712710499254, "grad_norm": 5.298324108123779, "learning_rate": 9.689906487576476e-06, "loss": 0.4306, "step": 169430 }, { "epoch": 1.0071865470692085, "grad_norm": 5.462961196899414, "learning_rate": 9.68983454895156e-06, "loss": 0.4119, "step": 169440 }, { "epoch": 1.0072459891458767, "grad_norm": 6.1215949058532715, "learning_rate": 9.689762602250188e-06, "loss": 0.3896, "step": 169450 }, { "epoch": 1.0073054312225451, "grad_norm": 3.885181188583374, "learning_rate": 9.689690647472487e-06, "loss": 0.433, "step": 169460 }, { "epoch": 1.0073648732992135, "grad_norm": 5.395380020141602, "learning_rate": 9.689618684618578e-06, "loss": 0.4313, "step": 169470 }, { "epoch": 1.007424315375882, "grad_norm": 5.695681095123291, "learning_rate": 9.689546713688587e-06, "loss": 0.4207, "step": 169480 }, { "epoch": 1.0074837574525504, "grad_norm": 5.713953971862793, "learning_rate": 9.689474734682636e-06, "loss": 0.4206, "step": 169490 }, { "epoch": 1.0075431995292188, "grad_norm": 5.164097785949707, "learning_rate": 9.689402747600852e-06, "loss": 0.4512, "step": 169500 }, { "epoch": 1.0076026416058872, "grad_norm": 6.457446575164795, "learning_rate": 9.689330752443353e-06, "loss": 0.4021, "step": 169510 }, { "epoch": 1.0076620836825556, "grad_norm": 5.975454807281494, "learning_rate": 9.689258749210272e-06, "loss": 0.4083, "step": 169520 }, { "epoch": 1.007721525759224, "grad_norm": 7.108635902404785, "learning_rate": 9.689186737901724e-06, "loss": 0.4422, "step": 169530 }, { "epoch": 1.0077809678358922, "grad_norm": 5.4272847175598145, "learning_rate": 9.689114718517837e-06, "loss": 0.4436, "step": 169540 }, { "epoch": 1.0078404099125606, "grad_norm": 5.057089328765869, "learning_rate": 9.689042691058737e-06, "loss": 0.4797, "step": 169550 }, { "epoch": 1.007899851989229, "grad_norm": 5.419480800628662, "learning_rate": 9.688970655524545e-06, "loss": 0.3976, "step": 169560 }, { "epoch": 1.0079592940658975, "grad_norm": 5.647129535675049, "learning_rate": 9.688898611915386e-06, "loss": 0.4081, "step": 169570 }, { "epoch": 1.0080187361425659, "grad_norm": 7.177538871765137, "learning_rate": 9.688826560231383e-06, "loss": 0.4212, "step": 169580 }, { "epoch": 1.0080781782192343, "grad_norm": 5.132684230804443, "learning_rate": 9.688754500472663e-06, "loss": 0.3927, "step": 169590 }, { "epoch": 1.0081376202959027, "grad_norm": 5.975996494293213, "learning_rate": 9.688682432639349e-06, "loss": 0.4126, "step": 169600 }, { "epoch": 1.0081970623725711, "grad_norm": 4.526484489440918, "learning_rate": 9.688610356731563e-06, "loss": 0.4003, "step": 169610 }, { "epoch": 1.0082565044492395, "grad_norm": 6.651701927185059, "learning_rate": 9.68853827274943e-06, "loss": 0.4292, "step": 169620 }, { "epoch": 1.0083159465259077, "grad_norm": 5.280257225036621, "learning_rate": 9.688466180693076e-06, "loss": 0.4067, "step": 169630 }, { "epoch": 1.0083753886025761, "grad_norm": 6.248052597045898, "learning_rate": 9.688394080562624e-06, "loss": 0.4166, "step": 169640 }, { "epoch": 1.0084348306792446, "grad_norm": 3.625359535217285, "learning_rate": 9.688321972358196e-06, "loss": 0.4406, "step": 169650 }, { "epoch": 1.008494272755913, "grad_norm": 4.631424903869629, "learning_rate": 9.688249856079919e-06, "loss": 0.4393, "step": 169660 }, { "epoch": 1.0085537148325814, "grad_norm": 6.691457748413086, "learning_rate": 9.688177731727916e-06, "loss": 0.4126, "step": 169670 }, { "epoch": 1.0086131569092498, "grad_norm": 3.896077871322632, "learning_rate": 9.688105599302314e-06, "loss": 0.3836, "step": 169680 }, { "epoch": 1.0086725989859182, "grad_norm": 5.763241291046143, "learning_rate": 9.688033458803232e-06, "loss": 0.4142, "step": 169690 }, { "epoch": 1.0087320410625866, "grad_norm": 4.820707321166992, "learning_rate": 9.687961310230799e-06, "loss": 0.3954, "step": 169700 }, { "epoch": 1.008791483139255, "grad_norm": 4.7822442054748535, "learning_rate": 9.687889153585136e-06, "loss": 0.4022, "step": 169710 }, { "epoch": 1.0088509252159232, "grad_norm": 5.377306938171387, "learning_rate": 9.687816988866369e-06, "loss": 0.422, "step": 169720 }, { "epoch": 1.0089103672925916, "grad_norm": 5.040341854095459, "learning_rate": 9.68774481607462e-06, "loss": 0.3872, "step": 169730 }, { "epoch": 1.00896980936926, "grad_norm": 4.7781572341918945, "learning_rate": 9.687672635210018e-06, "loss": 0.4066, "step": 169740 }, { "epoch": 1.0090292514459285, "grad_norm": 5.869736194610596, "learning_rate": 9.687600446272683e-06, "loss": 0.4606, "step": 169750 }, { "epoch": 1.009088693522597, "grad_norm": 6.317665100097656, "learning_rate": 9.687528249262741e-06, "loss": 0.36, "step": 169760 }, { "epoch": 1.0091481355992653, "grad_norm": 4.968085289001465, "learning_rate": 9.687456044180317e-06, "loss": 0.4001, "step": 169770 }, { "epoch": 1.0092075776759337, "grad_norm": 6.703841686248779, "learning_rate": 9.687383831025532e-06, "loss": 0.4296, "step": 169780 }, { "epoch": 1.0092670197526021, "grad_norm": 5.423020839691162, "learning_rate": 9.687311609798514e-06, "loss": 0.4129, "step": 169790 }, { "epoch": 1.0093264618292705, "grad_norm": 4.844915866851807, "learning_rate": 9.687239380499386e-06, "loss": 0.3955, "step": 169800 }, { "epoch": 1.009385903905939, "grad_norm": 6.737550735473633, "learning_rate": 9.687167143128274e-06, "loss": 0.3954, "step": 169810 }, { "epoch": 1.0094453459826072, "grad_norm": 4.744842529296875, "learning_rate": 9.687094897685298e-06, "loss": 0.3708, "step": 169820 }, { "epoch": 1.0095047880592756, "grad_norm": 5.537263870239258, "learning_rate": 9.687022644170587e-06, "loss": 0.4247, "step": 169830 }, { "epoch": 1.009564230135944, "grad_norm": 4.884530544281006, "learning_rate": 9.686950382584264e-06, "loss": 0.3973, "step": 169840 }, { "epoch": 1.0096236722126124, "grad_norm": 3.62009334564209, "learning_rate": 9.686878112926455e-06, "loss": 0.3919, "step": 169850 }, { "epoch": 1.0096831142892808, "grad_norm": 6.953118801116943, "learning_rate": 9.68680583519728e-06, "loss": 0.3783, "step": 169860 }, { "epoch": 1.0097425563659492, "grad_norm": 5.28945779800415, "learning_rate": 9.686733549396866e-06, "loss": 0.3991, "step": 169870 }, { "epoch": 1.0098019984426176, "grad_norm": 4.699832439422607, "learning_rate": 9.686661255525339e-06, "loss": 0.4103, "step": 169880 }, { "epoch": 1.009861440519286, "grad_norm": 6.35422420501709, "learning_rate": 9.686588953582821e-06, "loss": 0.3949, "step": 169890 }, { "epoch": 1.0099208825959545, "grad_norm": 4.700189113616943, "learning_rate": 9.686516643569438e-06, "loss": 0.3915, "step": 169900 }, { "epoch": 1.0099803246726227, "grad_norm": 4.471513748168945, "learning_rate": 9.686444325485313e-06, "loss": 0.436, "step": 169910 }, { "epoch": 1.010039766749291, "grad_norm": 4.506036281585693, "learning_rate": 9.686371999330574e-06, "loss": 0.4132, "step": 169920 }, { "epoch": 1.0100992088259595, "grad_norm": 6.679996967315674, "learning_rate": 9.686299665105342e-06, "loss": 0.3864, "step": 169930 }, { "epoch": 1.010158650902628, "grad_norm": 4.628590106964111, "learning_rate": 9.686227322809743e-06, "loss": 0.4169, "step": 169940 }, { "epoch": 1.0102180929792963, "grad_norm": 4.338108062744141, "learning_rate": 9.686154972443901e-06, "loss": 0.3649, "step": 169950 }, { "epoch": 1.0102775350559647, "grad_norm": 8.058305740356445, "learning_rate": 9.686082614007942e-06, "loss": 0.4193, "step": 169960 }, { "epoch": 1.0103369771326332, "grad_norm": 4.673255443572998, "learning_rate": 9.68601024750199e-06, "loss": 0.4384, "step": 169970 }, { "epoch": 1.0103964192093016, "grad_norm": 5.64310884475708, "learning_rate": 9.685937872926168e-06, "loss": 0.4549, "step": 169980 }, { "epoch": 1.01045586128597, "grad_norm": 4.494222640991211, "learning_rate": 9.6858654902806e-06, "loss": 0.3687, "step": 169990 }, { "epoch": 1.0105153033626382, "grad_norm": 3.9787073135375977, "learning_rate": 9.685793099565417e-06, "loss": 0.3836, "step": 170000 }, { "epoch": 1.0105747454393066, "grad_norm": 5.010434627532959, "learning_rate": 9.685720700780734e-06, "loss": 0.412, "step": 170010 }, { "epoch": 1.010634187515975, "grad_norm": 5.967068672180176, "learning_rate": 9.685648293926684e-06, "loss": 0.4241, "step": 170020 }, { "epoch": 1.0106936295926434, "grad_norm": 5.019604682922363, "learning_rate": 9.68557587900339e-06, "loss": 0.3823, "step": 170030 }, { "epoch": 1.0107530716693118, "grad_norm": 5.04473352432251, "learning_rate": 9.685503456010972e-06, "loss": 0.391, "step": 170040 }, { "epoch": 1.0108125137459802, "grad_norm": 6.076211929321289, "learning_rate": 9.68543102494956e-06, "loss": 0.4357, "step": 170050 }, { "epoch": 1.0108719558226487, "grad_norm": 5.057896137237549, "learning_rate": 9.685358585819276e-06, "loss": 0.4086, "step": 170060 }, { "epoch": 1.010931397899317, "grad_norm": 7.252308368682861, "learning_rate": 9.685286138620246e-06, "loss": 0.4151, "step": 170070 }, { "epoch": 1.0109908399759855, "grad_norm": 5.03185510635376, "learning_rate": 9.685213683352594e-06, "loss": 0.4448, "step": 170080 }, { "epoch": 1.0110502820526537, "grad_norm": 5.700104236602783, "learning_rate": 9.685141220016446e-06, "loss": 0.3792, "step": 170090 }, { "epoch": 1.011109724129322, "grad_norm": 5.323520183563232, "learning_rate": 9.685068748611924e-06, "loss": 0.4327, "step": 170100 }, { "epoch": 1.0111691662059905, "grad_norm": 5.006885528564453, "learning_rate": 9.684996269139156e-06, "loss": 0.405, "step": 170110 }, { "epoch": 1.011228608282659, "grad_norm": 5.588801860809326, "learning_rate": 9.684923781598264e-06, "loss": 0.4195, "step": 170120 }, { "epoch": 1.0112880503593273, "grad_norm": 4.638322353363037, "learning_rate": 9.684851285989374e-06, "loss": 0.3987, "step": 170130 }, { "epoch": 1.0113474924359958, "grad_norm": 3.49105167388916, "learning_rate": 9.684778782312612e-06, "loss": 0.3985, "step": 170140 }, { "epoch": 1.0114069345126642, "grad_norm": 5.763157367706299, "learning_rate": 9.684706270568102e-06, "loss": 0.4241, "step": 170150 }, { "epoch": 1.0114663765893326, "grad_norm": 5.758403778076172, "learning_rate": 9.68463375075597e-06, "loss": 0.4189, "step": 170160 }, { "epoch": 1.011525818666001, "grad_norm": 6.476668834686279, "learning_rate": 9.684561222876337e-06, "loss": 0.4587, "step": 170170 }, { "epoch": 1.0115852607426694, "grad_norm": 5.216503143310547, "learning_rate": 9.684488686929332e-06, "loss": 0.4326, "step": 170180 }, { "epoch": 1.0116447028193376, "grad_norm": 6.419327735900879, "learning_rate": 9.684416142915079e-06, "loss": 0.4098, "step": 170190 }, { "epoch": 1.011704144896006, "grad_norm": 4.697789669036865, "learning_rate": 9.684343590833703e-06, "loss": 0.4216, "step": 170200 }, { "epoch": 1.0117635869726744, "grad_norm": 6.416660308837891, "learning_rate": 9.684271030685327e-06, "loss": 0.4113, "step": 170210 }, { "epoch": 1.0118230290493428, "grad_norm": 6.735210418701172, "learning_rate": 9.684198462470078e-06, "loss": 0.435, "step": 170220 }, { "epoch": 1.0118824711260113, "grad_norm": 5.962955474853516, "learning_rate": 9.68412588618808e-06, "loss": 0.4102, "step": 170230 }, { "epoch": 1.0119419132026797, "grad_norm": 6.188928604125977, "learning_rate": 9.68405330183946e-06, "loss": 0.4353, "step": 170240 }, { "epoch": 1.012001355279348, "grad_norm": 4.730652809143066, "learning_rate": 9.683980709424338e-06, "loss": 0.3946, "step": 170250 }, { "epoch": 1.0120607973560165, "grad_norm": 6.259733200073242, "learning_rate": 9.683908108942846e-06, "loss": 0.417, "step": 170260 }, { "epoch": 1.012120239432685, "grad_norm": 5.343627452850342, "learning_rate": 9.683835500395103e-06, "loss": 0.4307, "step": 170270 }, { "epoch": 1.0121796815093531, "grad_norm": 6.1752166748046875, "learning_rate": 9.683762883781238e-06, "loss": 0.4364, "step": 170280 }, { "epoch": 1.0122391235860215, "grad_norm": 4.61794900894165, "learning_rate": 9.683690259101373e-06, "loss": 0.3887, "step": 170290 }, { "epoch": 1.01229856566269, "grad_norm": 4.727553844451904, "learning_rate": 9.683617626355635e-06, "loss": 0.4135, "step": 170300 }, { "epoch": 1.0123580077393584, "grad_norm": 5.954432010650635, "learning_rate": 9.683544985544147e-06, "loss": 0.3843, "step": 170310 }, { "epoch": 1.0124174498160268, "grad_norm": 5.394768714904785, "learning_rate": 9.683472336667038e-06, "loss": 0.3674, "step": 170320 }, { "epoch": 1.0124768918926952, "grad_norm": 5.5577006340026855, "learning_rate": 9.68339967972443e-06, "loss": 0.4456, "step": 170330 }, { "epoch": 1.0125363339693636, "grad_norm": 5.590167045593262, "learning_rate": 9.683327014716448e-06, "loss": 0.4294, "step": 170340 }, { "epoch": 1.012595776046032, "grad_norm": 5.310103893280029, "learning_rate": 9.68325434164322e-06, "loss": 0.4209, "step": 170350 }, { "epoch": 1.0126552181227004, "grad_norm": 4.550602912902832, "learning_rate": 9.68318166050487e-06, "loss": 0.3787, "step": 170360 }, { "epoch": 1.0127146601993686, "grad_norm": 4.157722473144531, "learning_rate": 9.683108971301521e-06, "loss": 0.4133, "step": 170370 }, { "epoch": 1.012774102276037, "grad_norm": 6.017225742340088, "learning_rate": 9.683036274033297e-06, "loss": 0.3848, "step": 170380 }, { "epoch": 1.0128335443527055, "grad_norm": 6.448047637939453, "learning_rate": 9.68296356870033e-06, "loss": 0.4226, "step": 170390 }, { "epoch": 1.0128929864293739, "grad_norm": 5.340272426605225, "learning_rate": 9.682890855302738e-06, "loss": 0.4638, "step": 170400 }, { "epoch": 1.0129524285060423, "grad_norm": 4.951511383056641, "learning_rate": 9.682818133840651e-06, "loss": 0.3702, "step": 170410 }, { "epoch": 1.0130118705827107, "grad_norm": 5.7404632568359375, "learning_rate": 9.68274540431419e-06, "loss": 0.4586, "step": 170420 }, { "epoch": 1.013071312659379, "grad_norm": 7.130222797393799, "learning_rate": 9.682672666723485e-06, "loss": 0.4468, "step": 170430 }, { "epoch": 1.0131307547360475, "grad_norm": 4.206976890563965, "learning_rate": 9.682599921068658e-06, "loss": 0.4146, "step": 170440 }, { "epoch": 1.013190196812716, "grad_norm": 5.306924343109131, "learning_rate": 9.682527167349836e-06, "loss": 0.4028, "step": 170450 }, { "epoch": 1.0132496388893841, "grad_norm": 4.397561073303223, "learning_rate": 9.682454405567142e-06, "loss": 0.4016, "step": 170460 }, { "epoch": 1.0133090809660525, "grad_norm": 5.515102863311768, "learning_rate": 9.682381635720706e-06, "loss": 0.3892, "step": 170470 }, { "epoch": 1.013368523042721, "grad_norm": 4.42167854309082, "learning_rate": 9.682308857810648e-06, "loss": 0.4051, "step": 170480 }, { "epoch": 1.0134279651193894, "grad_norm": 5.8316121101379395, "learning_rate": 9.682236071837095e-06, "loss": 0.4339, "step": 170490 }, { "epoch": 1.0134874071960578, "grad_norm": 4.73142147064209, "learning_rate": 9.682163277800173e-06, "loss": 0.4324, "step": 170500 }, { "epoch": 1.0135468492727262, "grad_norm": 4.98613977432251, "learning_rate": 9.682090475700008e-06, "loss": 0.4411, "step": 170510 }, { "epoch": 1.0136062913493946, "grad_norm": 5.2204694747924805, "learning_rate": 9.682017665536722e-06, "loss": 0.4142, "step": 170520 }, { "epoch": 1.013665733426063, "grad_norm": 5.694300174713135, "learning_rate": 9.681944847310445e-06, "loss": 0.3819, "step": 170530 }, { "epoch": 1.0137251755027314, "grad_norm": 4.5853681564331055, "learning_rate": 9.6818720210213e-06, "loss": 0.3713, "step": 170540 }, { "epoch": 1.0137846175793999, "grad_norm": 3.8929800987243652, "learning_rate": 9.681799186669414e-06, "loss": 0.4013, "step": 170550 }, { "epoch": 1.013844059656068, "grad_norm": 6.3657050132751465, "learning_rate": 9.68172634425491e-06, "loss": 0.4395, "step": 170560 }, { "epoch": 1.0139035017327365, "grad_norm": 4.248103618621826, "learning_rate": 9.681653493777916e-06, "loss": 0.3691, "step": 170570 }, { "epoch": 1.0139629438094049, "grad_norm": 6.43340539932251, "learning_rate": 9.681580635238555e-06, "loss": 0.4465, "step": 170580 }, { "epoch": 1.0140223858860733, "grad_norm": 5.36431884765625, "learning_rate": 9.681507768636952e-06, "loss": 0.3911, "step": 170590 }, { "epoch": 1.0140818279627417, "grad_norm": 6.6872735023498535, "learning_rate": 9.681434893973236e-06, "loss": 0.4231, "step": 170600 }, { "epoch": 1.0141412700394101, "grad_norm": 5.015651702880859, "learning_rate": 9.68136201124753e-06, "loss": 0.3862, "step": 170610 }, { "epoch": 1.0142007121160785, "grad_norm": 6.689297676086426, "learning_rate": 9.68128912045996e-06, "loss": 0.3967, "step": 170620 }, { "epoch": 1.014260154192747, "grad_norm": 6.42944860458374, "learning_rate": 9.681216221610651e-06, "loss": 0.386, "step": 170630 }, { "epoch": 1.0143195962694154, "grad_norm": 3.7361059188842773, "learning_rate": 9.68114331469973e-06, "loss": 0.3985, "step": 170640 }, { "epoch": 1.0143790383460836, "grad_norm": 8.568180084228516, "learning_rate": 9.681070399727322e-06, "loss": 0.4161, "step": 170650 }, { "epoch": 1.014438480422752, "grad_norm": 3.9627065658569336, "learning_rate": 9.68099747669355e-06, "loss": 0.4076, "step": 170660 }, { "epoch": 1.0144979224994204, "grad_norm": 5.597522258758545, "learning_rate": 9.680924545598544e-06, "loss": 0.3775, "step": 170670 }, { "epoch": 1.0145573645760888, "grad_norm": 4.53041410446167, "learning_rate": 9.680851606442427e-06, "loss": 0.4102, "step": 170680 }, { "epoch": 1.0146168066527572, "grad_norm": 5.408559322357178, "learning_rate": 9.680778659225325e-06, "loss": 0.434, "step": 170690 }, { "epoch": 1.0146762487294256, "grad_norm": 6.890305995941162, "learning_rate": 9.680705703947364e-06, "loss": 0.4272, "step": 170700 }, { "epoch": 1.014735690806094, "grad_norm": 5.513442039489746, "learning_rate": 9.68063274060867e-06, "loss": 0.4678, "step": 170710 }, { "epoch": 1.0147951328827625, "grad_norm": 3.9698832035064697, "learning_rate": 9.680559769209366e-06, "loss": 0.4035, "step": 170720 }, { "epoch": 1.0148545749594309, "grad_norm": 5.657278537750244, "learning_rate": 9.68048678974958e-06, "loss": 0.4065, "step": 170730 }, { "epoch": 1.014914017036099, "grad_norm": 6.754522800445557, "learning_rate": 9.680413802229438e-06, "loss": 0.4365, "step": 170740 }, { "epoch": 1.0149734591127675, "grad_norm": 4.567541599273682, "learning_rate": 9.680340806649065e-06, "loss": 0.406, "step": 170750 }, { "epoch": 1.015032901189436, "grad_norm": 6.199436187744141, "learning_rate": 9.680267803008585e-06, "loss": 0.4019, "step": 170760 }, { "epoch": 1.0150923432661043, "grad_norm": 4.005524158477783, "learning_rate": 9.680194791308126e-06, "loss": 0.3875, "step": 170770 }, { "epoch": 1.0151517853427727, "grad_norm": 4.7491350173950195, "learning_rate": 9.680121771547815e-06, "loss": 0.3897, "step": 170780 }, { "epoch": 1.0152112274194411, "grad_norm": 6.579061031341553, "learning_rate": 9.680048743727774e-06, "loss": 0.3833, "step": 170790 }, { "epoch": 1.0152706694961096, "grad_norm": 4.430703639984131, "learning_rate": 9.679975707848131e-06, "loss": 0.4381, "step": 170800 }, { "epoch": 1.015330111572778, "grad_norm": 5.318037033081055, "learning_rate": 9.679902663909014e-06, "loss": 0.4167, "step": 170810 }, { "epoch": 1.0153895536494464, "grad_norm": 6.309804916381836, "learning_rate": 9.679829611910543e-06, "loss": 0.4064, "step": 170820 }, { "epoch": 1.0154489957261146, "grad_norm": 5.385793685913086, "learning_rate": 9.679756551852848e-06, "loss": 0.415, "step": 170830 }, { "epoch": 1.015508437802783, "grad_norm": 4.164328098297119, "learning_rate": 9.679683483736052e-06, "loss": 0.3878, "step": 170840 }, { "epoch": 1.0155678798794514, "grad_norm": 8.384709358215332, "learning_rate": 9.679610407560286e-06, "loss": 0.3952, "step": 170850 }, { "epoch": 1.0156273219561198, "grad_norm": 4.979422569274902, "learning_rate": 9.67953732332567e-06, "loss": 0.4161, "step": 170860 }, { "epoch": 1.0156867640327882, "grad_norm": 4.761297702789307, "learning_rate": 9.679464231032334e-06, "loss": 0.397, "step": 170870 }, { "epoch": 1.0157462061094567, "grad_norm": 7.961933612823486, "learning_rate": 9.679391130680402e-06, "loss": 0.4395, "step": 170880 }, { "epoch": 1.015805648186125, "grad_norm": 4.3913774490356445, "learning_rate": 9.679318022269999e-06, "loss": 0.3985, "step": 170890 }, { "epoch": 1.0158650902627935, "grad_norm": 6.636097431182861, "learning_rate": 9.679244905801253e-06, "loss": 0.4003, "step": 170900 }, { "epoch": 1.015924532339462, "grad_norm": 4.4924774169921875, "learning_rate": 9.67917178127429e-06, "loss": 0.4374, "step": 170910 }, { "epoch": 1.0159839744161303, "grad_norm": 5.020120143890381, "learning_rate": 9.679098648689234e-06, "loss": 0.4501, "step": 170920 }, { "epoch": 1.0160434164927985, "grad_norm": 6.0700483322143555, "learning_rate": 9.67902550804621e-06, "loss": 0.4113, "step": 170930 }, { "epoch": 1.016102858569467, "grad_norm": 5.777373790740967, "learning_rate": 9.678952359345348e-06, "loss": 0.4005, "step": 170940 }, { "epoch": 1.0161623006461353, "grad_norm": 4.5564680099487305, "learning_rate": 9.678879202586771e-06, "loss": 0.3968, "step": 170950 }, { "epoch": 1.0162217427228037, "grad_norm": 4.686110973358154, "learning_rate": 9.678806037770604e-06, "loss": 0.4066, "step": 170960 }, { "epoch": 1.0162811847994722, "grad_norm": 4.103755474090576, "learning_rate": 9.678732864896977e-06, "loss": 0.3847, "step": 170970 }, { "epoch": 1.0163406268761406, "grad_norm": 4.741143703460693, "learning_rate": 9.678659683966014e-06, "loss": 0.3847, "step": 170980 }, { "epoch": 1.016400068952809, "grad_norm": 5.454966068267822, "learning_rate": 9.678586494977839e-06, "loss": 0.4106, "step": 170990 }, { "epoch": 1.0164595110294774, "grad_norm": 5.933452129364014, "learning_rate": 9.678513297932582e-06, "loss": 0.4037, "step": 171000 }, { "epoch": 1.0165189531061458, "grad_norm": 4.481739521026611, "learning_rate": 9.678440092830366e-06, "loss": 0.4346, "step": 171010 }, { "epoch": 1.016578395182814, "grad_norm": 4.059203624725342, "learning_rate": 9.678366879671318e-06, "loss": 0.3659, "step": 171020 }, { "epoch": 1.0166378372594824, "grad_norm": 4.542205333709717, "learning_rate": 9.678293658455564e-06, "loss": 0.4189, "step": 171030 }, { "epoch": 1.0166972793361508, "grad_norm": 4.950164318084717, "learning_rate": 9.678220429183229e-06, "loss": 0.4261, "step": 171040 }, { "epoch": 1.0167567214128193, "grad_norm": 7.13145112991333, "learning_rate": 9.678147191854441e-06, "loss": 0.4207, "step": 171050 }, { "epoch": 1.0168161634894877, "grad_norm": 4.444032192230225, "learning_rate": 9.678073946469326e-06, "loss": 0.4166, "step": 171060 }, { "epoch": 1.016875605566156, "grad_norm": 5.854455471038818, "learning_rate": 9.678000693028008e-06, "loss": 0.4375, "step": 171070 }, { "epoch": 1.0169350476428245, "grad_norm": 4.606929302215576, "learning_rate": 9.677927431530616e-06, "loss": 0.4217, "step": 171080 }, { "epoch": 1.016994489719493, "grad_norm": 5.03029727935791, "learning_rate": 9.677854161977274e-06, "loss": 0.3863, "step": 171090 }, { "epoch": 1.0170539317961613, "grad_norm": 3.964010715484619, "learning_rate": 9.677780884368109e-06, "loss": 0.3857, "step": 171100 }, { "epoch": 1.0171133738728295, "grad_norm": 4.382178783416748, "learning_rate": 9.677707598703248e-06, "loss": 0.4207, "step": 171110 }, { "epoch": 1.017172815949498, "grad_norm": 3.467745065689087, "learning_rate": 9.677634304982815e-06, "loss": 0.4369, "step": 171120 }, { "epoch": 1.0172322580261663, "grad_norm": 5.397764682769775, "learning_rate": 9.677561003206938e-06, "loss": 0.392, "step": 171130 }, { "epoch": 1.0172917001028348, "grad_norm": 5.081275463104248, "learning_rate": 9.677487693375744e-06, "loss": 0.4514, "step": 171140 }, { "epoch": 1.0173511421795032, "grad_norm": 4.838357925415039, "learning_rate": 9.677414375489358e-06, "loss": 0.4123, "step": 171150 }, { "epoch": 1.0174105842561716, "grad_norm": 4.72930383682251, "learning_rate": 9.677341049547906e-06, "loss": 0.4056, "step": 171160 }, { "epoch": 1.01747002633284, "grad_norm": 5.0054192543029785, "learning_rate": 9.677267715551512e-06, "loss": 0.4101, "step": 171170 }, { "epoch": 1.0175294684095084, "grad_norm": 6.931312084197998, "learning_rate": 9.67719437350031e-06, "loss": 0.4292, "step": 171180 }, { "epoch": 1.0175889104861768, "grad_norm": 5.238154888153076, "learning_rate": 9.677121023394418e-06, "loss": 0.4251, "step": 171190 }, { "epoch": 1.017648352562845, "grad_norm": 5.416851997375488, "learning_rate": 9.677047665233965e-06, "loss": 0.3841, "step": 171200 }, { "epoch": 1.0177077946395134, "grad_norm": 4.871791839599609, "learning_rate": 9.67697429901908e-06, "loss": 0.4254, "step": 171210 }, { "epoch": 1.0177672367161819, "grad_norm": 3.71061110496521, "learning_rate": 9.676900924749884e-06, "loss": 0.4093, "step": 171220 }, { "epoch": 1.0178266787928503, "grad_norm": 5.444136619567871, "learning_rate": 9.67682754242651e-06, "loss": 0.4372, "step": 171230 }, { "epoch": 1.0178861208695187, "grad_norm": 4.8306379318237305, "learning_rate": 9.67675415204908e-06, "loss": 0.3839, "step": 171240 }, { "epoch": 1.017945562946187, "grad_norm": 4.524947643280029, "learning_rate": 9.676680753617719e-06, "loss": 0.4245, "step": 171250 }, { "epoch": 1.0180050050228555, "grad_norm": 5.682474136352539, "learning_rate": 9.676607347132558e-06, "loss": 0.422, "step": 171260 }, { "epoch": 1.018064447099524, "grad_norm": 4.198234558105469, "learning_rate": 9.676533932593722e-06, "loss": 0.4037, "step": 171270 }, { "epoch": 1.0181238891761923, "grad_norm": 6.461786270141602, "learning_rate": 9.676460510001335e-06, "loss": 0.4256, "step": 171280 }, { "epoch": 1.0181833312528608, "grad_norm": 5.873082637786865, "learning_rate": 9.676387079355526e-06, "loss": 0.4003, "step": 171290 }, { "epoch": 1.018242773329529, "grad_norm": 4.532270431518555, "learning_rate": 9.676313640656419e-06, "loss": 0.3811, "step": 171300 }, { "epoch": 1.0183022154061974, "grad_norm": 4.938126564025879, "learning_rate": 9.676240193904143e-06, "loss": 0.4129, "step": 171310 }, { "epoch": 1.0183616574828658, "grad_norm": 4.589117527008057, "learning_rate": 9.676166739098823e-06, "loss": 0.4171, "step": 171320 }, { "epoch": 1.0184210995595342, "grad_norm": 5.524413585662842, "learning_rate": 9.676093276240586e-06, "loss": 0.4059, "step": 171330 }, { "epoch": 1.0184805416362026, "grad_norm": 5.72935152053833, "learning_rate": 9.676019805329558e-06, "loss": 0.3868, "step": 171340 }, { "epoch": 1.018539983712871, "grad_norm": 5.475022315979004, "learning_rate": 9.675946326365866e-06, "loss": 0.4185, "step": 171350 }, { "epoch": 1.0185994257895394, "grad_norm": 5.5804057121276855, "learning_rate": 9.675872839349638e-06, "loss": 0.4248, "step": 171360 }, { "epoch": 1.0186588678662079, "grad_norm": 3.846759557723999, "learning_rate": 9.675799344280999e-06, "loss": 0.3881, "step": 171370 }, { "epoch": 1.0187183099428763, "grad_norm": 6.614734172821045, "learning_rate": 9.675725841160073e-06, "loss": 0.4425, "step": 171380 }, { "epoch": 1.0187777520195445, "grad_norm": 5.225610733032227, "learning_rate": 9.67565232998699e-06, "loss": 0.3813, "step": 171390 }, { "epoch": 1.0188371940962129, "grad_norm": 6.79468297958374, "learning_rate": 9.67557881076188e-06, "loss": 0.4227, "step": 171400 }, { "epoch": 1.0188966361728813, "grad_norm": 4.907666206359863, "learning_rate": 9.675505283484861e-06, "loss": 0.3959, "step": 171410 }, { "epoch": 1.0189560782495497, "grad_norm": 4.323849678039551, "learning_rate": 9.675431748156064e-06, "loss": 0.376, "step": 171420 }, { "epoch": 1.0190155203262181, "grad_norm": 5.551994323730469, "learning_rate": 9.675358204775618e-06, "loss": 0.4091, "step": 171430 }, { "epoch": 1.0190749624028865, "grad_norm": 4.799386978149414, "learning_rate": 9.675284653343644e-06, "loss": 0.4309, "step": 171440 }, { "epoch": 1.019134404479555, "grad_norm": 4.774550437927246, "learning_rate": 9.675211093860275e-06, "loss": 0.398, "step": 171450 }, { "epoch": 1.0191938465562234, "grad_norm": 7.585941791534424, "learning_rate": 9.675137526325634e-06, "loss": 0.4315, "step": 171460 }, { "epoch": 1.0192532886328918, "grad_norm": 4.642856121063232, "learning_rate": 9.675063950739848e-06, "loss": 0.4063, "step": 171470 }, { "epoch": 1.01931273070956, "grad_norm": 6.637650012969971, "learning_rate": 9.674990367103045e-06, "loss": 0.4549, "step": 171480 }, { "epoch": 1.0193721727862284, "grad_norm": 7.1848063468933105, "learning_rate": 9.67491677541535e-06, "loss": 0.4199, "step": 171490 }, { "epoch": 1.0194316148628968, "grad_norm": 6.6718430519104, "learning_rate": 9.674843175676888e-06, "loss": 0.4015, "step": 171500 }, { "epoch": 1.0194910569395652, "grad_norm": 5.645270347595215, "learning_rate": 9.674769567887793e-06, "loss": 0.4383, "step": 171510 }, { "epoch": 1.0195504990162336, "grad_norm": 4.005551815032959, "learning_rate": 9.674695952048184e-06, "loss": 0.454, "step": 171520 }, { "epoch": 1.019609941092902, "grad_norm": 6.801724433898926, "learning_rate": 9.674622328158191e-06, "loss": 0.4475, "step": 171530 }, { "epoch": 1.0196693831695705, "grad_norm": 4.518929958343506, "learning_rate": 9.674548696217941e-06, "loss": 0.3658, "step": 171540 }, { "epoch": 1.0197288252462389, "grad_norm": 4.485494136810303, "learning_rate": 9.674475056227562e-06, "loss": 0.4252, "step": 171550 }, { "epoch": 1.0197882673229073, "grad_norm": 4.891384601593018, "learning_rate": 9.674401408187177e-06, "loss": 0.4152, "step": 171560 }, { "epoch": 1.0198477093995755, "grad_norm": 4.654564380645752, "learning_rate": 9.674327752096916e-06, "loss": 0.4063, "step": 171570 }, { "epoch": 1.019907151476244, "grad_norm": 4.236772537231445, "learning_rate": 9.674254087956905e-06, "loss": 0.3889, "step": 171580 }, { "epoch": 1.0199665935529123, "grad_norm": 5.168183326721191, "learning_rate": 9.674180415767269e-06, "loss": 0.4103, "step": 171590 }, { "epoch": 1.0200260356295807, "grad_norm": 5.026098251342773, "learning_rate": 9.674106735528138e-06, "loss": 0.4135, "step": 171600 }, { "epoch": 1.0200854777062491, "grad_norm": 6.304509162902832, "learning_rate": 9.674033047239637e-06, "loss": 0.4011, "step": 171610 }, { "epoch": 1.0201449197829175, "grad_norm": 5.377142429351807, "learning_rate": 9.673959350901895e-06, "loss": 0.3674, "step": 171620 }, { "epoch": 1.020204361859586, "grad_norm": 5.893759250640869, "learning_rate": 9.673885646515035e-06, "loss": 0.4381, "step": 171630 }, { "epoch": 1.0202638039362544, "grad_norm": 4.170300006866455, "learning_rate": 9.673811934079188e-06, "loss": 0.4171, "step": 171640 }, { "epoch": 1.0203232460129228, "grad_norm": 5.844766139984131, "learning_rate": 9.67373821359448e-06, "loss": 0.4567, "step": 171650 }, { "epoch": 1.0203826880895912, "grad_norm": 4.999971866607666, "learning_rate": 9.673664485061034e-06, "loss": 0.4496, "step": 171660 }, { "epoch": 1.0204421301662594, "grad_norm": 5.848861217498779, "learning_rate": 9.673590748478983e-06, "loss": 0.4491, "step": 171670 }, { "epoch": 1.0205015722429278, "grad_norm": 4.431665897369385, "learning_rate": 9.67351700384845e-06, "loss": 0.4235, "step": 171680 }, { "epoch": 1.0205610143195962, "grad_norm": 4.469581604003906, "learning_rate": 9.673443251169562e-06, "loss": 0.4335, "step": 171690 }, { "epoch": 1.0206204563962646, "grad_norm": 4.950170516967773, "learning_rate": 9.673369490442447e-06, "loss": 0.4293, "step": 171700 }, { "epoch": 1.020679898472933, "grad_norm": 4.452422142028809, "learning_rate": 9.673295721667235e-06, "loss": 0.3863, "step": 171710 }, { "epoch": 1.0207393405496015, "grad_norm": 4.262515068054199, "learning_rate": 9.673221944844048e-06, "loss": 0.4054, "step": 171720 }, { "epoch": 1.0207987826262699, "grad_norm": 5.080971717834473, "learning_rate": 9.673148159973016e-06, "loss": 0.4154, "step": 171730 }, { "epoch": 1.0208582247029383, "grad_norm": 4.407110691070557, "learning_rate": 9.673074367054265e-06, "loss": 0.4075, "step": 171740 }, { "epoch": 1.0209176667796067, "grad_norm": 3.8018648624420166, "learning_rate": 9.673000566087921e-06, "loss": 0.3973, "step": 171750 }, { "epoch": 1.020977108856275, "grad_norm": 4.019376754760742, "learning_rate": 9.672926757074114e-06, "loss": 0.4113, "step": 171760 }, { "epoch": 1.0210365509329433, "grad_norm": 5.088629722595215, "learning_rate": 9.672852940012969e-06, "loss": 0.3749, "step": 171770 }, { "epoch": 1.0210959930096117, "grad_norm": 4.366239070892334, "learning_rate": 9.672779114904613e-06, "loss": 0.4053, "step": 171780 }, { "epoch": 1.0211554350862801, "grad_norm": 4.801264762878418, "learning_rate": 9.672705281749176e-06, "loss": 0.3406, "step": 171790 }, { "epoch": 1.0212148771629486, "grad_norm": 4.858572483062744, "learning_rate": 9.672631440546782e-06, "loss": 0.4209, "step": 171800 }, { "epoch": 1.021274319239617, "grad_norm": 5.6676249504089355, "learning_rate": 9.672557591297558e-06, "loss": 0.4259, "step": 171810 }, { "epoch": 1.0213337613162854, "grad_norm": 5.745235443115234, "learning_rate": 9.672483734001635e-06, "loss": 0.4516, "step": 171820 }, { "epoch": 1.0213932033929538, "grad_norm": 4.1804304122924805, "learning_rate": 9.672409868659134e-06, "loss": 0.3717, "step": 171830 }, { "epoch": 1.0214526454696222, "grad_norm": 5.833383560180664, "learning_rate": 9.672335995270187e-06, "loss": 0.3957, "step": 171840 }, { "epoch": 1.0215120875462904, "grad_norm": 5.583715915679932, "learning_rate": 9.672262113834921e-06, "loss": 0.4366, "step": 171850 }, { "epoch": 1.0215715296229588, "grad_norm": 3.7701501846313477, "learning_rate": 9.67218822435346e-06, "loss": 0.3701, "step": 171860 }, { "epoch": 1.0216309716996272, "grad_norm": 4.991240978240967, "learning_rate": 9.672114326825937e-06, "loss": 0.4102, "step": 171870 }, { "epoch": 1.0216904137762957, "grad_norm": 6.343316555023193, "learning_rate": 9.672040421252472e-06, "loss": 0.454, "step": 171880 }, { "epoch": 1.021749855852964, "grad_norm": 4.882709503173828, "learning_rate": 9.671966507633197e-06, "loss": 0.3995, "step": 171890 }, { "epoch": 1.0218092979296325, "grad_norm": 3.7931995391845703, "learning_rate": 9.67189258596824e-06, "loss": 0.3936, "step": 171900 }, { "epoch": 1.021868740006301, "grad_norm": 5.668703556060791, "learning_rate": 9.671818656257724e-06, "loss": 0.4007, "step": 171910 }, { "epoch": 1.0219281820829693, "grad_norm": 4.286593437194824, "learning_rate": 9.67174471850178e-06, "loss": 0.414, "step": 171920 }, { "epoch": 1.0219876241596377, "grad_norm": 5.34869384765625, "learning_rate": 9.671670772700535e-06, "loss": 0.4042, "step": 171930 }, { "epoch": 1.022047066236306, "grad_norm": 5.538359642028809, "learning_rate": 9.671596818854114e-06, "loss": 0.3947, "step": 171940 }, { "epoch": 1.0221065083129743, "grad_norm": 4.231283664703369, "learning_rate": 9.671522856962647e-06, "loss": 0.4755, "step": 171950 }, { "epoch": 1.0221659503896428, "grad_norm": 5.195382118225098, "learning_rate": 9.67144888702626e-06, "loss": 0.4024, "step": 171960 }, { "epoch": 1.0222253924663112, "grad_norm": 5.043871879577637, "learning_rate": 9.671374909045079e-06, "loss": 0.3651, "step": 171970 }, { "epoch": 1.0222848345429796, "grad_norm": 6.209076881408691, "learning_rate": 9.671300923019236e-06, "loss": 0.3998, "step": 171980 }, { "epoch": 1.022344276619648, "grad_norm": 5.91054630279541, "learning_rate": 9.671226928948854e-06, "loss": 0.4175, "step": 171990 }, { "epoch": 1.0224037186963164, "grad_norm": 5.113724708557129, "learning_rate": 9.671152926834061e-06, "loss": 0.3921, "step": 172000 }, { "epoch": 1.0224631607729848, "grad_norm": 4.605566024780273, "learning_rate": 9.671078916674986e-06, "loss": 0.3857, "step": 172010 }, { "epoch": 1.0225226028496532, "grad_norm": 5.2530598640441895, "learning_rate": 9.671004898471756e-06, "loss": 0.4199, "step": 172020 }, { "epoch": 1.0225820449263217, "grad_norm": 6.428163528442383, "learning_rate": 9.670930872224498e-06, "loss": 0.4925, "step": 172030 }, { "epoch": 1.0226414870029898, "grad_norm": 5.608638763427734, "learning_rate": 9.67085683793334e-06, "loss": 0.41, "step": 172040 }, { "epoch": 1.0227009290796583, "grad_norm": 4.882018089294434, "learning_rate": 9.670782795598408e-06, "loss": 0.4376, "step": 172050 }, { "epoch": 1.0227603711563267, "grad_norm": 4.5951619148254395, "learning_rate": 9.670708745219832e-06, "loss": 0.4199, "step": 172060 }, { "epoch": 1.022819813232995, "grad_norm": 4.998984336853027, "learning_rate": 9.670634686797737e-06, "loss": 0.4281, "step": 172070 }, { "epoch": 1.0228792553096635, "grad_norm": 6.301492691040039, "learning_rate": 9.670560620332254e-06, "loss": 0.3953, "step": 172080 }, { "epoch": 1.022938697386332, "grad_norm": 4.8013763427734375, "learning_rate": 9.670486545823508e-06, "loss": 0.4319, "step": 172090 }, { "epoch": 1.0229981394630003, "grad_norm": 4.231202125549316, "learning_rate": 9.670412463271624e-06, "loss": 0.4007, "step": 172100 }, { "epoch": 1.0230575815396687, "grad_norm": 4.594567775726318, "learning_rate": 9.670338372676735e-06, "loss": 0.3919, "step": 172110 }, { "epoch": 1.0231170236163372, "grad_norm": 4.899773120880127, "learning_rate": 9.670264274038965e-06, "loss": 0.3969, "step": 172120 }, { "epoch": 1.0231764656930054, "grad_norm": 7.284848690032959, "learning_rate": 9.670190167358444e-06, "loss": 0.4137, "step": 172130 }, { "epoch": 1.0232359077696738, "grad_norm": 4.060206413269043, "learning_rate": 9.670116052635296e-06, "loss": 0.3792, "step": 172140 }, { "epoch": 1.0232953498463422, "grad_norm": 5.9037675857543945, "learning_rate": 9.670041929869654e-06, "loss": 0.4499, "step": 172150 }, { "epoch": 1.0233547919230106, "grad_norm": 4.333358287811279, "learning_rate": 9.66996779906164e-06, "loss": 0.4212, "step": 172160 }, { "epoch": 1.023414233999679, "grad_norm": 5.229738712310791, "learning_rate": 9.669893660211385e-06, "loss": 0.4054, "step": 172170 }, { "epoch": 1.0234736760763474, "grad_norm": 5.243213653564453, "learning_rate": 9.669819513319017e-06, "loss": 0.42, "step": 172180 }, { "epoch": 1.0235331181530158, "grad_norm": 4.526639938354492, "learning_rate": 9.669745358384661e-06, "loss": 0.4364, "step": 172190 }, { "epoch": 1.0235925602296843, "grad_norm": 5.615834712982178, "learning_rate": 9.669671195408448e-06, "loss": 0.4467, "step": 172200 }, { "epoch": 1.0236520023063527, "grad_norm": 5.036820888519287, "learning_rate": 9.669597024390502e-06, "loss": 0.4044, "step": 172210 }, { "epoch": 1.0237114443830209, "grad_norm": 6.382699966430664, "learning_rate": 9.669522845330955e-06, "loss": 0.4232, "step": 172220 }, { "epoch": 1.0237708864596893, "grad_norm": 5.44492769241333, "learning_rate": 9.66944865822993e-06, "loss": 0.437, "step": 172230 }, { "epoch": 1.0238303285363577, "grad_norm": 6.337867259979248, "learning_rate": 9.669374463087559e-06, "loss": 0.3759, "step": 172240 }, { "epoch": 1.023889770613026, "grad_norm": 5.688075542449951, "learning_rate": 9.669300259903968e-06, "loss": 0.3619, "step": 172250 }, { "epoch": 1.0239492126896945, "grad_norm": 4.312415599822998, "learning_rate": 9.669226048679283e-06, "loss": 0.4045, "step": 172260 }, { "epoch": 1.024008654766363, "grad_norm": 3.8611233234405518, "learning_rate": 9.669151829413637e-06, "loss": 0.3919, "step": 172270 }, { "epoch": 1.0240680968430314, "grad_norm": 4.988245010375977, "learning_rate": 9.66907760210715e-06, "loss": 0.4098, "step": 172280 }, { "epoch": 1.0241275389196998, "grad_norm": 4.362753391265869, "learning_rate": 9.669003366759959e-06, "loss": 0.4147, "step": 172290 }, { "epoch": 1.0241869809963682, "grad_norm": 4.331930160522461, "learning_rate": 9.668929123372184e-06, "loss": 0.424, "step": 172300 }, { "epoch": 1.0242464230730364, "grad_norm": 4.074740886688232, "learning_rate": 9.668854871943957e-06, "loss": 0.3941, "step": 172310 }, { "epoch": 1.0243058651497048, "grad_norm": 4.390085697174072, "learning_rate": 9.668780612475404e-06, "loss": 0.4049, "step": 172320 }, { "epoch": 1.0243653072263732, "grad_norm": 5.453699111938477, "learning_rate": 9.668706344966654e-06, "loss": 0.4081, "step": 172330 }, { "epoch": 1.0244247493030416, "grad_norm": 5.1455278396606445, "learning_rate": 9.668632069417837e-06, "loss": 0.4111, "step": 172340 }, { "epoch": 1.02448419137971, "grad_norm": 4.219660758972168, "learning_rate": 9.668557785829076e-06, "loss": 0.4039, "step": 172350 }, { "epoch": 1.0245436334563784, "grad_norm": 5.796095371246338, "learning_rate": 9.668483494200501e-06, "loss": 0.4102, "step": 172360 }, { "epoch": 1.0246030755330469, "grad_norm": 4.654630661010742, "learning_rate": 9.668409194532243e-06, "loss": 0.3791, "step": 172370 }, { "epoch": 1.0246625176097153, "grad_norm": 6.033899307250977, "learning_rate": 9.668334886824424e-06, "loss": 0.3998, "step": 172380 }, { "epoch": 1.0247219596863837, "grad_norm": 5.123136043548584, "learning_rate": 9.668260571077178e-06, "loss": 0.4098, "step": 172390 }, { "epoch": 1.024781401763052, "grad_norm": 5.875850677490234, "learning_rate": 9.668186247290629e-06, "loss": 0.4354, "step": 172400 }, { "epoch": 1.0248408438397203, "grad_norm": 5.205731391906738, "learning_rate": 9.668111915464907e-06, "loss": 0.3462, "step": 172410 }, { "epoch": 1.0249002859163887, "grad_norm": 5.665280342102051, "learning_rate": 9.668037575600137e-06, "loss": 0.3886, "step": 172420 }, { "epoch": 1.0249597279930571, "grad_norm": 4.961385726928711, "learning_rate": 9.667963227696453e-06, "loss": 0.4159, "step": 172430 }, { "epoch": 1.0250191700697255, "grad_norm": 5.793961048126221, "learning_rate": 9.667888871753976e-06, "loss": 0.3897, "step": 172440 }, { "epoch": 1.025078612146394, "grad_norm": 5.261792182922363, "learning_rate": 9.667814507772839e-06, "loss": 0.4139, "step": 172450 }, { "epoch": 1.0251380542230624, "grad_norm": 6.20182466506958, "learning_rate": 9.66774013575317e-06, "loss": 0.4091, "step": 172460 }, { "epoch": 1.0251974962997308, "grad_norm": 5.235019683837891, "learning_rate": 9.667665755695092e-06, "loss": 0.4371, "step": 172470 }, { "epoch": 1.0252569383763992, "grad_norm": 4.073911666870117, "learning_rate": 9.667591367598739e-06, "loss": 0.4322, "step": 172480 }, { "epoch": 1.0253163804530676, "grad_norm": 4.7251176834106445, "learning_rate": 9.667516971464238e-06, "loss": 0.4459, "step": 172490 }, { "epoch": 1.0253758225297358, "grad_norm": 6.110222339630127, "learning_rate": 9.667442567291712e-06, "loss": 0.4025, "step": 172500 }, { "epoch": 1.0254352646064042, "grad_norm": 5.947420597076416, "learning_rate": 9.667368155081296e-06, "loss": 0.4049, "step": 172510 }, { "epoch": 1.0254947066830726, "grad_norm": 5.590342998504639, "learning_rate": 9.667293734833114e-06, "loss": 0.4122, "step": 172520 }, { "epoch": 1.025554148759741, "grad_norm": 5.580326557159424, "learning_rate": 9.667219306547295e-06, "loss": 0.4139, "step": 172530 }, { "epoch": 1.0256135908364095, "grad_norm": 5.233996868133545, "learning_rate": 9.667144870223967e-06, "loss": 0.4049, "step": 172540 }, { "epoch": 1.0256730329130779, "grad_norm": 3.7838454246520996, "learning_rate": 9.66707042586326e-06, "loss": 0.3706, "step": 172550 }, { "epoch": 1.0257324749897463, "grad_norm": 5.190861701965332, "learning_rate": 9.6669959734653e-06, "loss": 0.4169, "step": 172560 }, { "epoch": 1.0257919170664147, "grad_norm": 3.963945150375366, "learning_rate": 9.666921513030219e-06, "loss": 0.3828, "step": 172570 }, { "epoch": 1.0258513591430831, "grad_norm": 6.286623477935791, "learning_rate": 9.666847044558138e-06, "loss": 0.3884, "step": 172580 }, { "epoch": 1.0259108012197513, "grad_norm": 5.504608631134033, "learning_rate": 9.666772568049192e-06, "loss": 0.4272, "step": 172590 }, { "epoch": 1.0259702432964197, "grad_norm": 4.49426794052124, "learning_rate": 9.666698083503508e-06, "loss": 0.3863, "step": 172600 }, { "epoch": 1.0260296853730881, "grad_norm": 5.419284343719482, "learning_rate": 9.66662359092121e-06, "loss": 0.4059, "step": 172610 }, { "epoch": 1.0260891274497566, "grad_norm": 6.684869766235352, "learning_rate": 9.66654909030243e-06, "loss": 0.4038, "step": 172620 }, { "epoch": 1.026148569526425, "grad_norm": 6.240061283111572, "learning_rate": 9.666474581647296e-06, "loss": 0.3839, "step": 172630 }, { "epoch": 1.0262080116030934, "grad_norm": 4.010298252105713, "learning_rate": 9.666400064955937e-06, "loss": 0.4172, "step": 172640 }, { "epoch": 1.0262674536797618, "grad_norm": 5.227554798126221, "learning_rate": 9.66632554022848e-06, "loss": 0.4262, "step": 172650 }, { "epoch": 1.0263268957564302, "grad_norm": 5.808139801025391, "learning_rate": 9.666251007465052e-06, "loss": 0.4017, "step": 172660 }, { "epoch": 1.0263863378330986, "grad_norm": 4.764224052429199, "learning_rate": 9.666176466665787e-06, "loss": 0.4439, "step": 172670 }, { "epoch": 1.0264457799097668, "grad_norm": 4.84274435043335, "learning_rate": 9.666101917830805e-06, "loss": 0.3963, "step": 172680 }, { "epoch": 1.0265052219864352, "grad_norm": 3.9882869720458984, "learning_rate": 9.66602736096024e-06, "loss": 0.3874, "step": 172690 }, { "epoch": 1.0265646640631036, "grad_norm": 3.9139950275421143, "learning_rate": 9.665952796054221e-06, "loss": 0.3701, "step": 172700 }, { "epoch": 1.026624106139772, "grad_norm": 4.047298908233643, "learning_rate": 9.665878223112873e-06, "loss": 0.3917, "step": 172710 }, { "epoch": 1.0266835482164405, "grad_norm": 4.650284767150879, "learning_rate": 9.665803642136326e-06, "loss": 0.4229, "step": 172720 }, { "epoch": 1.026742990293109, "grad_norm": 4.720593452453613, "learning_rate": 9.665729053124708e-06, "loss": 0.3569, "step": 172730 }, { "epoch": 1.0268024323697773, "grad_norm": 5.439952373504639, "learning_rate": 9.665654456078149e-06, "loss": 0.4097, "step": 172740 }, { "epoch": 1.0268618744464457, "grad_norm": 3.751450538635254, "learning_rate": 9.665579850996775e-06, "loss": 0.4012, "step": 172750 }, { "epoch": 1.0269213165231141, "grad_norm": 5.1335649490356445, "learning_rate": 9.665505237880717e-06, "loss": 0.4118, "step": 172760 }, { "epoch": 1.0269807585997826, "grad_norm": 4.8868021965026855, "learning_rate": 9.6654306167301e-06, "loss": 0.4296, "step": 172770 }, { "epoch": 1.0270402006764507, "grad_norm": 4.774100303649902, "learning_rate": 9.665355987545057e-06, "loss": 0.4141, "step": 172780 }, { "epoch": 1.0270996427531192, "grad_norm": 5.486328125, "learning_rate": 9.665281350325715e-06, "loss": 0.3934, "step": 172790 }, { "epoch": 1.0271590848297876, "grad_norm": 4.994626522064209, "learning_rate": 9.6652067050722e-06, "loss": 0.4056, "step": 172800 }, { "epoch": 1.027218526906456, "grad_norm": 5.643640995025635, "learning_rate": 9.665132051784644e-06, "loss": 0.3641, "step": 172810 }, { "epoch": 1.0272779689831244, "grad_norm": 4.758264541625977, "learning_rate": 9.665057390463174e-06, "loss": 0.4286, "step": 172820 }, { "epoch": 1.0273374110597928, "grad_norm": 5.1144843101501465, "learning_rate": 9.664982721107915e-06, "loss": 0.4294, "step": 172830 }, { "epoch": 1.0273968531364612, "grad_norm": 5.777021884918213, "learning_rate": 9.664908043719004e-06, "loss": 0.4179, "step": 172840 }, { "epoch": 1.0274562952131296, "grad_norm": 4.275977611541748, "learning_rate": 9.664833358296561e-06, "loss": 0.3526, "step": 172850 }, { "epoch": 1.027515737289798, "grad_norm": 4.738951206207275, "learning_rate": 9.66475866484072e-06, "loss": 0.3988, "step": 172860 }, { "epoch": 1.0275751793664663, "grad_norm": 5.341110706329346, "learning_rate": 9.664683963351609e-06, "loss": 0.3747, "step": 172870 }, { "epoch": 1.0276346214431347, "grad_norm": 5.171635627746582, "learning_rate": 9.664609253829354e-06, "loss": 0.4299, "step": 172880 }, { "epoch": 1.027694063519803, "grad_norm": 4.36668586730957, "learning_rate": 9.664534536274086e-06, "loss": 0.4287, "step": 172890 }, { "epoch": 1.0277535055964715, "grad_norm": 5.919314861297607, "learning_rate": 9.664459810685933e-06, "loss": 0.4323, "step": 172900 }, { "epoch": 1.02781294767314, "grad_norm": 5.170780658721924, "learning_rate": 9.664385077065023e-06, "loss": 0.4178, "step": 172910 }, { "epoch": 1.0278723897498083, "grad_norm": 4.899355888366699, "learning_rate": 9.664310335411487e-06, "loss": 0.3836, "step": 172920 }, { "epoch": 1.0279318318264767, "grad_norm": 4.293219089508057, "learning_rate": 9.66423558572545e-06, "loss": 0.4223, "step": 172930 }, { "epoch": 1.0279912739031452, "grad_norm": 5.821152687072754, "learning_rate": 9.664160828007044e-06, "loss": 0.41, "step": 172940 }, { "epoch": 1.0280507159798136, "grad_norm": 5.74014949798584, "learning_rate": 9.664086062256398e-06, "loss": 0.404, "step": 172950 }, { "epoch": 1.0281101580564818, "grad_norm": 3.8471596240997314, "learning_rate": 9.664011288473636e-06, "loss": 0.4297, "step": 172960 }, { "epoch": 1.0281696001331502, "grad_norm": 4.324548721313477, "learning_rate": 9.663936506658893e-06, "loss": 0.3925, "step": 172970 }, { "epoch": 1.0282290422098186, "grad_norm": 5.148831844329834, "learning_rate": 9.663861716812293e-06, "loss": 0.4155, "step": 172980 }, { "epoch": 1.028288484286487, "grad_norm": 4.946537494659424, "learning_rate": 9.663786918933966e-06, "loss": 0.3778, "step": 172990 }, { "epoch": 1.0283479263631554, "grad_norm": 4.622663974761963, "learning_rate": 9.663712113024043e-06, "loss": 0.4252, "step": 173000 }, { "epoch": 1.0284073684398238, "grad_norm": 4.978462219238281, "learning_rate": 9.663637299082651e-06, "loss": 0.3554, "step": 173010 }, { "epoch": 1.0284668105164922, "grad_norm": 3.9025356769561768, "learning_rate": 9.663562477109918e-06, "loss": 0.4578, "step": 173020 }, { "epoch": 1.0285262525931607, "grad_norm": 6.0295915603637695, "learning_rate": 9.663487647105976e-06, "loss": 0.4056, "step": 173030 }, { "epoch": 1.028585694669829, "grad_norm": 6.6264424324035645, "learning_rate": 9.66341280907095e-06, "loss": 0.4015, "step": 173040 }, { "epoch": 1.0286451367464973, "grad_norm": 4.578053951263428, "learning_rate": 9.663337963004972e-06, "loss": 0.4119, "step": 173050 }, { "epoch": 1.0287045788231657, "grad_norm": 4.604589462280273, "learning_rate": 9.663263108908169e-06, "loss": 0.3753, "step": 173060 }, { "epoch": 1.028764020899834, "grad_norm": 5.077905178070068, "learning_rate": 9.66318824678067e-06, "loss": 0.3884, "step": 173070 }, { "epoch": 1.0288234629765025, "grad_norm": 5.783527374267578, "learning_rate": 9.663113376622607e-06, "loss": 0.3702, "step": 173080 }, { "epoch": 1.028882905053171, "grad_norm": 4.528611660003662, "learning_rate": 9.663038498434103e-06, "loss": 0.408, "step": 173090 }, { "epoch": 1.0289423471298393, "grad_norm": 4.681026458740234, "learning_rate": 9.66296361221529e-06, "loss": 0.4031, "step": 173100 }, { "epoch": 1.0290017892065078, "grad_norm": 4.907915115356445, "learning_rate": 9.6628887179663e-06, "loss": 0.3671, "step": 173110 }, { "epoch": 1.0290612312831762, "grad_norm": 4.810238361358643, "learning_rate": 9.662813815687259e-06, "loss": 0.4107, "step": 173120 }, { "epoch": 1.0291206733598446, "grad_norm": 5.858509540557861, "learning_rate": 9.662738905378295e-06, "loss": 0.4253, "step": 173130 }, { "epoch": 1.029180115436513, "grad_norm": 6.9310221672058105, "learning_rate": 9.662663987039538e-06, "loss": 0.4333, "step": 173140 }, { "epoch": 1.0292395575131812, "grad_norm": 6.726579666137695, "learning_rate": 9.66258906067112e-06, "loss": 0.4289, "step": 173150 }, { "epoch": 1.0292989995898496, "grad_norm": 6.908520698547363, "learning_rate": 9.662514126273164e-06, "loss": 0.4329, "step": 173160 }, { "epoch": 1.029358441666518, "grad_norm": 5.050114154815674, "learning_rate": 9.662439183845803e-06, "loss": 0.4163, "step": 173170 }, { "epoch": 1.0294178837431864, "grad_norm": 4.06589412689209, "learning_rate": 9.662364233389167e-06, "loss": 0.3777, "step": 173180 }, { "epoch": 1.0294773258198548, "grad_norm": 6.343341827392578, "learning_rate": 9.662289274903383e-06, "loss": 0.4205, "step": 173190 }, { "epoch": 1.0295367678965233, "grad_norm": 6.12291955947876, "learning_rate": 9.662214308388579e-06, "loss": 0.3921, "step": 173200 }, { "epoch": 1.0295962099731917, "grad_norm": 5.065810680389404, "learning_rate": 9.662139333844887e-06, "loss": 0.3878, "step": 173210 }, { "epoch": 1.02965565204986, "grad_norm": 5.971559524536133, "learning_rate": 9.662064351272436e-06, "loss": 0.4101, "step": 173220 }, { "epoch": 1.0297150941265285, "grad_norm": 5.284296035766602, "learning_rate": 9.661989360671352e-06, "loss": 0.4248, "step": 173230 }, { "epoch": 1.0297745362031967, "grad_norm": 5.319111347198486, "learning_rate": 9.661914362041766e-06, "loss": 0.4007, "step": 173240 }, { "epoch": 1.0298339782798651, "grad_norm": 5.908157825469971, "learning_rate": 9.66183935538381e-06, "loss": 0.377, "step": 173250 }, { "epoch": 1.0298934203565335, "grad_norm": 4.638279438018799, "learning_rate": 9.661764340697606e-06, "loss": 0.4163, "step": 173260 }, { "epoch": 1.029952862433202, "grad_norm": 6.381346702575684, "learning_rate": 9.66168931798329e-06, "loss": 0.3858, "step": 173270 }, { "epoch": 1.0300123045098704, "grad_norm": 4.842617034912109, "learning_rate": 9.661614287240987e-06, "loss": 0.3914, "step": 173280 }, { "epoch": 1.0300717465865388, "grad_norm": 6.146137714385986, "learning_rate": 9.66153924847083e-06, "loss": 0.432, "step": 173290 }, { "epoch": 1.0301311886632072, "grad_norm": 5.17877721786499, "learning_rate": 9.661464201672946e-06, "loss": 0.3762, "step": 173300 }, { "epoch": 1.0301906307398756, "grad_norm": 5.361102104187012, "learning_rate": 9.661389146847465e-06, "loss": 0.4276, "step": 173310 }, { "epoch": 1.030250072816544, "grad_norm": 3.951962947845459, "learning_rate": 9.661314083994515e-06, "loss": 0.4163, "step": 173320 }, { "epoch": 1.0303095148932122, "grad_norm": 4.17221736907959, "learning_rate": 9.661239013114225e-06, "loss": 0.393, "step": 173330 }, { "epoch": 1.0303689569698806, "grad_norm": 5.773423671722412, "learning_rate": 9.661163934206726e-06, "loss": 0.3828, "step": 173340 }, { "epoch": 1.030428399046549, "grad_norm": 6.581651210784912, "learning_rate": 9.661088847272146e-06, "loss": 0.4348, "step": 173350 }, { "epoch": 1.0304878411232175, "grad_norm": 5.4572343826293945, "learning_rate": 9.661013752310617e-06, "loss": 0.4448, "step": 173360 }, { "epoch": 1.0305472831998859, "grad_norm": 5.841696262359619, "learning_rate": 9.660938649322264e-06, "loss": 0.4583, "step": 173370 }, { "epoch": 1.0306067252765543, "grad_norm": 5.093456745147705, "learning_rate": 9.660863538307219e-06, "loss": 0.3875, "step": 173380 }, { "epoch": 1.0306661673532227, "grad_norm": 5.54188871383667, "learning_rate": 9.660788419265611e-06, "loss": 0.4528, "step": 173390 }, { "epoch": 1.030725609429891, "grad_norm": 4.3229660987854, "learning_rate": 9.66071329219757e-06, "loss": 0.3957, "step": 173400 }, { "epoch": 1.0307850515065595, "grad_norm": 4.632140159606934, "learning_rate": 9.660638157103223e-06, "loss": 0.4455, "step": 173410 }, { "epoch": 1.0308444935832277, "grad_norm": 5.586287021636963, "learning_rate": 9.660563013982702e-06, "loss": 0.496, "step": 173420 }, { "epoch": 1.0309039356598961, "grad_norm": 6.001609802246094, "learning_rate": 9.660487862836137e-06, "loss": 0.4116, "step": 173430 }, { "epoch": 1.0309633777365645, "grad_norm": 4.608117580413818, "learning_rate": 9.660412703663654e-06, "loss": 0.4385, "step": 173440 }, { "epoch": 1.031022819813233, "grad_norm": 5.758316516876221, "learning_rate": 9.660337536465382e-06, "loss": 0.4187, "step": 173450 }, { "epoch": 1.0310822618899014, "grad_norm": 4.31508731842041, "learning_rate": 9.660262361241457e-06, "loss": 0.4201, "step": 173460 }, { "epoch": 1.0311417039665698, "grad_norm": 5.560993671417236, "learning_rate": 9.660187177992002e-06, "loss": 0.3758, "step": 173470 }, { "epoch": 1.0312011460432382, "grad_norm": 5.6931538581848145, "learning_rate": 9.660111986717148e-06, "loss": 0.422, "step": 173480 }, { "epoch": 1.0312605881199066, "grad_norm": 5.605100154876709, "learning_rate": 9.660036787417026e-06, "loss": 0.4068, "step": 173490 }, { "epoch": 1.031320030196575, "grad_norm": 5.037858486175537, "learning_rate": 9.659961580091765e-06, "loss": 0.4387, "step": 173500 }, { "epoch": 1.0313794722732434, "grad_norm": 4.531060218811035, "learning_rate": 9.659886364741493e-06, "loss": 0.4038, "step": 173510 }, { "epoch": 1.0314389143499116, "grad_norm": 5.457247734069824, "learning_rate": 9.659811141366342e-06, "loss": 0.4094, "step": 173520 }, { "epoch": 1.03149835642658, "grad_norm": 5.392673969268799, "learning_rate": 9.659735909966439e-06, "loss": 0.4022, "step": 173530 }, { "epoch": 1.0315577985032485, "grad_norm": 4.389680862426758, "learning_rate": 9.659660670541915e-06, "loss": 0.3744, "step": 173540 }, { "epoch": 1.0316172405799169, "grad_norm": 3.734768867492676, "learning_rate": 9.659585423092902e-06, "loss": 0.3778, "step": 173550 }, { "epoch": 1.0316766826565853, "grad_norm": 4.608076095581055, "learning_rate": 9.659510167619523e-06, "loss": 0.4141, "step": 173560 }, { "epoch": 1.0317361247332537, "grad_norm": 6.956697940826416, "learning_rate": 9.659434904121913e-06, "loss": 0.4813, "step": 173570 }, { "epoch": 1.0317955668099221, "grad_norm": 6.516623020172119, "learning_rate": 9.659359632600201e-06, "loss": 0.4282, "step": 173580 }, { "epoch": 1.0318550088865905, "grad_norm": 4.557794094085693, "learning_rate": 9.659284353054514e-06, "loss": 0.4228, "step": 173590 }, { "epoch": 1.031914450963259, "grad_norm": 4.799242973327637, "learning_rate": 9.659209065484986e-06, "loss": 0.3943, "step": 173600 }, { "epoch": 1.0319738930399271, "grad_norm": 6.607781887054443, "learning_rate": 9.659133769891741e-06, "loss": 0.4634, "step": 173610 }, { "epoch": 1.0320333351165956, "grad_norm": 5.342343807220459, "learning_rate": 9.659058466274914e-06, "loss": 0.414, "step": 173620 }, { "epoch": 1.032092777193264, "grad_norm": 6.067237377166748, "learning_rate": 9.658983154634632e-06, "loss": 0.4228, "step": 173630 }, { "epoch": 1.0321522192699324, "grad_norm": 6.772129058837891, "learning_rate": 9.658907834971026e-06, "loss": 0.4447, "step": 173640 }, { "epoch": 1.0322116613466008, "grad_norm": 3.9085445404052734, "learning_rate": 9.658832507284223e-06, "loss": 0.3978, "step": 173650 }, { "epoch": 1.0322711034232692, "grad_norm": 5.328970432281494, "learning_rate": 9.658757171574354e-06, "loss": 0.4049, "step": 173660 }, { "epoch": 1.0323305454999376, "grad_norm": 4.746908664703369, "learning_rate": 9.658681827841552e-06, "loss": 0.3809, "step": 173670 }, { "epoch": 1.032389987576606, "grad_norm": 5.30259370803833, "learning_rate": 9.658606476085941e-06, "loss": 0.3877, "step": 173680 }, { "epoch": 1.0324494296532745, "grad_norm": 6.550839424133301, "learning_rate": 9.658531116307655e-06, "loss": 0.4319, "step": 173690 }, { "epoch": 1.0325088717299427, "grad_norm": 5.601734161376953, "learning_rate": 9.658455748506823e-06, "loss": 0.4243, "step": 173700 }, { "epoch": 1.032568313806611, "grad_norm": 4.672752857208252, "learning_rate": 9.658380372683576e-06, "loss": 0.4043, "step": 173710 }, { "epoch": 1.0326277558832795, "grad_norm": 4.684675216674805, "learning_rate": 9.65830498883804e-06, "loss": 0.4345, "step": 173720 }, { "epoch": 1.032687197959948, "grad_norm": 4.674333572387695, "learning_rate": 9.658229596970347e-06, "loss": 0.3933, "step": 173730 }, { "epoch": 1.0327466400366163, "grad_norm": 5.758159160614014, "learning_rate": 9.658154197080627e-06, "loss": 0.4, "step": 173740 }, { "epoch": 1.0328060821132847, "grad_norm": 4.930288314819336, "learning_rate": 9.65807878916901e-06, "loss": 0.3719, "step": 173750 }, { "epoch": 1.0328655241899531, "grad_norm": 6.12103796005249, "learning_rate": 9.658003373235625e-06, "loss": 0.4388, "step": 173760 }, { "epoch": 1.0329249662666216, "grad_norm": 4.973592281341553, "learning_rate": 9.657927949280603e-06, "loss": 0.4461, "step": 173770 }, { "epoch": 1.03298440834329, "grad_norm": 6.655965328216553, "learning_rate": 9.657852517304073e-06, "loss": 0.4291, "step": 173780 }, { "epoch": 1.0330438504199582, "grad_norm": 4.714688777923584, "learning_rate": 9.657777077306166e-06, "loss": 0.429, "step": 173790 }, { "epoch": 1.0331032924966266, "grad_norm": 5.967186450958252, "learning_rate": 9.65770162928701e-06, "loss": 0.3805, "step": 173800 }, { "epoch": 1.033162734573295, "grad_norm": 4.892575740814209, "learning_rate": 9.657626173246735e-06, "loss": 0.4268, "step": 173810 }, { "epoch": 1.0332221766499634, "grad_norm": 4.863521099090576, "learning_rate": 9.657550709185474e-06, "loss": 0.3596, "step": 173820 }, { "epoch": 1.0332816187266318, "grad_norm": 5.122528076171875, "learning_rate": 9.657475237103355e-06, "loss": 0.3768, "step": 173830 }, { "epoch": 1.0333410608033002, "grad_norm": 7.21622371673584, "learning_rate": 9.657399757000508e-06, "loss": 0.4176, "step": 173840 }, { "epoch": 1.0334005028799687, "grad_norm": 5.470756530761719, "learning_rate": 9.657324268877062e-06, "loss": 0.3929, "step": 173850 }, { "epoch": 1.033459944956637, "grad_norm": 6.43394136428833, "learning_rate": 9.657248772733148e-06, "loss": 0.3935, "step": 173860 }, { "epoch": 1.0335193870333055, "grad_norm": 4.688598155975342, "learning_rate": 9.657173268568895e-06, "loss": 0.4058, "step": 173870 }, { "epoch": 1.033578829109974, "grad_norm": 5.9571075439453125, "learning_rate": 9.657097756384435e-06, "loss": 0.3873, "step": 173880 }, { "epoch": 1.033638271186642, "grad_norm": 6.1472578048706055, "learning_rate": 9.657022236179899e-06, "loss": 0.4053, "step": 173890 }, { "epoch": 1.0336977132633105, "grad_norm": 4.367921829223633, "learning_rate": 9.65694670795541e-06, "loss": 0.3832, "step": 173900 }, { "epoch": 1.033757155339979, "grad_norm": 4.800048351287842, "learning_rate": 9.656871171711108e-06, "loss": 0.366, "step": 173910 }, { "epoch": 1.0338165974166473, "grad_norm": 4.319480895996094, "learning_rate": 9.656795627447115e-06, "loss": 0.3658, "step": 173920 }, { "epoch": 1.0338760394933157, "grad_norm": 5.657207489013672, "learning_rate": 9.656720075163566e-06, "loss": 0.3817, "step": 173930 }, { "epoch": 1.0339354815699842, "grad_norm": 6.538637161254883, "learning_rate": 9.656644514860588e-06, "loss": 0.421, "step": 173940 }, { "epoch": 1.0339949236466526, "grad_norm": 5.612523078918457, "learning_rate": 9.656568946538315e-06, "loss": 0.3865, "step": 173950 }, { "epoch": 1.034054365723321, "grad_norm": 6.237726211547852, "learning_rate": 9.656493370196873e-06, "loss": 0.4289, "step": 173960 }, { "epoch": 1.0341138077999894, "grad_norm": 4.683643817901611, "learning_rate": 9.656417785836393e-06, "loss": 0.4042, "step": 173970 }, { "epoch": 1.0341732498766576, "grad_norm": 5.407331943511963, "learning_rate": 9.656342193457008e-06, "loss": 0.3874, "step": 173980 }, { "epoch": 1.034232691953326, "grad_norm": 5.305732250213623, "learning_rate": 9.656266593058846e-06, "loss": 0.3765, "step": 173990 }, { "epoch": 1.0342921340299944, "grad_norm": 4.3449201583862305, "learning_rate": 9.656190984642035e-06, "loss": 0.4292, "step": 174000 }, { "epoch": 1.0343515761066628, "grad_norm": 4.207218647003174, "learning_rate": 9.65611536820671e-06, "loss": 0.4434, "step": 174010 }, { "epoch": 1.0344110181833313, "grad_norm": 5.996621608734131, "learning_rate": 9.656039743752999e-06, "loss": 0.4276, "step": 174020 }, { "epoch": 1.0344704602599997, "grad_norm": 5.6556572914123535, "learning_rate": 9.65596411128103e-06, "loss": 0.3741, "step": 174030 }, { "epoch": 1.034529902336668, "grad_norm": 5.674482822418213, "learning_rate": 9.655888470790935e-06, "loss": 0.4179, "step": 174040 }, { "epoch": 1.0345893444133365, "grad_norm": 5.166575908660889, "learning_rate": 9.655812822282846e-06, "loss": 0.4077, "step": 174050 }, { "epoch": 1.034648786490005, "grad_norm": 5.61142635345459, "learning_rate": 9.655737165756891e-06, "loss": 0.4352, "step": 174060 }, { "epoch": 1.034708228566673, "grad_norm": 5.184642791748047, "learning_rate": 9.655661501213203e-06, "loss": 0.3853, "step": 174070 }, { "epoch": 1.0347676706433415, "grad_norm": 3.3373007774353027, "learning_rate": 9.655585828651907e-06, "loss": 0.3997, "step": 174080 }, { "epoch": 1.03482711272001, "grad_norm": 4.99709415435791, "learning_rate": 9.65551014807314e-06, "loss": 0.4018, "step": 174090 }, { "epoch": 1.0348865547966783, "grad_norm": 6.112037658691406, "learning_rate": 9.655434459477027e-06, "loss": 0.4172, "step": 174100 }, { "epoch": 1.0349459968733468, "grad_norm": 3.4373176097869873, "learning_rate": 9.655358762863701e-06, "loss": 0.3606, "step": 174110 }, { "epoch": 1.0350054389500152, "grad_norm": 5.722005367279053, "learning_rate": 9.655283058233292e-06, "loss": 0.3948, "step": 174120 }, { "epoch": 1.0350648810266836, "grad_norm": 4.708670616149902, "learning_rate": 9.65520734558593e-06, "loss": 0.3974, "step": 174130 }, { "epoch": 1.035124323103352, "grad_norm": 4.465758323669434, "learning_rate": 9.655131624921745e-06, "loss": 0.402, "step": 174140 }, { "epoch": 1.0351837651800204, "grad_norm": 5.650317192077637, "learning_rate": 9.655055896240868e-06, "loss": 0.434, "step": 174150 }, { "epoch": 1.0352432072566886, "grad_norm": 4.20374870300293, "learning_rate": 9.65498015954343e-06, "loss": 0.4066, "step": 174160 }, { "epoch": 1.035302649333357, "grad_norm": 4.760581016540527, "learning_rate": 9.65490441482956e-06, "loss": 0.413, "step": 174170 }, { "epoch": 1.0353620914100254, "grad_norm": 5.332352638244629, "learning_rate": 9.654828662099391e-06, "loss": 0.3759, "step": 174180 }, { "epoch": 1.0354215334866939, "grad_norm": 5.882589817047119, "learning_rate": 9.65475290135305e-06, "loss": 0.4618, "step": 174190 }, { "epoch": 1.0354809755633623, "grad_norm": 5.443942070007324, "learning_rate": 9.654677132590668e-06, "loss": 0.4285, "step": 174200 }, { "epoch": 1.0355404176400307, "grad_norm": 4.5425872802734375, "learning_rate": 9.654601355812378e-06, "loss": 0.407, "step": 174210 }, { "epoch": 1.035599859716699, "grad_norm": 5.661268711090088, "learning_rate": 9.654525571018309e-06, "loss": 0.4098, "step": 174220 }, { "epoch": 1.0356593017933675, "grad_norm": 4.729262828826904, "learning_rate": 9.654449778208592e-06, "loss": 0.4482, "step": 174230 }, { "epoch": 1.035718743870036, "grad_norm": 5.308086395263672, "learning_rate": 9.654373977383357e-06, "loss": 0.4455, "step": 174240 }, { "epoch": 1.0357781859467043, "grad_norm": 4.398159503936768, "learning_rate": 9.654298168542734e-06, "loss": 0.3895, "step": 174250 }, { "epoch": 1.0358376280233725, "grad_norm": 5.6722092628479, "learning_rate": 9.654222351686855e-06, "loss": 0.4353, "step": 174260 }, { "epoch": 1.035897070100041, "grad_norm": 5.221963405609131, "learning_rate": 9.654146526815849e-06, "loss": 0.3988, "step": 174270 }, { "epoch": 1.0359565121767094, "grad_norm": 4.506019592285156, "learning_rate": 9.654070693929847e-06, "loss": 0.4013, "step": 174280 }, { "epoch": 1.0360159542533778, "grad_norm": 4.562057018280029, "learning_rate": 9.653994853028981e-06, "loss": 0.491, "step": 174290 }, { "epoch": 1.0360753963300462, "grad_norm": 5.456050872802734, "learning_rate": 9.65391900411338e-06, "loss": 0.421, "step": 174300 }, { "epoch": 1.0361348384067146, "grad_norm": 4.633456707000732, "learning_rate": 9.653843147183176e-06, "loss": 0.4344, "step": 174310 }, { "epoch": 1.036194280483383, "grad_norm": 6.270715713500977, "learning_rate": 9.653767282238497e-06, "loss": 0.4135, "step": 174320 }, { "epoch": 1.0362537225600514, "grad_norm": 5.591797828674316, "learning_rate": 9.653691409279477e-06, "loss": 0.42, "step": 174330 }, { "epoch": 1.0363131646367199, "grad_norm": 4.297194957733154, "learning_rate": 9.653615528306245e-06, "loss": 0.4211, "step": 174340 }, { "epoch": 1.036372606713388, "grad_norm": 5.867982387542725, "learning_rate": 9.653539639318932e-06, "loss": 0.397, "step": 174350 }, { "epoch": 1.0364320487900565, "grad_norm": 4.76797342300415, "learning_rate": 9.653463742317668e-06, "loss": 0.3744, "step": 174360 }, { "epoch": 1.0364914908667249, "grad_norm": 5.666780948638916, "learning_rate": 9.653387837302584e-06, "loss": 0.3997, "step": 174370 }, { "epoch": 1.0365509329433933, "grad_norm": 5.546473979949951, "learning_rate": 9.653311924273812e-06, "loss": 0.3965, "step": 174380 }, { "epoch": 1.0366103750200617, "grad_norm": 5.0721821784973145, "learning_rate": 9.65323600323148e-06, "loss": 0.4165, "step": 174390 }, { "epoch": 1.0366698170967301, "grad_norm": 3.84039044380188, "learning_rate": 9.653160074175722e-06, "loss": 0.3848, "step": 174400 }, { "epoch": 1.0367292591733985, "grad_norm": 4.0081939697265625, "learning_rate": 9.653084137106665e-06, "loss": 0.4113, "step": 174410 }, { "epoch": 1.036788701250067, "grad_norm": 4.266932010650635, "learning_rate": 9.653008192024445e-06, "loss": 0.4305, "step": 174420 }, { "epoch": 1.0368481433267354, "grad_norm": 5.4267473220825195, "learning_rate": 9.652932238929186e-06, "loss": 0.4089, "step": 174430 }, { "epoch": 1.0369075854034036, "grad_norm": 5.324921131134033, "learning_rate": 9.652856277821025e-06, "loss": 0.3999, "step": 174440 }, { "epoch": 1.036967027480072, "grad_norm": 4.74969482421875, "learning_rate": 9.652780308700089e-06, "loss": 0.3822, "step": 174450 }, { "epoch": 1.0370264695567404, "grad_norm": 5.676809310913086, "learning_rate": 9.652704331566511e-06, "loss": 0.4096, "step": 174460 }, { "epoch": 1.0370859116334088, "grad_norm": 4.463996410369873, "learning_rate": 9.652628346420422e-06, "loss": 0.4294, "step": 174470 }, { "epoch": 1.0371453537100772, "grad_norm": 4.504054069519043, "learning_rate": 9.65255235326195e-06, "loss": 0.3617, "step": 174480 }, { "epoch": 1.0372047957867456, "grad_norm": 5.349234580993652, "learning_rate": 9.652476352091229e-06, "loss": 0.4378, "step": 174490 }, { "epoch": 1.037264237863414, "grad_norm": 5.7816667556762695, "learning_rate": 9.652400342908388e-06, "loss": 0.4094, "step": 174500 }, { "epoch": 1.0373236799400825, "grad_norm": 4.046713829040527, "learning_rate": 9.652324325713558e-06, "loss": 0.4146, "step": 174510 }, { "epoch": 1.0373831220167509, "grad_norm": 6.536448001861572, "learning_rate": 9.652248300506873e-06, "loss": 0.3794, "step": 174520 }, { "epoch": 1.037442564093419, "grad_norm": 6.249169826507568, "learning_rate": 9.652172267288457e-06, "loss": 0.3389, "step": 174530 }, { "epoch": 1.0375020061700875, "grad_norm": 4.420853614807129, "learning_rate": 9.652096226058448e-06, "loss": 0.3869, "step": 174540 }, { "epoch": 1.037561448246756, "grad_norm": 5.120662689208984, "learning_rate": 9.652020176816974e-06, "loss": 0.3964, "step": 174550 }, { "epoch": 1.0376208903234243, "grad_norm": 5.071247577667236, "learning_rate": 9.651944119564166e-06, "loss": 0.393, "step": 174560 }, { "epoch": 1.0376803324000927, "grad_norm": 6.419013023376465, "learning_rate": 9.651868054300156e-06, "loss": 0.4164, "step": 174570 }, { "epoch": 1.0377397744767611, "grad_norm": 5.359957695007324, "learning_rate": 9.651791981025072e-06, "loss": 0.3904, "step": 174580 }, { "epoch": 1.0377992165534295, "grad_norm": 5.663415431976318, "learning_rate": 9.65171589973905e-06, "loss": 0.4514, "step": 174590 }, { "epoch": 1.037858658630098, "grad_norm": 4.226360321044922, "learning_rate": 9.651639810442216e-06, "loss": 0.401, "step": 174600 }, { "epoch": 1.0379181007067664, "grad_norm": 6.156988143920898, "learning_rate": 9.651563713134704e-06, "loss": 0.3762, "step": 174610 }, { "epoch": 1.0379775427834348, "grad_norm": 4.960148811340332, "learning_rate": 9.651487607816643e-06, "loss": 0.4204, "step": 174620 }, { "epoch": 1.038036984860103, "grad_norm": 5.659156799316406, "learning_rate": 9.651411494488167e-06, "loss": 0.4586, "step": 174630 }, { "epoch": 1.0380964269367714, "grad_norm": 5.773348808288574, "learning_rate": 9.651335373149405e-06, "loss": 0.3808, "step": 174640 }, { "epoch": 1.0381558690134398, "grad_norm": 5.132542133331299, "learning_rate": 9.651259243800488e-06, "loss": 0.3749, "step": 174650 }, { "epoch": 1.0382153110901082, "grad_norm": 4.4360480308532715, "learning_rate": 9.651183106441548e-06, "loss": 0.4052, "step": 174660 }, { "epoch": 1.0382747531667766, "grad_norm": 5.611371994018555, "learning_rate": 9.651106961072716e-06, "loss": 0.4126, "step": 174670 }, { "epoch": 1.038334195243445, "grad_norm": 4.481133460998535, "learning_rate": 9.651030807694123e-06, "loss": 0.3976, "step": 174680 }, { "epoch": 1.0383936373201135, "grad_norm": 5.4355998039245605, "learning_rate": 9.650954646305899e-06, "loss": 0.4071, "step": 174690 }, { "epoch": 1.0384530793967819, "grad_norm": 4.864652633666992, "learning_rate": 9.650878476908177e-06, "loss": 0.3827, "step": 174700 }, { "epoch": 1.0385125214734503, "grad_norm": 4.831679344177246, "learning_rate": 9.650802299501087e-06, "loss": 0.427, "step": 174710 }, { "epoch": 1.0385719635501185, "grad_norm": 5.653244495391846, "learning_rate": 9.65072611408476e-06, "loss": 0.3696, "step": 174720 }, { "epoch": 1.038631405626787, "grad_norm": 6.45433235168457, "learning_rate": 9.650649920659329e-06, "loss": 0.4403, "step": 174730 }, { "epoch": 1.0386908477034553, "grad_norm": 6.278619766235352, "learning_rate": 9.650573719224923e-06, "loss": 0.4604, "step": 174740 }, { "epoch": 1.0387502897801237, "grad_norm": 5.14678955078125, "learning_rate": 9.650497509781674e-06, "loss": 0.4238, "step": 174750 }, { "epoch": 1.0388097318567922, "grad_norm": 4.746161460876465, "learning_rate": 9.650421292329714e-06, "loss": 0.379, "step": 174760 }, { "epoch": 1.0388691739334606, "grad_norm": 5.941311359405518, "learning_rate": 9.650345066869173e-06, "loss": 0.3985, "step": 174770 }, { "epoch": 1.038928616010129, "grad_norm": 5.7266716957092285, "learning_rate": 9.650268833400185e-06, "loss": 0.37, "step": 174780 }, { "epoch": 1.0389880580867974, "grad_norm": 5.089620590209961, "learning_rate": 9.650192591922877e-06, "loss": 0.3844, "step": 174790 }, { "epoch": 1.0390475001634658, "grad_norm": 5.663436412811279, "learning_rate": 9.650116342437384e-06, "loss": 0.4046, "step": 174800 }, { "epoch": 1.039106942240134, "grad_norm": 6.298392295837402, "learning_rate": 9.650040084943834e-06, "loss": 0.391, "step": 174810 }, { "epoch": 1.0391663843168024, "grad_norm": 5.309613227844238, "learning_rate": 9.649963819442361e-06, "loss": 0.3806, "step": 174820 }, { "epoch": 1.0392258263934708, "grad_norm": 4.6566901206970215, "learning_rate": 9.649887545933094e-06, "loss": 0.4261, "step": 174830 }, { "epoch": 1.0392852684701392, "grad_norm": 5.748884677886963, "learning_rate": 9.649811264416168e-06, "loss": 0.3784, "step": 174840 }, { "epoch": 1.0393447105468077, "grad_norm": 4.354085445404053, "learning_rate": 9.649734974891712e-06, "loss": 0.3658, "step": 174850 }, { "epoch": 1.039404152623476, "grad_norm": 5.95935583114624, "learning_rate": 9.649658677359856e-06, "loss": 0.3832, "step": 174860 }, { "epoch": 1.0394635947001445, "grad_norm": 4.446649074554443, "learning_rate": 9.649582371820736e-06, "loss": 0.3903, "step": 174870 }, { "epoch": 1.039523036776813, "grad_norm": 4.514657497406006, "learning_rate": 9.649506058274479e-06, "loss": 0.3866, "step": 174880 }, { "epoch": 1.0395824788534813, "grad_norm": 5.824790000915527, "learning_rate": 9.649429736721216e-06, "loss": 0.4247, "step": 174890 }, { "epoch": 1.0396419209301495, "grad_norm": 4.329625129699707, "learning_rate": 9.649353407161081e-06, "loss": 0.421, "step": 174900 }, { "epoch": 1.039701363006818, "grad_norm": 5.2544846534729, "learning_rate": 9.649277069594205e-06, "loss": 0.3845, "step": 174910 }, { "epoch": 1.0397608050834863, "grad_norm": 6.189678192138672, "learning_rate": 9.64920072402072e-06, "loss": 0.4207, "step": 174920 }, { "epoch": 1.0398202471601548, "grad_norm": 6.348321914672852, "learning_rate": 9.649124370440755e-06, "loss": 0.3861, "step": 174930 }, { "epoch": 1.0398796892368232, "grad_norm": 6.4552202224731445, "learning_rate": 9.649048008854445e-06, "loss": 0.3982, "step": 174940 }, { "epoch": 1.0399391313134916, "grad_norm": 4.450392246246338, "learning_rate": 9.648971639261917e-06, "loss": 0.3848, "step": 174950 }, { "epoch": 1.03999857339016, "grad_norm": 4.85269021987915, "learning_rate": 9.648895261663309e-06, "loss": 0.3966, "step": 174960 }, { "epoch": 1.0400580154668284, "grad_norm": 4.2137017250061035, "learning_rate": 9.648818876058746e-06, "loss": 0.4404, "step": 174970 }, { "epoch": 1.0401174575434968, "grad_norm": 5.394957065582275, "learning_rate": 9.648742482448362e-06, "loss": 0.402, "step": 174980 }, { "epoch": 1.0401768996201652, "grad_norm": 4.412867069244385, "learning_rate": 9.64866608083229e-06, "loss": 0.4259, "step": 174990 }, { "epoch": 1.0402363416968334, "grad_norm": 5.824177265167236, "learning_rate": 9.64858967121066e-06, "loss": 0.4046, "step": 175000 }, { "epoch": 1.0402957837735018, "grad_norm": 5.493598461151123, "learning_rate": 9.648513253583602e-06, "loss": 0.405, "step": 175010 }, { "epoch": 1.0403552258501703, "grad_norm": 6.54581880569458, "learning_rate": 9.648436827951252e-06, "loss": 0.4411, "step": 175020 }, { "epoch": 1.0404146679268387, "grad_norm": 4.863463401794434, "learning_rate": 9.648360394313738e-06, "loss": 0.3889, "step": 175030 }, { "epoch": 1.040474110003507, "grad_norm": 3.3262267112731934, "learning_rate": 9.648283952671194e-06, "loss": 0.3803, "step": 175040 }, { "epoch": 1.0405335520801755, "grad_norm": 5.370612144470215, "learning_rate": 9.648207503023749e-06, "loss": 0.3471, "step": 175050 }, { "epoch": 1.040592994156844, "grad_norm": 4.23317289352417, "learning_rate": 9.648131045371536e-06, "loss": 0.4045, "step": 175060 }, { "epoch": 1.0406524362335123, "grad_norm": 4.81228494644165, "learning_rate": 9.648054579714688e-06, "loss": 0.4376, "step": 175070 }, { "epoch": 1.0407118783101807, "grad_norm": 5.830073833465576, "learning_rate": 9.647978106053336e-06, "loss": 0.4143, "step": 175080 }, { "epoch": 1.040771320386849, "grad_norm": 5.45711088180542, "learning_rate": 9.647901624387609e-06, "loss": 0.4125, "step": 175090 }, { "epoch": 1.0408307624635174, "grad_norm": 5.305629253387451, "learning_rate": 9.64782513471764e-06, "loss": 0.4, "step": 175100 }, { "epoch": 1.0408902045401858, "grad_norm": 6.17527437210083, "learning_rate": 9.647748637043563e-06, "loss": 0.4159, "step": 175110 }, { "epoch": 1.0409496466168542, "grad_norm": 7.591385364532471, "learning_rate": 9.647672131365509e-06, "loss": 0.4248, "step": 175120 }, { "epoch": 1.0410090886935226, "grad_norm": 4.878418922424316, "learning_rate": 9.64759561768361e-06, "loss": 0.3952, "step": 175130 }, { "epoch": 1.041068530770191, "grad_norm": 7.076300621032715, "learning_rate": 9.647519095997995e-06, "loss": 0.4338, "step": 175140 }, { "epoch": 1.0411279728468594, "grad_norm": 5.637385368347168, "learning_rate": 9.647442566308798e-06, "loss": 0.4335, "step": 175150 }, { "epoch": 1.0411874149235278, "grad_norm": 5.336765289306641, "learning_rate": 9.64736602861615e-06, "loss": 0.4176, "step": 175160 }, { "epoch": 1.0412468570001963, "grad_norm": 5.332683086395264, "learning_rate": 9.647289482920183e-06, "loss": 0.4101, "step": 175170 }, { "epoch": 1.0413062990768645, "grad_norm": 3.746764898300171, "learning_rate": 9.647212929221031e-06, "loss": 0.4327, "step": 175180 }, { "epoch": 1.0413657411535329, "grad_norm": 4.726525783538818, "learning_rate": 9.647136367518822e-06, "loss": 0.3828, "step": 175190 }, { "epoch": 1.0414251832302013, "grad_norm": 3.83503794670105, "learning_rate": 9.64705979781369e-06, "loss": 0.429, "step": 175200 }, { "epoch": 1.0414846253068697, "grad_norm": 6.804989337921143, "learning_rate": 9.646983220105766e-06, "loss": 0.4122, "step": 175210 }, { "epoch": 1.041544067383538, "grad_norm": 6.678714275360107, "learning_rate": 9.646906634395184e-06, "loss": 0.3625, "step": 175220 }, { "epoch": 1.0416035094602065, "grad_norm": 5.217545032501221, "learning_rate": 9.646830040682072e-06, "loss": 0.4084, "step": 175230 }, { "epoch": 1.041662951536875, "grad_norm": 4.949061393737793, "learning_rate": 9.646753438966565e-06, "loss": 0.4214, "step": 175240 }, { "epoch": 1.0417223936135434, "grad_norm": 4.914435863494873, "learning_rate": 9.646676829248796e-06, "loss": 0.4081, "step": 175250 }, { "epoch": 1.0417818356902118, "grad_norm": 5.1301140785217285, "learning_rate": 9.646600211528894e-06, "loss": 0.3979, "step": 175260 }, { "epoch": 1.04184127776688, "grad_norm": 4.978178977966309, "learning_rate": 9.646523585806991e-06, "loss": 0.4219, "step": 175270 }, { "epoch": 1.0419007198435484, "grad_norm": 6.14093542098999, "learning_rate": 9.64644695208322e-06, "loss": 0.419, "step": 175280 }, { "epoch": 1.0419601619202168, "grad_norm": 6.1341142654418945, "learning_rate": 9.646370310357713e-06, "loss": 0.4164, "step": 175290 }, { "epoch": 1.0420196039968852, "grad_norm": 5.026437282562256, "learning_rate": 9.646293660630603e-06, "loss": 0.4236, "step": 175300 }, { "epoch": 1.0420790460735536, "grad_norm": 4.108153343200684, "learning_rate": 9.64621700290202e-06, "loss": 0.4082, "step": 175310 }, { "epoch": 1.042138488150222, "grad_norm": 4.835165500640869, "learning_rate": 9.646140337172098e-06, "loss": 0.3883, "step": 175320 }, { "epoch": 1.0421979302268904, "grad_norm": 5.238485336303711, "learning_rate": 9.646063663440968e-06, "loss": 0.4277, "step": 175330 }, { "epoch": 1.0422573723035589, "grad_norm": 5.287414073944092, "learning_rate": 9.645986981708762e-06, "loss": 0.3826, "step": 175340 }, { "epoch": 1.0423168143802273, "grad_norm": 6.954153060913086, "learning_rate": 9.64591029197561e-06, "loss": 0.4361, "step": 175350 }, { "epoch": 1.0423762564568957, "grad_norm": 6.2126264572143555, "learning_rate": 9.64583359424165e-06, "loss": 0.3986, "step": 175360 }, { "epoch": 1.0424356985335639, "grad_norm": 4.0679931640625, "learning_rate": 9.645756888507005e-06, "loss": 0.3817, "step": 175370 }, { "epoch": 1.0424951406102323, "grad_norm": 5.488780975341797, "learning_rate": 9.645680174771817e-06, "loss": 0.427, "step": 175380 }, { "epoch": 1.0425545826869007, "grad_norm": 5.238228797912598, "learning_rate": 9.645603453036212e-06, "loss": 0.4245, "step": 175390 }, { "epoch": 1.0426140247635691, "grad_norm": 5.955862045288086, "learning_rate": 9.645526723300323e-06, "loss": 0.4312, "step": 175400 }, { "epoch": 1.0426734668402375, "grad_norm": 4.486146926879883, "learning_rate": 9.645449985564283e-06, "loss": 0.4177, "step": 175410 }, { "epoch": 1.042732908916906, "grad_norm": 3.9321541786193848, "learning_rate": 9.645373239828223e-06, "loss": 0.4059, "step": 175420 }, { "epoch": 1.0427923509935744, "grad_norm": 5.209376335144043, "learning_rate": 9.645296486092277e-06, "loss": 0.414, "step": 175430 }, { "epoch": 1.0428517930702428, "grad_norm": 5.620382308959961, "learning_rate": 9.645219724356577e-06, "loss": 0.4155, "step": 175440 }, { "epoch": 1.0429112351469112, "grad_norm": 4.992100715637207, "learning_rate": 9.645142954621251e-06, "loss": 0.4418, "step": 175450 }, { "epoch": 1.0429706772235794, "grad_norm": 5.007308483123779, "learning_rate": 9.645066176886438e-06, "loss": 0.4151, "step": 175460 }, { "epoch": 1.0430301193002478, "grad_norm": 5.199126243591309, "learning_rate": 9.644989391152264e-06, "loss": 0.4208, "step": 175470 }, { "epoch": 1.0430895613769162, "grad_norm": 6.491029739379883, "learning_rate": 9.644912597418868e-06, "loss": 0.4588, "step": 175480 }, { "epoch": 1.0431490034535846, "grad_norm": 4.808707237243652, "learning_rate": 9.644835795686374e-06, "loss": 0.4046, "step": 175490 }, { "epoch": 1.043208445530253, "grad_norm": 4.523190975189209, "learning_rate": 9.64475898595492e-06, "loss": 0.3959, "step": 175500 }, { "epoch": 1.0432678876069215, "grad_norm": 3.5577964782714844, "learning_rate": 9.64468216822464e-06, "loss": 0.4384, "step": 175510 }, { "epoch": 1.0433273296835899, "grad_norm": 6.616324424743652, "learning_rate": 9.64460534249566e-06, "loss": 0.3889, "step": 175520 }, { "epoch": 1.0433867717602583, "grad_norm": 6.005673408508301, "learning_rate": 9.644528508768114e-06, "loss": 0.3733, "step": 175530 }, { "epoch": 1.0434462138369267, "grad_norm": 5.682084560394287, "learning_rate": 9.644451667042139e-06, "loss": 0.3688, "step": 175540 }, { "epoch": 1.043505655913595, "grad_norm": 6.365228652954102, "learning_rate": 9.644374817317863e-06, "loss": 0.3996, "step": 175550 }, { "epoch": 1.0435650979902633, "grad_norm": 4.298473834991455, "learning_rate": 9.644297959595418e-06, "loss": 0.4203, "step": 175560 }, { "epoch": 1.0436245400669317, "grad_norm": 4.538695812225342, "learning_rate": 9.64422109387494e-06, "loss": 0.3647, "step": 175570 }, { "epoch": 1.0436839821436001, "grad_norm": 5.274439334869385, "learning_rate": 9.644144220156557e-06, "loss": 0.409, "step": 175580 }, { "epoch": 1.0437434242202686, "grad_norm": 5.297567367553711, "learning_rate": 9.644067338440404e-06, "loss": 0.374, "step": 175590 }, { "epoch": 1.043802866296937, "grad_norm": 5.639994144439697, "learning_rate": 9.643990448726614e-06, "loss": 0.4171, "step": 175600 }, { "epoch": 1.0438623083736054, "grad_norm": 4.470853328704834, "learning_rate": 9.643913551015318e-06, "loss": 0.3974, "step": 175610 }, { "epoch": 1.0439217504502738, "grad_norm": 5.050378322601318, "learning_rate": 9.643836645306648e-06, "loss": 0.4333, "step": 175620 }, { "epoch": 1.0439811925269422, "grad_norm": 4.329466342926025, "learning_rate": 9.643759731600737e-06, "loss": 0.3805, "step": 175630 }, { "epoch": 1.0440406346036104, "grad_norm": 4.620510578155518, "learning_rate": 9.643682809897718e-06, "loss": 0.4254, "step": 175640 }, { "epoch": 1.0441000766802788, "grad_norm": 4.857263088226318, "learning_rate": 9.643605880197723e-06, "loss": 0.3911, "step": 175650 }, { "epoch": 1.0441595187569472, "grad_norm": 5.495791912078857, "learning_rate": 9.643528942500887e-06, "loss": 0.4033, "step": 175660 }, { "epoch": 1.0442189608336157, "grad_norm": 6.54558801651001, "learning_rate": 9.643451996807338e-06, "loss": 0.4082, "step": 175670 }, { "epoch": 1.044278402910284, "grad_norm": 5.332968235015869, "learning_rate": 9.64337504311721e-06, "loss": 0.4075, "step": 175680 }, { "epoch": 1.0443378449869525, "grad_norm": 6.083249092102051, "learning_rate": 9.643298081430638e-06, "loss": 0.4114, "step": 175690 }, { "epoch": 1.044397287063621, "grad_norm": 4.8044562339782715, "learning_rate": 9.64322111174775e-06, "loss": 0.3865, "step": 175700 }, { "epoch": 1.0444567291402893, "grad_norm": 5.225224018096924, "learning_rate": 9.643144134068684e-06, "loss": 0.3934, "step": 175710 }, { "epoch": 1.0445161712169577, "grad_norm": 5.2446064949035645, "learning_rate": 9.64306714839357e-06, "loss": 0.3886, "step": 175720 }, { "epoch": 1.0445756132936261, "grad_norm": 4.991491794586182, "learning_rate": 9.642990154722538e-06, "loss": 0.3867, "step": 175730 }, { "epoch": 1.0446350553702943, "grad_norm": 4.836672306060791, "learning_rate": 9.642913153055724e-06, "loss": 0.4327, "step": 175740 }, { "epoch": 1.0446944974469627, "grad_norm": 4.903223037719727, "learning_rate": 9.64283614339326e-06, "loss": 0.3893, "step": 175750 }, { "epoch": 1.0447539395236312, "grad_norm": 6.837747097015381, "learning_rate": 9.642759125735276e-06, "loss": 0.456, "step": 175760 }, { "epoch": 1.0448133816002996, "grad_norm": 5.533475399017334, "learning_rate": 9.64268210008191e-06, "loss": 0.4167, "step": 175770 }, { "epoch": 1.044872823676968, "grad_norm": 6.937701225280762, "learning_rate": 9.64260506643329e-06, "loss": 0.3971, "step": 175780 }, { "epoch": 1.0449322657536364, "grad_norm": 4.44531774520874, "learning_rate": 9.64252802478955e-06, "loss": 0.39, "step": 175790 }, { "epoch": 1.0449917078303048, "grad_norm": 7.038640975952148, "learning_rate": 9.642450975150824e-06, "loss": 0.4041, "step": 175800 }, { "epoch": 1.0450511499069732, "grad_norm": 5.3081512451171875, "learning_rate": 9.642373917517241e-06, "loss": 0.4477, "step": 175810 }, { "epoch": 1.0451105919836416, "grad_norm": 4.901430606842041, "learning_rate": 9.642296851888938e-06, "loss": 0.4083, "step": 175820 }, { "epoch": 1.0451700340603098, "grad_norm": 5.328235626220703, "learning_rate": 9.642219778266045e-06, "loss": 0.3494, "step": 175830 }, { "epoch": 1.0452294761369783, "grad_norm": 4.714321613311768, "learning_rate": 9.642142696648697e-06, "loss": 0.4413, "step": 175840 }, { "epoch": 1.0452889182136467, "grad_norm": 4.681037425994873, "learning_rate": 9.642065607037024e-06, "loss": 0.4398, "step": 175850 }, { "epoch": 1.045348360290315, "grad_norm": 3.866313934326172, "learning_rate": 9.641988509431162e-06, "loss": 0.4083, "step": 175860 }, { "epoch": 1.0454078023669835, "grad_norm": 5.356034278869629, "learning_rate": 9.641911403831238e-06, "loss": 0.3908, "step": 175870 }, { "epoch": 1.045467244443652, "grad_norm": 3.9212117195129395, "learning_rate": 9.641834290237392e-06, "loss": 0.3682, "step": 175880 }, { "epoch": 1.0455266865203203, "grad_norm": 6.153787136077881, "learning_rate": 9.641757168649754e-06, "loss": 0.4289, "step": 175890 }, { "epoch": 1.0455861285969887, "grad_norm": 6.183964729309082, "learning_rate": 9.641680039068454e-06, "loss": 0.4277, "step": 175900 }, { "epoch": 1.0456455706736572, "grad_norm": 8.677851676940918, "learning_rate": 9.64160290149363e-06, "loss": 0.4122, "step": 175910 }, { "epoch": 1.0457050127503253, "grad_norm": 6.34800910949707, "learning_rate": 9.64152575592541e-06, "loss": 0.4298, "step": 175920 }, { "epoch": 1.0457644548269938, "grad_norm": 5.395798683166504, "learning_rate": 9.641448602363928e-06, "loss": 0.4516, "step": 175930 }, { "epoch": 1.0458238969036622, "grad_norm": 6.025244235992432, "learning_rate": 9.64137144080932e-06, "loss": 0.3959, "step": 175940 }, { "epoch": 1.0458833389803306, "grad_norm": 6.3004279136657715, "learning_rate": 9.641294271261714e-06, "loss": 0.4172, "step": 175950 }, { "epoch": 1.045942781056999, "grad_norm": 6.628564834594727, "learning_rate": 9.641217093721246e-06, "loss": 0.397, "step": 175960 }, { "epoch": 1.0460022231336674, "grad_norm": 4.155619144439697, "learning_rate": 9.64113990818805e-06, "loss": 0.3596, "step": 175970 }, { "epoch": 1.0460616652103358, "grad_norm": 5.652135372161865, "learning_rate": 9.641062714662258e-06, "loss": 0.4408, "step": 175980 }, { "epoch": 1.0461211072870042, "grad_norm": 5.620903015136719, "learning_rate": 9.640985513144e-06, "loss": 0.4058, "step": 175990 }, { "epoch": 1.0461805493636727, "grad_norm": 4.223913669586182, "learning_rate": 9.640908303633412e-06, "loss": 0.4026, "step": 176000 }, { "epoch": 1.0462399914403409, "grad_norm": 4.801507472991943, "learning_rate": 9.640831086130627e-06, "loss": 0.3885, "step": 176010 }, { "epoch": 1.0462994335170093, "grad_norm": 5.3305182456970215, "learning_rate": 9.640753860635775e-06, "loss": 0.398, "step": 176020 }, { "epoch": 1.0463588755936777, "grad_norm": 4.211833953857422, "learning_rate": 9.640676627148993e-06, "loss": 0.3943, "step": 176030 }, { "epoch": 1.046418317670346, "grad_norm": 6.138603687286377, "learning_rate": 9.64059938567041e-06, "loss": 0.426, "step": 176040 }, { "epoch": 1.0464777597470145, "grad_norm": 5.153581142425537, "learning_rate": 9.640522136200162e-06, "loss": 0.4119, "step": 176050 }, { "epoch": 1.046537201823683, "grad_norm": 4.353732109069824, "learning_rate": 9.640444878738384e-06, "loss": 0.3841, "step": 176060 }, { "epoch": 1.0465966439003513, "grad_norm": 5.629439830780029, "learning_rate": 9.640367613285205e-06, "loss": 0.4405, "step": 176070 }, { "epoch": 1.0466560859770198, "grad_norm": 5.388586521148682, "learning_rate": 9.640290339840756e-06, "loss": 0.403, "step": 176080 }, { "epoch": 1.0467155280536882, "grad_norm": 4.265262126922607, "learning_rate": 9.640213058405177e-06, "loss": 0.4161, "step": 176090 }, { "epoch": 1.0467749701303566, "grad_norm": 4.285078048706055, "learning_rate": 9.640135768978595e-06, "loss": 0.3629, "step": 176100 }, { "epoch": 1.0468344122070248, "grad_norm": 4.932142734527588, "learning_rate": 9.640058471561148e-06, "loss": 0.3943, "step": 176110 }, { "epoch": 1.0468938542836932, "grad_norm": 5.8519978523254395, "learning_rate": 9.639981166152965e-06, "loss": 0.3918, "step": 176120 }, { "epoch": 1.0469532963603616, "grad_norm": 5.975022792816162, "learning_rate": 9.639903852754181e-06, "loss": 0.3957, "step": 176130 }, { "epoch": 1.04701273843703, "grad_norm": 5.766907215118408, "learning_rate": 9.639826531364928e-06, "loss": 0.4185, "step": 176140 }, { "epoch": 1.0470721805136984, "grad_norm": 4.796880722045898, "learning_rate": 9.639749201985343e-06, "loss": 0.3967, "step": 176150 }, { "epoch": 1.0471316225903669, "grad_norm": 4.758070468902588, "learning_rate": 9.639671864615555e-06, "loss": 0.3753, "step": 176160 }, { "epoch": 1.0471910646670353, "grad_norm": 4.011148929595947, "learning_rate": 9.639594519255697e-06, "loss": 0.371, "step": 176170 }, { "epoch": 1.0472505067437037, "grad_norm": 4.984910011291504, "learning_rate": 9.639517165905905e-06, "loss": 0.384, "step": 176180 }, { "epoch": 1.047309948820372, "grad_norm": 5.289628505706787, "learning_rate": 9.639439804566311e-06, "loss": 0.4056, "step": 176190 }, { "epoch": 1.0473693908970403, "grad_norm": 6.438172340393066, "learning_rate": 9.639362435237047e-06, "loss": 0.4119, "step": 176200 }, { "epoch": 1.0474288329737087, "grad_norm": 5.005136966705322, "learning_rate": 9.639285057918248e-06, "loss": 0.3972, "step": 176210 }, { "epoch": 1.0474882750503771, "grad_norm": 7.106325626373291, "learning_rate": 9.639207672610046e-06, "loss": 0.4303, "step": 176220 }, { "epoch": 1.0475477171270455, "grad_norm": 5.393238067626953, "learning_rate": 9.639130279312575e-06, "loss": 0.3806, "step": 176230 }, { "epoch": 1.047607159203714, "grad_norm": 4.795646667480469, "learning_rate": 9.639052878025968e-06, "loss": 0.4021, "step": 176240 }, { "epoch": 1.0476666012803824, "grad_norm": 5.4822306632995605, "learning_rate": 9.63897546875036e-06, "loss": 0.389, "step": 176250 }, { "epoch": 1.0477260433570508, "grad_norm": 5.238506317138672, "learning_rate": 9.638898051485881e-06, "loss": 0.4506, "step": 176260 }, { "epoch": 1.0477854854337192, "grad_norm": 6.127787113189697, "learning_rate": 9.638820626232667e-06, "loss": 0.4559, "step": 176270 }, { "epoch": 1.0478449275103876, "grad_norm": 7.291885852813721, "learning_rate": 9.638743192990849e-06, "loss": 0.4513, "step": 176280 }, { "epoch": 1.0479043695870558, "grad_norm": 5.286793231964111, "learning_rate": 9.638665751760562e-06, "loss": 0.4284, "step": 176290 }, { "epoch": 1.0479638116637242, "grad_norm": 6.406345367431641, "learning_rate": 9.63858830254194e-06, "loss": 0.4321, "step": 176300 }, { "epoch": 1.0480232537403926, "grad_norm": 3.71097731590271, "learning_rate": 9.638510845335115e-06, "loss": 0.3711, "step": 176310 }, { "epoch": 1.048082695817061, "grad_norm": 5.499207973480225, "learning_rate": 9.638433380140222e-06, "loss": 0.3919, "step": 176320 }, { "epoch": 1.0481421378937295, "grad_norm": 5.293660640716553, "learning_rate": 9.638355906957394e-06, "loss": 0.408, "step": 176330 }, { "epoch": 1.0482015799703979, "grad_norm": 5.9535322189331055, "learning_rate": 9.638278425786763e-06, "loss": 0.3889, "step": 176340 }, { "epoch": 1.0482610220470663, "grad_norm": 5.56120491027832, "learning_rate": 9.63820093662846e-06, "loss": 0.4279, "step": 176350 }, { "epoch": 1.0483204641237347, "grad_norm": 5.200351238250732, "learning_rate": 9.638123439482626e-06, "loss": 0.4279, "step": 176360 }, { "epoch": 1.0483799062004031, "grad_norm": 4.246963024139404, "learning_rate": 9.638045934349387e-06, "loss": 0.3973, "step": 176370 }, { "epoch": 1.0484393482770713, "grad_norm": 5.694577693939209, "learning_rate": 9.63796842122888e-06, "loss": 0.3805, "step": 176380 }, { "epoch": 1.0484987903537397, "grad_norm": 4.36628532409668, "learning_rate": 9.637890900121238e-06, "loss": 0.42, "step": 176390 }, { "epoch": 1.0485582324304081, "grad_norm": 4.969264507293701, "learning_rate": 9.637813371026596e-06, "loss": 0.3974, "step": 176400 }, { "epoch": 1.0486176745070765, "grad_norm": 5.173695087432861, "learning_rate": 9.637735833945084e-06, "loss": 0.4123, "step": 176410 }, { "epoch": 1.048677116583745, "grad_norm": 4.573995113372803, "learning_rate": 9.637658288876839e-06, "loss": 0.385, "step": 176420 }, { "epoch": 1.0487365586604134, "grad_norm": 5.969658374786377, "learning_rate": 9.637580735821991e-06, "loss": 0.4158, "step": 176430 }, { "epoch": 1.0487960007370818, "grad_norm": 6.345257759094238, "learning_rate": 9.637503174780678e-06, "loss": 0.421, "step": 176440 }, { "epoch": 1.0488554428137502, "grad_norm": 4.77910041809082, "learning_rate": 9.63742560575303e-06, "loss": 0.4023, "step": 176450 }, { "epoch": 1.0489148848904186, "grad_norm": 6.669645309448242, "learning_rate": 9.637348028739182e-06, "loss": 0.4301, "step": 176460 }, { "epoch": 1.048974326967087, "grad_norm": 7.384522438049316, "learning_rate": 9.637270443739268e-06, "loss": 0.4333, "step": 176470 }, { "epoch": 1.0490337690437552, "grad_norm": 6.104977130889893, "learning_rate": 9.63719285075342e-06, "loss": 0.431, "step": 176480 }, { "epoch": 1.0490932111204236, "grad_norm": 3.89091420173645, "learning_rate": 9.637115249781772e-06, "loss": 0.3483, "step": 176490 }, { "epoch": 1.049152653197092, "grad_norm": 4.563876628875732, "learning_rate": 9.63703764082446e-06, "loss": 0.387, "step": 176500 }, { "epoch": 1.0492120952737605, "grad_norm": 5.1620659828186035, "learning_rate": 9.636960023881614e-06, "loss": 0.4421, "step": 176510 }, { "epoch": 1.0492715373504289, "grad_norm": 5.003219127655029, "learning_rate": 9.636882398953372e-06, "loss": 0.4062, "step": 176520 }, { "epoch": 1.0493309794270973, "grad_norm": 5.4614644050598145, "learning_rate": 9.636804766039865e-06, "loss": 0.4365, "step": 176530 }, { "epoch": 1.0493904215037657, "grad_norm": 6.424715042114258, "learning_rate": 9.636727125141225e-06, "loss": 0.4221, "step": 176540 }, { "epoch": 1.0494498635804341, "grad_norm": 5.706727981567383, "learning_rate": 9.63664947625759e-06, "loss": 0.4514, "step": 176550 }, { "epoch": 1.0495093056571025, "grad_norm": 7.23868989944458, "learning_rate": 9.63657181938909e-06, "loss": 0.4214, "step": 176560 }, { "epoch": 1.0495687477337707, "grad_norm": 5.6243181228637695, "learning_rate": 9.636494154535857e-06, "loss": 0.4191, "step": 176570 }, { "epoch": 1.0496281898104391, "grad_norm": 6.883228778839111, "learning_rate": 9.636416481698032e-06, "loss": 0.3838, "step": 176580 }, { "epoch": 1.0496876318871076, "grad_norm": 6.432353973388672, "learning_rate": 9.636338800875744e-06, "loss": 0.4113, "step": 176590 }, { "epoch": 1.049747073963776, "grad_norm": 5.198257923126221, "learning_rate": 9.636261112069128e-06, "loss": 0.4659, "step": 176600 }, { "epoch": 1.0498065160404444, "grad_norm": 7.813023090362549, "learning_rate": 9.636183415278315e-06, "loss": 0.4325, "step": 176610 }, { "epoch": 1.0498659581171128, "grad_norm": 5.672843933105469, "learning_rate": 9.636105710503441e-06, "loss": 0.4193, "step": 176620 }, { "epoch": 1.0499254001937812, "grad_norm": 4.485370635986328, "learning_rate": 9.636027997744641e-06, "loss": 0.4326, "step": 176630 }, { "epoch": 1.0499848422704496, "grad_norm": 5.856934070587158, "learning_rate": 9.635950277002048e-06, "loss": 0.4163, "step": 176640 }, { "epoch": 1.050044284347118, "grad_norm": 6.138936996459961, "learning_rate": 9.635872548275796e-06, "loss": 0.3548, "step": 176650 }, { "epoch": 1.0501037264237862, "grad_norm": 6.257663249969482, "learning_rate": 9.635794811566016e-06, "loss": 0.4241, "step": 176660 }, { "epoch": 1.0501631685004547, "grad_norm": 5.318364143371582, "learning_rate": 9.635717066872844e-06, "loss": 0.4407, "step": 176670 }, { "epoch": 1.050222610577123, "grad_norm": 5.164829254150391, "learning_rate": 9.635639314196417e-06, "loss": 0.3938, "step": 176680 }, { "epoch": 1.0502820526537915, "grad_norm": 5.238744735717773, "learning_rate": 9.635561553536866e-06, "loss": 0.3763, "step": 176690 }, { "epoch": 1.05034149473046, "grad_norm": 4.85401725769043, "learning_rate": 9.635483784894322e-06, "loss": 0.387, "step": 176700 }, { "epoch": 1.0504009368071283, "grad_norm": 6.830183506011963, "learning_rate": 9.635406008268924e-06, "loss": 0.3931, "step": 176710 }, { "epoch": 1.0504603788837967, "grad_norm": 6.041985988616943, "learning_rate": 9.635328223660802e-06, "loss": 0.3822, "step": 176720 }, { "epoch": 1.0505198209604651, "grad_norm": 4.074243545532227, "learning_rate": 9.635250431070094e-06, "loss": 0.3997, "step": 176730 }, { "epoch": 1.0505792630371336, "grad_norm": 5.085109233856201, "learning_rate": 9.63517263049693e-06, "loss": 0.3938, "step": 176740 }, { "epoch": 1.0506387051138018, "grad_norm": 5.802757740020752, "learning_rate": 9.635094821941445e-06, "loss": 0.403, "step": 176750 }, { "epoch": 1.0506981471904702, "grad_norm": 5.479599952697754, "learning_rate": 9.635017005403775e-06, "loss": 0.4389, "step": 176760 }, { "epoch": 1.0507575892671386, "grad_norm": 6.019244194030762, "learning_rate": 9.634939180884053e-06, "loss": 0.4338, "step": 176770 }, { "epoch": 1.050817031343807, "grad_norm": 5.678276062011719, "learning_rate": 9.634861348382411e-06, "loss": 0.406, "step": 176780 }, { "epoch": 1.0508764734204754, "grad_norm": 5.250826835632324, "learning_rate": 9.634783507898987e-06, "loss": 0.3574, "step": 176790 }, { "epoch": 1.0509359154971438, "grad_norm": 5.4117960929870605, "learning_rate": 9.634705659433911e-06, "loss": 0.3587, "step": 176800 }, { "epoch": 1.0509953575738122, "grad_norm": 5.64617919921875, "learning_rate": 9.63462780298732e-06, "loss": 0.3924, "step": 176810 }, { "epoch": 1.0510547996504807, "grad_norm": 4.638071060180664, "learning_rate": 9.634549938559346e-06, "loss": 0.4164, "step": 176820 }, { "epoch": 1.051114241727149, "grad_norm": 4.064546585083008, "learning_rate": 9.634472066150125e-06, "loss": 0.4134, "step": 176830 }, { "epoch": 1.0511736838038175, "grad_norm": 4.911360740661621, "learning_rate": 9.63439418575979e-06, "loss": 0.4069, "step": 176840 }, { "epoch": 1.0512331258804857, "grad_norm": 4.322892189025879, "learning_rate": 9.634316297388474e-06, "loss": 0.4218, "step": 176850 }, { "epoch": 1.051292567957154, "grad_norm": 4.899409294128418, "learning_rate": 9.634238401036313e-06, "loss": 0.4275, "step": 176860 }, { "epoch": 1.0513520100338225, "grad_norm": 4.459186553955078, "learning_rate": 9.634160496703441e-06, "loss": 0.4092, "step": 176870 }, { "epoch": 1.051411452110491, "grad_norm": 5.3323140144348145, "learning_rate": 9.634082584389991e-06, "loss": 0.3968, "step": 176880 }, { "epoch": 1.0514708941871593, "grad_norm": 5.272611141204834, "learning_rate": 9.6340046640961e-06, "loss": 0.4127, "step": 176890 }, { "epoch": 1.0515303362638277, "grad_norm": 5.930295467376709, "learning_rate": 9.633926735821898e-06, "loss": 0.4174, "step": 176900 }, { "epoch": 1.0515897783404962, "grad_norm": 4.709200859069824, "learning_rate": 9.63384879956752e-06, "loss": 0.4045, "step": 176910 }, { "epoch": 1.0516492204171646, "grad_norm": 4.871206283569336, "learning_rate": 9.633770855333103e-06, "loss": 0.4116, "step": 176920 }, { "epoch": 1.051708662493833, "grad_norm": 6.060352802276611, "learning_rate": 9.63369290311878e-06, "loss": 0.4209, "step": 176930 }, { "epoch": 1.0517681045705012, "grad_norm": 5.591313362121582, "learning_rate": 9.633614942924685e-06, "loss": 0.4347, "step": 176940 }, { "epoch": 1.0518275466471696, "grad_norm": 4.875638008117676, "learning_rate": 9.633536974750952e-06, "loss": 0.4208, "step": 176950 }, { "epoch": 1.051886988723838, "grad_norm": 4.437912464141846, "learning_rate": 9.633458998597716e-06, "loss": 0.3699, "step": 176960 }, { "epoch": 1.0519464308005064, "grad_norm": 4.602673053741455, "learning_rate": 9.633381014465108e-06, "loss": 0.4355, "step": 176970 }, { "epoch": 1.0520058728771748, "grad_norm": 4.798895835876465, "learning_rate": 9.633303022353269e-06, "loss": 0.3951, "step": 176980 }, { "epoch": 1.0520653149538433, "grad_norm": 5.920191287994385, "learning_rate": 9.633225022262328e-06, "loss": 0.4119, "step": 176990 }, { "epoch": 1.0521247570305117, "grad_norm": 10.534286499023438, "learning_rate": 9.63314701419242e-06, "loss": 0.4354, "step": 177000 }, { "epoch": 1.05218419910718, "grad_norm": 4.75333309173584, "learning_rate": 9.63306899814368e-06, "loss": 0.3783, "step": 177010 }, { "epoch": 1.0522436411838485, "grad_norm": 4.590106010437012, "learning_rate": 9.632990974116241e-06, "loss": 0.3892, "step": 177020 }, { "epoch": 1.0523030832605167, "grad_norm": 5.461090087890625, "learning_rate": 9.63291294211024e-06, "loss": 0.4257, "step": 177030 }, { "epoch": 1.052362525337185, "grad_norm": 5.252237319946289, "learning_rate": 9.632834902125812e-06, "loss": 0.4327, "step": 177040 }, { "epoch": 1.0524219674138535, "grad_norm": 5.089107513427734, "learning_rate": 9.632756854163088e-06, "loss": 0.3921, "step": 177050 }, { "epoch": 1.052481409490522, "grad_norm": 5.39410924911499, "learning_rate": 9.632678798222204e-06, "loss": 0.4261, "step": 177060 }, { "epoch": 1.0525408515671903, "grad_norm": 6.22470235824585, "learning_rate": 9.632600734303294e-06, "loss": 0.4187, "step": 177070 }, { "epoch": 1.0526002936438588, "grad_norm": 6.352588653564453, "learning_rate": 9.632522662406492e-06, "loss": 0.434, "step": 177080 }, { "epoch": 1.0526597357205272, "grad_norm": 6.009756565093994, "learning_rate": 9.632444582531934e-06, "loss": 0.3895, "step": 177090 }, { "epoch": 1.0527191777971956, "grad_norm": 4.19882345199585, "learning_rate": 9.632366494679755e-06, "loss": 0.3878, "step": 177100 }, { "epoch": 1.052778619873864, "grad_norm": 3.9255142211914062, "learning_rate": 9.632288398850086e-06, "loss": 0.4476, "step": 177110 }, { "epoch": 1.0528380619505322, "grad_norm": 6.510977745056152, "learning_rate": 9.632210295043064e-06, "loss": 0.4845, "step": 177120 }, { "epoch": 1.0528975040272006, "grad_norm": 3.5238444805145264, "learning_rate": 9.632132183258825e-06, "loss": 0.4103, "step": 177130 }, { "epoch": 1.052956946103869, "grad_norm": 5.144806861877441, "learning_rate": 9.632054063497501e-06, "loss": 0.4357, "step": 177140 }, { "epoch": 1.0530163881805374, "grad_norm": 4.7741899490356445, "learning_rate": 9.631975935759227e-06, "loss": 0.3832, "step": 177150 }, { "epoch": 1.0530758302572059, "grad_norm": 4.554405212402344, "learning_rate": 9.631897800044137e-06, "loss": 0.4274, "step": 177160 }, { "epoch": 1.0531352723338743, "grad_norm": 5.233636856079102, "learning_rate": 9.631819656352367e-06, "loss": 0.4515, "step": 177170 }, { "epoch": 1.0531947144105427, "grad_norm": 3.4092421531677246, "learning_rate": 9.631741504684051e-06, "loss": 0.4148, "step": 177180 }, { "epoch": 1.053254156487211, "grad_norm": 4.282182216644287, "learning_rate": 9.631663345039323e-06, "loss": 0.3598, "step": 177190 }, { "epoch": 1.0533135985638795, "grad_norm": 3.621532917022705, "learning_rate": 9.631585177418318e-06, "loss": 0.3588, "step": 177200 }, { "epoch": 1.053373040640548, "grad_norm": 5.122363090515137, "learning_rate": 9.631507001821172e-06, "loss": 0.3772, "step": 177210 }, { "epoch": 1.0534324827172161, "grad_norm": 5.533402442932129, "learning_rate": 9.631428818248017e-06, "loss": 0.4057, "step": 177220 }, { "epoch": 1.0534919247938845, "grad_norm": 6.041976451873779, "learning_rate": 9.63135062669899e-06, "loss": 0.41, "step": 177230 }, { "epoch": 1.053551366870553, "grad_norm": 5.224024295806885, "learning_rate": 9.631272427174223e-06, "loss": 0.3841, "step": 177240 }, { "epoch": 1.0536108089472214, "grad_norm": 5.1276326179504395, "learning_rate": 9.631194219673853e-06, "loss": 0.4228, "step": 177250 }, { "epoch": 1.0536702510238898, "grad_norm": 5.321330547332764, "learning_rate": 9.631116004198014e-06, "loss": 0.4163, "step": 177260 }, { "epoch": 1.0537296931005582, "grad_norm": 4.216792583465576, "learning_rate": 9.631037780746842e-06, "loss": 0.3588, "step": 177270 }, { "epoch": 1.0537891351772266, "grad_norm": 5.364570617675781, "learning_rate": 9.63095954932047e-06, "loss": 0.3918, "step": 177280 }, { "epoch": 1.053848577253895, "grad_norm": 4.539264678955078, "learning_rate": 9.630881309919031e-06, "loss": 0.3922, "step": 177290 }, { "epoch": 1.0539080193305634, "grad_norm": 4.646294116973877, "learning_rate": 9.630803062542664e-06, "loss": 0.4148, "step": 177300 }, { "epoch": 1.0539674614072316, "grad_norm": 4.3257575035095215, "learning_rate": 9.6307248071915e-06, "loss": 0.4032, "step": 177310 }, { "epoch": 1.0540269034839, "grad_norm": 5.010385036468506, "learning_rate": 9.630646543865676e-06, "loss": 0.4207, "step": 177320 }, { "epoch": 1.0540863455605685, "grad_norm": 5.603636264801025, "learning_rate": 9.630568272565326e-06, "loss": 0.4003, "step": 177330 }, { "epoch": 1.0541457876372369, "grad_norm": 6.361176013946533, "learning_rate": 9.630489993290586e-06, "loss": 0.3936, "step": 177340 }, { "epoch": 1.0542052297139053, "grad_norm": 5.065565586090088, "learning_rate": 9.63041170604159e-06, "loss": 0.4388, "step": 177350 }, { "epoch": 1.0542646717905737, "grad_norm": 4.951328277587891, "learning_rate": 9.630333410818469e-06, "loss": 0.4066, "step": 177360 }, { "epoch": 1.0543241138672421, "grad_norm": 4.444459438323975, "learning_rate": 9.630255107621365e-06, "loss": 0.4199, "step": 177370 }, { "epoch": 1.0543835559439105, "grad_norm": 4.771223545074463, "learning_rate": 9.630176796450407e-06, "loss": 0.419, "step": 177380 }, { "epoch": 1.054442998020579, "grad_norm": 4.542687892913818, "learning_rate": 9.630098477305733e-06, "loss": 0.3949, "step": 177390 }, { "epoch": 1.0545024400972471, "grad_norm": 4.1467461585998535, "learning_rate": 9.630020150187479e-06, "loss": 0.3843, "step": 177400 }, { "epoch": 1.0545618821739156, "grad_norm": 4.854774475097656, "learning_rate": 9.629941815095776e-06, "loss": 0.3992, "step": 177410 }, { "epoch": 1.054621324250584, "grad_norm": 4.920826435089111, "learning_rate": 9.629863472030761e-06, "loss": 0.4178, "step": 177420 }, { "epoch": 1.0546807663272524, "grad_norm": 5.1455206871032715, "learning_rate": 9.629785120992568e-06, "loss": 0.4046, "step": 177430 }, { "epoch": 1.0547402084039208, "grad_norm": 6.263668060302734, "learning_rate": 9.629706761981332e-06, "loss": 0.4167, "step": 177440 }, { "epoch": 1.0547996504805892, "grad_norm": 4.6988844871521, "learning_rate": 9.629628394997191e-06, "loss": 0.4267, "step": 177450 }, { "epoch": 1.0548590925572576, "grad_norm": 5.187908172607422, "learning_rate": 9.629550020040274e-06, "loss": 0.401, "step": 177460 }, { "epoch": 1.054918534633926, "grad_norm": 6.01263427734375, "learning_rate": 9.629471637110723e-06, "loss": 0.3898, "step": 177470 }, { "epoch": 1.0549779767105945, "grad_norm": 5.775552272796631, "learning_rate": 9.629393246208666e-06, "loss": 0.4274, "step": 177480 }, { "epoch": 1.0550374187872626, "grad_norm": 5.392817497253418, "learning_rate": 9.629314847334245e-06, "loss": 0.3981, "step": 177490 }, { "epoch": 1.055096860863931, "grad_norm": 5.2596211433410645, "learning_rate": 9.629236440487591e-06, "loss": 0.4028, "step": 177500 }, { "epoch": 1.0551563029405995, "grad_norm": 5.037397861480713, "learning_rate": 9.629158025668836e-06, "loss": 0.4568, "step": 177510 }, { "epoch": 1.055215745017268, "grad_norm": 4.82676887512207, "learning_rate": 9.629079602878123e-06, "loss": 0.4465, "step": 177520 }, { "epoch": 1.0552751870939363, "grad_norm": 6.251265525817871, "learning_rate": 9.62900117211558e-06, "loss": 0.4134, "step": 177530 }, { "epoch": 1.0553346291706047, "grad_norm": 3.4072606563568115, "learning_rate": 9.628922733381345e-06, "loss": 0.4127, "step": 177540 }, { "epoch": 1.0553940712472731, "grad_norm": 5.890923500061035, "learning_rate": 9.628844286675554e-06, "loss": 0.3671, "step": 177550 }, { "epoch": 1.0554535133239416, "grad_norm": 6.115203380584717, "learning_rate": 9.628765831998339e-06, "loss": 0.4106, "step": 177560 }, { "epoch": 1.05551295540061, "grad_norm": 6.73743200302124, "learning_rate": 9.628687369349837e-06, "loss": 0.4431, "step": 177570 }, { "epoch": 1.0555723974772784, "grad_norm": 5.306689262390137, "learning_rate": 9.628608898730185e-06, "loss": 0.4294, "step": 177580 }, { "epoch": 1.0556318395539466, "grad_norm": 5.29382848739624, "learning_rate": 9.628530420139514e-06, "loss": 0.4029, "step": 177590 }, { "epoch": 1.055691281630615, "grad_norm": 4.753750801086426, "learning_rate": 9.628451933577963e-06, "loss": 0.3333, "step": 177600 }, { "epoch": 1.0557507237072834, "grad_norm": 4.028921604156494, "learning_rate": 9.628373439045664e-06, "loss": 0.4529, "step": 177610 }, { "epoch": 1.0558101657839518, "grad_norm": 5.916229248046875, "learning_rate": 9.628294936542755e-06, "loss": 0.4591, "step": 177620 }, { "epoch": 1.0558696078606202, "grad_norm": 5.130810737609863, "learning_rate": 9.62821642606937e-06, "loss": 0.3533, "step": 177630 }, { "epoch": 1.0559290499372886, "grad_norm": 3.9570436477661133, "learning_rate": 9.628137907625644e-06, "loss": 0.413, "step": 177640 }, { "epoch": 1.055988492013957, "grad_norm": 4.218953609466553, "learning_rate": 9.628059381211711e-06, "loss": 0.4367, "step": 177650 }, { "epoch": 1.0560479340906255, "grad_norm": 5.6932806968688965, "learning_rate": 9.627980846827708e-06, "loss": 0.387, "step": 177660 }, { "epoch": 1.0561073761672939, "grad_norm": 5.2508368492126465, "learning_rate": 9.62790230447377e-06, "loss": 0.3966, "step": 177670 }, { "epoch": 1.056166818243962, "grad_norm": 4.54281759262085, "learning_rate": 9.627823754150032e-06, "loss": 0.4257, "step": 177680 }, { "epoch": 1.0562262603206305, "grad_norm": 6.020430564880371, "learning_rate": 9.62774519585663e-06, "loss": 0.3809, "step": 177690 }, { "epoch": 1.056285702397299, "grad_norm": 4.2900567054748535, "learning_rate": 9.627666629593699e-06, "loss": 0.4205, "step": 177700 }, { "epoch": 1.0563451444739673, "grad_norm": 6.083513259887695, "learning_rate": 9.627588055361372e-06, "loss": 0.4207, "step": 177710 }, { "epoch": 1.0564045865506357, "grad_norm": 4.754749298095703, "learning_rate": 9.627509473159787e-06, "loss": 0.5015, "step": 177720 }, { "epoch": 1.0564640286273042, "grad_norm": 5.435462474822998, "learning_rate": 9.62743088298908e-06, "loss": 0.4243, "step": 177730 }, { "epoch": 1.0565234707039726, "grad_norm": 5.955173969268799, "learning_rate": 9.627352284849383e-06, "loss": 0.3992, "step": 177740 }, { "epoch": 1.056582912780641, "grad_norm": 4.950185298919678, "learning_rate": 9.627273678740834e-06, "loss": 0.3865, "step": 177750 }, { "epoch": 1.0566423548573094, "grad_norm": 5.08233642578125, "learning_rate": 9.627195064663567e-06, "loss": 0.4228, "step": 177760 }, { "epoch": 1.0567017969339776, "grad_norm": 4.25555944442749, "learning_rate": 9.627116442617719e-06, "loss": 0.4016, "step": 177770 }, { "epoch": 1.056761239010646, "grad_norm": 5.524387359619141, "learning_rate": 9.627037812603424e-06, "loss": 0.4128, "step": 177780 }, { "epoch": 1.0568206810873144, "grad_norm": 5.479018211364746, "learning_rate": 9.626959174620817e-06, "loss": 0.4235, "step": 177790 }, { "epoch": 1.0568801231639828, "grad_norm": 5.919498443603516, "learning_rate": 9.626880528670035e-06, "loss": 0.4088, "step": 177800 }, { "epoch": 1.0569395652406512, "grad_norm": 4.844930648803711, "learning_rate": 9.626801874751213e-06, "loss": 0.3763, "step": 177810 }, { "epoch": 1.0569990073173197, "grad_norm": 6.410505771636963, "learning_rate": 9.626723212864486e-06, "loss": 0.363, "step": 177820 }, { "epoch": 1.057058449393988, "grad_norm": 4.872475624084473, "learning_rate": 9.626644543009989e-06, "loss": 0.3799, "step": 177830 }, { "epoch": 1.0571178914706565, "grad_norm": 4.5588788986206055, "learning_rate": 9.626565865187858e-06, "loss": 0.4107, "step": 177840 }, { "epoch": 1.057177333547325, "grad_norm": 4.454085826873779, "learning_rate": 9.626487179398229e-06, "loss": 0.3806, "step": 177850 }, { "epoch": 1.057236775623993, "grad_norm": 5.312549591064453, "learning_rate": 9.626408485641236e-06, "loss": 0.4168, "step": 177860 }, { "epoch": 1.0572962177006615, "grad_norm": 5.5465803146362305, "learning_rate": 9.626329783917016e-06, "loss": 0.3824, "step": 177870 }, { "epoch": 1.05735565977733, "grad_norm": 5.412705898284912, "learning_rate": 9.626251074225706e-06, "loss": 0.4241, "step": 177880 }, { "epoch": 1.0574151018539983, "grad_norm": 4.41617488861084, "learning_rate": 9.626172356567438e-06, "loss": 0.4327, "step": 177890 }, { "epoch": 1.0574745439306668, "grad_norm": 4.643048286437988, "learning_rate": 9.626093630942349e-06, "loss": 0.4419, "step": 177900 }, { "epoch": 1.0575339860073352, "grad_norm": 4.1944708824157715, "learning_rate": 9.626014897350576e-06, "loss": 0.3843, "step": 177910 }, { "epoch": 1.0575934280840036, "grad_norm": 5.400248050689697, "learning_rate": 9.625936155792253e-06, "loss": 0.3996, "step": 177920 }, { "epoch": 1.057652870160672, "grad_norm": 6.442696571350098, "learning_rate": 9.625857406267513e-06, "loss": 0.4321, "step": 177930 }, { "epoch": 1.0577123122373404, "grad_norm": 5.419911861419678, "learning_rate": 9.625778648776499e-06, "loss": 0.4095, "step": 177940 }, { "epoch": 1.0577717543140088, "grad_norm": 4.64791202545166, "learning_rate": 9.62569988331934e-06, "loss": 0.3696, "step": 177950 }, { "epoch": 1.057831196390677, "grad_norm": 4.063387393951416, "learning_rate": 9.625621109896174e-06, "loss": 0.4039, "step": 177960 }, { "epoch": 1.0578906384673454, "grad_norm": 5.678421974182129, "learning_rate": 9.625542328507137e-06, "loss": 0.3996, "step": 177970 }, { "epoch": 1.0579500805440138, "grad_norm": 5.126270771026611, "learning_rate": 9.625463539152365e-06, "loss": 0.4112, "step": 177980 }, { "epoch": 1.0580095226206823, "grad_norm": 5.701669216156006, "learning_rate": 9.625384741831991e-06, "loss": 0.3985, "step": 177990 }, { "epoch": 1.0580689646973507, "grad_norm": 4.320384502410889, "learning_rate": 9.625305936546154e-06, "loss": 0.4252, "step": 178000 }, { "epoch": 1.058128406774019, "grad_norm": 4.764025688171387, "learning_rate": 9.625227123294986e-06, "loss": 0.3926, "step": 178010 }, { "epoch": 1.0581878488506875, "grad_norm": 5.138021469116211, "learning_rate": 9.625148302078629e-06, "loss": 0.394, "step": 178020 }, { "epoch": 1.058247290927356, "grad_norm": 6.675856113433838, "learning_rate": 9.625069472897211e-06, "loss": 0.4074, "step": 178030 }, { "epoch": 1.0583067330040243, "grad_norm": 4.587922096252441, "learning_rate": 9.624990635750875e-06, "loss": 0.4409, "step": 178040 }, { "epoch": 1.0583661750806925, "grad_norm": 5.110705852508545, "learning_rate": 9.62491179063975e-06, "loss": 0.3909, "step": 178050 }, { "epoch": 1.058425617157361, "grad_norm": 4.73895263671875, "learning_rate": 9.624832937563977e-06, "loss": 0.3776, "step": 178060 }, { "epoch": 1.0584850592340294, "grad_norm": 4.61105489730835, "learning_rate": 9.624754076523688e-06, "loss": 0.3984, "step": 178070 }, { "epoch": 1.0585445013106978, "grad_norm": 4.198177337646484, "learning_rate": 9.624675207519023e-06, "loss": 0.4008, "step": 178080 }, { "epoch": 1.0586039433873662, "grad_norm": 5.727182865142822, "learning_rate": 9.624596330550113e-06, "loss": 0.3757, "step": 178090 }, { "epoch": 1.0586633854640346, "grad_norm": 5.60268497467041, "learning_rate": 9.624517445617099e-06, "loss": 0.4036, "step": 178100 }, { "epoch": 1.058722827540703, "grad_norm": 5.109190464019775, "learning_rate": 9.624438552720112e-06, "loss": 0.3754, "step": 178110 }, { "epoch": 1.0587822696173714, "grad_norm": 5.129573345184326, "learning_rate": 9.624359651859292e-06, "loss": 0.382, "step": 178120 }, { "epoch": 1.0588417116940398, "grad_norm": 5.172385215759277, "learning_rate": 9.624280743034771e-06, "loss": 0.4121, "step": 178130 }, { "epoch": 1.058901153770708, "grad_norm": 5.09671688079834, "learning_rate": 9.624201826246689e-06, "loss": 0.3922, "step": 178140 }, { "epoch": 1.0589605958473765, "grad_norm": 6.17918062210083, "learning_rate": 9.624122901495177e-06, "loss": 0.4364, "step": 178150 }, { "epoch": 1.0590200379240449, "grad_norm": 3.9766688346862793, "learning_rate": 9.624043968780375e-06, "loss": 0.3827, "step": 178160 }, { "epoch": 1.0590794800007133, "grad_norm": 4.735090255737305, "learning_rate": 9.623965028102418e-06, "loss": 0.3918, "step": 178170 }, { "epoch": 1.0591389220773817, "grad_norm": 4.628899574279785, "learning_rate": 9.623886079461441e-06, "loss": 0.4129, "step": 178180 }, { "epoch": 1.05919836415405, "grad_norm": 6.854069709777832, "learning_rate": 9.62380712285758e-06, "loss": 0.4303, "step": 178190 }, { "epoch": 1.0592578062307185, "grad_norm": 7.813761234283447, "learning_rate": 9.623728158290973e-06, "loss": 0.4525, "step": 178200 }, { "epoch": 1.059317248307387, "grad_norm": 5.214693546295166, "learning_rate": 9.623649185761752e-06, "loss": 0.3737, "step": 178210 }, { "epoch": 1.0593766903840554, "grad_norm": 6.33585262298584, "learning_rate": 9.623570205270058e-06, "loss": 0.4129, "step": 178220 }, { "epoch": 1.0594361324607235, "grad_norm": 6.03291130065918, "learning_rate": 9.623491216816022e-06, "loss": 0.4092, "step": 178230 }, { "epoch": 1.059495574537392, "grad_norm": 5.502504348754883, "learning_rate": 9.623412220399783e-06, "loss": 0.4117, "step": 178240 }, { "epoch": 1.0595550166140604, "grad_norm": 6.299953460693359, "learning_rate": 9.623333216021477e-06, "loss": 0.4217, "step": 178250 }, { "epoch": 1.0596144586907288, "grad_norm": 5.2179155349731445, "learning_rate": 9.62325420368124e-06, "loss": 0.3812, "step": 178260 }, { "epoch": 1.0596739007673972, "grad_norm": 4.319034576416016, "learning_rate": 9.623175183379207e-06, "loss": 0.4116, "step": 178270 }, { "epoch": 1.0597333428440656, "grad_norm": 4.221406936645508, "learning_rate": 9.623096155115517e-06, "loss": 0.3822, "step": 178280 }, { "epoch": 1.059792784920734, "grad_norm": 4.4312896728515625, "learning_rate": 9.6230171188903e-06, "loss": 0.3868, "step": 178290 }, { "epoch": 1.0598522269974024, "grad_norm": 4.870765686035156, "learning_rate": 9.622938074703698e-06, "loss": 0.4384, "step": 178300 }, { "epoch": 1.0599116690740709, "grad_norm": 5.455703258514404, "learning_rate": 9.622859022555845e-06, "loss": 0.3637, "step": 178310 }, { "epoch": 1.0599711111507393, "grad_norm": 6.75636625289917, "learning_rate": 9.622779962446878e-06, "loss": 0.41, "step": 178320 }, { "epoch": 1.0600305532274075, "grad_norm": 4.739826202392578, "learning_rate": 9.62270089437693e-06, "loss": 0.3874, "step": 178330 }, { "epoch": 1.0600899953040759, "grad_norm": 5.192788600921631, "learning_rate": 9.622621818346141e-06, "loss": 0.419, "step": 178340 }, { "epoch": 1.0601494373807443, "grad_norm": 6.110537528991699, "learning_rate": 9.622542734354646e-06, "loss": 0.3815, "step": 178350 }, { "epoch": 1.0602088794574127, "grad_norm": 4.677827835083008, "learning_rate": 9.62246364240258e-06, "loss": 0.4211, "step": 178360 }, { "epoch": 1.0602683215340811, "grad_norm": 6.11415433883667, "learning_rate": 9.62238454249008e-06, "loss": 0.4194, "step": 178370 }, { "epoch": 1.0603277636107495, "grad_norm": 5.424769401550293, "learning_rate": 9.622305434617282e-06, "loss": 0.3845, "step": 178380 }, { "epoch": 1.060387205687418, "grad_norm": 4.504484176635742, "learning_rate": 9.622226318784324e-06, "loss": 0.4019, "step": 178390 }, { "epoch": 1.0604466477640864, "grad_norm": 4.16138219833374, "learning_rate": 9.62214719499134e-06, "loss": 0.4277, "step": 178400 }, { "epoch": 1.0605060898407546, "grad_norm": 4.578234672546387, "learning_rate": 9.622068063238468e-06, "loss": 0.4263, "step": 178410 }, { "epoch": 1.060565531917423, "grad_norm": 4.680465221405029, "learning_rate": 9.62198892352584e-06, "loss": 0.4026, "step": 178420 }, { "epoch": 1.0606249739940914, "grad_norm": 6.085436820983887, "learning_rate": 9.621909775853599e-06, "loss": 0.3878, "step": 178430 }, { "epoch": 1.0606844160707598, "grad_norm": 6.54771614074707, "learning_rate": 9.621830620221877e-06, "loss": 0.4091, "step": 178440 }, { "epoch": 1.0607438581474282, "grad_norm": 4.927034854888916, "learning_rate": 9.621751456630811e-06, "loss": 0.4323, "step": 178450 }, { "epoch": 1.0608033002240966, "grad_norm": 4.7512969970703125, "learning_rate": 9.621672285080537e-06, "loss": 0.406, "step": 178460 }, { "epoch": 1.060862742300765, "grad_norm": 6.965289115905762, "learning_rate": 9.621593105571192e-06, "loss": 0.3986, "step": 178470 }, { "epoch": 1.0609221843774335, "grad_norm": 6.645700454711914, "learning_rate": 9.621513918102915e-06, "loss": 0.4805, "step": 178480 }, { "epoch": 1.0609816264541019, "grad_norm": 5.26939058303833, "learning_rate": 9.621434722675836e-06, "loss": 0.4321, "step": 178490 }, { "epoch": 1.0610410685307703, "grad_norm": 5.242196559906006, "learning_rate": 9.621355519290095e-06, "loss": 0.4394, "step": 178500 }, { "epoch": 1.0611005106074385, "grad_norm": 3.6478207111358643, "learning_rate": 9.621276307945831e-06, "loss": 0.3423, "step": 178510 }, { "epoch": 1.061159952684107, "grad_norm": 5.104048728942871, "learning_rate": 9.621197088643176e-06, "loss": 0.4058, "step": 178520 }, { "epoch": 1.0612193947607753, "grad_norm": 5.38069486618042, "learning_rate": 9.621117861382268e-06, "loss": 0.454, "step": 178530 }, { "epoch": 1.0612788368374437, "grad_norm": 5.311595916748047, "learning_rate": 9.621038626163244e-06, "loss": 0.4118, "step": 178540 }, { "epoch": 1.0613382789141121, "grad_norm": 5.399930953979492, "learning_rate": 9.62095938298624e-06, "loss": 0.3712, "step": 178550 }, { "epoch": 1.0613977209907806, "grad_norm": 6.124396324157715, "learning_rate": 9.620880131851393e-06, "loss": 0.4072, "step": 178560 }, { "epoch": 1.061457163067449, "grad_norm": 4.0557708740234375, "learning_rate": 9.62080087275884e-06, "loss": 0.409, "step": 178570 }, { "epoch": 1.0615166051441174, "grad_norm": 4.366175174713135, "learning_rate": 9.620721605708715e-06, "loss": 0.4326, "step": 178580 }, { "epoch": 1.0615760472207858, "grad_norm": 5.616716384887695, "learning_rate": 9.620642330701157e-06, "loss": 0.4174, "step": 178590 }, { "epoch": 1.061635489297454, "grad_norm": 8.145273208618164, "learning_rate": 9.6205630477363e-06, "loss": 0.4, "step": 178600 }, { "epoch": 1.0616949313741224, "grad_norm": 5.134983539581299, "learning_rate": 9.620483756814285e-06, "loss": 0.4163, "step": 178610 }, { "epoch": 1.0617543734507908, "grad_norm": 6.466879367828369, "learning_rate": 9.620404457935244e-06, "loss": 0.4089, "step": 178620 }, { "epoch": 1.0618138155274592, "grad_norm": 5.023736000061035, "learning_rate": 9.620325151099314e-06, "loss": 0.4024, "step": 178630 }, { "epoch": 1.0618732576041277, "grad_norm": 6.796196937561035, "learning_rate": 9.620245836306635e-06, "loss": 0.4157, "step": 178640 }, { "epoch": 1.061932699680796, "grad_norm": 4.488569259643555, "learning_rate": 9.620166513557338e-06, "loss": 0.4183, "step": 178650 }, { "epoch": 1.0619921417574645, "grad_norm": 4.793172836303711, "learning_rate": 9.620087182851566e-06, "loss": 0.4022, "step": 178660 }, { "epoch": 1.062051583834133, "grad_norm": 5.410383224487305, "learning_rate": 9.620007844189451e-06, "loss": 0.4197, "step": 178670 }, { "epoch": 1.0621110259108013, "grad_norm": 6.622155666351318, "learning_rate": 9.619928497571133e-06, "loss": 0.4012, "step": 178680 }, { "epoch": 1.0621704679874697, "grad_norm": 5.407651901245117, "learning_rate": 9.619849142996747e-06, "loss": 0.4162, "step": 178690 }, { "epoch": 1.062229910064138, "grad_norm": 4.972201347351074, "learning_rate": 9.619769780466428e-06, "loss": 0.4159, "step": 178700 }, { "epoch": 1.0622893521408063, "grad_norm": 6.125561237335205, "learning_rate": 9.619690409980316e-06, "loss": 0.4233, "step": 178710 }, { "epoch": 1.0623487942174747, "grad_norm": 5.769628524780273, "learning_rate": 9.619611031538544e-06, "loss": 0.3888, "step": 178720 }, { "epoch": 1.0624082362941432, "grad_norm": 4.263404369354248, "learning_rate": 9.619531645141252e-06, "loss": 0.4091, "step": 178730 }, { "epoch": 1.0624676783708116, "grad_norm": 4.636998653411865, "learning_rate": 9.619452250788575e-06, "loss": 0.424, "step": 178740 }, { "epoch": 1.06252712044748, "grad_norm": 5.0420823097229, "learning_rate": 9.619372848480648e-06, "loss": 0.3879, "step": 178750 }, { "epoch": 1.0625865625241484, "grad_norm": 5.868648052215576, "learning_rate": 9.619293438217612e-06, "loss": 0.4124, "step": 178760 }, { "epoch": 1.0626460046008168, "grad_norm": 5.561692714691162, "learning_rate": 9.6192140199996e-06, "loss": 0.4258, "step": 178770 }, { "epoch": 1.062705446677485, "grad_norm": 6.174230575561523, "learning_rate": 9.619134593826753e-06, "loss": 0.412, "step": 178780 }, { "epoch": 1.0627648887541534, "grad_norm": 6.297141075134277, "learning_rate": 9.619055159699202e-06, "loss": 0.4059, "step": 178790 }, { "epoch": 1.0628243308308218, "grad_norm": 4.109051704406738, "learning_rate": 9.61897571761709e-06, "loss": 0.4256, "step": 178800 }, { "epoch": 1.0628837729074903, "grad_norm": 5.389216899871826, "learning_rate": 9.618896267580548e-06, "loss": 0.4367, "step": 178810 }, { "epoch": 1.0629432149841587, "grad_norm": 4.490933895111084, "learning_rate": 9.618816809589716e-06, "loss": 0.3792, "step": 178820 }, { "epoch": 1.063002657060827, "grad_norm": 5.704396724700928, "learning_rate": 9.61873734364473e-06, "loss": 0.3942, "step": 178830 }, { "epoch": 1.0630620991374955, "grad_norm": 6.980907917022705, "learning_rate": 9.618657869745728e-06, "loss": 0.3912, "step": 178840 }, { "epoch": 1.063121541214164, "grad_norm": 4.54275369644165, "learning_rate": 9.618578387892847e-06, "loss": 0.4199, "step": 178850 }, { "epoch": 1.0631809832908323, "grad_norm": 4.218469619750977, "learning_rate": 9.618498898086222e-06, "loss": 0.4244, "step": 178860 }, { "epoch": 1.0632404253675007, "grad_norm": 5.2293596267700195, "learning_rate": 9.618419400325992e-06, "loss": 0.4316, "step": 178870 }, { "epoch": 1.063299867444169, "grad_norm": 5.158071041107178, "learning_rate": 9.618339894612291e-06, "loss": 0.4206, "step": 178880 }, { "epoch": 1.0633593095208373, "grad_norm": 4.302239418029785, "learning_rate": 9.618260380945258e-06, "loss": 0.4044, "step": 178890 }, { "epoch": 1.0634187515975058, "grad_norm": 6.307796001434326, "learning_rate": 9.618180859325031e-06, "loss": 0.4199, "step": 178900 }, { "epoch": 1.0634781936741742, "grad_norm": 5.27219295501709, "learning_rate": 9.618101329751744e-06, "loss": 0.4066, "step": 178910 }, { "epoch": 1.0635376357508426, "grad_norm": 5.352109909057617, "learning_rate": 9.618021792225536e-06, "loss": 0.4272, "step": 178920 }, { "epoch": 1.063597077827511, "grad_norm": 4.905877590179443, "learning_rate": 9.617942246746542e-06, "loss": 0.3982, "step": 178930 }, { "epoch": 1.0636565199041794, "grad_norm": 5.730227947235107, "learning_rate": 9.617862693314901e-06, "loss": 0.3919, "step": 178940 }, { "epoch": 1.0637159619808478, "grad_norm": 5.163327217102051, "learning_rate": 9.617783131930752e-06, "loss": 0.386, "step": 178950 }, { "epoch": 1.0637754040575162, "grad_norm": 4.855451583862305, "learning_rate": 9.617703562594228e-06, "loss": 0.3497, "step": 178960 }, { "epoch": 1.0638348461341844, "grad_norm": 5.022040843963623, "learning_rate": 9.617623985305467e-06, "loss": 0.4663, "step": 178970 }, { "epoch": 1.0638942882108529, "grad_norm": 5.858051776885986, "learning_rate": 9.617544400064606e-06, "loss": 0.4149, "step": 178980 }, { "epoch": 1.0639537302875213, "grad_norm": 6.421663761138916, "learning_rate": 9.617464806871782e-06, "loss": 0.4302, "step": 178990 }, { "epoch": 1.0640131723641897, "grad_norm": 5.655284404754639, "learning_rate": 9.617385205727135e-06, "loss": 0.4528, "step": 179000 }, { "epoch": 1.064072614440858, "grad_norm": 5.204153537750244, "learning_rate": 9.617305596630798e-06, "loss": 0.3908, "step": 179010 }, { "epoch": 1.0641320565175265, "grad_norm": 5.542069435119629, "learning_rate": 9.617225979582912e-06, "loss": 0.4195, "step": 179020 }, { "epoch": 1.064191498594195, "grad_norm": 4.5971455574035645, "learning_rate": 9.617146354583608e-06, "loss": 0.3822, "step": 179030 }, { "epoch": 1.0642509406708633, "grad_norm": 6.6519060134887695, "learning_rate": 9.61706672163303e-06, "loss": 0.4247, "step": 179040 }, { "epoch": 1.0643103827475318, "grad_norm": 5.311356544494629, "learning_rate": 9.616987080731312e-06, "loss": 0.4246, "step": 179050 }, { "epoch": 1.0643698248242002, "grad_norm": 4.141584873199463, "learning_rate": 9.616907431878591e-06, "loss": 0.409, "step": 179060 }, { "epoch": 1.0644292669008684, "grad_norm": 5.032960891723633, "learning_rate": 9.616827775075004e-06, "loss": 0.3847, "step": 179070 }, { "epoch": 1.0644887089775368, "grad_norm": 5.620294570922852, "learning_rate": 9.61674811032069e-06, "loss": 0.3629, "step": 179080 }, { "epoch": 1.0645481510542052, "grad_norm": 4.762140274047852, "learning_rate": 9.616668437615784e-06, "loss": 0.4091, "step": 179090 }, { "epoch": 1.0646075931308736, "grad_norm": 4.004848480224609, "learning_rate": 9.616588756960425e-06, "loss": 0.4696, "step": 179100 }, { "epoch": 1.064667035207542, "grad_norm": 4.328904151916504, "learning_rate": 9.616509068354747e-06, "loss": 0.4079, "step": 179110 }, { "epoch": 1.0647264772842104, "grad_norm": 4.522157192230225, "learning_rate": 9.616429371798893e-06, "loss": 0.4, "step": 179120 }, { "epoch": 1.0647859193608789, "grad_norm": 5.938544750213623, "learning_rate": 9.616349667292995e-06, "loss": 0.3879, "step": 179130 }, { "epoch": 1.0648453614375473, "grad_norm": 4.621085166931152, "learning_rate": 9.616269954837192e-06, "loss": 0.4018, "step": 179140 }, { "epoch": 1.0649048035142155, "grad_norm": 5.470083236694336, "learning_rate": 9.61619023443162e-06, "loss": 0.3927, "step": 179150 }, { "epoch": 1.0649642455908839, "grad_norm": 4.592885971069336, "learning_rate": 9.61611050607642e-06, "loss": 0.4372, "step": 179160 }, { "epoch": 1.0650236876675523, "grad_norm": 6.545943260192871, "learning_rate": 9.616030769771724e-06, "loss": 0.3803, "step": 179170 }, { "epoch": 1.0650831297442207, "grad_norm": 6.849271774291992, "learning_rate": 9.615951025517676e-06, "loss": 0.4476, "step": 179180 }, { "epoch": 1.0651425718208891, "grad_norm": 4.9105730056762695, "learning_rate": 9.615871273314408e-06, "loss": 0.3742, "step": 179190 }, { "epoch": 1.0652020138975575, "grad_norm": 3.763247013092041, "learning_rate": 9.615791513162059e-06, "loss": 0.455, "step": 179200 }, { "epoch": 1.065261455974226, "grad_norm": 6.488110065460205, "learning_rate": 9.615711745060765e-06, "loss": 0.4302, "step": 179210 }, { "epoch": 1.0653208980508944, "grad_norm": 4.804760932922363, "learning_rate": 9.615631969010665e-06, "loss": 0.4213, "step": 179220 }, { "epoch": 1.0653803401275628, "grad_norm": 6.48374605178833, "learning_rate": 9.615552185011896e-06, "loss": 0.3994, "step": 179230 }, { "epoch": 1.0654397822042312, "grad_norm": 5.055665493011475, "learning_rate": 9.615472393064597e-06, "loss": 0.3787, "step": 179240 }, { "epoch": 1.0654992242808994, "grad_norm": 5.952288627624512, "learning_rate": 9.615392593168902e-06, "loss": 0.4104, "step": 179250 }, { "epoch": 1.0655586663575678, "grad_norm": 3.9845826625823975, "learning_rate": 9.61531278532495e-06, "loss": 0.399, "step": 179260 }, { "epoch": 1.0656181084342362, "grad_norm": 4.2687835693359375, "learning_rate": 9.61523296953288e-06, "loss": 0.4226, "step": 179270 }, { "epoch": 1.0656775505109046, "grad_norm": 6.879122734069824, "learning_rate": 9.615153145792828e-06, "loss": 0.4377, "step": 179280 }, { "epoch": 1.065736992587573, "grad_norm": 6.942903995513916, "learning_rate": 9.615073314104933e-06, "loss": 0.4033, "step": 179290 }, { "epoch": 1.0657964346642415, "grad_norm": 3.1552231311798096, "learning_rate": 9.614993474469328e-06, "loss": 0.3811, "step": 179300 }, { "epoch": 1.0658558767409099, "grad_norm": 5.541163444519043, "learning_rate": 9.614913626886156e-06, "loss": 0.462, "step": 179310 }, { "epoch": 1.0659153188175783, "grad_norm": 3.9175026416778564, "learning_rate": 9.614833771355551e-06, "loss": 0.3914, "step": 179320 }, { "epoch": 1.0659747608942467, "grad_norm": 8.198466300964355, "learning_rate": 9.614753907877653e-06, "loss": 0.4752, "step": 179330 }, { "epoch": 1.066034202970915, "grad_norm": 4.889994144439697, "learning_rate": 9.614674036452597e-06, "loss": 0.3903, "step": 179340 }, { "epoch": 1.0660936450475833, "grad_norm": 5.776789665222168, "learning_rate": 9.614594157080522e-06, "loss": 0.4342, "step": 179350 }, { "epoch": 1.0661530871242517, "grad_norm": 4.384695053100586, "learning_rate": 9.614514269761563e-06, "loss": 0.4129, "step": 179360 }, { "epoch": 1.0662125292009201, "grad_norm": 5.004940032958984, "learning_rate": 9.614434374495862e-06, "loss": 0.3899, "step": 179370 }, { "epoch": 1.0662719712775885, "grad_norm": 6.77382755279541, "learning_rate": 9.614354471283555e-06, "loss": 0.4062, "step": 179380 }, { "epoch": 1.066331413354257, "grad_norm": 5.1103339195251465, "learning_rate": 9.614274560124778e-06, "loss": 0.3673, "step": 179390 }, { "epoch": 1.0663908554309254, "grad_norm": 5.2267327308654785, "learning_rate": 9.61419464101967e-06, "loss": 0.4496, "step": 179400 }, { "epoch": 1.0664502975075938, "grad_norm": 5.736598014831543, "learning_rate": 9.614114713968367e-06, "loss": 0.4178, "step": 179410 }, { "epoch": 1.0665097395842622, "grad_norm": 6.056636333465576, "learning_rate": 9.61403477897101e-06, "loss": 0.355, "step": 179420 }, { "epoch": 1.0665691816609306, "grad_norm": 5.995011329650879, "learning_rate": 9.613954836027733e-06, "loss": 0.4003, "step": 179430 }, { "epoch": 1.0666286237375988, "grad_norm": 5.178785800933838, "learning_rate": 9.613874885138676e-06, "loss": 0.4238, "step": 179440 }, { "epoch": 1.0666880658142672, "grad_norm": 5.701208591461182, "learning_rate": 9.613794926303977e-06, "loss": 0.41, "step": 179450 }, { "epoch": 1.0667475078909356, "grad_norm": 5.715317249298096, "learning_rate": 9.61371495952377e-06, "loss": 0.4168, "step": 179460 }, { "epoch": 1.066806949967604, "grad_norm": 5.580372333526611, "learning_rate": 9.613634984798198e-06, "loss": 0.4033, "step": 179470 }, { "epoch": 1.0668663920442725, "grad_norm": 6.251271724700928, "learning_rate": 9.613555002127394e-06, "loss": 0.4002, "step": 179480 }, { "epoch": 1.0669258341209409, "grad_norm": 4.908166408538818, "learning_rate": 9.6134750115115e-06, "loss": 0.3625, "step": 179490 }, { "epoch": 1.0669852761976093, "grad_norm": 7.71750545501709, "learning_rate": 9.613395012950647e-06, "loss": 0.3907, "step": 179500 }, { "epoch": 1.0670447182742777, "grad_norm": 4.614062309265137, "learning_rate": 9.613315006444983e-06, "loss": 0.419, "step": 179510 }, { "epoch": 1.067104160350946, "grad_norm": 5.249557971954346, "learning_rate": 9.613234991994638e-06, "loss": 0.4171, "step": 179520 }, { "epoch": 1.0671636024276143, "grad_norm": 5.448129177093506, "learning_rate": 9.61315496959975e-06, "loss": 0.4406, "step": 179530 }, { "epoch": 1.0672230445042827, "grad_norm": 4.953744888305664, "learning_rate": 9.613074939260461e-06, "loss": 0.4046, "step": 179540 }, { "epoch": 1.0672824865809512, "grad_norm": 5.342827320098877, "learning_rate": 9.612994900976906e-06, "loss": 0.4006, "step": 179550 }, { "epoch": 1.0673419286576196, "grad_norm": 6.3245415687561035, "learning_rate": 9.612914854749222e-06, "loss": 0.4427, "step": 179560 }, { "epoch": 1.067401370734288, "grad_norm": 5.576999187469482, "learning_rate": 9.61283480057755e-06, "loss": 0.4299, "step": 179570 }, { "epoch": 1.0674608128109564, "grad_norm": 5.449728965759277, "learning_rate": 9.612754738462026e-06, "loss": 0.4305, "step": 179580 }, { "epoch": 1.0675202548876248, "grad_norm": 4.200551986694336, "learning_rate": 9.612674668402787e-06, "loss": 0.4, "step": 179590 }, { "epoch": 1.0675796969642932, "grad_norm": 4.8066253662109375, "learning_rate": 9.612594590399973e-06, "loss": 0.4056, "step": 179600 }, { "epoch": 1.0676391390409616, "grad_norm": 7.286642074584961, "learning_rate": 9.612514504453719e-06, "loss": 0.4172, "step": 179610 }, { "epoch": 1.0676985811176298, "grad_norm": 6.201486110687256, "learning_rate": 9.612434410564167e-06, "loss": 0.3979, "step": 179620 }, { "epoch": 1.0677580231942982, "grad_norm": 4.750782012939453, "learning_rate": 9.61235430873145e-06, "loss": 0.4049, "step": 179630 }, { "epoch": 1.0678174652709667, "grad_norm": 6.259632587432861, "learning_rate": 9.612274198955708e-06, "loss": 0.4413, "step": 179640 }, { "epoch": 1.067876907347635, "grad_norm": 3.9395549297332764, "learning_rate": 9.612194081237083e-06, "loss": 0.4066, "step": 179650 }, { "epoch": 1.0679363494243035, "grad_norm": 5.478960990905762, "learning_rate": 9.612113955575708e-06, "loss": 0.4184, "step": 179660 }, { "epoch": 1.067995791500972, "grad_norm": 5.009877681732178, "learning_rate": 9.612033821971723e-06, "loss": 0.4174, "step": 179670 }, { "epoch": 1.0680552335776403, "grad_norm": 5.571063041687012, "learning_rate": 9.611953680425263e-06, "loss": 0.3922, "step": 179680 }, { "epoch": 1.0681146756543087, "grad_norm": 5.274011611938477, "learning_rate": 9.61187353093647e-06, "loss": 0.3856, "step": 179690 }, { "epoch": 1.0681741177309771, "grad_norm": 5.073701858520508, "learning_rate": 9.611793373505481e-06, "loss": 0.3992, "step": 179700 }, { "epoch": 1.0682335598076453, "grad_norm": 5.329071521759033, "learning_rate": 9.611713208132433e-06, "loss": 0.4024, "step": 179710 }, { "epoch": 1.0682930018843138, "grad_norm": 6.132817268371582, "learning_rate": 9.611633034817465e-06, "loss": 0.4245, "step": 179720 }, { "epoch": 1.0683524439609822, "grad_norm": 3.9061403274536133, "learning_rate": 9.611552853560715e-06, "loss": 0.4027, "step": 179730 }, { "epoch": 1.0684118860376506, "grad_norm": 5.4945783615112305, "learning_rate": 9.61147266436232e-06, "loss": 0.44, "step": 179740 }, { "epoch": 1.068471328114319, "grad_norm": 5.958047389984131, "learning_rate": 9.611392467222419e-06, "loss": 0.3997, "step": 179750 }, { "epoch": 1.0685307701909874, "grad_norm": 6.517532825469971, "learning_rate": 9.61131226214115e-06, "loss": 0.4118, "step": 179760 }, { "epoch": 1.0685902122676558, "grad_norm": 3.918097496032715, "learning_rate": 9.61123204911865e-06, "loss": 0.4078, "step": 179770 }, { "epoch": 1.0686496543443242, "grad_norm": 5.782526016235352, "learning_rate": 9.611151828155061e-06, "loss": 0.4232, "step": 179780 }, { "epoch": 1.0687090964209927, "grad_norm": 4.879267692565918, "learning_rate": 9.611071599250517e-06, "loss": 0.4008, "step": 179790 }, { "epoch": 1.068768538497661, "grad_norm": 5.482508659362793, "learning_rate": 9.610991362405156e-06, "loss": 0.4137, "step": 179800 }, { "epoch": 1.0688279805743293, "grad_norm": 6.362313747406006, "learning_rate": 9.61091111761912e-06, "loss": 0.4244, "step": 179810 }, { "epoch": 1.0688874226509977, "grad_norm": 5.587493419647217, "learning_rate": 9.610830864892544e-06, "loss": 0.3893, "step": 179820 }, { "epoch": 1.068946864727666, "grad_norm": 5.658544063568115, "learning_rate": 9.610750604225565e-06, "loss": 0.4189, "step": 179830 }, { "epoch": 1.0690063068043345, "grad_norm": 4.348601341247559, "learning_rate": 9.610670335618325e-06, "loss": 0.3748, "step": 179840 }, { "epoch": 1.069065748881003, "grad_norm": 4.288938522338867, "learning_rate": 9.610590059070961e-06, "loss": 0.424, "step": 179850 }, { "epoch": 1.0691251909576713, "grad_norm": 6.591076850891113, "learning_rate": 9.61050977458361e-06, "loss": 0.4497, "step": 179860 }, { "epoch": 1.0691846330343397, "grad_norm": 4.745572090148926, "learning_rate": 9.610429482156412e-06, "loss": 0.4032, "step": 179870 }, { "epoch": 1.0692440751110082, "grad_norm": 4.219250202178955, "learning_rate": 9.610349181789504e-06, "loss": 0.4006, "step": 179880 }, { "epoch": 1.0693035171876764, "grad_norm": 4.077481269836426, "learning_rate": 9.610268873483024e-06, "loss": 0.4271, "step": 179890 }, { "epoch": 1.0693629592643448, "grad_norm": 5.807762145996094, "learning_rate": 9.610188557237113e-06, "loss": 0.3621, "step": 179900 }, { "epoch": 1.0694224013410132, "grad_norm": 5.507626533508301, "learning_rate": 9.610108233051905e-06, "loss": 0.3769, "step": 179910 }, { "epoch": 1.0694818434176816, "grad_norm": 4.194027900695801, "learning_rate": 9.610027900927541e-06, "loss": 0.3827, "step": 179920 }, { "epoch": 1.06954128549435, "grad_norm": 4.750702381134033, "learning_rate": 9.60994756086416e-06, "loss": 0.4023, "step": 179930 }, { "epoch": 1.0696007275710184, "grad_norm": 5.024151802062988, "learning_rate": 9.609867212861898e-06, "loss": 0.4209, "step": 179940 }, { "epoch": 1.0696601696476868, "grad_norm": 6.404874801635742, "learning_rate": 9.609786856920896e-06, "loss": 0.4528, "step": 179950 }, { "epoch": 1.0697196117243553, "grad_norm": 3.8324265480041504, "learning_rate": 9.609706493041289e-06, "loss": 0.3873, "step": 179960 }, { "epoch": 1.0697790538010237, "grad_norm": 4.838727951049805, "learning_rate": 9.609626121223218e-06, "loss": 0.3895, "step": 179970 }, { "epoch": 1.069838495877692, "grad_norm": 6.059088230133057, "learning_rate": 9.609545741466821e-06, "loss": 0.4028, "step": 179980 }, { "epoch": 1.0698979379543603, "grad_norm": 6.804038047790527, "learning_rate": 9.609465353772236e-06, "loss": 0.4085, "step": 179990 }, { "epoch": 1.0699573800310287, "grad_norm": 5.229974269866943, "learning_rate": 9.609384958139602e-06, "loss": 0.4287, "step": 180000 }, { "epoch": 1.070016822107697, "grad_norm": 6.308681964874268, "learning_rate": 9.609304554569056e-06, "loss": 0.4309, "step": 180010 }, { "epoch": 1.0700762641843655, "grad_norm": 5.607819557189941, "learning_rate": 9.609224143060741e-06, "loss": 0.3693, "step": 180020 }, { "epoch": 1.070135706261034, "grad_norm": 4.912829399108887, "learning_rate": 9.609143723614789e-06, "loss": 0.3821, "step": 180030 }, { "epoch": 1.0701951483377024, "grad_norm": 4.910843849182129, "learning_rate": 9.609063296231343e-06, "loss": 0.4364, "step": 180040 }, { "epoch": 1.0702545904143708, "grad_norm": 5.729221343994141, "learning_rate": 9.608982860910538e-06, "loss": 0.4424, "step": 180050 }, { "epoch": 1.0703140324910392, "grad_norm": 6.301687240600586, "learning_rate": 9.608902417652516e-06, "loss": 0.4259, "step": 180060 }, { "epoch": 1.0703734745677076, "grad_norm": 5.12790584564209, "learning_rate": 9.608821966457416e-06, "loss": 0.4057, "step": 180070 }, { "epoch": 1.0704329166443758, "grad_norm": 5.877440929412842, "learning_rate": 9.608741507325372e-06, "loss": 0.4577, "step": 180080 }, { "epoch": 1.0704923587210442, "grad_norm": 3.9426028728485107, "learning_rate": 9.608661040256527e-06, "loss": 0.4035, "step": 180090 }, { "epoch": 1.0705518007977126, "grad_norm": 4.717446327209473, "learning_rate": 9.608580565251015e-06, "loss": 0.3791, "step": 180100 }, { "epoch": 1.070611242874381, "grad_norm": 3.980299472808838, "learning_rate": 9.60850008230898e-06, "loss": 0.3824, "step": 180110 }, { "epoch": 1.0706706849510494, "grad_norm": 4.526102542877197, "learning_rate": 9.608419591430557e-06, "loss": 0.3947, "step": 180120 }, { "epoch": 1.0707301270277179, "grad_norm": 7.731820583343506, "learning_rate": 9.608339092615886e-06, "loss": 0.3972, "step": 180130 }, { "epoch": 1.0707895691043863, "grad_norm": 6.463336944580078, "learning_rate": 9.608258585865104e-06, "loss": 0.3993, "step": 180140 }, { "epoch": 1.0708490111810547, "grad_norm": 5.811680793762207, "learning_rate": 9.60817807117835e-06, "loss": 0.3953, "step": 180150 }, { "epoch": 1.070908453257723, "grad_norm": 5.44295597076416, "learning_rate": 9.608097548555768e-06, "loss": 0.3874, "step": 180160 }, { "epoch": 1.0709678953343915, "grad_norm": 4.872737884521484, "learning_rate": 9.608017017997488e-06, "loss": 0.4288, "step": 180170 }, { "epoch": 1.0710273374110597, "grad_norm": 5.259539604187012, "learning_rate": 9.607936479503656e-06, "loss": 0.3703, "step": 180180 }, { "epoch": 1.0710867794877281, "grad_norm": 5.223438262939453, "learning_rate": 9.607855933074405e-06, "loss": 0.3979, "step": 180190 }, { "epoch": 1.0711462215643965, "grad_norm": 5.119017124176025, "learning_rate": 9.607775378709879e-06, "loss": 0.3952, "step": 180200 }, { "epoch": 1.071205663641065, "grad_norm": 4.927855491638184, "learning_rate": 9.60769481641021e-06, "loss": 0.3971, "step": 180210 }, { "epoch": 1.0712651057177334, "grad_norm": 5.868988037109375, "learning_rate": 9.607614246175545e-06, "loss": 0.4402, "step": 180220 }, { "epoch": 1.0713245477944018, "grad_norm": 5.2042999267578125, "learning_rate": 9.607533668006014e-06, "loss": 0.422, "step": 180230 }, { "epoch": 1.0713839898710702, "grad_norm": 4.948232650756836, "learning_rate": 9.607453081901764e-06, "loss": 0.3921, "step": 180240 }, { "epoch": 1.0714434319477386, "grad_norm": 4.826174736022949, "learning_rate": 9.60737248786293e-06, "loss": 0.4139, "step": 180250 }, { "epoch": 1.0715028740244068, "grad_norm": 5.5215654373168945, "learning_rate": 9.60729188588965e-06, "loss": 0.4093, "step": 180260 }, { "epoch": 1.0715623161010752, "grad_norm": 5.367963790893555, "learning_rate": 9.607211275982062e-06, "loss": 0.422, "step": 180270 }, { "epoch": 1.0716217581777436, "grad_norm": 6.730320930480957, "learning_rate": 9.607130658140308e-06, "loss": 0.4311, "step": 180280 }, { "epoch": 1.071681200254412, "grad_norm": 4.681067943572998, "learning_rate": 9.607050032364524e-06, "loss": 0.4304, "step": 180290 }, { "epoch": 1.0717406423310805, "grad_norm": 5.2549357414245605, "learning_rate": 9.606969398654852e-06, "loss": 0.4176, "step": 180300 }, { "epoch": 1.0718000844077489, "grad_norm": 6.228194236755371, "learning_rate": 9.606888757011427e-06, "loss": 0.4134, "step": 180310 }, { "epoch": 1.0718595264844173, "grad_norm": 3.8068904876708984, "learning_rate": 9.606808107434392e-06, "loss": 0.3664, "step": 180320 }, { "epoch": 1.0719189685610857, "grad_norm": 6.209715366363525, "learning_rate": 9.606727449923882e-06, "loss": 0.4103, "step": 180330 }, { "epoch": 1.0719784106377541, "grad_norm": 5.8191704750061035, "learning_rate": 9.60664678448004e-06, "loss": 0.4035, "step": 180340 }, { "epoch": 1.0720378527144225, "grad_norm": 5.743919849395752, "learning_rate": 9.606566111103e-06, "loss": 0.4352, "step": 180350 }, { "epoch": 1.0720972947910907, "grad_norm": 5.541680812835693, "learning_rate": 9.606485429792904e-06, "loss": 0.4205, "step": 180360 }, { "epoch": 1.0721567368677591, "grad_norm": 5.673117637634277, "learning_rate": 9.606404740549892e-06, "loss": 0.4252, "step": 180370 }, { "epoch": 1.0722161789444276, "grad_norm": 4.680668830871582, "learning_rate": 9.6063240433741e-06, "loss": 0.402, "step": 180380 }, { "epoch": 1.072275621021096, "grad_norm": 6.392832279205322, "learning_rate": 9.60624333826567e-06, "loss": 0.4127, "step": 180390 }, { "epoch": 1.0723350630977644, "grad_norm": 4.707252025604248, "learning_rate": 9.606162625224738e-06, "loss": 0.3871, "step": 180400 }, { "epoch": 1.0723945051744328, "grad_norm": 5.457065582275391, "learning_rate": 9.606081904251445e-06, "loss": 0.4061, "step": 180410 }, { "epoch": 1.0724539472511012, "grad_norm": 5.296030044555664, "learning_rate": 9.606001175345929e-06, "loss": 0.4135, "step": 180420 }, { "epoch": 1.0725133893277696, "grad_norm": 5.571611404418945, "learning_rate": 9.605920438508329e-06, "loss": 0.4122, "step": 180430 }, { "epoch": 1.072572831404438, "grad_norm": 7.071409225463867, "learning_rate": 9.605839693738785e-06, "loss": 0.3761, "step": 180440 }, { "epoch": 1.0726322734811062, "grad_norm": 5.579750061035156, "learning_rate": 9.605758941037433e-06, "loss": 0.5042, "step": 180450 }, { "epoch": 1.0726917155577746, "grad_norm": 4.584804534912109, "learning_rate": 9.605678180404418e-06, "loss": 0.3847, "step": 180460 }, { "epoch": 1.072751157634443, "grad_norm": 5.042179584503174, "learning_rate": 9.605597411839874e-06, "loss": 0.3983, "step": 180470 }, { "epoch": 1.0728105997111115, "grad_norm": 6.727593898773193, "learning_rate": 9.605516635343944e-06, "loss": 0.3879, "step": 180480 }, { "epoch": 1.07287004178778, "grad_norm": 6.14656400680542, "learning_rate": 9.605435850916763e-06, "loss": 0.4207, "step": 180490 }, { "epoch": 1.0729294838644483, "grad_norm": 4.908951282501221, "learning_rate": 9.60535505855847e-06, "loss": 0.4151, "step": 180500 }, { "epoch": 1.0729889259411167, "grad_norm": 5.2301740646362305, "learning_rate": 9.605274258269209e-06, "loss": 0.3637, "step": 180510 }, { "epoch": 1.0730483680177851, "grad_norm": 4.342747688293457, "learning_rate": 9.605193450049115e-06, "loss": 0.3981, "step": 180520 }, { "epoch": 1.0731078100944536, "grad_norm": 4.539994716644287, "learning_rate": 9.605112633898328e-06, "loss": 0.398, "step": 180530 }, { "epoch": 1.073167252171122, "grad_norm": 4.32936429977417, "learning_rate": 9.60503180981699e-06, "loss": 0.4092, "step": 180540 }, { "epoch": 1.0732266942477902, "grad_norm": 5.449431419372559, "learning_rate": 9.604950977805234e-06, "loss": 0.4304, "step": 180550 }, { "epoch": 1.0732861363244586, "grad_norm": 4.499675273895264, "learning_rate": 9.604870137863206e-06, "loss": 0.4087, "step": 180560 }, { "epoch": 1.073345578401127, "grad_norm": 6.264312267303467, "learning_rate": 9.604789289991042e-06, "loss": 0.4235, "step": 180570 }, { "epoch": 1.0734050204777954, "grad_norm": 6.595600605010986, "learning_rate": 9.604708434188879e-06, "loss": 0.4834, "step": 180580 }, { "epoch": 1.0734644625544638, "grad_norm": 4.307767868041992, "learning_rate": 9.604627570456861e-06, "loss": 0.3516, "step": 180590 }, { "epoch": 1.0735239046311322, "grad_norm": 6.325448036193848, "learning_rate": 9.604546698795122e-06, "loss": 0.3917, "step": 180600 }, { "epoch": 1.0735833467078006, "grad_norm": 5.714720726013184, "learning_rate": 9.604465819203807e-06, "loss": 0.3494, "step": 180610 }, { "epoch": 1.073642788784469, "grad_norm": 4.832814693450928, "learning_rate": 9.604384931683054e-06, "loss": 0.3631, "step": 180620 }, { "epoch": 1.0737022308611373, "grad_norm": 6.784504413604736, "learning_rate": 9.604304036232996e-06, "loss": 0.4659, "step": 180630 }, { "epoch": 1.0737616729378057, "grad_norm": 4.5213212966918945, "learning_rate": 9.60422313285378e-06, "loss": 0.3655, "step": 180640 }, { "epoch": 1.073821115014474, "grad_norm": 5.438058376312256, "learning_rate": 9.604142221545543e-06, "loss": 0.4277, "step": 180650 }, { "epoch": 1.0738805570911425, "grad_norm": 4.547152042388916, "learning_rate": 9.604061302308422e-06, "loss": 0.4006, "step": 180660 }, { "epoch": 1.073939999167811, "grad_norm": 4.3097357749938965, "learning_rate": 9.60398037514256e-06, "loss": 0.3892, "step": 180670 }, { "epoch": 1.0739994412444793, "grad_norm": 5.82790470123291, "learning_rate": 9.603899440048092e-06, "loss": 0.3855, "step": 180680 }, { "epoch": 1.0740588833211477, "grad_norm": 5.639772415161133, "learning_rate": 9.603818497025161e-06, "loss": 0.4005, "step": 180690 }, { "epoch": 1.0741183253978162, "grad_norm": 4.542818546295166, "learning_rate": 9.603737546073905e-06, "loss": 0.3828, "step": 180700 }, { "epoch": 1.0741777674744846, "grad_norm": 6.272717475891113, "learning_rate": 9.603656587194465e-06, "loss": 0.3668, "step": 180710 }, { "epoch": 1.074237209551153, "grad_norm": 7.123697280883789, "learning_rate": 9.603575620386977e-06, "loss": 0.4135, "step": 180720 }, { "epoch": 1.0742966516278212, "grad_norm": 6.452030181884766, "learning_rate": 9.603494645651585e-06, "loss": 0.4418, "step": 180730 }, { "epoch": 1.0743560937044896, "grad_norm": 5.185362339019775, "learning_rate": 9.603413662988423e-06, "loss": 0.4474, "step": 180740 }, { "epoch": 1.074415535781158, "grad_norm": 4.892202854156494, "learning_rate": 9.603332672397636e-06, "loss": 0.41, "step": 180750 }, { "epoch": 1.0744749778578264, "grad_norm": 3.9439454078674316, "learning_rate": 9.60325167387936e-06, "loss": 0.4029, "step": 180760 }, { "epoch": 1.0745344199344948, "grad_norm": 5.914945602416992, "learning_rate": 9.603170667433734e-06, "loss": 0.4254, "step": 180770 }, { "epoch": 1.0745938620111632, "grad_norm": 5.901427745819092, "learning_rate": 9.6030896530609e-06, "loss": 0.4004, "step": 180780 }, { "epoch": 1.0746533040878317, "grad_norm": 6.420494556427002, "learning_rate": 9.603008630760997e-06, "loss": 0.4166, "step": 180790 }, { "epoch": 1.0747127461645, "grad_norm": 4.515726089477539, "learning_rate": 9.602927600534162e-06, "loss": 0.4339, "step": 180800 }, { "epoch": 1.0747721882411685, "grad_norm": 5.321881294250488, "learning_rate": 9.602846562380539e-06, "loss": 0.3867, "step": 180810 }, { "epoch": 1.0748316303178367, "grad_norm": 5.210238933563232, "learning_rate": 9.602765516300263e-06, "loss": 0.4085, "step": 180820 }, { "epoch": 1.074891072394505, "grad_norm": 5.272916316986084, "learning_rate": 9.602684462293476e-06, "loss": 0.411, "step": 180830 }, { "epoch": 1.0749505144711735, "grad_norm": 4.803592681884766, "learning_rate": 9.60260340036032e-06, "loss": 0.3849, "step": 180840 }, { "epoch": 1.075009956547842, "grad_norm": 4.356727600097656, "learning_rate": 9.602522330500928e-06, "loss": 0.4229, "step": 180850 }, { "epoch": 1.0750693986245103, "grad_norm": 5.737023830413818, "learning_rate": 9.602441252715445e-06, "loss": 0.4386, "step": 180860 }, { "epoch": 1.0751288407011788, "grad_norm": 4.280793190002441, "learning_rate": 9.602360167004008e-06, "loss": 0.4148, "step": 180870 }, { "epoch": 1.0751882827778472, "grad_norm": 6.948132038116455, "learning_rate": 9.602279073366759e-06, "loss": 0.4529, "step": 180880 }, { "epoch": 1.0752477248545156, "grad_norm": 4.217682838439941, "learning_rate": 9.602197971803836e-06, "loss": 0.3997, "step": 180890 }, { "epoch": 1.075307166931184, "grad_norm": 5.141833782196045, "learning_rate": 9.602116862315378e-06, "loss": 0.4226, "step": 180900 }, { "epoch": 1.0753666090078524, "grad_norm": 4.736135959625244, "learning_rate": 9.602035744901526e-06, "loss": 0.3886, "step": 180910 }, { "epoch": 1.0754260510845206, "grad_norm": 7.206012725830078, "learning_rate": 9.601954619562418e-06, "loss": 0.4751, "step": 180920 }, { "epoch": 1.075485493161189, "grad_norm": 4.617943286895752, "learning_rate": 9.601873486298198e-06, "loss": 0.4311, "step": 180930 }, { "epoch": 1.0755449352378574, "grad_norm": 5.094822406768799, "learning_rate": 9.601792345109002e-06, "loss": 0.4147, "step": 180940 }, { "epoch": 1.0756043773145259, "grad_norm": 6.238468170166016, "learning_rate": 9.601711195994969e-06, "loss": 0.4097, "step": 180950 }, { "epoch": 1.0756638193911943, "grad_norm": 5.33305025100708, "learning_rate": 9.601630038956241e-06, "loss": 0.4051, "step": 180960 }, { "epoch": 1.0757232614678627, "grad_norm": 4.406291961669922, "learning_rate": 9.601548873992958e-06, "loss": 0.4362, "step": 180970 }, { "epoch": 1.075782703544531, "grad_norm": 4.825191497802734, "learning_rate": 9.601467701105256e-06, "loss": 0.3963, "step": 180980 }, { "epoch": 1.0758421456211995, "grad_norm": 6.145584583282471, "learning_rate": 9.60138652029328e-06, "loss": 0.3999, "step": 180990 }, { "epoch": 1.0759015876978677, "grad_norm": 4.277316570281982, "learning_rate": 9.601305331557167e-06, "loss": 0.3613, "step": 181000 }, { "epoch": 1.0759610297745361, "grad_norm": 4.736281871795654, "learning_rate": 9.601224134897059e-06, "loss": 0.3545, "step": 181010 }, { "epoch": 1.0760204718512045, "grad_norm": 4.134829044342041, "learning_rate": 9.601142930313091e-06, "loss": 0.455, "step": 181020 }, { "epoch": 1.076079913927873, "grad_norm": 4.276007175445557, "learning_rate": 9.601061717805407e-06, "loss": 0.4349, "step": 181030 }, { "epoch": 1.0761393560045414, "grad_norm": 5.411377429962158, "learning_rate": 9.600980497374145e-06, "loss": 0.4275, "step": 181040 }, { "epoch": 1.0761987980812098, "grad_norm": 5.78368616104126, "learning_rate": 9.600899269019447e-06, "loss": 0.465, "step": 181050 }, { "epoch": 1.0762582401578782, "grad_norm": 4.980220317840576, "learning_rate": 9.600818032741451e-06, "loss": 0.4035, "step": 181060 }, { "epoch": 1.0763176822345466, "grad_norm": 6.0810651779174805, "learning_rate": 9.600736788540297e-06, "loss": 0.4502, "step": 181070 }, { "epoch": 1.076377124311215, "grad_norm": 5.402539253234863, "learning_rate": 9.600655536416126e-06, "loss": 0.421, "step": 181080 }, { "epoch": 1.0764365663878834, "grad_norm": 3.859349012374878, "learning_rate": 9.600574276369076e-06, "loss": 0.4181, "step": 181090 }, { "epoch": 1.0764960084645516, "grad_norm": 5.784066200256348, "learning_rate": 9.60049300839929e-06, "loss": 0.4026, "step": 181100 }, { "epoch": 1.07655545054122, "grad_norm": 6.07493782043457, "learning_rate": 9.600411732506905e-06, "loss": 0.4289, "step": 181110 }, { "epoch": 1.0766148926178885, "grad_norm": 3.7559285163879395, "learning_rate": 9.600330448692062e-06, "loss": 0.3768, "step": 181120 }, { "epoch": 1.0766743346945569, "grad_norm": 5.2147111892700195, "learning_rate": 9.600249156954901e-06, "loss": 0.4306, "step": 181130 }, { "epoch": 1.0767337767712253, "grad_norm": 4.611854553222656, "learning_rate": 9.600167857295561e-06, "loss": 0.36, "step": 181140 }, { "epoch": 1.0767932188478937, "grad_norm": 6.396035671234131, "learning_rate": 9.600086549714184e-06, "loss": 0.452, "step": 181150 }, { "epoch": 1.076852660924562, "grad_norm": 5.044165134429932, "learning_rate": 9.60000523421091e-06, "loss": 0.3562, "step": 181160 }, { "epoch": 1.0769121030012305, "grad_norm": 4.205066680908203, "learning_rate": 9.599923910785877e-06, "loss": 0.3865, "step": 181170 }, { "epoch": 1.076971545077899, "grad_norm": 3.835069417953491, "learning_rate": 9.599842579439228e-06, "loss": 0.3845, "step": 181180 }, { "epoch": 1.0770309871545671, "grad_norm": 4.904399394989014, "learning_rate": 9.599761240171099e-06, "loss": 0.4061, "step": 181190 }, { "epoch": 1.0770904292312355, "grad_norm": 5.633236408233643, "learning_rate": 9.599679892981633e-06, "loss": 0.4597, "step": 181200 }, { "epoch": 1.077149871307904, "grad_norm": 5.135535717010498, "learning_rate": 9.599598537870971e-06, "loss": 0.4103, "step": 181210 }, { "epoch": 1.0772093133845724, "grad_norm": 5.93950891494751, "learning_rate": 9.59951717483925e-06, "loss": 0.4235, "step": 181220 }, { "epoch": 1.0772687554612408, "grad_norm": 5.825464725494385, "learning_rate": 9.599435803886613e-06, "loss": 0.4113, "step": 181230 }, { "epoch": 1.0773281975379092, "grad_norm": 4.9349284172058105, "learning_rate": 9.599354425013197e-06, "loss": 0.4089, "step": 181240 }, { "epoch": 1.0773876396145776, "grad_norm": 6.0931782722473145, "learning_rate": 9.599273038219144e-06, "loss": 0.392, "step": 181250 }, { "epoch": 1.077447081691246, "grad_norm": 5.62453556060791, "learning_rate": 9.599191643504594e-06, "loss": 0.4262, "step": 181260 }, { "epoch": 1.0775065237679144, "grad_norm": 6.113168239593506, "learning_rate": 9.599110240869687e-06, "loss": 0.4047, "step": 181270 }, { "epoch": 1.0775659658445829, "grad_norm": 6.030972480773926, "learning_rate": 9.599028830314566e-06, "loss": 0.4535, "step": 181280 }, { "epoch": 1.077625407921251, "grad_norm": 4.807823181152344, "learning_rate": 9.598947411839366e-06, "loss": 0.4184, "step": 181290 }, { "epoch": 1.0776848499979195, "grad_norm": 5.8420844078063965, "learning_rate": 9.59886598544423e-06, "loss": 0.4021, "step": 181300 }, { "epoch": 1.0777442920745879, "grad_norm": 4.562736511230469, "learning_rate": 9.598784551129299e-06, "loss": 0.4044, "step": 181310 }, { "epoch": 1.0778037341512563, "grad_norm": 4.255387783050537, "learning_rate": 9.598703108894712e-06, "loss": 0.4338, "step": 181320 }, { "epoch": 1.0778631762279247, "grad_norm": 6.168476104736328, "learning_rate": 9.598621658740609e-06, "loss": 0.3955, "step": 181330 }, { "epoch": 1.0779226183045931, "grad_norm": 4.9014058113098145, "learning_rate": 9.59854020066713e-06, "loss": 0.3833, "step": 181340 }, { "epoch": 1.0779820603812615, "grad_norm": 5.064899921417236, "learning_rate": 9.598458734674418e-06, "loss": 0.3967, "step": 181350 }, { "epoch": 1.07804150245793, "grad_norm": 4.737982749938965, "learning_rate": 9.59837726076261e-06, "loss": 0.3986, "step": 181360 }, { "epoch": 1.0781009445345981, "grad_norm": 6.2263031005859375, "learning_rate": 9.59829577893185e-06, "loss": 0.4251, "step": 181370 }, { "epoch": 1.0781603866112666, "grad_norm": 6.686954498291016, "learning_rate": 9.598214289182273e-06, "loss": 0.4498, "step": 181380 }, { "epoch": 1.078219828687935, "grad_norm": 6.753884315490723, "learning_rate": 9.598132791514025e-06, "loss": 0.4387, "step": 181390 }, { "epoch": 1.0782792707646034, "grad_norm": 5.0947794914245605, "learning_rate": 9.598051285927242e-06, "loss": 0.434, "step": 181400 }, { "epoch": 1.0783387128412718, "grad_norm": 5.120026588439941, "learning_rate": 9.597969772422066e-06, "loss": 0.3767, "step": 181410 }, { "epoch": 1.0783981549179402, "grad_norm": 5.66906213760376, "learning_rate": 9.597888250998638e-06, "loss": 0.4027, "step": 181420 }, { "epoch": 1.0784575969946086, "grad_norm": 4.667331695556641, "learning_rate": 9.597806721657097e-06, "loss": 0.4436, "step": 181430 }, { "epoch": 1.078517039071277, "grad_norm": 5.777091979980469, "learning_rate": 9.597725184397587e-06, "loss": 0.4007, "step": 181440 }, { "epoch": 1.0785764811479455, "grad_norm": 7.267655372619629, "learning_rate": 9.597643639220243e-06, "loss": 0.4517, "step": 181450 }, { "epoch": 1.0786359232246139, "grad_norm": 6.7261810302734375, "learning_rate": 9.597562086125208e-06, "loss": 0.3966, "step": 181460 }, { "epoch": 1.078695365301282, "grad_norm": 6.132227897644043, "learning_rate": 9.597480525112624e-06, "loss": 0.3738, "step": 181470 }, { "epoch": 1.0787548073779505, "grad_norm": 4.775149345397949, "learning_rate": 9.59739895618263e-06, "loss": 0.385, "step": 181480 }, { "epoch": 1.078814249454619, "grad_norm": 3.977199077606201, "learning_rate": 9.597317379335364e-06, "loss": 0.4433, "step": 181490 }, { "epoch": 1.0788736915312873, "grad_norm": 6.027193546295166, "learning_rate": 9.59723579457097e-06, "loss": 0.4137, "step": 181500 }, { "epoch": 1.0789331336079557, "grad_norm": 4.783392429351807, "learning_rate": 9.597154201889587e-06, "loss": 0.3837, "step": 181510 }, { "epoch": 1.0789925756846241, "grad_norm": 3.826918601989746, "learning_rate": 9.597072601291357e-06, "loss": 0.3661, "step": 181520 }, { "epoch": 1.0790520177612926, "grad_norm": 4.088207721710205, "learning_rate": 9.59699099277642e-06, "loss": 0.3899, "step": 181530 }, { "epoch": 1.079111459837961, "grad_norm": 5.661794185638428, "learning_rate": 9.596909376344917e-06, "loss": 0.3548, "step": 181540 }, { "epoch": 1.0791709019146294, "grad_norm": 6.857457637786865, "learning_rate": 9.596827751996984e-06, "loss": 0.3835, "step": 181550 }, { "epoch": 1.0792303439912976, "grad_norm": 2.9941768646240234, "learning_rate": 9.596746119732767e-06, "loss": 0.3663, "step": 181560 }, { "epoch": 1.079289786067966, "grad_norm": 6.183431625366211, "learning_rate": 9.596664479552405e-06, "loss": 0.4378, "step": 181570 }, { "epoch": 1.0793492281446344, "grad_norm": 4.4117431640625, "learning_rate": 9.596582831456038e-06, "loss": 0.4079, "step": 181580 }, { "epoch": 1.0794086702213028, "grad_norm": 4.482938289642334, "learning_rate": 9.596501175443806e-06, "loss": 0.4304, "step": 181590 }, { "epoch": 1.0794681122979712, "grad_norm": 5.538557529449463, "learning_rate": 9.596419511515854e-06, "loss": 0.4386, "step": 181600 }, { "epoch": 1.0795275543746397, "grad_norm": 5.387031078338623, "learning_rate": 9.596337839672315e-06, "loss": 0.416, "step": 181610 }, { "epoch": 1.079586996451308, "grad_norm": 4.104781150817871, "learning_rate": 9.596256159913335e-06, "loss": 0.4199, "step": 181620 }, { "epoch": 1.0796464385279765, "grad_norm": 5.630746841430664, "learning_rate": 9.596174472239054e-06, "loss": 0.4065, "step": 181630 }, { "epoch": 1.079705880604645, "grad_norm": 5.014960765838623, "learning_rate": 9.596092776649613e-06, "loss": 0.3922, "step": 181640 }, { "epoch": 1.0797653226813133, "grad_norm": 5.988407611846924, "learning_rate": 9.59601107314515e-06, "loss": 0.4144, "step": 181650 }, { "epoch": 1.0798247647579815, "grad_norm": 6.119176864624023, "learning_rate": 9.595929361725808e-06, "loss": 0.4197, "step": 181660 }, { "epoch": 1.07988420683465, "grad_norm": 5.972064971923828, "learning_rate": 9.59584764239173e-06, "loss": 0.4381, "step": 181670 }, { "epoch": 1.0799436489113183, "grad_norm": 4.851926803588867, "learning_rate": 9.595765915143051e-06, "loss": 0.4379, "step": 181680 }, { "epoch": 1.0800030909879867, "grad_norm": 5.3331756591796875, "learning_rate": 9.595684179979915e-06, "loss": 0.4025, "step": 181690 }, { "epoch": 1.0800625330646552, "grad_norm": 5.874069690704346, "learning_rate": 9.595602436902463e-06, "loss": 0.3883, "step": 181700 }, { "epoch": 1.0801219751413236, "grad_norm": 4.829065799713135, "learning_rate": 9.595520685910836e-06, "loss": 0.4063, "step": 181710 }, { "epoch": 1.080181417217992, "grad_norm": 4.862567901611328, "learning_rate": 9.595438927005172e-06, "loss": 0.4018, "step": 181720 }, { "epoch": 1.0802408592946604, "grad_norm": 4.915984153747559, "learning_rate": 9.595357160185615e-06, "loss": 0.4105, "step": 181730 }, { "epoch": 1.0803003013713286, "grad_norm": 5.9534807205200195, "learning_rate": 9.595275385452305e-06, "loss": 0.4109, "step": 181740 }, { "epoch": 1.080359743447997, "grad_norm": 7.296910762786865, "learning_rate": 9.595193602805381e-06, "loss": 0.4406, "step": 181750 }, { "epoch": 1.0804191855246654, "grad_norm": 4.790011405944824, "learning_rate": 9.595111812244988e-06, "loss": 0.3899, "step": 181760 }, { "epoch": 1.0804786276013338, "grad_norm": 5.021409511566162, "learning_rate": 9.595030013771262e-06, "loss": 0.4463, "step": 181770 }, { "epoch": 1.0805380696780023, "grad_norm": 5.26354455947876, "learning_rate": 9.594948207384347e-06, "loss": 0.4081, "step": 181780 }, { "epoch": 1.0805975117546707, "grad_norm": 5.15286111831665, "learning_rate": 9.594866393084383e-06, "loss": 0.384, "step": 181790 }, { "epoch": 1.080656953831339, "grad_norm": 5.985137462615967, "learning_rate": 9.594784570871512e-06, "loss": 0.4107, "step": 181800 }, { "epoch": 1.0807163959080075, "grad_norm": 5.764899253845215, "learning_rate": 9.594702740745871e-06, "loss": 0.4428, "step": 181810 }, { "epoch": 1.080775837984676, "grad_norm": 6.455442905426025, "learning_rate": 9.594620902707606e-06, "loss": 0.4119, "step": 181820 }, { "epoch": 1.0808352800613443, "grad_norm": 5.119967460632324, "learning_rate": 9.594539056756853e-06, "loss": 0.4004, "step": 181830 }, { "epoch": 1.0808947221380125, "grad_norm": 5.148792743682861, "learning_rate": 9.594457202893758e-06, "loss": 0.4231, "step": 181840 }, { "epoch": 1.080954164214681, "grad_norm": 6.156947612762451, "learning_rate": 9.594375341118458e-06, "loss": 0.4171, "step": 181850 }, { "epoch": 1.0810136062913493, "grad_norm": 5.967026710510254, "learning_rate": 9.594293471431096e-06, "loss": 0.3565, "step": 181860 }, { "epoch": 1.0810730483680178, "grad_norm": 4.80610990524292, "learning_rate": 9.594211593831813e-06, "loss": 0.427, "step": 181870 }, { "epoch": 1.0811324904446862, "grad_norm": 5.3485798835754395, "learning_rate": 9.59412970832075e-06, "loss": 0.3921, "step": 181880 }, { "epoch": 1.0811919325213546, "grad_norm": 7.540196418762207, "learning_rate": 9.594047814898045e-06, "loss": 0.4101, "step": 181890 }, { "epoch": 1.081251374598023, "grad_norm": 5.106944561004639, "learning_rate": 9.593965913563842e-06, "loss": 0.4055, "step": 181900 }, { "epoch": 1.0813108166746914, "grad_norm": 5.111853122711182, "learning_rate": 9.593884004318283e-06, "loss": 0.3815, "step": 181910 }, { "epoch": 1.0813702587513598, "grad_norm": 6.367177963256836, "learning_rate": 9.593802087161508e-06, "loss": 0.392, "step": 181920 }, { "epoch": 1.081429700828028, "grad_norm": 5.719873428344727, "learning_rate": 9.593720162093657e-06, "loss": 0.3898, "step": 181930 }, { "epoch": 1.0814891429046964, "grad_norm": 5.3108720779418945, "learning_rate": 9.593638229114872e-06, "loss": 0.3957, "step": 181940 }, { "epoch": 1.0815485849813649, "grad_norm": 4.746497631072998, "learning_rate": 9.593556288225292e-06, "loss": 0.3841, "step": 181950 }, { "epoch": 1.0816080270580333, "grad_norm": 5.131893634796143, "learning_rate": 9.593474339425061e-06, "loss": 0.4193, "step": 181960 }, { "epoch": 1.0816674691347017, "grad_norm": 4.896533966064453, "learning_rate": 9.593392382714319e-06, "loss": 0.3995, "step": 181970 }, { "epoch": 1.08172691121137, "grad_norm": 4.834181785583496, "learning_rate": 9.593310418093209e-06, "loss": 0.3841, "step": 181980 }, { "epoch": 1.0817863532880385, "grad_norm": 7.237595081329346, "learning_rate": 9.593228445561868e-06, "loss": 0.4255, "step": 181990 }, { "epoch": 1.081845795364707, "grad_norm": 6.011741638183594, "learning_rate": 9.593146465120442e-06, "loss": 0.3975, "step": 182000 }, { "epoch": 1.0819052374413753, "grad_norm": 5.965734958648682, "learning_rate": 9.593064476769067e-06, "loss": 0.3893, "step": 182010 }, { "epoch": 1.0819646795180438, "grad_norm": 5.835381984710693, "learning_rate": 9.59298248050789e-06, "loss": 0.4421, "step": 182020 }, { "epoch": 1.082024121594712, "grad_norm": 6.478164196014404, "learning_rate": 9.592900476337048e-06, "loss": 0.4202, "step": 182030 }, { "epoch": 1.0820835636713804, "grad_norm": 5.238816261291504, "learning_rate": 9.592818464256681e-06, "loss": 0.4199, "step": 182040 }, { "epoch": 1.0821430057480488, "grad_norm": 5.468237400054932, "learning_rate": 9.592736444266935e-06, "loss": 0.4281, "step": 182050 }, { "epoch": 1.0822024478247172, "grad_norm": 4.688064098358154, "learning_rate": 9.592654416367947e-06, "loss": 0.4127, "step": 182060 }, { "epoch": 1.0822618899013856, "grad_norm": 6.214217185974121, "learning_rate": 9.592572380559864e-06, "loss": 0.3888, "step": 182070 }, { "epoch": 1.082321331978054, "grad_norm": 5.556874752044678, "learning_rate": 9.592490336842819e-06, "loss": 0.3878, "step": 182080 }, { "epoch": 1.0823807740547224, "grad_norm": 5.012813568115234, "learning_rate": 9.592408285216961e-06, "loss": 0.4317, "step": 182090 }, { "epoch": 1.0824402161313909, "grad_norm": 4.368043422698975, "learning_rate": 9.592326225682426e-06, "loss": 0.3673, "step": 182100 }, { "epoch": 1.082499658208059, "grad_norm": 5.3618693351745605, "learning_rate": 9.592244158239358e-06, "loss": 0.4118, "step": 182110 }, { "epoch": 1.0825591002847275, "grad_norm": 6.845691204071045, "learning_rate": 9.592162082887897e-06, "loss": 0.4481, "step": 182120 }, { "epoch": 1.0826185423613959, "grad_norm": 4.322655200958252, "learning_rate": 9.592079999628186e-06, "loss": 0.4103, "step": 182130 }, { "epoch": 1.0826779844380643, "grad_norm": 4.787932872772217, "learning_rate": 9.591997908460364e-06, "loss": 0.3902, "step": 182140 }, { "epoch": 1.0827374265147327, "grad_norm": 4.943846225738525, "learning_rate": 9.591915809384574e-06, "loss": 0.398, "step": 182150 }, { "epoch": 1.0827968685914011, "grad_norm": 5.520811080932617, "learning_rate": 9.591833702400957e-06, "loss": 0.4322, "step": 182160 }, { "epoch": 1.0828563106680695, "grad_norm": 5.64968204498291, "learning_rate": 9.591751587509656e-06, "loss": 0.3741, "step": 182170 }, { "epoch": 1.082915752744738, "grad_norm": 5.803736686706543, "learning_rate": 9.591669464710808e-06, "loss": 0.4098, "step": 182180 }, { "epoch": 1.0829751948214064, "grad_norm": 6.540454387664795, "learning_rate": 9.59158733400456e-06, "loss": 0.456, "step": 182190 }, { "epoch": 1.0830346368980748, "grad_norm": 4.879960536956787, "learning_rate": 9.591505195391051e-06, "loss": 0.4252, "step": 182200 }, { "epoch": 1.083094078974743, "grad_norm": 6.313567161560059, "learning_rate": 9.59142304887042e-06, "loss": 0.4324, "step": 182210 }, { "epoch": 1.0831535210514114, "grad_norm": 4.516983985900879, "learning_rate": 9.591340894442811e-06, "loss": 0.4111, "step": 182220 }, { "epoch": 1.0832129631280798, "grad_norm": 5.4427266120910645, "learning_rate": 9.591258732108367e-06, "loss": 0.4178, "step": 182230 }, { "epoch": 1.0832724052047482, "grad_norm": 5.18314266204834, "learning_rate": 9.591176561867225e-06, "loss": 0.3645, "step": 182240 }, { "epoch": 1.0833318472814166, "grad_norm": 4.61708402633667, "learning_rate": 9.591094383719532e-06, "loss": 0.3867, "step": 182250 }, { "epoch": 1.083391289358085, "grad_norm": 5.464101314544678, "learning_rate": 9.591012197665426e-06, "loss": 0.4081, "step": 182260 }, { "epoch": 1.0834507314347535, "grad_norm": 4.961684226989746, "learning_rate": 9.590930003705048e-06, "loss": 0.4164, "step": 182270 }, { "epoch": 1.0835101735114219, "grad_norm": 5.133831977844238, "learning_rate": 9.59084780183854e-06, "loss": 0.3743, "step": 182280 }, { "epoch": 1.0835696155880903, "grad_norm": 4.752501964569092, "learning_rate": 9.590765592066048e-06, "loss": 0.4385, "step": 182290 }, { "epoch": 1.0836290576647585, "grad_norm": 4.688394546508789, "learning_rate": 9.590683374387705e-06, "loss": 0.4092, "step": 182300 }, { "epoch": 1.083688499741427, "grad_norm": 5.699128150939941, "learning_rate": 9.590601148803662e-06, "loss": 0.389, "step": 182310 }, { "epoch": 1.0837479418180953, "grad_norm": 4.881197929382324, "learning_rate": 9.590518915314054e-06, "loss": 0.4151, "step": 182320 }, { "epoch": 1.0838073838947637, "grad_norm": 4.838577747344971, "learning_rate": 9.590436673919024e-06, "loss": 0.3893, "step": 182330 }, { "epoch": 1.0838668259714321, "grad_norm": 7.3585381507873535, "learning_rate": 9.590354424618716e-06, "loss": 0.396, "step": 182340 }, { "epoch": 1.0839262680481005, "grad_norm": 5.990822792053223, "learning_rate": 9.590272167413269e-06, "loss": 0.3839, "step": 182350 }, { "epoch": 1.083985710124769, "grad_norm": 6.822451114654541, "learning_rate": 9.590189902302826e-06, "loss": 0.3946, "step": 182360 }, { "epoch": 1.0840451522014374, "grad_norm": 4.399038791656494, "learning_rate": 9.590107629287527e-06, "loss": 0.4272, "step": 182370 }, { "epoch": 1.0841045942781058, "grad_norm": 5.373062610626221, "learning_rate": 9.590025348367517e-06, "loss": 0.4338, "step": 182380 }, { "epoch": 1.0841640363547742, "grad_norm": 5.471730709075928, "learning_rate": 9.589943059542934e-06, "loss": 0.4407, "step": 182390 }, { "epoch": 1.0842234784314424, "grad_norm": 5.122223854064941, "learning_rate": 9.589860762813922e-06, "loss": 0.4079, "step": 182400 }, { "epoch": 1.0842829205081108, "grad_norm": 4.9952473640441895, "learning_rate": 9.589778458180622e-06, "loss": 0.375, "step": 182410 }, { "epoch": 1.0843423625847792, "grad_norm": 5.422123432159424, "learning_rate": 9.589696145643176e-06, "loss": 0.4117, "step": 182420 }, { "epoch": 1.0844018046614476, "grad_norm": 5.1737141609191895, "learning_rate": 9.589613825201726e-06, "loss": 0.3735, "step": 182430 }, { "epoch": 1.084461246738116, "grad_norm": 4.362910747528076, "learning_rate": 9.589531496856413e-06, "loss": 0.3464, "step": 182440 }, { "epoch": 1.0845206888147845, "grad_norm": 3.784379482269287, "learning_rate": 9.589449160607378e-06, "loss": 0.381, "step": 182450 }, { "epoch": 1.0845801308914529, "grad_norm": 4.894042015075684, "learning_rate": 9.589366816454765e-06, "loss": 0.4214, "step": 182460 }, { "epoch": 1.0846395729681213, "grad_norm": 4.677058219909668, "learning_rate": 9.589284464398716e-06, "loss": 0.4229, "step": 182470 }, { "epoch": 1.0846990150447895, "grad_norm": 4.288794994354248, "learning_rate": 9.58920210443937e-06, "loss": 0.4079, "step": 182480 }, { "epoch": 1.084758457121458, "grad_norm": 4.798641204833984, "learning_rate": 9.58911973657687e-06, "loss": 0.3983, "step": 182490 }, { "epoch": 1.0848178991981263, "grad_norm": 7.039403438568115, "learning_rate": 9.58903736081136e-06, "loss": 0.4634, "step": 182500 }, { "epoch": 1.0848773412747947, "grad_norm": 6.164714813232422, "learning_rate": 9.58895497714298e-06, "loss": 0.3873, "step": 182510 }, { "epoch": 1.0849367833514632, "grad_norm": 6.888555526733398, "learning_rate": 9.58887258557187e-06, "loss": 0.4194, "step": 182520 }, { "epoch": 1.0849962254281316, "grad_norm": 5.939793109893799, "learning_rate": 9.588790186098176e-06, "loss": 0.4192, "step": 182530 }, { "epoch": 1.0850556675048, "grad_norm": 6.652364730834961, "learning_rate": 9.588707778722035e-06, "loss": 0.4531, "step": 182540 }, { "epoch": 1.0851151095814684, "grad_norm": 4.826235294342041, "learning_rate": 9.588625363443594e-06, "loss": 0.3994, "step": 182550 }, { "epoch": 1.0851745516581368, "grad_norm": 4.945692539215088, "learning_rate": 9.588542940262992e-06, "loss": 0.3493, "step": 182560 }, { "epoch": 1.0852339937348052, "grad_norm": 6.295130729675293, "learning_rate": 9.588460509180372e-06, "loss": 0.4022, "step": 182570 }, { "epoch": 1.0852934358114734, "grad_norm": 4.562209606170654, "learning_rate": 9.588378070195874e-06, "loss": 0.4033, "step": 182580 }, { "epoch": 1.0853528778881418, "grad_norm": 4.8579511642456055, "learning_rate": 9.588295623309644e-06, "loss": 0.4009, "step": 182590 }, { "epoch": 1.0854123199648102, "grad_norm": 5.185168266296387, "learning_rate": 9.588213168521821e-06, "loss": 0.4114, "step": 182600 }, { "epoch": 1.0854717620414787, "grad_norm": 4.104575157165527, "learning_rate": 9.588130705832546e-06, "loss": 0.3722, "step": 182610 }, { "epoch": 1.085531204118147, "grad_norm": 5.295412063598633, "learning_rate": 9.588048235241963e-06, "loss": 0.4003, "step": 182620 }, { "epoch": 1.0855906461948155, "grad_norm": 4.9778852462768555, "learning_rate": 9.587965756750212e-06, "loss": 0.4, "step": 182630 }, { "epoch": 1.085650088271484, "grad_norm": 6.000651836395264, "learning_rate": 9.587883270357438e-06, "loss": 0.4199, "step": 182640 }, { "epoch": 1.0857095303481523, "grad_norm": 5.658271312713623, "learning_rate": 9.587800776063782e-06, "loss": 0.4331, "step": 182650 }, { "epoch": 1.0857689724248207, "grad_norm": 6.763593673706055, "learning_rate": 9.587718273869386e-06, "loss": 0.3953, "step": 182660 }, { "epoch": 1.085828414501489, "grad_norm": 4.960917949676514, "learning_rate": 9.587635763774391e-06, "loss": 0.3844, "step": 182670 }, { "epoch": 1.0858878565781573, "grad_norm": 4.936182022094727, "learning_rate": 9.58755324577894e-06, "loss": 0.4091, "step": 182680 }, { "epoch": 1.0859472986548258, "grad_norm": 4.263387203216553, "learning_rate": 9.587470719883174e-06, "loss": 0.4251, "step": 182690 }, { "epoch": 1.0860067407314942, "grad_norm": 4.74802827835083, "learning_rate": 9.587388186087238e-06, "loss": 0.4358, "step": 182700 }, { "epoch": 1.0860661828081626, "grad_norm": 6.501984119415283, "learning_rate": 9.587305644391271e-06, "loss": 0.4036, "step": 182710 }, { "epoch": 1.086125624884831, "grad_norm": 5.071086883544922, "learning_rate": 9.587223094795416e-06, "loss": 0.4082, "step": 182720 }, { "epoch": 1.0861850669614994, "grad_norm": 4.361051082611084, "learning_rate": 9.587140537299817e-06, "loss": 0.402, "step": 182730 }, { "epoch": 1.0862445090381678, "grad_norm": 4.6238555908203125, "learning_rate": 9.587057971904612e-06, "loss": 0.3797, "step": 182740 }, { "epoch": 1.0863039511148362, "grad_norm": 4.843418598175049, "learning_rate": 9.586975398609947e-06, "loss": 0.3869, "step": 182750 }, { "epoch": 1.0863633931915047, "grad_norm": 5.150845527648926, "learning_rate": 9.586892817415965e-06, "loss": 0.4272, "step": 182760 }, { "epoch": 1.0864228352681728, "grad_norm": 5.31688928604126, "learning_rate": 9.586810228322805e-06, "loss": 0.3972, "step": 182770 }, { "epoch": 1.0864822773448413, "grad_norm": 5.072838306427002, "learning_rate": 9.58672763133061e-06, "loss": 0.4337, "step": 182780 }, { "epoch": 1.0865417194215097, "grad_norm": 7.14434814453125, "learning_rate": 9.586645026439522e-06, "loss": 0.4379, "step": 182790 }, { "epoch": 1.086601161498178, "grad_norm": 5.880398273468018, "learning_rate": 9.586562413649685e-06, "loss": 0.4108, "step": 182800 }, { "epoch": 1.0866606035748465, "grad_norm": 5.0505290031433105, "learning_rate": 9.58647979296124e-06, "loss": 0.3925, "step": 182810 }, { "epoch": 1.086720045651515, "grad_norm": 5.271937847137451, "learning_rate": 9.58639716437433e-06, "loss": 0.3838, "step": 182820 }, { "epoch": 1.0867794877281833, "grad_norm": 6.008667469024658, "learning_rate": 9.586314527889096e-06, "loss": 0.4175, "step": 182830 }, { "epoch": 1.0868389298048517, "grad_norm": 8.14252758026123, "learning_rate": 9.586231883505684e-06, "loss": 0.4182, "step": 182840 }, { "epoch": 1.08689837188152, "grad_norm": 6.354509353637695, "learning_rate": 9.58614923122423e-06, "loss": 0.4529, "step": 182850 }, { "epoch": 1.0869578139581884, "grad_norm": 5.410556793212891, "learning_rate": 9.586066571044881e-06, "loss": 0.3647, "step": 182860 }, { "epoch": 1.0870172560348568, "grad_norm": 4.125386714935303, "learning_rate": 9.585983902967779e-06, "loss": 0.4273, "step": 182870 }, { "epoch": 1.0870766981115252, "grad_norm": 6.413267612457275, "learning_rate": 9.585901226993065e-06, "loss": 0.4197, "step": 182880 }, { "epoch": 1.0871361401881936, "grad_norm": 4.065756320953369, "learning_rate": 9.58581854312088e-06, "loss": 0.4297, "step": 182890 }, { "epoch": 1.087195582264862, "grad_norm": 5.329217433929443, "learning_rate": 9.58573585135137e-06, "loss": 0.4447, "step": 182900 }, { "epoch": 1.0872550243415304, "grad_norm": 4.841885566711426, "learning_rate": 9.585653151684677e-06, "loss": 0.4247, "step": 182910 }, { "epoch": 1.0873144664181988, "grad_norm": 4.474574565887451, "learning_rate": 9.58557044412094e-06, "loss": 0.3601, "step": 182920 }, { "epoch": 1.0873739084948673, "grad_norm": 4.567812919616699, "learning_rate": 9.585487728660306e-06, "loss": 0.396, "step": 182930 }, { "epoch": 1.0874333505715357, "grad_norm": 5.778552055358887, "learning_rate": 9.585405005302913e-06, "loss": 0.3913, "step": 182940 }, { "epoch": 1.0874927926482039, "grad_norm": 5.457355976104736, "learning_rate": 9.585322274048906e-06, "loss": 0.3968, "step": 182950 }, { "epoch": 1.0875522347248723, "grad_norm": 4.28581428527832, "learning_rate": 9.585239534898426e-06, "loss": 0.3635, "step": 182960 }, { "epoch": 1.0876116768015407, "grad_norm": 6.793848991394043, "learning_rate": 9.585156787851616e-06, "loss": 0.3911, "step": 182970 }, { "epoch": 1.087671118878209, "grad_norm": 7.1269307136535645, "learning_rate": 9.58507403290862e-06, "loss": 0.3987, "step": 182980 }, { "epoch": 1.0877305609548775, "grad_norm": 5.240443706512451, "learning_rate": 9.58499127006958e-06, "loss": 0.4476, "step": 182990 }, { "epoch": 1.087790003031546, "grad_norm": 4.775022029876709, "learning_rate": 9.584908499334637e-06, "loss": 0.4031, "step": 183000 }, { "epoch": 1.0878494451082144, "grad_norm": 4.889319896697998, "learning_rate": 9.584825720703935e-06, "loss": 0.4267, "step": 183010 }, { "epoch": 1.0879088871848828, "grad_norm": 4.462193965911865, "learning_rate": 9.584742934177616e-06, "loss": 0.377, "step": 183020 }, { "epoch": 1.0879683292615512, "grad_norm": 4.528286933898926, "learning_rate": 9.584660139755824e-06, "loss": 0.4252, "step": 183030 }, { "epoch": 1.0880277713382194, "grad_norm": 4.315241813659668, "learning_rate": 9.584577337438699e-06, "loss": 0.4077, "step": 183040 }, { "epoch": 1.0880872134148878, "grad_norm": 5.207150459289551, "learning_rate": 9.584494527226383e-06, "loss": 0.4136, "step": 183050 }, { "epoch": 1.0881466554915562, "grad_norm": 5.220714569091797, "learning_rate": 9.584411709119022e-06, "loss": 0.4114, "step": 183060 }, { "epoch": 1.0882060975682246, "grad_norm": 4.398025989532471, "learning_rate": 9.584328883116758e-06, "loss": 0.4574, "step": 183070 }, { "epoch": 1.088265539644893, "grad_norm": 5.205843925476074, "learning_rate": 9.584246049219732e-06, "loss": 0.4009, "step": 183080 }, { "epoch": 1.0883249817215614, "grad_norm": 6.827094554901123, "learning_rate": 9.584163207428087e-06, "loss": 0.4191, "step": 183090 }, { "epoch": 1.0883844237982299, "grad_norm": 5.481013774871826, "learning_rate": 9.584080357741965e-06, "loss": 0.4314, "step": 183100 }, { "epoch": 1.0884438658748983, "grad_norm": 6.388510227203369, "learning_rate": 9.583997500161512e-06, "loss": 0.4599, "step": 183110 }, { "epoch": 1.0885033079515667, "grad_norm": 4.13368558883667, "learning_rate": 9.583914634686866e-06, "loss": 0.3789, "step": 183120 }, { "epoch": 1.088562750028235, "grad_norm": 3.9913136959075928, "learning_rate": 9.583831761318174e-06, "loss": 0.3878, "step": 183130 }, { "epoch": 1.0886221921049033, "grad_norm": 5.191665172576904, "learning_rate": 9.583748880055576e-06, "loss": 0.4471, "step": 183140 }, { "epoch": 1.0886816341815717, "grad_norm": 5.329356670379639, "learning_rate": 9.583665990899215e-06, "loss": 0.4225, "step": 183150 }, { "epoch": 1.0887410762582401, "grad_norm": 4.916937351226807, "learning_rate": 9.583583093849234e-06, "loss": 0.3819, "step": 183160 }, { "epoch": 1.0888005183349085, "grad_norm": 4.819431304931641, "learning_rate": 9.583500188905776e-06, "loss": 0.4328, "step": 183170 }, { "epoch": 1.088859960411577, "grad_norm": 4.807032585144043, "learning_rate": 9.583417276068987e-06, "loss": 0.3686, "step": 183180 }, { "epoch": 1.0889194024882454, "grad_norm": 5.544739246368408, "learning_rate": 9.583334355339002e-06, "loss": 0.4291, "step": 183190 }, { "epoch": 1.0889788445649138, "grad_norm": 5.841348648071289, "learning_rate": 9.583251426715972e-06, "loss": 0.4517, "step": 183200 }, { "epoch": 1.0890382866415822, "grad_norm": 5.6316819190979, "learning_rate": 9.583168490200034e-06, "loss": 0.4179, "step": 183210 }, { "epoch": 1.0890977287182504, "grad_norm": 5.95659065246582, "learning_rate": 9.583085545791333e-06, "loss": 0.3916, "step": 183220 }, { "epoch": 1.0891571707949188, "grad_norm": 7.987307071685791, "learning_rate": 9.583002593490013e-06, "loss": 0.4114, "step": 183230 }, { "epoch": 1.0892166128715872, "grad_norm": 5.4474029541015625, "learning_rate": 9.582919633296216e-06, "loss": 0.3814, "step": 183240 }, { "epoch": 1.0892760549482556, "grad_norm": 5.435680866241455, "learning_rate": 9.582836665210082e-06, "loss": 0.4177, "step": 183250 }, { "epoch": 1.089335497024924, "grad_norm": 5.607026100158691, "learning_rate": 9.582753689231758e-06, "loss": 0.4179, "step": 183260 }, { "epoch": 1.0893949391015925, "grad_norm": 6.568395137786865, "learning_rate": 9.582670705361386e-06, "loss": 0.404, "step": 183270 }, { "epoch": 1.0894543811782609, "grad_norm": 5.136119842529297, "learning_rate": 9.582587713599108e-06, "loss": 0.4254, "step": 183280 }, { "epoch": 1.0895138232549293, "grad_norm": 5.345250129699707, "learning_rate": 9.582504713945067e-06, "loss": 0.3939, "step": 183290 }, { "epoch": 1.0895732653315977, "grad_norm": 3.733616352081299, "learning_rate": 9.582421706399405e-06, "loss": 0.3737, "step": 183300 }, { "epoch": 1.0896327074082661, "grad_norm": 7.168180465698242, "learning_rate": 9.582338690962267e-06, "loss": 0.462, "step": 183310 }, { "epoch": 1.0896921494849343, "grad_norm": 4.978472709655762, "learning_rate": 9.582255667633795e-06, "loss": 0.3892, "step": 183320 }, { "epoch": 1.0897515915616027, "grad_norm": 4.685102939605713, "learning_rate": 9.582172636414134e-06, "loss": 0.4024, "step": 183330 }, { "epoch": 1.0898110336382711, "grad_norm": 5.197543621063232, "learning_rate": 9.582089597303422e-06, "loss": 0.3986, "step": 183340 }, { "epoch": 1.0898704757149396, "grad_norm": 6.7859392166137695, "learning_rate": 9.582006550301806e-06, "loss": 0.412, "step": 183350 }, { "epoch": 1.089929917791608, "grad_norm": 6.187358856201172, "learning_rate": 9.581923495409429e-06, "loss": 0.4, "step": 183360 }, { "epoch": 1.0899893598682764, "grad_norm": 4.8854570388793945, "learning_rate": 9.581840432626431e-06, "loss": 0.4309, "step": 183370 }, { "epoch": 1.0900488019449448, "grad_norm": 4.815776348114014, "learning_rate": 9.581757361952958e-06, "loss": 0.4186, "step": 183380 }, { "epoch": 1.0901082440216132, "grad_norm": 6.194583892822266, "learning_rate": 9.581674283389152e-06, "loss": 0.3989, "step": 183390 }, { "epoch": 1.0901676860982816, "grad_norm": 4.707898139953613, "learning_rate": 9.581591196935157e-06, "loss": 0.4205, "step": 183400 }, { "epoch": 1.0902271281749498, "grad_norm": 4.686452388763428, "learning_rate": 9.581508102591114e-06, "loss": 0.3879, "step": 183410 }, { "epoch": 1.0902865702516182, "grad_norm": 5.408360481262207, "learning_rate": 9.58142500035717e-06, "loss": 0.4107, "step": 183420 }, { "epoch": 1.0903460123282867, "grad_norm": 5.315574645996094, "learning_rate": 9.581341890233464e-06, "loss": 0.3896, "step": 183430 }, { "epoch": 1.090405454404955, "grad_norm": 5.274676322937012, "learning_rate": 9.581258772220139e-06, "loss": 0.3966, "step": 183440 }, { "epoch": 1.0904648964816235, "grad_norm": 4.696222305297852, "learning_rate": 9.58117564631734e-06, "loss": 0.4514, "step": 183450 }, { "epoch": 1.090524338558292, "grad_norm": 5.898410797119141, "learning_rate": 9.581092512525212e-06, "loss": 0.4005, "step": 183460 }, { "epoch": 1.0905837806349603, "grad_norm": 4.459110736846924, "learning_rate": 9.581009370843896e-06, "loss": 0.4464, "step": 183470 }, { "epoch": 1.0906432227116287, "grad_norm": 4.904748916625977, "learning_rate": 9.580926221273535e-06, "loss": 0.3619, "step": 183480 }, { "epoch": 1.0907026647882971, "grad_norm": 5.816768169403076, "learning_rate": 9.58084306381427e-06, "loss": 0.4004, "step": 183490 }, { "epoch": 1.0907621068649653, "grad_norm": 5.348714351654053, "learning_rate": 9.580759898466249e-06, "loss": 0.3979, "step": 183500 }, { "epoch": 1.0908215489416337, "grad_norm": 4.416652679443359, "learning_rate": 9.580676725229612e-06, "loss": 0.3662, "step": 183510 }, { "epoch": 1.0908809910183022, "grad_norm": 4.942130088806152, "learning_rate": 9.580593544104504e-06, "loss": 0.3789, "step": 183520 }, { "epoch": 1.0909404330949706, "grad_norm": 5.922512531280518, "learning_rate": 9.580510355091067e-06, "loss": 0.4269, "step": 183530 }, { "epoch": 1.090999875171639, "grad_norm": 4.9003143310546875, "learning_rate": 9.580427158189445e-06, "loss": 0.4036, "step": 183540 }, { "epoch": 1.0910593172483074, "grad_norm": 4.804407119750977, "learning_rate": 9.58034395339978e-06, "loss": 0.3949, "step": 183550 }, { "epoch": 1.0911187593249758, "grad_norm": 5.091701507568359, "learning_rate": 9.580260740722216e-06, "loss": 0.3968, "step": 183560 }, { "epoch": 1.0911782014016442, "grad_norm": 5.952385902404785, "learning_rate": 9.580177520156898e-06, "loss": 0.4024, "step": 183570 }, { "epoch": 1.0912376434783126, "grad_norm": 3.428743362426758, "learning_rate": 9.580094291703966e-06, "loss": 0.3883, "step": 183580 }, { "epoch": 1.0912970855549808, "grad_norm": 5.208606243133545, "learning_rate": 9.580011055363566e-06, "loss": 0.4015, "step": 183590 }, { "epoch": 1.0913565276316493, "grad_norm": 4.885098457336426, "learning_rate": 9.57992781113584e-06, "loss": 0.365, "step": 183600 }, { "epoch": 1.0914159697083177, "grad_norm": 5.65356969833374, "learning_rate": 9.579844559020933e-06, "loss": 0.4184, "step": 183610 }, { "epoch": 1.091475411784986, "grad_norm": 5.058752536773682, "learning_rate": 9.579761299018988e-06, "loss": 0.4524, "step": 183620 }, { "epoch": 1.0915348538616545, "grad_norm": 5.59140157699585, "learning_rate": 9.579678031130145e-06, "loss": 0.3962, "step": 183630 }, { "epoch": 1.091594295938323, "grad_norm": 4.748194694519043, "learning_rate": 9.57959475535455e-06, "loss": 0.3953, "step": 183640 }, { "epoch": 1.0916537380149913, "grad_norm": 6.049684047698975, "learning_rate": 9.579511471692349e-06, "loss": 0.3438, "step": 183650 }, { "epoch": 1.0917131800916597, "grad_norm": 4.694107532501221, "learning_rate": 9.579428180143682e-06, "loss": 0.3828, "step": 183660 }, { "epoch": 1.0917726221683282, "grad_norm": 5.8965864181518555, "learning_rate": 9.579344880708692e-06, "loss": 0.3918, "step": 183670 }, { "epoch": 1.0918320642449966, "grad_norm": 5.9751739501953125, "learning_rate": 9.579261573387524e-06, "loss": 0.4238, "step": 183680 }, { "epoch": 1.0918915063216648, "grad_norm": 6.299147129058838, "learning_rate": 9.57917825818032e-06, "loss": 0.4447, "step": 183690 }, { "epoch": 1.0919509483983332, "grad_norm": 5.0719523429870605, "learning_rate": 9.579094935087228e-06, "loss": 0.3988, "step": 183700 }, { "epoch": 1.0920103904750016, "grad_norm": 3.2680604457855225, "learning_rate": 9.579011604108387e-06, "loss": 0.3565, "step": 183710 }, { "epoch": 1.09206983255167, "grad_norm": 5.51793098449707, "learning_rate": 9.578928265243941e-06, "loss": 0.4244, "step": 183720 }, { "epoch": 1.0921292746283384, "grad_norm": 6.602926254272461, "learning_rate": 9.578844918494033e-06, "loss": 0.4276, "step": 183730 }, { "epoch": 1.0921887167050068, "grad_norm": 5.46976375579834, "learning_rate": 9.57876156385881e-06, "loss": 0.4092, "step": 183740 }, { "epoch": 1.0922481587816752, "grad_norm": 4.654114723205566, "learning_rate": 9.578678201338412e-06, "loss": 0.4238, "step": 183750 }, { "epoch": 1.0923076008583437, "grad_norm": 5.651371479034424, "learning_rate": 9.578594830932984e-06, "loss": 0.438, "step": 183760 }, { "epoch": 1.092367042935012, "grad_norm": 5.684588432312012, "learning_rate": 9.578511452642669e-06, "loss": 0.4218, "step": 183770 }, { "epoch": 1.0924264850116803, "grad_norm": 5.04843807220459, "learning_rate": 9.578428066467612e-06, "loss": 0.4159, "step": 183780 }, { "epoch": 1.0924859270883487, "grad_norm": 5.6954545974731445, "learning_rate": 9.578344672407954e-06, "loss": 0.3804, "step": 183790 }, { "epoch": 1.092545369165017, "grad_norm": 4.180173873901367, "learning_rate": 9.578261270463842e-06, "loss": 0.401, "step": 183800 }, { "epoch": 1.0926048112416855, "grad_norm": 5.501240253448486, "learning_rate": 9.578177860635415e-06, "loss": 0.3823, "step": 183810 }, { "epoch": 1.092664253318354, "grad_norm": 4.39423942565918, "learning_rate": 9.578094442922823e-06, "loss": 0.3894, "step": 183820 }, { "epoch": 1.0927236953950223, "grad_norm": 4.270411014556885, "learning_rate": 9.578011017326203e-06, "loss": 0.3831, "step": 183830 }, { "epoch": 1.0927831374716908, "grad_norm": 5.09889030456543, "learning_rate": 9.577927583845705e-06, "loss": 0.422, "step": 183840 }, { "epoch": 1.0928425795483592, "grad_norm": 3.1763439178466797, "learning_rate": 9.577844142481467e-06, "loss": 0.4044, "step": 183850 }, { "epoch": 1.0929020216250276, "grad_norm": 6.5641069412231445, "learning_rate": 9.577760693233637e-06, "loss": 0.4498, "step": 183860 }, { "epoch": 1.0929614637016958, "grad_norm": 6.4061279296875, "learning_rate": 9.577677236102357e-06, "loss": 0.4072, "step": 183870 }, { "epoch": 1.0930209057783642, "grad_norm": 4.140481472015381, "learning_rate": 9.577593771087767e-06, "loss": 0.3622, "step": 183880 }, { "epoch": 1.0930803478550326, "grad_norm": 5.933701038360596, "learning_rate": 9.577510298190018e-06, "loss": 0.3939, "step": 183890 }, { "epoch": 1.093139789931701, "grad_norm": 5.205154895782471, "learning_rate": 9.57742681740925e-06, "loss": 0.4389, "step": 183900 }, { "epoch": 1.0931992320083694, "grad_norm": 6.1891889572143555, "learning_rate": 9.577343328745604e-06, "loss": 0.4093, "step": 183910 }, { "epoch": 1.0932586740850379, "grad_norm": 6.972349166870117, "learning_rate": 9.577259832199229e-06, "loss": 0.4398, "step": 183920 }, { "epoch": 1.0933181161617063, "grad_norm": 5.072172164916992, "learning_rate": 9.577176327770266e-06, "loss": 0.4242, "step": 183930 }, { "epoch": 1.0933775582383747, "grad_norm": 6.056193828582764, "learning_rate": 9.577092815458859e-06, "loss": 0.402, "step": 183940 }, { "epoch": 1.093437000315043, "grad_norm": 6.095548629760742, "learning_rate": 9.577009295265151e-06, "loss": 0.3705, "step": 183950 }, { "epoch": 1.0934964423917113, "grad_norm": 4.881830215454102, "learning_rate": 9.576925767189289e-06, "loss": 0.4026, "step": 183960 }, { "epoch": 1.0935558844683797, "grad_norm": 5.263264179229736, "learning_rate": 9.576842231231414e-06, "loss": 0.4097, "step": 183970 }, { "epoch": 1.0936153265450481, "grad_norm": 6.662302017211914, "learning_rate": 9.57675868739167e-06, "loss": 0.4145, "step": 183980 }, { "epoch": 1.0936747686217165, "grad_norm": 7.054260730743408, "learning_rate": 9.576675135670202e-06, "loss": 0.4183, "step": 183990 }, { "epoch": 1.093734210698385, "grad_norm": 5.658280849456787, "learning_rate": 9.576591576067151e-06, "loss": 0.4228, "step": 184000 }, { "epoch": 1.0937936527750534, "grad_norm": 5.368493556976318, "learning_rate": 9.576508008582665e-06, "loss": 0.3941, "step": 184010 }, { "epoch": 1.0938530948517218, "grad_norm": 3.870553731918335, "learning_rate": 9.576424433216887e-06, "loss": 0.3979, "step": 184020 }, { "epoch": 1.0939125369283902, "grad_norm": 5.216817855834961, "learning_rate": 9.57634084996996e-06, "loss": 0.4114, "step": 184030 }, { "epoch": 1.0939719790050586, "grad_norm": 5.88411283493042, "learning_rate": 9.576257258842028e-06, "loss": 0.4185, "step": 184040 }, { "epoch": 1.094031421081727, "grad_norm": 7.71539831161499, "learning_rate": 9.576173659833234e-06, "loss": 0.4401, "step": 184050 }, { "epoch": 1.0940908631583952, "grad_norm": 4.8806915283203125, "learning_rate": 9.576090052943722e-06, "loss": 0.4409, "step": 184060 }, { "epoch": 1.0941503052350636, "grad_norm": 5.695294380187988, "learning_rate": 9.57600643817364e-06, "loss": 0.3696, "step": 184070 }, { "epoch": 1.094209747311732, "grad_norm": 5.55307149887085, "learning_rate": 9.575922815523126e-06, "loss": 0.4071, "step": 184080 }, { "epoch": 1.0942691893884005, "grad_norm": 4.095341682434082, "learning_rate": 9.57583918499233e-06, "loss": 0.3927, "step": 184090 }, { "epoch": 1.0943286314650689, "grad_norm": 5.542481422424316, "learning_rate": 9.57575554658139e-06, "loss": 0.3696, "step": 184100 }, { "epoch": 1.0943880735417373, "grad_norm": 5.319841384887695, "learning_rate": 9.575671900290453e-06, "loss": 0.382, "step": 184110 }, { "epoch": 1.0944475156184057, "grad_norm": 5.64507532119751, "learning_rate": 9.575588246119664e-06, "loss": 0.3754, "step": 184120 }, { "epoch": 1.0945069576950741, "grad_norm": 4.962338447570801, "learning_rate": 9.575504584069168e-06, "loss": 0.3893, "step": 184130 }, { "epoch": 1.0945663997717425, "grad_norm": 5.712568283081055, "learning_rate": 9.575420914139105e-06, "loss": 0.4009, "step": 184140 }, { "epoch": 1.0946258418484107, "grad_norm": 5.92401647567749, "learning_rate": 9.575337236329622e-06, "loss": 0.4205, "step": 184150 }, { "epoch": 1.0946852839250791, "grad_norm": 5.917232513427734, "learning_rate": 9.575253550640862e-06, "loss": 0.3867, "step": 184160 }, { "epoch": 1.0947447260017475, "grad_norm": 5.082518577575684, "learning_rate": 9.575169857072969e-06, "loss": 0.4194, "step": 184170 }, { "epoch": 1.094804168078416, "grad_norm": 7.71143102645874, "learning_rate": 9.575086155626088e-06, "loss": 0.4286, "step": 184180 }, { "epoch": 1.0948636101550844, "grad_norm": 5.283700942993164, "learning_rate": 9.575002446300363e-06, "loss": 0.4025, "step": 184190 }, { "epoch": 1.0949230522317528, "grad_norm": 4.13926362991333, "learning_rate": 9.574918729095937e-06, "loss": 0.4441, "step": 184200 }, { "epoch": 1.0949824943084212, "grad_norm": 4.471526145935059, "learning_rate": 9.574835004012957e-06, "loss": 0.3914, "step": 184210 }, { "epoch": 1.0950419363850896, "grad_norm": 4.329090118408203, "learning_rate": 9.574751271051564e-06, "loss": 0.3705, "step": 184220 }, { "epoch": 1.095101378461758, "grad_norm": 3.551447629928589, "learning_rate": 9.574667530211903e-06, "loss": 0.3826, "step": 184230 }, { "epoch": 1.0951608205384262, "grad_norm": 4.6200995445251465, "learning_rate": 9.574583781494118e-06, "loss": 0.4168, "step": 184240 }, { "epoch": 1.0952202626150946, "grad_norm": 5.777351379394531, "learning_rate": 9.574500024898357e-06, "loss": 0.4389, "step": 184250 }, { "epoch": 1.095279704691763, "grad_norm": 3.630882740020752, "learning_rate": 9.574416260424759e-06, "loss": 0.4007, "step": 184260 }, { "epoch": 1.0953391467684315, "grad_norm": 5.410654544830322, "learning_rate": 9.574332488073471e-06, "loss": 0.4031, "step": 184270 }, { "epoch": 1.0953985888450999, "grad_norm": 4.138299465179443, "learning_rate": 9.574248707844636e-06, "loss": 0.4292, "step": 184280 }, { "epoch": 1.0954580309217683, "grad_norm": 6.006446361541748, "learning_rate": 9.574164919738399e-06, "loss": 0.3814, "step": 184290 }, { "epoch": 1.0955174729984367, "grad_norm": 6.359417915344238, "learning_rate": 9.574081123754903e-06, "loss": 0.3963, "step": 184300 }, { "epoch": 1.0955769150751051, "grad_norm": 6.548942565917969, "learning_rate": 9.573997319894295e-06, "loss": 0.4357, "step": 184310 }, { "epoch": 1.0956363571517735, "grad_norm": 5.483229637145996, "learning_rate": 9.573913508156717e-06, "loss": 0.3917, "step": 184320 }, { "epoch": 1.0956957992284417, "grad_norm": 3.9701147079467773, "learning_rate": 9.573829688542316e-06, "loss": 0.3596, "step": 184330 }, { "epoch": 1.0957552413051102, "grad_norm": 5.232504367828369, "learning_rate": 9.573745861051233e-06, "loss": 0.4147, "step": 184340 }, { "epoch": 1.0958146833817786, "grad_norm": 7.129417419433594, "learning_rate": 9.573662025683615e-06, "loss": 0.3841, "step": 184350 }, { "epoch": 1.095874125458447, "grad_norm": 4.313482284545898, "learning_rate": 9.573578182439605e-06, "loss": 0.3792, "step": 184360 }, { "epoch": 1.0959335675351154, "grad_norm": 5.744042873382568, "learning_rate": 9.573494331319347e-06, "loss": 0.4456, "step": 184370 }, { "epoch": 1.0959930096117838, "grad_norm": 5.326605796813965, "learning_rate": 9.573410472322986e-06, "loss": 0.4107, "step": 184380 }, { "epoch": 1.0960524516884522, "grad_norm": 4.837687015533447, "learning_rate": 9.573326605450668e-06, "loss": 0.3766, "step": 184390 }, { "epoch": 1.0961118937651206, "grad_norm": 6.726756572723389, "learning_rate": 9.573242730702535e-06, "loss": 0.4332, "step": 184400 }, { "epoch": 1.096171335841789, "grad_norm": 5.788357257843018, "learning_rate": 9.573158848078732e-06, "loss": 0.3892, "step": 184410 }, { "epoch": 1.0962307779184575, "grad_norm": 7.2449774742126465, "learning_rate": 9.573074957579404e-06, "loss": 0.4226, "step": 184420 }, { "epoch": 1.0962902199951257, "grad_norm": 6.123180389404297, "learning_rate": 9.572991059204694e-06, "loss": 0.4016, "step": 184430 }, { "epoch": 1.096349662071794, "grad_norm": 5.594692707061768, "learning_rate": 9.572907152954748e-06, "loss": 0.445, "step": 184440 }, { "epoch": 1.0964091041484625, "grad_norm": 5.625237464904785, "learning_rate": 9.572823238829714e-06, "loss": 0.3925, "step": 184450 }, { "epoch": 1.096468546225131, "grad_norm": 4.4599432945251465, "learning_rate": 9.572739316829729e-06, "loss": 0.3873, "step": 184460 }, { "epoch": 1.0965279883017993, "grad_norm": 5.994465351104736, "learning_rate": 9.572655386954943e-06, "loss": 0.3849, "step": 184470 }, { "epoch": 1.0965874303784677, "grad_norm": 4.607025146484375, "learning_rate": 9.572571449205497e-06, "loss": 0.4073, "step": 184480 }, { "epoch": 1.0966468724551361, "grad_norm": 7.152822494506836, "learning_rate": 9.57248750358154e-06, "loss": 0.4409, "step": 184490 }, { "epoch": 1.0967063145318046, "grad_norm": 5.379432678222656, "learning_rate": 9.572403550083211e-06, "loss": 0.4321, "step": 184500 }, { "epoch": 1.096765756608473, "grad_norm": 6.457536220550537, "learning_rate": 9.572319588710658e-06, "loss": 0.3889, "step": 184510 }, { "epoch": 1.0968251986851412, "grad_norm": 4.501596450805664, "learning_rate": 9.572235619464028e-06, "loss": 0.4209, "step": 184520 }, { "epoch": 1.0968846407618096, "grad_norm": 4.519650459289551, "learning_rate": 9.57215164234346e-06, "loss": 0.3996, "step": 184530 }, { "epoch": 1.096944082838478, "grad_norm": 6.0536580085754395, "learning_rate": 9.572067657349103e-06, "loss": 0.4174, "step": 184540 }, { "epoch": 1.0970035249151464, "grad_norm": 5.096256256103516, "learning_rate": 9.571983664481099e-06, "loss": 0.399, "step": 184550 }, { "epoch": 1.0970629669918148, "grad_norm": 4.779609203338623, "learning_rate": 9.571899663739593e-06, "loss": 0.3912, "step": 184560 }, { "epoch": 1.0971224090684832, "grad_norm": 3.516646385192871, "learning_rate": 9.571815655124729e-06, "loss": 0.389, "step": 184570 }, { "epoch": 1.0971818511451517, "grad_norm": 5.413943767547607, "learning_rate": 9.571731638636657e-06, "loss": 0.4245, "step": 184580 }, { "epoch": 1.09724129322182, "grad_norm": 5.326735496520996, "learning_rate": 9.571647614275514e-06, "loss": 0.3946, "step": 184590 }, { "epoch": 1.0973007352984885, "grad_norm": 4.786615371704102, "learning_rate": 9.571563582041451e-06, "loss": 0.4021, "step": 184600 }, { "epoch": 1.0973601773751567, "grad_norm": 4.877232551574707, "learning_rate": 9.57147954193461e-06, "loss": 0.4157, "step": 184610 }, { "epoch": 1.097419619451825, "grad_norm": 4.4728684425354, "learning_rate": 9.571395493955133e-06, "loss": 0.4217, "step": 184620 }, { "epoch": 1.0974790615284935, "grad_norm": 3.7894513607025146, "learning_rate": 9.57131143810317e-06, "loss": 0.4133, "step": 184630 }, { "epoch": 1.097538503605162, "grad_norm": 5.046781063079834, "learning_rate": 9.571227374378862e-06, "loss": 0.3921, "step": 184640 }, { "epoch": 1.0975979456818303, "grad_norm": 5.12869930267334, "learning_rate": 9.571143302782356e-06, "loss": 0.3898, "step": 184650 }, { "epoch": 1.0976573877584987, "grad_norm": 5.570610523223877, "learning_rate": 9.571059223313794e-06, "loss": 0.4141, "step": 184660 }, { "epoch": 1.0977168298351672, "grad_norm": 5.596194267272949, "learning_rate": 9.570975135973323e-06, "loss": 0.421, "step": 184670 }, { "epoch": 1.0977762719118356, "grad_norm": 4.378507137298584, "learning_rate": 9.57089104076109e-06, "loss": 0.4182, "step": 184680 }, { "epoch": 1.097835713988504, "grad_norm": 4.362967491149902, "learning_rate": 9.570806937677234e-06, "loss": 0.4044, "step": 184690 }, { "epoch": 1.0978951560651722, "grad_norm": 5.599686145782471, "learning_rate": 9.570722826721905e-06, "loss": 0.4356, "step": 184700 }, { "epoch": 1.0979545981418406, "grad_norm": 4.203041076660156, "learning_rate": 9.570638707895246e-06, "loss": 0.4041, "step": 184710 }, { "epoch": 1.098014040218509, "grad_norm": 5.6052775382995605, "learning_rate": 9.570554581197402e-06, "loss": 0.4142, "step": 184720 }, { "epoch": 1.0980734822951774, "grad_norm": 5.866065979003906, "learning_rate": 9.570470446628517e-06, "loss": 0.3941, "step": 184730 }, { "epoch": 1.0981329243718458, "grad_norm": 4.984190464019775, "learning_rate": 9.570386304188736e-06, "loss": 0.4032, "step": 184740 }, { "epoch": 1.0981923664485143, "grad_norm": 5.3964409828186035, "learning_rate": 9.570302153878206e-06, "loss": 0.4149, "step": 184750 }, { "epoch": 1.0982518085251827, "grad_norm": 6.27867317199707, "learning_rate": 9.570217995697069e-06, "loss": 0.4627, "step": 184760 }, { "epoch": 1.098311250601851, "grad_norm": 5.016286849975586, "learning_rate": 9.570133829645472e-06, "loss": 0.4167, "step": 184770 }, { "epoch": 1.0983706926785195, "grad_norm": 5.343871593475342, "learning_rate": 9.570049655723559e-06, "loss": 0.4225, "step": 184780 }, { "epoch": 1.098430134755188, "grad_norm": 5.690311431884766, "learning_rate": 9.569965473931474e-06, "loss": 0.4447, "step": 184790 }, { "epoch": 1.098489576831856, "grad_norm": 5.697225093841553, "learning_rate": 9.569881284269364e-06, "loss": 0.4567, "step": 184800 }, { "epoch": 1.0985490189085245, "grad_norm": 4.183588027954102, "learning_rate": 9.569797086737373e-06, "loss": 0.387, "step": 184810 }, { "epoch": 1.098608460985193, "grad_norm": 5.711824893951416, "learning_rate": 9.569712881335646e-06, "loss": 0.457, "step": 184820 }, { "epoch": 1.0986679030618614, "grad_norm": 4.7542901039123535, "learning_rate": 9.56962866806433e-06, "loss": 0.4177, "step": 184830 }, { "epoch": 1.0987273451385298, "grad_norm": 5.693793296813965, "learning_rate": 9.569544446923566e-06, "loss": 0.3786, "step": 184840 }, { "epoch": 1.0987867872151982, "grad_norm": 3.6072428226470947, "learning_rate": 9.569460217913503e-06, "loss": 0.3996, "step": 184850 }, { "epoch": 1.0988462292918666, "grad_norm": 5.773532390594482, "learning_rate": 9.569375981034283e-06, "loss": 0.4222, "step": 184860 }, { "epoch": 1.098905671368535, "grad_norm": 6.729175090789795, "learning_rate": 9.569291736286053e-06, "loss": 0.4168, "step": 184870 }, { "epoch": 1.0989651134452034, "grad_norm": 5.5864644050598145, "learning_rate": 9.569207483668958e-06, "loss": 0.4217, "step": 184880 }, { "epoch": 1.0990245555218716, "grad_norm": 5.029543399810791, "learning_rate": 9.569123223183142e-06, "loss": 0.4043, "step": 184890 }, { "epoch": 1.09908399759854, "grad_norm": 6.349591255187988, "learning_rate": 9.56903895482875e-06, "loss": 0.4248, "step": 184900 }, { "epoch": 1.0991434396752084, "grad_norm": 3.8236944675445557, "learning_rate": 9.568954678605928e-06, "loss": 0.3892, "step": 184910 }, { "epoch": 1.0992028817518769, "grad_norm": 6.413178443908691, "learning_rate": 9.568870394514821e-06, "loss": 0.3943, "step": 184920 }, { "epoch": 1.0992623238285453, "grad_norm": 6.104703426361084, "learning_rate": 9.568786102555574e-06, "loss": 0.4405, "step": 184930 }, { "epoch": 1.0993217659052137, "grad_norm": 5.528224945068359, "learning_rate": 9.568701802728333e-06, "loss": 0.4234, "step": 184940 }, { "epoch": 1.099381207981882, "grad_norm": 5.348651885986328, "learning_rate": 9.56861749503324e-06, "loss": 0.3879, "step": 184950 }, { "epoch": 1.0994406500585505, "grad_norm": 4.264646530151367, "learning_rate": 9.568533179470446e-06, "loss": 0.4274, "step": 184960 }, { "epoch": 1.099500092135219, "grad_norm": 4.748101234436035, "learning_rate": 9.56844885604009e-06, "loss": 0.4106, "step": 184970 }, { "epoch": 1.0995595342118871, "grad_norm": 5.760889053344727, "learning_rate": 9.568364524742321e-06, "loss": 0.4185, "step": 184980 }, { "epoch": 1.0996189762885555, "grad_norm": 4.933648586273193, "learning_rate": 9.568280185577283e-06, "loss": 0.4008, "step": 184990 }, { "epoch": 1.099678418365224, "grad_norm": 4.9225077629089355, "learning_rate": 9.568195838545122e-06, "loss": 0.3858, "step": 185000 }, { "epoch": 1.0997378604418924, "grad_norm": 6.0634965896606445, "learning_rate": 9.568111483645981e-06, "loss": 0.4056, "step": 185010 }, { "epoch": 1.0997973025185608, "grad_norm": 4.801777362823486, "learning_rate": 9.568027120880009e-06, "loss": 0.3883, "step": 185020 }, { "epoch": 1.0998567445952292, "grad_norm": 4.287352085113525, "learning_rate": 9.567942750247348e-06, "loss": 0.4232, "step": 185030 }, { "epoch": 1.0999161866718976, "grad_norm": 4.179465293884277, "learning_rate": 9.567858371748146e-06, "loss": 0.3994, "step": 185040 }, { "epoch": 1.099975628748566, "grad_norm": 4.673828125, "learning_rate": 9.567773985382545e-06, "loss": 0.4022, "step": 185050 }, { "epoch": 1.1000350708252344, "grad_norm": 5.772889614105225, "learning_rate": 9.567689591150692e-06, "loss": 0.398, "step": 185060 }, { "epoch": 1.1000945129019026, "grad_norm": 5.8336501121521, "learning_rate": 9.567605189052736e-06, "loss": 0.4463, "step": 185070 }, { "epoch": 1.100153954978571, "grad_norm": 5.0603132247924805, "learning_rate": 9.567520779088815e-06, "loss": 0.4388, "step": 185080 }, { "epoch": 1.1002133970552395, "grad_norm": 4.107059955596924, "learning_rate": 9.56743636125908e-06, "loss": 0.4605, "step": 185090 }, { "epoch": 1.1002728391319079, "grad_norm": 4.569031715393066, "learning_rate": 9.567351935563674e-06, "loss": 0.407, "step": 185100 }, { "epoch": 1.1003322812085763, "grad_norm": 5.999263286590576, "learning_rate": 9.567267502002743e-06, "loss": 0.3923, "step": 185110 }, { "epoch": 1.1003917232852447, "grad_norm": 4.393284320831299, "learning_rate": 9.567183060576433e-06, "loss": 0.3715, "step": 185120 }, { "epoch": 1.1004511653619131, "grad_norm": 6.739772319793701, "learning_rate": 9.567098611284889e-06, "loss": 0.4335, "step": 185130 }, { "epoch": 1.1005106074385815, "grad_norm": 4.892870903015137, "learning_rate": 9.567014154128256e-06, "loss": 0.4108, "step": 185140 }, { "epoch": 1.10057004951525, "grad_norm": 4.5688934326171875, "learning_rate": 9.566929689106679e-06, "loss": 0.3835, "step": 185150 }, { "epoch": 1.1006294915919184, "grad_norm": 5.337288856506348, "learning_rate": 9.566845216220304e-06, "loss": 0.431, "step": 185160 }, { "epoch": 1.1006889336685866, "grad_norm": 4.118907451629639, "learning_rate": 9.566760735469277e-06, "loss": 0.4161, "step": 185170 }, { "epoch": 1.100748375745255, "grad_norm": 6.723489761352539, "learning_rate": 9.566676246853745e-06, "loss": 0.3974, "step": 185180 }, { "epoch": 1.1008078178219234, "grad_norm": 6.239999771118164, "learning_rate": 9.56659175037385e-06, "loss": 0.4724, "step": 185190 }, { "epoch": 1.1008672598985918, "grad_norm": 4.149944305419922, "learning_rate": 9.566507246029739e-06, "loss": 0.4203, "step": 185200 }, { "epoch": 1.1009267019752602, "grad_norm": 4.479641437530518, "learning_rate": 9.566422733821557e-06, "loss": 0.3976, "step": 185210 }, { "epoch": 1.1009861440519286, "grad_norm": 5.470020771026611, "learning_rate": 9.566338213749451e-06, "loss": 0.3565, "step": 185220 }, { "epoch": 1.101045586128597, "grad_norm": 3.9545459747314453, "learning_rate": 9.566253685813566e-06, "loss": 0.3885, "step": 185230 }, { "epoch": 1.1011050282052655, "grad_norm": 7.416565895080566, "learning_rate": 9.566169150014046e-06, "loss": 0.4309, "step": 185240 }, { "epoch": 1.1011644702819339, "grad_norm": 5.5898356437683105, "learning_rate": 9.56608460635104e-06, "loss": 0.3632, "step": 185250 }, { "epoch": 1.101223912358602, "grad_norm": 4.750616550445557, "learning_rate": 9.56600005482469e-06, "loss": 0.4, "step": 185260 }, { "epoch": 1.1012833544352705, "grad_norm": 6.369289875030518, "learning_rate": 9.565915495435143e-06, "loss": 0.4411, "step": 185270 }, { "epoch": 1.101342796511939, "grad_norm": 5.145721435546875, "learning_rate": 9.565830928182545e-06, "loss": 0.4138, "step": 185280 }, { "epoch": 1.1014022385886073, "grad_norm": 4.4342041015625, "learning_rate": 9.565746353067042e-06, "loss": 0.393, "step": 185290 }, { "epoch": 1.1014616806652757, "grad_norm": 4.934176921844482, "learning_rate": 9.565661770088778e-06, "loss": 0.4269, "step": 185300 }, { "epoch": 1.1015211227419441, "grad_norm": 4.858887672424316, "learning_rate": 9.5655771792479e-06, "loss": 0.4204, "step": 185310 }, { "epoch": 1.1015805648186126, "grad_norm": 5.098814487457275, "learning_rate": 9.565492580544556e-06, "loss": 0.3858, "step": 185320 }, { "epoch": 1.101640006895281, "grad_norm": 5.086664199829102, "learning_rate": 9.565407973978885e-06, "loss": 0.3971, "step": 185330 }, { "epoch": 1.1016994489719494, "grad_norm": 4.644358158111572, "learning_rate": 9.565323359551038e-06, "loss": 0.3987, "step": 185340 }, { "epoch": 1.1017588910486176, "grad_norm": 4.390746116638184, "learning_rate": 9.56523873726116e-06, "loss": 0.4011, "step": 185350 }, { "epoch": 1.101818333125286, "grad_norm": 5.876929759979248, "learning_rate": 9.565154107109395e-06, "loss": 0.4018, "step": 185360 }, { "epoch": 1.1018777752019544, "grad_norm": 5.16617488861084, "learning_rate": 9.565069469095892e-06, "loss": 0.389, "step": 185370 }, { "epoch": 1.1019372172786228, "grad_norm": 5.796459674835205, "learning_rate": 9.564984823220793e-06, "loss": 0.3908, "step": 185380 }, { "epoch": 1.1019966593552912, "grad_norm": 4.7638092041015625, "learning_rate": 9.564900169484248e-06, "loss": 0.4085, "step": 185390 }, { "epoch": 1.1020561014319596, "grad_norm": 5.669353485107422, "learning_rate": 9.564815507886398e-06, "loss": 0.4313, "step": 185400 }, { "epoch": 1.102115543508628, "grad_norm": 5.244164943695068, "learning_rate": 9.564730838427391e-06, "loss": 0.4216, "step": 185410 }, { "epoch": 1.1021749855852965, "grad_norm": 6.135263919830322, "learning_rate": 9.564646161107373e-06, "loss": 0.4053, "step": 185420 }, { "epoch": 1.1022344276619649, "grad_norm": 4.132507801055908, "learning_rate": 9.56456147592649e-06, "loss": 0.413, "step": 185430 }, { "epoch": 1.102293869738633, "grad_norm": 3.5881264209747314, "learning_rate": 9.564476782884886e-06, "loss": 0.3732, "step": 185440 }, { "epoch": 1.1023533118153015, "grad_norm": 5.233328819274902, "learning_rate": 9.56439208198271e-06, "loss": 0.4283, "step": 185450 }, { "epoch": 1.10241275389197, "grad_norm": 5.51202917098999, "learning_rate": 9.564307373220106e-06, "loss": 0.4584, "step": 185460 }, { "epoch": 1.1024721959686383, "grad_norm": 10.439855575561523, "learning_rate": 9.564222656597219e-06, "loss": 0.4046, "step": 185470 }, { "epoch": 1.1025316380453067, "grad_norm": 4.997196674346924, "learning_rate": 9.564137932114198e-06, "loss": 0.3972, "step": 185480 }, { "epoch": 1.1025910801219752, "grad_norm": 4.76161003112793, "learning_rate": 9.564053199771186e-06, "loss": 0.4248, "step": 185490 }, { "epoch": 1.1026505221986436, "grad_norm": 4.146120071411133, "learning_rate": 9.56396845956833e-06, "loss": 0.4361, "step": 185500 }, { "epoch": 1.102709964275312, "grad_norm": 5.8644328117370605, "learning_rate": 9.563883711505775e-06, "loss": 0.3929, "step": 185510 }, { "epoch": 1.1027694063519804, "grad_norm": 5.202303409576416, "learning_rate": 9.563798955583668e-06, "loss": 0.3938, "step": 185520 }, { "epoch": 1.1028288484286488, "grad_norm": 6.749759674072266, "learning_rate": 9.563714191802155e-06, "loss": 0.4451, "step": 185530 }, { "epoch": 1.102888290505317, "grad_norm": 4.153453350067139, "learning_rate": 9.563629420161382e-06, "loss": 0.4036, "step": 185540 }, { "epoch": 1.1029477325819854, "grad_norm": 3.598573923110962, "learning_rate": 9.563544640661492e-06, "loss": 0.4115, "step": 185550 }, { "epoch": 1.1030071746586538, "grad_norm": 6.324011325836182, "learning_rate": 9.563459853302636e-06, "loss": 0.3945, "step": 185560 }, { "epoch": 1.1030666167353222, "grad_norm": 5.8605170249938965, "learning_rate": 9.563375058084958e-06, "loss": 0.4014, "step": 185570 }, { "epoch": 1.1031260588119907, "grad_norm": 5.126451015472412, "learning_rate": 9.563290255008604e-06, "loss": 0.4153, "step": 185580 }, { "epoch": 1.103185500888659, "grad_norm": 6.007073402404785, "learning_rate": 9.563205444073718e-06, "loss": 0.4168, "step": 185590 }, { "epoch": 1.1032449429653275, "grad_norm": 5.3619232177734375, "learning_rate": 9.563120625280448e-06, "loss": 0.4669, "step": 185600 }, { "epoch": 1.103304385041996, "grad_norm": 5.864057540893555, "learning_rate": 9.563035798628942e-06, "loss": 0.3858, "step": 185610 }, { "epoch": 1.1033638271186643, "grad_norm": 4.955806255340576, "learning_rate": 9.562950964119341e-06, "loss": 0.4523, "step": 185620 }, { "epoch": 1.1034232691953325, "grad_norm": 3.364130735397339, "learning_rate": 9.562866121751794e-06, "loss": 0.3695, "step": 185630 }, { "epoch": 1.103482711272001, "grad_norm": 5.357413291931152, "learning_rate": 9.56278127152645e-06, "loss": 0.4477, "step": 185640 }, { "epoch": 1.1035421533486693, "grad_norm": 5.119192600250244, "learning_rate": 9.56269641344345e-06, "loss": 0.4017, "step": 185650 }, { "epoch": 1.1036015954253378, "grad_norm": 4.274770259857178, "learning_rate": 9.562611547502943e-06, "loss": 0.4099, "step": 185660 }, { "epoch": 1.1036610375020062, "grad_norm": 3.6566853523254395, "learning_rate": 9.562526673705074e-06, "loss": 0.4008, "step": 185670 }, { "epoch": 1.1037204795786746, "grad_norm": 7.063771724700928, "learning_rate": 9.56244179204999e-06, "loss": 0.4152, "step": 185680 }, { "epoch": 1.103779921655343, "grad_norm": 4.4318976402282715, "learning_rate": 9.562356902537837e-06, "loss": 0.3552, "step": 185690 }, { "epoch": 1.1038393637320114, "grad_norm": 3.8714189529418945, "learning_rate": 9.56227200516876e-06, "loss": 0.3818, "step": 185700 }, { "epoch": 1.1038988058086798, "grad_norm": 5.040711879730225, "learning_rate": 9.562187099942907e-06, "loss": 0.4546, "step": 185710 }, { "epoch": 1.103958247885348, "grad_norm": 5.432076454162598, "learning_rate": 9.562102186860425e-06, "loss": 0.4227, "step": 185720 }, { "epoch": 1.1040176899620164, "grad_norm": 4.9004807472229, "learning_rate": 9.562017265921456e-06, "loss": 0.4097, "step": 185730 }, { "epoch": 1.1040771320386848, "grad_norm": 4.974296569824219, "learning_rate": 9.56193233712615e-06, "loss": 0.4322, "step": 185740 }, { "epoch": 1.1041365741153533, "grad_norm": 4.203306674957275, "learning_rate": 9.561847400474652e-06, "loss": 0.3785, "step": 185750 }, { "epoch": 1.1041960161920217, "grad_norm": 4.703953742980957, "learning_rate": 9.56176245596711e-06, "loss": 0.4274, "step": 185760 }, { "epoch": 1.10425545826869, "grad_norm": 5.757498264312744, "learning_rate": 9.561677503603668e-06, "loss": 0.4621, "step": 185770 }, { "epoch": 1.1043149003453585, "grad_norm": 5.219010829925537, "learning_rate": 9.561592543384473e-06, "loss": 0.4324, "step": 185780 }, { "epoch": 1.104374342422027, "grad_norm": 7.074261665344238, "learning_rate": 9.56150757530967e-06, "loss": 0.435, "step": 185790 }, { "epoch": 1.1044337844986953, "grad_norm": 4.6324872970581055, "learning_rate": 9.561422599379409e-06, "loss": 0.3648, "step": 185800 }, { "epoch": 1.1044932265753635, "grad_norm": 4.817239284515381, "learning_rate": 9.561337615593831e-06, "loss": 0.3878, "step": 185810 }, { "epoch": 1.104552668652032, "grad_norm": 5.466546535491943, "learning_rate": 9.561252623953088e-06, "loss": 0.4048, "step": 185820 }, { "epoch": 1.1046121107287004, "grad_norm": 4.676999568939209, "learning_rate": 9.561167624457323e-06, "loss": 0.4194, "step": 185830 }, { "epoch": 1.1046715528053688, "grad_norm": 6.185957431793213, "learning_rate": 9.561082617106684e-06, "loss": 0.4299, "step": 185840 }, { "epoch": 1.1047309948820372, "grad_norm": 5.5292744636535645, "learning_rate": 9.560997601901315e-06, "loss": 0.3954, "step": 185850 }, { "epoch": 1.1047904369587056, "grad_norm": 5.033553600311279, "learning_rate": 9.560912578841364e-06, "loss": 0.4179, "step": 185860 }, { "epoch": 1.104849879035374, "grad_norm": 4.23005485534668, "learning_rate": 9.560827547926978e-06, "loss": 0.4092, "step": 185870 }, { "epoch": 1.1049093211120424, "grad_norm": 5.7236552238464355, "learning_rate": 9.560742509158301e-06, "loss": 0.4119, "step": 185880 }, { "epoch": 1.1049687631887108, "grad_norm": 4.435645580291748, "learning_rate": 9.560657462535484e-06, "loss": 0.4068, "step": 185890 }, { "epoch": 1.1050282052653793, "grad_norm": 6.794802188873291, "learning_rate": 9.56057240805867e-06, "loss": 0.4136, "step": 185900 }, { "epoch": 1.1050876473420475, "grad_norm": 5.556999206542969, "learning_rate": 9.560487345728004e-06, "loss": 0.411, "step": 185910 }, { "epoch": 1.1051470894187159, "grad_norm": 6.209329128265381, "learning_rate": 9.560402275543636e-06, "loss": 0.4218, "step": 185920 }, { "epoch": 1.1052065314953843, "grad_norm": 4.324024677276611, "learning_rate": 9.560317197505714e-06, "loss": 0.4108, "step": 185930 }, { "epoch": 1.1052659735720527, "grad_norm": 4.746786594390869, "learning_rate": 9.560232111614378e-06, "loss": 0.4317, "step": 185940 }, { "epoch": 1.105325415648721, "grad_norm": 5.06550407409668, "learning_rate": 9.560147017869778e-06, "loss": 0.4161, "step": 185950 }, { "epoch": 1.1053848577253895, "grad_norm": 3.9943125247955322, "learning_rate": 9.560061916272063e-06, "loss": 0.4206, "step": 185960 }, { "epoch": 1.105444299802058, "grad_norm": 5.709838390350342, "learning_rate": 9.559976806821375e-06, "loss": 0.3755, "step": 185970 }, { "epoch": 1.1055037418787264, "grad_norm": 4.459173202514648, "learning_rate": 9.559891689517864e-06, "loss": 0.4188, "step": 185980 }, { "epoch": 1.1055631839553948, "grad_norm": 6.422900199890137, "learning_rate": 9.559806564361675e-06, "loss": 0.3987, "step": 185990 }, { "epoch": 1.105622626032063, "grad_norm": 3.8066446781158447, "learning_rate": 9.559721431352957e-06, "loss": 0.3972, "step": 186000 }, { "epoch": 1.1056820681087314, "grad_norm": 5.610835552215576, "learning_rate": 9.559636290491854e-06, "loss": 0.3907, "step": 186010 }, { "epoch": 1.1057415101853998, "grad_norm": 6.948763847351074, "learning_rate": 9.559551141778511e-06, "loss": 0.4125, "step": 186020 }, { "epoch": 1.1058009522620682, "grad_norm": 4.326054096221924, "learning_rate": 9.559465985213079e-06, "loss": 0.3455, "step": 186030 }, { "epoch": 1.1058603943387366, "grad_norm": 4.519001483917236, "learning_rate": 9.559380820795703e-06, "loss": 0.3687, "step": 186040 }, { "epoch": 1.105919836415405, "grad_norm": 6.560211181640625, "learning_rate": 9.559295648526527e-06, "loss": 0.4368, "step": 186050 }, { "epoch": 1.1059792784920734, "grad_norm": 5.818562030792236, "learning_rate": 9.5592104684057e-06, "loss": 0.3935, "step": 186060 }, { "epoch": 1.1060387205687419, "grad_norm": 4.482162952423096, "learning_rate": 9.55912528043337e-06, "loss": 0.4001, "step": 186070 }, { "epoch": 1.1060981626454103, "grad_norm": 5.0753889083862305, "learning_rate": 9.559040084609681e-06, "loss": 0.3976, "step": 186080 }, { "epoch": 1.1061576047220785, "grad_norm": 5.110920429229736, "learning_rate": 9.558954880934784e-06, "loss": 0.3858, "step": 186090 }, { "epoch": 1.1062170467987469, "grad_norm": 4.746794700622559, "learning_rate": 9.55886966940882e-06, "loss": 0.4077, "step": 186100 }, { "epoch": 1.1062764888754153, "grad_norm": 4.902775764465332, "learning_rate": 9.558784450031939e-06, "loss": 0.3606, "step": 186110 }, { "epoch": 1.1063359309520837, "grad_norm": 4.248501300811768, "learning_rate": 9.558699222804286e-06, "loss": 0.3803, "step": 186120 }, { "epoch": 1.1063953730287521, "grad_norm": 3.9468014240264893, "learning_rate": 9.558613987726012e-06, "loss": 0.3801, "step": 186130 }, { "epoch": 1.1064548151054205, "grad_norm": 5.98638391494751, "learning_rate": 9.558528744797258e-06, "loss": 0.3947, "step": 186140 }, { "epoch": 1.106514257182089, "grad_norm": 5.552487373352051, "learning_rate": 9.558443494018174e-06, "loss": 0.4123, "step": 186150 }, { "epoch": 1.1065736992587574, "grad_norm": 5.4218926429748535, "learning_rate": 9.558358235388908e-06, "loss": 0.3812, "step": 186160 }, { "epoch": 1.1066331413354258, "grad_norm": 4.991089820861816, "learning_rate": 9.558272968909604e-06, "loss": 0.3955, "step": 186170 }, { "epoch": 1.106692583412094, "grad_norm": 5.078907489776611, "learning_rate": 9.55818769458041e-06, "loss": 0.4431, "step": 186180 }, { "epoch": 1.1067520254887624, "grad_norm": 4.649806499481201, "learning_rate": 9.558102412401473e-06, "loss": 0.3955, "step": 186190 }, { "epoch": 1.1068114675654308, "grad_norm": 6.446650981903076, "learning_rate": 9.55801712237294e-06, "loss": 0.3773, "step": 186200 }, { "epoch": 1.1068709096420992, "grad_norm": 4.181961536407471, "learning_rate": 9.55793182449496e-06, "loss": 0.4027, "step": 186210 }, { "epoch": 1.1069303517187676, "grad_norm": 5.72929048538208, "learning_rate": 9.557846518767674e-06, "loss": 0.4113, "step": 186220 }, { "epoch": 1.106989793795436, "grad_norm": 4.470676898956299, "learning_rate": 9.557761205191235e-06, "loss": 0.4315, "step": 186230 }, { "epoch": 1.1070492358721045, "grad_norm": 5.369844913482666, "learning_rate": 9.557675883765785e-06, "loss": 0.4544, "step": 186240 }, { "epoch": 1.1071086779487729, "grad_norm": 5.996792793273926, "learning_rate": 9.557590554491473e-06, "loss": 0.449, "step": 186250 }, { "epoch": 1.1071681200254413, "grad_norm": 4.147791385650635, "learning_rate": 9.557505217368448e-06, "loss": 0.3831, "step": 186260 }, { "epoch": 1.1072275621021097, "grad_norm": 5.579563617706299, "learning_rate": 9.557419872396856e-06, "loss": 0.422, "step": 186270 }, { "epoch": 1.107287004178778, "grad_norm": 3.6595451831817627, "learning_rate": 9.557334519576842e-06, "loss": 0.3536, "step": 186280 }, { "epoch": 1.1073464462554463, "grad_norm": 7.199141979217529, "learning_rate": 9.557249158908554e-06, "loss": 0.4518, "step": 186290 }, { "epoch": 1.1074058883321147, "grad_norm": 5.55830717086792, "learning_rate": 9.557163790392138e-06, "loss": 0.4252, "step": 186300 }, { "epoch": 1.1074653304087831, "grad_norm": 4.146237373352051, "learning_rate": 9.557078414027745e-06, "loss": 0.4317, "step": 186310 }, { "epoch": 1.1075247724854516, "grad_norm": 5.68203067779541, "learning_rate": 9.556993029815518e-06, "loss": 0.3933, "step": 186320 }, { "epoch": 1.10758421456212, "grad_norm": 4.098933219909668, "learning_rate": 9.556907637755606e-06, "loss": 0.418, "step": 186330 }, { "epoch": 1.1076436566387884, "grad_norm": 6.119257926940918, "learning_rate": 9.556822237848154e-06, "loss": 0.3964, "step": 186340 }, { "epoch": 1.1077030987154568, "grad_norm": 4.627746105194092, "learning_rate": 9.556736830093311e-06, "loss": 0.4158, "step": 186350 }, { "epoch": 1.1077625407921252, "grad_norm": 4.402430057525635, "learning_rate": 9.556651414491223e-06, "loss": 0.3718, "step": 186360 }, { "epoch": 1.1078219828687934, "grad_norm": 5.855434417724609, "learning_rate": 9.556565991042037e-06, "loss": 0.4234, "step": 186370 }, { "epoch": 1.1078814249454618, "grad_norm": 4.418439865112305, "learning_rate": 9.556480559745902e-06, "loss": 0.3796, "step": 186380 }, { "epoch": 1.1079408670221302, "grad_norm": 6.507144927978516, "learning_rate": 9.556395120602964e-06, "loss": 0.426, "step": 186390 }, { "epoch": 1.1080003090987987, "grad_norm": 6.272754669189453, "learning_rate": 9.556309673613368e-06, "loss": 0.3774, "step": 186400 }, { "epoch": 1.108059751175467, "grad_norm": 6.169849872589111, "learning_rate": 9.556224218777266e-06, "loss": 0.4577, "step": 186410 }, { "epoch": 1.1081191932521355, "grad_norm": 4.96497917175293, "learning_rate": 9.556138756094801e-06, "loss": 0.3959, "step": 186420 }, { "epoch": 1.108178635328804, "grad_norm": 4.413745880126953, "learning_rate": 9.556053285566121e-06, "loss": 0.4042, "step": 186430 }, { "epoch": 1.1082380774054723, "grad_norm": 6.045168399810791, "learning_rate": 9.555967807191373e-06, "loss": 0.3933, "step": 186440 }, { "epoch": 1.1082975194821407, "grad_norm": 5.009432315826416, "learning_rate": 9.555882320970706e-06, "loss": 0.4117, "step": 186450 }, { "epoch": 1.108356961558809, "grad_norm": 5.6074910163879395, "learning_rate": 9.555796826904266e-06, "loss": 0.3884, "step": 186460 }, { "epoch": 1.1084164036354773, "grad_norm": 2.906426429748535, "learning_rate": 9.555711324992199e-06, "loss": 0.3716, "step": 186470 }, { "epoch": 1.1084758457121457, "grad_norm": 5.996771812438965, "learning_rate": 9.555625815234655e-06, "loss": 0.4169, "step": 186480 }, { "epoch": 1.1085352877888142, "grad_norm": 7.03344202041626, "learning_rate": 9.555540297631778e-06, "loss": 0.397, "step": 186490 }, { "epoch": 1.1085947298654826, "grad_norm": 5.374759197235107, "learning_rate": 9.555454772183718e-06, "loss": 0.3895, "step": 186500 }, { "epoch": 1.108654171942151, "grad_norm": 5.381871700286865, "learning_rate": 9.555369238890623e-06, "loss": 0.3918, "step": 186510 }, { "epoch": 1.1087136140188194, "grad_norm": 7.998779773712158, "learning_rate": 9.555283697752638e-06, "loss": 0.4048, "step": 186520 }, { "epoch": 1.1087730560954878, "grad_norm": 5.791915416717529, "learning_rate": 9.55519814876991e-06, "loss": 0.3873, "step": 186530 }, { "epoch": 1.1088324981721562, "grad_norm": 5.74595832824707, "learning_rate": 9.555112591942587e-06, "loss": 0.3888, "step": 186540 }, { "epoch": 1.1088919402488244, "grad_norm": 5.189455509185791, "learning_rate": 9.555027027270817e-06, "loss": 0.4075, "step": 186550 }, { "epoch": 1.1089513823254928, "grad_norm": 4.632988929748535, "learning_rate": 9.554941454754747e-06, "loss": 0.3529, "step": 186560 }, { "epoch": 1.1090108244021613, "grad_norm": 4.58772611618042, "learning_rate": 9.554855874394525e-06, "loss": 0.3933, "step": 186570 }, { "epoch": 1.1090702664788297, "grad_norm": 4.64168119430542, "learning_rate": 9.554770286190297e-06, "loss": 0.3956, "step": 186580 }, { "epoch": 1.109129708555498, "grad_norm": 4.556711196899414, "learning_rate": 9.554684690142211e-06, "loss": 0.3708, "step": 186590 }, { "epoch": 1.1091891506321665, "grad_norm": 5.013128757476807, "learning_rate": 9.554599086250413e-06, "loss": 0.4251, "step": 186600 }, { "epoch": 1.109248592708835, "grad_norm": 5.2605180740356445, "learning_rate": 9.554513474515055e-06, "loss": 0.3895, "step": 186610 }, { "epoch": 1.1093080347855033, "grad_norm": 6.101594924926758, "learning_rate": 9.55442785493628e-06, "loss": 0.4051, "step": 186620 }, { "epoch": 1.1093674768621717, "grad_norm": 5.188047409057617, "learning_rate": 9.554342227514238e-06, "loss": 0.4062, "step": 186630 }, { "epoch": 1.1094269189388402, "grad_norm": 5.579773902893066, "learning_rate": 9.554256592249073e-06, "loss": 0.3761, "step": 186640 }, { "epoch": 1.1094863610155083, "grad_norm": 4.154452800750732, "learning_rate": 9.554170949140935e-06, "loss": 0.3718, "step": 186650 }, { "epoch": 1.1095458030921768, "grad_norm": 5.757342338562012, "learning_rate": 9.554085298189973e-06, "loss": 0.3848, "step": 186660 }, { "epoch": 1.1096052451688452, "grad_norm": 5.7486419677734375, "learning_rate": 9.553999639396331e-06, "loss": 0.4405, "step": 186670 }, { "epoch": 1.1096646872455136, "grad_norm": 5.779119491577148, "learning_rate": 9.553913972760157e-06, "loss": 0.4378, "step": 186680 }, { "epoch": 1.109724129322182, "grad_norm": 3.8333494663238525, "learning_rate": 9.553828298281604e-06, "loss": 0.4153, "step": 186690 }, { "epoch": 1.1097835713988504, "grad_norm": 4.36299991607666, "learning_rate": 9.553742615960812e-06, "loss": 0.3987, "step": 186700 }, { "epoch": 1.1098430134755188, "grad_norm": 6.55642557144165, "learning_rate": 9.553656925797934e-06, "loss": 0.3875, "step": 186710 }, { "epoch": 1.1099024555521873, "grad_norm": 3.9363722801208496, "learning_rate": 9.553571227793114e-06, "loss": 0.3959, "step": 186720 }, { "epoch": 1.1099618976288557, "grad_norm": 6.205900192260742, "learning_rate": 9.553485521946501e-06, "loss": 0.4191, "step": 186730 }, { "epoch": 1.1100213397055239, "grad_norm": 5.845083236694336, "learning_rate": 9.553399808258243e-06, "loss": 0.3854, "step": 186740 }, { "epoch": 1.1100807817821923, "grad_norm": 4.060489177703857, "learning_rate": 9.553314086728488e-06, "loss": 0.4371, "step": 186750 }, { "epoch": 1.1101402238588607, "grad_norm": 5.858819484710693, "learning_rate": 9.553228357357383e-06, "loss": 0.4214, "step": 186760 }, { "epoch": 1.110199665935529, "grad_norm": 6.338876724243164, "learning_rate": 9.553142620145074e-06, "loss": 0.3754, "step": 186770 }, { "epoch": 1.1102591080121975, "grad_norm": 5.076476573944092, "learning_rate": 9.553056875091711e-06, "loss": 0.3708, "step": 186780 }, { "epoch": 1.110318550088866, "grad_norm": 4.340886116027832, "learning_rate": 9.552971122197439e-06, "loss": 0.3957, "step": 186790 }, { "epoch": 1.1103779921655343, "grad_norm": 4.085009574890137, "learning_rate": 9.55288536146241e-06, "loss": 0.3957, "step": 186800 }, { "epoch": 1.1104374342422028, "grad_norm": 4.243887901306152, "learning_rate": 9.552799592886768e-06, "loss": 0.3993, "step": 186810 }, { "epoch": 1.1104968763188712, "grad_norm": 3.8966963291168213, "learning_rate": 9.552713816470662e-06, "loss": 0.3725, "step": 186820 }, { "epoch": 1.1105563183955394, "grad_norm": 6.274742126464844, "learning_rate": 9.552628032214239e-06, "loss": 0.4386, "step": 186830 }, { "epoch": 1.1106157604722078, "grad_norm": 4.372372627258301, "learning_rate": 9.552542240117649e-06, "loss": 0.3767, "step": 186840 }, { "epoch": 1.1106752025488762, "grad_norm": 5.971381664276123, "learning_rate": 9.552456440181037e-06, "loss": 0.3811, "step": 186850 }, { "epoch": 1.1107346446255446, "grad_norm": 4.591334342956543, "learning_rate": 9.552370632404551e-06, "loss": 0.3788, "step": 186860 }, { "epoch": 1.110794086702213, "grad_norm": 4.99350643157959, "learning_rate": 9.552284816788341e-06, "loss": 0.4519, "step": 186870 }, { "epoch": 1.1108535287788814, "grad_norm": 4.842700004577637, "learning_rate": 9.552198993332553e-06, "loss": 0.382, "step": 186880 }, { "epoch": 1.1109129708555499, "grad_norm": 5.68044900894165, "learning_rate": 9.552113162037335e-06, "loss": 0.4571, "step": 186890 }, { "epoch": 1.1109724129322183, "grad_norm": 5.498301029205322, "learning_rate": 9.552027322902835e-06, "loss": 0.4288, "step": 186900 }, { "epoch": 1.1110318550088867, "grad_norm": 4.562534332275391, "learning_rate": 9.5519414759292e-06, "loss": 0.4458, "step": 186910 }, { "epoch": 1.1110912970855549, "grad_norm": 6.393948554992676, "learning_rate": 9.55185562111658e-06, "loss": 0.4432, "step": 186920 }, { "epoch": 1.1111507391622233, "grad_norm": 6.440752983093262, "learning_rate": 9.551769758465121e-06, "loss": 0.4063, "step": 186930 }, { "epoch": 1.1112101812388917, "grad_norm": 4.6676201820373535, "learning_rate": 9.551683887974971e-06, "loss": 0.4244, "step": 186940 }, { "epoch": 1.1112696233155601, "grad_norm": 4.1238179206848145, "learning_rate": 9.551598009646279e-06, "loss": 0.4167, "step": 186950 }, { "epoch": 1.1113290653922285, "grad_norm": 4.80247688293457, "learning_rate": 9.551512123479192e-06, "loss": 0.4022, "step": 186960 }, { "epoch": 1.111388507468897, "grad_norm": 5.4410786628723145, "learning_rate": 9.551426229473857e-06, "loss": 0.4343, "step": 186970 }, { "epoch": 1.1114479495455654, "grad_norm": 5.024807929992676, "learning_rate": 9.551340327630424e-06, "loss": 0.4541, "step": 186980 }, { "epoch": 1.1115073916222338, "grad_norm": 4.9789204597473145, "learning_rate": 9.551254417949038e-06, "loss": 0.4137, "step": 186990 }, { "epoch": 1.1115668336989022, "grad_norm": 5.934354305267334, "learning_rate": 9.551168500429852e-06, "loss": 0.3923, "step": 187000 }, { "epoch": 1.1116262757755706, "grad_norm": 4.79732608795166, "learning_rate": 9.551082575073009e-06, "loss": 0.4004, "step": 187010 }, { "epoch": 1.1116857178522388, "grad_norm": 5.256310939788818, "learning_rate": 9.550996641878658e-06, "loss": 0.3954, "step": 187020 }, { "epoch": 1.1117451599289072, "grad_norm": 3.863145589828491, "learning_rate": 9.550910700846949e-06, "loss": 0.4134, "step": 187030 }, { "epoch": 1.1118046020055756, "grad_norm": 5.798676490783691, "learning_rate": 9.55082475197803e-06, "loss": 0.4079, "step": 187040 }, { "epoch": 1.111864044082244, "grad_norm": 5.6096510887146, "learning_rate": 9.550738795272045e-06, "loss": 0.3978, "step": 187050 }, { "epoch": 1.1119234861589125, "grad_norm": 5.282068729400635, "learning_rate": 9.550652830729146e-06, "loss": 0.4762, "step": 187060 }, { "epoch": 1.1119829282355809, "grad_norm": 5.2691521644592285, "learning_rate": 9.55056685834948e-06, "loss": 0.3937, "step": 187070 }, { "epoch": 1.1120423703122493, "grad_norm": 6.75429630279541, "learning_rate": 9.550480878133195e-06, "loss": 0.4035, "step": 187080 }, { "epoch": 1.1121018123889177, "grad_norm": 4.662505149841309, "learning_rate": 9.550394890080438e-06, "loss": 0.3746, "step": 187090 }, { "epoch": 1.1121612544655861, "grad_norm": 5.114966869354248, "learning_rate": 9.55030889419136e-06, "loss": 0.4295, "step": 187100 }, { "epoch": 1.1122206965422543, "grad_norm": 5.577969551086426, "learning_rate": 9.550222890466107e-06, "loss": 0.3996, "step": 187110 }, { "epoch": 1.1122801386189227, "grad_norm": 4.611698627471924, "learning_rate": 9.550136878904826e-06, "loss": 0.4127, "step": 187120 }, { "epoch": 1.1123395806955911, "grad_norm": 4.7112884521484375, "learning_rate": 9.550050859507667e-06, "loss": 0.3803, "step": 187130 }, { "epoch": 1.1123990227722595, "grad_norm": 5.020637035369873, "learning_rate": 9.549964832274777e-06, "loss": 0.3765, "step": 187140 }, { "epoch": 1.112458464848928, "grad_norm": 4.519139289855957, "learning_rate": 9.549878797206305e-06, "loss": 0.4009, "step": 187150 }, { "epoch": 1.1125179069255964, "grad_norm": 6.254006385803223, "learning_rate": 9.549792754302399e-06, "loss": 0.442, "step": 187160 }, { "epoch": 1.1125773490022648, "grad_norm": 4.517573833465576, "learning_rate": 9.549706703563207e-06, "loss": 0.3651, "step": 187170 }, { "epoch": 1.1126367910789332, "grad_norm": 5.855288505554199, "learning_rate": 9.549620644988874e-06, "loss": 0.4066, "step": 187180 }, { "epoch": 1.1126962331556016, "grad_norm": 5.349693298339844, "learning_rate": 9.549534578579555e-06, "loss": 0.4163, "step": 187190 }, { "epoch": 1.1127556752322698, "grad_norm": 6.890962600708008, "learning_rate": 9.549448504335394e-06, "loss": 0.4581, "step": 187200 }, { "epoch": 1.1128151173089382, "grad_norm": 5.393824577331543, "learning_rate": 9.54936242225654e-06, "loss": 0.3772, "step": 187210 }, { "epoch": 1.1128745593856066, "grad_norm": 5.688656330108643, "learning_rate": 9.549276332343143e-06, "loss": 0.3546, "step": 187220 }, { "epoch": 1.112934001462275, "grad_norm": 5.2464776039123535, "learning_rate": 9.549190234595345e-06, "loss": 0.366, "step": 187230 }, { "epoch": 1.1129934435389435, "grad_norm": 4.996942043304443, "learning_rate": 9.549104129013302e-06, "loss": 0.388, "step": 187240 }, { "epoch": 1.1130528856156119, "grad_norm": 3.82487416267395, "learning_rate": 9.549018015597158e-06, "loss": 0.3861, "step": 187250 }, { "epoch": 1.1131123276922803, "grad_norm": 4.261960506439209, "learning_rate": 9.548931894347062e-06, "loss": 0.4075, "step": 187260 }, { "epoch": 1.1131717697689487, "grad_norm": 6.535036563873291, "learning_rate": 9.548845765263162e-06, "loss": 0.3856, "step": 187270 }, { "epoch": 1.1132312118456171, "grad_norm": 5.219538688659668, "learning_rate": 9.548759628345607e-06, "loss": 0.4186, "step": 187280 }, { "epoch": 1.1132906539222853, "grad_norm": 5.185186386108398, "learning_rate": 9.548673483594545e-06, "loss": 0.4212, "step": 187290 }, { "epoch": 1.1133500959989537, "grad_norm": 5.05555534362793, "learning_rate": 9.548587331010125e-06, "loss": 0.3524, "step": 187300 }, { "epoch": 1.1134095380756222, "grad_norm": 5.880059719085693, "learning_rate": 9.548501170592494e-06, "loss": 0.4496, "step": 187310 }, { "epoch": 1.1134689801522906, "grad_norm": 5.859523296356201, "learning_rate": 9.548415002341803e-06, "loss": 0.3697, "step": 187320 }, { "epoch": 1.113528422228959, "grad_norm": 4.178834915161133, "learning_rate": 9.548328826258197e-06, "loss": 0.3694, "step": 187330 }, { "epoch": 1.1135878643056274, "grad_norm": 5.238140106201172, "learning_rate": 9.548242642341828e-06, "loss": 0.4597, "step": 187340 }, { "epoch": 1.1136473063822958, "grad_norm": 6.423460960388184, "learning_rate": 9.54815645059284e-06, "loss": 0.4397, "step": 187350 }, { "epoch": 1.1137067484589642, "grad_norm": 5.207249164581299, "learning_rate": 9.548070251011386e-06, "loss": 0.4255, "step": 187360 }, { "epoch": 1.1137661905356326, "grad_norm": 5.26812219619751, "learning_rate": 9.547984043597611e-06, "loss": 0.381, "step": 187370 }, { "epoch": 1.113825632612301, "grad_norm": 4.698534965515137, "learning_rate": 9.547897828351667e-06, "loss": 0.3976, "step": 187380 }, { "epoch": 1.1138850746889692, "grad_norm": 3.8842997550964355, "learning_rate": 9.547811605273698e-06, "loss": 0.4083, "step": 187390 }, { "epoch": 1.1139445167656377, "grad_norm": 5.579216957092285, "learning_rate": 9.547725374363855e-06, "loss": 0.3766, "step": 187400 }, { "epoch": 1.114003958842306, "grad_norm": 5.458441734313965, "learning_rate": 9.547639135622287e-06, "loss": 0.402, "step": 187410 }, { "epoch": 1.1140634009189745, "grad_norm": 5.6212544441223145, "learning_rate": 9.547552889049143e-06, "loss": 0.4052, "step": 187420 }, { "epoch": 1.114122842995643, "grad_norm": 4.648222923278809, "learning_rate": 9.547466634644567e-06, "loss": 0.3964, "step": 187430 }, { "epoch": 1.1141822850723113, "grad_norm": 4.013345718383789, "learning_rate": 9.547380372408714e-06, "loss": 0.4141, "step": 187440 }, { "epoch": 1.1142417271489797, "grad_norm": 5.22379207611084, "learning_rate": 9.547294102341727e-06, "loss": 0.38, "step": 187450 }, { "epoch": 1.1143011692256481, "grad_norm": 5.235823631286621, "learning_rate": 9.547207824443757e-06, "loss": 0.3865, "step": 187460 }, { "epoch": 1.1143606113023166, "grad_norm": 6.772678852081299, "learning_rate": 9.547121538714955e-06, "loss": 0.4041, "step": 187470 }, { "epoch": 1.1144200533789848, "grad_norm": 6.096920013427734, "learning_rate": 9.547035245155468e-06, "loss": 0.3659, "step": 187480 }, { "epoch": 1.1144794954556532, "grad_norm": 4.716372489929199, "learning_rate": 9.54694894376544e-06, "loss": 0.4345, "step": 187490 }, { "epoch": 1.1145389375323216, "grad_norm": 5.809646129608154, "learning_rate": 9.546862634545025e-06, "loss": 0.3991, "step": 187500 }, { "epoch": 1.11459837960899, "grad_norm": 4.714229583740234, "learning_rate": 9.54677631749437e-06, "loss": 0.4006, "step": 187510 }, { "epoch": 1.1146578216856584, "grad_norm": 6.179319381713867, "learning_rate": 9.546689992613624e-06, "loss": 0.3977, "step": 187520 }, { "epoch": 1.1147172637623268, "grad_norm": 5.23720121383667, "learning_rate": 9.546603659902936e-06, "loss": 0.3856, "step": 187530 }, { "epoch": 1.1147767058389952, "grad_norm": 5.046128749847412, "learning_rate": 9.546517319362452e-06, "loss": 0.4133, "step": 187540 }, { "epoch": 1.1148361479156637, "grad_norm": 5.235387325286865, "learning_rate": 9.546430970992324e-06, "loss": 0.4193, "step": 187550 }, { "epoch": 1.114895589992332, "grad_norm": 5.310765743255615, "learning_rate": 9.546344614792699e-06, "loss": 0.4319, "step": 187560 }, { "epoch": 1.1149550320690003, "grad_norm": 5.257723808288574, "learning_rate": 9.546258250763725e-06, "loss": 0.3933, "step": 187570 }, { "epoch": 1.1150144741456687, "grad_norm": 5.837343215942383, "learning_rate": 9.546171878905554e-06, "loss": 0.4052, "step": 187580 }, { "epoch": 1.115073916222337, "grad_norm": 5.971739768981934, "learning_rate": 9.546085499218331e-06, "loss": 0.3957, "step": 187590 }, { "epoch": 1.1151333582990055, "grad_norm": 4.892043113708496, "learning_rate": 9.545999111702208e-06, "loss": 0.3837, "step": 187600 }, { "epoch": 1.115192800375674, "grad_norm": 4.421487331390381, "learning_rate": 9.545912716357331e-06, "loss": 0.4004, "step": 187610 }, { "epoch": 1.1152522424523423, "grad_norm": 4.707298278808594, "learning_rate": 9.54582631318385e-06, "loss": 0.3822, "step": 187620 }, { "epoch": 1.1153116845290107, "grad_norm": 5.150506496429443, "learning_rate": 9.545739902181913e-06, "loss": 0.3965, "step": 187630 }, { "epoch": 1.1153711266056792, "grad_norm": 5.266822338104248, "learning_rate": 9.545653483351671e-06, "loss": 0.3859, "step": 187640 }, { "epoch": 1.1154305686823476, "grad_norm": 5.78713321685791, "learning_rate": 9.54556705669327e-06, "loss": 0.383, "step": 187650 }, { "epoch": 1.1154900107590158, "grad_norm": 5.221339702606201, "learning_rate": 9.545480622206861e-06, "loss": 0.4227, "step": 187660 }, { "epoch": 1.1155494528356842, "grad_norm": 7.672635078430176, "learning_rate": 9.54539417989259e-06, "loss": 0.3965, "step": 187670 }, { "epoch": 1.1156088949123526, "grad_norm": 7.230347633361816, "learning_rate": 9.54530772975061e-06, "loss": 0.3964, "step": 187680 }, { "epoch": 1.115668336989021, "grad_norm": 4.676631450653076, "learning_rate": 9.545221271781069e-06, "loss": 0.3982, "step": 187690 }, { "epoch": 1.1157277790656894, "grad_norm": 5.0630950927734375, "learning_rate": 9.545134805984112e-06, "loss": 0.3904, "step": 187700 }, { "epoch": 1.1157872211423578, "grad_norm": 6.402388572692871, "learning_rate": 9.545048332359891e-06, "loss": 0.375, "step": 187710 }, { "epoch": 1.1158466632190263, "grad_norm": 4.65382719039917, "learning_rate": 9.544961850908556e-06, "loss": 0.3858, "step": 187720 }, { "epoch": 1.1159061052956947, "grad_norm": 5.057403564453125, "learning_rate": 9.544875361630253e-06, "loss": 0.4143, "step": 187730 }, { "epoch": 1.115965547372363, "grad_norm": 5.453074932098389, "learning_rate": 9.544788864525132e-06, "loss": 0.4045, "step": 187740 }, { "epoch": 1.1160249894490315, "grad_norm": 5.11614990234375, "learning_rate": 9.544702359593342e-06, "loss": 0.4254, "step": 187750 }, { "epoch": 1.1160844315256997, "grad_norm": 5.348404407501221, "learning_rate": 9.544615846835034e-06, "loss": 0.4245, "step": 187760 }, { "epoch": 1.116143873602368, "grad_norm": 5.796807765960693, "learning_rate": 9.544529326250356e-06, "loss": 0.402, "step": 187770 }, { "epoch": 1.1162033156790365, "grad_norm": 4.704668045043945, "learning_rate": 9.544442797839453e-06, "loss": 0.4342, "step": 187780 }, { "epoch": 1.116262757755705, "grad_norm": 6.837104320526123, "learning_rate": 9.544356261602481e-06, "loss": 0.3801, "step": 187790 }, { "epoch": 1.1163221998323734, "grad_norm": 4.615962505340576, "learning_rate": 9.544269717539583e-06, "loss": 0.3896, "step": 187800 }, { "epoch": 1.1163816419090418, "grad_norm": 6.169060230255127, "learning_rate": 9.54418316565091e-06, "loss": 0.4281, "step": 187810 }, { "epoch": 1.1164410839857102, "grad_norm": 6.103973388671875, "learning_rate": 9.544096605936613e-06, "loss": 0.4345, "step": 187820 }, { "epoch": 1.1165005260623786, "grad_norm": 5.368565082550049, "learning_rate": 9.544010038396838e-06, "loss": 0.3865, "step": 187830 }, { "epoch": 1.1165599681390468, "grad_norm": 5.7029523849487305, "learning_rate": 9.543923463031736e-06, "loss": 0.4121, "step": 187840 }, { "epoch": 1.1166194102157152, "grad_norm": 5.002110958099365, "learning_rate": 9.543836879841456e-06, "loss": 0.4414, "step": 187850 }, { "epoch": 1.1166788522923836, "grad_norm": 5.664616584777832, "learning_rate": 9.543750288826146e-06, "loss": 0.401, "step": 187860 }, { "epoch": 1.116738294369052, "grad_norm": 5.405303955078125, "learning_rate": 9.543663689985956e-06, "loss": 0.4368, "step": 187870 }, { "epoch": 1.1167977364457204, "grad_norm": 5.6446943283081055, "learning_rate": 9.543577083321037e-06, "loss": 0.3626, "step": 187880 }, { "epoch": 1.1168571785223889, "grad_norm": 7.370019912719727, "learning_rate": 9.543490468831534e-06, "loss": 0.4639, "step": 187890 }, { "epoch": 1.1169166205990573, "grad_norm": 4.634259223937988, "learning_rate": 9.543403846517598e-06, "loss": 0.4298, "step": 187900 }, { "epoch": 1.1169760626757257, "grad_norm": 4.742845058441162, "learning_rate": 9.543317216379378e-06, "loss": 0.3937, "step": 187910 }, { "epoch": 1.117035504752394, "grad_norm": 4.4322991371154785, "learning_rate": 9.543230578417025e-06, "loss": 0.357, "step": 187920 }, { "epoch": 1.1170949468290625, "grad_norm": 4.5123138427734375, "learning_rate": 9.543143932630688e-06, "loss": 0.3969, "step": 187930 }, { "epoch": 1.1171543889057307, "grad_norm": 4.750359058380127, "learning_rate": 9.543057279020512e-06, "loss": 0.421, "step": 187940 }, { "epoch": 1.1172138309823991, "grad_norm": 6.182735443115234, "learning_rate": 9.542970617586651e-06, "loss": 0.3958, "step": 187950 }, { "epoch": 1.1172732730590675, "grad_norm": 4.3786420822143555, "learning_rate": 9.542883948329253e-06, "loss": 0.3901, "step": 187960 }, { "epoch": 1.117332715135736, "grad_norm": 4.447498798370361, "learning_rate": 9.542797271248466e-06, "loss": 0.415, "step": 187970 }, { "epoch": 1.1173921572124044, "grad_norm": 5.3765716552734375, "learning_rate": 9.542710586344441e-06, "loss": 0.4145, "step": 187980 }, { "epoch": 1.1174515992890728, "grad_norm": 8.173455238342285, "learning_rate": 9.542623893617327e-06, "loss": 0.4102, "step": 187990 }, { "epoch": 1.1175110413657412, "grad_norm": 4.453743934631348, "learning_rate": 9.542537193067269e-06, "loss": 0.4068, "step": 188000 }, { "epoch": 1.1175704834424096, "grad_norm": 4.852017402648926, "learning_rate": 9.542450484694423e-06, "loss": 0.3902, "step": 188010 }, { "epoch": 1.117629925519078, "grad_norm": 5.396814823150635, "learning_rate": 9.542363768498935e-06, "loss": 0.3748, "step": 188020 }, { "epoch": 1.1176893675957462, "grad_norm": 5.760889053344727, "learning_rate": 9.542277044480955e-06, "loss": 0.4398, "step": 188030 }, { "epoch": 1.1177488096724146, "grad_norm": 6.423696994781494, "learning_rate": 9.54219031264063e-06, "loss": 0.4098, "step": 188040 }, { "epoch": 1.117808251749083, "grad_norm": 3.3468377590179443, "learning_rate": 9.542103572978112e-06, "loss": 0.4218, "step": 188050 }, { "epoch": 1.1178676938257515, "grad_norm": 4.788873672485352, "learning_rate": 9.542016825493552e-06, "loss": 0.3899, "step": 188060 }, { "epoch": 1.1179271359024199, "grad_norm": 5.168892860412598, "learning_rate": 9.541930070187094e-06, "loss": 0.4145, "step": 188070 }, { "epoch": 1.1179865779790883, "grad_norm": 4.65536642074585, "learning_rate": 9.541843307058891e-06, "loss": 0.4396, "step": 188080 }, { "epoch": 1.1180460200557567, "grad_norm": 4.697602272033691, "learning_rate": 9.541756536109094e-06, "loss": 0.4131, "step": 188090 }, { "epoch": 1.1181054621324251, "grad_norm": 4.499828815460205, "learning_rate": 9.541669757337847e-06, "loss": 0.4436, "step": 188100 }, { "epoch": 1.1181649042090935, "grad_norm": 7.01024055480957, "learning_rate": 9.541582970745307e-06, "loss": 0.396, "step": 188110 }, { "epoch": 1.118224346285762, "grad_norm": 4.9294962882995605, "learning_rate": 9.541496176331617e-06, "loss": 0.4091, "step": 188120 }, { "epoch": 1.1182837883624301, "grad_norm": 3.390695810317993, "learning_rate": 9.541409374096929e-06, "loss": 0.3763, "step": 188130 }, { "epoch": 1.1183432304390986, "grad_norm": 5.02827262878418, "learning_rate": 9.54132256404139e-06, "loss": 0.4222, "step": 188140 }, { "epoch": 1.118402672515767, "grad_norm": 5.135551929473877, "learning_rate": 9.541235746165154e-06, "loss": 0.3705, "step": 188150 }, { "epoch": 1.1184621145924354, "grad_norm": 6.903721332550049, "learning_rate": 9.541148920468368e-06, "loss": 0.3992, "step": 188160 }, { "epoch": 1.1185215566691038, "grad_norm": 5.173244476318359, "learning_rate": 9.54106208695118e-06, "loss": 0.4351, "step": 188170 }, { "epoch": 1.1185809987457722, "grad_norm": 5.475374221801758, "learning_rate": 9.540975245613744e-06, "loss": 0.3807, "step": 188180 }, { "epoch": 1.1186404408224406, "grad_norm": 5.5575103759765625, "learning_rate": 9.540888396456205e-06, "loss": 0.4089, "step": 188190 }, { "epoch": 1.118699882899109, "grad_norm": 5.719779968261719, "learning_rate": 9.540801539478716e-06, "loss": 0.4167, "step": 188200 }, { "epoch": 1.1187593249757772, "grad_norm": 4.958303928375244, "learning_rate": 9.540714674681424e-06, "loss": 0.3859, "step": 188210 }, { "epoch": 1.1188187670524457, "grad_norm": 5.525322437286377, "learning_rate": 9.54062780206448e-06, "loss": 0.4035, "step": 188220 }, { "epoch": 1.118878209129114, "grad_norm": 5.457451343536377, "learning_rate": 9.540540921628033e-06, "loss": 0.4201, "step": 188230 }, { "epoch": 1.1189376512057825, "grad_norm": 4.202428340911865, "learning_rate": 9.540454033372231e-06, "loss": 0.3625, "step": 188240 }, { "epoch": 1.118997093282451, "grad_norm": 3.8294677734375, "learning_rate": 9.540367137297226e-06, "loss": 0.3821, "step": 188250 }, { "epoch": 1.1190565353591193, "grad_norm": 4.861674785614014, "learning_rate": 9.540280233403167e-06, "loss": 0.4128, "step": 188260 }, { "epoch": 1.1191159774357877, "grad_norm": 5.160834312438965, "learning_rate": 9.540193321690206e-06, "loss": 0.4163, "step": 188270 }, { "epoch": 1.1191754195124561, "grad_norm": 4.693291187286377, "learning_rate": 9.540106402158487e-06, "loss": 0.3998, "step": 188280 }, { "epoch": 1.1192348615891246, "grad_norm": 5.531579494476318, "learning_rate": 9.540019474808166e-06, "loss": 0.3748, "step": 188290 }, { "epoch": 1.119294303665793, "grad_norm": 4.743404388427734, "learning_rate": 9.539932539639389e-06, "loss": 0.4209, "step": 188300 }, { "epoch": 1.1193537457424612, "grad_norm": 4.510262489318848, "learning_rate": 9.539845596652306e-06, "loss": 0.4046, "step": 188310 }, { "epoch": 1.1194131878191296, "grad_norm": 4.501636981964111, "learning_rate": 9.539758645847067e-06, "loss": 0.423, "step": 188320 }, { "epoch": 1.119472629895798, "grad_norm": 3.3804101943969727, "learning_rate": 9.539671687223822e-06, "loss": 0.4169, "step": 188330 }, { "epoch": 1.1195320719724664, "grad_norm": 4.089396953582764, "learning_rate": 9.539584720782721e-06, "loss": 0.4028, "step": 188340 }, { "epoch": 1.1195915140491348, "grad_norm": 4.740823268890381, "learning_rate": 9.539497746523914e-06, "loss": 0.3853, "step": 188350 }, { "epoch": 1.1196509561258032, "grad_norm": 5.362667560577393, "learning_rate": 9.53941076444755e-06, "loss": 0.4583, "step": 188360 }, { "epoch": 1.1197103982024716, "grad_norm": 5.699401378631592, "learning_rate": 9.539323774553778e-06, "loss": 0.4106, "step": 188370 }, { "epoch": 1.11976984027914, "grad_norm": 5.181830406188965, "learning_rate": 9.53923677684275e-06, "loss": 0.4515, "step": 188380 }, { "epoch": 1.1198292823558085, "grad_norm": 4.336574077606201, "learning_rate": 9.539149771314613e-06, "loss": 0.3979, "step": 188390 }, { "epoch": 1.1198887244324767, "grad_norm": 5.407506942749023, "learning_rate": 9.53906275796952e-06, "loss": 0.4018, "step": 188400 }, { "epoch": 1.119948166509145, "grad_norm": 5.231468200683594, "learning_rate": 9.53897573680762e-06, "loss": 0.3949, "step": 188410 }, { "epoch": 1.1200076085858135, "grad_norm": 5.22716760635376, "learning_rate": 9.538888707829059e-06, "loss": 0.3715, "step": 188420 }, { "epoch": 1.120067050662482, "grad_norm": 4.619911193847656, "learning_rate": 9.538801671033992e-06, "loss": 0.4037, "step": 188430 }, { "epoch": 1.1201264927391503, "grad_norm": 5.089295387268066, "learning_rate": 9.538714626422568e-06, "loss": 0.3978, "step": 188440 }, { "epoch": 1.1201859348158187, "grad_norm": 5.216240882873535, "learning_rate": 9.538627573994935e-06, "loss": 0.4104, "step": 188450 }, { "epoch": 1.1202453768924872, "grad_norm": 6.075999736785889, "learning_rate": 9.538540513751244e-06, "loss": 0.3678, "step": 188460 }, { "epoch": 1.1203048189691556, "grad_norm": 6.1039299964904785, "learning_rate": 9.538453445691644e-06, "loss": 0.4326, "step": 188470 }, { "epoch": 1.120364261045824, "grad_norm": 6.2899861335754395, "learning_rate": 9.538366369816288e-06, "loss": 0.4354, "step": 188480 }, { "epoch": 1.1204237031224924, "grad_norm": 3.966123104095459, "learning_rate": 9.53827928612532e-06, "loss": 0.3919, "step": 188490 }, { "epoch": 1.1204831451991606, "grad_norm": 5.4065093994140625, "learning_rate": 9.538192194618895e-06, "loss": 0.4149, "step": 188500 }, { "epoch": 1.120542587275829, "grad_norm": 5.76188325881958, "learning_rate": 9.538105095297163e-06, "loss": 0.4076, "step": 188510 }, { "epoch": 1.1206020293524974, "grad_norm": 6.20616340637207, "learning_rate": 9.53801798816027e-06, "loss": 0.3864, "step": 188520 }, { "epoch": 1.1206614714291658, "grad_norm": 5.165828227996826, "learning_rate": 9.537930873208372e-06, "loss": 0.4161, "step": 188530 }, { "epoch": 1.1207209135058342, "grad_norm": 6.03477144241333, "learning_rate": 9.537843750441613e-06, "loss": 0.3741, "step": 188540 }, { "epoch": 1.1207803555825027, "grad_norm": 5.249567985534668, "learning_rate": 9.537756619860146e-06, "loss": 0.3997, "step": 188550 }, { "epoch": 1.120839797659171, "grad_norm": 4.162200450897217, "learning_rate": 9.53766948146412e-06, "loss": 0.3706, "step": 188560 }, { "epoch": 1.1208992397358395, "grad_norm": 5.364685535430908, "learning_rate": 9.537582335253688e-06, "loss": 0.4865, "step": 188570 }, { "epoch": 1.1209586818125077, "grad_norm": 6.988439559936523, "learning_rate": 9.537495181228997e-06, "loss": 0.4084, "step": 188580 }, { "epoch": 1.121018123889176, "grad_norm": 5.629034996032715, "learning_rate": 9.537408019390197e-06, "loss": 0.409, "step": 188590 }, { "epoch": 1.1210775659658445, "grad_norm": 4.995090007781982, "learning_rate": 9.53732084973744e-06, "loss": 0.3874, "step": 188600 }, { "epoch": 1.121137008042513, "grad_norm": 5.647913932800293, "learning_rate": 9.537233672270873e-06, "loss": 0.4155, "step": 188610 }, { "epoch": 1.1211964501191813, "grad_norm": 4.712648391723633, "learning_rate": 9.537146486990649e-06, "loss": 0.3934, "step": 188620 }, { "epoch": 1.1212558921958498, "grad_norm": 6.531982421875, "learning_rate": 9.537059293896919e-06, "loss": 0.4127, "step": 188630 }, { "epoch": 1.1213153342725182, "grad_norm": 5.081508159637451, "learning_rate": 9.53697209298983e-06, "loss": 0.3935, "step": 188640 }, { "epoch": 1.1213747763491866, "grad_norm": 5.087873458862305, "learning_rate": 9.536884884269535e-06, "loss": 0.4283, "step": 188650 }, { "epoch": 1.121434218425855, "grad_norm": 5.991403102874756, "learning_rate": 9.536797667736183e-06, "loss": 0.3871, "step": 188660 }, { "epoch": 1.1214936605025234, "grad_norm": 3.7636237144470215, "learning_rate": 9.536710443389922e-06, "loss": 0.3824, "step": 188670 }, { "epoch": 1.1215531025791916, "grad_norm": 5.441300868988037, "learning_rate": 9.536623211230905e-06, "loss": 0.4242, "step": 188680 }, { "epoch": 1.12161254465586, "grad_norm": 4.874373912811279, "learning_rate": 9.536535971259282e-06, "loss": 0.427, "step": 188690 }, { "epoch": 1.1216719867325284, "grad_norm": 5.689715385437012, "learning_rate": 9.536448723475203e-06, "loss": 0.3968, "step": 188700 }, { "epoch": 1.1217314288091969, "grad_norm": 4.711100101470947, "learning_rate": 9.536361467878819e-06, "loss": 0.4086, "step": 188710 }, { "epoch": 1.1217908708858653, "grad_norm": 4.404580116271973, "learning_rate": 9.536274204470277e-06, "loss": 0.4037, "step": 188720 }, { "epoch": 1.1218503129625337, "grad_norm": 6.261508464813232, "learning_rate": 9.536186933249731e-06, "loss": 0.4021, "step": 188730 }, { "epoch": 1.121909755039202, "grad_norm": 4.1232171058654785, "learning_rate": 9.53609965421733e-06, "loss": 0.3656, "step": 188740 }, { "epoch": 1.1219691971158705, "grad_norm": 4.679494857788086, "learning_rate": 9.536012367373223e-06, "loss": 0.3909, "step": 188750 }, { "epoch": 1.122028639192539, "grad_norm": 3.5622785091400146, "learning_rate": 9.535925072717563e-06, "loss": 0.3738, "step": 188760 }, { "epoch": 1.1220880812692071, "grad_norm": 7.180375576019287, "learning_rate": 9.535837770250497e-06, "loss": 0.415, "step": 188770 }, { "epoch": 1.1221475233458755, "grad_norm": 5.571316242218018, "learning_rate": 9.53575045997218e-06, "loss": 0.4386, "step": 188780 }, { "epoch": 1.122206965422544, "grad_norm": 4.517690658569336, "learning_rate": 9.535663141882757e-06, "loss": 0.3908, "step": 188790 }, { "epoch": 1.1222664074992124, "grad_norm": 6.847939968109131, "learning_rate": 9.53557581598238e-06, "loss": 0.4292, "step": 188800 }, { "epoch": 1.1223258495758808, "grad_norm": 5.588809013366699, "learning_rate": 9.535488482271203e-06, "loss": 0.3753, "step": 188810 }, { "epoch": 1.1223852916525492, "grad_norm": 4.464200973510742, "learning_rate": 9.535401140749372e-06, "loss": 0.3891, "step": 188820 }, { "epoch": 1.1224447337292176, "grad_norm": 4.504544258117676, "learning_rate": 9.53531379141704e-06, "loss": 0.3894, "step": 188830 }, { "epoch": 1.122504175805886, "grad_norm": 5.217992782592773, "learning_rate": 9.535226434274355e-06, "loss": 0.3946, "step": 188840 }, { "epoch": 1.1225636178825544, "grad_norm": 4.544519901275635, "learning_rate": 9.53513906932147e-06, "loss": 0.4066, "step": 188850 }, { "epoch": 1.1226230599592228, "grad_norm": 7.917619228363037, "learning_rate": 9.535051696558536e-06, "loss": 0.3973, "step": 188860 }, { "epoch": 1.122682502035891, "grad_norm": 4.741735935211182, "learning_rate": 9.5349643159857e-06, "loss": 0.4413, "step": 188870 }, { "epoch": 1.1227419441125595, "grad_norm": 5.809654235839844, "learning_rate": 9.534876927603114e-06, "loss": 0.4519, "step": 188880 }, { "epoch": 1.1228013861892279, "grad_norm": 6.694679260253906, "learning_rate": 9.534789531410931e-06, "loss": 0.4341, "step": 188890 }, { "epoch": 1.1228608282658963, "grad_norm": 6.807122707366943, "learning_rate": 9.534702127409296e-06, "loss": 0.4119, "step": 188900 }, { "epoch": 1.1229202703425647, "grad_norm": 6.617881774902344, "learning_rate": 9.534614715598366e-06, "loss": 0.4397, "step": 188910 }, { "epoch": 1.1229797124192331, "grad_norm": 4.29159688949585, "learning_rate": 9.534527295978286e-06, "loss": 0.418, "step": 188920 }, { "epoch": 1.1230391544959015, "grad_norm": 5.546430587768555, "learning_rate": 9.53443986854921e-06, "loss": 0.4485, "step": 188930 }, { "epoch": 1.12309859657257, "grad_norm": 4.469936370849609, "learning_rate": 9.534352433311288e-06, "loss": 0.3948, "step": 188940 }, { "epoch": 1.1231580386492381, "grad_norm": 6.30052375793457, "learning_rate": 9.53426499026467e-06, "loss": 0.4708, "step": 188950 }, { "epoch": 1.1232174807259065, "grad_norm": 5.334502696990967, "learning_rate": 9.534177539409507e-06, "loss": 0.4095, "step": 188960 }, { "epoch": 1.123276922802575, "grad_norm": 5.04148006439209, "learning_rate": 9.534090080745948e-06, "loss": 0.4073, "step": 188970 }, { "epoch": 1.1233363648792434, "grad_norm": 6.348030090332031, "learning_rate": 9.534002614274146e-06, "loss": 0.3616, "step": 188980 }, { "epoch": 1.1233958069559118, "grad_norm": 5.0759758949279785, "learning_rate": 9.53391513999425e-06, "loss": 0.3991, "step": 188990 }, { "epoch": 1.1234552490325802, "grad_norm": 6.490746974945068, "learning_rate": 9.53382765790641e-06, "loss": 0.4207, "step": 189000 }, { "epoch": 1.1235146911092486, "grad_norm": 6.293345928192139, "learning_rate": 9.533740168010778e-06, "loss": 0.4321, "step": 189010 }, { "epoch": 1.123574133185917, "grad_norm": 3.758322238922119, "learning_rate": 9.533652670307507e-06, "loss": 0.4155, "step": 189020 }, { "epoch": 1.1236335752625854, "grad_norm": 5.2488322257995605, "learning_rate": 9.533565164796744e-06, "loss": 0.3874, "step": 189030 }, { "epoch": 1.1236930173392539, "grad_norm": 4.0370402336120605, "learning_rate": 9.53347765147864e-06, "loss": 0.3619, "step": 189040 }, { "epoch": 1.123752459415922, "grad_norm": 4.653965950012207, "learning_rate": 9.533390130353346e-06, "loss": 0.413, "step": 189050 }, { "epoch": 1.1238119014925905, "grad_norm": 6.231476783752441, "learning_rate": 9.533302601421015e-06, "loss": 0.3992, "step": 189060 }, { "epoch": 1.1238713435692589, "grad_norm": 6.189362049102783, "learning_rate": 9.533215064681796e-06, "loss": 0.3488, "step": 189070 }, { "epoch": 1.1239307856459273, "grad_norm": 5.784515380859375, "learning_rate": 9.533127520135839e-06, "loss": 0.3835, "step": 189080 }, { "epoch": 1.1239902277225957, "grad_norm": 4.958658218383789, "learning_rate": 9.533039967783294e-06, "loss": 0.3822, "step": 189090 }, { "epoch": 1.1240496697992641, "grad_norm": 4.127031326293945, "learning_rate": 9.532952407624315e-06, "loss": 0.4399, "step": 189100 }, { "epoch": 1.1241091118759325, "grad_norm": 4.704782485961914, "learning_rate": 9.53286483965905e-06, "loss": 0.391, "step": 189110 }, { "epoch": 1.124168553952601, "grad_norm": 6.448771953582764, "learning_rate": 9.532777263887653e-06, "loss": 0.3989, "step": 189120 }, { "epoch": 1.1242279960292694, "grad_norm": 6.369302272796631, "learning_rate": 9.532689680310272e-06, "loss": 0.4116, "step": 189130 }, { "epoch": 1.1242874381059376, "grad_norm": 6.961594581604004, "learning_rate": 9.532602088927058e-06, "loss": 0.4137, "step": 189140 }, { "epoch": 1.124346880182606, "grad_norm": 4.757899284362793, "learning_rate": 9.532514489738162e-06, "loss": 0.4307, "step": 189150 }, { "epoch": 1.1244063222592744, "grad_norm": 3.9434337615966797, "learning_rate": 9.532426882743736e-06, "loss": 0.3891, "step": 189160 }, { "epoch": 1.1244657643359428, "grad_norm": 5.137123107910156, "learning_rate": 9.53233926794393e-06, "loss": 0.3939, "step": 189170 }, { "epoch": 1.1245252064126112, "grad_norm": 6.039784908294678, "learning_rate": 9.532251645338895e-06, "loss": 0.3897, "step": 189180 }, { "epoch": 1.1245846484892796, "grad_norm": 5.236324310302734, "learning_rate": 9.532164014928783e-06, "loss": 0.4139, "step": 189190 }, { "epoch": 1.124644090565948, "grad_norm": 5.495560646057129, "learning_rate": 9.532076376713742e-06, "loss": 0.3893, "step": 189200 }, { "epoch": 1.1247035326426165, "grad_norm": 6.273902416229248, "learning_rate": 9.531988730693924e-06, "loss": 0.4025, "step": 189210 }, { "epoch": 1.1247629747192849, "grad_norm": 4.2631001472473145, "learning_rate": 9.531901076869482e-06, "loss": 0.3643, "step": 189220 }, { "epoch": 1.1248224167959533, "grad_norm": 6.258014678955078, "learning_rate": 9.531813415240565e-06, "loss": 0.4317, "step": 189230 }, { "epoch": 1.1248818588726215, "grad_norm": 4.468955039978027, "learning_rate": 9.531725745807325e-06, "loss": 0.3867, "step": 189240 }, { "epoch": 1.12494130094929, "grad_norm": 3.846350908279419, "learning_rate": 9.531638068569913e-06, "loss": 0.3577, "step": 189250 }, { "epoch": 1.1250007430259583, "grad_norm": 5.570854187011719, "learning_rate": 9.531550383528479e-06, "loss": 0.4439, "step": 189260 }, { "epoch": 1.1250601851026267, "grad_norm": 5.686561107635498, "learning_rate": 9.531462690683175e-06, "loss": 0.3904, "step": 189270 }, { "epoch": 1.1251196271792951, "grad_norm": 4.775129318237305, "learning_rate": 9.53137499003415e-06, "loss": 0.3981, "step": 189280 }, { "epoch": 1.1251790692559636, "grad_norm": 4.758281707763672, "learning_rate": 9.531287281581559e-06, "loss": 0.4769, "step": 189290 }, { "epoch": 1.125238511332632, "grad_norm": 6.153963565826416, "learning_rate": 9.531199565325549e-06, "loss": 0.4298, "step": 189300 }, { "epoch": 1.1252979534093004, "grad_norm": 5.010392189025879, "learning_rate": 9.531111841266273e-06, "loss": 0.4229, "step": 189310 }, { "epoch": 1.1253573954859686, "grad_norm": 3.534029722213745, "learning_rate": 9.531024109403881e-06, "loss": 0.399, "step": 189320 }, { "epoch": 1.125416837562637, "grad_norm": 4.641607284545898, "learning_rate": 9.530936369738527e-06, "loss": 0.4485, "step": 189330 }, { "epoch": 1.1254762796393054, "grad_norm": 6.780542850494385, "learning_rate": 9.53084862227036e-06, "loss": 0.3654, "step": 189340 }, { "epoch": 1.1255357217159738, "grad_norm": 6.086666584014893, "learning_rate": 9.530760866999529e-06, "loss": 0.4131, "step": 189350 }, { "epoch": 1.1255951637926422, "grad_norm": 6.5675482749938965, "learning_rate": 9.530673103926187e-06, "loss": 0.3937, "step": 189360 }, { "epoch": 1.1256546058693107, "grad_norm": 4.500105857849121, "learning_rate": 9.530585333050486e-06, "loss": 0.4148, "step": 189370 }, { "epoch": 1.125714047945979, "grad_norm": 4.66318416595459, "learning_rate": 9.530497554372577e-06, "loss": 0.3914, "step": 189380 }, { "epoch": 1.1257734900226475, "grad_norm": 6.307463645935059, "learning_rate": 9.530409767892612e-06, "loss": 0.4163, "step": 189390 }, { "epoch": 1.125832932099316, "grad_norm": 4.846471309661865, "learning_rate": 9.530321973610739e-06, "loss": 0.4307, "step": 189400 }, { "epoch": 1.1258923741759843, "grad_norm": 5.978818893432617, "learning_rate": 9.530234171527111e-06, "loss": 0.4083, "step": 189410 }, { "epoch": 1.1259518162526527, "grad_norm": 4.685030937194824, "learning_rate": 9.530146361641879e-06, "loss": 0.3983, "step": 189420 }, { "epoch": 1.126011258329321, "grad_norm": 5.853547096252441, "learning_rate": 9.530058543955194e-06, "loss": 0.3719, "step": 189430 }, { "epoch": 1.1260707004059893, "grad_norm": 4.335109710693359, "learning_rate": 9.52997071846721e-06, "loss": 0.4085, "step": 189440 }, { "epoch": 1.1261301424826577, "grad_norm": 3.5566258430480957, "learning_rate": 9.529882885178074e-06, "loss": 0.4179, "step": 189450 }, { "epoch": 1.1261895845593262, "grad_norm": 5.048929691314697, "learning_rate": 9.529795044087939e-06, "loss": 0.3825, "step": 189460 }, { "epoch": 1.1262490266359946, "grad_norm": 5.44913911819458, "learning_rate": 9.529707195196958e-06, "loss": 0.3963, "step": 189470 }, { "epoch": 1.126308468712663, "grad_norm": 6.72797155380249, "learning_rate": 9.529619338505279e-06, "loss": 0.4191, "step": 189480 }, { "epoch": 1.1263679107893314, "grad_norm": 4.059828281402588, "learning_rate": 9.529531474013057e-06, "loss": 0.3843, "step": 189490 }, { "epoch": 1.1264273528659998, "grad_norm": 5.154915809631348, "learning_rate": 9.529443601720439e-06, "loss": 0.3819, "step": 189500 }, { "epoch": 1.126486794942668, "grad_norm": 4.943930149078369, "learning_rate": 9.52935572162758e-06, "loss": 0.4014, "step": 189510 }, { "epoch": 1.1265462370193364, "grad_norm": 4.9384236335754395, "learning_rate": 9.52926783373463e-06, "loss": 0.3964, "step": 189520 }, { "epoch": 1.1266056790960048, "grad_norm": 5.245701313018799, "learning_rate": 9.529179938041741e-06, "loss": 0.3883, "step": 189530 }, { "epoch": 1.1266651211726733, "grad_norm": 5.509408950805664, "learning_rate": 9.529092034549062e-06, "loss": 0.4144, "step": 189540 }, { "epoch": 1.1267245632493417, "grad_norm": 5.282553672790527, "learning_rate": 9.529004123256747e-06, "loss": 0.4123, "step": 189550 }, { "epoch": 1.12678400532601, "grad_norm": 4.871417999267578, "learning_rate": 9.528916204164947e-06, "loss": 0.4532, "step": 189560 }, { "epoch": 1.1268434474026785, "grad_norm": 6.389796257019043, "learning_rate": 9.528828277273812e-06, "loss": 0.4094, "step": 189570 }, { "epoch": 1.126902889479347, "grad_norm": 7.330383777618408, "learning_rate": 9.528740342583496e-06, "loss": 0.4488, "step": 189580 }, { "epoch": 1.1269623315560153, "grad_norm": 5.381470203399658, "learning_rate": 9.528652400094147e-06, "loss": 0.4466, "step": 189590 }, { "epoch": 1.1270217736326837, "grad_norm": 4.715933322906494, "learning_rate": 9.528564449805919e-06, "loss": 0.4304, "step": 189600 }, { "epoch": 1.127081215709352, "grad_norm": 5.673605918884277, "learning_rate": 9.528476491718963e-06, "loss": 0.4441, "step": 189610 }, { "epoch": 1.1271406577860204, "grad_norm": 6.41929817199707, "learning_rate": 9.52838852583343e-06, "loss": 0.4173, "step": 189620 }, { "epoch": 1.1272000998626888, "grad_norm": 5.191941261291504, "learning_rate": 9.52830055214947e-06, "loss": 0.3734, "step": 189630 }, { "epoch": 1.1272595419393572, "grad_norm": 5.3447041511535645, "learning_rate": 9.528212570667238e-06, "loss": 0.3962, "step": 189640 }, { "epoch": 1.1273189840160256, "grad_norm": 4.390974998474121, "learning_rate": 9.528124581386884e-06, "loss": 0.3674, "step": 189650 }, { "epoch": 1.127378426092694, "grad_norm": 5.581170558929443, "learning_rate": 9.528036584308558e-06, "loss": 0.3659, "step": 189660 }, { "epoch": 1.1274378681693624, "grad_norm": 4.477788925170898, "learning_rate": 9.527948579432412e-06, "loss": 0.3524, "step": 189670 }, { "epoch": 1.1274973102460308, "grad_norm": 4.3503289222717285, "learning_rate": 9.5278605667586e-06, "loss": 0.4344, "step": 189680 }, { "epoch": 1.127556752322699, "grad_norm": 4.085549831390381, "learning_rate": 9.527772546287271e-06, "loss": 0.3743, "step": 189690 }, { "epoch": 1.1276161943993674, "grad_norm": 4.975578784942627, "learning_rate": 9.527684518018577e-06, "loss": 0.4051, "step": 189700 }, { "epoch": 1.1276756364760359, "grad_norm": 6.075377941131592, "learning_rate": 9.527596481952671e-06, "loss": 0.45, "step": 189710 }, { "epoch": 1.1277350785527043, "grad_norm": 5.174416542053223, "learning_rate": 9.527508438089703e-06, "loss": 0.4124, "step": 189720 }, { "epoch": 1.1277945206293727, "grad_norm": 4.574236869812012, "learning_rate": 9.527420386429827e-06, "loss": 0.3916, "step": 189730 }, { "epoch": 1.127853962706041, "grad_norm": 5.066956043243408, "learning_rate": 9.527332326973192e-06, "loss": 0.3766, "step": 189740 }, { "epoch": 1.1279134047827095, "grad_norm": 6.115466594696045, "learning_rate": 9.527244259719947e-06, "loss": 0.3919, "step": 189750 }, { "epoch": 1.127972846859378, "grad_norm": 4.4550065994262695, "learning_rate": 9.527156184670252e-06, "loss": 0.4337, "step": 189760 }, { "epoch": 1.1280322889360463, "grad_norm": 5.416319847106934, "learning_rate": 9.527068101824251e-06, "loss": 0.3859, "step": 189770 }, { "epoch": 1.1280917310127148, "grad_norm": 6.363348960876465, "learning_rate": 9.5269800111821e-06, "loss": 0.4148, "step": 189780 }, { "epoch": 1.1281511730893832, "grad_norm": 5.167999267578125, "learning_rate": 9.52689191274395e-06, "loss": 0.4094, "step": 189790 }, { "epoch": 1.1282106151660514, "grad_norm": 4.90219259262085, "learning_rate": 9.52680380650995e-06, "loss": 0.4467, "step": 189800 }, { "epoch": 1.1282700572427198, "grad_norm": 5.990267753601074, "learning_rate": 9.526715692480254e-06, "loss": 0.384, "step": 189810 }, { "epoch": 1.1283294993193882, "grad_norm": 4.98590087890625, "learning_rate": 9.526627570655014e-06, "loss": 0.362, "step": 189820 }, { "epoch": 1.1283889413960566, "grad_norm": 5.7134199142456055, "learning_rate": 9.526539441034381e-06, "loss": 0.4271, "step": 189830 }, { "epoch": 1.128448383472725, "grad_norm": 5.5065016746521, "learning_rate": 9.526451303618508e-06, "loss": 0.3888, "step": 189840 }, { "epoch": 1.1285078255493934, "grad_norm": 5.207204341888428, "learning_rate": 9.526363158407546e-06, "loss": 0.395, "step": 189850 }, { "epoch": 1.1285672676260619, "grad_norm": 5.974095821380615, "learning_rate": 9.526275005401643e-06, "loss": 0.3826, "step": 189860 }, { "epoch": 1.1286267097027303, "grad_norm": 5.069467544555664, "learning_rate": 9.526186844600957e-06, "loss": 0.4259, "step": 189870 }, { "epoch": 1.1286861517793985, "grad_norm": 5.051928520202637, "learning_rate": 9.526098676005638e-06, "loss": 0.4018, "step": 189880 }, { "epoch": 1.1287455938560669, "grad_norm": 7.444272041320801, "learning_rate": 9.526010499615837e-06, "loss": 0.4128, "step": 189890 }, { "epoch": 1.1288050359327353, "grad_norm": 4.817368984222412, "learning_rate": 9.525922315431705e-06, "loss": 0.4113, "step": 189900 }, { "epoch": 1.1288644780094037, "grad_norm": 7.572098731994629, "learning_rate": 9.525834123453394e-06, "loss": 0.3823, "step": 189910 }, { "epoch": 1.1289239200860721, "grad_norm": 4.180343151092529, "learning_rate": 9.525745923681058e-06, "loss": 0.3728, "step": 189920 }, { "epoch": 1.1289833621627405, "grad_norm": 6.484223365783691, "learning_rate": 9.525657716114847e-06, "loss": 0.3904, "step": 189930 }, { "epoch": 1.129042804239409, "grad_norm": 5.670058727264404, "learning_rate": 9.525569500754914e-06, "loss": 0.4078, "step": 189940 }, { "epoch": 1.1291022463160774, "grad_norm": 3.712822198867798, "learning_rate": 9.52548127760141e-06, "loss": 0.3716, "step": 189950 }, { "epoch": 1.1291616883927458, "grad_norm": 5.207447528839111, "learning_rate": 9.525393046654484e-06, "loss": 0.4454, "step": 189960 }, { "epoch": 1.1292211304694142, "grad_norm": 5.302786827087402, "learning_rate": 9.525304807914297e-06, "loss": 0.4706, "step": 189970 }, { "epoch": 1.1292805725460824, "grad_norm": 5.219302654266357, "learning_rate": 9.525216561380991e-06, "loss": 0.3862, "step": 189980 }, { "epoch": 1.1293400146227508, "grad_norm": 4.595667839050293, "learning_rate": 9.525128307054723e-06, "loss": 0.3893, "step": 189990 }, { "epoch": 1.1293994566994192, "grad_norm": 4.185056686401367, "learning_rate": 9.525040044935646e-06, "loss": 0.386, "step": 190000 }, { "epoch": 1.1294588987760876, "grad_norm": 4.834248065948486, "learning_rate": 9.524951775023907e-06, "loss": 0.3855, "step": 190010 }, { "epoch": 1.129518340852756, "grad_norm": 7.465380668640137, "learning_rate": 9.524863497319664e-06, "loss": 0.4527, "step": 190020 }, { "epoch": 1.1295777829294245, "grad_norm": 4.586970806121826, "learning_rate": 9.524775211823066e-06, "loss": 0.4757, "step": 190030 }, { "epoch": 1.1296372250060929, "grad_norm": 5.073634624481201, "learning_rate": 9.524686918534263e-06, "loss": 0.3897, "step": 190040 }, { "epoch": 1.1296966670827613, "grad_norm": 6.271401882171631, "learning_rate": 9.524598617453411e-06, "loss": 0.3606, "step": 190050 }, { "epoch": 1.1297561091594295, "grad_norm": 5.571972370147705, "learning_rate": 9.52451030858066e-06, "loss": 0.3855, "step": 190060 }, { "epoch": 1.129815551236098, "grad_norm": 4.921970367431641, "learning_rate": 9.524421991916161e-06, "loss": 0.3757, "step": 190070 }, { "epoch": 1.1298749933127663, "grad_norm": 5.746649265289307, "learning_rate": 9.52433366746007e-06, "loss": 0.3783, "step": 190080 }, { "epoch": 1.1299344353894347, "grad_norm": 3.965799331665039, "learning_rate": 9.524245335212534e-06, "loss": 0.3818, "step": 190090 }, { "epoch": 1.1299938774661031, "grad_norm": 4.839277744293213, "learning_rate": 9.52415699517371e-06, "loss": 0.4269, "step": 190100 }, { "epoch": 1.1300533195427716, "grad_norm": 4.483477592468262, "learning_rate": 9.524068647343747e-06, "loss": 0.4107, "step": 190110 }, { "epoch": 1.13011276161944, "grad_norm": 5.026092052459717, "learning_rate": 9.523980291722796e-06, "loss": 0.4422, "step": 190120 }, { "epoch": 1.1301722036961084, "grad_norm": 4.608700275421143, "learning_rate": 9.523891928311014e-06, "loss": 0.394, "step": 190130 }, { "epoch": 1.1302316457727768, "grad_norm": 6.599402904510498, "learning_rate": 9.523803557108548e-06, "loss": 0.4292, "step": 190140 }, { "epoch": 1.1302910878494452, "grad_norm": 4.959027290344238, "learning_rate": 9.523715178115556e-06, "loss": 0.4319, "step": 190150 }, { "epoch": 1.1303505299261136, "grad_norm": 6.486842632293701, "learning_rate": 9.523626791332184e-06, "loss": 0.4034, "step": 190160 }, { "epoch": 1.1304099720027818, "grad_norm": 5.6145853996276855, "learning_rate": 9.523538396758588e-06, "loss": 0.3819, "step": 190170 }, { "epoch": 1.1304694140794502, "grad_norm": 5.021949768066406, "learning_rate": 9.523449994394918e-06, "loss": 0.4605, "step": 190180 }, { "epoch": 1.1305288561561186, "grad_norm": 5.111780166625977, "learning_rate": 9.523361584241327e-06, "loss": 0.4705, "step": 190190 }, { "epoch": 1.130588298232787, "grad_norm": 4.836669445037842, "learning_rate": 9.523273166297969e-06, "loss": 0.4053, "step": 190200 }, { "epoch": 1.1306477403094555, "grad_norm": 5.560200214385986, "learning_rate": 9.523184740564995e-06, "loss": 0.3896, "step": 190210 }, { "epoch": 1.1307071823861239, "grad_norm": 5.454835414886475, "learning_rate": 9.523096307042556e-06, "loss": 0.407, "step": 190220 }, { "epoch": 1.1307666244627923, "grad_norm": 5.365839004516602, "learning_rate": 9.523007865730808e-06, "loss": 0.3967, "step": 190230 }, { "epoch": 1.1308260665394607, "grad_norm": 7.426080226898193, "learning_rate": 9.522919416629896e-06, "loss": 0.4176, "step": 190240 }, { "epoch": 1.130885508616129, "grad_norm": 5.856130599975586, "learning_rate": 9.522830959739981e-06, "loss": 0.392, "step": 190250 }, { "epoch": 1.1309449506927973, "grad_norm": 6.111084938049316, "learning_rate": 9.52274249506121e-06, "loss": 0.4246, "step": 190260 }, { "epoch": 1.1310043927694657, "grad_norm": 5.410915851593018, "learning_rate": 9.522654022593739e-06, "loss": 0.3852, "step": 190270 }, { "epoch": 1.1310638348461342, "grad_norm": 5.9793243408203125, "learning_rate": 9.522565542337714e-06, "loss": 0.3696, "step": 190280 }, { "epoch": 1.1311232769228026, "grad_norm": 4.179442882537842, "learning_rate": 9.522477054293293e-06, "loss": 0.3945, "step": 190290 }, { "epoch": 1.131182718999471, "grad_norm": 6.479665756225586, "learning_rate": 9.522388558460629e-06, "loss": 0.3801, "step": 190300 }, { "epoch": 1.1312421610761394, "grad_norm": 7.443849563598633, "learning_rate": 9.522300054839871e-06, "loss": 0.3924, "step": 190310 }, { "epoch": 1.1313016031528078, "grad_norm": 4.291736125946045, "learning_rate": 9.522211543431172e-06, "loss": 0.3639, "step": 190320 }, { "epoch": 1.1313610452294762, "grad_norm": 4.190338134765625, "learning_rate": 9.522123024234686e-06, "loss": 0.4219, "step": 190330 }, { "epoch": 1.1314204873061446, "grad_norm": 5.939023971557617, "learning_rate": 9.522034497250566e-06, "loss": 0.4346, "step": 190340 }, { "epoch": 1.1314799293828128, "grad_norm": 5.811250686645508, "learning_rate": 9.52194596247896e-06, "loss": 0.4339, "step": 190350 }, { "epoch": 1.1315393714594812, "grad_norm": 5.46306848526001, "learning_rate": 9.521857419920026e-06, "loss": 0.4066, "step": 190360 }, { "epoch": 1.1315988135361497, "grad_norm": 4.2832159996032715, "learning_rate": 9.521768869573914e-06, "loss": 0.3762, "step": 190370 }, { "epoch": 1.131658255612818, "grad_norm": 4.812211990356445, "learning_rate": 9.521680311440775e-06, "loss": 0.3824, "step": 190380 }, { "epoch": 1.1317176976894865, "grad_norm": 5.135520935058594, "learning_rate": 9.521591745520762e-06, "loss": 0.3747, "step": 190390 }, { "epoch": 1.131777139766155, "grad_norm": 8.580084800720215, "learning_rate": 9.52150317181403e-06, "loss": 0.4661, "step": 190400 }, { "epoch": 1.1318365818428233, "grad_norm": 5.5913615226745605, "learning_rate": 9.52141459032073e-06, "loss": 0.3995, "step": 190410 }, { "epoch": 1.1318960239194917, "grad_norm": 4.802120208740234, "learning_rate": 9.521326001041016e-06, "loss": 0.3855, "step": 190420 }, { "epoch": 1.13195546599616, "grad_norm": 4.618261814117432, "learning_rate": 9.521237403975036e-06, "loss": 0.4055, "step": 190430 }, { "epoch": 1.1320149080728283, "grad_norm": 5.075397491455078, "learning_rate": 9.521148799122948e-06, "loss": 0.3738, "step": 190440 }, { "epoch": 1.1320743501494968, "grad_norm": 4.699209690093994, "learning_rate": 9.521060186484903e-06, "loss": 0.4136, "step": 190450 }, { "epoch": 1.1321337922261652, "grad_norm": 7.05473518371582, "learning_rate": 9.52097156606105e-06, "loss": 0.4348, "step": 190460 }, { "epoch": 1.1321932343028336, "grad_norm": 4.859647750854492, "learning_rate": 9.520882937851548e-06, "loss": 0.3917, "step": 190470 }, { "epoch": 1.132252676379502, "grad_norm": 5.814300060272217, "learning_rate": 9.520794301856544e-06, "loss": 0.3986, "step": 190480 }, { "epoch": 1.1323121184561704, "grad_norm": 5.815572738647461, "learning_rate": 9.520705658076192e-06, "loss": 0.3919, "step": 190490 }, { "epoch": 1.1323715605328388, "grad_norm": 6.3124189376831055, "learning_rate": 9.520617006510647e-06, "loss": 0.3981, "step": 190500 }, { "epoch": 1.1324310026095072, "grad_norm": 3.7349977493286133, "learning_rate": 9.520528347160061e-06, "loss": 0.4243, "step": 190510 }, { "epoch": 1.1324904446861757, "grad_norm": 5.6660990715026855, "learning_rate": 9.520439680024584e-06, "loss": 0.4089, "step": 190520 }, { "epoch": 1.132549886762844, "grad_norm": 4.806652069091797, "learning_rate": 9.520351005104372e-06, "loss": 0.3944, "step": 190530 }, { "epoch": 1.1326093288395123, "grad_norm": 7.1598358154296875, "learning_rate": 9.520262322399573e-06, "loss": 0.3744, "step": 190540 }, { "epoch": 1.1326687709161807, "grad_norm": 4.978269100189209, "learning_rate": 9.520173631910345e-06, "loss": 0.3869, "step": 190550 }, { "epoch": 1.132728212992849, "grad_norm": 4.251201152801514, "learning_rate": 9.52008493363684e-06, "loss": 0.3834, "step": 190560 }, { "epoch": 1.1327876550695175, "grad_norm": 4.204861640930176, "learning_rate": 9.519996227579207e-06, "loss": 0.389, "step": 190570 }, { "epoch": 1.132847097146186, "grad_norm": 7.177105903625488, "learning_rate": 9.519907513737603e-06, "loss": 0.385, "step": 190580 }, { "epoch": 1.1329065392228543, "grad_norm": 4.157573699951172, "learning_rate": 9.519818792112179e-06, "loss": 0.4291, "step": 190590 }, { "epoch": 1.1329659812995228, "grad_norm": 5.140589714050293, "learning_rate": 9.519730062703088e-06, "loss": 0.39, "step": 190600 }, { "epoch": 1.1330254233761912, "grad_norm": 5.480661869049072, "learning_rate": 9.51964132551048e-06, "loss": 0.436, "step": 190610 }, { "epoch": 1.1330848654528594, "grad_norm": 5.672448635101318, "learning_rate": 9.519552580534513e-06, "loss": 0.3787, "step": 190620 }, { "epoch": 1.1331443075295278, "grad_norm": 5.775949478149414, "learning_rate": 9.519463827775336e-06, "loss": 0.4057, "step": 190630 }, { "epoch": 1.1332037496061962, "grad_norm": 4.238016605377197, "learning_rate": 9.519375067233104e-06, "loss": 0.4077, "step": 190640 }, { "epoch": 1.1332631916828646, "grad_norm": 4.858602046966553, "learning_rate": 9.519286298907968e-06, "loss": 0.3941, "step": 190650 }, { "epoch": 1.133322633759533, "grad_norm": 7.110492706298828, "learning_rate": 9.51919752280008e-06, "loss": 0.4661, "step": 190660 }, { "epoch": 1.1333820758362014, "grad_norm": 6.185695171356201, "learning_rate": 9.519108738909598e-06, "loss": 0.4425, "step": 190670 }, { "epoch": 1.1334415179128698, "grad_norm": 5.042944431304932, "learning_rate": 9.519019947236669e-06, "loss": 0.3554, "step": 190680 }, { "epoch": 1.1335009599895383, "grad_norm": 4.639228343963623, "learning_rate": 9.51893114778145e-06, "loss": 0.3668, "step": 190690 }, { "epoch": 1.1335604020662067, "grad_norm": 6.17830753326416, "learning_rate": 9.518842340544092e-06, "loss": 0.4215, "step": 190700 }, { "epoch": 1.133619844142875, "grad_norm": 6.118157863616943, "learning_rate": 9.518753525524749e-06, "loss": 0.3962, "step": 190710 }, { "epoch": 1.1336792862195433, "grad_norm": 5.203001499176025, "learning_rate": 9.518664702723572e-06, "loss": 0.3975, "step": 190720 }, { "epoch": 1.1337387282962117, "grad_norm": 5.192499160766602, "learning_rate": 9.518575872140715e-06, "loss": 0.4293, "step": 190730 }, { "epoch": 1.13379817037288, "grad_norm": 4.993703365325928, "learning_rate": 9.518487033776333e-06, "loss": 0.366, "step": 190740 }, { "epoch": 1.1338576124495485, "grad_norm": 3.796492576599121, "learning_rate": 9.518398187630576e-06, "loss": 0.3701, "step": 190750 }, { "epoch": 1.133917054526217, "grad_norm": 6.122339248657227, "learning_rate": 9.5183093337036e-06, "loss": 0.3943, "step": 190760 }, { "epoch": 1.1339764966028854, "grad_norm": 4.764071941375732, "learning_rate": 9.518220471995553e-06, "loss": 0.384, "step": 190770 }, { "epoch": 1.1340359386795538, "grad_norm": 4.30470609664917, "learning_rate": 9.518131602506593e-06, "loss": 0.4263, "step": 190780 }, { "epoch": 1.1340953807562222, "grad_norm": 7.829622745513916, "learning_rate": 9.518042725236871e-06, "loss": 0.4543, "step": 190790 }, { "epoch": 1.1341548228328904, "grad_norm": 6.163127422332764, "learning_rate": 9.51795384018654e-06, "loss": 0.3841, "step": 190800 }, { "epoch": 1.1342142649095588, "grad_norm": 5.700114727020264, "learning_rate": 9.517864947355756e-06, "loss": 0.4051, "step": 190810 }, { "epoch": 1.1342737069862272, "grad_norm": 5.707698345184326, "learning_rate": 9.517776046744665e-06, "loss": 0.3924, "step": 190820 }, { "epoch": 1.1343331490628956, "grad_norm": 6.4068193435668945, "learning_rate": 9.517687138353428e-06, "loss": 0.4115, "step": 190830 }, { "epoch": 1.134392591139564, "grad_norm": 4.243619441986084, "learning_rate": 9.517598222182193e-06, "loss": 0.4052, "step": 190840 }, { "epoch": 1.1344520332162324, "grad_norm": 4.316286087036133, "learning_rate": 9.517509298231115e-06, "loss": 0.4054, "step": 190850 }, { "epoch": 1.1345114752929009, "grad_norm": 4.7512431144714355, "learning_rate": 9.517420366500348e-06, "loss": 0.4219, "step": 190860 }, { "epoch": 1.1345709173695693, "grad_norm": 4.450577259063721, "learning_rate": 9.517331426990045e-06, "loss": 0.3856, "step": 190870 }, { "epoch": 1.1346303594462377, "grad_norm": 4.550522804260254, "learning_rate": 9.517242479700355e-06, "loss": 0.4111, "step": 190880 }, { "epoch": 1.134689801522906, "grad_norm": 5.005178928375244, "learning_rate": 9.517153524631437e-06, "loss": 0.4212, "step": 190890 }, { "epoch": 1.1347492435995743, "grad_norm": 5.1786885261535645, "learning_rate": 9.51706456178344e-06, "loss": 0.3998, "step": 190900 }, { "epoch": 1.1348086856762427, "grad_norm": 3.94346022605896, "learning_rate": 9.51697559115652e-06, "loss": 0.405, "step": 190910 }, { "epoch": 1.1348681277529111, "grad_norm": 5.124558925628662, "learning_rate": 9.516886612750829e-06, "loss": 0.4409, "step": 190920 }, { "epoch": 1.1349275698295795, "grad_norm": 5.704023838043213, "learning_rate": 9.51679762656652e-06, "loss": 0.4196, "step": 190930 }, { "epoch": 1.134987011906248, "grad_norm": 6.529943466186523, "learning_rate": 9.516708632603748e-06, "loss": 0.4235, "step": 190940 }, { "epoch": 1.1350464539829164, "grad_norm": 4.499895095825195, "learning_rate": 9.516619630862663e-06, "loss": 0.3878, "step": 190950 }, { "epoch": 1.1351058960595848, "grad_norm": 4.67260217666626, "learning_rate": 9.51653062134342e-06, "loss": 0.3985, "step": 190960 }, { "epoch": 1.1351653381362532, "grad_norm": 4.699478626251221, "learning_rate": 9.516441604046174e-06, "loss": 0.4011, "step": 190970 }, { "epoch": 1.1352247802129216, "grad_norm": 3.7078492641448975, "learning_rate": 9.516352578971075e-06, "loss": 0.3758, "step": 190980 }, { "epoch": 1.1352842222895898, "grad_norm": 5.182061195373535, "learning_rate": 9.516263546118278e-06, "loss": 0.4076, "step": 190990 }, { "epoch": 1.1353436643662582, "grad_norm": 4.033281326293945, "learning_rate": 9.516174505487939e-06, "loss": 0.3783, "step": 191000 }, { "epoch": 1.1354031064429266, "grad_norm": 3.9249634742736816, "learning_rate": 9.516085457080206e-06, "loss": 0.3852, "step": 191010 }, { "epoch": 1.135462548519595, "grad_norm": 4.001441478729248, "learning_rate": 9.515996400895235e-06, "loss": 0.442, "step": 191020 }, { "epoch": 1.1355219905962635, "grad_norm": 6.505521774291992, "learning_rate": 9.51590733693318e-06, "loss": 0.4142, "step": 191030 }, { "epoch": 1.1355814326729319, "grad_norm": 5.42737340927124, "learning_rate": 9.515818265194193e-06, "loss": 0.4264, "step": 191040 }, { "epoch": 1.1356408747496003, "grad_norm": 4.046413421630859, "learning_rate": 9.51572918567843e-06, "loss": 0.3901, "step": 191050 }, { "epoch": 1.1357003168262687, "grad_norm": 4.7728705406188965, "learning_rate": 9.515640098386042e-06, "loss": 0.3798, "step": 191060 }, { "epoch": 1.1357597589029371, "grad_norm": 6.127691745758057, "learning_rate": 9.515551003317181e-06, "loss": 0.4075, "step": 191070 }, { "epoch": 1.1358192009796055, "grad_norm": 5.539126873016357, "learning_rate": 9.515461900472002e-06, "loss": 0.3837, "step": 191080 }, { "epoch": 1.1358786430562737, "grad_norm": 5.692878723144531, "learning_rate": 9.515372789850661e-06, "loss": 0.4316, "step": 191090 }, { "epoch": 1.1359380851329421, "grad_norm": 4.648863315582275, "learning_rate": 9.51528367145331e-06, "loss": 0.4257, "step": 191100 }, { "epoch": 1.1359975272096106, "grad_norm": 4.252518653869629, "learning_rate": 9.5151945452801e-06, "loss": 0.4409, "step": 191110 }, { "epoch": 1.136056969286279, "grad_norm": 4.551198482513428, "learning_rate": 9.515105411331186e-06, "loss": 0.4304, "step": 191120 }, { "epoch": 1.1361164113629474, "grad_norm": 6.25071907043457, "learning_rate": 9.515016269606725e-06, "loss": 0.473, "step": 191130 }, { "epoch": 1.1361758534396158, "grad_norm": 6.574451446533203, "learning_rate": 9.514927120106864e-06, "loss": 0.4343, "step": 191140 }, { "epoch": 1.1362352955162842, "grad_norm": 4.84666633605957, "learning_rate": 9.51483796283176e-06, "loss": 0.3729, "step": 191150 }, { "epoch": 1.1362947375929526, "grad_norm": 4.822945594787598, "learning_rate": 9.514748797781568e-06, "loss": 0.4265, "step": 191160 }, { "epoch": 1.1363541796696208, "grad_norm": 4.078074932098389, "learning_rate": 9.514659624956438e-06, "loss": 0.3704, "step": 191170 }, { "epoch": 1.1364136217462892, "grad_norm": 5.129934787750244, "learning_rate": 9.514570444356525e-06, "loss": 0.3943, "step": 191180 }, { "epoch": 1.1364730638229577, "grad_norm": 4.885557651519775, "learning_rate": 9.514481255981986e-06, "loss": 0.3976, "step": 191190 }, { "epoch": 1.136532505899626, "grad_norm": 3.5509324073791504, "learning_rate": 9.514392059832969e-06, "loss": 0.382, "step": 191200 }, { "epoch": 1.1365919479762945, "grad_norm": 6.474827289581299, "learning_rate": 9.514302855909632e-06, "loss": 0.4678, "step": 191210 }, { "epoch": 1.136651390052963, "grad_norm": 4.878931045532227, "learning_rate": 9.514213644212124e-06, "loss": 0.4045, "step": 191220 }, { "epoch": 1.1367108321296313, "grad_norm": 5.517617225646973, "learning_rate": 9.514124424740606e-06, "loss": 0.4196, "step": 191230 }, { "epoch": 1.1367702742062997, "grad_norm": 3.698723793029785, "learning_rate": 9.514035197495223e-06, "loss": 0.3948, "step": 191240 }, { "epoch": 1.1368297162829681, "grad_norm": 5.56808614730835, "learning_rate": 9.513945962476135e-06, "loss": 0.4964, "step": 191250 }, { "epoch": 1.1368891583596366, "grad_norm": 6.1996989250183105, "learning_rate": 9.513856719683492e-06, "loss": 0.38, "step": 191260 }, { "epoch": 1.1369486004363047, "grad_norm": 4.532848834991455, "learning_rate": 9.51376746911745e-06, "loss": 0.4037, "step": 191270 }, { "epoch": 1.1370080425129732, "grad_norm": 4.4296746253967285, "learning_rate": 9.513678210778162e-06, "loss": 0.4223, "step": 191280 }, { "epoch": 1.1370674845896416, "grad_norm": 4.534340858459473, "learning_rate": 9.513588944665782e-06, "loss": 0.3889, "step": 191290 }, { "epoch": 1.13712692666631, "grad_norm": 4.994624137878418, "learning_rate": 9.513499670780462e-06, "loss": 0.4261, "step": 191300 }, { "epoch": 1.1371863687429784, "grad_norm": 5.26499605178833, "learning_rate": 9.513410389122357e-06, "loss": 0.4231, "step": 191310 }, { "epoch": 1.1372458108196468, "grad_norm": 4.700418472290039, "learning_rate": 9.513321099691622e-06, "loss": 0.4064, "step": 191320 }, { "epoch": 1.1373052528963152, "grad_norm": 5.207810878753662, "learning_rate": 9.51323180248841e-06, "loss": 0.4261, "step": 191330 }, { "epoch": 1.1373646949729836, "grad_norm": 5.07927942276001, "learning_rate": 9.513142497512872e-06, "loss": 0.4298, "step": 191340 }, { "epoch": 1.137424137049652, "grad_norm": 5.552003383636475, "learning_rate": 9.513053184765166e-06, "loss": 0.4229, "step": 191350 }, { "epoch": 1.1374835791263203, "grad_norm": 3.1220598220825195, "learning_rate": 9.512963864245443e-06, "loss": 0.4225, "step": 191360 }, { "epoch": 1.1375430212029887, "grad_norm": 5.2460432052612305, "learning_rate": 9.512874535953857e-06, "loss": 0.4233, "step": 191370 }, { "epoch": 1.137602463279657, "grad_norm": 4.273685455322266, "learning_rate": 9.512785199890565e-06, "loss": 0.3552, "step": 191380 }, { "epoch": 1.1376619053563255, "grad_norm": 3.617386817932129, "learning_rate": 9.512695856055718e-06, "loss": 0.4355, "step": 191390 }, { "epoch": 1.137721347432994, "grad_norm": 6.244566917419434, "learning_rate": 9.512606504449468e-06, "loss": 0.4122, "step": 191400 }, { "epoch": 1.1377807895096623, "grad_norm": 5.177329063415527, "learning_rate": 9.512517145071974e-06, "loss": 0.4324, "step": 191410 }, { "epoch": 1.1378402315863307, "grad_norm": 4.508477687835693, "learning_rate": 9.512427777923385e-06, "loss": 0.4195, "step": 191420 }, { "epoch": 1.1378996736629992, "grad_norm": 5.777759552001953, "learning_rate": 9.512338403003857e-06, "loss": 0.4144, "step": 191430 }, { "epoch": 1.1379591157396676, "grad_norm": 6.336381912231445, "learning_rate": 9.512249020313545e-06, "loss": 0.4172, "step": 191440 }, { "epoch": 1.138018557816336, "grad_norm": 5.619199275970459, "learning_rate": 9.512159629852601e-06, "loss": 0.3994, "step": 191450 }, { "epoch": 1.1380779998930042, "grad_norm": 5.162379264831543, "learning_rate": 9.51207023162118e-06, "loss": 0.3824, "step": 191460 }, { "epoch": 1.1381374419696726, "grad_norm": 5.92843770980835, "learning_rate": 9.511980825619436e-06, "loss": 0.4025, "step": 191470 }, { "epoch": 1.138196884046341, "grad_norm": 4.537914276123047, "learning_rate": 9.511891411847522e-06, "loss": 0.3517, "step": 191480 }, { "epoch": 1.1382563261230094, "grad_norm": 5.714245796203613, "learning_rate": 9.511801990305594e-06, "loss": 0.3448, "step": 191490 }, { "epoch": 1.1383157681996778, "grad_norm": 3.840650796890259, "learning_rate": 9.511712560993802e-06, "loss": 0.3972, "step": 191500 }, { "epoch": 1.1383752102763462, "grad_norm": 5.230829238891602, "learning_rate": 9.511623123912304e-06, "loss": 0.3875, "step": 191510 }, { "epoch": 1.1384346523530147, "grad_norm": 5.043038845062256, "learning_rate": 9.511533679061253e-06, "loss": 0.3864, "step": 191520 }, { "epoch": 1.138494094429683, "grad_norm": 5.460920333862305, "learning_rate": 9.511444226440803e-06, "loss": 0.3956, "step": 191530 }, { "epoch": 1.1385535365063513, "grad_norm": 4.991513252258301, "learning_rate": 9.511354766051108e-06, "loss": 0.4152, "step": 191540 }, { "epoch": 1.1386129785830197, "grad_norm": 4.223065376281738, "learning_rate": 9.51126529789232e-06, "loss": 0.3858, "step": 191550 }, { "epoch": 1.138672420659688, "grad_norm": 6.01182746887207, "learning_rate": 9.511175821964597e-06, "loss": 0.397, "step": 191560 }, { "epoch": 1.1387318627363565, "grad_norm": 6.489462852478027, "learning_rate": 9.511086338268089e-06, "loss": 0.4795, "step": 191570 }, { "epoch": 1.138791304813025, "grad_norm": 4.458809852600098, "learning_rate": 9.510996846802954e-06, "loss": 0.3768, "step": 191580 }, { "epoch": 1.1388507468896933, "grad_norm": 5.341712474822998, "learning_rate": 9.510907347569343e-06, "loss": 0.4199, "step": 191590 }, { "epoch": 1.1389101889663618, "grad_norm": 4.81217098236084, "learning_rate": 9.510817840567413e-06, "loss": 0.3521, "step": 191600 }, { "epoch": 1.1389696310430302, "grad_norm": 5.2243218421936035, "learning_rate": 9.510728325797313e-06, "loss": 0.397, "step": 191610 }, { "epoch": 1.1390290731196986, "grad_norm": 5.923254013061523, "learning_rate": 9.510638803259203e-06, "loss": 0.4333, "step": 191620 }, { "epoch": 1.139088515196367, "grad_norm": 4.809140205383301, "learning_rate": 9.510549272953234e-06, "loss": 0.411, "step": 191630 }, { "epoch": 1.1391479572730352, "grad_norm": 5.062839984893799, "learning_rate": 9.510459734879562e-06, "loss": 0.4195, "step": 191640 }, { "epoch": 1.1392073993497036, "grad_norm": 4.96856689453125, "learning_rate": 9.510370189038339e-06, "loss": 0.4223, "step": 191650 }, { "epoch": 1.139266841426372, "grad_norm": 6.877764701843262, "learning_rate": 9.510280635429722e-06, "loss": 0.3792, "step": 191660 }, { "epoch": 1.1393262835030404, "grad_norm": 4.9178900718688965, "learning_rate": 9.510191074053862e-06, "loss": 0.3986, "step": 191670 }, { "epoch": 1.1393857255797089, "grad_norm": 5.623954772949219, "learning_rate": 9.510101504910915e-06, "loss": 0.4111, "step": 191680 }, { "epoch": 1.1394451676563773, "grad_norm": 5.086485385894775, "learning_rate": 9.510011928001036e-06, "loss": 0.3901, "step": 191690 }, { "epoch": 1.1395046097330457, "grad_norm": 5.051449775695801, "learning_rate": 9.509922343324379e-06, "loss": 0.42, "step": 191700 }, { "epoch": 1.139564051809714, "grad_norm": 5.783231258392334, "learning_rate": 9.509832750881093e-06, "loss": 0.4199, "step": 191710 }, { "epoch": 1.1396234938863825, "grad_norm": 5.979615688323975, "learning_rate": 9.509743150671343e-06, "loss": 0.432, "step": 191720 }, { "epoch": 1.1396829359630507, "grad_norm": 4.81531286239624, "learning_rate": 9.509653542695274e-06, "loss": 0.4166, "step": 191730 }, { "epoch": 1.1397423780397191, "grad_norm": 4.977654457092285, "learning_rate": 9.509563926953042e-06, "loss": 0.3957, "step": 191740 }, { "epoch": 1.1398018201163875, "grad_norm": 3.9494435787200928, "learning_rate": 9.509474303444805e-06, "loss": 0.403, "step": 191750 }, { "epoch": 1.139861262193056, "grad_norm": 4.8121747970581055, "learning_rate": 9.509384672170716e-06, "loss": 0.4022, "step": 191760 }, { "epoch": 1.1399207042697244, "grad_norm": 3.5508499145507812, "learning_rate": 9.509295033130928e-06, "loss": 0.3995, "step": 191770 }, { "epoch": 1.1399801463463928, "grad_norm": 4.978022575378418, "learning_rate": 9.509205386325595e-06, "loss": 0.419, "step": 191780 }, { "epoch": 1.1400395884230612, "grad_norm": 5.415351867675781, "learning_rate": 9.509115731754873e-06, "loss": 0.3731, "step": 191790 }, { "epoch": 1.1400990304997296, "grad_norm": 4.818883419036865, "learning_rate": 9.509026069418915e-06, "loss": 0.3851, "step": 191800 }, { "epoch": 1.140158472576398, "grad_norm": 5.399894714355469, "learning_rate": 9.508936399317876e-06, "loss": 0.4139, "step": 191810 }, { "epoch": 1.1402179146530664, "grad_norm": 6.347097396850586, "learning_rate": 9.508846721451912e-06, "loss": 0.3833, "step": 191820 }, { "epoch": 1.1402773567297346, "grad_norm": 5.5629472732543945, "learning_rate": 9.508757035821174e-06, "loss": 0.4531, "step": 191830 }, { "epoch": 1.140336798806403, "grad_norm": 5.552097320556641, "learning_rate": 9.508667342425821e-06, "loss": 0.433, "step": 191840 }, { "epoch": 1.1403962408830715, "grad_norm": 6.2593913078308105, "learning_rate": 9.508577641266001e-06, "loss": 0.426, "step": 191850 }, { "epoch": 1.1404556829597399, "grad_norm": 5.221224784851074, "learning_rate": 9.508487932341877e-06, "loss": 0.4058, "step": 191860 }, { "epoch": 1.1405151250364083, "grad_norm": 5.294651508331299, "learning_rate": 9.508398215653595e-06, "loss": 0.4295, "step": 191870 }, { "epoch": 1.1405745671130767, "grad_norm": 4.896151542663574, "learning_rate": 9.508308491201315e-06, "loss": 0.4207, "step": 191880 }, { "epoch": 1.1406340091897451, "grad_norm": 5.545525074005127, "learning_rate": 9.508218758985191e-06, "loss": 0.4416, "step": 191890 }, { "epoch": 1.1406934512664135, "grad_norm": 3.761115550994873, "learning_rate": 9.508129019005374e-06, "loss": 0.3594, "step": 191900 }, { "epoch": 1.1407528933430817, "grad_norm": 4.91270112991333, "learning_rate": 9.508039271262021e-06, "loss": 0.4028, "step": 191910 }, { "epoch": 1.1408123354197501, "grad_norm": 5.020292282104492, "learning_rate": 9.507949515755288e-06, "loss": 0.3819, "step": 191920 }, { "epoch": 1.1408717774964185, "grad_norm": 5.424337863922119, "learning_rate": 9.507859752485328e-06, "loss": 0.4418, "step": 191930 }, { "epoch": 1.140931219573087, "grad_norm": 5.441291332244873, "learning_rate": 9.507769981452295e-06, "loss": 0.3825, "step": 191940 }, { "epoch": 1.1409906616497554, "grad_norm": 4.813205718994141, "learning_rate": 9.507680202656343e-06, "loss": 0.4147, "step": 191950 }, { "epoch": 1.1410501037264238, "grad_norm": 5.4275383949279785, "learning_rate": 9.50759041609763e-06, "loss": 0.4126, "step": 191960 }, { "epoch": 1.1411095458030922, "grad_norm": 4.587428092956543, "learning_rate": 9.507500621776309e-06, "loss": 0.4335, "step": 191970 }, { "epoch": 1.1411689878797606, "grad_norm": 5.28614616394043, "learning_rate": 9.507410819692532e-06, "loss": 0.4568, "step": 191980 }, { "epoch": 1.141228429956429, "grad_norm": 5.811802387237549, "learning_rate": 9.507321009846457e-06, "loss": 0.4103, "step": 191990 }, { "epoch": 1.1412878720330975, "grad_norm": 4.699965000152588, "learning_rate": 9.507231192238236e-06, "loss": 0.4195, "step": 192000 }, { "epoch": 1.1413473141097656, "grad_norm": 4.132298946380615, "learning_rate": 9.507141366868026e-06, "loss": 0.399, "step": 192010 }, { "epoch": 1.141406756186434, "grad_norm": 5.626223087310791, "learning_rate": 9.507051533735982e-06, "loss": 0.375, "step": 192020 }, { "epoch": 1.1414661982631025, "grad_norm": 5.247307300567627, "learning_rate": 9.506961692842257e-06, "loss": 0.4079, "step": 192030 }, { "epoch": 1.1415256403397709, "grad_norm": 4.6937689781188965, "learning_rate": 9.506871844187004e-06, "loss": 0.3916, "step": 192040 }, { "epoch": 1.1415850824164393, "grad_norm": 4.787930011749268, "learning_rate": 9.506781987770382e-06, "loss": 0.4063, "step": 192050 }, { "epoch": 1.1416445244931077, "grad_norm": 4.8313446044921875, "learning_rate": 9.506692123592542e-06, "loss": 0.4379, "step": 192060 }, { "epoch": 1.1417039665697761, "grad_norm": 5.991524696350098, "learning_rate": 9.506602251653643e-06, "loss": 0.4264, "step": 192070 }, { "epoch": 1.1417634086464445, "grad_norm": 4.178889274597168, "learning_rate": 9.506512371953835e-06, "loss": 0.4158, "step": 192080 }, { "epoch": 1.141822850723113, "grad_norm": 4.234869956970215, "learning_rate": 9.506422484493276e-06, "loss": 0.398, "step": 192090 }, { "epoch": 1.1418822927997812, "grad_norm": 5.195391654968262, "learning_rate": 9.506332589272119e-06, "loss": 0.4434, "step": 192100 }, { "epoch": 1.1419417348764496, "grad_norm": 4.3748393058776855, "learning_rate": 9.506242686290521e-06, "loss": 0.4327, "step": 192110 }, { "epoch": 1.142001176953118, "grad_norm": 5.621273994445801, "learning_rate": 9.506152775548634e-06, "loss": 0.3854, "step": 192120 }, { "epoch": 1.1420606190297864, "grad_norm": 4.825586318969727, "learning_rate": 9.506062857046615e-06, "loss": 0.4119, "step": 192130 }, { "epoch": 1.1421200611064548, "grad_norm": 5.356390953063965, "learning_rate": 9.505972930784618e-06, "loss": 0.4304, "step": 192140 }, { "epoch": 1.1421795031831232, "grad_norm": 5.118432521820068, "learning_rate": 9.505882996762798e-06, "loss": 0.3591, "step": 192150 }, { "epoch": 1.1422389452597916, "grad_norm": 5.508744239807129, "learning_rate": 9.505793054981309e-06, "loss": 0.4376, "step": 192160 }, { "epoch": 1.14229838733646, "grad_norm": 3.021810293197632, "learning_rate": 9.505703105440309e-06, "loss": 0.3626, "step": 192170 }, { "epoch": 1.1423578294131285, "grad_norm": 5.364662170410156, "learning_rate": 9.505613148139947e-06, "loss": 0.3884, "step": 192180 }, { "epoch": 1.1424172714897969, "grad_norm": 6.395988941192627, "learning_rate": 9.505523183080385e-06, "loss": 0.3914, "step": 192190 }, { "epoch": 1.142476713566465, "grad_norm": 5.700072765350342, "learning_rate": 9.505433210261773e-06, "loss": 0.4102, "step": 192200 }, { "epoch": 1.1425361556431335, "grad_norm": 4.299895286560059, "learning_rate": 9.505343229684267e-06, "loss": 0.4223, "step": 192210 }, { "epoch": 1.142595597719802, "grad_norm": 5.35331392288208, "learning_rate": 9.505253241348023e-06, "loss": 0.3718, "step": 192220 }, { "epoch": 1.1426550397964703, "grad_norm": 3.5524773597717285, "learning_rate": 9.505163245253195e-06, "loss": 0.4015, "step": 192230 }, { "epoch": 1.1427144818731387, "grad_norm": 4.901880264282227, "learning_rate": 9.505073241399939e-06, "loss": 0.4231, "step": 192240 }, { "epoch": 1.1427739239498071, "grad_norm": 5.624546051025391, "learning_rate": 9.504983229788409e-06, "loss": 0.3973, "step": 192250 }, { "epoch": 1.1428333660264756, "grad_norm": 5.27997350692749, "learning_rate": 9.504893210418761e-06, "loss": 0.4234, "step": 192260 }, { "epoch": 1.142892808103144, "grad_norm": 5.043271541595459, "learning_rate": 9.50480318329115e-06, "loss": 0.3658, "step": 192270 }, { "epoch": 1.1429522501798122, "grad_norm": 4.810430526733398, "learning_rate": 9.504713148405727e-06, "loss": 0.3926, "step": 192280 }, { "epoch": 1.1430116922564806, "grad_norm": 5.3213725090026855, "learning_rate": 9.504623105762653e-06, "loss": 0.4213, "step": 192290 }, { "epoch": 1.143071134333149, "grad_norm": 5.430090427398682, "learning_rate": 9.50453305536208e-06, "loss": 0.4327, "step": 192300 }, { "epoch": 1.1431305764098174, "grad_norm": 5.359980583190918, "learning_rate": 9.504442997204164e-06, "loss": 0.3689, "step": 192310 }, { "epoch": 1.1431900184864858, "grad_norm": 5.329919338226318, "learning_rate": 9.50435293128906e-06, "loss": 0.4138, "step": 192320 }, { "epoch": 1.1432494605631542, "grad_norm": 5.113574981689453, "learning_rate": 9.504262857616921e-06, "loss": 0.4578, "step": 192330 }, { "epoch": 1.1433089026398227, "grad_norm": 5.184890270233154, "learning_rate": 9.504172776187906e-06, "loss": 0.4256, "step": 192340 }, { "epoch": 1.143368344716491, "grad_norm": 7.299839973449707, "learning_rate": 9.504082687002167e-06, "loss": 0.4152, "step": 192350 }, { "epoch": 1.1434277867931595, "grad_norm": 5.689453601837158, "learning_rate": 9.50399259005986e-06, "loss": 0.3881, "step": 192360 }, { "epoch": 1.143487228869828, "grad_norm": 3.9836266040802, "learning_rate": 9.503902485361142e-06, "loss": 0.3957, "step": 192370 }, { "epoch": 1.143546670946496, "grad_norm": 7.2887797355651855, "learning_rate": 9.503812372906165e-06, "loss": 0.3962, "step": 192380 }, { "epoch": 1.1436061130231645, "grad_norm": 6.011715888977051, "learning_rate": 9.503722252695087e-06, "loss": 0.4537, "step": 192390 }, { "epoch": 1.143665555099833, "grad_norm": 3.9211671352386475, "learning_rate": 9.503632124728059e-06, "loss": 0.366, "step": 192400 }, { "epoch": 1.1437249971765013, "grad_norm": 5.538163661956787, "learning_rate": 9.503541989005241e-06, "loss": 0.4063, "step": 192410 }, { "epoch": 1.1437844392531697, "grad_norm": 4.693158149719238, "learning_rate": 9.503451845526788e-06, "loss": 0.4291, "step": 192420 }, { "epoch": 1.1438438813298382, "grad_norm": 4.749876499176025, "learning_rate": 9.503361694292852e-06, "loss": 0.4242, "step": 192430 }, { "epoch": 1.1439033234065066, "grad_norm": 5.1355509757995605, "learning_rate": 9.50327153530359e-06, "loss": 0.4139, "step": 192440 }, { "epoch": 1.143962765483175, "grad_norm": 4.916330814361572, "learning_rate": 9.503181368559155e-06, "loss": 0.4167, "step": 192450 }, { "epoch": 1.1440222075598434, "grad_norm": 5.240574836730957, "learning_rate": 9.503091194059706e-06, "loss": 0.3599, "step": 192460 }, { "epoch": 1.1440816496365116, "grad_norm": 5.169466495513916, "learning_rate": 9.503001011805398e-06, "loss": 0.4035, "step": 192470 }, { "epoch": 1.14414109171318, "grad_norm": 4.580820560455322, "learning_rate": 9.502910821796384e-06, "loss": 0.4401, "step": 192480 }, { "epoch": 1.1442005337898484, "grad_norm": 5.377711296081543, "learning_rate": 9.502820624032821e-06, "loss": 0.4097, "step": 192490 }, { "epoch": 1.1442599758665168, "grad_norm": 4.344366073608398, "learning_rate": 9.502730418514863e-06, "loss": 0.4026, "step": 192500 }, { "epoch": 1.1443194179431853, "grad_norm": 5.603531837463379, "learning_rate": 9.502640205242665e-06, "loss": 0.3709, "step": 192510 }, { "epoch": 1.1443788600198537, "grad_norm": 4.1396484375, "learning_rate": 9.502549984216384e-06, "loss": 0.408, "step": 192520 }, { "epoch": 1.144438302096522, "grad_norm": 4.883429527282715, "learning_rate": 9.502459755436174e-06, "loss": 0.3718, "step": 192530 }, { "epoch": 1.1444977441731905, "grad_norm": 6.0731658935546875, "learning_rate": 9.502369518902193e-06, "loss": 0.3764, "step": 192540 }, { "epoch": 1.144557186249859, "grad_norm": 5.254795074462891, "learning_rate": 9.502279274614591e-06, "loss": 0.3843, "step": 192550 }, { "epoch": 1.1446166283265273, "grad_norm": 5.410284519195557, "learning_rate": 9.502189022573532e-06, "loss": 0.4117, "step": 192560 }, { "epoch": 1.1446760704031955, "grad_norm": 5.421194076538086, "learning_rate": 9.502098762779162e-06, "loss": 0.3916, "step": 192570 }, { "epoch": 1.144735512479864, "grad_norm": 7.059011936187744, "learning_rate": 9.502008495231643e-06, "loss": 0.4463, "step": 192580 }, { "epoch": 1.1447949545565324, "grad_norm": 5.266102313995361, "learning_rate": 9.501918219931128e-06, "loss": 0.4133, "step": 192590 }, { "epoch": 1.1448543966332008, "grad_norm": 5.763955593109131, "learning_rate": 9.501827936877771e-06, "loss": 0.4002, "step": 192600 }, { "epoch": 1.1449138387098692, "grad_norm": 5.542813777923584, "learning_rate": 9.50173764607173e-06, "loss": 0.4496, "step": 192610 }, { "epoch": 1.1449732807865376, "grad_norm": 5.311418056488037, "learning_rate": 9.50164734751316e-06, "loss": 0.3516, "step": 192620 }, { "epoch": 1.145032722863206, "grad_norm": 5.633856296539307, "learning_rate": 9.501557041202217e-06, "loss": 0.4053, "step": 192630 }, { "epoch": 1.1450921649398744, "grad_norm": 6.712540626525879, "learning_rate": 9.501466727139055e-06, "loss": 0.4166, "step": 192640 }, { "epoch": 1.1451516070165426, "grad_norm": 6.588115692138672, "learning_rate": 9.501376405323828e-06, "loss": 0.3898, "step": 192650 }, { "epoch": 1.145211049093211, "grad_norm": 5.060123920440674, "learning_rate": 9.501286075756697e-06, "loss": 0.4083, "step": 192660 }, { "epoch": 1.1452704911698794, "grad_norm": 5.477969169616699, "learning_rate": 9.501195738437812e-06, "loss": 0.3903, "step": 192670 }, { "epoch": 1.1453299332465479, "grad_norm": 4.579459190368652, "learning_rate": 9.501105393367332e-06, "loss": 0.3918, "step": 192680 }, { "epoch": 1.1453893753232163, "grad_norm": 5.882404327392578, "learning_rate": 9.501015040545411e-06, "loss": 0.4233, "step": 192690 }, { "epoch": 1.1454488173998847, "grad_norm": 5.33547830581665, "learning_rate": 9.500924679972205e-06, "loss": 0.4226, "step": 192700 }, { "epoch": 1.145508259476553, "grad_norm": 4.99186897277832, "learning_rate": 9.50083431164787e-06, "loss": 0.4288, "step": 192710 }, { "epoch": 1.1455677015532215, "grad_norm": 5.066351413726807, "learning_rate": 9.500743935572562e-06, "loss": 0.4141, "step": 192720 }, { "epoch": 1.14562714362989, "grad_norm": 6.556192398071289, "learning_rate": 9.500653551746435e-06, "loss": 0.4344, "step": 192730 }, { "epoch": 1.1456865857065583, "grad_norm": 6.486767292022705, "learning_rate": 9.500563160169645e-06, "loss": 0.3778, "step": 192740 }, { "epoch": 1.1457460277832265, "grad_norm": 4.7893524169921875, "learning_rate": 9.500472760842349e-06, "loss": 0.4021, "step": 192750 }, { "epoch": 1.145805469859895, "grad_norm": 4.7995734214782715, "learning_rate": 9.500382353764703e-06, "loss": 0.411, "step": 192760 }, { "epoch": 1.1458649119365634, "grad_norm": 6.05605936050415, "learning_rate": 9.50029193893686e-06, "loss": 0.4312, "step": 192770 }, { "epoch": 1.1459243540132318, "grad_norm": 5.390400409698486, "learning_rate": 9.500201516358978e-06, "loss": 0.4095, "step": 192780 }, { "epoch": 1.1459837960899002, "grad_norm": 4.620394229888916, "learning_rate": 9.500111086031211e-06, "loss": 0.3865, "step": 192790 }, { "epoch": 1.1460432381665686, "grad_norm": 5.010606288909912, "learning_rate": 9.500020647953716e-06, "loss": 0.3754, "step": 192800 }, { "epoch": 1.146102680243237, "grad_norm": 4.9346232414245605, "learning_rate": 9.49993020212665e-06, "loss": 0.3665, "step": 192810 }, { "epoch": 1.1461621223199054, "grad_norm": 4.687390327453613, "learning_rate": 9.499839748550166e-06, "loss": 0.3762, "step": 192820 }, { "epoch": 1.1462215643965739, "grad_norm": 6.695763111114502, "learning_rate": 9.499749287224423e-06, "loss": 0.4419, "step": 192830 }, { "epoch": 1.146281006473242, "grad_norm": 6.265111923217773, "learning_rate": 9.499658818149573e-06, "loss": 0.4085, "step": 192840 }, { "epoch": 1.1463404485499105, "grad_norm": 5.251086235046387, "learning_rate": 9.499568341325774e-06, "loss": 0.3528, "step": 192850 }, { "epoch": 1.1463998906265789, "grad_norm": 3.977785110473633, "learning_rate": 9.49947785675318e-06, "loss": 0.3821, "step": 192860 }, { "epoch": 1.1464593327032473, "grad_norm": 3.8987936973571777, "learning_rate": 9.49938736443195e-06, "loss": 0.3646, "step": 192870 }, { "epoch": 1.1465187747799157, "grad_norm": 4.211014270782471, "learning_rate": 9.499296864362238e-06, "loss": 0.3547, "step": 192880 }, { "epoch": 1.1465782168565841, "grad_norm": 5.820033073425293, "learning_rate": 9.4992063565442e-06, "loss": 0.4393, "step": 192890 }, { "epoch": 1.1466376589332525, "grad_norm": 4.5816650390625, "learning_rate": 9.499115840977991e-06, "loss": 0.4245, "step": 192900 }, { "epoch": 1.146697101009921, "grad_norm": 4.921800136566162, "learning_rate": 9.499025317663767e-06, "loss": 0.4381, "step": 192910 }, { "epoch": 1.1467565430865894, "grad_norm": 5.709991455078125, "learning_rate": 9.498934786601686e-06, "loss": 0.3882, "step": 192920 }, { "epoch": 1.1468159851632578, "grad_norm": 6.463001251220703, "learning_rate": 9.498844247791903e-06, "loss": 0.416, "step": 192930 }, { "epoch": 1.146875427239926, "grad_norm": 4.110937118530273, "learning_rate": 9.498753701234573e-06, "loss": 0.3866, "step": 192940 }, { "epoch": 1.1469348693165944, "grad_norm": 6.0668559074401855, "learning_rate": 9.498663146929852e-06, "loss": 0.3997, "step": 192950 }, { "epoch": 1.1469943113932628, "grad_norm": 4.614202499389648, "learning_rate": 9.498572584877896e-06, "loss": 0.366, "step": 192960 }, { "epoch": 1.1470537534699312, "grad_norm": 5.293254375457764, "learning_rate": 9.498482015078862e-06, "loss": 0.3786, "step": 192970 }, { "epoch": 1.1471131955465996, "grad_norm": 5.3071722984313965, "learning_rate": 9.498391437532905e-06, "loss": 0.4073, "step": 192980 }, { "epoch": 1.147172637623268, "grad_norm": 7.635786056518555, "learning_rate": 9.49830085224018e-06, "loss": 0.4383, "step": 192990 }, { "epoch": 1.1472320796999365, "grad_norm": 5.261894702911377, "learning_rate": 9.498210259200846e-06, "loss": 0.3811, "step": 193000 }, { "epoch": 1.1472915217766049, "grad_norm": 5.225710868835449, "learning_rate": 9.498119658415054e-06, "loss": 0.3783, "step": 193010 }, { "epoch": 1.147350963853273, "grad_norm": 5.375743865966797, "learning_rate": 9.498029049882967e-06, "loss": 0.3811, "step": 193020 }, { "epoch": 1.1474104059299415, "grad_norm": 4.486634254455566, "learning_rate": 9.497938433604736e-06, "loss": 0.3958, "step": 193030 }, { "epoch": 1.14746984800661, "grad_norm": 4.822564601898193, "learning_rate": 9.497847809580517e-06, "loss": 0.4097, "step": 193040 }, { "epoch": 1.1475292900832783, "grad_norm": 4.867579936981201, "learning_rate": 9.497757177810469e-06, "loss": 0.4073, "step": 193050 }, { "epoch": 1.1475887321599467, "grad_norm": 5.010668754577637, "learning_rate": 9.497666538294748e-06, "loss": 0.3882, "step": 193060 }, { "epoch": 1.1476481742366151, "grad_norm": 6.916816711425781, "learning_rate": 9.497575891033505e-06, "loss": 0.4522, "step": 193070 }, { "epoch": 1.1477076163132836, "grad_norm": 5.7024078369140625, "learning_rate": 9.497485236026902e-06, "loss": 0.4546, "step": 193080 }, { "epoch": 1.147767058389952, "grad_norm": 4.911181926727295, "learning_rate": 9.497394573275092e-06, "loss": 0.4033, "step": 193090 }, { "epoch": 1.1478265004666204, "grad_norm": 4.91497278213501, "learning_rate": 9.497303902778232e-06, "loss": 0.4043, "step": 193100 }, { "epoch": 1.1478859425432888, "grad_norm": 6.4465203285217285, "learning_rate": 9.49721322453648e-06, "loss": 0.4089, "step": 193110 }, { "epoch": 1.147945384619957, "grad_norm": 6.304958343505859, "learning_rate": 9.497122538549986e-06, "loss": 0.4601, "step": 193120 }, { "epoch": 1.1480048266966254, "grad_norm": 5.272876262664795, "learning_rate": 9.497031844818914e-06, "loss": 0.3935, "step": 193130 }, { "epoch": 1.1480642687732938, "grad_norm": 4.512570381164551, "learning_rate": 9.496941143343414e-06, "loss": 0.4354, "step": 193140 }, { "epoch": 1.1481237108499622, "grad_norm": 3.9264488220214844, "learning_rate": 9.496850434123647e-06, "loss": 0.367, "step": 193150 }, { "epoch": 1.1481831529266306, "grad_norm": 5.633058547973633, "learning_rate": 9.496759717159765e-06, "loss": 0.3807, "step": 193160 }, { "epoch": 1.148242595003299, "grad_norm": 6.526533126831055, "learning_rate": 9.496668992451929e-06, "loss": 0.4044, "step": 193170 }, { "epoch": 1.1483020370799675, "grad_norm": 4.600785255432129, "learning_rate": 9.49657826000029e-06, "loss": 0.431, "step": 193180 }, { "epoch": 1.148361479156636, "grad_norm": 4.931839942932129, "learning_rate": 9.496487519805008e-06, "loss": 0.3889, "step": 193190 }, { "epoch": 1.1484209212333043, "grad_norm": 6.343194961547852, "learning_rate": 9.496396771866236e-06, "loss": 0.3952, "step": 193200 }, { "epoch": 1.1484803633099725, "grad_norm": 5.084786415100098, "learning_rate": 9.496306016184135e-06, "loss": 0.4176, "step": 193210 }, { "epoch": 1.148539805386641, "grad_norm": 4.296105861663818, "learning_rate": 9.496215252758856e-06, "loss": 0.3854, "step": 193220 }, { "epoch": 1.1485992474633093, "grad_norm": 4.593697547912598, "learning_rate": 9.496124481590561e-06, "loss": 0.3796, "step": 193230 }, { "epoch": 1.1486586895399777, "grad_norm": 6.134754657745361, "learning_rate": 9.4960337026794e-06, "loss": 0.4448, "step": 193240 }, { "epoch": 1.1487181316166462, "grad_norm": 4.509540557861328, "learning_rate": 9.495942916025534e-06, "loss": 0.3749, "step": 193250 }, { "epoch": 1.1487775736933146, "grad_norm": 4.763919353485107, "learning_rate": 9.495852121629119e-06, "loss": 0.385, "step": 193260 }, { "epoch": 1.148837015769983, "grad_norm": 4.491764545440674, "learning_rate": 9.495761319490307e-06, "loss": 0.3925, "step": 193270 }, { "epoch": 1.1488964578466514, "grad_norm": 5.327001571655273, "learning_rate": 9.49567050960926e-06, "loss": 0.3781, "step": 193280 }, { "epoch": 1.1489558999233198, "grad_norm": 4.729029178619385, "learning_rate": 9.495579691986131e-06, "loss": 0.426, "step": 193290 }, { "epoch": 1.1490153419999882, "grad_norm": 6.769636154174805, "learning_rate": 9.495488866621078e-06, "loss": 0.4577, "step": 193300 }, { "epoch": 1.1490747840766564, "grad_norm": 2.9818623065948486, "learning_rate": 9.495398033514256e-06, "loss": 0.3775, "step": 193310 }, { "epoch": 1.1491342261533248, "grad_norm": 5.323143005371094, "learning_rate": 9.495307192665824e-06, "loss": 0.3826, "step": 193320 }, { "epoch": 1.1491936682299932, "grad_norm": 3.8434572219848633, "learning_rate": 9.495216344075934e-06, "loss": 0.386, "step": 193330 }, { "epoch": 1.1492531103066617, "grad_norm": 5.4901041984558105, "learning_rate": 9.495125487744748e-06, "loss": 0.4046, "step": 193340 }, { "epoch": 1.14931255238333, "grad_norm": 4.445573329925537, "learning_rate": 9.495034623672418e-06, "loss": 0.3694, "step": 193350 }, { "epoch": 1.1493719944599985, "grad_norm": 6.12003755569458, "learning_rate": 9.494943751859103e-06, "loss": 0.4275, "step": 193360 }, { "epoch": 1.149431436536667, "grad_norm": 5.157266616821289, "learning_rate": 9.494852872304958e-06, "loss": 0.4023, "step": 193370 }, { "epoch": 1.1494908786133353, "grad_norm": 6.410888195037842, "learning_rate": 9.49476198501014e-06, "loss": 0.3584, "step": 193380 }, { "epoch": 1.1495503206900035, "grad_norm": 5.271761894226074, "learning_rate": 9.494671089974804e-06, "loss": 0.3614, "step": 193390 }, { "epoch": 1.149609762766672, "grad_norm": 4.524472236633301, "learning_rate": 9.49458018719911e-06, "loss": 0.3908, "step": 193400 }, { "epoch": 1.1496692048433403, "grad_norm": 5.016190052032471, "learning_rate": 9.494489276683213e-06, "loss": 0.3877, "step": 193410 }, { "epoch": 1.1497286469200088, "grad_norm": 6.05573844909668, "learning_rate": 9.494398358427267e-06, "loss": 0.3615, "step": 193420 }, { "epoch": 1.1497880889966772, "grad_norm": 5.166775703430176, "learning_rate": 9.494307432431432e-06, "loss": 0.4083, "step": 193430 }, { "epoch": 1.1498475310733456, "grad_norm": 5.58953332901001, "learning_rate": 9.494216498695862e-06, "loss": 0.424, "step": 193440 }, { "epoch": 1.149906973150014, "grad_norm": 5.590681076049805, "learning_rate": 9.494125557220717e-06, "loss": 0.4378, "step": 193450 }, { "epoch": 1.1499664152266824, "grad_norm": 5.696840763092041, "learning_rate": 9.49403460800615e-06, "loss": 0.4364, "step": 193460 }, { "epoch": 1.1500258573033508, "grad_norm": 6.5872602462768555, "learning_rate": 9.49394365105232e-06, "loss": 0.4095, "step": 193470 }, { "epoch": 1.1500852993800192, "grad_norm": 5.225399494171143, "learning_rate": 9.493852686359384e-06, "loss": 0.4292, "step": 193480 }, { "epoch": 1.1501447414566874, "grad_norm": 5.03970193862915, "learning_rate": 9.493761713927495e-06, "loss": 0.4081, "step": 193490 }, { "epoch": 1.1502041835333559, "grad_norm": 7.983736038208008, "learning_rate": 9.493670733756815e-06, "loss": 0.3895, "step": 193500 }, { "epoch": 1.1502636256100243, "grad_norm": 4.685959815979004, "learning_rate": 9.493579745847495e-06, "loss": 0.439, "step": 193510 }, { "epoch": 1.1503230676866927, "grad_norm": 7.571852207183838, "learning_rate": 9.493488750199696e-06, "loss": 0.4179, "step": 193520 }, { "epoch": 1.150382509763361, "grad_norm": 6.536774158477783, "learning_rate": 9.493397746813572e-06, "loss": 0.4193, "step": 193530 }, { "epoch": 1.1504419518400295, "grad_norm": 5.406519412994385, "learning_rate": 9.493306735689283e-06, "loss": 0.4074, "step": 193540 }, { "epoch": 1.150501393916698, "grad_norm": 4.764137268066406, "learning_rate": 9.493215716826982e-06, "loss": 0.3822, "step": 193550 }, { "epoch": 1.1505608359933663, "grad_norm": 5.2423481941223145, "learning_rate": 9.493124690226828e-06, "loss": 0.4369, "step": 193560 }, { "epoch": 1.1506202780700345, "grad_norm": 4.1111321449279785, "learning_rate": 9.493033655888977e-06, "loss": 0.4183, "step": 193570 }, { "epoch": 1.150679720146703, "grad_norm": 4.550641059875488, "learning_rate": 9.492942613813588e-06, "loss": 0.4419, "step": 193580 }, { "epoch": 1.1507391622233714, "grad_norm": 3.558457851409912, "learning_rate": 9.492851564000813e-06, "loss": 0.4238, "step": 193590 }, { "epoch": 1.1507986043000398, "grad_norm": 5.7074384689331055, "learning_rate": 9.492760506450812e-06, "loss": 0.4191, "step": 193600 }, { "epoch": 1.1508580463767082, "grad_norm": 4.439080238342285, "learning_rate": 9.492669441163743e-06, "loss": 0.3674, "step": 193610 }, { "epoch": 1.1509174884533766, "grad_norm": 6.706607341766357, "learning_rate": 9.492578368139758e-06, "loss": 0.4263, "step": 193620 }, { "epoch": 1.150976930530045, "grad_norm": 6.987256050109863, "learning_rate": 9.49248728737902e-06, "loss": 0.4269, "step": 193630 }, { "epoch": 1.1510363726067134, "grad_norm": 5.2919721603393555, "learning_rate": 9.49239619888168e-06, "loss": 0.3803, "step": 193640 }, { "epoch": 1.1510958146833818, "grad_norm": 6.774683475494385, "learning_rate": 9.4923051026479e-06, "loss": 0.3836, "step": 193650 }, { "epoch": 1.1511552567600503, "grad_norm": 5.282779216766357, "learning_rate": 9.492213998677834e-06, "loss": 0.412, "step": 193660 }, { "epoch": 1.1512146988367187, "grad_norm": 3.7392966747283936, "learning_rate": 9.49212288697164e-06, "loss": 0.3938, "step": 193670 }, { "epoch": 1.1512741409133869, "grad_norm": 4.155398368835449, "learning_rate": 9.492031767529474e-06, "loss": 0.4178, "step": 193680 }, { "epoch": 1.1513335829900553, "grad_norm": 4.227291584014893, "learning_rate": 9.491940640351493e-06, "loss": 0.3849, "step": 193690 }, { "epoch": 1.1513930250667237, "grad_norm": 3.6619150638580322, "learning_rate": 9.491849505437855e-06, "loss": 0.377, "step": 193700 }, { "epoch": 1.1514524671433921, "grad_norm": 5.970765590667725, "learning_rate": 9.491758362788714e-06, "loss": 0.3693, "step": 193710 }, { "epoch": 1.1515119092200605, "grad_norm": 7.308631420135498, "learning_rate": 9.491667212404232e-06, "loss": 0.42, "step": 193720 }, { "epoch": 1.151571351296729, "grad_norm": 5.3968186378479, "learning_rate": 9.491576054284561e-06, "loss": 0.3847, "step": 193730 }, { "epoch": 1.1516307933733974, "grad_norm": 4.677959442138672, "learning_rate": 9.491484888429863e-06, "loss": 0.442, "step": 193740 }, { "epoch": 1.1516902354500658, "grad_norm": 6.573901176452637, "learning_rate": 9.491393714840289e-06, "loss": 0.3848, "step": 193750 }, { "epoch": 1.151749677526734, "grad_norm": 3.544675827026367, "learning_rate": 9.491302533516e-06, "loss": 0.3277, "step": 193760 }, { "epoch": 1.1518091196034024, "grad_norm": 5.332882881164551, "learning_rate": 9.491211344457153e-06, "loss": 0.3955, "step": 193770 }, { "epoch": 1.1518685616800708, "grad_norm": 5.286750316619873, "learning_rate": 9.491120147663904e-06, "loss": 0.376, "step": 193780 }, { "epoch": 1.1519280037567392, "grad_norm": 4.94091796875, "learning_rate": 9.491028943136409e-06, "loss": 0.3975, "step": 193790 }, { "epoch": 1.1519874458334076, "grad_norm": 4.0237298011779785, "learning_rate": 9.490937730874827e-06, "loss": 0.3752, "step": 193800 }, { "epoch": 1.152046887910076, "grad_norm": 5.200217247009277, "learning_rate": 9.490846510879314e-06, "loss": 0.438, "step": 193810 }, { "epoch": 1.1521063299867444, "grad_norm": 5.974358558654785, "learning_rate": 9.490755283150029e-06, "loss": 0.3977, "step": 193820 }, { "epoch": 1.1521657720634129, "grad_norm": 6.225445747375488, "learning_rate": 9.490664047687127e-06, "loss": 0.3717, "step": 193830 }, { "epoch": 1.1522252141400813, "grad_norm": 6.349860191345215, "learning_rate": 9.490572804490765e-06, "loss": 0.4087, "step": 193840 }, { "epoch": 1.1522846562167497, "grad_norm": 5.4229912757873535, "learning_rate": 9.490481553561101e-06, "loss": 0.4087, "step": 193850 }, { "epoch": 1.1523440982934179, "grad_norm": 5.197995662689209, "learning_rate": 9.490390294898292e-06, "loss": 0.4215, "step": 193860 }, { "epoch": 1.1524035403700863, "grad_norm": 5.016171932220459, "learning_rate": 9.490299028502496e-06, "loss": 0.356, "step": 193870 }, { "epoch": 1.1524629824467547, "grad_norm": 6.110613822937012, "learning_rate": 9.490207754373869e-06, "loss": 0.4261, "step": 193880 }, { "epoch": 1.1525224245234231, "grad_norm": 4.572592258453369, "learning_rate": 9.490116472512567e-06, "loss": 0.432, "step": 193890 }, { "epoch": 1.1525818666000915, "grad_norm": 4.187939167022705, "learning_rate": 9.49002518291875e-06, "loss": 0.4086, "step": 193900 }, { "epoch": 1.15264130867676, "grad_norm": 5.063394546508789, "learning_rate": 9.489933885592573e-06, "loss": 0.4201, "step": 193910 }, { "epoch": 1.1527007507534284, "grad_norm": 5.977393627166748, "learning_rate": 9.489842580534195e-06, "loss": 0.4025, "step": 193920 }, { "epoch": 1.1527601928300968, "grad_norm": 5.216566562652588, "learning_rate": 9.489751267743772e-06, "loss": 0.4879, "step": 193930 }, { "epoch": 1.152819634906765, "grad_norm": 4.784954071044922, "learning_rate": 9.48965994722146e-06, "loss": 0.3869, "step": 193940 }, { "epoch": 1.1528790769834334, "grad_norm": 4.530984401702881, "learning_rate": 9.489568618967421e-06, "loss": 0.4033, "step": 193950 }, { "epoch": 1.1529385190601018, "grad_norm": 6.117514133453369, "learning_rate": 9.489477282981807e-06, "loss": 0.3862, "step": 193960 }, { "epoch": 1.1529979611367702, "grad_norm": 6.384991645812988, "learning_rate": 9.48938593926478e-06, "loss": 0.4272, "step": 193970 }, { "epoch": 1.1530574032134386, "grad_norm": 6.21505069732666, "learning_rate": 9.48929458781649e-06, "loss": 0.3892, "step": 193980 }, { "epoch": 1.153116845290107, "grad_norm": 6.281667709350586, "learning_rate": 9.489203228637103e-06, "loss": 0.4243, "step": 193990 }, { "epoch": 1.1531762873667755, "grad_norm": 5.67346715927124, "learning_rate": 9.489111861726772e-06, "loss": 0.4407, "step": 194000 }, { "epoch": 1.1532357294434439, "grad_norm": 5.172847270965576, "learning_rate": 9.489020487085654e-06, "loss": 0.3907, "step": 194010 }, { "epoch": 1.1532951715201123, "grad_norm": 4.364455223083496, "learning_rate": 9.488929104713907e-06, "loss": 0.3995, "step": 194020 }, { "epoch": 1.1533546135967807, "grad_norm": 4.63068962097168, "learning_rate": 9.48883771461169e-06, "loss": 0.3648, "step": 194030 }, { "epoch": 1.1534140556734491, "grad_norm": 5.829652309417725, "learning_rate": 9.488746316779155e-06, "loss": 0.3653, "step": 194040 }, { "epoch": 1.1534734977501173, "grad_norm": 5.37621545791626, "learning_rate": 9.488654911216468e-06, "loss": 0.38, "step": 194050 }, { "epoch": 1.1535329398267857, "grad_norm": 4.410164833068848, "learning_rate": 9.488563497923778e-06, "loss": 0.4014, "step": 194060 }, { "epoch": 1.1535923819034541, "grad_norm": 6.21904993057251, "learning_rate": 9.488472076901248e-06, "loss": 0.4339, "step": 194070 }, { "epoch": 1.1536518239801226, "grad_norm": 4.325029373168945, "learning_rate": 9.488380648149034e-06, "loss": 0.3932, "step": 194080 }, { "epoch": 1.153711266056791, "grad_norm": 4.453587055206299, "learning_rate": 9.488289211667291e-06, "loss": 0.3836, "step": 194090 }, { "epoch": 1.1537707081334594, "grad_norm": 6.3572096824646, "learning_rate": 9.488197767456179e-06, "loss": 0.4358, "step": 194100 }, { "epoch": 1.1538301502101278, "grad_norm": 5.582474708557129, "learning_rate": 9.488106315515856e-06, "loss": 0.4379, "step": 194110 }, { "epoch": 1.1538895922867962, "grad_norm": 5.954913139343262, "learning_rate": 9.488014855846477e-06, "loss": 0.4673, "step": 194120 }, { "epoch": 1.1539490343634644, "grad_norm": 4.21189546585083, "learning_rate": 9.487923388448202e-06, "loss": 0.3756, "step": 194130 }, { "epoch": 1.1540084764401328, "grad_norm": 4.305840969085693, "learning_rate": 9.487831913321189e-06, "loss": 0.3764, "step": 194140 }, { "epoch": 1.1540679185168012, "grad_norm": 3.945038080215454, "learning_rate": 9.487740430465591e-06, "loss": 0.4146, "step": 194150 }, { "epoch": 1.1541273605934697, "grad_norm": 5.4882731437683105, "learning_rate": 9.487648939881568e-06, "loss": 0.4062, "step": 194160 }, { "epoch": 1.154186802670138, "grad_norm": 5.328987121582031, "learning_rate": 9.487557441569281e-06, "loss": 0.4299, "step": 194170 }, { "epoch": 1.1542462447468065, "grad_norm": 5.63865852355957, "learning_rate": 9.487465935528884e-06, "loss": 0.406, "step": 194180 }, { "epoch": 1.154305686823475, "grad_norm": 5.235421657562256, "learning_rate": 9.487374421760534e-06, "loss": 0.3893, "step": 194190 }, { "epoch": 1.1543651289001433, "grad_norm": 4.323756694793701, "learning_rate": 9.48728290026439e-06, "loss": 0.4187, "step": 194200 }, { "epoch": 1.1544245709768117, "grad_norm": 5.858948707580566, "learning_rate": 9.487191371040609e-06, "loss": 0.4137, "step": 194210 }, { "epoch": 1.1544840130534801, "grad_norm": 4.481442928314209, "learning_rate": 9.48709983408935e-06, "loss": 0.3927, "step": 194220 }, { "epoch": 1.1545434551301483, "grad_norm": 5.535284996032715, "learning_rate": 9.487008289410771e-06, "loss": 0.4351, "step": 194230 }, { "epoch": 1.1546028972068167, "grad_norm": 6.978250026702881, "learning_rate": 9.486916737005027e-06, "loss": 0.4183, "step": 194240 }, { "epoch": 1.1546623392834852, "grad_norm": 5.153499603271484, "learning_rate": 9.486825176872276e-06, "loss": 0.4096, "step": 194250 }, { "epoch": 1.1547217813601536, "grad_norm": 4.7254791259765625, "learning_rate": 9.486733609012678e-06, "loss": 0.3987, "step": 194260 }, { "epoch": 1.154781223436822, "grad_norm": 4.734925270080566, "learning_rate": 9.486642033426388e-06, "loss": 0.3546, "step": 194270 }, { "epoch": 1.1548406655134904, "grad_norm": 5.333698749542236, "learning_rate": 9.486550450113565e-06, "loss": 0.4118, "step": 194280 }, { "epoch": 1.1549001075901588, "grad_norm": 6.605005741119385, "learning_rate": 9.486458859074371e-06, "loss": 0.4358, "step": 194290 }, { "epoch": 1.1549595496668272, "grad_norm": 3.951432943344116, "learning_rate": 9.486367260308955e-06, "loss": 0.4043, "step": 194300 }, { "epoch": 1.1550189917434954, "grad_norm": 5.912590503692627, "learning_rate": 9.48627565381748e-06, "loss": 0.4197, "step": 194310 }, { "epoch": 1.1550784338201638, "grad_norm": 5.52711820602417, "learning_rate": 9.486184039600104e-06, "loss": 0.438, "step": 194320 }, { "epoch": 1.1551378758968323, "grad_norm": 4.101690292358398, "learning_rate": 9.486092417656983e-06, "loss": 0.4254, "step": 194330 }, { "epoch": 1.1551973179735007, "grad_norm": 5.457239627838135, "learning_rate": 9.486000787988276e-06, "loss": 0.351, "step": 194340 }, { "epoch": 1.155256760050169, "grad_norm": 4.534240245819092, "learning_rate": 9.485909150594142e-06, "loss": 0.3761, "step": 194350 }, { "epoch": 1.1553162021268375, "grad_norm": 3.477715253829956, "learning_rate": 9.485817505474734e-06, "loss": 0.3967, "step": 194360 }, { "epoch": 1.155375644203506, "grad_norm": 5.944279193878174, "learning_rate": 9.485725852630215e-06, "loss": 0.3918, "step": 194370 }, { "epoch": 1.1554350862801743, "grad_norm": 7.411794185638428, "learning_rate": 9.48563419206074e-06, "loss": 0.3992, "step": 194380 }, { "epoch": 1.1554945283568427, "grad_norm": 5.426864147186279, "learning_rate": 9.48554252376647e-06, "loss": 0.375, "step": 194390 }, { "epoch": 1.1555539704335112, "grad_norm": 4.792275428771973, "learning_rate": 9.485450847747558e-06, "loss": 0.4151, "step": 194400 }, { "epoch": 1.1556134125101796, "grad_norm": 4.511129856109619, "learning_rate": 9.485359164004166e-06, "loss": 0.4287, "step": 194410 }, { "epoch": 1.1556728545868478, "grad_norm": 5.162724018096924, "learning_rate": 9.485267472536447e-06, "loss": 0.3885, "step": 194420 }, { "epoch": 1.1557322966635162, "grad_norm": 6.784773826599121, "learning_rate": 9.485175773344566e-06, "loss": 0.4249, "step": 194430 }, { "epoch": 1.1557917387401846, "grad_norm": 5.789727687835693, "learning_rate": 9.485084066428675e-06, "loss": 0.4054, "step": 194440 }, { "epoch": 1.155851180816853, "grad_norm": 4.593270778656006, "learning_rate": 9.484992351788937e-06, "loss": 0.3733, "step": 194450 }, { "epoch": 1.1559106228935214, "grad_norm": 5.966941833496094, "learning_rate": 9.484900629425504e-06, "loss": 0.407, "step": 194460 }, { "epoch": 1.1559700649701898, "grad_norm": 4.3441691398620605, "learning_rate": 9.484808899338537e-06, "loss": 0.3812, "step": 194470 }, { "epoch": 1.1560295070468583, "grad_norm": 4.337647438049316, "learning_rate": 9.484717161528196e-06, "loss": 0.3916, "step": 194480 }, { "epoch": 1.1560889491235267, "grad_norm": 4.61825704574585, "learning_rate": 9.484625415994637e-06, "loss": 0.4083, "step": 194490 }, { "epoch": 1.1561483912001949, "grad_norm": 5.260613918304443, "learning_rate": 9.484533662738016e-06, "loss": 0.4265, "step": 194500 }, { "epoch": 1.1562078332768633, "grad_norm": 5.447279930114746, "learning_rate": 9.484441901758495e-06, "loss": 0.3879, "step": 194510 }, { "epoch": 1.1562672753535317, "grad_norm": 5.420323371887207, "learning_rate": 9.484350133056228e-06, "loss": 0.3993, "step": 194520 }, { "epoch": 1.1563267174302, "grad_norm": 3.9623827934265137, "learning_rate": 9.484258356631374e-06, "loss": 0.4099, "step": 194530 }, { "epoch": 1.1563861595068685, "grad_norm": 4.379549503326416, "learning_rate": 9.484166572484095e-06, "loss": 0.3887, "step": 194540 }, { "epoch": 1.156445601583537, "grad_norm": 4.990978717803955, "learning_rate": 9.484074780614544e-06, "loss": 0.4485, "step": 194550 }, { "epoch": 1.1565050436602053, "grad_norm": 4.85704231262207, "learning_rate": 9.483982981022884e-06, "loss": 0.4201, "step": 194560 }, { "epoch": 1.1565644857368738, "grad_norm": 4.941699981689453, "learning_rate": 9.483891173709267e-06, "loss": 0.4043, "step": 194570 }, { "epoch": 1.1566239278135422, "grad_norm": 4.354520320892334, "learning_rate": 9.483799358673858e-06, "loss": 0.3841, "step": 194580 }, { "epoch": 1.1566833698902106, "grad_norm": 5.059015274047852, "learning_rate": 9.483707535916808e-06, "loss": 0.3788, "step": 194590 }, { "epoch": 1.1567428119668788, "grad_norm": 4.058518886566162, "learning_rate": 9.483615705438281e-06, "loss": 0.4399, "step": 194600 }, { "epoch": 1.1568022540435472, "grad_norm": 6.394501209259033, "learning_rate": 9.483523867238432e-06, "loss": 0.4387, "step": 194610 }, { "epoch": 1.1568616961202156, "grad_norm": 5.234776973724365, "learning_rate": 9.48343202131742e-06, "loss": 0.4026, "step": 194620 }, { "epoch": 1.156921138196884, "grad_norm": 5.1720194816589355, "learning_rate": 9.4833401676754e-06, "loss": 0.3863, "step": 194630 }, { "epoch": 1.1569805802735524, "grad_norm": 4.618701457977295, "learning_rate": 9.483248306312539e-06, "loss": 0.3919, "step": 194640 }, { "epoch": 1.1570400223502209, "grad_norm": 5.5928544998168945, "learning_rate": 9.483156437228986e-06, "loss": 0.4165, "step": 194650 }, { "epoch": 1.1570994644268893, "grad_norm": 4.79456090927124, "learning_rate": 9.483064560424903e-06, "loss": 0.3968, "step": 194660 }, { "epoch": 1.1571589065035577, "grad_norm": 5.13178014755249, "learning_rate": 9.482972675900447e-06, "loss": 0.436, "step": 194670 }, { "epoch": 1.1572183485802259, "grad_norm": 4.136111736297607, "learning_rate": 9.48288078365578e-06, "loss": 0.3946, "step": 194680 }, { "epoch": 1.1572777906568943, "grad_norm": 5.843329429626465, "learning_rate": 9.482788883691055e-06, "loss": 0.4131, "step": 194690 }, { "epoch": 1.1573372327335627, "grad_norm": 5.322864055633545, "learning_rate": 9.482696976006433e-06, "loss": 0.404, "step": 194700 }, { "epoch": 1.1573966748102311, "grad_norm": 5.114100933074951, "learning_rate": 9.482605060602073e-06, "loss": 0.4335, "step": 194710 }, { "epoch": 1.1574561168868995, "grad_norm": 4.638782501220703, "learning_rate": 9.482513137478131e-06, "loss": 0.4197, "step": 194720 }, { "epoch": 1.157515558963568, "grad_norm": 5.142360210418701, "learning_rate": 9.482421206634768e-06, "loss": 0.3615, "step": 194730 }, { "epoch": 1.1575750010402364, "grad_norm": 5.0059814453125, "learning_rate": 9.48232926807214e-06, "loss": 0.4116, "step": 194740 }, { "epoch": 1.1576344431169048, "grad_norm": 6.981037139892578, "learning_rate": 9.482237321790407e-06, "loss": 0.4352, "step": 194750 }, { "epoch": 1.1576938851935732, "grad_norm": 5.737584114074707, "learning_rate": 9.482145367789725e-06, "loss": 0.3456, "step": 194760 }, { "epoch": 1.1577533272702416, "grad_norm": 5.375273704528809, "learning_rate": 9.482053406070255e-06, "loss": 0.3822, "step": 194770 }, { "epoch": 1.15781276934691, "grad_norm": 4.827122688293457, "learning_rate": 9.481961436632152e-06, "loss": 0.3756, "step": 194780 }, { "epoch": 1.1578722114235782, "grad_norm": 5.944488048553467, "learning_rate": 9.481869459475579e-06, "loss": 0.3937, "step": 194790 }, { "epoch": 1.1579316535002466, "grad_norm": 5.1249260902404785, "learning_rate": 9.481777474600692e-06, "loss": 0.3894, "step": 194800 }, { "epoch": 1.157991095576915, "grad_norm": 4.7569403648376465, "learning_rate": 9.481685482007648e-06, "loss": 0.3474, "step": 194810 }, { "epoch": 1.1580505376535835, "grad_norm": 6.540919780731201, "learning_rate": 9.481593481696609e-06, "loss": 0.4019, "step": 194820 }, { "epoch": 1.1581099797302519, "grad_norm": 5.461714744567871, "learning_rate": 9.481501473667729e-06, "loss": 0.408, "step": 194830 }, { "epoch": 1.1581694218069203, "grad_norm": 4.958946704864502, "learning_rate": 9.48140945792117e-06, "loss": 0.4079, "step": 194840 }, { "epoch": 1.1582288638835887, "grad_norm": 4.2753682136535645, "learning_rate": 9.481317434457088e-06, "loss": 0.3988, "step": 194850 }, { "epoch": 1.1582883059602571, "grad_norm": 5.378864765167236, "learning_rate": 9.481225403275644e-06, "loss": 0.4129, "step": 194860 }, { "epoch": 1.1583477480369253, "grad_norm": 5.646078586578369, "learning_rate": 9.481133364376996e-06, "loss": 0.4132, "step": 194870 }, { "epoch": 1.1584071901135937, "grad_norm": 4.701876640319824, "learning_rate": 9.4810413177613e-06, "loss": 0.422, "step": 194880 }, { "epoch": 1.1584666321902621, "grad_norm": 4.865720272064209, "learning_rate": 9.480949263428715e-06, "loss": 0.391, "step": 194890 }, { "epoch": 1.1585260742669306, "grad_norm": 5.138334274291992, "learning_rate": 9.480857201379403e-06, "loss": 0.4068, "step": 194900 }, { "epoch": 1.158585516343599, "grad_norm": 4.398614406585693, "learning_rate": 9.480765131613521e-06, "loss": 0.3691, "step": 194910 }, { "epoch": 1.1586449584202674, "grad_norm": 4.5083842277526855, "learning_rate": 9.480673054131224e-06, "loss": 0.4059, "step": 194920 }, { "epoch": 1.1587044004969358, "grad_norm": 5.129205226898193, "learning_rate": 9.480580968932676e-06, "loss": 0.384, "step": 194930 }, { "epoch": 1.1587638425736042, "grad_norm": 4.550729751586914, "learning_rate": 9.48048887601803e-06, "loss": 0.4026, "step": 194940 }, { "epoch": 1.1588232846502726, "grad_norm": 4.705333709716797, "learning_rate": 9.48039677538745e-06, "loss": 0.3737, "step": 194950 }, { "epoch": 1.158882726726941, "grad_norm": 3.483708143234253, "learning_rate": 9.480304667041091e-06, "loss": 0.4055, "step": 194960 }, { "epoch": 1.1589421688036092, "grad_norm": 4.483016490936279, "learning_rate": 9.480212550979114e-06, "loss": 0.398, "step": 194970 }, { "epoch": 1.1590016108802776, "grad_norm": 4.755285739898682, "learning_rate": 9.480120427201676e-06, "loss": 0.4027, "step": 194980 }, { "epoch": 1.159061052956946, "grad_norm": 4.236902236938477, "learning_rate": 9.480028295708937e-06, "loss": 0.4094, "step": 194990 }, { "epoch": 1.1591204950336145, "grad_norm": 4.2890424728393555, "learning_rate": 9.479936156501052e-06, "loss": 0.4204, "step": 195000 }, { "epoch": 1.1591799371102829, "grad_norm": 5.556948661804199, "learning_rate": 9.479844009578185e-06, "loss": 0.4124, "step": 195010 }, { "epoch": 1.1592393791869513, "grad_norm": 6.3809590339660645, "learning_rate": 9.47975185494049e-06, "loss": 0.3927, "step": 195020 }, { "epoch": 1.1592988212636197, "grad_norm": 4.712493419647217, "learning_rate": 9.479659692588127e-06, "loss": 0.4272, "step": 195030 }, { "epoch": 1.1593582633402881, "grad_norm": 5.8063788414001465, "learning_rate": 9.479567522521259e-06, "loss": 0.4123, "step": 195040 }, { "epoch": 1.1594177054169563, "grad_norm": 5.082276344299316, "learning_rate": 9.479475344740039e-06, "loss": 0.4025, "step": 195050 }, { "epoch": 1.1594771474936247, "grad_norm": 6.087332248687744, "learning_rate": 9.479383159244628e-06, "loss": 0.4419, "step": 195060 }, { "epoch": 1.1595365895702932, "grad_norm": 5.859510898590088, "learning_rate": 9.479290966035186e-06, "loss": 0.3907, "step": 195070 }, { "epoch": 1.1595960316469616, "grad_norm": 6.173720836639404, "learning_rate": 9.47919876511187e-06, "loss": 0.3765, "step": 195080 }, { "epoch": 1.15965547372363, "grad_norm": 5.002053260803223, "learning_rate": 9.479106556474839e-06, "loss": 0.4055, "step": 195090 }, { "epoch": 1.1597149158002984, "grad_norm": 5.372070789337158, "learning_rate": 9.479014340124252e-06, "loss": 0.3747, "step": 195100 }, { "epoch": 1.1597743578769668, "grad_norm": 6.6038336753845215, "learning_rate": 9.478922116060267e-06, "loss": 0.4285, "step": 195110 }, { "epoch": 1.1598337999536352, "grad_norm": 4.563429355621338, "learning_rate": 9.478829884283045e-06, "loss": 0.3937, "step": 195120 }, { "epoch": 1.1598932420303036, "grad_norm": 6.386491775512695, "learning_rate": 9.478737644792744e-06, "loss": 0.4337, "step": 195130 }, { "epoch": 1.159952684106972, "grad_norm": 3.9287431240081787, "learning_rate": 9.478645397589521e-06, "loss": 0.4327, "step": 195140 }, { "epoch": 1.1600121261836405, "grad_norm": 5.176884651184082, "learning_rate": 9.478553142673536e-06, "loss": 0.387, "step": 195150 }, { "epoch": 1.1600715682603087, "grad_norm": 4.536246299743652, "learning_rate": 9.47846088004495e-06, "loss": 0.3733, "step": 195160 }, { "epoch": 1.160131010336977, "grad_norm": 5.932276725769043, "learning_rate": 9.478368609703919e-06, "loss": 0.4164, "step": 195170 }, { "epoch": 1.1601904524136455, "grad_norm": 5.039723873138428, "learning_rate": 9.478276331650602e-06, "loss": 0.4384, "step": 195180 }, { "epoch": 1.160249894490314, "grad_norm": 4.94675350189209, "learning_rate": 9.478184045885159e-06, "loss": 0.4114, "step": 195190 }, { "epoch": 1.1603093365669823, "grad_norm": 5.720937252044678, "learning_rate": 9.47809175240775e-06, "loss": 0.4349, "step": 195200 }, { "epoch": 1.1603687786436507, "grad_norm": 4.558060646057129, "learning_rate": 9.47799945121853e-06, "loss": 0.3662, "step": 195210 }, { "epoch": 1.1604282207203191, "grad_norm": 6.186172008514404, "learning_rate": 9.477907142317665e-06, "loss": 0.3915, "step": 195220 }, { "epoch": 1.1604876627969876, "grad_norm": 4.761868953704834, "learning_rate": 9.477814825705307e-06, "loss": 0.3957, "step": 195230 }, { "epoch": 1.1605471048736558, "grad_norm": 5.453886985778809, "learning_rate": 9.477722501381618e-06, "loss": 0.401, "step": 195240 }, { "epoch": 1.1606065469503242, "grad_norm": 5.668956756591797, "learning_rate": 9.477630169346756e-06, "loss": 0.4271, "step": 195250 }, { "epoch": 1.1606659890269926, "grad_norm": 5.183548450469971, "learning_rate": 9.477537829600882e-06, "loss": 0.4007, "step": 195260 }, { "epoch": 1.160725431103661, "grad_norm": 5.322646141052246, "learning_rate": 9.477445482144152e-06, "loss": 0.3602, "step": 195270 }, { "epoch": 1.1607848731803294, "grad_norm": 5.073062419891357, "learning_rate": 9.477353126976727e-06, "loss": 0.4031, "step": 195280 }, { "epoch": 1.1608443152569978, "grad_norm": 4.114273548126221, "learning_rate": 9.477260764098766e-06, "loss": 0.3916, "step": 195290 }, { "epoch": 1.1609037573336662, "grad_norm": 4.1195549964904785, "learning_rate": 9.477168393510427e-06, "loss": 0.355, "step": 195300 }, { "epoch": 1.1609631994103347, "grad_norm": 5.320464134216309, "learning_rate": 9.477076015211872e-06, "loss": 0.4019, "step": 195310 }, { "epoch": 1.161022641487003, "grad_norm": 4.18771505355835, "learning_rate": 9.476983629203256e-06, "loss": 0.4013, "step": 195320 }, { "epoch": 1.1610820835636715, "grad_norm": 6.4986958503723145, "learning_rate": 9.47689123548474e-06, "loss": 0.436, "step": 195330 }, { "epoch": 1.1611415256403397, "grad_norm": 5.27372932434082, "learning_rate": 9.476798834056484e-06, "loss": 0.4364, "step": 195340 }, { "epoch": 1.161200967717008, "grad_norm": 5.708188533782959, "learning_rate": 9.476706424918645e-06, "loss": 0.3809, "step": 195350 }, { "epoch": 1.1612604097936765, "grad_norm": 7.018909454345703, "learning_rate": 9.476614008071385e-06, "loss": 0.424, "step": 195360 }, { "epoch": 1.161319851870345, "grad_norm": 5.422849178314209, "learning_rate": 9.47652158351486e-06, "loss": 0.3681, "step": 195370 }, { "epoch": 1.1613792939470133, "grad_norm": 5.5003533363342285, "learning_rate": 9.476429151249231e-06, "loss": 0.4354, "step": 195380 }, { "epoch": 1.1614387360236818, "grad_norm": 4.49298620223999, "learning_rate": 9.476336711274658e-06, "loss": 0.413, "step": 195390 }, { "epoch": 1.1614981781003502, "grad_norm": 7.5638298988342285, "learning_rate": 9.4762442635913e-06, "loss": 0.41, "step": 195400 }, { "epoch": 1.1615576201770186, "grad_norm": 3.2056121826171875, "learning_rate": 9.476151808199312e-06, "loss": 0.423, "step": 195410 }, { "epoch": 1.1616170622536868, "grad_norm": 7.706875324249268, "learning_rate": 9.476059345098858e-06, "loss": 0.3843, "step": 195420 }, { "epoch": 1.1616765043303552, "grad_norm": 4.122464656829834, "learning_rate": 9.475966874290097e-06, "loss": 0.4207, "step": 195430 }, { "epoch": 1.1617359464070236, "grad_norm": 5.494146823883057, "learning_rate": 9.475874395773186e-06, "loss": 0.4167, "step": 195440 }, { "epoch": 1.161795388483692, "grad_norm": 6.7461137771606445, "learning_rate": 9.475781909548285e-06, "loss": 0.4322, "step": 195450 }, { "epoch": 1.1618548305603604, "grad_norm": 4.865231990814209, "learning_rate": 9.475689415615552e-06, "loss": 0.3874, "step": 195460 }, { "epoch": 1.1619142726370288, "grad_norm": 5.787696838378906, "learning_rate": 9.47559691397515e-06, "loss": 0.4122, "step": 195470 }, { "epoch": 1.1619737147136973, "grad_norm": 3.9419379234313965, "learning_rate": 9.475504404627236e-06, "loss": 0.3956, "step": 195480 }, { "epoch": 1.1620331567903657, "grad_norm": 6.719714164733887, "learning_rate": 9.475411887571969e-06, "loss": 0.4398, "step": 195490 }, { "epoch": 1.162092598867034, "grad_norm": 4.77410364151001, "learning_rate": 9.475319362809508e-06, "loss": 0.3804, "step": 195500 }, { "epoch": 1.1621520409437025, "grad_norm": 5.584178447723389, "learning_rate": 9.475226830340015e-06, "loss": 0.3904, "step": 195510 }, { "epoch": 1.162211483020371, "grad_norm": 4.997765064239502, "learning_rate": 9.475134290163645e-06, "loss": 0.4192, "step": 195520 }, { "epoch": 1.162270925097039, "grad_norm": 6.214514255523682, "learning_rate": 9.475041742280561e-06, "loss": 0.4142, "step": 195530 }, { "epoch": 1.1623303671737075, "grad_norm": 4.7739481925964355, "learning_rate": 9.47494918669092e-06, "loss": 0.4077, "step": 195540 }, { "epoch": 1.162389809250376, "grad_norm": 6.132011413574219, "learning_rate": 9.474856623394885e-06, "loss": 0.3772, "step": 195550 }, { "epoch": 1.1624492513270444, "grad_norm": 5.051578044891357, "learning_rate": 9.47476405239261e-06, "loss": 0.3642, "step": 195560 }, { "epoch": 1.1625086934037128, "grad_norm": 4.342929840087891, "learning_rate": 9.47467147368426e-06, "loss": 0.3912, "step": 195570 }, { "epoch": 1.1625681354803812, "grad_norm": 5.081418037414551, "learning_rate": 9.474578887269991e-06, "loss": 0.433, "step": 195580 }, { "epoch": 1.1626275775570496, "grad_norm": 6.977457046508789, "learning_rate": 9.474486293149962e-06, "loss": 0.4334, "step": 195590 }, { "epoch": 1.162687019633718, "grad_norm": 5.908831596374512, "learning_rate": 9.474393691324337e-06, "loss": 0.4233, "step": 195600 }, { "epoch": 1.1627464617103862, "grad_norm": 5.617760181427002, "learning_rate": 9.474301081793268e-06, "loss": 0.3923, "step": 195610 }, { "epoch": 1.1628059037870546, "grad_norm": 4.6570868492126465, "learning_rate": 9.474208464556923e-06, "loss": 0.3676, "step": 195620 }, { "epoch": 1.162865345863723, "grad_norm": 5.523332118988037, "learning_rate": 9.474115839615455e-06, "loss": 0.4349, "step": 195630 }, { "epoch": 1.1629247879403914, "grad_norm": 6.1138176918029785, "learning_rate": 9.474023206969023e-06, "loss": 0.4336, "step": 195640 }, { "epoch": 1.1629842300170599, "grad_norm": 4.786656856536865, "learning_rate": 9.473930566617792e-06, "loss": 0.399, "step": 195650 }, { "epoch": 1.1630436720937283, "grad_norm": 5.413215637207031, "learning_rate": 9.473837918561919e-06, "loss": 0.4066, "step": 195660 }, { "epoch": 1.1631031141703967, "grad_norm": 4.366760730743408, "learning_rate": 9.473745262801564e-06, "loss": 0.3696, "step": 195670 }, { "epoch": 1.163162556247065, "grad_norm": 3.9278013706207275, "learning_rate": 9.473652599336884e-06, "loss": 0.4387, "step": 195680 }, { "epoch": 1.1632219983237335, "grad_norm": 4.583829402923584, "learning_rate": 9.473559928168041e-06, "loss": 0.4354, "step": 195690 }, { "epoch": 1.163281440400402, "grad_norm": 4.9104323387146, "learning_rate": 9.473467249295194e-06, "loss": 0.3617, "step": 195700 }, { "epoch": 1.1633408824770701, "grad_norm": 4.837879657745361, "learning_rate": 9.473374562718502e-06, "loss": 0.4116, "step": 195710 }, { "epoch": 1.1634003245537385, "grad_norm": 5.6165971755981445, "learning_rate": 9.473281868438126e-06, "loss": 0.3482, "step": 195720 }, { "epoch": 1.163459766630407, "grad_norm": 6.9794206619262695, "learning_rate": 9.473189166454225e-06, "loss": 0.3798, "step": 195730 }, { "epoch": 1.1635192087070754, "grad_norm": 6.135961055755615, "learning_rate": 9.473096456766959e-06, "loss": 0.3872, "step": 195740 }, { "epoch": 1.1635786507837438, "grad_norm": 4.938994884490967, "learning_rate": 9.473003739376485e-06, "loss": 0.4125, "step": 195750 }, { "epoch": 1.1636380928604122, "grad_norm": 4.618594646453857, "learning_rate": 9.472911014282967e-06, "loss": 0.3525, "step": 195760 }, { "epoch": 1.1636975349370806, "grad_norm": 5.131804466247559, "learning_rate": 9.472818281486563e-06, "loss": 0.4021, "step": 195770 }, { "epoch": 1.163756977013749, "grad_norm": 4.842046737670898, "learning_rate": 9.472725540987431e-06, "loss": 0.4238, "step": 195780 }, { "epoch": 1.1638164190904172, "grad_norm": 5.095194339752197, "learning_rate": 9.472632792785732e-06, "loss": 0.4437, "step": 195790 }, { "epoch": 1.1638758611670856, "grad_norm": 6.150270462036133, "learning_rate": 9.472540036881626e-06, "loss": 0.4117, "step": 195800 }, { "epoch": 1.163935303243754, "grad_norm": 4.5425801277160645, "learning_rate": 9.472447273275271e-06, "loss": 0.3781, "step": 195810 }, { "epoch": 1.1639947453204225, "grad_norm": 4.015657424926758, "learning_rate": 9.472354501966829e-06, "loss": 0.4108, "step": 195820 }, { "epoch": 1.1640541873970909, "grad_norm": 4.8505778312683105, "learning_rate": 9.47226172295646e-06, "loss": 0.4459, "step": 195830 }, { "epoch": 1.1641136294737593, "grad_norm": 5.052803993225098, "learning_rate": 9.472168936244322e-06, "loss": 0.4479, "step": 195840 }, { "epoch": 1.1641730715504277, "grad_norm": 4.789435863494873, "learning_rate": 9.472076141830574e-06, "loss": 0.3946, "step": 195850 }, { "epoch": 1.1642325136270961, "grad_norm": 5.679357528686523, "learning_rate": 9.471983339715381e-06, "loss": 0.4282, "step": 195860 }, { "epoch": 1.1642919557037645, "grad_norm": 7.189048767089844, "learning_rate": 9.471890529898895e-06, "loss": 0.4141, "step": 195870 }, { "epoch": 1.164351397780433, "grad_norm": 6.035469055175781, "learning_rate": 9.471797712381283e-06, "loss": 0.3956, "step": 195880 }, { "epoch": 1.1644108398571014, "grad_norm": 5.642750263214111, "learning_rate": 9.4717048871627e-06, "loss": 0.3911, "step": 195890 }, { "epoch": 1.1644702819337696, "grad_norm": 6.019397735595703, "learning_rate": 9.47161205424331e-06, "loss": 0.3809, "step": 195900 }, { "epoch": 1.164529724010438, "grad_norm": 4.762635707855225, "learning_rate": 9.471519213623265e-06, "loss": 0.4353, "step": 195910 }, { "epoch": 1.1645891660871064, "grad_norm": 4.909453868865967, "learning_rate": 9.471426365302737e-06, "loss": 0.4183, "step": 195920 }, { "epoch": 1.1646486081637748, "grad_norm": 4.596107482910156, "learning_rate": 9.471333509281875e-06, "loss": 0.415, "step": 195930 }, { "epoch": 1.1647080502404432, "grad_norm": 6.116096019744873, "learning_rate": 9.471240645560844e-06, "loss": 0.3993, "step": 195940 }, { "epoch": 1.1647674923171116, "grad_norm": 5.095906734466553, "learning_rate": 9.471147774139804e-06, "loss": 0.3768, "step": 195950 }, { "epoch": 1.16482693439378, "grad_norm": 5.047323226928711, "learning_rate": 9.471054895018914e-06, "loss": 0.4549, "step": 195960 }, { "epoch": 1.1648863764704485, "grad_norm": 6.154385089874268, "learning_rate": 9.470962008198333e-06, "loss": 0.4006, "step": 195970 }, { "epoch": 1.1649458185471167, "grad_norm": 4.960599422454834, "learning_rate": 9.470869113678223e-06, "loss": 0.3533, "step": 195980 }, { "epoch": 1.165005260623785, "grad_norm": 5.721158027648926, "learning_rate": 9.470776211458741e-06, "loss": 0.3646, "step": 195990 }, { "epoch": 1.1650647027004535, "grad_norm": 4.5482282638549805, "learning_rate": 9.47068330154005e-06, "loss": 0.3619, "step": 196000 }, { "epoch": 1.165124144777122, "grad_norm": 4.811966896057129, "learning_rate": 9.470590383922311e-06, "loss": 0.3698, "step": 196010 }, { "epoch": 1.1651835868537903, "grad_norm": 3.850069284439087, "learning_rate": 9.47049745860568e-06, "loss": 0.4103, "step": 196020 }, { "epoch": 1.1652430289304587, "grad_norm": 7.311882019042969, "learning_rate": 9.47040452559032e-06, "loss": 0.3937, "step": 196030 }, { "epoch": 1.1653024710071271, "grad_norm": 5.365577220916748, "learning_rate": 9.470311584876389e-06, "loss": 0.3829, "step": 196040 }, { "epoch": 1.1653619130837956, "grad_norm": 5.752358913421631, "learning_rate": 9.470218636464049e-06, "loss": 0.4057, "step": 196050 }, { "epoch": 1.165421355160464, "grad_norm": 4.072961807250977, "learning_rate": 9.470125680353458e-06, "loss": 0.399, "step": 196060 }, { "epoch": 1.1654807972371324, "grad_norm": 5.4444451332092285, "learning_rate": 9.470032716544777e-06, "loss": 0.3943, "step": 196070 }, { "epoch": 1.1655402393138006, "grad_norm": 4.938246250152588, "learning_rate": 9.469939745038167e-06, "loss": 0.3785, "step": 196080 }, { "epoch": 1.165599681390469, "grad_norm": 5.717207908630371, "learning_rate": 9.469846765833788e-06, "loss": 0.37, "step": 196090 }, { "epoch": 1.1656591234671374, "grad_norm": 4.415745258331299, "learning_rate": 9.469753778931798e-06, "loss": 0.3316, "step": 196100 }, { "epoch": 1.1657185655438058, "grad_norm": 6.04935359954834, "learning_rate": 9.469660784332359e-06, "loss": 0.4401, "step": 196110 }, { "epoch": 1.1657780076204742, "grad_norm": 5.808382511138916, "learning_rate": 9.469567782035631e-06, "loss": 0.3886, "step": 196120 }, { "epoch": 1.1658374496971426, "grad_norm": 7.182071685791016, "learning_rate": 9.469474772041775e-06, "loss": 0.4016, "step": 196130 }, { "epoch": 1.165896891773811, "grad_norm": 4.798746585845947, "learning_rate": 9.46938175435095e-06, "loss": 0.4031, "step": 196140 }, { "epoch": 1.1659563338504795, "grad_norm": 4.409106254577637, "learning_rate": 9.469288728963315e-06, "loss": 0.3765, "step": 196150 }, { "epoch": 1.1660157759271477, "grad_norm": 4.715367317199707, "learning_rate": 9.469195695879034e-06, "loss": 0.4044, "step": 196160 }, { "epoch": 1.166075218003816, "grad_norm": 5.157047271728516, "learning_rate": 9.469102655098262e-06, "loss": 0.4076, "step": 196170 }, { "epoch": 1.1661346600804845, "grad_norm": 4.782010555267334, "learning_rate": 9.469009606621163e-06, "loss": 0.3486, "step": 196180 }, { "epoch": 1.166194102157153, "grad_norm": 5.489102363586426, "learning_rate": 9.468916550447897e-06, "loss": 0.4397, "step": 196190 }, { "epoch": 1.1662535442338213, "grad_norm": 4.3807477951049805, "learning_rate": 9.468823486578621e-06, "loss": 0.3607, "step": 196200 }, { "epoch": 1.1663129863104897, "grad_norm": 5.246793270111084, "learning_rate": 9.468730415013501e-06, "loss": 0.3967, "step": 196210 }, { "epoch": 1.1663724283871582, "grad_norm": 4.632747650146484, "learning_rate": 9.468637335752694e-06, "loss": 0.4134, "step": 196220 }, { "epoch": 1.1664318704638266, "grad_norm": 4.506432056427002, "learning_rate": 9.468544248796358e-06, "loss": 0.3994, "step": 196230 }, { "epoch": 1.166491312540495, "grad_norm": 5.19257116317749, "learning_rate": 9.468451154144655e-06, "loss": 0.3944, "step": 196240 }, { "epoch": 1.1665507546171634, "grad_norm": 4.564715385437012, "learning_rate": 9.468358051797748e-06, "loss": 0.4428, "step": 196250 }, { "epoch": 1.1666101966938318, "grad_norm": 5.470582485198975, "learning_rate": 9.468264941755797e-06, "loss": 0.359, "step": 196260 }, { "epoch": 1.1666696387705, "grad_norm": 5.38019323348999, "learning_rate": 9.468171824018956e-06, "loss": 0.4263, "step": 196270 }, { "epoch": 1.1667290808471684, "grad_norm": 5.051625728607178, "learning_rate": 9.468078698587392e-06, "loss": 0.4076, "step": 196280 }, { "epoch": 1.1667885229238368, "grad_norm": 4.627703666687012, "learning_rate": 9.467985565461264e-06, "loss": 0.3958, "step": 196290 }, { "epoch": 1.1668479650005052, "grad_norm": 4.365655422210693, "learning_rate": 9.467892424640733e-06, "loss": 0.3896, "step": 196300 }, { "epoch": 1.1669074070771737, "grad_norm": 5.3067755699157715, "learning_rate": 9.467799276125956e-06, "loss": 0.4013, "step": 196310 }, { "epoch": 1.166966849153842, "grad_norm": 4.570945739746094, "learning_rate": 9.467706119917098e-06, "loss": 0.4149, "step": 196320 }, { "epoch": 1.1670262912305105, "grad_norm": 5.403372287750244, "learning_rate": 9.467612956014314e-06, "loss": 0.4013, "step": 196330 }, { "epoch": 1.167085733307179, "grad_norm": 7.321971416473389, "learning_rate": 9.467519784417769e-06, "loss": 0.4168, "step": 196340 }, { "epoch": 1.167145175383847, "grad_norm": 6.46401834487915, "learning_rate": 9.467426605127622e-06, "loss": 0.3805, "step": 196350 }, { "epoch": 1.1672046174605155, "grad_norm": 4.127858638763428, "learning_rate": 9.467333418144032e-06, "loss": 0.3693, "step": 196360 }, { "epoch": 1.167264059537184, "grad_norm": 4.01137638092041, "learning_rate": 9.467240223467162e-06, "loss": 0.4146, "step": 196370 }, { "epoch": 1.1673235016138523, "grad_norm": 3.376986503601074, "learning_rate": 9.46714702109717e-06, "loss": 0.3916, "step": 196380 }, { "epoch": 1.1673829436905208, "grad_norm": 5.305337905883789, "learning_rate": 9.467053811034219e-06, "loss": 0.3744, "step": 196390 }, { "epoch": 1.1674423857671892, "grad_norm": 6.548985004425049, "learning_rate": 9.466960593278468e-06, "loss": 0.4001, "step": 196400 }, { "epoch": 1.1675018278438576, "grad_norm": 5.764761447906494, "learning_rate": 9.466867367830077e-06, "loss": 0.3874, "step": 196410 }, { "epoch": 1.167561269920526, "grad_norm": 4.221714019775391, "learning_rate": 9.466774134689209e-06, "loss": 0.3598, "step": 196420 }, { "epoch": 1.1676207119971944, "grad_norm": 5.6528801918029785, "learning_rate": 9.466680893856023e-06, "loss": 0.4057, "step": 196430 }, { "epoch": 1.1676801540738628, "grad_norm": 5.576752185821533, "learning_rate": 9.466587645330678e-06, "loss": 0.3582, "step": 196440 }, { "epoch": 1.167739596150531, "grad_norm": 6.100302219390869, "learning_rate": 9.466494389113338e-06, "loss": 0.4077, "step": 196450 }, { "epoch": 1.1677990382271994, "grad_norm": 4.045449733734131, "learning_rate": 9.46640112520416e-06, "loss": 0.3984, "step": 196460 }, { "epoch": 1.1678584803038679, "grad_norm": 5.413858890533447, "learning_rate": 9.466307853603308e-06, "loss": 0.3929, "step": 196470 }, { "epoch": 1.1679179223805363, "grad_norm": 4.554259300231934, "learning_rate": 9.46621457431094e-06, "loss": 0.4119, "step": 196480 }, { "epoch": 1.1679773644572047, "grad_norm": 5.013943672180176, "learning_rate": 9.466121287327216e-06, "loss": 0.3742, "step": 196490 }, { "epoch": 1.168036806533873, "grad_norm": 5.081979751586914, "learning_rate": 9.466027992652301e-06, "loss": 0.3815, "step": 196500 }, { "epoch": 1.1680962486105415, "grad_norm": 3.7611584663391113, "learning_rate": 9.465934690286351e-06, "loss": 0.4209, "step": 196510 }, { "epoch": 1.16815569068721, "grad_norm": 4.493208885192871, "learning_rate": 9.46584138022953e-06, "loss": 0.4064, "step": 196520 }, { "epoch": 1.1682151327638781, "grad_norm": 3.904682159423828, "learning_rate": 9.465748062481998e-06, "loss": 0.3964, "step": 196530 }, { "epoch": 1.1682745748405465, "grad_norm": 4.030411243438721, "learning_rate": 9.465654737043912e-06, "loss": 0.3873, "step": 196540 }, { "epoch": 1.168334016917215, "grad_norm": 5.503063678741455, "learning_rate": 9.465561403915438e-06, "loss": 0.3921, "step": 196550 }, { "epoch": 1.1683934589938834, "grad_norm": 4.746406078338623, "learning_rate": 9.465468063096735e-06, "loss": 0.4449, "step": 196560 }, { "epoch": 1.1684529010705518, "grad_norm": 5.805588245391846, "learning_rate": 9.465374714587962e-06, "loss": 0.4303, "step": 196570 }, { "epoch": 1.1685123431472202, "grad_norm": 5.765008926391602, "learning_rate": 9.46528135838928e-06, "loss": 0.3838, "step": 196580 }, { "epoch": 1.1685717852238886, "grad_norm": 5.039243698120117, "learning_rate": 9.465187994500851e-06, "loss": 0.437, "step": 196590 }, { "epoch": 1.168631227300557, "grad_norm": 4.993810653686523, "learning_rate": 9.465094622922836e-06, "loss": 0.3832, "step": 196600 }, { "epoch": 1.1686906693772254, "grad_norm": 5.158937931060791, "learning_rate": 9.465001243655396e-06, "loss": 0.4138, "step": 196610 }, { "epoch": 1.1687501114538938, "grad_norm": 4.1748857498168945, "learning_rate": 9.464907856698692e-06, "loss": 0.4276, "step": 196620 }, { "epoch": 1.1688095535305623, "grad_norm": 4.629283428192139, "learning_rate": 9.464814462052883e-06, "loss": 0.4135, "step": 196630 }, { "epoch": 1.1688689956072305, "grad_norm": 5.4065375328063965, "learning_rate": 9.464721059718129e-06, "loss": 0.4396, "step": 196640 }, { "epoch": 1.1689284376838989, "grad_norm": 4.867790222167969, "learning_rate": 9.464627649694594e-06, "loss": 0.3623, "step": 196650 }, { "epoch": 1.1689878797605673, "grad_norm": 5.359926223754883, "learning_rate": 9.464534231982438e-06, "loss": 0.3738, "step": 196660 }, { "epoch": 1.1690473218372357, "grad_norm": 6.255230903625488, "learning_rate": 9.46444080658182e-06, "loss": 0.3781, "step": 196670 }, { "epoch": 1.1691067639139041, "grad_norm": 6.417033672332764, "learning_rate": 9.464347373492904e-06, "loss": 0.3572, "step": 196680 }, { "epoch": 1.1691662059905725, "grad_norm": 5.497292995452881, "learning_rate": 9.464253932715847e-06, "loss": 0.4386, "step": 196690 }, { "epoch": 1.169225648067241, "grad_norm": 5.692161560058594, "learning_rate": 9.464160484250813e-06, "loss": 0.397, "step": 196700 }, { "epoch": 1.1692850901439094, "grad_norm": 5.423797607421875, "learning_rate": 9.464067028097963e-06, "loss": 0.378, "step": 196710 }, { "epoch": 1.1693445322205775, "grad_norm": 6.038138389587402, "learning_rate": 9.463973564257456e-06, "loss": 0.3882, "step": 196720 }, { "epoch": 1.169403974297246, "grad_norm": 5.215680122375488, "learning_rate": 9.463880092729453e-06, "loss": 0.3934, "step": 196730 }, { "epoch": 1.1694634163739144, "grad_norm": 5.906015396118164, "learning_rate": 9.463786613514118e-06, "loss": 0.4063, "step": 196740 }, { "epoch": 1.1695228584505828, "grad_norm": 4.686592102050781, "learning_rate": 9.463693126611608e-06, "loss": 0.3705, "step": 196750 }, { "epoch": 1.1695823005272512, "grad_norm": 4.105775833129883, "learning_rate": 9.463599632022086e-06, "loss": 0.3665, "step": 196760 }, { "epoch": 1.1696417426039196, "grad_norm": 4.950223922729492, "learning_rate": 9.463506129745715e-06, "loss": 0.3781, "step": 196770 }, { "epoch": 1.169701184680588, "grad_norm": 5.366743087768555, "learning_rate": 9.463412619782652e-06, "loss": 0.4198, "step": 196780 }, { "epoch": 1.1697606267572564, "grad_norm": 4.3449602127075195, "learning_rate": 9.46331910213306e-06, "loss": 0.4218, "step": 196790 }, { "epoch": 1.1698200688339249, "grad_norm": 7.3416218757629395, "learning_rate": 9.463225576797099e-06, "loss": 0.3919, "step": 196800 }, { "epoch": 1.1698795109105933, "grad_norm": 6.4539594650268555, "learning_rate": 9.463132043774932e-06, "loss": 0.4311, "step": 196810 }, { "epoch": 1.1699389529872615, "grad_norm": 7.07673978805542, "learning_rate": 9.463038503066721e-06, "loss": 0.4221, "step": 196820 }, { "epoch": 1.1699983950639299, "grad_norm": 4.80485200881958, "learning_rate": 9.462944954672623e-06, "loss": 0.4076, "step": 196830 }, { "epoch": 1.1700578371405983, "grad_norm": 4.817022800445557, "learning_rate": 9.4628513985928e-06, "loss": 0.3822, "step": 196840 }, { "epoch": 1.1701172792172667, "grad_norm": 5.031533718109131, "learning_rate": 9.462757834827417e-06, "loss": 0.3616, "step": 196850 }, { "epoch": 1.1701767212939351, "grad_norm": 5.3740057945251465, "learning_rate": 9.462664263376631e-06, "loss": 0.3846, "step": 196860 }, { "epoch": 1.1702361633706035, "grad_norm": 5.761392593383789, "learning_rate": 9.462570684240605e-06, "loss": 0.4531, "step": 196870 }, { "epoch": 1.170295605447272, "grad_norm": 5.742705821990967, "learning_rate": 9.4624770974195e-06, "loss": 0.3841, "step": 196880 }, { "epoch": 1.1703550475239404, "grad_norm": 6.139212131500244, "learning_rate": 9.462383502913477e-06, "loss": 0.4241, "step": 196890 }, { "epoch": 1.1704144896006086, "grad_norm": 4.441955089569092, "learning_rate": 9.462289900722699e-06, "loss": 0.3984, "step": 196900 }, { "epoch": 1.170473931677277, "grad_norm": 4.187251091003418, "learning_rate": 9.462196290847322e-06, "loss": 0.406, "step": 196910 }, { "epoch": 1.1705333737539454, "grad_norm": 3.9223270416259766, "learning_rate": 9.462102673287514e-06, "loss": 0.3967, "step": 196920 }, { "epoch": 1.1705928158306138, "grad_norm": 5.600811958312988, "learning_rate": 9.46200904804343e-06, "loss": 0.4017, "step": 196930 }, { "epoch": 1.1706522579072822, "grad_norm": 4.679666996002197, "learning_rate": 9.461915415115234e-06, "loss": 0.4068, "step": 196940 }, { "epoch": 1.1707116999839506, "grad_norm": 4.7392988204956055, "learning_rate": 9.461821774503089e-06, "loss": 0.3758, "step": 196950 }, { "epoch": 1.170771142060619, "grad_norm": 5.044631481170654, "learning_rate": 9.461728126207153e-06, "loss": 0.4409, "step": 196960 }, { "epoch": 1.1708305841372875, "grad_norm": 4.263103485107422, "learning_rate": 9.46163447022759e-06, "loss": 0.3769, "step": 196970 }, { "epoch": 1.1708900262139559, "grad_norm": 5.020422458648682, "learning_rate": 9.46154080656456e-06, "loss": 0.4399, "step": 196980 }, { "epoch": 1.1709494682906243, "grad_norm": 4.063854217529297, "learning_rate": 9.461447135218225e-06, "loss": 0.4054, "step": 196990 }, { "epoch": 1.1710089103672927, "grad_norm": 5.0267109870910645, "learning_rate": 9.461353456188744e-06, "loss": 0.4024, "step": 197000 }, { "epoch": 1.171068352443961, "grad_norm": 6.724291801452637, "learning_rate": 9.461259769476281e-06, "loss": 0.4036, "step": 197010 }, { "epoch": 1.1711277945206293, "grad_norm": 4.05196475982666, "learning_rate": 9.461166075080996e-06, "loss": 0.4247, "step": 197020 }, { "epoch": 1.1711872365972977, "grad_norm": 5.810636520385742, "learning_rate": 9.46107237300305e-06, "loss": 0.421, "step": 197030 }, { "epoch": 1.1712466786739661, "grad_norm": 4.614626884460449, "learning_rate": 9.460978663242606e-06, "loss": 0.4156, "step": 197040 }, { "epoch": 1.1713061207506346, "grad_norm": 6.200112819671631, "learning_rate": 9.460884945799824e-06, "loss": 0.4042, "step": 197050 }, { "epoch": 1.171365562827303, "grad_norm": 4.833479881286621, "learning_rate": 9.460791220674868e-06, "loss": 0.4024, "step": 197060 }, { "epoch": 1.1714250049039714, "grad_norm": 6.35704231262207, "learning_rate": 9.460697487867895e-06, "loss": 0.39, "step": 197070 }, { "epoch": 1.1714844469806398, "grad_norm": 4.699102878570557, "learning_rate": 9.460603747379069e-06, "loss": 0.4198, "step": 197080 }, { "epoch": 1.171543889057308, "grad_norm": 5.526114463806152, "learning_rate": 9.460509999208552e-06, "loss": 0.3849, "step": 197090 }, { "epoch": 1.1716033311339764, "grad_norm": 5.66714334487915, "learning_rate": 9.460416243356503e-06, "loss": 0.3865, "step": 197100 }, { "epoch": 1.1716627732106448, "grad_norm": 5.230933666229248, "learning_rate": 9.460322479823085e-06, "loss": 0.3457, "step": 197110 }, { "epoch": 1.1717222152873132, "grad_norm": 4.861626148223877, "learning_rate": 9.460228708608461e-06, "loss": 0.3953, "step": 197120 }, { "epoch": 1.1717816573639817, "grad_norm": 4.221236228942871, "learning_rate": 9.460134929712791e-06, "loss": 0.434, "step": 197130 }, { "epoch": 1.17184109944065, "grad_norm": 4.501339912414551, "learning_rate": 9.460041143136237e-06, "loss": 0.3964, "step": 197140 }, { "epoch": 1.1719005415173185, "grad_norm": 5.583224773406982, "learning_rate": 9.459947348878957e-06, "loss": 0.426, "step": 197150 }, { "epoch": 1.171959983593987, "grad_norm": 5.282902717590332, "learning_rate": 9.459853546941118e-06, "loss": 0.3827, "step": 197160 }, { "epoch": 1.1720194256706553, "grad_norm": 6.104539394378662, "learning_rate": 9.459759737322878e-06, "loss": 0.442, "step": 197170 }, { "epoch": 1.1720788677473237, "grad_norm": 4.254986763000488, "learning_rate": 9.4596659200244e-06, "loss": 0.3885, "step": 197180 }, { "epoch": 1.172138309823992, "grad_norm": 4.919764995574951, "learning_rate": 9.459572095045847e-06, "loss": 0.3874, "step": 197190 }, { "epoch": 1.1721977519006603, "grad_norm": 4.704347610473633, "learning_rate": 9.459478262387374e-06, "loss": 0.4011, "step": 197200 }, { "epoch": 1.1722571939773287, "grad_norm": 5.573332786560059, "learning_rate": 9.45938442204915e-06, "loss": 0.4686, "step": 197210 }, { "epoch": 1.1723166360539972, "grad_norm": 4.0976362228393555, "learning_rate": 9.459290574031335e-06, "loss": 0.3703, "step": 197220 }, { "epoch": 1.1723760781306656, "grad_norm": 5.215718746185303, "learning_rate": 9.459196718334089e-06, "loss": 0.3982, "step": 197230 }, { "epoch": 1.172435520207334, "grad_norm": 4.787551403045654, "learning_rate": 9.459102854957573e-06, "loss": 0.4002, "step": 197240 }, { "epoch": 1.1724949622840024, "grad_norm": 4.431103706359863, "learning_rate": 9.45900898390195e-06, "loss": 0.4046, "step": 197250 }, { "epoch": 1.1725544043606708, "grad_norm": 5.0518670082092285, "learning_rate": 9.458915105167385e-06, "loss": 0.381, "step": 197260 }, { "epoch": 1.172613846437339, "grad_norm": 6.641024589538574, "learning_rate": 9.458821218754033e-06, "loss": 0.4116, "step": 197270 }, { "epoch": 1.1726732885140074, "grad_norm": 5.014892578125, "learning_rate": 9.458727324662059e-06, "loss": 0.3959, "step": 197280 }, { "epoch": 1.1727327305906758, "grad_norm": 6.475034236907959, "learning_rate": 9.458633422891626e-06, "loss": 0.4384, "step": 197290 }, { "epoch": 1.1727921726673443, "grad_norm": 5.377184867858887, "learning_rate": 9.458539513442893e-06, "loss": 0.357, "step": 197300 }, { "epoch": 1.1728516147440127, "grad_norm": 5.0792107582092285, "learning_rate": 9.458445596316022e-06, "loss": 0.4021, "step": 197310 }, { "epoch": 1.172911056820681, "grad_norm": 5.920752048492432, "learning_rate": 9.458351671511176e-06, "loss": 0.4016, "step": 197320 }, { "epoch": 1.1729704988973495, "grad_norm": 5.611278533935547, "learning_rate": 9.458257739028518e-06, "loss": 0.3873, "step": 197330 }, { "epoch": 1.173029940974018, "grad_norm": 4.732358932495117, "learning_rate": 9.458163798868207e-06, "loss": 0.4213, "step": 197340 }, { "epoch": 1.1730893830506863, "grad_norm": 4.6077351570129395, "learning_rate": 9.458069851030408e-06, "loss": 0.389, "step": 197350 }, { "epoch": 1.1731488251273547, "grad_norm": 6.179616451263428, "learning_rate": 9.457975895515278e-06, "loss": 0.4119, "step": 197360 }, { "epoch": 1.1732082672040232, "grad_norm": 5.549502372741699, "learning_rate": 9.457881932322983e-06, "loss": 0.4017, "step": 197370 }, { "epoch": 1.1732677092806914, "grad_norm": 5.121743202209473, "learning_rate": 9.457787961453682e-06, "loss": 0.3982, "step": 197380 }, { "epoch": 1.1733271513573598, "grad_norm": 5.478333950042725, "learning_rate": 9.45769398290754e-06, "loss": 0.4129, "step": 197390 }, { "epoch": 1.1733865934340282, "grad_norm": 4.9741082191467285, "learning_rate": 9.457599996684717e-06, "loss": 0.39, "step": 197400 }, { "epoch": 1.1734460355106966, "grad_norm": 4.561641216278076, "learning_rate": 9.457506002785375e-06, "loss": 0.387, "step": 197410 }, { "epoch": 1.173505477587365, "grad_norm": 4.806303977966309, "learning_rate": 9.457412001209673e-06, "loss": 0.4242, "step": 197420 }, { "epoch": 1.1735649196640334, "grad_norm": 4.184037685394287, "learning_rate": 9.457317991957779e-06, "loss": 0.3698, "step": 197430 }, { "epoch": 1.1736243617407018, "grad_norm": 4.913201808929443, "learning_rate": 9.45722397502985e-06, "loss": 0.386, "step": 197440 }, { "epoch": 1.1736838038173703, "grad_norm": 4.697737216949463, "learning_rate": 9.45712995042605e-06, "loss": 0.4237, "step": 197450 }, { "epoch": 1.1737432458940384, "grad_norm": 5.329914093017578, "learning_rate": 9.45703591814654e-06, "loss": 0.4187, "step": 197460 }, { "epoch": 1.1738026879707069, "grad_norm": 5.591716766357422, "learning_rate": 9.456941878191484e-06, "loss": 0.3532, "step": 197470 }, { "epoch": 1.1738621300473753, "grad_norm": 4.602294445037842, "learning_rate": 9.45684783056104e-06, "loss": 0.3717, "step": 197480 }, { "epoch": 1.1739215721240437, "grad_norm": 5.118812084197998, "learning_rate": 9.456753775255374e-06, "loss": 0.4263, "step": 197490 }, { "epoch": 1.173981014200712, "grad_norm": 5.145125389099121, "learning_rate": 9.456659712274645e-06, "loss": 0.4126, "step": 197500 }, { "epoch": 1.1740404562773805, "grad_norm": 4.727192401885986, "learning_rate": 9.456565641619017e-06, "loss": 0.3626, "step": 197510 }, { "epoch": 1.174099898354049, "grad_norm": 4.562948703765869, "learning_rate": 9.456471563288652e-06, "loss": 0.3664, "step": 197520 }, { "epoch": 1.1741593404307173, "grad_norm": 5.431646823883057, "learning_rate": 9.45637747728371e-06, "loss": 0.3958, "step": 197530 }, { "epoch": 1.1742187825073858, "grad_norm": 4.8382039070129395, "learning_rate": 9.456283383604354e-06, "loss": 0.3604, "step": 197540 }, { "epoch": 1.1742782245840542, "grad_norm": 5.812928676605225, "learning_rate": 9.456189282250747e-06, "loss": 0.4188, "step": 197550 }, { "epoch": 1.1743376666607224, "grad_norm": 6.024089813232422, "learning_rate": 9.45609517322305e-06, "loss": 0.395, "step": 197560 }, { "epoch": 1.1743971087373908, "grad_norm": 9.830059051513672, "learning_rate": 9.456001056521426e-06, "loss": 0.417, "step": 197570 }, { "epoch": 1.1744565508140592, "grad_norm": 3.7328107357025146, "learning_rate": 9.455906932146035e-06, "loss": 0.4125, "step": 197580 }, { "epoch": 1.1745159928907276, "grad_norm": 4.181743621826172, "learning_rate": 9.455812800097042e-06, "loss": 0.3699, "step": 197590 }, { "epoch": 1.174575434967396, "grad_norm": 4.734286785125732, "learning_rate": 9.455718660374608e-06, "loss": 0.4028, "step": 197600 }, { "epoch": 1.1746348770440644, "grad_norm": 6.582047939300537, "learning_rate": 9.455624512978895e-06, "loss": 0.4181, "step": 197610 }, { "epoch": 1.1746943191207329, "grad_norm": 5.069691181182861, "learning_rate": 9.455530357910063e-06, "loss": 0.3895, "step": 197620 }, { "epoch": 1.1747537611974013, "grad_norm": 4.523963451385498, "learning_rate": 9.455436195168278e-06, "loss": 0.4059, "step": 197630 }, { "epoch": 1.1748132032740695, "grad_norm": 5.185969352722168, "learning_rate": 9.455342024753698e-06, "loss": 0.3673, "step": 197640 }, { "epoch": 1.1748726453507379, "grad_norm": 4.60333776473999, "learning_rate": 9.45524784666649e-06, "loss": 0.4323, "step": 197650 }, { "epoch": 1.1749320874274063, "grad_norm": 6.30001163482666, "learning_rate": 9.455153660906812e-06, "loss": 0.4293, "step": 197660 }, { "epoch": 1.1749915295040747, "grad_norm": 4.698116779327393, "learning_rate": 9.455059467474827e-06, "loss": 0.4081, "step": 197670 }, { "epoch": 1.1750509715807431, "grad_norm": 4.32380485534668, "learning_rate": 9.4549652663707e-06, "loss": 0.4043, "step": 197680 }, { "epoch": 1.1751104136574115, "grad_norm": 6.804919719696045, "learning_rate": 9.45487105759459e-06, "loss": 0.4151, "step": 197690 }, { "epoch": 1.17516985573408, "grad_norm": 5.46583890914917, "learning_rate": 9.454776841146662e-06, "loss": 0.3953, "step": 197700 }, { "epoch": 1.1752292978107484, "grad_norm": 6.059215068817139, "learning_rate": 9.454682617027075e-06, "loss": 0.4247, "step": 197710 }, { "epoch": 1.1752887398874168, "grad_norm": 4.025675296783447, "learning_rate": 9.454588385235995e-06, "loss": 0.359, "step": 197720 }, { "epoch": 1.1753481819640852, "grad_norm": 5.486734867095947, "learning_rate": 9.45449414577358e-06, "loss": 0.4133, "step": 197730 }, { "epoch": 1.1754076240407536, "grad_norm": 4.934789657592773, "learning_rate": 9.454399898639996e-06, "loss": 0.4057, "step": 197740 }, { "epoch": 1.1754670661174218, "grad_norm": 5.67762565612793, "learning_rate": 9.454305643835404e-06, "loss": 0.385, "step": 197750 }, { "epoch": 1.1755265081940902, "grad_norm": 5.531607627868652, "learning_rate": 9.454211381359966e-06, "loss": 0.3713, "step": 197760 }, { "epoch": 1.1755859502707586, "grad_norm": 4.374423027038574, "learning_rate": 9.454117111213843e-06, "loss": 0.3715, "step": 197770 }, { "epoch": 1.175645392347427, "grad_norm": 4.8871049880981445, "learning_rate": 9.4540228333972e-06, "loss": 0.3716, "step": 197780 }, { "epoch": 1.1757048344240955, "grad_norm": 4.2381463050842285, "learning_rate": 9.4539285479102e-06, "loss": 0.3924, "step": 197790 }, { "epoch": 1.1757642765007639, "grad_norm": 4.969043254852295, "learning_rate": 9.453834254753001e-06, "loss": 0.4123, "step": 197800 }, { "epoch": 1.1758237185774323, "grad_norm": 4.57363224029541, "learning_rate": 9.45373995392577e-06, "loss": 0.4305, "step": 197810 }, { "epoch": 1.1758831606541007, "grad_norm": 6.489940166473389, "learning_rate": 9.453645645428665e-06, "loss": 0.4633, "step": 197820 }, { "epoch": 1.175942602730769, "grad_norm": 3.612396240234375, "learning_rate": 9.453551329261854e-06, "loss": 0.3642, "step": 197830 }, { "epoch": 1.1760020448074373, "grad_norm": 4.483058452606201, "learning_rate": 9.453457005425494e-06, "loss": 0.3842, "step": 197840 }, { "epoch": 1.1760614868841057, "grad_norm": 6.961716651916504, "learning_rate": 9.453362673919751e-06, "loss": 0.413, "step": 197850 }, { "epoch": 1.1761209289607741, "grad_norm": 4.960860252380371, "learning_rate": 9.453268334744784e-06, "loss": 0.4247, "step": 197860 }, { "epoch": 1.1761803710374426, "grad_norm": 3.946373224258423, "learning_rate": 9.45317398790076e-06, "loss": 0.4028, "step": 197870 }, { "epoch": 1.176239813114111, "grad_norm": 4.752208232879639, "learning_rate": 9.453079633387836e-06, "loss": 0.3627, "step": 197880 }, { "epoch": 1.1762992551907794, "grad_norm": 4.566895961761475, "learning_rate": 9.45298527120618e-06, "loss": 0.3887, "step": 197890 }, { "epoch": 1.1763586972674478, "grad_norm": 5.850378036499023, "learning_rate": 9.452890901355952e-06, "loss": 0.4103, "step": 197900 }, { "epoch": 1.1764181393441162, "grad_norm": 4.2749481201171875, "learning_rate": 9.452796523837314e-06, "loss": 0.41, "step": 197910 }, { "epoch": 1.1764775814207846, "grad_norm": 4.989584445953369, "learning_rate": 9.452702138650429e-06, "loss": 0.4021, "step": 197920 }, { "epoch": 1.1765370234974528, "grad_norm": 5.415186405181885, "learning_rate": 9.452607745795458e-06, "loss": 0.3975, "step": 197930 }, { "epoch": 1.1765964655741212, "grad_norm": 6.736348628997803, "learning_rate": 9.452513345272568e-06, "loss": 0.3914, "step": 197940 }, { "epoch": 1.1766559076507896, "grad_norm": 5.776017189025879, "learning_rate": 9.452418937081918e-06, "loss": 0.4218, "step": 197950 }, { "epoch": 1.176715349727458, "grad_norm": 6.6880106925964355, "learning_rate": 9.45232452122367e-06, "loss": 0.3832, "step": 197960 }, { "epoch": 1.1767747918041265, "grad_norm": 4.327997207641602, "learning_rate": 9.45223009769799e-06, "loss": 0.3943, "step": 197970 }, { "epoch": 1.1768342338807949, "grad_norm": 4.946475505828857, "learning_rate": 9.452135666505037e-06, "loss": 0.4038, "step": 197980 }, { "epoch": 1.1768936759574633, "grad_norm": 4.799163341522217, "learning_rate": 9.452041227644976e-06, "loss": 0.3727, "step": 197990 }, { "epoch": 1.1769531180341317, "grad_norm": 5.290200710296631, "learning_rate": 9.451946781117967e-06, "loss": 0.4263, "step": 198000 }, { "epoch": 1.1770125601108, "grad_norm": 6.485302448272705, "learning_rate": 9.451852326924177e-06, "loss": 0.3995, "step": 198010 }, { "epoch": 1.1770720021874683, "grad_norm": 6.726682662963867, "learning_rate": 9.451757865063764e-06, "loss": 0.3962, "step": 198020 }, { "epoch": 1.1771314442641367, "grad_norm": 4.780923843383789, "learning_rate": 9.451663395536893e-06, "loss": 0.3803, "step": 198030 }, { "epoch": 1.1771908863408052, "grad_norm": 6.624138832092285, "learning_rate": 9.451568918343728e-06, "loss": 0.4361, "step": 198040 }, { "epoch": 1.1772503284174736, "grad_norm": 5.164810657501221, "learning_rate": 9.45147443348443e-06, "loss": 0.4438, "step": 198050 }, { "epoch": 1.177309770494142, "grad_norm": 3.9770913124084473, "learning_rate": 9.451379940959162e-06, "loss": 0.3873, "step": 198060 }, { "epoch": 1.1773692125708104, "grad_norm": 4.756283283233643, "learning_rate": 9.451285440768086e-06, "loss": 0.3642, "step": 198070 }, { "epoch": 1.1774286546474788, "grad_norm": 6.297393321990967, "learning_rate": 9.451190932911364e-06, "loss": 0.3969, "step": 198080 }, { "epoch": 1.1774880967241472, "grad_norm": 3.953394889831543, "learning_rate": 9.451096417389162e-06, "loss": 0.365, "step": 198090 }, { "epoch": 1.1775475388008156, "grad_norm": 4.431504726409912, "learning_rate": 9.45100189420164e-06, "loss": 0.4016, "step": 198100 }, { "epoch": 1.177606980877484, "grad_norm": 4.824119567871094, "learning_rate": 9.450907363348962e-06, "loss": 0.4142, "step": 198110 }, { "epoch": 1.1776664229541522, "grad_norm": 4.735435962677002, "learning_rate": 9.450812824831291e-06, "loss": 0.3825, "step": 198120 }, { "epoch": 1.1777258650308207, "grad_norm": 5.233534812927246, "learning_rate": 9.450718278648788e-06, "loss": 0.3868, "step": 198130 }, { "epoch": 1.177785307107489, "grad_norm": 4.890094757080078, "learning_rate": 9.450623724801617e-06, "loss": 0.4589, "step": 198140 }, { "epoch": 1.1778447491841575, "grad_norm": 4.894556522369385, "learning_rate": 9.45052916328994e-06, "loss": 0.4019, "step": 198150 }, { "epoch": 1.177904191260826, "grad_norm": 5.334609508514404, "learning_rate": 9.450434594113923e-06, "loss": 0.4076, "step": 198160 }, { "epoch": 1.1779636333374943, "grad_norm": 5.573944568634033, "learning_rate": 9.450340017273727e-06, "loss": 0.3986, "step": 198170 }, { "epoch": 1.1780230754141627, "grad_norm": 6.391816139221191, "learning_rate": 9.450245432769514e-06, "loss": 0.4539, "step": 198180 }, { "epoch": 1.1780825174908311, "grad_norm": 4.792212009429932, "learning_rate": 9.450150840601446e-06, "loss": 0.3627, "step": 198190 }, { "epoch": 1.1781419595674993, "grad_norm": 6.640141487121582, "learning_rate": 9.450056240769687e-06, "loss": 0.4355, "step": 198200 }, { "epoch": 1.1782014016441678, "grad_norm": 7.0166120529174805, "learning_rate": 9.449961633274402e-06, "loss": 0.4445, "step": 198210 }, { "epoch": 1.1782608437208362, "grad_norm": 4.94222354888916, "learning_rate": 9.44986701811575e-06, "loss": 0.3796, "step": 198220 }, { "epoch": 1.1783202857975046, "grad_norm": 5.263849258422852, "learning_rate": 9.449772395293899e-06, "loss": 0.3578, "step": 198230 }, { "epoch": 1.178379727874173, "grad_norm": 4.916452407836914, "learning_rate": 9.449677764809007e-06, "loss": 0.3765, "step": 198240 }, { "epoch": 1.1784391699508414, "grad_norm": 3.878145456314087, "learning_rate": 9.44958312666124e-06, "loss": 0.4084, "step": 198250 }, { "epoch": 1.1784986120275098, "grad_norm": 5.646025657653809, "learning_rate": 9.449488480850759e-06, "loss": 0.3775, "step": 198260 }, { "epoch": 1.1785580541041782, "grad_norm": 7.673285007476807, "learning_rate": 9.449393827377728e-06, "loss": 0.469, "step": 198270 }, { "epoch": 1.1786174961808467, "grad_norm": 5.2478227615356445, "learning_rate": 9.44929916624231e-06, "loss": 0.3942, "step": 198280 }, { "epoch": 1.178676938257515, "grad_norm": 4.541884422302246, "learning_rate": 9.44920449744467e-06, "loss": 0.4025, "step": 198290 }, { "epoch": 1.1787363803341833, "grad_norm": 5.059298992156982, "learning_rate": 9.449109820984965e-06, "loss": 0.3686, "step": 198300 }, { "epoch": 1.1787958224108517, "grad_norm": 5.063520908355713, "learning_rate": 9.449015136863365e-06, "loss": 0.4057, "step": 198310 }, { "epoch": 1.17885526448752, "grad_norm": 5.113884925842285, "learning_rate": 9.448920445080028e-06, "loss": 0.412, "step": 198320 }, { "epoch": 1.1789147065641885, "grad_norm": 5.709935665130615, "learning_rate": 9.44882574563512e-06, "loss": 0.4373, "step": 198330 }, { "epoch": 1.178974148640857, "grad_norm": 4.449862003326416, "learning_rate": 9.448731038528804e-06, "loss": 0.3785, "step": 198340 }, { "epoch": 1.1790335907175253, "grad_norm": 5.552320957183838, "learning_rate": 9.448636323761242e-06, "loss": 0.4223, "step": 198350 }, { "epoch": 1.1790930327941938, "grad_norm": 5.241524696350098, "learning_rate": 9.448541601332598e-06, "loss": 0.4266, "step": 198360 }, { "epoch": 1.1791524748708622, "grad_norm": 5.294169902801514, "learning_rate": 9.448446871243033e-06, "loss": 0.4252, "step": 198370 }, { "epoch": 1.1792119169475304, "grad_norm": 5.204838752746582, "learning_rate": 9.448352133492714e-06, "loss": 0.4074, "step": 198380 }, { "epoch": 1.1792713590241988, "grad_norm": 5.756213665008545, "learning_rate": 9.448257388081799e-06, "loss": 0.4349, "step": 198390 }, { "epoch": 1.1793308011008672, "grad_norm": 4.788944244384766, "learning_rate": 9.448162635010456e-06, "loss": 0.4075, "step": 198400 }, { "epoch": 1.1793902431775356, "grad_norm": 6.337084770202637, "learning_rate": 9.448067874278846e-06, "loss": 0.4027, "step": 198410 }, { "epoch": 1.179449685254204, "grad_norm": 5.513172149658203, "learning_rate": 9.44797310588713e-06, "loss": 0.3967, "step": 198420 }, { "epoch": 1.1795091273308724, "grad_norm": 6.119421005249023, "learning_rate": 9.447878329835476e-06, "loss": 0.3658, "step": 198430 }, { "epoch": 1.1795685694075408, "grad_norm": 6.00921106338501, "learning_rate": 9.447783546124045e-06, "loss": 0.4223, "step": 198440 }, { "epoch": 1.1796280114842093, "grad_norm": 5.998872756958008, "learning_rate": 9.447688754752999e-06, "loss": 0.3913, "step": 198450 }, { "epoch": 1.1796874535608777, "grad_norm": 5.131414890289307, "learning_rate": 9.447593955722504e-06, "loss": 0.3846, "step": 198460 }, { "epoch": 1.179746895637546, "grad_norm": 5.815920352935791, "learning_rate": 9.447499149032719e-06, "loss": 0.3903, "step": 198470 }, { "epoch": 1.1798063377142145, "grad_norm": 5.174139499664307, "learning_rate": 9.447404334683812e-06, "loss": 0.4008, "step": 198480 }, { "epoch": 1.1798657797908827, "grad_norm": 5.829983711242676, "learning_rate": 9.447309512675944e-06, "loss": 0.4474, "step": 198490 }, { "epoch": 1.179925221867551, "grad_norm": 5.153415203094482, "learning_rate": 9.447214683009278e-06, "loss": 0.3982, "step": 198500 }, { "epoch": 1.1799846639442195, "grad_norm": 6.066790580749512, "learning_rate": 9.447119845683976e-06, "loss": 0.394, "step": 198510 }, { "epoch": 1.180044106020888, "grad_norm": 5.3205647468566895, "learning_rate": 9.447025000700204e-06, "loss": 0.3851, "step": 198520 }, { "epoch": 1.1801035480975564, "grad_norm": 6.278794288635254, "learning_rate": 9.446930148058125e-06, "loss": 0.4589, "step": 198530 }, { "epoch": 1.1801629901742248, "grad_norm": 4.675424098968506, "learning_rate": 9.446835287757902e-06, "loss": 0.422, "step": 198540 }, { "epoch": 1.1802224322508932, "grad_norm": 4.327776908874512, "learning_rate": 9.446740419799696e-06, "loss": 0.386, "step": 198550 }, { "epoch": 1.1802818743275616, "grad_norm": 6.725909233093262, "learning_rate": 9.446645544183674e-06, "loss": 0.3831, "step": 198560 }, { "epoch": 1.1803413164042298, "grad_norm": 5.671751022338867, "learning_rate": 9.446550660909998e-06, "loss": 0.4185, "step": 198570 }, { "epoch": 1.1804007584808982, "grad_norm": 6.911351203918457, "learning_rate": 9.446455769978831e-06, "loss": 0.4188, "step": 198580 }, { "epoch": 1.1804602005575666, "grad_norm": 4.950423240661621, "learning_rate": 9.446360871390337e-06, "loss": 0.381, "step": 198590 }, { "epoch": 1.180519642634235, "grad_norm": 6.435720443725586, "learning_rate": 9.446265965144677e-06, "loss": 0.4244, "step": 198600 }, { "epoch": 1.1805790847109034, "grad_norm": 7.094619274139404, "learning_rate": 9.446171051242019e-06, "loss": 0.4341, "step": 198610 }, { "epoch": 1.1806385267875719, "grad_norm": 5.71324348449707, "learning_rate": 9.446076129682522e-06, "loss": 0.4007, "step": 198620 }, { "epoch": 1.1806979688642403, "grad_norm": 4.439262866973877, "learning_rate": 9.445981200466351e-06, "loss": 0.3888, "step": 198630 }, { "epoch": 1.1807574109409087, "grad_norm": 3.775745391845703, "learning_rate": 9.445886263593674e-06, "loss": 0.4191, "step": 198640 }, { "epoch": 1.180816853017577, "grad_norm": 4.312479496002197, "learning_rate": 9.445791319064647e-06, "loss": 0.37, "step": 198650 }, { "epoch": 1.1808762950942455, "grad_norm": 6.960539817810059, "learning_rate": 9.445696366879437e-06, "loss": 0.4395, "step": 198660 }, { "epoch": 1.1809357371709137, "grad_norm": 6.050571918487549, "learning_rate": 9.445601407038207e-06, "loss": 0.3911, "step": 198670 }, { "epoch": 1.1809951792475821, "grad_norm": 6.284171104431152, "learning_rate": 9.445506439541122e-06, "loss": 0.4072, "step": 198680 }, { "epoch": 1.1810546213242505, "grad_norm": 5.280661582946777, "learning_rate": 9.445411464388344e-06, "loss": 0.3953, "step": 198690 }, { "epoch": 1.181114063400919, "grad_norm": 6.411454200744629, "learning_rate": 9.445316481580038e-06, "loss": 0.4458, "step": 198700 }, { "epoch": 1.1811735054775874, "grad_norm": 5.8938374519348145, "learning_rate": 9.445221491116365e-06, "loss": 0.3903, "step": 198710 }, { "epoch": 1.1812329475542558, "grad_norm": 4.831735610961914, "learning_rate": 9.445126492997492e-06, "loss": 0.3973, "step": 198720 }, { "epoch": 1.1812923896309242, "grad_norm": 7.372858047485352, "learning_rate": 9.44503148722358e-06, "loss": 0.4285, "step": 198730 }, { "epoch": 1.1813518317075926, "grad_norm": 4.916810512542725, "learning_rate": 9.444936473794793e-06, "loss": 0.4104, "step": 198740 }, { "epoch": 1.1814112737842608, "grad_norm": 5.456665992736816, "learning_rate": 9.444841452711296e-06, "loss": 0.3824, "step": 198750 }, { "epoch": 1.1814707158609292, "grad_norm": 5.507028579711914, "learning_rate": 9.44474642397325e-06, "loss": 0.4373, "step": 198760 }, { "epoch": 1.1815301579375976, "grad_norm": 8.270813941955566, "learning_rate": 9.444651387580822e-06, "loss": 0.4081, "step": 198770 }, { "epoch": 1.181589600014266, "grad_norm": 3.5762648582458496, "learning_rate": 9.444556343534172e-06, "loss": 0.3947, "step": 198780 }, { "epoch": 1.1816490420909345, "grad_norm": 7.484197616577148, "learning_rate": 9.444461291833468e-06, "loss": 0.4281, "step": 198790 }, { "epoch": 1.1817084841676029, "grad_norm": 4.428379535675049, "learning_rate": 9.44436623247887e-06, "loss": 0.399, "step": 198800 }, { "epoch": 1.1817679262442713, "grad_norm": 4.8910346031188965, "learning_rate": 9.444271165470544e-06, "loss": 0.3981, "step": 198810 }, { "epoch": 1.1818273683209397, "grad_norm": 5.328052043914795, "learning_rate": 9.444176090808652e-06, "loss": 0.4112, "step": 198820 }, { "epoch": 1.1818868103976081, "grad_norm": 4.9624199867248535, "learning_rate": 9.444081008493358e-06, "loss": 0.3715, "step": 198830 }, { "epoch": 1.1819462524742765, "grad_norm": 4.918741226196289, "learning_rate": 9.443985918524827e-06, "loss": 0.4145, "step": 198840 }, { "epoch": 1.182005694550945, "grad_norm": 4.3053107261657715, "learning_rate": 9.443890820903221e-06, "loss": 0.3994, "step": 198850 }, { "epoch": 1.1820651366276131, "grad_norm": 4.725227355957031, "learning_rate": 9.443795715628707e-06, "loss": 0.3753, "step": 198860 }, { "epoch": 1.1821245787042816, "grad_norm": 4.36019229888916, "learning_rate": 9.443700602701444e-06, "loss": 0.3534, "step": 198870 }, { "epoch": 1.18218402078095, "grad_norm": 5.760865688323975, "learning_rate": 9.4436054821216e-06, "loss": 0.4158, "step": 198880 }, { "epoch": 1.1822434628576184, "grad_norm": 6.107649326324463, "learning_rate": 9.443510353889336e-06, "loss": 0.3816, "step": 198890 }, { "epoch": 1.1823029049342868, "grad_norm": 6.080932140350342, "learning_rate": 9.44341521800482e-06, "loss": 0.3921, "step": 198900 }, { "epoch": 1.1823623470109552, "grad_norm": 5.598757266998291, "learning_rate": 9.443320074468209e-06, "loss": 0.427, "step": 198910 }, { "epoch": 1.1824217890876236, "grad_norm": 7.106720447540283, "learning_rate": 9.443224923279672e-06, "loss": 0.4151, "step": 198920 }, { "epoch": 1.182481231164292, "grad_norm": 5.541663646697998, "learning_rate": 9.443129764439371e-06, "loss": 0.3862, "step": 198930 }, { "epoch": 1.1825406732409602, "grad_norm": 4.643085479736328, "learning_rate": 9.443034597947472e-06, "loss": 0.3948, "step": 198940 }, { "epoch": 1.1826001153176287, "grad_norm": 4.970611572265625, "learning_rate": 9.442939423804137e-06, "loss": 0.4161, "step": 198950 }, { "epoch": 1.182659557394297, "grad_norm": 6.442958831787109, "learning_rate": 9.44284424200953e-06, "loss": 0.4106, "step": 198960 }, { "epoch": 1.1827189994709655, "grad_norm": 7.549197196960449, "learning_rate": 9.442749052563813e-06, "loss": 0.4177, "step": 198970 }, { "epoch": 1.182778441547634, "grad_norm": 5.454111099243164, "learning_rate": 9.442653855467154e-06, "loss": 0.3834, "step": 198980 }, { "epoch": 1.1828378836243023, "grad_norm": 6.414048194885254, "learning_rate": 9.442558650719716e-06, "loss": 0.4113, "step": 198990 }, { "epoch": 1.1828973257009707, "grad_norm": 3.5235021114349365, "learning_rate": 9.44246343832166e-06, "loss": 0.3739, "step": 199000 }, { "epoch": 1.1829567677776391, "grad_norm": 6.714576244354248, "learning_rate": 9.442368218273152e-06, "loss": 0.3729, "step": 199010 }, { "epoch": 1.1830162098543076, "grad_norm": 3.5538604259490967, "learning_rate": 9.442272990574357e-06, "loss": 0.3678, "step": 199020 }, { "epoch": 1.183075651930976, "grad_norm": 4.6348090171813965, "learning_rate": 9.442177755225436e-06, "loss": 0.3614, "step": 199030 }, { "epoch": 1.1831350940076442, "grad_norm": 3.976423978805542, "learning_rate": 9.442082512226557e-06, "loss": 0.3812, "step": 199040 }, { "epoch": 1.1831945360843126, "grad_norm": 5.324184417724609, "learning_rate": 9.44198726157788e-06, "loss": 0.393, "step": 199050 }, { "epoch": 1.183253978160981, "grad_norm": 4.603302478790283, "learning_rate": 9.441892003279574e-06, "loss": 0.3989, "step": 199060 }, { "epoch": 1.1833134202376494, "grad_norm": 4.861972332000732, "learning_rate": 9.441796737331797e-06, "loss": 0.3937, "step": 199070 }, { "epoch": 1.1833728623143178, "grad_norm": 5.437632083892822, "learning_rate": 9.441701463734717e-06, "loss": 0.377, "step": 199080 }, { "epoch": 1.1834323043909862, "grad_norm": 6.155579566955566, "learning_rate": 9.441606182488496e-06, "loss": 0.4259, "step": 199090 }, { "epoch": 1.1834917464676546, "grad_norm": 5.731876850128174, "learning_rate": 9.441510893593301e-06, "loss": 0.4012, "step": 199100 }, { "epoch": 1.183551188544323, "grad_norm": 6.43637752532959, "learning_rate": 9.441415597049294e-06, "loss": 0.4011, "step": 199110 }, { "epoch": 1.1836106306209913, "grad_norm": 6.64249324798584, "learning_rate": 9.441320292856638e-06, "loss": 0.4283, "step": 199120 }, { "epoch": 1.1836700726976597, "grad_norm": 4.947811126708984, "learning_rate": 9.4412249810155e-06, "loss": 0.403, "step": 199130 }, { "epoch": 1.183729514774328, "grad_norm": 6.054828643798828, "learning_rate": 9.441129661526043e-06, "loss": 0.4257, "step": 199140 }, { "epoch": 1.1837889568509965, "grad_norm": 5.347382545471191, "learning_rate": 9.441034334388429e-06, "loss": 0.3989, "step": 199150 }, { "epoch": 1.183848398927665, "grad_norm": 4.799441337585449, "learning_rate": 9.440938999602824e-06, "loss": 0.3656, "step": 199160 }, { "epoch": 1.1839078410043333, "grad_norm": 6.036642074584961, "learning_rate": 9.440843657169394e-06, "loss": 0.3795, "step": 199170 }, { "epoch": 1.1839672830810017, "grad_norm": 3.8133254051208496, "learning_rate": 9.4407483070883e-06, "loss": 0.4131, "step": 199180 }, { "epoch": 1.1840267251576702, "grad_norm": 6.196313381195068, "learning_rate": 9.440652949359707e-06, "loss": 0.4073, "step": 199190 }, { "epoch": 1.1840861672343386, "grad_norm": 5.817307949066162, "learning_rate": 9.440557583983782e-06, "loss": 0.3681, "step": 199200 }, { "epoch": 1.184145609311007, "grad_norm": 5.323429584503174, "learning_rate": 9.440462210960686e-06, "loss": 0.4336, "step": 199210 }, { "epoch": 1.1842050513876754, "grad_norm": 5.361630916595459, "learning_rate": 9.440366830290584e-06, "loss": 0.3829, "step": 199220 }, { "epoch": 1.1842644934643436, "grad_norm": 5.649398326873779, "learning_rate": 9.44027144197364e-06, "loss": 0.3831, "step": 199230 }, { "epoch": 1.184323935541012, "grad_norm": 4.11624002456665, "learning_rate": 9.440176046010019e-06, "loss": 0.3505, "step": 199240 }, { "epoch": 1.1843833776176804, "grad_norm": 6.599151134490967, "learning_rate": 9.440080642399885e-06, "loss": 0.4314, "step": 199250 }, { "epoch": 1.1844428196943488, "grad_norm": 5.968958377838135, "learning_rate": 9.439985231143404e-06, "loss": 0.4107, "step": 199260 }, { "epoch": 1.1845022617710173, "grad_norm": 5.183750629425049, "learning_rate": 9.439889812240736e-06, "loss": 0.4135, "step": 199270 }, { "epoch": 1.1845617038476857, "grad_norm": 4.505592346191406, "learning_rate": 9.43979438569205e-06, "loss": 0.4386, "step": 199280 }, { "epoch": 1.184621145924354, "grad_norm": 4.584534645080566, "learning_rate": 9.439698951497509e-06, "loss": 0.41, "step": 199290 }, { "epoch": 1.1846805880010225, "grad_norm": 5.622010231018066, "learning_rate": 9.439603509657273e-06, "loss": 0.4017, "step": 199300 }, { "epoch": 1.1847400300776907, "grad_norm": 6.0474467277526855, "learning_rate": 9.439508060171513e-06, "loss": 0.3775, "step": 199310 }, { "epoch": 1.184799472154359, "grad_norm": 4.316591262817383, "learning_rate": 9.43941260304039e-06, "loss": 0.3919, "step": 199320 }, { "epoch": 1.1848589142310275, "grad_norm": 6.669929504394531, "learning_rate": 9.439317138264067e-06, "loss": 0.3977, "step": 199330 }, { "epoch": 1.184918356307696, "grad_norm": 4.314704895019531, "learning_rate": 9.439221665842713e-06, "loss": 0.3677, "step": 199340 }, { "epoch": 1.1849777983843643, "grad_norm": 5.664742946624756, "learning_rate": 9.439126185776487e-06, "loss": 0.4139, "step": 199350 }, { "epoch": 1.1850372404610328, "grad_norm": 5.882846355438232, "learning_rate": 9.439030698065559e-06, "loss": 0.3803, "step": 199360 }, { "epoch": 1.1850966825377012, "grad_norm": 4.870591163635254, "learning_rate": 9.43893520271009e-06, "loss": 0.429, "step": 199370 }, { "epoch": 1.1851561246143696, "grad_norm": 5.727903842926025, "learning_rate": 9.438839699710243e-06, "loss": 0.3747, "step": 199380 }, { "epoch": 1.185215566691038, "grad_norm": 5.430005073547363, "learning_rate": 9.438744189066184e-06, "loss": 0.3744, "step": 199390 }, { "epoch": 1.1852750087677064, "grad_norm": 4.226281642913818, "learning_rate": 9.43864867077808e-06, "loss": 0.3854, "step": 199400 }, { "epoch": 1.1853344508443746, "grad_norm": 3.984494209289551, "learning_rate": 9.438553144846093e-06, "loss": 0.3937, "step": 199410 }, { "epoch": 1.185393892921043, "grad_norm": 6.538318157196045, "learning_rate": 9.438457611270386e-06, "loss": 0.4161, "step": 199420 }, { "epoch": 1.1854533349977114, "grad_norm": 4.170321941375732, "learning_rate": 9.438362070051128e-06, "loss": 0.4133, "step": 199430 }, { "epoch": 1.1855127770743799, "grad_norm": 4.036825656890869, "learning_rate": 9.438266521188479e-06, "loss": 0.4148, "step": 199440 }, { "epoch": 1.1855722191510483, "grad_norm": 4.723703861236572, "learning_rate": 9.438170964682607e-06, "loss": 0.3754, "step": 199450 }, { "epoch": 1.1856316612277167, "grad_norm": 5.946317672729492, "learning_rate": 9.438075400533673e-06, "loss": 0.3858, "step": 199460 }, { "epoch": 1.185691103304385, "grad_norm": 6.014099597930908, "learning_rate": 9.437979828741846e-06, "loss": 0.4052, "step": 199470 }, { "epoch": 1.1857505453810535, "grad_norm": 6.376224040985107, "learning_rate": 9.437884249307286e-06, "loss": 0.3903, "step": 199480 }, { "epoch": 1.1858099874577217, "grad_norm": 4.943675994873047, "learning_rate": 9.43778866223016e-06, "loss": 0.3795, "step": 199490 }, { "epoch": 1.1858694295343901, "grad_norm": 4.9231486320495605, "learning_rate": 9.437693067510635e-06, "loss": 0.4006, "step": 199500 }, { "epoch": 1.1859288716110585, "grad_norm": 4.7984938621521, "learning_rate": 9.43759746514887e-06, "loss": 0.3715, "step": 199510 }, { "epoch": 1.185988313687727, "grad_norm": 5.873351097106934, "learning_rate": 9.437501855145034e-06, "loss": 0.3987, "step": 199520 }, { "epoch": 1.1860477557643954, "grad_norm": 4.061049938201904, "learning_rate": 9.437406237499292e-06, "loss": 0.3835, "step": 199530 }, { "epoch": 1.1861071978410638, "grad_norm": 5.448441505432129, "learning_rate": 9.437310612211805e-06, "loss": 0.4636, "step": 199540 }, { "epoch": 1.1861666399177322, "grad_norm": 4.768537998199463, "learning_rate": 9.437214979282739e-06, "loss": 0.3755, "step": 199550 }, { "epoch": 1.1862260819944006, "grad_norm": 8.413651466369629, "learning_rate": 9.437119338712262e-06, "loss": 0.4405, "step": 199560 }, { "epoch": 1.186285524071069, "grad_norm": 4.881920337677002, "learning_rate": 9.437023690500533e-06, "loss": 0.3497, "step": 199570 }, { "epoch": 1.1863449661477374, "grad_norm": 5.872345924377441, "learning_rate": 9.436928034647721e-06, "loss": 0.4411, "step": 199580 }, { "epoch": 1.1864044082244058, "grad_norm": 5.005528450012207, "learning_rate": 9.43683237115399e-06, "loss": 0.4231, "step": 199590 }, { "epoch": 1.186463850301074, "grad_norm": 6.254087448120117, "learning_rate": 9.436736700019504e-06, "loss": 0.417, "step": 199600 }, { "epoch": 1.1865232923777425, "grad_norm": 4.806350231170654, "learning_rate": 9.436641021244427e-06, "loss": 0.4154, "step": 199610 }, { "epoch": 1.1865827344544109, "grad_norm": 7.448764801025391, "learning_rate": 9.436545334828927e-06, "loss": 0.4315, "step": 199620 }, { "epoch": 1.1866421765310793, "grad_norm": 5.45871114730835, "learning_rate": 9.436449640773166e-06, "loss": 0.3926, "step": 199630 }, { "epoch": 1.1867016186077477, "grad_norm": 6.124419689178467, "learning_rate": 9.436353939077309e-06, "loss": 0.4107, "step": 199640 }, { "epoch": 1.1867610606844161, "grad_norm": 4.982299327850342, "learning_rate": 9.43625822974152e-06, "loss": 0.392, "step": 199650 }, { "epoch": 1.1868205027610845, "grad_norm": 5.825934410095215, "learning_rate": 9.436162512765966e-06, "loss": 0.3937, "step": 199660 }, { "epoch": 1.186879944837753, "grad_norm": 4.562841415405273, "learning_rate": 9.436066788150811e-06, "loss": 0.3658, "step": 199670 }, { "epoch": 1.1869393869144211, "grad_norm": 5.649802207946777, "learning_rate": 9.435971055896219e-06, "loss": 0.4128, "step": 199680 }, { "epoch": 1.1869988289910895, "grad_norm": 5.753535747528076, "learning_rate": 9.435875316002357e-06, "loss": 0.3762, "step": 199690 }, { "epoch": 1.187058271067758, "grad_norm": 5.080825328826904, "learning_rate": 9.435779568469386e-06, "loss": 0.4476, "step": 199700 }, { "epoch": 1.1871177131444264, "grad_norm": 5.0538129806518555, "learning_rate": 9.435683813297475e-06, "loss": 0.347, "step": 199710 }, { "epoch": 1.1871771552210948, "grad_norm": 4.918304443359375, "learning_rate": 9.435588050486788e-06, "loss": 0.4399, "step": 199720 }, { "epoch": 1.1872365972977632, "grad_norm": 6.1970534324646, "learning_rate": 9.435492280037488e-06, "loss": 0.38, "step": 199730 }, { "epoch": 1.1872960393744316, "grad_norm": 5.116016387939453, "learning_rate": 9.435396501949741e-06, "loss": 0.3884, "step": 199740 }, { "epoch": 1.1873554814511, "grad_norm": 5.713592052459717, "learning_rate": 9.435300716223712e-06, "loss": 0.4466, "step": 199750 }, { "epoch": 1.1874149235277685, "grad_norm": 5.64749813079834, "learning_rate": 9.435204922859567e-06, "loss": 0.3861, "step": 199760 }, { "epoch": 1.1874743656044369, "grad_norm": 4.790661811828613, "learning_rate": 9.435109121857468e-06, "loss": 0.4072, "step": 199770 }, { "epoch": 1.187533807681105, "grad_norm": 4.560920238494873, "learning_rate": 9.435013313217582e-06, "loss": 0.3838, "step": 199780 }, { "epoch": 1.1875932497577735, "grad_norm": 5.4364213943481445, "learning_rate": 9.434917496940076e-06, "loss": 0.385, "step": 199790 }, { "epoch": 1.1876526918344419, "grad_norm": 6.14309024810791, "learning_rate": 9.434821673025111e-06, "loss": 0.4182, "step": 199800 }, { "epoch": 1.1877121339111103, "grad_norm": 6.153936386108398, "learning_rate": 9.434725841472855e-06, "loss": 0.3877, "step": 199810 }, { "epoch": 1.1877715759877787, "grad_norm": 6.41788387298584, "learning_rate": 9.434630002283472e-06, "loss": 0.4322, "step": 199820 }, { "epoch": 1.1878310180644471, "grad_norm": 7.088290691375732, "learning_rate": 9.434534155457126e-06, "loss": 0.4201, "step": 199830 }, { "epoch": 1.1878904601411155, "grad_norm": 4.631259918212891, "learning_rate": 9.434438300993984e-06, "loss": 0.401, "step": 199840 }, { "epoch": 1.187949902217784, "grad_norm": 5.575017929077148, "learning_rate": 9.434342438894211e-06, "loss": 0.4369, "step": 199850 }, { "epoch": 1.1880093442944522, "grad_norm": 4.229197025299072, "learning_rate": 9.43424656915797e-06, "loss": 0.3515, "step": 199860 }, { "epoch": 1.1880687863711206, "grad_norm": 4.000473976135254, "learning_rate": 9.434150691785427e-06, "loss": 0.4269, "step": 199870 }, { "epoch": 1.188128228447789, "grad_norm": 4.105359077453613, "learning_rate": 9.434054806776747e-06, "loss": 0.3563, "step": 199880 }, { "epoch": 1.1881876705244574, "grad_norm": 4.688065052032471, "learning_rate": 9.433958914132097e-06, "loss": 0.3839, "step": 199890 }, { "epoch": 1.1882471126011258, "grad_norm": 5.0434770584106445, "learning_rate": 9.43386301385164e-06, "loss": 0.3969, "step": 199900 }, { "epoch": 1.1883065546777942, "grad_norm": 5.585630416870117, "learning_rate": 9.433767105935542e-06, "loss": 0.3814, "step": 199910 }, { "epoch": 1.1883659967544626, "grad_norm": 5.441911697387695, "learning_rate": 9.433671190383967e-06, "loss": 0.4378, "step": 199920 }, { "epoch": 1.188425438831131, "grad_norm": 4.492454528808594, "learning_rate": 9.433575267197082e-06, "loss": 0.4584, "step": 199930 }, { "epoch": 1.1884848809077995, "grad_norm": 5.059621334075928, "learning_rate": 9.433479336375052e-06, "loss": 0.381, "step": 199940 }, { "epoch": 1.1885443229844679, "grad_norm": 5.166414737701416, "learning_rate": 9.43338339791804e-06, "loss": 0.4095, "step": 199950 }, { "epoch": 1.1886037650611363, "grad_norm": 3.833993434906006, "learning_rate": 9.433287451826215e-06, "loss": 0.4232, "step": 199960 }, { "epoch": 1.1886632071378045, "grad_norm": 6.298245906829834, "learning_rate": 9.433191498099739e-06, "loss": 0.4101, "step": 199970 }, { "epoch": 1.188722649214473, "grad_norm": 5.857337951660156, "learning_rate": 9.433095536738779e-06, "loss": 0.3591, "step": 199980 }, { "epoch": 1.1887820912911413, "grad_norm": 6.8293070793151855, "learning_rate": 9.432999567743498e-06, "loss": 0.4071, "step": 199990 }, { "epoch": 1.1888415333678097, "grad_norm": 5.161730766296387, "learning_rate": 9.432903591114064e-06, "loss": 0.428, "step": 200000 }, { "epoch": 1.1889009754444781, "grad_norm": 4.739044189453125, "learning_rate": 9.432807606850641e-06, "loss": 0.4262, "step": 200010 }, { "epoch": 1.1889604175211466, "grad_norm": 4.46919059753418, "learning_rate": 9.432711614953394e-06, "loss": 0.378, "step": 200020 }, { "epoch": 1.189019859597815, "grad_norm": 6.032243728637695, "learning_rate": 9.432615615422489e-06, "loss": 0.4265, "step": 200030 }, { "epoch": 1.1890793016744834, "grad_norm": 6.067550182342529, "learning_rate": 9.43251960825809e-06, "loss": 0.4058, "step": 200040 }, { "epoch": 1.1891387437511516, "grad_norm": 4.318905353546143, "learning_rate": 9.432423593460364e-06, "loss": 0.4021, "step": 200050 }, { "epoch": 1.18919818582782, "grad_norm": 5.528258323669434, "learning_rate": 9.432327571029476e-06, "loss": 0.3908, "step": 200060 }, { "epoch": 1.1892576279044884, "grad_norm": 4.679116249084473, "learning_rate": 9.43223154096559e-06, "loss": 0.3563, "step": 200070 }, { "epoch": 1.1893170699811568, "grad_norm": 4.857574939727783, "learning_rate": 9.432135503268874e-06, "loss": 0.3898, "step": 200080 }, { "epoch": 1.1893765120578252, "grad_norm": 4.959534645080566, "learning_rate": 9.43203945793949e-06, "loss": 0.4258, "step": 200090 }, { "epoch": 1.1894359541344937, "grad_norm": 4.546695709228516, "learning_rate": 9.431943404977609e-06, "loss": 0.4053, "step": 200100 }, { "epoch": 1.189495396211162, "grad_norm": 5.034873962402344, "learning_rate": 9.43184734438339e-06, "loss": 0.3824, "step": 200110 }, { "epoch": 1.1895548382878305, "grad_norm": 5.281280040740967, "learning_rate": 9.431751276157e-06, "loss": 0.4029, "step": 200120 }, { "epoch": 1.189614280364499, "grad_norm": 5.8068013191223145, "learning_rate": 9.431655200298606e-06, "loss": 0.3726, "step": 200130 }, { "epoch": 1.1896737224411673, "grad_norm": 5.507607936859131, "learning_rate": 9.431559116808373e-06, "loss": 0.3789, "step": 200140 }, { "epoch": 1.1897331645178355, "grad_norm": 5.03295373916626, "learning_rate": 9.431463025686467e-06, "loss": 0.4307, "step": 200150 }, { "epoch": 1.189792606594504, "grad_norm": 4.939356803894043, "learning_rate": 9.431366926933055e-06, "loss": 0.4402, "step": 200160 }, { "epoch": 1.1898520486711723, "grad_norm": 6.564633369445801, "learning_rate": 9.431270820548297e-06, "loss": 0.4243, "step": 200170 }, { "epoch": 1.1899114907478407, "grad_norm": 3.5937540531158447, "learning_rate": 9.431174706532363e-06, "loss": 0.4119, "step": 200180 }, { "epoch": 1.1899709328245092, "grad_norm": 6.42134952545166, "learning_rate": 9.431078584885418e-06, "loss": 0.3752, "step": 200190 }, { "epoch": 1.1900303749011776, "grad_norm": 5.12761116027832, "learning_rate": 9.430982455607627e-06, "loss": 0.3935, "step": 200200 }, { "epoch": 1.190089816977846, "grad_norm": 9.08675479888916, "learning_rate": 9.430886318699155e-06, "loss": 0.4056, "step": 200210 }, { "epoch": 1.1901492590545144, "grad_norm": 5.142230987548828, "learning_rate": 9.430790174160168e-06, "loss": 0.3569, "step": 200220 }, { "epoch": 1.1902087011311826, "grad_norm": 6.520576477050781, "learning_rate": 9.430694021990832e-06, "loss": 0.3523, "step": 200230 }, { "epoch": 1.190268143207851, "grad_norm": 5.735757827758789, "learning_rate": 9.430597862191313e-06, "loss": 0.3961, "step": 200240 }, { "epoch": 1.1903275852845194, "grad_norm": 5.795200824737549, "learning_rate": 9.430501694761773e-06, "loss": 0.3861, "step": 200250 }, { "epoch": 1.1903870273611878, "grad_norm": 4.941676139831543, "learning_rate": 9.430405519702383e-06, "loss": 0.3598, "step": 200260 }, { "epoch": 1.1904464694378563, "grad_norm": 5.465167045593262, "learning_rate": 9.430309337013307e-06, "loss": 0.4153, "step": 200270 }, { "epoch": 1.1905059115145247, "grad_norm": 4.617461681365967, "learning_rate": 9.430213146694706e-06, "loss": 0.4053, "step": 200280 }, { "epoch": 1.190565353591193, "grad_norm": 4.290652751922607, "learning_rate": 9.430116948746753e-06, "loss": 0.3844, "step": 200290 }, { "epoch": 1.1906247956678615, "grad_norm": 5.136760234832764, "learning_rate": 9.430020743169607e-06, "loss": 0.3922, "step": 200300 }, { "epoch": 1.19068423774453, "grad_norm": 6.078474044799805, "learning_rate": 9.42992452996344e-06, "loss": 0.4278, "step": 200310 }, { "epoch": 1.1907436798211983, "grad_norm": 4.487107276916504, "learning_rate": 9.429828309128412e-06, "loss": 0.4176, "step": 200320 }, { "epoch": 1.1908031218978667, "grad_norm": 7.06056547164917, "learning_rate": 9.429732080664692e-06, "loss": 0.3856, "step": 200330 }, { "epoch": 1.190862563974535, "grad_norm": 5.518015384674072, "learning_rate": 9.429635844572445e-06, "loss": 0.3407, "step": 200340 }, { "epoch": 1.1909220060512034, "grad_norm": 4.245453357696533, "learning_rate": 9.429539600851835e-06, "loss": 0.3952, "step": 200350 }, { "epoch": 1.1909814481278718, "grad_norm": 3.9329423904418945, "learning_rate": 9.429443349503032e-06, "loss": 0.3758, "step": 200360 }, { "epoch": 1.1910408902045402, "grad_norm": 5.662696838378906, "learning_rate": 9.429347090526196e-06, "loss": 0.3851, "step": 200370 }, { "epoch": 1.1911003322812086, "grad_norm": 6.854371547698975, "learning_rate": 9.429250823921499e-06, "loss": 0.3794, "step": 200380 }, { "epoch": 1.191159774357877, "grad_norm": 4.1961894035339355, "learning_rate": 9.4291545496891e-06, "loss": 0.3784, "step": 200390 }, { "epoch": 1.1912192164345454, "grad_norm": 4.1374077796936035, "learning_rate": 9.429058267829171e-06, "loss": 0.4243, "step": 200400 }, { "epoch": 1.1912786585112138, "grad_norm": 6.6296820640563965, "learning_rate": 9.428961978341876e-06, "loss": 0.4319, "step": 200410 }, { "epoch": 1.191338100587882, "grad_norm": 5.580480575561523, "learning_rate": 9.428865681227377e-06, "loss": 0.4251, "step": 200420 }, { "epoch": 1.1913975426645504, "grad_norm": 5.249853134155273, "learning_rate": 9.428769376485844e-06, "loss": 0.3933, "step": 200430 }, { "epoch": 1.1914569847412189, "grad_norm": 4.521797180175781, "learning_rate": 9.428673064117443e-06, "loss": 0.3949, "step": 200440 }, { "epoch": 1.1915164268178873, "grad_norm": 5.617555618286133, "learning_rate": 9.428576744122336e-06, "loss": 0.394, "step": 200450 }, { "epoch": 1.1915758688945557, "grad_norm": 6.132679462432861, "learning_rate": 9.428480416500694e-06, "loss": 0.3625, "step": 200460 }, { "epoch": 1.191635310971224, "grad_norm": 6.667908191680908, "learning_rate": 9.42838408125268e-06, "loss": 0.388, "step": 200470 }, { "epoch": 1.1916947530478925, "grad_norm": 4.737773418426514, "learning_rate": 9.42828773837846e-06, "loss": 0.3834, "step": 200480 }, { "epoch": 1.191754195124561, "grad_norm": 7.148282051086426, "learning_rate": 9.428191387878199e-06, "loss": 0.4346, "step": 200490 }, { "epoch": 1.1918136372012293, "grad_norm": 7.067902565002441, "learning_rate": 9.428095029752063e-06, "loss": 0.4086, "step": 200500 }, { "epoch": 1.1918730792778978, "grad_norm": 5.21574592590332, "learning_rate": 9.427998664000222e-06, "loss": 0.4338, "step": 200510 }, { "epoch": 1.191932521354566, "grad_norm": 5.791735649108887, "learning_rate": 9.427902290622837e-06, "loss": 0.4155, "step": 200520 }, { "epoch": 1.1919919634312344, "grad_norm": 5.861109733581543, "learning_rate": 9.427805909620076e-06, "loss": 0.3723, "step": 200530 }, { "epoch": 1.1920514055079028, "grad_norm": 3.9507737159729004, "learning_rate": 9.427709520992106e-06, "loss": 0.3815, "step": 200540 }, { "epoch": 1.1921108475845712, "grad_norm": 3.8099701404571533, "learning_rate": 9.427613124739093e-06, "loss": 0.3778, "step": 200550 }, { "epoch": 1.1921702896612396, "grad_norm": 5.44598388671875, "learning_rate": 9.4275167208612e-06, "loss": 0.4117, "step": 200560 }, { "epoch": 1.192229731737908, "grad_norm": 4.758079528808594, "learning_rate": 9.427420309358594e-06, "loss": 0.3631, "step": 200570 }, { "epoch": 1.1922891738145764, "grad_norm": 5.3235063552856445, "learning_rate": 9.427323890231443e-06, "loss": 0.3733, "step": 200580 }, { "epoch": 1.1923486158912449, "grad_norm": 3.566810369491577, "learning_rate": 9.427227463479914e-06, "loss": 0.3885, "step": 200590 }, { "epoch": 1.192408057967913, "grad_norm": 6.502386569976807, "learning_rate": 9.427131029104169e-06, "loss": 0.371, "step": 200600 }, { "epoch": 1.1924675000445815, "grad_norm": 4.227850437164307, "learning_rate": 9.427034587104376e-06, "loss": 0.3926, "step": 200610 }, { "epoch": 1.1925269421212499, "grad_norm": 6.217029571533203, "learning_rate": 9.426938137480701e-06, "loss": 0.403, "step": 200620 }, { "epoch": 1.1925863841979183, "grad_norm": 4.361169815063477, "learning_rate": 9.426841680233312e-06, "loss": 0.4152, "step": 200630 }, { "epoch": 1.1926458262745867, "grad_norm": 4.021322250366211, "learning_rate": 9.426745215362371e-06, "loss": 0.3717, "step": 200640 }, { "epoch": 1.1927052683512551, "grad_norm": 5.486144542694092, "learning_rate": 9.426648742868047e-06, "loss": 0.3771, "step": 200650 }, { "epoch": 1.1927647104279235, "grad_norm": 4.309396266937256, "learning_rate": 9.426552262750507e-06, "loss": 0.4106, "step": 200660 }, { "epoch": 1.192824152504592, "grad_norm": 5.533365249633789, "learning_rate": 9.426455775009916e-06, "loss": 0.3673, "step": 200670 }, { "epoch": 1.1928835945812604, "grad_norm": 5.211155414581299, "learning_rate": 9.42635927964644e-06, "loss": 0.4074, "step": 200680 }, { "epoch": 1.1929430366579288, "grad_norm": 4.563838005065918, "learning_rate": 9.426262776660245e-06, "loss": 0.3703, "step": 200690 }, { "epoch": 1.1930024787345972, "grad_norm": 5.73195743560791, "learning_rate": 9.426166266051497e-06, "loss": 0.3575, "step": 200700 }, { "epoch": 1.1930619208112654, "grad_norm": 4.834787368774414, "learning_rate": 9.42606974782036e-06, "loss": 0.4027, "step": 200710 }, { "epoch": 1.1931213628879338, "grad_norm": 6.0361104011535645, "learning_rate": 9.425973221967007e-06, "loss": 0.4052, "step": 200720 }, { "epoch": 1.1931808049646022, "grad_norm": 4.562893390655518, "learning_rate": 9.425876688491598e-06, "loss": 0.4181, "step": 200730 }, { "epoch": 1.1932402470412706, "grad_norm": 5.225008964538574, "learning_rate": 9.425780147394303e-06, "loss": 0.4151, "step": 200740 }, { "epoch": 1.193299689117939, "grad_norm": 4.743371486663818, "learning_rate": 9.425683598675285e-06, "loss": 0.3818, "step": 200750 }, { "epoch": 1.1933591311946075, "grad_norm": 5.326634407043457, "learning_rate": 9.425587042334711e-06, "loss": 0.4123, "step": 200760 }, { "epoch": 1.1934185732712759, "grad_norm": 5.359729290008545, "learning_rate": 9.425490478372749e-06, "loss": 0.3694, "step": 200770 }, { "epoch": 1.1934780153479443, "grad_norm": 6.333818435668945, "learning_rate": 9.425393906789564e-06, "loss": 0.4022, "step": 200780 }, { "epoch": 1.1935374574246125, "grad_norm": 5.4998345375061035, "learning_rate": 9.425297327585323e-06, "loss": 0.4238, "step": 200790 }, { "epoch": 1.193596899501281, "grad_norm": 5.801299095153809, "learning_rate": 9.425200740760191e-06, "loss": 0.3768, "step": 200800 }, { "epoch": 1.1936563415779493, "grad_norm": 5.6267924308776855, "learning_rate": 9.425104146314338e-06, "loss": 0.3831, "step": 200810 }, { "epoch": 1.1937157836546177, "grad_norm": 4.761580467224121, "learning_rate": 9.425007544247926e-06, "loss": 0.3854, "step": 200820 }, { "epoch": 1.1937752257312861, "grad_norm": 4.4634599685668945, "learning_rate": 9.424910934561121e-06, "loss": 0.3813, "step": 200830 }, { "epoch": 1.1938346678079546, "grad_norm": 5.238093852996826, "learning_rate": 9.424814317254095e-06, "loss": 0.4036, "step": 200840 }, { "epoch": 1.193894109884623, "grad_norm": 5.266650676727295, "learning_rate": 9.424717692327009e-06, "loss": 0.4072, "step": 200850 }, { "epoch": 1.1939535519612914, "grad_norm": 4.112845420837402, "learning_rate": 9.424621059780032e-06, "loss": 0.427, "step": 200860 }, { "epoch": 1.1940129940379598, "grad_norm": 4.606914520263672, "learning_rate": 9.424524419613327e-06, "loss": 0.4023, "step": 200870 }, { "epoch": 1.1940724361146282, "grad_norm": 6.9708943367004395, "learning_rate": 9.424427771827067e-06, "loss": 0.383, "step": 200880 }, { "epoch": 1.1941318781912964, "grad_norm": 4.57869815826416, "learning_rate": 9.424331116421413e-06, "loss": 0.4241, "step": 200890 }, { "epoch": 1.1941913202679648, "grad_norm": 5.740164279937744, "learning_rate": 9.424234453396532e-06, "loss": 0.4109, "step": 200900 }, { "epoch": 1.1942507623446332, "grad_norm": 5.577169418334961, "learning_rate": 9.42413778275259e-06, "loss": 0.3883, "step": 200910 }, { "epoch": 1.1943102044213016, "grad_norm": 5.90493106842041, "learning_rate": 9.424041104489758e-06, "loss": 0.3903, "step": 200920 }, { "epoch": 1.19436964649797, "grad_norm": 6.669317245483398, "learning_rate": 9.423944418608197e-06, "loss": 0.368, "step": 200930 }, { "epoch": 1.1944290885746385, "grad_norm": 5.947846412658691, "learning_rate": 9.423847725108077e-06, "loss": 0.3886, "step": 200940 }, { "epoch": 1.194488530651307, "grad_norm": 3.7095162868499756, "learning_rate": 9.423751023989563e-06, "loss": 0.3632, "step": 200950 }, { "epoch": 1.1945479727279753, "grad_norm": 5.337551116943359, "learning_rate": 9.423654315252822e-06, "loss": 0.3695, "step": 200960 }, { "epoch": 1.1946074148046435, "grad_norm": 5.891542911529541, "learning_rate": 9.423557598898021e-06, "loss": 0.4115, "step": 200970 }, { "epoch": 1.194666856881312, "grad_norm": 5.0208821296691895, "learning_rate": 9.423460874925325e-06, "loss": 0.3809, "step": 200980 }, { "epoch": 1.1947262989579803, "grad_norm": 4.241384506225586, "learning_rate": 9.423364143334902e-06, "loss": 0.4212, "step": 200990 }, { "epoch": 1.1947857410346487, "grad_norm": 5.380870342254639, "learning_rate": 9.423267404126919e-06, "loss": 0.4163, "step": 201000 }, { "epoch": 1.1948451831113172, "grad_norm": 6.090592861175537, "learning_rate": 9.42317065730154e-06, "loss": 0.394, "step": 201010 }, { "epoch": 1.1949046251879856, "grad_norm": 5.117999076843262, "learning_rate": 9.423073902858935e-06, "loss": 0.4407, "step": 201020 }, { "epoch": 1.194964067264654, "grad_norm": 4.970324516296387, "learning_rate": 9.422977140799268e-06, "loss": 0.3602, "step": 201030 }, { "epoch": 1.1950235093413224, "grad_norm": 5.052427291870117, "learning_rate": 9.422880371122706e-06, "loss": 0.4366, "step": 201040 }, { "epoch": 1.1950829514179908, "grad_norm": 5.04954719543457, "learning_rate": 9.422783593829418e-06, "loss": 0.4385, "step": 201050 }, { "epoch": 1.1951423934946592, "grad_norm": 5.058742523193359, "learning_rate": 9.422686808919567e-06, "loss": 0.3839, "step": 201060 }, { "epoch": 1.1952018355713276, "grad_norm": 4.410556316375732, "learning_rate": 9.422590016393324e-06, "loss": 0.3707, "step": 201070 }, { "epoch": 1.1952612776479958, "grad_norm": 5.64505672454834, "learning_rate": 9.422493216250851e-06, "loss": 0.3844, "step": 201080 }, { "epoch": 1.1953207197246642, "grad_norm": 4.941985130310059, "learning_rate": 9.422396408492319e-06, "loss": 0.4265, "step": 201090 }, { "epoch": 1.1953801618013327, "grad_norm": 4.17043924331665, "learning_rate": 9.422299593117891e-06, "loss": 0.3742, "step": 201100 }, { "epoch": 1.195439603878001, "grad_norm": 5.622839450836182, "learning_rate": 9.422202770127738e-06, "loss": 0.4012, "step": 201110 }, { "epoch": 1.1954990459546695, "grad_norm": 7.897493362426758, "learning_rate": 9.422105939522021e-06, "loss": 0.4039, "step": 201120 }, { "epoch": 1.195558488031338, "grad_norm": 5.225444793701172, "learning_rate": 9.422009101300912e-06, "loss": 0.416, "step": 201130 }, { "epoch": 1.1956179301080063, "grad_norm": 5.5026044845581055, "learning_rate": 9.421912255464576e-06, "loss": 0.4045, "step": 201140 }, { "epoch": 1.1956773721846747, "grad_norm": 5.868077754974365, "learning_rate": 9.421815402013176e-06, "loss": 0.4122, "step": 201150 }, { "epoch": 1.195736814261343, "grad_norm": 7.196618556976318, "learning_rate": 9.421718540946888e-06, "loss": 0.4095, "step": 201160 }, { "epoch": 1.1957962563380113, "grad_norm": 5.106100082397461, "learning_rate": 9.421621672265868e-06, "loss": 0.3969, "step": 201170 }, { "epoch": 1.1958556984146798, "grad_norm": 4.630707740783691, "learning_rate": 9.421524795970291e-06, "loss": 0.3774, "step": 201180 }, { "epoch": 1.1959151404913482, "grad_norm": 4.954579830169678, "learning_rate": 9.421427912060319e-06, "loss": 0.3759, "step": 201190 }, { "epoch": 1.1959745825680166, "grad_norm": 6.404453277587891, "learning_rate": 9.421331020536121e-06, "loss": 0.3898, "step": 201200 }, { "epoch": 1.196034024644685, "grad_norm": 5.014090538024902, "learning_rate": 9.421234121397865e-06, "loss": 0.4073, "step": 201210 }, { "epoch": 1.1960934667213534, "grad_norm": 4.412323951721191, "learning_rate": 9.421137214645713e-06, "loss": 0.4136, "step": 201220 }, { "epoch": 1.1961529087980218, "grad_norm": 5.964134693145752, "learning_rate": 9.421040300279839e-06, "loss": 0.4171, "step": 201230 }, { "epoch": 1.1962123508746902, "grad_norm": 5.76732063293457, "learning_rate": 9.420943378300402e-06, "loss": 0.4189, "step": 201240 }, { "epoch": 1.1962717929513587, "grad_norm": 5.018564224243164, "learning_rate": 9.420846448707576e-06, "loss": 0.4005, "step": 201250 }, { "epoch": 1.1963312350280269, "grad_norm": 6.336435794830322, "learning_rate": 9.420749511501523e-06, "loss": 0.4232, "step": 201260 }, { "epoch": 1.1963906771046953, "grad_norm": 6.018191814422607, "learning_rate": 9.420652566682414e-06, "loss": 0.3762, "step": 201270 }, { "epoch": 1.1964501191813637, "grad_norm": 5.164746284484863, "learning_rate": 9.420555614250414e-06, "loss": 0.4212, "step": 201280 }, { "epoch": 1.196509561258032, "grad_norm": 6.293909549713135, "learning_rate": 9.420458654205686e-06, "loss": 0.4099, "step": 201290 }, { "epoch": 1.1965690033347005, "grad_norm": 5.318264961242676, "learning_rate": 9.420361686548404e-06, "loss": 0.3567, "step": 201300 }, { "epoch": 1.196628445411369, "grad_norm": 5.840214252471924, "learning_rate": 9.420264711278731e-06, "loss": 0.3823, "step": 201310 }, { "epoch": 1.1966878874880373, "grad_norm": 4.693830966949463, "learning_rate": 9.420167728396835e-06, "loss": 0.3815, "step": 201320 }, { "epoch": 1.1967473295647058, "grad_norm": 5.74144172668457, "learning_rate": 9.420070737902882e-06, "loss": 0.4026, "step": 201330 }, { "epoch": 1.196806771641374, "grad_norm": 5.987451076507568, "learning_rate": 9.419973739797042e-06, "loss": 0.4006, "step": 201340 }, { "epoch": 1.1968662137180424, "grad_norm": 4.7521653175354, "learning_rate": 9.419876734079476e-06, "loss": 0.4075, "step": 201350 }, { "epoch": 1.1969256557947108, "grad_norm": 7.836706161499023, "learning_rate": 9.419779720750357e-06, "loss": 0.4041, "step": 201360 }, { "epoch": 1.1969850978713792, "grad_norm": 4.449769496917725, "learning_rate": 9.41968269980985e-06, "loss": 0.3748, "step": 201370 }, { "epoch": 1.1970445399480476, "grad_norm": 5.095093250274658, "learning_rate": 9.419585671258123e-06, "loss": 0.4088, "step": 201380 }, { "epoch": 1.197103982024716, "grad_norm": 6.331483840942383, "learning_rate": 9.419488635095342e-06, "loss": 0.3539, "step": 201390 }, { "epoch": 1.1971634241013844, "grad_norm": 5.827732563018799, "learning_rate": 9.419391591321673e-06, "loss": 0.3585, "step": 201400 }, { "epoch": 1.1972228661780528, "grad_norm": 6.189463138580322, "learning_rate": 9.419294539937285e-06, "loss": 0.3884, "step": 201410 }, { "epoch": 1.1972823082547213, "grad_norm": 5.077577590942383, "learning_rate": 9.419197480942344e-06, "loss": 0.3687, "step": 201420 }, { "epoch": 1.1973417503313897, "grad_norm": 5.378130912780762, "learning_rate": 9.419100414337018e-06, "loss": 0.4461, "step": 201430 }, { "epoch": 1.197401192408058, "grad_norm": 4.866017818450928, "learning_rate": 9.419003340121473e-06, "loss": 0.3742, "step": 201440 }, { "epoch": 1.1974606344847263, "grad_norm": 5.022213459014893, "learning_rate": 9.418906258295879e-06, "loss": 0.392, "step": 201450 }, { "epoch": 1.1975200765613947, "grad_norm": 5.938526153564453, "learning_rate": 9.418809168860399e-06, "loss": 0.4014, "step": 201460 }, { "epoch": 1.1975795186380631, "grad_norm": 6.362222671508789, "learning_rate": 9.418712071815204e-06, "loss": 0.3805, "step": 201470 }, { "epoch": 1.1976389607147315, "grad_norm": 7.536286354064941, "learning_rate": 9.418614967160459e-06, "loss": 0.4043, "step": 201480 }, { "epoch": 1.1976984027914, "grad_norm": 4.590877056121826, "learning_rate": 9.418517854896331e-06, "loss": 0.3642, "step": 201490 }, { "epoch": 1.1977578448680684, "grad_norm": 5.992278099060059, "learning_rate": 9.418420735022988e-06, "loss": 0.4049, "step": 201500 }, { "epoch": 1.1978172869447368, "grad_norm": 4.6052470207214355, "learning_rate": 9.4183236075406e-06, "loss": 0.3823, "step": 201510 }, { "epoch": 1.1978767290214052, "grad_norm": 5.328411102294922, "learning_rate": 9.418226472449328e-06, "loss": 0.3615, "step": 201520 }, { "epoch": 1.1979361710980734, "grad_norm": 7.316061019897461, "learning_rate": 9.418129329749345e-06, "loss": 0.4174, "step": 201530 }, { "epoch": 1.1979956131747418, "grad_norm": 6.405150890350342, "learning_rate": 9.418032179440816e-06, "loss": 0.4185, "step": 201540 }, { "epoch": 1.1980550552514102, "grad_norm": 3.8670716285705566, "learning_rate": 9.417935021523908e-06, "loss": 0.4008, "step": 201550 }, { "epoch": 1.1981144973280786, "grad_norm": 4.91677188873291, "learning_rate": 9.417837855998789e-06, "loss": 0.4331, "step": 201560 }, { "epoch": 1.198173939404747, "grad_norm": 4.394547462463379, "learning_rate": 9.417740682865625e-06, "loss": 0.4047, "step": 201570 }, { "epoch": 1.1982333814814154, "grad_norm": 5.490747451782227, "learning_rate": 9.417643502124586e-06, "loss": 0.432, "step": 201580 }, { "epoch": 1.1982928235580839, "grad_norm": 5.313020706176758, "learning_rate": 9.417546313775835e-06, "loss": 0.3846, "step": 201590 }, { "epoch": 1.1983522656347523, "grad_norm": 4.404727458953857, "learning_rate": 9.417449117819547e-06, "loss": 0.3925, "step": 201600 }, { "epoch": 1.1984117077114207, "grad_norm": 4.927533149719238, "learning_rate": 9.41735191425588e-06, "loss": 0.3691, "step": 201610 }, { "epoch": 1.198471149788089, "grad_norm": 6.010795593261719, "learning_rate": 9.417254703085008e-06, "loss": 0.4125, "step": 201620 }, { "epoch": 1.1985305918647573, "grad_norm": 4.68486213684082, "learning_rate": 9.417157484307096e-06, "loss": 0.4148, "step": 201630 }, { "epoch": 1.1985900339414257, "grad_norm": 4.110015869140625, "learning_rate": 9.417060257922312e-06, "loss": 0.4263, "step": 201640 }, { "epoch": 1.1986494760180941, "grad_norm": 5.603702545166016, "learning_rate": 9.416963023930822e-06, "loss": 0.3952, "step": 201650 }, { "epoch": 1.1987089180947625, "grad_norm": 6.345089435577393, "learning_rate": 9.416865782332795e-06, "loss": 0.4348, "step": 201660 }, { "epoch": 1.198768360171431, "grad_norm": 5.592759609222412, "learning_rate": 9.4167685331284e-06, "loss": 0.434, "step": 201670 }, { "epoch": 1.1988278022480994, "grad_norm": 3.956679344177246, "learning_rate": 9.416671276317802e-06, "loss": 0.3611, "step": 201680 }, { "epoch": 1.1988872443247678, "grad_norm": 5.700167179107666, "learning_rate": 9.416574011901166e-06, "loss": 0.3533, "step": 201690 }, { "epoch": 1.1989466864014362, "grad_norm": 4.300257205963135, "learning_rate": 9.416476739878666e-06, "loss": 0.4092, "step": 201700 }, { "epoch": 1.1990061284781044, "grad_norm": 4.97387170791626, "learning_rate": 9.416379460250466e-06, "loss": 0.3983, "step": 201710 }, { "epoch": 1.1990655705547728, "grad_norm": 3.9006316661834717, "learning_rate": 9.416282173016733e-06, "loss": 0.3923, "step": 201720 }, { "epoch": 1.1991250126314412, "grad_norm": 5.606871128082275, "learning_rate": 9.416184878177635e-06, "loss": 0.3939, "step": 201730 }, { "epoch": 1.1991844547081096, "grad_norm": 5.891225814819336, "learning_rate": 9.41608757573334e-06, "loss": 0.4511, "step": 201740 }, { "epoch": 1.199243896784778, "grad_norm": 5.258094310760498, "learning_rate": 9.415990265684014e-06, "loss": 0.3962, "step": 201750 }, { "epoch": 1.1993033388614465, "grad_norm": 4.9684529304504395, "learning_rate": 9.415892948029826e-06, "loss": 0.4197, "step": 201760 }, { "epoch": 1.1993627809381149, "grad_norm": 4.675630569458008, "learning_rate": 9.415795622770944e-06, "loss": 0.4293, "step": 201770 }, { "epoch": 1.1994222230147833, "grad_norm": 5.931822776794434, "learning_rate": 9.415698289907536e-06, "loss": 0.3793, "step": 201780 }, { "epoch": 1.1994816650914517, "grad_norm": 6.835222244262695, "learning_rate": 9.415600949439768e-06, "loss": 0.4549, "step": 201790 }, { "epoch": 1.1995411071681201, "grad_norm": 5.250261306762695, "learning_rate": 9.415503601367809e-06, "loss": 0.3852, "step": 201800 }, { "epoch": 1.1996005492447885, "grad_norm": 4.71911096572876, "learning_rate": 9.415406245691825e-06, "loss": 0.4209, "step": 201810 }, { "epoch": 1.1996599913214567, "grad_norm": 7.138097286224365, "learning_rate": 9.415308882411985e-06, "loss": 0.4186, "step": 201820 }, { "epoch": 1.1997194333981251, "grad_norm": 4.445674896240234, "learning_rate": 9.415211511528455e-06, "loss": 0.3928, "step": 201830 }, { "epoch": 1.1997788754747936, "grad_norm": 4.168442249298096, "learning_rate": 9.415114133041406e-06, "loss": 0.4009, "step": 201840 }, { "epoch": 1.199838317551462, "grad_norm": 5.08127498626709, "learning_rate": 9.415016746951001e-06, "loss": 0.4255, "step": 201850 }, { "epoch": 1.1998977596281304, "grad_norm": 5.923496246337891, "learning_rate": 9.414919353257412e-06, "loss": 0.4272, "step": 201860 }, { "epoch": 1.1999572017047988, "grad_norm": 6.936990737915039, "learning_rate": 9.414821951960804e-06, "loss": 0.4263, "step": 201870 }, { "epoch": 1.2000166437814672, "grad_norm": 6.233206748962402, "learning_rate": 9.41472454306135e-06, "loss": 0.3666, "step": 201880 }, { "epoch": 1.2000760858581356, "grad_norm": 5.998044490814209, "learning_rate": 9.414627126559208e-06, "loss": 0.4039, "step": 201890 }, { "epoch": 1.2001355279348038, "grad_norm": 4.155436038970947, "learning_rate": 9.414529702454554e-06, "loss": 0.4214, "step": 201900 }, { "epoch": 1.2001949700114722, "grad_norm": 5.802859783172607, "learning_rate": 9.414432270747553e-06, "loss": 0.4407, "step": 201910 }, { "epoch": 1.2002544120881407, "grad_norm": 5.013514518737793, "learning_rate": 9.414334831438373e-06, "loss": 0.4005, "step": 201920 }, { "epoch": 1.200313854164809, "grad_norm": 4.08458948135376, "learning_rate": 9.414237384527181e-06, "loss": 0.4071, "step": 201930 }, { "epoch": 1.2003732962414775, "grad_norm": 5.181602954864502, "learning_rate": 9.414139930014148e-06, "loss": 0.3937, "step": 201940 }, { "epoch": 1.200432738318146, "grad_norm": 4.536351680755615, "learning_rate": 9.414042467899436e-06, "loss": 0.3992, "step": 201950 }, { "epoch": 1.2004921803948143, "grad_norm": 5.686124324798584, "learning_rate": 9.413944998183217e-06, "loss": 0.3997, "step": 201960 }, { "epoch": 1.2005516224714827, "grad_norm": 7.659846305847168, "learning_rate": 9.41384752086566e-06, "loss": 0.4012, "step": 201970 }, { "epoch": 1.2006110645481511, "grad_norm": 4.117170810699463, "learning_rate": 9.413750035946929e-06, "loss": 0.3519, "step": 201980 }, { "epoch": 1.2006705066248196, "grad_norm": 5.566458225250244, "learning_rate": 9.413652543427194e-06, "loss": 0.3847, "step": 201990 }, { "epoch": 1.2007299487014877, "grad_norm": 5.8637261390686035, "learning_rate": 9.413555043306624e-06, "loss": 0.4053, "step": 202000 }, { "epoch": 1.2007893907781562, "grad_norm": 5.342378616333008, "learning_rate": 9.413457535585385e-06, "loss": 0.4258, "step": 202010 }, { "epoch": 1.2008488328548246, "grad_norm": 6.095523357391357, "learning_rate": 9.413360020263645e-06, "loss": 0.4547, "step": 202020 }, { "epoch": 1.200908274931493, "grad_norm": 4.16245698928833, "learning_rate": 9.413262497341573e-06, "loss": 0.373, "step": 202030 }, { "epoch": 1.2009677170081614, "grad_norm": 4.514686584472656, "learning_rate": 9.413164966819335e-06, "loss": 0.398, "step": 202040 }, { "epoch": 1.2010271590848298, "grad_norm": 5.058328151702881, "learning_rate": 9.413067428697103e-06, "loss": 0.3878, "step": 202050 }, { "epoch": 1.2010866011614982, "grad_norm": 4.6622233390808105, "learning_rate": 9.41296988297504e-06, "loss": 0.4272, "step": 202060 }, { "epoch": 1.2011460432381666, "grad_norm": 4.041558742523193, "learning_rate": 9.412872329653318e-06, "loss": 0.3943, "step": 202070 }, { "epoch": 1.2012054853148348, "grad_norm": 5.984569549560547, "learning_rate": 9.4127747687321e-06, "loss": 0.366, "step": 202080 }, { "epoch": 1.2012649273915033, "grad_norm": 5.9677839279174805, "learning_rate": 9.412677200211561e-06, "loss": 0.375, "step": 202090 }, { "epoch": 1.2013243694681717, "grad_norm": 5.031476974487305, "learning_rate": 9.412579624091864e-06, "loss": 0.4056, "step": 202100 }, { "epoch": 1.20138381154484, "grad_norm": 4.336956977844238, "learning_rate": 9.41248204037318e-06, "loss": 0.3798, "step": 202110 }, { "epoch": 1.2014432536215085, "grad_norm": 4.246786594390869, "learning_rate": 9.412384449055672e-06, "loss": 0.4166, "step": 202120 }, { "epoch": 1.201502695698177, "grad_norm": 3.9570584297180176, "learning_rate": 9.412286850139513e-06, "loss": 0.3912, "step": 202130 }, { "epoch": 1.2015621377748453, "grad_norm": 4.626461982727051, "learning_rate": 9.412189243624871e-06, "loss": 0.3999, "step": 202140 }, { "epoch": 1.2016215798515137, "grad_norm": 4.608360290527344, "learning_rate": 9.412091629511911e-06, "loss": 0.3728, "step": 202150 }, { "epoch": 1.2016810219281822, "grad_norm": 5.841908931732178, "learning_rate": 9.411994007800805e-06, "loss": 0.4334, "step": 202160 }, { "epoch": 1.2017404640048506, "grad_norm": 5.822381496429443, "learning_rate": 9.411896378491717e-06, "loss": 0.3678, "step": 202170 }, { "epoch": 1.201799906081519, "grad_norm": 4.1720452308654785, "learning_rate": 9.411798741584816e-06, "loss": 0.3793, "step": 202180 }, { "epoch": 1.2018593481581872, "grad_norm": 4.477406024932861, "learning_rate": 9.411701097080272e-06, "loss": 0.408, "step": 202190 }, { "epoch": 1.2019187902348556, "grad_norm": 6.118837833404541, "learning_rate": 9.411603444978254e-06, "loss": 0.4134, "step": 202200 }, { "epoch": 1.201978232311524, "grad_norm": 6.1399827003479, "learning_rate": 9.411505785278928e-06, "loss": 0.435, "step": 202210 }, { "epoch": 1.2020376743881924, "grad_norm": 5.911288738250732, "learning_rate": 9.411408117982462e-06, "loss": 0.4247, "step": 202220 }, { "epoch": 1.2020971164648608, "grad_norm": 4.6718430519104, "learning_rate": 9.411310443089023e-06, "loss": 0.4325, "step": 202230 }, { "epoch": 1.2021565585415293, "grad_norm": 6.801551342010498, "learning_rate": 9.411212760598783e-06, "loss": 0.4141, "step": 202240 }, { "epoch": 1.2022160006181977, "grad_norm": 6.963194370269775, "learning_rate": 9.41111507051191e-06, "loss": 0.3584, "step": 202250 }, { "epoch": 1.202275442694866, "grad_norm": 5.812780857086182, "learning_rate": 9.411017372828567e-06, "loss": 0.4316, "step": 202260 }, { "epoch": 1.2023348847715343, "grad_norm": 4.960552215576172, "learning_rate": 9.410919667548928e-06, "loss": 0.4114, "step": 202270 }, { "epoch": 1.2023943268482027, "grad_norm": 5.133181571960449, "learning_rate": 9.410821954673158e-06, "loss": 0.401, "step": 202280 }, { "epoch": 1.202453768924871, "grad_norm": 6.7651238441467285, "learning_rate": 9.410724234201427e-06, "loss": 0.4163, "step": 202290 }, { "epoch": 1.2025132110015395, "grad_norm": 5.3133931159973145, "learning_rate": 9.410626506133903e-06, "loss": 0.4117, "step": 202300 }, { "epoch": 1.202572653078208, "grad_norm": 5.935606479644775, "learning_rate": 9.410528770470753e-06, "loss": 0.3945, "step": 202310 }, { "epoch": 1.2026320951548763, "grad_norm": 8.447484970092773, "learning_rate": 9.410431027212145e-06, "loss": 0.4292, "step": 202320 }, { "epoch": 1.2026915372315448, "grad_norm": 5.968394756317139, "learning_rate": 9.41033327635825e-06, "loss": 0.4118, "step": 202330 }, { "epoch": 1.2027509793082132, "grad_norm": 4.4452314376831055, "learning_rate": 9.410235517909237e-06, "loss": 0.377, "step": 202340 }, { "epoch": 1.2028104213848816, "grad_norm": 6.343527317047119, "learning_rate": 9.41013775186527e-06, "loss": 0.3956, "step": 202350 }, { "epoch": 1.20286986346155, "grad_norm": 5.282415866851807, "learning_rate": 9.410039978226519e-06, "loss": 0.43, "step": 202360 }, { "epoch": 1.2029293055382182, "grad_norm": 3.9606223106384277, "learning_rate": 9.409942196993154e-06, "loss": 0.3746, "step": 202370 }, { "epoch": 1.2029887476148866, "grad_norm": 6.647861957550049, "learning_rate": 9.409844408165341e-06, "loss": 0.4189, "step": 202380 }, { "epoch": 1.203048189691555, "grad_norm": 4.285645008087158, "learning_rate": 9.40974661174325e-06, "loss": 0.3781, "step": 202390 }, { "epoch": 1.2031076317682234, "grad_norm": 5.451066017150879, "learning_rate": 9.40964880772705e-06, "loss": 0.3784, "step": 202400 }, { "epoch": 1.2031670738448919, "grad_norm": 5.313720703125, "learning_rate": 9.40955099611691e-06, "loss": 0.3902, "step": 202410 }, { "epoch": 1.2032265159215603, "grad_norm": 5.012515544891357, "learning_rate": 9.409453176912995e-06, "loss": 0.3962, "step": 202420 }, { "epoch": 1.2032859579982287, "grad_norm": 4.862160682678223, "learning_rate": 9.409355350115475e-06, "loss": 0.4035, "step": 202430 }, { "epoch": 1.203345400074897, "grad_norm": 4.608460903167725, "learning_rate": 9.409257515724521e-06, "loss": 0.3829, "step": 202440 }, { "epoch": 1.2034048421515653, "grad_norm": 5.024584770202637, "learning_rate": 9.409159673740299e-06, "loss": 0.4198, "step": 202450 }, { "epoch": 1.2034642842282337, "grad_norm": 4.525650501251221, "learning_rate": 9.409061824162977e-06, "loss": 0.3874, "step": 202460 }, { "epoch": 1.2035237263049021, "grad_norm": 4.918333530426025, "learning_rate": 9.408963966992724e-06, "loss": 0.4221, "step": 202470 }, { "epoch": 1.2035831683815705, "grad_norm": 5.870923042297363, "learning_rate": 9.40886610222971e-06, "loss": 0.3637, "step": 202480 }, { "epoch": 1.203642610458239, "grad_norm": 4.374875545501709, "learning_rate": 9.408768229874103e-06, "loss": 0.385, "step": 202490 }, { "epoch": 1.2037020525349074, "grad_norm": 5.4035773277282715, "learning_rate": 9.40867034992607e-06, "loss": 0.3926, "step": 202500 }, { "epoch": 1.2037614946115758, "grad_norm": 5.080871105194092, "learning_rate": 9.40857246238578e-06, "loss": 0.4186, "step": 202510 }, { "epoch": 1.2038209366882442, "grad_norm": 3.838862180709839, "learning_rate": 9.408474567253405e-06, "loss": 0.4379, "step": 202520 }, { "epoch": 1.2038803787649126, "grad_norm": 5.702784061431885, "learning_rate": 9.408376664529108e-06, "loss": 0.3826, "step": 202530 }, { "epoch": 1.203939820841581, "grad_norm": 4.112323760986328, "learning_rate": 9.408278754213062e-06, "loss": 0.3696, "step": 202540 }, { "epoch": 1.2039992629182494, "grad_norm": 5.561212539672852, "learning_rate": 9.408180836305434e-06, "loss": 0.3848, "step": 202550 }, { "epoch": 1.2040587049949176, "grad_norm": 5.27761697769165, "learning_rate": 9.408082910806391e-06, "loss": 0.3864, "step": 202560 }, { "epoch": 1.204118147071586, "grad_norm": 4.8828935623168945, "learning_rate": 9.407984977716104e-06, "loss": 0.4279, "step": 202570 }, { "epoch": 1.2041775891482545, "grad_norm": 4.408444404602051, "learning_rate": 9.407887037034742e-06, "loss": 0.4129, "step": 202580 }, { "epoch": 1.2042370312249229, "grad_norm": 5.068039894104004, "learning_rate": 9.407789088762471e-06, "loss": 0.389, "step": 202590 }, { "epoch": 1.2042964733015913, "grad_norm": 4.80290412902832, "learning_rate": 9.407691132899463e-06, "loss": 0.3323, "step": 202600 }, { "epoch": 1.2043559153782597, "grad_norm": 6.331470966339111, "learning_rate": 9.407593169445884e-06, "loss": 0.4106, "step": 202610 }, { "epoch": 1.2044153574549281, "grad_norm": 5.384927749633789, "learning_rate": 9.407495198401903e-06, "loss": 0.4733, "step": 202620 }, { "epoch": 1.2044747995315965, "grad_norm": 4.446260452270508, "learning_rate": 9.407397219767691e-06, "loss": 0.3615, "step": 202630 }, { "epoch": 1.2045342416082647, "grad_norm": 4.47257137298584, "learning_rate": 9.407299233543414e-06, "loss": 0.3951, "step": 202640 }, { "epoch": 1.2045936836849331, "grad_norm": 6.563266754150391, "learning_rate": 9.407201239729241e-06, "loss": 0.3849, "step": 202650 }, { "epoch": 1.2046531257616016, "grad_norm": 5.671576023101807, "learning_rate": 9.407103238325344e-06, "loss": 0.3961, "step": 202660 }, { "epoch": 1.20471256783827, "grad_norm": 5.435807228088379, "learning_rate": 9.407005229331887e-06, "loss": 0.3949, "step": 202670 }, { "epoch": 1.2047720099149384, "grad_norm": 4.605526924133301, "learning_rate": 9.406907212749042e-06, "loss": 0.3713, "step": 202680 }, { "epoch": 1.2048314519916068, "grad_norm": 5.396780967712402, "learning_rate": 9.406809188576977e-06, "loss": 0.3947, "step": 202690 }, { "epoch": 1.2048908940682752, "grad_norm": 5.164566993713379, "learning_rate": 9.406711156815862e-06, "loss": 0.3524, "step": 202700 }, { "epoch": 1.2049503361449436, "grad_norm": 5.601476192474365, "learning_rate": 9.406613117465863e-06, "loss": 0.3665, "step": 202710 }, { "epoch": 1.205009778221612, "grad_norm": 4.436226844787598, "learning_rate": 9.406515070527151e-06, "loss": 0.3919, "step": 202720 }, { "epoch": 1.2050692202982805, "grad_norm": 4.308388710021973, "learning_rate": 9.406417015999893e-06, "loss": 0.3658, "step": 202730 }, { "epoch": 1.2051286623749486, "grad_norm": 5.485639572143555, "learning_rate": 9.406318953884262e-06, "loss": 0.4034, "step": 202740 }, { "epoch": 1.205188104451617, "grad_norm": 6.323779106140137, "learning_rate": 9.406220884180422e-06, "loss": 0.4596, "step": 202750 }, { "epoch": 1.2052475465282855, "grad_norm": 5.379349708557129, "learning_rate": 9.406122806888544e-06, "loss": 0.4186, "step": 202760 }, { "epoch": 1.2053069886049539, "grad_norm": 4.027956008911133, "learning_rate": 9.406024722008796e-06, "loss": 0.3643, "step": 202770 }, { "epoch": 1.2053664306816223, "grad_norm": 4.219271659851074, "learning_rate": 9.405926629541348e-06, "loss": 0.4491, "step": 202780 }, { "epoch": 1.2054258727582907, "grad_norm": 4.776740074157715, "learning_rate": 9.40582852948637e-06, "loss": 0.4049, "step": 202790 }, { "epoch": 1.2054853148349591, "grad_norm": 4.234004497528076, "learning_rate": 9.40573042184403e-06, "loss": 0.3664, "step": 202800 }, { "epoch": 1.2055447569116275, "grad_norm": 8.823311805725098, "learning_rate": 9.405632306614493e-06, "loss": 0.4187, "step": 202810 }, { "epoch": 1.2056041989882957, "grad_norm": 4.045548439025879, "learning_rate": 9.405534183797935e-06, "loss": 0.3926, "step": 202820 }, { "epoch": 1.2056636410649642, "grad_norm": 5.463229656219482, "learning_rate": 9.40543605339452e-06, "loss": 0.4088, "step": 202830 }, { "epoch": 1.2057230831416326, "grad_norm": 4.71874475479126, "learning_rate": 9.40533791540442e-06, "loss": 0.3426, "step": 202840 }, { "epoch": 1.205782525218301, "grad_norm": 4.411509037017822, "learning_rate": 9.405239769827801e-06, "loss": 0.395, "step": 202850 }, { "epoch": 1.2058419672949694, "grad_norm": 4.845405578613281, "learning_rate": 9.405141616664834e-06, "loss": 0.3582, "step": 202860 }, { "epoch": 1.2059014093716378, "grad_norm": 5.410036563873291, "learning_rate": 9.405043455915687e-06, "loss": 0.364, "step": 202870 }, { "epoch": 1.2059608514483062, "grad_norm": 5.1228132247924805, "learning_rate": 9.40494528758053e-06, "loss": 0.4001, "step": 202880 }, { "epoch": 1.2060202935249746, "grad_norm": 7.838979721069336, "learning_rate": 9.404847111659533e-06, "loss": 0.3977, "step": 202890 }, { "epoch": 1.206079735601643, "grad_norm": 4.480997085571289, "learning_rate": 9.40474892815286e-06, "loss": 0.4047, "step": 202900 }, { "epoch": 1.2061391776783115, "grad_norm": 5.845705986022949, "learning_rate": 9.404650737060688e-06, "loss": 0.4201, "step": 202910 }, { "epoch": 1.2061986197549799, "grad_norm": 4.242374897003174, "learning_rate": 9.40455253838318e-06, "loss": 0.4243, "step": 202920 }, { "epoch": 1.206258061831648, "grad_norm": 5.443394184112549, "learning_rate": 9.404454332120506e-06, "loss": 0.4047, "step": 202930 }, { "epoch": 1.2063175039083165, "grad_norm": 5.267441749572754, "learning_rate": 9.404356118272837e-06, "loss": 0.3731, "step": 202940 }, { "epoch": 1.206376945984985, "grad_norm": 3.6994681358337402, "learning_rate": 9.404257896840341e-06, "loss": 0.4292, "step": 202950 }, { "epoch": 1.2064363880616533, "grad_norm": 6.969283103942871, "learning_rate": 9.404159667823186e-06, "loss": 0.4538, "step": 202960 }, { "epoch": 1.2064958301383217, "grad_norm": 5.996601581573486, "learning_rate": 9.404061431221546e-06, "loss": 0.3733, "step": 202970 }, { "epoch": 1.2065552722149901, "grad_norm": 3.7177233695983887, "learning_rate": 9.403963187035585e-06, "loss": 0.4169, "step": 202980 }, { "epoch": 1.2066147142916586, "grad_norm": 4.559075832366943, "learning_rate": 9.403864935265474e-06, "loss": 0.3805, "step": 202990 }, { "epoch": 1.206674156368327, "grad_norm": 6.241567611694336, "learning_rate": 9.40376667591138e-06, "loss": 0.4331, "step": 203000 }, { "epoch": 1.2067335984449952, "grad_norm": 4.286059856414795, "learning_rate": 9.403668408973479e-06, "loss": 0.4236, "step": 203010 }, { "epoch": 1.2067930405216636, "grad_norm": 4.341630458831787, "learning_rate": 9.403570134451932e-06, "loss": 0.4118, "step": 203020 }, { "epoch": 1.206852482598332, "grad_norm": 5.62277364730835, "learning_rate": 9.403471852346913e-06, "loss": 0.394, "step": 203030 }, { "epoch": 1.2069119246750004, "grad_norm": 3.865219831466675, "learning_rate": 9.40337356265859e-06, "loss": 0.3746, "step": 203040 }, { "epoch": 1.2069713667516688, "grad_norm": 4.390082359313965, "learning_rate": 9.403275265387132e-06, "loss": 0.3498, "step": 203050 }, { "epoch": 1.2070308088283372, "grad_norm": 4.422875881195068, "learning_rate": 9.403176960532709e-06, "loss": 0.4457, "step": 203060 }, { "epoch": 1.2070902509050057, "grad_norm": 4.280606269836426, "learning_rate": 9.403078648095489e-06, "loss": 0.3677, "step": 203070 }, { "epoch": 1.207149692981674, "grad_norm": 5.153003692626953, "learning_rate": 9.402980328075642e-06, "loss": 0.3732, "step": 203080 }, { "epoch": 1.2072091350583425, "grad_norm": 5.11881160736084, "learning_rate": 9.402882000473339e-06, "loss": 0.4423, "step": 203090 }, { "epoch": 1.207268577135011, "grad_norm": 5.40344762802124, "learning_rate": 9.402783665288748e-06, "loss": 0.3921, "step": 203100 }, { "epoch": 1.207328019211679, "grad_norm": 6.807620048522949, "learning_rate": 9.402685322522036e-06, "loss": 0.4097, "step": 203110 }, { "epoch": 1.2073874612883475, "grad_norm": 6.477778911590576, "learning_rate": 9.402586972173375e-06, "loss": 0.3984, "step": 203120 }, { "epoch": 1.207446903365016, "grad_norm": 5.302927017211914, "learning_rate": 9.402488614242936e-06, "loss": 0.4152, "step": 203130 }, { "epoch": 1.2075063454416843, "grad_norm": 5.293636322021484, "learning_rate": 9.402390248730885e-06, "loss": 0.4038, "step": 203140 }, { "epoch": 1.2075657875183528, "grad_norm": 5.0718560218811035, "learning_rate": 9.402291875637392e-06, "loss": 0.3912, "step": 203150 }, { "epoch": 1.2076252295950212, "grad_norm": 3.794311761856079, "learning_rate": 9.402193494962627e-06, "loss": 0.4095, "step": 203160 }, { "epoch": 1.2076846716716896, "grad_norm": 3.9380509853363037, "learning_rate": 9.402095106706762e-06, "loss": 0.4092, "step": 203170 }, { "epoch": 1.207744113748358, "grad_norm": 5.425234317779541, "learning_rate": 9.401996710869963e-06, "loss": 0.4059, "step": 203180 }, { "epoch": 1.2078035558250262, "grad_norm": 5.4290056228637695, "learning_rate": 9.401898307452399e-06, "loss": 0.4185, "step": 203190 }, { "epoch": 1.2078629979016946, "grad_norm": 4.388041019439697, "learning_rate": 9.401799896454243e-06, "loss": 0.4354, "step": 203200 }, { "epoch": 1.207922439978363, "grad_norm": 6.245023250579834, "learning_rate": 9.40170147787566e-06, "loss": 0.392, "step": 203210 }, { "epoch": 1.2079818820550314, "grad_norm": 4.5970845222473145, "learning_rate": 9.401603051716823e-06, "loss": 0.3583, "step": 203220 }, { "epoch": 1.2080413241316998, "grad_norm": 4.103761672973633, "learning_rate": 9.401504617977902e-06, "loss": 0.3932, "step": 203230 }, { "epoch": 1.2081007662083683, "grad_norm": 5.58771276473999, "learning_rate": 9.401406176659063e-06, "loss": 0.3607, "step": 203240 }, { "epoch": 1.2081602082850367, "grad_norm": 3.2100882530212402, "learning_rate": 9.401307727760476e-06, "loss": 0.3774, "step": 203250 }, { "epoch": 1.208219650361705, "grad_norm": 3.691861152648926, "learning_rate": 9.401209271282314e-06, "loss": 0.3702, "step": 203260 }, { "epoch": 1.2082790924383735, "grad_norm": 5.597285747528076, "learning_rate": 9.401110807224745e-06, "loss": 0.4137, "step": 203270 }, { "epoch": 1.208338534515042, "grad_norm": 7.709561347961426, "learning_rate": 9.401012335587936e-06, "loss": 0.3918, "step": 203280 }, { "epoch": 1.2083979765917103, "grad_norm": 5.7493767738342285, "learning_rate": 9.40091385637206e-06, "loss": 0.4303, "step": 203290 }, { "epoch": 1.2084574186683785, "grad_norm": 5.244587421417236, "learning_rate": 9.400815369577286e-06, "loss": 0.4107, "step": 203300 }, { "epoch": 1.208516860745047, "grad_norm": 5.325454235076904, "learning_rate": 9.40071687520378e-06, "loss": 0.3813, "step": 203310 }, { "epoch": 1.2085763028217154, "grad_norm": 4.097288608551025, "learning_rate": 9.400618373251718e-06, "loss": 0.3991, "step": 203320 }, { "epoch": 1.2086357448983838, "grad_norm": 7.335484027862549, "learning_rate": 9.400519863721263e-06, "loss": 0.3988, "step": 203330 }, { "epoch": 1.2086951869750522, "grad_norm": 4.46091365814209, "learning_rate": 9.400421346612589e-06, "loss": 0.3558, "step": 203340 }, { "epoch": 1.2087546290517206, "grad_norm": 5.538710117340088, "learning_rate": 9.400322821925865e-06, "loss": 0.4222, "step": 203350 }, { "epoch": 1.208814071128389, "grad_norm": 5.370662689208984, "learning_rate": 9.400224289661259e-06, "loss": 0.3895, "step": 203360 }, { "epoch": 1.2088735132050574, "grad_norm": 5.657732963562012, "learning_rate": 9.400125749818942e-06, "loss": 0.402, "step": 203370 }, { "epoch": 1.2089329552817256, "grad_norm": 6.289825439453125, "learning_rate": 9.400027202399084e-06, "loss": 0.3798, "step": 203380 }, { "epoch": 1.208992397358394, "grad_norm": 4.25990104675293, "learning_rate": 9.399928647401855e-06, "loss": 0.4043, "step": 203390 }, { "epoch": 1.2090518394350624, "grad_norm": 6.86664342880249, "learning_rate": 9.399830084827422e-06, "loss": 0.426, "step": 203400 }, { "epoch": 1.2091112815117309, "grad_norm": 4.55226469039917, "learning_rate": 9.399731514675957e-06, "loss": 0.3905, "step": 203410 }, { "epoch": 1.2091707235883993, "grad_norm": 4.960278034210205, "learning_rate": 9.39963293694763e-06, "loss": 0.37, "step": 203420 }, { "epoch": 1.2092301656650677, "grad_norm": 5.1421356201171875, "learning_rate": 9.39953435164261e-06, "loss": 0.4169, "step": 203430 }, { "epoch": 1.209289607741736, "grad_norm": 4.492392539978027, "learning_rate": 9.399435758761066e-06, "loss": 0.3959, "step": 203440 }, { "epoch": 1.2093490498184045, "grad_norm": 4.139105319976807, "learning_rate": 9.39933715830317e-06, "loss": 0.4292, "step": 203450 }, { "epoch": 1.209408491895073, "grad_norm": 5.583295822143555, "learning_rate": 9.39923855026909e-06, "loss": 0.4512, "step": 203460 }, { "epoch": 1.2094679339717413, "grad_norm": 4.433524131774902, "learning_rate": 9.399139934658996e-06, "loss": 0.3636, "step": 203470 }, { "epoch": 1.2095273760484095, "grad_norm": 5.756192207336426, "learning_rate": 9.399041311473057e-06, "loss": 0.4343, "step": 203480 }, { "epoch": 1.209586818125078, "grad_norm": 3.932488203048706, "learning_rate": 9.398942680711447e-06, "loss": 0.415, "step": 203490 }, { "epoch": 1.2096462602017464, "grad_norm": 5.928318977355957, "learning_rate": 9.398844042374332e-06, "loss": 0.3813, "step": 203500 }, { "epoch": 1.2097057022784148, "grad_norm": 5.103134632110596, "learning_rate": 9.39874539646188e-06, "loss": 0.3861, "step": 203510 }, { "epoch": 1.2097651443550832, "grad_norm": 4.2529826164245605, "learning_rate": 9.398646742974266e-06, "loss": 0.3488, "step": 203520 }, { "epoch": 1.2098245864317516, "grad_norm": 5.287014961242676, "learning_rate": 9.398548081911658e-06, "loss": 0.3784, "step": 203530 }, { "epoch": 1.20988402850842, "grad_norm": 4.818619728088379, "learning_rate": 9.398449413274224e-06, "loss": 0.4203, "step": 203540 }, { "epoch": 1.2099434705850884, "grad_norm": 6.030760288238525, "learning_rate": 9.398350737062136e-06, "loss": 0.385, "step": 203550 }, { "epoch": 1.2100029126617566, "grad_norm": 7.450601100921631, "learning_rate": 9.398252053275563e-06, "loss": 0.4231, "step": 203560 }, { "epoch": 1.210062354738425, "grad_norm": 4.888775825500488, "learning_rate": 9.398153361914675e-06, "loss": 0.4087, "step": 203570 }, { "epoch": 1.2101217968150935, "grad_norm": 5.726640701293945, "learning_rate": 9.398054662979642e-06, "loss": 0.4163, "step": 203580 }, { "epoch": 1.2101812388917619, "grad_norm": 4.371438026428223, "learning_rate": 9.397955956470633e-06, "loss": 0.376, "step": 203590 }, { "epoch": 1.2102406809684303, "grad_norm": 4.542349338531494, "learning_rate": 9.397857242387822e-06, "loss": 0.4187, "step": 203600 }, { "epoch": 1.2103001230450987, "grad_norm": 5.293537139892578, "learning_rate": 9.397758520731372e-06, "loss": 0.4305, "step": 203610 }, { "epoch": 1.2103595651217671, "grad_norm": 5.667083740234375, "learning_rate": 9.397659791501461e-06, "loss": 0.3941, "step": 203620 }, { "epoch": 1.2104190071984355, "grad_norm": 5.445878505706787, "learning_rate": 9.397561054698255e-06, "loss": 0.4083, "step": 203630 }, { "epoch": 1.210478449275104, "grad_norm": 4.27038049697876, "learning_rate": 9.397462310321922e-06, "loss": 0.3848, "step": 203640 }, { "epoch": 1.2105378913517724, "grad_norm": 5.137112140655518, "learning_rate": 9.397363558372635e-06, "loss": 0.4003, "step": 203650 }, { "epoch": 1.2105973334284408, "grad_norm": 5.712766170501709, "learning_rate": 9.397264798850563e-06, "loss": 0.4484, "step": 203660 }, { "epoch": 1.210656775505109, "grad_norm": 4.951687335968018, "learning_rate": 9.397166031755876e-06, "loss": 0.4147, "step": 203670 }, { "epoch": 1.2107162175817774, "grad_norm": 4.422049045562744, "learning_rate": 9.397067257088745e-06, "loss": 0.3909, "step": 203680 }, { "epoch": 1.2107756596584458, "grad_norm": 5.752038955688477, "learning_rate": 9.39696847484934e-06, "loss": 0.3818, "step": 203690 }, { "epoch": 1.2108351017351142, "grad_norm": 4.47658109664917, "learning_rate": 9.39686968503783e-06, "loss": 0.4248, "step": 203700 }, { "epoch": 1.2108945438117826, "grad_norm": 5.941658020019531, "learning_rate": 9.396770887654387e-06, "loss": 0.3933, "step": 203710 }, { "epoch": 1.210953985888451, "grad_norm": 6.155580520629883, "learning_rate": 9.396672082699179e-06, "loss": 0.4002, "step": 203720 }, { "epoch": 1.2110134279651195, "grad_norm": 5.554340362548828, "learning_rate": 9.396573270172375e-06, "loss": 0.4058, "step": 203730 }, { "epoch": 1.2110728700417879, "grad_norm": 7.1461591720581055, "learning_rate": 9.39647445007415e-06, "loss": 0.4001, "step": 203740 }, { "epoch": 1.211132312118456, "grad_norm": 4.821164131164551, "learning_rate": 9.39637562240467e-06, "loss": 0.4196, "step": 203750 }, { "epoch": 1.2111917541951245, "grad_norm": 5.605015277862549, "learning_rate": 9.396276787164107e-06, "loss": 0.3411, "step": 203760 }, { "epoch": 1.211251196271793, "grad_norm": 5.194195747375488, "learning_rate": 9.396177944352632e-06, "loss": 0.3779, "step": 203770 }, { "epoch": 1.2113106383484613, "grad_norm": 5.081545352935791, "learning_rate": 9.396079093970413e-06, "loss": 0.4248, "step": 203780 }, { "epoch": 1.2113700804251297, "grad_norm": 6.46803092956543, "learning_rate": 9.395980236017621e-06, "loss": 0.409, "step": 203790 }, { "epoch": 1.2114295225017981, "grad_norm": 4.668968677520752, "learning_rate": 9.395881370494428e-06, "loss": 0.4262, "step": 203800 }, { "epoch": 1.2114889645784666, "grad_norm": 4.856701850891113, "learning_rate": 9.395782497401001e-06, "loss": 0.4224, "step": 203810 }, { "epoch": 1.211548406655135, "grad_norm": 7.306987762451172, "learning_rate": 9.395683616737514e-06, "loss": 0.3873, "step": 203820 }, { "epoch": 1.2116078487318034, "grad_norm": 6.212204456329346, "learning_rate": 9.395584728504132e-06, "loss": 0.4194, "step": 203830 }, { "epoch": 1.2116672908084718, "grad_norm": 4.346816062927246, "learning_rate": 9.395485832701032e-06, "loss": 0.4266, "step": 203840 }, { "epoch": 1.21172673288514, "grad_norm": 5.532627105712891, "learning_rate": 9.395386929328378e-06, "loss": 0.3971, "step": 203850 }, { "epoch": 1.2117861749618084, "grad_norm": 5.674691200256348, "learning_rate": 9.395288018386346e-06, "loss": 0.3928, "step": 203860 }, { "epoch": 1.2118456170384768, "grad_norm": 5.908758163452148, "learning_rate": 9.395189099875103e-06, "loss": 0.4309, "step": 203870 }, { "epoch": 1.2119050591151452, "grad_norm": 5.2896223068237305, "learning_rate": 9.395090173794818e-06, "loss": 0.3718, "step": 203880 }, { "epoch": 1.2119645011918136, "grad_norm": 4.768351078033447, "learning_rate": 9.394991240145666e-06, "loss": 0.4293, "step": 203890 }, { "epoch": 1.212023943268482, "grad_norm": 6.083907127380371, "learning_rate": 9.394892298927814e-06, "loss": 0.4148, "step": 203900 }, { "epoch": 1.2120833853451505, "grad_norm": 3.919384002685547, "learning_rate": 9.39479335014143e-06, "loss": 0.3501, "step": 203910 }, { "epoch": 1.212142827421819, "grad_norm": 6.798941135406494, "learning_rate": 9.394694393786691e-06, "loss": 0.3781, "step": 203920 }, { "epoch": 1.212202269498487, "grad_norm": 5.485935211181641, "learning_rate": 9.394595429863764e-06, "loss": 0.3998, "step": 203930 }, { "epoch": 1.2122617115751555, "grad_norm": 4.696234226226807, "learning_rate": 9.394496458372817e-06, "loss": 0.4256, "step": 203940 }, { "epoch": 1.212321153651824, "grad_norm": 4.980212211608887, "learning_rate": 9.394397479314023e-06, "loss": 0.385, "step": 203950 }, { "epoch": 1.2123805957284923, "grad_norm": 4.491605281829834, "learning_rate": 9.394298492687554e-06, "loss": 0.4159, "step": 203960 }, { "epoch": 1.2124400378051607, "grad_norm": 4.419707298278809, "learning_rate": 9.394199498493578e-06, "loss": 0.3818, "step": 203970 }, { "epoch": 1.2124994798818292, "grad_norm": 4.659236431121826, "learning_rate": 9.394100496732266e-06, "loss": 0.387, "step": 203980 }, { "epoch": 1.2125589219584976, "grad_norm": 6.8887858390808105, "learning_rate": 9.394001487403788e-06, "loss": 0.3943, "step": 203990 }, { "epoch": 1.212618364035166, "grad_norm": 4.177188873291016, "learning_rate": 9.393902470508315e-06, "loss": 0.3766, "step": 204000 }, { "epoch": 1.2126778061118344, "grad_norm": 4.552728652954102, "learning_rate": 9.39380344604602e-06, "loss": 0.3739, "step": 204010 }, { "epoch": 1.2127372481885028, "grad_norm": 3.674765110015869, "learning_rate": 9.393704414017069e-06, "loss": 0.3815, "step": 204020 }, { "epoch": 1.2127966902651712, "grad_norm": 7.624352931976318, "learning_rate": 9.393605374421636e-06, "loss": 0.3792, "step": 204030 }, { "epoch": 1.2128561323418394, "grad_norm": 3.5038046836853027, "learning_rate": 9.393506327259889e-06, "loss": 0.363, "step": 204040 }, { "epoch": 1.2129155744185078, "grad_norm": 6.811939239501953, "learning_rate": 9.393407272532e-06, "loss": 0.4068, "step": 204050 }, { "epoch": 1.2129750164951763, "grad_norm": 6.2381463050842285, "learning_rate": 9.393308210238142e-06, "loss": 0.4003, "step": 204060 }, { "epoch": 1.2130344585718447, "grad_norm": 4.993310451507568, "learning_rate": 9.39320914037848e-06, "loss": 0.3896, "step": 204070 }, { "epoch": 1.213093900648513, "grad_norm": 3.8216676712036133, "learning_rate": 9.393110062953188e-06, "loss": 0.3648, "step": 204080 }, { "epoch": 1.2131533427251815, "grad_norm": 4.4079060554504395, "learning_rate": 9.393010977962439e-06, "loss": 0.4029, "step": 204090 }, { "epoch": 1.21321278480185, "grad_norm": 4.580311298370361, "learning_rate": 9.392911885406397e-06, "loss": 0.4278, "step": 204100 }, { "epoch": 1.2132722268785183, "grad_norm": 5.831902027130127, "learning_rate": 9.392812785285239e-06, "loss": 0.3585, "step": 204110 }, { "epoch": 1.2133316689551865, "grad_norm": 5.352039813995361, "learning_rate": 9.392713677599132e-06, "loss": 0.4104, "step": 204120 }, { "epoch": 1.213391111031855, "grad_norm": 5.27921199798584, "learning_rate": 9.39261456234825e-06, "loss": 0.4069, "step": 204130 }, { "epoch": 1.2134505531085233, "grad_norm": 3.8324573040008545, "learning_rate": 9.39251543953276e-06, "loss": 0.3952, "step": 204140 }, { "epoch": 1.2135099951851918, "grad_norm": 5.267551898956299, "learning_rate": 9.392416309152833e-06, "loss": 0.3564, "step": 204150 }, { "epoch": 1.2135694372618602, "grad_norm": 3.119077205657959, "learning_rate": 9.392317171208645e-06, "loss": 0.3947, "step": 204160 }, { "epoch": 1.2136288793385286, "grad_norm": 4.734192371368408, "learning_rate": 9.392218025700359e-06, "loss": 0.3718, "step": 204170 }, { "epoch": 1.213688321415197, "grad_norm": 5.724745750427246, "learning_rate": 9.39211887262815e-06, "loss": 0.3819, "step": 204180 }, { "epoch": 1.2137477634918654, "grad_norm": 7.432494640350342, "learning_rate": 9.392019711992192e-06, "loss": 0.4269, "step": 204190 }, { "epoch": 1.2138072055685338, "grad_norm": 6.05915641784668, "learning_rate": 9.391920543792647e-06, "loss": 0.3933, "step": 204200 }, { "epoch": 1.2138666476452022, "grad_norm": 4.1341681480407715, "learning_rate": 9.391821368029694e-06, "loss": 0.3733, "step": 204210 }, { "epoch": 1.2139260897218704, "grad_norm": 6.067148685455322, "learning_rate": 9.3917221847035e-06, "loss": 0.4199, "step": 204220 }, { "epoch": 1.2139855317985389, "grad_norm": 5.471443176269531, "learning_rate": 9.391622993814235e-06, "loss": 0.4097, "step": 204230 }, { "epoch": 1.2140449738752073, "grad_norm": 6.028655052185059, "learning_rate": 9.391523795362072e-06, "loss": 0.4082, "step": 204240 }, { "epoch": 1.2141044159518757, "grad_norm": 5.863046169281006, "learning_rate": 9.391424589347182e-06, "loss": 0.375, "step": 204250 }, { "epoch": 1.214163858028544, "grad_norm": 5.798050403594971, "learning_rate": 9.391325375769732e-06, "loss": 0.3915, "step": 204260 }, { "epoch": 1.2142233001052125, "grad_norm": 5.372092247009277, "learning_rate": 9.391226154629898e-06, "loss": 0.4209, "step": 204270 }, { "epoch": 1.214282742181881, "grad_norm": 7.081620216369629, "learning_rate": 9.391126925927849e-06, "loss": 0.4264, "step": 204280 }, { "epoch": 1.2143421842585493, "grad_norm": 6.726443767547607, "learning_rate": 9.391027689663756e-06, "loss": 0.4029, "step": 204290 }, { "epoch": 1.2144016263352175, "grad_norm": 5.970205783843994, "learning_rate": 9.390928445837787e-06, "loss": 0.4232, "step": 204300 }, { "epoch": 1.214461068411886, "grad_norm": 6.331360816955566, "learning_rate": 9.390829194450117e-06, "loss": 0.3591, "step": 204310 }, { "epoch": 1.2145205104885544, "grad_norm": 3.5595450401306152, "learning_rate": 9.390729935500915e-06, "loss": 0.4311, "step": 204320 }, { "epoch": 1.2145799525652228, "grad_norm": 4.736912250518799, "learning_rate": 9.390630668990352e-06, "loss": 0.3566, "step": 204330 }, { "epoch": 1.2146393946418912, "grad_norm": 5.839194297790527, "learning_rate": 9.390531394918599e-06, "loss": 0.422, "step": 204340 }, { "epoch": 1.2146988367185596, "grad_norm": 5.646596908569336, "learning_rate": 9.390432113285827e-06, "loss": 0.4151, "step": 204350 }, { "epoch": 1.214758278795228, "grad_norm": 4.7780022621154785, "learning_rate": 9.390332824092208e-06, "loss": 0.384, "step": 204360 }, { "epoch": 1.2148177208718964, "grad_norm": 5.898469924926758, "learning_rate": 9.39023352733791e-06, "loss": 0.4176, "step": 204370 }, { "epoch": 1.2148771629485648, "grad_norm": 4.862727165222168, "learning_rate": 9.390134223023107e-06, "loss": 0.3603, "step": 204380 }, { "epoch": 1.2149366050252333, "grad_norm": 4.929337978363037, "learning_rate": 9.390034911147969e-06, "loss": 0.3774, "step": 204390 }, { "epoch": 1.2149960471019015, "grad_norm": 5.108541011810303, "learning_rate": 9.389935591712667e-06, "loss": 0.4103, "step": 204400 }, { "epoch": 1.2150554891785699, "grad_norm": 5.736443996429443, "learning_rate": 9.389836264717374e-06, "loss": 0.4061, "step": 204410 }, { "epoch": 1.2151149312552383, "grad_norm": 4.797802448272705, "learning_rate": 9.389736930162256e-06, "loss": 0.3961, "step": 204420 }, { "epoch": 1.2151743733319067, "grad_norm": 4.763479232788086, "learning_rate": 9.38963758804749e-06, "loss": 0.4167, "step": 204430 }, { "epoch": 1.2152338154085751, "grad_norm": 4.849771499633789, "learning_rate": 9.389538238373243e-06, "loss": 0.4047, "step": 204440 }, { "epoch": 1.2152932574852435, "grad_norm": 5.139297008514404, "learning_rate": 9.389438881139687e-06, "loss": 0.427, "step": 204450 }, { "epoch": 1.215352699561912, "grad_norm": 6.327341079711914, "learning_rate": 9.389339516346995e-06, "loss": 0.4265, "step": 204460 }, { "epoch": 1.2154121416385804, "grad_norm": 6.550021648406982, "learning_rate": 9.389240143995334e-06, "loss": 0.4448, "step": 204470 }, { "epoch": 1.2154715837152488, "grad_norm": 7.910645484924316, "learning_rate": 9.389140764084882e-06, "loss": 0.4152, "step": 204480 }, { "epoch": 1.215531025791917, "grad_norm": 6.7497124671936035, "learning_rate": 9.389041376615802e-06, "loss": 0.4217, "step": 204490 }, { "epoch": 1.2155904678685854, "grad_norm": 5.01019287109375, "learning_rate": 9.388941981588271e-06, "loss": 0.3597, "step": 204500 }, { "epoch": 1.2156499099452538, "grad_norm": 4.658982276916504, "learning_rate": 9.388842579002457e-06, "loss": 0.3898, "step": 204510 }, { "epoch": 1.2157093520219222, "grad_norm": 5.132532119750977, "learning_rate": 9.388743168858533e-06, "loss": 0.3498, "step": 204520 }, { "epoch": 1.2157687940985906, "grad_norm": 5.181612968444824, "learning_rate": 9.388643751156669e-06, "loss": 0.3918, "step": 204530 }, { "epoch": 1.215828236175259, "grad_norm": 4.332919597625732, "learning_rate": 9.388544325897038e-06, "loss": 0.3988, "step": 204540 }, { "epoch": 1.2158876782519275, "grad_norm": 6.4681549072265625, "learning_rate": 9.388444893079808e-06, "loss": 0.3625, "step": 204550 }, { "epoch": 1.2159471203285959, "grad_norm": 7.222527503967285, "learning_rate": 9.388345452705155e-06, "loss": 0.3977, "step": 204560 }, { "epoch": 1.2160065624052643, "grad_norm": 5.749591827392578, "learning_rate": 9.388246004773248e-06, "loss": 0.4129, "step": 204570 }, { "epoch": 1.2160660044819327, "grad_norm": 4.800492763519287, "learning_rate": 9.388146549284254e-06, "loss": 0.3967, "step": 204580 }, { "epoch": 1.2161254465586009, "grad_norm": 5.8275837898254395, "learning_rate": 9.388047086238351e-06, "loss": 0.3842, "step": 204590 }, { "epoch": 1.2161848886352693, "grad_norm": 6.904587268829346, "learning_rate": 9.387947615635707e-06, "loss": 0.4171, "step": 204600 }, { "epoch": 1.2162443307119377, "grad_norm": 5.480550765991211, "learning_rate": 9.387848137476491e-06, "loss": 0.3799, "step": 204610 }, { "epoch": 1.2163037727886061, "grad_norm": 4.705132961273193, "learning_rate": 9.38774865176088e-06, "loss": 0.4033, "step": 204620 }, { "epoch": 1.2163632148652745, "grad_norm": 5.883053302764893, "learning_rate": 9.387649158489042e-06, "loss": 0.4019, "step": 204630 }, { "epoch": 1.216422656941943, "grad_norm": 7.068432807922363, "learning_rate": 9.387549657661148e-06, "loss": 0.403, "step": 204640 }, { "epoch": 1.2164820990186114, "grad_norm": 4.578166484832764, "learning_rate": 9.38745014927737e-06, "loss": 0.4286, "step": 204650 }, { "epoch": 1.2165415410952798, "grad_norm": 4.726048946380615, "learning_rate": 9.387350633337879e-06, "loss": 0.405, "step": 204660 }, { "epoch": 1.216600983171948, "grad_norm": 5.418725967407227, "learning_rate": 9.387251109842848e-06, "loss": 0.4234, "step": 204670 }, { "epoch": 1.2166604252486164, "grad_norm": 5.462291240692139, "learning_rate": 9.387151578792444e-06, "loss": 0.3468, "step": 204680 }, { "epoch": 1.2167198673252848, "grad_norm": 4.86016845703125, "learning_rate": 9.387052040186845e-06, "loss": 0.3689, "step": 204690 }, { "epoch": 1.2167793094019532, "grad_norm": 4.953678131103516, "learning_rate": 9.386952494026217e-06, "loss": 0.3954, "step": 204700 }, { "epoch": 1.2168387514786216, "grad_norm": 5.524608612060547, "learning_rate": 9.386852940310733e-06, "loss": 0.3561, "step": 204710 }, { "epoch": 1.21689819355529, "grad_norm": 4.403926849365234, "learning_rate": 9.386753379040567e-06, "loss": 0.3737, "step": 204720 }, { "epoch": 1.2169576356319585, "grad_norm": 4.946287155151367, "learning_rate": 9.386653810215887e-06, "loss": 0.4037, "step": 204730 }, { "epoch": 1.2170170777086269, "grad_norm": 4.675740718841553, "learning_rate": 9.386554233836866e-06, "loss": 0.4013, "step": 204740 }, { "epoch": 1.2170765197852953, "grad_norm": 6.730678558349609, "learning_rate": 9.386454649903674e-06, "loss": 0.3974, "step": 204750 }, { "epoch": 1.2171359618619637, "grad_norm": 5.083139896392822, "learning_rate": 9.386355058416485e-06, "loss": 0.4103, "step": 204760 }, { "epoch": 1.217195403938632, "grad_norm": 5.102785110473633, "learning_rate": 9.386255459375468e-06, "loss": 0.4, "step": 204770 }, { "epoch": 1.2172548460153003, "grad_norm": 5.486025333404541, "learning_rate": 9.386155852780798e-06, "loss": 0.3838, "step": 204780 }, { "epoch": 1.2173142880919687, "grad_norm": 4.703861713409424, "learning_rate": 9.386056238632642e-06, "loss": 0.3536, "step": 204790 }, { "epoch": 1.2173737301686371, "grad_norm": 5.294278621673584, "learning_rate": 9.385956616931176e-06, "loss": 0.4561, "step": 204800 }, { "epoch": 1.2174331722453056, "grad_norm": 4.541928291320801, "learning_rate": 9.385856987676567e-06, "loss": 0.3377, "step": 204810 }, { "epoch": 1.217492614321974, "grad_norm": 6.289568901062012, "learning_rate": 9.38575735086899e-06, "loss": 0.3943, "step": 204820 }, { "epoch": 1.2175520563986424, "grad_norm": 3.297508716583252, "learning_rate": 9.385657706508616e-06, "loss": 0.3696, "step": 204830 }, { "epoch": 1.2176114984753108, "grad_norm": 6.042461395263672, "learning_rate": 9.385558054595616e-06, "loss": 0.4291, "step": 204840 }, { "epoch": 1.2176709405519792, "grad_norm": 4.8980183601379395, "learning_rate": 9.385458395130162e-06, "loss": 0.3824, "step": 204850 }, { "epoch": 1.2177303826286474, "grad_norm": 5.946195125579834, "learning_rate": 9.385358728112423e-06, "loss": 0.4231, "step": 204860 }, { "epoch": 1.2177898247053158, "grad_norm": 6.0851521492004395, "learning_rate": 9.385259053542576e-06, "loss": 0.4136, "step": 204870 }, { "epoch": 1.2178492667819842, "grad_norm": 4.358853816986084, "learning_rate": 9.385159371420789e-06, "loss": 0.3581, "step": 204880 }, { "epoch": 1.2179087088586527, "grad_norm": 3.9963607788085938, "learning_rate": 9.385059681747233e-06, "loss": 0.3908, "step": 204890 }, { "epoch": 1.217968150935321, "grad_norm": 5.544698238372803, "learning_rate": 9.384959984522082e-06, "loss": 0.3911, "step": 204900 }, { "epoch": 1.2180275930119895, "grad_norm": 4.802209377288818, "learning_rate": 9.384860279745507e-06, "loss": 0.389, "step": 204910 }, { "epoch": 1.218087035088658, "grad_norm": 5.0240325927734375, "learning_rate": 9.384760567417679e-06, "loss": 0.4292, "step": 204920 }, { "epoch": 1.2181464771653263, "grad_norm": 4.499625205993652, "learning_rate": 9.38466084753877e-06, "loss": 0.4482, "step": 204930 }, { "epoch": 1.2182059192419947, "grad_norm": 5.395695686340332, "learning_rate": 9.384561120108953e-06, "loss": 0.3858, "step": 204940 }, { "epoch": 1.2182653613186631, "grad_norm": 5.625587463378906, "learning_rate": 9.384461385128396e-06, "loss": 0.3765, "step": 204950 }, { "epoch": 1.2183248033953313, "grad_norm": 4.795146465301514, "learning_rate": 9.384361642597276e-06, "loss": 0.4059, "step": 204960 }, { "epoch": 1.2183842454719997, "grad_norm": 4.573817729949951, "learning_rate": 9.38426189251576e-06, "loss": 0.4271, "step": 204970 }, { "epoch": 1.2184436875486682, "grad_norm": 5.1312947273254395, "learning_rate": 9.384162134884024e-06, "loss": 0.3727, "step": 204980 }, { "epoch": 1.2185031296253366, "grad_norm": 4.876213550567627, "learning_rate": 9.384062369702236e-06, "loss": 0.3968, "step": 204990 }, { "epoch": 1.218562571702005, "grad_norm": 5.06065034866333, "learning_rate": 9.38396259697057e-06, "loss": 0.3906, "step": 205000 }, { "epoch": 1.2186220137786734, "grad_norm": 5.8809814453125, "learning_rate": 9.383862816689198e-06, "loss": 0.4432, "step": 205010 }, { "epoch": 1.2186814558553418, "grad_norm": 6.399606704711914, "learning_rate": 9.38376302885829e-06, "loss": 0.4044, "step": 205020 }, { "epoch": 1.2187408979320102, "grad_norm": 4.4625091552734375, "learning_rate": 9.38366323347802e-06, "loss": 0.4399, "step": 205030 }, { "epoch": 1.2188003400086784, "grad_norm": 7.49110746383667, "learning_rate": 9.38356343054856e-06, "loss": 0.3906, "step": 205040 }, { "epoch": 1.2188597820853468, "grad_norm": 5.641273498535156, "learning_rate": 9.383463620070077e-06, "loss": 0.4531, "step": 205050 }, { "epoch": 1.2189192241620153, "grad_norm": 4.583201885223389, "learning_rate": 9.38336380204275e-06, "loss": 0.3944, "step": 205060 }, { "epoch": 1.2189786662386837, "grad_norm": 5.5761637687683105, "learning_rate": 9.383263976466745e-06, "loss": 0.4462, "step": 205070 }, { "epoch": 1.219038108315352, "grad_norm": 4.049483776092529, "learning_rate": 9.383164143342239e-06, "loss": 0.4351, "step": 205080 }, { "epoch": 1.2190975503920205, "grad_norm": 5.706693649291992, "learning_rate": 9.3830643026694e-06, "loss": 0.3864, "step": 205090 }, { "epoch": 1.219156992468689, "grad_norm": 4.762480735778809, "learning_rate": 9.3829644544484e-06, "loss": 0.4044, "step": 205100 }, { "epoch": 1.2192164345453573, "grad_norm": 5.147640705108643, "learning_rate": 9.382864598679415e-06, "loss": 0.3646, "step": 205110 }, { "epoch": 1.2192758766220257, "grad_norm": 6.549318790435791, "learning_rate": 9.382764735362613e-06, "loss": 0.3963, "step": 205120 }, { "epoch": 1.2193353186986942, "grad_norm": 4.106494426727295, "learning_rate": 9.382664864498166e-06, "loss": 0.3935, "step": 205130 }, { "epoch": 1.2193947607753624, "grad_norm": 5.860292434692383, "learning_rate": 9.382564986086249e-06, "loss": 0.4151, "step": 205140 }, { "epoch": 1.2194542028520308, "grad_norm": 5.369646072387695, "learning_rate": 9.382465100127032e-06, "loss": 0.3876, "step": 205150 }, { "epoch": 1.2195136449286992, "grad_norm": 4.5488433837890625, "learning_rate": 9.382365206620685e-06, "loss": 0.3657, "step": 205160 }, { "epoch": 1.2195730870053676, "grad_norm": 4.454870700836182, "learning_rate": 9.382265305567384e-06, "loss": 0.3995, "step": 205170 }, { "epoch": 1.219632529082036, "grad_norm": 7.412030220031738, "learning_rate": 9.3821653969673e-06, "loss": 0.3907, "step": 205180 }, { "epoch": 1.2196919711587044, "grad_norm": 4.663792610168457, "learning_rate": 9.382065480820604e-06, "loss": 0.385, "step": 205190 }, { "epoch": 1.2197514132353728, "grad_norm": 5.07957124710083, "learning_rate": 9.381965557127466e-06, "loss": 0.3759, "step": 205200 }, { "epoch": 1.2198108553120413, "grad_norm": 4.960376262664795, "learning_rate": 9.381865625888062e-06, "loss": 0.4115, "step": 205210 }, { "epoch": 1.2198702973887097, "grad_norm": 5.784944534301758, "learning_rate": 9.381765687102564e-06, "loss": 0.3461, "step": 205220 }, { "epoch": 1.2199297394653779, "grad_norm": 5.622802257537842, "learning_rate": 9.381665740771142e-06, "loss": 0.4173, "step": 205230 }, { "epoch": 1.2199891815420463, "grad_norm": 7.202266693115234, "learning_rate": 9.381565786893966e-06, "loss": 0.4014, "step": 205240 }, { "epoch": 1.2200486236187147, "grad_norm": 6.134061336517334, "learning_rate": 9.381465825471214e-06, "loss": 0.3945, "step": 205250 }, { "epoch": 1.220108065695383, "grad_norm": 6.267488956451416, "learning_rate": 9.381365856503056e-06, "loss": 0.3972, "step": 205260 }, { "epoch": 1.2201675077720515, "grad_norm": 4.012171268463135, "learning_rate": 9.381265879989661e-06, "loss": 0.3984, "step": 205270 }, { "epoch": 1.22022694984872, "grad_norm": 5.344106674194336, "learning_rate": 9.381165895931204e-06, "loss": 0.3668, "step": 205280 }, { "epoch": 1.2202863919253883, "grad_norm": 4.0656938552856445, "learning_rate": 9.381065904327855e-06, "loss": 0.3708, "step": 205290 }, { "epoch": 1.2203458340020568, "grad_norm": 4.307458400726318, "learning_rate": 9.38096590517979e-06, "loss": 0.3803, "step": 205300 }, { "epoch": 1.2204052760787252, "grad_norm": 6.385595798492432, "learning_rate": 9.380865898487178e-06, "loss": 0.4159, "step": 205310 }, { "epoch": 1.2204647181553936, "grad_norm": 5.595812797546387, "learning_rate": 9.380765884250192e-06, "loss": 0.4135, "step": 205320 }, { "epoch": 1.2205241602320618, "grad_norm": 4.68387508392334, "learning_rate": 9.380665862469005e-06, "loss": 0.3983, "step": 205330 }, { "epoch": 1.2205836023087302, "grad_norm": 5.35486364364624, "learning_rate": 9.38056583314379e-06, "loss": 0.3876, "step": 205340 }, { "epoch": 1.2206430443853986, "grad_norm": 4.5647053718566895, "learning_rate": 9.380465796274715e-06, "loss": 0.3996, "step": 205350 }, { "epoch": 1.220702486462067, "grad_norm": 6.1538286209106445, "learning_rate": 9.380365751861957e-06, "loss": 0.4477, "step": 205360 }, { "epoch": 1.2207619285387354, "grad_norm": 4.29074764251709, "learning_rate": 9.380265699905686e-06, "loss": 0.3741, "step": 205370 }, { "epoch": 1.2208213706154039, "grad_norm": 4.1481781005859375, "learning_rate": 9.380165640406075e-06, "loss": 0.4031, "step": 205380 }, { "epoch": 1.2208808126920723, "grad_norm": 4.909923076629639, "learning_rate": 9.380065573363296e-06, "loss": 0.399, "step": 205390 }, { "epoch": 1.2209402547687407, "grad_norm": 5.381598472595215, "learning_rate": 9.379965498777522e-06, "loss": 0.387, "step": 205400 }, { "epoch": 1.2209996968454089, "grad_norm": 4.38757848739624, "learning_rate": 9.379865416648923e-06, "loss": 0.348, "step": 205410 }, { "epoch": 1.2210591389220773, "grad_norm": 4.584015369415283, "learning_rate": 9.379765326977674e-06, "loss": 0.3947, "step": 205420 }, { "epoch": 1.2211185809987457, "grad_norm": 4.830680847167969, "learning_rate": 9.379665229763948e-06, "loss": 0.3798, "step": 205430 }, { "epoch": 1.2211780230754141, "grad_norm": 4.670444011688232, "learning_rate": 9.379565125007916e-06, "loss": 0.3538, "step": 205440 }, { "epoch": 1.2212374651520825, "grad_norm": 4.713510036468506, "learning_rate": 9.379465012709748e-06, "loss": 0.4264, "step": 205450 }, { "epoch": 1.221296907228751, "grad_norm": 5.656538486480713, "learning_rate": 9.37936489286962e-06, "loss": 0.4152, "step": 205460 }, { "epoch": 1.2213563493054194, "grad_norm": 5.590686321258545, "learning_rate": 9.379264765487703e-06, "loss": 0.3775, "step": 205470 }, { "epoch": 1.2214157913820878, "grad_norm": 5.4747724533081055, "learning_rate": 9.37916463056417e-06, "loss": 0.3805, "step": 205480 }, { "epoch": 1.2214752334587562, "grad_norm": 4.450954437255859, "learning_rate": 9.379064488099193e-06, "loss": 0.4019, "step": 205490 }, { "epoch": 1.2215346755354246, "grad_norm": 4.813657283782959, "learning_rate": 9.378964338092944e-06, "loss": 0.4184, "step": 205500 }, { "epoch": 1.2215941176120928, "grad_norm": 4.91008186340332, "learning_rate": 9.378864180545597e-06, "loss": 0.4321, "step": 205510 }, { "epoch": 1.2216535596887612, "grad_norm": 5.891327857971191, "learning_rate": 9.378764015457322e-06, "loss": 0.4216, "step": 205520 }, { "epoch": 1.2217130017654296, "grad_norm": 5.393025875091553, "learning_rate": 9.378663842828294e-06, "loss": 0.4061, "step": 205530 }, { "epoch": 1.221772443842098, "grad_norm": 5.005898475646973, "learning_rate": 9.378563662658683e-06, "loss": 0.4121, "step": 205540 }, { "epoch": 1.2218318859187665, "grad_norm": 5.381773948669434, "learning_rate": 9.378463474948664e-06, "loss": 0.4684, "step": 205550 }, { "epoch": 1.2218913279954349, "grad_norm": 5.783541679382324, "learning_rate": 9.378363279698408e-06, "loss": 0.3844, "step": 205560 }, { "epoch": 1.2219507700721033, "grad_norm": 6.599943161010742, "learning_rate": 9.378263076908088e-06, "loss": 0.4085, "step": 205570 }, { "epoch": 1.2220102121487717, "grad_norm": 4.244142532348633, "learning_rate": 9.378162866577876e-06, "loss": 0.3679, "step": 205580 }, { "epoch": 1.2220696542254401, "grad_norm": 4.882353782653809, "learning_rate": 9.378062648707947e-06, "loss": 0.3868, "step": 205590 }, { "epoch": 1.2221290963021083, "grad_norm": 5.340470314025879, "learning_rate": 9.37796242329847e-06, "loss": 0.3506, "step": 205600 }, { "epoch": 1.2221885383787767, "grad_norm": 5.82960844039917, "learning_rate": 9.37786219034962e-06, "loss": 0.4174, "step": 205610 }, { "epoch": 1.2222479804554451, "grad_norm": 5.067771911621094, "learning_rate": 9.377761949861568e-06, "loss": 0.3918, "step": 205620 }, { "epoch": 1.2223074225321136, "grad_norm": 5.397755146026611, "learning_rate": 9.377661701834488e-06, "loss": 0.3727, "step": 205630 }, { "epoch": 1.222366864608782, "grad_norm": 4.924916744232178, "learning_rate": 9.377561446268554e-06, "loss": 0.3825, "step": 205640 }, { "epoch": 1.2224263066854504, "grad_norm": 5.793407917022705, "learning_rate": 9.377461183163936e-06, "loss": 0.3753, "step": 205650 }, { "epoch": 1.2224857487621188, "grad_norm": 6.059511184692383, "learning_rate": 9.377360912520807e-06, "loss": 0.3984, "step": 205660 }, { "epoch": 1.2225451908387872, "grad_norm": 4.148298740386963, "learning_rate": 9.37726063433934e-06, "loss": 0.3385, "step": 205670 }, { "epoch": 1.2226046329154556, "grad_norm": 5.037259578704834, "learning_rate": 9.377160348619707e-06, "loss": 0.4184, "step": 205680 }, { "epoch": 1.222664074992124, "grad_norm": 6.3491106033325195, "learning_rate": 9.377060055362085e-06, "loss": 0.4062, "step": 205690 }, { "epoch": 1.2227235170687922, "grad_norm": 5.327484607696533, "learning_rate": 9.37695975456664e-06, "loss": 0.3688, "step": 205700 }, { "epoch": 1.2227829591454606, "grad_norm": 6.632300853729248, "learning_rate": 9.376859446233548e-06, "loss": 0.4179, "step": 205710 }, { "epoch": 1.222842401222129, "grad_norm": 5.375586986541748, "learning_rate": 9.376759130362984e-06, "loss": 0.384, "step": 205720 }, { "epoch": 1.2229018432987975, "grad_norm": 5.270650863647461, "learning_rate": 9.376658806955117e-06, "loss": 0.4094, "step": 205730 }, { "epoch": 1.222961285375466, "grad_norm": 5.066639423370361, "learning_rate": 9.376558476010122e-06, "loss": 0.4559, "step": 205740 }, { "epoch": 1.2230207274521343, "grad_norm": 6.050290584564209, "learning_rate": 9.37645813752817e-06, "loss": 0.3374, "step": 205750 }, { "epoch": 1.2230801695288027, "grad_norm": 7.0075364112854, "learning_rate": 9.376357791509436e-06, "loss": 0.3655, "step": 205760 }, { "epoch": 1.2231396116054711, "grad_norm": 3.5656847953796387, "learning_rate": 9.376257437954092e-06, "loss": 0.3949, "step": 205770 }, { "epoch": 1.2231990536821393, "grad_norm": 5.126442909240723, "learning_rate": 9.376157076862312e-06, "loss": 0.3646, "step": 205780 }, { "epoch": 1.2232584957588077, "grad_norm": 4.8239545822143555, "learning_rate": 9.376056708234264e-06, "loss": 0.3772, "step": 205790 }, { "epoch": 1.2233179378354762, "grad_norm": 5.517814636230469, "learning_rate": 9.375956332070127e-06, "loss": 0.3812, "step": 205800 }, { "epoch": 1.2233773799121446, "grad_norm": 4.820255756378174, "learning_rate": 9.375855948370068e-06, "loss": 0.4244, "step": 205810 }, { "epoch": 1.223436821988813, "grad_norm": 5.326731204986572, "learning_rate": 9.375755557134265e-06, "loss": 0.4163, "step": 205820 }, { "epoch": 1.2234962640654814, "grad_norm": 6.345792293548584, "learning_rate": 9.375655158362888e-06, "loss": 0.363, "step": 205830 }, { "epoch": 1.2235557061421498, "grad_norm": 4.605964660644531, "learning_rate": 9.375554752056112e-06, "loss": 0.3405, "step": 205840 }, { "epoch": 1.2236151482188182, "grad_norm": 4.457460880279541, "learning_rate": 9.375454338214108e-06, "loss": 0.3852, "step": 205850 }, { "epoch": 1.2236745902954866, "grad_norm": 4.912403583526611, "learning_rate": 9.375353916837049e-06, "loss": 0.3774, "step": 205860 }, { "epoch": 1.223734032372155, "grad_norm": 5.829495906829834, "learning_rate": 9.37525348792511e-06, "loss": 0.4081, "step": 205870 }, { "epoch": 1.2237934744488232, "grad_norm": 5.650339126586914, "learning_rate": 9.37515305147846e-06, "loss": 0.3952, "step": 205880 }, { "epoch": 1.2238529165254917, "grad_norm": 5.5471978187561035, "learning_rate": 9.375052607497276e-06, "loss": 0.391, "step": 205890 }, { "epoch": 1.22391235860216, "grad_norm": 4.756260395050049, "learning_rate": 9.374952155981728e-06, "loss": 0.3755, "step": 205900 }, { "epoch": 1.2239718006788285, "grad_norm": 7.680150032043457, "learning_rate": 9.374851696931992e-06, "loss": 0.4004, "step": 205910 }, { "epoch": 1.224031242755497, "grad_norm": 5.130472183227539, "learning_rate": 9.37475123034824e-06, "loss": 0.3741, "step": 205920 }, { "epoch": 1.2240906848321653, "grad_norm": 6.2182936668396, "learning_rate": 9.374650756230643e-06, "loss": 0.4222, "step": 205930 }, { "epoch": 1.2241501269088337, "grad_norm": 4.885495185852051, "learning_rate": 9.374550274579375e-06, "loss": 0.3982, "step": 205940 }, { "epoch": 1.2242095689855022, "grad_norm": 5.122242450714111, "learning_rate": 9.37444978539461e-06, "loss": 0.4095, "step": 205950 }, { "epoch": 1.2242690110621706, "grad_norm": 5.058537006378174, "learning_rate": 9.374349288676521e-06, "loss": 0.4001, "step": 205960 }, { "epoch": 1.2243284531388388, "grad_norm": 3.919062614440918, "learning_rate": 9.37424878442528e-06, "loss": 0.3668, "step": 205970 }, { "epoch": 1.2243878952155072, "grad_norm": 6.921008586883545, "learning_rate": 9.374148272641061e-06, "loss": 0.3693, "step": 205980 }, { "epoch": 1.2244473372921756, "grad_norm": 4.623863220214844, "learning_rate": 9.374047753324038e-06, "loss": 0.3969, "step": 205990 }, { "epoch": 1.224506779368844, "grad_norm": 6.330742359161377, "learning_rate": 9.373947226474381e-06, "loss": 0.4172, "step": 206000 }, { "epoch": 1.2245662214455124, "grad_norm": 4.175950527191162, "learning_rate": 9.373846692092265e-06, "loss": 0.3713, "step": 206010 }, { "epoch": 1.2246256635221808, "grad_norm": 4.665940761566162, "learning_rate": 9.373746150177863e-06, "loss": 0.3865, "step": 206020 }, { "epoch": 1.2246851055988492, "grad_norm": 7.0675787925720215, "learning_rate": 9.37364560073135e-06, "loss": 0.4476, "step": 206030 }, { "epoch": 1.2247445476755177, "grad_norm": 4.291897773742676, "learning_rate": 9.373545043752896e-06, "loss": 0.3714, "step": 206040 }, { "epoch": 1.224803989752186, "grad_norm": 7.3696794509887695, "learning_rate": 9.373444479242676e-06, "loss": 0.4362, "step": 206050 }, { "epoch": 1.2248634318288545, "grad_norm": 4.923579216003418, "learning_rate": 9.373343907200862e-06, "loss": 0.3834, "step": 206060 }, { "epoch": 1.2249228739055227, "grad_norm": 4.585901737213135, "learning_rate": 9.373243327627629e-06, "loss": 0.3952, "step": 206070 }, { "epoch": 1.224982315982191, "grad_norm": 6.621971607208252, "learning_rate": 9.373142740523148e-06, "loss": 0.4083, "step": 206080 }, { "epoch": 1.2250417580588595, "grad_norm": 4.365217208862305, "learning_rate": 9.373042145887595e-06, "loss": 0.3864, "step": 206090 }, { "epoch": 1.225101200135528, "grad_norm": 5.060901641845703, "learning_rate": 9.372941543721142e-06, "loss": 0.391, "step": 206100 }, { "epoch": 1.2251606422121963, "grad_norm": 5.475841045379639, "learning_rate": 9.37284093402396e-06, "loss": 0.3833, "step": 206110 }, { "epoch": 1.2252200842888648, "grad_norm": 6.398330211639404, "learning_rate": 9.372740316796225e-06, "loss": 0.3588, "step": 206120 }, { "epoch": 1.2252795263655332, "grad_norm": 4.2149200439453125, "learning_rate": 9.372639692038109e-06, "loss": 0.3806, "step": 206130 }, { "epoch": 1.2253389684422016, "grad_norm": 6.450647830963135, "learning_rate": 9.372539059749786e-06, "loss": 0.445, "step": 206140 }, { "epoch": 1.2253984105188698, "grad_norm": 4.667154788970947, "learning_rate": 9.37243841993143e-06, "loss": 0.36, "step": 206150 }, { "epoch": 1.2254578525955382, "grad_norm": 4.959964275360107, "learning_rate": 9.372337772583213e-06, "loss": 0.4075, "step": 206160 }, { "epoch": 1.2255172946722066, "grad_norm": 5.067644119262695, "learning_rate": 9.372237117705307e-06, "loss": 0.3786, "step": 206170 }, { "epoch": 1.225576736748875, "grad_norm": 5.912140846252441, "learning_rate": 9.372136455297888e-06, "loss": 0.3973, "step": 206180 }, { "epoch": 1.2256361788255434, "grad_norm": 3.786303997039795, "learning_rate": 9.372035785361129e-06, "loss": 0.3598, "step": 206190 }, { "epoch": 1.2256956209022118, "grad_norm": 6.1948652267456055, "learning_rate": 9.3719351078952e-06, "loss": 0.3757, "step": 206200 }, { "epoch": 1.2257550629788803, "grad_norm": 5.150028705596924, "learning_rate": 9.371834422900281e-06, "loss": 0.4154, "step": 206210 }, { "epoch": 1.2258145050555487, "grad_norm": 6.229006767272949, "learning_rate": 9.37173373037654e-06, "loss": 0.4344, "step": 206220 }, { "epoch": 1.225873947132217, "grad_norm": 4.888662338256836, "learning_rate": 9.371633030324153e-06, "loss": 0.3978, "step": 206230 }, { "epoch": 1.2259333892088855, "grad_norm": 5.028791427612305, "learning_rate": 9.37153232274329e-06, "loss": 0.4196, "step": 206240 }, { "epoch": 1.2259928312855537, "grad_norm": 4.890722274780273, "learning_rate": 9.371431607634128e-06, "loss": 0.4439, "step": 206250 }, { "epoch": 1.2260522733622221, "grad_norm": 4.818038463592529, "learning_rate": 9.371330884996837e-06, "loss": 0.4098, "step": 206260 }, { "epoch": 1.2261117154388905, "grad_norm": 4.754726409912109, "learning_rate": 9.371230154831595e-06, "loss": 0.4206, "step": 206270 }, { "epoch": 1.226171157515559, "grad_norm": 5.145942211151123, "learning_rate": 9.371129417138573e-06, "loss": 0.388, "step": 206280 }, { "epoch": 1.2262305995922274, "grad_norm": 4.549163818359375, "learning_rate": 9.371028671917944e-06, "loss": 0.4213, "step": 206290 }, { "epoch": 1.2262900416688958, "grad_norm": 5.212496757507324, "learning_rate": 9.370927919169882e-06, "loss": 0.3862, "step": 206300 }, { "epoch": 1.2263494837455642, "grad_norm": 4.173943042755127, "learning_rate": 9.37082715889456e-06, "loss": 0.3926, "step": 206310 }, { "epoch": 1.2264089258222326, "grad_norm": 5.8670783042907715, "learning_rate": 9.370726391092153e-06, "loss": 0.3853, "step": 206320 }, { "epoch": 1.226468367898901, "grad_norm": 5.179152011871338, "learning_rate": 9.370625615762834e-06, "loss": 0.3705, "step": 206330 }, { "epoch": 1.2265278099755692, "grad_norm": 5.863461017608643, "learning_rate": 9.370524832906777e-06, "loss": 0.3838, "step": 206340 }, { "epoch": 1.2265872520522376, "grad_norm": 5.042982578277588, "learning_rate": 9.370424042524154e-06, "loss": 0.3413, "step": 206350 }, { "epoch": 1.226646694128906, "grad_norm": 5.159191131591797, "learning_rate": 9.370323244615138e-06, "loss": 0.3771, "step": 206360 }, { "epoch": 1.2267061362055744, "grad_norm": 5.657831192016602, "learning_rate": 9.370222439179904e-06, "loss": 0.3725, "step": 206370 }, { "epoch": 1.2267655782822429, "grad_norm": 5.467815399169922, "learning_rate": 9.370121626218627e-06, "loss": 0.3973, "step": 206380 }, { "epoch": 1.2268250203589113, "grad_norm": 5.301375389099121, "learning_rate": 9.370020805731478e-06, "loss": 0.35, "step": 206390 }, { "epoch": 1.2268844624355797, "grad_norm": 5.207756042480469, "learning_rate": 9.369919977718634e-06, "loss": 0.3694, "step": 206400 }, { "epoch": 1.226943904512248, "grad_norm": 4.395775318145752, "learning_rate": 9.369819142180264e-06, "loss": 0.3918, "step": 206410 }, { "epoch": 1.2270033465889165, "grad_norm": 6.077803134918213, "learning_rate": 9.369718299116543e-06, "loss": 0.4146, "step": 206420 }, { "epoch": 1.227062788665585, "grad_norm": 4.950048446655273, "learning_rate": 9.369617448527648e-06, "loss": 0.4089, "step": 206430 }, { "epoch": 1.2271222307422531, "grad_norm": 5.170133113861084, "learning_rate": 9.36951659041375e-06, "loss": 0.3894, "step": 206440 }, { "epoch": 1.2271816728189215, "grad_norm": 4.016005992889404, "learning_rate": 9.369415724775024e-06, "loss": 0.343, "step": 206450 }, { "epoch": 1.22724111489559, "grad_norm": 5.637190818786621, "learning_rate": 9.36931485161164e-06, "loss": 0.386, "step": 206460 }, { "epoch": 1.2273005569722584, "grad_norm": 6.852299690246582, "learning_rate": 9.369213970923776e-06, "loss": 0.3879, "step": 206470 }, { "epoch": 1.2273599990489268, "grad_norm": 5.621408939361572, "learning_rate": 9.369113082711606e-06, "loss": 0.4334, "step": 206480 }, { "epoch": 1.2274194411255952, "grad_norm": 3.691988468170166, "learning_rate": 9.369012186975299e-06, "loss": 0.3969, "step": 206490 }, { "epoch": 1.2274788832022636, "grad_norm": 4.73637056350708, "learning_rate": 9.368911283715034e-06, "loss": 0.3626, "step": 206500 }, { "epoch": 1.227538325278932, "grad_norm": 4.932922840118408, "learning_rate": 9.368810372930981e-06, "loss": 0.3718, "step": 206510 }, { "epoch": 1.2275977673556002, "grad_norm": 5.260555267333984, "learning_rate": 9.368709454623315e-06, "loss": 0.3922, "step": 206520 }, { "epoch": 1.2276572094322686, "grad_norm": 9.80734634399414, "learning_rate": 9.368608528792212e-06, "loss": 0.4075, "step": 206530 }, { "epoch": 1.227716651508937, "grad_norm": 5.392708778381348, "learning_rate": 9.36850759543784e-06, "loss": 0.4267, "step": 206540 }, { "epoch": 1.2277760935856055, "grad_norm": 4.918770790100098, "learning_rate": 9.36840665456038e-06, "loss": 0.3516, "step": 206550 }, { "epoch": 1.2278355356622739, "grad_norm": 5.292253017425537, "learning_rate": 9.368305706160003e-06, "loss": 0.3732, "step": 206560 }, { "epoch": 1.2278949777389423, "grad_norm": 6.227064609527588, "learning_rate": 9.36820475023688e-06, "loss": 0.3805, "step": 206570 }, { "epoch": 1.2279544198156107, "grad_norm": 4.507498264312744, "learning_rate": 9.368103786791189e-06, "loss": 0.3896, "step": 206580 }, { "epoch": 1.2280138618922791, "grad_norm": 5.444003105163574, "learning_rate": 9.368002815823101e-06, "loss": 0.3583, "step": 206590 }, { "epoch": 1.2280733039689475, "grad_norm": 6.4979424476623535, "learning_rate": 9.367901837332792e-06, "loss": 0.4034, "step": 206600 }, { "epoch": 1.228132746045616, "grad_norm": 4.4104204177856445, "learning_rate": 9.367800851320434e-06, "loss": 0.3739, "step": 206610 }, { "epoch": 1.2281921881222841, "grad_norm": 5.197769641876221, "learning_rate": 9.3676998577862e-06, "loss": 0.3908, "step": 206620 }, { "epoch": 1.2282516301989526, "grad_norm": 4.076558589935303, "learning_rate": 9.36759885673027e-06, "loss": 0.3359, "step": 206630 }, { "epoch": 1.228311072275621, "grad_norm": 5.170225143432617, "learning_rate": 9.367497848152811e-06, "loss": 0.3722, "step": 206640 }, { "epoch": 1.2283705143522894, "grad_norm": 5.230787754058838, "learning_rate": 9.367396832054e-06, "loss": 0.3978, "step": 206650 }, { "epoch": 1.2284299564289578, "grad_norm": 5.827296733856201, "learning_rate": 9.36729580843401e-06, "loss": 0.4297, "step": 206660 }, { "epoch": 1.2284893985056262, "grad_norm": 5.411619663238525, "learning_rate": 9.367194777293016e-06, "loss": 0.4391, "step": 206670 }, { "epoch": 1.2285488405822946, "grad_norm": 4.767024517059326, "learning_rate": 9.367093738631192e-06, "loss": 0.4055, "step": 206680 }, { "epoch": 1.228608282658963, "grad_norm": 5.1719536781311035, "learning_rate": 9.366992692448711e-06, "loss": 0.4134, "step": 206690 }, { "epoch": 1.2286677247356312, "grad_norm": 3.9482221603393555, "learning_rate": 9.366891638745747e-06, "loss": 0.3903, "step": 206700 }, { "epoch": 1.2287271668122997, "grad_norm": 5.323825359344482, "learning_rate": 9.366790577522475e-06, "loss": 0.4023, "step": 206710 }, { "epoch": 1.228786608888968, "grad_norm": 6.066838264465332, "learning_rate": 9.36668950877907e-06, "loss": 0.4244, "step": 206720 }, { "epoch": 1.2288460509656365, "grad_norm": 4.4595184326171875, "learning_rate": 9.366588432515702e-06, "loss": 0.3504, "step": 206730 }, { "epoch": 1.228905493042305, "grad_norm": 6.385360240936279, "learning_rate": 9.36648734873255e-06, "loss": 0.3771, "step": 206740 }, { "epoch": 1.2289649351189733, "grad_norm": 5.736155986785889, "learning_rate": 9.366386257429785e-06, "loss": 0.4136, "step": 206750 }, { "epoch": 1.2290243771956417, "grad_norm": 6.525819778442383, "learning_rate": 9.366285158607583e-06, "loss": 0.4356, "step": 206760 }, { "epoch": 1.2290838192723101, "grad_norm": 7.311835765838623, "learning_rate": 9.366184052266114e-06, "loss": 0.4501, "step": 206770 }, { "epoch": 1.2291432613489786, "grad_norm": 5.380303859710693, "learning_rate": 9.366082938405557e-06, "loss": 0.4265, "step": 206780 }, { "epoch": 1.229202703425647, "grad_norm": 6.256770133972168, "learning_rate": 9.365981817026085e-06, "loss": 0.4234, "step": 206790 }, { "epoch": 1.2292621455023154, "grad_norm": 4.688780307769775, "learning_rate": 9.365880688127869e-06, "loss": 0.3861, "step": 206800 }, { "epoch": 1.2293215875789836, "grad_norm": 4.1974029541015625, "learning_rate": 9.365779551711087e-06, "loss": 0.3921, "step": 206810 }, { "epoch": 1.229381029655652, "grad_norm": 4.935776233673096, "learning_rate": 9.365678407775912e-06, "loss": 0.3828, "step": 206820 }, { "epoch": 1.2294404717323204, "grad_norm": 6.144765853881836, "learning_rate": 9.365577256322517e-06, "loss": 0.3875, "step": 206830 }, { "epoch": 1.2294999138089888, "grad_norm": 5.339454174041748, "learning_rate": 9.365476097351079e-06, "loss": 0.4191, "step": 206840 }, { "epoch": 1.2295593558856572, "grad_norm": 6.629244804382324, "learning_rate": 9.365374930861768e-06, "loss": 0.3873, "step": 206850 }, { "epoch": 1.2296187979623256, "grad_norm": 5.338774681091309, "learning_rate": 9.36527375685476e-06, "loss": 0.3783, "step": 206860 }, { "epoch": 1.229678240038994, "grad_norm": 6.873861789703369, "learning_rate": 9.365172575330233e-06, "loss": 0.4487, "step": 206870 }, { "epoch": 1.2297376821156625, "grad_norm": 4.114101409912109, "learning_rate": 9.365071386288354e-06, "loss": 0.3925, "step": 206880 }, { "epoch": 1.2297971241923307, "grad_norm": 5.852427005767822, "learning_rate": 9.364970189729304e-06, "loss": 0.3963, "step": 206890 }, { "epoch": 1.229856566268999, "grad_norm": 5.848514080047607, "learning_rate": 9.364868985653253e-06, "loss": 0.4328, "step": 206900 }, { "epoch": 1.2299160083456675, "grad_norm": 5.07226037979126, "learning_rate": 9.36476777406038e-06, "loss": 0.3918, "step": 206910 }, { "epoch": 1.229975450422336, "grad_norm": 5.043797969818115, "learning_rate": 9.364666554950851e-06, "loss": 0.4145, "step": 206920 }, { "epoch": 1.2300348924990043, "grad_norm": 4.168633460998535, "learning_rate": 9.364565328324849e-06, "loss": 0.3934, "step": 206930 }, { "epoch": 1.2300943345756727, "grad_norm": 4.976507186889648, "learning_rate": 9.364464094182544e-06, "loss": 0.3547, "step": 206940 }, { "epoch": 1.2301537766523412, "grad_norm": 6.058968544006348, "learning_rate": 9.364362852524112e-06, "loss": 0.3986, "step": 206950 }, { "epoch": 1.2302132187290096, "grad_norm": 6.9808831214904785, "learning_rate": 9.364261603349725e-06, "loss": 0.4082, "step": 206960 }, { "epoch": 1.230272660805678, "grad_norm": 5.542845726013184, "learning_rate": 9.364160346659558e-06, "loss": 0.3674, "step": 206970 }, { "epoch": 1.2303321028823464, "grad_norm": 7.228794097900391, "learning_rate": 9.364059082453789e-06, "loss": 0.3887, "step": 206980 }, { "epoch": 1.2303915449590146, "grad_norm": 5.341312408447266, "learning_rate": 9.363957810732587e-06, "loss": 0.4241, "step": 206990 }, { "epoch": 1.230450987035683, "grad_norm": 5.605911731719971, "learning_rate": 9.363856531496129e-06, "loss": 0.3785, "step": 207000 }, { "epoch": 1.2305104291123514, "grad_norm": 7.601796627044678, "learning_rate": 9.36375524474459e-06, "loss": 0.4311, "step": 207010 }, { "epoch": 1.2305698711890198, "grad_norm": 6.453742027282715, "learning_rate": 9.363653950478145e-06, "loss": 0.4132, "step": 207020 }, { "epoch": 1.2306293132656883, "grad_norm": 4.690586090087891, "learning_rate": 9.363552648696966e-06, "loss": 0.3937, "step": 207030 }, { "epoch": 1.2306887553423567, "grad_norm": 7.751011848449707, "learning_rate": 9.363451339401228e-06, "loss": 0.4343, "step": 207040 }, { "epoch": 1.230748197419025, "grad_norm": 4.821156024932861, "learning_rate": 9.363350022591108e-06, "loss": 0.3894, "step": 207050 }, { "epoch": 1.2308076394956935, "grad_norm": 4.862692832946777, "learning_rate": 9.363248698266779e-06, "loss": 0.3863, "step": 207060 }, { "epoch": 1.2308670815723617, "grad_norm": 4.293143272399902, "learning_rate": 9.363147366428412e-06, "loss": 0.3703, "step": 207070 }, { "epoch": 1.23092652364903, "grad_norm": 5.912734031677246, "learning_rate": 9.363046027076187e-06, "loss": 0.3957, "step": 207080 }, { "epoch": 1.2309859657256985, "grad_norm": 4.950606822967529, "learning_rate": 9.362944680210276e-06, "loss": 0.3517, "step": 207090 }, { "epoch": 1.231045407802367, "grad_norm": 5.9010515213012695, "learning_rate": 9.362843325830853e-06, "loss": 0.4048, "step": 207100 }, { "epoch": 1.2311048498790353, "grad_norm": 5.825408935546875, "learning_rate": 9.362741963938093e-06, "loss": 0.3741, "step": 207110 }, { "epoch": 1.2311642919557038, "grad_norm": 6.658686637878418, "learning_rate": 9.36264059453217e-06, "loss": 0.4429, "step": 207120 }, { "epoch": 1.2312237340323722, "grad_norm": 5.398172378540039, "learning_rate": 9.362539217613263e-06, "loss": 0.409, "step": 207130 }, { "epoch": 1.2312831761090406, "grad_norm": 6.0146565437316895, "learning_rate": 9.36243783318154e-06, "loss": 0.3805, "step": 207140 }, { "epoch": 1.231342618185709, "grad_norm": 6.598771095275879, "learning_rate": 9.362336441237179e-06, "loss": 0.3868, "step": 207150 }, { "epoch": 1.2314020602623774, "grad_norm": 5.771999835968018, "learning_rate": 9.362235041780355e-06, "loss": 0.4295, "step": 207160 }, { "epoch": 1.2314615023390458, "grad_norm": 5.8140034675598145, "learning_rate": 9.36213363481124e-06, "loss": 0.4013, "step": 207170 }, { "epoch": 1.231520944415714, "grad_norm": 5.695365905761719, "learning_rate": 9.36203222033001e-06, "loss": 0.4101, "step": 207180 }, { "epoch": 1.2315803864923824, "grad_norm": 5.704893112182617, "learning_rate": 9.361930798336843e-06, "loss": 0.3756, "step": 207190 }, { "epoch": 1.2316398285690509, "grad_norm": 5.471921920776367, "learning_rate": 9.361829368831908e-06, "loss": 0.4165, "step": 207200 }, { "epoch": 1.2316992706457193, "grad_norm": 5.059525012969971, "learning_rate": 9.361727931815385e-06, "loss": 0.4445, "step": 207210 }, { "epoch": 1.2317587127223877, "grad_norm": 4.383606910705566, "learning_rate": 9.361626487287443e-06, "loss": 0.379, "step": 207220 }, { "epoch": 1.231818154799056, "grad_norm": 4.312253475189209, "learning_rate": 9.361525035248261e-06, "loss": 0.4124, "step": 207230 }, { "epoch": 1.2318775968757245, "grad_norm": 7.6982622146606445, "learning_rate": 9.361423575698014e-06, "loss": 0.3717, "step": 207240 }, { "epoch": 1.231937038952393, "grad_norm": 4.894495487213135, "learning_rate": 9.361322108636875e-06, "loss": 0.4197, "step": 207250 }, { "epoch": 1.2319964810290611, "grad_norm": 3.476893663406372, "learning_rate": 9.361220634065016e-06, "loss": 0.3596, "step": 207260 }, { "epoch": 1.2320559231057295, "grad_norm": 4.995865821838379, "learning_rate": 9.361119151982616e-06, "loss": 0.4195, "step": 207270 }, { "epoch": 1.232115365182398, "grad_norm": 5.048244953155518, "learning_rate": 9.36101766238985e-06, "loss": 0.3558, "step": 207280 }, { "epoch": 1.2321748072590664, "grad_norm": 4.037063121795654, "learning_rate": 9.360916165286891e-06, "loss": 0.3608, "step": 207290 }, { "epoch": 1.2322342493357348, "grad_norm": 4.023026943206787, "learning_rate": 9.360814660673913e-06, "loss": 0.3918, "step": 207300 }, { "epoch": 1.2322936914124032, "grad_norm": 5.030305862426758, "learning_rate": 9.360713148551092e-06, "loss": 0.3875, "step": 207310 }, { "epoch": 1.2323531334890716, "grad_norm": 6.328551769256592, "learning_rate": 9.360611628918604e-06, "loss": 0.403, "step": 207320 }, { "epoch": 1.23241257556574, "grad_norm": 6.422595024108887, "learning_rate": 9.360510101776621e-06, "loss": 0.4021, "step": 207330 }, { "epoch": 1.2324720176424084, "grad_norm": 4.848132610321045, "learning_rate": 9.360408567125319e-06, "loss": 0.4057, "step": 207340 }, { "epoch": 1.2325314597190768, "grad_norm": 6.000708103179932, "learning_rate": 9.360307024964875e-06, "loss": 0.4267, "step": 207350 }, { "epoch": 1.232590901795745, "grad_norm": 4.924659252166748, "learning_rate": 9.360205475295461e-06, "loss": 0.3535, "step": 207360 }, { "epoch": 1.2326503438724135, "grad_norm": 5.463184356689453, "learning_rate": 9.360103918117252e-06, "loss": 0.4018, "step": 207370 }, { "epoch": 1.2327097859490819, "grad_norm": 4.679527759552002, "learning_rate": 9.360002353430425e-06, "loss": 0.3871, "step": 207380 }, { "epoch": 1.2327692280257503, "grad_norm": 4.603235721588135, "learning_rate": 9.359900781235153e-06, "loss": 0.3823, "step": 207390 }, { "epoch": 1.2328286701024187, "grad_norm": 5.5609025955200195, "learning_rate": 9.359799201531612e-06, "loss": 0.4091, "step": 207400 }, { "epoch": 1.2328881121790871, "grad_norm": 4.456794261932373, "learning_rate": 9.359697614319977e-06, "loss": 0.3794, "step": 207410 }, { "epoch": 1.2329475542557555, "grad_norm": 5.318575382232666, "learning_rate": 9.35959601960042e-06, "loss": 0.3476, "step": 207420 }, { "epoch": 1.233006996332424, "grad_norm": 5.038951396942139, "learning_rate": 9.359494417373123e-06, "loss": 0.4337, "step": 207430 }, { "epoch": 1.2330664384090921, "grad_norm": 4.61416482925415, "learning_rate": 9.359392807638253e-06, "loss": 0.379, "step": 207440 }, { "epoch": 1.2331258804857606, "grad_norm": 6.269337177276611, "learning_rate": 9.359291190395989e-06, "loss": 0.4237, "step": 207450 }, { "epoch": 1.233185322562429, "grad_norm": 5.646175861358643, "learning_rate": 9.359189565646507e-06, "loss": 0.3845, "step": 207460 }, { "epoch": 1.2332447646390974, "grad_norm": 5.889509201049805, "learning_rate": 9.359087933389978e-06, "loss": 0.3885, "step": 207470 }, { "epoch": 1.2333042067157658, "grad_norm": 5.09030294418335, "learning_rate": 9.358986293626581e-06, "loss": 0.402, "step": 207480 }, { "epoch": 1.2333636487924342, "grad_norm": 4.728762149810791, "learning_rate": 9.358884646356489e-06, "loss": 0.382, "step": 207490 }, { "epoch": 1.2334230908691026, "grad_norm": 7.760434627532959, "learning_rate": 9.358782991579879e-06, "loss": 0.4249, "step": 207500 }, { "epoch": 1.233482532945771, "grad_norm": 6.536926746368408, "learning_rate": 9.358681329296923e-06, "loss": 0.3748, "step": 207510 }, { "epoch": 1.2335419750224395, "grad_norm": 4.8795576095581055, "learning_rate": 9.358579659507798e-06, "loss": 0.4271, "step": 207520 }, { "epoch": 1.2336014170991079, "grad_norm": 4.675422668457031, "learning_rate": 9.35847798221268e-06, "loss": 0.3854, "step": 207530 }, { "epoch": 1.2336608591757763, "grad_norm": 6.341337203979492, "learning_rate": 9.358376297411741e-06, "loss": 0.3705, "step": 207540 }, { "epoch": 1.2337203012524445, "grad_norm": 5.5554962158203125, "learning_rate": 9.358274605105159e-06, "loss": 0.4171, "step": 207550 }, { "epoch": 1.2337797433291129, "grad_norm": 5.122354984283447, "learning_rate": 9.358172905293108e-06, "loss": 0.3896, "step": 207560 }, { "epoch": 1.2338391854057813, "grad_norm": 3.7372827529907227, "learning_rate": 9.358071197975762e-06, "loss": 0.3871, "step": 207570 }, { "epoch": 1.2338986274824497, "grad_norm": 5.263646602630615, "learning_rate": 9.3579694831533e-06, "loss": 0.398, "step": 207580 }, { "epoch": 1.2339580695591181, "grad_norm": 4.97523832321167, "learning_rate": 9.357867760825892e-06, "loss": 0.3896, "step": 207590 }, { "epoch": 1.2340175116357865, "grad_norm": 4.644611835479736, "learning_rate": 9.357766030993717e-06, "loss": 0.3598, "step": 207600 }, { "epoch": 1.234076953712455, "grad_norm": 4.748357772827148, "learning_rate": 9.357664293656948e-06, "loss": 0.3681, "step": 207610 }, { "epoch": 1.2341363957891234, "grad_norm": 5.814706802368164, "learning_rate": 9.357562548815761e-06, "loss": 0.4001, "step": 207620 }, { "epoch": 1.2341958378657916, "grad_norm": 5.875915050506592, "learning_rate": 9.357460796470334e-06, "loss": 0.4019, "step": 207630 }, { "epoch": 1.23425527994246, "grad_norm": 6.083237648010254, "learning_rate": 9.357359036620837e-06, "loss": 0.4428, "step": 207640 }, { "epoch": 1.2343147220191284, "grad_norm": 5.171443939208984, "learning_rate": 9.357257269267449e-06, "loss": 0.3912, "step": 207650 }, { "epoch": 1.2343741640957968, "grad_norm": 5.264474391937256, "learning_rate": 9.357155494410344e-06, "loss": 0.3829, "step": 207660 }, { "epoch": 1.2344336061724652, "grad_norm": 5.4226765632629395, "learning_rate": 9.357053712049698e-06, "loss": 0.4101, "step": 207670 }, { "epoch": 1.2344930482491336, "grad_norm": 5.0561203956604, "learning_rate": 9.356951922185683e-06, "loss": 0.4219, "step": 207680 }, { "epoch": 1.234552490325802, "grad_norm": 5.487586975097656, "learning_rate": 9.35685012481848e-06, "loss": 0.3741, "step": 207690 }, { "epoch": 1.2346119324024705, "grad_norm": 5.133676528930664, "learning_rate": 9.356748319948259e-06, "loss": 0.3726, "step": 207700 }, { "epoch": 1.2346713744791389, "grad_norm": 6.069986820220947, "learning_rate": 9.356646507575197e-06, "loss": 0.3449, "step": 207710 }, { "epoch": 1.2347308165558073, "grad_norm": 6.540643692016602, "learning_rate": 9.356544687699473e-06, "loss": 0.4338, "step": 207720 }, { "epoch": 1.2347902586324755, "grad_norm": 4.449635982513428, "learning_rate": 9.356442860321258e-06, "loss": 0.3922, "step": 207730 }, { "epoch": 1.234849700709144, "grad_norm": 5.336597442626953, "learning_rate": 9.356341025440727e-06, "loss": 0.4353, "step": 207740 }, { "epoch": 1.2349091427858123, "grad_norm": 6.540042877197266, "learning_rate": 9.356239183058057e-06, "loss": 0.4133, "step": 207750 }, { "epoch": 1.2349685848624807, "grad_norm": 6.839689254760742, "learning_rate": 9.356137333173425e-06, "loss": 0.3918, "step": 207760 }, { "epoch": 1.2350280269391491, "grad_norm": 5.401368618011475, "learning_rate": 9.356035475787004e-06, "loss": 0.4186, "step": 207770 }, { "epoch": 1.2350874690158176, "grad_norm": 4.711450099945068, "learning_rate": 9.35593361089897e-06, "loss": 0.3512, "step": 207780 }, { "epoch": 1.235146911092486, "grad_norm": 4.811288833618164, "learning_rate": 9.3558317385095e-06, "loss": 0.397, "step": 207790 }, { "epoch": 1.2352063531691544, "grad_norm": 5.055963039398193, "learning_rate": 9.355729858618767e-06, "loss": 0.4139, "step": 207800 }, { "epoch": 1.2352657952458226, "grad_norm": 6.372113227844238, "learning_rate": 9.355627971226949e-06, "loss": 0.4226, "step": 207810 }, { "epoch": 1.235325237322491, "grad_norm": 5.480618953704834, "learning_rate": 9.355526076334216e-06, "loss": 0.436, "step": 207820 }, { "epoch": 1.2353846793991594, "grad_norm": 4.390773773193359, "learning_rate": 9.355424173940751e-06, "loss": 0.3687, "step": 207830 }, { "epoch": 1.2354441214758278, "grad_norm": 3.722203493118286, "learning_rate": 9.355322264046724e-06, "loss": 0.3665, "step": 207840 }, { "epoch": 1.2355035635524962, "grad_norm": 4.8336992263793945, "learning_rate": 9.355220346652314e-06, "loss": 0.3866, "step": 207850 }, { "epoch": 1.2355630056291647, "grad_norm": 5.270549297332764, "learning_rate": 9.355118421757693e-06, "loss": 0.3876, "step": 207860 }, { "epoch": 1.235622447705833, "grad_norm": 5.473578929901123, "learning_rate": 9.35501648936304e-06, "loss": 0.4155, "step": 207870 }, { "epoch": 1.2356818897825015, "grad_norm": 4.477594375610352, "learning_rate": 9.354914549468527e-06, "loss": 0.4302, "step": 207880 }, { "epoch": 1.23574133185917, "grad_norm": 5.725455284118652, "learning_rate": 9.354812602074334e-06, "loss": 0.3754, "step": 207890 }, { "epoch": 1.2358007739358383, "grad_norm": 4.426101207733154, "learning_rate": 9.354710647180632e-06, "loss": 0.3663, "step": 207900 }, { "epoch": 1.2358602160125067, "grad_norm": 4.98320198059082, "learning_rate": 9.3546086847876e-06, "loss": 0.3965, "step": 207910 }, { "epoch": 1.235919658089175, "grad_norm": 8.492111206054688, "learning_rate": 9.354506714895412e-06, "loss": 0.4117, "step": 207920 }, { "epoch": 1.2359791001658433, "grad_norm": 6.221505641937256, "learning_rate": 9.354404737504244e-06, "loss": 0.4005, "step": 207930 }, { "epoch": 1.2360385422425118, "grad_norm": 4.330998420715332, "learning_rate": 9.354302752614271e-06, "loss": 0.3357, "step": 207940 }, { "epoch": 1.2360979843191802, "grad_norm": 4.171181678771973, "learning_rate": 9.35420076022567e-06, "loss": 0.3743, "step": 207950 }, { "epoch": 1.2361574263958486, "grad_norm": 6.555410861968994, "learning_rate": 9.354098760338614e-06, "loss": 0.4207, "step": 207960 }, { "epoch": 1.236216868472517, "grad_norm": 5.051746845245361, "learning_rate": 9.353996752953282e-06, "loss": 0.4065, "step": 207970 }, { "epoch": 1.2362763105491854, "grad_norm": 5.21743631362915, "learning_rate": 9.353894738069847e-06, "loss": 0.3622, "step": 207980 }, { "epoch": 1.2363357526258538, "grad_norm": 5.456210136413574, "learning_rate": 9.353792715688486e-06, "loss": 0.3889, "step": 207990 }, { "epoch": 1.236395194702522, "grad_norm": 7.015052318572998, "learning_rate": 9.353690685809376e-06, "loss": 0.3724, "step": 208000 }, { "epoch": 1.2364546367791904, "grad_norm": 5.002773284912109, "learning_rate": 9.35358864843269e-06, "loss": 0.3705, "step": 208010 }, { "epoch": 1.2365140788558588, "grad_norm": 5.145589351654053, "learning_rate": 9.353486603558603e-06, "loss": 0.4349, "step": 208020 }, { "epoch": 1.2365735209325273, "grad_norm": 4.787680149078369, "learning_rate": 9.353384551187297e-06, "loss": 0.4358, "step": 208030 }, { "epoch": 1.2366329630091957, "grad_norm": 4.810732364654541, "learning_rate": 9.35328249131894e-06, "loss": 0.3856, "step": 208040 }, { "epoch": 1.236692405085864, "grad_norm": 5.276052951812744, "learning_rate": 9.353180423953711e-06, "loss": 0.4032, "step": 208050 }, { "epoch": 1.2367518471625325, "grad_norm": 6.251273155212402, "learning_rate": 9.353078349091788e-06, "loss": 0.4134, "step": 208060 }, { "epoch": 1.236811289239201, "grad_norm": 5.569491863250732, "learning_rate": 9.352976266733343e-06, "loss": 0.4131, "step": 208070 }, { "epoch": 1.2368707313158693, "grad_norm": 4.1667633056640625, "learning_rate": 9.352874176878555e-06, "loss": 0.3926, "step": 208080 }, { "epoch": 1.2369301733925377, "grad_norm": 3.5219502449035645, "learning_rate": 9.352772079527596e-06, "loss": 0.3431, "step": 208090 }, { "epoch": 1.236989615469206, "grad_norm": 5.86137580871582, "learning_rate": 9.352669974680646e-06, "loss": 0.42, "step": 208100 }, { "epoch": 1.2370490575458744, "grad_norm": 4.072829723358154, "learning_rate": 9.352567862337878e-06, "loss": 0.4033, "step": 208110 }, { "epoch": 1.2371084996225428, "grad_norm": 4.828704357147217, "learning_rate": 9.35246574249947e-06, "loss": 0.3766, "step": 208120 }, { "epoch": 1.2371679416992112, "grad_norm": 4.009701251983643, "learning_rate": 9.352363615165595e-06, "loss": 0.3955, "step": 208130 }, { "epoch": 1.2372273837758796, "grad_norm": 6.055923938751221, "learning_rate": 9.352261480336432e-06, "loss": 0.399, "step": 208140 }, { "epoch": 1.237286825852548, "grad_norm": 5.063500881195068, "learning_rate": 9.352159338012155e-06, "loss": 0.392, "step": 208150 }, { "epoch": 1.2373462679292164, "grad_norm": 6.017610549926758, "learning_rate": 9.35205718819294e-06, "loss": 0.3977, "step": 208160 }, { "epoch": 1.2374057100058848, "grad_norm": 4.887063503265381, "learning_rate": 9.351955030878964e-06, "loss": 0.4044, "step": 208170 }, { "epoch": 1.237465152082553, "grad_norm": 4.532161235809326, "learning_rate": 9.3518528660704e-06, "loss": 0.4288, "step": 208180 }, { "epoch": 1.2375245941592214, "grad_norm": 5.266045093536377, "learning_rate": 9.351750693767429e-06, "loss": 0.3745, "step": 208190 }, { "epoch": 1.2375840362358899, "grad_norm": 4.465863227844238, "learning_rate": 9.351648513970223e-06, "loss": 0.3792, "step": 208200 }, { "epoch": 1.2376434783125583, "grad_norm": 5.105269908905029, "learning_rate": 9.351546326678957e-06, "loss": 0.4123, "step": 208210 }, { "epoch": 1.2377029203892267, "grad_norm": 3.590914726257324, "learning_rate": 9.351444131893811e-06, "loss": 0.4071, "step": 208220 }, { "epoch": 1.237762362465895, "grad_norm": 3.993424654006958, "learning_rate": 9.351341929614958e-06, "loss": 0.3954, "step": 208230 }, { "epoch": 1.2378218045425635, "grad_norm": 4.73469352722168, "learning_rate": 9.351239719842578e-06, "loss": 0.3586, "step": 208240 }, { "epoch": 1.237881246619232, "grad_norm": 6.403651237487793, "learning_rate": 9.351137502576842e-06, "loss": 0.3811, "step": 208250 }, { "epoch": 1.2379406886959003, "grad_norm": 5.00404691696167, "learning_rate": 9.351035277817926e-06, "loss": 0.3998, "step": 208260 }, { "epoch": 1.2380001307725688, "grad_norm": 5.54470682144165, "learning_rate": 9.350933045566011e-06, "loss": 0.3841, "step": 208270 }, { "epoch": 1.2380595728492372, "grad_norm": 4.9767374992370605, "learning_rate": 9.35083080582127e-06, "loss": 0.384, "step": 208280 }, { "epoch": 1.2381190149259054, "grad_norm": 5.418187141418457, "learning_rate": 9.350728558583876e-06, "loss": 0.4112, "step": 208290 }, { "epoch": 1.2381784570025738, "grad_norm": 3.9481308460235596, "learning_rate": 9.350626303854011e-06, "loss": 0.3944, "step": 208300 }, { "epoch": 1.2382378990792422, "grad_norm": 4.083164691925049, "learning_rate": 9.35052404163185e-06, "loss": 0.3599, "step": 208310 }, { "epoch": 1.2382973411559106, "grad_norm": 6.408860683441162, "learning_rate": 9.350421771917564e-06, "loss": 0.4292, "step": 208320 }, { "epoch": 1.238356783232579, "grad_norm": 6.2353515625, "learning_rate": 9.350319494711334e-06, "loss": 0.387, "step": 208330 }, { "epoch": 1.2384162253092474, "grad_norm": 6.505711555480957, "learning_rate": 9.350217210013334e-06, "loss": 0.4084, "step": 208340 }, { "epoch": 1.2384756673859159, "grad_norm": 4.5727458000183105, "learning_rate": 9.350114917823743e-06, "loss": 0.3306, "step": 208350 }, { "epoch": 1.2385351094625843, "grad_norm": 5.249305725097656, "learning_rate": 9.350012618142734e-06, "loss": 0.3671, "step": 208360 }, { "epoch": 1.2385945515392525, "grad_norm": 6.215539932250977, "learning_rate": 9.349910310970485e-06, "loss": 0.4194, "step": 208370 }, { "epoch": 1.2386539936159209, "grad_norm": 4.03645133972168, "learning_rate": 9.34980799630717e-06, "loss": 0.3849, "step": 208380 }, { "epoch": 1.2387134356925893, "grad_norm": 4.6076226234436035, "learning_rate": 9.349705674152967e-06, "loss": 0.426, "step": 208390 }, { "epoch": 1.2387728777692577, "grad_norm": 4.467285633087158, "learning_rate": 9.349603344508052e-06, "loss": 0.4427, "step": 208400 }, { "epoch": 1.2388323198459261, "grad_norm": 6.4447760581970215, "learning_rate": 9.3495010073726e-06, "loss": 0.3704, "step": 208410 }, { "epoch": 1.2388917619225945, "grad_norm": 5.467375755310059, "learning_rate": 9.34939866274679e-06, "loss": 0.3465, "step": 208420 }, { "epoch": 1.238951203999263, "grad_norm": 6.7326178550720215, "learning_rate": 9.349296310630795e-06, "loss": 0.3848, "step": 208430 }, { "epoch": 1.2390106460759314, "grad_norm": 3.7110836505889893, "learning_rate": 9.349193951024794e-06, "loss": 0.4021, "step": 208440 }, { "epoch": 1.2390700881525998, "grad_norm": 5.042169094085693, "learning_rate": 9.349091583928963e-06, "loss": 0.3603, "step": 208450 }, { "epoch": 1.2391295302292682, "grad_norm": 5.629910945892334, "learning_rate": 9.348989209343476e-06, "loss": 0.4116, "step": 208460 }, { "epoch": 1.2391889723059364, "grad_norm": 5.382060527801514, "learning_rate": 9.34888682726851e-06, "loss": 0.3979, "step": 208470 }, { "epoch": 1.2392484143826048, "grad_norm": 4.647486209869385, "learning_rate": 9.348784437704244e-06, "loss": 0.3793, "step": 208480 }, { "epoch": 1.2393078564592732, "grad_norm": 5.799503803253174, "learning_rate": 9.348682040650849e-06, "loss": 0.3877, "step": 208490 }, { "epoch": 1.2393672985359416, "grad_norm": 4.812178134918213, "learning_rate": 9.348579636108507e-06, "loss": 0.3705, "step": 208500 }, { "epoch": 1.23942674061261, "grad_norm": 4.916708469390869, "learning_rate": 9.348477224077392e-06, "loss": 0.3657, "step": 208510 }, { "epoch": 1.2394861826892785, "grad_norm": 5.50095796585083, "learning_rate": 9.348374804557681e-06, "loss": 0.4172, "step": 208520 }, { "epoch": 1.2395456247659469, "grad_norm": 4.06417179107666, "learning_rate": 9.348272377549547e-06, "loss": 0.3774, "step": 208530 }, { "epoch": 1.2396050668426153, "grad_norm": 5.917476177215576, "learning_rate": 9.348169943053171e-06, "loss": 0.3838, "step": 208540 }, { "epoch": 1.2396645089192835, "grad_norm": 4.20023250579834, "learning_rate": 9.34806750106873e-06, "loss": 0.3818, "step": 208550 }, { "epoch": 1.239723950995952, "grad_norm": 4.897958755493164, "learning_rate": 9.347965051596394e-06, "loss": 0.3962, "step": 208560 }, { "epoch": 1.2397833930726203, "grad_norm": 5.092849254608154, "learning_rate": 9.347862594636345e-06, "loss": 0.3486, "step": 208570 }, { "epoch": 1.2398428351492887, "grad_norm": 5.784195899963379, "learning_rate": 9.347760130188758e-06, "loss": 0.3632, "step": 208580 }, { "epoch": 1.2399022772259571, "grad_norm": 4.636066913604736, "learning_rate": 9.347657658253807e-06, "loss": 0.3673, "step": 208590 }, { "epoch": 1.2399617193026256, "grad_norm": 4.273444652557373, "learning_rate": 9.347555178831674e-06, "loss": 0.3921, "step": 208600 }, { "epoch": 1.240021161379294, "grad_norm": 4.802918910980225, "learning_rate": 9.347452691922531e-06, "loss": 0.4015, "step": 208610 }, { "epoch": 1.2400806034559624, "grad_norm": 4.682805061340332, "learning_rate": 9.347350197526556e-06, "loss": 0.3849, "step": 208620 }, { "epoch": 1.2401400455326308, "grad_norm": 6.175283432006836, "learning_rate": 9.347247695643925e-06, "loss": 0.3783, "step": 208630 }, { "epoch": 1.2401994876092992, "grad_norm": 5.041998863220215, "learning_rate": 9.347145186274816e-06, "loss": 0.4066, "step": 208640 }, { "epoch": 1.2402589296859676, "grad_norm": 5.234441757202148, "learning_rate": 9.347042669419402e-06, "loss": 0.3809, "step": 208650 }, { "epoch": 1.2403183717626358, "grad_norm": 4.807320594787598, "learning_rate": 9.346940145077863e-06, "loss": 0.3861, "step": 208660 }, { "epoch": 1.2403778138393042, "grad_norm": 4.8271026611328125, "learning_rate": 9.346837613250373e-06, "loss": 0.3761, "step": 208670 }, { "epoch": 1.2404372559159726, "grad_norm": 5.681161880493164, "learning_rate": 9.346735073937112e-06, "loss": 0.3906, "step": 208680 }, { "epoch": 1.240496697992641, "grad_norm": 5.294798851013184, "learning_rate": 9.346632527138255e-06, "loss": 0.3735, "step": 208690 }, { "epoch": 1.2405561400693095, "grad_norm": 4.779543399810791, "learning_rate": 9.346529972853976e-06, "loss": 0.3786, "step": 208700 }, { "epoch": 1.240615582145978, "grad_norm": 5.019421577453613, "learning_rate": 9.346427411084456e-06, "loss": 0.4045, "step": 208710 }, { "epoch": 1.2406750242226463, "grad_norm": 6.522717475891113, "learning_rate": 9.346324841829867e-06, "loss": 0.3817, "step": 208720 }, { "epoch": 1.2407344662993147, "grad_norm": 4.606908321380615, "learning_rate": 9.34622226509039e-06, "loss": 0.3537, "step": 208730 }, { "epoch": 1.240793908375983, "grad_norm": 5.90715217590332, "learning_rate": 9.346119680866197e-06, "loss": 0.4028, "step": 208740 }, { "epoch": 1.2408533504526513, "grad_norm": 4.729006290435791, "learning_rate": 9.34601708915747e-06, "loss": 0.3961, "step": 208750 }, { "epoch": 1.2409127925293197, "grad_norm": 4.341459274291992, "learning_rate": 9.345914489964384e-06, "loss": 0.393, "step": 208760 }, { "epoch": 1.2409722346059882, "grad_norm": 5.237171649932861, "learning_rate": 9.34581188328711e-06, "loss": 0.3553, "step": 208770 }, { "epoch": 1.2410316766826566, "grad_norm": 5.565549373626709, "learning_rate": 9.345709269125834e-06, "loss": 0.3768, "step": 208780 }, { "epoch": 1.241091118759325, "grad_norm": 5.268949508666992, "learning_rate": 9.345606647480725e-06, "loss": 0.392, "step": 208790 }, { "epoch": 1.2411505608359934, "grad_norm": 4.880741119384766, "learning_rate": 9.345504018351965e-06, "loss": 0.3912, "step": 208800 }, { "epoch": 1.2412100029126618, "grad_norm": 4.400308609008789, "learning_rate": 9.345401381739728e-06, "loss": 0.3864, "step": 208810 }, { "epoch": 1.2412694449893302, "grad_norm": 3.8084959983825684, "learning_rate": 9.34529873764419e-06, "loss": 0.3632, "step": 208820 }, { "epoch": 1.2413288870659986, "grad_norm": 5.477424621582031, "learning_rate": 9.345196086065531e-06, "loss": 0.3776, "step": 208830 }, { "epoch": 1.2413883291426668, "grad_norm": 4.9875311851501465, "learning_rate": 9.345093427003926e-06, "loss": 0.4076, "step": 208840 }, { "epoch": 1.2414477712193352, "grad_norm": 4.31714391708374, "learning_rate": 9.34499076045955e-06, "loss": 0.3656, "step": 208850 }, { "epoch": 1.2415072132960037, "grad_norm": 4.616601467132568, "learning_rate": 9.344888086432582e-06, "loss": 0.3944, "step": 208860 }, { "epoch": 1.241566655372672, "grad_norm": 6.005672454833984, "learning_rate": 9.344785404923199e-06, "loss": 0.3839, "step": 208870 }, { "epoch": 1.2416260974493405, "grad_norm": 6.039467811584473, "learning_rate": 9.344682715931576e-06, "loss": 0.4458, "step": 208880 }, { "epoch": 1.241685539526009, "grad_norm": 8.715086936950684, "learning_rate": 9.344580019457892e-06, "loss": 0.3827, "step": 208890 }, { "epoch": 1.2417449816026773, "grad_norm": 4.715780258178711, "learning_rate": 9.344477315502323e-06, "loss": 0.368, "step": 208900 }, { "epoch": 1.2418044236793457, "grad_norm": 4.30357027053833, "learning_rate": 9.344374604065045e-06, "loss": 0.3915, "step": 208910 }, { "epoch": 1.241863865756014, "grad_norm": 4.479729175567627, "learning_rate": 9.344271885146235e-06, "loss": 0.4129, "step": 208920 }, { "epoch": 1.2419233078326823, "grad_norm": 4.885450839996338, "learning_rate": 9.344169158746073e-06, "loss": 0.3934, "step": 208930 }, { "epoch": 1.2419827499093508, "grad_norm": 5.55717658996582, "learning_rate": 9.344066424864731e-06, "loss": 0.3756, "step": 208940 }, { "epoch": 1.2420421919860192, "grad_norm": 5.754613399505615, "learning_rate": 9.343963683502389e-06, "loss": 0.4027, "step": 208950 }, { "epoch": 1.2421016340626876, "grad_norm": 5.567948341369629, "learning_rate": 9.343860934659222e-06, "loss": 0.3767, "step": 208960 }, { "epoch": 1.242161076139356, "grad_norm": 4.033736705780029, "learning_rate": 9.34375817833541e-06, "loss": 0.4002, "step": 208970 }, { "epoch": 1.2422205182160244, "grad_norm": 4.73708963394165, "learning_rate": 9.343655414531128e-06, "loss": 0.4126, "step": 208980 }, { "epoch": 1.2422799602926928, "grad_norm": 5.152352809906006, "learning_rate": 9.343552643246551e-06, "loss": 0.3904, "step": 208990 }, { "epoch": 1.2423394023693612, "grad_norm": 7.845552921295166, "learning_rate": 9.34344986448186e-06, "loss": 0.4463, "step": 209000 }, { "epoch": 1.2423988444460297, "grad_norm": 4.4542999267578125, "learning_rate": 9.34334707823723e-06, "loss": 0.4029, "step": 209010 }, { "epoch": 1.242458286522698, "grad_norm": 4.960895538330078, "learning_rate": 9.343244284512839e-06, "loss": 0.3922, "step": 209020 }, { "epoch": 1.2425177285993663, "grad_norm": 5.62849760055542, "learning_rate": 9.343141483308859e-06, "loss": 0.3916, "step": 209030 }, { "epoch": 1.2425771706760347, "grad_norm": 4.728219032287598, "learning_rate": 9.343038674625475e-06, "loss": 0.3705, "step": 209040 }, { "epoch": 1.242636612752703, "grad_norm": 4.814558029174805, "learning_rate": 9.34293585846286e-06, "loss": 0.4064, "step": 209050 }, { "epoch": 1.2426960548293715, "grad_norm": 5.816844463348389, "learning_rate": 9.34283303482119e-06, "loss": 0.4041, "step": 209060 }, { "epoch": 1.24275549690604, "grad_norm": 4.690891742706299, "learning_rate": 9.342730203700643e-06, "loss": 0.4091, "step": 209070 }, { "epoch": 1.2428149389827083, "grad_norm": 5.794406890869141, "learning_rate": 9.342627365101399e-06, "loss": 0.3958, "step": 209080 }, { "epoch": 1.2428743810593768, "grad_norm": 7.328494071960449, "learning_rate": 9.342524519023631e-06, "loss": 0.4074, "step": 209090 }, { "epoch": 1.2429338231360452, "grad_norm": 4.85601282119751, "learning_rate": 9.342421665467516e-06, "loss": 0.3935, "step": 209100 }, { "epoch": 1.2429932652127134, "grad_norm": 5.602780342102051, "learning_rate": 9.342318804433234e-06, "loss": 0.3608, "step": 209110 }, { "epoch": 1.2430527072893818, "grad_norm": 5.4190473556518555, "learning_rate": 9.342215935920962e-06, "loss": 0.3868, "step": 209120 }, { "epoch": 1.2431121493660502, "grad_norm": 6.308932304382324, "learning_rate": 9.342113059930875e-06, "loss": 0.4218, "step": 209130 }, { "epoch": 1.2431715914427186, "grad_norm": 5.188483238220215, "learning_rate": 9.342010176463152e-06, "loss": 0.3881, "step": 209140 }, { "epoch": 1.243231033519387, "grad_norm": 5.5080180168151855, "learning_rate": 9.341907285517968e-06, "loss": 0.3879, "step": 209150 }, { "epoch": 1.2432904755960554, "grad_norm": 4.08392858505249, "learning_rate": 9.3418043870955e-06, "loss": 0.4102, "step": 209160 }, { "epoch": 1.2433499176727238, "grad_norm": 6.2667927742004395, "learning_rate": 9.341701481195931e-06, "loss": 0.4366, "step": 209170 }, { "epoch": 1.2434093597493923, "grad_norm": 4.570102691650391, "learning_rate": 9.341598567819432e-06, "loss": 0.4104, "step": 209180 }, { "epoch": 1.2434688018260607, "grad_norm": 4.7880635261535645, "learning_rate": 9.341495646966182e-06, "loss": 0.3452, "step": 209190 }, { "epoch": 1.243528243902729, "grad_norm": 4.838850498199463, "learning_rate": 9.341392718636359e-06, "loss": 0.364, "step": 209200 }, { "epoch": 1.2435876859793973, "grad_norm": 4.352127552032471, "learning_rate": 9.34128978283014e-06, "loss": 0.3851, "step": 209210 }, { "epoch": 1.2436471280560657, "grad_norm": 5.875418186187744, "learning_rate": 9.341186839547701e-06, "loss": 0.3994, "step": 209220 }, { "epoch": 1.2437065701327341, "grad_norm": 4.193339824676514, "learning_rate": 9.341083888789221e-06, "loss": 0.3752, "step": 209230 }, { "epoch": 1.2437660122094025, "grad_norm": 5.296003341674805, "learning_rate": 9.340980930554878e-06, "loss": 0.3807, "step": 209240 }, { "epoch": 1.243825454286071, "grad_norm": 4.313014507293701, "learning_rate": 9.340877964844845e-06, "loss": 0.4207, "step": 209250 }, { "epoch": 1.2438848963627394, "grad_norm": 5.941688537597656, "learning_rate": 9.340774991659303e-06, "loss": 0.3772, "step": 209260 }, { "epoch": 1.2439443384394078, "grad_norm": 7.813210964202881, "learning_rate": 9.340672010998428e-06, "loss": 0.4019, "step": 209270 }, { "epoch": 1.2440037805160762, "grad_norm": 5.291979789733887, "learning_rate": 9.3405690228624e-06, "loss": 0.3994, "step": 209280 }, { "epoch": 1.2440632225927444, "grad_norm": 5.020669937133789, "learning_rate": 9.340466027251393e-06, "loss": 0.4091, "step": 209290 }, { "epoch": 1.2441226646694128, "grad_norm": 6.225609302520752, "learning_rate": 9.340363024165586e-06, "loss": 0.3776, "step": 209300 }, { "epoch": 1.2441821067460812, "grad_norm": 4.861265182495117, "learning_rate": 9.340260013605157e-06, "loss": 0.3991, "step": 209310 }, { "epoch": 1.2442415488227496, "grad_norm": 4.712583065032959, "learning_rate": 9.34015699557028e-06, "loss": 0.3848, "step": 209320 }, { "epoch": 1.244300990899418, "grad_norm": 3.719484567642212, "learning_rate": 9.340053970061136e-06, "loss": 0.3674, "step": 209330 }, { "epoch": 1.2443604329760865, "grad_norm": 4.806724548339844, "learning_rate": 9.339950937077901e-06, "loss": 0.3749, "step": 209340 }, { "epoch": 1.2444198750527549, "grad_norm": 4.898313045501709, "learning_rate": 9.339847896620753e-06, "loss": 0.4113, "step": 209350 }, { "epoch": 1.2444793171294233, "grad_norm": 4.490393161773682, "learning_rate": 9.339744848689869e-06, "loss": 0.3779, "step": 209360 }, { "epoch": 1.2445387592060917, "grad_norm": 5.585205078125, "learning_rate": 9.339641793285425e-06, "loss": 0.4075, "step": 209370 }, { "epoch": 1.24459820128276, "grad_norm": 4.550081253051758, "learning_rate": 9.339538730407603e-06, "loss": 0.3686, "step": 209380 }, { "epoch": 1.2446576433594285, "grad_norm": 4.754117012023926, "learning_rate": 9.339435660056575e-06, "loss": 0.4066, "step": 209390 }, { "epoch": 1.2447170854360967, "grad_norm": 5.820346355438232, "learning_rate": 9.339332582232523e-06, "loss": 0.3871, "step": 209400 }, { "epoch": 1.2447765275127651, "grad_norm": 6.066333770751953, "learning_rate": 9.33922949693562e-06, "loss": 0.4242, "step": 209410 }, { "epoch": 1.2448359695894335, "grad_norm": 4.9154253005981445, "learning_rate": 9.339126404166048e-06, "loss": 0.4037, "step": 209420 }, { "epoch": 1.244895411666102, "grad_norm": 4.140414714813232, "learning_rate": 9.339023303923983e-06, "loss": 0.3768, "step": 209430 }, { "epoch": 1.2449548537427704, "grad_norm": 6.539836406707764, "learning_rate": 9.338920196209601e-06, "loss": 0.3693, "step": 209440 }, { "epoch": 1.2450142958194388, "grad_norm": 7.31166410446167, "learning_rate": 9.338817081023082e-06, "loss": 0.3959, "step": 209450 }, { "epoch": 1.2450737378961072, "grad_norm": 5.053895473480225, "learning_rate": 9.3387139583646e-06, "loss": 0.392, "step": 209460 }, { "epoch": 1.2451331799727756, "grad_norm": 5.792245388031006, "learning_rate": 9.338610828234336e-06, "loss": 0.4302, "step": 209470 }, { "epoch": 1.2451926220494438, "grad_norm": 4.778452396392822, "learning_rate": 9.338507690632469e-06, "loss": 0.3933, "step": 209480 }, { "epoch": 1.2452520641261122, "grad_norm": 4.514700412750244, "learning_rate": 9.33840454555917e-06, "loss": 0.3875, "step": 209490 }, { "epoch": 1.2453115062027806, "grad_norm": 4.482474327087402, "learning_rate": 9.338301393014622e-06, "loss": 0.3813, "step": 209500 }, { "epoch": 1.245370948279449, "grad_norm": 5.034359931945801, "learning_rate": 9.338198232999004e-06, "loss": 0.4142, "step": 209510 }, { "epoch": 1.2454303903561175, "grad_norm": 6.394282341003418, "learning_rate": 9.338095065512487e-06, "loss": 0.3482, "step": 209520 }, { "epoch": 1.2454898324327859, "grad_norm": 5.384265899658203, "learning_rate": 9.337991890555255e-06, "loss": 0.4226, "step": 209530 }, { "epoch": 1.2455492745094543, "grad_norm": 3.959951877593994, "learning_rate": 9.337888708127482e-06, "loss": 0.3799, "step": 209540 }, { "epoch": 1.2456087165861227, "grad_norm": 4.597132205963135, "learning_rate": 9.33778551822935e-06, "loss": 0.3761, "step": 209550 }, { "epoch": 1.2456681586627911, "grad_norm": 7.153939723968506, "learning_rate": 9.33768232086103e-06, "loss": 0.4064, "step": 209560 }, { "epoch": 1.2457276007394595, "grad_norm": 5.380186557769775, "learning_rate": 9.337579116022707e-06, "loss": 0.3812, "step": 209570 }, { "epoch": 1.2457870428161277, "grad_norm": 5.634125232696533, "learning_rate": 9.337475903714552e-06, "loss": 0.3818, "step": 209580 }, { "epoch": 1.2458464848927961, "grad_norm": 4.7397332191467285, "learning_rate": 9.337372683936748e-06, "loss": 0.4106, "step": 209590 }, { "epoch": 1.2459059269694646, "grad_norm": 6.167348861694336, "learning_rate": 9.33726945668947e-06, "loss": 0.3867, "step": 209600 }, { "epoch": 1.245965369046133, "grad_norm": 6.959643840789795, "learning_rate": 9.337166221972895e-06, "loss": 0.4292, "step": 209610 }, { "epoch": 1.2460248111228014, "grad_norm": 5.827305316925049, "learning_rate": 9.337062979787205e-06, "loss": 0.3852, "step": 209620 }, { "epoch": 1.2460842531994698, "grad_norm": 7.06918478012085, "learning_rate": 9.336959730132573e-06, "loss": 0.4074, "step": 209630 }, { "epoch": 1.2461436952761382, "grad_norm": 5.646742820739746, "learning_rate": 9.33685647300918e-06, "loss": 0.381, "step": 209640 }, { "epoch": 1.2462031373528066, "grad_norm": 8.972378730773926, "learning_rate": 9.336753208417203e-06, "loss": 0.3909, "step": 209650 }, { "epoch": 1.2462625794294748, "grad_norm": 6.367489337921143, "learning_rate": 9.336649936356819e-06, "loss": 0.3882, "step": 209660 }, { "epoch": 1.2463220215061432, "grad_norm": 4.15580940246582, "learning_rate": 9.336546656828208e-06, "loss": 0.4122, "step": 209670 }, { "epoch": 1.2463814635828117, "grad_norm": 4.637899875640869, "learning_rate": 9.336443369831543e-06, "loss": 0.4236, "step": 209680 }, { "epoch": 1.24644090565948, "grad_norm": 4.852449893951416, "learning_rate": 9.336340075367008e-06, "loss": 0.3643, "step": 209690 }, { "epoch": 1.2465003477361485, "grad_norm": 6.087662220001221, "learning_rate": 9.336236773434775e-06, "loss": 0.4162, "step": 209700 }, { "epoch": 1.246559789812817, "grad_norm": 4.407064914703369, "learning_rate": 9.336133464035027e-06, "loss": 0.3818, "step": 209710 }, { "epoch": 1.2466192318894853, "grad_norm": 4.813179969787598, "learning_rate": 9.33603014716794e-06, "loss": 0.4431, "step": 209720 }, { "epoch": 1.2466786739661537, "grad_norm": 5.615771770477295, "learning_rate": 9.33592682283369e-06, "loss": 0.4, "step": 209730 }, { "epoch": 1.2467381160428221, "grad_norm": 4.880815505981445, "learning_rate": 9.33582349103246e-06, "loss": 0.4027, "step": 209740 }, { "epoch": 1.2467975581194906, "grad_norm": 4.993436336517334, "learning_rate": 9.33572015176442e-06, "loss": 0.3896, "step": 209750 }, { "epoch": 1.246857000196159, "grad_norm": 6.741681098937988, "learning_rate": 9.335616805029755e-06, "loss": 0.3992, "step": 209760 }, { "epoch": 1.2469164422728272, "grad_norm": 5.734239101409912, "learning_rate": 9.33551345082864e-06, "loss": 0.3626, "step": 209770 }, { "epoch": 1.2469758843494956, "grad_norm": 6.274969100952148, "learning_rate": 9.335410089161254e-06, "loss": 0.4205, "step": 209780 }, { "epoch": 1.247035326426164, "grad_norm": 5.450712203979492, "learning_rate": 9.335306720027775e-06, "loss": 0.4137, "step": 209790 }, { "epoch": 1.2470947685028324, "grad_norm": 6.530629634857178, "learning_rate": 9.33520334342838e-06, "loss": 0.4009, "step": 209800 }, { "epoch": 1.2471542105795008, "grad_norm": 5.559000492095947, "learning_rate": 9.335099959363247e-06, "loss": 0.3739, "step": 209810 }, { "epoch": 1.2472136526561692, "grad_norm": 6.586656093597412, "learning_rate": 9.334996567832557e-06, "loss": 0.4308, "step": 209820 }, { "epoch": 1.2472730947328377, "grad_norm": 5.494560241699219, "learning_rate": 9.334893168836482e-06, "loss": 0.4372, "step": 209830 }, { "epoch": 1.247332536809506, "grad_norm": 5.478513717651367, "learning_rate": 9.334789762375207e-06, "loss": 0.3679, "step": 209840 }, { "epoch": 1.2473919788861743, "grad_norm": 4.375277519226074, "learning_rate": 9.334686348448904e-06, "loss": 0.3792, "step": 209850 }, { "epoch": 1.2474514209628427, "grad_norm": 4.984381198883057, "learning_rate": 9.334582927057757e-06, "loss": 0.4018, "step": 209860 }, { "epoch": 1.247510863039511, "grad_norm": 5.786381721496582, "learning_rate": 9.334479498201938e-06, "loss": 0.3996, "step": 209870 }, { "epoch": 1.2475703051161795, "grad_norm": 6.700081825256348, "learning_rate": 9.334376061881631e-06, "loss": 0.3858, "step": 209880 }, { "epoch": 1.247629747192848, "grad_norm": 5.28361701965332, "learning_rate": 9.334272618097009e-06, "loss": 0.3893, "step": 209890 }, { "epoch": 1.2476891892695163, "grad_norm": 5.160772800445557, "learning_rate": 9.334169166848253e-06, "loss": 0.3687, "step": 209900 }, { "epoch": 1.2477486313461847, "grad_norm": 5.426459312438965, "learning_rate": 9.334065708135541e-06, "loss": 0.3898, "step": 209910 }, { "epoch": 1.2478080734228532, "grad_norm": 3.59073805809021, "learning_rate": 9.333962241959051e-06, "loss": 0.3896, "step": 209920 }, { "epoch": 1.2478675154995216, "grad_norm": 5.15263557434082, "learning_rate": 9.33385876831896e-06, "loss": 0.4232, "step": 209930 }, { "epoch": 1.24792695757619, "grad_norm": 5.149461269378662, "learning_rate": 9.333755287215448e-06, "loss": 0.4009, "step": 209940 }, { "epoch": 1.2479863996528582, "grad_norm": 4.950209617614746, "learning_rate": 9.33365179864869e-06, "loss": 0.3597, "step": 209950 }, { "epoch": 1.2480458417295266, "grad_norm": 4.5174126625061035, "learning_rate": 9.333548302618869e-06, "loss": 0.397, "step": 209960 }, { "epoch": 1.248105283806195, "grad_norm": 6.244837760925293, "learning_rate": 9.33344479912616e-06, "loss": 0.4002, "step": 209970 }, { "epoch": 1.2481647258828634, "grad_norm": 4.491209983825684, "learning_rate": 9.333341288170742e-06, "loss": 0.3857, "step": 209980 }, { "epoch": 1.2482241679595318, "grad_norm": 5.030851364135742, "learning_rate": 9.333237769752794e-06, "loss": 0.3691, "step": 209990 }, { "epoch": 1.2482836100362003, "grad_norm": 4.9879865646362305, "learning_rate": 9.333134243872493e-06, "loss": 0.4205, "step": 210000 }, { "epoch": 1.2483430521128687, "grad_norm": 5.507044792175293, "learning_rate": 9.333030710530017e-06, "loss": 0.3971, "step": 210010 }, { "epoch": 1.248402494189537, "grad_norm": 4.492822170257568, "learning_rate": 9.332927169725545e-06, "loss": 0.4043, "step": 210020 }, { "epoch": 1.2484619362662053, "grad_norm": 5.0287275314331055, "learning_rate": 9.332823621459257e-06, "loss": 0.415, "step": 210030 }, { "epoch": 1.2485213783428737, "grad_norm": 5.037214756011963, "learning_rate": 9.332720065731328e-06, "loss": 0.404, "step": 210040 }, { "epoch": 1.248580820419542, "grad_norm": 4.480367183685303, "learning_rate": 9.332616502541939e-06, "loss": 0.4028, "step": 210050 }, { "epoch": 1.2486402624962105, "grad_norm": 5.870081424713135, "learning_rate": 9.332512931891266e-06, "loss": 0.3472, "step": 210060 }, { "epoch": 1.248699704572879, "grad_norm": 4.5965776443481445, "learning_rate": 9.33240935377949e-06, "loss": 0.386, "step": 210070 }, { "epoch": 1.2487591466495473, "grad_norm": 5.007896900177002, "learning_rate": 9.33230576820679e-06, "loss": 0.4024, "step": 210080 }, { "epoch": 1.2488185887262158, "grad_norm": 5.242151260375977, "learning_rate": 9.332202175173341e-06, "loss": 0.3802, "step": 210090 }, { "epoch": 1.2488780308028842, "grad_norm": 4.790197849273682, "learning_rate": 9.332098574679323e-06, "loss": 0.3846, "step": 210100 }, { "epoch": 1.2489374728795526, "grad_norm": 4.248588562011719, "learning_rate": 9.331994966724913e-06, "loss": 0.3823, "step": 210110 }, { "epoch": 1.248996914956221, "grad_norm": 5.8021135330200195, "learning_rate": 9.331891351310293e-06, "loss": 0.3991, "step": 210120 }, { "epoch": 1.2490563570328894, "grad_norm": 5.426196098327637, "learning_rate": 9.331787728435638e-06, "loss": 0.3634, "step": 210130 }, { "epoch": 1.2491157991095576, "grad_norm": 5.097165584564209, "learning_rate": 9.331684098101127e-06, "loss": 0.3579, "step": 210140 }, { "epoch": 1.249175241186226, "grad_norm": 6.463644504547119, "learning_rate": 9.331580460306939e-06, "loss": 0.3746, "step": 210150 }, { "epoch": 1.2492346832628944, "grad_norm": 5.153833389282227, "learning_rate": 9.331476815053255e-06, "loss": 0.3524, "step": 210160 }, { "epoch": 1.2492941253395629, "grad_norm": 4.193157196044922, "learning_rate": 9.331373162340249e-06, "loss": 0.4359, "step": 210170 }, { "epoch": 1.2493535674162313, "grad_norm": 5.148288249969482, "learning_rate": 9.331269502168103e-06, "loss": 0.4141, "step": 210180 }, { "epoch": 1.2494130094928997, "grad_norm": 5.301785945892334, "learning_rate": 9.331165834536993e-06, "loss": 0.3986, "step": 210190 }, { "epoch": 1.249472451569568, "grad_norm": 4.417707443237305, "learning_rate": 9.3310621594471e-06, "loss": 0.4082, "step": 210200 }, { "epoch": 1.2495318936462365, "grad_norm": 5.446503639221191, "learning_rate": 9.3309584768986e-06, "loss": 0.4293, "step": 210210 }, { "epoch": 1.2495913357229047, "grad_norm": 5.548840045928955, "learning_rate": 9.330854786891672e-06, "loss": 0.4156, "step": 210220 }, { "epoch": 1.2496507777995731, "grad_norm": 3.9035205841064453, "learning_rate": 9.330751089426496e-06, "loss": 0.3942, "step": 210230 }, { "epoch": 1.2497102198762415, "grad_norm": 4.561830997467041, "learning_rate": 9.330647384503251e-06, "loss": 0.3742, "step": 210240 }, { "epoch": 1.24976966195291, "grad_norm": 4.710606098175049, "learning_rate": 9.330543672122113e-06, "loss": 0.3663, "step": 210250 }, { "epoch": 1.2498291040295784, "grad_norm": 5.594536304473877, "learning_rate": 9.330439952283264e-06, "loss": 0.3906, "step": 210260 }, { "epoch": 1.2498885461062468, "grad_norm": 5.699937343597412, "learning_rate": 9.330336224986878e-06, "loss": 0.4058, "step": 210270 }, { "epoch": 1.2499479881829152, "grad_norm": 4.585418224334717, "learning_rate": 9.330232490233137e-06, "loss": 0.3618, "step": 210280 }, { "epoch": 1.2500074302595836, "grad_norm": 4.522826671600342, "learning_rate": 9.33012874802222e-06, "loss": 0.4104, "step": 210290 }, { "epoch": 1.250066872336252, "grad_norm": 5.628182411193848, "learning_rate": 9.330024998354305e-06, "loss": 0.4088, "step": 210300 }, { "epoch": 1.2501263144129204, "grad_norm": 4.573484420776367, "learning_rate": 9.329921241229568e-06, "loss": 0.3515, "step": 210310 }, { "epoch": 1.2501857564895889, "grad_norm": 4.988336563110352, "learning_rate": 9.329817476648192e-06, "loss": 0.4031, "step": 210320 }, { "epoch": 1.250245198566257, "grad_norm": 6.436356067657471, "learning_rate": 9.329713704610355e-06, "loss": 0.428, "step": 210330 }, { "epoch": 1.2503046406429255, "grad_norm": 4.216571807861328, "learning_rate": 9.329609925116231e-06, "loss": 0.3936, "step": 210340 }, { "epoch": 1.2503640827195939, "grad_norm": 6.778853893280029, "learning_rate": 9.329506138166004e-06, "loss": 0.4095, "step": 210350 }, { "epoch": 1.2504235247962623, "grad_norm": 6.159926891326904, "learning_rate": 9.329402343759853e-06, "loss": 0.3837, "step": 210360 }, { "epoch": 1.2504829668729307, "grad_norm": 4.611310958862305, "learning_rate": 9.329298541897951e-06, "loss": 0.3655, "step": 210370 }, { "epoch": 1.2505424089495991, "grad_norm": 4.226815223693848, "learning_rate": 9.329194732580482e-06, "loss": 0.3658, "step": 210380 }, { "epoch": 1.2506018510262675, "grad_norm": 3.7023441791534424, "learning_rate": 9.329090915807621e-06, "loss": 0.3897, "step": 210390 }, { "epoch": 1.2506612931029357, "grad_norm": 5.8801188468933105, "learning_rate": 9.328987091579552e-06, "loss": 0.4264, "step": 210400 }, { "epoch": 1.2507207351796041, "grad_norm": 4.140679836273193, "learning_rate": 9.328883259896449e-06, "loss": 0.431, "step": 210410 }, { "epoch": 1.2507801772562726, "grad_norm": 5.049950122833252, "learning_rate": 9.328779420758492e-06, "loss": 0.4093, "step": 210420 }, { "epoch": 1.250839619332941, "grad_norm": 5.445639133453369, "learning_rate": 9.328675574165862e-06, "loss": 0.4065, "step": 210430 }, { "epoch": 1.2508990614096094, "grad_norm": 5.79194450378418, "learning_rate": 9.328571720118736e-06, "loss": 0.4305, "step": 210440 }, { "epoch": 1.2509585034862778, "grad_norm": 5.474434852600098, "learning_rate": 9.328467858617292e-06, "loss": 0.3835, "step": 210450 }, { "epoch": 1.2510179455629462, "grad_norm": 5.373343467712402, "learning_rate": 9.32836398966171e-06, "loss": 0.4188, "step": 210460 }, { "epoch": 1.2510773876396146, "grad_norm": 5.492124080657959, "learning_rate": 9.328260113252168e-06, "loss": 0.3632, "step": 210470 }, { "epoch": 1.251136829716283, "grad_norm": 4.565701961517334, "learning_rate": 9.328156229388848e-06, "loss": 0.3731, "step": 210480 }, { "epoch": 1.2511962717929515, "grad_norm": 6.125092506408691, "learning_rate": 9.328052338071925e-06, "loss": 0.4066, "step": 210490 }, { "epoch": 1.2512557138696199, "grad_norm": 4.7668914794921875, "learning_rate": 9.32794843930158e-06, "loss": 0.4005, "step": 210500 }, { "epoch": 1.251315155946288, "grad_norm": 4.880295276641846, "learning_rate": 9.32784453307799e-06, "loss": 0.3959, "step": 210510 }, { "epoch": 1.2513745980229565, "grad_norm": 4.1565070152282715, "learning_rate": 9.327740619401338e-06, "loss": 0.3654, "step": 210520 }, { "epoch": 1.251434040099625, "grad_norm": 5.598930835723877, "learning_rate": 9.327636698271799e-06, "loss": 0.3919, "step": 210530 }, { "epoch": 1.2514934821762933, "grad_norm": 6.633373737335205, "learning_rate": 9.327532769689552e-06, "loss": 0.4275, "step": 210540 }, { "epoch": 1.2515529242529617, "grad_norm": 6.597583293914795, "learning_rate": 9.327428833654777e-06, "loss": 0.3692, "step": 210550 }, { "epoch": 1.2516123663296301, "grad_norm": 3.928938150405884, "learning_rate": 9.327324890167655e-06, "loss": 0.3697, "step": 210560 }, { "epoch": 1.2516718084062985, "grad_norm": 3.272655725479126, "learning_rate": 9.327220939228363e-06, "loss": 0.3638, "step": 210570 }, { "epoch": 1.2517312504829667, "grad_norm": 5.246588706970215, "learning_rate": 9.327116980837078e-06, "loss": 0.4207, "step": 210580 }, { "epoch": 1.2517906925596352, "grad_norm": 5.87012243270874, "learning_rate": 9.327013014993984e-06, "loss": 0.4049, "step": 210590 }, { "epoch": 1.2518501346363036, "grad_norm": 4.437928676605225, "learning_rate": 9.326909041699256e-06, "loss": 0.4006, "step": 210600 }, { "epoch": 1.251909576712972, "grad_norm": 6.159112453460693, "learning_rate": 9.326805060953074e-06, "loss": 0.3656, "step": 210610 }, { "epoch": 1.2519690187896404, "grad_norm": 4.788689136505127, "learning_rate": 9.32670107275562e-06, "loss": 0.4255, "step": 210620 }, { "epoch": 1.2520284608663088, "grad_norm": 6.245307922363281, "learning_rate": 9.326597077107068e-06, "loss": 0.3992, "step": 210630 }, { "epoch": 1.2520879029429772, "grad_norm": 5.109186172485352, "learning_rate": 9.326493074007598e-06, "loss": 0.4041, "step": 210640 }, { "epoch": 1.2521473450196456, "grad_norm": 5.346577167510986, "learning_rate": 9.326389063457394e-06, "loss": 0.4168, "step": 210650 }, { "epoch": 1.252206787096314, "grad_norm": 4.507806777954102, "learning_rate": 9.326285045456631e-06, "loss": 0.3901, "step": 210660 }, { "epoch": 1.2522662291729825, "grad_norm": 4.964521408081055, "learning_rate": 9.326181020005489e-06, "loss": 0.4119, "step": 210670 }, { "epoch": 1.2523256712496509, "grad_norm": 5.144760608673096, "learning_rate": 9.326076987104146e-06, "loss": 0.3733, "step": 210680 }, { "epoch": 1.2523851133263193, "grad_norm": 4.92957878112793, "learning_rate": 9.325972946752785e-06, "loss": 0.3622, "step": 210690 }, { "epoch": 1.2524445554029875, "grad_norm": 4.486719608306885, "learning_rate": 9.325868898951578e-06, "loss": 0.4535, "step": 210700 }, { "epoch": 1.252503997479656, "grad_norm": 5.961645126342773, "learning_rate": 9.32576484370071e-06, "loss": 0.4088, "step": 210710 }, { "epoch": 1.2525634395563243, "grad_norm": 4.362003326416016, "learning_rate": 9.325660781000361e-06, "loss": 0.391, "step": 210720 }, { "epoch": 1.2526228816329927, "grad_norm": 4.920215129852295, "learning_rate": 9.325556710850707e-06, "loss": 0.3739, "step": 210730 }, { "epoch": 1.2526823237096611, "grad_norm": 6.442429542541504, "learning_rate": 9.325452633251927e-06, "loss": 0.4073, "step": 210740 }, { "epoch": 1.2527417657863296, "grad_norm": 5.134753227233887, "learning_rate": 9.325348548204203e-06, "loss": 0.427, "step": 210750 }, { "epoch": 1.252801207862998, "grad_norm": 4.868250846862793, "learning_rate": 9.325244455707712e-06, "loss": 0.3645, "step": 210760 }, { "epoch": 1.2528606499396662, "grad_norm": 7.170560359954834, "learning_rate": 9.325140355762634e-06, "loss": 0.3822, "step": 210770 }, { "epoch": 1.2529200920163346, "grad_norm": 5.1854705810546875, "learning_rate": 9.325036248369149e-06, "loss": 0.4133, "step": 210780 }, { "epoch": 1.252979534093003, "grad_norm": 3.882176160812378, "learning_rate": 9.324932133527436e-06, "loss": 0.3708, "step": 210790 }, { "epoch": 1.2530389761696714, "grad_norm": 4.4816107749938965, "learning_rate": 9.324828011237672e-06, "loss": 0.4002, "step": 210800 }, { "epoch": 1.2530984182463398, "grad_norm": 5.173249244689941, "learning_rate": 9.324723881500038e-06, "loss": 0.4102, "step": 210810 }, { "epoch": 1.2531578603230082, "grad_norm": 5.45531702041626, "learning_rate": 9.324619744314716e-06, "loss": 0.3912, "step": 210820 }, { "epoch": 1.2532173023996767, "grad_norm": 6.279401779174805, "learning_rate": 9.32451559968188e-06, "loss": 0.3837, "step": 210830 }, { "epoch": 1.253276744476345, "grad_norm": 5.9568352699279785, "learning_rate": 9.324411447601713e-06, "loss": 0.4256, "step": 210840 }, { "epoch": 1.2533361865530135, "grad_norm": 5.399464130401611, "learning_rate": 9.324307288074395e-06, "loss": 0.4199, "step": 210850 }, { "epoch": 1.253395628629682, "grad_norm": 5.798605918884277, "learning_rate": 9.324203121100102e-06, "loss": 0.4232, "step": 210860 }, { "epoch": 1.2534550707063503, "grad_norm": 4.211551666259766, "learning_rate": 9.324098946679015e-06, "loss": 0.4071, "step": 210870 }, { "epoch": 1.2535145127830185, "grad_norm": 5.089767932891846, "learning_rate": 9.323994764811314e-06, "loss": 0.4066, "step": 210880 }, { "epoch": 1.253573954859687, "grad_norm": 5.1560139656066895, "learning_rate": 9.32389057549718e-06, "loss": 0.3758, "step": 210890 }, { "epoch": 1.2536333969363553, "grad_norm": 6.068520545959473, "learning_rate": 9.32378637873679e-06, "loss": 0.4384, "step": 210900 }, { "epoch": 1.2536928390130238, "grad_norm": 4.485372066497803, "learning_rate": 9.323682174530322e-06, "loss": 0.4003, "step": 210910 }, { "epoch": 1.2537522810896922, "grad_norm": 4.475156307220459, "learning_rate": 9.32357796287796e-06, "loss": 0.3805, "step": 210920 }, { "epoch": 1.2538117231663606, "grad_norm": 4.423215389251709, "learning_rate": 9.323473743779878e-06, "loss": 0.43, "step": 210930 }, { "epoch": 1.253871165243029, "grad_norm": 3.807368755340576, "learning_rate": 9.323369517236261e-06, "loss": 0.4053, "step": 210940 }, { "epoch": 1.2539306073196972, "grad_norm": 5.355470180511475, "learning_rate": 9.323265283247284e-06, "loss": 0.4241, "step": 210950 }, { "epoch": 1.2539900493963656, "grad_norm": 4.180361747741699, "learning_rate": 9.323161041813128e-06, "loss": 0.3587, "step": 210960 }, { "epoch": 1.254049491473034, "grad_norm": 5.258188247680664, "learning_rate": 9.323056792933973e-06, "loss": 0.3815, "step": 210970 }, { "epoch": 1.2541089335497024, "grad_norm": 4.498248100280762, "learning_rate": 9.322952536610001e-06, "loss": 0.3708, "step": 210980 }, { "epoch": 1.2541683756263708, "grad_norm": 4.872032642364502, "learning_rate": 9.322848272841385e-06, "loss": 0.364, "step": 210990 }, { "epoch": 1.2542278177030393, "grad_norm": 7.90101432800293, "learning_rate": 9.322744001628312e-06, "loss": 0.3931, "step": 211000 }, { "epoch": 1.2542872597797077, "grad_norm": 5.078333377838135, "learning_rate": 9.322639722970957e-06, "loss": 0.3869, "step": 211010 }, { "epoch": 1.254346701856376, "grad_norm": 5.042198657989502, "learning_rate": 9.322535436869499e-06, "loss": 0.3776, "step": 211020 }, { "epoch": 1.2544061439330445, "grad_norm": 5.6856255531311035, "learning_rate": 9.322431143324121e-06, "loss": 0.4098, "step": 211030 }, { "epoch": 1.254465586009713, "grad_norm": 4.71588134765625, "learning_rate": 9.322326842335001e-06, "loss": 0.3649, "step": 211040 }, { "epoch": 1.2545250280863813, "grad_norm": 5.7630767822265625, "learning_rate": 9.322222533902316e-06, "loss": 0.3803, "step": 211050 }, { "epoch": 1.2545844701630497, "grad_norm": 4.434632778167725, "learning_rate": 9.322118218026251e-06, "loss": 0.437, "step": 211060 }, { "epoch": 1.254643912239718, "grad_norm": 4.769401550292969, "learning_rate": 9.32201389470698e-06, "loss": 0.3854, "step": 211070 }, { "epoch": 1.2547033543163864, "grad_norm": 7.612421989440918, "learning_rate": 9.32190956394469e-06, "loss": 0.4207, "step": 211080 }, { "epoch": 1.2547627963930548, "grad_norm": 4.898624420166016, "learning_rate": 9.32180522573955e-06, "loss": 0.3633, "step": 211090 }, { "epoch": 1.2548222384697232, "grad_norm": 4.706326961517334, "learning_rate": 9.321700880091751e-06, "loss": 0.4116, "step": 211100 }, { "epoch": 1.2548816805463916, "grad_norm": 4.597447395324707, "learning_rate": 9.321596527001463e-06, "loss": 0.4286, "step": 211110 }, { "epoch": 1.25494112262306, "grad_norm": 5.31559419631958, "learning_rate": 9.321492166468873e-06, "loss": 0.4091, "step": 211120 }, { "epoch": 1.2550005646997284, "grad_norm": 3.9491171836853027, "learning_rate": 9.321387798494158e-06, "loss": 0.3577, "step": 211130 }, { "epoch": 1.2550600067763966, "grad_norm": 3.8751089572906494, "learning_rate": 9.321283423077496e-06, "loss": 0.3683, "step": 211140 }, { "epoch": 1.255119448853065, "grad_norm": 6.208808422088623, "learning_rate": 9.32117904021907e-06, "loss": 0.4132, "step": 211150 }, { "epoch": 1.2551788909297334, "grad_norm": 5.119109630584717, "learning_rate": 9.321074649919058e-06, "loss": 0.381, "step": 211160 }, { "epoch": 1.2552383330064019, "grad_norm": 5.113381385803223, "learning_rate": 9.320970252177637e-06, "loss": 0.3797, "step": 211170 }, { "epoch": 1.2552977750830703, "grad_norm": 5.82282829284668, "learning_rate": 9.320865846994992e-06, "loss": 0.3772, "step": 211180 }, { "epoch": 1.2553572171597387, "grad_norm": 6.52428674697876, "learning_rate": 9.3207614343713e-06, "loss": 0.3945, "step": 211190 }, { "epoch": 1.255416659236407, "grad_norm": 6.045621871948242, "learning_rate": 9.320657014306742e-06, "loss": 0.4503, "step": 211200 }, { "epoch": 1.2554761013130755, "grad_norm": 4.90437126159668, "learning_rate": 9.320552586801497e-06, "loss": 0.3764, "step": 211210 }, { "epoch": 1.255535543389744, "grad_norm": 5.109428405761719, "learning_rate": 9.320448151855743e-06, "loss": 0.3919, "step": 211220 }, { "epoch": 1.2555949854664123, "grad_norm": 4.93417501449585, "learning_rate": 9.320343709469664e-06, "loss": 0.4009, "step": 211230 }, { "epoch": 1.2556544275430808, "grad_norm": 4.8441267013549805, "learning_rate": 9.320239259643436e-06, "loss": 0.3527, "step": 211240 }, { "epoch": 1.255713869619749, "grad_norm": 4.554752826690674, "learning_rate": 9.320134802377242e-06, "loss": 0.3539, "step": 211250 }, { "epoch": 1.2557733116964174, "grad_norm": 4.59246301651001, "learning_rate": 9.32003033767126e-06, "loss": 0.391, "step": 211260 }, { "epoch": 1.2558327537730858, "grad_norm": 4.790377616882324, "learning_rate": 9.319925865525669e-06, "loss": 0.3869, "step": 211270 }, { "epoch": 1.2558921958497542, "grad_norm": 5.872345924377441, "learning_rate": 9.319821385940651e-06, "loss": 0.417, "step": 211280 }, { "epoch": 1.2559516379264226, "grad_norm": 4.735311985015869, "learning_rate": 9.319716898916387e-06, "loss": 0.3758, "step": 211290 }, { "epoch": 1.256011080003091, "grad_norm": 6.519821643829346, "learning_rate": 9.319612404453053e-06, "loss": 0.3757, "step": 211300 }, { "epoch": 1.2560705220797594, "grad_norm": 4.075234413146973, "learning_rate": 9.319507902550831e-06, "loss": 0.3639, "step": 211310 }, { "epoch": 1.2561299641564276, "grad_norm": 8.135370254516602, "learning_rate": 9.319403393209902e-06, "loss": 0.443, "step": 211320 }, { "epoch": 1.256189406233096, "grad_norm": 6.674516201019287, "learning_rate": 9.319298876430446e-06, "loss": 0.449, "step": 211330 }, { "epoch": 1.2562488483097645, "grad_norm": 5.037683486938477, "learning_rate": 9.319194352212638e-06, "loss": 0.3948, "step": 211340 }, { "epoch": 1.2563082903864329, "grad_norm": 4.565103054046631, "learning_rate": 9.319089820556664e-06, "loss": 0.4118, "step": 211350 }, { "epoch": 1.2563677324631013, "grad_norm": 6.105252742767334, "learning_rate": 9.318985281462703e-06, "loss": 0.3571, "step": 211360 }, { "epoch": 1.2564271745397697, "grad_norm": 5.393931865692139, "learning_rate": 9.318880734930934e-06, "loss": 0.3553, "step": 211370 }, { "epoch": 1.2564866166164381, "grad_norm": 5.707821846008301, "learning_rate": 9.318776180961536e-06, "loss": 0.3859, "step": 211380 }, { "epoch": 1.2565460586931065, "grad_norm": 5.5750041007995605, "learning_rate": 9.31867161955469e-06, "loss": 0.4451, "step": 211390 }, { "epoch": 1.256605500769775, "grad_norm": 5.209138870239258, "learning_rate": 9.318567050710577e-06, "loss": 0.351, "step": 211400 }, { "epoch": 1.2566649428464434, "grad_norm": 4.221881866455078, "learning_rate": 9.318462474429376e-06, "loss": 0.3839, "step": 211410 }, { "epoch": 1.2567243849231118, "grad_norm": 4.024713039398193, "learning_rate": 9.318357890711268e-06, "loss": 0.3705, "step": 211420 }, { "epoch": 1.2567838269997802, "grad_norm": 6.266519069671631, "learning_rate": 9.318253299556432e-06, "loss": 0.4035, "step": 211430 }, { "epoch": 1.2568432690764484, "grad_norm": 5.956172943115234, "learning_rate": 9.318148700965049e-06, "loss": 0.4315, "step": 211440 }, { "epoch": 1.2569027111531168, "grad_norm": 3.6927645206451416, "learning_rate": 9.318044094937297e-06, "loss": 0.3728, "step": 211450 }, { "epoch": 1.2569621532297852, "grad_norm": 5.068751335144043, "learning_rate": 9.317939481473359e-06, "loss": 0.4397, "step": 211460 }, { "epoch": 1.2570215953064536, "grad_norm": 6.182003498077393, "learning_rate": 9.317834860573413e-06, "loss": 0.3865, "step": 211470 }, { "epoch": 1.257081037383122, "grad_norm": 4.827028274536133, "learning_rate": 9.317730232237641e-06, "loss": 0.3995, "step": 211480 }, { "epoch": 1.2571404794597905, "grad_norm": 4.506155014038086, "learning_rate": 9.317625596466223e-06, "loss": 0.3586, "step": 211490 }, { "epoch": 1.2571999215364589, "grad_norm": 5.695016384124756, "learning_rate": 9.317520953259339e-06, "loss": 0.3629, "step": 211500 }, { "epoch": 1.257259363613127, "grad_norm": 3.995732307434082, "learning_rate": 9.317416302617168e-06, "loss": 0.3869, "step": 211510 }, { "epoch": 1.2573188056897955, "grad_norm": 6.934301853179932, "learning_rate": 9.31731164453989e-06, "loss": 0.3852, "step": 211520 }, { "epoch": 1.257378247766464, "grad_norm": 6.272441387176514, "learning_rate": 9.317206979027686e-06, "loss": 0.4108, "step": 211530 }, { "epoch": 1.2574376898431323, "grad_norm": 5.7472758293151855, "learning_rate": 9.317102306080739e-06, "loss": 0.4304, "step": 211540 }, { "epoch": 1.2574971319198007, "grad_norm": 4.448355674743652, "learning_rate": 9.316997625699224e-06, "loss": 0.4025, "step": 211550 }, { "epoch": 1.2575565739964691, "grad_norm": 4.800028324127197, "learning_rate": 9.316892937883326e-06, "loss": 0.4149, "step": 211560 }, { "epoch": 1.2576160160731376, "grad_norm": 6.359274864196777, "learning_rate": 9.31678824263322e-06, "loss": 0.3814, "step": 211570 }, { "epoch": 1.257675458149806, "grad_norm": 5.481746196746826, "learning_rate": 9.316683539949094e-06, "loss": 0.401, "step": 211580 }, { "epoch": 1.2577349002264744, "grad_norm": 4.6538543701171875, "learning_rate": 9.316578829831122e-06, "loss": 0.4097, "step": 211590 }, { "epoch": 1.2577943423031428, "grad_norm": 4.298740863800049, "learning_rate": 9.316474112279486e-06, "loss": 0.3774, "step": 211600 }, { "epoch": 1.2578537843798112, "grad_norm": 5.528616905212402, "learning_rate": 9.316369387294366e-06, "loss": 0.3789, "step": 211610 }, { "epoch": 1.2579132264564794, "grad_norm": 6.066503524780273, "learning_rate": 9.316264654875945e-06, "loss": 0.3792, "step": 211620 }, { "epoch": 1.2579726685331478, "grad_norm": 3.6912829875946045, "learning_rate": 9.316159915024399e-06, "loss": 0.3674, "step": 211630 }, { "epoch": 1.2580321106098162, "grad_norm": 6.732479095458984, "learning_rate": 9.31605516773991e-06, "loss": 0.3969, "step": 211640 }, { "epoch": 1.2580915526864846, "grad_norm": 5.160379409790039, "learning_rate": 9.31595041302266e-06, "loss": 0.3755, "step": 211650 }, { "epoch": 1.258150994763153, "grad_norm": 5.3550848960876465, "learning_rate": 9.31584565087283e-06, "loss": 0.4084, "step": 211660 }, { "epoch": 1.2582104368398215, "grad_norm": 4.688901424407959, "learning_rate": 9.315740881290597e-06, "loss": 0.3838, "step": 211670 }, { "epoch": 1.25826987891649, "grad_norm": 4.623870849609375, "learning_rate": 9.315636104276145e-06, "loss": 0.386, "step": 211680 }, { "epoch": 1.258329320993158, "grad_norm": 5.00024938583374, "learning_rate": 9.315531319829652e-06, "loss": 0.3936, "step": 211690 }, { "epoch": 1.2583887630698265, "grad_norm": 4.395733833312988, "learning_rate": 9.3154265279513e-06, "loss": 0.3876, "step": 211700 }, { "epoch": 1.258448205146495, "grad_norm": 4.299642562866211, "learning_rate": 9.315321728641266e-06, "loss": 0.3921, "step": 211710 }, { "epoch": 1.2585076472231633, "grad_norm": 5.035742282867432, "learning_rate": 9.315216921899735e-06, "loss": 0.397, "step": 211720 }, { "epoch": 1.2585670892998317, "grad_norm": 6.0868401527404785, "learning_rate": 9.315112107726885e-06, "loss": 0.3993, "step": 211730 }, { "epoch": 1.2586265313765002, "grad_norm": 6.055732250213623, "learning_rate": 9.315007286122897e-06, "loss": 0.385, "step": 211740 }, { "epoch": 1.2586859734531686, "grad_norm": 6.396833419799805, "learning_rate": 9.31490245708795e-06, "loss": 0.4379, "step": 211750 }, { "epoch": 1.258745415529837, "grad_norm": 5.2689995765686035, "learning_rate": 9.314797620622229e-06, "loss": 0.3943, "step": 211760 }, { "epoch": 1.2588048576065054, "grad_norm": 4.149528980255127, "learning_rate": 9.314692776725911e-06, "loss": 0.3674, "step": 211770 }, { "epoch": 1.2588642996831738, "grad_norm": 5.553913593292236, "learning_rate": 9.314587925399177e-06, "loss": 0.3975, "step": 211780 }, { "epoch": 1.2589237417598422, "grad_norm": 4.556573867797852, "learning_rate": 9.314483066642207e-06, "loss": 0.4081, "step": 211790 }, { "epoch": 1.2589831838365106, "grad_norm": 4.974509239196777, "learning_rate": 9.314378200455183e-06, "loss": 0.3966, "step": 211800 }, { "epoch": 1.2590426259131788, "grad_norm": 6.539395332336426, "learning_rate": 9.314273326838284e-06, "loss": 0.3777, "step": 211810 }, { "epoch": 1.2591020679898473, "grad_norm": 4.844759941101074, "learning_rate": 9.314168445791694e-06, "loss": 0.3943, "step": 211820 }, { "epoch": 1.2591615100665157, "grad_norm": 5.722136497497559, "learning_rate": 9.314063557315589e-06, "loss": 0.4098, "step": 211830 }, { "epoch": 1.259220952143184, "grad_norm": 6.254887104034424, "learning_rate": 9.313958661410152e-06, "loss": 0.4511, "step": 211840 }, { "epoch": 1.2592803942198525, "grad_norm": 4.558328151702881, "learning_rate": 9.313853758075564e-06, "loss": 0.3889, "step": 211850 }, { "epoch": 1.259339836296521, "grad_norm": 5.4224534034729, "learning_rate": 9.313748847312006e-06, "loss": 0.372, "step": 211860 }, { "epoch": 1.2593992783731893, "grad_norm": 5.565971851348877, "learning_rate": 9.313643929119655e-06, "loss": 0.3892, "step": 211870 }, { "epoch": 1.2594587204498575, "grad_norm": 4.30195951461792, "learning_rate": 9.313539003498697e-06, "loss": 0.4383, "step": 211880 }, { "epoch": 1.259518162526526, "grad_norm": 6.0497283935546875, "learning_rate": 9.31343407044931e-06, "loss": 0.3931, "step": 211890 }, { "epoch": 1.2595776046031943, "grad_norm": 5.321001052856445, "learning_rate": 9.313329129971673e-06, "loss": 0.4211, "step": 211900 }, { "epoch": 1.2596370466798628, "grad_norm": 5.887043476104736, "learning_rate": 9.31322418206597e-06, "loss": 0.4324, "step": 211910 }, { "epoch": 1.2596964887565312, "grad_norm": 5.2105817794799805, "learning_rate": 9.31311922673238e-06, "loss": 0.396, "step": 211920 }, { "epoch": 1.2597559308331996, "grad_norm": 4.780110836029053, "learning_rate": 9.313014263971085e-06, "loss": 0.3596, "step": 211930 }, { "epoch": 1.259815372909868, "grad_norm": 4.874194145202637, "learning_rate": 9.312909293782263e-06, "loss": 0.4131, "step": 211940 }, { "epoch": 1.2598748149865364, "grad_norm": 4.068001747131348, "learning_rate": 9.312804316166097e-06, "loss": 0.4329, "step": 211950 }, { "epoch": 1.2599342570632048, "grad_norm": 5.963895797729492, "learning_rate": 9.312699331122767e-06, "loss": 0.3676, "step": 211960 }, { "epoch": 1.2599936991398732, "grad_norm": 3.043107271194458, "learning_rate": 9.312594338652456e-06, "loss": 0.4091, "step": 211970 }, { "epoch": 1.2600531412165417, "grad_norm": 5.397517681121826, "learning_rate": 9.312489338755343e-06, "loss": 0.3746, "step": 211980 }, { "epoch": 1.2601125832932099, "grad_norm": 4.824840545654297, "learning_rate": 9.312384331431607e-06, "loss": 0.3904, "step": 211990 }, { "epoch": 1.2601720253698783, "grad_norm": 3.800550937652588, "learning_rate": 9.312279316681433e-06, "loss": 0.372, "step": 212000 }, { "epoch": 1.2602314674465467, "grad_norm": 4.717129230499268, "learning_rate": 9.312174294504996e-06, "loss": 0.3724, "step": 212010 }, { "epoch": 1.260290909523215, "grad_norm": 6.315726280212402, "learning_rate": 9.312069264902484e-06, "loss": 0.4214, "step": 212020 }, { "epoch": 1.2603503515998835, "grad_norm": 4.882123947143555, "learning_rate": 9.311964227874072e-06, "loss": 0.3592, "step": 212030 }, { "epoch": 1.260409793676552, "grad_norm": 5.881509304046631, "learning_rate": 9.311859183419944e-06, "loss": 0.4054, "step": 212040 }, { "epoch": 1.2604692357532203, "grad_norm": 5.625136375427246, "learning_rate": 9.31175413154028e-06, "loss": 0.3707, "step": 212050 }, { "epoch": 1.2605286778298885, "grad_norm": 4.218432426452637, "learning_rate": 9.311649072235261e-06, "loss": 0.4008, "step": 212060 }, { "epoch": 1.260588119906557, "grad_norm": 4.799240589141846, "learning_rate": 9.311544005505066e-06, "loss": 0.3774, "step": 212070 }, { "epoch": 1.2606475619832254, "grad_norm": 6.014559745788574, "learning_rate": 9.311438931349879e-06, "loss": 0.366, "step": 212080 }, { "epoch": 1.2607070040598938, "grad_norm": 6.5597662925720215, "learning_rate": 9.31133384976988e-06, "loss": 0.3796, "step": 212090 }, { "epoch": 1.2607664461365622, "grad_norm": 7.494150638580322, "learning_rate": 9.31122876076525e-06, "loss": 0.4192, "step": 212100 }, { "epoch": 1.2608258882132306, "grad_norm": 5.412215232849121, "learning_rate": 9.31112366433617e-06, "loss": 0.3779, "step": 212110 }, { "epoch": 1.260885330289899, "grad_norm": 4.768380641937256, "learning_rate": 9.311018560482818e-06, "loss": 0.4032, "step": 212120 }, { "epoch": 1.2609447723665674, "grad_norm": 5.671905994415283, "learning_rate": 9.310913449205382e-06, "loss": 0.3782, "step": 212130 }, { "epoch": 1.2610042144432358, "grad_norm": 3.7324657440185547, "learning_rate": 9.310808330504036e-06, "loss": 0.3595, "step": 212140 }, { "epoch": 1.2610636565199043, "grad_norm": 4.9900336265563965, "learning_rate": 9.310703204378964e-06, "loss": 0.4112, "step": 212150 }, { "epoch": 1.2611230985965727, "grad_norm": 5.12758207321167, "learning_rate": 9.310598070830345e-06, "loss": 0.4056, "step": 212160 }, { "epoch": 1.261182540673241, "grad_norm": 5.302170753479004, "learning_rate": 9.310492929858363e-06, "loss": 0.3857, "step": 212170 }, { "epoch": 1.2612419827499093, "grad_norm": 4.294308185577393, "learning_rate": 9.3103877814632e-06, "loss": 0.3994, "step": 212180 }, { "epoch": 1.2613014248265777, "grad_norm": 4.212962627410889, "learning_rate": 9.310282625645032e-06, "loss": 0.4131, "step": 212190 }, { "epoch": 1.2613608669032461, "grad_norm": 4.108173847198486, "learning_rate": 9.310177462404044e-06, "loss": 0.3502, "step": 212200 }, { "epoch": 1.2614203089799145, "grad_norm": 5.574644088745117, "learning_rate": 9.310072291740418e-06, "loss": 0.4107, "step": 212210 }, { "epoch": 1.261479751056583, "grad_norm": 5.139553070068359, "learning_rate": 9.30996711365433e-06, "loss": 0.3764, "step": 212220 }, { "epoch": 1.2615391931332514, "grad_norm": 5.28045129776001, "learning_rate": 9.309861928145966e-06, "loss": 0.4108, "step": 212230 }, { "epoch": 1.2615986352099198, "grad_norm": 3.842392683029175, "learning_rate": 9.309756735215508e-06, "loss": 0.3577, "step": 212240 }, { "epoch": 1.261658077286588, "grad_norm": 4.671679496765137, "learning_rate": 9.309651534863131e-06, "loss": 0.3885, "step": 212250 }, { "epoch": 1.2617175193632564, "grad_norm": 6.334003448486328, "learning_rate": 9.30954632708902e-06, "loss": 0.3842, "step": 212260 }, { "epoch": 1.2617769614399248, "grad_norm": 4.490030288696289, "learning_rate": 9.309441111893359e-06, "loss": 0.3807, "step": 212270 }, { "epoch": 1.2618364035165932, "grad_norm": 4.433351039886475, "learning_rate": 9.309335889276323e-06, "loss": 0.3892, "step": 212280 }, { "epoch": 1.2618958455932616, "grad_norm": 4.539186477661133, "learning_rate": 9.309230659238097e-06, "loss": 0.3945, "step": 212290 }, { "epoch": 1.26195528766993, "grad_norm": 5.8756608963012695, "learning_rate": 9.309125421778862e-06, "loss": 0.3876, "step": 212300 }, { "epoch": 1.2620147297465985, "grad_norm": 5.800599575042725, "learning_rate": 9.309020176898799e-06, "loss": 0.4454, "step": 212310 }, { "epoch": 1.2620741718232669, "grad_norm": 3.323629140853882, "learning_rate": 9.308914924598092e-06, "loss": 0.3708, "step": 212320 }, { "epoch": 1.2621336138999353, "grad_norm": 4.833123683929443, "learning_rate": 9.308809664876915e-06, "loss": 0.3975, "step": 212330 }, { "epoch": 1.2621930559766037, "grad_norm": 5.175973415374756, "learning_rate": 9.308704397735456e-06, "loss": 0.3851, "step": 212340 }, { "epoch": 1.262252498053272, "grad_norm": 4.4637064933776855, "learning_rate": 9.308599123173893e-06, "loss": 0.3421, "step": 212350 }, { "epoch": 1.2623119401299403, "grad_norm": 4.568337917327881, "learning_rate": 9.30849384119241e-06, "loss": 0.3702, "step": 212360 }, { "epoch": 1.2623713822066087, "grad_norm": 5.176529407501221, "learning_rate": 9.308388551791183e-06, "loss": 0.377, "step": 212370 }, { "epoch": 1.2624308242832771, "grad_norm": 5.471601486206055, "learning_rate": 9.308283254970399e-06, "loss": 0.3681, "step": 212380 }, { "epoch": 1.2624902663599455, "grad_norm": 6.360265254974365, "learning_rate": 9.308177950730238e-06, "loss": 0.3765, "step": 212390 }, { "epoch": 1.262549708436614, "grad_norm": 6.775488376617432, "learning_rate": 9.308072639070878e-06, "loss": 0.4173, "step": 212400 }, { "epoch": 1.2626091505132824, "grad_norm": 6.127389907836914, "learning_rate": 9.307967319992506e-06, "loss": 0.3958, "step": 212410 }, { "epoch": 1.2626685925899508, "grad_norm": 3.5567150115966797, "learning_rate": 9.307861993495297e-06, "loss": 0.3811, "step": 212420 }, { "epoch": 1.262728034666619, "grad_norm": 3.8939647674560547, "learning_rate": 9.307756659579439e-06, "loss": 0.4113, "step": 212430 }, { "epoch": 1.2627874767432874, "grad_norm": 4.414266109466553, "learning_rate": 9.307651318245108e-06, "loss": 0.365, "step": 212440 }, { "epoch": 1.2628469188199558, "grad_norm": 6.6732611656188965, "learning_rate": 9.307545969492488e-06, "loss": 0.4165, "step": 212450 }, { "epoch": 1.2629063608966242, "grad_norm": 5.540313243865967, "learning_rate": 9.307440613321759e-06, "loss": 0.37, "step": 212460 }, { "epoch": 1.2629658029732926, "grad_norm": 5.565810680389404, "learning_rate": 9.307335249733105e-06, "loss": 0.4009, "step": 212470 }, { "epoch": 1.263025245049961, "grad_norm": 6.2688703536987305, "learning_rate": 9.307229878726705e-06, "loss": 0.3935, "step": 212480 }, { "epoch": 1.2630846871266295, "grad_norm": 3.883897066116333, "learning_rate": 9.30712450030274e-06, "loss": 0.3744, "step": 212490 }, { "epoch": 1.2631441292032979, "grad_norm": 6.400665283203125, "learning_rate": 9.307019114461393e-06, "loss": 0.393, "step": 212500 }, { "epoch": 1.2632035712799663, "grad_norm": 4.832909107208252, "learning_rate": 9.306913721202846e-06, "loss": 0.3744, "step": 212510 }, { "epoch": 1.2632630133566347, "grad_norm": 7.143001079559326, "learning_rate": 9.30680832052728e-06, "loss": 0.3686, "step": 212520 }, { "epoch": 1.2633224554333031, "grad_norm": 5.120278358459473, "learning_rate": 9.306702912434876e-06, "loss": 0.3553, "step": 212530 }, { "epoch": 1.2633818975099715, "grad_norm": 7.911155700683594, "learning_rate": 9.306597496925816e-06, "loss": 0.4239, "step": 212540 }, { "epoch": 1.2634413395866397, "grad_norm": 5.124356269836426, "learning_rate": 9.306492074000279e-06, "loss": 0.3764, "step": 212550 }, { "epoch": 1.2635007816633081, "grad_norm": 3.917422294616699, "learning_rate": 9.306386643658452e-06, "loss": 0.3416, "step": 212560 }, { "epoch": 1.2635602237399766, "grad_norm": 4.43225622177124, "learning_rate": 9.306281205900512e-06, "loss": 0.3892, "step": 212570 }, { "epoch": 1.263619665816645, "grad_norm": 5.448544025421143, "learning_rate": 9.306175760726642e-06, "loss": 0.3941, "step": 212580 }, { "epoch": 1.2636791078933134, "grad_norm": 4.060577392578125, "learning_rate": 9.306070308137022e-06, "loss": 0.3763, "step": 212590 }, { "epoch": 1.2637385499699818, "grad_norm": 5.285868167877197, "learning_rate": 9.305964848131837e-06, "loss": 0.3589, "step": 212600 }, { "epoch": 1.2637979920466502, "grad_norm": 3.709425449371338, "learning_rate": 9.305859380711267e-06, "loss": 0.3964, "step": 212610 }, { "epoch": 1.2638574341233184, "grad_norm": 6.8441481590271, "learning_rate": 9.305753905875492e-06, "loss": 0.364, "step": 212620 }, { "epoch": 1.2639168761999868, "grad_norm": 5.209945201873779, "learning_rate": 9.305648423624696e-06, "loss": 0.4128, "step": 212630 }, { "epoch": 1.2639763182766552, "grad_norm": 4.143743991851807, "learning_rate": 9.305542933959057e-06, "loss": 0.375, "step": 212640 }, { "epoch": 1.2640357603533237, "grad_norm": 5.840458393096924, "learning_rate": 9.305437436878764e-06, "loss": 0.4079, "step": 212650 }, { "epoch": 1.264095202429992, "grad_norm": 5.5957865715026855, "learning_rate": 9.30533193238399e-06, "loss": 0.3474, "step": 212660 }, { "epoch": 1.2641546445066605, "grad_norm": 5.772006034851074, "learning_rate": 9.305226420474924e-06, "loss": 0.3689, "step": 212670 }, { "epoch": 1.264214086583329, "grad_norm": 5.165313720703125, "learning_rate": 9.305120901151742e-06, "loss": 0.3971, "step": 212680 }, { "epoch": 1.2642735286599973, "grad_norm": 4.790052890777588, "learning_rate": 9.305015374414628e-06, "loss": 0.4075, "step": 212690 }, { "epoch": 1.2643329707366657, "grad_norm": 5.968373775482178, "learning_rate": 9.304909840263766e-06, "loss": 0.3486, "step": 212700 }, { "epoch": 1.2643924128133341, "grad_norm": 5.109405994415283, "learning_rate": 9.304804298699334e-06, "loss": 0.4079, "step": 212710 }, { "epoch": 1.2644518548900026, "grad_norm": 5.951296329498291, "learning_rate": 9.304698749721515e-06, "loss": 0.399, "step": 212720 }, { "epoch": 1.2645112969666708, "grad_norm": 5.301070690155029, "learning_rate": 9.304593193330493e-06, "loss": 0.3983, "step": 212730 }, { "epoch": 1.2645707390433392, "grad_norm": 5.3549628257751465, "learning_rate": 9.304487629526447e-06, "loss": 0.3233, "step": 212740 }, { "epoch": 1.2646301811200076, "grad_norm": 5.3585591316223145, "learning_rate": 9.30438205830956e-06, "loss": 0.347, "step": 212750 }, { "epoch": 1.264689623196676, "grad_norm": 6.8576340675354, "learning_rate": 9.304276479680012e-06, "loss": 0.3611, "step": 212760 }, { "epoch": 1.2647490652733444, "grad_norm": 4.647834300994873, "learning_rate": 9.304170893637987e-06, "loss": 0.4388, "step": 212770 }, { "epoch": 1.2648085073500128, "grad_norm": 5.4251861572265625, "learning_rate": 9.304065300183666e-06, "loss": 0.4106, "step": 212780 }, { "epoch": 1.2648679494266812, "grad_norm": 6.783638000488281, "learning_rate": 9.30395969931723e-06, "loss": 0.3868, "step": 212790 }, { "epoch": 1.2649273915033494, "grad_norm": 5.9092631340026855, "learning_rate": 9.303854091038866e-06, "loss": 0.3849, "step": 212800 }, { "epoch": 1.2649868335800178, "grad_norm": 6.952226638793945, "learning_rate": 9.303748475348749e-06, "loss": 0.4036, "step": 212810 }, { "epoch": 1.2650462756566863, "grad_norm": 5.750553131103516, "learning_rate": 9.303642852247064e-06, "loss": 0.3984, "step": 212820 }, { "epoch": 1.2651057177333547, "grad_norm": 4.914551734924316, "learning_rate": 9.30353722173399e-06, "loss": 0.4178, "step": 212830 }, { "epoch": 1.265165159810023, "grad_norm": 5.836183547973633, "learning_rate": 9.303431583809715e-06, "loss": 0.4074, "step": 212840 }, { "epoch": 1.2652246018866915, "grad_norm": 4.04323148727417, "learning_rate": 9.303325938474416e-06, "loss": 0.3732, "step": 212850 }, { "epoch": 1.26528404396336, "grad_norm": 6.485874176025391, "learning_rate": 9.303220285728276e-06, "loss": 0.4024, "step": 212860 }, { "epoch": 1.2653434860400283, "grad_norm": 4.86863899230957, "learning_rate": 9.303114625571476e-06, "loss": 0.3564, "step": 212870 }, { "epoch": 1.2654029281166967, "grad_norm": 5.136256217956543, "learning_rate": 9.303008958004202e-06, "loss": 0.4548, "step": 212880 }, { "epoch": 1.2654623701933652, "grad_norm": 6.177566051483154, "learning_rate": 9.30290328302663e-06, "loss": 0.3911, "step": 212890 }, { "epoch": 1.2655218122700336, "grad_norm": 5.630335807800293, "learning_rate": 9.302797600638949e-06, "loss": 0.4216, "step": 212900 }, { "epoch": 1.265581254346702, "grad_norm": 5.882184982299805, "learning_rate": 9.302691910841334e-06, "loss": 0.3725, "step": 212910 }, { "epoch": 1.2656406964233702, "grad_norm": 5.198927879333496, "learning_rate": 9.30258621363397e-06, "loss": 0.3595, "step": 212920 }, { "epoch": 1.2657001385000386, "grad_norm": 3.558880567550659, "learning_rate": 9.302480509017043e-06, "loss": 0.4087, "step": 212930 }, { "epoch": 1.265759580576707, "grad_norm": 5.303025722503662, "learning_rate": 9.302374796990727e-06, "loss": 0.3849, "step": 212940 }, { "epoch": 1.2658190226533754, "grad_norm": 5.0054030418396, "learning_rate": 9.30226907755521e-06, "loss": 0.3759, "step": 212950 }, { "epoch": 1.2658784647300438, "grad_norm": 5.228458881378174, "learning_rate": 9.30216335071067e-06, "loss": 0.4233, "step": 212960 }, { "epoch": 1.2659379068067123, "grad_norm": 5.1287841796875, "learning_rate": 9.302057616457295e-06, "loss": 0.454, "step": 212970 }, { "epoch": 1.2659973488833807, "grad_norm": 5.560808181762695, "learning_rate": 9.301951874795261e-06, "loss": 0.3615, "step": 212980 }, { "epoch": 1.2660567909600489, "grad_norm": 5.310404300689697, "learning_rate": 9.301846125724754e-06, "loss": 0.3893, "step": 212990 }, { "epoch": 1.2661162330367173, "grad_norm": 4.62162446975708, "learning_rate": 9.301740369245953e-06, "loss": 0.3804, "step": 213000 }, { "epoch": 1.2661756751133857, "grad_norm": 5.865492343902588, "learning_rate": 9.301634605359044e-06, "loss": 0.3695, "step": 213010 }, { "epoch": 1.266235117190054, "grad_norm": 5.467318058013916, "learning_rate": 9.301528834064206e-06, "loss": 0.3858, "step": 213020 }, { "epoch": 1.2662945592667225, "grad_norm": 4.694089889526367, "learning_rate": 9.301423055361623e-06, "loss": 0.4004, "step": 213030 }, { "epoch": 1.266354001343391, "grad_norm": 5.271993637084961, "learning_rate": 9.301317269251476e-06, "loss": 0.4028, "step": 213040 }, { "epoch": 1.2664134434200593, "grad_norm": 5.999131679534912, "learning_rate": 9.301211475733946e-06, "loss": 0.4007, "step": 213050 }, { "epoch": 1.2664728854967278, "grad_norm": 4.16355562210083, "learning_rate": 9.301105674809216e-06, "loss": 0.3367, "step": 213060 }, { "epoch": 1.2665323275733962, "grad_norm": 5.5757646560668945, "learning_rate": 9.300999866477471e-06, "loss": 0.3979, "step": 213070 }, { "epoch": 1.2665917696500646, "grad_norm": 6.442595481872559, "learning_rate": 9.30089405073889e-06, "loss": 0.4443, "step": 213080 }, { "epoch": 1.266651211726733, "grad_norm": 5.367482662200928, "learning_rate": 9.300788227593656e-06, "loss": 0.4302, "step": 213090 }, { "epoch": 1.2667106538034012, "grad_norm": 6.247208118438721, "learning_rate": 9.300682397041952e-06, "loss": 0.3882, "step": 213100 }, { "epoch": 1.2667700958800696, "grad_norm": 4.461869716644287, "learning_rate": 9.300576559083961e-06, "loss": 0.4543, "step": 213110 }, { "epoch": 1.266829537956738, "grad_norm": 4.3937907218933105, "learning_rate": 9.300470713719863e-06, "loss": 0.3559, "step": 213120 }, { "epoch": 1.2668889800334064, "grad_norm": 4.5960469245910645, "learning_rate": 9.30036486094984e-06, "loss": 0.3738, "step": 213130 }, { "epoch": 1.2669484221100749, "grad_norm": 5.341116905212402, "learning_rate": 9.300259000774077e-06, "loss": 0.4128, "step": 213140 }, { "epoch": 1.2670078641867433, "grad_norm": 4.795694351196289, "learning_rate": 9.300153133192754e-06, "loss": 0.3933, "step": 213150 }, { "epoch": 1.2670673062634117, "grad_norm": 5.702805042266846, "learning_rate": 9.300047258206055e-06, "loss": 0.3848, "step": 213160 }, { "epoch": 1.2671267483400799, "grad_norm": 6.481991767883301, "learning_rate": 9.29994137581416e-06, "loss": 0.3779, "step": 213170 }, { "epoch": 1.2671861904167483, "grad_norm": 5.443138122558594, "learning_rate": 9.299835486017255e-06, "loss": 0.3668, "step": 213180 }, { "epoch": 1.2672456324934167, "grad_norm": 5.167536735534668, "learning_rate": 9.29972958881552e-06, "loss": 0.3591, "step": 213190 }, { "epoch": 1.2673050745700851, "grad_norm": 4.325425148010254, "learning_rate": 9.299623684209136e-06, "loss": 0.38, "step": 213200 }, { "epoch": 1.2673645166467535, "grad_norm": 4.4995951652526855, "learning_rate": 9.29951777219829e-06, "loss": 0.3796, "step": 213210 }, { "epoch": 1.267423958723422, "grad_norm": 4.560125350952148, "learning_rate": 9.299411852783157e-06, "loss": 0.4041, "step": 213220 }, { "epoch": 1.2674834008000904, "grad_norm": 5.137107849121094, "learning_rate": 9.299305925963929e-06, "loss": 0.3801, "step": 213230 }, { "epoch": 1.2675428428767588, "grad_norm": 5.091676235198975, "learning_rate": 9.299199991740779e-06, "loss": 0.3467, "step": 213240 }, { "epoch": 1.2676022849534272, "grad_norm": 4.756208896636963, "learning_rate": 9.299094050113895e-06, "loss": 0.417, "step": 213250 }, { "epoch": 1.2676617270300956, "grad_norm": 3.9855029582977295, "learning_rate": 9.29898810108346e-06, "loss": 0.3601, "step": 213260 }, { "epoch": 1.267721169106764, "grad_norm": 5.296408176422119, "learning_rate": 9.298882144649652e-06, "loss": 0.4368, "step": 213270 }, { "epoch": 1.2677806111834324, "grad_norm": 6.204514503479004, "learning_rate": 9.298776180812656e-06, "loss": 0.4198, "step": 213280 }, { "epoch": 1.2678400532601006, "grad_norm": 6.650757312774658, "learning_rate": 9.298670209572656e-06, "loss": 0.3935, "step": 213290 }, { "epoch": 1.267899495336769, "grad_norm": 3.7958078384399414, "learning_rate": 9.298564230929832e-06, "loss": 0.37, "step": 213300 }, { "epoch": 1.2679589374134375, "grad_norm": 4.351587772369385, "learning_rate": 9.298458244884368e-06, "loss": 0.3469, "step": 213310 }, { "epoch": 1.2680183794901059, "grad_norm": 7.747364521026611, "learning_rate": 9.298352251436444e-06, "loss": 0.4059, "step": 213320 }, { "epoch": 1.2680778215667743, "grad_norm": 5.256741046905518, "learning_rate": 9.298246250586247e-06, "loss": 0.3489, "step": 213330 }, { "epoch": 1.2681372636434427, "grad_norm": 4.9856414794921875, "learning_rate": 9.298140242333957e-06, "loss": 0.3934, "step": 213340 }, { "epoch": 1.2681967057201111, "grad_norm": 4.66489315032959, "learning_rate": 9.298034226679755e-06, "loss": 0.3828, "step": 213350 }, { "epoch": 1.2682561477967793, "grad_norm": 4.883203029632568, "learning_rate": 9.297928203623827e-06, "loss": 0.41, "step": 213360 }, { "epoch": 1.2683155898734477, "grad_norm": 4.616685390472412, "learning_rate": 9.297822173166353e-06, "loss": 0.3994, "step": 213370 }, { "epoch": 1.2683750319501161, "grad_norm": 5.30105447769165, "learning_rate": 9.297716135307518e-06, "loss": 0.4013, "step": 213380 }, { "epoch": 1.2684344740267846, "grad_norm": 4.505061149597168, "learning_rate": 9.2976100900475e-06, "loss": 0.3657, "step": 213390 }, { "epoch": 1.268493916103453, "grad_norm": 5.323044300079346, "learning_rate": 9.297504037386487e-06, "loss": 0.4122, "step": 213400 }, { "epoch": 1.2685533581801214, "grad_norm": 4.951785564422607, "learning_rate": 9.297397977324658e-06, "loss": 0.3719, "step": 213410 }, { "epoch": 1.2686128002567898, "grad_norm": 4.7195305824279785, "learning_rate": 9.297291909862197e-06, "loss": 0.4011, "step": 213420 }, { "epoch": 1.2686722423334582, "grad_norm": 4.786567211151123, "learning_rate": 9.297185834999288e-06, "loss": 0.3943, "step": 213430 }, { "epoch": 1.2687316844101266, "grad_norm": 6.3483357429504395, "learning_rate": 9.297079752736112e-06, "loss": 0.3762, "step": 213440 }, { "epoch": 1.268791126486795, "grad_norm": 5.019558906555176, "learning_rate": 9.29697366307285e-06, "loss": 0.4244, "step": 213450 }, { "epoch": 1.2688505685634635, "grad_norm": 6.647223949432373, "learning_rate": 9.296867566009688e-06, "loss": 0.4154, "step": 213460 }, { "epoch": 1.2689100106401316, "grad_norm": 4.753612518310547, "learning_rate": 9.296761461546807e-06, "loss": 0.4008, "step": 213470 }, { "epoch": 1.2689694527168, "grad_norm": 5.69119119644165, "learning_rate": 9.29665534968439e-06, "loss": 0.38, "step": 213480 }, { "epoch": 1.2690288947934685, "grad_norm": 6.089683532714844, "learning_rate": 9.29654923042262e-06, "loss": 0.4272, "step": 213490 }, { "epoch": 1.269088336870137, "grad_norm": 5.732782363891602, "learning_rate": 9.29644310376168e-06, "loss": 0.4103, "step": 213500 }, { "epoch": 1.2691477789468053, "grad_norm": 6.985897541046143, "learning_rate": 9.29633696970175e-06, "loss": 0.4168, "step": 213510 }, { "epoch": 1.2692072210234737, "grad_norm": 5.779684066772461, "learning_rate": 9.296230828243018e-06, "loss": 0.3992, "step": 213520 }, { "epoch": 1.2692666631001421, "grad_norm": 5.528343677520752, "learning_rate": 9.296124679385664e-06, "loss": 0.3963, "step": 213530 }, { "epoch": 1.2693261051768103, "grad_norm": 5.588128566741943, "learning_rate": 9.296018523129869e-06, "loss": 0.4105, "step": 213540 }, { "epoch": 1.2693855472534787, "grad_norm": 6.068502902984619, "learning_rate": 9.295912359475819e-06, "loss": 0.3661, "step": 213550 }, { "epoch": 1.2694449893301472, "grad_norm": 4.680022716522217, "learning_rate": 9.295806188423694e-06, "loss": 0.411, "step": 213560 }, { "epoch": 1.2695044314068156, "grad_norm": 6.018226146697998, "learning_rate": 9.295700009973679e-06, "loss": 0.4179, "step": 213570 }, { "epoch": 1.269563873483484, "grad_norm": 5.603877544403076, "learning_rate": 9.295593824125955e-06, "loss": 0.3772, "step": 213580 }, { "epoch": 1.2696233155601524, "grad_norm": 5.401582717895508, "learning_rate": 9.295487630880707e-06, "loss": 0.3628, "step": 213590 }, { "epoch": 1.2696827576368208, "grad_norm": 5.063644886016846, "learning_rate": 9.295381430238118e-06, "loss": 0.4063, "step": 213600 }, { "epoch": 1.2697421997134892, "grad_norm": 4.917556285858154, "learning_rate": 9.295275222198367e-06, "loss": 0.391, "step": 213610 }, { "epoch": 1.2698016417901576, "grad_norm": 6.013174533843994, "learning_rate": 9.29516900676164e-06, "loss": 0.4185, "step": 213620 }, { "epoch": 1.269861083866826, "grad_norm": 5.3643999099731445, "learning_rate": 9.29506278392812e-06, "loss": 0.3838, "step": 213630 }, { "epoch": 1.2699205259434945, "grad_norm": 5.7825775146484375, "learning_rate": 9.294956553697988e-06, "loss": 0.3622, "step": 213640 }, { "epoch": 1.2699799680201629, "grad_norm": 5.279777526855469, "learning_rate": 9.294850316071431e-06, "loss": 0.4296, "step": 213650 }, { "epoch": 1.270039410096831, "grad_norm": 4.370816230773926, "learning_rate": 9.294744071048629e-06, "loss": 0.4173, "step": 213660 }, { "epoch": 1.2700988521734995, "grad_norm": 4.3418450355529785, "learning_rate": 9.294637818629764e-06, "loss": 0.3844, "step": 213670 }, { "epoch": 1.270158294250168, "grad_norm": 5.119439125061035, "learning_rate": 9.29453155881502e-06, "loss": 0.3978, "step": 213680 }, { "epoch": 1.2702177363268363, "grad_norm": 5.831460952758789, "learning_rate": 9.294425291604582e-06, "loss": 0.386, "step": 213690 }, { "epoch": 1.2702771784035047, "grad_norm": 5.9075822830200195, "learning_rate": 9.29431901699863e-06, "loss": 0.399, "step": 213700 }, { "epoch": 1.2703366204801732, "grad_norm": 4.450274467468262, "learning_rate": 9.294212734997347e-06, "loss": 0.406, "step": 213710 }, { "epoch": 1.2703960625568416, "grad_norm": 5.266371250152588, "learning_rate": 9.29410644560092e-06, "loss": 0.3553, "step": 213720 }, { "epoch": 1.2704555046335098, "grad_norm": 4.452884674072266, "learning_rate": 9.294000148809528e-06, "loss": 0.3809, "step": 213730 }, { "epoch": 1.2705149467101782, "grad_norm": 3.8152718544006348, "learning_rate": 9.293893844623355e-06, "loss": 0.3779, "step": 213740 }, { "epoch": 1.2705743887868466, "grad_norm": 5.6217427253723145, "learning_rate": 9.293787533042586e-06, "loss": 0.3978, "step": 213750 }, { "epoch": 1.270633830863515, "grad_norm": 4.7953033447265625, "learning_rate": 9.293681214067401e-06, "loss": 0.3925, "step": 213760 }, { "epoch": 1.2706932729401834, "grad_norm": 4.617581367492676, "learning_rate": 9.293574887697985e-06, "loss": 0.3944, "step": 213770 }, { "epoch": 1.2707527150168518, "grad_norm": 4.875343322753906, "learning_rate": 9.293468553934522e-06, "loss": 0.4548, "step": 213780 }, { "epoch": 1.2708121570935202, "grad_norm": 4.831484794616699, "learning_rate": 9.293362212777191e-06, "loss": 0.41, "step": 213790 }, { "epoch": 1.2708715991701887, "grad_norm": 4.258354663848877, "learning_rate": 9.293255864226181e-06, "loss": 0.3799, "step": 213800 }, { "epoch": 1.270931041246857, "grad_norm": 4.782198429107666, "learning_rate": 9.293149508281671e-06, "loss": 0.3571, "step": 213810 }, { "epoch": 1.2709904833235255, "grad_norm": 5.69854211807251, "learning_rate": 9.293043144943846e-06, "loss": 0.3646, "step": 213820 }, { "epoch": 1.271049925400194, "grad_norm": 5.967484474182129, "learning_rate": 9.292936774212887e-06, "loss": 0.3673, "step": 213830 }, { "epoch": 1.271109367476862, "grad_norm": 5.757839679718018, "learning_rate": 9.292830396088978e-06, "loss": 0.4024, "step": 213840 }, { "epoch": 1.2711688095535305, "grad_norm": 5.749485492706299, "learning_rate": 9.292724010572305e-06, "loss": 0.3851, "step": 213850 }, { "epoch": 1.271228251630199, "grad_norm": 4.03425931930542, "learning_rate": 9.292617617663047e-06, "loss": 0.4526, "step": 213860 }, { "epoch": 1.2712876937068673, "grad_norm": 5.071951389312744, "learning_rate": 9.29251121736139e-06, "loss": 0.3777, "step": 213870 }, { "epoch": 1.2713471357835358, "grad_norm": 6.235197067260742, "learning_rate": 9.292404809667517e-06, "loss": 0.3559, "step": 213880 }, { "epoch": 1.2714065778602042, "grad_norm": 5.88637638092041, "learning_rate": 9.292298394581612e-06, "loss": 0.4286, "step": 213890 }, { "epoch": 1.2714660199368726, "grad_norm": 5.706225872039795, "learning_rate": 9.292191972103855e-06, "loss": 0.3791, "step": 213900 }, { "epoch": 1.2715254620135408, "grad_norm": 7.721365928649902, "learning_rate": 9.292085542234432e-06, "loss": 0.4328, "step": 213910 }, { "epoch": 1.2715849040902092, "grad_norm": 4.491693019866943, "learning_rate": 9.291979104973526e-06, "loss": 0.3732, "step": 213920 }, { "epoch": 1.2716443461668776, "grad_norm": 6.408070087432861, "learning_rate": 9.291872660321319e-06, "loss": 0.4105, "step": 213930 }, { "epoch": 1.271703788243546, "grad_norm": 4.530360221862793, "learning_rate": 9.291766208277995e-06, "loss": 0.4092, "step": 213940 }, { "epoch": 1.2717632303202144, "grad_norm": 5.001097202301025, "learning_rate": 9.291659748843738e-06, "loss": 0.3824, "step": 213950 }, { "epoch": 1.2718226723968828, "grad_norm": 5.09372615814209, "learning_rate": 9.291553282018731e-06, "loss": 0.3959, "step": 213960 }, { "epoch": 1.2718821144735513, "grad_norm": 5.1946821212768555, "learning_rate": 9.291446807803156e-06, "loss": 0.4279, "step": 213970 }, { "epoch": 1.2719415565502197, "grad_norm": 4.828627586364746, "learning_rate": 9.2913403261972e-06, "loss": 0.419, "step": 213980 }, { "epoch": 1.272000998626888, "grad_norm": 6.036613464355469, "learning_rate": 9.291233837201043e-06, "loss": 0.4171, "step": 213990 }, { "epoch": 1.2720604407035565, "grad_norm": 4.052611827850342, "learning_rate": 9.291127340814869e-06, "loss": 0.3949, "step": 214000 }, { "epoch": 1.272119882780225, "grad_norm": 5.177825927734375, "learning_rate": 9.291020837038862e-06, "loss": 0.4108, "step": 214010 }, { "epoch": 1.2721793248568933, "grad_norm": 4.730538845062256, "learning_rate": 9.290914325873203e-06, "loss": 0.3861, "step": 214020 }, { "epoch": 1.2722387669335615, "grad_norm": 3.5137133598327637, "learning_rate": 9.290807807318081e-06, "loss": 0.3963, "step": 214030 }, { "epoch": 1.27229820901023, "grad_norm": 5.963936805725098, "learning_rate": 9.290701281373674e-06, "loss": 0.3935, "step": 214040 }, { "epoch": 1.2723576510868984, "grad_norm": 5.526973724365234, "learning_rate": 9.290594748040167e-06, "loss": 0.4014, "step": 214050 }, { "epoch": 1.2724170931635668, "grad_norm": 4.297657489776611, "learning_rate": 9.290488207317745e-06, "loss": 0.369, "step": 214060 }, { "epoch": 1.2724765352402352, "grad_norm": 6.06746768951416, "learning_rate": 9.29038165920659e-06, "loss": 0.3796, "step": 214070 }, { "epoch": 1.2725359773169036, "grad_norm": 6.13091516494751, "learning_rate": 9.290275103706887e-06, "loss": 0.3867, "step": 214080 }, { "epoch": 1.272595419393572, "grad_norm": 5.968693733215332, "learning_rate": 9.290168540818816e-06, "loss": 0.3992, "step": 214090 }, { "epoch": 1.2726548614702402, "grad_norm": 5.342940807342529, "learning_rate": 9.290061970542565e-06, "loss": 0.4203, "step": 214100 }, { "epoch": 1.2727143035469086, "grad_norm": 4.798439979553223, "learning_rate": 9.289955392878314e-06, "loss": 0.3991, "step": 214110 }, { "epoch": 1.272773745623577, "grad_norm": 6.094692230224609, "learning_rate": 9.289848807826249e-06, "loss": 0.4498, "step": 214120 }, { "epoch": 1.2728331877002454, "grad_norm": 5.720115661621094, "learning_rate": 9.289742215386552e-06, "loss": 0.4406, "step": 214130 }, { "epoch": 1.2728926297769139, "grad_norm": 5.3253397941589355, "learning_rate": 9.289635615559408e-06, "loss": 0.4211, "step": 214140 }, { "epoch": 1.2729520718535823, "grad_norm": 4.561988353729248, "learning_rate": 9.289529008344998e-06, "loss": 0.3925, "step": 214150 }, { "epoch": 1.2730115139302507, "grad_norm": 4.679141521453857, "learning_rate": 9.289422393743507e-06, "loss": 0.3757, "step": 214160 }, { "epoch": 1.273070956006919, "grad_norm": 4.6610260009765625, "learning_rate": 9.289315771755119e-06, "loss": 0.4108, "step": 214170 }, { "epoch": 1.2731303980835875, "grad_norm": 5.533139705657959, "learning_rate": 9.289209142380018e-06, "loss": 0.3917, "step": 214180 }, { "epoch": 1.273189840160256, "grad_norm": 5.373917579650879, "learning_rate": 9.289102505618389e-06, "loss": 0.389, "step": 214190 }, { "epoch": 1.2732492822369244, "grad_norm": 4.8596696853637695, "learning_rate": 9.28899586147041e-06, "loss": 0.3676, "step": 214200 }, { "epoch": 1.2733087243135925, "grad_norm": 4.5309247970581055, "learning_rate": 9.288889209936272e-06, "loss": 0.3669, "step": 214210 }, { "epoch": 1.273368166390261, "grad_norm": 3.9910764694213867, "learning_rate": 9.288782551016153e-06, "loss": 0.3582, "step": 214220 }, { "epoch": 1.2734276084669294, "grad_norm": 5.88350248336792, "learning_rate": 9.28867588471024e-06, "loss": 0.4107, "step": 214230 }, { "epoch": 1.2734870505435978, "grad_norm": 5.621830463409424, "learning_rate": 9.288569211018712e-06, "loss": 0.3807, "step": 214240 }, { "epoch": 1.2735464926202662, "grad_norm": 5.727417945861816, "learning_rate": 9.28846252994176e-06, "loss": 0.3429, "step": 214250 }, { "epoch": 1.2736059346969346, "grad_norm": 4.137085437774658, "learning_rate": 9.288355841479561e-06, "loss": 0.38, "step": 214260 }, { "epoch": 1.273665376773603, "grad_norm": 4.437970161437988, "learning_rate": 9.288249145632303e-06, "loss": 0.3765, "step": 214270 }, { "epoch": 1.2737248188502712, "grad_norm": 6.238731384277344, "learning_rate": 9.28814244240017e-06, "loss": 0.3828, "step": 214280 }, { "epoch": 1.2737842609269396, "grad_norm": 5.656424045562744, "learning_rate": 9.288035731783343e-06, "loss": 0.4196, "step": 214290 }, { "epoch": 1.273843703003608, "grad_norm": 5.733041286468506, "learning_rate": 9.287929013782004e-06, "loss": 0.4115, "step": 214300 }, { "epoch": 1.2739031450802765, "grad_norm": 5.197347640991211, "learning_rate": 9.287822288396343e-06, "loss": 0.3882, "step": 214310 }, { "epoch": 1.2739625871569449, "grad_norm": 6.3834943771362305, "learning_rate": 9.287715555626539e-06, "loss": 0.3898, "step": 214320 }, { "epoch": 1.2740220292336133, "grad_norm": 5.6892571449279785, "learning_rate": 9.287608815472777e-06, "loss": 0.4086, "step": 214330 }, { "epoch": 1.2740814713102817, "grad_norm": 5.756380081176758, "learning_rate": 9.287502067935242e-06, "loss": 0.4192, "step": 214340 }, { "epoch": 1.2741409133869501, "grad_norm": 6.486628532409668, "learning_rate": 9.287395313014115e-06, "loss": 0.3818, "step": 214350 }, { "epoch": 1.2742003554636185, "grad_norm": 6.8201680183410645, "learning_rate": 9.287288550709583e-06, "loss": 0.3944, "step": 214360 }, { "epoch": 1.274259797540287, "grad_norm": 4.672975540161133, "learning_rate": 9.28718178102183e-06, "loss": 0.3725, "step": 214370 }, { "epoch": 1.2743192396169554, "grad_norm": 4.541365146636963, "learning_rate": 9.287075003951036e-06, "loss": 0.3865, "step": 214380 }, { "epoch": 1.2743786816936238, "grad_norm": 5.733573913574219, "learning_rate": 9.286968219497389e-06, "loss": 0.3783, "step": 214390 }, { "epoch": 1.274438123770292, "grad_norm": 5.437792778015137, "learning_rate": 9.286861427661071e-06, "loss": 0.3955, "step": 214400 }, { "epoch": 1.2744975658469604, "grad_norm": 6.298849105834961, "learning_rate": 9.286754628442265e-06, "loss": 0.367, "step": 214410 }, { "epoch": 1.2745570079236288, "grad_norm": 4.906239032745361, "learning_rate": 9.286647821841158e-06, "loss": 0.3724, "step": 214420 }, { "epoch": 1.2746164500002972, "grad_norm": 3.298382043838501, "learning_rate": 9.28654100785793e-06, "loss": 0.3658, "step": 214430 }, { "epoch": 1.2746758920769656, "grad_norm": 6.055619716644287, "learning_rate": 9.286434186492768e-06, "loss": 0.3807, "step": 214440 }, { "epoch": 1.274735334153634, "grad_norm": 7.009244918823242, "learning_rate": 9.286327357745854e-06, "loss": 0.3995, "step": 214450 }, { "epoch": 1.2747947762303025, "grad_norm": 5.619719982147217, "learning_rate": 9.286220521617372e-06, "loss": 0.3578, "step": 214460 }, { "epoch": 1.2748542183069707, "grad_norm": 5.706319808959961, "learning_rate": 9.28611367810751e-06, "loss": 0.372, "step": 214470 }, { "epoch": 1.274913660383639, "grad_norm": 5.21187162399292, "learning_rate": 9.286006827216447e-06, "loss": 0.4649, "step": 214480 }, { "epoch": 1.2749731024603075, "grad_norm": 6.688312530517578, "learning_rate": 9.285899968944367e-06, "loss": 0.3969, "step": 214490 }, { "epoch": 1.275032544536976, "grad_norm": 3.7407898902893066, "learning_rate": 9.285793103291459e-06, "loss": 0.3682, "step": 214500 }, { "epoch": 1.2750919866136443, "grad_norm": 4.901830196380615, "learning_rate": 9.285686230257902e-06, "loss": 0.331, "step": 214510 }, { "epoch": 1.2751514286903127, "grad_norm": 6.544472694396973, "learning_rate": 9.285579349843883e-06, "loss": 0.4248, "step": 214520 }, { "epoch": 1.2752108707669811, "grad_norm": 4.395831108093262, "learning_rate": 9.285472462049586e-06, "loss": 0.4201, "step": 214530 }, { "epoch": 1.2752703128436496, "grad_norm": 3.9199812412261963, "learning_rate": 9.28536556687519e-06, "loss": 0.4468, "step": 214540 }, { "epoch": 1.275329754920318, "grad_norm": 5.799554347991943, "learning_rate": 9.285258664320887e-06, "loss": 0.3905, "step": 214550 }, { "epoch": 1.2753891969969864, "grad_norm": 6.885025978088379, "learning_rate": 9.285151754386857e-06, "loss": 0.4321, "step": 214560 }, { "epoch": 1.2754486390736548, "grad_norm": 4.421646595001221, "learning_rate": 9.285044837073282e-06, "loss": 0.4147, "step": 214570 }, { "epoch": 1.275508081150323, "grad_norm": 4.141261100769043, "learning_rate": 9.284937912380353e-06, "loss": 0.3774, "step": 214580 }, { "epoch": 1.2755675232269914, "grad_norm": 6.1321234703063965, "learning_rate": 9.284830980308245e-06, "loss": 0.3669, "step": 214590 }, { "epoch": 1.2756269653036598, "grad_norm": 4.012176036834717, "learning_rate": 9.284724040857148e-06, "loss": 0.3769, "step": 214600 }, { "epoch": 1.2756864073803282, "grad_norm": 5.750396251678467, "learning_rate": 9.284617094027246e-06, "loss": 0.3696, "step": 214610 }, { "epoch": 1.2757458494569967, "grad_norm": 3.527012586593628, "learning_rate": 9.28451013981872e-06, "loss": 0.4216, "step": 214620 }, { "epoch": 1.275805291533665, "grad_norm": 5.007271766662598, "learning_rate": 9.284403178231758e-06, "loss": 0.3814, "step": 214630 }, { "epoch": 1.2758647336103335, "grad_norm": 5.016308784484863, "learning_rate": 9.284296209266543e-06, "loss": 0.3795, "step": 214640 }, { "epoch": 1.2759241756870017, "grad_norm": 5.7143025398254395, "learning_rate": 9.284189232923259e-06, "loss": 0.3777, "step": 214650 }, { "epoch": 1.27598361776367, "grad_norm": 4.347054958343506, "learning_rate": 9.28408224920209e-06, "loss": 0.384, "step": 214660 }, { "epoch": 1.2760430598403385, "grad_norm": 5.804432392120361, "learning_rate": 9.283975258103217e-06, "loss": 0.3724, "step": 214670 }, { "epoch": 1.276102501917007, "grad_norm": 5.084386825561523, "learning_rate": 9.283868259626832e-06, "loss": 0.3784, "step": 214680 }, { "epoch": 1.2761619439936753, "grad_norm": 4.591022491455078, "learning_rate": 9.283761253773111e-06, "loss": 0.3774, "step": 214690 }, { "epoch": 1.2762213860703437, "grad_norm": 5.0966997146606445, "learning_rate": 9.283654240542244e-06, "loss": 0.3743, "step": 214700 }, { "epoch": 1.2762808281470122, "grad_norm": 5.233903884887695, "learning_rate": 9.283547219934412e-06, "loss": 0.3731, "step": 214710 }, { "epoch": 1.2763402702236806, "grad_norm": 5.096946716308594, "learning_rate": 9.283440191949801e-06, "loss": 0.4154, "step": 214720 }, { "epoch": 1.276399712300349, "grad_norm": 6.471127510070801, "learning_rate": 9.283333156588596e-06, "loss": 0.4141, "step": 214730 }, { "epoch": 1.2764591543770174, "grad_norm": 3.51080322265625, "learning_rate": 9.28322611385098e-06, "loss": 0.3868, "step": 214740 }, { "epoch": 1.2765185964536858, "grad_norm": 3.8016369342803955, "learning_rate": 9.283119063737137e-06, "loss": 0.3642, "step": 214750 }, { "epoch": 1.2765780385303542, "grad_norm": 5.050448417663574, "learning_rate": 9.283012006247251e-06, "loss": 0.3778, "step": 214760 }, { "epoch": 1.2766374806070224, "grad_norm": 4.610074043273926, "learning_rate": 9.282904941381508e-06, "loss": 0.3802, "step": 214770 }, { "epoch": 1.2766969226836908, "grad_norm": 4.503568649291992, "learning_rate": 9.282797869140093e-06, "loss": 0.3782, "step": 214780 }, { "epoch": 1.2767563647603593, "grad_norm": 4.66926908493042, "learning_rate": 9.282690789523187e-06, "loss": 0.3748, "step": 214790 }, { "epoch": 1.2768158068370277, "grad_norm": 4.734463214874268, "learning_rate": 9.282583702530978e-06, "loss": 0.4003, "step": 214800 }, { "epoch": 1.276875248913696, "grad_norm": 5.042824745178223, "learning_rate": 9.282476608163648e-06, "loss": 0.3525, "step": 214810 }, { "epoch": 1.2769346909903645, "grad_norm": 3.7973313331604004, "learning_rate": 9.282369506421383e-06, "loss": 0.3599, "step": 214820 }, { "epoch": 1.276994133067033, "grad_norm": 4.068342685699463, "learning_rate": 9.282262397304365e-06, "loss": 0.3718, "step": 214830 }, { "epoch": 1.277053575143701, "grad_norm": 6.136430740356445, "learning_rate": 9.282155280812782e-06, "loss": 0.3906, "step": 214840 }, { "epoch": 1.2771130172203695, "grad_norm": 4.172723293304443, "learning_rate": 9.282048156946816e-06, "loss": 0.3839, "step": 214850 }, { "epoch": 1.277172459297038, "grad_norm": 7.190732955932617, "learning_rate": 9.281941025706653e-06, "loss": 0.4545, "step": 214860 }, { "epoch": 1.2772319013737063, "grad_norm": 4.900475978851318, "learning_rate": 9.281833887092474e-06, "loss": 0.4482, "step": 214870 }, { "epoch": 1.2772913434503748, "grad_norm": 6.583137035369873, "learning_rate": 9.281726741104468e-06, "loss": 0.4211, "step": 214880 }, { "epoch": 1.2773507855270432, "grad_norm": 6.2494940757751465, "learning_rate": 9.28161958774282e-06, "loss": 0.3752, "step": 214890 }, { "epoch": 1.2774102276037116, "grad_norm": 4.3456549644470215, "learning_rate": 9.28151242700771e-06, "loss": 0.4265, "step": 214900 }, { "epoch": 1.27746966968038, "grad_norm": 5.605406284332275, "learning_rate": 9.281405258899325e-06, "loss": 0.413, "step": 214910 }, { "epoch": 1.2775291117570484, "grad_norm": 5.0504255294799805, "learning_rate": 9.28129808341785e-06, "loss": 0.3507, "step": 214920 }, { "epoch": 1.2775885538337168, "grad_norm": 7.404397487640381, "learning_rate": 9.281190900563466e-06, "loss": 0.4226, "step": 214930 }, { "epoch": 1.2776479959103852, "grad_norm": 6.506258964538574, "learning_rate": 9.281083710336363e-06, "loss": 0.359, "step": 214940 }, { "epoch": 1.2777074379870534, "grad_norm": 6.076480388641357, "learning_rate": 9.280976512736721e-06, "loss": 0.382, "step": 214950 }, { "epoch": 1.2777668800637219, "grad_norm": 5.201907634735107, "learning_rate": 9.280869307764729e-06, "loss": 0.4094, "step": 214960 }, { "epoch": 1.2778263221403903, "grad_norm": 5.831955432891846, "learning_rate": 9.280762095420568e-06, "loss": 0.3844, "step": 214970 }, { "epoch": 1.2778857642170587, "grad_norm": 5.169007778167725, "learning_rate": 9.280654875704425e-06, "loss": 0.3995, "step": 214980 }, { "epoch": 1.277945206293727, "grad_norm": 4.868131637573242, "learning_rate": 9.280547648616483e-06, "loss": 0.3842, "step": 214990 }, { "epoch": 1.2780046483703955, "grad_norm": 3.8164312839508057, "learning_rate": 9.280440414156927e-06, "loss": 0.38, "step": 215000 }, { "epoch": 1.278064090447064, "grad_norm": 3.9654557704925537, "learning_rate": 9.280333172325941e-06, "loss": 0.3797, "step": 215010 }, { "epoch": 1.2781235325237321, "grad_norm": 7.7474822998046875, "learning_rate": 9.28022592312371e-06, "loss": 0.4036, "step": 215020 }, { "epoch": 1.2781829746004005, "grad_norm": 6.047937393188477, "learning_rate": 9.280118666550422e-06, "loss": 0.3827, "step": 215030 }, { "epoch": 1.278242416677069, "grad_norm": 4.597365856170654, "learning_rate": 9.280011402606257e-06, "loss": 0.3596, "step": 215040 }, { "epoch": 1.2783018587537374, "grad_norm": 5.141854286193848, "learning_rate": 9.279904131291401e-06, "loss": 0.4241, "step": 215050 }, { "epoch": 1.2783613008304058, "grad_norm": 5.115845203399658, "learning_rate": 9.279796852606042e-06, "loss": 0.3717, "step": 215060 }, { "epoch": 1.2784207429070742, "grad_norm": 4.7086896896362305, "learning_rate": 9.27968956655036e-06, "loss": 0.3666, "step": 215070 }, { "epoch": 1.2784801849837426, "grad_norm": 4.416051387786865, "learning_rate": 9.279582273124543e-06, "loss": 0.3657, "step": 215080 }, { "epoch": 1.278539627060411, "grad_norm": 3.656891345977783, "learning_rate": 9.279474972328775e-06, "loss": 0.4164, "step": 215090 }, { "epoch": 1.2785990691370794, "grad_norm": 5.0308756828308105, "learning_rate": 9.27936766416324e-06, "loss": 0.457, "step": 215100 }, { "epoch": 1.2786585112137479, "grad_norm": 4.9929423332214355, "learning_rate": 9.279260348628122e-06, "loss": 0.3631, "step": 215110 }, { "epoch": 1.2787179532904163, "grad_norm": 4.673593997955322, "learning_rate": 9.279153025723609e-06, "loss": 0.3945, "step": 215120 }, { "epoch": 1.2787773953670847, "grad_norm": 5.809854984283447, "learning_rate": 9.279045695449883e-06, "loss": 0.4134, "step": 215130 }, { "epoch": 1.2788368374437529, "grad_norm": 4.201045989990234, "learning_rate": 9.27893835780713e-06, "loss": 0.4148, "step": 215140 }, { "epoch": 1.2788962795204213, "grad_norm": 5.769652366638184, "learning_rate": 9.278831012795535e-06, "loss": 0.4109, "step": 215150 }, { "epoch": 1.2789557215970897, "grad_norm": 5.297826290130615, "learning_rate": 9.278723660415281e-06, "loss": 0.3825, "step": 215160 }, { "epoch": 1.2790151636737581, "grad_norm": 4.534816741943359, "learning_rate": 9.278616300666557e-06, "loss": 0.3694, "step": 215170 }, { "epoch": 1.2790746057504265, "grad_norm": 4.597060203552246, "learning_rate": 9.278508933549543e-06, "loss": 0.3775, "step": 215180 }, { "epoch": 1.279134047827095, "grad_norm": 5.58005428314209, "learning_rate": 9.278401559064426e-06, "loss": 0.4076, "step": 215190 }, { "epoch": 1.2791934899037634, "grad_norm": 4.951568603515625, "learning_rate": 9.27829417721139e-06, "loss": 0.3932, "step": 215200 }, { "epoch": 1.2792529319804316, "grad_norm": 5.40924596786499, "learning_rate": 9.278186787990624e-06, "loss": 0.3839, "step": 215210 }, { "epoch": 1.2793123740571, "grad_norm": 6.119570255279541, "learning_rate": 9.278079391402308e-06, "loss": 0.4023, "step": 215220 }, { "epoch": 1.2793718161337684, "grad_norm": 5.202879905700684, "learning_rate": 9.27797198744663e-06, "loss": 0.3909, "step": 215230 }, { "epoch": 1.2794312582104368, "grad_norm": 5.357691287994385, "learning_rate": 9.277864576123774e-06, "loss": 0.3881, "step": 215240 }, { "epoch": 1.2794907002871052, "grad_norm": 5.872326850891113, "learning_rate": 9.277757157433923e-06, "loss": 0.4066, "step": 215250 }, { "epoch": 1.2795501423637736, "grad_norm": 3.8897626399993896, "learning_rate": 9.277649731377266e-06, "loss": 0.3832, "step": 215260 }, { "epoch": 1.279609584440442, "grad_norm": 4.364502906799316, "learning_rate": 9.277542297953984e-06, "loss": 0.3963, "step": 215270 }, { "epoch": 1.2796690265171105, "grad_norm": 3.9341819286346436, "learning_rate": 9.277434857164264e-06, "loss": 0.38, "step": 215280 }, { "epoch": 1.2797284685937789, "grad_norm": 3.888434648513794, "learning_rate": 9.27732740900829e-06, "loss": 0.3374, "step": 215290 }, { "epoch": 1.2797879106704473, "grad_norm": 6.128018856048584, "learning_rate": 9.27721995348625e-06, "loss": 0.3958, "step": 215300 }, { "epoch": 1.2798473527471157, "grad_norm": 5.251778602600098, "learning_rate": 9.277112490598326e-06, "loss": 0.4038, "step": 215310 }, { "epoch": 1.2799067948237839, "grad_norm": 4.48422908782959, "learning_rate": 9.277005020344703e-06, "loss": 0.4076, "step": 215320 }, { "epoch": 1.2799662369004523, "grad_norm": 5.228750228881836, "learning_rate": 9.276897542725567e-06, "loss": 0.4263, "step": 215330 }, { "epoch": 1.2800256789771207, "grad_norm": 5.09846830368042, "learning_rate": 9.276790057741104e-06, "loss": 0.4055, "step": 215340 }, { "epoch": 1.2800851210537891, "grad_norm": 5.141944885253906, "learning_rate": 9.276682565391498e-06, "loss": 0.3773, "step": 215350 }, { "epoch": 1.2801445631304575, "grad_norm": 5.629286289215088, "learning_rate": 9.276575065676934e-06, "loss": 0.3964, "step": 215360 }, { "epoch": 1.280204005207126, "grad_norm": 5.81730318069458, "learning_rate": 9.276467558597598e-06, "loss": 0.3627, "step": 215370 }, { "epoch": 1.2802634472837944, "grad_norm": 4.781085014343262, "learning_rate": 9.276360044153675e-06, "loss": 0.3745, "step": 215380 }, { "epoch": 1.2803228893604626, "grad_norm": 4.949948787689209, "learning_rate": 9.276252522345349e-06, "loss": 0.3852, "step": 215390 }, { "epoch": 1.280382331437131, "grad_norm": 4.9403395652771, "learning_rate": 9.276144993172807e-06, "loss": 0.3951, "step": 215400 }, { "epoch": 1.2804417735137994, "grad_norm": 5.261824607849121, "learning_rate": 9.276037456636231e-06, "loss": 0.4095, "step": 215410 }, { "epoch": 1.2805012155904678, "grad_norm": 5.040498733520508, "learning_rate": 9.27592991273581e-06, "loss": 0.4646, "step": 215420 }, { "epoch": 1.2805606576671362, "grad_norm": 3.6371214389801025, "learning_rate": 9.275822361471727e-06, "loss": 0.3737, "step": 215430 }, { "epoch": 1.2806200997438046, "grad_norm": 4.21928596496582, "learning_rate": 9.275714802844168e-06, "loss": 0.402, "step": 215440 }, { "epoch": 1.280679541820473, "grad_norm": 3.8246705532073975, "learning_rate": 9.275607236853316e-06, "loss": 0.382, "step": 215450 }, { "epoch": 1.2807389838971415, "grad_norm": 4.4236040115356445, "learning_rate": 9.275499663499361e-06, "loss": 0.3474, "step": 215460 }, { "epoch": 1.2807984259738099, "grad_norm": 4.921041011810303, "learning_rate": 9.275392082782484e-06, "loss": 0.3898, "step": 215470 }, { "epoch": 1.2808578680504783, "grad_norm": 4.630543231964111, "learning_rate": 9.275284494702871e-06, "loss": 0.4451, "step": 215480 }, { "epoch": 1.2809173101271467, "grad_norm": 5.883364677429199, "learning_rate": 9.27517689926071e-06, "loss": 0.3934, "step": 215490 }, { "epoch": 1.2809767522038151, "grad_norm": 4.260111331939697, "learning_rate": 9.275069296456184e-06, "loss": 0.3688, "step": 215500 }, { "epoch": 1.2810361942804833, "grad_norm": 4.181352615356445, "learning_rate": 9.274961686289477e-06, "loss": 0.3776, "step": 215510 }, { "epoch": 1.2810956363571517, "grad_norm": 4.5091962814331055, "learning_rate": 9.274854068760777e-06, "loss": 0.3726, "step": 215520 }, { "epoch": 1.2811550784338201, "grad_norm": 3.6764585971832275, "learning_rate": 9.274746443870269e-06, "loss": 0.3436, "step": 215530 }, { "epoch": 1.2812145205104886, "grad_norm": 5.38090181350708, "learning_rate": 9.274638811618135e-06, "loss": 0.3581, "step": 215540 }, { "epoch": 1.281273962587157, "grad_norm": 5.038095474243164, "learning_rate": 9.274531172004565e-06, "loss": 0.3833, "step": 215550 }, { "epoch": 1.2813334046638254, "grad_norm": 5.1152801513671875, "learning_rate": 9.274423525029742e-06, "loss": 0.4154, "step": 215560 }, { "epoch": 1.2813928467404938, "grad_norm": 7.508362293243408, "learning_rate": 9.27431587069385e-06, "loss": 0.3824, "step": 215570 }, { "epoch": 1.281452288817162, "grad_norm": 5.488178253173828, "learning_rate": 9.274208208997079e-06, "loss": 0.4195, "step": 215580 }, { "epoch": 1.2815117308938304, "grad_norm": 5.157278537750244, "learning_rate": 9.27410053993961e-06, "loss": 0.346, "step": 215590 }, { "epoch": 1.2815711729704988, "grad_norm": 5.827846050262451, "learning_rate": 9.27399286352163e-06, "loss": 0.3977, "step": 215600 }, { "epoch": 1.2816306150471672, "grad_norm": 3.560093402862549, "learning_rate": 9.273885179743324e-06, "loss": 0.3829, "step": 215610 }, { "epoch": 1.2816900571238357, "grad_norm": 6.800568103790283, "learning_rate": 9.273777488604879e-06, "loss": 0.3816, "step": 215620 }, { "epoch": 1.281749499200504, "grad_norm": 5.54301643371582, "learning_rate": 9.273669790106476e-06, "loss": 0.3906, "step": 215630 }, { "epoch": 1.2818089412771725, "grad_norm": 4.07984733581543, "learning_rate": 9.273562084248306e-06, "loss": 0.3626, "step": 215640 }, { "epoch": 1.281868383353841, "grad_norm": 5.493069648742676, "learning_rate": 9.273454371030552e-06, "loss": 0.3497, "step": 215650 }, { "epoch": 1.2819278254305093, "grad_norm": 4.186031818389893, "learning_rate": 9.273346650453401e-06, "loss": 0.4076, "step": 215660 }, { "epoch": 1.2819872675071777, "grad_norm": 4.0434956550598145, "learning_rate": 9.273238922517036e-06, "loss": 0.3773, "step": 215670 }, { "epoch": 1.2820467095838461, "grad_norm": 4.676759243011475, "learning_rate": 9.273131187221643e-06, "loss": 0.3878, "step": 215680 }, { "epoch": 1.2821061516605143, "grad_norm": 5.2375288009643555, "learning_rate": 9.273023444567408e-06, "loss": 0.4042, "step": 215690 }, { "epoch": 1.2821655937371828, "grad_norm": 4.731456279754639, "learning_rate": 9.272915694554518e-06, "loss": 0.398, "step": 215700 }, { "epoch": 1.2822250358138512, "grad_norm": 6.091939926147461, "learning_rate": 9.272807937183156e-06, "loss": 0.3419, "step": 215710 }, { "epoch": 1.2822844778905196, "grad_norm": 5.595303058624268, "learning_rate": 9.272700172453511e-06, "loss": 0.4008, "step": 215720 }, { "epoch": 1.282343919967188, "grad_norm": 5.200359344482422, "learning_rate": 9.272592400365765e-06, "loss": 0.3837, "step": 215730 }, { "epoch": 1.2824033620438564, "grad_norm": 5.857070446014404, "learning_rate": 9.272484620920105e-06, "loss": 0.3779, "step": 215740 }, { "epoch": 1.2824628041205248, "grad_norm": 6.100256443023682, "learning_rate": 9.272376834116719e-06, "loss": 0.4061, "step": 215750 }, { "epoch": 1.282522246197193, "grad_norm": 4.566219329833984, "learning_rate": 9.272269039955789e-06, "loss": 0.4046, "step": 215760 }, { "epoch": 1.2825816882738614, "grad_norm": 5.469229698181152, "learning_rate": 9.2721612384375e-06, "loss": 0.4105, "step": 215770 }, { "epoch": 1.2826411303505298, "grad_norm": 4.871620178222656, "learning_rate": 9.272053429562041e-06, "loss": 0.4354, "step": 215780 }, { "epoch": 1.2827005724271983, "grad_norm": 5.552180767059326, "learning_rate": 9.271945613329596e-06, "loss": 0.3831, "step": 215790 }, { "epoch": 1.2827600145038667, "grad_norm": 5.566052436828613, "learning_rate": 9.271837789740353e-06, "loss": 0.3823, "step": 215800 }, { "epoch": 1.282819456580535, "grad_norm": 5.371792316436768, "learning_rate": 9.271729958794492e-06, "loss": 0.4058, "step": 215810 }, { "epoch": 1.2828788986572035, "grad_norm": 5.1892313957214355, "learning_rate": 9.271622120492203e-06, "loss": 0.3837, "step": 215820 }, { "epoch": 1.282938340733872, "grad_norm": 3.6464462280273438, "learning_rate": 9.271514274833673e-06, "loss": 0.3764, "step": 215830 }, { "epoch": 1.2829977828105403, "grad_norm": 4.350366592407227, "learning_rate": 9.271406421819084e-06, "loss": 0.4085, "step": 215840 }, { "epoch": 1.2830572248872087, "grad_norm": 4.877425670623779, "learning_rate": 9.271298561448627e-06, "loss": 0.4054, "step": 215850 }, { "epoch": 1.2831166669638772, "grad_norm": 6.1742072105407715, "learning_rate": 9.27119069372248e-06, "loss": 0.4287, "step": 215860 }, { "epoch": 1.2831761090405456, "grad_norm": 3.778729200363159, "learning_rate": 9.271082818640836e-06, "loss": 0.386, "step": 215870 }, { "epoch": 1.2832355511172138, "grad_norm": 5.223757743835449, "learning_rate": 9.270974936203875e-06, "loss": 0.3968, "step": 215880 }, { "epoch": 1.2832949931938822, "grad_norm": 4.724550247192383, "learning_rate": 9.270867046411787e-06, "loss": 0.3571, "step": 215890 }, { "epoch": 1.2833544352705506, "grad_norm": 4.364007472991943, "learning_rate": 9.270759149264756e-06, "loss": 0.3896, "step": 215900 }, { "epoch": 1.283413877347219, "grad_norm": 4.793666839599609, "learning_rate": 9.270651244762969e-06, "loss": 0.3946, "step": 215910 }, { "epoch": 1.2834733194238874, "grad_norm": 4.64845085144043, "learning_rate": 9.27054333290661e-06, "loss": 0.364, "step": 215920 }, { "epoch": 1.2835327615005558, "grad_norm": 5.15687894821167, "learning_rate": 9.270435413695866e-06, "loss": 0.4068, "step": 215930 }, { "epoch": 1.2835922035772243, "grad_norm": 6.283986568450928, "learning_rate": 9.270327487130924e-06, "loss": 0.3877, "step": 215940 }, { "epoch": 1.2836516456538924, "grad_norm": 5.047669887542725, "learning_rate": 9.270219553211968e-06, "loss": 0.4088, "step": 215950 }, { "epoch": 1.2837110877305609, "grad_norm": 4.978093147277832, "learning_rate": 9.270111611939183e-06, "loss": 0.416, "step": 215960 }, { "epoch": 1.2837705298072293, "grad_norm": 4.122134685516357, "learning_rate": 9.270003663312757e-06, "loss": 0.412, "step": 215970 }, { "epoch": 1.2838299718838977, "grad_norm": 3.3205513954162598, "learning_rate": 9.269895707332876e-06, "loss": 0.4408, "step": 215980 }, { "epoch": 1.283889413960566, "grad_norm": 5.568950653076172, "learning_rate": 9.269787743999726e-06, "loss": 0.3952, "step": 215990 }, { "epoch": 1.2839488560372345, "grad_norm": 5.136590480804443, "learning_rate": 9.26967977331349e-06, "loss": 0.3469, "step": 216000 }, { "epoch": 1.284008298113903, "grad_norm": 4.165693283081055, "learning_rate": 9.269571795274356e-06, "loss": 0.3718, "step": 216010 }, { "epoch": 1.2840677401905713, "grad_norm": 5.361721992492676, "learning_rate": 9.269463809882511e-06, "loss": 0.4215, "step": 216020 }, { "epoch": 1.2841271822672398, "grad_norm": 4.1799516677856445, "learning_rate": 9.269355817138139e-06, "loss": 0.4222, "step": 216030 }, { "epoch": 1.2841866243439082, "grad_norm": 3.4499473571777344, "learning_rate": 9.269247817041426e-06, "loss": 0.4097, "step": 216040 }, { "epoch": 1.2842460664205766, "grad_norm": 4.417942047119141, "learning_rate": 9.26913980959256e-06, "loss": 0.3599, "step": 216050 }, { "epoch": 1.2843055084972448, "grad_norm": 4.178038120269775, "learning_rate": 9.269031794791728e-06, "loss": 0.4034, "step": 216060 }, { "epoch": 1.2843649505739132, "grad_norm": 5.454610824584961, "learning_rate": 9.26892377263911e-06, "loss": 0.3994, "step": 216070 }, { "epoch": 1.2844243926505816, "grad_norm": 4.182310104370117, "learning_rate": 9.268815743134898e-06, "loss": 0.4004, "step": 216080 }, { "epoch": 1.28448383472725, "grad_norm": 5.080660820007324, "learning_rate": 9.268707706279276e-06, "loss": 0.3788, "step": 216090 }, { "epoch": 1.2845432768039184, "grad_norm": 5.205387592315674, "learning_rate": 9.268599662072431e-06, "loss": 0.4126, "step": 216100 }, { "epoch": 1.2846027188805869, "grad_norm": 4.03159761428833, "learning_rate": 9.268491610514546e-06, "loss": 0.4027, "step": 216110 }, { "epoch": 1.2846621609572553, "grad_norm": 6.3262224197387695, "learning_rate": 9.26838355160581e-06, "loss": 0.3788, "step": 216120 }, { "epoch": 1.2847216030339235, "grad_norm": 6.5533318519592285, "learning_rate": 9.268275485346407e-06, "loss": 0.3776, "step": 216130 }, { "epoch": 1.2847810451105919, "grad_norm": 5.893458843231201, "learning_rate": 9.268167411736526e-06, "loss": 0.3937, "step": 216140 }, { "epoch": 1.2848404871872603, "grad_norm": 5.989163398742676, "learning_rate": 9.26805933077635e-06, "loss": 0.3894, "step": 216150 }, { "epoch": 1.2848999292639287, "grad_norm": 5.903449058532715, "learning_rate": 9.267951242466069e-06, "loss": 0.3621, "step": 216160 }, { "epoch": 1.2849593713405971, "grad_norm": 5.278048992156982, "learning_rate": 9.267843146805865e-06, "loss": 0.4687, "step": 216170 }, { "epoch": 1.2850188134172655, "grad_norm": 4.727224349975586, "learning_rate": 9.267735043795927e-06, "loss": 0.3733, "step": 216180 }, { "epoch": 1.285078255493934, "grad_norm": 5.004872798919678, "learning_rate": 9.267626933436437e-06, "loss": 0.3594, "step": 216190 }, { "epoch": 1.2851376975706024, "grad_norm": 5.554847240447998, "learning_rate": 9.267518815727587e-06, "loss": 0.4186, "step": 216200 }, { "epoch": 1.2851971396472708, "grad_norm": 4.335738658905029, "learning_rate": 9.26741069066956e-06, "loss": 0.3707, "step": 216210 }, { "epoch": 1.2852565817239392, "grad_norm": 3.648176431655884, "learning_rate": 9.267302558262543e-06, "loss": 0.386, "step": 216220 }, { "epoch": 1.2853160238006076, "grad_norm": 6.502570152282715, "learning_rate": 9.267194418506721e-06, "loss": 0.3989, "step": 216230 }, { "epoch": 1.285375465877276, "grad_norm": 5.229872703552246, "learning_rate": 9.267086271402282e-06, "loss": 0.4054, "step": 216240 }, { "epoch": 1.2854349079539442, "grad_norm": 5.697407245635986, "learning_rate": 9.26697811694941e-06, "loss": 0.3567, "step": 216250 }, { "epoch": 1.2854943500306126, "grad_norm": 5.151431560516357, "learning_rate": 9.266869955148291e-06, "loss": 0.3779, "step": 216260 }, { "epoch": 1.285553792107281, "grad_norm": 5.606619358062744, "learning_rate": 9.266761785999117e-06, "loss": 0.3671, "step": 216270 }, { "epoch": 1.2856132341839495, "grad_norm": 4.4334516525268555, "learning_rate": 9.266653609502068e-06, "loss": 0.3989, "step": 216280 }, { "epoch": 1.2856726762606179, "grad_norm": 6.024613380432129, "learning_rate": 9.266545425657332e-06, "loss": 0.4053, "step": 216290 }, { "epoch": 1.2857321183372863, "grad_norm": 6.110884189605713, "learning_rate": 9.266437234465096e-06, "loss": 0.4406, "step": 216300 }, { "epoch": 1.2857915604139547, "grad_norm": 4.928974151611328, "learning_rate": 9.266329035925545e-06, "loss": 0.361, "step": 216310 }, { "epoch": 1.285851002490623, "grad_norm": 4.772425651550293, "learning_rate": 9.266220830038869e-06, "loss": 0.3854, "step": 216320 }, { "epoch": 1.2859104445672913, "grad_norm": 8.141398429870605, "learning_rate": 9.266112616805249e-06, "loss": 0.3968, "step": 216330 }, { "epoch": 1.2859698866439597, "grad_norm": 6.77299690246582, "learning_rate": 9.266004396224877e-06, "loss": 0.3905, "step": 216340 }, { "epoch": 1.2860293287206281, "grad_norm": 5.704429626464844, "learning_rate": 9.265896168297935e-06, "loss": 0.4125, "step": 216350 }, { "epoch": 1.2860887707972966, "grad_norm": 6.3321075439453125, "learning_rate": 9.26578793302461e-06, "loss": 0.4019, "step": 216360 }, { "epoch": 1.286148212873965, "grad_norm": 6.432831764221191, "learning_rate": 9.265679690405089e-06, "loss": 0.3783, "step": 216370 }, { "epoch": 1.2862076549506334, "grad_norm": 6.7081828117370605, "learning_rate": 9.265571440439559e-06, "loss": 0.4047, "step": 216380 }, { "epoch": 1.2862670970273018, "grad_norm": 4.330756664276123, "learning_rate": 9.265463183128207e-06, "loss": 0.4244, "step": 216390 }, { "epoch": 1.2863265391039702, "grad_norm": 4.127828121185303, "learning_rate": 9.265354918471217e-06, "loss": 0.3561, "step": 216400 }, { "epoch": 1.2863859811806386, "grad_norm": 4.922796249389648, "learning_rate": 9.265246646468778e-06, "loss": 0.3706, "step": 216410 }, { "epoch": 1.286445423257307, "grad_norm": 4.832760334014893, "learning_rate": 9.265138367121075e-06, "loss": 0.3497, "step": 216420 }, { "epoch": 1.2865048653339752, "grad_norm": 6.2082929611206055, "learning_rate": 9.265030080428295e-06, "loss": 0.3973, "step": 216430 }, { "epoch": 1.2865643074106436, "grad_norm": 6.586325645446777, "learning_rate": 9.264921786390624e-06, "loss": 0.3957, "step": 216440 }, { "epoch": 1.286623749487312, "grad_norm": 3.3671200275421143, "learning_rate": 9.264813485008249e-06, "loss": 0.3908, "step": 216450 }, { "epoch": 1.2866831915639805, "grad_norm": 4.3484392166137695, "learning_rate": 9.264705176281356e-06, "loss": 0.41, "step": 216460 }, { "epoch": 1.286742633640649, "grad_norm": 4.843056678771973, "learning_rate": 9.26459686021013e-06, "loss": 0.3371, "step": 216470 }, { "epoch": 1.2868020757173173, "grad_norm": 5.589706897735596, "learning_rate": 9.264488536794762e-06, "loss": 0.4281, "step": 216480 }, { "epoch": 1.2868615177939857, "grad_norm": 5.8022613525390625, "learning_rate": 9.264380206035437e-06, "loss": 0.3888, "step": 216490 }, { "epoch": 1.286920959870654, "grad_norm": 6.026579856872559, "learning_rate": 9.264271867932338e-06, "loss": 0.404, "step": 216500 }, { "epoch": 1.2869804019473223, "grad_norm": 5.141749858856201, "learning_rate": 9.264163522485655e-06, "loss": 0.3658, "step": 216510 }, { "epoch": 1.2870398440239907, "grad_norm": 4.780274868011475, "learning_rate": 9.264055169695574e-06, "loss": 0.3958, "step": 216520 }, { "epoch": 1.2870992861006592, "grad_norm": 5.579103469848633, "learning_rate": 9.26394680956228e-06, "loss": 0.3882, "step": 216530 }, { "epoch": 1.2871587281773276, "grad_norm": 6.147547245025635, "learning_rate": 9.263838442085962e-06, "loss": 0.4488, "step": 216540 }, { "epoch": 1.287218170253996, "grad_norm": 3.543196201324463, "learning_rate": 9.263730067266806e-06, "loss": 0.4117, "step": 216550 }, { "epoch": 1.2872776123306644, "grad_norm": 4.222645282745361, "learning_rate": 9.263621685104996e-06, "loss": 0.4051, "step": 216560 }, { "epoch": 1.2873370544073328, "grad_norm": 5.383221626281738, "learning_rate": 9.263513295600722e-06, "loss": 0.3447, "step": 216570 }, { "epoch": 1.2873964964840012, "grad_norm": 5.127771854400635, "learning_rate": 9.26340489875417e-06, "loss": 0.3434, "step": 216580 }, { "epoch": 1.2874559385606696, "grad_norm": 4.395604610443115, "learning_rate": 9.263296494565523e-06, "loss": 0.3974, "step": 216590 }, { "epoch": 1.287515380637338, "grad_norm": 7.521201133728027, "learning_rate": 9.263188083034974e-06, "loss": 0.3975, "step": 216600 }, { "epoch": 1.2875748227140065, "grad_norm": 4.317533493041992, "learning_rate": 9.263079664162705e-06, "loss": 0.384, "step": 216610 }, { "epoch": 1.2876342647906747, "grad_norm": 5.2491350173950195, "learning_rate": 9.262971237948904e-06, "loss": 0.3931, "step": 216620 }, { "epoch": 1.287693706867343, "grad_norm": 3.953735828399658, "learning_rate": 9.26286280439376e-06, "loss": 0.3897, "step": 216630 }, { "epoch": 1.2877531489440115, "grad_norm": 4.671705722808838, "learning_rate": 9.262754363497455e-06, "loss": 0.392, "step": 216640 }, { "epoch": 1.28781259102068, "grad_norm": 7.44379186630249, "learning_rate": 9.26264591526018e-06, "loss": 0.3968, "step": 216650 }, { "epoch": 1.2878720330973483, "grad_norm": 4.4901018142700195, "learning_rate": 9.26253745968212e-06, "loss": 0.3736, "step": 216660 }, { "epoch": 1.2879314751740167, "grad_norm": 5.213525772094727, "learning_rate": 9.26242899676346e-06, "loss": 0.3814, "step": 216670 }, { "epoch": 1.2879909172506852, "grad_norm": 4.892262935638428, "learning_rate": 9.26232052650439e-06, "loss": 0.3865, "step": 216680 }, { "epoch": 1.2880503593273533, "grad_norm": 6.817185401916504, "learning_rate": 9.262212048905096e-06, "loss": 0.4317, "step": 216690 }, { "epoch": 1.2881098014040218, "grad_norm": 4.149212837219238, "learning_rate": 9.262103563965763e-06, "loss": 0.3761, "step": 216700 }, { "epoch": 1.2881692434806902, "grad_norm": 5.7151103019714355, "learning_rate": 9.26199507168658e-06, "loss": 0.4171, "step": 216710 }, { "epoch": 1.2882286855573586, "grad_norm": 5.7939934730529785, "learning_rate": 9.261886572067733e-06, "loss": 0.3925, "step": 216720 }, { "epoch": 1.288288127634027, "grad_norm": 4.8945183753967285, "learning_rate": 9.26177806510941e-06, "loss": 0.38, "step": 216730 }, { "epoch": 1.2883475697106954, "grad_norm": 5.374950885772705, "learning_rate": 9.261669550811795e-06, "loss": 0.3783, "step": 216740 }, { "epoch": 1.2884070117873638, "grad_norm": 6.125424385070801, "learning_rate": 9.261561029175077e-06, "loss": 0.3619, "step": 216750 }, { "epoch": 1.2884664538640322, "grad_norm": 4.795740604400635, "learning_rate": 9.261452500199443e-06, "loss": 0.3472, "step": 216760 }, { "epoch": 1.2885258959407007, "grad_norm": 5.310986042022705, "learning_rate": 9.26134396388508e-06, "loss": 0.3796, "step": 216770 }, { "epoch": 1.288585338017369, "grad_norm": 4.556995391845703, "learning_rate": 9.26123542023217e-06, "loss": 0.3408, "step": 216780 }, { "epoch": 1.2886447800940375, "grad_norm": 7.1366801261901855, "learning_rate": 9.261126869240909e-06, "loss": 0.3584, "step": 216790 }, { "epoch": 1.2887042221707057, "grad_norm": 4.161815643310547, "learning_rate": 9.261018310911476e-06, "loss": 0.3753, "step": 216800 }, { "epoch": 1.288763664247374, "grad_norm": 6.693809509277344, "learning_rate": 9.260909745244062e-06, "loss": 0.3518, "step": 216810 }, { "epoch": 1.2888231063240425, "grad_norm": 5.297373294830322, "learning_rate": 9.260801172238853e-06, "loss": 0.4213, "step": 216820 }, { "epoch": 1.288882548400711, "grad_norm": 4.972711086273193, "learning_rate": 9.260692591896036e-06, "loss": 0.3818, "step": 216830 }, { "epoch": 1.2889419904773793, "grad_norm": 4.286489486694336, "learning_rate": 9.2605840042158e-06, "loss": 0.3784, "step": 216840 }, { "epoch": 1.2890014325540478, "grad_norm": 4.704067707061768, "learning_rate": 9.260475409198329e-06, "loss": 0.4094, "step": 216850 }, { "epoch": 1.2890608746307162, "grad_norm": 6.277997970581055, "learning_rate": 9.26036680684381e-06, "loss": 0.3731, "step": 216860 }, { "epoch": 1.2891203167073844, "grad_norm": 5.4260783195495605, "learning_rate": 9.26025819715243e-06, "loss": 0.4033, "step": 216870 }, { "epoch": 1.2891797587840528, "grad_norm": 3.695681095123291, "learning_rate": 9.260149580124379e-06, "loss": 0.3676, "step": 216880 }, { "epoch": 1.2892392008607212, "grad_norm": 5.795007228851318, "learning_rate": 9.260040955759842e-06, "loss": 0.3874, "step": 216890 }, { "epoch": 1.2892986429373896, "grad_norm": 3.8898706436157227, "learning_rate": 9.259932324059005e-06, "loss": 0.372, "step": 216900 }, { "epoch": 1.289358085014058, "grad_norm": 3.5599918365478516, "learning_rate": 9.259823685022055e-06, "loss": 0.3732, "step": 216910 }, { "epoch": 1.2894175270907264, "grad_norm": 5.544124126434326, "learning_rate": 9.259715038649185e-06, "loss": 0.4238, "step": 216920 }, { "epoch": 1.2894769691673948, "grad_norm": 4.116166591644287, "learning_rate": 9.259606384940574e-06, "loss": 0.3697, "step": 216930 }, { "epoch": 1.2895364112440633, "grad_norm": 6.2124505043029785, "learning_rate": 9.259497723896412e-06, "loss": 0.3771, "step": 216940 }, { "epoch": 1.2895958533207317, "grad_norm": 4.850876331329346, "learning_rate": 9.259389055516889e-06, "loss": 0.388, "step": 216950 }, { "epoch": 1.2896552953974, "grad_norm": 6.083180904388428, "learning_rate": 9.259280379802187e-06, "loss": 0.3829, "step": 216960 }, { "epoch": 1.2897147374740685, "grad_norm": 5.2279510498046875, "learning_rate": 9.259171696752497e-06, "loss": 0.3878, "step": 216970 }, { "epoch": 1.289774179550737, "grad_norm": 5.271570205688477, "learning_rate": 9.259063006368007e-06, "loss": 0.4113, "step": 216980 }, { "epoch": 1.2898336216274051, "grad_norm": 4.339865207672119, "learning_rate": 9.258954308648902e-06, "loss": 0.3874, "step": 216990 }, { "epoch": 1.2898930637040735, "grad_norm": 5.187505722045898, "learning_rate": 9.258845603595368e-06, "loss": 0.3998, "step": 217000 }, { "epoch": 1.289952505780742, "grad_norm": 5.029961109161377, "learning_rate": 9.258736891207594e-06, "loss": 0.4005, "step": 217010 }, { "epoch": 1.2900119478574104, "grad_norm": 3.869112014770508, "learning_rate": 9.258628171485769e-06, "loss": 0.3693, "step": 217020 }, { "epoch": 1.2900713899340788, "grad_norm": 5.161887168884277, "learning_rate": 9.258519444430074e-06, "loss": 0.3232, "step": 217030 }, { "epoch": 1.2901308320107472, "grad_norm": 4.411715984344482, "learning_rate": 9.258410710040704e-06, "loss": 0.3647, "step": 217040 }, { "epoch": 1.2901902740874156, "grad_norm": 6.399928569793701, "learning_rate": 9.258301968317842e-06, "loss": 0.3661, "step": 217050 }, { "epoch": 1.2902497161640838, "grad_norm": 4.744248867034912, "learning_rate": 9.258193219261675e-06, "loss": 0.4106, "step": 217060 }, { "epoch": 1.2903091582407522, "grad_norm": 6.257377624511719, "learning_rate": 9.258084462872392e-06, "loss": 0.4268, "step": 217070 }, { "epoch": 1.2903686003174206, "grad_norm": 4.066125869750977, "learning_rate": 9.257975699150178e-06, "loss": 0.3862, "step": 217080 }, { "epoch": 1.290428042394089, "grad_norm": 7.990057468414307, "learning_rate": 9.257866928095224e-06, "loss": 0.4162, "step": 217090 }, { "epoch": 1.2904874844707575, "grad_norm": 5.978827476501465, "learning_rate": 9.257758149707713e-06, "loss": 0.3572, "step": 217100 }, { "epoch": 1.2905469265474259, "grad_norm": 6.123470306396484, "learning_rate": 9.257649363987837e-06, "loss": 0.3909, "step": 217110 }, { "epoch": 1.2906063686240943, "grad_norm": 4.206942558288574, "learning_rate": 9.257540570935779e-06, "loss": 0.4073, "step": 217120 }, { "epoch": 1.2906658107007627, "grad_norm": 5.998331546783447, "learning_rate": 9.257431770551729e-06, "loss": 0.4042, "step": 217130 }, { "epoch": 1.290725252777431, "grad_norm": 5.058104991912842, "learning_rate": 9.25732296283587e-06, "loss": 0.4159, "step": 217140 }, { "epoch": 1.2907846948540995, "grad_norm": 4.399489879608154, "learning_rate": 9.257214147788398e-06, "loss": 0.424, "step": 217150 }, { "epoch": 1.290844136930768, "grad_norm": 6.061822414398193, "learning_rate": 9.257105325409493e-06, "loss": 0.3993, "step": 217160 }, { "epoch": 1.2909035790074361, "grad_norm": 3.7923171520233154, "learning_rate": 9.256996495699344e-06, "loss": 0.366, "step": 217170 }, { "epoch": 1.2909630210841045, "grad_norm": 7.270752429962158, "learning_rate": 9.25688765865814e-06, "loss": 0.4024, "step": 217180 }, { "epoch": 1.291022463160773, "grad_norm": 4.971397876739502, "learning_rate": 9.256778814286066e-06, "loss": 0.4001, "step": 217190 }, { "epoch": 1.2910819052374414, "grad_norm": 3.991711139678955, "learning_rate": 9.256669962583314e-06, "loss": 0.3537, "step": 217200 }, { "epoch": 1.2911413473141098, "grad_norm": 4.713150501251221, "learning_rate": 9.256561103550066e-06, "loss": 0.3499, "step": 217210 }, { "epoch": 1.2912007893907782, "grad_norm": 5.2951202392578125, "learning_rate": 9.256452237186512e-06, "loss": 0.3807, "step": 217220 }, { "epoch": 1.2912602314674466, "grad_norm": 3.685349225997925, "learning_rate": 9.256343363492842e-06, "loss": 0.3846, "step": 217230 }, { "epoch": 1.2913196735441148, "grad_norm": 6.144449710845947, "learning_rate": 9.256234482469238e-06, "loss": 0.3803, "step": 217240 }, { "epoch": 1.2913791156207832, "grad_norm": 4.235292434692383, "learning_rate": 9.25612559411589e-06, "loss": 0.4096, "step": 217250 }, { "epoch": 1.2914385576974516, "grad_norm": 5.8246541023254395, "learning_rate": 9.256016698432988e-06, "loss": 0.3994, "step": 217260 }, { "epoch": 1.29149799977412, "grad_norm": 4.2521491050720215, "learning_rate": 9.255907795420717e-06, "loss": 0.3615, "step": 217270 }, { "epoch": 1.2915574418507885, "grad_norm": 4.8985595703125, "learning_rate": 9.255798885079263e-06, "loss": 0.4172, "step": 217280 }, { "epoch": 1.2916168839274569, "grad_norm": 4.950993537902832, "learning_rate": 9.255689967408818e-06, "loss": 0.3942, "step": 217290 }, { "epoch": 1.2916763260041253, "grad_norm": 4.89419412612915, "learning_rate": 9.255581042409565e-06, "loss": 0.3752, "step": 217300 }, { "epoch": 1.2917357680807937, "grad_norm": 4.2858734130859375, "learning_rate": 9.255472110081696e-06, "loss": 0.3722, "step": 217310 }, { "epoch": 1.2917952101574621, "grad_norm": 4.269414901733398, "learning_rate": 9.255363170425396e-06, "loss": 0.4028, "step": 217320 }, { "epoch": 1.2918546522341305, "grad_norm": 4.2042646408081055, "learning_rate": 9.25525422344085e-06, "loss": 0.3677, "step": 217330 }, { "epoch": 1.291914094310799, "grad_norm": 5.70189094543457, "learning_rate": 9.255145269128251e-06, "loss": 0.4185, "step": 217340 }, { "epoch": 1.2919735363874674, "grad_norm": 4.115318298339844, "learning_rate": 9.255036307487783e-06, "loss": 0.3969, "step": 217350 }, { "epoch": 1.2920329784641356, "grad_norm": 5.0996012687683105, "learning_rate": 9.254927338519637e-06, "loss": 0.3688, "step": 217360 }, { "epoch": 1.292092420540804, "grad_norm": 4.89761209487915, "learning_rate": 9.254818362223996e-06, "loss": 0.4107, "step": 217370 }, { "epoch": 1.2921518626174724, "grad_norm": 4.253756046295166, "learning_rate": 9.254709378601052e-06, "loss": 0.3657, "step": 217380 }, { "epoch": 1.2922113046941408, "grad_norm": 4.351510524749756, "learning_rate": 9.254600387650989e-06, "loss": 0.3971, "step": 217390 }, { "epoch": 1.2922707467708092, "grad_norm": 5.34967565536499, "learning_rate": 9.254491389373998e-06, "loss": 0.4002, "step": 217400 }, { "epoch": 1.2923301888474776, "grad_norm": 4.635878086090088, "learning_rate": 9.254382383770264e-06, "loss": 0.3662, "step": 217410 }, { "epoch": 1.292389630924146, "grad_norm": 4.8366522789001465, "learning_rate": 9.254273370839977e-06, "loss": 0.3654, "step": 217420 }, { "epoch": 1.2924490730008142, "grad_norm": 5.957144737243652, "learning_rate": 9.254164350583322e-06, "loss": 0.3817, "step": 217430 }, { "epoch": 1.2925085150774827, "grad_norm": 6.9330291748046875, "learning_rate": 9.254055323000489e-06, "loss": 0.3995, "step": 217440 }, { "epoch": 1.292567957154151, "grad_norm": 5.898448944091797, "learning_rate": 9.253946288091666e-06, "loss": 0.3796, "step": 217450 }, { "epoch": 1.2926273992308195, "grad_norm": 4.627196788787842, "learning_rate": 9.25383724585704e-06, "loss": 0.329, "step": 217460 }, { "epoch": 1.292686841307488, "grad_norm": 4.712747097015381, "learning_rate": 9.253728196296798e-06, "loss": 0.3718, "step": 217470 }, { "epoch": 1.2927462833841563, "grad_norm": 6.389196395874023, "learning_rate": 9.253619139411128e-06, "loss": 0.3895, "step": 217480 }, { "epoch": 1.2928057254608247, "grad_norm": 5.124215126037598, "learning_rate": 9.253510075200218e-06, "loss": 0.4016, "step": 217490 }, { "epoch": 1.2928651675374931, "grad_norm": 5.641745567321777, "learning_rate": 9.253401003664257e-06, "loss": 0.4131, "step": 217500 }, { "epoch": 1.2929246096141616, "grad_norm": 4.211391925811768, "learning_rate": 9.253291924803432e-06, "loss": 0.4127, "step": 217510 }, { "epoch": 1.29298405169083, "grad_norm": 4.508485317230225, "learning_rate": 9.253182838617931e-06, "loss": 0.3944, "step": 217520 }, { "epoch": 1.2930434937674984, "grad_norm": 4.777985572814941, "learning_rate": 9.25307374510794e-06, "loss": 0.3741, "step": 217530 }, { "epoch": 1.2931029358441666, "grad_norm": 5.80204963684082, "learning_rate": 9.252964644273652e-06, "loss": 0.364, "step": 217540 }, { "epoch": 1.293162377920835, "grad_norm": 5.43911075592041, "learning_rate": 9.25285553611525e-06, "loss": 0.4195, "step": 217550 }, { "epoch": 1.2932218199975034, "grad_norm": 7.427092552185059, "learning_rate": 9.252746420632922e-06, "loss": 0.4332, "step": 217560 }, { "epoch": 1.2932812620741718, "grad_norm": 5.964314937591553, "learning_rate": 9.252637297826859e-06, "loss": 0.3886, "step": 217570 }, { "epoch": 1.2933407041508402, "grad_norm": 4.920337200164795, "learning_rate": 9.252528167697246e-06, "loss": 0.3683, "step": 217580 }, { "epoch": 1.2934001462275087, "grad_norm": 5.502433776855469, "learning_rate": 9.25241903024427e-06, "loss": 0.4044, "step": 217590 }, { "epoch": 1.293459588304177, "grad_norm": 4.03230619430542, "learning_rate": 9.252309885468125e-06, "loss": 0.3662, "step": 217600 }, { "epoch": 1.2935190303808453, "grad_norm": 5.281162738800049, "learning_rate": 9.252200733368994e-06, "loss": 0.3726, "step": 217610 }, { "epoch": 1.2935784724575137, "grad_norm": 4.82453727722168, "learning_rate": 9.252091573947065e-06, "loss": 0.3575, "step": 217620 }, { "epoch": 1.293637914534182, "grad_norm": 4.282095909118652, "learning_rate": 9.251982407202527e-06, "loss": 0.3909, "step": 217630 }, { "epoch": 1.2936973566108505, "grad_norm": 4.627073764801025, "learning_rate": 9.251873233135568e-06, "loss": 0.3866, "step": 217640 }, { "epoch": 1.293756798687519, "grad_norm": 5.609975814819336, "learning_rate": 9.251764051746378e-06, "loss": 0.3619, "step": 217650 }, { "epoch": 1.2938162407641873, "grad_norm": 5.132467269897461, "learning_rate": 9.25165486303514e-06, "loss": 0.3769, "step": 217660 }, { "epoch": 1.2938756828408557, "grad_norm": 5.003846168518066, "learning_rate": 9.251545667002045e-06, "loss": 0.4187, "step": 217670 }, { "epoch": 1.2939351249175242, "grad_norm": 4.951531887054443, "learning_rate": 9.251436463647283e-06, "loss": 0.3983, "step": 217680 }, { "epoch": 1.2939945669941926, "grad_norm": 5.225114822387695, "learning_rate": 9.251327252971038e-06, "loss": 0.3302, "step": 217690 }, { "epoch": 1.294054009070861, "grad_norm": 6.301059246063232, "learning_rate": 9.251218034973502e-06, "loss": 0.3402, "step": 217700 }, { "epoch": 1.2941134511475294, "grad_norm": 7.010702610015869, "learning_rate": 9.251108809654861e-06, "loss": 0.4601, "step": 217710 }, { "epoch": 1.2941728932241978, "grad_norm": 3.7564117908477783, "learning_rate": 9.250999577015304e-06, "loss": 0.3732, "step": 217720 }, { "epoch": 1.294232335300866, "grad_norm": 5.3963189125061035, "learning_rate": 9.250890337055017e-06, "loss": 0.4306, "step": 217730 }, { "epoch": 1.2942917773775344, "grad_norm": 4.863814353942871, "learning_rate": 9.25078108977419e-06, "loss": 0.3881, "step": 217740 }, { "epoch": 1.2943512194542028, "grad_norm": 3.90852952003479, "learning_rate": 9.250671835173012e-06, "loss": 0.377, "step": 217750 }, { "epoch": 1.2944106615308713, "grad_norm": 4.2820725440979, "learning_rate": 9.250562573251668e-06, "loss": 0.3942, "step": 217760 }, { "epoch": 1.2944701036075397, "grad_norm": 5.110568523406982, "learning_rate": 9.25045330401035e-06, "loss": 0.4087, "step": 217770 }, { "epoch": 1.294529545684208, "grad_norm": 5.049433708190918, "learning_rate": 9.250344027449243e-06, "loss": 0.3805, "step": 217780 }, { "epoch": 1.2945889877608763, "grad_norm": 5.637625217437744, "learning_rate": 9.250234743568538e-06, "loss": 0.4346, "step": 217790 }, { "epoch": 1.2946484298375447, "grad_norm": 4.872706890106201, "learning_rate": 9.25012545236842e-06, "loss": 0.3828, "step": 217800 }, { "epoch": 1.294707871914213, "grad_norm": 5.834474563598633, "learning_rate": 9.25001615384908e-06, "loss": 0.4714, "step": 217810 }, { "epoch": 1.2947673139908815, "grad_norm": 5.443066120147705, "learning_rate": 9.249906848010704e-06, "loss": 0.3856, "step": 217820 }, { "epoch": 1.29482675606755, "grad_norm": 6.017660140991211, "learning_rate": 9.249797534853482e-06, "loss": 0.3784, "step": 217830 }, { "epoch": 1.2948861981442183, "grad_norm": 4.003678798675537, "learning_rate": 9.249688214377601e-06, "loss": 0.3473, "step": 217840 }, { "epoch": 1.2949456402208868, "grad_norm": 5.7056756019592285, "learning_rate": 9.24957888658325e-06, "loss": 0.3802, "step": 217850 }, { "epoch": 1.2950050822975552, "grad_norm": 5.280236721038818, "learning_rate": 9.249469551470618e-06, "loss": 0.3694, "step": 217860 }, { "epoch": 1.2950645243742236, "grad_norm": 4.823439598083496, "learning_rate": 9.249360209039892e-06, "loss": 0.4142, "step": 217870 }, { "epoch": 1.295123966450892, "grad_norm": 5.25401496887207, "learning_rate": 9.249250859291258e-06, "loss": 0.4124, "step": 217880 }, { "epoch": 1.2951834085275604, "grad_norm": 6.412899017333984, "learning_rate": 9.249141502224911e-06, "loss": 0.3894, "step": 217890 }, { "epoch": 1.2952428506042288, "grad_norm": 5.533189296722412, "learning_rate": 9.249032137841034e-06, "loss": 0.4324, "step": 217900 }, { "epoch": 1.295302292680897, "grad_norm": 6.206660747528076, "learning_rate": 9.248922766139816e-06, "loss": 0.3538, "step": 217910 }, { "epoch": 1.2953617347575654, "grad_norm": 4.719137668609619, "learning_rate": 9.248813387121447e-06, "loss": 0.3905, "step": 217920 }, { "epoch": 1.2954211768342339, "grad_norm": 4.1527605056762695, "learning_rate": 9.248704000786114e-06, "loss": 0.3687, "step": 217930 }, { "epoch": 1.2954806189109023, "grad_norm": 4.863561153411865, "learning_rate": 9.248594607134004e-06, "loss": 0.4338, "step": 217940 }, { "epoch": 1.2955400609875707, "grad_norm": 4.637052536010742, "learning_rate": 9.248485206165309e-06, "loss": 0.3702, "step": 217950 }, { "epoch": 1.295599503064239, "grad_norm": 5.083813667297363, "learning_rate": 9.248375797880216e-06, "loss": 0.3953, "step": 217960 }, { "epoch": 1.2956589451409075, "grad_norm": 5.527531623840332, "learning_rate": 9.248266382278911e-06, "loss": 0.4223, "step": 217970 }, { "epoch": 1.2957183872175757, "grad_norm": 6.1148505210876465, "learning_rate": 9.248156959361587e-06, "loss": 0.3799, "step": 217980 }, { "epoch": 1.2957778292942441, "grad_norm": 4.759909629821777, "learning_rate": 9.248047529128428e-06, "loss": 0.3724, "step": 217990 }, { "epoch": 1.2958372713709125, "grad_norm": 3.642253875732422, "learning_rate": 9.247938091579624e-06, "loss": 0.365, "step": 218000 }, { "epoch": 1.295896713447581, "grad_norm": 5.577477931976318, "learning_rate": 9.247828646715366e-06, "loss": 0.388, "step": 218010 }, { "epoch": 1.2959561555242494, "grad_norm": 5.447638988494873, "learning_rate": 9.247719194535838e-06, "loss": 0.3849, "step": 218020 }, { "epoch": 1.2960155976009178, "grad_norm": 5.113281726837158, "learning_rate": 9.247609735041231e-06, "loss": 0.4177, "step": 218030 }, { "epoch": 1.2960750396775862, "grad_norm": 6.348034858703613, "learning_rate": 9.247500268231735e-06, "loss": 0.3859, "step": 218040 }, { "epoch": 1.2961344817542546, "grad_norm": 5.066874980926514, "learning_rate": 9.247390794107535e-06, "loss": 0.4157, "step": 218050 }, { "epoch": 1.296193923830923, "grad_norm": 5.108171463012695, "learning_rate": 9.247281312668821e-06, "loss": 0.3846, "step": 218060 }, { "epoch": 1.2962533659075914, "grad_norm": 6.543271541595459, "learning_rate": 9.247171823915783e-06, "loss": 0.3989, "step": 218070 }, { "epoch": 1.2963128079842599, "grad_norm": 3.8119454383850098, "learning_rate": 9.247062327848608e-06, "loss": 0.3326, "step": 218080 }, { "epoch": 1.2963722500609283, "grad_norm": 4.357351779937744, "learning_rate": 9.246952824467485e-06, "loss": 0.4022, "step": 218090 }, { "epoch": 1.2964316921375965, "grad_norm": 4.421139240264893, "learning_rate": 9.246843313772602e-06, "loss": 0.3876, "step": 218100 }, { "epoch": 1.2964911342142649, "grad_norm": 5.252579689025879, "learning_rate": 9.246733795764148e-06, "loss": 0.3813, "step": 218110 }, { "epoch": 1.2965505762909333, "grad_norm": 6.369124889373779, "learning_rate": 9.246624270442312e-06, "loss": 0.4129, "step": 218120 }, { "epoch": 1.2966100183676017, "grad_norm": 5.481821537017822, "learning_rate": 9.246514737807282e-06, "loss": 0.3536, "step": 218130 }, { "epoch": 1.2966694604442701, "grad_norm": 5.879735469818115, "learning_rate": 9.246405197859247e-06, "loss": 0.3717, "step": 218140 }, { "epoch": 1.2967289025209385, "grad_norm": 5.161329746246338, "learning_rate": 9.246295650598397e-06, "loss": 0.4276, "step": 218150 }, { "epoch": 1.2967883445976067, "grad_norm": 4.288645267486572, "learning_rate": 9.246186096024918e-06, "loss": 0.4138, "step": 218160 }, { "epoch": 1.2968477866742751, "grad_norm": 7.149938583374023, "learning_rate": 9.246076534138999e-06, "loss": 0.4117, "step": 218170 }, { "epoch": 1.2969072287509436, "grad_norm": 5.093979835510254, "learning_rate": 9.245966964940831e-06, "loss": 0.398, "step": 218180 }, { "epoch": 1.296966670827612, "grad_norm": 4.32092809677124, "learning_rate": 9.2458573884306e-06, "loss": 0.3805, "step": 218190 }, { "epoch": 1.2970261129042804, "grad_norm": 4.717116832733154, "learning_rate": 9.245747804608498e-06, "loss": 0.3968, "step": 218200 }, { "epoch": 1.2970855549809488, "grad_norm": 6.215762138366699, "learning_rate": 9.24563821347471e-06, "loss": 0.3883, "step": 218210 }, { "epoch": 1.2971449970576172, "grad_norm": 5.970362663269043, "learning_rate": 9.245528615029427e-06, "loss": 0.3589, "step": 218220 }, { "epoch": 1.2972044391342856, "grad_norm": 5.559999942779541, "learning_rate": 9.245419009272836e-06, "loss": 0.4086, "step": 218230 }, { "epoch": 1.297263881210954, "grad_norm": 4.355564594268799, "learning_rate": 9.245309396205129e-06, "loss": 0.345, "step": 218240 }, { "epoch": 1.2973233232876225, "grad_norm": 5.442795753479004, "learning_rate": 9.24519977582649e-06, "loss": 0.4369, "step": 218250 }, { "epoch": 1.2973827653642909, "grad_norm": 5.867910861968994, "learning_rate": 9.245090148137114e-06, "loss": 0.3998, "step": 218260 }, { "epoch": 1.2974422074409593, "grad_norm": 4.446506500244141, "learning_rate": 9.244980513137183e-06, "loss": 0.3977, "step": 218270 }, { "epoch": 1.2975016495176275, "grad_norm": 4.741032123565674, "learning_rate": 9.24487087082689e-06, "loss": 0.4199, "step": 218280 }, { "epoch": 1.297561091594296, "grad_norm": 3.459543466567993, "learning_rate": 9.244761221206423e-06, "loss": 0.3657, "step": 218290 }, { "epoch": 1.2976205336709643, "grad_norm": 6.587302207946777, "learning_rate": 9.244651564275972e-06, "loss": 0.4106, "step": 218300 }, { "epoch": 1.2976799757476327, "grad_norm": 5.2700676918029785, "learning_rate": 9.244541900035724e-06, "loss": 0.41, "step": 218310 }, { "epoch": 1.2977394178243011, "grad_norm": 4.831609725952148, "learning_rate": 9.244432228485867e-06, "loss": 0.3784, "step": 218320 }, { "epoch": 1.2977988599009695, "grad_norm": 5.242485523223877, "learning_rate": 9.244322549626594e-06, "loss": 0.3824, "step": 218330 }, { "epoch": 1.297858301977638, "grad_norm": 6.858484745025635, "learning_rate": 9.244212863458088e-06, "loss": 0.4131, "step": 218340 }, { "epoch": 1.2979177440543062, "grad_norm": 7.810136795043945, "learning_rate": 9.244103169980542e-06, "loss": 0.4266, "step": 218350 }, { "epoch": 1.2979771861309746, "grad_norm": 4.05375337600708, "learning_rate": 9.243993469194144e-06, "loss": 0.3715, "step": 218360 }, { "epoch": 1.298036628207643, "grad_norm": 6.437008380889893, "learning_rate": 9.243883761099085e-06, "loss": 0.336, "step": 218370 }, { "epoch": 1.2980960702843114, "grad_norm": 4.402800559997559, "learning_rate": 9.243774045695549e-06, "loss": 0.3969, "step": 218380 }, { "epoch": 1.2981555123609798, "grad_norm": 5.983553886413574, "learning_rate": 9.243664322983728e-06, "loss": 0.4462, "step": 218390 }, { "epoch": 1.2982149544376482, "grad_norm": 5.712721824645996, "learning_rate": 9.243554592963812e-06, "loss": 0.3969, "step": 218400 }, { "epoch": 1.2982743965143166, "grad_norm": 4.3965229988098145, "learning_rate": 9.243444855635987e-06, "loss": 0.3697, "step": 218410 }, { "epoch": 1.298333838590985, "grad_norm": 6.450283527374268, "learning_rate": 9.243335111000445e-06, "loss": 0.4182, "step": 218420 }, { "epoch": 1.2983932806676535, "grad_norm": 5.6272454261779785, "learning_rate": 9.243225359057375e-06, "loss": 0.3828, "step": 218430 }, { "epoch": 1.2984527227443219, "grad_norm": 5.995842456817627, "learning_rate": 9.243115599806962e-06, "loss": 0.3478, "step": 218440 }, { "epoch": 1.2985121648209903, "grad_norm": 6.763095855712891, "learning_rate": 9.243005833249398e-06, "loss": 0.4002, "step": 218450 }, { "epoch": 1.2985716068976587, "grad_norm": 5.156470775604248, "learning_rate": 9.242896059384873e-06, "loss": 0.3951, "step": 218460 }, { "epoch": 1.298631048974327, "grad_norm": 6.28713321685791, "learning_rate": 9.242786278213573e-06, "loss": 0.3951, "step": 218470 }, { "epoch": 1.2986904910509953, "grad_norm": 3.943110942840576, "learning_rate": 9.24267648973569e-06, "loss": 0.4089, "step": 218480 }, { "epoch": 1.2987499331276637, "grad_norm": 5.15779972076416, "learning_rate": 9.24256669395141e-06, "loss": 0.3471, "step": 218490 }, { "epoch": 1.2988093752043322, "grad_norm": 5.1046576499938965, "learning_rate": 9.242456890860927e-06, "loss": 0.4011, "step": 218500 }, { "epoch": 1.2988688172810006, "grad_norm": 6.084895610809326, "learning_rate": 9.242347080464427e-06, "loss": 0.3896, "step": 218510 }, { "epoch": 1.298928259357669, "grad_norm": 5.299434185028076, "learning_rate": 9.242237262762098e-06, "loss": 0.3782, "step": 218520 }, { "epoch": 1.2989877014343372, "grad_norm": 5.955693244934082, "learning_rate": 9.24212743775413e-06, "loss": 0.3981, "step": 218530 }, { "epoch": 1.2990471435110056, "grad_norm": 5.4933600425720215, "learning_rate": 9.242017605440711e-06, "loss": 0.4177, "step": 218540 }, { "epoch": 1.299106585587674, "grad_norm": 3.5745391845703125, "learning_rate": 9.241907765822033e-06, "loss": 0.327, "step": 218550 }, { "epoch": 1.2991660276643424, "grad_norm": 4.166670799255371, "learning_rate": 9.241797918898284e-06, "loss": 0.3728, "step": 218560 }, { "epoch": 1.2992254697410108, "grad_norm": 4.4228596687316895, "learning_rate": 9.241688064669651e-06, "loss": 0.3718, "step": 218570 }, { "epoch": 1.2992849118176792, "grad_norm": 5.859536647796631, "learning_rate": 9.241578203136327e-06, "loss": 0.364, "step": 218580 }, { "epoch": 1.2993443538943477, "grad_norm": 5.14522647857666, "learning_rate": 9.2414683342985e-06, "loss": 0.4037, "step": 218590 }, { "epoch": 1.299403795971016, "grad_norm": 6.287108421325684, "learning_rate": 9.241358458156358e-06, "loss": 0.3819, "step": 218600 }, { "epoch": 1.2994632380476845, "grad_norm": 4.406177043914795, "learning_rate": 9.24124857471009e-06, "loss": 0.391, "step": 218610 }, { "epoch": 1.299522680124353, "grad_norm": 4.288108825683594, "learning_rate": 9.241138683959885e-06, "loss": 0.3879, "step": 218620 }, { "epoch": 1.2995821222010213, "grad_norm": 4.222664833068848, "learning_rate": 9.241028785905934e-06, "loss": 0.3628, "step": 218630 }, { "epoch": 1.2996415642776897, "grad_norm": 5.453518867492676, "learning_rate": 9.240918880548424e-06, "loss": 0.3626, "step": 218640 }, { "epoch": 1.299701006354358, "grad_norm": 4.698914527893066, "learning_rate": 9.240808967887547e-06, "loss": 0.3521, "step": 218650 }, { "epoch": 1.2997604484310263, "grad_norm": 5.963568210601807, "learning_rate": 9.240699047923491e-06, "loss": 0.379, "step": 218660 }, { "epoch": 1.2998198905076948, "grad_norm": 5.216673374176025, "learning_rate": 9.240589120656446e-06, "loss": 0.3907, "step": 218670 }, { "epoch": 1.2998793325843632, "grad_norm": 3.5096094608306885, "learning_rate": 9.2404791860866e-06, "loss": 0.3792, "step": 218680 }, { "epoch": 1.2999387746610316, "grad_norm": 6.132411003112793, "learning_rate": 9.240369244214143e-06, "loss": 0.3974, "step": 218690 }, { "epoch": 1.2999982167377, "grad_norm": 5.202242374420166, "learning_rate": 9.240259295039263e-06, "loss": 0.3834, "step": 218700 }, { "epoch": 1.3000576588143684, "grad_norm": 6.129304885864258, "learning_rate": 9.240149338562151e-06, "loss": 0.3889, "step": 218710 }, { "epoch": 1.3001171008910366, "grad_norm": 5.085268974304199, "learning_rate": 9.240039374782997e-06, "loss": 0.4135, "step": 218720 }, { "epoch": 1.300176542967705, "grad_norm": 5.077983379364014, "learning_rate": 9.239929403701988e-06, "loss": 0.3805, "step": 218730 }, { "epoch": 1.3002359850443734, "grad_norm": 3.92939829826355, "learning_rate": 9.239819425319317e-06, "loss": 0.428, "step": 218740 }, { "epoch": 1.3002954271210418, "grad_norm": 4.17356014251709, "learning_rate": 9.239709439635167e-06, "loss": 0.3386, "step": 218750 }, { "epoch": 1.3003548691977103, "grad_norm": 5.124776363372803, "learning_rate": 9.239599446649734e-06, "loss": 0.4049, "step": 218760 }, { "epoch": 1.3004143112743787, "grad_norm": 5.162036895751953, "learning_rate": 9.239489446363205e-06, "loss": 0.3308, "step": 218770 }, { "epoch": 1.300473753351047, "grad_norm": 4.928988456726074, "learning_rate": 9.239379438775768e-06, "loss": 0.4011, "step": 218780 }, { "epoch": 1.3005331954277155, "grad_norm": 7.2918477058410645, "learning_rate": 9.239269423887616e-06, "loss": 0.3715, "step": 218790 }, { "epoch": 1.300592637504384, "grad_norm": 4.025322914123535, "learning_rate": 9.239159401698935e-06, "loss": 0.3812, "step": 218800 }, { "epoch": 1.3006520795810523, "grad_norm": 4.237921237945557, "learning_rate": 9.239049372209916e-06, "loss": 0.4385, "step": 218810 }, { "epoch": 1.3007115216577207, "grad_norm": 4.178022384643555, "learning_rate": 9.238939335420746e-06, "loss": 0.363, "step": 218820 }, { "epoch": 1.3007709637343892, "grad_norm": 3.9684977531433105, "learning_rate": 9.238829291331618e-06, "loss": 0.3557, "step": 218830 }, { "epoch": 1.3008304058110574, "grad_norm": 6.518617630004883, "learning_rate": 9.238719239942723e-06, "loss": 0.3758, "step": 218840 }, { "epoch": 1.3008898478877258, "grad_norm": 4.721467971801758, "learning_rate": 9.238609181254246e-06, "loss": 0.4528, "step": 218850 }, { "epoch": 1.3009492899643942, "grad_norm": 5.528075218200684, "learning_rate": 9.238499115266377e-06, "loss": 0.4247, "step": 218860 }, { "epoch": 1.3010087320410626, "grad_norm": 6.187267780303955, "learning_rate": 9.238389041979308e-06, "loss": 0.4704, "step": 218870 }, { "epoch": 1.301068174117731, "grad_norm": 4.66825008392334, "learning_rate": 9.238278961393226e-06, "loss": 0.3973, "step": 218880 }, { "epoch": 1.3011276161943994, "grad_norm": 4.428161144256592, "learning_rate": 9.238168873508322e-06, "loss": 0.3765, "step": 218890 }, { "epoch": 1.3011870582710676, "grad_norm": 5.15241813659668, "learning_rate": 9.238058778324788e-06, "loss": 0.3856, "step": 218900 }, { "epoch": 1.301246500347736, "grad_norm": 4.666928291320801, "learning_rate": 9.23794867584281e-06, "loss": 0.3824, "step": 218910 }, { "epoch": 1.3013059424244044, "grad_norm": 7.002762794494629, "learning_rate": 9.237838566062576e-06, "loss": 0.3989, "step": 218920 }, { "epoch": 1.3013653845010729, "grad_norm": 4.895103931427002, "learning_rate": 9.237728448984282e-06, "loss": 0.3793, "step": 218930 }, { "epoch": 1.3014248265777413, "grad_norm": 6.509405612945557, "learning_rate": 9.237618324608111e-06, "loss": 0.3841, "step": 218940 }, { "epoch": 1.3014842686544097, "grad_norm": 4.429379463195801, "learning_rate": 9.237508192934259e-06, "loss": 0.3596, "step": 218950 }, { "epoch": 1.301543710731078, "grad_norm": 4.9113359451293945, "learning_rate": 9.237398053962909e-06, "loss": 0.3588, "step": 218960 }, { "epoch": 1.3016031528077465, "grad_norm": 4.993574619293213, "learning_rate": 9.237287907694255e-06, "loss": 0.3893, "step": 218970 }, { "epoch": 1.301662594884415, "grad_norm": 5.984969139099121, "learning_rate": 9.237177754128487e-06, "loss": 0.3618, "step": 218980 }, { "epoch": 1.3017220369610834, "grad_norm": 5.1850409507751465, "learning_rate": 9.237067593265791e-06, "loss": 0.3537, "step": 218990 }, { "epoch": 1.3017814790377518, "grad_norm": 5.520182132720947, "learning_rate": 9.236957425106362e-06, "loss": 0.3774, "step": 219000 }, { "epoch": 1.3018409211144202, "grad_norm": 5.555444717407227, "learning_rate": 9.236847249650384e-06, "loss": 0.3994, "step": 219010 }, { "epoch": 1.3019003631910884, "grad_norm": 4.187219619750977, "learning_rate": 9.236737066898051e-06, "loss": 0.3627, "step": 219020 }, { "epoch": 1.3019598052677568, "grad_norm": 4.852174758911133, "learning_rate": 9.23662687684955e-06, "loss": 0.3581, "step": 219030 }, { "epoch": 1.3020192473444252, "grad_norm": 5.669781684875488, "learning_rate": 9.236516679505073e-06, "loss": 0.3876, "step": 219040 }, { "epoch": 1.3020786894210936, "grad_norm": 6.350513935089111, "learning_rate": 9.236406474864809e-06, "loss": 0.4063, "step": 219050 }, { "epoch": 1.302138131497762, "grad_norm": 4.889266014099121, "learning_rate": 9.236296262928948e-06, "loss": 0.3548, "step": 219060 }, { "epoch": 1.3021975735744304, "grad_norm": 5.144321441650391, "learning_rate": 9.236186043697677e-06, "loss": 0.399, "step": 219070 }, { "epoch": 1.3022570156510989, "grad_norm": 4.471341133117676, "learning_rate": 9.23607581717119e-06, "loss": 0.4344, "step": 219080 }, { "epoch": 1.302316457727767, "grad_norm": 3.7721996307373047, "learning_rate": 9.235965583349675e-06, "loss": 0.4033, "step": 219090 }, { "epoch": 1.3023758998044355, "grad_norm": 4.189981460571289, "learning_rate": 9.235855342233321e-06, "loss": 0.3983, "step": 219100 }, { "epoch": 1.3024353418811039, "grad_norm": 5.829751491546631, "learning_rate": 9.23574509382232e-06, "loss": 0.364, "step": 219110 }, { "epoch": 1.3024947839577723, "grad_norm": 4.4979119300842285, "learning_rate": 9.23563483811686e-06, "loss": 0.3772, "step": 219120 }, { "epoch": 1.3025542260344407, "grad_norm": 4.8956780433654785, "learning_rate": 9.23552457511713e-06, "loss": 0.3751, "step": 219130 }, { "epoch": 1.3026136681111091, "grad_norm": 6.428068161010742, "learning_rate": 9.235414304823324e-06, "loss": 0.3656, "step": 219140 }, { "epoch": 1.3026731101877775, "grad_norm": 5.189494609832764, "learning_rate": 9.235304027235628e-06, "loss": 0.3799, "step": 219150 }, { "epoch": 1.302732552264446, "grad_norm": 7.315845012664795, "learning_rate": 9.235193742354232e-06, "loss": 0.4097, "step": 219160 }, { "epoch": 1.3027919943411144, "grad_norm": 4.9701151847839355, "learning_rate": 9.235083450179327e-06, "loss": 0.3671, "step": 219170 }, { "epoch": 1.3028514364177828, "grad_norm": 4.378046035766602, "learning_rate": 9.234973150711105e-06, "loss": 0.3649, "step": 219180 }, { "epoch": 1.3029108784944512, "grad_norm": 6.007637023925781, "learning_rate": 9.234862843949752e-06, "loss": 0.3908, "step": 219190 }, { "epoch": 1.3029703205711196, "grad_norm": 4.35441255569458, "learning_rate": 9.23475252989546e-06, "loss": 0.4005, "step": 219200 }, { "epoch": 1.3030297626477878, "grad_norm": 4.843649387359619, "learning_rate": 9.23464220854842e-06, "loss": 0.4045, "step": 219210 }, { "epoch": 1.3030892047244562, "grad_norm": 6.49044132232666, "learning_rate": 9.234531879908821e-06, "loss": 0.3597, "step": 219220 }, { "epoch": 1.3031486468011246, "grad_norm": 4.924829006195068, "learning_rate": 9.234421543976853e-06, "loss": 0.3278, "step": 219230 }, { "epoch": 1.303208088877793, "grad_norm": 4.609453201293945, "learning_rate": 9.234311200752706e-06, "loss": 0.3745, "step": 219240 }, { "epoch": 1.3032675309544615, "grad_norm": 4.537737846374512, "learning_rate": 9.234200850236567e-06, "loss": 0.3973, "step": 219250 }, { "epoch": 1.3033269730311299, "grad_norm": 5.869812488555908, "learning_rate": 9.234090492428631e-06, "loss": 0.3956, "step": 219260 }, { "epoch": 1.303386415107798, "grad_norm": 5.56050968170166, "learning_rate": 9.233980127329088e-06, "loss": 0.3893, "step": 219270 }, { "epoch": 1.3034458571844665, "grad_norm": 4.680631160736084, "learning_rate": 9.233869754938123e-06, "loss": 0.3901, "step": 219280 }, { "epoch": 1.303505299261135, "grad_norm": 5.763478755950928, "learning_rate": 9.23375937525593e-06, "loss": 0.3544, "step": 219290 }, { "epoch": 1.3035647413378033, "grad_norm": 4.4365949630737305, "learning_rate": 9.233648988282697e-06, "loss": 0.3728, "step": 219300 }, { "epoch": 1.3036241834144717, "grad_norm": 5.204407691955566, "learning_rate": 9.233538594018617e-06, "loss": 0.3604, "step": 219310 }, { "epoch": 1.3036836254911401, "grad_norm": 7.01436710357666, "learning_rate": 9.233428192463879e-06, "loss": 0.3883, "step": 219320 }, { "epoch": 1.3037430675678086, "grad_norm": 4.909659385681152, "learning_rate": 9.23331778361867e-06, "loss": 0.3827, "step": 219330 }, { "epoch": 1.303802509644477, "grad_norm": 6.166971683502197, "learning_rate": 9.233207367483185e-06, "loss": 0.4338, "step": 219340 }, { "epoch": 1.3038619517211454, "grad_norm": 5.387884140014648, "learning_rate": 9.23309694405761e-06, "loss": 0.3987, "step": 219350 }, { "epoch": 1.3039213937978138, "grad_norm": 5.604742050170898, "learning_rate": 9.232986513342139e-06, "loss": 0.3997, "step": 219360 }, { "epoch": 1.3039808358744822, "grad_norm": 6.526537895202637, "learning_rate": 9.232876075336959e-06, "loss": 0.4033, "step": 219370 }, { "epoch": 1.3040402779511506, "grad_norm": 6.7022786140441895, "learning_rate": 9.232765630042261e-06, "loss": 0.3892, "step": 219380 }, { "epoch": 1.3040997200278188, "grad_norm": 4.778238773345947, "learning_rate": 9.232655177458236e-06, "loss": 0.4491, "step": 219390 }, { "epoch": 1.3041591621044872, "grad_norm": 5.014383792877197, "learning_rate": 9.232544717585073e-06, "loss": 0.3532, "step": 219400 }, { "epoch": 1.3042186041811556, "grad_norm": 5.140329360961914, "learning_rate": 9.232434250422963e-06, "loss": 0.3966, "step": 219410 }, { "epoch": 1.304278046257824, "grad_norm": 4.859828948974609, "learning_rate": 9.232323775972098e-06, "loss": 0.346, "step": 219420 }, { "epoch": 1.3043374883344925, "grad_norm": 5.477402687072754, "learning_rate": 9.232213294232666e-06, "loss": 0.4061, "step": 219430 }, { "epoch": 1.304396930411161, "grad_norm": 4.700450897216797, "learning_rate": 9.232102805204857e-06, "loss": 0.3811, "step": 219440 }, { "epoch": 1.3044563724878293, "grad_norm": 4.665627956390381, "learning_rate": 9.231992308888862e-06, "loss": 0.4052, "step": 219450 }, { "epoch": 1.3045158145644975, "grad_norm": 5.262538433074951, "learning_rate": 9.23188180528487e-06, "loss": 0.3785, "step": 219460 }, { "epoch": 1.304575256641166, "grad_norm": 5.936870574951172, "learning_rate": 9.231771294393075e-06, "loss": 0.3959, "step": 219470 }, { "epoch": 1.3046346987178343, "grad_norm": 5.661844730377197, "learning_rate": 9.231660776213665e-06, "loss": 0.4165, "step": 219480 }, { "epoch": 1.3046941407945027, "grad_norm": 5.560606956481934, "learning_rate": 9.231550250746828e-06, "loss": 0.3627, "step": 219490 }, { "epoch": 1.3047535828711712, "grad_norm": 5.6633620262146, "learning_rate": 9.231439717992758e-06, "loss": 0.3993, "step": 219500 }, { "epoch": 1.3048130249478396, "grad_norm": 5.606533050537109, "learning_rate": 9.231329177951643e-06, "loss": 0.3731, "step": 219510 }, { "epoch": 1.304872467024508, "grad_norm": 5.358537673950195, "learning_rate": 9.231218630623674e-06, "loss": 0.3777, "step": 219520 }, { "epoch": 1.3049319091011764, "grad_norm": 7.378981590270996, "learning_rate": 9.231108076009043e-06, "loss": 0.3683, "step": 219530 }, { "epoch": 1.3049913511778448, "grad_norm": 4.727837562561035, "learning_rate": 9.230997514107939e-06, "loss": 0.3526, "step": 219540 }, { "epoch": 1.3050507932545132, "grad_norm": 4.760234355926514, "learning_rate": 9.230886944920552e-06, "loss": 0.4125, "step": 219550 }, { "epoch": 1.3051102353311816, "grad_norm": 6.341650485992432, "learning_rate": 9.230776368447073e-06, "loss": 0.3939, "step": 219560 }, { "epoch": 1.3051696774078498, "grad_norm": 6.102309703826904, "learning_rate": 9.23066578468769e-06, "loss": 0.3805, "step": 219570 }, { "epoch": 1.3052291194845183, "grad_norm": 4.636322498321533, "learning_rate": 9.2305551936426e-06, "loss": 0.3787, "step": 219580 }, { "epoch": 1.3052885615611867, "grad_norm": 4.453725337982178, "learning_rate": 9.230444595311987e-06, "loss": 0.3625, "step": 219590 }, { "epoch": 1.305348003637855, "grad_norm": 4.315883636474609, "learning_rate": 9.230333989696042e-06, "loss": 0.3989, "step": 219600 }, { "epoch": 1.3054074457145235, "grad_norm": 4.867331504821777, "learning_rate": 9.23022337679496e-06, "loss": 0.3785, "step": 219610 }, { "epoch": 1.305466887791192, "grad_norm": 5.581725597381592, "learning_rate": 9.230112756608927e-06, "loss": 0.4009, "step": 219620 }, { "epoch": 1.3055263298678603, "grad_norm": 4.231964111328125, "learning_rate": 9.230002129138135e-06, "loss": 0.3932, "step": 219630 }, { "epoch": 1.3055857719445285, "grad_norm": 3.999199628829956, "learning_rate": 9.229891494382777e-06, "loss": 0.3845, "step": 219640 }, { "epoch": 1.305645214021197, "grad_norm": 3.9879937171936035, "learning_rate": 9.229780852343039e-06, "loss": 0.4436, "step": 219650 }, { "epoch": 1.3057046560978653, "grad_norm": 5.110739707946777, "learning_rate": 9.229670203019114e-06, "loss": 0.3324, "step": 219660 }, { "epoch": 1.3057640981745338, "grad_norm": 6.856705665588379, "learning_rate": 9.229559546411191e-06, "loss": 0.4, "step": 219670 }, { "epoch": 1.3058235402512022, "grad_norm": 5.160233497619629, "learning_rate": 9.229448882519463e-06, "loss": 0.3364, "step": 219680 }, { "epoch": 1.3058829823278706, "grad_norm": 5.074419021606445, "learning_rate": 9.229338211344121e-06, "loss": 0.3577, "step": 219690 }, { "epoch": 1.305942424404539, "grad_norm": 4.555700778961182, "learning_rate": 9.229227532885353e-06, "loss": 0.4237, "step": 219700 }, { "epoch": 1.3060018664812074, "grad_norm": 4.192538738250732, "learning_rate": 9.22911684714335e-06, "loss": 0.373, "step": 219710 }, { "epoch": 1.3060613085578758, "grad_norm": 3.7355053424835205, "learning_rate": 9.229006154118301e-06, "loss": 0.385, "step": 219720 }, { "epoch": 1.3061207506345442, "grad_norm": 5.933909893035889, "learning_rate": 9.2288954538104e-06, "loss": 0.4476, "step": 219730 }, { "epoch": 1.3061801927112127, "grad_norm": 5.2301716804504395, "learning_rate": 9.228784746219838e-06, "loss": 0.4007, "step": 219740 }, { "epoch": 1.306239634787881, "grad_norm": 5.112834930419922, "learning_rate": 9.228674031346805e-06, "loss": 0.4053, "step": 219750 }, { "epoch": 1.3062990768645493, "grad_norm": 4.665765285491943, "learning_rate": 9.228563309191489e-06, "loss": 0.4012, "step": 219760 }, { "epoch": 1.3063585189412177, "grad_norm": 5.295487880706787, "learning_rate": 9.228452579754081e-06, "loss": 0.3787, "step": 219770 }, { "epoch": 1.306417961017886, "grad_norm": 4.407024383544922, "learning_rate": 9.228341843034775e-06, "loss": 0.3812, "step": 219780 }, { "epoch": 1.3064774030945545, "grad_norm": 5.849641799926758, "learning_rate": 9.22823109903376e-06, "loss": 0.3672, "step": 219790 }, { "epoch": 1.306536845171223, "grad_norm": 6.506241321563721, "learning_rate": 9.228120347751227e-06, "loss": 0.3713, "step": 219800 }, { "epoch": 1.3065962872478913, "grad_norm": 5.423861026763916, "learning_rate": 9.228009589187365e-06, "loss": 0.4145, "step": 219810 }, { "epoch": 1.3066557293245598, "grad_norm": 5.251806735992432, "learning_rate": 9.227898823342365e-06, "loss": 0.3758, "step": 219820 }, { "epoch": 1.306715171401228, "grad_norm": 4.512701988220215, "learning_rate": 9.227788050216422e-06, "loss": 0.3599, "step": 219830 }, { "epoch": 1.3067746134778964, "grad_norm": 5.03742790222168, "learning_rate": 9.227677269809721e-06, "loss": 0.3777, "step": 219840 }, { "epoch": 1.3068340555545648, "grad_norm": 5.351989269256592, "learning_rate": 9.227566482122456e-06, "loss": 0.3678, "step": 219850 }, { "epoch": 1.3068934976312332, "grad_norm": 4.809078216552734, "learning_rate": 9.227455687154817e-06, "loss": 0.3587, "step": 219860 }, { "epoch": 1.3069529397079016, "grad_norm": 4.012665271759033, "learning_rate": 9.227344884906995e-06, "loss": 0.3984, "step": 219870 }, { "epoch": 1.30701238178457, "grad_norm": 7.023594856262207, "learning_rate": 9.227234075379181e-06, "loss": 0.4014, "step": 219880 }, { "epoch": 1.3070718238612384, "grad_norm": 3.846480131149292, "learning_rate": 9.227123258571564e-06, "loss": 0.3757, "step": 219890 }, { "epoch": 1.3071312659379068, "grad_norm": 4.077526092529297, "learning_rate": 9.227012434484338e-06, "loss": 0.3516, "step": 219900 }, { "epoch": 1.3071907080145753, "grad_norm": 3.787750720977783, "learning_rate": 9.226901603117693e-06, "loss": 0.4132, "step": 219910 }, { "epoch": 1.3072501500912437, "grad_norm": 4.3541259765625, "learning_rate": 9.226790764471818e-06, "loss": 0.405, "step": 219920 }, { "epoch": 1.307309592167912, "grad_norm": 5.942427635192871, "learning_rate": 9.226679918546904e-06, "loss": 0.4257, "step": 219930 }, { "epoch": 1.3073690342445803, "grad_norm": 6.060328006744385, "learning_rate": 9.226569065343145e-06, "loss": 0.3881, "step": 219940 }, { "epoch": 1.3074284763212487, "grad_norm": 5.433993339538574, "learning_rate": 9.226458204860728e-06, "loss": 0.4044, "step": 219950 }, { "epoch": 1.3074879183979171, "grad_norm": 7.2018723487854, "learning_rate": 9.226347337099845e-06, "loss": 0.425, "step": 219960 }, { "epoch": 1.3075473604745855, "grad_norm": 5.402310848236084, "learning_rate": 9.22623646206069e-06, "loss": 0.3877, "step": 219970 }, { "epoch": 1.307606802551254, "grad_norm": 4.8125224113464355, "learning_rate": 9.22612557974345e-06, "loss": 0.389, "step": 219980 }, { "epoch": 1.3076662446279224, "grad_norm": 6.618754863739014, "learning_rate": 9.226014690148318e-06, "loss": 0.3556, "step": 219990 }, { "epoch": 1.3077256867045908, "grad_norm": 5.2836995124816895, "learning_rate": 9.225903793275484e-06, "loss": 0.3967, "step": 220000 }, { "epoch": 1.307785128781259, "grad_norm": 4.387447357177734, "learning_rate": 9.22579288912514e-06, "loss": 0.4026, "step": 220010 }, { "epoch": 1.3078445708579274, "grad_norm": 5.8343186378479, "learning_rate": 9.225681977697476e-06, "loss": 0.3678, "step": 220020 }, { "epoch": 1.3079040129345958, "grad_norm": 5.295384407043457, "learning_rate": 9.225571058992685e-06, "loss": 0.3975, "step": 220030 }, { "epoch": 1.3079634550112642, "grad_norm": 5.01909065246582, "learning_rate": 9.225460133010953e-06, "loss": 0.3755, "step": 220040 }, { "epoch": 1.3080228970879326, "grad_norm": 3.9583373069763184, "learning_rate": 9.225349199752477e-06, "loss": 0.4271, "step": 220050 }, { "epoch": 1.308082339164601, "grad_norm": 4.68502140045166, "learning_rate": 9.225238259217445e-06, "loss": 0.3431, "step": 220060 }, { "epoch": 1.3081417812412695, "grad_norm": 6.91134786605835, "learning_rate": 9.225127311406049e-06, "loss": 0.3545, "step": 220070 }, { "epoch": 1.3082012233179379, "grad_norm": 6.491092681884766, "learning_rate": 9.22501635631848e-06, "loss": 0.4348, "step": 220080 }, { "epoch": 1.3082606653946063, "grad_norm": 5.319870471954346, "learning_rate": 9.224905393954926e-06, "loss": 0.4055, "step": 220090 }, { "epoch": 1.3083201074712747, "grad_norm": 3.7933990955352783, "learning_rate": 9.224794424315584e-06, "loss": 0.3594, "step": 220100 }, { "epoch": 1.308379549547943, "grad_norm": 5.173564910888672, "learning_rate": 9.22468344740064e-06, "loss": 0.3609, "step": 220110 }, { "epoch": 1.3084389916246115, "grad_norm": 5.049593925476074, "learning_rate": 9.224572463210289e-06, "loss": 0.4291, "step": 220120 }, { "epoch": 1.3084984337012797, "grad_norm": 5.323087215423584, "learning_rate": 9.224461471744718e-06, "loss": 0.3765, "step": 220130 }, { "epoch": 1.3085578757779481, "grad_norm": 4.957830429077148, "learning_rate": 9.22435047300412e-06, "loss": 0.4014, "step": 220140 }, { "epoch": 1.3086173178546165, "grad_norm": 6.639767646789551, "learning_rate": 9.224239466988689e-06, "loss": 0.4305, "step": 220150 }, { "epoch": 1.308676759931285, "grad_norm": 4.7143683433532715, "learning_rate": 9.224128453698613e-06, "loss": 0.4094, "step": 220160 }, { "epoch": 1.3087362020079534, "grad_norm": 5.429442882537842, "learning_rate": 9.224017433134082e-06, "loss": 0.4102, "step": 220170 }, { "epoch": 1.3087956440846218, "grad_norm": 5.097253322601318, "learning_rate": 9.22390640529529e-06, "loss": 0.4079, "step": 220180 }, { "epoch": 1.3088550861612902, "grad_norm": 3.6555917263031006, "learning_rate": 9.223795370182427e-06, "loss": 0.3533, "step": 220190 }, { "epoch": 1.3089145282379584, "grad_norm": 5.913020133972168, "learning_rate": 9.223684327795685e-06, "loss": 0.398, "step": 220200 }, { "epoch": 1.3089739703146268, "grad_norm": 6.155914783477783, "learning_rate": 9.223573278135254e-06, "loss": 0.3727, "step": 220210 }, { "epoch": 1.3090334123912952, "grad_norm": 4.598689556121826, "learning_rate": 9.223462221201326e-06, "loss": 0.3833, "step": 220220 }, { "epoch": 1.3090928544679636, "grad_norm": 5.648428916931152, "learning_rate": 9.223351156994092e-06, "loss": 0.3929, "step": 220230 }, { "epoch": 1.309152296544632, "grad_norm": 4.792531967163086, "learning_rate": 9.223240085513742e-06, "loss": 0.4016, "step": 220240 }, { "epoch": 1.3092117386213005, "grad_norm": 5.1184515953063965, "learning_rate": 9.223129006760472e-06, "loss": 0.3839, "step": 220250 }, { "epoch": 1.3092711806979689, "grad_norm": 4.85050630569458, "learning_rate": 9.223017920734468e-06, "loss": 0.3808, "step": 220260 }, { "epoch": 1.3093306227746373, "grad_norm": 4.697544097900391, "learning_rate": 9.222906827435923e-06, "loss": 0.3508, "step": 220270 }, { "epoch": 1.3093900648513057, "grad_norm": 4.594944000244141, "learning_rate": 9.222795726865029e-06, "loss": 0.3768, "step": 220280 }, { "epoch": 1.3094495069279741, "grad_norm": 6.074418544769287, "learning_rate": 9.222684619021978e-06, "loss": 0.3997, "step": 220290 }, { "epoch": 1.3095089490046425, "grad_norm": 5.337569713592529, "learning_rate": 9.222573503906958e-06, "loss": 0.3638, "step": 220300 }, { "epoch": 1.3095683910813107, "grad_norm": 5.886741638183594, "learning_rate": 9.222462381520165e-06, "loss": 0.3987, "step": 220310 }, { "epoch": 1.3096278331579791, "grad_norm": 6.38266658782959, "learning_rate": 9.222351251861785e-06, "loss": 0.3884, "step": 220320 }, { "epoch": 1.3096872752346476, "grad_norm": 5.539353370666504, "learning_rate": 9.222240114932016e-06, "loss": 0.354, "step": 220330 }, { "epoch": 1.309746717311316, "grad_norm": 6.136091232299805, "learning_rate": 9.222128970731043e-06, "loss": 0.4005, "step": 220340 }, { "epoch": 1.3098061593879844, "grad_norm": 5.504856109619141, "learning_rate": 9.222017819259061e-06, "loss": 0.4406, "step": 220350 }, { "epoch": 1.3098656014646528, "grad_norm": 6.281885623931885, "learning_rate": 9.22190666051626e-06, "loss": 0.374, "step": 220360 }, { "epoch": 1.3099250435413212, "grad_norm": 4.636435508728027, "learning_rate": 9.221795494502832e-06, "loss": 0.41, "step": 220370 }, { "epoch": 1.3099844856179894, "grad_norm": 7.182599067687988, "learning_rate": 9.22168432121897e-06, "loss": 0.4131, "step": 220380 }, { "epoch": 1.3100439276946578, "grad_norm": 5.418089389801025, "learning_rate": 9.221573140664862e-06, "loss": 0.3555, "step": 220390 }, { "epoch": 1.3101033697713262, "grad_norm": 4.303263187408447, "learning_rate": 9.221461952840703e-06, "loss": 0.3781, "step": 220400 }, { "epoch": 1.3101628118479947, "grad_norm": 4.371227264404297, "learning_rate": 9.22135075774668e-06, "loss": 0.3896, "step": 220410 }, { "epoch": 1.310222253924663, "grad_norm": 4.5928497314453125, "learning_rate": 9.22123955538299e-06, "loss": 0.3282, "step": 220420 }, { "epoch": 1.3102816960013315, "grad_norm": 4.826045989990234, "learning_rate": 9.221128345749822e-06, "loss": 0.402, "step": 220430 }, { "epoch": 1.310341138078, "grad_norm": 5.019022464752197, "learning_rate": 9.221017128847366e-06, "loss": 0.3719, "step": 220440 }, { "epoch": 1.3104005801546683, "grad_norm": 4.40350341796875, "learning_rate": 9.220905904675815e-06, "loss": 0.3957, "step": 220450 }, { "epoch": 1.3104600222313367, "grad_norm": 6.0379815101623535, "learning_rate": 9.220794673235361e-06, "loss": 0.3816, "step": 220460 }, { "epoch": 1.3105194643080051, "grad_norm": 4.199878692626953, "learning_rate": 9.220683434526194e-06, "loss": 0.3471, "step": 220470 }, { "epoch": 1.3105789063846736, "grad_norm": 4.453105926513672, "learning_rate": 9.220572188548507e-06, "loss": 0.3938, "step": 220480 }, { "epoch": 1.310638348461342, "grad_norm": 4.520206451416016, "learning_rate": 9.220460935302491e-06, "loss": 0.3849, "step": 220490 }, { "epoch": 1.3106977905380102, "grad_norm": 5.114169120788574, "learning_rate": 9.220349674788338e-06, "loss": 0.3946, "step": 220500 }, { "epoch": 1.3107572326146786, "grad_norm": 5.15496826171875, "learning_rate": 9.220238407006239e-06, "loss": 0.3894, "step": 220510 }, { "epoch": 1.310816674691347, "grad_norm": 5.001232624053955, "learning_rate": 9.220127131956387e-06, "loss": 0.3474, "step": 220520 }, { "epoch": 1.3108761167680154, "grad_norm": 5.554012775421143, "learning_rate": 9.220015849638972e-06, "loss": 0.3797, "step": 220530 }, { "epoch": 1.3109355588446838, "grad_norm": 4.210726737976074, "learning_rate": 9.219904560054186e-06, "loss": 0.3763, "step": 220540 }, { "epoch": 1.3109950009213522, "grad_norm": 5.339270114898682, "learning_rate": 9.219793263202219e-06, "loss": 0.3989, "step": 220550 }, { "epoch": 1.3110544429980207, "grad_norm": 6.289532661437988, "learning_rate": 9.219681959083267e-06, "loss": 0.3674, "step": 220560 }, { "epoch": 1.3111138850746888, "grad_norm": 3.712170124053955, "learning_rate": 9.219570647697518e-06, "loss": 0.3759, "step": 220570 }, { "epoch": 1.3111733271513573, "grad_norm": 4.547926902770996, "learning_rate": 9.219459329045166e-06, "loss": 0.382, "step": 220580 }, { "epoch": 1.3112327692280257, "grad_norm": 4.042778015136719, "learning_rate": 9.2193480031264e-06, "loss": 0.3565, "step": 220590 }, { "epoch": 1.311292211304694, "grad_norm": 6.174621105194092, "learning_rate": 9.219236669941414e-06, "loss": 0.3756, "step": 220600 }, { "epoch": 1.3113516533813625, "grad_norm": 4.377117156982422, "learning_rate": 9.219125329490398e-06, "loss": 0.3415, "step": 220610 }, { "epoch": 1.311411095458031, "grad_norm": 4.451150894165039, "learning_rate": 9.219013981773548e-06, "loss": 0.4101, "step": 220620 }, { "epoch": 1.3114705375346993, "grad_norm": 5.402502536773682, "learning_rate": 9.21890262679105e-06, "loss": 0.4281, "step": 220630 }, { "epoch": 1.3115299796113677, "grad_norm": 5.005306720733643, "learning_rate": 9.218791264543098e-06, "loss": 0.3958, "step": 220640 }, { "epoch": 1.3115894216880362, "grad_norm": 4.912779331207275, "learning_rate": 9.218679895029886e-06, "loss": 0.4086, "step": 220650 }, { "epoch": 1.3116488637647046, "grad_norm": 6.312378406524658, "learning_rate": 9.218568518251602e-06, "loss": 0.3708, "step": 220660 }, { "epoch": 1.311708305841373, "grad_norm": 5.218009948730469, "learning_rate": 9.218457134208441e-06, "loss": 0.4196, "step": 220670 }, { "epoch": 1.3117677479180412, "grad_norm": 5.495754718780518, "learning_rate": 9.218345742900591e-06, "loss": 0.3971, "step": 220680 }, { "epoch": 1.3118271899947096, "grad_norm": 5.542585372924805, "learning_rate": 9.21823434432825e-06, "loss": 0.3504, "step": 220690 }, { "epoch": 1.311886632071378, "grad_norm": 5.012430191040039, "learning_rate": 9.218122938491603e-06, "loss": 0.374, "step": 220700 }, { "epoch": 1.3119460741480464, "grad_norm": 5.513172626495361, "learning_rate": 9.218011525390846e-06, "loss": 0.3759, "step": 220710 }, { "epoch": 1.3120055162247148, "grad_norm": 5.788945198059082, "learning_rate": 9.21790010502617e-06, "loss": 0.3947, "step": 220720 }, { "epoch": 1.3120649583013833, "grad_norm": 5.4469709396362305, "learning_rate": 9.217788677397768e-06, "loss": 0.437, "step": 220730 }, { "epoch": 1.3121244003780517, "grad_norm": 5.194035053253174, "learning_rate": 9.21767724250583e-06, "loss": 0.4218, "step": 220740 }, { "epoch": 1.3121838424547199, "grad_norm": 5.214304447174072, "learning_rate": 9.217565800350548e-06, "loss": 0.3932, "step": 220750 }, { "epoch": 1.3122432845313883, "grad_norm": 5.569438934326172, "learning_rate": 9.217454350932113e-06, "loss": 0.4005, "step": 220760 }, { "epoch": 1.3123027266080567, "grad_norm": 4.072530746459961, "learning_rate": 9.21734289425072e-06, "loss": 0.3706, "step": 220770 }, { "epoch": 1.312362168684725, "grad_norm": 3.890498399734497, "learning_rate": 9.21723143030656e-06, "loss": 0.3837, "step": 220780 }, { "epoch": 1.3124216107613935, "grad_norm": 5.856587886810303, "learning_rate": 9.217119959099823e-06, "loss": 0.3835, "step": 220790 }, { "epoch": 1.312481052838062, "grad_norm": 4.638991832733154, "learning_rate": 9.217008480630703e-06, "loss": 0.3766, "step": 220800 }, { "epoch": 1.3125404949147303, "grad_norm": 6.824349403381348, "learning_rate": 9.21689699489939e-06, "loss": 0.3599, "step": 220810 }, { "epoch": 1.3125999369913988, "grad_norm": 6.017502307891846, "learning_rate": 9.216785501906078e-06, "loss": 0.3937, "step": 220820 }, { "epoch": 1.3126593790680672, "grad_norm": 4.425079822540283, "learning_rate": 9.216674001650959e-06, "loss": 0.3735, "step": 220830 }, { "epoch": 1.3127188211447356, "grad_norm": 4.956940650939941, "learning_rate": 9.216562494134224e-06, "loss": 0.3984, "step": 220840 }, { "epoch": 1.312778263221404, "grad_norm": 4.805010795593262, "learning_rate": 9.216450979356064e-06, "loss": 0.4041, "step": 220850 }, { "epoch": 1.3128377052980724, "grad_norm": 5.042102813720703, "learning_rate": 9.216339457316675e-06, "loss": 0.3789, "step": 220860 }, { "epoch": 1.3128971473747406, "grad_norm": 6.693687438964844, "learning_rate": 9.216227928016243e-06, "loss": 0.4037, "step": 220870 }, { "epoch": 1.312956589451409, "grad_norm": 6.681138038635254, "learning_rate": 9.216116391454966e-06, "loss": 0.424, "step": 220880 }, { "epoch": 1.3130160315280774, "grad_norm": 5.14653205871582, "learning_rate": 9.216004847633032e-06, "loss": 0.4027, "step": 220890 }, { "epoch": 1.3130754736047459, "grad_norm": 6.568835258483887, "learning_rate": 9.215893296550636e-06, "loss": 0.4048, "step": 220900 }, { "epoch": 1.3131349156814143, "grad_norm": 4.250080585479736, "learning_rate": 9.215781738207967e-06, "loss": 0.4079, "step": 220910 }, { "epoch": 1.3131943577580827, "grad_norm": 4.592588424682617, "learning_rate": 9.21567017260522e-06, "loss": 0.3932, "step": 220920 }, { "epoch": 1.313253799834751, "grad_norm": 5.935316562652588, "learning_rate": 9.215558599742585e-06, "loss": 0.4054, "step": 220930 }, { "epoch": 1.3133132419114193, "grad_norm": 4.956270694732666, "learning_rate": 9.215447019620256e-06, "loss": 0.3572, "step": 220940 }, { "epoch": 1.3133726839880877, "grad_norm": 4.158783435821533, "learning_rate": 9.215335432238423e-06, "loss": 0.3759, "step": 220950 }, { "epoch": 1.3134321260647561, "grad_norm": 7.114057540893555, "learning_rate": 9.215223837597282e-06, "loss": 0.4189, "step": 220960 }, { "epoch": 1.3134915681414245, "grad_norm": 6.008260726928711, "learning_rate": 9.215112235697021e-06, "loss": 0.3795, "step": 220970 }, { "epoch": 1.313551010218093, "grad_norm": 5.235452175140381, "learning_rate": 9.215000626537834e-06, "loss": 0.3737, "step": 220980 }, { "epoch": 1.3136104522947614, "grad_norm": 3.7999794483184814, "learning_rate": 9.214889010119911e-06, "loss": 0.3384, "step": 220990 }, { "epoch": 1.3136698943714298, "grad_norm": 4.864530086517334, "learning_rate": 9.21477738644345e-06, "loss": 0.421, "step": 221000 }, { "epoch": 1.3137293364480982, "grad_norm": 5.656365394592285, "learning_rate": 9.214665755508638e-06, "loss": 0.3535, "step": 221010 }, { "epoch": 1.3137887785247666, "grad_norm": 3.7936644554138184, "learning_rate": 9.214554117315666e-06, "loss": 0.3399, "step": 221020 }, { "epoch": 1.313848220601435, "grad_norm": 6.193423271179199, "learning_rate": 9.214442471864732e-06, "loss": 0.3692, "step": 221030 }, { "epoch": 1.3139076626781034, "grad_norm": 5.662559509277344, "learning_rate": 9.214330819156024e-06, "loss": 0.3481, "step": 221040 }, { "epoch": 1.3139671047547716, "grad_norm": 8.790257453918457, "learning_rate": 9.214219159189737e-06, "loss": 0.3646, "step": 221050 }, { "epoch": 1.31402654683144, "grad_norm": 4.060445308685303, "learning_rate": 9.21410749196606e-06, "loss": 0.3809, "step": 221060 }, { "epoch": 1.3140859889081085, "grad_norm": 5.557764530181885, "learning_rate": 9.213995817485187e-06, "loss": 0.4331, "step": 221070 }, { "epoch": 1.3141454309847769, "grad_norm": 5.373885154724121, "learning_rate": 9.21388413574731e-06, "loss": 0.374, "step": 221080 }, { "epoch": 1.3142048730614453, "grad_norm": 4.1848602294921875, "learning_rate": 9.213772446752625e-06, "loss": 0.4069, "step": 221090 }, { "epoch": 1.3142643151381137, "grad_norm": 7.060923099517822, "learning_rate": 9.213660750501319e-06, "loss": 0.3756, "step": 221100 }, { "epoch": 1.3143237572147821, "grad_norm": 6.3557915687561035, "learning_rate": 9.213549046993584e-06, "loss": 0.3838, "step": 221110 }, { "epoch": 1.3143831992914503, "grad_norm": 5.690393924713135, "learning_rate": 9.213437336229618e-06, "loss": 0.3901, "step": 221120 }, { "epoch": 1.3144426413681187, "grad_norm": 6.202353000640869, "learning_rate": 9.21332561820961e-06, "loss": 0.4071, "step": 221130 }, { "epoch": 1.3145020834447871, "grad_norm": 4.095022201538086, "learning_rate": 9.213213892933751e-06, "loss": 0.3574, "step": 221140 }, { "epoch": 1.3145615255214556, "grad_norm": 5.283877372741699, "learning_rate": 9.213102160402237e-06, "loss": 0.4076, "step": 221150 }, { "epoch": 1.314620967598124, "grad_norm": 5.402928829193115, "learning_rate": 9.212990420615256e-06, "loss": 0.4358, "step": 221160 }, { "epoch": 1.3146804096747924, "grad_norm": 5.861209869384766, "learning_rate": 9.212878673573005e-06, "loss": 0.3767, "step": 221170 }, { "epoch": 1.3147398517514608, "grad_norm": 5.393055438995361, "learning_rate": 9.212766919275674e-06, "loss": 0.3558, "step": 221180 }, { "epoch": 1.3147992938281292, "grad_norm": 6.0552449226379395, "learning_rate": 9.212655157723453e-06, "loss": 0.387, "step": 221190 }, { "epoch": 1.3148587359047976, "grad_norm": 6.1694746017456055, "learning_rate": 9.21254338891654e-06, "loss": 0.4062, "step": 221200 }, { "epoch": 1.314918177981466, "grad_norm": 4.757126808166504, "learning_rate": 9.212431612855122e-06, "loss": 0.347, "step": 221210 }, { "epoch": 1.3149776200581345, "grad_norm": 6.246779441833496, "learning_rate": 9.212319829539396e-06, "loss": 0.3729, "step": 221220 }, { "epoch": 1.3150370621348029, "grad_norm": 5.641655445098877, "learning_rate": 9.212208038969553e-06, "loss": 0.4366, "step": 221230 }, { "epoch": 1.315096504211471, "grad_norm": 5.522206783294678, "learning_rate": 9.212096241145784e-06, "loss": 0.4137, "step": 221240 }, { "epoch": 1.3151559462881395, "grad_norm": 6.492897033691406, "learning_rate": 9.211984436068284e-06, "loss": 0.4257, "step": 221250 }, { "epoch": 1.315215388364808, "grad_norm": 4.438814163208008, "learning_rate": 9.211872623737243e-06, "loss": 0.384, "step": 221260 }, { "epoch": 1.3152748304414763, "grad_norm": 5.331174373626709, "learning_rate": 9.211760804152856e-06, "loss": 0.4019, "step": 221270 }, { "epoch": 1.3153342725181447, "grad_norm": 5.363588333129883, "learning_rate": 9.211648977315313e-06, "loss": 0.3712, "step": 221280 }, { "epoch": 1.3153937145948131, "grad_norm": 6.599649429321289, "learning_rate": 9.211537143224809e-06, "loss": 0.4072, "step": 221290 }, { "epoch": 1.3154531566714815, "grad_norm": 5.242809772491455, "learning_rate": 9.211425301881536e-06, "loss": 0.4086, "step": 221300 }, { "epoch": 1.3155125987481497, "grad_norm": 4.977997779846191, "learning_rate": 9.211313453285684e-06, "loss": 0.3922, "step": 221310 }, { "epoch": 1.3155720408248182, "grad_norm": 4.023496150970459, "learning_rate": 9.21120159743745e-06, "loss": 0.3784, "step": 221320 }, { "epoch": 1.3156314829014866, "grad_norm": 4.302016258239746, "learning_rate": 9.211089734337023e-06, "loss": 0.3992, "step": 221330 }, { "epoch": 1.315690924978155, "grad_norm": 4.831821918487549, "learning_rate": 9.210977863984598e-06, "loss": 0.4073, "step": 221340 }, { "epoch": 1.3157503670548234, "grad_norm": 5.245952129364014, "learning_rate": 9.210865986380366e-06, "loss": 0.3981, "step": 221350 }, { "epoch": 1.3158098091314918, "grad_norm": 4.8226518630981445, "learning_rate": 9.210754101524521e-06, "loss": 0.3865, "step": 221360 }, { "epoch": 1.3158692512081602, "grad_norm": 4.116033554077148, "learning_rate": 9.210642209417254e-06, "loss": 0.3627, "step": 221370 }, { "epoch": 1.3159286932848286, "grad_norm": 4.671098709106445, "learning_rate": 9.21053031005876e-06, "loss": 0.375, "step": 221380 }, { "epoch": 1.315988135361497, "grad_norm": 5.837828159332275, "learning_rate": 9.210418403449228e-06, "loss": 0.4139, "step": 221390 }, { "epoch": 1.3160475774381655, "grad_norm": 5.62517786026001, "learning_rate": 9.210306489588855e-06, "loss": 0.4034, "step": 221400 }, { "epoch": 1.3161070195148339, "grad_norm": 6.277210235595703, "learning_rate": 9.210194568477833e-06, "loss": 0.4146, "step": 221410 }, { "epoch": 1.316166461591502, "grad_norm": 5.512338638305664, "learning_rate": 9.210082640116352e-06, "loss": 0.364, "step": 221420 }, { "epoch": 1.3162259036681705, "grad_norm": 4.856425762176514, "learning_rate": 9.209970704504607e-06, "loss": 0.3769, "step": 221430 }, { "epoch": 1.316285345744839, "grad_norm": 6.694306373596191, "learning_rate": 9.20985876164279e-06, "loss": 0.408, "step": 221440 }, { "epoch": 1.3163447878215073, "grad_norm": 5.968816757202148, "learning_rate": 9.209746811531093e-06, "loss": 0.419, "step": 221450 }, { "epoch": 1.3164042298981757, "grad_norm": 4.893836498260498, "learning_rate": 9.209634854169708e-06, "loss": 0.3667, "step": 221460 }, { "epoch": 1.3164636719748442, "grad_norm": 3.482351779937744, "learning_rate": 9.209522889558833e-06, "loss": 0.39, "step": 221470 }, { "epoch": 1.3165231140515126, "grad_norm": 4.7181830406188965, "learning_rate": 9.209410917698656e-06, "loss": 0.377, "step": 221480 }, { "epoch": 1.3165825561281808, "grad_norm": 5.041008472442627, "learning_rate": 9.209298938589372e-06, "loss": 0.4003, "step": 221490 }, { "epoch": 1.3166419982048492, "grad_norm": 5.9783525466918945, "learning_rate": 9.209186952231171e-06, "loss": 0.3724, "step": 221500 }, { "epoch": 1.3167014402815176, "grad_norm": 5.318465709686279, "learning_rate": 9.20907495862425e-06, "loss": 0.394, "step": 221510 }, { "epoch": 1.316760882358186, "grad_norm": 4.770479202270508, "learning_rate": 9.208962957768799e-06, "loss": 0.3688, "step": 221520 }, { "epoch": 1.3168203244348544, "grad_norm": 4.260910987854004, "learning_rate": 9.208850949665011e-06, "loss": 0.353, "step": 221530 }, { "epoch": 1.3168797665115228, "grad_norm": 5.890309810638428, "learning_rate": 9.20873893431308e-06, "loss": 0.4041, "step": 221540 }, { "epoch": 1.3169392085881912, "grad_norm": 4.336592674255371, "learning_rate": 9.208626911713198e-06, "loss": 0.3887, "step": 221550 }, { "epoch": 1.3169986506648597, "grad_norm": 5.331230163574219, "learning_rate": 9.208514881865558e-06, "loss": 0.3666, "step": 221560 }, { "epoch": 1.317058092741528, "grad_norm": 5.901906967163086, "learning_rate": 9.208402844770355e-06, "loss": 0.3561, "step": 221570 }, { "epoch": 1.3171175348181965, "grad_norm": 4.258291721343994, "learning_rate": 9.208290800427779e-06, "loss": 0.405, "step": 221580 }, { "epoch": 1.317176976894865, "grad_norm": 4.211429119110107, "learning_rate": 9.208178748838023e-06, "loss": 0.4113, "step": 221590 }, { "epoch": 1.3172364189715333, "grad_norm": 4.4944539070129395, "learning_rate": 9.208066690001283e-06, "loss": 0.4167, "step": 221600 }, { "epoch": 1.3172958610482015, "grad_norm": 6.004848003387451, "learning_rate": 9.207954623917748e-06, "loss": 0.3986, "step": 221610 }, { "epoch": 1.31735530312487, "grad_norm": 4.490540981292725, "learning_rate": 9.207842550587614e-06, "loss": 0.3716, "step": 221620 }, { "epoch": 1.3174147452015383, "grad_norm": 6.169543266296387, "learning_rate": 9.207730470011073e-06, "loss": 0.4106, "step": 221630 }, { "epoch": 1.3174741872782068, "grad_norm": 4.603091239929199, "learning_rate": 9.207618382188319e-06, "loss": 0.4173, "step": 221640 }, { "epoch": 1.3175336293548752, "grad_norm": 5.154919147491455, "learning_rate": 9.207506287119543e-06, "loss": 0.405, "step": 221650 }, { "epoch": 1.3175930714315436, "grad_norm": 5.936939716339111, "learning_rate": 9.20739418480494e-06, "loss": 0.3669, "step": 221660 }, { "epoch": 1.317652513508212, "grad_norm": 4.956131935119629, "learning_rate": 9.207282075244701e-06, "loss": 0.3611, "step": 221670 }, { "epoch": 1.3177119555848802, "grad_norm": 5.350559234619141, "learning_rate": 9.207169958439022e-06, "loss": 0.3774, "step": 221680 }, { "epoch": 1.3177713976615486, "grad_norm": 6.089832305908203, "learning_rate": 9.207057834388093e-06, "loss": 0.3892, "step": 221690 }, { "epoch": 1.317830839738217, "grad_norm": 6.130149841308594, "learning_rate": 9.206945703092108e-06, "loss": 0.349, "step": 221700 }, { "epoch": 1.3178902818148854, "grad_norm": 5.035712718963623, "learning_rate": 9.206833564551262e-06, "loss": 0.3733, "step": 221710 }, { "epoch": 1.3179497238915538, "grad_norm": 3.966301918029785, "learning_rate": 9.206721418765746e-06, "loss": 0.4197, "step": 221720 }, { "epoch": 1.3180091659682223, "grad_norm": 5.796477317810059, "learning_rate": 9.206609265735752e-06, "loss": 0.3982, "step": 221730 }, { "epoch": 1.3180686080448907, "grad_norm": 5.627789497375488, "learning_rate": 9.206497105461478e-06, "loss": 0.4164, "step": 221740 }, { "epoch": 1.318128050121559, "grad_norm": 3.8235201835632324, "learning_rate": 9.206384937943113e-06, "loss": 0.3974, "step": 221750 }, { "epoch": 1.3181874921982275, "grad_norm": 5.6551618576049805, "learning_rate": 9.20627276318085e-06, "loss": 0.4062, "step": 221760 }, { "epoch": 1.318246934274896, "grad_norm": 4.60787296295166, "learning_rate": 9.206160581174886e-06, "loss": 0.3763, "step": 221770 }, { "epoch": 1.3183063763515643, "grad_norm": 3.377614974975586, "learning_rate": 9.20604839192541e-06, "loss": 0.4201, "step": 221780 }, { "epoch": 1.3183658184282325, "grad_norm": 4.915871620178223, "learning_rate": 9.205936195432617e-06, "loss": 0.4012, "step": 221790 }, { "epoch": 1.318425260504901, "grad_norm": 5.740525245666504, "learning_rate": 9.205823991696698e-06, "loss": 0.3758, "step": 221800 }, { "epoch": 1.3184847025815694, "grad_norm": 4.685929775238037, "learning_rate": 9.205711780717851e-06, "loss": 0.3609, "step": 221810 }, { "epoch": 1.3185441446582378, "grad_norm": 5.75468111038208, "learning_rate": 9.205599562496265e-06, "loss": 0.3566, "step": 221820 }, { "epoch": 1.3186035867349062, "grad_norm": 4.2929205894470215, "learning_rate": 9.205487337032136e-06, "loss": 0.4221, "step": 221830 }, { "epoch": 1.3186630288115746, "grad_norm": 5.995182991027832, "learning_rate": 9.205375104325655e-06, "loss": 0.372, "step": 221840 }, { "epoch": 1.318722470888243, "grad_norm": 4.223078727722168, "learning_rate": 9.205262864377017e-06, "loss": 0.3909, "step": 221850 }, { "epoch": 1.3187819129649112, "grad_norm": 6.538289546966553, "learning_rate": 9.205150617186413e-06, "loss": 0.405, "step": 221860 }, { "epoch": 1.3188413550415796, "grad_norm": 4.10338020324707, "learning_rate": 9.205038362754041e-06, "loss": 0.3468, "step": 221870 }, { "epoch": 1.318900797118248, "grad_norm": 5.532823085784912, "learning_rate": 9.204926101080089e-06, "loss": 0.3787, "step": 221880 }, { "epoch": 1.3189602391949165, "grad_norm": 4.1775803565979, "learning_rate": 9.204813832164752e-06, "loss": 0.3851, "step": 221890 }, { "epoch": 1.3190196812715849, "grad_norm": 4.971224308013916, "learning_rate": 9.204701556008225e-06, "loss": 0.4115, "step": 221900 }, { "epoch": 1.3190791233482533, "grad_norm": 6.082062244415283, "learning_rate": 9.2045892726107e-06, "loss": 0.3926, "step": 221910 }, { "epoch": 1.3191385654249217, "grad_norm": 5.804149150848389, "learning_rate": 9.20447698197237e-06, "loss": 0.4089, "step": 221920 }, { "epoch": 1.31919800750159, "grad_norm": 5.924300670623779, "learning_rate": 9.20436468409343e-06, "loss": 0.3984, "step": 221930 }, { "epoch": 1.3192574495782585, "grad_norm": 3.874455213546753, "learning_rate": 9.204252378974072e-06, "loss": 0.3875, "step": 221940 }, { "epoch": 1.319316891654927, "grad_norm": 7.61196231842041, "learning_rate": 9.20414006661449e-06, "loss": 0.3894, "step": 221950 }, { "epoch": 1.3193763337315954, "grad_norm": 5.158316135406494, "learning_rate": 9.204027747014876e-06, "loss": 0.4027, "step": 221960 }, { "epoch": 1.3194357758082638, "grad_norm": 4.580839157104492, "learning_rate": 9.203915420175426e-06, "loss": 0.3782, "step": 221970 }, { "epoch": 1.319495217884932, "grad_norm": 5.331738471984863, "learning_rate": 9.203803086096332e-06, "loss": 0.4014, "step": 221980 }, { "epoch": 1.3195546599616004, "grad_norm": 6.309868812561035, "learning_rate": 9.203690744777787e-06, "loss": 0.3581, "step": 221990 }, { "epoch": 1.3196141020382688, "grad_norm": 4.681944370269775, "learning_rate": 9.203578396219984e-06, "loss": 0.3754, "step": 222000 }, { "epoch": 1.3196735441149372, "grad_norm": 3.9853575229644775, "learning_rate": 9.203466040423119e-06, "loss": 0.3603, "step": 222010 }, { "epoch": 1.3197329861916056, "grad_norm": 5.331529140472412, "learning_rate": 9.203353677387383e-06, "loss": 0.4066, "step": 222020 }, { "epoch": 1.319792428268274, "grad_norm": 5.572680950164795, "learning_rate": 9.203241307112972e-06, "loss": 0.3466, "step": 222030 }, { "epoch": 1.3198518703449424, "grad_norm": 5.521311283111572, "learning_rate": 9.203128929600074e-06, "loss": 0.3991, "step": 222040 }, { "epoch": 1.3199113124216106, "grad_norm": 5.880692481994629, "learning_rate": 9.20301654484889e-06, "loss": 0.3876, "step": 222050 }, { "epoch": 1.319970754498279, "grad_norm": 5.264321804046631, "learning_rate": 9.20290415285961e-06, "loss": 0.3642, "step": 222060 }, { "epoch": 1.3200301965749475, "grad_norm": 6.645962238311768, "learning_rate": 9.202791753632425e-06, "loss": 0.4039, "step": 222070 }, { "epoch": 1.3200896386516159, "grad_norm": 4.855038166046143, "learning_rate": 9.202679347167534e-06, "loss": 0.3622, "step": 222080 }, { "epoch": 1.3201490807282843, "grad_norm": 5.756795883178711, "learning_rate": 9.202566933465127e-06, "loss": 0.383, "step": 222090 }, { "epoch": 1.3202085228049527, "grad_norm": 4.166719436645508, "learning_rate": 9.202454512525397e-06, "loss": 0.3477, "step": 222100 }, { "epoch": 1.3202679648816211, "grad_norm": 7.278448104858398, "learning_rate": 9.20234208434854e-06, "loss": 0.4133, "step": 222110 }, { "epoch": 1.3203274069582895, "grad_norm": 3.843167781829834, "learning_rate": 9.202229648934749e-06, "loss": 0.3735, "step": 222120 }, { "epoch": 1.320386849034958, "grad_norm": 5.485041618347168, "learning_rate": 9.202117206284216e-06, "loss": 0.3533, "step": 222130 }, { "epoch": 1.3204462911116264, "grad_norm": 6.5464653968811035, "learning_rate": 9.202004756397136e-06, "loss": 0.4089, "step": 222140 }, { "epoch": 1.3205057331882948, "grad_norm": 4.676297187805176, "learning_rate": 9.201892299273702e-06, "loss": 0.3829, "step": 222150 }, { "epoch": 1.320565175264963, "grad_norm": 4.416945457458496, "learning_rate": 9.201779834914108e-06, "loss": 0.3645, "step": 222160 }, { "epoch": 1.3206246173416314, "grad_norm": 3.987142562866211, "learning_rate": 9.201667363318549e-06, "loss": 0.3231, "step": 222170 }, { "epoch": 1.3206840594182998, "grad_norm": 4.77487850189209, "learning_rate": 9.201554884487219e-06, "loss": 0.3829, "step": 222180 }, { "epoch": 1.3207435014949682, "grad_norm": 5.368893146514893, "learning_rate": 9.201442398420307e-06, "loss": 0.3997, "step": 222190 }, { "epoch": 1.3208029435716366, "grad_norm": 5.128037452697754, "learning_rate": 9.20132990511801e-06, "loss": 0.3858, "step": 222200 }, { "epoch": 1.320862385648305, "grad_norm": 4.649110317230225, "learning_rate": 9.201217404580524e-06, "loss": 0.362, "step": 222210 }, { "epoch": 1.3209218277249735, "grad_norm": 5.2179694175720215, "learning_rate": 9.201104896808037e-06, "loss": 0.3722, "step": 222220 }, { "epoch": 1.3209812698016417, "grad_norm": 5.334902763366699, "learning_rate": 9.200992381800748e-06, "loss": 0.3724, "step": 222230 }, { "epoch": 1.32104071187831, "grad_norm": 4.164458274841309, "learning_rate": 9.20087985955885e-06, "loss": 0.3571, "step": 222240 }, { "epoch": 1.3211001539549785, "grad_norm": 5.111573219299316, "learning_rate": 9.200767330082534e-06, "loss": 0.386, "step": 222250 }, { "epoch": 1.321159596031647, "grad_norm": 6.818265438079834, "learning_rate": 9.200654793371996e-06, "loss": 0.4317, "step": 222260 }, { "epoch": 1.3212190381083153, "grad_norm": 5.954360485076904, "learning_rate": 9.20054224942743e-06, "loss": 0.4136, "step": 222270 }, { "epoch": 1.3212784801849837, "grad_norm": 5.7729692459106445, "learning_rate": 9.200429698249029e-06, "loss": 0.3918, "step": 222280 }, { "epoch": 1.3213379222616521, "grad_norm": 4.753907680511475, "learning_rate": 9.200317139836985e-06, "loss": 0.4011, "step": 222290 }, { "epoch": 1.3213973643383206, "grad_norm": 5.623127460479736, "learning_rate": 9.200204574191495e-06, "loss": 0.3787, "step": 222300 }, { "epoch": 1.321456806414989, "grad_norm": 4.477180480957031, "learning_rate": 9.200092001312752e-06, "loss": 0.3763, "step": 222310 }, { "epoch": 1.3215162484916574, "grad_norm": 5.050816059112549, "learning_rate": 9.199979421200949e-06, "loss": 0.3524, "step": 222320 }, { "epoch": 1.3215756905683258, "grad_norm": 4.593960762023926, "learning_rate": 9.19986683385628e-06, "loss": 0.3888, "step": 222330 }, { "epoch": 1.3216351326449942, "grad_norm": 3.2630724906921387, "learning_rate": 9.199754239278939e-06, "loss": 0.3502, "step": 222340 }, { "epoch": 1.3216945747216624, "grad_norm": 5.919381618499756, "learning_rate": 9.19964163746912e-06, "loss": 0.3847, "step": 222350 }, { "epoch": 1.3217540167983308, "grad_norm": 6.379737377166748, "learning_rate": 9.199529028427019e-06, "loss": 0.4298, "step": 222360 }, { "epoch": 1.3218134588749992, "grad_norm": 5.774291515350342, "learning_rate": 9.199416412152824e-06, "loss": 0.3902, "step": 222370 }, { "epoch": 1.3218729009516677, "grad_norm": 4.753879547119141, "learning_rate": 9.199303788646736e-06, "loss": 0.3832, "step": 222380 }, { "epoch": 1.321932343028336, "grad_norm": 5.520394325256348, "learning_rate": 9.199191157908946e-06, "loss": 0.3985, "step": 222390 }, { "epoch": 1.3219917851050045, "grad_norm": 5.088593006134033, "learning_rate": 9.199078519939646e-06, "loss": 0.3872, "step": 222400 }, { "epoch": 1.322051227181673, "grad_norm": 6.018418788909912, "learning_rate": 9.198965874739031e-06, "loss": 0.3778, "step": 222410 }, { "epoch": 1.322110669258341, "grad_norm": 5.357217788696289, "learning_rate": 9.1988532223073e-06, "loss": 0.4071, "step": 222420 }, { "epoch": 1.3221701113350095, "grad_norm": 4.464254856109619, "learning_rate": 9.198740562644639e-06, "loss": 0.4093, "step": 222430 }, { "epoch": 1.322229553411678, "grad_norm": 4.2403974533081055, "learning_rate": 9.198627895751246e-06, "loss": 0.4027, "step": 222440 }, { "epoch": 1.3222889954883463, "grad_norm": 5.997260570526123, "learning_rate": 9.198515221627317e-06, "loss": 0.4063, "step": 222450 }, { "epoch": 1.3223484375650147, "grad_norm": 4.415696620941162, "learning_rate": 9.198402540273042e-06, "loss": 0.3617, "step": 222460 }, { "epoch": 1.3224078796416832, "grad_norm": 5.132955551147461, "learning_rate": 9.198289851688618e-06, "loss": 0.3763, "step": 222470 }, { "epoch": 1.3224673217183516, "grad_norm": 5.790048122406006, "learning_rate": 9.198177155874237e-06, "loss": 0.4138, "step": 222480 }, { "epoch": 1.32252676379502, "grad_norm": 4.244265079498291, "learning_rate": 9.198064452830094e-06, "loss": 0.3628, "step": 222490 }, { "epoch": 1.3225862058716884, "grad_norm": 4.309670925140381, "learning_rate": 9.197951742556383e-06, "loss": 0.4005, "step": 222500 }, { "epoch": 1.3226456479483568, "grad_norm": 5.2140069007873535, "learning_rate": 9.197839025053299e-06, "loss": 0.3501, "step": 222510 }, { "epoch": 1.3227050900250252, "grad_norm": 5.9799346923828125, "learning_rate": 9.197726300321037e-06, "loss": 0.4266, "step": 222520 }, { "epoch": 1.3227645321016934, "grad_norm": 5.015195846557617, "learning_rate": 9.197613568359787e-06, "loss": 0.4027, "step": 222530 }, { "epoch": 1.3228239741783618, "grad_norm": 5.6563944816589355, "learning_rate": 9.197500829169745e-06, "loss": 0.3912, "step": 222540 }, { "epoch": 1.3228834162550303, "grad_norm": 4.313802242279053, "learning_rate": 9.197388082751106e-06, "loss": 0.3858, "step": 222550 }, { "epoch": 1.3229428583316987, "grad_norm": 6.325006484985352, "learning_rate": 9.197275329104065e-06, "loss": 0.4082, "step": 222560 }, { "epoch": 1.323002300408367, "grad_norm": 3.848909616470337, "learning_rate": 9.197162568228815e-06, "loss": 0.3541, "step": 222570 }, { "epoch": 1.3230617424850355, "grad_norm": 6.145546913146973, "learning_rate": 9.197049800125551e-06, "loss": 0.398, "step": 222580 }, { "epoch": 1.323121184561704, "grad_norm": 5.312529563903809, "learning_rate": 9.196937024794465e-06, "loss": 0.3668, "step": 222590 }, { "epoch": 1.323180626638372, "grad_norm": 4.201168060302734, "learning_rate": 9.196824242235753e-06, "loss": 0.3695, "step": 222600 }, { "epoch": 1.3232400687150405, "grad_norm": 5.555853366851807, "learning_rate": 9.19671145244961e-06, "loss": 0.3595, "step": 222610 }, { "epoch": 1.323299510791709, "grad_norm": 4.687233924865723, "learning_rate": 9.196598655436226e-06, "loss": 0.3477, "step": 222620 }, { "epoch": 1.3233589528683773, "grad_norm": 4.916604042053223, "learning_rate": 9.196485851195802e-06, "loss": 0.4149, "step": 222630 }, { "epoch": 1.3234183949450458, "grad_norm": 4.543025016784668, "learning_rate": 9.196373039728527e-06, "loss": 0.3889, "step": 222640 }, { "epoch": 1.3234778370217142, "grad_norm": 4.790781497955322, "learning_rate": 9.196260221034597e-06, "loss": 0.4407, "step": 222650 }, { "epoch": 1.3235372790983826, "grad_norm": 6.4880523681640625, "learning_rate": 9.196147395114205e-06, "loss": 0.4033, "step": 222660 }, { "epoch": 1.323596721175051, "grad_norm": 7.504624843597412, "learning_rate": 9.196034561967549e-06, "loss": 0.4176, "step": 222670 }, { "epoch": 1.3236561632517194, "grad_norm": 4.833093643188477, "learning_rate": 9.195921721594819e-06, "loss": 0.3835, "step": 222680 }, { "epoch": 1.3237156053283878, "grad_norm": 3.19411563873291, "learning_rate": 9.195808873996213e-06, "loss": 0.374, "step": 222690 }, { "epoch": 1.3237750474050562, "grad_norm": 6.740845680236816, "learning_rate": 9.195696019171921e-06, "loss": 0.4199, "step": 222700 }, { "epoch": 1.3238344894817247, "grad_norm": 4.822772979736328, "learning_rate": 9.195583157122142e-06, "loss": 0.4083, "step": 222710 }, { "epoch": 1.3238939315583929, "grad_norm": 6.293362140655518, "learning_rate": 9.195470287847067e-06, "loss": 0.378, "step": 222720 }, { "epoch": 1.3239533736350613, "grad_norm": 5.344241619110107, "learning_rate": 9.195357411346893e-06, "loss": 0.3851, "step": 222730 }, { "epoch": 1.3240128157117297, "grad_norm": 5.0776472091674805, "learning_rate": 9.19524452762181e-06, "loss": 0.3914, "step": 222740 }, { "epoch": 1.324072257788398, "grad_norm": 4.490881443023682, "learning_rate": 9.195131636672018e-06, "loss": 0.4228, "step": 222750 }, { "epoch": 1.3241316998650665, "grad_norm": 4.420971393585205, "learning_rate": 9.195018738497708e-06, "loss": 0.3944, "step": 222760 }, { "epoch": 1.324191141941735, "grad_norm": 4.190263271331787, "learning_rate": 9.194905833099075e-06, "loss": 0.3769, "step": 222770 }, { "epoch": 1.3242505840184033, "grad_norm": 6.335081577301025, "learning_rate": 9.194792920476315e-06, "loss": 0.4343, "step": 222780 }, { "epoch": 1.3243100260950715, "grad_norm": 4.463169097900391, "learning_rate": 9.194680000629619e-06, "loss": 0.3551, "step": 222790 }, { "epoch": 1.32436946817174, "grad_norm": 4.926708698272705, "learning_rate": 9.194567073559184e-06, "loss": 0.3824, "step": 222800 }, { "epoch": 1.3244289102484084, "grad_norm": 4.699770450592041, "learning_rate": 9.194454139265204e-06, "loss": 0.4097, "step": 222810 }, { "epoch": 1.3244883523250768, "grad_norm": 7.549728870391846, "learning_rate": 9.194341197747873e-06, "loss": 0.3631, "step": 222820 }, { "epoch": 1.3245477944017452, "grad_norm": 5.553009033203125, "learning_rate": 9.194228249007389e-06, "loss": 0.3843, "step": 222830 }, { "epoch": 1.3246072364784136, "grad_norm": 4.938045024871826, "learning_rate": 9.19411529304394e-06, "loss": 0.337, "step": 222840 }, { "epoch": 1.324666678555082, "grad_norm": 4.848514556884766, "learning_rate": 9.194002329857726e-06, "loss": 0.4078, "step": 222850 }, { "epoch": 1.3247261206317504, "grad_norm": 4.935560703277588, "learning_rate": 9.19388935944894e-06, "loss": 0.3846, "step": 222860 }, { "epoch": 1.3247855627084189, "grad_norm": 4.552617073059082, "learning_rate": 9.193776381817774e-06, "loss": 0.3637, "step": 222870 }, { "epoch": 1.3248450047850873, "grad_norm": 5.110508441925049, "learning_rate": 9.193663396964425e-06, "loss": 0.381, "step": 222880 }, { "epoch": 1.3249044468617557, "grad_norm": 4.9485063552856445, "learning_rate": 9.193550404889089e-06, "loss": 0.3927, "step": 222890 }, { "epoch": 1.3249638889384239, "grad_norm": 4.279695987701416, "learning_rate": 9.193437405591959e-06, "loss": 0.389, "step": 222900 }, { "epoch": 1.3250233310150923, "grad_norm": 4.213424205780029, "learning_rate": 9.193324399073227e-06, "loss": 0.3454, "step": 222910 }, { "epoch": 1.3250827730917607, "grad_norm": 4.192724704742432, "learning_rate": 9.193211385333091e-06, "loss": 0.3401, "step": 222920 }, { "epoch": 1.3251422151684291, "grad_norm": 6.576266288757324, "learning_rate": 9.193098364371746e-06, "loss": 0.4027, "step": 222930 }, { "epoch": 1.3252016572450975, "grad_norm": 5.342761039733887, "learning_rate": 9.192985336189383e-06, "loss": 0.4025, "step": 222940 }, { "epoch": 1.325261099321766, "grad_norm": 6.7937140464782715, "learning_rate": 9.1928723007862e-06, "loss": 0.3712, "step": 222950 }, { "epoch": 1.3253205413984344, "grad_norm": 5.44115686416626, "learning_rate": 9.192759258162392e-06, "loss": 0.3766, "step": 222960 }, { "epoch": 1.3253799834751026, "grad_norm": 4.330860614776611, "learning_rate": 9.192646208318151e-06, "loss": 0.352, "step": 222970 }, { "epoch": 1.325439425551771, "grad_norm": 4.999512195587158, "learning_rate": 9.192533151253673e-06, "loss": 0.4371, "step": 222980 }, { "epoch": 1.3254988676284394, "grad_norm": 5.409399509429932, "learning_rate": 9.192420086969154e-06, "loss": 0.3874, "step": 222990 }, { "epoch": 1.3255583097051078, "grad_norm": 6.754721641540527, "learning_rate": 9.192307015464785e-06, "loss": 0.4082, "step": 223000 }, { "epoch": 1.3256177517817762, "grad_norm": 5.275491714477539, "learning_rate": 9.192193936740764e-06, "loss": 0.3932, "step": 223010 }, { "epoch": 1.3256771938584446, "grad_norm": 3.950173854827881, "learning_rate": 9.192080850797285e-06, "loss": 0.4073, "step": 223020 }, { "epoch": 1.325736635935113, "grad_norm": 4.311515808105469, "learning_rate": 9.191967757634543e-06, "loss": 0.4347, "step": 223030 }, { "epoch": 1.3257960780117815, "grad_norm": 5.126163959503174, "learning_rate": 9.191854657252732e-06, "loss": 0.4397, "step": 223040 }, { "epoch": 1.3258555200884499, "grad_norm": 5.74686861038208, "learning_rate": 9.191741549652047e-06, "loss": 0.3737, "step": 223050 }, { "epoch": 1.3259149621651183, "grad_norm": 4.705180644989014, "learning_rate": 9.191628434832683e-06, "loss": 0.3548, "step": 223060 }, { "epoch": 1.3259744042417867, "grad_norm": 7.57402229309082, "learning_rate": 9.191515312794837e-06, "loss": 0.3645, "step": 223070 }, { "epoch": 1.3260338463184551, "grad_norm": 3.4960079193115234, "learning_rate": 9.191402183538697e-06, "loss": 0.3648, "step": 223080 }, { "epoch": 1.3260932883951233, "grad_norm": 4.525182247161865, "learning_rate": 9.191289047064465e-06, "loss": 0.3734, "step": 223090 }, { "epoch": 1.3261527304717917, "grad_norm": 4.71110725402832, "learning_rate": 9.191175903372333e-06, "loss": 0.3679, "step": 223100 }, { "epoch": 1.3262121725484601, "grad_norm": 5.604613780975342, "learning_rate": 9.191062752462496e-06, "loss": 0.3667, "step": 223110 }, { "epoch": 1.3262716146251285, "grad_norm": 3.738142967224121, "learning_rate": 9.19094959433515e-06, "loss": 0.3621, "step": 223120 }, { "epoch": 1.326331056701797, "grad_norm": 6.601992607116699, "learning_rate": 9.190836428990485e-06, "loss": 0.3744, "step": 223130 }, { "epoch": 1.3263904987784654, "grad_norm": 5.693269729614258, "learning_rate": 9.190723256428702e-06, "loss": 0.3746, "step": 223140 }, { "epoch": 1.3264499408551338, "grad_norm": 6.421031475067139, "learning_rate": 9.190610076649996e-06, "loss": 0.3918, "step": 223150 }, { "epoch": 1.326509382931802, "grad_norm": 6.0375823974609375, "learning_rate": 9.190496889654556e-06, "loss": 0.3584, "step": 223160 }, { "epoch": 1.3265688250084704, "grad_norm": 5.094666481018066, "learning_rate": 9.190383695442582e-06, "loss": 0.3713, "step": 223170 }, { "epoch": 1.3266282670851388, "grad_norm": 4.973586082458496, "learning_rate": 9.190270494014266e-06, "loss": 0.3843, "step": 223180 }, { "epoch": 1.3266877091618072, "grad_norm": 4.9791412353515625, "learning_rate": 9.190157285369806e-06, "loss": 0.3417, "step": 223190 }, { "epoch": 1.3267471512384756, "grad_norm": 3.8197598457336426, "learning_rate": 9.190044069509393e-06, "loss": 0.3921, "step": 223200 }, { "epoch": 1.326806593315144, "grad_norm": 4.280013084411621, "learning_rate": 9.189930846433224e-06, "loss": 0.4019, "step": 223210 }, { "epoch": 1.3268660353918125, "grad_norm": 5.511407375335693, "learning_rate": 9.189817616141496e-06, "loss": 0.411, "step": 223220 }, { "epoch": 1.3269254774684809, "grad_norm": 4.892280101776123, "learning_rate": 9.189704378634402e-06, "loss": 0.3685, "step": 223230 }, { "epoch": 1.3269849195451493, "grad_norm": 4.695044994354248, "learning_rate": 9.189591133912138e-06, "loss": 0.4024, "step": 223240 }, { "epoch": 1.3270443616218177, "grad_norm": 6.743942737579346, "learning_rate": 9.189477881974896e-06, "loss": 0.3974, "step": 223250 }, { "epoch": 1.3271038036984861, "grad_norm": 4.7977190017700195, "learning_rate": 9.189364622822874e-06, "loss": 0.4202, "step": 223260 }, { "epoch": 1.3271632457751543, "grad_norm": 4.013365268707275, "learning_rate": 9.189251356456267e-06, "loss": 0.3856, "step": 223270 }, { "epoch": 1.3272226878518227, "grad_norm": 5.630587100982666, "learning_rate": 9.189138082875268e-06, "loss": 0.3324, "step": 223280 }, { "epoch": 1.3272821299284912, "grad_norm": 4.404409408569336, "learning_rate": 9.189024802080074e-06, "loss": 0.3624, "step": 223290 }, { "epoch": 1.3273415720051596, "grad_norm": 5.548140048980713, "learning_rate": 9.18891151407088e-06, "loss": 0.3887, "step": 223300 }, { "epoch": 1.327401014081828, "grad_norm": 6.429224491119385, "learning_rate": 9.18879821884788e-06, "loss": 0.3705, "step": 223310 }, { "epoch": 1.3274604561584964, "grad_norm": 5.755197048187256, "learning_rate": 9.188684916411268e-06, "loss": 0.338, "step": 223320 }, { "epoch": 1.3275198982351648, "grad_norm": 5.409450531005859, "learning_rate": 9.188571606761243e-06, "loss": 0.3555, "step": 223330 }, { "epoch": 1.327579340311833, "grad_norm": 5.348448276519775, "learning_rate": 9.188458289897997e-06, "loss": 0.3471, "step": 223340 }, { "epoch": 1.3276387823885014, "grad_norm": 6.003054618835449, "learning_rate": 9.188344965821727e-06, "loss": 0.3958, "step": 223350 }, { "epoch": 1.3276982244651698, "grad_norm": 5.272902011871338, "learning_rate": 9.188231634532628e-06, "loss": 0.3689, "step": 223360 }, { "epoch": 1.3277576665418382, "grad_norm": 4.621282577514648, "learning_rate": 9.188118296030892e-06, "loss": 0.3526, "step": 223370 }, { "epoch": 1.3278171086185067, "grad_norm": 6.054479598999023, "learning_rate": 9.188004950316718e-06, "loss": 0.4141, "step": 223380 }, { "epoch": 1.327876550695175, "grad_norm": 3.301079511642456, "learning_rate": 9.187891597390299e-06, "loss": 0.3339, "step": 223390 }, { "epoch": 1.3279359927718435, "grad_norm": 5.281944274902344, "learning_rate": 9.187778237251831e-06, "loss": 0.4259, "step": 223400 }, { "epoch": 1.327995434848512, "grad_norm": 6.1894707679748535, "learning_rate": 9.187664869901509e-06, "loss": 0.3776, "step": 223410 }, { "epoch": 1.3280548769251803, "grad_norm": 4.602908611297607, "learning_rate": 9.187551495339529e-06, "loss": 0.3403, "step": 223420 }, { "epoch": 1.3281143190018487, "grad_norm": 6.176238536834717, "learning_rate": 9.187438113566087e-06, "loss": 0.3756, "step": 223430 }, { "epoch": 1.3281737610785171, "grad_norm": 4.250999450683594, "learning_rate": 9.187324724581375e-06, "loss": 0.3851, "step": 223440 }, { "epoch": 1.3282332031551856, "grad_norm": 5.835953712463379, "learning_rate": 9.187211328385591e-06, "loss": 0.3779, "step": 223450 }, { "epoch": 1.3282926452318538, "grad_norm": 6.794545650482178, "learning_rate": 9.187097924978929e-06, "loss": 0.4091, "step": 223460 }, { "epoch": 1.3283520873085222, "grad_norm": 5.458734512329102, "learning_rate": 9.186984514361585e-06, "loss": 0.3768, "step": 223470 }, { "epoch": 1.3284115293851906, "grad_norm": 4.084803104400635, "learning_rate": 9.186871096533754e-06, "loss": 0.3974, "step": 223480 }, { "epoch": 1.328470971461859, "grad_norm": 5.632932662963867, "learning_rate": 9.186757671495632e-06, "loss": 0.3811, "step": 223490 }, { "epoch": 1.3285304135385274, "grad_norm": 6.427992343902588, "learning_rate": 9.186644239247414e-06, "loss": 0.383, "step": 223500 }, { "epoch": 1.3285898556151958, "grad_norm": 5.082912921905518, "learning_rate": 9.186530799789295e-06, "loss": 0.3468, "step": 223510 }, { "epoch": 1.3286492976918642, "grad_norm": 7.012707710266113, "learning_rate": 9.186417353121468e-06, "loss": 0.3986, "step": 223520 }, { "epoch": 1.3287087397685324, "grad_norm": 7.328822612762451, "learning_rate": 9.186303899244133e-06, "loss": 0.3868, "step": 223530 }, { "epoch": 1.3287681818452008, "grad_norm": 5.295263767242432, "learning_rate": 9.186190438157483e-06, "loss": 0.3842, "step": 223540 }, { "epoch": 1.3288276239218693, "grad_norm": 5.450290203094482, "learning_rate": 9.186076969861714e-06, "loss": 0.3971, "step": 223550 }, { "epoch": 1.3288870659985377, "grad_norm": 4.693726062774658, "learning_rate": 9.185963494357019e-06, "loss": 0.3617, "step": 223560 }, { "epoch": 1.328946508075206, "grad_norm": 4.240846157073975, "learning_rate": 9.185850011643597e-06, "loss": 0.373, "step": 223570 }, { "epoch": 1.3290059501518745, "grad_norm": 4.950621604919434, "learning_rate": 9.185736521721642e-06, "loss": 0.3524, "step": 223580 }, { "epoch": 1.329065392228543, "grad_norm": 5.357747554779053, "learning_rate": 9.185623024591349e-06, "loss": 0.381, "step": 223590 }, { "epoch": 1.3291248343052113, "grad_norm": 6.978742599487305, "learning_rate": 9.185509520252913e-06, "loss": 0.3723, "step": 223600 }, { "epoch": 1.3291842763818797, "grad_norm": 6.165913105010986, "learning_rate": 9.18539600870653e-06, "loss": 0.4004, "step": 223610 }, { "epoch": 1.3292437184585482, "grad_norm": 5.946145534515381, "learning_rate": 9.185282489952399e-06, "loss": 0.3906, "step": 223620 }, { "epoch": 1.3293031605352166, "grad_norm": 4.727291584014893, "learning_rate": 9.18516896399071e-06, "loss": 0.3657, "step": 223630 }, { "epoch": 1.3293626026118848, "grad_norm": 5.748874187469482, "learning_rate": 9.185055430821658e-06, "loss": 0.3705, "step": 223640 }, { "epoch": 1.3294220446885532, "grad_norm": 6.835817813873291, "learning_rate": 9.184941890445445e-06, "loss": 0.4353, "step": 223650 }, { "epoch": 1.3294814867652216, "grad_norm": 5.21348237991333, "learning_rate": 9.184828342862261e-06, "loss": 0.4021, "step": 223660 }, { "epoch": 1.32954092884189, "grad_norm": 4.439318656921387, "learning_rate": 9.184714788072304e-06, "loss": 0.3688, "step": 223670 }, { "epoch": 1.3296003709185584, "grad_norm": 6.2180280685424805, "learning_rate": 9.184601226075768e-06, "loss": 0.416, "step": 223680 }, { "epoch": 1.3296598129952268, "grad_norm": 5.907814979553223, "learning_rate": 9.184487656872849e-06, "loss": 0.378, "step": 223690 }, { "epoch": 1.3297192550718953, "grad_norm": 5.034913063049316, "learning_rate": 9.184374080463744e-06, "loss": 0.4028, "step": 223700 }, { "epoch": 1.3297786971485634, "grad_norm": 4.61821174621582, "learning_rate": 9.184260496848648e-06, "loss": 0.329, "step": 223710 }, { "epoch": 1.3298381392252319, "grad_norm": 6.297434329986572, "learning_rate": 9.184146906027755e-06, "loss": 0.3828, "step": 223720 }, { "epoch": 1.3298975813019003, "grad_norm": 4.219641208648682, "learning_rate": 9.184033308001262e-06, "loss": 0.368, "step": 223730 }, { "epoch": 1.3299570233785687, "grad_norm": 6.394946098327637, "learning_rate": 9.183919702769364e-06, "loss": 0.3708, "step": 223740 }, { "epoch": 1.330016465455237, "grad_norm": 4.23231840133667, "learning_rate": 9.183806090332259e-06, "loss": 0.4113, "step": 223750 }, { "epoch": 1.3300759075319055, "grad_norm": 5.4564313888549805, "learning_rate": 9.18369247069014e-06, "loss": 0.3502, "step": 223760 }, { "epoch": 1.330135349608574, "grad_norm": 5.06501579284668, "learning_rate": 9.183578843843202e-06, "loss": 0.3753, "step": 223770 }, { "epoch": 1.3301947916852424, "grad_norm": 4.976125717163086, "learning_rate": 9.183465209791642e-06, "loss": 0.3909, "step": 223780 }, { "epoch": 1.3302542337619108, "grad_norm": 4.587662696838379, "learning_rate": 9.183351568535657e-06, "loss": 0.3563, "step": 223790 }, { "epoch": 1.3303136758385792, "grad_norm": 4.962926864624023, "learning_rate": 9.183237920075441e-06, "loss": 0.404, "step": 223800 }, { "epoch": 1.3303731179152476, "grad_norm": 4.77548360824585, "learning_rate": 9.183124264411191e-06, "loss": 0.3766, "step": 223810 }, { "epoch": 1.330432559991916, "grad_norm": 5.949981212615967, "learning_rate": 9.183010601543101e-06, "loss": 0.4159, "step": 223820 }, { "epoch": 1.3304920020685842, "grad_norm": 6.185729026794434, "learning_rate": 9.182896931471369e-06, "loss": 0.3706, "step": 223830 }, { "epoch": 1.3305514441452526, "grad_norm": 4.186119556427002, "learning_rate": 9.182783254196186e-06, "loss": 0.3959, "step": 223840 }, { "epoch": 1.330610886221921, "grad_norm": 4.352588653564453, "learning_rate": 9.182669569717753e-06, "loss": 0.3592, "step": 223850 }, { "epoch": 1.3306703282985894, "grad_norm": 3.8925466537475586, "learning_rate": 9.182555878036265e-06, "loss": 0.3503, "step": 223860 }, { "epoch": 1.3307297703752579, "grad_norm": 5.340627670288086, "learning_rate": 9.182442179151916e-06, "loss": 0.4286, "step": 223870 }, { "epoch": 1.3307892124519263, "grad_norm": 5.183155536651611, "learning_rate": 9.182328473064903e-06, "loss": 0.4056, "step": 223880 }, { "epoch": 1.3308486545285947, "grad_norm": 5.555105209350586, "learning_rate": 9.18221475977542e-06, "loss": 0.3736, "step": 223890 }, { "epoch": 1.3309080966052629, "grad_norm": 5.14495849609375, "learning_rate": 9.182101039283664e-06, "loss": 0.3783, "step": 223900 }, { "epoch": 1.3309675386819313, "grad_norm": 4.205202102661133, "learning_rate": 9.181987311589832e-06, "loss": 0.3845, "step": 223910 }, { "epoch": 1.3310269807585997, "grad_norm": 6.595266342163086, "learning_rate": 9.18187357669412e-06, "loss": 0.3871, "step": 223920 }, { "epoch": 1.3310864228352681, "grad_norm": 4.574689865112305, "learning_rate": 9.181759834596722e-06, "loss": 0.3826, "step": 223930 }, { "epoch": 1.3311458649119365, "grad_norm": 4.2263407707214355, "learning_rate": 9.181646085297833e-06, "loss": 0.3361, "step": 223940 }, { "epoch": 1.331205306988605, "grad_norm": 5.487466335296631, "learning_rate": 9.181532328797652e-06, "loss": 0.3792, "step": 223950 }, { "epoch": 1.3312647490652734, "grad_norm": 3.770461320877075, "learning_rate": 9.181418565096373e-06, "loss": 0.3536, "step": 223960 }, { "epoch": 1.3313241911419418, "grad_norm": 5.281510353088379, "learning_rate": 9.181304794194192e-06, "loss": 0.4117, "step": 223970 }, { "epoch": 1.3313836332186102, "grad_norm": 7.164330959320068, "learning_rate": 9.181191016091307e-06, "loss": 0.3873, "step": 223980 }, { "epoch": 1.3314430752952786, "grad_norm": 4.680443286895752, "learning_rate": 9.18107723078791e-06, "loss": 0.3657, "step": 223990 }, { "epoch": 1.331502517371947, "grad_norm": 6.273386001586914, "learning_rate": 9.180963438284201e-06, "loss": 0.4299, "step": 224000 }, { "epoch": 1.3315619594486152, "grad_norm": 4.374436855316162, "learning_rate": 9.180849638580371e-06, "loss": 0.3866, "step": 224010 }, { "epoch": 1.3316214015252836, "grad_norm": 5.331665992736816, "learning_rate": 9.180735831676622e-06, "loss": 0.3655, "step": 224020 }, { "epoch": 1.331680843601952, "grad_norm": 5.77623987197876, "learning_rate": 9.180622017573147e-06, "loss": 0.4259, "step": 224030 }, { "epoch": 1.3317402856786205, "grad_norm": 3.3300321102142334, "learning_rate": 9.180508196270141e-06, "loss": 0.3579, "step": 224040 }, { "epoch": 1.3317997277552889, "grad_norm": 7.902667045593262, "learning_rate": 9.1803943677678e-06, "loss": 0.3825, "step": 224050 }, { "epoch": 1.3318591698319573, "grad_norm": 6.334039211273193, "learning_rate": 9.180280532066324e-06, "loss": 0.3763, "step": 224060 }, { "epoch": 1.3319186119086257, "grad_norm": 7.338493347167969, "learning_rate": 9.180166689165904e-06, "loss": 0.4144, "step": 224070 }, { "epoch": 1.331978053985294, "grad_norm": 5.024709224700928, "learning_rate": 9.180052839066737e-06, "loss": 0.3324, "step": 224080 }, { "epoch": 1.3320374960619623, "grad_norm": 5.018380641937256, "learning_rate": 9.179938981769024e-06, "loss": 0.3855, "step": 224090 }, { "epoch": 1.3320969381386307, "grad_norm": 4.465993404388428, "learning_rate": 9.179825117272955e-06, "loss": 0.372, "step": 224100 }, { "epoch": 1.3321563802152991, "grad_norm": 6.11495304107666, "learning_rate": 9.179711245578729e-06, "loss": 0.4332, "step": 224110 }, { "epoch": 1.3322158222919676, "grad_norm": 6.02025032043457, "learning_rate": 9.17959736668654e-06, "loss": 0.4101, "step": 224120 }, { "epoch": 1.332275264368636, "grad_norm": 6.172039985656738, "learning_rate": 9.179483480596587e-06, "loss": 0.3895, "step": 224130 }, { "epoch": 1.3323347064453044, "grad_norm": 6.2148590087890625, "learning_rate": 9.179369587309067e-06, "loss": 0.3883, "step": 224140 }, { "epoch": 1.3323941485219728, "grad_norm": 5.539519786834717, "learning_rate": 9.17925568682417e-06, "loss": 0.3805, "step": 224150 }, { "epoch": 1.3324535905986412, "grad_norm": 4.384332180023193, "learning_rate": 9.179141779142098e-06, "loss": 0.4088, "step": 224160 }, { "epoch": 1.3325130326753096, "grad_norm": 5.09623908996582, "learning_rate": 9.179027864263044e-06, "loss": 0.3862, "step": 224170 }, { "epoch": 1.332572474751978, "grad_norm": 4.067798137664795, "learning_rate": 9.178913942187207e-06, "loss": 0.3308, "step": 224180 }, { "epoch": 1.3326319168286465, "grad_norm": 5.265471935272217, "learning_rate": 9.17880001291478e-06, "loss": 0.4296, "step": 224190 }, { "epoch": 1.3326913589053146, "grad_norm": 4.105524063110352, "learning_rate": 9.178686076445961e-06, "loss": 0.3926, "step": 224200 }, { "epoch": 1.332750800981983, "grad_norm": 5.4520158767700195, "learning_rate": 9.178572132780948e-06, "loss": 0.3861, "step": 224210 }, { "epoch": 1.3328102430586515, "grad_norm": 3.668802499771118, "learning_rate": 9.178458181919933e-06, "loss": 0.4027, "step": 224220 }, { "epoch": 1.33286968513532, "grad_norm": 4.800638198852539, "learning_rate": 9.178344223863115e-06, "loss": 0.3545, "step": 224230 }, { "epoch": 1.3329291272119883, "grad_norm": 4.921010971069336, "learning_rate": 9.17823025861069e-06, "loss": 0.3582, "step": 224240 }, { "epoch": 1.3329885692886567, "grad_norm": 5.455257892608643, "learning_rate": 9.178116286162854e-06, "loss": 0.3849, "step": 224250 }, { "epoch": 1.3330480113653251, "grad_norm": 3.613753318786621, "learning_rate": 9.178002306519802e-06, "loss": 0.3268, "step": 224260 }, { "epoch": 1.3331074534419933, "grad_norm": 4.4715352058410645, "learning_rate": 9.177888319681733e-06, "loss": 0.4061, "step": 224270 }, { "epoch": 1.3331668955186617, "grad_norm": 4.479504585266113, "learning_rate": 9.177774325648841e-06, "loss": 0.3719, "step": 224280 }, { "epoch": 1.3332263375953302, "grad_norm": 6.086211204528809, "learning_rate": 9.177660324421324e-06, "loss": 0.343, "step": 224290 }, { "epoch": 1.3332857796719986, "grad_norm": 5.24068021774292, "learning_rate": 9.177546315999377e-06, "loss": 0.3813, "step": 224300 }, { "epoch": 1.333345221748667, "grad_norm": 6.1161980628967285, "learning_rate": 9.177432300383198e-06, "loss": 0.4489, "step": 224310 }, { "epoch": 1.3334046638253354, "grad_norm": 5.164342880249023, "learning_rate": 9.17731827757298e-06, "loss": 0.3647, "step": 224320 }, { "epoch": 1.3334641059020038, "grad_norm": 5.802142143249512, "learning_rate": 9.177204247568923e-06, "loss": 0.3706, "step": 224330 }, { "epoch": 1.3335235479786722, "grad_norm": 5.256405830383301, "learning_rate": 9.17709021037122e-06, "loss": 0.3919, "step": 224340 }, { "epoch": 1.3335829900553406, "grad_norm": 6.16420841217041, "learning_rate": 9.176976165980072e-06, "loss": 0.4209, "step": 224350 }, { "epoch": 1.333642432132009, "grad_norm": 4.350703716278076, "learning_rate": 9.17686211439567e-06, "loss": 0.357, "step": 224360 }, { "epoch": 1.3337018742086775, "grad_norm": 7.1526336669921875, "learning_rate": 9.176748055618214e-06, "loss": 0.398, "step": 224370 }, { "epoch": 1.3337613162853457, "grad_norm": 8.754281997680664, "learning_rate": 9.176633989647901e-06, "loss": 0.4373, "step": 224380 }, { "epoch": 1.333820758362014, "grad_norm": 4.449162006378174, "learning_rate": 9.176519916484922e-06, "loss": 0.3905, "step": 224390 }, { "epoch": 1.3338802004386825, "grad_norm": 5.082187652587891, "learning_rate": 9.176405836129481e-06, "loss": 0.3437, "step": 224400 }, { "epoch": 1.333939642515351, "grad_norm": 4.431657314300537, "learning_rate": 9.17629174858177e-06, "loss": 0.3704, "step": 224410 }, { "epoch": 1.3339990845920193, "grad_norm": 5.7228474617004395, "learning_rate": 9.176177653841987e-06, "loss": 0.3755, "step": 224420 }, { "epoch": 1.3340585266686877, "grad_norm": 5.491061687469482, "learning_rate": 9.176063551910326e-06, "loss": 0.3479, "step": 224430 }, { "epoch": 1.3341179687453562, "grad_norm": 6.1053948402404785, "learning_rate": 9.175949442786987e-06, "loss": 0.3864, "step": 224440 }, { "epoch": 1.3341774108220243, "grad_norm": 4.73300838470459, "learning_rate": 9.175835326472165e-06, "loss": 0.3913, "step": 224450 }, { "epoch": 1.3342368528986928, "grad_norm": 5.75006628036499, "learning_rate": 9.175721202966055e-06, "loss": 0.3923, "step": 224460 }, { "epoch": 1.3342962949753612, "grad_norm": 4.493914604187012, "learning_rate": 9.175607072268854e-06, "loss": 0.3865, "step": 224470 }, { "epoch": 1.3343557370520296, "grad_norm": 5.8721418380737305, "learning_rate": 9.17549293438076e-06, "loss": 0.4113, "step": 224480 }, { "epoch": 1.334415179128698, "grad_norm": 5.000305652618408, "learning_rate": 9.17537878930197e-06, "loss": 0.3688, "step": 224490 }, { "epoch": 1.3344746212053664, "grad_norm": 6.376143932342529, "learning_rate": 9.17526463703268e-06, "loss": 0.3721, "step": 224500 }, { "epoch": 1.3345340632820348, "grad_norm": 6.612317085266113, "learning_rate": 9.175150477573084e-06, "loss": 0.3994, "step": 224510 }, { "epoch": 1.3345935053587032, "grad_norm": 5.248411655426025, "learning_rate": 9.175036310923382e-06, "loss": 0.3649, "step": 224520 }, { "epoch": 1.3346529474353717, "grad_norm": 4.265666484832764, "learning_rate": 9.174922137083771e-06, "loss": 0.3626, "step": 224530 }, { "epoch": 1.33471238951204, "grad_norm": 4.601926326751709, "learning_rate": 9.174807956054444e-06, "loss": 0.3593, "step": 224540 }, { "epoch": 1.3347718315887085, "grad_norm": 5.2574286460876465, "learning_rate": 9.174693767835598e-06, "loss": 0.3877, "step": 224550 }, { "epoch": 1.334831273665377, "grad_norm": 5.81861686706543, "learning_rate": 9.174579572427433e-06, "loss": 0.3772, "step": 224560 }, { "epoch": 1.334890715742045, "grad_norm": 6.364940643310547, "learning_rate": 9.174465369830144e-06, "loss": 0.393, "step": 224570 }, { "epoch": 1.3349501578187135, "grad_norm": 3.659339666366577, "learning_rate": 9.174351160043927e-06, "loss": 0.3855, "step": 224580 }, { "epoch": 1.335009599895382, "grad_norm": 3.8236865997314453, "learning_rate": 9.17423694306898e-06, "loss": 0.3834, "step": 224590 }, { "epoch": 1.3350690419720503, "grad_norm": 5.140856742858887, "learning_rate": 9.174122718905498e-06, "loss": 0.3776, "step": 224600 }, { "epoch": 1.3351284840487188, "grad_norm": 5.315720081329346, "learning_rate": 9.17400848755368e-06, "loss": 0.4213, "step": 224610 }, { "epoch": 1.3351879261253872, "grad_norm": 4.310149669647217, "learning_rate": 9.17389424901372e-06, "loss": 0.3562, "step": 224620 }, { "epoch": 1.3352473682020556, "grad_norm": 5.268435478210449, "learning_rate": 9.173780003285816e-06, "loss": 0.4138, "step": 224630 }, { "epoch": 1.3353068102787238, "grad_norm": 6.454239368438721, "learning_rate": 9.173665750370167e-06, "loss": 0.3515, "step": 224640 }, { "epoch": 1.3353662523553922, "grad_norm": 5.170239448547363, "learning_rate": 9.173551490266965e-06, "loss": 0.3583, "step": 224650 }, { "epoch": 1.3354256944320606, "grad_norm": 6.317379474639893, "learning_rate": 9.17343722297641e-06, "loss": 0.4139, "step": 224660 }, { "epoch": 1.335485136508729, "grad_norm": 4.439958572387695, "learning_rate": 9.173322948498698e-06, "loss": 0.4619, "step": 224670 }, { "epoch": 1.3355445785853974, "grad_norm": 4.13834285736084, "learning_rate": 9.173208666834025e-06, "loss": 0.3681, "step": 224680 }, { "epoch": 1.3356040206620658, "grad_norm": 4.447027206420898, "learning_rate": 9.173094377982592e-06, "loss": 0.4241, "step": 224690 }, { "epoch": 1.3356634627387343, "grad_norm": 5.244879245758057, "learning_rate": 9.17298008194459e-06, "loss": 0.3888, "step": 224700 }, { "epoch": 1.3357229048154027, "grad_norm": 4.445311546325684, "learning_rate": 9.172865778720219e-06, "loss": 0.3795, "step": 224710 }, { "epoch": 1.335782346892071, "grad_norm": 5.774088382720947, "learning_rate": 9.172751468309675e-06, "loss": 0.4031, "step": 224720 }, { "epoch": 1.3358417889687395, "grad_norm": 5.5914812088012695, "learning_rate": 9.172637150713156e-06, "loss": 0.3839, "step": 224730 }, { "epoch": 1.335901231045408, "grad_norm": 4.476009368896484, "learning_rate": 9.172522825930857e-06, "loss": 0.3723, "step": 224740 }, { "epoch": 1.3359606731220761, "grad_norm": 4.398732662200928, "learning_rate": 9.172408493962976e-06, "loss": 0.3852, "step": 224750 }, { "epoch": 1.3360201151987445, "grad_norm": 5.486022472381592, "learning_rate": 9.172294154809712e-06, "loss": 0.4123, "step": 224760 }, { "epoch": 1.336079557275413, "grad_norm": 4.488095760345459, "learning_rate": 9.172179808471255e-06, "loss": 0.4031, "step": 224770 }, { "epoch": 1.3361389993520814, "grad_norm": 4.874614238739014, "learning_rate": 9.172065454947809e-06, "loss": 0.3781, "step": 224780 }, { "epoch": 1.3361984414287498, "grad_norm": 4.1295857429504395, "learning_rate": 9.17195109423957e-06, "loss": 0.4113, "step": 224790 }, { "epoch": 1.3362578835054182, "grad_norm": 5.076277256011963, "learning_rate": 9.171836726346732e-06, "loss": 0.3579, "step": 224800 }, { "epoch": 1.3363173255820866, "grad_norm": 6.582302570343018, "learning_rate": 9.171722351269492e-06, "loss": 0.3945, "step": 224810 }, { "epoch": 1.3363767676587548, "grad_norm": 4.797580718994141, "learning_rate": 9.171607969008051e-06, "loss": 0.3376, "step": 224820 }, { "epoch": 1.3364362097354232, "grad_norm": 4.8144683837890625, "learning_rate": 9.171493579562602e-06, "loss": 0.3438, "step": 224830 }, { "epoch": 1.3364956518120916, "grad_norm": 4.160070419311523, "learning_rate": 9.171379182933344e-06, "loss": 0.4009, "step": 224840 }, { "epoch": 1.33655509388876, "grad_norm": 5.333456993103027, "learning_rate": 9.171264779120473e-06, "loss": 0.4067, "step": 224850 }, { "epoch": 1.3366145359654285, "grad_norm": 5.309295177459717, "learning_rate": 9.171150368124184e-06, "loss": 0.3927, "step": 224860 }, { "epoch": 1.3366739780420969, "grad_norm": 6.363593101501465, "learning_rate": 9.17103594994468e-06, "loss": 0.4043, "step": 224870 }, { "epoch": 1.3367334201187653, "grad_norm": 5.903320789337158, "learning_rate": 9.17092152458215e-06, "loss": 0.3953, "step": 224880 }, { "epoch": 1.3367928621954337, "grad_norm": 5.654779434204102, "learning_rate": 9.1708070920368e-06, "loss": 0.405, "step": 224890 }, { "epoch": 1.336852304272102, "grad_norm": 5.253203868865967, "learning_rate": 9.17069265230882e-06, "loss": 0.3881, "step": 224900 }, { "epoch": 1.3369117463487705, "grad_norm": 5.501282691955566, "learning_rate": 9.17057820539841e-06, "loss": 0.4168, "step": 224910 }, { "epoch": 1.336971188425439, "grad_norm": 5.9067888259887695, "learning_rate": 9.17046375130577e-06, "loss": 0.3767, "step": 224920 }, { "epoch": 1.3370306305021074, "grad_norm": 5.585583209991455, "learning_rate": 9.17034929003109e-06, "loss": 0.4019, "step": 224930 }, { "epoch": 1.3370900725787755, "grad_norm": 4.124727249145508, "learning_rate": 9.170234821574571e-06, "loss": 0.3506, "step": 224940 }, { "epoch": 1.337149514655444, "grad_norm": 4.168961524963379, "learning_rate": 9.170120345936411e-06, "loss": 0.3661, "step": 224950 }, { "epoch": 1.3372089567321124, "grad_norm": 3.76141357421875, "learning_rate": 9.170005863116806e-06, "loss": 0.4373, "step": 224960 }, { "epoch": 1.3372683988087808, "grad_norm": 5.695826053619385, "learning_rate": 9.169891373115954e-06, "loss": 0.3822, "step": 224970 }, { "epoch": 1.3373278408854492, "grad_norm": 4.664109706878662, "learning_rate": 9.169776875934051e-06, "loss": 0.3769, "step": 224980 }, { "epoch": 1.3373872829621176, "grad_norm": 4.660265922546387, "learning_rate": 9.169662371571295e-06, "loss": 0.3805, "step": 224990 }, { "epoch": 1.337446725038786, "grad_norm": 6.1602253913879395, "learning_rate": 9.169547860027882e-06, "loss": 0.3714, "step": 225000 }, { "epoch": 1.3375061671154542, "grad_norm": 5.321721076965332, "learning_rate": 9.16943334130401e-06, "loss": 0.4156, "step": 225010 }, { "epoch": 1.3375656091921226, "grad_norm": 5.51826810836792, "learning_rate": 9.169318815399876e-06, "loss": 0.4236, "step": 225020 }, { "epoch": 1.337625051268791, "grad_norm": 6.322381973266602, "learning_rate": 9.16920428231568e-06, "loss": 0.3736, "step": 225030 }, { "epoch": 1.3376844933454595, "grad_norm": 5.796841621398926, "learning_rate": 9.169089742051614e-06, "loss": 0.376, "step": 225040 }, { "epoch": 1.3377439354221279, "grad_norm": 4.50002384185791, "learning_rate": 9.168975194607881e-06, "loss": 0.382, "step": 225050 }, { "epoch": 1.3378033774987963, "grad_norm": 5.2910637855529785, "learning_rate": 9.168860639984673e-06, "loss": 0.411, "step": 225060 }, { "epoch": 1.3378628195754647, "grad_norm": 4.787912845611572, "learning_rate": 9.16874607818219e-06, "loss": 0.3708, "step": 225070 }, { "epoch": 1.3379222616521331, "grad_norm": 5.6931915283203125, "learning_rate": 9.16863150920063e-06, "loss": 0.3941, "step": 225080 }, { "epoch": 1.3379817037288015, "grad_norm": 5.864654541015625, "learning_rate": 9.168516933040187e-06, "loss": 0.3437, "step": 225090 }, { "epoch": 1.33804114580547, "grad_norm": 5.774521827697754, "learning_rate": 9.168402349701061e-06, "loss": 0.3523, "step": 225100 }, { "epoch": 1.3381005878821384, "grad_norm": 5.854369640350342, "learning_rate": 9.16828775918345e-06, "loss": 0.412, "step": 225110 }, { "epoch": 1.3381600299588066, "grad_norm": 3.706352472305298, "learning_rate": 9.168173161487549e-06, "loss": 0.3962, "step": 225120 }, { "epoch": 1.338219472035475, "grad_norm": 4.614429473876953, "learning_rate": 9.168058556613557e-06, "loss": 0.3455, "step": 225130 }, { "epoch": 1.3382789141121434, "grad_norm": 6.826141834259033, "learning_rate": 9.167943944561671e-06, "loss": 0.4025, "step": 225140 }, { "epoch": 1.3383383561888118, "grad_norm": 5.419859409332275, "learning_rate": 9.167829325332087e-06, "loss": 0.3999, "step": 225150 }, { "epoch": 1.3383977982654802, "grad_norm": 5.069563865661621, "learning_rate": 9.167714698925005e-06, "loss": 0.3891, "step": 225160 }, { "epoch": 1.3384572403421486, "grad_norm": 7.084824085235596, "learning_rate": 9.16760006534062e-06, "loss": 0.4382, "step": 225170 }, { "epoch": 1.338516682418817, "grad_norm": 4.987011432647705, "learning_rate": 9.167485424579133e-06, "loss": 0.3647, "step": 225180 }, { "epoch": 1.3385761244954852, "grad_norm": 6.527477741241455, "learning_rate": 9.167370776640736e-06, "loss": 0.3742, "step": 225190 }, { "epoch": 1.3386355665721537, "grad_norm": 4.423490524291992, "learning_rate": 9.167256121525629e-06, "loss": 0.3312, "step": 225200 }, { "epoch": 1.338695008648822, "grad_norm": 6.386044025421143, "learning_rate": 9.167141459234011e-06, "loss": 0.3428, "step": 225210 }, { "epoch": 1.3387544507254905, "grad_norm": 4.530912399291992, "learning_rate": 9.167026789766078e-06, "loss": 0.3624, "step": 225220 }, { "epoch": 1.338813892802159, "grad_norm": 5.491520404815674, "learning_rate": 9.166912113122029e-06, "loss": 0.3704, "step": 225230 }, { "epoch": 1.3388733348788273, "grad_norm": 5.378631114959717, "learning_rate": 9.16679742930206e-06, "loss": 0.3801, "step": 225240 }, { "epoch": 1.3389327769554957, "grad_norm": 3.8421249389648438, "learning_rate": 9.166682738306366e-06, "loss": 0.3774, "step": 225250 }, { "epoch": 1.3389922190321641, "grad_norm": 5.906884670257568, "learning_rate": 9.166568040135149e-06, "loss": 0.4072, "step": 225260 }, { "epoch": 1.3390516611088326, "grad_norm": 5.573848247528076, "learning_rate": 9.166453334788603e-06, "loss": 0.3675, "step": 225270 }, { "epoch": 1.339111103185501, "grad_norm": 7.946454048156738, "learning_rate": 9.16633862226693e-06, "loss": 0.3794, "step": 225280 }, { "epoch": 1.3391705452621694, "grad_norm": 5.844522476196289, "learning_rate": 9.166223902570323e-06, "loss": 0.3992, "step": 225290 }, { "epoch": 1.3392299873388378, "grad_norm": 6.5028462409973145, "learning_rate": 9.16610917569898e-06, "loss": 0.3881, "step": 225300 }, { "epoch": 1.339289429415506, "grad_norm": 6.296828269958496, "learning_rate": 9.165994441653103e-06, "loss": 0.3811, "step": 225310 }, { "epoch": 1.3393488714921744, "grad_norm": 5.9556884765625, "learning_rate": 9.165879700432885e-06, "loss": 0.3571, "step": 225320 }, { "epoch": 1.3394083135688428, "grad_norm": 4.42018985748291, "learning_rate": 9.165764952038525e-06, "loss": 0.3444, "step": 225330 }, { "epoch": 1.3394677556455112, "grad_norm": 5.72566032409668, "learning_rate": 9.165650196470221e-06, "loss": 0.3373, "step": 225340 }, { "epoch": 1.3395271977221797, "grad_norm": 4.496449947357178, "learning_rate": 9.16553543372817e-06, "loss": 0.3641, "step": 225350 }, { "epoch": 1.339586639798848, "grad_norm": 5.414062023162842, "learning_rate": 9.16542066381257e-06, "loss": 0.388, "step": 225360 }, { "epoch": 1.3396460818755165, "grad_norm": 4.535284996032715, "learning_rate": 9.165305886723619e-06, "loss": 0.4214, "step": 225370 }, { "epoch": 1.3397055239521847, "grad_norm": 4.999260902404785, "learning_rate": 9.165191102461515e-06, "loss": 0.3947, "step": 225380 }, { "epoch": 1.339764966028853, "grad_norm": 6.877987861633301, "learning_rate": 9.165076311026454e-06, "loss": 0.421, "step": 225390 }, { "epoch": 1.3398244081055215, "grad_norm": 4.928901195526123, "learning_rate": 9.164961512418634e-06, "loss": 0.3527, "step": 225400 }, { "epoch": 1.33988385018219, "grad_norm": 5.728662014007568, "learning_rate": 9.164846706638254e-06, "loss": 0.3728, "step": 225410 }, { "epoch": 1.3399432922588583, "grad_norm": 5.201332092285156, "learning_rate": 9.164731893685511e-06, "loss": 0.3754, "step": 225420 }, { "epoch": 1.3400027343355267, "grad_norm": 4.323013782501221, "learning_rate": 9.164617073560602e-06, "loss": 0.3165, "step": 225430 }, { "epoch": 1.3400621764121952, "grad_norm": 7.640111446380615, "learning_rate": 9.164502246263727e-06, "loss": 0.4211, "step": 225440 }, { "epoch": 1.3401216184888636, "grad_norm": 5.001745700836182, "learning_rate": 9.164387411795082e-06, "loss": 0.3656, "step": 225450 }, { "epoch": 1.340181060565532, "grad_norm": 4.906998634338379, "learning_rate": 9.164272570154865e-06, "loss": 0.4237, "step": 225460 }, { "epoch": 1.3402405026422004, "grad_norm": 4.27748441696167, "learning_rate": 9.164157721343272e-06, "loss": 0.3673, "step": 225470 }, { "epoch": 1.3402999447188688, "grad_norm": 5.319165229797363, "learning_rate": 9.164042865360503e-06, "loss": 0.3614, "step": 225480 }, { "epoch": 1.340359386795537, "grad_norm": 4.680405616760254, "learning_rate": 9.163928002206757e-06, "loss": 0.3596, "step": 225490 }, { "epoch": 1.3404188288722054, "grad_norm": 5.475924015045166, "learning_rate": 9.16381313188223e-06, "loss": 0.373, "step": 225500 }, { "epoch": 1.3404782709488738, "grad_norm": 4.7119550704956055, "learning_rate": 9.163698254387118e-06, "loss": 0.4008, "step": 225510 }, { "epoch": 1.3405377130255423, "grad_norm": 7.544169902801514, "learning_rate": 9.163583369721623e-06, "loss": 0.4388, "step": 225520 }, { "epoch": 1.3405971551022107, "grad_norm": 5.49086332321167, "learning_rate": 9.16346847788594e-06, "loss": 0.3892, "step": 225530 }, { "epoch": 1.340656597178879, "grad_norm": 4.529129981994629, "learning_rate": 9.163353578880266e-06, "loss": 0.3788, "step": 225540 }, { "epoch": 1.3407160392555475, "grad_norm": 6.065544605255127, "learning_rate": 9.163238672704801e-06, "loss": 0.3795, "step": 225550 }, { "epoch": 1.3407754813322157, "grad_norm": 4.791876792907715, "learning_rate": 9.163123759359742e-06, "loss": 0.3754, "step": 225560 }, { "epoch": 1.340834923408884, "grad_norm": 6.039668083190918, "learning_rate": 9.163008838845288e-06, "loss": 0.391, "step": 225570 }, { "epoch": 1.3408943654855525, "grad_norm": 5.632439613342285, "learning_rate": 9.162893911161636e-06, "loss": 0.3616, "step": 225580 }, { "epoch": 1.340953807562221, "grad_norm": 5.357974529266357, "learning_rate": 9.162778976308985e-06, "loss": 0.3512, "step": 225590 }, { "epoch": 1.3410132496388893, "grad_norm": 6.8215765953063965, "learning_rate": 9.16266403428753e-06, "loss": 0.3731, "step": 225600 }, { "epoch": 1.3410726917155578, "grad_norm": 6.358259677886963, "learning_rate": 9.162549085097471e-06, "loss": 0.3724, "step": 225610 }, { "epoch": 1.3411321337922262, "grad_norm": 4.809292793273926, "learning_rate": 9.162434128739008e-06, "loss": 0.3889, "step": 225620 }, { "epoch": 1.3411915758688946, "grad_norm": 5.401186466217041, "learning_rate": 9.162319165212335e-06, "loss": 0.3914, "step": 225630 }, { "epoch": 1.341251017945563, "grad_norm": 4.842189311981201, "learning_rate": 9.162204194517651e-06, "loss": 0.3467, "step": 225640 }, { "epoch": 1.3413104600222314, "grad_norm": 5.531851291656494, "learning_rate": 9.162089216655156e-06, "loss": 0.4093, "step": 225650 }, { "epoch": 1.3413699020988998, "grad_norm": 4.306536674499512, "learning_rate": 9.161974231625048e-06, "loss": 0.4222, "step": 225660 }, { "epoch": 1.3414293441755683, "grad_norm": 5.60487174987793, "learning_rate": 9.161859239427522e-06, "loss": 0.3678, "step": 225670 }, { "epoch": 1.3414887862522364, "grad_norm": 4.499800205230713, "learning_rate": 9.161744240062777e-06, "loss": 0.3843, "step": 225680 }, { "epoch": 1.3415482283289049, "grad_norm": 4.60858154296875, "learning_rate": 9.161629233531014e-06, "loss": 0.3812, "step": 225690 }, { "epoch": 1.3416076704055733, "grad_norm": 3.7470624446868896, "learning_rate": 9.161514219832428e-06, "loss": 0.3682, "step": 225700 }, { "epoch": 1.3416671124822417, "grad_norm": 5.75844669342041, "learning_rate": 9.161399198967218e-06, "loss": 0.3671, "step": 225710 }, { "epoch": 1.34172655455891, "grad_norm": 5.088785171508789, "learning_rate": 9.161284170935582e-06, "loss": 0.3649, "step": 225720 }, { "epoch": 1.3417859966355785, "grad_norm": 7.109492301940918, "learning_rate": 9.161169135737717e-06, "loss": 0.373, "step": 225730 }, { "epoch": 1.341845438712247, "grad_norm": 4.867929935455322, "learning_rate": 9.161054093373824e-06, "loss": 0.3332, "step": 225740 }, { "epoch": 1.3419048807889151, "grad_norm": 5.020948886871338, "learning_rate": 9.1609390438441e-06, "loss": 0.3225, "step": 225750 }, { "epoch": 1.3419643228655835, "grad_norm": 5.005666255950928, "learning_rate": 9.16082398714874e-06, "loss": 0.3783, "step": 225760 }, { "epoch": 1.342023764942252, "grad_norm": 4.3999528884887695, "learning_rate": 9.160708923287946e-06, "loss": 0.3758, "step": 225770 }, { "epoch": 1.3420832070189204, "grad_norm": 4.433241367340088, "learning_rate": 9.160593852261915e-06, "loss": 0.3438, "step": 225780 }, { "epoch": 1.3421426490955888, "grad_norm": 5.609699249267578, "learning_rate": 9.160478774070845e-06, "loss": 0.3679, "step": 225790 }, { "epoch": 1.3422020911722572, "grad_norm": 4.566959381103516, "learning_rate": 9.160363688714932e-06, "loss": 0.365, "step": 225800 }, { "epoch": 1.3422615332489256, "grad_norm": 5.817870140075684, "learning_rate": 9.16024859619438e-06, "loss": 0.3737, "step": 225810 }, { "epoch": 1.342320975325594, "grad_norm": 4.769458293914795, "learning_rate": 9.16013349650938e-06, "loss": 0.3685, "step": 225820 }, { "epoch": 1.3423804174022624, "grad_norm": 5.717170715332031, "learning_rate": 9.160018389660134e-06, "loss": 0.3819, "step": 225830 }, { "epoch": 1.3424398594789309, "grad_norm": 4.044840335845947, "learning_rate": 9.159903275646842e-06, "loss": 0.3656, "step": 225840 }, { "epoch": 1.3424993015555993, "grad_norm": 6.227480888366699, "learning_rate": 9.1597881544697e-06, "loss": 0.3943, "step": 225850 }, { "epoch": 1.3425587436322675, "grad_norm": 6.594444751739502, "learning_rate": 9.159673026128906e-06, "loss": 0.4119, "step": 225860 }, { "epoch": 1.3426181857089359, "grad_norm": 5.69857120513916, "learning_rate": 9.159557890624658e-06, "loss": 0.3655, "step": 225870 }, { "epoch": 1.3426776277856043, "grad_norm": 6.063795566558838, "learning_rate": 9.159442747957156e-06, "loss": 0.418, "step": 225880 }, { "epoch": 1.3427370698622727, "grad_norm": 4.578734397888184, "learning_rate": 9.159327598126598e-06, "loss": 0.3952, "step": 225890 }, { "epoch": 1.3427965119389411, "grad_norm": 4.829905986785889, "learning_rate": 9.159212441133178e-06, "loss": 0.3626, "step": 225900 }, { "epoch": 1.3428559540156095, "grad_norm": 5.8356194496154785, "learning_rate": 9.159097276977102e-06, "loss": 0.3978, "step": 225910 }, { "epoch": 1.342915396092278, "grad_norm": 5.468912601470947, "learning_rate": 9.158982105658562e-06, "loss": 0.3712, "step": 225920 }, { "epoch": 1.3429748381689461, "grad_norm": 4.887528419494629, "learning_rate": 9.158866927177758e-06, "loss": 0.3759, "step": 225930 }, { "epoch": 1.3430342802456146, "grad_norm": 4.839572906494141, "learning_rate": 9.15875174153489e-06, "loss": 0.3524, "step": 225940 }, { "epoch": 1.343093722322283, "grad_norm": 6.757166385650635, "learning_rate": 9.158636548730158e-06, "loss": 0.3926, "step": 225950 }, { "epoch": 1.3431531643989514, "grad_norm": 5.3944783210754395, "learning_rate": 9.158521348763754e-06, "loss": 0.3835, "step": 225960 }, { "epoch": 1.3432126064756198, "grad_norm": 4.941978931427002, "learning_rate": 9.15840614163588e-06, "loss": 0.3345, "step": 225970 }, { "epoch": 1.3432720485522882, "grad_norm": 6.562311172485352, "learning_rate": 9.158290927346735e-06, "loss": 0.3653, "step": 225980 }, { "epoch": 1.3433314906289566, "grad_norm": 4.211164951324463, "learning_rate": 9.15817570589652e-06, "loss": 0.3652, "step": 225990 }, { "epoch": 1.343390932705625, "grad_norm": 3.863978385925293, "learning_rate": 9.158060477285426e-06, "loss": 0.366, "step": 226000 }, { "epoch": 1.3434503747822935, "grad_norm": 3.9994513988494873, "learning_rate": 9.157945241513658e-06, "loss": 0.3954, "step": 226010 }, { "epoch": 1.3435098168589619, "grad_norm": 5.368409633636475, "learning_rate": 9.157829998581412e-06, "loss": 0.4034, "step": 226020 }, { "epoch": 1.3435692589356303, "grad_norm": 6.144800662994385, "learning_rate": 9.157714748488886e-06, "loss": 0.3973, "step": 226030 }, { "epoch": 1.3436287010122987, "grad_norm": 4.746836185455322, "learning_rate": 9.15759949123628e-06, "loss": 0.3821, "step": 226040 }, { "epoch": 1.343688143088967, "grad_norm": 5.573594093322754, "learning_rate": 9.157484226823791e-06, "loss": 0.3672, "step": 226050 }, { "epoch": 1.3437475851656353, "grad_norm": 5.1559367179870605, "learning_rate": 9.157368955251617e-06, "loss": 0.3888, "step": 226060 }, { "epoch": 1.3438070272423037, "grad_norm": 4.800156593322754, "learning_rate": 9.15725367651996e-06, "loss": 0.3408, "step": 226070 }, { "epoch": 1.3438664693189721, "grad_norm": 4.911198139190674, "learning_rate": 9.157138390629015e-06, "loss": 0.3774, "step": 226080 }, { "epoch": 1.3439259113956405, "grad_norm": 5.232894420623779, "learning_rate": 9.157023097578982e-06, "loss": 0.3953, "step": 226090 }, { "epoch": 1.343985353472309, "grad_norm": 6.256135940551758, "learning_rate": 9.156907797370057e-06, "loss": 0.3749, "step": 226100 }, { "epoch": 1.3440447955489774, "grad_norm": 7.253439426422119, "learning_rate": 9.156792490002443e-06, "loss": 0.3689, "step": 226110 }, { "epoch": 1.3441042376256456, "grad_norm": 4.955971717834473, "learning_rate": 9.156677175476336e-06, "loss": 0.3662, "step": 226120 }, { "epoch": 1.344163679702314, "grad_norm": 7.230921268463135, "learning_rate": 9.156561853791934e-06, "loss": 0.3875, "step": 226130 }, { "epoch": 1.3442231217789824, "grad_norm": 4.797323703765869, "learning_rate": 9.156446524949438e-06, "loss": 0.377, "step": 226140 }, { "epoch": 1.3442825638556508, "grad_norm": 4.32442045211792, "learning_rate": 9.156331188949043e-06, "loss": 0.4266, "step": 226150 }, { "epoch": 1.3443420059323192, "grad_norm": 5.751436233520508, "learning_rate": 9.156215845790953e-06, "loss": 0.3656, "step": 226160 }, { "epoch": 1.3444014480089876, "grad_norm": 4.150358200073242, "learning_rate": 9.156100495475362e-06, "loss": 0.3573, "step": 226170 }, { "epoch": 1.344460890085656, "grad_norm": 5.50989294052124, "learning_rate": 9.15598513800247e-06, "loss": 0.3589, "step": 226180 }, { "epoch": 1.3445203321623245, "grad_norm": 4.478477954864502, "learning_rate": 9.155869773372474e-06, "loss": 0.3592, "step": 226190 }, { "epoch": 1.3445797742389929, "grad_norm": 4.023228645324707, "learning_rate": 9.155754401585576e-06, "loss": 0.3898, "step": 226200 }, { "epoch": 1.3446392163156613, "grad_norm": 5.2224202156066895, "learning_rate": 9.155639022641973e-06, "loss": 0.3892, "step": 226210 }, { "epoch": 1.3446986583923297, "grad_norm": 4.217709064483643, "learning_rate": 9.155523636541864e-06, "loss": 0.426, "step": 226220 }, { "epoch": 1.344758100468998, "grad_norm": 5.572593688964844, "learning_rate": 9.155408243285446e-06, "loss": 0.3895, "step": 226230 }, { "epoch": 1.3448175425456663, "grad_norm": 4.890732765197754, "learning_rate": 9.155292842872921e-06, "loss": 0.4081, "step": 226240 }, { "epoch": 1.3448769846223347, "grad_norm": 5.997775077819824, "learning_rate": 9.155177435304486e-06, "loss": 0.3936, "step": 226250 }, { "epoch": 1.3449364266990032, "grad_norm": 4.8523688316345215, "learning_rate": 9.155062020580338e-06, "loss": 0.3957, "step": 226260 }, { "epoch": 1.3449958687756716, "grad_norm": 5.573572158813477, "learning_rate": 9.154946598700678e-06, "loss": 0.3702, "step": 226270 }, { "epoch": 1.34505531085234, "grad_norm": 5.435445308685303, "learning_rate": 9.154831169665704e-06, "loss": 0.3624, "step": 226280 }, { "epoch": 1.3451147529290084, "grad_norm": 5.752146244049072, "learning_rate": 9.154715733475616e-06, "loss": 0.3743, "step": 226290 }, { "epoch": 1.3451741950056766, "grad_norm": 5.685248851776123, "learning_rate": 9.154600290130611e-06, "loss": 0.4186, "step": 226300 }, { "epoch": 1.345233637082345, "grad_norm": 5.068908214569092, "learning_rate": 9.154484839630889e-06, "loss": 0.3433, "step": 226310 }, { "epoch": 1.3452930791590134, "grad_norm": 4.485485076904297, "learning_rate": 9.154369381976648e-06, "loss": 0.358, "step": 226320 }, { "epoch": 1.3453525212356818, "grad_norm": 6.4458699226379395, "learning_rate": 9.154253917168088e-06, "loss": 0.3612, "step": 226330 }, { "epoch": 1.3454119633123502, "grad_norm": 4.813594818115234, "learning_rate": 9.154138445205406e-06, "loss": 0.3832, "step": 226340 }, { "epoch": 1.3454714053890187, "grad_norm": 5.6955413818359375, "learning_rate": 9.154022966088803e-06, "loss": 0.3533, "step": 226350 }, { "epoch": 1.345530847465687, "grad_norm": 4.909186363220215, "learning_rate": 9.153907479818476e-06, "loss": 0.3608, "step": 226360 }, { "epoch": 1.3455902895423555, "grad_norm": 4.403860092163086, "learning_rate": 9.153791986394625e-06, "loss": 0.3994, "step": 226370 }, { "epoch": 1.345649731619024, "grad_norm": 5.352137088775635, "learning_rate": 9.153676485817449e-06, "loss": 0.3413, "step": 226380 }, { "epoch": 1.3457091736956923, "grad_norm": 5.186549186706543, "learning_rate": 9.153560978087144e-06, "loss": 0.3743, "step": 226390 }, { "epoch": 1.3457686157723607, "grad_norm": 6.202600002288818, "learning_rate": 9.153445463203914e-06, "loss": 0.4044, "step": 226400 }, { "epoch": 1.3458280578490291, "grad_norm": 5.693451404571533, "learning_rate": 9.153329941167954e-06, "loss": 0.3763, "step": 226410 }, { "epoch": 1.3458874999256973, "grad_norm": 4.72952938079834, "learning_rate": 9.153214411979465e-06, "loss": 0.3575, "step": 226420 }, { "epoch": 1.3459469420023658, "grad_norm": 4.888370037078857, "learning_rate": 9.153098875638646e-06, "loss": 0.3556, "step": 226430 }, { "epoch": 1.3460063840790342, "grad_norm": 5.279747486114502, "learning_rate": 9.152983332145695e-06, "loss": 0.385, "step": 226440 }, { "epoch": 1.3460658261557026, "grad_norm": 5.896203994750977, "learning_rate": 9.15286778150081e-06, "loss": 0.4187, "step": 226450 }, { "epoch": 1.346125268232371, "grad_norm": 4.696088790893555, "learning_rate": 9.152752223704192e-06, "loss": 0.3586, "step": 226460 }, { "epoch": 1.3461847103090394, "grad_norm": 5.435573577880859, "learning_rate": 9.152636658756039e-06, "loss": 0.3622, "step": 226470 }, { "epoch": 1.3462441523857078, "grad_norm": 6.731990337371826, "learning_rate": 9.15252108665655e-06, "loss": 0.4515, "step": 226480 }, { "epoch": 1.346303594462376, "grad_norm": 4.99448823928833, "learning_rate": 9.152405507405925e-06, "loss": 0.3625, "step": 226490 }, { "epoch": 1.3463630365390444, "grad_norm": 3.419597864151001, "learning_rate": 9.15228992100436e-06, "loss": 0.361, "step": 226500 }, { "epoch": 1.3464224786157128, "grad_norm": 5.6471734046936035, "learning_rate": 9.152174327452059e-06, "loss": 0.3809, "step": 226510 }, { "epoch": 1.3464819206923813, "grad_norm": 4.38472318649292, "learning_rate": 9.152058726749217e-06, "loss": 0.3813, "step": 226520 }, { "epoch": 1.3465413627690497, "grad_norm": 5.580231189727783, "learning_rate": 9.151943118896035e-06, "loss": 0.3785, "step": 226530 }, { "epoch": 1.346600804845718, "grad_norm": 3.5858993530273438, "learning_rate": 9.151827503892712e-06, "loss": 0.3316, "step": 226540 }, { "epoch": 1.3466602469223865, "grad_norm": 4.0336103439331055, "learning_rate": 9.151711881739444e-06, "loss": 0.3673, "step": 226550 }, { "epoch": 1.346719688999055, "grad_norm": 4.288697719573975, "learning_rate": 9.151596252436436e-06, "loss": 0.4131, "step": 226560 }, { "epoch": 1.3467791310757233, "grad_norm": 5.524310111999512, "learning_rate": 9.151480615983883e-06, "loss": 0.3777, "step": 226570 }, { "epoch": 1.3468385731523917, "grad_norm": 3.468515634536743, "learning_rate": 9.151364972381984e-06, "loss": 0.3268, "step": 226580 }, { "epoch": 1.3468980152290602, "grad_norm": 5.0547099113464355, "learning_rate": 9.15124932163094e-06, "loss": 0.3793, "step": 226590 }, { "epoch": 1.3469574573057284, "grad_norm": 5.540288925170898, "learning_rate": 9.151133663730948e-06, "loss": 0.3779, "step": 226600 }, { "epoch": 1.3470168993823968, "grad_norm": 4.017536640167236, "learning_rate": 9.15101799868221e-06, "loss": 0.3861, "step": 226610 }, { "epoch": 1.3470763414590652, "grad_norm": 5.737935543060303, "learning_rate": 9.150902326484926e-06, "loss": 0.3546, "step": 226620 }, { "epoch": 1.3471357835357336, "grad_norm": 4.502367973327637, "learning_rate": 9.15078664713929e-06, "loss": 0.4043, "step": 226630 }, { "epoch": 1.347195225612402, "grad_norm": 5.311004638671875, "learning_rate": 9.150670960645502e-06, "loss": 0.4095, "step": 226640 }, { "epoch": 1.3472546676890704, "grad_norm": 5.704314231872559, "learning_rate": 9.150555267003767e-06, "loss": 0.3646, "step": 226650 }, { "epoch": 1.3473141097657388, "grad_norm": 4.144287109375, "learning_rate": 9.15043956621428e-06, "loss": 0.375, "step": 226660 }, { "epoch": 1.347373551842407, "grad_norm": 7.048561096191406, "learning_rate": 9.15032385827724e-06, "loss": 0.3565, "step": 226670 }, { "epoch": 1.3474329939190755, "grad_norm": 4.328470230102539, "learning_rate": 9.150208143192847e-06, "loss": 0.3923, "step": 226680 }, { "epoch": 1.3474924359957439, "grad_norm": 4.893441677093506, "learning_rate": 9.150092420961301e-06, "loss": 0.3577, "step": 226690 }, { "epoch": 1.3475518780724123, "grad_norm": 4.581905841827393, "learning_rate": 9.149976691582801e-06, "loss": 0.3751, "step": 226700 }, { "epoch": 1.3476113201490807, "grad_norm": 4.455202102661133, "learning_rate": 9.149860955057545e-06, "loss": 0.3547, "step": 226710 }, { "epoch": 1.347670762225749, "grad_norm": 4.411649227142334, "learning_rate": 9.149745211385733e-06, "loss": 0.3724, "step": 226720 }, { "epoch": 1.3477302043024175, "grad_norm": 6.459436893463135, "learning_rate": 9.149629460567566e-06, "loss": 0.3466, "step": 226730 }, { "epoch": 1.347789646379086, "grad_norm": 6.849616527557373, "learning_rate": 9.149513702603242e-06, "loss": 0.3753, "step": 226740 }, { "epoch": 1.3478490884557544, "grad_norm": 4.985233783721924, "learning_rate": 9.149397937492958e-06, "loss": 0.3641, "step": 226750 }, { "epoch": 1.3479085305324228, "grad_norm": 4.339380264282227, "learning_rate": 9.149282165236917e-06, "loss": 0.3628, "step": 226760 }, { "epoch": 1.3479679726090912, "grad_norm": 4.651357173919678, "learning_rate": 9.149166385835318e-06, "loss": 0.3859, "step": 226770 }, { "epoch": 1.3480274146857596, "grad_norm": 4.392143249511719, "learning_rate": 9.149050599288358e-06, "loss": 0.3888, "step": 226780 }, { "epoch": 1.3480868567624278, "grad_norm": 6.3484578132629395, "learning_rate": 9.148934805596239e-06, "loss": 0.4043, "step": 226790 }, { "epoch": 1.3481462988390962, "grad_norm": 3.8722047805786133, "learning_rate": 9.148819004759158e-06, "loss": 0.3873, "step": 226800 }, { "epoch": 1.3482057409157646, "grad_norm": 5.671827793121338, "learning_rate": 9.148703196777317e-06, "loss": 0.3724, "step": 226810 }, { "epoch": 1.348265182992433, "grad_norm": 5.999156951904297, "learning_rate": 9.148587381650913e-06, "loss": 0.3729, "step": 226820 }, { "epoch": 1.3483246250691014, "grad_norm": 6.222949504852295, "learning_rate": 9.148471559380148e-06, "loss": 0.4463, "step": 226830 }, { "epoch": 1.3483840671457699, "grad_norm": 4.913932800292969, "learning_rate": 9.148355729965217e-06, "loss": 0.361, "step": 226840 }, { "epoch": 1.3484435092224383, "grad_norm": 5.118415355682373, "learning_rate": 9.148239893406326e-06, "loss": 0.3909, "step": 226850 }, { "epoch": 1.3485029512991065, "grad_norm": 3.8049352169036865, "learning_rate": 9.148124049703668e-06, "loss": 0.3389, "step": 226860 }, { "epoch": 1.3485623933757749, "grad_norm": 6.789117336273193, "learning_rate": 9.148008198857447e-06, "loss": 0.4024, "step": 226870 }, { "epoch": 1.3486218354524433, "grad_norm": 5.21682071685791, "learning_rate": 9.147892340867861e-06, "loss": 0.3586, "step": 226880 }, { "epoch": 1.3486812775291117, "grad_norm": 6.112573146820068, "learning_rate": 9.147776475735108e-06, "loss": 0.3964, "step": 226890 }, { "epoch": 1.3487407196057801, "grad_norm": 4.546594142913818, "learning_rate": 9.147660603459392e-06, "loss": 0.37, "step": 226900 }, { "epoch": 1.3488001616824485, "grad_norm": 4.637713432312012, "learning_rate": 9.147544724040906e-06, "loss": 0.3589, "step": 226910 }, { "epoch": 1.348859603759117, "grad_norm": 4.696634769439697, "learning_rate": 9.147428837479855e-06, "loss": 0.4396, "step": 226920 }, { "epoch": 1.3489190458357854, "grad_norm": 5.798417091369629, "learning_rate": 9.147312943776437e-06, "loss": 0.3856, "step": 226930 }, { "epoch": 1.3489784879124538, "grad_norm": 3.4071803092956543, "learning_rate": 9.147197042930851e-06, "loss": 0.3616, "step": 226940 }, { "epoch": 1.3490379299891222, "grad_norm": 4.871037006378174, "learning_rate": 9.147081134943296e-06, "loss": 0.3606, "step": 226950 }, { "epoch": 1.3490973720657906, "grad_norm": 5.353881359100342, "learning_rate": 9.146965219813972e-06, "loss": 0.3989, "step": 226960 }, { "epoch": 1.3491568141424588, "grad_norm": 4.5755839347839355, "learning_rate": 9.146849297543082e-06, "loss": 0.3844, "step": 226970 }, { "epoch": 1.3492162562191272, "grad_norm": 4.878472328186035, "learning_rate": 9.14673336813082e-06, "loss": 0.3457, "step": 226980 }, { "epoch": 1.3492756982957956, "grad_norm": 6.3991780281066895, "learning_rate": 9.14661743157739e-06, "loss": 0.4189, "step": 226990 }, { "epoch": 1.349335140372464, "grad_norm": 5.9000701904296875, "learning_rate": 9.146501487882989e-06, "loss": 0.3607, "step": 227000 }, { "epoch": 1.3493945824491325, "grad_norm": 4.360710620880127, "learning_rate": 9.146385537047816e-06, "loss": 0.3777, "step": 227010 }, { "epoch": 1.3494540245258009, "grad_norm": 5.765895843505859, "learning_rate": 9.146269579072076e-06, "loss": 0.3917, "step": 227020 }, { "epoch": 1.3495134666024693, "grad_norm": 3.841460943222046, "learning_rate": 9.146153613955964e-06, "loss": 0.429, "step": 227030 }, { "epoch": 1.3495729086791375, "grad_norm": 4.46983528137207, "learning_rate": 9.146037641699679e-06, "loss": 0.3992, "step": 227040 }, { "epoch": 1.349632350755806, "grad_norm": 3.923733949661255, "learning_rate": 9.145921662303424e-06, "loss": 0.3563, "step": 227050 }, { "epoch": 1.3496917928324743, "grad_norm": 4.475543975830078, "learning_rate": 9.145805675767397e-06, "loss": 0.387, "step": 227060 }, { "epoch": 1.3497512349091427, "grad_norm": 5.689544200897217, "learning_rate": 9.145689682091798e-06, "loss": 0.3653, "step": 227070 }, { "epoch": 1.3498106769858111, "grad_norm": 5.225000858306885, "learning_rate": 9.145573681276826e-06, "loss": 0.4049, "step": 227080 }, { "epoch": 1.3498701190624796, "grad_norm": 4.804491996765137, "learning_rate": 9.145457673322681e-06, "loss": 0.3706, "step": 227090 }, { "epoch": 1.349929561139148, "grad_norm": 5.2010321617126465, "learning_rate": 9.145341658229565e-06, "loss": 0.4017, "step": 227100 }, { "epoch": 1.3499890032158164, "grad_norm": 5.1398138999938965, "learning_rate": 9.145225635997677e-06, "loss": 0.3778, "step": 227110 }, { "epoch": 1.3500484452924848, "grad_norm": 5.547334671020508, "learning_rate": 9.145109606627212e-06, "loss": 0.3704, "step": 227120 }, { "epoch": 1.3501078873691532, "grad_norm": 4.540857791900635, "learning_rate": 9.144993570118377e-06, "loss": 0.3601, "step": 227130 }, { "epoch": 1.3501673294458216, "grad_norm": 4.809189319610596, "learning_rate": 9.144877526471368e-06, "loss": 0.3743, "step": 227140 }, { "epoch": 1.35022677152249, "grad_norm": 5.236953258514404, "learning_rate": 9.144761475686384e-06, "loss": 0.3759, "step": 227150 }, { "epoch": 1.3502862135991582, "grad_norm": 6.034179210662842, "learning_rate": 9.144645417763626e-06, "loss": 0.4021, "step": 227160 }, { "epoch": 1.3503456556758267, "grad_norm": 4.659711837768555, "learning_rate": 9.144529352703296e-06, "loss": 0.3845, "step": 227170 }, { "epoch": 1.350405097752495, "grad_norm": 6.431591510772705, "learning_rate": 9.14441328050559e-06, "loss": 0.3928, "step": 227180 }, { "epoch": 1.3504645398291635, "grad_norm": 6.7512898445129395, "learning_rate": 9.144297201170711e-06, "loss": 0.3718, "step": 227190 }, { "epoch": 1.350523981905832, "grad_norm": 4.178687572479248, "learning_rate": 9.144181114698857e-06, "loss": 0.3759, "step": 227200 }, { "epoch": 1.3505834239825003, "grad_norm": 4.296667098999023, "learning_rate": 9.14406502109023e-06, "loss": 0.3673, "step": 227210 }, { "epoch": 1.3506428660591687, "grad_norm": 5.063290596008301, "learning_rate": 9.143948920345026e-06, "loss": 0.3558, "step": 227220 }, { "epoch": 1.350702308135837, "grad_norm": 5.0667829513549805, "learning_rate": 9.143832812463449e-06, "loss": 0.3691, "step": 227230 }, { "epoch": 1.3507617502125053, "grad_norm": 6.25416374206543, "learning_rate": 9.143716697445698e-06, "loss": 0.4097, "step": 227240 }, { "epoch": 1.3508211922891737, "grad_norm": 4.7164459228515625, "learning_rate": 9.143600575291972e-06, "loss": 0.393, "step": 227250 }, { "epoch": 1.3508806343658422, "grad_norm": 5.3584513664245605, "learning_rate": 9.143484446002472e-06, "loss": 0.3729, "step": 227260 }, { "epoch": 1.3509400764425106, "grad_norm": 5.0337653160095215, "learning_rate": 9.143368309577397e-06, "loss": 0.381, "step": 227270 }, { "epoch": 1.350999518519179, "grad_norm": 4.805927276611328, "learning_rate": 9.143252166016946e-06, "loss": 0.3886, "step": 227280 }, { "epoch": 1.3510589605958474, "grad_norm": 5.985617160797119, "learning_rate": 9.143136015321322e-06, "loss": 0.3838, "step": 227290 }, { "epoch": 1.3511184026725158, "grad_norm": 5.677071571350098, "learning_rate": 9.143019857490723e-06, "loss": 0.4013, "step": 227300 }, { "epoch": 1.3511778447491842, "grad_norm": 4.728821277618408, "learning_rate": 9.142903692525349e-06, "loss": 0.3983, "step": 227310 }, { "epoch": 1.3512372868258526, "grad_norm": 5.465184211730957, "learning_rate": 9.142787520425402e-06, "loss": 0.4157, "step": 227320 }, { "epoch": 1.351296728902521, "grad_norm": 4.129827976226807, "learning_rate": 9.142671341191079e-06, "loss": 0.3737, "step": 227330 }, { "epoch": 1.3513561709791893, "grad_norm": 5.017733573913574, "learning_rate": 9.142555154822583e-06, "loss": 0.3704, "step": 227340 }, { "epoch": 1.3514156130558577, "grad_norm": 6.125351428985596, "learning_rate": 9.14243896132011e-06, "loss": 0.3713, "step": 227350 }, { "epoch": 1.351475055132526, "grad_norm": 4.3489203453063965, "learning_rate": 9.142322760683867e-06, "loss": 0.3524, "step": 227360 }, { "epoch": 1.3515344972091945, "grad_norm": 5.768462181091309, "learning_rate": 9.142206552914048e-06, "loss": 0.4188, "step": 227370 }, { "epoch": 1.351593939285863, "grad_norm": 4.920506954193115, "learning_rate": 9.142090338010853e-06, "loss": 0.3951, "step": 227380 }, { "epoch": 1.3516533813625313, "grad_norm": 5.229698657989502, "learning_rate": 9.141974115974488e-06, "loss": 0.3415, "step": 227390 }, { "epoch": 1.3517128234391997, "grad_norm": 5.158847332000732, "learning_rate": 9.141857886805146e-06, "loss": 0.3935, "step": 227400 }, { "epoch": 1.351772265515868, "grad_norm": 4.601110935211182, "learning_rate": 9.141741650503033e-06, "loss": 0.3761, "step": 227410 }, { "epoch": 1.3518317075925363, "grad_norm": 5.174519062042236, "learning_rate": 9.141625407068345e-06, "loss": 0.3984, "step": 227420 }, { "epoch": 1.3518911496692048, "grad_norm": 4.81704568862915, "learning_rate": 9.141509156501285e-06, "loss": 0.3908, "step": 227430 }, { "epoch": 1.3519505917458732, "grad_norm": 5.606501579284668, "learning_rate": 9.141392898802051e-06, "loss": 0.3755, "step": 227440 }, { "epoch": 1.3520100338225416, "grad_norm": 5.634883880615234, "learning_rate": 9.141276633970847e-06, "loss": 0.3824, "step": 227450 }, { "epoch": 1.35206947589921, "grad_norm": 6.422784328460693, "learning_rate": 9.141160362007865e-06, "loss": 0.4182, "step": 227460 }, { "epoch": 1.3521289179758784, "grad_norm": 4.94836950302124, "learning_rate": 9.141044082913316e-06, "loss": 0.3526, "step": 227470 }, { "epoch": 1.3521883600525468, "grad_norm": 5.237245082855225, "learning_rate": 9.140927796687394e-06, "loss": 0.4375, "step": 227480 }, { "epoch": 1.3522478021292152, "grad_norm": 5.380687236785889, "learning_rate": 9.140811503330299e-06, "loss": 0.3862, "step": 227490 }, { "epoch": 1.3523072442058837, "grad_norm": 5.890495777130127, "learning_rate": 9.140695202842233e-06, "loss": 0.3799, "step": 227500 }, { "epoch": 1.352366686282552, "grad_norm": 5.300011157989502, "learning_rate": 9.140578895223396e-06, "loss": 0.4041, "step": 227510 }, { "epoch": 1.3524261283592205, "grad_norm": 6.66351318359375, "learning_rate": 9.140462580473987e-06, "loss": 0.3892, "step": 227520 }, { "epoch": 1.3524855704358887, "grad_norm": 3.826361894607544, "learning_rate": 9.140346258594207e-06, "loss": 0.3459, "step": 227530 }, { "epoch": 1.352545012512557, "grad_norm": 3.9585957527160645, "learning_rate": 9.140229929584259e-06, "loss": 0.3722, "step": 227540 }, { "epoch": 1.3526044545892255, "grad_norm": 5.506584167480469, "learning_rate": 9.14011359344434e-06, "loss": 0.3676, "step": 227550 }, { "epoch": 1.352663896665894, "grad_norm": 5.726540565490723, "learning_rate": 9.139997250174651e-06, "loss": 0.4103, "step": 227560 }, { "epoch": 1.3527233387425623, "grad_norm": 6.92172908782959, "learning_rate": 9.139880899775392e-06, "loss": 0.3755, "step": 227570 }, { "epoch": 1.3527827808192308, "grad_norm": 5.9231414794921875, "learning_rate": 9.139764542246766e-06, "loss": 0.3961, "step": 227580 }, { "epoch": 1.3528422228958992, "grad_norm": 4.830471992492676, "learning_rate": 9.139648177588971e-06, "loss": 0.3736, "step": 227590 }, { "epoch": 1.3529016649725674, "grad_norm": 5.126120090484619, "learning_rate": 9.139531805802208e-06, "loss": 0.3985, "step": 227600 }, { "epoch": 1.3529611070492358, "grad_norm": 5.20928430557251, "learning_rate": 9.139415426886677e-06, "loss": 0.3523, "step": 227610 }, { "epoch": 1.3530205491259042, "grad_norm": 5.101996421813965, "learning_rate": 9.139299040842578e-06, "loss": 0.3739, "step": 227620 }, { "epoch": 1.3530799912025726, "grad_norm": 6.180858612060547, "learning_rate": 9.139182647670112e-06, "loss": 0.3808, "step": 227630 }, { "epoch": 1.353139433279241, "grad_norm": 5.692371368408203, "learning_rate": 9.139066247369481e-06, "loss": 0.3883, "step": 227640 }, { "epoch": 1.3531988753559094, "grad_norm": 4.814121246337891, "learning_rate": 9.138949839940885e-06, "loss": 0.3678, "step": 227650 }, { "epoch": 1.3532583174325779, "grad_norm": 4.850691795349121, "learning_rate": 9.138833425384522e-06, "loss": 0.3452, "step": 227660 }, { "epoch": 1.3533177595092463, "grad_norm": 4.818914890289307, "learning_rate": 9.138717003700593e-06, "loss": 0.3578, "step": 227670 }, { "epoch": 1.3533772015859147, "grad_norm": 5.292877674102783, "learning_rate": 9.1386005748893e-06, "loss": 0.3637, "step": 227680 }, { "epoch": 1.353436643662583, "grad_norm": 4.258031368255615, "learning_rate": 9.138484138950844e-06, "loss": 0.4093, "step": 227690 }, { "epoch": 1.3534960857392515, "grad_norm": 4.7449564933776855, "learning_rate": 9.138367695885424e-06, "loss": 0.4157, "step": 227700 }, { "epoch": 1.3535555278159197, "grad_norm": 3.2707905769348145, "learning_rate": 9.138251245693241e-06, "loss": 0.3803, "step": 227710 }, { "epoch": 1.3536149698925881, "grad_norm": 3.9863650798797607, "learning_rate": 9.138134788374497e-06, "loss": 0.377, "step": 227720 }, { "epoch": 1.3536744119692565, "grad_norm": 4.428478717803955, "learning_rate": 9.13801832392939e-06, "loss": 0.3765, "step": 227730 }, { "epoch": 1.353733854045925, "grad_norm": 4.603607177734375, "learning_rate": 9.13790185235812e-06, "loss": 0.3765, "step": 227740 }, { "epoch": 1.3537932961225934, "grad_norm": 5.442327499389648, "learning_rate": 9.137785373660892e-06, "loss": 0.3654, "step": 227750 }, { "epoch": 1.3538527381992618, "grad_norm": 4.0084147453308105, "learning_rate": 9.137668887837902e-06, "loss": 0.3389, "step": 227760 }, { "epoch": 1.3539121802759302, "grad_norm": 4.183302402496338, "learning_rate": 9.137552394889353e-06, "loss": 0.3405, "step": 227770 }, { "epoch": 1.3539716223525984, "grad_norm": 6.423964023590088, "learning_rate": 9.137435894815445e-06, "loss": 0.3907, "step": 227780 }, { "epoch": 1.3540310644292668, "grad_norm": 4.573371410369873, "learning_rate": 9.13731938761638e-06, "loss": 0.3999, "step": 227790 }, { "epoch": 1.3540905065059352, "grad_norm": 6.8207244873046875, "learning_rate": 9.137202873292356e-06, "loss": 0.3665, "step": 227800 }, { "epoch": 1.3541499485826036, "grad_norm": 6.076817512512207, "learning_rate": 9.137086351843576e-06, "loss": 0.4, "step": 227810 }, { "epoch": 1.354209390659272, "grad_norm": 4.179213047027588, "learning_rate": 9.136969823270239e-06, "loss": 0.3852, "step": 227820 }, { "epoch": 1.3542688327359405, "grad_norm": 5.666306972503662, "learning_rate": 9.136853287572546e-06, "loss": 0.3911, "step": 227830 }, { "epoch": 1.3543282748126089, "grad_norm": 4.654898643493652, "learning_rate": 9.136736744750699e-06, "loss": 0.372, "step": 227840 }, { "epoch": 1.3543877168892773, "grad_norm": 6.173269748687744, "learning_rate": 9.136620194804897e-06, "loss": 0.3441, "step": 227850 }, { "epoch": 1.3544471589659457, "grad_norm": 4.106394290924072, "learning_rate": 9.13650363773534e-06, "loss": 0.3676, "step": 227860 }, { "epoch": 1.3545066010426141, "grad_norm": 4.61860466003418, "learning_rate": 9.136387073542232e-06, "loss": 0.3589, "step": 227870 }, { "epoch": 1.3545660431192825, "grad_norm": 5.089734077453613, "learning_rate": 9.136270502225772e-06, "loss": 0.3704, "step": 227880 }, { "epoch": 1.354625485195951, "grad_norm": 4.968677520751953, "learning_rate": 9.136153923786162e-06, "loss": 0.3554, "step": 227890 }, { "epoch": 1.3546849272726191, "grad_norm": 5.588508605957031, "learning_rate": 9.136037338223598e-06, "loss": 0.3788, "step": 227900 }, { "epoch": 1.3547443693492875, "grad_norm": 4.551196098327637, "learning_rate": 9.135920745538286e-06, "loss": 0.3741, "step": 227910 }, { "epoch": 1.354803811425956, "grad_norm": 4.762676239013672, "learning_rate": 9.135804145730425e-06, "loss": 0.3287, "step": 227920 }, { "epoch": 1.3548632535026244, "grad_norm": 5.032179355621338, "learning_rate": 9.135687538800217e-06, "loss": 0.3486, "step": 227930 }, { "epoch": 1.3549226955792928, "grad_norm": 5.518968105316162, "learning_rate": 9.13557092474786e-06, "loss": 0.3897, "step": 227940 }, { "epoch": 1.3549821376559612, "grad_norm": 6.283910751342773, "learning_rate": 9.135454303573557e-06, "loss": 0.392, "step": 227950 }, { "epoch": 1.3550415797326296, "grad_norm": 5.234181880950928, "learning_rate": 9.135337675277507e-06, "loss": 0.3874, "step": 227960 }, { "epoch": 1.3551010218092978, "grad_norm": 5.214046478271484, "learning_rate": 9.135221039859915e-06, "loss": 0.4112, "step": 227970 }, { "epoch": 1.3551604638859662, "grad_norm": 4.579280376434326, "learning_rate": 9.135104397320974e-06, "loss": 0.39, "step": 227980 }, { "epoch": 1.3552199059626346, "grad_norm": 6.176056861877441, "learning_rate": 9.134987747660894e-06, "loss": 0.3544, "step": 227990 }, { "epoch": 1.355279348039303, "grad_norm": 5.171658039093018, "learning_rate": 9.134871090879871e-06, "loss": 0.3861, "step": 228000 }, { "epoch": 1.3553387901159715, "grad_norm": 4.920952320098877, "learning_rate": 9.134754426978106e-06, "loss": 0.4046, "step": 228010 }, { "epoch": 1.3553982321926399, "grad_norm": 5.117657661437988, "learning_rate": 9.134637755955803e-06, "loss": 0.36, "step": 228020 }, { "epoch": 1.3554576742693083, "grad_norm": 5.809947490692139, "learning_rate": 9.134521077813157e-06, "loss": 0.3895, "step": 228030 }, { "epoch": 1.3555171163459767, "grad_norm": 5.626580238342285, "learning_rate": 9.134404392550373e-06, "loss": 0.4184, "step": 228040 }, { "epoch": 1.3555765584226451, "grad_norm": 5.171792984008789, "learning_rate": 9.134287700167652e-06, "loss": 0.3783, "step": 228050 }, { "epoch": 1.3556360004993135, "grad_norm": 5.111085891723633, "learning_rate": 9.134171000665194e-06, "loss": 0.3949, "step": 228060 }, { "epoch": 1.355695442575982, "grad_norm": 5.7130513191223145, "learning_rate": 9.1340542940432e-06, "loss": 0.4112, "step": 228070 }, { "epoch": 1.3557548846526501, "grad_norm": 5.20734977722168, "learning_rate": 9.133937580301873e-06, "loss": 0.4013, "step": 228080 }, { "epoch": 1.3558143267293186, "grad_norm": 6.076318264007568, "learning_rate": 9.133820859441411e-06, "loss": 0.3529, "step": 228090 }, { "epoch": 1.355873768805987, "grad_norm": 5.809216499328613, "learning_rate": 9.133704131462015e-06, "loss": 0.3582, "step": 228100 }, { "epoch": 1.3559332108826554, "grad_norm": 5.541487693786621, "learning_rate": 9.13358739636389e-06, "loss": 0.3821, "step": 228110 }, { "epoch": 1.3559926529593238, "grad_norm": 5.750369548797607, "learning_rate": 9.133470654147232e-06, "loss": 0.4178, "step": 228120 }, { "epoch": 1.3560520950359922, "grad_norm": 4.720303535461426, "learning_rate": 9.133353904812245e-06, "loss": 0.3827, "step": 228130 }, { "epoch": 1.3561115371126606, "grad_norm": 5.306736469268799, "learning_rate": 9.133237148359129e-06, "loss": 0.3688, "step": 228140 }, { "epoch": 1.3561709791893288, "grad_norm": 6.3292083740234375, "learning_rate": 9.133120384788086e-06, "loss": 0.3561, "step": 228150 }, { "epoch": 1.3562304212659972, "grad_norm": 3.7695140838623047, "learning_rate": 9.133003614099317e-06, "loss": 0.3881, "step": 228160 }, { "epoch": 1.3562898633426657, "grad_norm": 6.873889446258545, "learning_rate": 9.132886836293022e-06, "loss": 0.4354, "step": 228170 }, { "epoch": 1.356349305419334, "grad_norm": 4.380659103393555, "learning_rate": 9.132770051369404e-06, "loss": 0.3872, "step": 228180 }, { "epoch": 1.3564087474960025, "grad_norm": 5.087594509124756, "learning_rate": 9.13265325932866e-06, "loss": 0.3704, "step": 228190 }, { "epoch": 1.356468189572671, "grad_norm": 5.121788501739502, "learning_rate": 9.132536460170997e-06, "loss": 0.3965, "step": 228200 }, { "epoch": 1.3565276316493393, "grad_norm": 5.313833236694336, "learning_rate": 9.13241965389661e-06, "loss": 0.3957, "step": 228210 }, { "epoch": 1.3565870737260077, "grad_norm": 5.615516185760498, "learning_rate": 9.132302840505707e-06, "loss": 0.3538, "step": 228220 }, { "epoch": 1.3566465158026761, "grad_norm": 4.385005950927734, "learning_rate": 9.132186019998484e-06, "loss": 0.3605, "step": 228230 }, { "epoch": 1.3567059578793446, "grad_norm": 6.46603536605835, "learning_rate": 9.132069192375142e-06, "loss": 0.4049, "step": 228240 }, { "epoch": 1.356765399956013, "grad_norm": 4.820001602172852, "learning_rate": 9.131952357635884e-06, "loss": 0.3627, "step": 228250 }, { "epoch": 1.3568248420326814, "grad_norm": 5.446072101593018, "learning_rate": 9.131835515780913e-06, "loss": 0.408, "step": 228260 }, { "epoch": 1.3568842841093496, "grad_norm": 4.187233924865723, "learning_rate": 9.131718666810427e-06, "loss": 0.3816, "step": 228270 }, { "epoch": 1.356943726186018, "grad_norm": 4.882689952850342, "learning_rate": 9.131601810724628e-06, "loss": 0.4002, "step": 228280 }, { "epoch": 1.3570031682626864, "grad_norm": 4.956866264343262, "learning_rate": 9.131484947523718e-06, "loss": 0.3821, "step": 228290 }, { "epoch": 1.3570626103393548, "grad_norm": 5.612305164337158, "learning_rate": 9.131368077207901e-06, "loss": 0.4444, "step": 228300 }, { "epoch": 1.3571220524160232, "grad_norm": 6.890054225921631, "learning_rate": 9.131251199777372e-06, "loss": 0.3837, "step": 228310 }, { "epoch": 1.3571814944926917, "grad_norm": 5.197717189788818, "learning_rate": 9.131134315232335e-06, "loss": 0.3982, "step": 228320 }, { "epoch": 1.35724093656936, "grad_norm": 5.514360427856445, "learning_rate": 9.131017423572994e-06, "loss": 0.3669, "step": 228330 }, { "epoch": 1.3573003786460283, "grad_norm": 5.0495734214782715, "learning_rate": 9.130900524799546e-06, "loss": 0.35, "step": 228340 }, { "epoch": 1.3573598207226967, "grad_norm": 4.551076889038086, "learning_rate": 9.130783618912196e-06, "loss": 0.4168, "step": 228350 }, { "epoch": 1.357419262799365, "grad_norm": 5.525374412536621, "learning_rate": 9.130666705911144e-06, "loss": 0.3589, "step": 228360 }, { "epoch": 1.3574787048760335, "grad_norm": 3.709404468536377, "learning_rate": 9.13054978579659e-06, "loss": 0.3951, "step": 228370 }, { "epoch": 1.357538146952702, "grad_norm": 5.419583320617676, "learning_rate": 9.130432858568735e-06, "loss": 0.3634, "step": 228380 }, { "epoch": 1.3575975890293703, "grad_norm": 5.142426013946533, "learning_rate": 9.130315924227783e-06, "loss": 0.4429, "step": 228390 }, { "epoch": 1.3576570311060387, "grad_norm": 4.553865909576416, "learning_rate": 9.130198982773937e-06, "loss": 0.3936, "step": 228400 }, { "epoch": 1.3577164731827072, "grad_norm": 4.839121341705322, "learning_rate": 9.130082034207393e-06, "loss": 0.4111, "step": 228410 }, { "epoch": 1.3577759152593756, "grad_norm": 4.765000820159912, "learning_rate": 9.129965078528355e-06, "loss": 0.3635, "step": 228420 }, { "epoch": 1.357835357336044, "grad_norm": 5.299402236938477, "learning_rate": 9.129848115737023e-06, "loss": 0.3586, "step": 228430 }, { "epoch": 1.3578947994127124, "grad_norm": 5.790377140045166, "learning_rate": 9.129731145833603e-06, "loss": 0.3704, "step": 228440 }, { "epoch": 1.3579542414893806, "grad_norm": 3.741318464279175, "learning_rate": 9.129614168818291e-06, "loss": 0.3258, "step": 228450 }, { "epoch": 1.358013683566049, "grad_norm": 4.657088756561279, "learning_rate": 9.12949718469129e-06, "loss": 0.3554, "step": 228460 }, { "epoch": 1.3580731256427174, "grad_norm": 5.369395732879639, "learning_rate": 9.129380193452804e-06, "loss": 0.3732, "step": 228470 }, { "epoch": 1.3581325677193858, "grad_norm": 3.946734666824341, "learning_rate": 9.129263195103031e-06, "loss": 0.4132, "step": 228480 }, { "epoch": 1.3581920097960543, "grad_norm": 4.520989894866943, "learning_rate": 9.129146189642176e-06, "loss": 0.3789, "step": 228490 }, { "epoch": 1.3582514518727227, "grad_norm": 6.270786285400391, "learning_rate": 9.129029177070436e-06, "loss": 0.4245, "step": 228500 }, { "epoch": 1.358310893949391, "grad_norm": 4.879939556121826, "learning_rate": 9.128912157388016e-06, "loss": 0.3778, "step": 228510 }, { "epoch": 1.3583703360260593, "grad_norm": 4.907074928283691, "learning_rate": 9.128795130595119e-06, "loss": 0.3672, "step": 228520 }, { "epoch": 1.3584297781027277, "grad_norm": 4.935873508453369, "learning_rate": 9.128678096691943e-06, "loss": 0.3956, "step": 228530 }, { "epoch": 1.358489220179396, "grad_norm": 4.838538646697998, "learning_rate": 9.128561055678689e-06, "loss": 0.3784, "step": 228540 }, { "epoch": 1.3585486622560645, "grad_norm": 6.465914249420166, "learning_rate": 9.128444007555562e-06, "loss": 0.4237, "step": 228550 }, { "epoch": 1.358608104332733, "grad_norm": 4.933789253234863, "learning_rate": 9.12832695232276e-06, "loss": 0.4225, "step": 228560 }, { "epoch": 1.3586675464094013, "grad_norm": 4.570152759552002, "learning_rate": 9.128209889980489e-06, "loss": 0.4011, "step": 228570 }, { "epoch": 1.3587269884860698, "grad_norm": 5.553548812866211, "learning_rate": 9.128092820528944e-06, "loss": 0.3814, "step": 228580 }, { "epoch": 1.3587864305627382, "grad_norm": 6.268958568572998, "learning_rate": 9.127975743968334e-06, "loss": 0.3995, "step": 228590 }, { "epoch": 1.3588458726394066, "grad_norm": 4.68262243270874, "learning_rate": 9.127858660298857e-06, "loss": 0.3967, "step": 228600 }, { "epoch": 1.358905314716075, "grad_norm": 7.379611492156982, "learning_rate": 9.127741569520715e-06, "loss": 0.406, "step": 228610 }, { "epoch": 1.3589647567927434, "grad_norm": 3.840057611465454, "learning_rate": 9.127624471634108e-06, "loss": 0.401, "step": 228620 }, { "epoch": 1.3590241988694118, "grad_norm": 5.112066745758057, "learning_rate": 9.127507366639239e-06, "loss": 0.3518, "step": 228630 }, { "epoch": 1.35908364094608, "grad_norm": 5.554575443267822, "learning_rate": 9.12739025453631e-06, "loss": 0.3483, "step": 228640 }, { "epoch": 1.3591430830227484, "grad_norm": 5.928308486938477, "learning_rate": 9.127273135325524e-06, "loss": 0.3638, "step": 228650 }, { "epoch": 1.3592025250994169, "grad_norm": 6.665173530578613, "learning_rate": 9.127156009007082e-06, "loss": 0.3797, "step": 228660 }, { "epoch": 1.3592619671760853, "grad_norm": 5.566831588745117, "learning_rate": 9.127038875581183e-06, "loss": 0.3561, "step": 228670 }, { "epoch": 1.3593214092527537, "grad_norm": 5.4547119140625, "learning_rate": 9.126921735048029e-06, "loss": 0.3855, "step": 228680 }, { "epoch": 1.359380851329422, "grad_norm": 5.032756805419922, "learning_rate": 9.126804587407826e-06, "loss": 0.3914, "step": 228690 }, { "epoch": 1.3594402934060905, "grad_norm": 4.7439188957214355, "learning_rate": 9.126687432660772e-06, "loss": 0.3436, "step": 228700 }, { "epoch": 1.3594997354827587, "grad_norm": 5.85626745223999, "learning_rate": 9.12657027080707e-06, "loss": 0.3969, "step": 228710 }, { "epoch": 1.3595591775594271, "grad_norm": 3.7007710933685303, "learning_rate": 9.126453101846921e-06, "loss": 0.3417, "step": 228720 }, { "epoch": 1.3596186196360955, "grad_norm": 4.933771133422852, "learning_rate": 9.12633592578053e-06, "loss": 0.385, "step": 228730 }, { "epoch": 1.359678061712764, "grad_norm": 6.30407190322876, "learning_rate": 9.126218742608095e-06, "loss": 0.3769, "step": 228740 }, { "epoch": 1.3597375037894324, "grad_norm": 4.97770357131958, "learning_rate": 9.126101552329817e-06, "loss": 0.3546, "step": 228750 }, { "epoch": 1.3597969458661008, "grad_norm": 5.342926025390625, "learning_rate": 9.125984354945902e-06, "loss": 0.338, "step": 228760 }, { "epoch": 1.3598563879427692, "grad_norm": 5.119649410247803, "learning_rate": 9.125867150456548e-06, "loss": 0.3801, "step": 228770 }, { "epoch": 1.3599158300194376, "grad_norm": 4.5618577003479, "learning_rate": 9.12574993886196e-06, "loss": 0.393, "step": 228780 }, { "epoch": 1.359975272096106, "grad_norm": 4.091367721557617, "learning_rate": 9.125632720162337e-06, "loss": 0.3759, "step": 228790 }, { "epoch": 1.3600347141727744, "grad_norm": 5.217737197875977, "learning_rate": 9.125515494357883e-06, "loss": 0.3647, "step": 228800 }, { "epoch": 1.3600941562494429, "grad_norm": 7.4959564208984375, "learning_rate": 9.1253982614488e-06, "loss": 0.405, "step": 228810 }, { "epoch": 1.360153598326111, "grad_norm": 5.1395583152771, "learning_rate": 9.125281021435287e-06, "loss": 0.3562, "step": 228820 }, { "epoch": 1.3602130404027795, "grad_norm": 3.919038772583008, "learning_rate": 9.12516377431755e-06, "loss": 0.3881, "step": 228830 }, { "epoch": 1.3602724824794479, "grad_norm": 4.876099586486816, "learning_rate": 9.125046520095786e-06, "loss": 0.3389, "step": 228840 }, { "epoch": 1.3603319245561163, "grad_norm": 4.9632391929626465, "learning_rate": 9.1249292587702e-06, "loss": 0.3677, "step": 228850 }, { "epoch": 1.3603913666327847, "grad_norm": 4.238877773284912, "learning_rate": 9.124811990340996e-06, "loss": 0.346, "step": 228860 }, { "epoch": 1.3604508087094531, "grad_norm": 5.691020488739014, "learning_rate": 9.124694714808373e-06, "loss": 0.4036, "step": 228870 }, { "epoch": 1.3605102507861215, "grad_norm": 5.624436855316162, "learning_rate": 9.124577432172533e-06, "loss": 0.3887, "step": 228880 }, { "epoch": 1.3605696928627897, "grad_norm": 6.156968593597412, "learning_rate": 9.124460142433678e-06, "loss": 0.3406, "step": 228890 }, { "epoch": 1.3606291349394581, "grad_norm": 6.181517601013184, "learning_rate": 9.124342845592012e-06, "loss": 0.3878, "step": 228900 }, { "epoch": 1.3606885770161266, "grad_norm": 4.225375652313232, "learning_rate": 9.124225541647734e-06, "loss": 0.3565, "step": 228910 }, { "epoch": 1.360748019092795, "grad_norm": 5.891340732574463, "learning_rate": 9.124108230601047e-06, "loss": 0.3905, "step": 228920 }, { "epoch": 1.3608074611694634, "grad_norm": 4.4502153396606445, "learning_rate": 9.123990912452157e-06, "loss": 0.3788, "step": 228930 }, { "epoch": 1.3608669032461318, "grad_norm": 4.337221145629883, "learning_rate": 9.12387358720126e-06, "loss": 0.403, "step": 228940 }, { "epoch": 1.3609263453228002, "grad_norm": 5.861604690551758, "learning_rate": 9.12375625484856e-06, "loss": 0.4116, "step": 228950 }, { "epoch": 1.3609857873994686, "grad_norm": 4.754542827606201, "learning_rate": 9.12363891539426e-06, "loss": 0.3686, "step": 228960 }, { "epoch": 1.361045229476137, "grad_norm": 6.030790328979492, "learning_rate": 9.123521568838563e-06, "loss": 0.3697, "step": 228970 }, { "epoch": 1.3611046715528055, "grad_norm": 8.375592231750488, "learning_rate": 9.123404215181669e-06, "loss": 0.3828, "step": 228980 }, { "epoch": 1.3611641136294739, "grad_norm": 5.682888031005859, "learning_rate": 9.12328685442378e-06, "loss": 0.3771, "step": 228990 }, { "epoch": 1.3612235557061423, "grad_norm": 6.405819416046143, "learning_rate": 9.1231694865651e-06, "loss": 0.4034, "step": 229000 }, { "epoch": 1.3612829977828105, "grad_norm": 5.282705783843994, "learning_rate": 9.123052111605831e-06, "loss": 0.3955, "step": 229010 }, { "epoch": 1.361342439859479, "grad_norm": 3.937617063522339, "learning_rate": 9.122934729546174e-06, "loss": 0.4087, "step": 229020 }, { "epoch": 1.3614018819361473, "grad_norm": 5.057582378387451, "learning_rate": 9.12281734038633e-06, "loss": 0.3525, "step": 229030 }, { "epoch": 1.3614613240128157, "grad_norm": 4.886786460876465, "learning_rate": 9.122699944126505e-06, "loss": 0.3979, "step": 229040 }, { "epoch": 1.3615207660894841, "grad_norm": 4.850895404815674, "learning_rate": 9.122582540766896e-06, "loss": 0.3657, "step": 229050 }, { "epoch": 1.3615802081661526, "grad_norm": 5.940548419952393, "learning_rate": 9.12246513030771e-06, "loss": 0.3705, "step": 229060 }, { "epoch": 1.361639650242821, "grad_norm": 4.661940574645996, "learning_rate": 9.122347712749147e-06, "loss": 0.334, "step": 229070 }, { "epoch": 1.3616990923194892, "grad_norm": 5.371415615081787, "learning_rate": 9.122230288091409e-06, "loss": 0.3849, "step": 229080 }, { "epoch": 1.3617585343961576, "grad_norm": 5.6965789794921875, "learning_rate": 9.122112856334699e-06, "loss": 0.3705, "step": 229090 }, { "epoch": 1.361817976472826, "grad_norm": 4.740911960601807, "learning_rate": 9.121995417479217e-06, "loss": 0.408, "step": 229100 }, { "epoch": 1.3618774185494944, "grad_norm": 4.101311206817627, "learning_rate": 9.12187797152517e-06, "loss": 0.3907, "step": 229110 }, { "epoch": 1.3619368606261628, "grad_norm": 6.727740287780762, "learning_rate": 9.121760518472755e-06, "loss": 0.426, "step": 229120 }, { "epoch": 1.3619963027028312, "grad_norm": 4.206009387969971, "learning_rate": 9.121643058322178e-06, "loss": 0.3891, "step": 229130 }, { "epoch": 1.3620557447794996, "grad_norm": 5.565295696258545, "learning_rate": 9.121525591073639e-06, "loss": 0.3803, "step": 229140 }, { "epoch": 1.362115186856168, "grad_norm": 5.224750518798828, "learning_rate": 9.121408116727341e-06, "loss": 0.3897, "step": 229150 }, { "epoch": 1.3621746289328365, "grad_norm": 3.2536895275115967, "learning_rate": 9.121290635283487e-06, "loss": 0.3759, "step": 229160 }, { "epoch": 1.3622340710095049, "grad_norm": 5.155941009521484, "learning_rate": 9.121173146742278e-06, "loss": 0.39, "step": 229170 }, { "epoch": 1.3622935130861733, "grad_norm": 5.509160041809082, "learning_rate": 9.121055651103918e-06, "loss": 0.3849, "step": 229180 }, { "epoch": 1.3623529551628415, "grad_norm": 5.255130767822266, "learning_rate": 9.120938148368609e-06, "loss": 0.3787, "step": 229190 }, { "epoch": 1.36241239723951, "grad_norm": 4.800874710083008, "learning_rate": 9.120820638536552e-06, "loss": 0.3499, "step": 229200 }, { "epoch": 1.3624718393161783, "grad_norm": 4.650317192077637, "learning_rate": 9.12070312160795e-06, "loss": 0.3754, "step": 229210 }, { "epoch": 1.3625312813928467, "grad_norm": 3.9075052738189697, "learning_rate": 9.120585597583006e-06, "loss": 0.333, "step": 229220 }, { "epoch": 1.3625907234695152, "grad_norm": 6.657644271850586, "learning_rate": 9.120468066461921e-06, "loss": 0.3994, "step": 229230 }, { "epoch": 1.3626501655461836, "grad_norm": 4.2236247062683105, "learning_rate": 9.1203505282449e-06, "loss": 0.3933, "step": 229240 }, { "epoch": 1.362709607622852, "grad_norm": 6.335010051727295, "learning_rate": 9.120232982932142e-06, "loss": 0.4125, "step": 229250 }, { "epoch": 1.3627690496995202, "grad_norm": 6.110003471374512, "learning_rate": 9.120115430523852e-06, "loss": 0.4159, "step": 229260 }, { "epoch": 1.3628284917761886, "grad_norm": 7.921304225921631, "learning_rate": 9.11999787102023e-06, "loss": 0.3418, "step": 229270 }, { "epoch": 1.362887933852857, "grad_norm": 5.6992645263671875, "learning_rate": 9.119880304421482e-06, "loss": 0.3837, "step": 229280 }, { "epoch": 1.3629473759295254, "grad_norm": 5.272532939910889, "learning_rate": 9.119762730727808e-06, "loss": 0.4268, "step": 229290 }, { "epoch": 1.3630068180061938, "grad_norm": 4.850693225860596, "learning_rate": 9.119645149939412e-06, "loss": 0.3748, "step": 229300 }, { "epoch": 1.3630662600828622, "grad_norm": 4.475638389587402, "learning_rate": 9.119527562056495e-06, "loss": 0.3819, "step": 229310 }, { "epoch": 1.3631257021595307, "grad_norm": 3.465297222137451, "learning_rate": 9.11940996707926e-06, "loss": 0.4169, "step": 229320 }, { "epoch": 1.363185144236199, "grad_norm": 5.327980995178223, "learning_rate": 9.119292365007907e-06, "loss": 0.3717, "step": 229330 }, { "epoch": 1.3632445863128675, "grad_norm": 4.557621479034424, "learning_rate": 9.119174755842645e-06, "loss": 0.3797, "step": 229340 }, { "epoch": 1.363304028389536, "grad_norm": 7.235947132110596, "learning_rate": 9.119057139583672e-06, "loss": 0.4364, "step": 229350 }, { "epoch": 1.3633634704662043, "grad_norm": 4.435528755187988, "learning_rate": 9.118939516231189e-06, "loss": 0.3404, "step": 229360 }, { "epoch": 1.3634229125428727, "grad_norm": 4.777390956878662, "learning_rate": 9.1188218857854e-06, "loss": 0.3869, "step": 229370 }, { "epoch": 1.363482354619541, "grad_norm": 5.148366451263428, "learning_rate": 9.118704248246511e-06, "loss": 0.3758, "step": 229380 }, { "epoch": 1.3635417966962093, "grad_norm": 4.646501541137695, "learning_rate": 9.11858660361472e-06, "loss": 0.4329, "step": 229390 }, { "epoch": 1.3636012387728778, "grad_norm": 5.278763294219971, "learning_rate": 9.118468951890234e-06, "loss": 0.3481, "step": 229400 }, { "epoch": 1.3636606808495462, "grad_norm": 5.485452651977539, "learning_rate": 9.11835129307325e-06, "loss": 0.3804, "step": 229410 }, { "epoch": 1.3637201229262146, "grad_norm": 5.065253257751465, "learning_rate": 9.118233627163974e-06, "loss": 0.3878, "step": 229420 }, { "epoch": 1.363779565002883, "grad_norm": 3.9559476375579834, "learning_rate": 9.118115954162611e-06, "loss": 0.3869, "step": 229430 }, { "epoch": 1.3638390070795514, "grad_norm": 4.745145797729492, "learning_rate": 9.117998274069358e-06, "loss": 0.3975, "step": 229440 }, { "epoch": 1.3638984491562196, "grad_norm": 3.9084739685058594, "learning_rate": 9.117880586884423e-06, "loss": 0.3415, "step": 229450 }, { "epoch": 1.363957891232888, "grad_norm": 4.94858980178833, "learning_rate": 9.117762892608004e-06, "loss": 0.3577, "step": 229460 }, { "epoch": 1.3640173333095564, "grad_norm": 5.896417617797852, "learning_rate": 9.117645191240307e-06, "loss": 0.3642, "step": 229470 }, { "epoch": 1.3640767753862248, "grad_norm": 6.399606704711914, "learning_rate": 9.117527482781535e-06, "loss": 0.402, "step": 229480 }, { "epoch": 1.3641362174628933, "grad_norm": 5.694960594177246, "learning_rate": 9.117409767231888e-06, "loss": 0.4101, "step": 229490 }, { "epoch": 1.3641956595395617, "grad_norm": 3.0381271839141846, "learning_rate": 9.11729204459157e-06, "loss": 0.3514, "step": 229500 }, { "epoch": 1.36425510161623, "grad_norm": 4.5496344566345215, "learning_rate": 9.117174314860783e-06, "loss": 0.3498, "step": 229510 }, { "epoch": 1.3643145436928985, "grad_norm": 5.0989789962768555, "learning_rate": 9.117056578039733e-06, "loss": 0.394, "step": 229520 }, { "epoch": 1.364373985769567, "grad_norm": 3.660571336746216, "learning_rate": 9.116938834128619e-06, "loss": 0.3934, "step": 229530 }, { "epoch": 1.3644334278462353, "grad_norm": 4.880977630615234, "learning_rate": 9.116821083127645e-06, "loss": 0.3543, "step": 229540 }, { "epoch": 1.3644928699229038, "grad_norm": 5.0846381187438965, "learning_rate": 9.116703325037013e-06, "loss": 0.3679, "step": 229550 }, { "epoch": 1.364552311999572, "grad_norm": 6.301589012145996, "learning_rate": 9.116585559856929e-06, "loss": 0.3785, "step": 229560 }, { "epoch": 1.3646117540762404, "grad_norm": 5.000483512878418, "learning_rate": 9.116467787587592e-06, "loss": 0.3733, "step": 229570 }, { "epoch": 1.3646711961529088, "grad_norm": 5.329992771148682, "learning_rate": 9.116350008229206e-06, "loss": 0.3777, "step": 229580 }, { "epoch": 1.3647306382295772, "grad_norm": 4.271628379821777, "learning_rate": 9.116232221781976e-06, "loss": 0.3609, "step": 229590 }, { "epoch": 1.3647900803062456, "grad_norm": 4.557328701019287, "learning_rate": 9.1161144282461e-06, "loss": 0.3556, "step": 229600 }, { "epoch": 1.364849522382914, "grad_norm": 4.821113109588623, "learning_rate": 9.115996627621786e-06, "loss": 0.4568, "step": 229610 }, { "epoch": 1.3649089644595824, "grad_norm": 4.563065052032471, "learning_rate": 9.115878819909235e-06, "loss": 0.3716, "step": 229620 }, { "epoch": 1.3649684065362506, "grad_norm": 6.290095806121826, "learning_rate": 9.115761005108647e-06, "loss": 0.387, "step": 229630 }, { "epoch": 1.365027848612919, "grad_norm": 5.440983772277832, "learning_rate": 9.11564318322023e-06, "loss": 0.3929, "step": 229640 }, { "epoch": 1.3650872906895875, "grad_norm": 6.526583194732666, "learning_rate": 9.115525354244184e-06, "loss": 0.3699, "step": 229650 }, { "epoch": 1.3651467327662559, "grad_norm": 4.81964111328125, "learning_rate": 9.11540751818071e-06, "loss": 0.3782, "step": 229660 }, { "epoch": 1.3652061748429243, "grad_norm": 4.113694667816162, "learning_rate": 9.115289675030016e-06, "loss": 0.3495, "step": 229670 }, { "epoch": 1.3652656169195927, "grad_norm": 5.340234756469727, "learning_rate": 9.115171824792301e-06, "loss": 0.3822, "step": 229680 }, { "epoch": 1.365325058996261, "grad_norm": 4.63438081741333, "learning_rate": 9.115053967467768e-06, "loss": 0.3529, "step": 229690 }, { "epoch": 1.3653845010729295, "grad_norm": 5.761673450469971, "learning_rate": 9.114936103056625e-06, "loss": 0.393, "step": 229700 }, { "epoch": 1.365443943149598, "grad_norm": 4.904240131378174, "learning_rate": 9.114818231559066e-06, "loss": 0.3829, "step": 229710 }, { "epoch": 1.3655033852262664, "grad_norm": 5.4033989906311035, "learning_rate": 9.114700352975301e-06, "loss": 0.3632, "step": 229720 }, { "epoch": 1.3655628273029348, "grad_norm": 4.249139308929443, "learning_rate": 9.114582467305532e-06, "loss": 0.4181, "step": 229730 }, { "epoch": 1.3656222693796032, "grad_norm": 4.5045695304870605, "learning_rate": 9.114464574549962e-06, "loss": 0.3839, "step": 229740 }, { "epoch": 1.3656817114562714, "grad_norm": 6.473053932189941, "learning_rate": 9.114346674708791e-06, "loss": 0.3766, "step": 229750 }, { "epoch": 1.3657411535329398, "grad_norm": 4.927706241607666, "learning_rate": 9.114228767782225e-06, "loss": 0.3517, "step": 229760 }, { "epoch": 1.3658005956096082, "grad_norm": 4.165980339050293, "learning_rate": 9.114110853770465e-06, "loss": 0.369, "step": 229770 }, { "epoch": 1.3658600376862766, "grad_norm": 4.7865753173828125, "learning_rate": 9.113992932673717e-06, "loss": 0.3762, "step": 229780 }, { "epoch": 1.365919479762945, "grad_norm": 4.604431629180908, "learning_rate": 9.11387500449218e-06, "loss": 0.3449, "step": 229790 }, { "epoch": 1.3659789218396134, "grad_norm": 4.340435028076172, "learning_rate": 9.113757069226061e-06, "loss": 0.3527, "step": 229800 }, { "epoch": 1.3660383639162819, "grad_norm": 4.977412700653076, "learning_rate": 9.113639126875561e-06, "loss": 0.3979, "step": 229810 }, { "epoch": 1.36609780599295, "grad_norm": 4.3538079261779785, "learning_rate": 9.113521177440884e-06, "loss": 0.379, "step": 229820 }, { "epoch": 1.3661572480696185, "grad_norm": 6.13369083404541, "learning_rate": 9.113403220922232e-06, "loss": 0.3831, "step": 229830 }, { "epoch": 1.3662166901462869, "grad_norm": 6.739216327667236, "learning_rate": 9.113285257319809e-06, "loss": 0.3536, "step": 229840 }, { "epoch": 1.3662761322229553, "grad_norm": 6.232117176055908, "learning_rate": 9.113167286633819e-06, "loss": 0.3536, "step": 229850 }, { "epoch": 1.3663355742996237, "grad_norm": 5.554931163787842, "learning_rate": 9.113049308864464e-06, "loss": 0.3574, "step": 229860 }, { "epoch": 1.3663950163762921, "grad_norm": 5.414205074310303, "learning_rate": 9.112931324011946e-06, "loss": 0.365, "step": 229870 }, { "epoch": 1.3664544584529605, "grad_norm": 4.7283735275268555, "learning_rate": 9.112813332076471e-06, "loss": 0.4284, "step": 229880 }, { "epoch": 1.366513900529629, "grad_norm": 6.095282077789307, "learning_rate": 9.112695333058239e-06, "loss": 0.3787, "step": 229890 }, { "epoch": 1.3665733426062974, "grad_norm": 6.307525634765625, "learning_rate": 9.112577326957457e-06, "loss": 0.4294, "step": 229900 }, { "epoch": 1.3666327846829658, "grad_norm": 4.745154857635498, "learning_rate": 9.112459313774325e-06, "loss": 0.3822, "step": 229910 }, { "epoch": 1.3666922267596342, "grad_norm": 4.673131942749023, "learning_rate": 9.112341293509047e-06, "loss": 0.382, "step": 229920 }, { "epoch": 1.3667516688363024, "grad_norm": 4.574262619018555, "learning_rate": 9.112223266161827e-06, "loss": 0.3789, "step": 229930 }, { "epoch": 1.3668111109129708, "grad_norm": 5.646036148071289, "learning_rate": 9.112105231732869e-06, "loss": 0.3619, "step": 229940 }, { "epoch": 1.3668705529896392, "grad_norm": 6.150104522705078, "learning_rate": 9.111987190222373e-06, "loss": 0.3741, "step": 229950 }, { "epoch": 1.3669299950663076, "grad_norm": 6.020632743835449, "learning_rate": 9.111869141630546e-06, "loss": 0.3667, "step": 229960 }, { "epoch": 1.366989437142976, "grad_norm": 4.92063045501709, "learning_rate": 9.11175108595759e-06, "loss": 0.4038, "step": 229970 }, { "epoch": 1.3670488792196445, "grad_norm": 6.821527004241943, "learning_rate": 9.111633023203707e-06, "loss": 0.382, "step": 229980 }, { "epoch": 1.3671083212963129, "grad_norm": 5.723916530609131, "learning_rate": 9.1115149533691e-06, "loss": 0.3499, "step": 229990 }, { "epoch": 1.367167763372981, "grad_norm": 8.186944961547852, "learning_rate": 9.111396876453977e-06, "loss": 0.4439, "step": 230000 }, { "epoch": 1.3672272054496495, "grad_norm": 5.9900665283203125, "learning_rate": 9.111278792458535e-06, "loss": 0.418, "step": 230010 }, { "epoch": 1.367286647526318, "grad_norm": 5.702118873596191, "learning_rate": 9.111160701382981e-06, "loss": 0.4364, "step": 230020 }, { "epoch": 1.3673460896029863, "grad_norm": 6.152092456817627, "learning_rate": 9.11104260322752e-06, "loss": 0.3937, "step": 230030 }, { "epoch": 1.3674055316796547, "grad_norm": 5.362644195556641, "learning_rate": 9.11092449799235e-06, "loss": 0.4001, "step": 230040 }, { "epoch": 1.3674649737563231, "grad_norm": 5.631868839263916, "learning_rate": 9.11080638567768e-06, "loss": 0.3263, "step": 230050 }, { "epoch": 1.3675244158329916, "grad_norm": 4.478231430053711, "learning_rate": 9.11068826628371e-06, "loss": 0.4092, "step": 230060 }, { "epoch": 1.36758385790966, "grad_norm": 6.172242164611816, "learning_rate": 9.110570139810643e-06, "loss": 0.4635, "step": 230070 }, { "epoch": 1.3676432999863284, "grad_norm": 5.728280544281006, "learning_rate": 9.110452006258686e-06, "loss": 0.3845, "step": 230080 }, { "epoch": 1.3677027420629968, "grad_norm": 4.935756683349609, "learning_rate": 9.110333865628041e-06, "loss": 0.3599, "step": 230090 }, { "epoch": 1.3677621841396652, "grad_norm": 6.4222731590271, "learning_rate": 9.110215717918908e-06, "loss": 0.3842, "step": 230100 }, { "epoch": 1.3678216262163336, "grad_norm": 5.6266770362854, "learning_rate": 9.110097563131494e-06, "loss": 0.4141, "step": 230110 }, { "epoch": 1.3678810682930018, "grad_norm": 4.695816993713379, "learning_rate": 9.109979401266e-06, "loss": 0.3626, "step": 230120 }, { "epoch": 1.3679405103696702, "grad_norm": 5.781668663024902, "learning_rate": 9.109861232322634e-06, "loss": 0.3781, "step": 230130 }, { "epoch": 1.3679999524463387, "grad_norm": 4.829800605773926, "learning_rate": 9.109743056301595e-06, "loss": 0.3591, "step": 230140 }, { "epoch": 1.368059394523007, "grad_norm": 5.203527450561523, "learning_rate": 9.109624873203088e-06, "loss": 0.3513, "step": 230150 }, { "epoch": 1.3681188365996755, "grad_norm": 4.369701862335205, "learning_rate": 9.109506683027317e-06, "loss": 0.3757, "step": 230160 }, { "epoch": 1.368178278676344, "grad_norm": 6.809126853942871, "learning_rate": 9.109388485774485e-06, "loss": 0.365, "step": 230170 }, { "epoch": 1.3682377207530123, "grad_norm": 5.305285453796387, "learning_rate": 9.109270281444795e-06, "loss": 0.3935, "step": 230180 }, { "epoch": 1.3682971628296805, "grad_norm": 7.712368488311768, "learning_rate": 9.109152070038454e-06, "loss": 0.4062, "step": 230190 }, { "epoch": 1.368356604906349, "grad_norm": 4.928075790405273, "learning_rate": 9.10903385155566e-06, "loss": 0.4016, "step": 230200 }, { "epoch": 1.3684160469830173, "grad_norm": 6.451671600341797, "learning_rate": 9.108915625996621e-06, "loss": 0.373, "step": 230210 }, { "epoch": 1.3684754890596857, "grad_norm": 4.814346790313721, "learning_rate": 9.108797393361537e-06, "loss": 0.4272, "step": 230220 }, { "epoch": 1.3685349311363542, "grad_norm": 4.641756057739258, "learning_rate": 9.108679153650615e-06, "loss": 0.4035, "step": 230230 }, { "epoch": 1.3685943732130226, "grad_norm": 6.000851154327393, "learning_rate": 9.108560906864058e-06, "loss": 0.3854, "step": 230240 }, { "epoch": 1.368653815289691, "grad_norm": 4.698038101196289, "learning_rate": 9.108442653002067e-06, "loss": 0.3991, "step": 230250 }, { "epoch": 1.3687132573663594, "grad_norm": 4.255537986755371, "learning_rate": 9.108324392064849e-06, "loss": 0.3331, "step": 230260 }, { "epoch": 1.3687726994430278, "grad_norm": 5.613856315612793, "learning_rate": 9.108206124052607e-06, "loss": 0.4348, "step": 230270 }, { "epoch": 1.3688321415196962, "grad_norm": 4.119487285614014, "learning_rate": 9.108087848965542e-06, "loss": 0.4084, "step": 230280 }, { "epoch": 1.3688915835963646, "grad_norm": 5.038297653198242, "learning_rate": 9.10796956680386e-06, "loss": 0.368, "step": 230290 }, { "epoch": 1.3689510256730328, "grad_norm": 4.072024822235107, "learning_rate": 9.107851277567766e-06, "loss": 0.3293, "step": 230300 }, { "epoch": 1.3690104677497013, "grad_norm": 6.078791618347168, "learning_rate": 9.10773298125746e-06, "loss": 0.3948, "step": 230310 }, { "epoch": 1.3690699098263697, "grad_norm": 5.341633319854736, "learning_rate": 9.107614677873147e-06, "loss": 0.4181, "step": 230320 }, { "epoch": 1.369129351903038, "grad_norm": 5.602383613586426, "learning_rate": 9.107496367415033e-06, "loss": 0.3739, "step": 230330 }, { "epoch": 1.3691887939797065, "grad_norm": 6.284890174865723, "learning_rate": 9.10737804988332e-06, "loss": 0.3697, "step": 230340 }, { "epoch": 1.369248236056375, "grad_norm": 4.6502790451049805, "learning_rate": 9.107259725278212e-06, "loss": 0.417, "step": 230350 }, { "epoch": 1.3693076781330433, "grad_norm": 5.51118803024292, "learning_rate": 9.107141393599912e-06, "loss": 0.4082, "step": 230360 }, { "epoch": 1.3693671202097115, "grad_norm": 5.471754550933838, "learning_rate": 9.107023054848625e-06, "loss": 0.3836, "step": 230370 }, { "epoch": 1.36942656228638, "grad_norm": 3.7927162647247314, "learning_rate": 9.106904709024553e-06, "loss": 0.383, "step": 230380 }, { "epoch": 1.3694860043630483, "grad_norm": 5.3894267082214355, "learning_rate": 9.106786356127904e-06, "loss": 0.4413, "step": 230390 }, { "epoch": 1.3695454464397168, "grad_norm": 5.026391983032227, "learning_rate": 9.106667996158876e-06, "loss": 0.3714, "step": 230400 }, { "epoch": 1.3696048885163852, "grad_norm": 5.744479179382324, "learning_rate": 9.106549629117676e-06, "loss": 0.4016, "step": 230410 }, { "epoch": 1.3696643305930536, "grad_norm": 3.0937488079071045, "learning_rate": 9.106431255004508e-06, "loss": 0.3395, "step": 230420 }, { "epoch": 1.369723772669722, "grad_norm": 4.172908306121826, "learning_rate": 9.106312873819575e-06, "loss": 0.3289, "step": 230430 }, { "epoch": 1.3697832147463904, "grad_norm": 6.892511367797852, "learning_rate": 9.106194485563083e-06, "loss": 0.3851, "step": 230440 }, { "epoch": 1.3698426568230588, "grad_norm": 4.915607929229736, "learning_rate": 9.106076090235235e-06, "loss": 0.3554, "step": 230450 }, { "epoch": 1.3699020988997272, "grad_norm": 4.616130828857422, "learning_rate": 9.105957687836232e-06, "loss": 0.3996, "step": 230460 }, { "epoch": 1.3699615409763957, "grad_norm": 7.043684005737305, "learning_rate": 9.10583927836628e-06, "loss": 0.4262, "step": 230470 }, { "epoch": 1.370020983053064, "grad_norm": 5.991319179534912, "learning_rate": 9.105720861825583e-06, "loss": 0.4179, "step": 230480 }, { "epoch": 1.3700804251297323, "grad_norm": 5.3081746101379395, "learning_rate": 9.105602438214342e-06, "loss": 0.3493, "step": 230490 }, { "epoch": 1.3701398672064007, "grad_norm": 6.791470527648926, "learning_rate": 9.105484007532768e-06, "loss": 0.4, "step": 230500 }, { "epoch": 1.370199309283069, "grad_norm": 3.721393585205078, "learning_rate": 9.10536556978106e-06, "loss": 0.3902, "step": 230510 }, { "epoch": 1.3702587513597375, "grad_norm": 3.5100505352020264, "learning_rate": 9.10524712495942e-06, "loss": 0.3635, "step": 230520 }, { "epoch": 1.370318193436406, "grad_norm": 5.029826641082764, "learning_rate": 9.105128673068057e-06, "loss": 0.3662, "step": 230530 }, { "epoch": 1.3703776355130743, "grad_norm": 4.5507707595825195, "learning_rate": 9.105010214107173e-06, "loss": 0.3775, "step": 230540 }, { "epoch": 1.3704370775897428, "grad_norm": 5.4327778816223145, "learning_rate": 9.10489174807697e-06, "loss": 0.3584, "step": 230550 }, { "epoch": 1.370496519666411, "grad_norm": 4.964379787445068, "learning_rate": 9.104773274977655e-06, "loss": 0.3683, "step": 230560 }, { "epoch": 1.3705559617430794, "grad_norm": 5.278062343597412, "learning_rate": 9.10465479480943e-06, "loss": 0.4155, "step": 230570 }, { "epoch": 1.3706154038197478, "grad_norm": 6.34873628616333, "learning_rate": 9.104536307572499e-06, "loss": 0.3931, "step": 230580 }, { "epoch": 1.3706748458964162, "grad_norm": 4.797345161437988, "learning_rate": 9.104417813267067e-06, "loss": 0.3835, "step": 230590 }, { "epoch": 1.3707342879730846, "grad_norm": 4.43766450881958, "learning_rate": 9.10429931189334e-06, "loss": 0.3868, "step": 230600 }, { "epoch": 1.370793730049753, "grad_norm": 3.2594521045684814, "learning_rate": 9.104180803451517e-06, "loss": 0.3393, "step": 230610 }, { "epoch": 1.3708531721264214, "grad_norm": 6.228961944580078, "learning_rate": 9.104062287941806e-06, "loss": 0.385, "step": 230620 }, { "epoch": 1.3709126142030899, "grad_norm": 4.7315778732299805, "learning_rate": 9.10394376536441e-06, "loss": 0.3724, "step": 230630 }, { "epoch": 1.3709720562797583, "grad_norm": 4.631433963775635, "learning_rate": 9.103825235719533e-06, "loss": 0.4167, "step": 230640 }, { "epoch": 1.3710314983564267, "grad_norm": 4.289194583892822, "learning_rate": 9.103706699007379e-06, "loss": 0.4081, "step": 230650 }, { "epoch": 1.371090940433095, "grad_norm": 4.535419940948486, "learning_rate": 9.103588155228152e-06, "loss": 0.3772, "step": 230660 }, { "epoch": 1.3711503825097633, "grad_norm": 4.5629730224609375, "learning_rate": 9.103469604382059e-06, "loss": 0.3921, "step": 230670 }, { "epoch": 1.3712098245864317, "grad_norm": 5.990062713623047, "learning_rate": 9.103351046469299e-06, "loss": 0.4135, "step": 230680 }, { "epoch": 1.3712692666631001, "grad_norm": 5.067467212677002, "learning_rate": 9.10323248149008e-06, "loss": 0.3715, "step": 230690 }, { "epoch": 1.3713287087397685, "grad_norm": 4.72227668762207, "learning_rate": 9.103113909444605e-06, "loss": 0.382, "step": 230700 }, { "epoch": 1.371388150816437, "grad_norm": 5.015393257141113, "learning_rate": 9.102995330333078e-06, "loss": 0.3412, "step": 230710 }, { "epoch": 1.3714475928931054, "grad_norm": 5.345669746398926, "learning_rate": 9.102876744155705e-06, "loss": 0.3564, "step": 230720 }, { "epoch": 1.3715070349697738, "grad_norm": 6.079336643218994, "learning_rate": 9.102758150912688e-06, "loss": 0.3514, "step": 230730 }, { "epoch": 1.371566477046442, "grad_norm": 4.351900577545166, "learning_rate": 9.102639550604231e-06, "loss": 0.3833, "step": 230740 }, { "epoch": 1.3716259191231104, "grad_norm": 5.3816633224487305, "learning_rate": 9.10252094323054e-06, "loss": 0.3826, "step": 230750 }, { "epoch": 1.3716853611997788, "grad_norm": 5.621718883514404, "learning_rate": 9.102402328791817e-06, "loss": 0.3639, "step": 230760 }, { "epoch": 1.3717448032764472, "grad_norm": 5.359347820281982, "learning_rate": 9.102283707288269e-06, "loss": 0.3571, "step": 230770 }, { "epoch": 1.3718042453531156, "grad_norm": 4.623016357421875, "learning_rate": 9.1021650787201e-06, "loss": 0.4118, "step": 230780 }, { "epoch": 1.371863687429784, "grad_norm": 4.2897748947143555, "learning_rate": 9.102046443087511e-06, "loss": 0.3896, "step": 230790 }, { "epoch": 1.3719231295064525, "grad_norm": 6.408973693847656, "learning_rate": 9.10192780039071e-06, "loss": 0.4233, "step": 230800 }, { "epoch": 1.3719825715831209, "grad_norm": 5.662176609039307, "learning_rate": 9.1018091506299e-06, "loss": 0.3513, "step": 230810 }, { "epoch": 1.3720420136597893, "grad_norm": 3.5177671909332275, "learning_rate": 9.101690493805284e-06, "loss": 0.3811, "step": 230820 }, { "epoch": 1.3721014557364577, "grad_norm": 4.9131999015808105, "learning_rate": 9.101571829917068e-06, "loss": 0.3624, "step": 230830 }, { "epoch": 1.3721608978131261, "grad_norm": 5.196233749389648, "learning_rate": 9.101453158965457e-06, "loss": 0.4107, "step": 230840 }, { "epoch": 1.3722203398897945, "grad_norm": 5.596948623657227, "learning_rate": 9.101334480950652e-06, "loss": 0.3577, "step": 230850 }, { "epoch": 1.3722797819664627, "grad_norm": 4.724248886108398, "learning_rate": 9.101215795872862e-06, "loss": 0.3729, "step": 230860 }, { "epoch": 1.3723392240431311, "grad_norm": 4.778316020965576, "learning_rate": 9.101097103732288e-06, "loss": 0.3841, "step": 230870 }, { "epoch": 1.3723986661197995, "grad_norm": 5.611104965209961, "learning_rate": 9.100978404529135e-06, "loss": 0.4006, "step": 230880 }, { "epoch": 1.372458108196468, "grad_norm": 5.376940727233887, "learning_rate": 9.100859698263608e-06, "loss": 0.3654, "step": 230890 }, { "epoch": 1.3725175502731364, "grad_norm": 4.119708061218262, "learning_rate": 9.100740984935913e-06, "loss": 0.3678, "step": 230900 }, { "epoch": 1.3725769923498048, "grad_norm": 4.146629810333252, "learning_rate": 9.100622264546252e-06, "loss": 0.3415, "step": 230910 }, { "epoch": 1.3726364344264732, "grad_norm": 4.673541069030762, "learning_rate": 9.100503537094829e-06, "loss": 0.3873, "step": 230920 }, { "epoch": 1.3726958765031414, "grad_norm": 6.114426612854004, "learning_rate": 9.10038480258185e-06, "loss": 0.425, "step": 230930 }, { "epoch": 1.3727553185798098, "grad_norm": 4.956153869628906, "learning_rate": 9.100266061007521e-06, "loss": 0.3664, "step": 230940 }, { "epoch": 1.3728147606564782, "grad_norm": 6.262927532196045, "learning_rate": 9.100147312372042e-06, "loss": 0.4082, "step": 230950 }, { "epoch": 1.3728742027331466, "grad_norm": 5.439023017883301, "learning_rate": 9.100028556675622e-06, "loss": 0.3811, "step": 230960 }, { "epoch": 1.372933644809815, "grad_norm": 5.215280532836914, "learning_rate": 9.099909793918463e-06, "loss": 0.3557, "step": 230970 }, { "epoch": 1.3729930868864835, "grad_norm": 5.860511779785156, "learning_rate": 9.09979102410077e-06, "loss": 0.3753, "step": 230980 }, { "epoch": 1.3730525289631519, "grad_norm": 5.681299686431885, "learning_rate": 9.099672247222748e-06, "loss": 0.3642, "step": 230990 }, { "epoch": 1.3731119710398203, "grad_norm": 5.45789098739624, "learning_rate": 9.099553463284601e-06, "loss": 0.4015, "step": 231000 }, { "epoch": 1.3731714131164887, "grad_norm": 4.734901428222656, "learning_rate": 9.099434672286533e-06, "loss": 0.3922, "step": 231010 }, { "epoch": 1.3732308551931571, "grad_norm": 6.034422874450684, "learning_rate": 9.09931587422875e-06, "loss": 0.3808, "step": 231020 }, { "epoch": 1.3732902972698255, "grad_norm": 4.980885982513428, "learning_rate": 9.099197069111455e-06, "loss": 0.3389, "step": 231030 }, { "epoch": 1.3733497393464937, "grad_norm": 6.27148962020874, "learning_rate": 9.099078256934855e-06, "loss": 0.3571, "step": 231040 }, { "epoch": 1.3734091814231622, "grad_norm": 6.134925842285156, "learning_rate": 9.098959437699153e-06, "loss": 0.3882, "step": 231050 }, { "epoch": 1.3734686234998306, "grad_norm": 3.947521209716797, "learning_rate": 9.098840611404554e-06, "loss": 0.3648, "step": 231060 }, { "epoch": 1.373528065576499, "grad_norm": 5.622143268585205, "learning_rate": 9.098721778051262e-06, "loss": 0.3524, "step": 231070 }, { "epoch": 1.3735875076531674, "grad_norm": 6.220335960388184, "learning_rate": 9.09860293763948e-06, "loss": 0.3763, "step": 231080 }, { "epoch": 1.3736469497298358, "grad_norm": 5.661426067352295, "learning_rate": 9.098484090169417e-06, "loss": 0.3677, "step": 231090 }, { "epoch": 1.3737063918065042, "grad_norm": 5.4071807861328125, "learning_rate": 9.098365235641276e-06, "loss": 0.408, "step": 231100 }, { "epoch": 1.3737658338831724, "grad_norm": 4.741203784942627, "learning_rate": 9.09824637405526e-06, "loss": 0.3796, "step": 231110 }, { "epoch": 1.3738252759598408, "grad_norm": 5.744628429412842, "learning_rate": 9.098127505411575e-06, "loss": 0.3381, "step": 231120 }, { "epoch": 1.3738847180365092, "grad_norm": 5.4225335121154785, "learning_rate": 9.098008629710424e-06, "loss": 0.3842, "step": 231130 }, { "epoch": 1.3739441601131777, "grad_norm": 3.818950653076172, "learning_rate": 9.097889746952015e-06, "loss": 0.3659, "step": 231140 }, { "epoch": 1.374003602189846, "grad_norm": 5.390066623687744, "learning_rate": 9.09777085713655e-06, "loss": 0.352, "step": 231150 }, { "epoch": 1.3740630442665145, "grad_norm": 5.876979827880859, "learning_rate": 9.097651960264236e-06, "loss": 0.3686, "step": 231160 }, { "epoch": 1.374122486343183, "grad_norm": 5.243257522583008, "learning_rate": 9.097533056335274e-06, "loss": 0.3922, "step": 231170 }, { "epoch": 1.3741819284198513, "grad_norm": 4.458412170410156, "learning_rate": 9.097414145349873e-06, "loss": 0.4118, "step": 231180 }, { "epoch": 1.3742413704965197, "grad_norm": 4.930961608886719, "learning_rate": 9.097295227308237e-06, "loss": 0.3798, "step": 231190 }, { "epoch": 1.3743008125731881, "grad_norm": 5.626485824584961, "learning_rate": 9.097176302210567e-06, "loss": 0.4309, "step": 231200 }, { "epoch": 1.3743602546498566, "grad_norm": 3.6680686473846436, "learning_rate": 9.097057370057072e-06, "loss": 0.3257, "step": 231210 }, { "epoch": 1.374419696726525, "grad_norm": 5.369558334350586, "learning_rate": 9.096938430847955e-06, "loss": 0.3764, "step": 231220 }, { "epoch": 1.3744791388031932, "grad_norm": 4.799725532531738, "learning_rate": 9.096819484583422e-06, "loss": 0.3894, "step": 231230 }, { "epoch": 1.3745385808798616, "grad_norm": 4.771873474121094, "learning_rate": 9.096700531263676e-06, "loss": 0.3818, "step": 231240 }, { "epoch": 1.37459802295653, "grad_norm": 4.718996524810791, "learning_rate": 9.096581570888922e-06, "loss": 0.4051, "step": 231250 }, { "epoch": 1.3746574650331984, "grad_norm": 7.877185344696045, "learning_rate": 9.096462603459366e-06, "loss": 0.4166, "step": 231260 }, { "epoch": 1.3747169071098668, "grad_norm": 4.2002434730529785, "learning_rate": 9.096343628975215e-06, "loss": 0.3542, "step": 231270 }, { "epoch": 1.3747763491865352, "grad_norm": 6.568928241729736, "learning_rate": 9.096224647436669e-06, "loss": 0.3856, "step": 231280 }, { "epoch": 1.3748357912632034, "grad_norm": 4.9463934898376465, "learning_rate": 9.096105658843937e-06, "loss": 0.3767, "step": 231290 }, { "epoch": 1.3748952333398718, "grad_norm": 6.285065174102783, "learning_rate": 9.095986663197222e-06, "loss": 0.3876, "step": 231300 }, { "epoch": 1.3749546754165403, "grad_norm": 4.239926815032959, "learning_rate": 9.09586766049673e-06, "loss": 0.3682, "step": 231310 }, { "epoch": 1.3750141174932087, "grad_norm": 5.370090484619141, "learning_rate": 9.095748650742663e-06, "loss": 0.3607, "step": 231320 }, { "epoch": 1.375073559569877, "grad_norm": 5.206599235534668, "learning_rate": 9.095629633935229e-06, "loss": 0.3514, "step": 231330 }, { "epoch": 1.3751330016465455, "grad_norm": 5.1875481605529785, "learning_rate": 9.095510610074633e-06, "loss": 0.3627, "step": 231340 }, { "epoch": 1.375192443723214, "grad_norm": 5.030158042907715, "learning_rate": 9.095391579161078e-06, "loss": 0.393, "step": 231350 }, { "epoch": 1.3752518857998823, "grad_norm": 4.472829818725586, "learning_rate": 9.09527254119477e-06, "loss": 0.3442, "step": 231360 }, { "epoch": 1.3753113278765507, "grad_norm": 7.579178810119629, "learning_rate": 9.095153496175914e-06, "loss": 0.4405, "step": 231370 }, { "epoch": 1.3753707699532192, "grad_norm": 7.048841953277588, "learning_rate": 9.095034444104717e-06, "loss": 0.3707, "step": 231380 }, { "epoch": 1.3754302120298876, "grad_norm": 6.337863445281982, "learning_rate": 9.09491538498138e-06, "loss": 0.3634, "step": 231390 }, { "epoch": 1.375489654106556, "grad_norm": 5.248260021209717, "learning_rate": 9.094796318806112e-06, "loss": 0.3992, "step": 231400 }, { "epoch": 1.3755490961832242, "grad_norm": 5.003908157348633, "learning_rate": 9.094677245579114e-06, "loss": 0.3566, "step": 231410 }, { "epoch": 1.3756085382598926, "grad_norm": 5.693117141723633, "learning_rate": 9.094558165300593e-06, "loss": 0.4328, "step": 231420 }, { "epoch": 1.375667980336561, "grad_norm": 4.252939701080322, "learning_rate": 9.094439077970756e-06, "loss": 0.3061, "step": 231430 }, { "epoch": 1.3757274224132294, "grad_norm": 4.21645450592041, "learning_rate": 9.094319983589806e-06, "loss": 0.3443, "step": 231440 }, { "epoch": 1.3757868644898978, "grad_norm": 4.861637115478516, "learning_rate": 9.094200882157948e-06, "loss": 0.4028, "step": 231450 }, { "epoch": 1.3758463065665663, "grad_norm": 5.514631748199463, "learning_rate": 9.094081773675389e-06, "loss": 0.4054, "step": 231460 }, { "epoch": 1.3759057486432347, "grad_norm": 5.766779899597168, "learning_rate": 9.09396265814233e-06, "loss": 0.322, "step": 231470 }, { "epoch": 1.3759651907199029, "grad_norm": 3.7360920906066895, "learning_rate": 9.093843535558982e-06, "loss": 0.3614, "step": 231480 }, { "epoch": 1.3760246327965713, "grad_norm": 5.04878568649292, "learning_rate": 9.093724405925544e-06, "loss": 0.3278, "step": 231490 }, { "epoch": 1.3760840748732397, "grad_norm": 5.620088577270508, "learning_rate": 9.093605269242225e-06, "loss": 0.3812, "step": 231500 }, { "epoch": 1.376143516949908, "grad_norm": 4.650605201721191, "learning_rate": 9.09348612550923e-06, "loss": 0.372, "step": 231510 }, { "epoch": 1.3762029590265765, "grad_norm": 4.410704612731934, "learning_rate": 9.093366974726764e-06, "loss": 0.3717, "step": 231520 }, { "epoch": 1.376262401103245, "grad_norm": 4.298392295837402, "learning_rate": 9.09324781689503e-06, "loss": 0.3978, "step": 231530 }, { "epoch": 1.3763218431799134, "grad_norm": 5.987573146820068, "learning_rate": 9.093128652014236e-06, "loss": 0.3872, "step": 231540 }, { "epoch": 1.3763812852565818, "grad_norm": 4.716927528381348, "learning_rate": 9.093009480084585e-06, "loss": 0.3794, "step": 231550 }, { "epoch": 1.3764407273332502, "grad_norm": 6.318617343902588, "learning_rate": 9.092890301106286e-06, "loss": 0.393, "step": 231560 }, { "epoch": 1.3765001694099186, "grad_norm": 5.079840183258057, "learning_rate": 9.092771115079539e-06, "loss": 0.386, "step": 231570 }, { "epoch": 1.376559611486587, "grad_norm": 4.685038089752197, "learning_rate": 9.092651922004551e-06, "loss": 0.3487, "step": 231580 }, { "epoch": 1.3766190535632554, "grad_norm": 4.64032506942749, "learning_rate": 9.092532721881531e-06, "loss": 0.3783, "step": 231590 }, { "epoch": 1.3766784956399236, "grad_norm": 5.841098308563232, "learning_rate": 9.092413514710679e-06, "loss": 0.3809, "step": 231600 }, { "epoch": 1.376737937716592, "grad_norm": 4.865499496459961, "learning_rate": 9.092294300492203e-06, "loss": 0.3908, "step": 231610 }, { "epoch": 1.3767973797932604, "grad_norm": 6.2196502685546875, "learning_rate": 9.09217507922631e-06, "loss": 0.4046, "step": 231620 }, { "epoch": 1.3768568218699289, "grad_norm": 5.148438930511475, "learning_rate": 9.092055850913201e-06, "loss": 0.3584, "step": 231630 }, { "epoch": 1.3769162639465973, "grad_norm": 4.383678436279297, "learning_rate": 9.091936615553083e-06, "loss": 0.363, "step": 231640 }, { "epoch": 1.3769757060232657, "grad_norm": 4.760165691375732, "learning_rate": 9.091817373146163e-06, "loss": 0.3578, "step": 231650 }, { "epoch": 1.3770351480999339, "grad_norm": 4.437214374542236, "learning_rate": 9.091698123692646e-06, "loss": 0.3782, "step": 231660 }, { "epoch": 1.3770945901766023, "grad_norm": 4.491178035736084, "learning_rate": 9.091578867192736e-06, "loss": 0.3769, "step": 231670 }, { "epoch": 1.3771540322532707, "grad_norm": 5.473836898803711, "learning_rate": 9.09145960364664e-06, "loss": 0.3944, "step": 231680 }, { "epoch": 1.3772134743299391, "grad_norm": 4.303037166595459, "learning_rate": 9.091340333054561e-06, "loss": 0.3479, "step": 231690 }, { "epoch": 1.3772729164066075, "grad_norm": 4.775966644287109, "learning_rate": 9.091221055416706e-06, "loss": 0.3722, "step": 231700 }, { "epoch": 1.377332358483276, "grad_norm": 4.853280067443848, "learning_rate": 9.09110177073328e-06, "loss": 0.3532, "step": 231710 }, { "epoch": 1.3773918005599444, "grad_norm": 5.597143650054932, "learning_rate": 9.090982479004488e-06, "loss": 0.4239, "step": 231720 }, { "epoch": 1.3774512426366128, "grad_norm": 5.413275718688965, "learning_rate": 9.090863180230537e-06, "loss": 0.3839, "step": 231730 }, { "epoch": 1.3775106847132812, "grad_norm": 3.8627023696899414, "learning_rate": 9.090743874411632e-06, "loss": 0.3416, "step": 231740 }, { "epoch": 1.3775701267899496, "grad_norm": 6.126500129699707, "learning_rate": 9.090624561547976e-06, "loss": 0.3666, "step": 231750 }, { "epoch": 1.377629568866618, "grad_norm": 4.716914176940918, "learning_rate": 9.09050524163978e-06, "loss": 0.3657, "step": 231760 }, { "epoch": 1.3776890109432864, "grad_norm": 6.867598056793213, "learning_rate": 9.090385914687243e-06, "loss": 0.4019, "step": 231770 }, { "epoch": 1.3777484530199546, "grad_norm": 5.414957523345947, "learning_rate": 9.090266580690574e-06, "loss": 0.3587, "step": 231780 }, { "epoch": 1.377807895096623, "grad_norm": 6.06189489364624, "learning_rate": 9.090147239649978e-06, "loss": 0.3817, "step": 231790 }, { "epoch": 1.3778673371732915, "grad_norm": 5.206636905670166, "learning_rate": 9.09002789156566e-06, "loss": 0.3728, "step": 231800 }, { "epoch": 1.3779267792499599, "grad_norm": 4.136671543121338, "learning_rate": 9.089908536437827e-06, "loss": 0.3275, "step": 231810 }, { "epoch": 1.3779862213266283, "grad_norm": 5.176122665405273, "learning_rate": 9.089789174266682e-06, "loss": 0.3431, "step": 231820 }, { "epoch": 1.3780456634032967, "grad_norm": 6.852656841278076, "learning_rate": 9.089669805052433e-06, "loss": 0.372, "step": 231830 }, { "epoch": 1.3781051054799651, "grad_norm": 5.088434219360352, "learning_rate": 9.089550428795285e-06, "loss": 0.3617, "step": 231840 }, { "epoch": 1.3781645475566333, "grad_norm": 3.8436026573181152, "learning_rate": 9.089431045495442e-06, "loss": 0.3931, "step": 231850 }, { "epoch": 1.3782239896333017, "grad_norm": 6.253415584564209, "learning_rate": 9.089311655153113e-06, "loss": 0.3956, "step": 231860 }, { "epoch": 1.3782834317099701, "grad_norm": 4.321005344390869, "learning_rate": 9.0891922577685e-06, "loss": 0.3515, "step": 231870 }, { "epoch": 1.3783428737866386, "grad_norm": 4.625336170196533, "learning_rate": 9.089072853341809e-06, "loss": 0.3355, "step": 231880 }, { "epoch": 1.378402315863307, "grad_norm": 4.647920608520508, "learning_rate": 9.088953441873247e-06, "loss": 0.3914, "step": 231890 }, { "epoch": 1.3784617579399754, "grad_norm": 4.689501762390137, "learning_rate": 9.08883402336302e-06, "loss": 0.3886, "step": 231900 }, { "epoch": 1.3785212000166438, "grad_norm": 4.444258213043213, "learning_rate": 9.088714597811334e-06, "loss": 0.3915, "step": 231910 }, { "epoch": 1.3785806420933122, "grad_norm": 5.789731025695801, "learning_rate": 9.088595165218392e-06, "loss": 0.3946, "step": 231920 }, { "epoch": 1.3786400841699806, "grad_norm": 4.2683186531066895, "learning_rate": 9.088475725584402e-06, "loss": 0.3755, "step": 231930 }, { "epoch": 1.378699526246649, "grad_norm": 5.871083736419678, "learning_rate": 9.08835627890957e-06, "loss": 0.4048, "step": 231940 }, { "epoch": 1.3787589683233175, "grad_norm": 4.658292770385742, "learning_rate": 9.088236825194097e-06, "loss": 0.3657, "step": 231950 }, { "epoch": 1.3788184103999859, "grad_norm": 4.778223514556885, "learning_rate": 9.088117364438196e-06, "loss": 0.3693, "step": 231960 }, { "epoch": 1.378877852476654, "grad_norm": 5.781525135040283, "learning_rate": 9.087997896642066e-06, "loss": 0.3859, "step": 231970 }, { "epoch": 1.3789372945533225, "grad_norm": 3.354793071746826, "learning_rate": 9.08787842180592e-06, "loss": 0.3656, "step": 231980 }, { "epoch": 1.378996736629991, "grad_norm": 4.866857528686523, "learning_rate": 9.087758939929956e-06, "loss": 0.3544, "step": 231990 }, { "epoch": 1.3790561787066593, "grad_norm": 4.60568904876709, "learning_rate": 9.087639451014384e-06, "loss": 0.3611, "step": 232000 }, { "epoch": 1.3791156207833277, "grad_norm": 5.281558513641357, "learning_rate": 9.087519955059412e-06, "loss": 0.3686, "step": 232010 }, { "epoch": 1.3791750628599961, "grad_norm": 5.258068084716797, "learning_rate": 9.08740045206524e-06, "loss": 0.4285, "step": 232020 }, { "epoch": 1.3792345049366643, "grad_norm": 5.532895088195801, "learning_rate": 9.087280942032077e-06, "loss": 0.3624, "step": 232030 }, { "epoch": 1.3792939470133327, "grad_norm": 5.215693950653076, "learning_rate": 9.08716142496013e-06, "loss": 0.3879, "step": 232040 }, { "epoch": 1.3793533890900012, "grad_norm": 4.248358726501465, "learning_rate": 9.087041900849602e-06, "loss": 0.4094, "step": 232050 }, { "epoch": 1.3794128311666696, "grad_norm": 5.561836242675781, "learning_rate": 9.0869223697007e-06, "loss": 0.3509, "step": 232060 }, { "epoch": 1.379472273243338, "grad_norm": 4.752262115478516, "learning_rate": 9.08680283151363e-06, "loss": 0.3783, "step": 232070 }, { "epoch": 1.3795317153200064, "grad_norm": 6.47318172454834, "learning_rate": 9.086683286288599e-06, "loss": 0.3599, "step": 232080 }, { "epoch": 1.3795911573966748, "grad_norm": 4.179187774658203, "learning_rate": 9.086563734025812e-06, "loss": 0.37, "step": 232090 }, { "epoch": 1.3796505994733432, "grad_norm": 6.610424518585205, "learning_rate": 9.086444174725472e-06, "loss": 0.387, "step": 232100 }, { "epoch": 1.3797100415500116, "grad_norm": 4.4655256271362305, "learning_rate": 9.086324608387791e-06, "loss": 0.3874, "step": 232110 }, { "epoch": 1.37976948362668, "grad_norm": 4.4682087898254395, "learning_rate": 9.086205035012969e-06, "loss": 0.3613, "step": 232120 }, { "epoch": 1.3798289257033485, "grad_norm": 5.945606231689453, "learning_rate": 9.086085454601216e-06, "loss": 0.377, "step": 232130 }, { "epoch": 1.379888367780017, "grad_norm": 4.987214088439941, "learning_rate": 9.085965867152734e-06, "loss": 0.3487, "step": 232140 }, { "epoch": 1.379947809856685, "grad_norm": 7.171333312988281, "learning_rate": 9.085846272667735e-06, "loss": 0.3822, "step": 232150 }, { "epoch": 1.3800072519333535, "grad_norm": 4.261467933654785, "learning_rate": 9.085726671146418e-06, "loss": 0.385, "step": 232160 }, { "epoch": 1.380066694010022, "grad_norm": 4.625657081604004, "learning_rate": 9.085607062588993e-06, "loss": 0.3835, "step": 232170 }, { "epoch": 1.3801261360866903, "grad_norm": 4.543142795562744, "learning_rate": 9.085487446995667e-06, "loss": 0.362, "step": 232180 }, { "epoch": 1.3801855781633587, "grad_norm": 4.495640754699707, "learning_rate": 9.085367824366643e-06, "loss": 0.3517, "step": 232190 }, { "epoch": 1.3802450202400272, "grad_norm": 4.194704055786133, "learning_rate": 9.085248194702126e-06, "loss": 0.4122, "step": 232200 }, { "epoch": 1.3803044623166956, "grad_norm": 4.793452262878418, "learning_rate": 9.085128558002324e-06, "loss": 0.3448, "step": 232210 }, { "epoch": 1.3803639043933638, "grad_norm": 7.339120388031006, "learning_rate": 9.085008914267447e-06, "loss": 0.3441, "step": 232220 }, { "epoch": 1.3804233464700322, "grad_norm": 3.7707927227020264, "learning_rate": 9.084889263497696e-06, "loss": 0.3136, "step": 232230 }, { "epoch": 1.3804827885467006, "grad_norm": 5.530745029449463, "learning_rate": 9.084769605693277e-06, "loss": 0.3737, "step": 232240 }, { "epoch": 1.380542230623369, "grad_norm": 4.998989582061768, "learning_rate": 9.084649940854398e-06, "loss": 0.3783, "step": 232250 }, { "epoch": 1.3806016727000374, "grad_norm": 5.527764797210693, "learning_rate": 9.084530268981265e-06, "loss": 0.3793, "step": 232260 }, { "epoch": 1.3806611147767058, "grad_norm": 4.947764873504639, "learning_rate": 9.084410590074083e-06, "loss": 0.3601, "step": 232270 }, { "epoch": 1.3807205568533742, "grad_norm": 4.969328880310059, "learning_rate": 9.084290904133057e-06, "loss": 0.3684, "step": 232280 }, { "epoch": 1.3807799989300427, "grad_norm": 4.72102689743042, "learning_rate": 9.084171211158396e-06, "loss": 0.3412, "step": 232290 }, { "epoch": 1.380839441006711, "grad_norm": 5.426742076873779, "learning_rate": 9.084051511150305e-06, "loss": 0.3823, "step": 232300 }, { "epoch": 1.3808988830833795, "grad_norm": 5.095857620239258, "learning_rate": 9.08393180410899e-06, "loss": 0.3655, "step": 232310 }, { "epoch": 1.380958325160048, "grad_norm": 4.584234237670898, "learning_rate": 9.083812090034658e-06, "loss": 0.3309, "step": 232320 }, { "epoch": 1.3810177672367163, "grad_norm": 5.376959800720215, "learning_rate": 9.083692368927513e-06, "loss": 0.3879, "step": 232330 }, { "epoch": 1.3810772093133845, "grad_norm": 3.6480557918548584, "learning_rate": 9.083572640787764e-06, "loss": 0.3777, "step": 232340 }, { "epoch": 1.381136651390053, "grad_norm": 5.37347412109375, "learning_rate": 9.083452905615613e-06, "loss": 0.4447, "step": 232350 }, { "epoch": 1.3811960934667213, "grad_norm": 3.52994966506958, "learning_rate": 9.08333316341127e-06, "loss": 0.3604, "step": 232360 }, { "epoch": 1.3812555355433898, "grad_norm": 4.262118339538574, "learning_rate": 9.083213414174942e-06, "loss": 0.352, "step": 232370 }, { "epoch": 1.3813149776200582, "grad_norm": 4.481027126312256, "learning_rate": 9.083093657906831e-06, "loss": 0.3743, "step": 232380 }, { "epoch": 1.3813744196967266, "grad_norm": 6.050744533538818, "learning_rate": 9.082973894607146e-06, "loss": 0.38, "step": 232390 }, { "epoch": 1.3814338617733948, "grad_norm": 5.428446292877197, "learning_rate": 9.082854124276095e-06, "loss": 0.3474, "step": 232400 }, { "epoch": 1.3814933038500632, "grad_norm": 5.342790603637695, "learning_rate": 9.08273434691388e-06, "loss": 0.4043, "step": 232410 }, { "epoch": 1.3815527459267316, "grad_norm": 4.787558555603027, "learning_rate": 9.082614562520708e-06, "loss": 0.414, "step": 232420 }, { "epoch": 1.3816121880034, "grad_norm": 5.2233991622924805, "learning_rate": 9.082494771096788e-06, "loss": 0.3781, "step": 232430 }, { "epoch": 1.3816716300800684, "grad_norm": 5.162438869476318, "learning_rate": 9.082374972642326e-06, "loss": 0.386, "step": 232440 }, { "epoch": 1.3817310721567369, "grad_norm": 5.695178031921387, "learning_rate": 9.082255167157527e-06, "loss": 0.4028, "step": 232450 }, { "epoch": 1.3817905142334053, "grad_norm": 4.835712909698486, "learning_rate": 9.082135354642596e-06, "loss": 0.3595, "step": 232460 }, { "epoch": 1.3818499563100737, "grad_norm": 5.638393402099609, "learning_rate": 9.082015535097741e-06, "loss": 0.356, "step": 232470 }, { "epoch": 1.381909398386742, "grad_norm": 5.664212226867676, "learning_rate": 9.08189570852317e-06, "loss": 0.3848, "step": 232480 }, { "epoch": 1.3819688404634105, "grad_norm": 5.072152614593506, "learning_rate": 9.081775874919086e-06, "loss": 0.4071, "step": 232490 }, { "epoch": 1.382028282540079, "grad_norm": 4.515293598175049, "learning_rate": 9.081656034285698e-06, "loss": 0.3889, "step": 232500 }, { "epoch": 1.3820877246167473, "grad_norm": 5.571632385253906, "learning_rate": 9.08153618662321e-06, "loss": 0.4042, "step": 232510 }, { "epoch": 1.3821471666934155, "grad_norm": 5.228745937347412, "learning_rate": 9.081416331931829e-06, "loss": 0.3586, "step": 232520 }, { "epoch": 1.382206608770084, "grad_norm": 4.9015631675720215, "learning_rate": 9.081296470211765e-06, "loss": 0.3747, "step": 232530 }, { "epoch": 1.3822660508467524, "grad_norm": 5.539820194244385, "learning_rate": 9.081176601463218e-06, "loss": 0.3433, "step": 232540 }, { "epoch": 1.3823254929234208, "grad_norm": 4.301220417022705, "learning_rate": 9.0810567256864e-06, "loss": 0.3827, "step": 232550 }, { "epoch": 1.3823849350000892, "grad_norm": 5.657859802246094, "learning_rate": 9.080936842881517e-06, "loss": 0.3842, "step": 232560 }, { "epoch": 1.3824443770767576, "grad_norm": 5.233244895935059, "learning_rate": 9.08081695304877e-06, "loss": 0.3937, "step": 232570 }, { "epoch": 1.382503819153426, "grad_norm": 5.292342662811279, "learning_rate": 9.080697056188372e-06, "loss": 0.3757, "step": 232580 }, { "epoch": 1.3825632612300942, "grad_norm": 5.2205119132995605, "learning_rate": 9.080577152300525e-06, "loss": 0.3572, "step": 232590 }, { "epoch": 1.3826227033067626, "grad_norm": 4.5701212882995605, "learning_rate": 9.080457241385438e-06, "loss": 0.4001, "step": 232600 }, { "epoch": 1.382682145383431, "grad_norm": 4.54897403717041, "learning_rate": 9.080337323443318e-06, "loss": 0.3645, "step": 232610 }, { "epoch": 1.3827415874600995, "grad_norm": 5.260355472564697, "learning_rate": 9.08021739847437e-06, "loss": 0.4087, "step": 232620 }, { "epoch": 1.3828010295367679, "grad_norm": 5.530891418457031, "learning_rate": 9.0800974664788e-06, "loss": 0.378, "step": 232630 }, { "epoch": 1.3828604716134363, "grad_norm": 5.052082061767578, "learning_rate": 9.079977527456815e-06, "loss": 0.3778, "step": 232640 }, { "epoch": 1.3829199136901047, "grad_norm": 4.793673038482666, "learning_rate": 9.079857581408623e-06, "loss": 0.3921, "step": 232650 }, { "epoch": 1.382979355766773, "grad_norm": 6.229013919830322, "learning_rate": 9.079737628334429e-06, "loss": 0.3673, "step": 232660 }, { "epoch": 1.3830387978434415, "grad_norm": 6.783694744110107, "learning_rate": 9.079617668234438e-06, "loss": 0.3649, "step": 232670 }, { "epoch": 1.38309823992011, "grad_norm": 4.280592441558838, "learning_rate": 9.07949770110886e-06, "loss": 0.3738, "step": 232680 }, { "epoch": 1.3831576819967784, "grad_norm": 5.159572601318359, "learning_rate": 9.0793777269579e-06, "loss": 0.38, "step": 232690 }, { "epoch": 1.3832171240734465, "grad_norm": 4.638011455535889, "learning_rate": 9.079257745781766e-06, "loss": 0.3747, "step": 232700 }, { "epoch": 1.383276566150115, "grad_norm": 5.8981032371521, "learning_rate": 9.079137757580664e-06, "loss": 0.4051, "step": 232710 }, { "epoch": 1.3833360082267834, "grad_norm": 5.071655750274658, "learning_rate": 9.079017762354798e-06, "loss": 0.376, "step": 232720 }, { "epoch": 1.3833954503034518, "grad_norm": 4.9899210929870605, "learning_rate": 9.078897760104377e-06, "loss": 0.356, "step": 232730 }, { "epoch": 1.3834548923801202, "grad_norm": 4.238986492156982, "learning_rate": 9.078777750829609e-06, "loss": 0.3762, "step": 232740 }, { "epoch": 1.3835143344567886, "grad_norm": 3.908662796020508, "learning_rate": 9.078657734530698e-06, "loss": 0.3596, "step": 232750 }, { "epoch": 1.383573776533457, "grad_norm": 5.156475067138672, "learning_rate": 9.07853771120785e-06, "loss": 0.3827, "step": 232760 }, { "epoch": 1.3836332186101252, "grad_norm": 4.9399733543396, "learning_rate": 9.078417680861277e-06, "loss": 0.3542, "step": 232770 }, { "epoch": 1.3836926606867936, "grad_norm": 5.007340908050537, "learning_rate": 9.07829764349118e-06, "loss": 0.367, "step": 232780 }, { "epoch": 1.383752102763462, "grad_norm": 4.603679180145264, "learning_rate": 9.078177599097768e-06, "loss": 0.3765, "step": 232790 }, { "epoch": 1.3838115448401305, "grad_norm": 8.238153457641602, "learning_rate": 9.078057547681247e-06, "loss": 0.3581, "step": 232800 }, { "epoch": 1.3838709869167989, "grad_norm": 5.628807067871094, "learning_rate": 9.077937489241825e-06, "loss": 0.3987, "step": 232810 }, { "epoch": 1.3839304289934673, "grad_norm": 5.159264087677002, "learning_rate": 9.077817423779709e-06, "loss": 0.397, "step": 232820 }, { "epoch": 1.3839898710701357, "grad_norm": 4.883433818817139, "learning_rate": 9.077697351295103e-06, "loss": 0.3583, "step": 232830 }, { "epoch": 1.3840493131468041, "grad_norm": 3.888274908065796, "learning_rate": 9.077577271788217e-06, "loss": 0.3762, "step": 232840 }, { "epoch": 1.3841087552234725, "grad_norm": 4.50182580947876, "learning_rate": 9.077457185259256e-06, "loss": 0.3974, "step": 232850 }, { "epoch": 1.384168197300141, "grad_norm": 6.304883003234863, "learning_rate": 9.077337091708426e-06, "loss": 0.3982, "step": 232860 }, { "epoch": 1.3842276393768094, "grad_norm": 5.507902145385742, "learning_rate": 9.077216991135937e-06, "loss": 0.3578, "step": 232870 }, { "epoch": 1.3842870814534778, "grad_norm": 4.478982925415039, "learning_rate": 9.077096883541994e-06, "loss": 0.3902, "step": 232880 }, { "epoch": 1.384346523530146, "grad_norm": 4.778661251068115, "learning_rate": 9.076976768926802e-06, "loss": 0.3547, "step": 232890 }, { "epoch": 1.3844059656068144, "grad_norm": 4.6598968505859375, "learning_rate": 9.07685664729057e-06, "loss": 0.3668, "step": 232900 }, { "epoch": 1.3844654076834828, "grad_norm": 4.912398815155029, "learning_rate": 9.076736518633506e-06, "loss": 0.3768, "step": 232910 }, { "epoch": 1.3845248497601512, "grad_norm": 6.28255033493042, "learning_rate": 9.076616382955814e-06, "loss": 0.4007, "step": 232920 }, { "epoch": 1.3845842918368196, "grad_norm": 4.4957146644592285, "learning_rate": 9.076496240257701e-06, "loss": 0.3499, "step": 232930 }, { "epoch": 1.384643733913488, "grad_norm": 5.04018497467041, "learning_rate": 9.076376090539377e-06, "loss": 0.3798, "step": 232940 }, { "epoch": 1.3847031759901565, "grad_norm": 5.134847640991211, "learning_rate": 9.076255933801046e-06, "loss": 0.349, "step": 232950 }, { "epoch": 1.3847626180668247, "grad_norm": 4.703497886657715, "learning_rate": 9.076135770042916e-06, "loss": 0.361, "step": 232960 }, { "epoch": 1.384822060143493, "grad_norm": 4.298976898193359, "learning_rate": 9.076015599265194e-06, "loss": 0.3576, "step": 232970 }, { "epoch": 1.3848815022201615, "grad_norm": 6.414365768432617, "learning_rate": 9.075895421468086e-06, "loss": 0.3881, "step": 232980 }, { "epoch": 1.38494094429683, "grad_norm": 5.385581970214844, "learning_rate": 9.075775236651802e-06, "loss": 0.3511, "step": 232990 }, { "epoch": 1.3850003863734983, "grad_norm": 5.755056381225586, "learning_rate": 9.075655044816544e-06, "loss": 0.3599, "step": 233000 }, { "epoch": 1.3850598284501667, "grad_norm": 5.970247268676758, "learning_rate": 9.075534845962524e-06, "loss": 0.3898, "step": 233010 }, { "epoch": 1.3851192705268351, "grad_norm": 4.514209270477295, "learning_rate": 9.075414640089945e-06, "loss": 0.3406, "step": 233020 }, { "epoch": 1.3851787126035036, "grad_norm": 6.575074195861816, "learning_rate": 9.075294427199017e-06, "loss": 0.3922, "step": 233030 }, { "epoch": 1.385238154680172, "grad_norm": 5.058494567871094, "learning_rate": 9.075174207289945e-06, "loss": 0.3927, "step": 233040 }, { "epoch": 1.3852975967568404, "grad_norm": 3.4734764099121094, "learning_rate": 9.075053980362937e-06, "loss": 0.39, "step": 233050 }, { "epoch": 1.3853570388335088, "grad_norm": 4.356720447540283, "learning_rate": 9.0749337464182e-06, "loss": 0.3874, "step": 233060 }, { "epoch": 1.385416480910177, "grad_norm": 4.784961700439453, "learning_rate": 9.07481350545594e-06, "loss": 0.3641, "step": 233070 }, { "epoch": 1.3854759229868454, "grad_norm": 4.490183353424072, "learning_rate": 9.074693257476366e-06, "loss": 0.3646, "step": 233080 }, { "epoch": 1.3855353650635138, "grad_norm": 4.9522576332092285, "learning_rate": 9.074573002479683e-06, "loss": 0.3844, "step": 233090 }, { "epoch": 1.3855948071401822, "grad_norm": 6.8093109130859375, "learning_rate": 9.0744527404661e-06, "loss": 0.3737, "step": 233100 }, { "epoch": 1.3856542492168507, "grad_norm": 4.595474720001221, "learning_rate": 9.074332471435822e-06, "loss": 0.3414, "step": 233110 }, { "epoch": 1.385713691293519, "grad_norm": 4.912372589111328, "learning_rate": 9.074212195389059e-06, "loss": 0.3553, "step": 233120 }, { "epoch": 1.3857731333701875, "grad_norm": 5.660552501678467, "learning_rate": 9.074091912326015e-06, "loss": 0.397, "step": 233130 }, { "epoch": 1.3858325754468557, "grad_norm": 5.995185375213623, "learning_rate": 9.0739716222469e-06, "loss": 0.3949, "step": 233140 }, { "epoch": 1.385892017523524, "grad_norm": 4.561934471130371, "learning_rate": 9.073851325151919e-06, "loss": 0.3912, "step": 233150 }, { "epoch": 1.3859514596001925, "grad_norm": 5.182578086853027, "learning_rate": 9.073731021041282e-06, "loss": 0.3725, "step": 233160 }, { "epoch": 1.386010901676861, "grad_norm": 4.947819709777832, "learning_rate": 9.07361070991519e-06, "loss": 0.3654, "step": 233170 }, { "epoch": 1.3860703437535293, "grad_norm": 4.763689041137695, "learning_rate": 9.073490391773858e-06, "loss": 0.3427, "step": 233180 }, { "epoch": 1.3861297858301977, "grad_norm": 4.346673488616943, "learning_rate": 9.073370066617486e-06, "loss": 0.3151, "step": 233190 }, { "epoch": 1.3861892279068662, "grad_norm": 4.91672420501709, "learning_rate": 9.073249734446287e-06, "loss": 0.3478, "step": 233200 }, { "epoch": 1.3862486699835346, "grad_norm": 5.477118968963623, "learning_rate": 9.073129395260466e-06, "loss": 0.4018, "step": 233210 }, { "epoch": 1.386308112060203, "grad_norm": 5.031672954559326, "learning_rate": 9.07300904906023e-06, "loss": 0.3722, "step": 233220 }, { "epoch": 1.3863675541368714, "grad_norm": 5.926705360412598, "learning_rate": 9.072888695845785e-06, "loss": 0.3527, "step": 233230 }, { "epoch": 1.3864269962135398, "grad_norm": 4.911984443664551, "learning_rate": 9.072768335617342e-06, "loss": 0.3855, "step": 233240 }, { "epoch": 1.3864864382902082, "grad_norm": 5.1417012214660645, "learning_rate": 9.072647968375105e-06, "loss": 0.3837, "step": 233250 }, { "epoch": 1.3865458803668764, "grad_norm": 5.563697814941406, "learning_rate": 9.072527594119282e-06, "loss": 0.4064, "step": 233260 }, { "epoch": 1.3866053224435448, "grad_norm": 5.529440402984619, "learning_rate": 9.07240721285008e-06, "loss": 0.344, "step": 233270 }, { "epoch": 1.3866647645202133, "grad_norm": 5.012754917144775, "learning_rate": 9.072286824567709e-06, "loss": 0.3925, "step": 233280 }, { "epoch": 1.3867242065968817, "grad_norm": 4.1141557693481445, "learning_rate": 9.072166429272372e-06, "loss": 0.3777, "step": 233290 }, { "epoch": 1.38678364867355, "grad_norm": 6.850703239440918, "learning_rate": 9.072046026964279e-06, "loss": 0.4088, "step": 233300 }, { "epoch": 1.3868430907502185, "grad_norm": 5.046115875244141, "learning_rate": 9.071925617643637e-06, "loss": 0.4058, "step": 233310 }, { "epoch": 1.386902532826887, "grad_norm": 6.896100044250488, "learning_rate": 9.071805201310655e-06, "loss": 0.4105, "step": 233320 }, { "epoch": 1.386961974903555, "grad_norm": 6.458634376525879, "learning_rate": 9.071684777965536e-06, "loss": 0.408, "step": 233330 }, { "epoch": 1.3870214169802235, "grad_norm": 4.942066192626953, "learning_rate": 9.07156434760849e-06, "loss": 0.3627, "step": 233340 }, { "epoch": 1.387080859056892, "grad_norm": 5.0700554847717285, "learning_rate": 9.071443910239727e-06, "loss": 0.3985, "step": 233350 }, { "epoch": 1.3871403011335603, "grad_norm": 5.998619556427002, "learning_rate": 9.07132346585945e-06, "loss": 0.3684, "step": 233360 }, { "epoch": 1.3871997432102288, "grad_norm": 4.883893966674805, "learning_rate": 9.071203014467869e-06, "loss": 0.3669, "step": 233370 }, { "epoch": 1.3872591852868972, "grad_norm": 4.163069725036621, "learning_rate": 9.07108255606519e-06, "loss": 0.3696, "step": 233380 }, { "epoch": 1.3873186273635656, "grad_norm": 6.385467052459717, "learning_rate": 9.07096209065162e-06, "loss": 0.3977, "step": 233390 }, { "epoch": 1.387378069440234, "grad_norm": 4.30330753326416, "learning_rate": 9.070841618227368e-06, "loss": 0.4002, "step": 233400 }, { "epoch": 1.3874375115169024, "grad_norm": 5.23667049407959, "learning_rate": 9.070721138792642e-06, "loss": 0.3595, "step": 233410 }, { "epoch": 1.3874969535935708, "grad_norm": 5.075882434844971, "learning_rate": 9.07060065234765e-06, "loss": 0.3647, "step": 233420 }, { "epoch": 1.3875563956702393, "grad_norm": 4.521337985992432, "learning_rate": 9.070480158892596e-06, "loss": 0.3685, "step": 233430 }, { "epoch": 1.3876158377469074, "grad_norm": 4.435425758361816, "learning_rate": 9.070359658427689e-06, "loss": 0.3709, "step": 233440 }, { "epoch": 1.3876752798235759, "grad_norm": 3.808391809463501, "learning_rate": 9.070239150953138e-06, "loss": 0.3512, "step": 233450 }, { "epoch": 1.3877347219002443, "grad_norm": 5.202068328857422, "learning_rate": 9.070118636469148e-06, "loss": 0.4261, "step": 233460 }, { "epoch": 1.3877941639769127, "grad_norm": 7.334848403930664, "learning_rate": 9.06999811497593e-06, "loss": 0.4381, "step": 233470 }, { "epoch": 1.387853606053581, "grad_norm": 4.138758182525635, "learning_rate": 9.069877586473688e-06, "loss": 0.4126, "step": 233480 }, { "epoch": 1.3879130481302495, "grad_norm": 4.2582621574401855, "learning_rate": 9.069757050962633e-06, "loss": 0.374, "step": 233490 }, { "epoch": 1.387972490206918, "grad_norm": 7.371082305908203, "learning_rate": 9.069636508442969e-06, "loss": 0.3895, "step": 233500 }, { "epoch": 1.3880319322835861, "grad_norm": 6.061994552612305, "learning_rate": 9.069515958914906e-06, "loss": 0.3833, "step": 233510 }, { "epoch": 1.3880913743602545, "grad_norm": 5.084892749786377, "learning_rate": 9.06939540237865e-06, "loss": 0.4008, "step": 233520 }, { "epoch": 1.388150816436923, "grad_norm": 5.8506903648376465, "learning_rate": 9.069274838834412e-06, "loss": 0.3793, "step": 233530 }, { "epoch": 1.3882102585135914, "grad_norm": 4.3695807456970215, "learning_rate": 9.069154268282396e-06, "loss": 0.3734, "step": 233540 }, { "epoch": 1.3882697005902598, "grad_norm": 5.650787830352783, "learning_rate": 9.069033690722811e-06, "loss": 0.3527, "step": 233550 }, { "epoch": 1.3883291426669282, "grad_norm": 3.504729747772217, "learning_rate": 9.068913106155864e-06, "loss": 0.3675, "step": 233560 }, { "epoch": 1.3883885847435966, "grad_norm": 4.05534553527832, "learning_rate": 9.068792514581763e-06, "loss": 0.3801, "step": 233570 }, { "epoch": 1.388448026820265, "grad_norm": 4.854397296905518, "learning_rate": 9.068671916000717e-06, "loss": 0.3893, "step": 233580 }, { "epoch": 1.3885074688969334, "grad_norm": 4.731453895568848, "learning_rate": 9.06855131041293e-06, "loss": 0.3423, "step": 233590 }, { "epoch": 1.3885669109736019, "grad_norm": 4.459052562713623, "learning_rate": 9.068430697818615e-06, "loss": 0.3617, "step": 233600 }, { "epoch": 1.3886263530502703, "grad_norm": 6.085090637207031, "learning_rate": 9.068310078217975e-06, "loss": 0.4122, "step": 233610 }, { "epoch": 1.3886857951269387, "grad_norm": 4.664645195007324, "learning_rate": 9.06818945161122e-06, "loss": 0.3515, "step": 233620 }, { "epoch": 1.3887452372036069, "grad_norm": 4.539979934692383, "learning_rate": 9.068068817998558e-06, "loss": 0.3794, "step": 233630 }, { "epoch": 1.3888046792802753, "grad_norm": 5.425359725952148, "learning_rate": 9.067948177380196e-06, "loss": 0.3904, "step": 233640 }, { "epoch": 1.3888641213569437, "grad_norm": 5.97902774810791, "learning_rate": 9.06782752975634e-06, "loss": 0.3617, "step": 233650 }, { "epoch": 1.3889235634336121, "grad_norm": 4.282603740692139, "learning_rate": 9.067706875127202e-06, "loss": 0.4168, "step": 233660 }, { "epoch": 1.3889830055102805, "grad_norm": 4.444393634796143, "learning_rate": 9.067586213492987e-06, "loss": 0.4076, "step": 233670 }, { "epoch": 1.389042447586949, "grad_norm": 7.9252610206604, "learning_rate": 9.067465544853904e-06, "loss": 0.3916, "step": 233680 }, { "epoch": 1.3891018896636174, "grad_norm": 4.088543891906738, "learning_rate": 9.067344869210158e-06, "loss": 0.3818, "step": 233690 }, { "epoch": 1.3891613317402856, "grad_norm": 6.168730735778809, "learning_rate": 9.06722418656196e-06, "loss": 0.4137, "step": 233700 }, { "epoch": 1.389220773816954, "grad_norm": 5.44127082824707, "learning_rate": 9.067103496909517e-06, "loss": 0.3945, "step": 233710 }, { "epoch": 1.3892802158936224, "grad_norm": 5.145664215087891, "learning_rate": 9.066982800253034e-06, "loss": 0.3835, "step": 233720 }, { "epoch": 1.3893396579702908, "grad_norm": 5.539910316467285, "learning_rate": 9.066862096592724e-06, "loss": 0.3842, "step": 233730 }, { "epoch": 1.3893991000469592, "grad_norm": 5.055333137512207, "learning_rate": 9.066741385928792e-06, "loss": 0.3733, "step": 233740 }, { "epoch": 1.3894585421236276, "grad_norm": 5.105173587799072, "learning_rate": 9.066620668261445e-06, "loss": 0.3781, "step": 233750 }, { "epoch": 1.389517984200296, "grad_norm": 5.282960891723633, "learning_rate": 9.066499943590893e-06, "loss": 0.3735, "step": 233760 }, { "epoch": 1.3895774262769645, "grad_norm": 6.678073883056641, "learning_rate": 9.066379211917343e-06, "loss": 0.3417, "step": 233770 }, { "epoch": 1.3896368683536329, "grad_norm": 5.445339679718018, "learning_rate": 9.066258473241e-06, "loss": 0.4112, "step": 233780 }, { "epoch": 1.3896963104303013, "grad_norm": 7.077950477600098, "learning_rate": 9.066137727562078e-06, "loss": 0.3696, "step": 233790 }, { "epoch": 1.3897557525069697, "grad_norm": 5.869205474853516, "learning_rate": 9.06601697488078e-06, "loss": 0.372, "step": 233800 }, { "epoch": 1.389815194583638, "grad_norm": 4.249977111816406, "learning_rate": 9.065896215197317e-06, "loss": 0.3831, "step": 233810 }, { "epoch": 1.3898746366603063, "grad_norm": 4.998911380767822, "learning_rate": 9.065775448511895e-06, "loss": 0.4213, "step": 233820 }, { "epoch": 1.3899340787369747, "grad_norm": 5.0542778968811035, "learning_rate": 9.065654674824721e-06, "loss": 0.3881, "step": 233830 }, { "epoch": 1.3899935208136431, "grad_norm": 4.861763000488281, "learning_rate": 9.065533894136007e-06, "loss": 0.3674, "step": 233840 }, { "epoch": 1.3900529628903115, "grad_norm": 5.253427505493164, "learning_rate": 9.065413106445956e-06, "loss": 0.3568, "step": 233850 }, { "epoch": 1.39011240496698, "grad_norm": 6.061034202575684, "learning_rate": 9.065292311754782e-06, "loss": 0.399, "step": 233860 }, { "epoch": 1.3901718470436484, "grad_norm": 5.54509162902832, "learning_rate": 9.065171510062687e-06, "loss": 0.4062, "step": 233870 }, { "epoch": 1.3902312891203166, "grad_norm": 3.7738804817199707, "learning_rate": 9.065050701369881e-06, "loss": 0.3605, "step": 233880 }, { "epoch": 1.390290731196985, "grad_norm": 6.090760231018066, "learning_rate": 9.064929885676575e-06, "loss": 0.3609, "step": 233890 }, { "epoch": 1.3903501732736534, "grad_norm": 4.225345611572266, "learning_rate": 9.064809062982972e-06, "loss": 0.3538, "step": 233900 }, { "epoch": 1.3904096153503218, "grad_norm": 5.157269477844238, "learning_rate": 9.064688233289288e-06, "loss": 0.4084, "step": 233910 }, { "epoch": 1.3904690574269902, "grad_norm": 3.9474527835845947, "learning_rate": 9.064567396595721e-06, "loss": 0.3653, "step": 233920 }, { "epoch": 1.3905284995036586, "grad_norm": 5.080996036529541, "learning_rate": 9.064446552902484e-06, "loss": 0.3808, "step": 233930 }, { "epoch": 1.390587941580327, "grad_norm": 5.851436138153076, "learning_rate": 9.064325702209786e-06, "loss": 0.3894, "step": 233940 }, { "epoch": 1.3906473836569955, "grad_norm": 4.755721092224121, "learning_rate": 9.064204844517835e-06, "loss": 0.39, "step": 233950 }, { "epoch": 1.3907068257336639, "grad_norm": 3.9933764934539795, "learning_rate": 9.06408397982684e-06, "loss": 0.3923, "step": 233960 }, { "epoch": 1.3907662678103323, "grad_norm": 7.880696773529053, "learning_rate": 9.063963108137004e-06, "loss": 0.4116, "step": 233970 }, { "epoch": 1.3908257098870007, "grad_norm": 5.475414752960205, "learning_rate": 9.06384222944854e-06, "loss": 0.3565, "step": 233980 }, { "epoch": 1.3908851519636691, "grad_norm": 4.523216724395752, "learning_rate": 9.063721343761654e-06, "loss": 0.3771, "step": 233990 }, { "epoch": 1.3909445940403373, "grad_norm": 7.134592533111572, "learning_rate": 9.063600451076555e-06, "loss": 0.3727, "step": 234000 }, { "epoch": 1.3910040361170057, "grad_norm": 6.532296657562256, "learning_rate": 9.063479551393452e-06, "loss": 0.355, "step": 234010 }, { "epoch": 1.3910634781936742, "grad_norm": 3.67645263671875, "learning_rate": 9.063358644712554e-06, "loss": 0.359, "step": 234020 }, { "epoch": 1.3911229202703426, "grad_norm": 4.77921724319458, "learning_rate": 9.063237731034065e-06, "loss": 0.3926, "step": 234030 }, { "epoch": 1.391182362347011, "grad_norm": 4.6954522132873535, "learning_rate": 9.063116810358196e-06, "loss": 0.339, "step": 234040 }, { "epoch": 1.3912418044236794, "grad_norm": 4.960562229156494, "learning_rate": 9.062995882685154e-06, "loss": 0.4074, "step": 234050 }, { "epoch": 1.3913012465003478, "grad_norm": 4.9678778648376465, "learning_rate": 9.062874948015153e-06, "loss": 0.3626, "step": 234060 }, { "epoch": 1.391360688577016, "grad_norm": 6.329978942871094, "learning_rate": 9.062754006348392e-06, "loss": 0.362, "step": 234070 }, { "epoch": 1.3914201306536844, "grad_norm": 6.434418201446533, "learning_rate": 9.062633057685086e-06, "loss": 0.4165, "step": 234080 }, { "epoch": 1.3914795727303528, "grad_norm": 3.482893705368042, "learning_rate": 9.06251210202544e-06, "loss": 0.3188, "step": 234090 }, { "epoch": 1.3915390148070212, "grad_norm": 4.6286797523498535, "learning_rate": 9.062391139369665e-06, "loss": 0.3665, "step": 234100 }, { "epoch": 1.3915984568836897, "grad_norm": 5.929090976715088, "learning_rate": 9.062270169717966e-06, "loss": 0.3451, "step": 234110 }, { "epoch": 1.391657898960358, "grad_norm": 4.5822434425354, "learning_rate": 9.062149193070554e-06, "loss": 0.3516, "step": 234120 }, { "epoch": 1.3917173410370265, "grad_norm": 5.910992622375488, "learning_rate": 9.062028209427636e-06, "loss": 0.3699, "step": 234130 }, { "epoch": 1.391776783113695, "grad_norm": 4.425619602203369, "learning_rate": 9.061907218789421e-06, "loss": 0.3616, "step": 234140 }, { "epoch": 1.3918362251903633, "grad_norm": 5.260516166687012, "learning_rate": 9.061786221156117e-06, "loss": 0.3894, "step": 234150 }, { "epoch": 1.3918956672670317, "grad_norm": 4.185871124267578, "learning_rate": 9.061665216527931e-06, "loss": 0.358, "step": 234160 }, { "epoch": 1.3919551093437001, "grad_norm": 4.461226940155029, "learning_rate": 9.061544204905074e-06, "loss": 0.3879, "step": 234170 }, { "epoch": 1.3920145514203683, "grad_norm": 5.746274471282959, "learning_rate": 9.061423186287755e-06, "loss": 0.3824, "step": 234180 }, { "epoch": 1.3920739934970368, "grad_norm": 3.9665768146514893, "learning_rate": 9.061302160676178e-06, "loss": 0.3238, "step": 234190 }, { "epoch": 1.3921334355737052, "grad_norm": 6.245787143707275, "learning_rate": 9.061181128070557e-06, "loss": 0.3378, "step": 234200 }, { "epoch": 1.3921928776503736, "grad_norm": 4.762747287750244, "learning_rate": 9.061060088471095e-06, "loss": 0.3849, "step": 234210 }, { "epoch": 1.392252319727042, "grad_norm": 4.375284194946289, "learning_rate": 9.060939041878003e-06, "loss": 0.3566, "step": 234220 }, { "epoch": 1.3923117618037104, "grad_norm": 5.909230709075928, "learning_rate": 9.06081798829149e-06, "loss": 0.3574, "step": 234230 }, { "epoch": 1.3923712038803788, "grad_norm": 5.186158657073975, "learning_rate": 9.060696927711765e-06, "loss": 0.3937, "step": 234240 }, { "epoch": 1.392430645957047, "grad_norm": 5.9598236083984375, "learning_rate": 9.060575860139035e-06, "loss": 0.3523, "step": 234250 }, { "epoch": 1.3924900880337154, "grad_norm": 10.179104804992676, "learning_rate": 9.060454785573509e-06, "loss": 0.3324, "step": 234260 }, { "epoch": 1.3925495301103838, "grad_norm": 3.735743999481201, "learning_rate": 9.060333704015394e-06, "loss": 0.3594, "step": 234270 }, { "epoch": 1.3926089721870523, "grad_norm": 5.990791320800781, "learning_rate": 9.060212615464901e-06, "loss": 0.3811, "step": 234280 }, { "epoch": 1.3926684142637207, "grad_norm": 5.7862162590026855, "learning_rate": 9.060091519922237e-06, "loss": 0.4126, "step": 234290 }, { "epoch": 1.392727856340389, "grad_norm": 5.019819259643555, "learning_rate": 9.059970417387612e-06, "loss": 0.3739, "step": 234300 }, { "epoch": 1.3927872984170575, "grad_norm": 4.026691913604736, "learning_rate": 9.059849307861231e-06, "loss": 0.3454, "step": 234310 }, { "epoch": 1.392846740493726, "grad_norm": 5.184266090393066, "learning_rate": 9.059728191343307e-06, "loss": 0.3759, "step": 234320 }, { "epoch": 1.3929061825703943, "grad_norm": 8.344173431396484, "learning_rate": 9.059607067834047e-06, "loss": 0.3775, "step": 234330 }, { "epoch": 1.3929656246470628, "grad_norm": 5.635224342346191, "learning_rate": 9.059485937333657e-06, "loss": 0.4487, "step": 234340 }, { "epoch": 1.3930250667237312, "grad_norm": 4.741037368774414, "learning_rate": 9.05936479984235e-06, "loss": 0.414, "step": 234350 }, { "epoch": 1.3930845088003996, "grad_norm": 3.981529474258423, "learning_rate": 9.059243655360332e-06, "loss": 0.3787, "step": 234360 }, { "epoch": 1.3931439508770678, "grad_norm": 5.905489921569824, "learning_rate": 9.059122503887811e-06, "loss": 0.3521, "step": 234370 }, { "epoch": 1.3932033929537362, "grad_norm": 5.371246814727783, "learning_rate": 9.059001345424998e-06, "loss": 0.3977, "step": 234380 }, { "epoch": 1.3932628350304046, "grad_norm": 5.291730880737305, "learning_rate": 9.0588801799721e-06, "loss": 0.4137, "step": 234390 }, { "epoch": 1.393322277107073, "grad_norm": 5.050656795501709, "learning_rate": 9.058759007529327e-06, "loss": 0.3347, "step": 234400 }, { "epoch": 1.3933817191837414, "grad_norm": 5.610015869140625, "learning_rate": 9.058637828096885e-06, "loss": 0.3804, "step": 234410 }, { "epoch": 1.3934411612604098, "grad_norm": 4.6471686363220215, "learning_rate": 9.058516641674986e-06, "loss": 0.3611, "step": 234420 }, { "epoch": 1.3935006033370783, "grad_norm": 4.027009010314941, "learning_rate": 9.058395448263835e-06, "loss": 0.3656, "step": 234430 }, { "epoch": 1.3935600454137465, "grad_norm": 5.975730895996094, "learning_rate": 9.058274247863645e-06, "loss": 0.3285, "step": 234440 }, { "epoch": 1.3936194874904149, "grad_norm": 5.429351806640625, "learning_rate": 9.058153040474621e-06, "loss": 0.3443, "step": 234450 }, { "epoch": 1.3936789295670833, "grad_norm": 4.487953186035156, "learning_rate": 9.058031826096973e-06, "loss": 0.3581, "step": 234460 }, { "epoch": 1.3937383716437517, "grad_norm": 4.770088195800781, "learning_rate": 9.057910604730912e-06, "loss": 0.3835, "step": 234470 }, { "epoch": 1.39379781372042, "grad_norm": 5.969126224517822, "learning_rate": 9.057789376376644e-06, "loss": 0.3792, "step": 234480 }, { "epoch": 1.3938572557970885, "grad_norm": 5.183129787445068, "learning_rate": 9.057668141034378e-06, "loss": 0.4402, "step": 234490 }, { "epoch": 1.393916697873757, "grad_norm": 4.730625629425049, "learning_rate": 9.057546898704322e-06, "loss": 0.3718, "step": 234500 }, { "epoch": 1.3939761399504254, "grad_norm": 4.74156379699707, "learning_rate": 9.057425649386688e-06, "loss": 0.4104, "step": 234510 }, { "epoch": 1.3940355820270938, "grad_norm": 5.277389049530029, "learning_rate": 9.057304393081683e-06, "loss": 0.3641, "step": 234520 }, { "epoch": 1.3940950241037622, "grad_norm": 6.588227272033691, "learning_rate": 9.057183129789516e-06, "loss": 0.3899, "step": 234530 }, { "epoch": 1.3941544661804306, "grad_norm": 4.053411483764648, "learning_rate": 9.057061859510395e-06, "loss": 0.3955, "step": 234540 }, { "epoch": 1.3942139082570988, "grad_norm": 4.62141752243042, "learning_rate": 9.056940582244526e-06, "loss": 0.3554, "step": 234550 }, { "epoch": 1.3942733503337672, "grad_norm": 5.789541721343994, "learning_rate": 9.056819297992125e-06, "loss": 0.3861, "step": 234560 }, { "epoch": 1.3943327924104356, "grad_norm": 4.82998514175415, "learning_rate": 9.056698006753397e-06, "loss": 0.3715, "step": 234570 }, { "epoch": 1.394392234487104, "grad_norm": 5.867631435394287, "learning_rate": 9.05657670852855e-06, "loss": 0.3935, "step": 234580 }, { "epoch": 1.3944516765637724, "grad_norm": 4.57239294052124, "learning_rate": 9.056455403317795e-06, "loss": 0.3778, "step": 234590 }, { "epoch": 1.3945111186404409, "grad_norm": 4.089113235473633, "learning_rate": 9.05633409112134e-06, "loss": 0.3541, "step": 234600 }, { "epoch": 1.3945705607171093, "grad_norm": 4.522186279296875, "learning_rate": 9.056212771939391e-06, "loss": 0.3794, "step": 234610 }, { "epoch": 1.3946300027937775, "grad_norm": 4.915804862976074, "learning_rate": 9.056091445772163e-06, "loss": 0.3798, "step": 234620 }, { "epoch": 1.3946894448704459, "grad_norm": 6.2122321128845215, "learning_rate": 9.05597011261986e-06, "loss": 0.4116, "step": 234630 }, { "epoch": 1.3947488869471143, "grad_norm": 4.915190696716309, "learning_rate": 9.055848772482691e-06, "loss": 0.4082, "step": 234640 }, { "epoch": 1.3948083290237827, "grad_norm": 5.121915817260742, "learning_rate": 9.05572742536087e-06, "loss": 0.396, "step": 234650 }, { "epoch": 1.3948677711004511, "grad_norm": 4.7222089767456055, "learning_rate": 9.055606071254598e-06, "loss": 0.3755, "step": 234660 }, { "epoch": 1.3949272131771195, "grad_norm": 5.731154441833496, "learning_rate": 9.055484710164093e-06, "loss": 0.3864, "step": 234670 }, { "epoch": 1.394986655253788, "grad_norm": 3.864691972732544, "learning_rate": 9.055363342089557e-06, "loss": 0.3585, "step": 234680 }, { "epoch": 1.3950460973304564, "grad_norm": 4.579163074493408, "learning_rate": 9.055241967031202e-06, "loss": 0.32, "step": 234690 }, { "epoch": 1.3951055394071248, "grad_norm": 4.519887924194336, "learning_rate": 9.055120584989236e-06, "loss": 0.3337, "step": 234700 }, { "epoch": 1.3951649814837932, "grad_norm": 5.980532169342041, "learning_rate": 9.054999195963869e-06, "loss": 0.3719, "step": 234710 }, { "epoch": 1.3952244235604616, "grad_norm": 5.641685962677002, "learning_rate": 9.054877799955309e-06, "loss": 0.3902, "step": 234720 }, { "epoch": 1.39528386563713, "grad_norm": 5.433279514312744, "learning_rate": 9.054756396963766e-06, "loss": 0.3775, "step": 234730 }, { "epoch": 1.3953433077137982, "grad_norm": 8.173360824584961, "learning_rate": 9.054634986989447e-06, "loss": 0.3897, "step": 234740 }, { "epoch": 1.3954027497904666, "grad_norm": 4.656210899353027, "learning_rate": 9.054513570032565e-06, "loss": 0.3623, "step": 234750 }, { "epoch": 1.395462191867135, "grad_norm": 4.7617998123168945, "learning_rate": 9.054392146093326e-06, "loss": 0.3445, "step": 234760 }, { "epoch": 1.3955216339438035, "grad_norm": 5.096941947937012, "learning_rate": 9.05427071517194e-06, "loss": 0.3393, "step": 234770 }, { "epoch": 1.3955810760204719, "grad_norm": 4.3778910636901855, "learning_rate": 9.054149277268618e-06, "loss": 0.3576, "step": 234780 }, { "epoch": 1.3956405180971403, "grad_norm": 6.499176502227783, "learning_rate": 9.054027832383566e-06, "loss": 0.3541, "step": 234790 }, { "epoch": 1.3956999601738087, "grad_norm": 4.897678375244141, "learning_rate": 9.053906380516993e-06, "loss": 0.3759, "step": 234800 }, { "epoch": 1.395759402250477, "grad_norm": 5.169148921966553, "learning_rate": 9.05378492166911e-06, "loss": 0.3527, "step": 234810 }, { "epoch": 1.3958188443271453, "grad_norm": 4.4789557456970215, "learning_rate": 9.053663455840127e-06, "loss": 0.3927, "step": 234820 }, { "epoch": 1.3958782864038137, "grad_norm": 5.911265850067139, "learning_rate": 9.05354198303025e-06, "loss": 0.3899, "step": 234830 }, { "epoch": 1.3959377284804821, "grad_norm": 4.875696182250977, "learning_rate": 9.05342050323969e-06, "loss": 0.3579, "step": 234840 }, { "epoch": 1.3959971705571506, "grad_norm": 4.906160354614258, "learning_rate": 9.053299016468657e-06, "loss": 0.4008, "step": 234850 }, { "epoch": 1.396056612633819, "grad_norm": 3.2040493488311768, "learning_rate": 9.05317752271736e-06, "loss": 0.3172, "step": 234860 }, { "epoch": 1.3961160547104874, "grad_norm": 5.952724456787109, "learning_rate": 9.053056021986007e-06, "loss": 0.3661, "step": 234870 }, { "epoch": 1.3961754967871558, "grad_norm": 5.829719066619873, "learning_rate": 9.05293451427481e-06, "loss": 0.365, "step": 234880 }, { "epoch": 1.3962349388638242, "grad_norm": 5.582938194274902, "learning_rate": 9.052812999583973e-06, "loss": 0.3672, "step": 234890 }, { "epoch": 1.3962943809404926, "grad_norm": 4.71017599105835, "learning_rate": 9.052691477913711e-06, "loss": 0.3683, "step": 234900 }, { "epoch": 1.396353823017161, "grad_norm": 3.718391180038452, "learning_rate": 9.052569949264229e-06, "loss": 0.3584, "step": 234910 }, { "epoch": 1.3964132650938292, "grad_norm": 5.1510748863220215, "learning_rate": 9.052448413635739e-06, "loss": 0.3844, "step": 234920 }, { "epoch": 1.3964727071704977, "grad_norm": 4.795889377593994, "learning_rate": 9.052326871028448e-06, "loss": 0.3225, "step": 234930 }, { "epoch": 1.396532149247166, "grad_norm": 5.143944263458252, "learning_rate": 9.052205321442568e-06, "loss": 0.3586, "step": 234940 }, { "epoch": 1.3965915913238345, "grad_norm": 4.99356746673584, "learning_rate": 9.052083764878306e-06, "loss": 0.4425, "step": 234950 }, { "epoch": 1.396651033400503, "grad_norm": 4.597568511962891, "learning_rate": 9.051962201335873e-06, "loss": 0.3535, "step": 234960 }, { "epoch": 1.3967104754771713, "grad_norm": 5.6982951164245605, "learning_rate": 9.051840630815476e-06, "loss": 0.3568, "step": 234970 }, { "epoch": 1.3967699175538397, "grad_norm": 4.715022563934326, "learning_rate": 9.051719053317328e-06, "loss": 0.3868, "step": 234980 }, { "epoch": 1.396829359630508, "grad_norm": 4.773504257202148, "learning_rate": 9.051597468841635e-06, "loss": 0.3599, "step": 234990 }, { "epoch": 1.3968888017071763, "grad_norm": 3.588836669921875, "learning_rate": 9.051475877388609e-06, "loss": 0.3609, "step": 235000 }, { "epoch": 1.3969482437838447, "grad_norm": 7.222203254699707, "learning_rate": 9.051354278958458e-06, "loss": 0.3716, "step": 235010 }, { "epoch": 1.3970076858605132, "grad_norm": 4.67665958404541, "learning_rate": 9.05123267355139e-06, "loss": 0.3679, "step": 235020 }, { "epoch": 1.3970671279371816, "grad_norm": 5.081927299499512, "learning_rate": 9.051111061167617e-06, "loss": 0.3905, "step": 235030 }, { "epoch": 1.39712657001385, "grad_norm": 6.705543041229248, "learning_rate": 9.050989441807347e-06, "loss": 0.3594, "step": 235040 }, { "epoch": 1.3971860120905184, "grad_norm": 4.895864963531494, "learning_rate": 9.05086781547079e-06, "loss": 0.3521, "step": 235050 }, { "epoch": 1.3972454541671868, "grad_norm": 5.553323268890381, "learning_rate": 9.050746182158156e-06, "loss": 0.3726, "step": 235060 }, { "epoch": 1.3973048962438552, "grad_norm": 4.705615520477295, "learning_rate": 9.050624541869653e-06, "loss": 0.3799, "step": 235070 }, { "epoch": 1.3973643383205236, "grad_norm": 5.181658744812012, "learning_rate": 9.050502894605492e-06, "loss": 0.3892, "step": 235080 }, { "epoch": 1.397423780397192, "grad_norm": 4.73276948928833, "learning_rate": 9.050381240365882e-06, "loss": 0.3632, "step": 235090 }, { "epoch": 1.3974832224738605, "grad_norm": 5.644019603729248, "learning_rate": 9.05025957915103e-06, "loss": 0.4178, "step": 235100 }, { "epoch": 1.3975426645505287, "grad_norm": 4.0545454025268555, "learning_rate": 9.050137910961149e-06, "loss": 0.3708, "step": 235110 }, { "epoch": 1.397602106627197, "grad_norm": 4.71815824508667, "learning_rate": 9.050016235796448e-06, "loss": 0.3689, "step": 235120 }, { "epoch": 1.3976615487038655, "grad_norm": 3.819688081741333, "learning_rate": 9.049894553657135e-06, "loss": 0.3734, "step": 235130 }, { "epoch": 1.397720990780534, "grad_norm": 5.376829624176025, "learning_rate": 9.04977286454342e-06, "loss": 0.419, "step": 235140 }, { "epoch": 1.3977804328572023, "grad_norm": 6.401885509490967, "learning_rate": 9.049651168455514e-06, "loss": 0.3757, "step": 235150 }, { "epoch": 1.3978398749338707, "grad_norm": 5.118279933929443, "learning_rate": 9.049529465393625e-06, "loss": 0.3872, "step": 235160 }, { "epoch": 1.3978993170105392, "grad_norm": 4.264605522155762, "learning_rate": 9.049407755357962e-06, "loss": 0.3697, "step": 235170 }, { "epoch": 1.3979587590872073, "grad_norm": 5.750025749206543, "learning_rate": 9.049286038348737e-06, "loss": 0.3638, "step": 235180 }, { "epoch": 1.3980182011638758, "grad_norm": 5.024202346801758, "learning_rate": 9.04916431436616e-06, "loss": 0.4015, "step": 235190 }, { "epoch": 1.3980776432405442, "grad_norm": 4.974424362182617, "learning_rate": 9.049042583410435e-06, "loss": 0.4015, "step": 235200 }, { "epoch": 1.3981370853172126, "grad_norm": 4.78944206237793, "learning_rate": 9.048920845481778e-06, "loss": 0.3255, "step": 235210 }, { "epoch": 1.398196527393881, "grad_norm": 7.895766735076904, "learning_rate": 9.048799100580395e-06, "loss": 0.3964, "step": 235220 }, { "epoch": 1.3982559694705494, "grad_norm": 3.903477430343628, "learning_rate": 9.048677348706499e-06, "loss": 0.3172, "step": 235230 }, { "epoch": 1.3983154115472178, "grad_norm": 5.72792911529541, "learning_rate": 9.048555589860296e-06, "loss": 0.3881, "step": 235240 }, { "epoch": 1.3983748536238862, "grad_norm": 6.689871788024902, "learning_rate": 9.048433824041996e-06, "loss": 0.3636, "step": 235250 }, { "epoch": 1.3984342957005547, "grad_norm": 5.289355278015137, "learning_rate": 9.048312051251811e-06, "loss": 0.3601, "step": 235260 }, { "epoch": 1.398493737777223, "grad_norm": 4.057260990142822, "learning_rate": 9.04819027148995e-06, "loss": 0.3531, "step": 235270 }, { "epoch": 1.3985531798538915, "grad_norm": 3.929164409637451, "learning_rate": 9.048068484756622e-06, "loss": 0.4384, "step": 235280 }, { "epoch": 1.3986126219305597, "grad_norm": 5.9027180671691895, "learning_rate": 9.047946691052038e-06, "loss": 0.3846, "step": 235290 }, { "epoch": 1.398672064007228, "grad_norm": 6.0254693031311035, "learning_rate": 9.047824890376405e-06, "loss": 0.3769, "step": 235300 }, { "epoch": 1.3987315060838965, "grad_norm": 5.157626628875732, "learning_rate": 9.047703082729935e-06, "loss": 0.3715, "step": 235310 }, { "epoch": 1.398790948160565, "grad_norm": 4.0957722663879395, "learning_rate": 9.047581268112839e-06, "loss": 0.4025, "step": 235320 }, { "epoch": 1.3988503902372333, "grad_norm": 4.572100639343262, "learning_rate": 9.047459446525323e-06, "loss": 0.3581, "step": 235330 }, { "epoch": 1.3989098323139018, "grad_norm": 4.422701835632324, "learning_rate": 9.0473376179676e-06, "loss": 0.4059, "step": 235340 }, { "epoch": 1.3989692743905702, "grad_norm": 4.938124656677246, "learning_rate": 9.047215782439878e-06, "loss": 0.3912, "step": 235350 }, { "epoch": 1.3990287164672384, "grad_norm": 4.5718488693237305, "learning_rate": 9.047093939942368e-06, "loss": 0.3235, "step": 235360 }, { "epoch": 1.3990881585439068, "grad_norm": 5.010931491851807, "learning_rate": 9.04697209047528e-06, "loss": 0.3305, "step": 235370 }, { "epoch": 1.3991476006205752, "grad_norm": 4.324982643127441, "learning_rate": 9.046850234038821e-06, "loss": 0.3669, "step": 235380 }, { "epoch": 1.3992070426972436, "grad_norm": 5.693941593170166, "learning_rate": 9.046728370633206e-06, "loss": 0.3515, "step": 235390 }, { "epoch": 1.399266484773912, "grad_norm": 5.034090518951416, "learning_rate": 9.046606500258642e-06, "loss": 0.4087, "step": 235400 }, { "epoch": 1.3993259268505804, "grad_norm": 5.12392520904541, "learning_rate": 9.046484622915336e-06, "loss": 0.3921, "step": 235410 }, { "epoch": 1.3993853689272489, "grad_norm": 5.766040802001953, "learning_rate": 9.046362738603502e-06, "loss": 0.3546, "step": 235420 }, { "epoch": 1.3994448110039173, "grad_norm": 7.132388114929199, "learning_rate": 9.046240847323348e-06, "loss": 0.3617, "step": 235430 }, { "epoch": 1.3995042530805857, "grad_norm": 4.116990089416504, "learning_rate": 9.046118949075085e-06, "loss": 0.346, "step": 235440 }, { "epoch": 1.399563695157254, "grad_norm": 6.212525367736816, "learning_rate": 9.045997043858923e-06, "loss": 0.3958, "step": 235450 }, { "epoch": 1.3996231372339225, "grad_norm": 4.190750598907471, "learning_rate": 9.04587513167507e-06, "loss": 0.3705, "step": 235460 }, { "epoch": 1.399682579310591, "grad_norm": 5.47459077835083, "learning_rate": 9.045753212523738e-06, "loss": 0.3547, "step": 235470 }, { "epoch": 1.3997420213872591, "grad_norm": 4.890307903289795, "learning_rate": 9.045631286405136e-06, "loss": 0.3847, "step": 235480 }, { "epoch": 1.3998014634639275, "grad_norm": 4.391407489776611, "learning_rate": 9.045509353319475e-06, "loss": 0.3555, "step": 235490 }, { "epoch": 1.399860905540596, "grad_norm": 5.134901523590088, "learning_rate": 9.045387413266964e-06, "loss": 0.4273, "step": 235500 }, { "epoch": 1.3999203476172644, "grad_norm": 5.84307336807251, "learning_rate": 9.045265466247813e-06, "loss": 0.3199, "step": 235510 }, { "epoch": 1.3999797896939328, "grad_norm": 5.232336044311523, "learning_rate": 9.045143512262232e-06, "loss": 0.3309, "step": 235520 }, { "epoch": 1.4000392317706012, "grad_norm": 7.019224643707275, "learning_rate": 9.045021551310431e-06, "loss": 0.4106, "step": 235530 }, { "epoch": 1.4000986738472696, "grad_norm": 4.6994099617004395, "learning_rate": 9.044899583392619e-06, "loss": 0.329, "step": 235540 }, { "epoch": 1.4001581159239378, "grad_norm": 5.320550441741943, "learning_rate": 9.04477760850901e-06, "loss": 0.4092, "step": 235550 }, { "epoch": 1.4002175580006062, "grad_norm": 3.1873562335968018, "learning_rate": 9.04465562665981e-06, "loss": 0.3686, "step": 235560 }, { "epoch": 1.4002770000772746, "grad_norm": 6.982334613800049, "learning_rate": 9.04453363784523e-06, "loss": 0.4276, "step": 235570 }, { "epoch": 1.400336442153943, "grad_norm": 5.293982982635498, "learning_rate": 9.04441164206548e-06, "loss": 0.3829, "step": 235580 }, { "epoch": 1.4003958842306115, "grad_norm": 4.5775299072265625, "learning_rate": 9.044289639320772e-06, "loss": 0.3547, "step": 235590 }, { "epoch": 1.4004553263072799, "grad_norm": 6.510487079620361, "learning_rate": 9.044167629611315e-06, "loss": 0.3788, "step": 235600 }, { "epoch": 1.4005147683839483, "grad_norm": 5.6260457038879395, "learning_rate": 9.044045612937318e-06, "loss": 0.3531, "step": 235610 }, { "epoch": 1.4005742104606167, "grad_norm": 5.085992336273193, "learning_rate": 9.043923589298991e-06, "loss": 0.3559, "step": 235620 }, { "epoch": 1.4006336525372851, "grad_norm": 6.0351881980896, "learning_rate": 9.043801558696546e-06, "loss": 0.3868, "step": 235630 }, { "epoch": 1.4006930946139535, "grad_norm": 4.665838241577148, "learning_rate": 9.043679521130192e-06, "loss": 0.3246, "step": 235640 }, { "epoch": 1.400752536690622, "grad_norm": 3.8648366928100586, "learning_rate": 9.04355747660014e-06, "loss": 0.3769, "step": 235650 }, { "epoch": 1.4008119787672901, "grad_norm": 5.523283958435059, "learning_rate": 9.0434354251066e-06, "loss": 0.3928, "step": 235660 }, { "epoch": 1.4008714208439585, "grad_norm": 6.009152889251709, "learning_rate": 9.04331336664978e-06, "loss": 0.3448, "step": 235670 }, { "epoch": 1.400930862920627, "grad_norm": 5.539667129516602, "learning_rate": 9.043191301229894e-06, "loss": 0.366, "step": 235680 }, { "epoch": 1.4009903049972954, "grad_norm": 4.455197334289551, "learning_rate": 9.043069228847149e-06, "loss": 0.3799, "step": 235690 }, { "epoch": 1.4010497470739638, "grad_norm": 4.657332897186279, "learning_rate": 9.042947149501755e-06, "loss": 0.3442, "step": 235700 }, { "epoch": 1.4011091891506322, "grad_norm": 5.457087993621826, "learning_rate": 9.042825063193926e-06, "loss": 0.3562, "step": 235710 }, { "epoch": 1.4011686312273006, "grad_norm": 4.025641441345215, "learning_rate": 9.042702969923868e-06, "loss": 0.4055, "step": 235720 }, { "epoch": 1.4012280733039688, "grad_norm": 4.086222171783447, "learning_rate": 9.042580869691794e-06, "loss": 0.3489, "step": 235730 }, { "epoch": 1.4012875153806372, "grad_norm": 5.1970062255859375, "learning_rate": 9.042458762497914e-06, "loss": 0.3815, "step": 235740 }, { "epoch": 1.4013469574573056, "grad_norm": 5.664590358734131, "learning_rate": 9.042336648342437e-06, "loss": 0.4093, "step": 235750 }, { "epoch": 1.401406399533974, "grad_norm": 4.062880992889404, "learning_rate": 9.042214527225574e-06, "loss": 0.3697, "step": 235760 }, { "epoch": 1.4014658416106425, "grad_norm": 3.823061943054199, "learning_rate": 9.042092399147535e-06, "loss": 0.3523, "step": 235770 }, { "epoch": 1.4015252836873109, "grad_norm": 5.61363410949707, "learning_rate": 9.041970264108531e-06, "loss": 0.391, "step": 235780 }, { "epoch": 1.4015847257639793, "grad_norm": 5.054015159606934, "learning_rate": 9.041848122108771e-06, "loss": 0.4018, "step": 235790 }, { "epoch": 1.4016441678406477, "grad_norm": 4.9541802406311035, "learning_rate": 9.041725973148467e-06, "loss": 0.363, "step": 235800 }, { "epoch": 1.4017036099173161, "grad_norm": 4.78214168548584, "learning_rate": 9.04160381722783e-06, "loss": 0.3808, "step": 235810 }, { "epoch": 1.4017630519939845, "grad_norm": 3.7548935413360596, "learning_rate": 9.041481654347068e-06, "loss": 0.376, "step": 235820 }, { "epoch": 1.401822494070653, "grad_norm": 4.995851516723633, "learning_rate": 9.04135948450639e-06, "loss": 0.3897, "step": 235830 }, { "epoch": 1.4018819361473214, "grad_norm": 7.174063682556152, "learning_rate": 9.041237307706013e-06, "loss": 0.3311, "step": 235840 }, { "epoch": 1.4019413782239896, "grad_norm": 5.94321346282959, "learning_rate": 9.04111512394614e-06, "loss": 0.4184, "step": 235850 }, { "epoch": 1.402000820300658, "grad_norm": 5.094141483306885, "learning_rate": 9.040992933226986e-06, "loss": 0.4036, "step": 235860 }, { "epoch": 1.4020602623773264, "grad_norm": 5.612638473510742, "learning_rate": 9.040870735548759e-06, "loss": 0.3607, "step": 235870 }, { "epoch": 1.4021197044539948, "grad_norm": 4.8119072914123535, "learning_rate": 9.040748530911672e-06, "loss": 0.401, "step": 235880 }, { "epoch": 1.4021791465306632, "grad_norm": 5.133551597595215, "learning_rate": 9.040626319315933e-06, "loss": 0.3754, "step": 235890 }, { "epoch": 1.4022385886073316, "grad_norm": 6.222679138183594, "learning_rate": 9.040504100761752e-06, "loss": 0.4135, "step": 235900 }, { "epoch": 1.402298030684, "grad_norm": 4.649223327636719, "learning_rate": 9.040381875249341e-06, "loss": 0.3774, "step": 235910 }, { "epoch": 1.4023574727606682, "grad_norm": 4.637944221496582, "learning_rate": 9.040259642778912e-06, "loss": 0.4114, "step": 235920 }, { "epoch": 1.4024169148373367, "grad_norm": 7.756821632385254, "learning_rate": 9.040137403350674e-06, "loss": 0.3995, "step": 235930 }, { "epoch": 1.402476356914005, "grad_norm": 5.07365083694458, "learning_rate": 9.040015156964837e-06, "loss": 0.3475, "step": 235940 }, { "epoch": 1.4025357989906735, "grad_norm": 4.6534271240234375, "learning_rate": 9.03989290362161e-06, "loss": 0.4038, "step": 235950 }, { "epoch": 1.402595241067342, "grad_norm": 4.307662010192871, "learning_rate": 9.039770643321209e-06, "loss": 0.3588, "step": 235960 }, { "epoch": 1.4026546831440103, "grad_norm": 4.663610458374023, "learning_rate": 9.039648376063838e-06, "loss": 0.385, "step": 235970 }, { "epoch": 1.4027141252206787, "grad_norm": 3.80208683013916, "learning_rate": 9.039526101849711e-06, "loss": 0.3856, "step": 235980 }, { "epoch": 1.4027735672973471, "grad_norm": 4.195587158203125, "learning_rate": 9.039403820679038e-06, "loss": 0.3852, "step": 235990 }, { "epoch": 1.4028330093740156, "grad_norm": 4.789480686187744, "learning_rate": 9.03928153255203e-06, "loss": 0.3413, "step": 236000 }, { "epoch": 1.402892451450684, "grad_norm": 4.583400726318359, "learning_rate": 9.039159237468898e-06, "loss": 0.3704, "step": 236010 }, { "epoch": 1.4029518935273524, "grad_norm": 6.052829265594482, "learning_rate": 9.03903693542985e-06, "loss": 0.3128, "step": 236020 }, { "epoch": 1.4030113356040206, "grad_norm": 5.860992431640625, "learning_rate": 9.0389146264351e-06, "loss": 0.4292, "step": 236030 }, { "epoch": 1.403070777680689, "grad_norm": 6.064321041107178, "learning_rate": 9.038792310484857e-06, "loss": 0.3749, "step": 236040 }, { "epoch": 1.4031302197573574, "grad_norm": 3.371105432510376, "learning_rate": 9.03866998757933e-06, "loss": 0.3516, "step": 236050 }, { "epoch": 1.4031896618340258, "grad_norm": 6.150348663330078, "learning_rate": 9.038547657718734e-06, "loss": 0.3929, "step": 236060 }, { "epoch": 1.4032491039106942, "grad_norm": 4.066555976867676, "learning_rate": 9.038425320903275e-06, "loss": 0.3824, "step": 236070 }, { "epoch": 1.4033085459873627, "grad_norm": 7.2422075271606445, "learning_rate": 9.038302977133166e-06, "loss": 0.3832, "step": 236080 }, { "epoch": 1.403367988064031, "grad_norm": 4.237705707550049, "learning_rate": 9.03818062640862e-06, "loss": 0.3721, "step": 236090 }, { "epoch": 1.4034274301406993, "grad_norm": 4.874255657196045, "learning_rate": 9.038058268729841e-06, "loss": 0.3461, "step": 236100 }, { "epoch": 1.4034868722173677, "grad_norm": 5.275630474090576, "learning_rate": 9.037935904097046e-06, "loss": 0.3838, "step": 236110 }, { "epoch": 1.403546314294036, "grad_norm": 4.621574401855469, "learning_rate": 9.037813532510445e-06, "loss": 0.4111, "step": 236120 }, { "epoch": 1.4036057563707045, "grad_norm": 6.756855487823486, "learning_rate": 9.037691153970244e-06, "loss": 0.4109, "step": 236130 }, { "epoch": 1.403665198447373, "grad_norm": 4.019325256347656, "learning_rate": 9.03756876847666e-06, "loss": 0.3832, "step": 236140 }, { "epoch": 1.4037246405240413, "grad_norm": 4.587062358856201, "learning_rate": 9.0374463760299e-06, "loss": 0.3389, "step": 236150 }, { "epoch": 1.4037840826007097, "grad_norm": 6.746500492095947, "learning_rate": 9.037323976630174e-06, "loss": 0.3759, "step": 236160 }, { "epoch": 1.4038435246773782, "grad_norm": 4.955700874328613, "learning_rate": 9.037201570277696e-06, "loss": 0.3713, "step": 236170 }, { "epoch": 1.4039029667540466, "grad_norm": 4.388116836547852, "learning_rate": 9.037079156972675e-06, "loss": 0.4157, "step": 236180 }, { "epoch": 1.403962408830715, "grad_norm": 5.937274932861328, "learning_rate": 9.036956736715323e-06, "loss": 0.4004, "step": 236190 }, { "epoch": 1.4040218509073834, "grad_norm": 5.108365535736084, "learning_rate": 9.036834309505848e-06, "loss": 0.4128, "step": 236200 }, { "epoch": 1.4040812929840518, "grad_norm": 4.421167373657227, "learning_rate": 9.036711875344464e-06, "loss": 0.3623, "step": 236210 }, { "epoch": 1.40414073506072, "grad_norm": 5.117299556732178, "learning_rate": 9.03658943423138e-06, "loss": 0.3477, "step": 236220 }, { "epoch": 1.4042001771373884, "grad_norm": 6.092824459075928, "learning_rate": 9.036466986166807e-06, "loss": 0.3609, "step": 236230 }, { "epoch": 1.4042596192140568, "grad_norm": 6.141971111297607, "learning_rate": 9.036344531150955e-06, "loss": 0.4082, "step": 236240 }, { "epoch": 1.4043190612907253, "grad_norm": 5.779712200164795, "learning_rate": 9.036222069184039e-06, "loss": 0.3502, "step": 236250 }, { "epoch": 1.4043785033673937, "grad_norm": 7.069151401519775, "learning_rate": 9.036099600266267e-06, "loss": 0.3952, "step": 236260 }, { "epoch": 1.404437945444062, "grad_norm": 4.849919319152832, "learning_rate": 9.035977124397847e-06, "loss": 0.3597, "step": 236270 }, { "epoch": 1.4044973875207305, "grad_norm": 4.394993305206299, "learning_rate": 9.035854641578994e-06, "loss": 0.3355, "step": 236280 }, { "epoch": 1.4045568295973987, "grad_norm": 5.8178815841674805, "learning_rate": 9.035732151809919e-06, "loss": 0.3812, "step": 236290 }, { "epoch": 1.404616271674067, "grad_norm": 5.2297844886779785, "learning_rate": 9.03560965509083e-06, "loss": 0.3769, "step": 236300 }, { "epoch": 1.4046757137507355, "grad_norm": 5.662918567657471, "learning_rate": 9.03548715142194e-06, "loss": 0.371, "step": 236310 }, { "epoch": 1.404735155827404, "grad_norm": 5.555050373077393, "learning_rate": 9.03536464080346e-06, "loss": 0.4123, "step": 236320 }, { "epoch": 1.4047945979040724, "grad_norm": 4.689886093139648, "learning_rate": 9.035242123235602e-06, "loss": 0.3899, "step": 236330 }, { "epoch": 1.4048540399807408, "grad_norm": 6.261574745178223, "learning_rate": 9.035119598718574e-06, "loss": 0.3817, "step": 236340 }, { "epoch": 1.4049134820574092, "grad_norm": 4.49146032333374, "learning_rate": 9.034997067252587e-06, "loss": 0.3979, "step": 236350 }, { "epoch": 1.4049729241340776, "grad_norm": 4.650092124938965, "learning_rate": 9.034874528837856e-06, "loss": 0.3656, "step": 236360 }, { "epoch": 1.405032366210746, "grad_norm": 6.0689849853515625, "learning_rate": 9.03475198347459e-06, "loss": 0.3736, "step": 236370 }, { "epoch": 1.4050918082874144, "grad_norm": 4.7959723472595215, "learning_rate": 9.034629431162998e-06, "loss": 0.3571, "step": 236380 }, { "epoch": 1.4051512503640828, "grad_norm": 5.789693355560303, "learning_rate": 9.034506871903294e-06, "loss": 0.4046, "step": 236390 }, { "epoch": 1.405210692440751, "grad_norm": 7.014885902404785, "learning_rate": 9.034384305695687e-06, "loss": 0.3737, "step": 236400 }, { "epoch": 1.4052701345174194, "grad_norm": 4.896275520324707, "learning_rate": 9.034261732540387e-06, "loss": 0.3506, "step": 236410 }, { "epoch": 1.4053295765940879, "grad_norm": 4.073861598968506, "learning_rate": 9.034139152437611e-06, "loss": 0.3607, "step": 236420 }, { "epoch": 1.4053890186707563, "grad_norm": 6.18184232711792, "learning_rate": 9.034016565387563e-06, "loss": 0.3963, "step": 236430 }, { "epoch": 1.4054484607474247, "grad_norm": 6.042287349700928, "learning_rate": 9.03389397139046e-06, "loss": 0.3824, "step": 236440 }, { "epoch": 1.405507902824093, "grad_norm": 6.385483264923096, "learning_rate": 9.033771370446507e-06, "loss": 0.3645, "step": 236450 }, { "epoch": 1.4055673449007615, "grad_norm": 5.575207710266113, "learning_rate": 9.03364876255592e-06, "loss": 0.365, "step": 236460 }, { "epoch": 1.4056267869774297, "grad_norm": 5.891155242919922, "learning_rate": 9.033526147718907e-06, "loss": 0.3432, "step": 236470 }, { "epoch": 1.4056862290540981, "grad_norm": 4.196707248687744, "learning_rate": 9.033403525935681e-06, "loss": 0.3796, "step": 236480 }, { "epoch": 1.4057456711307665, "grad_norm": 4.443968296051025, "learning_rate": 9.033280897206455e-06, "loss": 0.3575, "step": 236490 }, { "epoch": 1.405805113207435, "grad_norm": 3.2246768474578857, "learning_rate": 9.033158261531438e-06, "loss": 0.3502, "step": 236500 }, { "epoch": 1.4058645552841034, "grad_norm": 6.421701908111572, "learning_rate": 9.03303561891084e-06, "loss": 0.382, "step": 236510 }, { "epoch": 1.4059239973607718, "grad_norm": 5.524577617645264, "learning_rate": 9.032912969344873e-06, "loss": 0.3779, "step": 236520 }, { "epoch": 1.4059834394374402, "grad_norm": 5.035128593444824, "learning_rate": 9.03279031283375e-06, "loss": 0.3315, "step": 236530 }, { "epoch": 1.4060428815141086, "grad_norm": 6.482256889343262, "learning_rate": 9.03266764937768e-06, "loss": 0.3431, "step": 236540 }, { "epoch": 1.406102323590777, "grad_norm": 4.4525628089904785, "learning_rate": 9.032544978976876e-06, "loss": 0.3625, "step": 236550 }, { "epoch": 1.4061617656674454, "grad_norm": 5.694743633270264, "learning_rate": 9.032422301631547e-06, "loss": 0.3816, "step": 236560 }, { "epoch": 1.4062212077441139, "grad_norm": 4.561776161193848, "learning_rate": 9.032299617341907e-06, "loss": 0.3996, "step": 236570 }, { "epoch": 1.4062806498207823, "grad_norm": 3.9241693019866943, "learning_rate": 9.032176926108164e-06, "loss": 0.3565, "step": 236580 }, { "epoch": 1.4063400918974505, "grad_norm": 5.266925811767578, "learning_rate": 9.032054227930534e-06, "loss": 0.3502, "step": 236590 }, { "epoch": 1.4063995339741189, "grad_norm": 6.625753879547119, "learning_rate": 9.031931522809224e-06, "loss": 0.3725, "step": 236600 }, { "epoch": 1.4064589760507873, "grad_norm": 5.699306964874268, "learning_rate": 9.031808810744447e-06, "loss": 0.3984, "step": 236610 }, { "epoch": 1.4065184181274557, "grad_norm": 6.043219566345215, "learning_rate": 9.031686091736413e-06, "loss": 0.3775, "step": 236620 }, { "epoch": 1.4065778602041241, "grad_norm": 3.629511594772339, "learning_rate": 9.031563365785336e-06, "loss": 0.3709, "step": 236630 }, { "epoch": 1.4066373022807925, "grad_norm": 4.772734642028809, "learning_rate": 9.031440632891426e-06, "loss": 0.3583, "step": 236640 }, { "epoch": 1.406696744357461, "grad_norm": 4.588901996612549, "learning_rate": 9.031317893054894e-06, "loss": 0.3758, "step": 236650 }, { "epoch": 1.4067561864341291, "grad_norm": 7.442616939544678, "learning_rate": 9.03119514627595e-06, "loss": 0.3962, "step": 236660 }, { "epoch": 1.4068156285107976, "grad_norm": 6.121880054473877, "learning_rate": 9.03107239255481e-06, "loss": 0.3877, "step": 236670 }, { "epoch": 1.406875070587466, "grad_norm": 4.8670477867126465, "learning_rate": 9.030949631891679e-06, "loss": 0.3419, "step": 236680 }, { "epoch": 1.4069345126641344, "grad_norm": 5.825854778289795, "learning_rate": 9.030826864286774e-06, "loss": 0.3852, "step": 236690 }, { "epoch": 1.4069939547408028, "grad_norm": 6.046542644500732, "learning_rate": 9.030704089740304e-06, "loss": 0.3849, "step": 236700 }, { "epoch": 1.4070533968174712, "grad_norm": 6.841022491455078, "learning_rate": 9.03058130825248e-06, "loss": 0.3748, "step": 236710 }, { "epoch": 1.4071128388941396, "grad_norm": 4.173027038574219, "learning_rate": 9.030458519823513e-06, "loss": 0.3693, "step": 236720 }, { "epoch": 1.407172280970808, "grad_norm": 5.43383264541626, "learning_rate": 9.030335724453618e-06, "loss": 0.3881, "step": 236730 }, { "epoch": 1.4072317230474765, "grad_norm": 4.132787227630615, "learning_rate": 9.030212922143002e-06, "loss": 0.3416, "step": 236740 }, { "epoch": 1.4072911651241449, "grad_norm": 5.948251247406006, "learning_rate": 9.03009011289188e-06, "loss": 0.3456, "step": 236750 }, { "epoch": 1.4073506072008133, "grad_norm": 6.834616661071777, "learning_rate": 9.02996729670046e-06, "loss": 0.3644, "step": 236760 }, { "epoch": 1.4074100492774815, "grad_norm": 3.554898738861084, "learning_rate": 9.029844473568956e-06, "loss": 0.3901, "step": 236770 }, { "epoch": 1.40746949135415, "grad_norm": 4.449458122253418, "learning_rate": 9.02972164349758e-06, "loss": 0.3719, "step": 236780 }, { "epoch": 1.4075289334308183, "grad_norm": 6.018351078033447, "learning_rate": 9.029598806486543e-06, "loss": 0.3921, "step": 236790 }, { "epoch": 1.4075883755074867, "grad_norm": 4.970475196838379, "learning_rate": 9.029475962536054e-06, "loss": 0.3595, "step": 236800 }, { "epoch": 1.4076478175841551, "grad_norm": 5.327314853668213, "learning_rate": 9.029353111646329e-06, "loss": 0.3605, "step": 236810 }, { "epoch": 1.4077072596608236, "grad_norm": 6.0077104568481445, "learning_rate": 9.029230253817575e-06, "loss": 0.3702, "step": 236820 }, { "epoch": 1.407766701737492, "grad_norm": 4.436749458312988, "learning_rate": 9.029107389050007e-06, "loss": 0.3333, "step": 236830 }, { "epoch": 1.4078261438141602, "grad_norm": 4.499398708343506, "learning_rate": 9.028984517343835e-06, "loss": 0.3561, "step": 236840 }, { "epoch": 1.4078855858908286, "grad_norm": 5.281592845916748, "learning_rate": 9.02886163869927e-06, "loss": 0.395, "step": 236850 }, { "epoch": 1.407945027967497, "grad_norm": 5.9613189697265625, "learning_rate": 9.028738753116525e-06, "loss": 0.3637, "step": 236860 }, { "epoch": 1.4080044700441654, "grad_norm": 5.042420864105225, "learning_rate": 9.028615860595813e-06, "loss": 0.375, "step": 236870 }, { "epoch": 1.4080639121208338, "grad_norm": 6.058798789978027, "learning_rate": 9.028492961137343e-06, "loss": 0.4007, "step": 236880 }, { "epoch": 1.4081233541975022, "grad_norm": 4.645135879516602, "learning_rate": 9.028370054741326e-06, "loss": 0.3313, "step": 236890 }, { "epoch": 1.4081827962741706, "grad_norm": 5.748995304107666, "learning_rate": 9.028247141407976e-06, "loss": 0.354, "step": 236900 }, { "epoch": 1.408242238350839, "grad_norm": 4.894736289978027, "learning_rate": 9.028124221137504e-06, "loss": 0.3752, "step": 236910 }, { "epoch": 1.4083016804275075, "grad_norm": 6.232283115386963, "learning_rate": 9.028001293930123e-06, "loss": 0.3651, "step": 236920 }, { "epoch": 1.4083611225041759, "grad_norm": 6.3612823486328125, "learning_rate": 9.02787835978604e-06, "loss": 0.3854, "step": 236930 }, { "epoch": 1.4084205645808443, "grad_norm": 4.098033428192139, "learning_rate": 9.027755418705471e-06, "loss": 0.3413, "step": 236940 }, { "epoch": 1.4084800066575127, "grad_norm": 5.662503719329834, "learning_rate": 9.027632470688627e-06, "loss": 0.3888, "step": 236950 }, { "epoch": 1.408539448734181, "grad_norm": 5.5964179039001465, "learning_rate": 9.02750951573572e-06, "loss": 0.3785, "step": 236960 }, { "epoch": 1.4085988908108493, "grad_norm": 4.757570743560791, "learning_rate": 9.02738655384696e-06, "loss": 0.333, "step": 236970 }, { "epoch": 1.4086583328875177, "grad_norm": 3.765592575073242, "learning_rate": 9.02726358502256e-06, "loss": 0.3473, "step": 236980 }, { "epoch": 1.4087177749641862, "grad_norm": 4.940054893493652, "learning_rate": 9.027140609262732e-06, "loss": 0.3182, "step": 236990 }, { "epoch": 1.4087772170408546, "grad_norm": 4.7532806396484375, "learning_rate": 9.027017626567686e-06, "loss": 0.34, "step": 237000 }, { "epoch": 1.408836659117523, "grad_norm": 3.5340280532836914, "learning_rate": 9.026894636937636e-06, "loss": 0.404, "step": 237010 }, { "epoch": 1.4088961011941914, "grad_norm": 5.965267658233643, "learning_rate": 9.026771640372794e-06, "loss": 0.3688, "step": 237020 }, { "epoch": 1.4089555432708596, "grad_norm": 4.681600570678711, "learning_rate": 9.026648636873369e-06, "loss": 0.3684, "step": 237030 }, { "epoch": 1.409014985347528, "grad_norm": 6.552794456481934, "learning_rate": 9.026525626439575e-06, "loss": 0.359, "step": 237040 }, { "epoch": 1.4090744274241964, "grad_norm": 6.079900741577148, "learning_rate": 9.026402609071624e-06, "loss": 0.4129, "step": 237050 }, { "epoch": 1.4091338695008648, "grad_norm": 5.244453430175781, "learning_rate": 9.026279584769727e-06, "loss": 0.3797, "step": 237060 }, { "epoch": 1.4091933115775332, "grad_norm": 4.59080171585083, "learning_rate": 9.026156553534096e-06, "loss": 0.4247, "step": 237070 }, { "epoch": 1.4092527536542017, "grad_norm": 6.237450122833252, "learning_rate": 9.026033515364943e-06, "loss": 0.4113, "step": 237080 }, { "epoch": 1.40931219573087, "grad_norm": 7.564767837524414, "learning_rate": 9.02591047026248e-06, "loss": 0.3979, "step": 237090 }, { "epoch": 1.4093716378075385, "grad_norm": 6.395269870758057, "learning_rate": 9.02578741822692e-06, "loss": 0.3814, "step": 237100 }, { "epoch": 1.409431079884207, "grad_norm": 5.594934940338135, "learning_rate": 9.025664359258473e-06, "loss": 0.3699, "step": 237110 }, { "epoch": 1.4094905219608753, "grad_norm": 5.433999538421631, "learning_rate": 9.025541293357351e-06, "loss": 0.3437, "step": 237120 }, { "epoch": 1.4095499640375437, "grad_norm": 3.6473164558410645, "learning_rate": 9.025418220523767e-06, "loss": 0.3892, "step": 237130 }, { "epoch": 1.409609406114212, "grad_norm": 5.161436080932617, "learning_rate": 9.025295140757932e-06, "loss": 0.3768, "step": 237140 }, { "epoch": 1.4096688481908803, "grad_norm": 4.685422897338867, "learning_rate": 9.02517205406006e-06, "loss": 0.377, "step": 237150 }, { "epoch": 1.4097282902675488, "grad_norm": 6.363135814666748, "learning_rate": 9.025048960430361e-06, "loss": 0.3682, "step": 237160 }, { "epoch": 1.4097877323442172, "grad_norm": 4.876674175262451, "learning_rate": 9.024925859869048e-06, "loss": 0.3661, "step": 237170 }, { "epoch": 1.4098471744208856, "grad_norm": 8.398005485534668, "learning_rate": 9.024802752376328e-06, "loss": 0.3864, "step": 237180 }, { "epoch": 1.409906616497554, "grad_norm": 5.637218952178955, "learning_rate": 9.024679637952423e-06, "loss": 0.4035, "step": 237190 }, { "epoch": 1.4099660585742224, "grad_norm": 4.484912872314453, "learning_rate": 9.024556516597535e-06, "loss": 0.3591, "step": 237200 }, { "epoch": 1.4100255006508906, "grad_norm": 4.356809616088867, "learning_rate": 9.024433388311883e-06, "loss": 0.4122, "step": 237210 }, { "epoch": 1.410084942727559, "grad_norm": 4.9483561515808105, "learning_rate": 9.024310253095677e-06, "loss": 0.3762, "step": 237220 }, { "epoch": 1.4101443848042274, "grad_norm": 4.73459005355835, "learning_rate": 9.024187110949127e-06, "loss": 0.3501, "step": 237230 }, { "epoch": 1.4102038268808958, "grad_norm": 5.550251483917236, "learning_rate": 9.024063961872449e-06, "loss": 0.3622, "step": 237240 }, { "epoch": 1.4102632689575643, "grad_norm": 4.755807876586914, "learning_rate": 9.02394080586585e-06, "loss": 0.3902, "step": 237250 }, { "epoch": 1.4103227110342327, "grad_norm": 5.230942726135254, "learning_rate": 9.023817642929547e-06, "loss": 0.423, "step": 237260 }, { "epoch": 1.410382153110901, "grad_norm": 5.666652202606201, "learning_rate": 9.023694473063747e-06, "loss": 0.3931, "step": 237270 }, { "epoch": 1.4104415951875695, "grad_norm": 4.157620906829834, "learning_rate": 9.023571296268667e-06, "loss": 0.3443, "step": 237280 }, { "epoch": 1.410501037264238, "grad_norm": 4.259225845336914, "learning_rate": 9.023448112544518e-06, "loss": 0.3607, "step": 237290 }, { "epoch": 1.4105604793409063, "grad_norm": 3.2374062538146973, "learning_rate": 9.02332492189151e-06, "loss": 0.3952, "step": 237300 }, { "epoch": 1.4106199214175748, "grad_norm": 5.181187629699707, "learning_rate": 9.023201724309855e-06, "loss": 0.4005, "step": 237310 }, { "epoch": 1.4106793634942432, "grad_norm": 4.276620388031006, "learning_rate": 9.023078519799769e-06, "loss": 0.3903, "step": 237320 }, { "epoch": 1.4107388055709114, "grad_norm": 4.032047748565674, "learning_rate": 9.02295530836146e-06, "loss": 0.4216, "step": 237330 }, { "epoch": 1.4107982476475798, "grad_norm": 5.669396877288818, "learning_rate": 9.022832089995144e-06, "loss": 0.3686, "step": 237340 }, { "epoch": 1.4108576897242482, "grad_norm": 6.18440055847168, "learning_rate": 9.02270886470103e-06, "loss": 0.4233, "step": 237350 }, { "epoch": 1.4109171318009166, "grad_norm": 8.45340633392334, "learning_rate": 9.022585632479332e-06, "loss": 0.425, "step": 237360 }, { "epoch": 1.410976573877585, "grad_norm": 4.416017055511475, "learning_rate": 9.02246239333026e-06, "loss": 0.3668, "step": 237370 }, { "epoch": 1.4110360159542534, "grad_norm": 5.933701992034912, "learning_rate": 9.02233914725403e-06, "loss": 0.4142, "step": 237380 }, { "epoch": 1.4110954580309218, "grad_norm": 4.616318225860596, "learning_rate": 9.02221589425085e-06, "loss": 0.3305, "step": 237390 }, { "epoch": 1.41115490010759, "grad_norm": 4.000852108001709, "learning_rate": 9.022092634320935e-06, "loss": 0.363, "step": 237400 }, { "epoch": 1.4112143421842585, "grad_norm": 5.68461799621582, "learning_rate": 9.021969367464498e-06, "loss": 0.3689, "step": 237410 }, { "epoch": 1.4112737842609269, "grad_norm": 6.007453918457031, "learning_rate": 9.021846093681747e-06, "loss": 0.3921, "step": 237420 }, { "epoch": 1.4113332263375953, "grad_norm": 4.900369644165039, "learning_rate": 9.0217228129729e-06, "loss": 0.3909, "step": 237430 }, { "epoch": 1.4113926684142637, "grad_norm": 4.4955973625183105, "learning_rate": 9.021599525338164e-06, "loss": 0.3933, "step": 237440 }, { "epoch": 1.411452110490932, "grad_norm": 5.931891918182373, "learning_rate": 9.021476230777756e-06, "loss": 0.3758, "step": 237450 }, { "epoch": 1.4115115525676005, "grad_norm": 4.459069728851318, "learning_rate": 9.021352929291885e-06, "loss": 0.3447, "step": 237460 }, { "epoch": 1.411570994644269, "grad_norm": 6.50747537612915, "learning_rate": 9.021229620880765e-06, "loss": 0.3908, "step": 237470 }, { "epoch": 1.4116304367209374, "grad_norm": 4.411740779876709, "learning_rate": 9.021106305544607e-06, "loss": 0.3376, "step": 237480 }, { "epoch": 1.4116898787976058, "grad_norm": 4.868409633636475, "learning_rate": 9.020982983283624e-06, "loss": 0.3557, "step": 237490 }, { "epoch": 1.4117493208742742, "grad_norm": 4.982208251953125, "learning_rate": 9.020859654098029e-06, "loss": 0.3701, "step": 237500 }, { "epoch": 1.4118087629509424, "grad_norm": 5.1325907707214355, "learning_rate": 9.020736317988035e-06, "loss": 0.3944, "step": 237510 }, { "epoch": 1.4118682050276108, "grad_norm": 5.457051753997803, "learning_rate": 9.020612974953851e-06, "loss": 0.3927, "step": 237520 }, { "epoch": 1.4119276471042792, "grad_norm": 5.383574485778809, "learning_rate": 9.020489624995694e-06, "loss": 0.3307, "step": 237530 }, { "epoch": 1.4119870891809476, "grad_norm": 4.52662992477417, "learning_rate": 9.020366268113771e-06, "loss": 0.3789, "step": 237540 }, { "epoch": 1.412046531257616, "grad_norm": 4.669181823730469, "learning_rate": 9.0202429043083e-06, "loss": 0.3761, "step": 237550 }, { "epoch": 1.4121059733342844, "grad_norm": 5.677224636077881, "learning_rate": 9.020119533579492e-06, "loss": 0.3634, "step": 237560 }, { "epoch": 1.4121654154109529, "grad_norm": 4.448680877685547, "learning_rate": 9.019996155927557e-06, "loss": 0.3445, "step": 237570 }, { "epoch": 1.412224857487621, "grad_norm": 5.420155048370361, "learning_rate": 9.019872771352708e-06, "loss": 0.3517, "step": 237580 }, { "epoch": 1.4122842995642895, "grad_norm": 6.276263236999512, "learning_rate": 9.019749379855161e-06, "loss": 0.4037, "step": 237590 }, { "epoch": 1.4123437416409579, "grad_norm": 4.859986305236816, "learning_rate": 9.019625981435123e-06, "loss": 0.3694, "step": 237600 }, { "epoch": 1.4124031837176263, "grad_norm": 5.160341262817383, "learning_rate": 9.019502576092813e-06, "loss": 0.39, "step": 237610 }, { "epoch": 1.4124626257942947, "grad_norm": 4.4265241622924805, "learning_rate": 9.019379163828437e-06, "loss": 0.3756, "step": 237620 }, { "epoch": 1.4125220678709631, "grad_norm": 5.789834499359131, "learning_rate": 9.01925574464221e-06, "loss": 0.3741, "step": 237630 }, { "epoch": 1.4125815099476315, "grad_norm": 5.233291149139404, "learning_rate": 9.019132318534347e-06, "loss": 0.3612, "step": 237640 }, { "epoch": 1.4126409520243, "grad_norm": 4.936072826385498, "learning_rate": 9.019008885505058e-06, "loss": 0.4116, "step": 237650 }, { "epoch": 1.4127003941009684, "grad_norm": 5.189456939697266, "learning_rate": 9.018885445554556e-06, "loss": 0.3576, "step": 237660 }, { "epoch": 1.4127598361776368, "grad_norm": 3.949340343475342, "learning_rate": 9.018761998683055e-06, "loss": 0.3249, "step": 237670 }, { "epoch": 1.4128192782543052, "grad_norm": 6.041872024536133, "learning_rate": 9.018638544890765e-06, "loss": 0.3895, "step": 237680 }, { "epoch": 1.4128787203309736, "grad_norm": 5.683066368103027, "learning_rate": 9.018515084177902e-06, "loss": 0.3717, "step": 237690 }, { "epoch": 1.4129381624076418, "grad_norm": 4.4127397537231445, "learning_rate": 9.018391616544673e-06, "loss": 0.3775, "step": 237700 }, { "epoch": 1.4129976044843102, "grad_norm": 6.852243423461914, "learning_rate": 9.018268141991295e-06, "loss": 0.3942, "step": 237710 }, { "epoch": 1.4130570465609786, "grad_norm": 4.094921112060547, "learning_rate": 9.018144660517983e-06, "loss": 0.4097, "step": 237720 }, { "epoch": 1.413116488637647, "grad_norm": 5.31835412979126, "learning_rate": 9.018021172124943e-06, "loss": 0.3325, "step": 237730 }, { "epoch": 1.4131759307143155, "grad_norm": 6.050485134124756, "learning_rate": 9.017897676812392e-06, "loss": 0.4169, "step": 237740 }, { "epoch": 1.4132353727909839, "grad_norm": 3.9172306060791016, "learning_rate": 9.017774174580542e-06, "loss": 0.3668, "step": 237750 }, { "epoch": 1.4132948148676523, "grad_norm": 6.044376850128174, "learning_rate": 9.017650665429605e-06, "loss": 0.3524, "step": 237760 }, { "epoch": 1.4133542569443205, "grad_norm": 4.983534812927246, "learning_rate": 9.017527149359796e-06, "loss": 0.3693, "step": 237770 }, { "epoch": 1.413413699020989, "grad_norm": 4.642873764038086, "learning_rate": 9.017403626371324e-06, "loss": 0.379, "step": 237780 }, { "epoch": 1.4134731410976573, "grad_norm": 5.755893707275391, "learning_rate": 9.017280096464404e-06, "loss": 0.3535, "step": 237790 }, { "epoch": 1.4135325831743257, "grad_norm": 4.455787181854248, "learning_rate": 9.01715655963925e-06, "loss": 0.4066, "step": 237800 }, { "epoch": 1.4135920252509941, "grad_norm": 6.223581790924072, "learning_rate": 9.017033015896071e-06, "loss": 0.3417, "step": 237810 }, { "epoch": 1.4136514673276626, "grad_norm": 4.022331714630127, "learning_rate": 9.016909465235082e-06, "loss": 0.373, "step": 237820 }, { "epoch": 1.413710909404331, "grad_norm": 5.061978340148926, "learning_rate": 9.016785907656497e-06, "loss": 0.3807, "step": 237830 }, { "epoch": 1.4137703514809994, "grad_norm": 5.172269344329834, "learning_rate": 9.016662343160525e-06, "loss": 0.3914, "step": 237840 }, { "epoch": 1.4138297935576678, "grad_norm": 4.95280647277832, "learning_rate": 9.016538771747385e-06, "loss": 0.367, "step": 237850 }, { "epoch": 1.4138892356343362, "grad_norm": 3.749368667602539, "learning_rate": 9.016415193417283e-06, "loss": 0.367, "step": 237860 }, { "epoch": 1.4139486777110046, "grad_norm": 5.089090824127197, "learning_rate": 9.016291608170436e-06, "loss": 0.3873, "step": 237870 }, { "epoch": 1.4140081197876728, "grad_norm": 5.462857246398926, "learning_rate": 9.016168016007053e-06, "loss": 0.3545, "step": 237880 }, { "epoch": 1.4140675618643412, "grad_norm": 6.009264945983887, "learning_rate": 9.016044416927354e-06, "loss": 0.3752, "step": 237890 }, { "epoch": 1.4141270039410097, "grad_norm": 5.587552070617676, "learning_rate": 9.015920810931545e-06, "loss": 0.3525, "step": 237900 }, { "epoch": 1.414186446017678, "grad_norm": 3.234354257583618, "learning_rate": 9.01579719801984e-06, "loss": 0.328, "step": 237910 }, { "epoch": 1.4142458880943465, "grad_norm": 5.8855814933776855, "learning_rate": 9.015673578192454e-06, "loss": 0.3589, "step": 237920 }, { "epoch": 1.414305330171015, "grad_norm": 5.697781562805176, "learning_rate": 9.0155499514496e-06, "loss": 0.3979, "step": 237930 }, { "epoch": 1.4143647722476833, "grad_norm": 4.866982936859131, "learning_rate": 9.015426317791488e-06, "loss": 0.3978, "step": 237940 }, { "epoch": 1.4144242143243515, "grad_norm": 4.83951997756958, "learning_rate": 9.015302677218334e-06, "loss": 0.371, "step": 237950 }, { "epoch": 1.41448365640102, "grad_norm": 4.428467750549316, "learning_rate": 9.01517902973035e-06, "loss": 0.3381, "step": 237960 }, { "epoch": 1.4145430984776883, "grad_norm": 6.1927595138549805, "learning_rate": 9.015055375327747e-06, "loss": 0.3471, "step": 237970 }, { "epoch": 1.4146025405543567, "grad_norm": 5.000892639160156, "learning_rate": 9.014931714010742e-06, "loss": 0.3863, "step": 237980 }, { "epoch": 1.4146619826310252, "grad_norm": 4.636439800262451, "learning_rate": 9.014808045779545e-06, "loss": 0.4374, "step": 237990 }, { "epoch": 1.4147214247076936, "grad_norm": 4.791009426116943, "learning_rate": 9.014684370634369e-06, "loss": 0.3994, "step": 238000 }, { "epoch": 1.414780866784362, "grad_norm": 4.845305919647217, "learning_rate": 9.014560688575425e-06, "loss": 0.3647, "step": 238010 }, { "epoch": 1.4148403088610304, "grad_norm": 3.7301316261291504, "learning_rate": 9.01443699960293e-06, "loss": 0.3673, "step": 238020 }, { "epoch": 1.4148997509376988, "grad_norm": 6.512169361114502, "learning_rate": 9.014313303717097e-06, "loss": 0.3793, "step": 238030 }, { "epoch": 1.4149591930143672, "grad_norm": 5.590819358825684, "learning_rate": 9.014189600918137e-06, "loss": 0.3781, "step": 238040 }, { "epoch": 1.4150186350910356, "grad_norm": 4.588690280914307, "learning_rate": 9.014065891206263e-06, "loss": 0.3846, "step": 238050 }, { "epoch": 1.415078077167704, "grad_norm": 5.171382427215576, "learning_rate": 9.01394217458169e-06, "loss": 0.337, "step": 238060 }, { "epoch": 1.4151375192443723, "grad_norm": 4.128319263458252, "learning_rate": 9.013818451044627e-06, "loss": 0.3642, "step": 238070 }, { "epoch": 1.4151969613210407, "grad_norm": 4.103898525238037, "learning_rate": 9.013694720595292e-06, "loss": 0.3466, "step": 238080 }, { "epoch": 1.415256403397709, "grad_norm": 3.6544930934906006, "learning_rate": 9.013570983233894e-06, "loss": 0.3606, "step": 238090 }, { "epoch": 1.4153158454743775, "grad_norm": 5.608826637268066, "learning_rate": 9.013447238960648e-06, "loss": 0.3526, "step": 238100 }, { "epoch": 1.415375287551046, "grad_norm": 5.166215896606445, "learning_rate": 9.01332348777577e-06, "loss": 0.4096, "step": 238110 }, { "epoch": 1.4154347296277143, "grad_norm": 5.422319412231445, "learning_rate": 9.013199729679468e-06, "loss": 0.3895, "step": 238120 }, { "epoch": 1.4154941717043827, "grad_norm": 4.6481709480285645, "learning_rate": 9.013075964671956e-06, "loss": 0.3719, "step": 238130 }, { "epoch": 1.415553613781051, "grad_norm": 5.655405044555664, "learning_rate": 9.01295219275345e-06, "loss": 0.3586, "step": 238140 }, { "epoch": 1.4156130558577193, "grad_norm": 3.9636316299438477, "learning_rate": 9.01282841392416e-06, "loss": 0.3601, "step": 238150 }, { "epoch": 1.4156724979343878, "grad_norm": 6.139506816864014, "learning_rate": 9.012704628184303e-06, "loss": 0.4165, "step": 238160 }, { "epoch": 1.4157319400110562, "grad_norm": 5.277230262756348, "learning_rate": 9.012580835534088e-06, "loss": 0.3305, "step": 238170 }, { "epoch": 1.4157913820877246, "grad_norm": 4.938276767730713, "learning_rate": 9.01245703597373e-06, "loss": 0.3703, "step": 238180 }, { "epoch": 1.415850824164393, "grad_norm": 5.494331359863281, "learning_rate": 9.012333229503442e-06, "loss": 0.393, "step": 238190 }, { "epoch": 1.4159102662410614, "grad_norm": 4.74094820022583, "learning_rate": 9.012209416123439e-06, "loss": 0.3568, "step": 238200 }, { "epoch": 1.4159697083177298, "grad_norm": 4.858513355255127, "learning_rate": 9.012085595833933e-06, "loss": 0.3596, "step": 238210 }, { "epoch": 1.4160291503943983, "grad_norm": 5.604734897613525, "learning_rate": 9.011961768635135e-06, "loss": 0.3376, "step": 238220 }, { "epoch": 1.4160885924710667, "grad_norm": 5.1890034675598145, "learning_rate": 9.01183793452726e-06, "loss": 0.3757, "step": 238230 }, { "epoch": 1.416148034547735, "grad_norm": 4.825851917266846, "learning_rate": 9.011714093510524e-06, "loss": 0.3686, "step": 238240 }, { "epoch": 1.4162074766244033, "grad_norm": 6.466336250305176, "learning_rate": 9.011590245585134e-06, "loss": 0.3645, "step": 238250 }, { "epoch": 1.4162669187010717, "grad_norm": 4.389820575714111, "learning_rate": 9.011466390751308e-06, "loss": 0.3471, "step": 238260 }, { "epoch": 1.41632636077774, "grad_norm": 5.324219226837158, "learning_rate": 9.01134252900926e-06, "loss": 0.3779, "step": 238270 }, { "epoch": 1.4163858028544085, "grad_norm": 4.746215343475342, "learning_rate": 9.011218660359202e-06, "loss": 0.3566, "step": 238280 }, { "epoch": 1.416445244931077, "grad_norm": 4.773647785186768, "learning_rate": 9.011094784801345e-06, "loss": 0.4079, "step": 238290 }, { "epoch": 1.4165046870077453, "grad_norm": 5.48347806930542, "learning_rate": 9.010970902335905e-06, "loss": 0.3698, "step": 238300 }, { "epoch": 1.4165641290844138, "grad_norm": 4.386343002319336, "learning_rate": 9.010847012963093e-06, "loss": 0.36, "step": 238310 }, { "epoch": 1.416623571161082, "grad_norm": 6.731029987335205, "learning_rate": 9.010723116683125e-06, "loss": 0.4002, "step": 238320 }, { "epoch": 1.4166830132377504, "grad_norm": 7.033021926879883, "learning_rate": 9.010599213496213e-06, "loss": 0.3764, "step": 238330 }, { "epoch": 1.4167424553144188, "grad_norm": 5.12873649597168, "learning_rate": 9.010475303402571e-06, "loss": 0.3561, "step": 238340 }, { "epoch": 1.4168018973910872, "grad_norm": 3.6679062843322754, "learning_rate": 9.010351386402412e-06, "loss": 0.3817, "step": 238350 }, { "epoch": 1.4168613394677556, "grad_norm": 5.351810455322266, "learning_rate": 9.01022746249595e-06, "loss": 0.3802, "step": 238360 }, { "epoch": 1.416920781544424, "grad_norm": 4.909972667694092, "learning_rate": 9.010103531683398e-06, "loss": 0.3748, "step": 238370 }, { "epoch": 1.4169802236210924, "grad_norm": 4.2877373695373535, "learning_rate": 9.009979593964969e-06, "loss": 0.3272, "step": 238380 }, { "epoch": 1.4170396656977609, "grad_norm": 3.6258163452148438, "learning_rate": 9.009855649340875e-06, "loss": 0.3325, "step": 238390 }, { "epoch": 1.4170991077744293, "grad_norm": 4.807564735412598, "learning_rate": 9.009731697811332e-06, "loss": 0.3458, "step": 238400 }, { "epoch": 1.4171585498510977, "grad_norm": 4.780511856079102, "learning_rate": 9.009607739376552e-06, "loss": 0.3861, "step": 238410 }, { "epoch": 1.417217991927766, "grad_norm": 6.425661563873291, "learning_rate": 9.009483774036752e-06, "loss": 0.3978, "step": 238420 }, { "epoch": 1.4172774340044345, "grad_norm": 4.367690086364746, "learning_rate": 9.009359801792138e-06, "loss": 0.4051, "step": 238430 }, { "epoch": 1.4173368760811027, "grad_norm": 4.387454986572266, "learning_rate": 9.00923582264293e-06, "loss": 0.3863, "step": 238440 }, { "epoch": 1.4173963181577711, "grad_norm": 4.991693019866943, "learning_rate": 9.009111836589341e-06, "loss": 0.4035, "step": 238450 }, { "epoch": 1.4174557602344395, "grad_norm": 4.821409225463867, "learning_rate": 9.008987843631582e-06, "loss": 0.3815, "step": 238460 }, { "epoch": 1.417515202311108, "grad_norm": 5.347572326660156, "learning_rate": 9.008863843769868e-06, "loss": 0.3806, "step": 238470 }, { "epoch": 1.4175746443877764, "grad_norm": 4.8000617027282715, "learning_rate": 9.008739837004412e-06, "loss": 0.3721, "step": 238480 }, { "epoch": 1.4176340864644448, "grad_norm": 7.916701316833496, "learning_rate": 9.008615823335427e-06, "loss": 0.4202, "step": 238490 }, { "epoch": 1.4176935285411132, "grad_norm": 4.340745449066162, "learning_rate": 9.008491802763128e-06, "loss": 0.3766, "step": 238500 }, { "epoch": 1.4177529706177814, "grad_norm": 5.074230670928955, "learning_rate": 9.008367775287727e-06, "loss": 0.3653, "step": 238510 }, { "epoch": 1.4178124126944498, "grad_norm": 5.415369510650635, "learning_rate": 9.008243740909438e-06, "loss": 0.3837, "step": 238520 }, { "epoch": 1.4178718547711182, "grad_norm": 6.575194835662842, "learning_rate": 9.008119699628477e-06, "loss": 0.3593, "step": 238530 }, { "epoch": 1.4179312968477866, "grad_norm": 6.201816082000732, "learning_rate": 9.007995651445054e-06, "loss": 0.391, "step": 238540 }, { "epoch": 1.417990738924455, "grad_norm": 5.989140510559082, "learning_rate": 9.007871596359386e-06, "loss": 0.4129, "step": 238550 }, { "epoch": 1.4180501810011235, "grad_norm": 5.062399387359619, "learning_rate": 9.007747534371682e-06, "loss": 0.3501, "step": 238560 }, { "epoch": 1.4181096230777919, "grad_norm": 4.641506671905518, "learning_rate": 9.007623465482161e-06, "loss": 0.3737, "step": 238570 }, { "epoch": 1.4181690651544603, "grad_norm": 3.8570380210876465, "learning_rate": 9.007499389691033e-06, "loss": 0.3733, "step": 238580 }, { "epoch": 1.4182285072311287, "grad_norm": 5.868574142456055, "learning_rate": 9.007375306998514e-06, "loss": 0.4176, "step": 238590 }, { "epoch": 1.4182879493077971, "grad_norm": 4.400897979736328, "learning_rate": 9.007251217404816e-06, "loss": 0.3381, "step": 238600 }, { "epoch": 1.4183473913844655, "grad_norm": 7.105812072753906, "learning_rate": 9.007127120910153e-06, "loss": 0.3878, "step": 238610 }, { "epoch": 1.4184068334611337, "grad_norm": 6.4389777183532715, "learning_rate": 9.007003017514739e-06, "loss": 0.3941, "step": 238620 }, { "epoch": 1.4184662755378021, "grad_norm": 4.06434965133667, "learning_rate": 9.006878907218789e-06, "loss": 0.3543, "step": 238630 }, { "epoch": 1.4185257176144705, "grad_norm": 4.72428560256958, "learning_rate": 9.006754790022515e-06, "loss": 0.3633, "step": 238640 }, { "epoch": 1.418585159691139, "grad_norm": 6.1435441970825195, "learning_rate": 9.006630665926129e-06, "loss": 0.3847, "step": 238650 }, { "epoch": 1.4186446017678074, "grad_norm": 5.672520160675049, "learning_rate": 9.006506534929848e-06, "loss": 0.37, "step": 238660 }, { "epoch": 1.4187040438444758, "grad_norm": 4.509183883666992, "learning_rate": 9.006382397033887e-06, "loss": 0.39, "step": 238670 }, { "epoch": 1.4187634859211442, "grad_norm": 4.083316326141357, "learning_rate": 9.006258252238454e-06, "loss": 0.3446, "step": 238680 }, { "epoch": 1.4188229279978124, "grad_norm": 5.8198957443237305, "learning_rate": 9.00613410054377e-06, "loss": 0.3988, "step": 238690 }, { "epoch": 1.4188823700744808, "grad_norm": 5.222778797149658, "learning_rate": 9.00600994195004e-06, "loss": 0.3591, "step": 238700 }, { "epoch": 1.4189418121511492, "grad_norm": 5.803696632385254, "learning_rate": 9.005885776457486e-06, "loss": 0.3543, "step": 238710 }, { "epoch": 1.4190012542278176, "grad_norm": 4.3391194343566895, "learning_rate": 9.005761604066318e-06, "loss": 0.3448, "step": 238720 }, { "epoch": 1.419060696304486, "grad_norm": 5.868214130401611, "learning_rate": 9.005637424776752e-06, "loss": 0.3357, "step": 238730 }, { "epoch": 1.4191201383811545, "grad_norm": 6.515678882598877, "learning_rate": 9.005513238588999e-06, "loss": 0.3751, "step": 238740 }, { "epoch": 1.4191795804578229, "grad_norm": 5.099325656890869, "learning_rate": 9.005389045503276e-06, "loss": 0.3671, "step": 238750 }, { "epoch": 1.4192390225344913, "grad_norm": 4.346776485443115, "learning_rate": 9.005264845519794e-06, "loss": 0.3698, "step": 238760 }, { "epoch": 1.4192984646111597, "grad_norm": 5.3121466636657715, "learning_rate": 9.005140638638767e-06, "loss": 0.3625, "step": 238770 }, { "epoch": 1.4193579066878281, "grad_norm": 5.029825687408447, "learning_rate": 9.005016424860411e-06, "loss": 0.3555, "step": 238780 }, { "epoch": 1.4194173487644965, "grad_norm": 5.75293493270874, "learning_rate": 9.004892204184938e-06, "loss": 0.3698, "step": 238790 }, { "epoch": 1.419476790841165, "grad_norm": 5.627089500427246, "learning_rate": 9.004767976612565e-06, "loss": 0.3786, "step": 238800 }, { "epoch": 1.4195362329178332, "grad_norm": 4.281987190246582, "learning_rate": 9.004643742143502e-06, "loss": 0.3982, "step": 238810 }, { "epoch": 1.4195956749945016, "grad_norm": 6.730819225311279, "learning_rate": 9.004519500777964e-06, "loss": 0.366, "step": 238820 }, { "epoch": 1.41965511707117, "grad_norm": 4.90070104598999, "learning_rate": 9.004395252516167e-06, "loss": 0.3472, "step": 238830 }, { "epoch": 1.4197145591478384, "grad_norm": 5.894533634185791, "learning_rate": 9.004270997358323e-06, "loss": 0.3808, "step": 238840 }, { "epoch": 1.4197740012245068, "grad_norm": 4.4546074867248535, "learning_rate": 9.004146735304646e-06, "loss": 0.3485, "step": 238850 }, { "epoch": 1.4198334433011752, "grad_norm": 5.5994462966918945, "learning_rate": 9.004022466355352e-06, "loss": 0.3697, "step": 238860 }, { "epoch": 1.4198928853778436, "grad_norm": 5.114845275878906, "learning_rate": 9.003898190510652e-06, "loss": 0.3851, "step": 238870 }, { "epoch": 1.4199523274545118, "grad_norm": 4.4526472091674805, "learning_rate": 9.003773907770762e-06, "loss": 0.393, "step": 238880 }, { "epoch": 1.4200117695311802, "grad_norm": 5.128113269805908, "learning_rate": 9.003649618135897e-06, "loss": 0.4024, "step": 238890 }, { "epoch": 1.4200712116078487, "grad_norm": 4.348134517669678, "learning_rate": 9.003525321606268e-06, "loss": 0.3621, "step": 238900 }, { "epoch": 1.420130653684517, "grad_norm": 5.0361714363098145, "learning_rate": 9.003401018182091e-06, "loss": 0.3684, "step": 238910 }, { "epoch": 1.4201900957611855, "grad_norm": 5.599057197570801, "learning_rate": 9.00327670786358e-06, "loss": 0.3978, "step": 238920 }, { "epoch": 1.420249537837854, "grad_norm": 4.330798625946045, "learning_rate": 9.00315239065095e-06, "loss": 0.369, "step": 238930 }, { "epoch": 1.4203089799145223, "grad_norm": 4.410763263702393, "learning_rate": 9.003028066544413e-06, "loss": 0.3756, "step": 238940 }, { "epoch": 1.4203684219911907, "grad_norm": 4.974795818328857, "learning_rate": 9.002903735544183e-06, "loss": 0.3625, "step": 238950 }, { "epoch": 1.4204278640678591, "grad_norm": 4.960745334625244, "learning_rate": 9.002779397650477e-06, "loss": 0.3216, "step": 238960 }, { "epoch": 1.4204873061445276, "grad_norm": 6.037522792816162, "learning_rate": 9.002655052863505e-06, "loss": 0.3484, "step": 238970 }, { "epoch": 1.420546748221196, "grad_norm": 5.981492519378662, "learning_rate": 9.002530701183485e-06, "loss": 0.3614, "step": 238980 }, { "epoch": 1.4206061902978642, "grad_norm": 4.177178859710693, "learning_rate": 9.00240634261063e-06, "loss": 0.3676, "step": 238990 }, { "epoch": 1.4206656323745326, "grad_norm": 6.17052698135376, "learning_rate": 9.002281977145153e-06, "loss": 0.3336, "step": 239000 }, { "epoch": 1.420725074451201, "grad_norm": 4.659122467041016, "learning_rate": 9.002157604787268e-06, "loss": 0.3627, "step": 239010 }, { "epoch": 1.4207845165278694, "grad_norm": 5.054797172546387, "learning_rate": 9.002033225537191e-06, "loss": 0.3152, "step": 239020 }, { "epoch": 1.4208439586045378, "grad_norm": 3.888613700866699, "learning_rate": 9.001908839395136e-06, "loss": 0.3768, "step": 239030 }, { "epoch": 1.4209034006812062, "grad_norm": 4.069625377655029, "learning_rate": 9.001784446361315e-06, "loss": 0.3769, "step": 239040 }, { "epoch": 1.4209628427578747, "grad_norm": 5.315978527069092, "learning_rate": 9.001660046435945e-06, "loss": 0.3707, "step": 239050 }, { "epoch": 1.4210222848345428, "grad_norm": 6.116227149963379, "learning_rate": 9.001535639619238e-06, "loss": 0.3589, "step": 239060 }, { "epoch": 1.4210817269112113, "grad_norm": 4.979023456573486, "learning_rate": 9.00141122591141e-06, "loss": 0.4077, "step": 239070 }, { "epoch": 1.4211411689878797, "grad_norm": 5.760619640350342, "learning_rate": 9.001286805312673e-06, "loss": 0.3823, "step": 239080 }, { "epoch": 1.421200611064548, "grad_norm": 4.647885799407959, "learning_rate": 9.001162377823245e-06, "loss": 0.359, "step": 239090 }, { "epoch": 1.4212600531412165, "grad_norm": 4.2096357345581055, "learning_rate": 9.001037943443335e-06, "loss": 0.3704, "step": 239100 }, { "epoch": 1.421319495217885, "grad_norm": 3.952341318130493, "learning_rate": 9.000913502173162e-06, "loss": 0.3585, "step": 239110 }, { "epoch": 1.4213789372945533, "grad_norm": 4.6127753257751465, "learning_rate": 9.00078905401294e-06, "loss": 0.3466, "step": 239120 }, { "epoch": 1.4214383793712217, "grad_norm": 4.931371688842773, "learning_rate": 9.000664598962879e-06, "loss": 0.4155, "step": 239130 }, { "epoch": 1.4214978214478902, "grad_norm": 4.337383270263672, "learning_rate": 9.000540137023198e-06, "loss": 0.3595, "step": 239140 }, { "epoch": 1.4215572635245586, "grad_norm": 6.170294761657715, "learning_rate": 9.00041566819411e-06, "loss": 0.3298, "step": 239150 }, { "epoch": 1.421616705601227, "grad_norm": 5.12098503112793, "learning_rate": 9.000291192475826e-06, "loss": 0.3532, "step": 239160 }, { "epoch": 1.4216761476778954, "grad_norm": 5.809019565582275, "learning_rate": 9.000166709868565e-06, "loss": 0.3665, "step": 239170 }, { "epoch": 1.4217355897545636, "grad_norm": 4.793874263763428, "learning_rate": 9.00004222037254e-06, "loss": 0.3923, "step": 239180 }, { "epoch": 1.421795031831232, "grad_norm": 5.6302595138549805, "learning_rate": 8.999917723987966e-06, "loss": 0.3686, "step": 239190 }, { "epoch": 1.4218544739079004, "grad_norm": 4.484185695648193, "learning_rate": 8.999793220715054e-06, "loss": 0.3413, "step": 239200 }, { "epoch": 1.4219139159845688, "grad_norm": 4.89025354385376, "learning_rate": 8.999668710554022e-06, "loss": 0.3733, "step": 239210 }, { "epoch": 1.4219733580612373, "grad_norm": 4.668429374694824, "learning_rate": 8.999544193505083e-06, "loss": 0.3755, "step": 239220 }, { "epoch": 1.4220328001379057, "grad_norm": 4.10957145690918, "learning_rate": 8.999419669568453e-06, "loss": 0.351, "step": 239230 }, { "epoch": 1.422092242214574, "grad_norm": 5.6808857917785645, "learning_rate": 8.999295138744344e-06, "loss": 0.3888, "step": 239240 }, { "epoch": 1.4221516842912423, "grad_norm": 6.132379055023193, "learning_rate": 8.999170601032971e-06, "loss": 0.3539, "step": 239250 }, { "epoch": 1.4222111263679107, "grad_norm": 5.114525318145752, "learning_rate": 8.99904605643455e-06, "loss": 0.3551, "step": 239260 }, { "epoch": 1.422270568444579, "grad_norm": 3.7169723510742188, "learning_rate": 8.998921504949293e-06, "loss": 0.3463, "step": 239270 }, { "epoch": 1.4223300105212475, "grad_norm": 5.984145641326904, "learning_rate": 8.99879694657742e-06, "loss": 0.3569, "step": 239280 }, { "epoch": 1.422389452597916, "grad_norm": 4.5789971351623535, "learning_rate": 8.998672381319138e-06, "loss": 0.3368, "step": 239290 }, { "epoch": 1.4224488946745844, "grad_norm": 5.610450744628906, "learning_rate": 8.998547809174666e-06, "loss": 0.3287, "step": 239300 }, { "epoch": 1.4225083367512528, "grad_norm": 8.652726173400879, "learning_rate": 8.998423230144218e-06, "loss": 0.4013, "step": 239310 }, { "epoch": 1.4225677788279212, "grad_norm": 5.090541839599609, "learning_rate": 8.998298644228007e-06, "loss": 0.3364, "step": 239320 }, { "epoch": 1.4226272209045896, "grad_norm": 4.4250969886779785, "learning_rate": 8.998174051426249e-06, "loss": 0.3431, "step": 239330 }, { "epoch": 1.422686662981258, "grad_norm": 5.3589348793029785, "learning_rate": 8.998049451739159e-06, "loss": 0.339, "step": 239340 }, { "epoch": 1.4227461050579264, "grad_norm": 4.355068683624268, "learning_rate": 8.99792484516695e-06, "loss": 0.3928, "step": 239350 }, { "epoch": 1.4228055471345946, "grad_norm": 5.167178630828857, "learning_rate": 8.99780023170984e-06, "loss": 0.3681, "step": 239360 }, { "epoch": 1.422864989211263, "grad_norm": 5.432625770568848, "learning_rate": 8.997675611368038e-06, "loss": 0.3583, "step": 239370 }, { "epoch": 1.4229244312879314, "grad_norm": 4.66532564163208, "learning_rate": 8.99755098414176e-06, "loss": 0.3669, "step": 239380 }, { "epoch": 1.4229838733645999, "grad_norm": 5.051778316497803, "learning_rate": 8.997426350031225e-06, "loss": 0.3776, "step": 239390 }, { "epoch": 1.4230433154412683, "grad_norm": 5.3309526443481445, "learning_rate": 8.997301709036646e-06, "loss": 0.3898, "step": 239400 }, { "epoch": 1.4231027575179367, "grad_norm": 4.859283924102783, "learning_rate": 8.997177061158233e-06, "loss": 0.3678, "step": 239410 }, { "epoch": 1.423162199594605, "grad_norm": 4.730767726898193, "learning_rate": 8.997052406396207e-06, "loss": 0.3849, "step": 239420 }, { "epoch": 1.4232216416712733, "grad_norm": 5.206958770751953, "learning_rate": 8.996927744750779e-06, "loss": 0.4251, "step": 239430 }, { "epoch": 1.4232810837479417, "grad_norm": 4.229156017303467, "learning_rate": 8.996803076222165e-06, "loss": 0.3906, "step": 239440 }, { "epoch": 1.4233405258246101, "grad_norm": 3.563868761062622, "learning_rate": 8.996678400810578e-06, "loss": 0.3162, "step": 239450 }, { "epoch": 1.4233999679012785, "grad_norm": 5.142847061157227, "learning_rate": 8.996553718516234e-06, "loss": 0.3618, "step": 239460 }, { "epoch": 1.423459409977947, "grad_norm": 3.9783554077148438, "learning_rate": 8.996429029339348e-06, "loss": 0.338, "step": 239470 }, { "epoch": 1.4235188520546154, "grad_norm": 4.19696569442749, "learning_rate": 8.996304333280134e-06, "loss": 0.4131, "step": 239480 }, { "epoch": 1.4235782941312838, "grad_norm": 6.8701653480529785, "learning_rate": 8.996179630338808e-06, "loss": 0.3584, "step": 239490 }, { "epoch": 1.4236377362079522, "grad_norm": 4.726860523223877, "learning_rate": 8.996054920515584e-06, "loss": 0.3518, "step": 239500 }, { "epoch": 1.4236971782846206, "grad_norm": 6.314087390899658, "learning_rate": 8.995930203810676e-06, "loss": 0.3816, "step": 239510 }, { "epoch": 1.423756620361289, "grad_norm": 6.3326592445373535, "learning_rate": 8.9958054802243e-06, "loss": 0.3655, "step": 239520 }, { "epoch": 1.4238160624379574, "grad_norm": 5.519008159637451, "learning_rate": 8.99568074975667e-06, "loss": 0.3737, "step": 239530 }, { "epoch": 1.4238755045146259, "grad_norm": 6.434310436248779, "learning_rate": 8.995556012408e-06, "loss": 0.4241, "step": 239540 }, { "epoch": 1.423934946591294, "grad_norm": 4.77875280380249, "learning_rate": 8.995431268178507e-06, "loss": 0.366, "step": 239550 }, { "epoch": 1.4239943886679625, "grad_norm": 4.888055801391602, "learning_rate": 8.995306517068405e-06, "loss": 0.3583, "step": 239560 }, { "epoch": 1.4240538307446309, "grad_norm": 6.034857749938965, "learning_rate": 8.995181759077906e-06, "loss": 0.3684, "step": 239570 }, { "epoch": 1.4241132728212993, "grad_norm": 5.956765651702881, "learning_rate": 8.99505699420723e-06, "loss": 0.4121, "step": 239580 }, { "epoch": 1.4241727148979677, "grad_norm": 3.8690764904022217, "learning_rate": 8.994932222456587e-06, "loss": 0.3498, "step": 239590 }, { "epoch": 1.4242321569746361, "grad_norm": 4.453476905822754, "learning_rate": 8.994807443826196e-06, "loss": 0.3648, "step": 239600 }, { "epoch": 1.4242915990513045, "grad_norm": 4.967825412750244, "learning_rate": 8.99468265831627e-06, "loss": 0.3523, "step": 239610 }, { "epoch": 1.4243510411279727, "grad_norm": 5.840472221374512, "learning_rate": 8.994557865927021e-06, "loss": 0.3604, "step": 239620 }, { "epoch": 1.4244104832046411, "grad_norm": 5.147259712219238, "learning_rate": 8.99443306665867e-06, "loss": 0.352, "step": 239630 }, { "epoch": 1.4244699252813096, "grad_norm": 4.5009636878967285, "learning_rate": 8.994308260511427e-06, "loss": 0.3574, "step": 239640 }, { "epoch": 1.424529367357978, "grad_norm": 5.200311660766602, "learning_rate": 8.99418344748551e-06, "loss": 0.3953, "step": 239650 }, { "epoch": 1.4245888094346464, "grad_norm": 4.560925006866455, "learning_rate": 8.99405862758113e-06, "loss": 0.3621, "step": 239660 }, { "epoch": 1.4246482515113148, "grad_norm": 4.490273952484131, "learning_rate": 8.993933800798507e-06, "loss": 0.3583, "step": 239670 }, { "epoch": 1.4247076935879832, "grad_norm": 6.35578727722168, "learning_rate": 8.993808967137852e-06, "loss": 0.353, "step": 239680 }, { "epoch": 1.4247671356646516, "grad_norm": 5.003477096557617, "learning_rate": 8.99368412659938e-06, "loss": 0.3405, "step": 239690 }, { "epoch": 1.42482657774132, "grad_norm": 6.2615461349487305, "learning_rate": 8.99355927918331e-06, "loss": 0.3375, "step": 239700 }, { "epoch": 1.4248860198179885, "grad_norm": 5.162607192993164, "learning_rate": 8.993434424889854e-06, "loss": 0.3773, "step": 239710 }, { "epoch": 1.4249454618946569, "grad_norm": 4.399675369262695, "learning_rate": 8.993309563719226e-06, "loss": 0.3704, "step": 239720 }, { "epoch": 1.425004903971325, "grad_norm": 6.986472129821777, "learning_rate": 8.993184695671644e-06, "loss": 0.4006, "step": 239730 }, { "epoch": 1.4250643460479935, "grad_norm": 4.197441101074219, "learning_rate": 8.993059820747321e-06, "loss": 0.369, "step": 239740 }, { "epoch": 1.425123788124662, "grad_norm": 5.64388370513916, "learning_rate": 8.992934938946472e-06, "loss": 0.3597, "step": 239750 }, { "epoch": 1.4251832302013303, "grad_norm": 4.208636283874512, "learning_rate": 8.992810050269314e-06, "loss": 0.3406, "step": 239760 }, { "epoch": 1.4252426722779987, "grad_norm": 4.293647289276123, "learning_rate": 8.992685154716058e-06, "loss": 0.3769, "step": 239770 }, { "epoch": 1.4253021143546671, "grad_norm": 4.233129978179932, "learning_rate": 8.992560252286925e-06, "loss": 0.3706, "step": 239780 }, { "epoch": 1.4253615564313356, "grad_norm": 6.381417274475098, "learning_rate": 8.992435342982126e-06, "loss": 0.3887, "step": 239790 }, { "epoch": 1.4254209985080037, "grad_norm": 4.599800109863281, "learning_rate": 8.992310426801877e-06, "loss": 0.3876, "step": 239800 }, { "epoch": 1.4254804405846722, "grad_norm": 4.479369640350342, "learning_rate": 8.992185503746392e-06, "loss": 0.3688, "step": 239810 }, { "epoch": 1.4255398826613406, "grad_norm": 5.9070916175842285, "learning_rate": 8.992060573815886e-06, "loss": 0.3561, "step": 239820 }, { "epoch": 1.425599324738009, "grad_norm": 5.164360523223877, "learning_rate": 8.991935637010578e-06, "loss": 0.395, "step": 239830 }, { "epoch": 1.4256587668146774, "grad_norm": 5.161342620849609, "learning_rate": 8.991810693330679e-06, "loss": 0.3738, "step": 239840 }, { "epoch": 1.4257182088913458, "grad_norm": 4.589406490325928, "learning_rate": 8.991685742776406e-06, "loss": 0.4063, "step": 239850 }, { "epoch": 1.4257776509680142, "grad_norm": 6.25811767578125, "learning_rate": 8.991560785347975e-06, "loss": 0.3928, "step": 239860 }, { "epoch": 1.4258370930446826, "grad_norm": 4.203727722167969, "learning_rate": 8.9914358210456e-06, "loss": 0.3579, "step": 239870 }, { "epoch": 1.425896535121351, "grad_norm": 4.1948161125183105, "learning_rate": 8.991310849869495e-06, "loss": 0.3863, "step": 239880 }, { "epoch": 1.4259559771980195, "grad_norm": 5.9667534828186035, "learning_rate": 8.991185871819876e-06, "loss": 0.3846, "step": 239890 }, { "epoch": 1.426015419274688, "grad_norm": 5.328498840332031, "learning_rate": 8.99106088689696e-06, "loss": 0.3935, "step": 239900 }, { "epoch": 1.4260748613513563, "grad_norm": 5.494460582733154, "learning_rate": 8.99093589510096e-06, "loss": 0.3519, "step": 239910 }, { "epoch": 1.4261343034280245, "grad_norm": 4.99183464050293, "learning_rate": 8.990810896432094e-06, "loss": 0.396, "step": 239920 }, { "epoch": 1.426193745504693, "grad_norm": 5.456345081329346, "learning_rate": 8.990685890890574e-06, "loss": 0.354, "step": 239930 }, { "epoch": 1.4262531875813613, "grad_norm": 3.6453375816345215, "learning_rate": 8.990560878476617e-06, "loss": 0.3574, "step": 239940 }, { "epoch": 1.4263126296580297, "grad_norm": 4.9427409172058105, "learning_rate": 8.990435859190439e-06, "loss": 0.385, "step": 239950 }, { "epoch": 1.4263720717346982, "grad_norm": 5.450680732727051, "learning_rate": 8.990310833032252e-06, "loss": 0.3736, "step": 239960 }, { "epoch": 1.4264315138113666, "grad_norm": 4.9947662353515625, "learning_rate": 8.990185800002276e-06, "loss": 0.3329, "step": 239970 }, { "epoch": 1.426490955888035, "grad_norm": 6.148914813995361, "learning_rate": 8.990060760100722e-06, "loss": 0.3786, "step": 239980 }, { "epoch": 1.4265503979647032, "grad_norm": 4.857200622558594, "learning_rate": 8.989935713327808e-06, "loss": 0.3517, "step": 239990 }, { "epoch": 1.4266098400413716, "grad_norm": 5.718310356140137, "learning_rate": 8.98981065968375e-06, "loss": 0.373, "step": 240000 }, { "epoch": 1.42666928211804, "grad_norm": 5.50747537612915, "learning_rate": 8.98968559916876e-06, "loss": 0.3547, "step": 240010 }, { "epoch": 1.4267287241947084, "grad_norm": 5.052874565124512, "learning_rate": 8.989560531783058e-06, "loss": 0.3719, "step": 240020 }, { "epoch": 1.4267881662713768, "grad_norm": 5.431837558746338, "learning_rate": 8.989435457526854e-06, "loss": 0.3882, "step": 240030 }, { "epoch": 1.4268476083480452, "grad_norm": 4.443514347076416, "learning_rate": 8.989310376400367e-06, "loss": 0.3539, "step": 240040 }, { "epoch": 1.4269070504247137, "grad_norm": 5.821462154388428, "learning_rate": 8.98918528840381e-06, "loss": 0.3704, "step": 240050 }, { "epoch": 1.426966492501382, "grad_norm": 5.057858943939209, "learning_rate": 8.989060193537402e-06, "loss": 0.3839, "step": 240060 }, { "epoch": 1.4270259345780505, "grad_norm": 4.49867057800293, "learning_rate": 8.988935091801357e-06, "loss": 0.3727, "step": 240070 }, { "epoch": 1.427085376654719, "grad_norm": 4.832683563232422, "learning_rate": 8.988809983195888e-06, "loss": 0.3522, "step": 240080 }, { "epoch": 1.4271448187313873, "grad_norm": 4.023819923400879, "learning_rate": 8.988684867721214e-06, "loss": 0.3409, "step": 240090 }, { "epoch": 1.4272042608080555, "grad_norm": 4.565354347229004, "learning_rate": 8.988559745377547e-06, "loss": 0.3499, "step": 240100 }, { "epoch": 1.427263702884724, "grad_norm": 5.837610721588135, "learning_rate": 8.988434616165105e-06, "loss": 0.3351, "step": 240110 }, { "epoch": 1.4273231449613923, "grad_norm": 5.9506120681762695, "learning_rate": 8.988309480084103e-06, "loss": 0.355, "step": 240120 }, { "epoch": 1.4273825870380608, "grad_norm": 6.206965446472168, "learning_rate": 8.988184337134755e-06, "loss": 0.3882, "step": 240130 }, { "epoch": 1.4274420291147292, "grad_norm": 5.085696697235107, "learning_rate": 8.98805918731728e-06, "loss": 0.3595, "step": 240140 }, { "epoch": 1.4275014711913976, "grad_norm": 6.655448913574219, "learning_rate": 8.987934030631888e-06, "loss": 0.3929, "step": 240150 }, { "epoch": 1.427560913268066, "grad_norm": 4.6728410720825195, "learning_rate": 8.9878088670788e-06, "loss": 0.3465, "step": 240160 }, { "epoch": 1.4276203553447342, "grad_norm": 6.442740440368652, "learning_rate": 8.98768369665823e-06, "loss": 0.3934, "step": 240170 }, { "epoch": 1.4276797974214026, "grad_norm": 5.9557671546936035, "learning_rate": 8.987558519370392e-06, "loss": 0.3415, "step": 240180 }, { "epoch": 1.427739239498071, "grad_norm": 3.2186646461486816, "learning_rate": 8.987433335215501e-06, "loss": 0.3427, "step": 240190 }, { "epoch": 1.4277986815747394, "grad_norm": 3.968337297439575, "learning_rate": 8.987308144193776e-06, "loss": 0.3846, "step": 240200 }, { "epoch": 1.4278581236514079, "grad_norm": 5.1640191078186035, "learning_rate": 8.987182946305429e-06, "loss": 0.3338, "step": 240210 }, { "epoch": 1.4279175657280763, "grad_norm": 5.547473907470703, "learning_rate": 8.987057741550677e-06, "loss": 0.3725, "step": 240220 }, { "epoch": 1.4279770078047447, "grad_norm": 6.6097588539123535, "learning_rate": 8.986932529929739e-06, "loss": 0.4047, "step": 240230 }, { "epoch": 1.428036449881413, "grad_norm": 5.719438552856445, "learning_rate": 8.986807311442825e-06, "loss": 0.3846, "step": 240240 }, { "epoch": 1.4280958919580815, "grad_norm": 5.879844665527344, "learning_rate": 8.986682086090153e-06, "loss": 0.3734, "step": 240250 }, { "epoch": 1.42815533403475, "grad_norm": 3.5287880897521973, "learning_rate": 8.98655685387194e-06, "loss": 0.3394, "step": 240260 }, { "epoch": 1.4282147761114183, "grad_norm": 4.490779399871826, "learning_rate": 8.9864316147884e-06, "loss": 0.3687, "step": 240270 }, { "epoch": 1.4282742181880868, "grad_norm": 4.516223430633545, "learning_rate": 8.986306368839749e-06, "loss": 0.3545, "step": 240280 }, { "epoch": 1.428333660264755, "grad_norm": 4.876094818115234, "learning_rate": 8.9861811160262e-06, "loss": 0.3101, "step": 240290 }, { "epoch": 1.4283931023414234, "grad_norm": 3.8465476036071777, "learning_rate": 8.986055856347976e-06, "loss": 0.3338, "step": 240300 }, { "epoch": 1.4284525444180918, "grad_norm": 2.899230718612671, "learning_rate": 8.985930589805286e-06, "loss": 0.4318, "step": 240310 }, { "epoch": 1.4285119864947602, "grad_norm": 3.902813196182251, "learning_rate": 8.985805316398348e-06, "loss": 0.3365, "step": 240320 }, { "epoch": 1.4285714285714286, "grad_norm": 3.7771708965301514, "learning_rate": 8.985680036127378e-06, "loss": 0.3417, "step": 240330 }, { "epoch": 1.428630870648097, "grad_norm": 7.043489456176758, "learning_rate": 8.98555474899259e-06, "loss": 0.3491, "step": 240340 }, { "epoch": 1.4286903127247654, "grad_norm": 4.6681413650512695, "learning_rate": 8.985429454994203e-06, "loss": 0.3828, "step": 240350 }, { "epoch": 1.4287497548014336, "grad_norm": 5.163170337677002, "learning_rate": 8.98530415413243e-06, "loss": 0.3678, "step": 240360 }, { "epoch": 1.428809196878102, "grad_norm": 5.592308044433594, "learning_rate": 8.98517884640749e-06, "loss": 0.3709, "step": 240370 }, { "epoch": 1.4288686389547705, "grad_norm": 5.216702938079834, "learning_rate": 8.985053531819595e-06, "loss": 0.3423, "step": 240380 }, { "epoch": 1.4289280810314389, "grad_norm": 5.736177444458008, "learning_rate": 8.984928210368961e-06, "loss": 0.3617, "step": 240390 }, { "epoch": 1.4289875231081073, "grad_norm": 4.685297012329102, "learning_rate": 8.984802882055806e-06, "loss": 0.3443, "step": 240400 }, { "epoch": 1.4290469651847757, "grad_norm": 4.8816423416137695, "learning_rate": 8.984677546880345e-06, "loss": 0.3463, "step": 240410 }, { "epoch": 1.4291064072614441, "grad_norm": 3.8543550968170166, "learning_rate": 8.984552204842793e-06, "loss": 0.3678, "step": 240420 }, { "epoch": 1.4291658493381125, "grad_norm": 5.36497688293457, "learning_rate": 8.984426855943369e-06, "loss": 0.3661, "step": 240430 }, { "epoch": 1.429225291414781, "grad_norm": 4.855179786682129, "learning_rate": 8.984301500182284e-06, "loss": 0.3262, "step": 240440 }, { "epoch": 1.4292847334914494, "grad_norm": 5.694732189178467, "learning_rate": 8.984176137559759e-06, "loss": 0.3708, "step": 240450 }, { "epoch": 1.4293441755681178, "grad_norm": 5.34566068649292, "learning_rate": 8.984050768076004e-06, "loss": 0.3438, "step": 240460 }, { "epoch": 1.429403617644786, "grad_norm": 6.652386665344238, "learning_rate": 8.983925391731241e-06, "loss": 0.3725, "step": 240470 }, { "epoch": 1.4294630597214544, "grad_norm": 5.814610481262207, "learning_rate": 8.983800008525683e-06, "loss": 0.3858, "step": 240480 }, { "epoch": 1.4295225017981228, "grad_norm": 3.5234153270721436, "learning_rate": 8.983674618459545e-06, "loss": 0.3809, "step": 240490 }, { "epoch": 1.4295819438747912, "grad_norm": 4.303258895874023, "learning_rate": 8.983549221533043e-06, "loss": 0.352, "step": 240500 }, { "epoch": 1.4296413859514596, "grad_norm": 4.768426418304443, "learning_rate": 8.983423817746396e-06, "loss": 0.356, "step": 240510 }, { "epoch": 1.429700828028128, "grad_norm": 6.38103723526001, "learning_rate": 8.983298407099817e-06, "loss": 0.3599, "step": 240520 }, { "epoch": 1.4297602701047964, "grad_norm": 4.662487506866455, "learning_rate": 8.983172989593523e-06, "loss": 0.346, "step": 240530 }, { "epoch": 1.4298197121814646, "grad_norm": 7.247921943664551, "learning_rate": 8.983047565227729e-06, "loss": 0.3753, "step": 240540 }, { "epoch": 1.429879154258133, "grad_norm": 4.160167694091797, "learning_rate": 8.982922134002652e-06, "loss": 0.3661, "step": 240550 }, { "epoch": 1.4299385963348015, "grad_norm": 3.742677688598633, "learning_rate": 8.98279669591851e-06, "loss": 0.3554, "step": 240560 }, { "epoch": 1.4299980384114699, "grad_norm": 5.56978702545166, "learning_rate": 8.982671250975514e-06, "loss": 0.3281, "step": 240570 }, { "epoch": 1.4300574804881383, "grad_norm": 5.292911052703857, "learning_rate": 8.982545799173885e-06, "loss": 0.3956, "step": 240580 }, { "epoch": 1.4301169225648067, "grad_norm": 4.58025598526001, "learning_rate": 8.982420340513837e-06, "loss": 0.3407, "step": 240590 }, { "epoch": 1.4301763646414751, "grad_norm": 4.948901176452637, "learning_rate": 8.982294874995586e-06, "loss": 0.3959, "step": 240600 }, { "epoch": 1.4302358067181435, "grad_norm": 5.730764865875244, "learning_rate": 8.982169402619346e-06, "loss": 0.3845, "step": 240610 }, { "epoch": 1.430295248794812, "grad_norm": 4.915286064147949, "learning_rate": 8.982043923385336e-06, "loss": 0.3908, "step": 240620 }, { "epoch": 1.4303546908714804, "grad_norm": 4.338289260864258, "learning_rate": 8.981918437293772e-06, "loss": 0.388, "step": 240630 }, { "epoch": 1.4304141329481488, "grad_norm": 5.719488143920898, "learning_rate": 8.981792944344869e-06, "loss": 0.3045, "step": 240640 }, { "epoch": 1.4304735750248172, "grad_norm": 5.975135803222656, "learning_rate": 8.981667444538843e-06, "loss": 0.415, "step": 240650 }, { "epoch": 1.4305330171014854, "grad_norm": 7.088764190673828, "learning_rate": 8.98154193787591e-06, "loss": 0.3423, "step": 240660 }, { "epoch": 1.4305924591781538, "grad_norm": 5.349047660827637, "learning_rate": 8.981416424356289e-06, "loss": 0.3782, "step": 240670 }, { "epoch": 1.4306519012548222, "grad_norm": 5.424667835235596, "learning_rate": 8.981290903980193e-06, "loss": 0.3925, "step": 240680 }, { "epoch": 1.4307113433314906, "grad_norm": 4.594758033752441, "learning_rate": 8.981165376747838e-06, "loss": 0.3747, "step": 240690 }, { "epoch": 1.430770785408159, "grad_norm": 5.25190544128418, "learning_rate": 8.981039842659441e-06, "loss": 0.3835, "step": 240700 }, { "epoch": 1.4308302274848275, "grad_norm": 6.065706729888916, "learning_rate": 8.98091430171522e-06, "loss": 0.3646, "step": 240710 }, { "epoch": 1.4308896695614959, "grad_norm": 4.796453475952148, "learning_rate": 8.980788753915387e-06, "loss": 0.3837, "step": 240720 }, { "epoch": 1.430949111638164, "grad_norm": 4.991218566894531, "learning_rate": 8.980663199260165e-06, "loss": 0.4106, "step": 240730 }, { "epoch": 1.4310085537148325, "grad_norm": 4.384206771850586, "learning_rate": 8.980537637749762e-06, "loss": 0.3569, "step": 240740 }, { "epoch": 1.431067995791501, "grad_norm": 4.912411689758301, "learning_rate": 8.980412069384401e-06, "loss": 0.3939, "step": 240750 }, { "epoch": 1.4311274378681693, "grad_norm": 5.618342399597168, "learning_rate": 8.980286494164294e-06, "loss": 0.3631, "step": 240760 }, { "epoch": 1.4311868799448377, "grad_norm": 4.656757354736328, "learning_rate": 8.98016091208966e-06, "loss": 0.3814, "step": 240770 }, { "epoch": 1.4312463220215061, "grad_norm": 4.566569805145264, "learning_rate": 8.980035323160713e-06, "loss": 0.3955, "step": 240780 }, { "epoch": 1.4313057640981746, "grad_norm": 6.608717441558838, "learning_rate": 8.97990972737767e-06, "loss": 0.3458, "step": 240790 }, { "epoch": 1.431365206174843, "grad_norm": 5.788427829742432, "learning_rate": 8.979784124740748e-06, "loss": 0.3912, "step": 240800 }, { "epoch": 1.4314246482515114, "grad_norm": 6.0873565673828125, "learning_rate": 8.979658515250162e-06, "loss": 0.3621, "step": 240810 }, { "epoch": 1.4314840903281798, "grad_norm": 4.947926044464111, "learning_rate": 8.97953289890613e-06, "loss": 0.3684, "step": 240820 }, { "epoch": 1.4315435324048482, "grad_norm": 6.805795192718506, "learning_rate": 8.979407275708867e-06, "loss": 0.4155, "step": 240830 }, { "epoch": 1.4316029744815164, "grad_norm": 4.890058517456055, "learning_rate": 8.979281645658591e-06, "loss": 0.3501, "step": 240840 }, { "epoch": 1.4316624165581848, "grad_norm": 4.641409397125244, "learning_rate": 8.979156008755517e-06, "loss": 0.3556, "step": 240850 }, { "epoch": 1.4317218586348532, "grad_norm": 4.71845006942749, "learning_rate": 8.97903036499986e-06, "loss": 0.3675, "step": 240860 }, { "epoch": 1.4317813007115217, "grad_norm": 4.916753768920898, "learning_rate": 8.978904714391839e-06, "loss": 0.3671, "step": 240870 }, { "epoch": 1.43184074278819, "grad_norm": 6.618852615356445, "learning_rate": 8.97877905693167e-06, "loss": 0.3358, "step": 240880 }, { "epoch": 1.4319001848648585, "grad_norm": 4.325465202331543, "learning_rate": 8.978653392619567e-06, "loss": 0.3176, "step": 240890 }, { "epoch": 1.431959626941527, "grad_norm": 6.241244792938232, "learning_rate": 8.97852772145575e-06, "loss": 0.4069, "step": 240900 }, { "epoch": 1.432019069018195, "grad_norm": 3.684516429901123, "learning_rate": 8.978402043440433e-06, "loss": 0.3748, "step": 240910 }, { "epoch": 1.4320785110948635, "grad_norm": 4.151205539703369, "learning_rate": 8.978276358573832e-06, "loss": 0.3627, "step": 240920 }, { "epoch": 1.432137953171532, "grad_norm": 5.29753303527832, "learning_rate": 8.978150666856164e-06, "loss": 0.3679, "step": 240930 }, { "epoch": 1.4321973952482003, "grad_norm": 7.18183708190918, "learning_rate": 8.978024968287648e-06, "loss": 0.4041, "step": 240940 }, { "epoch": 1.4322568373248687, "grad_norm": 5.0642900466918945, "learning_rate": 8.977899262868498e-06, "loss": 0.393, "step": 240950 }, { "epoch": 1.4323162794015372, "grad_norm": 4.594702243804932, "learning_rate": 8.97777355059893e-06, "loss": 0.3534, "step": 240960 }, { "epoch": 1.4323757214782056, "grad_norm": 6.706636428833008, "learning_rate": 8.977647831479161e-06, "loss": 0.331, "step": 240970 }, { "epoch": 1.432435163554874, "grad_norm": 5.09053373336792, "learning_rate": 8.977522105509409e-06, "loss": 0.4112, "step": 240980 }, { "epoch": 1.4324946056315424, "grad_norm": 3.9636871814727783, "learning_rate": 8.977396372689888e-06, "loss": 0.3288, "step": 240990 }, { "epoch": 1.4325540477082108, "grad_norm": 4.939821720123291, "learning_rate": 8.977270633020818e-06, "loss": 0.3758, "step": 241000 }, { "epoch": 1.4326134897848792, "grad_norm": 5.738269329071045, "learning_rate": 8.977144886502412e-06, "loss": 0.3925, "step": 241010 }, { "epoch": 1.4326729318615476, "grad_norm": 5.0886406898498535, "learning_rate": 8.977019133134886e-06, "loss": 0.3541, "step": 241020 }, { "epoch": 1.4327323739382158, "grad_norm": 4.293024063110352, "learning_rate": 8.97689337291846e-06, "loss": 0.399, "step": 241030 }, { "epoch": 1.4327918160148843, "grad_norm": 3.4578285217285156, "learning_rate": 8.976767605853351e-06, "loss": 0.3126, "step": 241040 }, { "epoch": 1.4328512580915527, "grad_norm": 4.8394694328308105, "learning_rate": 8.976641831939772e-06, "loss": 0.3521, "step": 241050 }, { "epoch": 1.432910700168221, "grad_norm": 5.776456832885742, "learning_rate": 8.97651605117794e-06, "loss": 0.3541, "step": 241060 }, { "epoch": 1.4329701422448895, "grad_norm": 6.748908996582031, "learning_rate": 8.976390263568076e-06, "loss": 0.3793, "step": 241070 }, { "epoch": 1.433029584321558, "grad_norm": 4.39353609085083, "learning_rate": 8.976264469110391e-06, "loss": 0.3639, "step": 241080 }, { "epoch": 1.4330890263982263, "grad_norm": 4.489938259124756, "learning_rate": 8.976138667805105e-06, "loss": 0.3803, "step": 241090 }, { "epoch": 1.4331484684748945, "grad_norm": 4.91241979598999, "learning_rate": 8.976012859652435e-06, "loss": 0.3548, "step": 241100 }, { "epoch": 1.433207910551563, "grad_norm": 4.960348606109619, "learning_rate": 8.975887044652596e-06, "loss": 0.3739, "step": 241110 }, { "epoch": 1.4332673526282314, "grad_norm": 5.149694442749023, "learning_rate": 8.975761222805803e-06, "loss": 0.3546, "step": 241120 }, { "epoch": 1.4333267947048998, "grad_norm": 4.396477699279785, "learning_rate": 8.975635394112277e-06, "loss": 0.4094, "step": 241130 }, { "epoch": 1.4333862367815682, "grad_norm": 4.323002815246582, "learning_rate": 8.975509558572232e-06, "loss": 0.3636, "step": 241140 }, { "epoch": 1.4334456788582366, "grad_norm": 6.310556888580322, "learning_rate": 8.975383716185885e-06, "loss": 0.3689, "step": 241150 }, { "epoch": 1.433505120934905, "grad_norm": 6.103054523468018, "learning_rate": 8.975257866953452e-06, "loss": 0.3718, "step": 241160 }, { "epoch": 1.4335645630115734, "grad_norm": 4.803770065307617, "learning_rate": 8.975132010875152e-06, "loss": 0.3789, "step": 241170 }, { "epoch": 1.4336240050882418, "grad_norm": 5.668119430541992, "learning_rate": 8.9750061479512e-06, "loss": 0.3857, "step": 241180 }, { "epoch": 1.4336834471649103, "grad_norm": 6.493108749389648, "learning_rate": 8.974880278181811e-06, "loss": 0.4446, "step": 241190 }, { "epoch": 1.4337428892415787, "grad_norm": 5.097163200378418, "learning_rate": 8.974754401567207e-06, "loss": 0.3657, "step": 241200 }, { "epoch": 1.4338023313182469, "grad_norm": 4.459499359130859, "learning_rate": 8.974628518107601e-06, "loss": 0.372, "step": 241210 }, { "epoch": 1.4338617733949153, "grad_norm": 4.099560737609863, "learning_rate": 8.97450262780321e-06, "loss": 0.3704, "step": 241220 }, { "epoch": 1.4339212154715837, "grad_norm": 5.479910373687744, "learning_rate": 8.97437673065425e-06, "loss": 0.3753, "step": 241230 }, { "epoch": 1.433980657548252, "grad_norm": 4.317727088928223, "learning_rate": 8.974250826660942e-06, "loss": 0.3449, "step": 241240 }, { "epoch": 1.4340400996249205, "grad_norm": 4.892221450805664, "learning_rate": 8.974124915823496e-06, "loss": 0.3809, "step": 241250 }, { "epoch": 1.434099541701589, "grad_norm": 5.649758338928223, "learning_rate": 8.973998998142138e-06, "loss": 0.3448, "step": 241260 }, { "epoch": 1.4341589837782573, "grad_norm": 5.47097635269165, "learning_rate": 8.973873073617073e-06, "loss": 0.337, "step": 241270 }, { "epoch": 1.4342184258549255, "grad_norm": 5.073949337005615, "learning_rate": 8.97374714224853e-06, "loss": 0.3703, "step": 241280 }, { "epoch": 1.434277867931594, "grad_norm": 6.3130950927734375, "learning_rate": 8.973621204036717e-06, "loss": 0.3804, "step": 241290 }, { "epoch": 1.4343373100082624, "grad_norm": 3.321382999420166, "learning_rate": 8.973495258981856e-06, "loss": 0.347, "step": 241300 }, { "epoch": 1.4343967520849308, "grad_norm": 6.059813022613525, "learning_rate": 8.973369307084161e-06, "loss": 0.4424, "step": 241310 }, { "epoch": 1.4344561941615992, "grad_norm": 5.571721076965332, "learning_rate": 8.97324334834385e-06, "loss": 0.3668, "step": 241320 }, { "epoch": 1.4345156362382676, "grad_norm": 5.971263408660889, "learning_rate": 8.97311738276114e-06, "loss": 0.3726, "step": 241330 }, { "epoch": 1.434575078314936, "grad_norm": 5.553476810455322, "learning_rate": 8.972991410336249e-06, "loss": 0.4222, "step": 241340 }, { "epoch": 1.4346345203916044, "grad_norm": 6.159079551696777, "learning_rate": 8.972865431069391e-06, "loss": 0.3698, "step": 241350 }, { "epoch": 1.4346939624682729, "grad_norm": 6.279825210571289, "learning_rate": 8.972739444960784e-06, "loss": 0.4045, "step": 241360 }, { "epoch": 1.4347534045449413, "grad_norm": 5.128188133239746, "learning_rate": 8.972613452010648e-06, "loss": 0.3373, "step": 241370 }, { "epoch": 1.4348128466216097, "grad_norm": 5.461886882781982, "learning_rate": 8.972487452219197e-06, "loss": 0.372, "step": 241380 }, { "epoch": 1.434872288698278, "grad_norm": 4.189671516418457, "learning_rate": 8.972361445586648e-06, "loss": 0.3422, "step": 241390 }, { "epoch": 1.4349317307749463, "grad_norm": 4.641722679138184, "learning_rate": 8.972235432113219e-06, "loss": 0.3234, "step": 241400 }, { "epoch": 1.4349911728516147, "grad_norm": 4.866203784942627, "learning_rate": 8.972109411799128e-06, "loss": 0.354, "step": 241410 }, { "epoch": 1.4350506149282831, "grad_norm": 5.320100784301758, "learning_rate": 8.971983384644588e-06, "loss": 0.3867, "step": 241420 }, { "epoch": 1.4351100570049515, "grad_norm": 3.6164214611053467, "learning_rate": 8.97185735064982e-06, "loss": 0.3723, "step": 241430 }, { "epoch": 1.43516949908162, "grad_norm": 4.818731307983398, "learning_rate": 8.971731309815039e-06, "loss": 0.37, "step": 241440 }, { "epoch": 1.4352289411582884, "grad_norm": 3.123302459716797, "learning_rate": 8.971605262140464e-06, "loss": 0.3391, "step": 241450 }, { "epoch": 1.4352883832349568, "grad_norm": 3.3937466144561768, "learning_rate": 8.97147920762631e-06, "loss": 0.316, "step": 241460 }, { "epoch": 1.435347825311625, "grad_norm": 4.90593957901001, "learning_rate": 8.971353146272795e-06, "loss": 0.347, "step": 241470 }, { "epoch": 1.4354072673882934, "grad_norm": 3.3605380058288574, "learning_rate": 8.971227078080136e-06, "loss": 0.3961, "step": 241480 }, { "epoch": 1.4354667094649618, "grad_norm": 13.240081787109375, "learning_rate": 8.97110100304855e-06, "loss": 0.4154, "step": 241490 }, { "epoch": 1.4355261515416302, "grad_norm": 5.981122970581055, "learning_rate": 8.970974921178256e-06, "loss": 0.3896, "step": 241500 }, { "epoch": 1.4355855936182986, "grad_norm": 4.947093963623047, "learning_rate": 8.970848832469468e-06, "loss": 0.3904, "step": 241510 }, { "epoch": 1.435645035694967, "grad_norm": 6.952276706695557, "learning_rate": 8.970722736922403e-06, "loss": 0.4163, "step": 241520 }, { "epoch": 1.4357044777716355, "grad_norm": 5.115734100341797, "learning_rate": 8.970596634537281e-06, "loss": 0.3576, "step": 241530 }, { "epoch": 1.4357639198483039, "grad_norm": 5.027926921844482, "learning_rate": 8.970470525314319e-06, "loss": 0.3705, "step": 241540 }, { "epoch": 1.4358233619249723, "grad_norm": 4.320234298706055, "learning_rate": 8.970344409253731e-06, "loss": 0.3538, "step": 241550 }, { "epoch": 1.4358828040016407, "grad_norm": 5.593551158905029, "learning_rate": 8.97021828635574e-06, "loss": 0.3908, "step": 241560 }, { "epoch": 1.4359422460783091, "grad_norm": 5.178590774536133, "learning_rate": 8.970092156620555e-06, "loss": 0.371, "step": 241570 }, { "epoch": 1.4360016881549773, "grad_norm": 4.8144941329956055, "learning_rate": 8.969966020048398e-06, "loss": 0.3616, "step": 241580 }, { "epoch": 1.4360611302316457, "grad_norm": 5.3339691162109375, "learning_rate": 8.969839876639488e-06, "loss": 0.4114, "step": 241590 }, { "epoch": 1.4361205723083141, "grad_norm": 5.351650714874268, "learning_rate": 8.969713726394038e-06, "loss": 0.3961, "step": 241600 }, { "epoch": 1.4361800143849826, "grad_norm": 5.913530349731445, "learning_rate": 8.969587569312268e-06, "loss": 0.3786, "step": 241610 }, { "epoch": 1.436239456461651, "grad_norm": 4.869203567504883, "learning_rate": 8.969461405394395e-06, "loss": 0.329, "step": 241620 }, { "epoch": 1.4362988985383194, "grad_norm": 4.557713508605957, "learning_rate": 8.969335234640637e-06, "loss": 0.3404, "step": 241630 }, { "epoch": 1.4363583406149878, "grad_norm": 5.959454536437988, "learning_rate": 8.969209057051208e-06, "loss": 0.3513, "step": 241640 }, { "epoch": 1.436417782691656, "grad_norm": 5.724571704864502, "learning_rate": 8.969082872626328e-06, "loss": 0.3943, "step": 241650 }, { "epoch": 1.4364772247683244, "grad_norm": 5.4444684982299805, "learning_rate": 8.968956681366215e-06, "loss": 0.4146, "step": 241660 }, { "epoch": 1.4365366668449928, "grad_norm": 5.518002033233643, "learning_rate": 8.968830483271082e-06, "loss": 0.3876, "step": 241670 }, { "epoch": 1.4365961089216612, "grad_norm": 4.349277019500732, "learning_rate": 8.968704278341154e-06, "loss": 0.3569, "step": 241680 }, { "epoch": 1.4366555509983296, "grad_norm": 5.2352800369262695, "learning_rate": 8.96857806657664e-06, "loss": 0.37, "step": 241690 }, { "epoch": 1.436714993074998, "grad_norm": 4.237436771392822, "learning_rate": 8.968451847977762e-06, "loss": 0.3549, "step": 241700 }, { "epoch": 1.4367744351516665, "grad_norm": 5.9046525955200195, "learning_rate": 8.968325622544736e-06, "loss": 0.341, "step": 241710 }, { "epoch": 1.4368338772283349, "grad_norm": 4.235123157501221, "learning_rate": 8.968199390277782e-06, "loss": 0.3604, "step": 241720 }, { "epoch": 1.4368933193050033, "grad_norm": 3.3509581089019775, "learning_rate": 8.968073151177113e-06, "loss": 0.3241, "step": 241730 }, { "epoch": 1.4369527613816717, "grad_norm": 5.591789722442627, "learning_rate": 8.967946905242947e-06, "loss": 0.3658, "step": 241740 }, { "epoch": 1.4370122034583401, "grad_norm": 4.801602840423584, "learning_rate": 8.967820652475506e-06, "loss": 0.3826, "step": 241750 }, { "epoch": 1.4370716455350085, "grad_norm": 5.032168388366699, "learning_rate": 8.967694392875003e-06, "loss": 0.3378, "step": 241760 }, { "epoch": 1.4371310876116767, "grad_norm": 5.758896350860596, "learning_rate": 8.967568126441657e-06, "loss": 0.3647, "step": 241770 }, { "epoch": 1.4371905296883452, "grad_norm": 5.1778883934021, "learning_rate": 8.967441853175686e-06, "loss": 0.4022, "step": 241780 }, { "epoch": 1.4372499717650136, "grad_norm": 5.079549312591553, "learning_rate": 8.967315573077307e-06, "loss": 0.3401, "step": 241790 }, { "epoch": 1.437309413841682, "grad_norm": 4.847164154052734, "learning_rate": 8.967189286146736e-06, "loss": 0.3681, "step": 241800 }, { "epoch": 1.4373688559183504, "grad_norm": 4.582900047302246, "learning_rate": 8.967062992384193e-06, "loss": 0.3379, "step": 241810 }, { "epoch": 1.4374282979950188, "grad_norm": 6.3007378578186035, "learning_rate": 8.966936691789893e-06, "loss": 0.3372, "step": 241820 }, { "epoch": 1.4374877400716872, "grad_norm": 5.756333351135254, "learning_rate": 8.966810384364055e-06, "loss": 0.3684, "step": 241830 }, { "epoch": 1.4375471821483554, "grad_norm": 4.1296820640563965, "learning_rate": 8.966684070106896e-06, "loss": 0.3605, "step": 241840 }, { "epoch": 1.4376066242250238, "grad_norm": 6.7938385009765625, "learning_rate": 8.966557749018634e-06, "loss": 0.3697, "step": 241850 }, { "epoch": 1.4376660663016922, "grad_norm": 3.797539234161377, "learning_rate": 8.966431421099486e-06, "loss": 0.3313, "step": 241860 }, { "epoch": 1.4377255083783607, "grad_norm": 4.558897495269775, "learning_rate": 8.966305086349669e-06, "loss": 0.3806, "step": 241870 }, { "epoch": 1.437784950455029, "grad_norm": 3.5025227069854736, "learning_rate": 8.966178744769403e-06, "loss": 0.31, "step": 241880 }, { "epoch": 1.4378443925316975, "grad_norm": 4.289325714111328, "learning_rate": 8.966052396358904e-06, "loss": 0.3432, "step": 241890 }, { "epoch": 1.437903834608366, "grad_norm": 6.104865074157715, "learning_rate": 8.965926041118389e-06, "loss": 0.3824, "step": 241900 }, { "epoch": 1.4379632766850343, "grad_norm": 4.637607574462891, "learning_rate": 8.965799679048076e-06, "loss": 0.4011, "step": 241910 }, { "epoch": 1.4380227187617027, "grad_norm": 4.994743824005127, "learning_rate": 8.965673310148184e-06, "loss": 0.3729, "step": 241920 }, { "epoch": 1.4380821608383711, "grad_norm": 6.291313171386719, "learning_rate": 8.965546934418927e-06, "loss": 0.3681, "step": 241930 }, { "epoch": 1.4381416029150396, "grad_norm": 5.429618835449219, "learning_rate": 8.965420551860526e-06, "loss": 0.3898, "step": 241940 }, { "epoch": 1.4382010449917078, "grad_norm": 4.4845781326293945, "learning_rate": 8.965294162473199e-06, "loss": 0.3565, "step": 241950 }, { "epoch": 1.4382604870683762, "grad_norm": 5.150407314300537, "learning_rate": 8.965167766257161e-06, "loss": 0.383, "step": 241960 }, { "epoch": 1.4383199291450446, "grad_norm": 5.741672992706299, "learning_rate": 8.96504136321263e-06, "loss": 0.3291, "step": 241970 }, { "epoch": 1.438379371221713, "grad_norm": 5.932906627655029, "learning_rate": 8.964914953339827e-06, "loss": 0.4188, "step": 241980 }, { "epoch": 1.4384388132983814, "grad_norm": 4.806318759918213, "learning_rate": 8.964788536638967e-06, "loss": 0.3966, "step": 241990 }, { "epoch": 1.4384982553750498, "grad_norm": 7.196174144744873, "learning_rate": 8.964662113110268e-06, "loss": 0.3733, "step": 242000 }, { "epoch": 1.4385576974517182, "grad_norm": 6.0707688331604, "learning_rate": 8.964535682753946e-06, "loss": 0.3852, "step": 242010 }, { "epoch": 1.4386171395283864, "grad_norm": 5.722754001617432, "learning_rate": 8.964409245570221e-06, "loss": 0.3535, "step": 242020 }, { "epoch": 1.4386765816050548, "grad_norm": 6.284488677978516, "learning_rate": 8.964282801559312e-06, "loss": 0.3507, "step": 242030 }, { "epoch": 1.4387360236817233, "grad_norm": 4.505097389221191, "learning_rate": 8.964156350721433e-06, "loss": 0.365, "step": 242040 }, { "epoch": 1.4387954657583917, "grad_norm": 4.190564155578613, "learning_rate": 8.964029893056805e-06, "loss": 0.3532, "step": 242050 }, { "epoch": 1.43885490783506, "grad_norm": 5.184736251831055, "learning_rate": 8.963903428565644e-06, "loss": 0.3874, "step": 242060 }, { "epoch": 1.4389143499117285, "grad_norm": 8.027953147888184, "learning_rate": 8.96377695724817e-06, "loss": 0.4038, "step": 242070 }, { "epoch": 1.438973791988397, "grad_norm": 4.1603684425354, "learning_rate": 8.963650479104597e-06, "loss": 0.3661, "step": 242080 }, { "epoch": 1.4390332340650653, "grad_norm": 4.844612121582031, "learning_rate": 8.963523994135146e-06, "loss": 0.3511, "step": 242090 }, { "epoch": 1.4390926761417338, "grad_norm": 4.738929748535156, "learning_rate": 8.963397502340033e-06, "loss": 0.324, "step": 242100 }, { "epoch": 1.4391521182184022, "grad_norm": 5.695833206176758, "learning_rate": 8.963271003719478e-06, "loss": 0.3632, "step": 242110 }, { "epoch": 1.4392115602950706, "grad_norm": 5.011661052703857, "learning_rate": 8.963144498273695e-06, "loss": 0.3507, "step": 242120 }, { "epoch": 1.439271002371739, "grad_norm": 4.752589702606201, "learning_rate": 8.963017986002907e-06, "loss": 0.3853, "step": 242130 }, { "epoch": 1.4393304444484072, "grad_norm": 4.610135555267334, "learning_rate": 8.962891466907326e-06, "loss": 0.3476, "step": 242140 }, { "epoch": 1.4393898865250756, "grad_norm": 6.067122459411621, "learning_rate": 8.962764940987177e-06, "loss": 0.3581, "step": 242150 }, { "epoch": 1.439449328601744, "grad_norm": 4.9223246574401855, "learning_rate": 8.96263840824267e-06, "loss": 0.3475, "step": 242160 }, { "epoch": 1.4395087706784124, "grad_norm": 4.742700576782227, "learning_rate": 8.96251186867403e-06, "loss": 0.3739, "step": 242170 }, { "epoch": 1.4395682127550808, "grad_norm": 5.141477108001709, "learning_rate": 8.96238532228147e-06, "loss": 0.3749, "step": 242180 }, { "epoch": 1.4396276548317493, "grad_norm": 6.209548473358154, "learning_rate": 8.96225876906521e-06, "loss": 0.3597, "step": 242190 }, { "epoch": 1.4396870969084177, "grad_norm": 5.117579460144043, "learning_rate": 8.962132209025467e-06, "loss": 0.3772, "step": 242200 }, { "epoch": 1.4397465389850859, "grad_norm": 4.1422600746154785, "learning_rate": 8.96200564216246e-06, "loss": 0.3863, "step": 242210 }, { "epoch": 1.4398059810617543, "grad_norm": 4.989842414855957, "learning_rate": 8.961879068476409e-06, "loss": 0.3626, "step": 242220 }, { "epoch": 1.4398654231384227, "grad_norm": 4.830109119415283, "learning_rate": 8.961752487967527e-06, "loss": 0.3828, "step": 242230 }, { "epoch": 1.439924865215091, "grad_norm": 4.751139163970947, "learning_rate": 8.961625900636036e-06, "loss": 0.3277, "step": 242240 }, { "epoch": 1.4399843072917595, "grad_norm": 5.107143878936768, "learning_rate": 8.961499306482151e-06, "loss": 0.3762, "step": 242250 }, { "epoch": 1.440043749368428, "grad_norm": 5.9572062492370605, "learning_rate": 8.96137270550609e-06, "loss": 0.3556, "step": 242260 }, { "epoch": 1.4401031914450964, "grad_norm": 4.729299545288086, "learning_rate": 8.961246097708077e-06, "loss": 0.3827, "step": 242270 }, { "epoch": 1.4401626335217648, "grad_norm": 6.806540489196777, "learning_rate": 8.961119483088323e-06, "loss": 0.3244, "step": 242280 }, { "epoch": 1.4402220755984332, "grad_norm": 5.620334625244141, "learning_rate": 8.960992861647048e-06, "loss": 0.4023, "step": 242290 }, { "epoch": 1.4402815176751016, "grad_norm": 5.245569229125977, "learning_rate": 8.960866233384471e-06, "loss": 0.4352, "step": 242300 }, { "epoch": 1.44034095975177, "grad_norm": 3.5918266773223877, "learning_rate": 8.960739598300811e-06, "loss": 0.3663, "step": 242310 }, { "epoch": 1.4404004018284382, "grad_norm": 5.797423839569092, "learning_rate": 8.960612956396285e-06, "loss": 0.3995, "step": 242320 }, { "epoch": 1.4404598439051066, "grad_norm": 5.831311225891113, "learning_rate": 8.960486307671108e-06, "loss": 0.371, "step": 242330 }, { "epoch": 1.440519285981775, "grad_norm": 5.26161527633667, "learning_rate": 8.960359652125504e-06, "loss": 0.3535, "step": 242340 }, { "epoch": 1.4405787280584434, "grad_norm": 5.941750526428223, "learning_rate": 8.960232989759686e-06, "loss": 0.3635, "step": 242350 }, { "epoch": 1.4406381701351119, "grad_norm": 4.777236461639404, "learning_rate": 8.960106320573875e-06, "loss": 0.3589, "step": 242360 }, { "epoch": 1.4406976122117803, "grad_norm": 4.988335132598877, "learning_rate": 8.959979644568288e-06, "loss": 0.3962, "step": 242370 }, { "epoch": 1.4407570542884487, "grad_norm": 5.41047477722168, "learning_rate": 8.959852961743146e-06, "loss": 0.3448, "step": 242380 }, { "epoch": 1.4408164963651169, "grad_norm": 4.670403003692627, "learning_rate": 8.959726272098663e-06, "loss": 0.3746, "step": 242390 }, { "epoch": 1.4408759384417853, "grad_norm": 4.376158237457275, "learning_rate": 8.959599575635058e-06, "loss": 0.3657, "step": 242400 }, { "epoch": 1.4409353805184537, "grad_norm": 4.445085525512695, "learning_rate": 8.959472872352552e-06, "loss": 0.3257, "step": 242410 }, { "epoch": 1.4409948225951221, "grad_norm": 7.32120418548584, "learning_rate": 8.959346162251358e-06, "loss": 0.3328, "step": 242420 }, { "epoch": 1.4410542646717905, "grad_norm": 5.644985198974609, "learning_rate": 8.959219445331701e-06, "loss": 0.3813, "step": 242430 }, { "epoch": 1.441113706748459, "grad_norm": 5.5647783279418945, "learning_rate": 8.959092721593795e-06, "loss": 0.381, "step": 242440 }, { "epoch": 1.4411731488251274, "grad_norm": 4.11021089553833, "learning_rate": 8.958965991037858e-06, "loss": 0.3527, "step": 242450 }, { "epoch": 1.4412325909017958, "grad_norm": 5.429651260375977, "learning_rate": 8.95883925366411e-06, "loss": 0.3753, "step": 242460 }, { "epoch": 1.4412920329784642, "grad_norm": 6.413092613220215, "learning_rate": 8.958712509472768e-06, "loss": 0.3721, "step": 242470 }, { "epoch": 1.4413514750551326, "grad_norm": 4.531588077545166, "learning_rate": 8.958585758464052e-06, "loss": 0.38, "step": 242480 }, { "epoch": 1.441410917131801, "grad_norm": 5.121812343597412, "learning_rate": 8.958459000638177e-06, "loss": 0.4004, "step": 242490 }, { "epoch": 1.4414703592084694, "grad_norm": 4.446737289428711, "learning_rate": 8.958332235995364e-06, "loss": 0.3604, "step": 242500 }, { "epoch": 1.4415298012851376, "grad_norm": 5.0059027671813965, "learning_rate": 8.95820546453583e-06, "loss": 0.3313, "step": 242510 }, { "epoch": 1.441589243361806, "grad_norm": 5.4365620613098145, "learning_rate": 8.958078686259795e-06, "loss": 0.4222, "step": 242520 }, { "epoch": 1.4416486854384745, "grad_norm": 5.642045974731445, "learning_rate": 8.957951901167474e-06, "loss": 0.3863, "step": 242530 }, { "epoch": 1.4417081275151429, "grad_norm": 4.049345970153809, "learning_rate": 8.95782510925909e-06, "loss": 0.3213, "step": 242540 }, { "epoch": 1.4417675695918113, "grad_norm": 4.350526332855225, "learning_rate": 8.957698310534859e-06, "loss": 0.3422, "step": 242550 }, { "epoch": 1.4418270116684797, "grad_norm": 5.504902362823486, "learning_rate": 8.957571504994998e-06, "loss": 0.3524, "step": 242560 }, { "epoch": 1.4418864537451481, "grad_norm": 4.9843430519104, "learning_rate": 8.957444692639727e-06, "loss": 0.343, "step": 242570 }, { "epoch": 1.4419458958218163, "grad_norm": 4.48388671875, "learning_rate": 8.957317873469265e-06, "loss": 0.3696, "step": 242580 }, { "epoch": 1.4420053378984847, "grad_norm": 5.439704418182373, "learning_rate": 8.957191047483828e-06, "loss": 0.3528, "step": 242590 }, { "epoch": 1.4420647799751531, "grad_norm": 3.1793830394744873, "learning_rate": 8.957064214683637e-06, "loss": 0.3299, "step": 242600 }, { "epoch": 1.4421242220518216, "grad_norm": 4.496552467346191, "learning_rate": 8.956937375068908e-06, "loss": 0.3482, "step": 242610 }, { "epoch": 1.44218366412849, "grad_norm": 5.23807954788208, "learning_rate": 8.956810528639862e-06, "loss": 0.4144, "step": 242620 }, { "epoch": 1.4422431062051584, "grad_norm": 4.972750186920166, "learning_rate": 8.956683675396715e-06, "loss": 0.3348, "step": 242630 }, { "epoch": 1.4423025482818268, "grad_norm": 4.625372409820557, "learning_rate": 8.956556815339688e-06, "loss": 0.3576, "step": 242640 }, { "epoch": 1.4423619903584952, "grad_norm": 5.623478889465332, "learning_rate": 8.956429948468997e-06, "loss": 0.3865, "step": 242650 }, { "epoch": 1.4424214324351636, "grad_norm": 6.633790016174316, "learning_rate": 8.956303074784862e-06, "loss": 0.3724, "step": 242660 }, { "epoch": 1.442480874511832, "grad_norm": 5.615618705749512, "learning_rate": 8.956176194287501e-06, "loss": 0.3825, "step": 242670 }, { "epoch": 1.4425403165885005, "grad_norm": 4.97325325012207, "learning_rate": 8.956049306977133e-06, "loss": 0.3471, "step": 242680 }, { "epoch": 1.4425997586651687, "grad_norm": 4.668089866638184, "learning_rate": 8.955922412853974e-06, "loss": 0.3657, "step": 242690 }, { "epoch": 1.442659200741837, "grad_norm": 3.57460355758667, "learning_rate": 8.955795511918247e-06, "loss": 0.3465, "step": 242700 }, { "epoch": 1.4427186428185055, "grad_norm": 5.72222375869751, "learning_rate": 8.955668604170167e-06, "loss": 0.3903, "step": 242710 }, { "epoch": 1.442778084895174, "grad_norm": 5.584628582000732, "learning_rate": 8.955541689609954e-06, "loss": 0.3822, "step": 242720 }, { "epoch": 1.4428375269718423, "grad_norm": 3.243318557739258, "learning_rate": 8.955414768237827e-06, "loss": 0.3494, "step": 242730 }, { "epoch": 1.4428969690485107, "grad_norm": 4.992088317871094, "learning_rate": 8.955287840054004e-06, "loss": 0.357, "step": 242740 }, { "epoch": 1.4429564111251791, "grad_norm": 3.8662595748901367, "learning_rate": 8.955160905058701e-06, "loss": 0.3582, "step": 242750 }, { "epoch": 1.4430158532018473, "grad_norm": 5.152862548828125, "learning_rate": 8.955033963252139e-06, "loss": 0.3529, "step": 242760 }, { "epoch": 1.4430752952785157, "grad_norm": 6.608667373657227, "learning_rate": 8.95490701463454e-06, "loss": 0.4126, "step": 242770 }, { "epoch": 1.4431347373551842, "grad_norm": 5.248345375061035, "learning_rate": 8.954780059206117e-06, "loss": 0.389, "step": 242780 }, { "epoch": 1.4431941794318526, "grad_norm": 4.242449760437012, "learning_rate": 8.954653096967089e-06, "loss": 0.3427, "step": 242790 }, { "epoch": 1.443253621508521, "grad_norm": 4.825101375579834, "learning_rate": 8.95452612791768e-06, "loss": 0.3823, "step": 242800 }, { "epoch": 1.4433130635851894, "grad_norm": 3.4998490810394287, "learning_rate": 8.954399152058104e-06, "loss": 0.3451, "step": 242810 }, { "epoch": 1.4433725056618578, "grad_norm": 8.088813781738281, "learning_rate": 8.95427216938858e-06, "loss": 0.3759, "step": 242820 }, { "epoch": 1.4434319477385262, "grad_norm": 4.362119197845459, "learning_rate": 8.95414517990933e-06, "loss": 0.3713, "step": 242830 }, { "epoch": 1.4434913898151946, "grad_norm": 6.1475934982299805, "learning_rate": 8.954018183620568e-06, "loss": 0.3666, "step": 242840 }, { "epoch": 1.443550831891863, "grad_norm": 3.5891010761260986, "learning_rate": 8.953891180522514e-06, "loss": 0.3471, "step": 242850 }, { "epoch": 1.4436102739685315, "grad_norm": 5.412476539611816, "learning_rate": 8.953764170615389e-06, "loss": 0.3777, "step": 242860 }, { "epoch": 1.4436697160452, "grad_norm": 5.8564348220825195, "learning_rate": 8.95363715389941e-06, "loss": 0.3358, "step": 242870 }, { "epoch": 1.443729158121868, "grad_norm": 5.103874206542969, "learning_rate": 8.953510130374797e-06, "loss": 0.393, "step": 242880 }, { "epoch": 1.4437886001985365, "grad_norm": 5.8569183349609375, "learning_rate": 8.953383100041767e-06, "loss": 0.3709, "step": 242890 }, { "epoch": 1.443848042275205, "grad_norm": 5.155213832855225, "learning_rate": 8.953256062900539e-06, "loss": 0.35, "step": 242900 }, { "epoch": 1.4439074843518733, "grad_norm": 4.80032205581665, "learning_rate": 8.953129018951334e-06, "loss": 0.3515, "step": 242910 }, { "epoch": 1.4439669264285417, "grad_norm": 6.008097171783447, "learning_rate": 8.953001968194368e-06, "loss": 0.3631, "step": 242920 }, { "epoch": 1.4440263685052102, "grad_norm": 5.103997230529785, "learning_rate": 8.95287491062986e-06, "loss": 0.3831, "step": 242930 }, { "epoch": 1.4440858105818786, "grad_norm": 4.193637371063232, "learning_rate": 8.952747846258032e-06, "loss": 0.3975, "step": 242940 }, { "epoch": 1.4441452526585468, "grad_norm": 4.46827507019043, "learning_rate": 8.952620775079099e-06, "loss": 0.3296, "step": 242950 }, { "epoch": 1.4442046947352152, "grad_norm": 4.552116394042969, "learning_rate": 8.952493697093283e-06, "loss": 0.3352, "step": 242960 }, { "epoch": 1.4442641368118836, "grad_norm": 5.180378437042236, "learning_rate": 8.9523666123008e-06, "loss": 0.3664, "step": 242970 }, { "epoch": 1.444323578888552, "grad_norm": 6.248739719390869, "learning_rate": 8.952239520701868e-06, "loss": 0.3524, "step": 242980 }, { "epoch": 1.4443830209652204, "grad_norm": 5.749435901641846, "learning_rate": 8.952112422296712e-06, "loss": 0.3337, "step": 242990 }, { "epoch": 1.4444424630418888, "grad_norm": 4.472527027130127, "learning_rate": 8.951985317085546e-06, "loss": 0.3387, "step": 243000 }, { "epoch": 1.4445019051185573, "grad_norm": 3.92895770072937, "learning_rate": 8.951858205068587e-06, "loss": 0.3801, "step": 243010 }, { "epoch": 1.4445613471952257, "grad_norm": 9.40134048461914, "learning_rate": 8.951731086246058e-06, "loss": 0.3774, "step": 243020 }, { "epoch": 1.444620789271894, "grad_norm": 5.387111663818359, "learning_rate": 8.951603960618179e-06, "loss": 0.3757, "step": 243030 }, { "epoch": 1.4446802313485625, "grad_norm": 5.471378326416016, "learning_rate": 8.951476828185163e-06, "loss": 0.3472, "step": 243040 }, { "epoch": 1.444739673425231, "grad_norm": 4.8005595207214355, "learning_rate": 8.951349688947234e-06, "loss": 0.3571, "step": 243050 }, { "epoch": 1.444799115501899, "grad_norm": 6.739849090576172, "learning_rate": 8.951222542904609e-06, "loss": 0.357, "step": 243060 }, { "epoch": 1.4448585575785675, "grad_norm": 3.692797899246216, "learning_rate": 8.951095390057508e-06, "loss": 0.3609, "step": 243070 }, { "epoch": 1.444917999655236, "grad_norm": 6.994931697845459, "learning_rate": 8.95096823040615e-06, "loss": 0.403, "step": 243080 }, { "epoch": 1.4449774417319043, "grad_norm": 5.474425315856934, "learning_rate": 8.95084106395075e-06, "loss": 0.3872, "step": 243090 }, { "epoch": 1.4450368838085728, "grad_norm": 4.060690879821777, "learning_rate": 8.950713890691534e-06, "loss": 0.3605, "step": 243100 }, { "epoch": 1.4450963258852412, "grad_norm": 4.482598781585693, "learning_rate": 8.950586710628715e-06, "loss": 0.3243, "step": 243110 }, { "epoch": 1.4451557679619096, "grad_norm": 5.612920761108398, "learning_rate": 8.950459523762516e-06, "loss": 0.3582, "step": 243120 }, { "epoch": 1.4452152100385778, "grad_norm": 6.390183925628662, "learning_rate": 8.950332330093151e-06, "loss": 0.3674, "step": 243130 }, { "epoch": 1.4452746521152462, "grad_norm": 5.220112323760986, "learning_rate": 8.950205129620845e-06, "loss": 0.3379, "step": 243140 }, { "epoch": 1.4453340941919146, "grad_norm": 6.579837322235107, "learning_rate": 8.950077922345816e-06, "loss": 0.348, "step": 243150 }, { "epoch": 1.445393536268583, "grad_norm": 5.9455084800720215, "learning_rate": 8.94995070826828e-06, "loss": 0.3746, "step": 243160 }, { "epoch": 1.4454529783452514, "grad_norm": 5.130786418914795, "learning_rate": 8.949823487388457e-06, "loss": 0.3699, "step": 243170 }, { "epoch": 1.4455124204219199, "grad_norm": 5.660304069519043, "learning_rate": 8.949696259706565e-06, "loss": 0.3743, "step": 243180 }, { "epoch": 1.4455718624985883, "grad_norm": 6.323657989501953, "learning_rate": 8.949569025222829e-06, "loss": 0.3431, "step": 243190 }, { "epoch": 1.4456313045752567, "grad_norm": 4.4309163093566895, "learning_rate": 8.94944178393746e-06, "loss": 0.3565, "step": 243200 }, { "epoch": 1.445690746651925, "grad_norm": 4.382028102874756, "learning_rate": 8.949314535850684e-06, "loss": 0.3428, "step": 243210 }, { "epoch": 1.4457501887285935, "grad_norm": 7.068562984466553, "learning_rate": 8.949187280962716e-06, "loss": 0.3631, "step": 243220 }, { "epoch": 1.445809630805262, "grad_norm": 7.590723037719727, "learning_rate": 8.949060019273775e-06, "loss": 0.3535, "step": 243230 }, { "epoch": 1.4458690728819303, "grad_norm": 5.0574870109558105, "learning_rate": 8.948932750784083e-06, "loss": 0.3667, "step": 243240 }, { "epoch": 1.4459285149585985, "grad_norm": 4.969887733459473, "learning_rate": 8.948805475493858e-06, "loss": 0.3779, "step": 243250 }, { "epoch": 1.445987957035267, "grad_norm": 5.424901485443115, "learning_rate": 8.948678193403317e-06, "loss": 0.4181, "step": 243260 }, { "epoch": 1.4460473991119354, "grad_norm": 5.1937456130981445, "learning_rate": 8.948550904512684e-06, "loss": 0.3789, "step": 243270 }, { "epoch": 1.4461068411886038, "grad_norm": 4.7079362869262695, "learning_rate": 8.948423608822172e-06, "loss": 0.3734, "step": 243280 }, { "epoch": 1.4461662832652722, "grad_norm": 6.954969882965088, "learning_rate": 8.948296306332004e-06, "loss": 0.403, "step": 243290 }, { "epoch": 1.4462257253419406, "grad_norm": 6.276385307312012, "learning_rate": 8.948168997042398e-06, "loss": 0.3557, "step": 243300 }, { "epoch": 1.446285167418609, "grad_norm": 4.713016986846924, "learning_rate": 8.948041680953576e-06, "loss": 0.3281, "step": 243310 }, { "epoch": 1.4463446094952772, "grad_norm": 4.3865065574646, "learning_rate": 8.947914358065754e-06, "loss": 0.3252, "step": 243320 }, { "epoch": 1.4464040515719456, "grad_norm": 6.29740571975708, "learning_rate": 8.947787028379153e-06, "loss": 0.3931, "step": 243330 }, { "epoch": 1.446463493648614, "grad_norm": 4.251911640167236, "learning_rate": 8.947659691893991e-06, "loss": 0.3633, "step": 243340 }, { "epoch": 1.4465229357252825, "grad_norm": 4.21931791305542, "learning_rate": 8.947532348610488e-06, "loss": 0.3674, "step": 243350 }, { "epoch": 1.4465823778019509, "grad_norm": 4.192014217376709, "learning_rate": 8.947404998528863e-06, "loss": 0.3306, "step": 243360 }, { "epoch": 1.4466418198786193, "grad_norm": 7.096203327178955, "learning_rate": 8.947277641649338e-06, "loss": 0.3956, "step": 243370 }, { "epoch": 1.4467012619552877, "grad_norm": 3.0543930530548096, "learning_rate": 8.947150277972128e-06, "loss": 0.3732, "step": 243380 }, { "epoch": 1.4467607040319561, "grad_norm": 5.412384033203125, "learning_rate": 8.947022907497453e-06, "loss": 0.3516, "step": 243390 }, { "epoch": 1.4468201461086245, "grad_norm": 3.9173004627227783, "learning_rate": 8.946895530225537e-06, "loss": 0.3375, "step": 243400 }, { "epoch": 1.446879588185293, "grad_norm": 4.6061787605285645, "learning_rate": 8.946768146156592e-06, "loss": 0.3611, "step": 243410 }, { "epoch": 1.4469390302619614, "grad_norm": 4.165053844451904, "learning_rate": 8.946640755290845e-06, "loss": 0.3717, "step": 243420 }, { "epoch": 1.4469984723386295, "grad_norm": 4.191568374633789, "learning_rate": 8.94651335762851e-06, "loss": 0.376, "step": 243430 }, { "epoch": 1.447057914415298, "grad_norm": 4.7140069007873535, "learning_rate": 8.946385953169808e-06, "loss": 0.3535, "step": 243440 }, { "epoch": 1.4471173564919664, "grad_norm": 3.970658540725708, "learning_rate": 8.946258541914959e-06, "loss": 0.3363, "step": 243450 }, { "epoch": 1.4471767985686348, "grad_norm": 5.952245235443115, "learning_rate": 8.946131123864181e-06, "loss": 0.3715, "step": 243460 }, { "epoch": 1.4472362406453032, "grad_norm": 5.244540214538574, "learning_rate": 8.946003699017696e-06, "loss": 0.3514, "step": 243470 }, { "epoch": 1.4472956827219716, "grad_norm": 5.454427719116211, "learning_rate": 8.945876267375719e-06, "loss": 0.3627, "step": 243480 }, { "epoch": 1.44735512479864, "grad_norm": 5.6158833503723145, "learning_rate": 8.945748828938475e-06, "loss": 0.3677, "step": 243490 }, { "epoch": 1.4474145668753082, "grad_norm": 4.670623302459717, "learning_rate": 8.94562138370618e-06, "loss": 0.371, "step": 243500 }, { "epoch": 1.4474740089519766, "grad_norm": 3.2123472690582275, "learning_rate": 8.945493931679054e-06, "loss": 0.3919, "step": 243510 }, { "epoch": 1.447533451028645, "grad_norm": 5.232809066772461, "learning_rate": 8.945366472857315e-06, "loss": 0.379, "step": 243520 }, { "epoch": 1.4475928931053135, "grad_norm": 4.540645122528076, "learning_rate": 8.945239007241187e-06, "loss": 0.3723, "step": 243530 }, { "epoch": 1.4476523351819819, "grad_norm": 3.776264190673828, "learning_rate": 8.945111534830886e-06, "loss": 0.3375, "step": 243540 }, { "epoch": 1.4477117772586503, "grad_norm": 5.753610610961914, "learning_rate": 8.944984055626632e-06, "loss": 0.3898, "step": 243550 }, { "epoch": 1.4477712193353187, "grad_norm": 5.5892252922058105, "learning_rate": 8.944856569628643e-06, "loss": 0.3533, "step": 243560 }, { "epoch": 1.4478306614119871, "grad_norm": 5.341220378875732, "learning_rate": 8.944729076837142e-06, "loss": 0.3781, "step": 243570 }, { "epoch": 1.4478901034886555, "grad_norm": 4.5602617263793945, "learning_rate": 8.944601577252347e-06, "loss": 0.354, "step": 243580 }, { "epoch": 1.447949545565324, "grad_norm": 3.7620084285736084, "learning_rate": 8.944474070874477e-06, "loss": 0.3304, "step": 243590 }, { "epoch": 1.4480089876419924, "grad_norm": 5.180063247680664, "learning_rate": 8.94434655770375e-06, "loss": 0.3801, "step": 243600 }, { "epoch": 1.4480684297186608, "grad_norm": 4.803884029388428, "learning_rate": 8.944219037740392e-06, "loss": 0.3864, "step": 243610 }, { "epoch": 1.448127871795329, "grad_norm": 5.553839683532715, "learning_rate": 8.944091510984614e-06, "loss": 0.3733, "step": 243620 }, { "epoch": 1.4481873138719974, "grad_norm": 5.296145439147949, "learning_rate": 8.943963977436642e-06, "loss": 0.4009, "step": 243630 }, { "epoch": 1.4482467559486658, "grad_norm": 6.465505599975586, "learning_rate": 8.943836437096693e-06, "loss": 0.3868, "step": 243640 }, { "epoch": 1.4483061980253342, "grad_norm": 4.028286457061768, "learning_rate": 8.943708889964989e-06, "loss": 0.3745, "step": 243650 }, { "epoch": 1.4483656401020026, "grad_norm": 4.679059028625488, "learning_rate": 8.943581336041745e-06, "loss": 0.363, "step": 243660 }, { "epoch": 1.448425082178671, "grad_norm": 3.2500874996185303, "learning_rate": 8.943453775327185e-06, "loss": 0.3754, "step": 243670 }, { "epoch": 1.4484845242553395, "grad_norm": 5.512287139892578, "learning_rate": 8.943326207821525e-06, "loss": 0.357, "step": 243680 }, { "epoch": 1.4485439663320077, "grad_norm": 5.203485488891602, "learning_rate": 8.943198633524988e-06, "loss": 0.3644, "step": 243690 }, { "epoch": 1.448603408408676, "grad_norm": 5.536666393280029, "learning_rate": 8.943071052437794e-06, "loss": 0.3749, "step": 243700 }, { "epoch": 1.4486628504853445, "grad_norm": 4.675585746765137, "learning_rate": 8.94294346456016e-06, "loss": 0.3369, "step": 243710 }, { "epoch": 1.448722292562013, "grad_norm": 4.891366004943848, "learning_rate": 8.942815869892306e-06, "loss": 0.341, "step": 243720 }, { "epoch": 1.4487817346386813, "grad_norm": 5.323825359344482, "learning_rate": 8.942688268434454e-06, "loss": 0.3605, "step": 243730 }, { "epoch": 1.4488411767153497, "grad_norm": 5.416619777679443, "learning_rate": 8.94256066018682e-06, "loss": 0.3619, "step": 243740 }, { "epoch": 1.4489006187920181, "grad_norm": 5.484627723693848, "learning_rate": 8.942433045149627e-06, "loss": 0.3514, "step": 243750 }, { "epoch": 1.4489600608686866, "grad_norm": 4.930256366729736, "learning_rate": 8.942305423323097e-06, "loss": 0.3454, "step": 243760 }, { "epoch": 1.449019502945355, "grad_norm": 6.635138988494873, "learning_rate": 8.942177794707442e-06, "loss": 0.3679, "step": 243770 }, { "epoch": 1.4490789450220234, "grad_norm": 5.377144813537598, "learning_rate": 8.94205015930289e-06, "loss": 0.3358, "step": 243780 }, { "epoch": 1.4491383870986918, "grad_norm": 6.496126174926758, "learning_rate": 8.941922517109655e-06, "loss": 0.366, "step": 243790 }, { "epoch": 1.44919782917536, "grad_norm": 6.389839172363281, "learning_rate": 8.941794868127962e-06, "loss": 0.3576, "step": 243800 }, { "epoch": 1.4492572712520284, "grad_norm": 4.879520416259766, "learning_rate": 8.941667212358025e-06, "loss": 0.341, "step": 243810 }, { "epoch": 1.4493167133286968, "grad_norm": 4.719399929046631, "learning_rate": 8.94153954980007e-06, "loss": 0.3376, "step": 243820 }, { "epoch": 1.4493761554053652, "grad_norm": 8.039393424987793, "learning_rate": 8.94141188045431e-06, "loss": 0.3778, "step": 243830 }, { "epoch": 1.4494355974820337, "grad_norm": 4.965529441833496, "learning_rate": 8.94128420432097e-06, "loss": 0.3587, "step": 243840 }, { "epoch": 1.449495039558702, "grad_norm": 5.398270130157471, "learning_rate": 8.941156521400266e-06, "loss": 0.3619, "step": 243850 }, { "epoch": 1.4495544816353705, "grad_norm": 6.585119247436523, "learning_rate": 8.941028831692425e-06, "loss": 0.3485, "step": 243860 }, { "epoch": 1.4496139237120387, "grad_norm": 5.1150994300842285, "learning_rate": 8.94090113519766e-06, "loss": 0.3643, "step": 243870 }, { "epoch": 1.449673365788707, "grad_norm": 4.562805652618408, "learning_rate": 8.940773431916191e-06, "loss": 0.3476, "step": 243880 }, { "epoch": 1.4497328078653755, "grad_norm": 5.6398420333862305, "learning_rate": 8.940645721848242e-06, "loss": 0.4398, "step": 243890 }, { "epoch": 1.449792249942044, "grad_norm": 6.075047969818115, "learning_rate": 8.94051800499403e-06, "loss": 0.3805, "step": 243900 }, { "epoch": 1.4498516920187123, "grad_norm": 4.263748645782471, "learning_rate": 8.940390281353777e-06, "loss": 0.363, "step": 243910 }, { "epoch": 1.4499111340953807, "grad_norm": 5.957101821899414, "learning_rate": 8.9402625509277e-06, "loss": 0.3735, "step": 243920 }, { "epoch": 1.4499705761720492, "grad_norm": 5.5434770584106445, "learning_rate": 8.940134813716022e-06, "loss": 0.3592, "step": 243930 }, { "epoch": 1.4500300182487176, "grad_norm": 5.489282608032227, "learning_rate": 8.940007069718962e-06, "loss": 0.3924, "step": 243940 }, { "epoch": 1.450089460325386, "grad_norm": 4.853211879730225, "learning_rate": 8.939879318936739e-06, "loss": 0.3849, "step": 243950 }, { "epoch": 1.4501489024020544, "grad_norm": 4.483644008636475, "learning_rate": 8.939751561369573e-06, "loss": 0.3589, "step": 243960 }, { "epoch": 1.4502083444787228, "grad_norm": 3.696894645690918, "learning_rate": 8.939623797017686e-06, "loss": 0.3599, "step": 243970 }, { "epoch": 1.4502677865553912, "grad_norm": 5.881192207336426, "learning_rate": 8.939496025881295e-06, "loss": 0.3946, "step": 243980 }, { "epoch": 1.4503272286320594, "grad_norm": 5.784334659576416, "learning_rate": 8.939368247960625e-06, "loss": 0.4093, "step": 243990 }, { "epoch": 1.4503866707087278, "grad_norm": 5.7438459396362305, "learning_rate": 8.93924046325589e-06, "loss": 0.4077, "step": 244000 }, { "epoch": 1.4504461127853963, "grad_norm": 5.837491989135742, "learning_rate": 8.939112671767314e-06, "loss": 0.3499, "step": 244010 }, { "epoch": 1.4505055548620647, "grad_norm": 6.857997417449951, "learning_rate": 8.938984873495115e-06, "loss": 0.3828, "step": 244020 }, { "epoch": 1.450564996938733, "grad_norm": 4.432329177856445, "learning_rate": 8.938857068439516e-06, "loss": 0.3581, "step": 244030 }, { "epoch": 1.4506244390154015, "grad_norm": 4.107656955718994, "learning_rate": 8.938729256600733e-06, "loss": 0.3438, "step": 244040 }, { "epoch": 1.45068388109207, "grad_norm": 4.686768531799316, "learning_rate": 8.93860143797899e-06, "loss": 0.3639, "step": 244050 }, { "epoch": 1.450743323168738, "grad_norm": 6.1104736328125, "learning_rate": 8.938473612574506e-06, "loss": 0.3398, "step": 244060 }, { "epoch": 1.4508027652454065, "grad_norm": 4.369533538818359, "learning_rate": 8.938345780387499e-06, "loss": 0.3954, "step": 244070 }, { "epoch": 1.450862207322075, "grad_norm": 4.813938140869141, "learning_rate": 8.93821794141819e-06, "loss": 0.3411, "step": 244080 }, { "epoch": 1.4509216493987434, "grad_norm": 5.679834365844727, "learning_rate": 8.9380900956668e-06, "loss": 0.3766, "step": 244090 }, { "epoch": 1.4509810914754118, "grad_norm": 4.418076515197754, "learning_rate": 8.937962243133551e-06, "loss": 0.3414, "step": 244100 }, { "epoch": 1.4510405335520802, "grad_norm": 5.2539567947387695, "learning_rate": 8.937834383818659e-06, "loss": 0.3579, "step": 244110 }, { "epoch": 1.4510999756287486, "grad_norm": 6.445415496826172, "learning_rate": 8.937706517722347e-06, "loss": 0.3436, "step": 244120 }, { "epoch": 1.451159417705417, "grad_norm": 6.388987064361572, "learning_rate": 8.937578644844835e-06, "loss": 0.3517, "step": 244130 }, { "epoch": 1.4512188597820854, "grad_norm": 5.554295539855957, "learning_rate": 8.937450765186343e-06, "loss": 0.3631, "step": 244140 }, { "epoch": 1.4512783018587538, "grad_norm": 5.205760955810547, "learning_rate": 8.93732287874709e-06, "loss": 0.3701, "step": 244150 }, { "epoch": 1.4513377439354223, "grad_norm": 4.321778297424316, "learning_rate": 8.937194985527298e-06, "loss": 0.367, "step": 244160 }, { "epoch": 1.4513971860120904, "grad_norm": 3.366978406906128, "learning_rate": 8.937067085527184e-06, "loss": 0.3579, "step": 244170 }, { "epoch": 1.4514566280887589, "grad_norm": 5.084084510803223, "learning_rate": 8.936939178746973e-06, "loss": 0.3518, "step": 244180 }, { "epoch": 1.4515160701654273, "grad_norm": 4.867258548736572, "learning_rate": 8.936811265186884e-06, "loss": 0.3556, "step": 244190 }, { "epoch": 1.4515755122420957, "grad_norm": 4.642681121826172, "learning_rate": 8.936683344847134e-06, "loss": 0.3352, "step": 244200 }, { "epoch": 1.451634954318764, "grad_norm": 5.26202392578125, "learning_rate": 8.936555417727947e-06, "loss": 0.37, "step": 244210 }, { "epoch": 1.4516943963954325, "grad_norm": 4.7555742263793945, "learning_rate": 8.936427483829541e-06, "loss": 0.3789, "step": 244220 }, { "epoch": 1.451753838472101, "grad_norm": 5.451607704162598, "learning_rate": 8.936299543152139e-06, "loss": 0.3713, "step": 244230 }, { "epoch": 1.4518132805487691, "grad_norm": 5.474188327789307, "learning_rate": 8.936171595695957e-06, "loss": 0.3572, "step": 244240 }, { "epoch": 1.4518727226254375, "grad_norm": 3.9782564640045166, "learning_rate": 8.936043641461219e-06, "loss": 0.3868, "step": 244250 }, { "epoch": 1.451932164702106, "grad_norm": 5.468381881713867, "learning_rate": 8.935915680448144e-06, "loss": 0.3253, "step": 244260 }, { "epoch": 1.4519916067787744, "grad_norm": 3.7009201049804688, "learning_rate": 8.935787712656953e-06, "loss": 0.3608, "step": 244270 }, { "epoch": 1.4520510488554428, "grad_norm": 6.932760715484619, "learning_rate": 8.935659738087865e-06, "loss": 0.3671, "step": 244280 }, { "epoch": 1.4521104909321112, "grad_norm": 6.937389373779297, "learning_rate": 8.935531756741103e-06, "loss": 0.3528, "step": 244290 }, { "epoch": 1.4521699330087796, "grad_norm": 6.214828968048096, "learning_rate": 8.935403768616884e-06, "loss": 0.3864, "step": 244300 }, { "epoch": 1.452229375085448, "grad_norm": 5.054511070251465, "learning_rate": 8.935275773715431e-06, "loss": 0.3997, "step": 244310 }, { "epoch": 1.4522888171621164, "grad_norm": 4.941857814788818, "learning_rate": 8.935147772036964e-06, "loss": 0.3534, "step": 244320 }, { "epoch": 1.4523482592387849, "grad_norm": 5.354321479797363, "learning_rate": 8.935019763581703e-06, "loss": 0.3804, "step": 244330 }, { "epoch": 1.4524077013154533, "grad_norm": 3.680569887161255, "learning_rate": 8.934891748349867e-06, "loss": 0.3768, "step": 244340 }, { "epoch": 1.4524671433921217, "grad_norm": 4.208533763885498, "learning_rate": 8.934763726341679e-06, "loss": 0.3472, "step": 244350 }, { "epoch": 1.4525265854687899, "grad_norm": 3.856348991394043, "learning_rate": 8.93463569755736e-06, "loss": 0.3182, "step": 244360 }, { "epoch": 1.4525860275454583, "grad_norm": 4.895737171173096, "learning_rate": 8.934507661997124e-06, "loss": 0.3405, "step": 244370 }, { "epoch": 1.4526454696221267, "grad_norm": 6.070562839508057, "learning_rate": 8.934379619661201e-06, "loss": 0.3483, "step": 244380 }, { "epoch": 1.4527049116987951, "grad_norm": 4.414004802703857, "learning_rate": 8.934251570549805e-06, "loss": 0.3699, "step": 244390 }, { "epoch": 1.4527643537754635, "grad_norm": 5.471780776977539, "learning_rate": 8.934123514663159e-06, "loss": 0.3612, "step": 244400 }, { "epoch": 1.452823795852132, "grad_norm": 4.987745761871338, "learning_rate": 8.933995452001483e-06, "loss": 0.3943, "step": 244410 }, { "epoch": 1.4528832379288001, "grad_norm": 3.36114501953125, "learning_rate": 8.933867382564996e-06, "loss": 0.3244, "step": 244420 }, { "epoch": 1.4529426800054686, "grad_norm": 5.199028491973877, "learning_rate": 8.933739306353921e-06, "loss": 0.354, "step": 244430 }, { "epoch": 1.453002122082137, "grad_norm": 6.017404079437256, "learning_rate": 8.933611223368477e-06, "loss": 0.3418, "step": 244440 }, { "epoch": 1.4530615641588054, "grad_norm": 4.404947757720947, "learning_rate": 8.933483133608887e-06, "loss": 0.3714, "step": 244450 }, { "epoch": 1.4531210062354738, "grad_norm": 3.986969470977783, "learning_rate": 8.933355037075369e-06, "loss": 0.3421, "step": 244460 }, { "epoch": 1.4531804483121422, "grad_norm": 5.176558971405029, "learning_rate": 8.933226933768142e-06, "loss": 0.3621, "step": 244470 }, { "epoch": 1.4532398903888106, "grad_norm": 5.451767921447754, "learning_rate": 8.933098823687432e-06, "loss": 0.3496, "step": 244480 }, { "epoch": 1.453299332465479, "grad_norm": 3.8052358627319336, "learning_rate": 8.932970706833455e-06, "loss": 0.3999, "step": 244490 }, { "epoch": 1.4533587745421475, "grad_norm": 5.676823139190674, "learning_rate": 8.932842583206433e-06, "loss": 0.3891, "step": 244500 }, { "epoch": 1.4534182166188159, "grad_norm": 4.893855571746826, "learning_rate": 8.932714452806587e-06, "loss": 0.4199, "step": 244510 }, { "epoch": 1.4534776586954843, "grad_norm": 6.755373477935791, "learning_rate": 8.932586315634137e-06, "loss": 0.3707, "step": 244520 }, { "epoch": 1.4535371007721527, "grad_norm": 5.247707843780518, "learning_rate": 8.932458171689304e-06, "loss": 0.3706, "step": 244530 }, { "epoch": 1.453596542848821, "grad_norm": 4.024280548095703, "learning_rate": 8.93233002097231e-06, "loss": 0.3594, "step": 244540 }, { "epoch": 1.4536559849254893, "grad_norm": 5.11078405380249, "learning_rate": 8.932201863483374e-06, "loss": 0.401, "step": 244550 }, { "epoch": 1.4537154270021577, "grad_norm": 4.292903423309326, "learning_rate": 8.932073699222718e-06, "loss": 0.3717, "step": 244560 }, { "epoch": 1.4537748690788261, "grad_norm": 4.45094108581543, "learning_rate": 8.93194552819056e-06, "loss": 0.3043, "step": 244570 }, { "epoch": 1.4538343111554946, "grad_norm": 6.865291118621826, "learning_rate": 8.931817350387125e-06, "loss": 0.4034, "step": 244580 }, { "epoch": 1.453893753232163, "grad_norm": 4.505405902862549, "learning_rate": 8.93168916581263e-06, "loss": 0.3629, "step": 244590 }, { "epoch": 1.4539531953088314, "grad_norm": 5.846909046173096, "learning_rate": 8.931560974467297e-06, "loss": 0.3832, "step": 244600 }, { "epoch": 1.4540126373854996, "grad_norm": 4.5875244140625, "learning_rate": 8.931432776351348e-06, "loss": 0.3709, "step": 244610 }, { "epoch": 1.454072079462168, "grad_norm": 5.230190277099609, "learning_rate": 8.931304571465001e-06, "loss": 0.3608, "step": 244620 }, { "epoch": 1.4541315215388364, "grad_norm": 5.255791187286377, "learning_rate": 8.93117635980848e-06, "loss": 0.3416, "step": 244630 }, { "epoch": 1.4541909636155048, "grad_norm": 4.724942207336426, "learning_rate": 8.931048141382004e-06, "loss": 0.3689, "step": 244640 }, { "epoch": 1.4542504056921732, "grad_norm": 5.030346393585205, "learning_rate": 8.930919916185793e-06, "loss": 0.3952, "step": 244650 }, { "epoch": 1.4543098477688416, "grad_norm": 6.09370756149292, "learning_rate": 8.930791684220068e-06, "loss": 0.3831, "step": 244660 }, { "epoch": 1.45436928984551, "grad_norm": 4.7589030265808105, "learning_rate": 8.930663445485052e-06, "loss": 0.323, "step": 244670 }, { "epoch": 1.4544287319221785, "grad_norm": 5.585973262786865, "learning_rate": 8.930535199980966e-06, "loss": 0.4193, "step": 244680 }, { "epoch": 1.454488173998847, "grad_norm": 4.210452556610107, "learning_rate": 8.930406947708027e-06, "loss": 0.3657, "step": 244690 }, { "epoch": 1.4545476160755153, "grad_norm": 6.536482810974121, "learning_rate": 8.930278688666461e-06, "loss": 0.4023, "step": 244700 }, { "epoch": 1.4546070581521837, "grad_norm": 3.6291005611419678, "learning_rate": 8.930150422856485e-06, "loss": 0.3475, "step": 244710 }, { "epoch": 1.4546665002288521, "grad_norm": 5.93214225769043, "learning_rate": 8.93002215027832e-06, "loss": 0.3875, "step": 244720 }, { "epoch": 1.4547259423055203, "grad_norm": 5.393021106719971, "learning_rate": 8.929893870932188e-06, "loss": 0.3752, "step": 244730 }, { "epoch": 1.4547853843821887, "grad_norm": 5.726675510406494, "learning_rate": 8.929765584818311e-06, "loss": 0.3586, "step": 244740 }, { "epoch": 1.4548448264588572, "grad_norm": 4.179854393005371, "learning_rate": 8.929637291936908e-06, "loss": 0.38, "step": 244750 }, { "epoch": 1.4549042685355256, "grad_norm": 5.858643054962158, "learning_rate": 8.9295089922882e-06, "loss": 0.3658, "step": 244760 }, { "epoch": 1.454963710612194, "grad_norm": 5.2974324226379395, "learning_rate": 8.929380685872411e-06, "loss": 0.3468, "step": 244770 }, { "epoch": 1.4550231526888624, "grad_norm": 4.648387432098389, "learning_rate": 8.929252372689757e-06, "loss": 0.3467, "step": 244780 }, { "epoch": 1.4550825947655306, "grad_norm": 4.239354610443115, "learning_rate": 8.929124052740464e-06, "loss": 0.3615, "step": 244790 }, { "epoch": 1.455142036842199, "grad_norm": 3.7866578102111816, "learning_rate": 8.928995726024748e-06, "loss": 0.3658, "step": 244800 }, { "epoch": 1.4552014789188674, "grad_norm": 4.017775535583496, "learning_rate": 8.928867392542835e-06, "loss": 0.3957, "step": 244810 }, { "epoch": 1.4552609209955358, "grad_norm": 5.780515670776367, "learning_rate": 8.928739052294941e-06, "loss": 0.3518, "step": 244820 }, { "epoch": 1.4553203630722042, "grad_norm": 4.67242956161499, "learning_rate": 8.928610705281293e-06, "loss": 0.4171, "step": 244830 }, { "epoch": 1.4553798051488727, "grad_norm": 4.880065441131592, "learning_rate": 8.928482351502105e-06, "loss": 0.3777, "step": 244840 }, { "epoch": 1.455439247225541, "grad_norm": 4.948062896728516, "learning_rate": 8.928353990957603e-06, "loss": 0.3352, "step": 244850 }, { "epoch": 1.4554986893022095, "grad_norm": 5.837652683258057, "learning_rate": 8.928225623648008e-06, "loss": 0.4126, "step": 244860 }, { "epoch": 1.455558131378878, "grad_norm": 5.0348286628723145, "learning_rate": 8.928097249573538e-06, "loss": 0.3356, "step": 244870 }, { "epoch": 1.4556175734555463, "grad_norm": 5.192623615264893, "learning_rate": 8.927968868734417e-06, "loss": 0.3625, "step": 244880 }, { "epoch": 1.4556770155322147, "grad_norm": 5.280588150024414, "learning_rate": 8.927840481130866e-06, "loss": 0.3447, "step": 244890 }, { "epoch": 1.4557364576088831, "grad_norm": 5.631850719451904, "learning_rate": 8.927712086763101e-06, "loss": 0.3858, "step": 244900 }, { "epoch": 1.4557958996855513, "grad_norm": 6.938237190246582, "learning_rate": 8.927583685631352e-06, "loss": 0.3464, "step": 244910 }, { "epoch": 1.4558553417622198, "grad_norm": 5.424161911010742, "learning_rate": 8.927455277735831e-06, "loss": 0.3562, "step": 244920 }, { "epoch": 1.4559147838388882, "grad_norm": 4.271059513092041, "learning_rate": 8.927326863076766e-06, "loss": 0.3699, "step": 244930 }, { "epoch": 1.4559742259155566, "grad_norm": 3.4123613834381104, "learning_rate": 8.927198441654374e-06, "loss": 0.3385, "step": 244940 }, { "epoch": 1.456033667992225, "grad_norm": 5.554233074188232, "learning_rate": 8.927070013468878e-06, "loss": 0.3293, "step": 244950 }, { "epoch": 1.4560931100688934, "grad_norm": 4.427496433258057, "learning_rate": 8.9269415785205e-06, "loss": 0.3754, "step": 244960 }, { "epoch": 1.4561525521455618, "grad_norm": 5.845665454864502, "learning_rate": 8.92681313680946e-06, "loss": 0.3786, "step": 244970 }, { "epoch": 1.45621199422223, "grad_norm": 4.991262435913086, "learning_rate": 8.926684688335978e-06, "loss": 0.3447, "step": 244980 }, { "epoch": 1.4562714362988984, "grad_norm": 5.38149356842041, "learning_rate": 8.926556233100279e-06, "loss": 0.3993, "step": 244990 }, { "epoch": 1.4563308783755669, "grad_norm": 5.022817134857178, "learning_rate": 8.92642777110258e-06, "loss": 0.3437, "step": 245000 }, { "epoch": 1.4563903204522353, "grad_norm": 5.035477161407471, "learning_rate": 8.926299302343101e-06, "loss": 0.3627, "step": 245010 }, { "epoch": 1.4564497625289037, "grad_norm": 5.240447521209717, "learning_rate": 8.926170826822071e-06, "loss": 0.3962, "step": 245020 }, { "epoch": 1.456509204605572, "grad_norm": 6.29313325881958, "learning_rate": 8.926042344539703e-06, "loss": 0.3603, "step": 245030 }, { "epoch": 1.4565686466822405, "grad_norm": 5.382262229919434, "learning_rate": 8.925913855496224e-06, "loss": 0.3956, "step": 245040 }, { "epoch": 1.456628088758909, "grad_norm": 4.024631500244141, "learning_rate": 8.92578535969185e-06, "loss": 0.3679, "step": 245050 }, { "epoch": 1.4566875308355773, "grad_norm": 3.6180992126464844, "learning_rate": 8.925656857126808e-06, "loss": 0.3718, "step": 245060 }, { "epoch": 1.4567469729122458, "grad_norm": 5.180095195770264, "learning_rate": 8.925528347801316e-06, "loss": 0.3844, "step": 245070 }, { "epoch": 1.4568064149889142, "grad_norm": 6.630515098571777, "learning_rate": 8.925399831715595e-06, "loss": 0.3685, "step": 245080 }, { "epoch": 1.4568658570655826, "grad_norm": 5.682374954223633, "learning_rate": 8.925271308869868e-06, "loss": 0.3593, "step": 245090 }, { "epoch": 1.4569252991422508, "grad_norm": 4.728577613830566, "learning_rate": 8.925142779264354e-06, "loss": 0.3547, "step": 245100 }, { "epoch": 1.4569847412189192, "grad_norm": 5.383651256561279, "learning_rate": 8.925014242899278e-06, "loss": 0.3403, "step": 245110 }, { "epoch": 1.4570441832955876, "grad_norm": 4.17869234085083, "learning_rate": 8.924885699774857e-06, "loss": 0.4043, "step": 245120 }, { "epoch": 1.457103625372256, "grad_norm": 5.059142589569092, "learning_rate": 8.924757149891315e-06, "loss": 0.4008, "step": 245130 }, { "epoch": 1.4571630674489244, "grad_norm": 4.7166748046875, "learning_rate": 8.924628593248873e-06, "loss": 0.4049, "step": 245140 }, { "epoch": 1.4572225095255928, "grad_norm": 4.777646541595459, "learning_rate": 8.924500029847751e-06, "loss": 0.3649, "step": 245150 }, { "epoch": 1.457281951602261, "grad_norm": 5.478543758392334, "learning_rate": 8.924371459688173e-06, "loss": 0.3784, "step": 245160 }, { "epoch": 1.4573413936789295, "grad_norm": 6.202089309692383, "learning_rate": 8.92424288277036e-06, "loss": 0.343, "step": 245170 }, { "epoch": 1.4574008357555979, "grad_norm": 5.937962532043457, "learning_rate": 8.924114299094532e-06, "loss": 0.3843, "step": 245180 }, { "epoch": 1.4574602778322663, "grad_norm": 4.595594882965088, "learning_rate": 8.92398570866091e-06, "loss": 0.3744, "step": 245190 }, { "epoch": 1.4575197199089347, "grad_norm": 4.355752944946289, "learning_rate": 8.923857111469719e-06, "loss": 0.3095, "step": 245200 }, { "epoch": 1.4575791619856031, "grad_norm": 4.951122760772705, "learning_rate": 8.923728507521175e-06, "loss": 0.3819, "step": 245210 }, { "epoch": 1.4576386040622715, "grad_norm": 4.808084011077881, "learning_rate": 8.923599896815502e-06, "loss": 0.3561, "step": 245220 }, { "epoch": 1.45769804613894, "grad_norm": 4.835071086883545, "learning_rate": 8.923471279352924e-06, "loss": 0.3649, "step": 245230 }, { "epoch": 1.4577574882156084, "grad_norm": 3.4740149974823, "learning_rate": 8.92334265513366e-06, "loss": 0.351, "step": 245240 }, { "epoch": 1.4578169302922768, "grad_norm": 4.770398139953613, "learning_rate": 8.923214024157931e-06, "loss": 0.3883, "step": 245250 }, { "epoch": 1.4578763723689452, "grad_norm": 5.132587909698486, "learning_rate": 8.92308538642596e-06, "loss": 0.3598, "step": 245260 }, { "epoch": 1.4579358144456136, "grad_norm": 5.340453624725342, "learning_rate": 8.922956741937967e-06, "loss": 0.3789, "step": 245270 }, { "epoch": 1.4579952565222818, "grad_norm": 5.011593818664551, "learning_rate": 8.922828090694176e-06, "loss": 0.3335, "step": 245280 }, { "epoch": 1.4580546985989502, "grad_norm": 6.336791515350342, "learning_rate": 8.922699432694805e-06, "loss": 0.3608, "step": 245290 }, { "epoch": 1.4581141406756186, "grad_norm": 6.098165512084961, "learning_rate": 8.922570767940078e-06, "loss": 0.3685, "step": 245300 }, { "epoch": 1.458173582752287, "grad_norm": 5.908629417419434, "learning_rate": 8.922442096430218e-06, "loss": 0.3904, "step": 245310 }, { "epoch": 1.4582330248289554, "grad_norm": 4.961234092712402, "learning_rate": 8.922313418165443e-06, "loss": 0.3771, "step": 245320 }, { "epoch": 1.4582924669056239, "grad_norm": 4.033046245574951, "learning_rate": 8.922184733145976e-06, "loss": 0.3617, "step": 245330 }, { "epoch": 1.4583519089822923, "grad_norm": 4.057784080505371, "learning_rate": 8.922056041372039e-06, "loss": 0.3849, "step": 245340 }, { "epoch": 1.4584113510589605, "grad_norm": 4.844178676605225, "learning_rate": 8.921927342843854e-06, "loss": 0.3526, "step": 245350 }, { "epoch": 1.4584707931356289, "grad_norm": 6.792047023773193, "learning_rate": 8.921798637561641e-06, "loss": 0.3585, "step": 245360 }, { "epoch": 1.4585302352122973, "grad_norm": 5.797336101531982, "learning_rate": 8.921669925525625e-06, "loss": 0.3797, "step": 245370 }, { "epoch": 1.4585896772889657, "grad_norm": 5.368711948394775, "learning_rate": 8.921541206736024e-06, "loss": 0.3808, "step": 245380 }, { "epoch": 1.4586491193656341, "grad_norm": 5.569016456604004, "learning_rate": 8.921412481193061e-06, "loss": 0.3679, "step": 245390 }, { "epoch": 1.4587085614423025, "grad_norm": 4.240179538726807, "learning_rate": 8.921283748896959e-06, "loss": 0.3489, "step": 245400 }, { "epoch": 1.458768003518971, "grad_norm": 5.317129611968994, "learning_rate": 8.921155009847938e-06, "loss": 0.3592, "step": 245410 }, { "epoch": 1.4588274455956394, "grad_norm": 5.1990556716918945, "learning_rate": 8.92102626404622e-06, "loss": 0.3818, "step": 245420 }, { "epoch": 1.4588868876723078, "grad_norm": 5.965861797332764, "learning_rate": 8.920897511492026e-06, "loss": 0.4096, "step": 245430 }, { "epoch": 1.4589463297489762, "grad_norm": 4.010021686553955, "learning_rate": 8.92076875218558e-06, "loss": 0.3519, "step": 245440 }, { "epoch": 1.4590057718256446, "grad_norm": 5.132509231567383, "learning_rate": 8.920639986127101e-06, "loss": 0.3531, "step": 245450 }, { "epoch": 1.459065213902313, "grad_norm": 8.280211448669434, "learning_rate": 8.920511213316814e-06, "loss": 0.3808, "step": 245460 }, { "epoch": 1.4591246559789812, "grad_norm": 4.764700412750244, "learning_rate": 8.920382433754938e-06, "loss": 0.3334, "step": 245470 }, { "epoch": 1.4591840980556496, "grad_norm": 3.7017693519592285, "learning_rate": 8.920253647441695e-06, "loss": 0.3706, "step": 245480 }, { "epoch": 1.459243540132318, "grad_norm": 5.395727157592773, "learning_rate": 8.920124854377308e-06, "loss": 0.3632, "step": 245490 }, { "epoch": 1.4593029822089865, "grad_norm": 5.6167988777160645, "learning_rate": 8.919996054561998e-06, "loss": 0.4216, "step": 245500 }, { "epoch": 1.4593624242856549, "grad_norm": 5.271366596221924, "learning_rate": 8.919867247995987e-06, "loss": 0.3621, "step": 245510 }, { "epoch": 1.4594218663623233, "grad_norm": 4.052340507507324, "learning_rate": 8.9197384346795e-06, "loss": 0.3364, "step": 245520 }, { "epoch": 1.4594813084389915, "grad_norm": 3.7974207401275635, "learning_rate": 8.919609614612753e-06, "loss": 0.3591, "step": 245530 }, { "epoch": 1.45954075051566, "grad_norm": 5.373176097869873, "learning_rate": 8.91948078779597e-06, "loss": 0.3226, "step": 245540 }, { "epoch": 1.4596001925923283, "grad_norm": 4.3222761154174805, "learning_rate": 8.919351954229372e-06, "loss": 0.3882, "step": 245550 }, { "epoch": 1.4596596346689967, "grad_norm": 5.974847316741943, "learning_rate": 8.919223113913186e-06, "loss": 0.3617, "step": 245560 }, { "epoch": 1.4597190767456651, "grad_norm": 4.174277305603027, "learning_rate": 8.919094266847628e-06, "loss": 0.3909, "step": 245570 }, { "epoch": 1.4597785188223336, "grad_norm": 5.95844841003418, "learning_rate": 8.918965413032923e-06, "loss": 0.4269, "step": 245580 }, { "epoch": 1.459837960899002, "grad_norm": 5.793174743652344, "learning_rate": 8.918836552469291e-06, "loss": 0.3405, "step": 245590 }, { "epoch": 1.4598974029756704, "grad_norm": 5.950225830078125, "learning_rate": 8.918707685156956e-06, "loss": 0.3609, "step": 245600 }, { "epoch": 1.4599568450523388, "grad_norm": 3.8490724563598633, "learning_rate": 8.918578811096137e-06, "loss": 0.3435, "step": 245610 }, { "epoch": 1.4600162871290072, "grad_norm": 4.655300617218018, "learning_rate": 8.918449930287058e-06, "loss": 0.3546, "step": 245620 }, { "epoch": 1.4600757292056756, "grad_norm": 4.881601333618164, "learning_rate": 8.918321042729942e-06, "loss": 0.3271, "step": 245630 }, { "epoch": 1.460135171282344, "grad_norm": 7.0352044105529785, "learning_rate": 8.918192148425011e-06, "loss": 0.4, "step": 245640 }, { "epoch": 1.4601946133590122, "grad_norm": 5.052455902099609, "learning_rate": 8.918063247372483e-06, "loss": 0.3419, "step": 245650 }, { "epoch": 1.4602540554356807, "grad_norm": 4.364931583404541, "learning_rate": 8.917934339572582e-06, "loss": 0.3329, "step": 245660 }, { "epoch": 1.460313497512349, "grad_norm": 9.052159309387207, "learning_rate": 8.917805425025534e-06, "loss": 0.3908, "step": 245670 }, { "epoch": 1.4603729395890175, "grad_norm": 5.609930038452148, "learning_rate": 8.917676503731555e-06, "loss": 0.3772, "step": 245680 }, { "epoch": 1.460432381665686, "grad_norm": 7.321102142333984, "learning_rate": 8.91754757569087e-06, "loss": 0.3519, "step": 245690 }, { "epoch": 1.4604918237423543, "grad_norm": 4.075865745544434, "learning_rate": 8.917418640903701e-06, "loss": 0.3648, "step": 245700 }, { "epoch": 1.4605512658190227, "grad_norm": 4.198521614074707, "learning_rate": 8.91728969937027e-06, "loss": 0.3723, "step": 245710 }, { "epoch": 1.460610707895691, "grad_norm": 4.820686340332031, "learning_rate": 8.917160751090798e-06, "loss": 0.3433, "step": 245720 }, { "epoch": 1.4606701499723593, "grad_norm": 6.3101277351379395, "learning_rate": 8.917031796065507e-06, "loss": 0.3654, "step": 245730 }, { "epoch": 1.4607295920490277, "grad_norm": 5.881519317626953, "learning_rate": 8.916902834294622e-06, "loss": 0.3356, "step": 245740 }, { "epoch": 1.4607890341256962, "grad_norm": 4.474745750427246, "learning_rate": 8.916773865778361e-06, "loss": 0.3642, "step": 245750 }, { "epoch": 1.4608484762023646, "grad_norm": 5.428519248962402, "learning_rate": 8.91664489051695e-06, "loss": 0.3691, "step": 245760 }, { "epoch": 1.460907918279033, "grad_norm": 5.012600898742676, "learning_rate": 8.916515908510608e-06, "loss": 0.3227, "step": 245770 }, { "epoch": 1.4609673603557014, "grad_norm": 5.385634899139404, "learning_rate": 8.916386919759559e-06, "loss": 0.3667, "step": 245780 }, { "epoch": 1.4610268024323698, "grad_norm": 5.882843494415283, "learning_rate": 8.916257924264023e-06, "loss": 0.3503, "step": 245790 }, { "epoch": 1.4610862445090382, "grad_norm": 4.208028316497803, "learning_rate": 8.916128922024224e-06, "loss": 0.3503, "step": 245800 }, { "epoch": 1.4611456865857066, "grad_norm": 4.454182147979736, "learning_rate": 8.915999913040385e-06, "loss": 0.3457, "step": 245810 }, { "epoch": 1.461205128662375, "grad_norm": 6.05618143081665, "learning_rate": 8.915870897312727e-06, "loss": 0.3968, "step": 245820 }, { "epoch": 1.4612645707390435, "grad_norm": 6.182954788208008, "learning_rate": 8.91574187484147e-06, "loss": 0.3715, "step": 245830 }, { "epoch": 1.4613240128157117, "grad_norm": 3.973680257797241, "learning_rate": 8.915612845626838e-06, "loss": 0.398, "step": 245840 }, { "epoch": 1.46138345489238, "grad_norm": 4.0438666343688965, "learning_rate": 8.915483809669057e-06, "loss": 0.3153, "step": 245850 }, { "epoch": 1.4614428969690485, "grad_norm": 6.244033336639404, "learning_rate": 8.915354766968342e-06, "loss": 0.3326, "step": 245860 }, { "epoch": 1.461502339045717, "grad_norm": 5.9096269607543945, "learning_rate": 8.91522571752492e-06, "loss": 0.3307, "step": 245870 }, { "epoch": 1.4615617811223853, "grad_norm": 4.127996921539307, "learning_rate": 8.915096661339013e-06, "loss": 0.3229, "step": 245880 }, { "epoch": 1.4616212231990537, "grad_norm": 6.426212787628174, "learning_rate": 8.914967598410842e-06, "loss": 0.4046, "step": 245890 }, { "epoch": 1.461680665275722, "grad_norm": 4.632016181945801, "learning_rate": 8.914838528740631e-06, "loss": 0.3701, "step": 245900 }, { "epoch": 1.4617401073523903, "grad_norm": 7.57317590713501, "learning_rate": 8.9147094523286e-06, "loss": 0.3592, "step": 245910 }, { "epoch": 1.4617995494290588, "grad_norm": 5.570882797241211, "learning_rate": 8.914580369174971e-06, "loss": 0.3738, "step": 245920 }, { "epoch": 1.4618589915057272, "grad_norm": 5.301146984100342, "learning_rate": 8.914451279279968e-06, "loss": 0.3629, "step": 245930 }, { "epoch": 1.4619184335823956, "grad_norm": 4.612959384918213, "learning_rate": 8.914322182643813e-06, "loss": 0.4019, "step": 245940 }, { "epoch": 1.461977875659064, "grad_norm": 4.750373840332031, "learning_rate": 8.914193079266728e-06, "loss": 0.362, "step": 245950 }, { "epoch": 1.4620373177357324, "grad_norm": 4.767364978790283, "learning_rate": 8.914063969148935e-06, "loss": 0.4083, "step": 245960 }, { "epoch": 1.4620967598124008, "grad_norm": 4.417736053466797, "learning_rate": 8.91393485229066e-06, "loss": 0.3667, "step": 245970 }, { "epoch": 1.4621562018890693, "grad_norm": 5.065903663635254, "learning_rate": 8.91380572869212e-06, "loss": 0.3373, "step": 245980 }, { "epoch": 1.4622156439657377, "grad_norm": 4.802794933319092, "learning_rate": 8.913676598353539e-06, "loss": 0.3767, "step": 245990 }, { "epoch": 1.462275086042406, "grad_norm": 4.018484592437744, "learning_rate": 8.913547461275141e-06, "loss": 0.3495, "step": 246000 }, { "epoch": 1.4623345281190745, "grad_norm": 4.2435712814331055, "learning_rate": 8.913418317457145e-06, "loss": 0.3862, "step": 246010 }, { "epoch": 1.4623939701957427, "grad_norm": 5.1310296058654785, "learning_rate": 8.913289166899778e-06, "loss": 0.3656, "step": 246020 }, { "epoch": 1.462453412272411, "grad_norm": 6.466279029846191, "learning_rate": 8.91316000960326e-06, "loss": 0.4074, "step": 246030 }, { "epoch": 1.4625128543490795, "grad_norm": 5.490807056427002, "learning_rate": 8.913030845567812e-06, "loss": 0.4125, "step": 246040 }, { "epoch": 1.462572296425748, "grad_norm": 4.816614151000977, "learning_rate": 8.91290167479366e-06, "loss": 0.3949, "step": 246050 }, { "epoch": 1.4626317385024163, "grad_norm": 4.251229763031006, "learning_rate": 8.912772497281024e-06, "loss": 0.3863, "step": 246060 }, { "epoch": 1.4626911805790848, "grad_norm": 4.499320983886719, "learning_rate": 8.912643313030125e-06, "loss": 0.3808, "step": 246070 }, { "epoch": 1.4627506226557532, "grad_norm": 3.855138063430786, "learning_rate": 8.91251412204119e-06, "loss": 0.3297, "step": 246080 }, { "epoch": 1.4628100647324214, "grad_norm": 3.964299201965332, "learning_rate": 8.912384924314437e-06, "loss": 0.3542, "step": 246090 }, { "epoch": 1.4628695068090898, "grad_norm": 6.254653453826904, "learning_rate": 8.912255719850091e-06, "loss": 0.3579, "step": 246100 }, { "epoch": 1.4629289488857582, "grad_norm": 6.755798816680908, "learning_rate": 8.912126508648374e-06, "loss": 0.4332, "step": 246110 }, { "epoch": 1.4629883909624266, "grad_norm": 4.611730098724365, "learning_rate": 8.91199729070951e-06, "loss": 0.3785, "step": 246120 }, { "epoch": 1.463047833039095, "grad_norm": 5.154419422149658, "learning_rate": 8.911868066033717e-06, "loss": 0.3326, "step": 246130 }, { "epoch": 1.4631072751157634, "grad_norm": 5.383684158325195, "learning_rate": 8.911738834621221e-06, "loss": 0.4083, "step": 246140 }, { "epoch": 1.4631667171924319, "grad_norm": 4.818805694580078, "learning_rate": 8.911609596472244e-06, "loss": 0.3313, "step": 246150 }, { "epoch": 1.4632261592691003, "grad_norm": 5.486067771911621, "learning_rate": 8.91148035158701e-06, "loss": 0.3715, "step": 246160 }, { "epoch": 1.4632856013457687, "grad_norm": 5.650633335113525, "learning_rate": 8.911351099965738e-06, "loss": 0.4036, "step": 246170 }, { "epoch": 1.463345043422437, "grad_norm": 6.130836009979248, "learning_rate": 8.911221841608654e-06, "loss": 0.3368, "step": 246180 }, { "epoch": 1.4634044854991055, "grad_norm": 4.104104995727539, "learning_rate": 8.911092576515979e-06, "loss": 0.361, "step": 246190 }, { "epoch": 1.4634639275757737, "grad_norm": 3.627148151397705, "learning_rate": 8.910963304687936e-06, "loss": 0.3589, "step": 246200 }, { "epoch": 1.4635233696524421, "grad_norm": 5.209776878356934, "learning_rate": 8.910834026124748e-06, "loss": 0.3209, "step": 246210 }, { "epoch": 1.4635828117291105, "grad_norm": 5.266246318817139, "learning_rate": 8.910704740826637e-06, "loss": 0.3712, "step": 246220 }, { "epoch": 1.463642253805779, "grad_norm": 4.978879451751709, "learning_rate": 8.910575448793826e-06, "loss": 0.3493, "step": 246230 }, { "epoch": 1.4637016958824474, "grad_norm": 5.284839630126953, "learning_rate": 8.910446150026538e-06, "loss": 0.3768, "step": 246240 }, { "epoch": 1.4637611379591158, "grad_norm": 7.097965240478516, "learning_rate": 8.910316844524993e-06, "loss": 0.3996, "step": 246250 }, { "epoch": 1.4638205800357842, "grad_norm": 5.405487060546875, "learning_rate": 8.910187532289417e-06, "loss": 0.339, "step": 246260 }, { "epoch": 1.4638800221124524, "grad_norm": 4.371321678161621, "learning_rate": 8.910058213320031e-06, "loss": 0.3902, "step": 246270 }, { "epoch": 1.4639394641891208, "grad_norm": 5.829280853271484, "learning_rate": 8.909928887617058e-06, "loss": 0.3678, "step": 246280 }, { "epoch": 1.4639989062657892, "grad_norm": 5.887002468109131, "learning_rate": 8.909799555180723e-06, "loss": 0.3907, "step": 246290 }, { "epoch": 1.4640583483424576, "grad_norm": 4.81840705871582, "learning_rate": 8.909670216011245e-06, "loss": 0.3576, "step": 246300 }, { "epoch": 1.464117790419126, "grad_norm": 5.496401786804199, "learning_rate": 8.90954087010885e-06, "loss": 0.342, "step": 246310 }, { "epoch": 1.4641772324957945, "grad_norm": 5.928880214691162, "learning_rate": 8.909411517473757e-06, "loss": 0.38, "step": 246320 }, { "epoch": 1.4642366745724629, "grad_norm": 4.52390193939209, "learning_rate": 8.909282158106191e-06, "loss": 0.3559, "step": 246330 }, { "epoch": 1.4642961166491313, "grad_norm": 5.795870780944824, "learning_rate": 8.909152792006377e-06, "loss": 0.38, "step": 246340 }, { "epoch": 1.4643555587257997, "grad_norm": 5.36689567565918, "learning_rate": 8.909023419174534e-06, "loss": 0.387, "step": 246350 }, { "epoch": 1.4644150008024681, "grad_norm": 6.567811012268066, "learning_rate": 8.908894039610885e-06, "loss": 0.4355, "step": 246360 }, { "epoch": 1.4644744428791365, "grad_norm": 4.480808258056641, "learning_rate": 8.908764653315655e-06, "loss": 0.3495, "step": 246370 }, { "epoch": 1.464533884955805, "grad_norm": 3.788973569869995, "learning_rate": 8.908635260289066e-06, "loss": 0.3866, "step": 246380 }, { "epoch": 1.4645933270324731, "grad_norm": 3.89032244682312, "learning_rate": 8.908505860531342e-06, "loss": 0.3618, "step": 246390 }, { "epoch": 1.4646527691091416, "grad_norm": 4.317750453948975, "learning_rate": 8.908376454042704e-06, "loss": 0.3608, "step": 246400 }, { "epoch": 1.46471221118581, "grad_norm": 6.888152122497559, "learning_rate": 8.908247040823375e-06, "loss": 0.3395, "step": 246410 }, { "epoch": 1.4647716532624784, "grad_norm": 3.8577351570129395, "learning_rate": 8.908117620873578e-06, "loss": 0.3721, "step": 246420 }, { "epoch": 1.4648310953391468, "grad_norm": 3.8417391777038574, "learning_rate": 8.907988194193535e-06, "loss": 0.3919, "step": 246430 }, { "epoch": 1.4648905374158152, "grad_norm": 4.6268839836120605, "learning_rate": 8.907858760783472e-06, "loss": 0.3397, "step": 246440 }, { "epoch": 1.4649499794924836, "grad_norm": 5.1875176429748535, "learning_rate": 8.90772932064361e-06, "loss": 0.3871, "step": 246450 }, { "epoch": 1.4650094215691518, "grad_norm": 4.34052848815918, "learning_rate": 8.90759987377417e-06, "loss": 0.3529, "step": 246460 }, { "epoch": 1.4650688636458202, "grad_norm": 6.226837635040283, "learning_rate": 8.907470420175378e-06, "loss": 0.3936, "step": 246470 }, { "epoch": 1.4651283057224886, "grad_norm": 4.489241123199463, "learning_rate": 8.907340959847454e-06, "loss": 0.3436, "step": 246480 }, { "epoch": 1.465187747799157, "grad_norm": 5.272471904754639, "learning_rate": 8.907211492790626e-06, "loss": 0.3646, "step": 246490 }, { "epoch": 1.4652471898758255, "grad_norm": 4.665974140167236, "learning_rate": 8.907082019005111e-06, "loss": 0.3834, "step": 246500 }, { "epoch": 1.4653066319524939, "grad_norm": 3.7367265224456787, "learning_rate": 8.906952538491135e-06, "loss": 0.3766, "step": 246510 }, { "epoch": 1.4653660740291623, "grad_norm": 5.904439926147461, "learning_rate": 8.906823051248923e-06, "loss": 0.3467, "step": 246520 }, { "epoch": 1.4654255161058307, "grad_norm": 4.608538627624512, "learning_rate": 8.906693557278692e-06, "loss": 0.3318, "step": 246530 }, { "epoch": 1.4654849581824991, "grad_norm": 5.687463283538818, "learning_rate": 8.906564056580671e-06, "loss": 0.326, "step": 246540 }, { "epoch": 1.4655444002591675, "grad_norm": 3.926013231277466, "learning_rate": 8.906434549155078e-06, "loss": 0.3611, "step": 246550 }, { "epoch": 1.465603842335836, "grad_norm": 5.903465270996094, "learning_rate": 8.90630503500214e-06, "loss": 0.3867, "step": 246560 }, { "epoch": 1.4656632844125042, "grad_norm": 6.283835411071777, "learning_rate": 8.90617551412208e-06, "loss": 0.3444, "step": 246570 }, { "epoch": 1.4657227264891726, "grad_norm": 5.232810020446777, "learning_rate": 8.906045986515119e-06, "loss": 0.3359, "step": 246580 }, { "epoch": 1.465782168565841, "grad_norm": 5.700502872467041, "learning_rate": 8.90591645218148e-06, "loss": 0.3542, "step": 246590 }, { "epoch": 1.4658416106425094, "grad_norm": 4.501864910125732, "learning_rate": 8.905786911121388e-06, "loss": 0.379, "step": 246600 }, { "epoch": 1.4659010527191778, "grad_norm": 4.100266456604004, "learning_rate": 8.905657363335063e-06, "loss": 0.3891, "step": 246610 }, { "epoch": 1.4659604947958462, "grad_norm": 5.291355609893799, "learning_rate": 8.905527808822732e-06, "loss": 0.3964, "step": 246620 }, { "epoch": 1.4660199368725146, "grad_norm": 4.8591694831848145, "learning_rate": 8.905398247584614e-06, "loss": 0.3693, "step": 246630 }, { "epoch": 1.4660793789491828, "grad_norm": 4.907866477966309, "learning_rate": 8.905268679620936e-06, "loss": 0.3522, "step": 246640 }, { "epoch": 1.4661388210258512, "grad_norm": 5.009256362915039, "learning_rate": 8.90513910493192e-06, "loss": 0.3668, "step": 246650 }, { "epoch": 1.4661982631025197, "grad_norm": 5.286914348602295, "learning_rate": 8.905009523517786e-06, "loss": 0.3526, "step": 246660 }, { "epoch": 1.466257705179188, "grad_norm": 4.231805801391602, "learning_rate": 8.90487993537876e-06, "loss": 0.3693, "step": 246670 }, { "epoch": 1.4663171472558565, "grad_norm": 5.130094051361084, "learning_rate": 8.904750340515068e-06, "loss": 0.3595, "step": 246680 }, { "epoch": 1.466376589332525, "grad_norm": 4.668972492218018, "learning_rate": 8.904620738926926e-06, "loss": 0.3741, "step": 246690 }, { "epoch": 1.4664360314091933, "grad_norm": 6.890751838684082, "learning_rate": 8.904491130614564e-06, "loss": 0.4073, "step": 246700 }, { "epoch": 1.4664954734858617, "grad_norm": 5.016106605529785, "learning_rate": 8.9043615155782e-06, "loss": 0.3609, "step": 246710 }, { "epoch": 1.4665549155625301, "grad_norm": 5.050302982330322, "learning_rate": 8.90423189381806e-06, "loss": 0.3616, "step": 246720 }, { "epoch": 1.4666143576391986, "grad_norm": 4.709315776824951, "learning_rate": 8.904102265334369e-06, "loss": 0.3504, "step": 246730 }, { "epoch": 1.466673799715867, "grad_norm": 3.791165828704834, "learning_rate": 8.903972630127347e-06, "loss": 0.3573, "step": 246740 }, { "epoch": 1.4667332417925354, "grad_norm": 4.80330228805542, "learning_rate": 8.903842988197218e-06, "loss": 0.3775, "step": 246750 }, { "epoch": 1.4667926838692036, "grad_norm": 5.876664161682129, "learning_rate": 8.903713339544205e-06, "loss": 0.3748, "step": 246760 }, { "epoch": 1.466852125945872, "grad_norm": 5.916049957275391, "learning_rate": 8.903583684168533e-06, "loss": 0.3327, "step": 246770 }, { "epoch": 1.4669115680225404, "grad_norm": 6.371768474578857, "learning_rate": 8.903454022070424e-06, "loss": 0.371, "step": 246780 }, { "epoch": 1.4669710100992088, "grad_norm": 6.778852939605713, "learning_rate": 8.9033243532501e-06, "loss": 0.3616, "step": 246790 }, { "epoch": 1.4670304521758772, "grad_norm": 3.7086455821990967, "learning_rate": 8.903194677707786e-06, "loss": 0.3468, "step": 246800 }, { "epoch": 1.4670898942525457, "grad_norm": 6.864353656768799, "learning_rate": 8.903064995443707e-06, "loss": 0.4111, "step": 246810 }, { "epoch": 1.467149336329214, "grad_norm": 6.621394634246826, "learning_rate": 8.902935306458085e-06, "loss": 0.3635, "step": 246820 }, { "epoch": 1.4672087784058823, "grad_norm": 4.011720657348633, "learning_rate": 8.902805610751139e-06, "loss": 0.3629, "step": 246830 }, { "epoch": 1.4672682204825507, "grad_norm": 5.027769565582275, "learning_rate": 8.9026759083231e-06, "loss": 0.3795, "step": 246840 }, { "epoch": 1.467327662559219, "grad_norm": 3.8850796222686768, "learning_rate": 8.902546199174184e-06, "loss": 0.3648, "step": 246850 }, { "epoch": 1.4673871046358875, "grad_norm": 6.019469261169434, "learning_rate": 8.90241648330462e-06, "loss": 0.3862, "step": 246860 }, { "epoch": 1.467446546712556, "grad_norm": 5.209229946136475, "learning_rate": 8.90228676071463e-06, "loss": 0.3733, "step": 246870 }, { "epoch": 1.4675059887892243, "grad_norm": 4.886905670166016, "learning_rate": 8.902157031404433e-06, "loss": 0.3798, "step": 246880 }, { "epoch": 1.4675654308658928, "grad_norm": 5.792269229888916, "learning_rate": 8.902027295374257e-06, "loss": 0.3732, "step": 246890 }, { "epoch": 1.4676248729425612, "grad_norm": 5.523950099945068, "learning_rate": 8.901897552624328e-06, "loss": 0.3586, "step": 246900 }, { "epoch": 1.4676843150192296, "grad_norm": 5.502930164337158, "learning_rate": 8.901767803154862e-06, "loss": 0.3664, "step": 246910 }, { "epoch": 1.467743757095898, "grad_norm": 4.381716251373291, "learning_rate": 8.901638046966088e-06, "loss": 0.368, "step": 246920 }, { "epoch": 1.4678031991725664, "grad_norm": 9.2982177734375, "learning_rate": 8.901508284058226e-06, "loss": 0.4204, "step": 246930 }, { "epoch": 1.4678626412492346, "grad_norm": 4.819067478179932, "learning_rate": 8.901378514431504e-06, "loss": 0.3329, "step": 246940 }, { "epoch": 1.467922083325903, "grad_norm": 5.58229923248291, "learning_rate": 8.901248738086142e-06, "loss": 0.344, "step": 246950 }, { "epoch": 1.4679815254025714, "grad_norm": 5.873407363891602, "learning_rate": 8.901118955022363e-06, "loss": 0.3913, "step": 246960 }, { "epoch": 1.4680409674792398, "grad_norm": 4.901272296905518, "learning_rate": 8.900989165240392e-06, "loss": 0.3486, "step": 246970 }, { "epoch": 1.4681004095559083, "grad_norm": 6.784825801849365, "learning_rate": 8.900859368740451e-06, "loss": 0.3801, "step": 246980 }, { "epoch": 1.4681598516325767, "grad_norm": 6.000204563140869, "learning_rate": 8.900729565522767e-06, "loss": 0.3623, "step": 246990 }, { "epoch": 1.468219293709245, "grad_norm": 5.064528942108154, "learning_rate": 8.90059975558756e-06, "loss": 0.3483, "step": 247000 }, { "epoch": 1.4682787357859133, "grad_norm": 5.556774616241455, "learning_rate": 8.900469938935054e-06, "loss": 0.3841, "step": 247010 }, { "epoch": 1.4683381778625817, "grad_norm": 6.2586565017700195, "learning_rate": 8.900340115565475e-06, "loss": 0.4039, "step": 247020 }, { "epoch": 1.46839761993925, "grad_norm": 6.435431480407715, "learning_rate": 8.900210285479045e-06, "loss": 0.3489, "step": 247030 }, { "epoch": 1.4684570620159185, "grad_norm": 4.665806770324707, "learning_rate": 8.900080448675988e-06, "loss": 0.3415, "step": 247040 }, { "epoch": 1.468516504092587, "grad_norm": 5.941117763519287, "learning_rate": 8.899950605156526e-06, "loss": 0.3306, "step": 247050 }, { "epoch": 1.4685759461692554, "grad_norm": 4.934258460998535, "learning_rate": 8.899820754920883e-06, "loss": 0.3565, "step": 247060 }, { "epoch": 1.4686353882459238, "grad_norm": 5.389595985412598, "learning_rate": 8.899690897969284e-06, "loss": 0.3699, "step": 247070 }, { "epoch": 1.4686948303225922, "grad_norm": 5.522769451141357, "learning_rate": 8.899561034301953e-06, "loss": 0.3916, "step": 247080 }, { "epoch": 1.4687542723992606, "grad_norm": 4.371081829071045, "learning_rate": 8.89943116391911e-06, "loss": 0.3723, "step": 247090 }, { "epoch": 1.468813714475929, "grad_norm": 4.530514240264893, "learning_rate": 8.899301286820984e-06, "loss": 0.3468, "step": 247100 }, { "epoch": 1.4688731565525974, "grad_norm": 5.5088210105896, "learning_rate": 8.899171403007795e-06, "loss": 0.4064, "step": 247110 }, { "epoch": 1.4689325986292658, "grad_norm": 6.878532886505127, "learning_rate": 8.899041512479768e-06, "loss": 0.3567, "step": 247120 }, { "epoch": 1.468992040705934, "grad_norm": 5.491110324859619, "learning_rate": 8.898911615237125e-06, "loss": 0.367, "step": 247130 }, { "epoch": 1.4690514827826024, "grad_norm": 3.320619583129883, "learning_rate": 8.898781711280091e-06, "loss": 0.3676, "step": 247140 }, { "epoch": 1.4691109248592709, "grad_norm": 5.842501640319824, "learning_rate": 8.89865180060889e-06, "loss": 0.3333, "step": 247150 }, { "epoch": 1.4691703669359393, "grad_norm": 5.092345714569092, "learning_rate": 8.898521883223747e-06, "loss": 0.3635, "step": 247160 }, { "epoch": 1.4692298090126077, "grad_norm": 6.243788719177246, "learning_rate": 8.898391959124883e-06, "loss": 0.372, "step": 247170 }, { "epoch": 1.469289251089276, "grad_norm": 5.291684150695801, "learning_rate": 8.898262028312524e-06, "loss": 0.3401, "step": 247180 }, { "epoch": 1.4693486931659445, "grad_norm": 5.02920389175415, "learning_rate": 8.89813209078689e-06, "loss": 0.3715, "step": 247190 }, { "epoch": 1.4694081352426127, "grad_norm": 5.750710964202881, "learning_rate": 8.89800214654821e-06, "loss": 0.3853, "step": 247200 }, { "epoch": 1.4694675773192811, "grad_norm": 3.8550028800964355, "learning_rate": 8.897872195596704e-06, "loss": 0.3547, "step": 247210 }, { "epoch": 1.4695270193959495, "grad_norm": 4.692810535430908, "learning_rate": 8.897742237932598e-06, "loss": 0.3855, "step": 247220 }, { "epoch": 1.469586461472618, "grad_norm": 4.452895641326904, "learning_rate": 8.897612273556113e-06, "loss": 0.3406, "step": 247230 }, { "epoch": 1.4696459035492864, "grad_norm": 5.828473091125488, "learning_rate": 8.897482302467474e-06, "loss": 0.3306, "step": 247240 }, { "epoch": 1.4697053456259548, "grad_norm": 4.939067363739014, "learning_rate": 8.89735232466691e-06, "loss": 0.3495, "step": 247250 }, { "epoch": 1.4697647877026232, "grad_norm": 4.940457820892334, "learning_rate": 8.897222340154637e-06, "loss": 0.3549, "step": 247260 }, { "epoch": 1.4698242297792916, "grad_norm": 4.906582832336426, "learning_rate": 8.897092348930882e-06, "loss": 0.3478, "step": 247270 }, { "epoch": 1.46988367185596, "grad_norm": 4.175807476043701, "learning_rate": 8.89696235099587e-06, "loss": 0.3717, "step": 247280 }, { "epoch": 1.4699431139326284, "grad_norm": 5.059558391571045, "learning_rate": 8.896832346349822e-06, "loss": 0.3945, "step": 247290 }, { "epoch": 1.4700025560092969, "grad_norm": 5.741881847381592, "learning_rate": 8.896702334992967e-06, "loss": 0.3753, "step": 247300 }, { "epoch": 1.470061998085965, "grad_norm": 4.565145969390869, "learning_rate": 8.896572316925523e-06, "loss": 0.3801, "step": 247310 }, { "epoch": 1.4701214401626335, "grad_norm": 5.4268269538879395, "learning_rate": 8.896442292147716e-06, "loss": 0.3698, "step": 247320 }, { "epoch": 1.4701808822393019, "grad_norm": 6.292603015899658, "learning_rate": 8.896312260659772e-06, "loss": 0.3604, "step": 247330 }, { "epoch": 1.4702403243159703, "grad_norm": 6.4385504722595215, "learning_rate": 8.896182222461913e-06, "loss": 0.3579, "step": 247340 }, { "epoch": 1.4702997663926387, "grad_norm": 3.824312448501587, "learning_rate": 8.896052177554363e-06, "loss": 0.3901, "step": 247350 }, { "epoch": 1.4703592084693071, "grad_norm": 5.061266899108887, "learning_rate": 8.895922125937346e-06, "loss": 0.3296, "step": 247360 }, { "epoch": 1.4704186505459755, "grad_norm": 5.179562091827393, "learning_rate": 8.895792067611088e-06, "loss": 0.3411, "step": 247370 }, { "epoch": 1.4704780926226437, "grad_norm": 5.826656818389893, "learning_rate": 8.89566200257581e-06, "loss": 0.3587, "step": 247380 }, { "epoch": 1.4705375346993121, "grad_norm": 4.252946376800537, "learning_rate": 8.895531930831737e-06, "loss": 0.3103, "step": 247390 }, { "epoch": 1.4705969767759806, "grad_norm": 4.444239616394043, "learning_rate": 8.895401852379093e-06, "loss": 0.3581, "step": 247400 }, { "epoch": 1.470656418852649, "grad_norm": 6.600004196166992, "learning_rate": 8.895271767218103e-06, "loss": 0.3579, "step": 247410 }, { "epoch": 1.4707158609293174, "grad_norm": 4.767196178436279, "learning_rate": 8.89514167534899e-06, "loss": 0.3839, "step": 247420 }, { "epoch": 1.4707753030059858, "grad_norm": 5.075299263000488, "learning_rate": 8.89501157677198e-06, "loss": 0.405, "step": 247430 }, { "epoch": 1.4708347450826542, "grad_norm": 5.66847562789917, "learning_rate": 8.894881471487292e-06, "loss": 0.3881, "step": 247440 }, { "epoch": 1.4708941871593226, "grad_norm": 4.795198917388916, "learning_rate": 8.894751359495155e-06, "loss": 0.3657, "step": 247450 }, { "epoch": 1.470953629235991, "grad_norm": 5.162037372589111, "learning_rate": 8.89462124079579e-06, "loss": 0.351, "step": 247460 }, { "epoch": 1.4710130713126595, "grad_norm": 6.4058990478515625, "learning_rate": 8.894491115389426e-06, "loss": 0.4015, "step": 247470 }, { "epoch": 1.4710725133893279, "grad_norm": 5.819565773010254, "learning_rate": 8.89436098327628e-06, "loss": 0.3501, "step": 247480 }, { "epoch": 1.4711319554659963, "grad_norm": 3.9758729934692383, "learning_rate": 8.894230844456582e-06, "loss": 0.3585, "step": 247490 }, { "epoch": 1.4711913975426645, "grad_norm": 5.291857719421387, "learning_rate": 8.894100698930553e-06, "loss": 0.351, "step": 247500 }, { "epoch": 1.471250839619333, "grad_norm": 4.862692356109619, "learning_rate": 8.893970546698418e-06, "loss": 0.3189, "step": 247510 }, { "epoch": 1.4713102816960013, "grad_norm": 5.568894386291504, "learning_rate": 8.893840387760401e-06, "loss": 0.3906, "step": 247520 }, { "epoch": 1.4713697237726697, "grad_norm": 6.177195072174072, "learning_rate": 8.893710222116726e-06, "loss": 0.3375, "step": 247530 }, { "epoch": 1.4714291658493381, "grad_norm": 3.86666202545166, "learning_rate": 8.893580049767618e-06, "loss": 0.376, "step": 247540 }, { "epoch": 1.4714886079260066, "grad_norm": 4.9031662940979, "learning_rate": 8.893449870713303e-06, "loss": 0.3704, "step": 247550 }, { "epoch": 1.471548050002675, "grad_norm": 6.203137397766113, "learning_rate": 8.893319684953998e-06, "loss": 0.3973, "step": 247560 }, { "epoch": 1.4716074920793432, "grad_norm": 6.349907875061035, "learning_rate": 8.893189492489934e-06, "loss": 0.3906, "step": 247570 }, { "epoch": 1.4716669341560116, "grad_norm": 3.3715755939483643, "learning_rate": 8.893059293321334e-06, "loss": 0.3649, "step": 247580 }, { "epoch": 1.47172637623268, "grad_norm": 6.1457624435424805, "learning_rate": 8.89292908744842e-06, "loss": 0.4183, "step": 247590 }, { "epoch": 1.4717858183093484, "grad_norm": 4.705082416534424, "learning_rate": 8.892798874871419e-06, "loss": 0.371, "step": 247600 }, { "epoch": 1.4718452603860168, "grad_norm": 4.820365905761719, "learning_rate": 8.892668655590553e-06, "loss": 0.3428, "step": 247610 }, { "epoch": 1.4719047024626852, "grad_norm": 4.471480369567871, "learning_rate": 8.892538429606048e-06, "loss": 0.326, "step": 247620 }, { "epoch": 1.4719641445393536, "grad_norm": 5.641711235046387, "learning_rate": 8.892408196918125e-06, "loss": 0.3778, "step": 247630 }, { "epoch": 1.472023586616022, "grad_norm": 5.961860179901123, "learning_rate": 8.892277957527013e-06, "loss": 0.3583, "step": 247640 }, { "epoch": 1.4720830286926905, "grad_norm": 4.080749034881592, "learning_rate": 8.892147711432933e-06, "loss": 0.3549, "step": 247650 }, { "epoch": 1.472142470769359, "grad_norm": 4.183895111083984, "learning_rate": 8.89201745863611e-06, "loss": 0.3686, "step": 247660 }, { "epoch": 1.4722019128460273, "grad_norm": 6.067172527313232, "learning_rate": 8.89188719913677e-06, "loss": 0.3837, "step": 247670 }, { "epoch": 1.4722613549226955, "grad_norm": 5.631363391876221, "learning_rate": 8.891756932935134e-06, "loss": 0.3891, "step": 247680 }, { "epoch": 1.472320796999364, "grad_norm": 5.055768013000488, "learning_rate": 8.89162666003143e-06, "loss": 0.3331, "step": 247690 }, { "epoch": 1.4723802390760323, "grad_norm": 5.501468658447266, "learning_rate": 8.891496380425878e-06, "loss": 0.3461, "step": 247700 }, { "epoch": 1.4724396811527007, "grad_norm": 7.368775367736816, "learning_rate": 8.891366094118708e-06, "loss": 0.3737, "step": 247710 }, { "epoch": 1.4724991232293692, "grad_norm": 4.721928596496582, "learning_rate": 8.891235801110139e-06, "loss": 0.4019, "step": 247720 }, { "epoch": 1.4725585653060376, "grad_norm": 5.976146697998047, "learning_rate": 8.891105501400398e-06, "loss": 0.3884, "step": 247730 }, { "epoch": 1.472618007382706, "grad_norm": 5.533921241760254, "learning_rate": 8.89097519498971e-06, "loss": 0.3429, "step": 247740 }, { "epoch": 1.4726774494593742, "grad_norm": 4.574466705322266, "learning_rate": 8.890844881878297e-06, "loss": 0.3543, "step": 247750 }, { "epoch": 1.4727368915360426, "grad_norm": 5.736861228942871, "learning_rate": 8.890714562066387e-06, "loss": 0.3538, "step": 247760 }, { "epoch": 1.472796333612711, "grad_norm": 5.242705821990967, "learning_rate": 8.890584235554202e-06, "loss": 0.3536, "step": 247770 }, { "epoch": 1.4728557756893794, "grad_norm": 7.618374347686768, "learning_rate": 8.890453902341966e-06, "loss": 0.4169, "step": 247780 }, { "epoch": 1.4729152177660478, "grad_norm": 4.235716819763184, "learning_rate": 8.890323562429904e-06, "loss": 0.3318, "step": 247790 }, { "epoch": 1.4729746598427162, "grad_norm": 5.5997138023376465, "learning_rate": 8.89019321581824e-06, "loss": 0.3672, "step": 247800 }, { "epoch": 1.4730341019193847, "grad_norm": 4.150930404663086, "learning_rate": 8.8900628625072e-06, "loss": 0.357, "step": 247810 }, { "epoch": 1.473093543996053, "grad_norm": 4.504913806915283, "learning_rate": 8.889932502497007e-06, "loss": 0.371, "step": 247820 }, { "epoch": 1.4731529860727215, "grad_norm": 5.79854679107666, "learning_rate": 8.889802135787885e-06, "loss": 0.4087, "step": 247830 }, { "epoch": 1.47321242814939, "grad_norm": 4.773143768310547, "learning_rate": 8.889671762380062e-06, "loss": 0.3585, "step": 247840 }, { "epoch": 1.4732718702260583, "grad_norm": 6.6616106033325195, "learning_rate": 8.889541382273759e-06, "loss": 0.3678, "step": 247850 }, { "epoch": 1.4733313123027267, "grad_norm": 5.625021934509277, "learning_rate": 8.889410995469204e-06, "loss": 0.385, "step": 247860 }, { "epoch": 1.473390754379395, "grad_norm": 4.640432357788086, "learning_rate": 8.889280601966615e-06, "loss": 0.3778, "step": 247870 }, { "epoch": 1.4734501964560633, "grad_norm": 6.085733890533447, "learning_rate": 8.889150201766224e-06, "loss": 0.3425, "step": 247880 }, { "epoch": 1.4735096385327318, "grad_norm": 5.1595892906188965, "learning_rate": 8.88901979486825e-06, "loss": 0.3923, "step": 247890 }, { "epoch": 1.4735690806094002, "grad_norm": 6.233414649963379, "learning_rate": 8.888889381272922e-06, "loss": 0.3711, "step": 247900 }, { "epoch": 1.4736285226860686, "grad_norm": 3.913151264190674, "learning_rate": 8.888758960980462e-06, "loss": 0.3473, "step": 247910 }, { "epoch": 1.473687964762737, "grad_norm": 4.359255790710449, "learning_rate": 8.888628533991093e-06, "loss": 0.3765, "step": 247920 }, { "epoch": 1.4737474068394054, "grad_norm": 5.749810695648193, "learning_rate": 8.888498100305043e-06, "loss": 0.3867, "step": 247930 }, { "epoch": 1.4738068489160736, "grad_norm": 4.600471496582031, "learning_rate": 8.888367659922537e-06, "loss": 0.3479, "step": 247940 }, { "epoch": 1.473866290992742, "grad_norm": 5.470196723937988, "learning_rate": 8.888237212843796e-06, "loss": 0.3262, "step": 247950 }, { "epoch": 1.4739257330694104, "grad_norm": 6.330387592315674, "learning_rate": 8.888106759069047e-06, "loss": 0.3984, "step": 247960 }, { "epoch": 1.4739851751460789, "grad_norm": 4.804434299468994, "learning_rate": 8.887976298598512e-06, "loss": 0.3453, "step": 247970 }, { "epoch": 1.4740446172227473, "grad_norm": 5.159667015075684, "learning_rate": 8.887845831432423e-06, "loss": 0.3711, "step": 247980 }, { "epoch": 1.4741040592994157, "grad_norm": 4.189136028289795, "learning_rate": 8.887715357570995e-06, "loss": 0.3685, "step": 247990 }, { "epoch": 1.474163501376084, "grad_norm": 4.862663745880127, "learning_rate": 8.887584877014458e-06, "loss": 0.3351, "step": 248000 }, { "epoch": 1.4742229434527525, "grad_norm": 6.544410228729248, "learning_rate": 8.887454389763039e-06, "loss": 0.3389, "step": 248010 }, { "epoch": 1.474282385529421, "grad_norm": 6.668850421905518, "learning_rate": 8.887323895816958e-06, "loss": 0.3875, "step": 248020 }, { "epoch": 1.4743418276060893, "grad_norm": 4.280974388122559, "learning_rate": 8.88719339517644e-06, "loss": 0.3729, "step": 248030 }, { "epoch": 1.4744012696827578, "grad_norm": 5.192768573760986, "learning_rate": 8.887062887841713e-06, "loss": 0.3676, "step": 248040 }, { "epoch": 1.474460711759426, "grad_norm": 4.278002738952637, "learning_rate": 8.886932373813e-06, "loss": 0.3691, "step": 248050 }, { "epoch": 1.4745201538360944, "grad_norm": 6.167352199554443, "learning_rate": 8.886801853090522e-06, "loss": 0.3397, "step": 248060 }, { "epoch": 1.4745795959127628, "grad_norm": 5.611417770385742, "learning_rate": 8.886671325674512e-06, "loss": 0.3792, "step": 248070 }, { "epoch": 1.4746390379894312, "grad_norm": 5.478694915771484, "learning_rate": 8.886540791565188e-06, "loss": 0.3514, "step": 248080 }, { "epoch": 1.4746984800660996, "grad_norm": 4.621236324310303, "learning_rate": 8.886410250762778e-06, "loss": 0.3773, "step": 248090 }, { "epoch": 1.474757922142768, "grad_norm": 3.9241130352020264, "learning_rate": 8.886279703267505e-06, "loss": 0.3875, "step": 248100 }, { "epoch": 1.4748173642194364, "grad_norm": 5.836715221405029, "learning_rate": 8.886149149079595e-06, "loss": 0.3943, "step": 248110 }, { "epoch": 1.4748768062961046, "grad_norm": 3.91717529296875, "learning_rate": 8.886018588199272e-06, "loss": 0.3486, "step": 248120 }, { "epoch": 1.474936248372773, "grad_norm": 6.244385719299316, "learning_rate": 8.885888020626763e-06, "loss": 0.355, "step": 248130 }, { "epoch": 1.4749956904494415, "grad_norm": 6.905844211578369, "learning_rate": 8.885757446362288e-06, "loss": 0.3858, "step": 248140 }, { "epoch": 1.4750551325261099, "grad_norm": 4.674093246459961, "learning_rate": 8.885626865406079e-06, "loss": 0.3603, "step": 248150 }, { "epoch": 1.4751145746027783, "grad_norm": 4.604450702667236, "learning_rate": 8.885496277758354e-06, "loss": 0.3803, "step": 248160 }, { "epoch": 1.4751740166794467, "grad_norm": 4.662646770477295, "learning_rate": 8.885365683419342e-06, "loss": 0.4109, "step": 248170 }, { "epoch": 1.4752334587561151, "grad_norm": 5.971229553222656, "learning_rate": 8.885235082389267e-06, "loss": 0.3321, "step": 248180 }, { "epoch": 1.4752929008327835, "grad_norm": 4.317133903503418, "learning_rate": 8.885104474668353e-06, "loss": 0.3471, "step": 248190 }, { "epoch": 1.475352342909452, "grad_norm": 5.867225646972656, "learning_rate": 8.884973860256826e-06, "loss": 0.3584, "step": 248200 }, { "epoch": 1.4754117849861204, "grad_norm": 4.140484809875488, "learning_rate": 8.884843239154909e-06, "loss": 0.3558, "step": 248210 }, { "epoch": 1.4754712270627888, "grad_norm": 5.244411945343018, "learning_rate": 8.884712611362829e-06, "loss": 0.3437, "step": 248220 }, { "epoch": 1.4755306691394572, "grad_norm": 7.0060954093933105, "learning_rate": 8.88458197688081e-06, "loss": 0.3628, "step": 248230 }, { "epoch": 1.4755901112161254, "grad_norm": 4.202057361602783, "learning_rate": 8.88445133570908e-06, "loss": 0.3446, "step": 248240 }, { "epoch": 1.4756495532927938, "grad_norm": 5.792383193969727, "learning_rate": 8.884320687847859e-06, "loss": 0.36, "step": 248250 }, { "epoch": 1.4757089953694622, "grad_norm": 4.96207332611084, "learning_rate": 8.884190033297375e-06, "loss": 0.3438, "step": 248260 }, { "epoch": 1.4757684374461306, "grad_norm": 5.427502632141113, "learning_rate": 8.884059372057851e-06, "loss": 0.3853, "step": 248270 }, { "epoch": 1.475827879522799, "grad_norm": 4.574823379516602, "learning_rate": 8.883928704129515e-06, "loss": 0.3661, "step": 248280 }, { "epoch": 1.4758873215994674, "grad_norm": 5.349433898925781, "learning_rate": 8.88379802951259e-06, "loss": 0.3915, "step": 248290 }, { "epoch": 1.4759467636761359, "grad_norm": 4.261478900909424, "learning_rate": 8.8836673482073e-06, "loss": 0.378, "step": 248300 }, { "epoch": 1.476006205752804, "grad_norm": 4.58381986618042, "learning_rate": 8.883536660213873e-06, "loss": 0.3394, "step": 248310 }, { "epoch": 1.4760656478294725, "grad_norm": 4.8459272384643555, "learning_rate": 8.883405965532534e-06, "loss": 0.3479, "step": 248320 }, { "epoch": 1.4761250899061409, "grad_norm": 4.395446300506592, "learning_rate": 8.883275264163503e-06, "loss": 0.3532, "step": 248330 }, { "epoch": 1.4761845319828093, "grad_norm": 6.307663917541504, "learning_rate": 8.88314455610701e-06, "loss": 0.3669, "step": 248340 }, { "epoch": 1.4762439740594777, "grad_norm": 4.923311233520508, "learning_rate": 8.88301384136328e-06, "loss": 0.3587, "step": 248350 }, { "epoch": 1.4763034161361461, "grad_norm": 4.643148899078369, "learning_rate": 8.882883119932535e-06, "loss": 0.3759, "step": 248360 }, { "epoch": 1.4763628582128145, "grad_norm": 4.942432880401611, "learning_rate": 8.882752391815005e-06, "loss": 0.3821, "step": 248370 }, { "epoch": 1.476422300289483, "grad_norm": 5.106539249420166, "learning_rate": 8.882621657010908e-06, "loss": 0.3399, "step": 248380 }, { "epoch": 1.4764817423661514, "grad_norm": 4.448563098907471, "learning_rate": 8.882490915520477e-06, "loss": 0.3274, "step": 248390 }, { "epoch": 1.4765411844428198, "grad_norm": 4.997034072875977, "learning_rate": 8.88236016734393e-06, "loss": 0.388, "step": 248400 }, { "epoch": 1.4766006265194882, "grad_norm": 5.552271366119385, "learning_rate": 8.882229412481498e-06, "loss": 0.3643, "step": 248410 }, { "epoch": 1.4766600685961564, "grad_norm": 4.681993007659912, "learning_rate": 8.882098650933402e-06, "loss": 0.3697, "step": 248420 }, { "epoch": 1.4767195106728248, "grad_norm": 5.415643692016602, "learning_rate": 8.88196788269987e-06, "loss": 0.3721, "step": 248430 }, { "epoch": 1.4767789527494932, "grad_norm": 5.892323970794678, "learning_rate": 8.881837107781126e-06, "loss": 0.3436, "step": 248440 }, { "epoch": 1.4768383948261616, "grad_norm": 3.838914155960083, "learning_rate": 8.881706326177395e-06, "loss": 0.354, "step": 248450 }, { "epoch": 1.47689783690283, "grad_norm": 3.8038523197174072, "learning_rate": 8.881575537888903e-06, "loss": 0.4203, "step": 248460 }, { "epoch": 1.4769572789794985, "grad_norm": 3.5910112857818604, "learning_rate": 8.881444742915874e-06, "loss": 0.3326, "step": 248470 }, { "epoch": 1.4770167210561669, "grad_norm": 4.851748943328857, "learning_rate": 8.881313941258535e-06, "loss": 0.3368, "step": 248480 }, { "epoch": 1.477076163132835, "grad_norm": 6.970139026641846, "learning_rate": 8.88118313291711e-06, "loss": 0.3425, "step": 248490 }, { "epoch": 1.4771356052095035, "grad_norm": 4.613606929779053, "learning_rate": 8.881052317891825e-06, "loss": 0.348, "step": 248500 }, { "epoch": 1.477195047286172, "grad_norm": 5.512401103973389, "learning_rate": 8.880921496182904e-06, "loss": 0.3836, "step": 248510 }, { "epoch": 1.4772544893628403, "grad_norm": 4.179591178894043, "learning_rate": 8.880790667790573e-06, "loss": 0.3789, "step": 248520 }, { "epoch": 1.4773139314395087, "grad_norm": 5.294222354888916, "learning_rate": 8.880659832715057e-06, "loss": 0.3629, "step": 248530 }, { "epoch": 1.4773733735161771, "grad_norm": 4.082483291625977, "learning_rate": 8.880528990956583e-06, "loss": 0.3671, "step": 248540 }, { "epoch": 1.4774328155928456, "grad_norm": 4.598280906677246, "learning_rate": 8.880398142515375e-06, "loss": 0.3301, "step": 248550 }, { "epoch": 1.477492257669514, "grad_norm": 6.500400066375732, "learning_rate": 8.880267287391657e-06, "loss": 0.3522, "step": 248560 }, { "epoch": 1.4775516997461824, "grad_norm": 5.654680252075195, "learning_rate": 8.880136425585657e-06, "loss": 0.3408, "step": 248570 }, { "epoch": 1.4776111418228508, "grad_norm": 5.099513053894043, "learning_rate": 8.8800055570976e-06, "loss": 0.3185, "step": 248580 }, { "epoch": 1.4776705838995192, "grad_norm": 4.994621276855469, "learning_rate": 8.87987468192771e-06, "loss": 0.3713, "step": 248590 }, { "epoch": 1.4777300259761876, "grad_norm": 5.228333473205566, "learning_rate": 8.87974380007621e-06, "loss": 0.3554, "step": 248600 }, { "epoch": 1.4777894680528558, "grad_norm": 6.4610395431518555, "learning_rate": 8.879612911543332e-06, "loss": 0.3948, "step": 248610 }, { "epoch": 1.4778489101295242, "grad_norm": 7.784525394439697, "learning_rate": 8.879482016329295e-06, "loss": 0.3669, "step": 248620 }, { "epoch": 1.4779083522061927, "grad_norm": 6.498021125793457, "learning_rate": 8.879351114434328e-06, "loss": 0.3639, "step": 248630 }, { "epoch": 1.477967794282861, "grad_norm": 6.928443908691406, "learning_rate": 8.879220205858657e-06, "loss": 0.3914, "step": 248640 }, { "epoch": 1.4780272363595295, "grad_norm": 4.956545829772949, "learning_rate": 8.879089290602504e-06, "loss": 0.3533, "step": 248650 }, { "epoch": 1.478086678436198, "grad_norm": 4.212451457977295, "learning_rate": 8.878958368666097e-06, "loss": 0.3502, "step": 248660 }, { "epoch": 1.4781461205128663, "grad_norm": 4.225381374359131, "learning_rate": 8.87882744004966e-06, "loss": 0.367, "step": 248670 }, { "epoch": 1.4782055625895345, "grad_norm": 4.879597187042236, "learning_rate": 8.87869650475342e-06, "loss": 0.3583, "step": 248680 }, { "epoch": 1.478265004666203, "grad_norm": 5.7977681159973145, "learning_rate": 8.878565562777604e-06, "loss": 0.3835, "step": 248690 }, { "epoch": 1.4783244467428713, "grad_norm": 4.996944427490234, "learning_rate": 8.878434614122432e-06, "loss": 0.3406, "step": 248700 }, { "epoch": 1.4783838888195397, "grad_norm": 6.035228252410889, "learning_rate": 8.878303658788134e-06, "loss": 0.3351, "step": 248710 }, { "epoch": 1.4784433308962082, "grad_norm": 4.286381244659424, "learning_rate": 8.878172696774934e-06, "loss": 0.3807, "step": 248720 }, { "epoch": 1.4785027729728766, "grad_norm": 4.533377647399902, "learning_rate": 8.87804172808306e-06, "loss": 0.3718, "step": 248730 }, { "epoch": 1.478562215049545, "grad_norm": 5.183544635772705, "learning_rate": 8.877910752712733e-06, "loss": 0.3352, "step": 248740 }, { "epoch": 1.4786216571262134, "grad_norm": 4.264852046966553, "learning_rate": 8.877779770664181e-06, "loss": 0.3871, "step": 248750 }, { "epoch": 1.4786810992028818, "grad_norm": 5.406031608581543, "learning_rate": 8.877648781937631e-06, "loss": 0.3644, "step": 248760 }, { "epoch": 1.4787405412795502, "grad_norm": 6.524969577789307, "learning_rate": 8.877517786533308e-06, "loss": 0.3472, "step": 248770 }, { "epoch": 1.4787999833562187, "grad_norm": 4.983278274536133, "learning_rate": 8.877386784451433e-06, "loss": 0.3803, "step": 248780 }, { "epoch": 1.4788594254328868, "grad_norm": 6.2061309814453125, "learning_rate": 8.877255775692238e-06, "loss": 0.3657, "step": 248790 }, { "epoch": 1.4789188675095553, "grad_norm": 4.653939723968506, "learning_rate": 8.877124760255946e-06, "loss": 0.3734, "step": 248800 }, { "epoch": 1.4789783095862237, "grad_norm": 4.212536811828613, "learning_rate": 8.876993738142782e-06, "loss": 0.3616, "step": 248810 }, { "epoch": 1.479037751662892, "grad_norm": 5.634879112243652, "learning_rate": 8.876862709352972e-06, "loss": 0.3757, "step": 248820 }, { "epoch": 1.4790971937395605, "grad_norm": 4.43845272064209, "learning_rate": 8.876731673886742e-06, "loss": 0.3558, "step": 248830 }, { "epoch": 1.479156635816229, "grad_norm": 3.8776767253875732, "learning_rate": 8.876600631744318e-06, "loss": 0.3584, "step": 248840 }, { "epoch": 1.4792160778928973, "grad_norm": 5.240277290344238, "learning_rate": 8.876469582925924e-06, "loss": 0.329, "step": 248850 }, { "epoch": 1.4792755199695655, "grad_norm": 5.5105438232421875, "learning_rate": 8.876338527431787e-06, "loss": 0.3679, "step": 248860 }, { "epoch": 1.479334962046234, "grad_norm": 5.515544891357422, "learning_rate": 8.876207465262134e-06, "loss": 0.3718, "step": 248870 }, { "epoch": 1.4793944041229024, "grad_norm": 6.358967304229736, "learning_rate": 8.876076396417188e-06, "loss": 0.367, "step": 248880 }, { "epoch": 1.4794538461995708, "grad_norm": 5.066736221313477, "learning_rate": 8.875945320897177e-06, "loss": 0.3591, "step": 248890 }, { "epoch": 1.4795132882762392, "grad_norm": 4.878321647644043, "learning_rate": 8.875814238702323e-06, "loss": 0.3097, "step": 248900 }, { "epoch": 1.4795727303529076, "grad_norm": 6.65852689743042, "learning_rate": 8.875683149832856e-06, "loss": 0.3295, "step": 248910 }, { "epoch": 1.479632172429576, "grad_norm": 5.547812461853027, "learning_rate": 8.875552054289004e-06, "loss": 0.3472, "step": 248920 }, { "epoch": 1.4796916145062444, "grad_norm": 5.243201732635498, "learning_rate": 8.875420952070983e-06, "loss": 0.3872, "step": 248930 }, { "epoch": 1.4797510565829128, "grad_norm": 5.15591287612915, "learning_rate": 8.875289843179026e-06, "loss": 0.326, "step": 248940 }, { "epoch": 1.4798104986595813, "grad_norm": 4.1790242195129395, "learning_rate": 8.87515872761336e-06, "loss": 0.3838, "step": 248950 }, { "epoch": 1.4798699407362497, "grad_norm": 4.3990020751953125, "learning_rate": 8.875027605374206e-06, "loss": 0.3859, "step": 248960 }, { "epoch": 1.479929382812918, "grad_norm": 5.010986328125, "learning_rate": 8.874896476461794e-06, "loss": 0.3588, "step": 248970 }, { "epoch": 1.4799888248895863, "grad_norm": 4.574150562286377, "learning_rate": 8.874765340876347e-06, "loss": 0.3824, "step": 248980 }, { "epoch": 1.4800482669662547, "grad_norm": 4.957248687744141, "learning_rate": 8.874634198618092e-06, "loss": 0.385, "step": 248990 }, { "epoch": 1.480107709042923, "grad_norm": 5.129744529724121, "learning_rate": 8.874503049687254e-06, "loss": 0.3513, "step": 249000 }, { "epoch": 1.4801671511195915, "grad_norm": 5.953532695770264, "learning_rate": 8.874371894084059e-06, "loss": 0.3536, "step": 249010 }, { "epoch": 1.48022659319626, "grad_norm": 6.52327823638916, "learning_rate": 8.874240731808734e-06, "loss": 0.393, "step": 249020 }, { "epoch": 1.4802860352729283, "grad_norm": 4.4401068687438965, "learning_rate": 8.874109562861506e-06, "loss": 0.3666, "step": 249030 }, { "epoch": 1.4803454773495968, "grad_norm": 5.565300941467285, "learning_rate": 8.873978387242596e-06, "loss": 0.3899, "step": 249040 }, { "epoch": 1.480404919426265, "grad_norm": 4.347588062286377, "learning_rate": 8.873847204952235e-06, "loss": 0.329, "step": 249050 }, { "epoch": 1.4804643615029334, "grad_norm": 5.019649982452393, "learning_rate": 8.873716015990647e-06, "loss": 0.3265, "step": 249060 }, { "epoch": 1.4805238035796018, "grad_norm": 5.569045066833496, "learning_rate": 8.873584820358057e-06, "loss": 0.3553, "step": 249070 }, { "epoch": 1.4805832456562702, "grad_norm": 4.871891975402832, "learning_rate": 8.873453618054692e-06, "loss": 0.3504, "step": 249080 }, { "epoch": 1.4806426877329386, "grad_norm": 5.641314506530762, "learning_rate": 8.873322409080776e-06, "loss": 0.3606, "step": 249090 }, { "epoch": 1.480702129809607, "grad_norm": 4.862854957580566, "learning_rate": 8.873191193436538e-06, "loss": 0.3547, "step": 249100 }, { "epoch": 1.4807615718862754, "grad_norm": 5.074965953826904, "learning_rate": 8.873059971122204e-06, "loss": 0.3901, "step": 249110 }, { "epoch": 1.4808210139629439, "grad_norm": 4.01747465133667, "learning_rate": 8.872928742137997e-06, "loss": 0.3522, "step": 249120 }, { "epoch": 1.4808804560396123, "grad_norm": 6.652047157287598, "learning_rate": 8.872797506484145e-06, "loss": 0.3631, "step": 249130 }, { "epoch": 1.4809398981162807, "grad_norm": 5.002446174621582, "learning_rate": 8.872666264160875e-06, "loss": 0.3461, "step": 249140 }, { "epoch": 1.480999340192949, "grad_norm": 5.587029933929443, "learning_rate": 8.87253501516841e-06, "loss": 0.3816, "step": 249150 }, { "epoch": 1.4810587822696173, "grad_norm": 5.298887729644775, "learning_rate": 8.872403759506978e-06, "loss": 0.3683, "step": 249160 }, { "epoch": 1.4811182243462857, "grad_norm": 5.12549352645874, "learning_rate": 8.872272497176803e-06, "loss": 0.3775, "step": 249170 }, { "epoch": 1.4811776664229541, "grad_norm": 4.898989200592041, "learning_rate": 8.872141228178114e-06, "loss": 0.3632, "step": 249180 }, { "epoch": 1.4812371084996225, "grad_norm": 5.239275932312012, "learning_rate": 8.872009952511137e-06, "loss": 0.346, "step": 249190 }, { "epoch": 1.481296550576291, "grad_norm": 6.378735065460205, "learning_rate": 8.871878670176095e-06, "loss": 0.3723, "step": 249200 }, { "epoch": 1.4813559926529594, "grad_norm": 4.8697614669799805, "learning_rate": 8.871747381173217e-06, "loss": 0.386, "step": 249210 }, { "epoch": 1.4814154347296278, "grad_norm": 6.605130672454834, "learning_rate": 8.871616085502728e-06, "loss": 0.3894, "step": 249220 }, { "epoch": 1.481474876806296, "grad_norm": 6.242714881896973, "learning_rate": 8.871484783164855e-06, "loss": 0.3612, "step": 249230 }, { "epoch": 1.4815343188829644, "grad_norm": 6.252852916717529, "learning_rate": 8.871353474159822e-06, "loss": 0.3671, "step": 249240 }, { "epoch": 1.4815937609596328, "grad_norm": 5.868643760681152, "learning_rate": 8.871222158487856e-06, "loss": 0.3632, "step": 249250 }, { "epoch": 1.4816532030363012, "grad_norm": 4.461031913757324, "learning_rate": 8.871090836149185e-06, "loss": 0.3467, "step": 249260 }, { "epoch": 1.4817126451129696, "grad_norm": 5.355073928833008, "learning_rate": 8.870959507144033e-06, "loss": 0.349, "step": 249270 }, { "epoch": 1.481772087189638, "grad_norm": 5.098484039306641, "learning_rate": 8.870828171472628e-06, "loss": 0.3502, "step": 249280 }, { "epoch": 1.4818315292663065, "grad_norm": 6.050840377807617, "learning_rate": 8.870696829135192e-06, "loss": 0.3225, "step": 249290 }, { "epoch": 1.4818909713429749, "grad_norm": 4.684101104736328, "learning_rate": 8.870565480131956e-06, "loss": 0.3845, "step": 249300 }, { "epoch": 1.4819504134196433, "grad_norm": 3.623314619064331, "learning_rate": 8.870434124463145e-06, "loss": 0.3259, "step": 249310 }, { "epoch": 1.4820098554963117, "grad_norm": 4.9419684410095215, "learning_rate": 8.870302762128985e-06, "loss": 0.3642, "step": 249320 }, { "epoch": 1.4820692975729801, "grad_norm": 5.092264175415039, "learning_rate": 8.8701713931297e-06, "loss": 0.3549, "step": 249330 }, { "epoch": 1.4821287396496485, "grad_norm": 4.960381984710693, "learning_rate": 8.870040017465519e-06, "loss": 0.3536, "step": 249340 }, { "epoch": 1.4821881817263167, "grad_norm": 3.837581157684326, "learning_rate": 8.869908635136668e-06, "loss": 0.3236, "step": 249350 }, { "epoch": 1.4822476238029851, "grad_norm": 5.831647872924805, "learning_rate": 8.869777246143371e-06, "loss": 0.3761, "step": 249360 }, { "epoch": 1.4823070658796536, "grad_norm": 5.894590854644775, "learning_rate": 8.869645850485857e-06, "loss": 0.3492, "step": 249370 }, { "epoch": 1.482366507956322, "grad_norm": 5.587060928344727, "learning_rate": 8.869514448164352e-06, "loss": 0.3491, "step": 249380 }, { "epoch": 1.4824259500329904, "grad_norm": 4.1772027015686035, "learning_rate": 8.869383039179079e-06, "loss": 0.3631, "step": 249390 }, { "epoch": 1.4824853921096588, "grad_norm": 5.093135356903076, "learning_rate": 8.86925162353027e-06, "loss": 0.3687, "step": 249400 }, { "epoch": 1.4825448341863272, "grad_norm": 3.518756866455078, "learning_rate": 8.869120201218144e-06, "loss": 0.3135, "step": 249410 }, { "epoch": 1.4826042762629954, "grad_norm": 5.1100873947143555, "learning_rate": 8.868988772242933e-06, "loss": 0.333, "step": 249420 }, { "epoch": 1.4826637183396638, "grad_norm": 5.191009521484375, "learning_rate": 8.868857336604862e-06, "loss": 0.3504, "step": 249430 }, { "epoch": 1.4827231604163322, "grad_norm": 5.598674297332764, "learning_rate": 8.868725894304157e-06, "loss": 0.3543, "step": 249440 }, { "epoch": 1.4827826024930006, "grad_norm": 4.991488456726074, "learning_rate": 8.868594445341045e-06, "loss": 0.3426, "step": 249450 }, { "epoch": 1.482842044569669, "grad_norm": 4.755275249481201, "learning_rate": 8.868462989715752e-06, "loss": 0.3685, "step": 249460 }, { "epoch": 1.4829014866463375, "grad_norm": 3.4808225631713867, "learning_rate": 8.868331527428503e-06, "loss": 0.3507, "step": 249470 }, { "epoch": 1.4829609287230059, "grad_norm": 4.33701753616333, "learning_rate": 8.868200058479527e-06, "loss": 0.3609, "step": 249480 }, { "epoch": 1.4830203707996743, "grad_norm": 6.437906265258789, "learning_rate": 8.868068582869048e-06, "loss": 0.3911, "step": 249490 }, { "epoch": 1.4830798128763427, "grad_norm": 4.922593116760254, "learning_rate": 8.867937100597292e-06, "loss": 0.3175, "step": 249500 }, { "epoch": 1.4831392549530111, "grad_norm": 4.544683933258057, "learning_rate": 8.867805611664489e-06, "loss": 0.3386, "step": 249510 }, { "epoch": 1.4831986970296795, "grad_norm": 5.829313278198242, "learning_rate": 8.867674116070861e-06, "loss": 0.3375, "step": 249520 }, { "epoch": 1.4832581391063477, "grad_norm": 5.024085521697998, "learning_rate": 8.86754261381664e-06, "loss": 0.3491, "step": 249530 }, { "epoch": 1.4833175811830162, "grad_norm": 3.8461899757385254, "learning_rate": 8.867411104902047e-06, "loss": 0.3901, "step": 249540 }, { "epoch": 1.4833770232596846, "grad_norm": 6.049745559692383, "learning_rate": 8.86727958932731e-06, "loss": 0.3544, "step": 249550 }, { "epoch": 1.483436465336353, "grad_norm": 5.363459587097168, "learning_rate": 8.867148067092656e-06, "loss": 0.3808, "step": 249560 }, { "epoch": 1.4834959074130214, "grad_norm": 4.0367021560668945, "learning_rate": 8.867016538198315e-06, "loss": 0.3474, "step": 249570 }, { "epoch": 1.4835553494896898, "grad_norm": 6.1394147872924805, "learning_rate": 8.866885002644507e-06, "loss": 0.3589, "step": 249580 }, { "epoch": 1.4836147915663582, "grad_norm": 5.467527866363525, "learning_rate": 8.866753460431461e-06, "loss": 0.3977, "step": 249590 }, { "epoch": 1.4836742336430264, "grad_norm": 5.442974090576172, "learning_rate": 8.866621911559405e-06, "loss": 0.3643, "step": 249600 }, { "epoch": 1.4837336757196948, "grad_norm": 4.795630931854248, "learning_rate": 8.866490356028566e-06, "loss": 0.3234, "step": 249610 }, { "epoch": 1.4837931177963632, "grad_norm": 4.633798122406006, "learning_rate": 8.866358793839169e-06, "loss": 0.3707, "step": 249620 }, { "epoch": 1.4838525598730317, "grad_norm": 4.030547142028809, "learning_rate": 8.86622722499144e-06, "loss": 0.3638, "step": 249630 }, { "epoch": 1.4839120019497, "grad_norm": 5.010873794555664, "learning_rate": 8.866095649485607e-06, "loss": 0.4359, "step": 249640 }, { "epoch": 1.4839714440263685, "grad_norm": 5.488147258758545, "learning_rate": 8.865964067321895e-06, "loss": 0.3589, "step": 249650 }, { "epoch": 1.484030886103037, "grad_norm": 7.119475841522217, "learning_rate": 8.865832478500533e-06, "loss": 0.388, "step": 249660 }, { "epoch": 1.4840903281797053, "grad_norm": 6.407166481018066, "learning_rate": 8.865700883021745e-06, "loss": 0.3686, "step": 249670 }, { "epoch": 1.4841497702563737, "grad_norm": 4.249390602111816, "learning_rate": 8.86556928088576e-06, "loss": 0.3702, "step": 249680 }, { "epoch": 1.4842092123330421, "grad_norm": 6.783030986785889, "learning_rate": 8.865437672092803e-06, "loss": 0.4052, "step": 249690 }, { "epoch": 1.4842686544097106, "grad_norm": 4.389271259307861, "learning_rate": 8.8653060566431e-06, "loss": 0.3476, "step": 249700 }, { "epoch": 1.484328096486379, "grad_norm": 4.619025707244873, "learning_rate": 8.865174434536879e-06, "loss": 0.3754, "step": 249710 }, { "epoch": 1.4843875385630472, "grad_norm": 4.842109203338623, "learning_rate": 8.865042805774368e-06, "loss": 0.3336, "step": 249720 }, { "epoch": 1.4844469806397156, "grad_norm": 3.868896961212158, "learning_rate": 8.86491117035579e-06, "loss": 0.3454, "step": 249730 }, { "epoch": 1.484506422716384, "grad_norm": 5.342020511627197, "learning_rate": 8.864779528281376e-06, "loss": 0.3693, "step": 249740 }, { "epoch": 1.4845658647930524, "grad_norm": 5.773416519165039, "learning_rate": 8.864647879551349e-06, "loss": 0.4071, "step": 249750 }, { "epoch": 1.4846253068697208, "grad_norm": 4.152219295501709, "learning_rate": 8.864516224165938e-06, "loss": 0.3642, "step": 249760 }, { "epoch": 1.4846847489463892, "grad_norm": 4.9547576904296875, "learning_rate": 8.86438456212537e-06, "loss": 0.3495, "step": 249770 }, { "epoch": 1.4847441910230577, "grad_norm": 4.705438137054443, "learning_rate": 8.864252893429868e-06, "loss": 0.3651, "step": 249780 }, { "epoch": 1.4848036330997259, "grad_norm": 4.254247188568115, "learning_rate": 8.864121218079664e-06, "loss": 0.3509, "step": 249790 }, { "epoch": 1.4848630751763943, "grad_norm": 4.9010748863220215, "learning_rate": 8.86398953607498e-06, "loss": 0.3687, "step": 249800 }, { "epoch": 1.4849225172530627, "grad_norm": 6.532114028930664, "learning_rate": 8.863857847416046e-06, "loss": 0.3658, "step": 249810 }, { "epoch": 1.484981959329731, "grad_norm": 4.802618026733398, "learning_rate": 8.863726152103088e-06, "loss": 0.3302, "step": 249820 }, { "epoch": 1.4850414014063995, "grad_norm": 5.738353252410889, "learning_rate": 8.863594450136332e-06, "loss": 0.3632, "step": 249830 }, { "epoch": 1.485100843483068, "grad_norm": 5.458709716796875, "learning_rate": 8.863462741516007e-06, "loss": 0.3561, "step": 249840 }, { "epoch": 1.4851602855597363, "grad_norm": 4.674106597900391, "learning_rate": 8.863331026242336e-06, "loss": 0.3998, "step": 249850 }, { "epoch": 1.4852197276364048, "grad_norm": 5.688077926635742, "learning_rate": 8.863199304315549e-06, "loss": 0.3837, "step": 249860 }, { "epoch": 1.4852791697130732, "grad_norm": 6.33889102935791, "learning_rate": 8.863067575735871e-06, "loss": 0.3401, "step": 249870 }, { "epoch": 1.4853386117897416, "grad_norm": 4.867642879486084, "learning_rate": 8.862935840503531e-06, "loss": 0.3543, "step": 249880 }, { "epoch": 1.48539805386641, "grad_norm": 5.477051258087158, "learning_rate": 8.862804098618754e-06, "loss": 0.3407, "step": 249890 }, { "epoch": 1.4854574959430782, "grad_norm": 4.672529220581055, "learning_rate": 8.862672350081767e-06, "loss": 0.3353, "step": 249900 }, { "epoch": 1.4855169380197466, "grad_norm": 4.586544513702393, "learning_rate": 8.862540594892799e-06, "loss": 0.3625, "step": 249910 }, { "epoch": 1.485576380096415, "grad_norm": 10.556395530700684, "learning_rate": 8.862408833052074e-06, "loss": 0.3476, "step": 249920 }, { "epoch": 1.4856358221730834, "grad_norm": 5.718367576599121, "learning_rate": 8.86227706455982e-06, "loss": 0.3585, "step": 249930 }, { "epoch": 1.4856952642497518, "grad_norm": 4.739795207977295, "learning_rate": 8.862145289416265e-06, "loss": 0.3384, "step": 249940 }, { "epoch": 1.4857547063264203, "grad_norm": 4.544895648956299, "learning_rate": 8.862013507621632e-06, "loss": 0.3484, "step": 249950 }, { "epoch": 1.4858141484030887, "grad_norm": 5.605616569519043, "learning_rate": 8.861881719176155e-06, "loss": 0.3776, "step": 249960 }, { "epoch": 1.4858735904797569, "grad_norm": 4.41739559173584, "learning_rate": 8.861749924080054e-06, "loss": 0.3422, "step": 249970 }, { "epoch": 1.4859330325564253, "grad_norm": 5.145942687988281, "learning_rate": 8.86161812233356e-06, "loss": 0.3747, "step": 249980 }, { "epoch": 1.4859924746330937, "grad_norm": 6.190276622772217, "learning_rate": 8.861486313936898e-06, "loss": 0.3503, "step": 249990 }, { "epoch": 1.486051916709762, "grad_norm": 4.121457576751709, "learning_rate": 8.861354498890297e-06, "loss": 0.3727, "step": 250000 }, { "epoch": 1.4861113587864305, "grad_norm": 5.1621809005737305, "learning_rate": 8.861222677193982e-06, "loss": 0.3775, "step": 250010 }, { "epoch": 1.486170800863099, "grad_norm": 4.226367950439453, "learning_rate": 8.861090848848181e-06, "loss": 0.3332, "step": 250020 }, { "epoch": 1.4862302429397674, "grad_norm": 7.837626934051514, "learning_rate": 8.860959013853122e-06, "loss": 0.3736, "step": 250030 }, { "epoch": 1.4862896850164358, "grad_norm": 4.831070899963379, "learning_rate": 8.86082717220903e-06, "loss": 0.3227, "step": 250040 }, { "epoch": 1.4863491270931042, "grad_norm": 5.203779697418213, "learning_rate": 8.860695323916134e-06, "loss": 0.3621, "step": 250050 }, { "epoch": 1.4864085691697726, "grad_norm": 5.241329669952393, "learning_rate": 8.860563468974658e-06, "loss": 0.3976, "step": 250060 }, { "epoch": 1.486468011246441, "grad_norm": 5.968685626983643, "learning_rate": 8.860431607384832e-06, "loss": 0.3595, "step": 250070 }, { "epoch": 1.4865274533231094, "grad_norm": 5.260402202606201, "learning_rate": 8.860299739146882e-06, "loss": 0.365, "step": 250080 }, { "epoch": 1.4865868953997776, "grad_norm": 4.648761749267578, "learning_rate": 8.860167864261035e-06, "loss": 0.3538, "step": 250090 }, { "epoch": 1.486646337476446, "grad_norm": 4.4214653968811035, "learning_rate": 8.86003598272752e-06, "loss": 0.3961, "step": 250100 }, { "epoch": 1.4867057795531144, "grad_norm": 4.904012680053711, "learning_rate": 8.85990409454656e-06, "loss": 0.3982, "step": 250110 }, { "epoch": 1.4867652216297829, "grad_norm": 5.691779136657715, "learning_rate": 8.859772199718386e-06, "loss": 0.3725, "step": 250120 }, { "epoch": 1.4868246637064513, "grad_norm": 5.105457305908203, "learning_rate": 8.859640298243223e-06, "loss": 0.3433, "step": 250130 }, { "epoch": 1.4868841057831197, "grad_norm": 5.867372989654541, "learning_rate": 8.859508390121299e-06, "loss": 0.3977, "step": 250140 }, { "epoch": 1.486943547859788, "grad_norm": 4.293753623962402, "learning_rate": 8.859376475352841e-06, "loss": 0.3432, "step": 250150 }, { "epoch": 1.4870029899364563, "grad_norm": 6.745965957641602, "learning_rate": 8.859244553938077e-06, "loss": 0.3695, "step": 250160 }, { "epoch": 1.4870624320131247, "grad_norm": 4.695953369140625, "learning_rate": 8.859112625877233e-06, "loss": 0.3497, "step": 250170 }, { "epoch": 1.4871218740897931, "grad_norm": 5.149327278137207, "learning_rate": 8.858980691170538e-06, "loss": 0.3904, "step": 250180 }, { "epoch": 1.4871813161664615, "grad_norm": 3.2391154766082764, "learning_rate": 8.858848749818216e-06, "loss": 0.3624, "step": 250190 }, { "epoch": 1.48724075824313, "grad_norm": 6.085865020751953, "learning_rate": 8.858716801820498e-06, "loss": 0.3803, "step": 250200 }, { "epoch": 1.4873002003197984, "grad_norm": 4.3385233879089355, "learning_rate": 8.858584847177607e-06, "loss": 0.384, "step": 250210 }, { "epoch": 1.4873596423964668, "grad_norm": 4.9473490715026855, "learning_rate": 8.858452885889773e-06, "loss": 0.42, "step": 250220 }, { "epoch": 1.4874190844731352, "grad_norm": 5.194122314453125, "learning_rate": 8.85832091795722e-06, "loss": 0.381, "step": 250230 }, { "epoch": 1.4874785265498036, "grad_norm": 4.680936813354492, "learning_rate": 8.858188943380184e-06, "loss": 0.3215, "step": 250240 }, { "epoch": 1.487537968626472, "grad_norm": 6.075861930847168, "learning_rate": 8.858056962158883e-06, "loss": 0.3885, "step": 250250 }, { "epoch": 1.4875974107031404, "grad_norm": 5.488952159881592, "learning_rate": 8.857924974293548e-06, "loss": 0.3218, "step": 250260 }, { "epoch": 1.4876568527798086, "grad_norm": 4.862621784210205, "learning_rate": 8.857792979784406e-06, "loss": 0.3496, "step": 250270 }, { "epoch": 1.487716294856477, "grad_norm": 5.681468963623047, "learning_rate": 8.857660978631683e-06, "loss": 0.3737, "step": 250280 }, { "epoch": 1.4877757369331455, "grad_norm": 7.191110134124756, "learning_rate": 8.857528970835607e-06, "loss": 0.386, "step": 250290 }, { "epoch": 1.4878351790098139, "grad_norm": 4.212114334106445, "learning_rate": 8.857396956396409e-06, "loss": 0.344, "step": 250300 }, { "epoch": 1.4878946210864823, "grad_norm": 4.6295084953308105, "learning_rate": 8.857264935314311e-06, "loss": 0.3198, "step": 250310 }, { "epoch": 1.4879540631631507, "grad_norm": 5.456733226776123, "learning_rate": 8.857132907589543e-06, "loss": 0.3444, "step": 250320 }, { "epoch": 1.4880135052398191, "grad_norm": 6.17533540725708, "learning_rate": 8.857000873222332e-06, "loss": 0.3726, "step": 250330 }, { "epoch": 1.4880729473164873, "grad_norm": 4.596384048461914, "learning_rate": 8.856868832212905e-06, "loss": 0.3415, "step": 250340 }, { "epoch": 1.4881323893931557, "grad_norm": 4.379834175109863, "learning_rate": 8.856736784561489e-06, "loss": 0.3475, "step": 250350 }, { "epoch": 1.4881918314698241, "grad_norm": 4.6874260902404785, "learning_rate": 8.856604730268314e-06, "loss": 0.4081, "step": 250360 }, { "epoch": 1.4882512735464926, "grad_norm": 5.527770519256592, "learning_rate": 8.856472669333604e-06, "loss": 0.3813, "step": 250370 }, { "epoch": 1.488310715623161, "grad_norm": 4.653624534606934, "learning_rate": 8.856340601757588e-06, "loss": 0.3635, "step": 250380 }, { "epoch": 1.4883701576998294, "grad_norm": 5.026575565338135, "learning_rate": 8.856208527540494e-06, "loss": 0.3571, "step": 250390 }, { "epoch": 1.4884295997764978, "grad_norm": 5.201361656188965, "learning_rate": 8.85607644668255e-06, "loss": 0.32, "step": 250400 }, { "epoch": 1.4884890418531662, "grad_norm": 4.187312126159668, "learning_rate": 8.855944359183979e-06, "loss": 0.3499, "step": 250410 }, { "epoch": 1.4885484839298346, "grad_norm": 4.8422932624816895, "learning_rate": 8.855812265045014e-06, "loss": 0.3431, "step": 250420 }, { "epoch": 1.488607926006503, "grad_norm": 4.66121768951416, "learning_rate": 8.855680164265878e-06, "loss": 0.346, "step": 250430 }, { "epoch": 1.4886673680831715, "grad_norm": 6.156506061553955, "learning_rate": 8.855548056846803e-06, "loss": 0.3615, "step": 250440 }, { "epoch": 1.4887268101598399, "grad_norm": 5.158383369445801, "learning_rate": 8.855415942788015e-06, "loss": 0.3418, "step": 250450 }, { "epoch": 1.488786252236508, "grad_norm": 4.868465900421143, "learning_rate": 8.855283822089738e-06, "loss": 0.3622, "step": 250460 }, { "epoch": 1.4888456943131765, "grad_norm": 4.962652683258057, "learning_rate": 8.855151694752204e-06, "loss": 0.3403, "step": 250470 }, { "epoch": 1.488905136389845, "grad_norm": 5.200438976287842, "learning_rate": 8.855019560775638e-06, "loss": 0.323, "step": 250480 }, { "epoch": 1.4889645784665133, "grad_norm": 5.108071804046631, "learning_rate": 8.85488742016027e-06, "loss": 0.3734, "step": 250490 }, { "epoch": 1.4890240205431817, "grad_norm": 4.733513355255127, "learning_rate": 8.854755272906323e-06, "loss": 0.3435, "step": 250500 }, { "epoch": 1.4890834626198501, "grad_norm": 5.161498069763184, "learning_rate": 8.854623119014029e-06, "loss": 0.336, "step": 250510 }, { "epoch": 1.4891429046965186, "grad_norm": 4.407047271728516, "learning_rate": 8.854490958483615e-06, "loss": 0.3919, "step": 250520 }, { "epoch": 1.4892023467731867, "grad_norm": 5.531271934509277, "learning_rate": 8.854358791315308e-06, "loss": 0.3416, "step": 250530 }, { "epoch": 1.4892617888498552, "grad_norm": 5.355897426605225, "learning_rate": 8.854226617509333e-06, "loss": 0.3134, "step": 250540 }, { "epoch": 1.4893212309265236, "grad_norm": 4.488295555114746, "learning_rate": 8.854094437065922e-06, "loss": 0.3378, "step": 250550 }, { "epoch": 1.489380673003192, "grad_norm": 5.740710735321045, "learning_rate": 8.8539622499853e-06, "loss": 0.3464, "step": 250560 }, { "epoch": 1.4894401150798604, "grad_norm": 6.910279750823975, "learning_rate": 8.853830056267692e-06, "loss": 0.4034, "step": 250570 }, { "epoch": 1.4894995571565288, "grad_norm": 4.941052436828613, "learning_rate": 8.853697855913332e-06, "loss": 0.358, "step": 250580 }, { "epoch": 1.4895589992331972, "grad_norm": 6.369339466094971, "learning_rate": 8.853565648922444e-06, "loss": 0.3671, "step": 250590 }, { "epoch": 1.4896184413098656, "grad_norm": 6.593032360076904, "learning_rate": 8.853433435295255e-06, "loss": 0.336, "step": 250600 }, { "epoch": 1.489677883386534, "grad_norm": 5.046792984008789, "learning_rate": 8.853301215031997e-06, "loss": 0.3735, "step": 250610 }, { "epoch": 1.4897373254632025, "grad_norm": 7.143319129943848, "learning_rate": 8.853168988132893e-06, "loss": 0.3852, "step": 250620 }, { "epoch": 1.489796767539871, "grad_norm": 3.482050895690918, "learning_rate": 8.85303675459817e-06, "loss": 0.3296, "step": 250630 }, { "epoch": 1.489856209616539, "grad_norm": 4.832408428192139, "learning_rate": 8.85290451442806e-06, "loss": 0.3781, "step": 250640 }, { "epoch": 1.4899156516932075, "grad_norm": 6.075974941253662, "learning_rate": 8.852772267622788e-06, "loss": 0.3631, "step": 250650 }, { "epoch": 1.489975093769876, "grad_norm": 4.931996822357178, "learning_rate": 8.852640014182582e-06, "loss": 0.39, "step": 250660 }, { "epoch": 1.4900345358465443, "grad_norm": 4.736235618591309, "learning_rate": 8.852507754107673e-06, "loss": 0.3247, "step": 250670 }, { "epoch": 1.4900939779232127, "grad_norm": 6.662118434906006, "learning_rate": 8.852375487398284e-06, "loss": 0.3697, "step": 250680 }, { "epoch": 1.4901534199998812, "grad_norm": 6.62415885925293, "learning_rate": 8.852243214054644e-06, "loss": 0.3505, "step": 250690 }, { "epoch": 1.4902128620765496, "grad_norm": 5.348306179046631, "learning_rate": 8.852110934076982e-06, "loss": 0.3963, "step": 250700 }, { "epoch": 1.4902723041532178, "grad_norm": 6.206231117248535, "learning_rate": 8.851978647465526e-06, "loss": 0.3962, "step": 250710 }, { "epoch": 1.4903317462298862, "grad_norm": 3.611971139907837, "learning_rate": 8.851846354220503e-06, "loss": 0.3302, "step": 250720 }, { "epoch": 1.4903911883065546, "grad_norm": 5.561914443969727, "learning_rate": 8.85171405434214e-06, "loss": 0.3805, "step": 250730 }, { "epoch": 1.490450630383223, "grad_norm": 4.013886451721191, "learning_rate": 8.851581747830666e-06, "loss": 0.3552, "step": 250740 }, { "epoch": 1.4905100724598914, "grad_norm": 5.872219562530518, "learning_rate": 8.85144943468631e-06, "loss": 0.3858, "step": 250750 }, { "epoch": 1.4905695145365598, "grad_norm": 5.578961372375488, "learning_rate": 8.851317114909299e-06, "loss": 0.3438, "step": 250760 }, { "epoch": 1.4906289566132283, "grad_norm": 4.903227806091309, "learning_rate": 8.851184788499857e-06, "loss": 0.3784, "step": 250770 }, { "epoch": 1.4906883986898967, "grad_norm": 3.8670921325683594, "learning_rate": 8.85105245545822e-06, "loss": 0.347, "step": 250780 }, { "epoch": 1.490747840766565, "grad_norm": 5.290073871612549, "learning_rate": 8.850920115784606e-06, "loss": 0.3661, "step": 250790 }, { "epoch": 1.4908072828432335, "grad_norm": 5.738582611083984, "learning_rate": 8.850787769479252e-06, "loss": 0.3625, "step": 250800 }, { "epoch": 1.490866724919902, "grad_norm": 5.5762481689453125, "learning_rate": 8.850655416542382e-06, "loss": 0.3888, "step": 250810 }, { "epoch": 1.4909261669965703, "grad_norm": 6.109391212463379, "learning_rate": 8.850523056974222e-06, "loss": 0.3808, "step": 250820 }, { "epoch": 1.4909856090732385, "grad_norm": 5.068085670471191, "learning_rate": 8.850390690775001e-06, "loss": 0.3766, "step": 250830 }, { "epoch": 1.491045051149907, "grad_norm": 4.9304399490356445, "learning_rate": 8.850258317944951e-06, "loss": 0.3437, "step": 250840 }, { "epoch": 1.4911044932265753, "grad_norm": 4.540465354919434, "learning_rate": 8.850125938484295e-06, "loss": 0.3795, "step": 250850 }, { "epoch": 1.4911639353032438, "grad_norm": 3.6317641735076904, "learning_rate": 8.849993552393262e-06, "loss": 0.3186, "step": 250860 }, { "epoch": 1.4912233773799122, "grad_norm": 5.568088531494141, "learning_rate": 8.849861159672082e-06, "loss": 0.3967, "step": 250870 }, { "epoch": 1.4912828194565806, "grad_norm": 3.932868480682373, "learning_rate": 8.849728760320981e-06, "loss": 0.3663, "step": 250880 }, { "epoch": 1.491342261533249, "grad_norm": 5.250442981719971, "learning_rate": 8.849596354340189e-06, "loss": 0.3567, "step": 250890 }, { "epoch": 1.4914017036099172, "grad_norm": 6.085320472717285, "learning_rate": 8.84946394172993e-06, "loss": 0.4045, "step": 250900 }, { "epoch": 1.4914611456865856, "grad_norm": 5.158551216125488, "learning_rate": 8.849331522490437e-06, "loss": 0.39, "step": 250910 }, { "epoch": 1.491520587763254, "grad_norm": 7.1781768798828125, "learning_rate": 8.849199096621937e-06, "loss": 0.3683, "step": 250920 }, { "epoch": 1.4915800298399224, "grad_norm": 4.312541484832764, "learning_rate": 8.849066664124654e-06, "loss": 0.3528, "step": 250930 }, { "epoch": 1.4916394719165909, "grad_norm": 3.668724298477173, "learning_rate": 8.84893422499882e-06, "loss": 0.3608, "step": 250940 }, { "epoch": 1.4916989139932593, "grad_norm": 5.714381217956543, "learning_rate": 8.848801779244662e-06, "loss": 0.354, "step": 250950 }, { "epoch": 1.4917583560699277, "grad_norm": 4.114759922027588, "learning_rate": 8.848669326862409e-06, "loss": 0.3307, "step": 250960 }, { "epoch": 1.491817798146596, "grad_norm": 6.745090961456299, "learning_rate": 8.848536867852287e-06, "loss": 0.3779, "step": 250970 }, { "epoch": 1.4918772402232645, "grad_norm": 5.052472114562988, "learning_rate": 8.848404402214526e-06, "loss": 0.3563, "step": 250980 }, { "epoch": 1.491936682299933, "grad_norm": 3.974151849746704, "learning_rate": 8.848271929949352e-06, "loss": 0.3367, "step": 250990 }, { "epoch": 1.4919961243766013, "grad_norm": 3.943453311920166, "learning_rate": 8.848139451056997e-06, "loss": 0.3303, "step": 251000 }, { "epoch": 1.4920555664532695, "grad_norm": 5.377516746520996, "learning_rate": 8.848006965537685e-06, "loss": 0.3949, "step": 251010 }, { "epoch": 1.492115008529938, "grad_norm": 4.588129043579102, "learning_rate": 8.847874473391647e-06, "loss": 0.3456, "step": 251020 }, { "epoch": 1.4921744506066064, "grad_norm": 4.460446834564209, "learning_rate": 8.84774197461911e-06, "loss": 0.3493, "step": 251030 }, { "epoch": 1.4922338926832748, "grad_norm": 5.62357234954834, "learning_rate": 8.847609469220302e-06, "loss": 0.3505, "step": 251040 }, { "epoch": 1.4922933347599432, "grad_norm": 4.476423263549805, "learning_rate": 8.84747695719545e-06, "loss": 0.3402, "step": 251050 }, { "epoch": 1.4923527768366116, "grad_norm": 8.036930084228516, "learning_rate": 8.847344438544784e-06, "loss": 0.3975, "step": 251060 }, { "epoch": 1.49241221891328, "grad_norm": 4.505929470062256, "learning_rate": 8.847211913268534e-06, "loss": 0.3598, "step": 251070 }, { "epoch": 1.4924716609899482, "grad_norm": 4.162320137023926, "learning_rate": 8.847079381366923e-06, "loss": 0.3375, "step": 251080 }, { "epoch": 1.4925311030666166, "grad_norm": 4.922820091247559, "learning_rate": 8.846946842840186e-06, "loss": 0.3924, "step": 251090 }, { "epoch": 1.492590545143285, "grad_norm": 4.542243480682373, "learning_rate": 8.846814297688545e-06, "loss": 0.3606, "step": 251100 }, { "epoch": 1.4926499872199535, "grad_norm": 6.109029293060303, "learning_rate": 8.84668174591223e-06, "loss": 0.42, "step": 251110 }, { "epoch": 1.4927094292966219, "grad_norm": 5.191373348236084, "learning_rate": 8.846549187511471e-06, "loss": 0.3215, "step": 251120 }, { "epoch": 1.4927688713732903, "grad_norm": 4.79059362411499, "learning_rate": 8.846416622486496e-06, "loss": 0.3299, "step": 251130 }, { "epoch": 1.4928283134499587, "grad_norm": 5.427631378173828, "learning_rate": 8.846284050837533e-06, "loss": 0.3576, "step": 251140 }, { "epoch": 1.4928877555266271, "grad_norm": 4.756258964538574, "learning_rate": 8.846151472564809e-06, "loss": 0.3861, "step": 251150 }, { "epoch": 1.4929471976032955, "grad_norm": 5.473341464996338, "learning_rate": 8.846018887668552e-06, "loss": 0.3661, "step": 251160 }, { "epoch": 1.493006639679964, "grad_norm": 4.961182594299316, "learning_rate": 8.845886296148993e-06, "loss": 0.3733, "step": 251170 }, { "epoch": 1.4930660817566324, "grad_norm": 4.194660186767578, "learning_rate": 8.845753698006359e-06, "loss": 0.3591, "step": 251180 }, { "epoch": 1.4931255238333008, "grad_norm": 3.4933362007141113, "learning_rate": 8.84562109324088e-06, "loss": 0.3456, "step": 251190 }, { "epoch": 1.493184965909969, "grad_norm": 4.910672664642334, "learning_rate": 8.845488481852779e-06, "loss": 0.3711, "step": 251200 }, { "epoch": 1.4932444079866374, "grad_norm": 4.113356590270996, "learning_rate": 8.84535586384229e-06, "loss": 0.3647, "step": 251210 }, { "epoch": 1.4933038500633058, "grad_norm": 5.81821870803833, "learning_rate": 8.845223239209639e-06, "loss": 0.3529, "step": 251220 }, { "epoch": 1.4933632921399742, "grad_norm": 5.01251220703125, "learning_rate": 8.845090607955054e-06, "loss": 0.378, "step": 251230 }, { "epoch": 1.4934227342166426, "grad_norm": 5.2506279945373535, "learning_rate": 8.844957970078765e-06, "loss": 0.401, "step": 251240 }, { "epoch": 1.493482176293311, "grad_norm": 5.763344764709473, "learning_rate": 8.844825325581e-06, "loss": 0.3476, "step": 251250 }, { "epoch": 1.4935416183699795, "grad_norm": 6.155869007110596, "learning_rate": 8.844692674461987e-06, "loss": 0.3735, "step": 251260 }, { "epoch": 1.4936010604466476, "grad_norm": 5.628325462341309, "learning_rate": 8.844560016721954e-06, "loss": 0.3673, "step": 251270 }, { "epoch": 1.493660502523316, "grad_norm": 5.550623893737793, "learning_rate": 8.84442735236113e-06, "loss": 0.3781, "step": 251280 }, { "epoch": 1.4937199445999845, "grad_norm": 5.271868705749512, "learning_rate": 8.844294681379743e-06, "loss": 0.3091, "step": 251290 }, { "epoch": 1.4937793866766529, "grad_norm": 4.37211275100708, "learning_rate": 8.844162003778023e-06, "loss": 0.3657, "step": 251300 }, { "epoch": 1.4938388287533213, "grad_norm": 4.056360244750977, "learning_rate": 8.844029319556196e-06, "loss": 0.3709, "step": 251310 }, { "epoch": 1.4938982708299897, "grad_norm": 5.93163537979126, "learning_rate": 8.843896628714494e-06, "loss": 0.333, "step": 251320 }, { "epoch": 1.4939577129066581, "grad_norm": 4.472984313964844, "learning_rate": 8.84376393125314e-06, "loss": 0.3536, "step": 251330 }, { "epoch": 1.4940171549833265, "grad_norm": 5.283675670623779, "learning_rate": 8.843631227172369e-06, "loss": 0.3748, "step": 251340 }, { "epoch": 1.494076597059995, "grad_norm": 4.7462286949157715, "learning_rate": 8.843498516472406e-06, "loss": 0.3686, "step": 251350 }, { "epoch": 1.4941360391366634, "grad_norm": 5.810953140258789, "learning_rate": 8.843365799153478e-06, "loss": 0.3709, "step": 251360 }, { "epoch": 1.4941954812133318, "grad_norm": 3.217768430709839, "learning_rate": 8.843233075215816e-06, "loss": 0.3379, "step": 251370 }, { "epoch": 1.49425492329, "grad_norm": 6.213286399841309, "learning_rate": 8.84310034465965e-06, "loss": 0.353, "step": 251380 }, { "epoch": 1.4943143653666684, "grad_norm": 4.954405307769775, "learning_rate": 8.842967607485204e-06, "loss": 0.3509, "step": 251390 }, { "epoch": 1.4943738074433368, "grad_norm": 5.396091461181641, "learning_rate": 8.842834863692712e-06, "loss": 0.36, "step": 251400 }, { "epoch": 1.4944332495200052, "grad_norm": 4.794474124908447, "learning_rate": 8.842702113282398e-06, "loss": 0.3619, "step": 251410 }, { "epoch": 1.4944926915966736, "grad_norm": 5.7010698318481445, "learning_rate": 8.842569356254493e-06, "loss": 0.3162, "step": 251420 }, { "epoch": 1.494552133673342, "grad_norm": 5.71540641784668, "learning_rate": 8.842436592609224e-06, "loss": 0.3468, "step": 251430 }, { "epoch": 1.4946115757500105, "grad_norm": 4.363979816436768, "learning_rate": 8.842303822346822e-06, "loss": 0.3636, "step": 251440 }, { "epoch": 1.4946710178266787, "grad_norm": 5.454238414764404, "learning_rate": 8.842171045467514e-06, "loss": 0.3274, "step": 251450 }, { "epoch": 1.494730459903347, "grad_norm": 5.7122721672058105, "learning_rate": 8.84203826197153e-06, "loss": 0.3884, "step": 251460 }, { "epoch": 1.4947899019800155, "grad_norm": 3.874677896499634, "learning_rate": 8.841905471859096e-06, "loss": 0.3494, "step": 251470 }, { "epoch": 1.494849344056684, "grad_norm": 4.917586326599121, "learning_rate": 8.841772675130444e-06, "loss": 0.3818, "step": 251480 }, { "epoch": 1.4949087861333523, "grad_norm": 5.933521270751953, "learning_rate": 8.8416398717858e-06, "loss": 0.3878, "step": 251490 }, { "epoch": 1.4949682282100207, "grad_norm": 4.749464511871338, "learning_rate": 8.841507061825395e-06, "loss": 0.3404, "step": 251500 }, { "epoch": 1.4950276702866891, "grad_norm": 4.188602447509766, "learning_rate": 8.841374245249454e-06, "loss": 0.3701, "step": 251510 }, { "epoch": 1.4950871123633576, "grad_norm": 5.446201801300049, "learning_rate": 8.841241422058211e-06, "loss": 0.3896, "step": 251520 }, { "epoch": 1.495146554440026, "grad_norm": 5.829193115234375, "learning_rate": 8.84110859225189e-06, "loss": 0.3673, "step": 251530 }, { "epoch": 1.4952059965166944, "grad_norm": 5.9611005783081055, "learning_rate": 8.840975755830722e-06, "loss": 0.3699, "step": 251540 }, { "epoch": 1.4952654385933628, "grad_norm": 3.9906721115112305, "learning_rate": 8.840842912794935e-06, "loss": 0.3734, "step": 251550 }, { "epoch": 1.4953248806700312, "grad_norm": 6.052330017089844, "learning_rate": 8.84071006314476e-06, "loss": 0.3421, "step": 251560 }, { "epoch": 1.4953843227466994, "grad_norm": 4.4577860832214355, "learning_rate": 8.840577206880423e-06, "loss": 0.3546, "step": 251570 }, { "epoch": 1.4954437648233678, "grad_norm": 5.08726692199707, "learning_rate": 8.840444344002155e-06, "loss": 0.3654, "step": 251580 }, { "epoch": 1.4955032069000362, "grad_norm": 4.6256585121154785, "learning_rate": 8.840311474510182e-06, "loss": 0.3376, "step": 251590 }, { "epoch": 1.4955626489767047, "grad_norm": 6.273210525512695, "learning_rate": 8.840178598404734e-06, "loss": 0.3676, "step": 251600 }, { "epoch": 1.495622091053373, "grad_norm": 4.6710357666015625, "learning_rate": 8.840045715686042e-06, "loss": 0.3498, "step": 251610 }, { "epoch": 1.4956815331300415, "grad_norm": 5.005459785461426, "learning_rate": 8.839912826354331e-06, "loss": 0.3651, "step": 251620 }, { "epoch": 1.49574097520671, "grad_norm": 4.250631809234619, "learning_rate": 8.839779930409833e-06, "loss": 0.3998, "step": 251630 }, { "epoch": 1.495800417283378, "grad_norm": 5.379429817199707, "learning_rate": 8.839647027852775e-06, "loss": 0.371, "step": 251640 }, { "epoch": 1.4958598593600465, "grad_norm": 5.546351432800293, "learning_rate": 8.839514118683387e-06, "loss": 0.3596, "step": 251650 }, { "epoch": 1.495919301436715, "grad_norm": 4.487044811248779, "learning_rate": 8.8393812029019e-06, "loss": 0.3521, "step": 251660 }, { "epoch": 1.4959787435133833, "grad_norm": 4.2283148765563965, "learning_rate": 8.839248280508538e-06, "loss": 0.3771, "step": 251670 }, { "epoch": 1.4960381855900518, "grad_norm": 5.215083122253418, "learning_rate": 8.839115351503534e-06, "loss": 0.3717, "step": 251680 }, { "epoch": 1.4960976276667202, "grad_norm": 5.394628047943115, "learning_rate": 8.838982415887114e-06, "loss": 0.3754, "step": 251690 }, { "epoch": 1.4961570697433886, "grad_norm": 6.119748592376709, "learning_rate": 8.838849473659508e-06, "loss": 0.3772, "step": 251700 }, { "epoch": 1.496216511820057, "grad_norm": 7.65753698348999, "learning_rate": 8.838716524820946e-06, "loss": 0.4065, "step": 251710 }, { "epoch": 1.4962759538967254, "grad_norm": 5.93230676651001, "learning_rate": 8.838583569371655e-06, "loss": 0.37, "step": 251720 }, { "epoch": 1.4963353959733938, "grad_norm": 5.3114166259765625, "learning_rate": 8.838450607311866e-06, "loss": 0.3765, "step": 251730 }, { "epoch": 1.4963948380500622, "grad_norm": 4.659787178039551, "learning_rate": 8.838317638641807e-06, "loss": 0.3478, "step": 251740 }, { "epoch": 1.4964542801267304, "grad_norm": 6.04848575592041, "learning_rate": 8.838184663361707e-06, "loss": 0.3277, "step": 251750 }, { "epoch": 1.4965137222033988, "grad_norm": 7.219409465789795, "learning_rate": 8.838051681471796e-06, "loss": 0.3359, "step": 251760 }, { "epoch": 1.4965731642800673, "grad_norm": 4.754420757293701, "learning_rate": 8.8379186929723e-06, "loss": 0.3763, "step": 251770 }, { "epoch": 1.4966326063567357, "grad_norm": 5.556006908416748, "learning_rate": 8.837785697863451e-06, "loss": 0.3469, "step": 251780 }, { "epoch": 1.496692048433404, "grad_norm": 4.877128601074219, "learning_rate": 8.837652696145478e-06, "loss": 0.3622, "step": 251790 }, { "epoch": 1.4967514905100725, "grad_norm": 6.005046844482422, "learning_rate": 8.837519687818607e-06, "loss": 0.376, "step": 251800 }, { "epoch": 1.496810932586741, "grad_norm": 4.442829608917236, "learning_rate": 8.837386672883071e-06, "loss": 0.3607, "step": 251810 }, { "epoch": 1.496870374663409, "grad_norm": 4.034066677093506, "learning_rate": 8.837253651339098e-06, "loss": 0.3768, "step": 251820 }, { "epoch": 1.4969298167400775, "grad_norm": 5.566182613372803, "learning_rate": 8.837120623186915e-06, "loss": 0.3389, "step": 251830 }, { "epoch": 1.496989258816746, "grad_norm": 6.559616565704346, "learning_rate": 8.836987588426753e-06, "loss": 0.3593, "step": 251840 }, { "epoch": 1.4970487008934144, "grad_norm": 5.024402141571045, "learning_rate": 8.83685454705884e-06, "loss": 0.3368, "step": 251850 }, { "epoch": 1.4971081429700828, "grad_norm": 5.1288862228393555, "learning_rate": 8.836721499083405e-06, "loss": 0.3489, "step": 251860 }, { "epoch": 1.4971675850467512, "grad_norm": 4.789349555969238, "learning_rate": 8.83658844450068e-06, "loss": 0.3746, "step": 251870 }, { "epoch": 1.4972270271234196, "grad_norm": 5.926638126373291, "learning_rate": 8.836455383310889e-06, "loss": 0.3237, "step": 251880 }, { "epoch": 1.497286469200088, "grad_norm": 5.19882869720459, "learning_rate": 8.836322315514268e-06, "loss": 0.3472, "step": 251890 }, { "epoch": 1.4973459112767564, "grad_norm": 4.483888626098633, "learning_rate": 8.836189241111039e-06, "loss": 0.3545, "step": 251900 }, { "epoch": 1.4974053533534248, "grad_norm": 4.3507490158081055, "learning_rate": 8.836056160101436e-06, "loss": 0.3535, "step": 251910 }, { "epoch": 1.4974647954300933, "grad_norm": 6.217637062072754, "learning_rate": 8.835923072485686e-06, "loss": 0.4043, "step": 251920 }, { "epoch": 1.4975242375067617, "grad_norm": 4.466973781585693, "learning_rate": 8.835789978264019e-06, "loss": 0.3399, "step": 251930 }, { "epoch": 1.4975836795834299, "grad_norm": 5.287928581237793, "learning_rate": 8.835656877436662e-06, "loss": 0.3431, "step": 251940 }, { "epoch": 1.4976431216600983, "grad_norm": 4.7062249183654785, "learning_rate": 8.835523770003849e-06, "loss": 0.3535, "step": 251950 }, { "epoch": 1.4977025637367667, "grad_norm": 6.900053024291992, "learning_rate": 8.835390655965804e-06, "loss": 0.3536, "step": 251960 }, { "epoch": 1.497762005813435, "grad_norm": 4.3367204666137695, "learning_rate": 8.83525753532276e-06, "loss": 0.3351, "step": 251970 }, { "epoch": 1.4978214478901035, "grad_norm": 5.934792995452881, "learning_rate": 8.835124408074945e-06, "loss": 0.3722, "step": 251980 }, { "epoch": 1.497880889966772, "grad_norm": 5.9875078201293945, "learning_rate": 8.834991274222588e-06, "loss": 0.3347, "step": 251990 }, { "epoch": 1.4979403320434403, "grad_norm": 5.542037487030029, "learning_rate": 8.834858133765917e-06, "loss": 0.3823, "step": 252000 }, { "epoch": 1.4979997741201085, "grad_norm": 7.1922526359558105, "learning_rate": 8.834724986705166e-06, "loss": 0.3877, "step": 252010 }, { "epoch": 1.498059216196777, "grad_norm": 4.985219478607178, "learning_rate": 8.834591833040558e-06, "loss": 0.3615, "step": 252020 }, { "epoch": 1.4981186582734454, "grad_norm": 4.221568584442139, "learning_rate": 8.834458672772327e-06, "loss": 0.3443, "step": 252030 }, { "epoch": 1.4981781003501138, "grad_norm": 4.377115726470947, "learning_rate": 8.8343255059007e-06, "loss": 0.3694, "step": 252040 }, { "epoch": 1.4982375424267822, "grad_norm": 4.33611536026001, "learning_rate": 8.834192332425907e-06, "loss": 0.3679, "step": 252050 }, { "epoch": 1.4982969845034506, "grad_norm": 5.410574436187744, "learning_rate": 8.834059152348178e-06, "loss": 0.3393, "step": 252060 }, { "epoch": 1.498356426580119, "grad_norm": 5.1465349197387695, "learning_rate": 8.833925965667742e-06, "loss": 0.3522, "step": 252070 }, { "epoch": 1.4984158686567874, "grad_norm": 4.211056709289551, "learning_rate": 8.833792772384826e-06, "loss": 0.3768, "step": 252080 }, { "epoch": 1.4984753107334559, "grad_norm": 5.470165252685547, "learning_rate": 8.833659572499661e-06, "loss": 0.386, "step": 252090 }, { "epoch": 1.4985347528101243, "grad_norm": 4.972594738006592, "learning_rate": 8.83352636601248e-06, "loss": 0.3495, "step": 252100 }, { "epoch": 1.4985941948867927, "grad_norm": 5.535538196563721, "learning_rate": 8.833393152923508e-06, "loss": 0.3758, "step": 252110 }, { "epoch": 1.4986536369634609, "grad_norm": 4.53737211227417, "learning_rate": 8.833259933232975e-06, "loss": 0.3551, "step": 252120 }, { "epoch": 1.4987130790401293, "grad_norm": 4.901724815368652, "learning_rate": 8.83312670694111e-06, "loss": 0.3771, "step": 252130 }, { "epoch": 1.4987725211167977, "grad_norm": 5.418988227844238, "learning_rate": 8.832993474048146e-06, "loss": 0.384, "step": 252140 }, { "epoch": 1.4988319631934661, "grad_norm": 5.680058002471924, "learning_rate": 8.832860234554308e-06, "loss": 0.3637, "step": 252150 }, { "epoch": 1.4988914052701345, "grad_norm": 4.586326599121094, "learning_rate": 8.832726988459828e-06, "loss": 0.334, "step": 252160 }, { "epoch": 1.498950847346803, "grad_norm": 4.874438285827637, "learning_rate": 8.832593735764934e-06, "loss": 0.3279, "step": 252170 }, { "epoch": 1.4990102894234714, "grad_norm": 5.60910177230835, "learning_rate": 8.832460476469858e-06, "loss": 0.3685, "step": 252180 }, { "epoch": 1.4990697315001396, "grad_norm": 4.8321123123168945, "learning_rate": 8.832327210574827e-06, "loss": 0.3651, "step": 252190 }, { "epoch": 1.499129173576808, "grad_norm": 6.0059709548950195, "learning_rate": 8.83219393808007e-06, "loss": 0.3346, "step": 252200 }, { "epoch": 1.4991886156534764, "grad_norm": 4.991122722625732, "learning_rate": 8.83206065898582e-06, "loss": 0.3596, "step": 252210 }, { "epoch": 1.4992480577301448, "grad_norm": 5.238415241241455, "learning_rate": 8.831927373292302e-06, "loss": 0.3476, "step": 252220 }, { "epoch": 1.4993074998068132, "grad_norm": 4.905357837677002, "learning_rate": 8.83179408099975e-06, "loss": 0.3631, "step": 252230 }, { "epoch": 1.4993669418834816, "grad_norm": 6.004348278045654, "learning_rate": 8.83166078210839e-06, "loss": 0.3486, "step": 252240 }, { "epoch": 1.49942638396015, "grad_norm": 4.5424299240112305, "learning_rate": 8.831527476618454e-06, "loss": 0.3842, "step": 252250 }, { "epoch": 1.4994858260368185, "grad_norm": 5.383671760559082, "learning_rate": 8.83139416453017e-06, "loss": 0.3729, "step": 252260 }, { "epoch": 1.4995452681134869, "grad_norm": 6.217944622039795, "learning_rate": 8.831260845843766e-06, "loss": 0.3422, "step": 252270 }, { "epoch": 1.4996047101901553, "grad_norm": 5.056530952453613, "learning_rate": 8.831127520559478e-06, "loss": 0.3415, "step": 252280 }, { "epoch": 1.4996641522668237, "grad_norm": 4.41042423248291, "learning_rate": 8.830994188677527e-06, "loss": 0.365, "step": 252290 }, { "epoch": 1.4997235943434921, "grad_norm": 3.219881057739258, "learning_rate": 8.830860850198148e-06, "loss": 0.3676, "step": 252300 }, { "epoch": 1.4997830364201603, "grad_norm": 4.734934329986572, "learning_rate": 8.830727505121571e-06, "loss": 0.3782, "step": 252310 }, { "epoch": 1.4998424784968287, "grad_norm": 7.510839462280273, "learning_rate": 8.830594153448023e-06, "loss": 0.3824, "step": 252320 }, { "epoch": 1.4999019205734971, "grad_norm": 5.970127582550049, "learning_rate": 8.830460795177736e-06, "loss": 0.4042, "step": 252330 }, { "epoch": 1.4999613626501656, "grad_norm": 4.811554431915283, "learning_rate": 8.830327430310938e-06, "loss": 0.3522, "step": 252340 }, { "epoch": 1.500020804726834, "grad_norm": 4.860675811767578, "learning_rate": 8.830194058847859e-06, "loss": 0.3746, "step": 252350 }, { "epoch": 1.5000802468035024, "grad_norm": 5.456182956695557, "learning_rate": 8.830060680788727e-06, "loss": 0.3571, "step": 252360 }, { "epoch": 1.5001396888801706, "grad_norm": 5.0691633224487305, "learning_rate": 8.829927296133776e-06, "loss": 0.3717, "step": 252370 }, { "epoch": 1.500199130956839, "grad_norm": 5.256349086761475, "learning_rate": 8.829793904883233e-06, "loss": 0.3468, "step": 252380 }, { "epoch": 1.5002585730335074, "grad_norm": 5.081629276275635, "learning_rate": 8.829660507037327e-06, "loss": 0.3398, "step": 252390 }, { "epoch": 1.5003180151101758, "grad_norm": 4.648613929748535, "learning_rate": 8.82952710259629e-06, "loss": 0.3515, "step": 252400 }, { "epoch": 1.5003774571868442, "grad_norm": 5.491341590881348, "learning_rate": 8.829393691560348e-06, "loss": 0.3422, "step": 252410 }, { "epoch": 1.5004368992635126, "grad_norm": 4.495481967926025, "learning_rate": 8.829260273929734e-06, "loss": 0.389, "step": 252420 }, { "epoch": 1.500496341340181, "grad_norm": 6.173864364624023, "learning_rate": 8.829126849704678e-06, "loss": 0.3657, "step": 252430 }, { "epoch": 1.5005557834168495, "grad_norm": 5.587704181671143, "learning_rate": 8.828993418885408e-06, "loss": 0.3602, "step": 252440 }, { "epoch": 1.500615225493518, "grad_norm": 6.04960298538208, "learning_rate": 8.828859981472156e-06, "loss": 0.3928, "step": 252450 }, { "epoch": 1.5006746675701863, "grad_norm": 3.5853092670440674, "learning_rate": 8.828726537465148e-06, "loss": 0.3273, "step": 252460 }, { "epoch": 1.5007341096468547, "grad_norm": 4.837705135345459, "learning_rate": 8.828593086864616e-06, "loss": 0.341, "step": 252470 }, { "epoch": 1.5007935517235231, "grad_norm": 6.624095439910889, "learning_rate": 8.828459629670791e-06, "loss": 0.3426, "step": 252480 }, { "epoch": 1.5008529938001915, "grad_norm": 5.081714630126953, "learning_rate": 8.828326165883902e-06, "loss": 0.3547, "step": 252490 }, { "epoch": 1.5009124358768597, "grad_norm": 5.757503986358643, "learning_rate": 8.828192695504178e-06, "loss": 0.3452, "step": 252500 }, { "epoch": 1.5009718779535282, "grad_norm": 4.019261837005615, "learning_rate": 8.82805921853185e-06, "loss": 0.3149, "step": 252510 }, { "epoch": 1.5010313200301966, "grad_norm": 4.401933193206787, "learning_rate": 8.827925734967147e-06, "loss": 0.3276, "step": 252520 }, { "epoch": 1.501090762106865, "grad_norm": 5.119396686553955, "learning_rate": 8.827792244810298e-06, "loss": 0.3367, "step": 252530 }, { "epoch": 1.5011502041835334, "grad_norm": 7.723830223083496, "learning_rate": 8.827658748061535e-06, "loss": 0.3766, "step": 252540 }, { "epoch": 1.5012096462602016, "grad_norm": 4.018094062805176, "learning_rate": 8.827525244721086e-06, "loss": 0.3346, "step": 252550 }, { "epoch": 1.50126908833687, "grad_norm": 5.840155124664307, "learning_rate": 8.827391734789184e-06, "loss": 0.399, "step": 252560 }, { "epoch": 1.5013285304135384, "grad_norm": 5.613881587982178, "learning_rate": 8.827258218266055e-06, "loss": 0.3656, "step": 252570 }, { "epoch": 1.5013879724902068, "grad_norm": 4.7484307289123535, "learning_rate": 8.827124695151932e-06, "loss": 0.3411, "step": 252580 }, { "epoch": 1.5014474145668752, "grad_norm": 4.9320244789123535, "learning_rate": 8.826991165447042e-06, "loss": 0.4031, "step": 252590 }, { "epoch": 1.5015068566435437, "grad_norm": 5.214675426483154, "learning_rate": 8.826857629151617e-06, "loss": 0.3662, "step": 252600 }, { "epoch": 1.501566298720212, "grad_norm": 7.5395331382751465, "learning_rate": 8.826724086265888e-06, "loss": 0.3845, "step": 252610 }, { "epoch": 1.5016257407968805, "grad_norm": 5.344977855682373, "learning_rate": 8.826590536790083e-06, "loss": 0.3529, "step": 252620 }, { "epoch": 1.501685182873549, "grad_norm": 5.102365493774414, "learning_rate": 8.826456980724432e-06, "loss": 0.3553, "step": 252630 }, { "epoch": 1.5017446249502173, "grad_norm": 6.457696914672852, "learning_rate": 8.826323418069164e-06, "loss": 0.3472, "step": 252640 }, { "epoch": 1.5018040670268857, "grad_norm": 5.001519203186035, "learning_rate": 8.826189848824512e-06, "loss": 0.3417, "step": 252650 }, { "epoch": 1.5018635091035542, "grad_norm": 5.068964004516602, "learning_rate": 8.826056272990706e-06, "loss": 0.3253, "step": 252660 }, { "epoch": 1.5019229511802226, "grad_norm": 4.56638240814209, "learning_rate": 8.825922690567972e-06, "loss": 0.2938, "step": 252670 }, { "epoch": 1.501982393256891, "grad_norm": 5.5017571449279785, "learning_rate": 8.825789101556543e-06, "loss": 0.3644, "step": 252680 }, { "epoch": 1.5020418353335592, "grad_norm": 3.8780994415283203, "learning_rate": 8.82565550595665e-06, "loss": 0.3615, "step": 252690 }, { "epoch": 1.5021012774102276, "grad_norm": 5.436025619506836, "learning_rate": 8.825521903768521e-06, "loss": 0.3906, "step": 252700 }, { "epoch": 1.502160719486896, "grad_norm": 6.532880783081055, "learning_rate": 8.825388294992388e-06, "loss": 0.3848, "step": 252710 }, { "epoch": 1.5022201615635644, "grad_norm": 5.42350435256958, "learning_rate": 8.825254679628479e-06, "loss": 0.3782, "step": 252720 }, { "epoch": 1.5022796036402328, "grad_norm": 4.9765191078186035, "learning_rate": 8.825121057677023e-06, "loss": 0.3635, "step": 252730 }, { "epoch": 1.502339045716901, "grad_norm": 4.122467041015625, "learning_rate": 8.824987429138254e-06, "loss": 0.358, "step": 252740 }, { "epoch": 1.5023984877935694, "grad_norm": 5.384840965270996, "learning_rate": 8.824853794012402e-06, "loss": 0.3793, "step": 252750 }, { "epoch": 1.5024579298702379, "grad_norm": 6.301228046417236, "learning_rate": 8.824720152299694e-06, "loss": 0.3852, "step": 252760 }, { "epoch": 1.5025173719469063, "grad_norm": 4.613801956176758, "learning_rate": 8.82458650400036e-06, "loss": 0.3463, "step": 252770 }, { "epoch": 1.5025768140235747, "grad_norm": 4.959345817565918, "learning_rate": 8.824452849114633e-06, "loss": 0.309, "step": 252780 }, { "epoch": 1.502636256100243, "grad_norm": 6.506496429443359, "learning_rate": 8.824319187642743e-06, "loss": 0.382, "step": 252790 }, { "epoch": 1.5026956981769115, "grad_norm": 6.585312366485596, "learning_rate": 8.824185519584918e-06, "loss": 0.3569, "step": 252800 }, { "epoch": 1.50275514025358, "grad_norm": 7.67259407043457, "learning_rate": 8.824051844941387e-06, "loss": 0.3657, "step": 252810 }, { "epoch": 1.5028145823302483, "grad_norm": 4.199132442474365, "learning_rate": 8.823918163712386e-06, "loss": 0.3471, "step": 252820 }, { "epoch": 1.5028740244069168, "grad_norm": 3.7572038173675537, "learning_rate": 8.823784475898141e-06, "loss": 0.4027, "step": 252830 }, { "epoch": 1.5029334664835852, "grad_norm": 3.687950611114502, "learning_rate": 8.823650781498882e-06, "loss": 0.3206, "step": 252840 }, { "epoch": 1.5029929085602536, "grad_norm": 5.425558090209961, "learning_rate": 8.82351708051484e-06, "loss": 0.3883, "step": 252850 }, { "epoch": 1.503052350636922, "grad_norm": 4.912356853485107, "learning_rate": 8.823383372946245e-06, "loss": 0.3506, "step": 252860 }, { "epoch": 1.5031117927135902, "grad_norm": 6.1908955574035645, "learning_rate": 8.823249658793329e-06, "loss": 0.3489, "step": 252870 }, { "epoch": 1.5031712347902586, "grad_norm": 5.452581405639648, "learning_rate": 8.823115938056319e-06, "loss": 0.3431, "step": 252880 }, { "epoch": 1.503230676866927, "grad_norm": 3.803166151046753, "learning_rate": 8.822982210735449e-06, "loss": 0.3269, "step": 252890 }, { "epoch": 1.5032901189435954, "grad_norm": 4.45247745513916, "learning_rate": 8.822848476830946e-06, "loss": 0.3206, "step": 252900 }, { "epoch": 1.5033495610202638, "grad_norm": 3.941100597381592, "learning_rate": 8.822714736343044e-06, "loss": 0.3606, "step": 252910 }, { "epoch": 1.503409003096932, "grad_norm": 5.046854019165039, "learning_rate": 8.822580989271969e-06, "loss": 0.3348, "step": 252920 }, { "epoch": 1.5034684451736005, "grad_norm": 5.913544654846191, "learning_rate": 8.822447235617953e-06, "loss": 0.3663, "step": 252930 }, { "epoch": 1.5035278872502689, "grad_norm": 5.100362777709961, "learning_rate": 8.822313475381228e-06, "loss": 0.3184, "step": 252940 }, { "epoch": 1.5035873293269373, "grad_norm": 4.610305309295654, "learning_rate": 8.822179708562025e-06, "loss": 0.3577, "step": 252950 }, { "epoch": 1.5036467714036057, "grad_norm": 5.15261173248291, "learning_rate": 8.822045935160569e-06, "loss": 0.3752, "step": 252960 }, { "epoch": 1.5037062134802741, "grad_norm": 3.751225471496582, "learning_rate": 8.821912155177095e-06, "loss": 0.374, "step": 252970 }, { "epoch": 1.5037656555569425, "grad_norm": 4.473618984222412, "learning_rate": 8.821778368611832e-06, "loss": 0.3903, "step": 252980 }, { "epoch": 1.503825097633611, "grad_norm": 4.310499668121338, "learning_rate": 8.821644575465013e-06, "loss": 0.3838, "step": 252990 }, { "epoch": 1.5038845397102794, "grad_norm": 4.0110249519348145, "learning_rate": 8.821510775736864e-06, "loss": 0.3203, "step": 253000 }, { "epoch": 1.5039439817869478, "grad_norm": 5.734536170959473, "learning_rate": 8.821376969427617e-06, "loss": 0.3416, "step": 253010 }, { "epoch": 1.5040034238636162, "grad_norm": 4.30073356628418, "learning_rate": 8.821243156537505e-06, "loss": 0.3096, "step": 253020 }, { "epoch": 1.5040628659402846, "grad_norm": 3.3532798290252686, "learning_rate": 8.821109337066753e-06, "loss": 0.3246, "step": 253030 }, { "epoch": 1.504122308016953, "grad_norm": 4.594283580780029, "learning_rate": 8.820975511015598e-06, "loss": 0.3548, "step": 253040 }, { "epoch": 1.5041817500936214, "grad_norm": 5.306041240692139, "learning_rate": 8.820841678384267e-06, "loss": 0.3531, "step": 253050 }, { "epoch": 1.5042411921702896, "grad_norm": 4.0239081382751465, "learning_rate": 8.820707839172989e-06, "loss": 0.344, "step": 253060 }, { "epoch": 1.504300634246958, "grad_norm": 6.041999816894531, "learning_rate": 8.820573993381996e-06, "loss": 0.378, "step": 253070 }, { "epoch": 1.5043600763236264, "grad_norm": 6.011212348937988, "learning_rate": 8.82044014101152e-06, "loss": 0.3603, "step": 253080 }, { "epoch": 1.5044195184002949, "grad_norm": 6.25914192199707, "learning_rate": 8.82030628206179e-06, "loss": 0.3732, "step": 253090 }, { "epoch": 1.5044789604769633, "grad_norm": 4.158633232116699, "learning_rate": 8.820172416533037e-06, "loss": 0.3437, "step": 253100 }, { "epoch": 1.5045384025536315, "grad_norm": 6.496128559112549, "learning_rate": 8.820038544425491e-06, "loss": 0.3885, "step": 253110 }, { "epoch": 1.5045978446302999, "grad_norm": 4.812371253967285, "learning_rate": 8.819904665739383e-06, "loss": 0.3436, "step": 253120 }, { "epoch": 1.5046572867069683, "grad_norm": 7.078542232513428, "learning_rate": 8.819770780474943e-06, "loss": 0.3635, "step": 253130 }, { "epoch": 1.5047167287836367, "grad_norm": 5.012845516204834, "learning_rate": 8.819636888632403e-06, "loss": 0.3561, "step": 253140 }, { "epoch": 1.5047761708603051, "grad_norm": 5.402356147766113, "learning_rate": 8.819502990211993e-06, "loss": 0.3552, "step": 253150 }, { "epoch": 1.5048356129369735, "grad_norm": 4.504262924194336, "learning_rate": 8.81936908521394e-06, "loss": 0.3762, "step": 253160 }, { "epoch": 1.504895055013642, "grad_norm": 5.7313737869262695, "learning_rate": 8.81923517363848e-06, "loss": 0.4111, "step": 253170 }, { "epoch": 1.5049544970903104, "grad_norm": 4.738219261169434, "learning_rate": 8.81910125548584e-06, "loss": 0.3129, "step": 253180 }, { "epoch": 1.5050139391669788, "grad_norm": 4.9060540199279785, "learning_rate": 8.818967330756254e-06, "loss": 0.3741, "step": 253190 }, { "epoch": 1.5050733812436472, "grad_norm": 4.287905693054199, "learning_rate": 8.818833399449948e-06, "loss": 0.3583, "step": 253200 }, { "epoch": 1.5051328233203156, "grad_norm": 4.396265983581543, "learning_rate": 8.818699461567157e-06, "loss": 0.3632, "step": 253210 }, { "epoch": 1.505192265396984, "grad_norm": 4.770636558532715, "learning_rate": 8.81856551710811e-06, "loss": 0.3372, "step": 253220 }, { "epoch": 1.5052517074736524, "grad_norm": 5.760562419891357, "learning_rate": 8.818431566073037e-06, "loss": 0.3878, "step": 253230 }, { "epoch": 1.5053111495503206, "grad_norm": 4.532455921173096, "learning_rate": 8.818297608462169e-06, "loss": 0.377, "step": 253240 }, { "epoch": 1.505370591626989, "grad_norm": 3.875559091567993, "learning_rate": 8.818163644275737e-06, "loss": 0.3764, "step": 253250 }, { "epoch": 1.5054300337036575, "grad_norm": 5.936422348022461, "learning_rate": 8.818029673513972e-06, "loss": 0.3466, "step": 253260 }, { "epoch": 1.5054894757803259, "grad_norm": 4.869206428527832, "learning_rate": 8.817895696177105e-06, "loss": 0.3448, "step": 253270 }, { "epoch": 1.5055489178569943, "grad_norm": 5.03508186340332, "learning_rate": 8.817761712265364e-06, "loss": 0.3665, "step": 253280 }, { "epoch": 1.5056083599336625, "grad_norm": 3.764740467071533, "learning_rate": 8.817627721778982e-06, "loss": 0.3313, "step": 253290 }, { "epoch": 1.505667802010331, "grad_norm": 4.987027645111084, "learning_rate": 8.817493724718192e-06, "loss": 0.3448, "step": 253300 }, { "epoch": 1.5057272440869993, "grad_norm": 4.446549892425537, "learning_rate": 8.817359721083221e-06, "loss": 0.3125, "step": 253310 }, { "epoch": 1.5057866861636677, "grad_norm": 5.832111835479736, "learning_rate": 8.817225710874303e-06, "loss": 0.3559, "step": 253320 }, { "epoch": 1.5058461282403361, "grad_norm": 4.671882629394531, "learning_rate": 8.817091694091665e-06, "loss": 0.3261, "step": 253330 }, { "epoch": 1.5059055703170046, "grad_norm": 4.326424598693848, "learning_rate": 8.816957670735538e-06, "loss": 0.3496, "step": 253340 }, { "epoch": 1.505965012393673, "grad_norm": 5.840362548828125, "learning_rate": 8.816823640806155e-06, "loss": 0.3496, "step": 253350 }, { "epoch": 1.5060244544703414, "grad_norm": 3.7715141773223877, "learning_rate": 8.816689604303748e-06, "loss": 0.3805, "step": 253360 }, { "epoch": 1.5060838965470098, "grad_norm": 4.386387825012207, "learning_rate": 8.816555561228545e-06, "loss": 0.3688, "step": 253370 }, { "epoch": 1.5061433386236782, "grad_norm": 4.99907922744751, "learning_rate": 8.81642151158078e-06, "loss": 0.3617, "step": 253380 }, { "epoch": 1.5062027807003466, "grad_norm": 5.15285062789917, "learning_rate": 8.816287455360679e-06, "loss": 0.3789, "step": 253390 }, { "epoch": 1.506262222777015, "grad_norm": 4.226715564727783, "learning_rate": 8.816153392568477e-06, "loss": 0.3658, "step": 253400 }, { "epoch": 1.5063216648536835, "grad_norm": 4.973760604858398, "learning_rate": 8.816019323204403e-06, "loss": 0.3829, "step": 253410 }, { "epoch": 1.5063811069303519, "grad_norm": 4.517800331115723, "learning_rate": 8.815885247268689e-06, "loss": 0.3712, "step": 253420 }, { "epoch": 1.50644054900702, "grad_norm": 4.708703994750977, "learning_rate": 8.815751164761565e-06, "loss": 0.3475, "step": 253430 }, { "epoch": 1.5064999910836885, "grad_norm": 4.592892169952393, "learning_rate": 8.815617075683262e-06, "loss": 0.3056, "step": 253440 }, { "epoch": 1.506559433160357, "grad_norm": 5.719088077545166, "learning_rate": 8.815482980034011e-06, "loss": 0.3688, "step": 253450 }, { "epoch": 1.5066188752370253, "grad_norm": 3.2230541706085205, "learning_rate": 8.815348877814043e-06, "loss": 0.3114, "step": 253460 }, { "epoch": 1.5066783173136935, "grad_norm": 5.554831504821777, "learning_rate": 8.81521476902359e-06, "loss": 0.3317, "step": 253470 }, { "epoch": 1.506737759390362, "grad_norm": 5.842437267303467, "learning_rate": 8.815080653662881e-06, "loss": 0.3527, "step": 253480 }, { "epoch": 1.5067972014670303, "grad_norm": 5.279348850250244, "learning_rate": 8.814946531732148e-06, "loss": 0.3375, "step": 253490 }, { "epoch": 1.5068566435436987, "grad_norm": 5.233646869659424, "learning_rate": 8.814812403231622e-06, "loss": 0.3812, "step": 253500 }, { "epoch": 1.5069160856203672, "grad_norm": 5.201170921325684, "learning_rate": 8.814678268161534e-06, "loss": 0.3912, "step": 253510 }, { "epoch": 1.5069755276970356, "grad_norm": 6.203339099884033, "learning_rate": 8.814544126522115e-06, "loss": 0.3535, "step": 253520 }, { "epoch": 1.507034969773704, "grad_norm": 5.1298112869262695, "learning_rate": 8.814409978313596e-06, "loss": 0.3329, "step": 253530 }, { "epoch": 1.5070944118503724, "grad_norm": 5.011632919311523, "learning_rate": 8.814275823536207e-06, "loss": 0.3601, "step": 253540 }, { "epoch": 1.5071538539270408, "grad_norm": 6.772011756896973, "learning_rate": 8.814141662190182e-06, "loss": 0.4067, "step": 253550 }, { "epoch": 1.5072132960037092, "grad_norm": 3.9598610401153564, "learning_rate": 8.814007494275747e-06, "loss": 0.3499, "step": 253560 }, { "epoch": 1.5072727380803776, "grad_norm": 5.513275146484375, "learning_rate": 8.813873319793137e-06, "loss": 0.3666, "step": 253570 }, { "epoch": 1.507332180157046, "grad_norm": 3.968785047531128, "learning_rate": 8.813739138742582e-06, "loss": 0.3428, "step": 253580 }, { "epoch": 1.5073916222337145, "grad_norm": 4.231422424316406, "learning_rate": 8.813604951124315e-06, "loss": 0.3388, "step": 253590 }, { "epoch": 1.507451064310383, "grad_norm": 4.624623775482178, "learning_rate": 8.813470756938563e-06, "loss": 0.3427, "step": 253600 }, { "epoch": 1.507510506387051, "grad_norm": 5.29371452331543, "learning_rate": 8.813336556185561e-06, "loss": 0.3797, "step": 253610 }, { "epoch": 1.5075699484637195, "grad_norm": 5.420663356781006, "learning_rate": 8.813202348865537e-06, "loss": 0.3293, "step": 253620 }, { "epoch": 1.507629390540388, "grad_norm": 6.030889987945557, "learning_rate": 8.813068134978725e-06, "loss": 0.3844, "step": 253630 }, { "epoch": 1.5076888326170563, "grad_norm": 6.118200302124023, "learning_rate": 8.812933914525354e-06, "loss": 0.3625, "step": 253640 }, { "epoch": 1.5077482746937247, "grad_norm": 5.72283935546875, "learning_rate": 8.812799687505656e-06, "loss": 0.3865, "step": 253650 }, { "epoch": 1.507807716770393, "grad_norm": 5.031939506530762, "learning_rate": 8.812665453919861e-06, "loss": 0.3966, "step": 253660 }, { "epoch": 1.5078671588470614, "grad_norm": 5.109475612640381, "learning_rate": 8.812531213768203e-06, "loss": 0.3754, "step": 253670 }, { "epoch": 1.5079266009237298, "grad_norm": 6.364129066467285, "learning_rate": 8.812396967050909e-06, "loss": 0.3354, "step": 253680 }, { "epoch": 1.5079860430003982, "grad_norm": 5.600826263427734, "learning_rate": 8.812262713768215e-06, "loss": 0.3472, "step": 253690 }, { "epoch": 1.5080454850770666, "grad_norm": 5.129036903381348, "learning_rate": 8.812128453920348e-06, "loss": 0.3398, "step": 253700 }, { "epoch": 1.508104927153735, "grad_norm": 6.333071708679199, "learning_rate": 8.811994187507543e-06, "loss": 0.3831, "step": 253710 }, { "epoch": 1.5081643692304034, "grad_norm": 5.57567024230957, "learning_rate": 8.811859914530027e-06, "loss": 0.3632, "step": 253720 }, { "epoch": 1.5082238113070718, "grad_norm": 5.258233547210693, "learning_rate": 8.811725634988033e-06, "loss": 0.3822, "step": 253730 }, { "epoch": 1.5082832533837403, "grad_norm": 6.340396404266357, "learning_rate": 8.811591348881794e-06, "loss": 0.3715, "step": 253740 }, { "epoch": 1.5083426954604087, "grad_norm": 4.8258891105651855, "learning_rate": 8.811457056211542e-06, "loss": 0.3056, "step": 253750 }, { "epoch": 1.508402137537077, "grad_norm": 5.209165096282959, "learning_rate": 8.811322756977502e-06, "loss": 0.3387, "step": 253760 }, { "epoch": 1.5084615796137455, "grad_norm": 5.167218208312988, "learning_rate": 8.811188451179912e-06, "loss": 0.3427, "step": 253770 }, { "epoch": 1.508521021690414, "grad_norm": 6.431919097900391, "learning_rate": 8.811054138819e-06, "loss": 0.388, "step": 253780 }, { "epoch": 1.5085804637670823, "grad_norm": 5.625868320465088, "learning_rate": 8.810919819894999e-06, "loss": 0.3304, "step": 253790 }, { "epoch": 1.5086399058437505, "grad_norm": 4.721519947052002, "learning_rate": 8.810785494408137e-06, "loss": 0.3273, "step": 253800 }, { "epoch": 1.508699347920419, "grad_norm": 5.558123588562012, "learning_rate": 8.81065116235865e-06, "loss": 0.3941, "step": 253810 }, { "epoch": 1.5087587899970873, "grad_norm": 5.352217674255371, "learning_rate": 8.810516823746767e-06, "loss": 0.3569, "step": 253820 }, { "epoch": 1.5088182320737558, "grad_norm": 5.371608257293701, "learning_rate": 8.810382478572716e-06, "loss": 0.3471, "step": 253830 }, { "epoch": 1.508877674150424, "grad_norm": 4.798305988311768, "learning_rate": 8.810248126836735e-06, "loss": 0.3595, "step": 253840 }, { "epoch": 1.5089371162270924, "grad_norm": 3.757964849472046, "learning_rate": 8.810113768539052e-06, "loss": 0.3702, "step": 253850 }, { "epoch": 1.5089965583037608, "grad_norm": 5.559086322784424, "learning_rate": 8.809979403679898e-06, "loss": 0.3496, "step": 253860 }, { "epoch": 1.5090560003804292, "grad_norm": 5.187314510345459, "learning_rate": 8.809845032259505e-06, "loss": 0.3419, "step": 253870 }, { "epoch": 1.5091154424570976, "grad_norm": 5.043233394622803, "learning_rate": 8.809710654278103e-06, "loss": 0.3505, "step": 253880 }, { "epoch": 1.509174884533766, "grad_norm": 4.347635269165039, "learning_rate": 8.809576269735925e-06, "loss": 0.3327, "step": 253890 }, { "epoch": 1.5092343266104344, "grad_norm": 5.934157371520996, "learning_rate": 8.809441878633203e-06, "loss": 0.3611, "step": 253900 }, { "epoch": 1.5092937686871029, "grad_norm": 5.936441898345947, "learning_rate": 8.80930748097017e-06, "loss": 0.3598, "step": 253910 }, { "epoch": 1.5093532107637713, "grad_norm": 3.89872145652771, "learning_rate": 8.809173076747051e-06, "loss": 0.3526, "step": 253920 }, { "epoch": 1.5094126528404397, "grad_norm": 4.074224948883057, "learning_rate": 8.809038665964082e-06, "loss": 0.349, "step": 253930 }, { "epoch": 1.509472094917108, "grad_norm": 5.063326358795166, "learning_rate": 8.808904248621494e-06, "loss": 0.3703, "step": 253940 }, { "epoch": 1.5095315369937765, "grad_norm": 5.945765495300293, "learning_rate": 8.80876982471952e-06, "loss": 0.3651, "step": 253950 }, { "epoch": 1.509590979070445, "grad_norm": 4.7064948081970215, "learning_rate": 8.808635394258388e-06, "loss": 0.3611, "step": 253960 }, { "epoch": 1.5096504211471133, "grad_norm": 5.722664833068848, "learning_rate": 8.808500957238333e-06, "loss": 0.3494, "step": 253970 }, { "epoch": 1.5097098632237815, "grad_norm": 3.9293127059936523, "learning_rate": 8.808366513659586e-06, "loss": 0.3387, "step": 253980 }, { "epoch": 1.50976930530045, "grad_norm": 5.445034027099609, "learning_rate": 8.808232063522374e-06, "loss": 0.3519, "step": 253990 }, { "epoch": 1.5098287473771184, "grad_norm": 5.266330718994141, "learning_rate": 8.808097606826936e-06, "loss": 0.3804, "step": 254000 }, { "epoch": 1.5098881894537868, "grad_norm": 6.236804008483887, "learning_rate": 8.807963143573496e-06, "loss": 0.3576, "step": 254010 }, { "epoch": 1.5099476315304552, "grad_norm": 7.6039204597473145, "learning_rate": 8.80782867376229e-06, "loss": 0.397, "step": 254020 }, { "epoch": 1.5100070736071234, "grad_norm": 5.85790491104126, "learning_rate": 8.80769419739355e-06, "loss": 0.3609, "step": 254030 }, { "epoch": 1.5100665156837918, "grad_norm": 5.095876216888428, "learning_rate": 8.807559714467505e-06, "loss": 0.3733, "step": 254040 }, { "epoch": 1.5101259577604602, "grad_norm": 5.621261119842529, "learning_rate": 8.807425224984388e-06, "loss": 0.3524, "step": 254050 }, { "epoch": 1.5101853998371286, "grad_norm": 3.5307953357696533, "learning_rate": 8.80729072894443e-06, "loss": 0.3683, "step": 254060 }, { "epoch": 1.510244841913797, "grad_norm": 3.533602476119995, "learning_rate": 8.807156226347865e-06, "loss": 0.3545, "step": 254070 }, { "epoch": 1.5103042839904655, "grad_norm": 5.2041401863098145, "learning_rate": 8.80702171719492e-06, "loss": 0.3277, "step": 254080 }, { "epoch": 1.5103637260671339, "grad_norm": 5.036858558654785, "learning_rate": 8.806887201485833e-06, "loss": 0.3331, "step": 254090 }, { "epoch": 1.5104231681438023, "grad_norm": 4.615034103393555, "learning_rate": 8.806752679220828e-06, "loss": 0.3398, "step": 254100 }, { "epoch": 1.5104826102204707, "grad_norm": 7.767596244812012, "learning_rate": 8.806618150400143e-06, "loss": 0.3748, "step": 254110 }, { "epoch": 1.5105420522971391, "grad_norm": 6.031670570373535, "learning_rate": 8.806483615024007e-06, "loss": 0.3624, "step": 254120 }, { "epoch": 1.5106014943738075, "grad_norm": 5.11517333984375, "learning_rate": 8.806349073092653e-06, "loss": 0.3582, "step": 254130 }, { "epoch": 1.510660936450476, "grad_norm": 5.234407424926758, "learning_rate": 8.80621452460631e-06, "loss": 0.3625, "step": 254140 }, { "epoch": 1.5107203785271444, "grad_norm": 4.568188190460205, "learning_rate": 8.806079969565214e-06, "loss": 0.3951, "step": 254150 }, { "epoch": 1.5107798206038128, "grad_norm": 5.890463829040527, "learning_rate": 8.805945407969592e-06, "loss": 0.3601, "step": 254160 }, { "epoch": 1.510839262680481, "grad_norm": 5.260749340057373, "learning_rate": 8.805810839819678e-06, "loss": 0.3832, "step": 254170 }, { "epoch": 1.5108987047571494, "grad_norm": 6.575860500335693, "learning_rate": 8.805676265115704e-06, "loss": 0.3716, "step": 254180 }, { "epoch": 1.5109581468338178, "grad_norm": 5.930068492889404, "learning_rate": 8.8055416838579e-06, "loss": 0.4087, "step": 254190 }, { "epoch": 1.5110175889104862, "grad_norm": 4.378680229187012, "learning_rate": 8.8054070960465e-06, "loss": 0.3892, "step": 254200 }, { "epoch": 1.5110770309871544, "grad_norm": 3.713052272796631, "learning_rate": 8.805272501681736e-06, "loss": 0.3733, "step": 254210 }, { "epoch": 1.5111364730638228, "grad_norm": 5.0768141746521, "learning_rate": 8.805137900763838e-06, "loss": 0.3583, "step": 254220 }, { "epoch": 1.5111959151404912, "grad_norm": 4.706590175628662, "learning_rate": 8.805003293293038e-06, "loss": 0.3689, "step": 254230 }, { "epoch": 1.5112553572171596, "grad_norm": 5.1623640060424805, "learning_rate": 8.80486867926957e-06, "loss": 0.4016, "step": 254240 }, { "epoch": 1.511314799293828, "grad_norm": 5.4382100105285645, "learning_rate": 8.804734058693663e-06, "loss": 0.3703, "step": 254250 }, { "epoch": 1.5113742413704965, "grad_norm": 6.281483173370361, "learning_rate": 8.80459943156555e-06, "loss": 0.3646, "step": 254260 }, { "epoch": 1.5114336834471649, "grad_norm": 5.301836013793945, "learning_rate": 8.804464797885461e-06, "loss": 0.3434, "step": 254270 }, { "epoch": 1.5114931255238333, "grad_norm": 5.937009811401367, "learning_rate": 8.804330157653633e-06, "loss": 0.3714, "step": 254280 }, { "epoch": 1.5115525676005017, "grad_norm": 4.577593803405762, "learning_rate": 8.804195510870293e-06, "loss": 0.368, "step": 254290 }, { "epoch": 1.5116120096771701, "grad_norm": 4.302643299102783, "learning_rate": 8.804060857535675e-06, "loss": 0.3556, "step": 254300 }, { "epoch": 1.5116714517538385, "grad_norm": 5.894618511199951, "learning_rate": 8.803926197650009e-06, "loss": 0.3381, "step": 254310 }, { "epoch": 1.511730893830507, "grad_norm": 4.886743068695068, "learning_rate": 8.803791531213529e-06, "loss": 0.3614, "step": 254320 }, { "epoch": 1.5117903359071754, "grad_norm": 5.111824035644531, "learning_rate": 8.803656858226465e-06, "loss": 0.3847, "step": 254330 }, { "epoch": 1.5118497779838438, "grad_norm": 4.835217475891113, "learning_rate": 8.803522178689052e-06, "loss": 0.3947, "step": 254340 }, { "epoch": 1.511909220060512, "grad_norm": 6.096824645996094, "learning_rate": 8.803387492601518e-06, "loss": 0.3369, "step": 254350 }, { "epoch": 1.5119686621371804, "grad_norm": 5.17539119720459, "learning_rate": 8.8032527999641e-06, "loss": 0.3185, "step": 254360 }, { "epoch": 1.5120281042138488, "grad_norm": 5.421403408050537, "learning_rate": 8.803118100777024e-06, "loss": 0.3578, "step": 254370 }, { "epoch": 1.5120875462905172, "grad_norm": 4.432441234588623, "learning_rate": 8.802983395040526e-06, "loss": 0.3331, "step": 254380 }, { "epoch": 1.5121469883671856, "grad_norm": 5.535301208496094, "learning_rate": 8.802848682754837e-06, "loss": 0.3365, "step": 254390 }, { "epoch": 1.5122064304438538, "grad_norm": 4.515746116638184, "learning_rate": 8.802713963920187e-06, "loss": 0.3428, "step": 254400 }, { "epoch": 1.5122658725205222, "grad_norm": 5.9145636558532715, "learning_rate": 8.802579238536811e-06, "loss": 0.3377, "step": 254410 }, { "epoch": 1.5123253145971907, "grad_norm": 6.066169261932373, "learning_rate": 8.802444506604942e-06, "loss": 0.3557, "step": 254420 }, { "epoch": 1.512384756673859, "grad_norm": 5.155047416687012, "learning_rate": 8.802309768124806e-06, "loss": 0.3585, "step": 254430 }, { "epoch": 1.5124441987505275, "grad_norm": 4.619157791137695, "learning_rate": 8.802175023096642e-06, "loss": 0.3594, "step": 254440 }, { "epoch": 1.512503640827196, "grad_norm": 5.79344367980957, "learning_rate": 8.802040271520678e-06, "loss": 0.37, "step": 254450 }, { "epoch": 1.5125630829038643, "grad_norm": 5.471377372741699, "learning_rate": 8.801905513397147e-06, "loss": 0.3644, "step": 254460 }, { "epoch": 1.5126225249805327, "grad_norm": 3.9711272716522217, "learning_rate": 8.801770748726279e-06, "loss": 0.3902, "step": 254470 }, { "epoch": 1.5126819670572011, "grad_norm": 4.125965118408203, "learning_rate": 8.801635977508311e-06, "loss": 0.2967, "step": 254480 }, { "epoch": 1.5127414091338696, "grad_norm": 4.676072597503662, "learning_rate": 8.80150119974347e-06, "loss": 0.3952, "step": 254490 }, { "epoch": 1.512800851210538, "grad_norm": 7.523401737213135, "learning_rate": 8.801366415431992e-06, "loss": 0.3931, "step": 254500 }, { "epoch": 1.5128602932872064, "grad_norm": 4.54160213470459, "learning_rate": 8.801231624574107e-06, "loss": 0.3466, "step": 254510 }, { "epoch": 1.5129197353638748, "grad_norm": 4.665150165557861, "learning_rate": 8.801096827170049e-06, "loss": 0.374, "step": 254520 }, { "epoch": 1.5129791774405432, "grad_norm": 4.966285705566406, "learning_rate": 8.800962023220047e-06, "loss": 0.3338, "step": 254530 }, { "epoch": 1.5130386195172114, "grad_norm": 4.434120178222656, "learning_rate": 8.800827212724335e-06, "loss": 0.3394, "step": 254540 }, { "epoch": 1.5130980615938798, "grad_norm": 4.799610137939453, "learning_rate": 8.800692395683146e-06, "loss": 0.3648, "step": 254550 }, { "epoch": 1.5131575036705482, "grad_norm": 6.365093231201172, "learning_rate": 8.800557572096709e-06, "loss": 0.3986, "step": 254560 }, { "epoch": 1.5132169457472167, "grad_norm": 5.358041763305664, "learning_rate": 8.800422741965259e-06, "loss": 0.3598, "step": 254570 }, { "epoch": 1.5132763878238848, "grad_norm": 6.012187480926514, "learning_rate": 8.80028790528903e-06, "loss": 0.382, "step": 254580 }, { "epoch": 1.5133358299005533, "grad_norm": 4.556001663208008, "learning_rate": 8.800153062068249e-06, "loss": 0.3575, "step": 254590 }, { "epoch": 1.5133952719772217, "grad_norm": 5.557825088500977, "learning_rate": 8.800018212303153e-06, "loss": 0.3674, "step": 254600 }, { "epoch": 1.51345471405389, "grad_norm": 4.484928607940674, "learning_rate": 8.79988335599397e-06, "loss": 0.3966, "step": 254610 }, { "epoch": 1.5135141561305585, "grad_norm": 5.4439215660095215, "learning_rate": 8.799748493140936e-06, "loss": 0.3649, "step": 254620 }, { "epoch": 1.513573598207227, "grad_norm": 5.4439287185668945, "learning_rate": 8.799613623744283e-06, "loss": 0.4204, "step": 254630 }, { "epoch": 1.5136330402838953, "grad_norm": 3.7725272178649902, "learning_rate": 8.79947874780424e-06, "loss": 0.3365, "step": 254640 }, { "epoch": 1.5136924823605638, "grad_norm": 5.345370769500732, "learning_rate": 8.799343865321042e-06, "loss": 0.3905, "step": 254650 }, { "epoch": 1.5137519244372322, "grad_norm": 5.986122131347656, "learning_rate": 8.79920897629492e-06, "loss": 0.3453, "step": 254660 }, { "epoch": 1.5138113665139006, "grad_norm": 4.630634307861328, "learning_rate": 8.799074080726108e-06, "loss": 0.3586, "step": 254670 }, { "epoch": 1.513870808590569, "grad_norm": 5.769543170928955, "learning_rate": 8.798939178614835e-06, "loss": 0.342, "step": 254680 }, { "epoch": 1.5139302506672374, "grad_norm": 4.7038702964782715, "learning_rate": 8.798804269961339e-06, "loss": 0.3869, "step": 254690 }, { "epoch": 1.5139896927439058, "grad_norm": 6.461796283721924, "learning_rate": 8.798669354765845e-06, "loss": 0.3343, "step": 254700 }, { "epoch": 1.5140491348205742, "grad_norm": 6.555282115936279, "learning_rate": 8.798534433028591e-06, "loss": 0.3907, "step": 254710 }, { "epoch": 1.5141085768972424, "grad_norm": 4.283510208129883, "learning_rate": 8.798399504749807e-06, "loss": 0.3589, "step": 254720 }, { "epoch": 1.5141680189739108, "grad_norm": 4.723199844360352, "learning_rate": 8.798264569929727e-06, "loss": 0.3742, "step": 254730 }, { "epoch": 1.5142274610505793, "grad_norm": 4.297354221343994, "learning_rate": 8.79812962856858e-06, "loss": 0.344, "step": 254740 }, { "epoch": 1.5142869031272477, "grad_norm": 3.977180004119873, "learning_rate": 8.797994680666601e-06, "loss": 0.3525, "step": 254750 }, { "epoch": 1.514346345203916, "grad_norm": 4.557053089141846, "learning_rate": 8.797859726224023e-06, "loss": 0.3409, "step": 254760 }, { "epoch": 1.5144057872805843, "grad_norm": 6.188294410705566, "learning_rate": 8.797724765241079e-06, "loss": 0.3447, "step": 254770 }, { "epoch": 1.5144652293572527, "grad_norm": 4.54156494140625, "learning_rate": 8.797589797717998e-06, "loss": 0.3594, "step": 254780 }, { "epoch": 1.514524671433921, "grad_norm": 5.881933212280273, "learning_rate": 8.797454823655013e-06, "loss": 0.3417, "step": 254790 }, { "epoch": 1.5145841135105895, "grad_norm": 4.074979305267334, "learning_rate": 8.797319843052358e-06, "loss": 0.3577, "step": 254800 }, { "epoch": 1.514643555587258, "grad_norm": 4.540358543395996, "learning_rate": 8.797184855910268e-06, "loss": 0.3714, "step": 254810 }, { "epoch": 1.5147029976639264, "grad_norm": 6.311412811279297, "learning_rate": 8.79704986222897e-06, "loss": 0.3374, "step": 254820 }, { "epoch": 1.5147624397405948, "grad_norm": 4.9786248207092285, "learning_rate": 8.7969148620087e-06, "loss": 0.3372, "step": 254830 }, { "epoch": 1.5148218818172632, "grad_norm": 4.549047470092773, "learning_rate": 8.796779855249688e-06, "loss": 0.3481, "step": 254840 }, { "epoch": 1.5148813238939316, "grad_norm": 6.051608562469482, "learning_rate": 8.796644841952171e-06, "loss": 0.3566, "step": 254850 }, { "epoch": 1.5149407659706, "grad_norm": 5.941130638122559, "learning_rate": 8.796509822116376e-06, "loss": 0.3793, "step": 254860 }, { "epoch": 1.5150002080472684, "grad_norm": 5.302557945251465, "learning_rate": 8.796374795742539e-06, "loss": 0.363, "step": 254870 }, { "epoch": 1.5150596501239368, "grad_norm": 7.0749897956848145, "learning_rate": 8.796239762830892e-06, "loss": 0.3459, "step": 254880 }, { "epoch": 1.5151190922006053, "grad_norm": 5.926662921905518, "learning_rate": 8.796104723381666e-06, "loss": 0.3805, "step": 254890 }, { "epoch": 1.5151785342772737, "grad_norm": 4.693347454071045, "learning_rate": 8.795969677395096e-06, "loss": 0.3593, "step": 254900 }, { "epoch": 1.5152379763539419, "grad_norm": 4.8147172927856445, "learning_rate": 8.795834624871414e-06, "loss": 0.3414, "step": 254910 }, { "epoch": 1.5152974184306103, "grad_norm": 5.53635311126709, "learning_rate": 8.79569956581085e-06, "loss": 0.3561, "step": 254920 }, { "epoch": 1.5153568605072787, "grad_norm": 5.372436046600342, "learning_rate": 8.795564500213641e-06, "loss": 0.3581, "step": 254930 }, { "epoch": 1.515416302583947, "grad_norm": 4.270506858825684, "learning_rate": 8.795429428080014e-06, "loss": 0.3446, "step": 254940 }, { "epoch": 1.5154757446606153, "grad_norm": 4.234926223754883, "learning_rate": 8.795294349410205e-06, "loss": 0.3341, "step": 254950 }, { "epoch": 1.5155351867372837, "grad_norm": 4.125400543212891, "learning_rate": 8.795159264204446e-06, "loss": 0.3607, "step": 254960 }, { "epoch": 1.5155946288139521, "grad_norm": 5.064743995666504, "learning_rate": 8.795024172462974e-06, "loss": 0.351, "step": 254970 }, { "epoch": 1.5156540708906205, "grad_norm": 4.874804973602295, "learning_rate": 8.794889074186015e-06, "loss": 0.3732, "step": 254980 }, { "epoch": 1.515713512967289, "grad_norm": 3.8539681434631348, "learning_rate": 8.794753969373801e-06, "loss": 0.3159, "step": 254990 }, { "epoch": 1.5157729550439574, "grad_norm": 4.173079013824463, "learning_rate": 8.79461885802657e-06, "loss": 0.357, "step": 255000 }, { "epoch": 1.5158323971206258, "grad_norm": 5.062502861022949, "learning_rate": 8.794483740144556e-06, "loss": 0.4017, "step": 255010 }, { "epoch": 1.5158918391972942, "grad_norm": 5.238036632537842, "learning_rate": 8.794348615727986e-06, "loss": 0.348, "step": 255020 }, { "epoch": 1.5159512812739626, "grad_norm": 5.2066545486450195, "learning_rate": 8.794213484777095e-06, "loss": 0.3214, "step": 255030 }, { "epoch": 1.516010723350631, "grad_norm": 6.7631754875183105, "learning_rate": 8.794078347292115e-06, "loss": 0.4148, "step": 255040 }, { "epoch": 1.5160701654272994, "grad_norm": 4.585719108581543, "learning_rate": 8.793943203273279e-06, "loss": 0.3165, "step": 255050 }, { "epoch": 1.5161296075039679, "grad_norm": 4.991519927978516, "learning_rate": 8.79380805272082e-06, "loss": 0.3729, "step": 255060 }, { "epoch": 1.5161890495806363, "grad_norm": 5.005373001098633, "learning_rate": 8.793672895634971e-06, "loss": 0.3654, "step": 255070 }, { "epoch": 1.5162484916573047, "grad_norm": 5.274080753326416, "learning_rate": 8.793537732015966e-06, "loss": 0.3308, "step": 255080 }, { "epoch": 1.5163079337339729, "grad_norm": 6.341644287109375, "learning_rate": 8.793402561864035e-06, "loss": 0.3812, "step": 255090 }, { "epoch": 1.5163673758106413, "grad_norm": 6.991087913513184, "learning_rate": 8.793267385179412e-06, "loss": 0.3679, "step": 255100 }, { "epoch": 1.5164268178873097, "grad_norm": 4.370875835418701, "learning_rate": 8.793132201962331e-06, "loss": 0.3414, "step": 255110 }, { "epoch": 1.5164862599639781, "grad_norm": 4.777034282684326, "learning_rate": 8.792997012213025e-06, "loss": 0.3244, "step": 255120 }, { "epoch": 1.5165457020406465, "grad_norm": 5.501535415649414, "learning_rate": 8.792861815931724e-06, "loss": 0.3583, "step": 255130 }, { "epoch": 1.5166051441173147, "grad_norm": 5.793209552764893, "learning_rate": 8.79272661311866e-06, "loss": 0.3544, "step": 255140 }, { "epoch": 1.5166645861939831, "grad_norm": 6.179479122161865, "learning_rate": 8.792591403774072e-06, "loss": 0.3699, "step": 255150 }, { "epoch": 1.5167240282706516, "grad_norm": 6.664356231689453, "learning_rate": 8.792456187898187e-06, "loss": 0.3985, "step": 255160 }, { "epoch": 1.51678347034732, "grad_norm": 3.893907308578491, "learning_rate": 8.79232096549124e-06, "loss": 0.3561, "step": 255170 }, { "epoch": 1.5168429124239884, "grad_norm": 4.158507823944092, "learning_rate": 8.792185736553465e-06, "loss": 0.3461, "step": 255180 }, { "epoch": 1.5169023545006568, "grad_norm": 4.694202899932861, "learning_rate": 8.792050501085095e-06, "loss": 0.3213, "step": 255190 }, { "epoch": 1.5169617965773252, "grad_norm": 6.129732131958008, "learning_rate": 8.79191525908636e-06, "loss": 0.3643, "step": 255200 }, { "epoch": 1.5170212386539936, "grad_norm": 4.688035488128662, "learning_rate": 8.791780010557493e-06, "loss": 0.3516, "step": 255210 }, { "epoch": 1.517080680730662, "grad_norm": 4.91939640045166, "learning_rate": 8.79164475549873e-06, "loss": 0.3479, "step": 255220 }, { "epoch": 1.5171401228073305, "grad_norm": 3.6731224060058594, "learning_rate": 8.791509493910302e-06, "loss": 0.3636, "step": 255230 }, { "epoch": 1.5171995648839989, "grad_norm": 4.960202217102051, "learning_rate": 8.791374225792442e-06, "loss": 0.3657, "step": 255240 }, { "epoch": 1.5172590069606673, "grad_norm": 5.043614864349365, "learning_rate": 8.791238951145382e-06, "loss": 0.3595, "step": 255250 }, { "epoch": 1.5173184490373357, "grad_norm": 5.566836833953857, "learning_rate": 8.791103669969359e-06, "loss": 0.3583, "step": 255260 }, { "epoch": 1.5173778911140041, "grad_norm": 5.70598030090332, "learning_rate": 8.7909683822646e-06, "loss": 0.3717, "step": 255270 }, { "epoch": 1.5174373331906723, "grad_norm": 4.2256293296813965, "learning_rate": 8.790833088031342e-06, "loss": 0.3501, "step": 255280 }, { "epoch": 1.5174967752673407, "grad_norm": 4.232511520385742, "learning_rate": 8.79069778726982e-06, "loss": 0.3398, "step": 255290 }, { "epoch": 1.5175562173440091, "grad_norm": 6.176131248474121, "learning_rate": 8.790562479980262e-06, "loss": 0.3433, "step": 255300 }, { "epoch": 1.5176156594206776, "grad_norm": 5.51135778427124, "learning_rate": 8.790427166162902e-06, "loss": 0.359, "step": 255310 }, { "epoch": 1.5176751014973457, "grad_norm": 5.429257869720459, "learning_rate": 8.790291845817975e-06, "loss": 0.3279, "step": 255320 }, { "epoch": 1.5177345435740142, "grad_norm": 4.8109211921691895, "learning_rate": 8.790156518945713e-06, "loss": 0.3257, "step": 255330 }, { "epoch": 1.5177939856506826, "grad_norm": 4.236133575439453, "learning_rate": 8.790021185546351e-06, "loss": 0.3476, "step": 255340 }, { "epoch": 1.517853427727351, "grad_norm": 5.819764137268066, "learning_rate": 8.78988584562012e-06, "loss": 0.3415, "step": 255350 }, { "epoch": 1.5179128698040194, "grad_norm": 5.035898685455322, "learning_rate": 8.789750499167251e-06, "loss": 0.3721, "step": 255360 }, { "epoch": 1.5179723118806878, "grad_norm": 6.287266254425049, "learning_rate": 8.789615146187982e-06, "loss": 0.3477, "step": 255370 }, { "epoch": 1.5180317539573562, "grad_norm": 6.482071399688721, "learning_rate": 8.789479786682541e-06, "loss": 0.3569, "step": 255380 }, { "epoch": 1.5180911960340246, "grad_norm": 4.884171009063721, "learning_rate": 8.789344420651166e-06, "loss": 0.3633, "step": 255390 }, { "epoch": 1.518150638110693, "grad_norm": 3.59116792678833, "learning_rate": 8.789209048094087e-06, "loss": 0.3487, "step": 255400 }, { "epoch": 1.5182100801873615, "grad_norm": 4.1450371742248535, "learning_rate": 8.789073669011538e-06, "loss": 0.3455, "step": 255410 }, { "epoch": 1.51826952226403, "grad_norm": 4.519565582275391, "learning_rate": 8.788938283403752e-06, "loss": 0.3131, "step": 255420 }, { "epoch": 1.5183289643406983, "grad_norm": 5.272187232971191, "learning_rate": 8.78880289127096e-06, "loss": 0.3781, "step": 255430 }, { "epoch": 1.5183884064173667, "grad_norm": 5.648469924926758, "learning_rate": 8.7886674926134e-06, "loss": 0.3655, "step": 255440 }, { "epoch": 1.5184478484940351, "grad_norm": 4.97371244430542, "learning_rate": 8.788532087431301e-06, "loss": 0.3472, "step": 255450 }, { "epoch": 1.5185072905707033, "grad_norm": 5.772852420806885, "learning_rate": 8.788396675724899e-06, "loss": 0.3541, "step": 255460 }, { "epoch": 1.5185667326473717, "grad_norm": 5.940608501434326, "learning_rate": 8.788261257494426e-06, "loss": 0.3479, "step": 255470 }, { "epoch": 1.5186261747240402, "grad_norm": 4.837067127227783, "learning_rate": 8.788125832740115e-06, "loss": 0.3767, "step": 255480 }, { "epoch": 1.5186856168007086, "grad_norm": 5.346160888671875, "learning_rate": 8.7879904014622e-06, "loss": 0.3403, "step": 255490 }, { "epoch": 1.518745058877377, "grad_norm": 5.467031002044678, "learning_rate": 8.78785496366091e-06, "loss": 0.3686, "step": 255500 }, { "epoch": 1.5188045009540452, "grad_norm": 4.631277561187744, "learning_rate": 8.787719519336485e-06, "loss": 0.4023, "step": 255510 }, { "epoch": 1.5188639430307136, "grad_norm": 5.608329772949219, "learning_rate": 8.787584068489154e-06, "loss": 0.3888, "step": 255520 }, { "epoch": 1.518923385107382, "grad_norm": 3.70868182182312, "learning_rate": 8.787448611119151e-06, "loss": 0.3309, "step": 255530 }, { "epoch": 1.5189828271840504, "grad_norm": 5.110309600830078, "learning_rate": 8.78731314722671e-06, "loss": 0.3595, "step": 255540 }, { "epoch": 1.5190422692607188, "grad_norm": 4.966554164886475, "learning_rate": 8.787177676812064e-06, "loss": 0.3351, "step": 255550 }, { "epoch": 1.5191017113373873, "grad_norm": 5.823507308959961, "learning_rate": 8.787042199875446e-06, "loss": 0.3499, "step": 255560 }, { "epoch": 1.5191611534140557, "grad_norm": 8.858442306518555, "learning_rate": 8.78690671641709e-06, "loss": 0.3872, "step": 255570 }, { "epoch": 1.519220595490724, "grad_norm": 4.430838108062744, "learning_rate": 8.786771226437229e-06, "loss": 0.3464, "step": 255580 }, { "epoch": 1.5192800375673925, "grad_norm": 5.687460422515869, "learning_rate": 8.786635729936094e-06, "loss": 0.3346, "step": 255590 }, { "epoch": 1.519339479644061, "grad_norm": 4.040829181671143, "learning_rate": 8.786500226913923e-06, "loss": 0.3931, "step": 255600 }, { "epoch": 1.5193989217207293, "grad_norm": 3.6493310928344727, "learning_rate": 8.786364717370945e-06, "loss": 0.3667, "step": 255610 }, { "epoch": 1.5194583637973977, "grad_norm": 5.137277603149414, "learning_rate": 8.786229201307397e-06, "loss": 0.332, "step": 255620 }, { "epoch": 1.5195178058740662, "grad_norm": 7.145559310913086, "learning_rate": 8.786093678723509e-06, "loss": 0.3954, "step": 255630 }, { "epoch": 1.5195772479507346, "grad_norm": 6.253528594970703, "learning_rate": 8.785958149619517e-06, "loss": 0.3908, "step": 255640 }, { "epoch": 1.5196366900274028, "grad_norm": 5.563519477844238, "learning_rate": 8.785822613995652e-06, "loss": 0.3505, "step": 255650 }, { "epoch": 1.5196961321040712, "grad_norm": 6.501814842224121, "learning_rate": 8.78568707185215e-06, "loss": 0.383, "step": 255660 }, { "epoch": 1.5197555741807396, "grad_norm": 4.526034832000732, "learning_rate": 8.785551523189243e-06, "loss": 0.3603, "step": 255670 }, { "epoch": 1.519815016257408, "grad_norm": 5.239336013793945, "learning_rate": 8.785415968007165e-06, "loss": 0.3399, "step": 255680 }, { "epoch": 1.5198744583340762, "grad_norm": 6.68332576751709, "learning_rate": 8.785280406306147e-06, "loss": 0.3807, "step": 255690 }, { "epoch": 1.5199339004107446, "grad_norm": 5.541757583618164, "learning_rate": 8.785144838086426e-06, "loss": 0.3537, "step": 255700 }, { "epoch": 1.519993342487413, "grad_norm": 4.34147834777832, "learning_rate": 8.785009263348235e-06, "loss": 0.3391, "step": 255710 }, { "epoch": 1.5200527845640814, "grad_norm": 3.9021849632263184, "learning_rate": 8.784873682091804e-06, "loss": 0.3626, "step": 255720 }, { "epoch": 1.5201122266407499, "grad_norm": 5.229992866516113, "learning_rate": 8.78473809431737e-06, "loss": 0.3354, "step": 255730 }, { "epoch": 1.5201716687174183, "grad_norm": 4.695542335510254, "learning_rate": 8.784602500025166e-06, "loss": 0.3326, "step": 255740 }, { "epoch": 1.5202311107940867, "grad_norm": 5.357458591461182, "learning_rate": 8.784466899215424e-06, "loss": 0.3464, "step": 255750 }, { "epoch": 1.520290552870755, "grad_norm": 4.958894729614258, "learning_rate": 8.78433129188838e-06, "loss": 0.3831, "step": 255760 }, { "epoch": 1.5203499949474235, "grad_norm": 7.410703659057617, "learning_rate": 8.784195678044265e-06, "loss": 0.3761, "step": 255770 }, { "epoch": 1.520409437024092, "grad_norm": 5.07831335067749, "learning_rate": 8.784060057683313e-06, "loss": 0.3921, "step": 255780 }, { "epoch": 1.5204688791007603, "grad_norm": 4.563725471496582, "learning_rate": 8.783924430805758e-06, "loss": 0.3623, "step": 255790 }, { "epoch": 1.5205283211774288, "grad_norm": 4.353304386138916, "learning_rate": 8.783788797411834e-06, "loss": 0.376, "step": 255800 }, { "epoch": 1.5205877632540972, "grad_norm": 6.609533309936523, "learning_rate": 8.783653157501775e-06, "loss": 0.3725, "step": 255810 }, { "epoch": 1.5206472053307656, "grad_norm": 4.637513637542725, "learning_rate": 8.783517511075812e-06, "loss": 0.3736, "step": 255820 }, { "epoch": 1.5207066474074338, "grad_norm": 4.872871398925781, "learning_rate": 8.78338185813418e-06, "loss": 0.3734, "step": 255830 }, { "epoch": 1.5207660894841022, "grad_norm": 3.9612650871276855, "learning_rate": 8.783246198677116e-06, "loss": 0.282, "step": 255840 }, { "epoch": 1.5208255315607706, "grad_norm": 6.251888275146484, "learning_rate": 8.783110532704851e-06, "loss": 0.3802, "step": 255850 }, { "epoch": 1.520884973637439, "grad_norm": 5.186967372894287, "learning_rate": 8.782974860217614e-06, "loss": 0.3432, "step": 255860 }, { "epoch": 1.5209444157141074, "grad_norm": 5.284180641174316, "learning_rate": 8.782839181215645e-06, "loss": 0.3608, "step": 255870 }, { "epoch": 1.5210038577907756, "grad_norm": 5.99674129486084, "learning_rate": 8.782703495699178e-06, "loss": 0.377, "step": 255880 }, { "epoch": 1.521063299867444, "grad_norm": 5.535506725311279, "learning_rate": 8.782567803668441e-06, "loss": 0.3567, "step": 255890 }, { "epoch": 1.5211227419441125, "grad_norm": 4.795752048492432, "learning_rate": 8.782432105123673e-06, "loss": 0.3256, "step": 255900 }, { "epoch": 1.5211821840207809, "grad_norm": 5.29176139831543, "learning_rate": 8.782296400065104e-06, "loss": 0.3667, "step": 255910 }, { "epoch": 1.5212416260974493, "grad_norm": 6.2259297370910645, "learning_rate": 8.78216068849297e-06, "loss": 0.3487, "step": 255920 }, { "epoch": 1.5213010681741177, "grad_norm": 5.256192684173584, "learning_rate": 8.782024970407503e-06, "loss": 0.3677, "step": 255930 }, { "epoch": 1.5213605102507861, "grad_norm": 4.143329620361328, "learning_rate": 8.78188924580894e-06, "loss": 0.3621, "step": 255940 }, { "epoch": 1.5214199523274545, "grad_norm": 3.72438907623291, "learning_rate": 8.781753514697511e-06, "loss": 0.3658, "step": 255950 }, { "epoch": 1.521479394404123, "grad_norm": 4.2508087158203125, "learning_rate": 8.781617777073452e-06, "loss": 0.3334, "step": 255960 }, { "epoch": 1.5215388364807914, "grad_norm": 6.390689373016357, "learning_rate": 8.781482032936994e-06, "loss": 0.3622, "step": 255970 }, { "epoch": 1.5215982785574598, "grad_norm": 4.084229469299316, "learning_rate": 8.781346282288374e-06, "loss": 0.3529, "step": 255980 }, { "epoch": 1.5216577206341282, "grad_norm": 4.900520324707031, "learning_rate": 8.781210525127826e-06, "loss": 0.3328, "step": 255990 }, { "epoch": 1.5217171627107966, "grad_norm": 5.916159152984619, "learning_rate": 8.78107476145558e-06, "loss": 0.3573, "step": 256000 }, { "epoch": 1.521776604787465, "grad_norm": 5.032616138458252, "learning_rate": 8.780938991271874e-06, "loss": 0.2843, "step": 256010 }, { "epoch": 1.5218360468641332, "grad_norm": 5.360231399536133, "learning_rate": 8.780803214576938e-06, "loss": 0.3363, "step": 256020 }, { "epoch": 1.5218954889408016, "grad_norm": 3.6648943424224854, "learning_rate": 8.780667431371009e-06, "loss": 0.3582, "step": 256030 }, { "epoch": 1.52195493101747, "grad_norm": 5.002445697784424, "learning_rate": 8.78053164165432e-06, "loss": 0.3656, "step": 256040 }, { "epoch": 1.5220143730941385, "grad_norm": 6.0521650314331055, "learning_rate": 8.780395845427103e-06, "loss": 0.3306, "step": 256050 }, { "epoch": 1.5220738151708066, "grad_norm": 5.14619255065918, "learning_rate": 8.780260042689595e-06, "loss": 0.3832, "step": 256060 }, { "epoch": 1.522133257247475, "grad_norm": 4.652491569519043, "learning_rate": 8.780124233442026e-06, "loss": 0.3848, "step": 256070 }, { "epoch": 1.5221926993241435, "grad_norm": 6.862921714782715, "learning_rate": 8.779988417684633e-06, "loss": 0.3468, "step": 256080 }, { "epoch": 1.5222521414008119, "grad_norm": 3.915459156036377, "learning_rate": 8.779852595417649e-06, "loss": 0.3666, "step": 256090 }, { "epoch": 1.5223115834774803, "grad_norm": 6.167533874511719, "learning_rate": 8.779716766641308e-06, "loss": 0.3325, "step": 256100 }, { "epoch": 1.5223710255541487, "grad_norm": 6.298801898956299, "learning_rate": 8.779580931355845e-06, "loss": 0.368, "step": 256110 }, { "epoch": 1.5224304676308171, "grad_norm": 5.074582099914551, "learning_rate": 8.779445089561492e-06, "loss": 0.3178, "step": 256120 }, { "epoch": 1.5224899097074855, "grad_norm": 5.452214241027832, "learning_rate": 8.779309241258482e-06, "loss": 0.4177, "step": 256130 }, { "epoch": 1.522549351784154, "grad_norm": 5.921733379364014, "learning_rate": 8.77917338644705e-06, "loss": 0.324, "step": 256140 }, { "epoch": 1.5226087938608224, "grad_norm": 7.431034088134766, "learning_rate": 8.779037525127433e-06, "loss": 0.3346, "step": 256150 }, { "epoch": 1.5226682359374908, "grad_norm": 5.502493381500244, "learning_rate": 8.77890165729986e-06, "loss": 0.3577, "step": 256160 }, { "epoch": 1.5227276780141592, "grad_norm": 4.421473026275635, "learning_rate": 8.778765782964572e-06, "loss": 0.3188, "step": 256170 }, { "epoch": 1.5227871200908276, "grad_norm": 4.517874717712402, "learning_rate": 8.778629902121794e-06, "loss": 0.3379, "step": 256180 }, { "epoch": 1.522846562167496, "grad_norm": 5.053754806518555, "learning_rate": 8.778494014771766e-06, "loss": 0.3644, "step": 256190 }, { "epoch": 1.5229060042441642, "grad_norm": 4.533553600311279, "learning_rate": 8.778358120914721e-06, "loss": 0.3045, "step": 256200 }, { "epoch": 1.5229654463208326, "grad_norm": 5.8058247566223145, "learning_rate": 8.778222220550891e-06, "loss": 0.3691, "step": 256210 }, { "epoch": 1.523024888397501, "grad_norm": 5.510642051696777, "learning_rate": 8.778086313680512e-06, "loss": 0.3808, "step": 256220 }, { "epoch": 1.5230843304741695, "grad_norm": 6.776656627655029, "learning_rate": 8.777950400303818e-06, "loss": 0.4154, "step": 256230 }, { "epoch": 1.5231437725508379, "grad_norm": 5.6603522300720215, "learning_rate": 8.777814480421042e-06, "loss": 0.3586, "step": 256240 }, { "epoch": 1.523203214627506, "grad_norm": 4.194243431091309, "learning_rate": 8.77767855403242e-06, "loss": 0.3492, "step": 256250 }, { "epoch": 1.5232626567041745, "grad_norm": 5.119441986083984, "learning_rate": 8.777542621138185e-06, "loss": 0.3467, "step": 256260 }, { "epoch": 1.523322098780843, "grad_norm": 6.287261962890625, "learning_rate": 8.777406681738569e-06, "loss": 0.3358, "step": 256270 }, { "epoch": 1.5233815408575113, "grad_norm": 6.191254138946533, "learning_rate": 8.777270735833809e-06, "loss": 0.3703, "step": 256280 }, { "epoch": 1.5234409829341797, "grad_norm": 5.586648941040039, "learning_rate": 8.777134783424136e-06, "loss": 0.35, "step": 256290 }, { "epoch": 1.5235004250108481, "grad_norm": 4.678866863250732, "learning_rate": 8.776998824509791e-06, "loss": 0.395, "step": 256300 }, { "epoch": 1.5235598670875166, "grad_norm": 5.217734336853027, "learning_rate": 8.776862859091e-06, "loss": 0.3633, "step": 256310 }, { "epoch": 1.523619309164185, "grad_norm": 5.467315196990967, "learning_rate": 8.776726887168e-06, "loss": 0.3138, "step": 256320 }, { "epoch": 1.5236787512408534, "grad_norm": 4.072561740875244, "learning_rate": 8.776590908741028e-06, "loss": 0.3375, "step": 256330 }, { "epoch": 1.5237381933175218, "grad_norm": 5.438312530517578, "learning_rate": 8.776454923810313e-06, "loss": 0.3458, "step": 256340 }, { "epoch": 1.5237976353941902, "grad_norm": 6.057702541351318, "learning_rate": 8.776318932376094e-06, "loss": 0.3801, "step": 256350 }, { "epoch": 1.5238570774708586, "grad_norm": 5.801211833953857, "learning_rate": 8.776182934438604e-06, "loss": 0.3666, "step": 256360 }, { "epoch": 1.523916519547527, "grad_norm": 6.443503379821777, "learning_rate": 8.776046929998074e-06, "loss": 0.3734, "step": 256370 }, { "epoch": 1.5239759616241955, "grad_norm": 6.378936290740967, "learning_rate": 8.775910919054742e-06, "loss": 0.3565, "step": 256380 }, { "epoch": 1.5240354037008637, "grad_norm": 7.01762580871582, "learning_rate": 8.77577490160884e-06, "loss": 0.3633, "step": 256390 }, { "epoch": 1.524094845777532, "grad_norm": 5.1395721435546875, "learning_rate": 8.775638877660605e-06, "loss": 0.3455, "step": 256400 }, { "epoch": 1.5241542878542005, "grad_norm": 4.729388236999512, "learning_rate": 8.775502847210268e-06, "loss": 0.3407, "step": 256410 }, { "epoch": 1.524213729930869, "grad_norm": 4.824492931365967, "learning_rate": 8.775366810258064e-06, "loss": 0.3692, "step": 256420 }, { "epoch": 1.524273172007537, "grad_norm": 5.63165807723999, "learning_rate": 8.775230766804228e-06, "loss": 0.3731, "step": 256430 }, { "epoch": 1.5243326140842055, "grad_norm": 6.163626670837402, "learning_rate": 8.775094716848996e-06, "loss": 0.3626, "step": 256440 }, { "epoch": 1.524392056160874, "grad_norm": 5.888672351837158, "learning_rate": 8.7749586603926e-06, "loss": 0.323, "step": 256450 }, { "epoch": 1.5244514982375423, "grad_norm": 3.7628660202026367, "learning_rate": 8.774822597435273e-06, "loss": 0.3502, "step": 256460 }, { "epoch": 1.5245109403142107, "grad_norm": 5.044466018676758, "learning_rate": 8.774686527977253e-06, "loss": 0.4099, "step": 256470 }, { "epoch": 1.5245703823908792, "grad_norm": 5.3102874755859375, "learning_rate": 8.77455045201877e-06, "loss": 0.3531, "step": 256480 }, { "epoch": 1.5246298244675476, "grad_norm": 4.765499114990234, "learning_rate": 8.774414369560063e-06, "loss": 0.3895, "step": 256490 }, { "epoch": 1.524689266544216, "grad_norm": 6.0418009757995605, "learning_rate": 8.774278280601365e-06, "loss": 0.3456, "step": 256500 }, { "epoch": 1.5247487086208844, "grad_norm": 5.419264316558838, "learning_rate": 8.774142185142906e-06, "loss": 0.3895, "step": 256510 }, { "epoch": 1.5248081506975528, "grad_norm": 4.157761573791504, "learning_rate": 8.774006083184928e-06, "loss": 0.372, "step": 256520 }, { "epoch": 1.5248675927742212, "grad_norm": 4.500997543334961, "learning_rate": 8.773869974727658e-06, "loss": 0.3536, "step": 256530 }, { "epoch": 1.5249270348508897, "grad_norm": 5.2776265144348145, "learning_rate": 8.773733859771334e-06, "loss": 0.3443, "step": 256540 }, { "epoch": 1.524986476927558, "grad_norm": 4.853152275085449, "learning_rate": 8.77359773831619e-06, "loss": 0.3303, "step": 256550 }, { "epoch": 1.5250459190042265, "grad_norm": 6.13499641418457, "learning_rate": 8.773461610362462e-06, "loss": 0.3804, "step": 256560 }, { "epoch": 1.5251053610808947, "grad_norm": 4.13722562789917, "learning_rate": 8.773325475910382e-06, "loss": 0.3414, "step": 256570 }, { "epoch": 1.525164803157563, "grad_norm": 4.066603183746338, "learning_rate": 8.773189334960184e-06, "loss": 0.3273, "step": 256580 }, { "epoch": 1.5252242452342315, "grad_norm": 6.093438148498535, "learning_rate": 8.773053187512106e-06, "loss": 0.343, "step": 256590 }, { "epoch": 1.5252836873109, "grad_norm": 4.95719575881958, "learning_rate": 8.772917033566378e-06, "loss": 0.3159, "step": 256600 }, { "epoch": 1.5253431293875683, "grad_norm": 5.294651031494141, "learning_rate": 8.77278087312324e-06, "loss": 0.3384, "step": 256610 }, { "epoch": 1.5254025714642365, "grad_norm": 5.4964141845703125, "learning_rate": 8.77264470618292e-06, "loss": 0.3794, "step": 256620 }, { "epoch": 1.525462013540905, "grad_norm": 5.7879228591918945, "learning_rate": 8.772508532745656e-06, "loss": 0.3876, "step": 256630 }, { "epoch": 1.5255214556175734, "grad_norm": 5.051405906677246, "learning_rate": 8.772372352811682e-06, "loss": 0.3294, "step": 256640 }, { "epoch": 1.5255808976942418, "grad_norm": 5.126925945281982, "learning_rate": 8.772236166381234e-06, "loss": 0.3789, "step": 256650 }, { "epoch": 1.5256403397709102, "grad_norm": 5.284648418426514, "learning_rate": 8.772099973454545e-06, "loss": 0.3456, "step": 256660 }, { "epoch": 1.5256997818475786, "grad_norm": 5.151288032531738, "learning_rate": 8.77196377403185e-06, "loss": 0.3401, "step": 256670 }, { "epoch": 1.525759223924247, "grad_norm": 4.13690710067749, "learning_rate": 8.771827568113382e-06, "loss": 0.3329, "step": 256680 }, { "epoch": 1.5258186660009154, "grad_norm": 4.667523384094238, "learning_rate": 8.771691355699378e-06, "loss": 0.3726, "step": 256690 }, { "epoch": 1.5258781080775838, "grad_norm": 4.611929416656494, "learning_rate": 8.77155513679007e-06, "loss": 0.3938, "step": 256700 }, { "epoch": 1.5259375501542523, "grad_norm": 5.355118751525879, "learning_rate": 8.771418911385696e-06, "loss": 0.3638, "step": 256710 }, { "epoch": 1.5259969922309207, "grad_norm": 5.58824348449707, "learning_rate": 8.771282679486489e-06, "loss": 0.3654, "step": 256720 }, { "epoch": 1.526056434307589, "grad_norm": 5.273484706878662, "learning_rate": 8.771146441092682e-06, "loss": 0.3612, "step": 256730 }, { "epoch": 1.5261158763842575, "grad_norm": 5.34458065032959, "learning_rate": 8.77101019620451e-06, "loss": 0.3346, "step": 256740 }, { "epoch": 1.526175318460926, "grad_norm": 4.198904037475586, "learning_rate": 8.77087394482221e-06, "loss": 0.3374, "step": 256750 }, { "epoch": 1.526234760537594, "grad_norm": 4.82907772064209, "learning_rate": 8.770737686946014e-06, "loss": 0.3363, "step": 256760 }, { "epoch": 1.5262942026142625, "grad_norm": 5.510193347930908, "learning_rate": 8.77060142257616e-06, "loss": 0.3789, "step": 256770 }, { "epoch": 1.526353644690931, "grad_norm": 5.051616191864014, "learning_rate": 8.770465151712879e-06, "loss": 0.3384, "step": 256780 }, { "epoch": 1.5264130867675993, "grad_norm": 4.39932918548584, "learning_rate": 8.770328874356407e-06, "loss": 0.3317, "step": 256790 }, { "epoch": 1.5264725288442675, "grad_norm": 6.58590841293335, "learning_rate": 8.770192590506979e-06, "loss": 0.3448, "step": 256800 }, { "epoch": 1.526531970920936, "grad_norm": 5.607310771942139, "learning_rate": 8.770056300164828e-06, "loss": 0.3745, "step": 256810 }, { "epoch": 1.5265914129976044, "grad_norm": 5.637650489807129, "learning_rate": 8.769920003330192e-06, "loss": 0.3942, "step": 256820 }, { "epoch": 1.5266508550742728, "grad_norm": 4.741238117218018, "learning_rate": 8.769783700003302e-06, "loss": 0.3395, "step": 256830 }, { "epoch": 1.5267102971509412, "grad_norm": 4.07896614074707, "learning_rate": 8.769647390184397e-06, "loss": 0.35, "step": 256840 }, { "epoch": 1.5267697392276096, "grad_norm": 2.814077138900757, "learning_rate": 8.769511073873709e-06, "loss": 0.3436, "step": 256850 }, { "epoch": 1.526829181304278, "grad_norm": 4.819221496582031, "learning_rate": 8.769374751071472e-06, "loss": 0.3391, "step": 256860 }, { "epoch": 1.5268886233809464, "grad_norm": 5.779409885406494, "learning_rate": 8.769238421777923e-06, "loss": 0.3862, "step": 256870 }, { "epoch": 1.5269480654576149, "grad_norm": 6.348313808441162, "learning_rate": 8.769102085993295e-06, "loss": 0.383, "step": 256880 }, { "epoch": 1.5270075075342833, "grad_norm": 6.156994819641113, "learning_rate": 8.768965743717822e-06, "loss": 0.3813, "step": 256890 }, { "epoch": 1.5270669496109517, "grad_norm": 3.973078489303589, "learning_rate": 8.768829394951743e-06, "loss": 0.3563, "step": 256900 }, { "epoch": 1.52712639168762, "grad_norm": 5.6790547370910645, "learning_rate": 8.768693039695291e-06, "loss": 0.3298, "step": 256910 }, { "epoch": 1.5271858337642885, "grad_norm": 4.911720275878906, "learning_rate": 8.768556677948697e-06, "loss": 0.3912, "step": 256920 }, { "epoch": 1.527245275840957, "grad_norm": 4.602901935577393, "learning_rate": 8.7684203097122e-06, "loss": 0.3507, "step": 256930 }, { "epoch": 1.5273047179176251, "grad_norm": 6.859870433807373, "learning_rate": 8.768283934986034e-06, "loss": 0.3902, "step": 256940 }, { "epoch": 1.5273641599942935, "grad_norm": 6.986501693725586, "learning_rate": 8.768147553770432e-06, "loss": 0.3726, "step": 256950 }, { "epoch": 1.527423602070962, "grad_norm": 5.564939022064209, "learning_rate": 8.76801116606563e-06, "loss": 0.3479, "step": 256960 }, { "epoch": 1.5274830441476304, "grad_norm": 5.41733980178833, "learning_rate": 8.767874771871865e-06, "loss": 0.3183, "step": 256970 }, { "epoch": 1.5275424862242988, "grad_norm": 5.470337867736816, "learning_rate": 8.76773837118937e-06, "loss": 0.3299, "step": 256980 }, { "epoch": 1.527601928300967, "grad_norm": 4.630420684814453, "learning_rate": 8.76760196401838e-06, "loss": 0.3441, "step": 256990 }, { "epoch": 1.5276613703776354, "grad_norm": 5.353459358215332, "learning_rate": 8.767465550359129e-06, "loss": 0.3664, "step": 257000 }, { "epoch": 1.5277208124543038, "grad_norm": 5.976609230041504, "learning_rate": 8.767329130211852e-06, "loss": 0.3649, "step": 257010 }, { "epoch": 1.5277802545309722, "grad_norm": 4.830657958984375, "learning_rate": 8.767192703576785e-06, "loss": 0.3562, "step": 257020 }, { "epoch": 1.5278396966076406, "grad_norm": 5.517858982086182, "learning_rate": 8.767056270454163e-06, "loss": 0.3669, "step": 257030 }, { "epoch": 1.527899138684309, "grad_norm": 4.3255934715271, "learning_rate": 8.766919830844223e-06, "loss": 0.3426, "step": 257040 }, { "epoch": 1.5279585807609775, "grad_norm": 4.95326566696167, "learning_rate": 8.766783384747195e-06, "loss": 0.3451, "step": 257050 }, { "epoch": 1.5280180228376459, "grad_norm": 4.807833671569824, "learning_rate": 8.766646932163317e-06, "loss": 0.3638, "step": 257060 }, { "epoch": 1.5280774649143143, "grad_norm": 3.850742816925049, "learning_rate": 8.766510473092825e-06, "loss": 0.3404, "step": 257070 }, { "epoch": 1.5281369069909827, "grad_norm": 5.233095645904541, "learning_rate": 8.76637400753595e-06, "loss": 0.3249, "step": 257080 }, { "epoch": 1.5281963490676511, "grad_norm": 4.965734958648682, "learning_rate": 8.766237535492932e-06, "loss": 0.3086, "step": 257090 }, { "epoch": 1.5282557911443195, "grad_norm": 5.351268768310547, "learning_rate": 8.766101056964003e-06, "loss": 0.3403, "step": 257100 }, { "epoch": 1.528315233220988, "grad_norm": 4.396044731140137, "learning_rate": 8.765964571949398e-06, "loss": 0.3415, "step": 257110 }, { "epoch": 1.5283746752976564, "grad_norm": 3.970752239227295, "learning_rate": 8.765828080449351e-06, "loss": 0.3124, "step": 257120 }, { "epoch": 1.5284341173743246, "grad_norm": 4.879464149475098, "learning_rate": 8.7656915824641e-06, "loss": 0.3449, "step": 257130 }, { "epoch": 1.528493559450993, "grad_norm": 4.930455684661865, "learning_rate": 8.765555077993879e-06, "loss": 0.3641, "step": 257140 }, { "epoch": 1.5285530015276614, "grad_norm": 5.108311176300049, "learning_rate": 8.765418567038924e-06, "loss": 0.3496, "step": 257150 }, { "epoch": 1.5286124436043298, "grad_norm": 5.9183244705200195, "learning_rate": 8.765282049599469e-06, "loss": 0.3198, "step": 257160 }, { "epoch": 1.528671885680998, "grad_norm": 4.430744647979736, "learning_rate": 8.765145525675747e-06, "loss": 0.337, "step": 257170 }, { "epoch": 1.5287313277576664, "grad_norm": 5.09999942779541, "learning_rate": 8.765008995267996e-06, "loss": 0.3645, "step": 257180 }, { "epoch": 1.5287907698343348, "grad_norm": 5.153372764587402, "learning_rate": 8.76487245837645e-06, "loss": 0.3481, "step": 257190 }, { "epoch": 1.5288502119110032, "grad_norm": 5.087642669677734, "learning_rate": 8.764735915001346e-06, "loss": 0.3613, "step": 257200 }, { "epoch": 1.5289096539876716, "grad_norm": 4.991779804229736, "learning_rate": 8.764599365142917e-06, "loss": 0.3577, "step": 257210 }, { "epoch": 1.52896909606434, "grad_norm": 7.675570011138916, "learning_rate": 8.764462808801397e-06, "loss": 0.3712, "step": 257220 }, { "epoch": 1.5290285381410085, "grad_norm": 5.318893909454346, "learning_rate": 8.764326245977024e-06, "loss": 0.3798, "step": 257230 }, { "epoch": 1.529087980217677, "grad_norm": 4.535680294036865, "learning_rate": 8.764189676670034e-06, "loss": 0.3551, "step": 257240 }, { "epoch": 1.5291474222943453, "grad_norm": 5.014572620391846, "learning_rate": 8.764053100880656e-06, "loss": 0.3685, "step": 257250 }, { "epoch": 1.5292068643710137, "grad_norm": 4.724040985107422, "learning_rate": 8.763916518609132e-06, "loss": 0.3394, "step": 257260 }, { "epoch": 1.5292663064476821, "grad_norm": 5.360907554626465, "learning_rate": 8.763779929855697e-06, "loss": 0.3781, "step": 257270 }, { "epoch": 1.5293257485243505, "grad_norm": 4.307647228240967, "learning_rate": 8.763643334620579e-06, "loss": 0.3596, "step": 257280 }, { "epoch": 1.529385190601019, "grad_norm": 7.211451053619385, "learning_rate": 8.76350673290402e-06, "loss": 0.3664, "step": 257290 }, { "epoch": 1.5294446326776874, "grad_norm": 5.44679069519043, "learning_rate": 8.763370124706255e-06, "loss": 0.39, "step": 257300 }, { "epoch": 1.5295040747543556, "grad_norm": 4.297154426574707, "learning_rate": 8.763233510027516e-06, "loss": 0.3139, "step": 257310 }, { "epoch": 1.529563516831024, "grad_norm": 5.261530876159668, "learning_rate": 8.76309688886804e-06, "loss": 0.361, "step": 257320 }, { "epoch": 1.5296229589076924, "grad_norm": 5.027508735656738, "learning_rate": 8.762960261228062e-06, "loss": 0.3387, "step": 257330 }, { "epoch": 1.5296824009843608, "grad_norm": 3.65926194190979, "learning_rate": 8.76282362710782e-06, "loss": 0.3519, "step": 257340 }, { "epoch": 1.5297418430610292, "grad_norm": 4.736214637756348, "learning_rate": 8.762686986507542e-06, "loss": 0.3765, "step": 257350 }, { "epoch": 1.5298012851376974, "grad_norm": 5.766276836395264, "learning_rate": 8.76255033942747e-06, "loss": 0.3792, "step": 257360 }, { "epoch": 1.5298607272143658, "grad_norm": 4.075677394866943, "learning_rate": 8.76241368586784e-06, "loss": 0.3857, "step": 257370 }, { "epoch": 1.5299201692910342, "grad_norm": 4.8168559074401855, "learning_rate": 8.762277025828882e-06, "loss": 0.3835, "step": 257380 }, { "epoch": 1.5299796113677027, "grad_norm": 4.862682342529297, "learning_rate": 8.762140359310836e-06, "loss": 0.3214, "step": 257390 }, { "epoch": 1.530039053444371, "grad_norm": 6.797468662261963, "learning_rate": 8.762003686313934e-06, "loss": 0.3553, "step": 257400 }, { "epoch": 1.5300984955210395, "grad_norm": 3.8262014389038086, "learning_rate": 8.761867006838412e-06, "loss": 0.3388, "step": 257410 }, { "epoch": 1.530157937597708, "grad_norm": 4.635578632354736, "learning_rate": 8.761730320884507e-06, "loss": 0.3691, "step": 257420 }, { "epoch": 1.5302173796743763, "grad_norm": 5.687143325805664, "learning_rate": 8.761593628452453e-06, "loss": 0.3636, "step": 257430 }, { "epoch": 1.5302768217510447, "grad_norm": 5.170926570892334, "learning_rate": 8.761456929542488e-06, "loss": 0.3875, "step": 257440 }, { "epoch": 1.5303362638277132, "grad_norm": 5.8417768478393555, "learning_rate": 8.761320224154844e-06, "loss": 0.3408, "step": 257450 }, { "epoch": 1.5303957059043816, "grad_norm": 3.6772470474243164, "learning_rate": 8.761183512289757e-06, "loss": 0.3892, "step": 257460 }, { "epoch": 1.53045514798105, "grad_norm": 3.9327268600463867, "learning_rate": 8.761046793947463e-06, "loss": 0.3629, "step": 257470 }, { "epoch": 1.5305145900577184, "grad_norm": 6.278825283050537, "learning_rate": 8.760910069128199e-06, "loss": 0.3699, "step": 257480 }, { "epoch": 1.5305740321343868, "grad_norm": 4.943283557891846, "learning_rate": 8.7607733378322e-06, "loss": 0.3433, "step": 257490 }, { "epoch": 1.530633474211055, "grad_norm": 5.101743221282959, "learning_rate": 8.760636600059699e-06, "loss": 0.3367, "step": 257500 }, { "epoch": 1.5306929162877234, "grad_norm": 5.691959381103516, "learning_rate": 8.760499855810933e-06, "loss": 0.3968, "step": 257510 }, { "epoch": 1.5307523583643918, "grad_norm": 6.543729782104492, "learning_rate": 8.760363105086138e-06, "loss": 0.3486, "step": 257520 }, { "epoch": 1.5308118004410602, "grad_norm": 6.359330654144287, "learning_rate": 8.760226347885548e-06, "loss": 0.3553, "step": 257530 }, { "epoch": 1.5308712425177284, "grad_norm": 6.0133748054504395, "learning_rate": 8.7600895842094e-06, "loss": 0.3755, "step": 257540 }, { "epoch": 1.5309306845943969, "grad_norm": 5.138962268829346, "learning_rate": 8.759952814057932e-06, "loss": 0.3604, "step": 257550 }, { "epoch": 1.5309901266710653, "grad_norm": 4.695157527923584, "learning_rate": 8.759816037431373e-06, "loss": 0.3501, "step": 257560 }, { "epoch": 1.5310495687477337, "grad_norm": 4.693273067474365, "learning_rate": 8.759679254329963e-06, "loss": 0.3904, "step": 257570 }, { "epoch": 1.531109010824402, "grad_norm": 4.419139862060547, "learning_rate": 8.759542464753939e-06, "loss": 0.3548, "step": 257580 }, { "epoch": 1.5311684529010705, "grad_norm": 6.06669807434082, "learning_rate": 8.759405668703531e-06, "loss": 0.3597, "step": 257590 }, { "epoch": 1.531227894977739, "grad_norm": 6.1417131423950195, "learning_rate": 8.75926886617898e-06, "loss": 0.3491, "step": 257600 }, { "epoch": 1.5312873370544073, "grad_norm": 5.357452869415283, "learning_rate": 8.759132057180519e-06, "loss": 0.3831, "step": 257610 }, { "epoch": 1.5313467791310758, "grad_norm": 5.5235795974731445, "learning_rate": 8.758995241708383e-06, "loss": 0.3789, "step": 257620 }, { "epoch": 1.5314062212077442, "grad_norm": 5.288597583770752, "learning_rate": 8.75885841976281e-06, "loss": 0.3519, "step": 257630 }, { "epoch": 1.5314656632844126, "grad_norm": 4.453839302062988, "learning_rate": 8.758721591344033e-06, "loss": 0.3496, "step": 257640 }, { "epoch": 1.531525105361081, "grad_norm": 4.546736717224121, "learning_rate": 8.758584756452292e-06, "loss": 0.3215, "step": 257650 }, { "epoch": 1.5315845474377494, "grad_norm": 6.021363258361816, "learning_rate": 8.758447915087815e-06, "loss": 0.3677, "step": 257660 }, { "epoch": 1.5316439895144178, "grad_norm": 5.485434532165527, "learning_rate": 8.758311067250846e-06, "loss": 0.35, "step": 257670 }, { "epoch": 1.531703431591086, "grad_norm": 6.303644180297852, "learning_rate": 8.758174212941616e-06, "loss": 0.3655, "step": 257680 }, { "epoch": 1.5317628736677544, "grad_norm": 3.3914265632629395, "learning_rate": 8.758037352160361e-06, "loss": 0.3363, "step": 257690 }, { "epoch": 1.5318223157444228, "grad_norm": 5.155705451965332, "learning_rate": 8.757900484907316e-06, "loss": 0.3842, "step": 257700 }, { "epoch": 1.5318817578210913, "grad_norm": 4.962247848510742, "learning_rate": 8.75776361118272e-06, "loss": 0.3981, "step": 257710 }, { "epoch": 1.5319411998977597, "grad_norm": 3.982628107070923, "learning_rate": 8.757626730986806e-06, "loss": 0.3643, "step": 257720 }, { "epoch": 1.5320006419744279, "grad_norm": 5.4187164306640625, "learning_rate": 8.757489844319811e-06, "loss": 0.3674, "step": 257730 }, { "epoch": 1.5320600840510963, "grad_norm": 4.270171165466309, "learning_rate": 8.75735295118197e-06, "loss": 0.3583, "step": 257740 }, { "epoch": 1.5321195261277647, "grad_norm": 4.830354690551758, "learning_rate": 8.757216051573517e-06, "loss": 0.357, "step": 257750 }, { "epoch": 1.5321789682044331, "grad_norm": 4.733658790588379, "learning_rate": 8.75707914549469e-06, "loss": 0.3405, "step": 257760 }, { "epoch": 1.5322384102811015, "grad_norm": 5.797569751739502, "learning_rate": 8.756942232945727e-06, "loss": 0.382, "step": 257770 }, { "epoch": 1.53229785235777, "grad_norm": 6.338341236114502, "learning_rate": 8.756805313926859e-06, "loss": 0.3835, "step": 257780 }, { "epoch": 1.5323572944344384, "grad_norm": 5.330425262451172, "learning_rate": 8.756668388438325e-06, "loss": 0.34, "step": 257790 }, { "epoch": 1.5324167365111068, "grad_norm": 7.242847919464111, "learning_rate": 8.75653145648036e-06, "loss": 0.3742, "step": 257800 }, { "epoch": 1.5324761785877752, "grad_norm": 4.012510299682617, "learning_rate": 8.756394518053199e-06, "loss": 0.3673, "step": 257810 }, { "epoch": 1.5325356206644436, "grad_norm": 5.1853437423706055, "learning_rate": 8.756257573157079e-06, "loss": 0.3784, "step": 257820 }, { "epoch": 1.532595062741112, "grad_norm": 6.200255393981934, "learning_rate": 8.756120621792235e-06, "loss": 0.361, "step": 257830 }, { "epoch": 1.5326545048177804, "grad_norm": 4.1982808113098145, "learning_rate": 8.755983663958903e-06, "loss": 0.316, "step": 257840 }, { "epoch": 1.5327139468944488, "grad_norm": 4.346276760101318, "learning_rate": 8.755846699657318e-06, "loss": 0.3495, "step": 257850 }, { "epoch": 1.5327733889711173, "grad_norm": 5.9031267166137695, "learning_rate": 8.755709728887717e-06, "loss": 0.3365, "step": 257860 }, { "epoch": 1.5328328310477854, "grad_norm": 3.8858487606048584, "learning_rate": 8.755572751650339e-06, "loss": 0.3288, "step": 257870 }, { "epoch": 1.5328922731244539, "grad_norm": 4.5384931564331055, "learning_rate": 8.755435767945413e-06, "loss": 0.3264, "step": 257880 }, { "epoch": 1.5329517152011223, "grad_norm": 6.105223655700684, "learning_rate": 8.755298777773181e-06, "loss": 0.3227, "step": 257890 }, { "epoch": 1.5330111572777907, "grad_norm": 5.281463146209717, "learning_rate": 8.755161781133874e-06, "loss": 0.388, "step": 257900 }, { "epoch": 1.5330705993544589, "grad_norm": 4.12518310546875, "learning_rate": 8.755024778027732e-06, "loss": 0.3574, "step": 257910 }, { "epoch": 1.5331300414311273, "grad_norm": 6.440531253814697, "learning_rate": 8.754887768454987e-06, "loss": 0.3855, "step": 257920 }, { "epoch": 1.5331894835077957, "grad_norm": 4.434814929962158, "learning_rate": 8.75475075241588e-06, "loss": 0.3647, "step": 257930 }, { "epoch": 1.5332489255844641, "grad_norm": 5.083308696746826, "learning_rate": 8.754613729910644e-06, "loss": 0.3643, "step": 257940 }, { "epoch": 1.5333083676611325, "grad_norm": 5.554958820343018, "learning_rate": 8.754476700939513e-06, "loss": 0.3497, "step": 257950 }, { "epoch": 1.533367809737801, "grad_norm": 5.827452659606934, "learning_rate": 8.754339665502726e-06, "loss": 0.3471, "step": 257960 }, { "epoch": 1.5334272518144694, "grad_norm": 5.404165267944336, "learning_rate": 8.75420262360052e-06, "loss": 0.3564, "step": 257970 }, { "epoch": 1.5334866938911378, "grad_norm": 3.907658576965332, "learning_rate": 8.754065575233128e-06, "loss": 0.3522, "step": 257980 }, { "epoch": 1.5335461359678062, "grad_norm": 6.230869293212891, "learning_rate": 8.753928520400787e-06, "loss": 0.3318, "step": 257990 }, { "epoch": 1.5336055780444746, "grad_norm": 4.192953586578369, "learning_rate": 8.753791459103734e-06, "loss": 0.3335, "step": 258000 }, { "epoch": 1.533665020121143, "grad_norm": 3.955772876739502, "learning_rate": 8.753654391342201e-06, "loss": 0.3852, "step": 258010 }, { "epoch": 1.5337244621978114, "grad_norm": 4.256870746612549, "learning_rate": 8.753517317116432e-06, "loss": 0.3544, "step": 258020 }, { "epoch": 1.5337839042744799, "grad_norm": 3.4327456951141357, "learning_rate": 8.753380236426654e-06, "loss": 0.3245, "step": 258030 }, { "epoch": 1.5338433463511483, "grad_norm": 4.295184135437012, "learning_rate": 8.75324314927311e-06, "loss": 0.3257, "step": 258040 }, { "epoch": 1.5339027884278165, "grad_norm": 4.698886394500732, "learning_rate": 8.753106055656034e-06, "loss": 0.3494, "step": 258050 }, { "epoch": 1.5339622305044849, "grad_norm": 6.220355033874512, "learning_rate": 8.752968955575659e-06, "loss": 0.3565, "step": 258060 }, { "epoch": 1.5340216725811533, "grad_norm": 5.498640060424805, "learning_rate": 8.752831849032225e-06, "loss": 0.347, "step": 258070 }, { "epoch": 1.5340811146578217, "grad_norm": 6.071815490722656, "learning_rate": 8.752694736025966e-06, "loss": 0.3706, "step": 258080 }, { "epoch": 1.5341405567344901, "grad_norm": 5.979570388793945, "learning_rate": 8.752557616557121e-06, "loss": 0.3636, "step": 258090 }, { "epoch": 1.5341999988111583, "grad_norm": 3.755601167678833, "learning_rate": 8.75242049062592e-06, "loss": 0.3533, "step": 258100 }, { "epoch": 1.5342594408878267, "grad_norm": 4.77218770980835, "learning_rate": 8.752283358232608e-06, "loss": 0.331, "step": 258110 }, { "epoch": 1.5343188829644951, "grad_norm": 4.437663555145264, "learning_rate": 8.752146219377415e-06, "loss": 0.357, "step": 258120 }, { "epoch": 1.5343783250411636, "grad_norm": 4.225827693939209, "learning_rate": 8.752009074060576e-06, "loss": 0.3522, "step": 258130 }, { "epoch": 1.534437767117832, "grad_norm": 5.288755416870117, "learning_rate": 8.751871922282332e-06, "loss": 0.3704, "step": 258140 }, { "epoch": 1.5344972091945004, "grad_norm": 4.496340274810791, "learning_rate": 8.751734764042917e-06, "loss": 0.3838, "step": 258150 }, { "epoch": 1.5345566512711688, "grad_norm": 4.205266952514648, "learning_rate": 8.751597599342564e-06, "loss": 0.3351, "step": 258160 }, { "epoch": 1.5346160933478372, "grad_norm": 5.272558212280273, "learning_rate": 8.751460428181516e-06, "loss": 0.3445, "step": 258170 }, { "epoch": 1.5346755354245056, "grad_norm": 5.034206867218018, "learning_rate": 8.751323250560005e-06, "loss": 0.3326, "step": 258180 }, { "epoch": 1.534734977501174, "grad_norm": 6.838879585266113, "learning_rate": 8.751186066478265e-06, "loss": 0.3421, "step": 258190 }, { "epoch": 1.5347944195778425, "grad_norm": 5.275295734405518, "learning_rate": 8.751048875936538e-06, "loss": 0.4011, "step": 258200 }, { "epoch": 1.5348538616545109, "grad_norm": 5.784485816955566, "learning_rate": 8.750911678935057e-06, "loss": 0.3222, "step": 258210 }, { "epoch": 1.5349133037311793, "grad_norm": 3.6918673515319824, "learning_rate": 8.750774475474057e-06, "loss": 0.2881, "step": 258220 }, { "epoch": 1.5349727458078477, "grad_norm": 3.910996437072754, "learning_rate": 8.750637265553777e-06, "loss": 0.3541, "step": 258230 }, { "epoch": 1.535032187884516, "grad_norm": 3.917368173599243, "learning_rate": 8.75050004917445e-06, "loss": 0.3456, "step": 258240 }, { "epoch": 1.5350916299611843, "grad_norm": 5.634490489959717, "learning_rate": 8.750362826336318e-06, "loss": 0.3529, "step": 258250 }, { "epoch": 1.5351510720378527, "grad_norm": 5.5758795738220215, "learning_rate": 8.750225597039612e-06, "loss": 0.3517, "step": 258260 }, { "epoch": 1.5352105141145211, "grad_norm": 5.026772499084473, "learning_rate": 8.75008836128457e-06, "loss": 0.3287, "step": 258270 }, { "epoch": 1.5352699561911893, "grad_norm": 4.042686462402344, "learning_rate": 8.749951119071426e-06, "loss": 0.3502, "step": 258280 }, { "epoch": 1.5353293982678577, "grad_norm": 7.7947492599487305, "learning_rate": 8.749813870400424e-06, "loss": 0.4102, "step": 258290 }, { "epoch": 1.5353888403445262, "grad_norm": 3.8299272060394287, "learning_rate": 8.749676615271792e-06, "loss": 0.3705, "step": 258300 }, { "epoch": 1.5354482824211946, "grad_norm": 5.565222263336182, "learning_rate": 8.749539353685768e-06, "loss": 0.3207, "step": 258310 }, { "epoch": 1.535507724497863, "grad_norm": 5.570425033569336, "learning_rate": 8.749402085642592e-06, "loss": 0.3252, "step": 258320 }, { "epoch": 1.5355671665745314, "grad_norm": 3.3756215572357178, "learning_rate": 8.749264811142497e-06, "loss": 0.3443, "step": 258330 }, { "epoch": 1.5356266086511998, "grad_norm": 7.091033935546875, "learning_rate": 8.74912753018572e-06, "loss": 0.3602, "step": 258340 }, { "epoch": 1.5356860507278682, "grad_norm": 5.533904552459717, "learning_rate": 8.748990242772502e-06, "loss": 0.3507, "step": 258350 }, { "epoch": 1.5357454928045366, "grad_norm": 5.357010841369629, "learning_rate": 8.748852948903071e-06, "loss": 0.3611, "step": 258360 }, { "epoch": 1.535804934881205, "grad_norm": 4.303886890411377, "learning_rate": 8.74871564857767e-06, "loss": 0.352, "step": 258370 }, { "epoch": 1.5358643769578735, "grad_norm": 7.3469767570495605, "learning_rate": 8.748578341796535e-06, "loss": 0.4064, "step": 258380 }, { "epoch": 1.535923819034542, "grad_norm": 4.005967140197754, "learning_rate": 8.748441028559897e-06, "loss": 0.3776, "step": 258390 }, { "epoch": 1.5359832611112103, "grad_norm": 4.288536548614502, "learning_rate": 8.748303708867998e-06, "loss": 0.368, "step": 258400 }, { "epoch": 1.5360427031878787, "grad_norm": 5.500993251800537, "learning_rate": 8.748166382721074e-06, "loss": 0.3805, "step": 258410 }, { "epoch": 1.536102145264547, "grad_norm": 5.267347812652588, "learning_rate": 8.748029050119359e-06, "loss": 0.3683, "step": 258420 }, { "epoch": 1.5361615873412153, "grad_norm": 4.110484600067139, "learning_rate": 8.747891711063092e-06, "loss": 0.3335, "step": 258430 }, { "epoch": 1.5362210294178837, "grad_norm": 4.453976154327393, "learning_rate": 8.747754365552507e-06, "loss": 0.3462, "step": 258440 }, { "epoch": 1.5362804714945522, "grad_norm": 7.0140485763549805, "learning_rate": 8.74761701358784e-06, "loss": 0.3737, "step": 258450 }, { "epoch": 1.5363399135712206, "grad_norm": 3.609816789627075, "learning_rate": 8.747479655169334e-06, "loss": 0.3553, "step": 258460 }, { "epoch": 1.5363993556478888, "grad_norm": 4.7327561378479, "learning_rate": 8.747342290297217e-06, "loss": 0.33, "step": 258470 }, { "epoch": 1.5364587977245572, "grad_norm": 6.188196182250977, "learning_rate": 8.74720491897173e-06, "loss": 0.3194, "step": 258480 }, { "epoch": 1.5365182398012256, "grad_norm": 5.231290817260742, "learning_rate": 8.74706754119311e-06, "loss": 0.3539, "step": 258490 }, { "epoch": 1.536577681877894, "grad_norm": 5.675126075744629, "learning_rate": 8.746930156961593e-06, "loss": 0.3477, "step": 258500 }, { "epoch": 1.5366371239545624, "grad_norm": 5.272424221038818, "learning_rate": 8.746792766277414e-06, "loss": 0.3638, "step": 258510 }, { "epoch": 1.5366965660312308, "grad_norm": 5.880475044250488, "learning_rate": 8.746655369140813e-06, "loss": 0.3645, "step": 258520 }, { "epoch": 1.5367560081078993, "grad_norm": 9.412683486938477, "learning_rate": 8.746517965552021e-06, "loss": 0.3278, "step": 258530 }, { "epoch": 1.5368154501845677, "grad_norm": 3.584289073944092, "learning_rate": 8.746380555511281e-06, "loss": 0.3537, "step": 258540 }, { "epoch": 1.536874892261236, "grad_norm": 5.21296501159668, "learning_rate": 8.746243139018827e-06, "loss": 0.3502, "step": 258550 }, { "epoch": 1.5369343343379045, "grad_norm": 3.7490549087524414, "learning_rate": 8.746105716074894e-06, "loss": 0.3234, "step": 258560 }, { "epoch": 1.536993776414573, "grad_norm": 5.568656921386719, "learning_rate": 8.745968286679719e-06, "loss": 0.3622, "step": 258570 }, { "epoch": 1.5370532184912413, "grad_norm": 6.125831604003906, "learning_rate": 8.74583085083354e-06, "loss": 0.3445, "step": 258580 }, { "epoch": 1.5371126605679097, "grad_norm": 6.606405258178711, "learning_rate": 8.745693408536593e-06, "loss": 0.3863, "step": 258590 }, { "epoch": 1.5371721026445782, "grad_norm": 6.369804859161377, "learning_rate": 8.745555959789116e-06, "loss": 0.3709, "step": 258600 }, { "epoch": 1.5372315447212463, "grad_norm": 6.186792850494385, "learning_rate": 8.745418504591345e-06, "loss": 0.3625, "step": 258610 }, { "epoch": 1.5372909867979148, "grad_norm": 3.682131052017212, "learning_rate": 8.745281042943517e-06, "loss": 0.3589, "step": 258620 }, { "epoch": 1.5373504288745832, "grad_norm": 5.549936771392822, "learning_rate": 8.745143574845867e-06, "loss": 0.3911, "step": 258630 }, { "epoch": 1.5374098709512516, "grad_norm": 3.928067684173584, "learning_rate": 8.745006100298631e-06, "loss": 0.2954, "step": 258640 }, { "epoch": 1.5374693130279198, "grad_norm": 4.831490516662598, "learning_rate": 8.744868619302052e-06, "loss": 0.3747, "step": 258650 }, { "epoch": 1.5375287551045882, "grad_norm": 5.375893592834473, "learning_rate": 8.74473113185636e-06, "loss": 0.3505, "step": 258660 }, { "epoch": 1.5375881971812566, "grad_norm": 4.753620147705078, "learning_rate": 8.744593637961794e-06, "loss": 0.3486, "step": 258670 }, { "epoch": 1.537647639257925, "grad_norm": 9.134498596191406, "learning_rate": 8.74445613761859e-06, "loss": 0.3457, "step": 258680 }, { "epoch": 1.5377070813345934, "grad_norm": 3.2326622009277344, "learning_rate": 8.744318630826987e-06, "loss": 0.3524, "step": 258690 }, { "epoch": 1.5377665234112619, "grad_norm": 4.256784439086914, "learning_rate": 8.744181117587221e-06, "loss": 0.352, "step": 258700 }, { "epoch": 1.5378259654879303, "grad_norm": 5.234180450439453, "learning_rate": 8.744043597899528e-06, "loss": 0.3493, "step": 258710 }, { "epoch": 1.5378854075645987, "grad_norm": 4.764863014221191, "learning_rate": 8.743906071764146e-06, "loss": 0.3433, "step": 258720 }, { "epoch": 1.537944849641267, "grad_norm": 4.600494861602783, "learning_rate": 8.74376853918131e-06, "loss": 0.3434, "step": 258730 }, { "epoch": 1.5380042917179355, "grad_norm": 6.164270877838135, "learning_rate": 8.743631000151258e-06, "loss": 0.367, "step": 258740 }, { "epoch": 1.538063733794604, "grad_norm": 4.584936141967773, "learning_rate": 8.743493454674226e-06, "loss": 0.3492, "step": 258750 }, { "epoch": 1.5381231758712723, "grad_norm": 4.288726329803467, "learning_rate": 8.743355902750453e-06, "loss": 0.3368, "step": 258760 }, { "epoch": 1.5381826179479408, "grad_norm": 4.562821865081787, "learning_rate": 8.743218344380173e-06, "loss": 0.3439, "step": 258770 }, { "epoch": 1.5382420600246092, "grad_norm": 3.4477639198303223, "learning_rate": 8.743080779563625e-06, "loss": 0.3017, "step": 258780 }, { "epoch": 1.5383015021012774, "grad_norm": 5.597331523895264, "learning_rate": 8.742943208301046e-06, "loss": 0.382, "step": 258790 }, { "epoch": 1.5383609441779458, "grad_norm": 4.093056678771973, "learning_rate": 8.742805630592672e-06, "loss": 0.3246, "step": 258800 }, { "epoch": 1.5384203862546142, "grad_norm": 7.086940765380859, "learning_rate": 8.74266804643874e-06, "loss": 0.3484, "step": 258810 }, { "epoch": 1.5384798283312826, "grad_norm": 5.523016929626465, "learning_rate": 8.742530455839487e-06, "loss": 0.3725, "step": 258820 }, { "epoch": 1.538539270407951, "grad_norm": 4.567221164703369, "learning_rate": 8.74239285879515e-06, "loss": 0.3751, "step": 258830 }, { "epoch": 1.5385987124846192, "grad_norm": 6.603911399841309, "learning_rate": 8.742255255305965e-06, "loss": 0.3698, "step": 258840 }, { "epoch": 1.5386581545612876, "grad_norm": 4.894683837890625, "learning_rate": 8.742117645372172e-06, "loss": 0.3489, "step": 258850 }, { "epoch": 1.538717596637956, "grad_norm": 5.870779991149902, "learning_rate": 8.741980028994004e-06, "loss": 0.3537, "step": 258860 }, { "epoch": 1.5387770387146245, "grad_norm": 6.424056529998779, "learning_rate": 8.7418424061717e-06, "loss": 0.3473, "step": 258870 }, { "epoch": 1.5388364807912929, "grad_norm": 6.676653861999512, "learning_rate": 8.741704776905498e-06, "loss": 0.4167, "step": 258880 }, { "epoch": 1.5388959228679613, "grad_norm": 6.805614471435547, "learning_rate": 8.741567141195633e-06, "loss": 0.3743, "step": 258890 }, { "epoch": 1.5389553649446297, "grad_norm": 4.667736530303955, "learning_rate": 8.741429499042344e-06, "loss": 0.345, "step": 258900 }, { "epoch": 1.5390148070212981, "grad_norm": 4.130266189575195, "learning_rate": 8.741291850445866e-06, "loss": 0.3717, "step": 258910 }, { "epoch": 1.5390742490979665, "grad_norm": 5.716128826141357, "learning_rate": 8.741154195406438e-06, "loss": 0.3641, "step": 258920 }, { "epoch": 1.539133691174635, "grad_norm": 4.472263336181641, "learning_rate": 8.741016533924295e-06, "loss": 0.3409, "step": 258930 }, { "epoch": 1.5391931332513034, "grad_norm": 4.898244857788086, "learning_rate": 8.740878865999676e-06, "loss": 0.3169, "step": 258940 }, { "epoch": 1.5392525753279718, "grad_norm": 5.156275272369385, "learning_rate": 8.740741191632815e-06, "loss": 0.3621, "step": 258950 }, { "epoch": 1.5393120174046402, "grad_norm": 4.839425563812256, "learning_rate": 8.740603510823955e-06, "loss": 0.3232, "step": 258960 }, { "epoch": 1.5393714594813086, "grad_norm": 6.052577018737793, "learning_rate": 8.740465823573328e-06, "loss": 0.3448, "step": 258970 }, { "epoch": 1.5394309015579768, "grad_norm": 3.891352415084839, "learning_rate": 8.74032812988117e-06, "loss": 0.3788, "step": 258980 }, { "epoch": 1.5394903436346452, "grad_norm": 4.808452129364014, "learning_rate": 8.740190429747723e-06, "loss": 0.3819, "step": 258990 }, { "epoch": 1.5395497857113136, "grad_norm": 6.408614635467529, "learning_rate": 8.740052723173222e-06, "loss": 0.3802, "step": 259000 }, { "epoch": 1.539609227787982, "grad_norm": 4.996182918548584, "learning_rate": 8.739915010157904e-06, "loss": 0.3806, "step": 259010 }, { "epoch": 1.5396686698646502, "grad_norm": 5.599640369415283, "learning_rate": 8.739777290702007e-06, "loss": 0.3501, "step": 259020 }, { "epoch": 1.5397281119413186, "grad_norm": 4.827666282653809, "learning_rate": 8.739639564805766e-06, "loss": 0.3726, "step": 259030 }, { "epoch": 1.539787554017987, "grad_norm": 4.315455913543701, "learning_rate": 8.73950183246942e-06, "loss": 0.3563, "step": 259040 }, { "epoch": 1.5398469960946555, "grad_norm": 4.399487018585205, "learning_rate": 8.739364093693204e-06, "loss": 0.3377, "step": 259050 }, { "epoch": 1.5399064381713239, "grad_norm": 4.198240280151367, "learning_rate": 8.739226348477358e-06, "loss": 0.3464, "step": 259060 }, { "epoch": 1.5399658802479923, "grad_norm": 3.7576677799224854, "learning_rate": 8.739088596822118e-06, "loss": 0.3707, "step": 259070 }, { "epoch": 1.5400253223246607, "grad_norm": 4.577714443206787, "learning_rate": 8.738950838727722e-06, "loss": 0.3444, "step": 259080 }, { "epoch": 1.5400847644013291, "grad_norm": 4.991291522979736, "learning_rate": 8.738813074194405e-06, "loss": 0.3483, "step": 259090 }, { "epoch": 1.5401442064779975, "grad_norm": 5.3829240798950195, "learning_rate": 8.738675303222406e-06, "loss": 0.3846, "step": 259100 }, { "epoch": 1.540203648554666, "grad_norm": 7.066652774810791, "learning_rate": 8.738537525811962e-06, "loss": 0.3566, "step": 259110 }, { "epoch": 1.5402630906313344, "grad_norm": 6.61861515045166, "learning_rate": 8.738399741963313e-06, "loss": 0.3743, "step": 259120 }, { "epoch": 1.5403225327080028, "grad_norm": 5.356057643890381, "learning_rate": 8.73826195167669e-06, "loss": 0.3579, "step": 259130 }, { "epoch": 1.5403819747846712, "grad_norm": 3.7286717891693115, "learning_rate": 8.738124154952337e-06, "loss": 0.3315, "step": 259140 }, { "epoch": 1.5404414168613396, "grad_norm": 4.557412624359131, "learning_rate": 8.737986351790486e-06, "loss": 0.341, "step": 259150 }, { "epoch": 1.5405008589380078, "grad_norm": 3.666886568069458, "learning_rate": 8.737848542191377e-06, "loss": 0.3395, "step": 259160 }, { "epoch": 1.5405603010146762, "grad_norm": 5.048759937286377, "learning_rate": 8.737710726155247e-06, "loss": 0.3589, "step": 259170 }, { "epoch": 1.5406197430913446, "grad_norm": 5.499537944793701, "learning_rate": 8.737572903682334e-06, "loss": 0.3653, "step": 259180 }, { "epoch": 1.540679185168013, "grad_norm": 6.05750846862793, "learning_rate": 8.737435074772873e-06, "loss": 0.3533, "step": 259190 }, { "epoch": 1.5407386272446815, "grad_norm": 4.552273750305176, "learning_rate": 8.737297239427102e-06, "loss": 0.3451, "step": 259200 }, { "epoch": 1.5407980693213497, "grad_norm": 5.677950859069824, "learning_rate": 8.737159397645261e-06, "loss": 0.3629, "step": 259210 }, { "epoch": 1.540857511398018, "grad_norm": 5.44005012512207, "learning_rate": 8.737021549427586e-06, "loss": 0.3384, "step": 259220 }, { "epoch": 1.5409169534746865, "grad_norm": 3.3330352306365967, "learning_rate": 8.736883694774312e-06, "loss": 0.3577, "step": 259230 }, { "epoch": 1.540976395551355, "grad_norm": 5.1252312660217285, "learning_rate": 8.736745833685682e-06, "loss": 0.3708, "step": 259240 }, { "epoch": 1.5410358376280233, "grad_norm": 6.46595573425293, "learning_rate": 8.736607966161927e-06, "loss": 0.3747, "step": 259250 }, { "epoch": 1.5410952797046917, "grad_norm": 5.181931972503662, "learning_rate": 8.736470092203287e-06, "loss": 0.3904, "step": 259260 }, { "epoch": 1.5411547217813601, "grad_norm": 5.071918487548828, "learning_rate": 8.736332211810001e-06, "loss": 0.3281, "step": 259270 }, { "epoch": 1.5412141638580286, "grad_norm": 5.464134216308594, "learning_rate": 8.736194324982303e-06, "loss": 0.3392, "step": 259280 }, { "epoch": 1.541273605934697, "grad_norm": 3.855996608734131, "learning_rate": 8.736056431720436e-06, "loss": 0.3534, "step": 259290 }, { "epoch": 1.5413330480113654, "grad_norm": 7.123787879943848, "learning_rate": 8.735918532024631e-06, "loss": 0.3615, "step": 259300 }, { "epoch": 1.5413924900880338, "grad_norm": 4.872958660125732, "learning_rate": 8.735780625895129e-06, "loss": 0.3748, "step": 259310 }, { "epoch": 1.5414519321647022, "grad_norm": 4.259509086608887, "learning_rate": 8.735642713332169e-06, "loss": 0.3679, "step": 259320 }, { "epoch": 1.5415113742413706, "grad_norm": 5.264830589294434, "learning_rate": 8.735504794335986e-06, "loss": 0.3319, "step": 259330 }, { "epoch": 1.541570816318039, "grad_norm": 3.8226795196533203, "learning_rate": 8.735366868906816e-06, "loss": 0.3275, "step": 259340 }, { "epoch": 1.5416302583947072, "grad_norm": 4.2964301109313965, "learning_rate": 8.7352289370449e-06, "loss": 0.3075, "step": 259350 }, { "epoch": 1.5416897004713757, "grad_norm": 4.689841270446777, "learning_rate": 8.735090998750475e-06, "loss": 0.3745, "step": 259360 }, { "epoch": 1.541749142548044, "grad_norm": 7.180261611938477, "learning_rate": 8.734953054023777e-06, "loss": 0.4, "step": 259370 }, { "epoch": 1.5418085846247125, "grad_norm": 4.948429107666016, "learning_rate": 8.734815102865042e-06, "loss": 0.3752, "step": 259380 }, { "epoch": 1.5418680267013807, "grad_norm": 4.630152702331543, "learning_rate": 8.734677145274512e-06, "loss": 0.3221, "step": 259390 }, { "epoch": 1.541927468778049, "grad_norm": 5.507796764373779, "learning_rate": 8.734539181252422e-06, "loss": 0.3786, "step": 259400 }, { "epoch": 1.5419869108547175, "grad_norm": 5.014004707336426, "learning_rate": 8.73440121079901e-06, "loss": 0.3279, "step": 259410 }, { "epoch": 1.542046352931386, "grad_norm": 4.45638370513916, "learning_rate": 8.734263233914512e-06, "loss": 0.3477, "step": 259420 }, { "epoch": 1.5421057950080543, "grad_norm": 5.432981014251709, "learning_rate": 8.73412525059917e-06, "loss": 0.3768, "step": 259430 }, { "epoch": 1.5421652370847228, "grad_norm": 4.3130340576171875, "learning_rate": 8.733987260853216e-06, "loss": 0.3792, "step": 259440 }, { "epoch": 1.5422246791613912, "grad_norm": 4.829418182373047, "learning_rate": 8.733849264676893e-06, "loss": 0.3876, "step": 259450 }, { "epoch": 1.5422841212380596, "grad_norm": 5.4288330078125, "learning_rate": 8.733711262070433e-06, "loss": 0.3397, "step": 259460 }, { "epoch": 1.542343563314728, "grad_norm": 6.46856689453125, "learning_rate": 8.73357325303408e-06, "loss": 0.3712, "step": 259470 }, { "epoch": 1.5424030053913964, "grad_norm": 4.775481224060059, "learning_rate": 8.733435237568067e-06, "loss": 0.3888, "step": 259480 }, { "epoch": 1.5424624474680648, "grad_norm": 6.183586120605469, "learning_rate": 8.733297215672632e-06, "loss": 0.3684, "step": 259490 }, { "epoch": 1.5425218895447332, "grad_norm": 4.576695442199707, "learning_rate": 8.733159187348015e-06, "loss": 0.361, "step": 259500 }, { "epoch": 1.5425813316214017, "grad_norm": 6.034307956695557, "learning_rate": 8.73302115259445e-06, "loss": 0.3803, "step": 259510 }, { "epoch": 1.54264077369807, "grad_norm": 4.865149974822998, "learning_rate": 8.73288311141218e-06, "loss": 0.3147, "step": 259520 }, { "epoch": 1.5427002157747383, "grad_norm": 4.541135787963867, "learning_rate": 8.73274506380144e-06, "loss": 0.3516, "step": 259530 }, { "epoch": 1.5427596578514067, "grad_norm": 5.678318023681641, "learning_rate": 8.732607009762466e-06, "loss": 0.3532, "step": 259540 }, { "epoch": 1.542819099928075, "grad_norm": 5.9869160652160645, "learning_rate": 8.732468949295498e-06, "loss": 0.3365, "step": 259550 }, { "epoch": 1.5428785420047435, "grad_norm": 4.019567012786865, "learning_rate": 8.732330882400772e-06, "loss": 0.3098, "step": 259560 }, { "epoch": 1.542937984081412, "grad_norm": 5.410967826843262, "learning_rate": 8.73219280907853e-06, "loss": 0.3729, "step": 259570 }, { "epoch": 1.54299742615808, "grad_norm": 4.771038055419922, "learning_rate": 8.732054729329003e-06, "loss": 0.3449, "step": 259580 }, { "epoch": 1.5430568682347485, "grad_norm": 4.576104164123535, "learning_rate": 8.731916643152434e-06, "loss": 0.3573, "step": 259590 }, { "epoch": 1.543116310311417, "grad_norm": 6.715157985687256, "learning_rate": 8.73177855054906e-06, "loss": 0.3841, "step": 259600 }, { "epoch": 1.5431757523880854, "grad_norm": 5.311599254608154, "learning_rate": 8.731640451519118e-06, "loss": 0.3337, "step": 259610 }, { "epoch": 1.5432351944647538, "grad_norm": 5.0610432624816895, "learning_rate": 8.731502346062846e-06, "loss": 0.3701, "step": 259620 }, { "epoch": 1.5432946365414222, "grad_norm": 4.597486972808838, "learning_rate": 8.731364234180479e-06, "loss": 0.3576, "step": 259630 }, { "epoch": 1.5433540786180906, "grad_norm": 5.171154975891113, "learning_rate": 8.73122611587226e-06, "loss": 0.3691, "step": 259640 }, { "epoch": 1.543413520694759, "grad_norm": 4.115548610687256, "learning_rate": 8.731087991138425e-06, "loss": 0.3484, "step": 259650 }, { "epoch": 1.5434729627714274, "grad_norm": 4.873702049255371, "learning_rate": 8.73094985997921e-06, "loss": 0.3427, "step": 259660 }, { "epoch": 1.5435324048480958, "grad_norm": 4.979827404022217, "learning_rate": 8.730811722394854e-06, "loss": 0.3417, "step": 259670 }, { "epoch": 1.5435918469247643, "grad_norm": 4.553794860839844, "learning_rate": 8.730673578385596e-06, "loss": 0.324, "step": 259680 }, { "epoch": 1.5436512890014327, "grad_norm": 4.576889514923096, "learning_rate": 8.730535427951673e-06, "loss": 0.3492, "step": 259690 }, { "epoch": 1.543710731078101, "grad_norm": 4.803538799285889, "learning_rate": 8.730397271093322e-06, "loss": 0.3462, "step": 259700 }, { "epoch": 1.5437701731547695, "grad_norm": 5.473301887512207, "learning_rate": 8.730259107810783e-06, "loss": 0.3681, "step": 259710 }, { "epoch": 1.5438296152314377, "grad_norm": 5.646155834197998, "learning_rate": 8.730120938104291e-06, "loss": 0.3651, "step": 259720 }, { "epoch": 1.543889057308106, "grad_norm": 6.078362464904785, "learning_rate": 8.729982761974087e-06, "loss": 0.3225, "step": 259730 }, { "epoch": 1.5439484993847745, "grad_norm": 7.617842197418213, "learning_rate": 8.729844579420409e-06, "loss": 0.3433, "step": 259740 }, { "epoch": 1.544007941461443, "grad_norm": 6.383821964263916, "learning_rate": 8.729706390443491e-06, "loss": 0.329, "step": 259750 }, { "epoch": 1.5440673835381111, "grad_norm": 3.9031906127929688, "learning_rate": 8.729568195043574e-06, "loss": 0.3613, "step": 259760 }, { "epoch": 1.5441268256147795, "grad_norm": 4.2542266845703125, "learning_rate": 8.729429993220894e-06, "loss": 0.3431, "step": 259770 }, { "epoch": 1.544186267691448, "grad_norm": 4.967826843261719, "learning_rate": 8.729291784975693e-06, "loss": 0.3392, "step": 259780 }, { "epoch": 1.5442457097681164, "grad_norm": 3.497393846511841, "learning_rate": 8.729153570308206e-06, "loss": 0.3441, "step": 259790 }, { "epoch": 1.5443051518447848, "grad_norm": 5.710801124572754, "learning_rate": 8.729015349218672e-06, "loss": 0.3704, "step": 259800 }, { "epoch": 1.5443645939214532, "grad_norm": 5.656868934631348, "learning_rate": 8.728877121707329e-06, "loss": 0.3486, "step": 259810 }, { "epoch": 1.5444240359981216, "grad_norm": 4.380704402923584, "learning_rate": 8.728738887774414e-06, "loss": 0.3214, "step": 259820 }, { "epoch": 1.54448347807479, "grad_norm": 5.791842460632324, "learning_rate": 8.728600647420165e-06, "loss": 0.3742, "step": 259830 }, { "epoch": 1.5445429201514584, "grad_norm": 4.917672157287598, "learning_rate": 8.728462400644823e-06, "loss": 0.3227, "step": 259840 }, { "epoch": 1.5446023622281269, "grad_norm": 4.847977638244629, "learning_rate": 8.728324147448622e-06, "loss": 0.3224, "step": 259850 }, { "epoch": 1.5446618043047953, "grad_norm": 4.685305595397949, "learning_rate": 8.728185887831801e-06, "loss": 0.3827, "step": 259860 }, { "epoch": 1.5447212463814637, "grad_norm": 4.710657119750977, "learning_rate": 8.728047621794602e-06, "loss": 0.3524, "step": 259870 }, { "epoch": 1.544780688458132, "grad_norm": 4.241079330444336, "learning_rate": 8.727909349337258e-06, "loss": 0.3459, "step": 259880 }, { "epoch": 1.5448401305348005, "grad_norm": 5.009128093719482, "learning_rate": 8.727771070460011e-06, "loss": 0.3494, "step": 259890 }, { "epoch": 1.5448995726114687, "grad_norm": 4.754095077514648, "learning_rate": 8.727632785163096e-06, "loss": 0.3431, "step": 259900 }, { "epoch": 1.5449590146881371, "grad_norm": 4.787204265594482, "learning_rate": 8.727494493446752e-06, "loss": 0.3552, "step": 259910 }, { "epoch": 1.5450184567648055, "grad_norm": 4.027863025665283, "learning_rate": 8.72735619531122e-06, "loss": 0.3356, "step": 259920 }, { "epoch": 1.545077898841474, "grad_norm": 4.933455944061279, "learning_rate": 8.727217890756734e-06, "loss": 0.3595, "step": 259930 }, { "epoch": 1.5451373409181424, "grad_norm": 4.686739444732666, "learning_rate": 8.727079579783535e-06, "loss": 0.3232, "step": 259940 }, { "epoch": 1.5451967829948106, "grad_norm": 3.730424165725708, "learning_rate": 8.726941262391859e-06, "loss": 0.3445, "step": 259950 }, { "epoch": 1.545256225071479, "grad_norm": 5.59593391418457, "learning_rate": 8.726802938581947e-06, "loss": 0.3521, "step": 259960 }, { "epoch": 1.5453156671481474, "grad_norm": 5.880173206329346, "learning_rate": 8.726664608354034e-06, "loss": 0.3498, "step": 259970 }, { "epoch": 1.5453751092248158, "grad_norm": 4.922674655914307, "learning_rate": 8.726526271708362e-06, "loss": 0.3747, "step": 259980 }, { "epoch": 1.5454345513014842, "grad_norm": 6.079050540924072, "learning_rate": 8.726387928645166e-06, "loss": 0.3491, "step": 259990 }, { "epoch": 1.5454939933781526, "grad_norm": 6.664604187011719, "learning_rate": 8.726249579164685e-06, "loss": 0.3338, "step": 260000 }, { "epoch": 1.545553435454821, "grad_norm": 5.035144329071045, "learning_rate": 8.726111223267158e-06, "loss": 0.3543, "step": 260010 }, { "epoch": 1.5456128775314895, "grad_norm": 5.55925178527832, "learning_rate": 8.725972860952823e-06, "loss": 0.3558, "step": 260020 }, { "epoch": 1.5456723196081579, "grad_norm": 4.37276029586792, "learning_rate": 8.725834492221918e-06, "loss": 0.3193, "step": 260030 }, { "epoch": 1.5457317616848263, "grad_norm": 5.031432151794434, "learning_rate": 8.72569611707468e-06, "loss": 0.3516, "step": 260040 }, { "epoch": 1.5457912037614947, "grad_norm": 5.771453857421875, "learning_rate": 8.72555773551135e-06, "loss": 0.3418, "step": 260050 }, { "epoch": 1.5458506458381631, "grad_norm": 4.366854190826416, "learning_rate": 8.725419347532167e-06, "loss": 0.3438, "step": 260060 }, { "epoch": 1.5459100879148315, "grad_norm": 5.26619291305542, "learning_rate": 8.725280953137366e-06, "loss": 0.396, "step": 260070 }, { "epoch": 1.5459695299915, "grad_norm": 4.75000524520874, "learning_rate": 8.725142552327187e-06, "loss": 0.3337, "step": 260080 }, { "epoch": 1.5460289720681681, "grad_norm": 6.846249580383301, "learning_rate": 8.725004145101865e-06, "loss": 0.334, "step": 260090 }, { "epoch": 1.5460884141448366, "grad_norm": 4.5240583419799805, "learning_rate": 8.724865731461645e-06, "loss": 0.3446, "step": 260100 }, { "epoch": 1.546147856221505, "grad_norm": 5.465093612670898, "learning_rate": 8.72472731140676e-06, "loss": 0.3508, "step": 260110 }, { "epoch": 1.5462072982981734, "grad_norm": 3.7987236976623535, "learning_rate": 8.72458888493745e-06, "loss": 0.3498, "step": 260120 }, { "epoch": 1.5462667403748416, "grad_norm": 5.619712829589844, "learning_rate": 8.724450452053955e-06, "loss": 0.3216, "step": 260130 }, { "epoch": 1.54632618245151, "grad_norm": 4.2426581382751465, "learning_rate": 8.724312012756511e-06, "loss": 0.3778, "step": 260140 }, { "epoch": 1.5463856245281784, "grad_norm": 5.266399383544922, "learning_rate": 8.724173567045358e-06, "loss": 0.3702, "step": 260150 }, { "epoch": 1.5464450666048468, "grad_norm": 5.7817206382751465, "learning_rate": 8.724035114920733e-06, "loss": 0.353, "step": 260160 }, { "epoch": 1.5465045086815152, "grad_norm": 4.273777961730957, "learning_rate": 8.723896656382875e-06, "loss": 0.3107, "step": 260170 }, { "epoch": 1.5465639507581836, "grad_norm": 6.370200157165527, "learning_rate": 8.723758191432024e-06, "loss": 0.3663, "step": 260180 }, { "epoch": 1.546623392834852, "grad_norm": 4.276250839233398, "learning_rate": 8.723619720068415e-06, "loss": 0.328, "step": 260190 }, { "epoch": 1.5466828349115205, "grad_norm": 6.050050735473633, "learning_rate": 8.723481242292289e-06, "loss": 0.351, "step": 260200 }, { "epoch": 1.546742276988189, "grad_norm": 5.054330348968506, "learning_rate": 8.723342758103885e-06, "loss": 0.3392, "step": 260210 }, { "epoch": 1.5468017190648573, "grad_norm": 5.23643684387207, "learning_rate": 8.723204267503441e-06, "loss": 0.367, "step": 260220 }, { "epoch": 1.5468611611415257, "grad_norm": 3.7533037662506104, "learning_rate": 8.723065770491193e-06, "loss": 0.3353, "step": 260230 }, { "epoch": 1.5469206032181941, "grad_norm": 5.023320198059082, "learning_rate": 8.722927267067384e-06, "loss": 0.3341, "step": 260240 }, { "epoch": 1.5469800452948625, "grad_norm": 5.362346172332764, "learning_rate": 8.722788757232248e-06, "loss": 0.3426, "step": 260250 }, { "epoch": 1.547039487371531, "grad_norm": 5.344088554382324, "learning_rate": 8.722650240986027e-06, "loss": 0.3137, "step": 260260 }, { "epoch": 1.5470989294481992, "grad_norm": 4.2013139724731445, "learning_rate": 8.722511718328956e-06, "loss": 0.3506, "step": 260270 }, { "epoch": 1.5471583715248676, "grad_norm": 4.47124719619751, "learning_rate": 8.722373189261278e-06, "loss": 0.3068, "step": 260280 }, { "epoch": 1.547217813601536, "grad_norm": 5.266513347625732, "learning_rate": 8.722234653783228e-06, "loss": 0.3425, "step": 260290 }, { "epoch": 1.5472772556782044, "grad_norm": 5.20528507232666, "learning_rate": 8.722096111895046e-06, "loss": 0.3473, "step": 260300 }, { "epoch": 1.5473366977548728, "grad_norm": 5.119193077087402, "learning_rate": 8.721957563596971e-06, "loss": 0.3676, "step": 260310 }, { "epoch": 1.547396139831541, "grad_norm": 4.724347114562988, "learning_rate": 8.72181900888924e-06, "loss": 0.3378, "step": 260320 }, { "epoch": 1.5474555819082094, "grad_norm": 4.3328776359558105, "learning_rate": 8.721680447772094e-06, "loss": 0.3617, "step": 260330 }, { "epoch": 1.5475150239848778, "grad_norm": 4.70716667175293, "learning_rate": 8.721541880245768e-06, "loss": 0.3578, "step": 260340 }, { "epoch": 1.5475744660615463, "grad_norm": 5.167655944824219, "learning_rate": 8.721403306310504e-06, "loss": 0.3492, "step": 260350 }, { "epoch": 1.5476339081382147, "grad_norm": 3.212975263595581, "learning_rate": 8.72126472596654e-06, "loss": 0.3191, "step": 260360 }, { "epoch": 1.547693350214883, "grad_norm": 4.663278102874756, "learning_rate": 8.721126139214113e-06, "loss": 0.3415, "step": 260370 }, { "epoch": 1.5477527922915515, "grad_norm": 6.10021448135376, "learning_rate": 8.720987546053465e-06, "loss": 0.3723, "step": 260380 }, { "epoch": 1.54781223436822, "grad_norm": 3.9222753047943115, "learning_rate": 8.72084894648483e-06, "loss": 0.3322, "step": 260390 }, { "epoch": 1.5478716764448883, "grad_norm": 5.449613094329834, "learning_rate": 8.720710340508451e-06, "loss": 0.3566, "step": 260400 }, { "epoch": 1.5479311185215567, "grad_norm": 5.970459938049316, "learning_rate": 8.720571728124563e-06, "loss": 0.3983, "step": 260410 }, { "epoch": 1.5479905605982252, "grad_norm": 5.587202072143555, "learning_rate": 8.720433109333408e-06, "loss": 0.378, "step": 260420 }, { "epoch": 1.5480500026748936, "grad_norm": 4.8156046867370605, "learning_rate": 8.720294484135222e-06, "loss": 0.3199, "step": 260430 }, { "epoch": 1.548109444751562, "grad_norm": 4.693717002868652, "learning_rate": 8.720155852530247e-06, "loss": 0.347, "step": 260440 }, { "epoch": 1.5481688868282304, "grad_norm": 6.149562358856201, "learning_rate": 8.720017214518718e-06, "loss": 0.3559, "step": 260450 }, { "epoch": 1.5482283289048986, "grad_norm": 6.231698036193848, "learning_rate": 8.719878570100876e-06, "loss": 0.3592, "step": 260460 }, { "epoch": 1.548287770981567, "grad_norm": 4.569862365722656, "learning_rate": 8.719739919276959e-06, "loss": 0.3561, "step": 260470 }, { "epoch": 1.5483472130582354, "grad_norm": 6.581461429595947, "learning_rate": 8.719601262047206e-06, "loss": 0.3493, "step": 260480 }, { "epoch": 1.5484066551349038, "grad_norm": 4.717122554779053, "learning_rate": 8.719462598411856e-06, "loss": 0.2998, "step": 260490 }, { "epoch": 1.548466097211572, "grad_norm": 5.6072096824646, "learning_rate": 8.719323928371149e-06, "loss": 0.4048, "step": 260500 }, { "epoch": 1.5485255392882404, "grad_norm": 4.660084247589111, "learning_rate": 8.71918525192532e-06, "loss": 0.3357, "step": 260510 }, { "epoch": 1.5485849813649089, "grad_norm": 4.65321159362793, "learning_rate": 8.719046569074611e-06, "loss": 0.309, "step": 260520 }, { "epoch": 1.5486444234415773, "grad_norm": 5.313394546508789, "learning_rate": 8.718907879819261e-06, "loss": 0.3334, "step": 260530 }, { "epoch": 1.5487038655182457, "grad_norm": 5.300450325012207, "learning_rate": 8.718769184159508e-06, "loss": 0.3432, "step": 260540 }, { "epoch": 1.548763307594914, "grad_norm": 4.368021011352539, "learning_rate": 8.718630482095589e-06, "loss": 0.3848, "step": 260550 }, { "epoch": 1.5488227496715825, "grad_norm": 7.177157878875732, "learning_rate": 8.718491773627746e-06, "loss": 0.3413, "step": 260560 }, { "epoch": 1.548882191748251, "grad_norm": 4.313554286956787, "learning_rate": 8.718353058756217e-06, "loss": 0.3485, "step": 260570 }, { "epoch": 1.5489416338249193, "grad_norm": 5.285628318786621, "learning_rate": 8.718214337481239e-06, "loss": 0.3699, "step": 260580 }, { "epoch": 1.5490010759015878, "grad_norm": 5.535035133361816, "learning_rate": 8.718075609803051e-06, "loss": 0.363, "step": 260590 }, { "epoch": 1.5490605179782562, "grad_norm": 4.957712650299072, "learning_rate": 8.717936875721896e-06, "loss": 0.3612, "step": 260600 }, { "epoch": 1.5491199600549246, "grad_norm": 5.076618194580078, "learning_rate": 8.71779813523801e-06, "loss": 0.3339, "step": 260610 }, { "epoch": 1.549179402131593, "grad_norm": 3.4997305870056152, "learning_rate": 8.71765938835163e-06, "loss": 0.3433, "step": 260620 }, { "epoch": 1.5492388442082614, "grad_norm": 5.999391078948975, "learning_rate": 8.717520635062998e-06, "loss": 0.3367, "step": 260630 }, { "epoch": 1.5492982862849296, "grad_norm": 3.7343502044677734, "learning_rate": 8.717381875372352e-06, "loss": 0.3122, "step": 260640 }, { "epoch": 1.549357728361598, "grad_norm": 4.294251441955566, "learning_rate": 8.717243109279931e-06, "loss": 0.3449, "step": 260650 }, { "epoch": 1.5494171704382664, "grad_norm": 5.0113701820373535, "learning_rate": 8.717104336785972e-06, "loss": 0.3777, "step": 260660 }, { "epoch": 1.5494766125149348, "grad_norm": 4.676808834075928, "learning_rate": 8.716965557890718e-06, "loss": 0.3702, "step": 260670 }, { "epoch": 1.5495360545916033, "grad_norm": 4.407150745391846, "learning_rate": 8.716826772594406e-06, "loss": 0.3237, "step": 260680 }, { "epoch": 1.5495954966682715, "grad_norm": 4.58450984954834, "learning_rate": 8.716687980897274e-06, "loss": 0.3151, "step": 260690 }, { "epoch": 1.5496549387449399, "grad_norm": 5.838535308837891, "learning_rate": 8.716549182799562e-06, "loss": 0.358, "step": 260700 }, { "epoch": 1.5497143808216083, "grad_norm": 5.319748878479004, "learning_rate": 8.716410378301507e-06, "loss": 0.3086, "step": 260710 }, { "epoch": 1.5497738228982767, "grad_norm": 4.039284706115723, "learning_rate": 8.716271567403353e-06, "loss": 0.3144, "step": 260720 }, { "epoch": 1.5498332649749451, "grad_norm": 4.891817569732666, "learning_rate": 8.716132750105334e-06, "loss": 0.3142, "step": 260730 }, { "epoch": 1.5498927070516135, "grad_norm": 7.871729373931885, "learning_rate": 8.715993926407692e-06, "loss": 0.3492, "step": 260740 }, { "epoch": 1.549952149128282, "grad_norm": 4.2968010902404785, "learning_rate": 8.715855096310664e-06, "loss": 0.3255, "step": 260750 }, { "epoch": 1.5500115912049504, "grad_norm": 5.853773593902588, "learning_rate": 8.71571625981449e-06, "loss": 0.3545, "step": 260760 }, { "epoch": 1.5500710332816188, "grad_norm": 4.766226291656494, "learning_rate": 8.715577416919412e-06, "loss": 0.3684, "step": 260770 }, { "epoch": 1.5501304753582872, "grad_norm": 5.615771293640137, "learning_rate": 8.715438567625664e-06, "loss": 0.3418, "step": 260780 }, { "epoch": 1.5501899174349556, "grad_norm": 7.5584917068481445, "learning_rate": 8.715299711933488e-06, "loss": 0.3785, "step": 260790 }, { "epoch": 1.550249359511624, "grad_norm": 6.761753559112549, "learning_rate": 8.715160849843121e-06, "loss": 0.3912, "step": 260800 }, { "epoch": 1.5503088015882924, "grad_norm": 4.558095455169678, "learning_rate": 8.715021981354806e-06, "loss": 0.3796, "step": 260810 }, { "epoch": 1.5503682436649608, "grad_norm": 5.881048679351807, "learning_rate": 8.714883106468779e-06, "loss": 0.3749, "step": 260820 }, { "epoch": 1.550427685741629, "grad_norm": 3.915032148361206, "learning_rate": 8.714744225185281e-06, "loss": 0.3527, "step": 260830 }, { "epoch": 1.5504871278182975, "grad_norm": 7.2395339012146, "learning_rate": 8.714605337504548e-06, "loss": 0.3519, "step": 260840 }, { "epoch": 1.5505465698949659, "grad_norm": 5.592584133148193, "learning_rate": 8.714466443426823e-06, "loss": 0.3354, "step": 260850 }, { "epoch": 1.5506060119716343, "grad_norm": 6.327945232391357, "learning_rate": 8.714327542952344e-06, "loss": 0.3748, "step": 260860 }, { "epoch": 1.5506654540483025, "grad_norm": 4.451363563537598, "learning_rate": 8.71418863608135e-06, "loss": 0.3626, "step": 260870 }, { "epoch": 1.5507248961249709, "grad_norm": 8.364639282226562, "learning_rate": 8.714049722814077e-06, "loss": 0.3243, "step": 260880 }, { "epoch": 1.5507843382016393, "grad_norm": 4.526728630065918, "learning_rate": 8.71391080315077e-06, "loss": 0.3802, "step": 260890 }, { "epoch": 1.5508437802783077, "grad_norm": 4.831692218780518, "learning_rate": 8.713771877091663e-06, "loss": 0.3831, "step": 260900 }, { "epoch": 1.5509032223549761, "grad_norm": 5.082941055297852, "learning_rate": 8.713632944637001e-06, "loss": 0.3511, "step": 260910 }, { "epoch": 1.5509626644316445, "grad_norm": 5.045196533203125, "learning_rate": 8.713494005787018e-06, "loss": 0.3209, "step": 260920 }, { "epoch": 1.551022106508313, "grad_norm": 4.3914313316345215, "learning_rate": 8.713355060541957e-06, "loss": 0.3769, "step": 260930 }, { "epoch": 1.5510815485849814, "grad_norm": 4.724606990814209, "learning_rate": 8.713216108902052e-06, "loss": 0.3742, "step": 260940 }, { "epoch": 1.5511409906616498, "grad_norm": 4.323281288146973, "learning_rate": 8.713077150867549e-06, "loss": 0.338, "step": 260950 }, { "epoch": 1.5512004327383182, "grad_norm": 3.725767135620117, "learning_rate": 8.712938186438684e-06, "loss": 0.3202, "step": 260960 }, { "epoch": 1.5512598748149866, "grad_norm": 4.944276809692383, "learning_rate": 8.712799215615696e-06, "loss": 0.3293, "step": 260970 }, { "epoch": 1.551319316891655, "grad_norm": 5.960474014282227, "learning_rate": 8.712660238398822e-06, "loss": 0.3446, "step": 260980 }, { "epoch": 1.5513787589683234, "grad_norm": 6.980203628540039, "learning_rate": 8.712521254788306e-06, "loss": 0.3482, "step": 260990 }, { "epoch": 1.5514382010449919, "grad_norm": 5.207275867462158, "learning_rate": 8.712382264784387e-06, "loss": 0.3343, "step": 261000 }, { "epoch": 1.55149764312166, "grad_norm": 5.915952205657959, "learning_rate": 8.7122432683873e-06, "loss": 0.3337, "step": 261010 }, { "epoch": 1.5515570851983285, "grad_norm": 4.735951900482178, "learning_rate": 8.71210426559729e-06, "loss": 0.3824, "step": 261020 }, { "epoch": 1.5516165272749969, "grad_norm": 3.7086896896362305, "learning_rate": 8.711965256414591e-06, "loss": 0.3282, "step": 261030 }, { "epoch": 1.5516759693516653, "grad_norm": 6.454884052276611, "learning_rate": 8.711826240839447e-06, "loss": 0.3503, "step": 261040 }, { "epoch": 1.5517354114283337, "grad_norm": 6.08038854598999, "learning_rate": 8.711687218872093e-06, "loss": 0.371, "step": 261050 }, { "epoch": 1.551794853505002, "grad_norm": 5.238519191741943, "learning_rate": 8.711548190512773e-06, "loss": 0.3574, "step": 261060 }, { "epoch": 1.5518542955816703, "grad_norm": 4.300561428070068, "learning_rate": 8.711409155761724e-06, "loss": 0.306, "step": 261070 }, { "epoch": 1.5519137376583387, "grad_norm": 5.477790355682373, "learning_rate": 8.711270114619184e-06, "loss": 0.3442, "step": 261080 }, { "epoch": 1.5519731797350071, "grad_norm": 4.29390287399292, "learning_rate": 8.711131067085396e-06, "loss": 0.3343, "step": 261090 }, { "epoch": 1.5520326218116756, "grad_norm": 4.36182165145874, "learning_rate": 8.710992013160596e-06, "loss": 0.3312, "step": 261100 }, { "epoch": 1.552092063888344, "grad_norm": 4.918492317199707, "learning_rate": 8.710852952845027e-06, "loss": 0.3425, "step": 261110 }, { "epoch": 1.5521515059650124, "grad_norm": 5.40129280090332, "learning_rate": 8.710713886138924e-06, "loss": 0.3699, "step": 261120 }, { "epoch": 1.5522109480416808, "grad_norm": 4.284684181213379, "learning_rate": 8.71057481304253e-06, "loss": 0.3329, "step": 261130 }, { "epoch": 1.5522703901183492, "grad_norm": 4.635473251342773, "learning_rate": 8.710435733556083e-06, "loss": 0.3623, "step": 261140 }, { "epoch": 1.5523298321950176, "grad_norm": 5.876473903656006, "learning_rate": 8.710296647679824e-06, "loss": 0.347, "step": 261150 }, { "epoch": 1.552389274271686, "grad_norm": 4.602342128753662, "learning_rate": 8.71015755541399e-06, "loss": 0.3463, "step": 261160 }, { "epoch": 1.5524487163483545, "grad_norm": 5.278497219085693, "learning_rate": 8.710018456758823e-06, "loss": 0.3679, "step": 261170 }, { "epoch": 1.5525081584250229, "grad_norm": 4.627243995666504, "learning_rate": 8.70987935171456e-06, "loss": 0.3446, "step": 261180 }, { "epoch": 1.5525676005016913, "grad_norm": 5.203805446624756, "learning_rate": 8.709740240281443e-06, "loss": 0.3627, "step": 261190 }, { "epoch": 1.5526270425783595, "grad_norm": 4.675380229949951, "learning_rate": 8.709601122459712e-06, "loss": 0.3681, "step": 261200 }, { "epoch": 1.552686484655028, "grad_norm": 5.126776218414307, "learning_rate": 8.709461998249604e-06, "loss": 0.3541, "step": 261210 }, { "epoch": 1.5527459267316963, "grad_norm": 4.079960823059082, "learning_rate": 8.70932286765136e-06, "loss": 0.3515, "step": 261220 }, { "epoch": 1.5528053688083647, "grad_norm": 3.983041763305664, "learning_rate": 8.70918373066522e-06, "loss": 0.3191, "step": 261230 }, { "epoch": 1.552864810885033, "grad_norm": 4.231263160705566, "learning_rate": 8.709044587291422e-06, "loss": 0.3327, "step": 261240 }, { "epoch": 1.5529242529617013, "grad_norm": 4.17917537689209, "learning_rate": 8.708905437530208e-06, "loss": 0.3241, "step": 261250 }, { "epoch": 1.5529836950383697, "grad_norm": 5.054193019866943, "learning_rate": 8.708766281381815e-06, "loss": 0.3565, "step": 261260 }, { "epoch": 1.5530431371150382, "grad_norm": 4.8076934814453125, "learning_rate": 8.708627118846485e-06, "loss": 0.346, "step": 261270 }, { "epoch": 1.5531025791917066, "grad_norm": 5.441963195800781, "learning_rate": 8.708487949924456e-06, "loss": 0.3802, "step": 261280 }, { "epoch": 1.553162021268375, "grad_norm": 4.811967849731445, "learning_rate": 8.708348774615966e-06, "loss": 0.3531, "step": 261290 }, { "epoch": 1.5532214633450434, "grad_norm": 5.021958351135254, "learning_rate": 8.708209592921261e-06, "loss": 0.3627, "step": 261300 }, { "epoch": 1.5532809054217118, "grad_norm": 4.867743968963623, "learning_rate": 8.708070404840575e-06, "loss": 0.3691, "step": 261310 }, { "epoch": 1.5533403474983802, "grad_norm": 5.546723365783691, "learning_rate": 8.70793121037415e-06, "loss": 0.3429, "step": 261320 }, { "epoch": 1.5533997895750487, "grad_norm": 5.188997268676758, "learning_rate": 8.707792009522222e-06, "loss": 0.3248, "step": 261330 }, { "epoch": 1.553459231651717, "grad_norm": 4.554448127746582, "learning_rate": 8.707652802285037e-06, "loss": 0.3701, "step": 261340 }, { "epoch": 1.5535186737283855, "grad_norm": 6.830495834350586, "learning_rate": 8.707513588662831e-06, "loss": 0.3751, "step": 261350 }, { "epoch": 1.553578115805054, "grad_norm": 6.535480976104736, "learning_rate": 8.707374368655843e-06, "loss": 0.3551, "step": 261360 }, { "epoch": 1.5536375578817223, "grad_norm": 4.544994831085205, "learning_rate": 8.707235142264314e-06, "loss": 0.3247, "step": 261370 }, { "epoch": 1.5536969999583905, "grad_norm": 6.186124801635742, "learning_rate": 8.707095909488486e-06, "loss": 0.3789, "step": 261380 }, { "epoch": 1.553756442035059, "grad_norm": 5.421939849853516, "learning_rate": 8.706956670328594e-06, "loss": 0.3242, "step": 261390 }, { "epoch": 1.5538158841117273, "grad_norm": 4.385322093963623, "learning_rate": 8.706817424784881e-06, "loss": 0.3461, "step": 261400 }, { "epoch": 1.5538753261883957, "grad_norm": 5.69984245300293, "learning_rate": 8.706678172857587e-06, "loss": 0.3421, "step": 261410 }, { "epoch": 1.5539347682650642, "grad_norm": 5.046504497528076, "learning_rate": 8.70653891454695e-06, "loss": 0.3436, "step": 261420 }, { "epoch": 1.5539942103417324, "grad_norm": 5.1276092529296875, "learning_rate": 8.70639964985321e-06, "loss": 0.3717, "step": 261430 }, { "epoch": 1.5540536524184008, "grad_norm": 4.897794246673584, "learning_rate": 8.706260378776609e-06, "loss": 0.3376, "step": 261440 }, { "epoch": 1.5541130944950692, "grad_norm": 5.049663066864014, "learning_rate": 8.706121101317386e-06, "loss": 0.3444, "step": 261450 }, { "epoch": 1.5541725365717376, "grad_norm": 5.70307731628418, "learning_rate": 8.705981817475779e-06, "loss": 0.361, "step": 261460 }, { "epoch": 1.554231978648406, "grad_norm": 7.05000638961792, "learning_rate": 8.705842527252028e-06, "loss": 0.3636, "step": 261470 }, { "epoch": 1.5542914207250744, "grad_norm": 3.3524370193481445, "learning_rate": 8.705703230646375e-06, "loss": 0.3646, "step": 261480 }, { "epoch": 1.5543508628017428, "grad_norm": 4.256131649017334, "learning_rate": 8.70556392765906e-06, "loss": 0.3508, "step": 261490 }, { "epoch": 1.5544103048784113, "grad_norm": 5.102805137634277, "learning_rate": 8.705424618290321e-06, "loss": 0.3683, "step": 261500 }, { "epoch": 1.5544697469550797, "grad_norm": 4.911311626434326, "learning_rate": 8.705285302540399e-06, "loss": 0.3684, "step": 261510 }, { "epoch": 1.554529189031748, "grad_norm": 4.770995616912842, "learning_rate": 8.705145980409532e-06, "loss": 0.3637, "step": 261520 }, { "epoch": 1.5545886311084165, "grad_norm": 4.491992950439453, "learning_rate": 8.705006651897964e-06, "loss": 0.3661, "step": 261530 }, { "epoch": 1.554648073185085, "grad_norm": 5.982619762420654, "learning_rate": 8.704867317005931e-06, "loss": 0.3729, "step": 261540 }, { "epoch": 1.5547075152617533, "grad_norm": 5.347405910491943, "learning_rate": 8.704727975733675e-06, "loss": 0.3539, "step": 261550 }, { "epoch": 1.5547669573384217, "grad_norm": 6.44752311706543, "learning_rate": 8.704588628081436e-06, "loss": 0.3514, "step": 261560 }, { "epoch": 1.55482639941509, "grad_norm": 3.8576154708862305, "learning_rate": 8.704449274049451e-06, "loss": 0.2814, "step": 261570 }, { "epoch": 1.5548858414917583, "grad_norm": 4.36926794052124, "learning_rate": 8.704309913637965e-06, "loss": 0.3534, "step": 261580 }, { "epoch": 1.5549452835684268, "grad_norm": 4.849981784820557, "learning_rate": 8.704170546847212e-06, "loss": 0.3223, "step": 261590 }, { "epoch": 1.5550047256450952, "grad_norm": 3.996166467666626, "learning_rate": 8.704031173677438e-06, "loss": 0.3521, "step": 261600 }, { "epoch": 1.5550641677217634, "grad_norm": 5.381114959716797, "learning_rate": 8.70389179412888e-06, "loss": 0.3601, "step": 261610 }, { "epoch": 1.5551236097984318, "grad_norm": 5.387823581695557, "learning_rate": 8.703752408201779e-06, "loss": 0.3391, "step": 261620 }, { "epoch": 1.5551830518751002, "grad_norm": 4.397706508636475, "learning_rate": 8.703613015896372e-06, "loss": 0.3299, "step": 261630 }, { "epoch": 1.5552424939517686, "grad_norm": 3.7625277042388916, "learning_rate": 8.703473617212904e-06, "loss": 0.3347, "step": 261640 }, { "epoch": 1.555301936028437, "grad_norm": 4.333590030670166, "learning_rate": 8.703334212151612e-06, "loss": 0.365, "step": 261650 }, { "epoch": 1.5553613781051054, "grad_norm": 5.284379959106445, "learning_rate": 8.703194800712737e-06, "loss": 0.3506, "step": 261660 }, { "epoch": 1.5554208201817739, "grad_norm": 6.163937091827393, "learning_rate": 8.703055382896517e-06, "loss": 0.3438, "step": 261670 }, { "epoch": 1.5554802622584423, "grad_norm": 4.353270053863525, "learning_rate": 8.702915958703195e-06, "loss": 0.3939, "step": 261680 }, { "epoch": 1.5555397043351107, "grad_norm": 5.322847366333008, "learning_rate": 8.70277652813301e-06, "loss": 0.3036, "step": 261690 }, { "epoch": 1.555599146411779, "grad_norm": 6.278406620025635, "learning_rate": 8.702637091186202e-06, "loss": 0.3986, "step": 261700 }, { "epoch": 1.5556585884884475, "grad_norm": 4.351674556732178, "learning_rate": 8.702497647863011e-06, "loss": 0.3361, "step": 261710 }, { "epoch": 1.555718030565116, "grad_norm": 5.495206832885742, "learning_rate": 8.702358198163676e-06, "loss": 0.339, "step": 261720 }, { "epoch": 1.5557774726417843, "grad_norm": 5.935900688171387, "learning_rate": 8.70221874208844e-06, "loss": 0.3627, "step": 261730 }, { "epoch": 1.5558369147184528, "grad_norm": 4.627386569976807, "learning_rate": 8.702079279637541e-06, "loss": 0.3646, "step": 261740 }, { "epoch": 1.555896356795121, "grad_norm": 5.105022430419922, "learning_rate": 8.70193981081122e-06, "loss": 0.3402, "step": 261750 }, { "epoch": 1.5559557988717894, "grad_norm": 5.225512504577637, "learning_rate": 8.701800335609716e-06, "loss": 0.3706, "step": 261760 }, { "epoch": 1.5560152409484578, "grad_norm": 5.539919376373291, "learning_rate": 8.701660854033272e-06, "loss": 0.3336, "step": 261770 }, { "epoch": 1.5560746830251262, "grad_norm": 4.85695219039917, "learning_rate": 8.701521366082124e-06, "loss": 0.3374, "step": 261780 }, { "epoch": 1.5561341251017946, "grad_norm": 4.7016472816467285, "learning_rate": 8.701381871756515e-06, "loss": 0.3481, "step": 261790 }, { "epoch": 1.5561935671784628, "grad_norm": 6.730844974517822, "learning_rate": 8.701242371056686e-06, "loss": 0.3413, "step": 261800 }, { "epoch": 1.5562530092551312, "grad_norm": 5.225490093231201, "learning_rate": 8.701102863982875e-06, "loss": 0.3355, "step": 261810 }, { "epoch": 1.5563124513317996, "grad_norm": 5.614591598510742, "learning_rate": 8.700963350535324e-06, "loss": 0.3698, "step": 261820 }, { "epoch": 1.556371893408468, "grad_norm": 4.221651077270508, "learning_rate": 8.700823830714274e-06, "loss": 0.3371, "step": 261830 }, { "epoch": 1.5564313354851365, "grad_norm": 4.752955913543701, "learning_rate": 8.700684304519962e-06, "loss": 0.3349, "step": 261840 }, { "epoch": 1.5564907775618049, "grad_norm": 5.181159019470215, "learning_rate": 8.70054477195263e-06, "loss": 0.3714, "step": 261850 }, { "epoch": 1.5565502196384733, "grad_norm": 6.722122669219971, "learning_rate": 8.700405233012519e-06, "loss": 0.3814, "step": 261860 }, { "epoch": 1.5566096617151417, "grad_norm": 4.498288154602051, "learning_rate": 8.700265687699868e-06, "loss": 0.3281, "step": 261870 }, { "epoch": 1.5566691037918101, "grad_norm": 3.9368999004364014, "learning_rate": 8.700126136014919e-06, "loss": 0.3379, "step": 261880 }, { "epoch": 1.5567285458684785, "grad_norm": 6.195059299468994, "learning_rate": 8.699986577957908e-06, "loss": 0.3516, "step": 261890 }, { "epoch": 1.556787987945147, "grad_norm": 4.482211112976074, "learning_rate": 8.699847013529082e-06, "loss": 0.3365, "step": 261900 }, { "epoch": 1.5568474300218154, "grad_norm": 5.599018096923828, "learning_rate": 8.699707442728678e-06, "loss": 0.3446, "step": 261910 }, { "epoch": 1.5569068720984838, "grad_norm": 5.214020729064941, "learning_rate": 8.699567865556935e-06, "loss": 0.3592, "step": 261920 }, { "epoch": 1.5569663141751522, "grad_norm": 4.514019012451172, "learning_rate": 8.699428282014095e-06, "loss": 0.3436, "step": 261930 }, { "epoch": 1.5570257562518204, "grad_norm": 5.1317667961120605, "learning_rate": 8.699288692100398e-06, "loss": 0.3226, "step": 261940 }, { "epoch": 1.5570851983284888, "grad_norm": 4.06815242767334, "learning_rate": 8.699149095816086e-06, "loss": 0.3618, "step": 261950 }, { "epoch": 1.5571446404051572, "grad_norm": 5.4053826332092285, "learning_rate": 8.699009493161397e-06, "loss": 0.3496, "step": 261960 }, { "epoch": 1.5572040824818256, "grad_norm": 6.809720516204834, "learning_rate": 8.69886988413657e-06, "loss": 0.3632, "step": 261970 }, { "epoch": 1.5572635245584938, "grad_norm": 6.179295539855957, "learning_rate": 8.69873026874185e-06, "loss": 0.3508, "step": 261980 }, { "epoch": 1.5573229666351622, "grad_norm": 6.679162502288818, "learning_rate": 8.698590646977475e-06, "loss": 0.3318, "step": 261990 }, { "epoch": 1.5573824087118306, "grad_norm": 5.373998165130615, "learning_rate": 8.698451018843685e-06, "loss": 0.3802, "step": 262000 }, { "epoch": 1.557441850788499, "grad_norm": 4.2170281410217285, "learning_rate": 8.698311384340723e-06, "loss": 0.3318, "step": 262010 }, { "epoch": 1.5575012928651675, "grad_norm": 4.176820755004883, "learning_rate": 8.698171743468826e-06, "loss": 0.3492, "step": 262020 }, { "epoch": 1.557560734941836, "grad_norm": 4.758420944213867, "learning_rate": 8.698032096228235e-06, "loss": 0.3714, "step": 262030 }, { "epoch": 1.5576201770185043, "grad_norm": 5.670612812042236, "learning_rate": 8.697892442619193e-06, "loss": 0.3511, "step": 262040 }, { "epoch": 1.5576796190951727, "grad_norm": 4.182048797607422, "learning_rate": 8.697752782641937e-06, "loss": 0.3355, "step": 262050 }, { "epoch": 1.5577390611718411, "grad_norm": 4.7852983474731445, "learning_rate": 8.697613116296712e-06, "loss": 0.3253, "step": 262060 }, { "epoch": 1.5577985032485095, "grad_norm": 5.8381218910217285, "learning_rate": 8.697473443583755e-06, "loss": 0.3459, "step": 262070 }, { "epoch": 1.557857945325178, "grad_norm": 3.7175216674804688, "learning_rate": 8.697333764503308e-06, "loss": 0.3525, "step": 262080 }, { "epoch": 1.5579173874018464, "grad_norm": 4.979298114776611, "learning_rate": 8.69719407905561e-06, "loss": 0.3344, "step": 262090 }, { "epoch": 1.5579768294785148, "grad_norm": 4.635833740234375, "learning_rate": 8.697054387240903e-06, "loss": 0.3538, "step": 262100 }, { "epoch": 1.5580362715551832, "grad_norm": 4.443904876708984, "learning_rate": 8.696914689059429e-06, "loss": 0.3044, "step": 262110 }, { "epoch": 1.5580957136318514, "grad_norm": 5.993476867675781, "learning_rate": 8.696774984511424e-06, "loss": 0.3168, "step": 262120 }, { "epoch": 1.5581551557085198, "grad_norm": 4.5888824462890625, "learning_rate": 8.696635273597132e-06, "loss": 0.3528, "step": 262130 }, { "epoch": 1.5582145977851882, "grad_norm": 5.811859130859375, "learning_rate": 8.696495556316795e-06, "loss": 0.3678, "step": 262140 }, { "epoch": 1.5582740398618566, "grad_norm": 5.03615665435791, "learning_rate": 8.696355832670649e-06, "loss": 0.3429, "step": 262150 }, { "epoch": 1.558333481938525, "grad_norm": 4.168208599090576, "learning_rate": 8.696216102658938e-06, "loss": 0.3762, "step": 262160 }, { "epoch": 1.5583929240151932, "grad_norm": 5.028194427490234, "learning_rate": 8.696076366281902e-06, "loss": 0.3429, "step": 262170 }, { "epoch": 1.5584523660918617, "grad_norm": 5.168144226074219, "learning_rate": 8.695936623539783e-06, "loss": 0.4019, "step": 262180 }, { "epoch": 1.55851180816853, "grad_norm": 6.421457290649414, "learning_rate": 8.695796874432818e-06, "loss": 0.3681, "step": 262190 }, { "epoch": 1.5585712502451985, "grad_norm": 4.233029365539551, "learning_rate": 8.695657118961252e-06, "loss": 0.3367, "step": 262200 }, { "epoch": 1.558630692321867, "grad_norm": 4.482472896575928, "learning_rate": 8.695517357125323e-06, "loss": 0.3232, "step": 262210 }, { "epoch": 1.5586901343985353, "grad_norm": 6.158020496368408, "learning_rate": 8.695377588925271e-06, "loss": 0.377, "step": 262220 }, { "epoch": 1.5587495764752037, "grad_norm": 4.052829742431641, "learning_rate": 8.695237814361337e-06, "loss": 0.3075, "step": 262230 }, { "epoch": 1.5588090185518721, "grad_norm": 6.28220272064209, "learning_rate": 8.695098033433765e-06, "loss": 0.361, "step": 262240 }, { "epoch": 1.5588684606285406, "grad_norm": 4.384746074676514, "learning_rate": 8.694958246142791e-06, "loss": 0.3639, "step": 262250 }, { "epoch": 1.558927902705209, "grad_norm": 4.501104831695557, "learning_rate": 8.69481845248866e-06, "loss": 0.3998, "step": 262260 }, { "epoch": 1.5589873447818774, "grad_norm": 4.543695449829102, "learning_rate": 8.69467865247161e-06, "loss": 0.3421, "step": 262270 }, { "epoch": 1.5590467868585458, "grad_norm": 6.142723083496094, "learning_rate": 8.694538846091882e-06, "loss": 0.3424, "step": 262280 }, { "epoch": 1.5591062289352142, "grad_norm": 5.235957622528076, "learning_rate": 8.694399033349718e-06, "loss": 0.3585, "step": 262290 }, { "epoch": 1.5591656710118826, "grad_norm": 3.87664532661438, "learning_rate": 8.694259214245358e-06, "loss": 0.3261, "step": 262300 }, { "epoch": 1.5592251130885508, "grad_norm": 5.33515739440918, "learning_rate": 8.694119388779043e-06, "loss": 0.3414, "step": 262310 }, { "epoch": 1.5592845551652192, "grad_norm": 5.634721279144287, "learning_rate": 8.693979556951013e-06, "loss": 0.375, "step": 262320 }, { "epoch": 1.5593439972418877, "grad_norm": 6.107908725738525, "learning_rate": 8.69383971876151e-06, "loss": 0.3548, "step": 262330 }, { "epoch": 1.559403439318556, "grad_norm": 3.922691822052002, "learning_rate": 8.693699874210774e-06, "loss": 0.34, "step": 262340 }, { "epoch": 1.5594628813952243, "grad_norm": 5.41508150100708, "learning_rate": 8.693560023299045e-06, "loss": 0.339, "step": 262350 }, { "epoch": 1.5595223234718927, "grad_norm": 5.969839096069336, "learning_rate": 8.693420166026566e-06, "loss": 0.374, "step": 262360 }, { "epoch": 1.559581765548561, "grad_norm": 6.694385051727295, "learning_rate": 8.693280302393577e-06, "loss": 0.3442, "step": 262370 }, { "epoch": 1.5596412076252295, "grad_norm": 4.268919467926025, "learning_rate": 8.693140432400317e-06, "loss": 0.3383, "step": 262380 }, { "epoch": 1.559700649701898, "grad_norm": 4.765628814697266, "learning_rate": 8.693000556047031e-06, "loss": 0.3179, "step": 262390 }, { "epoch": 1.5597600917785663, "grad_norm": 5.952585220336914, "learning_rate": 8.692860673333956e-06, "loss": 0.3634, "step": 262400 }, { "epoch": 1.5598195338552348, "grad_norm": 4.575984001159668, "learning_rate": 8.692720784261335e-06, "loss": 0.3408, "step": 262410 }, { "epoch": 1.5598789759319032, "grad_norm": 4.683300018310547, "learning_rate": 8.692580888829408e-06, "loss": 0.3751, "step": 262420 }, { "epoch": 1.5599384180085716, "grad_norm": 4.090432643890381, "learning_rate": 8.692440987038416e-06, "loss": 0.3383, "step": 262430 }, { "epoch": 1.55999786008524, "grad_norm": 7.548013687133789, "learning_rate": 8.692301078888599e-06, "loss": 0.357, "step": 262440 }, { "epoch": 1.5600573021619084, "grad_norm": 6.381507873535156, "learning_rate": 8.692161164380202e-06, "loss": 0.3711, "step": 262450 }, { "epoch": 1.5601167442385768, "grad_norm": 5.928642749786377, "learning_rate": 8.69202124351346e-06, "loss": 0.3227, "step": 262460 }, { "epoch": 1.5601761863152452, "grad_norm": 3.4901199340820312, "learning_rate": 8.691881316288618e-06, "loss": 0.3446, "step": 262470 }, { "epoch": 1.5602356283919137, "grad_norm": 6.1919708251953125, "learning_rate": 8.691741382705915e-06, "loss": 0.3733, "step": 262480 }, { "epoch": 1.5602950704685818, "grad_norm": 4.8976616859436035, "learning_rate": 8.691601442765593e-06, "loss": 0.3283, "step": 262490 }, { "epoch": 1.5603545125452503, "grad_norm": 5.968334674835205, "learning_rate": 8.691461496467894e-06, "loss": 0.3761, "step": 262500 }, { "epoch": 1.5604139546219187, "grad_norm": 6.113463878631592, "learning_rate": 8.691321543813058e-06, "loss": 0.363, "step": 262510 }, { "epoch": 1.560473396698587, "grad_norm": 5.957183837890625, "learning_rate": 8.691181584801325e-06, "loss": 0.3296, "step": 262520 }, { "epoch": 1.5605328387752555, "grad_norm": 4.985801696777344, "learning_rate": 8.691041619432937e-06, "loss": 0.3344, "step": 262530 }, { "epoch": 1.5605922808519237, "grad_norm": 5.785022258758545, "learning_rate": 8.690901647708134e-06, "loss": 0.4024, "step": 262540 }, { "epoch": 1.5606517229285921, "grad_norm": 6.142150402069092, "learning_rate": 8.69076166962716e-06, "loss": 0.3908, "step": 262550 }, { "epoch": 1.5607111650052605, "grad_norm": 4.042313575744629, "learning_rate": 8.690621685190252e-06, "loss": 0.3377, "step": 262560 }, { "epoch": 1.560770607081929, "grad_norm": 4.439048767089844, "learning_rate": 8.690481694397655e-06, "loss": 0.3366, "step": 262570 }, { "epoch": 1.5608300491585974, "grad_norm": 4.818658828735352, "learning_rate": 8.690341697249607e-06, "loss": 0.3574, "step": 262580 }, { "epoch": 1.5608894912352658, "grad_norm": 4.247861385345459, "learning_rate": 8.69020169374635e-06, "loss": 0.3398, "step": 262590 }, { "epoch": 1.5609489333119342, "grad_norm": 6.813750267028809, "learning_rate": 8.690061683888125e-06, "loss": 0.3542, "step": 262600 }, { "epoch": 1.5610083753886026, "grad_norm": 5.3913092613220215, "learning_rate": 8.689921667675175e-06, "loss": 0.3558, "step": 262610 }, { "epoch": 1.561067817465271, "grad_norm": 5.635314464569092, "learning_rate": 8.689781645107739e-06, "loss": 0.3334, "step": 262620 }, { "epoch": 1.5611272595419394, "grad_norm": 5.1613450050354, "learning_rate": 8.689641616186057e-06, "loss": 0.3479, "step": 262630 }, { "epoch": 1.5611867016186078, "grad_norm": 5.376539707183838, "learning_rate": 8.689501580910376e-06, "loss": 0.3452, "step": 262640 }, { "epoch": 1.5612461436952763, "grad_norm": 4.781767845153809, "learning_rate": 8.68936153928093e-06, "loss": 0.3387, "step": 262650 }, { "epoch": 1.5613055857719447, "grad_norm": 6.346310138702393, "learning_rate": 8.689221491297963e-06, "loss": 0.3412, "step": 262660 }, { "epoch": 1.561365027848613, "grad_norm": 6.0912885665893555, "learning_rate": 8.689081436961717e-06, "loss": 0.3481, "step": 262670 }, { "epoch": 1.5614244699252813, "grad_norm": 4.914464950561523, "learning_rate": 8.688941376272433e-06, "loss": 0.3542, "step": 262680 }, { "epoch": 1.5614839120019497, "grad_norm": 5.885212421417236, "learning_rate": 8.688801309230353e-06, "loss": 0.3542, "step": 262690 }, { "epoch": 1.561543354078618, "grad_norm": 5.159574031829834, "learning_rate": 8.688661235835713e-06, "loss": 0.3328, "step": 262700 }, { "epoch": 1.5616027961552865, "grad_norm": 4.712855815887451, "learning_rate": 8.688521156088762e-06, "loss": 0.3117, "step": 262710 }, { "epoch": 1.5616622382319547, "grad_norm": 6.6391191482543945, "learning_rate": 8.688381069989737e-06, "loss": 0.3107, "step": 262720 }, { "epoch": 1.5617216803086231, "grad_norm": 6.2325005531311035, "learning_rate": 8.688240977538878e-06, "loss": 0.3812, "step": 262730 }, { "epoch": 1.5617811223852915, "grad_norm": 4.578217029571533, "learning_rate": 8.688100878736429e-06, "loss": 0.3448, "step": 262740 }, { "epoch": 1.56184056446196, "grad_norm": 5.700848579406738, "learning_rate": 8.68796077358263e-06, "loss": 0.3539, "step": 262750 }, { "epoch": 1.5619000065386284, "grad_norm": 4.980753421783447, "learning_rate": 8.687820662077724e-06, "loss": 0.3449, "step": 262760 }, { "epoch": 1.5619594486152968, "grad_norm": 5.1764655113220215, "learning_rate": 8.687680544221948e-06, "loss": 0.344, "step": 262770 }, { "epoch": 1.5620188906919652, "grad_norm": 5.483603477478027, "learning_rate": 8.687540420015548e-06, "loss": 0.365, "step": 262780 }, { "epoch": 1.5620783327686336, "grad_norm": 4.691564559936523, "learning_rate": 8.687400289458764e-06, "loss": 0.344, "step": 262790 }, { "epoch": 1.562137774845302, "grad_norm": 4.142924785614014, "learning_rate": 8.687260152551834e-06, "loss": 0.3632, "step": 262800 }, { "epoch": 1.5621972169219704, "grad_norm": 4.560054302215576, "learning_rate": 8.687120009295004e-06, "loss": 0.3489, "step": 262810 }, { "epoch": 1.5622566589986389, "grad_norm": 5.076569080352783, "learning_rate": 8.686979859688515e-06, "loss": 0.3507, "step": 262820 }, { "epoch": 1.5623161010753073, "grad_norm": 5.01682186126709, "learning_rate": 8.686839703732604e-06, "loss": 0.3716, "step": 262830 }, { "epoch": 1.5623755431519757, "grad_norm": 6.134175777435303, "learning_rate": 8.686699541427517e-06, "loss": 0.3338, "step": 262840 }, { "epoch": 1.562434985228644, "grad_norm": 4.5576395988464355, "learning_rate": 8.686559372773491e-06, "loss": 0.3598, "step": 262850 }, { "epoch": 1.5624944273053123, "grad_norm": 5.236208438873291, "learning_rate": 8.686419197770772e-06, "loss": 0.3286, "step": 262860 }, { "epoch": 1.5625538693819807, "grad_norm": 3.7529399394989014, "learning_rate": 8.6862790164196e-06, "loss": 0.3017, "step": 262870 }, { "epoch": 1.5626133114586491, "grad_norm": 6.158917427062988, "learning_rate": 8.686138828720214e-06, "loss": 0.3599, "step": 262880 }, { "epoch": 1.5626727535353175, "grad_norm": 5.38067626953125, "learning_rate": 8.685998634672857e-06, "loss": 0.3301, "step": 262890 }, { "epoch": 1.562732195611986, "grad_norm": 5.951984405517578, "learning_rate": 8.685858434277773e-06, "loss": 0.3475, "step": 262900 }, { "epoch": 1.5627916376886541, "grad_norm": 5.567246437072754, "learning_rate": 8.685718227535198e-06, "loss": 0.3663, "step": 262910 }, { "epoch": 1.5628510797653226, "grad_norm": 4.090653896331787, "learning_rate": 8.685578014445378e-06, "loss": 0.3379, "step": 262920 }, { "epoch": 1.562910521841991, "grad_norm": 6.511590480804443, "learning_rate": 8.68543779500855e-06, "loss": 0.3625, "step": 262930 }, { "epoch": 1.5629699639186594, "grad_norm": 5.886556625366211, "learning_rate": 8.685297569224961e-06, "loss": 0.3316, "step": 262940 }, { "epoch": 1.5630294059953278, "grad_norm": 5.609210968017578, "learning_rate": 8.685157337094852e-06, "loss": 0.3431, "step": 262950 }, { "epoch": 1.5630888480719962, "grad_norm": 4.192655086517334, "learning_rate": 8.68501709861846e-06, "loss": 0.3402, "step": 262960 }, { "epoch": 1.5631482901486646, "grad_norm": 6.197451591491699, "learning_rate": 8.684876853796027e-06, "loss": 0.3535, "step": 262970 }, { "epoch": 1.563207732225333, "grad_norm": 5.630110263824463, "learning_rate": 8.6847366026278e-06, "loss": 0.3287, "step": 262980 }, { "epoch": 1.5632671743020015, "grad_norm": 4.855064392089844, "learning_rate": 8.684596345114015e-06, "loss": 0.3795, "step": 262990 }, { "epoch": 1.5633266163786699, "grad_norm": 5.563204765319824, "learning_rate": 8.684456081254914e-06, "loss": 0.3568, "step": 263000 }, { "epoch": 1.5633860584553383, "grad_norm": 4.922842979431152, "learning_rate": 8.684315811050742e-06, "loss": 0.3143, "step": 263010 }, { "epoch": 1.5634455005320067, "grad_norm": 4.814973831176758, "learning_rate": 8.68417553450174e-06, "loss": 0.2926, "step": 263020 }, { "epoch": 1.5635049426086751, "grad_norm": 6.003058910369873, "learning_rate": 8.684035251608145e-06, "loss": 0.3511, "step": 263030 }, { "epoch": 1.5635643846853435, "grad_norm": 4.733210563659668, "learning_rate": 8.683894962370204e-06, "loss": 0.3571, "step": 263040 }, { "epoch": 1.5636238267620117, "grad_norm": 4.540000915527344, "learning_rate": 8.683754666788155e-06, "loss": 0.3228, "step": 263050 }, { "epoch": 1.5636832688386801, "grad_norm": 5.857832431793213, "learning_rate": 8.683614364862242e-06, "loss": 0.3813, "step": 263060 }, { "epoch": 1.5637427109153486, "grad_norm": 6.985666275024414, "learning_rate": 8.683474056592705e-06, "loss": 0.3454, "step": 263070 }, { "epoch": 1.563802152992017, "grad_norm": 4.48007869720459, "learning_rate": 8.683333741979785e-06, "loss": 0.3608, "step": 263080 }, { "epoch": 1.5638615950686852, "grad_norm": 4.328696250915527, "learning_rate": 8.683193421023726e-06, "loss": 0.3411, "step": 263090 }, { "epoch": 1.5639210371453536, "grad_norm": 6.474086284637451, "learning_rate": 8.68305309372477e-06, "loss": 0.3829, "step": 263100 }, { "epoch": 1.563980479222022, "grad_norm": 5.11341667175293, "learning_rate": 8.682912760083154e-06, "loss": 0.3494, "step": 263110 }, { "epoch": 1.5640399212986904, "grad_norm": 5.442784309387207, "learning_rate": 8.682772420099124e-06, "loss": 0.3326, "step": 263120 }, { "epoch": 1.5640993633753588, "grad_norm": 6.133039951324463, "learning_rate": 8.68263207377292e-06, "loss": 0.3564, "step": 263130 }, { "epoch": 1.5641588054520272, "grad_norm": 5.835700511932373, "learning_rate": 8.682491721104787e-06, "loss": 0.3308, "step": 263140 }, { "epoch": 1.5642182475286956, "grad_norm": 7.539418697357178, "learning_rate": 8.682351362094961e-06, "loss": 0.3286, "step": 263150 }, { "epoch": 1.564277689605364, "grad_norm": 4.0332112312316895, "learning_rate": 8.682210996743687e-06, "loss": 0.3421, "step": 263160 }, { "epoch": 1.5643371316820325, "grad_norm": 4.690665245056152, "learning_rate": 8.682070625051206e-06, "loss": 0.3357, "step": 263170 }, { "epoch": 1.564396573758701, "grad_norm": 5.214815616607666, "learning_rate": 8.681930247017761e-06, "loss": 0.3492, "step": 263180 }, { "epoch": 1.5644560158353693, "grad_norm": 5.445830345153809, "learning_rate": 8.681789862643592e-06, "loss": 0.3865, "step": 263190 }, { "epoch": 1.5645154579120377, "grad_norm": 5.624214172363281, "learning_rate": 8.681649471928944e-06, "loss": 0.3742, "step": 263200 }, { "epoch": 1.5645748999887061, "grad_norm": 5.395421504974365, "learning_rate": 8.681509074874053e-06, "loss": 0.3019, "step": 263210 }, { "epoch": 1.5646343420653746, "grad_norm": 3.940735101699829, "learning_rate": 8.681368671479166e-06, "loss": 0.3662, "step": 263220 }, { "epoch": 1.5646937841420427, "grad_norm": 5.293108940124512, "learning_rate": 8.681228261744522e-06, "loss": 0.3265, "step": 263230 }, { "epoch": 1.5647532262187112, "grad_norm": 4.931204795837402, "learning_rate": 8.681087845670364e-06, "loss": 0.3933, "step": 263240 }, { "epoch": 1.5648126682953796, "grad_norm": 4.809643268585205, "learning_rate": 8.680947423256933e-06, "loss": 0.3877, "step": 263250 }, { "epoch": 1.564872110372048, "grad_norm": 5.110173225402832, "learning_rate": 8.680806994504473e-06, "loss": 0.3397, "step": 263260 }, { "epoch": 1.5649315524487164, "grad_norm": 6.389183044433594, "learning_rate": 8.680666559413222e-06, "loss": 0.3537, "step": 263270 }, { "epoch": 1.5649909945253846, "grad_norm": 5.682868957519531, "learning_rate": 8.680526117983425e-06, "loss": 0.3497, "step": 263280 }, { "epoch": 1.565050436602053, "grad_norm": 5.178840637207031, "learning_rate": 8.680385670215324e-06, "loss": 0.3788, "step": 263290 }, { "epoch": 1.5651098786787214, "grad_norm": 6.440403461456299, "learning_rate": 8.680245216109157e-06, "loss": 0.4026, "step": 263300 }, { "epoch": 1.5651693207553898, "grad_norm": 5.043726444244385, "learning_rate": 8.680104755665171e-06, "loss": 0.3284, "step": 263310 }, { "epoch": 1.5652287628320583, "grad_norm": 4.62738037109375, "learning_rate": 8.679964288883605e-06, "loss": 0.3358, "step": 263320 }, { "epoch": 1.5652882049087267, "grad_norm": 4.285745620727539, "learning_rate": 8.679823815764701e-06, "loss": 0.3811, "step": 263330 }, { "epoch": 1.565347646985395, "grad_norm": 5.228123188018799, "learning_rate": 8.679683336308702e-06, "loss": 0.3922, "step": 263340 }, { "epoch": 1.5654070890620635, "grad_norm": 5.328349590301514, "learning_rate": 8.679542850515849e-06, "loss": 0.3389, "step": 263350 }, { "epoch": 1.565466531138732, "grad_norm": 5.489261150360107, "learning_rate": 8.679402358386385e-06, "loss": 0.3752, "step": 263360 }, { "epoch": 1.5655259732154003, "grad_norm": 4.233407974243164, "learning_rate": 8.679261859920549e-06, "loss": 0.3274, "step": 263370 }, { "epoch": 1.5655854152920687, "grad_norm": 4.170445442199707, "learning_rate": 8.679121355118586e-06, "loss": 0.3598, "step": 263380 }, { "epoch": 1.5656448573687372, "grad_norm": 4.170062065124512, "learning_rate": 8.678980843980738e-06, "loss": 0.3384, "step": 263390 }, { "epoch": 1.5657042994454056, "grad_norm": 3.9667232036590576, "learning_rate": 8.678840326507244e-06, "loss": 0.3276, "step": 263400 }, { "epoch": 1.5657637415220738, "grad_norm": 5.387746334075928, "learning_rate": 8.67869980269835e-06, "loss": 0.404, "step": 263410 }, { "epoch": 1.5658231835987422, "grad_norm": 4.595165252685547, "learning_rate": 8.678559272554294e-06, "loss": 0.3746, "step": 263420 }, { "epoch": 1.5658826256754106, "grad_norm": 4.072630882263184, "learning_rate": 8.678418736075323e-06, "loss": 0.3235, "step": 263430 }, { "epoch": 1.565942067752079, "grad_norm": 5.444760799407959, "learning_rate": 8.678278193261673e-06, "loss": 0.3639, "step": 263440 }, { "epoch": 1.5660015098287474, "grad_norm": 5.608520030975342, "learning_rate": 8.678137644113591e-06, "loss": 0.363, "step": 263450 }, { "epoch": 1.5660609519054156, "grad_norm": 8.627775192260742, "learning_rate": 8.677997088631316e-06, "loss": 0.3415, "step": 263460 }, { "epoch": 1.566120393982084, "grad_norm": 4.848359107971191, "learning_rate": 8.677856526815091e-06, "loss": 0.3574, "step": 263470 }, { "epoch": 1.5661798360587524, "grad_norm": 6.01948881149292, "learning_rate": 8.67771595866516e-06, "loss": 0.3575, "step": 263480 }, { "epoch": 1.5662392781354209, "grad_norm": 4.905383586883545, "learning_rate": 8.677575384181762e-06, "loss": 0.3489, "step": 263490 }, { "epoch": 1.5662987202120893, "grad_norm": 4.244132995605469, "learning_rate": 8.67743480336514e-06, "loss": 0.3638, "step": 263500 }, { "epoch": 1.5663581622887577, "grad_norm": 4.525743007659912, "learning_rate": 8.677294216215537e-06, "loss": 0.3407, "step": 263510 }, { "epoch": 1.566417604365426, "grad_norm": 6.169864654541016, "learning_rate": 8.677153622733194e-06, "loss": 0.3372, "step": 263520 }, { "epoch": 1.5664770464420945, "grad_norm": 4.472573280334473, "learning_rate": 8.677013022918354e-06, "loss": 0.3745, "step": 263530 }, { "epoch": 1.566536488518763, "grad_norm": 4.235527038574219, "learning_rate": 8.67687241677126e-06, "loss": 0.3477, "step": 263540 }, { "epoch": 1.5665959305954313, "grad_norm": 5.9231743812561035, "learning_rate": 8.676731804292152e-06, "loss": 0.3508, "step": 263550 }, { "epoch": 1.5666553726720998, "grad_norm": 4.246403694152832, "learning_rate": 8.676591185481274e-06, "loss": 0.3272, "step": 263560 }, { "epoch": 1.5667148147487682, "grad_norm": 5.888554096221924, "learning_rate": 8.676450560338867e-06, "loss": 0.3399, "step": 263570 }, { "epoch": 1.5667742568254366, "grad_norm": 5.479062080383301, "learning_rate": 8.676309928865171e-06, "loss": 0.3349, "step": 263580 }, { "epoch": 1.566833698902105, "grad_norm": 4.6207685470581055, "learning_rate": 8.676169291060435e-06, "loss": 0.325, "step": 263590 }, { "epoch": 1.5668931409787732, "grad_norm": 5.170670509338379, "learning_rate": 8.676028646924893e-06, "loss": 0.3401, "step": 263600 }, { "epoch": 1.5669525830554416, "grad_norm": 4.933128833770752, "learning_rate": 8.675887996458792e-06, "loss": 0.3456, "step": 263610 }, { "epoch": 1.56701202513211, "grad_norm": 4.7405266761779785, "learning_rate": 8.675747339662374e-06, "loss": 0.3501, "step": 263620 }, { "epoch": 1.5670714672087784, "grad_norm": 3.969069004058838, "learning_rate": 8.675606676535881e-06, "loss": 0.3545, "step": 263630 }, { "epoch": 1.5671309092854468, "grad_norm": 5.1643781661987305, "learning_rate": 8.675466007079554e-06, "loss": 0.3293, "step": 263640 }, { "epoch": 1.567190351362115, "grad_norm": 5.795694828033447, "learning_rate": 8.675325331293635e-06, "loss": 0.3351, "step": 263650 }, { "epoch": 1.5672497934387835, "grad_norm": 6.43562126159668, "learning_rate": 8.675184649178369e-06, "loss": 0.3505, "step": 263660 }, { "epoch": 1.5673092355154519, "grad_norm": 5.228232383728027, "learning_rate": 8.675043960733997e-06, "loss": 0.3362, "step": 263670 }, { "epoch": 1.5673686775921203, "grad_norm": 5.0042266845703125, "learning_rate": 8.67490326596076e-06, "loss": 0.3456, "step": 263680 }, { "epoch": 1.5674281196687887, "grad_norm": 5.032217025756836, "learning_rate": 8.6747625648589e-06, "loss": 0.3463, "step": 263690 }, { "epoch": 1.5674875617454571, "grad_norm": 5.5456132888793945, "learning_rate": 8.674621857428661e-06, "loss": 0.373, "step": 263700 }, { "epoch": 1.5675470038221255, "grad_norm": 6.266397953033447, "learning_rate": 8.674481143670284e-06, "loss": 0.354, "step": 263710 }, { "epoch": 1.567606445898794, "grad_norm": 5.6392717361450195, "learning_rate": 8.674340423584013e-06, "loss": 0.3175, "step": 263720 }, { "epoch": 1.5676658879754624, "grad_norm": 4.247036457061768, "learning_rate": 8.67419969717009e-06, "loss": 0.334, "step": 263730 }, { "epoch": 1.5677253300521308, "grad_norm": 6.664214611053467, "learning_rate": 8.674058964428755e-06, "loss": 0.3482, "step": 263740 }, { "epoch": 1.5677847721287992, "grad_norm": 5.8549346923828125, "learning_rate": 8.673918225360254e-06, "loss": 0.3819, "step": 263750 }, { "epoch": 1.5678442142054676, "grad_norm": 3.8775174617767334, "learning_rate": 8.673777479964826e-06, "loss": 0.3834, "step": 263760 }, { "epoch": 1.567903656282136, "grad_norm": 4.519149303436279, "learning_rate": 8.673636728242715e-06, "loss": 0.3562, "step": 263770 }, { "epoch": 1.5679630983588042, "grad_norm": 6.967744827270508, "learning_rate": 8.673495970194164e-06, "loss": 0.4101, "step": 263780 }, { "epoch": 1.5680225404354726, "grad_norm": 5.57485818862915, "learning_rate": 8.673355205819414e-06, "loss": 0.3725, "step": 263790 }, { "epoch": 1.568081982512141, "grad_norm": 4.981348037719727, "learning_rate": 8.67321443511871e-06, "loss": 0.3468, "step": 263800 }, { "epoch": 1.5681414245888095, "grad_norm": 5.196776866912842, "learning_rate": 8.673073658092288e-06, "loss": 0.2989, "step": 263810 }, { "epoch": 1.5682008666654779, "grad_norm": 6.098941802978516, "learning_rate": 8.672932874740398e-06, "loss": 0.3293, "step": 263820 }, { "epoch": 1.568260308742146, "grad_norm": 6.116456508636475, "learning_rate": 8.67279208506328e-06, "loss": 0.3497, "step": 263830 }, { "epoch": 1.5683197508188145, "grad_norm": 4.6756110191345215, "learning_rate": 8.672651289061174e-06, "loss": 0.3432, "step": 263840 }, { "epoch": 1.5683791928954829, "grad_norm": 5.2860565185546875, "learning_rate": 8.672510486734326e-06, "loss": 0.3522, "step": 263850 }, { "epoch": 1.5684386349721513, "grad_norm": 5.421048164367676, "learning_rate": 8.672369678082975e-06, "loss": 0.3513, "step": 263860 }, { "epoch": 1.5684980770488197, "grad_norm": 7.160788536071777, "learning_rate": 8.672228863107366e-06, "loss": 0.3542, "step": 263870 }, { "epoch": 1.5685575191254881, "grad_norm": 4.262103080749512, "learning_rate": 8.672088041807742e-06, "loss": 0.3613, "step": 263880 }, { "epoch": 1.5686169612021565, "grad_norm": 3.6689586639404297, "learning_rate": 8.671947214184342e-06, "loss": 0.3336, "step": 263890 }, { "epoch": 1.568676403278825, "grad_norm": 4.050418853759766, "learning_rate": 8.67180638023741e-06, "loss": 0.3577, "step": 263900 }, { "epoch": 1.5687358453554934, "grad_norm": 6.192570686340332, "learning_rate": 8.671665539967193e-06, "loss": 0.3038, "step": 263910 }, { "epoch": 1.5687952874321618, "grad_norm": 5.71290922164917, "learning_rate": 8.671524693373927e-06, "loss": 0.3478, "step": 263920 }, { "epoch": 1.5688547295088302, "grad_norm": 4.254999160766602, "learning_rate": 8.671383840457859e-06, "loss": 0.3257, "step": 263930 }, { "epoch": 1.5689141715854986, "grad_norm": 6.046544551849365, "learning_rate": 8.671242981219228e-06, "loss": 0.3624, "step": 263940 }, { "epoch": 1.568973613662167, "grad_norm": 5.521550178527832, "learning_rate": 8.671102115658281e-06, "loss": 0.3401, "step": 263950 }, { "epoch": 1.5690330557388354, "grad_norm": 4.232819557189941, "learning_rate": 8.670961243775256e-06, "loss": 0.3041, "step": 263960 }, { "epoch": 1.5690924978155036, "grad_norm": 5.846439838409424, "learning_rate": 8.670820365570399e-06, "loss": 0.3612, "step": 263970 }, { "epoch": 1.569151939892172, "grad_norm": 4.6282124519348145, "learning_rate": 8.67067948104395e-06, "loss": 0.3578, "step": 263980 }, { "epoch": 1.5692113819688405, "grad_norm": 4.086646556854248, "learning_rate": 8.670538590196156e-06, "loss": 0.3731, "step": 263990 }, { "epoch": 1.5692708240455089, "grad_norm": 4.342926025390625, "learning_rate": 8.670397693027254e-06, "loss": 0.3301, "step": 264000 }, { "epoch": 1.5693302661221773, "grad_norm": 5.433058261871338, "learning_rate": 8.67025678953749e-06, "loss": 0.3352, "step": 264010 }, { "epoch": 1.5693897081988455, "grad_norm": 4.712745189666748, "learning_rate": 8.670115879727104e-06, "loss": 0.3145, "step": 264020 }, { "epoch": 1.569449150275514, "grad_norm": 6.12605619430542, "learning_rate": 8.669974963596343e-06, "loss": 0.3555, "step": 264030 }, { "epoch": 1.5695085923521823, "grad_norm": 5.553964138031006, "learning_rate": 8.669834041145446e-06, "loss": 0.3588, "step": 264040 }, { "epoch": 1.5695680344288507, "grad_norm": 6.640691757202148, "learning_rate": 8.669693112374657e-06, "loss": 0.3795, "step": 264050 }, { "epoch": 1.5696274765055191, "grad_norm": 5.150139331817627, "learning_rate": 8.669552177284219e-06, "loss": 0.3576, "step": 264060 }, { "epoch": 1.5696869185821876, "grad_norm": 6.435564994812012, "learning_rate": 8.669411235874375e-06, "loss": 0.3878, "step": 264070 }, { "epoch": 1.569746360658856, "grad_norm": 4.8704633712768555, "learning_rate": 8.669270288145367e-06, "loss": 0.3581, "step": 264080 }, { "epoch": 1.5698058027355244, "grad_norm": 5.883113861083984, "learning_rate": 8.669129334097436e-06, "loss": 0.3459, "step": 264090 }, { "epoch": 1.5698652448121928, "grad_norm": 6.711334705352783, "learning_rate": 8.668988373730826e-06, "loss": 0.345, "step": 264100 }, { "epoch": 1.5699246868888612, "grad_norm": 4.762378215789795, "learning_rate": 8.668847407045783e-06, "loss": 0.3691, "step": 264110 }, { "epoch": 1.5699841289655296, "grad_norm": 6.541594982147217, "learning_rate": 8.668706434042546e-06, "loss": 0.3236, "step": 264120 }, { "epoch": 1.570043571042198, "grad_norm": 7.628197193145752, "learning_rate": 8.668565454721358e-06, "loss": 0.3638, "step": 264130 }, { "epoch": 1.5701030131188665, "grad_norm": 4.725068092346191, "learning_rate": 8.668424469082464e-06, "loss": 0.3533, "step": 264140 }, { "epoch": 1.5701624551955347, "grad_norm": 5.329288482666016, "learning_rate": 8.668283477126103e-06, "loss": 0.3166, "step": 264150 }, { "epoch": 1.570221897272203, "grad_norm": 5.7565813064575195, "learning_rate": 8.668142478852522e-06, "loss": 0.3772, "step": 264160 }, { "epoch": 1.5702813393488715, "grad_norm": 5.456167697906494, "learning_rate": 8.668001474261962e-06, "loss": 0.3366, "step": 264170 }, { "epoch": 1.57034078142554, "grad_norm": 5.7024993896484375, "learning_rate": 8.667860463354665e-06, "loss": 0.3377, "step": 264180 }, { "epoch": 1.5704002235022083, "grad_norm": 5.3014631271362305, "learning_rate": 8.667719446130876e-06, "loss": 0.3603, "step": 264190 }, { "epoch": 1.5704596655788765, "grad_norm": 5.794694900512695, "learning_rate": 8.667578422590834e-06, "loss": 0.346, "step": 264200 }, { "epoch": 1.570519107655545, "grad_norm": 5.050912857055664, "learning_rate": 8.667437392734785e-06, "loss": 0.3831, "step": 264210 }, { "epoch": 1.5705785497322133, "grad_norm": 5.1852545738220215, "learning_rate": 8.667296356562973e-06, "loss": 0.3332, "step": 264220 }, { "epoch": 1.5706379918088818, "grad_norm": 4.414313316345215, "learning_rate": 8.667155314075638e-06, "loss": 0.3284, "step": 264230 }, { "epoch": 1.5706974338855502, "grad_norm": 5.067963600158691, "learning_rate": 8.667014265273023e-06, "loss": 0.3511, "step": 264240 }, { "epoch": 1.5707568759622186, "grad_norm": 3.920180320739746, "learning_rate": 8.666873210155374e-06, "loss": 0.356, "step": 264250 }, { "epoch": 1.570816318038887, "grad_norm": 5.968817234039307, "learning_rate": 8.666732148722931e-06, "loss": 0.3428, "step": 264260 }, { "epoch": 1.5708757601155554, "grad_norm": 5.321745872497559, "learning_rate": 8.666591080975938e-06, "loss": 0.3343, "step": 264270 }, { "epoch": 1.5709352021922238, "grad_norm": 5.424629211425781, "learning_rate": 8.666450006914637e-06, "loss": 0.3411, "step": 264280 }, { "epoch": 1.5709946442688922, "grad_norm": 4.869030952453613, "learning_rate": 8.666308926539272e-06, "loss": 0.363, "step": 264290 }, { "epoch": 1.5710540863455607, "grad_norm": 5.660684108734131, "learning_rate": 8.666167839850086e-06, "loss": 0.3398, "step": 264300 }, { "epoch": 1.571113528422229, "grad_norm": 5.695190906524658, "learning_rate": 8.666026746847321e-06, "loss": 0.3503, "step": 264310 }, { "epoch": 1.5711729704988975, "grad_norm": 6.555342197418213, "learning_rate": 8.66588564753122e-06, "loss": 0.3397, "step": 264320 }, { "epoch": 1.571232412575566, "grad_norm": 5.975964546203613, "learning_rate": 8.665744541902026e-06, "loss": 0.3511, "step": 264330 }, { "epoch": 1.571291854652234, "grad_norm": 5.964962005615234, "learning_rate": 8.665603429959984e-06, "loss": 0.3579, "step": 264340 }, { "epoch": 1.5713512967289025, "grad_norm": 5.664371013641357, "learning_rate": 8.665462311705334e-06, "loss": 0.3457, "step": 264350 }, { "epoch": 1.571410738805571, "grad_norm": 3.831611156463623, "learning_rate": 8.665321187138322e-06, "loss": 0.3216, "step": 264360 }, { "epoch": 1.5714701808822393, "grad_norm": 5.256392478942871, "learning_rate": 8.66518005625919e-06, "loss": 0.3355, "step": 264370 }, { "epoch": 1.5715296229589077, "grad_norm": 5.115385055541992, "learning_rate": 8.66503891906818e-06, "loss": 0.3538, "step": 264380 }, { "epoch": 1.571589065035576, "grad_norm": 4.825108051300049, "learning_rate": 8.664897775565536e-06, "loss": 0.3591, "step": 264390 }, { "epoch": 1.5716485071122444, "grad_norm": 4.632442474365234, "learning_rate": 8.664756625751499e-06, "loss": 0.3227, "step": 264400 }, { "epoch": 1.5717079491889128, "grad_norm": 5.808621883392334, "learning_rate": 8.664615469626316e-06, "loss": 0.344, "step": 264410 }, { "epoch": 1.5717673912655812, "grad_norm": 4.526769161224365, "learning_rate": 8.664474307190226e-06, "loss": 0.3475, "step": 264420 }, { "epoch": 1.5718268333422496, "grad_norm": 4.787616729736328, "learning_rate": 8.664333138443474e-06, "loss": 0.3325, "step": 264430 }, { "epoch": 1.571886275418918, "grad_norm": 6.124383449554443, "learning_rate": 8.664191963386305e-06, "loss": 0.3673, "step": 264440 }, { "epoch": 1.5719457174955864, "grad_norm": 5.092389106750488, "learning_rate": 8.66405078201896e-06, "loss": 0.3147, "step": 264450 }, { "epoch": 1.5720051595722548, "grad_norm": 4.983735084533691, "learning_rate": 8.66390959434168e-06, "loss": 0.3733, "step": 264460 }, { "epoch": 1.5720646016489233, "grad_norm": 5.466298580169678, "learning_rate": 8.663768400354713e-06, "loss": 0.3621, "step": 264470 }, { "epoch": 1.5721240437255917, "grad_norm": 5.771085262298584, "learning_rate": 8.6636272000583e-06, "loss": 0.3351, "step": 264480 }, { "epoch": 1.57218348580226, "grad_norm": 4.891274929046631, "learning_rate": 8.663485993452682e-06, "loss": 0.3866, "step": 264490 }, { "epoch": 1.5722429278789285, "grad_norm": 4.901971340179443, "learning_rate": 8.663344780538104e-06, "loss": 0.3292, "step": 264500 }, { "epoch": 1.572302369955597, "grad_norm": 4.5170111656188965, "learning_rate": 8.66320356131481e-06, "loss": 0.3379, "step": 264510 }, { "epoch": 1.572361812032265, "grad_norm": 3.9358396530151367, "learning_rate": 8.663062335783042e-06, "loss": 0.3369, "step": 264520 }, { "epoch": 1.5724212541089335, "grad_norm": 5.206480979919434, "learning_rate": 8.662921103943044e-06, "loss": 0.3447, "step": 264530 }, { "epoch": 1.572480696185602, "grad_norm": 4.132507801055908, "learning_rate": 8.66277986579506e-06, "loss": 0.3733, "step": 264540 }, { "epoch": 1.5725401382622703, "grad_norm": 4.5629730224609375, "learning_rate": 8.662638621339329e-06, "loss": 0.3655, "step": 264550 }, { "epoch": 1.5725995803389388, "grad_norm": 4.646419525146484, "learning_rate": 8.662497370576099e-06, "loss": 0.3597, "step": 264560 }, { "epoch": 1.572659022415607, "grad_norm": 7.206197738647461, "learning_rate": 8.66235611350561e-06, "loss": 0.3267, "step": 264570 }, { "epoch": 1.5727184644922754, "grad_norm": 6.026342868804932, "learning_rate": 8.66221485012811e-06, "loss": 0.3734, "step": 264580 }, { "epoch": 1.5727779065689438, "grad_norm": 4.983488082885742, "learning_rate": 8.662073580443838e-06, "loss": 0.3343, "step": 264590 }, { "epoch": 1.5728373486456122, "grad_norm": 5.333493232727051, "learning_rate": 8.661932304453035e-06, "loss": 0.3706, "step": 264600 }, { "epoch": 1.5728967907222806, "grad_norm": 6.081876754760742, "learning_rate": 8.66179102215595e-06, "loss": 0.3422, "step": 264610 }, { "epoch": 1.572956232798949, "grad_norm": 6.894246578216553, "learning_rate": 8.661649733552825e-06, "loss": 0.363, "step": 264620 }, { "epoch": 1.5730156748756174, "grad_norm": 7.292882442474365, "learning_rate": 8.661508438643901e-06, "loss": 0.3586, "step": 264630 }, { "epoch": 1.5730751169522859, "grad_norm": 4.626110553741455, "learning_rate": 8.661367137429423e-06, "loss": 0.3061, "step": 264640 }, { "epoch": 1.5731345590289543, "grad_norm": 5.503361225128174, "learning_rate": 8.661225829909634e-06, "loss": 0.3403, "step": 264650 }, { "epoch": 1.5731940011056227, "grad_norm": 5.599647045135498, "learning_rate": 8.66108451608478e-06, "loss": 0.3392, "step": 264660 }, { "epoch": 1.573253443182291, "grad_norm": 6.138928413391113, "learning_rate": 8.660943195955095e-06, "loss": 0.3876, "step": 264670 }, { "epoch": 1.5733128852589595, "grad_norm": 5.160760879516602, "learning_rate": 8.660801869520835e-06, "loss": 0.4061, "step": 264680 }, { "epoch": 1.573372327335628, "grad_norm": 4.663692951202393, "learning_rate": 8.660660536782235e-06, "loss": 0.3357, "step": 264690 }, { "epoch": 1.5734317694122963, "grad_norm": 5.16304349899292, "learning_rate": 8.660519197739541e-06, "loss": 0.3698, "step": 264700 }, { "epoch": 1.5734912114889645, "grad_norm": 5.541341304779053, "learning_rate": 8.660377852392995e-06, "loss": 0.361, "step": 264710 }, { "epoch": 1.573550653565633, "grad_norm": 6.218822956085205, "learning_rate": 8.660236500742843e-06, "loss": 0.3534, "step": 264720 }, { "epoch": 1.5736100956423014, "grad_norm": 4.231414794921875, "learning_rate": 8.660095142789326e-06, "loss": 0.3686, "step": 264730 }, { "epoch": 1.5736695377189698, "grad_norm": 4.474384307861328, "learning_rate": 8.65995377853269e-06, "loss": 0.3683, "step": 264740 }, { "epoch": 1.5737289797956382, "grad_norm": 5.79428768157959, "learning_rate": 8.659812407973176e-06, "loss": 0.3527, "step": 264750 }, { "epoch": 1.5737884218723064, "grad_norm": 5.575537204742432, "learning_rate": 8.65967103111103e-06, "loss": 0.3509, "step": 264760 }, { "epoch": 1.5738478639489748, "grad_norm": 4.4961018562316895, "learning_rate": 8.659529647946491e-06, "loss": 0.3065, "step": 264770 }, { "epoch": 1.5739073060256432, "grad_norm": 5.9786376953125, "learning_rate": 8.659388258479806e-06, "loss": 0.3457, "step": 264780 }, { "epoch": 1.5739667481023116, "grad_norm": 4.799814701080322, "learning_rate": 8.65924686271122e-06, "loss": 0.3327, "step": 264790 }, { "epoch": 1.57402619017898, "grad_norm": 4.746427059173584, "learning_rate": 8.659105460640972e-06, "loss": 0.337, "step": 264800 }, { "epoch": 1.5740856322556485, "grad_norm": 3.540286064147949, "learning_rate": 8.658964052269308e-06, "loss": 0.348, "step": 264810 }, { "epoch": 1.5741450743323169, "grad_norm": 5.272883892059326, "learning_rate": 8.658822637596473e-06, "loss": 0.3061, "step": 264820 }, { "epoch": 1.5742045164089853, "grad_norm": 4.685226917266846, "learning_rate": 8.658681216622707e-06, "loss": 0.3564, "step": 264830 }, { "epoch": 1.5742639584856537, "grad_norm": 5.413345813751221, "learning_rate": 8.658539789348255e-06, "loss": 0.3849, "step": 264840 }, { "epoch": 1.5743234005623221, "grad_norm": 6.318887710571289, "learning_rate": 8.658398355773363e-06, "loss": 0.3553, "step": 264850 }, { "epoch": 1.5743828426389905, "grad_norm": 4.0519328117370605, "learning_rate": 8.65825691589827e-06, "loss": 0.3224, "step": 264860 }, { "epoch": 1.574442284715659, "grad_norm": 5.777555465698242, "learning_rate": 8.658115469723226e-06, "loss": 0.3802, "step": 264870 }, { "epoch": 1.5745017267923274, "grad_norm": 5.742175102233887, "learning_rate": 8.657974017248467e-06, "loss": 0.3859, "step": 264880 }, { "epoch": 1.5745611688689956, "grad_norm": 4.424766540527344, "learning_rate": 8.657832558474241e-06, "loss": 0.3248, "step": 264890 }, { "epoch": 1.574620610945664, "grad_norm": 4.410714149475098, "learning_rate": 8.657691093400792e-06, "loss": 0.3128, "step": 264900 }, { "epoch": 1.5746800530223324, "grad_norm": 4.809361457824707, "learning_rate": 8.657549622028362e-06, "loss": 0.3714, "step": 264910 }, { "epoch": 1.5747394950990008, "grad_norm": 5.875665664672852, "learning_rate": 8.657408144357196e-06, "loss": 0.327, "step": 264920 }, { "epoch": 1.5747989371756692, "grad_norm": 5.541257858276367, "learning_rate": 8.657266660387536e-06, "loss": 0.3227, "step": 264930 }, { "epoch": 1.5748583792523374, "grad_norm": 6.108999252319336, "learning_rate": 8.657125170119624e-06, "loss": 0.3562, "step": 264940 }, { "epoch": 1.5749178213290058, "grad_norm": 6.317085266113281, "learning_rate": 8.656983673553709e-06, "loss": 0.3207, "step": 264950 }, { "epoch": 1.5749772634056742, "grad_norm": 5.612290859222412, "learning_rate": 8.656842170690032e-06, "loss": 0.3356, "step": 264960 }, { "epoch": 1.5750367054823426, "grad_norm": 4.825738430023193, "learning_rate": 8.656700661528837e-06, "loss": 0.3168, "step": 264970 }, { "epoch": 1.575096147559011, "grad_norm": 6.300061225891113, "learning_rate": 8.656559146070365e-06, "loss": 0.3488, "step": 264980 }, { "epoch": 1.5751555896356795, "grad_norm": 5.848944664001465, "learning_rate": 8.656417624314862e-06, "loss": 0.3284, "step": 264990 }, { "epoch": 1.575215031712348, "grad_norm": 6.5768723487854, "learning_rate": 8.656276096262572e-06, "loss": 0.3713, "step": 265000 }, { "epoch": 1.5752744737890163, "grad_norm": 4.5783820152282715, "learning_rate": 8.656134561913739e-06, "loss": 0.3243, "step": 265010 }, { "epoch": 1.5753339158656847, "grad_norm": 5.003209590911865, "learning_rate": 8.655993021268605e-06, "loss": 0.3359, "step": 265020 }, { "epoch": 1.5753933579423531, "grad_norm": 4.153021335601807, "learning_rate": 8.655851474327416e-06, "loss": 0.3527, "step": 265030 }, { "epoch": 1.5754528000190215, "grad_norm": 5.606919288635254, "learning_rate": 8.655709921090414e-06, "loss": 0.3262, "step": 265040 }, { "epoch": 1.57551224209569, "grad_norm": 6.14607048034668, "learning_rate": 8.655568361557843e-06, "loss": 0.3748, "step": 265050 }, { "epoch": 1.5755716841723584, "grad_norm": 4.302348613739014, "learning_rate": 8.655426795729947e-06, "loss": 0.3326, "step": 265060 }, { "epoch": 1.5756311262490268, "grad_norm": 4.387056350708008, "learning_rate": 8.655285223606971e-06, "loss": 0.3682, "step": 265070 }, { "epoch": 1.575690568325695, "grad_norm": 5.032905101776123, "learning_rate": 8.655143645189157e-06, "loss": 0.3967, "step": 265080 }, { "epoch": 1.5757500104023634, "grad_norm": 4.836647987365723, "learning_rate": 8.65500206047675e-06, "loss": 0.3513, "step": 265090 }, { "epoch": 1.5758094524790318, "grad_norm": 4.433516979217529, "learning_rate": 8.654860469469993e-06, "loss": 0.3463, "step": 265100 }, { "epoch": 1.5758688945557002, "grad_norm": 4.377754211425781, "learning_rate": 8.654718872169127e-06, "loss": 0.3446, "step": 265110 }, { "epoch": 1.5759283366323686, "grad_norm": 5.1619791984558105, "learning_rate": 8.654577268574404e-06, "loss": 0.3671, "step": 265120 }, { "epoch": 1.5759877787090368, "grad_norm": 4.74807596206665, "learning_rate": 8.65443565868606e-06, "loss": 0.3347, "step": 265130 }, { "epoch": 1.5760472207857052, "grad_norm": 4.777148246765137, "learning_rate": 8.654294042504343e-06, "loss": 0.3304, "step": 265140 }, { "epoch": 1.5761066628623737, "grad_norm": 5.2835822105407715, "learning_rate": 8.654152420029496e-06, "loss": 0.3572, "step": 265150 }, { "epoch": 1.576166104939042, "grad_norm": 5.047309398651123, "learning_rate": 8.654010791261761e-06, "loss": 0.3701, "step": 265160 }, { "epoch": 1.5762255470157105, "grad_norm": 3.8972856998443604, "learning_rate": 8.653869156201384e-06, "loss": 0.3154, "step": 265170 }, { "epoch": 1.576284989092379, "grad_norm": 4.871643543243408, "learning_rate": 8.65372751484861e-06, "loss": 0.3754, "step": 265180 }, { "epoch": 1.5763444311690473, "grad_norm": 6.914477348327637, "learning_rate": 8.653585867203679e-06, "loss": 0.3606, "step": 265190 }, { "epoch": 1.5764038732457157, "grad_norm": 4.796240329742432, "learning_rate": 8.653444213266838e-06, "loss": 0.3339, "step": 265200 }, { "epoch": 1.5764633153223842, "grad_norm": 5.071869850158691, "learning_rate": 8.653302553038329e-06, "loss": 0.3661, "step": 265210 }, { "epoch": 1.5765227573990526, "grad_norm": 5.075249195098877, "learning_rate": 8.653160886518399e-06, "loss": 0.3793, "step": 265220 }, { "epoch": 1.576582199475721, "grad_norm": 5.6751790046691895, "learning_rate": 8.65301921370729e-06, "loss": 0.3311, "step": 265230 }, { "epoch": 1.5766416415523894, "grad_norm": 5.405330657958984, "learning_rate": 8.652877534605245e-06, "loss": 0.3353, "step": 265240 }, { "epoch": 1.5767010836290578, "grad_norm": 3.639075756072998, "learning_rate": 8.652735849212509e-06, "loss": 0.3268, "step": 265250 }, { "epoch": 1.576760525705726, "grad_norm": 6.391277313232422, "learning_rate": 8.652594157529327e-06, "loss": 0.3415, "step": 265260 }, { "epoch": 1.5768199677823944, "grad_norm": 3.953786611557007, "learning_rate": 8.652452459555941e-06, "loss": 0.3133, "step": 265270 }, { "epoch": 1.5768794098590628, "grad_norm": 6.491246223449707, "learning_rate": 8.652310755292597e-06, "loss": 0.3609, "step": 265280 }, { "epoch": 1.5769388519357312, "grad_norm": 6.42121696472168, "learning_rate": 8.652169044739538e-06, "loss": 0.3272, "step": 265290 }, { "epoch": 1.5769982940123997, "grad_norm": 4.279595851898193, "learning_rate": 8.652027327897008e-06, "loss": 0.3329, "step": 265300 }, { "epoch": 1.5770577360890679, "grad_norm": 4.243013381958008, "learning_rate": 8.651885604765251e-06, "loss": 0.3118, "step": 265310 }, { "epoch": 1.5771171781657363, "grad_norm": 6.28875207901001, "learning_rate": 8.65174387534451e-06, "loss": 0.3597, "step": 265320 }, { "epoch": 1.5771766202424047, "grad_norm": 4.365520477294922, "learning_rate": 8.651602139635032e-06, "loss": 0.3302, "step": 265330 }, { "epoch": 1.577236062319073, "grad_norm": 6.052591323852539, "learning_rate": 8.65146039763706e-06, "loss": 0.3848, "step": 265340 }, { "epoch": 1.5772955043957415, "grad_norm": 5.131904602050781, "learning_rate": 8.651318649350835e-06, "loss": 0.3068, "step": 265350 }, { "epoch": 1.57735494647241, "grad_norm": 4.382275581359863, "learning_rate": 8.651176894776605e-06, "loss": 0.3632, "step": 265360 }, { "epoch": 1.5774143885490783, "grad_norm": 3.4068121910095215, "learning_rate": 8.651035133914614e-06, "loss": 0.3453, "step": 265370 }, { "epoch": 1.5774738306257468, "grad_norm": 3.7386109828948975, "learning_rate": 8.650893366765103e-06, "loss": 0.3388, "step": 265380 }, { "epoch": 1.5775332727024152, "grad_norm": 6.229621410369873, "learning_rate": 8.650751593328319e-06, "loss": 0.3384, "step": 265390 }, { "epoch": 1.5775927147790836, "grad_norm": 5.16127347946167, "learning_rate": 8.650609813604505e-06, "loss": 0.3552, "step": 265400 }, { "epoch": 1.577652156855752, "grad_norm": 4.834427833557129, "learning_rate": 8.650468027593905e-06, "loss": 0.3723, "step": 265410 }, { "epoch": 1.5777115989324204, "grad_norm": 3.143402338027954, "learning_rate": 8.650326235296763e-06, "loss": 0.3506, "step": 265420 }, { "epoch": 1.5777710410090888, "grad_norm": 5.145246982574463, "learning_rate": 8.650184436713325e-06, "loss": 0.334, "step": 265430 }, { "epoch": 1.5778304830857572, "grad_norm": 5.6292266845703125, "learning_rate": 8.650042631843834e-06, "loss": 0.3006, "step": 265440 }, { "epoch": 1.5778899251624254, "grad_norm": 6.575375080108643, "learning_rate": 8.649900820688532e-06, "loss": 0.3373, "step": 265450 }, { "epoch": 1.5779493672390938, "grad_norm": 4.663961887359619, "learning_rate": 8.649759003247666e-06, "loss": 0.3418, "step": 265460 }, { "epoch": 1.5780088093157623, "grad_norm": 3.7733893394470215, "learning_rate": 8.649617179521482e-06, "loss": 0.3163, "step": 265470 }, { "epoch": 1.5780682513924307, "grad_norm": 4.2538042068481445, "learning_rate": 8.64947534951022e-06, "loss": 0.3326, "step": 265480 }, { "epoch": 1.578127693469099, "grad_norm": 7.052505970001221, "learning_rate": 8.649333513214124e-06, "loss": 0.3557, "step": 265490 }, { "epoch": 1.5781871355457673, "grad_norm": 6.954900741577148, "learning_rate": 8.649191670633442e-06, "loss": 0.3474, "step": 265500 }, { "epoch": 1.5782465776224357, "grad_norm": 5.9547529220581055, "learning_rate": 8.649049821768416e-06, "loss": 0.3462, "step": 265510 }, { "epoch": 1.5783060196991041, "grad_norm": 5.31591272354126, "learning_rate": 8.648907966619294e-06, "loss": 0.3296, "step": 265520 }, { "epoch": 1.5783654617757725, "grad_norm": 5.579280376434326, "learning_rate": 8.648766105186313e-06, "loss": 0.3595, "step": 265530 }, { "epoch": 1.578424903852441, "grad_norm": 5.5429368019104, "learning_rate": 8.648624237469723e-06, "loss": 0.3409, "step": 265540 }, { "epoch": 1.5784843459291094, "grad_norm": 5.945009231567383, "learning_rate": 8.648482363469765e-06, "loss": 0.3001, "step": 265550 }, { "epoch": 1.5785437880057778, "grad_norm": 5.730470180511475, "learning_rate": 8.648340483186688e-06, "loss": 0.3407, "step": 265560 }, { "epoch": 1.5786032300824462, "grad_norm": 4.395977020263672, "learning_rate": 8.648198596620732e-06, "loss": 0.3366, "step": 265570 }, { "epoch": 1.5786626721591146, "grad_norm": 4.209347724914551, "learning_rate": 8.648056703772143e-06, "loss": 0.3566, "step": 265580 }, { "epoch": 1.578722114235783, "grad_norm": 5.050596237182617, "learning_rate": 8.647914804641165e-06, "loss": 0.3877, "step": 265590 }, { "epoch": 1.5787815563124514, "grad_norm": 5.2432942390441895, "learning_rate": 8.647772899228041e-06, "loss": 0.3239, "step": 265600 }, { "epoch": 1.5788409983891198, "grad_norm": 6.41391134262085, "learning_rate": 8.647630987533018e-06, "loss": 0.3507, "step": 265610 }, { "epoch": 1.5789004404657883, "grad_norm": 5.14419412612915, "learning_rate": 8.647489069556341e-06, "loss": 0.3197, "step": 265620 }, { "epoch": 1.5789598825424564, "grad_norm": 5.835426330566406, "learning_rate": 8.647347145298251e-06, "loss": 0.3586, "step": 265630 }, { "epoch": 1.5790193246191249, "grad_norm": 7.880404472351074, "learning_rate": 8.647205214758993e-06, "loss": 0.3736, "step": 265640 }, { "epoch": 1.5790787666957933, "grad_norm": 6.053441047668457, "learning_rate": 8.647063277938814e-06, "loss": 0.3427, "step": 265650 }, { "epoch": 1.5791382087724617, "grad_norm": 4.0885419845581055, "learning_rate": 8.646921334837956e-06, "loss": 0.3538, "step": 265660 }, { "epoch": 1.57919765084913, "grad_norm": 4.6341233253479, "learning_rate": 8.646779385456665e-06, "loss": 0.3742, "step": 265670 }, { "epoch": 1.5792570929257983, "grad_norm": 4.725848197937012, "learning_rate": 8.646637429795184e-06, "loss": 0.38, "step": 265680 }, { "epoch": 1.5793165350024667, "grad_norm": 5.453150749206543, "learning_rate": 8.64649546785376e-06, "loss": 0.3673, "step": 265690 }, { "epoch": 1.5793759770791351, "grad_norm": 3.7181568145751953, "learning_rate": 8.646353499632632e-06, "loss": 0.3027, "step": 265700 }, { "epoch": 1.5794354191558035, "grad_norm": 4.970386505126953, "learning_rate": 8.64621152513205e-06, "loss": 0.3566, "step": 265710 }, { "epoch": 1.579494861232472, "grad_norm": 5.782662391662598, "learning_rate": 8.646069544352258e-06, "loss": 0.3398, "step": 265720 }, { "epoch": 1.5795543033091404, "grad_norm": 5.972182750701904, "learning_rate": 8.645927557293498e-06, "loss": 0.3651, "step": 265730 }, { "epoch": 1.5796137453858088, "grad_norm": 5.3452630043029785, "learning_rate": 8.645785563956017e-06, "loss": 0.3513, "step": 265740 }, { "epoch": 1.5796731874624772, "grad_norm": 4.130149841308594, "learning_rate": 8.645643564340058e-06, "loss": 0.375, "step": 265750 }, { "epoch": 1.5797326295391456, "grad_norm": 6.463980197906494, "learning_rate": 8.645501558445864e-06, "loss": 0.353, "step": 265760 }, { "epoch": 1.579792071615814, "grad_norm": 5.366837501525879, "learning_rate": 8.645359546273682e-06, "loss": 0.374, "step": 265770 }, { "epoch": 1.5798515136924824, "grad_norm": 4.0755109786987305, "learning_rate": 8.645217527823758e-06, "loss": 0.342, "step": 265780 }, { "epoch": 1.5799109557691509, "grad_norm": 6.321760654449463, "learning_rate": 8.645075503096332e-06, "loss": 0.3096, "step": 265790 }, { "epoch": 1.5799703978458193, "grad_norm": 6.555228233337402, "learning_rate": 8.644933472091653e-06, "loss": 0.3502, "step": 265800 }, { "epoch": 1.5800298399224877, "grad_norm": 6.301416397094727, "learning_rate": 8.644791434809963e-06, "loss": 0.3355, "step": 265810 }, { "epoch": 1.5800892819991559, "grad_norm": 5.068611145019531, "learning_rate": 8.644649391251506e-06, "loss": 0.3325, "step": 265820 }, { "epoch": 1.5801487240758243, "grad_norm": 6.761319160461426, "learning_rate": 8.644507341416529e-06, "loss": 0.3549, "step": 265830 }, { "epoch": 1.5802081661524927, "grad_norm": 4.523504734039307, "learning_rate": 8.644365285305275e-06, "loss": 0.3197, "step": 265840 }, { "epoch": 1.5802676082291611, "grad_norm": 4.519225120544434, "learning_rate": 8.64422322291799e-06, "loss": 0.3478, "step": 265850 }, { "epoch": 1.5803270503058295, "grad_norm": 5.191660404205322, "learning_rate": 8.644081154254917e-06, "loss": 0.3323, "step": 265860 }, { "epoch": 1.5803864923824977, "grad_norm": 4.915655136108398, "learning_rate": 8.643939079316301e-06, "loss": 0.3485, "step": 265870 }, { "epoch": 1.5804459344591661, "grad_norm": 5.4108428955078125, "learning_rate": 8.643796998102387e-06, "loss": 0.346, "step": 265880 }, { "epoch": 1.5805053765358346, "grad_norm": 5.9484710693359375, "learning_rate": 8.643654910613421e-06, "loss": 0.3301, "step": 265890 }, { "epoch": 1.580564818612503, "grad_norm": 5.348291397094727, "learning_rate": 8.643512816849645e-06, "loss": 0.3587, "step": 265900 }, { "epoch": 1.5806242606891714, "grad_norm": 4.374766826629639, "learning_rate": 8.643370716811309e-06, "loss": 0.3459, "step": 265910 }, { "epoch": 1.5806837027658398, "grad_norm": 3.6468827724456787, "learning_rate": 8.64322861049865e-06, "loss": 0.3223, "step": 265920 }, { "epoch": 1.5807431448425082, "grad_norm": 4.796102523803711, "learning_rate": 8.643086497911916e-06, "loss": 0.3843, "step": 265930 }, { "epoch": 1.5808025869191766, "grad_norm": 3.909393787384033, "learning_rate": 8.642944379051356e-06, "loss": 0.342, "step": 265940 }, { "epoch": 1.580862028995845, "grad_norm": 4.317630767822266, "learning_rate": 8.642802253917208e-06, "loss": 0.3548, "step": 265950 }, { "epoch": 1.5809214710725135, "grad_norm": 4.731395244598389, "learning_rate": 8.642660122509721e-06, "loss": 0.3611, "step": 265960 }, { "epoch": 1.5809809131491819, "grad_norm": 4.757562637329102, "learning_rate": 8.64251798482914e-06, "loss": 0.3372, "step": 265970 }, { "epoch": 1.5810403552258503, "grad_norm": 4.573760032653809, "learning_rate": 8.642375840875706e-06, "loss": 0.3236, "step": 265980 }, { "epoch": 1.5810997973025187, "grad_norm": 5.0343403816223145, "learning_rate": 8.64223369064967e-06, "loss": 0.3468, "step": 265990 }, { "epoch": 1.581159239379187, "grad_norm": 3.9266645908355713, "learning_rate": 8.642091534151269e-06, "loss": 0.3061, "step": 266000 }, { "epoch": 1.5812186814558553, "grad_norm": 5.448358058929443, "learning_rate": 8.641949371380752e-06, "loss": 0.3792, "step": 266010 }, { "epoch": 1.5812781235325237, "grad_norm": 4.674623966217041, "learning_rate": 8.641807202338366e-06, "loss": 0.3598, "step": 266020 }, { "epoch": 1.5813375656091921, "grad_norm": 5.35251522064209, "learning_rate": 8.641665027024352e-06, "loss": 0.3175, "step": 266030 }, { "epoch": 1.5813970076858606, "grad_norm": 6.907690048217773, "learning_rate": 8.641522845438957e-06, "loss": 0.3455, "step": 266040 }, { "epoch": 1.5814564497625287, "grad_norm": 5.981419563293457, "learning_rate": 8.641380657582423e-06, "loss": 0.3309, "step": 266050 }, { "epoch": 1.5815158918391972, "grad_norm": 5.1601457595825195, "learning_rate": 8.641238463454999e-06, "loss": 0.3356, "step": 266060 }, { "epoch": 1.5815753339158656, "grad_norm": 4.488548278808594, "learning_rate": 8.641096263056929e-06, "loss": 0.3146, "step": 266070 }, { "epoch": 1.581634775992534, "grad_norm": 4.241847991943359, "learning_rate": 8.640954056388455e-06, "loss": 0.3346, "step": 266080 }, { "epoch": 1.5816942180692024, "grad_norm": 4.126395225524902, "learning_rate": 8.640811843449824e-06, "loss": 0.3158, "step": 266090 }, { "epoch": 1.5817536601458708, "grad_norm": 7.6543707847595215, "learning_rate": 8.64066962424128e-06, "loss": 0.3466, "step": 266100 }, { "epoch": 1.5818131022225392, "grad_norm": 4.8369011878967285, "learning_rate": 8.64052739876307e-06, "loss": 0.3408, "step": 266110 }, { "epoch": 1.5818725442992077, "grad_norm": 6.031725883483887, "learning_rate": 8.640385167015438e-06, "loss": 0.3411, "step": 266120 }, { "epoch": 1.581931986375876, "grad_norm": 6.986598014831543, "learning_rate": 8.640242928998625e-06, "loss": 0.3797, "step": 266130 }, { "epoch": 1.5819914284525445, "grad_norm": 5.359816074371338, "learning_rate": 8.640100684712882e-06, "loss": 0.3675, "step": 266140 }, { "epoch": 1.582050870529213, "grad_norm": 4.995939254760742, "learning_rate": 8.63995843415845e-06, "loss": 0.3468, "step": 266150 }, { "epoch": 1.5821103126058813, "grad_norm": 5.66404914855957, "learning_rate": 8.639816177335575e-06, "loss": 0.3578, "step": 266160 }, { "epoch": 1.5821697546825497, "grad_norm": 6.070556163787842, "learning_rate": 8.639673914244504e-06, "loss": 0.3308, "step": 266170 }, { "epoch": 1.5822291967592181, "grad_norm": 4.107086181640625, "learning_rate": 8.639531644885479e-06, "loss": 0.3923, "step": 266180 }, { "epoch": 1.5822886388358863, "grad_norm": 5.20040225982666, "learning_rate": 8.639389369258749e-06, "loss": 0.3591, "step": 266190 }, { "epoch": 1.5823480809125547, "grad_norm": 5.099667549133301, "learning_rate": 8.639247087364552e-06, "loss": 0.3428, "step": 266200 }, { "epoch": 1.5824075229892232, "grad_norm": 5.099377632141113, "learning_rate": 8.639104799203139e-06, "loss": 0.3497, "step": 266210 }, { "epoch": 1.5824669650658916, "grad_norm": 4.080174922943115, "learning_rate": 8.638962504774756e-06, "loss": 0.3349, "step": 266220 }, { "epoch": 1.58252640714256, "grad_norm": 5.080996036529541, "learning_rate": 8.638820204079642e-06, "loss": 0.3487, "step": 266230 }, { "epoch": 1.5825858492192282, "grad_norm": 4.349323272705078, "learning_rate": 8.638677897118046e-06, "loss": 0.3408, "step": 266240 }, { "epoch": 1.5826452912958966, "grad_norm": 3.159276008605957, "learning_rate": 8.638535583890213e-06, "loss": 0.3324, "step": 266250 }, { "epoch": 1.582704733372565, "grad_norm": 6.7129716873168945, "learning_rate": 8.638393264396387e-06, "loss": 0.398, "step": 266260 }, { "epoch": 1.5827641754492334, "grad_norm": 4.090178966522217, "learning_rate": 8.638250938636814e-06, "loss": 0.3321, "step": 266270 }, { "epoch": 1.5828236175259018, "grad_norm": 5.0691328048706055, "learning_rate": 8.638108606611739e-06, "loss": 0.3498, "step": 266280 }, { "epoch": 1.5828830596025703, "grad_norm": 5.597811698913574, "learning_rate": 8.637966268321408e-06, "loss": 0.3557, "step": 266290 }, { "epoch": 1.5829425016792387, "grad_norm": 6.48606014251709, "learning_rate": 8.637823923766062e-06, "loss": 0.3347, "step": 266300 }, { "epoch": 1.583001943755907, "grad_norm": 6.046656608581543, "learning_rate": 8.63768157294595e-06, "loss": 0.3314, "step": 266310 }, { "epoch": 1.5830613858325755, "grad_norm": 6.119452476501465, "learning_rate": 8.637539215861319e-06, "loss": 0.3828, "step": 266320 }, { "epoch": 1.583120827909244, "grad_norm": 7.1904616355896, "learning_rate": 8.637396852512409e-06, "loss": 0.3791, "step": 266330 }, { "epoch": 1.5831802699859123, "grad_norm": 4.168032169342041, "learning_rate": 8.637254482899469e-06, "loss": 0.3498, "step": 266340 }, { "epoch": 1.5832397120625807, "grad_norm": 5.384570121765137, "learning_rate": 8.637112107022742e-06, "loss": 0.3502, "step": 266350 }, { "epoch": 1.5832991541392492, "grad_norm": 4.346959590911865, "learning_rate": 8.636969724882474e-06, "loss": 0.3404, "step": 266360 }, { "epoch": 1.5833585962159173, "grad_norm": 5.7456231117248535, "learning_rate": 8.63682733647891e-06, "loss": 0.345, "step": 266370 }, { "epoch": 1.5834180382925858, "grad_norm": 4.076266288757324, "learning_rate": 8.636684941812295e-06, "loss": 0.3168, "step": 266380 }, { "epoch": 1.5834774803692542, "grad_norm": 5.27757453918457, "learning_rate": 8.636542540882876e-06, "loss": 0.3488, "step": 266390 }, { "epoch": 1.5835369224459226, "grad_norm": 7.649281978607178, "learning_rate": 8.636400133690896e-06, "loss": 0.3418, "step": 266400 }, { "epoch": 1.583596364522591, "grad_norm": 7.382558345794678, "learning_rate": 8.6362577202366e-06, "loss": 0.37, "step": 266410 }, { "epoch": 1.5836558065992592, "grad_norm": 4.5346832275390625, "learning_rate": 8.636115300520235e-06, "loss": 0.3146, "step": 266420 }, { "epoch": 1.5837152486759276, "grad_norm": 7.957292556762695, "learning_rate": 8.635972874542047e-06, "loss": 0.3906, "step": 266430 }, { "epoch": 1.583774690752596, "grad_norm": 4.7308502197265625, "learning_rate": 8.635830442302279e-06, "loss": 0.3272, "step": 266440 }, { "epoch": 1.5838341328292644, "grad_norm": 5.754374027252197, "learning_rate": 8.635688003801177e-06, "loss": 0.2985, "step": 266450 }, { "epoch": 1.5838935749059329, "grad_norm": 3.71484637260437, "learning_rate": 8.635545559038988e-06, "loss": 0.3669, "step": 266460 }, { "epoch": 1.5839530169826013, "grad_norm": 3.9373176097869873, "learning_rate": 8.635403108015952e-06, "loss": 0.3484, "step": 266470 }, { "epoch": 1.5840124590592697, "grad_norm": 4.777796745300293, "learning_rate": 8.63526065073232e-06, "loss": 0.3352, "step": 266480 }, { "epoch": 1.584071901135938, "grad_norm": 5.467185020446777, "learning_rate": 8.635118187188337e-06, "loss": 0.3413, "step": 266490 }, { "epoch": 1.5841313432126065, "grad_norm": 4.454290390014648, "learning_rate": 8.634975717384246e-06, "loss": 0.352, "step": 266500 }, { "epoch": 1.584190785289275, "grad_norm": 3.996948003768921, "learning_rate": 8.634833241320292e-06, "loss": 0.3025, "step": 266510 }, { "epoch": 1.5842502273659433, "grad_norm": 5.128293991088867, "learning_rate": 8.634690758996722e-06, "loss": 0.3544, "step": 266520 }, { "epoch": 1.5843096694426118, "grad_norm": 4.8520050048828125, "learning_rate": 8.63454827041378e-06, "loss": 0.3657, "step": 266530 }, { "epoch": 1.5843691115192802, "grad_norm": 5.644320964813232, "learning_rate": 8.634405775571715e-06, "loss": 0.3205, "step": 266540 }, { "epoch": 1.5844285535959486, "grad_norm": 4.970698833465576, "learning_rate": 8.634263274470767e-06, "loss": 0.3511, "step": 266550 }, { "epoch": 1.5844879956726168, "grad_norm": 4.776477336883545, "learning_rate": 8.634120767111185e-06, "loss": 0.3292, "step": 266560 }, { "epoch": 1.5845474377492852, "grad_norm": 4.252306938171387, "learning_rate": 8.633978253493214e-06, "loss": 0.363, "step": 266570 }, { "epoch": 1.5846068798259536, "grad_norm": 6.543057441711426, "learning_rate": 8.633835733617097e-06, "loss": 0.3414, "step": 266580 }, { "epoch": 1.584666321902622, "grad_norm": 3.9370861053466797, "learning_rate": 8.633693207483083e-06, "loss": 0.3706, "step": 266590 }, { "epoch": 1.5847257639792902, "grad_norm": 5.52957820892334, "learning_rate": 8.633550675091413e-06, "loss": 0.3433, "step": 266600 }, { "epoch": 1.5847852060559586, "grad_norm": 5.796140670776367, "learning_rate": 8.633408136442338e-06, "loss": 0.3823, "step": 266610 }, { "epoch": 1.584844648132627, "grad_norm": 4.906821250915527, "learning_rate": 8.6332655915361e-06, "loss": 0.3319, "step": 266620 }, { "epoch": 1.5849040902092955, "grad_norm": 6.0553693771362305, "learning_rate": 8.633123040372946e-06, "loss": 0.3659, "step": 266630 }, { "epoch": 1.5849635322859639, "grad_norm": 4.699570178985596, "learning_rate": 8.63298048295312e-06, "loss": 0.3399, "step": 266640 }, { "epoch": 1.5850229743626323, "grad_norm": 4.412002086639404, "learning_rate": 8.632837919276866e-06, "loss": 0.3262, "step": 266650 }, { "epoch": 1.5850824164393007, "grad_norm": 4.523359298706055, "learning_rate": 8.632695349344434e-06, "loss": 0.3559, "step": 266660 }, { "epoch": 1.5851418585159691, "grad_norm": 5.126243591308594, "learning_rate": 8.632552773156067e-06, "loss": 0.3124, "step": 266670 }, { "epoch": 1.5852013005926375, "grad_norm": 4.659965515136719, "learning_rate": 8.63241019071201e-06, "loss": 0.3512, "step": 266680 }, { "epoch": 1.585260742669306, "grad_norm": 4.942643165588379, "learning_rate": 8.63226760201251e-06, "loss": 0.3013, "step": 266690 }, { "epoch": 1.5853201847459744, "grad_norm": 5.125066757202148, "learning_rate": 8.63212500705781e-06, "loss": 0.3783, "step": 266700 }, { "epoch": 1.5853796268226428, "grad_norm": 5.063279628753662, "learning_rate": 8.63198240584816e-06, "loss": 0.3419, "step": 266710 }, { "epoch": 1.5854390688993112, "grad_norm": 5.985655307769775, "learning_rate": 8.6318397983838e-06, "loss": 0.3224, "step": 266720 }, { "epoch": 1.5854985109759796, "grad_norm": 4.619215965270996, "learning_rate": 8.63169718466498e-06, "loss": 0.341, "step": 266730 }, { "epoch": 1.5855579530526478, "grad_norm": 4.948259353637695, "learning_rate": 8.631554564691946e-06, "loss": 0.3367, "step": 266740 }, { "epoch": 1.5856173951293162, "grad_norm": 6.441205024719238, "learning_rate": 8.63141193846494e-06, "loss": 0.3443, "step": 266750 }, { "epoch": 1.5856768372059846, "grad_norm": 4.537866115570068, "learning_rate": 8.63126930598421e-06, "loss": 0.3291, "step": 266760 }, { "epoch": 1.585736279282653, "grad_norm": 3.7970776557922363, "learning_rate": 8.631126667249998e-06, "loss": 0.333, "step": 266770 }, { "epoch": 1.5857957213593215, "grad_norm": 5.309054851531982, "learning_rate": 8.630984022262556e-06, "loss": 0.3225, "step": 266780 }, { "epoch": 1.5858551634359896, "grad_norm": 5.9265594482421875, "learning_rate": 8.630841371022124e-06, "loss": 0.37, "step": 266790 }, { "epoch": 1.585914605512658, "grad_norm": 5.444469928741455, "learning_rate": 8.630698713528952e-06, "loss": 0.3436, "step": 266800 }, { "epoch": 1.5859740475893265, "grad_norm": 7.934391975402832, "learning_rate": 8.630556049783284e-06, "loss": 0.3425, "step": 266810 }, { "epoch": 1.5860334896659949, "grad_norm": 5.181074142456055, "learning_rate": 8.630413379785362e-06, "loss": 0.339, "step": 266820 }, { "epoch": 1.5860929317426633, "grad_norm": 5.5697760581970215, "learning_rate": 8.630270703535438e-06, "loss": 0.387, "step": 266830 }, { "epoch": 1.5861523738193317, "grad_norm": 4.06907844543457, "learning_rate": 8.630128021033753e-06, "loss": 0.353, "step": 266840 }, { "epoch": 1.5862118158960001, "grad_norm": 5.279249668121338, "learning_rate": 8.629985332280555e-06, "loss": 0.3649, "step": 266850 }, { "epoch": 1.5862712579726685, "grad_norm": 7.11776065826416, "learning_rate": 8.62984263727609e-06, "loss": 0.4173, "step": 266860 }, { "epoch": 1.586330700049337, "grad_norm": 4.036864757537842, "learning_rate": 8.629699936020601e-06, "loss": 0.3371, "step": 266870 }, { "epoch": 1.5863901421260054, "grad_norm": 6.515970230102539, "learning_rate": 8.629557228514338e-06, "loss": 0.4024, "step": 266880 }, { "epoch": 1.5864495842026738, "grad_norm": 4.192667484283447, "learning_rate": 8.629414514757542e-06, "loss": 0.3174, "step": 266890 }, { "epoch": 1.5865090262793422, "grad_norm": 4.1670145988464355, "learning_rate": 8.629271794750463e-06, "loss": 0.3478, "step": 266900 }, { "epoch": 1.5865684683560106, "grad_norm": 5.376330375671387, "learning_rate": 8.629129068493345e-06, "loss": 0.3746, "step": 266910 }, { "epoch": 1.586627910432679, "grad_norm": 5.333285331726074, "learning_rate": 8.628986335986432e-06, "loss": 0.35, "step": 266920 }, { "epoch": 1.5866873525093472, "grad_norm": 5.396081924438477, "learning_rate": 8.628843597229972e-06, "loss": 0.3394, "step": 266930 }, { "epoch": 1.5867467945860156, "grad_norm": 5.333425045013428, "learning_rate": 8.628700852224212e-06, "loss": 0.3374, "step": 266940 }, { "epoch": 1.586806236662684, "grad_norm": 6.034271717071533, "learning_rate": 8.628558100969394e-06, "loss": 0.327, "step": 266950 }, { "epoch": 1.5868656787393525, "grad_norm": 5.210970878601074, "learning_rate": 8.628415343465768e-06, "loss": 0.3428, "step": 266960 }, { "epoch": 1.5869251208160207, "grad_norm": 5.525193691253662, "learning_rate": 8.628272579713576e-06, "loss": 0.3508, "step": 266970 }, { "epoch": 1.586984562892689, "grad_norm": 4.595481872558594, "learning_rate": 8.628129809713066e-06, "loss": 0.3315, "step": 266980 }, { "epoch": 1.5870440049693575, "grad_norm": 5.512343406677246, "learning_rate": 8.627987033464485e-06, "loss": 0.3432, "step": 266990 }, { "epoch": 1.587103447046026, "grad_norm": 4.712112903594971, "learning_rate": 8.627844250968076e-06, "loss": 0.3408, "step": 267000 }, { "epoch": 1.5871628891226943, "grad_norm": 3.863428831100464, "learning_rate": 8.627701462224087e-06, "loss": 0.3156, "step": 267010 }, { "epoch": 1.5872223311993627, "grad_norm": 4.783153057098389, "learning_rate": 8.627558667232762e-06, "loss": 0.3276, "step": 267020 }, { "epoch": 1.5872817732760311, "grad_norm": 6.088550090789795, "learning_rate": 8.627415865994351e-06, "loss": 0.3743, "step": 267030 }, { "epoch": 1.5873412153526996, "grad_norm": 4.518797397613525, "learning_rate": 8.627273058509093e-06, "loss": 0.3462, "step": 267040 }, { "epoch": 1.587400657429368, "grad_norm": 4.497586727142334, "learning_rate": 8.627130244777242e-06, "loss": 0.3878, "step": 267050 }, { "epoch": 1.5874600995060364, "grad_norm": 4.821547985076904, "learning_rate": 8.626987424799037e-06, "loss": 0.3598, "step": 267060 }, { "epoch": 1.5875195415827048, "grad_norm": 4.538608074188232, "learning_rate": 8.626844598574728e-06, "loss": 0.3466, "step": 267070 }, { "epoch": 1.5875789836593732, "grad_norm": 4.248632431030273, "learning_rate": 8.626701766104561e-06, "loss": 0.317, "step": 267080 }, { "epoch": 1.5876384257360416, "grad_norm": 6.106659889221191, "learning_rate": 8.626558927388779e-06, "loss": 0.3455, "step": 267090 }, { "epoch": 1.58769786781271, "grad_norm": 5.388530254364014, "learning_rate": 8.62641608242763e-06, "loss": 0.3691, "step": 267100 }, { "epoch": 1.5877573098893782, "grad_norm": 4.207064628601074, "learning_rate": 8.626273231221362e-06, "loss": 0.3488, "step": 267110 }, { "epoch": 1.5878167519660467, "grad_norm": 4.520059108734131, "learning_rate": 8.626130373770216e-06, "loss": 0.3598, "step": 267120 }, { "epoch": 1.587876194042715, "grad_norm": 4.630663871765137, "learning_rate": 8.625987510074443e-06, "loss": 0.3337, "step": 267130 }, { "epoch": 1.5879356361193835, "grad_norm": 5.1097798347473145, "learning_rate": 8.625844640134286e-06, "loss": 0.329, "step": 267140 }, { "epoch": 1.587995078196052, "grad_norm": 5.204594612121582, "learning_rate": 8.625701763949991e-06, "loss": 0.3424, "step": 267150 }, { "epoch": 1.58805452027272, "grad_norm": 5.211356163024902, "learning_rate": 8.625558881521807e-06, "loss": 0.3576, "step": 267160 }, { "epoch": 1.5881139623493885, "grad_norm": 3.88791561126709, "learning_rate": 8.625415992849977e-06, "loss": 0.3611, "step": 267170 }, { "epoch": 1.588173404426057, "grad_norm": 4.701474666595459, "learning_rate": 8.625273097934747e-06, "loss": 0.3436, "step": 267180 }, { "epoch": 1.5882328465027253, "grad_norm": 5.034608364105225, "learning_rate": 8.625130196776365e-06, "loss": 0.3465, "step": 267190 }, { "epoch": 1.5882922885793938, "grad_norm": 4.440364837646484, "learning_rate": 8.624987289375075e-06, "loss": 0.3185, "step": 267200 }, { "epoch": 1.5883517306560622, "grad_norm": 4.121863842010498, "learning_rate": 8.624844375731128e-06, "loss": 0.369, "step": 267210 }, { "epoch": 1.5884111727327306, "grad_norm": 5.2961859703063965, "learning_rate": 8.624701455844763e-06, "loss": 0.3351, "step": 267220 }, { "epoch": 1.588470614809399, "grad_norm": 5.057530403137207, "learning_rate": 8.62455852971623e-06, "loss": 0.3516, "step": 267230 }, { "epoch": 1.5885300568860674, "grad_norm": 5.045741081237793, "learning_rate": 8.624415597345777e-06, "loss": 0.3586, "step": 267240 }, { "epoch": 1.5885894989627358, "grad_norm": 5.009985446929932, "learning_rate": 8.624272658733645e-06, "loss": 0.3779, "step": 267250 }, { "epoch": 1.5886489410394042, "grad_norm": 5.524316787719727, "learning_rate": 8.624129713880085e-06, "loss": 0.3778, "step": 267260 }, { "epoch": 1.5887083831160727, "grad_norm": 5.853779315948486, "learning_rate": 8.62398676278534e-06, "loss": 0.3537, "step": 267270 }, { "epoch": 1.588767825192741, "grad_norm": 4.545289039611816, "learning_rate": 8.623843805449658e-06, "loss": 0.4021, "step": 267280 }, { "epoch": 1.5888272672694095, "grad_norm": 3.891831636428833, "learning_rate": 8.623700841873285e-06, "loss": 0.3479, "step": 267290 }, { "epoch": 1.5888867093460777, "grad_norm": 4.355381488800049, "learning_rate": 8.623557872056466e-06, "loss": 0.3088, "step": 267300 }, { "epoch": 1.588946151422746, "grad_norm": 5.432835578918457, "learning_rate": 8.623414895999449e-06, "loss": 0.3268, "step": 267310 }, { "epoch": 1.5890055934994145, "grad_norm": 5.547430038452148, "learning_rate": 8.623271913702478e-06, "loss": 0.3763, "step": 267320 }, { "epoch": 1.589065035576083, "grad_norm": 4.859096527099609, "learning_rate": 8.6231289251658e-06, "loss": 0.384, "step": 267330 }, { "epoch": 1.589124477652751, "grad_norm": 5.442753314971924, "learning_rate": 8.622985930389664e-06, "loss": 0.3875, "step": 267340 }, { "epoch": 1.5891839197294195, "grad_norm": 6.075198650360107, "learning_rate": 8.622842929374312e-06, "loss": 0.4021, "step": 267350 }, { "epoch": 1.589243361806088, "grad_norm": 7.66656494140625, "learning_rate": 8.622699922119992e-06, "loss": 0.3721, "step": 267360 }, { "epoch": 1.5893028038827564, "grad_norm": 6.527475357055664, "learning_rate": 8.622556908626953e-06, "loss": 0.3224, "step": 267370 }, { "epoch": 1.5893622459594248, "grad_norm": 5.331303596496582, "learning_rate": 8.622413888895436e-06, "loss": 0.315, "step": 267380 }, { "epoch": 1.5894216880360932, "grad_norm": 3.376624584197998, "learning_rate": 8.622270862925691e-06, "loss": 0.3449, "step": 267390 }, { "epoch": 1.5894811301127616, "grad_norm": 6.566938400268555, "learning_rate": 8.622127830717963e-06, "loss": 0.3536, "step": 267400 }, { "epoch": 1.58954057218943, "grad_norm": 4.350761890411377, "learning_rate": 8.6219847922725e-06, "loss": 0.2985, "step": 267410 }, { "epoch": 1.5896000142660984, "grad_norm": 4.453739643096924, "learning_rate": 8.621841747589546e-06, "loss": 0.3534, "step": 267420 }, { "epoch": 1.5896594563427668, "grad_norm": 5.190074920654297, "learning_rate": 8.62169869666935e-06, "loss": 0.3603, "step": 267430 }, { "epoch": 1.5897188984194353, "grad_norm": 4.106047630310059, "learning_rate": 8.621555639512153e-06, "loss": 0.33, "step": 267440 }, { "epoch": 1.5897783404961037, "grad_norm": 4.8387532234191895, "learning_rate": 8.621412576118209e-06, "loss": 0.3686, "step": 267450 }, { "epoch": 1.589837782572772, "grad_norm": 5.408150672912598, "learning_rate": 8.621269506487759e-06, "loss": 0.3215, "step": 267460 }, { "epoch": 1.5898972246494405, "grad_norm": 4.790402412414551, "learning_rate": 8.62112643062105e-06, "loss": 0.3526, "step": 267470 }, { "epoch": 1.5899566667261087, "grad_norm": 7.062023639678955, "learning_rate": 8.62098334851833e-06, "loss": 0.3431, "step": 267480 }, { "epoch": 1.590016108802777, "grad_norm": 4.82273530960083, "learning_rate": 8.620840260179844e-06, "loss": 0.3257, "step": 267490 }, { "epoch": 1.5900755508794455, "grad_norm": 5.5521135330200195, "learning_rate": 8.62069716560584e-06, "loss": 0.3648, "step": 267500 }, { "epoch": 1.590134992956114, "grad_norm": 5.01624870300293, "learning_rate": 8.620554064796563e-06, "loss": 0.355, "step": 267510 }, { "epoch": 1.5901944350327823, "grad_norm": 4.370069980621338, "learning_rate": 8.62041095775226e-06, "loss": 0.3708, "step": 267520 }, { "epoch": 1.5902538771094505, "grad_norm": 4.196676731109619, "learning_rate": 8.620267844473176e-06, "loss": 0.3199, "step": 267530 }, { "epoch": 1.590313319186119, "grad_norm": 6.271114349365234, "learning_rate": 8.62012472495956e-06, "loss": 0.3916, "step": 267540 }, { "epoch": 1.5903727612627874, "grad_norm": 4.5937395095825195, "learning_rate": 8.619981599211658e-06, "loss": 0.3418, "step": 267550 }, { "epoch": 1.5904322033394558, "grad_norm": 5.59548282623291, "learning_rate": 8.619838467229715e-06, "loss": 0.3437, "step": 267560 }, { "epoch": 1.5904916454161242, "grad_norm": 6.2870659828186035, "learning_rate": 8.619695329013978e-06, "loss": 0.3384, "step": 267570 }, { "epoch": 1.5905510874927926, "grad_norm": 3.9047553539276123, "learning_rate": 8.619552184564695e-06, "loss": 0.343, "step": 267580 }, { "epoch": 1.590610529569461, "grad_norm": 6.206045627593994, "learning_rate": 8.61940903388211e-06, "loss": 0.3212, "step": 267590 }, { "epoch": 1.5906699716461294, "grad_norm": 4.728107452392578, "learning_rate": 8.61926587696647e-06, "loss": 0.3485, "step": 267600 }, { "epoch": 1.5907294137227979, "grad_norm": 4.987541198730469, "learning_rate": 8.619122713818025e-06, "loss": 0.3396, "step": 267610 }, { "epoch": 1.5907888557994663, "grad_norm": 4.8108906745910645, "learning_rate": 8.618979544437016e-06, "loss": 0.3191, "step": 267620 }, { "epoch": 1.5908482978761347, "grad_norm": 5.306891441345215, "learning_rate": 8.618836368823693e-06, "loss": 0.3608, "step": 267630 }, { "epoch": 1.590907739952803, "grad_norm": 3.908008575439453, "learning_rate": 8.618693186978303e-06, "loss": 0.3407, "step": 267640 }, { "epoch": 1.5909671820294715, "grad_norm": 6.320718765258789, "learning_rate": 8.61854999890109e-06, "loss": 0.3211, "step": 267650 }, { "epoch": 1.59102662410614, "grad_norm": 5.465092182159424, "learning_rate": 8.618406804592306e-06, "loss": 0.3375, "step": 267660 }, { "epoch": 1.5910860661828081, "grad_norm": 5.637680530548096, "learning_rate": 8.61826360405219e-06, "loss": 0.3366, "step": 267670 }, { "epoch": 1.5911455082594765, "grad_norm": 4.6050004959106445, "learning_rate": 8.618120397280993e-06, "loss": 0.3659, "step": 267680 }, { "epoch": 1.591204950336145, "grad_norm": 6.664388179779053, "learning_rate": 8.617977184278962e-06, "loss": 0.3093, "step": 267690 }, { "epoch": 1.5912643924128134, "grad_norm": 4.071874141693115, "learning_rate": 8.617833965046342e-06, "loss": 0.3003, "step": 267700 }, { "epoch": 1.5913238344894816, "grad_norm": 4.943999767303467, "learning_rate": 8.61769073958338e-06, "loss": 0.3375, "step": 267710 }, { "epoch": 1.59138327656615, "grad_norm": 6.124679088592529, "learning_rate": 8.617547507890322e-06, "loss": 0.3972, "step": 267720 }, { "epoch": 1.5914427186428184, "grad_norm": 4.0364990234375, "learning_rate": 8.617404269967417e-06, "loss": 0.3401, "step": 267730 }, { "epoch": 1.5915021607194868, "grad_norm": 3.5549750328063965, "learning_rate": 8.617261025814911e-06, "loss": 0.334, "step": 267740 }, { "epoch": 1.5915616027961552, "grad_norm": 5.966026306152344, "learning_rate": 8.617117775433048e-06, "loss": 0.3301, "step": 267750 }, { "epoch": 1.5916210448728236, "grad_norm": 4.852620601654053, "learning_rate": 8.61697451882208e-06, "loss": 0.2857, "step": 267760 }, { "epoch": 1.591680486949492, "grad_norm": 5.127358436584473, "learning_rate": 8.616831255982245e-06, "loss": 0.2776, "step": 267770 }, { "epoch": 1.5917399290261605, "grad_norm": 4.246830463409424, "learning_rate": 8.616687986913799e-06, "loss": 0.3695, "step": 267780 }, { "epoch": 1.5917993711028289, "grad_norm": 4.610109329223633, "learning_rate": 8.616544711616984e-06, "loss": 0.3424, "step": 267790 }, { "epoch": 1.5918588131794973, "grad_norm": 4.7825026512146, "learning_rate": 8.616401430092047e-06, "loss": 0.3218, "step": 267800 }, { "epoch": 1.5919182552561657, "grad_norm": 5.289831638336182, "learning_rate": 8.616258142339234e-06, "loss": 0.3195, "step": 267810 }, { "epoch": 1.5919776973328341, "grad_norm": 5.194951057434082, "learning_rate": 8.616114848358795e-06, "loss": 0.3424, "step": 267820 }, { "epoch": 1.5920371394095025, "grad_norm": 4.130486011505127, "learning_rate": 8.615971548150974e-06, "loss": 0.3291, "step": 267830 }, { "epoch": 1.592096581486171, "grad_norm": 5.206794261932373, "learning_rate": 8.615828241716018e-06, "loss": 0.3427, "step": 267840 }, { "epoch": 1.5921560235628391, "grad_norm": 5.895584583282471, "learning_rate": 8.615684929054176e-06, "loss": 0.3615, "step": 267850 }, { "epoch": 1.5922154656395076, "grad_norm": 5.0451178550720215, "learning_rate": 8.61554161016569e-06, "loss": 0.3613, "step": 267860 }, { "epoch": 1.592274907716176, "grad_norm": 5.197994232177734, "learning_rate": 8.615398285050814e-06, "loss": 0.36, "step": 267870 }, { "epoch": 1.5923343497928444, "grad_norm": 5.455724239349365, "learning_rate": 8.615254953709789e-06, "loss": 0.3371, "step": 267880 }, { "epoch": 1.5923937918695128, "grad_norm": 5.427381992340088, "learning_rate": 8.615111616142862e-06, "loss": 0.341, "step": 267890 }, { "epoch": 1.592453233946181, "grad_norm": 4.337355613708496, "learning_rate": 8.614968272350283e-06, "loss": 0.3424, "step": 267900 }, { "epoch": 1.5925126760228494, "grad_norm": 4.417582035064697, "learning_rate": 8.614824922332297e-06, "loss": 0.3577, "step": 267910 }, { "epoch": 1.5925721180995178, "grad_norm": 4.709622383117676, "learning_rate": 8.614681566089151e-06, "loss": 0.3245, "step": 267920 }, { "epoch": 1.5926315601761862, "grad_norm": 5.101978302001953, "learning_rate": 8.614538203621092e-06, "loss": 0.3481, "step": 267930 }, { "epoch": 1.5926910022528546, "grad_norm": 5.622896671295166, "learning_rate": 8.614394834928367e-06, "loss": 0.3134, "step": 267940 }, { "epoch": 1.592750444329523, "grad_norm": 5.438478946685791, "learning_rate": 8.614251460011224e-06, "loss": 0.3301, "step": 267950 }, { "epoch": 1.5928098864061915, "grad_norm": 5.377799987792969, "learning_rate": 8.614108078869907e-06, "loss": 0.3272, "step": 267960 }, { "epoch": 1.59286932848286, "grad_norm": 5.415059566497803, "learning_rate": 8.613964691504666e-06, "loss": 0.3632, "step": 267970 }, { "epoch": 1.5929287705595283, "grad_norm": 4.791825294494629, "learning_rate": 8.613821297915746e-06, "loss": 0.3411, "step": 267980 }, { "epoch": 1.5929882126361967, "grad_norm": 5.23428201675415, "learning_rate": 8.613677898103393e-06, "loss": 0.3342, "step": 267990 }, { "epoch": 1.5930476547128651, "grad_norm": 5.096884250640869, "learning_rate": 8.61353449206786e-06, "loss": 0.3433, "step": 268000 }, { "epoch": 1.5931070967895335, "grad_norm": 5.3894243240356445, "learning_rate": 8.613391079809386e-06, "loss": 0.3787, "step": 268010 }, { "epoch": 1.593166538866202, "grad_norm": 5.798831939697266, "learning_rate": 8.613247661328222e-06, "loss": 0.3488, "step": 268020 }, { "epoch": 1.5932259809428704, "grad_norm": 6.117081642150879, "learning_rate": 8.613104236624615e-06, "loss": 0.3748, "step": 268030 }, { "epoch": 1.5932854230195386, "grad_norm": 5.183478355407715, "learning_rate": 8.61296080569881e-06, "loss": 0.3442, "step": 268040 }, { "epoch": 1.593344865096207, "grad_norm": 4.648926258087158, "learning_rate": 8.612817368551057e-06, "loss": 0.3638, "step": 268050 }, { "epoch": 1.5934043071728754, "grad_norm": 6.9291276931762695, "learning_rate": 8.612673925181599e-06, "loss": 0.394, "step": 268060 }, { "epoch": 1.5934637492495438, "grad_norm": 5.602865695953369, "learning_rate": 8.612530475590687e-06, "loss": 0.3288, "step": 268070 }, { "epoch": 1.593523191326212, "grad_norm": 5.528825283050537, "learning_rate": 8.612387019778567e-06, "loss": 0.347, "step": 268080 }, { "epoch": 1.5935826334028804, "grad_norm": 4.826425552368164, "learning_rate": 8.612243557745485e-06, "loss": 0.3537, "step": 268090 }, { "epoch": 1.5936420754795488, "grad_norm": 3.405329942703247, "learning_rate": 8.612100089491689e-06, "loss": 0.3337, "step": 268100 }, { "epoch": 1.5937015175562173, "grad_norm": 4.035414218902588, "learning_rate": 8.611956615017426e-06, "loss": 0.3658, "step": 268110 }, { "epoch": 1.5937609596328857, "grad_norm": 3.6715712547302246, "learning_rate": 8.61181313432294e-06, "loss": 0.342, "step": 268120 }, { "epoch": 1.593820401709554, "grad_norm": 4.259185791015625, "learning_rate": 8.611669647408482e-06, "loss": 0.3638, "step": 268130 }, { "epoch": 1.5938798437862225, "grad_norm": 4.639532089233398, "learning_rate": 8.611526154274298e-06, "loss": 0.3543, "step": 268140 }, { "epoch": 1.593939285862891, "grad_norm": 5.1729559898376465, "learning_rate": 8.611382654920638e-06, "loss": 0.3605, "step": 268150 }, { "epoch": 1.5939987279395593, "grad_norm": 3.7177438735961914, "learning_rate": 8.611239149347743e-06, "loss": 0.3505, "step": 268160 }, { "epoch": 1.5940581700162277, "grad_norm": 5.609963893890381, "learning_rate": 8.611095637555864e-06, "loss": 0.3394, "step": 268170 }, { "epoch": 1.5941176120928962, "grad_norm": 4.941905498504639, "learning_rate": 8.610952119545248e-06, "loss": 0.363, "step": 268180 }, { "epoch": 1.5941770541695646, "grad_norm": 4.960461139678955, "learning_rate": 8.610808595316142e-06, "loss": 0.3198, "step": 268190 }, { "epoch": 1.594236496246233, "grad_norm": 5.2647576332092285, "learning_rate": 8.610665064868791e-06, "loss": 0.4113, "step": 268200 }, { "epoch": 1.5942959383229014, "grad_norm": 5.577197074890137, "learning_rate": 8.610521528203446e-06, "loss": 0.3389, "step": 268210 }, { "epoch": 1.5943553803995696, "grad_norm": 7.122043132781982, "learning_rate": 8.610377985320351e-06, "loss": 0.3499, "step": 268220 }, { "epoch": 1.594414822476238, "grad_norm": 5.623186111450195, "learning_rate": 8.610234436219756e-06, "loss": 0.3409, "step": 268230 }, { "epoch": 1.5944742645529064, "grad_norm": 4.962183475494385, "learning_rate": 8.610090880901904e-06, "loss": 0.3557, "step": 268240 }, { "epoch": 1.5945337066295748, "grad_norm": 5.208922863006592, "learning_rate": 8.609947319367045e-06, "loss": 0.3295, "step": 268250 }, { "epoch": 1.5945931487062432, "grad_norm": 5.45468807220459, "learning_rate": 8.609803751615426e-06, "loss": 0.3258, "step": 268260 }, { "epoch": 1.5946525907829114, "grad_norm": 4.703589916229248, "learning_rate": 8.609660177647297e-06, "loss": 0.3515, "step": 268270 }, { "epoch": 1.5947120328595799, "grad_norm": 4.801303386688232, "learning_rate": 8.609516597462899e-06, "loss": 0.3564, "step": 268280 }, { "epoch": 1.5947714749362483, "grad_norm": 4.369913578033447, "learning_rate": 8.609373011062484e-06, "loss": 0.3697, "step": 268290 }, { "epoch": 1.5948309170129167, "grad_norm": 5.2333831787109375, "learning_rate": 8.609229418446299e-06, "loss": 0.3479, "step": 268300 }, { "epoch": 1.594890359089585, "grad_norm": 4.8271050453186035, "learning_rate": 8.609085819614588e-06, "loss": 0.3496, "step": 268310 }, { "epoch": 1.5949498011662535, "grad_norm": 3.5854392051696777, "learning_rate": 8.608942214567604e-06, "loss": 0.3256, "step": 268320 }, { "epoch": 1.595009243242922, "grad_norm": 4.302696704864502, "learning_rate": 8.608798603305589e-06, "loss": 0.362, "step": 268330 }, { "epoch": 1.5950686853195903, "grad_norm": 5.05510139465332, "learning_rate": 8.608654985828791e-06, "loss": 0.3331, "step": 268340 }, { "epoch": 1.5951281273962588, "grad_norm": 4.182602882385254, "learning_rate": 8.60851136213746e-06, "loss": 0.3796, "step": 268350 }, { "epoch": 1.5951875694729272, "grad_norm": 4.87575626373291, "learning_rate": 8.608367732231841e-06, "loss": 0.3681, "step": 268360 }, { "epoch": 1.5952470115495956, "grad_norm": 5.8217854499816895, "learning_rate": 8.608224096112184e-06, "loss": 0.3355, "step": 268370 }, { "epoch": 1.595306453626264, "grad_norm": 5.068816661834717, "learning_rate": 8.608080453778733e-06, "loss": 0.3188, "step": 268380 }, { "epoch": 1.5953658957029324, "grad_norm": 5.067958354949951, "learning_rate": 8.607936805231737e-06, "loss": 0.3978, "step": 268390 }, { "epoch": 1.5954253377796008, "grad_norm": 6.914889812469482, "learning_rate": 8.607793150471444e-06, "loss": 0.3953, "step": 268400 }, { "epoch": 1.595484779856269, "grad_norm": 3.9882616996765137, "learning_rate": 8.6076494894981e-06, "loss": 0.365, "step": 268410 }, { "epoch": 1.5955442219329374, "grad_norm": 4.8966193199157715, "learning_rate": 8.607505822311954e-06, "loss": 0.2987, "step": 268420 }, { "epoch": 1.5956036640096058, "grad_norm": 4.209775447845459, "learning_rate": 8.607362148913252e-06, "loss": 0.3529, "step": 268430 }, { "epoch": 1.5956631060862743, "grad_norm": 4.2408952713012695, "learning_rate": 8.60721846930224e-06, "loss": 0.3559, "step": 268440 }, { "epoch": 1.5957225481629425, "grad_norm": 5.453343868255615, "learning_rate": 8.60707478347917e-06, "loss": 0.3309, "step": 268450 }, { "epoch": 1.5957819902396109, "grad_norm": 4.775643825531006, "learning_rate": 8.606931091444287e-06, "loss": 0.36, "step": 268460 }, { "epoch": 1.5958414323162793, "grad_norm": 5.784192085266113, "learning_rate": 8.606787393197837e-06, "loss": 0.3744, "step": 268470 }, { "epoch": 1.5959008743929477, "grad_norm": 4.464701175689697, "learning_rate": 8.60664368874007e-06, "loss": 0.2991, "step": 268480 }, { "epoch": 1.5959603164696161, "grad_norm": 6.536586284637451, "learning_rate": 8.606499978071231e-06, "loss": 0.3968, "step": 268490 }, { "epoch": 1.5960197585462845, "grad_norm": 5.7815470695495605, "learning_rate": 8.60635626119157e-06, "loss": 0.3482, "step": 268500 }, { "epoch": 1.596079200622953, "grad_norm": 4.485178470611572, "learning_rate": 8.606212538101332e-06, "loss": 0.3387, "step": 268510 }, { "epoch": 1.5961386426996214, "grad_norm": 5.474353790283203, "learning_rate": 8.606068808800766e-06, "loss": 0.3522, "step": 268520 }, { "epoch": 1.5961980847762898, "grad_norm": 6.170570373535156, "learning_rate": 8.60592507329012e-06, "loss": 0.3835, "step": 268530 }, { "epoch": 1.5962575268529582, "grad_norm": 3.722904682159424, "learning_rate": 8.60578133156964e-06, "loss": 0.3244, "step": 268540 }, { "epoch": 1.5963169689296266, "grad_norm": 4.859686851501465, "learning_rate": 8.605637583639574e-06, "loss": 0.3248, "step": 268550 }, { "epoch": 1.596376411006295, "grad_norm": 5.399481773376465, "learning_rate": 8.605493829500172e-06, "loss": 0.3882, "step": 268560 }, { "epoch": 1.5964358530829634, "grad_norm": 5.150479793548584, "learning_rate": 8.605350069151677e-06, "loss": 0.3418, "step": 268570 }, { "epoch": 1.5964952951596318, "grad_norm": 5.152989864349365, "learning_rate": 8.605206302594338e-06, "loss": 0.3659, "step": 268580 }, { "epoch": 1.5965547372363, "grad_norm": 5.206892013549805, "learning_rate": 8.605062529828407e-06, "loss": 0.3312, "step": 268590 }, { "epoch": 1.5966141793129685, "grad_norm": 4.656223297119141, "learning_rate": 8.604918750854125e-06, "loss": 0.3528, "step": 268600 }, { "epoch": 1.5966736213896369, "grad_norm": 6.010281562805176, "learning_rate": 8.604774965671744e-06, "loss": 0.3578, "step": 268610 }, { "epoch": 1.5967330634663053, "grad_norm": 4.482248306274414, "learning_rate": 8.604631174281512e-06, "loss": 0.3321, "step": 268620 }, { "epoch": 1.5967925055429737, "grad_norm": 4.21757173538208, "learning_rate": 8.604487376683673e-06, "loss": 0.3453, "step": 268630 }, { "epoch": 1.5968519476196419, "grad_norm": 4.696587562561035, "learning_rate": 8.604343572878478e-06, "loss": 0.356, "step": 268640 }, { "epoch": 1.5969113896963103, "grad_norm": 6.7343974113464355, "learning_rate": 8.604199762866172e-06, "loss": 0.3669, "step": 268650 }, { "epoch": 1.5969708317729787, "grad_norm": 5.404538154602051, "learning_rate": 8.604055946647005e-06, "loss": 0.3252, "step": 268660 }, { "epoch": 1.5970302738496471, "grad_norm": 6.283994197845459, "learning_rate": 8.603912124221222e-06, "loss": 0.3239, "step": 268670 }, { "epoch": 1.5970897159263155, "grad_norm": 5.088531017303467, "learning_rate": 8.603768295589074e-06, "loss": 0.3442, "step": 268680 }, { "epoch": 1.597149158002984, "grad_norm": 5.243353366851807, "learning_rate": 8.603624460750808e-06, "loss": 0.341, "step": 268690 }, { "epoch": 1.5972086000796524, "grad_norm": 5.1952056884765625, "learning_rate": 8.603480619706669e-06, "loss": 0.3324, "step": 268700 }, { "epoch": 1.5972680421563208, "grad_norm": 3.5655136108398438, "learning_rate": 8.603336772456907e-06, "loss": 0.3364, "step": 268710 }, { "epoch": 1.5973274842329892, "grad_norm": 4.151121139526367, "learning_rate": 8.603192919001768e-06, "loss": 0.3377, "step": 268720 }, { "epoch": 1.5973869263096576, "grad_norm": 4.662346839904785, "learning_rate": 8.603049059341501e-06, "loss": 0.3564, "step": 268730 }, { "epoch": 1.597446368386326, "grad_norm": 3.4443252086639404, "learning_rate": 8.602905193476354e-06, "loss": 0.3349, "step": 268740 }, { "epoch": 1.5975058104629944, "grad_norm": 6.028129577636719, "learning_rate": 8.602761321406576e-06, "loss": 0.3586, "step": 268750 }, { "epoch": 1.5975652525396629, "grad_norm": 4.586940288543701, "learning_rate": 8.602617443132411e-06, "loss": 0.3483, "step": 268760 }, { "epoch": 1.5976246946163313, "grad_norm": 5.019026756286621, "learning_rate": 8.60247355865411e-06, "loss": 0.3163, "step": 268770 }, { "epoch": 1.5976841366929995, "grad_norm": 4.625227928161621, "learning_rate": 8.60232966797192e-06, "loss": 0.3229, "step": 268780 }, { "epoch": 1.5977435787696679, "grad_norm": 4.231567859649658, "learning_rate": 8.602185771086087e-06, "loss": 0.359, "step": 268790 }, { "epoch": 1.5978030208463363, "grad_norm": 4.770742416381836, "learning_rate": 8.602041867996862e-06, "loss": 0.3469, "step": 268800 }, { "epoch": 1.5978624629230047, "grad_norm": 6.68633508682251, "learning_rate": 8.60189795870449e-06, "loss": 0.349, "step": 268810 }, { "epoch": 1.597921904999673, "grad_norm": 3.7419028282165527, "learning_rate": 8.601754043209221e-06, "loss": 0.278, "step": 268820 }, { "epoch": 1.5979813470763413, "grad_norm": 4.648861408233643, "learning_rate": 8.601610121511301e-06, "loss": 0.3657, "step": 268830 }, { "epoch": 1.5980407891530097, "grad_norm": 5.423413276672363, "learning_rate": 8.601466193610977e-06, "loss": 0.3302, "step": 268840 }, { "epoch": 1.5981002312296781, "grad_norm": 4.453372955322266, "learning_rate": 8.6013222595085e-06, "loss": 0.3312, "step": 268850 }, { "epoch": 1.5981596733063466, "grad_norm": 4.840575218200684, "learning_rate": 8.601178319204117e-06, "loss": 0.3178, "step": 268860 }, { "epoch": 1.598219115383015, "grad_norm": 5.086569309234619, "learning_rate": 8.601034372698075e-06, "loss": 0.3341, "step": 268870 }, { "epoch": 1.5982785574596834, "grad_norm": 7.12946081161499, "learning_rate": 8.600890419990621e-06, "loss": 0.3544, "step": 268880 }, { "epoch": 1.5983379995363518, "grad_norm": 5.449692249298096, "learning_rate": 8.600746461082005e-06, "loss": 0.3809, "step": 268890 }, { "epoch": 1.5983974416130202, "grad_norm": 5.444324493408203, "learning_rate": 8.600602495972474e-06, "loss": 0.3233, "step": 268900 }, { "epoch": 1.5984568836896886, "grad_norm": 5.782732963562012, "learning_rate": 8.600458524662276e-06, "loss": 0.3597, "step": 268910 }, { "epoch": 1.598516325766357, "grad_norm": 5.212957382202148, "learning_rate": 8.600314547151659e-06, "loss": 0.3206, "step": 268920 }, { "epoch": 1.5985757678430255, "grad_norm": 5.329644680023193, "learning_rate": 8.60017056344087e-06, "loss": 0.3181, "step": 268930 }, { "epoch": 1.5986352099196939, "grad_norm": 4.475995063781738, "learning_rate": 8.60002657353016e-06, "loss": 0.3311, "step": 268940 }, { "epoch": 1.5986946519963623, "grad_norm": 5.098187446594238, "learning_rate": 8.599882577419771e-06, "loss": 0.3389, "step": 268950 }, { "epoch": 1.5987540940730305, "grad_norm": 5.057862281799316, "learning_rate": 8.599738575109957e-06, "loss": 0.3519, "step": 268960 }, { "epoch": 1.598813536149699, "grad_norm": 5.19516658782959, "learning_rate": 8.599594566600964e-06, "loss": 0.3139, "step": 268970 }, { "epoch": 1.5988729782263673, "grad_norm": 5.489750862121582, "learning_rate": 8.599450551893039e-06, "loss": 0.3768, "step": 268980 }, { "epoch": 1.5989324203030357, "grad_norm": 4.721195220947266, "learning_rate": 8.599306530986429e-06, "loss": 0.3825, "step": 268990 }, { "epoch": 1.5989918623797041, "grad_norm": 6.146909713745117, "learning_rate": 8.599162503881386e-06, "loss": 0.3488, "step": 269000 }, { "epoch": 1.5990513044563723, "grad_norm": 4.657812118530273, "learning_rate": 8.599018470578154e-06, "loss": 0.2916, "step": 269010 }, { "epoch": 1.5991107465330407, "grad_norm": 4.529426574707031, "learning_rate": 8.598874431076985e-06, "loss": 0.336, "step": 269020 }, { "epoch": 1.5991701886097092, "grad_norm": 5.350211143493652, "learning_rate": 8.598730385378122e-06, "loss": 0.3352, "step": 269030 }, { "epoch": 1.5992296306863776, "grad_norm": 4.241409778594971, "learning_rate": 8.598586333481817e-06, "loss": 0.3339, "step": 269040 }, { "epoch": 1.599289072763046, "grad_norm": 5.924076080322266, "learning_rate": 8.59844227538832e-06, "loss": 0.345, "step": 269050 }, { "epoch": 1.5993485148397144, "grad_norm": 7.380964756011963, "learning_rate": 8.598298211097871e-06, "loss": 0.335, "step": 269060 }, { "epoch": 1.5994079569163828, "grad_norm": 5.630156517028809, "learning_rate": 8.598154140610726e-06, "loss": 0.348, "step": 269070 }, { "epoch": 1.5994673989930512, "grad_norm": 4.174744606018066, "learning_rate": 8.598010063927129e-06, "loss": 0.3398, "step": 269080 }, { "epoch": 1.5995268410697197, "grad_norm": 5.1414031982421875, "learning_rate": 8.597865981047331e-06, "loss": 0.357, "step": 269090 }, { "epoch": 1.599586283146388, "grad_norm": 5.516692638397217, "learning_rate": 8.597721891971577e-06, "loss": 0.3436, "step": 269100 }, { "epoch": 1.5996457252230565, "grad_norm": 7.677894592285156, "learning_rate": 8.597577796700118e-06, "loss": 0.3473, "step": 269110 }, { "epoch": 1.599705167299725, "grad_norm": 4.120017051696777, "learning_rate": 8.5974336952332e-06, "loss": 0.3475, "step": 269120 }, { "epoch": 1.5997646093763933, "grad_norm": 4.582875728607178, "learning_rate": 8.597289587571072e-06, "loss": 0.3572, "step": 269130 }, { "epoch": 1.5998240514530617, "grad_norm": 4.37462854385376, "learning_rate": 8.597145473713981e-06, "loss": 0.3333, "step": 269140 }, { "epoch": 1.59988349352973, "grad_norm": 4.296713352203369, "learning_rate": 8.597001353662178e-06, "loss": 0.3566, "step": 269150 }, { "epoch": 1.5999429356063983, "grad_norm": 5.014687538146973, "learning_rate": 8.596857227415908e-06, "loss": 0.3108, "step": 269160 }, { "epoch": 1.6000023776830667, "grad_norm": 6.160484790802002, "learning_rate": 8.596713094975422e-06, "loss": 0.3371, "step": 269170 }, { "epoch": 1.6000618197597352, "grad_norm": 4.966912746429443, "learning_rate": 8.596568956340966e-06, "loss": 0.3647, "step": 269180 }, { "epoch": 1.6001212618364034, "grad_norm": 4.038372039794922, "learning_rate": 8.596424811512789e-06, "loss": 0.3171, "step": 269190 }, { "epoch": 1.6001807039130718, "grad_norm": 4.688011646270752, "learning_rate": 8.59628066049114e-06, "loss": 0.3642, "step": 269200 }, { "epoch": 1.6002401459897402, "grad_norm": 4.520746231079102, "learning_rate": 8.596136503276266e-06, "loss": 0.3261, "step": 269210 }, { "epoch": 1.6002995880664086, "grad_norm": 5.555144309997559, "learning_rate": 8.595992339868418e-06, "loss": 0.3675, "step": 269220 }, { "epoch": 1.600359030143077, "grad_norm": 4.927792072296143, "learning_rate": 8.59584817026784e-06, "loss": 0.3222, "step": 269230 }, { "epoch": 1.6004184722197454, "grad_norm": 5.2438459396362305, "learning_rate": 8.595703994474783e-06, "loss": 0.337, "step": 269240 }, { "epoch": 1.6004779142964138, "grad_norm": 5.885430812835693, "learning_rate": 8.595559812489494e-06, "loss": 0.3332, "step": 269250 }, { "epoch": 1.6005373563730823, "grad_norm": 4.6746087074279785, "learning_rate": 8.595415624312222e-06, "loss": 0.3366, "step": 269260 }, { "epoch": 1.6005967984497507, "grad_norm": 6.15955114364624, "learning_rate": 8.595271429943217e-06, "loss": 0.3656, "step": 269270 }, { "epoch": 1.600656240526419, "grad_norm": 4.433974742889404, "learning_rate": 8.595127229382723e-06, "loss": 0.3153, "step": 269280 }, { "epoch": 1.6007156826030875, "grad_norm": 3.3094482421875, "learning_rate": 8.594983022630994e-06, "loss": 0.3114, "step": 269290 }, { "epoch": 1.600775124679756, "grad_norm": 4.90439510345459, "learning_rate": 8.594838809688273e-06, "loss": 0.308, "step": 269300 }, { "epoch": 1.6008345667564243, "grad_norm": 4.578560829162598, "learning_rate": 8.594694590554811e-06, "loss": 0.3245, "step": 269310 }, { "epoch": 1.6008940088330927, "grad_norm": 5.683259010314941, "learning_rate": 8.594550365230856e-06, "loss": 0.347, "step": 269320 }, { "epoch": 1.600953450909761, "grad_norm": 5.116477966308594, "learning_rate": 8.594406133716658e-06, "loss": 0.3736, "step": 269330 }, { "epoch": 1.6010128929864293, "grad_norm": 4.735099792480469, "learning_rate": 8.594261896012461e-06, "loss": 0.3554, "step": 269340 }, { "epoch": 1.6010723350630978, "grad_norm": 4.393157958984375, "learning_rate": 8.594117652118519e-06, "loss": 0.319, "step": 269350 }, { "epoch": 1.6011317771397662, "grad_norm": 5.504885673522949, "learning_rate": 8.593973402035077e-06, "loss": 0.3213, "step": 269360 }, { "epoch": 1.6011912192164346, "grad_norm": 4.960832118988037, "learning_rate": 8.593829145762383e-06, "loss": 0.3431, "step": 269370 }, { "epoch": 1.6012506612931028, "grad_norm": 5.3013176918029785, "learning_rate": 8.593684883300686e-06, "loss": 0.3537, "step": 269380 }, { "epoch": 1.6013101033697712, "grad_norm": 4.804752349853516, "learning_rate": 8.593540614650233e-06, "loss": 0.3625, "step": 269390 }, { "epoch": 1.6013695454464396, "grad_norm": 4.803531169891357, "learning_rate": 8.593396339811279e-06, "loss": 0.323, "step": 269400 }, { "epoch": 1.601428987523108, "grad_norm": 4.470235824584961, "learning_rate": 8.593252058784064e-06, "loss": 0.3444, "step": 269410 }, { "epoch": 1.6014884295997764, "grad_norm": 5.405508041381836, "learning_rate": 8.593107771568842e-06, "loss": 0.3214, "step": 269420 }, { "epoch": 1.6015478716764449, "grad_norm": 5.012024402618408, "learning_rate": 8.59296347816586e-06, "loss": 0.3917, "step": 269430 }, { "epoch": 1.6016073137531133, "grad_norm": 4.8796563148498535, "learning_rate": 8.592819178575364e-06, "loss": 0.3203, "step": 269440 }, { "epoch": 1.6016667558297817, "grad_norm": 4.480456829071045, "learning_rate": 8.592674872797608e-06, "loss": 0.3253, "step": 269450 }, { "epoch": 1.60172619790645, "grad_norm": 4.129672527313232, "learning_rate": 8.592530560832835e-06, "loss": 0.32, "step": 269460 }, { "epoch": 1.6017856399831185, "grad_norm": 4.2862067222595215, "learning_rate": 8.592386242681297e-06, "loss": 0.3335, "step": 269470 }, { "epoch": 1.601845082059787, "grad_norm": 5.122979164123535, "learning_rate": 8.59224191834324e-06, "loss": 0.291, "step": 269480 }, { "epoch": 1.6019045241364553, "grad_norm": 5.740420341491699, "learning_rate": 8.592097587818912e-06, "loss": 0.3272, "step": 269490 }, { "epoch": 1.6019639662131238, "grad_norm": 5.017291069030762, "learning_rate": 8.591953251108567e-06, "loss": 0.3335, "step": 269500 }, { "epoch": 1.6020234082897922, "grad_norm": 5.94149112701416, "learning_rate": 8.59180890821245e-06, "loss": 0.3673, "step": 269510 }, { "epoch": 1.6020828503664604, "grad_norm": 5.51616907119751, "learning_rate": 8.591664559130805e-06, "loss": 0.3105, "step": 269520 }, { "epoch": 1.6021422924431288, "grad_norm": 4.67674446105957, "learning_rate": 8.591520203863888e-06, "loss": 0.323, "step": 269530 }, { "epoch": 1.6022017345197972, "grad_norm": 4.7743964195251465, "learning_rate": 8.591375842411946e-06, "loss": 0.3504, "step": 269540 }, { "epoch": 1.6022611765964656, "grad_norm": 4.5182108879089355, "learning_rate": 8.591231474775226e-06, "loss": 0.331, "step": 269550 }, { "epoch": 1.6023206186731338, "grad_norm": 6.443962574005127, "learning_rate": 8.591087100953973e-06, "loss": 0.3194, "step": 269560 }, { "epoch": 1.6023800607498022, "grad_norm": 5.075364589691162, "learning_rate": 8.590942720948445e-06, "loss": 0.3484, "step": 269570 }, { "epoch": 1.6024395028264706, "grad_norm": 5.512581825256348, "learning_rate": 8.590798334758881e-06, "loss": 0.341, "step": 269580 }, { "epoch": 1.602498944903139, "grad_norm": 5.650716781616211, "learning_rate": 8.590653942385537e-06, "loss": 0.3423, "step": 269590 }, { "epoch": 1.6025583869798075, "grad_norm": 5.722670078277588, "learning_rate": 8.590509543828655e-06, "loss": 0.3543, "step": 269600 }, { "epoch": 1.6026178290564759, "grad_norm": 4.679995536804199, "learning_rate": 8.59036513908849e-06, "loss": 0.3257, "step": 269610 }, { "epoch": 1.6026772711331443, "grad_norm": 6.106729984283447, "learning_rate": 8.590220728165286e-06, "loss": 0.3816, "step": 269620 }, { "epoch": 1.6027367132098127, "grad_norm": 4.469152450561523, "learning_rate": 8.590076311059294e-06, "loss": 0.3403, "step": 269630 }, { "epoch": 1.6027961552864811, "grad_norm": 6.445494651794434, "learning_rate": 8.589931887770763e-06, "loss": 0.3262, "step": 269640 }, { "epoch": 1.6028555973631495, "grad_norm": 6.466548442840576, "learning_rate": 8.58978745829994e-06, "loss": 0.3666, "step": 269650 }, { "epoch": 1.602915039439818, "grad_norm": 5.9756574630737305, "learning_rate": 8.589643022647077e-06, "loss": 0.3776, "step": 269660 }, { "epoch": 1.6029744815164864, "grad_norm": 3.5986857414245605, "learning_rate": 8.589498580812419e-06, "loss": 0.3339, "step": 269670 }, { "epoch": 1.6030339235931548, "grad_norm": 3.7535483837127686, "learning_rate": 8.589354132796215e-06, "loss": 0.3737, "step": 269680 }, { "epoch": 1.6030933656698232, "grad_norm": 4.8563947677612305, "learning_rate": 8.589209678598716e-06, "loss": 0.3266, "step": 269690 }, { "epoch": 1.6031528077464914, "grad_norm": 3.728766441345215, "learning_rate": 8.58906521822017e-06, "loss": 0.3525, "step": 269700 }, { "epoch": 1.6032122498231598, "grad_norm": 5.8585381507873535, "learning_rate": 8.588920751660823e-06, "loss": 0.3082, "step": 269710 }, { "epoch": 1.6032716918998282, "grad_norm": 6.9864888191223145, "learning_rate": 8.58877627892093e-06, "loss": 0.3264, "step": 269720 }, { "epoch": 1.6033311339764966, "grad_norm": 4.812865257263184, "learning_rate": 8.588631800000732e-06, "loss": 0.3251, "step": 269730 }, { "epoch": 1.603390576053165, "grad_norm": 4.3210768699646, "learning_rate": 8.588487314900484e-06, "loss": 0.3199, "step": 269740 }, { "epoch": 1.6034500181298332, "grad_norm": 5.030636310577393, "learning_rate": 8.588342823620433e-06, "loss": 0.3238, "step": 269750 }, { "epoch": 1.6035094602065016, "grad_norm": 5.012286186218262, "learning_rate": 8.588198326160829e-06, "loss": 0.3604, "step": 269760 }, { "epoch": 1.60356890228317, "grad_norm": 5.163362979888916, "learning_rate": 8.588053822521916e-06, "loss": 0.3744, "step": 269770 }, { "epoch": 1.6036283443598385, "grad_norm": 4.267698764801025, "learning_rate": 8.587909312703948e-06, "loss": 0.3542, "step": 269780 }, { "epoch": 1.603687786436507, "grad_norm": 6.262831687927246, "learning_rate": 8.587764796707172e-06, "loss": 0.3825, "step": 269790 }, { "epoch": 1.6037472285131753, "grad_norm": 5.682201862335205, "learning_rate": 8.587620274531835e-06, "loss": 0.3532, "step": 269800 }, { "epoch": 1.6038066705898437, "grad_norm": 4.084682941436768, "learning_rate": 8.587475746178191e-06, "loss": 0.3138, "step": 269810 }, { "epoch": 1.6038661126665121, "grad_norm": 5.656409740447998, "learning_rate": 8.587331211646484e-06, "loss": 0.333, "step": 269820 }, { "epoch": 1.6039255547431805, "grad_norm": 4.206312656402588, "learning_rate": 8.587186670936964e-06, "loss": 0.34, "step": 269830 }, { "epoch": 1.603984996819849, "grad_norm": 4.893013954162598, "learning_rate": 8.587042124049882e-06, "loss": 0.3181, "step": 269840 }, { "epoch": 1.6040444388965174, "grad_norm": 5.554963111877441, "learning_rate": 8.586897570985485e-06, "loss": 0.3976, "step": 269850 }, { "epoch": 1.6041038809731858, "grad_norm": 4.817056655883789, "learning_rate": 8.586753011744022e-06, "loss": 0.3747, "step": 269860 }, { "epoch": 1.6041633230498542, "grad_norm": 3.446296215057373, "learning_rate": 8.586608446325743e-06, "loss": 0.355, "step": 269870 }, { "epoch": 1.6042227651265226, "grad_norm": 4.837390422821045, "learning_rate": 8.586463874730896e-06, "loss": 0.3526, "step": 269880 }, { "epoch": 1.6042822072031908, "grad_norm": 4.500522136688232, "learning_rate": 8.586319296959729e-06, "loss": 0.3753, "step": 269890 }, { "epoch": 1.6043416492798592, "grad_norm": 5.422204494476318, "learning_rate": 8.586174713012494e-06, "loss": 0.3542, "step": 269900 }, { "epoch": 1.6044010913565276, "grad_norm": 4.872522354125977, "learning_rate": 8.586030122889437e-06, "loss": 0.352, "step": 269910 }, { "epoch": 1.604460533433196, "grad_norm": 3.651336669921875, "learning_rate": 8.58588552659081e-06, "loss": 0.311, "step": 269920 }, { "epoch": 1.6045199755098642, "grad_norm": 3.8288018703460693, "learning_rate": 8.585740924116858e-06, "loss": 0.292, "step": 269930 }, { "epoch": 1.6045794175865327, "grad_norm": 5.0752997398376465, "learning_rate": 8.585596315467835e-06, "loss": 0.324, "step": 269940 }, { "epoch": 1.604638859663201, "grad_norm": 6.045736312866211, "learning_rate": 8.585451700643986e-06, "loss": 0.3703, "step": 269950 }, { "epoch": 1.6046983017398695, "grad_norm": 5.099301815032959, "learning_rate": 8.58530707964556e-06, "loss": 0.3502, "step": 269960 }, { "epoch": 1.604757743816538, "grad_norm": 5.013528347015381, "learning_rate": 8.585162452472808e-06, "loss": 0.3476, "step": 269970 }, { "epoch": 1.6048171858932063, "grad_norm": 4.711950302124023, "learning_rate": 8.58501781912598e-06, "loss": 0.3605, "step": 269980 }, { "epoch": 1.6048766279698747, "grad_norm": 5.157452583312988, "learning_rate": 8.584873179605323e-06, "loss": 0.3202, "step": 269990 }, { "epoch": 1.6049360700465432, "grad_norm": 6.203441619873047, "learning_rate": 8.584728533911087e-06, "loss": 0.372, "step": 270000 }, { "epoch": 1.6049955121232116, "grad_norm": 6.315461158752441, "learning_rate": 8.584583882043519e-06, "loss": 0.3113, "step": 270010 }, { "epoch": 1.60505495419988, "grad_norm": 4.596642017364502, "learning_rate": 8.584439224002871e-06, "loss": 0.3578, "step": 270020 }, { "epoch": 1.6051143962765484, "grad_norm": 5.421436786651611, "learning_rate": 8.58429455978939e-06, "loss": 0.3436, "step": 270030 }, { "epoch": 1.6051738383532168, "grad_norm": 5.4621262550354, "learning_rate": 8.584149889403328e-06, "loss": 0.3426, "step": 270040 }, { "epoch": 1.6052332804298852, "grad_norm": 5.11193323135376, "learning_rate": 8.58400521284493e-06, "loss": 0.3641, "step": 270050 }, { "epoch": 1.6052927225065536, "grad_norm": 5.593723297119141, "learning_rate": 8.58386053011445e-06, "loss": 0.3544, "step": 270060 }, { "epoch": 1.6053521645832218, "grad_norm": 4.888693809509277, "learning_rate": 8.583715841212132e-06, "loss": 0.2948, "step": 270070 }, { "epoch": 1.6054116066598902, "grad_norm": 5.472147464752197, "learning_rate": 8.58357114613823e-06, "loss": 0.3257, "step": 270080 }, { "epoch": 1.6054710487365587, "grad_norm": 5.425399303436279, "learning_rate": 8.583426444892988e-06, "loss": 0.3764, "step": 270090 }, { "epoch": 1.605530490813227, "grad_norm": 4.929218769073486, "learning_rate": 8.583281737476662e-06, "loss": 0.3174, "step": 270100 }, { "epoch": 1.6055899328898955, "grad_norm": 6.710903167724609, "learning_rate": 8.583137023889494e-06, "loss": 0.3637, "step": 270110 }, { "epoch": 1.6056493749665637, "grad_norm": 3.9443466663360596, "learning_rate": 8.582992304131737e-06, "loss": 0.36, "step": 270120 }, { "epoch": 1.605708817043232, "grad_norm": 4.5727338790893555, "learning_rate": 8.582847578203642e-06, "loss": 0.3351, "step": 270130 }, { "epoch": 1.6057682591199005, "grad_norm": 4.832973957061768, "learning_rate": 8.582702846105453e-06, "loss": 0.312, "step": 270140 }, { "epoch": 1.605827701196569, "grad_norm": 5.659033298492432, "learning_rate": 8.582558107837425e-06, "loss": 0.3316, "step": 270150 }, { "epoch": 1.6058871432732373, "grad_norm": 6.557253837585449, "learning_rate": 8.582413363399803e-06, "loss": 0.3353, "step": 270160 }, { "epoch": 1.6059465853499058, "grad_norm": 6.625061988830566, "learning_rate": 8.582268612792836e-06, "loss": 0.3733, "step": 270170 }, { "epoch": 1.6060060274265742, "grad_norm": 6.220977783203125, "learning_rate": 8.582123856016777e-06, "loss": 0.3462, "step": 270180 }, { "epoch": 1.6060654695032426, "grad_norm": 6.467791557312012, "learning_rate": 8.581979093071873e-06, "loss": 0.3358, "step": 270190 }, { "epoch": 1.606124911579911, "grad_norm": 4.880735397338867, "learning_rate": 8.581834323958374e-06, "loss": 0.364, "step": 270200 }, { "epoch": 1.6061843536565794, "grad_norm": 4.548768043518066, "learning_rate": 8.581689548676528e-06, "loss": 0.3441, "step": 270210 }, { "epoch": 1.6062437957332478, "grad_norm": 3.8323028087615967, "learning_rate": 8.581544767226587e-06, "loss": 0.3104, "step": 270220 }, { "epoch": 1.6063032378099162, "grad_norm": 4.810322284698486, "learning_rate": 8.581399979608797e-06, "loss": 0.3503, "step": 270230 }, { "epoch": 1.6063626798865847, "grad_norm": 4.38029670715332, "learning_rate": 8.58125518582341e-06, "loss": 0.3214, "step": 270240 }, { "epoch": 1.606422121963253, "grad_norm": 4.505904674530029, "learning_rate": 8.581110385870673e-06, "loss": 0.3256, "step": 270250 }, { "epoch": 1.6064815640399213, "grad_norm": 7.224747657775879, "learning_rate": 8.580965579750837e-06, "loss": 0.3544, "step": 270260 }, { "epoch": 1.6065410061165897, "grad_norm": 5.009901523590088, "learning_rate": 8.58082076746415e-06, "loss": 0.3319, "step": 270270 }, { "epoch": 1.606600448193258, "grad_norm": 3.783949851989746, "learning_rate": 8.580675949010863e-06, "loss": 0.3146, "step": 270280 }, { "epoch": 1.6066598902699265, "grad_norm": 3.961029052734375, "learning_rate": 8.580531124391227e-06, "loss": 0.3161, "step": 270290 }, { "epoch": 1.6067193323465947, "grad_norm": 6.487024307250977, "learning_rate": 8.580386293605487e-06, "loss": 0.3448, "step": 270300 }, { "epoch": 1.6067787744232631, "grad_norm": 4.6874213218688965, "learning_rate": 8.580241456653895e-06, "loss": 0.309, "step": 270310 }, { "epoch": 1.6068382164999315, "grad_norm": 6.216097831726074, "learning_rate": 8.580096613536701e-06, "loss": 0.389, "step": 270320 }, { "epoch": 1.6068976585766, "grad_norm": 4.026830673217773, "learning_rate": 8.579951764254152e-06, "loss": 0.3304, "step": 270330 }, { "epoch": 1.6069571006532684, "grad_norm": 5.316323280334473, "learning_rate": 8.579806908806501e-06, "loss": 0.3282, "step": 270340 }, { "epoch": 1.6070165427299368, "grad_norm": 4.658027172088623, "learning_rate": 8.579662047193994e-06, "loss": 0.3071, "step": 270350 }, { "epoch": 1.6070759848066052, "grad_norm": 4.580874443054199, "learning_rate": 8.57951717941688e-06, "loss": 0.3468, "step": 270360 }, { "epoch": 1.6071354268832736, "grad_norm": 4.675622940063477, "learning_rate": 8.579372305475414e-06, "loss": 0.337, "step": 270370 }, { "epoch": 1.607194868959942, "grad_norm": 4.965803146362305, "learning_rate": 8.579227425369839e-06, "loss": 0.3433, "step": 270380 }, { "epoch": 1.6072543110366104, "grad_norm": 6.029847145080566, "learning_rate": 8.579082539100407e-06, "loss": 0.3657, "step": 270390 }, { "epoch": 1.6073137531132788, "grad_norm": 4.4082417488098145, "learning_rate": 8.57893764666737e-06, "loss": 0.348, "step": 270400 }, { "epoch": 1.6073731951899473, "grad_norm": 3.545044183731079, "learning_rate": 8.578792748070974e-06, "loss": 0.3406, "step": 270410 }, { "epoch": 1.6074326372666157, "grad_norm": 3.7254016399383545, "learning_rate": 8.578647843311469e-06, "loss": 0.3484, "step": 270420 }, { "epoch": 1.607492079343284, "grad_norm": 5.8983049392700195, "learning_rate": 8.578502932389108e-06, "loss": 0.3059, "step": 270430 }, { "epoch": 1.6075515214199523, "grad_norm": 4.0327301025390625, "learning_rate": 8.578358015304136e-06, "loss": 0.3554, "step": 270440 }, { "epoch": 1.6076109634966207, "grad_norm": 6.364401817321777, "learning_rate": 8.578213092056805e-06, "loss": 0.3372, "step": 270450 }, { "epoch": 1.607670405573289, "grad_norm": 5.132669448852539, "learning_rate": 8.578068162647364e-06, "loss": 0.3674, "step": 270460 }, { "epoch": 1.6077298476499575, "grad_norm": 5.769030570983887, "learning_rate": 8.577923227076065e-06, "loss": 0.3397, "step": 270470 }, { "epoch": 1.607789289726626, "grad_norm": 4.178032398223877, "learning_rate": 8.577778285343153e-06, "loss": 0.3132, "step": 270480 }, { "epoch": 1.6078487318032941, "grad_norm": 5.376582145690918, "learning_rate": 8.577633337448879e-06, "loss": 0.3392, "step": 270490 }, { "epoch": 1.6079081738799625, "grad_norm": 5.298402309417725, "learning_rate": 8.577488383393495e-06, "loss": 0.2987, "step": 270500 }, { "epoch": 1.607967615956631, "grad_norm": 6.5343732833862305, "learning_rate": 8.577343423177248e-06, "loss": 0.3462, "step": 270510 }, { "epoch": 1.6080270580332994, "grad_norm": 4.903979301452637, "learning_rate": 8.57719845680039e-06, "loss": 0.3515, "step": 270520 }, { "epoch": 1.6080865001099678, "grad_norm": 4.6001877784729, "learning_rate": 8.577053484263169e-06, "loss": 0.3276, "step": 270530 }, { "epoch": 1.6081459421866362, "grad_norm": 5.96597957611084, "learning_rate": 8.576908505565836e-06, "loss": 0.3366, "step": 270540 }, { "epoch": 1.6082053842633046, "grad_norm": 5.265657424926758, "learning_rate": 8.576763520708637e-06, "loss": 0.3668, "step": 270550 }, { "epoch": 1.608264826339973, "grad_norm": 5.3293070793151855, "learning_rate": 8.576618529691828e-06, "loss": 0.3555, "step": 270560 }, { "epoch": 1.6083242684166414, "grad_norm": 5.747192859649658, "learning_rate": 8.576473532515653e-06, "loss": 0.3627, "step": 270570 }, { "epoch": 1.6083837104933099, "grad_norm": 5.630478858947754, "learning_rate": 8.576328529180364e-06, "loss": 0.3276, "step": 270580 }, { "epoch": 1.6084431525699783, "grad_norm": 3.557046890258789, "learning_rate": 8.57618351968621e-06, "loss": 0.3297, "step": 270590 }, { "epoch": 1.6085025946466467, "grad_norm": 4.6211934089660645, "learning_rate": 8.576038504033443e-06, "loss": 0.3738, "step": 270600 }, { "epoch": 1.608562036723315, "grad_norm": 4.26634407043457, "learning_rate": 8.575893482222309e-06, "loss": 0.3692, "step": 270610 }, { "epoch": 1.6086214787999835, "grad_norm": 4.782625675201416, "learning_rate": 8.575748454253061e-06, "loss": 0.3224, "step": 270620 }, { "epoch": 1.6086809208766517, "grad_norm": 5.210999011993408, "learning_rate": 8.57560342012595e-06, "loss": 0.3266, "step": 270630 }, { "epoch": 1.6087403629533201, "grad_norm": 5.7943878173828125, "learning_rate": 8.57545837984122e-06, "loss": 0.3464, "step": 270640 }, { "epoch": 1.6087998050299885, "grad_norm": 4.738941192626953, "learning_rate": 8.575313333399123e-06, "loss": 0.362, "step": 270650 }, { "epoch": 1.608859247106657, "grad_norm": 5.9282402992248535, "learning_rate": 8.575168280799912e-06, "loss": 0.3445, "step": 270660 }, { "epoch": 1.6089186891833251, "grad_norm": 6.011966228485107, "learning_rate": 8.575023222043834e-06, "loss": 0.3614, "step": 270670 }, { "epoch": 1.6089781312599936, "grad_norm": 4.187802314758301, "learning_rate": 8.574878157131139e-06, "loss": 0.3495, "step": 270680 }, { "epoch": 1.609037573336662, "grad_norm": 4.747269153594971, "learning_rate": 8.57473308606208e-06, "loss": 0.3239, "step": 270690 }, { "epoch": 1.6090970154133304, "grad_norm": 6.173657417297363, "learning_rate": 8.5745880088369e-06, "loss": 0.3349, "step": 270700 }, { "epoch": 1.6091564574899988, "grad_norm": 5.685144424438477, "learning_rate": 8.574442925455856e-06, "loss": 0.3209, "step": 270710 }, { "epoch": 1.6092158995666672, "grad_norm": 4.91652774810791, "learning_rate": 8.574297835919193e-06, "loss": 0.3362, "step": 270720 }, { "epoch": 1.6092753416433356, "grad_norm": 4.081739902496338, "learning_rate": 8.574152740227163e-06, "loss": 0.3678, "step": 270730 }, { "epoch": 1.609334783720004, "grad_norm": 4.9485883712768555, "learning_rate": 8.574007638380017e-06, "loss": 0.3587, "step": 270740 }, { "epoch": 1.6093942257966725, "grad_norm": 5.219393730163574, "learning_rate": 8.573862530378002e-06, "loss": 0.3453, "step": 270750 }, { "epoch": 1.6094536678733409, "grad_norm": 5.154773712158203, "learning_rate": 8.57371741622137e-06, "loss": 0.3013, "step": 270760 }, { "epoch": 1.6095131099500093, "grad_norm": 3.7747433185577393, "learning_rate": 8.573572295910368e-06, "loss": 0.3325, "step": 270770 }, { "epoch": 1.6095725520266777, "grad_norm": 4.0149641036987305, "learning_rate": 8.57342716944525e-06, "loss": 0.3195, "step": 270780 }, { "epoch": 1.6096319941033461, "grad_norm": 3.8625259399414062, "learning_rate": 8.573282036826266e-06, "loss": 0.2913, "step": 270790 }, { "epoch": 1.6096914361800145, "grad_norm": 4.399684906005859, "learning_rate": 8.57313689805366e-06, "loss": 0.3258, "step": 270800 }, { "epoch": 1.6097508782566827, "grad_norm": 5.167392730712891, "learning_rate": 8.57299175312769e-06, "loss": 0.3911, "step": 270810 }, { "epoch": 1.6098103203333511, "grad_norm": 5.550490379333496, "learning_rate": 8.572846602048599e-06, "loss": 0.3483, "step": 270820 }, { "epoch": 1.6098697624100196, "grad_norm": 5.354302883148193, "learning_rate": 8.57270144481664e-06, "loss": 0.3349, "step": 270830 }, { "epoch": 1.609929204486688, "grad_norm": 4.27252721786499, "learning_rate": 8.572556281432063e-06, "loss": 0.3044, "step": 270840 }, { "epoch": 1.6099886465633564, "grad_norm": 5.747807025909424, "learning_rate": 8.572411111895119e-06, "loss": 0.3874, "step": 270850 }, { "epoch": 1.6100480886400246, "grad_norm": 5.459982395172119, "learning_rate": 8.572265936206055e-06, "loss": 0.3383, "step": 270860 }, { "epoch": 1.610107530716693, "grad_norm": 4.57315731048584, "learning_rate": 8.572120754365126e-06, "loss": 0.3326, "step": 270870 }, { "epoch": 1.6101669727933614, "grad_norm": 4.772860527038574, "learning_rate": 8.571975566372575e-06, "loss": 0.3705, "step": 270880 }, { "epoch": 1.6102264148700298, "grad_norm": 4.145089149475098, "learning_rate": 8.571830372228658e-06, "loss": 0.3576, "step": 270890 }, { "epoch": 1.6102858569466982, "grad_norm": 4.907696723937988, "learning_rate": 8.571685171933621e-06, "loss": 0.3313, "step": 270900 }, { "epoch": 1.6103452990233666, "grad_norm": 4.7064290046691895, "learning_rate": 8.571539965487719e-06, "loss": 0.3669, "step": 270910 }, { "epoch": 1.610404741100035, "grad_norm": 5.561077117919922, "learning_rate": 8.571394752891197e-06, "loss": 0.3378, "step": 270920 }, { "epoch": 1.6104641831767035, "grad_norm": 5.521298408508301, "learning_rate": 8.571249534144309e-06, "loss": 0.3363, "step": 270930 }, { "epoch": 1.610523625253372, "grad_norm": 3.6330535411834717, "learning_rate": 8.5711043092473e-06, "loss": 0.3379, "step": 270940 }, { "epoch": 1.6105830673300403, "grad_norm": 4.279906749725342, "learning_rate": 8.570959078200426e-06, "loss": 0.3508, "step": 270950 }, { "epoch": 1.6106425094067087, "grad_norm": 4.983497619628906, "learning_rate": 8.570813841003933e-06, "loss": 0.3361, "step": 270960 }, { "epoch": 1.6107019514833771, "grad_norm": 5.147820472717285, "learning_rate": 8.570668597658072e-06, "loss": 0.31, "step": 270970 }, { "epoch": 1.6107613935600456, "grad_norm": 6.169742107391357, "learning_rate": 8.570523348163096e-06, "loss": 0.3392, "step": 270980 }, { "epoch": 1.610820835636714, "grad_norm": 6.415215492248535, "learning_rate": 8.57037809251925e-06, "loss": 0.3499, "step": 270990 }, { "epoch": 1.6108802777133822, "grad_norm": 5.560572147369385, "learning_rate": 8.570232830726788e-06, "loss": 0.3323, "step": 271000 }, { "epoch": 1.6109397197900506, "grad_norm": 6.836584568023682, "learning_rate": 8.57008756278596e-06, "loss": 0.3174, "step": 271010 }, { "epoch": 1.610999161866719, "grad_norm": 6.278081893920898, "learning_rate": 8.569942288697015e-06, "loss": 0.3779, "step": 271020 }, { "epoch": 1.6110586039433874, "grad_norm": 6.02714204788208, "learning_rate": 8.569797008460203e-06, "loss": 0.3704, "step": 271030 }, { "epoch": 1.6111180460200556, "grad_norm": 4.958766460418701, "learning_rate": 8.569651722075773e-06, "loss": 0.3411, "step": 271040 }, { "epoch": 1.611177488096724, "grad_norm": 5.8424506187438965, "learning_rate": 8.569506429543978e-06, "loss": 0.3463, "step": 271050 }, { "epoch": 1.6112369301733924, "grad_norm": 4.727768898010254, "learning_rate": 8.569361130865069e-06, "loss": 0.3286, "step": 271060 }, { "epoch": 1.6112963722500608, "grad_norm": 5.835424900054932, "learning_rate": 8.569215826039292e-06, "loss": 0.3321, "step": 271070 }, { "epoch": 1.6113558143267293, "grad_norm": 5.612460136413574, "learning_rate": 8.5690705150669e-06, "loss": 0.3371, "step": 271080 }, { "epoch": 1.6114152564033977, "grad_norm": 5.682687282562256, "learning_rate": 8.568925197948144e-06, "loss": 0.3597, "step": 271090 }, { "epoch": 1.611474698480066, "grad_norm": 4.476108551025391, "learning_rate": 8.568779874683271e-06, "loss": 0.3694, "step": 271100 }, { "epoch": 1.6115341405567345, "grad_norm": 5.577610969543457, "learning_rate": 8.568634545272534e-06, "loss": 0.3309, "step": 271110 }, { "epoch": 1.611593582633403, "grad_norm": 4.225053310394287, "learning_rate": 8.568489209716184e-06, "loss": 0.337, "step": 271120 }, { "epoch": 1.6116530247100713, "grad_norm": 4.116135120391846, "learning_rate": 8.568343868014468e-06, "loss": 0.3291, "step": 271130 }, { "epoch": 1.6117124667867397, "grad_norm": 3.9824235439300537, "learning_rate": 8.568198520167637e-06, "loss": 0.3102, "step": 271140 }, { "epoch": 1.6117719088634082, "grad_norm": 4.8936991691589355, "learning_rate": 8.568053166175945e-06, "loss": 0.329, "step": 271150 }, { "epoch": 1.6118313509400766, "grad_norm": 3.871593713760376, "learning_rate": 8.567907806039638e-06, "loss": 0.34, "step": 271160 }, { "epoch": 1.611890793016745, "grad_norm": 4.737676620483398, "learning_rate": 8.567762439758968e-06, "loss": 0.37, "step": 271170 }, { "epoch": 1.6119502350934132, "grad_norm": 4.426005840301514, "learning_rate": 8.567617067334187e-06, "loss": 0.3266, "step": 271180 }, { "epoch": 1.6120096771700816, "grad_norm": 4.990720272064209, "learning_rate": 8.567471688765544e-06, "loss": 0.3585, "step": 271190 }, { "epoch": 1.61206911924675, "grad_norm": 5.852462291717529, "learning_rate": 8.567326304053286e-06, "loss": 0.3732, "step": 271200 }, { "epoch": 1.6121285613234184, "grad_norm": 6.08693790435791, "learning_rate": 8.567180913197667e-06, "loss": 0.3653, "step": 271210 }, { "epoch": 1.6121880034000868, "grad_norm": 5.042360782623291, "learning_rate": 8.56703551619894e-06, "loss": 0.3541, "step": 271220 }, { "epoch": 1.612247445476755, "grad_norm": 6.20785665512085, "learning_rate": 8.56689011305735e-06, "loss": 0.3524, "step": 271230 }, { "epoch": 1.6123068875534234, "grad_norm": 3.890536069869995, "learning_rate": 8.56674470377315e-06, "loss": 0.369, "step": 271240 }, { "epoch": 1.6123663296300919, "grad_norm": 5.184338092803955, "learning_rate": 8.56659928834659e-06, "loss": 0.3517, "step": 271250 }, { "epoch": 1.6124257717067603, "grad_norm": 4.354795455932617, "learning_rate": 8.56645386677792e-06, "loss": 0.3623, "step": 271260 }, { "epoch": 1.6124852137834287, "grad_norm": 3.6607651710510254, "learning_rate": 8.566308439067392e-06, "loss": 0.317, "step": 271270 }, { "epoch": 1.612544655860097, "grad_norm": 5.127852439880371, "learning_rate": 8.566163005215255e-06, "loss": 0.3148, "step": 271280 }, { "epoch": 1.6126040979367655, "grad_norm": 4.182417869567871, "learning_rate": 8.566017565221759e-06, "loss": 0.3001, "step": 271290 }, { "epoch": 1.612663540013434, "grad_norm": 4.347513675689697, "learning_rate": 8.565872119087154e-06, "loss": 0.3342, "step": 271300 }, { "epoch": 1.6127229820901023, "grad_norm": 4.453871250152588, "learning_rate": 8.565726666811696e-06, "loss": 0.3314, "step": 271310 }, { "epoch": 1.6127824241667708, "grad_norm": 6.244272708892822, "learning_rate": 8.565581208395627e-06, "loss": 0.369, "step": 271320 }, { "epoch": 1.6128418662434392, "grad_norm": 5.45586633682251, "learning_rate": 8.565435743839205e-06, "loss": 0.3406, "step": 271330 }, { "epoch": 1.6129013083201076, "grad_norm": 5.586031913757324, "learning_rate": 8.565290273142674e-06, "loss": 0.3518, "step": 271340 }, { "epoch": 1.612960750396776, "grad_norm": 5.7182793617248535, "learning_rate": 8.565144796306291e-06, "loss": 0.3366, "step": 271350 }, { "epoch": 1.6130201924734444, "grad_norm": 5.497264862060547, "learning_rate": 8.564999313330302e-06, "loss": 0.3267, "step": 271360 }, { "epoch": 1.6130796345501126, "grad_norm": 4.887702465057373, "learning_rate": 8.564853824214958e-06, "loss": 0.3268, "step": 271370 }, { "epoch": 1.613139076626781, "grad_norm": 5.145912170410156, "learning_rate": 8.564708328960512e-06, "loss": 0.3648, "step": 271380 }, { "epoch": 1.6131985187034494, "grad_norm": 3.7097511291503906, "learning_rate": 8.56456282756721e-06, "loss": 0.3383, "step": 271390 }, { "epoch": 1.6132579607801179, "grad_norm": 6.450765132904053, "learning_rate": 8.564417320035308e-06, "loss": 0.332, "step": 271400 }, { "epoch": 1.613317402856786, "grad_norm": 4.235958099365234, "learning_rate": 8.564271806365055e-06, "loss": 0.3676, "step": 271410 }, { "epoch": 1.6133768449334545, "grad_norm": 5.0299201011657715, "learning_rate": 8.564126286556697e-06, "loss": 0.3764, "step": 271420 }, { "epoch": 1.6134362870101229, "grad_norm": 4.552548408508301, "learning_rate": 8.56398076061049e-06, "loss": 0.3491, "step": 271430 }, { "epoch": 1.6134957290867913, "grad_norm": 4.456300735473633, "learning_rate": 8.563835228526684e-06, "loss": 0.3619, "step": 271440 }, { "epoch": 1.6135551711634597, "grad_norm": 3.6533002853393555, "learning_rate": 8.563689690305529e-06, "loss": 0.3334, "step": 271450 }, { "epoch": 1.6136146132401281, "grad_norm": 5.138882160186768, "learning_rate": 8.563544145947272e-06, "loss": 0.3384, "step": 271460 }, { "epoch": 1.6136740553167965, "grad_norm": 4.918532848358154, "learning_rate": 8.56339859545217e-06, "loss": 0.3448, "step": 271470 }, { "epoch": 1.613733497393465, "grad_norm": 6.028501987457275, "learning_rate": 8.563253038820467e-06, "loss": 0.3196, "step": 271480 }, { "epoch": 1.6137929394701334, "grad_norm": 4.739839553833008, "learning_rate": 8.56310747605242e-06, "loss": 0.3343, "step": 271490 }, { "epoch": 1.6138523815468018, "grad_norm": 4.683279514312744, "learning_rate": 8.562961907148276e-06, "loss": 0.326, "step": 271500 }, { "epoch": 1.6139118236234702, "grad_norm": 4.361998081207275, "learning_rate": 8.562816332108285e-06, "loss": 0.3373, "step": 271510 }, { "epoch": 1.6139712657001386, "grad_norm": 7.270082950592041, "learning_rate": 8.562670750932702e-06, "loss": 0.336, "step": 271520 }, { "epoch": 1.614030707776807, "grad_norm": 6.9047651290893555, "learning_rate": 8.562525163621773e-06, "loss": 0.3306, "step": 271530 }, { "epoch": 1.6140901498534754, "grad_norm": 4.388394355773926, "learning_rate": 8.562379570175751e-06, "loss": 0.2994, "step": 271540 }, { "epoch": 1.6141495919301436, "grad_norm": 4.546326637268066, "learning_rate": 8.562233970594886e-06, "loss": 0.3065, "step": 271550 }, { "epoch": 1.614209034006812, "grad_norm": 4.32147216796875, "learning_rate": 8.562088364879431e-06, "loss": 0.3442, "step": 271560 }, { "epoch": 1.6142684760834805, "grad_norm": 5.935161113739014, "learning_rate": 8.561942753029632e-06, "loss": 0.3282, "step": 271570 }, { "epoch": 1.6143279181601489, "grad_norm": 4.829160690307617, "learning_rate": 8.561797135045744e-06, "loss": 0.3479, "step": 271580 }, { "epoch": 1.6143873602368173, "grad_norm": 4.947659015655518, "learning_rate": 8.561651510928018e-06, "loss": 0.3523, "step": 271590 }, { "epoch": 1.6144468023134855, "grad_norm": 4.871246814727783, "learning_rate": 8.561505880676699e-06, "loss": 0.3538, "step": 271600 }, { "epoch": 1.6145062443901539, "grad_norm": 6.237017631530762, "learning_rate": 8.561360244292045e-06, "loss": 0.3409, "step": 271610 }, { "epoch": 1.6145656864668223, "grad_norm": 5.166469573974609, "learning_rate": 8.561214601774304e-06, "loss": 0.3181, "step": 271620 }, { "epoch": 1.6146251285434907, "grad_norm": 6.140163898468018, "learning_rate": 8.561068953123725e-06, "loss": 0.3494, "step": 271630 }, { "epoch": 1.6146845706201591, "grad_norm": 5.716149806976318, "learning_rate": 8.560923298340562e-06, "loss": 0.3071, "step": 271640 }, { "epoch": 1.6147440126968275, "grad_norm": 5.705016136169434, "learning_rate": 8.560777637425061e-06, "loss": 0.3503, "step": 271650 }, { "epoch": 1.614803454773496, "grad_norm": 5.910730838775635, "learning_rate": 8.560631970377479e-06, "loss": 0.3501, "step": 271660 }, { "epoch": 1.6148628968501644, "grad_norm": 5.306509971618652, "learning_rate": 8.560486297198063e-06, "loss": 0.3564, "step": 271670 }, { "epoch": 1.6149223389268328, "grad_norm": 5.669841289520264, "learning_rate": 8.560340617887065e-06, "loss": 0.3502, "step": 271680 }, { "epoch": 1.6149817810035012, "grad_norm": 7.240171909332275, "learning_rate": 8.560194932444736e-06, "loss": 0.3328, "step": 271690 }, { "epoch": 1.6150412230801696, "grad_norm": 3.6204071044921875, "learning_rate": 8.560049240871325e-06, "loss": 0.3107, "step": 271700 }, { "epoch": 1.615100665156838, "grad_norm": 4.700511932373047, "learning_rate": 8.559903543167085e-06, "loss": 0.3627, "step": 271710 }, { "epoch": 1.6151601072335064, "grad_norm": 5.1111345291137695, "learning_rate": 8.559757839332267e-06, "loss": 0.354, "step": 271720 }, { "epoch": 1.6152195493101749, "grad_norm": 6.4186110496521, "learning_rate": 8.559612129367121e-06, "loss": 0.3565, "step": 271730 }, { "epoch": 1.615278991386843, "grad_norm": 4.5156636238098145, "learning_rate": 8.559466413271898e-06, "loss": 0.3375, "step": 271740 }, { "epoch": 1.6153384334635115, "grad_norm": 5.021573543548584, "learning_rate": 8.55932069104685e-06, "loss": 0.3196, "step": 271750 }, { "epoch": 1.6153978755401799, "grad_norm": 6.8053879737854, "learning_rate": 8.559174962692226e-06, "loss": 0.342, "step": 271760 }, { "epoch": 1.6154573176168483, "grad_norm": 6.44260311126709, "learning_rate": 8.559029228208277e-06, "loss": 0.3348, "step": 271770 }, { "epoch": 1.6155167596935165, "grad_norm": 5.985740661621094, "learning_rate": 8.558883487595257e-06, "loss": 0.3696, "step": 271780 }, { "epoch": 1.615576201770185, "grad_norm": 3.837148904800415, "learning_rate": 8.558737740853416e-06, "loss": 0.3063, "step": 271790 }, { "epoch": 1.6156356438468533, "grad_norm": 5.465943336486816, "learning_rate": 8.558591987983002e-06, "loss": 0.3432, "step": 271800 }, { "epoch": 1.6156950859235217, "grad_norm": 4.180629730224609, "learning_rate": 8.558446228984268e-06, "loss": 0.3201, "step": 271810 }, { "epoch": 1.6157545280001901, "grad_norm": 4.76898193359375, "learning_rate": 8.558300463857465e-06, "loss": 0.3528, "step": 271820 }, { "epoch": 1.6158139700768586, "grad_norm": 4.5765180587768555, "learning_rate": 8.558154692602845e-06, "loss": 0.3422, "step": 271830 }, { "epoch": 1.615873412153527, "grad_norm": 4.274449348449707, "learning_rate": 8.558008915220657e-06, "loss": 0.3383, "step": 271840 }, { "epoch": 1.6159328542301954, "grad_norm": 5.752263069152832, "learning_rate": 8.557863131711154e-06, "loss": 0.3374, "step": 271850 }, { "epoch": 1.6159922963068638, "grad_norm": 5.056330680847168, "learning_rate": 8.557717342074585e-06, "loss": 0.3061, "step": 271860 }, { "epoch": 1.6160517383835322, "grad_norm": 5.501590728759766, "learning_rate": 8.557571546311202e-06, "loss": 0.3442, "step": 271870 }, { "epoch": 1.6161111804602006, "grad_norm": 4.205453395843506, "learning_rate": 8.557425744421259e-06, "loss": 0.3179, "step": 271880 }, { "epoch": 1.616170622536869, "grad_norm": 5.438313007354736, "learning_rate": 8.557279936405002e-06, "loss": 0.3335, "step": 271890 }, { "epoch": 1.6162300646135375, "grad_norm": 4.809144496917725, "learning_rate": 8.557134122262687e-06, "loss": 0.368, "step": 271900 }, { "epoch": 1.6162895066902059, "grad_norm": 5.523889064788818, "learning_rate": 8.55698830199456e-06, "loss": 0.3558, "step": 271910 }, { "epoch": 1.616348948766874, "grad_norm": 5.880710601806641, "learning_rate": 8.556842475600876e-06, "loss": 0.3583, "step": 271920 }, { "epoch": 1.6164083908435425, "grad_norm": 3.621046543121338, "learning_rate": 8.556696643081884e-06, "loss": 0.3311, "step": 271930 }, { "epoch": 1.616467832920211, "grad_norm": 4.312537670135498, "learning_rate": 8.556550804437836e-06, "loss": 0.3218, "step": 271940 }, { "epoch": 1.6165272749968793, "grad_norm": 5.346024513244629, "learning_rate": 8.556404959668984e-06, "loss": 0.3763, "step": 271950 }, { "epoch": 1.6165867170735477, "grad_norm": 4.312221050262451, "learning_rate": 8.556259108775577e-06, "loss": 0.3087, "step": 271960 }, { "epoch": 1.616646159150216, "grad_norm": 4.6091156005859375, "learning_rate": 8.55611325175787e-06, "loss": 0.3851, "step": 271970 }, { "epoch": 1.6167056012268843, "grad_norm": 5.556053638458252, "learning_rate": 8.55596738861611e-06, "loss": 0.3731, "step": 271980 }, { "epoch": 1.6167650433035528, "grad_norm": 4.72116756439209, "learning_rate": 8.555821519350548e-06, "loss": 0.3421, "step": 271990 }, { "epoch": 1.6168244853802212, "grad_norm": 3.5361533164978027, "learning_rate": 8.555675643961442e-06, "loss": 0.3431, "step": 272000 }, { "epoch": 1.6168839274568896, "grad_norm": 6.625577449798584, "learning_rate": 8.555529762449034e-06, "loss": 0.3316, "step": 272010 }, { "epoch": 1.616943369533558, "grad_norm": 4.625260829925537, "learning_rate": 8.555383874813581e-06, "loss": 0.3658, "step": 272020 }, { "epoch": 1.6170028116102264, "grad_norm": 5.406004905700684, "learning_rate": 8.555237981055332e-06, "loss": 0.3587, "step": 272030 }, { "epoch": 1.6170622536868948, "grad_norm": 4.772122859954834, "learning_rate": 8.55509208117454e-06, "loss": 0.3442, "step": 272040 }, { "epoch": 1.6171216957635632, "grad_norm": 5.236979007720947, "learning_rate": 8.554946175171454e-06, "loss": 0.3397, "step": 272050 }, { "epoch": 1.6171811378402317, "grad_norm": 5.695236682891846, "learning_rate": 8.554800263046327e-06, "loss": 0.3822, "step": 272060 }, { "epoch": 1.6172405799169, "grad_norm": 6.138321876525879, "learning_rate": 8.554654344799412e-06, "loss": 0.3535, "step": 272070 }, { "epoch": 1.6173000219935685, "grad_norm": 5.550805568695068, "learning_rate": 8.554508420430956e-06, "loss": 0.361, "step": 272080 }, { "epoch": 1.617359464070237, "grad_norm": 5.354491233825684, "learning_rate": 8.55436248994121e-06, "loss": 0.3514, "step": 272090 }, { "epoch": 1.6174189061469053, "grad_norm": 3.7006783485412598, "learning_rate": 8.554216553330433e-06, "loss": 0.3042, "step": 272100 }, { "epoch": 1.6174783482235735, "grad_norm": 3.6967368125915527, "learning_rate": 8.554070610598868e-06, "loss": 0.3763, "step": 272110 }, { "epoch": 1.617537790300242, "grad_norm": 5.933793544769287, "learning_rate": 8.553924661746769e-06, "loss": 0.3515, "step": 272120 }, { "epoch": 1.6175972323769103, "grad_norm": 4.1002116203308105, "learning_rate": 8.553778706774389e-06, "loss": 0.315, "step": 272130 }, { "epoch": 1.6176566744535787, "grad_norm": 5.239040374755859, "learning_rate": 8.553632745681977e-06, "loss": 0.3412, "step": 272140 }, { "epoch": 1.617716116530247, "grad_norm": 6.077712535858154, "learning_rate": 8.553486778469784e-06, "loss": 0.3646, "step": 272150 }, { "epoch": 1.6177755586069154, "grad_norm": 4.552314758300781, "learning_rate": 8.553340805138067e-06, "loss": 0.3359, "step": 272160 }, { "epoch": 1.6178350006835838, "grad_norm": 4.845847129821777, "learning_rate": 8.55319482568707e-06, "loss": 0.3347, "step": 272170 }, { "epoch": 1.6178944427602522, "grad_norm": 4.735466957092285, "learning_rate": 8.553048840117047e-06, "loss": 0.3475, "step": 272180 }, { "epoch": 1.6179538848369206, "grad_norm": 4.461246013641357, "learning_rate": 8.552902848428252e-06, "loss": 0.3582, "step": 272190 }, { "epoch": 1.618013326913589, "grad_norm": 7.531692981719971, "learning_rate": 8.552756850620933e-06, "loss": 0.3759, "step": 272200 }, { "epoch": 1.6180727689902574, "grad_norm": 4.900313377380371, "learning_rate": 8.552610846695344e-06, "loss": 0.3385, "step": 272210 }, { "epoch": 1.6181322110669258, "grad_norm": 3.0533082485198975, "learning_rate": 8.552464836651735e-06, "loss": 0.3098, "step": 272220 }, { "epoch": 1.6181916531435943, "grad_norm": 7.579708099365234, "learning_rate": 8.552318820490357e-06, "loss": 0.3705, "step": 272230 }, { "epoch": 1.6182510952202627, "grad_norm": 5.037505626678467, "learning_rate": 8.552172798211462e-06, "loss": 0.3773, "step": 272240 }, { "epoch": 1.618310537296931, "grad_norm": 4.077211380004883, "learning_rate": 8.552026769815303e-06, "loss": 0.3703, "step": 272250 }, { "epoch": 1.6183699793735995, "grad_norm": 5.371853828430176, "learning_rate": 8.551880735302128e-06, "loss": 0.3431, "step": 272260 }, { "epoch": 1.618429421450268, "grad_norm": 5.081958293914795, "learning_rate": 8.55173469467219e-06, "loss": 0.3443, "step": 272270 }, { "epoch": 1.6184888635269363, "grad_norm": 7.54735803604126, "learning_rate": 8.551588647925744e-06, "loss": 0.3442, "step": 272280 }, { "epoch": 1.6185483056036045, "grad_norm": 5.962329864501953, "learning_rate": 8.551442595063038e-06, "loss": 0.3553, "step": 272290 }, { "epoch": 1.618607747680273, "grad_norm": 4.01653528213501, "learning_rate": 8.551296536084323e-06, "loss": 0.3452, "step": 272300 }, { "epoch": 1.6186671897569413, "grad_norm": 4.728696346282959, "learning_rate": 8.551150470989852e-06, "loss": 0.3866, "step": 272310 }, { "epoch": 1.6187266318336098, "grad_norm": 5.790891647338867, "learning_rate": 8.551004399779877e-06, "loss": 0.3267, "step": 272320 }, { "epoch": 1.6187860739102782, "grad_norm": 5.505862236022949, "learning_rate": 8.550858322454647e-06, "loss": 0.3296, "step": 272330 }, { "epoch": 1.6188455159869464, "grad_norm": 5.360100269317627, "learning_rate": 8.550712239014416e-06, "loss": 0.3034, "step": 272340 }, { "epoch": 1.6189049580636148, "grad_norm": 4.9586334228515625, "learning_rate": 8.550566149459436e-06, "loss": 0.3214, "step": 272350 }, { "epoch": 1.6189644001402832, "grad_norm": 4.008652687072754, "learning_rate": 8.550420053789957e-06, "loss": 0.3471, "step": 272360 }, { "epoch": 1.6190238422169516, "grad_norm": 5.98309850692749, "learning_rate": 8.55027395200623e-06, "loss": 0.3293, "step": 272370 }, { "epoch": 1.61908328429362, "grad_norm": 5.587223529815674, "learning_rate": 8.550127844108509e-06, "loss": 0.3347, "step": 272380 }, { "epoch": 1.6191427263702884, "grad_norm": 6.225031852722168, "learning_rate": 8.549981730097043e-06, "loss": 0.3136, "step": 272390 }, { "epoch": 1.6192021684469569, "grad_norm": 4.996999263763428, "learning_rate": 8.549835609972084e-06, "loss": 0.358, "step": 272400 }, { "epoch": 1.6192616105236253, "grad_norm": 3.773271083831787, "learning_rate": 8.549689483733886e-06, "loss": 0.3402, "step": 272410 }, { "epoch": 1.6193210526002937, "grad_norm": 5.8041181564331055, "learning_rate": 8.549543351382698e-06, "loss": 0.3524, "step": 272420 }, { "epoch": 1.619380494676962, "grad_norm": 5.014623165130615, "learning_rate": 8.549397212918775e-06, "loss": 0.3509, "step": 272430 }, { "epoch": 1.6194399367536305, "grad_norm": 4.631161212921143, "learning_rate": 8.549251068342366e-06, "loss": 0.3277, "step": 272440 }, { "epoch": 1.619499378830299, "grad_norm": 6.065723419189453, "learning_rate": 8.549104917653721e-06, "loss": 0.3677, "step": 272450 }, { "epoch": 1.6195588209069673, "grad_norm": 3.93444561958313, "learning_rate": 8.548958760853097e-06, "loss": 0.3527, "step": 272460 }, { "epoch": 1.6196182629836358, "grad_norm": 6.302928447723389, "learning_rate": 8.54881259794074e-06, "loss": 0.3873, "step": 272470 }, { "epoch": 1.619677705060304, "grad_norm": 5.246609210968018, "learning_rate": 8.548666428916905e-06, "loss": 0.3083, "step": 272480 }, { "epoch": 1.6197371471369724, "grad_norm": 5.548828601837158, "learning_rate": 8.548520253781843e-06, "loss": 0.3418, "step": 272490 }, { "epoch": 1.6197965892136408, "grad_norm": 4.143876552581787, "learning_rate": 8.548374072535807e-06, "loss": 0.3465, "step": 272500 }, { "epoch": 1.6198560312903092, "grad_norm": 4.2188920974731445, "learning_rate": 8.548227885179045e-06, "loss": 0.3305, "step": 272510 }, { "epoch": 1.6199154733669774, "grad_norm": 6.6641387939453125, "learning_rate": 8.548081691711814e-06, "loss": 0.3651, "step": 272520 }, { "epoch": 1.6199749154436458, "grad_norm": 5.5506391525268555, "learning_rate": 8.547935492134361e-06, "loss": 0.3141, "step": 272530 }, { "epoch": 1.6200343575203142, "grad_norm": 5.255727291107178, "learning_rate": 8.54778928644694e-06, "loss": 0.3491, "step": 272540 }, { "epoch": 1.6200937995969826, "grad_norm": 5.29398250579834, "learning_rate": 8.547643074649803e-06, "loss": 0.3642, "step": 272550 }, { "epoch": 1.620153241673651, "grad_norm": 4.692953109741211, "learning_rate": 8.547496856743202e-06, "loss": 0.3296, "step": 272560 }, { "epoch": 1.6202126837503195, "grad_norm": 4.534193992614746, "learning_rate": 8.547350632727386e-06, "loss": 0.3102, "step": 272570 }, { "epoch": 1.6202721258269879, "grad_norm": 5.118465423583984, "learning_rate": 8.547204402602611e-06, "loss": 0.3631, "step": 272580 }, { "epoch": 1.6203315679036563, "grad_norm": 3.459237575531006, "learning_rate": 8.547058166369126e-06, "loss": 0.3081, "step": 272590 }, { "epoch": 1.6203910099803247, "grad_norm": 4.857621192932129, "learning_rate": 8.546911924027183e-06, "loss": 0.319, "step": 272600 }, { "epoch": 1.6204504520569931, "grad_norm": 4.5830607414245605, "learning_rate": 8.546765675577036e-06, "loss": 0.3707, "step": 272610 }, { "epoch": 1.6205098941336615, "grad_norm": 3.9068615436553955, "learning_rate": 8.546619421018933e-06, "loss": 0.3565, "step": 272620 }, { "epoch": 1.62056933621033, "grad_norm": 5.827957630157471, "learning_rate": 8.54647316035313e-06, "loss": 0.3579, "step": 272630 }, { "epoch": 1.6206287782869984, "grad_norm": 6.251158714294434, "learning_rate": 8.546326893579877e-06, "loss": 0.3554, "step": 272640 }, { "epoch": 1.6206882203636668, "grad_norm": 5.987935543060303, "learning_rate": 8.546180620699426e-06, "loss": 0.3464, "step": 272650 }, { "epoch": 1.620747662440335, "grad_norm": 4.766423225402832, "learning_rate": 8.546034341712028e-06, "loss": 0.3533, "step": 272660 }, { "epoch": 1.6208071045170034, "grad_norm": 4.882299423217773, "learning_rate": 8.545888056617936e-06, "loss": 0.2917, "step": 272670 }, { "epoch": 1.6208665465936718, "grad_norm": 4.374755382537842, "learning_rate": 8.545741765417402e-06, "loss": 0.3041, "step": 272680 }, { "epoch": 1.6209259886703402, "grad_norm": 5.205779075622559, "learning_rate": 8.545595468110678e-06, "loss": 0.3418, "step": 272690 }, { "epoch": 1.6209854307470086, "grad_norm": 6.736212253570557, "learning_rate": 8.545449164698015e-06, "loss": 0.3232, "step": 272700 }, { "epoch": 1.6210448728236768, "grad_norm": 5.034926414489746, "learning_rate": 8.545302855179666e-06, "loss": 0.3301, "step": 272710 }, { "epoch": 1.6211043149003452, "grad_norm": 4.549310684204102, "learning_rate": 8.545156539555881e-06, "loss": 0.3256, "step": 272720 }, { "epoch": 1.6211637569770136, "grad_norm": 5.454611301422119, "learning_rate": 8.545010217826914e-06, "loss": 0.3418, "step": 272730 }, { "epoch": 1.621223199053682, "grad_norm": 6.759243488311768, "learning_rate": 8.544863889993017e-06, "loss": 0.358, "step": 272740 }, { "epoch": 1.6212826411303505, "grad_norm": 4.204483509063721, "learning_rate": 8.544717556054442e-06, "loss": 0.3227, "step": 272750 }, { "epoch": 1.621342083207019, "grad_norm": 4.398705959320068, "learning_rate": 8.544571216011438e-06, "loss": 0.3619, "step": 272760 }, { "epoch": 1.6214015252836873, "grad_norm": 4.576289176940918, "learning_rate": 8.544424869864263e-06, "loss": 0.3116, "step": 272770 }, { "epoch": 1.6214609673603557, "grad_norm": 4.347952842712402, "learning_rate": 8.544278517613164e-06, "loss": 0.352, "step": 272780 }, { "epoch": 1.6215204094370241, "grad_norm": 3.8592543601989746, "learning_rate": 8.544132159258394e-06, "loss": 0.3421, "step": 272790 }, { "epoch": 1.6215798515136925, "grad_norm": 6.194403648376465, "learning_rate": 8.543985794800205e-06, "loss": 0.3825, "step": 272800 }, { "epoch": 1.621639293590361, "grad_norm": 4.670581817626953, "learning_rate": 8.54383942423885e-06, "loss": 0.3473, "step": 272810 }, { "epoch": 1.6216987356670294, "grad_norm": 3.9908998012542725, "learning_rate": 8.543693047574581e-06, "loss": 0.3417, "step": 272820 }, { "epoch": 1.6217581777436978, "grad_norm": 4.750267505645752, "learning_rate": 8.543546664807649e-06, "loss": 0.3133, "step": 272830 }, { "epoch": 1.6218176198203662, "grad_norm": 5.752963066101074, "learning_rate": 8.543400275938308e-06, "loss": 0.339, "step": 272840 }, { "epoch": 1.6218770618970344, "grad_norm": 4.379388809204102, "learning_rate": 8.543253880966808e-06, "loss": 0.3412, "step": 272850 }, { "epoch": 1.6219365039737028, "grad_norm": 5.738609790802002, "learning_rate": 8.543107479893403e-06, "loss": 0.3114, "step": 272860 }, { "epoch": 1.6219959460503712, "grad_norm": 3.9736316204071045, "learning_rate": 8.542961072718344e-06, "loss": 0.3533, "step": 272870 }, { "epoch": 1.6220553881270396, "grad_norm": 6.370487213134766, "learning_rate": 8.542814659441882e-06, "loss": 0.35, "step": 272880 }, { "epoch": 1.6221148302037078, "grad_norm": 3.926889657974243, "learning_rate": 8.542668240064273e-06, "loss": 0.3163, "step": 272890 }, { "epoch": 1.6221742722803763, "grad_norm": 6.019043445587158, "learning_rate": 8.542521814585765e-06, "loss": 0.3457, "step": 272900 }, { "epoch": 1.6222337143570447, "grad_norm": 5.791374206542969, "learning_rate": 8.542375383006611e-06, "loss": 0.3319, "step": 272910 }, { "epoch": 1.622293156433713, "grad_norm": 4.1544508934021, "learning_rate": 8.542228945327064e-06, "loss": 0.3463, "step": 272920 }, { "epoch": 1.6223525985103815, "grad_norm": 4.193679332733154, "learning_rate": 8.542082501547378e-06, "loss": 0.3315, "step": 272930 }, { "epoch": 1.62241204058705, "grad_norm": 5.73162317276001, "learning_rate": 8.5419360516678e-06, "loss": 0.3287, "step": 272940 }, { "epoch": 1.6224714826637183, "grad_norm": 4.317592620849609, "learning_rate": 8.541789595688588e-06, "loss": 0.3386, "step": 272950 }, { "epoch": 1.6225309247403867, "grad_norm": 3.6719062328338623, "learning_rate": 8.541643133609992e-06, "loss": 0.2978, "step": 272960 }, { "epoch": 1.6225903668170552, "grad_norm": 3.570986270904541, "learning_rate": 8.541496665432263e-06, "loss": 0.3167, "step": 272970 }, { "epoch": 1.6226498088937236, "grad_norm": 5.7602338790893555, "learning_rate": 8.541350191155655e-06, "loss": 0.3434, "step": 272980 }, { "epoch": 1.622709250970392, "grad_norm": 6.521101474761963, "learning_rate": 8.541203710780419e-06, "loss": 0.3148, "step": 272990 }, { "epoch": 1.6227686930470604, "grad_norm": 4.808199405670166, "learning_rate": 8.541057224306807e-06, "loss": 0.3508, "step": 273000 }, { "epoch": 1.6228281351237288, "grad_norm": 3.9963459968566895, "learning_rate": 8.540910731735072e-06, "loss": 0.3075, "step": 273010 }, { "epoch": 1.6228875772003972, "grad_norm": 4.1637163162231445, "learning_rate": 8.540764233065465e-06, "loss": 0.3684, "step": 273020 }, { "epoch": 1.6229470192770654, "grad_norm": 4.248136520385742, "learning_rate": 8.540617728298243e-06, "loss": 0.3291, "step": 273030 }, { "epoch": 1.6230064613537338, "grad_norm": 5.434103012084961, "learning_rate": 8.540471217433652e-06, "loss": 0.327, "step": 273040 }, { "epoch": 1.6230659034304022, "grad_norm": 4.256748199462891, "learning_rate": 8.540324700471949e-06, "loss": 0.3226, "step": 273050 }, { "epoch": 1.6231253455070707, "grad_norm": 4.3226776123046875, "learning_rate": 8.540178177413383e-06, "loss": 0.3189, "step": 273060 }, { "epoch": 1.623184787583739, "grad_norm": 4.203751564025879, "learning_rate": 8.540031648258209e-06, "loss": 0.309, "step": 273070 }, { "epoch": 1.6232442296604073, "grad_norm": 3.9361510276794434, "learning_rate": 8.539885113006677e-06, "loss": 0.2918, "step": 273080 }, { "epoch": 1.6233036717370757, "grad_norm": 5.148859024047852, "learning_rate": 8.53973857165904e-06, "loss": 0.3482, "step": 273090 }, { "epoch": 1.623363113813744, "grad_norm": 5.9416584968566895, "learning_rate": 8.539592024215552e-06, "loss": 0.3002, "step": 273100 }, { "epoch": 1.6234225558904125, "grad_norm": 4.556342601776123, "learning_rate": 8.539445470676464e-06, "loss": 0.3314, "step": 273110 }, { "epoch": 1.623481997967081, "grad_norm": 6.585011959075928, "learning_rate": 8.539298911042029e-06, "loss": 0.3582, "step": 273120 }, { "epoch": 1.6235414400437493, "grad_norm": 4.699563503265381, "learning_rate": 8.539152345312498e-06, "loss": 0.3489, "step": 273130 }, { "epoch": 1.6236008821204178, "grad_norm": 4.554171562194824, "learning_rate": 8.539005773488125e-06, "loss": 0.3318, "step": 273140 }, { "epoch": 1.6236603241970862, "grad_norm": 4.748894691467285, "learning_rate": 8.538859195569162e-06, "loss": 0.3376, "step": 273150 }, { "epoch": 1.6237197662737546, "grad_norm": 6.227278709411621, "learning_rate": 8.538712611555861e-06, "loss": 0.3645, "step": 273160 }, { "epoch": 1.623779208350423, "grad_norm": 4.6685991287231445, "learning_rate": 8.538566021448474e-06, "loss": 0.3543, "step": 273170 }, { "epoch": 1.6238386504270914, "grad_norm": 3.9630515575408936, "learning_rate": 8.538419425247255e-06, "loss": 0.3049, "step": 273180 }, { "epoch": 1.6238980925037598, "grad_norm": 5.907183647155762, "learning_rate": 8.538272822952455e-06, "loss": 0.3122, "step": 273190 }, { "epoch": 1.6239575345804282, "grad_norm": 3.559209108352661, "learning_rate": 8.538126214564326e-06, "loss": 0.3265, "step": 273200 }, { "epoch": 1.6240169766570967, "grad_norm": 5.742710113525391, "learning_rate": 8.537979600083124e-06, "loss": 0.382, "step": 273210 }, { "epoch": 1.6240764187337648, "grad_norm": 6.418368816375732, "learning_rate": 8.537832979509097e-06, "loss": 0.3577, "step": 273220 }, { "epoch": 1.6241358608104333, "grad_norm": 4.546584606170654, "learning_rate": 8.5376863528425e-06, "loss": 0.3218, "step": 273230 }, { "epoch": 1.6241953028871017, "grad_norm": 4.379211902618408, "learning_rate": 8.537539720083585e-06, "loss": 0.3153, "step": 273240 }, { "epoch": 1.62425474496377, "grad_norm": 5.081657409667969, "learning_rate": 8.537393081232604e-06, "loss": 0.3348, "step": 273250 }, { "epoch": 1.6243141870404383, "grad_norm": 4.09597635269165, "learning_rate": 8.537246436289813e-06, "loss": 0.3237, "step": 273260 }, { "epoch": 1.6243736291171067, "grad_norm": 5.35224723815918, "learning_rate": 8.537099785255459e-06, "loss": 0.3177, "step": 273270 }, { "epoch": 1.6244330711937751, "grad_norm": 5.9457268714904785, "learning_rate": 8.536953128129796e-06, "loss": 0.3626, "step": 273280 }, { "epoch": 1.6244925132704435, "grad_norm": 4.502385139465332, "learning_rate": 8.536806464913079e-06, "loss": 0.2885, "step": 273290 }, { "epoch": 1.624551955347112, "grad_norm": 6.0434980392456055, "learning_rate": 8.536659795605559e-06, "loss": 0.3076, "step": 273300 }, { "epoch": 1.6246113974237804, "grad_norm": 5.437389850616455, "learning_rate": 8.53651312020749e-06, "loss": 0.3587, "step": 273310 }, { "epoch": 1.6246708395004488, "grad_norm": 4.401772975921631, "learning_rate": 8.536366438719121e-06, "loss": 0.3336, "step": 273320 }, { "epoch": 1.6247302815771172, "grad_norm": 5.447149753570557, "learning_rate": 8.53621975114071e-06, "loss": 0.3276, "step": 273330 }, { "epoch": 1.6247897236537856, "grad_norm": 3.734569787979126, "learning_rate": 8.536073057472504e-06, "loss": 0.3261, "step": 273340 }, { "epoch": 1.624849165730454, "grad_norm": 4.302093029022217, "learning_rate": 8.53592635771476e-06, "loss": 0.3305, "step": 273350 }, { "epoch": 1.6249086078071224, "grad_norm": 5.691623210906982, "learning_rate": 8.535779651867728e-06, "loss": 0.3564, "step": 273360 }, { "epoch": 1.6249680498837908, "grad_norm": 5.46944522857666, "learning_rate": 8.535632939931663e-06, "loss": 0.3822, "step": 273370 }, { "epoch": 1.6250274919604593, "grad_norm": 4.0153727531433105, "learning_rate": 8.535486221906815e-06, "loss": 0.3189, "step": 273380 }, { "epoch": 1.6250869340371277, "grad_norm": 4.394289970397949, "learning_rate": 8.535339497793438e-06, "loss": 0.3288, "step": 273390 }, { "epoch": 1.6251463761137959, "grad_norm": 5.172295093536377, "learning_rate": 8.535192767591784e-06, "loss": 0.3552, "step": 273400 }, { "epoch": 1.6252058181904643, "grad_norm": 5.500026226043701, "learning_rate": 8.535046031302107e-06, "loss": 0.3142, "step": 273410 }, { "epoch": 1.6252652602671327, "grad_norm": 4.979584217071533, "learning_rate": 8.53489928892466e-06, "loss": 0.3255, "step": 273420 }, { "epoch": 1.625324702343801, "grad_norm": 5.678621768951416, "learning_rate": 8.534752540459693e-06, "loss": 0.3662, "step": 273430 }, { "epoch": 1.6253841444204695, "grad_norm": 3.6344664096832275, "learning_rate": 8.534605785907462e-06, "loss": 0.3139, "step": 273440 }, { "epoch": 1.6254435864971377, "grad_norm": 4.855307579040527, "learning_rate": 8.534459025268216e-06, "loss": 0.3087, "step": 273450 }, { "epoch": 1.6255030285738061, "grad_norm": 4.630471706390381, "learning_rate": 8.53431225854221e-06, "loss": 0.3665, "step": 273460 }, { "epoch": 1.6255624706504745, "grad_norm": 4.671898365020752, "learning_rate": 8.534165485729698e-06, "loss": 0.3276, "step": 273470 }, { "epoch": 1.625621912727143, "grad_norm": 5.373249053955078, "learning_rate": 8.534018706830932e-06, "loss": 0.2961, "step": 273480 }, { "epoch": 1.6256813548038114, "grad_norm": 5.109818935394287, "learning_rate": 8.533871921846162e-06, "loss": 0.3514, "step": 273490 }, { "epoch": 1.6257407968804798, "grad_norm": 4.770007133483887, "learning_rate": 8.533725130775644e-06, "loss": 0.3545, "step": 273500 }, { "epoch": 1.6258002389571482, "grad_norm": 4.429872035980225, "learning_rate": 8.533578333619629e-06, "loss": 0.2772, "step": 273510 }, { "epoch": 1.6258596810338166, "grad_norm": 4.588372707366943, "learning_rate": 8.53343153037837e-06, "loss": 0.3229, "step": 273520 }, { "epoch": 1.625919123110485, "grad_norm": 5.87546443939209, "learning_rate": 8.533284721052122e-06, "loss": 0.3145, "step": 273530 }, { "epoch": 1.6259785651871534, "grad_norm": 4.31191873550415, "learning_rate": 8.533137905641136e-06, "loss": 0.3428, "step": 273540 }, { "epoch": 1.6260380072638219, "grad_norm": 6.004758358001709, "learning_rate": 8.532991084145664e-06, "loss": 0.298, "step": 273550 }, { "epoch": 1.6260974493404903, "grad_norm": 4.245486736297607, "learning_rate": 8.532844256565959e-06, "loss": 0.308, "step": 273560 }, { "epoch": 1.6261568914171587, "grad_norm": 6.126604080200195, "learning_rate": 8.532697422902277e-06, "loss": 0.3414, "step": 273570 }, { "epoch": 1.626216333493827, "grad_norm": 5.935750484466553, "learning_rate": 8.532550583154866e-06, "loss": 0.3688, "step": 273580 }, { "epoch": 1.6262757755704953, "grad_norm": 4.525979995727539, "learning_rate": 8.532403737323983e-06, "loss": 0.3267, "step": 273590 }, { "epoch": 1.6263352176471637, "grad_norm": 4.3231425285339355, "learning_rate": 8.53225688540988e-06, "loss": 0.3597, "step": 273600 }, { "epoch": 1.6263946597238321, "grad_norm": 3.9291322231292725, "learning_rate": 8.532110027412808e-06, "loss": 0.3486, "step": 273610 }, { "epoch": 1.6264541018005005, "grad_norm": 5.844146251678467, "learning_rate": 8.531963163333022e-06, "loss": 0.36, "step": 273620 }, { "epoch": 1.6265135438771687, "grad_norm": 4.394356727600098, "learning_rate": 8.531816293170772e-06, "loss": 0.3051, "step": 273630 }, { "epoch": 1.6265729859538371, "grad_norm": 4.413776874542236, "learning_rate": 8.531669416926314e-06, "loss": 0.3517, "step": 273640 }, { "epoch": 1.6266324280305056, "grad_norm": 5.320200443267822, "learning_rate": 8.5315225345999e-06, "loss": 0.2946, "step": 273650 }, { "epoch": 1.626691870107174, "grad_norm": 3.9494903087615967, "learning_rate": 8.531375646191782e-06, "loss": 0.289, "step": 273660 }, { "epoch": 1.6267513121838424, "grad_norm": 5.384907245635986, "learning_rate": 8.531228751702215e-06, "loss": 0.3402, "step": 273670 }, { "epoch": 1.6268107542605108, "grad_norm": 4.407838344573975, "learning_rate": 8.53108185113145e-06, "loss": 0.3134, "step": 273680 }, { "epoch": 1.6268701963371792, "grad_norm": 6.225263595581055, "learning_rate": 8.530934944479742e-06, "loss": 0.3688, "step": 273690 }, { "epoch": 1.6269296384138476, "grad_norm": 6.065957069396973, "learning_rate": 8.53078803174734e-06, "loss": 0.3465, "step": 273700 }, { "epoch": 1.626989080490516, "grad_norm": 4.331005573272705, "learning_rate": 8.530641112934503e-06, "loss": 0.3675, "step": 273710 }, { "epoch": 1.6270485225671845, "grad_norm": 3.401686429977417, "learning_rate": 8.53049418804148e-06, "loss": 0.3111, "step": 273720 }, { "epoch": 1.6271079646438529, "grad_norm": 4.5571608543396, "learning_rate": 8.530347257068523e-06, "loss": 0.3142, "step": 273730 }, { "epoch": 1.6271674067205213, "grad_norm": 4.854711055755615, "learning_rate": 8.530200320015888e-06, "loss": 0.3326, "step": 273740 }, { "epoch": 1.6272268487971897, "grad_norm": 4.792582035064697, "learning_rate": 8.530053376883827e-06, "loss": 0.3393, "step": 273750 }, { "epoch": 1.6272862908738581, "grad_norm": 4.638806343078613, "learning_rate": 8.529906427672592e-06, "loss": 0.3637, "step": 273760 }, { "epoch": 1.6273457329505263, "grad_norm": 5.643076419830322, "learning_rate": 8.529759472382437e-06, "loss": 0.315, "step": 273770 }, { "epoch": 1.6274051750271947, "grad_norm": 4.016009330749512, "learning_rate": 8.529612511013617e-06, "loss": 0.3075, "step": 273780 }, { "epoch": 1.6274646171038631, "grad_norm": 6.8303680419921875, "learning_rate": 8.529465543566382e-06, "loss": 0.3319, "step": 273790 }, { "epoch": 1.6275240591805316, "grad_norm": 3.6446948051452637, "learning_rate": 8.529318570040985e-06, "loss": 0.3143, "step": 273800 }, { "epoch": 1.6275835012572, "grad_norm": 3.898491382598877, "learning_rate": 8.529171590437682e-06, "loss": 0.3254, "step": 273810 }, { "epoch": 1.6276429433338682, "grad_norm": 4.721729755401611, "learning_rate": 8.529024604756723e-06, "loss": 0.375, "step": 273820 }, { "epoch": 1.6277023854105366, "grad_norm": 6.403454303741455, "learning_rate": 8.528877612998363e-06, "loss": 0.3464, "step": 273830 }, { "epoch": 1.627761827487205, "grad_norm": 5.903060436248779, "learning_rate": 8.528730615162854e-06, "loss": 0.3146, "step": 273840 }, { "epoch": 1.6278212695638734, "grad_norm": 4.987784385681152, "learning_rate": 8.528583611250452e-06, "loss": 0.3374, "step": 273850 }, { "epoch": 1.6278807116405418, "grad_norm": 4.479918956756592, "learning_rate": 8.528436601261408e-06, "loss": 0.322, "step": 273860 }, { "epoch": 1.6279401537172102, "grad_norm": 4.130216121673584, "learning_rate": 8.528289585195972e-06, "loss": 0.3122, "step": 273870 }, { "epoch": 1.6279995957938787, "grad_norm": 3.4489662647247314, "learning_rate": 8.528142563054402e-06, "loss": 0.3489, "step": 273880 }, { "epoch": 1.628059037870547, "grad_norm": 6.2596940994262695, "learning_rate": 8.52799553483695e-06, "loss": 0.3423, "step": 273890 }, { "epoch": 1.6281184799472155, "grad_norm": 5.2075886726379395, "learning_rate": 8.527848500543869e-06, "loss": 0.3517, "step": 273900 }, { "epoch": 1.628177922023884, "grad_norm": 4.822597980499268, "learning_rate": 8.52770146017541e-06, "loss": 0.3206, "step": 273910 }, { "epoch": 1.6282373641005523, "grad_norm": 4.314154624938965, "learning_rate": 8.52755441373183e-06, "loss": 0.3571, "step": 273920 }, { "epoch": 1.6282968061772207, "grad_norm": 4.703547954559326, "learning_rate": 8.52740736121338e-06, "loss": 0.3228, "step": 273930 }, { "epoch": 1.6283562482538891, "grad_norm": 4.659236907958984, "learning_rate": 8.527260302620314e-06, "loss": 0.3719, "step": 273940 }, { "epoch": 1.6284156903305576, "grad_norm": 5.021233558654785, "learning_rate": 8.527113237952884e-06, "loss": 0.3008, "step": 273950 }, { "epoch": 1.6284751324072257, "grad_norm": 4.016917705535889, "learning_rate": 8.526966167211346e-06, "loss": 0.2914, "step": 273960 }, { "epoch": 1.6285345744838942, "grad_norm": 4.600347518920898, "learning_rate": 8.52681909039595e-06, "loss": 0.3396, "step": 273970 }, { "epoch": 1.6285940165605626, "grad_norm": 5.727869033813477, "learning_rate": 8.526672007506949e-06, "loss": 0.3572, "step": 273980 }, { "epoch": 1.628653458637231, "grad_norm": 4.16666316986084, "learning_rate": 8.526524918544601e-06, "loss": 0.3005, "step": 273990 }, { "epoch": 1.6287129007138992, "grad_norm": 4.263204097747803, "learning_rate": 8.526377823509156e-06, "loss": 0.3269, "step": 274000 }, { "epoch": 1.6287723427905676, "grad_norm": 5.545773983001709, "learning_rate": 8.526230722400865e-06, "loss": 0.3422, "step": 274010 }, { "epoch": 1.628831784867236, "grad_norm": 5.797074317932129, "learning_rate": 8.526083615219987e-06, "loss": 0.3055, "step": 274020 }, { "epoch": 1.6288912269439044, "grad_norm": 4.137858867645264, "learning_rate": 8.52593650196677e-06, "loss": 0.342, "step": 274030 }, { "epoch": 1.6289506690205728, "grad_norm": 5.217269420623779, "learning_rate": 8.525789382641471e-06, "loss": 0.338, "step": 274040 }, { "epoch": 1.6290101110972413, "grad_norm": 4.640698432922363, "learning_rate": 8.525642257244342e-06, "loss": 0.3413, "step": 274050 }, { "epoch": 1.6290695531739097, "grad_norm": 5.414860248565674, "learning_rate": 8.525495125775636e-06, "loss": 0.3519, "step": 274060 }, { "epoch": 1.629128995250578, "grad_norm": 6.2584381103515625, "learning_rate": 8.525347988235608e-06, "loss": 0.3325, "step": 274070 }, { "epoch": 1.6291884373272465, "grad_norm": 4.784811496734619, "learning_rate": 8.525200844624508e-06, "loss": 0.3678, "step": 274080 }, { "epoch": 1.629247879403915, "grad_norm": 5.6223554611206055, "learning_rate": 8.525053694942592e-06, "loss": 0.3654, "step": 274090 }, { "epoch": 1.6293073214805833, "grad_norm": 4.5266218185424805, "learning_rate": 8.524906539190112e-06, "loss": 0.3519, "step": 274100 }, { "epoch": 1.6293667635572517, "grad_norm": 4.706116676330566, "learning_rate": 8.524759377367325e-06, "loss": 0.3144, "step": 274110 }, { "epoch": 1.6294262056339202, "grad_norm": 5.651052474975586, "learning_rate": 8.52461220947448e-06, "loss": 0.372, "step": 274120 }, { "epoch": 1.6294856477105886, "grad_norm": 4.305356502532959, "learning_rate": 8.524465035511833e-06, "loss": 0.2854, "step": 274130 }, { "epoch": 1.6295450897872568, "grad_norm": 4.855418682098389, "learning_rate": 8.524317855479637e-06, "loss": 0.3468, "step": 274140 }, { "epoch": 1.6296045318639252, "grad_norm": 5.017311096191406, "learning_rate": 8.524170669378144e-06, "loss": 0.3169, "step": 274150 }, { "epoch": 1.6296639739405936, "grad_norm": 5.462364673614502, "learning_rate": 8.524023477207608e-06, "loss": 0.3202, "step": 274160 }, { "epoch": 1.629723416017262, "grad_norm": 5.991523265838623, "learning_rate": 8.523876278968284e-06, "loss": 0.3524, "step": 274170 }, { "epoch": 1.6297828580939304, "grad_norm": 6.4407548904418945, "learning_rate": 8.523729074660427e-06, "loss": 0.34, "step": 274180 }, { "epoch": 1.6298423001705986, "grad_norm": 4.9686384201049805, "learning_rate": 8.523581864284285e-06, "loss": 0.2902, "step": 274190 }, { "epoch": 1.629901742247267, "grad_norm": 7.326864242553711, "learning_rate": 8.523434647840114e-06, "loss": 0.3896, "step": 274200 }, { "epoch": 1.6299611843239354, "grad_norm": 5.274993419647217, "learning_rate": 8.52328742532817e-06, "loss": 0.3909, "step": 274210 }, { "epoch": 1.6300206264006039, "grad_norm": 5.056275844573975, "learning_rate": 8.523140196748705e-06, "loss": 0.3707, "step": 274220 }, { "epoch": 1.6300800684772723, "grad_norm": 4.358101844787598, "learning_rate": 8.522992962101971e-06, "loss": 0.3261, "step": 274230 }, { "epoch": 1.6301395105539407, "grad_norm": 4.774967670440674, "learning_rate": 8.522845721388222e-06, "loss": 0.3095, "step": 274240 }, { "epoch": 1.630198952630609, "grad_norm": 4.276384353637695, "learning_rate": 8.522698474607716e-06, "loss": 0.3257, "step": 274250 }, { "epoch": 1.6302583947072775, "grad_norm": 5.939250469207764, "learning_rate": 8.5225512217607e-06, "loss": 0.3695, "step": 274260 }, { "epoch": 1.630317836783946, "grad_norm": 3.866065263748169, "learning_rate": 8.52240396284743e-06, "loss": 0.3442, "step": 274270 }, { "epoch": 1.6303772788606143, "grad_norm": 5.559407711029053, "learning_rate": 8.522256697868163e-06, "loss": 0.3368, "step": 274280 }, { "epoch": 1.6304367209372828, "grad_norm": 4.923030376434326, "learning_rate": 8.522109426823147e-06, "loss": 0.3379, "step": 274290 }, { "epoch": 1.6304961630139512, "grad_norm": 5.636270046234131, "learning_rate": 8.52196214971264e-06, "loss": 0.365, "step": 274300 }, { "epoch": 1.6305556050906196, "grad_norm": 5.326041221618652, "learning_rate": 8.52181486653689e-06, "loss": 0.3535, "step": 274310 }, { "epoch": 1.630615047167288, "grad_norm": 5.913824558258057, "learning_rate": 8.521667577296157e-06, "loss": 0.3591, "step": 274320 }, { "epoch": 1.6306744892439562, "grad_norm": 5.347146987915039, "learning_rate": 8.521520281990695e-06, "loss": 0.3507, "step": 274330 }, { "epoch": 1.6307339313206246, "grad_norm": 4.790587425231934, "learning_rate": 8.521372980620752e-06, "loss": 0.3075, "step": 274340 }, { "epoch": 1.630793373397293, "grad_norm": 4.976121425628662, "learning_rate": 8.521225673186586e-06, "loss": 0.2903, "step": 274350 }, { "epoch": 1.6308528154739614, "grad_norm": 4.525750637054443, "learning_rate": 8.521078359688448e-06, "loss": 0.3214, "step": 274360 }, { "epoch": 1.6309122575506296, "grad_norm": 4.948159694671631, "learning_rate": 8.520931040126595e-06, "loss": 0.3701, "step": 274370 }, { "epoch": 1.630971699627298, "grad_norm": 7.564978122711182, "learning_rate": 8.520783714501276e-06, "loss": 0.3389, "step": 274380 }, { "epoch": 1.6310311417039665, "grad_norm": 4.597550392150879, "learning_rate": 8.520636382812749e-06, "loss": 0.3003, "step": 274390 }, { "epoch": 1.6310905837806349, "grad_norm": 3.4055135250091553, "learning_rate": 8.520489045061264e-06, "loss": 0.3221, "step": 274400 }, { "epoch": 1.6311500258573033, "grad_norm": 5.03200101852417, "learning_rate": 8.520341701247079e-06, "loss": 0.3133, "step": 274410 }, { "epoch": 1.6312094679339717, "grad_norm": 5.250290870666504, "learning_rate": 8.520194351370444e-06, "loss": 0.362, "step": 274420 }, { "epoch": 1.6312689100106401, "grad_norm": 5.021322250366211, "learning_rate": 8.520046995431616e-06, "loss": 0.3605, "step": 274430 }, { "epoch": 1.6313283520873085, "grad_norm": 5.720603942871094, "learning_rate": 8.519899633430845e-06, "loss": 0.329, "step": 274440 }, { "epoch": 1.631387794163977, "grad_norm": 5.121556282043457, "learning_rate": 8.519752265368388e-06, "loss": 0.3165, "step": 274450 }, { "epoch": 1.6314472362406454, "grad_norm": 4.62576961517334, "learning_rate": 8.5196048912445e-06, "loss": 0.3819, "step": 274460 }, { "epoch": 1.6315066783173138, "grad_norm": 5.283365726470947, "learning_rate": 8.519457511059429e-06, "loss": 0.353, "step": 274470 }, { "epoch": 1.6315661203939822, "grad_norm": 5.185922145843506, "learning_rate": 8.519310124813434e-06, "loss": 0.2788, "step": 274480 }, { "epoch": 1.6316255624706506, "grad_norm": 4.180751323699951, "learning_rate": 8.519162732506767e-06, "loss": 0.3473, "step": 274490 }, { "epoch": 1.631685004547319, "grad_norm": 6.584948539733887, "learning_rate": 8.51901533413968e-06, "loss": 0.3159, "step": 274500 }, { "epoch": 1.6317444466239872, "grad_norm": 7.699590682983398, "learning_rate": 8.518867929712432e-06, "loss": 0.3323, "step": 274510 }, { "epoch": 1.6318038887006556, "grad_norm": 6.019432067871094, "learning_rate": 8.518720519225269e-06, "loss": 0.3185, "step": 274520 }, { "epoch": 1.631863330777324, "grad_norm": 6.118160724639893, "learning_rate": 8.518573102678453e-06, "loss": 0.3345, "step": 274530 }, { "epoch": 1.6319227728539925, "grad_norm": 4.806029796600342, "learning_rate": 8.518425680072233e-06, "loss": 0.3418, "step": 274540 }, { "epoch": 1.6319822149306609, "grad_norm": 6.483447074890137, "learning_rate": 8.518278251406864e-06, "loss": 0.3348, "step": 274550 }, { "epoch": 1.632041657007329, "grad_norm": 5.446460723876953, "learning_rate": 8.5181308166826e-06, "loss": 0.3372, "step": 274560 }, { "epoch": 1.6321010990839975, "grad_norm": 5.334934234619141, "learning_rate": 8.517983375899697e-06, "loss": 0.3856, "step": 274570 }, { "epoch": 1.632160541160666, "grad_norm": 5.477726459503174, "learning_rate": 8.517835929058404e-06, "loss": 0.3392, "step": 274580 }, { "epoch": 1.6322199832373343, "grad_norm": 6.372776031494141, "learning_rate": 8.51768847615898e-06, "loss": 0.3178, "step": 274590 }, { "epoch": 1.6322794253140027, "grad_norm": 5.086221218109131, "learning_rate": 8.517541017201675e-06, "loss": 0.334, "step": 274600 }, { "epoch": 1.6323388673906711, "grad_norm": 4.896900177001953, "learning_rate": 8.517393552186746e-06, "loss": 0.3249, "step": 274610 }, { "epoch": 1.6323983094673395, "grad_norm": 5.910764217376709, "learning_rate": 8.517246081114444e-06, "loss": 0.3548, "step": 274620 }, { "epoch": 1.632457751544008, "grad_norm": 4.096792221069336, "learning_rate": 8.517098603985028e-06, "loss": 0.3096, "step": 274630 }, { "epoch": 1.6325171936206764, "grad_norm": 5.201441287994385, "learning_rate": 8.516951120798744e-06, "loss": 0.3277, "step": 274640 }, { "epoch": 1.6325766356973448, "grad_norm": 5.324676036834717, "learning_rate": 8.516803631555854e-06, "loss": 0.3403, "step": 274650 }, { "epoch": 1.6326360777740132, "grad_norm": 4.47791051864624, "learning_rate": 8.516656136256607e-06, "loss": 0.3279, "step": 274660 }, { "epoch": 1.6326955198506816, "grad_norm": 5.196465015411377, "learning_rate": 8.51650863490126e-06, "loss": 0.3364, "step": 274670 }, { "epoch": 1.63275496192735, "grad_norm": 5.256359100341797, "learning_rate": 8.516361127490063e-06, "loss": 0.3221, "step": 274680 }, { "epoch": 1.6328144040040184, "grad_norm": 3.970139265060425, "learning_rate": 8.516213614023274e-06, "loss": 0.3428, "step": 274690 }, { "epoch": 1.6328738460806866, "grad_norm": 5.051267147064209, "learning_rate": 8.516066094501147e-06, "loss": 0.3384, "step": 274700 }, { "epoch": 1.632933288157355, "grad_norm": 4.506657123565674, "learning_rate": 8.515918568923931e-06, "loss": 0.3257, "step": 274710 }, { "epoch": 1.6329927302340235, "grad_norm": 5.244492053985596, "learning_rate": 8.515771037291887e-06, "loss": 0.3492, "step": 274720 }, { "epoch": 1.6330521723106919, "grad_norm": 5.543972492218018, "learning_rate": 8.515623499605265e-06, "loss": 0.3356, "step": 274730 }, { "epoch": 1.63311161438736, "grad_norm": 5.53729772567749, "learning_rate": 8.51547595586432e-06, "loss": 0.3205, "step": 274740 }, { "epoch": 1.6331710564640285, "grad_norm": 5.608399391174316, "learning_rate": 8.515328406069305e-06, "loss": 0.3172, "step": 274750 }, { "epoch": 1.633230498540697, "grad_norm": 6.508484363555908, "learning_rate": 8.515180850220474e-06, "loss": 0.3685, "step": 274760 }, { "epoch": 1.6332899406173653, "grad_norm": 4.869442939758301, "learning_rate": 8.515033288318085e-06, "loss": 0.3041, "step": 274770 }, { "epoch": 1.6333493826940337, "grad_norm": 4.964632987976074, "learning_rate": 8.514885720362388e-06, "loss": 0.347, "step": 274780 }, { "epoch": 1.6334088247707022, "grad_norm": 5.758183002471924, "learning_rate": 8.514738146353638e-06, "loss": 0.3175, "step": 274790 }, { "epoch": 1.6334682668473706, "grad_norm": 5.225813388824463, "learning_rate": 8.514590566292092e-06, "loss": 0.3532, "step": 274800 }, { "epoch": 1.633527708924039, "grad_norm": 5.941699981689453, "learning_rate": 8.514442980177998e-06, "loss": 0.3572, "step": 274810 }, { "epoch": 1.6335871510007074, "grad_norm": 4.782036781311035, "learning_rate": 8.514295388011616e-06, "loss": 0.3289, "step": 274820 }, { "epoch": 1.6336465930773758, "grad_norm": 5.0930352210998535, "learning_rate": 8.514147789793197e-06, "loss": 0.3663, "step": 274830 }, { "epoch": 1.6337060351540442, "grad_norm": 5.512289047241211, "learning_rate": 8.514000185522997e-06, "loss": 0.3792, "step": 274840 }, { "epoch": 1.6337654772307126, "grad_norm": 4.33231782913208, "learning_rate": 8.513852575201269e-06, "loss": 0.338, "step": 274850 }, { "epoch": 1.633824919307381, "grad_norm": 3.9187228679656982, "learning_rate": 8.513704958828268e-06, "loss": 0.3345, "step": 274860 }, { "epoch": 1.6338843613840495, "grad_norm": 5.167750835418701, "learning_rate": 8.513557336404246e-06, "loss": 0.3468, "step": 274870 }, { "epoch": 1.6339438034607177, "grad_norm": 3.835545063018799, "learning_rate": 8.513409707929461e-06, "loss": 0.3345, "step": 274880 }, { "epoch": 1.634003245537386, "grad_norm": 4.395544528961182, "learning_rate": 8.513262073404165e-06, "loss": 0.3347, "step": 274890 }, { "epoch": 1.6340626876140545, "grad_norm": 4.487815856933594, "learning_rate": 8.513114432828613e-06, "loss": 0.3384, "step": 274900 }, { "epoch": 1.634122129690723, "grad_norm": 4.628198623657227, "learning_rate": 8.512966786203058e-06, "loss": 0.3205, "step": 274910 }, { "epoch": 1.6341815717673913, "grad_norm": 4.797954559326172, "learning_rate": 8.512819133527754e-06, "loss": 0.3198, "step": 274920 }, { "epoch": 1.6342410138440595, "grad_norm": 4.236500263214111, "learning_rate": 8.512671474802958e-06, "loss": 0.352, "step": 274930 }, { "epoch": 1.634300455920728, "grad_norm": 6.818780422210693, "learning_rate": 8.512523810028924e-06, "loss": 0.3617, "step": 274940 }, { "epoch": 1.6343598979973963, "grad_norm": 4.815789222717285, "learning_rate": 8.512376139205902e-06, "loss": 0.3351, "step": 274950 }, { "epoch": 1.6344193400740648, "grad_norm": 4.898650646209717, "learning_rate": 8.512228462334148e-06, "loss": 0.3406, "step": 274960 }, { "epoch": 1.6344787821507332, "grad_norm": 5.249475002288818, "learning_rate": 8.51208077941392e-06, "loss": 0.3203, "step": 274970 }, { "epoch": 1.6345382242274016, "grad_norm": 4.604719638824463, "learning_rate": 8.51193309044547e-06, "loss": 0.3804, "step": 274980 }, { "epoch": 1.63459766630407, "grad_norm": 3.8652737140655518, "learning_rate": 8.511785395429052e-06, "loss": 0.3106, "step": 274990 }, { "epoch": 1.6346571083807384, "grad_norm": 3.7827646732330322, "learning_rate": 8.511637694364921e-06, "loss": 0.3586, "step": 275000 }, { "epoch": 1.6347165504574068, "grad_norm": 4.068277835845947, "learning_rate": 8.511489987253329e-06, "loss": 0.3053, "step": 275010 }, { "epoch": 1.6347759925340752, "grad_norm": 5.521953105926514, "learning_rate": 8.511342274094535e-06, "loss": 0.3236, "step": 275020 }, { "epoch": 1.6348354346107437, "grad_norm": 5.284460544586182, "learning_rate": 8.511194554888788e-06, "loss": 0.3136, "step": 275030 }, { "epoch": 1.634894876687412, "grad_norm": 5.953371524810791, "learning_rate": 8.511046829636345e-06, "loss": 0.3117, "step": 275040 }, { "epoch": 1.6349543187640805, "grad_norm": 5.344489574432373, "learning_rate": 8.510899098337461e-06, "loss": 0.3431, "step": 275050 }, { "epoch": 1.635013760840749, "grad_norm": 4.810895919799805, "learning_rate": 8.51075136099239e-06, "loss": 0.3274, "step": 275060 }, { "epoch": 1.635073202917417, "grad_norm": 5.947513580322266, "learning_rate": 8.510603617601388e-06, "loss": 0.3362, "step": 275070 }, { "epoch": 1.6351326449940855, "grad_norm": 3.761369466781616, "learning_rate": 8.510455868164706e-06, "loss": 0.3123, "step": 275080 }, { "epoch": 1.635192087070754, "grad_norm": 6.255672931671143, "learning_rate": 8.5103081126826e-06, "loss": 0.343, "step": 275090 }, { "epoch": 1.6352515291474223, "grad_norm": 5.090877532958984, "learning_rate": 8.510160351155326e-06, "loss": 0.3656, "step": 275100 }, { "epoch": 1.6353109712240905, "grad_norm": 4.6126708984375, "learning_rate": 8.510012583583135e-06, "loss": 0.3375, "step": 275110 }, { "epoch": 1.635370413300759, "grad_norm": 4.6158246994018555, "learning_rate": 8.509864809966284e-06, "loss": 0.3129, "step": 275120 }, { "epoch": 1.6354298553774274, "grad_norm": 7.300315856933594, "learning_rate": 8.509717030305029e-06, "loss": 0.3521, "step": 275130 }, { "epoch": 1.6354892974540958, "grad_norm": 4.644682884216309, "learning_rate": 8.509569244599621e-06, "loss": 0.3062, "step": 275140 }, { "epoch": 1.6355487395307642, "grad_norm": 5.226425647735596, "learning_rate": 8.509421452850315e-06, "loss": 0.3322, "step": 275150 }, { "epoch": 1.6356081816074326, "grad_norm": 5.547576904296875, "learning_rate": 8.509273655057368e-06, "loss": 0.3605, "step": 275160 }, { "epoch": 1.635667623684101, "grad_norm": 5.043104648590088, "learning_rate": 8.509125851221032e-06, "loss": 0.3803, "step": 275170 }, { "epoch": 1.6357270657607694, "grad_norm": 7.058213710784912, "learning_rate": 8.508978041341563e-06, "loss": 0.3262, "step": 275180 }, { "epoch": 1.6357865078374378, "grad_norm": 6.625611305236816, "learning_rate": 8.508830225419216e-06, "loss": 0.3179, "step": 275190 }, { "epoch": 1.6358459499141063, "grad_norm": 4.081151485443115, "learning_rate": 8.508682403454242e-06, "loss": 0.3572, "step": 275200 }, { "epoch": 1.6359053919907747, "grad_norm": 4.581953048706055, "learning_rate": 8.508534575446901e-06, "loss": 0.3721, "step": 275210 }, { "epoch": 1.635964834067443, "grad_norm": 6.691521644592285, "learning_rate": 8.508386741397445e-06, "loss": 0.3642, "step": 275220 }, { "epoch": 1.6360242761441115, "grad_norm": 5.437903881072998, "learning_rate": 8.508238901306128e-06, "loss": 0.3493, "step": 275230 }, { "epoch": 1.63608371822078, "grad_norm": 4.740066051483154, "learning_rate": 8.508091055173205e-06, "loss": 0.3226, "step": 275240 }, { "epoch": 1.636143160297448, "grad_norm": 5.320876598358154, "learning_rate": 8.50794320299893e-06, "loss": 0.3377, "step": 275250 }, { "epoch": 1.6362026023741165, "grad_norm": 5.744325637817383, "learning_rate": 8.507795344783558e-06, "loss": 0.346, "step": 275260 }, { "epoch": 1.636262044450785, "grad_norm": 4.294227600097656, "learning_rate": 8.507647480527344e-06, "loss": 0.3346, "step": 275270 }, { "epoch": 1.6363214865274534, "grad_norm": 4.284489631652832, "learning_rate": 8.507499610230543e-06, "loss": 0.315, "step": 275280 }, { "epoch": 1.6363809286041218, "grad_norm": 4.778311252593994, "learning_rate": 8.507351733893408e-06, "loss": 0.3364, "step": 275290 }, { "epoch": 1.63644037068079, "grad_norm": 5.404636859893799, "learning_rate": 8.507203851516196e-06, "loss": 0.3636, "step": 275300 }, { "epoch": 1.6364998127574584, "grad_norm": 4.035187721252441, "learning_rate": 8.50705596309916e-06, "loss": 0.308, "step": 275310 }, { "epoch": 1.6365592548341268, "grad_norm": 4.069862365722656, "learning_rate": 8.506908068642556e-06, "loss": 0.3279, "step": 275320 }, { "epoch": 1.6366186969107952, "grad_norm": 3.5211081504821777, "learning_rate": 8.506760168146637e-06, "loss": 0.33, "step": 275330 }, { "epoch": 1.6366781389874636, "grad_norm": 4.873973846435547, "learning_rate": 8.506612261611659e-06, "loss": 0.3435, "step": 275340 }, { "epoch": 1.636737581064132, "grad_norm": 4.653593063354492, "learning_rate": 8.506464349037877e-06, "loss": 0.3302, "step": 275350 }, { "epoch": 1.6367970231408004, "grad_norm": 4.271881103515625, "learning_rate": 8.506316430425542e-06, "loss": 0.3204, "step": 275360 }, { "epoch": 1.6368564652174689, "grad_norm": 5.362790584564209, "learning_rate": 8.506168505774915e-06, "loss": 0.3438, "step": 275370 }, { "epoch": 1.6369159072941373, "grad_norm": 3.897937536239624, "learning_rate": 8.506020575086248e-06, "loss": 0.349, "step": 275380 }, { "epoch": 1.6369753493708057, "grad_norm": 5.051926136016846, "learning_rate": 8.505872638359792e-06, "loss": 0.3609, "step": 275390 }, { "epoch": 1.637034791447474, "grad_norm": 4.618448734283447, "learning_rate": 8.505724695595807e-06, "loss": 0.3428, "step": 275400 }, { "epoch": 1.6370942335241425, "grad_norm": 4.037027359008789, "learning_rate": 8.505576746794545e-06, "loss": 0.3522, "step": 275410 }, { "epoch": 1.637153675600811, "grad_norm": 6.224353313446045, "learning_rate": 8.505428791956261e-06, "loss": 0.3613, "step": 275420 }, { "epoch": 1.6372131176774793, "grad_norm": 5.601126194000244, "learning_rate": 8.505280831081211e-06, "loss": 0.3799, "step": 275430 }, { "epoch": 1.6372725597541475, "grad_norm": 6.1152024269104, "learning_rate": 8.505132864169649e-06, "loss": 0.3396, "step": 275440 }, { "epoch": 1.637332001830816, "grad_norm": 4.868237495422363, "learning_rate": 8.504984891221833e-06, "loss": 0.3188, "step": 275450 }, { "epoch": 1.6373914439074844, "grad_norm": 4.62952995300293, "learning_rate": 8.504836912238012e-06, "loss": 0.3186, "step": 275460 }, { "epoch": 1.6374508859841528, "grad_norm": 4.874467849731445, "learning_rate": 8.504688927218443e-06, "loss": 0.3047, "step": 275470 }, { "epoch": 1.637510328060821, "grad_norm": 4.48989725112915, "learning_rate": 8.504540936163384e-06, "loss": 0.3243, "step": 275480 }, { "epoch": 1.6375697701374894, "grad_norm": 4.957899570465088, "learning_rate": 8.504392939073085e-06, "loss": 0.3265, "step": 275490 }, { "epoch": 1.6376292122141578, "grad_norm": 5.081517219543457, "learning_rate": 8.504244935947803e-06, "loss": 0.3521, "step": 275500 }, { "epoch": 1.6376886542908262, "grad_norm": 5.715052604675293, "learning_rate": 8.504096926787795e-06, "loss": 0.3539, "step": 275510 }, { "epoch": 1.6377480963674946, "grad_norm": 5.5139946937561035, "learning_rate": 8.503948911593312e-06, "loss": 0.3431, "step": 275520 }, { "epoch": 1.637807538444163, "grad_norm": 4.442067623138428, "learning_rate": 8.503800890364613e-06, "loss": 0.3301, "step": 275530 }, { "epoch": 1.6378669805208315, "grad_norm": 4.783541202545166, "learning_rate": 8.503652863101948e-06, "loss": 0.3388, "step": 275540 }, { "epoch": 1.6379264225974999, "grad_norm": 5.638967990875244, "learning_rate": 8.503504829805578e-06, "loss": 0.3543, "step": 275550 }, { "epoch": 1.6379858646741683, "grad_norm": 4.794112682342529, "learning_rate": 8.503356790475751e-06, "loss": 0.3443, "step": 275560 }, { "epoch": 1.6380453067508367, "grad_norm": 3.6929750442504883, "learning_rate": 8.503208745112729e-06, "loss": 0.3406, "step": 275570 }, { "epoch": 1.6381047488275051, "grad_norm": 4.203489780426025, "learning_rate": 8.503060693716762e-06, "loss": 0.3244, "step": 275580 }, { "epoch": 1.6381641909041735, "grad_norm": 4.904210090637207, "learning_rate": 8.502912636288108e-06, "loss": 0.3851, "step": 275590 }, { "epoch": 1.638223632980842, "grad_norm": 4.006721019744873, "learning_rate": 8.502764572827018e-06, "loss": 0.32, "step": 275600 }, { "epoch": 1.6382830750575104, "grad_norm": 4.43397855758667, "learning_rate": 8.502616503333751e-06, "loss": 0.307, "step": 275610 }, { "epoch": 1.6383425171341786, "grad_norm": 3.326093912124634, "learning_rate": 8.502468427808562e-06, "loss": 0.3281, "step": 275620 }, { "epoch": 1.638401959210847, "grad_norm": 5.141115665435791, "learning_rate": 8.502320346251702e-06, "loss": 0.3398, "step": 275630 }, { "epoch": 1.6384614012875154, "grad_norm": 4.575697898864746, "learning_rate": 8.502172258663428e-06, "loss": 0.3548, "step": 275640 }, { "epoch": 1.6385208433641838, "grad_norm": 4.383706092834473, "learning_rate": 8.502024165043995e-06, "loss": 0.3144, "step": 275650 }, { "epoch": 1.6385802854408522, "grad_norm": 4.349756240844727, "learning_rate": 8.501876065393661e-06, "loss": 0.2978, "step": 275660 }, { "epoch": 1.6386397275175204, "grad_norm": 4.754319667816162, "learning_rate": 8.501727959712679e-06, "loss": 0.323, "step": 275670 }, { "epoch": 1.6386991695941888, "grad_norm": 5.481331825256348, "learning_rate": 8.501579848001302e-06, "loss": 0.3699, "step": 275680 }, { "epoch": 1.6387586116708572, "grad_norm": 4.519944667816162, "learning_rate": 8.501431730259789e-06, "loss": 0.3326, "step": 275690 }, { "epoch": 1.6388180537475256, "grad_norm": 6.771666526794434, "learning_rate": 8.501283606488388e-06, "loss": 0.3359, "step": 275700 }, { "epoch": 1.638877495824194, "grad_norm": 5.245849609375, "learning_rate": 8.501135476687364e-06, "loss": 0.3448, "step": 275710 }, { "epoch": 1.6389369379008625, "grad_norm": 4.355391979217529, "learning_rate": 8.500987340856963e-06, "loss": 0.325, "step": 275720 }, { "epoch": 1.638996379977531, "grad_norm": 5.5627007484436035, "learning_rate": 8.500839198997447e-06, "loss": 0.3204, "step": 275730 }, { "epoch": 1.6390558220541993, "grad_norm": 5.876522541046143, "learning_rate": 8.500691051109065e-06, "loss": 0.3661, "step": 275740 }, { "epoch": 1.6391152641308677, "grad_norm": 5.625355243682861, "learning_rate": 8.500542897192078e-06, "loss": 0.3192, "step": 275750 }, { "epoch": 1.6391747062075361, "grad_norm": 5.6180338859558105, "learning_rate": 8.500394737246738e-06, "loss": 0.3503, "step": 275760 }, { "epoch": 1.6392341482842046, "grad_norm": 5.308413505554199, "learning_rate": 8.5002465712733e-06, "loss": 0.338, "step": 275770 }, { "epoch": 1.639293590360873, "grad_norm": 6.200932502746582, "learning_rate": 8.50009839927202e-06, "loss": 0.3545, "step": 275780 }, { "epoch": 1.6393530324375414, "grad_norm": 4.390260219573975, "learning_rate": 8.499950221243154e-06, "loss": 0.3165, "step": 275790 }, { "epoch": 1.6394124745142098, "grad_norm": 6.239222526550293, "learning_rate": 8.499802037186955e-06, "loss": 0.3878, "step": 275800 }, { "epoch": 1.639471916590878, "grad_norm": 4.904754638671875, "learning_rate": 8.499653847103679e-06, "loss": 0.2918, "step": 275810 }, { "epoch": 1.6395313586675464, "grad_norm": 5.658093452453613, "learning_rate": 8.499505650993583e-06, "loss": 0.2899, "step": 275820 }, { "epoch": 1.6395908007442148, "grad_norm": 4.972282409667969, "learning_rate": 8.499357448856917e-06, "loss": 0.3278, "step": 275830 }, { "epoch": 1.6396502428208832, "grad_norm": 5.053638458251953, "learning_rate": 8.499209240693944e-06, "loss": 0.3307, "step": 275840 }, { "epoch": 1.6397096848975514, "grad_norm": 5.256111145019531, "learning_rate": 8.499061026504914e-06, "loss": 0.3152, "step": 275850 }, { "epoch": 1.6397691269742198, "grad_norm": 5.291415214538574, "learning_rate": 8.498912806290084e-06, "loss": 0.3383, "step": 275860 }, { "epoch": 1.6398285690508883, "grad_norm": 6.117563724517822, "learning_rate": 8.498764580049706e-06, "loss": 0.3506, "step": 275870 }, { "epoch": 1.6398880111275567, "grad_norm": 5.147332191467285, "learning_rate": 8.49861634778404e-06, "loss": 0.3171, "step": 275880 }, { "epoch": 1.639947453204225, "grad_norm": 8.523128509521484, "learning_rate": 8.49846810949334e-06, "loss": 0.381, "step": 275890 }, { "epoch": 1.6400068952808935, "grad_norm": 5.387383460998535, "learning_rate": 8.498319865177858e-06, "loss": 0.3713, "step": 275900 }, { "epoch": 1.640066337357562, "grad_norm": 3.8780694007873535, "learning_rate": 8.498171614837854e-06, "loss": 0.3156, "step": 275910 }, { "epoch": 1.6401257794342303, "grad_norm": 5.142096996307373, "learning_rate": 8.49802335847358e-06, "loss": 0.3399, "step": 275920 }, { "epoch": 1.6401852215108987, "grad_norm": 5.127541542053223, "learning_rate": 8.497875096085294e-06, "loss": 0.3533, "step": 275930 }, { "epoch": 1.6402446635875672, "grad_norm": 5.8995361328125, "learning_rate": 8.497726827673248e-06, "loss": 0.3514, "step": 275940 }, { "epoch": 1.6403041056642356, "grad_norm": 5.062497138977051, "learning_rate": 8.497578553237699e-06, "loss": 0.3161, "step": 275950 }, { "epoch": 1.640363547740904, "grad_norm": 5.067439556121826, "learning_rate": 8.497430272778902e-06, "loss": 0.3467, "step": 275960 }, { "epoch": 1.6404229898175724, "grad_norm": 3.977959394454956, "learning_rate": 8.497281986297114e-06, "loss": 0.3115, "step": 275970 }, { "epoch": 1.6404824318942408, "grad_norm": 3.947061538696289, "learning_rate": 8.497133693792587e-06, "loss": 0.3185, "step": 275980 }, { "epoch": 1.640541873970909, "grad_norm": 4.259409427642822, "learning_rate": 8.496985395265581e-06, "loss": 0.3284, "step": 275990 }, { "epoch": 1.6406013160475774, "grad_norm": 5.542903423309326, "learning_rate": 8.496837090716349e-06, "loss": 0.3482, "step": 276000 }, { "epoch": 1.6406607581242458, "grad_norm": 4.287477016448975, "learning_rate": 8.496688780145146e-06, "loss": 0.3253, "step": 276010 }, { "epoch": 1.6407202002009142, "grad_norm": 5.549703598022461, "learning_rate": 8.496540463552226e-06, "loss": 0.3183, "step": 276020 }, { "epoch": 1.6407796422775827, "grad_norm": 5.267623424530029, "learning_rate": 8.496392140937848e-06, "loss": 0.3619, "step": 276030 }, { "epoch": 1.6408390843542509, "grad_norm": 4.901757717132568, "learning_rate": 8.496243812302265e-06, "loss": 0.3157, "step": 276040 }, { "epoch": 1.6408985264309193, "grad_norm": 5.457666397094727, "learning_rate": 8.496095477645732e-06, "loss": 0.3331, "step": 276050 }, { "epoch": 1.6409579685075877, "grad_norm": 4.570146560668945, "learning_rate": 8.495947136968507e-06, "loss": 0.3271, "step": 276060 }, { "epoch": 1.641017410584256, "grad_norm": 6.008772850036621, "learning_rate": 8.495798790270842e-06, "loss": 0.3281, "step": 276070 }, { "epoch": 1.6410768526609245, "grad_norm": 4.660557746887207, "learning_rate": 8.495650437552996e-06, "loss": 0.3351, "step": 276080 }, { "epoch": 1.641136294737593, "grad_norm": 5.086550712585449, "learning_rate": 8.495502078815222e-06, "loss": 0.3632, "step": 276090 }, { "epoch": 1.6411957368142613, "grad_norm": 4.642610549926758, "learning_rate": 8.495353714057777e-06, "loss": 0.3371, "step": 276100 }, { "epoch": 1.6412551788909298, "grad_norm": 4.477445602416992, "learning_rate": 8.495205343280915e-06, "loss": 0.3503, "step": 276110 }, { "epoch": 1.6413146209675982, "grad_norm": 5.588336944580078, "learning_rate": 8.495056966484893e-06, "loss": 0.3555, "step": 276120 }, { "epoch": 1.6413740630442666, "grad_norm": 4.861100196838379, "learning_rate": 8.494908583669966e-06, "loss": 0.3456, "step": 276130 }, { "epoch": 1.641433505120935, "grad_norm": 4.444373607635498, "learning_rate": 8.49476019483639e-06, "loss": 0.3557, "step": 276140 }, { "epoch": 1.6414929471976034, "grad_norm": 6.198487281799316, "learning_rate": 8.494611799984418e-06, "loss": 0.3723, "step": 276150 }, { "epoch": 1.6415523892742718, "grad_norm": 5.607785701751709, "learning_rate": 8.49446339911431e-06, "loss": 0.3477, "step": 276160 }, { "epoch": 1.6416118313509402, "grad_norm": 4.891611099243164, "learning_rate": 8.494314992226318e-06, "loss": 0.3621, "step": 276170 }, { "epoch": 1.6416712734276084, "grad_norm": 4.399031639099121, "learning_rate": 8.494166579320698e-06, "loss": 0.3104, "step": 276180 }, { "epoch": 1.6417307155042768, "grad_norm": 5.5118021965026855, "learning_rate": 8.494018160397706e-06, "loss": 0.3321, "step": 276190 }, { "epoch": 1.6417901575809453, "grad_norm": 5.428158760070801, "learning_rate": 8.493869735457599e-06, "loss": 0.3704, "step": 276200 }, { "epoch": 1.6418495996576137, "grad_norm": 5.064195156097412, "learning_rate": 8.49372130450063e-06, "loss": 0.3441, "step": 276210 }, { "epoch": 1.6419090417342819, "grad_norm": 5.585641384124756, "learning_rate": 8.493572867527058e-06, "loss": 0.3606, "step": 276220 }, { "epoch": 1.6419684838109503, "grad_norm": 4.518469333648682, "learning_rate": 8.493424424537136e-06, "loss": 0.3262, "step": 276230 }, { "epoch": 1.6420279258876187, "grad_norm": 4.352304935455322, "learning_rate": 8.493275975531119e-06, "loss": 0.3546, "step": 276240 }, { "epoch": 1.6420873679642871, "grad_norm": 5.155548095703125, "learning_rate": 8.493127520509265e-06, "loss": 0.3082, "step": 276250 }, { "epoch": 1.6421468100409555, "grad_norm": 6.2811994552612305, "learning_rate": 8.492979059471829e-06, "loss": 0.3329, "step": 276260 }, { "epoch": 1.642206252117624, "grad_norm": 6.23975944519043, "learning_rate": 8.492830592419066e-06, "loss": 0.325, "step": 276270 }, { "epoch": 1.6422656941942924, "grad_norm": 5.407735824584961, "learning_rate": 8.492682119351232e-06, "loss": 0.3448, "step": 276280 }, { "epoch": 1.6423251362709608, "grad_norm": 5.633184909820557, "learning_rate": 8.49253364026858e-06, "loss": 0.3582, "step": 276290 }, { "epoch": 1.6423845783476292, "grad_norm": 5.615192413330078, "learning_rate": 8.492385155171372e-06, "loss": 0.3524, "step": 276300 }, { "epoch": 1.6424440204242976, "grad_norm": 6.07690954208374, "learning_rate": 8.492236664059858e-06, "loss": 0.367, "step": 276310 }, { "epoch": 1.642503462500966, "grad_norm": 3.65470027923584, "learning_rate": 8.492088166934299e-06, "loss": 0.3203, "step": 276320 }, { "epoch": 1.6425629045776344, "grad_norm": 4.6361775398254395, "learning_rate": 8.491939663794944e-06, "loss": 0.3612, "step": 276330 }, { "epoch": 1.6426223466543028, "grad_norm": 5.9012770652771, "learning_rate": 8.491791154642052e-06, "loss": 0.3454, "step": 276340 }, { "epoch": 1.6426817887309713, "grad_norm": 4.477347373962402, "learning_rate": 8.49164263947588e-06, "loss": 0.3492, "step": 276350 }, { "epoch": 1.6427412308076395, "grad_norm": 4.458871841430664, "learning_rate": 8.491494118296684e-06, "loss": 0.3317, "step": 276360 }, { "epoch": 1.6428006728843079, "grad_norm": 6.611647605895996, "learning_rate": 8.491345591104718e-06, "loss": 0.3091, "step": 276370 }, { "epoch": 1.6428601149609763, "grad_norm": 5.398751735687256, "learning_rate": 8.491197057900238e-06, "loss": 0.3357, "step": 276380 }, { "epoch": 1.6429195570376447, "grad_norm": 4.549917221069336, "learning_rate": 8.4910485186835e-06, "loss": 0.3797, "step": 276390 }, { "epoch": 1.642978999114313, "grad_norm": 6.102112770080566, "learning_rate": 8.49089997345476e-06, "loss": 0.3237, "step": 276400 }, { "epoch": 1.6430384411909813, "grad_norm": 4.057749271392822, "learning_rate": 8.490751422214273e-06, "loss": 0.3337, "step": 276410 }, { "epoch": 1.6430978832676497, "grad_norm": 7.622949600219727, "learning_rate": 8.490602864962297e-06, "loss": 0.3595, "step": 276420 }, { "epoch": 1.6431573253443181, "grad_norm": 4.203795433044434, "learning_rate": 8.490454301699086e-06, "loss": 0.3253, "step": 276430 }, { "epoch": 1.6432167674209865, "grad_norm": 5.150757789611816, "learning_rate": 8.490305732424894e-06, "loss": 0.3417, "step": 276440 }, { "epoch": 1.643276209497655, "grad_norm": 5.7142534255981445, "learning_rate": 8.490157157139981e-06, "loss": 0.3724, "step": 276450 }, { "epoch": 1.6433356515743234, "grad_norm": 4.975289344787598, "learning_rate": 8.490008575844602e-06, "loss": 0.3433, "step": 276460 }, { "epoch": 1.6433950936509918, "grad_norm": 4.640448093414307, "learning_rate": 8.489859988539011e-06, "loss": 0.338, "step": 276470 }, { "epoch": 1.6434545357276602, "grad_norm": 5.02846097946167, "learning_rate": 8.489711395223464e-06, "loss": 0.3146, "step": 276480 }, { "epoch": 1.6435139778043286, "grad_norm": 5.098976135253906, "learning_rate": 8.489562795898219e-06, "loss": 0.3124, "step": 276490 }, { "epoch": 1.643573419880997, "grad_norm": 5.636886119842529, "learning_rate": 8.489414190563528e-06, "loss": 0.3578, "step": 276500 }, { "epoch": 1.6436328619576654, "grad_norm": 4.584203243255615, "learning_rate": 8.489265579219652e-06, "loss": 0.3146, "step": 276510 }, { "epoch": 1.6436923040343339, "grad_norm": 5.385915756225586, "learning_rate": 8.48911696186684e-06, "loss": 0.3935, "step": 276520 }, { "epoch": 1.6437517461110023, "grad_norm": 6.473704814910889, "learning_rate": 8.488968338505357e-06, "loss": 0.3187, "step": 276530 }, { "epoch": 1.6438111881876705, "grad_norm": 5.448671340942383, "learning_rate": 8.488819709135454e-06, "loss": 0.3642, "step": 276540 }, { "epoch": 1.6438706302643389, "grad_norm": 6.370771408081055, "learning_rate": 8.488671073757386e-06, "loss": 0.3509, "step": 276550 }, { "epoch": 1.6439300723410073, "grad_norm": 3.9684789180755615, "learning_rate": 8.488522432371409e-06, "loss": 0.349, "step": 276560 }, { "epoch": 1.6439895144176757, "grad_norm": 4.757302284240723, "learning_rate": 8.488373784977781e-06, "loss": 0.3654, "step": 276570 }, { "epoch": 1.6440489564943441, "grad_norm": 3.620047092437744, "learning_rate": 8.488225131576758e-06, "loss": 0.3303, "step": 276580 }, { "epoch": 1.6441083985710123, "grad_norm": 4.895028114318848, "learning_rate": 8.488076472168595e-06, "loss": 0.34, "step": 276590 }, { "epoch": 1.6441678406476807, "grad_norm": 6.197850704193115, "learning_rate": 8.487927806753547e-06, "loss": 0.3449, "step": 276600 }, { "epoch": 1.6442272827243491, "grad_norm": 6.027028560638428, "learning_rate": 8.487779135331871e-06, "loss": 0.3366, "step": 276610 }, { "epoch": 1.6442867248010176, "grad_norm": 4.7094926834106445, "learning_rate": 8.487630457903824e-06, "loss": 0.3527, "step": 276620 }, { "epoch": 1.644346166877686, "grad_norm": 5.398895263671875, "learning_rate": 8.48748177446966e-06, "loss": 0.3061, "step": 276630 }, { "epoch": 1.6444056089543544, "grad_norm": 5.070091724395752, "learning_rate": 8.487333085029637e-06, "loss": 0.3238, "step": 276640 }, { "epoch": 1.6444650510310228, "grad_norm": 3.244964599609375, "learning_rate": 8.48718438958401e-06, "loss": 0.3456, "step": 276650 }, { "epoch": 1.6445244931076912, "grad_norm": 4.174107074737549, "learning_rate": 8.487035688133037e-06, "loss": 0.3176, "step": 276660 }, { "epoch": 1.6445839351843596, "grad_norm": 5.06232213973999, "learning_rate": 8.486886980676972e-06, "loss": 0.3513, "step": 276670 }, { "epoch": 1.644643377261028, "grad_norm": 6.33467435836792, "learning_rate": 8.486738267216071e-06, "loss": 0.3431, "step": 276680 }, { "epoch": 1.6447028193376965, "grad_norm": 5.567098617553711, "learning_rate": 8.48658954775059e-06, "loss": 0.3116, "step": 276690 }, { "epoch": 1.6447622614143649, "grad_norm": 4.96804141998291, "learning_rate": 8.486440822280788e-06, "loss": 0.3281, "step": 276700 }, { "epoch": 1.6448217034910333, "grad_norm": 3.5966684818267822, "learning_rate": 8.486292090806916e-06, "loss": 0.3309, "step": 276710 }, { "epoch": 1.6448811455677017, "grad_norm": 4.4411725997924805, "learning_rate": 8.486143353329234e-06, "loss": 0.3181, "step": 276720 }, { "epoch": 1.64494058764437, "grad_norm": 5.303109645843506, "learning_rate": 8.485994609847998e-06, "loss": 0.3168, "step": 276730 }, { "epoch": 1.6450000297210383, "grad_norm": 3.964416027069092, "learning_rate": 8.485845860363464e-06, "loss": 0.302, "step": 276740 }, { "epoch": 1.6450594717977067, "grad_norm": 5.235170364379883, "learning_rate": 8.485697104875887e-06, "loss": 0.3711, "step": 276750 }, { "epoch": 1.6451189138743751, "grad_norm": 4.875207901000977, "learning_rate": 8.485548343385522e-06, "loss": 0.3173, "step": 276760 }, { "epoch": 1.6451783559510436, "grad_norm": 5.527310848236084, "learning_rate": 8.485399575892628e-06, "loss": 0.3514, "step": 276770 }, { "epoch": 1.6452377980277118, "grad_norm": 7.4552693367004395, "learning_rate": 8.48525080239746e-06, "loss": 0.3364, "step": 276780 }, { "epoch": 1.6452972401043802, "grad_norm": 5.016251087188721, "learning_rate": 8.485102022900276e-06, "loss": 0.3126, "step": 276790 }, { "epoch": 1.6453566821810486, "grad_norm": 4.396121025085449, "learning_rate": 8.484953237401328e-06, "loss": 0.3265, "step": 276800 }, { "epoch": 1.645416124257717, "grad_norm": 4.613921165466309, "learning_rate": 8.484804445900876e-06, "loss": 0.3547, "step": 276810 }, { "epoch": 1.6454755663343854, "grad_norm": 6.398821830749512, "learning_rate": 8.484655648399173e-06, "loss": 0.325, "step": 276820 }, { "epoch": 1.6455350084110538, "grad_norm": 5.483181476593018, "learning_rate": 8.484506844896479e-06, "loss": 0.311, "step": 276830 }, { "epoch": 1.6455944504877222, "grad_norm": 4.4073333740234375, "learning_rate": 8.484358035393048e-06, "loss": 0.316, "step": 276840 }, { "epoch": 1.6456538925643907, "grad_norm": 6.923343658447266, "learning_rate": 8.484209219889137e-06, "loss": 0.3814, "step": 276850 }, { "epoch": 1.645713334641059, "grad_norm": 4.941736221313477, "learning_rate": 8.484060398385002e-06, "loss": 0.3369, "step": 276860 }, { "epoch": 1.6457727767177275, "grad_norm": 4.112094402313232, "learning_rate": 8.4839115708809e-06, "loss": 0.3436, "step": 276870 }, { "epoch": 1.645832218794396, "grad_norm": 4.775604724884033, "learning_rate": 8.483762737377086e-06, "loss": 0.3345, "step": 276880 }, { "epoch": 1.6458916608710643, "grad_norm": 4.685365676879883, "learning_rate": 8.483613897873816e-06, "loss": 0.3314, "step": 276890 }, { "epoch": 1.6459511029477327, "grad_norm": 3.8098511695861816, "learning_rate": 8.483465052371346e-06, "loss": 0.3199, "step": 276900 }, { "epoch": 1.646010545024401, "grad_norm": 4.882425308227539, "learning_rate": 8.483316200869938e-06, "loss": 0.3085, "step": 276910 }, { "epoch": 1.6460699871010693, "grad_norm": 4.776979923248291, "learning_rate": 8.48316734336984e-06, "loss": 0.3752, "step": 276920 }, { "epoch": 1.6461294291777377, "grad_norm": 3.3061740398406982, "learning_rate": 8.483018479871315e-06, "loss": 0.3534, "step": 276930 }, { "epoch": 1.6461888712544062, "grad_norm": 4.718541145324707, "learning_rate": 8.482869610374613e-06, "loss": 0.3046, "step": 276940 }, { "epoch": 1.6462483133310746, "grad_norm": 4.842931747436523, "learning_rate": 8.482720734879997e-06, "loss": 0.3519, "step": 276950 }, { "epoch": 1.6463077554077428, "grad_norm": 4.93198823928833, "learning_rate": 8.482571853387718e-06, "loss": 0.3319, "step": 276960 }, { "epoch": 1.6463671974844112, "grad_norm": 5.7259392738342285, "learning_rate": 8.482422965898037e-06, "loss": 0.3443, "step": 276970 }, { "epoch": 1.6464266395610796, "grad_norm": 4.56689453125, "learning_rate": 8.482274072411207e-06, "loss": 0.2905, "step": 276980 }, { "epoch": 1.646486081637748, "grad_norm": 5.398021221160889, "learning_rate": 8.482125172927487e-06, "loss": 0.309, "step": 276990 }, { "epoch": 1.6465455237144164, "grad_norm": 4.538562774658203, "learning_rate": 8.48197626744713e-06, "loss": 0.3624, "step": 277000 }, { "epoch": 1.6466049657910848, "grad_norm": 5.578433513641357, "learning_rate": 8.481827355970395e-06, "loss": 0.325, "step": 277010 }, { "epoch": 1.6466644078677533, "grad_norm": 4.0416388511657715, "learning_rate": 8.481678438497537e-06, "loss": 0.3395, "step": 277020 }, { "epoch": 1.6467238499444217, "grad_norm": 4.451737880706787, "learning_rate": 8.481529515028815e-06, "loss": 0.3651, "step": 277030 }, { "epoch": 1.64678329202109, "grad_norm": 4.278634071350098, "learning_rate": 8.481380585564483e-06, "loss": 0.2995, "step": 277040 }, { "epoch": 1.6468427340977585, "grad_norm": 5.300267219543457, "learning_rate": 8.481231650104798e-06, "loss": 0.3216, "step": 277050 }, { "epoch": 1.646902176174427, "grad_norm": 4.750133037567139, "learning_rate": 8.481082708650017e-06, "loss": 0.3394, "step": 277060 }, { "epoch": 1.6469616182510953, "grad_norm": 4.9568305015563965, "learning_rate": 8.480933761200396e-06, "loss": 0.343, "step": 277070 }, { "epoch": 1.6470210603277637, "grad_norm": 4.202791213989258, "learning_rate": 8.480784807756194e-06, "loss": 0.3304, "step": 277080 }, { "epoch": 1.6470805024044322, "grad_norm": 6.020330429077148, "learning_rate": 8.480635848317661e-06, "loss": 0.3437, "step": 277090 }, { "epoch": 1.6471399444811003, "grad_norm": 6.248881816864014, "learning_rate": 8.480486882885061e-06, "loss": 0.3149, "step": 277100 }, { "epoch": 1.6471993865577688, "grad_norm": 4.9800705909729, "learning_rate": 8.480337911458646e-06, "loss": 0.3623, "step": 277110 }, { "epoch": 1.6472588286344372, "grad_norm": 6.349677562713623, "learning_rate": 8.480188934038675e-06, "loss": 0.3286, "step": 277120 }, { "epoch": 1.6473182707111056, "grad_norm": 4.421393394470215, "learning_rate": 8.480039950625402e-06, "loss": 0.3612, "step": 277130 }, { "epoch": 1.647377712787774, "grad_norm": 3.7039225101470947, "learning_rate": 8.479890961219086e-06, "loss": 0.3054, "step": 277140 }, { "epoch": 1.6474371548644422, "grad_norm": 4.362705230712891, "learning_rate": 8.479741965819982e-06, "loss": 0.3095, "step": 277150 }, { "epoch": 1.6474965969411106, "grad_norm": 5.982137680053711, "learning_rate": 8.479592964428347e-06, "loss": 0.3784, "step": 277160 }, { "epoch": 1.647556039017779, "grad_norm": 5.115388870239258, "learning_rate": 8.479443957044438e-06, "loss": 0.3188, "step": 277170 }, { "epoch": 1.6476154810944474, "grad_norm": 4.784938335418701, "learning_rate": 8.47929494366851e-06, "loss": 0.3297, "step": 277180 }, { "epoch": 1.6476749231711159, "grad_norm": 4.690308570861816, "learning_rate": 8.479145924300824e-06, "loss": 0.38, "step": 277190 }, { "epoch": 1.6477343652477843, "grad_norm": 5.051988124847412, "learning_rate": 8.478996898941632e-06, "loss": 0.3023, "step": 277200 }, { "epoch": 1.6477938073244527, "grad_norm": 4.825772285461426, "learning_rate": 8.478847867591192e-06, "loss": 0.3069, "step": 277210 }, { "epoch": 1.647853249401121, "grad_norm": 4.384236812591553, "learning_rate": 8.47869883024976e-06, "loss": 0.3694, "step": 277220 }, { "epoch": 1.6479126914777895, "grad_norm": 4.832161903381348, "learning_rate": 8.478549786917595e-06, "loss": 0.3414, "step": 277230 }, { "epoch": 1.647972133554458, "grad_norm": 5.956887722015381, "learning_rate": 8.478400737594952e-06, "loss": 0.3578, "step": 277240 }, { "epoch": 1.6480315756311263, "grad_norm": 4.563859939575195, "learning_rate": 8.478251682282087e-06, "loss": 0.3434, "step": 277250 }, { "epoch": 1.6480910177077948, "grad_norm": 5.619439125061035, "learning_rate": 8.478102620979259e-06, "loss": 0.3493, "step": 277260 }, { "epoch": 1.6481504597844632, "grad_norm": 3.945732593536377, "learning_rate": 8.477953553686722e-06, "loss": 0.3152, "step": 277270 }, { "epoch": 1.6482099018611314, "grad_norm": 3.7380175590515137, "learning_rate": 8.477804480404734e-06, "loss": 0.3308, "step": 277280 }, { "epoch": 1.6482693439377998, "grad_norm": 4.833364486694336, "learning_rate": 8.47765540113355e-06, "loss": 0.3166, "step": 277290 }, { "epoch": 1.6483287860144682, "grad_norm": 5.109114170074463, "learning_rate": 8.477506315873432e-06, "loss": 0.3245, "step": 277300 }, { "epoch": 1.6483882280911366, "grad_norm": 4.241260528564453, "learning_rate": 8.477357224624632e-06, "loss": 0.3572, "step": 277310 }, { "epoch": 1.648447670167805, "grad_norm": 5.213187217712402, "learning_rate": 8.477208127387409e-06, "loss": 0.3552, "step": 277320 }, { "epoch": 1.6485071122444732, "grad_norm": 5.982976913452148, "learning_rate": 8.477059024162018e-06, "loss": 0.3003, "step": 277330 }, { "epoch": 1.6485665543211416, "grad_norm": 5.894961357116699, "learning_rate": 8.476909914948714e-06, "loss": 0.3614, "step": 277340 }, { "epoch": 1.64862599639781, "grad_norm": 4.209003925323486, "learning_rate": 8.47676079974776e-06, "loss": 0.3363, "step": 277350 }, { "epoch": 1.6486854384744785, "grad_norm": 4.432659149169922, "learning_rate": 8.476611678559406e-06, "loss": 0.3502, "step": 277360 }, { "epoch": 1.6487448805511469, "grad_norm": 5.720832347869873, "learning_rate": 8.476462551383914e-06, "loss": 0.3237, "step": 277370 }, { "epoch": 1.6488043226278153, "grad_norm": 6.680107116699219, "learning_rate": 8.476313418221538e-06, "loss": 0.3188, "step": 277380 }, { "epoch": 1.6488637647044837, "grad_norm": 4.072545051574707, "learning_rate": 8.476164279072535e-06, "loss": 0.3249, "step": 277390 }, { "epoch": 1.6489232067811521, "grad_norm": 4.564853668212891, "learning_rate": 8.476015133937164e-06, "loss": 0.3287, "step": 277400 }, { "epoch": 1.6489826488578205, "grad_norm": 4.413882732391357, "learning_rate": 8.475865982815677e-06, "loss": 0.2962, "step": 277410 }, { "epoch": 1.649042090934489, "grad_norm": 5.659477710723877, "learning_rate": 8.475716825708335e-06, "loss": 0.3603, "step": 277420 }, { "epoch": 1.6491015330111574, "grad_norm": 6.729337215423584, "learning_rate": 8.475567662615396e-06, "loss": 0.279, "step": 277430 }, { "epoch": 1.6491609750878258, "grad_norm": 5.014903545379639, "learning_rate": 8.475418493537112e-06, "loss": 0.3089, "step": 277440 }, { "epoch": 1.6492204171644942, "grad_norm": 5.876032829284668, "learning_rate": 8.475269318473746e-06, "loss": 0.3186, "step": 277450 }, { "epoch": 1.6492798592411626, "grad_norm": 6.292931079864502, "learning_rate": 8.47512013742555e-06, "loss": 0.327, "step": 277460 }, { "epoch": 1.6493393013178308, "grad_norm": 5.028340816497803, "learning_rate": 8.474970950392782e-06, "loss": 0.3464, "step": 277470 }, { "epoch": 1.6493987433944992, "grad_norm": 4.977876663208008, "learning_rate": 8.4748217573757e-06, "loss": 0.3337, "step": 277480 }, { "epoch": 1.6494581854711676, "grad_norm": 6.6127238273620605, "learning_rate": 8.474672558374561e-06, "loss": 0.3779, "step": 277490 }, { "epoch": 1.649517627547836, "grad_norm": 6.050694465637207, "learning_rate": 8.47452335338962e-06, "loss": 0.3566, "step": 277500 }, { "epoch": 1.6495770696245045, "grad_norm": 4.503259181976318, "learning_rate": 8.474374142421136e-06, "loss": 0.3569, "step": 277510 }, { "epoch": 1.6496365117011726, "grad_norm": 5.4063801765441895, "learning_rate": 8.474224925469364e-06, "loss": 0.3287, "step": 277520 }, { "epoch": 1.649695953777841, "grad_norm": 4.468736171722412, "learning_rate": 8.474075702534563e-06, "loss": 0.3321, "step": 277530 }, { "epoch": 1.6497553958545095, "grad_norm": 4.618673801422119, "learning_rate": 8.47392647361699e-06, "loss": 0.3328, "step": 277540 }, { "epoch": 1.649814837931178, "grad_norm": 5.566838264465332, "learning_rate": 8.473777238716899e-06, "loss": 0.3356, "step": 277550 }, { "epoch": 1.6498742800078463, "grad_norm": 5.526435852050781, "learning_rate": 8.47362799783455e-06, "loss": 0.3136, "step": 277560 }, { "epoch": 1.6499337220845147, "grad_norm": 5.689438819885254, "learning_rate": 8.473478750970198e-06, "loss": 0.3182, "step": 277570 }, { "epoch": 1.6499931641611831, "grad_norm": 4.167050838470459, "learning_rate": 8.473329498124103e-06, "loss": 0.3403, "step": 277580 }, { "epoch": 1.6500526062378515, "grad_norm": 4.170713901519775, "learning_rate": 8.47318023929652e-06, "loss": 0.3479, "step": 277590 }, { "epoch": 1.65011204831452, "grad_norm": 4.927309513092041, "learning_rate": 8.473030974487706e-06, "loss": 0.326, "step": 277600 }, { "epoch": 1.6501714903911884, "grad_norm": 4.631343841552734, "learning_rate": 8.472881703697918e-06, "loss": 0.3367, "step": 277610 }, { "epoch": 1.6502309324678568, "grad_norm": 4.686307430267334, "learning_rate": 8.472732426927413e-06, "loss": 0.3228, "step": 277620 }, { "epoch": 1.6502903745445252, "grad_norm": 5.390954971313477, "learning_rate": 8.472583144176449e-06, "loss": 0.3485, "step": 277630 }, { "epoch": 1.6503498166211936, "grad_norm": 4.62788200378418, "learning_rate": 8.472433855445283e-06, "loss": 0.3228, "step": 277640 }, { "epoch": 1.6504092586978618, "grad_norm": 5.1057963371276855, "learning_rate": 8.472284560734171e-06, "loss": 0.3321, "step": 277650 }, { "epoch": 1.6504687007745302, "grad_norm": 3.0353035926818848, "learning_rate": 8.47213526004337e-06, "loss": 0.3423, "step": 277660 }, { "epoch": 1.6505281428511986, "grad_norm": 4.057426452636719, "learning_rate": 8.471985953373138e-06, "loss": 0.3021, "step": 277670 }, { "epoch": 1.650587584927867, "grad_norm": 4.655341625213623, "learning_rate": 8.471836640723734e-06, "loss": 0.3252, "step": 277680 }, { "epoch": 1.6506470270045355, "grad_norm": 3.807800054550171, "learning_rate": 8.471687322095412e-06, "loss": 0.2922, "step": 277690 }, { "epoch": 1.6507064690812037, "grad_norm": 4.831136703491211, "learning_rate": 8.471537997488428e-06, "loss": 0.3085, "step": 277700 }, { "epoch": 1.650765911157872, "grad_norm": 4.429659366607666, "learning_rate": 8.471388666903045e-06, "loss": 0.3525, "step": 277710 }, { "epoch": 1.6508253532345405, "grad_norm": 5.329281330108643, "learning_rate": 8.471239330339512e-06, "loss": 0.3249, "step": 277720 }, { "epoch": 1.650884795311209, "grad_norm": 5.4674153327941895, "learning_rate": 8.471089987798094e-06, "loss": 0.3323, "step": 277730 }, { "epoch": 1.6509442373878773, "grad_norm": 5.36168098449707, "learning_rate": 8.470940639279043e-06, "loss": 0.347, "step": 277740 }, { "epoch": 1.6510036794645457, "grad_norm": 5.534495830535889, "learning_rate": 8.47079128478262e-06, "loss": 0.3655, "step": 277750 }, { "epoch": 1.6510631215412142, "grad_norm": 6.924467086791992, "learning_rate": 8.47064192430908e-06, "loss": 0.3339, "step": 277760 }, { "epoch": 1.6511225636178826, "grad_norm": 4.833935260772705, "learning_rate": 8.47049255785868e-06, "loss": 0.3587, "step": 277770 }, { "epoch": 1.651182005694551, "grad_norm": 5.254169464111328, "learning_rate": 8.470343185431677e-06, "loss": 0.3207, "step": 277780 }, { "epoch": 1.6512414477712194, "grad_norm": 3.9550468921661377, "learning_rate": 8.470193807028328e-06, "loss": 0.3198, "step": 277790 }, { "epoch": 1.6513008898478878, "grad_norm": 6.196021556854248, "learning_rate": 8.470044422648894e-06, "loss": 0.3666, "step": 277800 }, { "epoch": 1.6513603319245562, "grad_norm": 4.372398853302002, "learning_rate": 8.469895032293629e-06, "loss": 0.3014, "step": 277810 }, { "epoch": 1.6514197740012246, "grad_norm": 4.69790506362915, "learning_rate": 8.46974563596279e-06, "loss": 0.3733, "step": 277820 }, { "epoch": 1.651479216077893, "grad_norm": 4.352318286895752, "learning_rate": 8.469596233656634e-06, "loss": 0.2942, "step": 277830 }, { "epoch": 1.6515386581545612, "grad_norm": 5.877785682678223, "learning_rate": 8.46944682537542e-06, "loss": 0.3478, "step": 277840 }, { "epoch": 1.6515981002312297, "grad_norm": 4.8576483726501465, "learning_rate": 8.469297411119405e-06, "loss": 0.3364, "step": 277850 }, { "epoch": 1.651657542307898, "grad_norm": 4.924488067626953, "learning_rate": 8.469147990888846e-06, "loss": 0.3209, "step": 277860 }, { "epoch": 1.6517169843845665, "grad_norm": 6.668790817260742, "learning_rate": 8.468998564684e-06, "loss": 0.3297, "step": 277870 }, { "epoch": 1.651776426461235, "grad_norm": 5.639607906341553, "learning_rate": 8.468849132505125e-06, "loss": 0.3616, "step": 277880 }, { "epoch": 1.651835868537903, "grad_norm": 3.648399829864502, "learning_rate": 8.468699694352477e-06, "loss": 0.2953, "step": 277890 }, { "epoch": 1.6518953106145715, "grad_norm": 4.580738067626953, "learning_rate": 8.468550250226315e-06, "loss": 0.329, "step": 277900 }, { "epoch": 1.65195475269124, "grad_norm": 4.767788410186768, "learning_rate": 8.468400800126895e-06, "loss": 0.3373, "step": 277910 }, { "epoch": 1.6520141947679083, "grad_norm": 5.3671135902404785, "learning_rate": 8.468251344054474e-06, "loss": 0.3271, "step": 277920 }, { "epoch": 1.6520736368445768, "grad_norm": 4.620441913604736, "learning_rate": 8.468101882009313e-06, "loss": 0.3608, "step": 277930 }, { "epoch": 1.6521330789212452, "grad_norm": 5.690487384796143, "learning_rate": 8.467952413991664e-06, "loss": 0.3569, "step": 277940 }, { "epoch": 1.6521925209979136, "grad_norm": 4.74755334854126, "learning_rate": 8.46780294000179e-06, "loss": 0.292, "step": 277950 }, { "epoch": 1.652251963074582, "grad_norm": 4.767306804656982, "learning_rate": 8.467653460039945e-06, "loss": 0.3254, "step": 277960 }, { "epoch": 1.6523114051512504, "grad_norm": 4.86787223815918, "learning_rate": 8.467503974106385e-06, "loss": 0.3597, "step": 277970 }, { "epoch": 1.6523708472279188, "grad_norm": 5.302379131317139, "learning_rate": 8.467354482201371e-06, "loss": 0.3176, "step": 277980 }, { "epoch": 1.6524302893045872, "grad_norm": 4.406154632568359, "learning_rate": 8.467204984325158e-06, "loss": 0.3574, "step": 277990 }, { "epoch": 1.6524897313812557, "grad_norm": 4.074280738830566, "learning_rate": 8.467055480478004e-06, "loss": 0.337, "step": 278000 }, { "epoch": 1.652549173457924, "grad_norm": 4.859485149383545, "learning_rate": 8.466905970660168e-06, "loss": 0.3393, "step": 278010 }, { "epoch": 1.6526086155345923, "grad_norm": 5.432437896728516, "learning_rate": 8.466756454871905e-06, "loss": 0.346, "step": 278020 }, { "epoch": 1.6526680576112607, "grad_norm": 5.053784370422363, "learning_rate": 8.466606933113474e-06, "loss": 0.3428, "step": 278030 }, { "epoch": 1.652727499687929, "grad_norm": 4.331248760223389, "learning_rate": 8.466457405385134e-06, "loss": 0.3476, "step": 278040 }, { "epoch": 1.6527869417645975, "grad_norm": 5.883158206939697, "learning_rate": 8.46630787168714e-06, "loss": 0.3256, "step": 278050 }, { "epoch": 1.652846383841266, "grad_norm": 8.143231391906738, "learning_rate": 8.46615833201975e-06, "loss": 0.3661, "step": 278060 }, { "epoch": 1.6529058259179341, "grad_norm": 4.977073669433594, "learning_rate": 8.46600878638322e-06, "loss": 0.3545, "step": 278070 }, { "epoch": 1.6529652679946025, "grad_norm": 5.530230522155762, "learning_rate": 8.465859234777812e-06, "loss": 0.341, "step": 278080 }, { "epoch": 1.653024710071271, "grad_norm": 5.360105037689209, "learning_rate": 8.465709677203779e-06, "loss": 0.3452, "step": 278090 }, { "epoch": 1.6530841521479394, "grad_norm": 2.850452184677124, "learning_rate": 8.46556011366138e-06, "loss": 0.3069, "step": 278100 }, { "epoch": 1.6531435942246078, "grad_norm": 4.875175476074219, "learning_rate": 8.465410544150875e-06, "loss": 0.3289, "step": 278110 }, { "epoch": 1.6532030363012762, "grad_norm": 5.231165409088135, "learning_rate": 8.465260968672519e-06, "loss": 0.3266, "step": 278120 }, { "epoch": 1.6532624783779446, "grad_norm": 5.521613597869873, "learning_rate": 8.46511138722657e-06, "loss": 0.3366, "step": 278130 }, { "epoch": 1.653321920454613, "grad_norm": 4.406348705291748, "learning_rate": 8.464961799813286e-06, "loss": 0.3126, "step": 278140 }, { "epoch": 1.6533813625312814, "grad_norm": 5.466873645782471, "learning_rate": 8.464812206432922e-06, "loss": 0.3145, "step": 278150 }, { "epoch": 1.6534408046079498, "grad_norm": 4.898237705230713, "learning_rate": 8.46466260708574e-06, "loss": 0.3461, "step": 278160 }, { "epoch": 1.6535002466846183, "grad_norm": 4.6754326820373535, "learning_rate": 8.464513001771995e-06, "loss": 0.3238, "step": 278170 }, { "epoch": 1.6535596887612867, "grad_norm": 4.5262956619262695, "learning_rate": 8.464363390491947e-06, "loss": 0.3452, "step": 278180 }, { "epoch": 1.653619130837955, "grad_norm": 3.8461015224456787, "learning_rate": 8.464213773245849e-06, "loss": 0.3114, "step": 278190 }, { "epoch": 1.6536785729146235, "grad_norm": 4.873222827911377, "learning_rate": 8.464064150033964e-06, "loss": 0.3391, "step": 278200 }, { "epoch": 1.6537380149912917, "grad_norm": 4.637221336364746, "learning_rate": 8.463914520856547e-06, "loss": 0.3319, "step": 278210 }, { "epoch": 1.65379745706796, "grad_norm": 5.915131568908691, "learning_rate": 8.463764885713854e-06, "loss": 0.3321, "step": 278220 }, { "epoch": 1.6538568991446285, "grad_norm": 6.7027974128723145, "learning_rate": 8.463615244606146e-06, "loss": 0.3492, "step": 278230 }, { "epoch": 1.653916341221297, "grad_norm": 5.046153545379639, "learning_rate": 8.46346559753368e-06, "loss": 0.2965, "step": 278240 }, { "epoch": 1.6539757832979654, "grad_norm": 6.682884693145752, "learning_rate": 8.46331594449671e-06, "loss": 0.3495, "step": 278250 }, { "epoch": 1.6540352253746335, "grad_norm": 5.188667297363281, "learning_rate": 8.4631662854955e-06, "loss": 0.3014, "step": 278260 }, { "epoch": 1.654094667451302, "grad_norm": 4.903119087219238, "learning_rate": 8.463016620530302e-06, "loss": 0.328, "step": 278270 }, { "epoch": 1.6541541095279704, "grad_norm": 6.204939365386963, "learning_rate": 8.462866949601378e-06, "loss": 0.3159, "step": 278280 }, { "epoch": 1.6542135516046388, "grad_norm": 5.454200267791748, "learning_rate": 8.462717272708982e-06, "loss": 0.3486, "step": 278290 }, { "epoch": 1.6542729936813072, "grad_norm": 3.844233989715576, "learning_rate": 8.462567589853377e-06, "loss": 0.3492, "step": 278300 }, { "epoch": 1.6543324357579756, "grad_norm": 6.141401290893555, "learning_rate": 8.462417901034813e-06, "loss": 0.3404, "step": 278310 }, { "epoch": 1.654391877834644, "grad_norm": 4.161875247955322, "learning_rate": 8.462268206253557e-06, "loss": 0.3422, "step": 278320 }, { "epoch": 1.6544513199113124, "grad_norm": 4.3813796043396, "learning_rate": 8.462118505509858e-06, "loss": 0.3153, "step": 278330 }, { "epoch": 1.6545107619879809, "grad_norm": 4.3536505699157715, "learning_rate": 8.46196879880398e-06, "loss": 0.3421, "step": 278340 }, { "epoch": 1.6545702040646493, "grad_norm": 3.740764617919922, "learning_rate": 8.461819086136178e-06, "loss": 0.3096, "step": 278350 }, { "epoch": 1.6546296461413177, "grad_norm": 4.620594501495361, "learning_rate": 8.46166936750671e-06, "loss": 0.2971, "step": 278360 }, { "epoch": 1.654689088217986, "grad_norm": 4.9457688331604, "learning_rate": 8.461519642915836e-06, "loss": 0.3412, "step": 278370 }, { "epoch": 1.6547485302946545, "grad_norm": 5.275125503540039, "learning_rate": 8.461369912363811e-06, "loss": 0.3028, "step": 278380 }, { "epoch": 1.6548079723713227, "grad_norm": 4.931281089782715, "learning_rate": 8.461220175850895e-06, "loss": 0.3474, "step": 278390 }, { "epoch": 1.6548674144479911, "grad_norm": 3.43402099609375, "learning_rate": 8.461070433377344e-06, "loss": 0.3299, "step": 278400 }, { "epoch": 1.6549268565246595, "grad_norm": 6.591651439666748, "learning_rate": 8.460920684943415e-06, "loss": 0.3537, "step": 278410 }, { "epoch": 1.654986298601328, "grad_norm": 4.71250057220459, "learning_rate": 8.460770930549371e-06, "loss": 0.3455, "step": 278420 }, { "epoch": 1.6550457406779964, "grad_norm": 8.597050666809082, "learning_rate": 8.460621170195464e-06, "loss": 0.3319, "step": 278430 }, { "epoch": 1.6551051827546646, "grad_norm": 4.885025978088379, "learning_rate": 8.460471403881956e-06, "loss": 0.3415, "step": 278440 }, { "epoch": 1.655164624831333, "grad_norm": 4.184524059295654, "learning_rate": 8.460321631609103e-06, "loss": 0.3378, "step": 278450 }, { "epoch": 1.6552240669080014, "grad_norm": 5.798043251037598, "learning_rate": 8.460171853377161e-06, "loss": 0.2814, "step": 278460 }, { "epoch": 1.6552835089846698, "grad_norm": 4.643346786499023, "learning_rate": 8.460022069186394e-06, "loss": 0.3031, "step": 278470 }, { "epoch": 1.6553429510613382, "grad_norm": 4.574998378753662, "learning_rate": 8.459872279037054e-06, "loss": 0.3292, "step": 278480 }, { "epoch": 1.6554023931380066, "grad_norm": 3.7354726791381836, "learning_rate": 8.4597224829294e-06, "loss": 0.3133, "step": 278490 }, { "epoch": 1.655461835214675, "grad_norm": 3.977339744567871, "learning_rate": 8.459572680863692e-06, "loss": 0.3219, "step": 278500 }, { "epoch": 1.6555212772913435, "grad_norm": 5.366125583648682, "learning_rate": 8.459422872840189e-06, "loss": 0.3304, "step": 278510 }, { "epoch": 1.6555807193680119, "grad_norm": 4.5940704345703125, "learning_rate": 8.459273058859145e-06, "loss": 0.3666, "step": 278520 }, { "epoch": 1.6556401614446803, "grad_norm": 5.0915751457214355, "learning_rate": 8.459123238920821e-06, "loss": 0.3588, "step": 278530 }, { "epoch": 1.6556996035213487, "grad_norm": 5.043738842010498, "learning_rate": 8.458973413025473e-06, "loss": 0.3119, "step": 278540 }, { "epoch": 1.6557590455980171, "grad_norm": 6.568845272064209, "learning_rate": 8.458823581173361e-06, "loss": 0.3707, "step": 278550 }, { "epoch": 1.6558184876746855, "grad_norm": 6.231036186218262, "learning_rate": 8.458673743364743e-06, "loss": 0.3326, "step": 278560 }, { "epoch": 1.655877929751354, "grad_norm": 4.888076305389404, "learning_rate": 8.458523899599875e-06, "loss": 0.344, "step": 278570 }, { "epoch": 1.6559373718280221, "grad_norm": 5.827671527862549, "learning_rate": 8.458374049879016e-06, "loss": 0.3524, "step": 278580 }, { "epoch": 1.6559968139046906, "grad_norm": 5.258763313293457, "learning_rate": 8.458224194202424e-06, "loss": 0.3235, "step": 278590 }, { "epoch": 1.656056255981359, "grad_norm": 5.841001987457275, "learning_rate": 8.458074332570358e-06, "loss": 0.3301, "step": 278600 }, { "epoch": 1.6561156980580274, "grad_norm": 5.0719146728515625, "learning_rate": 8.457924464983075e-06, "loss": 0.3372, "step": 278610 }, { "epoch": 1.6561751401346958, "grad_norm": 5.883163928985596, "learning_rate": 8.457774591440833e-06, "loss": 0.2987, "step": 278620 }, { "epoch": 1.656234582211364, "grad_norm": 5.5088677406311035, "learning_rate": 8.45762471194389e-06, "loss": 0.3268, "step": 278630 }, { "epoch": 1.6562940242880324, "grad_norm": 5.755592346191406, "learning_rate": 8.457474826492507e-06, "loss": 0.3496, "step": 278640 }, { "epoch": 1.6563534663647008, "grad_norm": 5.954291820526123, "learning_rate": 8.457324935086938e-06, "loss": 0.3318, "step": 278650 }, { "epoch": 1.6564129084413692, "grad_norm": 6.148260593414307, "learning_rate": 8.457175037727445e-06, "loss": 0.3269, "step": 278660 }, { "epoch": 1.6564723505180377, "grad_norm": 3.88303542137146, "learning_rate": 8.457025134414282e-06, "loss": 0.2992, "step": 278670 }, { "epoch": 1.656531792594706, "grad_norm": 5.701662540435791, "learning_rate": 8.456875225147709e-06, "loss": 0.3128, "step": 278680 }, { "epoch": 1.6565912346713745, "grad_norm": 5.464194297790527, "learning_rate": 8.456725309927987e-06, "loss": 0.3527, "step": 278690 }, { "epoch": 1.656650676748043, "grad_norm": 5.882296085357666, "learning_rate": 8.456575388755368e-06, "loss": 0.3547, "step": 278700 }, { "epoch": 1.6567101188247113, "grad_norm": 5.234766006469727, "learning_rate": 8.456425461630116e-06, "loss": 0.3521, "step": 278710 }, { "epoch": 1.6567695609013797, "grad_norm": 5.041654586791992, "learning_rate": 8.456275528552487e-06, "loss": 0.3299, "step": 278720 }, { "epoch": 1.6568290029780481, "grad_norm": 4.777060031890869, "learning_rate": 8.45612558952274e-06, "loss": 0.3043, "step": 278730 }, { "epoch": 1.6568884450547166, "grad_norm": 4.509798526763916, "learning_rate": 8.45597564454113e-06, "loss": 0.3281, "step": 278740 }, { "epoch": 1.656947887131385, "grad_norm": 4.509352207183838, "learning_rate": 8.455825693607918e-06, "loss": 0.3655, "step": 278750 }, { "epoch": 1.6570073292080532, "grad_norm": 4.974486827850342, "learning_rate": 8.455675736723363e-06, "loss": 0.3276, "step": 278760 }, { "epoch": 1.6570667712847216, "grad_norm": 5.724655628204346, "learning_rate": 8.455525773887721e-06, "loss": 0.3332, "step": 278770 }, { "epoch": 1.65712621336139, "grad_norm": 6.632248401641846, "learning_rate": 8.45537580510125e-06, "loss": 0.3301, "step": 278780 }, { "epoch": 1.6571856554380584, "grad_norm": 5.808193206787109, "learning_rate": 8.455225830364213e-06, "loss": 0.3518, "step": 278790 }, { "epoch": 1.6572450975147268, "grad_norm": 5.118954181671143, "learning_rate": 8.455075849676864e-06, "loss": 0.3399, "step": 278800 }, { "epoch": 1.657304539591395, "grad_norm": 5.447656631469727, "learning_rate": 8.45492586303946e-06, "loss": 0.3204, "step": 278810 }, { "epoch": 1.6573639816680634, "grad_norm": 7.55658483505249, "learning_rate": 8.454775870452264e-06, "loss": 0.3675, "step": 278820 }, { "epoch": 1.6574234237447318, "grad_norm": 4.54863977432251, "learning_rate": 8.45462587191553e-06, "loss": 0.3609, "step": 278830 }, { "epoch": 1.6574828658214003, "grad_norm": 5.425649642944336, "learning_rate": 8.454475867429518e-06, "loss": 0.3038, "step": 278840 }, { "epoch": 1.6575423078980687, "grad_norm": 5.901553153991699, "learning_rate": 8.454325856994488e-06, "loss": 0.3816, "step": 278850 }, { "epoch": 1.657601749974737, "grad_norm": 3.9067370891571045, "learning_rate": 8.454175840610694e-06, "loss": 0.3418, "step": 278860 }, { "epoch": 1.6576611920514055, "grad_norm": 4.225880146026611, "learning_rate": 8.4540258182784e-06, "loss": 0.3467, "step": 278870 }, { "epoch": 1.657720634128074, "grad_norm": 4.693147659301758, "learning_rate": 8.453875789997859e-06, "loss": 0.3285, "step": 278880 }, { "epoch": 1.6577800762047423, "grad_norm": 7.703773498535156, "learning_rate": 8.453725755769333e-06, "loss": 0.3536, "step": 278890 }, { "epoch": 1.6578395182814107, "grad_norm": 5.714343547821045, "learning_rate": 8.45357571559308e-06, "loss": 0.3207, "step": 278900 }, { "epoch": 1.6578989603580792, "grad_norm": 5.332101821899414, "learning_rate": 8.453425669469355e-06, "loss": 0.3543, "step": 278910 }, { "epoch": 1.6579584024347476, "grad_norm": 3.5710129737854004, "learning_rate": 8.453275617398421e-06, "loss": 0.3425, "step": 278920 }, { "epoch": 1.658017844511416, "grad_norm": 5.84490966796875, "learning_rate": 8.453125559380535e-06, "loss": 0.3693, "step": 278930 }, { "epoch": 1.6580772865880844, "grad_norm": 6.039200782775879, "learning_rate": 8.452975495415954e-06, "loss": 0.3211, "step": 278940 }, { "epoch": 1.6581367286647526, "grad_norm": 3.8604276180267334, "learning_rate": 8.452825425504936e-06, "loss": 0.3295, "step": 278950 }, { "epoch": 1.658196170741421, "grad_norm": 4.9095001220703125, "learning_rate": 8.452675349647741e-06, "loss": 0.3606, "step": 278960 }, { "epoch": 1.6582556128180894, "grad_norm": 4.392080783843994, "learning_rate": 8.45252526784463e-06, "loss": 0.3054, "step": 278970 }, { "epoch": 1.6583150548947578, "grad_norm": 6.364124298095703, "learning_rate": 8.452375180095854e-06, "loss": 0.3256, "step": 278980 }, { "epoch": 1.6583744969714262, "grad_norm": 5.679196357727051, "learning_rate": 8.452225086401677e-06, "loss": 0.3232, "step": 278990 }, { "epoch": 1.6584339390480944, "grad_norm": 5.253663063049316, "learning_rate": 8.452074986762359e-06, "loss": 0.3325, "step": 279000 }, { "epoch": 1.6584933811247629, "grad_norm": 4.131861686706543, "learning_rate": 8.451924881178155e-06, "loss": 0.3346, "step": 279010 }, { "epoch": 1.6585528232014313, "grad_norm": 4.379931449890137, "learning_rate": 8.451774769649323e-06, "loss": 0.3249, "step": 279020 }, { "epoch": 1.6586122652780997, "grad_norm": 6.5772223472595215, "learning_rate": 8.451624652176124e-06, "loss": 0.3234, "step": 279030 }, { "epoch": 1.658671707354768, "grad_norm": 5.3345818519592285, "learning_rate": 8.451474528758816e-06, "loss": 0.3235, "step": 279040 }, { "epoch": 1.6587311494314365, "grad_norm": 7.216028690338135, "learning_rate": 8.451324399397657e-06, "loss": 0.3392, "step": 279050 }, { "epoch": 1.658790591508105, "grad_norm": 4.95610237121582, "learning_rate": 8.451174264092905e-06, "loss": 0.322, "step": 279060 }, { "epoch": 1.6588500335847733, "grad_norm": 4.771431922912598, "learning_rate": 8.45102412284482e-06, "loss": 0.3462, "step": 279070 }, { "epoch": 1.6589094756614418, "grad_norm": 4.543039321899414, "learning_rate": 8.450873975653657e-06, "loss": 0.3352, "step": 279080 }, { "epoch": 1.6589689177381102, "grad_norm": 5.6436262130737305, "learning_rate": 8.45072382251968e-06, "loss": 0.3384, "step": 279090 }, { "epoch": 1.6590283598147786, "grad_norm": 5.648866653442383, "learning_rate": 8.450573663443145e-06, "loss": 0.2919, "step": 279100 }, { "epoch": 1.659087801891447, "grad_norm": 5.189599990844727, "learning_rate": 8.45042349842431e-06, "loss": 0.3249, "step": 279110 }, { "epoch": 1.6591472439681154, "grad_norm": 6.09727668762207, "learning_rate": 8.450273327463433e-06, "loss": 0.311, "step": 279120 }, { "epoch": 1.6592066860447836, "grad_norm": 4.991522312164307, "learning_rate": 8.450123150560774e-06, "loss": 0.3488, "step": 279130 }, { "epoch": 1.659266128121452, "grad_norm": 5.492835521697998, "learning_rate": 8.449972967716591e-06, "loss": 0.3108, "step": 279140 }, { "epoch": 1.6593255701981204, "grad_norm": 6.478760719299316, "learning_rate": 8.449822778931143e-06, "loss": 0.3602, "step": 279150 }, { "epoch": 1.6593850122747889, "grad_norm": 4.1465864181518555, "learning_rate": 8.449672584204688e-06, "loss": 0.345, "step": 279160 }, { "epoch": 1.6594444543514573, "grad_norm": 5.284509181976318, "learning_rate": 8.449522383537487e-06, "loss": 0.3084, "step": 279170 }, { "epoch": 1.6595038964281255, "grad_norm": 4.428637981414795, "learning_rate": 8.449372176929796e-06, "loss": 0.2966, "step": 279180 }, { "epoch": 1.6595633385047939, "grad_norm": 6.986252307891846, "learning_rate": 8.449221964381875e-06, "loss": 0.3473, "step": 279190 }, { "epoch": 1.6596227805814623, "grad_norm": 5.587689399719238, "learning_rate": 8.449071745893982e-06, "loss": 0.3244, "step": 279200 }, { "epoch": 1.6596822226581307, "grad_norm": 5.354218482971191, "learning_rate": 8.448921521466375e-06, "loss": 0.3192, "step": 279210 }, { "epoch": 1.6597416647347991, "grad_norm": 3.7805771827697754, "learning_rate": 8.448771291099315e-06, "loss": 0.3022, "step": 279220 }, { "epoch": 1.6598011068114675, "grad_norm": 4.837993621826172, "learning_rate": 8.448621054793059e-06, "loss": 0.3084, "step": 279230 }, { "epoch": 1.659860548888136, "grad_norm": 5.349567890167236, "learning_rate": 8.448470812547866e-06, "loss": 0.3353, "step": 279240 }, { "epoch": 1.6599199909648044, "grad_norm": 5.012570381164551, "learning_rate": 8.448320564363993e-06, "loss": 0.3358, "step": 279250 }, { "epoch": 1.6599794330414728, "grad_norm": 5.960639953613281, "learning_rate": 8.448170310241703e-06, "loss": 0.3471, "step": 279260 }, { "epoch": 1.6600388751181412, "grad_norm": 4.504553318023682, "learning_rate": 8.448020050181251e-06, "loss": 0.3318, "step": 279270 }, { "epoch": 1.6600983171948096, "grad_norm": 3.11910080909729, "learning_rate": 8.447869784182899e-06, "loss": 0.3043, "step": 279280 }, { "epoch": 1.660157759271478, "grad_norm": 5.191591739654541, "learning_rate": 8.447719512246901e-06, "loss": 0.3144, "step": 279290 }, { "epoch": 1.6602172013481464, "grad_norm": 5.39899206161499, "learning_rate": 8.447569234373519e-06, "loss": 0.309, "step": 279300 }, { "epoch": 1.6602766434248148, "grad_norm": 6.734436988830566, "learning_rate": 8.447418950563014e-06, "loss": 0.37, "step": 279310 }, { "epoch": 1.660336085501483, "grad_norm": 4.181172847747803, "learning_rate": 8.44726866081564e-06, "loss": 0.3351, "step": 279320 }, { "epoch": 1.6603955275781515, "grad_norm": 4.981591701507568, "learning_rate": 8.447118365131658e-06, "loss": 0.3411, "step": 279330 }, { "epoch": 1.6604549696548199, "grad_norm": 5.23043966293335, "learning_rate": 8.446968063511326e-06, "loss": 0.3289, "step": 279340 }, { "epoch": 1.6605144117314883, "grad_norm": 4.352142333984375, "learning_rate": 8.446817755954906e-06, "loss": 0.3388, "step": 279350 }, { "epoch": 1.6605738538081567, "grad_norm": 5.496828556060791, "learning_rate": 8.446667442462656e-06, "loss": 0.3147, "step": 279360 }, { "epoch": 1.660633295884825, "grad_norm": 6.058608055114746, "learning_rate": 8.44651712303483e-06, "loss": 0.357, "step": 279370 }, { "epoch": 1.6606927379614933, "grad_norm": 6.025175094604492, "learning_rate": 8.44636679767169e-06, "loss": 0.3514, "step": 279380 }, { "epoch": 1.6607521800381617, "grad_norm": 6.81257963180542, "learning_rate": 8.446216466373497e-06, "loss": 0.3482, "step": 279390 }, { "epoch": 1.6608116221148301, "grad_norm": 4.881299018859863, "learning_rate": 8.446066129140507e-06, "loss": 0.3545, "step": 279400 }, { "epoch": 1.6608710641914985, "grad_norm": 6.690151214599609, "learning_rate": 8.445915785972982e-06, "loss": 0.3268, "step": 279410 }, { "epoch": 1.660930506268167, "grad_norm": 5.868812561035156, "learning_rate": 8.445765436871177e-06, "loss": 0.4244, "step": 279420 }, { "epoch": 1.6609899483448354, "grad_norm": 4.9497389793396, "learning_rate": 8.445615081835353e-06, "loss": 0.3477, "step": 279430 }, { "epoch": 1.6610493904215038, "grad_norm": 4.577653884887695, "learning_rate": 8.445464720865769e-06, "loss": 0.3312, "step": 279440 }, { "epoch": 1.6611088324981722, "grad_norm": 4.4389328956604, "learning_rate": 8.445314353962684e-06, "loss": 0.2937, "step": 279450 }, { "epoch": 1.6611682745748406, "grad_norm": 5.373781204223633, "learning_rate": 8.445163981126356e-06, "loss": 0.323, "step": 279460 }, { "epoch": 1.661227716651509, "grad_norm": 4.7334065437316895, "learning_rate": 8.445013602357045e-06, "loss": 0.3436, "step": 279470 }, { "epoch": 1.6612871587281774, "grad_norm": 4.284688472747803, "learning_rate": 8.444863217655009e-06, "loss": 0.3592, "step": 279480 }, { "epoch": 1.6613466008048459, "grad_norm": 7.361234664916992, "learning_rate": 8.444712827020507e-06, "loss": 0.3348, "step": 279490 }, { "epoch": 1.661406042881514, "grad_norm": 5.773632526397705, "learning_rate": 8.4445624304538e-06, "loss": 0.3261, "step": 279500 }, { "epoch": 1.6614654849581825, "grad_norm": 5.940744400024414, "learning_rate": 8.444412027955145e-06, "loss": 0.3538, "step": 279510 }, { "epoch": 1.6615249270348509, "grad_norm": 4.639369010925293, "learning_rate": 8.4442616195248e-06, "loss": 0.3078, "step": 279520 }, { "epoch": 1.6615843691115193, "grad_norm": 3.959275245666504, "learning_rate": 8.444111205163028e-06, "loss": 0.2896, "step": 279530 }, { "epoch": 1.6616438111881877, "grad_norm": 4.76460075378418, "learning_rate": 8.443960784870085e-06, "loss": 0.3227, "step": 279540 }, { "epoch": 1.661703253264856, "grad_norm": 5.067911624908447, "learning_rate": 8.443810358646228e-06, "loss": 0.3373, "step": 279550 }, { "epoch": 1.6617626953415243, "grad_norm": 4.984614372253418, "learning_rate": 8.44365992649172e-06, "loss": 0.3133, "step": 279560 }, { "epoch": 1.6618221374181927, "grad_norm": 6.294325351715088, "learning_rate": 8.44350948840682e-06, "loss": 0.3315, "step": 279570 }, { "epoch": 1.6618815794948611, "grad_norm": 5.334068298339844, "learning_rate": 8.443359044391786e-06, "loss": 0.3452, "step": 279580 }, { "epoch": 1.6619410215715296, "grad_norm": 5.043936252593994, "learning_rate": 8.443208594446875e-06, "loss": 0.3211, "step": 279590 }, { "epoch": 1.662000463648198, "grad_norm": 5.621601104736328, "learning_rate": 8.443058138572348e-06, "loss": 0.4012, "step": 279600 }, { "epoch": 1.6620599057248664, "grad_norm": 5.832698822021484, "learning_rate": 8.442907676768465e-06, "loss": 0.3397, "step": 279610 }, { "epoch": 1.6621193478015348, "grad_norm": 4.78071928024292, "learning_rate": 8.442757209035486e-06, "loss": 0.3198, "step": 279620 }, { "epoch": 1.6621787898782032, "grad_norm": 5.073624610900879, "learning_rate": 8.442606735373665e-06, "loss": 0.3576, "step": 279630 }, { "epoch": 1.6622382319548716, "grad_norm": 4.597540378570557, "learning_rate": 8.442456255783266e-06, "loss": 0.3285, "step": 279640 }, { "epoch": 1.66229767403154, "grad_norm": 5.965753555297852, "learning_rate": 8.442305770264548e-06, "loss": 0.3651, "step": 279650 }, { "epoch": 1.6623571161082085, "grad_norm": 5.612433433532715, "learning_rate": 8.442155278817766e-06, "loss": 0.3634, "step": 279660 }, { "epoch": 1.6624165581848769, "grad_norm": 6.353189468383789, "learning_rate": 8.442004781443182e-06, "loss": 0.3325, "step": 279670 }, { "epoch": 1.6624760002615453, "grad_norm": 5.3443603515625, "learning_rate": 8.441854278141058e-06, "loss": 0.344, "step": 279680 }, { "epoch": 1.6625354423382135, "grad_norm": 4.06280517578125, "learning_rate": 8.441703768911648e-06, "loss": 0.338, "step": 279690 }, { "epoch": 1.662594884414882, "grad_norm": 7.0677947998046875, "learning_rate": 8.441553253755213e-06, "loss": 0.3589, "step": 279700 }, { "epoch": 1.6626543264915503, "grad_norm": 6.724340915679932, "learning_rate": 8.441402732672014e-06, "loss": 0.3282, "step": 279710 }, { "epoch": 1.6627137685682187, "grad_norm": 3.7018778324127197, "learning_rate": 8.441252205662309e-06, "loss": 0.3451, "step": 279720 }, { "epoch": 1.6627732106448871, "grad_norm": 7.102794647216797, "learning_rate": 8.441101672726356e-06, "loss": 0.3486, "step": 279730 }, { "epoch": 1.6628326527215553, "grad_norm": 5.120495796203613, "learning_rate": 8.440951133864416e-06, "loss": 0.3553, "step": 279740 }, { "epoch": 1.6628920947982238, "grad_norm": 5.398993492126465, "learning_rate": 8.440800589076748e-06, "loss": 0.3301, "step": 279750 }, { "epoch": 1.6629515368748922, "grad_norm": 5.234888076782227, "learning_rate": 8.44065003836361e-06, "loss": 0.3159, "step": 279760 }, { "epoch": 1.6630109789515606, "grad_norm": 4.78248929977417, "learning_rate": 8.440499481725261e-06, "loss": 0.3432, "step": 279770 }, { "epoch": 1.663070421028229, "grad_norm": 4.296267032623291, "learning_rate": 8.440348919161964e-06, "loss": 0.3514, "step": 279780 }, { "epoch": 1.6631298631048974, "grad_norm": 6.09812593460083, "learning_rate": 8.440198350673973e-06, "loss": 0.3358, "step": 279790 }, { "epoch": 1.6631893051815658, "grad_norm": 4.501604080200195, "learning_rate": 8.440047776261553e-06, "loss": 0.3634, "step": 279800 }, { "epoch": 1.6632487472582342, "grad_norm": 5.3405985832214355, "learning_rate": 8.439897195924957e-06, "loss": 0.3629, "step": 279810 }, { "epoch": 1.6633081893349027, "grad_norm": 6.819809436798096, "learning_rate": 8.43974660966445e-06, "loss": 0.3571, "step": 279820 }, { "epoch": 1.663367631411571, "grad_norm": 5.603182792663574, "learning_rate": 8.439596017480289e-06, "loss": 0.295, "step": 279830 }, { "epoch": 1.6634270734882395, "grad_norm": 5.320865154266357, "learning_rate": 8.439445419372731e-06, "loss": 0.292, "step": 279840 }, { "epoch": 1.663486515564908, "grad_norm": 4.631688594818115, "learning_rate": 8.439294815342039e-06, "loss": 0.3139, "step": 279850 }, { "epoch": 1.6635459576415763, "grad_norm": 7.2149553298950195, "learning_rate": 8.439144205388472e-06, "loss": 0.3364, "step": 279860 }, { "epoch": 1.6636053997182445, "grad_norm": 5.269172191619873, "learning_rate": 8.438993589512288e-06, "loss": 0.3794, "step": 279870 }, { "epoch": 1.663664841794913, "grad_norm": 4.2625508308410645, "learning_rate": 8.438842967713746e-06, "loss": 0.3188, "step": 279880 }, { "epoch": 1.6637242838715813, "grad_norm": 6.522876262664795, "learning_rate": 8.438692339993105e-06, "loss": 0.3394, "step": 279890 }, { "epoch": 1.6637837259482497, "grad_norm": 5.893592357635498, "learning_rate": 8.438541706350627e-06, "loss": 0.3264, "step": 279900 }, { "epoch": 1.6638431680249182, "grad_norm": 6.111698150634766, "learning_rate": 8.438391066786568e-06, "loss": 0.3318, "step": 279910 }, { "epoch": 1.6639026101015864, "grad_norm": 7.5079264640808105, "learning_rate": 8.438240421301192e-06, "loss": 0.3449, "step": 279920 }, { "epoch": 1.6639620521782548, "grad_norm": 4.488455295562744, "learning_rate": 8.438089769894754e-06, "loss": 0.3444, "step": 279930 }, { "epoch": 1.6640214942549232, "grad_norm": 6.048071384429932, "learning_rate": 8.437939112567515e-06, "loss": 0.3286, "step": 279940 }, { "epoch": 1.6640809363315916, "grad_norm": 5.925268650054932, "learning_rate": 8.437788449319736e-06, "loss": 0.3422, "step": 279950 }, { "epoch": 1.66414037840826, "grad_norm": 5.116119384765625, "learning_rate": 8.437637780151675e-06, "loss": 0.3147, "step": 279960 }, { "epoch": 1.6641998204849284, "grad_norm": 4.110199928283691, "learning_rate": 8.437487105063591e-06, "loss": 0.3014, "step": 279970 }, { "epoch": 1.6642592625615968, "grad_norm": 6.312500953674316, "learning_rate": 8.437336424055744e-06, "loss": 0.3444, "step": 279980 }, { "epoch": 1.6643187046382653, "grad_norm": 4.206779956817627, "learning_rate": 8.437185737128395e-06, "loss": 0.3233, "step": 279990 }, { "epoch": 1.6643781467149337, "grad_norm": 4.250734806060791, "learning_rate": 8.4370350442818e-06, "loss": 0.2955, "step": 280000 }, { "epoch": 1.664437588791602, "grad_norm": 4.224026203155518, "learning_rate": 8.436884345516222e-06, "loss": 0.3434, "step": 280010 }, { "epoch": 1.6644970308682705, "grad_norm": 4.6691575050354, "learning_rate": 8.436733640831918e-06, "loss": 0.3387, "step": 280020 }, { "epoch": 1.664556472944939, "grad_norm": 4.864597320556641, "learning_rate": 8.436582930229147e-06, "loss": 0.3302, "step": 280030 }, { "epoch": 1.6646159150216073, "grad_norm": 5.4759745597839355, "learning_rate": 8.436432213708173e-06, "loss": 0.3011, "step": 280040 }, { "epoch": 1.6646753570982757, "grad_norm": 4.7600274085998535, "learning_rate": 8.436281491269252e-06, "loss": 0.3127, "step": 280050 }, { "epoch": 1.664734799174944, "grad_norm": 4.7503981590271, "learning_rate": 8.436130762912642e-06, "loss": 0.2955, "step": 280060 }, { "epoch": 1.6647942412516124, "grad_norm": 4.164255619049072, "learning_rate": 8.435980028638608e-06, "loss": 0.3167, "step": 280070 }, { "epoch": 1.6648536833282808, "grad_norm": 4.908191680908203, "learning_rate": 8.435829288447406e-06, "loss": 0.3636, "step": 280080 }, { "epoch": 1.6649131254049492, "grad_norm": 4.586912631988525, "learning_rate": 8.435678542339295e-06, "loss": 0.3284, "step": 280090 }, { "epoch": 1.6649725674816174, "grad_norm": 5.411156177520752, "learning_rate": 8.435527790314535e-06, "loss": 0.3438, "step": 280100 }, { "epoch": 1.6650320095582858, "grad_norm": 5.337183475494385, "learning_rate": 8.435377032373387e-06, "loss": 0.3433, "step": 280110 }, { "epoch": 1.6650914516349542, "grad_norm": 5.017058849334717, "learning_rate": 8.435226268516112e-06, "loss": 0.3198, "step": 280120 }, { "epoch": 1.6651508937116226, "grad_norm": 5.478906631469727, "learning_rate": 8.435075498742964e-06, "loss": 0.3369, "step": 280130 }, { "epoch": 1.665210335788291, "grad_norm": 5.819338321685791, "learning_rate": 8.434924723054207e-06, "loss": 0.3445, "step": 280140 }, { "epoch": 1.6652697778649594, "grad_norm": 4.436709403991699, "learning_rate": 8.434773941450101e-06, "loss": 0.3422, "step": 280150 }, { "epoch": 1.6653292199416279, "grad_norm": 4.889200687408447, "learning_rate": 8.434623153930903e-06, "loss": 0.3279, "step": 280160 }, { "epoch": 1.6653886620182963, "grad_norm": 4.039671897888184, "learning_rate": 8.434472360496875e-06, "loss": 0.3245, "step": 280170 }, { "epoch": 1.6654481040949647, "grad_norm": 5.236122131347656, "learning_rate": 8.434321561148276e-06, "loss": 0.3427, "step": 280180 }, { "epoch": 1.665507546171633, "grad_norm": 5.355445384979248, "learning_rate": 8.434170755885366e-06, "loss": 0.3453, "step": 280190 }, { "epoch": 1.6655669882483015, "grad_norm": 6.024513244628906, "learning_rate": 8.434019944708402e-06, "loss": 0.3506, "step": 280200 }, { "epoch": 1.66562643032497, "grad_norm": 4.6126556396484375, "learning_rate": 8.433869127617649e-06, "loss": 0.3399, "step": 280210 }, { "epoch": 1.6656858724016383, "grad_norm": 6.20914363861084, "learning_rate": 8.433718304613361e-06, "loss": 0.3222, "step": 280220 }, { "epoch": 1.6657453144783068, "grad_norm": 5.319504737854004, "learning_rate": 8.433567475695802e-06, "loss": 0.2967, "step": 280230 }, { "epoch": 1.665804756554975, "grad_norm": 5.292912006378174, "learning_rate": 8.433416640865228e-06, "loss": 0.3367, "step": 280240 }, { "epoch": 1.6658641986316434, "grad_norm": 5.255349159240723, "learning_rate": 8.433265800121903e-06, "loss": 0.2986, "step": 280250 }, { "epoch": 1.6659236407083118, "grad_norm": 4.513771057128906, "learning_rate": 8.433114953466083e-06, "loss": 0.3524, "step": 280260 }, { "epoch": 1.6659830827849802, "grad_norm": 5.973965644836426, "learning_rate": 8.432964100898031e-06, "loss": 0.3613, "step": 280270 }, { "epoch": 1.6660425248616486, "grad_norm": 3.7939212322235107, "learning_rate": 8.432813242418006e-06, "loss": 0.3452, "step": 280280 }, { "epoch": 1.6661019669383168, "grad_norm": 4.834338665008545, "learning_rate": 8.432662378026263e-06, "loss": 0.3111, "step": 280290 }, { "epoch": 1.6661614090149852, "grad_norm": 4.9202728271484375, "learning_rate": 8.43251150772307e-06, "loss": 0.327, "step": 280300 }, { "epoch": 1.6662208510916536, "grad_norm": 4.040284156799316, "learning_rate": 8.43236063150868e-06, "loss": 0.329, "step": 280310 }, { "epoch": 1.666280293168322, "grad_norm": 5.270691871643066, "learning_rate": 8.432209749383357e-06, "loss": 0.3357, "step": 280320 }, { "epoch": 1.6663397352449905, "grad_norm": 5.919773101806641, "learning_rate": 8.43205886134736e-06, "loss": 0.3199, "step": 280330 }, { "epoch": 1.6663991773216589, "grad_norm": 4.231298923492432, "learning_rate": 8.431907967400946e-06, "loss": 0.3091, "step": 280340 }, { "epoch": 1.6664586193983273, "grad_norm": 4.401744365692139, "learning_rate": 8.431757067544378e-06, "loss": 0.3179, "step": 280350 }, { "epoch": 1.6665180614749957, "grad_norm": 8.343406677246094, "learning_rate": 8.431606161777915e-06, "loss": 0.344, "step": 280360 }, { "epoch": 1.6665775035516641, "grad_norm": 6.373902320861816, "learning_rate": 8.431455250101816e-06, "loss": 0.3574, "step": 280370 }, { "epoch": 1.6666369456283325, "grad_norm": 4.5829758644104, "learning_rate": 8.431304332516342e-06, "loss": 0.3108, "step": 280380 }, { "epoch": 1.666696387705001, "grad_norm": 4.528542518615723, "learning_rate": 8.431153409021752e-06, "loss": 0.3333, "step": 280390 }, { "epoch": 1.6667558297816694, "grad_norm": 6.246206760406494, "learning_rate": 8.431002479618308e-06, "loss": 0.3315, "step": 280400 }, { "epoch": 1.6668152718583378, "grad_norm": 5.617865085601807, "learning_rate": 8.430851544306267e-06, "loss": 0.3756, "step": 280410 }, { "epoch": 1.6668747139350062, "grad_norm": 6.714474678039551, "learning_rate": 8.43070060308589e-06, "loss": 0.3803, "step": 280420 }, { "epoch": 1.6669341560116744, "grad_norm": 5.1256914138793945, "learning_rate": 8.430549655957438e-06, "loss": 0.3367, "step": 280430 }, { "epoch": 1.6669935980883428, "grad_norm": 5.3139753341674805, "learning_rate": 8.430398702921172e-06, "loss": 0.3153, "step": 280440 }, { "epoch": 1.6670530401650112, "grad_norm": 4.928883075714111, "learning_rate": 8.430247743977347e-06, "loss": 0.3107, "step": 280450 }, { "epoch": 1.6671124822416796, "grad_norm": 4.488643646240234, "learning_rate": 8.430096779126228e-06, "loss": 0.369, "step": 280460 }, { "epoch": 1.6671719243183478, "grad_norm": 3.766430616378784, "learning_rate": 8.429945808368072e-06, "loss": 0.3159, "step": 280470 }, { "epoch": 1.6672313663950162, "grad_norm": 5.016350746154785, "learning_rate": 8.42979483170314e-06, "loss": 0.3316, "step": 280480 }, { "epoch": 1.6672908084716846, "grad_norm": 5.387765884399414, "learning_rate": 8.429643849131692e-06, "loss": 0.3321, "step": 280490 }, { "epoch": 1.667350250548353, "grad_norm": 5.154737949371338, "learning_rate": 8.42949286065399e-06, "loss": 0.3161, "step": 280500 }, { "epoch": 1.6674096926250215, "grad_norm": 5.559878349304199, "learning_rate": 8.42934186627029e-06, "loss": 0.344, "step": 280510 }, { "epoch": 1.66746913470169, "grad_norm": 4.955050468444824, "learning_rate": 8.429190865980854e-06, "loss": 0.307, "step": 280520 }, { "epoch": 1.6675285767783583, "grad_norm": 5.226240634918213, "learning_rate": 8.429039859785943e-06, "loss": 0.32, "step": 280530 }, { "epoch": 1.6675880188550267, "grad_norm": 4.055650234222412, "learning_rate": 8.428888847685817e-06, "loss": 0.292, "step": 280540 }, { "epoch": 1.6676474609316951, "grad_norm": 5.879397869110107, "learning_rate": 8.428737829680734e-06, "loss": 0.3359, "step": 280550 }, { "epoch": 1.6677069030083636, "grad_norm": 5.599837779998779, "learning_rate": 8.428586805770956e-06, "loss": 0.3367, "step": 280560 }, { "epoch": 1.667766345085032, "grad_norm": 4.716720104217529, "learning_rate": 8.428435775956742e-06, "loss": 0.3171, "step": 280570 }, { "epoch": 1.6678257871617004, "grad_norm": 4.175112247467041, "learning_rate": 8.428284740238352e-06, "loss": 0.3251, "step": 280580 }, { "epoch": 1.6678852292383688, "grad_norm": 4.726548671722412, "learning_rate": 8.428133698616048e-06, "loss": 0.3362, "step": 280590 }, { "epoch": 1.6679446713150372, "grad_norm": 8.016200065612793, "learning_rate": 8.427982651090088e-06, "loss": 0.3267, "step": 280600 }, { "epoch": 1.6680041133917054, "grad_norm": 7.628994941711426, "learning_rate": 8.427831597660734e-06, "loss": 0.3203, "step": 280610 }, { "epoch": 1.6680635554683738, "grad_norm": 4.830770015716553, "learning_rate": 8.427680538328241e-06, "loss": 0.2912, "step": 280620 }, { "epoch": 1.6681229975450422, "grad_norm": 3.9423747062683105, "learning_rate": 8.427529473092878e-06, "loss": 0.3421, "step": 280630 }, { "epoch": 1.6681824396217106, "grad_norm": 5.900148391723633, "learning_rate": 8.427378401954899e-06, "loss": 0.3295, "step": 280640 }, { "epoch": 1.668241881698379, "grad_norm": 5.158711910247803, "learning_rate": 8.427227324914564e-06, "loss": 0.3143, "step": 280650 }, { "epoch": 1.6683013237750473, "grad_norm": 4.746365547180176, "learning_rate": 8.427076241972134e-06, "loss": 0.3381, "step": 280660 }, { "epoch": 1.6683607658517157, "grad_norm": 3.614516496658325, "learning_rate": 8.426925153127872e-06, "loss": 0.3169, "step": 280670 }, { "epoch": 1.668420207928384, "grad_norm": 5.207210540771484, "learning_rate": 8.426774058382036e-06, "loss": 0.35, "step": 280680 }, { "epoch": 1.6684796500050525, "grad_norm": 6.775511741638184, "learning_rate": 8.426622957734885e-06, "loss": 0.3175, "step": 280690 }, { "epoch": 1.668539092081721, "grad_norm": 7.247359752655029, "learning_rate": 8.42647185118668e-06, "loss": 0.3466, "step": 280700 }, { "epoch": 1.6685985341583893, "grad_norm": 6.262369155883789, "learning_rate": 8.426320738737683e-06, "loss": 0.3479, "step": 280710 }, { "epoch": 1.6686579762350577, "grad_norm": 5.438034534454346, "learning_rate": 8.426169620388153e-06, "loss": 0.3233, "step": 280720 }, { "epoch": 1.6687174183117262, "grad_norm": 4.327707767486572, "learning_rate": 8.426018496138349e-06, "loss": 0.3388, "step": 280730 }, { "epoch": 1.6687768603883946, "grad_norm": 4.160877704620361, "learning_rate": 8.425867365988533e-06, "loss": 0.3014, "step": 280740 }, { "epoch": 1.668836302465063, "grad_norm": 5.095694541931152, "learning_rate": 8.425716229938966e-06, "loss": 0.3134, "step": 280750 }, { "epoch": 1.6688957445417314, "grad_norm": 5.455577373504639, "learning_rate": 8.425565087989905e-06, "loss": 0.3389, "step": 280760 }, { "epoch": 1.6689551866183998, "grad_norm": 4.273160934448242, "learning_rate": 8.425413940141612e-06, "loss": 0.318, "step": 280770 }, { "epoch": 1.6690146286950682, "grad_norm": 5.557081699371338, "learning_rate": 8.425262786394346e-06, "loss": 0.3302, "step": 280780 }, { "epoch": 1.6690740707717366, "grad_norm": 5.5739665031433105, "learning_rate": 8.425111626748372e-06, "loss": 0.3381, "step": 280790 }, { "epoch": 1.6691335128484048, "grad_norm": 4.467101097106934, "learning_rate": 8.424960461203945e-06, "loss": 0.3395, "step": 280800 }, { "epoch": 1.6691929549250732, "grad_norm": 4.927382469177246, "learning_rate": 8.424809289761329e-06, "loss": 0.3343, "step": 280810 }, { "epoch": 1.6692523970017417, "grad_norm": 4.815666198730469, "learning_rate": 8.424658112420782e-06, "loss": 0.3414, "step": 280820 }, { "epoch": 1.66931183907841, "grad_norm": 6.165205955505371, "learning_rate": 8.424506929182565e-06, "loss": 0.3223, "step": 280830 }, { "epoch": 1.6693712811550783, "grad_norm": 4.520242691040039, "learning_rate": 8.424355740046938e-06, "loss": 0.3242, "step": 280840 }, { "epoch": 1.6694307232317467, "grad_norm": 4.7689995765686035, "learning_rate": 8.424204545014164e-06, "loss": 0.3263, "step": 280850 }, { "epoch": 1.669490165308415, "grad_norm": 4.664782524108887, "learning_rate": 8.424053344084498e-06, "loss": 0.3355, "step": 280860 }, { "epoch": 1.6695496073850835, "grad_norm": 4.694634437561035, "learning_rate": 8.423902137258206e-06, "loss": 0.331, "step": 280870 }, { "epoch": 1.669609049461752, "grad_norm": 4.97363805770874, "learning_rate": 8.423750924535546e-06, "loss": 0.3178, "step": 280880 }, { "epoch": 1.6696684915384203, "grad_norm": 4.798237323760986, "learning_rate": 8.423599705916776e-06, "loss": 0.3579, "step": 280890 }, { "epoch": 1.6697279336150888, "grad_norm": 5.00091552734375, "learning_rate": 8.42344848140216e-06, "loss": 0.3419, "step": 280900 }, { "epoch": 1.6697873756917572, "grad_norm": 4.409764766693115, "learning_rate": 8.423297250991957e-06, "loss": 0.3327, "step": 280910 }, { "epoch": 1.6698468177684256, "grad_norm": 6.481643199920654, "learning_rate": 8.42314601468643e-06, "loss": 0.3278, "step": 280920 }, { "epoch": 1.669906259845094, "grad_norm": 6.515028953552246, "learning_rate": 8.422994772485836e-06, "loss": 0.3271, "step": 280930 }, { "epoch": 1.6699657019217624, "grad_norm": 4.288937091827393, "learning_rate": 8.422843524390435e-06, "loss": 0.3222, "step": 280940 }, { "epoch": 1.6700251439984308, "grad_norm": 5.7375311851501465, "learning_rate": 8.42269227040049e-06, "loss": 0.3413, "step": 280950 }, { "epoch": 1.6700845860750992, "grad_norm": 4.794025897979736, "learning_rate": 8.422541010516261e-06, "loss": 0.319, "step": 280960 }, { "epoch": 1.6701440281517677, "grad_norm": 4.517731189727783, "learning_rate": 8.422389744738007e-06, "loss": 0.3377, "step": 280970 }, { "epoch": 1.6702034702284358, "grad_norm": 5.47487211227417, "learning_rate": 8.422238473065991e-06, "loss": 0.3064, "step": 280980 }, { "epoch": 1.6702629123051043, "grad_norm": 4.651556015014648, "learning_rate": 8.42208719550047e-06, "loss": 0.3139, "step": 280990 }, { "epoch": 1.6703223543817727, "grad_norm": 3.366089344024658, "learning_rate": 8.421935912041708e-06, "loss": 0.3019, "step": 281000 }, { "epoch": 1.670381796458441, "grad_norm": 5.736173152923584, "learning_rate": 8.421784622689963e-06, "loss": 0.3498, "step": 281010 }, { "epoch": 1.6704412385351095, "grad_norm": 4.6065545082092285, "learning_rate": 8.421633327445498e-06, "loss": 0.332, "step": 281020 }, { "epoch": 1.6705006806117777, "grad_norm": 4.786386489868164, "learning_rate": 8.421482026308572e-06, "loss": 0.3375, "step": 281030 }, { "epoch": 1.6705601226884461, "grad_norm": 3.8939061164855957, "learning_rate": 8.421330719279444e-06, "loss": 0.3369, "step": 281040 }, { "epoch": 1.6706195647651145, "grad_norm": 5.242977142333984, "learning_rate": 8.421179406358379e-06, "loss": 0.3442, "step": 281050 }, { "epoch": 1.670679006841783, "grad_norm": 5.004267692565918, "learning_rate": 8.421028087545633e-06, "loss": 0.2932, "step": 281060 }, { "epoch": 1.6707384489184514, "grad_norm": 3.8153297901153564, "learning_rate": 8.420876762841467e-06, "loss": 0.3672, "step": 281070 }, { "epoch": 1.6707978909951198, "grad_norm": 5.8802666664123535, "learning_rate": 8.420725432246147e-06, "loss": 0.3707, "step": 281080 }, { "epoch": 1.6708573330717882, "grad_norm": 4.372486591339111, "learning_rate": 8.420574095759925e-06, "loss": 0.332, "step": 281090 }, { "epoch": 1.6709167751484566, "grad_norm": 5.376892566680908, "learning_rate": 8.42042275338307e-06, "loss": 0.3423, "step": 281100 }, { "epoch": 1.670976217225125, "grad_norm": 5.116206169128418, "learning_rate": 8.420271405115839e-06, "loss": 0.3214, "step": 281110 }, { "epoch": 1.6710356593017934, "grad_norm": 5.970006465911865, "learning_rate": 8.42012005095849e-06, "loss": 0.3276, "step": 281120 }, { "epoch": 1.6710951013784618, "grad_norm": 7.59724235534668, "learning_rate": 8.419968690911287e-06, "loss": 0.3202, "step": 281130 }, { "epoch": 1.6711545434551303, "grad_norm": 5.100957870483398, "learning_rate": 8.41981732497449e-06, "loss": 0.3192, "step": 281140 }, { "epoch": 1.6712139855317987, "grad_norm": 3.828604221343994, "learning_rate": 8.41966595314836e-06, "loss": 0.2898, "step": 281150 }, { "epoch": 1.671273427608467, "grad_norm": 4.424616813659668, "learning_rate": 8.419514575433157e-06, "loss": 0.357, "step": 281160 }, { "epoch": 1.6713328696851353, "grad_norm": 6.287264823913574, "learning_rate": 8.419363191829142e-06, "loss": 0.3462, "step": 281170 }, { "epoch": 1.6713923117618037, "grad_norm": 5.552585124969482, "learning_rate": 8.419211802336576e-06, "loss": 0.3507, "step": 281180 }, { "epoch": 1.671451753838472, "grad_norm": 3.7769217491149902, "learning_rate": 8.419060406955718e-06, "loss": 0.3311, "step": 281190 }, { "epoch": 1.6715111959151405, "grad_norm": 5.236350059509277, "learning_rate": 8.41890900568683e-06, "loss": 0.3282, "step": 281200 }, { "epoch": 1.6715706379918087, "grad_norm": 5.370683193206787, "learning_rate": 8.418757598530174e-06, "loss": 0.3386, "step": 281210 }, { "epoch": 1.6716300800684771, "grad_norm": 5.0308709144592285, "learning_rate": 8.41860618548601e-06, "loss": 0.3513, "step": 281220 }, { "epoch": 1.6716895221451455, "grad_norm": 6.90207052230835, "learning_rate": 8.418454766554595e-06, "loss": 0.3346, "step": 281230 }, { "epoch": 1.671748964221814, "grad_norm": 5.735838890075684, "learning_rate": 8.418303341736197e-06, "loss": 0.3372, "step": 281240 }, { "epoch": 1.6718084062984824, "grad_norm": 4.321957588195801, "learning_rate": 8.41815191103107e-06, "loss": 0.3185, "step": 281250 }, { "epoch": 1.6718678483751508, "grad_norm": 6.680556774139404, "learning_rate": 8.418000474439477e-06, "loss": 0.3718, "step": 281260 }, { "epoch": 1.6719272904518192, "grad_norm": 4.304046630859375, "learning_rate": 8.417849031961682e-06, "loss": 0.3355, "step": 281270 }, { "epoch": 1.6719867325284876, "grad_norm": 4.063101768493652, "learning_rate": 8.417697583597943e-06, "loss": 0.339, "step": 281280 }, { "epoch": 1.672046174605156, "grad_norm": 4.59902811050415, "learning_rate": 8.417546129348519e-06, "loss": 0.3628, "step": 281290 }, { "epoch": 1.6721056166818244, "grad_norm": 7.474594593048096, "learning_rate": 8.417394669213674e-06, "loss": 0.3391, "step": 281300 }, { "epoch": 1.6721650587584929, "grad_norm": 4.274471282958984, "learning_rate": 8.417243203193669e-06, "loss": 0.3279, "step": 281310 }, { "epoch": 1.6722245008351613, "grad_norm": 5.647670745849609, "learning_rate": 8.417091731288761e-06, "loss": 0.3244, "step": 281320 }, { "epoch": 1.6722839429118297, "grad_norm": 4.050127029418945, "learning_rate": 8.416940253499214e-06, "loss": 0.2849, "step": 281330 }, { "epoch": 1.672343384988498, "grad_norm": 4.809049129486084, "learning_rate": 8.416788769825289e-06, "loss": 0.3364, "step": 281340 }, { "epoch": 1.6724028270651663, "grad_norm": 7.014402389526367, "learning_rate": 8.416637280267245e-06, "loss": 0.3178, "step": 281350 }, { "epoch": 1.6724622691418347, "grad_norm": 3.2504777908325195, "learning_rate": 8.416485784825344e-06, "loss": 0.322, "step": 281360 }, { "epoch": 1.6725217112185031, "grad_norm": 5.068276882171631, "learning_rate": 8.416334283499848e-06, "loss": 0.3183, "step": 281370 }, { "epoch": 1.6725811532951715, "grad_norm": 4.435726165771484, "learning_rate": 8.416182776291015e-06, "loss": 0.3552, "step": 281380 }, { "epoch": 1.67264059537184, "grad_norm": 6.170088291168213, "learning_rate": 8.416031263199109e-06, "loss": 0.365, "step": 281390 }, { "epoch": 1.6727000374485081, "grad_norm": 4.095209121704102, "learning_rate": 8.415879744224389e-06, "loss": 0.3142, "step": 281400 }, { "epoch": 1.6727594795251766, "grad_norm": 5.4651899337768555, "learning_rate": 8.415728219367117e-06, "loss": 0.3445, "step": 281410 }, { "epoch": 1.672818921601845, "grad_norm": 7.020043849945068, "learning_rate": 8.415576688627553e-06, "loss": 0.2969, "step": 281420 }, { "epoch": 1.6728783636785134, "grad_norm": 5.780528545379639, "learning_rate": 8.415425152005959e-06, "loss": 0.2977, "step": 281430 }, { "epoch": 1.6729378057551818, "grad_norm": 5.025506019592285, "learning_rate": 8.415273609502595e-06, "loss": 0.3551, "step": 281440 }, { "epoch": 1.6729972478318502, "grad_norm": 5.947285175323486, "learning_rate": 8.415122061117722e-06, "loss": 0.3402, "step": 281450 }, { "epoch": 1.6730566899085186, "grad_norm": 4.774015426635742, "learning_rate": 8.414970506851601e-06, "loss": 0.3387, "step": 281460 }, { "epoch": 1.673116131985187, "grad_norm": 5.661704063415527, "learning_rate": 8.414818946704494e-06, "loss": 0.3633, "step": 281470 }, { "epoch": 1.6731755740618555, "grad_norm": 4.3747172355651855, "learning_rate": 8.414667380676662e-06, "loss": 0.2946, "step": 281480 }, { "epoch": 1.6732350161385239, "grad_norm": 4.379235744476318, "learning_rate": 8.414515808768364e-06, "loss": 0.3361, "step": 281490 }, { "epoch": 1.6732944582151923, "grad_norm": 4.751852512359619, "learning_rate": 8.414364230979864e-06, "loss": 0.3479, "step": 281500 }, { "epoch": 1.6733539002918607, "grad_norm": 5.150888442993164, "learning_rate": 8.414212647311419e-06, "loss": 0.3419, "step": 281510 }, { "epoch": 1.6734133423685291, "grad_norm": 5.12490701675415, "learning_rate": 8.414061057763295e-06, "loss": 0.3235, "step": 281520 }, { "epoch": 1.6734727844451975, "grad_norm": 4.580554962158203, "learning_rate": 8.413909462335747e-06, "loss": 0.362, "step": 281530 }, { "epoch": 1.6735322265218657, "grad_norm": 4.968012809753418, "learning_rate": 8.413757861029043e-06, "loss": 0.3474, "step": 281540 }, { "epoch": 1.6735916685985341, "grad_norm": 6.336874008178711, "learning_rate": 8.41360625384344e-06, "loss": 0.3524, "step": 281550 }, { "epoch": 1.6736511106752026, "grad_norm": 4.090762615203857, "learning_rate": 8.413454640779199e-06, "loss": 0.3561, "step": 281560 }, { "epoch": 1.673710552751871, "grad_norm": 6.476444244384766, "learning_rate": 8.41330302183658e-06, "loss": 0.3232, "step": 281570 }, { "epoch": 1.6737699948285392, "grad_norm": 6.909219264984131, "learning_rate": 8.413151397015849e-06, "loss": 0.343, "step": 281580 }, { "epoch": 1.6738294369052076, "grad_norm": 5.965011119842529, "learning_rate": 8.412999766317263e-06, "loss": 0.3209, "step": 281590 }, { "epoch": 1.673888878981876, "grad_norm": 5.240588665008545, "learning_rate": 8.412848129741085e-06, "loss": 0.3292, "step": 281600 }, { "epoch": 1.6739483210585444, "grad_norm": 5.1745924949646, "learning_rate": 8.412696487287574e-06, "loss": 0.3251, "step": 281610 }, { "epoch": 1.6740077631352128, "grad_norm": 6.042333126068115, "learning_rate": 8.412544838956993e-06, "loss": 0.3493, "step": 281620 }, { "epoch": 1.6740672052118812, "grad_norm": 4.841569423675537, "learning_rate": 8.412393184749604e-06, "loss": 0.3341, "step": 281630 }, { "epoch": 1.6741266472885497, "grad_norm": 5.454197883605957, "learning_rate": 8.412241524665663e-06, "loss": 0.3221, "step": 281640 }, { "epoch": 1.674186089365218, "grad_norm": 5.231579780578613, "learning_rate": 8.412089858705438e-06, "loss": 0.3641, "step": 281650 }, { "epoch": 1.6742455314418865, "grad_norm": 5.053788661956787, "learning_rate": 8.411938186869186e-06, "loss": 0.3127, "step": 281660 }, { "epoch": 1.674304973518555, "grad_norm": 5.913790702819824, "learning_rate": 8.41178650915717e-06, "loss": 0.3646, "step": 281670 }, { "epoch": 1.6743644155952233, "grad_norm": 4.599883556365967, "learning_rate": 8.41163482556965e-06, "loss": 0.3412, "step": 281680 }, { "epoch": 1.6744238576718917, "grad_norm": 5.472611427307129, "learning_rate": 8.411483136106888e-06, "loss": 0.345, "step": 281690 }, { "epoch": 1.6744832997485601, "grad_norm": 5.246592998504639, "learning_rate": 8.411331440769146e-06, "loss": 0.3045, "step": 281700 }, { "epoch": 1.6745427418252286, "grad_norm": 6.287829875946045, "learning_rate": 8.411179739556683e-06, "loss": 0.3055, "step": 281710 }, { "epoch": 1.6746021839018967, "grad_norm": 4.614284038543701, "learning_rate": 8.41102803246976e-06, "loss": 0.3366, "step": 281720 }, { "epoch": 1.6746616259785652, "grad_norm": 5.255568981170654, "learning_rate": 8.410876319508643e-06, "loss": 0.3434, "step": 281730 }, { "epoch": 1.6747210680552336, "grad_norm": 4.725086212158203, "learning_rate": 8.410724600673587e-06, "loss": 0.3087, "step": 281740 }, { "epoch": 1.674780510131902, "grad_norm": 5.6338934898376465, "learning_rate": 8.410572875964859e-06, "loss": 0.3147, "step": 281750 }, { "epoch": 1.6748399522085704, "grad_norm": 5.279738426208496, "learning_rate": 8.410421145382717e-06, "loss": 0.3493, "step": 281760 }, { "epoch": 1.6748993942852386, "grad_norm": 5.946422100067139, "learning_rate": 8.41026940892742e-06, "loss": 0.3457, "step": 281770 }, { "epoch": 1.674958836361907, "grad_norm": 5.821944236755371, "learning_rate": 8.410117666599237e-06, "loss": 0.3418, "step": 281780 }, { "epoch": 1.6750182784385754, "grad_norm": 5.291932106018066, "learning_rate": 8.409965918398419e-06, "loss": 0.3514, "step": 281790 }, { "epoch": 1.6750777205152438, "grad_norm": 4.9403276443481445, "learning_rate": 8.409814164325236e-06, "loss": 0.3346, "step": 281800 }, { "epoch": 1.6751371625919123, "grad_norm": 4.048808574676514, "learning_rate": 8.409662404379946e-06, "loss": 0.3191, "step": 281810 }, { "epoch": 1.6751966046685807, "grad_norm": 6.664565563201904, "learning_rate": 8.40951063856281e-06, "loss": 0.3366, "step": 281820 }, { "epoch": 1.675256046745249, "grad_norm": 4.340482711791992, "learning_rate": 8.40935886687409e-06, "loss": 0.3096, "step": 281830 }, { "epoch": 1.6753154888219175, "grad_norm": 4.716066837310791, "learning_rate": 8.409207089314049e-06, "loss": 0.3234, "step": 281840 }, { "epoch": 1.675374930898586, "grad_norm": 3.35453462600708, "learning_rate": 8.409055305882944e-06, "loss": 0.3023, "step": 281850 }, { "epoch": 1.6754343729752543, "grad_norm": 5.725344181060791, "learning_rate": 8.40890351658104e-06, "loss": 0.3577, "step": 281860 }, { "epoch": 1.6754938150519227, "grad_norm": 4.8720173835754395, "learning_rate": 8.408751721408597e-06, "loss": 0.281, "step": 281870 }, { "epoch": 1.6755532571285912, "grad_norm": 5.063111782073975, "learning_rate": 8.408599920365878e-06, "loss": 0.3313, "step": 281880 }, { "epoch": 1.6756126992052596, "grad_norm": 6.914234638214111, "learning_rate": 8.408448113453143e-06, "loss": 0.3407, "step": 281890 }, { "epoch": 1.675672141281928, "grad_norm": 6.682929992675781, "learning_rate": 8.408296300670651e-06, "loss": 0.3603, "step": 281900 }, { "epoch": 1.6757315833585962, "grad_norm": 4.4432783126831055, "learning_rate": 8.40814448201867e-06, "loss": 0.3159, "step": 281910 }, { "epoch": 1.6757910254352646, "grad_norm": 5.480711460113525, "learning_rate": 8.407992657497455e-06, "loss": 0.3275, "step": 281920 }, { "epoch": 1.675850467511933, "grad_norm": 4.793411731719971, "learning_rate": 8.40784082710727e-06, "loss": 0.3302, "step": 281930 }, { "epoch": 1.6759099095886014, "grad_norm": 4.995768070220947, "learning_rate": 8.407688990848379e-06, "loss": 0.3067, "step": 281940 }, { "epoch": 1.6759693516652696, "grad_norm": 4.346560955047607, "learning_rate": 8.407537148721039e-06, "loss": 0.3116, "step": 281950 }, { "epoch": 1.676028793741938, "grad_norm": 5.106812953948975, "learning_rate": 8.407385300725513e-06, "loss": 0.3323, "step": 281960 }, { "epoch": 1.6760882358186064, "grad_norm": 4.355680465698242, "learning_rate": 8.407233446862064e-06, "loss": 0.3231, "step": 281970 }, { "epoch": 1.6761476778952749, "grad_norm": 5.038439750671387, "learning_rate": 8.407081587130953e-06, "loss": 0.3113, "step": 281980 }, { "epoch": 1.6762071199719433, "grad_norm": 3.457977533340454, "learning_rate": 8.40692972153244e-06, "loss": 0.342, "step": 281990 }, { "epoch": 1.6762665620486117, "grad_norm": 5.439571857452393, "learning_rate": 8.406777850066785e-06, "loss": 0.3268, "step": 282000 }, { "epoch": 1.67632600412528, "grad_norm": 4.833072662353516, "learning_rate": 8.406625972734256e-06, "loss": 0.3303, "step": 282010 }, { "epoch": 1.6763854462019485, "grad_norm": 5.464732646942139, "learning_rate": 8.406474089535108e-06, "loss": 0.3447, "step": 282020 }, { "epoch": 1.676444888278617, "grad_norm": 5.306019306182861, "learning_rate": 8.406322200469608e-06, "loss": 0.3397, "step": 282030 }, { "epoch": 1.6765043303552853, "grad_norm": 5.866925239562988, "learning_rate": 8.406170305538014e-06, "loss": 0.3086, "step": 282040 }, { "epoch": 1.6765637724319538, "grad_norm": 4.285838603973389, "learning_rate": 8.406018404740585e-06, "loss": 0.3622, "step": 282050 }, { "epoch": 1.6766232145086222, "grad_norm": 5.81388521194458, "learning_rate": 8.40586649807759e-06, "loss": 0.3455, "step": 282060 }, { "epoch": 1.6766826565852906, "grad_norm": 4.071467876434326, "learning_rate": 8.405714585549285e-06, "loss": 0.3152, "step": 282070 }, { "epoch": 1.676742098661959, "grad_norm": 4.635529041290283, "learning_rate": 8.405562667155932e-06, "loss": 0.3339, "step": 282080 }, { "epoch": 1.6768015407386272, "grad_norm": 5.11970329284668, "learning_rate": 8.405410742897795e-06, "loss": 0.318, "step": 282090 }, { "epoch": 1.6768609828152956, "grad_norm": 4.702212810516357, "learning_rate": 8.405258812775134e-06, "loss": 0.3333, "step": 282100 }, { "epoch": 1.676920424891964, "grad_norm": 6.116694927215576, "learning_rate": 8.40510687678821e-06, "loss": 0.3427, "step": 282110 }, { "epoch": 1.6769798669686324, "grad_norm": 5.252892017364502, "learning_rate": 8.404954934937287e-06, "loss": 0.3865, "step": 282120 }, { "epoch": 1.6770393090453009, "grad_norm": 4.504489898681641, "learning_rate": 8.404802987222626e-06, "loss": 0.3445, "step": 282130 }, { "epoch": 1.677098751121969, "grad_norm": 3.737680673599243, "learning_rate": 8.404651033644486e-06, "loss": 0.3321, "step": 282140 }, { "epoch": 1.6771581931986375, "grad_norm": 5.90274715423584, "learning_rate": 8.404499074203132e-06, "loss": 0.3621, "step": 282150 }, { "epoch": 1.6772176352753059, "grad_norm": 5.49809455871582, "learning_rate": 8.404347108898825e-06, "loss": 0.3396, "step": 282160 }, { "epoch": 1.6772770773519743, "grad_norm": 4.57144021987915, "learning_rate": 8.404195137731826e-06, "loss": 0.2935, "step": 282170 }, { "epoch": 1.6773365194286427, "grad_norm": 5.181797504425049, "learning_rate": 8.404043160702395e-06, "loss": 0.316, "step": 282180 }, { "epoch": 1.6773959615053111, "grad_norm": 6.7986979484558105, "learning_rate": 8.403891177810798e-06, "loss": 0.3466, "step": 282190 }, { "epoch": 1.6774554035819795, "grad_norm": 5.136913299560547, "learning_rate": 8.403739189057292e-06, "loss": 0.3148, "step": 282200 }, { "epoch": 1.677514845658648, "grad_norm": 5.313693046569824, "learning_rate": 8.40358719444214e-06, "loss": 0.3341, "step": 282210 }, { "epoch": 1.6775742877353164, "grad_norm": 4.936261177062988, "learning_rate": 8.403435193965607e-06, "loss": 0.2883, "step": 282220 }, { "epoch": 1.6776337298119848, "grad_norm": 5.053851127624512, "learning_rate": 8.403283187627952e-06, "loss": 0.3487, "step": 282230 }, { "epoch": 1.6776931718886532, "grad_norm": 4.069618225097656, "learning_rate": 8.403131175429438e-06, "loss": 0.2988, "step": 282240 }, { "epoch": 1.6777526139653216, "grad_norm": 6.16703987121582, "learning_rate": 8.402979157370326e-06, "loss": 0.3681, "step": 282250 }, { "epoch": 1.67781205604199, "grad_norm": 5.045318126678467, "learning_rate": 8.402827133450877e-06, "loss": 0.349, "step": 282260 }, { "epoch": 1.6778714981186584, "grad_norm": 4.737496376037598, "learning_rate": 8.402675103671352e-06, "loss": 0.3184, "step": 282270 }, { "epoch": 1.6779309401953266, "grad_norm": 5.495019435882568, "learning_rate": 8.402523068032019e-06, "loss": 0.3036, "step": 282280 }, { "epoch": 1.677990382271995, "grad_norm": 5.570125102996826, "learning_rate": 8.402371026533131e-06, "loss": 0.36, "step": 282290 }, { "epoch": 1.6780498243486635, "grad_norm": 4.247960090637207, "learning_rate": 8.402218979174956e-06, "loss": 0.3171, "step": 282300 }, { "epoch": 1.6781092664253319, "grad_norm": 5.1909871101379395, "learning_rate": 8.402066925957753e-06, "loss": 0.3092, "step": 282310 }, { "epoch": 1.678168708502, "grad_norm": 4.790701866149902, "learning_rate": 8.401914866881787e-06, "loss": 0.3333, "step": 282320 }, { "epoch": 1.6782281505786685, "grad_norm": 5.053513526916504, "learning_rate": 8.401762801947316e-06, "loss": 0.3096, "step": 282330 }, { "epoch": 1.678287592655337, "grad_norm": 2.9726152420043945, "learning_rate": 8.401610731154603e-06, "loss": 0.3181, "step": 282340 }, { "epoch": 1.6783470347320053, "grad_norm": 4.62991189956665, "learning_rate": 8.401458654503911e-06, "loss": 0.3423, "step": 282350 }, { "epoch": 1.6784064768086737, "grad_norm": 6.933771133422852, "learning_rate": 8.401306571995501e-06, "loss": 0.3211, "step": 282360 }, { "epoch": 1.6784659188853421, "grad_norm": 7.009036064147949, "learning_rate": 8.401154483629637e-06, "loss": 0.3142, "step": 282370 }, { "epoch": 1.6785253609620105, "grad_norm": 3.8985564708709717, "learning_rate": 8.401002389406579e-06, "loss": 0.3226, "step": 282380 }, { "epoch": 1.678584803038679, "grad_norm": 6.566103935241699, "learning_rate": 8.400850289326586e-06, "loss": 0.3513, "step": 282390 }, { "epoch": 1.6786442451153474, "grad_norm": 4.055688858032227, "learning_rate": 8.400698183389926e-06, "loss": 0.3468, "step": 282400 }, { "epoch": 1.6787036871920158, "grad_norm": 4.632096290588379, "learning_rate": 8.400546071596857e-06, "loss": 0.2996, "step": 282410 }, { "epoch": 1.6787631292686842, "grad_norm": 6.548727512359619, "learning_rate": 8.400393953947642e-06, "loss": 0.2954, "step": 282420 }, { "epoch": 1.6788225713453526, "grad_norm": 4.165985107421875, "learning_rate": 8.400241830442543e-06, "loss": 0.3415, "step": 282430 }, { "epoch": 1.678882013422021, "grad_norm": 5.7744669914245605, "learning_rate": 8.400089701081821e-06, "loss": 0.3268, "step": 282440 }, { "epoch": 1.6789414554986895, "grad_norm": 5.795758247375488, "learning_rate": 8.39993756586574e-06, "loss": 0.3266, "step": 282450 }, { "epoch": 1.6790008975753576, "grad_norm": 3.484374761581421, "learning_rate": 8.39978542479456e-06, "loss": 0.315, "step": 282460 }, { "epoch": 1.679060339652026, "grad_norm": 5.545176029205322, "learning_rate": 8.399633277868544e-06, "loss": 0.3408, "step": 282470 }, { "epoch": 1.6791197817286945, "grad_norm": 5.292890548706055, "learning_rate": 8.399481125087955e-06, "loss": 0.3513, "step": 282480 }, { "epoch": 1.6791792238053629, "grad_norm": 6.076379776000977, "learning_rate": 8.399328966453054e-06, "loss": 0.3401, "step": 282490 }, { "epoch": 1.6792386658820313, "grad_norm": 5.6558308601379395, "learning_rate": 8.3991768019641e-06, "loss": 0.3334, "step": 282500 }, { "epoch": 1.6792981079586995, "grad_norm": 5.168488502502441, "learning_rate": 8.39902463162136e-06, "loss": 0.3266, "step": 282510 }, { "epoch": 1.679357550035368, "grad_norm": 4.961984157562256, "learning_rate": 8.398872455425094e-06, "loss": 0.3145, "step": 282520 }, { "epoch": 1.6794169921120363, "grad_norm": 4.379695415496826, "learning_rate": 8.398720273375565e-06, "loss": 0.3408, "step": 282530 }, { "epoch": 1.6794764341887047, "grad_norm": 5.191341876983643, "learning_rate": 8.398568085473033e-06, "loss": 0.3452, "step": 282540 }, { "epoch": 1.6795358762653732, "grad_norm": 4.439101219177246, "learning_rate": 8.398415891717759e-06, "loss": 0.2874, "step": 282550 }, { "epoch": 1.6795953183420416, "grad_norm": 4.8851399421691895, "learning_rate": 8.39826369211001e-06, "loss": 0.3185, "step": 282560 }, { "epoch": 1.67965476041871, "grad_norm": 5.406369209289551, "learning_rate": 8.398111486650047e-06, "loss": 0.3032, "step": 282570 }, { "epoch": 1.6797142024953784, "grad_norm": 6.95720100402832, "learning_rate": 8.397959275338128e-06, "loss": 0.3903, "step": 282580 }, { "epoch": 1.6797736445720468, "grad_norm": 6.503120422363281, "learning_rate": 8.397807058174518e-06, "loss": 0.2916, "step": 282590 }, { "epoch": 1.6798330866487152, "grad_norm": 5.178149700164795, "learning_rate": 8.39765483515948e-06, "loss": 0.284, "step": 282600 }, { "epoch": 1.6798925287253836, "grad_norm": 5.492086410522461, "learning_rate": 8.397502606293274e-06, "loss": 0.3131, "step": 282610 }, { "epoch": 1.679951970802052, "grad_norm": 7.5011162757873535, "learning_rate": 8.397350371576163e-06, "loss": 0.3112, "step": 282620 }, { "epoch": 1.6800114128787205, "grad_norm": 5.608905792236328, "learning_rate": 8.39719813100841e-06, "loss": 0.3096, "step": 282630 }, { "epoch": 1.6800708549553889, "grad_norm": 6.023277282714844, "learning_rate": 8.397045884590275e-06, "loss": 0.3889, "step": 282640 }, { "epoch": 1.680130297032057, "grad_norm": 5.564691543579102, "learning_rate": 8.396893632322025e-06, "loss": 0.3377, "step": 282650 }, { "epoch": 1.6801897391087255, "grad_norm": 4.557284832000732, "learning_rate": 8.396741374203916e-06, "loss": 0.2739, "step": 282660 }, { "epoch": 1.680249181185394, "grad_norm": 3.7523937225341797, "learning_rate": 8.396589110236214e-06, "loss": 0.3034, "step": 282670 }, { "epoch": 1.6803086232620623, "grad_norm": 4.407756805419922, "learning_rate": 8.396436840419178e-06, "loss": 0.3469, "step": 282680 }, { "epoch": 1.6803680653387305, "grad_norm": 5.118978500366211, "learning_rate": 8.396284564753076e-06, "loss": 0.3264, "step": 282690 }, { "epoch": 1.680427507415399, "grad_norm": 4.4466166496276855, "learning_rate": 8.396132283238165e-06, "loss": 0.3277, "step": 282700 }, { "epoch": 1.6804869494920673, "grad_norm": 4.668871879577637, "learning_rate": 8.395979995874708e-06, "loss": 0.3125, "step": 282710 }, { "epoch": 1.6805463915687358, "grad_norm": 4.443117618560791, "learning_rate": 8.39582770266297e-06, "loss": 0.3139, "step": 282720 }, { "epoch": 1.6806058336454042, "grad_norm": 6.2597551345825195, "learning_rate": 8.395675403603212e-06, "loss": 0.3362, "step": 282730 }, { "epoch": 1.6806652757220726, "grad_norm": 6.551174163818359, "learning_rate": 8.395523098695695e-06, "loss": 0.2979, "step": 282740 }, { "epoch": 1.680724717798741, "grad_norm": 4.941954135894775, "learning_rate": 8.39537078794068e-06, "loss": 0.3532, "step": 282750 }, { "epoch": 1.6807841598754094, "grad_norm": 6.436695098876953, "learning_rate": 8.395218471338434e-06, "loss": 0.3292, "step": 282760 }, { "epoch": 1.6808436019520778, "grad_norm": 4.190412521362305, "learning_rate": 8.395066148889214e-06, "loss": 0.3553, "step": 282770 }, { "epoch": 1.6809030440287462, "grad_norm": 6.060323238372803, "learning_rate": 8.394913820593289e-06, "loss": 0.329, "step": 282780 }, { "epoch": 1.6809624861054147, "grad_norm": 4.34675407409668, "learning_rate": 8.394761486450915e-06, "loss": 0.328, "step": 282790 }, { "epoch": 1.681021928182083, "grad_norm": 6.600947856903076, "learning_rate": 8.394609146462356e-06, "loss": 0.3236, "step": 282800 }, { "epoch": 1.6810813702587515, "grad_norm": 5.879398822784424, "learning_rate": 8.394456800627877e-06, "loss": 0.3458, "step": 282810 }, { "epoch": 1.68114081233542, "grad_norm": 5.463468551635742, "learning_rate": 8.394304448947736e-06, "loss": 0.3521, "step": 282820 }, { "epoch": 1.681200254412088, "grad_norm": 4.798402309417725, "learning_rate": 8.394152091422201e-06, "loss": 0.3356, "step": 282830 }, { "epoch": 1.6812596964887565, "grad_norm": 4.445190906524658, "learning_rate": 8.393999728051527e-06, "loss": 0.3368, "step": 282840 }, { "epoch": 1.681319138565425, "grad_norm": 4.41644811630249, "learning_rate": 8.393847358835983e-06, "loss": 0.3074, "step": 282850 }, { "epoch": 1.6813785806420933, "grad_norm": 5.858642578125, "learning_rate": 8.393694983775828e-06, "loss": 0.3602, "step": 282860 }, { "epoch": 1.6814380227187617, "grad_norm": 5.319158554077148, "learning_rate": 8.393542602871328e-06, "loss": 0.318, "step": 282870 }, { "epoch": 1.68149746479543, "grad_norm": 3.5794124603271484, "learning_rate": 8.39339021612274e-06, "loss": 0.3239, "step": 282880 }, { "epoch": 1.6815569068720984, "grad_norm": 4.323157787322998, "learning_rate": 8.39323782353033e-06, "loss": 0.3432, "step": 282890 }, { "epoch": 1.6816163489487668, "grad_norm": 6.404481887817383, "learning_rate": 8.393085425094359e-06, "loss": 0.3482, "step": 282900 }, { "epoch": 1.6816757910254352, "grad_norm": 5.111059188842773, "learning_rate": 8.39293302081509e-06, "loss": 0.2982, "step": 282910 }, { "epoch": 1.6817352331021036, "grad_norm": 5.461263179779053, "learning_rate": 8.392780610692785e-06, "loss": 0.3282, "step": 282920 }, { "epoch": 1.681794675178772, "grad_norm": 4.163887977600098, "learning_rate": 8.392628194727708e-06, "loss": 0.3091, "step": 282930 }, { "epoch": 1.6818541172554404, "grad_norm": 4.987726211547852, "learning_rate": 8.39247577292012e-06, "loss": 0.3124, "step": 282940 }, { "epoch": 1.6819135593321088, "grad_norm": 4.158037185668945, "learning_rate": 8.392323345270284e-06, "loss": 0.2991, "step": 282950 }, { "epoch": 1.6819730014087773, "grad_norm": 5.147687911987305, "learning_rate": 8.392170911778464e-06, "loss": 0.3155, "step": 282960 }, { "epoch": 1.6820324434854457, "grad_norm": 4.001704692840576, "learning_rate": 8.392018472444918e-06, "loss": 0.3394, "step": 282970 }, { "epoch": 1.682091885562114, "grad_norm": 4.8367719650268555, "learning_rate": 8.391866027269914e-06, "loss": 0.3223, "step": 282980 }, { "epoch": 1.6821513276387825, "grad_norm": 5.966004848480225, "learning_rate": 8.39171357625371e-06, "loss": 0.3364, "step": 282990 }, { "epoch": 1.682210769715451, "grad_norm": 5.572542667388916, "learning_rate": 8.391561119396571e-06, "loss": 0.3304, "step": 283000 }, { "epoch": 1.6822702117921193, "grad_norm": 4.798366546630859, "learning_rate": 8.391408656698761e-06, "loss": 0.3245, "step": 283010 }, { "epoch": 1.6823296538687875, "grad_norm": 4.711997985839844, "learning_rate": 8.39125618816054e-06, "loss": 0.29, "step": 283020 }, { "epoch": 1.682389095945456, "grad_norm": 5.671640396118164, "learning_rate": 8.391103713782169e-06, "loss": 0.3478, "step": 283030 }, { "epoch": 1.6824485380221244, "grad_norm": 4.240973472595215, "learning_rate": 8.390951233563915e-06, "loss": 0.3293, "step": 283040 }, { "epoch": 1.6825079800987928, "grad_norm": 5.464234352111816, "learning_rate": 8.390798747506038e-06, "loss": 0.3577, "step": 283050 }, { "epoch": 1.682567422175461, "grad_norm": 5.560340881347656, "learning_rate": 8.3906462556088e-06, "loss": 0.3208, "step": 283060 }, { "epoch": 1.6826268642521294, "grad_norm": 7.158114910125732, "learning_rate": 8.390493757872465e-06, "loss": 0.3402, "step": 283070 }, { "epoch": 1.6826863063287978, "grad_norm": 7.404935359954834, "learning_rate": 8.390341254297296e-06, "loss": 0.3441, "step": 283080 }, { "epoch": 1.6827457484054662, "grad_norm": 4.53587007522583, "learning_rate": 8.390188744883554e-06, "loss": 0.3227, "step": 283090 }, { "epoch": 1.6828051904821346, "grad_norm": 4.8644304275512695, "learning_rate": 8.390036229631502e-06, "loss": 0.3516, "step": 283100 }, { "epoch": 1.682864632558803, "grad_norm": 4.062996864318848, "learning_rate": 8.389883708541405e-06, "loss": 0.2912, "step": 283110 }, { "epoch": 1.6829240746354714, "grad_norm": 5.642731666564941, "learning_rate": 8.389731181613522e-06, "loss": 0.3237, "step": 283120 }, { "epoch": 1.6829835167121399, "grad_norm": 5.800530910491943, "learning_rate": 8.389578648848119e-06, "loss": 0.3546, "step": 283130 }, { "epoch": 1.6830429587888083, "grad_norm": 4.516591548919678, "learning_rate": 8.389426110245455e-06, "loss": 0.3379, "step": 283140 }, { "epoch": 1.6831024008654767, "grad_norm": 5.686051845550537, "learning_rate": 8.389273565805795e-06, "loss": 0.3633, "step": 283150 }, { "epoch": 1.683161842942145, "grad_norm": 5.133774280548096, "learning_rate": 8.389121015529405e-06, "loss": 0.3207, "step": 283160 }, { "epoch": 1.6832212850188135, "grad_norm": 6.729526996612549, "learning_rate": 8.38896845941654e-06, "loss": 0.3431, "step": 283170 }, { "epoch": 1.683280727095482, "grad_norm": 4.853427410125732, "learning_rate": 8.388815897467469e-06, "loss": 0.3207, "step": 283180 }, { "epoch": 1.6833401691721503, "grad_norm": 5.6772918701171875, "learning_rate": 8.388663329682452e-06, "loss": 0.3274, "step": 283190 }, { "epoch": 1.6833996112488185, "grad_norm": 5.728731155395508, "learning_rate": 8.388510756061754e-06, "loss": 0.347, "step": 283200 }, { "epoch": 1.683459053325487, "grad_norm": 6.476767063140869, "learning_rate": 8.388358176605634e-06, "loss": 0.3886, "step": 283210 }, { "epoch": 1.6835184954021554, "grad_norm": 4.529173851013184, "learning_rate": 8.388205591314359e-06, "loss": 0.3309, "step": 283220 }, { "epoch": 1.6835779374788238, "grad_norm": 5.302154541015625, "learning_rate": 8.388053000188187e-06, "loss": 0.3396, "step": 283230 }, { "epoch": 1.6836373795554922, "grad_norm": 4.168148994445801, "learning_rate": 8.387900403227385e-06, "loss": 0.3385, "step": 283240 }, { "epoch": 1.6836968216321604, "grad_norm": 4.284428119659424, "learning_rate": 8.387747800432215e-06, "loss": 0.3464, "step": 283250 }, { "epoch": 1.6837562637088288, "grad_norm": 6.495034217834473, "learning_rate": 8.387595191802937e-06, "loss": 0.3788, "step": 283260 }, { "epoch": 1.6838157057854972, "grad_norm": 5.420953273773193, "learning_rate": 8.387442577339819e-06, "loss": 0.3395, "step": 283270 }, { "epoch": 1.6838751478621656, "grad_norm": 4.984471797943115, "learning_rate": 8.387289957043118e-06, "loss": 0.2815, "step": 283280 }, { "epoch": 1.683934589938834, "grad_norm": 5.946844100952148, "learning_rate": 8.3871373309131e-06, "loss": 0.3274, "step": 283290 }, { "epoch": 1.6839940320155025, "grad_norm": 5.16510009765625, "learning_rate": 8.386984698950028e-06, "loss": 0.3188, "step": 283300 }, { "epoch": 1.6840534740921709, "grad_norm": 5.785364151000977, "learning_rate": 8.386832061154164e-06, "loss": 0.3245, "step": 283310 }, { "epoch": 1.6841129161688393, "grad_norm": 5.679572582244873, "learning_rate": 8.386679417525772e-06, "loss": 0.3062, "step": 283320 }, { "epoch": 1.6841723582455077, "grad_norm": 4.4449968338012695, "learning_rate": 8.386526768065114e-06, "loss": 0.3169, "step": 283330 }, { "epoch": 1.6842318003221761, "grad_norm": 4.802642822265625, "learning_rate": 8.38637411277245e-06, "loss": 0.3278, "step": 283340 }, { "epoch": 1.6842912423988445, "grad_norm": 4.10080099105835, "learning_rate": 8.386221451648049e-06, "loss": 0.317, "step": 283350 }, { "epoch": 1.684350684475513, "grad_norm": 4.537355899810791, "learning_rate": 8.386068784692168e-06, "loss": 0.3103, "step": 283360 }, { "epoch": 1.6844101265521814, "grad_norm": 5.577857971191406, "learning_rate": 8.385916111905074e-06, "loss": 0.3317, "step": 283370 }, { "epoch": 1.6844695686288498, "grad_norm": 5.898521423339844, "learning_rate": 8.385763433287028e-06, "loss": 0.3221, "step": 283380 }, { "epoch": 1.684529010705518, "grad_norm": 4.944029808044434, "learning_rate": 8.385610748838294e-06, "loss": 0.3377, "step": 283390 }, { "epoch": 1.6845884527821864, "grad_norm": 3.517014265060425, "learning_rate": 8.385458058559135e-06, "loss": 0.3351, "step": 283400 }, { "epoch": 1.6846478948588548, "grad_norm": 4.81455135345459, "learning_rate": 8.385305362449812e-06, "loss": 0.2797, "step": 283410 }, { "epoch": 1.6847073369355232, "grad_norm": 4.956149578094482, "learning_rate": 8.38515266051059e-06, "loss": 0.3093, "step": 283420 }, { "epoch": 1.6847667790121914, "grad_norm": 4.4010233879089355, "learning_rate": 8.38499995274173e-06, "loss": 0.3225, "step": 283430 }, { "epoch": 1.6848262210888598, "grad_norm": 4.62924337387085, "learning_rate": 8.384847239143496e-06, "loss": 0.3538, "step": 283440 }, { "epoch": 1.6848856631655282, "grad_norm": 5.3302459716796875, "learning_rate": 8.384694519716152e-06, "loss": 0.3196, "step": 283450 }, { "epoch": 1.6849451052421967, "grad_norm": 6.774979114532471, "learning_rate": 8.38454179445996e-06, "loss": 0.3368, "step": 283460 }, { "epoch": 1.685004547318865, "grad_norm": 3.771200180053711, "learning_rate": 8.384389063375185e-06, "loss": 0.321, "step": 283470 }, { "epoch": 1.6850639893955335, "grad_norm": 6.2645649909973145, "learning_rate": 8.384236326462085e-06, "loss": 0.3203, "step": 283480 }, { "epoch": 1.685123431472202, "grad_norm": 5.1971435546875, "learning_rate": 8.38408358372093e-06, "loss": 0.3038, "step": 283490 }, { "epoch": 1.6851828735488703, "grad_norm": 5.313784599304199, "learning_rate": 8.383930835151977e-06, "loss": 0.3473, "step": 283500 }, { "epoch": 1.6852423156255387, "grad_norm": 3.7724082469940186, "learning_rate": 8.383778080755492e-06, "loss": 0.2985, "step": 283510 }, { "epoch": 1.6853017577022071, "grad_norm": 4.189948558807373, "learning_rate": 8.383625320531735e-06, "loss": 0.3059, "step": 283520 }, { "epoch": 1.6853611997788756, "grad_norm": 5.794593811035156, "learning_rate": 8.383472554480973e-06, "loss": 0.3222, "step": 283530 }, { "epoch": 1.685420641855544, "grad_norm": 4.665335655212402, "learning_rate": 8.38331978260347e-06, "loss": 0.3054, "step": 283540 }, { "epoch": 1.6854800839322124, "grad_norm": 4.924455165863037, "learning_rate": 8.383167004899484e-06, "loss": 0.3469, "step": 283550 }, { "epoch": 1.6855395260088808, "grad_norm": 4.357213020324707, "learning_rate": 8.383014221369282e-06, "loss": 0.334, "step": 283560 }, { "epoch": 1.685598968085549, "grad_norm": 5.1920485496521, "learning_rate": 8.382861432013123e-06, "loss": 0.288, "step": 283570 }, { "epoch": 1.6856584101622174, "grad_norm": 4.008875370025635, "learning_rate": 8.382708636831276e-06, "loss": 0.3491, "step": 283580 }, { "epoch": 1.6857178522388858, "grad_norm": 4.981886386871338, "learning_rate": 8.382555835824e-06, "loss": 0.3115, "step": 283590 }, { "epoch": 1.6857772943155542, "grad_norm": 4.7206268310546875, "learning_rate": 8.382403028991559e-06, "loss": 0.3655, "step": 283600 }, { "epoch": 1.6858367363922226, "grad_norm": 4.098483562469482, "learning_rate": 8.382250216334218e-06, "loss": 0.297, "step": 283610 }, { "epoch": 1.6858961784688908, "grad_norm": 4.012762546539307, "learning_rate": 8.382097397852238e-06, "loss": 0.2978, "step": 283620 }, { "epoch": 1.6859556205455593, "grad_norm": 6.412101745605469, "learning_rate": 8.381944573545882e-06, "loss": 0.3367, "step": 283630 }, { "epoch": 1.6860150626222277, "grad_norm": 6.715175628662109, "learning_rate": 8.381791743415414e-06, "loss": 0.3307, "step": 283640 }, { "epoch": 1.686074504698896, "grad_norm": 4.416727542877197, "learning_rate": 8.381638907461096e-06, "loss": 0.2932, "step": 283650 }, { "epoch": 1.6861339467755645, "grad_norm": 4.910896301269531, "learning_rate": 8.381486065683195e-06, "loss": 0.3173, "step": 283660 }, { "epoch": 1.686193388852233, "grad_norm": 4.236160755157471, "learning_rate": 8.381333218081969e-06, "loss": 0.3152, "step": 283670 }, { "epoch": 1.6862528309289013, "grad_norm": 6.125763416290283, "learning_rate": 8.381180364657684e-06, "loss": 0.3171, "step": 283680 }, { "epoch": 1.6863122730055697, "grad_norm": 5.393307685852051, "learning_rate": 8.381027505410604e-06, "loss": 0.3396, "step": 283690 }, { "epoch": 1.6863717150822382, "grad_norm": 6.574395656585693, "learning_rate": 8.380874640340993e-06, "loss": 0.3566, "step": 283700 }, { "epoch": 1.6864311571589066, "grad_norm": 5.071804046630859, "learning_rate": 8.38072176944911e-06, "loss": 0.3153, "step": 283710 }, { "epoch": 1.686490599235575, "grad_norm": 5.99000883102417, "learning_rate": 8.380568892735221e-06, "loss": 0.3588, "step": 283720 }, { "epoch": 1.6865500413122434, "grad_norm": 5.249231815338135, "learning_rate": 8.380416010199589e-06, "loss": 0.3363, "step": 283730 }, { "epoch": 1.6866094833889118, "grad_norm": 6.68322229385376, "learning_rate": 8.380263121842478e-06, "loss": 0.3161, "step": 283740 }, { "epoch": 1.6866689254655802, "grad_norm": 4.646416187286377, "learning_rate": 8.38011022766415e-06, "loss": 0.3129, "step": 283750 }, { "epoch": 1.6867283675422484, "grad_norm": 5.664539813995361, "learning_rate": 8.379957327664868e-06, "loss": 0.3288, "step": 283760 }, { "epoch": 1.6867878096189168, "grad_norm": 4.779285907745361, "learning_rate": 8.379804421844896e-06, "loss": 0.3252, "step": 283770 }, { "epoch": 1.6868472516955852, "grad_norm": 4.433474063873291, "learning_rate": 8.3796515102045e-06, "loss": 0.2892, "step": 283780 }, { "epoch": 1.6869066937722537, "grad_norm": 4.0811448097229, "learning_rate": 8.37949859274394e-06, "loss": 0.3037, "step": 283790 }, { "epoch": 1.6869661358489219, "grad_norm": 4.260080814361572, "learning_rate": 8.379345669463479e-06, "loss": 0.3269, "step": 283800 }, { "epoch": 1.6870255779255903, "grad_norm": 4.3411149978637695, "learning_rate": 8.379192740363384e-06, "loss": 0.341, "step": 283810 }, { "epoch": 1.6870850200022587, "grad_norm": 4.337987899780273, "learning_rate": 8.379039805443913e-06, "loss": 0.2987, "step": 283820 }, { "epoch": 1.687144462078927, "grad_norm": 3.9698710441589355, "learning_rate": 8.378886864705333e-06, "loss": 0.3424, "step": 283830 }, { "epoch": 1.6872039041555955, "grad_norm": 5.030401706695557, "learning_rate": 8.378733918147908e-06, "loss": 0.3678, "step": 283840 }, { "epoch": 1.687263346232264, "grad_norm": 6.146359443664551, "learning_rate": 8.3785809657719e-06, "loss": 0.3127, "step": 283850 }, { "epoch": 1.6873227883089323, "grad_norm": 4.1111650466918945, "learning_rate": 8.378428007577571e-06, "loss": 0.3151, "step": 283860 }, { "epoch": 1.6873822303856008, "grad_norm": 5.897157669067383, "learning_rate": 8.378275043565185e-06, "loss": 0.3571, "step": 283870 }, { "epoch": 1.6874416724622692, "grad_norm": 3.575678825378418, "learning_rate": 8.378122073735008e-06, "loss": 0.3112, "step": 283880 }, { "epoch": 1.6875011145389376, "grad_norm": 3.936049699783325, "learning_rate": 8.377969098087302e-06, "loss": 0.3229, "step": 283890 }, { "epoch": 1.687560556615606, "grad_norm": 5.704056739807129, "learning_rate": 8.377816116622329e-06, "loss": 0.3188, "step": 283900 }, { "epoch": 1.6876199986922744, "grad_norm": 6.227819442749023, "learning_rate": 8.377663129340354e-06, "loss": 0.3291, "step": 283910 }, { "epoch": 1.6876794407689428, "grad_norm": 5.754913330078125, "learning_rate": 8.377510136241641e-06, "loss": 0.3655, "step": 283920 }, { "epoch": 1.6877388828456112, "grad_norm": 4.652585029602051, "learning_rate": 8.377357137326451e-06, "loss": 0.344, "step": 283930 }, { "epoch": 1.6877983249222794, "grad_norm": 7.813845157623291, "learning_rate": 8.37720413259505e-06, "loss": 0.2951, "step": 283940 }, { "epoch": 1.6878577669989479, "grad_norm": 4.511675834655762, "learning_rate": 8.3770511220477e-06, "loss": 0.3406, "step": 283950 }, { "epoch": 1.6879172090756163, "grad_norm": 4.989918231964111, "learning_rate": 8.376898105684667e-06, "loss": 0.2915, "step": 283960 }, { "epoch": 1.6879766511522847, "grad_norm": 5.576320171356201, "learning_rate": 8.37674508350621e-06, "loss": 0.3567, "step": 283970 }, { "epoch": 1.688036093228953, "grad_norm": 4.24949312210083, "learning_rate": 8.376592055512596e-06, "loss": 0.3299, "step": 283980 }, { "epoch": 1.6880955353056213, "grad_norm": 5.5892181396484375, "learning_rate": 8.376439021704088e-06, "loss": 0.332, "step": 283990 }, { "epoch": 1.6881549773822897, "grad_norm": 4.919508934020996, "learning_rate": 8.37628598208095e-06, "loss": 0.3444, "step": 284000 }, { "epoch": 1.6882144194589581, "grad_norm": 4.167409896850586, "learning_rate": 8.376132936643441e-06, "loss": 0.3213, "step": 284010 }, { "epoch": 1.6882738615356265, "grad_norm": 5.737410068511963, "learning_rate": 8.375979885391832e-06, "loss": 0.3334, "step": 284020 }, { "epoch": 1.688333303612295, "grad_norm": 4.556258678436279, "learning_rate": 8.37582682832638e-06, "loss": 0.2962, "step": 284030 }, { "epoch": 1.6883927456889634, "grad_norm": 6.418288707733154, "learning_rate": 8.375673765447353e-06, "loss": 0.3096, "step": 284040 }, { "epoch": 1.6884521877656318, "grad_norm": 4.6440300941467285, "learning_rate": 8.375520696755016e-06, "loss": 0.3363, "step": 284050 }, { "epoch": 1.6885116298423002, "grad_norm": 5.261022090911865, "learning_rate": 8.375367622249625e-06, "loss": 0.3302, "step": 284060 }, { "epoch": 1.6885710719189686, "grad_norm": 6.91106653213501, "learning_rate": 8.375214541931448e-06, "loss": 0.3123, "step": 284070 }, { "epoch": 1.688630513995637, "grad_norm": 4.6202521324157715, "learning_rate": 8.375061455800752e-06, "loss": 0.309, "step": 284080 }, { "epoch": 1.6886899560723054, "grad_norm": 4.628332138061523, "learning_rate": 8.374908363857795e-06, "loss": 0.3453, "step": 284090 }, { "epoch": 1.6887493981489738, "grad_norm": 4.216333389282227, "learning_rate": 8.374755266102846e-06, "loss": 0.3014, "step": 284100 }, { "epoch": 1.6888088402256423, "grad_norm": 4.276450157165527, "learning_rate": 8.374602162536163e-06, "loss": 0.3131, "step": 284110 }, { "epoch": 1.6888682823023107, "grad_norm": 4.436514854431152, "learning_rate": 8.374449053158014e-06, "loss": 0.334, "step": 284120 }, { "epoch": 1.6889277243789789, "grad_norm": 6.570579528808594, "learning_rate": 8.37429593796866e-06, "loss": 0.3686, "step": 284130 }, { "epoch": 1.6889871664556473, "grad_norm": 5.6161274909973145, "learning_rate": 8.374142816968366e-06, "loss": 0.3269, "step": 284140 }, { "epoch": 1.6890466085323157, "grad_norm": 4.892532825469971, "learning_rate": 8.373989690157395e-06, "loss": 0.3473, "step": 284150 }, { "epoch": 1.689106050608984, "grad_norm": 4.8466105461120605, "learning_rate": 8.373836557536013e-06, "loss": 0.3096, "step": 284160 }, { "epoch": 1.6891654926856523, "grad_norm": 5.3787970542907715, "learning_rate": 8.37368341910448e-06, "loss": 0.3419, "step": 284170 }, { "epoch": 1.6892249347623207, "grad_norm": 6.304422855377197, "learning_rate": 8.373530274863063e-06, "loss": 0.3509, "step": 284180 }, { "epoch": 1.6892843768389891, "grad_norm": 5.357503890991211, "learning_rate": 8.373377124812023e-06, "loss": 0.3256, "step": 284190 }, { "epoch": 1.6893438189156575, "grad_norm": 5.2700605392456055, "learning_rate": 8.373223968951627e-06, "loss": 0.3067, "step": 284200 }, { "epoch": 1.689403260992326, "grad_norm": 3.886749029159546, "learning_rate": 8.373070807282134e-06, "loss": 0.2851, "step": 284210 }, { "epoch": 1.6894627030689944, "grad_norm": 6.446643829345703, "learning_rate": 8.372917639803813e-06, "loss": 0.3381, "step": 284220 }, { "epoch": 1.6895221451456628, "grad_norm": 3.8214316368103027, "learning_rate": 8.372764466516925e-06, "loss": 0.3192, "step": 284230 }, { "epoch": 1.6895815872223312, "grad_norm": 4.700741767883301, "learning_rate": 8.372611287421732e-06, "loss": 0.3236, "step": 284240 }, { "epoch": 1.6896410292989996, "grad_norm": 5.248210430145264, "learning_rate": 8.372458102518503e-06, "loss": 0.3368, "step": 284250 }, { "epoch": 1.689700471375668, "grad_norm": 4.915761470794678, "learning_rate": 8.372304911807497e-06, "loss": 0.3013, "step": 284260 }, { "epoch": 1.6897599134523364, "grad_norm": 4.94158411026001, "learning_rate": 8.37215171528898e-06, "loss": 0.3099, "step": 284270 }, { "epoch": 1.6898193555290049, "grad_norm": 5.019307613372803, "learning_rate": 8.371998512963216e-06, "loss": 0.3752, "step": 284280 }, { "epoch": 1.6898787976056733, "grad_norm": 5.386276721954346, "learning_rate": 8.371845304830468e-06, "loss": 0.349, "step": 284290 }, { "epoch": 1.6899382396823417, "grad_norm": 4.600142478942871, "learning_rate": 8.371692090890999e-06, "loss": 0.3416, "step": 284300 }, { "epoch": 1.6899976817590099, "grad_norm": 4.470168590545654, "learning_rate": 8.371538871145075e-06, "loss": 0.3139, "step": 284310 }, { "epoch": 1.6900571238356783, "grad_norm": 4.001435279846191, "learning_rate": 8.371385645592957e-06, "loss": 0.3123, "step": 284320 }, { "epoch": 1.6901165659123467, "grad_norm": 4.713481426239014, "learning_rate": 8.371232414234913e-06, "loss": 0.3467, "step": 284330 }, { "epoch": 1.6901760079890151, "grad_norm": 5.147700309753418, "learning_rate": 8.371079177071204e-06, "loss": 0.3002, "step": 284340 }, { "epoch": 1.6902354500656835, "grad_norm": 6.732520580291748, "learning_rate": 8.370925934102093e-06, "loss": 0.3196, "step": 284350 }, { "epoch": 1.6902948921423517, "grad_norm": 4.710211753845215, "learning_rate": 8.370772685327847e-06, "loss": 0.3304, "step": 284360 }, { "epoch": 1.6903543342190201, "grad_norm": 5.760640621185303, "learning_rate": 8.370619430748728e-06, "loss": 0.2984, "step": 284370 }, { "epoch": 1.6904137762956886, "grad_norm": 4.724093437194824, "learning_rate": 8.370466170365e-06, "loss": 0.3192, "step": 284380 }, { "epoch": 1.690473218372357, "grad_norm": 3.7355902194976807, "learning_rate": 8.370312904176927e-06, "loss": 0.3278, "step": 284390 }, { "epoch": 1.6905326604490254, "grad_norm": 5.602024555206299, "learning_rate": 8.370159632184773e-06, "loss": 0.3479, "step": 284400 }, { "epoch": 1.6905921025256938, "grad_norm": 6.434767723083496, "learning_rate": 8.370006354388801e-06, "loss": 0.3309, "step": 284410 }, { "epoch": 1.6906515446023622, "grad_norm": 5.396291732788086, "learning_rate": 8.369853070789275e-06, "loss": 0.3298, "step": 284420 }, { "epoch": 1.6907109866790306, "grad_norm": 4.372956275939941, "learning_rate": 8.369699781386462e-06, "loss": 0.342, "step": 284430 }, { "epoch": 1.690770428755699, "grad_norm": 3.9826910495758057, "learning_rate": 8.369546486180624e-06, "loss": 0.3191, "step": 284440 }, { "epoch": 1.6908298708323675, "grad_norm": 3.9908862113952637, "learning_rate": 8.369393185172025e-06, "loss": 0.3637, "step": 284450 }, { "epoch": 1.6908893129090359, "grad_norm": 5.945725917816162, "learning_rate": 8.369239878360928e-06, "loss": 0.3472, "step": 284460 }, { "epoch": 1.6909487549857043, "grad_norm": 4.619192600250244, "learning_rate": 8.3690865657476e-06, "loss": 0.3427, "step": 284470 }, { "epoch": 1.6910081970623727, "grad_norm": 6.485463619232178, "learning_rate": 8.3689332473323e-06, "loss": 0.3462, "step": 284480 }, { "epoch": 1.6910676391390411, "grad_norm": 5.513054847717285, "learning_rate": 8.368779923115298e-06, "loss": 0.3081, "step": 284490 }, { "epoch": 1.6911270812157093, "grad_norm": 5.356634616851807, "learning_rate": 8.368626593096853e-06, "loss": 0.302, "step": 284500 }, { "epoch": 1.6911865232923777, "grad_norm": 5.9753522872924805, "learning_rate": 8.36847325727723e-06, "loss": 0.328, "step": 284510 }, { "epoch": 1.6912459653690461, "grad_norm": 5.571518898010254, "learning_rate": 8.368319915656697e-06, "loss": 0.3117, "step": 284520 }, { "epoch": 1.6913054074457146, "grad_norm": 4.483627796173096, "learning_rate": 8.368166568235511e-06, "loss": 0.3262, "step": 284530 }, { "epoch": 1.6913648495223828, "grad_norm": 5.494019031524658, "learning_rate": 8.368013215013944e-06, "loss": 0.3572, "step": 284540 }, { "epoch": 1.6914242915990512, "grad_norm": 4.866793155670166, "learning_rate": 8.367859855992255e-06, "loss": 0.3518, "step": 284550 }, { "epoch": 1.6914837336757196, "grad_norm": 5.609968185424805, "learning_rate": 8.36770649117071e-06, "loss": 0.3288, "step": 284560 }, { "epoch": 1.691543175752388, "grad_norm": 4.1688947677612305, "learning_rate": 8.367553120549574e-06, "loss": 0.2937, "step": 284570 }, { "epoch": 1.6916026178290564, "grad_norm": 4.6610331535339355, "learning_rate": 8.367399744129108e-06, "loss": 0.344, "step": 284580 }, { "epoch": 1.6916620599057248, "grad_norm": 4.19852876663208, "learning_rate": 8.367246361909578e-06, "loss": 0.3075, "step": 284590 }, { "epoch": 1.6917215019823932, "grad_norm": 5.962975025177002, "learning_rate": 8.367092973891247e-06, "loss": 0.3559, "step": 284600 }, { "epoch": 1.6917809440590617, "grad_norm": 2.764707088470459, "learning_rate": 8.366939580074383e-06, "loss": 0.296, "step": 284610 }, { "epoch": 1.69184038613573, "grad_norm": 5.121926307678223, "learning_rate": 8.366786180459244e-06, "loss": 0.3276, "step": 284620 }, { "epoch": 1.6918998282123985, "grad_norm": 4.218780517578125, "learning_rate": 8.3666327750461e-06, "loss": 0.3138, "step": 284630 }, { "epoch": 1.691959270289067, "grad_norm": 5.8234124183654785, "learning_rate": 8.366479363835211e-06, "loss": 0.332, "step": 284640 }, { "epoch": 1.6920187123657353, "grad_norm": 5.339170455932617, "learning_rate": 8.366325946826844e-06, "loss": 0.3303, "step": 284650 }, { "epoch": 1.6920781544424037, "grad_norm": 7.1421637535095215, "learning_rate": 8.366172524021261e-06, "loss": 0.3502, "step": 284660 }, { "epoch": 1.6921375965190721, "grad_norm": 4.225508689880371, "learning_rate": 8.366019095418727e-06, "loss": 0.2936, "step": 284670 }, { "epoch": 1.6921970385957403, "grad_norm": 4.866697788238525, "learning_rate": 8.365865661019508e-06, "loss": 0.3171, "step": 284680 }, { "epoch": 1.6922564806724087, "grad_norm": 5.543940544128418, "learning_rate": 8.365712220823866e-06, "loss": 0.326, "step": 284690 }, { "epoch": 1.6923159227490772, "grad_norm": 6.897927284240723, "learning_rate": 8.365558774832066e-06, "loss": 0.3277, "step": 284700 }, { "epoch": 1.6923753648257456, "grad_norm": 4.314606189727783, "learning_rate": 8.365405323044371e-06, "loss": 0.3408, "step": 284710 }, { "epoch": 1.692434806902414, "grad_norm": 6.392140865325928, "learning_rate": 8.365251865461049e-06, "loss": 0.3494, "step": 284720 }, { "epoch": 1.6924942489790822, "grad_norm": 3.307523727416992, "learning_rate": 8.365098402082361e-06, "loss": 0.3198, "step": 284730 }, { "epoch": 1.6925536910557506, "grad_norm": 5.627016544342041, "learning_rate": 8.36494493290857e-06, "loss": 0.3412, "step": 284740 }, { "epoch": 1.692613133132419, "grad_norm": 4.98482084274292, "learning_rate": 8.364791457939945e-06, "loss": 0.3413, "step": 284750 }, { "epoch": 1.6926725752090874, "grad_norm": 5.798043727874756, "learning_rate": 8.364637977176746e-06, "loss": 0.3386, "step": 284760 }, { "epoch": 1.6927320172857558, "grad_norm": 6.323154926300049, "learning_rate": 8.364484490619237e-06, "loss": 0.3495, "step": 284770 }, { "epoch": 1.6927914593624243, "grad_norm": 4.887080669403076, "learning_rate": 8.36433099826769e-06, "loss": 0.3139, "step": 284780 }, { "epoch": 1.6928509014390927, "grad_norm": 3.563969612121582, "learning_rate": 8.36417750012236e-06, "loss": 0.3353, "step": 284790 }, { "epoch": 1.692910343515761, "grad_norm": 4.705052375793457, "learning_rate": 8.364023996183514e-06, "loss": 0.3004, "step": 284800 }, { "epoch": 1.6929697855924295, "grad_norm": 4.913609504699707, "learning_rate": 8.363870486451419e-06, "loss": 0.3095, "step": 284810 }, { "epoch": 1.693029227669098, "grad_norm": 6.596997261047363, "learning_rate": 8.363716970926337e-06, "loss": 0.2838, "step": 284820 }, { "epoch": 1.6930886697457663, "grad_norm": 5.0311970710754395, "learning_rate": 8.363563449608532e-06, "loss": 0.3297, "step": 284830 }, { "epoch": 1.6931481118224347, "grad_norm": 4.627654075622559, "learning_rate": 8.363409922498272e-06, "loss": 0.3368, "step": 284840 }, { "epoch": 1.6932075538991032, "grad_norm": 5.345291614532471, "learning_rate": 8.363256389595816e-06, "loss": 0.3171, "step": 284850 }, { "epoch": 1.6932669959757716, "grad_norm": 4.680975437164307, "learning_rate": 8.363102850901432e-06, "loss": 0.3145, "step": 284860 }, { "epoch": 1.6933264380524398, "grad_norm": 4.940361022949219, "learning_rate": 8.362949306415385e-06, "loss": 0.3598, "step": 284870 }, { "epoch": 1.6933858801291082, "grad_norm": 5.086215019226074, "learning_rate": 8.362795756137937e-06, "loss": 0.3111, "step": 284880 }, { "epoch": 1.6934453222057766, "grad_norm": 6.0222392082214355, "learning_rate": 8.362642200069353e-06, "loss": 0.3322, "step": 284890 }, { "epoch": 1.693504764282445, "grad_norm": 5.22160530090332, "learning_rate": 8.362488638209899e-06, "loss": 0.3242, "step": 284900 }, { "epoch": 1.6935642063591132, "grad_norm": 4.542684555053711, "learning_rate": 8.362335070559839e-06, "loss": 0.3448, "step": 284910 }, { "epoch": 1.6936236484357816, "grad_norm": 6.414628028869629, "learning_rate": 8.362181497119434e-06, "loss": 0.3463, "step": 284920 }, { "epoch": 1.69368309051245, "grad_norm": 4.851598262786865, "learning_rate": 8.362027917888954e-06, "loss": 0.3348, "step": 284930 }, { "epoch": 1.6937425325891184, "grad_norm": 4.324453353881836, "learning_rate": 8.36187433286866e-06, "loss": 0.3207, "step": 284940 }, { "epoch": 1.6938019746657869, "grad_norm": 6.848789691925049, "learning_rate": 8.361720742058817e-06, "loss": 0.3435, "step": 284950 }, { "epoch": 1.6938614167424553, "grad_norm": 5.4312872886657715, "learning_rate": 8.36156714545969e-06, "loss": 0.3172, "step": 284960 }, { "epoch": 1.6939208588191237, "grad_norm": 5.051022529602051, "learning_rate": 8.361413543071542e-06, "loss": 0.2956, "step": 284970 }, { "epoch": 1.693980300895792, "grad_norm": 5.486966133117676, "learning_rate": 8.361259934894642e-06, "loss": 0.3275, "step": 284980 }, { "epoch": 1.6940397429724605, "grad_norm": 5.600443363189697, "learning_rate": 8.361106320929247e-06, "loss": 0.3342, "step": 284990 }, { "epoch": 1.694099185049129, "grad_norm": 4.61915922164917, "learning_rate": 8.36095270117563e-06, "loss": 0.3466, "step": 285000 }, { "epoch": 1.6941586271257973, "grad_norm": 6.3477783203125, "learning_rate": 8.360799075634049e-06, "loss": 0.3409, "step": 285010 }, { "epoch": 1.6942180692024658, "grad_norm": 3.7264065742492676, "learning_rate": 8.360645444304772e-06, "loss": 0.3405, "step": 285020 }, { "epoch": 1.6942775112791342, "grad_norm": 5.975335121154785, "learning_rate": 8.360491807188061e-06, "loss": 0.3168, "step": 285030 }, { "epoch": 1.6943369533558026, "grad_norm": 5.927779197692871, "learning_rate": 8.360338164284182e-06, "loss": 0.3331, "step": 285040 }, { "epoch": 1.6943963954324708, "grad_norm": 4.875098705291748, "learning_rate": 8.360184515593401e-06, "loss": 0.3313, "step": 285050 }, { "epoch": 1.6944558375091392, "grad_norm": 5.429304599761963, "learning_rate": 8.360030861115981e-06, "loss": 0.3595, "step": 285060 }, { "epoch": 1.6945152795858076, "grad_norm": 7.377281188964844, "learning_rate": 8.35987720085219e-06, "loss": 0.3098, "step": 285070 }, { "epoch": 1.694574721662476, "grad_norm": 5.124823093414307, "learning_rate": 8.359723534802285e-06, "loss": 0.3044, "step": 285080 }, { "epoch": 1.6946341637391444, "grad_norm": 4.937986850738525, "learning_rate": 8.359569862966537e-06, "loss": 0.3116, "step": 285090 }, { "epoch": 1.6946936058158126, "grad_norm": 3.8615880012512207, "learning_rate": 8.359416185345209e-06, "loss": 0.3366, "step": 285100 }, { "epoch": 1.694753047892481, "grad_norm": 5.52548360824585, "learning_rate": 8.359262501938566e-06, "loss": 0.3469, "step": 285110 }, { "epoch": 1.6948124899691495, "grad_norm": 4.664130210876465, "learning_rate": 8.35910881274687e-06, "loss": 0.3151, "step": 285120 }, { "epoch": 1.6948719320458179, "grad_norm": 4.363882064819336, "learning_rate": 8.35895511777039e-06, "loss": 0.3126, "step": 285130 }, { "epoch": 1.6949313741224863, "grad_norm": 4.874549865722656, "learning_rate": 8.358801417009388e-06, "loss": 0.3394, "step": 285140 }, { "epoch": 1.6949908161991547, "grad_norm": 5.289290904998779, "learning_rate": 8.35864771046413e-06, "loss": 0.3313, "step": 285150 }, { "epoch": 1.6950502582758231, "grad_norm": 4.911072254180908, "learning_rate": 8.358493998134877e-06, "loss": 0.2969, "step": 285160 }, { "epoch": 1.6951097003524915, "grad_norm": 4.356515407562256, "learning_rate": 8.3583402800219e-06, "loss": 0.33, "step": 285170 }, { "epoch": 1.69516914242916, "grad_norm": 4.465477466583252, "learning_rate": 8.358186556125459e-06, "loss": 0.3299, "step": 285180 }, { "epoch": 1.6952285845058284, "grad_norm": 4.638867378234863, "learning_rate": 8.35803282644582e-06, "loss": 0.3223, "step": 285190 }, { "epoch": 1.6952880265824968, "grad_norm": 4.466237545013428, "learning_rate": 8.357879090983247e-06, "loss": 0.3217, "step": 285200 }, { "epoch": 1.6953474686591652, "grad_norm": 3.9644672870635986, "learning_rate": 8.357725349738006e-06, "loss": 0.3001, "step": 285210 }, { "epoch": 1.6954069107358336, "grad_norm": 5.5390706062316895, "learning_rate": 8.357571602710361e-06, "loss": 0.3141, "step": 285220 }, { "epoch": 1.695466352812502, "grad_norm": 4.583688735961914, "learning_rate": 8.357417849900578e-06, "loss": 0.3072, "step": 285230 }, { "epoch": 1.6955257948891702, "grad_norm": 4.908221244812012, "learning_rate": 8.35726409130892e-06, "loss": 0.3396, "step": 285240 }, { "epoch": 1.6955852369658386, "grad_norm": 5.582614898681641, "learning_rate": 8.357110326935653e-06, "loss": 0.3081, "step": 285250 }, { "epoch": 1.695644679042507, "grad_norm": 3.856848955154419, "learning_rate": 8.356956556781042e-06, "loss": 0.3453, "step": 285260 }, { "epoch": 1.6957041211191755, "grad_norm": 4.403136730194092, "learning_rate": 8.35680278084535e-06, "loss": 0.308, "step": 285270 }, { "epoch": 1.6957635631958436, "grad_norm": 3.9517617225646973, "learning_rate": 8.356648999128845e-06, "loss": 0.3389, "step": 285280 }, { "epoch": 1.695823005272512, "grad_norm": 4.482861518859863, "learning_rate": 8.356495211631788e-06, "loss": 0.326, "step": 285290 }, { "epoch": 1.6958824473491805, "grad_norm": 5.027798652648926, "learning_rate": 8.356341418354449e-06, "loss": 0.3311, "step": 285300 }, { "epoch": 1.695941889425849, "grad_norm": 5.275031566619873, "learning_rate": 8.356187619297085e-06, "loss": 0.3043, "step": 285310 }, { "epoch": 1.6960013315025173, "grad_norm": 6.997076988220215, "learning_rate": 8.356033814459968e-06, "loss": 0.3676, "step": 285320 }, { "epoch": 1.6960607735791857, "grad_norm": 5.255414962768555, "learning_rate": 8.355880003843359e-06, "loss": 0.3521, "step": 285330 }, { "epoch": 1.6961202156558541, "grad_norm": 5.455195903778076, "learning_rate": 8.355726187447525e-06, "loss": 0.3444, "step": 285340 }, { "epoch": 1.6961796577325225, "grad_norm": 4.072019577026367, "learning_rate": 8.355572365272732e-06, "loss": 0.3261, "step": 285350 }, { "epoch": 1.696239099809191, "grad_norm": 6.621331214904785, "learning_rate": 8.35541853731924e-06, "loss": 0.355, "step": 285360 }, { "epoch": 1.6962985418858594, "grad_norm": 3.807293176651001, "learning_rate": 8.355264703587319e-06, "loss": 0.2894, "step": 285370 }, { "epoch": 1.6963579839625278, "grad_norm": 6.271218776702881, "learning_rate": 8.355110864077232e-06, "loss": 0.3346, "step": 285380 }, { "epoch": 1.6964174260391962, "grad_norm": 5.187533855438232, "learning_rate": 8.354957018789242e-06, "loss": 0.3313, "step": 285390 }, { "epoch": 1.6964768681158646, "grad_norm": 5.768904685974121, "learning_rate": 8.354803167723618e-06, "loss": 0.3501, "step": 285400 }, { "epoch": 1.696536310192533, "grad_norm": 4.715207576751709, "learning_rate": 8.354649310880621e-06, "loss": 0.307, "step": 285410 }, { "epoch": 1.6965957522692012, "grad_norm": 5.124019622802734, "learning_rate": 8.354495448260516e-06, "loss": 0.3226, "step": 285420 }, { "epoch": 1.6966551943458696, "grad_norm": 5.260545253753662, "learning_rate": 8.354341579863571e-06, "loss": 0.3402, "step": 285430 }, { "epoch": 1.696714636422538, "grad_norm": 5.803827285766602, "learning_rate": 8.354187705690052e-06, "loss": 0.3466, "step": 285440 }, { "epoch": 1.6967740784992065, "grad_norm": 5.984119892120361, "learning_rate": 8.354033825740218e-06, "loss": 0.3154, "step": 285450 }, { "epoch": 1.6968335205758749, "grad_norm": 7.076931476593018, "learning_rate": 8.35387994001434e-06, "loss": 0.3588, "step": 285460 }, { "epoch": 1.696892962652543, "grad_norm": 5.2986931800842285, "learning_rate": 8.35372604851268e-06, "loss": 0.3134, "step": 285470 }, { "epoch": 1.6969524047292115, "grad_norm": 4.143115520477295, "learning_rate": 8.353572151235503e-06, "loss": 0.3074, "step": 285480 }, { "epoch": 1.69701184680588, "grad_norm": 4.685490131378174, "learning_rate": 8.353418248183076e-06, "loss": 0.3401, "step": 285490 }, { "epoch": 1.6970712888825483, "grad_norm": 5.025805473327637, "learning_rate": 8.35326433935566e-06, "loss": 0.3608, "step": 285500 }, { "epoch": 1.6971307309592167, "grad_norm": 4.133182048797607, "learning_rate": 8.353110424753525e-06, "loss": 0.3155, "step": 285510 }, { "epoch": 1.6971901730358852, "grad_norm": 3.886286973953247, "learning_rate": 8.352956504376931e-06, "loss": 0.3145, "step": 285520 }, { "epoch": 1.6972496151125536, "grad_norm": 5.0693254470825195, "learning_rate": 8.35280257822615e-06, "loss": 0.3487, "step": 285530 }, { "epoch": 1.697309057189222, "grad_norm": 4.931401252746582, "learning_rate": 8.35264864630144e-06, "loss": 0.2567, "step": 285540 }, { "epoch": 1.6973684992658904, "grad_norm": 5.749468803405762, "learning_rate": 8.35249470860307e-06, "loss": 0.2907, "step": 285550 }, { "epoch": 1.6974279413425588, "grad_norm": 4.8294219970703125, "learning_rate": 8.352340765131305e-06, "loss": 0.2782, "step": 285560 }, { "epoch": 1.6974873834192272, "grad_norm": 3.898045301437378, "learning_rate": 8.352186815886407e-06, "loss": 0.2986, "step": 285570 }, { "epoch": 1.6975468254958956, "grad_norm": 3.9237594604492188, "learning_rate": 8.352032860868644e-06, "loss": 0.3087, "step": 285580 }, { "epoch": 1.697606267572564, "grad_norm": 7.0131096839904785, "learning_rate": 8.35187890007828e-06, "loss": 0.3199, "step": 285590 }, { "epoch": 1.6976657096492325, "grad_norm": 6.002169132232666, "learning_rate": 8.351724933515581e-06, "loss": 0.3443, "step": 285600 }, { "epoch": 1.6977251517259007, "grad_norm": 4.389641284942627, "learning_rate": 8.351570961180813e-06, "loss": 0.3448, "step": 285610 }, { "epoch": 1.697784593802569, "grad_norm": 4.832958698272705, "learning_rate": 8.351416983074238e-06, "loss": 0.32, "step": 285620 }, { "epoch": 1.6978440358792375, "grad_norm": 5.311826705932617, "learning_rate": 8.351262999196126e-06, "loss": 0.3258, "step": 285630 }, { "epoch": 1.697903477955906, "grad_norm": 6.238505840301514, "learning_rate": 8.351109009546736e-06, "loss": 0.3758, "step": 285640 }, { "epoch": 1.697962920032574, "grad_norm": 4.947016716003418, "learning_rate": 8.350955014126338e-06, "loss": 0.3019, "step": 285650 }, { "epoch": 1.6980223621092425, "grad_norm": 4.473322868347168, "learning_rate": 8.350801012935195e-06, "loss": 0.3062, "step": 285660 }, { "epoch": 1.698081804185911, "grad_norm": 3.813678026199341, "learning_rate": 8.350647005973574e-06, "loss": 0.327, "step": 285670 }, { "epoch": 1.6981412462625793, "grad_norm": 4.1140642166137695, "learning_rate": 8.35049299324174e-06, "loss": 0.2865, "step": 285680 }, { "epoch": 1.6982006883392478, "grad_norm": 5.813352108001709, "learning_rate": 8.350338974739955e-06, "loss": 0.3176, "step": 285690 }, { "epoch": 1.6982601304159162, "grad_norm": 6.824833393096924, "learning_rate": 8.350184950468485e-06, "loss": 0.3249, "step": 285700 }, { "epoch": 1.6983195724925846, "grad_norm": 5.699674606323242, "learning_rate": 8.3500309204276e-06, "loss": 0.3129, "step": 285710 }, { "epoch": 1.698379014569253, "grad_norm": 3.716355085372925, "learning_rate": 8.349876884617561e-06, "loss": 0.3463, "step": 285720 }, { "epoch": 1.6984384566459214, "grad_norm": 5.54425573348999, "learning_rate": 8.349722843038634e-06, "loss": 0.3018, "step": 285730 }, { "epoch": 1.6984978987225898, "grad_norm": 4.958308696746826, "learning_rate": 8.349568795691085e-06, "loss": 0.3069, "step": 285740 }, { "epoch": 1.6985573407992582, "grad_norm": 4.647828102111816, "learning_rate": 8.349414742575179e-06, "loss": 0.3502, "step": 285750 }, { "epoch": 1.6986167828759267, "grad_norm": 5.089536666870117, "learning_rate": 8.34926068369118e-06, "loss": 0.3199, "step": 285760 }, { "epoch": 1.698676224952595, "grad_norm": 4.306434154510498, "learning_rate": 8.349106619039356e-06, "loss": 0.2995, "step": 285770 }, { "epoch": 1.6987356670292635, "grad_norm": 3.721204996109009, "learning_rate": 8.34895254861997e-06, "loss": 0.3483, "step": 285780 }, { "epoch": 1.6987951091059317, "grad_norm": 5.737631797790527, "learning_rate": 8.348798472433289e-06, "loss": 0.3452, "step": 285790 }, { "epoch": 1.6988545511826, "grad_norm": 5.152157306671143, "learning_rate": 8.348644390479577e-06, "loss": 0.3397, "step": 285800 }, { "epoch": 1.6989139932592685, "grad_norm": 6.083193302154541, "learning_rate": 8.348490302759099e-06, "loss": 0.3349, "step": 285810 }, { "epoch": 1.698973435335937, "grad_norm": 4.011091709136963, "learning_rate": 8.348336209272122e-06, "loss": 0.2998, "step": 285820 }, { "epoch": 1.6990328774126053, "grad_norm": 4.647378444671631, "learning_rate": 8.34818211001891e-06, "loss": 0.3205, "step": 285830 }, { "epoch": 1.6990923194892735, "grad_norm": 5.14565896987915, "learning_rate": 8.34802800499973e-06, "loss": 0.3142, "step": 285840 }, { "epoch": 1.699151761565942, "grad_norm": 5.429957389831543, "learning_rate": 8.347873894214844e-06, "loss": 0.3566, "step": 285850 }, { "epoch": 1.6992112036426104, "grad_norm": 5.010240077972412, "learning_rate": 8.347719777664522e-06, "loss": 0.3334, "step": 285860 }, { "epoch": 1.6992706457192788, "grad_norm": 5.153090000152588, "learning_rate": 8.347565655349026e-06, "loss": 0.2825, "step": 285870 }, { "epoch": 1.6993300877959472, "grad_norm": 4.978390216827393, "learning_rate": 8.347411527268624e-06, "loss": 0.3179, "step": 285880 }, { "epoch": 1.6993895298726156, "grad_norm": 3.603195905685425, "learning_rate": 8.347257393423578e-06, "loss": 0.3045, "step": 285890 }, { "epoch": 1.699448971949284, "grad_norm": 6.720326900482178, "learning_rate": 8.347103253814154e-06, "loss": 0.3365, "step": 285900 }, { "epoch": 1.6995084140259524, "grad_norm": 3.284602642059326, "learning_rate": 8.346949108440623e-06, "loss": 0.2942, "step": 285910 }, { "epoch": 1.6995678561026208, "grad_norm": 4.641438007354736, "learning_rate": 8.346794957303243e-06, "loss": 0.3183, "step": 285920 }, { "epoch": 1.6996272981792893, "grad_norm": 5.55915641784668, "learning_rate": 8.346640800402284e-06, "loss": 0.3356, "step": 285930 }, { "epoch": 1.6996867402559577, "grad_norm": 5.152143478393555, "learning_rate": 8.346486637738012e-06, "loss": 0.3255, "step": 285940 }, { "epoch": 1.699746182332626, "grad_norm": 4.58857536315918, "learning_rate": 8.346332469310687e-06, "loss": 0.332, "step": 285950 }, { "epoch": 1.6998056244092945, "grad_norm": 4.7486572265625, "learning_rate": 8.34617829512058e-06, "loss": 0.3311, "step": 285960 }, { "epoch": 1.699865066485963, "grad_norm": 3.716104030609131, "learning_rate": 8.346024115167956e-06, "loss": 0.3628, "step": 285970 }, { "epoch": 1.699924508562631, "grad_norm": 4.449371814727783, "learning_rate": 8.345869929453078e-06, "loss": 0.3358, "step": 285980 }, { "epoch": 1.6999839506392995, "grad_norm": 6.0885114669799805, "learning_rate": 8.345715737976212e-06, "loss": 0.3265, "step": 285990 }, { "epoch": 1.700043392715968, "grad_norm": 4.986295223236084, "learning_rate": 8.345561540737626e-06, "loss": 0.325, "step": 286000 }, { "epoch": 1.7001028347926364, "grad_norm": 5.721743106842041, "learning_rate": 8.345407337737583e-06, "loss": 0.3359, "step": 286010 }, { "epoch": 1.7001622768693045, "grad_norm": 6.078148365020752, "learning_rate": 8.34525312897635e-06, "loss": 0.3153, "step": 286020 }, { "epoch": 1.700221718945973, "grad_norm": 4.843048095703125, "learning_rate": 8.34509891445419e-06, "loss": 0.3338, "step": 286030 }, { "epoch": 1.7002811610226414, "grad_norm": 4.750906467437744, "learning_rate": 8.344944694171373e-06, "loss": 0.3139, "step": 286040 }, { "epoch": 1.7003406030993098, "grad_norm": 5.730037212371826, "learning_rate": 8.34479046812816e-06, "loss": 0.3194, "step": 286050 }, { "epoch": 1.7004000451759782, "grad_norm": 4.367712497711182, "learning_rate": 8.34463623632482e-06, "loss": 0.3248, "step": 286060 }, { "epoch": 1.7004594872526466, "grad_norm": 4.6683244705200195, "learning_rate": 8.344481998761616e-06, "loss": 0.3292, "step": 286070 }, { "epoch": 1.700518929329315, "grad_norm": 6.300610542297363, "learning_rate": 8.344327755438817e-06, "loss": 0.2974, "step": 286080 }, { "epoch": 1.7005783714059834, "grad_norm": 4.8087077140808105, "learning_rate": 8.344173506356685e-06, "loss": 0.3429, "step": 286090 }, { "epoch": 1.7006378134826519, "grad_norm": 4.169849395751953, "learning_rate": 8.344019251515487e-06, "loss": 0.3028, "step": 286100 }, { "epoch": 1.7006972555593203, "grad_norm": 8.261113166809082, "learning_rate": 8.343864990915491e-06, "loss": 0.349, "step": 286110 }, { "epoch": 1.7007566976359887, "grad_norm": 5.053533554077148, "learning_rate": 8.343710724556959e-06, "loss": 0.2945, "step": 286120 }, { "epoch": 1.700816139712657, "grad_norm": 6.195252418518066, "learning_rate": 8.343556452440157e-06, "loss": 0.3718, "step": 286130 }, { "epoch": 1.7008755817893255, "grad_norm": 5.166672706604004, "learning_rate": 8.343402174565353e-06, "loss": 0.3343, "step": 286140 }, { "epoch": 1.700935023865994, "grad_norm": 4.994574069976807, "learning_rate": 8.343247890932814e-06, "loss": 0.2924, "step": 286150 }, { "epoch": 1.7009944659426621, "grad_norm": 5.463367938995361, "learning_rate": 8.3430936015428e-06, "loss": 0.3102, "step": 286160 }, { "epoch": 1.7010539080193305, "grad_norm": 4.855740547180176, "learning_rate": 8.34293930639558e-06, "loss": 0.3575, "step": 286170 }, { "epoch": 1.701113350095999, "grad_norm": 4.0891032218933105, "learning_rate": 8.342785005491421e-06, "loss": 0.3336, "step": 286180 }, { "epoch": 1.7011727921726674, "grad_norm": 3.8322198390960693, "learning_rate": 8.342630698830587e-06, "loss": 0.328, "step": 286190 }, { "epoch": 1.7012322342493358, "grad_norm": 5.987965106964111, "learning_rate": 8.342476386413343e-06, "loss": 0.3011, "step": 286200 }, { "epoch": 1.701291676326004, "grad_norm": 3.816817045211792, "learning_rate": 8.342322068239956e-06, "loss": 0.3512, "step": 286210 }, { "epoch": 1.7013511184026724, "grad_norm": 7.094846725463867, "learning_rate": 8.342167744310693e-06, "loss": 0.3503, "step": 286220 }, { "epoch": 1.7014105604793408, "grad_norm": 4.79752779006958, "learning_rate": 8.342013414625817e-06, "loss": 0.3647, "step": 286230 }, { "epoch": 1.7014700025560092, "grad_norm": 4.972457408905029, "learning_rate": 8.341859079185597e-06, "loss": 0.349, "step": 286240 }, { "epoch": 1.7015294446326776, "grad_norm": 3.8924310207366943, "learning_rate": 8.341704737990296e-06, "loss": 0.3073, "step": 286250 }, { "epoch": 1.701588886709346, "grad_norm": 9.28065299987793, "learning_rate": 8.34155039104018e-06, "loss": 0.3147, "step": 286260 }, { "epoch": 1.7016483287860145, "grad_norm": 4.281991481781006, "learning_rate": 8.341396038335517e-06, "loss": 0.3113, "step": 286270 }, { "epoch": 1.7017077708626829, "grad_norm": 5.885356903076172, "learning_rate": 8.34124167987657e-06, "loss": 0.3146, "step": 286280 }, { "epoch": 1.7017672129393513, "grad_norm": 5.4958319664001465, "learning_rate": 8.341087315663606e-06, "loss": 0.36, "step": 286290 }, { "epoch": 1.7018266550160197, "grad_norm": 5.008279323577881, "learning_rate": 8.340932945696891e-06, "loss": 0.3264, "step": 286300 }, { "epoch": 1.7018860970926881, "grad_norm": 4.841807842254639, "learning_rate": 8.340778569976691e-06, "loss": 0.2866, "step": 286310 }, { "epoch": 1.7019455391693565, "grad_norm": 4.4381866455078125, "learning_rate": 8.340624188503273e-06, "loss": 0.3265, "step": 286320 }, { "epoch": 1.702004981246025, "grad_norm": 5.307925224304199, "learning_rate": 8.3404698012769e-06, "loss": 0.3243, "step": 286330 }, { "epoch": 1.7020644233226934, "grad_norm": 3.6253647804260254, "learning_rate": 8.34031540829784e-06, "loss": 0.3135, "step": 286340 }, { "epoch": 1.7021238653993616, "grad_norm": 5.898421764373779, "learning_rate": 8.340161009566358e-06, "loss": 0.3371, "step": 286350 }, { "epoch": 1.70218330747603, "grad_norm": 6.278400897979736, "learning_rate": 8.34000660508272e-06, "loss": 0.3386, "step": 286360 }, { "epoch": 1.7022427495526984, "grad_norm": 4.8592848777771, "learning_rate": 8.339852194847193e-06, "loss": 0.3604, "step": 286370 }, { "epoch": 1.7023021916293668, "grad_norm": 4.210415840148926, "learning_rate": 8.33969777886004e-06, "loss": 0.3408, "step": 286380 }, { "epoch": 1.702361633706035, "grad_norm": 4.4190874099731445, "learning_rate": 8.339543357121533e-06, "loss": 0.3128, "step": 286390 }, { "epoch": 1.7024210757827034, "grad_norm": 4.240088939666748, "learning_rate": 8.33938892963193e-06, "loss": 0.3409, "step": 286400 }, { "epoch": 1.7024805178593718, "grad_norm": 5.018385887145996, "learning_rate": 8.339234496391502e-06, "loss": 0.3117, "step": 286410 }, { "epoch": 1.7025399599360402, "grad_norm": 4.667579650878906, "learning_rate": 8.339080057400516e-06, "loss": 0.3086, "step": 286420 }, { "epoch": 1.7025994020127087, "grad_norm": 5.95877742767334, "learning_rate": 8.338925612659231e-06, "loss": 0.3415, "step": 286430 }, { "epoch": 1.702658844089377, "grad_norm": 3.6940369606018066, "learning_rate": 8.338771162167922e-06, "loss": 0.2909, "step": 286440 }, { "epoch": 1.7027182861660455, "grad_norm": 4.815003871917725, "learning_rate": 8.338616705926849e-06, "loss": 0.3122, "step": 286450 }, { "epoch": 1.702777728242714, "grad_norm": 6.820000171661377, "learning_rate": 8.338462243936279e-06, "loss": 0.356, "step": 286460 }, { "epoch": 1.7028371703193823, "grad_norm": 4.802865505218506, "learning_rate": 8.33830777619648e-06, "loss": 0.306, "step": 286470 }, { "epoch": 1.7028966123960507, "grad_norm": 6.589577674865723, "learning_rate": 8.338153302707716e-06, "loss": 0.3448, "step": 286480 }, { "epoch": 1.7029560544727191, "grad_norm": 4.153833389282227, "learning_rate": 8.337998823470254e-06, "loss": 0.3275, "step": 286490 }, { "epoch": 1.7030154965493876, "grad_norm": 4.884321212768555, "learning_rate": 8.33784433848436e-06, "loss": 0.2947, "step": 286500 }, { "epoch": 1.703074938626056, "grad_norm": 4.993609428405762, "learning_rate": 8.3376898477503e-06, "loss": 0.3472, "step": 286510 }, { "epoch": 1.7031343807027244, "grad_norm": 6.018041133880615, "learning_rate": 8.337535351268338e-06, "loss": 0.3145, "step": 286520 }, { "epoch": 1.7031938227793926, "grad_norm": 6.33770751953125, "learning_rate": 8.337380849038743e-06, "loss": 0.3388, "step": 286530 }, { "epoch": 1.703253264856061, "grad_norm": 3.899397373199463, "learning_rate": 8.337226341061778e-06, "loss": 0.3068, "step": 286540 }, { "epoch": 1.7033127069327294, "grad_norm": 5.524351119995117, "learning_rate": 8.337071827337714e-06, "loss": 0.3497, "step": 286550 }, { "epoch": 1.7033721490093978, "grad_norm": 4.64607048034668, "learning_rate": 8.336917307866815e-06, "loss": 0.3167, "step": 286560 }, { "epoch": 1.7034315910860662, "grad_norm": 5.2855048179626465, "learning_rate": 8.336762782649343e-06, "loss": 0.3238, "step": 286570 }, { "epoch": 1.7034910331627344, "grad_norm": 4.338416576385498, "learning_rate": 8.33660825168557e-06, "loss": 0.286, "step": 286580 }, { "epoch": 1.7035504752394028, "grad_norm": 5.638165473937988, "learning_rate": 8.33645371497576e-06, "loss": 0.3526, "step": 286590 }, { "epoch": 1.7036099173160713, "grad_norm": 5.819841384887695, "learning_rate": 8.336299172520175e-06, "loss": 0.3257, "step": 286600 }, { "epoch": 1.7036693593927397, "grad_norm": 4.070712566375732, "learning_rate": 8.336144624319086e-06, "loss": 0.3091, "step": 286610 }, { "epoch": 1.703728801469408, "grad_norm": 5.689816474914551, "learning_rate": 8.33599007037276e-06, "loss": 0.3688, "step": 286620 }, { "epoch": 1.7037882435460765, "grad_norm": 4.595267295837402, "learning_rate": 8.335835510681458e-06, "loss": 0.358, "step": 286630 }, { "epoch": 1.703847685622745, "grad_norm": 5.840030670166016, "learning_rate": 8.335680945245451e-06, "loss": 0.3529, "step": 286640 }, { "epoch": 1.7039071276994133, "grad_norm": 5.331264019012451, "learning_rate": 8.335526374065004e-06, "loss": 0.3491, "step": 286650 }, { "epoch": 1.7039665697760817, "grad_norm": 4.878144264221191, "learning_rate": 8.335371797140381e-06, "loss": 0.3065, "step": 286660 }, { "epoch": 1.7040260118527502, "grad_norm": 4.350952625274658, "learning_rate": 8.335217214471852e-06, "loss": 0.31, "step": 286670 }, { "epoch": 1.7040854539294186, "grad_norm": 4.129727363586426, "learning_rate": 8.335062626059678e-06, "loss": 0.2838, "step": 286680 }, { "epoch": 1.704144896006087, "grad_norm": 4.772891044616699, "learning_rate": 8.33490803190413e-06, "loss": 0.3078, "step": 286690 }, { "epoch": 1.7042043380827554, "grad_norm": 3.9667043685913086, "learning_rate": 8.334753432005473e-06, "loss": 0.3397, "step": 286700 }, { "epoch": 1.7042637801594238, "grad_norm": 4.079395771026611, "learning_rate": 8.334598826363972e-06, "loss": 0.3264, "step": 286710 }, { "epoch": 1.704323222236092, "grad_norm": 4.684771537780762, "learning_rate": 8.334444214979892e-06, "loss": 0.3102, "step": 286720 }, { "epoch": 1.7043826643127604, "grad_norm": 5.072237968444824, "learning_rate": 8.334289597853504e-06, "loss": 0.3421, "step": 286730 }, { "epoch": 1.7044421063894288, "grad_norm": 4.89739990234375, "learning_rate": 8.33413497498507e-06, "loss": 0.3046, "step": 286740 }, { "epoch": 1.7045015484660972, "grad_norm": 4.348462104797363, "learning_rate": 8.33398034637486e-06, "loss": 0.2976, "step": 286750 }, { "epoch": 1.7045609905427654, "grad_norm": 4.710173606872559, "learning_rate": 8.333825712023136e-06, "loss": 0.3521, "step": 286760 }, { "epoch": 1.7046204326194339, "grad_norm": 4.322238445281982, "learning_rate": 8.333671071930167e-06, "loss": 0.3339, "step": 286770 }, { "epoch": 1.7046798746961023, "grad_norm": 4.731513977050781, "learning_rate": 8.333516426096217e-06, "loss": 0.3434, "step": 286780 }, { "epoch": 1.7047393167727707, "grad_norm": 4.805090427398682, "learning_rate": 8.333361774521557e-06, "loss": 0.3353, "step": 286790 }, { "epoch": 1.704798758849439, "grad_norm": 6.014317512512207, "learning_rate": 8.333207117206447e-06, "loss": 0.3139, "step": 286800 }, { "epoch": 1.7048582009261075, "grad_norm": 6.140639781951904, "learning_rate": 8.33305245415116e-06, "loss": 0.2988, "step": 286810 }, { "epoch": 1.704917643002776, "grad_norm": 5.49261999130249, "learning_rate": 8.332897785355958e-06, "loss": 0.3557, "step": 286820 }, { "epoch": 1.7049770850794443, "grad_norm": 4.752841472625732, "learning_rate": 8.332743110821107e-06, "loss": 0.3086, "step": 286830 }, { "epoch": 1.7050365271561128, "grad_norm": 4.609434604644775, "learning_rate": 8.332588430546875e-06, "loss": 0.3134, "step": 286840 }, { "epoch": 1.7050959692327812, "grad_norm": 4.275546550750732, "learning_rate": 8.332433744533528e-06, "loss": 0.2853, "step": 286850 }, { "epoch": 1.7051554113094496, "grad_norm": 4.761288166046143, "learning_rate": 8.332279052781334e-06, "loss": 0.3353, "step": 286860 }, { "epoch": 1.705214853386118, "grad_norm": 3.770800828933716, "learning_rate": 8.332124355290557e-06, "loss": 0.2993, "step": 286870 }, { "epoch": 1.7052742954627864, "grad_norm": 5.53261137008667, "learning_rate": 8.331969652061463e-06, "loss": 0.3293, "step": 286880 }, { "epoch": 1.7053337375394548, "grad_norm": 6.574053764343262, "learning_rate": 8.33181494309432e-06, "loss": 0.3491, "step": 286890 }, { "epoch": 1.705393179616123, "grad_norm": 4.805100440979004, "learning_rate": 8.331660228389396e-06, "loss": 0.3303, "step": 286900 }, { "epoch": 1.7054526216927914, "grad_norm": 4.3302693367004395, "learning_rate": 8.331505507946953e-06, "loss": 0.3367, "step": 286910 }, { "epoch": 1.7055120637694599, "grad_norm": 4.587122917175293, "learning_rate": 8.331350781767262e-06, "loss": 0.3435, "step": 286920 }, { "epoch": 1.7055715058461283, "grad_norm": 4.980489253997803, "learning_rate": 8.331196049850587e-06, "loss": 0.3356, "step": 286930 }, { "epoch": 1.7056309479227967, "grad_norm": 5.778034210205078, "learning_rate": 8.331041312197194e-06, "loss": 0.3581, "step": 286940 }, { "epoch": 1.7056903899994649, "grad_norm": 5.351917266845703, "learning_rate": 8.330886568807351e-06, "loss": 0.3373, "step": 286950 }, { "epoch": 1.7057498320761333, "grad_norm": 6.028048038482666, "learning_rate": 8.330731819681326e-06, "loss": 0.311, "step": 286960 }, { "epoch": 1.7058092741528017, "grad_norm": 4.1748504638671875, "learning_rate": 8.330577064819381e-06, "loss": 0.3579, "step": 286970 }, { "epoch": 1.7058687162294701, "grad_norm": 4.594092845916748, "learning_rate": 8.330422304221784e-06, "loss": 0.3202, "step": 286980 }, { "epoch": 1.7059281583061385, "grad_norm": 6.21909236907959, "learning_rate": 8.330267537888805e-06, "loss": 0.3271, "step": 286990 }, { "epoch": 1.705987600382807, "grad_norm": 5.12944221496582, "learning_rate": 8.330112765820705e-06, "loss": 0.2933, "step": 287000 }, { "epoch": 1.7060470424594754, "grad_norm": 5.587998390197754, "learning_rate": 8.329957988017757e-06, "loss": 0.3132, "step": 287010 }, { "epoch": 1.7061064845361438, "grad_norm": 3.96470046043396, "learning_rate": 8.329803204480222e-06, "loss": 0.2932, "step": 287020 }, { "epoch": 1.7061659266128122, "grad_norm": 4.5462727546691895, "learning_rate": 8.329648415208368e-06, "loss": 0.3613, "step": 287030 }, { "epoch": 1.7062253686894806, "grad_norm": 4.953509330749512, "learning_rate": 8.329493620202465e-06, "loss": 0.3044, "step": 287040 }, { "epoch": 1.706284810766149, "grad_norm": 3.9686472415924072, "learning_rate": 8.329338819462773e-06, "loss": 0.3558, "step": 287050 }, { "epoch": 1.7063442528428174, "grad_norm": 5.315100193023682, "learning_rate": 8.329184012989565e-06, "loss": 0.3119, "step": 287060 }, { "epoch": 1.7064036949194858, "grad_norm": 6.385828495025635, "learning_rate": 8.329029200783103e-06, "loss": 0.2982, "step": 287070 }, { "epoch": 1.7064631369961543, "grad_norm": 5.126317024230957, "learning_rate": 8.328874382843657e-06, "loss": 0.3363, "step": 287080 }, { "epoch": 1.7065225790728225, "grad_norm": 5.1877899169921875, "learning_rate": 8.328719559171491e-06, "loss": 0.3337, "step": 287090 }, { "epoch": 1.7065820211494909, "grad_norm": 5.84865665435791, "learning_rate": 8.328564729766872e-06, "loss": 0.3229, "step": 287100 }, { "epoch": 1.7066414632261593, "grad_norm": 5.433754920959473, "learning_rate": 8.328409894630069e-06, "loss": 0.3236, "step": 287110 }, { "epoch": 1.7067009053028277, "grad_norm": 5.9054388999938965, "learning_rate": 8.328255053761347e-06, "loss": 0.2731, "step": 287120 }, { "epoch": 1.706760347379496, "grad_norm": 4.094418525695801, "learning_rate": 8.328100207160973e-06, "loss": 0.2914, "step": 287130 }, { "epoch": 1.7068197894561643, "grad_norm": 5.7193121910095215, "learning_rate": 8.327945354829212e-06, "loss": 0.3358, "step": 287140 }, { "epoch": 1.7068792315328327, "grad_norm": 4.50007438659668, "learning_rate": 8.327790496766334e-06, "loss": 0.3385, "step": 287150 }, { "epoch": 1.7069386736095011, "grad_norm": 3.735935688018799, "learning_rate": 8.327635632972602e-06, "loss": 0.3154, "step": 287160 }, { "epoch": 1.7069981156861695, "grad_norm": 5.2446393966674805, "learning_rate": 8.327480763448283e-06, "loss": 0.3218, "step": 287170 }, { "epoch": 1.707057557762838, "grad_norm": 5.000779628753662, "learning_rate": 8.327325888193647e-06, "loss": 0.3509, "step": 287180 }, { "epoch": 1.7071169998395064, "grad_norm": 4.401078224182129, "learning_rate": 8.32717100720896e-06, "loss": 0.3143, "step": 287190 }, { "epoch": 1.7071764419161748, "grad_norm": 5.067668914794922, "learning_rate": 8.327016120494486e-06, "loss": 0.3059, "step": 287200 }, { "epoch": 1.7072358839928432, "grad_norm": 4.799567699432373, "learning_rate": 8.326861228050494e-06, "loss": 0.2996, "step": 287210 }, { "epoch": 1.7072953260695116, "grad_norm": 6.189117431640625, "learning_rate": 8.326706329877248e-06, "loss": 0.3101, "step": 287220 }, { "epoch": 1.70735476814618, "grad_norm": 5.381837844848633, "learning_rate": 8.326551425975019e-06, "loss": 0.2997, "step": 287230 }, { "epoch": 1.7074142102228484, "grad_norm": 4.7880730628967285, "learning_rate": 8.32639651634407e-06, "loss": 0.3246, "step": 287240 }, { "epoch": 1.7074736522995169, "grad_norm": 5.353309631347656, "learning_rate": 8.326241600984671e-06, "loss": 0.3043, "step": 287250 }, { "epoch": 1.7075330943761853, "grad_norm": 4.577975749969482, "learning_rate": 8.326086679897087e-06, "loss": 0.2888, "step": 287260 }, { "epoch": 1.7075925364528535, "grad_norm": 6.822198867797852, "learning_rate": 8.325931753081583e-06, "loss": 0.3018, "step": 287270 }, { "epoch": 1.7076519785295219, "grad_norm": 6.600842475891113, "learning_rate": 8.325776820538428e-06, "loss": 0.3773, "step": 287280 }, { "epoch": 1.7077114206061903, "grad_norm": 5.2682881355285645, "learning_rate": 8.32562188226789e-06, "loss": 0.3318, "step": 287290 }, { "epoch": 1.7077708626828587, "grad_norm": 5.741448879241943, "learning_rate": 8.325466938270234e-06, "loss": 0.3554, "step": 287300 }, { "epoch": 1.7078303047595271, "grad_norm": 4.865925312042236, "learning_rate": 8.325311988545725e-06, "loss": 0.3114, "step": 287310 }, { "epoch": 1.7078897468361953, "grad_norm": 4.604866981506348, "learning_rate": 8.325157033094635e-06, "loss": 0.3229, "step": 287320 }, { "epoch": 1.7079491889128637, "grad_norm": 5.5786452293396, "learning_rate": 8.325002071917227e-06, "loss": 0.3296, "step": 287330 }, { "epoch": 1.7080086309895322, "grad_norm": 7.255047798156738, "learning_rate": 8.324847105013766e-06, "loss": 0.3391, "step": 287340 }, { "epoch": 1.7080680730662006, "grad_norm": 4.732399940490723, "learning_rate": 8.324692132384524e-06, "loss": 0.322, "step": 287350 }, { "epoch": 1.708127515142869, "grad_norm": 5.666369915008545, "learning_rate": 8.324537154029766e-06, "loss": 0.2989, "step": 287360 }, { "epoch": 1.7081869572195374, "grad_norm": 5.5848069190979, "learning_rate": 8.324382169949758e-06, "loss": 0.3164, "step": 287370 }, { "epoch": 1.7082463992962058, "grad_norm": 5.147060394287109, "learning_rate": 8.324227180144766e-06, "loss": 0.3487, "step": 287380 }, { "epoch": 1.7083058413728742, "grad_norm": 5.77612829208374, "learning_rate": 8.32407218461506e-06, "loss": 0.3377, "step": 287390 }, { "epoch": 1.7083652834495426, "grad_norm": 4.45797872543335, "learning_rate": 8.323917183360903e-06, "loss": 0.3179, "step": 287400 }, { "epoch": 1.708424725526211, "grad_norm": 4.404750823974609, "learning_rate": 8.323762176382566e-06, "loss": 0.3063, "step": 287410 }, { "epoch": 1.7084841676028795, "grad_norm": 5.294768810272217, "learning_rate": 8.323607163680312e-06, "loss": 0.3192, "step": 287420 }, { "epoch": 1.7085436096795479, "grad_norm": 5.8030171394348145, "learning_rate": 8.323452145254412e-06, "loss": 0.3113, "step": 287430 }, { "epoch": 1.7086030517562163, "grad_norm": 4.6397318840026855, "learning_rate": 8.323297121105129e-06, "loss": 0.3068, "step": 287440 }, { "epoch": 1.7086624938328847, "grad_norm": 6.147792816162109, "learning_rate": 8.323142091232733e-06, "loss": 0.3263, "step": 287450 }, { "epoch": 1.708721935909553, "grad_norm": 6.145893096923828, "learning_rate": 8.322987055637489e-06, "loss": 0.3434, "step": 287460 }, { "epoch": 1.7087813779862213, "grad_norm": 4.028102874755859, "learning_rate": 8.322832014319665e-06, "loss": 0.3096, "step": 287470 }, { "epoch": 1.7088408200628897, "grad_norm": 4.630961894989014, "learning_rate": 8.322676967279528e-06, "loss": 0.3624, "step": 287480 }, { "epoch": 1.7089002621395581, "grad_norm": 5.790482997894287, "learning_rate": 8.322521914517346e-06, "loss": 0.2962, "step": 287490 }, { "epoch": 1.7089597042162263, "grad_norm": 5.951589584350586, "learning_rate": 8.322366856033381e-06, "loss": 0.3231, "step": 287500 }, { "epoch": 1.7090191462928948, "grad_norm": 4.68806791305542, "learning_rate": 8.322211791827908e-06, "loss": 0.2993, "step": 287510 }, { "epoch": 1.7090785883695632, "grad_norm": 5.275221347808838, "learning_rate": 8.322056721901188e-06, "loss": 0.3315, "step": 287520 }, { "epoch": 1.7091380304462316, "grad_norm": 5.08599328994751, "learning_rate": 8.32190164625349e-06, "loss": 0.3592, "step": 287530 }, { "epoch": 1.7091974725229, "grad_norm": 5.749359607696533, "learning_rate": 8.321746564885081e-06, "loss": 0.3108, "step": 287540 }, { "epoch": 1.7092569145995684, "grad_norm": 4.73422384262085, "learning_rate": 8.32159147779623e-06, "loss": 0.3545, "step": 287550 }, { "epoch": 1.7093163566762368, "grad_norm": 5.118271827697754, "learning_rate": 8.3214363849872e-06, "loss": 0.3262, "step": 287560 }, { "epoch": 1.7093757987529052, "grad_norm": 6.948041915893555, "learning_rate": 8.32128128645826e-06, "loss": 0.3054, "step": 287570 }, { "epoch": 1.7094352408295737, "grad_norm": 6.173730850219727, "learning_rate": 8.321126182209677e-06, "loss": 0.3416, "step": 287580 }, { "epoch": 1.709494682906242, "grad_norm": 5.930317401885986, "learning_rate": 8.320971072241722e-06, "loss": 0.331, "step": 287590 }, { "epoch": 1.7095541249829105, "grad_norm": 4.077592372894287, "learning_rate": 8.320815956554656e-06, "loss": 0.327, "step": 287600 }, { "epoch": 1.709613567059579, "grad_norm": 3.524355411529541, "learning_rate": 8.320660835148748e-06, "loss": 0.3592, "step": 287610 }, { "epoch": 1.7096730091362473, "grad_norm": 6.123580455780029, "learning_rate": 8.320505708024268e-06, "loss": 0.3181, "step": 287620 }, { "epoch": 1.7097324512129157, "grad_norm": 4.097419738769531, "learning_rate": 8.320350575181478e-06, "loss": 0.3051, "step": 287630 }, { "epoch": 1.709791893289584, "grad_norm": 5.897547721862793, "learning_rate": 8.32019543662065e-06, "loss": 0.3392, "step": 287640 }, { "epoch": 1.7098513353662523, "grad_norm": 4.093113899230957, "learning_rate": 8.320040292342049e-06, "loss": 0.3205, "step": 287650 }, { "epoch": 1.7099107774429207, "grad_norm": 4.210876941680908, "learning_rate": 8.319885142345942e-06, "loss": 0.2853, "step": 287660 }, { "epoch": 1.7099702195195892, "grad_norm": 6.479396343231201, "learning_rate": 8.319729986632598e-06, "loss": 0.3395, "step": 287670 }, { "epoch": 1.7100296615962576, "grad_norm": 5.765331745147705, "learning_rate": 8.319574825202282e-06, "loss": 0.3435, "step": 287680 }, { "epoch": 1.7100891036729258, "grad_norm": 4.32589054107666, "learning_rate": 8.31941965805526e-06, "loss": 0.3044, "step": 287690 }, { "epoch": 1.7101485457495942, "grad_norm": 4.841044902801514, "learning_rate": 8.319264485191805e-06, "loss": 0.3201, "step": 287700 }, { "epoch": 1.7102079878262626, "grad_norm": 4.876517295837402, "learning_rate": 8.319109306612179e-06, "loss": 0.3059, "step": 287710 }, { "epoch": 1.710267429902931, "grad_norm": 5.084802627563477, "learning_rate": 8.318954122316649e-06, "loss": 0.3468, "step": 287720 }, { "epoch": 1.7103268719795994, "grad_norm": 4.094510078430176, "learning_rate": 8.318798932305486e-06, "loss": 0.3181, "step": 287730 }, { "epoch": 1.7103863140562678, "grad_norm": 4.879949569702148, "learning_rate": 8.318643736578956e-06, "loss": 0.3429, "step": 287740 }, { "epoch": 1.7104457561329363, "grad_norm": 7.118128776550293, "learning_rate": 8.318488535137324e-06, "loss": 0.3262, "step": 287750 }, { "epoch": 1.7105051982096047, "grad_norm": 5.00057315826416, "learning_rate": 8.318333327980859e-06, "loss": 0.3322, "step": 287760 }, { "epoch": 1.710564640286273, "grad_norm": 4.39496374130249, "learning_rate": 8.318178115109827e-06, "loss": 0.34, "step": 287770 }, { "epoch": 1.7106240823629415, "grad_norm": 5.150950908660889, "learning_rate": 8.318022896524499e-06, "loss": 0.3479, "step": 287780 }, { "epoch": 1.71068352443961, "grad_norm": 5.472488880157471, "learning_rate": 8.317867672225137e-06, "loss": 0.3314, "step": 287790 }, { "epoch": 1.7107429665162783, "grad_norm": 3.7212910652160645, "learning_rate": 8.317712442212013e-06, "loss": 0.3168, "step": 287800 }, { "epoch": 1.7108024085929467, "grad_norm": 5.9341139793396, "learning_rate": 8.317557206485391e-06, "loss": 0.3504, "step": 287810 }, { "epoch": 1.7108618506696152, "grad_norm": 6.990475177764893, "learning_rate": 8.317401965045542e-06, "loss": 0.3009, "step": 287820 }, { "epoch": 1.7109212927462834, "grad_norm": 4.082180023193359, "learning_rate": 8.317246717892728e-06, "loss": 0.357, "step": 287830 }, { "epoch": 1.7109807348229518, "grad_norm": 3.9163546562194824, "learning_rate": 8.317091465027221e-06, "loss": 0.3191, "step": 287840 }, { "epoch": 1.7110401768996202, "grad_norm": 4.593971252441406, "learning_rate": 8.316936206449287e-06, "loss": 0.3183, "step": 287850 }, { "epoch": 1.7110996189762886, "grad_norm": 7.248312950134277, "learning_rate": 8.31678094215919e-06, "loss": 0.351, "step": 287860 }, { "epoch": 1.7111590610529568, "grad_norm": 4.108039855957031, "learning_rate": 8.316625672157204e-06, "loss": 0.3529, "step": 287870 }, { "epoch": 1.7112185031296252, "grad_norm": 4.7949628829956055, "learning_rate": 8.316470396443592e-06, "loss": 0.3261, "step": 287880 }, { "epoch": 1.7112779452062936, "grad_norm": 4.530508041381836, "learning_rate": 8.316315115018622e-06, "loss": 0.3465, "step": 287890 }, { "epoch": 1.711337387282962, "grad_norm": 4.30757999420166, "learning_rate": 8.316159827882562e-06, "loss": 0.3348, "step": 287900 }, { "epoch": 1.7113968293596304, "grad_norm": 3.8050758838653564, "learning_rate": 8.316004535035678e-06, "loss": 0.315, "step": 287910 }, { "epoch": 1.7114562714362989, "grad_norm": 7.006770610809326, "learning_rate": 8.31584923647824e-06, "loss": 0.3203, "step": 287920 }, { "epoch": 1.7115157135129673, "grad_norm": 5.0606231689453125, "learning_rate": 8.315693932210513e-06, "loss": 0.3265, "step": 287930 }, { "epoch": 1.7115751555896357, "grad_norm": 5.0566725730896, "learning_rate": 8.315538622232764e-06, "loss": 0.3231, "step": 287940 }, { "epoch": 1.711634597666304, "grad_norm": 6.850610256195068, "learning_rate": 8.315383306545264e-06, "loss": 0.3342, "step": 287950 }, { "epoch": 1.7116940397429725, "grad_norm": 4.753170967102051, "learning_rate": 8.315227985148278e-06, "loss": 0.3148, "step": 287960 }, { "epoch": 1.711753481819641, "grad_norm": 2.945007562637329, "learning_rate": 8.315072658042073e-06, "loss": 0.3169, "step": 287970 }, { "epoch": 1.7118129238963093, "grad_norm": 5.148588180541992, "learning_rate": 8.314917325226918e-06, "loss": 0.3378, "step": 287980 }, { "epoch": 1.7118723659729778, "grad_norm": 4.718253135681152, "learning_rate": 8.31476198670308e-06, "loss": 0.2893, "step": 287990 }, { "epoch": 1.7119318080496462, "grad_norm": 6.74943733215332, "learning_rate": 8.314606642470826e-06, "loss": 0.3124, "step": 288000 }, { "epoch": 1.7119912501263144, "grad_norm": 4.083735466003418, "learning_rate": 8.314451292530425e-06, "loss": 0.3209, "step": 288010 }, { "epoch": 1.7120506922029828, "grad_norm": 4.981467247009277, "learning_rate": 8.314295936882142e-06, "loss": 0.3181, "step": 288020 }, { "epoch": 1.7121101342796512, "grad_norm": 7.063474178314209, "learning_rate": 8.314140575526246e-06, "loss": 0.3359, "step": 288030 }, { "epoch": 1.7121695763563196, "grad_norm": 4.653003692626953, "learning_rate": 8.313985208463007e-06, "loss": 0.3377, "step": 288040 }, { "epoch": 1.712229018432988, "grad_norm": 5.625988960266113, "learning_rate": 8.313829835692686e-06, "loss": 0.3484, "step": 288050 }, { "epoch": 1.7122884605096562, "grad_norm": 5.407811164855957, "learning_rate": 8.313674457215558e-06, "loss": 0.3358, "step": 288060 }, { "epoch": 1.7123479025863246, "grad_norm": 4.737203598022461, "learning_rate": 8.313519073031885e-06, "loss": 0.2866, "step": 288070 }, { "epoch": 1.712407344662993, "grad_norm": 4.819262981414795, "learning_rate": 8.313363683141938e-06, "loss": 0.3354, "step": 288080 }, { "epoch": 1.7124667867396615, "grad_norm": 3.717176914215088, "learning_rate": 8.313208287545983e-06, "loss": 0.3054, "step": 288090 }, { "epoch": 1.7125262288163299, "grad_norm": 4.517704010009766, "learning_rate": 8.313052886244288e-06, "loss": 0.2993, "step": 288100 }, { "epoch": 1.7125856708929983, "grad_norm": 5.336744785308838, "learning_rate": 8.312897479237121e-06, "loss": 0.318, "step": 288110 }, { "epoch": 1.7126451129696667, "grad_norm": 4.590488910675049, "learning_rate": 8.312742066524749e-06, "loss": 0.3045, "step": 288120 }, { "epoch": 1.7127045550463351, "grad_norm": 4.403906345367432, "learning_rate": 8.31258664810744e-06, "loss": 0.358, "step": 288130 }, { "epoch": 1.7127639971230035, "grad_norm": 5.579864501953125, "learning_rate": 8.31243122398546e-06, "loss": 0.3308, "step": 288140 }, { "epoch": 1.712823439199672, "grad_norm": 5.302235126495361, "learning_rate": 8.312275794159079e-06, "loss": 0.3352, "step": 288150 }, { "epoch": 1.7128828812763404, "grad_norm": 5.026684284210205, "learning_rate": 8.312120358628565e-06, "loss": 0.3071, "step": 288160 }, { "epoch": 1.7129423233530088, "grad_norm": 4.8580803871154785, "learning_rate": 8.311964917394184e-06, "loss": 0.3471, "step": 288170 }, { "epoch": 1.7130017654296772, "grad_norm": 6.652805328369141, "learning_rate": 8.311809470456204e-06, "loss": 0.3081, "step": 288180 }, { "epoch": 1.7130612075063456, "grad_norm": 6.782504558563232, "learning_rate": 8.311654017814893e-06, "loss": 0.3445, "step": 288190 }, { "epoch": 1.7131206495830138, "grad_norm": 5.070336818695068, "learning_rate": 8.31149855947052e-06, "loss": 0.3096, "step": 288200 }, { "epoch": 1.7131800916596822, "grad_norm": 4.7843217849731445, "learning_rate": 8.31134309542335e-06, "loss": 0.3092, "step": 288210 }, { "epoch": 1.7132395337363506, "grad_norm": 4.921152591705322, "learning_rate": 8.311187625673652e-06, "loss": 0.3133, "step": 288220 }, { "epoch": 1.713298975813019, "grad_norm": 5.886902809143066, "learning_rate": 8.311032150221694e-06, "loss": 0.3277, "step": 288230 }, { "epoch": 1.7133584178896872, "grad_norm": 4.9872965812683105, "learning_rate": 8.310876669067742e-06, "loss": 0.3324, "step": 288240 }, { "epoch": 1.7134178599663556, "grad_norm": 4.7561211585998535, "learning_rate": 8.310721182212068e-06, "loss": 0.336, "step": 288250 }, { "epoch": 1.713477302043024, "grad_norm": 4.146040916442871, "learning_rate": 8.310565689654936e-06, "loss": 0.2909, "step": 288260 }, { "epoch": 1.7135367441196925, "grad_norm": 5.002764701843262, "learning_rate": 8.310410191396613e-06, "loss": 0.3122, "step": 288270 }, { "epoch": 1.713596186196361, "grad_norm": 5.99986457824707, "learning_rate": 8.310254687437371e-06, "loss": 0.3113, "step": 288280 }, { "epoch": 1.7136556282730293, "grad_norm": 4.578563213348389, "learning_rate": 8.310099177777475e-06, "loss": 0.2995, "step": 288290 }, { "epoch": 1.7137150703496977, "grad_norm": 4.469181537628174, "learning_rate": 8.309943662417194e-06, "loss": 0.3097, "step": 288300 }, { "epoch": 1.7137745124263661, "grad_norm": 7.131732940673828, "learning_rate": 8.309788141356794e-06, "loss": 0.3438, "step": 288310 }, { "epoch": 1.7138339545030346, "grad_norm": 5.302974700927734, "learning_rate": 8.309632614596546e-06, "loss": 0.3246, "step": 288320 }, { "epoch": 1.713893396579703, "grad_norm": 5.143283367156982, "learning_rate": 8.309477082136711e-06, "loss": 0.349, "step": 288330 }, { "epoch": 1.7139528386563714, "grad_norm": 4.3721818923950195, "learning_rate": 8.309321543977567e-06, "loss": 0.2999, "step": 288340 }, { "epoch": 1.7140122807330398, "grad_norm": 4.620985984802246, "learning_rate": 8.309166000119373e-06, "loss": 0.3653, "step": 288350 }, { "epoch": 1.7140717228097082, "grad_norm": 6.929314613342285, "learning_rate": 8.309010450562402e-06, "loss": 0.3204, "step": 288360 }, { "epoch": 1.7141311648863766, "grad_norm": 5.9540228843688965, "learning_rate": 8.308854895306919e-06, "loss": 0.3183, "step": 288370 }, { "epoch": 1.7141906069630448, "grad_norm": 4.709235191345215, "learning_rate": 8.308699334353192e-06, "loss": 0.3442, "step": 288380 }, { "epoch": 1.7142500490397132, "grad_norm": 6.819858551025391, "learning_rate": 8.308543767701493e-06, "loss": 0.3559, "step": 288390 }, { "epoch": 1.7143094911163816, "grad_norm": 4.295886993408203, "learning_rate": 8.308388195352085e-06, "loss": 0.2923, "step": 288400 }, { "epoch": 1.71436893319305, "grad_norm": 6.135361671447754, "learning_rate": 8.308232617305239e-06, "loss": 0.3263, "step": 288410 }, { "epoch": 1.7144283752697185, "grad_norm": 4.768213748931885, "learning_rate": 8.308077033561219e-06, "loss": 0.3117, "step": 288420 }, { "epoch": 1.7144878173463867, "grad_norm": 6.310304641723633, "learning_rate": 8.307921444120299e-06, "loss": 0.3406, "step": 288430 }, { "epoch": 1.714547259423055, "grad_norm": 4.506927013397217, "learning_rate": 8.307765848982742e-06, "loss": 0.3106, "step": 288440 }, { "epoch": 1.7146067014997235, "grad_norm": 3.334001064300537, "learning_rate": 8.307610248148818e-06, "loss": 0.3183, "step": 288450 }, { "epoch": 1.714666143576392, "grad_norm": 5.320619583129883, "learning_rate": 8.307454641618793e-06, "loss": 0.3121, "step": 288460 }, { "epoch": 1.7147255856530603, "grad_norm": 4.9861016273498535, "learning_rate": 8.307299029392938e-06, "loss": 0.3362, "step": 288470 }, { "epoch": 1.7147850277297287, "grad_norm": 6.042850494384766, "learning_rate": 8.30714341147152e-06, "loss": 0.3274, "step": 288480 }, { "epoch": 1.7148444698063972, "grad_norm": 6.164109706878662, "learning_rate": 8.306987787854804e-06, "loss": 0.319, "step": 288490 }, { "epoch": 1.7149039118830656, "grad_norm": 4.236633777618408, "learning_rate": 8.306832158543062e-06, "loss": 0.3262, "step": 288500 }, { "epoch": 1.714963353959734, "grad_norm": 4.057116985321045, "learning_rate": 8.30667652353656e-06, "loss": 0.3038, "step": 288510 }, { "epoch": 1.7150227960364024, "grad_norm": 5.711933612823486, "learning_rate": 8.306520882835567e-06, "loss": 0.3338, "step": 288520 }, { "epoch": 1.7150822381130708, "grad_norm": 5.974920749664307, "learning_rate": 8.30636523644035e-06, "loss": 0.3557, "step": 288530 }, { "epoch": 1.7151416801897392, "grad_norm": 5.496508598327637, "learning_rate": 8.30620958435118e-06, "loss": 0.3287, "step": 288540 }, { "epoch": 1.7152011222664076, "grad_norm": 5.3334879875183105, "learning_rate": 8.306053926568318e-06, "loss": 0.3261, "step": 288550 }, { "epoch": 1.715260564343076, "grad_norm": 6.000007152557373, "learning_rate": 8.30589826309204e-06, "loss": 0.3018, "step": 288560 }, { "epoch": 1.7153200064197442, "grad_norm": 5.751840114593506, "learning_rate": 8.30574259392261e-06, "loss": 0.3674, "step": 288570 }, { "epoch": 1.7153794484964127, "grad_norm": 4.076218605041504, "learning_rate": 8.305586919060296e-06, "loss": 0.3163, "step": 288580 }, { "epoch": 1.715438890573081, "grad_norm": 5.7718658447265625, "learning_rate": 8.305431238505369e-06, "loss": 0.2943, "step": 288590 }, { "epoch": 1.7154983326497495, "grad_norm": 4.051687717437744, "learning_rate": 8.305275552258092e-06, "loss": 0.344, "step": 288600 }, { "epoch": 1.7155577747264177, "grad_norm": 4.268828392028809, "learning_rate": 8.305119860318738e-06, "loss": 0.2894, "step": 288610 }, { "epoch": 1.715617216803086, "grad_norm": 4.14119815826416, "learning_rate": 8.304964162687574e-06, "loss": 0.3394, "step": 288620 }, { "epoch": 1.7156766588797545, "grad_norm": 4.552466869354248, "learning_rate": 8.304808459364865e-06, "loss": 0.3225, "step": 288630 }, { "epoch": 1.715736100956423, "grad_norm": 5.646022319793701, "learning_rate": 8.304652750350883e-06, "loss": 0.3424, "step": 288640 }, { "epoch": 1.7157955430330913, "grad_norm": 5.179969787597656, "learning_rate": 8.304497035645896e-06, "loss": 0.3081, "step": 288650 }, { "epoch": 1.7158549851097598, "grad_norm": 4.021819114685059, "learning_rate": 8.304341315250169e-06, "loss": 0.2974, "step": 288660 }, { "epoch": 1.7159144271864282, "grad_norm": 4.553660869598389, "learning_rate": 8.304185589163973e-06, "loss": 0.3534, "step": 288670 }, { "epoch": 1.7159738692630966, "grad_norm": 4.838250160217285, "learning_rate": 8.304029857387574e-06, "loss": 0.3095, "step": 288680 }, { "epoch": 1.716033311339765, "grad_norm": 5.680098533630371, "learning_rate": 8.303874119921243e-06, "loss": 0.3164, "step": 288690 }, { "epoch": 1.7160927534164334, "grad_norm": 5.146408557891846, "learning_rate": 8.303718376765245e-06, "loss": 0.3407, "step": 288700 }, { "epoch": 1.7161521954931018, "grad_norm": 5.443508625030518, "learning_rate": 8.30356262791985e-06, "loss": 0.3203, "step": 288710 }, { "epoch": 1.7162116375697702, "grad_norm": 5.510018348693848, "learning_rate": 8.303406873385325e-06, "loss": 0.3356, "step": 288720 }, { "epoch": 1.7162710796464387, "grad_norm": 5.596317768096924, "learning_rate": 8.303251113161941e-06, "loss": 0.2886, "step": 288730 }, { "epoch": 1.716330521723107, "grad_norm": 5.287601470947266, "learning_rate": 8.303095347249962e-06, "loss": 0.3538, "step": 288740 }, { "epoch": 1.7163899637997753, "grad_norm": 3.7211904525756836, "learning_rate": 8.302939575649662e-06, "loss": 0.3267, "step": 288750 }, { "epoch": 1.7164494058764437, "grad_norm": 6.835208415985107, "learning_rate": 8.302783798361304e-06, "loss": 0.3445, "step": 288760 }, { "epoch": 1.716508847953112, "grad_norm": 5.457718849182129, "learning_rate": 8.30262801538516e-06, "loss": 0.3509, "step": 288770 }, { "epoch": 1.7165682900297805, "grad_norm": 4.861515045166016, "learning_rate": 8.302472226721495e-06, "loss": 0.2965, "step": 288780 }, { "epoch": 1.716627732106449, "grad_norm": 6.1656365394592285, "learning_rate": 8.302316432370579e-06, "loss": 0.3159, "step": 288790 }, { "epoch": 1.7166871741831171, "grad_norm": 6.174569129943848, "learning_rate": 8.30216063233268e-06, "loss": 0.3194, "step": 288800 }, { "epoch": 1.7167466162597855, "grad_norm": 5.24476957321167, "learning_rate": 8.302004826608066e-06, "loss": 0.3471, "step": 288810 }, { "epoch": 1.716806058336454, "grad_norm": 5.699140548706055, "learning_rate": 8.301849015197006e-06, "loss": 0.323, "step": 288820 }, { "epoch": 1.7168655004131224, "grad_norm": 5.306554794311523, "learning_rate": 8.301693198099768e-06, "loss": 0.3288, "step": 288830 }, { "epoch": 1.7169249424897908, "grad_norm": 5.4068379402160645, "learning_rate": 8.301537375316619e-06, "loss": 0.3378, "step": 288840 }, { "epoch": 1.7169843845664592, "grad_norm": 4.6094746589660645, "learning_rate": 8.301381546847831e-06, "loss": 0.3371, "step": 288850 }, { "epoch": 1.7170438266431276, "grad_norm": 5.477540016174316, "learning_rate": 8.30122571269367e-06, "loss": 0.3079, "step": 288860 }, { "epoch": 1.717103268719796, "grad_norm": 4.368564605712891, "learning_rate": 8.301069872854404e-06, "loss": 0.3277, "step": 288870 }, { "epoch": 1.7171627107964644, "grad_norm": 4.224676609039307, "learning_rate": 8.3009140273303e-06, "loss": 0.3066, "step": 288880 }, { "epoch": 1.7172221528731328, "grad_norm": 5.85460090637207, "learning_rate": 8.30075817612163e-06, "loss": 0.324, "step": 288890 }, { "epoch": 1.7172815949498013, "grad_norm": 4.61497688293457, "learning_rate": 8.300602319228661e-06, "loss": 0.2869, "step": 288900 }, { "epoch": 1.7173410370264697, "grad_norm": 5.036218643188477, "learning_rate": 8.30044645665166e-06, "loss": 0.3524, "step": 288910 }, { "epoch": 1.717400479103138, "grad_norm": 6.195979118347168, "learning_rate": 8.300290588390897e-06, "loss": 0.336, "step": 288920 }, { "epoch": 1.7174599211798065, "grad_norm": 4.10758638381958, "learning_rate": 8.30013471444664e-06, "loss": 0.306, "step": 288930 }, { "epoch": 1.7175193632564747, "grad_norm": 4.306551933288574, "learning_rate": 8.299978834819156e-06, "loss": 0.3136, "step": 288940 }, { "epoch": 1.717578805333143, "grad_norm": 4.789648532867432, "learning_rate": 8.299822949508716e-06, "loss": 0.3334, "step": 288950 }, { "epoch": 1.7176382474098115, "grad_norm": 6.148641586303711, "learning_rate": 8.299667058515586e-06, "loss": 0.3183, "step": 288960 }, { "epoch": 1.71769768948648, "grad_norm": 5.488863945007324, "learning_rate": 8.299511161840037e-06, "loss": 0.333, "step": 288970 }, { "epoch": 1.7177571315631481, "grad_norm": 5.048559188842773, "learning_rate": 8.299355259482334e-06, "loss": 0.3186, "step": 288980 }, { "epoch": 1.7178165736398165, "grad_norm": 5.007978439331055, "learning_rate": 8.299199351442747e-06, "loss": 0.307, "step": 288990 }, { "epoch": 1.717876015716485, "grad_norm": 3.802999973297119, "learning_rate": 8.29904343772155e-06, "loss": 0.3354, "step": 289000 }, { "epoch": 1.7179354577931534, "grad_norm": 4.8716630935668945, "learning_rate": 8.298887518319004e-06, "loss": 0.3005, "step": 289010 }, { "epoch": 1.7179948998698218, "grad_norm": 4.994833946228027, "learning_rate": 8.298731593235378e-06, "loss": 0.3144, "step": 289020 }, { "epoch": 1.7180543419464902, "grad_norm": 5.454105377197266, "learning_rate": 8.298575662470945e-06, "loss": 0.2985, "step": 289030 }, { "epoch": 1.7181137840231586, "grad_norm": 4.808834552764893, "learning_rate": 8.29841972602597e-06, "loss": 0.333, "step": 289040 }, { "epoch": 1.718173226099827, "grad_norm": 4.62263822555542, "learning_rate": 8.298263783900722e-06, "loss": 0.3061, "step": 289050 }, { "epoch": 1.7182326681764954, "grad_norm": 4.871665954589844, "learning_rate": 8.298107836095472e-06, "loss": 0.3216, "step": 289060 }, { "epoch": 1.7182921102531639, "grad_norm": 4.962937831878662, "learning_rate": 8.297951882610484e-06, "loss": 0.2706, "step": 289070 }, { "epoch": 1.7183515523298323, "grad_norm": 4.458853244781494, "learning_rate": 8.297795923446032e-06, "loss": 0.3221, "step": 289080 }, { "epoch": 1.7184109944065007, "grad_norm": 5.102402687072754, "learning_rate": 8.297639958602382e-06, "loss": 0.3467, "step": 289090 }, { "epoch": 1.718470436483169, "grad_norm": 4.8662519454956055, "learning_rate": 8.297483988079801e-06, "loss": 0.3164, "step": 289100 }, { "epoch": 1.7185298785598375, "grad_norm": 5.679056644439697, "learning_rate": 8.29732801187856e-06, "loss": 0.2924, "step": 289110 }, { "epoch": 1.7185893206365057, "grad_norm": 4.412486553192139, "learning_rate": 8.297172029998928e-06, "loss": 0.3537, "step": 289120 }, { "epoch": 1.7186487627131741, "grad_norm": 6.120370388031006, "learning_rate": 8.297016042441171e-06, "loss": 0.3322, "step": 289130 }, { "epoch": 1.7187082047898425, "grad_norm": 5.653064727783203, "learning_rate": 8.29686004920556e-06, "loss": 0.3304, "step": 289140 }, { "epoch": 1.718767646866511, "grad_norm": 6.273892879486084, "learning_rate": 8.296704050292358e-06, "loss": 0.2827, "step": 289150 }, { "epoch": 1.7188270889431794, "grad_norm": 4.399934768676758, "learning_rate": 8.296548045701843e-06, "loss": 0.3267, "step": 289160 }, { "epoch": 1.7188865310198476, "grad_norm": 6.1258673667907715, "learning_rate": 8.296392035434277e-06, "loss": 0.3264, "step": 289170 }, { "epoch": 1.718945973096516, "grad_norm": 4.724178791046143, "learning_rate": 8.296236019489932e-06, "loss": 0.2855, "step": 289180 }, { "epoch": 1.7190054151731844, "grad_norm": 5.934378147125244, "learning_rate": 8.296079997869076e-06, "loss": 0.3167, "step": 289190 }, { "epoch": 1.7190648572498528, "grad_norm": 4.764760971069336, "learning_rate": 8.295923970571975e-06, "loss": 0.3282, "step": 289200 }, { "epoch": 1.7191242993265212, "grad_norm": 4.7538981437683105, "learning_rate": 8.2957679375989e-06, "loss": 0.2916, "step": 289210 }, { "epoch": 1.7191837414031896, "grad_norm": 4.94854736328125, "learning_rate": 8.29561189895012e-06, "loss": 0.347, "step": 289220 }, { "epoch": 1.719243183479858, "grad_norm": 5.922868251800537, "learning_rate": 8.295455854625902e-06, "loss": 0.316, "step": 289230 }, { "epoch": 1.7193026255565265, "grad_norm": 6.3208842277526855, "learning_rate": 8.295299804626518e-06, "loss": 0.3637, "step": 289240 }, { "epoch": 1.7193620676331949, "grad_norm": 4.861375331878662, "learning_rate": 8.295143748952233e-06, "loss": 0.3191, "step": 289250 }, { "epoch": 1.7194215097098633, "grad_norm": 4.88834810256958, "learning_rate": 8.294987687603317e-06, "loss": 0.3194, "step": 289260 }, { "epoch": 1.7194809517865317, "grad_norm": 5.274259567260742, "learning_rate": 8.294831620580038e-06, "loss": 0.3151, "step": 289270 }, { "epoch": 1.7195403938632001, "grad_norm": 5.441020965576172, "learning_rate": 8.294675547882668e-06, "loss": 0.3275, "step": 289280 }, { "epoch": 1.7195998359398685, "grad_norm": 4.461367130279541, "learning_rate": 8.294519469511473e-06, "loss": 0.2953, "step": 289290 }, { "epoch": 1.719659278016537, "grad_norm": 6.133481979370117, "learning_rate": 8.294363385466722e-06, "loss": 0.2964, "step": 289300 }, { "epoch": 1.7197187200932051, "grad_norm": 5.356837749481201, "learning_rate": 8.294207295748684e-06, "loss": 0.3036, "step": 289310 }, { "epoch": 1.7197781621698736, "grad_norm": 5.368215084075928, "learning_rate": 8.294051200357629e-06, "loss": 0.3094, "step": 289320 }, { "epoch": 1.719837604246542, "grad_norm": 4.243043899536133, "learning_rate": 8.293895099293823e-06, "loss": 0.3345, "step": 289330 }, { "epoch": 1.7198970463232104, "grad_norm": 3.5781595706939697, "learning_rate": 8.293738992557538e-06, "loss": 0.326, "step": 289340 }, { "epoch": 1.7199564883998786, "grad_norm": 4.20126485824585, "learning_rate": 8.293582880149042e-06, "loss": 0.3434, "step": 289350 }, { "epoch": 1.720015930476547, "grad_norm": 5.244731426239014, "learning_rate": 8.293426762068602e-06, "loss": 0.3275, "step": 289360 }, { "epoch": 1.7200753725532154, "grad_norm": 5.2873311042785645, "learning_rate": 8.293270638316489e-06, "loss": 0.2789, "step": 289370 }, { "epoch": 1.7201348146298838, "grad_norm": 6.207695484161377, "learning_rate": 8.29311450889297e-06, "loss": 0.3505, "step": 289380 }, { "epoch": 1.7201942567065522, "grad_norm": 5.086358547210693, "learning_rate": 8.292958373798316e-06, "loss": 0.3117, "step": 289390 }, { "epoch": 1.7202536987832207, "grad_norm": 5.14789342880249, "learning_rate": 8.292802233032796e-06, "loss": 0.3175, "step": 289400 }, { "epoch": 1.720313140859889, "grad_norm": 5.180290699005127, "learning_rate": 8.292646086596674e-06, "loss": 0.3087, "step": 289410 }, { "epoch": 1.7203725829365575, "grad_norm": 4.292630672454834, "learning_rate": 8.292489934490226e-06, "loss": 0.3199, "step": 289420 }, { "epoch": 1.720432025013226, "grad_norm": 5.547852516174316, "learning_rate": 8.292333776713714e-06, "loss": 0.3248, "step": 289430 }, { "epoch": 1.7204914670898943, "grad_norm": 6.64719295501709, "learning_rate": 8.292177613267414e-06, "loss": 0.3659, "step": 289440 }, { "epoch": 1.7205509091665627, "grad_norm": 5.042877197265625, "learning_rate": 8.29202144415159e-06, "loss": 0.3003, "step": 289450 }, { "epoch": 1.7206103512432311, "grad_norm": 4.398794174194336, "learning_rate": 8.291865269366511e-06, "loss": 0.3285, "step": 289460 }, { "epoch": 1.7206697933198996, "grad_norm": 5.167571067810059, "learning_rate": 8.291709088912449e-06, "loss": 0.3226, "step": 289470 }, { "epoch": 1.720729235396568, "grad_norm": 4.798023700714111, "learning_rate": 8.291552902789671e-06, "loss": 0.3323, "step": 289480 }, { "epoch": 1.7207886774732362, "grad_norm": 5.39276123046875, "learning_rate": 8.291396710998445e-06, "loss": 0.3052, "step": 289490 }, { "epoch": 1.7208481195499046, "grad_norm": 4.638185501098633, "learning_rate": 8.291240513539041e-06, "loss": 0.3309, "step": 289500 }, { "epoch": 1.720907561626573, "grad_norm": 4.3399152755737305, "learning_rate": 8.29108431041173e-06, "loss": 0.3196, "step": 289510 }, { "epoch": 1.7209670037032414, "grad_norm": 4.425207614898682, "learning_rate": 8.290928101616778e-06, "loss": 0.2685, "step": 289520 }, { "epoch": 1.7210264457799098, "grad_norm": 5.794168949127197, "learning_rate": 8.290771887154454e-06, "loss": 0.3298, "step": 289530 }, { "epoch": 1.721085887856578, "grad_norm": 5.975149154663086, "learning_rate": 8.29061566702503e-06, "loss": 0.3084, "step": 289540 }, { "epoch": 1.7211453299332464, "grad_norm": 4.98551607131958, "learning_rate": 8.290459441228774e-06, "loss": 0.3274, "step": 289550 }, { "epoch": 1.7212047720099148, "grad_norm": 5.9886345863342285, "learning_rate": 8.29030320976595e-06, "loss": 0.3096, "step": 289560 }, { "epoch": 1.7212642140865833, "grad_norm": 4.935058116912842, "learning_rate": 8.290146972636835e-06, "loss": 0.3513, "step": 289570 }, { "epoch": 1.7213236561632517, "grad_norm": 5.9185686111450195, "learning_rate": 8.289990729841695e-06, "loss": 0.334, "step": 289580 }, { "epoch": 1.72138309823992, "grad_norm": 5.707134246826172, "learning_rate": 8.289834481380795e-06, "loss": 0.3197, "step": 289590 }, { "epoch": 1.7214425403165885, "grad_norm": 5.614477157592773, "learning_rate": 8.28967822725441e-06, "loss": 0.312, "step": 289600 }, { "epoch": 1.721501982393257, "grad_norm": 4.621911525726318, "learning_rate": 8.289521967462806e-06, "loss": 0.3163, "step": 289610 }, { "epoch": 1.7215614244699253, "grad_norm": 5.767082214355469, "learning_rate": 8.289365702006253e-06, "loss": 0.2936, "step": 289620 }, { "epoch": 1.7216208665465937, "grad_norm": 3.866086006164551, "learning_rate": 8.28920943088502e-06, "loss": 0.2889, "step": 289630 }, { "epoch": 1.7216803086232622, "grad_norm": 6.682137489318848, "learning_rate": 8.289053154099374e-06, "loss": 0.3149, "step": 289640 }, { "epoch": 1.7217397506999306, "grad_norm": 5.8300371170043945, "learning_rate": 8.288896871649588e-06, "loss": 0.3336, "step": 289650 }, { "epoch": 1.721799192776599, "grad_norm": 4.256688594818115, "learning_rate": 8.288740583535927e-06, "loss": 0.3139, "step": 289660 }, { "epoch": 1.7218586348532674, "grad_norm": 4.438606262207031, "learning_rate": 8.288584289758663e-06, "loss": 0.3201, "step": 289670 }, { "epoch": 1.7219180769299356, "grad_norm": 6.587610721588135, "learning_rate": 8.288427990318066e-06, "loss": 0.3605, "step": 289680 }, { "epoch": 1.721977519006604, "grad_norm": 4.827579975128174, "learning_rate": 8.288271685214403e-06, "loss": 0.3044, "step": 289690 }, { "epoch": 1.7220369610832724, "grad_norm": 4.027151107788086, "learning_rate": 8.288115374447942e-06, "loss": 0.2994, "step": 289700 }, { "epoch": 1.7220964031599408, "grad_norm": 4.871821403503418, "learning_rate": 8.287959058018957e-06, "loss": 0.3035, "step": 289710 }, { "epoch": 1.722155845236609, "grad_norm": 4.069499492645264, "learning_rate": 8.287802735927713e-06, "loss": 0.3168, "step": 289720 }, { "epoch": 1.7222152873132774, "grad_norm": 4.542705535888672, "learning_rate": 8.28764640817448e-06, "loss": 0.2933, "step": 289730 }, { "epoch": 1.7222747293899459, "grad_norm": 6.465901851654053, "learning_rate": 8.287490074759527e-06, "loss": 0.3856, "step": 289740 }, { "epoch": 1.7223341714666143, "grad_norm": 4.923088073730469, "learning_rate": 8.287333735683126e-06, "loss": 0.3239, "step": 289750 }, { "epoch": 1.7223936135432827, "grad_norm": 4.79508113861084, "learning_rate": 8.287177390945542e-06, "loss": 0.3001, "step": 289760 }, { "epoch": 1.722453055619951, "grad_norm": 4.889365196228027, "learning_rate": 8.287021040547048e-06, "loss": 0.3158, "step": 289770 }, { "epoch": 1.7225124976966195, "grad_norm": 4.526858806610107, "learning_rate": 8.28686468448791e-06, "loss": 0.3042, "step": 289780 }, { "epoch": 1.722571939773288, "grad_norm": 5.159313678741455, "learning_rate": 8.2867083227684e-06, "loss": 0.3584, "step": 289790 }, { "epoch": 1.7226313818499563, "grad_norm": 6.500898838043213, "learning_rate": 8.286551955388784e-06, "loss": 0.3187, "step": 289800 }, { "epoch": 1.7226908239266248, "grad_norm": 7.390066623687744, "learning_rate": 8.286395582349336e-06, "loss": 0.3272, "step": 289810 }, { "epoch": 1.7227502660032932, "grad_norm": 5.862948894500732, "learning_rate": 8.286239203650321e-06, "loss": 0.3244, "step": 289820 }, { "epoch": 1.7228097080799616, "grad_norm": 5.042474269866943, "learning_rate": 8.286082819292011e-06, "loss": 0.3415, "step": 289830 }, { "epoch": 1.72286915015663, "grad_norm": 4.310596942901611, "learning_rate": 8.285926429274674e-06, "loss": 0.3139, "step": 289840 }, { "epoch": 1.7229285922332984, "grad_norm": 5.364680290222168, "learning_rate": 8.285770033598579e-06, "loss": 0.2903, "step": 289850 }, { "epoch": 1.7229880343099666, "grad_norm": 5.008967399597168, "learning_rate": 8.285613632263996e-06, "loss": 0.3321, "step": 289860 }, { "epoch": 1.723047476386635, "grad_norm": 5.569101810455322, "learning_rate": 8.285457225271195e-06, "loss": 0.3331, "step": 289870 }, { "epoch": 1.7231069184633034, "grad_norm": 5.598202228546143, "learning_rate": 8.285300812620445e-06, "loss": 0.3379, "step": 289880 }, { "epoch": 1.7231663605399719, "grad_norm": 6.475419521331787, "learning_rate": 8.285144394312014e-06, "loss": 0.3519, "step": 289890 }, { "epoch": 1.7232258026166403, "grad_norm": 4.1052565574646, "learning_rate": 8.284987970346173e-06, "loss": 0.2926, "step": 289900 }, { "epoch": 1.7232852446933085, "grad_norm": 5.199034214019775, "learning_rate": 8.284831540723191e-06, "loss": 0.3282, "step": 289910 }, { "epoch": 1.7233446867699769, "grad_norm": 4.626508712768555, "learning_rate": 8.284675105443336e-06, "loss": 0.3091, "step": 289920 }, { "epoch": 1.7234041288466453, "grad_norm": 6.715545177459717, "learning_rate": 8.284518664506877e-06, "loss": 0.2986, "step": 289930 }, { "epoch": 1.7234635709233137, "grad_norm": 4.671605110168457, "learning_rate": 8.284362217914089e-06, "loss": 0.3071, "step": 289940 }, { "epoch": 1.7235230129999821, "grad_norm": 3.7068657875061035, "learning_rate": 8.284205765665236e-06, "loss": 0.3214, "step": 289950 }, { "epoch": 1.7235824550766505, "grad_norm": 5.249070644378662, "learning_rate": 8.284049307760588e-06, "loss": 0.3391, "step": 289960 }, { "epoch": 1.723641897153319, "grad_norm": 4.608241081237793, "learning_rate": 8.283892844200415e-06, "loss": 0.2899, "step": 289970 }, { "epoch": 1.7237013392299874, "grad_norm": 6.0507893562316895, "learning_rate": 8.283736374984988e-06, "loss": 0.3314, "step": 289980 }, { "epoch": 1.7237607813066558, "grad_norm": 6.178908348083496, "learning_rate": 8.283579900114575e-06, "loss": 0.316, "step": 289990 }, { "epoch": 1.7238202233833242, "grad_norm": 5.079111099243164, "learning_rate": 8.283423419589445e-06, "loss": 0.2892, "step": 290000 }, { "epoch": 1.7238796654599926, "grad_norm": 4.683163642883301, "learning_rate": 8.283266933409868e-06, "loss": 0.3346, "step": 290010 }, { "epoch": 1.723939107536661, "grad_norm": 4.387166976928711, "learning_rate": 8.283110441576113e-06, "loss": 0.3171, "step": 290020 }, { "epoch": 1.7239985496133294, "grad_norm": 4.602876663208008, "learning_rate": 8.28295394408845e-06, "loss": 0.317, "step": 290030 }, { "epoch": 1.7240579916899976, "grad_norm": 4.591170310974121, "learning_rate": 8.28279744094715e-06, "loss": 0.3567, "step": 290040 }, { "epoch": 1.724117433766666, "grad_norm": 6.522747039794922, "learning_rate": 8.282640932152481e-06, "loss": 0.3494, "step": 290050 }, { "epoch": 1.7241768758433345, "grad_norm": 5.094311714172363, "learning_rate": 8.282484417704712e-06, "loss": 0.2916, "step": 290060 }, { "epoch": 1.7242363179200029, "grad_norm": 4.657101154327393, "learning_rate": 8.282327897604113e-06, "loss": 0.3133, "step": 290070 }, { "epoch": 1.7242957599966713, "grad_norm": 5.919622421264648, "learning_rate": 8.282171371850953e-06, "loss": 0.3529, "step": 290080 }, { "epoch": 1.7243552020733395, "grad_norm": 6.521193027496338, "learning_rate": 8.282014840445506e-06, "loss": 0.3343, "step": 290090 }, { "epoch": 1.724414644150008, "grad_norm": 5.539138317108154, "learning_rate": 8.281858303388035e-06, "loss": 0.3246, "step": 290100 }, { "epoch": 1.7244740862266763, "grad_norm": 4.429687976837158, "learning_rate": 8.28170176067881e-06, "loss": 0.3307, "step": 290110 }, { "epoch": 1.7245335283033447, "grad_norm": 5.004642009735107, "learning_rate": 8.281545212318107e-06, "loss": 0.3574, "step": 290120 }, { "epoch": 1.7245929703800131, "grad_norm": 3.8237805366516113, "learning_rate": 8.28138865830619e-06, "loss": 0.2958, "step": 290130 }, { "epoch": 1.7246524124566815, "grad_norm": 3.694972276687622, "learning_rate": 8.28123209864333e-06, "loss": 0.3269, "step": 290140 }, { "epoch": 1.72471185453335, "grad_norm": 3.9970500469207764, "learning_rate": 8.281075533329797e-06, "loss": 0.2999, "step": 290150 }, { "epoch": 1.7247712966100184, "grad_norm": 4.562115669250488, "learning_rate": 8.28091896236586e-06, "loss": 0.3169, "step": 290160 }, { "epoch": 1.7248307386866868, "grad_norm": 5.82737922668457, "learning_rate": 8.28076238575179e-06, "loss": 0.3311, "step": 290170 }, { "epoch": 1.7248901807633552, "grad_norm": 3.939129114151001, "learning_rate": 8.280605803487856e-06, "loss": 0.3227, "step": 290180 }, { "epoch": 1.7249496228400236, "grad_norm": 6.515475749969482, "learning_rate": 8.280449215574327e-06, "loss": 0.3202, "step": 290190 }, { "epoch": 1.725009064916692, "grad_norm": 4.381670951843262, "learning_rate": 8.280292622011473e-06, "loss": 0.3332, "step": 290200 }, { "epoch": 1.7250685069933605, "grad_norm": 4.866070747375488, "learning_rate": 8.280136022799563e-06, "loss": 0.3033, "step": 290210 }, { "epoch": 1.7251279490700289, "grad_norm": 4.850962162017822, "learning_rate": 8.279979417938868e-06, "loss": 0.3632, "step": 290220 }, { "epoch": 1.725187391146697, "grad_norm": 4.80982780456543, "learning_rate": 8.279822807429658e-06, "loss": 0.3211, "step": 290230 }, { "epoch": 1.7252468332233655, "grad_norm": 5.643202304840088, "learning_rate": 8.2796661912722e-06, "loss": 0.33, "step": 290240 }, { "epoch": 1.7253062753000339, "grad_norm": 6.89453125, "learning_rate": 8.279509569466766e-06, "loss": 0.3642, "step": 290250 }, { "epoch": 1.7253657173767023, "grad_norm": 5.84696626663208, "learning_rate": 8.279352942013626e-06, "loss": 0.3096, "step": 290260 }, { "epoch": 1.7254251594533707, "grad_norm": 4.186290264129639, "learning_rate": 8.279196308913047e-06, "loss": 0.3337, "step": 290270 }, { "epoch": 1.725484601530039, "grad_norm": 6.284195423126221, "learning_rate": 8.279039670165304e-06, "loss": 0.3259, "step": 290280 }, { "epoch": 1.7255440436067073, "grad_norm": 5.0497050285339355, "learning_rate": 8.27888302577066e-06, "loss": 0.3267, "step": 290290 }, { "epoch": 1.7256034856833757, "grad_norm": 5.5782670974731445, "learning_rate": 8.27872637572939e-06, "loss": 0.3292, "step": 290300 }, { "epoch": 1.7256629277600442, "grad_norm": 4.144867420196533, "learning_rate": 8.278569720041762e-06, "loss": 0.3384, "step": 290310 }, { "epoch": 1.7257223698367126, "grad_norm": 6.929663181304932, "learning_rate": 8.278413058708046e-06, "loss": 0.3625, "step": 290320 }, { "epoch": 1.725781811913381, "grad_norm": 4.597139835357666, "learning_rate": 8.278256391728513e-06, "loss": 0.3082, "step": 290330 }, { "epoch": 1.7258412539900494, "grad_norm": 5.14380407333374, "learning_rate": 8.278099719103427e-06, "loss": 0.2913, "step": 290340 }, { "epoch": 1.7259006960667178, "grad_norm": 6.133173942565918, "learning_rate": 8.277943040833065e-06, "loss": 0.3347, "step": 290350 }, { "epoch": 1.7259601381433862, "grad_norm": 5.913848400115967, "learning_rate": 8.277786356917694e-06, "loss": 0.3194, "step": 290360 }, { "epoch": 1.7260195802200546, "grad_norm": 5.845767974853516, "learning_rate": 8.277629667357582e-06, "loss": 0.3545, "step": 290370 }, { "epoch": 1.726079022296723, "grad_norm": 5.425771713256836, "learning_rate": 8.277472972153002e-06, "loss": 0.3171, "step": 290380 }, { "epoch": 1.7261384643733915, "grad_norm": 4.469618797302246, "learning_rate": 8.277316271304223e-06, "loss": 0.3194, "step": 290390 }, { "epoch": 1.7261979064500599, "grad_norm": 3.1953539848327637, "learning_rate": 8.277159564811514e-06, "loss": 0.2996, "step": 290400 }, { "epoch": 1.726257348526728, "grad_norm": 4.416511058807373, "learning_rate": 8.277002852675145e-06, "loss": 0.3428, "step": 290410 }, { "epoch": 1.7263167906033965, "grad_norm": 4.878419876098633, "learning_rate": 8.276846134895387e-06, "loss": 0.3169, "step": 290420 }, { "epoch": 1.726376232680065, "grad_norm": 4.743175983428955, "learning_rate": 8.276689411472507e-06, "loss": 0.343, "step": 290430 }, { "epoch": 1.7264356747567333, "grad_norm": 5.914637088775635, "learning_rate": 8.276532682406778e-06, "loss": 0.3379, "step": 290440 }, { "epoch": 1.7264951168334017, "grad_norm": 6.095001697540283, "learning_rate": 8.276375947698469e-06, "loss": 0.3228, "step": 290450 }, { "epoch": 1.72655455891007, "grad_norm": 5.022485256195068, "learning_rate": 8.276219207347849e-06, "loss": 0.328, "step": 290460 }, { "epoch": 1.7266140009867383, "grad_norm": 5.904683589935303, "learning_rate": 8.276062461355188e-06, "loss": 0.3102, "step": 290470 }, { "epoch": 1.7266734430634068, "grad_norm": 5.17781400680542, "learning_rate": 8.275905709720757e-06, "loss": 0.3285, "step": 290480 }, { "epoch": 1.7267328851400752, "grad_norm": 4.179851531982422, "learning_rate": 8.275748952444826e-06, "loss": 0.3025, "step": 290490 }, { "epoch": 1.7267923272167436, "grad_norm": 5.593169689178467, "learning_rate": 8.275592189527666e-06, "loss": 0.3043, "step": 290500 }, { "epoch": 1.726851769293412, "grad_norm": 4.20817232131958, "learning_rate": 8.275435420969545e-06, "loss": 0.3066, "step": 290510 }, { "epoch": 1.7269112113700804, "grad_norm": 5.497282028198242, "learning_rate": 8.27527864677073e-06, "loss": 0.3293, "step": 290520 }, { "epoch": 1.7269706534467488, "grad_norm": 5.705191612243652, "learning_rate": 8.275121866931497e-06, "loss": 0.3241, "step": 290530 }, { "epoch": 1.7270300955234172, "grad_norm": 6.1238017082214355, "learning_rate": 8.274965081452113e-06, "loss": 0.3209, "step": 290540 }, { "epoch": 1.7270895376000857, "grad_norm": 4.628628253936768, "learning_rate": 8.27480829033285e-06, "loss": 0.3123, "step": 290550 }, { "epoch": 1.727148979676754, "grad_norm": 3.936666488647461, "learning_rate": 8.274651493573972e-06, "loss": 0.2865, "step": 290560 }, { "epoch": 1.7272084217534225, "grad_norm": 4.116259574890137, "learning_rate": 8.274494691175758e-06, "loss": 0.3015, "step": 290570 }, { "epoch": 1.727267863830091, "grad_norm": 7.037785530090332, "learning_rate": 8.27433788313847e-06, "loss": 0.3114, "step": 290580 }, { "epoch": 1.7273273059067593, "grad_norm": 4.752624034881592, "learning_rate": 8.274181069462384e-06, "loss": 0.334, "step": 290590 }, { "epoch": 1.7273867479834275, "grad_norm": 6.445151329040527, "learning_rate": 8.274024250147767e-06, "loss": 0.3159, "step": 290600 }, { "epoch": 1.727446190060096, "grad_norm": 4.918718338012695, "learning_rate": 8.273867425194888e-06, "loss": 0.3519, "step": 290610 }, { "epoch": 1.7275056321367643, "grad_norm": 6.328521728515625, "learning_rate": 8.273710594604021e-06, "loss": 0.3178, "step": 290620 }, { "epoch": 1.7275650742134327, "grad_norm": 4.729687690734863, "learning_rate": 8.273553758375433e-06, "loss": 0.2905, "step": 290630 }, { "epoch": 1.7276245162901012, "grad_norm": 6.135591506958008, "learning_rate": 8.273396916509393e-06, "loss": 0.3106, "step": 290640 }, { "epoch": 1.7276839583667694, "grad_norm": 4.029583930969238, "learning_rate": 8.273240069006175e-06, "loss": 0.326, "step": 290650 }, { "epoch": 1.7277434004434378, "grad_norm": 4.166675090789795, "learning_rate": 8.273083215866047e-06, "loss": 0.3254, "step": 290660 }, { "epoch": 1.7278028425201062, "grad_norm": 5.20454216003418, "learning_rate": 8.272926357089276e-06, "loss": 0.3286, "step": 290670 }, { "epoch": 1.7278622845967746, "grad_norm": 5.9649577140808105, "learning_rate": 8.272769492676141e-06, "loss": 0.3222, "step": 290680 }, { "epoch": 1.727921726673443, "grad_norm": 7.491549968719482, "learning_rate": 8.272612622626901e-06, "loss": 0.3511, "step": 290690 }, { "epoch": 1.7279811687501114, "grad_norm": 6.377598285675049, "learning_rate": 8.272455746941835e-06, "loss": 0.3228, "step": 290700 }, { "epoch": 1.7280406108267798, "grad_norm": 4.1660895347595215, "learning_rate": 8.272298865621207e-06, "loss": 0.3388, "step": 290710 }, { "epoch": 1.7281000529034483, "grad_norm": 5.351796627044678, "learning_rate": 8.272141978665293e-06, "loss": 0.3208, "step": 290720 }, { "epoch": 1.7281594949801167, "grad_norm": 5.454313278198242, "learning_rate": 8.271985086074359e-06, "loss": 0.3153, "step": 290730 }, { "epoch": 1.728218937056785, "grad_norm": 5.507297515869141, "learning_rate": 8.271828187848675e-06, "loss": 0.3421, "step": 290740 }, { "epoch": 1.7282783791334535, "grad_norm": 4.389447212219238, "learning_rate": 8.271671283988514e-06, "loss": 0.3445, "step": 290750 }, { "epoch": 1.728337821210122, "grad_norm": 5.0383195877075195, "learning_rate": 8.271514374494142e-06, "loss": 0.3481, "step": 290760 }, { "epoch": 1.7283972632867903, "grad_norm": 4.707754135131836, "learning_rate": 8.271357459365834e-06, "loss": 0.3149, "step": 290770 }, { "epoch": 1.7284567053634585, "grad_norm": 4.977842807769775, "learning_rate": 8.271200538603858e-06, "loss": 0.3338, "step": 290780 }, { "epoch": 1.728516147440127, "grad_norm": 4.862453937530518, "learning_rate": 8.271043612208486e-06, "loss": 0.32, "step": 290790 }, { "epoch": 1.7285755895167954, "grad_norm": 4.9305009841918945, "learning_rate": 8.270886680179983e-06, "loss": 0.3132, "step": 290800 }, { "epoch": 1.7286350315934638, "grad_norm": 4.370254039764404, "learning_rate": 8.270729742518626e-06, "loss": 0.2996, "step": 290810 }, { "epoch": 1.7286944736701322, "grad_norm": 4.901006698608398, "learning_rate": 8.270572799224682e-06, "loss": 0.305, "step": 290820 }, { "epoch": 1.7287539157468004, "grad_norm": 5.110462665557861, "learning_rate": 8.27041585029842e-06, "loss": 0.297, "step": 290830 }, { "epoch": 1.7288133578234688, "grad_norm": 8.190850257873535, "learning_rate": 8.270258895740111e-06, "loss": 0.3102, "step": 290840 }, { "epoch": 1.7288727999001372, "grad_norm": 4.7328948974609375, "learning_rate": 8.270101935550028e-06, "loss": 0.3012, "step": 290850 }, { "epoch": 1.7289322419768056, "grad_norm": 5.732700824737549, "learning_rate": 8.269944969728438e-06, "loss": 0.3166, "step": 290860 }, { "epoch": 1.728991684053474, "grad_norm": 4.1929216384887695, "learning_rate": 8.269787998275614e-06, "loss": 0.3124, "step": 290870 }, { "epoch": 1.7290511261301424, "grad_norm": 4.489222526550293, "learning_rate": 8.269631021191823e-06, "loss": 0.3545, "step": 290880 }, { "epoch": 1.7291105682068109, "grad_norm": 5.8082661628723145, "learning_rate": 8.269474038477339e-06, "loss": 0.3208, "step": 290890 }, { "epoch": 1.7291700102834793, "grad_norm": 4.325409889221191, "learning_rate": 8.269317050132428e-06, "loss": 0.2571, "step": 290900 }, { "epoch": 1.7292294523601477, "grad_norm": 3.498122215270996, "learning_rate": 8.269160056157365e-06, "loss": 0.2969, "step": 290910 }, { "epoch": 1.729288894436816, "grad_norm": 4.564760684967041, "learning_rate": 8.269003056552419e-06, "loss": 0.304, "step": 290920 }, { "epoch": 1.7293483365134845, "grad_norm": 5.603360176086426, "learning_rate": 8.268846051317857e-06, "loss": 0.3273, "step": 290930 }, { "epoch": 1.729407778590153, "grad_norm": 5.368228435516357, "learning_rate": 8.268689040453954e-06, "loss": 0.3595, "step": 290940 }, { "epoch": 1.7294672206668213, "grad_norm": 5.06701135635376, "learning_rate": 8.268532023960978e-06, "loss": 0.3385, "step": 290950 }, { "epoch": 1.7295266627434898, "grad_norm": 5.115903377532959, "learning_rate": 8.2683750018392e-06, "loss": 0.3144, "step": 290960 }, { "epoch": 1.729586104820158, "grad_norm": 4.372871398925781, "learning_rate": 8.26821797408889e-06, "loss": 0.2875, "step": 290970 }, { "epoch": 1.7296455468968264, "grad_norm": 5.633475303649902, "learning_rate": 8.26806094071032e-06, "loss": 0.3067, "step": 290980 }, { "epoch": 1.7297049889734948, "grad_norm": 5.38510274887085, "learning_rate": 8.267903901703758e-06, "loss": 0.3178, "step": 290990 }, { "epoch": 1.7297644310501632, "grad_norm": 5.0218329429626465, "learning_rate": 8.267746857069476e-06, "loss": 0.3194, "step": 291000 }, { "epoch": 1.7298238731268316, "grad_norm": 5.0774149894714355, "learning_rate": 8.267589806807742e-06, "loss": 0.3245, "step": 291010 }, { "epoch": 1.7298833152034998, "grad_norm": 4.691773414611816, "learning_rate": 8.267432750918832e-06, "loss": 0.3113, "step": 291020 }, { "epoch": 1.7299427572801682, "grad_norm": 5.036823749542236, "learning_rate": 8.26727568940301e-06, "loss": 0.2979, "step": 291030 }, { "epoch": 1.7300021993568366, "grad_norm": 6.968279838562012, "learning_rate": 8.26711862226055e-06, "loss": 0.3092, "step": 291040 }, { "epoch": 1.730061641433505, "grad_norm": 4.501131057739258, "learning_rate": 8.266961549491724e-06, "loss": 0.3032, "step": 291050 }, { "epoch": 1.7301210835101735, "grad_norm": 6.529170513153076, "learning_rate": 8.266804471096799e-06, "loss": 0.3153, "step": 291060 }, { "epoch": 1.7301805255868419, "grad_norm": 5.935776710510254, "learning_rate": 8.266647387076046e-06, "loss": 0.3268, "step": 291070 }, { "epoch": 1.7302399676635103, "grad_norm": 4.816170692443848, "learning_rate": 8.266490297429736e-06, "loss": 0.3211, "step": 291080 }, { "epoch": 1.7302994097401787, "grad_norm": 4.397045135498047, "learning_rate": 8.266333202158143e-06, "loss": 0.3364, "step": 291090 }, { "epoch": 1.7303588518168471, "grad_norm": 4.255160808563232, "learning_rate": 8.266176101261532e-06, "loss": 0.319, "step": 291100 }, { "epoch": 1.7304182938935155, "grad_norm": 6.478333473205566, "learning_rate": 8.266018994740177e-06, "loss": 0.3437, "step": 291110 }, { "epoch": 1.730477735970184, "grad_norm": 5.084285259246826, "learning_rate": 8.265861882594346e-06, "loss": 0.2967, "step": 291120 }, { "epoch": 1.7305371780468524, "grad_norm": 4.798707485198975, "learning_rate": 8.265704764824314e-06, "loss": 0.2799, "step": 291130 }, { "epoch": 1.7305966201235208, "grad_norm": 5.583645820617676, "learning_rate": 8.265547641430345e-06, "loss": 0.3213, "step": 291140 }, { "epoch": 1.730656062200189, "grad_norm": 5.107414722442627, "learning_rate": 8.265390512412717e-06, "loss": 0.2633, "step": 291150 }, { "epoch": 1.7307155042768574, "grad_norm": 4.986048698425293, "learning_rate": 8.265233377771696e-06, "loss": 0.3226, "step": 291160 }, { "epoch": 1.7307749463535258, "grad_norm": 4.613174915313721, "learning_rate": 8.265076237507551e-06, "loss": 0.2917, "step": 291170 }, { "epoch": 1.7308343884301942, "grad_norm": 5.697165012359619, "learning_rate": 8.264919091620559e-06, "loss": 0.3114, "step": 291180 }, { "epoch": 1.7308938305068626, "grad_norm": 5.156887531280518, "learning_rate": 8.264761940110983e-06, "loss": 0.3033, "step": 291190 }, { "epoch": 1.7309532725835308, "grad_norm": 5.032482147216797, "learning_rate": 8.2646047829791e-06, "loss": 0.3075, "step": 291200 }, { "epoch": 1.7310127146601992, "grad_norm": 6.084583282470703, "learning_rate": 8.264447620225178e-06, "loss": 0.3533, "step": 291210 }, { "epoch": 1.7310721567368677, "grad_norm": 5.68448543548584, "learning_rate": 8.264290451849486e-06, "loss": 0.292, "step": 291220 }, { "epoch": 1.731131598813536, "grad_norm": 3.749997854232788, "learning_rate": 8.264133277852297e-06, "loss": 0.3084, "step": 291230 }, { "epoch": 1.7311910408902045, "grad_norm": 4.397329330444336, "learning_rate": 8.26397609823388e-06, "loss": 0.3066, "step": 291240 }, { "epoch": 1.731250482966873, "grad_norm": 4.986108303070068, "learning_rate": 8.26381891299451e-06, "loss": 0.3392, "step": 291250 }, { "epoch": 1.7313099250435413, "grad_norm": 5.8301777839660645, "learning_rate": 8.263661722134451e-06, "loss": 0.3287, "step": 291260 }, { "epoch": 1.7313693671202097, "grad_norm": 5.685340404510498, "learning_rate": 8.26350452565398e-06, "loss": 0.3418, "step": 291270 }, { "epoch": 1.7314288091968781, "grad_norm": 4.084920406341553, "learning_rate": 8.263347323553363e-06, "loss": 0.2927, "step": 291280 }, { "epoch": 1.7314882512735466, "grad_norm": 5.296927452087402, "learning_rate": 8.263190115832874e-06, "loss": 0.295, "step": 291290 }, { "epoch": 1.731547693350215, "grad_norm": 7.801799297332764, "learning_rate": 8.26303290249278e-06, "loss": 0.3218, "step": 291300 }, { "epoch": 1.7316071354268834, "grad_norm": 3.9973628520965576, "learning_rate": 8.262875683533356e-06, "loss": 0.3029, "step": 291310 }, { "epoch": 1.7316665775035518, "grad_norm": 3.398597240447998, "learning_rate": 8.26271845895487e-06, "loss": 0.2839, "step": 291320 }, { "epoch": 1.7317260195802202, "grad_norm": 4.040262222290039, "learning_rate": 8.262561228757593e-06, "loss": 0.3716, "step": 291330 }, { "epoch": 1.7317854616568884, "grad_norm": 4.599150657653809, "learning_rate": 8.262403992941796e-06, "loss": 0.2946, "step": 291340 }, { "epoch": 1.7318449037335568, "grad_norm": 4.4011735916137695, "learning_rate": 8.26224675150775e-06, "loss": 0.3105, "step": 291350 }, { "epoch": 1.7319043458102252, "grad_norm": 5.025451183319092, "learning_rate": 8.262089504455727e-06, "loss": 0.297, "step": 291360 }, { "epoch": 1.7319637878868936, "grad_norm": 4.549379825592041, "learning_rate": 8.261932251785997e-06, "loss": 0.297, "step": 291370 }, { "epoch": 1.732023229963562, "grad_norm": 5.874941349029541, "learning_rate": 8.26177499349883e-06, "loss": 0.3377, "step": 291380 }, { "epoch": 1.7320826720402303, "grad_norm": 4.927103042602539, "learning_rate": 8.261617729594496e-06, "loss": 0.3169, "step": 291390 }, { "epoch": 1.7321421141168987, "grad_norm": 5.867595195770264, "learning_rate": 8.261460460073268e-06, "loss": 0.3576, "step": 291400 }, { "epoch": 1.732201556193567, "grad_norm": 5.13657808303833, "learning_rate": 8.261303184935417e-06, "loss": 0.3025, "step": 291410 }, { "epoch": 1.7322609982702355, "grad_norm": 4.054872512817383, "learning_rate": 8.261145904181211e-06, "loss": 0.2626, "step": 291420 }, { "epoch": 1.732320440346904, "grad_norm": 4.6483917236328125, "learning_rate": 8.260988617810924e-06, "loss": 0.321, "step": 291430 }, { "epoch": 1.7323798824235723, "grad_norm": 3.88006329536438, "learning_rate": 8.260831325824825e-06, "loss": 0.2962, "step": 291440 }, { "epoch": 1.7324393245002407, "grad_norm": 4.485471725463867, "learning_rate": 8.260674028223186e-06, "loss": 0.3314, "step": 291450 }, { "epoch": 1.7324987665769092, "grad_norm": 5.304847240447998, "learning_rate": 8.260516725006276e-06, "loss": 0.3511, "step": 291460 }, { "epoch": 1.7325582086535776, "grad_norm": 4.6750359535217285, "learning_rate": 8.260359416174368e-06, "loss": 0.3179, "step": 291470 }, { "epoch": 1.732617650730246, "grad_norm": 4.746216297149658, "learning_rate": 8.26020210172773e-06, "loss": 0.2864, "step": 291480 }, { "epoch": 1.7326770928069144, "grad_norm": 4.839817523956299, "learning_rate": 8.260044781666638e-06, "loss": 0.3142, "step": 291490 }, { "epoch": 1.7327365348835828, "grad_norm": 4.395814418792725, "learning_rate": 8.259887455991357e-06, "loss": 0.3316, "step": 291500 }, { "epoch": 1.7327959769602512, "grad_norm": 4.047662734985352, "learning_rate": 8.259730124702163e-06, "loss": 0.2872, "step": 291510 }, { "epoch": 1.7328554190369194, "grad_norm": 5.678274631500244, "learning_rate": 8.259572787799327e-06, "loss": 0.2992, "step": 291520 }, { "epoch": 1.7329148611135878, "grad_norm": 5.509218215942383, "learning_rate": 8.259415445283113e-06, "loss": 0.3391, "step": 291530 }, { "epoch": 1.7329743031902562, "grad_norm": 4.528312683105469, "learning_rate": 8.259258097153799e-06, "loss": 0.3064, "step": 291540 }, { "epoch": 1.7330337452669247, "grad_norm": 5.393881320953369, "learning_rate": 8.259100743411653e-06, "loss": 0.3315, "step": 291550 }, { "epoch": 1.733093187343593, "grad_norm": 5.93684196472168, "learning_rate": 8.258943384056948e-06, "loss": 0.3271, "step": 291560 }, { "epoch": 1.7331526294202613, "grad_norm": 6.08331823348999, "learning_rate": 8.258786019089952e-06, "loss": 0.3185, "step": 291570 }, { "epoch": 1.7332120714969297, "grad_norm": 5.080176830291748, "learning_rate": 8.258628648510938e-06, "loss": 0.3447, "step": 291580 }, { "epoch": 1.733271513573598, "grad_norm": 7.706935882568359, "learning_rate": 8.258471272320177e-06, "loss": 0.3101, "step": 291590 }, { "epoch": 1.7333309556502665, "grad_norm": 4.632296085357666, "learning_rate": 8.258313890517939e-06, "loss": 0.2938, "step": 291600 }, { "epoch": 1.733390397726935, "grad_norm": 6.566349983215332, "learning_rate": 8.258156503104497e-06, "loss": 0.3033, "step": 291610 }, { "epoch": 1.7334498398036033, "grad_norm": 4.802281856536865, "learning_rate": 8.25799911008012e-06, "loss": 0.3205, "step": 291620 }, { "epoch": 1.7335092818802718, "grad_norm": 6.593557834625244, "learning_rate": 8.25784171144508e-06, "loss": 0.3198, "step": 291630 }, { "epoch": 1.7335687239569402, "grad_norm": 4.503722190856934, "learning_rate": 8.257684307199648e-06, "loss": 0.3137, "step": 291640 }, { "epoch": 1.7336281660336086, "grad_norm": 5.4825239181518555, "learning_rate": 8.257526897344095e-06, "loss": 0.2893, "step": 291650 }, { "epoch": 1.733687608110277, "grad_norm": 5.404110908508301, "learning_rate": 8.257369481878692e-06, "loss": 0.3465, "step": 291660 }, { "epoch": 1.7337470501869454, "grad_norm": 4.742967128753662, "learning_rate": 8.25721206080371e-06, "loss": 0.3377, "step": 291670 }, { "epoch": 1.7338064922636138, "grad_norm": 5.030779838562012, "learning_rate": 8.257054634119419e-06, "loss": 0.2795, "step": 291680 }, { "epoch": 1.7338659343402822, "grad_norm": 4.964868545532227, "learning_rate": 8.256897201826093e-06, "loss": 0.3493, "step": 291690 }, { "epoch": 1.7339253764169507, "grad_norm": 5.08419942855835, "learning_rate": 8.256739763924e-06, "loss": 0.3126, "step": 291700 }, { "epoch": 1.7339848184936189, "grad_norm": 5.222855567932129, "learning_rate": 8.256582320413413e-06, "loss": 0.346, "step": 291710 }, { "epoch": 1.7340442605702873, "grad_norm": 4.514653205871582, "learning_rate": 8.256424871294604e-06, "loss": 0.3367, "step": 291720 }, { "epoch": 1.7341037026469557, "grad_norm": 5.504334449768066, "learning_rate": 8.25626741656784e-06, "loss": 0.3207, "step": 291730 }, { "epoch": 1.734163144723624, "grad_norm": 6.5674896240234375, "learning_rate": 8.256109956233397e-06, "loss": 0.3087, "step": 291740 }, { "epoch": 1.7342225868002925, "grad_norm": 5.205588340759277, "learning_rate": 8.255952490291544e-06, "loss": 0.3753, "step": 291750 }, { "epoch": 1.7342820288769607, "grad_norm": 4.933356761932373, "learning_rate": 8.255795018742552e-06, "loss": 0.3082, "step": 291760 }, { "epoch": 1.7343414709536291, "grad_norm": 5.482749938964844, "learning_rate": 8.255637541586694e-06, "loss": 0.3191, "step": 291770 }, { "epoch": 1.7344009130302975, "grad_norm": 4.246940612792969, "learning_rate": 8.255480058824237e-06, "loss": 0.3157, "step": 291780 }, { "epoch": 1.734460355106966, "grad_norm": 4.6436381340026855, "learning_rate": 8.255322570455455e-06, "loss": 0.328, "step": 291790 }, { "epoch": 1.7345197971836344, "grad_norm": 5.625781536102295, "learning_rate": 8.255165076480622e-06, "loss": 0.3421, "step": 291800 }, { "epoch": 1.7345792392603028, "grad_norm": 4.240164279937744, "learning_rate": 8.255007576900006e-06, "loss": 0.304, "step": 291810 }, { "epoch": 1.7346386813369712, "grad_norm": 6.734434604644775, "learning_rate": 8.254850071713876e-06, "loss": 0.3346, "step": 291820 }, { "epoch": 1.7346981234136396, "grad_norm": 6.392403602600098, "learning_rate": 8.254692560922508e-06, "loss": 0.3235, "step": 291830 }, { "epoch": 1.734757565490308, "grad_norm": 5.691857814788818, "learning_rate": 8.25453504452617e-06, "loss": 0.3303, "step": 291840 }, { "epoch": 1.7348170075669764, "grad_norm": 6.260270595550537, "learning_rate": 8.254377522525134e-06, "loss": 0.3298, "step": 291850 }, { "epoch": 1.7348764496436448, "grad_norm": 5.678361892700195, "learning_rate": 8.254219994919672e-06, "loss": 0.3286, "step": 291860 }, { "epoch": 1.7349358917203133, "grad_norm": 5.900057792663574, "learning_rate": 8.254062461710055e-06, "loss": 0.3174, "step": 291870 }, { "epoch": 1.7349953337969817, "grad_norm": 5.15875244140625, "learning_rate": 8.253904922896554e-06, "loss": 0.3308, "step": 291880 }, { "epoch": 1.7350547758736499, "grad_norm": 5.0228118896484375, "learning_rate": 8.253747378479441e-06, "loss": 0.3031, "step": 291890 }, { "epoch": 1.7351142179503183, "grad_norm": 4.564205169677734, "learning_rate": 8.253589828458985e-06, "loss": 0.3269, "step": 291900 }, { "epoch": 1.7351736600269867, "grad_norm": 5.10255241394043, "learning_rate": 8.25343227283546e-06, "loss": 0.2986, "step": 291910 }, { "epoch": 1.7352331021036551, "grad_norm": 4.820673942565918, "learning_rate": 8.253274711609138e-06, "loss": 0.3252, "step": 291920 }, { "epoch": 1.7352925441803235, "grad_norm": 5.719823360443115, "learning_rate": 8.253117144780288e-06, "loss": 0.3109, "step": 291930 }, { "epoch": 1.7353519862569917, "grad_norm": 5.615176677703857, "learning_rate": 8.252959572349182e-06, "loss": 0.3043, "step": 291940 }, { "epoch": 1.7354114283336601, "grad_norm": 6.148099422454834, "learning_rate": 8.252801994316091e-06, "loss": 0.3207, "step": 291950 }, { "epoch": 1.7354708704103285, "grad_norm": 4.2314863204956055, "learning_rate": 8.252644410681287e-06, "loss": 0.3033, "step": 291960 }, { "epoch": 1.735530312486997, "grad_norm": 4.732946395874023, "learning_rate": 8.252486821445042e-06, "loss": 0.3115, "step": 291970 }, { "epoch": 1.7355897545636654, "grad_norm": 4.621884822845459, "learning_rate": 8.252329226607626e-06, "loss": 0.3405, "step": 291980 }, { "epoch": 1.7356491966403338, "grad_norm": 4.308620929718018, "learning_rate": 8.25217162616931e-06, "loss": 0.2983, "step": 291990 }, { "epoch": 1.7357086387170022, "grad_norm": 4.319540500640869, "learning_rate": 8.252014020130368e-06, "loss": 0.3107, "step": 292000 }, { "epoch": 1.7357680807936706, "grad_norm": 4.8799567222595215, "learning_rate": 8.251856408491067e-06, "loss": 0.3032, "step": 292010 }, { "epoch": 1.735827522870339, "grad_norm": 3.583379030227661, "learning_rate": 8.251698791251686e-06, "loss": 0.3503, "step": 292020 }, { "epoch": 1.7358869649470074, "grad_norm": 5.344173908233643, "learning_rate": 8.251541168412489e-06, "loss": 0.2842, "step": 292030 }, { "epoch": 1.7359464070236759, "grad_norm": 4.900580406188965, "learning_rate": 8.25138353997375e-06, "loss": 0.295, "step": 292040 }, { "epoch": 1.7360058491003443, "grad_norm": 5.653132438659668, "learning_rate": 8.251225905935742e-06, "loss": 0.304, "step": 292050 }, { "epoch": 1.7360652911770127, "grad_norm": 5.32119607925415, "learning_rate": 8.251068266298733e-06, "loss": 0.3177, "step": 292060 }, { "epoch": 1.736124733253681, "grad_norm": 5.521571159362793, "learning_rate": 8.250910621062997e-06, "loss": 0.3199, "step": 292070 }, { "epoch": 1.7361841753303493, "grad_norm": 4.465667247772217, "learning_rate": 8.250752970228807e-06, "loss": 0.299, "step": 292080 }, { "epoch": 1.7362436174070177, "grad_norm": 4.060949802398682, "learning_rate": 8.25059531379643e-06, "loss": 0.3251, "step": 292090 }, { "epoch": 1.7363030594836861, "grad_norm": 6.712145805358887, "learning_rate": 8.250437651766141e-06, "loss": 0.3101, "step": 292100 }, { "epoch": 1.7363625015603545, "grad_norm": 5.5541157722473145, "learning_rate": 8.250279984138212e-06, "loss": 0.343, "step": 292110 }, { "epoch": 1.736421943637023, "grad_norm": 5.408764839172363, "learning_rate": 8.25012231091291e-06, "loss": 0.3417, "step": 292120 }, { "epoch": 1.7364813857136912, "grad_norm": 4.534841060638428, "learning_rate": 8.24996463209051e-06, "loss": 0.296, "step": 292130 }, { "epoch": 1.7365408277903596, "grad_norm": 4.757592678070068, "learning_rate": 8.249806947671286e-06, "loss": 0.3384, "step": 292140 }, { "epoch": 1.736600269867028, "grad_norm": 5.289956569671631, "learning_rate": 8.249649257655505e-06, "loss": 0.3222, "step": 292150 }, { "epoch": 1.7366597119436964, "grad_norm": 5.190437316894531, "learning_rate": 8.24949156204344e-06, "loss": 0.2898, "step": 292160 }, { "epoch": 1.7367191540203648, "grad_norm": 5.252591133117676, "learning_rate": 8.249333860835364e-06, "loss": 0.3055, "step": 292170 }, { "epoch": 1.7367785960970332, "grad_norm": 6.700460910797119, "learning_rate": 8.249176154031545e-06, "loss": 0.3487, "step": 292180 }, { "epoch": 1.7368380381737016, "grad_norm": 6.045417785644531, "learning_rate": 8.24901844163226e-06, "loss": 0.3059, "step": 292190 }, { "epoch": 1.73689748025037, "grad_norm": 5.323917865753174, "learning_rate": 8.248860723637774e-06, "loss": 0.2597, "step": 292200 }, { "epoch": 1.7369569223270385, "grad_norm": 4.972696304321289, "learning_rate": 8.248703000048367e-06, "loss": 0.3613, "step": 292210 }, { "epoch": 1.7370163644037069, "grad_norm": 5.343850612640381, "learning_rate": 8.248545270864301e-06, "loss": 0.3041, "step": 292220 }, { "epoch": 1.7370758064803753, "grad_norm": 3.9513766765594482, "learning_rate": 8.248387536085855e-06, "loss": 0.3134, "step": 292230 }, { "epoch": 1.7371352485570437, "grad_norm": 5.284168720245361, "learning_rate": 8.248229795713297e-06, "loss": 0.323, "step": 292240 }, { "epoch": 1.7371946906337121, "grad_norm": 3.5019657611846924, "learning_rate": 8.2480720497469e-06, "loss": 0.3147, "step": 292250 }, { "epoch": 1.7372541327103803, "grad_norm": 4.4512763023376465, "learning_rate": 8.247914298186937e-06, "loss": 0.2882, "step": 292260 }, { "epoch": 1.7373135747870487, "grad_norm": 4.989081859588623, "learning_rate": 8.247756541033676e-06, "loss": 0.3116, "step": 292270 }, { "epoch": 1.7373730168637171, "grad_norm": 5.026554107666016, "learning_rate": 8.24759877828739e-06, "loss": 0.3454, "step": 292280 }, { "epoch": 1.7374324589403856, "grad_norm": 5.222204685211182, "learning_rate": 8.247441009948353e-06, "loss": 0.3082, "step": 292290 }, { "epoch": 1.737491901017054, "grad_norm": 6.493361473083496, "learning_rate": 8.247283236016837e-06, "loss": 0.3073, "step": 292300 }, { "epoch": 1.7375513430937222, "grad_norm": 4.968749046325684, "learning_rate": 8.247125456493109e-06, "loss": 0.3192, "step": 292310 }, { "epoch": 1.7376107851703906, "grad_norm": 4.314116477966309, "learning_rate": 8.246967671377444e-06, "loss": 0.3062, "step": 292320 }, { "epoch": 1.737670227247059, "grad_norm": 5.558896064758301, "learning_rate": 8.246809880670113e-06, "loss": 0.3002, "step": 292330 }, { "epoch": 1.7377296693237274, "grad_norm": 3.682380199432373, "learning_rate": 8.246652084371389e-06, "loss": 0.2976, "step": 292340 }, { "epoch": 1.7377891114003958, "grad_norm": 4.246217727661133, "learning_rate": 8.24649428248154e-06, "loss": 0.3156, "step": 292350 }, { "epoch": 1.7378485534770642, "grad_norm": 4.01520299911499, "learning_rate": 8.246336475000845e-06, "loss": 0.3104, "step": 292360 }, { "epoch": 1.7379079955537327, "grad_norm": 6.103037357330322, "learning_rate": 8.246178661929567e-06, "loss": 0.3586, "step": 292370 }, { "epoch": 1.737967437630401, "grad_norm": 4.318338394165039, "learning_rate": 8.246020843267986e-06, "loss": 0.3483, "step": 292380 }, { "epoch": 1.7380268797070695, "grad_norm": 6.05305290222168, "learning_rate": 8.245863019016366e-06, "loss": 0.3281, "step": 292390 }, { "epoch": 1.738086321783738, "grad_norm": 4.777003765106201, "learning_rate": 8.245705189174987e-06, "loss": 0.3032, "step": 292400 }, { "epoch": 1.7381457638604063, "grad_norm": 7.099269390106201, "learning_rate": 8.245547353744113e-06, "loss": 0.3414, "step": 292410 }, { "epoch": 1.7382052059370747, "grad_norm": 4.181283950805664, "learning_rate": 8.245389512724019e-06, "loss": 0.3074, "step": 292420 }, { "epoch": 1.7382646480137431, "grad_norm": 5.9676971435546875, "learning_rate": 8.245231666114979e-06, "loss": 0.3187, "step": 292430 }, { "epoch": 1.7383240900904116, "grad_norm": 4.7943010330200195, "learning_rate": 8.245073813917262e-06, "loss": 0.3397, "step": 292440 }, { "epoch": 1.7383835321670797, "grad_norm": 5.193602561950684, "learning_rate": 8.244915956131139e-06, "loss": 0.3267, "step": 292450 }, { "epoch": 1.7384429742437482, "grad_norm": 5.598081588745117, "learning_rate": 8.244758092756885e-06, "loss": 0.3128, "step": 292460 }, { "epoch": 1.7385024163204166, "grad_norm": 7.496905326843262, "learning_rate": 8.24460022379477e-06, "loss": 0.3344, "step": 292470 }, { "epoch": 1.738561858397085, "grad_norm": 4.785830974578857, "learning_rate": 8.244442349245067e-06, "loss": 0.3199, "step": 292480 }, { "epoch": 1.7386213004737534, "grad_norm": 5.707100868225098, "learning_rate": 8.244284469108047e-06, "loss": 0.3242, "step": 292490 }, { "epoch": 1.7386807425504216, "grad_norm": 4.998287200927734, "learning_rate": 8.244126583383982e-06, "loss": 0.3132, "step": 292500 }, { "epoch": 1.73874018462709, "grad_norm": 5.432432651519775, "learning_rate": 8.243968692073144e-06, "loss": 0.3448, "step": 292510 }, { "epoch": 1.7387996267037584, "grad_norm": 5.25850772857666, "learning_rate": 8.243810795175804e-06, "loss": 0.3416, "step": 292520 }, { "epoch": 1.7388590687804268, "grad_norm": 5.25654935836792, "learning_rate": 8.243652892692235e-06, "loss": 0.3275, "step": 292530 }, { "epoch": 1.7389185108570953, "grad_norm": 4.149964332580566, "learning_rate": 8.243494984622711e-06, "loss": 0.3407, "step": 292540 }, { "epoch": 1.7389779529337637, "grad_norm": 5.018974304199219, "learning_rate": 8.2433370709675e-06, "loss": 0.2966, "step": 292550 }, { "epoch": 1.739037395010432, "grad_norm": 5.0378499031066895, "learning_rate": 8.243179151726874e-06, "loss": 0.3025, "step": 292560 }, { "epoch": 1.7390968370871005, "grad_norm": 5.207239627838135, "learning_rate": 8.243021226901109e-06, "loss": 0.3333, "step": 292570 }, { "epoch": 1.739156279163769, "grad_norm": 4.817622661590576, "learning_rate": 8.242863296490472e-06, "loss": 0.2683, "step": 292580 }, { "epoch": 1.7392157212404373, "grad_norm": 6.161640167236328, "learning_rate": 8.242705360495239e-06, "loss": 0.3332, "step": 292590 }, { "epoch": 1.7392751633171057, "grad_norm": 5.404421329498291, "learning_rate": 8.24254741891568e-06, "loss": 0.2998, "step": 292600 }, { "epoch": 1.7393346053937742, "grad_norm": 4.730815410614014, "learning_rate": 8.242389471752068e-06, "loss": 0.3203, "step": 292610 }, { "epoch": 1.7393940474704426, "grad_norm": 3.7396295070648193, "learning_rate": 8.242231519004675e-06, "loss": 0.2953, "step": 292620 }, { "epoch": 1.7394534895471108, "grad_norm": 4.865085124969482, "learning_rate": 8.24207356067377e-06, "loss": 0.3334, "step": 292630 }, { "epoch": 1.7395129316237792, "grad_norm": 5.014814376831055, "learning_rate": 8.24191559675963e-06, "loss": 0.3159, "step": 292640 }, { "epoch": 1.7395723737004476, "grad_norm": 4.967804908752441, "learning_rate": 8.241757627262524e-06, "loss": 0.3434, "step": 292650 }, { "epoch": 1.739631815777116, "grad_norm": 6.09124231338501, "learning_rate": 8.241599652182724e-06, "loss": 0.3042, "step": 292660 }, { "epoch": 1.7396912578537844, "grad_norm": 5.8040547370910645, "learning_rate": 8.241441671520503e-06, "loss": 0.3513, "step": 292670 }, { "epoch": 1.7397506999304526, "grad_norm": 4.511475563049316, "learning_rate": 8.241283685276133e-06, "loss": 0.2793, "step": 292680 }, { "epoch": 1.739810142007121, "grad_norm": 4.449093341827393, "learning_rate": 8.241125693449885e-06, "loss": 0.3149, "step": 292690 }, { "epoch": 1.7398695840837894, "grad_norm": 5.680891036987305, "learning_rate": 8.240967696042032e-06, "loss": 0.3361, "step": 292700 }, { "epoch": 1.7399290261604579, "grad_norm": 4.493230819702148, "learning_rate": 8.240809693052848e-06, "loss": 0.2983, "step": 292710 }, { "epoch": 1.7399884682371263, "grad_norm": 4.356468677520752, "learning_rate": 8.2406516844826e-06, "loss": 0.3013, "step": 292720 }, { "epoch": 1.7400479103137947, "grad_norm": 5.9006524085998535, "learning_rate": 8.240493670331564e-06, "loss": 0.3474, "step": 292730 }, { "epoch": 1.740107352390463, "grad_norm": 5.561289310455322, "learning_rate": 8.24033565060001e-06, "loss": 0.3561, "step": 292740 }, { "epoch": 1.7401667944671315, "grad_norm": 4.88916540145874, "learning_rate": 8.240177625288214e-06, "loss": 0.2993, "step": 292750 }, { "epoch": 1.7402262365438, "grad_norm": 5.995359420776367, "learning_rate": 8.240019594396444e-06, "loss": 0.3616, "step": 292760 }, { "epoch": 1.7402856786204683, "grad_norm": 4.979866981506348, "learning_rate": 8.239861557924975e-06, "loss": 0.3158, "step": 292770 }, { "epoch": 1.7403451206971368, "grad_norm": 6.130234241485596, "learning_rate": 8.239703515874076e-06, "loss": 0.3529, "step": 292780 }, { "epoch": 1.7404045627738052, "grad_norm": 15.79093074798584, "learning_rate": 8.23954546824402e-06, "loss": 0.3209, "step": 292790 }, { "epoch": 1.7404640048504736, "grad_norm": 4.7480621337890625, "learning_rate": 8.239387415035084e-06, "loss": 0.3286, "step": 292800 }, { "epoch": 1.740523446927142, "grad_norm": 5.2136688232421875, "learning_rate": 8.239229356247533e-06, "loss": 0.2993, "step": 292810 }, { "epoch": 1.7405828890038102, "grad_norm": 4.4906697273254395, "learning_rate": 8.239071291881646e-06, "loss": 0.3184, "step": 292820 }, { "epoch": 1.7406423310804786, "grad_norm": 4.644402980804443, "learning_rate": 8.23891322193769e-06, "loss": 0.3091, "step": 292830 }, { "epoch": 1.740701773157147, "grad_norm": 5.0200605392456055, "learning_rate": 8.238755146415938e-06, "loss": 0.3264, "step": 292840 }, { "epoch": 1.7407612152338154, "grad_norm": 4.629685401916504, "learning_rate": 8.238597065316663e-06, "loss": 0.3275, "step": 292850 }, { "epoch": 1.7408206573104839, "grad_norm": 5.911131858825684, "learning_rate": 8.238438978640139e-06, "loss": 0.3377, "step": 292860 }, { "epoch": 1.740880099387152, "grad_norm": 6.770895957946777, "learning_rate": 8.238280886386636e-06, "loss": 0.3557, "step": 292870 }, { "epoch": 1.7409395414638205, "grad_norm": 4.806975364685059, "learning_rate": 8.238122788556427e-06, "loss": 0.2962, "step": 292880 }, { "epoch": 1.7409989835404889, "grad_norm": 5.231917381286621, "learning_rate": 8.237964685149784e-06, "loss": 0.3272, "step": 292890 }, { "epoch": 1.7410584256171573, "grad_norm": 5.485345840454102, "learning_rate": 8.237806576166978e-06, "loss": 0.2843, "step": 292900 }, { "epoch": 1.7411178676938257, "grad_norm": 3.1309173107147217, "learning_rate": 8.237648461608286e-06, "loss": 0.3018, "step": 292910 }, { "epoch": 1.7411773097704941, "grad_norm": 4.557179927825928, "learning_rate": 8.237490341473975e-06, "loss": 0.312, "step": 292920 }, { "epoch": 1.7412367518471625, "grad_norm": 5.45314884185791, "learning_rate": 8.237332215764319e-06, "loss": 0.3231, "step": 292930 }, { "epoch": 1.741296193923831, "grad_norm": 5.097953796386719, "learning_rate": 8.237174084479592e-06, "loss": 0.329, "step": 292940 }, { "epoch": 1.7413556360004994, "grad_norm": 6.607746124267578, "learning_rate": 8.237015947620063e-06, "loss": 0.3157, "step": 292950 }, { "epoch": 1.7414150780771678, "grad_norm": 7.096525192260742, "learning_rate": 8.236857805186008e-06, "loss": 0.3065, "step": 292960 }, { "epoch": 1.7414745201538362, "grad_norm": 4.685893535614014, "learning_rate": 8.236699657177698e-06, "loss": 0.3116, "step": 292970 }, { "epoch": 1.7415339622305046, "grad_norm": 5.687493801116943, "learning_rate": 8.236541503595402e-06, "loss": 0.3011, "step": 292980 }, { "epoch": 1.741593404307173, "grad_norm": 4.795614719390869, "learning_rate": 8.2363833444394e-06, "loss": 0.3238, "step": 292990 }, { "epoch": 1.7416528463838412, "grad_norm": 5.2170939445495605, "learning_rate": 8.236225179709955e-06, "loss": 0.322, "step": 293000 }, { "epoch": 1.7417122884605096, "grad_norm": 5.100729465484619, "learning_rate": 8.236067009407346e-06, "loss": 0.3158, "step": 293010 }, { "epoch": 1.741771730537178, "grad_norm": 4.445224285125732, "learning_rate": 8.235908833531846e-06, "loss": 0.2999, "step": 293020 }, { "epoch": 1.7418311726138465, "grad_norm": 4.093264579772949, "learning_rate": 8.235750652083723e-06, "loss": 0.313, "step": 293030 }, { "epoch": 1.7418906146905149, "grad_norm": 3.9011099338531494, "learning_rate": 8.235592465063251e-06, "loss": 0.3095, "step": 293040 }, { "epoch": 1.741950056767183, "grad_norm": 4.949594974517822, "learning_rate": 8.235434272470701e-06, "loss": 0.3041, "step": 293050 }, { "epoch": 1.7420094988438515, "grad_norm": 5.202996730804443, "learning_rate": 8.23527607430635e-06, "loss": 0.302, "step": 293060 }, { "epoch": 1.74206894092052, "grad_norm": 5.586515426635742, "learning_rate": 8.235117870570466e-06, "loss": 0.3288, "step": 293070 }, { "epoch": 1.7421283829971883, "grad_norm": 4.737339496612549, "learning_rate": 8.234959661263324e-06, "loss": 0.314, "step": 293080 }, { "epoch": 1.7421878250738567, "grad_norm": 4.352565288543701, "learning_rate": 8.234801446385195e-06, "loss": 0.3006, "step": 293090 }, { "epoch": 1.7422472671505251, "grad_norm": 5.1375579833984375, "learning_rate": 8.234643225936352e-06, "loss": 0.2713, "step": 293100 }, { "epoch": 1.7423067092271936, "grad_norm": 4.172584533691406, "learning_rate": 8.234484999917066e-06, "loss": 0.3134, "step": 293110 }, { "epoch": 1.742366151303862, "grad_norm": 4.868924617767334, "learning_rate": 8.234326768327614e-06, "loss": 0.3162, "step": 293120 }, { "epoch": 1.7424255933805304, "grad_norm": 5.153140068054199, "learning_rate": 8.234168531168263e-06, "loss": 0.3448, "step": 293130 }, { "epoch": 1.7424850354571988, "grad_norm": 4.832891941070557, "learning_rate": 8.23401028843929e-06, "loss": 0.3119, "step": 293140 }, { "epoch": 1.7425444775338672, "grad_norm": 6.021298885345459, "learning_rate": 8.233852040140962e-06, "loss": 0.324, "step": 293150 }, { "epoch": 1.7426039196105356, "grad_norm": 5.4682159423828125, "learning_rate": 8.233693786273557e-06, "loss": 0.3066, "step": 293160 }, { "epoch": 1.742663361687204, "grad_norm": 5.35075044631958, "learning_rate": 8.233535526837347e-06, "loss": 0.3481, "step": 293170 }, { "epoch": 1.7427228037638725, "grad_norm": 4.976998329162598, "learning_rate": 8.2333772618326e-06, "loss": 0.3408, "step": 293180 }, { "epoch": 1.7427822458405406, "grad_norm": 6.070616245269775, "learning_rate": 8.233218991259592e-06, "loss": 0.3152, "step": 293190 }, { "epoch": 1.742841687917209, "grad_norm": 5.499378681182861, "learning_rate": 8.233060715118597e-06, "loss": 0.2964, "step": 293200 }, { "epoch": 1.7429011299938775, "grad_norm": 4.8231987953186035, "learning_rate": 8.232902433409884e-06, "loss": 0.2964, "step": 293210 }, { "epoch": 1.7429605720705459, "grad_norm": 4.328221321105957, "learning_rate": 8.23274414613373e-06, "loss": 0.3192, "step": 293220 }, { "epoch": 1.743020014147214, "grad_norm": 6.200336933135986, "learning_rate": 8.2325858532904e-06, "loss": 0.3365, "step": 293230 }, { "epoch": 1.7430794562238825, "grad_norm": 4.611039161682129, "learning_rate": 8.232427554880176e-06, "loss": 0.3376, "step": 293240 }, { "epoch": 1.743138898300551, "grad_norm": 5.097490310668945, "learning_rate": 8.232269250903323e-06, "loss": 0.2889, "step": 293250 }, { "epoch": 1.7431983403772193, "grad_norm": 7.688168525695801, "learning_rate": 8.232110941360118e-06, "loss": 0.3272, "step": 293260 }, { "epoch": 1.7432577824538877, "grad_norm": 5.184417724609375, "learning_rate": 8.231952626250832e-06, "loss": 0.3151, "step": 293270 }, { "epoch": 1.7433172245305562, "grad_norm": 5.301103115081787, "learning_rate": 8.23179430557574e-06, "loss": 0.3223, "step": 293280 }, { "epoch": 1.7433766666072246, "grad_norm": 4.693228244781494, "learning_rate": 8.231635979335111e-06, "loss": 0.2773, "step": 293290 }, { "epoch": 1.743436108683893, "grad_norm": 4.543259143829346, "learning_rate": 8.231477647529218e-06, "loss": 0.3691, "step": 293300 }, { "epoch": 1.7434955507605614, "grad_norm": 4.826574802398682, "learning_rate": 8.231319310158336e-06, "loss": 0.3349, "step": 293310 }, { "epoch": 1.7435549928372298, "grad_norm": 6.464442253112793, "learning_rate": 8.231160967222737e-06, "loss": 0.3106, "step": 293320 }, { "epoch": 1.7436144349138982, "grad_norm": 4.553134918212891, "learning_rate": 8.231002618722692e-06, "loss": 0.3034, "step": 293330 }, { "epoch": 1.7436738769905666, "grad_norm": 5.433614253997803, "learning_rate": 8.230844264658476e-06, "loss": 0.2855, "step": 293340 }, { "epoch": 1.743733319067235, "grad_norm": 4.56410026550293, "learning_rate": 8.230685905030362e-06, "loss": 0.336, "step": 293350 }, { "epoch": 1.7437927611439035, "grad_norm": 5.053354263305664, "learning_rate": 8.230527539838618e-06, "loss": 0.2955, "step": 293360 }, { "epoch": 1.7438522032205717, "grad_norm": 4.88238525390625, "learning_rate": 8.230369169083523e-06, "loss": 0.326, "step": 293370 }, { "epoch": 1.74391164529724, "grad_norm": 6.617352485656738, "learning_rate": 8.230210792765346e-06, "loss": 0.3428, "step": 293380 }, { "epoch": 1.7439710873739085, "grad_norm": 5.0914154052734375, "learning_rate": 8.230052410884361e-06, "loss": 0.3535, "step": 293390 }, { "epoch": 1.744030529450577, "grad_norm": 5.151051998138428, "learning_rate": 8.229894023440838e-06, "loss": 0.3322, "step": 293400 }, { "epoch": 1.7440899715272453, "grad_norm": 6.2314677238464355, "learning_rate": 8.229735630435055e-06, "loss": 0.3301, "step": 293410 }, { "epoch": 1.7441494136039135, "grad_norm": 4.852277755737305, "learning_rate": 8.22957723186728e-06, "loss": 0.2887, "step": 293420 }, { "epoch": 1.744208855680582, "grad_norm": 4.7057905197143555, "learning_rate": 8.22941882773779e-06, "loss": 0.2702, "step": 293430 }, { "epoch": 1.7442682977572503, "grad_norm": 4.9537434577941895, "learning_rate": 8.229260418046853e-06, "loss": 0.291, "step": 293440 }, { "epoch": 1.7443277398339188, "grad_norm": 6.322291374206543, "learning_rate": 8.229102002794746e-06, "loss": 0.3105, "step": 293450 }, { "epoch": 1.7443871819105872, "grad_norm": 6.618444442749023, "learning_rate": 8.228943581981738e-06, "loss": 0.3263, "step": 293460 }, { "epoch": 1.7444466239872556, "grad_norm": 4.062893867492676, "learning_rate": 8.228785155608105e-06, "loss": 0.3209, "step": 293470 }, { "epoch": 1.744506066063924, "grad_norm": 6.235098838806152, "learning_rate": 8.22862672367412e-06, "loss": 0.3305, "step": 293480 }, { "epoch": 1.7445655081405924, "grad_norm": 6.256221771240234, "learning_rate": 8.228468286180054e-06, "loss": 0.3099, "step": 293490 }, { "epoch": 1.7446249502172608, "grad_norm": 6.3046674728393555, "learning_rate": 8.228309843126179e-06, "loss": 0.3107, "step": 293500 }, { "epoch": 1.7446843922939292, "grad_norm": 6.725488662719727, "learning_rate": 8.22815139451277e-06, "loss": 0.3586, "step": 293510 }, { "epoch": 1.7447438343705977, "grad_norm": 4.3726887702941895, "learning_rate": 8.227992940340099e-06, "loss": 0.3423, "step": 293520 }, { "epoch": 1.744803276447266, "grad_norm": 5.996765613555908, "learning_rate": 8.227834480608438e-06, "loss": 0.3022, "step": 293530 }, { "epoch": 1.7448627185239345, "grad_norm": 5.4065985679626465, "learning_rate": 8.227676015318064e-06, "loss": 0.3338, "step": 293540 }, { "epoch": 1.744922160600603, "grad_norm": 4.140926837921143, "learning_rate": 8.227517544469243e-06, "loss": 0.2903, "step": 293550 }, { "epoch": 1.744981602677271, "grad_norm": 5.184288024902344, "learning_rate": 8.227359068062255e-06, "loss": 0.334, "step": 293560 }, { "epoch": 1.7450410447539395, "grad_norm": 4.14723539352417, "learning_rate": 8.227200586097366e-06, "loss": 0.2906, "step": 293570 }, { "epoch": 1.745100486830608, "grad_norm": 3.6453704833984375, "learning_rate": 8.227042098574856e-06, "loss": 0.3145, "step": 293580 }, { "epoch": 1.7451599289072763, "grad_norm": 4.82325553894043, "learning_rate": 8.226883605494993e-06, "loss": 0.3093, "step": 293590 }, { "epoch": 1.7452193709839445, "grad_norm": 5.977562427520752, "learning_rate": 8.226725106858052e-06, "loss": 0.308, "step": 293600 }, { "epoch": 1.745278813060613, "grad_norm": 5.5957794189453125, "learning_rate": 8.226566602664305e-06, "loss": 0.3438, "step": 293610 }, { "epoch": 1.7453382551372814, "grad_norm": 5.357617378234863, "learning_rate": 8.226408092914024e-06, "loss": 0.3689, "step": 293620 }, { "epoch": 1.7453976972139498, "grad_norm": 5.739077568054199, "learning_rate": 8.226249577607486e-06, "loss": 0.3098, "step": 293630 }, { "epoch": 1.7454571392906182, "grad_norm": 4.682522773742676, "learning_rate": 8.22609105674496e-06, "loss": 0.3417, "step": 293640 }, { "epoch": 1.7455165813672866, "grad_norm": 6.005290985107422, "learning_rate": 8.22593253032672e-06, "loss": 0.3162, "step": 293650 }, { "epoch": 1.745576023443955, "grad_norm": 5.07077693939209, "learning_rate": 8.225773998353038e-06, "loss": 0.2944, "step": 293660 }, { "epoch": 1.7456354655206234, "grad_norm": 4.793994903564453, "learning_rate": 8.22561546082419e-06, "loss": 0.309, "step": 293670 }, { "epoch": 1.7456949075972918, "grad_norm": 5.592759132385254, "learning_rate": 8.225456917740446e-06, "loss": 0.3091, "step": 293680 }, { "epoch": 1.7457543496739603, "grad_norm": 4.511389255523682, "learning_rate": 8.225298369102081e-06, "loss": 0.322, "step": 293690 }, { "epoch": 1.7458137917506287, "grad_norm": 4.584061145782471, "learning_rate": 8.225139814909369e-06, "loss": 0.3021, "step": 293700 }, { "epoch": 1.745873233827297, "grad_norm": 5.215575695037842, "learning_rate": 8.224981255162578e-06, "loss": 0.2974, "step": 293710 }, { "epoch": 1.7459326759039655, "grad_norm": 6.0468926429748535, "learning_rate": 8.224822689861989e-06, "loss": 0.3288, "step": 293720 }, { "epoch": 1.745992117980634, "grad_norm": 4.877847194671631, "learning_rate": 8.224664119007867e-06, "loss": 0.3225, "step": 293730 }, { "epoch": 1.746051560057302, "grad_norm": 6.099508762359619, "learning_rate": 8.22450554260049e-06, "loss": 0.3064, "step": 293740 }, { "epoch": 1.7461110021339705, "grad_norm": 4.195741176605225, "learning_rate": 8.22434696064013e-06, "loss": 0.2933, "step": 293750 }, { "epoch": 1.746170444210639, "grad_norm": 7.404427528381348, "learning_rate": 8.224188373127058e-06, "loss": 0.3426, "step": 293760 }, { "epoch": 1.7462298862873074, "grad_norm": 5.367329120635986, "learning_rate": 8.22402978006155e-06, "loss": 0.3223, "step": 293770 }, { "epoch": 1.7462893283639758, "grad_norm": 4.338974952697754, "learning_rate": 8.223871181443878e-06, "loss": 0.3386, "step": 293780 }, { "epoch": 1.746348770440644, "grad_norm": 4.534195899963379, "learning_rate": 8.223712577274316e-06, "loss": 0.3236, "step": 293790 }, { "epoch": 1.7464082125173124, "grad_norm": 4.3555588722229, "learning_rate": 8.223553967553135e-06, "loss": 0.3258, "step": 293800 }, { "epoch": 1.7464676545939808, "grad_norm": 4.061319828033447, "learning_rate": 8.22339535228061e-06, "loss": 0.3131, "step": 293810 }, { "epoch": 1.7465270966706492, "grad_norm": 6.705744743347168, "learning_rate": 8.223236731457014e-06, "loss": 0.3209, "step": 293820 }, { "epoch": 1.7465865387473176, "grad_norm": 4.7218427658081055, "learning_rate": 8.223078105082619e-06, "loss": 0.3257, "step": 293830 }, { "epoch": 1.746645980823986, "grad_norm": 4.584601879119873, "learning_rate": 8.2229194731577e-06, "loss": 0.3066, "step": 293840 }, { "epoch": 1.7467054229006544, "grad_norm": 4.830333709716797, "learning_rate": 8.222760835682529e-06, "loss": 0.3099, "step": 293850 }, { "epoch": 1.7467648649773229, "grad_norm": 4.762053966522217, "learning_rate": 8.222602192657378e-06, "loss": 0.3331, "step": 293860 }, { "epoch": 1.7468243070539913, "grad_norm": 6.316553592681885, "learning_rate": 8.222443544082522e-06, "loss": 0.3258, "step": 293870 }, { "epoch": 1.7468837491306597, "grad_norm": 3.682722330093384, "learning_rate": 8.222284889958235e-06, "loss": 0.3262, "step": 293880 }, { "epoch": 1.746943191207328, "grad_norm": 5.033317565917969, "learning_rate": 8.222126230284785e-06, "loss": 0.3337, "step": 293890 }, { "epoch": 1.7470026332839965, "grad_norm": 5.12964391708374, "learning_rate": 8.221967565062454e-06, "loss": 0.3414, "step": 293900 }, { "epoch": 1.747062075360665, "grad_norm": 4.583791732788086, "learning_rate": 8.221808894291507e-06, "loss": 0.3085, "step": 293910 }, { "epoch": 1.7471215174373333, "grad_norm": 5.041548728942871, "learning_rate": 8.221650217972224e-06, "loss": 0.3298, "step": 293920 }, { "epoch": 1.7471809595140015, "grad_norm": 4.150269985198975, "learning_rate": 8.221491536104873e-06, "loss": 0.316, "step": 293930 }, { "epoch": 1.74724040159067, "grad_norm": 5.47061824798584, "learning_rate": 8.22133284868973e-06, "loss": 0.3404, "step": 293940 }, { "epoch": 1.7472998436673384, "grad_norm": 5.196298122406006, "learning_rate": 8.221174155727066e-06, "loss": 0.3195, "step": 293950 }, { "epoch": 1.7473592857440068, "grad_norm": 5.481953144073486, "learning_rate": 8.221015457217156e-06, "loss": 0.3852, "step": 293960 }, { "epoch": 1.747418727820675, "grad_norm": 5.570820331573486, "learning_rate": 8.220856753160273e-06, "loss": 0.3304, "step": 293970 }, { "epoch": 1.7474781698973434, "grad_norm": 5.520693302154541, "learning_rate": 8.220698043556693e-06, "loss": 0.3253, "step": 293980 }, { "epoch": 1.7475376119740118, "grad_norm": 6.979237079620361, "learning_rate": 8.220539328406683e-06, "loss": 0.3026, "step": 293990 }, { "epoch": 1.7475970540506802, "grad_norm": 4.936462879180908, "learning_rate": 8.220380607710522e-06, "loss": 0.3183, "step": 294000 }, { "epoch": 1.7476564961273486, "grad_norm": 4.672348976135254, "learning_rate": 8.22022188146848e-06, "loss": 0.3256, "step": 294010 }, { "epoch": 1.747715938204017, "grad_norm": 5.728853702545166, "learning_rate": 8.220063149680832e-06, "loss": 0.3318, "step": 294020 }, { "epoch": 1.7477753802806855, "grad_norm": 4.064762592315674, "learning_rate": 8.219904412347853e-06, "loss": 0.3055, "step": 294030 }, { "epoch": 1.7478348223573539, "grad_norm": 5.910569667816162, "learning_rate": 8.219745669469813e-06, "loss": 0.3244, "step": 294040 }, { "epoch": 1.7478942644340223, "grad_norm": 3.9067745208740234, "learning_rate": 8.219586921046988e-06, "loss": 0.3118, "step": 294050 }, { "epoch": 1.7479537065106907, "grad_norm": 5.331332206726074, "learning_rate": 8.219428167079649e-06, "loss": 0.3202, "step": 294060 }, { "epoch": 1.7480131485873591, "grad_norm": 5.482355117797852, "learning_rate": 8.21926940756807e-06, "loss": 0.3146, "step": 294070 }, { "epoch": 1.7480725906640275, "grad_norm": 4.087424278259277, "learning_rate": 8.219110642512525e-06, "loss": 0.307, "step": 294080 }, { "epoch": 1.748132032740696, "grad_norm": 5.331298828125, "learning_rate": 8.21895187191329e-06, "loss": 0.3164, "step": 294090 }, { "epoch": 1.7481914748173644, "grad_norm": 5.292670249938965, "learning_rate": 8.218793095770631e-06, "loss": 0.3191, "step": 294100 }, { "epoch": 1.7482509168940326, "grad_norm": 5.979193210601807, "learning_rate": 8.21863431408483e-06, "loss": 0.3305, "step": 294110 }, { "epoch": 1.748310358970701, "grad_norm": 4.0851850509643555, "learning_rate": 8.218475526856156e-06, "loss": 0.2797, "step": 294120 }, { "epoch": 1.7483698010473694, "grad_norm": 3.9560494422912598, "learning_rate": 8.218316734084883e-06, "loss": 0.2783, "step": 294130 }, { "epoch": 1.7484292431240378, "grad_norm": 5.877142429351807, "learning_rate": 8.218157935771284e-06, "loss": 0.3103, "step": 294140 }, { "epoch": 1.7484886852007062, "grad_norm": 5.081494331359863, "learning_rate": 8.217999131915633e-06, "loss": 0.34, "step": 294150 }, { "epoch": 1.7485481272773744, "grad_norm": 4.676815032958984, "learning_rate": 8.217840322518205e-06, "loss": 0.3492, "step": 294160 }, { "epoch": 1.7486075693540428, "grad_norm": 5.376086235046387, "learning_rate": 8.21768150757927e-06, "loss": 0.332, "step": 294170 }, { "epoch": 1.7486670114307112, "grad_norm": 4.624396800994873, "learning_rate": 8.217522687099104e-06, "loss": 0.3169, "step": 294180 }, { "epoch": 1.7487264535073797, "grad_norm": 4.115337371826172, "learning_rate": 8.21736386107798e-06, "loss": 0.3391, "step": 294190 }, { "epoch": 1.748785895584048, "grad_norm": 4.485617160797119, "learning_rate": 8.217205029516173e-06, "loss": 0.2998, "step": 294200 }, { "epoch": 1.7488453376607165, "grad_norm": 4.942129135131836, "learning_rate": 8.217046192413953e-06, "loss": 0.337, "step": 294210 }, { "epoch": 1.748904779737385, "grad_norm": 4.163845539093018, "learning_rate": 8.216887349771597e-06, "loss": 0.3504, "step": 294220 }, { "epoch": 1.7489642218140533, "grad_norm": 5.317141056060791, "learning_rate": 8.216728501589378e-06, "loss": 0.3009, "step": 294230 }, { "epoch": 1.7490236638907217, "grad_norm": 4.931094169616699, "learning_rate": 8.216569647867567e-06, "loss": 0.2949, "step": 294240 }, { "epoch": 1.7490831059673901, "grad_norm": 3.3174777030944824, "learning_rate": 8.21641078860644e-06, "loss": 0.2976, "step": 294250 }, { "epoch": 1.7491425480440586, "grad_norm": 5.262207984924316, "learning_rate": 8.21625192380627e-06, "loss": 0.3315, "step": 294260 }, { "epoch": 1.749201990120727, "grad_norm": 4.935128688812256, "learning_rate": 8.21609305346733e-06, "loss": 0.3119, "step": 294270 }, { "epoch": 1.7492614321973954, "grad_norm": 4.95424222946167, "learning_rate": 8.215934177589895e-06, "loss": 0.3067, "step": 294280 }, { "epoch": 1.7493208742740638, "grad_norm": 4.57172966003418, "learning_rate": 8.215775296174235e-06, "loss": 0.3266, "step": 294290 }, { "epoch": 1.749380316350732, "grad_norm": 5.081357479095459, "learning_rate": 8.21561640922063e-06, "loss": 0.3046, "step": 294300 }, { "epoch": 1.7494397584274004, "grad_norm": 4.50724983215332, "learning_rate": 8.215457516729348e-06, "loss": 0.332, "step": 294310 }, { "epoch": 1.7494992005040688, "grad_norm": 4.097795009613037, "learning_rate": 8.215298618700663e-06, "loss": 0.3195, "step": 294320 }, { "epoch": 1.7495586425807372, "grad_norm": 5.774791240692139, "learning_rate": 8.21513971513485e-06, "loss": 0.3302, "step": 294330 }, { "epoch": 1.7496180846574054, "grad_norm": 6.051885604858398, "learning_rate": 8.214980806032186e-06, "loss": 0.3093, "step": 294340 }, { "epoch": 1.7496775267340738, "grad_norm": 3.9211020469665527, "learning_rate": 8.214821891392939e-06, "loss": 0.2589, "step": 294350 }, { "epoch": 1.7497369688107423, "grad_norm": 5.1007771492004395, "learning_rate": 8.214662971217387e-06, "loss": 0.3127, "step": 294360 }, { "epoch": 1.7497964108874107, "grad_norm": 5.111102104187012, "learning_rate": 8.2145040455058e-06, "loss": 0.2987, "step": 294370 }, { "epoch": 1.749855852964079, "grad_norm": 4.7017741203308105, "learning_rate": 8.214345114258455e-06, "loss": 0.311, "step": 294380 }, { "epoch": 1.7499152950407475, "grad_norm": 4.105687141418457, "learning_rate": 8.214186177475622e-06, "loss": 0.3017, "step": 294390 }, { "epoch": 1.749974737117416, "grad_norm": 5.027479648590088, "learning_rate": 8.21402723515758e-06, "loss": 0.3057, "step": 294400 }, { "epoch": 1.7500341791940843, "grad_norm": 5.036664962768555, "learning_rate": 8.213868287304596e-06, "loss": 0.3167, "step": 294410 }, { "epoch": 1.7500936212707527, "grad_norm": 5.412770748138428, "learning_rate": 8.213709333916951e-06, "loss": 0.318, "step": 294420 }, { "epoch": 1.7501530633474212, "grad_norm": 4.761646270751953, "learning_rate": 8.213550374994912e-06, "loss": 0.3099, "step": 294430 }, { "epoch": 1.7502125054240896, "grad_norm": 6.342932224273682, "learning_rate": 8.213391410538757e-06, "loss": 0.323, "step": 294440 }, { "epoch": 1.750271947500758, "grad_norm": 4.885812759399414, "learning_rate": 8.213232440548758e-06, "loss": 0.2923, "step": 294450 }, { "epoch": 1.7503313895774264, "grad_norm": 5.861350059509277, "learning_rate": 8.21307346502519e-06, "loss": 0.3325, "step": 294460 }, { "epoch": 1.7503908316540948, "grad_norm": 5.08750581741333, "learning_rate": 8.212914483968326e-06, "loss": 0.3432, "step": 294470 }, { "epoch": 1.750450273730763, "grad_norm": 4.379510402679443, "learning_rate": 8.21275549737844e-06, "loss": 0.2773, "step": 294480 }, { "epoch": 1.7505097158074314, "grad_norm": 5.788926601409912, "learning_rate": 8.212596505255806e-06, "loss": 0.3257, "step": 294490 }, { "epoch": 1.7505691578840998, "grad_norm": 5.193562030792236, "learning_rate": 8.212437507600696e-06, "loss": 0.3274, "step": 294500 }, { "epoch": 1.7506285999607683, "grad_norm": 4.223367691040039, "learning_rate": 8.212278504413388e-06, "loss": 0.3378, "step": 294510 }, { "epoch": 1.7506880420374367, "grad_norm": 6.014212608337402, "learning_rate": 8.212119495694151e-06, "loss": 0.2991, "step": 294520 }, { "epoch": 1.7507474841141049, "grad_norm": 5.011949062347412, "learning_rate": 8.211960481443262e-06, "loss": 0.2855, "step": 294530 }, { "epoch": 1.7508069261907733, "grad_norm": 5.179921627044678, "learning_rate": 8.211801461660992e-06, "loss": 0.3012, "step": 294540 }, { "epoch": 1.7508663682674417, "grad_norm": 4.741006851196289, "learning_rate": 8.21164243634762e-06, "loss": 0.3238, "step": 294550 }, { "epoch": 1.75092581034411, "grad_norm": 5.549642086029053, "learning_rate": 8.211483405503413e-06, "loss": 0.3191, "step": 294560 }, { "epoch": 1.7509852524207785, "grad_norm": 5.801891803741455, "learning_rate": 8.21132436912865e-06, "loss": 0.3138, "step": 294570 }, { "epoch": 1.751044694497447, "grad_norm": 5.177647113800049, "learning_rate": 8.211165327223604e-06, "loss": 0.3105, "step": 294580 }, { "epoch": 1.7511041365741153, "grad_norm": 4.605088710784912, "learning_rate": 8.211006279788546e-06, "loss": 0.3038, "step": 294590 }, { "epoch": 1.7511635786507838, "grad_norm": 4.336099147796631, "learning_rate": 8.210847226823754e-06, "loss": 0.3483, "step": 294600 }, { "epoch": 1.7512230207274522, "grad_norm": 4.5194220542907715, "learning_rate": 8.2106881683295e-06, "loss": 0.2986, "step": 294610 }, { "epoch": 1.7512824628041206, "grad_norm": 4.791754245758057, "learning_rate": 8.210529104306058e-06, "loss": 0.3091, "step": 294620 }, { "epoch": 1.751341904880789, "grad_norm": 5.9488372802734375, "learning_rate": 8.2103700347537e-06, "loss": 0.3085, "step": 294630 }, { "epoch": 1.7514013469574574, "grad_norm": 5.687824726104736, "learning_rate": 8.210210959672704e-06, "loss": 0.3244, "step": 294640 }, { "epoch": 1.7514607890341258, "grad_norm": 6.134141445159912, "learning_rate": 8.21005187906334e-06, "loss": 0.3152, "step": 294650 }, { "epoch": 1.7515202311107942, "grad_norm": 4.98339319229126, "learning_rate": 8.209892792925884e-06, "loss": 0.2958, "step": 294660 }, { "epoch": 1.7515796731874624, "grad_norm": 4.319579601287842, "learning_rate": 8.209733701260609e-06, "loss": 0.3518, "step": 294670 }, { "epoch": 1.7516391152641309, "grad_norm": 4.86904239654541, "learning_rate": 8.209574604067791e-06, "loss": 0.3534, "step": 294680 }, { "epoch": 1.7516985573407993, "grad_norm": 5.593754291534424, "learning_rate": 8.209415501347701e-06, "loss": 0.3053, "step": 294690 }, { "epoch": 1.7517579994174677, "grad_norm": 5.8892669677734375, "learning_rate": 8.209256393100616e-06, "loss": 0.3141, "step": 294700 }, { "epoch": 1.7518174414941359, "grad_norm": 4.609423637390137, "learning_rate": 8.209097279326808e-06, "loss": 0.3175, "step": 294710 }, { "epoch": 1.7518768835708043, "grad_norm": 4.875481605529785, "learning_rate": 8.208938160026551e-06, "loss": 0.2931, "step": 294720 }, { "epoch": 1.7519363256474727, "grad_norm": 5.639276504516602, "learning_rate": 8.20877903520012e-06, "loss": 0.3496, "step": 294730 }, { "epoch": 1.7519957677241411, "grad_norm": 5.249271869659424, "learning_rate": 8.20861990484779e-06, "loss": 0.2997, "step": 294740 }, { "epoch": 1.7520552098008095, "grad_norm": 5.234907150268555, "learning_rate": 8.208460768969832e-06, "loss": 0.3367, "step": 294750 }, { "epoch": 1.752114651877478, "grad_norm": 4.89741849899292, "learning_rate": 8.208301627566523e-06, "loss": 0.3075, "step": 294760 }, { "epoch": 1.7521740939541464, "grad_norm": 7.686731815338135, "learning_rate": 8.208142480638134e-06, "loss": 0.3555, "step": 294770 }, { "epoch": 1.7522335360308148, "grad_norm": 6.31206750869751, "learning_rate": 8.207983328184943e-06, "loss": 0.2971, "step": 294780 }, { "epoch": 1.7522929781074832, "grad_norm": 4.6067047119140625, "learning_rate": 8.207824170207222e-06, "loss": 0.2965, "step": 294790 }, { "epoch": 1.7523524201841516, "grad_norm": 6.600975036621094, "learning_rate": 8.207665006705244e-06, "loss": 0.319, "step": 294800 }, { "epoch": 1.75241186226082, "grad_norm": 7.122443675994873, "learning_rate": 8.207505837679284e-06, "loss": 0.3606, "step": 294810 }, { "epoch": 1.7524713043374884, "grad_norm": 3.1914193630218506, "learning_rate": 8.207346663129615e-06, "loss": 0.3157, "step": 294820 }, { "epoch": 1.7525307464141568, "grad_norm": 6.564229965209961, "learning_rate": 8.207187483056513e-06, "loss": 0.3282, "step": 294830 }, { "epoch": 1.7525901884908253, "grad_norm": 6.004141807556152, "learning_rate": 8.207028297460254e-06, "loss": 0.3447, "step": 294840 }, { "epoch": 1.7526496305674935, "grad_norm": 5.053372859954834, "learning_rate": 8.206869106341107e-06, "loss": 0.3097, "step": 294850 }, { "epoch": 1.7527090726441619, "grad_norm": 5.653716564178467, "learning_rate": 8.206709909699348e-06, "loss": 0.2951, "step": 294860 }, { "epoch": 1.7527685147208303, "grad_norm": 4.490056991577148, "learning_rate": 8.206550707535254e-06, "loss": 0.3255, "step": 294870 }, { "epoch": 1.7528279567974987, "grad_norm": 4.431553840637207, "learning_rate": 8.206391499849096e-06, "loss": 0.3055, "step": 294880 }, { "epoch": 1.7528873988741671, "grad_norm": 6.041015148162842, "learning_rate": 8.20623228664115e-06, "loss": 0.3028, "step": 294890 }, { "epoch": 1.7529468409508353, "grad_norm": 5.102680206298828, "learning_rate": 8.20607306791169e-06, "loss": 0.302, "step": 294900 }, { "epoch": 1.7530062830275037, "grad_norm": 4.516477108001709, "learning_rate": 8.205913843660988e-06, "loss": 0.3255, "step": 294910 }, { "epoch": 1.7530657251041721, "grad_norm": 5.050586700439453, "learning_rate": 8.20575461388932e-06, "loss": 0.3009, "step": 294920 }, { "epoch": 1.7531251671808405, "grad_norm": 8.652222633361816, "learning_rate": 8.205595378596962e-06, "loss": 0.3683, "step": 294930 }, { "epoch": 1.753184609257509, "grad_norm": 5.1601643562316895, "learning_rate": 8.205436137784184e-06, "loss": 0.3115, "step": 294940 }, { "epoch": 1.7532440513341774, "grad_norm": 5.400936126708984, "learning_rate": 8.205276891451264e-06, "loss": 0.2966, "step": 294950 }, { "epoch": 1.7533034934108458, "grad_norm": 4.345040321350098, "learning_rate": 8.205117639598475e-06, "loss": 0.3447, "step": 294960 }, { "epoch": 1.7533629354875142, "grad_norm": 5.120326042175293, "learning_rate": 8.20495838222609e-06, "loss": 0.3179, "step": 294970 }, { "epoch": 1.7534223775641826, "grad_norm": 5.576148509979248, "learning_rate": 8.204799119334383e-06, "loss": 0.3173, "step": 294980 }, { "epoch": 1.753481819640851, "grad_norm": 4.781623363494873, "learning_rate": 8.204639850923633e-06, "loss": 0.3157, "step": 294990 }, { "epoch": 1.7535412617175195, "grad_norm": 5.440637111663818, "learning_rate": 8.204480576994106e-06, "loss": 0.3217, "step": 295000 }, { "epoch": 1.7536007037941879, "grad_norm": 4.204783916473389, "learning_rate": 8.204321297546086e-06, "loss": 0.296, "step": 295010 }, { "epoch": 1.7536601458708563, "grad_norm": 5.078603267669678, "learning_rate": 8.20416201257984e-06, "loss": 0.3142, "step": 295020 }, { "epoch": 1.7537195879475247, "grad_norm": 4.724582195281982, "learning_rate": 8.204002722095645e-06, "loss": 0.3248, "step": 295030 }, { "epoch": 1.7537790300241929, "grad_norm": 5.174854755401611, "learning_rate": 8.203843426093775e-06, "loss": 0.3346, "step": 295040 }, { "epoch": 1.7538384721008613, "grad_norm": 6.387901782989502, "learning_rate": 8.203684124574505e-06, "loss": 0.3313, "step": 295050 }, { "epoch": 1.7538979141775297, "grad_norm": 4.716275691986084, "learning_rate": 8.203524817538107e-06, "loss": 0.3281, "step": 295060 }, { "epoch": 1.7539573562541981, "grad_norm": 4.168235778808594, "learning_rate": 8.203365504984859e-06, "loss": 0.3052, "step": 295070 }, { "epoch": 1.7540167983308663, "grad_norm": 5.503393173217773, "learning_rate": 8.203206186915031e-06, "loss": 0.3453, "step": 295080 }, { "epoch": 1.7540762404075347, "grad_norm": 3.9414496421813965, "learning_rate": 8.203046863328902e-06, "loss": 0.2695, "step": 295090 }, { "epoch": 1.7541356824842032, "grad_norm": 4.3164801597595215, "learning_rate": 8.202887534226743e-06, "loss": 0.2904, "step": 295100 }, { "epoch": 1.7541951245608716, "grad_norm": 4.386247158050537, "learning_rate": 8.20272819960883e-06, "loss": 0.3205, "step": 295110 }, { "epoch": 1.75425456663754, "grad_norm": 5.780656337738037, "learning_rate": 8.202568859475437e-06, "loss": 0.3415, "step": 295120 }, { "epoch": 1.7543140087142084, "grad_norm": 4.374836444854736, "learning_rate": 8.202409513826838e-06, "loss": 0.3029, "step": 295130 }, { "epoch": 1.7543734507908768, "grad_norm": 4.981132507324219, "learning_rate": 8.202250162663309e-06, "loss": 0.3557, "step": 295140 }, { "epoch": 1.7544328928675452, "grad_norm": 5.455638408660889, "learning_rate": 8.20209080598512e-06, "loss": 0.3493, "step": 295150 }, { "epoch": 1.7544923349442136, "grad_norm": 4.991544723510742, "learning_rate": 8.201931443792552e-06, "loss": 0.2889, "step": 295160 }, { "epoch": 1.754551777020882, "grad_norm": 8.187877655029297, "learning_rate": 8.201772076085873e-06, "loss": 0.3447, "step": 295170 }, { "epoch": 1.7546112190975505, "grad_norm": 4.711576461791992, "learning_rate": 8.201612702865362e-06, "loss": 0.2935, "step": 295180 }, { "epoch": 1.7546706611742189, "grad_norm": 5.269411563873291, "learning_rate": 8.201453324131292e-06, "loss": 0.3079, "step": 295190 }, { "epoch": 1.7547301032508873, "grad_norm": 5.472836971282959, "learning_rate": 8.201293939883936e-06, "loss": 0.2892, "step": 295200 }, { "epoch": 1.7547895453275557, "grad_norm": 6.417708873748779, "learning_rate": 8.201134550123572e-06, "loss": 0.332, "step": 295210 }, { "epoch": 1.754848987404224, "grad_norm": 4.565943717956543, "learning_rate": 8.20097515485047e-06, "loss": 0.3109, "step": 295220 }, { "epoch": 1.7549084294808923, "grad_norm": 3.5753235816955566, "learning_rate": 8.20081575406491e-06, "loss": 0.2711, "step": 295230 }, { "epoch": 1.7549678715575607, "grad_norm": 4.4775543212890625, "learning_rate": 8.200656347767161e-06, "loss": 0.308, "step": 295240 }, { "epoch": 1.7550273136342291, "grad_norm": 4.479088306427002, "learning_rate": 8.2004969359575e-06, "loss": 0.3199, "step": 295250 }, { "epoch": 1.7550867557108976, "grad_norm": 4.811402320861816, "learning_rate": 8.200337518636203e-06, "loss": 0.3282, "step": 295260 }, { "epoch": 1.7551461977875658, "grad_norm": 4.826910018920898, "learning_rate": 8.200178095803541e-06, "loss": 0.3186, "step": 295270 }, { "epoch": 1.7552056398642342, "grad_norm": 5.902420520782471, "learning_rate": 8.200018667459791e-06, "loss": 0.3306, "step": 295280 }, { "epoch": 1.7552650819409026, "grad_norm": 3.813823699951172, "learning_rate": 8.199859233605228e-06, "loss": 0.3043, "step": 295290 }, { "epoch": 1.755324524017571, "grad_norm": 4.989192485809326, "learning_rate": 8.199699794240124e-06, "loss": 0.294, "step": 295300 }, { "epoch": 1.7553839660942394, "grad_norm": 5.578225135803223, "learning_rate": 8.199540349364756e-06, "loss": 0.3573, "step": 295310 }, { "epoch": 1.7554434081709078, "grad_norm": 5.0110578536987305, "learning_rate": 8.1993808989794e-06, "loss": 0.3406, "step": 295320 }, { "epoch": 1.7555028502475762, "grad_norm": 5.673133373260498, "learning_rate": 8.199221443084324e-06, "loss": 0.3082, "step": 295330 }, { "epoch": 1.7555622923242447, "grad_norm": 4.978925704956055, "learning_rate": 8.199061981679811e-06, "loss": 0.3422, "step": 295340 }, { "epoch": 1.755621734400913, "grad_norm": 4.755255699157715, "learning_rate": 8.19890251476613e-06, "loss": 0.2937, "step": 295350 }, { "epoch": 1.7556811764775815, "grad_norm": 6.448142051696777, "learning_rate": 8.198743042343556e-06, "loss": 0.2965, "step": 295360 }, { "epoch": 1.75574061855425, "grad_norm": 5.335115432739258, "learning_rate": 8.198583564412366e-06, "loss": 0.3296, "step": 295370 }, { "epoch": 1.7558000606309183, "grad_norm": 6.169192790985107, "learning_rate": 8.198424080972833e-06, "loss": 0.3106, "step": 295380 }, { "epoch": 1.7558595027075867, "grad_norm": 5.194125652313232, "learning_rate": 8.19826459202523e-06, "loss": 0.2975, "step": 295390 }, { "epoch": 1.7559189447842551, "grad_norm": 3.804145336151123, "learning_rate": 8.198105097569838e-06, "loss": 0.3095, "step": 295400 }, { "epoch": 1.7559783868609233, "grad_norm": 4.154376029968262, "learning_rate": 8.197945597606925e-06, "loss": 0.3023, "step": 295410 }, { "epoch": 1.7560378289375917, "grad_norm": 4.311051368713379, "learning_rate": 8.197786092136767e-06, "loss": 0.3018, "step": 295420 }, { "epoch": 1.7560972710142602, "grad_norm": 5.943682670593262, "learning_rate": 8.197626581159643e-06, "loss": 0.3355, "step": 295430 }, { "epoch": 1.7561567130909286, "grad_norm": 4.52408504486084, "learning_rate": 8.197467064675823e-06, "loss": 0.3076, "step": 295440 }, { "epoch": 1.7562161551675968, "grad_norm": 6.199961185455322, "learning_rate": 8.197307542685582e-06, "loss": 0.3486, "step": 295450 }, { "epoch": 1.7562755972442652, "grad_norm": 5.827255725860596, "learning_rate": 8.197148015189198e-06, "loss": 0.3089, "step": 295460 }, { "epoch": 1.7563350393209336, "grad_norm": 6.643496513366699, "learning_rate": 8.196988482186943e-06, "loss": 0.3012, "step": 295470 }, { "epoch": 1.756394481397602, "grad_norm": 6.128367900848389, "learning_rate": 8.196828943679092e-06, "loss": 0.3673, "step": 295480 }, { "epoch": 1.7564539234742704, "grad_norm": 5.510671615600586, "learning_rate": 8.196669399665919e-06, "loss": 0.3171, "step": 295490 }, { "epoch": 1.7565133655509388, "grad_norm": 5.596608638763428, "learning_rate": 8.196509850147702e-06, "loss": 0.2904, "step": 295500 }, { "epoch": 1.7565728076276073, "grad_norm": 4.031999588012695, "learning_rate": 8.196350295124712e-06, "loss": 0.3273, "step": 295510 }, { "epoch": 1.7566322497042757, "grad_norm": 4.299255847930908, "learning_rate": 8.196190734597225e-06, "loss": 0.2922, "step": 295520 }, { "epoch": 1.756691691780944, "grad_norm": 4.240139007568359, "learning_rate": 8.196031168565519e-06, "loss": 0.2999, "step": 295530 }, { "epoch": 1.7567511338576125, "grad_norm": 5.521426677703857, "learning_rate": 8.195871597029863e-06, "loss": 0.3159, "step": 295540 }, { "epoch": 1.756810575934281, "grad_norm": 5.564972400665283, "learning_rate": 8.195712019990536e-06, "loss": 0.3077, "step": 295550 }, { "epoch": 1.7568700180109493, "grad_norm": 5.647010803222656, "learning_rate": 8.195552437447811e-06, "loss": 0.2978, "step": 295560 }, { "epoch": 1.7569294600876177, "grad_norm": 5.235191822052002, "learning_rate": 8.195392849401966e-06, "loss": 0.3047, "step": 295570 }, { "epoch": 1.7569889021642862, "grad_norm": 6.018266201019287, "learning_rate": 8.19523325585327e-06, "loss": 0.3154, "step": 295580 }, { "epoch": 1.7570483442409544, "grad_norm": 5.236483573913574, "learning_rate": 8.195073656802002e-06, "loss": 0.3493, "step": 295590 }, { "epoch": 1.7571077863176228, "grad_norm": 5.294860363006592, "learning_rate": 8.194914052248438e-06, "loss": 0.2463, "step": 295600 }, { "epoch": 1.7571672283942912, "grad_norm": 5.087251663208008, "learning_rate": 8.194754442192848e-06, "loss": 0.3357, "step": 295610 }, { "epoch": 1.7572266704709596, "grad_norm": 4.195400714874268, "learning_rate": 8.194594826635511e-06, "loss": 0.303, "step": 295620 }, { "epoch": 1.757286112547628, "grad_norm": 5.009130954742432, "learning_rate": 8.194435205576699e-06, "loss": 0.3059, "step": 295630 }, { "epoch": 1.7573455546242962, "grad_norm": 4.935783386230469, "learning_rate": 8.19427557901669e-06, "loss": 0.3037, "step": 295640 }, { "epoch": 1.7574049967009646, "grad_norm": 4.417766571044922, "learning_rate": 8.194115946955756e-06, "loss": 0.3144, "step": 295650 }, { "epoch": 1.757464438777633, "grad_norm": 5.198586940765381, "learning_rate": 8.193956309394176e-06, "loss": 0.2784, "step": 295660 }, { "epoch": 1.7575238808543014, "grad_norm": 4.583455562591553, "learning_rate": 8.19379666633222e-06, "loss": 0.3016, "step": 295670 }, { "epoch": 1.7575833229309699, "grad_norm": 4.820418834686279, "learning_rate": 8.193637017770165e-06, "loss": 0.3373, "step": 295680 }, { "epoch": 1.7576427650076383, "grad_norm": 6.6031694412231445, "learning_rate": 8.193477363708286e-06, "loss": 0.3139, "step": 295690 }, { "epoch": 1.7577022070843067, "grad_norm": 4.998754024505615, "learning_rate": 8.19331770414686e-06, "loss": 0.3049, "step": 295700 }, { "epoch": 1.757761649160975, "grad_norm": 5.428272247314453, "learning_rate": 8.193158039086157e-06, "loss": 0.357, "step": 295710 }, { "epoch": 1.7578210912376435, "grad_norm": 5.105899810791016, "learning_rate": 8.192998368526457e-06, "loss": 0.2718, "step": 295720 }, { "epoch": 1.757880533314312, "grad_norm": 4.1537251472473145, "learning_rate": 8.192838692468031e-06, "loss": 0.3218, "step": 295730 }, { "epoch": 1.7579399753909803, "grad_norm": 5.020552635192871, "learning_rate": 8.192679010911156e-06, "loss": 0.3384, "step": 295740 }, { "epoch": 1.7579994174676488, "grad_norm": 4.5245771408081055, "learning_rate": 8.192519323856107e-06, "loss": 0.2673, "step": 295750 }, { "epoch": 1.7580588595443172, "grad_norm": 4.497067928314209, "learning_rate": 8.19235963130316e-06, "loss": 0.2813, "step": 295760 }, { "epoch": 1.7581183016209856, "grad_norm": 5.732623100280762, "learning_rate": 8.19219993325259e-06, "loss": 0.2875, "step": 295770 }, { "epoch": 1.7581777436976538, "grad_norm": 5.212900638580322, "learning_rate": 8.192040229704668e-06, "loss": 0.3007, "step": 295780 }, { "epoch": 1.7582371857743222, "grad_norm": 5.540855884552002, "learning_rate": 8.191880520659673e-06, "loss": 0.3147, "step": 295790 }, { "epoch": 1.7582966278509906, "grad_norm": 3.6342015266418457, "learning_rate": 8.191720806117877e-06, "loss": 0.3117, "step": 295800 }, { "epoch": 1.758356069927659, "grad_norm": 3.9351134300231934, "learning_rate": 8.19156108607956e-06, "loss": 0.3237, "step": 295810 }, { "epoch": 1.7584155120043272, "grad_norm": 4.954431056976318, "learning_rate": 8.191401360544992e-06, "loss": 0.3341, "step": 295820 }, { "epoch": 1.7584749540809956, "grad_norm": 4.9048662185668945, "learning_rate": 8.191241629514452e-06, "loss": 0.3083, "step": 295830 }, { "epoch": 1.758534396157664, "grad_norm": 5.030706405639648, "learning_rate": 8.191081892988212e-06, "loss": 0.3132, "step": 295840 }, { "epoch": 1.7585938382343325, "grad_norm": 4.307393550872803, "learning_rate": 8.190922150966547e-06, "loss": 0.299, "step": 295850 }, { "epoch": 1.7586532803110009, "grad_norm": 4.68196439743042, "learning_rate": 8.190762403449735e-06, "loss": 0.3038, "step": 295860 }, { "epoch": 1.7587127223876693, "grad_norm": 5.5030059814453125, "learning_rate": 8.190602650438048e-06, "loss": 0.3346, "step": 295870 }, { "epoch": 1.7587721644643377, "grad_norm": 5.605547904968262, "learning_rate": 8.190442891931764e-06, "loss": 0.272, "step": 295880 }, { "epoch": 1.7588316065410061, "grad_norm": 4.694082260131836, "learning_rate": 8.190283127931156e-06, "loss": 0.2727, "step": 295890 }, { "epoch": 1.7588910486176745, "grad_norm": 6.963851451873779, "learning_rate": 8.190123358436499e-06, "loss": 0.3173, "step": 295900 }, { "epoch": 1.758950490694343, "grad_norm": 5.291501998901367, "learning_rate": 8.189963583448071e-06, "loss": 0.3226, "step": 295910 }, { "epoch": 1.7590099327710114, "grad_norm": 5.023448944091797, "learning_rate": 8.189803802966144e-06, "loss": 0.3229, "step": 295920 }, { "epoch": 1.7590693748476798, "grad_norm": 5.361881732940674, "learning_rate": 8.189644016990994e-06, "loss": 0.3282, "step": 295930 }, { "epoch": 1.7591288169243482, "grad_norm": 5.984918117523193, "learning_rate": 8.189484225522896e-06, "loss": 0.3184, "step": 295940 }, { "epoch": 1.7591882590010166, "grad_norm": 5.976080894470215, "learning_rate": 8.189324428562127e-06, "loss": 0.3029, "step": 295950 }, { "epoch": 1.7592477010776848, "grad_norm": 6.544199466705322, "learning_rate": 8.189164626108958e-06, "loss": 0.3306, "step": 295960 }, { "epoch": 1.7593071431543532, "grad_norm": 5.158444404602051, "learning_rate": 8.189004818163669e-06, "loss": 0.3274, "step": 295970 }, { "epoch": 1.7593665852310216, "grad_norm": 5.876778602600098, "learning_rate": 8.188845004726534e-06, "loss": 0.3217, "step": 295980 }, { "epoch": 1.75942602730769, "grad_norm": 4.54480504989624, "learning_rate": 8.188685185797826e-06, "loss": 0.3159, "step": 295990 }, { "epoch": 1.7594854693843585, "grad_norm": 5.128086090087891, "learning_rate": 8.188525361377821e-06, "loss": 0.3403, "step": 296000 }, { "epoch": 1.7595449114610267, "grad_norm": 3.8138535022735596, "learning_rate": 8.188365531466798e-06, "loss": 0.2925, "step": 296010 }, { "epoch": 1.759604353537695, "grad_norm": 5.0892333984375, "learning_rate": 8.188205696065026e-06, "loss": 0.2788, "step": 296020 }, { "epoch": 1.7596637956143635, "grad_norm": 5.344953536987305, "learning_rate": 8.188045855172785e-06, "loss": 0.308, "step": 296030 }, { "epoch": 1.759723237691032, "grad_norm": 4.14773416519165, "learning_rate": 8.187886008790349e-06, "loss": 0.2936, "step": 296040 }, { "epoch": 1.7597826797677003, "grad_norm": 6.282765865325928, "learning_rate": 8.187726156917992e-06, "loss": 0.2948, "step": 296050 }, { "epoch": 1.7598421218443687, "grad_norm": 5.317302703857422, "learning_rate": 8.187566299555988e-06, "loss": 0.3015, "step": 296060 }, { "epoch": 1.7599015639210371, "grad_norm": 4.956201076507568, "learning_rate": 8.187406436704618e-06, "loss": 0.3414, "step": 296070 }, { "epoch": 1.7599610059977056, "grad_norm": 4.902065277099609, "learning_rate": 8.187246568364154e-06, "loss": 0.286, "step": 296080 }, { "epoch": 1.760020448074374, "grad_norm": 6.547638893127441, "learning_rate": 8.187086694534868e-06, "loss": 0.2995, "step": 296090 }, { "epoch": 1.7600798901510424, "grad_norm": 5.3167901039123535, "learning_rate": 8.18692681521704e-06, "loss": 0.3364, "step": 296100 }, { "epoch": 1.7601393322277108, "grad_norm": 4.412014007568359, "learning_rate": 8.186766930410945e-06, "loss": 0.3152, "step": 296110 }, { "epoch": 1.7601987743043792, "grad_norm": 5.137485980987549, "learning_rate": 8.186607040116856e-06, "loss": 0.3006, "step": 296120 }, { "epoch": 1.7602582163810476, "grad_norm": 5.3672895431518555, "learning_rate": 8.18644714433505e-06, "loss": 0.3434, "step": 296130 }, { "epoch": 1.760317658457716, "grad_norm": 4.38588285446167, "learning_rate": 8.1862872430658e-06, "loss": 0.2918, "step": 296140 }, { "epoch": 1.7603771005343842, "grad_norm": 4.969870567321777, "learning_rate": 8.186127336309385e-06, "loss": 0.3284, "step": 296150 }, { "epoch": 1.7604365426110526, "grad_norm": 5.246908187866211, "learning_rate": 8.185967424066078e-06, "loss": 0.3219, "step": 296160 }, { "epoch": 1.760495984687721, "grad_norm": 4.649540901184082, "learning_rate": 8.185807506336156e-06, "loss": 0.3188, "step": 296170 }, { "epoch": 1.7605554267643895, "grad_norm": 4.818814277648926, "learning_rate": 8.185647583119892e-06, "loss": 0.3001, "step": 296180 }, { "epoch": 1.7606148688410577, "grad_norm": 4.12794303894043, "learning_rate": 8.185487654417563e-06, "loss": 0.3068, "step": 296190 }, { "epoch": 1.760674310917726, "grad_norm": 3.232936143875122, "learning_rate": 8.185327720229443e-06, "loss": 0.3349, "step": 296200 }, { "epoch": 1.7607337529943945, "grad_norm": 5.558957099914551, "learning_rate": 8.18516778055581e-06, "loss": 0.3131, "step": 296210 }, { "epoch": 1.760793195071063, "grad_norm": 5.847671985626221, "learning_rate": 8.185007835396938e-06, "loss": 0.3205, "step": 296220 }, { "epoch": 1.7608526371477313, "grad_norm": 5.394564628601074, "learning_rate": 8.184847884753103e-06, "loss": 0.311, "step": 296230 }, { "epoch": 1.7609120792243997, "grad_norm": 5.213476181030273, "learning_rate": 8.18468792862458e-06, "loss": 0.3218, "step": 296240 }, { "epoch": 1.7609715213010682, "grad_norm": 3.5797266960144043, "learning_rate": 8.184527967011644e-06, "loss": 0.3136, "step": 296250 }, { "epoch": 1.7610309633777366, "grad_norm": 6.617773056030273, "learning_rate": 8.18436799991457e-06, "loss": 0.3019, "step": 296260 }, { "epoch": 1.761090405454405, "grad_norm": 4.852109909057617, "learning_rate": 8.184208027333635e-06, "loss": 0.3314, "step": 296270 }, { "epoch": 1.7611498475310734, "grad_norm": 5.32254695892334, "learning_rate": 8.184048049269113e-06, "loss": 0.2816, "step": 296280 }, { "epoch": 1.7612092896077418, "grad_norm": 4.851080894470215, "learning_rate": 8.183888065721282e-06, "loss": 0.3261, "step": 296290 }, { "epoch": 1.7612687316844102, "grad_norm": 6.229223251342773, "learning_rate": 8.183728076690413e-06, "loss": 0.3006, "step": 296300 }, { "epoch": 1.7613281737610786, "grad_norm": 5.840326309204102, "learning_rate": 8.183568082176787e-06, "loss": 0.3067, "step": 296310 }, { "epoch": 1.761387615837747, "grad_norm": 5.340787887573242, "learning_rate": 8.183408082180677e-06, "loss": 0.2899, "step": 296320 }, { "epoch": 1.7614470579144152, "grad_norm": 6.307971477508545, "learning_rate": 8.183248076702357e-06, "loss": 0.3369, "step": 296330 }, { "epoch": 1.7615064999910837, "grad_norm": 4.885294437408447, "learning_rate": 8.183088065742105e-06, "loss": 0.3065, "step": 296340 }, { "epoch": 1.761565942067752, "grad_norm": 4.622236251831055, "learning_rate": 8.182928049300197e-06, "loss": 0.286, "step": 296350 }, { "epoch": 1.7616253841444205, "grad_norm": 5.510340690612793, "learning_rate": 8.182768027376904e-06, "loss": 0.3183, "step": 296360 }, { "epoch": 1.761684826221089, "grad_norm": 5.667346477508545, "learning_rate": 8.182607999972506e-06, "loss": 0.3225, "step": 296370 }, { "epoch": 1.761744268297757, "grad_norm": 4.349517345428467, "learning_rate": 8.182447967087277e-06, "loss": 0.3424, "step": 296380 }, { "epoch": 1.7618037103744255, "grad_norm": 5.353257179260254, "learning_rate": 8.182287928721495e-06, "loss": 0.3065, "step": 296390 }, { "epoch": 1.761863152451094, "grad_norm": 4.786147594451904, "learning_rate": 8.18212788487543e-06, "loss": 0.3296, "step": 296400 }, { "epoch": 1.7619225945277623, "grad_norm": 4.343588829040527, "learning_rate": 8.181967835549363e-06, "loss": 0.2971, "step": 296410 }, { "epoch": 1.7619820366044308, "grad_norm": 5.118738651275635, "learning_rate": 8.181807780743569e-06, "loss": 0.3111, "step": 296420 }, { "epoch": 1.7620414786810992, "grad_norm": 4.840119361877441, "learning_rate": 8.181647720458319e-06, "loss": 0.2955, "step": 296430 }, { "epoch": 1.7621009207577676, "grad_norm": 5.167783260345459, "learning_rate": 8.181487654693893e-06, "loss": 0.2854, "step": 296440 }, { "epoch": 1.762160362834436, "grad_norm": 3.697910785675049, "learning_rate": 8.18132758345057e-06, "loss": 0.3084, "step": 296450 }, { "epoch": 1.7622198049111044, "grad_norm": 3.631843328475952, "learning_rate": 8.181167506728616e-06, "loss": 0.3132, "step": 296460 }, { "epoch": 1.7622792469877728, "grad_norm": 5.505855560302734, "learning_rate": 8.181007424528313e-06, "loss": 0.3127, "step": 296470 }, { "epoch": 1.7623386890644412, "grad_norm": 5.882466793060303, "learning_rate": 8.180847336849938e-06, "loss": 0.2791, "step": 296480 }, { "epoch": 1.7623981311411097, "grad_norm": 4.536003112792969, "learning_rate": 8.180687243693763e-06, "loss": 0.2859, "step": 296490 }, { "epoch": 1.762457573217778, "grad_norm": 6.949814796447754, "learning_rate": 8.180527145060063e-06, "loss": 0.317, "step": 296500 }, { "epoch": 1.7625170152944465, "grad_norm": 5.171996116638184, "learning_rate": 8.180367040949117e-06, "loss": 0.3225, "step": 296510 }, { "epoch": 1.7625764573711147, "grad_norm": 4.864716053009033, "learning_rate": 8.180206931361201e-06, "loss": 0.3169, "step": 296520 }, { "epoch": 1.762635899447783, "grad_norm": 4.447584629058838, "learning_rate": 8.18004681629659e-06, "loss": 0.3004, "step": 296530 }, { "epoch": 1.7626953415244515, "grad_norm": 4.678493976593018, "learning_rate": 8.179886695755558e-06, "loss": 0.2927, "step": 296540 }, { "epoch": 1.76275478360112, "grad_norm": 4.4412007331848145, "learning_rate": 8.17972656973838e-06, "loss": 0.3243, "step": 296550 }, { "epoch": 1.7628142256777881, "grad_norm": 5.002131938934326, "learning_rate": 8.179566438245334e-06, "loss": 0.3177, "step": 296560 }, { "epoch": 1.7628736677544565, "grad_norm": 6.089526653289795, "learning_rate": 8.179406301276695e-06, "loss": 0.3269, "step": 296570 }, { "epoch": 1.762933109831125, "grad_norm": 5.27114200592041, "learning_rate": 8.17924615883274e-06, "loss": 0.3292, "step": 296580 }, { "epoch": 1.7629925519077934, "grad_norm": 6.092923641204834, "learning_rate": 8.179086010913744e-06, "loss": 0.2938, "step": 296590 }, { "epoch": 1.7630519939844618, "grad_norm": 5.212093830108643, "learning_rate": 8.178925857519981e-06, "loss": 0.322, "step": 296600 }, { "epoch": 1.7631114360611302, "grad_norm": 5.7022881507873535, "learning_rate": 8.17876569865173e-06, "loss": 0.3442, "step": 296610 }, { "epoch": 1.7631708781377986, "grad_norm": 5.480710983276367, "learning_rate": 8.178605534309264e-06, "loss": 0.3331, "step": 296620 }, { "epoch": 1.763230320214467, "grad_norm": 5.0371174812316895, "learning_rate": 8.17844536449286e-06, "loss": 0.3261, "step": 296630 }, { "epoch": 1.7632897622911354, "grad_norm": 4.805577278137207, "learning_rate": 8.178285189202795e-06, "loss": 0.3248, "step": 296640 }, { "epoch": 1.7633492043678038, "grad_norm": 4.699958801269531, "learning_rate": 8.178125008439344e-06, "loss": 0.3167, "step": 296650 }, { "epoch": 1.7634086464444723, "grad_norm": 5.378582000732422, "learning_rate": 8.177964822202781e-06, "loss": 0.3022, "step": 296660 }, { "epoch": 1.7634680885211407, "grad_norm": 5.810905933380127, "learning_rate": 8.177804630493385e-06, "loss": 0.3681, "step": 296670 }, { "epoch": 1.763527530597809, "grad_norm": 4.975376129150391, "learning_rate": 8.177644433311429e-06, "loss": 0.3162, "step": 296680 }, { "epoch": 1.7635869726744775, "grad_norm": 5.54744815826416, "learning_rate": 8.177484230657189e-06, "loss": 0.3009, "step": 296690 }, { "epoch": 1.7636464147511457, "grad_norm": 4.831430435180664, "learning_rate": 8.177324022530944e-06, "loss": 0.3001, "step": 296700 }, { "epoch": 1.7637058568278141, "grad_norm": 5.531678199768066, "learning_rate": 8.177163808932966e-06, "loss": 0.2931, "step": 296710 }, { "epoch": 1.7637652989044825, "grad_norm": 5.063685894012451, "learning_rate": 8.177003589863534e-06, "loss": 0.31, "step": 296720 }, { "epoch": 1.763824740981151, "grad_norm": 6.8000617027282715, "learning_rate": 8.176843365322924e-06, "loss": 0.3011, "step": 296730 }, { "epoch": 1.7638841830578194, "grad_norm": 4.358518600463867, "learning_rate": 8.17668313531141e-06, "loss": 0.3285, "step": 296740 }, { "epoch": 1.7639436251344875, "grad_norm": 5.120163917541504, "learning_rate": 8.176522899829267e-06, "loss": 0.3134, "step": 296750 }, { "epoch": 1.764003067211156, "grad_norm": 4.134200572967529, "learning_rate": 8.176362658876775e-06, "loss": 0.317, "step": 296760 }, { "epoch": 1.7640625092878244, "grad_norm": 5.712602138519287, "learning_rate": 8.176202412454207e-06, "loss": 0.3097, "step": 296770 }, { "epoch": 1.7641219513644928, "grad_norm": 6.50032901763916, "learning_rate": 8.176042160561837e-06, "loss": 0.3326, "step": 296780 }, { "epoch": 1.7641813934411612, "grad_norm": 4.824042320251465, "learning_rate": 8.175881903199945e-06, "loss": 0.3124, "step": 296790 }, { "epoch": 1.7642408355178296, "grad_norm": 4.136457443237305, "learning_rate": 8.175721640368805e-06, "loss": 0.3253, "step": 296800 }, { "epoch": 1.764300277594498, "grad_norm": 5.6441192626953125, "learning_rate": 8.175561372068694e-06, "loss": 0.327, "step": 296810 }, { "epoch": 1.7643597196711664, "grad_norm": 4.3949737548828125, "learning_rate": 8.175401098299889e-06, "loss": 0.322, "step": 296820 }, { "epoch": 1.7644191617478349, "grad_norm": 5.078719139099121, "learning_rate": 8.175240819062663e-06, "loss": 0.2884, "step": 296830 }, { "epoch": 1.7644786038245033, "grad_norm": 4.929742813110352, "learning_rate": 8.175080534357292e-06, "loss": 0.3129, "step": 296840 }, { "epoch": 1.7645380459011717, "grad_norm": 5.894698619842529, "learning_rate": 8.174920244184054e-06, "loss": 0.3365, "step": 296850 }, { "epoch": 1.76459748797784, "grad_norm": 6.381145000457764, "learning_rate": 8.174759948543225e-06, "loss": 0.3153, "step": 296860 }, { "epoch": 1.7646569300545085, "grad_norm": 3.4802355766296387, "learning_rate": 8.174599647435082e-06, "loss": 0.2852, "step": 296870 }, { "epoch": 1.764716372131177, "grad_norm": 5.25084924697876, "learning_rate": 8.1744393408599e-06, "loss": 0.3132, "step": 296880 }, { "epoch": 1.7647758142078451, "grad_norm": 5.228492736816406, "learning_rate": 8.174279028817951e-06, "loss": 0.3366, "step": 296890 }, { "epoch": 1.7648352562845135, "grad_norm": 4.958481788635254, "learning_rate": 8.174118711309519e-06, "loss": 0.3096, "step": 296900 }, { "epoch": 1.764894698361182, "grad_norm": 4.363556861877441, "learning_rate": 8.173958388334872e-06, "loss": 0.3264, "step": 296910 }, { "epoch": 1.7649541404378504, "grad_norm": 3.338268995285034, "learning_rate": 8.173798059894292e-06, "loss": 0.3034, "step": 296920 }, { "epoch": 1.7650135825145186, "grad_norm": 4.897923469543457, "learning_rate": 8.173637725988053e-06, "loss": 0.3058, "step": 296930 }, { "epoch": 1.765073024591187, "grad_norm": 5.122639179229736, "learning_rate": 8.173477386616431e-06, "loss": 0.2875, "step": 296940 }, { "epoch": 1.7651324666678554, "grad_norm": 5.505696773529053, "learning_rate": 8.1733170417797e-06, "loss": 0.3288, "step": 296950 }, { "epoch": 1.7651919087445238, "grad_norm": 5.465450286865234, "learning_rate": 8.173156691478141e-06, "loss": 0.3206, "step": 296960 }, { "epoch": 1.7652513508211922, "grad_norm": 5.396201133728027, "learning_rate": 8.172996335712027e-06, "loss": 0.3248, "step": 296970 }, { "epoch": 1.7653107928978606, "grad_norm": 4.749661445617676, "learning_rate": 8.172835974481636e-06, "loss": 0.322, "step": 296980 }, { "epoch": 1.765370234974529, "grad_norm": 5.882747173309326, "learning_rate": 8.172675607787242e-06, "loss": 0.309, "step": 296990 }, { "epoch": 1.7654296770511975, "grad_norm": 5.509256839752197, "learning_rate": 8.172515235629122e-06, "loss": 0.2898, "step": 297000 }, { "epoch": 1.7654891191278659, "grad_norm": 5.368101119995117, "learning_rate": 8.172354858007552e-06, "loss": 0.3781, "step": 297010 }, { "epoch": 1.7655485612045343, "grad_norm": 7.747151851654053, "learning_rate": 8.172194474922808e-06, "loss": 0.2927, "step": 297020 }, { "epoch": 1.7656080032812027, "grad_norm": 4.1858229637146, "learning_rate": 8.172034086375167e-06, "loss": 0.3294, "step": 297030 }, { "epoch": 1.7656674453578711, "grad_norm": 4.978925704956055, "learning_rate": 8.171873692364904e-06, "loss": 0.3125, "step": 297040 }, { "epoch": 1.7657268874345395, "grad_norm": 5.781925201416016, "learning_rate": 8.171713292892298e-06, "loss": 0.3518, "step": 297050 }, { "epoch": 1.765786329511208, "grad_norm": 5.341287136077881, "learning_rate": 8.17155288795762e-06, "loss": 0.2985, "step": 297060 }, { "epoch": 1.7658457715878761, "grad_norm": 6.052894592285156, "learning_rate": 8.171392477561152e-06, "loss": 0.2933, "step": 297070 }, { "epoch": 1.7659052136645446, "grad_norm": 7.139562129974365, "learning_rate": 8.171232061703169e-06, "loss": 0.3298, "step": 297080 }, { "epoch": 1.765964655741213, "grad_norm": 5.108866214752197, "learning_rate": 8.171071640383943e-06, "loss": 0.3185, "step": 297090 }, { "epoch": 1.7660240978178814, "grad_norm": 3.5427088737487793, "learning_rate": 8.170911213603756e-06, "loss": 0.2856, "step": 297100 }, { "epoch": 1.7660835398945498, "grad_norm": 5.365501880645752, "learning_rate": 8.170750781362879e-06, "loss": 0.3245, "step": 297110 }, { "epoch": 1.766142981971218, "grad_norm": 4.044704437255859, "learning_rate": 8.170590343661592e-06, "loss": 0.294, "step": 297120 }, { "epoch": 1.7662024240478864, "grad_norm": 4.765658855438232, "learning_rate": 8.170429900500172e-06, "loss": 0.2956, "step": 297130 }, { "epoch": 1.7662618661245548, "grad_norm": 4.4818525314331055, "learning_rate": 8.170269451878891e-06, "loss": 0.2909, "step": 297140 }, { "epoch": 1.7663213082012232, "grad_norm": 4.09840726852417, "learning_rate": 8.170108997798027e-06, "loss": 0.3159, "step": 297150 }, { "epoch": 1.7663807502778917, "grad_norm": 4.540935039520264, "learning_rate": 8.16994853825786e-06, "loss": 0.3306, "step": 297160 }, { "epoch": 1.76644019235456, "grad_norm": 4.008482933044434, "learning_rate": 8.16978807325866e-06, "loss": 0.3219, "step": 297170 }, { "epoch": 1.7664996344312285, "grad_norm": 5.10714054107666, "learning_rate": 8.16962760280071e-06, "loss": 0.2939, "step": 297180 }, { "epoch": 1.766559076507897, "grad_norm": 6.587578773498535, "learning_rate": 8.16946712688428e-06, "loss": 0.3082, "step": 297190 }, { "epoch": 1.7666185185845653, "grad_norm": 3.9036848545074463, "learning_rate": 8.169306645509651e-06, "loss": 0.3343, "step": 297200 }, { "epoch": 1.7666779606612337, "grad_norm": 4.763049602508545, "learning_rate": 8.1691461586771e-06, "loss": 0.3172, "step": 297210 }, { "epoch": 1.7667374027379021, "grad_norm": 4.930959701538086, "learning_rate": 8.168985666386898e-06, "loss": 0.338, "step": 297220 }, { "epoch": 1.7667968448145706, "grad_norm": 4.746018409729004, "learning_rate": 8.168825168639326e-06, "loss": 0.307, "step": 297230 }, { "epoch": 1.766856286891239, "grad_norm": 6.1818413734436035, "learning_rate": 8.168664665434659e-06, "loss": 0.3307, "step": 297240 }, { "epoch": 1.7669157289679074, "grad_norm": 6.006245136260986, "learning_rate": 8.168504156773172e-06, "loss": 0.3228, "step": 297250 }, { "epoch": 1.7669751710445756, "grad_norm": 4.74376106262207, "learning_rate": 8.168343642655143e-06, "loss": 0.3015, "step": 297260 }, { "epoch": 1.767034613121244, "grad_norm": 5.823909759521484, "learning_rate": 8.16818312308085e-06, "loss": 0.3233, "step": 297270 }, { "epoch": 1.7670940551979124, "grad_norm": 3.214003086090088, "learning_rate": 8.168022598050566e-06, "loss": 0.2993, "step": 297280 }, { "epoch": 1.7671534972745808, "grad_norm": 6.529485702514648, "learning_rate": 8.167862067564569e-06, "loss": 0.3106, "step": 297290 }, { "epoch": 1.767212939351249, "grad_norm": 3.6501801013946533, "learning_rate": 8.167701531623135e-06, "loss": 0.3057, "step": 297300 }, { "epoch": 1.7672723814279174, "grad_norm": 5.2034173011779785, "learning_rate": 8.167540990226544e-06, "loss": 0.3154, "step": 297310 }, { "epoch": 1.7673318235045858, "grad_norm": 4.218080997467041, "learning_rate": 8.167380443375067e-06, "loss": 0.3071, "step": 297320 }, { "epoch": 1.7673912655812543, "grad_norm": 4.056796550750732, "learning_rate": 8.167219891068983e-06, "loss": 0.316, "step": 297330 }, { "epoch": 1.7674507076579227, "grad_norm": 4.449352264404297, "learning_rate": 8.167059333308569e-06, "loss": 0.281, "step": 297340 }, { "epoch": 1.767510149734591, "grad_norm": 4.457604885101318, "learning_rate": 8.166898770094101e-06, "loss": 0.3005, "step": 297350 }, { "epoch": 1.7675695918112595, "grad_norm": 5.150149345397949, "learning_rate": 8.166738201425856e-06, "loss": 0.3194, "step": 297360 }, { "epoch": 1.767629033887928, "grad_norm": 4.602223873138428, "learning_rate": 8.16657762730411e-06, "loss": 0.332, "step": 297370 }, { "epoch": 1.7676884759645963, "grad_norm": 5.344515323638916, "learning_rate": 8.166417047729138e-06, "loss": 0.317, "step": 297380 }, { "epoch": 1.7677479180412647, "grad_norm": 4.506405830383301, "learning_rate": 8.166256462701219e-06, "loss": 0.3372, "step": 297390 }, { "epoch": 1.7678073601179332, "grad_norm": 5.133406639099121, "learning_rate": 8.166095872220627e-06, "loss": 0.297, "step": 297400 }, { "epoch": 1.7678668021946016, "grad_norm": 5.894493103027344, "learning_rate": 8.165935276287643e-06, "loss": 0.3241, "step": 297410 }, { "epoch": 1.76792624427127, "grad_norm": 5.462803840637207, "learning_rate": 8.165774674902538e-06, "loss": 0.3054, "step": 297420 }, { "epoch": 1.7679856863479384, "grad_norm": 5.971087455749512, "learning_rate": 8.165614068065594e-06, "loss": 0.2774, "step": 297430 }, { "epoch": 1.7680451284246066, "grad_norm": 3.9933197498321533, "learning_rate": 8.165453455777084e-06, "loss": 0.2944, "step": 297440 }, { "epoch": 1.768104570501275, "grad_norm": 4.886012554168701, "learning_rate": 8.165292838037284e-06, "loss": 0.3394, "step": 297450 }, { "epoch": 1.7681640125779434, "grad_norm": 5.157359600067139, "learning_rate": 8.165132214846473e-06, "loss": 0.2865, "step": 297460 }, { "epoch": 1.7682234546546118, "grad_norm": 4.689391613006592, "learning_rate": 8.164971586204926e-06, "loss": 0.2941, "step": 297470 }, { "epoch": 1.7682828967312803, "grad_norm": 5.2042555809021, "learning_rate": 8.164810952112921e-06, "loss": 0.3095, "step": 297480 }, { "epoch": 1.7683423388079484, "grad_norm": 5.440143585205078, "learning_rate": 8.164650312570734e-06, "loss": 0.2866, "step": 297490 }, { "epoch": 1.7684017808846169, "grad_norm": 4.242342472076416, "learning_rate": 8.16448966757864e-06, "loss": 0.2739, "step": 297500 }, { "epoch": 1.7684612229612853, "grad_norm": 4.285037994384766, "learning_rate": 8.16432901713692e-06, "loss": 0.2983, "step": 297510 }, { "epoch": 1.7685206650379537, "grad_norm": 4.0921220779418945, "learning_rate": 8.164168361245847e-06, "loss": 0.3261, "step": 297520 }, { "epoch": 1.768580107114622, "grad_norm": 4.853250980377197, "learning_rate": 8.164007699905697e-06, "loss": 0.3321, "step": 297530 }, { "epoch": 1.7686395491912905, "grad_norm": 4.375058174133301, "learning_rate": 8.16384703311675e-06, "loss": 0.2856, "step": 297540 }, { "epoch": 1.768698991267959, "grad_norm": 5.381117343902588, "learning_rate": 8.16368636087928e-06, "loss": 0.3399, "step": 297550 }, { "epoch": 1.7687584333446273, "grad_norm": 5.570542812347412, "learning_rate": 8.163525683193566e-06, "loss": 0.3279, "step": 297560 }, { "epoch": 1.7688178754212958, "grad_norm": 5.237552642822266, "learning_rate": 8.16336500005988e-06, "loss": 0.3381, "step": 297570 }, { "epoch": 1.7688773174979642, "grad_norm": 5.6741623878479, "learning_rate": 8.163204311478505e-06, "loss": 0.3016, "step": 297580 }, { "epoch": 1.7689367595746326, "grad_norm": 5.288206100463867, "learning_rate": 8.163043617449712e-06, "loss": 0.3015, "step": 297590 }, { "epoch": 1.768996201651301, "grad_norm": 6.6866278648376465, "learning_rate": 8.162882917973785e-06, "loss": 0.3024, "step": 297600 }, { "epoch": 1.7690556437279694, "grad_norm": 4.537544250488281, "learning_rate": 8.162722213050991e-06, "loss": 0.3084, "step": 297610 }, { "epoch": 1.7691150858046378, "grad_norm": 4.987977027893066, "learning_rate": 8.162561502681617e-06, "loss": 0.314, "step": 297620 }, { "epoch": 1.769174527881306, "grad_norm": 6.121054649353027, "learning_rate": 8.16240078686593e-06, "loss": 0.3083, "step": 297630 }, { "epoch": 1.7692339699579744, "grad_norm": 4.101352214813232, "learning_rate": 8.162240065604215e-06, "loss": 0.2975, "step": 297640 }, { "epoch": 1.7692934120346429, "grad_norm": 5.985834121704102, "learning_rate": 8.162079338896744e-06, "loss": 0.3536, "step": 297650 }, { "epoch": 1.7693528541113113, "grad_norm": 5.312063694000244, "learning_rate": 8.161918606743795e-06, "loss": 0.3292, "step": 297660 }, { "epoch": 1.7694122961879795, "grad_norm": 4.461727619171143, "learning_rate": 8.161757869145645e-06, "loss": 0.2767, "step": 297670 }, { "epoch": 1.7694717382646479, "grad_norm": 5.9684739112854, "learning_rate": 8.16159712610257e-06, "loss": 0.3195, "step": 297680 }, { "epoch": 1.7695311803413163, "grad_norm": 4.31369686126709, "learning_rate": 8.161436377614848e-06, "loss": 0.298, "step": 297690 }, { "epoch": 1.7695906224179847, "grad_norm": 5.211028099060059, "learning_rate": 8.161275623682755e-06, "loss": 0.3225, "step": 297700 }, { "epoch": 1.7696500644946531, "grad_norm": 5.304697036743164, "learning_rate": 8.16111486430657e-06, "loss": 0.2978, "step": 297710 }, { "epoch": 1.7697095065713215, "grad_norm": 4.185134410858154, "learning_rate": 8.160954099486567e-06, "loss": 0.3152, "step": 297720 }, { "epoch": 1.76976894864799, "grad_norm": 5.833794593811035, "learning_rate": 8.160793329223022e-06, "loss": 0.327, "step": 297730 }, { "epoch": 1.7698283907246584, "grad_norm": 3.798576831817627, "learning_rate": 8.160632553516218e-06, "loss": 0.341, "step": 297740 }, { "epoch": 1.7698878328013268, "grad_norm": 3.923497438430786, "learning_rate": 8.160471772366424e-06, "loss": 0.325, "step": 297750 }, { "epoch": 1.7699472748779952, "grad_norm": 4.908023357391357, "learning_rate": 8.160310985773921e-06, "loss": 0.3335, "step": 297760 }, { "epoch": 1.7700067169546636, "grad_norm": 4.3109354972839355, "learning_rate": 8.160150193738987e-06, "loss": 0.2828, "step": 297770 }, { "epoch": 1.770066159031332, "grad_norm": 5.037671089172363, "learning_rate": 8.159989396261896e-06, "loss": 0.3182, "step": 297780 }, { "epoch": 1.7701256011080004, "grad_norm": 5.365140914916992, "learning_rate": 8.159828593342926e-06, "loss": 0.3077, "step": 297790 }, { "epoch": 1.7701850431846688, "grad_norm": 5.45034646987915, "learning_rate": 8.159667784982355e-06, "loss": 0.3416, "step": 297800 }, { "epoch": 1.770244485261337, "grad_norm": 4.8146257400512695, "learning_rate": 8.159506971180457e-06, "loss": 0.3265, "step": 297810 }, { "epoch": 1.7703039273380055, "grad_norm": 5.216412544250488, "learning_rate": 8.159346151937513e-06, "loss": 0.323, "step": 297820 }, { "epoch": 1.7703633694146739, "grad_norm": 4.567836761474609, "learning_rate": 8.159185327253799e-06, "loss": 0.3447, "step": 297830 }, { "epoch": 1.7704228114913423, "grad_norm": 6.820001602172852, "learning_rate": 8.159024497129588e-06, "loss": 0.3152, "step": 297840 }, { "epoch": 1.7704822535680107, "grad_norm": 4.958375930786133, "learning_rate": 8.158863661565163e-06, "loss": 0.2967, "step": 297850 }, { "epoch": 1.770541695644679, "grad_norm": 4.626076698303223, "learning_rate": 8.158702820560795e-06, "loss": 0.2956, "step": 297860 }, { "epoch": 1.7706011377213473, "grad_norm": 5.76356840133667, "learning_rate": 8.158541974116765e-06, "loss": 0.3167, "step": 297870 }, { "epoch": 1.7706605797980157, "grad_norm": 5.097423076629639, "learning_rate": 8.15838112223335e-06, "loss": 0.3258, "step": 297880 }, { "epoch": 1.7707200218746841, "grad_norm": 4.93244743347168, "learning_rate": 8.158220264910824e-06, "loss": 0.3106, "step": 297890 }, { "epoch": 1.7707794639513526, "grad_norm": 5.641669273376465, "learning_rate": 8.158059402149468e-06, "loss": 0.2872, "step": 297900 }, { "epoch": 1.770838906028021, "grad_norm": 5.588712692260742, "learning_rate": 8.157898533949556e-06, "loss": 0.2989, "step": 297910 }, { "epoch": 1.7708983481046894, "grad_norm": 6.036904335021973, "learning_rate": 8.157737660311364e-06, "loss": 0.3061, "step": 297920 }, { "epoch": 1.7709577901813578, "grad_norm": 4.560481071472168, "learning_rate": 8.157576781235173e-06, "loss": 0.2966, "step": 297930 }, { "epoch": 1.7710172322580262, "grad_norm": 4.175429821014404, "learning_rate": 8.157415896721257e-06, "loss": 0.3327, "step": 297940 }, { "epoch": 1.7710766743346946, "grad_norm": 3.7518961429595947, "learning_rate": 8.157255006769895e-06, "loss": 0.2669, "step": 297950 }, { "epoch": 1.771136116411363, "grad_norm": 5.296675682067871, "learning_rate": 8.157094111381364e-06, "loss": 0.3194, "step": 297960 }, { "epoch": 1.7711955584880315, "grad_norm": 4.6541242599487305, "learning_rate": 8.156933210555938e-06, "loss": 0.306, "step": 297970 }, { "epoch": 1.7712550005646999, "grad_norm": 7.245932579040527, "learning_rate": 8.156772304293896e-06, "loss": 0.3358, "step": 297980 }, { "epoch": 1.7713144426413683, "grad_norm": 4.795560836791992, "learning_rate": 8.156611392595518e-06, "loss": 0.283, "step": 297990 }, { "epoch": 1.7713738847180365, "grad_norm": 4.506383419036865, "learning_rate": 8.156450475461078e-06, "loss": 0.3185, "step": 298000 }, { "epoch": 1.7714333267947049, "grad_norm": 4.326946258544922, "learning_rate": 8.156289552890853e-06, "loss": 0.302, "step": 298010 }, { "epoch": 1.7714927688713733, "grad_norm": 4.8757405281066895, "learning_rate": 8.15612862488512e-06, "loss": 0.3032, "step": 298020 }, { "epoch": 1.7715522109480417, "grad_norm": 5.183350563049316, "learning_rate": 8.155967691444158e-06, "loss": 0.3421, "step": 298030 }, { "epoch": 1.77161165302471, "grad_norm": 6.4447855949401855, "learning_rate": 8.155806752568242e-06, "loss": 0.3145, "step": 298040 }, { "epoch": 1.7716710951013783, "grad_norm": 5.1983466148376465, "learning_rate": 8.155645808257651e-06, "loss": 0.2887, "step": 298050 }, { "epoch": 1.7717305371780467, "grad_norm": 6.49363374710083, "learning_rate": 8.15548485851266e-06, "loss": 0.3118, "step": 298060 }, { "epoch": 1.7717899792547152, "grad_norm": 5.154625415802002, "learning_rate": 8.155323903333551e-06, "loss": 0.331, "step": 298070 }, { "epoch": 1.7718494213313836, "grad_norm": 4.224953651428223, "learning_rate": 8.155162942720596e-06, "loss": 0.2976, "step": 298080 }, { "epoch": 1.771908863408052, "grad_norm": 5.205280303955078, "learning_rate": 8.155001976674072e-06, "loss": 0.3306, "step": 298090 }, { "epoch": 1.7719683054847204, "grad_norm": 3.9838013648986816, "learning_rate": 8.154841005194261e-06, "loss": 0.3155, "step": 298100 }, { "epoch": 1.7720277475613888, "grad_norm": 6.596429347991943, "learning_rate": 8.154680028281436e-06, "loss": 0.2756, "step": 298110 }, { "epoch": 1.7720871896380572, "grad_norm": 5.565365314483643, "learning_rate": 8.154519045935876e-06, "loss": 0.2881, "step": 298120 }, { "epoch": 1.7721466317147256, "grad_norm": 5.1488447189331055, "learning_rate": 8.154358058157858e-06, "loss": 0.3046, "step": 298130 }, { "epoch": 1.772206073791394, "grad_norm": 4.945131778717041, "learning_rate": 8.154197064947658e-06, "loss": 0.3121, "step": 298140 }, { "epoch": 1.7722655158680625, "grad_norm": 4.955782413482666, "learning_rate": 8.154036066305555e-06, "loss": 0.3155, "step": 298150 }, { "epoch": 1.7723249579447309, "grad_norm": 5.923223972320557, "learning_rate": 8.153875062231824e-06, "loss": 0.3347, "step": 298160 }, { "epoch": 1.7723844000213993, "grad_norm": 4.6112260818481445, "learning_rate": 8.153714052726747e-06, "loss": 0.2876, "step": 298170 }, { "epoch": 1.7724438420980675, "grad_norm": 4.964049816131592, "learning_rate": 8.153553037790596e-06, "loss": 0.2941, "step": 298180 }, { "epoch": 1.772503284174736, "grad_norm": 3.3800137042999268, "learning_rate": 8.153392017423651e-06, "loss": 0.306, "step": 298190 }, { "epoch": 1.7725627262514043, "grad_norm": 7.6125922203063965, "learning_rate": 8.153230991626188e-06, "loss": 0.3219, "step": 298200 }, { "epoch": 1.7726221683280727, "grad_norm": 5.933839321136475, "learning_rate": 8.153069960398485e-06, "loss": 0.3038, "step": 298210 }, { "epoch": 1.7726816104047411, "grad_norm": 5.304394245147705, "learning_rate": 8.152908923740822e-06, "loss": 0.3214, "step": 298220 }, { "epoch": 1.7727410524814093, "grad_norm": 4.173455238342285, "learning_rate": 8.15274788165347e-06, "loss": 0.3483, "step": 298230 }, { "epoch": 1.7728004945580778, "grad_norm": 5.53528356552124, "learning_rate": 8.15258683413671e-06, "loss": 0.3042, "step": 298240 }, { "epoch": 1.7728599366347462, "grad_norm": 4.335525989532471, "learning_rate": 8.152425781190823e-06, "loss": 0.2878, "step": 298250 }, { "epoch": 1.7729193787114146, "grad_norm": 5.679286003112793, "learning_rate": 8.15226472281608e-06, "loss": 0.2893, "step": 298260 }, { "epoch": 1.772978820788083, "grad_norm": 5.503379821777344, "learning_rate": 8.15210365901276e-06, "loss": 0.3347, "step": 298270 }, { "epoch": 1.7730382628647514, "grad_norm": 4.458060264587402, "learning_rate": 8.151942589781144e-06, "loss": 0.3207, "step": 298280 }, { "epoch": 1.7730977049414198, "grad_norm": 6.679325580596924, "learning_rate": 8.151781515121505e-06, "loss": 0.3426, "step": 298290 }, { "epoch": 1.7731571470180882, "grad_norm": 4.425271987915039, "learning_rate": 8.151620435034122e-06, "loss": 0.291, "step": 298300 }, { "epoch": 1.7732165890947567, "grad_norm": 5.452114582061768, "learning_rate": 8.151459349519273e-06, "loss": 0.3196, "step": 298310 }, { "epoch": 1.773276031171425, "grad_norm": 5.1357221603393555, "learning_rate": 8.151298258577236e-06, "loss": 0.2727, "step": 298320 }, { "epoch": 1.7733354732480935, "grad_norm": 4.478309154510498, "learning_rate": 8.151137162208287e-06, "loss": 0.2874, "step": 298330 }, { "epoch": 1.773394915324762, "grad_norm": 6.673108100891113, "learning_rate": 8.150976060412704e-06, "loss": 0.3268, "step": 298340 }, { "epoch": 1.7734543574014303, "grad_norm": 6.346728324890137, "learning_rate": 8.150814953190763e-06, "loss": 0.3016, "step": 298350 }, { "epoch": 1.7735137994780987, "grad_norm": 5.714790344238281, "learning_rate": 8.150653840542743e-06, "loss": 0.3264, "step": 298360 }, { "epoch": 1.773573241554767, "grad_norm": 5.058535099029541, "learning_rate": 8.150492722468923e-06, "loss": 0.3128, "step": 298370 }, { "epoch": 1.7736326836314353, "grad_norm": 4.921173572540283, "learning_rate": 8.150331598969576e-06, "loss": 0.3218, "step": 298380 }, { "epoch": 1.7736921257081038, "grad_norm": 4.734162330627441, "learning_rate": 8.150170470044983e-06, "loss": 0.3459, "step": 298390 }, { "epoch": 1.7737515677847722, "grad_norm": 3.7968873977661133, "learning_rate": 8.150009335695421e-06, "loss": 0.3413, "step": 298400 }, { "epoch": 1.7738110098614404, "grad_norm": 5.2632856369018555, "learning_rate": 8.149848195921168e-06, "loss": 0.3362, "step": 298410 }, { "epoch": 1.7738704519381088, "grad_norm": 5.815878391265869, "learning_rate": 8.149687050722498e-06, "loss": 0.3213, "step": 298420 }, { "epoch": 1.7739298940147772, "grad_norm": 6.161065101623535, "learning_rate": 8.149525900099694e-06, "loss": 0.314, "step": 298430 }, { "epoch": 1.7739893360914456, "grad_norm": 5.642813205718994, "learning_rate": 8.14936474405303e-06, "loss": 0.3164, "step": 298440 }, { "epoch": 1.774048778168114, "grad_norm": 4.522560119628906, "learning_rate": 8.149203582582783e-06, "loss": 0.3189, "step": 298450 }, { "epoch": 1.7741082202447824, "grad_norm": 6.846390247344971, "learning_rate": 8.149042415689233e-06, "loss": 0.3143, "step": 298460 }, { "epoch": 1.7741676623214508, "grad_norm": 5.955678462982178, "learning_rate": 8.148881243372655e-06, "loss": 0.3251, "step": 298470 }, { "epoch": 1.7742271043981193, "grad_norm": 4.480559825897217, "learning_rate": 8.148720065633327e-06, "loss": 0.3514, "step": 298480 }, { "epoch": 1.7742865464747877, "grad_norm": 4.367259979248047, "learning_rate": 8.148558882471527e-06, "loss": 0.3203, "step": 298490 }, { "epoch": 1.774345988551456, "grad_norm": 5.348423957824707, "learning_rate": 8.148397693887535e-06, "loss": 0.3311, "step": 298500 }, { "epoch": 1.7744054306281245, "grad_norm": 7.137136936187744, "learning_rate": 8.148236499881626e-06, "loss": 0.3717, "step": 298510 }, { "epoch": 1.774464872704793, "grad_norm": 3.675365447998047, "learning_rate": 8.148075300454078e-06, "loss": 0.3241, "step": 298520 }, { "epoch": 1.7745243147814613, "grad_norm": 3.866152286529541, "learning_rate": 8.14791409560517e-06, "loss": 0.3041, "step": 298530 }, { "epoch": 1.7745837568581297, "grad_norm": 5.16977596282959, "learning_rate": 8.147752885335176e-06, "loss": 0.3559, "step": 298540 }, { "epoch": 1.774643198934798, "grad_norm": 4.038383960723877, "learning_rate": 8.147591669644377e-06, "loss": 0.2854, "step": 298550 }, { "epoch": 1.7747026410114664, "grad_norm": 3.7642533779144287, "learning_rate": 8.14743044853305e-06, "loss": 0.3421, "step": 298560 }, { "epoch": 1.7747620830881348, "grad_norm": 5.614407539367676, "learning_rate": 8.147269222001472e-06, "loss": 0.2865, "step": 298570 }, { "epoch": 1.7748215251648032, "grad_norm": 4.385634422302246, "learning_rate": 8.14710799004992e-06, "loss": 0.2898, "step": 298580 }, { "epoch": 1.7748809672414716, "grad_norm": 4.911033630371094, "learning_rate": 8.146946752678673e-06, "loss": 0.2928, "step": 298590 }, { "epoch": 1.7749404093181398, "grad_norm": 5.543754577636719, "learning_rate": 8.146785509888009e-06, "loss": 0.3076, "step": 298600 }, { "epoch": 1.7749998513948082, "grad_norm": 5.736454010009766, "learning_rate": 8.146624261678203e-06, "loss": 0.313, "step": 298610 }, { "epoch": 1.7750592934714766, "grad_norm": 7.316897392272949, "learning_rate": 8.146463008049537e-06, "loss": 0.3744, "step": 298620 }, { "epoch": 1.775118735548145, "grad_norm": 4.913711071014404, "learning_rate": 8.146301749002283e-06, "loss": 0.3318, "step": 298630 }, { "epoch": 1.7751781776248134, "grad_norm": 4.838226318359375, "learning_rate": 8.146140484536725e-06, "loss": 0.3352, "step": 298640 }, { "epoch": 1.7752376197014819, "grad_norm": 5.22496223449707, "learning_rate": 8.145979214653137e-06, "loss": 0.3083, "step": 298650 }, { "epoch": 1.7752970617781503, "grad_norm": 5.804651260375977, "learning_rate": 8.145817939351797e-06, "loss": 0.3018, "step": 298660 }, { "epoch": 1.7753565038548187, "grad_norm": 3.4794468879699707, "learning_rate": 8.145656658632983e-06, "loss": 0.3336, "step": 298670 }, { "epoch": 1.775415945931487, "grad_norm": 5.409396648406982, "learning_rate": 8.145495372496974e-06, "loss": 0.313, "step": 298680 }, { "epoch": 1.7754753880081555, "grad_norm": 4.964654445648193, "learning_rate": 8.145334080944045e-06, "loss": 0.3085, "step": 298690 }, { "epoch": 1.775534830084824, "grad_norm": 5.610008716583252, "learning_rate": 8.145172783974478e-06, "loss": 0.3299, "step": 298700 }, { "epoch": 1.7755942721614923, "grad_norm": 5.843349933624268, "learning_rate": 8.145011481588545e-06, "loss": 0.3371, "step": 298710 }, { "epoch": 1.7756537142381608, "grad_norm": 4.6824445724487305, "learning_rate": 8.144850173786528e-06, "loss": 0.3058, "step": 298720 }, { "epoch": 1.7757131563148292, "grad_norm": 5.372195720672607, "learning_rate": 8.144688860568706e-06, "loss": 0.3127, "step": 298730 }, { "epoch": 1.7757725983914974, "grad_norm": 4.403832912445068, "learning_rate": 8.144527541935351e-06, "loss": 0.328, "step": 298740 }, { "epoch": 1.7758320404681658, "grad_norm": 6.208166599273682, "learning_rate": 8.144366217886747e-06, "loss": 0.3184, "step": 298750 }, { "epoch": 1.7758914825448342, "grad_norm": 4.729137897491455, "learning_rate": 8.144204888423168e-06, "loss": 0.3281, "step": 298760 }, { "epoch": 1.7759509246215026, "grad_norm": 4.055437088012695, "learning_rate": 8.144043553544894e-06, "loss": 0.336, "step": 298770 }, { "epoch": 1.7760103666981708, "grad_norm": 5.074547290802002, "learning_rate": 8.1438822132522e-06, "loss": 0.2849, "step": 298780 }, { "epoch": 1.7760698087748392, "grad_norm": 4.339906215667725, "learning_rate": 8.143720867545369e-06, "loss": 0.3397, "step": 298790 }, { "epoch": 1.7761292508515076, "grad_norm": 5.214492321014404, "learning_rate": 8.143559516424672e-06, "loss": 0.3128, "step": 298800 }, { "epoch": 1.776188692928176, "grad_norm": 5.640066146850586, "learning_rate": 8.143398159890393e-06, "loss": 0.3429, "step": 298810 }, { "epoch": 1.7762481350048445, "grad_norm": 4.541362762451172, "learning_rate": 8.143236797942806e-06, "loss": 0.315, "step": 298820 }, { "epoch": 1.7763075770815129, "grad_norm": 5.638700485229492, "learning_rate": 8.143075430582189e-06, "loss": 0.309, "step": 298830 }, { "epoch": 1.7763670191581813, "grad_norm": 4.999192237854004, "learning_rate": 8.142914057808823e-06, "loss": 0.3189, "step": 298840 }, { "epoch": 1.7764264612348497, "grad_norm": 4.801389217376709, "learning_rate": 8.142752679622984e-06, "loss": 0.3407, "step": 298850 }, { "epoch": 1.7764859033115181, "grad_norm": 5.6667094230651855, "learning_rate": 8.142591296024948e-06, "loss": 0.2979, "step": 298860 }, { "epoch": 1.7765453453881865, "grad_norm": 3.7184808254241943, "learning_rate": 8.142429907014997e-06, "loss": 0.2742, "step": 298870 }, { "epoch": 1.776604787464855, "grad_norm": 4.877180576324463, "learning_rate": 8.142268512593405e-06, "loss": 0.3194, "step": 298880 }, { "epoch": 1.7766642295415234, "grad_norm": 6.951562404632568, "learning_rate": 8.142107112760453e-06, "loss": 0.3364, "step": 298890 }, { "epoch": 1.7767236716181918, "grad_norm": 5.521808624267578, "learning_rate": 8.141945707516418e-06, "loss": 0.3309, "step": 298900 }, { "epoch": 1.7767831136948602, "grad_norm": 4.807753086090088, "learning_rate": 8.141784296861577e-06, "loss": 0.31, "step": 298910 }, { "epoch": 1.7768425557715284, "grad_norm": 5.109141826629639, "learning_rate": 8.141622880796208e-06, "loss": 0.3376, "step": 298920 }, { "epoch": 1.7769019978481968, "grad_norm": 4.5593156814575195, "learning_rate": 8.14146145932059e-06, "loss": 0.2892, "step": 298930 }, { "epoch": 1.7769614399248652, "grad_norm": 7.092306613922119, "learning_rate": 8.141300032435e-06, "loss": 0.3082, "step": 298940 }, { "epoch": 1.7770208820015336, "grad_norm": 5.710925579071045, "learning_rate": 8.141138600139717e-06, "loss": 0.3196, "step": 298950 }, { "epoch": 1.777080324078202, "grad_norm": 4.8023834228515625, "learning_rate": 8.14097716243502e-06, "loss": 0.2959, "step": 298960 }, { "epoch": 1.7771397661548702, "grad_norm": 5.0898542404174805, "learning_rate": 8.140815719321183e-06, "loss": 0.3099, "step": 298970 }, { "epoch": 1.7771992082315387, "grad_norm": 8.59448528289795, "learning_rate": 8.140654270798489e-06, "loss": 0.2995, "step": 298980 }, { "epoch": 1.777258650308207, "grad_norm": 4.758021354675293, "learning_rate": 8.140492816867211e-06, "loss": 0.2697, "step": 298990 }, { "epoch": 1.7773180923848755, "grad_norm": 4.778744697570801, "learning_rate": 8.14033135752763e-06, "loss": 0.3075, "step": 299000 }, { "epoch": 1.777377534461544, "grad_norm": 4.822986125946045, "learning_rate": 8.140169892780027e-06, "loss": 0.3276, "step": 299010 }, { "epoch": 1.7774369765382123, "grad_norm": 5.130570888519287, "learning_rate": 8.140008422624675e-06, "loss": 0.3363, "step": 299020 }, { "epoch": 1.7774964186148807, "grad_norm": 3.7143964767456055, "learning_rate": 8.139846947061852e-06, "loss": 0.3163, "step": 299030 }, { "epoch": 1.7775558606915491, "grad_norm": 4.4585466384887695, "learning_rate": 8.139685466091838e-06, "loss": 0.3238, "step": 299040 }, { "epoch": 1.7776153027682176, "grad_norm": 3.601400136947632, "learning_rate": 8.139523979714912e-06, "loss": 0.2816, "step": 299050 }, { "epoch": 1.777674744844886, "grad_norm": 5.588459491729736, "learning_rate": 8.139362487931352e-06, "loss": 0.2948, "step": 299060 }, { "epoch": 1.7777341869215544, "grad_norm": 5.428068161010742, "learning_rate": 8.139200990741435e-06, "loss": 0.2982, "step": 299070 }, { "epoch": 1.7777936289982228, "grad_norm": 5.374649524688721, "learning_rate": 8.13903948814544e-06, "loss": 0.2698, "step": 299080 }, { "epoch": 1.7778530710748912, "grad_norm": 5.432085037231445, "learning_rate": 8.138877980143643e-06, "loss": 0.3073, "step": 299090 }, { "epoch": 1.7779125131515596, "grad_norm": 6.832336902618408, "learning_rate": 8.138716466736322e-06, "loss": 0.3461, "step": 299100 }, { "epoch": 1.7779719552282278, "grad_norm": 5.4010162353515625, "learning_rate": 8.138554947923761e-06, "loss": 0.2861, "step": 299110 }, { "epoch": 1.7780313973048962, "grad_norm": 3.6865148544311523, "learning_rate": 8.13839342370623e-06, "loss": 0.2674, "step": 299120 }, { "epoch": 1.7780908393815646, "grad_norm": 6.31342077255249, "learning_rate": 8.138231894084014e-06, "loss": 0.3148, "step": 299130 }, { "epoch": 1.778150281458233, "grad_norm": 5.033749103546143, "learning_rate": 8.138070359057385e-06, "loss": 0.2976, "step": 299140 }, { "epoch": 1.7782097235349013, "grad_norm": 4.600461483001709, "learning_rate": 8.137908818626626e-06, "loss": 0.2861, "step": 299150 }, { "epoch": 1.7782691656115697, "grad_norm": 4.536177635192871, "learning_rate": 8.137747272792014e-06, "loss": 0.311, "step": 299160 }, { "epoch": 1.778328607688238, "grad_norm": 4.9618024826049805, "learning_rate": 8.137585721553827e-06, "loss": 0.3042, "step": 299170 }, { "epoch": 1.7783880497649065, "grad_norm": 5.295802593231201, "learning_rate": 8.137424164912343e-06, "loss": 0.3064, "step": 299180 }, { "epoch": 1.778447491841575, "grad_norm": 5.529808044433594, "learning_rate": 8.13726260286784e-06, "loss": 0.3218, "step": 299190 }, { "epoch": 1.7785069339182433, "grad_norm": 4.423212051391602, "learning_rate": 8.137101035420595e-06, "loss": 0.2758, "step": 299200 }, { "epoch": 1.7785663759949117, "grad_norm": 6.384745121002197, "learning_rate": 8.13693946257089e-06, "loss": 0.3065, "step": 299210 }, { "epoch": 1.7786258180715802, "grad_norm": 5.868311405181885, "learning_rate": 8.136777884319e-06, "loss": 0.3083, "step": 299220 }, { "epoch": 1.7786852601482486, "grad_norm": 4.8431220054626465, "learning_rate": 8.136616300665205e-06, "loss": 0.3336, "step": 299230 }, { "epoch": 1.778744702224917, "grad_norm": 6.10533332824707, "learning_rate": 8.136454711609782e-06, "loss": 0.3396, "step": 299240 }, { "epoch": 1.7788041443015854, "grad_norm": 5.45536994934082, "learning_rate": 8.13629311715301e-06, "loss": 0.3059, "step": 299250 }, { "epoch": 1.7788635863782538, "grad_norm": 4.368504524230957, "learning_rate": 8.136131517295165e-06, "loss": 0.2899, "step": 299260 }, { "epoch": 1.7789230284549222, "grad_norm": 5.164560794830322, "learning_rate": 8.13596991203653e-06, "loss": 0.3073, "step": 299270 }, { "epoch": 1.7789824705315906, "grad_norm": 5.496671676635742, "learning_rate": 8.13580830137738e-06, "loss": 0.3236, "step": 299280 }, { "epoch": 1.7790419126082588, "grad_norm": 3.98893404006958, "learning_rate": 8.135646685317993e-06, "loss": 0.3145, "step": 299290 }, { "epoch": 1.7791013546849272, "grad_norm": 5.594040870666504, "learning_rate": 8.135485063858648e-06, "loss": 0.3485, "step": 299300 }, { "epoch": 1.7791607967615957, "grad_norm": 5.378696441650391, "learning_rate": 8.135323436999625e-06, "loss": 0.3012, "step": 299310 }, { "epoch": 1.779220238838264, "grad_norm": 4.806238174438477, "learning_rate": 8.1351618047412e-06, "loss": 0.3004, "step": 299320 }, { "epoch": 1.7792796809149325, "grad_norm": 4.25321102142334, "learning_rate": 8.135000167083652e-06, "loss": 0.2779, "step": 299330 }, { "epoch": 1.7793391229916007, "grad_norm": 5.552432060241699, "learning_rate": 8.13483852402726e-06, "loss": 0.3082, "step": 299340 }, { "epoch": 1.779398565068269, "grad_norm": 4.911332130432129, "learning_rate": 8.134676875572302e-06, "loss": 0.2949, "step": 299350 }, { "epoch": 1.7794580071449375, "grad_norm": 5.613367080688477, "learning_rate": 8.134515221719057e-06, "loss": 0.2908, "step": 299360 }, { "epoch": 1.779517449221606, "grad_norm": 5.329156398773193, "learning_rate": 8.134353562467803e-06, "loss": 0.2952, "step": 299370 }, { "epoch": 1.7795768912982743, "grad_norm": 5.844208240509033, "learning_rate": 8.134191897818816e-06, "loss": 0.3337, "step": 299380 }, { "epoch": 1.7796363333749428, "grad_norm": 6.0355224609375, "learning_rate": 8.134030227772378e-06, "loss": 0.3327, "step": 299390 }, { "epoch": 1.7796957754516112, "grad_norm": 4.119927406311035, "learning_rate": 8.133868552328768e-06, "loss": 0.2765, "step": 299400 }, { "epoch": 1.7797552175282796, "grad_norm": 8.232054710388184, "learning_rate": 8.13370687148826e-06, "loss": 0.309, "step": 299410 }, { "epoch": 1.779814659604948, "grad_norm": 4.776459217071533, "learning_rate": 8.133545185251134e-06, "loss": 0.2761, "step": 299420 }, { "epoch": 1.7798741016816164, "grad_norm": 6.192263603210449, "learning_rate": 8.133383493617672e-06, "loss": 0.3041, "step": 299430 }, { "epoch": 1.7799335437582848, "grad_norm": 4.272262096405029, "learning_rate": 8.133221796588149e-06, "loss": 0.3169, "step": 299440 }, { "epoch": 1.7799929858349532, "grad_norm": 4.6778059005737305, "learning_rate": 8.133060094162844e-06, "loss": 0.3046, "step": 299450 }, { "epoch": 1.7800524279116217, "grad_norm": 5.268547534942627, "learning_rate": 8.132898386342035e-06, "loss": 0.3493, "step": 299460 }, { "epoch": 1.78011186998829, "grad_norm": 6.9473652839660645, "learning_rate": 8.132736673126e-06, "loss": 0.3214, "step": 299470 }, { "epoch": 1.7801713120649583, "grad_norm": 3.656200408935547, "learning_rate": 8.132574954515021e-06, "loss": 0.3187, "step": 299480 }, { "epoch": 1.7802307541416267, "grad_norm": 4.458373546600342, "learning_rate": 8.132413230509374e-06, "loss": 0.2674, "step": 299490 }, { "epoch": 1.780290196218295, "grad_norm": 4.292407989501953, "learning_rate": 8.132251501109336e-06, "loss": 0.3439, "step": 299500 }, { "epoch": 1.7803496382949635, "grad_norm": 5.442572116851807, "learning_rate": 8.132089766315188e-06, "loss": 0.3199, "step": 299510 }, { "epoch": 1.7804090803716317, "grad_norm": 4.956966400146484, "learning_rate": 8.131928026127208e-06, "loss": 0.319, "step": 299520 }, { "epoch": 1.7804685224483001, "grad_norm": 4.002012252807617, "learning_rate": 8.131766280545675e-06, "loss": 0.302, "step": 299530 }, { "epoch": 1.7805279645249685, "grad_norm": 4.885222434997559, "learning_rate": 8.131604529570866e-06, "loss": 0.3107, "step": 299540 }, { "epoch": 1.780587406601637, "grad_norm": 5.607822418212891, "learning_rate": 8.13144277320306e-06, "loss": 0.3187, "step": 299550 }, { "epoch": 1.7806468486783054, "grad_norm": 5.455800533294678, "learning_rate": 8.131281011442535e-06, "loss": 0.2887, "step": 299560 }, { "epoch": 1.7807062907549738, "grad_norm": 5.136393070220947, "learning_rate": 8.131119244289573e-06, "loss": 0.3303, "step": 299570 }, { "epoch": 1.7807657328316422, "grad_norm": 6.076428413391113, "learning_rate": 8.130957471744449e-06, "loss": 0.327, "step": 299580 }, { "epoch": 1.7808251749083106, "grad_norm": 5.8852338790893555, "learning_rate": 8.130795693807441e-06, "loss": 0.3212, "step": 299590 }, { "epoch": 1.780884616984979, "grad_norm": 4.680976867675781, "learning_rate": 8.13063391047883e-06, "loss": 0.2892, "step": 299600 }, { "epoch": 1.7809440590616474, "grad_norm": 4.487039566040039, "learning_rate": 8.130472121758895e-06, "loss": 0.3248, "step": 299610 }, { "epoch": 1.7810035011383158, "grad_norm": 6.269720077514648, "learning_rate": 8.130310327647914e-06, "loss": 0.3092, "step": 299620 }, { "epoch": 1.7810629432149843, "grad_norm": 4.778919696807861, "learning_rate": 8.130148528146164e-06, "loss": 0.3205, "step": 299630 }, { "epoch": 1.7811223852916527, "grad_norm": 4.216154098510742, "learning_rate": 8.129986723253924e-06, "loss": 0.307, "step": 299640 }, { "epoch": 1.781181827368321, "grad_norm": 4.489951133728027, "learning_rate": 8.129824912971476e-06, "loss": 0.3296, "step": 299650 }, { "epoch": 1.7812412694449893, "grad_norm": 4.3525214195251465, "learning_rate": 8.129663097299095e-06, "loss": 0.3006, "step": 299660 }, { "epoch": 1.7813007115216577, "grad_norm": 4.515242099761963, "learning_rate": 8.129501276237058e-06, "loss": 0.3257, "step": 299670 }, { "epoch": 1.7813601535983261, "grad_norm": 5.479123592376709, "learning_rate": 8.129339449785649e-06, "loss": 0.3294, "step": 299680 }, { "epoch": 1.7814195956749945, "grad_norm": 5.592580795288086, "learning_rate": 8.129177617945144e-06, "loss": 0.3697, "step": 299690 }, { "epoch": 1.781479037751663, "grad_norm": 5.187558650970459, "learning_rate": 8.12901578071582e-06, "loss": 0.3567, "step": 299700 }, { "epoch": 1.7815384798283311, "grad_norm": 4.767723560333252, "learning_rate": 8.12885393809796e-06, "loss": 0.3081, "step": 299710 }, { "epoch": 1.7815979219049995, "grad_norm": 5.226648330688477, "learning_rate": 8.12869209009184e-06, "loss": 0.2917, "step": 299720 }, { "epoch": 1.781657363981668, "grad_norm": 5.399087905883789, "learning_rate": 8.128530236697735e-06, "loss": 0.2895, "step": 299730 }, { "epoch": 1.7817168060583364, "grad_norm": 4.228143692016602, "learning_rate": 8.128368377915932e-06, "loss": 0.3236, "step": 299740 }, { "epoch": 1.7817762481350048, "grad_norm": 4.63191556930542, "learning_rate": 8.128206513746703e-06, "loss": 0.3039, "step": 299750 }, { "epoch": 1.7818356902116732, "grad_norm": 4.211607933044434, "learning_rate": 8.128044644190331e-06, "loss": 0.3247, "step": 299760 }, { "epoch": 1.7818951322883416, "grad_norm": 5.944253444671631, "learning_rate": 8.127882769247092e-06, "loss": 0.3118, "step": 299770 }, { "epoch": 1.78195457436501, "grad_norm": 4.2292375564575195, "learning_rate": 8.127720888917266e-06, "loss": 0.3192, "step": 299780 }, { "epoch": 1.7820140164416785, "grad_norm": 4.158064365386963, "learning_rate": 8.127559003201132e-06, "loss": 0.2918, "step": 299790 }, { "epoch": 1.7820734585183469, "grad_norm": 4.656636714935303, "learning_rate": 8.127397112098964e-06, "loss": 0.3143, "step": 299800 }, { "epoch": 1.7821329005950153, "grad_norm": 6.2598161697387695, "learning_rate": 8.127235215611049e-06, "loss": 0.2765, "step": 299810 }, { "epoch": 1.7821923426716837, "grad_norm": 5.49088716506958, "learning_rate": 8.127073313737661e-06, "loss": 0.309, "step": 299820 }, { "epoch": 1.782251784748352, "grad_norm": 6.346894264221191, "learning_rate": 8.12691140647908e-06, "loss": 0.334, "step": 299830 }, { "epoch": 1.7823112268250205, "grad_norm": 5.486730575561523, "learning_rate": 8.126749493835584e-06, "loss": 0.2888, "step": 299840 }, { "epoch": 1.7823706689016887, "grad_norm": 4.177654266357422, "learning_rate": 8.126587575807452e-06, "loss": 0.3176, "step": 299850 }, { "epoch": 1.7824301109783571, "grad_norm": 4.504347801208496, "learning_rate": 8.126425652394965e-06, "loss": 0.3235, "step": 299860 }, { "epoch": 1.7824895530550255, "grad_norm": 5.2500433921813965, "learning_rate": 8.126263723598398e-06, "loss": 0.3173, "step": 299870 }, { "epoch": 1.782548995131694, "grad_norm": 4.888648986816406, "learning_rate": 8.126101789418033e-06, "loss": 0.316, "step": 299880 }, { "epoch": 1.7826084372083622, "grad_norm": 5.849506855010986, "learning_rate": 8.125939849854146e-06, "loss": 0.2989, "step": 299890 }, { "epoch": 1.7826678792850306, "grad_norm": 5.453055381774902, "learning_rate": 8.12577790490702e-06, "loss": 0.3516, "step": 299900 }, { "epoch": 1.782727321361699, "grad_norm": 3.932652235031128, "learning_rate": 8.12561595457693e-06, "loss": 0.328, "step": 299910 }, { "epoch": 1.7827867634383674, "grad_norm": 3.6384947299957275, "learning_rate": 8.125453998864155e-06, "loss": 0.323, "step": 299920 }, { "epoch": 1.7828462055150358, "grad_norm": 4.650498390197754, "learning_rate": 8.125292037768977e-06, "loss": 0.3333, "step": 299930 }, { "epoch": 1.7829056475917042, "grad_norm": 4.5893731117248535, "learning_rate": 8.125130071291673e-06, "loss": 0.2902, "step": 299940 }, { "epoch": 1.7829650896683726, "grad_norm": 4.970417499542236, "learning_rate": 8.124968099432524e-06, "loss": 0.3046, "step": 299950 }, { "epoch": 1.783024531745041, "grad_norm": 3.9142649173736572, "learning_rate": 8.124806122191804e-06, "loss": 0.2789, "step": 299960 }, { "epoch": 1.7830839738217095, "grad_norm": 5.880694389343262, "learning_rate": 8.124644139569797e-06, "loss": 0.2873, "step": 299970 }, { "epoch": 1.7831434158983779, "grad_norm": 6.411342620849609, "learning_rate": 8.124482151566779e-06, "loss": 0.3141, "step": 299980 }, { "epoch": 1.7832028579750463, "grad_norm": 4.179333686828613, "learning_rate": 8.12432015818303e-06, "loss": 0.3492, "step": 299990 }, { "epoch": 1.7832623000517147, "grad_norm": 6.4401397705078125, "learning_rate": 8.12415815941883e-06, "loss": 0.3224, "step": 300000 }, { "epoch": 1.7833217421283831, "grad_norm": 5.538577556610107, "learning_rate": 8.123996155274456e-06, "loss": 0.3053, "step": 300010 }, { "epoch": 1.7833811842050515, "grad_norm": 5.371372699737549, "learning_rate": 8.123834145750187e-06, "loss": 0.3075, "step": 300020 }, { "epoch": 1.7834406262817197, "grad_norm": 4.6685099601745605, "learning_rate": 8.123672130846304e-06, "loss": 0.2992, "step": 300030 }, { "epoch": 1.7835000683583881, "grad_norm": 4.144970417022705, "learning_rate": 8.123510110563084e-06, "loss": 0.303, "step": 300040 }, { "epoch": 1.7835595104350566, "grad_norm": 4.581658363342285, "learning_rate": 8.123348084900808e-06, "loss": 0.2938, "step": 300050 }, { "epoch": 1.783618952511725, "grad_norm": 4.432619571685791, "learning_rate": 8.123186053859753e-06, "loss": 0.309, "step": 300060 }, { "epoch": 1.7836783945883934, "grad_norm": 5.049531936645508, "learning_rate": 8.123024017440199e-06, "loss": 0.3087, "step": 300070 }, { "epoch": 1.7837378366650616, "grad_norm": 6.936831474304199, "learning_rate": 8.122861975642427e-06, "loss": 0.3076, "step": 300080 }, { "epoch": 1.78379727874173, "grad_norm": 6.5412678718566895, "learning_rate": 8.122699928466712e-06, "loss": 0.3263, "step": 300090 }, { "epoch": 1.7838567208183984, "grad_norm": 3.8907973766326904, "learning_rate": 8.122537875913337e-06, "loss": 0.2897, "step": 300100 }, { "epoch": 1.7839161628950668, "grad_norm": 4.30772590637207, "learning_rate": 8.122375817982577e-06, "loss": 0.2715, "step": 300110 }, { "epoch": 1.7839756049717352, "grad_norm": 5.927131175994873, "learning_rate": 8.122213754674713e-06, "loss": 0.334, "step": 300120 }, { "epoch": 1.7840350470484037, "grad_norm": 4.994418144226074, "learning_rate": 8.122051685990026e-06, "loss": 0.3199, "step": 300130 }, { "epoch": 1.784094489125072, "grad_norm": 4.919848442077637, "learning_rate": 8.121889611928793e-06, "loss": 0.3215, "step": 300140 }, { "epoch": 1.7841539312017405, "grad_norm": 5.698148250579834, "learning_rate": 8.121727532491294e-06, "loss": 0.3334, "step": 300150 }, { "epoch": 1.784213373278409, "grad_norm": 3.79824161529541, "learning_rate": 8.121565447677807e-06, "loss": 0.2978, "step": 300160 }, { "epoch": 1.7842728153550773, "grad_norm": 3.955139398574829, "learning_rate": 8.12140335748861e-06, "loss": 0.2933, "step": 300170 }, { "epoch": 1.7843322574317457, "grad_norm": 4.75875997543335, "learning_rate": 8.121241261923988e-06, "loss": 0.2893, "step": 300180 }, { "epoch": 1.7843916995084141, "grad_norm": 5.33665132522583, "learning_rate": 8.121079160984214e-06, "loss": 0.3611, "step": 300190 }, { "epoch": 1.7844511415850826, "grad_norm": 5.8940205574035645, "learning_rate": 8.12091705466957e-06, "loss": 0.3211, "step": 300200 }, { "epoch": 1.784510583661751, "grad_norm": 5.235439300537109, "learning_rate": 8.120754942980333e-06, "loss": 0.2905, "step": 300210 }, { "epoch": 1.7845700257384192, "grad_norm": 5.066524028778076, "learning_rate": 8.120592825916785e-06, "loss": 0.3153, "step": 300220 }, { "epoch": 1.7846294678150876, "grad_norm": 5.048779487609863, "learning_rate": 8.120430703479202e-06, "loss": 0.2917, "step": 300230 }, { "epoch": 1.784688909891756, "grad_norm": 4.917144775390625, "learning_rate": 8.120268575667869e-06, "loss": 0.2977, "step": 300240 }, { "epoch": 1.7847483519684244, "grad_norm": 5.042723655700684, "learning_rate": 8.120106442483058e-06, "loss": 0.3121, "step": 300250 }, { "epoch": 1.7848077940450926, "grad_norm": 4.944562911987305, "learning_rate": 8.119944303925051e-06, "loss": 0.3005, "step": 300260 }, { "epoch": 1.784867236121761, "grad_norm": 5.490065097808838, "learning_rate": 8.11978215999413e-06, "loss": 0.3023, "step": 300270 }, { "epoch": 1.7849266781984294, "grad_norm": 4.810037136077881, "learning_rate": 8.11962001069057e-06, "loss": 0.3361, "step": 300280 }, { "epoch": 1.7849861202750978, "grad_norm": 5.244986534118652, "learning_rate": 8.119457856014652e-06, "loss": 0.3113, "step": 300290 }, { "epoch": 1.7850455623517663, "grad_norm": 5.9024128913879395, "learning_rate": 8.119295695966656e-06, "loss": 0.3072, "step": 300300 }, { "epoch": 1.7851050044284347, "grad_norm": 5.08173942565918, "learning_rate": 8.11913353054686e-06, "loss": 0.3175, "step": 300310 }, { "epoch": 1.785164446505103, "grad_norm": 4.1779913902282715, "learning_rate": 8.118971359755545e-06, "loss": 0.2959, "step": 300320 }, { "epoch": 1.7852238885817715, "grad_norm": 5.23226261138916, "learning_rate": 8.11880918359299e-06, "loss": 0.3214, "step": 300330 }, { "epoch": 1.78528333065844, "grad_norm": 4.688657283782959, "learning_rate": 8.118647002059472e-06, "loss": 0.2837, "step": 300340 }, { "epoch": 1.7853427727351083, "grad_norm": 4.693160057067871, "learning_rate": 8.118484815155272e-06, "loss": 0.3258, "step": 300350 }, { "epoch": 1.7854022148117767, "grad_norm": 5.821720600128174, "learning_rate": 8.118322622880669e-06, "loss": 0.3159, "step": 300360 }, { "epoch": 1.7854616568884452, "grad_norm": 3.200817346572876, "learning_rate": 8.11816042523594e-06, "loss": 0.2903, "step": 300370 }, { "epoch": 1.7855210989651136, "grad_norm": 4.787072658538818, "learning_rate": 8.117998222221371e-06, "loss": 0.3232, "step": 300380 }, { "epoch": 1.785580541041782, "grad_norm": 4.860125541687012, "learning_rate": 8.117836013837234e-06, "loss": 0.3265, "step": 300390 }, { "epoch": 1.7856399831184502, "grad_norm": 5.200329780578613, "learning_rate": 8.117673800083813e-06, "loss": 0.2889, "step": 300400 }, { "epoch": 1.7856994251951186, "grad_norm": 5.708707809448242, "learning_rate": 8.117511580961384e-06, "loss": 0.3271, "step": 300410 }, { "epoch": 1.785758867271787, "grad_norm": 4.353207588195801, "learning_rate": 8.11734935647023e-06, "loss": 0.3394, "step": 300420 }, { "epoch": 1.7858183093484554, "grad_norm": 4.477595329284668, "learning_rate": 8.117187126610628e-06, "loss": 0.2861, "step": 300430 }, { "epoch": 1.7858777514251238, "grad_norm": 4.758847236633301, "learning_rate": 8.117024891382858e-06, "loss": 0.2805, "step": 300440 }, { "epoch": 1.785937193501792, "grad_norm": 4.210032939910889, "learning_rate": 8.116862650787199e-06, "loss": 0.2882, "step": 300450 }, { "epoch": 1.7859966355784604, "grad_norm": 5.992927074432373, "learning_rate": 8.11670040482393e-06, "loss": 0.3596, "step": 300460 }, { "epoch": 1.7860560776551289, "grad_norm": 5.114233016967773, "learning_rate": 8.11653815349333e-06, "loss": 0.2815, "step": 300470 }, { "epoch": 1.7861155197317973, "grad_norm": 5.0809149742126465, "learning_rate": 8.116375896795681e-06, "loss": 0.2988, "step": 300480 }, { "epoch": 1.7861749618084657, "grad_norm": 5.344917297363281, "learning_rate": 8.116213634731262e-06, "loss": 0.3067, "step": 300490 }, { "epoch": 1.786234403885134, "grad_norm": 4.398754119873047, "learning_rate": 8.11605136730035e-06, "loss": 0.3224, "step": 300500 }, { "epoch": 1.7862938459618025, "grad_norm": 4.6322808265686035, "learning_rate": 8.115889094503225e-06, "loss": 0.2876, "step": 300510 }, { "epoch": 1.786353288038471, "grad_norm": 4.9778733253479, "learning_rate": 8.115726816340168e-06, "loss": 0.2836, "step": 300520 }, { "epoch": 1.7864127301151393, "grad_norm": 4.666708469390869, "learning_rate": 8.115564532811458e-06, "loss": 0.2845, "step": 300530 }, { "epoch": 1.7864721721918078, "grad_norm": 4.497325897216797, "learning_rate": 8.115402243917373e-06, "loss": 0.3251, "step": 300540 }, { "epoch": 1.7865316142684762, "grad_norm": 4.528227806091309, "learning_rate": 8.115239949658195e-06, "loss": 0.3037, "step": 300550 }, { "epoch": 1.7865910563451446, "grad_norm": 3.9453206062316895, "learning_rate": 8.1150776500342e-06, "loss": 0.296, "step": 300560 }, { "epoch": 1.786650498421813, "grad_norm": 5.4616899490356445, "learning_rate": 8.114915345045671e-06, "loss": 0.3026, "step": 300570 }, { "epoch": 1.7867099404984814, "grad_norm": 4.46489953994751, "learning_rate": 8.114753034692886e-06, "loss": 0.3004, "step": 300580 }, { "epoch": 1.7867693825751496, "grad_norm": 3.8555054664611816, "learning_rate": 8.114590718976126e-06, "loss": 0.3165, "step": 300590 }, { "epoch": 1.786828824651818, "grad_norm": 3.5625667572021484, "learning_rate": 8.114428397895668e-06, "loss": 0.3208, "step": 300600 }, { "epoch": 1.7868882667284864, "grad_norm": 6.0038981437683105, "learning_rate": 8.114266071451793e-06, "loss": 0.3402, "step": 300610 }, { "epoch": 1.7869477088051549, "grad_norm": 4.335305690765381, "learning_rate": 8.11410373964478e-06, "loss": 0.2981, "step": 300620 }, { "epoch": 1.787007150881823, "grad_norm": 4.296952247619629, "learning_rate": 8.113941402474907e-06, "loss": 0.3143, "step": 300630 }, { "epoch": 1.7870665929584915, "grad_norm": 4.520773887634277, "learning_rate": 8.113779059942458e-06, "loss": 0.3515, "step": 300640 }, { "epoch": 1.7871260350351599, "grad_norm": 4.789004802703857, "learning_rate": 8.11361671204771e-06, "loss": 0.3137, "step": 300650 }, { "epoch": 1.7871854771118283, "grad_norm": 5.8789825439453125, "learning_rate": 8.11345435879094e-06, "loss": 0.3131, "step": 300660 }, { "epoch": 1.7872449191884967, "grad_norm": 5.029082298278809, "learning_rate": 8.113292000172433e-06, "loss": 0.3065, "step": 300670 }, { "epoch": 1.7873043612651651, "grad_norm": 4.780681133270264, "learning_rate": 8.113129636192463e-06, "loss": 0.305, "step": 300680 }, { "epoch": 1.7873638033418335, "grad_norm": 5.010086536407471, "learning_rate": 8.112967266851313e-06, "loss": 0.3249, "step": 300690 }, { "epoch": 1.787423245418502, "grad_norm": 5.808867454528809, "learning_rate": 8.112804892149263e-06, "loss": 0.3317, "step": 300700 }, { "epoch": 1.7874826874951704, "grad_norm": 5.158170700073242, "learning_rate": 8.11264251208659e-06, "loss": 0.3007, "step": 300710 }, { "epoch": 1.7875421295718388, "grad_norm": 4.085102081298828, "learning_rate": 8.112480126663577e-06, "loss": 0.298, "step": 300720 }, { "epoch": 1.7876015716485072, "grad_norm": 5.027185916900635, "learning_rate": 8.112317735880502e-06, "loss": 0.335, "step": 300730 }, { "epoch": 1.7876610137251756, "grad_norm": 6.006155490875244, "learning_rate": 8.112155339737643e-06, "loss": 0.339, "step": 300740 }, { "epoch": 1.787720455801844, "grad_norm": 4.58743143081665, "learning_rate": 8.111992938235283e-06, "loss": 0.3245, "step": 300750 }, { "epoch": 1.7877798978785124, "grad_norm": 5.553315162658691, "learning_rate": 8.111830531373696e-06, "loss": 0.3322, "step": 300760 }, { "epoch": 1.7878393399551806, "grad_norm": 6.189889907836914, "learning_rate": 8.111668119153168e-06, "loss": 0.3091, "step": 300770 }, { "epoch": 1.787898782031849, "grad_norm": 5.184332370758057, "learning_rate": 8.111505701573979e-06, "loss": 0.3218, "step": 300780 }, { "epoch": 1.7879582241085175, "grad_norm": 5.374468803405762, "learning_rate": 8.111343278636402e-06, "loss": 0.289, "step": 300790 }, { "epoch": 1.7880176661851859, "grad_norm": 5.594184398651123, "learning_rate": 8.111180850340723e-06, "loss": 0.3541, "step": 300800 }, { "epoch": 1.7880771082618543, "grad_norm": 4.303031921386719, "learning_rate": 8.111018416687218e-06, "loss": 0.3005, "step": 300810 }, { "epoch": 1.7881365503385225, "grad_norm": 4.858274936676025, "learning_rate": 8.110855977676166e-06, "loss": 0.321, "step": 300820 }, { "epoch": 1.788195992415191, "grad_norm": 4.829312801361084, "learning_rate": 8.110693533307854e-06, "loss": 0.2823, "step": 300830 }, { "epoch": 1.7882554344918593, "grad_norm": 5.13222074508667, "learning_rate": 8.110531083582553e-06, "loss": 0.3321, "step": 300840 }, { "epoch": 1.7883148765685277, "grad_norm": 3.9777092933654785, "learning_rate": 8.110368628500546e-06, "loss": 0.3014, "step": 300850 }, { "epoch": 1.7883743186451961, "grad_norm": 5.82296085357666, "learning_rate": 8.110206168062115e-06, "loss": 0.3092, "step": 300860 }, { "epoch": 1.7884337607218646, "grad_norm": 4.732313632965088, "learning_rate": 8.110043702267537e-06, "loss": 0.2874, "step": 300870 }, { "epoch": 1.788493202798533, "grad_norm": 5.085825443267822, "learning_rate": 8.109881231117093e-06, "loss": 0.2824, "step": 300880 }, { "epoch": 1.7885526448752014, "grad_norm": 4.713848114013672, "learning_rate": 8.109718754611062e-06, "loss": 0.3013, "step": 300890 }, { "epoch": 1.7886120869518698, "grad_norm": 3.8147106170654297, "learning_rate": 8.109556272749724e-06, "loss": 0.2913, "step": 300900 }, { "epoch": 1.7886715290285382, "grad_norm": 5.463617324829102, "learning_rate": 8.10939378553336e-06, "loss": 0.3218, "step": 300910 }, { "epoch": 1.7887309711052066, "grad_norm": 6.03923225402832, "learning_rate": 8.109231292962247e-06, "loss": 0.3083, "step": 300920 }, { "epoch": 1.788790413181875, "grad_norm": 4.841972827911377, "learning_rate": 8.10906879503667e-06, "loss": 0.3182, "step": 300930 }, { "epoch": 1.7888498552585435, "grad_norm": 3.979299545288086, "learning_rate": 8.108906291756903e-06, "loss": 0.2881, "step": 300940 }, { "epoch": 1.7889092973352119, "grad_norm": 6.537721157073975, "learning_rate": 8.108743783123229e-06, "loss": 0.3068, "step": 300950 }, { "epoch": 1.78896873941188, "grad_norm": 4.858337879180908, "learning_rate": 8.108581269135927e-06, "loss": 0.2853, "step": 300960 }, { "epoch": 1.7890281814885485, "grad_norm": 4.517093181610107, "learning_rate": 8.108418749795277e-06, "loss": 0.3276, "step": 300970 }, { "epoch": 1.789087623565217, "grad_norm": 6.771533012390137, "learning_rate": 8.10825622510156e-06, "loss": 0.3325, "step": 300980 }, { "epoch": 1.7891470656418853, "grad_norm": 4.312048435211182, "learning_rate": 8.108093695055055e-06, "loss": 0.2908, "step": 300990 }, { "epoch": 1.7892065077185535, "grad_norm": 5.768284320831299, "learning_rate": 8.107931159656041e-06, "loss": 0.3066, "step": 301000 }, { "epoch": 1.789265949795222, "grad_norm": 4.776689529418945, "learning_rate": 8.107768618904799e-06, "loss": 0.2847, "step": 301010 }, { "epoch": 1.7893253918718903, "grad_norm": 3.5737860202789307, "learning_rate": 8.107606072801608e-06, "loss": 0.2865, "step": 301020 }, { "epoch": 1.7893848339485587, "grad_norm": 5.078262805938721, "learning_rate": 8.10744352134675e-06, "loss": 0.3019, "step": 301030 }, { "epoch": 1.7894442760252272, "grad_norm": 4.958188056945801, "learning_rate": 8.107280964540503e-06, "loss": 0.3198, "step": 301040 }, { "epoch": 1.7895037181018956, "grad_norm": 4.92852783203125, "learning_rate": 8.107118402383146e-06, "loss": 0.2816, "step": 301050 }, { "epoch": 1.789563160178564, "grad_norm": 5.847097396850586, "learning_rate": 8.10695583487496e-06, "loss": 0.3062, "step": 301060 }, { "epoch": 1.7896226022552324, "grad_norm": 4.848042964935303, "learning_rate": 8.106793262016228e-06, "loss": 0.3164, "step": 301070 }, { "epoch": 1.7896820443319008, "grad_norm": 5.243551731109619, "learning_rate": 8.106630683807227e-06, "loss": 0.3011, "step": 301080 }, { "epoch": 1.7897414864085692, "grad_norm": 5.817543983459473, "learning_rate": 8.106468100248237e-06, "loss": 0.3183, "step": 301090 }, { "epoch": 1.7898009284852376, "grad_norm": 4.982772350311279, "learning_rate": 8.106305511339536e-06, "loss": 0.3088, "step": 301100 }, { "epoch": 1.789860370561906, "grad_norm": 4.557474136352539, "learning_rate": 8.106142917081408e-06, "loss": 0.2977, "step": 301110 }, { "epoch": 1.7899198126385745, "grad_norm": 4.555978298187256, "learning_rate": 8.105980317474132e-06, "loss": 0.2914, "step": 301120 }, { "epoch": 1.7899792547152429, "grad_norm": 4.760471820831299, "learning_rate": 8.105817712517985e-06, "loss": 0.3499, "step": 301130 }, { "epoch": 1.790038696791911, "grad_norm": 5.949477672576904, "learning_rate": 8.105655102213253e-06, "loss": 0.2978, "step": 301140 }, { "epoch": 1.7900981388685795, "grad_norm": 5.646341323852539, "learning_rate": 8.10549248656021e-06, "loss": 0.3052, "step": 301150 }, { "epoch": 1.790157580945248, "grad_norm": 5.2891011238098145, "learning_rate": 8.105329865559138e-06, "loss": 0.3079, "step": 301160 }, { "epoch": 1.7902170230219163, "grad_norm": 5.484639644622803, "learning_rate": 8.105167239210317e-06, "loss": 0.286, "step": 301170 }, { "epoch": 1.7902764650985847, "grad_norm": 5.100240707397461, "learning_rate": 8.10500460751403e-06, "loss": 0.3121, "step": 301180 }, { "epoch": 1.790335907175253, "grad_norm": 4.420060157775879, "learning_rate": 8.104841970470552e-06, "loss": 0.269, "step": 301190 }, { "epoch": 1.7903953492519213, "grad_norm": 5.250702381134033, "learning_rate": 8.104679328080167e-06, "loss": 0.3159, "step": 301200 }, { "epoch": 1.7904547913285898, "grad_norm": 5.2614827156066895, "learning_rate": 8.104516680343154e-06, "loss": 0.2937, "step": 301210 }, { "epoch": 1.7905142334052582, "grad_norm": 4.151396751403809, "learning_rate": 8.104354027259793e-06, "loss": 0.3283, "step": 301220 }, { "epoch": 1.7905736754819266, "grad_norm": 5.295761585235596, "learning_rate": 8.104191368830363e-06, "loss": 0.3003, "step": 301230 }, { "epoch": 1.790633117558595, "grad_norm": 5.453941822052002, "learning_rate": 8.104028705055145e-06, "loss": 0.2907, "step": 301240 }, { "epoch": 1.7906925596352634, "grad_norm": 4.254949569702148, "learning_rate": 8.10386603593442e-06, "loss": 0.3198, "step": 301250 }, { "epoch": 1.7907520017119318, "grad_norm": 3.6334733963012695, "learning_rate": 8.103703361468466e-06, "loss": 0.3002, "step": 301260 }, { "epoch": 1.7908114437886002, "grad_norm": 4.924427509307861, "learning_rate": 8.103540681657566e-06, "loss": 0.3158, "step": 301270 }, { "epoch": 1.7908708858652687, "grad_norm": 4.746151924133301, "learning_rate": 8.103377996501997e-06, "loss": 0.2939, "step": 301280 }, { "epoch": 1.790930327941937, "grad_norm": 4.8071675300598145, "learning_rate": 8.103215306002043e-06, "loss": 0.258, "step": 301290 }, { "epoch": 1.7909897700186055, "grad_norm": 4.244723796844482, "learning_rate": 8.10305261015798e-06, "loss": 0.3146, "step": 301300 }, { "epoch": 1.791049212095274, "grad_norm": 5.14467191696167, "learning_rate": 8.10288990897009e-06, "loss": 0.2993, "step": 301310 }, { "epoch": 1.7911086541719423, "grad_norm": 6.3145036697387695, "learning_rate": 8.102727202438657e-06, "loss": 0.3099, "step": 301320 }, { "epoch": 1.7911680962486105, "grad_norm": 4.04495906829834, "learning_rate": 8.102564490563954e-06, "loss": 0.276, "step": 301330 }, { "epoch": 1.791227538325279, "grad_norm": 5.579132556915283, "learning_rate": 8.102401773346266e-06, "loss": 0.3092, "step": 301340 }, { "epoch": 1.7912869804019473, "grad_norm": 6.169338703155518, "learning_rate": 8.102239050785871e-06, "loss": 0.3074, "step": 301350 }, { "epoch": 1.7913464224786158, "grad_norm": 5.9256486892700195, "learning_rate": 8.10207632288305e-06, "loss": 0.3023, "step": 301360 }, { "epoch": 1.791405864555284, "grad_norm": 4.339125156402588, "learning_rate": 8.101913589638085e-06, "loss": 0.309, "step": 301370 }, { "epoch": 1.7914653066319524, "grad_norm": 6.488102912902832, "learning_rate": 8.101750851051254e-06, "loss": 0.3131, "step": 301380 }, { "epoch": 1.7915247487086208, "grad_norm": 4.997694969177246, "learning_rate": 8.101588107122838e-06, "loss": 0.2775, "step": 301390 }, { "epoch": 1.7915841907852892, "grad_norm": 4.621452331542969, "learning_rate": 8.101425357853116e-06, "loss": 0.32, "step": 301400 }, { "epoch": 1.7916436328619576, "grad_norm": 3.2681970596313477, "learning_rate": 8.101262603242372e-06, "loss": 0.3275, "step": 301410 }, { "epoch": 1.791703074938626, "grad_norm": 6.226658821105957, "learning_rate": 8.101099843290881e-06, "loss": 0.3203, "step": 301420 }, { "epoch": 1.7917625170152944, "grad_norm": 4.759803295135498, "learning_rate": 8.100937077998927e-06, "loss": 0.3068, "step": 301430 }, { "epoch": 1.7918219590919628, "grad_norm": 3.5703392028808594, "learning_rate": 8.10077430736679e-06, "loss": 0.3071, "step": 301440 }, { "epoch": 1.7918814011686313, "grad_norm": 4.95438814163208, "learning_rate": 8.10061153139475e-06, "loss": 0.3031, "step": 301450 }, { "epoch": 1.7919408432452997, "grad_norm": 5.056896686553955, "learning_rate": 8.100448750083085e-06, "loss": 0.2795, "step": 301460 }, { "epoch": 1.792000285321968, "grad_norm": 3.4600918292999268, "learning_rate": 8.10028596343208e-06, "loss": 0.341, "step": 301470 }, { "epoch": 1.7920597273986365, "grad_norm": 4.240484237670898, "learning_rate": 8.100123171442011e-06, "loss": 0.3, "step": 301480 }, { "epoch": 1.792119169475305, "grad_norm": 4.667699813842773, "learning_rate": 8.099960374113161e-06, "loss": 0.328, "step": 301490 }, { "epoch": 1.7921786115519733, "grad_norm": 5.194838523864746, "learning_rate": 8.09979757144581e-06, "loss": 0.2988, "step": 301500 }, { "epoch": 1.7922380536286415, "grad_norm": 5.39291524887085, "learning_rate": 8.099634763440236e-06, "loss": 0.3415, "step": 301510 }, { "epoch": 1.79229749570531, "grad_norm": 4.899790287017822, "learning_rate": 8.09947195009672e-06, "loss": 0.3374, "step": 301520 }, { "epoch": 1.7923569377819784, "grad_norm": 5.866812705993652, "learning_rate": 8.099309131415544e-06, "loss": 0.338, "step": 301530 }, { "epoch": 1.7924163798586468, "grad_norm": 5.124715805053711, "learning_rate": 8.09914630739699e-06, "loss": 0.308, "step": 301540 }, { "epoch": 1.7924758219353152, "grad_norm": 5.84462833404541, "learning_rate": 8.098983478041336e-06, "loss": 0.3323, "step": 301550 }, { "epoch": 1.7925352640119834, "grad_norm": 4.792107582092285, "learning_rate": 8.098820643348861e-06, "loss": 0.2784, "step": 301560 }, { "epoch": 1.7925947060886518, "grad_norm": 4.838237762451172, "learning_rate": 8.098657803319847e-06, "loss": 0.3277, "step": 301570 }, { "epoch": 1.7926541481653202, "grad_norm": 4.285577297210693, "learning_rate": 8.098494957954577e-06, "loss": 0.2868, "step": 301580 }, { "epoch": 1.7927135902419886, "grad_norm": 4.95764684677124, "learning_rate": 8.098332107253325e-06, "loss": 0.3027, "step": 301590 }, { "epoch": 1.792773032318657, "grad_norm": 4.694685935974121, "learning_rate": 8.098169251216379e-06, "loss": 0.2801, "step": 301600 }, { "epoch": 1.7928324743953254, "grad_norm": 5.247898101806641, "learning_rate": 8.098006389844015e-06, "loss": 0.2786, "step": 301610 }, { "epoch": 1.7928919164719939, "grad_norm": 5.544286251068115, "learning_rate": 8.097843523136515e-06, "loss": 0.3274, "step": 301620 }, { "epoch": 1.7929513585486623, "grad_norm": 6.136346817016602, "learning_rate": 8.097680651094158e-06, "loss": 0.3032, "step": 301630 }, { "epoch": 1.7930108006253307, "grad_norm": 5.120561122894287, "learning_rate": 8.097517773717224e-06, "loss": 0.2926, "step": 301640 }, { "epoch": 1.793070242701999, "grad_norm": 4.933882713317871, "learning_rate": 8.097354891005998e-06, "loss": 0.2879, "step": 301650 }, { "epoch": 1.7931296847786675, "grad_norm": 3.703953742980957, "learning_rate": 8.097192002960754e-06, "loss": 0.2957, "step": 301660 }, { "epoch": 1.793189126855336, "grad_norm": 5.300260543823242, "learning_rate": 8.097029109581777e-06, "loss": 0.3036, "step": 301670 }, { "epoch": 1.7932485689320043, "grad_norm": 5.207112789154053, "learning_rate": 8.096866210869346e-06, "loss": 0.3109, "step": 301680 }, { "epoch": 1.7933080110086728, "grad_norm": 5.529033184051514, "learning_rate": 8.096703306823743e-06, "loss": 0.2843, "step": 301690 }, { "epoch": 1.793367453085341, "grad_norm": 4.832819938659668, "learning_rate": 8.096540397445247e-06, "loss": 0.307, "step": 301700 }, { "epoch": 1.7934268951620094, "grad_norm": 7.14982271194458, "learning_rate": 8.096377482734139e-06, "loss": 0.313, "step": 301710 }, { "epoch": 1.7934863372386778, "grad_norm": 5.177783489227295, "learning_rate": 8.0962145626907e-06, "loss": 0.3301, "step": 301720 }, { "epoch": 1.7935457793153462, "grad_norm": 5.855278491973877, "learning_rate": 8.096051637315207e-06, "loss": 0.2956, "step": 301730 }, { "epoch": 1.7936052213920144, "grad_norm": 5.539609432220459, "learning_rate": 8.095888706607948e-06, "loss": 0.2948, "step": 301740 }, { "epoch": 1.7936646634686828, "grad_norm": 4.390592575073242, "learning_rate": 8.095725770569195e-06, "loss": 0.3075, "step": 301750 }, { "epoch": 1.7937241055453512, "grad_norm": 5.211451530456543, "learning_rate": 8.095562829199238e-06, "loss": 0.3245, "step": 301760 }, { "epoch": 1.7937835476220196, "grad_norm": 5.665103435516357, "learning_rate": 8.09539988249835e-06, "loss": 0.2978, "step": 301770 }, { "epoch": 1.793842989698688, "grad_norm": 5.603348731994629, "learning_rate": 8.095236930466812e-06, "loss": 0.3384, "step": 301780 }, { "epoch": 1.7939024317753565, "grad_norm": 4.998562812805176, "learning_rate": 8.095073973104909e-06, "loss": 0.3546, "step": 301790 }, { "epoch": 1.7939618738520249, "grad_norm": 4.578876495361328, "learning_rate": 8.094911010412918e-06, "loss": 0.3059, "step": 301800 }, { "epoch": 1.7940213159286933, "grad_norm": 4.380058765411377, "learning_rate": 8.094748042391121e-06, "loss": 0.2885, "step": 301810 }, { "epoch": 1.7940807580053617, "grad_norm": 4.318164348602295, "learning_rate": 8.0945850690398e-06, "loss": 0.3216, "step": 301820 }, { "epoch": 1.7941402000820301, "grad_norm": 4.202655792236328, "learning_rate": 8.094422090359234e-06, "loss": 0.286, "step": 301830 }, { "epoch": 1.7941996421586985, "grad_norm": 4.74794340133667, "learning_rate": 8.094259106349702e-06, "loss": 0.291, "step": 301840 }, { "epoch": 1.794259084235367, "grad_norm": 5.004612445831299, "learning_rate": 8.094096117011488e-06, "loss": 0.3061, "step": 301850 }, { "epoch": 1.7943185263120354, "grad_norm": 4.8227925300598145, "learning_rate": 8.093933122344872e-06, "loss": 0.2998, "step": 301860 }, { "epoch": 1.7943779683887038, "grad_norm": 4.874270439147949, "learning_rate": 8.093770122350133e-06, "loss": 0.356, "step": 301870 }, { "epoch": 1.794437410465372, "grad_norm": 4.376070499420166, "learning_rate": 8.093607117027553e-06, "loss": 0.3183, "step": 301880 }, { "epoch": 1.7944968525420404, "grad_norm": 6.3976569175720215, "learning_rate": 8.093444106377412e-06, "loss": 0.3354, "step": 301890 }, { "epoch": 1.7945562946187088, "grad_norm": 4.917484283447266, "learning_rate": 8.093281090399992e-06, "loss": 0.3007, "step": 301900 }, { "epoch": 1.7946157366953772, "grad_norm": 4.900851249694824, "learning_rate": 8.093118069095572e-06, "loss": 0.3212, "step": 301910 }, { "epoch": 1.7946751787720456, "grad_norm": 5.71358585357666, "learning_rate": 8.092955042464434e-06, "loss": 0.2874, "step": 301920 }, { "epoch": 1.7947346208487138, "grad_norm": 4.375190258026123, "learning_rate": 8.092792010506859e-06, "loss": 0.2784, "step": 301930 }, { "epoch": 1.7947940629253822, "grad_norm": 4.27271842956543, "learning_rate": 8.092628973223127e-06, "loss": 0.3049, "step": 301940 }, { "epoch": 1.7948535050020507, "grad_norm": 8.333121299743652, "learning_rate": 8.092465930613519e-06, "loss": 0.3106, "step": 301950 }, { "epoch": 1.794912947078719, "grad_norm": 7.211472988128662, "learning_rate": 8.092302882678316e-06, "loss": 0.3136, "step": 301960 }, { "epoch": 1.7949723891553875, "grad_norm": 4.700506687164307, "learning_rate": 8.092139829417796e-06, "loss": 0.2632, "step": 301970 }, { "epoch": 1.795031831232056, "grad_norm": 4.489504814147949, "learning_rate": 8.091976770832245e-06, "loss": 0.2658, "step": 301980 }, { "epoch": 1.7950912733087243, "grad_norm": 4.681429386138916, "learning_rate": 8.091813706921941e-06, "loss": 0.2872, "step": 301990 }, { "epoch": 1.7951507153853927, "grad_norm": 5.706447124481201, "learning_rate": 8.091650637687163e-06, "loss": 0.3465, "step": 302000 }, { "epoch": 1.7952101574620611, "grad_norm": 4.089914321899414, "learning_rate": 8.091487563128193e-06, "loss": 0.275, "step": 302010 }, { "epoch": 1.7952695995387296, "grad_norm": 4.759404182434082, "learning_rate": 8.091324483245316e-06, "loss": 0.3022, "step": 302020 }, { "epoch": 1.795329041615398, "grad_norm": 5.030570983886719, "learning_rate": 8.091161398038806e-06, "loss": 0.2826, "step": 302030 }, { "epoch": 1.7953884836920664, "grad_norm": 5.746597766876221, "learning_rate": 8.090998307508949e-06, "loss": 0.3056, "step": 302040 }, { "epoch": 1.7954479257687348, "grad_norm": 3.984382390975952, "learning_rate": 8.090835211656023e-06, "loss": 0.3138, "step": 302050 }, { "epoch": 1.7955073678454032, "grad_norm": 3.744262933731079, "learning_rate": 8.090672110480312e-06, "loss": 0.2998, "step": 302060 }, { "epoch": 1.7955668099220714, "grad_norm": 6.1576738357543945, "learning_rate": 8.090509003982094e-06, "loss": 0.324, "step": 302070 }, { "epoch": 1.7956262519987398, "grad_norm": 5.528167247772217, "learning_rate": 8.09034589216165e-06, "loss": 0.3275, "step": 302080 }, { "epoch": 1.7956856940754082, "grad_norm": 5.455602645874023, "learning_rate": 8.090182775019263e-06, "loss": 0.2713, "step": 302090 }, { "epoch": 1.7957451361520766, "grad_norm": 4.515411853790283, "learning_rate": 8.090019652555212e-06, "loss": 0.2958, "step": 302100 }, { "epoch": 1.7958045782287448, "grad_norm": 5.442423343658447, "learning_rate": 8.089856524769777e-06, "loss": 0.3049, "step": 302110 }, { "epoch": 1.7958640203054133, "grad_norm": 4.8186421394348145, "learning_rate": 8.089693391663241e-06, "loss": 0.3043, "step": 302120 }, { "epoch": 1.7959234623820817, "grad_norm": 3.8222031593322754, "learning_rate": 8.089530253235885e-06, "loss": 0.3172, "step": 302130 }, { "epoch": 1.79598290445875, "grad_norm": 4.4866743087768555, "learning_rate": 8.08936710948799e-06, "loss": 0.318, "step": 302140 }, { "epoch": 1.7960423465354185, "grad_norm": 4.976932525634766, "learning_rate": 8.089203960419834e-06, "loss": 0.2818, "step": 302150 }, { "epoch": 1.796101788612087, "grad_norm": 4.543910980224609, "learning_rate": 8.089040806031702e-06, "loss": 0.3254, "step": 302160 }, { "epoch": 1.7961612306887553, "grad_norm": 4.36668586730957, "learning_rate": 8.088877646323874e-06, "loss": 0.3162, "step": 302170 }, { "epoch": 1.7962206727654237, "grad_norm": 4.7169318199157715, "learning_rate": 8.088714481296627e-06, "loss": 0.3043, "step": 302180 }, { "epoch": 1.7962801148420922, "grad_norm": 4.564874172210693, "learning_rate": 8.088551310950247e-06, "loss": 0.3246, "step": 302190 }, { "epoch": 1.7963395569187606, "grad_norm": 5.584537506103516, "learning_rate": 8.088388135285015e-06, "loss": 0.3291, "step": 302200 }, { "epoch": 1.796398998995429, "grad_norm": 6.216095924377441, "learning_rate": 8.088224954301207e-06, "loss": 0.3512, "step": 302210 }, { "epoch": 1.7964584410720974, "grad_norm": 6.321244239807129, "learning_rate": 8.08806176799911e-06, "loss": 0.3208, "step": 302220 }, { "epoch": 1.7965178831487658, "grad_norm": 4.502956867218018, "learning_rate": 8.087898576378999e-06, "loss": 0.3062, "step": 302230 }, { "epoch": 1.7965773252254342, "grad_norm": 5.400216579437256, "learning_rate": 8.08773537944116e-06, "loss": 0.3122, "step": 302240 }, { "epoch": 1.7966367673021024, "grad_norm": 5.4283294677734375, "learning_rate": 8.087572177185873e-06, "loss": 0.3332, "step": 302250 }, { "epoch": 1.7966962093787708, "grad_norm": 4.479178428649902, "learning_rate": 8.087408969613416e-06, "loss": 0.3126, "step": 302260 }, { "epoch": 1.7967556514554393, "grad_norm": 4.801310062408447, "learning_rate": 8.087245756724074e-06, "loss": 0.3097, "step": 302270 }, { "epoch": 1.7968150935321077, "grad_norm": 4.0502119064331055, "learning_rate": 8.087082538518125e-06, "loss": 0.3021, "step": 302280 }, { "epoch": 1.796874535608776, "grad_norm": 5.726144313812256, "learning_rate": 8.086919314995853e-06, "loss": 0.2842, "step": 302290 }, { "epoch": 1.7969339776854443, "grad_norm": 5.837390899658203, "learning_rate": 8.086756086157537e-06, "loss": 0.3098, "step": 302300 }, { "epoch": 1.7969934197621127, "grad_norm": 4.126401424407959, "learning_rate": 8.086592852003458e-06, "loss": 0.3039, "step": 302310 }, { "epoch": 1.797052861838781, "grad_norm": 4.972165107727051, "learning_rate": 8.086429612533899e-06, "loss": 0.3057, "step": 302320 }, { "epoch": 1.7971123039154495, "grad_norm": 5.463834762573242, "learning_rate": 8.08626636774914e-06, "loss": 0.3026, "step": 302330 }, { "epoch": 1.797171745992118, "grad_norm": 4.742259502410889, "learning_rate": 8.086103117649461e-06, "loss": 0.3142, "step": 302340 }, { "epoch": 1.7972311880687863, "grad_norm": 6.501950263977051, "learning_rate": 8.085939862235146e-06, "loss": 0.2925, "step": 302350 }, { "epoch": 1.7972906301454548, "grad_norm": 5.515568733215332, "learning_rate": 8.085776601506474e-06, "loss": 0.3151, "step": 302360 }, { "epoch": 1.7973500722221232, "grad_norm": 4.008137226104736, "learning_rate": 8.085613335463724e-06, "loss": 0.2912, "step": 302370 }, { "epoch": 1.7974095142987916, "grad_norm": 6.120009899139404, "learning_rate": 8.085450064107183e-06, "loss": 0.2778, "step": 302380 }, { "epoch": 1.79746895637546, "grad_norm": 6.1857380867004395, "learning_rate": 8.085286787437127e-06, "loss": 0.289, "step": 302390 }, { "epoch": 1.7975283984521284, "grad_norm": 5.74578332901001, "learning_rate": 8.08512350545384e-06, "loss": 0.3341, "step": 302400 }, { "epoch": 1.7975878405287968, "grad_norm": 5.126713275909424, "learning_rate": 8.0849602181576e-06, "loss": 0.3468, "step": 302410 }, { "epoch": 1.7976472826054652, "grad_norm": 4.194963455200195, "learning_rate": 8.084796925548692e-06, "loss": 0.2691, "step": 302420 }, { "epoch": 1.7977067246821337, "grad_norm": 4.115903377532959, "learning_rate": 8.084633627627396e-06, "loss": 0.2765, "step": 302430 }, { "epoch": 1.7977661667588019, "grad_norm": 5.636917591094971, "learning_rate": 8.084470324393993e-06, "loss": 0.2775, "step": 302440 }, { "epoch": 1.7978256088354703, "grad_norm": 4.877626419067383, "learning_rate": 8.084307015848763e-06, "loss": 0.2958, "step": 302450 }, { "epoch": 1.7978850509121387, "grad_norm": 5.538452625274658, "learning_rate": 8.08414370199199e-06, "loss": 0.3108, "step": 302460 }, { "epoch": 1.797944492988807, "grad_norm": 5.0521063804626465, "learning_rate": 8.08398038282395e-06, "loss": 0.3226, "step": 302470 }, { "epoch": 1.7980039350654753, "grad_norm": 5.80983829498291, "learning_rate": 8.083817058344932e-06, "loss": 0.2673, "step": 302480 }, { "epoch": 1.7980633771421437, "grad_norm": 6.707552433013916, "learning_rate": 8.08365372855521e-06, "loss": 0.2939, "step": 302490 }, { "epoch": 1.7981228192188121, "grad_norm": 4.274495601654053, "learning_rate": 8.08349039345507e-06, "loss": 0.3374, "step": 302500 }, { "epoch": 1.7981822612954805, "grad_norm": 6.136226654052734, "learning_rate": 8.083327053044791e-06, "loss": 0.3324, "step": 302510 }, { "epoch": 1.798241703372149, "grad_norm": 5.523861408233643, "learning_rate": 8.083163707324656e-06, "loss": 0.2936, "step": 302520 }, { "epoch": 1.7983011454488174, "grad_norm": 4.7151408195495605, "learning_rate": 8.083000356294945e-06, "loss": 0.2892, "step": 302530 }, { "epoch": 1.7983605875254858, "grad_norm": 4.785990238189697, "learning_rate": 8.082836999955939e-06, "loss": 0.318, "step": 302540 }, { "epoch": 1.7984200296021542, "grad_norm": 3.865867853164673, "learning_rate": 8.08267363830792e-06, "loss": 0.312, "step": 302550 }, { "epoch": 1.7984794716788226, "grad_norm": 4.473167896270752, "learning_rate": 8.082510271351167e-06, "loss": 0.3263, "step": 302560 }, { "epoch": 1.798538913755491, "grad_norm": 4.92451286315918, "learning_rate": 8.082346899085966e-06, "loss": 0.3064, "step": 302570 }, { "epoch": 1.7985983558321594, "grad_norm": 5.541732311248779, "learning_rate": 8.082183521512594e-06, "loss": 0.2809, "step": 302580 }, { "epoch": 1.7986577979088278, "grad_norm": 5.429383277893066, "learning_rate": 8.082020138631338e-06, "loss": 0.2909, "step": 302590 }, { "epoch": 1.7987172399854963, "grad_norm": 4.780270576477051, "learning_rate": 8.081856750442471e-06, "loss": 0.2885, "step": 302600 }, { "epoch": 1.7987766820621647, "grad_norm": 5.395357608795166, "learning_rate": 8.08169335694628e-06, "loss": 0.333, "step": 302610 }, { "epoch": 1.7988361241388329, "grad_norm": 7.390750885009766, "learning_rate": 8.081529958143048e-06, "loss": 0.3084, "step": 302620 }, { "epoch": 1.7988955662155013, "grad_norm": 5.018841743469238, "learning_rate": 8.081366554033052e-06, "loss": 0.3233, "step": 302630 }, { "epoch": 1.7989550082921697, "grad_norm": 5.2982611656188965, "learning_rate": 8.081203144616576e-06, "loss": 0.3103, "step": 302640 }, { "epoch": 1.7990144503688381, "grad_norm": 5.19489049911499, "learning_rate": 8.081039729893897e-06, "loss": 0.2861, "step": 302650 }, { "epoch": 1.7990738924455065, "grad_norm": 4.163249492645264, "learning_rate": 8.080876309865305e-06, "loss": 0.3132, "step": 302660 }, { "epoch": 1.7991333345221747, "grad_norm": 4.476677417755127, "learning_rate": 8.080712884531072e-06, "loss": 0.278, "step": 302670 }, { "epoch": 1.7991927765988431, "grad_norm": 4.876550674438477, "learning_rate": 8.080549453891487e-06, "loss": 0.3047, "step": 302680 }, { "epoch": 1.7992522186755115, "grad_norm": 4.954895496368408, "learning_rate": 8.080386017946827e-06, "loss": 0.2674, "step": 302690 }, { "epoch": 1.79931166075218, "grad_norm": 4.842199325561523, "learning_rate": 8.080222576697376e-06, "loss": 0.3293, "step": 302700 }, { "epoch": 1.7993711028288484, "grad_norm": 4.6757001876831055, "learning_rate": 8.080059130143413e-06, "loss": 0.3516, "step": 302710 }, { "epoch": 1.7994305449055168, "grad_norm": 5.337704658508301, "learning_rate": 8.07989567828522e-06, "loss": 0.3282, "step": 302720 }, { "epoch": 1.7994899869821852, "grad_norm": 4.975830554962158, "learning_rate": 8.07973222112308e-06, "loss": 0.3152, "step": 302730 }, { "epoch": 1.7995494290588536, "grad_norm": 5.0708770751953125, "learning_rate": 8.079568758657274e-06, "loss": 0.2809, "step": 302740 }, { "epoch": 1.799608871135522, "grad_norm": 6.568369388580322, "learning_rate": 8.079405290888083e-06, "loss": 0.3183, "step": 302750 }, { "epoch": 1.7996683132121905, "grad_norm": 4.29410982131958, "learning_rate": 8.079241817815788e-06, "loss": 0.2858, "step": 302760 }, { "epoch": 1.7997277552888589, "grad_norm": 6.8304901123046875, "learning_rate": 8.079078339440673e-06, "loss": 0.3327, "step": 302770 }, { "epoch": 1.7997871973655273, "grad_norm": 4.524847030639648, "learning_rate": 8.078914855763014e-06, "loss": 0.3247, "step": 302780 }, { "epoch": 1.7998466394421957, "grad_norm": 5.697370529174805, "learning_rate": 8.0787513667831e-06, "loss": 0.2863, "step": 302790 }, { "epoch": 1.799906081518864, "grad_norm": 5.277231693267822, "learning_rate": 8.078587872501207e-06, "loss": 0.3176, "step": 302800 }, { "epoch": 1.7999655235955323, "grad_norm": 4.964577674865723, "learning_rate": 8.07842437291762e-06, "loss": 0.321, "step": 302810 }, { "epoch": 1.8000249656722007, "grad_norm": 5.003198623657227, "learning_rate": 8.078260868032618e-06, "loss": 0.3178, "step": 302820 }, { "epoch": 1.8000844077488691, "grad_norm": 5.052608966827393, "learning_rate": 8.078097357846482e-06, "loss": 0.328, "step": 302830 }, { "epoch": 1.8001438498255375, "grad_norm": 5.228946685791016, "learning_rate": 8.077933842359495e-06, "loss": 0.3032, "step": 302840 }, { "epoch": 1.8002032919022057, "grad_norm": 3.831087827682495, "learning_rate": 8.07777032157194e-06, "loss": 0.3007, "step": 302850 }, { "epoch": 1.8002627339788742, "grad_norm": 5.347973823547363, "learning_rate": 8.077606795484098e-06, "loss": 0.3311, "step": 302860 }, { "epoch": 1.8003221760555426, "grad_norm": 3.957470417022705, "learning_rate": 8.07744326409625e-06, "loss": 0.255, "step": 302870 }, { "epoch": 1.800381618132211, "grad_norm": 6.508852481842041, "learning_rate": 8.077279727408675e-06, "loss": 0.2818, "step": 302880 }, { "epoch": 1.8004410602088794, "grad_norm": 3.1636910438537598, "learning_rate": 8.077116185421658e-06, "loss": 0.3431, "step": 302890 }, { "epoch": 1.8005005022855478, "grad_norm": 4.7326836585998535, "learning_rate": 8.07695263813548e-06, "loss": 0.308, "step": 302900 }, { "epoch": 1.8005599443622162, "grad_norm": 5.535269737243652, "learning_rate": 8.076789085550424e-06, "loss": 0.3035, "step": 302910 }, { "epoch": 1.8006193864388846, "grad_norm": 4.013134479522705, "learning_rate": 8.076625527666769e-06, "loss": 0.3119, "step": 302920 }, { "epoch": 1.800678828515553, "grad_norm": 4.632597923278809, "learning_rate": 8.076461964484797e-06, "loss": 0.348, "step": 302930 }, { "epoch": 1.8007382705922215, "grad_norm": 4.524596691131592, "learning_rate": 8.076298396004791e-06, "loss": 0.3291, "step": 302940 }, { "epoch": 1.8007977126688899, "grad_norm": 5.848730087280273, "learning_rate": 8.076134822227034e-06, "loss": 0.2996, "step": 302950 }, { "epoch": 1.8008571547455583, "grad_norm": 5.846091270446777, "learning_rate": 8.075971243151803e-06, "loss": 0.3098, "step": 302960 }, { "epoch": 1.8009165968222267, "grad_norm": 5.491160869598389, "learning_rate": 8.075807658779384e-06, "loss": 0.3168, "step": 302970 }, { "epoch": 1.8009760388988951, "grad_norm": 3.567737340927124, "learning_rate": 8.075644069110055e-06, "loss": 0.2798, "step": 302980 }, { "epoch": 1.8010354809755633, "grad_norm": 5.652502536773682, "learning_rate": 8.075480474144103e-06, "loss": 0.3167, "step": 302990 }, { "epoch": 1.8010949230522317, "grad_norm": 5.024651050567627, "learning_rate": 8.075316873881804e-06, "loss": 0.3265, "step": 303000 }, { "epoch": 1.8011543651289001, "grad_norm": 3.325392723083496, "learning_rate": 8.075153268323444e-06, "loss": 0.3173, "step": 303010 }, { "epoch": 1.8012138072055686, "grad_norm": 4.182454586029053, "learning_rate": 8.074989657469303e-06, "loss": 0.3187, "step": 303020 }, { "epoch": 1.801273249282237, "grad_norm": 6.066709518432617, "learning_rate": 8.074826041319664e-06, "loss": 0.3073, "step": 303030 }, { "epoch": 1.8013326913589052, "grad_norm": 6.089590072631836, "learning_rate": 8.074662419874806e-06, "loss": 0.3233, "step": 303040 }, { "epoch": 1.8013921334355736, "grad_norm": 5.5598649978637695, "learning_rate": 8.074498793135013e-06, "loss": 0.3431, "step": 303050 }, { "epoch": 1.801451575512242, "grad_norm": 6.095813751220703, "learning_rate": 8.074335161100566e-06, "loss": 0.3067, "step": 303060 }, { "epoch": 1.8015110175889104, "grad_norm": 5.035592079162598, "learning_rate": 8.074171523771746e-06, "loss": 0.2853, "step": 303070 }, { "epoch": 1.8015704596655788, "grad_norm": 5.112330913543701, "learning_rate": 8.074007881148837e-06, "loss": 0.3136, "step": 303080 }, { "epoch": 1.8016299017422472, "grad_norm": 6.570888042449951, "learning_rate": 8.07384423323212e-06, "loss": 0.3262, "step": 303090 }, { "epoch": 1.8016893438189157, "grad_norm": 5.263064861297607, "learning_rate": 8.073680580021876e-06, "loss": 0.3357, "step": 303100 }, { "epoch": 1.801748785895584, "grad_norm": 5.016786575317383, "learning_rate": 8.073516921518387e-06, "loss": 0.3345, "step": 303110 }, { "epoch": 1.8018082279722525, "grad_norm": 6.337373733520508, "learning_rate": 8.073353257721937e-06, "loss": 0.3032, "step": 303120 }, { "epoch": 1.801867670048921, "grad_norm": 5.615935802459717, "learning_rate": 8.073189588632803e-06, "loss": 0.2925, "step": 303130 }, { "epoch": 1.8019271121255893, "grad_norm": 5.332149505615234, "learning_rate": 8.073025914251272e-06, "loss": 0.3377, "step": 303140 }, { "epoch": 1.8019865542022577, "grad_norm": 5.501285552978516, "learning_rate": 8.072862234577623e-06, "loss": 0.3402, "step": 303150 }, { "epoch": 1.8020459962789261, "grad_norm": 5.665746688842773, "learning_rate": 8.072698549612138e-06, "loss": 0.3295, "step": 303160 }, { "epoch": 1.8021054383555943, "grad_norm": 5.459997653961182, "learning_rate": 8.0725348593551e-06, "loss": 0.3096, "step": 303170 }, { "epoch": 1.8021648804322628, "grad_norm": 5.437974452972412, "learning_rate": 8.072371163806792e-06, "loss": 0.3291, "step": 303180 }, { "epoch": 1.8022243225089312, "grad_norm": 4.9453206062316895, "learning_rate": 8.072207462967492e-06, "loss": 0.2959, "step": 303190 }, { "epoch": 1.8022837645855996, "grad_norm": 4.687328338623047, "learning_rate": 8.072043756837485e-06, "loss": 0.2957, "step": 303200 }, { "epoch": 1.802343206662268, "grad_norm": 4.761216163635254, "learning_rate": 8.071880045417053e-06, "loss": 0.2845, "step": 303210 }, { "epoch": 1.8024026487389362, "grad_norm": 4.254067420959473, "learning_rate": 8.071716328706476e-06, "loss": 0.3176, "step": 303220 }, { "epoch": 1.8024620908156046, "grad_norm": 4.886063098907471, "learning_rate": 8.071552606706037e-06, "loss": 0.2966, "step": 303230 }, { "epoch": 1.802521532892273, "grad_norm": 5.610195636749268, "learning_rate": 8.071388879416017e-06, "loss": 0.2899, "step": 303240 }, { "epoch": 1.8025809749689414, "grad_norm": 4.607027530670166, "learning_rate": 8.0712251468367e-06, "loss": 0.3243, "step": 303250 }, { "epoch": 1.8026404170456098, "grad_norm": 4.627046585083008, "learning_rate": 8.071061408968367e-06, "loss": 0.3086, "step": 303260 }, { "epoch": 1.8026998591222783, "grad_norm": 3.992946147918701, "learning_rate": 8.0708976658113e-06, "loss": 0.2992, "step": 303270 }, { "epoch": 1.8027593011989467, "grad_norm": 4.100470066070557, "learning_rate": 8.07073391736578e-06, "loss": 0.3086, "step": 303280 }, { "epoch": 1.802818743275615, "grad_norm": 4.159958839416504, "learning_rate": 8.07057016363209e-06, "loss": 0.3002, "step": 303290 }, { "epoch": 1.8028781853522835, "grad_norm": 4.63380765914917, "learning_rate": 8.070406404610511e-06, "loss": 0.2748, "step": 303300 }, { "epoch": 1.802937627428952, "grad_norm": 5.131138324737549, "learning_rate": 8.070242640301329e-06, "loss": 0.3181, "step": 303310 }, { "epoch": 1.8029970695056203, "grad_norm": 4.4315409660339355, "learning_rate": 8.070078870704818e-06, "loss": 0.2868, "step": 303320 }, { "epoch": 1.8030565115822887, "grad_norm": 4.789194107055664, "learning_rate": 8.069915095821268e-06, "loss": 0.3053, "step": 303330 }, { "epoch": 1.8031159536589572, "grad_norm": 6.112425804138184, "learning_rate": 8.069751315650957e-06, "loss": 0.3092, "step": 303340 }, { "epoch": 1.8031753957356256, "grad_norm": 4.560986042022705, "learning_rate": 8.069587530194169e-06, "loss": 0.2954, "step": 303350 }, { "epoch": 1.8032348378122938, "grad_norm": 4.012414932250977, "learning_rate": 8.069423739451185e-06, "loss": 0.3166, "step": 303360 }, { "epoch": 1.8032942798889622, "grad_norm": 5.75433349609375, "learning_rate": 8.069259943422285e-06, "loss": 0.3353, "step": 303370 }, { "epoch": 1.8033537219656306, "grad_norm": 5.037307262420654, "learning_rate": 8.069096142107755e-06, "loss": 0.3063, "step": 303380 }, { "epoch": 1.803413164042299, "grad_norm": 6.550324440002441, "learning_rate": 8.068932335507876e-06, "loss": 0.3252, "step": 303390 }, { "epoch": 1.8034726061189674, "grad_norm": 5.737388610839844, "learning_rate": 8.068768523622928e-06, "loss": 0.3481, "step": 303400 }, { "epoch": 1.8035320481956356, "grad_norm": 4.414391040802002, "learning_rate": 8.068604706453193e-06, "loss": 0.2764, "step": 303410 }, { "epoch": 1.803591490272304, "grad_norm": 4.317295074462891, "learning_rate": 8.068440883998957e-06, "loss": 0.3376, "step": 303420 }, { "epoch": 1.8036509323489724, "grad_norm": 4.519075870513916, "learning_rate": 8.068277056260498e-06, "loss": 0.322, "step": 303430 }, { "epoch": 1.8037103744256409, "grad_norm": 4.0311760902404785, "learning_rate": 8.0681132232381e-06, "loss": 0.2831, "step": 303440 }, { "epoch": 1.8037698165023093, "grad_norm": 7.116058826446533, "learning_rate": 8.067949384932046e-06, "loss": 0.3438, "step": 303450 }, { "epoch": 1.8038292585789777, "grad_norm": 4.884950160980225, "learning_rate": 8.067785541342617e-06, "loss": 0.2906, "step": 303460 }, { "epoch": 1.803888700655646, "grad_norm": 4.925540447235107, "learning_rate": 8.067621692470095e-06, "loss": 0.2911, "step": 303470 }, { "epoch": 1.8039481427323145, "grad_norm": 4.531673908233643, "learning_rate": 8.067457838314763e-06, "loss": 0.3062, "step": 303480 }, { "epoch": 1.804007584808983, "grad_norm": 6.403196811676025, "learning_rate": 8.067293978876903e-06, "loss": 0.3292, "step": 303490 }, { "epoch": 1.8040670268856513, "grad_norm": 6.111213684082031, "learning_rate": 8.067130114156793e-06, "loss": 0.3013, "step": 303500 }, { "epoch": 1.8041264689623198, "grad_norm": 4.422734260559082, "learning_rate": 8.066966244154722e-06, "loss": 0.312, "step": 303510 }, { "epoch": 1.8041859110389882, "grad_norm": 7.0353546142578125, "learning_rate": 8.066802368870969e-06, "loss": 0.3225, "step": 303520 }, { "epoch": 1.8042453531156566, "grad_norm": 6.4326372146606445, "learning_rate": 8.066638488305818e-06, "loss": 0.3243, "step": 303530 }, { "epoch": 1.8043047951923248, "grad_norm": 5.863590240478516, "learning_rate": 8.066474602459546e-06, "loss": 0.2939, "step": 303540 }, { "epoch": 1.8043642372689932, "grad_norm": 6.113304138183594, "learning_rate": 8.066310711332442e-06, "loss": 0.3294, "step": 303550 }, { "epoch": 1.8044236793456616, "grad_norm": 6.071985721588135, "learning_rate": 8.066146814924784e-06, "loss": 0.3199, "step": 303560 }, { "epoch": 1.80448312142233, "grad_norm": 7.1778035163879395, "learning_rate": 8.065982913236854e-06, "loss": 0.3381, "step": 303570 }, { "epoch": 1.8045425634989984, "grad_norm": 5.542738914489746, "learning_rate": 8.065819006268939e-06, "loss": 0.3177, "step": 303580 }, { "epoch": 1.8046020055756666, "grad_norm": 5.011507034301758, "learning_rate": 8.065655094021314e-06, "loss": 0.338, "step": 303590 }, { "epoch": 1.804661447652335, "grad_norm": 3.562514305114746, "learning_rate": 8.065491176494266e-06, "loss": 0.3055, "step": 303600 }, { "epoch": 1.8047208897290035, "grad_norm": 6.381519794464111, "learning_rate": 8.065327253688078e-06, "loss": 0.3268, "step": 303610 }, { "epoch": 1.8047803318056719, "grad_norm": 3.8613698482513428, "learning_rate": 8.06516332560303e-06, "loss": 0.2899, "step": 303620 }, { "epoch": 1.8048397738823403, "grad_norm": 5.722442150115967, "learning_rate": 8.064999392239405e-06, "loss": 0.296, "step": 303630 }, { "epoch": 1.8048992159590087, "grad_norm": 5.05775785446167, "learning_rate": 8.064835453597485e-06, "loss": 0.3071, "step": 303640 }, { "epoch": 1.8049586580356771, "grad_norm": 4.8089518547058105, "learning_rate": 8.064671509677553e-06, "loss": 0.295, "step": 303650 }, { "epoch": 1.8050181001123455, "grad_norm": 4.823336124420166, "learning_rate": 8.06450756047989e-06, "loss": 0.3586, "step": 303660 }, { "epoch": 1.805077542189014, "grad_norm": 5.5953826904296875, "learning_rate": 8.064343606004782e-06, "loss": 0.3359, "step": 303670 }, { "epoch": 1.8051369842656824, "grad_norm": 5.592179775238037, "learning_rate": 8.064179646252505e-06, "loss": 0.2922, "step": 303680 }, { "epoch": 1.8051964263423508, "grad_norm": 3.86417555809021, "learning_rate": 8.064015681223348e-06, "loss": 0.2735, "step": 303690 }, { "epoch": 1.8052558684190192, "grad_norm": 2.871621608734131, "learning_rate": 8.06385171091759e-06, "loss": 0.3243, "step": 303700 }, { "epoch": 1.8053153104956876, "grad_norm": 4.221832752227783, "learning_rate": 8.063687735335512e-06, "loss": 0.3385, "step": 303710 }, { "epoch": 1.805374752572356, "grad_norm": 5.369959831237793, "learning_rate": 8.0635237544774e-06, "loss": 0.3293, "step": 303720 }, { "epoch": 1.8054341946490242, "grad_norm": 4.2434587478637695, "learning_rate": 8.063359768343533e-06, "loss": 0.3352, "step": 303730 }, { "epoch": 1.8054936367256926, "grad_norm": 4.1008734703063965, "learning_rate": 8.063195776934197e-06, "loss": 0.2815, "step": 303740 }, { "epoch": 1.805553078802361, "grad_norm": 4.1998677253723145, "learning_rate": 8.063031780249672e-06, "loss": 0.3095, "step": 303750 }, { "epoch": 1.8056125208790295, "grad_norm": 4.634762287139893, "learning_rate": 8.06286777829024e-06, "loss": 0.3231, "step": 303760 }, { "epoch": 1.8056719629556979, "grad_norm": 3.9406886100769043, "learning_rate": 8.062703771056182e-06, "loss": 0.294, "step": 303770 }, { "epoch": 1.805731405032366, "grad_norm": 5.201691150665283, "learning_rate": 8.062539758547785e-06, "loss": 0.3211, "step": 303780 }, { "epoch": 1.8057908471090345, "grad_norm": 5.551589488983154, "learning_rate": 8.06237574076533e-06, "loss": 0.2972, "step": 303790 }, { "epoch": 1.805850289185703, "grad_norm": 4.570013523101807, "learning_rate": 8.062211717709098e-06, "loss": 0.2683, "step": 303800 }, { "epoch": 1.8059097312623713, "grad_norm": 5.706124305725098, "learning_rate": 8.06204768937937e-06, "loss": 0.2922, "step": 303810 }, { "epoch": 1.8059691733390397, "grad_norm": 4.958663463592529, "learning_rate": 8.061883655776433e-06, "loss": 0.278, "step": 303820 }, { "epoch": 1.8060286154157081, "grad_norm": 4.9039435386657715, "learning_rate": 8.061719616900567e-06, "loss": 0.263, "step": 303830 }, { "epoch": 1.8060880574923766, "grad_norm": 4.722098350524902, "learning_rate": 8.061555572752054e-06, "loss": 0.321, "step": 303840 }, { "epoch": 1.806147499569045, "grad_norm": 5.101294994354248, "learning_rate": 8.061391523331177e-06, "loss": 0.2827, "step": 303850 }, { "epoch": 1.8062069416457134, "grad_norm": 6.170759677886963, "learning_rate": 8.061227468638217e-06, "loss": 0.3035, "step": 303860 }, { "epoch": 1.8062663837223818, "grad_norm": 5.330420970916748, "learning_rate": 8.06106340867346e-06, "loss": 0.2868, "step": 303870 }, { "epoch": 1.8063258257990502, "grad_norm": 5.388418674468994, "learning_rate": 8.060899343437186e-06, "loss": 0.3171, "step": 303880 }, { "epoch": 1.8063852678757186, "grad_norm": 6.323692321777344, "learning_rate": 8.060735272929677e-06, "loss": 0.2934, "step": 303890 }, { "epoch": 1.806444709952387, "grad_norm": 6.304410457611084, "learning_rate": 8.060571197151217e-06, "loss": 0.3158, "step": 303900 }, { "epoch": 1.8065041520290552, "grad_norm": 4.147335052490234, "learning_rate": 8.060407116102089e-06, "loss": 0.2782, "step": 303910 }, { "epoch": 1.8065635941057236, "grad_norm": 4.351635932922363, "learning_rate": 8.060243029782575e-06, "loss": 0.2952, "step": 303920 }, { "epoch": 1.806623036182392, "grad_norm": 6.322012901306152, "learning_rate": 8.060078938192958e-06, "loss": 0.3256, "step": 303930 }, { "epoch": 1.8066824782590605, "grad_norm": 4.252095699310303, "learning_rate": 8.059914841333519e-06, "loss": 0.3094, "step": 303940 }, { "epoch": 1.806741920335729, "grad_norm": 4.692478656768799, "learning_rate": 8.059750739204542e-06, "loss": 0.3036, "step": 303950 }, { "epoch": 1.806801362412397, "grad_norm": 5.165581226348877, "learning_rate": 8.059586631806307e-06, "loss": 0.3286, "step": 303960 }, { "epoch": 1.8068608044890655, "grad_norm": 4.131728172302246, "learning_rate": 8.0594225191391e-06, "loss": 0.3229, "step": 303970 }, { "epoch": 1.806920246565734, "grad_norm": 5.6334428787231445, "learning_rate": 8.059258401203204e-06, "loss": 0.2872, "step": 303980 }, { "epoch": 1.8069796886424023, "grad_norm": 4.51836633682251, "learning_rate": 8.059094277998897e-06, "loss": 0.3084, "step": 303990 }, { "epoch": 1.8070391307190707, "grad_norm": 4.929662227630615, "learning_rate": 8.058930149526467e-06, "loss": 0.3192, "step": 304000 }, { "epoch": 1.8070985727957392, "grad_norm": 6.104806900024414, "learning_rate": 8.058766015786194e-06, "loss": 0.2744, "step": 304010 }, { "epoch": 1.8071580148724076, "grad_norm": 4.8911919593811035, "learning_rate": 8.05860187677836e-06, "loss": 0.3062, "step": 304020 }, { "epoch": 1.807217456949076, "grad_norm": 5.033576965332031, "learning_rate": 8.058437732503251e-06, "loss": 0.3087, "step": 304030 }, { "epoch": 1.8072768990257444, "grad_norm": 4.4192609786987305, "learning_rate": 8.058273582961144e-06, "loss": 0.2813, "step": 304040 }, { "epoch": 1.8073363411024128, "grad_norm": 7.302925109863281, "learning_rate": 8.058109428152327e-06, "loss": 0.2927, "step": 304050 }, { "epoch": 1.8073957831790812, "grad_norm": 4.698563575744629, "learning_rate": 8.05794526807708e-06, "loss": 0.3347, "step": 304060 }, { "epoch": 1.8074552252557496, "grad_norm": 4.497373104095459, "learning_rate": 8.057781102735687e-06, "loss": 0.3134, "step": 304070 }, { "epoch": 1.807514667332418, "grad_norm": 5.191699504852295, "learning_rate": 8.05761693212843e-06, "loss": 0.2989, "step": 304080 }, { "epoch": 1.8075741094090865, "grad_norm": 5.736154079437256, "learning_rate": 8.057452756255592e-06, "loss": 0.2977, "step": 304090 }, { "epoch": 1.8076335514857547, "grad_norm": 3.911491870880127, "learning_rate": 8.057288575117453e-06, "loss": 0.2922, "step": 304100 }, { "epoch": 1.807692993562423, "grad_norm": 4.781367778778076, "learning_rate": 8.0571243887143e-06, "loss": 0.2861, "step": 304110 }, { "epoch": 1.8077524356390915, "grad_norm": 5.281059741973877, "learning_rate": 8.056960197046414e-06, "loss": 0.2862, "step": 304120 }, { "epoch": 1.80781187771576, "grad_norm": 3.684298038482666, "learning_rate": 8.05679600011408e-06, "loss": 0.2678, "step": 304130 }, { "epoch": 1.8078713197924283, "grad_norm": 3.485373020172119, "learning_rate": 8.056631797917577e-06, "loss": 0.3102, "step": 304140 }, { "epoch": 1.8079307618690965, "grad_norm": 6.455813407897949, "learning_rate": 8.056467590457189e-06, "loss": 0.277, "step": 304150 }, { "epoch": 1.807990203945765, "grad_norm": 7.128039360046387, "learning_rate": 8.056303377733199e-06, "loss": 0.3237, "step": 304160 }, { "epoch": 1.8080496460224333, "grad_norm": 5.088293075561523, "learning_rate": 8.05613915974589e-06, "loss": 0.2905, "step": 304170 }, { "epoch": 1.8081090880991018, "grad_norm": 5.346890449523926, "learning_rate": 8.055974936495545e-06, "loss": 0.3032, "step": 304180 }, { "epoch": 1.8081685301757702, "grad_norm": 4.264969348907471, "learning_rate": 8.055810707982446e-06, "loss": 0.306, "step": 304190 }, { "epoch": 1.8082279722524386, "grad_norm": 5.738027095794678, "learning_rate": 8.055646474206878e-06, "loss": 0.3125, "step": 304200 }, { "epoch": 1.808287414329107, "grad_norm": 6.8343987464904785, "learning_rate": 8.055482235169118e-06, "loss": 0.2945, "step": 304210 }, { "epoch": 1.8083468564057754, "grad_norm": 5.482481479644775, "learning_rate": 8.055317990869457e-06, "loss": 0.3131, "step": 304220 }, { "epoch": 1.8084062984824438, "grad_norm": 4.311356544494629, "learning_rate": 8.055153741308172e-06, "loss": 0.3272, "step": 304230 }, { "epoch": 1.8084657405591122, "grad_norm": 5.526033401489258, "learning_rate": 8.05498948648555e-06, "loss": 0.3234, "step": 304240 }, { "epoch": 1.8085251826357807, "grad_norm": 5.2498626708984375, "learning_rate": 8.05482522640187e-06, "loss": 0.3338, "step": 304250 }, { "epoch": 1.808584624712449, "grad_norm": 4.947145938873291, "learning_rate": 8.054660961057417e-06, "loss": 0.2764, "step": 304260 }, { "epoch": 1.8086440667891175, "grad_norm": 4.691162109375, "learning_rate": 8.05449669045247e-06, "loss": 0.2656, "step": 304270 }, { "epoch": 1.8087035088657857, "grad_norm": 4.002228260040283, "learning_rate": 8.054332414587321e-06, "loss": 0.2688, "step": 304280 }, { "epoch": 1.808762950942454, "grad_norm": 5.530405044555664, "learning_rate": 8.054168133462244e-06, "loss": 0.282, "step": 304290 }, { "epoch": 1.8088223930191225, "grad_norm": 4.2588582038879395, "learning_rate": 8.054003847077524e-06, "loss": 0.3052, "step": 304300 }, { "epoch": 1.808881835095791, "grad_norm": 4.0478692054748535, "learning_rate": 8.053839555433447e-06, "loss": 0.299, "step": 304310 }, { "epoch": 1.8089412771724593, "grad_norm": 5.096248626708984, "learning_rate": 8.053675258530292e-06, "loss": 0.2662, "step": 304320 }, { "epoch": 1.8090007192491275, "grad_norm": 5.356690883636475, "learning_rate": 8.053510956368345e-06, "loss": 0.3347, "step": 304330 }, { "epoch": 1.809060161325796, "grad_norm": 4.577081203460693, "learning_rate": 8.053346648947888e-06, "loss": 0.3445, "step": 304340 }, { "epoch": 1.8091196034024644, "grad_norm": 4.476861476898193, "learning_rate": 8.053182336269204e-06, "loss": 0.2887, "step": 304350 }, { "epoch": 1.8091790454791328, "grad_norm": 4.7274699211120605, "learning_rate": 8.053018018332575e-06, "loss": 0.3237, "step": 304360 }, { "epoch": 1.8092384875558012, "grad_norm": 4.625352382659912, "learning_rate": 8.052853695138285e-06, "loss": 0.295, "step": 304370 }, { "epoch": 1.8092979296324696, "grad_norm": 4.674252510070801, "learning_rate": 8.052689366686617e-06, "loss": 0.3097, "step": 304380 }, { "epoch": 1.809357371709138, "grad_norm": 6.15410852432251, "learning_rate": 8.052525032977854e-06, "loss": 0.3148, "step": 304390 }, { "epoch": 1.8094168137858064, "grad_norm": 4.340574264526367, "learning_rate": 8.052360694012278e-06, "loss": 0.3282, "step": 304400 }, { "epoch": 1.8094762558624748, "grad_norm": 5.049628734588623, "learning_rate": 8.052196349790172e-06, "loss": 0.3378, "step": 304410 }, { "epoch": 1.8095356979391433, "grad_norm": 5.081877708435059, "learning_rate": 8.052032000311821e-06, "loss": 0.2812, "step": 304420 }, { "epoch": 1.8095951400158117, "grad_norm": 5.078279972076416, "learning_rate": 8.051867645577504e-06, "loss": 0.3216, "step": 304430 }, { "epoch": 1.80965458209248, "grad_norm": 4.978749752044678, "learning_rate": 8.05170328558751e-06, "loss": 0.3379, "step": 304440 }, { "epoch": 1.8097140241691485, "grad_norm": 4.893807888031006, "learning_rate": 8.051538920342117e-06, "loss": 0.3119, "step": 304450 }, { "epoch": 1.809773466245817, "grad_norm": 4.577123165130615, "learning_rate": 8.051374549841612e-06, "loss": 0.2968, "step": 304460 }, { "epoch": 1.8098329083224851, "grad_norm": 4.9964494705200195, "learning_rate": 8.051210174086274e-06, "loss": 0.3149, "step": 304470 }, { "epoch": 1.8098923503991535, "grad_norm": 5.129109859466553, "learning_rate": 8.051045793076389e-06, "loss": 0.321, "step": 304480 }, { "epoch": 1.809951792475822, "grad_norm": 5.517902851104736, "learning_rate": 8.05088140681224e-06, "loss": 0.2766, "step": 304490 }, { "epoch": 1.8100112345524904, "grad_norm": 6.053656578063965, "learning_rate": 8.050717015294105e-06, "loss": 0.2682, "step": 304500 }, { "epoch": 1.8100706766291588, "grad_norm": 7.543394088745117, "learning_rate": 8.050552618522277e-06, "loss": 0.341, "step": 304510 }, { "epoch": 1.810130118705827, "grad_norm": 4.542171478271484, "learning_rate": 8.05038821649703e-06, "loss": 0.3048, "step": 304520 }, { "epoch": 1.8101895607824954, "grad_norm": 4.367161273956299, "learning_rate": 8.05022380921865e-06, "loss": 0.3163, "step": 304530 }, { "epoch": 1.8102490028591638, "grad_norm": 3.951603412628174, "learning_rate": 8.050059396687422e-06, "loss": 0.3361, "step": 304540 }, { "epoch": 1.8103084449358322, "grad_norm": 4.985818862915039, "learning_rate": 8.049894978903627e-06, "loss": 0.3111, "step": 304550 }, { "epoch": 1.8103678870125006, "grad_norm": 4.796683311462402, "learning_rate": 8.049730555867549e-06, "loss": 0.307, "step": 304560 }, { "epoch": 1.810427329089169, "grad_norm": 4.251535892486572, "learning_rate": 8.049566127579471e-06, "loss": 0.3265, "step": 304570 }, { "epoch": 1.8104867711658374, "grad_norm": 4.709476947784424, "learning_rate": 8.049401694039678e-06, "loss": 0.3008, "step": 304580 }, { "epoch": 1.8105462132425059, "grad_norm": 4.95495080947876, "learning_rate": 8.04923725524845e-06, "loss": 0.3261, "step": 304590 }, { "epoch": 1.8106056553191743, "grad_norm": 5.138727188110352, "learning_rate": 8.049072811206072e-06, "loss": 0.3253, "step": 304600 }, { "epoch": 1.8106650973958427, "grad_norm": 6.102019786834717, "learning_rate": 8.048908361912827e-06, "loss": 0.3245, "step": 304610 }, { "epoch": 1.810724539472511, "grad_norm": 5.120279788970947, "learning_rate": 8.048743907368997e-06, "loss": 0.3158, "step": 304620 }, { "epoch": 1.8107839815491795, "grad_norm": 4.246302604675293, "learning_rate": 8.048579447574868e-06, "loss": 0.2755, "step": 304630 }, { "epoch": 1.810843423625848, "grad_norm": 6.052717208862305, "learning_rate": 8.04841498253072e-06, "loss": 0.3172, "step": 304640 }, { "epoch": 1.8109028657025161, "grad_norm": 6.00744104385376, "learning_rate": 8.048250512236838e-06, "loss": 0.3734, "step": 304650 }, { "epoch": 1.8109623077791845, "grad_norm": 4.020755767822266, "learning_rate": 8.048086036693505e-06, "loss": 0.3016, "step": 304660 }, { "epoch": 1.811021749855853, "grad_norm": 5.641307353973389, "learning_rate": 8.047921555901003e-06, "loss": 0.3112, "step": 304670 }, { "epoch": 1.8110811919325214, "grad_norm": 5.135063648223877, "learning_rate": 8.047757069859617e-06, "loss": 0.3167, "step": 304680 }, { "epoch": 1.8111406340091898, "grad_norm": 3.836772918701172, "learning_rate": 8.047592578569631e-06, "loss": 0.2925, "step": 304690 }, { "epoch": 1.811200076085858, "grad_norm": 4.609968662261963, "learning_rate": 8.047428082031326e-06, "loss": 0.2816, "step": 304700 }, { "epoch": 1.8112595181625264, "grad_norm": 4.995397567749023, "learning_rate": 8.047263580244986e-06, "loss": 0.2946, "step": 304710 }, { "epoch": 1.8113189602391948, "grad_norm": 5.0146660804748535, "learning_rate": 8.047099073210896e-06, "loss": 0.3104, "step": 304720 }, { "epoch": 1.8113784023158632, "grad_norm": 4.641417503356934, "learning_rate": 8.046934560929337e-06, "loss": 0.3128, "step": 304730 }, { "epoch": 1.8114378443925316, "grad_norm": 5.9518022537231445, "learning_rate": 8.046770043400591e-06, "loss": 0.2775, "step": 304740 }, { "epoch": 1.8114972864692, "grad_norm": 5.361491680145264, "learning_rate": 8.046605520624946e-06, "loss": 0.2789, "step": 304750 }, { "epoch": 1.8115567285458685, "grad_norm": 5.2253618240356445, "learning_rate": 8.046440992602682e-06, "loss": 0.3186, "step": 304760 }, { "epoch": 1.8116161706225369, "grad_norm": 4.615225791931152, "learning_rate": 8.046276459334082e-06, "loss": 0.32, "step": 304770 }, { "epoch": 1.8116756126992053, "grad_norm": 4.338611125946045, "learning_rate": 8.046111920819433e-06, "loss": 0.287, "step": 304780 }, { "epoch": 1.8117350547758737, "grad_norm": 5.009875774383545, "learning_rate": 8.045947377059014e-06, "loss": 0.3099, "step": 304790 }, { "epoch": 1.8117944968525421, "grad_norm": 4.707656383514404, "learning_rate": 8.04578282805311e-06, "loss": 0.3043, "step": 304800 }, { "epoch": 1.8118539389292105, "grad_norm": 7.359311103820801, "learning_rate": 8.045618273802005e-06, "loss": 0.3065, "step": 304810 }, { "epoch": 1.811913381005879, "grad_norm": 4.029538631439209, "learning_rate": 8.045453714305984e-06, "loss": 0.2814, "step": 304820 }, { "epoch": 1.8119728230825474, "grad_norm": 4.001430034637451, "learning_rate": 8.045289149565324e-06, "loss": 0.3368, "step": 304830 }, { "epoch": 1.8120322651592156, "grad_norm": 5.016202449798584, "learning_rate": 8.045124579580316e-06, "loss": 0.2781, "step": 304840 }, { "epoch": 1.812091707235884, "grad_norm": 5.735378265380859, "learning_rate": 8.04496000435124e-06, "loss": 0.3045, "step": 304850 }, { "epoch": 1.8121511493125524, "grad_norm": 4.145130157470703, "learning_rate": 8.044795423878378e-06, "loss": 0.2939, "step": 304860 }, { "epoch": 1.8122105913892208, "grad_norm": 7.582405090332031, "learning_rate": 8.044630838162015e-06, "loss": 0.3275, "step": 304870 }, { "epoch": 1.8122700334658892, "grad_norm": 5.423324108123779, "learning_rate": 8.044466247202437e-06, "loss": 0.2826, "step": 304880 }, { "epoch": 1.8123294755425574, "grad_norm": 5.060634136199951, "learning_rate": 8.044301650999922e-06, "loss": 0.3105, "step": 304890 }, { "epoch": 1.8123889176192258, "grad_norm": 4.590551376342773, "learning_rate": 8.044137049554757e-06, "loss": 0.3114, "step": 304900 }, { "epoch": 1.8124483596958942, "grad_norm": 7.023123741149902, "learning_rate": 8.043972442867226e-06, "loss": 0.3175, "step": 304910 }, { "epoch": 1.8125078017725627, "grad_norm": 5.043313980102539, "learning_rate": 8.043807830937612e-06, "loss": 0.2817, "step": 304920 }, { "epoch": 1.812567243849231, "grad_norm": 4.482994079589844, "learning_rate": 8.043643213766194e-06, "loss": 0.2752, "step": 304930 }, { "epoch": 1.8126266859258995, "grad_norm": 4.00693416595459, "learning_rate": 8.043478591353262e-06, "loss": 0.2831, "step": 304940 }, { "epoch": 1.812686128002568, "grad_norm": 4.997134685516357, "learning_rate": 8.043313963699097e-06, "loss": 0.2975, "step": 304950 }, { "epoch": 1.8127455700792363, "grad_norm": 4.100216388702393, "learning_rate": 8.043149330803981e-06, "loss": 0.3014, "step": 304960 }, { "epoch": 1.8128050121559047, "grad_norm": 3.9183075428009033, "learning_rate": 8.042984692668198e-06, "loss": 0.2576, "step": 304970 }, { "epoch": 1.8128644542325731, "grad_norm": 5.313847541809082, "learning_rate": 8.042820049292032e-06, "loss": 0.303, "step": 304980 }, { "epoch": 1.8129238963092416, "grad_norm": 6.390481472015381, "learning_rate": 8.04265540067577e-06, "loss": 0.3201, "step": 304990 }, { "epoch": 1.81298333838591, "grad_norm": 6.009959697723389, "learning_rate": 8.04249074681969e-06, "loss": 0.3089, "step": 305000 }, { "epoch": 1.8130427804625784, "grad_norm": 5.1585693359375, "learning_rate": 8.042326087724079e-06, "loss": 0.3481, "step": 305010 }, { "epoch": 1.8131022225392466, "grad_norm": 4.683354377746582, "learning_rate": 8.04216142338922e-06, "loss": 0.3106, "step": 305020 }, { "epoch": 1.813161664615915, "grad_norm": 4.716577529907227, "learning_rate": 8.041996753815394e-06, "loss": 0.2735, "step": 305030 }, { "epoch": 1.8132211066925834, "grad_norm": 5.978458404541016, "learning_rate": 8.041832079002887e-06, "loss": 0.3103, "step": 305040 }, { "epoch": 1.8132805487692518, "grad_norm": 5.148746013641357, "learning_rate": 8.041667398951982e-06, "loss": 0.3202, "step": 305050 }, { "epoch": 1.8133399908459202, "grad_norm": 5.2346367835998535, "learning_rate": 8.041502713662966e-06, "loss": 0.33, "step": 305060 }, { "epoch": 1.8133994329225884, "grad_norm": 4.982419967651367, "learning_rate": 8.041338023136116e-06, "loss": 0.3403, "step": 305070 }, { "epoch": 1.8134588749992568, "grad_norm": 5.447973728179932, "learning_rate": 8.04117332737172e-06, "loss": 0.3181, "step": 305080 }, { "epoch": 1.8135183170759253, "grad_norm": 3.948373556137085, "learning_rate": 8.04100862637006e-06, "loss": 0.3251, "step": 305090 }, { "epoch": 1.8135777591525937, "grad_norm": 5.075109004974365, "learning_rate": 8.040843920131422e-06, "loss": 0.2964, "step": 305100 }, { "epoch": 1.813637201229262, "grad_norm": 5.052278518676758, "learning_rate": 8.040679208656085e-06, "loss": 0.294, "step": 305110 }, { "epoch": 1.8136966433059305, "grad_norm": 4.889138698577881, "learning_rate": 8.040514491944339e-06, "loss": 0.297, "step": 305120 }, { "epoch": 1.813756085382599, "grad_norm": 5.9503889083862305, "learning_rate": 8.040349769996463e-06, "loss": 0.3172, "step": 305130 }, { "epoch": 1.8138155274592673, "grad_norm": 3.563702344894409, "learning_rate": 8.040185042812742e-06, "loss": 0.3285, "step": 305140 }, { "epoch": 1.8138749695359357, "grad_norm": 6.519863605499268, "learning_rate": 8.040020310393459e-06, "loss": 0.3292, "step": 305150 }, { "epoch": 1.8139344116126042, "grad_norm": 5.397994041442871, "learning_rate": 8.039855572738899e-06, "loss": 0.3199, "step": 305160 }, { "epoch": 1.8139938536892726, "grad_norm": 4.180883407592773, "learning_rate": 8.039690829849345e-06, "loss": 0.3125, "step": 305170 }, { "epoch": 1.814053295765941, "grad_norm": 6.079697132110596, "learning_rate": 8.03952608172508e-06, "loss": 0.2788, "step": 305180 }, { "epoch": 1.8141127378426094, "grad_norm": 4.435947418212891, "learning_rate": 8.039361328366389e-06, "loss": 0.2834, "step": 305190 }, { "epoch": 1.8141721799192778, "grad_norm": 4.7636637687683105, "learning_rate": 8.039196569773553e-06, "loss": 0.2789, "step": 305200 }, { "epoch": 1.814231621995946, "grad_norm": 3.911073684692383, "learning_rate": 8.03903180594686e-06, "loss": 0.2872, "step": 305210 }, { "epoch": 1.8142910640726144, "grad_norm": 4.014829158782959, "learning_rate": 8.038867036886592e-06, "loss": 0.3029, "step": 305220 }, { "epoch": 1.8143505061492828, "grad_norm": 6.24130392074585, "learning_rate": 8.038702262593033e-06, "loss": 0.3228, "step": 305230 }, { "epoch": 1.8144099482259513, "grad_norm": 5.76024866104126, "learning_rate": 8.038537483066465e-06, "loss": 0.296, "step": 305240 }, { "epoch": 1.8144693903026197, "grad_norm": 4.781097412109375, "learning_rate": 8.038372698307171e-06, "loss": 0.2978, "step": 305250 }, { "epoch": 1.8145288323792879, "grad_norm": 4.865145206451416, "learning_rate": 8.03820790831544e-06, "loss": 0.3048, "step": 305260 }, { "epoch": 1.8145882744559563, "grad_norm": 5.09881067276001, "learning_rate": 8.03804311309155e-06, "loss": 0.3073, "step": 305270 }, { "epoch": 1.8146477165326247, "grad_norm": 3.2552030086517334, "learning_rate": 8.037878312635788e-06, "loss": 0.2729, "step": 305280 }, { "epoch": 1.814707158609293, "grad_norm": 5.459192752838135, "learning_rate": 8.03771350694844e-06, "loss": 0.315, "step": 305290 }, { "epoch": 1.8147666006859615, "grad_norm": 5.943406581878662, "learning_rate": 8.037548696029782e-06, "loss": 0.3315, "step": 305300 }, { "epoch": 1.81482604276263, "grad_norm": 5.553215503692627, "learning_rate": 8.037383879880104e-06, "loss": 0.2884, "step": 305310 }, { "epoch": 1.8148854848392983, "grad_norm": 5.070873737335205, "learning_rate": 8.03721905849969e-06, "loss": 0.3316, "step": 305320 }, { "epoch": 1.8149449269159668, "grad_norm": 5.272828102111816, "learning_rate": 8.03705423188882e-06, "loss": 0.3037, "step": 305330 }, { "epoch": 1.8150043689926352, "grad_norm": 5.833069324493408, "learning_rate": 8.036889400047785e-06, "loss": 0.273, "step": 305340 }, { "epoch": 1.8150638110693036, "grad_norm": 5.511466026306152, "learning_rate": 8.036724562976862e-06, "loss": 0.3181, "step": 305350 }, { "epoch": 1.815123253145972, "grad_norm": 5.300607204437256, "learning_rate": 8.036559720676334e-06, "loss": 0.2902, "step": 305360 }, { "epoch": 1.8151826952226404, "grad_norm": 5.2360148429870605, "learning_rate": 8.036394873146492e-06, "loss": 0.3308, "step": 305370 }, { "epoch": 1.8152421372993088, "grad_norm": 6.3991594314575195, "learning_rate": 8.036230020387612e-06, "loss": 0.2883, "step": 305380 }, { "epoch": 1.815301579375977, "grad_norm": 3.8426992893218994, "learning_rate": 8.036065162399984e-06, "loss": 0.3163, "step": 305390 }, { "epoch": 1.8153610214526454, "grad_norm": 5.880034446716309, "learning_rate": 8.035900299183889e-06, "loss": 0.2831, "step": 305400 }, { "epoch": 1.8154204635293139, "grad_norm": 5.100948810577393, "learning_rate": 8.03573543073961e-06, "loss": 0.2935, "step": 305410 }, { "epoch": 1.8154799056059823, "grad_norm": 6.856667995452881, "learning_rate": 8.035570557067434e-06, "loss": 0.3191, "step": 305420 }, { "epoch": 1.8155393476826507, "grad_norm": 5.370760440826416, "learning_rate": 8.035405678167642e-06, "loss": 0.2728, "step": 305430 }, { "epoch": 1.8155987897593189, "grad_norm": 4.076419353485107, "learning_rate": 8.035240794040521e-06, "loss": 0.2627, "step": 305440 }, { "epoch": 1.8156582318359873, "grad_norm": 4.973215579986572, "learning_rate": 8.035075904686354e-06, "loss": 0.33, "step": 305450 }, { "epoch": 1.8157176739126557, "grad_norm": 5.216640472412109, "learning_rate": 8.034911010105422e-06, "loss": 0.3198, "step": 305460 }, { "epoch": 1.8157771159893241, "grad_norm": 4.650338172912598, "learning_rate": 8.03474611029801e-06, "loss": 0.2872, "step": 305470 }, { "epoch": 1.8158365580659925, "grad_norm": 6.903105735778809, "learning_rate": 8.034581205264407e-06, "loss": 0.3247, "step": 305480 }, { "epoch": 1.815896000142661, "grad_norm": 4.705583095550537, "learning_rate": 8.03441629500489e-06, "loss": 0.3259, "step": 305490 }, { "epoch": 1.8159554422193294, "grad_norm": 4.48635196685791, "learning_rate": 8.034251379519747e-06, "loss": 0.2841, "step": 305500 }, { "epoch": 1.8160148842959978, "grad_norm": 4.645793914794922, "learning_rate": 8.03408645880926e-06, "loss": 0.2988, "step": 305510 }, { "epoch": 1.8160743263726662, "grad_norm": 5.081573486328125, "learning_rate": 8.033921532873716e-06, "loss": 0.2905, "step": 305520 }, { "epoch": 1.8161337684493346, "grad_norm": 4.820476531982422, "learning_rate": 8.033756601713395e-06, "loss": 0.2824, "step": 305530 }, { "epoch": 1.816193210526003, "grad_norm": 4.4222869873046875, "learning_rate": 8.033591665328585e-06, "loss": 0.3173, "step": 305540 }, { "epoch": 1.8162526526026714, "grad_norm": 4.091017723083496, "learning_rate": 8.033426723719568e-06, "loss": 0.3158, "step": 305550 }, { "epoch": 1.8163120946793399, "grad_norm": 6.356993198394775, "learning_rate": 8.033261776886627e-06, "loss": 0.293, "step": 305560 }, { "epoch": 1.8163715367560083, "grad_norm": 5.2067036628723145, "learning_rate": 8.033096824830049e-06, "loss": 0.3322, "step": 305570 }, { "epoch": 1.8164309788326765, "grad_norm": 4.559185981750488, "learning_rate": 8.032931867550115e-06, "loss": 0.295, "step": 305580 }, { "epoch": 1.8164904209093449, "grad_norm": 4.55674934387207, "learning_rate": 8.032766905047112e-06, "loss": 0.2951, "step": 305590 }, { "epoch": 1.8165498629860133, "grad_norm": 4.318853378295898, "learning_rate": 8.03260193732132e-06, "loss": 0.3055, "step": 305600 }, { "epoch": 1.8166093050626817, "grad_norm": 5.525547027587891, "learning_rate": 8.032436964373028e-06, "loss": 0.3082, "step": 305610 }, { "epoch": 1.8166687471393501, "grad_norm": 4.778092384338379, "learning_rate": 8.032271986202517e-06, "loss": 0.3009, "step": 305620 }, { "epoch": 1.8167281892160183, "grad_norm": 5.45762825012207, "learning_rate": 8.032107002810072e-06, "loss": 0.3538, "step": 305630 }, { "epoch": 1.8167876312926867, "grad_norm": 5.9665327072143555, "learning_rate": 8.031942014195976e-06, "loss": 0.3012, "step": 305640 }, { "epoch": 1.8168470733693551, "grad_norm": 5.280556678771973, "learning_rate": 8.031777020360514e-06, "loss": 0.3101, "step": 305650 }, { "epoch": 1.8169065154460236, "grad_norm": 3.6796340942382812, "learning_rate": 8.031612021303972e-06, "loss": 0.2946, "step": 305660 }, { "epoch": 1.816965957522692, "grad_norm": 3.7904200553894043, "learning_rate": 8.03144701702663e-06, "loss": 0.3247, "step": 305670 }, { "epoch": 1.8170253995993604, "grad_norm": 5.289262294769287, "learning_rate": 8.031282007528777e-06, "loss": 0.2696, "step": 305680 }, { "epoch": 1.8170848416760288, "grad_norm": 3.5506057739257812, "learning_rate": 8.031116992810694e-06, "loss": 0.3186, "step": 305690 }, { "epoch": 1.8171442837526972, "grad_norm": 5.764815330505371, "learning_rate": 8.030951972872666e-06, "loss": 0.309, "step": 305700 }, { "epoch": 1.8172037258293656, "grad_norm": 6.04996395111084, "learning_rate": 8.030786947714974e-06, "loss": 0.3111, "step": 305710 }, { "epoch": 1.817263167906034, "grad_norm": 4.997292995452881, "learning_rate": 8.030621917337908e-06, "loss": 0.2962, "step": 305720 }, { "epoch": 1.8173226099827025, "grad_norm": 6.808730125427246, "learning_rate": 8.03045688174175e-06, "loss": 0.2713, "step": 305730 }, { "epoch": 1.8173820520593709, "grad_norm": 5.516139507293701, "learning_rate": 8.030291840926782e-06, "loss": 0.3016, "step": 305740 }, { "epoch": 1.8174414941360393, "grad_norm": 4.939793586730957, "learning_rate": 8.030126794893291e-06, "loss": 0.3007, "step": 305750 }, { "epoch": 1.8175009362127075, "grad_norm": 3.456996202468872, "learning_rate": 8.02996174364156e-06, "loss": 0.3057, "step": 305760 }, { "epoch": 1.8175603782893759, "grad_norm": 5.041366100311279, "learning_rate": 8.029796687171873e-06, "loss": 0.3388, "step": 305770 }, { "epoch": 1.8176198203660443, "grad_norm": 5.5974812507629395, "learning_rate": 8.029631625484516e-06, "loss": 0.2995, "step": 305780 }, { "epoch": 1.8176792624427127, "grad_norm": 5.54890251159668, "learning_rate": 8.02946655857977e-06, "loss": 0.3148, "step": 305790 }, { "epoch": 1.8177387045193811, "grad_norm": 4.208761692047119, "learning_rate": 8.02930148645792e-06, "loss": 0.2813, "step": 305800 }, { "epoch": 1.8177981465960493, "grad_norm": 4.609651565551758, "learning_rate": 8.029136409119254e-06, "loss": 0.2881, "step": 305810 }, { "epoch": 1.8178575886727177, "grad_norm": 4.7356038093566895, "learning_rate": 8.028971326564054e-06, "loss": 0.3082, "step": 305820 }, { "epoch": 1.8179170307493862, "grad_norm": 4.296696662902832, "learning_rate": 8.028806238792601e-06, "loss": 0.2802, "step": 305830 }, { "epoch": 1.8179764728260546, "grad_norm": 4.4798264503479, "learning_rate": 8.028641145805185e-06, "loss": 0.2729, "step": 305840 }, { "epoch": 1.818035914902723, "grad_norm": 3.906890392303467, "learning_rate": 8.028476047602087e-06, "loss": 0.2911, "step": 305850 }, { "epoch": 1.8180953569793914, "grad_norm": 4.616490364074707, "learning_rate": 8.02831094418359e-06, "loss": 0.2938, "step": 305860 }, { "epoch": 1.8181547990560598, "grad_norm": 4.961673259735107, "learning_rate": 8.028145835549983e-06, "loss": 0.2976, "step": 305870 }, { "epoch": 1.8182142411327282, "grad_norm": 4.1606669425964355, "learning_rate": 8.027980721701546e-06, "loss": 0.3309, "step": 305880 }, { "epoch": 1.8182736832093966, "grad_norm": 3.8546676635742188, "learning_rate": 8.027815602638564e-06, "loss": 0.3017, "step": 305890 }, { "epoch": 1.818333125286065, "grad_norm": 4.782425403594971, "learning_rate": 8.027650478361324e-06, "loss": 0.3307, "step": 305900 }, { "epoch": 1.8183925673627335, "grad_norm": 4.6945672035217285, "learning_rate": 8.027485348870109e-06, "loss": 0.299, "step": 305910 }, { "epoch": 1.8184520094394019, "grad_norm": 4.521756649017334, "learning_rate": 8.027320214165201e-06, "loss": 0.2958, "step": 305920 }, { "epoch": 1.8185114515160703, "grad_norm": 4.483266353607178, "learning_rate": 8.027155074246888e-06, "loss": 0.2821, "step": 305930 }, { "epoch": 1.8185708935927387, "grad_norm": 5.557767391204834, "learning_rate": 8.026989929115452e-06, "loss": 0.3518, "step": 305940 }, { "epoch": 1.818630335669407, "grad_norm": 4.953090190887451, "learning_rate": 8.026824778771178e-06, "loss": 0.3156, "step": 305950 }, { "epoch": 1.8186897777460753, "grad_norm": 3.757168769836426, "learning_rate": 8.02665962321435e-06, "loss": 0.2848, "step": 305960 }, { "epoch": 1.8187492198227437, "grad_norm": 4.405065536499023, "learning_rate": 8.026494462445256e-06, "loss": 0.3057, "step": 305970 }, { "epoch": 1.8188086618994121, "grad_norm": 5.932797908782959, "learning_rate": 8.026329296464175e-06, "loss": 0.2975, "step": 305980 }, { "epoch": 1.8188681039760806, "grad_norm": 4.741601467132568, "learning_rate": 8.026164125271393e-06, "loss": 0.3373, "step": 305990 }, { "epoch": 1.8189275460527488, "grad_norm": 4.638638973236084, "learning_rate": 8.025998948867197e-06, "loss": 0.3071, "step": 306000 }, { "epoch": 1.8189869881294172, "grad_norm": 5.2396240234375, "learning_rate": 8.02583376725187e-06, "loss": 0.2646, "step": 306010 }, { "epoch": 1.8190464302060856, "grad_norm": 4.271303176879883, "learning_rate": 8.025668580425694e-06, "loss": 0.3415, "step": 306020 }, { "epoch": 1.819105872282754, "grad_norm": 4.84772253036499, "learning_rate": 8.025503388388958e-06, "loss": 0.3135, "step": 306030 }, { "epoch": 1.8191653143594224, "grad_norm": 6.73800802230835, "learning_rate": 8.025338191141943e-06, "loss": 0.3038, "step": 306040 }, { "epoch": 1.8192247564360908, "grad_norm": 4.691524028778076, "learning_rate": 8.025172988684934e-06, "loss": 0.3124, "step": 306050 }, { "epoch": 1.8192841985127592, "grad_norm": 5.5469279289245605, "learning_rate": 8.02500778101822e-06, "loss": 0.3293, "step": 306060 }, { "epoch": 1.8193436405894277, "grad_norm": 6.319897651672363, "learning_rate": 8.024842568142077e-06, "loss": 0.2916, "step": 306070 }, { "epoch": 1.819403082666096, "grad_norm": 5.016711235046387, "learning_rate": 8.024677350056796e-06, "loss": 0.295, "step": 306080 }, { "epoch": 1.8194625247427645, "grad_norm": 4.700216293334961, "learning_rate": 8.02451212676266e-06, "loss": 0.2815, "step": 306090 }, { "epoch": 1.819521966819433, "grad_norm": 7.136996269226074, "learning_rate": 8.024346898259953e-06, "loss": 0.3111, "step": 306100 }, { "epoch": 1.8195814088961013, "grad_norm": 4.302976608276367, "learning_rate": 8.024181664548958e-06, "loss": 0.3227, "step": 306110 }, { "epoch": 1.8196408509727697, "grad_norm": 4.696370601654053, "learning_rate": 8.024016425629965e-06, "loss": 0.2636, "step": 306120 }, { "epoch": 1.819700293049438, "grad_norm": 5.683739185333252, "learning_rate": 8.023851181503252e-06, "loss": 0.3358, "step": 306130 }, { "epoch": 1.8197597351261063, "grad_norm": 4.094555854797363, "learning_rate": 8.023685932169108e-06, "loss": 0.3155, "step": 306140 }, { "epoch": 1.8198191772027748, "grad_norm": 4.6329522132873535, "learning_rate": 8.023520677627815e-06, "loss": 0.3109, "step": 306150 }, { "epoch": 1.8198786192794432, "grad_norm": 4.836201190948486, "learning_rate": 8.02335541787966e-06, "loss": 0.2957, "step": 306160 }, { "epoch": 1.8199380613561116, "grad_norm": 5.025261878967285, "learning_rate": 8.023190152924925e-06, "loss": 0.3105, "step": 306170 }, { "epoch": 1.8199975034327798, "grad_norm": 5.359732627868652, "learning_rate": 8.023024882763897e-06, "loss": 0.3283, "step": 306180 }, { "epoch": 1.8200569455094482, "grad_norm": 5.127810001373291, "learning_rate": 8.022859607396857e-06, "loss": 0.3257, "step": 306190 }, { "epoch": 1.8201163875861166, "grad_norm": 5.600924015045166, "learning_rate": 8.022694326824094e-06, "loss": 0.3126, "step": 306200 }, { "epoch": 1.820175829662785, "grad_norm": 4.841278553009033, "learning_rate": 8.02252904104589e-06, "loss": 0.3189, "step": 306210 }, { "epoch": 1.8202352717394534, "grad_norm": 5.60923433303833, "learning_rate": 8.02236375006253e-06, "loss": 0.278, "step": 306220 }, { "epoch": 1.8202947138161218, "grad_norm": 3.783026695251465, "learning_rate": 8.022198453874301e-06, "loss": 0.2652, "step": 306230 }, { "epoch": 1.8203541558927903, "grad_norm": 5.850775718688965, "learning_rate": 8.022033152481483e-06, "loss": 0.3083, "step": 306240 }, { "epoch": 1.8204135979694587, "grad_norm": 5.027101993560791, "learning_rate": 8.021867845884365e-06, "loss": 0.2854, "step": 306250 }, { "epoch": 1.820473040046127, "grad_norm": 4.722412109375, "learning_rate": 8.021702534083232e-06, "loss": 0.3066, "step": 306260 }, { "epoch": 1.8205324821227955, "grad_norm": 3.9650750160217285, "learning_rate": 8.021537217078363e-06, "loss": 0.3031, "step": 306270 }, { "epoch": 1.820591924199464, "grad_norm": 4.419745445251465, "learning_rate": 8.021371894870048e-06, "loss": 0.3198, "step": 306280 }, { "epoch": 1.8206513662761323, "grad_norm": 5.755776405334473, "learning_rate": 8.021206567458571e-06, "loss": 0.3164, "step": 306290 }, { "epoch": 1.8207108083528007, "grad_norm": 3.987118721008301, "learning_rate": 8.021041234844213e-06, "loss": 0.3179, "step": 306300 }, { "epoch": 1.8207702504294692, "grad_norm": 5.115954875946045, "learning_rate": 8.020875897027262e-06, "loss": 0.3013, "step": 306310 }, { "epoch": 1.8208296925061374, "grad_norm": 4.136528015136719, "learning_rate": 8.020710554008005e-06, "loss": 0.2932, "step": 306320 }, { "epoch": 1.8208891345828058, "grad_norm": 5.578531742095947, "learning_rate": 8.020545205786723e-06, "loss": 0.3005, "step": 306330 }, { "epoch": 1.8209485766594742, "grad_norm": 4.890182018280029, "learning_rate": 8.0203798523637e-06, "loss": 0.3019, "step": 306340 }, { "epoch": 1.8210080187361426, "grad_norm": 5.295727252960205, "learning_rate": 8.020214493739225e-06, "loss": 0.3017, "step": 306350 }, { "epoch": 1.8210674608128108, "grad_norm": 4.564632415771484, "learning_rate": 8.020049129913578e-06, "loss": 0.2763, "step": 306360 }, { "epoch": 1.8211269028894792, "grad_norm": 5.581653594970703, "learning_rate": 8.019883760887046e-06, "loss": 0.2921, "step": 306370 }, { "epoch": 1.8211863449661476, "grad_norm": 6.003929138183594, "learning_rate": 8.019718386659917e-06, "loss": 0.3189, "step": 306380 }, { "epoch": 1.821245787042816, "grad_norm": 5.233071804046631, "learning_rate": 8.01955300723247e-06, "loss": 0.2976, "step": 306390 }, { "epoch": 1.8213052291194844, "grad_norm": 4.609664440155029, "learning_rate": 8.019387622604992e-06, "loss": 0.2856, "step": 306400 }, { "epoch": 1.8213646711961529, "grad_norm": 3.814021348953247, "learning_rate": 8.019222232777769e-06, "loss": 0.3213, "step": 306410 }, { "epoch": 1.8214241132728213, "grad_norm": 4.4861016273498535, "learning_rate": 8.019056837751086e-06, "loss": 0.3142, "step": 306420 }, { "epoch": 1.8214835553494897, "grad_norm": 4.6739301681518555, "learning_rate": 8.018891437525225e-06, "loss": 0.316, "step": 306430 }, { "epoch": 1.821542997426158, "grad_norm": 3.9426820278167725, "learning_rate": 8.018726032100475e-06, "loss": 0.288, "step": 306440 }, { "epoch": 1.8216024395028265, "grad_norm": 5.08428955078125, "learning_rate": 8.018560621477117e-06, "loss": 0.266, "step": 306450 }, { "epoch": 1.821661881579495, "grad_norm": 3.912348747253418, "learning_rate": 8.018395205655438e-06, "loss": 0.3026, "step": 306460 }, { "epoch": 1.8217213236561633, "grad_norm": 4.185243606567383, "learning_rate": 8.018229784635723e-06, "loss": 0.3201, "step": 306470 }, { "epoch": 1.8217807657328318, "grad_norm": 6.225895404815674, "learning_rate": 8.018064358418255e-06, "loss": 0.2847, "step": 306480 }, { "epoch": 1.8218402078095002, "grad_norm": 4.495994567871094, "learning_rate": 8.01789892700332e-06, "loss": 0.2717, "step": 306490 }, { "epoch": 1.8218996498861684, "grad_norm": 4.844232559204102, "learning_rate": 8.017733490391203e-06, "loss": 0.2871, "step": 306500 }, { "epoch": 1.8219590919628368, "grad_norm": 5.262228488922119, "learning_rate": 8.01756804858219e-06, "loss": 0.2984, "step": 306510 }, { "epoch": 1.8220185340395052, "grad_norm": 4.093235492706299, "learning_rate": 8.017402601576564e-06, "loss": 0.3184, "step": 306520 }, { "epoch": 1.8220779761161736, "grad_norm": 4.96173620223999, "learning_rate": 8.01723714937461e-06, "loss": 0.3026, "step": 306530 }, { "epoch": 1.822137418192842, "grad_norm": 5.338934421539307, "learning_rate": 8.017071691976616e-06, "loss": 0.2804, "step": 306540 }, { "epoch": 1.8221968602695102, "grad_norm": 5.522741794586182, "learning_rate": 8.016906229382862e-06, "loss": 0.3176, "step": 306550 }, { "epoch": 1.8222563023461786, "grad_norm": 5.183952331542969, "learning_rate": 8.016740761593637e-06, "loss": 0.3055, "step": 306560 }, { "epoch": 1.822315744422847, "grad_norm": 6.137866020202637, "learning_rate": 8.016575288609225e-06, "loss": 0.343, "step": 306570 }, { "epoch": 1.8223751864995155, "grad_norm": 4.786505222320557, "learning_rate": 8.016409810429909e-06, "loss": 0.3171, "step": 306580 }, { "epoch": 1.8224346285761839, "grad_norm": 4.35136079788208, "learning_rate": 8.016244327055975e-06, "loss": 0.3504, "step": 306590 }, { "epoch": 1.8224940706528523, "grad_norm": 5.040823459625244, "learning_rate": 8.016078838487709e-06, "loss": 0.2903, "step": 306600 }, { "epoch": 1.8225535127295207, "grad_norm": 5.298229217529297, "learning_rate": 8.015913344725396e-06, "loss": 0.3044, "step": 306610 }, { "epoch": 1.8226129548061891, "grad_norm": 5.020260334014893, "learning_rate": 8.01574784576932e-06, "loss": 0.3126, "step": 306620 }, { "epoch": 1.8226723968828575, "grad_norm": 5.115943908691406, "learning_rate": 8.015582341619766e-06, "loss": 0.3055, "step": 306630 }, { "epoch": 1.822731838959526, "grad_norm": 4.730833053588867, "learning_rate": 8.015416832277018e-06, "loss": 0.2946, "step": 306640 }, { "epoch": 1.8227912810361944, "grad_norm": 3.913609027862549, "learning_rate": 8.015251317741364e-06, "loss": 0.3319, "step": 306650 }, { "epoch": 1.8228507231128628, "grad_norm": 5.115962982177734, "learning_rate": 8.015085798013088e-06, "loss": 0.3216, "step": 306660 }, { "epoch": 1.8229101651895312, "grad_norm": 4.288735866546631, "learning_rate": 8.014920273092475e-06, "loss": 0.2893, "step": 306670 }, { "epoch": 1.8229696072661996, "grad_norm": 4.6484551429748535, "learning_rate": 8.014754742979807e-06, "loss": 0.2795, "step": 306680 }, { "epoch": 1.8230290493428678, "grad_norm": 6.387756824493408, "learning_rate": 8.014589207675375e-06, "loss": 0.3243, "step": 306690 }, { "epoch": 1.8230884914195362, "grad_norm": 7.646937370300293, "learning_rate": 8.014423667179459e-06, "loss": 0.307, "step": 306700 }, { "epoch": 1.8231479334962046, "grad_norm": 5.488826274871826, "learning_rate": 8.014258121492344e-06, "loss": 0.3286, "step": 306710 }, { "epoch": 1.823207375572873, "grad_norm": 6.6824188232421875, "learning_rate": 8.014092570614319e-06, "loss": 0.3173, "step": 306720 }, { "epoch": 1.8232668176495412, "grad_norm": 4.873350143432617, "learning_rate": 8.013927014545667e-06, "loss": 0.2972, "step": 306730 }, { "epoch": 1.8233262597262097, "grad_norm": 4.907548427581787, "learning_rate": 8.01376145328667e-06, "loss": 0.3266, "step": 306740 }, { "epoch": 1.823385701802878, "grad_norm": 4.649930000305176, "learning_rate": 8.01359588683762e-06, "loss": 0.3181, "step": 306750 }, { "epoch": 1.8234451438795465, "grad_norm": 5.408599376678467, "learning_rate": 8.013430315198797e-06, "loss": 0.2946, "step": 306760 }, { "epoch": 1.823504585956215, "grad_norm": 4.380927562713623, "learning_rate": 8.013264738370487e-06, "loss": 0.277, "step": 306770 }, { "epoch": 1.8235640280328833, "grad_norm": 5.318145751953125, "learning_rate": 8.013099156352977e-06, "loss": 0.2626, "step": 306780 }, { "epoch": 1.8236234701095517, "grad_norm": 5.361331462860107, "learning_rate": 8.01293356914655e-06, "loss": 0.3118, "step": 306790 }, { "epoch": 1.8236829121862201, "grad_norm": 4.325868129730225, "learning_rate": 8.012767976751491e-06, "loss": 0.2676, "step": 306800 }, { "epoch": 1.8237423542628886, "grad_norm": 4.2736406326293945, "learning_rate": 8.012602379168086e-06, "loss": 0.3087, "step": 306810 }, { "epoch": 1.823801796339557, "grad_norm": 5.9040679931640625, "learning_rate": 8.012436776396622e-06, "loss": 0.3022, "step": 306820 }, { "epoch": 1.8238612384162254, "grad_norm": 4.230907440185547, "learning_rate": 8.012271168437382e-06, "loss": 0.3091, "step": 306830 }, { "epoch": 1.8239206804928938, "grad_norm": 6.162624835968018, "learning_rate": 8.01210555529065e-06, "loss": 0.3148, "step": 306840 }, { "epoch": 1.8239801225695622, "grad_norm": 5.314797878265381, "learning_rate": 8.011939936956715e-06, "loss": 0.3051, "step": 306850 }, { "epoch": 1.8240395646462306, "grad_norm": 5.591552734375, "learning_rate": 8.011774313435859e-06, "loss": 0.3186, "step": 306860 }, { "epoch": 1.8240990067228988, "grad_norm": 5.022501468658447, "learning_rate": 8.011608684728366e-06, "loss": 0.3057, "step": 306870 }, { "epoch": 1.8241584487995672, "grad_norm": 7.067322731018066, "learning_rate": 8.011443050834527e-06, "loss": 0.3345, "step": 306880 }, { "epoch": 1.8242178908762356, "grad_norm": 4.645047187805176, "learning_rate": 8.011277411754623e-06, "loss": 0.285, "step": 306890 }, { "epoch": 1.824277332952904, "grad_norm": 4.250046730041504, "learning_rate": 8.011111767488939e-06, "loss": 0.2588, "step": 306900 }, { "epoch": 1.8243367750295725, "grad_norm": 5.9356842041015625, "learning_rate": 8.010946118037762e-06, "loss": 0.3148, "step": 306910 }, { "epoch": 1.8243962171062407, "grad_norm": 4.648085117340088, "learning_rate": 8.010780463401375e-06, "loss": 0.2924, "step": 306920 }, { "epoch": 1.824455659182909, "grad_norm": 5.752875804901123, "learning_rate": 8.010614803580066e-06, "loss": 0.3287, "step": 306930 }, { "epoch": 1.8245151012595775, "grad_norm": 5.011463165283203, "learning_rate": 8.010449138574119e-06, "loss": 0.2814, "step": 306940 }, { "epoch": 1.824574543336246, "grad_norm": 7.065505027770996, "learning_rate": 8.01028346838382e-06, "loss": 0.2948, "step": 306950 }, { "epoch": 1.8246339854129143, "grad_norm": 4.788095474243164, "learning_rate": 8.010117793009453e-06, "loss": 0.3091, "step": 306960 }, { "epoch": 1.8246934274895827, "grad_norm": 5.816641807556152, "learning_rate": 8.009952112451303e-06, "loss": 0.3174, "step": 306970 }, { "epoch": 1.8247528695662512, "grad_norm": 5.263435363769531, "learning_rate": 8.009786426709658e-06, "loss": 0.2563, "step": 306980 }, { "epoch": 1.8248123116429196, "grad_norm": 4.6460418701171875, "learning_rate": 8.009620735784802e-06, "loss": 0.3103, "step": 306990 }, { "epoch": 1.824871753719588, "grad_norm": 4.598062038421631, "learning_rate": 8.00945503967702e-06, "loss": 0.3029, "step": 307000 }, { "epoch": 1.8249311957962564, "grad_norm": 5.427774429321289, "learning_rate": 8.009289338386596e-06, "loss": 0.2972, "step": 307010 }, { "epoch": 1.8249906378729248, "grad_norm": 5.776743412017822, "learning_rate": 8.009123631913816e-06, "loss": 0.3122, "step": 307020 }, { "epoch": 1.8250500799495932, "grad_norm": 6.422582149505615, "learning_rate": 8.008957920258969e-06, "loss": 0.2823, "step": 307030 }, { "epoch": 1.8251095220262616, "grad_norm": 4.724719047546387, "learning_rate": 8.008792203422335e-06, "loss": 0.3479, "step": 307040 }, { "epoch": 1.82516896410293, "grad_norm": 6.378262042999268, "learning_rate": 8.008626481404202e-06, "loss": 0.3444, "step": 307050 }, { "epoch": 1.8252284061795983, "grad_norm": 4.333763599395752, "learning_rate": 8.008460754204855e-06, "loss": 0.3214, "step": 307060 }, { "epoch": 1.8252878482562667, "grad_norm": 5.601504802703857, "learning_rate": 8.00829502182458e-06, "loss": 0.3163, "step": 307070 }, { "epoch": 1.825347290332935, "grad_norm": 3.9615225791931152, "learning_rate": 8.008129284263664e-06, "loss": 0.3148, "step": 307080 }, { "epoch": 1.8254067324096035, "grad_norm": 5.18759298324585, "learning_rate": 8.007963541522387e-06, "loss": 0.2723, "step": 307090 }, { "epoch": 1.8254661744862717, "grad_norm": 4.523584842681885, "learning_rate": 8.00779779360104e-06, "loss": 0.2904, "step": 307100 }, { "epoch": 1.82552561656294, "grad_norm": 5.522993087768555, "learning_rate": 8.007632040499907e-06, "loss": 0.2769, "step": 307110 }, { "epoch": 1.8255850586396085, "grad_norm": 4.784794330596924, "learning_rate": 8.007466282219272e-06, "loss": 0.2921, "step": 307120 }, { "epoch": 1.825644500716277, "grad_norm": 6.968696117401123, "learning_rate": 8.00730051875942e-06, "loss": 0.3305, "step": 307130 }, { "epoch": 1.8257039427929453, "grad_norm": 6.055722713470459, "learning_rate": 8.00713475012064e-06, "loss": 0.2789, "step": 307140 }, { "epoch": 1.8257633848696138, "grad_norm": 4.288222789764404, "learning_rate": 8.006968976303213e-06, "loss": 0.2708, "step": 307150 }, { "epoch": 1.8258228269462822, "grad_norm": 4.842806816101074, "learning_rate": 8.006803197307427e-06, "loss": 0.2956, "step": 307160 }, { "epoch": 1.8258822690229506, "grad_norm": 6.48555326461792, "learning_rate": 8.006637413133568e-06, "loss": 0.351, "step": 307170 }, { "epoch": 1.825941711099619, "grad_norm": 5.653327465057373, "learning_rate": 8.00647162378192e-06, "loss": 0.2655, "step": 307180 }, { "epoch": 1.8260011531762874, "grad_norm": 4.718059062957764, "learning_rate": 8.006305829252769e-06, "loss": 0.2996, "step": 307190 }, { "epoch": 1.8260605952529558, "grad_norm": 5.850746154785156, "learning_rate": 8.0061400295464e-06, "loss": 0.2965, "step": 307200 }, { "epoch": 1.8261200373296242, "grad_norm": 4.843631267547607, "learning_rate": 8.0059742246631e-06, "loss": 0.3128, "step": 307210 }, { "epoch": 1.8261794794062927, "grad_norm": 5.036839008331299, "learning_rate": 8.005808414603155e-06, "loss": 0.3026, "step": 307220 }, { "epoch": 1.826238921482961, "grad_norm": 5.754422664642334, "learning_rate": 8.005642599366848e-06, "loss": 0.3137, "step": 307230 }, { "epoch": 1.8262983635596293, "grad_norm": 4.280267238616943, "learning_rate": 8.005476778954466e-06, "loss": 0.2736, "step": 307240 }, { "epoch": 1.8263578056362977, "grad_norm": 4.1300578117370605, "learning_rate": 8.005310953366294e-06, "loss": 0.3092, "step": 307250 }, { "epoch": 1.826417247712966, "grad_norm": 4.882002830505371, "learning_rate": 8.005145122602619e-06, "loss": 0.2781, "step": 307260 }, { "epoch": 1.8264766897896345, "grad_norm": 5.054145812988281, "learning_rate": 8.004979286663725e-06, "loss": 0.3023, "step": 307270 }, { "epoch": 1.826536131866303, "grad_norm": 4.923495769500732, "learning_rate": 8.004813445549897e-06, "loss": 0.2877, "step": 307280 }, { "epoch": 1.8265955739429711, "grad_norm": 4.443544864654541, "learning_rate": 8.004647599261424e-06, "loss": 0.2835, "step": 307290 }, { "epoch": 1.8266550160196395, "grad_norm": 5.311372756958008, "learning_rate": 8.004481747798586e-06, "loss": 0.3012, "step": 307300 }, { "epoch": 1.826714458096308, "grad_norm": 4.511360168457031, "learning_rate": 8.004315891161675e-06, "loss": 0.2922, "step": 307310 }, { "epoch": 1.8267739001729764, "grad_norm": 6.3442606925964355, "learning_rate": 8.004150029350973e-06, "loss": 0.3265, "step": 307320 }, { "epoch": 1.8268333422496448, "grad_norm": 8.161310195922852, "learning_rate": 8.003984162366764e-06, "loss": 0.2933, "step": 307330 }, { "epoch": 1.8268927843263132, "grad_norm": 4.507019519805908, "learning_rate": 8.003818290209338e-06, "loss": 0.2582, "step": 307340 }, { "epoch": 1.8269522264029816, "grad_norm": 4.143909931182861, "learning_rate": 8.00365241287898e-06, "loss": 0.3361, "step": 307350 }, { "epoch": 1.82701166847965, "grad_norm": 4.971213340759277, "learning_rate": 8.00348653037597e-06, "loss": 0.3082, "step": 307360 }, { "epoch": 1.8270711105563184, "grad_norm": 5.2009992599487305, "learning_rate": 8.0033206427006e-06, "loss": 0.285, "step": 307370 }, { "epoch": 1.8271305526329868, "grad_norm": 4.689193248748779, "learning_rate": 8.003154749853154e-06, "loss": 0.3087, "step": 307380 }, { "epoch": 1.8271899947096553, "grad_norm": 4.681985855102539, "learning_rate": 8.002988851833916e-06, "loss": 0.2937, "step": 307390 }, { "epoch": 1.8272494367863237, "grad_norm": 6.260456562042236, "learning_rate": 8.002822948643175e-06, "loss": 0.2944, "step": 307400 }, { "epoch": 1.827308878862992, "grad_norm": 6.075080394744873, "learning_rate": 8.002657040281212e-06, "loss": 0.307, "step": 307410 }, { "epoch": 1.8273683209396605, "grad_norm": 4.666005611419678, "learning_rate": 8.002491126748317e-06, "loss": 0.2804, "step": 307420 }, { "epoch": 1.8274277630163287, "grad_norm": 4.3259100914001465, "learning_rate": 8.002325208044775e-06, "loss": 0.2971, "step": 307430 }, { "epoch": 1.8274872050929971, "grad_norm": 3.8062446117401123, "learning_rate": 8.002159284170867e-06, "loss": 0.2934, "step": 307440 }, { "epoch": 1.8275466471696655, "grad_norm": 6.213301181793213, "learning_rate": 8.001993355126888e-06, "loss": 0.3332, "step": 307450 }, { "epoch": 1.827606089246334, "grad_norm": 4.484925746917725, "learning_rate": 8.001827420913114e-06, "loss": 0.2794, "step": 307460 }, { "epoch": 1.8276655313230021, "grad_norm": 5.084754943847656, "learning_rate": 8.001661481529835e-06, "loss": 0.2734, "step": 307470 }, { "epoch": 1.8277249733996705, "grad_norm": 4.358423709869385, "learning_rate": 8.001495536977339e-06, "loss": 0.317, "step": 307480 }, { "epoch": 1.827784415476339, "grad_norm": 4.280991554260254, "learning_rate": 8.001329587255908e-06, "loss": 0.3508, "step": 307490 }, { "epoch": 1.8278438575530074, "grad_norm": 4.492966651916504, "learning_rate": 8.00116363236583e-06, "loss": 0.2969, "step": 307500 }, { "epoch": 1.8279032996296758, "grad_norm": 4.209709644317627, "learning_rate": 8.00099767230739e-06, "loss": 0.2809, "step": 307510 }, { "epoch": 1.8279627417063442, "grad_norm": 4.208888530731201, "learning_rate": 8.000831707080871e-06, "loss": 0.3023, "step": 307520 }, { "epoch": 1.8280221837830126, "grad_norm": 4.5536723136901855, "learning_rate": 8.000665736686566e-06, "loss": 0.2936, "step": 307530 }, { "epoch": 1.828081625859681, "grad_norm": 5.668027400970459, "learning_rate": 8.000499761124755e-06, "loss": 0.3197, "step": 307540 }, { "epoch": 1.8281410679363495, "grad_norm": 5.219051361083984, "learning_rate": 8.000333780395726e-06, "loss": 0.3055, "step": 307550 }, { "epoch": 1.8282005100130179, "grad_norm": 6.405335426330566, "learning_rate": 8.000167794499762e-06, "loss": 0.3354, "step": 307560 }, { "epoch": 1.8282599520896863, "grad_norm": 6.413605213165283, "learning_rate": 8.000001803437153e-06, "loss": 0.3625, "step": 307570 }, { "epoch": 1.8283193941663547, "grad_norm": 4.931304454803467, "learning_rate": 7.999835807208184e-06, "loss": 0.2863, "step": 307580 }, { "epoch": 1.828378836243023, "grad_norm": 3.833925724029541, "learning_rate": 7.999669805813138e-06, "loss": 0.298, "step": 307590 }, { "epoch": 1.8284382783196915, "grad_norm": 4.3443827629089355, "learning_rate": 7.999503799252303e-06, "loss": 0.3215, "step": 307600 }, { "epoch": 1.8284977203963597, "grad_norm": 5.666493892669678, "learning_rate": 7.999337787525967e-06, "loss": 0.312, "step": 307610 }, { "epoch": 1.8285571624730281, "grad_norm": 4.490296840667725, "learning_rate": 7.99917177063441e-06, "loss": 0.321, "step": 307620 }, { "epoch": 1.8286166045496965, "grad_norm": 4.192611217498779, "learning_rate": 7.999005748577921e-06, "loss": 0.3103, "step": 307630 }, { "epoch": 1.828676046626365, "grad_norm": 6.785428524017334, "learning_rate": 7.998839721356789e-06, "loss": 0.3, "step": 307640 }, { "epoch": 1.8287354887030334, "grad_norm": 4.819526672363281, "learning_rate": 7.998673688971297e-06, "loss": 0.3266, "step": 307650 }, { "epoch": 1.8287949307797016, "grad_norm": 4.342597961425781, "learning_rate": 7.998507651421729e-06, "loss": 0.2894, "step": 307660 }, { "epoch": 1.82885437285637, "grad_norm": 4.097768306732178, "learning_rate": 7.998341608708374e-06, "loss": 0.2774, "step": 307670 }, { "epoch": 1.8289138149330384, "grad_norm": 4.188680648803711, "learning_rate": 7.998175560831518e-06, "loss": 0.3127, "step": 307680 }, { "epoch": 1.8289732570097068, "grad_norm": 4.823027610778809, "learning_rate": 7.998009507791444e-06, "loss": 0.2987, "step": 307690 }, { "epoch": 1.8290326990863752, "grad_norm": 5.576736927032471, "learning_rate": 7.997843449588442e-06, "loss": 0.3038, "step": 307700 }, { "epoch": 1.8290921411630436, "grad_norm": 4.241197109222412, "learning_rate": 7.997677386222796e-06, "loss": 0.2976, "step": 307710 }, { "epoch": 1.829151583239712, "grad_norm": 4.880699157714844, "learning_rate": 7.99751131769479e-06, "loss": 0.293, "step": 307720 }, { "epoch": 1.8292110253163805, "grad_norm": 5.513672351837158, "learning_rate": 7.997345244004714e-06, "loss": 0.3193, "step": 307730 }, { "epoch": 1.8292704673930489, "grad_norm": 5.633775234222412, "learning_rate": 7.997179165152849e-06, "loss": 0.2766, "step": 307740 }, { "epoch": 1.8293299094697173, "grad_norm": 4.723087787628174, "learning_rate": 7.997013081139484e-06, "loss": 0.3246, "step": 307750 }, { "epoch": 1.8293893515463857, "grad_norm": 3.944580554962158, "learning_rate": 7.996846991964908e-06, "loss": 0.2917, "step": 307760 }, { "epoch": 1.8294487936230541, "grad_norm": 4.0033674240112305, "learning_rate": 7.996680897629401e-06, "loss": 0.294, "step": 307770 }, { "epoch": 1.8295082356997225, "grad_norm": 6.02175760269165, "learning_rate": 7.996514798133253e-06, "loss": 0.3186, "step": 307780 }, { "epoch": 1.829567677776391, "grad_norm": 5.5116658210754395, "learning_rate": 7.99634869347675e-06, "loss": 0.301, "step": 307790 }, { "epoch": 1.8296271198530591, "grad_norm": 5.581877708435059, "learning_rate": 7.996182583660176e-06, "loss": 0.2802, "step": 307800 }, { "epoch": 1.8296865619297276, "grad_norm": 4.435884952545166, "learning_rate": 7.996016468683818e-06, "loss": 0.3256, "step": 307810 }, { "epoch": 1.829746004006396, "grad_norm": 5.352588176727295, "learning_rate": 7.995850348547962e-06, "loss": 0.3045, "step": 307820 }, { "epoch": 1.8298054460830644, "grad_norm": 3.8329503536224365, "learning_rate": 7.995684223252896e-06, "loss": 0.2782, "step": 307830 }, { "epoch": 1.8298648881597326, "grad_norm": 6.324325084686279, "learning_rate": 7.995518092798901e-06, "loss": 0.303, "step": 307840 }, { "epoch": 1.829924330236401, "grad_norm": 4.700623512268066, "learning_rate": 7.995351957186267e-06, "loss": 0.2938, "step": 307850 }, { "epoch": 1.8299837723130694, "grad_norm": 4.725390434265137, "learning_rate": 7.995185816415283e-06, "loss": 0.2824, "step": 307860 }, { "epoch": 1.8300432143897378, "grad_norm": 6.170550346374512, "learning_rate": 7.99501967048623e-06, "loss": 0.3461, "step": 307870 }, { "epoch": 1.8301026564664062, "grad_norm": 3.4929792881011963, "learning_rate": 7.994853519399395e-06, "loss": 0.3166, "step": 307880 }, { "epoch": 1.8301620985430747, "grad_norm": 4.375156879425049, "learning_rate": 7.994687363155065e-06, "loss": 0.2868, "step": 307890 }, { "epoch": 1.830221540619743, "grad_norm": 4.615800380706787, "learning_rate": 7.994521201753526e-06, "loss": 0.3155, "step": 307900 }, { "epoch": 1.8302809826964115, "grad_norm": 5.495224475860596, "learning_rate": 7.994355035195065e-06, "loss": 0.2938, "step": 307910 }, { "epoch": 1.83034042477308, "grad_norm": 4.567745208740234, "learning_rate": 7.994188863479967e-06, "loss": 0.2778, "step": 307920 }, { "epoch": 1.8303998668497483, "grad_norm": 4.848196506500244, "learning_rate": 7.994022686608517e-06, "loss": 0.2951, "step": 307930 }, { "epoch": 1.8304593089264167, "grad_norm": 4.886783599853516, "learning_rate": 7.993856504581004e-06, "loss": 0.2867, "step": 307940 }, { "epoch": 1.8305187510030851, "grad_norm": 5.743738174438477, "learning_rate": 7.993690317397713e-06, "loss": 0.2784, "step": 307950 }, { "epoch": 1.8305781930797536, "grad_norm": 4.27726411819458, "learning_rate": 7.993524125058929e-06, "loss": 0.2939, "step": 307960 }, { "epoch": 1.830637635156422, "grad_norm": 5.452815055847168, "learning_rate": 7.993357927564941e-06, "loss": 0.3044, "step": 307970 }, { "epoch": 1.8306970772330902, "grad_norm": 5.937709331512451, "learning_rate": 7.993191724916033e-06, "loss": 0.2932, "step": 307980 }, { "epoch": 1.8307565193097586, "grad_norm": 4.179781913757324, "learning_rate": 7.99302551711249e-06, "loss": 0.2692, "step": 307990 }, { "epoch": 1.830815961386427, "grad_norm": 4.714078903198242, "learning_rate": 7.992859304154604e-06, "loss": 0.2921, "step": 308000 }, { "epoch": 1.8308754034630954, "grad_norm": 4.387809753417969, "learning_rate": 7.992693086042653e-06, "loss": 0.3371, "step": 308010 }, { "epoch": 1.8309348455397638, "grad_norm": 4.847729682922363, "learning_rate": 7.99252686277693e-06, "loss": 0.2845, "step": 308020 }, { "epoch": 1.830994287616432, "grad_norm": 5.239004611968994, "learning_rate": 7.992360634357716e-06, "loss": 0.3059, "step": 308030 }, { "epoch": 1.8310537296931004, "grad_norm": 5.406315803527832, "learning_rate": 7.992194400785302e-06, "loss": 0.3039, "step": 308040 }, { "epoch": 1.8311131717697688, "grad_norm": 5.077014446258545, "learning_rate": 7.992028162059972e-06, "loss": 0.2893, "step": 308050 }, { "epoch": 1.8311726138464373, "grad_norm": 4.417444705963135, "learning_rate": 7.991861918182011e-06, "loss": 0.3173, "step": 308060 }, { "epoch": 1.8312320559231057, "grad_norm": 6.351469993591309, "learning_rate": 7.991695669151708e-06, "loss": 0.3015, "step": 308070 }, { "epoch": 1.831291497999774, "grad_norm": 4.74400520324707, "learning_rate": 7.99152941496935e-06, "loss": 0.2833, "step": 308080 }, { "epoch": 1.8313509400764425, "grad_norm": 7.292202472686768, "learning_rate": 7.99136315563522e-06, "loss": 0.3085, "step": 308090 }, { "epoch": 1.831410382153111, "grad_norm": 5.360403537750244, "learning_rate": 7.991196891149604e-06, "loss": 0.3291, "step": 308100 }, { "epoch": 1.8314698242297793, "grad_norm": 6.243887901306152, "learning_rate": 7.991030621512792e-06, "loss": 0.3229, "step": 308110 }, { "epoch": 1.8315292663064477, "grad_norm": 5.790831565856934, "learning_rate": 7.990864346725066e-06, "loss": 0.3082, "step": 308120 }, { "epoch": 1.8315887083831162, "grad_norm": 4.356307506561279, "learning_rate": 7.990698066786719e-06, "loss": 0.2931, "step": 308130 }, { "epoch": 1.8316481504597846, "grad_norm": 5.294848918914795, "learning_rate": 7.99053178169803e-06, "loss": 0.2961, "step": 308140 }, { "epoch": 1.831707592536453, "grad_norm": 4.976470947265625, "learning_rate": 7.990365491459288e-06, "loss": 0.2899, "step": 308150 }, { "epoch": 1.8317670346131214, "grad_norm": 6.067536354064941, "learning_rate": 7.99019919607078e-06, "loss": 0.3017, "step": 308160 }, { "epoch": 1.8318264766897896, "grad_norm": 5.237321376800537, "learning_rate": 7.990032895532794e-06, "loss": 0.3204, "step": 308170 }, { "epoch": 1.831885918766458, "grad_norm": 5.233293533325195, "learning_rate": 7.989866589845614e-06, "loss": 0.3129, "step": 308180 }, { "epoch": 1.8319453608431264, "grad_norm": 4.288268566131592, "learning_rate": 7.989700279009526e-06, "loss": 0.3046, "step": 308190 }, { "epoch": 1.8320048029197948, "grad_norm": 5.2115349769592285, "learning_rate": 7.989533963024818e-06, "loss": 0.3307, "step": 308200 }, { "epoch": 1.832064244996463, "grad_norm": 5.267232418060303, "learning_rate": 7.989367641891776e-06, "loss": 0.2663, "step": 308210 }, { "epoch": 1.8321236870731314, "grad_norm": 3.262197971343994, "learning_rate": 7.989201315610686e-06, "loss": 0.2964, "step": 308220 }, { "epoch": 1.8321831291497999, "grad_norm": 5.189021110534668, "learning_rate": 7.989034984181836e-06, "loss": 0.3185, "step": 308230 }, { "epoch": 1.8322425712264683, "grad_norm": 5.571071147918701, "learning_rate": 7.98886864760551e-06, "loss": 0.2916, "step": 308240 }, { "epoch": 1.8323020133031367, "grad_norm": 4.379235744476318, "learning_rate": 7.988702305881994e-06, "loss": 0.3336, "step": 308250 }, { "epoch": 1.832361455379805, "grad_norm": 5.527528762817383, "learning_rate": 7.98853595901158e-06, "loss": 0.3179, "step": 308260 }, { "epoch": 1.8324208974564735, "grad_norm": 5.356823921203613, "learning_rate": 7.988369606994545e-06, "loss": 0.2891, "step": 308270 }, { "epoch": 1.832480339533142, "grad_norm": 3.977640151977539, "learning_rate": 7.988203249831183e-06, "loss": 0.2877, "step": 308280 }, { "epoch": 1.8325397816098103, "grad_norm": 6.0266313552856445, "learning_rate": 7.98803688752178e-06, "loss": 0.3189, "step": 308290 }, { "epoch": 1.8325992236864788, "grad_norm": 5.314017295837402, "learning_rate": 7.98787052006662e-06, "loss": 0.2775, "step": 308300 }, { "epoch": 1.8326586657631472, "grad_norm": 6.373655796051025, "learning_rate": 7.98770414746599e-06, "loss": 0.3447, "step": 308310 }, { "epoch": 1.8327181078398156, "grad_norm": 5.380627632141113, "learning_rate": 7.98753776972018e-06, "loss": 0.3069, "step": 308320 }, { "epoch": 1.832777549916484, "grad_norm": 5.303581237792969, "learning_rate": 7.98737138682947e-06, "loss": 0.3084, "step": 308330 }, { "epoch": 1.8328369919931524, "grad_norm": 5.3585968017578125, "learning_rate": 7.987204998794151e-06, "loss": 0.2947, "step": 308340 }, { "epoch": 1.8328964340698206, "grad_norm": 5.347522258758545, "learning_rate": 7.98703860561451e-06, "loss": 0.314, "step": 308350 }, { "epoch": 1.832955876146489, "grad_norm": 4.1553778648376465, "learning_rate": 7.98687220729083e-06, "loss": 0.3044, "step": 308360 }, { "epoch": 1.8330153182231574, "grad_norm": 4.297736644744873, "learning_rate": 7.9867058038234e-06, "loss": 0.291, "step": 308370 }, { "epoch": 1.8330747602998259, "grad_norm": 5.012010097503662, "learning_rate": 7.986539395212507e-06, "loss": 0.2994, "step": 308380 }, { "epoch": 1.8331342023764943, "grad_norm": 5.4189581871032715, "learning_rate": 7.986372981458437e-06, "loss": 0.3448, "step": 308390 }, { "epoch": 1.8331936444531625, "grad_norm": 3.849970817565918, "learning_rate": 7.986206562561477e-06, "loss": 0.3233, "step": 308400 }, { "epoch": 1.8332530865298309, "grad_norm": 4.652071952819824, "learning_rate": 7.98604013852191e-06, "loss": 0.3117, "step": 308410 }, { "epoch": 1.8333125286064993, "grad_norm": 5.974343299865723, "learning_rate": 7.985873709340029e-06, "loss": 0.3255, "step": 308420 }, { "epoch": 1.8333719706831677, "grad_norm": 4.847177982330322, "learning_rate": 7.985707275016114e-06, "loss": 0.359, "step": 308430 }, { "epoch": 1.8334314127598361, "grad_norm": 5.892889976501465, "learning_rate": 7.985540835550458e-06, "loss": 0.3179, "step": 308440 }, { "epoch": 1.8334908548365045, "grad_norm": 3.8794682025909424, "learning_rate": 7.985374390943344e-06, "loss": 0.2768, "step": 308450 }, { "epoch": 1.833550296913173, "grad_norm": 4.967983722686768, "learning_rate": 7.985207941195057e-06, "loss": 0.3329, "step": 308460 }, { "epoch": 1.8336097389898414, "grad_norm": 4.955488204956055, "learning_rate": 7.985041486305887e-06, "loss": 0.3059, "step": 308470 }, { "epoch": 1.8336691810665098, "grad_norm": 5.030059337615967, "learning_rate": 7.98487502627612e-06, "loss": 0.2715, "step": 308480 }, { "epoch": 1.8337286231431782, "grad_norm": 4.934262275695801, "learning_rate": 7.984708561106041e-06, "loss": 0.2853, "step": 308490 }, { "epoch": 1.8337880652198466, "grad_norm": 5.487095832824707, "learning_rate": 7.984542090795938e-06, "loss": 0.2946, "step": 308500 }, { "epoch": 1.833847507296515, "grad_norm": 5.893535137176514, "learning_rate": 7.984375615346098e-06, "loss": 0.3009, "step": 308510 }, { "epoch": 1.8339069493731834, "grad_norm": 4.5920867919921875, "learning_rate": 7.984209134756806e-06, "loss": 0.2939, "step": 308520 }, { "epoch": 1.8339663914498519, "grad_norm": 3.89426326751709, "learning_rate": 7.98404264902835e-06, "loss": 0.2674, "step": 308530 }, { "epoch": 1.83402583352652, "grad_norm": 5.954172134399414, "learning_rate": 7.983876158161017e-06, "loss": 0.3302, "step": 308540 }, { "epoch": 1.8340852756031885, "grad_norm": 7.322144985198975, "learning_rate": 7.983709662155093e-06, "loss": 0.2986, "step": 308550 }, { "epoch": 1.8341447176798569, "grad_norm": 5.2504682540893555, "learning_rate": 7.983543161010865e-06, "loss": 0.2899, "step": 308560 }, { "epoch": 1.8342041597565253, "grad_norm": 6.052328109741211, "learning_rate": 7.983376654728621e-06, "loss": 0.3325, "step": 308570 }, { "epoch": 1.8342636018331935, "grad_norm": 4.765038013458252, "learning_rate": 7.983210143308645e-06, "loss": 0.2923, "step": 308580 }, { "epoch": 1.834323043909862, "grad_norm": 4.890621185302734, "learning_rate": 7.983043626751225e-06, "loss": 0.3065, "step": 308590 }, { "epoch": 1.8343824859865303, "grad_norm": 4.406247138977051, "learning_rate": 7.982877105056648e-06, "loss": 0.2967, "step": 308600 }, { "epoch": 1.8344419280631987, "grad_norm": 3.728118658065796, "learning_rate": 7.982710578225201e-06, "loss": 0.2875, "step": 308610 }, { "epoch": 1.8345013701398671, "grad_norm": 3.445561170578003, "learning_rate": 7.98254404625717e-06, "loss": 0.2778, "step": 308620 }, { "epoch": 1.8345608122165356, "grad_norm": 4.095524787902832, "learning_rate": 7.982377509152843e-06, "loss": 0.2793, "step": 308630 }, { "epoch": 1.834620254293204, "grad_norm": 4.4670233726501465, "learning_rate": 7.982210966912506e-06, "loss": 0.2823, "step": 308640 }, { "epoch": 1.8346796963698724, "grad_norm": 6.846240520477295, "learning_rate": 7.982044419536445e-06, "loss": 0.3101, "step": 308650 }, { "epoch": 1.8347391384465408, "grad_norm": 4.44331169128418, "learning_rate": 7.98187786702495e-06, "loss": 0.3014, "step": 308660 }, { "epoch": 1.8347985805232092, "grad_norm": 5.5551629066467285, "learning_rate": 7.981711309378303e-06, "loss": 0.3092, "step": 308670 }, { "epoch": 1.8348580225998776, "grad_norm": 4.411488056182861, "learning_rate": 7.981544746596795e-06, "loss": 0.2911, "step": 308680 }, { "epoch": 1.834917464676546, "grad_norm": 5.675960540771484, "learning_rate": 7.98137817868071e-06, "loss": 0.3103, "step": 308690 }, { "epoch": 1.8349769067532145, "grad_norm": 5.009215831756592, "learning_rate": 7.981211605630337e-06, "loss": 0.2761, "step": 308700 }, { "epoch": 1.8350363488298829, "grad_norm": 4.371436595916748, "learning_rate": 7.981045027445961e-06, "loss": 0.2827, "step": 308710 }, { "epoch": 1.835095790906551, "grad_norm": 4.692755222320557, "learning_rate": 7.98087844412787e-06, "loss": 0.2968, "step": 308720 }, { "epoch": 1.8351552329832195, "grad_norm": 5.301441669464111, "learning_rate": 7.98071185567635e-06, "loss": 0.3069, "step": 308730 }, { "epoch": 1.835214675059888, "grad_norm": 4.056273937225342, "learning_rate": 7.98054526209169e-06, "loss": 0.2776, "step": 308740 }, { "epoch": 1.8352741171365563, "grad_norm": 3.8746144771575928, "learning_rate": 7.980378663374175e-06, "loss": 0.3122, "step": 308750 }, { "epoch": 1.8353335592132247, "grad_norm": 4.6323370933532715, "learning_rate": 7.980212059524093e-06, "loss": 0.3221, "step": 308760 }, { "epoch": 1.835393001289893, "grad_norm": 3.8036181926727295, "learning_rate": 7.980045450541729e-06, "loss": 0.2922, "step": 308770 }, { "epoch": 1.8354524433665613, "grad_norm": 5.866058826446533, "learning_rate": 7.979878836427373e-06, "loss": 0.3231, "step": 308780 }, { "epoch": 1.8355118854432297, "grad_norm": 4.480807781219482, "learning_rate": 7.979712217181308e-06, "loss": 0.3486, "step": 308790 }, { "epoch": 1.8355713275198982, "grad_norm": 5.018427848815918, "learning_rate": 7.979545592803823e-06, "loss": 0.2989, "step": 308800 }, { "epoch": 1.8356307695965666, "grad_norm": 4.190305709838867, "learning_rate": 7.979378963295206e-06, "loss": 0.3095, "step": 308810 }, { "epoch": 1.835690211673235, "grad_norm": 3.592559337615967, "learning_rate": 7.979212328655742e-06, "loss": 0.3057, "step": 308820 }, { "epoch": 1.8357496537499034, "grad_norm": 4.181777000427246, "learning_rate": 7.97904568888572e-06, "loss": 0.2811, "step": 308830 }, { "epoch": 1.8358090958265718, "grad_norm": 4.194692134857178, "learning_rate": 7.978879043985427e-06, "loss": 0.3, "step": 308840 }, { "epoch": 1.8358685379032402, "grad_norm": 4.942652702331543, "learning_rate": 7.978712393955146e-06, "loss": 0.3378, "step": 308850 }, { "epoch": 1.8359279799799086, "grad_norm": 5.02235746383667, "learning_rate": 7.978545738795167e-06, "loss": 0.3006, "step": 308860 }, { "epoch": 1.835987422056577, "grad_norm": 4.301484107971191, "learning_rate": 7.978379078505777e-06, "loss": 0.2727, "step": 308870 }, { "epoch": 1.8360468641332455, "grad_norm": 4.2550764083862305, "learning_rate": 7.978212413087266e-06, "loss": 0.2867, "step": 308880 }, { "epoch": 1.8361063062099139, "grad_norm": 4.804636001586914, "learning_rate": 7.978045742539916e-06, "loss": 0.3002, "step": 308890 }, { "epoch": 1.8361657482865823, "grad_norm": 4.9329304695129395, "learning_rate": 7.977879066864015e-06, "loss": 0.3048, "step": 308900 }, { "epoch": 1.8362251903632505, "grad_norm": 5.291706562042236, "learning_rate": 7.977712386059851e-06, "loss": 0.297, "step": 308910 }, { "epoch": 1.836284632439919, "grad_norm": 6.594518184661865, "learning_rate": 7.977545700127711e-06, "loss": 0.3263, "step": 308920 }, { "epoch": 1.8363440745165873, "grad_norm": 9.822247505187988, "learning_rate": 7.977379009067883e-06, "loss": 0.2973, "step": 308930 }, { "epoch": 1.8364035165932557, "grad_norm": 3.7332041263580322, "learning_rate": 7.977212312880652e-06, "loss": 0.2781, "step": 308940 }, { "epoch": 1.836462958669924, "grad_norm": 4.776330471038818, "learning_rate": 7.977045611566307e-06, "loss": 0.2979, "step": 308950 }, { "epoch": 1.8365224007465923, "grad_norm": 5.970761299133301, "learning_rate": 7.976878905125135e-06, "loss": 0.3376, "step": 308960 }, { "epoch": 1.8365818428232608, "grad_norm": 3.995007276535034, "learning_rate": 7.97671219355742e-06, "loss": 0.2775, "step": 308970 }, { "epoch": 1.8366412848999292, "grad_norm": 6.229507923126221, "learning_rate": 7.976545476863453e-06, "loss": 0.3, "step": 308980 }, { "epoch": 1.8367007269765976, "grad_norm": 5.274013042449951, "learning_rate": 7.97637875504352e-06, "loss": 0.2961, "step": 308990 }, { "epoch": 1.836760169053266, "grad_norm": 6.380733013153076, "learning_rate": 7.976212028097907e-06, "loss": 0.2925, "step": 309000 }, { "epoch": 1.8368196111299344, "grad_norm": 4.800594806671143, "learning_rate": 7.976045296026901e-06, "loss": 0.31, "step": 309010 }, { "epoch": 1.8368790532066028, "grad_norm": 5.068183898925781, "learning_rate": 7.97587855883079e-06, "loss": 0.2971, "step": 309020 }, { "epoch": 1.8369384952832712, "grad_norm": 5.063835144042969, "learning_rate": 7.975711816509862e-06, "loss": 0.273, "step": 309030 }, { "epoch": 1.8369979373599397, "grad_norm": 3.14377760887146, "learning_rate": 7.975545069064403e-06, "loss": 0.3054, "step": 309040 }, { "epoch": 1.837057379436608, "grad_norm": 3.9462146759033203, "learning_rate": 7.975378316494699e-06, "loss": 0.2827, "step": 309050 }, { "epoch": 1.8371168215132765, "grad_norm": 5.202310562133789, "learning_rate": 7.975211558801042e-06, "loss": 0.3069, "step": 309060 }, { "epoch": 1.837176263589945, "grad_norm": 5.124287128448486, "learning_rate": 7.975044795983713e-06, "loss": 0.3155, "step": 309070 }, { "epoch": 1.8372357056666133, "grad_norm": 4.004499912261963, "learning_rate": 7.974878028043001e-06, "loss": 0.33, "step": 309080 }, { "epoch": 1.8372951477432815, "grad_norm": 4.499106407165527, "learning_rate": 7.974711254979196e-06, "loss": 0.274, "step": 309090 }, { "epoch": 1.83735458981995, "grad_norm": 5.069157123565674, "learning_rate": 7.974544476792583e-06, "loss": 0.3101, "step": 309100 }, { "epoch": 1.8374140318966183, "grad_norm": 4.3905558586120605, "learning_rate": 7.974377693483448e-06, "loss": 0.3095, "step": 309110 }, { "epoch": 1.8374734739732868, "grad_norm": 3.677125930786133, "learning_rate": 7.974210905052081e-06, "loss": 0.3001, "step": 309120 }, { "epoch": 1.8375329160499552, "grad_norm": 4.148507118225098, "learning_rate": 7.97404411149877e-06, "loss": 0.2733, "step": 309130 }, { "epoch": 1.8375923581266234, "grad_norm": 4.564640998840332, "learning_rate": 7.973877312823796e-06, "loss": 0.2762, "step": 309140 }, { "epoch": 1.8376518002032918, "grad_norm": 4.351361274719238, "learning_rate": 7.973710509027452e-06, "loss": 0.3042, "step": 309150 }, { "epoch": 1.8377112422799602, "grad_norm": 4.012313365936279, "learning_rate": 7.973543700110024e-06, "loss": 0.2794, "step": 309160 }, { "epoch": 1.8377706843566286, "grad_norm": 4.842984199523926, "learning_rate": 7.9733768860718e-06, "loss": 0.3058, "step": 309170 }, { "epoch": 1.837830126433297, "grad_norm": 5.418514728546143, "learning_rate": 7.973210066913064e-06, "loss": 0.2889, "step": 309180 }, { "epoch": 1.8378895685099654, "grad_norm": 4.535563945770264, "learning_rate": 7.973043242634108e-06, "loss": 0.295, "step": 309190 }, { "epoch": 1.8379490105866338, "grad_norm": 5.0267014503479, "learning_rate": 7.972876413235215e-06, "loss": 0.3007, "step": 309200 }, { "epoch": 1.8380084526633023, "grad_norm": 5.820461750030518, "learning_rate": 7.972709578716676e-06, "loss": 0.293, "step": 309210 }, { "epoch": 1.8380678947399707, "grad_norm": 5.075186729431152, "learning_rate": 7.972542739078775e-06, "loss": 0.3161, "step": 309220 }, { "epoch": 1.838127336816639, "grad_norm": 7.730268478393555, "learning_rate": 7.9723758943218e-06, "loss": 0.3414, "step": 309230 }, { "epoch": 1.8381867788933075, "grad_norm": 3.877256155014038, "learning_rate": 7.97220904444604e-06, "loss": 0.3083, "step": 309240 }, { "epoch": 1.838246220969976, "grad_norm": 3.9485952854156494, "learning_rate": 7.97204218945178e-06, "loss": 0.2839, "step": 309250 }, { "epoch": 1.8383056630466443, "grad_norm": 6.144512176513672, "learning_rate": 7.971875329339311e-06, "loss": 0.313, "step": 309260 }, { "epoch": 1.8383651051233127, "grad_norm": 3.9145965576171875, "learning_rate": 7.971708464108915e-06, "loss": 0.313, "step": 309270 }, { "epoch": 1.838424547199981, "grad_norm": 3.340169906616211, "learning_rate": 7.971541593760886e-06, "loss": 0.2862, "step": 309280 }, { "epoch": 1.8384839892766494, "grad_norm": 5.371625900268555, "learning_rate": 7.971374718295507e-06, "loss": 0.3199, "step": 309290 }, { "epoch": 1.8385434313533178, "grad_norm": 6.8381218910217285, "learning_rate": 7.971207837713066e-06, "loss": 0.3012, "step": 309300 }, { "epoch": 1.8386028734299862, "grad_norm": 5.0274553298950195, "learning_rate": 7.971040952013848e-06, "loss": 0.2896, "step": 309310 }, { "epoch": 1.8386623155066544, "grad_norm": 5.580686569213867, "learning_rate": 7.970874061198146e-06, "loss": 0.2943, "step": 309320 }, { "epoch": 1.8387217575833228, "grad_norm": 4.7101826667785645, "learning_rate": 7.970707165266244e-06, "loss": 0.286, "step": 309330 }, { "epoch": 1.8387811996599912, "grad_norm": 4.2569661140441895, "learning_rate": 7.97054026421843e-06, "loss": 0.3117, "step": 309340 }, { "epoch": 1.8388406417366596, "grad_norm": 4.359133243560791, "learning_rate": 7.97037335805499e-06, "loss": 0.3298, "step": 309350 }, { "epoch": 1.838900083813328, "grad_norm": 5.0550336837768555, "learning_rate": 7.970206446776214e-06, "loss": 0.2729, "step": 309360 }, { "epoch": 1.8389595258899964, "grad_norm": 5.200369834899902, "learning_rate": 7.970039530382385e-06, "loss": 0.3197, "step": 309370 }, { "epoch": 1.8390189679666649, "grad_norm": 6.021142482757568, "learning_rate": 7.969872608873796e-06, "loss": 0.341, "step": 309380 }, { "epoch": 1.8390784100433333, "grad_norm": 4.388424873352051, "learning_rate": 7.969705682250732e-06, "loss": 0.3186, "step": 309390 }, { "epoch": 1.8391378521200017, "grad_norm": 4.407780170440674, "learning_rate": 7.969538750513481e-06, "loss": 0.3089, "step": 309400 }, { "epoch": 1.83919729419667, "grad_norm": 5.442579746246338, "learning_rate": 7.969371813662329e-06, "loss": 0.2871, "step": 309410 }, { "epoch": 1.8392567362733385, "grad_norm": 4.656950950622559, "learning_rate": 7.969204871697565e-06, "loss": 0.2833, "step": 309420 }, { "epoch": 1.839316178350007, "grad_norm": 4.9799675941467285, "learning_rate": 7.969037924619475e-06, "loss": 0.3231, "step": 309430 }, { "epoch": 1.8393756204266754, "grad_norm": 5.2307024002075195, "learning_rate": 7.968870972428349e-06, "loss": 0.3011, "step": 309440 }, { "epoch": 1.8394350625033438, "grad_norm": 6.377286434173584, "learning_rate": 7.968704015124471e-06, "loss": 0.3097, "step": 309450 }, { "epoch": 1.839494504580012, "grad_norm": 5.30768346786499, "learning_rate": 7.968537052708132e-06, "loss": 0.3076, "step": 309460 }, { "epoch": 1.8395539466566804, "grad_norm": 4.373610973358154, "learning_rate": 7.968370085179618e-06, "loss": 0.3132, "step": 309470 }, { "epoch": 1.8396133887333488, "grad_norm": 5.535086154937744, "learning_rate": 7.968203112539214e-06, "loss": 0.2991, "step": 309480 }, { "epoch": 1.8396728308100172, "grad_norm": 6.052478313446045, "learning_rate": 7.968036134787214e-06, "loss": 0.2859, "step": 309490 }, { "epoch": 1.8397322728866856, "grad_norm": 4.924744129180908, "learning_rate": 7.9678691519239e-06, "loss": 0.2719, "step": 309500 }, { "epoch": 1.8397917149633538, "grad_norm": 6.180312633514404, "learning_rate": 7.96770216394956e-06, "loss": 0.3351, "step": 309510 }, { "epoch": 1.8398511570400222, "grad_norm": 4.595694541931152, "learning_rate": 7.967535170864483e-06, "loss": 0.2811, "step": 309520 }, { "epoch": 1.8399105991166906, "grad_norm": 4.710129261016846, "learning_rate": 7.967368172668957e-06, "loss": 0.2965, "step": 309530 }, { "epoch": 1.839970041193359, "grad_norm": 4.53888463973999, "learning_rate": 7.96720116936327e-06, "loss": 0.2814, "step": 309540 }, { "epoch": 1.8400294832700275, "grad_norm": 5.46510124206543, "learning_rate": 7.967034160947707e-06, "loss": 0.3203, "step": 309550 }, { "epoch": 1.8400889253466959, "grad_norm": 6.006836414337158, "learning_rate": 7.966867147422559e-06, "loss": 0.3163, "step": 309560 }, { "epoch": 1.8401483674233643, "grad_norm": 5.538287162780762, "learning_rate": 7.96670012878811e-06, "loss": 0.2945, "step": 309570 }, { "epoch": 1.8402078095000327, "grad_norm": 4.053194046020508, "learning_rate": 7.96653310504465e-06, "loss": 0.3212, "step": 309580 }, { "epoch": 1.8402672515767011, "grad_norm": 4.416130065917969, "learning_rate": 7.966366076192464e-06, "loss": 0.3067, "step": 309590 }, { "epoch": 1.8403266936533695, "grad_norm": 3.876826763153076, "learning_rate": 7.966199042231844e-06, "loss": 0.3487, "step": 309600 }, { "epoch": 1.840386135730038, "grad_norm": 3.5627830028533936, "learning_rate": 7.966032003163076e-06, "loss": 0.2709, "step": 309610 }, { "epoch": 1.8404455778067064, "grad_norm": 5.091433525085449, "learning_rate": 7.965864958986445e-06, "loss": 0.3135, "step": 309620 }, { "epoch": 1.8405050198833748, "grad_norm": 4.932619571685791, "learning_rate": 7.965697909702241e-06, "loss": 0.2851, "step": 309630 }, { "epoch": 1.8405644619600432, "grad_norm": 4.815038204193115, "learning_rate": 7.965530855310752e-06, "loss": 0.3172, "step": 309640 }, { "epoch": 1.8406239040367114, "grad_norm": 6.367650985717773, "learning_rate": 7.965363795812266e-06, "loss": 0.3314, "step": 309650 }, { "epoch": 1.8406833461133798, "grad_norm": 5.622385501861572, "learning_rate": 7.965196731207067e-06, "loss": 0.2681, "step": 309660 }, { "epoch": 1.8407427881900482, "grad_norm": 4.423653602600098, "learning_rate": 7.965029661495449e-06, "loss": 0.3244, "step": 309670 }, { "epoch": 1.8408022302667166, "grad_norm": 5.938997268676758, "learning_rate": 7.964862586677693e-06, "loss": 0.2883, "step": 309680 }, { "epoch": 1.8408616723433848, "grad_norm": 3.810795307159424, "learning_rate": 7.964695506754093e-06, "loss": 0.3108, "step": 309690 }, { "epoch": 1.8409211144200532, "grad_norm": 4.504421710968018, "learning_rate": 7.964528421724929e-06, "loss": 0.2962, "step": 309700 }, { "epoch": 1.8409805564967217, "grad_norm": 4.835396766662598, "learning_rate": 7.964361331590498e-06, "loss": 0.3351, "step": 309710 }, { "epoch": 1.84103999857339, "grad_norm": 4.838672161102295, "learning_rate": 7.964194236351079e-06, "loss": 0.2652, "step": 309720 }, { "epoch": 1.8410994406500585, "grad_norm": 3.676300048828125, "learning_rate": 7.964027136006967e-06, "loss": 0.297, "step": 309730 }, { "epoch": 1.841158882726727, "grad_norm": 6.093757629394531, "learning_rate": 7.963860030558446e-06, "loss": 0.3222, "step": 309740 }, { "epoch": 1.8412183248033953, "grad_norm": 5.1503095626831055, "learning_rate": 7.963692920005804e-06, "loss": 0.268, "step": 309750 }, { "epoch": 1.8412777668800637, "grad_norm": 4.42610502243042, "learning_rate": 7.963525804349328e-06, "loss": 0.2886, "step": 309760 }, { "epoch": 1.8413372089567321, "grad_norm": 5.242857456207275, "learning_rate": 7.963358683589308e-06, "loss": 0.3037, "step": 309770 }, { "epoch": 1.8413966510334006, "grad_norm": 4.4139299392700195, "learning_rate": 7.963191557726031e-06, "loss": 0.3082, "step": 309780 }, { "epoch": 1.841456093110069, "grad_norm": 5.927250385284424, "learning_rate": 7.963024426759785e-06, "loss": 0.3026, "step": 309790 }, { "epoch": 1.8415155351867374, "grad_norm": 5.191014289855957, "learning_rate": 7.962857290690857e-06, "loss": 0.2889, "step": 309800 }, { "epoch": 1.8415749772634058, "grad_norm": 4.7227373123168945, "learning_rate": 7.962690149519533e-06, "loss": 0.3104, "step": 309810 }, { "epoch": 1.8416344193400742, "grad_norm": 4.162628173828125, "learning_rate": 7.962523003246106e-06, "loss": 0.2882, "step": 309820 }, { "epoch": 1.8416938614167424, "grad_norm": 6.072129726409912, "learning_rate": 7.96235585187086e-06, "loss": 0.3053, "step": 309830 }, { "epoch": 1.8417533034934108, "grad_norm": 4.179869651794434, "learning_rate": 7.962188695394084e-06, "loss": 0.3299, "step": 309840 }, { "epoch": 1.8418127455700792, "grad_norm": 3.601553201675415, "learning_rate": 7.962021533816066e-06, "loss": 0.2898, "step": 309850 }, { "epoch": 1.8418721876467476, "grad_norm": 6.492301940917969, "learning_rate": 7.961854367137092e-06, "loss": 0.3324, "step": 309860 }, { "epoch": 1.841931629723416, "grad_norm": 5.012868881225586, "learning_rate": 7.961687195357453e-06, "loss": 0.3159, "step": 309870 }, { "epoch": 1.8419910718000843, "grad_norm": 6.297976493835449, "learning_rate": 7.961520018477434e-06, "loss": 0.3393, "step": 309880 }, { "epoch": 1.8420505138767527, "grad_norm": 5.4591965675354, "learning_rate": 7.961352836497325e-06, "loss": 0.3222, "step": 309890 }, { "epoch": 1.842109955953421, "grad_norm": 3.922766923904419, "learning_rate": 7.961185649417413e-06, "loss": 0.2544, "step": 309900 }, { "epoch": 1.8421693980300895, "grad_norm": 4.999393463134766, "learning_rate": 7.961018457237985e-06, "loss": 0.2968, "step": 309910 }, { "epoch": 1.842228840106758, "grad_norm": 4.689550399780273, "learning_rate": 7.96085125995933e-06, "loss": 0.2847, "step": 309920 }, { "epoch": 1.8422882821834263, "grad_norm": 4.218485355377197, "learning_rate": 7.960684057581736e-06, "loss": 0.3105, "step": 309930 }, { "epoch": 1.8423477242600947, "grad_norm": 4.456235408782959, "learning_rate": 7.960516850105491e-06, "loss": 0.3215, "step": 309940 }, { "epoch": 1.8424071663367632, "grad_norm": 4.376582145690918, "learning_rate": 7.960349637530884e-06, "loss": 0.3054, "step": 309950 }, { "epoch": 1.8424666084134316, "grad_norm": 4.870952606201172, "learning_rate": 7.9601824198582e-06, "loss": 0.2836, "step": 309960 }, { "epoch": 1.8425260504901, "grad_norm": 5.035359859466553, "learning_rate": 7.96001519708773e-06, "loss": 0.2871, "step": 309970 }, { "epoch": 1.8425854925667684, "grad_norm": 3.7403080463409424, "learning_rate": 7.95984796921976e-06, "loss": 0.278, "step": 309980 }, { "epoch": 1.8426449346434368, "grad_norm": 4.3816351890563965, "learning_rate": 7.95968073625458e-06, "loss": 0.2988, "step": 309990 }, { "epoch": 1.8427043767201052, "grad_norm": 4.992705821990967, "learning_rate": 7.959513498192475e-06, "loss": 0.3017, "step": 310000 }, { "epoch": 1.8427638187967736, "grad_norm": 3.804847002029419, "learning_rate": 7.959346255033736e-06, "loss": 0.2948, "step": 310010 }, { "epoch": 1.8428232608734418, "grad_norm": 4.557010650634766, "learning_rate": 7.959179006778648e-06, "loss": 0.282, "step": 310020 }, { "epoch": 1.8428827029501103, "grad_norm": 4.998538970947266, "learning_rate": 7.9590117534275e-06, "loss": 0.3455, "step": 310030 }, { "epoch": 1.8429421450267787, "grad_norm": 7.272087574005127, "learning_rate": 7.958844494980582e-06, "loss": 0.3313, "step": 310040 }, { "epoch": 1.843001587103447, "grad_norm": 3.8026537895202637, "learning_rate": 7.958677231438181e-06, "loss": 0.2638, "step": 310050 }, { "epoch": 1.8430610291801153, "grad_norm": 4.419658660888672, "learning_rate": 7.958509962800584e-06, "loss": 0.2838, "step": 310060 }, { "epoch": 1.8431204712567837, "grad_norm": 5.118561744689941, "learning_rate": 7.95834268906808e-06, "loss": 0.2638, "step": 310070 }, { "epoch": 1.843179913333452, "grad_norm": 5.119769096374512, "learning_rate": 7.958175410240958e-06, "loss": 0.312, "step": 310080 }, { "epoch": 1.8432393554101205, "grad_norm": 5.349540710449219, "learning_rate": 7.958008126319505e-06, "loss": 0.2946, "step": 310090 }, { "epoch": 1.843298797486789, "grad_norm": 5.298847675323486, "learning_rate": 7.957840837304008e-06, "loss": 0.2854, "step": 310100 }, { "epoch": 1.8433582395634573, "grad_norm": 5.576423168182373, "learning_rate": 7.957673543194756e-06, "loss": 0.2968, "step": 310110 }, { "epoch": 1.8434176816401258, "grad_norm": 4.177419185638428, "learning_rate": 7.957506243992038e-06, "loss": 0.2933, "step": 310120 }, { "epoch": 1.8434771237167942, "grad_norm": 4.733529567718506, "learning_rate": 7.957338939696139e-06, "loss": 0.2956, "step": 310130 }, { "epoch": 1.8435365657934626, "grad_norm": 5.328526496887207, "learning_rate": 7.957171630307351e-06, "loss": 0.2995, "step": 310140 }, { "epoch": 1.843596007870131, "grad_norm": 4.985143661499023, "learning_rate": 7.957004315825963e-06, "loss": 0.2883, "step": 310150 }, { "epoch": 1.8436554499467994, "grad_norm": 5.863162040710449, "learning_rate": 7.956836996252258e-06, "loss": 0.2603, "step": 310160 }, { "epoch": 1.8437148920234678, "grad_norm": 3.98246431350708, "learning_rate": 7.956669671586528e-06, "loss": 0.307, "step": 310170 }, { "epoch": 1.8437743341001362, "grad_norm": 3.852853536605835, "learning_rate": 7.95650234182906e-06, "loss": 0.2879, "step": 310180 }, { "epoch": 1.8438337761768047, "grad_norm": 5.4954094886779785, "learning_rate": 7.956335006980142e-06, "loss": 0.3061, "step": 310190 }, { "epoch": 1.8438932182534729, "grad_norm": 5.122967720031738, "learning_rate": 7.956167667040062e-06, "loss": 0.2945, "step": 310200 }, { "epoch": 1.8439526603301413, "grad_norm": 4.899064540863037, "learning_rate": 7.95600032200911e-06, "loss": 0.3213, "step": 310210 }, { "epoch": 1.8440121024068097, "grad_norm": 4.697540283203125, "learning_rate": 7.955832971887572e-06, "loss": 0.3087, "step": 310220 }, { "epoch": 1.844071544483478, "grad_norm": 4.752093315124512, "learning_rate": 7.955665616675735e-06, "loss": 0.3125, "step": 310230 }, { "epoch": 1.8441309865601465, "grad_norm": 3.6667442321777344, "learning_rate": 7.955498256373893e-06, "loss": 0.2613, "step": 310240 }, { "epoch": 1.8441904286368147, "grad_norm": 4.985024452209473, "learning_rate": 7.955330890982326e-06, "loss": 0.311, "step": 310250 }, { "epoch": 1.8442498707134831, "grad_norm": 5.1413373947143555, "learning_rate": 7.95516352050133e-06, "loss": 0.3335, "step": 310260 }, { "epoch": 1.8443093127901515, "grad_norm": 4.174751281738281, "learning_rate": 7.954996144931188e-06, "loss": 0.2842, "step": 310270 }, { "epoch": 1.84436875486682, "grad_norm": 4.921292304992676, "learning_rate": 7.95482876427219e-06, "loss": 0.3089, "step": 310280 }, { "epoch": 1.8444281969434884, "grad_norm": 4.371458053588867, "learning_rate": 7.954661378524625e-06, "loss": 0.2953, "step": 310290 }, { "epoch": 1.8444876390201568, "grad_norm": 5.482126712799072, "learning_rate": 7.954493987688781e-06, "loss": 0.3138, "step": 310300 }, { "epoch": 1.8445470810968252, "grad_norm": 4.218272686004639, "learning_rate": 7.954326591764944e-06, "loss": 0.2728, "step": 310310 }, { "epoch": 1.8446065231734936, "grad_norm": 5.501414775848389, "learning_rate": 7.954159190753406e-06, "loss": 0.288, "step": 310320 }, { "epoch": 1.844665965250162, "grad_norm": 5.734724044799805, "learning_rate": 7.953991784654453e-06, "loss": 0.294, "step": 310330 }, { "epoch": 1.8447254073268304, "grad_norm": 7.912524700164795, "learning_rate": 7.953824373468372e-06, "loss": 0.3164, "step": 310340 }, { "epoch": 1.8447848494034988, "grad_norm": 6.000040531158447, "learning_rate": 7.953656957195456e-06, "loss": 0.299, "step": 310350 }, { "epoch": 1.8448442914801673, "grad_norm": 4.000914573669434, "learning_rate": 7.953489535835988e-06, "loss": 0.3153, "step": 310360 }, { "epoch": 1.8449037335568357, "grad_norm": 6.277897834777832, "learning_rate": 7.953322109390259e-06, "loss": 0.2693, "step": 310370 }, { "epoch": 1.844963175633504, "grad_norm": 5.276374816894531, "learning_rate": 7.953154677858556e-06, "loss": 0.3244, "step": 310380 }, { "epoch": 1.8450226177101723, "grad_norm": 4.278835296630859, "learning_rate": 7.952987241241171e-06, "loss": 0.2928, "step": 310390 }, { "epoch": 1.8450820597868407, "grad_norm": 5.579256534576416, "learning_rate": 7.952819799538388e-06, "loss": 0.2789, "step": 310400 }, { "epoch": 1.8451415018635091, "grad_norm": 5.251640796661377, "learning_rate": 7.952652352750498e-06, "loss": 0.2978, "step": 310410 }, { "epoch": 1.8452009439401775, "grad_norm": 4.6596879959106445, "learning_rate": 7.952484900877787e-06, "loss": 0.2955, "step": 310420 }, { "epoch": 1.8452603860168457, "grad_norm": 4.938974380493164, "learning_rate": 7.952317443920545e-06, "loss": 0.3048, "step": 310430 }, { "epoch": 1.8453198280935141, "grad_norm": 4.579596042633057, "learning_rate": 7.95214998187906e-06, "loss": 0.3122, "step": 310440 }, { "epoch": 1.8453792701701826, "grad_norm": 4.766476154327393, "learning_rate": 7.951982514753621e-06, "loss": 0.2848, "step": 310450 }, { "epoch": 1.845438712246851, "grad_norm": 5.112443923950195, "learning_rate": 7.951815042544515e-06, "loss": 0.2868, "step": 310460 }, { "epoch": 1.8454981543235194, "grad_norm": 6.202546119689941, "learning_rate": 7.951647565252032e-06, "loss": 0.2998, "step": 310470 }, { "epoch": 1.8455575964001878, "grad_norm": 4.892000198364258, "learning_rate": 7.95148008287646e-06, "loss": 0.3023, "step": 310480 }, { "epoch": 1.8456170384768562, "grad_norm": 5.104568004608154, "learning_rate": 7.951312595418086e-06, "loss": 0.2721, "step": 310490 }, { "epoch": 1.8456764805535246, "grad_norm": 6.475595474243164, "learning_rate": 7.951145102877202e-06, "loss": 0.3186, "step": 310500 }, { "epoch": 1.845735922630193, "grad_norm": 5.162196636199951, "learning_rate": 7.950977605254092e-06, "loss": 0.278, "step": 310510 }, { "epoch": 1.8457953647068615, "grad_norm": 3.1921074390411377, "learning_rate": 7.950810102549047e-06, "loss": 0.3088, "step": 310520 }, { "epoch": 1.8458548067835299, "grad_norm": 5.194939136505127, "learning_rate": 7.950642594762354e-06, "loss": 0.3079, "step": 310530 }, { "epoch": 1.8459142488601983, "grad_norm": 5.4867329597473145, "learning_rate": 7.950475081894303e-06, "loss": 0.304, "step": 310540 }, { "epoch": 1.8459736909368667, "grad_norm": 4.80679178237915, "learning_rate": 7.950307563945183e-06, "loss": 0.293, "step": 310550 }, { "epoch": 1.846033133013535, "grad_norm": 4.075689792633057, "learning_rate": 7.950140040915279e-06, "loss": 0.2862, "step": 310560 }, { "epoch": 1.8460925750902033, "grad_norm": 4.872735023498535, "learning_rate": 7.949972512804885e-06, "loss": 0.3062, "step": 310570 }, { "epoch": 1.8461520171668717, "grad_norm": 7.907332420349121, "learning_rate": 7.949804979614284e-06, "loss": 0.2911, "step": 310580 }, { "epoch": 1.8462114592435401, "grad_norm": 4.238498687744141, "learning_rate": 7.949637441343766e-06, "loss": 0.2825, "step": 310590 }, { "epoch": 1.8462709013202085, "grad_norm": 3.725048780441284, "learning_rate": 7.949469897993623e-06, "loss": 0.2905, "step": 310600 }, { "epoch": 1.846330343396877, "grad_norm": 5.534891128540039, "learning_rate": 7.949302349564139e-06, "loss": 0.3002, "step": 310610 }, { "epoch": 1.8463897854735452, "grad_norm": 3.9898650646209717, "learning_rate": 7.949134796055605e-06, "loss": 0.2848, "step": 310620 }, { "epoch": 1.8464492275502136, "grad_norm": 4.631051540374756, "learning_rate": 7.94896723746831e-06, "loss": 0.2968, "step": 310630 }, { "epoch": 1.846508669626882, "grad_norm": 5.324337005615234, "learning_rate": 7.948799673802541e-06, "loss": 0.2819, "step": 310640 }, { "epoch": 1.8465681117035504, "grad_norm": 5.838925361633301, "learning_rate": 7.948632105058585e-06, "loss": 0.3047, "step": 310650 }, { "epoch": 1.8466275537802188, "grad_norm": 6.033946514129639, "learning_rate": 7.948464531236735e-06, "loss": 0.2843, "step": 310660 }, { "epoch": 1.8466869958568872, "grad_norm": 5.428109645843506, "learning_rate": 7.948296952337278e-06, "loss": 0.2896, "step": 310670 }, { "epoch": 1.8467464379335556, "grad_norm": 5.492950916290283, "learning_rate": 7.9481293683605e-06, "loss": 0.2827, "step": 310680 }, { "epoch": 1.846805880010224, "grad_norm": 5.728966236114502, "learning_rate": 7.947961779306692e-06, "loss": 0.2783, "step": 310690 }, { "epoch": 1.8468653220868925, "grad_norm": 5.691415309906006, "learning_rate": 7.947794185176141e-06, "loss": 0.2773, "step": 310700 }, { "epoch": 1.8469247641635609, "grad_norm": 5.607481956481934, "learning_rate": 7.947626585969139e-06, "loss": 0.3282, "step": 310710 }, { "epoch": 1.8469842062402293, "grad_norm": 5.694836139678955, "learning_rate": 7.947458981685971e-06, "loss": 0.3132, "step": 310720 }, { "epoch": 1.8470436483168977, "grad_norm": 5.2586259841918945, "learning_rate": 7.947291372326928e-06, "loss": 0.2997, "step": 310730 }, { "epoch": 1.8471030903935661, "grad_norm": 5.474231719970703, "learning_rate": 7.947123757892296e-06, "loss": 0.3099, "step": 310740 }, { "epoch": 1.8471625324702345, "grad_norm": 5.207277774810791, "learning_rate": 7.946956138382366e-06, "loss": 0.3115, "step": 310750 }, { "epoch": 1.8472219745469027, "grad_norm": 5.744876384735107, "learning_rate": 7.946788513797425e-06, "loss": 0.2798, "step": 310760 }, { "epoch": 1.8472814166235711, "grad_norm": 4.624577045440674, "learning_rate": 7.946620884137763e-06, "loss": 0.3131, "step": 310770 }, { "epoch": 1.8473408587002396, "grad_norm": 4.843113899230957, "learning_rate": 7.94645324940367e-06, "loss": 0.2979, "step": 310780 }, { "epoch": 1.847400300776908, "grad_norm": 6.5445098876953125, "learning_rate": 7.946285609595432e-06, "loss": 0.2945, "step": 310790 }, { "epoch": 1.8474597428535762, "grad_norm": 5.665777683258057, "learning_rate": 7.946117964713337e-06, "loss": 0.2853, "step": 310800 }, { "epoch": 1.8475191849302446, "grad_norm": 6.276013374328613, "learning_rate": 7.945950314757678e-06, "loss": 0.2538, "step": 310810 }, { "epoch": 1.847578627006913, "grad_norm": 4.745072364807129, "learning_rate": 7.945782659728738e-06, "loss": 0.2628, "step": 310820 }, { "epoch": 1.8476380690835814, "grad_norm": 5.250947952270508, "learning_rate": 7.94561499962681e-06, "loss": 0.3142, "step": 310830 }, { "epoch": 1.8476975111602498, "grad_norm": 5.121494770050049, "learning_rate": 7.945447334452183e-06, "loss": 0.3169, "step": 310840 }, { "epoch": 1.8477569532369182, "grad_norm": 5.395627975463867, "learning_rate": 7.945279664205144e-06, "loss": 0.298, "step": 310850 }, { "epoch": 1.8478163953135867, "grad_norm": 5.309494972229004, "learning_rate": 7.945111988885981e-06, "loss": 0.3182, "step": 310860 }, { "epoch": 1.847875837390255, "grad_norm": 5.878646373748779, "learning_rate": 7.944944308494984e-06, "loss": 0.3404, "step": 310870 }, { "epoch": 1.8479352794669235, "grad_norm": 5.577836036682129, "learning_rate": 7.944776623032442e-06, "loss": 0.3271, "step": 310880 }, { "epoch": 1.847994721543592, "grad_norm": 6.0926103591918945, "learning_rate": 7.944608932498641e-06, "loss": 0.314, "step": 310890 }, { "epoch": 1.8480541636202603, "grad_norm": 5.082061290740967, "learning_rate": 7.944441236893874e-06, "loss": 0.3132, "step": 310900 }, { "epoch": 1.8481136056969287, "grad_norm": 6.544000148773193, "learning_rate": 7.944273536218428e-06, "loss": 0.3123, "step": 310910 }, { "epoch": 1.8481730477735971, "grad_norm": 5.545363903045654, "learning_rate": 7.94410583047259e-06, "loss": 0.3103, "step": 310920 }, { "epoch": 1.8482324898502656, "grad_norm": 5.700615406036377, "learning_rate": 7.943938119656654e-06, "loss": 0.3063, "step": 310930 }, { "epoch": 1.8482919319269338, "grad_norm": 4.493831634521484, "learning_rate": 7.943770403770902e-06, "loss": 0.2961, "step": 310940 }, { "epoch": 1.8483513740036022, "grad_norm": 6.823813438415527, "learning_rate": 7.943602682815627e-06, "loss": 0.319, "step": 310950 }, { "epoch": 1.8484108160802706, "grad_norm": 4.114441871643066, "learning_rate": 7.943434956791118e-06, "loss": 0.301, "step": 310960 }, { "epoch": 1.848470258156939, "grad_norm": 6.462799072265625, "learning_rate": 7.943267225697662e-06, "loss": 0.3291, "step": 310970 }, { "epoch": 1.8485297002336074, "grad_norm": 4.476925849914551, "learning_rate": 7.943099489535549e-06, "loss": 0.2961, "step": 310980 }, { "epoch": 1.8485891423102756, "grad_norm": 5.092869758605957, "learning_rate": 7.942931748305067e-06, "loss": 0.281, "step": 310990 }, { "epoch": 1.848648584386944, "grad_norm": 4.5174479484558105, "learning_rate": 7.942764002006504e-06, "loss": 0.2917, "step": 311000 }, { "epoch": 1.8487080264636124, "grad_norm": 5.002486705780029, "learning_rate": 7.942596250640152e-06, "loss": 0.3001, "step": 311010 }, { "epoch": 1.8487674685402808, "grad_norm": 5.062582492828369, "learning_rate": 7.942428494206298e-06, "loss": 0.2923, "step": 311020 }, { "epoch": 1.8488269106169493, "grad_norm": 5.875536918640137, "learning_rate": 7.942260732705232e-06, "loss": 0.3047, "step": 311030 }, { "epoch": 1.8488863526936177, "grad_norm": 3.4749035835266113, "learning_rate": 7.94209296613724e-06, "loss": 0.2881, "step": 311040 }, { "epoch": 1.848945794770286, "grad_norm": 4.670229434967041, "learning_rate": 7.941925194502613e-06, "loss": 0.3147, "step": 311050 }, { "epoch": 1.8490052368469545, "grad_norm": 5.142640113830566, "learning_rate": 7.94175741780164e-06, "loss": 0.2794, "step": 311060 }, { "epoch": 1.849064678923623, "grad_norm": 5.2182207107543945, "learning_rate": 7.941589636034613e-06, "loss": 0.2837, "step": 311070 }, { "epoch": 1.8491241210002913, "grad_norm": 3.8352837562561035, "learning_rate": 7.941421849201813e-06, "loss": 0.2871, "step": 311080 }, { "epoch": 1.8491835630769597, "grad_norm": 5.483623027801514, "learning_rate": 7.941254057303536e-06, "loss": 0.3288, "step": 311090 }, { "epoch": 1.8492430051536282, "grad_norm": 6.7741498947143555, "learning_rate": 7.94108626034007e-06, "loss": 0.295, "step": 311100 }, { "epoch": 1.8493024472302966, "grad_norm": 5.824588775634766, "learning_rate": 7.940918458311699e-06, "loss": 0.3076, "step": 311110 }, { "epoch": 1.849361889306965, "grad_norm": 4.788887023925781, "learning_rate": 7.940750651218718e-06, "loss": 0.27, "step": 311120 }, { "epoch": 1.8494213313836332, "grad_norm": 4.315316200256348, "learning_rate": 7.94058283906141e-06, "loss": 0.2807, "step": 311130 }, { "epoch": 1.8494807734603016, "grad_norm": 5.105681896209717, "learning_rate": 7.94041502184007e-06, "loss": 0.296, "step": 311140 }, { "epoch": 1.84954021553697, "grad_norm": 4.903111934661865, "learning_rate": 7.940247199554987e-06, "loss": 0.3186, "step": 311150 }, { "epoch": 1.8495996576136384, "grad_norm": 5.274112224578857, "learning_rate": 7.940079372206445e-06, "loss": 0.2768, "step": 311160 }, { "epoch": 1.8496590996903066, "grad_norm": 3.9291281700134277, "learning_rate": 7.939911539794736e-06, "loss": 0.2904, "step": 311170 }, { "epoch": 1.849718541766975, "grad_norm": 5.272766590118408, "learning_rate": 7.939743702320149e-06, "loss": 0.2794, "step": 311180 }, { "epoch": 1.8497779838436434, "grad_norm": 4.952272891998291, "learning_rate": 7.939575859782971e-06, "loss": 0.2669, "step": 311190 }, { "epoch": 1.8498374259203119, "grad_norm": 5.612486362457275, "learning_rate": 7.939408012183494e-06, "loss": 0.2892, "step": 311200 }, { "epoch": 1.8498968679969803, "grad_norm": 5.147078037261963, "learning_rate": 7.939240159522004e-06, "loss": 0.3066, "step": 311210 }, { "epoch": 1.8499563100736487, "grad_norm": 5.116408348083496, "learning_rate": 7.939072301798793e-06, "loss": 0.3574, "step": 311220 }, { "epoch": 1.850015752150317, "grad_norm": 4.975276947021484, "learning_rate": 7.93890443901415e-06, "loss": 0.3061, "step": 311230 }, { "epoch": 1.8500751942269855, "grad_norm": 4.7444167137146, "learning_rate": 7.93873657116836e-06, "loss": 0.2999, "step": 311240 }, { "epoch": 1.850134636303654, "grad_norm": 8.567584991455078, "learning_rate": 7.938568698261717e-06, "loss": 0.3058, "step": 311250 }, { "epoch": 1.8501940783803223, "grad_norm": 4.97943639755249, "learning_rate": 7.938400820294508e-06, "loss": 0.3077, "step": 311260 }, { "epoch": 1.8502535204569908, "grad_norm": 5.64597749710083, "learning_rate": 7.93823293726702e-06, "loss": 0.3304, "step": 311270 }, { "epoch": 1.8503129625336592, "grad_norm": 5.920337200164795, "learning_rate": 7.938065049179548e-06, "loss": 0.294, "step": 311280 }, { "epoch": 1.8503724046103276, "grad_norm": 5.6844096183776855, "learning_rate": 7.937897156032375e-06, "loss": 0.3115, "step": 311290 }, { "epoch": 1.850431846686996, "grad_norm": 4.807896137237549, "learning_rate": 7.937729257825792e-06, "loss": 0.2933, "step": 311300 }, { "epoch": 1.8504912887636642, "grad_norm": 6.910105228424072, "learning_rate": 7.93756135456009e-06, "loss": 0.3032, "step": 311310 }, { "epoch": 1.8505507308403326, "grad_norm": 4.751864910125732, "learning_rate": 7.937393446235558e-06, "loss": 0.2593, "step": 311320 }, { "epoch": 1.850610172917001, "grad_norm": 4.430870532989502, "learning_rate": 7.937225532852482e-06, "loss": 0.322, "step": 311330 }, { "epoch": 1.8506696149936694, "grad_norm": 5.58958625793457, "learning_rate": 7.937057614411154e-06, "loss": 0.3059, "step": 311340 }, { "epoch": 1.8507290570703379, "grad_norm": 6.704938888549805, "learning_rate": 7.936889690911861e-06, "loss": 0.2977, "step": 311350 }, { "epoch": 1.850788499147006, "grad_norm": 4.837591648101807, "learning_rate": 7.936721762354895e-06, "loss": 0.3303, "step": 311360 }, { "epoch": 1.8508479412236745, "grad_norm": 4.985513687133789, "learning_rate": 7.936553828740543e-06, "loss": 0.2604, "step": 311370 }, { "epoch": 1.8509073833003429, "grad_norm": 5.580275535583496, "learning_rate": 7.936385890069095e-06, "loss": 0.3122, "step": 311380 }, { "epoch": 1.8509668253770113, "grad_norm": 3.6687674522399902, "learning_rate": 7.93621794634084e-06, "loss": 0.2837, "step": 311390 }, { "epoch": 1.8510262674536797, "grad_norm": 4.7033538818359375, "learning_rate": 7.93604999755607e-06, "loss": 0.2819, "step": 311400 }, { "epoch": 1.8510857095303481, "grad_norm": 5.682621002197266, "learning_rate": 7.93588204371507e-06, "loss": 0.3376, "step": 311410 }, { "epoch": 1.8511451516070165, "grad_norm": 6.779626846313477, "learning_rate": 7.93571408481813e-06, "loss": 0.2962, "step": 311420 }, { "epoch": 1.851204593683685, "grad_norm": 4.821515083312988, "learning_rate": 7.935546120865538e-06, "loss": 0.3067, "step": 311430 }, { "epoch": 1.8512640357603534, "grad_norm": 4.929446697235107, "learning_rate": 7.935378151857588e-06, "loss": 0.3114, "step": 311440 }, { "epoch": 1.8513234778370218, "grad_norm": 6.661805629730225, "learning_rate": 7.935210177794568e-06, "loss": 0.3086, "step": 311450 }, { "epoch": 1.8513829199136902, "grad_norm": 4.712819576263428, "learning_rate": 7.935042198676763e-06, "loss": 0.2917, "step": 311460 }, { "epoch": 1.8514423619903586, "grad_norm": 4.551842212677002, "learning_rate": 7.934874214504465e-06, "loss": 0.3244, "step": 311470 }, { "epoch": 1.851501804067027, "grad_norm": 5.119784355163574, "learning_rate": 7.934706225277965e-06, "loss": 0.3137, "step": 311480 }, { "epoch": 1.8515612461436954, "grad_norm": 5.754343032836914, "learning_rate": 7.93453823099755e-06, "loss": 0.3103, "step": 311490 }, { "epoch": 1.8516206882203636, "grad_norm": 4.880151271820068, "learning_rate": 7.93437023166351e-06, "loss": 0.2788, "step": 311500 }, { "epoch": 1.851680130297032, "grad_norm": 5.683052062988281, "learning_rate": 7.934202227276136e-06, "loss": 0.304, "step": 311510 }, { "epoch": 1.8517395723737005, "grad_norm": 4.396251201629639, "learning_rate": 7.934034217835714e-06, "loss": 0.2838, "step": 311520 }, { "epoch": 1.8517990144503689, "grad_norm": 4.694235324859619, "learning_rate": 7.933866203342535e-06, "loss": 0.2859, "step": 311530 }, { "epoch": 1.851858456527037, "grad_norm": 5.7453694343566895, "learning_rate": 7.93369818379689e-06, "loss": 0.2442, "step": 311540 }, { "epoch": 1.8519178986037055, "grad_norm": 5.568141937255859, "learning_rate": 7.933530159199063e-06, "loss": 0.323, "step": 311550 }, { "epoch": 1.851977340680374, "grad_norm": 4.793238162994385, "learning_rate": 7.93336212954935e-06, "loss": 0.3215, "step": 311560 }, { "epoch": 1.8520367827570423, "grad_norm": 4.7341742515563965, "learning_rate": 7.933194094848036e-06, "loss": 0.301, "step": 311570 }, { "epoch": 1.8520962248337107, "grad_norm": 4.572873592376709, "learning_rate": 7.933026055095413e-06, "loss": 0.2891, "step": 311580 }, { "epoch": 1.8521556669103791, "grad_norm": 6.431449890136719, "learning_rate": 7.932858010291769e-06, "loss": 0.334, "step": 311590 }, { "epoch": 1.8522151089870476, "grad_norm": 3.9534006118774414, "learning_rate": 7.932689960437394e-06, "loss": 0.286, "step": 311600 }, { "epoch": 1.852274551063716, "grad_norm": 5.086085319519043, "learning_rate": 7.932521905532575e-06, "loss": 0.3171, "step": 311610 }, { "epoch": 1.8523339931403844, "grad_norm": 5.067474842071533, "learning_rate": 7.932353845577604e-06, "loss": 0.277, "step": 311620 }, { "epoch": 1.8523934352170528, "grad_norm": 5.505037307739258, "learning_rate": 7.932185780572773e-06, "loss": 0.298, "step": 311630 }, { "epoch": 1.8524528772937212, "grad_norm": 6.03409481048584, "learning_rate": 7.932017710518364e-06, "loss": 0.3054, "step": 311640 }, { "epoch": 1.8525123193703896, "grad_norm": 4.876121520996094, "learning_rate": 7.931849635414672e-06, "loss": 0.2545, "step": 311650 }, { "epoch": 1.852571761447058, "grad_norm": 4.251157760620117, "learning_rate": 7.931681555261985e-06, "loss": 0.296, "step": 311660 }, { "epoch": 1.8526312035237265, "grad_norm": 4.645151138305664, "learning_rate": 7.931513470060594e-06, "loss": 0.2619, "step": 311670 }, { "epoch": 1.8526906456003946, "grad_norm": 4.112975597381592, "learning_rate": 7.931345379810786e-06, "loss": 0.2675, "step": 311680 }, { "epoch": 1.852750087677063, "grad_norm": 5.7219557762146, "learning_rate": 7.931177284512851e-06, "loss": 0.3234, "step": 311690 }, { "epoch": 1.8528095297537315, "grad_norm": 5.476553916931152, "learning_rate": 7.93100918416708e-06, "loss": 0.2503, "step": 311700 }, { "epoch": 1.8528689718304, "grad_norm": 6.375629901885986, "learning_rate": 7.93084107877376e-06, "loss": 0.2909, "step": 311710 }, { "epoch": 1.8529284139070683, "grad_norm": 5.862679958343506, "learning_rate": 7.930672968333183e-06, "loss": 0.3115, "step": 311720 }, { "epoch": 1.8529878559837365, "grad_norm": 5.134749412536621, "learning_rate": 7.930504852845637e-06, "loss": 0.2888, "step": 311730 }, { "epoch": 1.853047298060405, "grad_norm": 5.900571346282959, "learning_rate": 7.930336732311412e-06, "loss": 0.297, "step": 311740 }, { "epoch": 1.8531067401370733, "grad_norm": 5.229781627655029, "learning_rate": 7.9301686067308e-06, "loss": 0.2791, "step": 311750 }, { "epoch": 1.8531661822137417, "grad_norm": 4.5851664543151855, "learning_rate": 7.930000476104084e-06, "loss": 0.2986, "step": 311760 }, { "epoch": 1.8532256242904102, "grad_norm": 4.690115928649902, "learning_rate": 7.92983234043156e-06, "loss": 0.3431, "step": 311770 }, { "epoch": 1.8532850663670786, "grad_norm": 6.413808345794678, "learning_rate": 7.929664199713514e-06, "loss": 0.3076, "step": 311780 }, { "epoch": 1.853344508443747, "grad_norm": 5.002403259277344, "learning_rate": 7.929496053950237e-06, "loss": 0.296, "step": 311790 }, { "epoch": 1.8534039505204154, "grad_norm": 3.9563424587249756, "learning_rate": 7.929327903142018e-06, "loss": 0.3251, "step": 311800 }, { "epoch": 1.8534633925970838, "grad_norm": 4.8213067054748535, "learning_rate": 7.929159747289147e-06, "loss": 0.2638, "step": 311810 }, { "epoch": 1.8535228346737522, "grad_norm": 4.171972751617432, "learning_rate": 7.928991586391914e-06, "loss": 0.2977, "step": 311820 }, { "epoch": 1.8535822767504206, "grad_norm": 5.531715393066406, "learning_rate": 7.928823420450608e-06, "loss": 0.2717, "step": 311830 }, { "epoch": 1.853641718827089, "grad_norm": 5.015157699584961, "learning_rate": 7.928655249465519e-06, "loss": 0.2747, "step": 311840 }, { "epoch": 1.8537011609037575, "grad_norm": 4.819775104522705, "learning_rate": 7.928487073436936e-06, "loss": 0.305, "step": 311850 }, { "epoch": 1.8537606029804259, "grad_norm": 4.060586452484131, "learning_rate": 7.928318892365147e-06, "loss": 0.2815, "step": 311860 }, { "epoch": 1.853820045057094, "grad_norm": 4.396872043609619, "learning_rate": 7.928150706250447e-06, "loss": 0.309, "step": 311870 }, { "epoch": 1.8538794871337625, "grad_norm": 3.899435043334961, "learning_rate": 7.927982515093119e-06, "loss": 0.3174, "step": 311880 }, { "epoch": 1.853938929210431, "grad_norm": 6.213933944702148, "learning_rate": 7.927814318893456e-06, "loss": 0.3185, "step": 311890 }, { "epoch": 1.8539983712870993, "grad_norm": 4.899520397186279, "learning_rate": 7.927646117651749e-06, "loss": 0.3099, "step": 311900 }, { "epoch": 1.8540578133637675, "grad_norm": 3.907870292663574, "learning_rate": 7.927477911368285e-06, "loss": 0.2867, "step": 311910 }, { "epoch": 1.854117255440436, "grad_norm": 5.41591739654541, "learning_rate": 7.927309700043355e-06, "loss": 0.2908, "step": 311920 }, { "epoch": 1.8541766975171043, "grad_norm": 5.289614677429199, "learning_rate": 7.927141483677247e-06, "loss": 0.2797, "step": 311930 }, { "epoch": 1.8542361395937728, "grad_norm": 5.438940048217773, "learning_rate": 7.926973262270254e-06, "loss": 0.3028, "step": 311940 }, { "epoch": 1.8542955816704412, "grad_norm": 4.069793224334717, "learning_rate": 7.926805035822664e-06, "loss": 0.3223, "step": 311950 }, { "epoch": 1.8543550237471096, "grad_norm": 3.247098922729492, "learning_rate": 7.926636804334767e-06, "loss": 0.3163, "step": 311960 }, { "epoch": 1.854414465823778, "grad_norm": 5.250521659851074, "learning_rate": 7.926468567806849e-06, "loss": 0.3013, "step": 311970 }, { "epoch": 1.8544739079004464, "grad_norm": 5.869739055633545, "learning_rate": 7.926300326239204e-06, "loss": 0.3417, "step": 311980 }, { "epoch": 1.8545333499771148, "grad_norm": 4.380629539489746, "learning_rate": 7.926132079632123e-06, "loss": 0.296, "step": 311990 }, { "epoch": 1.8545927920537832, "grad_norm": 4.620114326477051, "learning_rate": 7.925963827985892e-06, "loss": 0.3049, "step": 312000 }, { "epoch": 1.8546522341304517, "grad_norm": 4.756225109100342, "learning_rate": 7.925795571300801e-06, "loss": 0.3131, "step": 312010 }, { "epoch": 1.85471167620712, "grad_norm": 5.16274881362915, "learning_rate": 7.925627309577144e-06, "loss": 0.2854, "step": 312020 }, { "epoch": 1.8547711182837885, "grad_norm": 5.905802249908447, "learning_rate": 7.925459042815205e-06, "loss": 0.2765, "step": 312030 }, { "epoch": 1.854830560360457, "grad_norm": 4.382707595825195, "learning_rate": 7.925290771015277e-06, "loss": 0.2662, "step": 312040 }, { "epoch": 1.854890002437125, "grad_norm": 5.419487953186035, "learning_rate": 7.92512249417765e-06, "loss": 0.3095, "step": 312050 }, { "epoch": 1.8549494445137935, "grad_norm": 3.738489866256714, "learning_rate": 7.924954212302612e-06, "loss": 0.2849, "step": 312060 }, { "epoch": 1.855008886590462, "grad_norm": 5.435583114624023, "learning_rate": 7.924785925390454e-06, "loss": 0.2798, "step": 312070 }, { "epoch": 1.8550683286671303, "grad_norm": 5.66477632522583, "learning_rate": 7.924617633441467e-06, "loss": 0.3036, "step": 312080 }, { "epoch": 1.8551277707437988, "grad_norm": 4.052591323852539, "learning_rate": 7.92444933645594e-06, "loss": 0.3079, "step": 312090 }, { "epoch": 1.855187212820467, "grad_norm": 3.7637064456939697, "learning_rate": 7.924281034434159e-06, "loss": 0.3004, "step": 312100 }, { "epoch": 1.8552466548971354, "grad_norm": 5.166083335876465, "learning_rate": 7.92411272737642e-06, "loss": 0.2749, "step": 312110 }, { "epoch": 1.8553060969738038, "grad_norm": 4.749144077301025, "learning_rate": 7.923944415283008e-06, "loss": 0.2697, "step": 312120 }, { "epoch": 1.8553655390504722, "grad_norm": 5.029067516326904, "learning_rate": 7.923776098154215e-06, "loss": 0.2559, "step": 312130 }, { "epoch": 1.8554249811271406, "grad_norm": 5.272529125213623, "learning_rate": 7.923607775990331e-06, "loss": 0.286, "step": 312140 }, { "epoch": 1.855484423203809, "grad_norm": 4.725042819976807, "learning_rate": 7.923439448791648e-06, "loss": 0.2743, "step": 312150 }, { "epoch": 1.8555438652804774, "grad_norm": 4.651412487030029, "learning_rate": 7.92327111655845e-06, "loss": 0.2899, "step": 312160 }, { "epoch": 1.8556033073571458, "grad_norm": 6.171031951904297, "learning_rate": 7.923102779291032e-06, "loss": 0.3061, "step": 312170 }, { "epoch": 1.8556627494338143, "grad_norm": 3.8249876499176025, "learning_rate": 7.922934436989683e-06, "loss": 0.3066, "step": 312180 }, { "epoch": 1.8557221915104827, "grad_norm": 4.982243061065674, "learning_rate": 7.92276608965469e-06, "loss": 0.2814, "step": 312190 }, { "epoch": 1.855781633587151, "grad_norm": 4.756347179412842, "learning_rate": 7.922597737286349e-06, "loss": 0.2879, "step": 312200 }, { "epoch": 1.8558410756638195, "grad_norm": 5.551219463348389, "learning_rate": 7.922429379884942e-06, "loss": 0.325, "step": 312210 }, { "epoch": 1.855900517740488, "grad_norm": 4.498708724975586, "learning_rate": 7.922261017450765e-06, "loss": 0.2923, "step": 312220 }, { "epoch": 1.8559599598171563, "grad_norm": 5.976160049438477, "learning_rate": 7.922092649984103e-06, "loss": 0.2764, "step": 312230 }, { "epoch": 1.8560194018938245, "grad_norm": 7.4020676612854, "learning_rate": 7.921924277485251e-06, "loss": 0.2793, "step": 312240 }, { "epoch": 1.856078843970493, "grad_norm": 5.169104099273682, "learning_rate": 7.921755899954498e-06, "loss": 0.3052, "step": 312250 }, { "epoch": 1.8561382860471614, "grad_norm": 5.154206275939941, "learning_rate": 7.92158751739213e-06, "loss": 0.2919, "step": 312260 }, { "epoch": 1.8561977281238298, "grad_norm": 4.724036693572998, "learning_rate": 7.921419129798442e-06, "loss": 0.2703, "step": 312270 }, { "epoch": 1.856257170200498, "grad_norm": 3.4766128063201904, "learning_rate": 7.92125073717372e-06, "loss": 0.2817, "step": 312280 }, { "epoch": 1.8563166122771664, "grad_norm": 3.9247827529907227, "learning_rate": 7.921082339518256e-06, "loss": 0.2617, "step": 312290 }, { "epoch": 1.8563760543538348, "grad_norm": 5.509608745574951, "learning_rate": 7.92091393683234e-06, "loss": 0.3001, "step": 312300 }, { "epoch": 1.8564354964305032, "grad_norm": 5.998761177062988, "learning_rate": 7.920745529116263e-06, "loss": 0.3278, "step": 312310 }, { "epoch": 1.8564949385071716, "grad_norm": 3.851301431655884, "learning_rate": 7.920577116370311e-06, "loss": 0.2839, "step": 312320 }, { "epoch": 1.85655438058384, "grad_norm": 5.254720687866211, "learning_rate": 7.920408698594778e-06, "loss": 0.309, "step": 312330 }, { "epoch": 1.8566138226605085, "grad_norm": 3.851123332977295, "learning_rate": 7.920240275789954e-06, "loss": 0.2896, "step": 312340 }, { "epoch": 1.8566732647371769, "grad_norm": 4.5279645919799805, "learning_rate": 7.920071847956126e-06, "loss": 0.2836, "step": 312350 }, { "epoch": 1.8567327068138453, "grad_norm": 5.985663414001465, "learning_rate": 7.919903415093587e-06, "loss": 0.3165, "step": 312360 }, { "epoch": 1.8567921488905137, "grad_norm": 5.753923416137695, "learning_rate": 7.919734977202625e-06, "loss": 0.3115, "step": 312370 }, { "epoch": 1.856851590967182, "grad_norm": 6.105908393859863, "learning_rate": 7.919566534283531e-06, "loss": 0.2937, "step": 312380 }, { "epoch": 1.8569110330438505, "grad_norm": 4.003360271453857, "learning_rate": 7.919398086336596e-06, "loss": 0.2968, "step": 312390 }, { "epoch": 1.856970475120519, "grad_norm": 4.415903568267822, "learning_rate": 7.919229633362108e-06, "loss": 0.2992, "step": 312400 }, { "epoch": 1.8570299171971874, "grad_norm": 4.961636066436768, "learning_rate": 7.91906117536036e-06, "loss": 0.2858, "step": 312410 }, { "epoch": 1.8570893592738555, "grad_norm": 4.121146202087402, "learning_rate": 7.91889271233164e-06, "loss": 0.3001, "step": 312420 }, { "epoch": 1.857148801350524, "grad_norm": 5.351988315582275, "learning_rate": 7.918724244276238e-06, "loss": 0.2833, "step": 312430 }, { "epoch": 1.8572082434271924, "grad_norm": 4.889526844024658, "learning_rate": 7.918555771194445e-06, "loss": 0.304, "step": 312440 }, { "epoch": 1.8572676855038608, "grad_norm": 6.192137241363525, "learning_rate": 7.918387293086549e-06, "loss": 0.3099, "step": 312450 }, { "epoch": 1.8573271275805292, "grad_norm": 4.823328018188477, "learning_rate": 7.918218809952842e-06, "loss": 0.3317, "step": 312460 }, { "epoch": 1.8573865696571974, "grad_norm": 5.824995994567871, "learning_rate": 7.918050321793615e-06, "loss": 0.305, "step": 312470 }, { "epoch": 1.8574460117338658, "grad_norm": 5.232779502868652, "learning_rate": 7.917881828609158e-06, "loss": 0.2749, "step": 312480 }, { "epoch": 1.8575054538105342, "grad_norm": 3.8863720893859863, "learning_rate": 7.91771333039976e-06, "loss": 0.2922, "step": 312490 }, { "epoch": 1.8575648958872026, "grad_norm": 5.84822940826416, "learning_rate": 7.91754482716571e-06, "loss": 0.2809, "step": 312500 }, { "epoch": 1.857624337963871, "grad_norm": 5.118844985961914, "learning_rate": 7.917376318907302e-06, "loss": 0.2726, "step": 312510 }, { "epoch": 1.8576837800405395, "grad_norm": 4.530570030212402, "learning_rate": 7.917207805624822e-06, "loss": 0.2915, "step": 312520 }, { "epoch": 1.8577432221172079, "grad_norm": 6.175412178039551, "learning_rate": 7.917039287318562e-06, "loss": 0.2628, "step": 312530 }, { "epoch": 1.8578026641938763, "grad_norm": 4.715901851654053, "learning_rate": 7.916870763988814e-06, "loss": 0.2976, "step": 312540 }, { "epoch": 1.8578621062705447, "grad_norm": 4.232208728790283, "learning_rate": 7.916702235635864e-06, "loss": 0.3103, "step": 312550 }, { "epoch": 1.8579215483472131, "grad_norm": 5.373734951019287, "learning_rate": 7.916533702260007e-06, "loss": 0.3139, "step": 312560 }, { "epoch": 1.8579809904238815, "grad_norm": 4.406471252441406, "learning_rate": 7.91636516386153e-06, "loss": 0.2697, "step": 312570 }, { "epoch": 1.85804043250055, "grad_norm": 4.4938201904296875, "learning_rate": 7.916196620440725e-06, "loss": 0.3044, "step": 312580 }, { "epoch": 1.8580998745772184, "grad_norm": 5.367587566375732, "learning_rate": 7.916028071997882e-06, "loss": 0.3291, "step": 312590 }, { "epoch": 1.8581593166538868, "grad_norm": 7.05778694152832, "learning_rate": 7.915859518533288e-06, "loss": 0.2947, "step": 312600 }, { "epoch": 1.858218758730555, "grad_norm": 5.093360424041748, "learning_rate": 7.915690960047238e-06, "loss": 0.2785, "step": 312610 }, { "epoch": 1.8582782008072234, "grad_norm": 3.8721702098846436, "learning_rate": 7.91552239654002e-06, "loss": 0.28, "step": 312620 }, { "epoch": 1.8583376428838918, "grad_norm": 5.54969596862793, "learning_rate": 7.915353828011925e-06, "loss": 0.3154, "step": 312630 }, { "epoch": 1.8583970849605602, "grad_norm": 5.393261432647705, "learning_rate": 7.915185254463242e-06, "loss": 0.2916, "step": 312640 }, { "epoch": 1.8584565270372284, "grad_norm": 5.177107334136963, "learning_rate": 7.915016675894262e-06, "loss": 0.2828, "step": 312650 }, { "epoch": 1.8585159691138968, "grad_norm": 4.142536640167236, "learning_rate": 7.914848092305277e-06, "loss": 0.2868, "step": 312660 }, { "epoch": 1.8585754111905652, "grad_norm": 4.067905902862549, "learning_rate": 7.914679503696573e-06, "loss": 0.2792, "step": 312670 }, { "epoch": 1.8586348532672337, "grad_norm": 3.924234390258789, "learning_rate": 7.914510910068446e-06, "loss": 0.3022, "step": 312680 }, { "epoch": 1.858694295343902, "grad_norm": 6.409358978271484, "learning_rate": 7.914342311421182e-06, "loss": 0.3277, "step": 312690 }, { "epoch": 1.8587537374205705, "grad_norm": 5.189189910888672, "learning_rate": 7.914173707755073e-06, "loss": 0.2814, "step": 312700 }, { "epoch": 1.858813179497239, "grad_norm": 5.039433002471924, "learning_rate": 7.91400509907041e-06, "loss": 0.2798, "step": 312710 }, { "epoch": 1.8588726215739073, "grad_norm": 5.4070611000061035, "learning_rate": 7.91383648536748e-06, "loss": 0.3252, "step": 312720 }, { "epoch": 1.8589320636505757, "grad_norm": 5.27243185043335, "learning_rate": 7.913667866646578e-06, "loss": 0.3034, "step": 312730 }, { "epoch": 1.8589915057272441, "grad_norm": 4.89142370223999, "learning_rate": 7.913499242907992e-06, "loss": 0.3156, "step": 312740 }, { "epoch": 1.8590509478039126, "grad_norm": 4.247326374053955, "learning_rate": 7.913330614152012e-06, "loss": 0.2987, "step": 312750 }, { "epoch": 1.859110389880581, "grad_norm": 5.0294952392578125, "learning_rate": 7.91316198037893e-06, "loss": 0.3065, "step": 312760 }, { "epoch": 1.8591698319572494, "grad_norm": 6.050943374633789, "learning_rate": 7.912993341589036e-06, "loss": 0.3099, "step": 312770 }, { "epoch": 1.8592292740339178, "grad_norm": 5.344635009765625, "learning_rate": 7.912824697782617e-06, "loss": 0.2802, "step": 312780 }, { "epoch": 1.859288716110586, "grad_norm": 5.857929706573486, "learning_rate": 7.91265604895997e-06, "loss": 0.2995, "step": 312790 }, { "epoch": 1.8593481581872544, "grad_norm": 4.604107856750488, "learning_rate": 7.91248739512138e-06, "loss": 0.2842, "step": 312800 }, { "epoch": 1.8594076002639228, "grad_norm": 5.283094882965088, "learning_rate": 7.91231873626714e-06, "loss": 0.3153, "step": 312810 }, { "epoch": 1.8594670423405912, "grad_norm": 5.189690589904785, "learning_rate": 7.912150072397538e-06, "loss": 0.3215, "step": 312820 }, { "epoch": 1.8595264844172597, "grad_norm": 4.279938697814941, "learning_rate": 7.911981403512867e-06, "loss": 0.2963, "step": 312830 }, { "epoch": 1.8595859264939278, "grad_norm": 4.524014949798584, "learning_rate": 7.911812729613417e-06, "loss": 0.294, "step": 312840 }, { "epoch": 1.8596453685705963, "grad_norm": 5.382680892944336, "learning_rate": 7.911644050699478e-06, "loss": 0.2888, "step": 312850 }, { "epoch": 1.8597048106472647, "grad_norm": 5.657503604888916, "learning_rate": 7.91147536677134e-06, "loss": 0.299, "step": 312860 }, { "epoch": 1.859764252723933, "grad_norm": 4.621780872344971, "learning_rate": 7.911306677829293e-06, "loss": 0.2959, "step": 312870 }, { "epoch": 1.8598236948006015, "grad_norm": 4.371861457824707, "learning_rate": 7.911137983873631e-06, "loss": 0.3201, "step": 312880 }, { "epoch": 1.85988313687727, "grad_norm": 4.075015068054199, "learning_rate": 7.91096928490464e-06, "loss": 0.2898, "step": 312890 }, { "epoch": 1.8599425789539383, "grad_norm": 5.367698669433594, "learning_rate": 7.910800580922613e-06, "loss": 0.2956, "step": 312900 }, { "epoch": 1.8600020210306067, "grad_norm": 4.143235683441162, "learning_rate": 7.91063187192784e-06, "loss": 0.2855, "step": 312910 }, { "epoch": 1.8600614631072752, "grad_norm": 4.07320499420166, "learning_rate": 7.910463157920613e-06, "loss": 0.2993, "step": 312920 }, { "epoch": 1.8601209051839436, "grad_norm": 3.584131956100464, "learning_rate": 7.910294438901221e-06, "loss": 0.3076, "step": 312930 }, { "epoch": 1.860180347260612, "grad_norm": 3.8614871501922607, "learning_rate": 7.910125714869953e-06, "loss": 0.3205, "step": 312940 }, { "epoch": 1.8602397893372804, "grad_norm": 5.360653877258301, "learning_rate": 7.909956985827104e-06, "loss": 0.2904, "step": 312950 }, { "epoch": 1.8602992314139488, "grad_norm": 4.748258113861084, "learning_rate": 7.909788251772958e-06, "loss": 0.2946, "step": 312960 }, { "epoch": 1.8603586734906172, "grad_norm": 7.053566932678223, "learning_rate": 7.909619512707813e-06, "loss": 0.31, "step": 312970 }, { "epoch": 1.8604181155672854, "grad_norm": 5.70904541015625, "learning_rate": 7.909450768631955e-06, "loss": 0.3218, "step": 312980 }, { "epoch": 1.8604775576439538, "grad_norm": 3.7965505123138428, "learning_rate": 7.909282019545675e-06, "loss": 0.2704, "step": 312990 }, { "epoch": 1.8605369997206223, "grad_norm": 5.522299766540527, "learning_rate": 7.909113265449264e-06, "loss": 0.3085, "step": 313000 }, { "epoch": 1.8605964417972907, "grad_norm": 4.919764995574951, "learning_rate": 7.908944506343013e-06, "loss": 0.3046, "step": 313010 }, { "epoch": 1.8606558838739589, "grad_norm": 4.502647876739502, "learning_rate": 7.908775742227212e-06, "loss": 0.2756, "step": 313020 }, { "epoch": 1.8607153259506273, "grad_norm": 5.522839069366455, "learning_rate": 7.908606973102154e-06, "loss": 0.3049, "step": 313030 }, { "epoch": 1.8607747680272957, "grad_norm": 4.724249839782715, "learning_rate": 7.908438198968125e-06, "loss": 0.2725, "step": 313040 }, { "epoch": 1.860834210103964, "grad_norm": 4.728402137756348, "learning_rate": 7.908269419825421e-06, "loss": 0.2903, "step": 313050 }, { "epoch": 1.8608936521806325, "grad_norm": 4.50628137588501, "learning_rate": 7.90810063567433e-06, "loss": 0.2998, "step": 313060 }, { "epoch": 1.860953094257301, "grad_norm": 5.148639678955078, "learning_rate": 7.907931846515142e-06, "loss": 0.2784, "step": 313070 }, { "epoch": 1.8610125363339693, "grad_norm": 4.754964351654053, "learning_rate": 7.907763052348147e-06, "loss": 0.2748, "step": 313080 }, { "epoch": 1.8610719784106378, "grad_norm": 4.457826614379883, "learning_rate": 7.907594253173639e-06, "loss": 0.2993, "step": 313090 }, { "epoch": 1.8611314204873062, "grad_norm": 5.244484901428223, "learning_rate": 7.907425448991906e-06, "loss": 0.325, "step": 313100 }, { "epoch": 1.8611908625639746, "grad_norm": 5.926239490509033, "learning_rate": 7.907256639803238e-06, "loss": 0.3283, "step": 313110 }, { "epoch": 1.861250304640643, "grad_norm": 5.410607814788818, "learning_rate": 7.907087825607929e-06, "loss": 0.2943, "step": 313120 }, { "epoch": 1.8613097467173114, "grad_norm": 4.815643310546875, "learning_rate": 7.906919006406269e-06, "loss": 0.2694, "step": 313130 }, { "epoch": 1.8613691887939798, "grad_norm": 4.668244361877441, "learning_rate": 7.906750182198546e-06, "loss": 0.325, "step": 313140 }, { "epoch": 1.8614286308706482, "grad_norm": 7.068449974060059, "learning_rate": 7.906581352985053e-06, "loss": 0.2989, "step": 313150 }, { "epoch": 1.8614880729473164, "grad_norm": 5.128065586090088, "learning_rate": 7.906412518766078e-06, "loss": 0.3246, "step": 313160 }, { "epoch": 1.8615475150239849, "grad_norm": 6.718605995178223, "learning_rate": 7.906243679541916e-06, "loss": 0.3489, "step": 313170 }, { "epoch": 1.8616069571006533, "grad_norm": 5.607481956481934, "learning_rate": 7.906074835312855e-06, "loss": 0.33, "step": 313180 }, { "epoch": 1.8616663991773217, "grad_norm": 5.404152870178223, "learning_rate": 7.905905986079186e-06, "loss": 0.3239, "step": 313190 }, { "epoch": 1.86172584125399, "grad_norm": 4.124892234802246, "learning_rate": 7.9057371318412e-06, "loss": 0.2789, "step": 313200 }, { "epoch": 1.8617852833306583, "grad_norm": 5.547064781188965, "learning_rate": 7.90556827259919e-06, "loss": 0.2523, "step": 313210 }, { "epoch": 1.8618447254073267, "grad_norm": 5.471535682678223, "learning_rate": 7.905399408353443e-06, "loss": 0.2655, "step": 313220 }, { "epoch": 1.8619041674839951, "grad_norm": 6.52700662612915, "learning_rate": 7.905230539104252e-06, "loss": 0.2913, "step": 313230 }, { "epoch": 1.8619636095606635, "grad_norm": 5.7874064445495605, "learning_rate": 7.905061664851908e-06, "loss": 0.2801, "step": 313240 }, { "epoch": 1.862023051637332, "grad_norm": 5.254646301269531, "learning_rate": 7.9048927855967e-06, "loss": 0.2906, "step": 313250 }, { "epoch": 1.8620824937140004, "grad_norm": 5.5418314933776855, "learning_rate": 7.90472390133892e-06, "loss": 0.2883, "step": 313260 }, { "epoch": 1.8621419357906688, "grad_norm": 4.976274013519287, "learning_rate": 7.90455501207886e-06, "loss": 0.263, "step": 313270 }, { "epoch": 1.8622013778673372, "grad_norm": 5.7956438064575195, "learning_rate": 7.90438611781681e-06, "loss": 0.2893, "step": 313280 }, { "epoch": 1.8622608199440056, "grad_norm": 4.014992713928223, "learning_rate": 7.904217218553058e-06, "loss": 0.2909, "step": 313290 }, { "epoch": 1.862320262020674, "grad_norm": 6.751459121704102, "learning_rate": 7.9040483142879e-06, "loss": 0.3016, "step": 313300 }, { "epoch": 1.8623797040973424, "grad_norm": 5.084506988525391, "learning_rate": 7.903879405021623e-06, "loss": 0.3058, "step": 313310 }, { "epoch": 1.8624391461740109, "grad_norm": 5.703866004943848, "learning_rate": 7.903710490754519e-06, "loss": 0.2901, "step": 313320 }, { "epoch": 1.8624985882506793, "grad_norm": 4.428325176239014, "learning_rate": 7.903541571486879e-06, "loss": 0.2481, "step": 313330 }, { "epoch": 1.8625580303273477, "grad_norm": 4.764927387237549, "learning_rate": 7.903372647218994e-06, "loss": 0.2768, "step": 313340 }, { "epoch": 1.8626174724040159, "grad_norm": 5.39029598236084, "learning_rate": 7.903203717951156e-06, "loss": 0.3308, "step": 313350 }, { "epoch": 1.8626769144806843, "grad_norm": 4.074028968811035, "learning_rate": 7.903034783683655e-06, "loss": 0.2801, "step": 313360 }, { "epoch": 1.8627363565573527, "grad_norm": 6.232341766357422, "learning_rate": 7.90286584441678e-06, "loss": 0.2949, "step": 313370 }, { "epoch": 1.8627957986340211, "grad_norm": 4.760274410247803, "learning_rate": 7.902696900150826e-06, "loss": 0.2873, "step": 313380 }, { "epoch": 1.8628552407106893, "grad_norm": 6.169244766235352, "learning_rate": 7.90252795088608e-06, "loss": 0.3075, "step": 313390 }, { "epoch": 1.8629146827873577, "grad_norm": 6.004775524139404, "learning_rate": 7.902358996622834e-06, "loss": 0.3286, "step": 313400 }, { "epoch": 1.8629741248640261, "grad_norm": 6.368932723999023, "learning_rate": 7.90219003736138e-06, "loss": 0.3174, "step": 313410 }, { "epoch": 1.8630335669406946, "grad_norm": 4.167980670928955, "learning_rate": 7.902021073102009e-06, "loss": 0.2886, "step": 313420 }, { "epoch": 1.863093009017363, "grad_norm": 4.017163276672363, "learning_rate": 7.901852103845011e-06, "loss": 0.2649, "step": 313430 }, { "epoch": 1.8631524510940314, "grad_norm": 5.086264133453369, "learning_rate": 7.901683129590679e-06, "loss": 0.3121, "step": 313440 }, { "epoch": 1.8632118931706998, "grad_norm": 4.396274566650391, "learning_rate": 7.9015141503393e-06, "loss": 0.2929, "step": 313450 }, { "epoch": 1.8632713352473682, "grad_norm": 6.476277828216553, "learning_rate": 7.901345166091168e-06, "loss": 0.2987, "step": 313460 }, { "epoch": 1.8633307773240366, "grad_norm": 4.698375701904297, "learning_rate": 7.901176176846574e-06, "loss": 0.2791, "step": 313470 }, { "epoch": 1.863390219400705, "grad_norm": 6.580660343170166, "learning_rate": 7.90100718260581e-06, "loss": 0.3183, "step": 313480 }, { "epoch": 1.8634496614773735, "grad_norm": 7.766757488250732, "learning_rate": 7.900838183369161e-06, "loss": 0.3506, "step": 313490 }, { "epoch": 1.8635091035540419, "grad_norm": 5.190940856933594, "learning_rate": 7.900669179136927e-06, "loss": 0.301, "step": 313500 }, { "epoch": 1.8635685456307103, "grad_norm": 5.979158401489258, "learning_rate": 7.900500169909393e-06, "loss": 0.2723, "step": 313510 }, { "epoch": 1.8636279877073787, "grad_norm": 3.38784122467041, "learning_rate": 7.90033115568685e-06, "loss": 0.3031, "step": 313520 }, { "epoch": 1.863687429784047, "grad_norm": 4.786421775817871, "learning_rate": 7.900162136469593e-06, "loss": 0.2793, "step": 313530 }, { "epoch": 1.8637468718607153, "grad_norm": 6.68419885635376, "learning_rate": 7.899993112257912e-06, "loss": 0.2914, "step": 313540 }, { "epoch": 1.8638063139373837, "grad_norm": 5.925723075866699, "learning_rate": 7.899824083052093e-06, "loss": 0.2923, "step": 313550 }, { "epoch": 1.8638657560140521, "grad_norm": 4.297068119049072, "learning_rate": 7.899655048852432e-06, "loss": 0.286, "step": 313560 }, { "epoch": 1.8639251980907205, "grad_norm": 5.793020725250244, "learning_rate": 7.899486009659221e-06, "loss": 0.3004, "step": 313570 }, { "epoch": 1.8639846401673887, "grad_norm": 4.458331108093262, "learning_rate": 7.899316965472747e-06, "loss": 0.3065, "step": 313580 }, { "epoch": 1.8640440822440572, "grad_norm": 5.154873371124268, "learning_rate": 7.899147916293304e-06, "loss": 0.3072, "step": 313590 }, { "epoch": 1.8641035243207256, "grad_norm": 4.513192653656006, "learning_rate": 7.898978862121182e-06, "loss": 0.2941, "step": 313600 }, { "epoch": 1.864162966397394, "grad_norm": 3.7605440616607666, "learning_rate": 7.898809802956674e-06, "loss": 0.263, "step": 313610 }, { "epoch": 1.8642224084740624, "grad_norm": 5.459580898284912, "learning_rate": 7.898640738800069e-06, "loss": 0.2937, "step": 313620 }, { "epoch": 1.8642818505507308, "grad_norm": 6.087914943695068, "learning_rate": 7.89847166965166e-06, "loss": 0.2899, "step": 313630 }, { "epoch": 1.8643412926273992, "grad_norm": 5.708076000213623, "learning_rate": 7.898302595511734e-06, "loss": 0.2886, "step": 313640 }, { "epoch": 1.8644007347040676, "grad_norm": 6.772042751312256, "learning_rate": 7.898133516380585e-06, "loss": 0.3435, "step": 313650 }, { "epoch": 1.864460176780736, "grad_norm": 4.8725080490112305, "learning_rate": 7.897964432258507e-06, "loss": 0.2793, "step": 313660 }, { "epoch": 1.8645196188574045, "grad_norm": 4.661799430847168, "learning_rate": 7.897795343145787e-06, "loss": 0.3176, "step": 313670 }, { "epoch": 1.8645790609340729, "grad_norm": 4.976499080657959, "learning_rate": 7.897626249042718e-06, "loss": 0.3228, "step": 313680 }, { "epoch": 1.8646385030107413, "grad_norm": 5.238734245300293, "learning_rate": 7.89745714994959e-06, "loss": 0.2647, "step": 313690 }, { "epoch": 1.8646979450874097, "grad_norm": 3.8765029907226562, "learning_rate": 7.897288045866697e-06, "loss": 0.2882, "step": 313700 }, { "epoch": 1.8647573871640781, "grad_norm": 5.21824836730957, "learning_rate": 7.897118936794327e-06, "loss": 0.2952, "step": 313710 }, { "epoch": 1.8648168292407463, "grad_norm": 4.314304828643799, "learning_rate": 7.896949822732773e-06, "loss": 0.2866, "step": 313720 }, { "epoch": 1.8648762713174147, "grad_norm": 6.730947494506836, "learning_rate": 7.896780703682325e-06, "loss": 0.2588, "step": 313730 }, { "epoch": 1.8649357133940831, "grad_norm": 4.215394020080566, "learning_rate": 7.896611579643275e-06, "loss": 0.2738, "step": 313740 }, { "epoch": 1.8649951554707516, "grad_norm": 4.139670372009277, "learning_rate": 7.896442450615915e-06, "loss": 0.2809, "step": 313750 }, { "epoch": 1.8650545975474198, "grad_norm": 4.097324848175049, "learning_rate": 7.896273316600536e-06, "loss": 0.315, "step": 313760 }, { "epoch": 1.8651140396240882, "grad_norm": 3.4183363914489746, "learning_rate": 7.896104177597425e-06, "loss": 0.2625, "step": 313770 }, { "epoch": 1.8651734817007566, "grad_norm": 5.6551995277404785, "learning_rate": 7.89593503360688e-06, "loss": 0.3005, "step": 313780 }, { "epoch": 1.865232923777425, "grad_norm": 4.270252704620361, "learning_rate": 7.895765884629192e-06, "loss": 0.2696, "step": 313790 }, { "epoch": 1.8652923658540934, "grad_norm": 4.9244256019592285, "learning_rate": 7.895596730664646e-06, "loss": 0.2811, "step": 313800 }, { "epoch": 1.8653518079307618, "grad_norm": 4.544763088226318, "learning_rate": 7.895427571713537e-06, "loss": 0.2792, "step": 313810 }, { "epoch": 1.8654112500074302, "grad_norm": 3.9003684520721436, "learning_rate": 7.89525840777616e-06, "loss": 0.301, "step": 313820 }, { "epoch": 1.8654706920840987, "grad_norm": 6.901137828826904, "learning_rate": 7.895089238852798e-06, "loss": 0.3175, "step": 313830 }, { "epoch": 1.865530134160767, "grad_norm": 3.8074023723602295, "learning_rate": 7.894920064943747e-06, "loss": 0.2952, "step": 313840 }, { "epoch": 1.8655895762374355, "grad_norm": 5.619516849517822, "learning_rate": 7.8947508860493e-06, "loss": 0.2852, "step": 313850 }, { "epoch": 1.865649018314104, "grad_norm": 4.985283851623535, "learning_rate": 7.894581702169748e-06, "loss": 0.2857, "step": 313860 }, { "epoch": 1.8657084603907723, "grad_norm": 4.62223482131958, "learning_rate": 7.894412513305378e-06, "loss": 0.2732, "step": 313870 }, { "epoch": 1.8657679024674407, "grad_norm": 4.2618408203125, "learning_rate": 7.894243319456486e-06, "loss": 0.2717, "step": 313880 }, { "epoch": 1.8658273445441091, "grad_norm": 5.55839729309082, "learning_rate": 7.89407412062336e-06, "loss": 0.2871, "step": 313890 }, { "epoch": 1.8658867866207773, "grad_norm": 3.8512144088745117, "learning_rate": 7.893904916806295e-06, "loss": 0.2829, "step": 313900 }, { "epoch": 1.8659462286974458, "grad_norm": 6.378754138946533, "learning_rate": 7.893735708005582e-06, "loss": 0.2997, "step": 313910 }, { "epoch": 1.8660056707741142, "grad_norm": 4.794705867767334, "learning_rate": 7.893566494221507e-06, "loss": 0.2841, "step": 313920 }, { "epoch": 1.8660651128507826, "grad_norm": 5.524451732635498, "learning_rate": 7.893397275454367e-06, "loss": 0.3042, "step": 313930 }, { "epoch": 1.866124554927451, "grad_norm": 5.289044380187988, "learning_rate": 7.89322805170445e-06, "loss": 0.325, "step": 313940 }, { "epoch": 1.8661839970041192, "grad_norm": 4.672050476074219, "learning_rate": 7.893058822972052e-06, "loss": 0.2691, "step": 313950 }, { "epoch": 1.8662434390807876, "grad_norm": 5.0485029220581055, "learning_rate": 7.89288958925746e-06, "loss": 0.3365, "step": 313960 }, { "epoch": 1.866302881157456, "grad_norm": 5.081357479095459, "learning_rate": 7.892720350560968e-06, "loss": 0.2869, "step": 313970 }, { "epoch": 1.8663623232341244, "grad_norm": 4.605602264404297, "learning_rate": 7.892551106882865e-06, "loss": 0.2819, "step": 313980 }, { "epoch": 1.8664217653107928, "grad_norm": 4.879775524139404, "learning_rate": 7.892381858223444e-06, "loss": 0.2917, "step": 313990 }, { "epoch": 1.8664812073874613, "grad_norm": 3.6938750743865967, "learning_rate": 7.892212604582997e-06, "loss": 0.2708, "step": 314000 }, { "epoch": 1.8665406494641297, "grad_norm": 5.551475524902344, "learning_rate": 7.892043345961813e-06, "loss": 0.267, "step": 314010 }, { "epoch": 1.866600091540798, "grad_norm": 4.777910232543945, "learning_rate": 7.891874082360187e-06, "loss": 0.3129, "step": 314020 }, { "epoch": 1.8666595336174665, "grad_norm": 3.7967116832733154, "learning_rate": 7.891704813778409e-06, "loss": 0.3087, "step": 314030 }, { "epoch": 1.866718975694135, "grad_norm": 4.300839424133301, "learning_rate": 7.89153554021677e-06, "loss": 0.276, "step": 314040 }, { "epoch": 1.8667784177708033, "grad_norm": 5.258528709411621, "learning_rate": 7.891366261675561e-06, "loss": 0.303, "step": 314050 }, { "epoch": 1.8668378598474717, "grad_norm": 4.778136253356934, "learning_rate": 7.891196978155075e-06, "loss": 0.2928, "step": 314060 }, { "epoch": 1.8668973019241402, "grad_norm": 4.703457832336426, "learning_rate": 7.891027689655603e-06, "loss": 0.289, "step": 314070 }, { "epoch": 1.8669567440008086, "grad_norm": 5.678496360778809, "learning_rate": 7.890858396177436e-06, "loss": 0.2921, "step": 314080 }, { "epoch": 1.8670161860774768, "grad_norm": 4.554376602172852, "learning_rate": 7.890689097720865e-06, "loss": 0.3064, "step": 314090 }, { "epoch": 1.8670756281541452, "grad_norm": 6.663622856140137, "learning_rate": 7.890519794286183e-06, "loss": 0.2761, "step": 314100 }, { "epoch": 1.8671350702308136, "grad_norm": 4.636039733886719, "learning_rate": 7.890350485873682e-06, "loss": 0.304, "step": 314110 }, { "epoch": 1.867194512307482, "grad_norm": 9.32844352722168, "learning_rate": 7.890181172483653e-06, "loss": 0.2875, "step": 314120 }, { "epoch": 1.8672539543841502, "grad_norm": 5.364639759063721, "learning_rate": 7.890011854116385e-06, "loss": 0.3032, "step": 314130 }, { "epoch": 1.8673133964608186, "grad_norm": 4.7791361808776855, "learning_rate": 7.889842530772173e-06, "loss": 0.2599, "step": 314140 }, { "epoch": 1.867372838537487, "grad_norm": 5.9713134765625, "learning_rate": 7.889673202451308e-06, "loss": 0.3398, "step": 314150 }, { "epoch": 1.8674322806141554, "grad_norm": 4.901464462280273, "learning_rate": 7.889503869154081e-06, "loss": 0.2772, "step": 314160 }, { "epoch": 1.8674917226908239, "grad_norm": 5.007384777069092, "learning_rate": 7.889334530880782e-06, "loss": 0.2669, "step": 314170 }, { "epoch": 1.8675511647674923, "grad_norm": 4.731342792510986, "learning_rate": 7.889165187631704e-06, "loss": 0.3057, "step": 314180 }, { "epoch": 1.8676106068441607, "grad_norm": 6.571298122406006, "learning_rate": 7.888995839407142e-06, "loss": 0.2916, "step": 314190 }, { "epoch": 1.867670048920829, "grad_norm": 6.058501720428467, "learning_rate": 7.888826486207382e-06, "loss": 0.2722, "step": 314200 }, { "epoch": 1.8677294909974975, "grad_norm": 5.195322513580322, "learning_rate": 7.888657128032717e-06, "loss": 0.3205, "step": 314210 }, { "epoch": 1.867788933074166, "grad_norm": 5.093578338623047, "learning_rate": 7.888487764883442e-06, "loss": 0.3061, "step": 314220 }, { "epoch": 1.8678483751508344, "grad_norm": 4.380303859710693, "learning_rate": 7.888318396759844e-06, "loss": 0.2623, "step": 314230 }, { "epoch": 1.8679078172275028, "grad_norm": 4.798422336578369, "learning_rate": 7.88814902366222e-06, "loss": 0.3073, "step": 314240 }, { "epoch": 1.8679672593041712, "grad_norm": 4.402775764465332, "learning_rate": 7.887979645590857e-06, "loss": 0.321, "step": 314250 }, { "epoch": 1.8680267013808396, "grad_norm": 5.2459635734558105, "learning_rate": 7.88781026254605e-06, "loss": 0.2867, "step": 314260 }, { "epoch": 1.8680861434575078, "grad_norm": 4.38711404800415, "learning_rate": 7.887640874528086e-06, "loss": 0.2775, "step": 314270 }, { "epoch": 1.8681455855341762, "grad_norm": 5.180351257324219, "learning_rate": 7.887471481537262e-06, "loss": 0.3211, "step": 314280 }, { "epoch": 1.8682050276108446, "grad_norm": 6.115153789520264, "learning_rate": 7.88730208357387e-06, "loss": 0.2904, "step": 314290 }, { "epoch": 1.868264469687513, "grad_norm": 5.662428855895996, "learning_rate": 7.887132680638196e-06, "loss": 0.3107, "step": 314300 }, { "epoch": 1.8683239117641814, "grad_norm": 6.679950714111328, "learning_rate": 7.886963272730536e-06, "loss": 0.2953, "step": 314310 }, { "epoch": 1.8683833538408496, "grad_norm": 5.232427597045898, "learning_rate": 7.88679385985118e-06, "loss": 0.2762, "step": 314320 }, { "epoch": 1.868442795917518, "grad_norm": 4.413154125213623, "learning_rate": 7.88662444200042e-06, "loss": 0.2791, "step": 314330 }, { "epoch": 1.8685022379941865, "grad_norm": 6.384819030761719, "learning_rate": 7.886455019178549e-06, "loss": 0.3143, "step": 314340 }, { "epoch": 1.8685616800708549, "grad_norm": 4.998887062072754, "learning_rate": 7.886285591385861e-06, "loss": 0.2576, "step": 314350 }, { "epoch": 1.8686211221475233, "grad_norm": 2.65878963470459, "learning_rate": 7.886116158622641e-06, "loss": 0.2731, "step": 314360 }, { "epoch": 1.8686805642241917, "grad_norm": 5.063774585723877, "learning_rate": 7.885946720889187e-06, "loss": 0.3, "step": 314370 }, { "epoch": 1.8687400063008601, "grad_norm": 4.098136901855469, "learning_rate": 7.885777278185786e-06, "loss": 0.2944, "step": 314380 }, { "epoch": 1.8687994483775285, "grad_norm": 4.699360370635986, "learning_rate": 7.885607830512734e-06, "loss": 0.2863, "step": 314390 }, { "epoch": 1.868858890454197, "grad_norm": 5.815922260284424, "learning_rate": 7.88543837787032e-06, "loss": 0.3068, "step": 314400 }, { "epoch": 1.8689183325308654, "grad_norm": 3.6409318447113037, "learning_rate": 7.885268920258838e-06, "loss": 0.286, "step": 314410 }, { "epoch": 1.8689777746075338, "grad_norm": 5.244677543640137, "learning_rate": 7.885099457678579e-06, "loss": 0.2904, "step": 314420 }, { "epoch": 1.8690372166842022, "grad_norm": 6.3902907371521, "learning_rate": 7.884929990129833e-06, "loss": 0.3335, "step": 314430 }, { "epoch": 1.8690966587608706, "grad_norm": 6.89898157119751, "learning_rate": 7.884760517612893e-06, "loss": 0.3401, "step": 314440 }, { "epoch": 1.869156100837539, "grad_norm": 5.0445637702941895, "learning_rate": 7.884591040128051e-06, "loss": 0.2913, "step": 314450 }, { "epoch": 1.8692155429142072, "grad_norm": 6.04264497756958, "learning_rate": 7.8844215576756e-06, "loss": 0.3015, "step": 314460 }, { "epoch": 1.8692749849908756, "grad_norm": 5.995119094848633, "learning_rate": 7.884252070255832e-06, "loss": 0.2728, "step": 314470 }, { "epoch": 1.869334427067544, "grad_norm": 5.912465572357178, "learning_rate": 7.884082577869037e-06, "loss": 0.2909, "step": 314480 }, { "epoch": 1.8693938691442125, "grad_norm": 4.97557258605957, "learning_rate": 7.883913080515508e-06, "loss": 0.3055, "step": 314490 }, { "epoch": 1.8694533112208807, "grad_norm": 6.129767417907715, "learning_rate": 7.883743578195535e-06, "loss": 0.3184, "step": 314500 }, { "epoch": 1.869512753297549, "grad_norm": 4.469931602478027, "learning_rate": 7.883574070909413e-06, "loss": 0.2848, "step": 314510 }, { "epoch": 1.8695721953742175, "grad_norm": 4.168304443359375, "learning_rate": 7.883404558657432e-06, "loss": 0.3124, "step": 314520 }, { "epoch": 1.869631637450886, "grad_norm": 3.715428352355957, "learning_rate": 7.883235041439884e-06, "loss": 0.264, "step": 314530 }, { "epoch": 1.8696910795275543, "grad_norm": 5.883607387542725, "learning_rate": 7.883065519257062e-06, "loss": 0.2851, "step": 314540 }, { "epoch": 1.8697505216042227, "grad_norm": 7.022182941436768, "learning_rate": 7.882895992109256e-06, "loss": 0.2989, "step": 314550 }, { "epoch": 1.8698099636808911, "grad_norm": 3.869476079940796, "learning_rate": 7.88272645999676e-06, "loss": 0.2982, "step": 314560 }, { "epoch": 1.8698694057575596, "grad_norm": 5.347358703613281, "learning_rate": 7.882556922919863e-06, "loss": 0.3436, "step": 314570 }, { "epoch": 1.869928847834228, "grad_norm": 5.834592342376709, "learning_rate": 7.882387380878862e-06, "loss": 0.3023, "step": 314580 }, { "epoch": 1.8699882899108964, "grad_norm": 4.730896949768066, "learning_rate": 7.882217833874047e-06, "loss": 0.3037, "step": 314590 }, { "epoch": 1.8700477319875648, "grad_norm": 3.819657564163208, "learning_rate": 7.882048281905705e-06, "loss": 0.3077, "step": 314600 }, { "epoch": 1.8701071740642332, "grad_norm": 4.938061237335205, "learning_rate": 7.881878724974134e-06, "loss": 0.2666, "step": 314610 }, { "epoch": 1.8701666161409016, "grad_norm": 4.616917133331299, "learning_rate": 7.881709163079625e-06, "loss": 0.3091, "step": 314620 }, { "epoch": 1.87022605821757, "grad_norm": 3.8252687454223633, "learning_rate": 7.881539596222467e-06, "loss": 0.307, "step": 314630 }, { "epoch": 1.8702855002942382, "grad_norm": 5.480836868286133, "learning_rate": 7.881370024402955e-06, "loss": 0.3012, "step": 314640 }, { "epoch": 1.8703449423709066, "grad_norm": 6.6932373046875, "learning_rate": 7.88120044762138e-06, "loss": 0.3134, "step": 314650 }, { "epoch": 1.870404384447575, "grad_norm": 4.628158092498779, "learning_rate": 7.881030865878033e-06, "loss": 0.3046, "step": 314660 }, { "epoch": 1.8704638265242435, "grad_norm": 5.338348388671875, "learning_rate": 7.880861279173209e-06, "loss": 0.2828, "step": 314670 }, { "epoch": 1.870523268600912, "grad_norm": 3.845196008682251, "learning_rate": 7.880691687507196e-06, "loss": 0.2886, "step": 314680 }, { "epoch": 1.87058271067758, "grad_norm": 4.378452777862549, "learning_rate": 7.88052209088029e-06, "loss": 0.3029, "step": 314690 }, { "epoch": 1.8706421527542485, "grad_norm": 5.417464256286621, "learning_rate": 7.88035248929278e-06, "loss": 0.2944, "step": 314700 }, { "epoch": 1.870701594830917, "grad_norm": 4.168055534362793, "learning_rate": 7.88018288274496e-06, "loss": 0.2724, "step": 314710 }, { "epoch": 1.8707610369075853, "grad_norm": 6.159140110015869, "learning_rate": 7.880013271237122e-06, "loss": 0.2881, "step": 314720 }, { "epoch": 1.8708204789842537, "grad_norm": 4.986047744750977, "learning_rate": 7.879843654769556e-06, "loss": 0.2934, "step": 314730 }, { "epoch": 1.8708799210609222, "grad_norm": 4.677046298980713, "learning_rate": 7.879674033342556e-06, "loss": 0.3192, "step": 314740 }, { "epoch": 1.8709393631375906, "grad_norm": 4.333773136138916, "learning_rate": 7.879504406956416e-06, "loss": 0.2893, "step": 314750 }, { "epoch": 1.870998805214259, "grad_norm": 5.040175437927246, "learning_rate": 7.879334775611423e-06, "loss": 0.2962, "step": 314760 }, { "epoch": 1.8710582472909274, "grad_norm": 4.939722061157227, "learning_rate": 7.879165139307872e-06, "loss": 0.2864, "step": 314770 }, { "epoch": 1.8711176893675958, "grad_norm": 4.522782325744629, "learning_rate": 7.878995498046056e-06, "loss": 0.2927, "step": 314780 }, { "epoch": 1.8711771314442642, "grad_norm": 5.576518535614014, "learning_rate": 7.878825851826266e-06, "loss": 0.323, "step": 314790 }, { "epoch": 1.8712365735209326, "grad_norm": 5.712343215942383, "learning_rate": 7.878656200648796e-06, "loss": 0.2878, "step": 314800 }, { "epoch": 1.871296015597601, "grad_norm": 3.9720020294189453, "learning_rate": 7.878486544513935e-06, "loss": 0.27, "step": 314810 }, { "epoch": 1.8713554576742695, "grad_norm": 6.231175422668457, "learning_rate": 7.878316883421977e-06, "loss": 0.3019, "step": 314820 }, { "epoch": 1.8714148997509377, "grad_norm": 4.850526809692383, "learning_rate": 7.878147217373213e-06, "loss": 0.3052, "step": 314830 }, { "epoch": 1.871474341827606, "grad_norm": 5.064570903778076, "learning_rate": 7.877977546367937e-06, "loss": 0.2748, "step": 314840 }, { "epoch": 1.8715337839042745, "grad_norm": 6.7786102294921875, "learning_rate": 7.87780787040644e-06, "loss": 0.3224, "step": 314850 }, { "epoch": 1.871593225980943, "grad_norm": 7.86237907409668, "learning_rate": 7.877638189489013e-06, "loss": 0.3235, "step": 314860 }, { "epoch": 1.871652668057611, "grad_norm": 3.665940284729004, "learning_rate": 7.877468503615952e-06, "loss": 0.2994, "step": 314870 }, { "epoch": 1.8717121101342795, "grad_norm": 5.671961784362793, "learning_rate": 7.877298812787545e-06, "loss": 0.2914, "step": 314880 }, { "epoch": 1.871771552210948, "grad_norm": 3.7630696296691895, "learning_rate": 7.877129117004089e-06, "loss": 0.2836, "step": 314890 }, { "epoch": 1.8718309942876163, "grad_norm": 5.6339497566223145, "learning_rate": 7.876959416265872e-06, "loss": 0.3283, "step": 314900 }, { "epoch": 1.8718904363642848, "grad_norm": 5.186543941497803, "learning_rate": 7.876789710573187e-06, "loss": 0.2696, "step": 314910 }, { "epoch": 1.8719498784409532, "grad_norm": 5.486465930938721, "learning_rate": 7.876619999926327e-06, "loss": 0.2963, "step": 314920 }, { "epoch": 1.8720093205176216, "grad_norm": 5.428111553192139, "learning_rate": 7.876450284325585e-06, "loss": 0.297, "step": 314930 }, { "epoch": 1.87206876259429, "grad_norm": 6.5800604820251465, "learning_rate": 7.876280563771252e-06, "loss": 0.2753, "step": 314940 }, { "epoch": 1.8721282046709584, "grad_norm": 4.436294078826904, "learning_rate": 7.87611083826362e-06, "loss": 0.3016, "step": 314950 }, { "epoch": 1.8721876467476268, "grad_norm": 4.974274158477783, "learning_rate": 7.875941107802982e-06, "loss": 0.2826, "step": 314960 }, { "epoch": 1.8722470888242952, "grad_norm": 4.227330207824707, "learning_rate": 7.875771372389632e-06, "loss": 0.3053, "step": 314970 }, { "epoch": 1.8723065309009637, "grad_norm": 5.002816677093506, "learning_rate": 7.875601632023856e-06, "loss": 0.3223, "step": 314980 }, { "epoch": 1.872365972977632, "grad_norm": 5.586599349975586, "learning_rate": 7.875431886705955e-06, "loss": 0.3124, "step": 314990 }, { "epoch": 1.8724254150543005, "grad_norm": 5.5047149658203125, "learning_rate": 7.875262136436217e-06, "loss": 0.3101, "step": 315000 }, { "epoch": 1.8724848571309687, "grad_norm": 4.190240383148193, "learning_rate": 7.875092381214933e-06, "loss": 0.2616, "step": 315010 }, { "epoch": 1.872544299207637, "grad_norm": 5.05616569519043, "learning_rate": 7.874922621042399e-06, "loss": 0.2709, "step": 315020 }, { "epoch": 1.8726037412843055, "grad_norm": 5.458128929138184, "learning_rate": 7.874752855918904e-06, "loss": 0.3005, "step": 315030 }, { "epoch": 1.872663183360974, "grad_norm": 4.445403099060059, "learning_rate": 7.87458308584474e-06, "loss": 0.284, "step": 315040 }, { "epoch": 1.8727226254376423, "grad_norm": 4.4874396324157715, "learning_rate": 7.874413310820203e-06, "loss": 0.2306, "step": 315050 }, { "epoch": 1.8727820675143105, "grad_norm": 5.295028209686279, "learning_rate": 7.874243530845583e-06, "loss": 0.294, "step": 315060 }, { "epoch": 1.872841509590979, "grad_norm": 6.074586868286133, "learning_rate": 7.874073745921172e-06, "loss": 0.2832, "step": 315070 }, { "epoch": 1.8729009516676474, "grad_norm": 3.994831085205078, "learning_rate": 7.873903956047264e-06, "loss": 0.2729, "step": 315080 }, { "epoch": 1.8729603937443158, "grad_norm": 5.911785125732422, "learning_rate": 7.87373416122415e-06, "loss": 0.2884, "step": 315090 }, { "epoch": 1.8730198358209842, "grad_norm": 5.333645343780518, "learning_rate": 7.873564361452122e-06, "loss": 0.2895, "step": 315100 }, { "epoch": 1.8730792778976526, "grad_norm": 4.13120174407959, "learning_rate": 7.873394556731475e-06, "loss": 0.3133, "step": 315110 }, { "epoch": 1.873138719974321, "grad_norm": 5.140955448150635, "learning_rate": 7.873224747062497e-06, "loss": 0.2943, "step": 315120 }, { "epoch": 1.8731981620509894, "grad_norm": 5.617437362670898, "learning_rate": 7.873054932445485e-06, "loss": 0.3254, "step": 315130 }, { "epoch": 1.8732576041276578, "grad_norm": 5.319162368774414, "learning_rate": 7.872885112880731e-06, "loss": 0.2845, "step": 315140 }, { "epoch": 1.8733170462043263, "grad_norm": 4.546753883361816, "learning_rate": 7.872715288368524e-06, "loss": 0.3103, "step": 315150 }, { "epoch": 1.8733764882809947, "grad_norm": 5.598750114440918, "learning_rate": 7.87254545890916e-06, "loss": 0.2741, "step": 315160 }, { "epoch": 1.873435930357663, "grad_norm": 6.037356853485107, "learning_rate": 7.872375624502927e-06, "loss": 0.3238, "step": 315170 }, { "epoch": 1.8734953724343315, "grad_norm": 5.797111988067627, "learning_rate": 7.872205785150124e-06, "loss": 0.3034, "step": 315180 }, { "epoch": 1.873554814511, "grad_norm": 3.3711602687835693, "learning_rate": 7.872035940851039e-06, "loss": 0.2738, "step": 315190 }, { "epoch": 1.8736142565876681, "grad_norm": 5.984405040740967, "learning_rate": 7.871866091605965e-06, "loss": 0.3014, "step": 315200 }, { "epoch": 1.8736736986643365, "grad_norm": 5.868547439575195, "learning_rate": 7.871696237415194e-06, "loss": 0.3336, "step": 315210 }, { "epoch": 1.873733140741005, "grad_norm": 5.769084453582764, "learning_rate": 7.871526378279019e-06, "loss": 0.3086, "step": 315220 }, { "epoch": 1.8737925828176734, "grad_norm": 5.157125949859619, "learning_rate": 7.871356514197736e-06, "loss": 0.3047, "step": 315230 }, { "epoch": 1.8738520248943416, "grad_norm": 5.025545120239258, "learning_rate": 7.871186645171633e-06, "loss": 0.2697, "step": 315240 }, { "epoch": 1.87391146697101, "grad_norm": 4.468240261077881, "learning_rate": 7.871016771201003e-06, "loss": 0.2907, "step": 315250 }, { "epoch": 1.8739709090476784, "grad_norm": 5.178589820861816, "learning_rate": 7.87084689228614e-06, "loss": 0.3112, "step": 315260 }, { "epoch": 1.8740303511243468, "grad_norm": 4.528769493103027, "learning_rate": 7.870677008427337e-06, "loss": 0.2989, "step": 315270 }, { "epoch": 1.8740897932010152, "grad_norm": 5.904494762420654, "learning_rate": 7.870507119624885e-06, "loss": 0.3017, "step": 315280 }, { "epoch": 1.8741492352776836, "grad_norm": 5.644998073577881, "learning_rate": 7.870337225879077e-06, "loss": 0.3068, "step": 315290 }, { "epoch": 1.874208677354352, "grad_norm": 5.302735328674316, "learning_rate": 7.870167327190207e-06, "loss": 0.2698, "step": 315300 }, { "epoch": 1.8742681194310205, "grad_norm": 3.4025139808654785, "learning_rate": 7.869997423558564e-06, "loss": 0.2699, "step": 315310 }, { "epoch": 1.8743275615076889, "grad_norm": 4.735682010650635, "learning_rate": 7.869827514984445e-06, "loss": 0.2901, "step": 315320 }, { "epoch": 1.8743870035843573, "grad_norm": 6.047113418579102, "learning_rate": 7.86965760146814e-06, "loss": 0.3177, "step": 315330 }, { "epoch": 1.8744464456610257, "grad_norm": 5.554981231689453, "learning_rate": 7.869487683009943e-06, "loss": 0.2948, "step": 315340 }, { "epoch": 1.874505887737694, "grad_norm": 3.996535539627075, "learning_rate": 7.869317759610144e-06, "loss": 0.2996, "step": 315350 }, { "epoch": 1.8745653298143625, "grad_norm": 5.605544567108154, "learning_rate": 7.86914783126904e-06, "loss": 0.2808, "step": 315360 }, { "epoch": 1.874624771891031, "grad_norm": 4.14343786239624, "learning_rate": 7.86897789798692e-06, "loss": 0.2656, "step": 315370 }, { "epoch": 1.8746842139676991, "grad_norm": 6.283926010131836, "learning_rate": 7.868807959764077e-06, "loss": 0.2933, "step": 315380 }, { "epoch": 1.8747436560443675, "grad_norm": 3.9098305702209473, "learning_rate": 7.868638016600804e-06, "loss": 0.3134, "step": 315390 }, { "epoch": 1.874803098121036, "grad_norm": 6.618559837341309, "learning_rate": 7.868468068497396e-06, "loss": 0.3075, "step": 315400 }, { "epoch": 1.8748625401977044, "grad_norm": 4.912886619567871, "learning_rate": 7.868298115454143e-06, "loss": 0.3164, "step": 315410 }, { "epoch": 1.8749219822743728, "grad_norm": 5.217492580413818, "learning_rate": 7.868128157471336e-06, "loss": 0.3025, "step": 315420 }, { "epoch": 1.874981424351041, "grad_norm": 4.555751323699951, "learning_rate": 7.867958194549272e-06, "loss": 0.2679, "step": 315430 }, { "epoch": 1.8750408664277094, "grad_norm": 5.639997959136963, "learning_rate": 7.867788226688243e-06, "loss": 0.2706, "step": 315440 }, { "epoch": 1.8751003085043778, "grad_norm": 5.0821661949157715, "learning_rate": 7.867618253888539e-06, "loss": 0.3094, "step": 315450 }, { "epoch": 1.8751597505810462, "grad_norm": 5.485579013824463, "learning_rate": 7.867448276150454e-06, "loss": 0.2984, "step": 315460 }, { "epoch": 1.8752191926577146, "grad_norm": 4.60081672668457, "learning_rate": 7.867278293474282e-06, "loss": 0.2772, "step": 315470 }, { "epoch": 1.875278634734383, "grad_norm": 4.623446464538574, "learning_rate": 7.867108305860314e-06, "loss": 0.2911, "step": 315480 }, { "epoch": 1.8753380768110515, "grad_norm": 4.615917682647705, "learning_rate": 7.866938313308844e-06, "loss": 0.2906, "step": 315490 }, { "epoch": 1.8753975188877199, "grad_norm": 5.546334266662598, "learning_rate": 7.866768315820164e-06, "loss": 0.3042, "step": 315500 }, { "epoch": 1.8754569609643883, "grad_norm": 5.123730659484863, "learning_rate": 7.866598313394567e-06, "loss": 0.3038, "step": 315510 }, { "epoch": 1.8755164030410567, "grad_norm": 5.511594295501709, "learning_rate": 7.866428306032346e-06, "loss": 0.2951, "step": 315520 }, { "epoch": 1.8755758451177251, "grad_norm": 6.532589912414551, "learning_rate": 7.86625829373379e-06, "loss": 0.3025, "step": 315530 }, { "epoch": 1.8756352871943935, "grad_norm": 4.7092061042785645, "learning_rate": 7.866088276499199e-06, "loss": 0.2932, "step": 315540 }, { "epoch": 1.875694729271062, "grad_norm": 5.784804344177246, "learning_rate": 7.865918254328862e-06, "loss": 0.3165, "step": 315550 }, { "epoch": 1.8757541713477304, "grad_norm": 5.797704219818115, "learning_rate": 7.86574822722307e-06, "loss": 0.3133, "step": 315560 }, { "epoch": 1.8758136134243986, "grad_norm": 5.4895830154418945, "learning_rate": 7.865578195182118e-06, "loss": 0.3142, "step": 315570 }, { "epoch": 1.875873055501067, "grad_norm": 4.632964611053467, "learning_rate": 7.8654081582063e-06, "loss": 0.2934, "step": 315580 }, { "epoch": 1.8759324975777354, "grad_norm": 6.516473770141602, "learning_rate": 7.865238116295905e-06, "loss": 0.2781, "step": 315590 }, { "epoch": 1.8759919396544038, "grad_norm": 6.192075729370117, "learning_rate": 7.86506806945123e-06, "loss": 0.3019, "step": 315600 }, { "epoch": 1.876051381731072, "grad_norm": 4.717068195343018, "learning_rate": 7.864898017672564e-06, "loss": 0.3092, "step": 315610 }, { "epoch": 1.8761108238077404, "grad_norm": 5.818652153015137, "learning_rate": 7.864727960960203e-06, "loss": 0.3232, "step": 315620 }, { "epoch": 1.8761702658844088, "grad_norm": 4.339376926422119, "learning_rate": 7.86455789931444e-06, "loss": 0.2871, "step": 315630 }, { "epoch": 1.8762297079610772, "grad_norm": 4.547708988189697, "learning_rate": 7.864387832735565e-06, "loss": 0.3001, "step": 315640 }, { "epoch": 1.8762891500377457, "grad_norm": 5.233769416809082, "learning_rate": 7.864217761223871e-06, "loss": 0.3072, "step": 315650 }, { "epoch": 1.876348592114414, "grad_norm": 5.608521938323975, "learning_rate": 7.864047684779654e-06, "loss": 0.2825, "step": 315660 }, { "epoch": 1.8764080341910825, "grad_norm": 4.444438457489014, "learning_rate": 7.863877603403205e-06, "loss": 0.2761, "step": 315670 }, { "epoch": 1.876467476267751, "grad_norm": 4.549466133117676, "learning_rate": 7.863707517094817e-06, "loss": 0.2876, "step": 315680 }, { "epoch": 1.8765269183444193, "grad_norm": 5.297886848449707, "learning_rate": 7.863537425854782e-06, "loss": 0.2641, "step": 315690 }, { "epoch": 1.8765863604210877, "grad_norm": 5.566335201263428, "learning_rate": 7.863367329683395e-06, "loss": 0.2972, "step": 315700 }, { "epoch": 1.8766458024977561, "grad_norm": 4.6719160079956055, "learning_rate": 7.863197228580948e-06, "loss": 0.2932, "step": 315710 }, { "epoch": 1.8767052445744246, "grad_norm": 6.273983001708984, "learning_rate": 7.863027122547732e-06, "loss": 0.2868, "step": 315720 }, { "epoch": 1.876764686651093, "grad_norm": 5.110716342926025, "learning_rate": 7.862857011584044e-06, "loss": 0.3034, "step": 315730 }, { "epoch": 1.8768241287277614, "grad_norm": 6.459779739379883, "learning_rate": 7.862686895690174e-06, "loss": 0.3176, "step": 315740 }, { "epoch": 1.8768835708044296, "grad_norm": 5.03997802734375, "learning_rate": 7.862516774866415e-06, "loss": 0.311, "step": 315750 }, { "epoch": 1.876943012881098, "grad_norm": 3.7048096656799316, "learning_rate": 7.86234664911306e-06, "loss": 0.3047, "step": 315760 }, { "epoch": 1.8770024549577664, "grad_norm": 4.296470642089844, "learning_rate": 7.862176518430405e-06, "loss": 0.2741, "step": 315770 }, { "epoch": 1.8770618970344348, "grad_norm": 5.5611572265625, "learning_rate": 7.862006382818738e-06, "loss": 0.2837, "step": 315780 }, { "epoch": 1.8771213391111032, "grad_norm": 4.658078193664551, "learning_rate": 7.861836242278355e-06, "loss": 0.2671, "step": 315790 }, { "epoch": 1.8771807811877714, "grad_norm": 5.428269386291504, "learning_rate": 7.861666096809549e-06, "loss": 0.2953, "step": 315800 }, { "epoch": 1.8772402232644398, "grad_norm": 5.241909027099609, "learning_rate": 7.861495946412611e-06, "loss": 0.3333, "step": 315810 }, { "epoch": 1.8772996653411083, "grad_norm": 5.726828098297119, "learning_rate": 7.861325791087838e-06, "loss": 0.3098, "step": 315820 }, { "epoch": 1.8773591074177767, "grad_norm": 5.3083696365356445, "learning_rate": 7.86115563083552e-06, "loss": 0.2915, "step": 315830 }, { "epoch": 1.877418549494445, "grad_norm": 5.041667461395264, "learning_rate": 7.86098546565595e-06, "loss": 0.2853, "step": 315840 }, { "epoch": 1.8774779915711135, "grad_norm": 5.009514808654785, "learning_rate": 7.860815295549421e-06, "loss": 0.2807, "step": 315850 }, { "epoch": 1.877537433647782, "grad_norm": 5.6133551597595215, "learning_rate": 7.860645120516228e-06, "loss": 0.322, "step": 315860 }, { "epoch": 1.8775968757244503, "grad_norm": 4.959700584411621, "learning_rate": 7.860474940556661e-06, "loss": 0.2914, "step": 315870 }, { "epoch": 1.8776563178011187, "grad_norm": 5.445544242858887, "learning_rate": 7.860304755671017e-06, "loss": 0.3052, "step": 315880 }, { "epoch": 1.8777157598777872, "grad_norm": 4.750942707061768, "learning_rate": 7.860134565859587e-06, "loss": 0.2798, "step": 315890 }, { "epoch": 1.8777752019544556, "grad_norm": 4.598667144775391, "learning_rate": 7.859964371122662e-06, "loss": 0.3094, "step": 315900 }, { "epoch": 1.877834644031124, "grad_norm": 4.00066614151001, "learning_rate": 7.859794171460538e-06, "loss": 0.2626, "step": 315910 }, { "epoch": 1.8778940861077924, "grad_norm": 4.280723571777344, "learning_rate": 7.859623966873508e-06, "loss": 0.2902, "step": 315920 }, { "epoch": 1.8779535281844608, "grad_norm": 4.406369209289551, "learning_rate": 7.859453757361863e-06, "loss": 0.2736, "step": 315930 }, { "epoch": 1.878012970261129, "grad_norm": 4.830261707305908, "learning_rate": 7.8592835429259e-06, "loss": 0.3103, "step": 315940 }, { "epoch": 1.8780724123377974, "grad_norm": 4.242980003356934, "learning_rate": 7.859113323565908e-06, "loss": 0.2923, "step": 315950 }, { "epoch": 1.8781318544144658, "grad_norm": 4.056633472442627, "learning_rate": 7.858943099282181e-06, "loss": 0.2668, "step": 315960 }, { "epoch": 1.8781912964911343, "grad_norm": 4.056474685668945, "learning_rate": 7.858772870075012e-06, "loss": 0.3385, "step": 315970 }, { "epoch": 1.8782507385678024, "grad_norm": 4.442397117614746, "learning_rate": 7.858602635944697e-06, "loss": 0.2707, "step": 315980 }, { "epoch": 1.8783101806444709, "grad_norm": 3.0622165203094482, "learning_rate": 7.858432396891526e-06, "loss": 0.2729, "step": 315990 }, { "epoch": 1.8783696227211393, "grad_norm": 5.923745155334473, "learning_rate": 7.858262152915795e-06, "loss": 0.303, "step": 316000 }, { "epoch": 1.8784290647978077, "grad_norm": 4.675674915313721, "learning_rate": 7.858091904017792e-06, "loss": 0.3059, "step": 316010 }, { "epoch": 1.878488506874476, "grad_norm": 5.650134086608887, "learning_rate": 7.857921650197817e-06, "loss": 0.2966, "step": 316020 }, { "epoch": 1.8785479489511445, "grad_norm": 5.138383388519287, "learning_rate": 7.85775139145616e-06, "loss": 0.3205, "step": 316030 }, { "epoch": 1.878607391027813, "grad_norm": 4.758114337921143, "learning_rate": 7.857581127793113e-06, "loss": 0.3165, "step": 316040 }, { "epoch": 1.8786668331044813, "grad_norm": 5.09840202331543, "learning_rate": 7.85741085920897e-06, "loss": 0.2648, "step": 316050 }, { "epoch": 1.8787262751811498, "grad_norm": 4.2189435958862305, "learning_rate": 7.857240585704026e-06, "loss": 0.2687, "step": 316060 }, { "epoch": 1.8787857172578182, "grad_norm": 4.609516620635986, "learning_rate": 7.857070307278572e-06, "loss": 0.2968, "step": 316070 }, { "epoch": 1.8788451593344866, "grad_norm": 5.518612384796143, "learning_rate": 7.8569000239329e-06, "loss": 0.2972, "step": 316080 }, { "epoch": 1.878904601411155, "grad_norm": 5.738429546356201, "learning_rate": 7.856729735667308e-06, "loss": 0.2878, "step": 316090 }, { "epoch": 1.8789640434878234, "grad_norm": 5.334571838378906, "learning_rate": 7.856559442482085e-06, "loss": 0.3079, "step": 316100 }, { "epoch": 1.8790234855644918, "grad_norm": 4.443511009216309, "learning_rate": 7.856389144377528e-06, "loss": 0.2983, "step": 316110 }, { "epoch": 1.87908292764116, "grad_norm": 4.843644618988037, "learning_rate": 7.856218841353925e-06, "loss": 0.3022, "step": 316120 }, { "epoch": 1.8791423697178284, "grad_norm": 4.247282028198242, "learning_rate": 7.856048533411575e-06, "loss": 0.269, "step": 316130 }, { "epoch": 1.8792018117944969, "grad_norm": 6.313143253326416, "learning_rate": 7.855878220550768e-06, "loss": 0.2706, "step": 316140 }, { "epoch": 1.8792612538711653, "grad_norm": 4.273153305053711, "learning_rate": 7.855707902771797e-06, "loss": 0.2891, "step": 316150 }, { "epoch": 1.8793206959478337, "grad_norm": 4.866721153259277, "learning_rate": 7.855537580074956e-06, "loss": 0.2887, "step": 316160 }, { "epoch": 1.8793801380245019, "grad_norm": 4.798839569091797, "learning_rate": 7.855367252460539e-06, "loss": 0.3034, "step": 316170 }, { "epoch": 1.8794395801011703, "grad_norm": 6.7885847091674805, "learning_rate": 7.85519691992884e-06, "loss": 0.3048, "step": 316180 }, { "epoch": 1.8794990221778387, "grad_norm": 6.093486309051514, "learning_rate": 7.85502658248015e-06, "loss": 0.3313, "step": 316190 }, { "epoch": 1.8795584642545071, "grad_norm": 4.637692928314209, "learning_rate": 7.854856240114765e-06, "loss": 0.2907, "step": 316200 }, { "epoch": 1.8796179063311755, "grad_norm": 7.694153308868408, "learning_rate": 7.854685892832974e-06, "loss": 0.3164, "step": 316210 }, { "epoch": 1.879677348407844, "grad_norm": 5.446391582489014, "learning_rate": 7.854515540635077e-06, "loss": 0.3053, "step": 316220 }, { "epoch": 1.8797367904845124, "grad_norm": 5.285922050476074, "learning_rate": 7.854345183521362e-06, "loss": 0.3138, "step": 316230 }, { "epoch": 1.8797962325611808, "grad_norm": 6.7361931800842285, "learning_rate": 7.854174821492123e-06, "loss": 0.3204, "step": 316240 }, { "epoch": 1.8798556746378492, "grad_norm": 4.630561351776123, "learning_rate": 7.854004454547655e-06, "loss": 0.3009, "step": 316250 }, { "epoch": 1.8799151167145176, "grad_norm": 5.458629131317139, "learning_rate": 7.853834082688251e-06, "loss": 0.3077, "step": 316260 }, { "epoch": 1.879974558791186, "grad_norm": 5.885043621063232, "learning_rate": 7.853663705914205e-06, "loss": 0.301, "step": 316270 }, { "epoch": 1.8800340008678544, "grad_norm": 5.704846382141113, "learning_rate": 7.853493324225809e-06, "loss": 0.2808, "step": 316280 }, { "epoch": 1.8800934429445229, "grad_norm": 5.02439546585083, "learning_rate": 7.853322937623358e-06, "loss": 0.2932, "step": 316290 }, { "epoch": 1.880152885021191, "grad_norm": 4.280763626098633, "learning_rate": 7.85315254610714e-06, "loss": 0.2594, "step": 316300 }, { "epoch": 1.8802123270978595, "grad_norm": 4.187784671783447, "learning_rate": 7.852982149677457e-06, "loss": 0.2768, "step": 316310 }, { "epoch": 1.8802717691745279, "grad_norm": 5.7679877281188965, "learning_rate": 7.852811748334599e-06, "loss": 0.3103, "step": 316320 }, { "epoch": 1.8803312112511963, "grad_norm": 4.608171463012695, "learning_rate": 7.852641342078857e-06, "loss": 0.2966, "step": 316330 }, { "epoch": 1.8803906533278647, "grad_norm": 6.078287124633789, "learning_rate": 7.852470930910527e-06, "loss": 0.2823, "step": 316340 }, { "epoch": 1.880450095404533, "grad_norm": 5.121182918548584, "learning_rate": 7.852300514829901e-06, "loss": 0.2961, "step": 316350 }, { "epoch": 1.8805095374812013, "grad_norm": 4.983944416046143, "learning_rate": 7.852130093837274e-06, "loss": 0.3181, "step": 316360 }, { "epoch": 1.8805689795578697, "grad_norm": 4.351569652557373, "learning_rate": 7.851959667932938e-06, "loss": 0.303, "step": 316370 }, { "epoch": 1.8806284216345381, "grad_norm": 5.651061534881592, "learning_rate": 7.851789237117187e-06, "loss": 0.3099, "step": 316380 }, { "epoch": 1.8806878637112066, "grad_norm": 6.541561603546143, "learning_rate": 7.851618801390315e-06, "loss": 0.2926, "step": 316390 }, { "epoch": 1.880747305787875, "grad_norm": 4.396756649017334, "learning_rate": 7.851448360752615e-06, "loss": 0.2902, "step": 316400 }, { "epoch": 1.8808067478645434, "grad_norm": 5.630216121673584, "learning_rate": 7.85127791520438e-06, "loss": 0.3166, "step": 316410 }, { "epoch": 1.8808661899412118, "grad_norm": 3.558720827102661, "learning_rate": 7.851107464745905e-06, "loss": 0.2894, "step": 316420 }, { "epoch": 1.8809256320178802, "grad_norm": 4.969439506530762, "learning_rate": 7.850937009377482e-06, "loss": 0.3321, "step": 316430 }, { "epoch": 1.8809850740945486, "grad_norm": 4.709372043609619, "learning_rate": 7.850766549099406e-06, "loss": 0.2912, "step": 316440 }, { "epoch": 1.881044516171217, "grad_norm": 6.4863762855529785, "learning_rate": 7.850596083911973e-06, "loss": 0.281, "step": 316450 }, { "epoch": 1.8811039582478855, "grad_norm": 3.897817373275757, "learning_rate": 7.850425613815468e-06, "loss": 0.2939, "step": 316460 }, { "epoch": 1.8811634003245539, "grad_norm": 5.553028106689453, "learning_rate": 7.850255138810193e-06, "loss": 0.303, "step": 316470 }, { "epoch": 1.8812228424012223, "grad_norm": 5.722341060638428, "learning_rate": 7.850084658896437e-06, "loss": 0.3044, "step": 316480 }, { "epoch": 1.8812822844778905, "grad_norm": 5.272485256195068, "learning_rate": 7.849914174074497e-06, "loss": 0.2691, "step": 316490 }, { "epoch": 1.881341726554559, "grad_norm": 4.379042625427246, "learning_rate": 7.849743684344664e-06, "loss": 0.2891, "step": 316500 }, { "epoch": 1.8814011686312273, "grad_norm": 4.342769145965576, "learning_rate": 7.849573189707233e-06, "loss": 0.2923, "step": 316510 }, { "epoch": 1.8814606107078957, "grad_norm": 4.037267684936523, "learning_rate": 7.849402690162495e-06, "loss": 0.2752, "step": 316520 }, { "epoch": 1.8815200527845641, "grad_norm": 6.57428503036499, "learning_rate": 7.849232185710747e-06, "loss": 0.298, "step": 316530 }, { "epoch": 1.8815794948612323, "grad_norm": 5.577286243438721, "learning_rate": 7.84906167635228e-06, "loss": 0.2973, "step": 316540 }, { "epoch": 1.8816389369379007, "grad_norm": 4.812927722930908, "learning_rate": 7.84889116208739e-06, "loss": 0.3185, "step": 316550 }, { "epoch": 1.8816983790145692, "grad_norm": 4.018134117126465, "learning_rate": 7.84872064291637e-06, "loss": 0.291, "step": 316560 }, { "epoch": 1.8817578210912376, "grad_norm": 4.583422660827637, "learning_rate": 7.848550118839513e-06, "loss": 0.2591, "step": 316570 }, { "epoch": 1.881817263167906, "grad_norm": 4.575523376464844, "learning_rate": 7.84837958985711e-06, "loss": 0.3146, "step": 316580 }, { "epoch": 1.8818767052445744, "grad_norm": 6.061269283294678, "learning_rate": 7.84820905596946e-06, "loss": 0.3021, "step": 316590 }, { "epoch": 1.8819361473212428, "grad_norm": 6.371779441833496, "learning_rate": 7.848038517176854e-06, "loss": 0.3191, "step": 316600 }, { "epoch": 1.8819955893979112, "grad_norm": 4.284409046173096, "learning_rate": 7.847867973479587e-06, "loss": 0.2595, "step": 316610 }, { "epoch": 1.8820550314745796, "grad_norm": 5.080738544464111, "learning_rate": 7.84769742487795e-06, "loss": 0.2897, "step": 316620 }, { "epoch": 1.882114473551248, "grad_norm": 5.639977931976318, "learning_rate": 7.847526871372238e-06, "loss": 0.2931, "step": 316630 }, { "epoch": 1.8821739156279165, "grad_norm": 6.4761786460876465, "learning_rate": 7.847356312962746e-06, "loss": 0.3214, "step": 316640 }, { "epoch": 1.8822333577045849, "grad_norm": 4.182766914367676, "learning_rate": 7.847185749649766e-06, "loss": 0.2934, "step": 316650 }, { "epoch": 1.8822927997812533, "grad_norm": 4.2710065841674805, "learning_rate": 7.847015181433592e-06, "loss": 0.3256, "step": 316660 }, { "epoch": 1.8823522418579215, "grad_norm": 5.701841831207275, "learning_rate": 7.846844608314519e-06, "loss": 0.3127, "step": 316670 }, { "epoch": 1.88241168393459, "grad_norm": 5.4771857261657715, "learning_rate": 7.84667403029284e-06, "loss": 0.2787, "step": 316680 }, { "epoch": 1.8824711260112583, "grad_norm": 4.91514778137207, "learning_rate": 7.846503447368849e-06, "loss": 0.3009, "step": 316690 }, { "epoch": 1.8825305680879267, "grad_norm": 2.937758684158325, "learning_rate": 7.846332859542838e-06, "loss": 0.2794, "step": 316700 }, { "epoch": 1.8825900101645952, "grad_norm": 5.826824188232422, "learning_rate": 7.846162266815103e-06, "loss": 0.2866, "step": 316710 }, { "epoch": 1.8826494522412633, "grad_norm": 3.82293963432312, "learning_rate": 7.845991669185937e-06, "loss": 0.2723, "step": 316720 }, { "epoch": 1.8827088943179318, "grad_norm": 5.611250400543213, "learning_rate": 7.845821066655634e-06, "loss": 0.3183, "step": 316730 }, { "epoch": 1.8827683363946002, "grad_norm": 4.966221809387207, "learning_rate": 7.845650459224486e-06, "loss": 0.29, "step": 316740 }, { "epoch": 1.8828277784712686, "grad_norm": 5.4651641845703125, "learning_rate": 7.84547984689279e-06, "loss": 0.3058, "step": 316750 }, { "epoch": 1.882887220547937, "grad_norm": 4.179057598114014, "learning_rate": 7.845309229660838e-06, "loss": 0.3072, "step": 316760 }, { "epoch": 1.8829466626246054, "grad_norm": 7.554204940795898, "learning_rate": 7.845138607528924e-06, "loss": 0.2975, "step": 316770 }, { "epoch": 1.8830061047012738, "grad_norm": 6.881021976470947, "learning_rate": 7.844967980497342e-06, "loss": 0.2871, "step": 316780 }, { "epoch": 1.8830655467779422, "grad_norm": 5.108966827392578, "learning_rate": 7.844797348566384e-06, "loss": 0.3035, "step": 316790 }, { "epoch": 1.8831249888546107, "grad_norm": 4.340888977050781, "learning_rate": 7.844626711736348e-06, "loss": 0.2937, "step": 316800 }, { "epoch": 1.883184430931279, "grad_norm": 6.132041931152344, "learning_rate": 7.844456070007524e-06, "loss": 0.3338, "step": 316810 }, { "epoch": 1.8832438730079475, "grad_norm": 5.857524871826172, "learning_rate": 7.844285423380207e-06, "loss": 0.3174, "step": 316820 }, { "epoch": 1.883303315084616, "grad_norm": 4.665904998779297, "learning_rate": 7.844114771854692e-06, "loss": 0.2901, "step": 316830 }, { "epoch": 1.8833627571612843, "grad_norm": 5.55730676651001, "learning_rate": 7.843944115431272e-06, "loss": 0.2813, "step": 316840 }, { "epoch": 1.8834221992379527, "grad_norm": 5.054698944091797, "learning_rate": 7.84377345411024e-06, "loss": 0.3136, "step": 316850 }, { "epoch": 1.883481641314621, "grad_norm": 8.403578758239746, "learning_rate": 7.843602787891892e-06, "loss": 0.2959, "step": 316860 }, { "epoch": 1.8835410833912893, "grad_norm": 5.742882251739502, "learning_rate": 7.843432116776518e-06, "loss": 0.2927, "step": 316870 }, { "epoch": 1.8836005254679578, "grad_norm": 5.8170623779296875, "learning_rate": 7.843261440764417e-06, "loss": 0.2775, "step": 316880 }, { "epoch": 1.8836599675446262, "grad_norm": 5.028580188751221, "learning_rate": 7.843090759855881e-06, "loss": 0.2776, "step": 316890 }, { "epoch": 1.8837194096212946, "grad_norm": 4.498251914978027, "learning_rate": 7.842920074051204e-06, "loss": 0.34, "step": 316900 }, { "epoch": 1.8837788516979628, "grad_norm": 3.8963727951049805, "learning_rate": 7.842749383350679e-06, "loss": 0.2645, "step": 316910 }, { "epoch": 1.8838382937746312, "grad_norm": 5.235620498657227, "learning_rate": 7.842578687754598e-06, "loss": 0.2858, "step": 316920 }, { "epoch": 1.8838977358512996, "grad_norm": 4.893606662750244, "learning_rate": 7.842407987263259e-06, "loss": 0.2981, "step": 316930 }, { "epoch": 1.883957177927968, "grad_norm": 5.639828205108643, "learning_rate": 7.842237281876954e-06, "loss": 0.281, "step": 316940 }, { "epoch": 1.8840166200046364, "grad_norm": 3.8058533668518066, "learning_rate": 7.842066571595977e-06, "loss": 0.2551, "step": 316950 }, { "epoch": 1.8840760620813048, "grad_norm": 5.258366584777832, "learning_rate": 7.841895856420623e-06, "loss": 0.2975, "step": 316960 }, { "epoch": 1.8841355041579733, "grad_norm": 4.386706352233887, "learning_rate": 7.841725136351184e-06, "loss": 0.2873, "step": 316970 }, { "epoch": 1.8841949462346417, "grad_norm": 7.156777381896973, "learning_rate": 7.841554411387957e-06, "loss": 0.3208, "step": 316980 }, { "epoch": 1.88425438831131, "grad_norm": 4.643474102020264, "learning_rate": 7.841383681531233e-06, "loss": 0.289, "step": 316990 }, { "epoch": 1.8843138303879785, "grad_norm": 5.509867191314697, "learning_rate": 7.841212946781307e-06, "loss": 0.3097, "step": 317000 }, { "epoch": 1.884373272464647, "grad_norm": 5.272125720977783, "learning_rate": 7.841042207138473e-06, "loss": 0.2688, "step": 317010 }, { "epoch": 1.8844327145413153, "grad_norm": 4.246386528015137, "learning_rate": 7.840871462603028e-06, "loss": 0.3379, "step": 317020 }, { "epoch": 1.8844921566179837, "grad_norm": 4.813362121582031, "learning_rate": 7.840700713175263e-06, "loss": 0.3106, "step": 317030 }, { "epoch": 1.884551598694652, "grad_norm": 6.434043884277344, "learning_rate": 7.840529958855469e-06, "loss": 0.3116, "step": 317040 }, { "epoch": 1.8846110407713204, "grad_norm": 6.008612632751465, "learning_rate": 7.840359199643946e-06, "loss": 0.2957, "step": 317050 }, { "epoch": 1.8846704828479888, "grad_norm": 5.407655239105225, "learning_rate": 7.840188435540986e-06, "loss": 0.2803, "step": 317060 }, { "epoch": 1.8847299249246572, "grad_norm": 4.517388343811035, "learning_rate": 7.840017666546882e-06, "loss": 0.296, "step": 317070 }, { "epoch": 1.8847893670013256, "grad_norm": 5.542501449584961, "learning_rate": 7.839846892661926e-06, "loss": 0.2869, "step": 317080 }, { "epoch": 1.8848488090779938, "grad_norm": 4.421365737915039, "learning_rate": 7.839676113886419e-06, "loss": 0.3069, "step": 317090 }, { "epoch": 1.8849082511546622, "grad_norm": 3.277783155441284, "learning_rate": 7.839505330220648e-06, "loss": 0.2977, "step": 317100 }, { "epoch": 1.8849676932313306, "grad_norm": 4.099187850952148, "learning_rate": 7.839334541664911e-06, "loss": 0.2822, "step": 317110 }, { "epoch": 1.885027135307999, "grad_norm": 4.910777568817139, "learning_rate": 7.839163748219503e-06, "loss": 0.2764, "step": 317120 }, { "epoch": 1.8850865773846675, "grad_norm": 5.012518405914307, "learning_rate": 7.838992949884714e-06, "loss": 0.3049, "step": 317130 }, { "epoch": 1.8851460194613359, "grad_norm": 4.617821216583252, "learning_rate": 7.83882214666084e-06, "loss": 0.2999, "step": 317140 }, { "epoch": 1.8852054615380043, "grad_norm": 5.321542739868164, "learning_rate": 7.838651338548177e-06, "loss": 0.2982, "step": 317150 }, { "epoch": 1.8852649036146727, "grad_norm": 4.550069808959961, "learning_rate": 7.838480525547018e-06, "loss": 0.3038, "step": 317160 }, { "epoch": 1.885324345691341, "grad_norm": 4.612276077270508, "learning_rate": 7.838309707657656e-06, "loss": 0.284, "step": 317170 }, { "epoch": 1.8853837877680095, "grad_norm": 4.139767646789551, "learning_rate": 7.838138884880386e-06, "loss": 0.2636, "step": 317180 }, { "epoch": 1.885443229844678, "grad_norm": 4.308298587799072, "learning_rate": 7.837968057215501e-06, "loss": 0.2776, "step": 317190 }, { "epoch": 1.8855026719213464, "grad_norm": 5.364570617675781, "learning_rate": 7.837797224663299e-06, "loss": 0.2746, "step": 317200 }, { "epoch": 1.8855621139980148, "grad_norm": 5.527988433837891, "learning_rate": 7.83762638722407e-06, "loss": 0.2987, "step": 317210 }, { "epoch": 1.8856215560746832, "grad_norm": 6.485441207885742, "learning_rate": 7.83745554489811e-06, "loss": 0.2617, "step": 317220 }, { "epoch": 1.8856809981513514, "grad_norm": 5.435844898223877, "learning_rate": 7.837284697685712e-06, "loss": 0.288, "step": 317230 }, { "epoch": 1.8857404402280198, "grad_norm": 5.124395370483398, "learning_rate": 7.837113845587173e-06, "loss": 0.2995, "step": 317240 }, { "epoch": 1.8857998823046882, "grad_norm": 3.483212947845459, "learning_rate": 7.836942988602784e-06, "loss": 0.2993, "step": 317250 }, { "epoch": 1.8858593243813566, "grad_norm": 3.9171526432037354, "learning_rate": 7.836772126732844e-06, "loss": 0.2595, "step": 317260 }, { "epoch": 1.885918766458025, "grad_norm": 4.751817226409912, "learning_rate": 7.83660125997764e-06, "loss": 0.2999, "step": 317270 }, { "epoch": 1.8859782085346932, "grad_norm": 5.484410285949707, "learning_rate": 7.836430388337471e-06, "loss": 0.2832, "step": 317280 }, { "epoch": 1.8860376506113616, "grad_norm": 5.0683722496032715, "learning_rate": 7.83625951181263e-06, "loss": 0.2988, "step": 317290 }, { "epoch": 1.88609709268803, "grad_norm": 5.598883628845215, "learning_rate": 7.836088630403414e-06, "loss": 0.2871, "step": 317300 }, { "epoch": 1.8861565347646985, "grad_norm": 5.1012864112854, "learning_rate": 7.835917744110113e-06, "loss": 0.2694, "step": 317310 }, { "epoch": 1.8862159768413669, "grad_norm": 4.293667316436768, "learning_rate": 7.835746852933024e-06, "loss": 0.312, "step": 317320 }, { "epoch": 1.8862754189180353, "grad_norm": 3.7309303283691406, "learning_rate": 7.835575956872441e-06, "loss": 0.2718, "step": 317330 }, { "epoch": 1.8863348609947037, "grad_norm": 5.1487135887146, "learning_rate": 7.835405055928657e-06, "loss": 0.2881, "step": 317340 }, { "epoch": 1.8863943030713721, "grad_norm": 6.63103723526001, "learning_rate": 7.835234150101967e-06, "loss": 0.3549, "step": 317350 }, { "epoch": 1.8864537451480405, "grad_norm": 4.9475178718566895, "learning_rate": 7.835063239392666e-06, "loss": 0.3077, "step": 317360 }, { "epoch": 1.886513187224709, "grad_norm": 6.530595302581787, "learning_rate": 7.834892323801048e-06, "loss": 0.2804, "step": 317370 }, { "epoch": 1.8865726293013774, "grad_norm": 5.52028226852417, "learning_rate": 7.834721403327408e-06, "loss": 0.2898, "step": 317380 }, { "epoch": 1.8866320713780458, "grad_norm": 4.865300178527832, "learning_rate": 7.834550477972038e-06, "loss": 0.2737, "step": 317390 }, { "epoch": 1.8866915134547142, "grad_norm": 4.685591697692871, "learning_rate": 7.834379547735234e-06, "loss": 0.265, "step": 317400 }, { "epoch": 1.8867509555313824, "grad_norm": 6.645280361175537, "learning_rate": 7.83420861261729e-06, "loss": 0.3086, "step": 317410 }, { "epoch": 1.8868103976080508, "grad_norm": 3.917144298553467, "learning_rate": 7.8340376726185e-06, "loss": 0.2746, "step": 317420 }, { "epoch": 1.8868698396847192, "grad_norm": 4.6851277351379395, "learning_rate": 7.833866727739161e-06, "loss": 0.2897, "step": 317430 }, { "epoch": 1.8869292817613876, "grad_norm": 5.10891580581665, "learning_rate": 7.833695777979564e-06, "loss": 0.3491, "step": 317440 }, { "epoch": 1.886988723838056, "grad_norm": 3.7714459896087646, "learning_rate": 7.833524823340007e-06, "loss": 0.2786, "step": 317450 }, { "epoch": 1.8870481659147242, "grad_norm": 5.780743598937988, "learning_rate": 7.83335386382078e-06, "loss": 0.291, "step": 317460 }, { "epoch": 1.8871076079913927, "grad_norm": 5.3946146965026855, "learning_rate": 7.83318289942218e-06, "loss": 0.3298, "step": 317470 }, { "epoch": 1.887167050068061, "grad_norm": 5.994387626647949, "learning_rate": 7.8330119301445e-06, "loss": 0.282, "step": 317480 }, { "epoch": 1.8872264921447295, "grad_norm": 8.06634521484375, "learning_rate": 7.832840955988037e-06, "loss": 0.2882, "step": 317490 }, { "epoch": 1.887285934221398, "grad_norm": 5.122754096984863, "learning_rate": 7.832669976953082e-06, "loss": 0.3034, "step": 317500 }, { "epoch": 1.8873453762980663, "grad_norm": 6.093923568725586, "learning_rate": 7.832498993039933e-06, "loss": 0.3048, "step": 317510 }, { "epoch": 1.8874048183747347, "grad_norm": 4.666504859924316, "learning_rate": 7.832328004248883e-06, "loss": 0.3041, "step": 317520 }, { "epoch": 1.8874642604514031, "grad_norm": 4.977110862731934, "learning_rate": 7.832157010580226e-06, "loss": 0.2579, "step": 317530 }, { "epoch": 1.8875237025280716, "grad_norm": 4.794666767120361, "learning_rate": 7.831986012034257e-06, "loss": 0.27, "step": 317540 }, { "epoch": 1.88758314460474, "grad_norm": 4.087697505950928, "learning_rate": 7.831815008611268e-06, "loss": 0.28, "step": 317550 }, { "epoch": 1.8876425866814084, "grad_norm": 6.035214900970459, "learning_rate": 7.831644000311557e-06, "loss": 0.2594, "step": 317560 }, { "epoch": 1.8877020287580768, "grad_norm": 5.220007419586182, "learning_rate": 7.831472987135418e-06, "loss": 0.2625, "step": 317570 }, { "epoch": 1.8877614708347452, "grad_norm": 5.043464660644531, "learning_rate": 7.831301969083143e-06, "loss": 0.309, "step": 317580 }, { "epoch": 1.8878209129114136, "grad_norm": 5.386398792266846, "learning_rate": 7.83113094615503e-06, "loss": 0.3115, "step": 317590 }, { "epoch": 1.8878803549880818, "grad_norm": 4.9546966552734375, "learning_rate": 7.830959918351371e-06, "loss": 0.2937, "step": 317600 }, { "epoch": 1.8879397970647502, "grad_norm": 5.279214859008789, "learning_rate": 7.83078888567246e-06, "loss": 0.2876, "step": 317610 }, { "epoch": 1.8879992391414187, "grad_norm": 5.318146228790283, "learning_rate": 7.830617848118593e-06, "loss": 0.2636, "step": 317620 }, { "epoch": 1.888058681218087, "grad_norm": 4.13804817199707, "learning_rate": 7.830446805690067e-06, "loss": 0.2601, "step": 317630 }, { "epoch": 1.8881181232947555, "grad_norm": 6.669679164886475, "learning_rate": 7.830275758387172e-06, "loss": 0.2825, "step": 317640 }, { "epoch": 1.8881775653714237, "grad_norm": 5.429562568664551, "learning_rate": 7.830104706210204e-06, "loss": 0.2936, "step": 317650 }, { "epoch": 1.888237007448092, "grad_norm": 4.616244316101074, "learning_rate": 7.829933649159459e-06, "loss": 0.2654, "step": 317660 }, { "epoch": 1.8882964495247605, "grad_norm": 4.619032859802246, "learning_rate": 7.82976258723523e-06, "loss": 0.28, "step": 317670 }, { "epoch": 1.888355891601429, "grad_norm": 5.432648658752441, "learning_rate": 7.829591520437811e-06, "loss": 0.2716, "step": 317680 }, { "epoch": 1.8884153336780973, "grad_norm": 3.3354685306549072, "learning_rate": 7.8294204487675e-06, "loss": 0.2904, "step": 317690 }, { "epoch": 1.8884747757547657, "grad_norm": 4.608119010925293, "learning_rate": 7.829249372224587e-06, "loss": 0.2881, "step": 317700 }, { "epoch": 1.8885342178314342, "grad_norm": 4.8649187088012695, "learning_rate": 7.829078290809371e-06, "loss": 0.2858, "step": 317710 }, { "epoch": 1.8885936599081026, "grad_norm": 5.859804630279541, "learning_rate": 7.828907204522144e-06, "loss": 0.2715, "step": 317720 }, { "epoch": 1.888653101984771, "grad_norm": 3.994933843612671, "learning_rate": 7.828736113363202e-06, "loss": 0.2817, "step": 317730 }, { "epoch": 1.8887125440614394, "grad_norm": 5.2812113761901855, "learning_rate": 7.82856501733284e-06, "loss": 0.2907, "step": 317740 }, { "epoch": 1.8887719861381078, "grad_norm": 4.118821144104004, "learning_rate": 7.828393916431348e-06, "loss": 0.2809, "step": 317750 }, { "epoch": 1.8888314282147762, "grad_norm": 5.180171966552734, "learning_rate": 7.828222810659026e-06, "loss": 0.287, "step": 317760 }, { "epoch": 1.8888908702914446, "grad_norm": 5.2675862312316895, "learning_rate": 7.828051700016166e-06, "loss": 0.2875, "step": 317770 }, { "epoch": 1.8889503123681128, "grad_norm": 5.984093189239502, "learning_rate": 7.827880584503065e-06, "loss": 0.3021, "step": 317780 }, { "epoch": 1.8890097544447813, "grad_norm": 5.313286781311035, "learning_rate": 7.827709464120015e-06, "loss": 0.3054, "step": 317790 }, { "epoch": 1.8890691965214497, "grad_norm": 5.5636067390441895, "learning_rate": 7.827538338867313e-06, "loss": 0.2438, "step": 317800 }, { "epoch": 1.889128638598118, "grad_norm": 6.245013236999512, "learning_rate": 7.827367208745253e-06, "loss": 0.2735, "step": 317810 }, { "epoch": 1.8891880806747865, "grad_norm": 4.878435134887695, "learning_rate": 7.827196073754128e-06, "loss": 0.2942, "step": 317820 }, { "epoch": 1.8892475227514547, "grad_norm": 6.1177449226379395, "learning_rate": 7.827024933894233e-06, "loss": 0.2799, "step": 317830 }, { "epoch": 1.889306964828123, "grad_norm": 4.431589603424072, "learning_rate": 7.826853789165866e-06, "loss": 0.2895, "step": 317840 }, { "epoch": 1.8893664069047915, "grad_norm": 4.665709972381592, "learning_rate": 7.826682639569318e-06, "loss": 0.2961, "step": 317850 }, { "epoch": 1.88942584898146, "grad_norm": 7.125980377197266, "learning_rate": 7.826511485104887e-06, "loss": 0.2932, "step": 317860 }, { "epoch": 1.8894852910581283, "grad_norm": 4.29541540145874, "learning_rate": 7.826340325772864e-06, "loss": 0.3227, "step": 317870 }, { "epoch": 1.8895447331347968, "grad_norm": 4.949416160583496, "learning_rate": 7.826169161573547e-06, "loss": 0.2851, "step": 317880 }, { "epoch": 1.8896041752114652, "grad_norm": 5.223796844482422, "learning_rate": 7.825997992507228e-06, "loss": 0.2882, "step": 317890 }, { "epoch": 1.8896636172881336, "grad_norm": 5.895389556884766, "learning_rate": 7.825826818574206e-06, "loss": 0.3059, "step": 317900 }, { "epoch": 1.889723059364802, "grad_norm": 5.093266010284424, "learning_rate": 7.82565563977477e-06, "loss": 0.3008, "step": 317910 }, { "epoch": 1.8897825014414704, "grad_norm": 3.8607516288757324, "learning_rate": 7.82548445610922e-06, "loss": 0.2753, "step": 317920 }, { "epoch": 1.8898419435181388, "grad_norm": 5.286767482757568, "learning_rate": 7.825313267577847e-06, "loss": 0.2755, "step": 317930 }, { "epoch": 1.8899013855948072, "grad_norm": 5.735193252563477, "learning_rate": 7.825142074180949e-06, "loss": 0.3003, "step": 317940 }, { "epoch": 1.8899608276714757, "grad_norm": 4.620377540588379, "learning_rate": 7.824970875918819e-06, "loss": 0.2798, "step": 317950 }, { "epoch": 1.890020269748144, "grad_norm": 4.2725396156311035, "learning_rate": 7.82479967279175e-06, "loss": 0.2874, "step": 317960 }, { "epoch": 1.8900797118248123, "grad_norm": 4.683473587036133, "learning_rate": 7.82462846480004e-06, "loss": 0.2884, "step": 317970 }, { "epoch": 1.8901391539014807, "grad_norm": 4.839288234710693, "learning_rate": 7.824457251943984e-06, "loss": 0.3253, "step": 317980 }, { "epoch": 1.890198595978149, "grad_norm": 4.563981533050537, "learning_rate": 7.824286034223876e-06, "loss": 0.2939, "step": 317990 }, { "epoch": 1.8902580380548175, "grad_norm": 4.714191913604736, "learning_rate": 7.82411481164001e-06, "loss": 0.2818, "step": 318000 }, { "epoch": 1.890317480131486, "grad_norm": 5.077323913574219, "learning_rate": 7.82394358419268e-06, "loss": 0.2759, "step": 318010 }, { "epoch": 1.8903769222081541, "grad_norm": 3.828265428543091, "learning_rate": 7.823772351882182e-06, "loss": 0.2904, "step": 318020 }, { "epoch": 1.8904363642848225, "grad_norm": 4.476435661315918, "learning_rate": 7.823601114708812e-06, "loss": 0.2686, "step": 318030 }, { "epoch": 1.890495806361491, "grad_norm": 4.295116424560547, "learning_rate": 7.823429872672865e-06, "loss": 0.3109, "step": 318040 }, { "epoch": 1.8905552484381594, "grad_norm": 4.284462928771973, "learning_rate": 7.823258625774633e-06, "loss": 0.3166, "step": 318050 }, { "epoch": 1.8906146905148278, "grad_norm": 5.551520824432373, "learning_rate": 7.823087374014414e-06, "loss": 0.2751, "step": 318060 }, { "epoch": 1.8906741325914962, "grad_norm": 5.849943161010742, "learning_rate": 7.8229161173925e-06, "loss": 0.2759, "step": 318070 }, { "epoch": 1.8907335746681646, "grad_norm": 5.363214492797852, "learning_rate": 7.82274485590919e-06, "loss": 0.3037, "step": 318080 }, { "epoch": 1.890793016744833, "grad_norm": 5.848117828369141, "learning_rate": 7.822573589564775e-06, "loss": 0.3017, "step": 318090 }, { "epoch": 1.8908524588215014, "grad_norm": 6.520884990692139, "learning_rate": 7.822402318359553e-06, "loss": 0.3079, "step": 318100 }, { "epoch": 1.8909119008981699, "grad_norm": 5.406185150146484, "learning_rate": 7.822231042293815e-06, "loss": 0.3239, "step": 318110 }, { "epoch": 1.8909713429748383, "grad_norm": 4.7042317390441895, "learning_rate": 7.82205976136786e-06, "loss": 0.2639, "step": 318120 }, { "epoch": 1.8910307850515067, "grad_norm": 4.595023155212402, "learning_rate": 7.82188847558198e-06, "loss": 0.2747, "step": 318130 }, { "epoch": 1.891090227128175, "grad_norm": 4.296533107757568, "learning_rate": 7.821717184936474e-06, "loss": 0.255, "step": 318140 }, { "epoch": 1.8911496692048433, "grad_norm": 4.861443996429443, "learning_rate": 7.821545889431633e-06, "loss": 0.2824, "step": 318150 }, { "epoch": 1.8912091112815117, "grad_norm": 4.607110023498535, "learning_rate": 7.821374589067754e-06, "loss": 0.2569, "step": 318160 }, { "epoch": 1.8912685533581801, "grad_norm": 5.152155876159668, "learning_rate": 7.821203283845129e-06, "loss": 0.2985, "step": 318170 }, { "epoch": 1.8913279954348485, "grad_norm": 5.415275573730469, "learning_rate": 7.821031973764057e-06, "loss": 0.3063, "step": 318180 }, { "epoch": 1.891387437511517, "grad_norm": 4.893556118011475, "learning_rate": 7.82086065882483e-06, "loss": 0.2932, "step": 318190 }, { "epoch": 1.8914468795881851, "grad_norm": 5.55495548248291, "learning_rate": 7.820689339027747e-06, "loss": 0.262, "step": 318200 }, { "epoch": 1.8915063216648536, "grad_norm": 5.6297101974487305, "learning_rate": 7.8205180143731e-06, "loss": 0.2794, "step": 318210 }, { "epoch": 1.891565763741522, "grad_norm": 4.832139492034912, "learning_rate": 7.820346684861182e-06, "loss": 0.2813, "step": 318220 }, { "epoch": 1.8916252058181904, "grad_norm": 5.446535110473633, "learning_rate": 7.820175350492291e-06, "loss": 0.2765, "step": 318230 }, { "epoch": 1.8916846478948588, "grad_norm": 4.431070327758789, "learning_rate": 7.820004011266725e-06, "loss": 0.2815, "step": 318240 }, { "epoch": 1.8917440899715272, "grad_norm": 4.892840385437012, "learning_rate": 7.819832667184771e-06, "loss": 0.2868, "step": 318250 }, { "epoch": 1.8918035320481956, "grad_norm": 7.079529762268066, "learning_rate": 7.819661318246732e-06, "loss": 0.3102, "step": 318260 }, { "epoch": 1.891862974124864, "grad_norm": 6.993287086486816, "learning_rate": 7.819489964452898e-06, "loss": 0.2752, "step": 318270 }, { "epoch": 1.8919224162015325, "grad_norm": 5.701323509216309, "learning_rate": 7.819318605803565e-06, "loss": 0.2835, "step": 318280 }, { "epoch": 1.8919818582782009, "grad_norm": 5.909604549407959, "learning_rate": 7.81914724229903e-06, "loss": 0.267, "step": 318290 }, { "epoch": 1.8920413003548693, "grad_norm": 6.797298908233643, "learning_rate": 7.818975873939588e-06, "loss": 0.2732, "step": 318300 }, { "epoch": 1.8921007424315377, "grad_norm": 7.347621440887451, "learning_rate": 7.818804500725532e-06, "loss": 0.2727, "step": 318310 }, { "epoch": 1.8921601845082061, "grad_norm": 5.148410320281982, "learning_rate": 7.818633122657159e-06, "loss": 0.2538, "step": 318320 }, { "epoch": 1.8922196265848745, "grad_norm": 6.133513927459717, "learning_rate": 7.818461739734764e-06, "loss": 0.3061, "step": 318330 }, { "epoch": 1.8922790686615427, "grad_norm": 4.6907477378845215, "learning_rate": 7.818290351958641e-06, "loss": 0.2955, "step": 318340 }, { "epoch": 1.8923385107382111, "grad_norm": 5.1951212882995605, "learning_rate": 7.818118959329085e-06, "loss": 0.2693, "step": 318350 }, { "epoch": 1.8923979528148795, "grad_norm": 4.744105815887451, "learning_rate": 7.817947561846394e-06, "loss": 0.2958, "step": 318360 }, { "epoch": 1.892457394891548, "grad_norm": 5.374679088592529, "learning_rate": 7.817776159510859e-06, "loss": 0.3129, "step": 318370 }, { "epoch": 1.8925168369682164, "grad_norm": 5.2322773933410645, "learning_rate": 7.817604752322779e-06, "loss": 0.2557, "step": 318380 }, { "epoch": 1.8925762790448846, "grad_norm": 3.8935461044311523, "learning_rate": 7.817433340282445e-06, "loss": 0.312, "step": 318390 }, { "epoch": 1.892635721121553, "grad_norm": 3.7501325607299805, "learning_rate": 7.817261923390156e-06, "loss": 0.2809, "step": 318400 }, { "epoch": 1.8926951631982214, "grad_norm": 3.5322813987731934, "learning_rate": 7.817090501646206e-06, "loss": 0.291, "step": 318410 }, { "epoch": 1.8927546052748898, "grad_norm": 5.135463714599609, "learning_rate": 7.81691907505089e-06, "loss": 0.2913, "step": 318420 }, { "epoch": 1.8928140473515582, "grad_norm": 3.8602092266082764, "learning_rate": 7.816747643604501e-06, "loss": 0.2526, "step": 318430 }, { "epoch": 1.8928734894282266, "grad_norm": 4.555288314819336, "learning_rate": 7.81657620730734e-06, "loss": 0.2744, "step": 318440 }, { "epoch": 1.892932931504895, "grad_norm": 6.717003345489502, "learning_rate": 7.816404766159698e-06, "loss": 0.2974, "step": 318450 }, { "epoch": 1.8929923735815635, "grad_norm": 4.574942588806152, "learning_rate": 7.81623332016187e-06, "loss": 0.2882, "step": 318460 }, { "epoch": 1.8930518156582319, "grad_norm": 4.070202827453613, "learning_rate": 7.81606186931415e-06, "loss": 0.2531, "step": 318470 }, { "epoch": 1.8931112577349003, "grad_norm": 5.88289213180542, "learning_rate": 7.815890413616839e-06, "loss": 0.3199, "step": 318480 }, { "epoch": 1.8931706998115687, "grad_norm": 4.698745250701904, "learning_rate": 7.815718953070228e-06, "loss": 0.2886, "step": 318490 }, { "epoch": 1.8932301418882371, "grad_norm": 5.336524963378906, "learning_rate": 7.81554748767461e-06, "loss": 0.3005, "step": 318500 }, { "epoch": 1.8932895839649055, "grad_norm": 5.369336128234863, "learning_rate": 7.815376017430287e-06, "loss": 0.3182, "step": 318510 }, { "epoch": 1.8933490260415737, "grad_norm": 4.789148807525635, "learning_rate": 7.81520454233755e-06, "loss": 0.2832, "step": 318520 }, { "epoch": 1.8934084681182421, "grad_norm": 6.737267017364502, "learning_rate": 7.815033062396695e-06, "loss": 0.2822, "step": 318530 }, { "epoch": 1.8934679101949106, "grad_norm": 10.066644668579102, "learning_rate": 7.814861577608015e-06, "loss": 0.26, "step": 318540 }, { "epoch": 1.893527352271579, "grad_norm": 4.269077301025391, "learning_rate": 7.81469008797181e-06, "loss": 0.2861, "step": 318550 }, { "epoch": 1.8935867943482474, "grad_norm": 5.481149673461914, "learning_rate": 7.814518593488372e-06, "loss": 0.2659, "step": 318560 }, { "epoch": 1.8936462364249156, "grad_norm": 4.4247002601623535, "learning_rate": 7.814347094157996e-06, "loss": 0.279, "step": 318570 }, { "epoch": 1.893705678501584, "grad_norm": 5.682458877563477, "learning_rate": 7.81417558998098e-06, "loss": 0.3091, "step": 318580 }, { "epoch": 1.8937651205782524, "grad_norm": 5.3967108726501465, "learning_rate": 7.814004080957616e-06, "loss": 0.2819, "step": 318590 }, { "epoch": 1.8938245626549208, "grad_norm": 5.3051276206970215, "learning_rate": 7.813832567088203e-06, "loss": 0.2901, "step": 318600 }, { "epoch": 1.8938840047315892, "grad_norm": 6.109927177429199, "learning_rate": 7.813661048373033e-06, "loss": 0.3232, "step": 318610 }, { "epoch": 1.8939434468082577, "grad_norm": 5.4640655517578125, "learning_rate": 7.813489524812404e-06, "loss": 0.2878, "step": 318620 }, { "epoch": 1.894002888884926, "grad_norm": 3.4495809078216553, "learning_rate": 7.813317996406611e-06, "loss": 0.2466, "step": 318630 }, { "epoch": 1.8940623309615945, "grad_norm": 6.338840484619141, "learning_rate": 7.813146463155948e-06, "loss": 0.2924, "step": 318640 }, { "epoch": 1.894121773038263, "grad_norm": 3.7577123641967773, "learning_rate": 7.81297492506071e-06, "loss": 0.2787, "step": 318650 }, { "epoch": 1.8941812151149313, "grad_norm": 4.788574695587158, "learning_rate": 7.812803382121195e-06, "loss": 0.2913, "step": 318660 }, { "epoch": 1.8942406571915997, "grad_norm": 6.239886283874512, "learning_rate": 7.812631834337697e-06, "loss": 0.299, "step": 318670 }, { "epoch": 1.8943000992682681, "grad_norm": 6.150119781494141, "learning_rate": 7.812460281710513e-06, "loss": 0.3063, "step": 318680 }, { "epoch": 1.8943595413449366, "grad_norm": 4.756155014038086, "learning_rate": 7.812288724239933e-06, "loss": 0.3007, "step": 318690 }, { "epoch": 1.894418983421605, "grad_norm": 6.718814849853516, "learning_rate": 7.812117161926258e-06, "loss": 0.302, "step": 318700 }, { "epoch": 1.8944784254982732, "grad_norm": 5.085412979125977, "learning_rate": 7.811945594769783e-06, "loss": 0.3077, "step": 318710 }, { "epoch": 1.8945378675749416, "grad_norm": 6.120364665985107, "learning_rate": 7.8117740227708e-06, "loss": 0.2718, "step": 318720 }, { "epoch": 1.89459730965161, "grad_norm": 5.470859050750732, "learning_rate": 7.811602445929608e-06, "loss": 0.2842, "step": 318730 }, { "epoch": 1.8946567517282784, "grad_norm": 4.75147819519043, "learning_rate": 7.811430864246501e-06, "loss": 0.2741, "step": 318740 }, { "epoch": 1.8947161938049468, "grad_norm": 4.145397663116455, "learning_rate": 7.811259277721775e-06, "loss": 0.2932, "step": 318750 }, { "epoch": 1.894775635881615, "grad_norm": 4.634668827056885, "learning_rate": 7.811087686355723e-06, "loss": 0.3002, "step": 318760 }, { "epoch": 1.8948350779582834, "grad_norm": 5.710285186767578, "learning_rate": 7.810916090148643e-06, "loss": 0.306, "step": 318770 }, { "epoch": 1.8948945200349518, "grad_norm": 5.005134105682373, "learning_rate": 7.810744489100832e-06, "loss": 0.3011, "step": 318780 }, { "epoch": 1.8949539621116203, "grad_norm": 5.104037761688232, "learning_rate": 7.810572883212583e-06, "loss": 0.266, "step": 318790 }, { "epoch": 1.8950134041882887, "grad_norm": 4.842893123626709, "learning_rate": 7.810401272484192e-06, "loss": 0.3098, "step": 318800 }, { "epoch": 1.895072846264957, "grad_norm": 4.726358890533447, "learning_rate": 7.810229656915955e-06, "loss": 0.2937, "step": 318810 }, { "epoch": 1.8951322883416255, "grad_norm": 4.17244291305542, "learning_rate": 7.810058036508167e-06, "loss": 0.2499, "step": 318820 }, { "epoch": 1.895191730418294, "grad_norm": 5.1225504875183105, "learning_rate": 7.809886411261123e-06, "loss": 0.2961, "step": 318830 }, { "epoch": 1.8952511724949623, "grad_norm": 4.069870471954346, "learning_rate": 7.80971478117512e-06, "loss": 0.2524, "step": 318840 }, { "epoch": 1.8953106145716307, "grad_norm": 5.783942699432373, "learning_rate": 7.809543146250452e-06, "loss": 0.3147, "step": 318850 }, { "epoch": 1.8953700566482992, "grad_norm": 5.02942419052124, "learning_rate": 7.809371506487417e-06, "loss": 0.2764, "step": 318860 }, { "epoch": 1.8954294987249676, "grad_norm": 5.100147724151611, "learning_rate": 7.809199861886307e-06, "loss": 0.3001, "step": 318870 }, { "epoch": 1.895488940801636, "grad_norm": 4.473742485046387, "learning_rate": 7.809028212447423e-06, "loss": 0.2979, "step": 318880 }, { "epoch": 1.8955483828783042, "grad_norm": 4.438973426818848, "learning_rate": 7.808856558171053e-06, "loss": 0.2964, "step": 318890 }, { "epoch": 1.8956078249549726, "grad_norm": 5.0851593017578125, "learning_rate": 7.8086848990575e-06, "loss": 0.277, "step": 318900 }, { "epoch": 1.895667267031641, "grad_norm": 4.959478378295898, "learning_rate": 7.808513235107056e-06, "loss": 0.2779, "step": 318910 }, { "epoch": 1.8957267091083094, "grad_norm": 4.8211212158203125, "learning_rate": 7.808341566320016e-06, "loss": 0.3163, "step": 318920 }, { "epoch": 1.8957861511849778, "grad_norm": 6.507444858551025, "learning_rate": 7.808169892696678e-06, "loss": 0.2804, "step": 318930 }, { "epoch": 1.895845593261646, "grad_norm": 4.033067226409912, "learning_rate": 7.807998214237336e-06, "loss": 0.2654, "step": 318940 }, { "epoch": 1.8959050353383144, "grad_norm": 4.748258113861084, "learning_rate": 7.807826530942286e-06, "loss": 0.3033, "step": 318950 }, { "epoch": 1.8959644774149829, "grad_norm": 4.2159342765808105, "learning_rate": 7.807654842811822e-06, "loss": 0.2971, "step": 318960 }, { "epoch": 1.8960239194916513, "grad_norm": 5.073882579803467, "learning_rate": 7.807483149846245e-06, "loss": 0.2959, "step": 318970 }, { "epoch": 1.8960833615683197, "grad_norm": 4.688161849975586, "learning_rate": 7.807311452045843e-06, "loss": 0.2915, "step": 318980 }, { "epoch": 1.896142803644988, "grad_norm": 5.1954216957092285, "learning_rate": 7.807139749410918e-06, "loss": 0.2978, "step": 318990 }, { "epoch": 1.8962022457216565, "grad_norm": 4.225099563598633, "learning_rate": 7.806968041941762e-06, "loss": 0.3049, "step": 319000 }, { "epoch": 1.896261687798325, "grad_norm": 5.273496627807617, "learning_rate": 7.806796329638676e-06, "loss": 0.2724, "step": 319010 }, { "epoch": 1.8963211298749933, "grad_norm": 4.378494739532471, "learning_rate": 7.806624612501948e-06, "loss": 0.2653, "step": 319020 }, { "epoch": 1.8963805719516618, "grad_norm": 5.619260311126709, "learning_rate": 7.806452890531878e-06, "loss": 0.2831, "step": 319030 }, { "epoch": 1.8964400140283302, "grad_norm": 4.150178909301758, "learning_rate": 7.806281163728761e-06, "loss": 0.3025, "step": 319040 }, { "epoch": 1.8964994561049986, "grad_norm": 4.742444038391113, "learning_rate": 7.806109432092895e-06, "loss": 0.2762, "step": 319050 }, { "epoch": 1.896558898181667, "grad_norm": 4.7332258224487305, "learning_rate": 7.805937695624572e-06, "loss": 0.2865, "step": 319060 }, { "epoch": 1.8966183402583354, "grad_norm": 4.108095169067383, "learning_rate": 7.80576595432409e-06, "loss": 0.2756, "step": 319070 }, { "epoch": 1.8966777823350036, "grad_norm": 5.668427467346191, "learning_rate": 7.805594208191744e-06, "loss": 0.2852, "step": 319080 }, { "epoch": 1.896737224411672, "grad_norm": 5.702456951141357, "learning_rate": 7.80542245722783e-06, "loss": 0.2956, "step": 319090 }, { "epoch": 1.8967966664883404, "grad_norm": 4.794633865356445, "learning_rate": 7.805250701432644e-06, "loss": 0.2894, "step": 319100 }, { "epoch": 1.8968561085650089, "grad_norm": 4.59803581237793, "learning_rate": 7.805078940806482e-06, "loss": 0.28, "step": 319110 }, { "epoch": 1.8969155506416773, "grad_norm": 3.9448587894439697, "learning_rate": 7.804907175349638e-06, "loss": 0.2859, "step": 319120 }, { "epoch": 1.8969749927183455, "grad_norm": 4.08807373046875, "learning_rate": 7.804735405062412e-06, "loss": 0.2894, "step": 319130 }, { "epoch": 1.8970344347950139, "grad_norm": 4.301951885223389, "learning_rate": 7.804563629945095e-06, "loss": 0.3344, "step": 319140 }, { "epoch": 1.8970938768716823, "grad_norm": 4.940084457397461, "learning_rate": 7.804391849997982e-06, "loss": 0.2815, "step": 319150 }, { "epoch": 1.8971533189483507, "grad_norm": 6.241657257080078, "learning_rate": 7.804220065221375e-06, "loss": 0.2725, "step": 319160 }, { "epoch": 1.8972127610250191, "grad_norm": 5.1376237869262695, "learning_rate": 7.804048275615568e-06, "loss": 0.2783, "step": 319170 }, { "epoch": 1.8972722031016875, "grad_norm": 5.17907190322876, "learning_rate": 7.803876481180851e-06, "loss": 0.3022, "step": 319180 }, { "epoch": 1.897331645178356, "grad_norm": 4.401787757873535, "learning_rate": 7.803704681917527e-06, "loss": 0.3052, "step": 319190 }, { "epoch": 1.8973910872550244, "grad_norm": 3.779453754425049, "learning_rate": 7.80353287782589e-06, "loss": 0.2857, "step": 319200 }, { "epoch": 1.8974505293316928, "grad_norm": 4.075033664703369, "learning_rate": 7.803361068906232e-06, "loss": 0.2987, "step": 319210 }, { "epoch": 1.8975099714083612, "grad_norm": 5.028857707977295, "learning_rate": 7.803189255158853e-06, "loss": 0.2868, "step": 319220 }, { "epoch": 1.8975694134850296, "grad_norm": 5.641091346740723, "learning_rate": 7.803017436584049e-06, "loss": 0.3153, "step": 319230 }, { "epoch": 1.897628855561698, "grad_norm": 4.036159515380859, "learning_rate": 7.802845613182113e-06, "loss": 0.2638, "step": 319240 }, { "epoch": 1.8976882976383664, "grad_norm": 5.183800220489502, "learning_rate": 7.802673784953342e-06, "loss": 0.2983, "step": 319250 }, { "epoch": 1.8977477397150346, "grad_norm": 5.054482936859131, "learning_rate": 7.802501951898033e-06, "loss": 0.2821, "step": 319260 }, { "epoch": 1.897807181791703, "grad_norm": 5.498953819274902, "learning_rate": 7.802330114016481e-06, "loss": 0.307, "step": 319270 }, { "epoch": 1.8978666238683715, "grad_norm": 5.251164436340332, "learning_rate": 7.802158271308981e-06, "loss": 0.3011, "step": 319280 }, { "epoch": 1.8979260659450399, "grad_norm": 5.7874226570129395, "learning_rate": 7.801986423775833e-06, "loss": 0.277, "step": 319290 }, { "epoch": 1.8979855080217083, "grad_norm": 5.362956523895264, "learning_rate": 7.801814571417327e-06, "loss": 0.2892, "step": 319300 }, { "epoch": 1.8980449500983765, "grad_norm": 4.57504940032959, "learning_rate": 7.801642714233765e-06, "loss": 0.2651, "step": 319310 }, { "epoch": 1.898104392175045, "grad_norm": 4.549185276031494, "learning_rate": 7.801470852225438e-06, "loss": 0.2946, "step": 319320 }, { "epoch": 1.8981638342517133, "grad_norm": 7.279600143432617, "learning_rate": 7.801298985392644e-06, "loss": 0.2865, "step": 319330 }, { "epoch": 1.8982232763283817, "grad_norm": 5.081090450286865, "learning_rate": 7.80112711373568e-06, "loss": 0.3196, "step": 319340 }, { "epoch": 1.8982827184050501, "grad_norm": 3.8440496921539307, "learning_rate": 7.80095523725484e-06, "loss": 0.2769, "step": 319350 }, { "epoch": 1.8983421604817186, "grad_norm": 4.309079170227051, "learning_rate": 7.80078335595042e-06, "loss": 0.283, "step": 319360 }, { "epoch": 1.898401602558387, "grad_norm": 5.3335442543029785, "learning_rate": 7.80061146982272e-06, "loss": 0.2907, "step": 319370 }, { "epoch": 1.8984610446350554, "grad_norm": 4.270536422729492, "learning_rate": 7.80043957887203e-06, "loss": 0.2864, "step": 319380 }, { "epoch": 1.8985204867117238, "grad_norm": 5.721475124359131, "learning_rate": 7.80026768309865e-06, "loss": 0.2872, "step": 319390 }, { "epoch": 1.8985799287883922, "grad_norm": 5.7121076583862305, "learning_rate": 7.800095782502875e-06, "loss": 0.2672, "step": 319400 }, { "epoch": 1.8986393708650606, "grad_norm": 6.718317985534668, "learning_rate": 7.799923877085001e-06, "loss": 0.2702, "step": 319410 }, { "epoch": 1.898698812941729, "grad_norm": 6.078567028045654, "learning_rate": 7.799751966845323e-06, "loss": 0.3303, "step": 319420 }, { "epoch": 1.8987582550183975, "grad_norm": 4.589061737060547, "learning_rate": 7.799580051784138e-06, "loss": 0.2649, "step": 319430 }, { "epoch": 1.8988176970950659, "grad_norm": 4.369184494018555, "learning_rate": 7.799408131901743e-06, "loss": 0.2878, "step": 319440 }, { "epoch": 1.898877139171734, "grad_norm": 5.090672969818115, "learning_rate": 7.799236207198433e-06, "loss": 0.2869, "step": 319450 }, { "epoch": 1.8989365812484025, "grad_norm": 3.6246469020843506, "learning_rate": 7.799064277674505e-06, "loss": 0.2787, "step": 319460 }, { "epoch": 1.898996023325071, "grad_norm": 5.235543251037598, "learning_rate": 7.798892343330254e-06, "loss": 0.2855, "step": 319470 }, { "epoch": 1.8990554654017393, "grad_norm": 4.028456211090088, "learning_rate": 7.798720404165976e-06, "loss": 0.2806, "step": 319480 }, { "epoch": 1.8991149074784077, "grad_norm": 4.144810199737549, "learning_rate": 7.798548460181966e-06, "loss": 0.2901, "step": 319490 }, { "epoch": 1.899174349555076, "grad_norm": 4.473872661590576, "learning_rate": 7.798376511378523e-06, "loss": 0.2642, "step": 319500 }, { "epoch": 1.8992337916317443, "grad_norm": 4.547872066497803, "learning_rate": 7.798204557755941e-06, "loss": 0.3185, "step": 319510 }, { "epoch": 1.8992932337084127, "grad_norm": 5.4178595542907715, "learning_rate": 7.79803259931452e-06, "loss": 0.2819, "step": 319520 }, { "epoch": 1.8993526757850812, "grad_norm": 3.6881234645843506, "learning_rate": 7.79786063605455e-06, "loss": 0.2742, "step": 319530 }, { "epoch": 1.8994121178617496, "grad_norm": 6.070049285888672, "learning_rate": 7.79768866797633e-06, "loss": 0.2747, "step": 319540 }, { "epoch": 1.899471559938418, "grad_norm": 4.541964530944824, "learning_rate": 7.797516695080158e-06, "loss": 0.3229, "step": 319550 }, { "epoch": 1.8995310020150864, "grad_norm": 4.912999153137207, "learning_rate": 7.797344717366328e-06, "loss": 0.3028, "step": 319560 }, { "epoch": 1.8995904440917548, "grad_norm": 5.12436580657959, "learning_rate": 7.797172734835136e-06, "loss": 0.3022, "step": 319570 }, { "epoch": 1.8996498861684232, "grad_norm": 5.996118545532227, "learning_rate": 7.797000747486879e-06, "loss": 0.2912, "step": 319580 }, { "epoch": 1.8997093282450916, "grad_norm": 5.020865440368652, "learning_rate": 7.796828755321852e-06, "loss": 0.2955, "step": 319590 }, { "epoch": 1.89976877032176, "grad_norm": 5.127835750579834, "learning_rate": 7.796656758340353e-06, "loss": 0.3025, "step": 319600 }, { "epoch": 1.8998282123984285, "grad_norm": 4.570035934448242, "learning_rate": 7.796484756542678e-06, "loss": 0.3269, "step": 319610 }, { "epoch": 1.8998876544750969, "grad_norm": 3.5077452659606934, "learning_rate": 7.796312749929122e-06, "loss": 0.2744, "step": 319620 }, { "epoch": 1.899947096551765, "grad_norm": 3.6812119483947754, "learning_rate": 7.796140738499982e-06, "loss": 0.271, "step": 319630 }, { "epoch": 1.9000065386284335, "grad_norm": 5.737827301025391, "learning_rate": 7.795968722255555e-06, "loss": 0.2859, "step": 319640 }, { "epoch": 1.900065980705102, "grad_norm": 3.7849349975585938, "learning_rate": 7.795796701196135e-06, "loss": 0.2981, "step": 319650 }, { "epoch": 1.9001254227817703, "grad_norm": 4.910406112670898, "learning_rate": 7.79562467532202e-06, "loss": 0.2893, "step": 319660 }, { "epoch": 1.9001848648584387, "grad_norm": 5.059139728546143, "learning_rate": 7.795452644633505e-06, "loss": 0.2929, "step": 319670 }, { "epoch": 1.900244306935107, "grad_norm": 7.05193567276001, "learning_rate": 7.795280609130888e-06, "loss": 0.299, "step": 319680 }, { "epoch": 1.9003037490117753, "grad_norm": 4.183769226074219, "learning_rate": 7.795108568814465e-06, "loss": 0.2876, "step": 319690 }, { "epoch": 1.9003631910884438, "grad_norm": 4.843547821044922, "learning_rate": 7.794936523684529e-06, "loss": 0.2788, "step": 319700 }, { "epoch": 1.9004226331651122, "grad_norm": 5.089284420013428, "learning_rate": 7.79476447374138e-06, "loss": 0.3032, "step": 319710 }, { "epoch": 1.9004820752417806, "grad_norm": 5.58787202835083, "learning_rate": 7.794592418985315e-06, "loss": 0.2901, "step": 319720 }, { "epoch": 1.900541517318449, "grad_norm": 4.662909507751465, "learning_rate": 7.794420359416626e-06, "loss": 0.292, "step": 319730 }, { "epoch": 1.9006009593951174, "grad_norm": 5.556455135345459, "learning_rate": 7.794248295035611e-06, "loss": 0.2651, "step": 319740 }, { "epoch": 1.9006604014717858, "grad_norm": 4.773064613342285, "learning_rate": 7.794076225842568e-06, "loss": 0.2696, "step": 319750 }, { "epoch": 1.9007198435484542, "grad_norm": 5.13067626953125, "learning_rate": 7.793904151837794e-06, "loss": 0.3118, "step": 319760 }, { "epoch": 1.9007792856251227, "grad_norm": 7.275045394897461, "learning_rate": 7.793732073021583e-06, "loss": 0.2626, "step": 319770 }, { "epoch": 1.900838727701791, "grad_norm": 4.357061862945557, "learning_rate": 7.793559989394231e-06, "loss": 0.289, "step": 319780 }, { "epoch": 1.9008981697784595, "grad_norm": 5.18262243270874, "learning_rate": 7.793387900956035e-06, "loss": 0.2831, "step": 319790 }, { "epoch": 1.900957611855128, "grad_norm": 5.400681972503662, "learning_rate": 7.793215807707292e-06, "loss": 0.3185, "step": 319800 }, { "epoch": 1.9010170539317963, "grad_norm": 5.372735500335693, "learning_rate": 7.7930437096483e-06, "loss": 0.311, "step": 319810 }, { "epoch": 1.9010764960084645, "grad_norm": 3.915459632873535, "learning_rate": 7.79287160677935e-06, "loss": 0.26, "step": 319820 }, { "epoch": 1.901135938085133, "grad_norm": 5.444474220275879, "learning_rate": 7.792699499100745e-06, "loss": 0.2933, "step": 319830 }, { "epoch": 1.9011953801618013, "grad_norm": 5.760071277618408, "learning_rate": 7.792527386612779e-06, "loss": 0.2959, "step": 319840 }, { "epoch": 1.9012548222384698, "grad_norm": 4.905543804168701, "learning_rate": 7.792355269315744e-06, "loss": 0.2948, "step": 319850 }, { "epoch": 1.901314264315138, "grad_norm": 5.49367618560791, "learning_rate": 7.792183147209942e-06, "loss": 0.3046, "step": 319860 }, { "epoch": 1.9013737063918064, "grad_norm": 5.278793811798096, "learning_rate": 7.792011020295668e-06, "loss": 0.2752, "step": 319870 }, { "epoch": 1.9014331484684748, "grad_norm": 5.723782539367676, "learning_rate": 7.791838888573218e-06, "loss": 0.3241, "step": 319880 }, { "epoch": 1.9014925905451432, "grad_norm": 7.014089107513428, "learning_rate": 7.791666752042887e-06, "loss": 0.3255, "step": 319890 }, { "epoch": 1.9015520326218116, "grad_norm": 4.540550231933594, "learning_rate": 7.791494610704973e-06, "loss": 0.293, "step": 319900 }, { "epoch": 1.90161147469848, "grad_norm": 3.6286516189575195, "learning_rate": 7.791322464559773e-06, "loss": 0.2854, "step": 319910 }, { "epoch": 1.9016709167751484, "grad_norm": 4.58969259262085, "learning_rate": 7.791150313607583e-06, "loss": 0.2833, "step": 319920 }, { "epoch": 1.9017303588518168, "grad_norm": 5.10645055770874, "learning_rate": 7.790978157848696e-06, "loss": 0.3189, "step": 319930 }, { "epoch": 1.9017898009284853, "grad_norm": 4.451138496398926, "learning_rate": 7.790805997283414e-06, "loss": 0.2887, "step": 319940 }, { "epoch": 1.9018492430051537, "grad_norm": 4.7012224197387695, "learning_rate": 7.790633831912032e-06, "loss": 0.281, "step": 319950 }, { "epoch": 1.901908685081822, "grad_norm": 3.9919862747192383, "learning_rate": 7.790461661734845e-06, "loss": 0.2648, "step": 319960 }, { "epoch": 1.9019681271584905, "grad_norm": 3.973890542984009, "learning_rate": 7.790289486752149e-06, "loss": 0.2914, "step": 319970 }, { "epoch": 1.902027569235159, "grad_norm": 5.791248798370361, "learning_rate": 7.790117306964242e-06, "loss": 0.2757, "step": 319980 }, { "epoch": 1.9020870113118273, "grad_norm": 4.796727180480957, "learning_rate": 7.78994512237142e-06, "loss": 0.2823, "step": 319990 }, { "epoch": 1.9021464533884955, "grad_norm": 6.327505111694336, "learning_rate": 7.78977293297398e-06, "loss": 0.2843, "step": 320000 }, { "epoch": 1.902205895465164, "grad_norm": 4.835315227508545, "learning_rate": 7.789600738772219e-06, "loss": 0.2859, "step": 320010 }, { "epoch": 1.9022653375418324, "grad_norm": 4.940774917602539, "learning_rate": 7.789428539766432e-06, "loss": 0.2868, "step": 320020 }, { "epoch": 1.9023247796185008, "grad_norm": 4.248334884643555, "learning_rate": 7.789256335956916e-06, "loss": 0.27, "step": 320030 }, { "epoch": 1.9023842216951692, "grad_norm": 4.8670220375061035, "learning_rate": 7.789084127343966e-06, "loss": 0.3217, "step": 320040 }, { "epoch": 1.9024436637718374, "grad_norm": 5.184963226318359, "learning_rate": 7.788911913927884e-06, "loss": 0.3074, "step": 320050 }, { "epoch": 1.9025031058485058, "grad_norm": 5.216429233551025, "learning_rate": 7.78873969570896e-06, "loss": 0.2613, "step": 320060 }, { "epoch": 1.9025625479251742, "grad_norm": 4.876762866973877, "learning_rate": 7.788567472687493e-06, "loss": 0.2991, "step": 320070 }, { "epoch": 1.9026219900018426, "grad_norm": 6.641356468200684, "learning_rate": 7.788395244863782e-06, "loss": 0.3016, "step": 320080 }, { "epoch": 1.902681432078511, "grad_norm": 5.367184162139893, "learning_rate": 7.788223012238122e-06, "loss": 0.2745, "step": 320090 }, { "epoch": 1.9027408741551795, "grad_norm": 4.541970252990723, "learning_rate": 7.788050774810809e-06, "loss": 0.2682, "step": 320100 }, { "epoch": 1.9028003162318479, "grad_norm": 6.593193054199219, "learning_rate": 7.787878532582139e-06, "loss": 0.2872, "step": 320110 }, { "epoch": 1.9028597583085163, "grad_norm": 4.271050930023193, "learning_rate": 7.78770628555241e-06, "loss": 0.293, "step": 320120 }, { "epoch": 1.9029192003851847, "grad_norm": 3.8852739334106445, "learning_rate": 7.787534033721919e-06, "loss": 0.2882, "step": 320130 }, { "epoch": 1.902978642461853, "grad_norm": 6.179661273956299, "learning_rate": 7.787361777090961e-06, "loss": 0.2908, "step": 320140 }, { "epoch": 1.9030380845385215, "grad_norm": 6.296902179718018, "learning_rate": 7.787189515659832e-06, "loss": 0.3017, "step": 320150 }, { "epoch": 1.90309752661519, "grad_norm": 4.0300774574279785, "learning_rate": 7.787017249428833e-06, "loss": 0.2776, "step": 320160 }, { "epoch": 1.9031569686918584, "grad_norm": 5.907680511474609, "learning_rate": 7.786844978398255e-06, "loss": 0.2662, "step": 320170 }, { "epoch": 1.9032164107685268, "grad_norm": 5.034904956817627, "learning_rate": 7.786672702568398e-06, "loss": 0.2692, "step": 320180 }, { "epoch": 1.903275852845195, "grad_norm": 4.849915504455566, "learning_rate": 7.78650042193956e-06, "loss": 0.2657, "step": 320190 }, { "epoch": 1.9033352949218634, "grad_norm": 6.1644487380981445, "learning_rate": 7.786328136512033e-06, "loss": 0.3136, "step": 320200 }, { "epoch": 1.9033947369985318, "grad_norm": 4.779977798461914, "learning_rate": 7.786155846286119e-06, "loss": 0.2736, "step": 320210 }, { "epoch": 1.9034541790752002, "grad_norm": 5.613974094390869, "learning_rate": 7.785983551262112e-06, "loss": 0.2963, "step": 320220 }, { "epoch": 1.9035136211518684, "grad_norm": 5.011109828948975, "learning_rate": 7.785811251440307e-06, "loss": 0.2752, "step": 320230 }, { "epoch": 1.9035730632285368, "grad_norm": 4.521664619445801, "learning_rate": 7.785638946821004e-06, "loss": 0.2973, "step": 320240 }, { "epoch": 1.9036325053052052, "grad_norm": 4.748108386993408, "learning_rate": 7.785466637404499e-06, "loss": 0.2825, "step": 320250 }, { "epoch": 1.9036919473818736, "grad_norm": 5.139268398284912, "learning_rate": 7.785294323191086e-06, "loss": 0.2718, "step": 320260 }, { "epoch": 1.903751389458542, "grad_norm": 5.634347915649414, "learning_rate": 7.785122004181064e-06, "loss": 0.2543, "step": 320270 }, { "epoch": 1.9038108315352105, "grad_norm": 4.82226037979126, "learning_rate": 7.784949680374732e-06, "loss": 0.294, "step": 320280 }, { "epoch": 1.9038702736118789, "grad_norm": 4.838350772857666, "learning_rate": 7.784777351772384e-06, "loss": 0.3005, "step": 320290 }, { "epoch": 1.9039297156885473, "grad_norm": 4.304484844207764, "learning_rate": 7.784605018374317e-06, "loss": 0.269, "step": 320300 }, { "epoch": 1.9039891577652157, "grad_norm": 5.441250801086426, "learning_rate": 7.784432680180825e-06, "loss": 0.297, "step": 320310 }, { "epoch": 1.9040485998418841, "grad_norm": 5.225231170654297, "learning_rate": 7.78426033719221e-06, "loss": 0.3253, "step": 320320 }, { "epoch": 1.9041080419185525, "grad_norm": 4.9654860496521, "learning_rate": 7.784087989408765e-06, "loss": 0.2822, "step": 320330 }, { "epoch": 1.904167483995221, "grad_norm": 7.272388458251953, "learning_rate": 7.78391563683079e-06, "loss": 0.2722, "step": 320340 }, { "epoch": 1.9042269260718894, "grad_norm": 6.63214111328125, "learning_rate": 7.783743279458579e-06, "loss": 0.3086, "step": 320350 }, { "epoch": 1.9042863681485578, "grad_norm": 4.268470764160156, "learning_rate": 7.783570917292432e-06, "loss": 0.3048, "step": 320360 }, { "epoch": 1.904345810225226, "grad_norm": 6.01021671295166, "learning_rate": 7.78339855033264e-06, "loss": 0.299, "step": 320370 }, { "epoch": 1.9044052523018944, "grad_norm": 4.357963562011719, "learning_rate": 7.783226178579509e-06, "loss": 0.2574, "step": 320380 }, { "epoch": 1.9044646943785628, "grad_norm": 4.895689487457275, "learning_rate": 7.783053802033326e-06, "loss": 0.3156, "step": 320390 }, { "epoch": 1.9045241364552312, "grad_norm": 4.203242778778076, "learning_rate": 7.782881420694393e-06, "loss": 0.247, "step": 320400 }, { "epoch": 1.9045835785318996, "grad_norm": 5.723985195159912, "learning_rate": 7.782709034563007e-06, "loss": 0.2904, "step": 320410 }, { "epoch": 1.9046430206085678, "grad_norm": 4.511838436126709, "learning_rate": 7.782536643639465e-06, "loss": 0.2859, "step": 320420 }, { "epoch": 1.9047024626852362, "grad_norm": 5.563351631164551, "learning_rate": 7.782364247924062e-06, "loss": 0.3132, "step": 320430 }, { "epoch": 1.9047619047619047, "grad_norm": 4.014270782470703, "learning_rate": 7.782191847417094e-06, "loss": 0.2814, "step": 320440 }, { "epoch": 1.904821346838573, "grad_norm": 6.538066387176514, "learning_rate": 7.782019442118862e-06, "loss": 0.315, "step": 320450 }, { "epoch": 1.9048807889152415, "grad_norm": 4.636931419372559, "learning_rate": 7.781847032029659e-06, "loss": 0.296, "step": 320460 }, { "epoch": 1.90494023099191, "grad_norm": 5.725148677825928, "learning_rate": 7.781674617149783e-06, "loss": 0.3089, "step": 320470 }, { "epoch": 1.9049996730685783, "grad_norm": 6.0417633056640625, "learning_rate": 7.781502197479533e-06, "loss": 0.321, "step": 320480 }, { "epoch": 1.9050591151452467, "grad_norm": 2.879354238510132, "learning_rate": 7.781329773019204e-06, "loss": 0.2748, "step": 320490 }, { "epoch": 1.9051185572219151, "grad_norm": 5.566316604614258, "learning_rate": 7.781157343769092e-06, "loss": 0.2879, "step": 320500 }, { "epoch": 1.9051779992985836, "grad_norm": 4.672191143035889, "learning_rate": 7.780984909729498e-06, "loss": 0.2823, "step": 320510 }, { "epoch": 1.905237441375252, "grad_norm": 3.77225399017334, "learning_rate": 7.780812470900714e-06, "loss": 0.2438, "step": 320520 }, { "epoch": 1.9052968834519204, "grad_norm": 3.7726006507873535, "learning_rate": 7.780640027283039e-06, "loss": 0.2758, "step": 320530 }, { "epoch": 1.9053563255285888, "grad_norm": 6.0959296226501465, "learning_rate": 7.78046757887677e-06, "loss": 0.2822, "step": 320540 }, { "epoch": 1.9054157676052572, "grad_norm": 5.633131504058838, "learning_rate": 7.780295125682207e-06, "loss": 0.3032, "step": 320550 }, { "epoch": 1.9054752096819254, "grad_norm": 4.373750686645508, "learning_rate": 7.78012266769964e-06, "loss": 0.2886, "step": 320560 }, { "epoch": 1.9055346517585938, "grad_norm": 3.8308074474334717, "learning_rate": 7.779950204929372e-06, "loss": 0.2693, "step": 320570 }, { "epoch": 1.9055940938352622, "grad_norm": 4.650601387023926, "learning_rate": 7.779777737371698e-06, "loss": 0.2756, "step": 320580 }, { "epoch": 1.9056535359119307, "grad_norm": 5.121057033538818, "learning_rate": 7.779605265026915e-06, "loss": 0.2913, "step": 320590 }, { "epoch": 1.9057129779885988, "grad_norm": 4.750465393066406, "learning_rate": 7.77943278789532e-06, "loss": 0.2852, "step": 320600 }, { "epoch": 1.9057724200652673, "grad_norm": 4.871310710906982, "learning_rate": 7.77926030597721e-06, "loss": 0.2945, "step": 320610 }, { "epoch": 1.9058318621419357, "grad_norm": 4.567020416259766, "learning_rate": 7.779087819272883e-06, "loss": 0.2676, "step": 320620 }, { "epoch": 1.905891304218604, "grad_norm": 5.201888561248779, "learning_rate": 7.778915327782635e-06, "loss": 0.2881, "step": 320630 }, { "epoch": 1.9059507462952725, "grad_norm": 4.090018272399902, "learning_rate": 7.778742831506763e-06, "loss": 0.2676, "step": 320640 }, { "epoch": 1.906010188371941, "grad_norm": 5.132020473480225, "learning_rate": 7.778570330445562e-06, "loss": 0.2945, "step": 320650 }, { "epoch": 1.9060696304486093, "grad_norm": 6.790102958679199, "learning_rate": 7.778397824599336e-06, "loss": 0.2889, "step": 320660 }, { "epoch": 1.9061290725252777, "grad_norm": 5.193708896636963, "learning_rate": 7.778225313968374e-06, "loss": 0.2849, "step": 320670 }, { "epoch": 1.9061885146019462, "grad_norm": 3.81254243850708, "learning_rate": 7.778052798552977e-06, "loss": 0.2881, "step": 320680 }, { "epoch": 1.9062479566786146, "grad_norm": 5.391637802124023, "learning_rate": 7.777880278353442e-06, "loss": 0.2882, "step": 320690 }, { "epoch": 1.906307398755283, "grad_norm": 5.983570098876953, "learning_rate": 7.777707753370066e-06, "loss": 0.2703, "step": 320700 }, { "epoch": 1.9063668408319514, "grad_norm": 4.314842700958252, "learning_rate": 7.777535223603146e-06, "loss": 0.274, "step": 320710 }, { "epoch": 1.9064262829086198, "grad_norm": 6.359877586364746, "learning_rate": 7.777362689052977e-06, "loss": 0.2967, "step": 320720 }, { "epoch": 1.9064857249852882, "grad_norm": 4.082645893096924, "learning_rate": 7.77719014971986e-06, "loss": 0.3007, "step": 320730 }, { "epoch": 1.9065451670619564, "grad_norm": 5.452763080596924, "learning_rate": 7.77701760560409e-06, "loss": 0.266, "step": 320740 }, { "epoch": 1.9066046091386248, "grad_norm": 6.790331840515137, "learning_rate": 7.776845056705964e-06, "loss": 0.2745, "step": 320750 }, { "epoch": 1.9066640512152933, "grad_norm": 4.142055988311768, "learning_rate": 7.776672503025779e-06, "loss": 0.3225, "step": 320760 }, { "epoch": 1.9067234932919617, "grad_norm": 4.5453996658325195, "learning_rate": 7.776499944563834e-06, "loss": 0.2712, "step": 320770 }, { "epoch": 1.90678293536863, "grad_norm": 6.780457973480225, "learning_rate": 7.776327381320424e-06, "loss": 0.2573, "step": 320780 }, { "epoch": 1.9068423774452983, "grad_norm": 4.916755676269531, "learning_rate": 7.776154813295846e-06, "loss": 0.2793, "step": 320790 }, { "epoch": 1.9069018195219667, "grad_norm": 5.162623882293701, "learning_rate": 7.7759822404904e-06, "loss": 0.2944, "step": 320800 }, { "epoch": 1.906961261598635, "grad_norm": 5.074532985687256, "learning_rate": 7.775809662904379e-06, "loss": 0.2875, "step": 320810 }, { "epoch": 1.9070207036753035, "grad_norm": 6.273111343383789, "learning_rate": 7.775637080538085e-06, "loss": 0.3017, "step": 320820 }, { "epoch": 1.907080145751972, "grad_norm": 4.985128402709961, "learning_rate": 7.775464493391811e-06, "loss": 0.2958, "step": 320830 }, { "epoch": 1.9071395878286403, "grad_norm": 4.4562788009643555, "learning_rate": 7.775291901465856e-06, "loss": 0.2959, "step": 320840 }, { "epoch": 1.9071990299053088, "grad_norm": 7.269254207611084, "learning_rate": 7.77511930476052e-06, "loss": 0.3147, "step": 320850 }, { "epoch": 1.9072584719819772, "grad_norm": 5.136757850646973, "learning_rate": 7.774946703276094e-06, "loss": 0.2798, "step": 320860 }, { "epoch": 1.9073179140586456, "grad_norm": 4.733641147613525, "learning_rate": 7.77477409701288e-06, "loss": 0.3048, "step": 320870 }, { "epoch": 1.907377356135314, "grad_norm": 5.846578598022461, "learning_rate": 7.774601485971174e-06, "loss": 0.3214, "step": 320880 }, { "epoch": 1.9074367982119824, "grad_norm": 3.8415396213531494, "learning_rate": 7.774428870151275e-06, "loss": 0.274, "step": 320890 }, { "epoch": 1.9074962402886508, "grad_norm": 5.387743949890137, "learning_rate": 7.774256249553476e-06, "loss": 0.3073, "step": 320900 }, { "epoch": 1.9075556823653192, "grad_norm": 4.892887592315674, "learning_rate": 7.774083624178077e-06, "loss": 0.2722, "step": 320910 }, { "epoch": 1.9076151244419877, "grad_norm": 5.489847183227539, "learning_rate": 7.773910994025374e-06, "loss": 0.282, "step": 320920 }, { "epoch": 1.9076745665186559, "grad_norm": 5.6619977951049805, "learning_rate": 7.773738359095666e-06, "loss": 0.3063, "step": 320930 }, { "epoch": 1.9077340085953243, "grad_norm": 5.685690879821777, "learning_rate": 7.773565719389252e-06, "loss": 0.313, "step": 320940 }, { "epoch": 1.9077934506719927, "grad_norm": 5.373100280761719, "learning_rate": 7.773393074906424e-06, "loss": 0.2717, "step": 320950 }, { "epoch": 1.907852892748661, "grad_norm": 3.504563570022583, "learning_rate": 7.773220425647483e-06, "loss": 0.2526, "step": 320960 }, { "epoch": 1.9079123348253293, "grad_norm": 5.096447467803955, "learning_rate": 7.773047771612726e-06, "loss": 0.2736, "step": 320970 }, { "epoch": 1.9079717769019977, "grad_norm": 5.1307373046875, "learning_rate": 7.772875112802449e-06, "loss": 0.3005, "step": 320980 }, { "epoch": 1.9080312189786661, "grad_norm": 5.409764289855957, "learning_rate": 7.77270244921695e-06, "loss": 0.3224, "step": 320990 }, { "epoch": 1.9080906610553345, "grad_norm": 5.475339889526367, "learning_rate": 7.77252978085653e-06, "loss": 0.2658, "step": 321000 }, { "epoch": 1.908150103132003, "grad_norm": 5.329102993011475, "learning_rate": 7.77235710772148e-06, "loss": 0.2896, "step": 321010 }, { "epoch": 1.9082095452086714, "grad_norm": 4.316894054412842, "learning_rate": 7.7721844298121e-06, "loss": 0.2866, "step": 321020 }, { "epoch": 1.9082689872853398, "grad_norm": 5.657276153564453, "learning_rate": 7.772011747128689e-06, "loss": 0.3001, "step": 321030 }, { "epoch": 1.9083284293620082, "grad_norm": 5.0406670570373535, "learning_rate": 7.771839059671542e-06, "loss": 0.2852, "step": 321040 }, { "epoch": 1.9083878714386766, "grad_norm": 5.561634540557861, "learning_rate": 7.771666367440957e-06, "loss": 0.2951, "step": 321050 }, { "epoch": 1.908447313515345, "grad_norm": 5.16749382019043, "learning_rate": 7.771493670437233e-06, "loss": 0.3193, "step": 321060 }, { "epoch": 1.9085067555920134, "grad_norm": 5.823695182800293, "learning_rate": 7.771320968660666e-06, "loss": 0.2692, "step": 321070 }, { "epoch": 1.9085661976686819, "grad_norm": 7.649488925933838, "learning_rate": 7.771148262111553e-06, "loss": 0.2729, "step": 321080 }, { "epoch": 1.9086256397453503, "grad_norm": 5.145723342895508, "learning_rate": 7.770975550790191e-06, "loss": 0.2822, "step": 321090 }, { "epoch": 1.9086850818220187, "grad_norm": 4.262170314788818, "learning_rate": 7.77080283469688e-06, "loss": 0.2884, "step": 321100 }, { "epoch": 1.9087445238986869, "grad_norm": 4.822778701782227, "learning_rate": 7.770630113831918e-06, "loss": 0.296, "step": 321110 }, { "epoch": 1.9088039659753553, "grad_norm": 4.142884731292725, "learning_rate": 7.770457388195596e-06, "loss": 0.2905, "step": 321120 }, { "epoch": 1.9088634080520237, "grad_norm": 5.07090950012207, "learning_rate": 7.770284657788218e-06, "loss": 0.2748, "step": 321130 }, { "epoch": 1.9089228501286921, "grad_norm": 5.547768592834473, "learning_rate": 7.770111922610079e-06, "loss": 0.2963, "step": 321140 }, { "epoch": 1.9089822922053605, "grad_norm": 4.98638391494751, "learning_rate": 7.769939182661478e-06, "loss": 0.2753, "step": 321150 }, { "epoch": 1.9090417342820287, "grad_norm": 4.694300174713135, "learning_rate": 7.76976643794271e-06, "loss": 0.2821, "step": 321160 }, { "epoch": 1.9091011763586971, "grad_norm": 5.6426005363464355, "learning_rate": 7.769593688454073e-06, "loss": 0.2643, "step": 321170 }, { "epoch": 1.9091606184353656, "grad_norm": 4.899416923522949, "learning_rate": 7.769420934195867e-06, "loss": 0.3216, "step": 321180 }, { "epoch": 1.909220060512034, "grad_norm": 5.679945468902588, "learning_rate": 7.769248175168387e-06, "loss": 0.2441, "step": 321190 }, { "epoch": 1.9092795025887024, "grad_norm": 4.638890266418457, "learning_rate": 7.769075411371932e-06, "loss": 0.2672, "step": 321200 }, { "epoch": 1.9093389446653708, "grad_norm": 5.266242027282715, "learning_rate": 7.768902642806797e-06, "loss": 0.3112, "step": 321210 }, { "epoch": 1.9093983867420392, "grad_norm": 4.735764980316162, "learning_rate": 7.768729869473281e-06, "loss": 0.2625, "step": 321220 }, { "epoch": 1.9094578288187076, "grad_norm": 4.202127456665039, "learning_rate": 7.768557091371683e-06, "loss": 0.2523, "step": 321230 }, { "epoch": 1.909517270895376, "grad_norm": 5.105688571929932, "learning_rate": 7.7683843085023e-06, "loss": 0.2804, "step": 321240 }, { "epoch": 1.9095767129720445, "grad_norm": 4.643923282623291, "learning_rate": 7.768211520865428e-06, "loss": 0.2836, "step": 321250 }, { "epoch": 1.9096361550487129, "grad_norm": 5.389118194580078, "learning_rate": 7.768038728461365e-06, "loss": 0.3025, "step": 321260 }, { "epoch": 1.9096955971253813, "grad_norm": 4.1216721534729, "learning_rate": 7.76786593129041e-06, "loss": 0.2519, "step": 321270 }, { "epoch": 1.9097550392020497, "grad_norm": 5.0174455642700195, "learning_rate": 7.767693129352857e-06, "loss": 0.2787, "step": 321280 }, { "epoch": 1.9098144812787181, "grad_norm": 4.049004077911377, "learning_rate": 7.76752032264901e-06, "loss": 0.2658, "step": 321290 }, { "epoch": 1.9098739233553863, "grad_norm": 4.170134544372559, "learning_rate": 7.767347511179162e-06, "loss": 0.2673, "step": 321300 }, { "epoch": 1.9099333654320547, "grad_norm": 6.048680305480957, "learning_rate": 7.76717469494361e-06, "loss": 0.3154, "step": 321310 }, { "epoch": 1.9099928075087231, "grad_norm": 3.792633533477783, "learning_rate": 7.767001873942655e-06, "loss": 0.2688, "step": 321320 }, { "epoch": 1.9100522495853915, "grad_norm": 4.417940139770508, "learning_rate": 7.766829048176589e-06, "loss": 0.2619, "step": 321330 }, { "epoch": 1.9101116916620597, "grad_norm": 4.669234752655029, "learning_rate": 7.766656217645717e-06, "loss": 0.2673, "step": 321340 }, { "epoch": 1.9101711337387282, "grad_norm": 5.164283275604248, "learning_rate": 7.76648338235033e-06, "loss": 0.2793, "step": 321350 }, { "epoch": 1.9102305758153966, "grad_norm": 4.705352783203125, "learning_rate": 7.76631054229073e-06, "loss": 0.2834, "step": 321360 }, { "epoch": 1.910290017892065, "grad_norm": 4.523997783660889, "learning_rate": 7.766137697467213e-06, "loss": 0.2642, "step": 321370 }, { "epoch": 1.9103494599687334, "grad_norm": 6.085474014282227, "learning_rate": 7.765964847880076e-06, "loss": 0.2978, "step": 321380 }, { "epoch": 1.9104089020454018, "grad_norm": 5.734559059143066, "learning_rate": 7.76579199352962e-06, "loss": 0.2898, "step": 321390 }, { "epoch": 1.9104683441220702, "grad_norm": 4.104042053222656, "learning_rate": 7.765619134416139e-06, "loss": 0.3273, "step": 321400 }, { "epoch": 1.9105277861987386, "grad_norm": 5.802376747131348, "learning_rate": 7.76544627053993e-06, "loss": 0.3089, "step": 321410 }, { "epoch": 1.910587228275407, "grad_norm": 5.02992582321167, "learning_rate": 7.765273401901295e-06, "loss": 0.3105, "step": 321420 }, { "epoch": 1.9106466703520755, "grad_norm": 4.658700942993164, "learning_rate": 7.765100528500527e-06, "loss": 0.2692, "step": 321430 }, { "epoch": 1.9107061124287439, "grad_norm": 3.6165590286254883, "learning_rate": 7.764927650337927e-06, "loss": 0.2884, "step": 321440 }, { "epoch": 1.9107655545054123, "grad_norm": 5.1939215660095215, "learning_rate": 7.764754767413793e-06, "loss": 0.2581, "step": 321450 }, { "epoch": 1.9108249965820807, "grad_norm": 4.634294033050537, "learning_rate": 7.764581879728419e-06, "loss": 0.2578, "step": 321460 }, { "epoch": 1.9108844386587491, "grad_norm": 5.614186763763428, "learning_rate": 7.764408987282106e-06, "loss": 0.2794, "step": 321470 }, { "epoch": 1.9109438807354173, "grad_norm": 6.318570613861084, "learning_rate": 7.764236090075152e-06, "loss": 0.2973, "step": 321480 }, { "epoch": 1.9110033228120857, "grad_norm": 4.729276657104492, "learning_rate": 7.764063188107853e-06, "loss": 0.2774, "step": 321490 }, { "epoch": 1.9110627648887542, "grad_norm": 5.648561000823975, "learning_rate": 7.763890281380508e-06, "loss": 0.2932, "step": 321500 }, { "epoch": 1.9111222069654226, "grad_norm": 6.828869342803955, "learning_rate": 7.763717369893413e-06, "loss": 0.3022, "step": 321510 }, { "epoch": 1.911181649042091, "grad_norm": 5.64813232421875, "learning_rate": 7.763544453646867e-06, "loss": 0.2764, "step": 321520 }, { "epoch": 1.9112410911187592, "grad_norm": 4.718214511871338, "learning_rate": 7.763371532641168e-06, "loss": 0.2812, "step": 321530 }, { "epoch": 1.9113005331954276, "grad_norm": 4.400645732879639, "learning_rate": 7.763198606876615e-06, "loss": 0.2793, "step": 321540 }, { "epoch": 1.911359975272096, "grad_norm": 3.8040475845336914, "learning_rate": 7.763025676353501e-06, "loss": 0.3083, "step": 321550 }, { "epoch": 1.9114194173487644, "grad_norm": 5.526897430419922, "learning_rate": 7.76285274107213e-06, "loss": 0.2925, "step": 321560 }, { "epoch": 1.9114788594254328, "grad_norm": 5.100221633911133, "learning_rate": 7.762679801032796e-06, "loss": 0.2773, "step": 321570 }, { "epoch": 1.9115383015021012, "grad_norm": 3.871826410293579, "learning_rate": 7.762506856235796e-06, "loss": 0.2995, "step": 321580 }, { "epoch": 1.9115977435787697, "grad_norm": 6.1429266929626465, "learning_rate": 7.762333906681431e-06, "loss": 0.3099, "step": 321590 }, { "epoch": 1.911657185655438, "grad_norm": 6.085879802703857, "learning_rate": 7.762160952369999e-06, "loss": 0.282, "step": 321600 }, { "epoch": 1.9117166277321065, "grad_norm": 5.6052470207214355, "learning_rate": 7.761987993301796e-06, "loss": 0.2953, "step": 321610 }, { "epoch": 1.911776069808775, "grad_norm": 4.662712574005127, "learning_rate": 7.761815029477118e-06, "loss": 0.2756, "step": 321620 }, { "epoch": 1.9118355118854433, "grad_norm": 5.5800909996032715, "learning_rate": 7.761642060896267e-06, "loss": 0.2692, "step": 321630 }, { "epoch": 1.9118949539621117, "grad_norm": 4.205834865570068, "learning_rate": 7.761469087559536e-06, "loss": 0.2885, "step": 321640 }, { "epoch": 1.9119543960387801, "grad_norm": 6.174051284790039, "learning_rate": 7.761296109467228e-06, "loss": 0.2672, "step": 321650 }, { "epoch": 1.9120138381154486, "grad_norm": 4.730685710906982, "learning_rate": 7.761123126619639e-06, "loss": 0.3168, "step": 321660 }, { "epoch": 1.9120732801921168, "grad_norm": 4.514004230499268, "learning_rate": 7.760950139017066e-06, "loss": 0.2842, "step": 321670 }, { "epoch": 1.9121327222687852, "grad_norm": 4.151491641998291, "learning_rate": 7.760777146659807e-06, "loss": 0.2665, "step": 321680 }, { "epoch": 1.9121921643454536, "grad_norm": 5.5336713790893555, "learning_rate": 7.760604149548159e-06, "loss": 0.2796, "step": 321690 }, { "epoch": 1.912251606422122, "grad_norm": 5.781860828399658, "learning_rate": 7.760431147682423e-06, "loss": 0.3022, "step": 321700 }, { "epoch": 1.9123110484987902, "grad_norm": 5.577198028564453, "learning_rate": 7.760258141062894e-06, "loss": 0.2773, "step": 321710 }, { "epoch": 1.9123704905754586, "grad_norm": 4.360363960266113, "learning_rate": 7.760085129689875e-06, "loss": 0.3201, "step": 321720 }, { "epoch": 1.912429932652127, "grad_norm": 4.755269527435303, "learning_rate": 7.759912113563657e-06, "loss": 0.2942, "step": 321730 }, { "epoch": 1.9124893747287954, "grad_norm": 4.35806131362915, "learning_rate": 7.75973909268454e-06, "loss": 0.2681, "step": 321740 }, { "epoch": 1.9125488168054638, "grad_norm": 5.545081615447998, "learning_rate": 7.759566067052824e-06, "loss": 0.2957, "step": 321750 }, { "epoch": 1.9126082588821323, "grad_norm": 5.701346397399902, "learning_rate": 7.759393036668808e-06, "loss": 0.2982, "step": 321760 }, { "epoch": 1.9126677009588007, "grad_norm": 6.231781005859375, "learning_rate": 7.759220001532786e-06, "loss": 0.2948, "step": 321770 }, { "epoch": 1.912727143035469, "grad_norm": 3.3526268005371094, "learning_rate": 7.759046961645057e-06, "loss": 0.2786, "step": 321780 }, { "epoch": 1.9127865851121375, "grad_norm": 6.894505023956299, "learning_rate": 7.75887391700592e-06, "loss": 0.3042, "step": 321790 }, { "epoch": 1.912846027188806, "grad_norm": 5.786044597625732, "learning_rate": 7.758700867615674e-06, "loss": 0.2875, "step": 321800 }, { "epoch": 1.9129054692654743, "grad_norm": 4.062945365905762, "learning_rate": 7.758527813474617e-06, "loss": 0.3323, "step": 321810 }, { "epoch": 1.9129649113421427, "grad_norm": 4.770710468292236, "learning_rate": 7.758354754583044e-06, "loss": 0.283, "step": 321820 }, { "epoch": 1.9130243534188112, "grad_norm": 4.545518398284912, "learning_rate": 7.758181690941256e-06, "loss": 0.3052, "step": 321830 }, { "epoch": 1.9130837954954796, "grad_norm": 4.153277397155762, "learning_rate": 7.758008622549551e-06, "loss": 0.2976, "step": 321840 }, { "epoch": 1.9131432375721478, "grad_norm": 4.879257678985596, "learning_rate": 7.757835549408224e-06, "loss": 0.2792, "step": 321850 }, { "epoch": 1.9132026796488162, "grad_norm": 3.771186590194702, "learning_rate": 7.757662471517576e-06, "loss": 0.2541, "step": 321860 }, { "epoch": 1.9132621217254846, "grad_norm": 4.194338798522949, "learning_rate": 7.757489388877905e-06, "loss": 0.2854, "step": 321870 }, { "epoch": 1.913321563802153, "grad_norm": 5.567135334014893, "learning_rate": 7.757316301489507e-06, "loss": 0.2961, "step": 321880 }, { "epoch": 1.9133810058788214, "grad_norm": 4.008162975311279, "learning_rate": 7.757143209352682e-06, "loss": 0.2904, "step": 321890 }, { "epoch": 1.9134404479554896, "grad_norm": 4.810972690582275, "learning_rate": 7.756970112467727e-06, "loss": 0.2977, "step": 321900 }, { "epoch": 1.913499890032158, "grad_norm": 5.062269687652588, "learning_rate": 7.75679701083494e-06, "loss": 0.2748, "step": 321910 }, { "epoch": 1.9135593321088264, "grad_norm": 6.428415775299072, "learning_rate": 7.756623904454621e-06, "loss": 0.2726, "step": 321920 }, { "epoch": 1.9136187741854949, "grad_norm": 4.523210525512695, "learning_rate": 7.756450793327066e-06, "loss": 0.2888, "step": 321930 }, { "epoch": 1.9136782162621633, "grad_norm": 4.954160213470459, "learning_rate": 7.756277677452573e-06, "loss": 0.2999, "step": 321940 }, { "epoch": 1.9137376583388317, "grad_norm": 4.958768367767334, "learning_rate": 7.756104556831443e-06, "loss": 0.2794, "step": 321950 }, { "epoch": 1.9137971004155, "grad_norm": 5.184624671936035, "learning_rate": 7.75593143146397e-06, "loss": 0.2805, "step": 321960 }, { "epoch": 1.9138565424921685, "grad_norm": 5.177396774291992, "learning_rate": 7.755758301350456e-06, "loss": 0.2674, "step": 321970 }, { "epoch": 1.913915984568837, "grad_norm": 6.524484157562256, "learning_rate": 7.755585166491197e-06, "loss": 0.2753, "step": 321980 }, { "epoch": 1.9139754266455054, "grad_norm": 5.509089469909668, "learning_rate": 7.75541202688649e-06, "loss": 0.2854, "step": 321990 }, { "epoch": 1.9140348687221738, "grad_norm": 5.670044422149658, "learning_rate": 7.755238882536637e-06, "loss": 0.293, "step": 322000 }, { "epoch": 1.9140943107988422, "grad_norm": 5.3148579597473145, "learning_rate": 7.755065733441932e-06, "loss": 0.277, "step": 322010 }, { "epoch": 1.9141537528755106, "grad_norm": 5.287055492401123, "learning_rate": 7.754892579602674e-06, "loss": 0.2901, "step": 322020 }, { "epoch": 1.914213194952179, "grad_norm": 4.102417469024658, "learning_rate": 7.754719421019165e-06, "loss": 0.2946, "step": 322030 }, { "epoch": 1.9142726370288472, "grad_norm": 5.177289962768555, "learning_rate": 7.754546257691701e-06, "loss": 0.2579, "step": 322040 }, { "epoch": 1.9143320791055156, "grad_norm": 6.02134895324707, "learning_rate": 7.754373089620578e-06, "loss": 0.2985, "step": 322050 }, { "epoch": 1.914391521182184, "grad_norm": 4.097111701965332, "learning_rate": 7.754199916806095e-06, "loss": 0.2539, "step": 322060 }, { "epoch": 1.9144509632588524, "grad_norm": 8.280158996582031, "learning_rate": 7.754026739248555e-06, "loss": 0.3301, "step": 322070 }, { "epoch": 1.9145104053355206, "grad_norm": 4.724422454833984, "learning_rate": 7.75385355694825e-06, "loss": 0.2792, "step": 322080 }, { "epoch": 1.914569847412189, "grad_norm": 5.754063606262207, "learning_rate": 7.753680369905478e-06, "loss": 0.2773, "step": 322090 }, { "epoch": 1.9146292894888575, "grad_norm": 4.476226329803467, "learning_rate": 7.753507178120543e-06, "loss": 0.2759, "step": 322100 }, { "epoch": 1.9146887315655259, "grad_norm": 6.264169692993164, "learning_rate": 7.753333981593739e-06, "loss": 0.2637, "step": 322110 }, { "epoch": 1.9147481736421943, "grad_norm": 5.792732238769531, "learning_rate": 7.753160780325365e-06, "loss": 0.3109, "step": 322120 }, { "epoch": 1.9148076157188627, "grad_norm": 5.182522773742676, "learning_rate": 7.75298757431572e-06, "loss": 0.2684, "step": 322130 }, { "epoch": 1.9148670577955311, "grad_norm": 5.483085632324219, "learning_rate": 7.752814363565103e-06, "loss": 0.2863, "step": 322140 }, { "epoch": 1.9149264998721995, "grad_norm": 4.966560363769531, "learning_rate": 7.75264114807381e-06, "loss": 0.2822, "step": 322150 }, { "epoch": 1.914985941948868, "grad_norm": 5.523221492767334, "learning_rate": 7.75246792784214e-06, "loss": 0.2858, "step": 322160 }, { "epoch": 1.9150453840255364, "grad_norm": 4.360236167907715, "learning_rate": 7.752294702870393e-06, "loss": 0.292, "step": 322170 }, { "epoch": 1.9151048261022048, "grad_norm": 5.598211288452148, "learning_rate": 7.752121473158866e-06, "loss": 0.2712, "step": 322180 }, { "epoch": 1.9151642681788732, "grad_norm": 5.993217945098877, "learning_rate": 7.751948238707856e-06, "loss": 0.3147, "step": 322190 }, { "epoch": 1.9152237102555416, "grad_norm": 4.995401382446289, "learning_rate": 7.751774999517665e-06, "loss": 0.3094, "step": 322200 }, { "epoch": 1.91528315233221, "grad_norm": 5.646591663360596, "learning_rate": 7.75160175558859e-06, "loss": 0.289, "step": 322210 }, { "epoch": 1.9153425944088782, "grad_norm": 5.774620532989502, "learning_rate": 7.751428506920925e-06, "loss": 0.278, "step": 322220 }, { "epoch": 1.9154020364855466, "grad_norm": 5.5204267501831055, "learning_rate": 7.751255253514974e-06, "loss": 0.3093, "step": 322230 }, { "epoch": 1.915461478562215, "grad_norm": 4.910901069641113, "learning_rate": 7.751081995371031e-06, "loss": 0.307, "step": 322240 }, { "epoch": 1.9155209206388835, "grad_norm": 4.509445667266846, "learning_rate": 7.750908732489398e-06, "loss": 0.2857, "step": 322250 }, { "epoch": 1.9155803627155519, "grad_norm": 5.02779483795166, "learning_rate": 7.750735464870373e-06, "loss": 0.2903, "step": 322260 }, { "epoch": 1.91563980479222, "grad_norm": 5.281944274902344, "learning_rate": 7.750562192514252e-06, "loss": 0.2629, "step": 322270 }, { "epoch": 1.9156992468688885, "grad_norm": 5.222230911254883, "learning_rate": 7.750388915421334e-06, "loss": 0.308, "step": 322280 }, { "epoch": 1.915758688945557, "grad_norm": 4.435738563537598, "learning_rate": 7.75021563359192e-06, "loss": 0.2765, "step": 322290 }, { "epoch": 1.9158181310222253, "grad_norm": 4.4015960693359375, "learning_rate": 7.750042347026305e-06, "loss": 0.3069, "step": 322300 }, { "epoch": 1.9158775730988937, "grad_norm": 5.1757121086120605, "learning_rate": 7.74986905572479e-06, "loss": 0.3184, "step": 322310 }, { "epoch": 1.9159370151755621, "grad_norm": 5.570037364959717, "learning_rate": 7.749695759687671e-06, "loss": 0.2799, "step": 322320 }, { "epoch": 1.9159964572522306, "grad_norm": 5.71963357925415, "learning_rate": 7.74952245891525e-06, "loss": 0.3252, "step": 322330 }, { "epoch": 1.916055899328899, "grad_norm": 4.631934642791748, "learning_rate": 7.74934915340782e-06, "loss": 0.2632, "step": 322340 }, { "epoch": 1.9161153414055674, "grad_norm": 7.538589000701904, "learning_rate": 7.749175843165686e-06, "loss": 0.3033, "step": 322350 }, { "epoch": 1.9161747834822358, "grad_norm": 4.807750701904297, "learning_rate": 7.749002528189143e-06, "loss": 0.2709, "step": 322360 }, { "epoch": 1.9162342255589042, "grad_norm": 5.687036514282227, "learning_rate": 7.748829208478488e-06, "loss": 0.2829, "step": 322370 }, { "epoch": 1.9162936676355726, "grad_norm": 5.505180358886719, "learning_rate": 7.748655884034022e-06, "loss": 0.2532, "step": 322380 }, { "epoch": 1.916353109712241, "grad_norm": 6.000914096832275, "learning_rate": 7.748482554856043e-06, "loss": 0.3068, "step": 322390 }, { "epoch": 1.9164125517889095, "grad_norm": 6.60636043548584, "learning_rate": 7.748309220944847e-06, "loss": 0.3159, "step": 322400 }, { "epoch": 1.9164719938655776, "grad_norm": 4.9243035316467285, "learning_rate": 7.748135882300736e-06, "loss": 0.2703, "step": 322410 }, { "epoch": 1.916531435942246, "grad_norm": 5.402668476104736, "learning_rate": 7.747962538924008e-06, "loss": 0.2957, "step": 322420 }, { "epoch": 1.9165908780189145, "grad_norm": 4.02627420425415, "learning_rate": 7.74778919081496e-06, "loss": 0.2618, "step": 322430 }, { "epoch": 1.916650320095583, "grad_norm": 4.019661903381348, "learning_rate": 7.74761583797389e-06, "loss": 0.2985, "step": 322440 }, { "epoch": 1.916709762172251, "grad_norm": 4.930426597595215, "learning_rate": 7.747442480401099e-06, "loss": 0.2967, "step": 322450 }, { "epoch": 1.9167692042489195, "grad_norm": 4.276146411895752, "learning_rate": 7.747269118096882e-06, "loss": 0.3024, "step": 322460 }, { "epoch": 1.916828646325588, "grad_norm": 3.825251817703247, "learning_rate": 7.747095751061543e-06, "loss": 0.2682, "step": 322470 }, { "epoch": 1.9168880884022563, "grad_norm": 4.502659320831299, "learning_rate": 7.746922379295376e-06, "loss": 0.3023, "step": 322480 }, { "epoch": 1.9169475304789247, "grad_norm": 4.039971351623535, "learning_rate": 7.746749002798682e-06, "loss": 0.2849, "step": 322490 }, { "epoch": 1.9170069725555932, "grad_norm": 4.6938629150390625, "learning_rate": 7.746575621571757e-06, "loss": 0.2934, "step": 322500 }, { "epoch": 1.9170664146322616, "grad_norm": 6.10841703414917, "learning_rate": 7.7464022356149e-06, "loss": 0.2859, "step": 322510 }, { "epoch": 1.91712585670893, "grad_norm": 6.542918682098389, "learning_rate": 7.746228844928413e-06, "loss": 0.2556, "step": 322520 }, { "epoch": 1.9171852987855984, "grad_norm": 5.550550937652588, "learning_rate": 7.746055449512591e-06, "loss": 0.2861, "step": 322530 }, { "epoch": 1.9172447408622668, "grad_norm": 3.9241340160369873, "learning_rate": 7.745882049367734e-06, "loss": 0.2791, "step": 322540 }, { "epoch": 1.9173041829389352, "grad_norm": 6.871211051940918, "learning_rate": 7.74570864449414e-06, "loss": 0.2976, "step": 322550 }, { "epoch": 1.9173636250156036, "grad_norm": 3.4545671939849854, "learning_rate": 7.745535234892109e-06, "loss": 0.286, "step": 322560 }, { "epoch": 1.917423067092272, "grad_norm": 5.287326335906982, "learning_rate": 7.745361820561938e-06, "loss": 0.304, "step": 322570 }, { "epoch": 1.9174825091689405, "grad_norm": 3.564887523651123, "learning_rate": 7.745188401503928e-06, "loss": 0.2627, "step": 322580 }, { "epoch": 1.9175419512456087, "grad_norm": 5.7633891105651855, "learning_rate": 7.745014977718375e-06, "loss": 0.2965, "step": 322590 }, { "epoch": 1.917601393322277, "grad_norm": 4.929312229156494, "learning_rate": 7.744841549205578e-06, "loss": 0.2786, "step": 322600 }, { "epoch": 1.9176608353989455, "grad_norm": 5.005314826965332, "learning_rate": 7.744668115965837e-06, "loss": 0.2706, "step": 322610 }, { "epoch": 1.917720277475614, "grad_norm": 5.139118194580078, "learning_rate": 7.74449467799945e-06, "loss": 0.2831, "step": 322620 }, { "epoch": 1.9177797195522823, "grad_norm": 4.64725399017334, "learning_rate": 7.744321235306715e-06, "loss": 0.2738, "step": 322630 }, { "epoch": 1.9178391616289505, "grad_norm": 5.129177093505859, "learning_rate": 7.744147787887933e-06, "loss": 0.3061, "step": 322640 }, { "epoch": 1.917898603705619, "grad_norm": 4.665308475494385, "learning_rate": 7.7439743357434e-06, "loss": 0.2528, "step": 322650 }, { "epoch": 1.9179580457822873, "grad_norm": 4.627000331878662, "learning_rate": 7.743800878873416e-06, "loss": 0.2478, "step": 322660 }, { "epoch": 1.9180174878589558, "grad_norm": 4.544497966766357, "learning_rate": 7.74362741727828e-06, "loss": 0.287, "step": 322670 }, { "epoch": 1.9180769299356242, "grad_norm": 6.70631217956543, "learning_rate": 7.743453950958289e-06, "loss": 0.2447, "step": 322680 }, { "epoch": 1.9181363720122926, "grad_norm": 5.329702854156494, "learning_rate": 7.743280479913743e-06, "loss": 0.2905, "step": 322690 }, { "epoch": 1.918195814088961, "grad_norm": 4.525388717651367, "learning_rate": 7.74310700414494e-06, "loss": 0.3038, "step": 322700 }, { "epoch": 1.9182552561656294, "grad_norm": 5.513645172119141, "learning_rate": 7.74293352365218e-06, "loss": 0.281, "step": 322710 }, { "epoch": 1.9183146982422978, "grad_norm": 4.37969970703125, "learning_rate": 7.742760038435764e-06, "loss": 0.2964, "step": 322720 }, { "epoch": 1.9183741403189662, "grad_norm": 4.67322301864624, "learning_rate": 7.742586548495984e-06, "loss": 0.2987, "step": 322730 }, { "epoch": 1.9184335823956347, "grad_norm": 4.836743354797363, "learning_rate": 7.742413053833146e-06, "loss": 0.2939, "step": 322740 }, { "epoch": 1.918493024472303, "grad_norm": 4.613743782043457, "learning_rate": 7.742239554447544e-06, "loss": 0.3042, "step": 322750 }, { "epoch": 1.9185524665489715, "grad_norm": 4.122216701507568, "learning_rate": 7.742066050339478e-06, "loss": 0.2621, "step": 322760 }, { "epoch": 1.91861190862564, "grad_norm": 4.823362827301025, "learning_rate": 7.741892541509248e-06, "loss": 0.2636, "step": 322770 }, { "epoch": 1.918671350702308, "grad_norm": 3.1370010375976562, "learning_rate": 7.74171902795715e-06, "loss": 0.2906, "step": 322780 }, { "epoch": 1.9187307927789765, "grad_norm": 5.098496437072754, "learning_rate": 7.741545509683485e-06, "loss": 0.2614, "step": 322790 }, { "epoch": 1.918790234855645, "grad_norm": 4.687753677368164, "learning_rate": 7.741371986688554e-06, "loss": 0.2584, "step": 322800 }, { "epoch": 1.9188496769323133, "grad_norm": 4.541540622711182, "learning_rate": 7.741198458972652e-06, "loss": 0.2771, "step": 322810 }, { "epoch": 1.9189091190089815, "grad_norm": 4.657423496246338, "learning_rate": 7.74102492653608e-06, "loss": 0.2841, "step": 322820 }, { "epoch": 1.91896856108565, "grad_norm": 6.028242588043213, "learning_rate": 7.740851389379133e-06, "loss": 0.2797, "step": 322830 }, { "epoch": 1.9190280031623184, "grad_norm": 5.959486484527588, "learning_rate": 7.740677847502116e-06, "loss": 0.307, "step": 322840 }, { "epoch": 1.9190874452389868, "grad_norm": 4.506704330444336, "learning_rate": 7.740504300905323e-06, "loss": 0.2633, "step": 322850 }, { "epoch": 1.9191468873156552, "grad_norm": 5.639561176300049, "learning_rate": 7.740330749589055e-06, "loss": 0.2713, "step": 322860 }, { "epoch": 1.9192063293923236, "grad_norm": 5.272469997406006, "learning_rate": 7.740157193553613e-06, "loss": 0.3046, "step": 322870 }, { "epoch": 1.919265771468992, "grad_norm": 4.690340518951416, "learning_rate": 7.739983632799291e-06, "loss": 0.2774, "step": 322880 }, { "epoch": 1.9193252135456604, "grad_norm": 5.109084606170654, "learning_rate": 7.739810067326389e-06, "loss": 0.2863, "step": 322890 }, { "epoch": 1.9193846556223289, "grad_norm": 8.990943908691406, "learning_rate": 7.739636497135209e-06, "loss": 0.2975, "step": 322900 }, { "epoch": 1.9194440976989973, "grad_norm": 5.125380516052246, "learning_rate": 7.739462922226046e-06, "loss": 0.2838, "step": 322910 }, { "epoch": 1.9195035397756657, "grad_norm": 4.92502498626709, "learning_rate": 7.739289342599203e-06, "loss": 0.287, "step": 322920 }, { "epoch": 1.919562981852334, "grad_norm": 5.645854949951172, "learning_rate": 7.739115758254976e-06, "loss": 0.2697, "step": 322930 }, { "epoch": 1.9196224239290025, "grad_norm": 4.9336419105529785, "learning_rate": 7.738942169193665e-06, "loss": 0.3345, "step": 322940 }, { "epoch": 1.919681866005671, "grad_norm": 5.09282922744751, "learning_rate": 7.73876857541557e-06, "loss": 0.2804, "step": 322950 }, { "epoch": 1.9197413080823391, "grad_norm": 5.106408596038818, "learning_rate": 7.738594976920989e-06, "loss": 0.2667, "step": 322960 }, { "epoch": 1.9198007501590075, "grad_norm": 6.446590423583984, "learning_rate": 7.738421373710219e-06, "loss": 0.2898, "step": 322970 }, { "epoch": 1.919860192235676, "grad_norm": 6.969088554382324, "learning_rate": 7.738247765783562e-06, "loss": 0.2866, "step": 322980 }, { "epoch": 1.9199196343123444, "grad_norm": 4.539636135101318, "learning_rate": 7.738074153141314e-06, "loss": 0.3051, "step": 322990 }, { "epoch": 1.9199790763890128, "grad_norm": 7.406282424926758, "learning_rate": 7.737900535783775e-06, "loss": 0.3003, "step": 323000 }, { "epoch": 1.920038518465681, "grad_norm": 5.663327693939209, "learning_rate": 7.737726913711247e-06, "loss": 0.2847, "step": 323010 }, { "epoch": 1.9200979605423494, "grad_norm": 5.985437393188477, "learning_rate": 7.737553286924024e-06, "loss": 0.3301, "step": 323020 }, { "epoch": 1.9201574026190178, "grad_norm": 4.713814735412598, "learning_rate": 7.73737965542241e-06, "loss": 0.3199, "step": 323030 }, { "epoch": 1.9202168446956862, "grad_norm": 5.936275005340576, "learning_rate": 7.737206019206702e-06, "loss": 0.2774, "step": 323040 }, { "epoch": 1.9202762867723546, "grad_norm": 4.5321364402771, "learning_rate": 7.737032378277196e-06, "loss": 0.2555, "step": 323050 }, { "epoch": 1.920335728849023, "grad_norm": 5.6849260330200195, "learning_rate": 7.736858732634196e-06, "loss": 0.2974, "step": 323060 }, { "epoch": 1.9203951709256915, "grad_norm": 6.9153571128845215, "learning_rate": 7.736685082277998e-06, "loss": 0.2833, "step": 323070 }, { "epoch": 1.9204546130023599, "grad_norm": 3.904118537902832, "learning_rate": 7.736511427208902e-06, "loss": 0.2914, "step": 323080 }, { "epoch": 1.9205140550790283, "grad_norm": 5.286327362060547, "learning_rate": 7.736337767427207e-06, "loss": 0.2785, "step": 323090 }, { "epoch": 1.9205734971556967, "grad_norm": 4.8399858474731445, "learning_rate": 7.73616410293321e-06, "loss": 0.2957, "step": 323100 }, { "epoch": 1.920632939232365, "grad_norm": 4.863643646240234, "learning_rate": 7.735990433727211e-06, "loss": 0.2813, "step": 323110 }, { "epoch": 1.9206923813090335, "grad_norm": 4.611822605133057, "learning_rate": 7.735816759809513e-06, "loss": 0.2999, "step": 323120 }, { "epoch": 1.920751823385702, "grad_norm": 5.913118362426758, "learning_rate": 7.735643081180412e-06, "loss": 0.3227, "step": 323130 }, { "epoch": 1.9208112654623704, "grad_norm": 5.026947021484375, "learning_rate": 7.735469397840207e-06, "loss": 0.2486, "step": 323140 }, { "epoch": 1.9208707075390385, "grad_norm": 5.230416297912598, "learning_rate": 7.735295709789197e-06, "loss": 0.2681, "step": 323150 }, { "epoch": 1.920930149615707, "grad_norm": 4.396877288818359, "learning_rate": 7.735122017027681e-06, "loss": 0.2313, "step": 323160 }, { "epoch": 1.9209895916923754, "grad_norm": 4.196229934692383, "learning_rate": 7.73494831955596e-06, "loss": 0.2903, "step": 323170 }, { "epoch": 1.9210490337690438, "grad_norm": 6.018375396728516, "learning_rate": 7.734774617374329e-06, "loss": 0.2632, "step": 323180 }, { "epoch": 1.921108475845712, "grad_norm": 3.7213563919067383, "learning_rate": 7.734600910483091e-06, "loss": 0.2838, "step": 323190 }, { "epoch": 1.9211679179223804, "grad_norm": 4.868865013122559, "learning_rate": 7.734427198882545e-06, "loss": 0.2607, "step": 323200 }, { "epoch": 1.9212273599990488, "grad_norm": 4.726775169372559, "learning_rate": 7.734253482572988e-06, "loss": 0.2814, "step": 323210 }, { "epoch": 1.9212868020757172, "grad_norm": 5.171883583068848, "learning_rate": 7.734079761554721e-06, "loss": 0.3383, "step": 323220 }, { "epoch": 1.9213462441523856, "grad_norm": 4.7957024574279785, "learning_rate": 7.73390603582804e-06, "loss": 0.2901, "step": 323230 }, { "epoch": 1.921405686229054, "grad_norm": 4.976718425750732, "learning_rate": 7.73373230539325e-06, "loss": 0.2918, "step": 323240 }, { "epoch": 1.9214651283057225, "grad_norm": 6.206859111785889, "learning_rate": 7.733558570250644e-06, "loss": 0.2923, "step": 323250 }, { "epoch": 1.9215245703823909, "grad_norm": 5.758506774902344, "learning_rate": 7.733384830400526e-06, "loss": 0.2733, "step": 323260 }, { "epoch": 1.9215840124590593, "grad_norm": 4.804173946380615, "learning_rate": 7.733211085843194e-06, "loss": 0.2709, "step": 323270 }, { "epoch": 1.9216434545357277, "grad_norm": 5.49875020980835, "learning_rate": 7.733037336578943e-06, "loss": 0.2874, "step": 323280 }, { "epoch": 1.9217028966123961, "grad_norm": 4.199647426605225, "learning_rate": 7.732863582608078e-06, "loss": 0.2875, "step": 323290 }, { "epoch": 1.9217623386890645, "grad_norm": 3.351391315460205, "learning_rate": 7.732689823930896e-06, "loss": 0.2893, "step": 323300 }, { "epoch": 1.921821780765733, "grad_norm": 4.87153434753418, "learning_rate": 7.732516060547695e-06, "loss": 0.2903, "step": 323310 }, { "epoch": 1.9218812228424014, "grad_norm": 4.828248977661133, "learning_rate": 7.732342292458776e-06, "loss": 0.2859, "step": 323320 }, { "epoch": 1.9219406649190696, "grad_norm": 8.25499439239502, "learning_rate": 7.732168519664436e-06, "loss": 0.3148, "step": 323330 }, { "epoch": 1.922000106995738, "grad_norm": 4.9457902908325195, "learning_rate": 7.731994742164976e-06, "loss": 0.2731, "step": 323340 }, { "epoch": 1.9220595490724064, "grad_norm": 5.699119567871094, "learning_rate": 7.731820959960697e-06, "loss": 0.3021, "step": 323350 }, { "epoch": 1.9221189911490748, "grad_norm": 4.710046768188477, "learning_rate": 7.731647173051895e-06, "loss": 0.2677, "step": 323360 }, { "epoch": 1.9221784332257432, "grad_norm": 3.8933732509613037, "learning_rate": 7.731473381438872e-06, "loss": 0.3319, "step": 323370 }, { "epoch": 1.9222378753024114, "grad_norm": 4.835116863250732, "learning_rate": 7.731299585121926e-06, "loss": 0.2763, "step": 323380 }, { "epoch": 1.9222973173790798, "grad_norm": 5.279272556304932, "learning_rate": 7.731125784101355e-06, "loss": 0.275, "step": 323390 }, { "epoch": 1.9223567594557482, "grad_norm": 4.317171096801758, "learning_rate": 7.73095197837746e-06, "loss": 0.302, "step": 323400 }, { "epoch": 1.9224162015324167, "grad_norm": 4.4929680824279785, "learning_rate": 7.730778167950539e-06, "loss": 0.3069, "step": 323410 }, { "epoch": 1.922475643609085, "grad_norm": 4.607122898101807, "learning_rate": 7.730604352820893e-06, "loss": 0.2894, "step": 323420 }, { "epoch": 1.9225350856857535, "grad_norm": 3.9090445041656494, "learning_rate": 7.73043053298882e-06, "loss": 0.2964, "step": 323430 }, { "epoch": 1.922594527762422, "grad_norm": 5.434455871582031, "learning_rate": 7.730256708454619e-06, "loss": 0.3097, "step": 323440 }, { "epoch": 1.9226539698390903, "grad_norm": 4.842618465423584, "learning_rate": 7.730082879218591e-06, "loss": 0.2708, "step": 323450 }, { "epoch": 1.9227134119157587, "grad_norm": 5.43021821975708, "learning_rate": 7.729909045281036e-06, "loss": 0.2664, "step": 323460 }, { "epoch": 1.9227728539924271, "grad_norm": 5.778348445892334, "learning_rate": 7.72973520664225e-06, "loss": 0.2819, "step": 323470 }, { "epoch": 1.9228322960690956, "grad_norm": 4.585629463195801, "learning_rate": 7.729561363302536e-06, "loss": 0.2768, "step": 323480 }, { "epoch": 1.922891738145764, "grad_norm": 4.083846092224121, "learning_rate": 7.72938751526219e-06, "loss": 0.2581, "step": 323490 }, { "epoch": 1.9229511802224324, "grad_norm": 6.430542469024658, "learning_rate": 7.729213662521513e-06, "loss": 0.2951, "step": 323500 }, { "epoch": 1.9230106222991008, "grad_norm": 4.043271064758301, "learning_rate": 7.729039805080806e-06, "loss": 0.2862, "step": 323510 }, { "epoch": 1.923070064375769, "grad_norm": 3.392307758331299, "learning_rate": 7.728865942940366e-06, "loss": 0.2893, "step": 323520 }, { "epoch": 1.9231295064524374, "grad_norm": 4.717119216918945, "learning_rate": 7.728692076100494e-06, "loss": 0.2692, "step": 323530 }, { "epoch": 1.9231889485291058, "grad_norm": 3.6221413612365723, "learning_rate": 7.728518204561487e-06, "loss": 0.3082, "step": 323540 }, { "epoch": 1.9232483906057742, "grad_norm": 5.14625358581543, "learning_rate": 7.728344328323647e-06, "loss": 0.2842, "step": 323550 }, { "epoch": 1.9233078326824424, "grad_norm": 5.047916412353516, "learning_rate": 7.728170447387273e-06, "loss": 0.3019, "step": 323560 }, { "epoch": 1.9233672747591108, "grad_norm": 4.839271545410156, "learning_rate": 7.727996561752663e-06, "loss": 0.2871, "step": 323570 }, { "epoch": 1.9234267168357793, "grad_norm": 4.633121490478516, "learning_rate": 7.727822671420118e-06, "loss": 0.2784, "step": 323580 }, { "epoch": 1.9234861589124477, "grad_norm": 4.865804195404053, "learning_rate": 7.727648776389935e-06, "loss": 0.2756, "step": 323590 }, { "epoch": 1.923545600989116, "grad_norm": 4.729046821594238, "learning_rate": 7.727474876662418e-06, "loss": 0.2906, "step": 323600 }, { "epoch": 1.9236050430657845, "grad_norm": 4.652431488037109, "learning_rate": 7.727300972237864e-06, "loss": 0.3047, "step": 323610 }, { "epoch": 1.923664485142453, "grad_norm": 4.131806373596191, "learning_rate": 7.72712706311657e-06, "loss": 0.2711, "step": 323620 }, { "epoch": 1.9237239272191213, "grad_norm": 5.936586380004883, "learning_rate": 7.72695314929884e-06, "loss": 0.2874, "step": 323630 }, { "epoch": 1.9237833692957897, "grad_norm": 4.709083557128906, "learning_rate": 7.72677923078497e-06, "loss": 0.2616, "step": 323640 }, { "epoch": 1.9238428113724582, "grad_norm": 5.477255821228027, "learning_rate": 7.726605307575261e-06, "loss": 0.2767, "step": 323650 }, { "epoch": 1.9239022534491266, "grad_norm": 4.712059497833252, "learning_rate": 7.726431379670012e-06, "loss": 0.279, "step": 323660 }, { "epoch": 1.923961695525795, "grad_norm": 5.780955791473389, "learning_rate": 7.726257447069522e-06, "loss": 0.2811, "step": 323670 }, { "epoch": 1.9240211376024634, "grad_norm": 6.308745384216309, "learning_rate": 7.726083509774093e-06, "loss": 0.3146, "step": 323680 }, { "epoch": 1.9240805796791318, "grad_norm": 4.783224105834961, "learning_rate": 7.725909567784023e-06, "loss": 0.3097, "step": 323690 }, { "epoch": 1.9241400217558, "grad_norm": 5.5733466148376465, "learning_rate": 7.725735621099611e-06, "loss": 0.2716, "step": 323700 }, { "epoch": 1.9241994638324684, "grad_norm": 5.9752984046936035, "learning_rate": 7.725561669721158e-06, "loss": 0.2841, "step": 323710 }, { "epoch": 1.9242589059091368, "grad_norm": 4.415013790130615, "learning_rate": 7.725387713648961e-06, "loss": 0.2637, "step": 323720 }, { "epoch": 1.9243183479858053, "grad_norm": 5.056416988372803, "learning_rate": 7.725213752883323e-06, "loss": 0.2851, "step": 323730 }, { "epoch": 1.9243777900624737, "grad_norm": 4.906469821929932, "learning_rate": 7.72503978742454e-06, "loss": 0.262, "step": 323740 }, { "epoch": 1.9244372321391419, "grad_norm": 5.1964592933654785, "learning_rate": 7.724865817272914e-06, "loss": 0.3122, "step": 323750 }, { "epoch": 1.9244966742158103, "grad_norm": 4.924957752227783, "learning_rate": 7.724691842428745e-06, "loss": 0.2732, "step": 323760 }, { "epoch": 1.9245561162924787, "grad_norm": 4.825492858886719, "learning_rate": 7.724517862892328e-06, "loss": 0.3002, "step": 323770 }, { "epoch": 1.924615558369147, "grad_norm": 4.230190753936768, "learning_rate": 7.724343878663969e-06, "loss": 0.2844, "step": 323780 }, { "epoch": 1.9246750004458155, "grad_norm": 5.366913318634033, "learning_rate": 7.724169889743965e-06, "loss": 0.304, "step": 323790 }, { "epoch": 1.924734442522484, "grad_norm": 5.093764781951904, "learning_rate": 7.723995896132615e-06, "loss": 0.2946, "step": 323800 }, { "epoch": 1.9247938845991523, "grad_norm": 3.7685625553131104, "learning_rate": 7.723821897830219e-06, "loss": 0.2558, "step": 323810 }, { "epoch": 1.9248533266758208, "grad_norm": 4.390841484069824, "learning_rate": 7.723647894837076e-06, "loss": 0.2568, "step": 323820 }, { "epoch": 1.9249127687524892, "grad_norm": 5.685421943664551, "learning_rate": 7.723473887153487e-06, "loss": 0.2937, "step": 323830 }, { "epoch": 1.9249722108291576, "grad_norm": 4.681762218475342, "learning_rate": 7.723299874779751e-06, "loss": 0.29, "step": 323840 }, { "epoch": 1.925031652905826, "grad_norm": 4.659204959869385, "learning_rate": 7.723125857716168e-06, "loss": 0.2778, "step": 323850 }, { "epoch": 1.9250910949824944, "grad_norm": 4.457130432128906, "learning_rate": 7.722951835963038e-06, "loss": 0.2536, "step": 323860 }, { "epoch": 1.9251505370591628, "grad_norm": 4.224851131439209, "learning_rate": 7.722777809520659e-06, "loss": 0.2791, "step": 323870 }, { "epoch": 1.9252099791358313, "grad_norm": 4.475069522857666, "learning_rate": 7.72260377838933e-06, "loss": 0.2956, "step": 323880 }, { "epoch": 1.9252694212124994, "grad_norm": 4.260161876678467, "learning_rate": 7.722429742569355e-06, "loss": 0.3028, "step": 323890 }, { "epoch": 1.9253288632891679, "grad_norm": 4.500741004943848, "learning_rate": 7.72225570206103e-06, "loss": 0.3011, "step": 323900 }, { "epoch": 1.9253883053658363, "grad_norm": 4.017389297485352, "learning_rate": 7.722081656864655e-06, "loss": 0.2744, "step": 323910 }, { "epoch": 1.9254477474425047, "grad_norm": 5.636417388916016, "learning_rate": 7.721907606980533e-06, "loss": 0.2641, "step": 323920 }, { "epoch": 1.9255071895191729, "grad_norm": 5.109306335449219, "learning_rate": 7.721733552408958e-06, "loss": 0.283, "step": 323930 }, { "epoch": 1.9255666315958413, "grad_norm": 4.594377517700195, "learning_rate": 7.721559493150238e-06, "loss": 0.2907, "step": 323940 }, { "epoch": 1.9256260736725097, "grad_norm": 4.72108793258667, "learning_rate": 7.721385429204663e-06, "loss": 0.2657, "step": 323950 }, { "epoch": 1.9256855157491781, "grad_norm": 6.041350841522217, "learning_rate": 7.72121136057254e-06, "loss": 0.29, "step": 323960 }, { "epoch": 1.9257449578258465, "grad_norm": 6.670652389526367, "learning_rate": 7.721037287254165e-06, "loss": 0.2945, "step": 323970 }, { "epoch": 1.925804399902515, "grad_norm": 4.130884170532227, "learning_rate": 7.720863209249842e-06, "loss": 0.2757, "step": 323980 }, { "epoch": 1.9258638419791834, "grad_norm": 3.8937973976135254, "learning_rate": 7.720689126559865e-06, "loss": 0.2702, "step": 323990 }, { "epoch": 1.9259232840558518, "grad_norm": 6.760933876037598, "learning_rate": 7.720515039184538e-06, "loss": 0.2784, "step": 324000 }, { "epoch": 1.9259827261325202, "grad_norm": 6.755414009094238, "learning_rate": 7.720340947124158e-06, "loss": 0.2902, "step": 324010 }, { "epoch": 1.9260421682091886, "grad_norm": 5.245748519897461, "learning_rate": 7.720166850379027e-06, "loss": 0.3017, "step": 324020 }, { "epoch": 1.926101610285857, "grad_norm": 5.096702575683594, "learning_rate": 7.719992748949444e-06, "loss": 0.262, "step": 324030 }, { "epoch": 1.9261610523625254, "grad_norm": 4.289389133453369, "learning_rate": 7.71981864283571e-06, "loss": 0.2988, "step": 324040 }, { "epoch": 1.9262204944391939, "grad_norm": 4.380831718444824, "learning_rate": 7.719644532038125e-06, "loss": 0.2774, "step": 324050 }, { "epoch": 1.9262799365158623, "grad_norm": 4.145292282104492, "learning_rate": 7.719470416556984e-06, "loss": 0.2373, "step": 324060 }, { "epoch": 1.9263393785925305, "grad_norm": 6.064626693725586, "learning_rate": 7.719296296392593e-06, "loss": 0.3146, "step": 324070 }, { "epoch": 1.9263988206691989, "grad_norm": 4.7600998878479, "learning_rate": 7.71912217154525e-06, "loss": 0.2769, "step": 324080 }, { "epoch": 1.9264582627458673, "grad_norm": 4.479150772094727, "learning_rate": 7.718948042015251e-06, "loss": 0.2537, "step": 324090 }, { "epoch": 1.9265177048225357, "grad_norm": 5.918411731719971, "learning_rate": 7.718773907802902e-06, "loss": 0.2782, "step": 324100 }, { "epoch": 1.9265771468992041, "grad_norm": 5.026429176330566, "learning_rate": 7.718599768908498e-06, "loss": 0.3014, "step": 324110 }, { "epoch": 1.9266365889758723, "grad_norm": 4.900449275970459, "learning_rate": 7.718425625332342e-06, "loss": 0.2684, "step": 324120 }, { "epoch": 1.9266960310525407, "grad_norm": 4.967950344085693, "learning_rate": 7.718251477074732e-06, "loss": 0.3232, "step": 324130 }, { "epoch": 1.9267554731292091, "grad_norm": 5.514081001281738, "learning_rate": 7.718077324135968e-06, "loss": 0.3242, "step": 324140 }, { "epoch": 1.9268149152058776, "grad_norm": 5.392307758331299, "learning_rate": 7.717903166516353e-06, "loss": 0.3101, "step": 324150 }, { "epoch": 1.926874357282546, "grad_norm": 4.800595760345459, "learning_rate": 7.717729004216183e-06, "loss": 0.2986, "step": 324160 }, { "epoch": 1.9269337993592144, "grad_norm": 5.090024471282959, "learning_rate": 7.717554837235759e-06, "loss": 0.3022, "step": 324170 }, { "epoch": 1.9269932414358828, "grad_norm": 3.7300167083740234, "learning_rate": 7.717380665575383e-06, "loss": 0.2715, "step": 324180 }, { "epoch": 1.9270526835125512, "grad_norm": 4.334651470184326, "learning_rate": 7.717206489235352e-06, "loss": 0.2824, "step": 324190 }, { "epoch": 1.9271121255892196, "grad_norm": 6.054681777954102, "learning_rate": 7.717032308215965e-06, "loss": 0.282, "step": 324200 }, { "epoch": 1.927171567665888, "grad_norm": 5.5424604415893555, "learning_rate": 7.716858122517526e-06, "loss": 0.3102, "step": 324210 }, { "epoch": 1.9272310097425565, "grad_norm": 4.529874801635742, "learning_rate": 7.716683932140335e-06, "loss": 0.3078, "step": 324220 }, { "epoch": 1.9272904518192249, "grad_norm": 5.654582500457764, "learning_rate": 7.716509737084687e-06, "loss": 0.2962, "step": 324230 }, { "epoch": 1.9273498938958933, "grad_norm": 4.743312835693359, "learning_rate": 7.716335537350888e-06, "loss": 0.2857, "step": 324240 }, { "epoch": 1.9274093359725617, "grad_norm": 4.765964508056641, "learning_rate": 7.716161332939233e-06, "loss": 0.3076, "step": 324250 }, { "epoch": 1.92746877804923, "grad_norm": 6.477710723876953, "learning_rate": 7.715987123850025e-06, "loss": 0.3249, "step": 324260 }, { "epoch": 1.9275282201258983, "grad_norm": 5.328325271606445, "learning_rate": 7.715812910083562e-06, "loss": 0.3121, "step": 324270 }, { "epoch": 1.9275876622025667, "grad_norm": 4.734867572784424, "learning_rate": 7.715638691640147e-06, "loss": 0.2752, "step": 324280 }, { "epoch": 1.9276471042792351, "grad_norm": 3.827465772628784, "learning_rate": 7.715464468520077e-06, "loss": 0.2793, "step": 324290 }, { "epoch": 1.9277065463559033, "grad_norm": 5.733577728271484, "learning_rate": 7.715290240723655e-06, "loss": 0.3195, "step": 324300 }, { "epoch": 1.9277659884325717, "grad_norm": 4.669129848480225, "learning_rate": 7.715116008251175e-06, "loss": 0.2737, "step": 324310 }, { "epoch": 1.9278254305092402, "grad_norm": 5.034495830535889, "learning_rate": 7.714941771102944e-06, "loss": 0.2584, "step": 324320 }, { "epoch": 1.9278848725859086, "grad_norm": 5.063443660736084, "learning_rate": 7.71476752927926e-06, "loss": 0.268, "step": 324330 }, { "epoch": 1.927944314662577, "grad_norm": 6.990377426147461, "learning_rate": 7.714593282780421e-06, "loss": 0.2973, "step": 324340 }, { "epoch": 1.9280037567392454, "grad_norm": 4.749171733856201, "learning_rate": 7.71441903160673e-06, "loss": 0.2866, "step": 324350 }, { "epoch": 1.9280631988159138, "grad_norm": 5.279387474060059, "learning_rate": 7.714244775758484e-06, "loss": 0.2923, "step": 324360 }, { "epoch": 1.9281226408925822, "grad_norm": 7.144991397857666, "learning_rate": 7.714070515235985e-06, "loss": 0.3194, "step": 324370 }, { "epoch": 1.9281820829692506, "grad_norm": 6.509509563446045, "learning_rate": 7.713896250039535e-06, "loss": 0.2736, "step": 324380 }, { "epoch": 1.928241525045919, "grad_norm": 5.304744243621826, "learning_rate": 7.713721980169428e-06, "loss": 0.2993, "step": 324390 }, { "epoch": 1.9283009671225875, "grad_norm": 5.727819442749023, "learning_rate": 7.71354770562597e-06, "loss": 0.2652, "step": 324400 }, { "epoch": 1.9283604091992559, "grad_norm": 4.520821571350098, "learning_rate": 7.71337342640946e-06, "loss": 0.2729, "step": 324410 }, { "epoch": 1.9284198512759243, "grad_norm": 5.225955486297607, "learning_rate": 7.713199142520197e-06, "loss": 0.2653, "step": 324420 }, { "epoch": 1.9284792933525927, "grad_norm": 4.088440418243408, "learning_rate": 7.713024853958478e-06, "loss": 0.2578, "step": 324430 }, { "epoch": 1.928538735429261, "grad_norm": 3.4055967330932617, "learning_rate": 7.71285056072461e-06, "loss": 0.2728, "step": 324440 }, { "epoch": 1.9285981775059293, "grad_norm": 4.629245758056641, "learning_rate": 7.712676262818888e-06, "loss": 0.2984, "step": 324450 }, { "epoch": 1.9286576195825977, "grad_norm": 4.768766403198242, "learning_rate": 7.712501960241613e-06, "loss": 0.2703, "step": 324460 }, { "epoch": 1.9287170616592662, "grad_norm": 4.468284606933594, "learning_rate": 7.712327652993089e-06, "loss": 0.2678, "step": 324470 }, { "epoch": 1.9287765037359346, "grad_norm": 4.712996959686279, "learning_rate": 7.712153341073612e-06, "loss": 0.2705, "step": 324480 }, { "epoch": 1.9288359458126028, "grad_norm": 6.2548041343688965, "learning_rate": 7.711979024483483e-06, "loss": 0.2876, "step": 324490 }, { "epoch": 1.9288953878892712, "grad_norm": 5.904378414154053, "learning_rate": 7.711804703223001e-06, "loss": 0.2487, "step": 324500 }, { "epoch": 1.9289548299659396, "grad_norm": 5.724136829376221, "learning_rate": 7.711630377292469e-06, "loss": 0.2755, "step": 324510 }, { "epoch": 1.929014272042608, "grad_norm": 5.063329696655273, "learning_rate": 7.711456046692187e-06, "loss": 0.2777, "step": 324520 }, { "epoch": 1.9290737141192764, "grad_norm": 4.387617588043213, "learning_rate": 7.711281711422454e-06, "loss": 0.2851, "step": 324530 }, { "epoch": 1.9291331561959448, "grad_norm": 5.09140157699585, "learning_rate": 7.711107371483569e-06, "loss": 0.2752, "step": 324540 }, { "epoch": 1.9291925982726132, "grad_norm": 5.189527988433838, "learning_rate": 7.710933026875833e-06, "loss": 0.3012, "step": 324550 }, { "epoch": 1.9292520403492817, "grad_norm": 4.513251781463623, "learning_rate": 7.710758677599548e-06, "loss": 0.297, "step": 324560 }, { "epoch": 1.92931148242595, "grad_norm": 3.946296453475952, "learning_rate": 7.710584323655014e-06, "loss": 0.2805, "step": 324570 }, { "epoch": 1.9293709245026185, "grad_norm": 3.7231428623199463, "learning_rate": 7.710409965042529e-06, "loss": 0.2791, "step": 324580 }, { "epoch": 1.929430366579287, "grad_norm": 4.668780326843262, "learning_rate": 7.710235601762394e-06, "loss": 0.2599, "step": 324590 }, { "epoch": 1.9294898086559553, "grad_norm": 5.9672112464904785, "learning_rate": 7.710061233814913e-06, "loss": 0.2683, "step": 324600 }, { "epoch": 1.9295492507326237, "grad_norm": 5.700332164764404, "learning_rate": 7.70988686120038e-06, "loss": 0.3048, "step": 324610 }, { "epoch": 1.9296086928092921, "grad_norm": 4.659118175506592, "learning_rate": 7.7097124839191e-06, "loss": 0.3114, "step": 324620 }, { "epoch": 1.9296681348859603, "grad_norm": 3.637596845626831, "learning_rate": 7.709538101971373e-06, "loss": 0.2671, "step": 324630 }, { "epoch": 1.9297275769626288, "grad_norm": 3.529392719268799, "learning_rate": 7.709363715357496e-06, "loss": 0.2881, "step": 324640 }, { "epoch": 1.9297870190392972, "grad_norm": 3.953744888305664, "learning_rate": 7.70918932407777e-06, "loss": 0.2849, "step": 324650 }, { "epoch": 1.9298464611159656, "grad_norm": 4.384675025939941, "learning_rate": 7.709014928132502e-06, "loss": 0.2592, "step": 324660 }, { "epoch": 1.9299059031926338, "grad_norm": 4.4053239822387695, "learning_rate": 7.708840527521983e-06, "loss": 0.2724, "step": 324670 }, { "epoch": 1.9299653452693022, "grad_norm": 5.311307907104492, "learning_rate": 7.708666122246517e-06, "loss": 0.2517, "step": 324680 }, { "epoch": 1.9300247873459706, "grad_norm": 5.4703569412231445, "learning_rate": 7.708491712306407e-06, "loss": 0.2644, "step": 324690 }, { "epoch": 1.930084229422639, "grad_norm": 5.401347637176514, "learning_rate": 7.70831729770195e-06, "loss": 0.2767, "step": 324700 }, { "epoch": 1.9301436714993074, "grad_norm": 3.8735692501068115, "learning_rate": 7.708142878433448e-06, "loss": 0.2993, "step": 324710 }, { "epoch": 1.9302031135759758, "grad_norm": 5.3389811515808105, "learning_rate": 7.7079684545012e-06, "loss": 0.2894, "step": 324720 }, { "epoch": 1.9302625556526443, "grad_norm": 5.1945037841796875, "learning_rate": 7.707794025905508e-06, "loss": 0.2764, "step": 324730 }, { "epoch": 1.9303219977293127, "grad_norm": 5.836806297302246, "learning_rate": 7.707619592646672e-06, "loss": 0.2742, "step": 324740 }, { "epoch": 1.930381439805981, "grad_norm": 5.498392105102539, "learning_rate": 7.707445154724991e-06, "loss": 0.2841, "step": 324750 }, { "epoch": 1.9304408818826495, "grad_norm": 4.6901326179504395, "learning_rate": 7.707270712140765e-06, "loss": 0.2781, "step": 324760 }, { "epoch": 1.930500323959318, "grad_norm": 5.744002819061279, "learning_rate": 7.707096264894298e-06, "loss": 0.2591, "step": 324770 }, { "epoch": 1.9305597660359863, "grad_norm": 4.355958938598633, "learning_rate": 7.706921812985889e-06, "loss": 0.2713, "step": 324780 }, { "epoch": 1.9306192081126547, "grad_norm": 5.353436470031738, "learning_rate": 7.706747356415835e-06, "loss": 0.2802, "step": 324790 }, { "epoch": 1.9306786501893232, "grad_norm": 4.875213146209717, "learning_rate": 7.70657289518444e-06, "loss": 0.2631, "step": 324800 }, { "epoch": 1.9307380922659914, "grad_norm": 6.589694023132324, "learning_rate": 7.706398429292004e-06, "loss": 0.2821, "step": 324810 }, { "epoch": 1.9307975343426598, "grad_norm": 6.131455898284912, "learning_rate": 7.706223958738828e-06, "loss": 0.2601, "step": 324820 }, { "epoch": 1.9308569764193282, "grad_norm": 4.4795074462890625, "learning_rate": 7.70604948352521e-06, "loss": 0.3045, "step": 324830 }, { "epoch": 1.9309164184959966, "grad_norm": 7.0806450843811035, "learning_rate": 7.705875003651452e-06, "loss": 0.3094, "step": 324840 }, { "epoch": 1.930975860572665, "grad_norm": 4.878492832183838, "learning_rate": 7.705700519117853e-06, "loss": 0.2523, "step": 324850 }, { "epoch": 1.9310353026493332, "grad_norm": 6.021373748779297, "learning_rate": 7.705526029924717e-06, "loss": 0.3088, "step": 324860 }, { "epoch": 1.9310947447260016, "grad_norm": 4.342461585998535, "learning_rate": 7.705351536072341e-06, "loss": 0.3094, "step": 324870 }, { "epoch": 1.93115418680267, "grad_norm": 3.8947947025299072, "learning_rate": 7.70517703756103e-06, "loss": 0.2802, "step": 324880 }, { "epoch": 1.9312136288793385, "grad_norm": 4.236543655395508, "learning_rate": 7.705002534391078e-06, "loss": 0.2636, "step": 324890 }, { "epoch": 1.9312730709560069, "grad_norm": 3.917726516723633, "learning_rate": 7.70482802656279e-06, "loss": 0.2705, "step": 324900 }, { "epoch": 1.9313325130326753, "grad_norm": 4.514641284942627, "learning_rate": 7.704653514076465e-06, "loss": 0.2431, "step": 324910 }, { "epoch": 1.9313919551093437, "grad_norm": 5.55778169631958, "learning_rate": 7.704478996932406e-06, "loss": 0.2947, "step": 324920 }, { "epoch": 1.931451397186012, "grad_norm": 4.644265174865723, "learning_rate": 7.704304475130908e-06, "loss": 0.2925, "step": 324930 }, { "epoch": 1.9315108392626805, "grad_norm": 4.897533893585205, "learning_rate": 7.704129948672277e-06, "loss": 0.2888, "step": 324940 }, { "epoch": 1.931570281339349, "grad_norm": 4.3836588859558105, "learning_rate": 7.703955417556812e-06, "loss": 0.2903, "step": 324950 }, { "epoch": 1.9316297234160174, "grad_norm": 6.059654235839844, "learning_rate": 7.703780881784813e-06, "loss": 0.2961, "step": 324960 }, { "epoch": 1.9316891654926858, "grad_norm": 3.955183506011963, "learning_rate": 7.70360634135658e-06, "loss": 0.2923, "step": 324970 }, { "epoch": 1.9317486075693542, "grad_norm": 5.006298542022705, "learning_rate": 7.703431796272414e-06, "loss": 0.2375, "step": 324980 }, { "epoch": 1.9318080496460226, "grad_norm": 4.721007347106934, "learning_rate": 7.703257246532616e-06, "loss": 0.2685, "step": 324990 }, { "epoch": 1.9318674917226908, "grad_norm": 5.092283725738525, "learning_rate": 7.703082692137487e-06, "loss": 0.2759, "step": 325000 }, { "epoch": 1.9319269337993592, "grad_norm": 4.439890384674072, "learning_rate": 7.702908133087328e-06, "loss": 0.2628, "step": 325010 }, { "epoch": 1.9319863758760276, "grad_norm": 4.820207118988037, "learning_rate": 7.702733569382437e-06, "loss": 0.3019, "step": 325020 }, { "epoch": 1.932045817952696, "grad_norm": 5.2048540115356445, "learning_rate": 7.702559001023117e-06, "loss": 0.2727, "step": 325030 }, { "epoch": 1.9321052600293642, "grad_norm": 5.5320611000061035, "learning_rate": 7.702384428009669e-06, "loss": 0.2757, "step": 325040 }, { "epoch": 1.9321647021060326, "grad_norm": 5.220674991607666, "learning_rate": 7.70220985034239e-06, "loss": 0.2853, "step": 325050 }, { "epoch": 1.932224144182701, "grad_norm": 4.245202541351318, "learning_rate": 7.702035268021583e-06, "loss": 0.3008, "step": 325060 }, { "epoch": 1.9322835862593695, "grad_norm": 4.266139507293701, "learning_rate": 7.701860681047553e-06, "loss": 0.2681, "step": 325070 }, { "epoch": 1.9323430283360379, "grad_norm": 5.107792854309082, "learning_rate": 7.701686089420594e-06, "loss": 0.2647, "step": 325080 }, { "epoch": 1.9324024704127063, "grad_norm": 3.3694047927856445, "learning_rate": 7.701511493141007e-06, "loss": 0.2867, "step": 325090 }, { "epoch": 1.9324619124893747, "grad_norm": 4.4472761154174805, "learning_rate": 7.7013368922091e-06, "loss": 0.2555, "step": 325100 }, { "epoch": 1.9325213545660431, "grad_norm": 5.283375263214111, "learning_rate": 7.701162286625163e-06, "loss": 0.282, "step": 325110 }, { "epoch": 1.9325807966427115, "grad_norm": 5.109054088592529, "learning_rate": 7.700987676389506e-06, "loss": 0.2731, "step": 325120 }, { "epoch": 1.93264023871938, "grad_norm": 4.348130226135254, "learning_rate": 7.700813061502425e-06, "loss": 0.266, "step": 325130 }, { "epoch": 1.9326996807960484, "grad_norm": 4.380304336547852, "learning_rate": 7.70063844196422e-06, "loss": 0.2884, "step": 325140 }, { "epoch": 1.9327591228727168, "grad_norm": 4.994290351867676, "learning_rate": 7.700463817775197e-06, "loss": 0.2873, "step": 325150 }, { "epoch": 1.9328185649493852, "grad_norm": 5.233159065246582, "learning_rate": 7.70028918893565e-06, "loss": 0.2736, "step": 325160 }, { "epoch": 1.9328780070260536, "grad_norm": 4.782151699066162, "learning_rate": 7.700114555445883e-06, "loss": 0.2873, "step": 325170 }, { "epoch": 1.9329374491027218, "grad_norm": 4.364293575286865, "learning_rate": 7.699939917306198e-06, "loss": 0.2787, "step": 325180 }, { "epoch": 1.9329968911793902, "grad_norm": 6.083322525024414, "learning_rate": 7.699765274516895e-06, "loss": 0.2938, "step": 325190 }, { "epoch": 1.9330563332560586, "grad_norm": 5.137935638427734, "learning_rate": 7.69959062707827e-06, "loss": 0.3075, "step": 325200 }, { "epoch": 1.933115775332727, "grad_norm": 4.823947906494141, "learning_rate": 7.699415974990632e-06, "loss": 0.2699, "step": 325210 }, { "epoch": 1.9331752174093955, "grad_norm": 4.409817218780518, "learning_rate": 7.699241318254276e-06, "loss": 0.2806, "step": 325220 }, { "epoch": 1.9332346594860637, "grad_norm": 5.167006015777588, "learning_rate": 7.699066656869505e-06, "loss": 0.2756, "step": 325230 }, { "epoch": 1.933294101562732, "grad_norm": 5.530739784240723, "learning_rate": 7.69889199083662e-06, "loss": 0.272, "step": 325240 }, { "epoch": 1.9333535436394005, "grad_norm": 4.623501300811768, "learning_rate": 7.698717320155919e-06, "loss": 0.2799, "step": 325250 }, { "epoch": 1.933412985716069, "grad_norm": 6.341459274291992, "learning_rate": 7.698542644827705e-06, "loss": 0.271, "step": 325260 }, { "epoch": 1.9334724277927373, "grad_norm": 5.688016414642334, "learning_rate": 7.698367964852278e-06, "loss": 0.2833, "step": 325270 }, { "epoch": 1.9335318698694057, "grad_norm": 5.798773765563965, "learning_rate": 7.698193280229942e-06, "loss": 0.2651, "step": 325280 }, { "epoch": 1.9335913119460741, "grad_norm": 4.750364780426025, "learning_rate": 7.698018590960993e-06, "loss": 0.3139, "step": 325290 }, { "epoch": 1.9336507540227426, "grad_norm": 5.471141338348389, "learning_rate": 7.697843897045735e-06, "loss": 0.3372, "step": 325300 }, { "epoch": 1.933710196099411, "grad_norm": 6.25059175491333, "learning_rate": 7.697669198484466e-06, "loss": 0.2758, "step": 325310 }, { "epoch": 1.9337696381760794, "grad_norm": 4.882702827453613, "learning_rate": 7.697494495277492e-06, "loss": 0.2758, "step": 325320 }, { "epoch": 1.9338290802527478, "grad_norm": 5.980690956115723, "learning_rate": 7.697319787425108e-06, "loss": 0.279, "step": 325330 }, { "epoch": 1.9338885223294162, "grad_norm": 5.450231075286865, "learning_rate": 7.697145074927619e-06, "loss": 0.2761, "step": 325340 }, { "epoch": 1.9339479644060846, "grad_norm": 4.270340919494629, "learning_rate": 7.696970357785323e-06, "loss": 0.3024, "step": 325350 }, { "epoch": 1.934007406482753, "grad_norm": 5.145007610321045, "learning_rate": 7.696795635998524e-06, "loss": 0.2895, "step": 325360 }, { "epoch": 1.9340668485594212, "grad_norm": 4.256533145904541, "learning_rate": 7.696620909567521e-06, "loss": 0.2929, "step": 325370 }, { "epoch": 1.9341262906360897, "grad_norm": 4.7414984703063965, "learning_rate": 7.696446178492614e-06, "loss": 0.3013, "step": 325380 }, { "epoch": 1.934185732712758, "grad_norm": 4.153506278991699, "learning_rate": 7.696271442774103e-06, "loss": 0.2679, "step": 325390 }, { "epoch": 1.9342451747894265, "grad_norm": 3.2879889011383057, "learning_rate": 7.696096702412295e-06, "loss": 0.2527, "step": 325400 }, { "epoch": 1.9343046168660947, "grad_norm": 4.253836631774902, "learning_rate": 7.695921957407486e-06, "loss": 0.2765, "step": 325410 }, { "epoch": 1.934364058942763, "grad_norm": 4.690153121948242, "learning_rate": 7.695747207759975e-06, "loss": 0.27, "step": 325420 }, { "epoch": 1.9344235010194315, "grad_norm": 5.7758259773254395, "learning_rate": 7.695572453470067e-06, "loss": 0.2704, "step": 325430 }, { "epoch": 1.9344829430961, "grad_norm": 7.648115158081055, "learning_rate": 7.695397694538063e-06, "loss": 0.3279, "step": 325440 }, { "epoch": 1.9345423851727683, "grad_norm": 5.897582054138184, "learning_rate": 7.695222930964262e-06, "loss": 0.2993, "step": 325450 }, { "epoch": 1.9346018272494367, "grad_norm": 5.884645938873291, "learning_rate": 7.695048162748964e-06, "loss": 0.2765, "step": 325460 }, { "epoch": 1.9346612693261052, "grad_norm": 5.423422336578369, "learning_rate": 7.694873389892472e-06, "loss": 0.3056, "step": 325470 }, { "epoch": 1.9347207114027736, "grad_norm": 5.862681865692139, "learning_rate": 7.694698612395087e-06, "loss": 0.2773, "step": 325480 }, { "epoch": 1.934780153479442, "grad_norm": 5.416244029998779, "learning_rate": 7.69452383025711e-06, "loss": 0.2703, "step": 325490 }, { "epoch": 1.9348395955561104, "grad_norm": 4.859950542449951, "learning_rate": 7.69434904347884e-06, "loss": 0.2584, "step": 325500 }, { "epoch": 1.9348990376327788, "grad_norm": 4.57570743560791, "learning_rate": 7.694174252060582e-06, "loss": 0.2544, "step": 325510 }, { "epoch": 1.9349584797094472, "grad_norm": 5.686230182647705, "learning_rate": 7.693999456002632e-06, "loss": 0.2721, "step": 325520 }, { "epoch": 1.9350179217861156, "grad_norm": 4.266943454742432, "learning_rate": 7.693824655305293e-06, "loss": 0.2593, "step": 325530 }, { "epoch": 1.935077363862784, "grad_norm": 5.661340713500977, "learning_rate": 7.693649849968868e-06, "loss": 0.3154, "step": 325540 }, { "epoch": 1.9351368059394523, "grad_norm": 4.303605079650879, "learning_rate": 7.693475039993657e-06, "loss": 0.2822, "step": 325550 }, { "epoch": 1.9351962480161207, "grad_norm": 5.040565013885498, "learning_rate": 7.693300225379958e-06, "loss": 0.2847, "step": 325560 }, { "epoch": 1.935255690092789, "grad_norm": 5.092231750488281, "learning_rate": 7.693125406128077e-06, "loss": 0.2986, "step": 325570 }, { "epoch": 1.9353151321694575, "grad_norm": 5.189128875732422, "learning_rate": 7.692950582238314e-06, "loss": 0.2413, "step": 325580 }, { "epoch": 1.935374574246126, "grad_norm": 4.162286281585693, "learning_rate": 7.692775753710965e-06, "loss": 0.2609, "step": 325590 }, { "epoch": 1.935434016322794, "grad_norm": 3.7290375232696533, "learning_rate": 7.692600920546339e-06, "loss": 0.2503, "step": 325600 }, { "epoch": 1.9354934583994625, "grad_norm": 5.325194835662842, "learning_rate": 7.69242608274473e-06, "loss": 0.2807, "step": 325610 }, { "epoch": 1.935552900476131, "grad_norm": 4.176643371582031, "learning_rate": 7.692251240306442e-06, "loss": 0.2841, "step": 325620 }, { "epoch": 1.9356123425527993, "grad_norm": 5.079863548278809, "learning_rate": 7.69207639323178e-06, "loss": 0.2943, "step": 325630 }, { "epoch": 1.9356717846294678, "grad_norm": 5.533195495605469, "learning_rate": 7.691901541521036e-06, "loss": 0.2568, "step": 325640 }, { "epoch": 1.9357312267061362, "grad_norm": 5.766654968261719, "learning_rate": 7.691726685174518e-06, "loss": 0.3092, "step": 325650 }, { "epoch": 1.9357906687828046, "grad_norm": 5.088891506195068, "learning_rate": 7.691551824192526e-06, "loss": 0.3015, "step": 325660 }, { "epoch": 1.935850110859473, "grad_norm": 5.292996406555176, "learning_rate": 7.691376958575362e-06, "loss": 0.2801, "step": 325670 }, { "epoch": 1.9359095529361414, "grad_norm": 4.512673854827881, "learning_rate": 7.691202088323324e-06, "loss": 0.2556, "step": 325680 }, { "epoch": 1.9359689950128098, "grad_norm": 5.278006553649902, "learning_rate": 7.691027213436714e-06, "loss": 0.2754, "step": 325690 }, { "epoch": 1.9360284370894782, "grad_norm": 4.884711265563965, "learning_rate": 7.690852333915838e-06, "loss": 0.2878, "step": 325700 }, { "epoch": 1.9360878791661467, "grad_norm": 4.3625168800354, "learning_rate": 7.690677449760991e-06, "loss": 0.29, "step": 325710 }, { "epoch": 1.936147321242815, "grad_norm": 4.259917259216309, "learning_rate": 7.690502560972475e-06, "loss": 0.2931, "step": 325720 }, { "epoch": 1.9362067633194835, "grad_norm": 4.271989822387695, "learning_rate": 7.690327667550595e-06, "loss": 0.2533, "step": 325730 }, { "epoch": 1.9362662053961517, "grad_norm": 5.067770004272461, "learning_rate": 7.690152769495646e-06, "loss": 0.3224, "step": 325740 }, { "epoch": 1.93632564747282, "grad_norm": 5.274653911590576, "learning_rate": 7.689977866807936e-06, "loss": 0.2652, "step": 325750 }, { "epoch": 1.9363850895494885, "grad_norm": 5.570021629333496, "learning_rate": 7.689802959487763e-06, "loss": 0.3031, "step": 325760 }, { "epoch": 1.936444531626157, "grad_norm": 4.36918306350708, "learning_rate": 7.689628047535426e-06, "loss": 0.2854, "step": 325770 }, { "epoch": 1.9365039737028251, "grad_norm": 4.961428642272949, "learning_rate": 7.689453130951232e-06, "loss": 0.2678, "step": 325780 }, { "epoch": 1.9365634157794935, "grad_norm": 5.448625564575195, "learning_rate": 7.689278209735476e-06, "loss": 0.2725, "step": 325790 }, { "epoch": 1.936622857856162, "grad_norm": 4.844777584075928, "learning_rate": 7.689103283888465e-06, "loss": 0.2931, "step": 325800 }, { "epoch": 1.9366822999328304, "grad_norm": 4.975452899932861, "learning_rate": 7.688928353410494e-06, "loss": 0.2903, "step": 325810 }, { "epoch": 1.9367417420094988, "grad_norm": 6.807047367095947, "learning_rate": 7.68875341830187e-06, "loss": 0.3183, "step": 325820 }, { "epoch": 1.9368011840861672, "grad_norm": 5.783092021942139, "learning_rate": 7.688578478562891e-06, "loss": 0.2673, "step": 325830 }, { "epoch": 1.9368606261628356, "grad_norm": 4.71551513671875, "learning_rate": 7.688403534193858e-06, "loss": 0.2713, "step": 325840 }, { "epoch": 1.936920068239504, "grad_norm": 4.6947102546691895, "learning_rate": 7.688228585195075e-06, "loss": 0.2759, "step": 325850 }, { "epoch": 1.9369795103161724, "grad_norm": 5.084043979644775, "learning_rate": 7.68805363156684e-06, "loss": 0.2592, "step": 325860 }, { "epoch": 1.9370389523928409, "grad_norm": 5.195581436157227, "learning_rate": 7.687878673309457e-06, "loss": 0.2968, "step": 325870 }, { "epoch": 1.9370983944695093, "grad_norm": 4.872910499572754, "learning_rate": 7.687703710423225e-06, "loss": 0.2778, "step": 325880 }, { "epoch": 1.9371578365461777, "grad_norm": 3.8830935955047607, "learning_rate": 7.687528742908448e-06, "loss": 0.2515, "step": 325890 }, { "epoch": 1.937217278622846, "grad_norm": 5.1681294441223145, "learning_rate": 7.687353770765426e-06, "loss": 0.2928, "step": 325900 }, { "epoch": 1.9372767206995145, "grad_norm": 4.566004753112793, "learning_rate": 7.68717879399446e-06, "loss": 0.2612, "step": 325910 }, { "epoch": 1.9373361627761827, "grad_norm": 4.989377975463867, "learning_rate": 7.68700381259585e-06, "loss": 0.3161, "step": 325920 }, { "epoch": 1.9373956048528511, "grad_norm": 4.073209762573242, "learning_rate": 7.6868288265699e-06, "loss": 0.3035, "step": 325930 }, { "epoch": 1.9374550469295195, "grad_norm": 5.892985820770264, "learning_rate": 7.68665383591691e-06, "loss": 0.2976, "step": 325940 }, { "epoch": 1.937514489006188, "grad_norm": 4.981037616729736, "learning_rate": 7.686478840637181e-06, "loss": 0.2849, "step": 325950 }, { "epoch": 1.9375739310828564, "grad_norm": 3.3308749198913574, "learning_rate": 7.686303840731016e-06, "loss": 0.2683, "step": 325960 }, { "epoch": 1.9376333731595246, "grad_norm": 4.618813514709473, "learning_rate": 7.686128836198714e-06, "loss": 0.2735, "step": 325970 }, { "epoch": 1.937692815236193, "grad_norm": 6.593848705291748, "learning_rate": 7.685953827040578e-06, "loss": 0.2965, "step": 325980 }, { "epoch": 1.9377522573128614, "grad_norm": 5.0759077072143555, "learning_rate": 7.68577881325691e-06, "loss": 0.2816, "step": 325990 }, { "epoch": 1.9378116993895298, "grad_norm": 5.4842634201049805, "learning_rate": 7.68560379484801e-06, "loss": 0.2542, "step": 326000 }, { "epoch": 1.9378711414661982, "grad_norm": 4.508739471435547, "learning_rate": 7.685428771814178e-06, "loss": 0.284, "step": 326010 }, { "epoch": 1.9379305835428666, "grad_norm": 5.256642818450928, "learning_rate": 7.685253744155721e-06, "loss": 0.2891, "step": 326020 }, { "epoch": 1.937990025619535, "grad_norm": 5.873542308807373, "learning_rate": 7.685078711872933e-06, "loss": 0.3135, "step": 326030 }, { "epoch": 1.9380494676962035, "grad_norm": 6.323501110076904, "learning_rate": 7.68490367496612e-06, "loss": 0.3006, "step": 326040 }, { "epoch": 1.9381089097728719, "grad_norm": 4.904122829437256, "learning_rate": 7.684728633435584e-06, "loss": 0.2989, "step": 326050 }, { "epoch": 1.9381683518495403, "grad_norm": 5.770355701446533, "learning_rate": 7.684553587281624e-06, "loss": 0.3068, "step": 326060 }, { "epoch": 1.9382277939262087, "grad_norm": 4.300681114196777, "learning_rate": 7.684378536504542e-06, "loss": 0.3127, "step": 326070 }, { "epoch": 1.9382872360028771, "grad_norm": 4.683475971221924, "learning_rate": 7.684203481104641e-06, "loss": 0.2586, "step": 326080 }, { "epoch": 1.9383466780795455, "grad_norm": 4.182537078857422, "learning_rate": 7.68402842108222e-06, "loss": 0.2644, "step": 326090 }, { "epoch": 1.938406120156214, "grad_norm": 4.408952236175537, "learning_rate": 7.683853356437582e-06, "loss": 0.2607, "step": 326100 }, { "epoch": 1.9384655622328821, "grad_norm": 6.0409626960754395, "learning_rate": 7.683678287171029e-06, "loss": 0.3137, "step": 326110 }, { "epoch": 1.9385250043095505, "grad_norm": 5.375979423522949, "learning_rate": 7.683503213282862e-06, "loss": 0.2807, "step": 326120 }, { "epoch": 1.938584446386219, "grad_norm": 6.393074035644531, "learning_rate": 7.683328134773382e-06, "loss": 0.2452, "step": 326130 }, { "epoch": 1.9386438884628874, "grad_norm": 5.097317695617676, "learning_rate": 7.683153051642892e-06, "loss": 0.2778, "step": 326140 }, { "epoch": 1.9387033305395556, "grad_norm": 3.774630546569824, "learning_rate": 7.682977963891689e-06, "loss": 0.277, "step": 326150 }, { "epoch": 1.938762772616224, "grad_norm": 5.973597049713135, "learning_rate": 7.682802871520081e-06, "loss": 0.3108, "step": 326160 }, { "epoch": 1.9388222146928924, "grad_norm": 4.823160171508789, "learning_rate": 7.682627774528364e-06, "loss": 0.2928, "step": 326170 }, { "epoch": 1.9388816567695608, "grad_norm": 5.581943988800049, "learning_rate": 7.682452672916843e-06, "loss": 0.3179, "step": 326180 }, { "epoch": 1.9389410988462292, "grad_norm": 5.213393211364746, "learning_rate": 7.682277566685819e-06, "loss": 0.2664, "step": 326190 }, { "epoch": 1.9390005409228976, "grad_norm": 5.36006498336792, "learning_rate": 7.682102455835591e-06, "loss": 0.2864, "step": 326200 }, { "epoch": 1.939059982999566, "grad_norm": 4.792906284332275, "learning_rate": 7.681927340366463e-06, "loss": 0.2518, "step": 326210 }, { "epoch": 1.9391194250762345, "grad_norm": 4.454243183135986, "learning_rate": 7.681752220278738e-06, "loss": 0.2774, "step": 326220 }, { "epoch": 1.9391788671529029, "grad_norm": 3.328627347946167, "learning_rate": 7.681577095572716e-06, "loss": 0.2686, "step": 326230 }, { "epoch": 1.9392383092295713, "grad_norm": 4.512869358062744, "learning_rate": 7.681401966248696e-06, "loss": 0.315, "step": 326240 }, { "epoch": 1.9392977513062397, "grad_norm": 4.423576831817627, "learning_rate": 7.681226832306983e-06, "loss": 0.2511, "step": 326250 }, { "epoch": 1.9393571933829081, "grad_norm": 5.619345188140869, "learning_rate": 7.68105169374788e-06, "loss": 0.27, "step": 326260 }, { "epoch": 1.9394166354595765, "grad_norm": 6.232115745544434, "learning_rate": 7.68087655057168e-06, "loss": 0.2795, "step": 326270 }, { "epoch": 1.939476077536245, "grad_norm": 3.417604923248291, "learning_rate": 7.680701402778695e-06, "loss": 0.2827, "step": 326280 }, { "epoch": 1.9395355196129132, "grad_norm": 4.750874042510986, "learning_rate": 7.680526250369222e-06, "loss": 0.2551, "step": 326290 }, { "epoch": 1.9395949616895816, "grad_norm": 5.744693279266357, "learning_rate": 7.68035109334356e-06, "loss": 0.2775, "step": 326300 }, { "epoch": 1.93965440376625, "grad_norm": 4.728458404541016, "learning_rate": 7.680175931702016e-06, "loss": 0.2797, "step": 326310 }, { "epoch": 1.9397138458429184, "grad_norm": 4.479628562927246, "learning_rate": 7.68000076544489e-06, "loss": 0.2917, "step": 326320 }, { "epoch": 1.9397732879195868, "grad_norm": 5.096429824829102, "learning_rate": 7.679825594572482e-06, "loss": 0.2709, "step": 326330 }, { "epoch": 1.939832729996255, "grad_norm": 5.010167598724365, "learning_rate": 7.679650419085096e-06, "loss": 0.3034, "step": 326340 }, { "epoch": 1.9398921720729234, "grad_norm": 5.832434177398682, "learning_rate": 7.679475238983031e-06, "loss": 0.2955, "step": 326350 }, { "epoch": 1.9399516141495918, "grad_norm": 4.931975364685059, "learning_rate": 7.67930005426659e-06, "loss": 0.2742, "step": 326360 }, { "epoch": 1.9400110562262602, "grad_norm": 3.910170078277588, "learning_rate": 7.679124864936074e-06, "loss": 0.2934, "step": 326370 }, { "epoch": 1.9400704983029287, "grad_norm": 4.683242321014404, "learning_rate": 7.678949670991787e-06, "loss": 0.2864, "step": 326380 }, { "epoch": 1.940129940379597, "grad_norm": 3.844210147857666, "learning_rate": 7.678774472434028e-06, "loss": 0.2938, "step": 326390 }, { "epoch": 1.9401893824562655, "grad_norm": 4.138564109802246, "learning_rate": 7.678599269263099e-06, "loss": 0.298, "step": 326400 }, { "epoch": 1.940248824532934, "grad_norm": 5.415981769561768, "learning_rate": 7.678424061479301e-06, "loss": 0.2681, "step": 326410 }, { "epoch": 1.9403082666096023, "grad_norm": 4.128005504608154, "learning_rate": 7.678248849082942e-06, "loss": 0.308, "step": 326420 }, { "epoch": 1.9403677086862707, "grad_norm": 5.541248798370361, "learning_rate": 7.678073632074315e-06, "loss": 0.2622, "step": 326430 }, { "epoch": 1.9404271507629391, "grad_norm": 4.725384712219238, "learning_rate": 7.677898410453726e-06, "loss": 0.2716, "step": 326440 }, { "epoch": 1.9404865928396076, "grad_norm": 4.792470455169678, "learning_rate": 7.677723184221478e-06, "loss": 0.3021, "step": 326450 }, { "epoch": 1.940546034916276, "grad_norm": 4.791079998016357, "learning_rate": 7.67754795337787e-06, "loss": 0.3003, "step": 326460 }, { "epoch": 1.9406054769929444, "grad_norm": 4.3261308670043945, "learning_rate": 7.677372717923205e-06, "loss": 0.2567, "step": 326470 }, { "epoch": 1.9406649190696126, "grad_norm": 4.767670631408691, "learning_rate": 7.677197477857784e-06, "loss": 0.2736, "step": 326480 }, { "epoch": 1.940724361146281, "grad_norm": 4.95453405380249, "learning_rate": 7.677022233181912e-06, "loss": 0.2474, "step": 326490 }, { "epoch": 1.9407838032229494, "grad_norm": 4.428674697875977, "learning_rate": 7.676846983895887e-06, "loss": 0.263, "step": 326500 }, { "epoch": 1.9408432452996178, "grad_norm": 4.461754322052002, "learning_rate": 7.676671730000012e-06, "loss": 0.2697, "step": 326510 }, { "epoch": 1.940902687376286, "grad_norm": 4.8791728019714355, "learning_rate": 7.676496471494589e-06, "loss": 0.3091, "step": 326520 }, { "epoch": 1.9409621294529544, "grad_norm": 5.701984405517578, "learning_rate": 7.67632120837992e-06, "loss": 0.2654, "step": 326530 }, { "epoch": 1.9410215715296228, "grad_norm": 5.378993988037109, "learning_rate": 7.676145940656306e-06, "loss": 0.2876, "step": 326540 }, { "epoch": 1.9410810136062913, "grad_norm": 5.562594413757324, "learning_rate": 7.67597066832405e-06, "loss": 0.3091, "step": 326550 }, { "epoch": 1.9411404556829597, "grad_norm": 5.549548625946045, "learning_rate": 7.675795391383452e-06, "loss": 0.2981, "step": 326560 }, { "epoch": 1.941199897759628, "grad_norm": 6.982335090637207, "learning_rate": 7.675620109834816e-06, "loss": 0.2607, "step": 326570 }, { "epoch": 1.9412593398362965, "grad_norm": 3.94596529006958, "learning_rate": 7.675444823678441e-06, "loss": 0.2885, "step": 326580 }, { "epoch": 1.941318781912965, "grad_norm": 4.7201642990112305, "learning_rate": 7.675269532914634e-06, "loss": 0.2561, "step": 326590 }, { "epoch": 1.9413782239896333, "grad_norm": 6.272654056549072, "learning_rate": 7.675094237543692e-06, "loss": 0.2528, "step": 326600 }, { "epoch": 1.9414376660663017, "grad_norm": 4.09773063659668, "learning_rate": 7.674918937565918e-06, "loss": 0.3036, "step": 326610 }, { "epoch": 1.9414971081429702, "grad_norm": 5.382109642028809, "learning_rate": 7.674743632981617e-06, "loss": 0.308, "step": 326620 }, { "epoch": 1.9415565502196386, "grad_norm": 5.6121015548706055, "learning_rate": 7.674568323791085e-06, "loss": 0.2783, "step": 326630 }, { "epoch": 1.941615992296307, "grad_norm": 4.538136005401611, "learning_rate": 7.674393009994628e-06, "loss": 0.2852, "step": 326640 }, { "epoch": 1.9416754343729754, "grad_norm": 5.429952144622803, "learning_rate": 7.674217691592549e-06, "loss": 0.2834, "step": 326650 }, { "epoch": 1.9417348764496436, "grad_norm": 4.746147632598877, "learning_rate": 7.674042368585147e-06, "loss": 0.2943, "step": 326660 }, { "epoch": 1.941794318526312, "grad_norm": 4.732874393463135, "learning_rate": 7.673867040972724e-06, "loss": 0.2646, "step": 326670 }, { "epoch": 1.9418537606029804, "grad_norm": 4.108608245849609, "learning_rate": 7.673691708755584e-06, "loss": 0.264, "step": 326680 }, { "epoch": 1.9419132026796488, "grad_norm": 5.060576915740967, "learning_rate": 7.673516371934026e-06, "loss": 0.2602, "step": 326690 }, { "epoch": 1.9419726447563173, "grad_norm": 5.057060718536377, "learning_rate": 7.673341030508357e-06, "loss": 0.264, "step": 326700 }, { "epoch": 1.9420320868329854, "grad_norm": 5.8535566329956055, "learning_rate": 7.673165684478875e-06, "loss": 0.3022, "step": 326710 }, { "epoch": 1.9420915289096539, "grad_norm": 4.124652862548828, "learning_rate": 7.672990333845881e-06, "loss": 0.3204, "step": 326720 }, { "epoch": 1.9421509709863223, "grad_norm": 6.440773963928223, "learning_rate": 7.67281497860968e-06, "loss": 0.2772, "step": 326730 }, { "epoch": 1.9422104130629907, "grad_norm": 6.295551776885986, "learning_rate": 7.672639618770572e-06, "loss": 0.2865, "step": 326740 }, { "epoch": 1.942269855139659, "grad_norm": 3.4242348670959473, "learning_rate": 7.67246425432886e-06, "loss": 0.2803, "step": 326750 }, { "epoch": 1.9423292972163275, "grad_norm": 4.655456066131592, "learning_rate": 7.672288885284845e-06, "loss": 0.258, "step": 326760 }, { "epoch": 1.942388739292996, "grad_norm": 4.15850305557251, "learning_rate": 7.67211351163883e-06, "loss": 0.3007, "step": 326770 }, { "epoch": 1.9424481813696644, "grad_norm": 3.35642147064209, "learning_rate": 7.671938133391119e-06, "loss": 0.28, "step": 326780 }, { "epoch": 1.9425076234463328, "grad_norm": 6.11293888092041, "learning_rate": 7.67176275054201e-06, "loss": 0.3224, "step": 326790 }, { "epoch": 1.9425670655230012, "grad_norm": 5.894067287445068, "learning_rate": 7.671587363091805e-06, "loss": 0.236, "step": 326800 }, { "epoch": 1.9426265075996696, "grad_norm": 7.674309253692627, "learning_rate": 7.67141197104081e-06, "loss": 0.3157, "step": 326810 }, { "epoch": 1.942685949676338, "grad_norm": 4.319775581359863, "learning_rate": 7.671236574389324e-06, "loss": 0.2833, "step": 326820 }, { "epoch": 1.9427453917530064, "grad_norm": 5.298051834106445, "learning_rate": 7.671061173137651e-06, "loss": 0.2763, "step": 326830 }, { "epoch": 1.9428048338296748, "grad_norm": 4.894079208374023, "learning_rate": 7.67088576728609e-06, "loss": 0.2887, "step": 326840 }, { "epoch": 1.942864275906343, "grad_norm": 4.997257232666016, "learning_rate": 7.670710356834947e-06, "loss": 0.2916, "step": 326850 }, { "epoch": 1.9429237179830114, "grad_norm": 6.670068740844727, "learning_rate": 7.67053494178452e-06, "loss": 0.2648, "step": 326860 }, { "epoch": 1.9429831600596799, "grad_norm": 5.117642879486084, "learning_rate": 7.670359522135115e-06, "loss": 0.2817, "step": 326870 }, { "epoch": 1.9430426021363483, "grad_norm": 4.395003318786621, "learning_rate": 7.670184097887032e-06, "loss": 0.2333, "step": 326880 }, { "epoch": 1.9431020442130165, "grad_norm": 4.819198131561279, "learning_rate": 7.670008669040572e-06, "loss": 0.2366, "step": 326890 }, { "epoch": 1.9431614862896849, "grad_norm": 3.9522972106933594, "learning_rate": 7.66983323559604e-06, "loss": 0.3026, "step": 326900 }, { "epoch": 1.9432209283663533, "grad_norm": 5.799772262573242, "learning_rate": 7.669657797553736e-06, "loss": 0.2838, "step": 326910 }, { "epoch": 1.9432803704430217, "grad_norm": 5.480555057525635, "learning_rate": 7.669482354913961e-06, "loss": 0.287, "step": 326920 }, { "epoch": 1.9433398125196901, "grad_norm": 5.64192533493042, "learning_rate": 7.669306907677023e-06, "loss": 0.2608, "step": 326930 }, { "epoch": 1.9433992545963585, "grad_norm": 4.166778564453125, "learning_rate": 7.669131455843217e-06, "loss": 0.2935, "step": 326940 }, { "epoch": 1.943458696673027, "grad_norm": 5.1922287940979, "learning_rate": 7.668955999412849e-06, "loss": 0.2852, "step": 326950 }, { "epoch": 1.9435181387496954, "grad_norm": 5.822006702423096, "learning_rate": 7.66878053838622e-06, "loss": 0.2758, "step": 326960 }, { "epoch": 1.9435775808263638, "grad_norm": 4.137552261352539, "learning_rate": 7.668605072763634e-06, "loss": 0.2684, "step": 326970 }, { "epoch": 1.9436370229030322, "grad_norm": 5.156696796417236, "learning_rate": 7.668429602545388e-06, "loss": 0.2513, "step": 326980 }, { "epoch": 1.9436964649797006, "grad_norm": 4.2463884353637695, "learning_rate": 7.66825412773179e-06, "loss": 0.2559, "step": 326990 }, { "epoch": 1.943755907056369, "grad_norm": 5.744813442230225, "learning_rate": 7.668078648323141e-06, "loss": 0.2782, "step": 327000 }, { "epoch": 1.9438153491330374, "grad_norm": 4.332812309265137, "learning_rate": 7.667903164319741e-06, "loss": 0.2863, "step": 327010 }, { "epoch": 1.9438747912097059, "grad_norm": 6.8054070472717285, "learning_rate": 7.667727675721894e-06, "loss": 0.2479, "step": 327020 }, { "epoch": 1.943934233286374, "grad_norm": 6.183628559112549, "learning_rate": 7.667552182529903e-06, "loss": 0.2868, "step": 327030 }, { "epoch": 1.9439936753630425, "grad_norm": 6.032427787780762, "learning_rate": 7.667376684744067e-06, "loss": 0.259, "step": 327040 }, { "epoch": 1.9440531174397109, "grad_norm": 4.951752185821533, "learning_rate": 7.66720118236469e-06, "loss": 0.2751, "step": 327050 }, { "epoch": 1.9441125595163793, "grad_norm": 5.160767078399658, "learning_rate": 7.667025675392074e-06, "loss": 0.2948, "step": 327060 }, { "epoch": 1.9441720015930477, "grad_norm": 5.654799461364746, "learning_rate": 7.666850163826522e-06, "loss": 0.2893, "step": 327070 }, { "epoch": 1.944231443669716, "grad_norm": 5.094104290008545, "learning_rate": 7.666674647668337e-06, "loss": 0.2923, "step": 327080 }, { "epoch": 1.9442908857463843, "grad_norm": 5.671940803527832, "learning_rate": 7.666499126917818e-06, "loss": 0.2956, "step": 327090 }, { "epoch": 1.9443503278230527, "grad_norm": 6.059420585632324, "learning_rate": 7.666323601575272e-06, "loss": 0.306, "step": 327100 }, { "epoch": 1.9444097698997211, "grad_norm": 4.786245346069336, "learning_rate": 7.666148071640997e-06, "loss": 0.2529, "step": 327110 }, { "epoch": 1.9444692119763896, "grad_norm": 4.736965656280518, "learning_rate": 7.665972537115295e-06, "loss": 0.2594, "step": 327120 }, { "epoch": 1.944528654053058, "grad_norm": 4.804189205169678, "learning_rate": 7.665796997998473e-06, "loss": 0.2975, "step": 327130 }, { "epoch": 1.9445880961297264, "grad_norm": 6.881760120391846, "learning_rate": 7.66562145429083e-06, "loss": 0.2828, "step": 327140 }, { "epoch": 1.9446475382063948, "grad_norm": 5.387188911437988, "learning_rate": 7.665445905992667e-06, "loss": 0.2803, "step": 327150 }, { "epoch": 1.9447069802830632, "grad_norm": 5.742828369140625, "learning_rate": 7.665270353104292e-06, "loss": 0.2476, "step": 327160 }, { "epoch": 1.9447664223597316, "grad_norm": 5.531856060028076, "learning_rate": 7.665094795626e-06, "loss": 0.2884, "step": 327170 }, { "epoch": 1.9448258644364, "grad_norm": 4.654299736022949, "learning_rate": 7.664919233558097e-06, "loss": 0.2642, "step": 327180 }, { "epoch": 1.9448853065130685, "grad_norm": 6.061376094818115, "learning_rate": 7.664743666900887e-06, "loss": 0.2935, "step": 327190 }, { "epoch": 1.9449447485897369, "grad_norm": 5.46475076675415, "learning_rate": 7.66456809565467e-06, "loss": 0.2466, "step": 327200 }, { "epoch": 1.9450041906664053, "grad_norm": 4.992799758911133, "learning_rate": 7.664392519819746e-06, "loss": 0.2725, "step": 327210 }, { "epoch": 1.9450636327430735, "grad_norm": 5.799256801605225, "learning_rate": 7.664216939396422e-06, "loss": 0.2559, "step": 327220 }, { "epoch": 1.945123074819742, "grad_norm": 6.187439918518066, "learning_rate": 7.664041354385e-06, "loss": 0.2743, "step": 327230 }, { "epoch": 1.9451825168964103, "grad_norm": 6.07161808013916, "learning_rate": 7.663865764785781e-06, "loss": 0.2812, "step": 327240 }, { "epoch": 1.9452419589730787, "grad_norm": 5.065945625305176, "learning_rate": 7.663690170599065e-06, "loss": 0.2616, "step": 327250 }, { "epoch": 1.945301401049747, "grad_norm": 6.862933158874512, "learning_rate": 7.663514571825158e-06, "loss": 0.2839, "step": 327260 }, { "epoch": 1.9453608431264153, "grad_norm": 4.785696506500244, "learning_rate": 7.663338968464362e-06, "loss": 0.3051, "step": 327270 }, { "epoch": 1.9454202852030837, "grad_norm": 5.757049560546875, "learning_rate": 7.663163360516977e-06, "loss": 0.2851, "step": 327280 }, { "epoch": 1.9454797272797522, "grad_norm": 5.113746643066406, "learning_rate": 7.662987747983305e-06, "loss": 0.2647, "step": 327290 }, { "epoch": 1.9455391693564206, "grad_norm": 6.007724761962891, "learning_rate": 7.662812130863655e-06, "loss": 0.2989, "step": 327300 }, { "epoch": 1.945598611433089, "grad_norm": 4.050387859344482, "learning_rate": 7.662636509158322e-06, "loss": 0.2491, "step": 327310 }, { "epoch": 1.9456580535097574, "grad_norm": 4.984035968780518, "learning_rate": 7.662460882867612e-06, "loss": 0.265, "step": 327320 }, { "epoch": 1.9457174955864258, "grad_norm": 5.012535572052002, "learning_rate": 7.662285251991826e-06, "loss": 0.3053, "step": 327330 }, { "epoch": 1.9457769376630942, "grad_norm": 5.084166049957275, "learning_rate": 7.662109616531268e-06, "loss": 0.2522, "step": 327340 }, { "epoch": 1.9458363797397626, "grad_norm": 6.066964149475098, "learning_rate": 7.661933976486238e-06, "loss": 0.2983, "step": 327350 }, { "epoch": 1.945895821816431, "grad_norm": 4.3169660568237305, "learning_rate": 7.661758331857043e-06, "loss": 0.2749, "step": 327360 }, { "epoch": 1.9459552638930995, "grad_norm": 3.507366180419922, "learning_rate": 7.66158268264398e-06, "loss": 0.2801, "step": 327370 }, { "epoch": 1.9460147059697679, "grad_norm": 5.822716236114502, "learning_rate": 7.661407028847354e-06, "loss": 0.2787, "step": 327380 }, { "epoch": 1.9460741480464363, "grad_norm": 5.3482666015625, "learning_rate": 7.66123137046747e-06, "loss": 0.263, "step": 327390 }, { "epoch": 1.9461335901231045, "grad_norm": 6.170148849487305, "learning_rate": 7.661055707504626e-06, "loss": 0.2978, "step": 327400 }, { "epoch": 1.946193032199773, "grad_norm": 5.186532020568848, "learning_rate": 7.660880039959127e-06, "loss": 0.2747, "step": 327410 }, { "epoch": 1.9462524742764413, "grad_norm": 4.459745407104492, "learning_rate": 7.660704367831274e-06, "loss": 0.2611, "step": 327420 }, { "epoch": 1.9463119163531097, "grad_norm": 5.759877681732178, "learning_rate": 7.660528691121372e-06, "loss": 0.2749, "step": 327430 }, { "epoch": 1.9463713584297782, "grad_norm": 5.0249834060668945, "learning_rate": 7.660353009829723e-06, "loss": 0.2793, "step": 327440 }, { "epoch": 1.9464308005064463, "grad_norm": 5.445567607879639, "learning_rate": 7.660177323956626e-06, "loss": 0.2725, "step": 327450 }, { "epoch": 1.9464902425831148, "grad_norm": 4.697207927703857, "learning_rate": 7.660001633502388e-06, "loss": 0.2906, "step": 327460 }, { "epoch": 1.9465496846597832, "grad_norm": 5.898633003234863, "learning_rate": 7.659825938467309e-06, "loss": 0.2583, "step": 327470 }, { "epoch": 1.9466091267364516, "grad_norm": 4.49343204498291, "learning_rate": 7.659650238851694e-06, "loss": 0.2845, "step": 327480 }, { "epoch": 1.94666856881312, "grad_norm": 4.744326591491699, "learning_rate": 7.659474534655843e-06, "loss": 0.2847, "step": 327490 }, { "epoch": 1.9467280108897884, "grad_norm": 4.734806060791016, "learning_rate": 7.659298825880059e-06, "loss": 0.2774, "step": 327500 }, { "epoch": 1.9467874529664568, "grad_norm": 5.679786682128906, "learning_rate": 7.659123112524645e-06, "loss": 0.2761, "step": 327510 }, { "epoch": 1.9468468950431252, "grad_norm": 6.292067527770996, "learning_rate": 7.658947394589904e-06, "loss": 0.3103, "step": 327520 }, { "epoch": 1.9469063371197937, "grad_norm": 5.279754638671875, "learning_rate": 7.65877167207614e-06, "loss": 0.2781, "step": 327530 }, { "epoch": 1.946965779196462, "grad_norm": 3.9857888221740723, "learning_rate": 7.65859594498365e-06, "loss": 0.2568, "step": 327540 }, { "epoch": 1.9470252212731305, "grad_norm": 6.806648254394531, "learning_rate": 7.658420213312745e-06, "loss": 0.304, "step": 327550 }, { "epoch": 1.947084663349799, "grad_norm": 5.021429061889648, "learning_rate": 7.65824447706372e-06, "loss": 0.3099, "step": 327560 }, { "epoch": 1.9471441054264673, "grad_norm": 7.095951557159424, "learning_rate": 7.658068736236883e-06, "loss": 0.2948, "step": 327570 }, { "epoch": 1.9472035475031357, "grad_norm": 3.3596508502960205, "learning_rate": 7.657892990832534e-06, "loss": 0.2593, "step": 327580 }, { "epoch": 1.947262989579804, "grad_norm": 4.664521217346191, "learning_rate": 7.657717240850975e-06, "loss": 0.3126, "step": 327590 }, { "epoch": 1.9473224316564723, "grad_norm": 4.960564613342285, "learning_rate": 7.657541486292511e-06, "loss": 0.2814, "step": 327600 }, { "epoch": 1.9473818737331408, "grad_norm": 5.394078254699707, "learning_rate": 7.657365727157443e-06, "loss": 0.2621, "step": 327610 }, { "epoch": 1.9474413158098092, "grad_norm": 5.222031593322754, "learning_rate": 7.657189963446074e-06, "loss": 0.2998, "step": 327620 }, { "epoch": 1.9475007578864774, "grad_norm": 5.28884220123291, "learning_rate": 7.657014195158708e-06, "loss": 0.2791, "step": 327630 }, { "epoch": 1.9475601999631458, "grad_norm": 6.266485691070557, "learning_rate": 7.656838422295643e-06, "loss": 0.3137, "step": 327640 }, { "epoch": 1.9476196420398142, "grad_norm": 5.228485584259033, "learning_rate": 7.65666264485719e-06, "loss": 0.2951, "step": 327650 }, { "epoch": 1.9476790841164826, "grad_norm": 6.025579452514648, "learning_rate": 7.656486862843644e-06, "loss": 0.2889, "step": 327660 }, { "epoch": 1.947738526193151, "grad_norm": 3.7602362632751465, "learning_rate": 7.65631107625531e-06, "loss": 0.2438, "step": 327670 }, { "epoch": 1.9477979682698194, "grad_norm": 5.962599754333496, "learning_rate": 7.656135285092495e-06, "loss": 0.3047, "step": 327680 }, { "epoch": 1.9478574103464878, "grad_norm": 4.158746242523193, "learning_rate": 7.655959489355495e-06, "loss": 0.2857, "step": 327690 }, { "epoch": 1.9479168524231563, "grad_norm": 5.245443820953369, "learning_rate": 7.655783689044615e-06, "loss": 0.3209, "step": 327700 }, { "epoch": 1.9479762944998247, "grad_norm": 3.9258873462677, "learning_rate": 7.65560788416016e-06, "loss": 0.246, "step": 327710 }, { "epoch": 1.948035736576493, "grad_norm": 6.180334568023682, "learning_rate": 7.655432074702433e-06, "loss": 0.2625, "step": 327720 }, { "epoch": 1.9480951786531615, "grad_norm": 5.095718860626221, "learning_rate": 7.655256260671732e-06, "loss": 0.3232, "step": 327730 }, { "epoch": 1.94815462072983, "grad_norm": 5.1090593338012695, "learning_rate": 7.655080442068366e-06, "loss": 0.2825, "step": 327740 }, { "epoch": 1.9482140628064983, "grad_norm": 5.182193756103516, "learning_rate": 7.654904618892634e-06, "loss": 0.2643, "step": 327750 }, { "epoch": 1.9482735048831668, "grad_norm": 4.075272560119629, "learning_rate": 7.654728791144839e-06, "loss": 0.282, "step": 327760 }, { "epoch": 1.948332946959835, "grad_norm": 5.551196098327637, "learning_rate": 7.654552958825284e-06, "loss": 0.263, "step": 327770 }, { "epoch": 1.9483923890365034, "grad_norm": 4.80449914932251, "learning_rate": 7.654377121934272e-06, "loss": 0.2983, "step": 327780 }, { "epoch": 1.9484518311131718, "grad_norm": 5.570900917053223, "learning_rate": 7.654201280472106e-06, "loss": 0.2576, "step": 327790 }, { "epoch": 1.9485112731898402, "grad_norm": 5.092106342315674, "learning_rate": 7.654025434439087e-06, "loss": 0.2894, "step": 327800 }, { "epoch": 1.9485707152665086, "grad_norm": 4.3701629638671875, "learning_rate": 7.653849583835521e-06, "loss": 0.2906, "step": 327810 }, { "epoch": 1.9486301573431768, "grad_norm": 5.4328813552856445, "learning_rate": 7.653673728661711e-06, "loss": 0.2908, "step": 327820 }, { "epoch": 1.9486895994198452, "grad_norm": 5.466791152954102, "learning_rate": 7.653497868917957e-06, "loss": 0.2502, "step": 327830 }, { "epoch": 1.9487490414965136, "grad_norm": 4.458670616149902, "learning_rate": 7.653322004604563e-06, "loss": 0.2388, "step": 327840 }, { "epoch": 1.948808483573182, "grad_norm": 6.0293803215026855, "learning_rate": 7.653146135721831e-06, "loss": 0.2834, "step": 327850 }, { "epoch": 1.9488679256498505, "grad_norm": 3.7571964263916016, "learning_rate": 7.652970262270065e-06, "loss": 0.2735, "step": 327860 }, { "epoch": 1.9489273677265189, "grad_norm": 4.7997517585754395, "learning_rate": 7.652794384249569e-06, "loss": 0.2824, "step": 327870 }, { "epoch": 1.9489868098031873, "grad_norm": 5.523326873779297, "learning_rate": 7.652618501660643e-06, "loss": 0.2716, "step": 327880 }, { "epoch": 1.9490462518798557, "grad_norm": 4.361896514892578, "learning_rate": 7.652442614503594e-06, "loss": 0.3348, "step": 327890 }, { "epoch": 1.949105693956524, "grad_norm": 5.832250595092773, "learning_rate": 7.65226672277872e-06, "loss": 0.2664, "step": 327900 }, { "epoch": 1.9491651360331925, "grad_norm": 4.595485210418701, "learning_rate": 7.652090826486327e-06, "loss": 0.2794, "step": 327910 }, { "epoch": 1.949224578109861, "grad_norm": 4.653618812561035, "learning_rate": 7.651914925626717e-06, "loss": 0.2757, "step": 327920 }, { "epoch": 1.9492840201865294, "grad_norm": 5.693650722503662, "learning_rate": 7.651739020200192e-06, "loss": 0.2808, "step": 327930 }, { "epoch": 1.9493434622631978, "grad_norm": 5.217539310455322, "learning_rate": 7.651563110207057e-06, "loss": 0.2758, "step": 327940 }, { "epoch": 1.9494029043398662, "grad_norm": 6.370286464691162, "learning_rate": 7.651387195647613e-06, "loss": 0.2785, "step": 327950 }, { "epoch": 1.9494623464165344, "grad_norm": 3.7549054622650146, "learning_rate": 7.651211276522167e-06, "loss": 0.2729, "step": 327960 }, { "epoch": 1.9495217884932028, "grad_norm": 3.82839298248291, "learning_rate": 7.651035352831016e-06, "loss": 0.2814, "step": 327970 }, { "epoch": 1.9495812305698712, "grad_norm": 4.842752456665039, "learning_rate": 7.650859424574466e-06, "loss": 0.3096, "step": 327980 }, { "epoch": 1.9496406726465396, "grad_norm": 5.207998275756836, "learning_rate": 7.650683491752819e-06, "loss": 0.274, "step": 327990 }, { "epoch": 1.9497001147232078, "grad_norm": 6.498921871185303, "learning_rate": 7.650507554366382e-06, "loss": 0.2871, "step": 328000 }, { "epoch": 1.9497595567998762, "grad_norm": 6.735543251037598, "learning_rate": 7.650331612415453e-06, "loss": 0.2888, "step": 328010 }, { "epoch": 1.9498189988765446, "grad_norm": 5.708182334899902, "learning_rate": 7.650155665900336e-06, "loss": 0.3089, "step": 328020 }, { "epoch": 1.949878440953213, "grad_norm": 5.191513538360596, "learning_rate": 7.649979714821335e-06, "loss": 0.27, "step": 328030 }, { "epoch": 1.9499378830298815, "grad_norm": 5.6871209144592285, "learning_rate": 7.649803759178753e-06, "loss": 0.2528, "step": 328040 }, { "epoch": 1.9499973251065499, "grad_norm": 4.987320423126221, "learning_rate": 7.649627798972892e-06, "loss": 0.273, "step": 328050 }, { "epoch": 1.9500567671832183, "grad_norm": 4.950378894805908, "learning_rate": 7.649451834204055e-06, "loss": 0.2862, "step": 328060 }, { "epoch": 1.9501162092598867, "grad_norm": 5.094954967498779, "learning_rate": 7.64927586487255e-06, "loss": 0.2426, "step": 328070 }, { "epoch": 1.9501756513365551, "grad_norm": 4.7027716636657715, "learning_rate": 7.649099890978673e-06, "loss": 0.2737, "step": 328080 }, { "epoch": 1.9502350934132235, "grad_norm": 4.214355945587158, "learning_rate": 7.64892391252273e-06, "loss": 0.2578, "step": 328090 }, { "epoch": 1.950294535489892, "grad_norm": 6.630659580230713, "learning_rate": 7.648747929505024e-06, "loss": 0.3007, "step": 328100 }, { "epoch": 1.9503539775665604, "grad_norm": 4.4635539054870605, "learning_rate": 7.648571941925858e-06, "loss": 0.303, "step": 328110 }, { "epoch": 1.9504134196432288, "grad_norm": 4.894101619720459, "learning_rate": 7.648395949785534e-06, "loss": 0.2652, "step": 328120 }, { "epoch": 1.9504728617198972, "grad_norm": 4.161472320556641, "learning_rate": 7.648219953084358e-06, "loss": 0.3169, "step": 328130 }, { "epoch": 1.9505323037965654, "grad_norm": 6.133109092712402, "learning_rate": 7.648043951822632e-06, "loss": 0.2991, "step": 328140 }, { "epoch": 1.9505917458732338, "grad_norm": 4.5149712562561035, "learning_rate": 7.647867946000656e-06, "loss": 0.249, "step": 328150 }, { "epoch": 1.9506511879499022, "grad_norm": 3.5602400302886963, "learning_rate": 7.647691935618736e-06, "loss": 0.2786, "step": 328160 }, { "epoch": 1.9507106300265706, "grad_norm": 4.752297878265381, "learning_rate": 7.647515920677175e-06, "loss": 0.2654, "step": 328170 }, { "epoch": 1.950770072103239, "grad_norm": 4.728939056396484, "learning_rate": 7.647339901176276e-06, "loss": 0.258, "step": 328180 }, { "epoch": 1.9508295141799072, "grad_norm": 3.5488319396972656, "learning_rate": 7.64716387711634e-06, "loss": 0.2516, "step": 328190 }, { "epoch": 1.9508889562565757, "grad_norm": 5.077110767364502, "learning_rate": 7.646987848497675e-06, "loss": 0.2895, "step": 328200 }, { "epoch": 1.950948398333244, "grad_norm": 6.9449286460876465, "learning_rate": 7.646811815320579e-06, "loss": 0.2779, "step": 328210 }, { "epoch": 1.9510078404099125, "grad_norm": 4.674505710601807, "learning_rate": 7.646635777585358e-06, "loss": 0.2816, "step": 328220 }, { "epoch": 1.951067282486581, "grad_norm": 6.9038190841674805, "learning_rate": 7.646459735292315e-06, "loss": 0.291, "step": 328230 }, { "epoch": 1.9511267245632493, "grad_norm": 6.027131080627441, "learning_rate": 7.64628368844175e-06, "loss": 0.2746, "step": 328240 }, { "epoch": 1.9511861666399177, "grad_norm": 3.9322896003723145, "learning_rate": 7.646107637033971e-06, "loss": 0.3343, "step": 328250 }, { "epoch": 1.9512456087165861, "grad_norm": 6.08551549911499, "learning_rate": 7.64593158106928e-06, "loss": 0.2903, "step": 328260 }, { "epoch": 1.9513050507932546, "grad_norm": 4.583146095275879, "learning_rate": 7.645755520547978e-06, "loss": 0.2786, "step": 328270 }, { "epoch": 1.951364492869923, "grad_norm": 6.807465076446533, "learning_rate": 7.645579455470367e-06, "loss": 0.303, "step": 328280 }, { "epoch": 1.9514239349465914, "grad_norm": 4.4197258949279785, "learning_rate": 7.645403385836755e-06, "loss": 0.2957, "step": 328290 }, { "epoch": 1.9514833770232598, "grad_norm": 4.969805717468262, "learning_rate": 7.645227311647441e-06, "loss": 0.2838, "step": 328300 }, { "epoch": 1.9515428190999282, "grad_norm": 5.880462169647217, "learning_rate": 7.645051232902732e-06, "loss": 0.2734, "step": 328310 }, { "epoch": 1.9516022611765966, "grad_norm": 4.982304573059082, "learning_rate": 7.644875149602925e-06, "loss": 0.2897, "step": 328320 }, { "epoch": 1.9516617032532648, "grad_norm": 3.968212366104126, "learning_rate": 7.644699061748333e-06, "loss": 0.2709, "step": 328330 }, { "epoch": 1.9517211453299332, "grad_norm": 5.973362445831299, "learning_rate": 7.644522969339253e-06, "loss": 0.2983, "step": 328340 }, { "epoch": 1.9517805874066017, "grad_norm": 6.178294658660889, "learning_rate": 7.644346872375985e-06, "loss": 0.2892, "step": 328350 }, { "epoch": 1.95184002948327, "grad_norm": 6.349532604217529, "learning_rate": 7.644170770858839e-06, "loss": 0.3036, "step": 328360 }, { "epoch": 1.9518994715599383, "grad_norm": 6.698276042938232, "learning_rate": 7.643994664788115e-06, "loss": 0.3032, "step": 328370 }, { "epoch": 1.9519589136366067, "grad_norm": 5.138767719268799, "learning_rate": 7.643818554164115e-06, "loss": 0.2751, "step": 328380 }, { "epoch": 1.952018355713275, "grad_norm": 4.625139236450195, "learning_rate": 7.643642438987145e-06, "loss": 0.2775, "step": 328390 }, { "epoch": 1.9520777977899435, "grad_norm": 5.030825138092041, "learning_rate": 7.643466319257508e-06, "loss": 0.2658, "step": 328400 }, { "epoch": 1.952137239866612, "grad_norm": 6.514553070068359, "learning_rate": 7.643290194975508e-06, "loss": 0.2823, "step": 328410 }, { "epoch": 1.9521966819432803, "grad_norm": 4.973184108734131, "learning_rate": 7.643114066141443e-06, "loss": 0.2924, "step": 328420 }, { "epoch": 1.9522561240199487, "grad_norm": 4.9593024253845215, "learning_rate": 7.642937932755623e-06, "loss": 0.2482, "step": 328430 }, { "epoch": 1.9523155660966172, "grad_norm": 6.068912982940674, "learning_rate": 7.642761794818349e-06, "loss": 0.2962, "step": 328440 }, { "epoch": 1.9523750081732856, "grad_norm": 6.862261772155762, "learning_rate": 7.642585652329921e-06, "loss": 0.2783, "step": 328450 }, { "epoch": 1.952434450249954, "grad_norm": 6.071090221405029, "learning_rate": 7.642409505290648e-06, "loss": 0.285, "step": 328460 }, { "epoch": 1.9524938923266224, "grad_norm": 4.685901641845703, "learning_rate": 7.64223335370083e-06, "loss": 0.277, "step": 328470 }, { "epoch": 1.9525533344032908, "grad_norm": 5.170740604400635, "learning_rate": 7.64205719756077e-06, "loss": 0.3155, "step": 328480 }, { "epoch": 1.9526127764799592, "grad_norm": 5.367992877960205, "learning_rate": 7.641881036870773e-06, "loss": 0.2662, "step": 328490 }, { "epoch": 1.9526722185566276, "grad_norm": 4.305130958557129, "learning_rate": 7.64170487163114e-06, "loss": 0.2587, "step": 328500 }, { "epoch": 1.9527316606332958, "grad_norm": 4.07806921005249, "learning_rate": 7.641528701842177e-06, "loss": 0.27, "step": 328510 }, { "epoch": 1.9527911027099643, "grad_norm": 5.422336578369141, "learning_rate": 7.641352527504188e-06, "loss": 0.2969, "step": 328520 }, { "epoch": 1.9528505447866327, "grad_norm": 4.7849297523498535, "learning_rate": 7.641176348617473e-06, "loss": 0.2673, "step": 328530 }, { "epoch": 1.952909986863301, "grad_norm": 3.3586838245391846, "learning_rate": 7.641000165182338e-06, "loss": 0.2823, "step": 328540 }, { "epoch": 1.9529694289399695, "grad_norm": 4.211588382720947, "learning_rate": 7.640823977199085e-06, "loss": 0.2602, "step": 328550 }, { "epoch": 1.9530288710166377, "grad_norm": 5.5030927658081055, "learning_rate": 7.64064778466802e-06, "loss": 0.2682, "step": 328560 }, { "epoch": 1.953088313093306, "grad_norm": 4.837373733520508, "learning_rate": 7.640471587589442e-06, "loss": 0.2657, "step": 328570 }, { "epoch": 1.9531477551699745, "grad_norm": 5.538293361663818, "learning_rate": 7.640295385963658e-06, "loss": 0.2639, "step": 328580 }, { "epoch": 1.953207197246643, "grad_norm": 4.98751163482666, "learning_rate": 7.64011917979097e-06, "loss": 0.2567, "step": 328590 }, { "epoch": 1.9532666393233113, "grad_norm": 4.079493999481201, "learning_rate": 7.639942969071682e-06, "loss": 0.2872, "step": 328600 }, { "epoch": 1.9533260813999798, "grad_norm": 4.93467378616333, "learning_rate": 7.639766753806095e-06, "loss": 0.2878, "step": 328610 }, { "epoch": 1.9533855234766482, "grad_norm": 5.0797224044799805, "learning_rate": 7.639590533994517e-06, "loss": 0.301, "step": 328620 }, { "epoch": 1.9534449655533166, "grad_norm": 4.991596221923828, "learning_rate": 7.63941430963725e-06, "loss": 0.2623, "step": 328630 }, { "epoch": 1.953504407629985, "grad_norm": 3.256824016571045, "learning_rate": 7.639238080734595e-06, "loss": 0.2707, "step": 328640 }, { "epoch": 1.9535638497066534, "grad_norm": 3.40169620513916, "learning_rate": 7.639061847286857e-06, "loss": 0.285, "step": 328650 }, { "epoch": 1.9536232917833218, "grad_norm": 4.499701976776123, "learning_rate": 7.63888560929434e-06, "loss": 0.2642, "step": 328660 }, { "epoch": 1.9536827338599903, "grad_norm": 4.85692834854126, "learning_rate": 7.638709366757346e-06, "loss": 0.2692, "step": 328670 }, { "epoch": 1.9537421759366587, "grad_norm": 6.410993576049805, "learning_rate": 7.63853311967618e-06, "loss": 0.3045, "step": 328680 }, { "epoch": 1.953801618013327, "grad_norm": 6.67364501953125, "learning_rate": 7.63835686805115e-06, "loss": 0.2953, "step": 328690 }, { "epoch": 1.9538610600899953, "grad_norm": 4.816603660583496, "learning_rate": 7.638180611882548e-06, "loss": 0.2864, "step": 328700 }, { "epoch": 1.9539205021666637, "grad_norm": 4.158491134643555, "learning_rate": 7.638004351170686e-06, "loss": 0.3105, "step": 328710 }, { "epoch": 1.953979944243332, "grad_norm": 5.878504753112793, "learning_rate": 7.637828085915868e-06, "loss": 0.2904, "step": 328720 }, { "epoch": 1.9540393863200005, "grad_norm": 4.844135761260986, "learning_rate": 7.637651816118395e-06, "loss": 0.3023, "step": 328730 }, { "epoch": 1.9540988283966687, "grad_norm": 5.0525078773498535, "learning_rate": 7.63747554177857e-06, "loss": 0.2713, "step": 328740 }, { "epoch": 1.9541582704733371, "grad_norm": 4.643665790557861, "learning_rate": 7.637299262896695e-06, "loss": 0.2654, "step": 328750 }, { "epoch": 1.9542177125500055, "grad_norm": 4.280092716217041, "learning_rate": 7.63712297947308e-06, "loss": 0.3034, "step": 328760 }, { "epoch": 1.954277154626674, "grad_norm": 4.561826705932617, "learning_rate": 7.636946691508022e-06, "loss": 0.2849, "step": 328770 }, { "epoch": 1.9543365967033424, "grad_norm": 5.427773952484131, "learning_rate": 7.636770399001826e-06, "loss": 0.271, "step": 328780 }, { "epoch": 1.9543960387800108, "grad_norm": 4.29927921295166, "learning_rate": 7.6365941019548e-06, "loss": 0.2916, "step": 328790 }, { "epoch": 1.9544554808566792, "grad_norm": 5.1927385330200195, "learning_rate": 7.636417800367243e-06, "loss": 0.2935, "step": 328800 }, { "epoch": 1.9545149229333476, "grad_norm": 5.665559768676758, "learning_rate": 7.636241494239461e-06, "loss": 0.275, "step": 328810 }, { "epoch": 1.954574365010016, "grad_norm": 5.200775146484375, "learning_rate": 7.636065183571754e-06, "loss": 0.2635, "step": 328820 }, { "epoch": 1.9546338070866844, "grad_norm": 4.512644290924072, "learning_rate": 7.63588886836443e-06, "loss": 0.2388, "step": 328830 }, { "epoch": 1.9546932491633529, "grad_norm": 5.210911750793457, "learning_rate": 7.63571254861779e-06, "loss": 0.2754, "step": 328840 }, { "epoch": 1.9547526912400213, "grad_norm": 6.502145767211914, "learning_rate": 7.635536224332141e-06, "loss": 0.2687, "step": 328850 }, { "epoch": 1.9548121333166897, "grad_norm": 5.420384883880615, "learning_rate": 7.635359895507782e-06, "loss": 0.2851, "step": 328860 }, { "epoch": 1.954871575393358, "grad_norm": 4.880100250244141, "learning_rate": 7.63518356214502e-06, "loss": 0.2873, "step": 328870 }, { "epoch": 1.9549310174700263, "grad_norm": 4.978274345397949, "learning_rate": 7.635007224244156e-06, "loss": 0.2811, "step": 328880 }, { "epoch": 1.9549904595466947, "grad_norm": 4.670113563537598, "learning_rate": 7.634830881805495e-06, "loss": 0.2664, "step": 328890 }, { "epoch": 1.9550499016233631, "grad_norm": 5.467463493347168, "learning_rate": 7.634654534829341e-06, "loss": 0.2604, "step": 328900 }, { "epoch": 1.9551093437000315, "grad_norm": 5.140778541564941, "learning_rate": 7.634478183315998e-06, "loss": 0.309, "step": 328910 }, { "epoch": 1.9551687857767, "grad_norm": 4.240037441253662, "learning_rate": 7.634301827265772e-06, "loss": 0.2727, "step": 328920 }, { "epoch": 1.9552282278533681, "grad_norm": 4.439615249633789, "learning_rate": 7.634125466678959e-06, "loss": 0.2932, "step": 328930 }, { "epoch": 1.9552876699300366, "grad_norm": 4.626313209533691, "learning_rate": 7.63394910155587e-06, "loss": 0.2707, "step": 328940 }, { "epoch": 1.955347112006705, "grad_norm": 4.40122652053833, "learning_rate": 7.633772731896807e-06, "loss": 0.295, "step": 328950 }, { "epoch": 1.9554065540833734, "grad_norm": 4.68951940536499, "learning_rate": 7.633596357702073e-06, "loss": 0.2935, "step": 328960 }, { "epoch": 1.9554659961600418, "grad_norm": 4.564360618591309, "learning_rate": 7.63341997897197e-06, "loss": 0.2556, "step": 328970 }, { "epoch": 1.9555254382367102, "grad_norm": 4.835826873779297, "learning_rate": 7.633243595706806e-06, "loss": 0.2677, "step": 328980 }, { "epoch": 1.9555848803133786, "grad_norm": 5.171745300292969, "learning_rate": 7.633067207906881e-06, "loss": 0.2676, "step": 328990 }, { "epoch": 1.955644322390047, "grad_norm": 4.930307388305664, "learning_rate": 7.6328908155725e-06, "loss": 0.2854, "step": 329000 }, { "epoch": 1.9557037644667155, "grad_norm": 4.284942150115967, "learning_rate": 7.632714418703967e-06, "loss": 0.2939, "step": 329010 }, { "epoch": 1.9557632065433839, "grad_norm": 6.016269683837891, "learning_rate": 7.632538017301586e-06, "loss": 0.295, "step": 329020 }, { "epoch": 1.9558226486200523, "grad_norm": 3.8578286170959473, "learning_rate": 7.632361611365659e-06, "loss": 0.2735, "step": 329030 }, { "epoch": 1.9558820906967207, "grad_norm": 4.662004470825195, "learning_rate": 7.632185200896493e-06, "loss": 0.2911, "step": 329040 }, { "epoch": 1.9559415327733891, "grad_norm": 4.46993350982666, "learning_rate": 7.63200878589439e-06, "loss": 0.2855, "step": 329050 }, { "epoch": 1.9560009748500575, "grad_norm": 4.0878167152404785, "learning_rate": 7.631832366359652e-06, "loss": 0.2785, "step": 329060 }, { "epoch": 1.9560604169267257, "grad_norm": 5.054075241088867, "learning_rate": 7.631655942292587e-06, "loss": 0.2748, "step": 329070 }, { "epoch": 1.9561198590033941, "grad_norm": 6.257608413696289, "learning_rate": 7.631479513693496e-06, "loss": 0.2746, "step": 329080 }, { "epoch": 1.9561793010800625, "grad_norm": 4.116382598876953, "learning_rate": 7.631303080562682e-06, "loss": 0.2435, "step": 329090 }, { "epoch": 1.956238743156731, "grad_norm": 4.785589694976807, "learning_rate": 7.63112664290045e-06, "loss": 0.3002, "step": 329100 }, { "epoch": 1.9562981852333992, "grad_norm": 5.470540523529053, "learning_rate": 7.630950200707105e-06, "loss": 0.2715, "step": 329110 }, { "epoch": 1.9563576273100676, "grad_norm": 4.5825114250183105, "learning_rate": 7.63077375398295e-06, "loss": 0.2535, "step": 329120 }, { "epoch": 1.956417069386736, "grad_norm": 4.701948165893555, "learning_rate": 7.630597302728289e-06, "loss": 0.2919, "step": 329130 }, { "epoch": 1.9564765114634044, "grad_norm": 4.298105239868164, "learning_rate": 7.630420846943425e-06, "loss": 0.2472, "step": 329140 }, { "epoch": 1.9565359535400728, "grad_norm": 5.011028289794922, "learning_rate": 7.630244386628662e-06, "loss": 0.2574, "step": 329150 }, { "epoch": 1.9565953956167412, "grad_norm": 6.385591506958008, "learning_rate": 7.630067921784303e-06, "loss": 0.2768, "step": 329160 }, { "epoch": 1.9566548376934096, "grad_norm": 4.958395481109619, "learning_rate": 7.629891452410656e-06, "loss": 0.2931, "step": 329170 }, { "epoch": 1.956714279770078, "grad_norm": 5.7338080406188965, "learning_rate": 7.62971497850802e-06, "loss": 0.2775, "step": 329180 }, { "epoch": 1.9567737218467465, "grad_norm": 3.9239392280578613, "learning_rate": 7.629538500076701e-06, "loss": 0.2681, "step": 329190 }, { "epoch": 1.9568331639234149, "grad_norm": 3.5363810062408447, "learning_rate": 7.629362017117006e-06, "loss": 0.2524, "step": 329200 }, { "epoch": 1.9568926060000833, "grad_norm": 5.245999813079834, "learning_rate": 7.629185529629234e-06, "loss": 0.2719, "step": 329210 }, { "epoch": 1.9569520480767517, "grad_norm": 4.2135701179504395, "learning_rate": 7.62900903761369e-06, "loss": 0.2596, "step": 329220 }, { "epoch": 1.9570114901534201, "grad_norm": 5.4531097412109375, "learning_rate": 7.62883254107068e-06, "loss": 0.2672, "step": 329230 }, { "epoch": 1.9570709322300885, "grad_norm": 5.063724994659424, "learning_rate": 7.628656040000506e-06, "loss": 0.2652, "step": 329240 }, { "epoch": 1.9571303743067567, "grad_norm": 5.6293487548828125, "learning_rate": 7.6284795344034735e-06, "loss": 0.2774, "step": 329250 }, { "epoch": 1.9571898163834252, "grad_norm": 6.341949462890625, "learning_rate": 7.628303024279884e-06, "loss": 0.2941, "step": 329260 }, { "epoch": 1.9572492584600936, "grad_norm": 6.284097194671631, "learning_rate": 7.628126509630043e-06, "loss": 0.2638, "step": 329270 }, { "epoch": 1.957308700536762, "grad_norm": 6.127630710601807, "learning_rate": 7.627949990454257e-06, "loss": 0.2963, "step": 329280 }, { "epoch": 1.9573681426134304, "grad_norm": 3.9957306385040283, "learning_rate": 7.627773466752824e-06, "loss": 0.2579, "step": 329290 }, { "epoch": 1.9574275846900986, "grad_norm": 4.984668731689453, "learning_rate": 7.627596938526054e-06, "loss": 0.2827, "step": 329300 }, { "epoch": 1.957487026766767, "grad_norm": 3.4864141941070557, "learning_rate": 7.627420405774249e-06, "loss": 0.2607, "step": 329310 }, { "epoch": 1.9575464688434354, "grad_norm": 3.4231038093566895, "learning_rate": 7.627243868497711e-06, "loss": 0.2664, "step": 329320 }, { "epoch": 1.9576059109201038, "grad_norm": 5.173196792602539, "learning_rate": 7.627067326696747e-06, "loss": 0.2891, "step": 329330 }, { "epoch": 1.9576653529967722, "grad_norm": 5.461955547332764, "learning_rate": 7.62689078037166e-06, "loss": 0.2816, "step": 329340 }, { "epoch": 1.9577247950734407, "grad_norm": 4.157496929168701, "learning_rate": 7.6267142295227515e-06, "loss": 0.2909, "step": 329350 }, { "epoch": 1.957784237150109, "grad_norm": 5.803371906280518, "learning_rate": 7.6265376741503295e-06, "loss": 0.3004, "step": 329360 }, { "epoch": 1.9578436792267775, "grad_norm": 5.274265766143799, "learning_rate": 7.626361114254696e-06, "loss": 0.285, "step": 329370 }, { "epoch": 1.957903121303446, "grad_norm": 4.902028560638428, "learning_rate": 7.626184549836153e-06, "loss": 0.265, "step": 329380 }, { "epoch": 1.9579625633801143, "grad_norm": 4.940432548522949, "learning_rate": 7.626007980895009e-06, "loss": 0.2934, "step": 329390 }, { "epoch": 1.9580220054567827, "grad_norm": 4.930306911468506, "learning_rate": 7.625831407431565e-06, "loss": 0.2872, "step": 329400 }, { "epoch": 1.9580814475334511, "grad_norm": 5.332109451293945, "learning_rate": 7.625654829446127e-06, "loss": 0.2791, "step": 329410 }, { "epoch": 1.9581408896101196, "grad_norm": 5.237401962280273, "learning_rate": 7.625478246938998e-06, "loss": 0.2751, "step": 329420 }, { "epoch": 1.958200331686788, "grad_norm": 5.980586051940918, "learning_rate": 7.625301659910482e-06, "loss": 0.2711, "step": 329430 }, { "epoch": 1.9582597737634562, "grad_norm": 5.684526443481445, "learning_rate": 7.625125068360883e-06, "loss": 0.262, "step": 329440 }, { "epoch": 1.9583192158401246, "grad_norm": 4.791303634643555, "learning_rate": 7.624948472290505e-06, "loss": 0.2603, "step": 329450 }, { "epoch": 1.958378657916793, "grad_norm": 5.910103797912598, "learning_rate": 7.624771871699655e-06, "loss": 0.3186, "step": 329460 }, { "epoch": 1.9584380999934614, "grad_norm": 3.667668342590332, "learning_rate": 7.624595266588632e-06, "loss": 0.2876, "step": 329470 }, { "epoch": 1.9584975420701296, "grad_norm": 4.866632461547852, "learning_rate": 7.624418656957743e-06, "loss": 0.2546, "step": 329480 }, { "epoch": 1.958556984146798, "grad_norm": 4.933913230895996, "learning_rate": 7.6242420428072915e-06, "loss": 0.3114, "step": 329490 }, { "epoch": 1.9586164262234664, "grad_norm": 5.114049911499023, "learning_rate": 7.624065424137583e-06, "loss": 0.2824, "step": 329500 }, { "epoch": 1.9586758683001348, "grad_norm": 5.398128509521484, "learning_rate": 7.623888800948922e-06, "loss": 0.2822, "step": 329510 }, { "epoch": 1.9587353103768033, "grad_norm": 4.418612480163574, "learning_rate": 7.62371217324161e-06, "loss": 0.2606, "step": 329520 }, { "epoch": 1.9587947524534717, "grad_norm": 5.4798736572265625, "learning_rate": 7.623535541015953e-06, "loss": 0.2731, "step": 329530 }, { "epoch": 1.95885419453014, "grad_norm": 5.2378058433532715, "learning_rate": 7.623358904272255e-06, "loss": 0.2782, "step": 329540 }, { "epoch": 1.9589136366068085, "grad_norm": 6.240213394165039, "learning_rate": 7.623182263010817e-06, "loss": 0.3058, "step": 329550 }, { "epoch": 1.958973078683477, "grad_norm": 6.468730926513672, "learning_rate": 7.623005617231951e-06, "loss": 0.2776, "step": 329560 }, { "epoch": 1.9590325207601453, "grad_norm": 4.595036029815674, "learning_rate": 7.622828966935953e-06, "loss": 0.2505, "step": 329570 }, { "epoch": 1.9590919628368137, "grad_norm": 5.2767839431762695, "learning_rate": 7.622652312123131e-06, "loss": 0.2657, "step": 329580 }, { "epoch": 1.9591514049134822, "grad_norm": 4.013813018798828, "learning_rate": 7.622475652793791e-06, "loss": 0.2543, "step": 329590 }, { "epoch": 1.9592108469901506, "grad_norm": 6.562255382537842, "learning_rate": 7.622298988948232e-06, "loss": 0.2935, "step": 329600 }, { "epoch": 1.959270289066819, "grad_norm": 4.54366397857666, "learning_rate": 7.622122320586763e-06, "loss": 0.3156, "step": 329610 }, { "epoch": 1.9593297311434872, "grad_norm": 5.160719394683838, "learning_rate": 7.621945647709686e-06, "loss": 0.3185, "step": 329620 }, { "epoch": 1.9593891732201556, "grad_norm": 5.408088207244873, "learning_rate": 7.621768970317306e-06, "loss": 0.2795, "step": 329630 }, { "epoch": 1.959448615296824, "grad_norm": 5.545362949371338, "learning_rate": 7.621592288409927e-06, "loss": 0.2963, "step": 329640 }, { "epoch": 1.9595080573734924, "grad_norm": 5.010126113891602, "learning_rate": 7.621415601987853e-06, "loss": 0.2965, "step": 329650 }, { "epoch": 1.9595674994501608, "grad_norm": 5.059442043304443, "learning_rate": 7.62123891105139e-06, "loss": 0.2694, "step": 329660 }, { "epoch": 1.959626941526829, "grad_norm": 5.636062145233154, "learning_rate": 7.621062215600838e-06, "loss": 0.2928, "step": 329670 }, { "epoch": 1.9596863836034975, "grad_norm": 6.486191272735596, "learning_rate": 7.620885515636506e-06, "loss": 0.3242, "step": 329680 }, { "epoch": 1.9597458256801659, "grad_norm": 5.027057647705078, "learning_rate": 7.620708811158697e-06, "loss": 0.2856, "step": 329690 }, { "epoch": 1.9598052677568343, "grad_norm": 5.602546215057373, "learning_rate": 7.620532102167713e-06, "loss": 0.281, "step": 329700 }, { "epoch": 1.9598647098335027, "grad_norm": 4.496652126312256, "learning_rate": 7.620355388663861e-06, "loss": 0.2604, "step": 329710 }, { "epoch": 1.959924151910171, "grad_norm": 4.121330738067627, "learning_rate": 7.6201786706474434e-06, "loss": 0.256, "step": 329720 }, { "epoch": 1.9599835939868395, "grad_norm": 4.712906360626221, "learning_rate": 7.620001948118767e-06, "loss": 0.2378, "step": 329730 }, { "epoch": 1.960043036063508, "grad_norm": 5.610776424407959, "learning_rate": 7.619825221078134e-06, "loss": 0.2796, "step": 329740 }, { "epoch": 1.9601024781401764, "grad_norm": 5.778883934020996, "learning_rate": 7.619648489525848e-06, "loss": 0.2958, "step": 329750 }, { "epoch": 1.9601619202168448, "grad_norm": 4.993825912475586, "learning_rate": 7.619471753462217e-06, "loss": 0.2713, "step": 329760 }, { "epoch": 1.9602213622935132, "grad_norm": 5.73248291015625, "learning_rate": 7.619295012887543e-06, "loss": 0.2998, "step": 329770 }, { "epoch": 1.9602808043701816, "grad_norm": 4.97258996963501, "learning_rate": 7.619118267802129e-06, "loss": 0.2715, "step": 329780 }, { "epoch": 1.96034024644685, "grad_norm": 5.897712707519531, "learning_rate": 7.618941518206282e-06, "loss": 0.3019, "step": 329790 }, { "epoch": 1.9603996885235182, "grad_norm": 4.759364128112793, "learning_rate": 7.618764764100305e-06, "loss": 0.2844, "step": 329800 }, { "epoch": 1.9604591306001866, "grad_norm": 5.405136585235596, "learning_rate": 7.618588005484502e-06, "loss": 0.2687, "step": 329810 }, { "epoch": 1.960518572676855, "grad_norm": 6.229555606842041, "learning_rate": 7.618411242359177e-06, "loss": 0.2679, "step": 329820 }, { "epoch": 1.9605780147535234, "grad_norm": 4.856870651245117, "learning_rate": 7.618234474724637e-06, "loss": 0.2692, "step": 329830 }, { "epoch": 1.9606374568301919, "grad_norm": 5.043941974639893, "learning_rate": 7.618057702581184e-06, "loss": 0.2625, "step": 329840 }, { "epoch": 1.96069689890686, "grad_norm": 4.841056823730469, "learning_rate": 7.6178809259291245e-06, "loss": 0.2942, "step": 329850 }, { "epoch": 1.9607563409835285, "grad_norm": 5.500434398651123, "learning_rate": 7.617704144768761e-06, "loss": 0.291, "step": 329860 }, { "epoch": 1.9608157830601969, "grad_norm": 6.442734241485596, "learning_rate": 7.617527359100398e-06, "loss": 0.2764, "step": 329870 }, { "epoch": 1.9608752251368653, "grad_norm": 5.7940449714660645, "learning_rate": 7.617350568924342e-06, "loss": 0.2995, "step": 329880 }, { "epoch": 1.9609346672135337, "grad_norm": 4.31965970993042, "learning_rate": 7.617173774240896e-06, "loss": 0.2711, "step": 329890 }, { "epoch": 1.9609941092902021, "grad_norm": 4.929821014404297, "learning_rate": 7.6169969750503635e-06, "loss": 0.2663, "step": 329900 }, { "epoch": 1.9610535513668705, "grad_norm": 6.636446475982666, "learning_rate": 7.61682017135305e-06, "loss": 0.3018, "step": 329910 }, { "epoch": 1.961112993443539, "grad_norm": 6.870960235595703, "learning_rate": 7.61664336314926e-06, "loss": 0.2806, "step": 329920 }, { "epoch": 1.9611724355202074, "grad_norm": 4.9038166999816895, "learning_rate": 7.6164665504392965e-06, "loss": 0.2569, "step": 329930 }, { "epoch": 1.9612318775968758, "grad_norm": 5.205807209014893, "learning_rate": 7.616289733223468e-06, "loss": 0.3019, "step": 329940 }, { "epoch": 1.9612913196735442, "grad_norm": 4.6920881271362305, "learning_rate": 7.616112911502075e-06, "loss": 0.2746, "step": 329950 }, { "epoch": 1.9613507617502126, "grad_norm": 4.3680901527404785, "learning_rate": 7.6159360852754235e-06, "loss": 0.2674, "step": 329960 }, { "epoch": 1.961410203826881, "grad_norm": 5.11000394821167, "learning_rate": 7.615759254543818e-06, "loss": 0.2617, "step": 329970 }, { "epoch": 1.9614696459035494, "grad_norm": 3.8860902786254883, "learning_rate": 7.615582419307563e-06, "loss": 0.2625, "step": 329980 }, { "epoch": 1.9615290879802176, "grad_norm": 4.4910125732421875, "learning_rate": 7.615405579566963e-06, "loss": 0.2702, "step": 329990 }, { "epoch": 1.961588530056886, "grad_norm": 4.374996185302734, "learning_rate": 7.615228735322322e-06, "loss": 0.2715, "step": 330000 }, { "epoch": 1.9616479721335545, "grad_norm": 4.961493968963623, "learning_rate": 7.615051886573947e-06, "loss": 0.2709, "step": 330010 }, { "epoch": 1.9617074142102229, "grad_norm": 4.990878105163574, "learning_rate": 7.61487503332214e-06, "loss": 0.2731, "step": 330020 }, { "epoch": 1.9617668562868913, "grad_norm": 4.339869499206543, "learning_rate": 7.6146981755672046e-06, "loss": 0.2664, "step": 330030 }, { "epoch": 1.9618262983635595, "grad_norm": 4.831304550170898, "learning_rate": 7.614521313309447e-06, "loss": 0.2767, "step": 330040 }, { "epoch": 1.961885740440228, "grad_norm": 5.555069446563721, "learning_rate": 7.6143444465491736e-06, "loss": 0.2677, "step": 330050 }, { "epoch": 1.9619451825168963, "grad_norm": 5.851579666137695, "learning_rate": 7.6141675752866864e-06, "loss": 0.2684, "step": 330060 }, { "epoch": 1.9620046245935647, "grad_norm": 5.630671501159668, "learning_rate": 7.613990699522289e-06, "loss": 0.259, "step": 330070 }, { "epoch": 1.9620640666702331, "grad_norm": 3.805798053741455, "learning_rate": 7.61381381925629e-06, "loss": 0.294, "step": 330080 }, { "epoch": 1.9621235087469016, "grad_norm": 4.866486072540283, "learning_rate": 7.61363693448899e-06, "loss": 0.2968, "step": 330090 }, { "epoch": 1.96218295082357, "grad_norm": 5.612034797668457, "learning_rate": 7.613460045220698e-06, "loss": 0.274, "step": 330100 }, { "epoch": 1.9622423929002384, "grad_norm": 4.833797931671143, "learning_rate": 7.613283151451713e-06, "loss": 0.2626, "step": 330110 }, { "epoch": 1.9623018349769068, "grad_norm": 3.827316999435425, "learning_rate": 7.613106253182346e-06, "loss": 0.2636, "step": 330120 }, { "epoch": 1.9623612770535752, "grad_norm": 5.870660305023193, "learning_rate": 7.612929350412894e-06, "loss": 0.2823, "step": 330130 }, { "epoch": 1.9624207191302436, "grad_norm": 5.867066383361816, "learning_rate": 7.612752443143668e-06, "loss": 0.2896, "step": 330140 }, { "epoch": 1.962480161206912, "grad_norm": 4.628873825073242, "learning_rate": 7.6125755313749705e-06, "loss": 0.2756, "step": 330150 }, { "epoch": 1.9625396032835805, "grad_norm": 4.731592655181885, "learning_rate": 7.612398615107106e-06, "loss": 0.2866, "step": 330160 }, { "epoch": 1.9625990453602487, "grad_norm": 6.371091365814209, "learning_rate": 7.612221694340379e-06, "loss": 0.248, "step": 330170 }, { "epoch": 1.962658487436917, "grad_norm": 6.422276496887207, "learning_rate": 7.612044769075096e-06, "loss": 0.2965, "step": 330180 }, { "epoch": 1.9627179295135855, "grad_norm": 5.97258996963501, "learning_rate": 7.61186783931156e-06, "loss": 0.2573, "step": 330190 }, { "epoch": 1.962777371590254, "grad_norm": 4.85960578918457, "learning_rate": 7.611690905050074e-06, "loss": 0.2666, "step": 330200 }, { "epoch": 1.9628368136669223, "grad_norm": 5.049291133880615, "learning_rate": 7.6115139662909464e-06, "loss": 0.2857, "step": 330210 }, { "epoch": 1.9628962557435905, "grad_norm": 3.2395753860473633, "learning_rate": 7.61133702303448e-06, "loss": 0.2623, "step": 330220 }, { "epoch": 1.962955697820259, "grad_norm": 6.681697845458984, "learning_rate": 7.611160075280979e-06, "loss": 0.3004, "step": 330230 }, { "epoch": 1.9630151398969273, "grad_norm": 4.538913726806641, "learning_rate": 7.610983123030749e-06, "loss": 0.2783, "step": 330240 }, { "epoch": 1.9630745819735957, "grad_norm": 4.5432448387146, "learning_rate": 7.610806166284095e-06, "loss": 0.2699, "step": 330250 }, { "epoch": 1.9631340240502642, "grad_norm": 5.196286678314209, "learning_rate": 7.610629205041321e-06, "loss": 0.2749, "step": 330260 }, { "epoch": 1.9631934661269326, "grad_norm": 5.997437477111816, "learning_rate": 7.6104522393027316e-06, "loss": 0.2695, "step": 330270 }, { "epoch": 1.963252908203601, "grad_norm": 5.629994869232178, "learning_rate": 7.610275269068632e-06, "loss": 0.2806, "step": 330280 }, { "epoch": 1.9633123502802694, "grad_norm": 4.227202892303467, "learning_rate": 7.6100982943393275e-06, "loss": 0.2335, "step": 330290 }, { "epoch": 1.9633717923569378, "grad_norm": 6.12222146987915, "learning_rate": 7.609921315115122e-06, "loss": 0.2986, "step": 330300 }, { "epoch": 1.9634312344336062, "grad_norm": 4.088881969451904, "learning_rate": 7.60974433139632e-06, "loss": 0.3123, "step": 330310 }, { "epoch": 1.9634906765102746, "grad_norm": 4.205399990081787, "learning_rate": 7.609567343183228e-06, "loss": 0.275, "step": 330320 }, { "epoch": 1.963550118586943, "grad_norm": 4.513370990753174, "learning_rate": 7.609390350476149e-06, "loss": 0.2684, "step": 330330 }, { "epoch": 1.9636095606636115, "grad_norm": 5.614542007446289, "learning_rate": 7.6092133532753894e-06, "loss": 0.3141, "step": 330340 }, { "epoch": 1.96366900274028, "grad_norm": 5.920223236083984, "learning_rate": 7.609036351581252e-06, "loss": 0.2924, "step": 330350 }, { "epoch": 1.963728444816948, "grad_norm": 5.281758785247803, "learning_rate": 7.608859345394044e-06, "loss": 0.2623, "step": 330360 }, { "epoch": 1.9637878868936165, "grad_norm": 4.150493621826172, "learning_rate": 7.608682334714066e-06, "loss": 0.2621, "step": 330370 }, { "epoch": 1.963847328970285, "grad_norm": 5.25558614730835, "learning_rate": 7.608505319541628e-06, "loss": 0.2774, "step": 330380 }, { "epoch": 1.9639067710469533, "grad_norm": 5.582224369049072, "learning_rate": 7.608328299877034e-06, "loss": 0.2647, "step": 330390 }, { "epoch": 1.9639662131236217, "grad_norm": 5.416298866271973, "learning_rate": 7.608151275720584e-06, "loss": 0.2671, "step": 330400 }, { "epoch": 1.96402565520029, "grad_norm": 5.354393482208252, "learning_rate": 7.607974247072589e-06, "loss": 0.3012, "step": 330410 }, { "epoch": 1.9640850972769583, "grad_norm": 5.539770126342773, "learning_rate": 7.60779721393335e-06, "loss": 0.2603, "step": 330420 }, { "epoch": 1.9641445393536268, "grad_norm": 4.840373516082764, "learning_rate": 7.6076201763031736e-06, "loss": 0.2535, "step": 330430 }, { "epoch": 1.9642039814302952, "grad_norm": 5.577813625335693, "learning_rate": 7.607443134182364e-06, "loss": 0.3046, "step": 330440 }, { "epoch": 1.9642634235069636, "grad_norm": 5.449052333831787, "learning_rate": 7.607266087571226e-06, "loss": 0.2818, "step": 330450 }, { "epoch": 1.964322865583632, "grad_norm": 5.132339000701904, "learning_rate": 7.607089036470064e-06, "loss": 0.294, "step": 330460 }, { "epoch": 1.9643823076603004, "grad_norm": 5.272554397583008, "learning_rate": 7.606911980879186e-06, "loss": 0.2605, "step": 330470 }, { "epoch": 1.9644417497369688, "grad_norm": 5.858198165893555, "learning_rate": 7.60673492079889e-06, "loss": 0.2857, "step": 330480 }, { "epoch": 1.9645011918136372, "grad_norm": 5.019320011138916, "learning_rate": 7.606557856229488e-06, "loss": 0.2474, "step": 330490 }, { "epoch": 1.9645606338903057, "grad_norm": 5.083520412445068, "learning_rate": 7.606380787171283e-06, "loss": 0.2911, "step": 330500 }, { "epoch": 1.964620075966974, "grad_norm": 4.844221591949463, "learning_rate": 7.6062037136245804e-06, "loss": 0.2614, "step": 330510 }, { "epoch": 1.9646795180436425, "grad_norm": 4.765994071960449, "learning_rate": 7.606026635589681e-06, "loss": 0.24, "step": 330520 }, { "epoch": 1.964738960120311, "grad_norm": 4.381624221801758, "learning_rate": 7.605849553066895e-06, "loss": 0.2128, "step": 330530 }, { "epoch": 1.964798402196979, "grad_norm": 4.574276924133301, "learning_rate": 7.6056724660565265e-06, "loss": 0.2728, "step": 330540 }, { "epoch": 1.9648578442736475, "grad_norm": 4.98674201965332, "learning_rate": 7.6054953745588755e-06, "loss": 0.2541, "step": 330550 }, { "epoch": 1.964917286350316, "grad_norm": 4.660770416259766, "learning_rate": 7.605318278574252e-06, "loss": 0.2879, "step": 330560 }, { "epoch": 1.9649767284269843, "grad_norm": 5.850782871246338, "learning_rate": 7.605141178102961e-06, "loss": 0.2801, "step": 330570 }, { "epoch": 1.9650361705036528, "grad_norm": 4.773675441741943, "learning_rate": 7.604964073145305e-06, "loss": 0.2721, "step": 330580 }, { "epoch": 1.965095612580321, "grad_norm": 4.268467426300049, "learning_rate": 7.604786963701588e-06, "loss": 0.2577, "step": 330590 }, { "epoch": 1.9651550546569894, "grad_norm": 6.83659029006958, "learning_rate": 7.60460984977212e-06, "loss": 0.2793, "step": 330600 }, { "epoch": 1.9652144967336578, "grad_norm": 4.68394660949707, "learning_rate": 7.604432731357202e-06, "loss": 0.2898, "step": 330610 }, { "epoch": 1.9652739388103262, "grad_norm": 4.27773904800415, "learning_rate": 7.604255608457139e-06, "loss": 0.2689, "step": 330620 }, { "epoch": 1.9653333808869946, "grad_norm": 3.879268169403076, "learning_rate": 7.604078481072239e-06, "loss": 0.2629, "step": 330630 }, { "epoch": 1.965392822963663, "grad_norm": 3.746507167816162, "learning_rate": 7.603901349202805e-06, "loss": 0.2521, "step": 330640 }, { "epoch": 1.9654522650403314, "grad_norm": 5.01356840133667, "learning_rate": 7.603724212849139e-06, "loss": 0.2966, "step": 330650 }, { "epoch": 1.9655117071169999, "grad_norm": 4.463867664337158, "learning_rate": 7.603547072011553e-06, "loss": 0.2475, "step": 330660 }, { "epoch": 1.9655711491936683, "grad_norm": 5.1911725997924805, "learning_rate": 7.603369926690347e-06, "loss": 0.2522, "step": 330670 }, { "epoch": 1.9656305912703367, "grad_norm": 4.30769157409668, "learning_rate": 7.603192776885828e-06, "loss": 0.282, "step": 330680 }, { "epoch": 1.965690033347005, "grad_norm": 5.166941165924072, "learning_rate": 7.6030156225983e-06, "loss": 0.2846, "step": 330690 }, { "epoch": 1.9657494754236735, "grad_norm": 4.950674057006836, "learning_rate": 7.602838463828068e-06, "loss": 0.2851, "step": 330700 }, { "epoch": 1.965808917500342, "grad_norm": 5.882453918457031, "learning_rate": 7.602661300575438e-06, "loss": 0.2918, "step": 330710 }, { "epoch": 1.9658683595770103, "grad_norm": 6.505142688751221, "learning_rate": 7.6024841328407125e-06, "loss": 0.2658, "step": 330720 }, { "epoch": 1.9659278016536785, "grad_norm": 6.002682209014893, "learning_rate": 7.602306960624201e-06, "loss": 0.2982, "step": 330730 }, { "epoch": 1.965987243730347, "grad_norm": 4.14794921875, "learning_rate": 7.602129783926209e-06, "loss": 0.2532, "step": 330740 }, { "epoch": 1.9660466858070154, "grad_norm": 5.672877788543701, "learning_rate": 7.601952602747035e-06, "loss": 0.2907, "step": 330750 }, { "epoch": 1.9661061278836838, "grad_norm": 4.410839080810547, "learning_rate": 7.601775417086989e-06, "loss": 0.2864, "step": 330760 }, { "epoch": 1.9661655699603522, "grad_norm": 3.8331124782562256, "learning_rate": 7.601598226946376e-06, "loss": 0.2744, "step": 330770 }, { "epoch": 1.9662250120370204, "grad_norm": 4.122811794281006, "learning_rate": 7.6014210323255e-06, "loss": 0.28, "step": 330780 }, { "epoch": 1.9662844541136888, "grad_norm": 4.251038074493408, "learning_rate": 7.601243833224667e-06, "loss": 0.279, "step": 330790 }, { "epoch": 1.9663438961903572, "grad_norm": 4.1347222328186035, "learning_rate": 7.601066629644183e-06, "loss": 0.3051, "step": 330800 }, { "epoch": 1.9664033382670256, "grad_norm": 6.212504863739014, "learning_rate": 7.60088942158435e-06, "loss": 0.2629, "step": 330810 }, { "epoch": 1.966462780343694, "grad_norm": 6.765577793121338, "learning_rate": 7.600712209045474e-06, "loss": 0.2585, "step": 330820 }, { "epoch": 1.9665222224203625, "grad_norm": 6.646942615509033, "learning_rate": 7.600534992027863e-06, "loss": 0.2876, "step": 330830 }, { "epoch": 1.9665816644970309, "grad_norm": 3.479207992553711, "learning_rate": 7.600357770531821e-06, "loss": 0.2582, "step": 330840 }, { "epoch": 1.9666411065736993, "grad_norm": 6.43574857711792, "learning_rate": 7.600180544557651e-06, "loss": 0.2847, "step": 330850 }, { "epoch": 1.9667005486503677, "grad_norm": 4.734439373016357, "learning_rate": 7.6000033141056615e-06, "loss": 0.2682, "step": 330860 }, { "epoch": 1.9667599907270361, "grad_norm": 5.392741680145264, "learning_rate": 7.599826079176156e-06, "loss": 0.2839, "step": 330870 }, { "epoch": 1.9668194328037045, "grad_norm": 4.99836540222168, "learning_rate": 7.599648839769438e-06, "loss": 0.2582, "step": 330880 }, { "epoch": 1.966878874880373, "grad_norm": 6.097676753997803, "learning_rate": 7.599471595885817e-06, "loss": 0.2726, "step": 330890 }, { "epoch": 1.9669383169570414, "grad_norm": 4.902099609375, "learning_rate": 7.599294347525594e-06, "loss": 0.291, "step": 330900 }, { "epoch": 1.9669977590337095, "grad_norm": 5.092325210571289, "learning_rate": 7.599117094689076e-06, "loss": 0.2691, "step": 330910 }, { "epoch": 1.967057201110378, "grad_norm": 5.344320774078369, "learning_rate": 7.598939837376568e-06, "loss": 0.2588, "step": 330920 }, { "epoch": 1.9671166431870464, "grad_norm": 3.7066383361816406, "learning_rate": 7.5987625755883765e-06, "loss": 0.2566, "step": 330930 }, { "epoch": 1.9671760852637148, "grad_norm": 5.632591247558594, "learning_rate": 7.598585309324806e-06, "loss": 0.2434, "step": 330940 }, { "epoch": 1.9672355273403832, "grad_norm": 3.767207384109497, "learning_rate": 7.59840803858616e-06, "loss": 0.2332, "step": 330950 }, { "epoch": 1.9672949694170514, "grad_norm": 5.60990571975708, "learning_rate": 7.598230763372747e-06, "loss": 0.2647, "step": 330960 }, { "epoch": 1.9673544114937198, "grad_norm": 5.052847385406494, "learning_rate": 7.598053483684869e-06, "loss": 0.2903, "step": 330970 }, { "epoch": 1.9674138535703882, "grad_norm": 5.061217308044434, "learning_rate": 7.597876199522833e-06, "loss": 0.2539, "step": 330980 }, { "epoch": 1.9674732956470566, "grad_norm": 6.441201686859131, "learning_rate": 7.597698910886946e-06, "loss": 0.283, "step": 330990 }, { "epoch": 1.967532737723725, "grad_norm": 5.705925941467285, "learning_rate": 7.5975216177775115e-06, "loss": 0.2721, "step": 331000 }, { "epoch": 1.9675921798003935, "grad_norm": 5.502346992492676, "learning_rate": 7.597344320194833e-06, "loss": 0.2569, "step": 331010 }, { "epoch": 1.9676516218770619, "grad_norm": 4.8658647537231445, "learning_rate": 7.597167018139219e-06, "loss": 0.2991, "step": 331020 }, { "epoch": 1.9677110639537303, "grad_norm": 4.640552997589111, "learning_rate": 7.5969897116109715e-06, "loss": 0.2828, "step": 331030 }, { "epoch": 1.9677705060303987, "grad_norm": 5.335054397583008, "learning_rate": 7.596812400610401e-06, "loss": 0.2827, "step": 331040 }, { "epoch": 1.9678299481070671, "grad_norm": 4.532369613647461, "learning_rate": 7.596635085137807e-06, "loss": 0.2746, "step": 331050 }, { "epoch": 1.9678893901837355, "grad_norm": 7.147353172302246, "learning_rate": 7.596457765193499e-06, "loss": 0.2822, "step": 331060 }, { "epoch": 1.967948832260404, "grad_norm": 4.4830546379089355, "learning_rate": 7.596280440777781e-06, "loss": 0.2892, "step": 331070 }, { "epoch": 1.9680082743370724, "grad_norm": 4.500885486602783, "learning_rate": 7.596103111890957e-06, "loss": 0.2926, "step": 331080 }, { "epoch": 1.9680677164137408, "grad_norm": 5.682489395141602, "learning_rate": 7.595925778533335e-06, "loss": 0.2843, "step": 331090 }, { "epoch": 1.968127158490409, "grad_norm": 3.828510284423828, "learning_rate": 7.59574844070522e-06, "loss": 0.2433, "step": 331100 }, { "epoch": 1.9681866005670774, "grad_norm": 3.8462467193603516, "learning_rate": 7.5955710984069135e-06, "loss": 0.2567, "step": 331110 }, { "epoch": 1.9682460426437458, "grad_norm": 4.677798271179199, "learning_rate": 7.5953937516387256e-06, "loss": 0.3145, "step": 331120 }, { "epoch": 1.9683054847204142, "grad_norm": 5.525860786437988, "learning_rate": 7.59521640040096e-06, "loss": 0.2447, "step": 331130 }, { "epoch": 1.9683649267970826, "grad_norm": 4.043126583099365, "learning_rate": 7.595039044693921e-06, "loss": 0.2663, "step": 331140 }, { "epoch": 1.9684243688737508, "grad_norm": 4.568477153778076, "learning_rate": 7.594861684517916e-06, "loss": 0.285, "step": 331150 }, { "epoch": 1.9684838109504192, "grad_norm": 5.3546319007873535, "learning_rate": 7.59468431987325e-06, "loss": 0.3002, "step": 331160 }, { "epoch": 1.9685432530270877, "grad_norm": 4.469583034515381, "learning_rate": 7.594506950760227e-06, "loss": 0.2726, "step": 331170 }, { "epoch": 1.968602695103756, "grad_norm": 3.9886693954467773, "learning_rate": 7.594329577179154e-06, "loss": 0.2795, "step": 331180 }, { "epoch": 1.9686621371804245, "grad_norm": 3.739206314086914, "learning_rate": 7.594152199130337e-06, "loss": 0.2727, "step": 331190 }, { "epoch": 1.968721579257093, "grad_norm": 5.4571146965026855, "learning_rate": 7.593974816614078e-06, "loss": 0.3017, "step": 331200 }, { "epoch": 1.9687810213337613, "grad_norm": 5.312275409698486, "learning_rate": 7.593797429630687e-06, "loss": 0.2904, "step": 331210 }, { "epoch": 1.9688404634104297, "grad_norm": 4.671890735626221, "learning_rate": 7.593620038180467e-06, "loss": 0.269, "step": 331220 }, { "epoch": 1.9688999054870981, "grad_norm": 4.978907585144043, "learning_rate": 7.593442642263724e-06, "loss": 0.2729, "step": 331230 }, { "epoch": 1.9689593475637666, "grad_norm": 4.358346462249756, "learning_rate": 7.593265241880762e-06, "loss": 0.2908, "step": 331240 }, { "epoch": 1.969018789640435, "grad_norm": 4.26575231552124, "learning_rate": 7.593087837031887e-06, "loss": 0.2835, "step": 331250 }, { "epoch": 1.9690782317171034, "grad_norm": 4.628771781921387, "learning_rate": 7.5929104277174085e-06, "loss": 0.2592, "step": 331260 }, { "epoch": 1.9691376737937718, "grad_norm": 4.11643123626709, "learning_rate": 7.592733013937625e-06, "loss": 0.2776, "step": 331270 }, { "epoch": 1.96919711587044, "grad_norm": 5.494586944580078, "learning_rate": 7.59255559569285e-06, "loss": 0.3045, "step": 331280 }, { "epoch": 1.9692565579471084, "grad_norm": 6.911808490753174, "learning_rate": 7.592378172983384e-06, "loss": 0.2925, "step": 331290 }, { "epoch": 1.9693160000237768, "grad_norm": 3.7463157176971436, "learning_rate": 7.59220074580953e-06, "loss": 0.2945, "step": 331300 }, { "epoch": 1.9693754421004452, "grad_norm": 5.022502899169922, "learning_rate": 7.592023314171601e-06, "loss": 0.2628, "step": 331310 }, { "epoch": 1.9694348841771137, "grad_norm": 4.743075847625732, "learning_rate": 7.591845878069897e-06, "loss": 0.2773, "step": 331320 }, { "epoch": 1.9694943262537818, "grad_norm": 4.004304885864258, "learning_rate": 7.591668437504724e-06, "loss": 0.2585, "step": 331330 }, { "epoch": 1.9695537683304503, "grad_norm": 4.270948886871338, "learning_rate": 7.591490992476391e-06, "loss": 0.2932, "step": 331340 }, { "epoch": 1.9696132104071187, "grad_norm": 5.490471363067627, "learning_rate": 7.591313542985202e-06, "loss": 0.2734, "step": 331350 }, { "epoch": 1.969672652483787, "grad_norm": 4.855360507965088, "learning_rate": 7.591136089031459e-06, "loss": 0.2635, "step": 331360 }, { "epoch": 1.9697320945604555, "grad_norm": 6.832025051116943, "learning_rate": 7.59095863061547e-06, "loss": 0.2836, "step": 331370 }, { "epoch": 1.969791536637124, "grad_norm": 5.994612693786621, "learning_rate": 7.590781167737544e-06, "loss": 0.2679, "step": 331380 }, { "epoch": 1.9698509787137923, "grad_norm": 6.036351680755615, "learning_rate": 7.590603700397983e-06, "loss": 0.2792, "step": 331390 }, { "epoch": 1.9699104207904607, "grad_norm": 5.659313201904297, "learning_rate": 7.590426228597092e-06, "loss": 0.2694, "step": 331400 }, { "epoch": 1.9699698628671292, "grad_norm": 4.960477352142334, "learning_rate": 7.590248752335179e-06, "loss": 0.2672, "step": 331410 }, { "epoch": 1.9700293049437976, "grad_norm": 5.747413158416748, "learning_rate": 7.590071271612549e-06, "loss": 0.2916, "step": 331420 }, { "epoch": 1.970088747020466, "grad_norm": 5.263427734375, "learning_rate": 7.589893786429505e-06, "loss": 0.2852, "step": 331430 }, { "epoch": 1.9701481890971344, "grad_norm": 5.430648326873779, "learning_rate": 7.589716296786358e-06, "loss": 0.32, "step": 331440 }, { "epoch": 1.9702076311738028, "grad_norm": 4.51524019241333, "learning_rate": 7.58953880268341e-06, "loss": 0.2831, "step": 331450 }, { "epoch": 1.9702670732504712, "grad_norm": 3.976020097732544, "learning_rate": 7.589361304120965e-06, "loss": 0.2709, "step": 331460 }, { "epoch": 1.9703265153271394, "grad_norm": 5.644541263580322, "learning_rate": 7.589183801099332e-06, "loss": 0.2446, "step": 331470 }, { "epoch": 1.9703859574038078, "grad_norm": 4.163245677947998, "learning_rate": 7.589006293618815e-06, "loss": 0.2362, "step": 331480 }, { "epoch": 1.9704453994804763, "grad_norm": 5.649964809417725, "learning_rate": 7.588828781679721e-06, "loss": 0.2772, "step": 331490 }, { "epoch": 1.9705048415571447, "grad_norm": 4.781136512756348, "learning_rate": 7.588651265282354e-06, "loss": 0.2735, "step": 331500 }, { "epoch": 1.970564283633813, "grad_norm": 5.36604642868042, "learning_rate": 7.588473744427023e-06, "loss": 0.3322, "step": 331510 }, { "epoch": 1.9706237257104813, "grad_norm": 4.244064807891846, "learning_rate": 7.588296219114028e-06, "loss": 0.2833, "step": 331520 }, { "epoch": 1.9706831677871497, "grad_norm": 5.281105041503906, "learning_rate": 7.58811868934368e-06, "loss": 0.2642, "step": 331530 }, { "epoch": 1.970742609863818, "grad_norm": 4.1729936599731445, "learning_rate": 7.587941155116283e-06, "loss": 0.2502, "step": 331540 }, { "epoch": 1.9708020519404865, "grad_norm": 6.616249084472656, "learning_rate": 7.587763616432143e-06, "loss": 0.2857, "step": 331550 }, { "epoch": 1.970861494017155, "grad_norm": 5.253407955169678, "learning_rate": 7.587586073291564e-06, "loss": 0.2725, "step": 331560 }, { "epoch": 1.9709209360938234, "grad_norm": 5.485156536102295, "learning_rate": 7.587408525694855e-06, "loss": 0.2541, "step": 331570 }, { "epoch": 1.9709803781704918, "grad_norm": 4.4641594886779785, "learning_rate": 7.5872309736423165e-06, "loss": 0.3001, "step": 331580 }, { "epoch": 1.9710398202471602, "grad_norm": 6.032472610473633, "learning_rate": 7.58705341713426e-06, "loss": 0.2559, "step": 331590 }, { "epoch": 1.9710992623238286, "grad_norm": 4.590671539306641, "learning_rate": 7.586875856170988e-06, "loss": 0.2551, "step": 331600 }, { "epoch": 1.971158704400497, "grad_norm": 5.684396266937256, "learning_rate": 7.586698290752807e-06, "loss": 0.2766, "step": 331610 }, { "epoch": 1.9712181464771654, "grad_norm": 3.5494163036346436, "learning_rate": 7.586520720880024e-06, "loss": 0.2492, "step": 331620 }, { "epoch": 1.9712775885538338, "grad_norm": 5.107802867889404, "learning_rate": 7.586343146552942e-06, "loss": 0.2739, "step": 331630 }, { "epoch": 1.9713370306305023, "grad_norm": 4.958431720733643, "learning_rate": 7.58616556777187e-06, "loss": 0.262, "step": 331640 }, { "epoch": 1.9713964727071704, "grad_norm": 4.612081050872803, "learning_rate": 7.585987984537113e-06, "loss": 0.2731, "step": 331650 }, { "epoch": 1.9714559147838389, "grad_norm": 5.996517658233643, "learning_rate": 7.585810396848974e-06, "loss": 0.2744, "step": 331660 }, { "epoch": 1.9715153568605073, "grad_norm": 5.685884952545166, "learning_rate": 7.585632804707762e-06, "loss": 0.2906, "step": 331670 }, { "epoch": 1.9715747989371757, "grad_norm": 5.626890659332275, "learning_rate": 7.5854552081137826e-06, "loss": 0.2637, "step": 331680 }, { "epoch": 1.971634241013844, "grad_norm": 4.052305698394775, "learning_rate": 7.585277607067338e-06, "loss": 0.2932, "step": 331690 }, { "epoch": 1.9716936830905123, "grad_norm": 3.3278322219848633, "learning_rate": 7.585100001568739e-06, "loss": 0.2729, "step": 331700 }, { "epoch": 1.9717531251671807, "grad_norm": 4.670992374420166, "learning_rate": 7.5849223916182904e-06, "loss": 0.2601, "step": 331710 }, { "epoch": 1.9718125672438491, "grad_norm": 6.0043840408325195, "learning_rate": 7.5847447772162955e-06, "loss": 0.2946, "step": 331720 }, { "epoch": 1.9718720093205175, "grad_norm": 4.748815059661865, "learning_rate": 7.584567158363061e-06, "loss": 0.2758, "step": 331730 }, { "epoch": 1.971931451397186, "grad_norm": 4.834239959716797, "learning_rate": 7.584389535058895e-06, "loss": 0.2558, "step": 331740 }, { "epoch": 1.9719908934738544, "grad_norm": 4.655974864959717, "learning_rate": 7.584211907304102e-06, "loss": 0.2831, "step": 331750 }, { "epoch": 1.9720503355505228, "grad_norm": 5.774151802062988, "learning_rate": 7.584034275098986e-06, "loss": 0.2963, "step": 331760 }, { "epoch": 1.9721097776271912, "grad_norm": 3.7629940509796143, "learning_rate": 7.583856638443856e-06, "loss": 0.2665, "step": 331770 }, { "epoch": 1.9721692197038596, "grad_norm": 3.5539822578430176, "learning_rate": 7.583678997339017e-06, "loss": 0.2704, "step": 331780 }, { "epoch": 1.972228661780528, "grad_norm": 5.266481876373291, "learning_rate": 7.5835013517847725e-06, "loss": 0.2593, "step": 331790 }, { "epoch": 1.9722881038571964, "grad_norm": 4.100068092346191, "learning_rate": 7.583323701781431e-06, "loss": 0.2717, "step": 331800 }, { "epoch": 1.9723475459338649, "grad_norm": 4.287452220916748, "learning_rate": 7.5831460473292994e-06, "loss": 0.2774, "step": 331810 }, { "epoch": 1.9724069880105333, "grad_norm": 4.355752944946289, "learning_rate": 7.58296838842868e-06, "loss": 0.3065, "step": 331820 }, { "epoch": 1.9724664300872017, "grad_norm": 5.198832988739014, "learning_rate": 7.582790725079883e-06, "loss": 0.2539, "step": 331830 }, { "epoch": 1.9725258721638699, "grad_norm": 5.338027000427246, "learning_rate": 7.582613057283212e-06, "loss": 0.2784, "step": 331840 }, { "epoch": 1.9725853142405383, "grad_norm": 4.11517858505249, "learning_rate": 7.582435385038971e-06, "loss": 0.2661, "step": 331850 }, { "epoch": 1.9726447563172067, "grad_norm": 5.039717674255371, "learning_rate": 7.58225770834747e-06, "loss": 0.2523, "step": 331860 }, { "epoch": 1.9727041983938751, "grad_norm": 5.013641357421875, "learning_rate": 7.582080027209013e-06, "loss": 0.2555, "step": 331870 }, { "epoch": 1.9727636404705435, "grad_norm": 6.349879264831543, "learning_rate": 7.581902341623906e-06, "loss": 0.2804, "step": 331880 }, { "epoch": 1.9728230825472117, "grad_norm": 6.031276702880859, "learning_rate": 7.581724651592455e-06, "loss": 0.2785, "step": 331890 }, { "epoch": 1.9728825246238801, "grad_norm": 4.506718635559082, "learning_rate": 7.581546957114965e-06, "loss": 0.2659, "step": 331900 }, { "epoch": 1.9729419667005486, "grad_norm": 3.8571152687072754, "learning_rate": 7.5813692581917446e-06, "loss": 0.284, "step": 331910 }, { "epoch": 1.973001408777217, "grad_norm": 4.065960884094238, "learning_rate": 7.5811915548230975e-06, "loss": 0.27, "step": 331920 }, { "epoch": 1.9730608508538854, "grad_norm": 3.954702854156494, "learning_rate": 7.581013847009331e-06, "loss": 0.2523, "step": 331930 }, { "epoch": 1.9731202929305538, "grad_norm": 3.8056139945983887, "learning_rate": 7.580836134750751e-06, "loss": 0.2722, "step": 331940 }, { "epoch": 1.9731797350072222, "grad_norm": 4.469030380249023, "learning_rate": 7.5806584180476615e-06, "loss": 0.2544, "step": 331950 }, { "epoch": 1.9732391770838906, "grad_norm": 4.847546100616455, "learning_rate": 7.580480696900372e-06, "loss": 0.2847, "step": 331960 }, { "epoch": 1.973298619160559, "grad_norm": 3.905444383621216, "learning_rate": 7.580302971309187e-06, "loss": 0.2655, "step": 331970 }, { "epoch": 1.9733580612372275, "grad_norm": 4.317485332489014, "learning_rate": 7.580125241274412e-06, "loss": 0.2866, "step": 331980 }, { "epoch": 1.9734175033138959, "grad_norm": 5.91923189163208, "learning_rate": 7.579947506796353e-06, "loss": 0.2688, "step": 331990 }, { "epoch": 1.9734769453905643, "grad_norm": 4.761724948883057, "learning_rate": 7.579769767875318e-06, "loss": 0.273, "step": 332000 }, { "epoch": 1.9735363874672327, "grad_norm": 4.542019367218018, "learning_rate": 7.579592024511608e-06, "loss": 0.2707, "step": 332010 }, { "epoch": 1.973595829543901, "grad_norm": 5.86995267868042, "learning_rate": 7.579414276705536e-06, "loss": 0.285, "step": 332020 }, { "epoch": 1.9736552716205693, "grad_norm": 7.18943977355957, "learning_rate": 7.579236524457405e-06, "loss": 0.3081, "step": 332030 }, { "epoch": 1.9737147136972377, "grad_norm": 5.099728584289551, "learning_rate": 7.5790587677675194e-06, "loss": 0.2621, "step": 332040 }, { "epoch": 1.9737741557739061, "grad_norm": 3.1505331993103027, "learning_rate": 7.578881006636187e-06, "loss": 0.2657, "step": 332050 }, { "epoch": 1.9738335978505746, "grad_norm": 4.053557395935059, "learning_rate": 7.578703241063715e-06, "loss": 0.256, "step": 332060 }, { "epoch": 1.9738930399272427, "grad_norm": 3.9741148948669434, "learning_rate": 7.578525471050409e-06, "loss": 0.2892, "step": 332070 }, { "epoch": 1.9739524820039112, "grad_norm": 7.5793561935424805, "learning_rate": 7.5783476965965705e-06, "loss": 0.2805, "step": 332080 }, { "epoch": 1.9740119240805796, "grad_norm": 4.632083415985107, "learning_rate": 7.578169917702514e-06, "loss": 0.249, "step": 332090 }, { "epoch": 1.974071366157248, "grad_norm": 5.837652206420898, "learning_rate": 7.5779921343685396e-06, "loss": 0.3108, "step": 332100 }, { "epoch": 1.9741308082339164, "grad_norm": 4.025376319885254, "learning_rate": 7.577814346594954e-06, "loss": 0.2787, "step": 332110 }, { "epoch": 1.9741902503105848, "grad_norm": 6.174186706542969, "learning_rate": 7.577636554382066e-06, "loss": 0.2825, "step": 332120 }, { "epoch": 1.9742496923872532, "grad_norm": 4.315295219421387, "learning_rate": 7.57745875773018e-06, "loss": 0.3185, "step": 332130 }, { "epoch": 1.9743091344639216, "grad_norm": 4.081666469573975, "learning_rate": 7.577280956639603e-06, "loss": 0.2904, "step": 332140 }, { "epoch": 1.97436857654059, "grad_norm": 5.748569965362549, "learning_rate": 7.5771031511106385e-06, "loss": 0.266, "step": 332150 }, { "epoch": 1.9744280186172585, "grad_norm": 4.572793483734131, "learning_rate": 7.576925341143597e-06, "loss": 0.2827, "step": 332160 }, { "epoch": 1.9744874606939269, "grad_norm": 5.0921454429626465, "learning_rate": 7.576747526738783e-06, "loss": 0.3005, "step": 332170 }, { "epoch": 1.9745469027705953, "grad_norm": 4.851970195770264, "learning_rate": 7.5765697078965004e-06, "loss": 0.266, "step": 332180 }, { "epoch": 1.9746063448472637, "grad_norm": 4.944284915924072, "learning_rate": 7.576391884617058e-06, "loss": 0.2628, "step": 332190 }, { "epoch": 1.9746657869239321, "grad_norm": 4.088388442993164, "learning_rate": 7.5762140569007625e-06, "loss": 0.2417, "step": 332200 }, { "epoch": 1.9747252290006003, "grad_norm": 5.281171798706055, "learning_rate": 7.576036224747918e-06, "loss": 0.3165, "step": 332210 }, { "epoch": 1.9747846710772687, "grad_norm": 5.560577392578125, "learning_rate": 7.575858388158832e-06, "loss": 0.2878, "step": 332220 }, { "epoch": 1.9748441131539372, "grad_norm": 4.8595194816589355, "learning_rate": 7.57568054713381e-06, "loss": 0.2631, "step": 332230 }, { "epoch": 1.9749035552306056, "grad_norm": 4.9790802001953125, "learning_rate": 7.575502701673158e-06, "loss": 0.2781, "step": 332240 }, { "epoch": 1.974962997307274, "grad_norm": 6.119300365447998, "learning_rate": 7.575324851777185e-06, "loss": 0.2639, "step": 332250 }, { "epoch": 1.9750224393839422, "grad_norm": 4.54070520401001, "learning_rate": 7.575146997446195e-06, "loss": 0.2873, "step": 332260 }, { "epoch": 1.9750818814606106, "grad_norm": 6.398759365081787, "learning_rate": 7.574969138680494e-06, "loss": 0.3088, "step": 332270 }, { "epoch": 1.975141323537279, "grad_norm": 4.221205711364746, "learning_rate": 7.5747912754803885e-06, "loss": 0.2653, "step": 332280 }, { "epoch": 1.9752007656139474, "grad_norm": 4.740989685058594, "learning_rate": 7.574613407846186e-06, "loss": 0.2497, "step": 332290 }, { "epoch": 1.9752602076906158, "grad_norm": 4.016137599945068, "learning_rate": 7.5744355357781926e-06, "loss": 0.2713, "step": 332300 }, { "epoch": 1.9753196497672842, "grad_norm": 4.55966329574585, "learning_rate": 7.574257659276712e-06, "loss": 0.2946, "step": 332310 }, { "epoch": 1.9753790918439527, "grad_norm": 6.207655429840088, "learning_rate": 7.574079778342054e-06, "loss": 0.2769, "step": 332320 }, { "epoch": 1.975438533920621, "grad_norm": 6.9308977127075195, "learning_rate": 7.573901892974524e-06, "loss": 0.2539, "step": 332330 }, { "epoch": 1.9754979759972895, "grad_norm": 4.835822105407715, "learning_rate": 7.573724003174426e-06, "loss": 0.2898, "step": 332340 }, { "epoch": 1.975557418073958, "grad_norm": 5.335979461669922, "learning_rate": 7.57354610894207e-06, "loss": 0.2737, "step": 332350 }, { "epoch": 1.9756168601506263, "grad_norm": 5.043951988220215, "learning_rate": 7.57336821027776e-06, "loss": 0.2478, "step": 332360 }, { "epoch": 1.9756763022272947, "grad_norm": 4.736015796661377, "learning_rate": 7.573190307181802e-06, "loss": 0.2803, "step": 332370 }, { "epoch": 1.9757357443039631, "grad_norm": 5.3919854164123535, "learning_rate": 7.573012399654503e-06, "loss": 0.2498, "step": 332380 }, { "epoch": 1.9757951863806313, "grad_norm": 4.815095901489258, "learning_rate": 7.572834487696172e-06, "loss": 0.2743, "step": 332390 }, { "epoch": 1.9758546284572998, "grad_norm": 4.56315803527832, "learning_rate": 7.572656571307111e-06, "loss": 0.2989, "step": 332400 }, { "epoch": 1.9759140705339682, "grad_norm": 3.55871319770813, "learning_rate": 7.5724786504876294e-06, "loss": 0.2567, "step": 332410 }, { "epoch": 1.9759735126106366, "grad_norm": 5.222744464874268, "learning_rate": 7.572300725238032e-06, "loss": 0.2782, "step": 332420 }, { "epoch": 1.976032954687305, "grad_norm": 4.439554691314697, "learning_rate": 7.572122795558626e-06, "loss": 0.3004, "step": 332430 }, { "epoch": 1.9760923967639732, "grad_norm": 6.1558756828308105, "learning_rate": 7.571944861449718e-06, "loss": 0.2967, "step": 332440 }, { "epoch": 1.9761518388406416, "grad_norm": 5.246096611022949, "learning_rate": 7.571766922911614e-06, "loss": 0.2743, "step": 332450 }, { "epoch": 1.97621128091731, "grad_norm": 5.141890525817871, "learning_rate": 7.571588979944619e-06, "loss": 0.3137, "step": 332460 }, { "epoch": 1.9762707229939784, "grad_norm": 5.741733074188232, "learning_rate": 7.571411032549042e-06, "loss": 0.3145, "step": 332470 }, { "epoch": 1.9763301650706468, "grad_norm": 3.684786319732666, "learning_rate": 7.571233080725189e-06, "loss": 0.2719, "step": 332480 }, { "epoch": 1.9763896071473153, "grad_norm": 5.777443885803223, "learning_rate": 7.571055124473366e-06, "loss": 0.2747, "step": 332490 }, { "epoch": 1.9764490492239837, "grad_norm": 5.971649169921875, "learning_rate": 7.570877163793878e-06, "loss": 0.2871, "step": 332500 }, { "epoch": 1.976508491300652, "grad_norm": 6.711495876312256, "learning_rate": 7.5706991986870336e-06, "loss": 0.2961, "step": 332510 }, { "epoch": 1.9765679333773205, "grad_norm": 4.719778060913086, "learning_rate": 7.570521229153138e-06, "loss": 0.2991, "step": 332520 }, { "epoch": 1.976627375453989, "grad_norm": 4.756906986236572, "learning_rate": 7.5703432551924985e-06, "loss": 0.2575, "step": 332530 }, { "epoch": 1.9766868175306573, "grad_norm": 3.178243398666382, "learning_rate": 7.570165276805421e-06, "loss": 0.2647, "step": 332540 }, { "epoch": 1.9767462596073258, "grad_norm": 4.9372758865356445, "learning_rate": 7.5699872939922135e-06, "loss": 0.2706, "step": 332550 }, { "epoch": 1.9768057016839942, "grad_norm": 4.106630802154541, "learning_rate": 7.5698093067531804e-06, "loss": 0.2763, "step": 332560 }, { "epoch": 1.9768651437606626, "grad_norm": 3.7829911708831787, "learning_rate": 7.569631315088628e-06, "loss": 0.268, "step": 332570 }, { "epoch": 1.9769245858373308, "grad_norm": 4.647604465484619, "learning_rate": 7.569453318998865e-06, "loss": 0.2824, "step": 332580 }, { "epoch": 1.9769840279139992, "grad_norm": 3.593653440475464, "learning_rate": 7.569275318484197e-06, "loss": 0.2175, "step": 332590 }, { "epoch": 1.9770434699906676, "grad_norm": 5.128565788269043, "learning_rate": 7.5690973135449285e-06, "loss": 0.2947, "step": 332600 }, { "epoch": 1.977102912067336, "grad_norm": 4.884007453918457, "learning_rate": 7.56891930418137e-06, "loss": 0.31, "step": 332610 }, { "epoch": 1.9771623541440044, "grad_norm": 5.15226936340332, "learning_rate": 7.568741290393826e-06, "loss": 0.3119, "step": 332620 }, { "epoch": 1.9772217962206726, "grad_norm": 4.92854642868042, "learning_rate": 7.5685632721826e-06, "loss": 0.2789, "step": 332630 }, { "epoch": 1.977281238297341, "grad_norm": 5.635497570037842, "learning_rate": 7.5683852495480045e-06, "loss": 0.2526, "step": 332640 }, { "epoch": 1.9773406803740095, "grad_norm": 4.138251304626465, "learning_rate": 7.568207222490344e-06, "loss": 0.2805, "step": 332650 }, { "epoch": 1.9774001224506779, "grad_norm": 5.152973175048828, "learning_rate": 7.568029191009921e-06, "loss": 0.2831, "step": 332660 }, { "epoch": 1.9774595645273463, "grad_norm": 5.895722389221191, "learning_rate": 7.567851155107048e-06, "loss": 0.2678, "step": 332670 }, { "epoch": 1.9775190066040147, "grad_norm": 3.98557448387146, "learning_rate": 7.567673114782027e-06, "loss": 0.2779, "step": 332680 }, { "epoch": 1.977578448680683, "grad_norm": 4.323043346405029, "learning_rate": 7.567495070035168e-06, "loss": 0.2543, "step": 332690 }, { "epoch": 1.9776378907573515, "grad_norm": 6.014801025390625, "learning_rate": 7.567317020866775e-06, "loss": 0.2667, "step": 332700 }, { "epoch": 1.97769733283402, "grad_norm": 4.4680562019348145, "learning_rate": 7.567138967277156e-06, "loss": 0.2841, "step": 332710 }, { "epoch": 1.9777567749106884, "grad_norm": 3.397224187850952, "learning_rate": 7.566960909266618e-06, "loss": 0.2621, "step": 332720 }, { "epoch": 1.9778162169873568, "grad_norm": 5.951827049255371, "learning_rate": 7.566782846835467e-06, "loss": 0.3001, "step": 332730 }, { "epoch": 1.9778756590640252, "grad_norm": 5.865478038787842, "learning_rate": 7.566604779984009e-06, "loss": 0.2851, "step": 332740 }, { "epoch": 1.9779351011406936, "grad_norm": 3.9017155170440674, "learning_rate": 7.566426708712553e-06, "loss": 0.2625, "step": 332750 }, { "epoch": 1.9779945432173618, "grad_norm": 5.472103595733643, "learning_rate": 7.566248633021401e-06, "loss": 0.2722, "step": 332760 }, { "epoch": 1.9780539852940302, "grad_norm": 5.236395359039307, "learning_rate": 7.566070552910865e-06, "loss": 0.2468, "step": 332770 }, { "epoch": 1.9781134273706986, "grad_norm": 5.55214262008667, "learning_rate": 7.56589246838125e-06, "loss": 0.2609, "step": 332780 }, { "epoch": 1.978172869447367, "grad_norm": 6.219236850738525, "learning_rate": 7.56571437943286e-06, "loss": 0.2467, "step": 332790 }, { "epoch": 1.9782323115240354, "grad_norm": 4.116722583770752, "learning_rate": 7.565536286066003e-06, "loss": 0.2711, "step": 332800 }, { "epoch": 1.9782917536007036, "grad_norm": 5.923603057861328, "learning_rate": 7.565358188280989e-06, "loss": 0.2663, "step": 332810 }, { "epoch": 1.978351195677372, "grad_norm": 6.6529340744018555, "learning_rate": 7.565180086078121e-06, "loss": 0.283, "step": 332820 }, { "epoch": 1.9784106377540405, "grad_norm": 4.886435031890869, "learning_rate": 7.565001979457705e-06, "loss": 0.3133, "step": 332830 }, { "epoch": 1.9784700798307089, "grad_norm": 4.505239963531494, "learning_rate": 7.564823868420053e-06, "loss": 0.2482, "step": 332840 }, { "epoch": 1.9785295219073773, "grad_norm": 4.0840744972229, "learning_rate": 7.564645752965467e-06, "loss": 0.2766, "step": 332850 }, { "epoch": 1.9785889639840457, "grad_norm": 4.482983112335205, "learning_rate": 7.5644676330942536e-06, "loss": 0.2653, "step": 332860 }, { "epoch": 1.9786484060607141, "grad_norm": 3.345836877822876, "learning_rate": 7.564289508806721e-06, "loss": 0.2805, "step": 332870 }, { "epoch": 1.9787078481373825, "grad_norm": 4.107678413391113, "learning_rate": 7.564111380103178e-06, "loss": 0.2678, "step": 332880 }, { "epoch": 1.978767290214051, "grad_norm": 5.586802959442139, "learning_rate": 7.563933246983928e-06, "loss": 0.2779, "step": 332890 }, { "epoch": 1.9788267322907194, "grad_norm": 5.340350151062012, "learning_rate": 7.563755109449278e-06, "loss": 0.2705, "step": 332900 }, { "epoch": 1.9788861743673878, "grad_norm": 5.0466718673706055, "learning_rate": 7.5635769674995376e-06, "loss": 0.2497, "step": 332910 }, { "epoch": 1.9789456164440562, "grad_norm": 5.907676696777344, "learning_rate": 7.56339882113501e-06, "loss": 0.2651, "step": 332920 }, { "epoch": 1.9790050585207246, "grad_norm": 5.427879333496094, "learning_rate": 7.563220670356005e-06, "loss": 0.2831, "step": 332930 }, { "epoch": 1.979064500597393, "grad_norm": 4.823727607727051, "learning_rate": 7.563042515162828e-06, "loss": 0.2413, "step": 332940 }, { "epoch": 1.9791239426740612, "grad_norm": 4.425714492797852, "learning_rate": 7.562864355555787e-06, "loss": 0.2774, "step": 332950 }, { "epoch": 1.9791833847507296, "grad_norm": 4.133189678192139, "learning_rate": 7.562686191535187e-06, "loss": 0.2839, "step": 332960 }, { "epoch": 1.979242826827398, "grad_norm": 3.5907530784606934, "learning_rate": 7.562508023101335e-06, "loss": 0.2624, "step": 332970 }, { "epoch": 1.9793022689040665, "grad_norm": 5.418914794921875, "learning_rate": 7.562329850254539e-06, "loss": 0.2889, "step": 332980 }, { "epoch": 1.9793617109807347, "grad_norm": 4.196321964263916, "learning_rate": 7.562151672995104e-06, "loss": 0.281, "step": 332990 }, { "epoch": 1.979421153057403, "grad_norm": 5.945650100708008, "learning_rate": 7.56197349132334e-06, "loss": 0.2784, "step": 333000 }, { "epoch": 1.9794805951340715, "grad_norm": 5.503503799438477, "learning_rate": 7.56179530523955e-06, "loss": 0.2676, "step": 333010 }, { "epoch": 1.97954003721074, "grad_norm": 3.7453370094299316, "learning_rate": 7.5616171147440445e-06, "loss": 0.2407, "step": 333020 }, { "epoch": 1.9795994792874083, "grad_norm": 3.900693655014038, "learning_rate": 7.561438919837127e-06, "loss": 0.2576, "step": 333030 }, { "epoch": 1.9796589213640767, "grad_norm": 5.253384113311768, "learning_rate": 7.561260720519108e-06, "loss": 0.2889, "step": 333040 }, { "epoch": 1.9797183634407451, "grad_norm": 6.606530666351318, "learning_rate": 7.561082516790293e-06, "loss": 0.2751, "step": 333050 }, { "epoch": 1.9797778055174136, "grad_norm": 4.234252452850342, "learning_rate": 7.5609043086509845e-06, "loss": 0.2811, "step": 333060 }, { "epoch": 1.979837247594082, "grad_norm": 4.047638416290283, "learning_rate": 7.5607260961014975e-06, "loss": 0.275, "step": 333070 }, { "epoch": 1.9798966896707504, "grad_norm": 6.242064476013184, "learning_rate": 7.5605478791421326e-06, "loss": 0.2834, "step": 333080 }, { "epoch": 1.9799561317474188, "grad_norm": 7.469267845153809, "learning_rate": 7.560369657773199e-06, "loss": 0.2594, "step": 333090 }, { "epoch": 1.9800155738240872, "grad_norm": 5.198741436004639, "learning_rate": 7.560191431995003e-06, "loss": 0.2713, "step": 333100 }, { "epoch": 1.9800750159007556, "grad_norm": 5.357650279998779, "learning_rate": 7.560013201807852e-06, "loss": 0.2793, "step": 333110 }, { "epoch": 1.980134457977424, "grad_norm": 4.252991199493408, "learning_rate": 7.559834967212052e-06, "loss": 0.31, "step": 333120 }, { "epoch": 1.9801939000540922, "grad_norm": 4.651091575622559, "learning_rate": 7.559656728207911e-06, "loss": 0.2487, "step": 333130 }, { "epoch": 1.9802533421307607, "grad_norm": 5.142212867736816, "learning_rate": 7.559478484795737e-06, "loss": 0.2622, "step": 333140 }, { "epoch": 1.980312784207429, "grad_norm": 4.722635746002197, "learning_rate": 7.559300236975835e-06, "loss": 0.2673, "step": 333150 }, { "epoch": 1.9803722262840975, "grad_norm": 6.400033950805664, "learning_rate": 7.559121984748513e-06, "loss": 0.2821, "step": 333160 }, { "epoch": 1.980431668360766, "grad_norm": 6.488284111022949, "learning_rate": 7.5589437281140775e-06, "loss": 0.269, "step": 333170 }, { "epoch": 1.980491110437434, "grad_norm": 4.582862854003906, "learning_rate": 7.558765467072835e-06, "loss": 0.2543, "step": 333180 }, { "epoch": 1.9805505525141025, "grad_norm": 4.57898473739624, "learning_rate": 7.558587201625094e-06, "loss": 0.2498, "step": 333190 }, { "epoch": 1.980609994590771, "grad_norm": 4.1037983894348145, "learning_rate": 7.55840893177116e-06, "loss": 0.2649, "step": 333200 }, { "epoch": 1.9806694366674393, "grad_norm": 5.181422233581543, "learning_rate": 7.558230657511341e-06, "loss": 0.3185, "step": 333210 }, { "epoch": 1.9807288787441077, "grad_norm": 7.579318046569824, "learning_rate": 7.5580523788459415e-06, "loss": 0.3028, "step": 333220 }, { "epoch": 1.9807883208207762, "grad_norm": 4.571646213531494, "learning_rate": 7.557874095775273e-06, "loss": 0.2399, "step": 333230 }, { "epoch": 1.9808477628974446, "grad_norm": 5.032779693603516, "learning_rate": 7.5576958082996384e-06, "loss": 0.2616, "step": 333240 }, { "epoch": 1.980907204974113, "grad_norm": 4.50356388092041, "learning_rate": 7.557517516419347e-06, "loss": 0.2709, "step": 333250 }, { "epoch": 1.9809666470507814, "grad_norm": 6.002161979675293, "learning_rate": 7.557339220134706e-06, "loss": 0.2698, "step": 333260 }, { "epoch": 1.9810260891274498, "grad_norm": 5.7090301513671875, "learning_rate": 7.557160919446022e-06, "loss": 0.2774, "step": 333270 }, { "epoch": 1.9810855312041182, "grad_norm": 4.726966381072998, "learning_rate": 7.5569826143536e-06, "loss": 0.2654, "step": 333280 }, { "epoch": 1.9811449732807866, "grad_norm": 5.011615753173828, "learning_rate": 7.55680430485775e-06, "loss": 0.2636, "step": 333290 }, { "epoch": 1.981204415357455, "grad_norm": 4.330877780914307, "learning_rate": 7.556625990958779e-06, "loss": 0.2772, "step": 333300 }, { "epoch": 1.9812638574341235, "grad_norm": 4.802555084228516, "learning_rate": 7.55644767265699e-06, "loss": 0.2882, "step": 333310 }, { "epoch": 1.9813232995107917, "grad_norm": 4.622309684753418, "learning_rate": 7.5562693499526966e-06, "loss": 0.2786, "step": 333320 }, { "epoch": 1.98138274158746, "grad_norm": 5.103168964385986, "learning_rate": 7.556091022846201e-06, "loss": 0.2592, "step": 333330 }, { "epoch": 1.9814421836641285, "grad_norm": 4.731681823730469, "learning_rate": 7.55591269133781e-06, "loss": 0.2827, "step": 333340 }, { "epoch": 1.981501625740797, "grad_norm": 6.869928359985352, "learning_rate": 7.555734355427833e-06, "loss": 0.2827, "step": 333350 }, { "epoch": 1.981561067817465, "grad_norm": 4.343555927276611, "learning_rate": 7.555556015116578e-06, "loss": 0.2865, "step": 333360 }, { "epoch": 1.9816205098941335, "grad_norm": 4.385809898376465, "learning_rate": 7.55537767040435e-06, "loss": 0.2675, "step": 333370 }, { "epoch": 1.981679951970802, "grad_norm": 5.720802307128906, "learning_rate": 7.555199321291457e-06, "loss": 0.2942, "step": 333380 }, { "epoch": 1.9817393940474703, "grad_norm": 4.090116024017334, "learning_rate": 7.555020967778205e-06, "loss": 0.2949, "step": 333390 }, { "epoch": 1.9817988361241388, "grad_norm": 5.265586853027344, "learning_rate": 7.554842609864903e-06, "loss": 0.2603, "step": 333400 }, { "epoch": 1.9818582782008072, "grad_norm": 5.440703392028809, "learning_rate": 7.554664247551856e-06, "loss": 0.2818, "step": 333410 }, { "epoch": 1.9819177202774756, "grad_norm": 5.037027359008789, "learning_rate": 7.554485880839373e-06, "loss": 0.2696, "step": 333420 }, { "epoch": 1.981977162354144, "grad_norm": 4.9707465171813965, "learning_rate": 7.55430750972776e-06, "loss": 0.2563, "step": 333430 }, { "epoch": 1.9820366044308124, "grad_norm": 4.719432353973389, "learning_rate": 7.554129134217326e-06, "loss": 0.2568, "step": 333440 }, { "epoch": 1.9820960465074808, "grad_norm": 5.704259872436523, "learning_rate": 7.553950754308376e-06, "loss": 0.2617, "step": 333450 }, { "epoch": 1.9821554885841492, "grad_norm": 4.639533996582031, "learning_rate": 7.553772370001218e-06, "loss": 0.2853, "step": 333460 }, { "epoch": 1.9822149306608177, "grad_norm": 4.498561859130859, "learning_rate": 7.55359398129616e-06, "loss": 0.2857, "step": 333470 }, { "epoch": 1.982274372737486, "grad_norm": 3.9125351905822754, "learning_rate": 7.553415588193507e-06, "loss": 0.2454, "step": 333480 }, { "epoch": 1.9823338148141545, "grad_norm": 4.970175743103027, "learning_rate": 7.55323719069357e-06, "loss": 0.291, "step": 333490 }, { "epoch": 1.9823932568908227, "grad_norm": 5.706159591674805, "learning_rate": 7.553058788796652e-06, "loss": 0.2797, "step": 333500 }, { "epoch": 1.982452698967491, "grad_norm": 4.35278844833374, "learning_rate": 7.5528803825030625e-06, "loss": 0.2497, "step": 333510 }, { "epoch": 1.9825121410441595, "grad_norm": 5.5225300788879395, "learning_rate": 7.552701971813108e-06, "loss": 0.2726, "step": 333520 }, { "epoch": 1.982571583120828, "grad_norm": 4.110819339752197, "learning_rate": 7.552523556727099e-06, "loss": 0.2966, "step": 333530 }, { "epoch": 1.9826310251974963, "grad_norm": 4.857229709625244, "learning_rate": 7.552345137245336e-06, "loss": 0.2782, "step": 333540 }, { "epoch": 1.9826904672741645, "grad_norm": 5.173206329345703, "learning_rate": 7.552166713368132e-06, "loss": 0.2632, "step": 333550 }, { "epoch": 1.982749909350833, "grad_norm": 5.5300469398498535, "learning_rate": 7.5519882850957906e-06, "loss": 0.3006, "step": 333560 }, { "epoch": 1.9828093514275014, "grad_norm": 5.487922191619873, "learning_rate": 7.551809852428623e-06, "loss": 0.2895, "step": 333570 }, { "epoch": 1.9828687935041698, "grad_norm": 5.486788272857666, "learning_rate": 7.551631415366934e-06, "loss": 0.2693, "step": 333580 }, { "epoch": 1.9829282355808382, "grad_norm": 4.187631607055664, "learning_rate": 7.5514529739110305e-06, "loss": 0.2603, "step": 333590 }, { "epoch": 1.9829876776575066, "grad_norm": 5.0842976570129395, "learning_rate": 7.551274528061221e-06, "loss": 0.2431, "step": 333600 }, { "epoch": 1.983047119734175, "grad_norm": 4.666178226470947, "learning_rate": 7.5510960778178125e-06, "loss": 0.2469, "step": 333610 }, { "epoch": 1.9831065618108434, "grad_norm": 5.921572685241699, "learning_rate": 7.550917623181112e-06, "loss": 0.2879, "step": 333620 }, { "epoch": 1.9831660038875119, "grad_norm": 4.50773811340332, "learning_rate": 7.550739164151428e-06, "loss": 0.2588, "step": 333630 }, { "epoch": 1.9832254459641803, "grad_norm": 5.270740032196045, "learning_rate": 7.5505607007290645e-06, "loss": 0.2729, "step": 333640 }, { "epoch": 1.9832848880408487, "grad_norm": 4.7660813331604, "learning_rate": 7.550382232914333e-06, "loss": 0.2854, "step": 333650 }, { "epoch": 1.983344330117517, "grad_norm": 5.300734996795654, "learning_rate": 7.5502037607075396e-06, "loss": 0.2882, "step": 333660 }, { "epoch": 1.9834037721941855, "grad_norm": 7.166122913360596, "learning_rate": 7.550025284108988e-06, "loss": 0.2844, "step": 333670 }, { "epoch": 1.983463214270854, "grad_norm": 5.986085414886475, "learning_rate": 7.54984680311899e-06, "loss": 0.2508, "step": 333680 }, { "epoch": 1.9835226563475221, "grad_norm": 4.734555721282959, "learning_rate": 7.549668317737853e-06, "loss": 0.2644, "step": 333690 }, { "epoch": 1.9835820984241905, "grad_norm": 6.9520063400268555, "learning_rate": 7.549489827965883e-06, "loss": 0.2929, "step": 333700 }, { "epoch": 1.983641540500859, "grad_norm": 4.49788761138916, "learning_rate": 7.549311333803384e-06, "loss": 0.2606, "step": 333710 }, { "epoch": 1.9837009825775274, "grad_norm": 5.781648635864258, "learning_rate": 7.54913283525067e-06, "loss": 0.2674, "step": 333720 }, { "epoch": 1.9837604246541956, "grad_norm": 4.780023097991943, "learning_rate": 7.548954332308045e-06, "loss": 0.2646, "step": 333730 }, { "epoch": 1.983819866730864, "grad_norm": 5.688884258270264, "learning_rate": 7.548775824975815e-06, "loss": 0.2815, "step": 333740 }, { "epoch": 1.9838793088075324, "grad_norm": 6.200292587280273, "learning_rate": 7.5485973132542885e-06, "loss": 0.2795, "step": 333750 }, { "epoch": 1.9839387508842008, "grad_norm": 5.943545341491699, "learning_rate": 7.548418797143775e-06, "loss": 0.2921, "step": 333760 }, { "epoch": 1.9839981929608692, "grad_norm": 6.183577537536621, "learning_rate": 7.548240276644579e-06, "loss": 0.2906, "step": 333770 }, { "epoch": 1.9840576350375376, "grad_norm": 4.66576623916626, "learning_rate": 7.54806175175701e-06, "loss": 0.2681, "step": 333780 }, { "epoch": 1.984117077114206, "grad_norm": 4.485372066497803, "learning_rate": 7.5478832224813744e-06, "loss": 0.2747, "step": 333790 }, { "epoch": 1.9841765191908745, "grad_norm": 6.009836196899414, "learning_rate": 7.5477046888179795e-06, "loss": 0.2722, "step": 333800 }, { "epoch": 1.9842359612675429, "grad_norm": 5.29018497467041, "learning_rate": 7.5475261507671335e-06, "loss": 0.2617, "step": 333810 }, { "epoch": 1.9842954033442113, "grad_norm": 5.0293731689453125, "learning_rate": 7.547347608329146e-06, "loss": 0.262, "step": 333820 }, { "epoch": 1.9843548454208797, "grad_norm": 2.789541482925415, "learning_rate": 7.547169061504318e-06, "loss": 0.2753, "step": 333830 }, { "epoch": 1.9844142874975481, "grad_norm": 4.971780776977539, "learning_rate": 7.546990510292962e-06, "loss": 0.2763, "step": 333840 }, { "epoch": 1.9844737295742165, "grad_norm": 5.229206085205078, "learning_rate": 7.5468119546953855e-06, "loss": 0.263, "step": 333850 }, { "epoch": 1.984533171650885, "grad_norm": 5.066108703613281, "learning_rate": 7.546633394711893e-06, "loss": 0.2553, "step": 333860 }, { "epoch": 1.9845926137275531, "grad_norm": 6.052231311798096, "learning_rate": 7.546454830342796e-06, "loss": 0.2814, "step": 333870 }, { "epoch": 1.9846520558042215, "grad_norm": 8.945713996887207, "learning_rate": 7.5462762615884e-06, "loss": 0.2623, "step": 333880 }, { "epoch": 1.98471149788089, "grad_norm": 3.9495410919189453, "learning_rate": 7.546097688449011e-06, "loss": 0.304, "step": 333890 }, { "epoch": 1.9847709399575584, "grad_norm": 3.4209892749786377, "learning_rate": 7.545919110924937e-06, "loss": 0.268, "step": 333900 }, { "epoch": 1.9848303820342268, "grad_norm": 4.320598125457764, "learning_rate": 7.54574052901649e-06, "loss": 0.2991, "step": 333910 }, { "epoch": 1.984889824110895, "grad_norm": 4.800296306610107, "learning_rate": 7.545561942723972e-06, "loss": 0.3054, "step": 333920 }, { "epoch": 1.9849492661875634, "grad_norm": 6.595334053039551, "learning_rate": 7.5453833520476926e-06, "loss": 0.277, "step": 333930 }, { "epoch": 1.9850087082642318, "grad_norm": 5.283450603485107, "learning_rate": 7.545204756987961e-06, "loss": 0.2652, "step": 333940 }, { "epoch": 1.9850681503409002, "grad_norm": 5.17133903503418, "learning_rate": 7.5450261575450815e-06, "loss": 0.2674, "step": 333950 }, { "epoch": 1.9851275924175686, "grad_norm": 5.390469551086426, "learning_rate": 7.544847553719363e-06, "loss": 0.2621, "step": 333960 }, { "epoch": 1.985187034494237, "grad_norm": 5.48183012008667, "learning_rate": 7.5446689455111135e-06, "loss": 0.2951, "step": 333970 }, { "epoch": 1.9852464765709055, "grad_norm": 4.696158409118652, "learning_rate": 7.544490332920642e-06, "loss": 0.2711, "step": 333980 }, { "epoch": 1.9853059186475739, "grad_norm": 4.05470609664917, "learning_rate": 7.544311715948252e-06, "loss": 0.2668, "step": 333990 }, { "epoch": 1.9853653607242423, "grad_norm": 3.817927122116089, "learning_rate": 7.544133094594255e-06, "loss": 0.2876, "step": 334000 }, { "epoch": 1.9854248028009107, "grad_norm": 5.817826747894287, "learning_rate": 7.543954468858957e-06, "loss": 0.2966, "step": 334010 }, { "epoch": 1.9854842448775791, "grad_norm": 4.571248531341553, "learning_rate": 7.543775838742666e-06, "loss": 0.2655, "step": 334020 }, { "epoch": 1.9855436869542475, "grad_norm": 3.9994988441467285, "learning_rate": 7.543597204245689e-06, "loss": 0.2707, "step": 334030 }, { "epoch": 1.985603129030916, "grad_norm": 7.039811611175537, "learning_rate": 7.5434185653683365e-06, "loss": 0.28, "step": 334040 }, { "epoch": 1.9856625711075844, "grad_norm": 5.904048919677734, "learning_rate": 7.543239922110912e-06, "loss": 0.2829, "step": 334050 }, { "epoch": 1.9857220131842526, "grad_norm": 4.763187408447266, "learning_rate": 7.543061274473724e-06, "loss": 0.2542, "step": 334060 }, { "epoch": 1.985781455260921, "grad_norm": 3.9634172916412354, "learning_rate": 7.542882622457082e-06, "loss": 0.2673, "step": 334070 }, { "epoch": 1.9858408973375894, "grad_norm": 4.315401554107666, "learning_rate": 7.542703966061293e-06, "loss": 0.2713, "step": 334080 }, { "epoch": 1.9859003394142578, "grad_norm": 5.189443111419678, "learning_rate": 7.542525305286663e-06, "loss": 0.2911, "step": 334090 }, { "epoch": 1.985959781490926, "grad_norm": 4.3691277503967285, "learning_rate": 7.542346640133503e-06, "loss": 0.2789, "step": 334100 }, { "epoch": 1.9860192235675944, "grad_norm": 7.1067891120910645, "learning_rate": 7.542167970602118e-06, "loss": 0.2669, "step": 334110 }, { "epoch": 1.9860786656442628, "grad_norm": 4.755127429962158, "learning_rate": 7.5419892966928154e-06, "loss": 0.2755, "step": 334120 }, { "epoch": 1.9861381077209312, "grad_norm": 5.170802593231201, "learning_rate": 7.541810618405905e-06, "loss": 0.3035, "step": 334130 }, { "epoch": 1.9861975497975997, "grad_norm": 5.950149059295654, "learning_rate": 7.541631935741694e-06, "loss": 0.2895, "step": 334140 }, { "epoch": 1.986256991874268, "grad_norm": 5.40059757232666, "learning_rate": 7.541453248700489e-06, "loss": 0.2749, "step": 334150 }, { "epoch": 1.9863164339509365, "grad_norm": 4.725374221801758, "learning_rate": 7.5412745572825965e-06, "loss": 0.241, "step": 334160 }, { "epoch": 1.986375876027605, "grad_norm": 3.9918758869171143, "learning_rate": 7.541095861488328e-06, "loss": 0.2569, "step": 334170 }, { "epoch": 1.9864353181042733, "grad_norm": 5.128540992736816, "learning_rate": 7.540917161317989e-06, "loss": 0.269, "step": 334180 }, { "epoch": 1.9864947601809417, "grad_norm": 5.443593978881836, "learning_rate": 7.540738456771888e-06, "loss": 0.2936, "step": 334190 }, { "epoch": 1.9865542022576101, "grad_norm": 4.339432239532471, "learning_rate": 7.540559747850331e-06, "loss": 0.277, "step": 334200 }, { "epoch": 1.9866136443342786, "grad_norm": 6.044698238372803, "learning_rate": 7.540381034553628e-06, "loss": 0.2232, "step": 334210 }, { "epoch": 1.986673086410947, "grad_norm": 5.420915603637695, "learning_rate": 7.540202316882084e-06, "loss": 0.2799, "step": 334220 }, { "epoch": 1.9867325284876154, "grad_norm": 6.200645446777344, "learning_rate": 7.54002359483601e-06, "loss": 0.2488, "step": 334230 }, { "epoch": 1.9867919705642836, "grad_norm": 3.7592101097106934, "learning_rate": 7.539844868415711e-06, "loss": 0.2757, "step": 334240 }, { "epoch": 1.986851412640952, "grad_norm": 4.487176418304443, "learning_rate": 7.539666137621497e-06, "loss": 0.2571, "step": 334250 }, { "epoch": 1.9869108547176204, "grad_norm": 4.490195274353027, "learning_rate": 7.539487402453675e-06, "loss": 0.2574, "step": 334260 }, { "epoch": 1.9869702967942888, "grad_norm": 4.3246588706970215, "learning_rate": 7.539308662912554e-06, "loss": 0.2611, "step": 334270 }, { "epoch": 1.9870297388709572, "grad_norm": 5.3002495765686035, "learning_rate": 7.539129918998439e-06, "loss": 0.2606, "step": 334280 }, { "epoch": 1.9870891809476254, "grad_norm": 3.845219373703003, "learning_rate": 7.538951170711639e-06, "loss": 0.2537, "step": 334290 }, { "epoch": 1.9871486230242938, "grad_norm": 4.554286956787109, "learning_rate": 7.538772418052462e-06, "loss": 0.296, "step": 334300 }, { "epoch": 1.9872080651009623, "grad_norm": 5.562192916870117, "learning_rate": 7.538593661021218e-06, "loss": 0.2664, "step": 334310 }, { "epoch": 1.9872675071776307, "grad_norm": 3.981051445007324, "learning_rate": 7.538414899618209e-06, "loss": 0.2765, "step": 334320 }, { "epoch": 1.987326949254299, "grad_norm": 3.1251089572906494, "learning_rate": 7.5382361338437505e-06, "loss": 0.2533, "step": 334330 }, { "epoch": 1.9873863913309675, "grad_norm": 4.4245381355285645, "learning_rate": 7.538057363698146e-06, "loss": 0.2912, "step": 334340 }, { "epoch": 1.987445833407636, "grad_norm": 4.712038040161133, "learning_rate": 7.537878589181702e-06, "loss": 0.2839, "step": 334350 }, { "epoch": 1.9875052754843043, "grad_norm": 5.632150173187256, "learning_rate": 7.53769981029473e-06, "loss": 0.2679, "step": 334360 }, { "epoch": 1.9875647175609727, "grad_norm": 6.805201053619385, "learning_rate": 7.537521027037536e-06, "loss": 0.3198, "step": 334370 }, { "epoch": 1.9876241596376412, "grad_norm": 4.5278449058532715, "learning_rate": 7.537342239410426e-06, "loss": 0.2469, "step": 334380 }, { "epoch": 1.9876836017143096, "grad_norm": 5.370113372802734, "learning_rate": 7.537163447413711e-06, "loss": 0.2671, "step": 334390 }, { "epoch": 1.987743043790978, "grad_norm": 5.5566792488098145, "learning_rate": 7.5369846510476985e-06, "loss": 0.2622, "step": 334400 }, { "epoch": 1.9878024858676464, "grad_norm": 4.617702007293701, "learning_rate": 7.536805850312696e-06, "loss": 0.2476, "step": 334410 }, { "epoch": 1.9878619279443148, "grad_norm": 6.427184581756592, "learning_rate": 7.536627045209009e-06, "loss": 0.2595, "step": 334420 }, { "epoch": 1.987921370020983, "grad_norm": 5.026888847351074, "learning_rate": 7.5364482357369484e-06, "loss": 0.2845, "step": 334430 }, { "epoch": 1.9879808120976514, "grad_norm": 4.9663166999816895, "learning_rate": 7.5362694218968225e-06, "loss": 0.2911, "step": 334440 }, { "epoch": 1.9880402541743198, "grad_norm": 4.938884258270264, "learning_rate": 7.536090603688937e-06, "loss": 0.2632, "step": 334450 }, { "epoch": 1.9880996962509883, "grad_norm": 4.510075092315674, "learning_rate": 7.535911781113602e-06, "loss": 0.269, "step": 334460 }, { "epoch": 1.9881591383276564, "grad_norm": 4.411069869995117, "learning_rate": 7.535732954171124e-06, "loss": 0.2972, "step": 334470 }, { "epoch": 1.9882185804043249, "grad_norm": 4.669015884399414, "learning_rate": 7.53555412286181e-06, "loss": 0.2966, "step": 334480 }, { "epoch": 1.9882780224809933, "grad_norm": 4.350018501281738, "learning_rate": 7.535375287185971e-06, "loss": 0.2545, "step": 334490 }, { "epoch": 1.9883374645576617, "grad_norm": 3.803286552429199, "learning_rate": 7.535196447143913e-06, "loss": 0.2688, "step": 334500 }, { "epoch": 1.98839690663433, "grad_norm": 4.491608142852783, "learning_rate": 7.535017602735944e-06, "loss": 0.2609, "step": 334510 }, { "epoch": 1.9884563487109985, "grad_norm": 4.628204345703125, "learning_rate": 7.534838753962371e-06, "loss": 0.2744, "step": 334520 }, { "epoch": 1.988515790787667, "grad_norm": 5.127689361572266, "learning_rate": 7.534659900823505e-06, "loss": 0.2769, "step": 334530 }, { "epoch": 1.9885752328643354, "grad_norm": 4.541579723358154, "learning_rate": 7.53448104331965e-06, "loss": 0.2618, "step": 334540 }, { "epoch": 1.9886346749410038, "grad_norm": 5.461353778839111, "learning_rate": 7.534302181451116e-06, "loss": 0.2655, "step": 334550 }, { "epoch": 1.9886941170176722, "grad_norm": 5.837432861328125, "learning_rate": 7.534123315218214e-06, "loss": 0.2723, "step": 334560 }, { "epoch": 1.9887535590943406, "grad_norm": 3.9719018936157227, "learning_rate": 7.5339444446212485e-06, "loss": 0.2624, "step": 334570 }, { "epoch": 1.988813001171009, "grad_norm": 5.1922383308410645, "learning_rate": 7.533765569660527e-06, "loss": 0.2651, "step": 334580 }, { "epoch": 1.9888724432476774, "grad_norm": 5.541519641876221, "learning_rate": 7.533586690336361e-06, "loss": 0.2743, "step": 334590 }, { "epoch": 1.9889318853243458, "grad_norm": 4.799245834350586, "learning_rate": 7.533407806649055e-06, "loss": 0.2791, "step": 334600 }, { "epoch": 1.988991327401014, "grad_norm": 5.345799446105957, "learning_rate": 7.533228918598919e-06, "loss": 0.268, "step": 334610 }, { "epoch": 1.9890507694776824, "grad_norm": 4.391790390014648, "learning_rate": 7.53305002618626e-06, "loss": 0.2602, "step": 334620 }, { "epoch": 1.9891102115543509, "grad_norm": 6.117446422576904, "learning_rate": 7.532871129411388e-06, "loss": 0.2708, "step": 334630 }, { "epoch": 1.9891696536310193, "grad_norm": 5.72154426574707, "learning_rate": 7.532692228274607e-06, "loss": 0.3133, "step": 334640 }, { "epoch": 1.9892290957076877, "grad_norm": 4.117959022521973, "learning_rate": 7.53251332277623e-06, "loss": 0.268, "step": 334650 }, { "epoch": 1.9892885377843559, "grad_norm": 3.907851457595825, "learning_rate": 7.5323344129165606e-06, "loss": 0.2478, "step": 334660 }, { "epoch": 1.9893479798610243, "grad_norm": 5.999772548675537, "learning_rate": 7.532155498695912e-06, "loss": 0.2752, "step": 334670 }, { "epoch": 1.9894074219376927, "grad_norm": 6.088980674743652, "learning_rate": 7.531976580114587e-06, "loss": 0.2821, "step": 334680 }, { "epoch": 1.9894668640143611, "grad_norm": 4.097567558288574, "learning_rate": 7.531797657172899e-06, "loss": 0.2804, "step": 334690 }, { "epoch": 1.9895263060910295, "grad_norm": 4.358227252960205, "learning_rate": 7.531618729871151e-06, "loss": 0.2668, "step": 334700 }, { "epoch": 1.989585748167698, "grad_norm": 5.145084857940674, "learning_rate": 7.531439798209654e-06, "loss": 0.2758, "step": 334710 }, { "epoch": 1.9896451902443664, "grad_norm": 5.2094621658325195, "learning_rate": 7.531260862188716e-06, "loss": 0.3129, "step": 334720 }, { "epoch": 1.9897046323210348, "grad_norm": 4.949987888336182, "learning_rate": 7.531081921808645e-06, "loss": 0.2748, "step": 334730 }, { "epoch": 1.9897640743977032, "grad_norm": 3.4191040992736816, "learning_rate": 7.530902977069748e-06, "loss": 0.3042, "step": 334740 }, { "epoch": 1.9898235164743716, "grad_norm": 6.269016265869141, "learning_rate": 7.530724027972336e-06, "loss": 0.2608, "step": 334750 }, { "epoch": 1.98988295855104, "grad_norm": 4.589778900146484, "learning_rate": 7.530545074516713e-06, "loss": 0.2637, "step": 334760 }, { "epoch": 1.9899424006277084, "grad_norm": 4.762278079986572, "learning_rate": 7.530366116703192e-06, "loss": 0.2434, "step": 334770 }, { "epoch": 1.9900018427043769, "grad_norm": 5.210390090942383, "learning_rate": 7.530187154532076e-06, "loss": 0.2894, "step": 334780 }, { "epoch": 1.9900612847810453, "grad_norm": 5.18287992477417, "learning_rate": 7.5300081880036765e-06, "loss": 0.263, "step": 334790 }, { "epoch": 1.9901207268577135, "grad_norm": 4.207042694091797, "learning_rate": 7.529829217118302e-06, "loss": 0.2842, "step": 334800 }, { "epoch": 1.9901801689343819, "grad_norm": 4.444934368133545, "learning_rate": 7.5296502418762585e-06, "loss": 0.2683, "step": 334810 }, { "epoch": 1.9902396110110503, "grad_norm": 6.490654945373535, "learning_rate": 7.529471262277856e-06, "loss": 0.3147, "step": 334820 }, { "epoch": 1.9902990530877187, "grad_norm": 6.965941429138184, "learning_rate": 7.529292278323403e-06, "loss": 0.2804, "step": 334830 }, { "epoch": 1.990358495164387, "grad_norm": 4.964329719543457, "learning_rate": 7.5291132900132054e-06, "loss": 0.2725, "step": 334840 }, { "epoch": 1.9904179372410553, "grad_norm": 6.005241870880127, "learning_rate": 7.528934297347574e-06, "loss": 0.2768, "step": 334850 }, { "epoch": 1.9904773793177237, "grad_norm": 4.02008581161499, "learning_rate": 7.5287553003268165e-06, "loss": 0.2625, "step": 334860 }, { "epoch": 1.9905368213943921, "grad_norm": 5.647498607635498, "learning_rate": 7.528576298951239e-06, "loss": 0.2771, "step": 334870 }, { "epoch": 1.9905962634710606, "grad_norm": 4.781754016876221, "learning_rate": 7.528397293221153e-06, "loss": 0.2943, "step": 334880 }, { "epoch": 1.990655705547729, "grad_norm": 4.808435916900635, "learning_rate": 7.528218283136863e-06, "loss": 0.2956, "step": 334890 }, { "epoch": 1.9907151476243974, "grad_norm": 5.33848762512207, "learning_rate": 7.528039268698681e-06, "loss": 0.2617, "step": 334900 }, { "epoch": 1.9907745897010658, "grad_norm": 4.9022345542907715, "learning_rate": 7.5278602499069144e-06, "loss": 0.2705, "step": 334910 }, { "epoch": 1.9908340317777342, "grad_norm": 4.841489791870117, "learning_rate": 7.527681226761869e-06, "loss": 0.245, "step": 334920 }, { "epoch": 1.9908934738544026, "grad_norm": 7.127992153167725, "learning_rate": 7.527502199263857e-06, "loss": 0.2679, "step": 334930 }, { "epoch": 1.990952915931071, "grad_norm": 4.066498756408691, "learning_rate": 7.527323167413183e-06, "loss": 0.2563, "step": 334940 }, { "epoch": 1.9910123580077395, "grad_norm": 6.165828704833984, "learning_rate": 7.527144131210158e-06, "loss": 0.2648, "step": 334950 }, { "epoch": 1.9910718000844079, "grad_norm": 4.160294055938721, "learning_rate": 7.52696509065509e-06, "loss": 0.2476, "step": 334960 }, { "epoch": 1.9911312421610763, "grad_norm": 5.636240482330322, "learning_rate": 7.526786045748285e-06, "loss": 0.253, "step": 334970 }, { "epoch": 1.9911906842377445, "grad_norm": 4.942093849182129, "learning_rate": 7.526606996490052e-06, "loss": 0.2929, "step": 334980 }, { "epoch": 1.991250126314413, "grad_norm": 5.367844581604004, "learning_rate": 7.526427942880703e-06, "loss": 0.2686, "step": 334990 }, { "epoch": 1.9913095683910813, "grad_norm": 5.022980690002441, "learning_rate": 7.526248884920542e-06, "loss": 0.2717, "step": 335000 }, { "epoch": 1.9913690104677497, "grad_norm": 4.847395420074463, "learning_rate": 7.526069822609878e-06, "loss": 0.2544, "step": 335010 }, { "epoch": 1.9914284525444181, "grad_norm": 5.198481559753418, "learning_rate": 7.525890755949023e-06, "loss": 0.2518, "step": 335020 }, { "epoch": 1.9914878946210863, "grad_norm": 4.385842800140381, "learning_rate": 7.5257116849382815e-06, "loss": 0.28, "step": 335030 }, { "epoch": 1.9915473366977547, "grad_norm": 6.36310338973999, "learning_rate": 7.525532609577962e-06, "loss": 0.2426, "step": 335040 }, { "epoch": 1.9916067787744232, "grad_norm": 4.802170753479004, "learning_rate": 7.525353529868376e-06, "loss": 0.2629, "step": 335050 }, { "epoch": 1.9916662208510916, "grad_norm": 3.6536707878112793, "learning_rate": 7.525174445809829e-06, "loss": 0.2513, "step": 335060 }, { "epoch": 1.99172566292776, "grad_norm": 4.375363826751709, "learning_rate": 7.5249953574026294e-06, "loss": 0.243, "step": 335070 }, { "epoch": 1.9917851050044284, "grad_norm": 4.1125946044921875, "learning_rate": 7.524816264647088e-06, "loss": 0.2375, "step": 335080 }, { "epoch": 1.9918445470810968, "grad_norm": 4.5851149559021, "learning_rate": 7.52463716754351e-06, "loss": 0.2521, "step": 335090 }, { "epoch": 1.9919039891577652, "grad_norm": 5.7064290046691895, "learning_rate": 7.524458066092206e-06, "loss": 0.2612, "step": 335100 }, { "epoch": 1.9919634312344336, "grad_norm": 6.259716987609863, "learning_rate": 7.524278960293485e-06, "loss": 0.2762, "step": 335110 }, { "epoch": 1.992022873311102, "grad_norm": 4.353155612945557, "learning_rate": 7.5240998501476545e-06, "loss": 0.2803, "step": 335120 }, { "epoch": 1.9920823153877705, "grad_norm": 5.4060959815979, "learning_rate": 7.523920735655023e-06, "loss": 0.2889, "step": 335130 }, { "epoch": 1.992141757464439, "grad_norm": 4.882318019866943, "learning_rate": 7.523741616815898e-06, "loss": 0.2589, "step": 335140 }, { "epoch": 1.9922011995411073, "grad_norm": 5.6042304039001465, "learning_rate": 7.523562493630589e-06, "loss": 0.3028, "step": 335150 }, { "epoch": 1.9922606416177757, "grad_norm": 4.852837085723877, "learning_rate": 7.523383366099403e-06, "loss": 0.2561, "step": 335160 }, { "epoch": 1.992320083694444, "grad_norm": 5.468598365783691, "learning_rate": 7.523204234222653e-06, "loss": 0.2832, "step": 335170 }, { "epoch": 1.9923795257711123, "grad_norm": 5.291379928588867, "learning_rate": 7.523025098000643e-06, "loss": 0.2872, "step": 335180 }, { "epoch": 1.9924389678477807, "grad_norm": 4.2806878089904785, "learning_rate": 7.522845957433682e-06, "loss": 0.2815, "step": 335190 }, { "epoch": 1.9924984099244492, "grad_norm": 4.191735744476318, "learning_rate": 7.522666812522078e-06, "loss": 0.3057, "step": 335200 }, { "epoch": 1.9925578520011173, "grad_norm": 5.187196254730225, "learning_rate": 7.522487663266142e-06, "loss": 0.2872, "step": 335210 }, { "epoch": 1.9926172940777858, "grad_norm": 4.460960388183594, "learning_rate": 7.522308509666183e-06, "loss": 0.272, "step": 335220 }, { "epoch": 1.9926767361544542, "grad_norm": 5.365761756896973, "learning_rate": 7.5221293517225045e-06, "loss": 0.2689, "step": 335230 }, { "epoch": 1.9927361782311226, "grad_norm": 4.216768264770508, "learning_rate": 7.5219501894354204e-06, "loss": 0.2541, "step": 335240 }, { "epoch": 1.992795620307791, "grad_norm": 4.919052600860596, "learning_rate": 7.521771022805238e-06, "loss": 0.2855, "step": 335250 }, { "epoch": 1.9928550623844594, "grad_norm": 3.6329379081726074, "learning_rate": 7.521591851832263e-06, "loss": 0.2951, "step": 335260 }, { "epoch": 1.9929145044611278, "grad_norm": 5.457801342010498, "learning_rate": 7.5214126765168065e-06, "loss": 0.2481, "step": 335270 }, { "epoch": 1.9929739465377962, "grad_norm": 5.060497283935547, "learning_rate": 7.521233496859177e-06, "loss": 0.2622, "step": 335280 }, { "epoch": 1.9930333886144647, "grad_norm": 4.643675804138184, "learning_rate": 7.521054312859683e-06, "loss": 0.2737, "step": 335290 }, { "epoch": 1.993092830691133, "grad_norm": 4.60056734085083, "learning_rate": 7.520875124518632e-06, "loss": 0.2747, "step": 335300 }, { "epoch": 1.9931522727678015, "grad_norm": 7.289217472076416, "learning_rate": 7.520695931836333e-06, "loss": 0.32, "step": 335310 }, { "epoch": 1.99321171484447, "grad_norm": 5.062859058380127, "learning_rate": 7.520516734813095e-06, "loss": 0.2555, "step": 335320 }, { "epoch": 1.9932711569211383, "grad_norm": 4.004428863525391, "learning_rate": 7.520337533449226e-06, "loss": 0.2607, "step": 335330 }, { "epoch": 1.9933305989978067, "grad_norm": 5.811785697937012, "learning_rate": 7.5201583277450355e-06, "loss": 0.2548, "step": 335340 }, { "epoch": 1.993390041074475, "grad_norm": 5.802314758300781, "learning_rate": 7.519979117700833e-06, "loss": 0.2618, "step": 335350 }, { "epoch": 1.9934494831511433, "grad_norm": 5.716897487640381, "learning_rate": 7.519799903316923e-06, "loss": 0.2914, "step": 335360 }, { "epoch": 1.9935089252278118, "grad_norm": 4.642345905303955, "learning_rate": 7.5196206845936185e-06, "loss": 0.2769, "step": 335370 }, { "epoch": 1.9935683673044802, "grad_norm": 6.622348308563232, "learning_rate": 7.519441461531228e-06, "loss": 0.2447, "step": 335380 }, { "epoch": 1.9936278093811486, "grad_norm": 5.067624568939209, "learning_rate": 7.519262234130056e-06, "loss": 0.2462, "step": 335390 }, { "epoch": 1.9936872514578168, "grad_norm": 4.268067359924316, "learning_rate": 7.519083002390415e-06, "loss": 0.2572, "step": 335400 }, { "epoch": 1.9937466935344852, "grad_norm": 4.248361110687256, "learning_rate": 7.518903766312613e-06, "loss": 0.2809, "step": 335410 }, { "epoch": 1.9938061356111536, "grad_norm": 4.309361934661865, "learning_rate": 7.518724525896957e-06, "loss": 0.2474, "step": 335420 }, { "epoch": 1.993865577687822, "grad_norm": 6.406317710876465, "learning_rate": 7.518545281143756e-06, "loss": 0.2832, "step": 335430 }, { "epoch": 1.9939250197644904, "grad_norm": 4.34786319732666, "learning_rate": 7.518366032053323e-06, "loss": 0.2904, "step": 335440 }, { "epoch": 1.9939844618411589, "grad_norm": 4.137753963470459, "learning_rate": 7.518186778625961e-06, "loss": 0.2725, "step": 335450 }, { "epoch": 1.9940439039178273, "grad_norm": 4.747987270355225, "learning_rate": 7.5180075208619806e-06, "loss": 0.2312, "step": 335460 }, { "epoch": 1.9941033459944957, "grad_norm": 5.573941707611084, "learning_rate": 7.517828258761693e-06, "loss": 0.2851, "step": 335470 }, { "epoch": 1.994162788071164, "grad_norm": 3.7379400730133057, "learning_rate": 7.517648992325402e-06, "loss": 0.282, "step": 335480 }, { "epoch": 1.9942222301478325, "grad_norm": 4.369951248168945, "learning_rate": 7.51746972155342e-06, "loss": 0.2398, "step": 335490 }, { "epoch": 1.994281672224501, "grad_norm": 5.277805805206299, "learning_rate": 7.517290446446055e-06, "loss": 0.2662, "step": 335500 }, { "epoch": 1.9943411143011693, "grad_norm": 4.720978260040283, "learning_rate": 7.517111167003616e-06, "loss": 0.3158, "step": 335510 }, { "epoch": 1.9944005563778378, "grad_norm": 3.8462414741516113, "learning_rate": 7.516931883226409e-06, "loss": 0.2758, "step": 335520 }, { "epoch": 1.9944599984545062, "grad_norm": 4.540832996368408, "learning_rate": 7.5167525951147466e-06, "loss": 0.2468, "step": 335530 }, { "epoch": 1.9945194405311744, "grad_norm": 4.6067585945129395, "learning_rate": 7.516573302668937e-06, "loss": 0.2661, "step": 335540 }, { "epoch": 1.9945788826078428, "grad_norm": 6.134123802185059, "learning_rate": 7.516394005889287e-06, "loss": 0.2912, "step": 335550 }, { "epoch": 1.9946383246845112, "grad_norm": 4.263063907623291, "learning_rate": 7.516214704776105e-06, "loss": 0.2855, "step": 335560 }, { "epoch": 1.9946977667611796, "grad_norm": 4.87118673324585, "learning_rate": 7.5160353993297015e-06, "loss": 0.2464, "step": 335570 }, { "epoch": 1.9947572088378478, "grad_norm": 5.259760856628418, "learning_rate": 7.5158560895503865e-06, "loss": 0.2924, "step": 335580 }, { "epoch": 1.9948166509145162, "grad_norm": 5.62630033493042, "learning_rate": 7.515676775438465e-06, "loss": 0.2813, "step": 335590 }, { "epoch": 1.9948760929911846, "grad_norm": 6.353065013885498, "learning_rate": 7.515497456994249e-06, "loss": 0.2974, "step": 335600 }, { "epoch": 1.994935535067853, "grad_norm": 6.434380054473877, "learning_rate": 7.515318134218048e-06, "loss": 0.2853, "step": 335610 }, { "epoch": 1.9949949771445215, "grad_norm": 4.552290916442871, "learning_rate": 7.515138807110166e-06, "loss": 0.2723, "step": 335620 }, { "epoch": 1.9950544192211899, "grad_norm": 3.973853826522827, "learning_rate": 7.514959475670917e-06, "loss": 0.2617, "step": 335630 }, { "epoch": 1.9951138612978583, "grad_norm": 4.795000076293945, "learning_rate": 7.514780139900606e-06, "loss": 0.2511, "step": 335640 }, { "epoch": 1.9951733033745267, "grad_norm": 4.118087291717529, "learning_rate": 7.514600799799544e-06, "loss": 0.2601, "step": 335650 }, { "epoch": 1.9952327454511951, "grad_norm": 3.415752410888672, "learning_rate": 7.514421455368039e-06, "loss": 0.2662, "step": 335660 }, { "epoch": 1.9952921875278635, "grad_norm": 4.635228157043457, "learning_rate": 7.514242106606402e-06, "loss": 0.249, "step": 335670 }, { "epoch": 1.995351629604532, "grad_norm": 5.394193649291992, "learning_rate": 7.514062753514939e-06, "loss": 0.2718, "step": 335680 }, { "epoch": 1.9954110716812004, "grad_norm": 4.372623443603516, "learning_rate": 7.51388339609396e-06, "loss": 0.261, "step": 335690 }, { "epoch": 1.9954705137578688, "grad_norm": 5.471097469329834, "learning_rate": 7.513704034343774e-06, "loss": 0.3135, "step": 335700 }, { "epoch": 1.9955299558345372, "grad_norm": 5.8680853843688965, "learning_rate": 7.513524668264691e-06, "loss": 0.2768, "step": 335710 }, { "epoch": 1.9955893979112054, "grad_norm": 4.39827823638916, "learning_rate": 7.513345297857016e-06, "loss": 0.2925, "step": 335720 }, { "epoch": 1.9956488399878738, "grad_norm": 4.98432731628418, "learning_rate": 7.513165923121062e-06, "loss": 0.2498, "step": 335730 }, { "epoch": 1.9957082820645422, "grad_norm": 3.9096593856811523, "learning_rate": 7.512986544057137e-06, "loss": 0.2722, "step": 335740 }, { "epoch": 1.9957677241412106, "grad_norm": 4.8781328201293945, "learning_rate": 7.512807160665548e-06, "loss": 0.2514, "step": 335750 }, { "epoch": 1.995827166217879, "grad_norm": 4.7148356437683105, "learning_rate": 7.512627772946606e-06, "loss": 0.263, "step": 335760 }, { "epoch": 1.9958866082945472, "grad_norm": 6.120100498199463, "learning_rate": 7.512448380900619e-06, "loss": 0.3116, "step": 335770 }, { "epoch": 1.9959460503712156, "grad_norm": 6.007613658905029, "learning_rate": 7.512268984527895e-06, "loss": 0.2439, "step": 335780 }, { "epoch": 1.996005492447884, "grad_norm": 4.295925617218018, "learning_rate": 7.512089583828745e-06, "loss": 0.2471, "step": 335790 }, { "epoch": 1.9960649345245525, "grad_norm": 4.283026218414307, "learning_rate": 7.511910178803478e-06, "loss": 0.2861, "step": 335800 }, { "epoch": 1.9961243766012209, "grad_norm": 4.503402233123779, "learning_rate": 7.5117307694524e-06, "loss": 0.2395, "step": 335810 }, { "epoch": 1.9961838186778893, "grad_norm": 4.642983913421631, "learning_rate": 7.511551355775824e-06, "loss": 0.2999, "step": 335820 }, { "epoch": 1.9962432607545577, "grad_norm": 2.9059202671051025, "learning_rate": 7.511371937774056e-06, "loss": 0.2816, "step": 335830 }, { "epoch": 1.9963027028312261, "grad_norm": 3.9837136268615723, "learning_rate": 7.511192515447406e-06, "loss": 0.2758, "step": 335840 }, { "epoch": 1.9963621449078945, "grad_norm": 5.079949855804443, "learning_rate": 7.511013088796182e-06, "loss": 0.2609, "step": 335850 }, { "epoch": 1.996421586984563, "grad_norm": 4.766582489013672, "learning_rate": 7.510833657820693e-06, "loss": 0.2603, "step": 335860 }, { "epoch": 1.9964810290612314, "grad_norm": 6.1522650718688965, "learning_rate": 7.510654222521252e-06, "loss": 0.2571, "step": 335870 }, { "epoch": 1.9965404711378998, "grad_norm": 5.6223015785217285, "learning_rate": 7.510474782898161e-06, "loss": 0.2601, "step": 335880 }, { "epoch": 1.9965999132145682, "grad_norm": 4.479264259338379, "learning_rate": 7.510295338951736e-06, "loss": 0.2432, "step": 335890 }, { "epoch": 1.9966593552912366, "grad_norm": 5.219557762145996, "learning_rate": 7.510115890682283e-06, "loss": 0.2698, "step": 335900 }, { "epoch": 1.9967187973679048, "grad_norm": 4.022284507751465, "learning_rate": 7.509936438090108e-06, "loss": 0.2583, "step": 335910 }, { "epoch": 1.9967782394445732, "grad_norm": 4.028975009918213, "learning_rate": 7.509756981175527e-06, "loss": 0.3025, "step": 335920 }, { "epoch": 1.9968376815212416, "grad_norm": 4.333677768707275, "learning_rate": 7.509577519938842e-06, "loss": 0.276, "step": 335930 }, { "epoch": 1.99689712359791, "grad_norm": 5.018249034881592, "learning_rate": 7.509398054380366e-06, "loss": 0.246, "step": 335940 }, { "epoch": 1.9969565656745782, "grad_norm": 4.982573509216309, "learning_rate": 7.509218584500407e-06, "loss": 0.2581, "step": 335950 }, { "epoch": 1.9970160077512467, "grad_norm": 6.4993672370910645, "learning_rate": 7.509039110299275e-06, "loss": 0.2699, "step": 335960 }, { "epoch": 1.997075449827915, "grad_norm": 4.472464561462402, "learning_rate": 7.508859631777276e-06, "loss": 0.3142, "step": 335970 }, { "epoch": 1.9971348919045835, "grad_norm": 3.6726977825164795, "learning_rate": 7.508680148934723e-06, "loss": 0.2547, "step": 335980 }, { "epoch": 1.997194333981252, "grad_norm": 5.5794572830200195, "learning_rate": 7.508500661771924e-06, "loss": 0.2744, "step": 335990 }, { "epoch": 1.9972537760579203, "grad_norm": 4.5468268394470215, "learning_rate": 7.5083211702891865e-06, "loss": 0.2547, "step": 336000 }, { "epoch": 1.9973132181345887, "grad_norm": 5.041313171386719, "learning_rate": 7.508141674486821e-06, "loss": 0.2422, "step": 336010 }, { "epoch": 1.9973726602112571, "grad_norm": 3.974959373474121, "learning_rate": 7.507962174365137e-06, "loss": 0.2416, "step": 336020 }, { "epoch": 1.9974321022879256, "grad_norm": 4.020918369293213, "learning_rate": 7.507782669924442e-06, "loss": 0.264, "step": 336030 }, { "epoch": 1.997491544364594, "grad_norm": 5.362493515014648, "learning_rate": 7.507603161165046e-06, "loss": 0.2487, "step": 336040 }, { "epoch": 1.9975509864412624, "grad_norm": 6.3074259757995605, "learning_rate": 7.5074236480872585e-06, "loss": 0.2763, "step": 336050 }, { "epoch": 1.9976104285179308, "grad_norm": 5.674617767333984, "learning_rate": 7.507244130691389e-06, "loss": 0.2546, "step": 336060 }, { "epoch": 1.9976698705945992, "grad_norm": 5.891424179077148, "learning_rate": 7.5070646089777446e-06, "loss": 0.2642, "step": 336070 }, { "epoch": 1.9977293126712676, "grad_norm": 4.9969096183776855, "learning_rate": 7.5068850829466355e-06, "loss": 0.2531, "step": 336080 }, { "epoch": 1.9977887547479358, "grad_norm": 5.577702522277832, "learning_rate": 7.506705552598372e-06, "loss": 0.2627, "step": 336090 }, { "epoch": 1.9978481968246042, "grad_norm": 4.725648403167725, "learning_rate": 7.506526017933263e-06, "loss": 0.2797, "step": 336100 }, { "epoch": 1.9979076389012727, "grad_norm": 4.123737812042236, "learning_rate": 7.506346478951616e-06, "loss": 0.2701, "step": 336110 }, { "epoch": 1.997967080977941, "grad_norm": 6.124706745147705, "learning_rate": 7.506166935653743e-06, "loss": 0.2608, "step": 336120 }, { "epoch": 1.9980265230546095, "grad_norm": 4.762934684753418, "learning_rate": 7.5059873880399505e-06, "loss": 0.2659, "step": 336130 }, { "epoch": 1.9980859651312777, "grad_norm": 4.461690425872803, "learning_rate": 7.505807836110548e-06, "loss": 0.2709, "step": 336140 }, { "epoch": 1.998145407207946, "grad_norm": 4.568955898284912, "learning_rate": 7.505628279865847e-06, "loss": 0.2792, "step": 336150 }, { "epoch": 1.9982048492846145, "grad_norm": 6.662491798400879, "learning_rate": 7.5054487193061545e-06, "loss": 0.269, "step": 336160 }, { "epoch": 1.998264291361283, "grad_norm": 5.745818138122559, "learning_rate": 7.505269154431778e-06, "loss": 0.3026, "step": 336170 }, { "epoch": 1.9983237334379513, "grad_norm": 4.733919143676758, "learning_rate": 7.5050895852430326e-06, "loss": 0.2689, "step": 336180 }, { "epoch": 1.9983831755146197, "grad_norm": 3.698316812515259, "learning_rate": 7.50491001174022e-06, "loss": 0.2592, "step": 336190 }, { "epoch": 1.9984426175912882, "grad_norm": 5.200448036193848, "learning_rate": 7.504730433923657e-06, "loss": 0.2454, "step": 336200 }, { "epoch": 1.9985020596679566, "grad_norm": 4.6114397048950195, "learning_rate": 7.5045508517936485e-06, "loss": 0.2804, "step": 336210 }, { "epoch": 1.998561501744625, "grad_norm": 6.733273983001709, "learning_rate": 7.5043712653505056e-06, "loss": 0.2966, "step": 336220 }, { "epoch": 1.9986209438212934, "grad_norm": 4.109350204467773, "learning_rate": 7.504191674594535e-06, "loss": 0.2533, "step": 336230 }, { "epoch": 1.9986803858979618, "grad_norm": 5.1177496910095215, "learning_rate": 7.504012079526047e-06, "loss": 0.257, "step": 336240 }, { "epoch": 1.9987398279746302, "grad_norm": 5.423490047454834, "learning_rate": 7.5038324801453535e-06, "loss": 0.2582, "step": 336250 }, { "epoch": 1.9987992700512986, "grad_norm": 4.218485355377197, "learning_rate": 7.503652876452761e-06, "loss": 0.2641, "step": 336260 }, { "epoch": 1.998858712127967, "grad_norm": 4.706046104431152, "learning_rate": 7.503473268448578e-06, "loss": 0.2804, "step": 336270 }, { "epoch": 1.9989181542046353, "grad_norm": 4.432046890258789, "learning_rate": 7.503293656133117e-06, "loss": 0.2524, "step": 336280 }, { "epoch": 1.9989775962813037, "grad_norm": 4.850768089294434, "learning_rate": 7.503114039506685e-06, "loss": 0.2755, "step": 336290 }, { "epoch": 1.999037038357972, "grad_norm": 4.844592094421387, "learning_rate": 7.5029344185695914e-06, "loss": 0.2971, "step": 336300 }, { "epoch": 1.9990964804346405, "grad_norm": 5.6885857582092285, "learning_rate": 7.502754793322146e-06, "loss": 0.276, "step": 336310 }, { "epoch": 1.9991559225113087, "grad_norm": 6.879983425140381, "learning_rate": 7.5025751637646604e-06, "loss": 0.2611, "step": 336320 }, { "epoch": 1.999215364587977, "grad_norm": 3.9634861946105957, "learning_rate": 7.50239552989744e-06, "loss": 0.2612, "step": 336330 }, { "epoch": 1.9992748066646455, "grad_norm": 5.811758995056152, "learning_rate": 7.502215891720796e-06, "loss": 0.2896, "step": 336340 }, { "epoch": 1.999334248741314, "grad_norm": 4.312726974487305, "learning_rate": 7.502036249235038e-06, "loss": 0.2604, "step": 336350 }, { "epoch": 1.9993936908179823, "grad_norm": 5.461699485778809, "learning_rate": 7.501856602440476e-06, "loss": 0.286, "step": 336360 }, { "epoch": 1.9994531328946508, "grad_norm": 5.112000942230225, "learning_rate": 7.501676951337415e-06, "loss": 0.2486, "step": 336370 }, { "epoch": 1.9995125749713192, "grad_norm": 4.711252689361572, "learning_rate": 7.501497295926172e-06, "loss": 0.2543, "step": 336380 }, { "epoch": 1.9995720170479876, "grad_norm": 6.485625743865967, "learning_rate": 7.501317636207051e-06, "loss": 0.2942, "step": 336390 }, { "epoch": 1.999631459124656, "grad_norm": 5.731174468994141, "learning_rate": 7.5011379721803614e-06, "loss": 0.2506, "step": 336400 }, { "epoch": 1.9996909012013244, "grad_norm": 4.240413188934326, "learning_rate": 7.500958303846413e-06, "loss": 0.2714, "step": 336410 }, { "epoch": 1.9997503432779928, "grad_norm": 5.706722259521484, "learning_rate": 7.500778631205518e-06, "loss": 0.2661, "step": 336420 }, { "epoch": 1.9998097853546613, "grad_norm": 4.8924994468688965, "learning_rate": 7.5005989542579826e-06, "loss": 0.2662, "step": 336430 }, { "epoch": 1.9998692274313297, "grad_norm": 4.73484992980957, "learning_rate": 7.500419273004118e-06, "loss": 0.2563, "step": 336440 }, { "epoch": 1.999928669507998, "grad_norm": 5.13757848739624, "learning_rate": 7.5002395874442335e-06, "loss": 0.2672, "step": 336450 }, { "epoch": 1.9999881115846663, "grad_norm": 4.198154449462891, "learning_rate": 7.500059897578638e-06, "loss": 0.2967, "step": 336460 }, { "epoch": 2.000047553661335, "grad_norm": 4.547418594360352, "learning_rate": 7.49988020340764e-06, "loss": 0.1548, "step": 336470 }, { "epoch": 2.0001069957380033, "grad_norm": 3.0905063152313232, "learning_rate": 7.49970050493155e-06, "loss": 0.1682, "step": 336480 }, { "epoch": 2.0001664378146713, "grad_norm": 4.213057518005371, "learning_rate": 7.4995208021506785e-06, "loss": 0.1608, "step": 336490 }, { "epoch": 2.0002258798913397, "grad_norm": 3.193804979324341, "learning_rate": 7.499341095065333e-06, "loss": 0.1565, "step": 336500 }, { "epoch": 2.000285321968008, "grad_norm": 3.6131808757781982, "learning_rate": 7.499161383675826e-06, "loss": 0.1754, "step": 336510 }, { "epoch": 2.0003447640446765, "grad_norm": 4.292726993560791, "learning_rate": 7.498981667982463e-06, "loss": 0.1668, "step": 336520 }, { "epoch": 2.000404206121345, "grad_norm": 4.122040748596191, "learning_rate": 7.498801947985555e-06, "loss": 0.1597, "step": 336530 }, { "epoch": 2.0004636481980134, "grad_norm": 3.673266887664795, "learning_rate": 7.498622223685413e-06, "loss": 0.1365, "step": 336540 }, { "epoch": 2.000523090274682, "grad_norm": 3.0078861713409424, "learning_rate": 7.498442495082346e-06, "loss": 0.1495, "step": 336550 }, { "epoch": 2.00058253235135, "grad_norm": 4.988905429840088, "learning_rate": 7.49826276217666e-06, "loss": 0.1583, "step": 336560 }, { "epoch": 2.0006419744280186, "grad_norm": 3.5542099475860596, "learning_rate": 7.49808302496867e-06, "loss": 0.1431, "step": 336570 }, { "epoch": 2.000701416504687, "grad_norm": 5.490033149719238, "learning_rate": 7.497903283458683e-06, "loss": 0.157, "step": 336580 }, { "epoch": 2.0007608585813554, "grad_norm": 3.30997896194458, "learning_rate": 7.497723537647008e-06, "loss": 0.1295, "step": 336590 }, { "epoch": 2.000820300658024, "grad_norm": 4.218826770782471, "learning_rate": 7.4975437875339555e-06, "loss": 0.1697, "step": 336600 }, { "epoch": 2.0008797427346923, "grad_norm": 3.9821152687072754, "learning_rate": 7.497364033119834e-06, "loss": 0.166, "step": 336610 }, { "epoch": 2.0009391848113607, "grad_norm": 3.157111883163452, "learning_rate": 7.497184274404952e-06, "loss": 0.1697, "step": 336620 }, { "epoch": 2.000998626888029, "grad_norm": 5.204813003540039, "learning_rate": 7.497004511389623e-06, "loss": 0.1551, "step": 336630 }, { "epoch": 2.0010580689646975, "grad_norm": 4.650130271911621, "learning_rate": 7.496824744074153e-06, "loss": 0.1688, "step": 336640 }, { "epoch": 2.001117511041366, "grad_norm": 3.8339736461639404, "learning_rate": 7.496644972458855e-06, "loss": 0.1543, "step": 336650 }, { "epoch": 2.0011769531180343, "grad_norm": 3.837204694747925, "learning_rate": 7.496465196544034e-06, "loss": 0.1637, "step": 336660 }, { "epoch": 2.0012363951947023, "grad_norm": 3.345653533935547, "learning_rate": 7.496285416330003e-06, "loss": 0.1426, "step": 336670 }, { "epoch": 2.0012958372713707, "grad_norm": 4.080896377563477, "learning_rate": 7.4961056318170724e-06, "loss": 0.15, "step": 336680 }, { "epoch": 2.001355279348039, "grad_norm": 5.121642589569092, "learning_rate": 7.495925843005547e-06, "loss": 0.1676, "step": 336690 }, { "epoch": 2.0014147214247076, "grad_norm": 3.62117600440979, "learning_rate": 7.495746049895741e-06, "loss": 0.1558, "step": 336700 }, { "epoch": 2.001474163501376, "grad_norm": 5.299684047698975, "learning_rate": 7.495566252487964e-06, "loss": 0.1684, "step": 336710 }, { "epoch": 2.0015336055780444, "grad_norm": 3.6023857593536377, "learning_rate": 7.495386450782521e-06, "loss": 0.1391, "step": 336720 }, { "epoch": 2.001593047654713, "grad_norm": 2.9080798625946045, "learning_rate": 7.495206644779727e-06, "loss": 0.1463, "step": 336730 }, { "epoch": 2.001652489731381, "grad_norm": 3.8367583751678467, "learning_rate": 7.495026834479888e-06, "loss": 0.1498, "step": 336740 }, { "epoch": 2.0017119318080496, "grad_norm": 4.617233753204346, "learning_rate": 7.494847019883317e-06, "loss": 0.1654, "step": 336750 }, { "epoch": 2.001771373884718, "grad_norm": 3.127842426300049, "learning_rate": 7.49466720099032e-06, "loss": 0.1233, "step": 336760 }, { "epoch": 2.0018308159613865, "grad_norm": 5.179683208465576, "learning_rate": 7.4944873778012096e-06, "loss": 0.1575, "step": 336770 }, { "epoch": 2.001890258038055, "grad_norm": 3.454150676727295, "learning_rate": 7.494307550316293e-06, "loss": 0.1587, "step": 336780 }, { "epoch": 2.0019497001147233, "grad_norm": 3.363412618637085, "learning_rate": 7.494127718535882e-06, "loss": 0.1468, "step": 336790 }, { "epoch": 2.0020091421913917, "grad_norm": 4.413885593414307, "learning_rate": 7.493947882460286e-06, "loss": 0.1406, "step": 336800 }, { "epoch": 2.00206858426806, "grad_norm": 4.466533660888672, "learning_rate": 7.493768042089814e-06, "loss": 0.1437, "step": 336810 }, { "epoch": 2.0021280263447285, "grad_norm": 3.821601390838623, "learning_rate": 7.493588197424775e-06, "loss": 0.1604, "step": 336820 }, { "epoch": 2.002187468421397, "grad_norm": 6.143558502197266, "learning_rate": 7.49340834846548e-06, "loss": 0.1558, "step": 336830 }, { "epoch": 2.0022469104980654, "grad_norm": 3.235079050064087, "learning_rate": 7.493228495212239e-06, "loss": 0.1456, "step": 336840 }, { "epoch": 2.0023063525747338, "grad_norm": 3.898139715194702, "learning_rate": 7.493048637665359e-06, "loss": 0.1575, "step": 336850 }, { "epoch": 2.0023657946514017, "grad_norm": 3.816723585128784, "learning_rate": 7.492868775825153e-06, "loss": 0.1606, "step": 336860 }, { "epoch": 2.00242523672807, "grad_norm": 3.737532138824463, "learning_rate": 7.49268890969193e-06, "loss": 0.1513, "step": 336870 }, { "epoch": 2.0024846788047386, "grad_norm": 5.003561973571777, "learning_rate": 7.492509039265999e-06, "loss": 0.1466, "step": 336880 }, { "epoch": 2.002544120881407, "grad_norm": 3.236112594604492, "learning_rate": 7.49232916454767e-06, "loss": 0.1536, "step": 336890 }, { "epoch": 2.0026035629580754, "grad_norm": 3.9530792236328125, "learning_rate": 7.492149285537253e-06, "loss": 0.167, "step": 336900 }, { "epoch": 2.002663005034744, "grad_norm": 3.1061885356903076, "learning_rate": 7.491969402235058e-06, "loss": 0.1387, "step": 336910 }, { "epoch": 2.0027224471114122, "grad_norm": 3.25852108001709, "learning_rate": 7.4917895146413935e-06, "loss": 0.1555, "step": 336920 }, { "epoch": 2.0027818891880806, "grad_norm": 4.141733646392822, "learning_rate": 7.491609622756571e-06, "loss": 0.1725, "step": 336930 }, { "epoch": 2.002841331264749, "grad_norm": 3.920772075653076, "learning_rate": 7.491429726580899e-06, "loss": 0.1671, "step": 336940 }, { "epoch": 2.0029007733414175, "grad_norm": 3.9495036602020264, "learning_rate": 7.491249826114687e-06, "loss": 0.1381, "step": 336950 }, { "epoch": 2.002960215418086, "grad_norm": 5.028132438659668, "learning_rate": 7.491069921358245e-06, "loss": 0.1639, "step": 336960 }, { "epoch": 2.0030196574947543, "grad_norm": 3.574799060821533, "learning_rate": 7.4908900123118855e-06, "loss": 0.1366, "step": 336970 }, { "epoch": 2.0030790995714227, "grad_norm": 4.861418724060059, "learning_rate": 7.490710098975914e-06, "loss": 0.1669, "step": 336980 }, { "epoch": 2.003138541648091, "grad_norm": 3.3420984745025635, "learning_rate": 7.4905301813506435e-06, "loss": 0.1568, "step": 336990 }, { "epoch": 2.0031979837247595, "grad_norm": 3.856901168823242, "learning_rate": 7.490350259436384e-06, "loss": 0.1543, "step": 337000 }, { "epoch": 2.003257425801428, "grad_norm": 4.192715644836426, "learning_rate": 7.490170333233443e-06, "loss": 0.1391, "step": 337010 }, { "epoch": 2.0033168678780964, "grad_norm": 4.375218391418457, "learning_rate": 7.489990402742132e-06, "loss": 0.1594, "step": 337020 }, { "epoch": 2.003376309954765, "grad_norm": 4.488522529602051, "learning_rate": 7.48981046796276e-06, "loss": 0.1539, "step": 337030 }, { "epoch": 2.0034357520314328, "grad_norm": 3.691706895828247, "learning_rate": 7.489630528895638e-06, "loss": 0.1553, "step": 337040 }, { "epoch": 2.003495194108101, "grad_norm": 4.310383319854736, "learning_rate": 7.489450585541075e-06, "loss": 0.1613, "step": 337050 }, { "epoch": 2.0035546361847696, "grad_norm": 4.848841667175293, "learning_rate": 7.489270637899381e-06, "loss": 0.16, "step": 337060 }, { "epoch": 2.003614078261438, "grad_norm": 5.622095584869385, "learning_rate": 7.489090685970866e-06, "loss": 0.1707, "step": 337070 }, { "epoch": 2.0036735203381064, "grad_norm": 5.016031742095947, "learning_rate": 7.488910729755839e-06, "loss": 0.1706, "step": 337080 }, { "epoch": 2.003732962414775, "grad_norm": 3.8983781337738037, "learning_rate": 7.488730769254611e-06, "loss": 0.1379, "step": 337090 }, { "epoch": 2.0037924044914432, "grad_norm": 3.731595993041992, "learning_rate": 7.488550804467492e-06, "loss": 0.1585, "step": 337100 }, { "epoch": 2.0038518465681117, "grad_norm": 5.4217634201049805, "learning_rate": 7.488370835394791e-06, "loss": 0.168, "step": 337110 }, { "epoch": 2.00391128864478, "grad_norm": 4.905737400054932, "learning_rate": 7.4881908620368195e-06, "loss": 0.1706, "step": 337120 }, { "epoch": 2.0039707307214485, "grad_norm": 3.64119291305542, "learning_rate": 7.488010884393886e-06, "loss": 0.1589, "step": 337130 }, { "epoch": 2.004030172798117, "grad_norm": 3.775287389755249, "learning_rate": 7.487830902466301e-06, "loss": 0.1496, "step": 337140 }, { "epoch": 2.0040896148747853, "grad_norm": 3.9712977409362793, "learning_rate": 7.487650916254374e-06, "loss": 0.1512, "step": 337150 }, { "epoch": 2.0041490569514537, "grad_norm": 4.135621070861816, "learning_rate": 7.4874709257584166e-06, "loss": 0.1778, "step": 337160 }, { "epoch": 2.004208499028122, "grad_norm": 3.825510263442993, "learning_rate": 7.487290930978736e-06, "loss": 0.1263, "step": 337170 }, { "epoch": 2.0042679411047906, "grad_norm": 4.477890491485596, "learning_rate": 7.487110931915643e-06, "loss": 0.1477, "step": 337180 }, { "epoch": 2.004327383181459, "grad_norm": 3.684581995010376, "learning_rate": 7.48693092856945e-06, "loss": 0.152, "step": 337190 }, { "epoch": 2.0043868252581274, "grad_norm": 3.5906028747558594, "learning_rate": 7.486750920940464e-06, "loss": 0.1545, "step": 337200 }, { "epoch": 2.004446267334796, "grad_norm": 4.283277988433838, "learning_rate": 7.486570909028997e-06, "loss": 0.1584, "step": 337210 }, { "epoch": 2.004505709411464, "grad_norm": 4.749707221984863, "learning_rate": 7.486390892835358e-06, "loss": 0.1688, "step": 337220 }, { "epoch": 2.004565151488132, "grad_norm": 5.573076248168945, "learning_rate": 7.486210872359858e-06, "loss": 0.1774, "step": 337230 }, { "epoch": 2.0046245935648006, "grad_norm": 3.994264841079712, "learning_rate": 7.486030847602804e-06, "loss": 0.1739, "step": 337240 }, { "epoch": 2.004684035641469, "grad_norm": 4.483393669128418, "learning_rate": 7.485850818564511e-06, "loss": 0.1546, "step": 337250 }, { "epoch": 2.0047434777181374, "grad_norm": 4.018766403198242, "learning_rate": 7.485670785245285e-06, "loss": 0.1443, "step": 337260 }, { "epoch": 2.004802919794806, "grad_norm": 5.235687732696533, "learning_rate": 7.485490747645437e-06, "loss": 0.1551, "step": 337270 }, { "epoch": 2.0048623618714743, "grad_norm": 3.4683306217193604, "learning_rate": 7.485310705765278e-06, "loss": 0.1739, "step": 337280 }, { "epoch": 2.0049218039481427, "grad_norm": 5.394737720489502, "learning_rate": 7.485130659605115e-06, "loss": 0.1696, "step": 337290 }, { "epoch": 2.004981246024811, "grad_norm": 5.356527328491211, "learning_rate": 7.484950609165263e-06, "loss": 0.1483, "step": 337300 }, { "epoch": 2.0050406881014795, "grad_norm": 4.896640777587891, "learning_rate": 7.484770554446029e-06, "loss": 0.155, "step": 337310 }, { "epoch": 2.005100130178148, "grad_norm": 3.5172677040100098, "learning_rate": 7.484590495447723e-06, "loss": 0.1568, "step": 337320 }, { "epoch": 2.0051595722548163, "grad_norm": 4.554403781890869, "learning_rate": 7.484410432170658e-06, "loss": 0.1526, "step": 337330 }, { "epoch": 2.0052190143314848, "grad_norm": 4.083191871643066, "learning_rate": 7.484230364615139e-06, "loss": 0.1465, "step": 337340 }, { "epoch": 2.005278456408153, "grad_norm": 4.007749557495117, "learning_rate": 7.484050292781481e-06, "loss": 0.1741, "step": 337350 }, { "epoch": 2.0053378984848216, "grad_norm": 6.169216632843018, "learning_rate": 7.48387021666999e-06, "loss": 0.15, "step": 337360 }, { "epoch": 2.00539734056149, "grad_norm": 3.7120440006256104, "learning_rate": 7.48369013628098e-06, "loss": 0.1412, "step": 337370 }, { "epoch": 2.0054567826381584, "grad_norm": 3.776686191558838, "learning_rate": 7.4835100516147585e-06, "loss": 0.1564, "step": 337380 }, { "epoch": 2.005516224714827, "grad_norm": 4.8776092529296875, "learning_rate": 7.483329962671637e-06, "loss": 0.1533, "step": 337390 }, { "epoch": 2.0055756667914952, "grad_norm": 3.2246203422546387, "learning_rate": 7.483149869451923e-06, "loss": 0.1512, "step": 337400 }, { "epoch": 2.005635108868163, "grad_norm": 3.656022310256958, "learning_rate": 7.48296977195593e-06, "loss": 0.1628, "step": 337410 }, { "epoch": 2.0056945509448316, "grad_norm": 4.524472236633301, "learning_rate": 7.482789670183968e-06, "loss": 0.135, "step": 337420 }, { "epoch": 2.0057539930215, "grad_norm": 3.970733642578125, "learning_rate": 7.482609564136344e-06, "loss": 0.1488, "step": 337430 }, { "epoch": 2.0058134350981685, "grad_norm": 5.827749252319336, "learning_rate": 7.48242945381337e-06, "loss": 0.1598, "step": 337440 }, { "epoch": 2.005872877174837, "grad_norm": 6.022874355316162, "learning_rate": 7.482249339215357e-06, "loss": 0.1758, "step": 337450 }, { "epoch": 2.0059323192515053, "grad_norm": 4.349006652832031, "learning_rate": 7.482069220342616e-06, "loss": 0.1686, "step": 337460 }, { "epoch": 2.0059917613281737, "grad_norm": 4.402012348175049, "learning_rate": 7.481889097195453e-06, "loss": 0.1427, "step": 337470 }, { "epoch": 2.006051203404842, "grad_norm": 4.575646877288818, "learning_rate": 7.481708969774182e-06, "loss": 0.1557, "step": 337480 }, { "epoch": 2.0061106454815105, "grad_norm": 4.573038578033447, "learning_rate": 7.481528838079113e-06, "loss": 0.1536, "step": 337490 }, { "epoch": 2.006170087558179, "grad_norm": 4.295996189117432, "learning_rate": 7.481348702110554e-06, "loss": 0.1639, "step": 337500 }, { "epoch": 2.0062295296348474, "grad_norm": 3.676530361175537, "learning_rate": 7.4811685618688155e-06, "loss": 0.1564, "step": 337510 }, { "epoch": 2.0062889717115158, "grad_norm": 3.436903715133667, "learning_rate": 7.48098841735421e-06, "loss": 0.1315, "step": 337520 }, { "epoch": 2.006348413788184, "grad_norm": 4.608948230743408, "learning_rate": 7.4808082685670466e-06, "loss": 0.158, "step": 337530 }, { "epoch": 2.0064078558648526, "grad_norm": 4.063488483428955, "learning_rate": 7.480628115507636e-06, "loss": 0.1398, "step": 337540 }, { "epoch": 2.006467297941521, "grad_norm": 4.662167072296143, "learning_rate": 7.480447958176287e-06, "loss": 0.1626, "step": 337550 }, { "epoch": 2.0065267400181894, "grad_norm": 3.715254306793213, "learning_rate": 7.480267796573311e-06, "loss": 0.1628, "step": 337560 }, { "epoch": 2.006586182094858, "grad_norm": 3.240670919418335, "learning_rate": 7.4800876306990165e-06, "loss": 0.1606, "step": 337570 }, { "epoch": 2.0066456241715263, "grad_norm": 4.376578330993652, "learning_rate": 7.479907460553717e-06, "loss": 0.1717, "step": 337580 }, { "epoch": 2.0067050662481947, "grad_norm": 3.3520474433898926, "learning_rate": 7.47972728613772e-06, "loss": 0.1584, "step": 337590 }, { "epoch": 2.0067645083248626, "grad_norm": 4.738522529602051, "learning_rate": 7.479547107451336e-06, "loss": 0.1641, "step": 337600 }, { "epoch": 2.006823950401531, "grad_norm": 3.88922381401062, "learning_rate": 7.479366924494877e-06, "loss": 0.1462, "step": 337610 }, { "epoch": 2.0068833924781995, "grad_norm": 5.372137069702148, "learning_rate": 7.4791867372686526e-06, "loss": 0.131, "step": 337620 }, { "epoch": 2.006942834554868, "grad_norm": 4.944807052612305, "learning_rate": 7.479006545772971e-06, "loss": 0.1468, "step": 337630 }, { "epoch": 2.0070022766315363, "grad_norm": 4.480158805847168, "learning_rate": 7.478826350008146e-06, "loss": 0.1631, "step": 337640 }, { "epoch": 2.0070617187082047, "grad_norm": 3.3526535034179688, "learning_rate": 7.478646149974486e-06, "loss": 0.152, "step": 337650 }, { "epoch": 2.007121160784873, "grad_norm": 2.183053970336914, "learning_rate": 7.478465945672302e-06, "loss": 0.1383, "step": 337660 }, { "epoch": 2.0071806028615415, "grad_norm": 4.144363880157471, "learning_rate": 7.4782857371019034e-06, "loss": 0.1631, "step": 337670 }, { "epoch": 2.00724004493821, "grad_norm": 3.3235816955566406, "learning_rate": 7.4781055242636015e-06, "loss": 0.1557, "step": 337680 }, { "epoch": 2.0072994870148784, "grad_norm": 4.2630767822265625, "learning_rate": 7.477925307157707e-06, "loss": 0.1701, "step": 337690 }, { "epoch": 2.007358929091547, "grad_norm": 3.7405364513397217, "learning_rate": 7.4777450857845265e-06, "loss": 0.1501, "step": 337700 }, { "epoch": 2.007418371168215, "grad_norm": 4.0279340744018555, "learning_rate": 7.477564860144376e-06, "loss": 0.1567, "step": 337710 }, { "epoch": 2.0074778132448836, "grad_norm": 4.776032447814941, "learning_rate": 7.477384630237563e-06, "loss": 0.1675, "step": 337720 }, { "epoch": 2.007537255321552, "grad_norm": 5.2756853103637695, "learning_rate": 7.477204396064396e-06, "loss": 0.1659, "step": 337730 }, { "epoch": 2.0075966973982204, "grad_norm": 3.78421688079834, "learning_rate": 7.47702415762519e-06, "loss": 0.1329, "step": 337740 }, { "epoch": 2.007656139474889, "grad_norm": 4.603847980499268, "learning_rate": 7.476843914920251e-06, "loss": 0.1661, "step": 337750 }, { "epoch": 2.0077155815515573, "grad_norm": 3.8449158668518066, "learning_rate": 7.476663667949892e-06, "loss": 0.1767, "step": 337760 }, { "epoch": 2.0077750236282257, "grad_norm": 4.228243350982666, "learning_rate": 7.476483416714423e-06, "loss": 0.1557, "step": 337770 }, { "epoch": 2.0078344657048937, "grad_norm": 4.930793762207031, "learning_rate": 7.4763031612141535e-06, "loss": 0.1515, "step": 337780 }, { "epoch": 2.007893907781562, "grad_norm": 5.694230079650879, "learning_rate": 7.4761229014493944e-06, "loss": 0.156, "step": 337790 }, { "epoch": 2.0079533498582305, "grad_norm": 6.332609176635742, "learning_rate": 7.475942637420457e-06, "loss": 0.153, "step": 337800 }, { "epoch": 2.008012791934899, "grad_norm": 3.8754050731658936, "learning_rate": 7.47576236912765e-06, "loss": 0.1579, "step": 337810 }, { "epoch": 2.0080722340115673, "grad_norm": 5.215613842010498, "learning_rate": 7.475582096571286e-06, "loss": 0.1648, "step": 337820 }, { "epoch": 2.0081316760882357, "grad_norm": 3.7967004776000977, "learning_rate": 7.4754018197516735e-06, "loss": 0.1606, "step": 337830 }, { "epoch": 2.008191118164904, "grad_norm": 4.961134433746338, "learning_rate": 7.475221538669123e-06, "loss": 0.1475, "step": 337840 }, { "epoch": 2.0082505602415726, "grad_norm": 3.1137075424194336, "learning_rate": 7.475041253323947e-06, "loss": 0.1727, "step": 337850 }, { "epoch": 2.008310002318241, "grad_norm": 5.060184001922607, "learning_rate": 7.474860963716453e-06, "loss": 0.1595, "step": 337860 }, { "epoch": 2.0083694443949094, "grad_norm": 3.5866167545318604, "learning_rate": 7.474680669846954e-06, "loss": 0.1445, "step": 337870 }, { "epoch": 2.008428886471578, "grad_norm": 4.084110260009766, "learning_rate": 7.4745003717157606e-06, "loss": 0.1488, "step": 337880 }, { "epoch": 2.008488328548246, "grad_norm": 4.1843647956848145, "learning_rate": 7.474320069323181e-06, "loss": 0.1686, "step": 337890 }, { "epoch": 2.0085477706249146, "grad_norm": 4.464334011077881, "learning_rate": 7.474139762669528e-06, "loss": 0.157, "step": 337900 }, { "epoch": 2.008607212701583, "grad_norm": 4.324191093444824, "learning_rate": 7.473959451755111e-06, "loss": 0.162, "step": 337910 }, { "epoch": 2.0086666547782515, "grad_norm": 6.867209434509277, "learning_rate": 7.47377913658024e-06, "loss": 0.1776, "step": 337920 }, { "epoch": 2.00872609685492, "grad_norm": 2.7447574138641357, "learning_rate": 7.4735988171452265e-06, "loss": 0.1467, "step": 337930 }, { "epoch": 2.0087855389315883, "grad_norm": 4.223226070404053, "learning_rate": 7.473418493450381e-06, "loss": 0.1637, "step": 337940 }, { "epoch": 2.0088449810082567, "grad_norm": 4.3433356285095215, "learning_rate": 7.4732381654960125e-06, "loss": 0.1573, "step": 337950 }, { "epoch": 2.0089044230849247, "grad_norm": 3.3359193801879883, "learning_rate": 7.473057833282433e-06, "loss": 0.1398, "step": 337960 }, { "epoch": 2.008963865161593, "grad_norm": 3.536823034286499, "learning_rate": 7.472877496809954e-06, "loss": 0.1499, "step": 337970 }, { "epoch": 2.0090233072382615, "grad_norm": 4.6848859786987305, "learning_rate": 7.472697156078885e-06, "loss": 0.1577, "step": 337980 }, { "epoch": 2.00908274931493, "grad_norm": 3.844851016998291, "learning_rate": 7.472516811089535e-06, "loss": 0.1542, "step": 337990 }, { "epoch": 2.0091421913915983, "grad_norm": 3.3264682292938232, "learning_rate": 7.472336461842218e-06, "loss": 0.1325, "step": 338000 }, { "epoch": 2.0092016334682667, "grad_norm": 3.6531355381011963, "learning_rate": 7.472156108337241e-06, "loss": 0.1543, "step": 338010 }, { "epoch": 2.009261075544935, "grad_norm": 3.7325222492218018, "learning_rate": 7.471975750574916e-06, "loss": 0.1471, "step": 338020 }, { "epoch": 2.0093205176216036, "grad_norm": 4.744961261749268, "learning_rate": 7.471795388555555e-06, "loss": 0.1448, "step": 338030 }, { "epoch": 2.009379959698272, "grad_norm": 4.234821796417236, "learning_rate": 7.471615022279467e-06, "loss": 0.1573, "step": 338040 }, { "epoch": 2.0094394017749404, "grad_norm": 3.384413957595825, "learning_rate": 7.4714346517469625e-06, "loss": 0.1273, "step": 338050 }, { "epoch": 2.009498843851609, "grad_norm": 4.568802356719971, "learning_rate": 7.471254276958353e-06, "loss": 0.1509, "step": 338060 }, { "epoch": 2.0095582859282772, "grad_norm": 4.1657843589782715, "learning_rate": 7.4710738979139485e-06, "loss": 0.1496, "step": 338070 }, { "epoch": 2.0096177280049456, "grad_norm": 4.132532119750977, "learning_rate": 7.470893514614061e-06, "loss": 0.1581, "step": 338080 }, { "epoch": 2.009677170081614, "grad_norm": 4.933383464813232, "learning_rate": 7.4707131270589986e-06, "loss": 0.1749, "step": 338090 }, { "epoch": 2.0097366121582825, "grad_norm": 4.293544292449951, "learning_rate": 7.470532735249074e-06, "loss": 0.1629, "step": 338100 }, { "epoch": 2.009796054234951, "grad_norm": 4.746092796325684, "learning_rate": 7.470352339184598e-06, "loss": 0.1513, "step": 338110 }, { "epoch": 2.0098554963116193, "grad_norm": 4.499486446380615, "learning_rate": 7.470171938865879e-06, "loss": 0.1704, "step": 338120 }, { "epoch": 2.0099149383882877, "grad_norm": 3.345309257507324, "learning_rate": 7.4699915342932306e-06, "loss": 0.1367, "step": 338130 }, { "epoch": 2.009974380464956, "grad_norm": 3.617560863494873, "learning_rate": 7.469811125466961e-06, "loss": 0.1444, "step": 338140 }, { "epoch": 2.010033822541624, "grad_norm": 3.8636624813079834, "learning_rate": 7.469630712387382e-06, "loss": 0.1519, "step": 338150 }, { "epoch": 2.0100932646182925, "grad_norm": 3.6809306144714355, "learning_rate": 7.469450295054806e-06, "loss": 0.1474, "step": 338160 }, { "epoch": 2.010152706694961, "grad_norm": 4.175322532653809, "learning_rate": 7.46926987346954e-06, "loss": 0.1564, "step": 338170 }, { "epoch": 2.0102121487716293, "grad_norm": 4.386196136474609, "learning_rate": 7.4690894476318965e-06, "loss": 0.1628, "step": 338180 }, { "epoch": 2.0102715908482978, "grad_norm": 5.153853893280029, "learning_rate": 7.468909017542187e-06, "loss": 0.1636, "step": 338190 }, { "epoch": 2.010331032924966, "grad_norm": 3.909738063812256, "learning_rate": 7.468728583200722e-06, "loss": 0.1476, "step": 338200 }, { "epoch": 2.0103904750016346, "grad_norm": 4.4326090812683105, "learning_rate": 7.468548144607812e-06, "loss": 0.1578, "step": 338210 }, { "epoch": 2.010449917078303, "grad_norm": 5.777360439300537, "learning_rate": 7.468367701763767e-06, "loss": 0.156, "step": 338220 }, { "epoch": 2.0105093591549714, "grad_norm": 6.132575988769531, "learning_rate": 7.468187254668898e-06, "loss": 0.1716, "step": 338230 }, { "epoch": 2.01056880123164, "grad_norm": 7.1335272789001465, "learning_rate": 7.468006803323517e-06, "loss": 0.1617, "step": 338240 }, { "epoch": 2.0106282433083082, "grad_norm": 5.057711124420166, "learning_rate": 7.467826347727932e-06, "loss": 0.167, "step": 338250 }, { "epoch": 2.0106876853849767, "grad_norm": 3.2476613521575928, "learning_rate": 7.467645887882458e-06, "loss": 0.1645, "step": 338260 }, { "epoch": 2.010747127461645, "grad_norm": 3.6867403984069824, "learning_rate": 7.467465423787402e-06, "loss": 0.1459, "step": 338270 }, { "epoch": 2.0108065695383135, "grad_norm": 3.9665236473083496, "learning_rate": 7.467284955443075e-06, "loss": 0.163, "step": 338280 }, { "epoch": 2.010866011614982, "grad_norm": 4.407590866088867, "learning_rate": 7.467104482849791e-06, "loss": 0.1389, "step": 338290 }, { "epoch": 2.0109254536916503, "grad_norm": 4.609338760375977, "learning_rate": 7.4669240060078584e-06, "loss": 0.1501, "step": 338300 }, { "epoch": 2.0109848957683187, "grad_norm": 4.697187900543213, "learning_rate": 7.4667435249175865e-06, "loss": 0.1496, "step": 338310 }, { "epoch": 2.011044337844987, "grad_norm": 3.6715848445892334, "learning_rate": 7.46656303957929e-06, "loss": 0.1356, "step": 338320 }, { "epoch": 2.0111037799216556, "grad_norm": 3.900266170501709, "learning_rate": 7.466382549993276e-06, "loss": 0.132, "step": 338330 }, { "epoch": 2.0111632219983235, "grad_norm": 3.5716042518615723, "learning_rate": 7.4662020561598584e-06, "loss": 0.1496, "step": 338340 }, { "epoch": 2.011222664074992, "grad_norm": 4.356112003326416, "learning_rate": 7.466021558079346e-06, "loss": 0.1793, "step": 338350 }, { "epoch": 2.0112821061516604, "grad_norm": 4.083605766296387, "learning_rate": 7.465841055752051e-06, "loss": 0.1567, "step": 338360 }, { "epoch": 2.011341548228329, "grad_norm": 4.81618070602417, "learning_rate": 7.465660549178283e-06, "loss": 0.1616, "step": 338370 }, { "epoch": 2.011400990304997, "grad_norm": 4.056109428405762, "learning_rate": 7.465480038358352e-06, "loss": 0.1393, "step": 338380 }, { "epoch": 2.0114604323816656, "grad_norm": 5.7468366622924805, "learning_rate": 7.465299523292571e-06, "loss": 0.1766, "step": 338390 }, { "epoch": 2.011519874458334, "grad_norm": 3.359285831451416, "learning_rate": 7.465119003981251e-06, "loss": 0.1462, "step": 338400 }, { "epoch": 2.0115793165350024, "grad_norm": 3.609851598739624, "learning_rate": 7.464938480424701e-06, "loss": 0.1718, "step": 338410 }, { "epoch": 2.011638758611671, "grad_norm": 4.632267951965332, "learning_rate": 7.4647579526232325e-06, "loss": 0.1555, "step": 338420 }, { "epoch": 2.0116982006883393, "grad_norm": 4.232232570648193, "learning_rate": 7.464577420577158e-06, "loss": 0.135, "step": 338430 }, { "epoch": 2.0117576427650077, "grad_norm": 3.918488025665283, "learning_rate": 7.464396884286786e-06, "loss": 0.1578, "step": 338440 }, { "epoch": 2.011817084841676, "grad_norm": 3.529080629348755, "learning_rate": 7.46421634375243e-06, "loss": 0.1492, "step": 338450 }, { "epoch": 2.0118765269183445, "grad_norm": 2.719794750213623, "learning_rate": 7.464035798974398e-06, "loss": 0.1302, "step": 338460 }, { "epoch": 2.011935968995013, "grad_norm": 3.5801279544830322, "learning_rate": 7.463855249953002e-06, "loss": 0.1552, "step": 338470 }, { "epoch": 2.0119954110716813, "grad_norm": 5.599265098571777, "learning_rate": 7.463674696688555e-06, "loss": 0.1399, "step": 338480 }, { "epoch": 2.0120548531483498, "grad_norm": 3.8679749965667725, "learning_rate": 7.463494139181366e-06, "loss": 0.1485, "step": 338490 }, { "epoch": 2.012114295225018, "grad_norm": 5.208912372589111, "learning_rate": 7.463313577431744e-06, "loss": 0.1495, "step": 338500 }, { "epoch": 2.0121737373016866, "grad_norm": 4.738786220550537, "learning_rate": 7.4631330114400024e-06, "loss": 0.1636, "step": 338510 }, { "epoch": 2.0122331793783546, "grad_norm": 3.7377524375915527, "learning_rate": 7.462952441206453e-06, "loss": 0.137, "step": 338520 }, { "epoch": 2.012292621455023, "grad_norm": 4.781370162963867, "learning_rate": 7.462771866731406e-06, "loss": 0.1682, "step": 338530 }, { "epoch": 2.0123520635316914, "grad_norm": 4.505883693695068, "learning_rate": 7.462591288015172e-06, "loss": 0.1548, "step": 338540 }, { "epoch": 2.01241150560836, "grad_norm": 6.397582054138184, "learning_rate": 7.462410705058062e-06, "loss": 0.1379, "step": 338550 }, { "epoch": 2.012470947685028, "grad_norm": 4.191143989562988, "learning_rate": 7.462230117860387e-06, "loss": 0.1368, "step": 338560 }, { "epoch": 2.0125303897616966, "grad_norm": 4.138571262359619, "learning_rate": 7.462049526422457e-06, "loss": 0.1544, "step": 338570 }, { "epoch": 2.012589831838365, "grad_norm": 4.769847869873047, "learning_rate": 7.4618689307445846e-06, "loss": 0.1547, "step": 338580 }, { "epoch": 2.0126492739150335, "grad_norm": 4.032701015472412, "learning_rate": 7.461688330827079e-06, "loss": 0.1568, "step": 338590 }, { "epoch": 2.012708715991702, "grad_norm": 4.35294771194458, "learning_rate": 7.461507726670254e-06, "loss": 0.156, "step": 338600 }, { "epoch": 2.0127681580683703, "grad_norm": 3.8904905319213867, "learning_rate": 7.461327118274417e-06, "loss": 0.1447, "step": 338610 }, { "epoch": 2.0128276001450387, "grad_norm": 4.08034610748291, "learning_rate": 7.461146505639883e-06, "loss": 0.1594, "step": 338620 }, { "epoch": 2.012887042221707, "grad_norm": 3.152620792388916, "learning_rate": 7.46096588876696e-06, "loss": 0.1536, "step": 338630 }, { "epoch": 2.0129464842983755, "grad_norm": 3.8824551105499268, "learning_rate": 7.460785267655961e-06, "loss": 0.1548, "step": 338640 }, { "epoch": 2.013005926375044, "grad_norm": 4.129548072814941, "learning_rate": 7.460604642307195e-06, "loss": 0.1499, "step": 338650 }, { "epoch": 2.0130653684517124, "grad_norm": 3.1190896034240723, "learning_rate": 7.460424012720976e-06, "loss": 0.1467, "step": 338660 }, { "epoch": 2.0131248105283808, "grad_norm": 5.15577507019043, "learning_rate": 7.460243378897612e-06, "loss": 0.16, "step": 338670 }, { "epoch": 2.013184252605049, "grad_norm": 3.609553813934326, "learning_rate": 7.460062740837415e-06, "loss": 0.1585, "step": 338680 }, { "epoch": 2.0132436946817176, "grad_norm": 4.684634685516357, "learning_rate": 7.459882098540697e-06, "loss": 0.1626, "step": 338690 }, { "epoch": 2.0133031367583856, "grad_norm": 3.345094919204712, "learning_rate": 7.459701452007768e-06, "loss": 0.1533, "step": 338700 }, { "epoch": 2.013362578835054, "grad_norm": 5.001931190490723, "learning_rate": 7.459520801238941e-06, "loss": 0.1514, "step": 338710 }, { "epoch": 2.0134220209117224, "grad_norm": 3.075974702835083, "learning_rate": 7.4593401462345236e-06, "loss": 0.1581, "step": 338720 }, { "epoch": 2.013481462988391, "grad_norm": 4.72568416595459, "learning_rate": 7.459159486994831e-06, "loss": 0.1517, "step": 338730 }, { "epoch": 2.0135409050650592, "grad_norm": 3.075904369354248, "learning_rate": 7.458978823520171e-06, "loss": 0.1586, "step": 338740 }, { "epoch": 2.0136003471417276, "grad_norm": 4.849198341369629, "learning_rate": 7.458798155810857e-06, "loss": 0.1497, "step": 338750 }, { "epoch": 2.013659789218396, "grad_norm": 4.131075382232666, "learning_rate": 7.458617483867199e-06, "loss": 0.1605, "step": 338760 }, { "epoch": 2.0137192312950645, "grad_norm": 3.75105619430542, "learning_rate": 7.4584368076895075e-06, "loss": 0.1695, "step": 338770 }, { "epoch": 2.013778673371733, "grad_norm": 4.707900524139404, "learning_rate": 7.458256127278095e-06, "loss": 0.1548, "step": 338780 }, { "epoch": 2.0138381154484013, "grad_norm": 3.778959035873413, "learning_rate": 7.458075442633273e-06, "loss": 0.1414, "step": 338790 }, { "epoch": 2.0138975575250697, "grad_norm": 5.747799873352051, "learning_rate": 7.45789475375535e-06, "loss": 0.1568, "step": 338800 }, { "epoch": 2.013956999601738, "grad_norm": 3.5733444690704346, "learning_rate": 7.457714060644641e-06, "loss": 0.1347, "step": 338810 }, { "epoch": 2.0140164416784065, "grad_norm": 3.4351627826690674, "learning_rate": 7.457533363301455e-06, "loss": 0.1415, "step": 338820 }, { "epoch": 2.014075883755075, "grad_norm": 4.907658100128174, "learning_rate": 7.4573526617261004e-06, "loss": 0.1424, "step": 338830 }, { "epoch": 2.0141353258317434, "grad_norm": 5.646499156951904, "learning_rate": 7.457171955918894e-06, "loss": 0.1508, "step": 338840 }, { "epoch": 2.014194767908412, "grad_norm": 4.868146896362305, "learning_rate": 7.456991245880143e-06, "loss": 0.1469, "step": 338850 }, { "epoch": 2.01425420998508, "grad_norm": 4.95039701461792, "learning_rate": 7.4568105316101616e-06, "loss": 0.1452, "step": 338860 }, { "epoch": 2.0143136520617486, "grad_norm": 3.9384655952453613, "learning_rate": 7.4566298131092574e-06, "loss": 0.1728, "step": 338870 }, { "epoch": 2.014373094138417, "grad_norm": 3.9302637577056885, "learning_rate": 7.456449090377744e-06, "loss": 0.1555, "step": 338880 }, { "epoch": 2.014432536215085, "grad_norm": 4.708521842956543, "learning_rate": 7.456268363415934e-06, "loss": 0.1769, "step": 338890 }, { "epoch": 2.0144919782917534, "grad_norm": 4.665721893310547, "learning_rate": 7.456087632224135e-06, "loss": 0.1629, "step": 338900 }, { "epoch": 2.014551420368422, "grad_norm": 4.138073921203613, "learning_rate": 7.455906896802661e-06, "loss": 0.1553, "step": 338910 }, { "epoch": 2.0146108624450902, "grad_norm": 3.7040297985076904, "learning_rate": 7.455726157151822e-06, "loss": 0.1497, "step": 338920 }, { "epoch": 2.0146703045217587, "grad_norm": 4.221353054046631, "learning_rate": 7.455545413271928e-06, "loss": 0.1731, "step": 338930 }, { "epoch": 2.014729746598427, "grad_norm": 4.4891767501831055, "learning_rate": 7.4553646651632926e-06, "loss": 0.1467, "step": 338940 }, { "epoch": 2.0147891886750955, "grad_norm": 3.7068068981170654, "learning_rate": 7.455183912826227e-06, "loss": 0.1614, "step": 338950 }, { "epoch": 2.014848630751764, "grad_norm": 4.263010025024414, "learning_rate": 7.455003156261042e-06, "loss": 0.1603, "step": 338960 }, { "epoch": 2.0149080728284323, "grad_norm": 3.5884251594543457, "learning_rate": 7.454822395468048e-06, "loss": 0.1436, "step": 338970 }, { "epoch": 2.0149675149051007, "grad_norm": 5.046239852905273, "learning_rate": 7.454641630447556e-06, "loss": 0.1374, "step": 338980 }, { "epoch": 2.015026956981769, "grad_norm": 3.9373185634613037, "learning_rate": 7.454460861199879e-06, "loss": 0.1715, "step": 338990 }, { "epoch": 2.0150863990584376, "grad_norm": 3.595283269882202, "learning_rate": 7.45428008772533e-06, "loss": 0.1778, "step": 339000 }, { "epoch": 2.015145841135106, "grad_norm": 5.5008134841918945, "learning_rate": 7.4540993100242156e-06, "loss": 0.1644, "step": 339010 }, { "epoch": 2.0152052832117744, "grad_norm": 3.5364480018615723, "learning_rate": 7.453918528096848e-06, "loss": 0.1494, "step": 339020 }, { "epoch": 2.015264725288443, "grad_norm": 6.08098030090332, "learning_rate": 7.453737741943542e-06, "loss": 0.1838, "step": 339030 }, { "epoch": 2.015324167365111, "grad_norm": 3.7877464294433594, "learning_rate": 7.453556951564607e-06, "loss": 0.1545, "step": 339040 }, { "epoch": 2.0153836094417796, "grad_norm": 5.715497016906738, "learning_rate": 7.453376156960352e-06, "loss": 0.1681, "step": 339050 }, { "epoch": 2.015443051518448, "grad_norm": 4.728593826293945, "learning_rate": 7.4531953581310914e-06, "loss": 0.1673, "step": 339060 }, { "epoch": 2.015502493595116, "grad_norm": 5.29689884185791, "learning_rate": 7.453014555077137e-06, "loss": 0.1425, "step": 339070 }, { "epoch": 2.0155619356717844, "grad_norm": 4.827944278717041, "learning_rate": 7.4528337477987975e-06, "loss": 0.1563, "step": 339080 }, { "epoch": 2.015621377748453, "grad_norm": 5.789124011993408, "learning_rate": 7.452652936296386e-06, "loss": 0.1516, "step": 339090 }, { "epoch": 2.0156808198251213, "grad_norm": 4.971220016479492, "learning_rate": 7.452472120570214e-06, "loss": 0.1449, "step": 339100 }, { "epoch": 2.0157402619017897, "grad_norm": 3.3381292819976807, "learning_rate": 7.452291300620593e-06, "loss": 0.1507, "step": 339110 }, { "epoch": 2.015799703978458, "grad_norm": 4.225128173828125, "learning_rate": 7.452110476447831e-06, "loss": 0.1476, "step": 339120 }, { "epoch": 2.0158591460551265, "grad_norm": 3.3254830837249756, "learning_rate": 7.4519296480522456e-06, "loss": 0.1416, "step": 339130 }, { "epoch": 2.015918588131795, "grad_norm": 3.7779037952423096, "learning_rate": 7.451748815434143e-06, "loss": 0.155, "step": 339140 }, { "epoch": 2.0159780302084633, "grad_norm": 3.669600486755371, "learning_rate": 7.451567978593837e-06, "loss": 0.135, "step": 339150 }, { "epoch": 2.0160374722851317, "grad_norm": 5.121242046356201, "learning_rate": 7.4513871375316374e-06, "loss": 0.1625, "step": 339160 }, { "epoch": 2.0160969143618, "grad_norm": 5.600822448730469, "learning_rate": 7.4512062922478565e-06, "loss": 0.1311, "step": 339170 }, { "epoch": 2.0161563564384686, "grad_norm": 5.053835868835449, "learning_rate": 7.451025442742807e-06, "loss": 0.1463, "step": 339180 }, { "epoch": 2.016215798515137, "grad_norm": 5.184214115142822, "learning_rate": 7.450844589016799e-06, "loss": 0.1878, "step": 339190 }, { "epoch": 2.0162752405918054, "grad_norm": 3.7044217586517334, "learning_rate": 7.450663731070145e-06, "loss": 0.1571, "step": 339200 }, { "epoch": 2.016334682668474, "grad_norm": 3.9685041904449463, "learning_rate": 7.450482868903155e-06, "loss": 0.1441, "step": 339210 }, { "epoch": 2.0163941247451422, "grad_norm": 5.877630710601807, "learning_rate": 7.45030200251614e-06, "loss": 0.1528, "step": 339220 }, { "epoch": 2.0164535668218107, "grad_norm": 3.6762218475341797, "learning_rate": 7.450121131909413e-06, "loss": 0.1399, "step": 339230 }, { "epoch": 2.016513008898479, "grad_norm": 4.172386646270752, "learning_rate": 7.449940257083286e-06, "loss": 0.152, "step": 339240 }, { "epoch": 2.0165724509751475, "grad_norm": 4.326999664306641, "learning_rate": 7.449759378038068e-06, "loss": 0.1596, "step": 339250 }, { "epoch": 2.0166318930518154, "grad_norm": 3.0227773189544678, "learning_rate": 7.4495784947740745e-06, "loss": 0.1412, "step": 339260 }, { "epoch": 2.016691335128484, "grad_norm": 4.194102764129639, "learning_rate": 7.449397607291612e-06, "loss": 0.1564, "step": 339270 }, { "epoch": 2.0167507772051523, "grad_norm": 5.45595645904541, "learning_rate": 7.4492167155909964e-06, "loss": 0.1475, "step": 339280 }, { "epoch": 2.0168102192818207, "grad_norm": 4.219013214111328, "learning_rate": 7.449035819672536e-06, "loss": 0.1592, "step": 339290 }, { "epoch": 2.016869661358489, "grad_norm": 4.617456436157227, "learning_rate": 7.448854919536544e-06, "loss": 0.1428, "step": 339300 }, { "epoch": 2.0169291034351575, "grad_norm": 3.605012893676758, "learning_rate": 7.4486740151833325e-06, "loss": 0.1529, "step": 339310 }, { "epoch": 2.016988545511826, "grad_norm": 3.820077419281006, "learning_rate": 7.448493106613211e-06, "loss": 0.1691, "step": 339320 }, { "epoch": 2.0170479875884944, "grad_norm": 3.293337106704712, "learning_rate": 7.448312193826495e-06, "loss": 0.1506, "step": 339330 }, { "epoch": 2.0171074296651628, "grad_norm": 4.5074238777160645, "learning_rate": 7.44813127682349e-06, "loss": 0.1573, "step": 339340 }, { "epoch": 2.017166871741831, "grad_norm": 3.6826889514923096, "learning_rate": 7.4479503556045114e-06, "loss": 0.1584, "step": 339350 }, { "epoch": 2.0172263138184996, "grad_norm": 3.8915867805480957, "learning_rate": 7.447769430169872e-06, "loss": 0.1572, "step": 339360 }, { "epoch": 2.017285755895168, "grad_norm": 4.282236576080322, "learning_rate": 7.44758850051988e-06, "loss": 0.1568, "step": 339370 }, { "epoch": 2.0173451979718364, "grad_norm": 5.292513847351074, "learning_rate": 7.447407566654849e-06, "loss": 0.154, "step": 339380 }, { "epoch": 2.017404640048505, "grad_norm": 3.876847743988037, "learning_rate": 7.44722662857509e-06, "loss": 0.1471, "step": 339390 }, { "epoch": 2.0174640821251733, "grad_norm": 2.765629768371582, "learning_rate": 7.447045686280915e-06, "loss": 0.1617, "step": 339400 }, { "epoch": 2.0175235242018417, "grad_norm": 4.836434841156006, "learning_rate": 7.446864739772635e-06, "loss": 0.1628, "step": 339410 }, { "epoch": 2.01758296627851, "grad_norm": 5.441515922546387, "learning_rate": 7.446683789050562e-06, "loss": 0.1625, "step": 339420 }, { "epoch": 2.0176424083551785, "grad_norm": 4.136786937713623, "learning_rate": 7.446502834115008e-06, "loss": 0.153, "step": 339430 }, { "epoch": 2.0177018504318465, "grad_norm": 4.65278434753418, "learning_rate": 7.446321874966285e-06, "loss": 0.1561, "step": 339440 }, { "epoch": 2.017761292508515, "grad_norm": 3.4810564517974854, "learning_rate": 7.446140911604702e-06, "loss": 0.1492, "step": 339450 }, { "epoch": 2.0178207345851833, "grad_norm": 4.125373363494873, "learning_rate": 7.445959944030573e-06, "loss": 0.1503, "step": 339460 }, { "epoch": 2.0178801766618517, "grad_norm": 3.5321662425994873, "learning_rate": 7.44577897224421e-06, "loss": 0.1577, "step": 339470 }, { "epoch": 2.01793961873852, "grad_norm": 3.5470376014709473, "learning_rate": 7.445597996245923e-06, "loss": 0.1581, "step": 339480 }, { "epoch": 2.0179990608151885, "grad_norm": 4.123781204223633, "learning_rate": 7.445417016036024e-06, "loss": 0.161, "step": 339490 }, { "epoch": 2.018058502891857, "grad_norm": 4.964261531829834, "learning_rate": 7.445236031614827e-06, "loss": 0.1356, "step": 339500 }, { "epoch": 2.0181179449685254, "grad_norm": 3.99716854095459, "learning_rate": 7.44505504298264e-06, "loss": 0.1486, "step": 339510 }, { "epoch": 2.018177387045194, "grad_norm": 3.9391987323760986, "learning_rate": 7.444874050139777e-06, "loss": 0.1555, "step": 339520 }, { "epoch": 2.018236829121862, "grad_norm": 3.7954211235046387, "learning_rate": 7.444693053086549e-06, "loss": 0.1397, "step": 339530 }, { "epoch": 2.0182962711985306, "grad_norm": 5.439921855926514, "learning_rate": 7.444512051823268e-06, "loss": 0.1559, "step": 339540 }, { "epoch": 2.018355713275199, "grad_norm": 5.2882914543151855, "learning_rate": 7.444331046350246e-06, "loss": 0.1739, "step": 339550 }, { "epoch": 2.0184151553518674, "grad_norm": 3.894137144088745, "learning_rate": 7.444150036667794e-06, "loss": 0.1579, "step": 339560 }, { "epoch": 2.018474597428536, "grad_norm": 3.9402127265930176, "learning_rate": 7.443969022776224e-06, "loss": 0.1449, "step": 339570 }, { "epoch": 2.0185340395052043, "grad_norm": 5.213105201721191, "learning_rate": 7.4437880046758475e-06, "loss": 0.1529, "step": 339580 }, { "epoch": 2.0185934815818727, "grad_norm": 4.75311279296875, "learning_rate": 7.4436069823669765e-06, "loss": 0.1586, "step": 339590 }, { "epoch": 2.018652923658541, "grad_norm": 5.62423849105835, "learning_rate": 7.443425955849922e-06, "loss": 0.172, "step": 339600 }, { "epoch": 2.0187123657352095, "grad_norm": 6.265994071960449, "learning_rate": 7.443244925124997e-06, "loss": 0.1491, "step": 339610 }, { "epoch": 2.018771807811878, "grad_norm": 5.697932720184326, "learning_rate": 7.443063890192514e-06, "loss": 0.1694, "step": 339620 }, { "epoch": 2.018831249888546, "grad_norm": 4.512685298919678, "learning_rate": 7.442882851052782e-06, "loss": 0.1572, "step": 339630 }, { "epoch": 2.0188906919652143, "grad_norm": 3.8694920539855957, "learning_rate": 7.442701807706114e-06, "loss": 0.1449, "step": 339640 }, { "epoch": 2.0189501340418827, "grad_norm": 5.271396160125732, "learning_rate": 7.442520760152824e-06, "loss": 0.1597, "step": 339650 }, { "epoch": 2.019009576118551, "grad_norm": 2.940622568130493, "learning_rate": 7.44233970839322e-06, "loss": 0.1641, "step": 339660 }, { "epoch": 2.0190690181952196, "grad_norm": 4.003462314605713, "learning_rate": 7.442158652427615e-06, "loss": 0.1402, "step": 339670 }, { "epoch": 2.019128460271888, "grad_norm": 4.046502590179443, "learning_rate": 7.441977592256324e-06, "loss": 0.148, "step": 339680 }, { "epoch": 2.0191879023485564, "grad_norm": 4.267287731170654, "learning_rate": 7.441796527879656e-06, "loss": 0.1562, "step": 339690 }, { "epoch": 2.019247344425225, "grad_norm": 3.363574981689453, "learning_rate": 7.441615459297922e-06, "loss": 0.1525, "step": 339700 }, { "epoch": 2.019306786501893, "grad_norm": 4.892195224761963, "learning_rate": 7.441434386511432e-06, "loss": 0.1529, "step": 339710 }, { "epoch": 2.0193662285785616, "grad_norm": 3.581244707107544, "learning_rate": 7.4412533095205044e-06, "loss": 0.1531, "step": 339720 }, { "epoch": 2.01942567065523, "grad_norm": 4.745358467102051, "learning_rate": 7.441072228325446e-06, "loss": 0.1614, "step": 339730 }, { "epoch": 2.0194851127318985, "grad_norm": 4.070210933685303, "learning_rate": 7.440891142926571e-06, "loss": 0.1502, "step": 339740 }, { "epoch": 2.019544554808567, "grad_norm": 3.928492784500122, "learning_rate": 7.44071005332419e-06, "loss": 0.1589, "step": 339750 }, { "epoch": 2.0196039968852353, "grad_norm": 4.50185489654541, "learning_rate": 7.440528959518614e-06, "loss": 0.1554, "step": 339760 }, { "epoch": 2.0196634389619037, "grad_norm": 4.984522342681885, "learning_rate": 7.4403478615101565e-06, "loss": 0.1491, "step": 339770 }, { "epoch": 2.019722881038572, "grad_norm": 4.843625545501709, "learning_rate": 7.4401667592991286e-06, "loss": 0.166, "step": 339780 }, { "epoch": 2.0197823231152405, "grad_norm": 4.2314133644104, "learning_rate": 7.439985652885844e-06, "loss": 0.166, "step": 339790 }, { "epoch": 2.019841765191909, "grad_norm": 5.112255573272705, "learning_rate": 7.43980454227061e-06, "loss": 0.1661, "step": 339800 }, { "epoch": 2.019901207268577, "grad_norm": 4.595649719238281, "learning_rate": 7.439623427453744e-06, "loss": 0.1548, "step": 339810 }, { "epoch": 2.0199606493452453, "grad_norm": 5.029671669006348, "learning_rate": 7.439442308435554e-06, "loss": 0.1782, "step": 339820 }, { "epoch": 2.0200200914219137, "grad_norm": 2.891479969024658, "learning_rate": 7.439261185216354e-06, "loss": 0.1595, "step": 339830 }, { "epoch": 2.020079533498582, "grad_norm": 5.102225303649902, "learning_rate": 7.439080057796454e-06, "loss": 0.1619, "step": 339840 }, { "epoch": 2.0201389755752506, "grad_norm": 4.84814977645874, "learning_rate": 7.438898926176168e-06, "loss": 0.1525, "step": 339850 }, { "epoch": 2.020198417651919, "grad_norm": 4.116409778594971, "learning_rate": 7.438717790355807e-06, "loss": 0.1639, "step": 339860 }, { "epoch": 2.0202578597285874, "grad_norm": 3.413487672805786, "learning_rate": 7.438536650335682e-06, "loss": 0.1538, "step": 339870 }, { "epoch": 2.020317301805256, "grad_norm": 4.786433219909668, "learning_rate": 7.438355506116109e-06, "loss": 0.137, "step": 339880 }, { "epoch": 2.0203767438819242, "grad_norm": 3.679652214050293, "learning_rate": 7.438174357697394e-06, "loss": 0.1457, "step": 339890 }, { "epoch": 2.0204361859585926, "grad_norm": 4.838201522827148, "learning_rate": 7.437993205079852e-06, "loss": 0.1506, "step": 339900 }, { "epoch": 2.020495628035261, "grad_norm": 4.49682092666626, "learning_rate": 7.437812048263796e-06, "loss": 0.1464, "step": 339910 }, { "epoch": 2.0205550701119295, "grad_norm": 4.898992538452148, "learning_rate": 7.437630887249536e-06, "loss": 0.1672, "step": 339920 }, { "epoch": 2.020614512188598, "grad_norm": 5.631250381469727, "learning_rate": 7.4374497220373845e-06, "loss": 0.1525, "step": 339930 }, { "epoch": 2.0206739542652663, "grad_norm": 4.081797122955322, "learning_rate": 7.437268552627654e-06, "loss": 0.1278, "step": 339940 }, { "epoch": 2.0207333963419347, "grad_norm": 4.24824857711792, "learning_rate": 7.437087379020657e-06, "loss": 0.1583, "step": 339950 }, { "epoch": 2.020792838418603, "grad_norm": 3.875777006149292, "learning_rate": 7.436906201216705e-06, "loss": 0.1315, "step": 339960 }, { "epoch": 2.0208522804952715, "grad_norm": 3.544879198074341, "learning_rate": 7.4367250192161074e-06, "loss": 0.1531, "step": 339970 }, { "epoch": 2.02091172257194, "grad_norm": 3.8304495811462402, "learning_rate": 7.436543833019181e-06, "loss": 0.1564, "step": 339980 }, { "epoch": 2.0209711646486084, "grad_norm": 3.769840717315674, "learning_rate": 7.436362642626235e-06, "loss": 0.1422, "step": 339990 }, { "epoch": 2.0210306067252763, "grad_norm": 3.5047295093536377, "learning_rate": 7.436181448037581e-06, "loss": 0.1443, "step": 340000 }, { "epoch": 2.0210900488019448, "grad_norm": 4.000813961029053, "learning_rate": 7.436000249253532e-06, "loss": 0.1504, "step": 340010 }, { "epoch": 2.021149490878613, "grad_norm": 4.214305400848389, "learning_rate": 7.4358190462744004e-06, "loss": 0.1523, "step": 340020 }, { "epoch": 2.0212089329552816, "grad_norm": 3.667222023010254, "learning_rate": 7.435637839100497e-06, "loss": 0.1382, "step": 340030 }, { "epoch": 2.02126837503195, "grad_norm": 3.6283111572265625, "learning_rate": 7.4354566277321335e-06, "loss": 0.1549, "step": 340040 }, { "epoch": 2.0213278171086184, "grad_norm": 3.1547207832336426, "learning_rate": 7.435275412169626e-06, "loss": 0.1447, "step": 340050 }, { "epoch": 2.021387259185287, "grad_norm": 3.5057570934295654, "learning_rate": 7.435094192413282e-06, "loss": 0.1386, "step": 340060 }, { "epoch": 2.0214467012619552, "grad_norm": 4.875545978546143, "learning_rate": 7.434912968463416e-06, "loss": 0.1715, "step": 340070 }, { "epoch": 2.0215061433386237, "grad_norm": 4.272340297698975, "learning_rate": 7.434731740320339e-06, "loss": 0.1441, "step": 340080 }, { "epoch": 2.021565585415292, "grad_norm": 4.65441370010376, "learning_rate": 7.434550507984364e-06, "loss": 0.1519, "step": 340090 }, { "epoch": 2.0216250274919605, "grad_norm": 3.7772293090820312, "learning_rate": 7.4343692714558015e-06, "loss": 0.1618, "step": 340100 }, { "epoch": 2.021684469568629, "grad_norm": 4.552903652191162, "learning_rate": 7.434188030734965e-06, "loss": 0.1492, "step": 340110 }, { "epoch": 2.0217439116452973, "grad_norm": 4.566956520080566, "learning_rate": 7.4340067858221664e-06, "loss": 0.1394, "step": 340120 }, { "epoch": 2.0218033537219657, "grad_norm": 3.6028285026550293, "learning_rate": 7.433825536717718e-06, "loss": 0.1405, "step": 340130 }, { "epoch": 2.021862795798634, "grad_norm": 5.026724338531494, "learning_rate": 7.433644283421931e-06, "loss": 0.1651, "step": 340140 }, { "epoch": 2.0219222378753026, "grad_norm": 4.634463787078857, "learning_rate": 7.4334630259351185e-06, "loss": 0.1418, "step": 340150 }, { "epoch": 2.021981679951971, "grad_norm": 4.2070722579956055, "learning_rate": 7.433281764257592e-06, "loss": 0.1318, "step": 340160 }, { "epoch": 2.0220411220286394, "grad_norm": 4.746787071228027, "learning_rate": 7.433100498389664e-06, "loss": 0.1448, "step": 340170 }, { "epoch": 2.0221005641053074, "grad_norm": 5.29141902923584, "learning_rate": 7.432919228331648e-06, "loss": 0.1632, "step": 340180 }, { "epoch": 2.0221600061819758, "grad_norm": 4.500362396240234, "learning_rate": 7.432737954083853e-06, "loss": 0.1455, "step": 340190 }, { "epoch": 2.022219448258644, "grad_norm": 5.181614875793457, "learning_rate": 7.432556675646593e-06, "loss": 0.157, "step": 340200 }, { "epoch": 2.0222788903353126, "grad_norm": 4.824009895324707, "learning_rate": 7.432375393020182e-06, "loss": 0.157, "step": 340210 }, { "epoch": 2.022338332411981, "grad_norm": 4.049837112426758, "learning_rate": 7.432194106204929e-06, "loss": 0.1466, "step": 340220 }, { "epoch": 2.0223977744886494, "grad_norm": 2.9557836055755615, "learning_rate": 7.432012815201146e-06, "loss": 0.14, "step": 340230 }, { "epoch": 2.022457216565318, "grad_norm": 3.9068427085876465, "learning_rate": 7.431831520009149e-06, "loss": 0.1432, "step": 340240 }, { "epoch": 2.0225166586419863, "grad_norm": 4.009904861450195, "learning_rate": 7.431650220629249e-06, "loss": 0.1607, "step": 340250 }, { "epoch": 2.0225761007186547, "grad_norm": 4.702436923980713, "learning_rate": 7.431468917061753e-06, "loss": 0.1518, "step": 340260 }, { "epoch": 2.022635542795323, "grad_norm": 3.2575526237487793, "learning_rate": 7.4312876093069806e-06, "loss": 0.1361, "step": 340270 }, { "epoch": 2.0226949848719915, "grad_norm": 4.822272300720215, "learning_rate": 7.431106297365241e-06, "loss": 0.1552, "step": 340280 }, { "epoch": 2.02275442694866, "grad_norm": 4.958537578582764, "learning_rate": 7.430924981236844e-06, "loss": 0.1666, "step": 340290 }, { "epoch": 2.0228138690253283, "grad_norm": 4.460629463195801, "learning_rate": 7.430743660922107e-06, "loss": 0.1588, "step": 340300 }, { "epoch": 2.0228733111019968, "grad_norm": 4.336812973022461, "learning_rate": 7.430562336421337e-06, "loss": 0.1442, "step": 340310 }, { "epoch": 2.022932753178665, "grad_norm": 4.6237406730651855, "learning_rate": 7.4303810077348505e-06, "loss": 0.1552, "step": 340320 }, { "epoch": 2.0229921952553336, "grad_norm": 5.431973934173584, "learning_rate": 7.430199674862957e-06, "loss": 0.1404, "step": 340330 }, { "epoch": 2.023051637332002, "grad_norm": 4.318017959594727, "learning_rate": 7.4300183378059696e-06, "loss": 0.1508, "step": 340340 }, { "epoch": 2.0231110794086704, "grad_norm": 3.8420908451080322, "learning_rate": 7.4298369965642005e-06, "loss": 0.1667, "step": 340350 }, { "epoch": 2.023170521485339, "grad_norm": 4.044063568115234, "learning_rate": 7.4296556511379626e-06, "loss": 0.1174, "step": 340360 }, { "epoch": 2.023229963562007, "grad_norm": 3.3064916133880615, "learning_rate": 7.429474301527567e-06, "loss": 0.1529, "step": 340370 }, { "epoch": 2.023289405638675, "grad_norm": 4.45625638961792, "learning_rate": 7.429292947733329e-06, "loss": 0.1599, "step": 340380 }, { "epoch": 2.0233488477153436, "grad_norm": 5.852017879486084, "learning_rate": 7.429111589755555e-06, "loss": 0.1539, "step": 340390 }, { "epoch": 2.023408289792012, "grad_norm": 4.2557525634765625, "learning_rate": 7.428930227594564e-06, "loss": 0.1581, "step": 340400 }, { "epoch": 2.0234677318686805, "grad_norm": 3.8860108852386475, "learning_rate": 7.428748861250666e-06, "loss": 0.1573, "step": 340410 }, { "epoch": 2.023527173945349, "grad_norm": 5.023233413696289, "learning_rate": 7.42856749072417e-06, "loss": 0.1463, "step": 340420 }, { "epoch": 2.0235866160220173, "grad_norm": 3.829596519470215, "learning_rate": 7.428386116015392e-06, "loss": 0.1501, "step": 340430 }, { "epoch": 2.0236460580986857, "grad_norm": 3.3459229469299316, "learning_rate": 7.428204737124644e-06, "loss": 0.1373, "step": 340440 }, { "epoch": 2.023705500175354, "grad_norm": 5.670900344848633, "learning_rate": 7.428023354052236e-06, "loss": 0.1612, "step": 340450 }, { "epoch": 2.0237649422520225, "grad_norm": 3.6757233142852783, "learning_rate": 7.427841966798484e-06, "loss": 0.1509, "step": 340460 }, { "epoch": 2.023824384328691, "grad_norm": 3.9439821243286133, "learning_rate": 7.427660575363698e-06, "loss": 0.1595, "step": 340470 }, { "epoch": 2.0238838264053594, "grad_norm": 3.832329750061035, "learning_rate": 7.4274791797481906e-06, "loss": 0.1518, "step": 340480 }, { "epoch": 2.0239432684820278, "grad_norm": 3.5819954872131348, "learning_rate": 7.427297779952274e-06, "loss": 0.1541, "step": 340490 }, { "epoch": 2.024002710558696, "grad_norm": 4.153768539428711, "learning_rate": 7.427116375976261e-06, "loss": 0.1478, "step": 340500 }, { "epoch": 2.0240621526353646, "grad_norm": 2.8854446411132812, "learning_rate": 7.426934967820465e-06, "loss": 0.1585, "step": 340510 }, { "epoch": 2.024121594712033, "grad_norm": 4.797954559326172, "learning_rate": 7.4267535554851965e-06, "loss": 0.1442, "step": 340520 }, { "epoch": 2.0241810367887014, "grad_norm": 5.267734527587891, "learning_rate": 7.426572138970769e-06, "loss": 0.1578, "step": 340530 }, { "epoch": 2.02424047886537, "grad_norm": 3.6989855766296387, "learning_rate": 7.426390718277495e-06, "loss": 0.163, "step": 340540 }, { "epoch": 2.024299920942038, "grad_norm": 4.41298770904541, "learning_rate": 7.426209293405686e-06, "loss": 0.1583, "step": 340550 }, { "epoch": 2.0243593630187062, "grad_norm": 5.159592151641846, "learning_rate": 7.426027864355656e-06, "loss": 0.1368, "step": 340560 }, { "epoch": 2.0244188050953746, "grad_norm": 5.498729705810547, "learning_rate": 7.425846431127717e-06, "loss": 0.1489, "step": 340570 }, { "epoch": 2.024478247172043, "grad_norm": 4.005210876464844, "learning_rate": 7.425664993722179e-06, "loss": 0.1703, "step": 340580 }, { "epoch": 2.0245376892487115, "grad_norm": 4.66966438293457, "learning_rate": 7.425483552139357e-06, "loss": 0.1818, "step": 340590 }, { "epoch": 2.02459713132538, "grad_norm": 3.40492844581604, "learning_rate": 7.425302106379564e-06, "loss": 0.1669, "step": 340600 }, { "epoch": 2.0246565734020483, "grad_norm": 3.4797401428222656, "learning_rate": 7.425120656443112e-06, "loss": 0.1335, "step": 340610 }, { "epoch": 2.0247160154787167, "grad_norm": 4.501642227172852, "learning_rate": 7.424939202330311e-06, "loss": 0.156, "step": 340620 }, { "epoch": 2.024775457555385, "grad_norm": 3.9267618656158447, "learning_rate": 7.424757744041476e-06, "loss": 0.1754, "step": 340630 }, { "epoch": 2.0248348996320535, "grad_norm": 4.80319881439209, "learning_rate": 7.42457628157692e-06, "loss": 0.1693, "step": 340640 }, { "epoch": 2.024894341708722, "grad_norm": 3.4378559589385986, "learning_rate": 7.424394814936953e-06, "loss": 0.1457, "step": 340650 }, { "epoch": 2.0249537837853904, "grad_norm": 4.466358661651611, "learning_rate": 7.424213344121889e-06, "loss": 0.1444, "step": 340660 }, { "epoch": 2.025013225862059, "grad_norm": 6.217207908630371, "learning_rate": 7.424031869132041e-06, "loss": 0.1648, "step": 340670 }, { "epoch": 2.025072667938727, "grad_norm": 3.0965168476104736, "learning_rate": 7.42385038996772e-06, "loss": 0.1691, "step": 340680 }, { "epoch": 2.0251321100153956, "grad_norm": 4.123117923736572, "learning_rate": 7.42366890662924e-06, "loss": 0.1418, "step": 340690 }, { "epoch": 2.025191552092064, "grad_norm": 4.674948215484619, "learning_rate": 7.423487419116913e-06, "loss": 0.1622, "step": 340700 }, { "epoch": 2.0252509941687324, "grad_norm": 4.222872734069824, "learning_rate": 7.423305927431051e-06, "loss": 0.1606, "step": 340710 }, { "epoch": 2.025310436245401, "grad_norm": 3.8188297748565674, "learning_rate": 7.423124431571966e-06, "loss": 0.1522, "step": 340720 }, { "epoch": 2.0253698783220693, "grad_norm": 4.087316036224365, "learning_rate": 7.422942931539975e-06, "loss": 0.1554, "step": 340730 }, { "epoch": 2.0254293203987372, "grad_norm": 4.350677013397217, "learning_rate": 7.4227614273353855e-06, "loss": 0.1734, "step": 340740 }, { "epoch": 2.0254887624754057, "grad_norm": 3.9219956398010254, "learning_rate": 7.42257991895851e-06, "loss": 0.175, "step": 340750 }, { "epoch": 2.025548204552074, "grad_norm": 4.4956440925598145, "learning_rate": 7.422398406409666e-06, "loss": 0.1661, "step": 340760 }, { "epoch": 2.0256076466287425, "grad_norm": 3.390187978744507, "learning_rate": 7.42221688968916e-06, "loss": 0.1535, "step": 340770 }, { "epoch": 2.025667088705411, "grad_norm": 3.418581962585449, "learning_rate": 7.422035368797309e-06, "loss": 0.1725, "step": 340780 }, { "epoch": 2.0257265307820793, "grad_norm": 5.284303188323975, "learning_rate": 7.421853843734424e-06, "loss": 0.1656, "step": 340790 }, { "epoch": 2.0257859728587477, "grad_norm": 5.667027473449707, "learning_rate": 7.421672314500817e-06, "loss": 0.1432, "step": 340800 }, { "epoch": 2.025845414935416, "grad_norm": 3.9341557025909424, "learning_rate": 7.421490781096801e-06, "loss": 0.1557, "step": 340810 }, { "epoch": 2.0259048570120846, "grad_norm": 4.017647743225098, "learning_rate": 7.42130924352269e-06, "loss": 0.1731, "step": 340820 }, { "epoch": 2.025964299088753, "grad_norm": 4.973150253295898, "learning_rate": 7.4211277017787955e-06, "loss": 0.1578, "step": 340830 }, { "epoch": 2.0260237411654214, "grad_norm": 4.54103946685791, "learning_rate": 7.420946155865431e-06, "loss": 0.1732, "step": 340840 }, { "epoch": 2.02608318324209, "grad_norm": 2.6006999015808105, "learning_rate": 7.420764605782906e-06, "loss": 0.1457, "step": 340850 }, { "epoch": 2.026142625318758, "grad_norm": 4.439814567565918, "learning_rate": 7.420583051531538e-06, "loss": 0.1681, "step": 340860 }, { "epoch": 2.0262020673954266, "grad_norm": 3.446873664855957, "learning_rate": 7.420401493111635e-06, "loss": 0.1719, "step": 340870 }, { "epoch": 2.026261509472095, "grad_norm": 3.023184299468994, "learning_rate": 7.420219930523514e-06, "loss": 0.1573, "step": 340880 }, { "epoch": 2.0263209515487635, "grad_norm": 5.047540664672852, "learning_rate": 7.4200383637674835e-06, "loss": 0.1541, "step": 340890 }, { "epoch": 2.026380393625432, "grad_norm": 3.5812830924987793, "learning_rate": 7.419856792843861e-06, "loss": 0.1574, "step": 340900 }, { "epoch": 2.0264398357021003, "grad_norm": 4.815765857696533, "learning_rate": 7.419675217752953e-06, "loss": 0.1508, "step": 340910 }, { "epoch": 2.0264992777787683, "grad_norm": 4.957838535308838, "learning_rate": 7.419493638495076e-06, "loss": 0.1674, "step": 340920 }, { "epoch": 2.0265587198554367, "grad_norm": 4.692878723144531, "learning_rate": 7.419312055070543e-06, "loss": 0.1738, "step": 340930 }, { "epoch": 2.026618161932105, "grad_norm": 3.48795485496521, "learning_rate": 7.419130467479666e-06, "loss": 0.1517, "step": 340940 }, { "epoch": 2.0266776040087735, "grad_norm": 5.275081634521484, "learning_rate": 7.418948875722759e-06, "loss": 0.1494, "step": 340950 }, { "epoch": 2.026737046085442, "grad_norm": 4.938845634460449, "learning_rate": 7.418767279800132e-06, "loss": 0.1505, "step": 340960 }, { "epoch": 2.0267964881621103, "grad_norm": 4.04077672958374, "learning_rate": 7.4185856797121e-06, "loss": 0.1699, "step": 340970 }, { "epoch": 2.0268559302387787, "grad_norm": 4.88199520111084, "learning_rate": 7.418404075458974e-06, "loss": 0.1574, "step": 340980 }, { "epoch": 2.026915372315447, "grad_norm": 4.544528007507324, "learning_rate": 7.418222467041068e-06, "loss": 0.1559, "step": 340990 }, { "epoch": 2.0269748143921156, "grad_norm": 4.1267313957214355, "learning_rate": 7.418040854458695e-06, "loss": 0.1571, "step": 341000 }, { "epoch": 2.027034256468784, "grad_norm": 4.644177436828613, "learning_rate": 7.417859237712166e-06, "loss": 0.1448, "step": 341010 }, { "epoch": 2.0270936985454524, "grad_norm": 3.872770071029663, "learning_rate": 7.417677616801796e-06, "loss": 0.1538, "step": 341020 }, { "epoch": 2.027153140622121, "grad_norm": 3.340848922729492, "learning_rate": 7.417495991727895e-06, "loss": 0.1589, "step": 341030 }, { "epoch": 2.0272125826987892, "grad_norm": 3.6327199935913086, "learning_rate": 7.417314362490778e-06, "loss": 0.169, "step": 341040 }, { "epoch": 2.0272720247754576, "grad_norm": 4.314850330352783, "learning_rate": 7.417132729090758e-06, "loss": 0.1503, "step": 341050 }, { "epoch": 2.027331466852126, "grad_norm": 3.5464913845062256, "learning_rate": 7.416951091528147e-06, "loss": 0.1391, "step": 341060 }, { "epoch": 2.0273909089287945, "grad_norm": 3.738905429840088, "learning_rate": 7.416769449803257e-06, "loss": 0.1553, "step": 341070 }, { "epoch": 2.027450351005463, "grad_norm": 3.913271427154541, "learning_rate": 7.416587803916403e-06, "loss": 0.1573, "step": 341080 }, { "epoch": 2.0275097930821313, "grad_norm": 4.855804443359375, "learning_rate": 7.416406153867897e-06, "loss": 0.1465, "step": 341090 }, { "epoch": 2.0275692351587997, "grad_norm": 5.0589680671691895, "learning_rate": 7.416224499658049e-06, "loss": 0.1458, "step": 341100 }, { "epoch": 2.0276286772354677, "grad_norm": 4.436915397644043, "learning_rate": 7.416042841287175e-06, "loss": 0.1748, "step": 341110 }, { "epoch": 2.027688119312136, "grad_norm": 3.915193557739258, "learning_rate": 7.415861178755588e-06, "loss": 0.143, "step": 341120 }, { "epoch": 2.0277475613888045, "grad_norm": 4.159493923187256, "learning_rate": 7.415679512063598e-06, "loss": 0.1679, "step": 341130 }, { "epoch": 2.027807003465473, "grad_norm": 3.3263766765594482, "learning_rate": 7.41549784121152e-06, "loss": 0.1278, "step": 341140 }, { "epoch": 2.0278664455421413, "grad_norm": 4.431764125823975, "learning_rate": 7.415316166199666e-06, "loss": 0.1606, "step": 341150 }, { "epoch": 2.0279258876188098, "grad_norm": 3.7837438583374023, "learning_rate": 7.415134487028352e-06, "loss": 0.1419, "step": 341160 }, { "epoch": 2.027985329695478, "grad_norm": 3.696139097213745, "learning_rate": 7.414952803697886e-06, "loss": 0.1449, "step": 341170 }, { "epoch": 2.0280447717721466, "grad_norm": 3.842212438583374, "learning_rate": 7.414771116208583e-06, "loss": 0.1323, "step": 341180 }, { "epoch": 2.028104213848815, "grad_norm": 3.0474002361297607, "learning_rate": 7.4145894245607586e-06, "loss": 0.1468, "step": 341190 }, { "epoch": 2.0281636559254834, "grad_norm": 3.5213623046875, "learning_rate": 7.41440772875472e-06, "loss": 0.1614, "step": 341200 }, { "epoch": 2.028223098002152, "grad_norm": 5.066454887390137, "learning_rate": 7.414226028790785e-06, "loss": 0.1636, "step": 341210 }, { "epoch": 2.0282825400788203, "grad_norm": 3.9808871746063232, "learning_rate": 7.414044324669265e-06, "loss": 0.1445, "step": 341220 }, { "epoch": 2.0283419821554887, "grad_norm": 4.770980358123779, "learning_rate": 7.4138626163904705e-06, "loss": 0.1589, "step": 341230 }, { "epoch": 2.028401424232157, "grad_norm": 4.24102783203125, "learning_rate": 7.4136809039547185e-06, "loss": 0.1458, "step": 341240 }, { "epoch": 2.0284608663088255, "grad_norm": 4.9079790115356445, "learning_rate": 7.413499187362318e-06, "loss": 0.164, "step": 341250 }, { "epoch": 2.028520308385494, "grad_norm": 4.846678733825684, "learning_rate": 7.413317466613587e-06, "loss": 0.1475, "step": 341260 }, { "epoch": 2.0285797504621623, "grad_norm": 3.8592166900634766, "learning_rate": 7.413135741708832e-06, "loss": 0.1516, "step": 341270 }, { "epoch": 2.0286391925388307, "grad_norm": 4.667898654937744, "learning_rate": 7.412954012648372e-06, "loss": 0.1565, "step": 341280 }, { "epoch": 2.0286986346154987, "grad_norm": 4.16784143447876, "learning_rate": 7.4127722794325165e-06, "loss": 0.1583, "step": 341290 }, { "epoch": 2.028758076692167, "grad_norm": 4.154720306396484, "learning_rate": 7.412590542061578e-06, "loss": 0.1728, "step": 341300 }, { "epoch": 2.0288175187688355, "grad_norm": 3.3384265899658203, "learning_rate": 7.412408800535873e-06, "loss": 0.18, "step": 341310 }, { "epoch": 2.028876960845504, "grad_norm": 4.759802341461182, "learning_rate": 7.412227054855711e-06, "loss": 0.1526, "step": 341320 }, { "epoch": 2.0289364029221724, "grad_norm": 5.9602861404418945, "learning_rate": 7.412045305021406e-06, "loss": 0.1724, "step": 341330 }, { "epoch": 2.028995844998841, "grad_norm": 4.978150844573975, "learning_rate": 7.411863551033271e-06, "loss": 0.1605, "step": 341340 }, { "epoch": 2.029055287075509, "grad_norm": 5.427020072937012, "learning_rate": 7.4116817928916205e-06, "loss": 0.1531, "step": 341350 }, { "epoch": 2.0291147291521776, "grad_norm": 5.415151119232178, "learning_rate": 7.411500030596765e-06, "loss": 0.1644, "step": 341360 }, { "epoch": 2.029174171228846, "grad_norm": 4.471595287322998, "learning_rate": 7.4113182641490175e-06, "loss": 0.142, "step": 341370 }, { "epoch": 2.0292336133055144, "grad_norm": 3.5012993812561035, "learning_rate": 7.411136493548694e-06, "loss": 0.1543, "step": 341380 }, { "epoch": 2.029293055382183, "grad_norm": 3.1987035274505615, "learning_rate": 7.410954718796106e-06, "loss": 0.1298, "step": 341390 }, { "epoch": 2.0293524974588513, "grad_norm": 3.257289409637451, "learning_rate": 7.410772939891565e-06, "loss": 0.1531, "step": 341400 }, { "epoch": 2.0294119395355197, "grad_norm": 4.326765060424805, "learning_rate": 7.410591156835386e-06, "loss": 0.1446, "step": 341410 }, { "epoch": 2.029471381612188, "grad_norm": 3.5737874507904053, "learning_rate": 7.4104093696278825e-06, "loss": 0.1386, "step": 341420 }, { "epoch": 2.0295308236888565, "grad_norm": 4.530682563781738, "learning_rate": 7.410227578269365e-06, "loss": 0.1561, "step": 341430 }, { "epoch": 2.029590265765525, "grad_norm": 3.6152749061584473, "learning_rate": 7.410045782760149e-06, "loss": 0.1559, "step": 341440 }, { "epoch": 2.0296497078421933, "grad_norm": 3.1262848377227783, "learning_rate": 7.409863983100546e-06, "loss": 0.1635, "step": 341450 }, { "epoch": 2.0297091499188618, "grad_norm": 4.749457359313965, "learning_rate": 7.409682179290869e-06, "loss": 0.1605, "step": 341460 }, { "epoch": 2.02976859199553, "grad_norm": 4.963404655456543, "learning_rate": 7.409500371331432e-06, "loss": 0.1521, "step": 341470 }, { "epoch": 2.029828034072198, "grad_norm": 4.189428806304932, "learning_rate": 7.409318559222549e-06, "loss": 0.1681, "step": 341480 }, { "epoch": 2.0298874761488666, "grad_norm": 4.884548664093018, "learning_rate": 7.409136742964531e-06, "loss": 0.1456, "step": 341490 }, { "epoch": 2.029946918225535, "grad_norm": 3.837475299835205, "learning_rate": 7.408954922557692e-06, "loss": 0.1568, "step": 341500 }, { "epoch": 2.0300063603022034, "grad_norm": 3.0792603492736816, "learning_rate": 7.408773098002347e-06, "loss": 0.1677, "step": 341510 }, { "epoch": 2.030065802378872, "grad_norm": 4.033732891082764, "learning_rate": 7.408591269298806e-06, "loss": 0.1449, "step": 341520 }, { "epoch": 2.03012524445554, "grad_norm": 6.371877193450928, "learning_rate": 7.4084094364473825e-06, "loss": 0.154, "step": 341530 }, { "epoch": 2.0301846865322086, "grad_norm": 4.743654251098633, "learning_rate": 7.4082275994483925e-06, "loss": 0.159, "step": 341540 }, { "epoch": 2.030244128608877, "grad_norm": 5.2844343185424805, "learning_rate": 7.408045758302146e-06, "loss": 0.17, "step": 341550 }, { "epoch": 2.0303035706855455, "grad_norm": 4.531750679016113, "learning_rate": 7.407863913008957e-06, "loss": 0.1519, "step": 341560 }, { "epoch": 2.030363012762214, "grad_norm": 3.811990261077881, "learning_rate": 7.407682063569139e-06, "loss": 0.1833, "step": 341570 }, { "epoch": 2.0304224548388823, "grad_norm": 3.729494333267212, "learning_rate": 7.4075002099830055e-06, "loss": 0.1373, "step": 341580 }, { "epoch": 2.0304818969155507, "grad_norm": 5.386635780334473, "learning_rate": 7.40731835225087e-06, "loss": 0.1564, "step": 341590 }, { "epoch": 2.030541338992219, "grad_norm": 4.1393842697143555, "learning_rate": 7.407136490373045e-06, "loss": 0.1594, "step": 341600 }, { "epoch": 2.0306007810688875, "grad_norm": 5.782165050506592, "learning_rate": 7.406954624349843e-06, "loss": 0.1579, "step": 341610 }, { "epoch": 2.030660223145556, "grad_norm": 3.87986159324646, "learning_rate": 7.4067727541815785e-06, "loss": 0.1412, "step": 341620 }, { "epoch": 2.0307196652222244, "grad_norm": 4.865036964416504, "learning_rate": 7.406590879868564e-06, "loss": 0.1417, "step": 341630 }, { "epoch": 2.0307791072988928, "grad_norm": 4.5056047439575195, "learning_rate": 7.406409001411113e-06, "loss": 0.1513, "step": 341640 }, { "epoch": 2.030838549375561, "grad_norm": 4.565554141998291, "learning_rate": 7.406227118809538e-06, "loss": 0.1613, "step": 341650 }, { "epoch": 2.030897991452229, "grad_norm": 4.9672675132751465, "learning_rate": 7.406045232064154e-06, "loss": 0.1558, "step": 341660 }, { "epoch": 2.0309574335288976, "grad_norm": 4.209778785705566, "learning_rate": 7.405863341175272e-06, "loss": 0.1531, "step": 341670 }, { "epoch": 2.031016875605566, "grad_norm": 2.9234609603881836, "learning_rate": 7.405681446143207e-06, "loss": 0.144, "step": 341680 }, { "epoch": 2.0310763176822344, "grad_norm": 5.133693218231201, "learning_rate": 7.40549954696827e-06, "loss": 0.1638, "step": 341690 }, { "epoch": 2.031135759758903, "grad_norm": 4.924614906311035, "learning_rate": 7.405317643650778e-06, "loss": 0.1564, "step": 341700 }, { "epoch": 2.0311952018355712, "grad_norm": 4.786227703094482, "learning_rate": 7.40513573619104e-06, "loss": 0.1561, "step": 341710 }, { "epoch": 2.0312546439122396, "grad_norm": 3.9343388080596924, "learning_rate": 7.404953824589373e-06, "loss": 0.1492, "step": 341720 }, { "epoch": 2.031314085988908, "grad_norm": 6.262111663818359, "learning_rate": 7.404771908846087e-06, "loss": 0.1795, "step": 341730 }, { "epoch": 2.0313735280655765, "grad_norm": 3.728947162628174, "learning_rate": 7.404589988961498e-06, "loss": 0.1498, "step": 341740 }, { "epoch": 2.031432970142245, "grad_norm": 4.218722820281982, "learning_rate": 7.4044080649359174e-06, "loss": 0.1553, "step": 341750 }, { "epoch": 2.0314924122189133, "grad_norm": 4.262979030609131, "learning_rate": 7.40422613676966e-06, "loss": 0.1618, "step": 341760 }, { "epoch": 2.0315518542955817, "grad_norm": 4.394123077392578, "learning_rate": 7.404044204463038e-06, "loss": 0.1549, "step": 341770 }, { "epoch": 2.03161129637225, "grad_norm": 3.943934440612793, "learning_rate": 7.403862268016364e-06, "loss": 0.1579, "step": 341780 }, { "epoch": 2.0316707384489185, "grad_norm": 5.437176704406738, "learning_rate": 7.403680327429954e-06, "loss": 0.1493, "step": 341790 }, { "epoch": 2.031730180525587, "grad_norm": 4.320186614990234, "learning_rate": 7.403498382704119e-06, "loss": 0.1652, "step": 341800 }, { "epoch": 2.0317896226022554, "grad_norm": 3.808541774749756, "learning_rate": 7.403316433839173e-06, "loss": 0.127, "step": 341810 }, { "epoch": 2.031849064678924, "grad_norm": 2.7192232608795166, "learning_rate": 7.403134480835428e-06, "loss": 0.162, "step": 341820 }, { "epoch": 2.031908506755592, "grad_norm": 3.8039186000823975, "learning_rate": 7.402952523693201e-06, "loss": 0.1566, "step": 341830 }, { "epoch": 2.0319679488322606, "grad_norm": 3.728015184402466, "learning_rate": 7.402770562412802e-06, "loss": 0.1328, "step": 341840 }, { "epoch": 2.0320273909089286, "grad_norm": 4.111863613128662, "learning_rate": 7.402588596994544e-06, "loss": 0.1572, "step": 341850 }, { "epoch": 2.032086832985597, "grad_norm": 4.994560718536377, "learning_rate": 7.402406627438744e-06, "loss": 0.1577, "step": 341860 }, { "epoch": 2.0321462750622654, "grad_norm": 3.5589187145233154, "learning_rate": 7.402224653745713e-06, "loss": 0.143, "step": 341870 }, { "epoch": 2.032205717138934, "grad_norm": 5.069854736328125, "learning_rate": 7.402042675915762e-06, "loss": 0.1453, "step": 341880 }, { "epoch": 2.0322651592156022, "grad_norm": 4.197709083557129, "learning_rate": 7.4018606939492095e-06, "loss": 0.1632, "step": 341890 }, { "epoch": 2.0323246012922707, "grad_norm": 4.89774751663208, "learning_rate": 7.401678707846367e-06, "loss": 0.1619, "step": 341900 }, { "epoch": 2.032384043368939, "grad_norm": 5.272623538970947, "learning_rate": 7.401496717607545e-06, "loss": 0.1461, "step": 341910 }, { "epoch": 2.0324434854456075, "grad_norm": 2.7715020179748535, "learning_rate": 7.4013147232330585e-06, "loss": 0.1492, "step": 341920 }, { "epoch": 2.032502927522276, "grad_norm": 3.985208749771118, "learning_rate": 7.401132724723224e-06, "loss": 0.1667, "step": 341930 }, { "epoch": 2.0325623695989443, "grad_norm": 4.638819694519043, "learning_rate": 7.40095072207835e-06, "loss": 0.1457, "step": 341940 }, { "epoch": 2.0326218116756127, "grad_norm": 3.613696813583374, "learning_rate": 7.400768715298754e-06, "loss": 0.1464, "step": 341950 }, { "epoch": 2.032681253752281, "grad_norm": 5.634185314178467, "learning_rate": 7.400586704384748e-06, "loss": 0.159, "step": 341960 }, { "epoch": 2.0327406958289496, "grad_norm": 5.106379508972168, "learning_rate": 7.4004046893366455e-06, "loss": 0.1587, "step": 341970 }, { "epoch": 2.032800137905618, "grad_norm": 5.040439605712891, "learning_rate": 7.400222670154757e-06, "loss": 0.1462, "step": 341980 }, { "epoch": 2.0328595799822864, "grad_norm": 3.7968664169311523, "learning_rate": 7.400040646839402e-06, "loss": 0.1581, "step": 341990 }, { "epoch": 2.032919022058955, "grad_norm": 4.1583638191223145, "learning_rate": 7.39985861939089e-06, "loss": 0.1519, "step": 342000 }, { "epoch": 2.032978464135623, "grad_norm": 6.144442558288574, "learning_rate": 7.3996765878095335e-06, "loss": 0.1556, "step": 342010 }, { "epoch": 2.0330379062122916, "grad_norm": 3.7547965049743652, "learning_rate": 7.399494552095648e-06, "loss": 0.1428, "step": 342020 }, { "epoch": 2.0330973482889596, "grad_norm": 2.7263996601104736, "learning_rate": 7.399312512249547e-06, "loss": 0.1557, "step": 342030 }, { "epoch": 2.033156790365628, "grad_norm": 4.497193813323975, "learning_rate": 7.399130468271545e-06, "loss": 0.1417, "step": 342040 }, { "epoch": 2.0332162324422964, "grad_norm": 4.494138717651367, "learning_rate": 7.398948420161951e-06, "loss": 0.1611, "step": 342050 }, { "epoch": 2.033275674518965, "grad_norm": 3.4594202041625977, "learning_rate": 7.398766367921084e-06, "loss": 0.149, "step": 342060 }, { "epoch": 2.0333351165956333, "grad_norm": 3.6335906982421875, "learning_rate": 7.398584311549255e-06, "loss": 0.1561, "step": 342070 }, { "epoch": 2.0333945586723017, "grad_norm": 4.426351070404053, "learning_rate": 7.3984022510467765e-06, "loss": 0.1571, "step": 342080 }, { "epoch": 2.03345400074897, "grad_norm": 3.987480878829956, "learning_rate": 7.3982201864139635e-06, "loss": 0.1458, "step": 342090 }, { "epoch": 2.0335134428256385, "grad_norm": 5.210380554199219, "learning_rate": 7.39803811765113e-06, "loss": 0.1575, "step": 342100 }, { "epoch": 2.033572884902307, "grad_norm": 3.5322725772857666, "learning_rate": 7.397856044758587e-06, "loss": 0.1519, "step": 342110 }, { "epoch": 2.0336323269789753, "grad_norm": 3.601806163787842, "learning_rate": 7.3976739677366515e-06, "loss": 0.1283, "step": 342120 }, { "epoch": 2.0336917690556437, "grad_norm": 4.203274726867676, "learning_rate": 7.397491886585634e-06, "loss": 0.1612, "step": 342130 }, { "epoch": 2.033751211132312, "grad_norm": 3.8982043266296387, "learning_rate": 7.39730980130585e-06, "loss": 0.1585, "step": 342140 }, { "epoch": 2.0338106532089806, "grad_norm": 4.585111141204834, "learning_rate": 7.397127711897613e-06, "loss": 0.158, "step": 342150 }, { "epoch": 2.033870095285649, "grad_norm": 3.9404141902923584, "learning_rate": 7.396945618361235e-06, "loss": 0.1661, "step": 342160 }, { "epoch": 2.0339295373623174, "grad_norm": 3.5958850383758545, "learning_rate": 7.396763520697033e-06, "loss": 0.1465, "step": 342170 }, { "epoch": 2.033988979438986, "grad_norm": 3.9641175270080566, "learning_rate": 7.396581418905315e-06, "loss": 0.1393, "step": 342180 }, { "epoch": 2.0340484215156542, "grad_norm": 3.8553192615509033, "learning_rate": 7.3963993129864e-06, "loss": 0.1687, "step": 342190 }, { "epoch": 2.0341078635923227, "grad_norm": 4.701083660125732, "learning_rate": 7.396217202940599e-06, "loss": 0.1555, "step": 342200 }, { "epoch": 2.034167305668991, "grad_norm": 5.000927448272705, "learning_rate": 7.396035088768225e-06, "loss": 0.1651, "step": 342210 }, { "epoch": 2.034226747745659, "grad_norm": 5.013103008270264, "learning_rate": 7.395852970469595e-06, "loss": 0.1396, "step": 342220 }, { "epoch": 2.0342861898223275, "grad_norm": 4.579346179962158, "learning_rate": 7.395670848045018e-06, "loss": 0.1502, "step": 342230 }, { "epoch": 2.034345631898996, "grad_norm": 4.327853202819824, "learning_rate": 7.39548872149481e-06, "loss": 0.1392, "step": 342240 }, { "epoch": 2.0344050739756643, "grad_norm": 4.187992572784424, "learning_rate": 7.3953065908192856e-06, "loss": 0.1489, "step": 342250 }, { "epoch": 2.0344645160523327, "grad_norm": 5.23176908493042, "learning_rate": 7.395124456018757e-06, "loss": 0.1397, "step": 342260 }, { "epoch": 2.034523958129001, "grad_norm": 5.1103129386901855, "learning_rate": 7.394942317093539e-06, "loss": 0.1439, "step": 342270 }, { "epoch": 2.0345834002056695, "grad_norm": 5.08458948135376, "learning_rate": 7.3947601740439446e-06, "loss": 0.1551, "step": 342280 }, { "epoch": 2.034642842282338, "grad_norm": 4.847832679748535, "learning_rate": 7.394578026870287e-06, "loss": 0.1483, "step": 342290 }, { "epoch": 2.0347022843590064, "grad_norm": 3.549757480621338, "learning_rate": 7.394395875572879e-06, "loss": 0.1238, "step": 342300 }, { "epoch": 2.0347617264356748, "grad_norm": 4.447208881378174, "learning_rate": 7.394213720152038e-06, "loss": 0.1404, "step": 342310 }, { "epoch": 2.034821168512343, "grad_norm": 3.4444403648376465, "learning_rate": 7.394031560608075e-06, "loss": 0.1518, "step": 342320 }, { "epoch": 2.0348806105890116, "grad_norm": 4.129439353942871, "learning_rate": 7.393849396941302e-06, "loss": 0.1565, "step": 342330 }, { "epoch": 2.03494005266568, "grad_norm": 3.278001546859741, "learning_rate": 7.393667229152036e-06, "loss": 0.1619, "step": 342340 }, { "epoch": 2.0349994947423484, "grad_norm": 4.88456392288208, "learning_rate": 7.3934850572405895e-06, "loss": 0.1627, "step": 342350 }, { "epoch": 2.035058936819017, "grad_norm": 4.33806037902832, "learning_rate": 7.393302881207276e-06, "loss": 0.1582, "step": 342360 }, { "epoch": 2.0351183788956853, "grad_norm": 5.506080150604248, "learning_rate": 7.3931207010524085e-06, "loss": 0.1645, "step": 342370 }, { "epoch": 2.0351778209723537, "grad_norm": 4.3706889152526855, "learning_rate": 7.3929385167763035e-06, "loss": 0.1621, "step": 342380 }, { "epoch": 2.035237263049022, "grad_norm": 6.383487701416016, "learning_rate": 7.3927563283792714e-06, "loss": 0.1714, "step": 342390 }, { "epoch": 2.03529670512569, "grad_norm": 2.6931254863739014, "learning_rate": 7.392574135861627e-06, "loss": 0.1521, "step": 342400 }, { "epoch": 2.0353561472023585, "grad_norm": 3.784301996231079, "learning_rate": 7.392391939223686e-06, "loss": 0.1502, "step": 342410 }, { "epoch": 2.035415589279027, "grad_norm": 5.1271562576293945, "learning_rate": 7.392209738465761e-06, "loss": 0.151, "step": 342420 }, { "epoch": 2.0354750313556953, "grad_norm": 5.116186141967773, "learning_rate": 7.392027533588164e-06, "loss": 0.1573, "step": 342430 }, { "epoch": 2.0355344734323637, "grad_norm": 3.986844301223755, "learning_rate": 7.39184532459121e-06, "loss": 0.1542, "step": 342440 }, { "epoch": 2.035593915509032, "grad_norm": 4.358508110046387, "learning_rate": 7.391663111475215e-06, "loss": 0.1465, "step": 342450 }, { "epoch": 2.0356533575857005, "grad_norm": 3.466888189315796, "learning_rate": 7.391480894240488e-06, "loss": 0.1501, "step": 342460 }, { "epoch": 2.035712799662369, "grad_norm": 3.842336416244507, "learning_rate": 7.391298672887346e-06, "loss": 0.1468, "step": 342470 }, { "epoch": 2.0357722417390374, "grad_norm": 4.37584114074707, "learning_rate": 7.3911164474161036e-06, "loss": 0.1584, "step": 342480 }, { "epoch": 2.035831683815706, "grad_norm": 3.7204785346984863, "learning_rate": 7.390934217827072e-06, "loss": 0.1436, "step": 342490 }, { "epoch": 2.035891125892374, "grad_norm": 4.191629886627197, "learning_rate": 7.3907519841205674e-06, "loss": 0.1573, "step": 342500 }, { "epoch": 2.0359505679690426, "grad_norm": 4.688618183135986, "learning_rate": 7.390569746296903e-06, "loss": 0.15, "step": 342510 }, { "epoch": 2.036010010045711, "grad_norm": 5.226485729217529, "learning_rate": 7.3903875043563925e-06, "loss": 0.1499, "step": 342520 }, { "epoch": 2.0360694521223794, "grad_norm": 4.584770679473877, "learning_rate": 7.390205258299348e-06, "loss": 0.1694, "step": 342530 }, { "epoch": 2.036128894199048, "grad_norm": 2.9770071506500244, "learning_rate": 7.390023008126086e-06, "loss": 0.1587, "step": 342540 }, { "epoch": 2.0361883362757163, "grad_norm": 5.590970516204834, "learning_rate": 7.38984075383692e-06, "loss": 0.1405, "step": 342550 }, { "epoch": 2.0362477783523847, "grad_norm": 3.7896859645843506, "learning_rate": 7.38965849543216e-06, "loss": 0.1611, "step": 342560 }, { "epoch": 2.036307220429053, "grad_norm": 4.380741596221924, "learning_rate": 7.389476232912125e-06, "loss": 0.1537, "step": 342570 }, { "epoch": 2.0363666625057215, "grad_norm": 3.6420438289642334, "learning_rate": 7.389293966277127e-06, "loss": 0.1672, "step": 342580 }, { "epoch": 2.0364261045823895, "grad_norm": 3.5167741775512695, "learning_rate": 7.38911169552748e-06, "loss": 0.1337, "step": 342590 }, { "epoch": 2.036485546659058, "grad_norm": 3.2591392993927, "learning_rate": 7.388929420663496e-06, "loss": 0.1515, "step": 342600 }, { "epoch": 2.0365449887357263, "grad_norm": 5.850749969482422, "learning_rate": 7.388747141685492e-06, "loss": 0.1576, "step": 342610 }, { "epoch": 2.0366044308123947, "grad_norm": 4.632018089294434, "learning_rate": 7.388564858593781e-06, "loss": 0.146, "step": 342620 }, { "epoch": 2.036663872889063, "grad_norm": 3.751913547515869, "learning_rate": 7.388382571388674e-06, "loss": 0.1696, "step": 342630 }, { "epoch": 2.0367233149657316, "grad_norm": 4.040346145629883, "learning_rate": 7.388200280070489e-06, "loss": 0.1295, "step": 342640 }, { "epoch": 2.0367827570424, "grad_norm": 4.518320083618164, "learning_rate": 7.388017984639537e-06, "loss": 0.1528, "step": 342650 }, { "epoch": 2.0368421991190684, "grad_norm": 4.113534927368164, "learning_rate": 7.387835685096134e-06, "loss": 0.1552, "step": 342660 }, { "epoch": 2.036901641195737, "grad_norm": 5.094455242156982, "learning_rate": 7.3876533814405924e-06, "loss": 0.1489, "step": 342670 }, { "epoch": 2.036961083272405, "grad_norm": 4.430411338806152, "learning_rate": 7.387471073673227e-06, "loss": 0.1722, "step": 342680 }, { "epoch": 2.0370205253490736, "grad_norm": 3.503335952758789, "learning_rate": 7.387288761794352e-06, "loss": 0.1299, "step": 342690 }, { "epoch": 2.037079967425742, "grad_norm": 4.624948024749756, "learning_rate": 7.387106445804279e-06, "loss": 0.1711, "step": 342700 }, { "epoch": 2.0371394095024105, "grad_norm": 3.5093576908111572, "learning_rate": 7.386924125703327e-06, "loss": 0.1557, "step": 342710 }, { "epoch": 2.037198851579079, "grad_norm": 4.589513778686523, "learning_rate": 7.386741801491805e-06, "loss": 0.1477, "step": 342720 }, { "epoch": 2.0372582936557473, "grad_norm": 4.397780895233154, "learning_rate": 7.386559473170029e-06, "loss": 0.1548, "step": 342730 }, { "epoch": 2.0373177357324157, "grad_norm": 2.780874252319336, "learning_rate": 7.3863771407383135e-06, "loss": 0.1508, "step": 342740 }, { "epoch": 2.037377177809084, "grad_norm": 5.561897277832031, "learning_rate": 7.3861948041969715e-06, "loss": 0.1646, "step": 342750 }, { "epoch": 2.0374366198857525, "grad_norm": 3.595670700073242, "learning_rate": 7.386012463546316e-06, "loss": 0.1419, "step": 342760 }, { "epoch": 2.0374960619624205, "grad_norm": 5.760647773742676, "learning_rate": 7.385830118786664e-06, "loss": 0.1596, "step": 342770 }, { "epoch": 2.037555504039089, "grad_norm": 4.175973892211914, "learning_rate": 7.385647769918329e-06, "loss": 0.1331, "step": 342780 }, { "epoch": 2.0376149461157573, "grad_norm": 3.911067247390747, "learning_rate": 7.385465416941619e-06, "loss": 0.1632, "step": 342790 }, { "epoch": 2.0376743881924257, "grad_norm": 4.405526161193848, "learning_rate": 7.385283059856857e-06, "loss": 0.148, "step": 342800 }, { "epoch": 2.037733830269094, "grad_norm": 3.9011588096618652, "learning_rate": 7.385100698664353e-06, "loss": 0.1657, "step": 342810 }, { "epoch": 2.0377932723457626, "grad_norm": 5.5835747718811035, "learning_rate": 7.3849183333644195e-06, "loss": 0.1461, "step": 342820 }, { "epoch": 2.037852714422431, "grad_norm": 4.6787590980529785, "learning_rate": 7.3847359639573724e-06, "loss": 0.1367, "step": 342830 }, { "epoch": 2.0379121564990994, "grad_norm": 3.959470748901367, "learning_rate": 7.384553590443526e-06, "loss": 0.1487, "step": 342840 }, { "epoch": 2.037971598575768, "grad_norm": 3.2619733810424805, "learning_rate": 7.384371212823193e-06, "loss": 0.1625, "step": 342850 }, { "epoch": 2.0380310406524362, "grad_norm": 4.260519981384277, "learning_rate": 7.384188831096689e-06, "loss": 0.137, "step": 342860 }, { "epoch": 2.0380904827291046, "grad_norm": 4.25253438949585, "learning_rate": 7.384006445264328e-06, "loss": 0.1438, "step": 342870 }, { "epoch": 2.038149924805773, "grad_norm": 5.186259746551514, "learning_rate": 7.383824055326423e-06, "loss": 0.1562, "step": 342880 }, { "epoch": 2.0382093668824415, "grad_norm": 5.922150611877441, "learning_rate": 7.383641661283287e-06, "loss": 0.1629, "step": 342890 }, { "epoch": 2.03826880895911, "grad_norm": 5.119959354400635, "learning_rate": 7.383459263135236e-06, "loss": 0.1335, "step": 342900 }, { "epoch": 2.0383282510357783, "grad_norm": 5.8943328857421875, "learning_rate": 7.383276860882584e-06, "loss": 0.1524, "step": 342910 }, { "epoch": 2.0383876931124467, "grad_norm": 4.805303573608398, "learning_rate": 7.383094454525646e-06, "loss": 0.1472, "step": 342920 }, { "epoch": 2.038447135189115, "grad_norm": 4.124302864074707, "learning_rate": 7.382912044064735e-06, "loss": 0.1527, "step": 342930 }, { "epoch": 2.0385065772657835, "grad_norm": 5.255245685577393, "learning_rate": 7.382729629500165e-06, "loss": 0.1467, "step": 342940 }, { "epoch": 2.038566019342452, "grad_norm": 4.269928455352783, "learning_rate": 7.38254721083225e-06, "loss": 0.1592, "step": 342950 }, { "epoch": 2.03862546141912, "grad_norm": 4.842513561248779, "learning_rate": 7.382364788061304e-06, "loss": 0.1545, "step": 342960 }, { "epoch": 2.0386849034957883, "grad_norm": 3.275022029876709, "learning_rate": 7.382182361187642e-06, "loss": 0.1507, "step": 342970 }, { "epoch": 2.0387443455724568, "grad_norm": 6.039428234100342, "learning_rate": 7.381999930211576e-06, "loss": 0.1537, "step": 342980 }, { "epoch": 2.038803787649125, "grad_norm": 3.1778955459594727, "learning_rate": 7.3818174951334245e-06, "loss": 0.1602, "step": 342990 }, { "epoch": 2.0388632297257936, "grad_norm": 3.489863634109497, "learning_rate": 7.381635055953498e-06, "loss": 0.1576, "step": 343000 }, { "epoch": 2.038922671802462, "grad_norm": 3.3780252933502197, "learning_rate": 7.3814526126721105e-06, "loss": 0.1436, "step": 343010 }, { "epoch": 2.0389821138791304, "grad_norm": 3.6418824195861816, "learning_rate": 7.3812701652895794e-06, "loss": 0.1557, "step": 343020 }, { "epoch": 2.039041555955799, "grad_norm": 3.750537157058716, "learning_rate": 7.381087713806216e-06, "loss": 0.1504, "step": 343030 }, { "epoch": 2.0391009980324672, "grad_norm": 4.930147171020508, "learning_rate": 7.380905258222336e-06, "loss": 0.1687, "step": 343040 }, { "epoch": 2.0391604401091357, "grad_norm": 4.2999396324157715, "learning_rate": 7.380722798538252e-06, "loss": 0.1535, "step": 343050 }, { "epoch": 2.039219882185804, "grad_norm": 3.850743055343628, "learning_rate": 7.38054033475428e-06, "loss": 0.1514, "step": 343060 }, { "epoch": 2.0392793242624725, "grad_norm": 3.1139097213745117, "learning_rate": 7.380357866870735e-06, "loss": 0.1514, "step": 343070 }, { "epoch": 2.039338766339141, "grad_norm": 4.495733261108398, "learning_rate": 7.380175394887927e-06, "loss": 0.1383, "step": 343080 }, { "epoch": 2.0393982084158093, "grad_norm": 3.9315829277038574, "learning_rate": 7.379992918806176e-06, "loss": 0.1606, "step": 343090 }, { "epoch": 2.0394576504924777, "grad_norm": 4.111230850219727, "learning_rate": 7.379810438625792e-06, "loss": 0.1563, "step": 343100 }, { "epoch": 2.039517092569146, "grad_norm": 4.40473747253418, "learning_rate": 7.379627954347089e-06, "loss": 0.1567, "step": 343110 }, { "epoch": 2.0395765346458146, "grad_norm": 4.146705150604248, "learning_rate": 7.379445465970383e-06, "loss": 0.148, "step": 343120 }, { "epoch": 2.039635976722483, "grad_norm": 4.117747783660889, "learning_rate": 7.379262973495989e-06, "loss": 0.1485, "step": 343130 }, { "epoch": 2.039695418799151, "grad_norm": 3.739961862564087, "learning_rate": 7.37908047692422e-06, "loss": 0.1479, "step": 343140 }, { "epoch": 2.0397548608758194, "grad_norm": 3.999772071838379, "learning_rate": 7.378897976255391e-06, "loss": 0.125, "step": 343150 }, { "epoch": 2.039814302952488, "grad_norm": 4.640206336975098, "learning_rate": 7.378715471489815e-06, "loss": 0.1653, "step": 343160 }, { "epoch": 2.039873745029156, "grad_norm": 4.644510269165039, "learning_rate": 7.378532962627808e-06, "loss": 0.162, "step": 343170 }, { "epoch": 2.0399331871058246, "grad_norm": 5.176710605621338, "learning_rate": 7.3783504496696826e-06, "loss": 0.1617, "step": 343180 }, { "epoch": 2.039992629182493, "grad_norm": 3.7581117153167725, "learning_rate": 7.378167932615754e-06, "loss": 0.1439, "step": 343190 }, { "epoch": 2.0400520712591614, "grad_norm": 4.21075963973999, "learning_rate": 7.377985411466337e-06, "loss": 0.1508, "step": 343200 }, { "epoch": 2.04011151333583, "grad_norm": 3.9367382526397705, "learning_rate": 7.377802886221744e-06, "loss": 0.1478, "step": 343210 }, { "epoch": 2.0401709554124983, "grad_norm": 3.8517537117004395, "learning_rate": 7.3776203568822924e-06, "loss": 0.167, "step": 343220 }, { "epoch": 2.0402303974891667, "grad_norm": 4.44027042388916, "learning_rate": 7.377437823448294e-06, "loss": 0.1466, "step": 343230 }, { "epoch": 2.040289839565835, "grad_norm": 3.822512149810791, "learning_rate": 7.377255285920064e-06, "loss": 0.1367, "step": 343240 }, { "epoch": 2.0403492816425035, "grad_norm": 4.576281547546387, "learning_rate": 7.377072744297917e-06, "loss": 0.1683, "step": 343250 }, { "epoch": 2.040408723719172, "grad_norm": 3.772016763687134, "learning_rate": 7.376890198582167e-06, "loss": 0.1424, "step": 343260 }, { "epoch": 2.0404681657958403, "grad_norm": 4.257792949676514, "learning_rate": 7.376707648773129e-06, "loss": 0.1544, "step": 343270 }, { "epoch": 2.0405276078725088, "grad_norm": 3.778092622756958, "learning_rate": 7.376525094871117e-06, "loss": 0.1494, "step": 343280 }, { "epoch": 2.040587049949177, "grad_norm": 3.377962589263916, "learning_rate": 7.376342536876444e-06, "loss": 0.1532, "step": 343290 }, { "epoch": 2.0406464920258456, "grad_norm": 3.0723087787628174, "learning_rate": 7.3761599747894276e-06, "loss": 0.1633, "step": 343300 }, { "epoch": 2.040705934102514, "grad_norm": 4.6632184982299805, "learning_rate": 7.3759774086103774e-06, "loss": 0.1752, "step": 343310 }, { "epoch": 2.0407653761791824, "grad_norm": 4.749109745025635, "learning_rate": 7.375794838339613e-06, "loss": 0.1557, "step": 343320 }, { "epoch": 2.0408248182558504, "grad_norm": 4.3373918533325195, "learning_rate": 7.375612263977445e-06, "loss": 0.1499, "step": 343330 }, { "epoch": 2.040884260332519, "grad_norm": 6.601983070373535, "learning_rate": 7.37542968552419e-06, "loss": 0.1646, "step": 343340 }, { "epoch": 2.040943702409187, "grad_norm": 4.1859869956970215, "learning_rate": 7.375247102980161e-06, "loss": 0.1418, "step": 343350 }, { "epoch": 2.0410031444858556, "grad_norm": 3.557150363922119, "learning_rate": 7.375064516345674e-06, "loss": 0.1513, "step": 343360 }, { "epoch": 2.041062586562524, "grad_norm": 2.918290138244629, "learning_rate": 7.374881925621043e-06, "loss": 0.1409, "step": 343370 }, { "epoch": 2.0411220286391925, "grad_norm": 4.214348793029785, "learning_rate": 7.374699330806579e-06, "loss": 0.1565, "step": 343380 }, { "epoch": 2.041181470715861, "grad_norm": 3.652244806289673, "learning_rate": 7.374516731902603e-06, "loss": 0.1575, "step": 343390 }, { "epoch": 2.0412409127925293, "grad_norm": 3.6374528408050537, "learning_rate": 7.374334128909424e-06, "loss": 0.1233, "step": 343400 }, { "epoch": 2.0413003548691977, "grad_norm": 4.618439674377441, "learning_rate": 7.3741515218273575e-06, "loss": 0.1638, "step": 343410 }, { "epoch": 2.041359796945866, "grad_norm": 4.445960521697998, "learning_rate": 7.37396891065672e-06, "loss": 0.1638, "step": 343420 }, { "epoch": 2.0414192390225345, "grad_norm": 6.44254207611084, "learning_rate": 7.3737862953978255e-06, "loss": 0.1676, "step": 343430 }, { "epoch": 2.041478681099203, "grad_norm": 4.270389556884766, "learning_rate": 7.3736036760509865e-06, "loss": 0.1606, "step": 343440 }, { "epoch": 2.0415381231758714, "grad_norm": 3.6974258422851562, "learning_rate": 7.373421052616518e-06, "loss": 0.1548, "step": 343450 }, { "epoch": 2.0415975652525398, "grad_norm": 5.184846878051758, "learning_rate": 7.373238425094736e-06, "loss": 0.1478, "step": 343460 }, { "epoch": 2.041657007329208, "grad_norm": 6.259243011474609, "learning_rate": 7.3730557934859545e-06, "loss": 0.1693, "step": 343470 }, { "epoch": 2.0417164494058766, "grad_norm": 3.307849407196045, "learning_rate": 7.3728731577904885e-06, "loss": 0.1427, "step": 343480 }, { "epoch": 2.041775891482545, "grad_norm": 4.537566661834717, "learning_rate": 7.372690518008652e-06, "loss": 0.1538, "step": 343490 }, { "epoch": 2.0418353335592134, "grad_norm": 3.6255674362182617, "learning_rate": 7.372507874140759e-06, "loss": 0.1638, "step": 343500 }, { "epoch": 2.0418947756358814, "grad_norm": 4.532138347625732, "learning_rate": 7.372325226187123e-06, "loss": 0.1397, "step": 343510 }, { "epoch": 2.04195421771255, "grad_norm": 3.464933395385742, "learning_rate": 7.372142574148061e-06, "loss": 0.1446, "step": 343520 }, { "epoch": 2.0420136597892182, "grad_norm": 4.640864849090576, "learning_rate": 7.371959918023887e-06, "loss": 0.1518, "step": 343530 }, { "epoch": 2.0420731018658866, "grad_norm": 4.352784156799316, "learning_rate": 7.371777257814914e-06, "loss": 0.1685, "step": 343540 }, { "epoch": 2.042132543942555, "grad_norm": 4.0980401039123535, "learning_rate": 7.371594593521458e-06, "loss": 0.1467, "step": 343550 }, { "epoch": 2.0421919860192235, "grad_norm": 4.4205498695373535, "learning_rate": 7.371411925143832e-06, "loss": 0.163, "step": 343560 }, { "epoch": 2.042251428095892, "grad_norm": 4.412920951843262, "learning_rate": 7.3712292526823524e-06, "loss": 0.1567, "step": 343570 }, { "epoch": 2.0423108701725603, "grad_norm": 5.32465124130249, "learning_rate": 7.371046576137333e-06, "loss": 0.1708, "step": 343580 }, { "epoch": 2.0423703122492287, "grad_norm": 3.581611156463623, "learning_rate": 7.37086389550909e-06, "loss": 0.1392, "step": 343590 }, { "epoch": 2.042429754325897, "grad_norm": 5.0516157150268555, "learning_rate": 7.3706812107979345e-06, "loss": 0.1559, "step": 343600 }, { "epoch": 2.0424891964025655, "grad_norm": 4.919041156768799, "learning_rate": 7.370498522004184e-06, "loss": 0.1529, "step": 343610 }, { "epoch": 2.042548638479234, "grad_norm": 3.6544673442840576, "learning_rate": 7.370315829128153e-06, "loss": 0.1385, "step": 343620 }, { "epoch": 2.0426080805559024, "grad_norm": 4.198539733886719, "learning_rate": 7.370133132170154e-06, "loss": 0.1854, "step": 343630 }, { "epoch": 2.042667522632571, "grad_norm": 4.916424751281738, "learning_rate": 7.369950431130504e-06, "loss": 0.1687, "step": 343640 }, { "epoch": 2.042726964709239, "grad_norm": 4.453660488128662, "learning_rate": 7.369767726009516e-06, "loss": 0.1687, "step": 343650 }, { "epoch": 2.0427864067859076, "grad_norm": 4.340653419494629, "learning_rate": 7.369585016807505e-06, "loss": 0.1541, "step": 343660 }, { "epoch": 2.042845848862576, "grad_norm": 5.581481456756592, "learning_rate": 7.369402303524785e-06, "loss": 0.1489, "step": 343670 }, { "epoch": 2.0429052909392444, "grad_norm": 4.1497578620910645, "learning_rate": 7.369219586161673e-06, "loss": 0.1583, "step": 343680 }, { "epoch": 2.042964733015913, "grad_norm": 4.202078819274902, "learning_rate": 7.369036864718482e-06, "loss": 0.1523, "step": 343690 }, { "epoch": 2.043024175092581, "grad_norm": 4.930681228637695, "learning_rate": 7.368854139195526e-06, "loss": 0.1339, "step": 343700 }, { "epoch": 2.0430836171692492, "grad_norm": 4.039124488830566, "learning_rate": 7.3686714095931215e-06, "loss": 0.1484, "step": 343710 }, { "epoch": 2.0431430592459177, "grad_norm": 5.468919277191162, "learning_rate": 7.368488675911582e-06, "loss": 0.1454, "step": 343720 }, { "epoch": 2.043202501322586, "grad_norm": 4.380799293518066, "learning_rate": 7.368305938151221e-06, "loss": 0.136, "step": 343730 }, { "epoch": 2.0432619433992545, "grad_norm": 3.55120587348938, "learning_rate": 7.368123196312357e-06, "loss": 0.1552, "step": 343740 }, { "epoch": 2.043321385475923, "grad_norm": 3.7859947681427, "learning_rate": 7.367940450395301e-06, "loss": 0.134, "step": 343750 }, { "epoch": 2.0433808275525913, "grad_norm": 4.5380120277404785, "learning_rate": 7.367757700400369e-06, "loss": 0.1682, "step": 343760 }, { "epoch": 2.0434402696292597, "grad_norm": 4.694995403289795, "learning_rate": 7.367574946327877e-06, "loss": 0.1555, "step": 343770 }, { "epoch": 2.043499711705928, "grad_norm": 5.256831169128418, "learning_rate": 7.367392188178136e-06, "loss": 0.1387, "step": 343780 }, { "epoch": 2.0435591537825966, "grad_norm": 6.682095527648926, "learning_rate": 7.367209425951465e-06, "loss": 0.1683, "step": 343790 }, { "epoch": 2.043618595859265, "grad_norm": 3.6255269050598145, "learning_rate": 7.367026659648175e-06, "loss": 0.1269, "step": 343800 }, { "epoch": 2.0436780379359334, "grad_norm": 3.0516815185546875, "learning_rate": 7.3668438892685855e-06, "loss": 0.141, "step": 343810 }, { "epoch": 2.043737480012602, "grad_norm": 5.112305641174316, "learning_rate": 7.366661114813007e-06, "loss": 0.1598, "step": 343820 }, { "epoch": 2.04379692208927, "grad_norm": 4.0979204177856445, "learning_rate": 7.366478336281755e-06, "loss": 0.1786, "step": 343830 }, { "epoch": 2.0438563641659386, "grad_norm": 2.7292227745056152, "learning_rate": 7.366295553675147e-06, "loss": 0.155, "step": 343840 }, { "epoch": 2.043915806242607, "grad_norm": 3.864828586578369, "learning_rate": 7.366112766993494e-06, "loss": 0.1552, "step": 343850 }, { "epoch": 2.0439752483192755, "grad_norm": 4.078824043273926, "learning_rate": 7.365929976237112e-06, "loss": 0.1283, "step": 343860 }, { "epoch": 2.044034690395944, "grad_norm": 6.058996200561523, "learning_rate": 7.365747181406318e-06, "loss": 0.1629, "step": 343870 }, { "epoch": 2.044094132472612, "grad_norm": 3.968888998031616, "learning_rate": 7.365564382501425e-06, "loss": 0.1469, "step": 343880 }, { "epoch": 2.0441535745492803, "grad_norm": 3.1835880279541016, "learning_rate": 7.3653815795227456e-06, "loss": 0.1412, "step": 343890 }, { "epoch": 2.0442130166259487, "grad_norm": 3.699521064758301, "learning_rate": 7.3651987724705975e-06, "loss": 0.1338, "step": 343900 }, { "epoch": 2.044272458702617, "grad_norm": 3.6770455837249756, "learning_rate": 7.365015961345297e-06, "loss": 0.1417, "step": 343910 }, { "epoch": 2.0443319007792855, "grad_norm": 4.299212455749512, "learning_rate": 7.364833146147156e-06, "loss": 0.1746, "step": 343920 }, { "epoch": 2.044391342855954, "grad_norm": 3.366821527481079, "learning_rate": 7.364650326876488e-06, "loss": 0.1516, "step": 343930 }, { "epoch": 2.0444507849326223, "grad_norm": 2.6618778705596924, "learning_rate": 7.364467503533612e-06, "loss": 0.1614, "step": 343940 }, { "epoch": 2.0445102270092907, "grad_norm": 3.77734375, "learning_rate": 7.364284676118841e-06, "loss": 0.1461, "step": 343950 }, { "epoch": 2.044569669085959, "grad_norm": 4.727577209472656, "learning_rate": 7.3641018446324895e-06, "loss": 0.1578, "step": 343960 }, { "epoch": 2.0446291111626276, "grad_norm": 5.931427955627441, "learning_rate": 7.363919009074872e-06, "loss": 0.1571, "step": 343970 }, { "epoch": 2.044688553239296, "grad_norm": 5.768977642059326, "learning_rate": 7.363736169446305e-06, "loss": 0.1753, "step": 343980 }, { "epoch": 2.0447479953159644, "grad_norm": 3.7435812950134277, "learning_rate": 7.3635533257471e-06, "loss": 0.1285, "step": 343990 }, { "epoch": 2.044807437392633, "grad_norm": 3.070143222808838, "learning_rate": 7.363370477977576e-06, "loss": 0.1408, "step": 344000 }, { "epoch": 2.0448668794693012, "grad_norm": 3.2150628566741943, "learning_rate": 7.363187626138047e-06, "loss": 0.1517, "step": 344010 }, { "epoch": 2.0449263215459696, "grad_norm": 4.509464740753174, "learning_rate": 7.363004770228826e-06, "loss": 0.1411, "step": 344020 }, { "epoch": 2.044985763622638, "grad_norm": 3.612379550933838, "learning_rate": 7.362821910250226e-06, "loss": 0.1439, "step": 344030 }, { "epoch": 2.0450452056993065, "grad_norm": 3.8566975593566895, "learning_rate": 7.362639046202569e-06, "loss": 0.1476, "step": 344040 }, { "epoch": 2.045104647775975, "grad_norm": 5.346041679382324, "learning_rate": 7.362456178086164e-06, "loss": 0.1457, "step": 344050 }, { "epoch": 2.0451640898526433, "grad_norm": 4.5557379722595215, "learning_rate": 7.362273305901326e-06, "loss": 0.1361, "step": 344060 }, { "epoch": 2.0452235319293113, "grad_norm": 3.227550983428955, "learning_rate": 7.362090429648374e-06, "loss": 0.1477, "step": 344070 }, { "epoch": 2.0452829740059797, "grad_norm": 5.332570552825928, "learning_rate": 7.36190754932762e-06, "loss": 0.1529, "step": 344080 }, { "epoch": 2.045342416082648, "grad_norm": 5.782135963439941, "learning_rate": 7.361724664939378e-06, "loss": 0.1443, "step": 344090 }, { "epoch": 2.0454018581593165, "grad_norm": 4.219482421875, "learning_rate": 7.361541776483965e-06, "loss": 0.1586, "step": 344100 }, { "epoch": 2.045461300235985, "grad_norm": 4.689638614654541, "learning_rate": 7.3613588839616945e-06, "loss": 0.1676, "step": 344110 }, { "epoch": 2.0455207423126534, "grad_norm": 3.4144668579101562, "learning_rate": 7.361175987372883e-06, "loss": 0.1626, "step": 344120 }, { "epoch": 2.0455801843893218, "grad_norm": 4.081871509552002, "learning_rate": 7.360993086717844e-06, "loss": 0.1717, "step": 344130 }, { "epoch": 2.04563962646599, "grad_norm": 3.9222331047058105, "learning_rate": 7.360810181996895e-06, "loss": 0.1435, "step": 344140 }, { "epoch": 2.0456990685426586, "grad_norm": 2.356757402420044, "learning_rate": 7.3606272732103475e-06, "loss": 0.1546, "step": 344150 }, { "epoch": 2.045758510619327, "grad_norm": 4.802338600158691, "learning_rate": 7.360444360358519e-06, "loss": 0.1766, "step": 344160 }, { "epoch": 2.0458179526959954, "grad_norm": 3.837097644805908, "learning_rate": 7.360261443441726e-06, "loss": 0.1553, "step": 344170 }, { "epoch": 2.045877394772664, "grad_norm": 4.940368175506592, "learning_rate": 7.3600785224602776e-06, "loss": 0.1405, "step": 344180 }, { "epoch": 2.0459368368493323, "grad_norm": 4.197602272033691, "learning_rate": 7.359895597414493e-06, "loss": 0.1519, "step": 344190 }, { "epoch": 2.0459962789260007, "grad_norm": 4.699241638183594, "learning_rate": 7.359712668304689e-06, "loss": 0.1423, "step": 344200 }, { "epoch": 2.046055721002669, "grad_norm": 4.055728912353516, "learning_rate": 7.359529735131175e-06, "loss": 0.1561, "step": 344210 }, { "epoch": 2.0461151630793375, "grad_norm": 5.318215847015381, "learning_rate": 7.359346797894269e-06, "loss": 0.1528, "step": 344220 }, { "epoch": 2.046174605156006, "grad_norm": 5.471564769744873, "learning_rate": 7.359163856594289e-06, "loss": 0.1473, "step": 344230 }, { "epoch": 2.0462340472326743, "grad_norm": 4.3302741050720215, "learning_rate": 7.358980911231546e-06, "loss": 0.1343, "step": 344240 }, { "epoch": 2.0462934893093423, "grad_norm": 3.9688539505004883, "learning_rate": 7.358797961806356e-06, "loss": 0.1603, "step": 344250 }, { "epoch": 2.0463529313860107, "grad_norm": 3.1347134113311768, "learning_rate": 7.358615008319035e-06, "loss": 0.1512, "step": 344260 }, { "epoch": 2.046412373462679, "grad_norm": 3.4308156967163086, "learning_rate": 7.358432050769899e-06, "loss": 0.1421, "step": 344270 }, { "epoch": 2.0464718155393475, "grad_norm": 2.853109121322632, "learning_rate": 7.35824908915926e-06, "loss": 0.1541, "step": 344280 }, { "epoch": 2.046531257616016, "grad_norm": 5.907319068908691, "learning_rate": 7.358066123487435e-06, "loss": 0.1678, "step": 344290 }, { "epoch": 2.0465906996926844, "grad_norm": 3.5254883766174316, "learning_rate": 7.357883153754739e-06, "loss": 0.1622, "step": 344300 }, { "epoch": 2.046650141769353, "grad_norm": 5.022421836853027, "learning_rate": 7.3577001799614855e-06, "loss": 0.1546, "step": 344310 }, { "epoch": 2.046709583846021, "grad_norm": 4.267223834991455, "learning_rate": 7.357517202107993e-06, "loss": 0.1554, "step": 344320 }, { "epoch": 2.0467690259226896, "grad_norm": 3.8177554607391357, "learning_rate": 7.357334220194573e-06, "loss": 0.1537, "step": 344330 }, { "epoch": 2.046828467999358, "grad_norm": 3.735231637954712, "learning_rate": 7.357151234221543e-06, "loss": 0.1617, "step": 344340 }, { "epoch": 2.0468879100760264, "grad_norm": 4.841885089874268, "learning_rate": 7.356968244189217e-06, "loss": 0.1484, "step": 344350 }, { "epoch": 2.046947352152695, "grad_norm": 5.598245143890381, "learning_rate": 7.356785250097911e-06, "loss": 0.1432, "step": 344360 }, { "epoch": 2.0470067942293633, "grad_norm": 3.370950698852539, "learning_rate": 7.35660225194794e-06, "loss": 0.1614, "step": 344370 }, { "epoch": 2.0470662363060317, "grad_norm": 3.9025070667266846, "learning_rate": 7.356419249739617e-06, "loss": 0.1584, "step": 344380 }, { "epoch": 2.0471256783827, "grad_norm": 3.675022840499878, "learning_rate": 7.3562362434732604e-06, "loss": 0.1462, "step": 344390 }, { "epoch": 2.0471851204593685, "grad_norm": 4.377420902252197, "learning_rate": 7.356053233149183e-06, "loss": 0.1644, "step": 344400 }, { "epoch": 2.047244562536037, "grad_norm": 4.220543384552002, "learning_rate": 7.3558702187677e-06, "loss": 0.1638, "step": 344410 }, { "epoch": 2.0473040046127053, "grad_norm": 3.9015564918518066, "learning_rate": 7.355687200329129e-06, "loss": 0.1761, "step": 344420 }, { "epoch": 2.0473634466893738, "grad_norm": 4.865692615509033, "learning_rate": 7.355504177833783e-06, "loss": 0.1627, "step": 344430 }, { "epoch": 2.0474228887660417, "grad_norm": 3.2561254501342773, "learning_rate": 7.355321151281978e-06, "loss": 0.1674, "step": 344440 }, { "epoch": 2.04748233084271, "grad_norm": 3.601210355758667, "learning_rate": 7.355138120674028e-06, "loss": 0.1574, "step": 344450 }, { "epoch": 2.0475417729193786, "grad_norm": 4.367956161499023, "learning_rate": 7.354955086010251e-06, "loss": 0.1666, "step": 344460 }, { "epoch": 2.047601214996047, "grad_norm": 4.996682167053223, "learning_rate": 7.354772047290959e-06, "loss": 0.154, "step": 344470 }, { "epoch": 2.0476606570727154, "grad_norm": 4.234717845916748, "learning_rate": 7.354589004516468e-06, "loss": 0.1463, "step": 344480 }, { "epoch": 2.047720099149384, "grad_norm": 7.22850227355957, "learning_rate": 7.354405957687095e-06, "loss": 0.1879, "step": 344490 }, { "epoch": 2.047779541226052, "grad_norm": 4.464226245880127, "learning_rate": 7.354222906803155e-06, "loss": 0.1235, "step": 344500 }, { "epoch": 2.0478389833027206, "grad_norm": 4.193222522735596, "learning_rate": 7.354039851864959e-06, "loss": 0.1566, "step": 344510 }, { "epoch": 2.047898425379389, "grad_norm": 4.669497489929199, "learning_rate": 7.3538567928728285e-06, "loss": 0.1632, "step": 344520 }, { "epoch": 2.0479578674560575, "grad_norm": 4.754706382751465, "learning_rate": 7.353673729827075e-06, "loss": 0.1556, "step": 344530 }, { "epoch": 2.048017309532726, "grad_norm": 6.401909828186035, "learning_rate": 7.353490662728013e-06, "loss": 0.1788, "step": 344540 }, { "epoch": 2.0480767516093943, "grad_norm": 3.5682601928710938, "learning_rate": 7.35330759157596e-06, "loss": 0.1383, "step": 344550 }, { "epoch": 2.0481361936860627, "grad_norm": 4.491870880126953, "learning_rate": 7.353124516371232e-06, "loss": 0.1451, "step": 344560 }, { "epoch": 2.048195635762731, "grad_norm": 5.372485637664795, "learning_rate": 7.352941437114142e-06, "loss": 0.1642, "step": 344570 }, { "epoch": 2.0482550778393995, "grad_norm": 5.785002708435059, "learning_rate": 7.352758353805005e-06, "loss": 0.1568, "step": 344580 }, { "epoch": 2.048314519916068, "grad_norm": 3.95611310005188, "learning_rate": 7.352575266444139e-06, "loss": 0.1572, "step": 344590 }, { "epoch": 2.0483739619927364, "grad_norm": 4.9941229820251465, "learning_rate": 7.352392175031856e-06, "loss": 0.1635, "step": 344600 }, { "epoch": 2.0484334040694048, "grad_norm": 3.6109251976013184, "learning_rate": 7.352209079568474e-06, "loss": 0.1372, "step": 344610 }, { "epoch": 2.0484928461460727, "grad_norm": 4.648273468017578, "learning_rate": 7.352025980054307e-06, "loss": 0.1555, "step": 344620 }, { "epoch": 2.048552288222741, "grad_norm": 5.355202674865723, "learning_rate": 7.351842876489672e-06, "loss": 0.1671, "step": 344630 }, { "epoch": 2.0486117302994096, "grad_norm": 4.360899448394775, "learning_rate": 7.35165976887488e-06, "loss": 0.159, "step": 344640 }, { "epoch": 2.048671172376078, "grad_norm": 3.7817203998565674, "learning_rate": 7.351476657210252e-06, "loss": 0.1488, "step": 344650 }, { "epoch": 2.0487306144527464, "grad_norm": 3.702857732772827, "learning_rate": 7.351293541496099e-06, "loss": 0.1469, "step": 344660 }, { "epoch": 2.048790056529415, "grad_norm": 3.8044207096099854, "learning_rate": 7.351110421732739e-06, "loss": 0.1469, "step": 344670 }, { "epoch": 2.0488494986060832, "grad_norm": 3.477551221847534, "learning_rate": 7.350927297920486e-06, "loss": 0.1492, "step": 344680 }, { "epoch": 2.0489089406827516, "grad_norm": 4.004011631011963, "learning_rate": 7.350744170059656e-06, "loss": 0.1491, "step": 344690 }, { "epoch": 2.04896838275942, "grad_norm": 4.363681793212891, "learning_rate": 7.350561038150563e-06, "loss": 0.1553, "step": 344700 }, { "epoch": 2.0490278248360885, "grad_norm": 3.5118179321289062, "learning_rate": 7.350377902193524e-06, "loss": 0.158, "step": 344710 }, { "epoch": 2.049087266912757, "grad_norm": 5.325732231140137, "learning_rate": 7.350194762188855e-06, "loss": 0.1658, "step": 344720 }, { "epoch": 2.0491467089894253, "grad_norm": 4.858410358428955, "learning_rate": 7.35001161813687e-06, "loss": 0.1789, "step": 344730 }, { "epoch": 2.0492061510660937, "grad_norm": 4.011089324951172, "learning_rate": 7.3498284700378815e-06, "loss": 0.1665, "step": 344740 }, { "epoch": 2.049265593142762, "grad_norm": 3.8350841999053955, "learning_rate": 7.349645317892211e-06, "loss": 0.154, "step": 344750 }, { "epoch": 2.0493250352194305, "grad_norm": 4.939553260803223, "learning_rate": 7.34946216170017e-06, "loss": 0.1533, "step": 344760 }, { "epoch": 2.049384477296099, "grad_norm": 4.798902988433838, "learning_rate": 7.349279001462074e-06, "loss": 0.1711, "step": 344770 }, { "epoch": 2.0494439193727674, "grad_norm": 4.686208724975586, "learning_rate": 7.349095837178241e-06, "loss": 0.1557, "step": 344780 }, { "epoch": 2.049503361449436, "grad_norm": 4.733326435089111, "learning_rate": 7.348912668848984e-06, "loss": 0.1495, "step": 344790 }, { "epoch": 2.049562803526104, "grad_norm": 3.477870225906372, "learning_rate": 7.348729496474618e-06, "loss": 0.162, "step": 344800 }, { "epoch": 2.049622245602772, "grad_norm": 4.058588981628418, "learning_rate": 7.348546320055461e-06, "loss": 0.1474, "step": 344810 }, { "epoch": 2.0496816876794406, "grad_norm": 4.565158843994141, "learning_rate": 7.348363139591828e-06, "loss": 0.1493, "step": 344820 }, { "epoch": 2.049741129756109, "grad_norm": 3.5688529014587402, "learning_rate": 7.348179955084031e-06, "loss": 0.1304, "step": 344830 }, { "epoch": 2.0498005718327774, "grad_norm": 5.048652172088623, "learning_rate": 7.347996766532389e-06, "loss": 0.1679, "step": 344840 }, { "epoch": 2.049860013909446, "grad_norm": 3.791504383087158, "learning_rate": 7.347813573937217e-06, "loss": 0.1536, "step": 344850 }, { "epoch": 2.0499194559861142, "grad_norm": 3.3511929512023926, "learning_rate": 7.34763037729883e-06, "loss": 0.1208, "step": 344860 }, { "epoch": 2.0499788980627827, "grad_norm": 4.758930683135986, "learning_rate": 7.347447176617541e-06, "loss": 0.1562, "step": 344870 }, { "epoch": 2.050038340139451, "grad_norm": 4.9542555809021, "learning_rate": 7.34726397189367e-06, "loss": 0.1807, "step": 344880 }, { "epoch": 2.0500977822161195, "grad_norm": 3.4664573669433594, "learning_rate": 7.347080763127529e-06, "loss": 0.1442, "step": 344890 }, { "epoch": 2.050157224292788, "grad_norm": 4.574469566345215, "learning_rate": 7.346897550319436e-06, "loss": 0.1498, "step": 344900 }, { "epoch": 2.0502166663694563, "grad_norm": 5.399059772491455, "learning_rate": 7.346714333469706e-06, "loss": 0.1742, "step": 344910 }, { "epoch": 2.0502761084461247, "grad_norm": 4.275939464569092, "learning_rate": 7.346531112578653e-06, "loss": 0.1469, "step": 344920 }, { "epoch": 2.050335550522793, "grad_norm": 4.7958903312683105, "learning_rate": 7.346347887646594e-06, "loss": 0.1533, "step": 344930 }, { "epoch": 2.0503949925994616, "grad_norm": 3.318936347961426, "learning_rate": 7.346164658673843e-06, "loss": 0.1643, "step": 344940 }, { "epoch": 2.05045443467613, "grad_norm": 3.113675117492676, "learning_rate": 7.345981425660717e-06, "loss": 0.1411, "step": 344950 }, { "epoch": 2.0505138767527984, "grad_norm": 4.356185436248779, "learning_rate": 7.345798188607532e-06, "loss": 0.1485, "step": 344960 }, { "epoch": 2.050573318829467, "grad_norm": 3.726705312728882, "learning_rate": 7.345614947514601e-06, "loss": 0.1347, "step": 344970 }, { "epoch": 2.050632760906135, "grad_norm": 6.024794101715088, "learning_rate": 7.345431702382242e-06, "loss": 0.18, "step": 344980 }, { "epoch": 2.050692202982803, "grad_norm": 4.069890975952148, "learning_rate": 7.34524845321077e-06, "loss": 0.1473, "step": 344990 }, { "epoch": 2.0507516450594716, "grad_norm": 4.943178176879883, "learning_rate": 7.345065200000498e-06, "loss": 0.1476, "step": 345000 }, { "epoch": 2.05081108713614, "grad_norm": 4.768566131591797, "learning_rate": 7.344881942751747e-06, "loss": 0.1436, "step": 345010 }, { "epoch": 2.0508705292128084, "grad_norm": 3.79278826713562, "learning_rate": 7.344698681464828e-06, "loss": 0.1418, "step": 345020 }, { "epoch": 2.050929971289477, "grad_norm": 4.464632034301758, "learning_rate": 7.344515416140059e-06, "loss": 0.1552, "step": 345030 }, { "epoch": 2.0509894133661453, "grad_norm": 6.00297737121582, "learning_rate": 7.344332146777754e-06, "loss": 0.1463, "step": 345040 }, { "epoch": 2.0510488554428137, "grad_norm": 4.865766525268555, "learning_rate": 7.344148873378229e-06, "loss": 0.168, "step": 345050 }, { "epoch": 2.051108297519482, "grad_norm": 4.958789348602295, "learning_rate": 7.343965595941801e-06, "loss": 0.162, "step": 345060 }, { "epoch": 2.0511677395961505, "grad_norm": 4.81746244430542, "learning_rate": 7.343782314468784e-06, "loss": 0.1706, "step": 345070 }, { "epoch": 2.051227181672819, "grad_norm": 3.631093740463257, "learning_rate": 7.343599028959495e-06, "loss": 0.1546, "step": 345080 }, { "epoch": 2.0512866237494873, "grad_norm": 5.36346435546875, "learning_rate": 7.343415739414248e-06, "loss": 0.1437, "step": 345090 }, { "epoch": 2.0513460658261558, "grad_norm": 6.670610427856445, "learning_rate": 7.3432324458333586e-06, "loss": 0.1497, "step": 345100 }, { "epoch": 2.051405507902824, "grad_norm": 4.194282054901123, "learning_rate": 7.343049148217145e-06, "loss": 0.1575, "step": 345110 }, { "epoch": 2.0514649499794926, "grad_norm": 4.236134052276611, "learning_rate": 7.342865846565921e-06, "loss": 0.1438, "step": 345120 }, { "epoch": 2.051524392056161, "grad_norm": 3.4980716705322266, "learning_rate": 7.342682540880001e-06, "loss": 0.1486, "step": 345130 }, { "epoch": 2.0515838341328294, "grad_norm": 4.762834072113037, "learning_rate": 7.342499231159703e-06, "loss": 0.17, "step": 345140 }, { "epoch": 2.051643276209498, "grad_norm": 3.7899768352508545, "learning_rate": 7.3423159174053426e-06, "loss": 0.1426, "step": 345150 }, { "epoch": 2.0517027182861662, "grad_norm": 3.4846107959747314, "learning_rate": 7.3421325996172335e-06, "loss": 0.1517, "step": 345160 }, { "epoch": 2.0517621603628347, "grad_norm": 3.761829137802124, "learning_rate": 7.341949277795693e-06, "loss": 0.15, "step": 345170 }, { "epoch": 2.0518216024395026, "grad_norm": 4.091308116912842, "learning_rate": 7.341765951941038e-06, "loss": 0.1542, "step": 345180 }, { "epoch": 2.051881044516171, "grad_norm": 4.145157337188721, "learning_rate": 7.34158262205358e-06, "loss": 0.1571, "step": 345190 }, { "epoch": 2.0519404865928395, "grad_norm": 5.402365684509277, "learning_rate": 7.3413992881336394e-06, "loss": 0.1708, "step": 345200 }, { "epoch": 2.051999928669508, "grad_norm": 3.645726203918457, "learning_rate": 7.341215950181528e-06, "loss": 0.1524, "step": 345210 }, { "epoch": 2.0520593707461763, "grad_norm": 4.910362720489502, "learning_rate": 7.341032608197565e-06, "loss": 0.1765, "step": 345220 }, { "epoch": 2.0521188128228447, "grad_norm": 4.687167167663574, "learning_rate": 7.340849262182062e-06, "loss": 0.146, "step": 345230 }, { "epoch": 2.052178254899513, "grad_norm": 5.726815223693848, "learning_rate": 7.3406659121353405e-06, "loss": 0.1881, "step": 345240 }, { "epoch": 2.0522376969761815, "grad_norm": 4.106337547302246, "learning_rate": 7.3404825580577125e-06, "loss": 0.151, "step": 345250 }, { "epoch": 2.05229713905285, "grad_norm": 4.348756790161133, "learning_rate": 7.340299199949492e-06, "loss": 0.1488, "step": 345260 }, { "epoch": 2.0523565811295184, "grad_norm": 3.6907308101654053, "learning_rate": 7.340115837810999e-06, "loss": 0.1561, "step": 345270 }, { "epoch": 2.0524160232061868, "grad_norm": 4.507002830505371, "learning_rate": 7.339932471642548e-06, "loss": 0.147, "step": 345280 }, { "epoch": 2.052475465282855, "grad_norm": 3.784409999847412, "learning_rate": 7.339749101444451e-06, "loss": 0.1421, "step": 345290 }, { "epoch": 2.0525349073595236, "grad_norm": 6.342434883117676, "learning_rate": 7.339565727217029e-06, "loss": 0.1668, "step": 345300 }, { "epoch": 2.052594349436192, "grad_norm": 3.9459431171417236, "learning_rate": 7.339382348960597e-06, "loss": 0.1599, "step": 345310 }, { "epoch": 2.0526537915128604, "grad_norm": 3.9591715335845947, "learning_rate": 7.339198966675467e-06, "loss": 0.1574, "step": 345320 }, { "epoch": 2.052713233589529, "grad_norm": 4.271758079528809, "learning_rate": 7.339015580361956e-06, "loss": 0.1526, "step": 345330 }, { "epoch": 2.0527726756661973, "grad_norm": 4.710054874420166, "learning_rate": 7.3388321900203856e-06, "loss": 0.158, "step": 345340 }, { "epoch": 2.0528321177428657, "grad_norm": 4.412839889526367, "learning_rate": 7.338648795651065e-06, "loss": 0.1506, "step": 345350 }, { "epoch": 2.0528915598195336, "grad_norm": 4.231698036193848, "learning_rate": 7.3384653972543105e-06, "loss": 0.1475, "step": 345360 }, { "epoch": 2.052951001896202, "grad_norm": 3.6505348682403564, "learning_rate": 7.3382819948304415e-06, "loss": 0.1483, "step": 345370 }, { "epoch": 2.0530104439728705, "grad_norm": 3.9921276569366455, "learning_rate": 7.338098588379772e-06, "loss": 0.1426, "step": 345380 }, { "epoch": 2.053069886049539, "grad_norm": 8.585164070129395, "learning_rate": 7.337915177902616e-06, "loss": 0.1697, "step": 345390 }, { "epoch": 2.0531293281262073, "grad_norm": 4.19095516204834, "learning_rate": 7.337731763399293e-06, "loss": 0.1758, "step": 345400 }, { "epoch": 2.0531887702028757, "grad_norm": 4.423528671264648, "learning_rate": 7.337548344870116e-06, "loss": 0.1378, "step": 345410 }, { "epoch": 2.053248212279544, "grad_norm": 4.7424635887146, "learning_rate": 7.337364922315402e-06, "loss": 0.1651, "step": 345420 }, { "epoch": 2.0533076543562125, "grad_norm": 3.119990587234497, "learning_rate": 7.337181495735466e-06, "loss": 0.1494, "step": 345430 }, { "epoch": 2.053367096432881, "grad_norm": 4.1913604736328125, "learning_rate": 7.336998065130625e-06, "loss": 0.1581, "step": 345440 }, { "epoch": 2.0534265385095494, "grad_norm": 3.6803934574127197, "learning_rate": 7.336814630501194e-06, "loss": 0.1715, "step": 345450 }, { "epoch": 2.053485980586218, "grad_norm": 3.7760093212127686, "learning_rate": 7.336631191847491e-06, "loss": 0.1618, "step": 345460 }, { "epoch": 2.053545422662886, "grad_norm": 4.166113376617432, "learning_rate": 7.33644774916983e-06, "loss": 0.145, "step": 345470 }, { "epoch": 2.0536048647395546, "grad_norm": 4.184514999389648, "learning_rate": 7.336264302468525e-06, "loss": 0.1457, "step": 345480 }, { "epoch": 2.053664306816223, "grad_norm": 8.865700721740723, "learning_rate": 7.336080851743897e-06, "loss": 0.1464, "step": 345490 }, { "epoch": 2.0537237488928914, "grad_norm": 3.7549853324890137, "learning_rate": 7.335897396996259e-06, "loss": 0.1586, "step": 345500 }, { "epoch": 2.05378319096956, "grad_norm": 4.078466415405273, "learning_rate": 7.335713938225926e-06, "loss": 0.1253, "step": 345510 }, { "epoch": 2.0538426330462283, "grad_norm": 4.6755218505859375, "learning_rate": 7.335530475433213e-06, "loss": 0.1541, "step": 345520 }, { "epoch": 2.0539020751228967, "grad_norm": 4.167229652404785, "learning_rate": 7.335347008618441e-06, "loss": 0.1499, "step": 345530 }, { "epoch": 2.053961517199565, "grad_norm": 3.808194160461426, "learning_rate": 7.33516353778192e-06, "loss": 0.157, "step": 345540 }, { "epoch": 2.054020959276233, "grad_norm": 4.575375080108643, "learning_rate": 7.33498006292397e-06, "loss": 0.1661, "step": 345550 }, { "epoch": 2.0540804013529015, "grad_norm": 5.116333484649658, "learning_rate": 7.334796584044905e-06, "loss": 0.1593, "step": 345560 }, { "epoch": 2.05413984342957, "grad_norm": 4.8901872634887695, "learning_rate": 7.334613101145044e-06, "loss": 0.1446, "step": 345570 }, { "epoch": 2.0541992855062383, "grad_norm": 4.506970405578613, "learning_rate": 7.334429614224699e-06, "loss": 0.1527, "step": 345580 }, { "epoch": 2.0542587275829067, "grad_norm": 4.429919242858887, "learning_rate": 7.334246123284188e-06, "loss": 0.1508, "step": 345590 }, { "epoch": 2.054318169659575, "grad_norm": 3.274247646331787, "learning_rate": 7.334062628323826e-06, "loss": 0.1344, "step": 345600 }, { "epoch": 2.0543776117362436, "grad_norm": 4.507434844970703, "learning_rate": 7.33387912934393e-06, "loss": 0.1558, "step": 345610 }, { "epoch": 2.054437053812912, "grad_norm": 5.403510570526123, "learning_rate": 7.333695626344817e-06, "loss": 0.168, "step": 345620 }, { "epoch": 2.0544964958895804, "grad_norm": 5.013119697570801, "learning_rate": 7.3335121193268e-06, "loss": 0.16, "step": 345630 }, { "epoch": 2.054555937966249, "grad_norm": 5.038121223449707, "learning_rate": 7.333328608290197e-06, "loss": 0.1648, "step": 345640 }, { "epoch": 2.054615380042917, "grad_norm": 4.897519588470459, "learning_rate": 7.333145093235323e-06, "loss": 0.1304, "step": 345650 }, { "epoch": 2.0546748221195856, "grad_norm": 5.30437707901001, "learning_rate": 7.332961574162496e-06, "loss": 0.16, "step": 345660 }, { "epoch": 2.054734264196254, "grad_norm": 3.0110280513763428, "learning_rate": 7.332778051072031e-06, "loss": 0.1618, "step": 345670 }, { "epoch": 2.0547937062729225, "grad_norm": 4.246376037597656, "learning_rate": 7.3325945239642424e-06, "loss": 0.1449, "step": 345680 }, { "epoch": 2.054853148349591, "grad_norm": 4.143579006195068, "learning_rate": 7.332410992839449e-06, "loss": 0.1475, "step": 345690 }, { "epoch": 2.0549125904262593, "grad_norm": 3.913532257080078, "learning_rate": 7.332227457697966e-06, "loss": 0.1412, "step": 345700 }, { "epoch": 2.0549720325029277, "grad_norm": 4.227200984954834, "learning_rate": 7.3320439185401086e-06, "loss": 0.1539, "step": 345710 }, { "epoch": 2.055031474579596, "grad_norm": 5.26492977142334, "learning_rate": 7.3318603753661935e-06, "loss": 0.1344, "step": 345720 }, { "epoch": 2.055090916656264, "grad_norm": 3.763197898864746, "learning_rate": 7.331676828176535e-06, "loss": 0.1431, "step": 345730 }, { "epoch": 2.0551503587329325, "grad_norm": 5.477076053619385, "learning_rate": 7.331493276971452e-06, "loss": 0.1714, "step": 345740 }, { "epoch": 2.055209800809601, "grad_norm": 5.917712688446045, "learning_rate": 7.331309721751259e-06, "loss": 0.1575, "step": 345750 }, { "epoch": 2.0552692428862693, "grad_norm": 4.569005012512207, "learning_rate": 7.331126162516273e-06, "loss": 0.161, "step": 345760 }, { "epoch": 2.0553286849629377, "grad_norm": 5.339329719543457, "learning_rate": 7.330942599266809e-06, "loss": 0.1661, "step": 345770 }, { "epoch": 2.055388127039606, "grad_norm": 4.199744701385498, "learning_rate": 7.330759032003184e-06, "loss": 0.1564, "step": 345780 }, { "epoch": 2.0554475691162746, "grad_norm": 3.886415958404541, "learning_rate": 7.330575460725714e-06, "loss": 0.1658, "step": 345790 }, { "epoch": 2.055507011192943, "grad_norm": 3.8834128379821777, "learning_rate": 7.330391885434715e-06, "loss": 0.1521, "step": 345800 }, { "epoch": 2.0555664532696114, "grad_norm": 4.848285675048828, "learning_rate": 7.330208306130503e-06, "loss": 0.1639, "step": 345810 }, { "epoch": 2.05562589534628, "grad_norm": 3.968876838684082, "learning_rate": 7.3300247228133945e-06, "loss": 0.1386, "step": 345820 }, { "epoch": 2.0556853374229482, "grad_norm": 5.083962440490723, "learning_rate": 7.329841135483706e-06, "loss": 0.1487, "step": 345830 }, { "epoch": 2.0557447794996166, "grad_norm": 4.4869914054870605, "learning_rate": 7.3296575441417514e-06, "loss": 0.14, "step": 345840 }, { "epoch": 2.055804221576285, "grad_norm": 3.4155161380767822, "learning_rate": 7.32947394878785e-06, "loss": 0.1546, "step": 345850 }, { "epoch": 2.0558636636529535, "grad_norm": 3.9057836532592773, "learning_rate": 7.329290349422315e-06, "loss": 0.1732, "step": 345860 }, { "epoch": 2.055923105729622, "grad_norm": 5.975527763366699, "learning_rate": 7.329106746045466e-06, "loss": 0.1623, "step": 345870 }, { "epoch": 2.0559825478062903, "grad_norm": 2.9969217777252197, "learning_rate": 7.328923138657615e-06, "loss": 0.16, "step": 345880 }, { "epoch": 2.0560419898829587, "grad_norm": 3.980943202972412, "learning_rate": 7.3287395272590825e-06, "loss": 0.1603, "step": 345890 }, { "epoch": 2.056101431959627, "grad_norm": 5.056488990783691, "learning_rate": 7.3285559118501825e-06, "loss": 0.1495, "step": 345900 }, { "epoch": 2.0561608740362955, "grad_norm": 3.2896149158477783, "learning_rate": 7.328372292431229e-06, "loss": 0.1588, "step": 345910 }, { "epoch": 2.0562203161129635, "grad_norm": 4.1768622398376465, "learning_rate": 7.3281886690025435e-06, "loss": 0.157, "step": 345920 }, { "epoch": 2.056279758189632, "grad_norm": 4.99452018737793, "learning_rate": 7.328005041564439e-06, "loss": 0.1584, "step": 345930 }, { "epoch": 2.0563392002663003, "grad_norm": 3.995997428894043, "learning_rate": 7.327821410117231e-06, "loss": 0.1626, "step": 345940 }, { "epoch": 2.0563986423429688, "grad_norm": 4.195951461791992, "learning_rate": 7.327637774661237e-06, "loss": 0.1334, "step": 345950 }, { "epoch": 2.056458084419637, "grad_norm": 3.512479066848755, "learning_rate": 7.327454135196773e-06, "loss": 0.1493, "step": 345960 }, { "epoch": 2.0565175264963056, "grad_norm": 3.710477352142334, "learning_rate": 7.3272704917241555e-06, "loss": 0.1508, "step": 345970 }, { "epoch": 2.056576968572974, "grad_norm": 4.382392883300781, "learning_rate": 7.3270868442437e-06, "loss": 0.1708, "step": 345980 }, { "epoch": 2.0566364106496424, "grad_norm": 3.7030839920043945, "learning_rate": 7.3269031927557235e-06, "loss": 0.1561, "step": 345990 }, { "epoch": 2.056695852726311, "grad_norm": 4.039041042327881, "learning_rate": 7.326719537260543e-06, "loss": 0.1493, "step": 346000 }, { "epoch": 2.0567552948029793, "grad_norm": 5.344600200653076, "learning_rate": 7.326535877758472e-06, "loss": 0.1461, "step": 346010 }, { "epoch": 2.0568147368796477, "grad_norm": 4.2876667976379395, "learning_rate": 7.32635221424983e-06, "loss": 0.1617, "step": 346020 }, { "epoch": 2.056874178956316, "grad_norm": 4.560632705688477, "learning_rate": 7.326168546734932e-06, "loss": 0.1383, "step": 346030 }, { "epoch": 2.0569336210329845, "grad_norm": 4.6050496101379395, "learning_rate": 7.325984875214094e-06, "loss": 0.1754, "step": 346040 }, { "epoch": 2.056993063109653, "grad_norm": 5.036665439605713, "learning_rate": 7.325801199687632e-06, "loss": 0.1826, "step": 346050 }, { "epoch": 2.0570525051863213, "grad_norm": 4.199892520904541, "learning_rate": 7.325617520155863e-06, "loss": 0.165, "step": 346060 }, { "epoch": 2.0571119472629897, "grad_norm": 4.246330261230469, "learning_rate": 7.325433836619104e-06, "loss": 0.1517, "step": 346070 }, { "epoch": 2.057171389339658, "grad_norm": 4.00253438949585, "learning_rate": 7.32525014907767e-06, "loss": 0.1707, "step": 346080 }, { "epoch": 2.0572308314163266, "grad_norm": 5.540181636810303, "learning_rate": 7.325066457531877e-06, "loss": 0.1546, "step": 346090 }, { "epoch": 2.0572902734929945, "grad_norm": 3.3098955154418945, "learning_rate": 7.324882761982042e-06, "loss": 0.1697, "step": 346100 }, { "epoch": 2.057349715569663, "grad_norm": 4.056527614593506, "learning_rate": 7.324699062428482e-06, "loss": 0.1502, "step": 346110 }, { "epoch": 2.0574091576463314, "grad_norm": 5.069723129272461, "learning_rate": 7.324515358871514e-06, "loss": 0.1596, "step": 346120 }, { "epoch": 2.057468599723, "grad_norm": 4.235300540924072, "learning_rate": 7.3243316513114515e-06, "loss": 0.1655, "step": 346130 }, { "epoch": 2.057528041799668, "grad_norm": 4.056425094604492, "learning_rate": 7.324147939748614e-06, "loss": 0.1296, "step": 346140 }, { "epoch": 2.0575874838763366, "grad_norm": 3.250765800476074, "learning_rate": 7.323964224183315e-06, "loss": 0.168, "step": 346150 }, { "epoch": 2.057646925953005, "grad_norm": 4.54242467880249, "learning_rate": 7.323780504615874e-06, "loss": 0.1542, "step": 346160 }, { "epoch": 2.0577063680296734, "grad_norm": 4.217164516448975, "learning_rate": 7.323596781046604e-06, "loss": 0.1318, "step": 346170 }, { "epoch": 2.057765810106342, "grad_norm": 4.5190110206604, "learning_rate": 7.323413053475824e-06, "loss": 0.156, "step": 346180 }, { "epoch": 2.0578252521830103, "grad_norm": 4.794641494750977, "learning_rate": 7.32322932190385e-06, "loss": 0.1723, "step": 346190 }, { "epoch": 2.0578846942596787, "grad_norm": 5.831862449645996, "learning_rate": 7.323045586330996e-06, "loss": 0.1527, "step": 346200 }, { "epoch": 2.057944136336347, "grad_norm": 4.279493808746338, "learning_rate": 7.322861846757582e-06, "loss": 0.1486, "step": 346210 }, { "epoch": 2.0580035784130155, "grad_norm": 4.399893760681152, "learning_rate": 7.322678103183922e-06, "loss": 0.1737, "step": 346220 }, { "epoch": 2.058063020489684, "grad_norm": 3.3978049755096436, "learning_rate": 7.3224943556103336e-06, "loss": 0.1516, "step": 346230 }, { "epoch": 2.0581224625663523, "grad_norm": 4.083780288696289, "learning_rate": 7.322310604037133e-06, "loss": 0.1581, "step": 346240 }, { "epoch": 2.0581819046430208, "grad_norm": 3.981644868850708, "learning_rate": 7.322126848464635e-06, "loss": 0.147, "step": 346250 }, { "epoch": 2.058241346719689, "grad_norm": 4.202147483825684, "learning_rate": 7.3219430888931596e-06, "loss": 0.1613, "step": 346260 }, { "epoch": 2.0583007887963576, "grad_norm": 4.018497943878174, "learning_rate": 7.32175932532302e-06, "loss": 0.1509, "step": 346270 }, { "epoch": 2.058360230873026, "grad_norm": 3.986839532852173, "learning_rate": 7.321575557754534e-06, "loss": 0.135, "step": 346280 }, { "epoch": 2.058419672949694, "grad_norm": 4.255588054656982, "learning_rate": 7.321391786188018e-06, "loss": 0.1384, "step": 346290 }, { "epoch": 2.0584791150263624, "grad_norm": 5.5113630294799805, "learning_rate": 7.3212080106237885e-06, "loss": 0.1505, "step": 346300 }, { "epoch": 2.058538557103031, "grad_norm": 3.6161019802093506, "learning_rate": 7.3210242310621606e-06, "loss": 0.1472, "step": 346310 }, { "epoch": 2.058597999179699, "grad_norm": 4.489309787750244, "learning_rate": 7.320840447503454e-06, "loss": 0.1568, "step": 346320 }, { "epoch": 2.0586574412563676, "grad_norm": 4.668119430541992, "learning_rate": 7.320656659947981e-06, "loss": 0.1462, "step": 346330 }, { "epoch": 2.058716883333036, "grad_norm": 4.886527061462402, "learning_rate": 7.320472868396062e-06, "loss": 0.1733, "step": 346340 }, { "epoch": 2.0587763254097045, "grad_norm": 4.053297519683838, "learning_rate": 7.3202890728480115e-06, "loss": 0.1603, "step": 346350 }, { "epoch": 2.058835767486373, "grad_norm": 4.492434501647949, "learning_rate": 7.320105273304145e-06, "loss": 0.1644, "step": 346360 }, { "epoch": 2.0588952095630413, "grad_norm": 4.640161514282227, "learning_rate": 7.319921469764783e-06, "loss": 0.1688, "step": 346370 }, { "epoch": 2.0589546516397097, "grad_norm": 4.255796432495117, "learning_rate": 7.319737662230239e-06, "loss": 0.1734, "step": 346380 }, { "epoch": 2.059014093716378, "grad_norm": 3.594461679458618, "learning_rate": 7.319553850700828e-06, "loss": 0.1561, "step": 346390 }, { "epoch": 2.0590735357930465, "grad_norm": 4.030817985534668, "learning_rate": 7.319370035176869e-06, "loss": 0.1593, "step": 346400 }, { "epoch": 2.059132977869715, "grad_norm": 5.543144702911377, "learning_rate": 7.31918621565868e-06, "loss": 0.1726, "step": 346410 }, { "epoch": 2.0591924199463834, "grad_norm": 4.904335975646973, "learning_rate": 7.319002392146574e-06, "loss": 0.157, "step": 346420 }, { "epoch": 2.0592518620230518, "grad_norm": 6.045042037963867, "learning_rate": 7.318818564640869e-06, "loss": 0.148, "step": 346430 }, { "epoch": 2.05931130409972, "grad_norm": 4.427095413208008, "learning_rate": 7.318634733141882e-06, "loss": 0.156, "step": 346440 }, { "epoch": 2.0593707461763886, "grad_norm": 4.546244144439697, "learning_rate": 7.318450897649929e-06, "loss": 0.1301, "step": 346450 }, { "epoch": 2.059430188253057, "grad_norm": 4.278745174407959, "learning_rate": 7.318267058165327e-06, "loss": 0.155, "step": 346460 }, { "epoch": 2.059489630329725, "grad_norm": 4.850862503051758, "learning_rate": 7.318083214688394e-06, "loss": 0.1616, "step": 346470 }, { "epoch": 2.0595490724063934, "grad_norm": 4.265535354614258, "learning_rate": 7.317899367219444e-06, "loss": 0.1537, "step": 346480 }, { "epoch": 2.059608514483062, "grad_norm": 4.532700538635254, "learning_rate": 7.317715515758794e-06, "loss": 0.1536, "step": 346490 }, { "epoch": 2.0596679565597302, "grad_norm": 4.209202289581299, "learning_rate": 7.317531660306762e-06, "loss": 0.1456, "step": 346500 }, { "epoch": 2.0597273986363986, "grad_norm": 4.172896385192871, "learning_rate": 7.317347800863665e-06, "loss": 0.1425, "step": 346510 }, { "epoch": 2.059786840713067, "grad_norm": 5.1725754737854, "learning_rate": 7.3171639374298175e-06, "loss": 0.1666, "step": 346520 }, { "epoch": 2.0598462827897355, "grad_norm": 3.1233930587768555, "learning_rate": 7.316980070005537e-06, "loss": 0.1619, "step": 346530 }, { "epoch": 2.059905724866404, "grad_norm": 4.9777913093566895, "learning_rate": 7.316796198591141e-06, "loss": 0.1671, "step": 346540 }, { "epoch": 2.0599651669430723, "grad_norm": 5.186730861663818, "learning_rate": 7.316612323186945e-06, "loss": 0.1488, "step": 346550 }, { "epoch": 2.0600246090197407, "grad_norm": 3.759467124938965, "learning_rate": 7.316428443793267e-06, "loss": 0.153, "step": 346560 }, { "epoch": 2.060084051096409, "grad_norm": 5.094873905181885, "learning_rate": 7.3162445604104216e-06, "loss": 0.1598, "step": 346570 }, { "epoch": 2.0601434931730775, "grad_norm": 4.635537147521973, "learning_rate": 7.316060673038727e-06, "loss": 0.159, "step": 346580 }, { "epoch": 2.060202935249746, "grad_norm": 4.7268195152282715, "learning_rate": 7.3158767816785006e-06, "loss": 0.1592, "step": 346590 }, { "epoch": 2.0602623773264144, "grad_norm": 3.829366445541382, "learning_rate": 7.315692886330057e-06, "loss": 0.1556, "step": 346600 }, { "epoch": 2.060321819403083, "grad_norm": 4.378290176391602, "learning_rate": 7.315508986993714e-06, "loss": 0.1484, "step": 346610 }, { "epoch": 2.060381261479751, "grad_norm": 4.796591281890869, "learning_rate": 7.3153250836697885e-06, "loss": 0.1351, "step": 346620 }, { "epoch": 2.0604407035564196, "grad_norm": 2.6340887546539307, "learning_rate": 7.315141176358598e-06, "loss": 0.1335, "step": 346630 }, { "epoch": 2.060500145633088, "grad_norm": 4.710798263549805, "learning_rate": 7.314957265060456e-06, "loss": 0.1606, "step": 346640 }, { "epoch": 2.0605595877097564, "grad_norm": 4.306038856506348, "learning_rate": 7.314773349775684e-06, "loss": 0.1471, "step": 346650 }, { "epoch": 2.0606190297864244, "grad_norm": 5.306382656097412, "learning_rate": 7.314589430504593e-06, "loss": 0.157, "step": 346660 }, { "epoch": 2.060678471863093, "grad_norm": 4.218417167663574, "learning_rate": 7.314405507247505e-06, "loss": 0.1586, "step": 346670 }, { "epoch": 2.0607379139397612, "grad_norm": 4.422074317932129, "learning_rate": 7.314221580004734e-06, "loss": 0.1735, "step": 346680 }, { "epoch": 2.0607973560164297, "grad_norm": 4.539713382720947, "learning_rate": 7.314037648776597e-06, "loss": 0.1651, "step": 346690 }, { "epoch": 2.060856798093098, "grad_norm": 5.524708271026611, "learning_rate": 7.313853713563411e-06, "loss": 0.157, "step": 346700 }, { "epoch": 2.0609162401697665, "grad_norm": 5.691425800323486, "learning_rate": 7.313669774365494e-06, "loss": 0.1652, "step": 346710 }, { "epoch": 2.060975682246435, "grad_norm": 6.375218391418457, "learning_rate": 7.31348583118316e-06, "loss": 0.154, "step": 346720 }, { "epoch": 2.0610351243231033, "grad_norm": 5.200112819671631, "learning_rate": 7.313301884016729e-06, "loss": 0.1606, "step": 346730 }, { "epoch": 2.0610945663997717, "grad_norm": 4.4763503074646, "learning_rate": 7.313117932866516e-06, "loss": 0.1539, "step": 346740 }, { "epoch": 2.06115400847644, "grad_norm": 3.592622756958008, "learning_rate": 7.312933977732836e-06, "loss": 0.1545, "step": 346750 }, { "epoch": 2.0612134505531086, "grad_norm": 4.686701774597168, "learning_rate": 7.312750018616008e-06, "loss": 0.1605, "step": 346760 }, { "epoch": 2.061272892629777, "grad_norm": 5.5644965171813965, "learning_rate": 7.31256605551635e-06, "loss": 0.1706, "step": 346770 }, { "epoch": 2.0613323347064454, "grad_norm": 4.339855670928955, "learning_rate": 7.312382088434177e-06, "loss": 0.1454, "step": 346780 }, { "epoch": 2.061391776783114, "grad_norm": 5.936323642730713, "learning_rate": 7.312198117369807e-06, "loss": 0.1788, "step": 346790 }, { "epoch": 2.061451218859782, "grad_norm": 4.075222969055176, "learning_rate": 7.312014142323553e-06, "loss": 0.1605, "step": 346800 }, { "epoch": 2.0615106609364506, "grad_norm": 3.4297423362731934, "learning_rate": 7.311830163295737e-06, "loss": 0.1605, "step": 346810 }, { "epoch": 2.061570103013119, "grad_norm": 4.337710857391357, "learning_rate": 7.311646180286673e-06, "loss": 0.1456, "step": 346820 }, { "epoch": 2.0616295450897875, "grad_norm": 5.208235263824463, "learning_rate": 7.31146219329668e-06, "loss": 0.1583, "step": 346830 }, { "epoch": 2.0616889871664554, "grad_norm": 3.977471351623535, "learning_rate": 7.311278202326072e-06, "loss": 0.141, "step": 346840 }, { "epoch": 2.061748429243124, "grad_norm": 4.765926361083984, "learning_rate": 7.311094207375167e-06, "loss": 0.1611, "step": 346850 }, { "epoch": 2.0618078713197923, "grad_norm": 3.7960636615753174, "learning_rate": 7.310910208444282e-06, "loss": 0.1383, "step": 346860 }, { "epoch": 2.0618673133964607, "grad_norm": 4.328174591064453, "learning_rate": 7.3107262055337335e-06, "loss": 0.1397, "step": 346870 }, { "epoch": 2.061926755473129, "grad_norm": 4.593847751617432, "learning_rate": 7.31054219864384e-06, "loss": 0.1447, "step": 346880 }, { "epoch": 2.0619861975497975, "grad_norm": 4.334284782409668, "learning_rate": 7.310358187774915e-06, "loss": 0.1583, "step": 346890 }, { "epoch": 2.062045639626466, "grad_norm": 3.3816146850585938, "learning_rate": 7.31017417292728e-06, "loss": 0.1508, "step": 346900 }, { "epoch": 2.0621050817031343, "grad_norm": 3.7514100074768066, "learning_rate": 7.3099901541012475e-06, "loss": 0.1543, "step": 346910 }, { "epoch": 2.0621645237798027, "grad_norm": 4.492838382720947, "learning_rate": 7.309806131297138e-06, "loss": 0.1532, "step": 346920 }, { "epoch": 2.062223965856471, "grad_norm": 3.540038824081421, "learning_rate": 7.309622104515266e-06, "loss": 0.1485, "step": 346930 }, { "epoch": 2.0622834079331396, "grad_norm": 4.39666223526001, "learning_rate": 7.309438073755949e-06, "loss": 0.1356, "step": 346940 }, { "epoch": 2.062342850009808, "grad_norm": 6.016067981719971, "learning_rate": 7.309254039019504e-06, "loss": 0.162, "step": 346950 }, { "epoch": 2.0624022920864764, "grad_norm": 3.6147334575653076, "learning_rate": 7.3090700003062495e-06, "loss": 0.1518, "step": 346960 }, { "epoch": 2.062461734163145, "grad_norm": 3.523982524871826, "learning_rate": 7.308885957616499e-06, "loss": 0.1466, "step": 346970 }, { "epoch": 2.0625211762398132, "grad_norm": 3.976874828338623, "learning_rate": 7.30870191095057e-06, "loss": 0.1553, "step": 346980 }, { "epoch": 2.0625806183164817, "grad_norm": 3.7282183170318604, "learning_rate": 7.3085178603087846e-06, "loss": 0.1429, "step": 346990 }, { "epoch": 2.06264006039315, "grad_norm": 3.9690048694610596, "learning_rate": 7.308333805691455e-06, "loss": 0.1573, "step": 347000 }, { "epoch": 2.0626995024698185, "grad_norm": 4.070546627044678, "learning_rate": 7.308149747098898e-06, "loss": 0.1517, "step": 347010 }, { "epoch": 2.062758944546487, "grad_norm": 4.919262886047363, "learning_rate": 7.3079656845314325e-06, "loss": 0.1442, "step": 347020 }, { "epoch": 2.062818386623155, "grad_norm": 4.0026655197143555, "learning_rate": 7.3077816179893746e-06, "loss": 0.1521, "step": 347030 }, { "epoch": 2.0628778286998233, "grad_norm": 3.5958898067474365, "learning_rate": 7.307597547473041e-06, "loss": 0.1671, "step": 347040 }, { "epoch": 2.0629372707764917, "grad_norm": 3.610799551010132, "learning_rate": 7.307413472982749e-06, "loss": 0.1352, "step": 347050 }, { "epoch": 2.06299671285316, "grad_norm": 4.464680194854736, "learning_rate": 7.307229394518817e-06, "loss": 0.1233, "step": 347060 }, { "epoch": 2.0630561549298285, "grad_norm": 5.076259613037109, "learning_rate": 7.307045312081559e-06, "loss": 0.1563, "step": 347070 }, { "epoch": 2.063115597006497, "grad_norm": 3.724546432495117, "learning_rate": 7.306861225671294e-06, "loss": 0.1565, "step": 347080 }, { "epoch": 2.0631750390831654, "grad_norm": 4.823726177215576, "learning_rate": 7.306677135288339e-06, "loss": 0.1388, "step": 347090 }, { "epoch": 2.0632344811598338, "grad_norm": 3.7264533042907715, "learning_rate": 7.3064930409330115e-06, "loss": 0.1482, "step": 347100 }, { "epoch": 2.063293923236502, "grad_norm": 5.076187610626221, "learning_rate": 7.306308942605626e-06, "loss": 0.1483, "step": 347110 }, { "epoch": 2.0633533653131706, "grad_norm": 5.383602619171143, "learning_rate": 7.306124840306504e-06, "loss": 0.1587, "step": 347120 }, { "epoch": 2.063412807389839, "grad_norm": 3.7131261825561523, "learning_rate": 7.305940734035958e-06, "loss": 0.1537, "step": 347130 }, { "epoch": 2.0634722494665074, "grad_norm": 6.8050456047058105, "learning_rate": 7.305756623794307e-06, "loss": 0.1636, "step": 347140 }, { "epoch": 2.063531691543176, "grad_norm": 5.380263805389404, "learning_rate": 7.3055725095818685e-06, "loss": 0.1647, "step": 347150 }, { "epoch": 2.0635911336198443, "grad_norm": 4.003680229187012, "learning_rate": 7.305388391398959e-06, "loss": 0.1458, "step": 347160 }, { "epoch": 2.0636505756965127, "grad_norm": 5.32673454284668, "learning_rate": 7.305204269245895e-06, "loss": 0.1576, "step": 347170 }, { "epoch": 2.063710017773181, "grad_norm": 4.749088764190674, "learning_rate": 7.305020143122994e-06, "loss": 0.1611, "step": 347180 }, { "epoch": 2.0637694598498495, "grad_norm": 4.51674747467041, "learning_rate": 7.304836013030574e-06, "loss": 0.1407, "step": 347190 }, { "epoch": 2.063828901926518, "grad_norm": 4.573192596435547, "learning_rate": 7.304651878968951e-06, "loss": 0.1715, "step": 347200 }, { "epoch": 2.063888344003186, "grad_norm": 4.7928314208984375, "learning_rate": 7.304467740938443e-06, "loss": 0.1622, "step": 347210 }, { "epoch": 2.0639477860798543, "grad_norm": 4.438778400421143, "learning_rate": 7.304283598939366e-06, "loss": 0.1638, "step": 347220 }, { "epoch": 2.0640072281565227, "grad_norm": 4.634745121002197, "learning_rate": 7.3040994529720374e-06, "loss": 0.1371, "step": 347230 }, { "epoch": 2.064066670233191, "grad_norm": 4.417736053466797, "learning_rate": 7.3039153030367746e-06, "loss": 0.1362, "step": 347240 }, { "epoch": 2.0641261123098595, "grad_norm": 7.356845378875732, "learning_rate": 7.303731149133897e-06, "loss": 0.1706, "step": 347250 }, { "epoch": 2.064185554386528, "grad_norm": 5.193790435791016, "learning_rate": 7.303546991263718e-06, "loss": 0.1539, "step": 347260 }, { "epoch": 2.0642449964631964, "grad_norm": 3.2081387042999268, "learning_rate": 7.303362829426555e-06, "loss": 0.1543, "step": 347270 }, { "epoch": 2.064304438539865, "grad_norm": 4.077403545379639, "learning_rate": 7.303178663622728e-06, "loss": 0.1474, "step": 347280 }, { "epoch": 2.064363880616533, "grad_norm": 4.603804588317871, "learning_rate": 7.302994493852552e-06, "loss": 0.1526, "step": 347290 }, { "epoch": 2.0644233226932016, "grad_norm": 5.897462368011475, "learning_rate": 7.302810320116345e-06, "loss": 0.1449, "step": 347300 }, { "epoch": 2.06448276476987, "grad_norm": 3.782863140106201, "learning_rate": 7.302626142414421e-06, "loss": 0.1479, "step": 347310 }, { "epoch": 2.0645422068465384, "grad_norm": 5.981287479400635, "learning_rate": 7.3024419607471046e-06, "loss": 0.162, "step": 347320 }, { "epoch": 2.064601648923207, "grad_norm": 5.2089433670043945, "learning_rate": 7.302257775114706e-06, "loss": 0.172, "step": 347330 }, { "epoch": 2.0646610909998753, "grad_norm": 4.245441436767578, "learning_rate": 7.302073585517545e-06, "loss": 0.1507, "step": 347340 }, { "epoch": 2.0647205330765437, "grad_norm": 4.365199565887451, "learning_rate": 7.301889391955939e-06, "loss": 0.1539, "step": 347350 }, { "epoch": 2.064779975153212, "grad_norm": 3.5332703590393066, "learning_rate": 7.301705194430205e-06, "loss": 0.1466, "step": 347360 }, { "epoch": 2.0648394172298805, "grad_norm": 4.2086005210876465, "learning_rate": 7.301520992940659e-06, "loss": 0.165, "step": 347370 }, { "epoch": 2.064898859306549, "grad_norm": 3.753014326095581, "learning_rate": 7.30133678748762e-06, "loss": 0.1458, "step": 347380 }, { "epoch": 2.064958301383217, "grad_norm": 3.4274230003356934, "learning_rate": 7.301152578071404e-06, "loss": 0.1558, "step": 347390 }, { "epoch": 2.0650177434598853, "grad_norm": 4.118276119232178, "learning_rate": 7.300968364692329e-06, "loss": 0.1588, "step": 347400 }, { "epoch": 2.0650771855365537, "grad_norm": 4.723078727722168, "learning_rate": 7.300784147350712e-06, "loss": 0.1516, "step": 347410 }, { "epoch": 2.065136627613222, "grad_norm": 4.212745189666748, "learning_rate": 7.30059992604687e-06, "loss": 0.1583, "step": 347420 }, { "epoch": 2.0651960696898906, "grad_norm": 3.759594202041626, "learning_rate": 7.3004157007811204e-06, "loss": 0.1536, "step": 347430 }, { "epoch": 2.065255511766559, "grad_norm": 3.9802534580230713, "learning_rate": 7.30023147155378e-06, "loss": 0.1559, "step": 347440 }, { "epoch": 2.0653149538432274, "grad_norm": 4.176445484161377, "learning_rate": 7.300047238365169e-06, "loss": 0.1643, "step": 347450 }, { "epoch": 2.065374395919896, "grad_norm": 3.587455987930298, "learning_rate": 7.299863001215599e-06, "loss": 0.1317, "step": 347460 }, { "epoch": 2.065433837996564, "grad_norm": 5.929264068603516, "learning_rate": 7.299678760105392e-06, "loss": 0.1706, "step": 347470 }, { "epoch": 2.0654932800732326, "grad_norm": 4.412550926208496, "learning_rate": 7.299494515034864e-06, "loss": 0.1482, "step": 347480 }, { "epoch": 2.065552722149901, "grad_norm": 4.601273059844971, "learning_rate": 7.299310266004331e-06, "loss": 0.1453, "step": 347490 }, { "epoch": 2.0656121642265695, "grad_norm": 3.2942378520965576, "learning_rate": 7.299126013014113e-06, "loss": 0.1664, "step": 347500 }, { "epoch": 2.065671606303238, "grad_norm": 3.646134376525879, "learning_rate": 7.2989417560645235e-06, "loss": 0.1634, "step": 347510 }, { "epoch": 2.0657310483799063, "grad_norm": 3.3047983646392822, "learning_rate": 7.298757495155884e-06, "loss": 0.1808, "step": 347520 }, { "epoch": 2.0657904904565747, "grad_norm": 4.297603130340576, "learning_rate": 7.298573230288508e-06, "loss": 0.1617, "step": 347530 }, { "epoch": 2.065849932533243, "grad_norm": 4.873007774353027, "learning_rate": 7.298388961462717e-06, "loss": 0.1603, "step": 347540 }, { "epoch": 2.0659093746099115, "grad_norm": 5.297911643981934, "learning_rate": 7.298204688678825e-06, "loss": 0.161, "step": 347550 }, { "epoch": 2.06596881668658, "grad_norm": 4.511499404907227, "learning_rate": 7.29802041193715e-06, "loss": 0.1645, "step": 347560 }, { "epoch": 2.0660282587632484, "grad_norm": 4.224338531494141, "learning_rate": 7.29783613123801e-06, "loss": 0.1339, "step": 347570 }, { "epoch": 2.0660877008399163, "grad_norm": 3.111259937286377, "learning_rate": 7.2976518465817215e-06, "loss": 0.1399, "step": 347580 }, { "epoch": 2.0661471429165847, "grad_norm": 3.945296049118042, "learning_rate": 7.297467557968602e-06, "loss": 0.159, "step": 347590 }, { "epoch": 2.066206584993253, "grad_norm": 3.7806437015533447, "learning_rate": 7.29728326539897e-06, "loss": 0.1523, "step": 347600 }, { "epoch": 2.0662660270699216, "grad_norm": 4.801852226257324, "learning_rate": 7.297098968873142e-06, "loss": 0.177, "step": 347610 }, { "epoch": 2.06632546914659, "grad_norm": 3.561877727508545, "learning_rate": 7.296914668391435e-06, "loss": 0.1416, "step": 347620 }, { "epoch": 2.0663849112232584, "grad_norm": 3.8484246730804443, "learning_rate": 7.296730363954167e-06, "loss": 0.1622, "step": 347630 }, { "epoch": 2.066444353299927, "grad_norm": 4.677850723266602, "learning_rate": 7.296546055561655e-06, "loss": 0.1629, "step": 347640 }, { "epoch": 2.0665037953765952, "grad_norm": 3.6250462532043457, "learning_rate": 7.296361743214217e-06, "loss": 0.1516, "step": 347650 }, { "epoch": 2.0665632374532636, "grad_norm": 4.087826251983643, "learning_rate": 7.296177426912171e-06, "loss": 0.1595, "step": 347660 }, { "epoch": 2.066622679529932, "grad_norm": 3.2417166233062744, "learning_rate": 7.295993106655833e-06, "loss": 0.1284, "step": 347670 }, { "epoch": 2.0666821216066005, "grad_norm": 6.1847615242004395, "learning_rate": 7.295808782445521e-06, "loss": 0.1678, "step": 347680 }, { "epoch": 2.066741563683269, "grad_norm": 6.1542181968688965, "learning_rate": 7.295624454281551e-06, "loss": 0.1592, "step": 347690 }, { "epoch": 2.0668010057599373, "grad_norm": 3.74869441986084, "learning_rate": 7.295440122164243e-06, "loss": 0.1447, "step": 347700 }, { "epoch": 2.0668604478366057, "grad_norm": 6.597863674163818, "learning_rate": 7.2952557860939145e-06, "loss": 0.1636, "step": 347710 }, { "epoch": 2.066919889913274, "grad_norm": 3.2684803009033203, "learning_rate": 7.2950714460708795e-06, "loss": 0.1639, "step": 347720 }, { "epoch": 2.0669793319899425, "grad_norm": 4.211406707763672, "learning_rate": 7.294887102095457e-06, "loss": 0.1396, "step": 347730 }, { "epoch": 2.067038774066611, "grad_norm": 5.382893085479736, "learning_rate": 7.294702754167967e-06, "loss": 0.1653, "step": 347740 }, { "epoch": 2.0670982161432794, "grad_norm": 4.0262556076049805, "learning_rate": 7.2945184022887246e-06, "loss": 0.1607, "step": 347750 }, { "epoch": 2.067157658219948, "grad_norm": 3.937628984451294, "learning_rate": 7.294334046458047e-06, "loss": 0.1617, "step": 347760 }, { "epoch": 2.0672171002966158, "grad_norm": 4.737650394439697, "learning_rate": 7.294149686676254e-06, "loss": 0.1494, "step": 347770 }, { "epoch": 2.067276542373284, "grad_norm": 4.752941608428955, "learning_rate": 7.293965322943661e-06, "loss": 0.1566, "step": 347780 }, { "epoch": 2.0673359844499526, "grad_norm": 3.160271406173706, "learning_rate": 7.293780955260585e-06, "loss": 0.1594, "step": 347790 }, { "epoch": 2.067395426526621, "grad_norm": 5.387716293334961, "learning_rate": 7.293596583627345e-06, "loss": 0.1542, "step": 347800 }, { "epoch": 2.0674548686032894, "grad_norm": 4.675880432128906, "learning_rate": 7.293412208044258e-06, "loss": 0.1638, "step": 347810 }, { "epoch": 2.067514310679958, "grad_norm": 4.612907886505127, "learning_rate": 7.293227828511642e-06, "loss": 0.1433, "step": 347820 }, { "epoch": 2.0675737527566262, "grad_norm": 4.770780563354492, "learning_rate": 7.293043445029814e-06, "loss": 0.1543, "step": 347830 }, { "epoch": 2.0676331948332947, "grad_norm": 3.6740469932556152, "learning_rate": 7.29285905759909e-06, "loss": 0.1415, "step": 347840 }, { "epoch": 2.067692636909963, "grad_norm": 5.664468765258789, "learning_rate": 7.292674666219791e-06, "loss": 0.1915, "step": 347850 }, { "epoch": 2.0677520789866315, "grad_norm": 4.773544788360596, "learning_rate": 7.292490270892232e-06, "loss": 0.137, "step": 347860 }, { "epoch": 2.0678115210633, "grad_norm": 3.2448890209198, "learning_rate": 7.292305871616731e-06, "loss": 0.1546, "step": 347870 }, { "epoch": 2.0678709631399683, "grad_norm": 5.609033584594727, "learning_rate": 7.292121468393606e-06, "loss": 0.1546, "step": 347880 }, { "epoch": 2.0679304052166367, "grad_norm": 4.670904159545898, "learning_rate": 7.291937061223175e-06, "loss": 0.1568, "step": 347890 }, { "epoch": 2.067989847293305, "grad_norm": 4.718354225158691, "learning_rate": 7.291752650105753e-06, "loss": 0.1534, "step": 347900 }, { "epoch": 2.0680492893699736, "grad_norm": 3.448704481124878, "learning_rate": 7.291568235041662e-06, "loss": 0.1496, "step": 347910 }, { "epoch": 2.068108731446642, "grad_norm": 4.398411273956299, "learning_rate": 7.291383816031215e-06, "loss": 0.1535, "step": 347920 }, { "epoch": 2.0681681735233104, "grad_norm": 3.86327862739563, "learning_rate": 7.2911993930747324e-06, "loss": 0.1433, "step": 347930 }, { "epoch": 2.068227615599979, "grad_norm": 4.732328414916992, "learning_rate": 7.291014966172532e-06, "loss": 0.1316, "step": 347940 }, { "epoch": 2.068287057676647, "grad_norm": 4.206674575805664, "learning_rate": 7.290830535324929e-06, "loss": 0.1466, "step": 347950 }, { "epoch": 2.068346499753315, "grad_norm": 4.631349086761475, "learning_rate": 7.2906461005322425e-06, "loss": 0.1648, "step": 347960 }, { "epoch": 2.0684059418299836, "grad_norm": 4.659683704376221, "learning_rate": 7.290461661794791e-06, "loss": 0.1656, "step": 347970 }, { "epoch": 2.068465383906652, "grad_norm": 4.837188243865967, "learning_rate": 7.290277219112891e-06, "loss": 0.1594, "step": 347980 }, { "epoch": 2.0685248259833204, "grad_norm": 3.6060526371002197, "learning_rate": 7.29009277248686e-06, "loss": 0.1595, "step": 347990 }, { "epoch": 2.068584268059989, "grad_norm": 4.622527122497559, "learning_rate": 7.289908321917016e-06, "loss": 0.1769, "step": 348000 }, { "epoch": 2.0686437101366573, "grad_norm": 4.395042419433594, "learning_rate": 7.289723867403677e-06, "loss": 0.1389, "step": 348010 }, { "epoch": 2.0687031522133257, "grad_norm": 4.888751029968262, "learning_rate": 7.289539408947161e-06, "loss": 0.1512, "step": 348020 }, { "epoch": 2.068762594289994, "grad_norm": 4.860494136810303, "learning_rate": 7.2893549465477845e-06, "loss": 0.1369, "step": 348030 }, { "epoch": 2.0688220363666625, "grad_norm": 3.768991708755493, "learning_rate": 7.289170480205865e-06, "loss": 0.1394, "step": 348040 }, { "epoch": 2.068881478443331, "grad_norm": 3.815765380859375, "learning_rate": 7.288986009921721e-06, "loss": 0.1596, "step": 348050 }, { "epoch": 2.0689409205199993, "grad_norm": 3.6523661613464355, "learning_rate": 7.288801535695669e-06, "loss": 0.1405, "step": 348060 }, { "epoch": 2.0690003625966678, "grad_norm": 5.455235004425049, "learning_rate": 7.288617057528029e-06, "loss": 0.1779, "step": 348070 }, { "epoch": 2.069059804673336, "grad_norm": 3.510498046875, "learning_rate": 7.2884325754191175e-06, "loss": 0.1466, "step": 348080 }, { "epoch": 2.0691192467500046, "grad_norm": 4.139479160308838, "learning_rate": 7.288248089369252e-06, "loss": 0.1586, "step": 348090 }, { "epoch": 2.069178688826673, "grad_norm": 4.607676029205322, "learning_rate": 7.2880635993787494e-06, "loss": 0.1633, "step": 348100 }, { "epoch": 2.0692381309033414, "grad_norm": 4.69915771484375, "learning_rate": 7.287879105447928e-06, "loss": 0.1608, "step": 348110 }, { "epoch": 2.06929757298001, "grad_norm": 3.9961743354797363, "learning_rate": 7.287694607577107e-06, "loss": 0.1483, "step": 348120 }, { "epoch": 2.069357015056678, "grad_norm": 2.8308122158050537, "learning_rate": 7.287510105766603e-06, "loss": 0.1448, "step": 348130 }, { "epoch": 2.069416457133346, "grad_norm": 3.4426276683807373, "learning_rate": 7.2873256000167325e-06, "loss": 0.1404, "step": 348140 }, { "epoch": 2.0694758992100146, "grad_norm": 4.950031280517578, "learning_rate": 7.287141090327816e-06, "loss": 0.1716, "step": 348150 }, { "epoch": 2.069535341286683, "grad_norm": 3.7637550830841064, "learning_rate": 7.286956576700168e-06, "loss": 0.1497, "step": 348160 }, { "epoch": 2.0695947833633515, "grad_norm": 3.760216474533081, "learning_rate": 7.286772059134109e-06, "loss": 0.1578, "step": 348170 }, { "epoch": 2.06965422544002, "grad_norm": 3.3527421951293945, "learning_rate": 7.286587537629954e-06, "loss": 0.134, "step": 348180 }, { "epoch": 2.0697136675166883, "grad_norm": 4.93421745300293, "learning_rate": 7.286403012188025e-06, "loss": 0.1457, "step": 348190 }, { "epoch": 2.0697731095933567, "grad_norm": 5.234933853149414, "learning_rate": 7.286218482808636e-06, "loss": 0.1516, "step": 348200 }, { "epoch": 2.069832551670025, "grad_norm": 4.425498962402344, "learning_rate": 7.286033949492105e-06, "loss": 0.1486, "step": 348210 }, { "epoch": 2.0698919937466935, "grad_norm": 4.082483768463135, "learning_rate": 7.285849412238752e-06, "loss": 0.1533, "step": 348220 }, { "epoch": 2.069951435823362, "grad_norm": 4.714242935180664, "learning_rate": 7.285664871048894e-06, "loss": 0.1422, "step": 348230 }, { "epoch": 2.0700108779000304, "grad_norm": 3.496239423751831, "learning_rate": 7.285480325922847e-06, "loss": 0.1618, "step": 348240 }, { "epoch": 2.0700703199766988, "grad_norm": 7.350405216217041, "learning_rate": 7.285295776860931e-06, "loss": 0.15, "step": 348250 }, { "epoch": 2.070129762053367, "grad_norm": 3.5750644207000732, "learning_rate": 7.2851112238634625e-06, "loss": 0.1577, "step": 348260 }, { "epoch": 2.0701892041300356, "grad_norm": 3.537781000137329, "learning_rate": 7.284926666930759e-06, "loss": 0.1465, "step": 348270 }, { "epoch": 2.070248646206704, "grad_norm": 4.267495632171631, "learning_rate": 7.28474210606314e-06, "loss": 0.157, "step": 348280 }, { "epoch": 2.0703080882833724, "grad_norm": 3.855617046356201, "learning_rate": 7.284557541260924e-06, "loss": 0.1508, "step": 348290 }, { "epoch": 2.070367530360041, "grad_norm": 3.7725679874420166, "learning_rate": 7.284372972524426e-06, "loss": 0.17, "step": 348300 }, { "epoch": 2.0704269724367093, "grad_norm": 3.6352953910827637, "learning_rate": 7.284188399853964e-06, "loss": 0.1553, "step": 348310 }, { "epoch": 2.0704864145133772, "grad_norm": 4.419924259185791, "learning_rate": 7.284003823249859e-06, "loss": 0.1422, "step": 348320 }, { "epoch": 2.0705458565900456, "grad_norm": 4.227747917175293, "learning_rate": 7.2838192427124265e-06, "loss": 0.1474, "step": 348330 }, { "epoch": 2.070605298666714, "grad_norm": 3.6887853145599365, "learning_rate": 7.283634658241984e-06, "loss": 0.1715, "step": 348340 }, { "epoch": 2.0706647407433825, "grad_norm": 6.043994903564453, "learning_rate": 7.283450069838851e-06, "loss": 0.181, "step": 348350 }, { "epoch": 2.070724182820051, "grad_norm": 5.277315616607666, "learning_rate": 7.283265477503344e-06, "loss": 0.1586, "step": 348360 }, { "epoch": 2.0707836248967193, "grad_norm": 5.450429916381836, "learning_rate": 7.283080881235781e-06, "loss": 0.1563, "step": 348370 }, { "epoch": 2.0708430669733877, "grad_norm": 5.160312652587891, "learning_rate": 7.2828962810364814e-06, "loss": 0.1543, "step": 348380 }, { "epoch": 2.070902509050056, "grad_norm": 4.754603385925293, "learning_rate": 7.2827116769057605e-06, "loss": 0.1663, "step": 348390 }, { "epoch": 2.0709619511267245, "grad_norm": 4.8835062980651855, "learning_rate": 7.282527068843938e-06, "loss": 0.1564, "step": 348400 }, { "epoch": 2.071021393203393, "grad_norm": 4.335681915283203, "learning_rate": 7.282342456851332e-06, "loss": 0.1448, "step": 348410 }, { "epoch": 2.0710808352800614, "grad_norm": 2.6999011039733887, "learning_rate": 7.282157840928262e-06, "loss": 0.1498, "step": 348420 }, { "epoch": 2.07114027735673, "grad_norm": 4.586845397949219, "learning_rate": 7.281973221075041e-06, "loss": 0.1578, "step": 348430 }, { "epoch": 2.071199719433398, "grad_norm": 4.2452521324157715, "learning_rate": 7.281788597291991e-06, "loss": 0.1493, "step": 348440 }, { "epoch": 2.0712591615100666, "grad_norm": 4.191161155700684, "learning_rate": 7.281603969579429e-06, "loss": 0.1544, "step": 348450 }, { "epoch": 2.071318603586735, "grad_norm": 4.193831920623779, "learning_rate": 7.281419337937672e-06, "loss": 0.1648, "step": 348460 }, { "epoch": 2.0713780456634034, "grad_norm": 4.946493148803711, "learning_rate": 7.2812347023670394e-06, "loss": 0.1662, "step": 348470 }, { "epoch": 2.071437487740072, "grad_norm": 4.174354076385498, "learning_rate": 7.281050062867848e-06, "loss": 0.1609, "step": 348480 }, { "epoch": 2.0714969298167403, "grad_norm": 3.29742169380188, "learning_rate": 7.280865419440417e-06, "loss": 0.1495, "step": 348490 }, { "epoch": 2.0715563718934087, "grad_norm": 5.133816719055176, "learning_rate": 7.280680772085062e-06, "loss": 0.1536, "step": 348500 }, { "epoch": 2.0716158139700767, "grad_norm": 4.362207412719727, "learning_rate": 7.280496120802103e-06, "loss": 0.1431, "step": 348510 }, { "epoch": 2.071675256046745, "grad_norm": 5.636826038360596, "learning_rate": 7.280311465591858e-06, "loss": 0.1643, "step": 348520 }, { "epoch": 2.0717346981234135, "grad_norm": 4.767886638641357, "learning_rate": 7.280126806454645e-06, "loss": 0.145, "step": 348530 }, { "epoch": 2.071794140200082, "grad_norm": 5.95189905166626, "learning_rate": 7.279942143390782e-06, "loss": 0.157, "step": 348540 }, { "epoch": 2.0718535822767503, "grad_norm": 3.86383056640625, "learning_rate": 7.279757476400585e-06, "loss": 0.1339, "step": 348550 }, { "epoch": 2.0719130243534187, "grad_norm": 3.107588768005371, "learning_rate": 7.279572805484375e-06, "loss": 0.1574, "step": 348560 }, { "epoch": 2.071972466430087, "grad_norm": 4.820980548858643, "learning_rate": 7.279388130642468e-06, "loss": 0.1504, "step": 348570 }, { "epoch": 2.0720319085067556, "grad_norm": 4.087888717651367, "learning_rate": 7.279203451875183e-06, "loss": 0.1357, "step": 348580 }, { "epoch": 2.072091350583424, "grad_norm": 3.453955888748169, "learning_rate": 7.279018769182837e-06, "loss": 0.145, "step": 348590 }, { "epoch": 2.0721507926600924, "grad_norm": 5.862361431121826, "learning_rate": 7.278834082565749e-06, "loss": 0.145, "step": 348600 }, { "epoch": 2.072210234736761, "grad_norm": 4.839739799499512, "learning_rate": 7.278649392024237e-06, "loss": 0.1453, "step": 348610 }, { "epoch": 2.072269676813429, "grad_norm": 4.566489219665527, "learning_rate": 7.278464697558618e-06, "loss": 0.1474, "step": 348620 }, { "epoch": 2.0723291188900976, "grad_norm": 3.8100993633270264, "learning_rate": 7.278279999169212e-06, "loss": 0.1529, "step": 348630 }, { "epoch": 2.072388560966766, "grad_norm": 5.317901134490967, "learning_rate": 7.278095296856336e-06, "loss": 0.159, "step": 348640 }, { "epoch": 2.0724480030434345, "grad_norm": 5.058198928833008, "learning_rate": 7.2779105906203075e-06, "loss": 0.1561, "step": 348650 }, { "epoch": 2.072507445120103, "grad_norm": 3.557802438735962, "learning_rate": 7.277725880461446e-06, "loss": 0.1567, "step": 348660 }, { "epoch": 2.0725668871967713, "grad_norm": 4.374805927276611, "learning_rate": 7.277541166380068e-06, "loss": 0.1389, "step": 348670 }, { "epoch": 2.0726263292734397, "grad_norm": 5.108868598937988, "learning_rate": 7.277356448376494e-06, "loss": 0.1698, "step": 348680 }, { "epoch": 2.0726857713501077, "grad_norm": 3.8176753520965576, "learning_rate": 7.277171726451039e-06, "loss": 0.1508, "step": 348690 }, { "epoch": 2.072745213426776, "grad_norm": 5.291536331176758, "learning_rate": 7.276987000604021e-06, "loss": 0.1823, "step": 348700 }, { "epoch": 2.0728046555034445, "grad_norm": 5.683254718780518, "learning_rate": 7.276802270835762e-06, "loss": 0.152, "step": 348710 }, { "epoch": 2.072864097580113, "grad_norm": 3.2347373962402344, "learning_rate": 7.276617537146578e-06, "loss": 0.1328, "step": 348720 }, { "epoch": 2.0729235396567813, "grad_norm": 4.687329292297363, "learning_rate": 7.276432799536785e-06, "loss": 0.1719, "step": 348730 }, { "epoch": 2.0729829817334497, "grad_norm": 4.3946614265441895, "learning_rate": 7.276248058006704e-06, "loss": 0.1381, "step": 348740 }, { "epoch": 2.073042423810118, "grad_norm": 4.640684127807617, "learning_rate": 7.276063312556653e-06, "loss": 0.1386, "step": 348750 }, { "epoch": 2.0731018658867866, "grad_norm": 4.832244873046875, "learning_rate": 7.275878563186949e-06, "loss": 0.1612, "step": 348760 }, { "epoch": 2.073161307963455, "grad_norm": 4.802462577819824, "learning_rate": 7.27569380989791e-06, "loss": 0.1488, "step": 348770 }, { "epoch": 2.0732207500401234, "grad_norm": 6.422487258911133, "learning_rate": 7.275509052689855e-06, "loss": 0.174, "step": 348780 }, { "epoch": 2.073280192116792, "grad_norm": 2.5392167568206787, "learning_rate": 7.275324291563101e-06, "loss": 0.1515, "step": 348790 }, { "epoch": 2.0733396341934602, "grad_norm": 4.15171480178833, "learning_rate": 7.27513952651797e-06, "loss": 0.154, "step": 348800 }, { "epoch": 2.0733990762701286, "grad_norm": 3.0632407665252686, "learning_rate": 7.274954757554775e-06, "loss": 0.1604, "step": 348810 }, { "epoch": 2.073458518346797, "grad_norm": 4.263441562652588, "learning_rate": 7.274769984673837e-06, "loss": 0.1425, "step": 348820 }, { "epoch": 2.0735179604234655, "grad_norm": 3.770768404006958, "learning_rate": 7.274585207875473e-06, "loss": 0.1539, "step": 348830 }, { "epoch": 2.073577402500134, "grad_norm": 3.872905969619751, "learning_rate": 7.274400427160002e-06, "loss": 0.1561, "step": 348840 }, { "epoch": 2.0736368445768023, "grad_norm": 3.708035469055176, "learning_rate": 7.274215642527744e-06, "loss": 0.1457, "step": 348850 }, { "epoch": 2.0736962866534707, "grad_norm": 4.75675106048584, "learning_rate": 7.274030853979013e-06, "loss": 0.1528, "step": 348860 }, { "epoch": 2.0737557287301387, "grad_norm": 4.1950154304504395, "learning_rate": 7.27384606151413e-06, "loss": 0.1613, "step": 348870 }, { "epoch": 2.073815170806807, "grad_norm": 3.9951226711273193, "learning_rate": 7.2736612651334135e-06, "loss": 0.1544, "step": 348880 }, { "epoch": 2.0738746128834755, "grad_norm": 5.401153564453125, "learning_rate": 7.273476464837181e-06, "loss": 0.1672, "step": 348890 }, { "epoch": 2.073934054960144, "grad_norm": 3.944762706756592, "learning_rate": 7.273291660625751e-06, "loss": 0.1616, "step": 348900 }, { "epoch": 2.0739934970368124, "grad_norm": 3.9772164821624756, "learning_rate": 7.273106852499441e-06, "loss": 0.1533, "step": 348910 }, { "epoch": 2.0740529391134808, "grad_norm": 5.1501946449279785, "learning_rate": 7.272922040458569e-06, "loss": 0.1464, "step": 348920 }, { "epoch": 2.074112381190149, "grad_norm": 4.685002326965332, "learning_rate": 7.272737224503455e-06, "loss": 0.1798, "step": 348930 }, { "epoch": 2.0741718232668176, "grad_norm": 4.04066801071167, "learning_rate": 7.272552404634417e-06, "loss": 0.1418, "step": 348940 }, { "epoch": 2.074231265343486, "grad_norm": 4.372626304626465, "learning_rate": 7.272367580851771e-06, "loss": 0.155, "step": 348950 }, { "epoch": 2.0742907074201544, "grad_norm": 4.510381698608398, "learning_rate": 7.272182753155836e-06, "loss": 0.1512, "step": 348960 }, { "epoch": 2.074350149496823, "grad_norm": 6.381560802459717, "learning_rate": 7.271997921546934e-06, "loss": 0.1665, "step": 348970 }, { "epoch": 2.0744095915734913, "grad_norm": 5.352813243865967, "learning_rate": 7.27181308602538e-06, "loss": 0.174, "step": 348980 }, { "epoch": 2.0744690336501597, "grad_norm": 3.495354652404785, "learning_rate": 7.271628246591491e-06, "loss": 0.1727, "step": 348990 }, { "epoch": 2.074528475726828, "grad_norm": 3.4424469470977783, "learning_rate": 7.271443403245588e-06, "loss": 0.1489, "step": 349000 }, { "epoch": 2.0745879178034965, "grad_norm": 4.6190185546875, "learning_rate": 7.27125855598799e-06, "loss": 0.1453, "step": 349010 }, { "epoch": 2.074647359880165, "grad_norm": 4.079877853393555, "learning_rate": 7.2710737048190115e-06, "loss": 0.1612, "step": 349020 }, { "epoch": 2.0747068019568333, "grad_norm": 4.747307300567627, "learning_rate": 7.270888849738974e-06, "loss": 0.1629, "step": 349030 }, { "epoch": 2.0747662440335017, "grad_norm": 4.418641567230225, "learning_rate": 7.270703990748196e-06, "loss": 0.1509, "step": 349040 }, { "epoch": 2.07482568611017, "grad_norm": 4.677828311920166, "learning_rate": 7.270519127846994e-06, "loss": 0.1498, "step": 349050 }, { "epoch": 2.074885128186838, "grad_norm": 5.468638896942139, "learning_rate": 7.270334261035686e-06, "loss": 0.1776, "step": 349060 }, { "epoch": 2.0749445702635065, "grad_norm": 4.578067779541016, "learning_rate": 7.270149390314591e-06, "loss": 0.1711, "step": 349070 }, { "epoch": 2.075004012340175, "grad_norm": 3.9797439575195312, "learning_rate": 7.269964515684031e-06, "loss": 0.148, "step": 349080 }, { "epoch": 2.0750634544168434, "grad_norm": 4.3683390617370605, "learning_rate": 7.269779637144318e-06, "loss": 0.1673, "step": 349090 }, { "epoch": 2.075122896493512, "grad_norm": 3.246798276901245, "learning_rate": 7.269594754695776e-06, "loss": 0.15, "step": 349100 }, { "epoch": 2.07518233857018, "grad_norm": 4.3657426834106445, "learning_rate": 7.26940986833872e-06, "loss": 0.136, "step": 349110 }, { "epoch": 2.0752417806468486, "grad_norm": 4.182703018188477, "learning_rate": 7.2692249780734695e-06, "loss": 0.1495, "step": 349120 }, { "epoch": 2.075301222723517, "grad_norm": 4.989732265472412, "learning_rate": 7.269040083900343e-06, "loss": 0.1509, "step": 349130 }, { "epoch": 2.0753606648001854, "grad_norm": 4.055772304534912, "learning_rate": 7.268855185819659e-06, "loss": 0.137, "step": 349140 }, { "epoch": 2.075420106876854, "grad_norm": 4.2698564529418945, "learning_rate": 7.268670283831735e-06, "loss": 0.1557, "step": 349150 }, { "epoch": 2.0754795489535223, "grad_norm": 4.073376178741455, "learning_rate": 7.268485377936889e-06, "loss": 0.1601, "step": 349160 }, { "epoch": 2.0755389910301907, "grad_norm": 4.504426002502441, "learning_rate": 7.268300468135443e-06, "loss": 0.1486, "step": 349170 }, { "epoch": 2.075598433106859, "grad_norm": 5.071841239929199, "learning_rate": 7.268115554427713e-06, "loss": 0.1695, "step": 349180 }, { "epoch": 2.0756578751835275, "grad_norm": 4.773815155029297, "learning_rate": 7.267930636814015e-06, "loss": 0.1601, "step": 349190 }, { "epoch": 2.075717317260196, "grad_norm": 4.521125793457031, "learning_rate": 7.2677457152946716e-06, "loss": 0.1651, "step": 349200 }, { "epoch": 2.0757767593368643, "grad_norm": 4.664554595947266, "learning_rate": 7.267560789869998e-06, "loss": 0.1438, "step": 349210 }, { "epoch": 2.0758362014135328, "grad_norm": 4.251399993896484, "learning_rate": 7.267375860540316e-06, "loss": 0.1483, "step": 349220 }, { "epoch": 2.075895643490201, "grad_norm": 4.50543212890625, "learning_rate": 7.267190927305942e-06, "loss": 0.1502, "step": 349230 }, { "epoch": 2.0759550855668696, "grad_norm": 4.199424743652344, "learning_rate": 7.267005990167194e-06, "loss": 0.1561, "step": 349240 }, { "epoch": 2.0760145276435376, "grad_norm": 4.810173988342285, "learning_rate": 7.266821049124391e-06, "loss": 0.1536, "step": 349250 }, { "epoch": 2.076073969720206, "grad_norm": 4.973043441772461, "learning_rate": 7.266636104177851e-06, "loss": 0.1741, "step": 349260 }, { "epoch": 2.0761334117968744, "grad_norm": 3.5492947101593018, "learning_rate": 7.266451155327894e-06, "loss": 0.1578, "step": 349270 }, { "epoch": 2.076192853873543, "grad_norm": 4.524798393249512, "learning_rate": 7.2662662025748374e-06, "loss": 0.1512, "step": 349280 }, { "epoch": 2.076252295950211, "grad_norm": 4.3898820877075195, "learning_rate": 7.266081245919001e-06, "loss": 0.1428, "step": 349290 }, { "epoch": 2.0763117380268796, "grad_norm": 4.7758073806762695, "learning_rate": 7.2658962853607015e-06, "loss": 0.1597, "step": 349300 }, { "epoch": 2.076371180103548, "grad_norm": 5.088501453399658, "learning_rate": 7.26571132090026e-06, "loss": 0.1588, "step": 349310 }, { "epoch": 2.0764306221802165, "grad_norm": 3.818325996398926, "learning_rate": 7.2655263525379905e-06, "loss": 0.157, "step": 349320 }, { "epoch": 2.076490064256885, "grad_norm": 4.2862396240234375, "learning_rate": 7.265341380274215e-06, "loss": 0.1474, "step": 349330 }, { "epoch": 2.0765495063335533, "grad_norm": 3.5271048545837402, "learning_rate": 7.265156404109253e-06, "loss": 0.1493, "step": 349340 }, { "epoch": 2.0766089484102217, "grad_norm": 4.570470333099365, "learning_rate": 7.26497142404342e-06, "loss": 0.1664, "step": 349350 }, { "epoch": 2.07666839048689, "grad_norm": 3.291563034057617, "learning_rate": 7.264786440077036e-06, "loss": 0.1463, "step": 349360 }, { "epoch": 2.0767278325635585, "grad_norm": 3.507481575012207, "learning_rate": 7.26460145221042e-06, "loss": 0.1433, "step": 349370 }, { "epoch": 2.076787274640227, "grad_norm": 4.795426845550537, "learning_rate": 7.264416460443888e-06, "loss": 0.1545, "step": 349380 }, { "epoch": 2.0768467167168954, "grad_norm": 5.34860372543335, "learning_rate": 7.264231464777763e-06, "loss": 0.151, "step": 349390 }, { "epoch": 2.0769061587935638, "grad_norm": 3.786658525466919, "learning_rate": 7.264046465212362e-06, "loss": 0.16, "step": 349400 }, { "epoch": 2.076965600870232, "grad_norm": 4.000965118408203, "learning_rate": 7.263861461748001e-06, "loss": 0.1354, "step": 349410 }, { "epoch": 2.0770250429469006, "grad_norm": 6.376407146453857, "learning_rate": 7.263676454385e-06, "loss": 0.1713, "step": 349420 }, { "epoch": 2.0770844850235686, "grad_norm": 5.32500696182251, "learning_rate": 7.26349144312368e-06, "loss": 0.1558, "step": 349430 }, { "epoch": 2.077143927100237, "grad_norm": 5.453754425048828, "learning_rate": 7.2633064279643564e-06, "loss": 0.1653, "step": 349440 }, { "epoch": 2.0772033691769054, "grad_norm": 3.847388982772827, "learning_rate": 7.26312140890735e-06, "loss": 0.1503, "step": 349450 }, { "epoch": 2.077262811253574, "grad_norm": 3.0124576091766357, "learning_rate": 7.262936385952978e-06, "loss": 0.1446, "step": 349460 }, { "epoch": 2.0773222533302422, "grad_norm": 4.342776298522949, "learning_rate": 7.262751359101559e-06, "loss": 0.1605, "step": 349470 }, { "epoch": 2.0773816954069106, "grad_norm": 3.73065447807312, "learning_rate": 7.262566328353413e-06, "loss": 0.1489, "step": 349480 }, { "epoch": 2.077441137483579, "grad_norm": 4.638499736785889, "learning_rate": 7.262381293708856e-06, "loss": 0.1417, "step": 349490 }, { "epoch": 2.0775005795602475, "grad_norm": 4.897395133972168, "learning_rate": 7.262196255168212e-06, "loss": 0.1488, "step": 349500 }, { "epoch": 2.077560021636916, "grad_norm": 4.785304546356201, "learning_rate": 7.262011212731792e-06, "loss": 0.1544, "step": 349510 }, { "epoch": 2.0776194637135843, "grad_norm": 5.161442756652832, "learning_rate": 7.2618261663999214e-06, "loss": 0.1521, "step": 349520 }, { "epoch": 2.0776789057902527, "grad_norm": 5.728309154510498, "learning_rate": 7.261641116172916e-06, "loss": 0.1723, "step": 349530 }, { "epoch": 2.077738347866921, "grad_norm": 4.436882019042969, "learning_rate": 7.261456062051095e-06, "loss": 0.1888, "step": 349540 }, { "epoch": 2.0777977899435895, "grad_norm": 3.59643292427063, "learning_rate": 7.2612710040347755e-06, "loss": 0.1517, "step": 349550 }, { "epoch": 2.077857232020258, "grad_norm": 4.17956018447876, "learning_rate": 7.26108594212428e-06, "loss": 0.1365, "step": 349560 }, { "epoch": 2.0779166740969264, "grad_norm": 3.6207897663116455, "learning_rate": 7.260900876319921e-06, "loss": 0.1637, "step": 349570 }, { "epoch": 2.077976116173595, "grad_norm": 5.414546489715576, "learning_rate": 7.260715806622024e-06, "loss": 0.1559, "step": 349580 }, { "epoch": 2.078035558250263, "grad_norm": 3.5106427669525146, "learning_rate": 7.260530733030904e-06, "loss": 0.1324, "step": 349590 }, { "epoch": 2.0780950003269316, "grad_norm": 4.59842586517334, "learning_rate": 7.260345655546879e-06, "loss": 0.1854, "step": 349600 }, { "epoch": 2.0781544424035996, "grad_norm": 4.170790195465088, "learning_rate": 7.26016057417027e-06, "loss": 0.1619, "step": 349610 }, { "epoch": 2.078213884480268, "grad_norm": 3.679966926574707, "learning_rate": 7.259975488901394e-06, "loss": 0.1421, "step": 349620 }, { "epoch": 2.0782733265569364, "grad_norm": 4.6373162269592285, "learning_rate": 7.259790399740573e-06, "loss": 0.1613, "step": 349630 }, { "epoch": 2.078332768633605, "grad_norm": 4.163497447967529, "learning_rate": 7.25960530668812e-06, "loss": 0.1842, "step": 349640 }, { "epoch": 2.0783922107102732, "grad_norm": 4.984753131866455, "learning_rate": 7.259420209744359e-06, "loss": 0.144, "step": 349650 }, { "epoch": 2.0784516527869417, "grad_norm": 3.599701404571533, "learning_rate": 7.259235108909608e-06, "loss": 0.145, "step": 349660 }, { "epoch": 2.07851109486361, "grad_norm": 4.798705101013184, "learning_rate": 7.259050004184181e-06, "loss": 0.1535, "step": 349670 }, { "epoch": 2.0785705369402785, "grad_norm": 6.157500267028809, "learning_rate": 7.2588648955684035e-06, "loss": 0.1571, "step": 349680 }, { "epoch": 2.078629979016947, "grad_norm": 4.266168117523193, "learning_rate": 7.258679783062591e-06, "loss": 0.148, "step": 349690 }, { "epoch": 2.0786894210936153, "grad_norm": 4.143688201904297, "learning_rate": 7.2584946666670604e-06, "loss": 0.1504, "step": 349700 }, { "epoch": 2.0787488631702837, "grad_norm": 4.207571983337402, "learning_rate": 7.258309546382133e-06, "loss": 0.1359, "step": 349710 }, { "epoch": 2.078808305246952, "grad_norm": 3.1146206855773926, "learning_rate": 7.258124422208129e-06, "loss": 0.1249, "step": 349720 }, { "epoch": 2.0788677473236206, "grad_norm": 3.8772857189178467, "learning_rate": 7.2579392941453644e-06, "loss": 0.1497, "step": 349730 }, { "epoch": 2.078927189400289, "grad_norm": 3.774601697921753, "learning_rate": 7.2577541621941575e-06, "loss": 0.1491, "step": 349740 }, { "epoch": 2.0789866314769574, "grad_norm": 4.626951694488525, "learning_rate": 7.25756902635483e-06, "loss": 0.1555, "step": 349750 }, { "epoch": 2.079046073553626, "grad_norm": 3.3568739891052246, "learning_rate": 7.257383886627699e-06, "loss": 0.1477, "step": 349760 }, { "epoch": 2.079105515630294, "grad_norm": 4.135044574737549, "learning_rate": 7.257198743013083e-06, "loss": 0.159, "step": 349770 }, { "epoch": 2.0791649577069626, "grad_norm": 5.5563435554504395, "learning_rate": 7.257013595511302e-06, "loss": 0.1679, "step": 349780 }, { "epoch": 2.079224399783631, "grad_norm": 3.642641067504883, "learning_rate": 7.256828444122674e-06, "loss": 0.1347, "step": 349790 }, { "epoch": 2.079283841860299, "grad_norm": 5.272860050201416, "learning_rate": 7.256643288847518e-06, "loss": 0.1559, "step": 349800 }, { "epoch": 2.0793432839369674, "grad_norm": 3.745537519454956, "learning_rate": 7.256458129686153e-06, "loss": 0.1577, "step": 349810 }, { "epoch": 2.079402726013636, "grad_norm": 4.043887615203857, "learning_rate": 7.256272966638899e-06, "loss": 0.1487, "step": 349820 }, { "epoch": 2.0794621680903043, "grad_norm": 4.368487358093262, "learning_rate": 7.256087799706073e-06, "loss": 0.1508, "step": 349830 }, { "epoch": 2.0795216101669727, "grad_norm": 4.519379138946533, "learning_rate": 7.255902628887994e-06, "loss": 0.1865, "step": 349840 }, { "epoch": 2.079581052243641, "grad_norm": 4.245850086212158, "learning_rate": 7.255717454184982e-06, "loss": 0.1481, "step": 349850 }, { "epoch": 2.0796404943203095, "grad_norm": 3.1852452754974365, "learning_rate": 7.255532275597355e-06, "loss": 0.1277, "step": 349860 }, { "epoch": 2.079699936396978, "grad_norm": 6.699606418609619, "learning_rate": 7.255347093125433e-06, "loss": 0.1632, "step": 349870 }, { "epoch": 2.0797593784736463, "grad_norm": 3.5238330364227295, "learning_rate": 7.255161906769535e-06, "loss": 0.1351, "step": 349880 }, { "epoch": 2.0798188205503148, "grad_norm": 3.734513998031616, "learning_rate": 7.254976716529978e-06, "loss": 0.1579, "step": 349890 }, { "epoch": 2.079878262626983, "grad_norm": 4.806310653686523, "learning_rate": 7.254791522407081e-06, "loss": 0.1442, "step": 349900 }, { "epoch": 2.0799377047036516, "grad_norm": 3.9487602710723877, "learning_rate": 7.2546063244011654e-06, "loss": 0.1641, "step": 349910 }, { "epoch": 2.07999714678032, "grad_norm": 3.5185184478759766, "learning_rate": 7.2544211225125495e-06, "loss": 0.1631, "step": 349920 }, { "epoch": 2.0800565888569884, "grad_norm": 3.7502365112304688, "learning_rate": 7.254235916741548e-06, "loss": 0.1529, "step": 349930 }, { "epoch": 2.080116030933657, "grad_norm": 2.6720285415649414, "learning_rate": 7.254050707088486e-06, "loss": 0.1541, "step": 349940 }, { "epoch": 2.0801754730103252, "grad_norm": 4.256397724151611, "learning_rate": 7.25386549355368e-06, "loss": 0.1649, "step": 349950 }, { "epoch": 2.0802349150869937, "grad_norm": 4.434881210327148, "learning_rate": 7.253680276137448e-06, "loss": 0.1536, "step": 349960 }, { "epoch": 2.080294357163662, "grad_norm": 4.982119083404541, "learning_rate": 7.2534950548401095e-06, "loss": 0.1402, "step": 349970 }, { "epoch": 2.0803537992403305, "grad_norm": 4.6722846031188965, "learning_rate": 7.253309829661983e-06, "loss": 0.1785, "step": 349980 }, { "epoch": 2.0804132413169985, "grad_norm": 4.0962395668029785, "learning_rate": 7.253124600603389e-06, "loss": 0.1405, "step": 349990 }, { "epoch": 2.080472683393667, "grad_norm": 5.461005687713623, "learning_rate": 7.252939367664645e-06, "loss": 0.1693, "step": 350000 }, { "epoch": 2.0805321254703353, "grad_norm": 4.3600335121154785, "learning_rate": 7.252754130846072e-06, "loss": 0.1664, "step": 350010 }, { "epoch": 2.0805915675470037, "grad_norm": 2.931220769882202, "learning_rate": 7.252568890147987e-06, "loss": 0.1709, "step": 350020 }, { "epoch": 2.080651009623672, "grad_norm": 5.59276819229126, "learning_rate": 7.252383645570709e-06, "loss": 0.1593, "step": 350030 }, { "epoch": 2.0807104517003405, "grad_norm": 2.7555925846099854, "learning_rate": 7.252198397114557e-06, "loss": 0.1291, "step": 350040 }, { "epoch": 2.080769893777009, "grad_norm": 4.222426414489746, "learning_rate": 7.252013144779853e-06, "loss": 0.1471, "step": 350050 }, { "epoch": 2.0808293358536774, "grad_norm": 4.241922378540039, "learning_rate": 7.25182788856691e-06, "loss": 0.1558, "step": 350060 }, { "epoch": 2.0808887779303458, "grad_norm": 5.229446887969971, "learning_rate": 7.251642628476055e-06, "loss": 0.1675, "step": 350070 }, { "epoch": 2.080948220007014, "grad_norm": 4.0671796798706055, "learning_rate": 7.2514573645076e-06, "loss": 0.1454, "step": 350080 }, { "epoch": 2.0810076620836826, "grad_norm": 3.6813228130340576, "learning_rate": 7.251272096661866e-06, "loss": 0.1534, "step": 350090 }, { "epoch": 2.081067104160351, "grad_norm": 4.489962577819824, "learning_rate": 7.251086824939175e-06, "loss": 0.1545, "step": 350100 }, { "epoch": 2.0811265462370194, "grad_norm": 3.7527267932891846, "learning_rate": 7.250901549339844e-06, "loss": 0.152, "step": 350110 }, { "epoch": 2.081185988313688, "grad_norm": 4.411059856414795, "learning_rate": 7.25071626986419e-06, "loss": 0.1716, "step": 350120 }, { "epoch": 2.0812454303903563, "grad_norm": 4.417267799377441, "learning_rate": 7.250530986512535e-06, "loss": 0.1529, "step": 350130 }, { "epoch": 2.0813048724670247, "grad_norm": 4.229187488555908, "learning_rate": 7.250345699285198e-06, "loss": 0.1349, "step": 350140 }, { "epoch": 2.081364314543693, "grad_norm": 5.021933078765869, "learning_rate": 7.250160408182496e-06, "loss": 0.1547, "step": 350150 }, { "epoch": 2.0814237566203615, "grad_norm": 5.602379322052002, "learning_rate": 7.249975113204749e-06, "loss": 0.162, "step": 350160 }, { "epoch": 2.0814831986970295, "grad_norm": 3.5606131553649902, "learning_rate": 7.249789814352277e-06, "loss": 0.1689, "step": 350170 }, { "epoch": 2.081542640773698, "grad_norm": 3.417264461517334, "learning_rate": 7.249604511625399e-06, "loss": 0.1481, "step": 350180 }, { "epoch": 2.0816020828503663, "grad_norm": 4.292647838592529, "learning_rate": 7.249419205024432e-06, "loss": 0.1593, "step": 350190 }, { "epoch": 2.0816615249270347, "grad_norm": 3.7868759632110596, "learning_rate": 7.2492338945496984e-06, "loss": 0.1529, "step": 350200 }, { "epoch": 2.081720967003703, "grad_norm": 4.000401496887207, "learning_rate": 7.249048580201517e-06, "loss": 0.1672, "step": 350210 }, { "epoch": 2.0817804090803715, "grad_norm": 4.558917999267578, "learning_rate": 7.248863261980202e-06, "loss": 0.1685, "step": 350220 }, { "epoch": 2.08183985115704, "grad_norm": 3.9877336025238037, "learning_rate": 7.248677939886079e-06, "loss": 0.172, "step": 350230 }, { "epoch": 2.0818992932337084, "grad_norm": 5.152071475982666, "learning_rate": 7.248492613919463e-06, "loss": 0.1674, "step": 350240 }, { "epoch": 2.081958735310377, "grad_norm": 3.797656297683716, "learning_rate": 7.248307284080674e-06, "loss": 0.1476, "step": 350250 }, { "epoch": 2.082018177387045, "grad_norm": 3.198761463165283, "learning_rate": 7.248121950370032e-06, "loss": 0.151, "step": 350260 }, { "epoch": 2.0820776194637136, "grad_norm": 4.642634868621826, "learning_rate": 7.247936612787856e-06, "loss": 0.1539, "step": 350270 }, { "epoch": 2.082137061540382, "grad_norm": 4.808751106262207, "learning_rate": 7.247751271334466e-06, "loss": 0.1491, "step": 350280 }, { "epoch": 2.0821965036170504, "grad_norm": 3.6808393001556396, "learning_rate": 7.247565926010178e-06, "loss": 0.1664, "step": 350290 }, { "epoch": 2.082255945693719, "grad_norm": 4.215417861938477, "learning_rate": 7.247380576815315e-06, "loss": 0.1514, "step": 350300 }, { "epoch": 2.0823153877703873, "grad_norm": 3.697697639465332, "learning_rate": 7.247195223750194e-06, "loss": 0.1549, "step": 350310 }, { "epoch": 2.0823748298470557, "grad_norm": 4.291619777679443, "learning_rate": 7.247009866815133e-06, "loss": 0.1488, "step": 350320 }, { "epoch": 2.082434271923724, "grad_norm": 4.077690124511719, "learning_rate": 7.246824506010456e-06, "loss": 0.1624, "step": 350330 }, { "epoch": 2.0824937140003925, "grad_norm": 5.635860919952393, "learning_rate": 7.246639141336478e-06, "loss": 0.1572, "step": 350340 }, { "epoch": 2.0825531560770605, "grad_norm": 4.918727874755859, "learning_rate": 7.246453772793518e-06, "loss": 0.1533, "step": 350350 }, { "epoch": 2.082612598153729, "grad_norm": 4.775973320007324, "learning_rate": 7.246268400381898e-06, "loss": 0.1369, "step": 350360 }, { "epoch": 2.0826720402303973, "grad_norm": 3.5219602584838867, "learning_rate": 7.246083024101934e-06, "loss": 0.1423, "step": 350370 }, { "epoch": 2.0827314823070657, "grad_norm": 5.241100788116455, "learning_rate": 7.245897643953948e-06, "loss": 0.1577, "step": 350380 }, { "epoch": 2.082790924383734, "grad_norm": 5.672959327697754, "learning_rate": 7.245712259938258e-06, "loss": 0.1451, "step": 350390 }, { "epoch": 2.0828503664604026, "grad_norm": 4.979864597320557, "learning_rate": 7.2455268720551855e-06, "loss": 0.1581, "step": 350400 }, { "epoch": 2.082909808537071, "grad_norm": 3.7104086875915527, "learning_rate": 7.245341480305046e-06, "loss": 0.1511, "step": 350410 }, { "epoch": 2.0829692506137394, "grad_norm": 4.4688615798950195, "learning_rate": 7.245156084688161e-06, "loss": 0.1587, "step": 350420 }, { "epoch": 2.083028692690408, "grad_norm": 6.781454563140869, "learning_rate": 7.2449706852048485e-06, "loss": 0.1645, "step": 350430 }, { "epoch": 2.083088134767076, "grad_norm": 3.3248417377471924, "learning_rate": 7.244785281855431e-06, "loss": 0.1203, "step": 350440 }, { "epoch": 2.0831475768437446, "grad_norm": 3.5254414081573486, "learning_rate": 7.2445998746402225e-06, "loss": 0.1603, "step": 350450 }, { "epoch": 2.083207018920413, "grad_norm": 3.7535791397094727, "learning_rate": 7.244414463559547e-06, "loss": 0.1555, "step": 350460 }, { "epoch": 2.0832664609970815, "grad_norm": 4.643671035766602, "learning_rate": 7.244229048613722e-06, "loss": 0.1425, "step": 350470 }, { "epoch": 2.08332590307375, "grad_norm": 3.4321603775024414, "learning_rate": 7.244043629803066e-06, "loss": 0.1444, "step": 350480 }, { "epoch": 2.0833853451504183, "grad_norm": 5.051488876342773, "learning_rate": 7.2438582071278985e-06, "loss": 0.1553, "step": 350490 }, { "epoch": 2.0834447872270867, "grad_norm": 5.0330586433410645, "learning_rate": 7.24367278058854e-06, "loss": 0.1567, "step": 350500 }, { "epoch": 2.083504229303755, "grad_norm": 3.8250300884246826, "learning_rate": 7.24348735018531e-06, "loss": 0.132, "step": 350510 }, { "epoch": 2.0835636713804235, "grad_norm": 4.021509170532227, "learning_rate": 7.243301915918526e-06, "loss": 0.1357, "step": 350520 }, { "epoch": 2.083623113457092, "grad_norm": 3.9536099433898926, "learning_rate": 7.24311647778851e-06, "loss": 0.1602, "step": 350530 }, { "epoch": 2.08368255553376, "grad_norm": 6.087017059326172, "learning_rate": 7.24293103579558e-06, "loss": 0.1461, "step": 350540 }, { "epoch": 2.0837419976104283, "grad_norm": 5.071223735809326, "learning_rate": 7.242745589940053e-06, "loss": 0.1634, "step": 350550 }, { "epoch": 2.0838014396870967, "grad_norm": 4.7976393699646, "learning_rate": 7.242560140222251e-06, "loss": 0.1509, "step": 350560 }, { "epoch": 2.083860881763765, "grad_norm": 4.314233303070068, "learning_rate": 7.242374686642494e-06, "loss": 0.1527, "step": 350570 }, { "epoch": 2.0839203238404336, "grad_norm": 4.417144298553467, "learning_rate": 7.242189229201099e-06, "loss": 0.1533, "step": 350580 }, { "epoch": 2.083979765917102, "grad_norm": 3.725043535232544, "learning_rate": 7.242003767898387e-06, "loss": 0.1667, "step": 350590 }, { "epoch": 2.0840392079937704, "grad_norm": 3.5607457160949707, "learning_rate": 7.241818302734678e-06, "loss": 0.1495, "step": 350600 }, { "epoch": 2.084098650070439, "grad_norm": 4.112400054931641, "learning_rate": 7.241632833710288e-06, "loss": 0.146, "step": 350610 }, { "epoch": 2.0841580921471072, "grad_norm": 3.9044604301452637, "learning_rate": 7.241447360825541e-06, "loss": 0.1436, "step": 350620 }, { "epoch": 2.0842175342237756, "grad_norm": 4.741395473480225, "learning_rate": 7.241261884080753e-06, "loss": 0.1665, "step": 350630 }, { "epoch": 2.084276976300444, "grad_norm": 3.6545426845550537, "learning_rate": 7.241076403476246e-06, "loss": 0.1631, "step": 350640 }, { "epoch": 2.0843364183771125, "grad_norm": 5.946336269378662, "learning_rate": 7.240890919012338e-06, "loss": 0.1597, "step": 350650 }, { "epoch": 2.084395860453781, "grad_norm": 3.87788987159729, "learning_rate": 7.240705430689348e-06, "loss": 0.1448, "step": 350660 }, { "epoch": 2.0844553025304493, "grad_norm": 4.450660705566406, "learning_rate": 7.240519938507595e-06, "loss": 0.1376, "step": 350670 }, { "epoch": 2.0845147446071177, "grad_norm": 3.9946656227111816, "learning_rate": 7.2403344424674e-06, "loss": 0.1446, "step": 350680 }, { "epoch": 2.084574186683786, "grad_norm": 5.679806232452393, "learning_rate": 7.240148942569082e-06, "loss": 0.1557, "step": 350690 }, { "epoch": 2.0846336287604545, "grad_norm": 4.4076714515686035, "learning_rate": 7.239963438812959e-06, "loss": 0.1537, "step": 350700 }, { "epoch": 2.084693070837123, "grad_norm": 3.7611756324768066, "learning_rate": 7.239777931199352e-06, "loss": 0.1387, "step": 350710 }, { "epoch": 2.0847525129137914, "grad_norm": 5.459211349487305, "learning_rate": 7.23959241972858e-06, "loss": 0.1395, "step": 350720 }, { "epoch": 2.0848119549904593, "grad_norm": 3.4912641048431396, "learning_rate": 7.239406904400965e-06, "loss": 0.1523, "step": 350730 }, { "epoch": 2.0848713970671278, "grad_norm": 3.9364821910858154, "learning_rate": 7.239221385216821e-06, "loss": 0.1518, "step": 350740 }, { "epoch": 2.084930839143796, "grad_norm": 5.905846118927002, "learning_rate": 7.239035862176474e-06, "loss": 0.1823, "step": 350750 }, { "epoch": 2.0849902812204646, "grad_norm": 4.957974910736084, "learning_rate": 7.238850335280238e-06, "loss": 0.1602, "step": 350760 }, { "epoch": 2.085049723297133, "grad_norm": 3.6015501022338867, "learning_rate": 7.238664804528435e-06, "loss": 0.1426, "step": 350770 }, { "epoch": 2.0851091653738014, "grad_norm": 3.636965036392212, "learning_rate": 7.238479269921383e-06, "loss": 0.1662, "step": 350780 }, { "epoch": 2.08516860745047, "grad_norm": 4.810731887817383, "learning_rate": 7.238293731459404e-06, "loss": 0.1528, "step": 350790 }, { "epoch": 2.0852280495271382, "grad_norm": 4.074427127838135, "learning_rate": 7.238108189142815e-06, "loss": 0.1545, "step": 350800 }, { "epoch": 2.0852874916038067, "grad_norm": 3.4152636528015137, "learning_rate": 7.237922642971938e-06, "loss": 0.1489, "step": 350810 }, { "epoch": 2.085346933680475, "grad_norm": 4.929439544677734, "learning_rate": 7.23773709294709e-06, "loss": 0.1659, "step": 350820 }, { "epoch": 2.0854063757571435, "grad_norm": 3.969348907470703, "learning_rate": 7.237551539068592e-06, "loss": 0.1564, "step": 350830 }, { "epoch": 2.085465817833812, "grad_norm": 5.106850624084473, "learning_rate": 7.237365981336764e-06, "loss": 0.1631, "step": 350840 }, { "epoch": 2.0855252599104803, "grad_norm": 3.451349973678589, "learning_rate": 7.237180419751923e-06, "loss": 0.1528, "step": 350850 }, { "epoch": 2.0855847019871487, "grad_norm": 6.062751770019531, "learning_rate": 7.236994854314393e-06, "loss": 0.1517, "step": 350860 }, { "epoch": 2.085644144063817, "grad_norm": 3.9155828952789307, "learning_rate": 7.236809285024489e-06, "loss": 0.1632, "step": 350870 }, { "epoch": 2.0857035861404856, "grad_norm": 4.344657897949219, "learning_rate": 7.236623711882533e-06, "loss": 0.1467, "step": 350880 }, { "epoch": 2.085763028217154, "grad_norm": 3.6299259662628174, "learning_rate": 7.2364381348888445e-06, "loss": 0.1466, "step": 350890 }, { "epoch": 2.0858224702938224, "grad_norm": 3.5458247661590576, "learning_rate": 7.236252554043743e-06, "loss": 0.1359, "step": 350900 }, { "epoch": 2.0858819123704904, "grad_norm": 5.1100640296936035, "learning_rate": 7.236066969347546e-06, "loss": 0.1497, "step": 350910 }, { "epoch": 2.085941354447159, "grad_norm": 4.446178913116455, "learning_rate": 7.235881380800576e-06, "loss": 0.1568, "step": 350920 }, { "epoch": 2.086000796523827, "grad_norm": 4.385490417480469, "learning_rate": 7.235695788403152e-06, "loss": 0.1496, "step": 350930 }, { "epoch": 2.0860602386004956, "grad_norm": 3.668334484100342, "learning_rate": 7.2355101921555925e-06, "loss": 0.1525, "step": 350940 }, { "epoch": 2.086119680677164, "grad_norm": 3.619929552078247, "learning_rate": 7.235324592058217e-06, "loss": 0.1629, "step": 350950 }, { "epoch": 2.0861791227538324, "grad_norm": 4.382725238800049, "learning_rate": 7.2351389881113475e-06, "loss": 0.1694, "step": 350960 }, { "epoch": 2.086238564830501, "grad_norm": 4.4108805656433105, "learning_rate": 7.2349533803153004e-06, "loss": 0.1569, "step": 350970 }, { "epoch": 2.0862980069071693, "grad_norm": 4.703856468200684, "learning_rate": 7.234767768670398e-06, "loss": 0.1577, "step": 350980 }, { "epoch": 2.0863574489838377, "grad_norm": 5.487725734710693, "learning_rate": 7.234582153176959e-06, "loss": 0.1495, "step": 350990 }, { "epoch": 2.086416891060506, "grad_norm": 3.4944236278533936, "learning_rate": 7.234396533835302e-06, "loss": 0.1385, "step": 351000 }, { "epoch": 2.0864763331371745, "grad_norm": 4.778999328613281, "learning_rate": 7.234210910645748e-06, "loss": 0.1756, "step": 351010 }, { "epoch": 2.086535775213843, "grad_norm": 5.488104820251465, "learning_rate": 7.234025283608617e-06, "loss": 0.1668, "step": 351020 }, { "epoch": 2.0865952172905113, "grad_norm": 4.126681327819824, "learning_rate": 7.233839652724226e-06, "loss": 0.1641, "step": 351030 }, { "epoch": 2.0866546593671798, "grad_norm": 3.8743677139282227, "learning_rate": 7.233654017992897e-06, "loss": 0.1474, "step": 351040 }, { "epoch": 2.086714101443848, "grad_norm": 3.633563280105591, "learning_rate": 7.2334683794149505e-06, "loss": 0.1739, "step": 351050 }, { "epoch": 2.0867735435205166, "grad_norm": 3.8275938034057617, "learning_rate": 7.233282736990706e-06, "loss": 0.1415, "step": 351060 }, { "epoch": 2.086832985597185, "grad_norm": 4.2789387702941895, "learning_rate": 7.233097090720479e-06, "loss": 0.1609, "step": 351070 }, { "epoch": 2.0868924276738534, "grad_norm": 3.975572109222412, "learning_rate": 7.232911440604594e-06, "loss": 0.1448, "step": 351080 }, { "epoch": 2.0869518697505214, "grad_norm": 2.9356489181518555, "learning_rate": 7.23272578664337e-06, "loss": 0.1569, "step": 351090 }, { "epoch": 2.08701131182719, "grad_norm": 3.7941718101501465, "learning_rate": 7.232540128837124e-06, "loss": 0.1578, "step": 351100 }, { "epoch": 2.087070753903858, "grad_norm": 4.687681198120117, "learning_rate": 7.232354467186179e-06, "loss": 0.1697, "step": 351110 }, { "epoch": 2.0871301959805266, "grad_norm": 4.170804977416992, "learning_rate": 7.232168801690853e-06, "loss": 0.1399, "step": 351120 }, { "epoch": 2.087189638057195, "grad_norm": 4.275956153869629, "learning_rate": 7.231983132351464e-06, "loss": 0.1406, "step": 351130 }, { "epoch": 2.0872490801338635, "grad_norm": 3.1738409996032715, "learning_rate": 7.231797459168335e-06, "loss": 0.1439, "step": 351140 }, { "epoch": 2.087308522210532, "grad_norm": 4.4842529296875, "learning_rate": 7.231611782141785e-06, "loss": 0.1578, "step": 351150 }, { "epoch": 2.0873679642872003, "grad_norm": 4.187760829925537, "learning_rate": 7.231426101272134e-06, "loss": 0.1548, "step": 351160 }, { "epoch": 2.0874274063638687, "grad_norm": 4.635411262512207, "learning_rate": 7.2312404165596994e-06, "loss": 0.1638, "step": 351170 }, { "epoch": 2.087486848440537, "grad_norm": 3.991198778152466, "learning_rate": 7.231054728004803e-06, "loss": 0.1644, "step": 351180 }, { "epoch": 2.0875462905172055, "grad_norm": 5.60683536529541, "learning_rate": 7.230869035607765e-06, "loss": 0.1586, "step": 351190 }, { "epoch": 2.087605732593874, "grad_norm": 3.3765478134155273, "learning_rate": 7.230683339368902e-06, "loss": 0.1369, "step": 351200 }, { "epoch": 2.0876651746705424, "grad_norm": 3.912379264831543, "learning_rate": 7.230497639288539e-06, "loss": 0.1487, "step": 351210 }, { "epoch": 2.0877246167472108, "grad_norm": 4.687250137329102, "learning_rate": 7.230311935366993e-06, "loss": 0.149, "step": 351220 }, { "epoch": 2.087784058823879, "grad_norm": 4.259668827056885, "learning_rate": 7.230126227604582e-06, "loss": 0.147, "step": 351230 }, { "epoch": 2.0878435009005476, "grad_norm": 4.679966449737549, "learning_rate": 7.229940516001628e-06, "loss": 0.144, "step": 351240 }, { "epoch": 2.087902942977216, "grad_norm": 4.660675048828125, "learning_rate": 7.22975480055845e-06, "loss": 0.1387, "step": 351250 }, { "epoch": 2.0879623850538844, "grad_norm": 6.227418422698975, "learning_rate": 7.229569081275367e-06, "loss": 0.1526, "step": 351260 }, { "epoch": 2.088021827130553, "grad_norm": 4.413043022155762, "learning_rate": 7.229383358152702e-06, "loss": 0.157, "step": 351270 }, { "epoch": 2.088081269207221, "grad_norm": 3.69946026802063, "learning_rate": 7.229197631190773e-06, "loss": 0.1349, "step": 351280 }, { "epoch": 2.0881407112838892, "grad_norm": 5.878931045532227, "learning_rate": 7.2290119003898996e-06, "loss": 0.1733, "step": 351290 }, { "epoch": 2.0882001533605576, "grad_norm": 5.592736721038818, "learning_rate": 7.2288261657504e-06, "loss": 0.1449, "step": 351300 }, { "epoch": 2.088259595437226, "grad_norm": 4.975331783294678, "learning_rate": 7.228640427272597e-06, "loss": 0.1372, "step": 351310 }, { "epoch": 2.0883190375138945, "grad_norm": 4.978298664093018, "learning_rate": 7.228454684956811e-06, "loss": 0.1554, "step": 351320 }, { "epoch": 2.088378479590563, "grad_norm": 4.611794471740723, "learning_rate": 7.228268938803358e-06, "loss": 0.1313, "step": 351330 }, { "epoch": 2.0884379216672313, "grad_norm": 4.030888080596924, "learning_rate": 7.22808318881256e-06, "loss": 0.1461, "step": 351340 }, { "epoch": 2.0884973637438997, "grad_norm": 3.8445372581481934, "learning_rate": 7.227897434984737e-06, "loss": 0.1532, "step": 351350 }, { "epoch": 2.088556805820568, "grad_norm": 3.9070041179656982, "learning_rate": 7.227711677320208e-06, "loss": 0.1485, "step": 351360 }, { "epoch": 2.0886162478972365, "grad_norm": 4.334084510803223, "learning_rate": 7.227525915819296e-06, "loss": 0.1365, "step": 351370 }, { "epoch": 2.088675689973905, "grad_norm": 5.564695835113525, "learning_rate": 7.227340150482317e-06, "loss": 0.1534, "step": 351380 }, { "epoch": 2.0887351320505734, "grad_norm": 3.9395132064819336, "learning_rate": 7.227154381309593e-06, "loss": 0.1348, "step": 351390 }, { "epoch": 2.088794574127242, "grad_norm": 4.420434951782227, "learning_rate": 7.226968608301444e-06, "loss": 0.1366, "step": 351400 }, { "epoch": 2.08885401620391, "grad_norm": 5.012402534484863, "learning_rate": 7.226782831458188e-06, "loss": 0.1766, "step": 351410 }, { "epoch": 2.0889134582805786, "grad_norm": 3.9989404678344727, "learning_rate": 7.226597050780147e-06, "loss": 0.1641, "step": 351420 }, { "epoch": 2.088972900357247, "grad_norm": 5.323464870452881, "learning_rate": 7.22641126626764e-06, "loss": 0.1559, "step": 351430 }, { "epoch": 2.0890323424339154, "grad_norm": 5.19510555267334, "learning_rate": 7.226225477920989e-06, "loss": 0.1804, "step": 351440 }, { "epoch": 2.089091784510584, "grad_norm": 4.729356288909912, "learning_rate": 7.226039685740509e-06, "loss": 0.1772, "step": 351450 }, { "epoch": 2.0891512265872523, "grad_norm": 4.084849834442139, "learning_rate": 7.225853889726524e-06, "loss": 0.1351, "step": 351460 }, { "epoch": 2.0892106686639202, "grad_norm": 4.659523963928223, "learning_rate": 7.225668089879354e-06, "loss": 0.1466, "step": 351470 }, { "epoch": 2.0892701107405887, "grad_norm": 3.8996453285217285, "learning_rate": 7.225482286199317e-06, "loss": 0.153, "step": 351480 }, { "epoch": 2.089329552817257, "grad_norm": 4.948398590087891, "learning_rate": 7.225296478686734e-06, "loss": 0.1473, "step": 351490 }, { "epoch": 2.0893889948939255, "grad_norm": 4.827080249786377, "learning_rate": 7.2251106673419255e-06, "loss": 0.1595, "step": 351500 }, { "epoch": 2.089448436970594, "grad_norm": 5.587960243225098, "learning_rate": 7.224924852165211e-06, "loss": 0.1363, "step": 351510 }, { "epoch": 2.0895078790472623, "grad_norm": 4.142667770385742, "learning_rate": 7.22473903315691e-06, "loss": 0.1599, "step": 351520 }, { "epoch": 2.0895673211239307, "grad_norm": 3.4332871437072754, "learning_rate": 7.224553210317344e-06, "loss": 0.1426, "step": 351530 }, { "epoch": 2.089626763200599, "grad_norm": 5.269819259643555, "learning_rate": 7.2243673836468305e-06, "loss": 0.1482, "step": 351540 }, { "epoch": 2.0896862052772676, "grad_norm": 6.57074499130249, "learning_rate": 7.224181553145692e-06, "loss": 0.1664, "step": 351550 }, { "epoch": 2.089745647353936, "grad_norm": 4.750101566314697, "learning_rate": 7.223995718814247e-06, "loss": 0.1535, "step": 351560 }, { "epoch": 2.0898050894306044, "grad_norm": 4.035411834716797, "learning_rate": 7.223809880652816e-06, "loss": 0.1742, "step": 351570 }, { "epoch": 2.089864531507273, "grad_norm": 5.627403736114502, "learning_rate": 7.223624038661718e-06, "loss": 0.1559, "step": 351580 }, { "epoch": 2.089923973583941, "grad_norm": 4.686828136444092, "learning_rate": 7.2234381928412755e-06, "loss": 0.155, "step": 351590 }, { "epoch": 2.0899834156606096, "grad_norm": 3.446732759475708, "learning_rate": 7.223252343191807e-06, "loss": 0.135, "step": 351600 }, { "epoch": 2.090042857737278, "grad_norm": 4.9106550216674805, "learning_rate": 7.223066489713632e-06, "loss": 0.1499, "step": 351610 }, { "epoch": 2.0901022998139465, "grad_norm": 4.43269681930542, "learning_rate": 7.222880632407072e-06, "loss": 0.1483, "step": 351620 }, { "epoch": 2.090161741890615, "grad_norm": 4.510354995727539, "learning_rate": 7.222694771272447e-06, "loss": 0.158, "step": 351630 }, { "epoch": 2.0902211839672833, "grad_norm": 3.423056125640869, "learning_rate": 7.222508906310075e-06, "loss": 0.1504, "step": 351640 }, { "epoch": 2.0902806260439513, "grad_norm": 3.6642048358917236, "learning_rate": 7.222323037520278e-06, "loss": 0.1498, "step": 351650 }, { "epoch": 2.0903400681206197, "grad_norm": 4.103990077972412, "learning_rate": 7.2221371649033754e-06, "loss": 0.1582, "step": 351660 }, { "epoch": 2.090399510197288, "grad_norm": 3.9597327709198, "learning_rate": 7.221951288459689e-06, "loss": 0.1488, "step": 351670 }, { "epoch": 2.0904589522739565, "grad_norm": 4.765270709991455, "learning_rate": 7.2217654081895346e-06, "loss": 0.1454, "step": 351680 }, { "epoch": 2.090518394350625, "grad_norm": 4.140628814697266, "learning_rate": 7.221579524093237e-06, "loss": 0.1671, "step": 351690 }, { "epoch": 2.0905778364272933, "grad_norm": 5.582165718078613, "learning_rate": 7.221393636171114e-06, "loss": 0.1497, "step": 351700 }, { "epoch": 2.0906372785039617, "grad_norm": 4.027615070343018, "learning_rate": 7.221207744423485e-06, "loss": 0.1475, "step": 351710 }, { "epoch": 2.09069672058063, "grad_norm": 5.6236042976379395, "learning_rate": 7.221021848850672e-06, "loss": 0.1538, "step": 351720 }, { "epoch": 2.0907561626572986, "grad_norm": 4.610978126525879, "learning_rate": 7.220835949452996e-06, "loss": 0.1644, "step": 351730 }, { "epoch": 2.090815604733967, "grad_norm": 4.382841110229492, "learning_rate": 7.220650046230773e-06, "loss": 0.1678, "step": 351740 }, { "epoch": 2.0908750468106354, "grad_norm": 4.370837688446045, "learning_rate": 7.220464139184326e-06, "loss": 0.1567, "step": 351750 }, { "epoch": 2.090934488887304, "grad_norm": 5.850169658660889, "learning_rate": 7.220278228313976e-06, "loss": 0.1787, "step": 351760 }, { "epoch": 2.0909939309639722, "grad_norm": 4.310197830200195, "learning_rate": 7.220092313620042e-06, "loss": 0.1602, "step": 351770 }, { "epoch": 2.0910533730406407, "grad_norm": 5.779502868652344, "learning_rate": 7.219906395102842e-06, "loss": 0.1551, "step": 351780 }, { "epoch": 2.091112815117309, "grad_norm": 3.653874635696411, "learning_rate": 7.219720472762701e-06, "loss": 0.1745, "step": 351790 }, { "epoch": 2.0911722571939775, "grad_norm": 4.654190540313721, "learning_rate": 7.2195345465999355e-06, "loss": 0.1505, "step": 351800 }, { "epoch": 2.091231699270646, "grad_norm": 3.757427215576172, "learning_rate": 7.219348616614868e-06, "loss": 0.1423, "step": 351810 }, { "epoch": 2.0912911413473143, "grad_norm": 3.205338478088379, "learning_rate": 7.219162682807815e-06, "loss": 0.1372, "step": 351820 }, { "epoch": 2.0913505834239823, "grad_norm": 4.960048198699951, "learning_rate": 7.2189767451791e-06, "loss": 0.1474, "step": 351830 }, { "epoch": 2.0914100255006507, "grad_norm": 3.609733819961548, "learning_rate": 7.218790803729042e-06, "loss": 0.1476, "step": 351840 }, { "epoch": 2.091469467577319, "grad_norm": 6.343861103057861, "learning_rate": 7.218604858457961e-06, "loss": 0.1605, "step": 351850 }, { "epoch": 2.0915289096539875, "grad_norm": 5.074982166290283, "learning_rate": 7.218418909366179e-06, "loss": 0.1333, "step": 351860 }, { "epoch": 2.091588351730656, "grad_norm": 3.376237392425537, "learning_rate": 7.218232956454015e-06, "loss": 0.157, "step": 351870 }, { "epoch": 2.0916477938073244, "grad_norm": 4.527040481567383, "learning_rate": 7.218046999721788e-06, "loss": 0.1493, "step": 351880 }, { "epoch": 2.0917072358839928, "grad_norm": 4.350261688232422, "learning_rate": 7.21786103916982e-06, "loss": 0.1655, "step": 351890 }, { "epoch": 2.091766677960661, "grad_norm": 3.6518445014953613, "learning_rate": 7.217675074798431e-06, "loss": 0.1332, "step": 351900 }, { "epoch": 2.0918261200373296, "grad_norm": 4.713712692260742, "learning_rate": 7.21748910660794e-06, "loss": 0.1591, "step": 351910 }, { "epoch": 2.091885562113998, "grad_norm": 4.380942344665527, "learning_rate": 7.2173031345986685e-06, "loss": 0.1482, "step": 351920 }, { "epoch": 2.0919450041906664, "grad_norm": 4.334845542907715, "learning_rate": 7.217117158770938e-06, "loss": 0.1525, "step": 351930 }, { "epoch": 2.092004446267335, "grad_norm": 4.203260898590088, "learning_rate": 7.216931179125065e-06, "loss": 0.1804, "step": 351940 }, { "epoch": 2.0920638883440033, "grad_norm": 4.372366905212402, "learning_rate": 7.216745195661373e-06, "loss": 0.1481, "step": 351950 }, { "epoch": 2.0921233304206717, "grad_norm": 4.650871753692627, "learning_rate": 7.216559208380181e-06, "loss": 0.1708, "step": 351960 }, { "epoch": 2.09218277249734, "grad_norm": 5.169161319732666, "learning_rate": 7.216373217281811e-06, "loss": 0.1691, "step": 351970 }, { "epoch": 2.0922422145740085, "grad_norm": 5.1370463371276855, "learning_rate": 7.21618722236658e-06, "loss": 0.1567, "step": 351980 }, { "epoch": 2.092301656650677, "grad_norm": 4.1613287925720215, "learning_rate": 7.216001223634811e-06, "loss": 0.1571, "step": 351990 }, { "epoch": 2.0923610987273453, "grad_norm": 3.4614791870117188, "learning_rate": 7.215815221086824e-06, "loss": 0.1542, "step": 352000 }, { "epoch": 2.0924205408040137, "grad_norm": 3.3617687225341797, "learning_rate": 7.215629214722937e-06, "loss": 0.1636, "step": 352010 }, { "epoch": 2.0924799828806817, "grad_norm": 4.458836555480957, "learning_rate": 7.215443204543473e-06, "loss": 0.1574, "step": 352020 }, { "epoch": 2.09253942495735, "grad_norm": 4.547436714172363, "learning_rate": 7.215257190548752e-06, "loss": 0.1503, "step": 352030 }, { "epoch": 2.0925988670340185, "grad_norm": 3.127596855163574, "learning_rate": 7.215071172739093e-06, "loss": 0.1411, "step": 352040 }, { "epoch": 2.092658309110687, "grad_norm": 4.078490734100342, "learning_rate": 7.214885151114818e-06, "loss": 0.1571, "step": 352050 }, { "epoch": 2.0927177511873554, "grad_norm": 5.890131950378418, "learning_rate": 7.214699125676246e-06, "loss": 0.1671, "step": 352060 }, { "epoch": 2.092777193264024, "grad_norm": 3.1067867279052734, "learning_rate": 7.214513096423698e-06, "loss": 0.1401, "step": 352070 }, { "epoch": 2.092836635340692, "grad_norm": 4.139360427856445, "learning_rate": 7.214327063357495e-06, "loss": 0.1504, "step": 352080 }, { "epoch": 2.0928960774173606, "grad_norm": 5.019741058349609, "learning_rate": 7.214141026477956e-06, "loss": 0.1757, "step": 352090 }, { "epoch": 2.092955519494029, "grad_norm": 3.9057061672210693, "learning_rate": 7.213954985785401e-06, "loss": 0.1773, "step": 352100 }, { "epoch": 2.0930149615706974, "grad_norm": 3.273799180984497, "learning_rate": 7.213768941280153e-06, "loss": 0.1321, "step": 352110 }, { "epoch": 2.093074403647366, "grad_norm": 3.4859066009521484, "learning_rate": 7.213582892962529e-06, "loss": 0.1613, "step": 352120 }, { "epoch": 2.0931338457240343, "grad_norm": 5.462535381317139, "learning_rate": 7.213396840832852e-06, "loss": 0.15, "step": 352130 }, { "epoch": 2.0931932878007027, "grad_norm": 5.148741722106934, "learning_rate": 7.21321078489144e-06, "loss": 0.1393, "step": 352140 }, { "epoch": 2.093252729877371, "grad_norm": 3.407409429550171, "learning_rate": 7.213024725138618e-06, "loss": 0.1384, "step": 352150 }, { "epoch": 2.0933121719540395, "grad_norm": 3.9666666984558105, "learning_rate": 7.212838661574702e-06, "loss": 0.1412, "step": 352160 }, { "epoch": 2.093371614030708, "grad_norm": 4.525083541870117, "learning_rate": 7.212652594200013e-06, "loss": 0.1447, "step": 352170 }, { "epoch": 2.0934310561073763, "grad_norm": 4.612943172454834, "learning_rate": 7.212466523014873e-06, "loss": 0.1466, "step": 352180 }, { "epoch": 2.0934904981840448, "grad_norm": 6.819973468780518, "learning_rate": 7.212280448019602e-06, "loss": 0.1669, "step": 352190 }, { "epoch": 2.093549940260713, "grad_norm": 4.271772384643555, "learning_rate": 7.212094369214518e-06, "loss": 0.1621, "step": 352200 }, { "epoch": 2.093609382337381, "grad_norm": 4.584837436676025, "learning_rate": 7.211908286599947e-06, "loss": 0.1447, "step": 352210 }, { "epoch": 2.0936688244140496, "grad_norm": 3.840379476547241, "learning_rate": 7.211722200176203e-06, "loss": 0.1521, "step": 352220 }, { "epoch": 2.093728266490718, "grad_norm": 2.9806325435638428, "learning_rate": 7.211536109943611e-06, "loss": 0.1453, "step": 352230 }, { "epoch": 2.0937877085673864, "grad_norm": 4.336552143096924, "learning_rate": 7.21135001590249e-06, "loss": 0.185, "step": 352240 }, { "epoch": 2.093847150644055, "grad_norm": 4.56827974319458, "learning_rate": 7.211163918053159e-06, "loss": 0.1449, "step": 352250 }, { "epoch": 2.093906592720723, "grad_norm": 4.140428066253662, "learning_rate": 7.210977816395941e-06, "loss": 0.1468, "step": 352260 }, { "epoch": 2.0939660347973916, "grad_norm": 3.9181759357452393, "learning_rate": 7.2107917109311554e-06, "loss": 0.1558, "step": 352270 }, { "epoch": 2.09402547687406, "grad_norm": 3.421689987182617, "learning_rate": 7.210605601659123e-06, "loss": 0.1587, "step": 352280 }, { "epoch": 2.0940849189507285, "grad_norm": 4.423826217651367, "learning_rate": 7.210419488580163e-06, "loss": 0.153, "step": 352290 }, { "epoch": 2.094144361027397, "grad_norm": 4.364318370819092, "learning_rate": 7.2102333716945976e-06, "loss": 0.1664, "step": 352300 }, { "epoch": 2.0942038031040653, "grad_norm": 3.505263328552246, "learning_rate": 7.210047251002748e-06, "loss": 0.1489, "step": 352310 }, { "epoch": 2.0942632451807337, "grad_norm": 5.751247406005859, "learning_rate": 7.209861126504932e-06, "loss": 0.1708, "step": 352320 }, { "epoch": 2.094322687257402, "grad_norm": 4.523890972137451, "learning_rate": 7.20967499820147e-06, "loss": 0.1711, "step": 352330 }, { "epoch": 2.0943821293340705, "grad_norm": 3.5852835178375244, "learning_rate": 7.209488866092685e-06, "loss": 0.152, "step": 352340 }, { "epoch": 2.094441571410739, "grad_norm": 6.009641647338867, "learning_rate": 7.209302730178897e-06, "loss": 0.1687, "step": 352350 }, { "epoch": 2.0945010134874074, "grad_norm": 4.561256408691406, "learning_rate": 7.2091165904604255e-06, "loss": 0.1676, "step": 352360 }, { "epoch": 2.0945604555640758, "grad_norm": 3.986248016357422, "learning_rate": 7.208930446937592e-06, "loss": 0.1462, "step": 352370 }, { "epoch": 2.094619897640744, "grad_norm": 4.647897720336914, "learning_rate": 7.2087442996107175e-06, "loss": 0.1434, "step": 352380 }, { "epoch": 2.094679339717412, "grad_norm": 4.8455023765563965, "learning_rate": 7.208558148480121e-06, "loss": 0.1343, "step": 352390 }, { "epoch": 2.0947387817940806, "grad_norm": 5.661658763885498, "learning_rate": 7.2083719935461235e-06, "loss": 0.1562, "step": 352400 }, { "epoch": 2.094798223870749, "grad_norm": 4.555295467376709, "learning_rate": 7.208185834809047e-06, "loss": 0.148, "step": 352410 }, { "epoch": 2.0948576659474174, "grad_norm": 4.159723281860352, "learning_rate": 7.20799967226921e-06, "loss": 0.1425, "step": 352420 }, { "epoch": 2.094917108024086, "grad_norm": 4.938438415527344, "learning_rate": 7.207813505926934e-06, "loss": 0.1645, "step": 352430 }, { "epoch": 2.0949765501007542, "grad_norm": 3.4775640964508057, "learning_rate": 7.207627335782541e-06, "loss": 0.1627, "step": 352440 }, { "epoch": 2.0950359921774226, "grad_norm": 5.4926323890686035, "learning_rate": 7.20744116183635e-06, "loss": 0.1714, "step": 352450 }, { "epoch": 2.095095434254091, "grad_norm": 3.441479444503784, "learning_rate": 7.207254984088681e-06, "loss": 0.1562, "step": 352460 }, { "epoch": 2.0951548763307595, "grad_norm": 3.914057493209839, "learning_rate": 7.207068802539855e-06, "loss": 0.158, "step": 352470 }, { "epoch": 2.095214318407428, "grad_norm": 3.9608192443847656, "learning_rate": 7.206882617190194e-06, "loss": 0.1621, "step": 352480 }, { "epoch": 2.0952737604840963, "grad_norm": 4.091065883636475, "learning_rate": 7.206696428040019e-06, "loss": 0.1476, "step": 352490 }, { "epoch": 2.0953332025607647, "grad_norm": 5.966179370880127, "learning_rate": 7.206510235089648e-06, "loss": 0.1449, "step": 352500 }, { "epoch": 2.095392644637433, "grad_norm": 3.67698335647583, "learning_rate": 7.206324038339403e-06, "loss": 0.1445, "step": 352510 }, { "epoch": 2.0954520867141015, "grad_norm": 3.638582468032837, "learning_rate": 7.206137837789606e-06, "loss": 0.1404, "step": 352520 }, { "epoch": 2.09551152879077, "grad_norm": 4.2994561195373535, "learning_rate": 7.205951633440575e-06, "loss": 0.1522, "step": 352530 }, { "epoch": 2.0955709708674384, "grad_norm": 4.127529621124268, "learning_rate": 7.205765425292632e-06, "loss": 0.1584, "step": 352540 }, { "epoch": 2.095630412944107, "grad_norm": 4.482946395874023, "learning_rate": 7.2055792133461e-06, "loss": 0.1608, "step": 352550 }, { "epoch": 2.095689855020775, "grad_norm": 4.812164783477783, "learning_rate": 7.205392997601295e-06, "loss": 0.1648, "step": 352560 }, { "epoch": 2.095749297097443, "grad_norm": 2.1778440475463867, "learning_rate": 7.20520677805854e-06, "loss": 0.1375, "step": 352570 }, { "epoch": 2.0958087391741116, "grad_norm": 3.25858736038208, "learning_rate": 7.205020554718158e-06, "loss": 0.1456, "step": 352580 }, { "epoch": 2.09586818125078, "grad_norm": 3.8311355113983154, "learning_rate": 7.2048343275804655e-06, "loss": 0.1413, "step": 352590 }, { "epoch": 2.0959276233274484, "grad_norm": 4.324924945831299, "learning_rate": 7.204648096645787e-06, "loss": 0.146, "step": 352600 }, { "epoch": 2.095987065404117, "grad_norm": 4.601138591766357, "learning_rate": 7.2044618619144405e-06, "loss": 0.1366, "step": 352610 }, { "epoch": 2.0960465074807852, "grad_norm": 4.399250507354736, "learning_rate": 7.204275623386748e-06, "loss": 0.1713, "step": 352620 }, { "epoch": 2.0961059495574537, "grad_norm": 3.3522684574127197, "learning_rate": 7.204089381063028e-06, "loss": 0.1524, "step": 352630 }, { "epoch": 2.096165391634122, "grad_norm": 4.289227485656738, "learning_rate": 7.203903134943606e-06, "loss": 0.1522, "step": 352640 }, { "epoch": 2.0962248337107905, "grad_norm": 4.81578254699707, "learning_rate": 7.203716885028799e-06, "loss": 0.1601, "step": 352650 }, { "epoch": 2.096284275787459, "grad_norm": 4.5633931159973145, "learning_rate": 7.203530631318927e-06, "loss": 0.1522, "step": 352660 }, { "epoch": 2.0963437178641273, "grad_norm": 3.9210832118988037, "learning_rate": 7.203344373814314e-06, "loss": 0.1637, "step": 352670 }, { "epoch": 2.0964031599407957, "grad_norm": 3.3318283557891846, "learning_rate": 7.203158112515277e-06, "loss": 0.1621, "step": 352680 }, { "epoch": 2.096462602017464, "grad_norm": 4.904854774475098, "learning_rate": 7.2029718474221396e-06, "loss": 0.157, "step": 352690 }, { "epoch": 2.0965220440941326, "grad_norm": 3.944188117980957, "learning_rate": 7.202785578535223e-06, "loss": 0.1384, "step": 352700 }, { "epoch": 2.096581486170801, "grad_norm": 3.1549227237701416, "learning_rate": 7.2025993058548475e-06, "loss": 0.1399, "step": 352710 }, { "epoch": 2.0966409282474694, "grad_norm": 3.1771748065948486, "learning_rate": 7.202413029381331e-06, "loss": 0.1332, "step": 352720 }, { "epoch": 2.096700370324138, "grad_norm": 2.971755266189575, "learning_rate": 7.202226749114998e-06, "loss": 0.1457, "step": 352730 }, { "epoch": 2.0967598124008062, "grad_norm": 3.2335145473480225, "learning_rate": 7.202040465056167e-06, "loss": 0.1412, "step": 352740 }, { "epoch": 2.0968192544774746, "grad_norm": 5.816854476928711, "learning_rate": 7.2018541772051596e-06, "loss": 0.1718, "step": 352750 }, { "epoch": 2.0968786965541426, "grad_norm": 4.866080284118652, "learning_rate": 7.201667885562298e-06, "loss": 0.1493, "step": 352760 }, { "epoch": 2.096938138630811, "grad_norm": 3.4619617462158203, "learning_rate": 7.2014815901279e-06, "loss": 0.1413, "step": 352770 }, { "epoch": 2.0969975807074794, "grad_norm": 4.960750579833984, "learning_rate": 7.201295290902288e-06, "loss": 0.165, "step": 352780 }, { "epoch": 2.097057022784148, "grad_norm": 4.168699264526367, "learning_rate": 7.201108987885783e-06, "loss": 0.1546, "step": 352790 }, { "epoch": 2.0971164648608163, "grad_norm": 5.288180351257324, "learning_rate": 7.200922681078706e-06, "loss": 0.1431, "step": 352800 }, { "epoch": 2.0971759069374847, "grad_norm": 4.8382134437561035, "learning_rate": 7.200736370481378e-06, "loss": 0.1681, "step": 352810 }, { "epoch": 2.097235349014153, "grad_norm": 3.3596644401550293, "learning_rate": 7.2005500560941175e-06, "loss": 0.1556, "step": 352820 }, { "epoch": 2.0972947910908215, "grad_norm": 5.084418773651123, "learning_rate": 7.20036373791725e-06, "loss": 0.1847, "step": 352830 }, { "epoch": 2.09735423316749, "grad_norm": 5.495421886444092, "learning_rate": 7.200177415951092e-06, "loss": 0.1335, "step": 352840 }, { "epoch": 2.0974136752441583, "grad_norm": 3.933100461959839, "learning_rate": 7.1999910901959655e-06, "loss": 0.1485, "step": 352850 }, { "epoch": 2.0974731173208268, "grad_norm": 4.441004276275635, "learning_rate": 7.199804760652194e-06, "loss": 0.156, "step": 352860 }, { "epoch": 2.097532559397495, "grad_norm": 4.378169059753418, "learning_rate": 7.199618427320094e-06, "loss": 0.162, "step": 352870 }, { "epoch": 2.0975920014741636, "grad_norm": 3.910808801651001, "learning_rate": 7.199432090199989e-06, "loss": 0.16, "step": 352880 }, { "epoch": 2.097651443550832, "grad_norm": 4.833665370941162, "learning_rate": 7.1992457492922e-06, "loss": 0.1697, "step": 352890 }, { "epoch": 2.0977108856275004, "grad_norm": 2.24912691116333, "learning_rate": 7.199059404597047e-06, "loss": 0.1531, "step": 352900 }, { "epoch": 2.097770327704169, "grad_norm": 2.9750027656555176, "learning_rate": 7.198873056114852e-06, "loss": 0.1682, "step": 352910 }, { "epoch": 2.0978297697808372, "grad_norm": 4.3084282875061035, "learning_rate": 7.198686703845934e-06, "loss": 0.1576, "step": 352920 }, { "epoch": 2.0978892118575057, "grad_norm": 3.2559595108032227, "learning_rate": 7.198500347790617e-06, "loss": 0.1646, "step": 352930 }, { "epoch": 2.097948653934174, "grad_norm": 4.138097286224365, "learning_rate": 7.198313987949219e-06, "loss": 0.1755, "step": 352940 }, { "epoch": 2.098008096010842, "grad_norm": 4.6031718254089355, "learning_rate": 7.198127624322062e-06, "loss": 0.1484, "step": 352950 }, { "epoch": 2.0980675380875105, "grad_norm": 4.3598151206970215, "learning_rate": 7.197941256909467e-06, "loss": 0.1413, "step": 352960 }, { "epoch": 2.098126980164179, "grad_norm": 2.8375017642974854, "learning_rate": 7.1977548857117555e-06, "loss": 0.1426, "step": 352970 }, { "epoch": 2.0981864222408473, "grad_norm": 4.640388488769531, "learning_rate": 7.197568510729247e-06, "loss": 0.1651, "step": 352980 }, { "epoch": 2.0982458643175157, "grad_norm": 2.7509756088256836, "learning_rate": 7.197382131962264e-06, "loss": 0.1428, "step": 352990 }, { "epoch": 2.098305306394184, "grad_norm": 4.147274971008301, "learning_rate": 7.197195749411127e-06, "loss": 0.1516, "step": 353000 }, { "epoch": 2.0983647484708525, "grad_norm": 4.195645809173584, "learning_rate": 7.197009363076155e-06, "loss": 0.1529, "step": 353010 }, { "epoch": 2.098424190547521, "grad_norm": 3.893994092941284, "learning_rate": 7.196822972957671e-06, "loss": 0.1413, "step": 353020 }, { "epoch": 2.0984836326241894, "grad_norm": 5.0565385818481445, "learning_rate": 7.196636579055998e-06, "loss": 0.1782, "step": 353030 }, { "epoch": 2.0985430747008578, "grad_norm": 4.5067949295043945, "learning_rate": 7.196450181371453e-06, "loss": 0.1439, "step": 353040 }, { "epoch": 2.098602516777526, "grad_norm": 5.205606460571289, "learning_rate": 7.196263779904358e-06, "loss": 0.1854, "step": 353050 }, { "epoch": 2.0986619588541946, "grad_norm": 5.625962257385254, "learning_rate": 7.196077374655036e-06, "loss": 0.1589, "step": 353060 }, { "epoch": 2.098721400930863, "grad_norm": 4.288707733154297, "learning_rate": 7.195890965623808e-06, "loss": 0.1471, "step": 353070 }, { "epoch": 2.0987808430075314, "grad_norm": 3.4227817058563232, "learning_rate": 7.195704552810992e-06, "loss": 0.1461, "step": 353080 }, { "epoch": 2.0988402850842, "grad_norm": 3.8624560832977295, "learning_rate": 7.1955181362169104e-06, "loss": 0.1686, "step": 353090 }, { "epoch": 2.0988997271608683, "grad_norm": 3.7838175296783447, "learning_rate": 7.195331715841886e-06, "loss": 0.1749, "step": 353100 }, { "epoch": 2.0989591692375367, "grad_norm": 3.746997117996216, "learning_rate": 7.1951452916862365e-06, "loss": 0.1463, "step": 353110 }, { "epoch": 2.099018611314205, "grad_norm": 4.372451305389404, "learning_rate": 7.194958863750286e-06, "loss": 0.1381, "step": 353120 }, { "epoch": 2.099078053390873, "grad_norm": 4.027943134307861, "learning_rate": 7.194772432034354e-06, "loss": 0.163, "step": 353130 }, { "epoch": 2.0991374954675415, "grad_norm": 4.679173469543457, "learning_rate": 7.194585996538763e-06, "loss": 0.1553, "step": 353140 }, { "epoch": 2.09919693754421, "grad_norm": 3.3732457160949707, "learning_rate": 7.194399557263832e-06, "loss": 0.165, "step": 353150 }, { "epoch": 2.0992563796208783, "grad_norm": 4.514906883239746, "learning_rate": 7.194213114209885e-06, "loss": 0.1447, "step": 353160 }, { "epoch": 2.0993158216975467, "grad_norm": 3.530738115310669, "learning_rate": 7.19402666737724e-06, "loss": 0.1628, "step": 353170 }, { "epoch": 2.099375263774215, "grad_norm": 5.087888240814209, "learning_rate": 7.193840216766218e-06, "loss": 0.1587, "step": 353180 }, { "epoch": 2.0994347058508835, "grad_norm": 4.017876148223877, "learning_rate": 7.193653762377143e-06, "loss": 0.1349, "step": 353190 }, { "epoch": 2.099494147927552, "grad_norm": 4.778705596923828, "learning_rate": 7.193467304210334e-06, "loss": 0.155, "step": 353200 }, { "epoch": 2.0995535900042204, "grad_norm": 4.136139392852783, "learning_rate": 7.193280842266112e-06, "loss": 0.1599, "step": 353210 }, { "epoch": 2.099613032080889, "grad_norm": 5.177460670471191, "learning_rate": 7.1930943765448e-06, "loss": 0.1588, "step": 353220 }, { "epoch": 2.099672474157557, "grad_norm": 4.668802738189697, "learning_rate": 7.192907907046717e-06, "loss": 0.1592, "step": 353230 }, { "epoch": 2.0997319162342256, "grad_norm": 4.149046897888184, "learning_rate": 7.192721433772184e-06, "loss": 0.1402, "step": 353240 }, { "epoch": 2.099791358310894, "grad_norm": 4.05956506729126, "learning_rate": 7.192534956721524e-06, "loss": 0.1471, "step": 353250 }, { "epoch": 2.0998508003875624, "grad_norm": 3.273346424102783, "learning_rate": 7.1923484758950575e-06, "loss": 0.1687, "step": 353260 }, { "epoch": 2.099910242464231, "grad_norm": 4.805477142333984, "learning_rate": 7.192161991293105e-06, "loss": 0.1742, "step": 353270 }, { "epoch": 2.0999696845408993, "grad_norm": 6.087779521942139, "learning_rate": 7.191975502915988e-06, "loss": 0.1706, "step": 353280 }, { "epoch": 2.1000291266175677, "grad_norm": 3.850281238555908, "learning_rate": 7.191789010764029e-06, "loss": 0.1469, "step": 353290 }, { "epoch": 2.100088568694236, "grad_norm": 3.505028009414673, "learning_rate": 7.1916025148375465e-06, "loss": 0.1407, "step": 353300 }, { "epoch": 2.100148010770904, "grad_norm": 4.6263747215271, "learning_rate": 7.191416015136863e-06, "loss": 0.1649, "step": 353310 }, { "epoch": 2.1002074528475725, "grad_norm": 3.8767287731170654, "learning_rate": 7.1912295116623e-06, "loss": 0.1545, "step": 353320 }, { "epoch": 2.100266894924241, "grad_norm": 3.6058695316314697, "learning_rate": 7.191043004414178e-06, "loss": 0.162, "step": 353330 }, { "epoch": 2.1003263370009093, "grad_norm": 3.650801181793213, "learning_rate": 7.190856493392817e-06, "loss": 0.1522, "step": 353340 }, { "epoch": 2.1003857790775777, "grad_norm": 4.54080057144165, "learning_rate": 7.190669978598541e-06, "loss": 0.147, "step": 353350 }, { "epoch": 2.100445221154246, "grad_norm": 4.350739479064941, "learning_rate": 7.190483460031671e-06, "loss": 0.1326, "step": 353360 }, { "epoch": 2.1005046632309146, "grad_norm": 5.606250286102295, "learning_rate": 7.1902969376925255e-06, "loss": 0.1653, "step": 353370 }, { "epoch": 2.100564105307583, "grad_norm": 4.439696311950684, "learning_rate": 7.190110411581429e-06, "loss": 0.1446, "step": 353380 }, { "epoch": 2.1006235473842514, "grad_norm": 3.1262710094451904, "learning_rate": 7.189923881698701e-06, "loss": 0.1436, "step": 353390 }, { "epoch": 2.10068298946092, "grad_norm": 3.359562397003174, "learning_rate": 7.189737348044661e-06, "loss": 0.1524, "step": 353400 }, { "epoch": 2.100742431537588, "grad_norm": 4.866189479827881, "learning_rate": 7.189550810619633e-06, "loss": 0.1629, "step": 353410 }, { "epoch": 2.1008018736142566, "grad_norm": 4.286573886871338, "learning_rate": 7.1893642694239375e-06, "loss": 0.1475, "step": 353420 }, { "epoch": 2.100861315690925, "grad_norm": 4.402192115783691, "learning_rate": 7.189177724457894e-06, "loss": 0.1505, "step": 353430 }, { "epoch": 2.1009207577675935, "grad_norm": 4.098146438598633, "learning_rate": 7.188991175721827e-06, "loss": 0.1291, "step": 353440 }, { "epoch": 2.100980199844262, "grad_norm": 3.7630577087402344, "learning_rate": 7.1888046232160544e-06, "loss": 0.1565, "step": 353450 }, { "epoch": 2.1010396419209303, "grad_norm": 4.661920547485352, "learning_rate": 7.188618066940901e-06, "loss": 0.1755, "step": 353460 }, { "epoch": 2.1010990839975987, "grad_norm": 3.6588234901428223, "learning_rate": 7.1884315068966845e-06, "loss": 0.1513, "step": 353470 }, { "epoch": 2.101158526074267, "grad_norm": 4.334007740020752, "learning_rate": 7.18824494308373e-06, "loss": 0.1727, "step": 353480 }, { "epoch": 2.1012179681509355, "grad_norm": 5.52583122253418, "learning_rate": 7.188058375502355e-06, "loss": 0.1574, "step": 353490 }, { "epoch": 2.1012774102276035, "grad_norm": 4.391794681549072, "learning_rate": 7.187871804152882e-06, "loss": 0.1695, "step": 353500 }, { "epoch": 2.101336852304272, "grad_norm": 5.112245082855225, "learning_rate": 7.187685229035633e-06, "loss": 0.1475, "step": 353510 }, { "epoch": 2.1013962943809403, "grad_norm": 3.3858914375305176, "learning_rate": 7.1874986501509305e-06, "loss": 0.1554, "step": 353520 }, { "epoch": 2.1014557364576087, "grad_norm": 3.608491897583008, "learning_rate": 7.187312067499093e-06, "loss": 0.1537, "step": 353530 }, { "epoch": 2.101515178534277, "grad_norm": 4.875796318054199, "learning_rate": 7.187125481080443e-06, "loss": 0.1597, "step": 353540 }, { "epoch": 2.1015746206109456, "grad_norm": 4.860053062438965, "learning_rate": 7.186938890895303e-06, "loss": 0.1589, "step": 353550 }, { "epoch": 2.101634062687614, "grad_norm": 6.094798564910889, "learning_rate": 7.186752296943992e-06, "loss": 0.1649, "step": 353560 }, { "epoch": 2.1016935047642824, "grad_norm": 3.892688512802124, "learning_rate": 7.186565699226832e-06, "loss": 0.1538, "step": 353570 }, { "epoch": 2.101752946840951, "grad_norm": 4.662128925323486, "learning_rate": 7.186379097744146e-06, "loss": 0.1436, "step": 353580 }, { "epoch": 2.1018123889176192, "grad_norm": 6.18971061706543, "learning_rate": 7.186192492496256e-06, "loss": 0.1725, "step": 353590 }, { "epoch": 2.1018718309942876, "grad_norm": 5.033054828643799, "learning_rate": 7.1860058834834785e-06, "loss": 0.158, "step": 353600 }, { "epoch": 2.101931273070956, "grad_norm": 4.256564140319824, "learning_rate": 7.1858192707061406e-06, "loss": 0.1503, "step": 353610 }, { "epoch": 2.1019907151476245, "grad_norm": 3.4936752319335938, "learning_rate": 7.18563265416456e-06, "loss": 0.1393, "step": 353620 }, { "epoch": 2.102050157224293, "grad_norm": 3.9617464542388916, "learning_rate": 7.185446033859059e-06, "loss": 0.1714, "step": 353630 }, { "epoch": 2.1021095993009613, "grad_norm": 3.9366705417633057, "learning_rate": 7.18525940978996e-06, "loss": 0.1427, "step": 353640 }, { "epoch": 2.1021690413776297, "grad_norm": 3.9448866844177246, "learning_rate": 7.185072781957583e-06, "loss": 0.1656, "step": 353650 }, { "epoch": 2.102228483454298, "grad_norm": 3.4337549209594727, "learning_rate": 7.184886150362249e-06, "loss": 0.2004, "step": 353660 }, { "epoch": 2.1022879255309666, "grad_norm": 3.644195556640625, "learning_rate": 7.184699515004281e-06, "loss": 0.1537, "step": 353670 }, { "epoch": 2.102347367607635, "grad_norm": 5.177931785583496, "learning_rate": 7.184512875884001e-06, "loss": 0.1617, "step": 353680 }, { "epoch": 2.102406809684303, "grad_norm": 4.859381675720215, "learning_rate": 7.1843262330017285e-06, "loss": 0.1621, "step": 353690 }, { "epoch": 2.1024662517609713, "grad_norm": 3.8976151943206787, "learning_rate": 7.184139586357785e-06, "loss": 0.1486, "step": 353700 }, { "epoch": 2.1025256938376398, "grad_norm": 3.535104513168335, "learning_rate": 7.183952935952493e-06, "loss": 0.1378, "step": 353710 }, { "epoch": 2.102585135914308, "grad_norm": 5.179810523986816, "learning_rate": 7.183766281786174e-06, "loss": 0.187, "step": 353720 }, { "epoch": 2.1026445779909766, "grad_norm": 3.933969020843506, "learning_rate": 7.183579623859147e-06, "loss": 0.1484, "step": 353730 }, { "epoch": 2.102704020067645, "grad_norm": 3.3956801891326904, "learning_rate": 7.183392962171738e-06, "loss": 0.1554, "step": 353740 }, { "epoch": 2.1027634621443134, "grad_norm": 3.639822483062744, "learning_rate": 7.183206296724264e-06, "loss": 0.1447, "step": 353750 }, { "epoch": 2.102822904220982, "grad_norm": 5.268588066101074, "learning_rate": 7.183019627517048e-06, "loss": 0.1674, "step": 353760 }, { "epoch": 2.1028823462976503, "grad_norm": 3.9827470779418945, "learning_rate": 7.182832954550413e-06, "loss": 0.148, "step": 353770 }, { "epoch": 2.1029417883743187, "grad_norm": 4.330987930297852, "learning_rate": 7.182646277824679e-06, "loss": 0.1682, "step": 353780 }, { "epoch": 2.103001230450987, "grad_norm": 4.334255218505859, "learning_rate": 7.182459597340167e-06, "loss": 0.1421, "step": 353790 }, { "epoch": 2.1030606725276555, "grad_norm": 3.647923231124878, "learning_rate": 7.182272913097199e-06, "loss": 0.1575, "step": 353800 }, { "epoch": 2.103120114604324, "grad_norm": 5.305253505706787, "learning_rate": 7.1820862250960964e-06, "loss": 0.1487, "step": 353810 }, { "epoch": 2.1031795566809923, "grad_norm": 4.842266082763672, "learning_rate": 7.181899533337182e-06, "loss": 0.145, "step": 353820 }, { "epoch": 2.1032389987576607, "grad_norm": 5.396824359893799, "learning_rate": 7.181712837820776e-06, "loss": 0.1623, "step": 353830 }, { "epoch": 2.103298440834329, "grad_norm": 4.590732097625732, "learning_rate": 7.181526138547201e-06, "loss": 0.1395, "step": 353840 }, { "epoch": 2.1033578829109976, "grad_norm": 5.401801109313965, "learning_rate": 7.181339435516777e-06, "loss": 0.1593, "step": 353850 }, { "epoch": 2.103417324987666, "grad_norm": 3.4624290466308594, "learning_rate": 7.181152728729825e-06, "loss": 0.1565, "step": 353860 }, { "epoch": 2.103476767064334, "grad_norm": 4.025583744049072, "learning_rate": 7.180966018186669e-06, "loss": 0.1566, "step": 353870 }, { "epoch": 2.1035362091410024, "grad_norm": 3.5705137252807617, "learning_rate": 7.1807793038876295e-06, "loss": 0.1506, "step": 353880 }, { "epoch": 2.103595651217671, "grad_norm": 3.454033136367798, "learning_rate": 7.180592585833026e-06, "loss": 0.146, "step": 353890 }, { "epoch": 2.103655093294339, "grad_norm": 3.9506959915161133, "learning_rate": 7.180405864023183e-06, "loss": 0.1506, "step": 353900 }, { "epoch": 2.1037145353710076, "grad_norm": 3.8119635581970215, "learning_rate": 7.180219138458422e-06, "loss": 0.1546, "step": 353910 }, { "epoch": 2.103773977447676, "grad_norm": 4.3836212158203125, "learning_rate": 7.1800324091390625e-06, "loss": 0.1486, "step": 353920 }, { "epoch": 2.1038334195243444, "grad_norm": 5.120005130767822, "learning_rate": 7.179845676065428e-06, "loss": 0.1759, "step": 353930 }, { "epoch": 2.103892861601013, "grad_norm": 4.109119892120361, "learning_rate": 7.179658939237839e-06, "loss": 0.1446, "step": 353940 }, { "epoch": 2.1039523036776813, "grad_norm": 4.074123382568359, "learning_rate": 7.1794721986566155e-06, "loss": 0.1725, "step": 353950 }, { "epoch": 2.1040117457543497, "grad_norm": 3.968498468399048, "learning_rate": 7.1792854543220826e-06, "loss": 0.1488, "step": 353960 }, { "epoch": 2.104071187831018, "grad_norm": 4.194250583648682, "learning_rate": 7.179098706234559e-06, "loss": 0.1767, "step": 353970 }, { "epoch": 2.1041306299076865, "grad_norm": 4.530448913574219, "learning_rate": 7.17891195439437e-06, "loss": 0.1559, "step": 353980 }, { "epoch": 2.104190071984355, "grad_norm": 3.99190616607666, "learning_rate": 7.1787251988018316e-06, "loss": 0.1377, "step": 353990 }, { "epoch": 2.1042495140610233, "grad_norm": 4.233924388885498, "learning_rate": 7.1785384394572675e-06, "loss": 0.1558, "step": 354000 }, { "epoch": 2.1043089561376918, "grad_norm": 4.558392524719238, "learning_rate": 7.178351676361004e-06, "loss": 0.1598, "step": 354010 }, { "epoch": 2.10436839821436, "grad_norm": 4.430513858795166, "learning_rate": 7.178164909513357e-06, "loss": 0.1402, "step": 354020 }, { "epoch": 2.1044278402910286, "grad_norm": 4.394810199737549, "learning_rate": 7.17797813891465e-06, "loss": 0.1619, "step": 354030 }, { "epoch": 2.104487282367697, "grad_norm": 4.504515171051025, "learning_rate": 7.177791364565205e-06, "loss": 0.149, "step": 354040 }, { "epoch": 2.104546724444365, "grad_norm": 3.773061990737915, "learning_rate": 7.177604586465343e-06, "loss": 0.146, "step": 354050 }, { "epoch": 2.1046061665210334, "grad_norm": 3.8513576984405518, "learning_rate": 7.177417804615387e-06, "loss": 0.1451, "step": 354060 }, { "epoch": 2.104665608597702, "grad_norm": 5.484616279602051, "learning_rate": 7.177231019015658e-06, "loss": 0.1561, "step": 354070 }, { "epoch": 2.10472505067437, "grad_norm": 4.713701248168945, "learning_rate": 7.1770442296664755e-06, "loss": 0.1528, "step": 354080 }, { "epoch": 2.1047844927510386, "grad_norm": 4.118145942687988, "learning_rate": 7.176857436568165e-06, "loss": 0.1576, "step": 354090 }, { "epoch": 2.104843934827707, "grad_norm": 4.0522918701171875, "learning_rate": 7.176670639721046e-06, "loss": 0.1637, "step": 354100 }, { "epoch": 2.1049033769043755, "grad_norm": 4.716741561889648, "learning_rate": 7.176483839125439e-06, "loss": 0.1583, "step": 354110 }, { "epoch": 2.104962818981044, "grad_norm": 4.715124130249023, "learning_rate": 7.176297034781668e-06, "loss": 0.1729, "step": 354120 }, { "epoch": 2.1050222610577123, "grad_norm": 4.466668128967285, "learning_rate": 7.176110226690054e-06, "loss": 0.1467, "step": 354130 }, { "epoch": 2.1050817031343807, "grad_norm": 4.891843795776367, "learning_rate": 7.17592341485092e-06, "loss": 0.1514, "step": 354140 }, { "epoch": 2.105141145211049, "grad_norm": 4.908140659332275, "learning_rate": 7.1757365992645835e-06, "loss": 0.167, "step": 354150 }, { "epoch": 2.1052005872877175, "grad_norm": 6.660770416259766, "learning_rate": 7.17554977993137e-06, "loss": 0.1521, "step": 354160 }, { "epoch": 2.105260029364386, "grad_norm": 4.656449317932129, "learning_rate": 7.175362956851602e-06, "loss": 0.1527, "step": 354170 }, { "epoch": 2.1053194714410544, "grad_norm": 4.046861171722412, "learning_rate": 7.1751761300255964e-06, "loss": 0.145, "step": 354180 }, { "epoch": 2.1053789135177228, "grad_norm": 3.2944607734680176, "learning_rate": 7.1749892994536795e-06, "loss": 0.1414, "step": 354190 }, { "epoch": 2.105438355594391, "grad_norm": 2.8264214992523193, "learning_rate": 7.174802465136173e-06, "loss": 0.158, "step": 354200 }, { "epoch": 2.1054977976710596, "grad_norm": 4.872550964355469, "learning_rate": 7.174615627073394e-06, "loss": 0.1545, "step": 354210 }, { "epoch": 2.105557239747728, "grad_norm": 5.274244785308838, "learning_rate": 7.174428785265668e-06, "loss": 0.1626, "step": 354220 }, { "epoch": 2.1056166818243964, "grad_norm": 4.393386363983154, "learning_rate": 7.174241939713318e-06, "loss": 0.1411, "step": 354230 }, { "epoch": 2.1056761239010644, "grad_norm": 4.199827671051025, "learning_rate": 7.174055090416664e-06, "loss": 0.1433, "step": 354240 }, { "epoch": 2.105735565977733, "grad_norm": 4.58524751663208, "learning_rate": 7.173868237376026e-06, "loss": 0.1462, "step": 354250 }, { "epoch": 2.1057950080544012, "grad_norm": 4.248244285583496, "learning_rate": 7.173681380591728e-06, "loss": 0.1413, "step": 354260 }, { "epoch": 2.1058544501310696, "grad_norm": 4.615657806396484, "learning_rate": 7.173494520064093e-06, "loss": 0.1387, "step": 354270 }, { "epoch": 2.105913892207738, "grad_norm": 5.015877723693848, "learning_rate": 7.1733076557934386e-06, "loss": 0.1579, "step": 354280 }, { "epoch": 2.1059733342844065, "grad_norm": 5.8109259605407715, "learning_rate": 7.173120787780091e-06, "loss": 0.1656, "step": 354290 }, { "epoch": 2.106032776361075, "grad_norm": 3.2931833267211914, "learning_rate": 7.172933916024369e-06, "loss": 0.1637, "step": 354300 }, { "epoch": 2.1060922184377433, "grad_norm": 4.814416885375977, "learning_rate": 7.1727470405265965e-06, "loss": 0.142, "step": 354310 }, { "epoch": 2.1061516605144117, "grad_norm": 4.519317150115967, "learning_rate": 7.1725601612870946e-06, "loss": 0.1629, "step": 354320 }, { "epoch": 2.10621110259108, "grad_norm": 4.224520206451416, "learning_rate": 7.172373278306183e-06, "loss": 0.1686, "step": 354330 }, { "epoch": 2.1062705446677485, "grad_norm": 4.593823432922363, "learning_rate": 7.172186391584186e-06, "loss": 0.1628, "step": 354340 }, { "epoch": 2.106329986744417, "grad_norm": 4.800379753112793, "learning_rate": 7.171999501121425e-06, "loss": 0.1671, "step": 354350 }, { "epoch": 2.1063894288210854, "grad_norm": 5.2600789070129395, "learning_rate": 7.1718126069182226e-06, "loss": 0.1616, "step": 354360 }, { "epoch": 2.106448870897754, "grad_norm": 3.6532933712005615, "learning_rate": 7.1716257089749e-06, "loss": 0.158, "step": 354370 }, { "epoch": 2.106508312974422, "grad_norm": 3.714081048965454, "learning_rate": 7.171438807291777e-06, "loss": 0.1591, "step": 354380 }, { "epoch": 2.1065677550510906, "grad_norm": 3.672546863555908, "learning_rate": 7.171251901869179e-06, "loss": 0.1472, "step": 354390 }, { "epoch": 2.106627197127759, "grad_norm": 4.0630035400390625, "learning_rate": 7.171064992707426e-06, "loss": 0.1296, "step": 354400 }, { "epoch": 2.1066866392044274, "grad_norm": 4.453274250030518, "learning_rate": 7.170878079806838e-06, "loss": 0.1649, "step": 354410 }, { "epoch": 2.106746081281096, "grad_norm": 3.9125800132751465, "learning_rate": 7.170691163167741e-06, "loss": 0.1605, "step": 354420 }, { "epoch": 2.106805523357764, "grad_norm": 6.34080696105957, "learning_rate": 7.170504242790455e-06, "loss": 0.1725, "step": 354430 }, { "epoch": 2.1068649654344322, "grad_norm": 4.473356246948242, "learning_rate": 7.1703173186753e-06, "loss": 0.1798, "step": 354440 }, { "epoch": 2.1069244075111007, "grad_norm": 4.031319618225098, "learning_rate": 7.170130390822601e-06, "loss": 0.1556, "step": 354450 }, { "epoch": 2.106983849587769, "grad_norm": 4.977386951446533, "learning_rate": 7.169943459232677e-06, "loss": 0.145, "step": 354460 }, { "epoch": 2.1070432916644375, "grad_norm": 3.79168438911438, "learning_rate": 7.169756523905853e-06, "loss": 0.1463, "step": 354470 }, { "epoch": 2.107102733741106, "grad_norm": 5.1535844802856445, "learning_rate": 7.1695695848424485e-06, "loss": 0.1693, "step": 354480 }, { "epoch": 2.1071621758177743, "grad_norm": 4.489431858062744, "learning_rate": 7.169382642042787e-06, "loss": 0.1808, "step": 354490 }, { "epoch": 2.1072216178944427, "grad_norm": 4.343851566314697, "learning_rate": 7.16919569550719e-06, "loss": 0.1516, "step": 354500 }, { "epoch": 2.107281059971111, "grad_norm": 3.8060615062713623, "learning_rate": 7.169008745235978e-06, "loss": 0.1782, "step": 354510 }, { "epoch": 2.1073405020477796, "grad_norm": 4.5752081871032715, "learning_rate": 7.168821791229475e-06, "loss": 0.159, "step": 354520 }, { "epoch": 2.107399944124448, "grad_norm": 3.566987991333008, "learning_rate": 7.168634833488002e-06, "loss": 0.1321, "step": 354530 }, { "epoch": 2.1074593862011164, "grad_norm": 4.209702491760254, "learning_rate": 7.168447872011881e-06, "loss": 0.1492, "step": 354540 }, { "epoch": 2.107518828277785, "grad_norm": 4.25364875793457, "learning_rate": 7.168260906801433e-06, "loss": 0.1563, "step": 354550 }, { "epoch": 2.107578270354453, "grad_norm": 5.984798431396484, "learning_rate": 7.168073937856983e-06, "loss": 0.1504, "step": 354560 }, { "epoch": 2.1076377124311216, "grad_norm": 3.0875637531280518, "learning_rate": 7.167886965178848e-06, "loss": 0.136, "step": 354570 }, { "epoch": 2.10769715450779, "grad_norm": 6.362573623657227, "learning_rate": 7.167699988767356e-06, "loss": 0.1474, "step": 354580 }, { "epoch": 2.1077565965844585, "grad_norm": 4.918099403381348, "learning_rate": 7.167513008622825e-06, "loss": 0.1575, "step": 354590 }, { "epoch": 2.107816038661127, "grad_norm": 3.6036226749420166, "learning_rate": 7.167326024745578e-06, "loss": 0.1433, "step": 354600 }, { "epoch": 2.107875480737795, "grad_norm": 4.679261684417725, "learning_rate": 7.167139037135937e-06, "loss": 0.1608, "step": 354610 }, { "epoch": 2.1079349228144633, "grad_norm": 3.8696999549865723, "learning_rate": 7.166952045794224e-06, "loss": 0.1476, "step": 354620 }, { "epoch": 2.1079943648911317, "grad_norm": 5.605597496032715, "learning_rate": 7.166765050720761e-06, "loss": 0.151, "step": 354630 }, { "epoch": 2.1080538069678, "grad_norm": 4.735100746154785, "learning_rate": 7.166578051915869e-06, "loss": 0.1434, "step": 354640 }, { "epoch": 2.1081132490444685, "grad_norm": 4.134409427642822, "learning_rate": 7.166391049379873e-06, "loss": 0.1656, "step": 354650 }, { "epoch": 2.108172691121137, "grad_norm": 4.391343593597412, "learning_rate": 7.166204043113092e-06, "loss": 0.1285, "step": 354660 }, { "epoch": 2.1082321331978053, "grad_norm": 4.87248420715332, "learning_rate": 7.166017033115849e-06, "loss": 0.168, "step": 354670 }, { "epoch": 2.1082915752744738, "grad_norm": 3.984886884689331, "learning_rate": 7.165830019388467e-06, "loss": 0.161, "step": 354680 }, { "epoch": 2.108351017351142, "grad_norm": 3.3206756114959717, "learning_rate": 7.165643001931266e-06, "loss": 0.1501, "step": 354690 }, { "epoch": 2.1084104594278106, "grad_norm": 5.670794486999512, "learning_rate": 7.16545598074457e-06, "loss": 0.1563, "step": 354700 }, { "epoch": 2.108469901504479, "grad_norm": 4.627237796783447, "learning_rate": 7.1652689558287014e-06, "loss": 0.1644, "step": 354710 }, { "epoch": 2.1085293435811474, "grad_norm": 3.4925665855407715, "learning_rate": 7.16508192718398e-06, "loss": 0.1642, "step": 354720 }, { "epoch": 2.108588785657816, "grad_norm": 4.62030553817749, "learning_rate": 7.16489489481073e-06, "loss": 0.1732, "step": 354730 }, { "epoch": 2.1086482277344842, "grad_norm": 4.3322319984436035, "learning_rate": 7.164707858709272e-06, "loss": 0.17, "step": 354740 }, { "epoch": 2.1087076698111527, "grad_norm": 4.400981426239014, "learning_rate": 7.16452081887993e-06, "loss": 0.134, "step": 354750 }, { "epoch": 2.108767111887821, "grad_norm": 4.115317344665527, "learning_rate": 7.164333775323022e-06, "loss": 0.1483, "step": 354760 }, { "epoch": 2.1088265539644895, "grad_norm": 4.768415927886963, "learning_rate": 7.164146728038875e-06, "loss": 0.1487, "step": 354770 }, { "epoch": 2.108885996041158, "grad_norm": 4.862826824188232, "learning_rate": 7.1639596770278095e-06, "loss": 0.1562, "step": 354780 }, { "epoch": 2.108945438117826, "grad_norm": 4.853446960449219, "learning_rate": 7.1637726222901485e-06, "loss": 0.1452, "step": 354790 }, { "epoch": 2.1090048801944943, "grad_norm": 4.050079345703125, "learning_rate": 7.16358556382621e-06, "loss": 0.1594, "step": 354800 }, { "epoch": 2.1090643222711627, "grad_norm": 3.0609853267669678, "learning_rate": 7.16339850163632e-06, "loss": 0.1542, "step": 354810 }, { "epoch": 2.109123764347831, "grad_norm": 3.8815746307373047, "learning_rate": 7.163211435720801e-06, "loss": 0.1587, "step": 354820 }, { "epoch": 2.1091832064244995, "grad_norm": 4.328681945800781, "learning_rate": 7.163024366079971e-06, "loss": 0.1473, "step": 354830 }, { "epoch": 2.109242648501168, "grad_norm": 4.941681861877441, "learning_rate": 7.162837292714158e-06, "loss": 0.154, "step": 354840 }, { "epoch": 2.1093020905778364, "grad_norm": 4.975999355316162, "learning_rate": 7.16265021562368e-06, "loss": 0.1386, "step": 354850 }, { "epoch": 2.1093615326545048, "grad_norm": 5.365633964538574, "learning_rate": 7.162463134808859e-06, "loss": 0.1634, "step": 354860 }, { "epoch": 2.109420974731173, "grad_norm": 3.48641037940979, "learning_rate": 7.162276050270021e-06, "loss": 0.1688, "step": 354870 }, { "epoch": 2.1094804168078416, "grad_norm": 3.711256504058838, "learning_rate": 7.162088962007483e-06, "loss": 0.16, "step": 354880 }, { "epoch": 2.10953985888451, "grad_norm": 3.093860626220703, "learning_rate": 7.161901870021572e-06, "loss": 0.1451, "step": 354890 }, { "epoch": 2.1095993009611784, "grad_norm": 5.177188396453857, "learning_rate": 7.161714774312606e-06, "loss": 0.1546, "step": 354900 }, { "epoch": 2.109658743037847, "grad_norm": 3.201836347579956, "learning_rate": 7.16152767488091e-06, "loss": 0.1523, "step": 354910 }, { "epoch": 2.1097181851145153, "grad_norm": 4.739468097686768, "learning_rate": 7.161340571726806e-06, "loss": 0.1639, "step": 354920 }, { "epoch": 2.1097776271911837, "grad_norm": 4.551087379455566, "learning_rate": 7.161153464850614e-06, "loss": 0.1555, "step": 354930 }, { "epoch": 2.109837069267852, "grad_norm": 4.772093296051025, "learning_rate": 7.160966354252661e-06, "loss": 0.1564, "step": 354940 }, { "epoch": 2.1098965113445205, "grad_norm": 4.3198676109313965, "learning_rate": 7.160779239933264e-06, "loss": 0.1474, "step": 354950 }, { "epoch": 2.109955953421189, "grad_norm": 3.76806378364563, "learning_rate": 7.160592121892747e-06, "loss": 0.1419, "step": 354960 }, { "epoch": 2.1100153954978573, "grad_norm": 4.496135234832764, "learning_rate": 7.160405000131434e-06, "loss": 0.1512, "step": 354970 }, { "epoch": 2.1100748375745253, "grad_norm": 3.052751302719116, "learning_rate": 7.160217874649645e-06, "loss": 0.1314, "step": 354980 }, { "epoch": 2.1101342796511937, "grad_norm": 4.861926555633545, "learning_rate": 7.160030745447703e-06, "loss": 0.1564, "step": 354990 }, { "epoch": 2.110193721727862, "grad_norm": 4.2230072021484375, "learning_rate": 7.159843612525929e-06, "loss": 0.1404, "step": 355000 }, { "epoch": 2.1102531638045305, "grad_norm": 3.8583927154541016, "learning_rate": 7.159656475884649e-06, "loss": 0.1713, "step": 355010 }, { "epoch": 2.110312605881199, "grad_norm": 3.9636080265045166, "learning_rate": 7.159469335524182e-06, "loss": 0.148, "step": 355020 }, { "epoch": 2.1103720479578674, "grad_norm": 2.9902596473693848, "learning_rate": 7.1592821914448495e-06, "loss": 0.1358, "step": 355030 }, { "epoch": 2.110431490034536, "grad_norm": 4.158348083496094, "learning_rate": 7.159095043646978e-06, "loss": 0.1502, "step": 355040 }, { "epoch": 2.110490932111204, "grad_norm": 4.162105083465576, "learning_rate": 7.1589078921308865e-06, "loss": 0.143, "step": 355050 }, { "epoch": 2.1105503741878726, "grad_norm": 3.5678038597106934, "learning_rate": 7.158720736896897e-06, "loss": 0.1373, "step": 355060 }, { "epoch": 2.110609816264541, "grad_norm": 5.090280055999756, "learning_rate": 7.158533577945334e-06, "loss": 0.1558, "step": 355070 }, { "epoch": 2.1106692583412094, "grad_norm": 3.0035014152526855, "learning_rate": 7.158346415276518e-06, "loss": 0.1671, "step": 355080 }, { "epoch": 2.110728700417878, "grad_norm": 3.87353253364563, "learning_rate": 7.158159248890771e-06, "loss": 0.1433, "step": 355090 }, { "epoch": 2.1107881424945463, "grad_norm": 3.0541183948516846, "learning_rate": 7.157972078788418e-06, "loss": 0.1503, "step": 355100 }, { "epoch": 2.1108475845712147, "grad_norm": 4.183560371398926, "learning_rate": 7.157784904969778e-06, "loss": 0.155, "step": 355110 }, { "epoch": 2.110907026647883, "grad_norm": 4.0176777839660645, "learning_rate": 7.157597727435177e-06, "loss": 0.1273, "step": 355120 }, { "epoch": 2.1109664687245515, "grad_norm": 4.3773064613342285, "learning_rate": 7.157410546184933e-06, "loss": 0.1494, "step": 355130 }, { "epoch": 2.11102591080122, "grad_norm": 5.071041584014893, "learning_rate": 7.157223361219372e-06, "loss": 0.1541, "step": 355140 }, { "epoch": 2.1110853528778883, "grad_norm": 3.4641976356506348, "learning_rate": 7.157036172538816e-06, "loss": 0.1574, "step": 355150 }, { "epoch": 2.1111447949545568, "grad_norm": 3.890228033065796, "learning_rate": 7.156848980143584e-06, "loss": 0.1535, "step": 355160 }, { "epoch": 2.1112042370312247, "grad_norm": 3.738896131515503, "learning_rate": 7.156661784034002e-06, "loss": 0.1728, "step": 355170 }, { "epoch": 2.111263679107893, "grad_norm": 4.187780380249023, "learning_rate": 7.156474584210391e-06, "loss": 0.1363, "step": 355180 }, { "epoch": 2.1113231211845616, "grad_norm": 3.8395748138427734, "learning_rate": 7.156287380673073e-06, "loss": 0.1616, "step": 355190 }, { "epoch": 2.11138256326123, "grad_norm": 3.035865545272827, "learning_rate": 7.156100173422371e-06, "loss": 0.1558, "step": 355200 }, { "epoch": 2.1114420053378984, "grad_norm": 3.170592784881592, "learning_rate": 7.155912962458606e-06, "loss": 0.1586, "step": 355210 }, { "epoch": 2.111501447414567, "grad_norm": 4.038411617279053, "learning_rate": 7.155725747782103e-06, "loss": 0.1722, "step": 355220 }, { "epoch": 2.111560889491235, "grad_norm": 5.358306884765625, "learning_rate": 7.155538529393183e-06, "loss": 0.1556, "step": 355230 }, { "epoch": 2.1116203315679036, "grad_norm": 4.770234107971191, "learning_rate": 7.15535130729217e-06, "loss": 0.142, "step": 355240 }, { "epoch": 2.111679773644572, "grad_norm": 4.135842800140381, "learning_rate": 7.155164081479382e-06, "loss": 0.1669, "step": 355250 }, { "epoch": 2.1117392157212405, "grad_norm": 4.803883075714111, "learning_rate": 7.154976851955147e-06, "loss": 0.1483, "step": 355260 }, { "epoch": 2.111798657797909, "grad_norm": 4.28909969329834, "learning_rate": 7.154789618719783e-06, "loss": 0.1411, "step": 355270 }, { "epoch": 2.1118580998745773, "grad_norm": 5.740940570831299, "learning_rate": 7.154602381773614e-06, "loss": 0.1694, "step": 355280 }, { "epoch": 2.1119175419512457, "grad_norm": 4.419942378997803, "learning_rate": 7.154415141116964e-06, "loss": 0.1498, "step": 355290 }, { "epoch": 2.111976984027914, "grad_norm": 4.176704406738281, "learning_rate": 7.154227896750153e-06, "loss": 0.151, "step": 355300 }, { "epoch": 2.1120364261045825, "grad_norm": 3.2888381481170654, "learning_rate": 7.154040648673506e-06, "loss": 0.1427, "step": 355310 }, { "epoch": 2.112095868181251, "grad_norm": 4.3983941078186035, "learning_rate": 7.15385339688734e-06, "loss": 0.1342, "step": 355320 }, { "epoch": 2.1121553102579194, "grad_norm": 3.999372720718384, "learning_rate": 7.153666141391985e-06, "loss": 0.1538, "step": 355330 }, { "epoch": 2.1122147523345878, "grad_norm": 6.097507476806641, "learning_rate": 7.15347888218776e-06, "loss": 0.1752, "step": 355340 }, { "epoch": 2.1122741944112557, "grad_norm": 4.283135890960693, "learning_rate": 7.153291619274986e-06, "loss": 0.1364, "step": 355350 }, { "epoch": 2.112333636487924, "grad_norm": 5.078175067901611, "learning_rate": 7.153104352653988e-06, "loss": 0.1646, "step": 355360 }, { "epoch": 2.1123930785645926, "grad_norm": 3.534188985824585, "learning_rate": 7.152917082325087e-06, "loss": 0.1469, "step": 355370 }, { "epoch": 2.112452520641261, "grad_norm": 4.076724529266357, "learning_rate": 7.152729808288605e-06, "loss": 0.1616, "step": 355380 }, { "epoch": 2.1125119627179294, "grad_norm": 4.547591686248779, "learning_rate": 7.152542530544866e-06, "loss": 0.1403, "step": 355390 }, { "epoch": 2.112571404794598, "grad_norm": 4.004341125488281, "learning_rate": 7.152355249094193e-06, "loss": 0.1463, "step": 355400 }, { "epoch": 2.1126308468712662, "grad_norm": 5.281393527984619, "learning_rate": 7.1521679639369055e-06, "loss": 0.1443, "step": 355410 }, { "epoch": 2.1126902889479346, "grad_norm": 3.264498472213745, "learning_rate": 7.15198067507333e-06, "loss": 0.174, "step": 355420 }, { "epoch": 2.112749731024603, "grad_norm": 3.795318841934204, "learning_rate": 7.151793382503785e-06, "loss": 0.1492, "step": 355430 }, { "epoch": 2.1128091731012715, "grad_norm": 3.2146918773651123, "learning_rate": 7.151606086228596e-06, "loss": 0.1581, "step": 355440 }, { "epoch": 2.11286861517794, "grad_norm": 4.133406639099121, "learning_rate": 7.151418786248084e-06, "loss": 0.1428, "step": 355450 }, { "epoch": 2.1129280572546083, "grad_norm": 5.8431010246276855, "learning_rate": 7.151231482562574e-06, "loss": 0.1539, "step": 355460 }, { "epoch": 2.1129874993312767, "grad_norm": 4.487646579742432, "learning_rate": 7.151044175172386e-06, "loss": 0.1624, "step": 355470 }, { "epoch": 2.113046941407945, "grad_norm": 4.068630218505859, "learning_rate": 7.150856864077842e-06, "loss": 0.1715, "step": 355480 }, { "epoch": 2.1131063834846135, "grad_norm": 4.582985877990723, "learning_rate": 7.150669549279268e-06, "loss": 0.1507, "step": 355490 }, { "epoch": 2.113165825561282, "grad_norm": 4.193681716918945, "learning_rate": 7.150482230776983e-06, "loss": 0.1538, "step": 355500 }, { "epoch": 2.1132252676379504, "grad_norm": 3.2247726917266846, "learning_rate": 7.15029490857131e-06, "loss": 0.1508, "step": 355510 }, { "epoch": 2.113284709714619, "grad_norm": 6.629062652587891, "learning_rate": 7.150107582662575e-06, "loss": 0.1811, "step": 355520 }, { "epoch": 2.1133441517912868, "grad_norm": 3.2114579677581787, "learning_rate": 7.149920253051097e-06, "loss": 0.1378, "step": 355530 }, { "epoch": 2.113403593867955, "grad_norm": 5.250069618225098, "learning_rate": 7.149732919737198e-06, "loss": 0.1391, "step": 355540 }, { "epoch": 2.1134630359446236, "grad_norm": 4.6051530838012695, "learning_rate": 7.149545582721203e-06, "loss": 0.1921, "step": 355550 }, { "epoch": 2.113522478021292, "grad_norm": 3.4565231800079346, "learning_rate": 7.149358242003437e-06, "loss": 0.1573, "step": 355560 }, { "epoch": 2.1135819200979604, "grad_norm": 4.4938435554504395, "learning_rate": 7.149170897584218e-06, "loss": 0.1631, "step": 355570 }, { "epoch": 2.113641362174629, "grad_norm": 5.124876976013184, "learning_rate": 7.148983549463869e-06, "loss": 0.1448, "step": 355580 }, { "epoch": 2.1137008042512972, "grad_norm": 5.242460250854492, "learning_rate": 7.148796197642716e-06, "loss": 0.1502, "step": 355590 }, { "epoch": 2.1137602463279657, "grad_norm": 5.0417938232421875, "learning_rate": 7.1486088421210784e-06, "loss": 0.1685, "step": 355600 }, { "epoch": 2.113819688404634, "grad_norm": 3.6340034008026123, "learning_rate": 7.1484214828992795e-06, "loss": 0.1458, "step": 355610 }, { "epoch": 2.1138791304813025, "grad_norm": 4.954206466674805, "learning_rate": 7.148234119977643e-06, "loss": 0.1634, "step": 355620 }, { "epoch": 2.113938572557971, "grad_norm": 4.170766353607178, "learning_rate": 7.148046753356492e-06, "loss": 0.1508, "step": 355630 }, { "epoch": 2.1139980146346393, "grad_norm": 4.247038841247559, "learning_rate": 7.147859383036147e-06, "loss": 0.1588, "step": 355640 }, { "epoch": 2.1140574567113077, "grad_norm": 5.327469348907471, "learning_rate": 7.14767200901693e-06, "loss": 0.1657, "step": 355650 }, { "epoch": 2.114116898787976, "grad_norm": 4.566788673400879, "learning_rate": 7.147484631299168e-06, "loss": 0.1616, "step": 355660 }, { "epoch": 2.1141763408646446, "grad_norm": 5.567615032196045, "learning_rate": 7.1472972498831824e-06, "loss": 0.1555, "step": 355670 }, { "epoch": 2.114235782941313, "grad_norm": 4.33173131942749, "learning_rate": 7.147109864769293e-06, "loss": 0.1539, "step": 355680 }, { "epoch": 2.1142952250179814, "grad_norm": 2.9794228076934814, "learning_rate": 7.1469224759578245e-06, "loss": 0.139, "step": 355690 }, { "epoch": 2.11435466709465, "grad_norm": 4.765918254852295, "learning_rate": 7.1467350834490986e-06, "loss": 0.1465, "step": 355700 }, { "epoch": 2.1144141091713182, "grad_norm": 3.7904789447784424, "learning_rate": 7.146547687243441e-06, "loss": 0.1656, "step": 355710 }, { "epoch": 2.114473551247986, "grad_norm": 3.781580924987793, "learning_rate": 7.14636028734117e-06, "loss": 0.1702, "step": 355720 }, { "epoch": 2.1145329933246546, "grad_norm": 4.235805034637451, "learning_rate": 7.146172883742611e-06, "loss": 0.1719, "step": 355730 }, { "epoch": 2.114592435401323, "grad_norm": 3.5895841121673584, "learning_rate": 7.1459854764480865e-06, "loss": 0.1432, "step": 355740 }, { "epoch": 2.1146518774779914, "grad_norm": 5.077361106872559, "learning_rate": 7.145798065457918e-06, "loss": 0.1637, "step": 355750 }, { "epoch": 2.11471131955466, "grad_norm": 5.316259384155273, "learning_rate": 7.14561065077243e-06, "loss": 0.152, "step": 355760 }, { "epoch": 2.1147707616313283, "grad_norm": 4.2300333976745605, "learning_rate": 7.145423232391945e-06, "loss": 0.1398, "step": 355770 }, { "epoch": 2.1148302037079967, "grad_norm": 6.508422374725342, "learning_rate": 7.145235810316784e-06, "loss": 0.1459, "step": 355780 }, { "epoch": 2.114889645784665, "grad_norm": 4.067439079284668, "learning_rate": 7.145048384547272e-06, "loss": 0.1527, "step": 355790 }, { "epoch": 2.1149490878613335, "grad_norm": 3.7808773517608643, "learning_rate": 7.14486095508373e-06, "loss": 0.1586, "step": 355800 }, { "epoch": 2.115008529938002, "grad_norm": 3.806494951248169, "learning_rate": 7.144673521926482e-06, "loss": 0.1565, "step": 355810 }, { "epoch": 2.1150679720146703, "grad_norm": 5.2164106369018555, "learning_rate": 7.14448608507585e-06, "loss": 0.1586, "step": 355820 }, { "epoch": 2.1151274140913388, "grad_norm": 4.739013195037842, "learning_rate": 7.144298644532158e-06, "loss": 0.1499, "step": 355830 }, { "epoch": 2.115186856168007, "grad_norm": 4.591109275817871, "learning_rate": 7.144111200295727e-06, "loss": 0.1668, "step": 355840 }, { "epoch": 2.1152462982446756, "grad_norm": 4.67637300491333, "learning_rate": 7.1439237523668806e-06, "loss": 0.1527, "step": 355850 }, { "epoch": 2.115305740321344, "grad_norm": 2.932375192642212, "learning_rate": 7.143736300745943e-06, "loss": 0.1346, "step": 355860 }, { "epoch": 2.1153651823980124, "grad_norm": 3.3517978191375732, "learning_rate": 7.143548845433232e-06, "loss": 0.1322, "step": 355870 }, { "epoch": 2.115424624474681, "grad_norm": 4.8373870849609375, "learning_rate": 7.143361386429078e-06, "loss": 0.1524, "step": 355880 }, { "epoch": 2.1154840665513492, "grad_norm": 5.014832019805908, "learning_rate": 7.143173923733798e-06, "loss": 0.1501, "step": 355890 }, { "epoch": 2.1155435086280177, "grad_norm": 3.655304193496704, "learning_rate": 7.142986457347717e-06, "loss": 0.1536, "step": 355900 }, { "epoch": 2.1156029507046856, "grad_norm": 4.446031093597412, "learning_rate": 7.142798987271159e-06, "loss": 0.1527, "step": 355910 }, { "epoch": 2.115662392781354, "grad_norm": 3.6645524501800537, "learning_rate": 7.142611513504445e-06, "loss": 0.1471, "step": 355920 }, { "epoch": 2.1157218348580225, "grad_norm": 4.89234733581543, "learning_rate": 7.142424036047897e-06, "loss": 0.1476, "step": 355930 }, { "epoch": 2.115781276934691, "grad_norm": 5.161955833435059, "learning_rate": 7.1422365549018405e-06, "loss": 0.1533, "step": 355940 }, { "epoch": 2.1158407190113593, "grad_norm": 3.4793169498443604, "learning_rate": 7.142049070066597e-06, "loss": 0.1417, "step": 355950 }, { "epoch": 2.1159001610880277, "grad_norm": 3.5054092407226562, "learning_rate": 7.141861581542489e-06, "loss": 0.1645, "step": 355960 }, { "epoch": 2.115959603164696, "grad_norm": 4.690634727478027, "learning_rate": 7.14167408932984e-06, "loss": 0.1478, "step": 355970 }, { "epoch": 2.1160190452413645, "grad_norm": 3.5117688179016113, "learning_rate": 7.1414865934289715e-06, "loss": 0.1586, "step": 355980 }, { "epoch": 2.116078487318033, "grad_norm": 3.1845216751098633, "learning_rate": 7.141299093840208e-06, "loss": 0.1484, "step": 355990 }, { "epoch": 2.1161379293947014, "grad_norm": 3.974907875061035, "learning_rate": 7.141111590563872e-06, "loss": 0.142, "step": 356000 }, { "epoch": 2.1161973714713698, "grad_norm": 4.412253379821777, "learning_rate": 7.140924083600288e-06, "loss": 0.1463, "step": 356010 }, { "epoch": 2.116256813548038, "grad_norm": 3.9506940841674805, "learning_rate": 7.140736572949776e-06, "loss": 0.171, "step": 356020 }, { "epoch": 2.1163162556247066, "grad_norm": 8.338231086730957, "learning_rate": 7.14054905861266e-06, "loss": 0.1428, "step": 356030 }, { "epoch": 2.116375697701375, "grad_norm": 4.288943290710449, "learning_rate": 7.140361540589263e-06, "loss": 0.1671, "step": 356040 }, { "epoch": 2.1164351397780434, "grad_norm": 3.587801218032837, "learning_rate": 7.14017401887991e-06, "loss": 0.1442, "step": 356050 }, { "epoch": 2.116494581854712, "grad_norm": 3.462571382522583, "learning_rate": 7.13998649348492e-06, "loss": 0.1413, "step": 356060 }, { "epoch": 2.1165540239313803, "grad_norm": 3.480194091796875, "learning_rate": 7.139798964404618e-06, "loss": 0.1568, "step": 356070 }, { "epoch": 2.1166134660080487, "grad_norm": 3.407449722290039, "learning_rate": 7.1396114316393285e-06, "loss": 0.1589, "step": 356080 }, { "epoch": 2.1166729080847166, "grad_norm": 5.341091156005859, "learning_rate": 7.13942389518937e-06, "loss": 0.161, "step": 356090 }, { "epoch": 2.116732350161385, "grad_norm": 4.138540744781494, "learning_rate": 7.13923635505507e-06, "loss": 0.1529, "step": 356100 }, { "epoch": 2.1167917922380535, "grad_norm": 3.8554112911224365, "learning_rate": 7.13904881123675e-06, "loss": 0.1534, "step": 356110 }, { "epoch": 2.116851234314722, "grad_norm": 5.229959964752197, "learning_rate": 7.138861263734732e-06, "loss": 0.1469, "step": 356120 }, { "epoch": 2.1169106763913903, "grad_norm": 3.6302406787872314, "learning_rate": 7.13867371254934e-06, "loss": 0.1651, "step": 356130 }, { "epoch": 2.1169701184680587, "grad_norm": 4.689620494842529, "learning_rate": 7.138486157680898e-06, "loss": 0.1273, "step": 356140 }, { "epoch": 2.117029560544727, "grad_norm": 5.083188056945801, "learning_rate": 7.138298599129726e-06, "loss": 0.1515, "step": 356150 }, { "epoch": 2.1170890026213955, "grad_norm": 5.1420769691467285, "learning_rate": 7.138111036896148e-06, "loss": 0.1756, "step": 356160 }, { "epoch": 2.117148444698064, "grad_norm": 2.8283238410949707, "learning_rate": 7.137923470980489e-06, "loss": 0.1548, "step": 356170 }, { "epoch": 2.1172078867747324, "grad_norm": 3.6938326358795166, "learning_rate": 7.1377359013830715e-06, "loss": 0.1527, "step": 356180 }, { "epoch": 2.117267328851401, "grad_norm": 4.127030849456787, "learning_rate": 7.137548328104215e-06, "loss": 0.1645, "step": 356190 }, { "epoch": 2.117326770928069, "grad_norm": 4.942465782165527, "learning_rate": 7.137360751144246e-06, "loss": 0.1614, "step": 356200 }, { "epoch": 2.1173862130047376, "grad_norm": 3.7617902755737305, "learning_rate": 7.137173170503488e-06, "loss": 0.1371, "step": 356210 }, { "epoch": 2.117445655081406, "grad_norm": 4.245311737060547, "learning_rate": 7.136985586182263e-06, "loss": 0.1361, "step": 356220 }, { "epoch": 2.1175050971580744, "grad_norm": 5.111997604370117, "learning_rate": 7.136797998180893e-06, "loss": 0.1384, "step": 356230 }, { "epoch": 2.117564539234743, "grad_norm": 5.078673839569092, "learning_rate": 7.136610406499703e-06, "loss": 0.1564, "step": 356240 }, { "epoch": 2.1176239813114113, "grad_norm": 4.166738986968994, "learning_rate": 7.136422811139014e-06, "loss": 0.1612, "step": 356250 }, { "epoch": 2.1176834233880797, "grad_norm": 4.226655006408691, "learning_rate": 7.136235212099149e-06, "loss": 0.1496, "step": 356260 }, { "epoch": 2.1177428654647477, "grad_norm": 4.449716091156006, "learning_rate": 7.136047609380434e-06, "loss": 0.1609, "step": 356270 }, { "epoch": 2.117802307541416, "grad_norm": 3.4735279083251953, "learning_rate": 7.13586000298319e-06, "loss": 0.1602, "step": 356280 }, { "epoch": 2.1178617496180845, "grad_norm": 3.5965569019317627, "learning_rate": 7.135672392907739e-06, "loss": 0.1231, "step": 356290 }, { "epoch": 2.117921191694753, "grad_norm": 4.339950084686279, "learning_rate": 7.135484779154407e-06, "loss": 0.1586, "step": 356300 }, { "epoch": 2.1179806337714213, "grad_norm": 3.7575669288635254, "learning_rate": 7.135297161723513e-06, "loss": 0.1323, "step": 356310 }, { "epoch": 2.1180400758480897, "grad_norm": 3.7935616970062256, "learning_rate": 7.135109540615384e-06, "loss": 0.1735, "step": 356320 }, { "epoch": 2.118099517924758, "grad_norm": 4.792891025543213, "learning_rate": 7.1349219158303405e-06, "loss": 0.1653, "step": 356330 }, { "epoch": 2.1181589600014266, "grad_norm": 4.16963529586792, "learning_rate": 7.134734287368708e-06, "loss": 0.1645, "step": 356340 }, { "epoch": 2.118218402078095, "grad_norm": 5.550014019012451, "learning_rate": 7.134546655230808e-06, "loss": 0.1687, "step": 356350 }, { "epoch": 2.1182778441547634, "grad_norm": 4.338594913482666, "learning_rate": 7.134359019416964e-06, "loss": 0.1466, "step": 356360 }, { "epoch": 2.118337286231432, "grad_norm": 3.7060165405273438, "learning_rate": 7.134171379927499e-06, "loss": 0.1546, "step": 356370 }, { "epoch": 2.1183967283081, "grad_norm": 4.157616138458252, "learning_rate": 7.133983736762737e-06, "loss": 0.1554, "step": 356380 }, { "epoch": 2.1184561703847686, "grad_norm": 4.3601908683776855, "learning_rate": 7.133796089923e-06, "loss": 0.154, "step": 356390 }, { "epoch": 2.118515612461437, "grad_norm": 4.263072490692139, "learning_rate": 7.13360843940861e-06, "loss": 0.157, "step": 356400 }, { "epoch": 2.1185750545381055, "grad_norm": 3.8933560848236084, "learning_rate": 7.1334207852198945e-06, "loss": 0.1545, "step": 356410 }, { "epoch": 2.118634496614774, "grad_norm": 3.338330030441284, "learning_rate": 7.133233127357171e-06, "loss": 0.1656, "step": 356420 }, { "epoch": 2.1186939386914423, "grad_norm": 4.8715901374816895, "learning_rate": 7.133045465820767e-06, "loss": 0.1499, "step": 356430 }, { "epoch": 2.1187533807681107, "grad_norm": 4.756425380706787, "learning_rate": 7.132857800611004e-06, "loss": 0.1665, "step": 356440 }, { "epoch": 2.118812822844779, "grad_norm": 4.525217533111572, "learning_rate": 7.132670131728206e-06, "loss": 0.1644, "step": 356450 }, { "epoch": 2.118872264921447, "grad_norm": 3.6964612007141113, "learning_rate": 7.132482459172694e-06, "loss": 0.1606, "step": 356460 }, { "epoch": 2.1189317069981155, "grad_norm": 4.3030619621276855, "learning_rate": 7.132294782944794e-06, "loss": 0.1376, "step": 356470 }, { "epoch": 2.118991149074784, "grad_norm": 4.170287132263184, "learning_rate": 7.1321071030448274e-06, "loss": 0.1484, "step": 356480 }, { "epoch": 2.1190505911514523, "grad_norm": 4.776062965393066, "learning_rate": 7.1319194194731175e-06, "loss": 0.1582, "step": 356490 }, { "epoch": 2.1191100332281207, "grad_norm": 3.998727560043335, "learning_rate": 7.131731732229989e-06, "loss": 0.1603, "step": 356500 }, { "epoch": 2.119169475304789, "grad_norm": 4.021592140197754, "learning_rate": 7.131544041315766e-06, "loss": 0.1729, "step": 356510 }, { "epoch": 2.1192289173814576, "grad_norm": 3.3162810802459717, "learning_rate": 7.131356346730766e-06, "loss": 0.1601, "step": 356520 }, { "epoch": 2.119288359458126, "grad_norm": 5.069407939910889, "learning_rate": 7.131168648475317e-06, "loss": 0.1422, "step": 356530 }, { "epoch": 2.1193478015347944, "grad_norm": 5.4807448387146, "learning_rate": 7.130980946549742e-06, "loss": 0.1809, "step": 356540 }, { "epoch": 2.119407243611463, "grad_norm": 4.046920299530029, "learning_rate": 7.1307932409543635e-06, "loss": 0.1749, "step": 356550 }, { "epoch": 2.1194666856881312, "grad_norm": 4.150910377502441, "learning_rate": 7.130605531689505e-06, "loss": 0.1526, "step": 356560 }, { "epoch": 2.1195261277647997, "grad_norm": 4.287456035614014, "learning_rate": 7.1304178187554894e-06, "loss": 0.1489, "step": 356570 }, { "epoch": 2.119585569841468, "grad_norm": 4.101456642150879, "learning_rate": 7.13023010215264e-06, "loss": 0.1404, "step": 356580 }, { "epoch": 2.1196450119181365, "grad_norm": 4.606624603271484, "learning_rate": 7.13004238188128e-06, "loss": 0.1695, "step": 356590 }, { "epoch": 2.119704453994805, "grad_norm": 3.6285648345947266, "learning_rate": 7.129854657941734e-06, "loss": 0.1335, "step": 356600 }, { "epoch": 2.1197638960714733, "grad_norm": 4.830138683319092, "learning_rate": 7.129666930334323e-06, "loss": 0.1432, "step": 356610 }, { "epoch": 2.1198233381481417, "grad_norm": 2.9840753078460693, "learning_rate": 7.129479199059372e-06, "loss": 0.1383, "step": 356620 }, { "epoch": 2.11988278022481, "grad_norm": 3.933070421218872, "learning_rate": 7.129291464117204e-06, "loss": 0.1548, "step": 356630 }, { "epoch": 2.1199422223014786, "grad_norm": 4.442899703979492, "learning_rate": 7.129103725508141e-06, "loss": 0.1537, "step": 356640 }, { "epoch": 2.1200016643781465, "grad_norm": 5.494942665100098, "learning_rate": 7.128915983232507e-06, "loss": 0.1584, "step": 356650 }, { "epoch": 2.120061106454815, "grad_norm": 3.8884096145629883, "learning_rate": 7.128728237290626e-06, "loss": 0.1588, "step": 356660 }, { "epoch": 2.1201205485314834, "grad_norm": 3.9750118255615234, "learning_rate": 7.1285404876828225e-06, "loss": 0.1468, "step": 356670 }, { "epoch": 2.1201799906081518, "grad_norm": 5.883869171142578, "learning_rate": 7.128352734409416e-06, "loss": 0.1581, "step": 356680 }, { "epoch": 2.12023943268482, "grad_norm": 5.124013900756836, "learning_rate": 7.128164977470735e-06, "loss": 0.1606, "step": 356690 }, { "epoch": 2.1202988747614886, "grad_norm": 4.3125996589660645, "learning_rate": 7.127977216867098e-06, "loss": 0.1708, "step": 356700 }, { "epoch": 2.120358316838157, "grad_norm": 4.631710052490234, "learning_rate": 7.12778945259883e-06, "loss": 0.1487, "step": 356710 }, { "epoch": 2.1204177589148254, "grad_norm": 2.8599677085876465, "learning_rate": 7.1276016846662566e-06, "loss": 0.152, "step": 356720 }, { "epoch": 2.120477200991494, "grad_norm": 5.047997951507568, "learning_rate": 7.127413913069699e-06, "loss": 0.166, "step": 356730 }, { "epoch": 2.1205366430681623, "grad_norm": 4.644470691680908, "learning_rate": 7.127226137809478e-06, "loss": 0.159, "step": 356740 }, { "epoch": 2.1205960851448307, "grad_norm": 3.6420607566833496, "learning_rate": 7.127038358885921e-06, "loss": 0.1447, "step": 356750 }, { "epoch": 2.120655527221499, "grad_norm": 4.9446120262146, "learning_rate": 7.126850576299351e-06, "loss": 0.1761, "step": 356760 }, { "epoch": 2.1207149692981675, "grad_norm": 4.6192626953125, "learning_rate": 7.126662790050092e-06, "loss": 0.1603, "step": 356770 }, { "epoch": 2.120774411374836, "grad_norm": 4.398612022399902, "learning_rate": 7.126475000138463e-06, "loss": 0.1482, "step": 356780 }, { "epoch": 2.1208338534515043, "grad_norm": 5.397063732147217, "learning_rate": 7.126287206564792e-06, "loss": 0.1642, "step": 356790 }, { "epoch": 2.1208932955281727, "grad_norm": 4.4625725746154785, "learning_rate": 7.1260994093294e-06, "loss": 0.14, "step": 356800 }, { "epoch": 2.120952737604841, "grad_norm": 3.6331562995910645, "learning_rate": 7.1259116084326115e-06, "loss": 0.1568, "step": 356810 }, { "epoch": 2.121012179681509, "grad_norm": 3.852724313735962, "learning_rate": 7.125723803874749e-06, "loss": 0.1293, "step": 356820 }, { "epoch": 2.1210716217581775, "grad_norm": 3.4146666526794434, "learning_rate": 7.125535995656138e-06, "loss": 0.1691, "step": 356830 }, { "epoch": 2.121131063834846, "grad_norm": 3.951626777648926, "learning_rate": 7.125348183777099e-06, "loss": 0.1596, "step": 356840 }, { "epoch": 2.1211905059115144, "grad_norm": 4.315340042114258, "learning_rate": 7.125160368237958e-06, "loss": 0.1369, "step": 356850 }, { "epoch": 2.121249947988183, "grad_norm": 4.680472373962402, "learning_rate": 7.124972549039035e-06, "loss": 0.157, "step": 356860 }, { "epoch": 2.121309390064851, "grad_norm": 3.556912660598755, "learning_rate": 7.124784726180658e-06, "loss": 0.1482, "step": 356870 }, { "epoch": 2.1213688321415196, "grad_norm": 3.911010980606079, "learning_rate": 7.1245968996631466e-06, "loss": 0.1543, "step": 356880 }, { "epoch": 2.121428274218188, "grad_norm": 4.497723579406738, "learning_rate": 7.124409069486826e-06, "loss": 0.1559, "step": 356890 }, { "epoch": 2.1214877162948564, "grad_norm": 4.8271355628967285, "learning_rate": 7.124221235652021e-06, "loss": 0.1561, "step": 356900 }, { "epoch": 2.121547158371525, "grad_norm": 3.9173340797424316, "learning_rate": 7.124033398159053e-06, "loss": 0.1745, "step": 356910 }, { "epoch": 2.1216066004481933, "grad_norm": 3.382695198059082, "learning_rate": 7.123845557008245e-06, "loss": 0.1521, "step": 356920 }, { "epoch": 2.1216660425248617, "grad_norm": 4.543457508087158, "learning_rate": 7.123657712199923e-06, "loss": 0.1503, "step": 356930 }, { "epoch": 2.12172548460153, "grad_norm": 3.868229627609253, "learning_rate": 7.123469863734408e-06, "loss": 0.1502, "step": 356940 }, { "epoch": 2.1217849266781985, "grad_norm": 4.168074607849121, "learning_rate": 7.123282011612025e-06, "loss": 0.1575, "step": 356950 }, { "epoch": 2.121844368754867, "grad_norm": 4.384625434875488, "learning_rate": 7.123094155833096e-06, "loss": 0.1588, "step": 356960 }, { "epoch": 2.1219038108315353, "grad_norm": 4.255149841308594, "learning_rate": 7.122906296397947e-06, "loss": 0.1368, "step": 356970 }, { "epoch": 2.1219632529082038, "grad_norm": 4.354841709136963, "learning_rate": 7.1227184333068985e-06, "loss": 0.1413, "step": 356980 }, { "epoch": 2.122022694984872, "grad_norm": 3.9166533946990967, "learning_rate": 7.122530566560278e-06, "loss": 0.148, "step": 356990 }, { "epoch": 2.1220821370615406, "grad_norm": 5.09316349029541, "learning_rate": 7.122342696158406e-06, "loss": 0.156, "step": 357000 }, { "epoch": 2.1221415791382086, "grad_norm": 5.039509296417236, "learning_rate": 7.122154822101603e-06, "loss": 0.1565, "step": 357010 }, { "epoch": 2.122201021214877, "grad_norm": 4.78888463973999, "learning_rate": 7.1219669443902e-06, "loss": 0.1675, "step": 357020 }, { "epoch": 2.1222604632915454, "grad_norm": 5.36821174621582, "learning_rate": 7.121779063024517e-06, "loss": 0.1697, "step": 357030 }, { "epoch": 2.122319905368214, "grad_norm": 5.156645774841309, "learning_rate": 7.121591178004875e-06, "loss": 0.1743, "step": 357040 }, { "epoch": 2.122379347444882, "grad_norm": 5.291646480560303, "learning_rate": 7.121403289331601e-06, "loss": 0.1749, "step": 357050 }, { "epoch": 2.1224387895215506, "grad_norm": 4.215636253356934, "learning_rate": 7.121215397005018e-06, "loss": 0.1643, "step": 357060 }, { "epoch": 2.122498231598219, "grad_norm": 5.603202819824219, "learning_rate": 7.121027501025447e-06, "loss": 0.169, "step": 357070 }, { "epoch": 2.1225576736748875, "grad_norm": 4.4039225578308105, "learning_rate": 7.120839601393214e-06, "loss": 0.1931, "step": 357080 }, { "epoch": 2.122617115751556, "grad_norm": 4.0839128494262695, "learning_rate": 7.120651698108644e-06, "loss": 0.1344, "step": 357090 }, { "epoch": 2.1226765578282243, "grad_norm": 3.9107842445373535, "learning_rate": 7.120463791172057e-06, "loss": 0.1475, "step": 357100 }, { "epoch": 2.1227359999048927, "grad_norm": 4.465473651885986, "learning_rate": 7.120275880583779e-06, "loss": 0.1392, "step": 357110 }, { "epoch": 2.122795441981561, "grad_norm": 4.064004421234131, "learning_rate": 7.120087966344134e-06, "loss": 0.1403, "step": 357120 }, { "epoch": 2.1228548840582295, "grad_norm": 4.245241641998291, "learning_rate": 7.119900048453443e-06, "loss": 0.1544, "step": 357130 }, { "epoch": 2.122914326134898, "grad_norm": 4.348758220672607, "learning_rate": 7.119712126912032e-06, "loss": 0.1492, "step": 357140 }, { "epoch": 2.1229737682115664, "grad_norm": 4.076193809509277, "learning_rate": 7.119524201720224e-06, "loss": 0.1397, "step": 357150 }, { "epoch": 2.1230332102882348, "grad_norm": 3.961668014526367, "learning_rate": 7.119336272878342e-06, "loss": 0.1705, "step": 357160 }, { "epoch": 2.123092652364903, "grad_norm": 3.183487892150879, "learning_rate": 7.119148340386709e-06, "loss": 0.1564, "step": 357170 }, { "epoch": 2.1231520944415716, "grad_norm": 4.958502769470215, "learning_rate": 7.118960404245651e-06, "loss": 0.1581, "step": 357180 }, { "epoch": 2.12321153651824, "grad_norm": 3.5941002368927, "learning_rate": 7.11877246445549e-06, "loss": 0.1603, "step": 357190 }, { "epoch": 2.123270978594908, "grad_norm": 4.217496871948242, "learning_rate": 7.118584521016549e-06, "loss": 0.1405, "step": 357200 }, { "epoch": 2.1233304206715764, "grad_norm": 5.303696632385254, "learning_rate": 7.118396573929154e-06, "loss": 0.1476, "step": 357210 }, { "epoch": 2.123389862748245, "grad_norm": 4.914854526519775, "learning_rate": 7.118208623193628e-06, "loss": 0.1525, "step": 357220 }, { "epoch": 2.1234493048249132, "grad_norm": 4.206593036651611, "learning_rate": 7.118020668810292e-06, "loss": 0.1648, "step": 357230 }, { "epoch": 2.1235087469015816, "grad_norm": 4.146196365356445, "learning_rate": 7.117832710779473e-06, "loss": 0.1435, "step": 357240 }, { "epoch": 2.12356818897825, "grad_norm": 3.7230658531188965, "learning_rate": 7.117644749101495e-06, "loss": 0.1303, "step": 357250 }, { "epoch": 2.1236276310549185, "grad_norm": 4.796083927154541, "learning_rate": 7.117456783776677e-06, "loss": 0.1541, "step": 357260 }, { "epoch": 2.123687073131587, "grad_norm": 4.612697601318359, "learning_rate": 7.117268814805347e-06, "loss": 0.1466, "step": 357270 }, { "epoch": 2.1237465152082553, "grad_norm": 5.358826160430908, "learning_rate": 7.117080842187828e-06, "loss": 0.1471, "step": 357280 }, { "epoch": 2.1238059572849237, "grad_norm": 4.953975200653076, "learning_rate": 7.116892865924442e-06, "loss": 0.1793, "step": 357290 }, { "epoch": 2.123865399361592, "grad_norm": 4.161590099334717, "learning_rate": 7.116704886015514e-06, "loss": 0.158, "step": 357300 }, { "epoch": 2.1239248414382605, "grad_norm": 5.173549175262451, "learning_rate": 7.116516902461368e-06, "loss": 0.1439, "step": 357310 }, { "epoch": 2.123984283514929, "grad_norm": 4.876543045043945, "learning_rate": 7.1163289152623286e-06, "loss": 0.1548, "step": 357320 }, { "epoch": 2.1240437255915974, "grad_norm": 3.8506386280059814, "learning_rate": 7.1161409244187165e-06, "loss": 0.1709, "step": 357330 }, { "epoch": 2.124103167668266, "grad_norm": 4.6187520027160645, "learning_rate": 7.115952929930859e-06, "loss": 0.1482, "step": 357340 }, { "epoch": 2.124162609744934, "grad_norm": 4.949190139770508, "learning_rate": 7.115764931799076e-06, "loss": 0.1416, "step": 357350 }, { "epoch": 2.1242220518216026, "grad_norm": 5.177211284637451, "learning_rate": 7.115576930023694e-06, "loss": 0.1517, "step": 357360 }, { "epoch": 2.124281493898271, "grad_norm": 7.383825302124023, "learning_rate": 7.115388924605038e-06, "loss": 0.146, "step": 357370 }, { "epoch": 2.1243409359749394, "grad_norm": 3.292415142059326, "learning_rate": 7.115200915543428e-06, "loss": 0.1405, "step": 357380 }, { "epoch": 2.1244003780516074, "grad_norm": 4.513245582580566, "learning_rate": 7.115012902839189e-06, "loss": 0.1549, "step": 357390 }, { "epoch": 2.124459820128276, "grad_norm": 5.60896635055542, "learning_rate": 7.114824886492647e-06, "loss": 0.1549, "step": 357400 }, { "epoch": 2.1245192622049442, "grad_norm": 4.1714606285095215, "learning_rate": 7.114636866504123e-06, "loss": 0.1465, "step": 357410 }, { "epoch": 2.1245787042816127, "grad_norm": 4.489899158477783, "learning_rate": 7.114448842873943e-06, "loss": 0.1533, "step": 357420 }, { "epoch": 2.124638146358281, "grad_norm": 4.930269718170166, "learning_rate": 7.11426081560243e-06, "loss": 0.1567, "step": 357430 }, { "epoch": 2.1246975884349495, "grad_norm": 5.477703094482422, "learning_rate": 7.114072784689907e-06, "loss": 0.1735, "step": 357440 }, { "epoch": 2.124757030511618, "grad_norm": 3.888228178024292, "learning_rate": 7.113884750136698e-06, "loss": 0.14, "step": 357450 }, { "epoch": 2.1248164725882863, "grad_norm": 4.89162540435791, "learning_rate": 7.113696711943128e-06, "loss": 0.1838, "step": 357460 }, { "epoch": 2.1248759146649547, "grad_norm": 6.249542713165283, "learning_rate": 7.113508670109519e-06, "loss": 0.17, "step": 357470 }, { "epoch": 2.124935356741623, "grad_norm": 3.7682290077209473, "learning_rate": 7.1133206246361976e-06, "loss": 0.1554, "step": 357480 }, { "epoch": 2.1249947988182916, "grad_norm": 4.927137851715088, "learning_rate": 7.113132575523485e-06, "loss": 0.1665, "step": 357490 }, { "epoch": 2.12505424089496, "grad_norm": 4.220339775085449, "learning_rate": 7.112944522771705e-06, "loss": 0.1593, "step": 357500 }, { "epoch": 2.1251136829716284, "grad_norm": 5.271183013916016, "learning_rate": 7.1127564663811845e-06, "loss": 0.1493, "step": 357510 }, { "epoch": 2.125173125048297, "grad_norm": 5.561431407928467, "learning_rate": 7.112568406352242e-06, "loss": 0.155, "step": 357520 }, { "epoch": 2.125232567124965, "grad_norm": 4.670550346374512, "learning_rate": 7.112380342685208e-06, "loss": 0.1722, "step": 357530 }, { "epoch": 2.1252920092016336, "grad_norm": 3.743903398513794, "learning_rate": 7.112192275380402e-06, "loss": 0.1616, "step": 357540 }, { "epoch": 2.125351451278302, "grad_norm": 3.3293514251708984, "learning_rate": 7.112004204438148e-06, "loss": 0.1315, "step": 357550 }, { "epoch": 2.12541089335497, "grad_norm": 2.7702345848083496, "learning_rate": 7.111816129858772e-06, "loss": 0.1568, "step": 357560 }, { "epoch": 2.1254703354316384, "grad_norm": 3.955329418182373, "learning_rate": 7.1116280516425965e-06, "loss": 0.1578, "step": 357570 }, { "epoch": 2.125529777508307, "grad_norm": 4.632959365844727, "learning_rate": 7.111439969789945e-06, "loss": 0.1662, "step": 357580 }, { "epoch": 2.1255892195849753, "grad_norm": 4.959566116333008, "learning_rate": 7.111251884301141e-06, "loss": 0.1666, "step": 357590 }, { "epoch": 2.1256486616616437, "grad_norm": 5.039499759674072, "learning_rate": 7.111063795176512e-06, "loss": 0.1573, "step": 357600 }, { "epoch": 2.125708103738312, "grad_norm": 4.235922336578369, "learning_rate": 7.110875702416377e-06, "loss": 0.1487, "step": 357610 }, { "epoch": 2.1257675458149805, "grad_norm": 4.002880573272705, "learning_rate": 7.110687606021063e-06, "loss": 0.1486, "step": 357620 }, { "epoch": 2.125826987891649, "grad_norm": 4.647790908813477, "learning_rate": 7.110499505990891e-06, "loss": 0.1493, "step": 357630 }, { "epoch": 2.1258864299683173, "grad_norm": 4.526237487792969, "learning_rate": 7.11031140232619e-06, "loss": 0.1476, "step": 357640 }, { "epoch": 2.1259458720449858, "grad_norm": 4.668416500091553, "learning_rate": 7.110123295027281e-06, "loss": 0.1655, "step": 357650 }, { "epoch": 2.126005314121654, "grad_norm": 4.317989826202393, "learning_rate": 7.109935184094485e-06, "loss": 0.1602, "step": 357660 }, { "epoch": 2.1260647561983226, "grad_norm": 4.182983875274658, "learning_rate": 7.109747069528131e-06, "loss": 0.1416, "step": 357670 }, { "epoch": 2.126124198274991, "grad_norm": 4.298084259033203, "learning_rate": 7.1095589513285416e-06, "loss": 0.1799, "step": 357680 }, { "epoch": 2.1261836403516594, "grad_norm": 4.669877529144287, "learning_rate": 7.109370829496039e-06, "loss": 0.1361, "step": 357690 }, { "epoch": 2.126243082428328, "grad_norm": 5.799745559692383, "learning_rate": 7.109182704030947e-06, "loss": 0.1581, "step": 357700 }, { "epoch": 2.1263025245049962, "grad_norm": 3.773671865463257, "learning_rate": 7.108994574933592e-06, "loss": 0.1424, "step": 357710 }, { "epoch": 2.1263619665816647, "grad_norm": 4.193071365356445, "learning_rate": 7.108806442204297e-06, "loss": 0.1384, "step": 357720 }, { "epoch": 2.126421408658333, "grad_norm": 4.868536949157715, "learning_rate": 7.108618305843385e-06, "loss": 0.1721, "step": 357730 }, { "epoch": 2.1264808507350015, "grad_norm": 3.6208138465881348, "learning_rate": 7.1084301658511805e-06, "loss": 0.1398, "step": 357740 }, { "epoch": 2.1265402928116695, "grad_norm": 4.754083156585693, "learning_rate": 7.108242022228007e-06, "loss": 0.1623, "step": 357750 }, { "epoch": 2.126599734888338, "grad_norm": 6.502513408660889, "learning_rate": 7.10805387497419e-06, "loss": 0.1673, "step": 357760 }, { "epoch": 2.1266591769650063, "grad_norm": 4.623015403747559, "learning_rate": 7.107865724090053e-06, "loss": 0.1565, "step": 357770 }, { "epoch": 2.1267186190416747, "grad_norm": 5.389311790466309, "learning_rate": 7.1076775695759206e-06, "loss": 0.152, "step": 357780 }, { "epoch": 2.126778061118343, "grad_norm": 4.202785491943359, "learning_rate": 7.107489411432114e-06, "loss": 0.13, "step": 357790 }, { "epoch": 2.1268375031950115, "grad_norm": 3.7274281978607178, "learning_rate": 7.1073012496589615e-06, "loss": 0.1688, "step": 357800 }, { "epoch": 2.12689694527168, "grad_norm": 5.128367900848389, "learning_rate": 7.107113084256783e-06, "loss": 0.1519, "step": 357810 }, { "epoch": 2.1269563873483484, "grad_norm": 3.4607553482055664, "learning_rate": 7.106924915225903e-06, "loss": 0.1557, "step": 357820 }, { "epoch": 2.1270158294250168, "grad_norm": 2.8978424072265625, "learning_rate": 7.10673674256665e-06, "loss": 0.1566, "step": 357830 }, { "epoch": 2.127075271501685, "grad_norm": 3.4250004291534424, "learning_rate": 7.1065485662793445e-06, "loss": 0.1662, "step": 357840 }, { "epoch": 2.1271347135783536, "grad_norm": 3.6035406589508057, "learning_rate": 7.106360386364308e-06, "loss": 0.1617, "step": 357850 }, { "epoch": 2.127194155655022, "grad_norm": 4.071681499481201, "learning_rate": 7.1061722028218706e-06, "loss": 0.1487, "step": 357860 }, { "epoch": 2.1272535977316904, "grad_norm": 4.250636100769043, "learning_rate": 7.105984015652352e-06, "loss": 0.1354, "step": 357870 }, { "epoch": 2.127313039808359, "grad_norm": 3.4433257579803467, "learning_rate": 7.1057958248560775e-06, "loss": 0.1566, "step": 357880 }, { "epoch": 2.1273724818850273, "grad_norm": 5.770240783691406, "learning_rate": 7.1056076304333735e-06, "loss": 0.1496, "step": 357890 }, { "epoch": 2.1274319239616957, "grad_norm": 5.591665744781494, "learning_rate": 7.1054194323845605e-06, "loss": 0.162, "step": 357900 }, { "epoch": 2.127491366038364, "grad_norm": 4.430544376373291, "learning_rate": 7.105231230709964e-06, "loss": 0.1434, "step": 357910 }, { "epoch": 2.1275508081150325, "grad_norm": 4.430169105529785, "learning_rate": 7.1050430254099075e-06, "loss": 0.1607, "step": 357920 }, { "epoch": 2.127610250191701, "grad_norm": 5.069686412811279, "learning_rate": 7.104854816484716e-06, "loss": 0.1493, "step": 357930 }, { "epoch": 2.127669692268369, "grad_norm": 5.599210262298584, "learning_rate": 7.1046666039347136e-06, "loss": 0.1526, "step": 357940 }, { "epoch": 2.1277291343450373, "grad_norm": 3.8055472373962402, "learning_rate": 7.104478387760224e-06, "loss": 0.1652, "step": 357950 }, { "epoch": 2.1277885764217057, "grad_norm": 3.583523750305176, "learning_rate": 7.104290167961572e-06, "loss": 0.1386, "step": 357960 }, { "epoch": 2.127848018498374, "grad_norm": 4.262732028961182, "learning_rate": 7.104101944539081e-06, "loss": 0.1555, "step": 357970 }, { "epoch": 2.1279074605750425, "grad_norm": 4.196108818054199, "learning_rate": 7.103913717493075e-06, "loss": 0.1496, "step": 357980 }, { "epoch": 2.127966902651711, "grad_norm": 4.061789035797119, "learning_rate": 7.103725486823879e-06, "loss": 0.1535, "step": 357990 }, { "epoch": 2.1280263447283794, "grad_norm": 3.643559455871582, "learning_rate": 7.103537252531817e-06, "loss": 0.1487, "step": 358000 }, { "epoch": 2.128085786805048, "grad_norm": 3.6521055698394775, "learning_rate": 7.103349014617211e-06, "loss": 0.1424, "step": 358010 }, { "epoch": 2.128145228881716, "grad_norm": 3.4901180267333984, "learning_rate": 7.10316077308039e-06, "loss": 0.1575, "step": 358020 }, { "epoch": 2.1282046709583846, "grad_norm": 3.9364850521087646, "learning_rate": 7.102972527921675e-06, "loss": 0.1565, "step": 358030 }, { "epoch": 2.128264113035053, "grad_norm": 4.1219000816345215, "learning_rate": 7.102784279141387e-06, "loss": 0.1297, "step": 358040 }, { "epoch": 2.1283235551117214, "grad_norm": 4.190454483032227, "learning_rate": 7.102596026739856e-06, "loss": 0.1613, "step": 358050 }, { "epoch": 2.12838299718839, "grad_norm": 3.6171438694000244, "learning_rate": 7.102407770717405e-06, "loss": 0.1494, "step": 358060 }, { "epoch": 2.1284424392650583, "grad_norm": 2.9075863361358643, "learning_rate": 7.102219511074354e-06, "loss": 0.1425, "step": 358070 }, { "epoch": 2.1285018813417267, "grad_norm": 3.2757136821746826, "learning_rate": 7.102031247811031e-06, "loss": 0.1417, "step": 358080 }, { "epoch": 2.128561323418395, "grad_norm": 4.442399024963379, "learning_rate": 7.10184298092776e-06, "loss": 0.1533, "step": 358090 }, { "epoch": 2.1286207654950635, "grad_norm": 3.2784225940704346, "learning_rate": 7.101654710424865e-06, "loss": 0.1425, "step": 358100 }, { "epoch": 2.128680207571732, "grad_norm": 3.525921106338501, "learning_rate": 7.101466436302669e-06, "loss": 0.1437, "step": 358110 }, { "epoch": 2.1287396496484003, "grad_norm": 4.5668044090271, "learning_rate": 7.101278158561498e-06, "loss": 0.1352, "step": 358120 }, { "epoch": 2.1287990917250683, "grad_norm": 4.187731742858887, "learning_rate": 7.101089877201674e-06, "loss": 0.1477, "step": 358130 }, { "epoch": 2.1288585338017367, "grad_norm": 4.030807018280029, "learning_rate": 7.1009015922235234e-06, "loss": 0.1571, "step": 358140 }, { "epoch": 2.128917975878405, "grad_norm": 4.786303520202637, "learning_rate": 7.10071330362737e-06, "loss": 0.1868, "step": 358150 }, { "epoch": 2.1289774179550736, "grad_norm": 4.843287467956543, "learning_rate": 7.100525011413537e-06, "loss": 0.137, "step": 358160 }, { "epoch": 2.129036860031742, "grad_norm": 4.8490309715271, "learning_rate": 7.100336715582349e-06, "loss": 0.1664, "step": 358170 }, { "epoch": 2.1290963021084104, "grad_norm": 3.7527763843536377, "learning_rate": 7.1001484161341305e-06, "loss": 0.1648, "step": 358180 }, { "epoch": 2.129155744185079, "grad_norm": 6.055775165557861, "learning_rate": 7.099960113069206e-06, "loss": 0.1603, "step": 358190 }, { "epoch": 2.129215186261747, "grad_norm": 3.945596933364868, "learning_rate": 7.099771806387901e-06, "loss": 0.1434, "step": 358200 }, { "epoch": 2.1292746283384156, "grad_norm": 5.184523582458496, "learning_rate": 7.099583496090536e-06, "loss": 0.1428, "step": 358210 }, { "epoch": 2.129334070415084, "grad_norm": 5.249960422515869, "learning_rate": 7.09939518217744e-06, "loss": 0.1591, "step": 358220 }, { "epoch": 2.1293935124917525, "grad_norm": 4.921031951904297, "learning_rate": 7.099206864648934e-06, "loss": 0.1692, "step": 358230 }, { "epoch": 2.129452954568421, "grad_norm": 4.713818073272705, "learning_rate": 7.0990185435053426e-06, "loss": 0.1561, "step": 358240 }, { "epoch": 2.1295123966450893, "grad_norm": 3.7179603576660156, "learning_rate": 7.098830218746992e-06, "loss": 0.132, "step": 358250 }, { "epoch": 2.1295718387217577, "grad_norm": 3.630810499191284, "learning_rate": 7.098641890374206e-06, "loss": 0.1446, "step": 358260 }, { "epoch": 2.129631280798426, "grad_norm": 4.56828498840332, "learning_rate": 7.098453558387306e-06, "loss": 0.1473, "step": 358270 }, { "epoch": 2.1296907228750945, "grad_norm": 3.868623733520508, "learning_rate": 7.09826522278662e-06, "loss": 0.1592, "step": 358280 }, { "epoch": 2.129750164951763, "grad_norm": 3.4373509883880615, "learning_rate": 7.09807688357247e-06, "loss": 0.1662, "step": 358290 }, { "epoch": 2.129809607028431, "grad_norm": 5.405612468719482, "learning_rate": 7.097888540745183e-06, "loss": 0.1555, "step": 358300 }, { "epoch": 2.1298690491050993, "grad_norm": 4.9774394035339355, "learning_rate": 7.0977001943050796e-06, "loss": 0.1398, "step": 358310 }, { "epoch": 2.1299284911817677, "grad_norm": 3.9903416633605957, "learning_rate": 7.097511844252487e-06, "loss": 0.1591, "step": 358320 }, { "epoch": 2.129987933258436, "grad_norm": 5.218074798583984, "learning_rate": 7.09732349058773e-06, "loss": 0.1408, "step": 358330 }, { "epoch": 2.1300473753351046, "grad_norm": 4.5381999015808105, "learning_rate": 7.097135133311129e-06, "loss": 0.1596, "step": 358340 }, { "epoch": 2.130106817411773, "grad_norm": 4.700118541717529, "learning_rate": 7.096946772423014e-06, "loss": 0.1536, "step": 358350 }, { "epoch": 2.1301662594884414, "grad_norm": 3.8905436992645264, "learning_rate": 7.0967584079237055e-06, "loss": 0.1633, "step": 358360 }, { "epoch": 2.13022570156511, "grad_norm": 3.313836097717285, "learning_rate": 7.096570039813527e-06, "loss": 0.1413, "step": 358370 }, { "epoch": 2.1302851436417782, "grad_norm": 5.08912992477417, "learning_rate": 7.096381668092806e-06, "loss": 0.1482, "step": 358380 }, { "epoch": 2.1303445857184466, "grad_norm": 4.2620391845703125, "learning_rate": 7.096193292761867e-06, "loss": 0.1503, "step": 358390 }, { "epoch": 2.130404027795115, "grad_norm": 5.369007587432861, "learning_rate": 7.0960049138210306e-06, "loss": 0.1618, "step": 358400 }, { "epoch": 2.1304634698717835, "grad_norm": 3.808037519454956, "learning_rate": 7.095816531270625e-06, "loss": 0.1417, "step": 358410 }, { "epoch": 2.130522911948452, "grad_norm": 5.131521701812744, "learning_rate": 7.095628145110973e-06, "loss": 0.1577, "step": 358420 }, { "epoch": 2.1305823540251203, "grad_norm": 4.495731353759766, "learning_rate": 7.0954397553424005e-06, "loss": 0.1508, "step": 358430 }, { "epoch": 2.1306417961017887, "grad_norm": 5.821054458618164, "learning_rate": 7.0952513619652285e-06, "loss": 0.1695, "step": 358440 }, { "epoch": 2.130701238178457, "grad_norm": 4.188305854797363, "learning_rate": 7.095062964979785e-06, "loss": 0.1371, "step": 358450 }, { "epoch": 2.1307606802551255, "grad_norm": 4.686079978942871, "learning_rate": 7.094874564386394e-06, "loss": 0.1634, "step": 358460 }, { "epoch": 2.130820122331794, "grad_norm": 5.575441360473633, "learning_rate": 7.094686160185376e-06, "loss": 0.1466, "step": 358470 }, { "epoch": 2.1308795644084624, "grad_norm": 4.802832126617432, "learning_rate": 7.094497752377061e-06, "loss": 0.1471, "step": 358480 }, { "epoch": 2.1309390064851303, "grad_norm": 3.8240177631378174, "learning_rate": 7.094309340961772e-06, "loss": 0.1552, "step": 358490 }, { "epoch": 2.1309984485617988, "grad_norm": 4.735233783721924, "learning_rate": 7.094120925939829e-06, "loss": 0.1469, "step": 358500 }, { "epoch": 2.131057890638467, "grad_norm": 3.860018014907837, "learning_rate": 7.093932507311562e-06, "loss": 0.1636, "step": 358510 }, { "epoch": 2.1311173327151356, "grad_norm": 5.140928268432617, "learning_rate": 7.0937440850772935e-06, "loss": 0.1509, "step": 358520 }, { "epoch": 2.131176774791804, "grad_norm": 3.7504844665527344, "learning_rate": 7.093555659237346e-06, "loss": 0.1612, "step": 358530 }, { "epoch": 2.1312362168684724, "grad_norm": 4.164671897888184, "learning_rate": 7.093367229792047e-06, "loss": 0.1513, "step": 358540 }, { "epoch": 2.131295658945141, "grad_norm": 2.7473490238189697, "learning_rate": 7.093178796741722e-06, "loss": 0.1628, "step": 358550 }, { "epoch": 2.1313551010218093, "grad_norm": 2.863192558288574, "learning_rate": 7.09299036008669e-06, "loss": 0.1473, "step": 358560 }, { "epoch": 2.1314145430984777, "grad_norm": 3.7464656829833984, "learning_rate": 7.092801919827281e-06, "loss": 0.141, "step": 358570 }, { "epoch": 2.131473985175146, "grad_norm": 4.668057441711426, "learning_rate": 7.092613475963816e-06, "loss": 0.1735, "step": 358580 }, { "epoch": 2.1315334272518145, "grad_norm": 5.801360607147217, "learning_rate": 7.092425028496622e-06, "loss": 0.1688, "step": 358590 }, { "epoch": 2.131592869328483, "grad_norm": 4.512113571166992, "learning_rate": 7.0922365774260225e-06, "loss": 0.168, "step": 358600 }, { "epoch": 2.1316523114051513, "grad_norm": 4.364295959472656, "learning_rate": 7.092048122752342e-06, "loss": 0.1678, "step": 358610 }, { "epoch": 2.1317117534818197, "grad_norm": 5.0457353591918945, "learning_rate": 7.091859664475904e-06, "loss": 0.1499, "step": 358620 }, { "epoch": 2.131771195558488, "grad_norm": 4.644479274749756, "learning_rate": 7.091671202597034e-06, "loss": 0.1692, "step": 358630 }, { "epoch": 2.1318306376351566, "grad_norm": 3.68113374710083, "learning_rate": 7.091482737116058e-06, "loss": 0.1601, "step": 358640 }, { "epoch": 2.131890079711825, "grad_norm": 4.495056629180908, "learning_rate": 7.091294268033299e-06, "loss": 0.1495, "step": 358650 }, { "epoch": 2.1319495217884934, "grad_norm": 4.564155578613281, "learning_rate": 7.091105795349081e-06, "loss": 0.1803, "step": 358660 }, { "epoch": 2.132008963865162, "grad_norm": 3.939488410949707, "learning_rate": 7.090917319063729e-06, "loss": 0.1448, "step": 358670 }, { "epoch": 2.13206840594183, "grad_norm": 3.80478572845459, "learning_rate": 7.0907288391775684e-06, "loss": 0.1442, "step": 358680 }, { "epoch": 2.132127848018498, "grad_norm": 3.2605772018432617, "learning_rate": 7.090540355690922e-06, "loss": 0.1343, "step": 358690 }, { "epoch": 2.1321872900951666, "grad_norm": 5.277642726898193, "learning_rate": 7.0903518686041185e-06, "loss": 0.1693, "step": 358700 }, { "epoch": 2.132246732171835, "grad_norm": 4.107612609863281, "learning_rate": 7.090163377917478e-06, "loss": 0.1395, "step": 358710 }, { "epoch": 2.1323061742485034, "grad_norm": 5.3242034912109375, "learning_rate": 7.089974883631326e-06, "loss": 0.1618, "step": 358720 }, { "epoch": 2.132365616325172, "grad_norm": 5.573873519897461, "learning_rate": 7.089786385745989e-06, "loss": 0.1591, "step": 358730 }, { "epoch": 2.1324250584018403, "grad_norm": 5.503774642944336, "learning_rate": 7.089597884261791e-06, "loss": 0.1709, "step": 358740 }, { "epoch": 2.1324845004785087, "grad_norm": 4.344479084014893, "learning_rate": 7.089409379179056e-06, "loss": 0.1519, "step": 358750 }, { "epoch": 2.132543942555177, "grad_norm": 4.356666088104248, "learning_rate": 7.0892208704981065e-06, "loss": 0.1418, "step": 358760 }, { "epoch": 2.1326033846318455, "grad_norm": 3.9398152828216553, "learning_rate": 7.089032358219272e-06, "loss": 0.1514, "step": 358770 }, { "epoch": 2.132662826708514, "grad_norm": 4.0127644538879395, "learning_rate": 7.088843842342874e-06, "loss": 0.1505, "step": 358780 }, { "epoch": 2.1327222687851823, "grad_norm": 3.7278432846069336, "learning_rate": 7.088655322869235e-06, "loss": 0.1474, "step": 358790 }, { "epoch": 2.1327817108618508, "grad_norm": 4.554404258728027, "learning_rate": 7.0884667997986855e-06, "loss": 0.1615, "step": 358800 }, { "epoch": 2.132841152938519, "grad_norm": 3.167819023132324, "learning_rate": 7.0882782731315466e-06, "loss": 0.1541, "step": 358810 }, { "epoch": 2.1329005950151876, "grad_norm": 4.978911876678467, "learning_rate": 7.088089742868143e-06, "loss": 0.1241, "step": 358820 }, { "epoch": 2.132960037091856, "grad_norm": 4.489762306213379, "learning_rate": 7.087901209008798e-06, "loss": 0.1516, "step": 358830 }, { "epoch": 2.1330194791685244, "grad_norm": 4.637091636657715, "learning_rate": 7.087712671553839e-06, "loss": 0.141, "step": 358840 }, { "epoch": 2.133078921245193, "grad_norm": 4.842315673828125, "learning_rate": 7.087524130503591e-06, "loss": 0.1563, "step": 358850 }, { "epoch": 2.1331383633218612, "grad_norm": 4.929187774658203, "learning_rate": 7.087335585858376e-06, "loss": 0.1696, "step": 358860 }, { "epoch": 2.133197805398529, "grad_norm": 5.4011359214782715, "learning_rate": 7.087147037618522e-06, "loss": 0.1694, "step": 358870 }, { "epoch": 2.1332572474751976, "grad_norm": 3.3501102924346924, "learning_rate": 7.08695848578435e-06, "loss": 0.1601, "step": 358880 }, { "epoch": 2.133316689551866, "grad_norm": 4.89184045791626, "learning_rate": 7.0867699303561854e-06, "loss": 0.1495, "step": 358890 }, { "epoch": 2.1333761316285345, "grad_norm": 3.972365617752075, "learning_rate": 7.086581371334356e-06, "loss": 0.14, "step": 358900 }, { "epoch": 2.133435573705203, "grad_norm": 3.5803720951080322, "learning_rate": 7.086392808719185e-06, "loss": 0.1479, "step": 358910 }, { "epoch": 2.1334950157818713, "grad_norm": 4.417430400848389, "learning_rate": 7.086204242510995e-06, "loss": 0.1653, "step": 358920 }, { "epoch": 2.1335544578585397, "grad_norm": 3.2735755443573, "learning_rate": 7.086015672710112e-06, "loss": 0.1404, "step": 358930 }, { "epoch": 2.133613899935208, "grad_norm": 4.653423309326172, "learning_rate": 7.085827099316863e-06, "loss": 0.1508, "step": 358940 }, { "epoch": 2.1336733420118765, "grad_norm": 4.602477550506592, "learning_rate": 7.0856385223315695e-06, "loss": 0.1391, "step": 358950 }, { "epoch": 2.133732784088545, "grad_norm": 3.247152805328369, "learning_rate": 7.085449941754558e-06, "loss": 0.146, "step": 358960 }, { "epoch": 2.1337922261652134, "grad_norm": 3.5031840801239014, "learning_rate": 7.085261357586153e-06, "loss": 0.138, "step": 358970 }, { "epoch": 2.1338516682418818, "grad_norm": 4.4681396484375, "learning_rate": 7.085072769826679e-06, "loss": 0.1617, "step": 358980 }, { "epoch": 2.13391111031855, "grad_norm": 4.931604862213135, "learning_rate": 7.08488417847646e-06, "loss": 0.168, "step": 358990 }, { "epoch": 2.1339705523952186, "grad_norm": 7.516438007354736, "learning_rate": 7.084695583535824e-06, "loss": 0.1556, "step": 359000 }, { "epoch": 2.134029994471887, "grad_norm": 5.0480780601501465, "learning_rate": 7.084506985005091e-06, "loss": 0.151, "step": 359010 }, { "epoch": 2.1340894365485554, "grad_norm": 3.9460179805755615, "learning_rate": 7.084318382884589e-06, "loss": 0.1457, "step": 359020 }, { "epoch": 2.134148878625224, "grad_norm": 3.1826233863830566, "learning_rate": 7.084129777174642e-06, "loss": 0.1306, "step": 359030 }, { "epoch": 2.134208320701892, "grad_norm": 3.176851987838745, "learning_rate": 7.083941167875576e-06, "loss": 0.1448, "step": 359040 }, { "epoch": 2.1342677627785602, "grad_norm": 4.484199047088623, "learning_rate": 7.083752554987713e-06, "loss": 0.1471, "step": 359050 }, { "epoch": 2.1343272048552286, "grad_norm": 3.614553689956665, "learning_rate": 7.08356393851138e-06, "loss": 0.1596, "step": 359060 }, { "epoch": 2.134386646931897, "grad_norm": 4.3443098068237305, "learning_rate": 7.0833753184469025e-06, "loss": 0.1695, "step": 359070 }, { "epoch": 2.1344460890085655, "grad_norm": 3.9155561923980713, "learning_rate": 7.083186694794601e-06, "loss": 0.1469, "step": 359080 }, { "epoch": 2.134505531085234, "grad_norm": 4.805355548858643, "learning_rate": 7.082998067554807e-06, "loss": 0.1444, "step": 359090 }, { "epoch": 2.1345649731619023, "grad_norm": 5.056953430175781, "learning_rate": 7.082809436727841e-06, "loss": 0.1555, "step": 359100 }, { "epoch": 2.1346244152385707, "grad_norm": 6.032301902770996, "learning_rate": 7.082620802314029e-06, "loss": 0.1631, "step": 359110 }, { "epoch": 2.134683857315239, "grad_norm": 4.973702907562256, "learning_rate": 7.082432164313693e-06, "loss": 0.1608, "step": 359120 }, { "epoch": 2.1347432993919075, "grad_norm": 4.629038333892822, "learning_rate": 7.082243522727162e-06, "loss": 0.1313, "step": 359130 }, { "epoch": 2.134802741468576, "grad_norm": 3.542698383331299, "learning_rate": 7.08205487755476e-06, "loss": 0.1574, "step": 359140 }, { "epoch": 2.1348621835452444, "grad_norm": 4.8139519691467285, "learning_rate": 7.08186622879681e-06, "loss": 0.1434, "step": 359150 }, { "epoch": 2.134921625621913, "grad_norm": 3.201647996902466, "learning_rate": 7.081677576453638e-06, "loss": 0.1343, "step": 359160 }, { "epoch": 2.134981067698581, "grad_norm": 4.336779594421387, "learning_rate": 7.081488920525569e-06, "loss": 0.1494, "step": 359170 }, { "epoch": 2.1350405097752496, "grad_norm": 5.5222930908203125, "learning_rate": 7.081300261012927e-06, "loss": 0.1546, "step": 359180 }, { "epoch": 2.135099951851918, "grad_norm": 4.879616737365723, "learning_rate": 7.0811115979160385e-06, "loss": 0.1404, "step": 359190 }, { "epoch": 2.1351593939285864, "grad_norm": 4.738144397735596, "learning_rate": 7.0809229312352275e-06, "loss": 0.1566, "step": 359200 }, { "epoch": 2.135218836005255, "grad_norm": 4.679149627685547, "learning_rate": 7.080734260970818e-06, "loss": 0.1848, "step": 359210 }, { "epoch": 2.1352782780819233, "grad_norm": 4.333768367767334, "learning_rate": 7.080545587123136e-06, "loss": 0.1764, "step": 359220 }, { "epoch": 2.1353377201585912, "grad_norm": 5.534186840057373, "learning_rate": 7.080356909692508e-06, "loss": 0.1376, "step": 359230 }, { "epoch": 2.1353971622352597, "grad_norm": 4.005893230438232, "learning_rate": 7.080168228679256e-06, "loss": 0.1451, "step": 359240 }, { "epoch": 2.135456604311928, "grad_norm": 3.518397092819214, "learning_rate": 7.079979544083706e-06, "loss": 0.1553, "step": 359250 }, { "epoch": 2.1355160463885965, "grad_norm": 3.683401107788086, "learning_rate": 7.079790855906184e-06, "loss": 0.1541, "step": 359260 }, { "epoch": 2.135575488465265, "grad_norm": 3.8012866973876953, "learning_rate": 7.0796021641470125e-06, "loss": 0.1637, "step": 359270 }, { "epoch": 2.1356349305419333, "grad_norm": 4.301339149475098, "learning_rate": 7.079413468806517e-06, "loss": 0.1593, "step": 359280 }, { "epoch": 2.1356943726186017, "grad_norm": 4.782215118408203, "learning_rate": 7.079224769885026e-06, "loss": 0.1461, "step": 359290 }, { "epoch": 2.13575381469527, "grad_norm": 3.6001107692718506, "learning_rate": 7.0790360673828606e-06, "loss": 0.1646, "step": 359300 }, { "epoch": 2.1358132567719386, "grad_norm": 2.556957483291626, "learning_rate": 7.078847361300347e-06, "loss": 0.1498, "step": 359310 }, { "epoch": 2.135872698848607, "grad_norm": 5.312987804412842, "learning_rate": 7.0786586516378104e-06, "loss": 0.1756, "step": 359320 }, { "epoch": 2.1359321409252754, "grad_norm": 3.8731982707977295, "learning_rate": 7.078469938395577e-06, "loss": 0.1371, "step": 359330 }, { "epoch": 2.135991583001944, "grad_norm": 4.379962921142578, "learning_rate": 7.078281221573968e-06, "loss": 0.1504, "step": 359340 }, { "epoch": 2.136051025078612, "grad_norm": 5.201884746551514, "learning_rate": 7.078092501173313e-06, "loss": 0.1657, "step": 359350 }, { "epoch": 2.1361104671552806, "grad_norm": 4.207528591156006, "learning_rate": 7.077903777193933e-06, "loss": 0.1405, "step": 359360 }, { "epoch": 2.136169909231949, "grad_norm": 4.086176872253418, "learning_rate": 7.077715049636155e-06, "loss": 0.1726, "step": 359370 }, { "epoch": 2.1362293513086175, "grad_norm": 3.872809648513794, "learning_rate": 7.077526318500304e-06, "loss": 0.1396, "step": 359380 }, { "epoch": 2.136288793385286, "grad_norm": 3.7114999294281006, "learning_rate": 7.077337583786704e-06, "loss": 0.1477, "step": 359390 }, { "epoch": 2.1363482354619543, "grad_norm": 4.808725833892822, "learning_rate": 7.0771488454956824e-06, "loss": 0.141, "step": 359400 }, { "epoch": 2.1364076775386227, "grad_norm": 4.141548156738281, "learning_rate": 7.076960103627562e-06, "loss": 0.1691, "step": 359410 }, { "epoch": 2.1364671196152907, "grad_norm": 4.107715129852295, "learning_rate": 7.076771358182668e-06, "loss": 0.1372, "step": 359420 }, { "epoch": 2.136526561691959, "grad_norm": 5.319585800170898, "learning_rate": 7.076582609161327e-06, "loss": 0.1617, "step": 359430 }, { "epoch": 2.1365860037686275, "grad_norm": 4.36515474319458, "learning_rate": 7.076393856563862e-06, "loss": 0.1533, "step": 359440 }, { "epoch": 2.136645445845296, "grad_norm": 4.7637104988098145, "learning_rate": 7.076205100390599e-06, "loss": 0.1871, "step": 359450 }, { "epoch": 2.1367048879219643, "grad_norm": 4.337817192077637, "learning_rate": 7.076016340641864e-06, "loss": 0.1561, "step": 359460 }, { "epoch": 2.1367643299986327, "grad_norm": 4.241856098175049, "learning_rate": 7.07582757731798e-06, "loss": 0.1586, "step": 359470 }, { "epoch": 2.136823772075301, "grad_norm": 4.597559452056885, "learning_rate": 7.075638810419274e-06, "loss": 0.1604, "step": 359480 }, { "epoch": 2.1368832141519696, "grad_norm": 4.105482578277588, "learning_rate": 7.0754500399460706e-06, "loss": 0.1606, "step": 359490 }, { "epoch": 2.136942656228638, "grad_norm": 4.308718204498291, "learning_rate": 7.075261265898693e-06, "loss": 0.1531, "step": 359500 }, { "epoch": 2.1370020983053064, "grad_norm": 4.929652214050293, "learning_rate": 7.075072488277469e-06, "loss": 0.1659, "step": 359510 }, { "epoch": 2.137061540381975, "grad_norm": 3.870231866836548, "learning_rate": 7.074883707082722e-06, "loss": 0.1735, "step": 359520 }, { "epoch": 2.1371209824586432, "grad_norm": 5.63086462020874, "learning_rate": 7.07469492231478e-06, "loss": 0.1682, "step": 359530 }, { "epoch": 2.1371804245353117, "grad_norm": 4.207785129547119, "learning_rate": 7.074506133973963e-06, "loss": 0.1446, "step": 359540 }, { "epoch": 2.13723986661198, "grad_norm": 4.224053859710693, "learning_rate": 7.074317342060601e-06, "loss": 0.1579, "step": 359550 }, { "epoch": 2.1372993086886485, "grad_norm": 4.6398091316223145, "learning_rate": 7.074128546575016e-06, "loss": 0.1519, "step": 359560 }, { "epoch": 2.137358750765317, "grad_norm": 3.539175510406494, "learning_rate": 7.073939747517533e-06, "loss": 0.1695, "step": 359570 }, { "epoch": 2.1374181928419853, "grad_norm": 4.827813625335693, "learning_rate": 7.07375094488848e-06, "loss": 0.1539, "step": 359580 }, { "epoch": 2.1374776349186537, "grad_norm": 4.07760763168335, "learning_rate": 7.07356213868818e-06, "loss": 0.1599, "step": 359590 }, { "epoch": 2.137537076995322, "grad_norm": 5.100221633911133, "learning_rate": 7.073373328916958e-06, "loss": 0.1494, "step": 359600 }, { "epoch": 2.13759651907199, "grad_norm": 4.626879692077637, "learning_rate": 7.07318451557514e-06, "loss": 0.1538, "step": 359610 }, { "epoch": 2.1376559611486585, "grad_norm": 4.111769199371338, "learning_rate": 7.072995698663051e-06, "loss": 0.158, "step": 359620 }, { "epoch": 2.137715403225327, "grad_norm": 4.243088245391846, "learning_rate": 7.072806878181017e-06, "loss": 0.1227, "step": 359630 }, { "epoch": 2.1377748453019954, "grad_norm": 2.990199327468872, "learning_rate": 7.072618054129361e-06, "loss": 0.1493, "step": 359640 }, { "epoch": 2.1378342873786638, "grad_norm": 6.338632106781006, "learning_rate": 7.07242922650841e-06, "loss": 0.1505, "step": 359650 }, { "epoch": 2.137893729455332, "grad_norm": 3.463301658630371, "learning_rate": 7.0722403953184885e-06, "loss": 0.1403, "step": 359660 }, { "epoch": 2.1379531715320006, "grad_norm": 3.8828651905059814, "learning_rate": 7.07205156055992e-06, "loss": 0.14, "step": 359670 }, { "epoch": 2.138012613608669, "grad_norm": 4.615590572357178, "learning_rate": 7.071862722233034e-06, "loss": 0.1555, "step": 359680 }, { "epoch": 2.1380720556853374, "grad_norm": 3.961618185043335, "learning_rate": 7.071673880338152e-06, "loss": 0.1459, "step": 359690 }, { "epoch": 2.138131497762006, "grad_norm": 3.9631175994873047, "learning_rate": 7.071485034875601e-06, "loss": 0.1509, "step": 359700 }, { "epoch": 2.1381909398386743, "grad_norm": 3.384404182434082, "learning_rate": 7.071296185845706e-06, "loss": 0.1425, "step": 359710 }, { "epoch": 2.1382503819153427, "grad_norm": 5.064742565155029, "learning_rate": 7.07110733324879e-06, "loss": 0.1428, "step": 359720 }, { "epoch": 2.138309823992011, "grad_norm": 3.5128042697906494, "learning_rate": 7.070918477085181e-06, "loss": 0.1394, "step": 359730 }, { "epoch": 2.1383692660686795, "grad_norm": 3.724090099334717, "learning_rate": 7.070729617355204e-06, "loss": 0.1453, "step": 359740 }, { "epoch": 2.138428708145348, "grad_norm": 3.3955090045928955, "learning_rate": 7.070540754059183e-06, "loss": 0.186, "step": 359750 }, { "epoch": 2.1384881502220163, "grad_norm": 4.305148601531982, "learning_rate": 7.070351887197444e-06, "loss": 0.1458, "step": 359760 }, { "epoch": 2.1385475922986847, "grad_norm": 3.9160871505737305, "learning_rate": 7.0701630167703114e-06, "loss": 0.1508, "step": 359770 }, { "epoch": 2.1386070343753527, "grad_norm": 3.99641489982605, "learning_rate": 7.069974142778112e-06, "loss": 0.1528, "step": 359780 }, { "epoch": 2.138666476452021, "grad_norm": 4.159703254699707, "learning_rate": 7.0697852652211695e-06, "loss": 0.1603, "step": 359790 }, { "epoch": 2.1387259185286895, "grad_norm": 5.123256206512451, "learning_rate": 7.069596384099811e-06, "loss": 0.1469, "step": 359800 }, { "epoch": 2.138785360605358, "grad_norm": 2.870435953140259, "learning_rate": 7.069407499414359e-06, "loss": 0.1581, "step": 359810 }, { "epoch": 2.1388448026820264, "grad_norm": 4.325112342834473, "learning_rate": 7.069218611165141e-06, "loss": 0.1425, "step": 359820 }, { "epoch": 2.138904244758695, "grad_norm": 3.299368381500244, "learning_rate": 7.06902971935248e-06, "loss": 0.1484, "step": 359830 }, { "epoch": 2.138963686835363, "grad_norm": 3.6445083618164062, "learning_rate": 7.068840823976705e-06, "loss": 0.1595, "step": 359840 }, { "epoch": 2.1390231289120316, "grad_norm": 2.992222309112549, "learning_rate": 7.068651925038139e-06, "loss": 0.1437, "step": 359850 }, { "epoch": 2.1390825709887, "grad_norm": 3.9427695274353027, "learning_rate": 7.068463022537106e-06, "loss": 0.1717, "step": 359860 }, { "epoch": 2.1391420130653684, "grad_norm": 5.407441139221191, "learning_rate": 7.0682741164739355e-06, "loss": 0.1696, "step": 359870 }, { "epoch": 2.139201455142037, "grad_norm": 4.370396137237549, "learning_rate": 7.068085206848949e-06, "loss": 0.1233, "step": 359880 }, { "epoch": 2.1392608972187053, "grad_norm": 4.636947154998779, "learning_rate": 7.067896293662473e-06, "loss": 0.1451, "step": 359890 }, { "epoch": 2.1393203392953737, "grad_norm": 4.137925624847412, "learning_rate": 7.067707376914832e-06, "loss": 0.1429, "step": 359900 }, { "epoch": 2.139379781372042, "grad_norm": 4.48412561416626, "learning_rate": 7.067518456606353e-06, "loss": 0.1638, "step": 359910 }, { "epoch": 2.1394392234487105, "grad_norm": 5.153934955596924, "learning_rate": 7.06732953273736e-06, "loss": 0.1404, "step": 359920 }, { "epoch": 2.139498665525379, "grad_norm": 4.916857719421387, "learning_rate": 7.0671406053081805e-06, "loss": 0.1577, "step": 359930 }, { "epoch": 2.1395581076020473, "grad_norm": 4.9155778884887695, "learning_rate": 7.066951674319136e-06, "loss": 0.1509, "step": 359940 }, { "epoch": 2.1396175496787158, "grad_norm": 3.544442653656006, "learning_rate": 7.066762739770556e-06, "loss": 0.1546, "step": 359950 }, { "epoch": 2.139676991755384, "grad_norm": 4.037675857543945, "learning_rate": 7.066573801662761e-06, "loss": 0.1481, "step": 359960 }, { "epoch": 2.139736433832052, "grad_norm": 3.707603931427002, "learning_rate": 7.066384859996083e-06, "loss": 0.1435, "step": 359970 }, { "epoch": 2.1397958759087206, "grad_norm": 4.3736958503723145, "learning_rate": 7.066195914770843e-06, "loss": 0.1576, "step": 359980 }, { "epoch": 2.139855317985389, "grad_norm": 3.3996050357818604, "learning_rate": 7.0660069659873655e-06, "loss": 0.1623, "step": 359990 }, { "epoch": 2.1399147600620574, "grad_norm": 5.105231285095215, "learning_rate": 7.065818013645977e-06, "loss": 0.1493, "step": 360000 }, { "epoch": 2.139974202138726, "grad_norm": 4.4524827003479, "learning_rate": 7.065629057747006e-06, "loss": 0.1354, "step": 360010 }, { "epoch": 2.140033644215394, "grad_norm": 3.731138229370117, "learning_rate": 7.065440098290773e-06, "loss": 0.1466, "step": 360020 }, { "epoch": 2.1400930862920626, "grad_norm": 4.085411071777344, "learning_rate": 7.065251135277608e-06, "loss": 0.1417, "step": 360030 }, { "epoch": 2.140152528368731, "grad_norm": 4.726363658905029, "learning_rate": 7.065062168707833e-06, "loss": 0.1558, "step": 360040 }, { "epoch": 2.1402119704453995, "grad_norm": 3.285552501678467, "learning_rate": 7.064873198581773e-06, "loss": 0.1494, "step": 360050 }, { "epoch": 2.140271412522068, "grad_norm": 3.4931893348693848, "learning_rate": 7.064684224899756e-06, "loss": 0.1452, "step": 360060 }, { "epoch": 2.1403308545987363, "grad_norm": 3.5131325721740723, "learning_rate": 7.064495247662106e-06, "loss": 0.1615, "step": 360070 }, { "epoch": 2.1403902966754047, "grad_norm": 3.5715394020080566, "learning_rate": 7.064306266869151e-06, "loss": 0.1558, "step": 360080 }, { "epoch": 2.140449738752073, "grad_norm": 4.521881580352783, "learning_rate": 7.064117282521212e-06, "loss": 0.1491, "step": 360090 }, { "epoch": 2.1405091808287415, "grad_norm": 3.9347681999206543, "learning_rate": 7.063928294618618e-06, "loss": 0.1392, "step": 360100 }, { "epoch": 2.14056862290541, "grad_norm": 5.104072570800781, "learning_rate": 7.063739303161693e-06, "loss": 0.1647, "step": 360110 }, { "epoch": 2.1406280649820784, "grad_norm": 4.166219711303711, "learning_rate": 7.063550308150762e-06, "loss": 0.1508, "step": 360120 }, { "epoch": 2.1406875070587468, "grad_norm": 4.523041725158691, "learning_rate": 7.063361309586152e-06, "loss": 0.1291, "step": 360130 }, { "epoch": 2.140746949135415, "grad_norm": 3.2041568756103516, "learning_rate": 7.063172307468188e-06, "loss": 0.1413, "step": 360140 }, { "epoch": 2.1408063912120836, "grad_norm": 5.874084949493408, "learning_rate": 7.062983301797194e-06, "loss": 0.1602, "step": 360150 }, { "epoch": 2.1408658332887516, "grad_norm": 5.078954219818115, "learning_rate": 7.062794292573496e-06, "loss": 0.1466, "step": 360160 }, { "epoch": 2.14092527536542, "grad_norm": 4.788768768310547, "learning_rate": 7.062605279797421e-06, "loss": 0.1831, "step": 360170 }, { "epoch": 2.1409847174420884, "grad_norm": 4.203492641448975, "learning_rate": 7.062416263469294e-06, "loss": 0.1724, "step": 360180 }, { "epoch": 2.141044159518757, "grad_norm": 4.303791522979736, "learning_rate": 7.062227243589439e-06, "loss": 0.1485, "step": 360190 }, { "epoch": 2.1411036015954252, "grad_norm": 4.172590255737305, "learning_rate": 7.062038220158185e-06, "loss": 0.1707, "step": 360200 }, { "epoch": 2.1411630436720936, "grad_norm": 4.046377658843994, "learning_rate": 7.061849193175854e-06, "loss": 0.1382, "step": 360210 }, { "epoch": 2.141222485748762, "grad_norm": 3.699148654937744, "learning_rate": 7.061660162642771e-06, "loss": 0.1428, "step": 360220 }, { "epoch": 2.1412819278254305, "grad_norm": 4.175751209259033, "learning_rate": 7.061471128559265e-06, "loss": 0.1519, "step": 360230 }, { "epoch": 2.141341369902099, "grad_norm": 6.705386638641357, "learning_rate": 7.061282090925659e-06, "loss": 0.1758, "step": 360240 }, { "epoch": 2.1414008119787673, "grad_norm": 4.582594394683838, "learning_rate": 7.061093049742279e-06, "loss": 0.1498, "step": 360250 }, { "epoch": 2.1414602540554357, "grad_norm": 3.9355533123016357, "learning_rate": 7.0609040050094525e-06, "loss": 0.1383, "step": 360260 }, { "epoch": 2.141519696132104, "grad_norm": 6.210249423980713, "learning_rate": 7.060714956727501e-06, "loss": 0.1566, "step": 360270 }, { "epoch": 2.1415791382087725, "grad_norm": 3.770624876022339, "learning_rate": 7.060525904896753e-06, "loss": 0.1558, "step": 360280 }, { "epoch": 2.141638580285441, "grad_norm": 4.696178913116455, "learning_rate": 7.060336849517535e-06, "loss": 0.1652, "step": 360290 }, { "epoch": 2.1416980223621094, "grad_norm": 4.350576877593994, "learning_rate": 7.0601477905901705e-06, "loss": 0.1441, "step": 360300 }, { "epoch": 2.141757464438778, "grad_norm": 4.151674747467041, "learning_rate": 7.059958728114986e-06, "loss": 0.177, "step": 360310 }, { "epoch": 2.141816906515446, "grad_norm": 5.40608549118042, "learning_rate": 7.059769662092305e-06, "loss": 0.1733, "step": 360320 }, { "epoch": 2.1418763485921146, "grad_norm": 5.077609539031982, "learning_rate": 7.059580592522457e-06, "loss": 0.1686, "step": 360330 }, { "epoch": 2.141935790668783, "grad_norm": 4.171819686889648, "learning_rate": 7.059391519405765e-06, "loss": 0.1778, "step": 360340 }, { "epoch": 2.141995232745451, "grad_norm": 3.801837205886841, "learning_rate": 7.059202442742554e-06, "loss": 0.1495, "step": 360350 }, { "epoch": 2.1420546748221194, "grad_norm": 3.235978364944458, "learning_rate": 7.059013362533151e-06, "loss": 0.1534, "step": 360360 }, { "epoch": 2.142114116898788, "grad_norm": 5.239291191101074, "learning_rate": 7.058824278777882e-06, "loss": 0.1452, "step": 360370 }, { "epoch": 2.1421735589754562, "grad_norm": 3.9462132453918457, "learning_rate": 7.058635191477071e-06, "loss": 0.1228, "step": 360380 }, { "epoch": 2.1422330010521247, "grad_norm": 5.594175338745117, "learning_rate": 7.0584461006310455e-06, "loss": 0.1354, "step": 360390 }, { "epoch": 2.142292443128793, "grad_norm": 2.9137561321258545, "learning_rate": 7.05825700624013e-06, "loss": 0.1542, "step": 360400 }, { "epoch": 2.1423518852054615, "grad_norm": 3.242812395095825, "learning_rate": 7.05806790830465e-06, "loss": 0.12, "step": 360410 }, { "epoch": 2.14241132728213, "grad_norm": 3.9775145053863525, "learning_rate": 7.057878806824932e-06, "loss": 0.1556, "step": 360420 }, { "epoch": 2.1424707693587983, "grad_norm": 5.1398749351501465, "learning_rate": 7.057689701801302e-06, "loss": 0.1447, "step": 360430 }, { "epoch": 2.1425302114354667, "grad_norm": 4.333705425262451, "learning_rate": 7.057500593234083e-06, "loss": 0.1606, "step": 360440 }, { "epoch": 2.142589653512135, "grad_norm": 4.257568359375, "learning_rate": 7.057311481123603e-06, "loss": 0.172, "step": 360450 }, { "epoch": 2.1426490955888036, "grad_norm": 4.261600971221924, "learning_rate": 7.057122365470188e-06, "loss": 0.1647, "step": 360460 }, { "epoch": 2.142708537665472, "grad_norm": 4.951866626739502, "learning_rate": 7.056933246274162e-06, "loss": 0.1642, "step": 360470 }, { "epoch": 2.1427679797421404, "grad_norm": 3.725475549697876, "learning_rate": 7.056744123535852e-06, "loss": 0.1577, "step": 360480 }, { "epoch": 2.142827421818809, "grad_norm": 4.612162113189697, "learning_rate": 7.0565549972555825e-06, "loss": 0.1341, "step": 360490 }, { "epoch": 2.1428868638954772, "grad_norm": 4.377233505249023, "learning_rate": 7.056365867433681e-06, "loss": 0.1429, "step": 360500 }, { "epoch": 2.1429463059721456, "grad_norm": 3.9730873107910156, "learning_rate": 7.05617673407047e-06, "loss": 0.1495, "step": 360510 }, { "epoch": 2.1430057480488136, "grad_norm": 3.577160120010376, "learning_rate": 7.05598759716628e-06, "loss": 0.1445, "step": 360520 }, { "epoch": 2.143065190125482, "grad_norm": 4.3566975593566895, "learning_rate": 7.055798456721432e-06, "loss": 0.1503, "step": 360530 }, { "epoch": 2.1431246322021504, "grad_norm": 4.790643692016602, "learning_rate": 7.055609312736254e-06, "loss": 0.1629, "step": 360540 }, { "epoch": 2.143184074278819, "grad_norm": 8.545236587524414, "learning_rate": 7.0554201652110734e-06, "loss": 0.1668, "step": 360550 }, { "epoch": 2.1432435163554873, "grad_norm": 4.305775165557861, "learning_rate": 7.055231014146213e-06, "loss": 0.1493, "step": 360560 }, { "epoch": 2.1433029584321557, "grad_norm": 4.8311357498168945, "learning_rate": 7.055041859541999e-06, "loss": 0.1484, "step": 360570 }, { "epoch": 2.143362400508824, "grad_norm": 4.695528984069824, "learning_rate": 7.054852701398758e-06, "loss": 0.1432, "step": 360580 }, { "epoch": 2.1434218425854925, "grad_norm": 4.337705135345459, "learning_rate": 7.054663539716816e-06, "loss": 0.1396, "step": 360590 }, { "epoch": 2.143481284662161, "grad_norm": 3.4334728717803955, "learning_rate": 7.054474374496497e-06, "loss": 0.1458, "step": 360600 }, { "epoch": 2.1435407267388293, "grad_norm": 5.834596633911133, "learning_rate": 7.054285205738128e-06, "loss": 0.1638, "step": 360610 }, { "epoch": 2.1436001688154978, "grad_norm": 5.600238800048828, "learning_rate": 7.054096033442036e-06, "loss": 0.1571, "step": 360620 }, { "epoch": 2.143659610892166, "grad_norm": 3.9450178146362305, "learning_rate": 7.053906857608546e-06, "loss": 0.1391, "step": 360630 }, { "epoch": 2.1437190529688346, "grad_norm": 5.077411651611328, "learning_rate": 7.053717678237981e-06, "loss": 0.1318, "step": 360640 }, { "epoch": 2.143778495045503, "grad_norm": 3.6445956230163574, "learning_rate": 7.053528495330671e-06, "loss": 0.1531, "step": 360650 }, { "epoch": 2.1438379371221714, "grad_norm": 3.536557674407959, "learning_rate": 7.05333930888694e-06, "loss": 0.1615, "step": 360660 }, { "epoch": 2.14389737919884, "grad_norm": 3.575773000717163, "learning_rate": 7.0531501189071115e-06, "loss": 0.1659, "step": 360670 }, { "epoch": 2.1439568212755082, "grad_norm": 5.095738887786865, "learning_rate": 7.052960925391515e-06, "loss": 0.1578, "step": 360680 }, { "epoch": 2.1440162633521767, "grad_norm": 3.6353824138641357, "learning_rate": 7.052771728340476e-06, "loss": 0.1489, "step": 360690 }, { "epoch": 2.144075705428845, "grad_norm": 4.7443013191223145, "learning_rate": 7.052582527754317e-06, "loss": 0.1376, "step": 360700 }, { "epoch": 2.144135147505513, "grad_norm": 3.310271978378296, "learning_rate": 7.052393323633366e-06, "loss": 0.1517, "step": 360710 }, { "epoch": 2.1441945895821815, "grad_norm": 4.301296710968018, "learning_rate": 7.052204115977951e-06, "loss": 0.1276, "step": 360720 }, { "epoch": 2.14425403165885, "grad_norm": 6.901492118835449, "learning_rate": 7.052014904788396e-06, "loss": 0.1557, "step": 360730 }, { "epoch": 2.1443134737355183, "grad_norm": 4.723089694976807, "learning_rate": 7.051825690065024e-06, "loss": 0.1412, "step": 360740 }, { "epoch": 2.1443729158121867, "grad_norm": 4.931989669799805, "learning_rate": 7.0516364718081645e-06, "loss": 0.1444, "step": 360750 }, { "epoch": 2.144432357888855, "grad_norm": 4.321400165557861, "learning_rate": 7.051447250018142e-06, "loss": 0.1503, "step": 360760 }, { "epoch": 2.1444917999655235, "grad_norm": 4.243966102600098, "learning_rate": 7.051258024695282e-06, "loss": 0.1438, "step": 360770 }, { "epoch": 2.144551242042192, "grad_norm": 5.209301471710205, "learning_rate": 7.051068795839912e-06, "loss": 0.1619, "step": 360780 }, { "epoch": 2.1446106841188604, "grad_norm": 5.293843746185303, "learning_rate": 7.0508795634523565e-06, "loss": 0.1543, "step": 360790 }, { "epoch": 2.1446701261955288, "grad_norm": 4.481320858001709, "learning_rate": 7.050690327532941e-06, "loss": 0.1482, "step": 360800 }, { "epoch": 2.144729568272197, "grad_norm": 4.510397911071777, "learning_rate": 7.050501088081991e-06, "loss": 0.1561, "step": 360810 }, { "epoch": 2.1447890103488656, "grad_norm": 4.210352420806885, "learning_rate": 7.050311845099836e-06, "loss": 0.1446, "step": 360820 }, { "epoch": 2.144848452425534, "grad_norm": 3.231844663619995, "learning_rate": 7.0501225985867995e-06, "loss": 0.1441, "step": 360830 }, { "epoch": 2.1449078945022024, "grad_norm": 4.536775588989258, "learning_rate": 7.049933348543205e-06, "loss": 0.1378, "step": 360840 }, { "epoch": 2.144967336578871, "grad_norm": 3.3245532512664795, "learning_rate": 7.0497440949693815e-06, "loss": 0.1569, "step": 360850 }, { "epoch": 2.1450267786555393, "grad_norm": 3.8345861434936523, "learning_rate": 7.049554837865656e-06, "loss": 0.1503, "step": 360860 }, { "epoch": 2.1450862207322077, "grad_norm": 4.685294151306152, "learning_rate": 7.04936557723235e-06, "loss": 0.149, "step": 360870 }, { "epoch": 2.145145662808876, "grad_norm": 5.206990718841553, "learning_rate": 7.049176313069793e-06, "loss": 0.1702, "step": 360880 }, { "epoch": 2.1452051048855445, "grad_norm": 5.005846977233887, "learning_rate": 7.0489870453783104e-06, "loss": 0.1583, "step": 360890 }, { "epoch": 2.1452645469622125, "grad_norm": 3.459940195083618, "learning_rate": 7.048797774158227e-06, "loss": 0.1537, "step": 360900 }, { "epoch": 2.145323989038881, "grad_norm": 4.448834419250488, "learning_rate": 7.048608499409869e-06, "loss": 0.1516, "step": 360910 }, { "epoch": 2.1453834311155493, "grad_norm": 4.210474014282227, "learning_rate": 7.048419221133562e-06, "loss": 0.1448, "step": 360920 }, { "epoch": 2.1454428731922177, "grad_norm": 4.723626613616943, "learning_rate": 7.048229939329635e-06, "loss": 0.1482, "step": 360930 }, { "epoch": 2.145502315268886, "grad_norm": 5.1784772872924805, "learning_rate": 7.048040653998409e-06, "loss": 0.1551, "step": 360940 }, { "epoch": 2.1455617573455545, "grad_norm": 5.118149280548096, "learning_rate": 7.047851365140215e-06, "loss": 0.1707, "step": 360950 }, { "epoch": 2.145621199422223, "grad_norm": 3.5495762825012207, "learning_rate": 7.047662072755377e-06, "loss": 0.151, "step": 360960 }, { "epoch": 2.1456806414988914, "grad_norm": 4.3838725090026855, "learning_rate": 7.047472776844218e-06, "loss": 0.1477, "step": 360970 }, { "epoch": 2.14574008357556, "grad_norm": 5.175063133239746, "learning_rate": 7.047283477407068e-06, "loss": 0.1577, "step": 360980 }, { "epoch": 2.145799525652228, "grad_norm": 4.218411922454834, "learning_rate": 7.047094174444252e-06, "loss": 0.1518, "step": 360990 }, { "epoch": 2.1458589677288966, "grad_norm": 4.02773904800415, "learning_rate": 7.046904867956095e-06, "loss": 0.1437, "step": 361000 }, { "epoch": 2.145918409805565, "grad_norm": 4.688418865203857, "learning_rate": 7.046715557942923e-06, "loss": 0.1614, "step": 361010 }, { "epoch": 2.1459778518822334, "grad_norm": 3.8831846714019775, "learning_rate": 7.046526244405064e-06, "loss": 0.1581, "step": 361020 }, { "epoch": 2.146037293958902, "grad_norm": 3.8615877628326416, "learning_rate": 7.04633692734284e-06, "loss": 0.1438, "step": 361030 }, { "epoch": 2.1460967360355703, "grad_norm": 4.907167911529541, "learning_rate": 7.046147606756581e-06, "loss": 0.1471, "step": 361040 }, { "epoch": 2.1461561781122387, "grad_norm": 3.8531501293182373, "learning_rate": 7.045958282646613e-06, "loss": 0.1557, "step": 361050 }, { "epoch": 2.146215620188907, "grad_norm": 4.07938814163208, "learning_rate": 7.04576895501326e-06, "loss": 0.1499, "step": 361060 }, { "epoch": 2.1462750622655755, "grad_norm": 4.348362445831299, "learning_rate": 7.045579623856849e-06, "loss": 0.1511, "step": 361070 }, { "epoch": 2.146334504342244, "grad_norm": 4.667150020599365, "learning_rate": 7.045390289177706e-06, "loss": 0.1565, "step": 361080 }, { "epoch": 2.146393946418912, "grad_norm": 3.413090944290161, "learning_rate": 7.045200950976156e-06, "loss": 0.1304, "step": 361090 }, { "epoch": 2.1464533884955803, "grad_norm": 3.178656578063965, "learning_rate": 7.0450116092525255e-06, "loss": 0.1558, "step": 361100 }, { "epoch": 2.1465128305722487, "grad_norm": 4.551164627075195, "learning_rate": 7.044822264007143e-06, "loss": 0.1375, "step": 361110 }, { "epoch": 2.146572272648917, "grad_norm": 6.6896514892578125, "learning_rate": 7.0446329152403316e-06, "loss": 0.1635, "step": 361120 }, { "epoch": 2.1466317147255856, "grad_norm": 7.603419780731201, "learning_rate": 7.044443562952417e-06, "loss": 0.1514, "step": 361130 }, { "epoch": 2.146691156802254, "grad_norm": 4.795316219329834, "learning_rate": 7.044254207143727e-06, "loss": 0.1695, "step": 361140 }, { "epoch": 2.1467505988789224, "grad_norm": 3.899226427078247, "learning_rate": 7.044064847814589e-06, "loss": 0.149, "step": 361150 }, { "epoch": 2.146810040955591, "grad_norm": 3.249074935913086, "learning_rate": 7.043875484965325e-06, "loss": 0.1612, "step": 361160 }, { "epoch": 2.146869483032259, "grad_norm": 4.055117607116699, "learning_rate": 7.043686118596266e-06, "loss": 0.1529, "step": 361170 }, { "epoch": 2.1469289251089276, "grad_norm": 4.349577903747559, "learning_rate": 7.043496748707734e-06, "loss": 0.1528, "step": 361180 }, { "epoch": 2.146988367185596, "grad_norm": 4.280007839202881, "learning_rate": 7.043307375300058e-06, "loss": 0.1458, "step": 361190 }, { "epoch": 2.1470478092622645, "grad_norm": 3.769080638885498, "learning_rate": 7.043117998373563e-06, "loss": 0.1585, "step": 361200 }, { "epoch": 2.147107251338933, "grad_norm": 3.768080472946167, "learning_rate": 7.042928617928575e-06, "loss": 0.1538, "step": 361210 }, { "epoch": 2.1471666934156013, "grad_norm": 3.334010124206543, "learning_rate": 7.042739233965419e-06, "loss": 0.1522, "step": 361220 }, { "epoch": 2.1472261354922697, "grad_norm": 5.7884840965271, "learning_rate": 7.042549846484422e-06, "loss": 0.1755, "step": 361230 }, { "epoch": 2.147285577568938, "grad_norm": 4.258829593658447, "learning_rate": 7.042360455485912e-06, "loss": 0.1649, "step": 361240 }, { "epoch": 2.1473450196456065, "grad_norm": 3.7188663482666016, "learning_rate": 7.042171060970213e-06, "loss": 0.139, "step": 361250 }, { "epoch": 2.1474044617222745, "grad_norm": 4.077926158905029, "learning_rate": 7.0419816629376505e-06, "loss": 0.1444, "step": 361260 }, { "epoch": 2.147463903798943, "grad_norm": 4.007465362548828, "learning_rate": 7.041792261388553e-06, "loss": 0.1642, "step": 361270 }, { "epoch": 2.1475233458756113, "grad_norm": 4.488755702972412, "learning_rate": 7.041602856323246e-06, "loss": 0.154, "step": 361280 }, { "epoch": 2.1475827879522797, "grad_norm": 3.4503889083862305, "learning_rate": 7.0414134477420544e-06, "loss": 0.1177, "step": 361290 }, { "epoch": 2.147642230028948, "grad_norm": 3.50911808013916, "learning_rate": 7.041224035645307e-06, "loss": 0.1571, "step": 361300 }, { "epoch": 2.1477016721056166, "grad_norm": 4.608484268188477, "learning_rate": 7.041034620033327e-06, "loss": 0.1525, "step": 361310 }, { "epoch": 2.147761114182285, "grad_norm": 3.9808616638183594, "learning_rate": 7.040845200906442e-06, "loss": 0.1379, "step": 361320 }, { "epoch": 2.1478205562589534, "grad_norm": 3.91082501411438, "learning_rate": 7.040655778264978e-06, "loss": 0.1599, "step": 361330 }, { "epoch": 2.147879998335622, "grad_norm": 6.083398818969727, "learning_rate": 7.040466352109262e-06, "loss": 0.151, "step": 361340 }, { "epoch": 2.1479394404122902, "grad_norm": 3.1448638439178467, "learning_rate": 7.040276922439619e-06, "loss": 0.1636, "step": 361350 }, { "epoch": 2.1479988824889586, "grad_norm": 3.8232226371765137, "learning_rate": 7.040087489256373e-06, "loss": 0.1412, "step": 361360 }, { "epoch": 2.148058324565627, "grad_norm": 2.4492335319519043, "learning_rate": 7.039898052559857e-06, "loss": 0.1679, "step": 361370 }, { "epoch": 2.1481177666422955, "grad_norm": 4.502462387084961, "learning_rate": 7.039708612350391e-06, "loss": 0.1483, "step": 361380 }, { "epoch": 2.148177208718964, "grad_norm": 3.9199182987213135, "learning_rate": 7.039519168628304e-06, "loss": 0.1729, "step": 361390 }, { "epoch": 2.1482366507956323, "grad_norm": 4.895991325378418, "learning_rate": 7.039329721393921e-06, "loss": 0.1495, "step": 361400 }, { "epoch": 2.1482960928723007, "grad_norm": 4.401675224304199, "learning_rate": 7.039140270647571e-06, "loss": 0.1551, "step": 361410 }, { "epoch": 2.148355534948969, "grad_norm": 4.364958763122559, "learning_rate": 7.038950816389576e-06, "loss": 0.1492, "step": 361420 }, { "epoch": 2.1484149770256376, "grad_norm": 3.9855263233184814, "learning_rate": 7.038761358620265e-06, "loss": 0.1392, "step": 361430 }, { "epoch": 2.148474419102306, "grad_norm": 3.993135690689087, "learning_rate": 7.038571897339964e-06, "loss": 0.1564, "step": 361440 }, { "epoch": 2.148533861178974, "grad_norm": 5.3870015144348145, "learning_rate": 7.038382432548998e-06, "loss": 0.1601, "step": 361450 }, { "epoch": 2.1485933032556424, "grad_norm": 6.498764991760254, "learning_rate": 7.038192964247695e-06, "loss": 0.1606, "step": 361460 }, { "epoch": 2.1486527453323108, "grad_norm": 4.996857643127441, "learning_rate": 7.03800349243638e-06, "loss": 0.1588, "step": 361470 }, { "epoch": 2.148712187408979, "grad_norm": 3.3678605556488037, "learning_rate": 7.03781401711538e-06, "loss": 0.1417, "step": 361480 }, { "epoch": 2.1487716294856476, "grad_norm": 5.350611209869385, "learning_rate": 7.0376245382850215e-06, "loss": 0.1639, "step": 361490 }, { "epoch": 2.148831071562316, "grad_norm": 3.0107245445251465, "learning_rate": 7.0374350559456305e-06, "loss": 0.1522, "step": 361500 }, { "epoch": 2.1488905136389844, "grad_norm": 4.00246524810791, "learning_rate": 7.037245570097534e-06, "loss": 0.1494, "step": 361510 }, { "epoch": 2.148949955715653, "grad_norm": 6.317199230194092, "learning_rate": 7.037056080741056e-06, "loss": 0.1471, "step": 361520 }, { "epoch": 2.1490093977923213, "grad_norm": 5.118170738220215, "learning_rate": 7.036866587876525e-06, "loss": 0.165, "step": 361530 }, { "epoch": 2.1490688398689897, "grad_norm": 5.453000545501709, "learning_rate": 7.0366770915042674e-06, "loss": 0.151, "step": 361540 }, { "epoch": 2.149128281945658, "grad_norm": 5.975435256958008, "learning_rate": 7.036487591624607e-06, "loss": 0.1534, "step": 361550 }, { "epoch": 2.1491877240223265, "grad_norm": 4.043334007263184, "learning_rate": 7.036298088237873e-06, "loss": 0.1296, "step": 361560 }, { "epoch": 2.149247166098995, "grad_norm": 3.984907865524292, "learning_rate": 7.036108581344392e-06, "loss": 0.1385, "step": 361570 }, { "epoch": 2.1493066081756633, "grad_norm": 3.3751986026763916, "learning_rate": 7.035919070944487e-06, "loss": 0.1485, "step": 361580 }, { "epoch": 2.1493660502523317, "grad_norm": 5.036322116851807, "learning_rate": 7.035729557038486e-06, "loss": 0.1702, "step": 361590 }, { "epoch": 2.149425492329, "grad_norm": 5.438186168670654, "learning_rate": 7.035540039626718e-06, "loss": 0.1623, "step": 361600 }, { "epoch": 2.1494849344056686, "grad_norm": 3.9052531719207764, "learning_rate": 7.035350518709506e-06, "loss": 0.1446, "step": 361610 }, { "epoch": 2.149544376482337, "grad_norm": 3.8881916999816895, "learning_rate": 7.035160994287178e-06, "loss": 0.1739, "step": 361620 }, { "epoch": 2.1496038185590054, "grad_norm": 3.772455930709839, "learning_rate": 7.03497146636006e-06, "loss": 0.1542, "step": 361630 }, { "epoch": 2.1496632606356734, "grad_norm": 2.9201340675354004, "learning_rate": 7.034781934928478e-06, "loss": 0.1407, "step": 361640 }, { "epoch": 2.149722702712342, "grad_norm": 7.476024150848389, "learning_rate": 7.034592399992758e-06, "loss": 0.1583, "step": 361650 }, { "epoch": 2.14978214478901, "grad_norm": 5.566036701202393, "learning_rate": 7.034402861553229e-06, "loss": 0.1639, "step": 361660 }, { "epoch": 2.1498415868656786, "grad_norm": 3.651942014694214, "learning_rate": 7.0342133196102145e-06, "loss": 0.1472, "step": 361670 }, { "epoch": 2.149901028942347, "grad_norm": 5.409160614013672, "learning_rate": 7.034023774164041e-06, "loss": 0.1702, "step": 361680 }, { "epoch": 2.1499604710190154, "grad_norm": 4.803881645202637, "learning_rate": 7.033834225215036e-06, "loss": 0.1773, "step": 361690 }, { "epoch": 2.150019913095684, "grad_norm": 4.012754440307617, "learning_rate": 7.033644672763527e-06, "loss": 0.1492, "step": 361700 }, { "epoch": 2.1500793551723523, "grad_norm": 3.6634786128997803, "learning_rate": 7.033455116809839e-06, "loss": 0.151, "step": 361710 }, { "epoch": 2.1501387972490207, "grad_norm": 4.672813415527344, "learning_rate": 7.033265557354298e-06, "loss": 0.1483, "step": 361720 }, { "epoch": 2.150198239325689, "grad_norm": 6.076969146728516, "learning_rate": 7.033075994397232e-06, "loss": 0.1469, "step": 361730 }, { "epoch": 2.1502576814023575, "grad_norm": 4.832533359527588, "learning_rate": 7.032886427938965e-06, "loss": 0.1494, "step": 361740 }, { "epoch": 2.150317123479026, "grad_norm": 4.908413887023926, "learning_rate": 7.032696857979827e-06, "loss": 0.158, "step": 361750 }, { "epoch": 2.1503765655556943, "grad_norm": 4.77893590927124, "learning_rate": 7.032507284520142e-06, "loss": 0.1461, "step": 361760 }, { "epoch": 2.1504360076323628, "grad_norm": 4.362532138824463, "learning_rate": 7.0323177075602364e-06, "loss": 0.1386, "step": 361770 }, { "epoch": 2.150495449709031, "grad_norm": 3.1575429439544678, "learning_rate": 7.032128127100437e-06, "loss": 0.1601, "step": 361780 }, { "epoch": 2.1505548917856996, "grad_norm": 4.60756778717041, "learning_rate": 7.031938543141072e-06, "loss": 0.151, "step": 361790 }, { "epoch": 2.150614333862368, "grad_norm": 3.400944471359253, "learning_rate": 7.0317489556824635e-06, "loss": 0.1704, "step": 361800 }, { "epoch": 2.1506737759390364, "grad_norm": 4.501847743988037, "learning_rate": 7.031559364724943e-06, "loss": 0.162, "step": 361810 }, { "epoch": 2.150733218015705, "grad_norm": 4.144947052001953, "learning_rate": 7.031369770268834e-06, "loss": 0.1404, "step": 361820 }, { "epoch": 2.150792660092373, "grad_norm": 3.7414348125457764, "learning_rate": 7.0311801723144646e-06, "loss": 0.163, "step": 361830 }, { "epoch": 2.150852102169041, "grad_norm": 4.203561305999756, "learning_rate": 7.03099057086216e-06, "loss": 0.147, "step": 361840 }, { "epoch": 2.1509115442457096, "grad_norm": 3.537310838699341, "learning_rate": 7.030800965912248e-06, "loss": 0.1666, "step": 361850 }, { "epoch": 2.150970986322378, "grad_norm": 4.749599456787109, "learning_rate": 7.030611357465055e-06, "loss": 0.156, "step": 361860 }, { "epoch": 2.1510304283990465, "grad_norm": 5.352370738983154, "learning_rate": 7.030421745520904e-06, "loss": 0.1565, "step": 361870 }, { "epoch": 2.151089870475715, "grad_norm": 5.213918685913086, "learning_rate": 7.030232130080128e-06, "loss": 0.1532, "step": 361880 }, { "epoch": 2.1511493125523833, "grad_norm": 4.200520038604736, "learning_rate": 7.03004251114305e-06, "loss": 0.1464, "step": 361890 }, { "epoch": 2.1512087546290517, "grad_norm": 5.19464635848999, "learning_rate": 7.029852888709994e-06, "loss": 0.1503, "step": 361900 }, { "epoch": 2.15126819670572, "grad_norm": 4.312294006347656, "learning_rate": 7.0296632627812885e-06, "loss": 0.1436, "step": 361910 }, { "epoch": 2.1513276387823885, "grad_norm": 4.9258575439453125, "learning_rate": 7.029473633357263e-06, "loss": 0.1692, "step": 361920 }, { "epoch": 2.151387080859057, "grad_norm": 4.419933795928955, "learning_rate": 7.0292840004382415e-06, "loss": 0.1603, "step": 361930 }, { "epoch": 2.1514465229357254, "grad_norm": 3.5216658115386963, "learning_rate": 7.02909436402455e-06, "loss": 0.1333, "step": 361940 }, { "epoch": 2.1515059650123938, "grad_norm": 4.631306171417236, "learning_rate": 7.0289047241165165e-06, "loss": 0.1727, "step": 361950 }, { "epoch": 2.151565407089062, "grad_norm": 4.7722296714782715, "learning_rate": 7.028715080714468e-06, "loss": 0.1573, "step": 361960 }, { "epoch": 2.1516248491657306, "grad_norm": 5.291921138763428, "learning_rate": 7.028525433818727e-06, "loss": 0.1517, "step": 361970 }, { "epoch": 2.151684291242399, "grad_norm": 4.321274757385254, "learning_rate": 7.028335783429626e-06, "loss": 0.1573, "step": 361980 }, { "epoch": 2.1517437333190674, "grad_norm": 3.9550375938415527, "learning_rate": 7.028146129547489e-06, "loss": 0.1449, "step": 361990 }, { "epoch": 2.1518031753957354, "grad_norm": 4.437930583953857, "learning_rate": 7.0279564721726405e-06, "loss": 0.1612, "step": 362000 }, { "epoch": 2.151862617472404, "grad_norm": 4.882862567901611, "learning_rate": 7.0277668113054094e-06, "loss": 0.1561, "step": 362010 }, { "epoch": 2.1519220595490722, "grad_norm": 5.049065113067627, "learning_rate": 7.0275771469461216e-06, "loss": 0.1628, "step": 362020 }, { "epoch": 2.1519815016257406, "grad_norm": 5.946536540985107, "learning_rate": 7.027387479095105e-06, "loss": 0.1386, "step": 362030 }, { "epoch": 2.152040943702409, "grad_norm": 4.364249229431152, "learning_rate": 7.027197807752684e-06, "loss": 0.1489, "step": 362040 }, { "epoch": 2.1521003857790775, "grad_norm": 4.118979454040527, "learning_rate": 7.027008132919188e-06, "loss": 0.141, "step": 362050 }, { "epoch": 2.152159827855746, "grad_norm": 4.945292949676514, "learning_rate": 7.026818454594941e-06, "loss": 0.1605, "step": 362060 }, { "epoch": 2.1522192699324143, "grad_norm": 4.642574310302734, "learning_rate": 7.026628772780272e-06, "loss": 0.1649, "step": 362070 }, { "epoch": 2.1522787120090827, "grad_norm": 3.5480031967163086, "learning_rate": 7.026439087475506e-06, "loss": 0.1578, "step": 362080 }, { "epoch": 2.152338154085751, "grad_norm": 3.750627279281616, "learning_rate": 7.02624939868097e-06, "loss": 0.1584, "step": 362090 }, { "epoch": 2.1523975961624195, "grad_norm": 3.931413412094116, "learning_rate": 7.0260597063969905e-06, "loss": 0.1646, "step": 362100 }, { "epoch": 2.152457038239088, "grad_norm": 4.080785751342773, "learning_rate": 7.025870010623894e-06, "loss": 0.1661, "step": 362110 }, { "epoch": 2.1525164803157564, "grad_norm": 3.280508518218994, "learning_rate": 7.025680311362009e-06, "loss": 0.1765, "step": 362120 }, { "epoch": 2.152575922392425, "grad_norm": 4.012807369232178, "learning_rate": 7.025490608611659e-06, "loss": 0.1416, "step": 362130 }, { "epoch": 2.152635364469093, "grad_norm": 3.5368852615356445, "learning_rate": 7.0253009023731735e-06, "loss": 0.1421, "step": 362140 }, { "epoch": 2.1526948065457616, "grad_norm": 3.9163124561309814, "learning_rate": 7.025111192646879e-06, "loss": 0.1451, "step": 362150 }, { "epoch": 2.15275424862243, "grad_norm": 3.0069899559020996, "learning_rate": 7.0249214794331e-06, "loss": 0.1394, "step": 362160 }, { "epoch": 2.1528136906990984, "grad_norm": 4.703362464904785, "learning_rate": 7.024731762732164e-06, "loss": 0.1382, "step": 362170 }, { "epoch": 2.152873132775767, "grad_norm": 4.987075328826904, "learning_rate": 7.0245420425444e-06, "loss": 0.1588, "step": 362180 }, { "epoch": 2.152932574852435, "grad_norm": 4.243566989898682, "learning_rate": 7.024352318870133e-06, "loss": 0.1546, "step": 362190 }, { "epoch": 2.1529920169291032, "grad_norm": 3.124359369277954, "learning_rate": 7.024162591709689e-06, "loss": 0.141, "step": 362200 }, { "epoch": 2.1530514590057717, "grad_norm": 3.3860416412353516, "learning_rate": 7.023972861063396e-06, "loss": 0.1353, "step": 362210 }, { "epoch": 2.15311090108244, "grad_norm": 4.1313323974609375, "learning_rate": 7.023783126931581e-06, "loss": 0.1437, "step": 362220 }, { "epoch": 2.1531703431591085, "grad_norm": 3.563572406768799, "learning_rate": 7.023593389314568e-06, "loss": 0.144, "step": 362230 }, { "epoch": 2.153229785235777, "grad_norm": 4.265011310577393, "learning_rate": 7.023403648212686e-06, "loss": 0.1505, "step": 362240 }, { "epoch": 2.1532892273124453, "grad_norm": 4.007582187652588, "learning_rate": 7.023213903626262e-06, "loss": 0.174, "step": 362250 }, { "epoch": 2.1533486693891137, "grad_norm": 5.736828327178955, "learning_rate": 7.023024155555623e-06, "loss": 0.1513, "step": 362260 }, { "epoch": 2.153408111465782, "grad_norm": 4.623603820800781, "learning_rate": 7.022834404001094e-06, "loss": 0.1587, "step": 362270 }, { "epoch": 2.1534675535424506, "grad_norm": 3.2754364013671875, "learning_rate": 7.022644648963004e-06, "loss": 0.156, "step": 362280 }, { "epoch": 2.153526995619119, "grad_norm": 4.133121013641357, "learning_rate": 7.022454890441679e-06, "loss": 0.1409, "step": 362290 }, { "epoch": 2.1535864376957874, "grad_norm": 4.5786871910095215, "learning_rate": 7.022265128437444e-06, "loss": 0.1764, "step": 362300 }, { "epoch": 2.153645879772456, "grad_norm": 6.84028434753418, "learning_rate": 7.022075362950627e-06, "loss": 0.1538, "step": 362310 }, { "epoch": 2.153705321849124, "grad_norm": 5.489261150360107, "learning_rate": 7.0218855939815555e-06, "loss": 0.1635, "step": 362320 }, { "epoch": 2.1537647639257926, "grad_norm": 3.175182819366455, "learning_rate": 7.021695821530555e-06, "loss": 0.142, "step": 362330 }, { "epoch": 2.153824206002461, "grad_norm": 5.686273574829102, "learning_rate": 7.021506045597955e-06, "loss": 0.1671, "step": 362340 }, { "epoch": 2.1538836480791295, "grad_norm": 3.9281461238861084, "learning_rate": 7.0213162661840776e-06, "loss": 0.1392, "step": 362350 }, { "epoch": 2.153943090155798, "grad_norm": 3.9685847759246826, "learning_rate": 7.021126483289253e-06, "loss": 0.1424, "step": 362360 }, { "epoch": 2.1540025322324663, "grad_norm": 4.700834274291992, "learning_rate": 7.020936696913809e-06, "loss": 0.1581, "step": 362370 }, { "epoch": 2.1540619743091343, "grad_norm": 3.996330976486206, "learning_rate": 7.0207469070580704e-06, "loss": 0.1484, "step": 362380 }, { "epoch": 2.1541214163858027, "grad_norm": 4.568392753601074, "learning_rate": 7.020557113722364e-06, "loss": 0.1562, "step": 362390 }, { "epoch": 2.154180858462471, "grad_norm": 3.1859285831451416, "learning_rate": 7.0203673169070175e-06, "loss": 0.1337, "step": 362400 }, { "epoch": 2.1542403005391395, "grad_norm": 3.9503514766693115, "learning_rate": 7.020177516612358e-06, "loss": 0.1359, "step": 362410 }, { "epoch": 2.154299742615808, "grad_norm": 4.4530744552612305, "learning_rate": 7.019987712838709e-06, "loss": 0.1376, "step": 362420 }, { "epoch": 2.1543591846924763, "grad_norm": 3.4845595359802246, "learning_rate": 7.019797905586404e-06, "loss": 0.1526, "step": 362430 }, { "epoch": 2.1544186267691448, "grad_norm": 5.128663063049316, "learning_rate": 7.019608094855765e-06, "loss": 0.1401, "step": 362440 }, { "epoch": 2.154478068845813, "grad_norm": 4.018523216247559, "learning_rate": 7.019418280647119e-06, "loss": 0.1475, "step": 362450 }, { "epoch": 2.1545375109224816, "grad_norm": 4.304973125457764, "learning_rate": 7.019228462960792e-06, "loss": 0.1679, "step": 362460 }, { "epoch": 2.15459695299915, "grad_norm": 3.9600765705108643, "learning_rate": 7.0190386417971155e-06, "loss": 0.1616, "step": 362470 }, { "epoch": 2.1546563950758184, "grad_norm": 4.960200786590576, "learning_rate": 7.018848817156413e-06, "loss": 0.1421, "step": 362480 }, { "epoch": 2.154715837152487, "grad_norm": 5.671098232269287, "learning_rate": 7.018658989039011e-06, "loss": 0.1533, "step": 362490 }, { "epoch": 2.1547752792291552, "grad_norm": 4.49697732925415, "learning_rate": 7.018469157445238e-06, "loss": 0.1526, "step": 362500 }, { "epoch": 2.1548347213058237, "grad_norm": 3.9312331676483154, "learning_rate": 7.018279322375421e-06, "loss": 0.1408, "step": 362510 }, { "epoch": 2.154894163382492, "grad_norm": 3.7038774490356445, "learning_rate": 7.018089483829884e-06, "loss": 0.1511, "step": 362520 }, { "epoch": 2.1549536054591605, "grad_norm": 3.5899417400360107, "learning_rate": 7.017899641808959e-06, "loss": 0.1364, "step": 362530 }, { "epoch": 2.155013047535829, "grad_norm": 4.076452255249023, "learning_rate": 7.017709796312968e-06, "loss": 0.133, "step": 362540 }, { "epoch": 2.155072489612497, "grad_norm": 4.6838297843933105, "learning_rate": 7.017519947342241e-06, "loss": 0.1521, "step": 362550 }, { "epoch": 2.1551319316891657, "grad_norm": 4.277061939239502, "learning_rate": 7.0173300948971034e-06, "loss": 0.1718, "step": 362560 }, { "epoch": 2.1551913737658337, "grad_norm": 4.5087890625, "learning_rate": 7.017140238977882e-06, "loss": 0.178, "step": 362570 }, { "epoch": 2.155250815842502, "grad_norm": 3.904729127883911, "learning_rate": 7.0169503795849055e-06, "loss": 0.1616, "step": 362580 }, { "epoch": 2.1553102579191705, "grad_norm": 3.6759700775146484, "learning_rate": 7.0167605167185e-06, "loss": 0.135, "step": 362590 }, { "epoch": 2.155369699995839, "grad_norm": 3.335970401763916, "learning_rate": 7.016570650378991e-06, "loss": 0.1444, "step": 362600 }, { "epoch": 2.1554291420725074, "grad_norm": 3.415121078491211, "learning_rate": 7.016380780566707e-06, "loss": 0.1604, "step": 362610 }, { "epoch": 2.1554885841491758, "grad_norm": 3.3391635417938232, "learning_rate": 7.0161909072819756e-06, "loss": 0.1423, "step": 362620 }, { "epoch": 2.155548026225844, "grad_norm": 3.212327241897583, "learning_rate": 7.016001030525122e-06, "loss": 0.1488, "step": 362630 }, { "epoch": 2.1556074683025126, "grad_norm": 3.71742582321167, "learning_rate": 7.015811150296476e-06, "loss": 0.1477, "step": 362640 }, { "epoch": 2.155666910379181, "grad_norm": 4.584391117095947, "learning_rate": 7.0156212665963595e-06, "loss": 0.1306, "step": 362650 }, { "epoch": 2.1557263524558494, "grad_norm": 3.7527196407318115, "learning_rate": 7.015431379425105e-06, "loss": 0.167, "step": 362660 }, { "epoch": 2.155785794532518, "grad_norm": 4.1757001876831055, "learning_rate": 7.015241488783038e-06, "loss": 0.1593, "step": 362670 }, { "epoch": 2.1558452366091863, "grad_norm": 3.042707681655884, "learning_rate": 7.015051594670481e-06, "loss": 0.1395, "step": 362680 }, { "epoch": 2.1559046786858547, "grad_norm": 3.788433790206909, "learning_rate": 7.014861697087767e-06, "loss": 0.1408, "step": 362690 }, { "epoch": 2.155964120762523, "grad_norm": 4.2010884284973145, "learning_rate": 7.014671796035222e-06, "loss": 0.1739, "step": 362700 }, { "epoch": 2.1560235628391915, "grad_norm": 4.421825885772705, "learning_rate": 7.01448189151317e-06, "loss": 0.1468, "step": 362710 }, { "epoch": 2.15608300491586, "grad_norm": 3.76753306388855, "learning_rate": 7.014291983521939e-06, "loss": 0.1607, "step": 362720 }, { "epoch": 2.1561424469925283, "grad_norm": 2.86234974861145, "learning_rate": 7.014102072061859e-06, "loss": 0.1506, "step": 362730 }, { "epoch": 2.1562018890691963, "grad_norm": 3.972609043121338, "learning_rate": 7.013912157133255e-06, "loss": 0.1576, "step": 362740 }, { "epoch": 2.1562613311458647, "grad_norm": 4.784181594848633, "learning_rate": 7.013722238736453e-06, "loss": 0.1389, "step": 362750 }, { "epoch": 2.156320773222533, "grad_norm": 5.051587104797363, "learning_rate": 7.0135323168717805e-06, "loss": 0.16, "step": 362760 }, { "epoch": 2.1563802152992015, "grad_norm": 5.754075050354004, "learning_rate": 7.013342391539566e-06, "loss": 0.1687, "step": 362770 }, { "epoch": 2.15643965737587, "grad_norm": 3.6256191730499268, "learning_rate": 7.013152462740135e-06, "loss": 0.1683, "step": 362780 }, { "epoch": 2.1564990994525384, "grad_norm": 4.039967060089111, "learning_rate": 7.012962530473815e-06, "loss": 0.154, "step": 362790 }, { "epoch": 2.156558541529207, "grad_norm": 4.4255194664001465, "learning_rate": 7.012772594740936e-06, "loss": 0.1715, "step": 362800 }, { "epoch": 2.156617983605875, "grad_norm": 2.7245261669158936, "learning_rate": 7.01258265554182e-06, "loss": 0.1533, "step": 362810 }, { "epoch": 2.1566774256825436, "grad_norm": 4.232931613922119, "learning_rate": 7.012392712876796e-06, "loss": 0.1451, "step": 362820 }, { "epoch": 2.156736867759212, "grad_norm": 5.027243614196777, "learning_rate": 7.0122027667461924e-06, "loss": 0.1484, "step": 362830 }, { "epoch": 2.1567963098358804, "grad_norm": 4.19136905670166, "learning_rate": 7.012012817150337e-06, "loss": 0.1567, "step": 362840 }, { "epoch": 2.156855751912549, "grad_norm": 4.839888095855713, "learning_rate": 7.011822864089553e-06, "loss": 0.1545, "step": 362850 }, { "epoch": 2.1569151939892173, "grad_norm": 4.716050624847412, "learning_rate": 7.011632907564172e-06, "loss": 0.1475, "step": 362860 }, { "epoch": 2.1569746360658857, "grad_norm": 3.81404709815979, "learning_rate": 7.011442947574518e-06, "loss": 0.1496, "step": 362870 }, { "epoch": 2.157034078142554, "grad_norm": 8.436915397644043, "learning_rate": 7.011252984120919e-06, "loss": 0.1752, "step": 362880 }, { "epoch": 2.1570935202192225, "grad_norm": 4.224205493927002, "learning_rate": 7.0110630172037035e-06, "loss": 0.1639, "step": 362890 }, { "epoch": 2.157152962295891, "grad_norm": 4.116203308105469, "learning_rate": 7.0108730468231965e-06, "loss": 0.1559, "step": 362900 }, { "epoch": 2.1572124043725593, "grad_norm": 4.489330768585205, "learning_rate": 7.010683072979727e-06, "loss": 0.1622, "step": 362910 }, { "epoch": 2.1572718464492278, "grad_norm": 4.113739490509033, "learning_rate": 7.010493095673619e-06, "loss": 0.159, "step": 362920 }, { "epoch": 2.1573312885258957, "grad_norm": 3.80222225189209, "learning_rate": 7.010303114905206e-06, "loss": 0.1565, "step": 362930 }, { "epoch": 2.157390730602564, "grad_norm": 4.067193031311035, "learning_rate": 7.010113130674809e-06, "loss": 0.1502, "step": 362940 }, { "epoch": 2.1574501726792326, "grad_norm": 4.532808303833008, "learning_rate": 7.009923142982756e-06, "loss": 0.1527, "step": 362950 }, { "epoch": 2.157509614755901, "grad_norm": 4.390816688537598, "learning_rate": 7.009733151829378e-06, "loss": 0.153, "step": 362960 }, { "epoch": 2.1575690568325694, "grad_norm": 3.3811588287353516, "learning_rate": 7.009543157215e-06, "loss": 0.1489, "step": 362970 }, { "epoch": 2.157628498909238, "grad_norm": 3.7328243255615234, "learning_rate": 7.009353159139947e-06, "loss": 0.1339, "step": 362980 }, { "epoch": 2.157687940985906, "grad_norm": 3.4191086292266846, "learning_rate": 7.009163157604548e-06, "loss": 0.1439, "step": 362990 }, { "epoch": 2.1577473830625746, "grad_norm": 4.867154598236084, "learning_rate": 7.008973152609131e-06, "loss": 0.1675, "step": 363000 }, { "epoch": 2.157806825139243, "grad_norm": 3.7200586795806885, "learning_rate": 7.008783144154021e-06, "loss": 0.15, "step": 363010 }, { "epoch": 2.1578662672159115, "grad_norm": 6.290412902832031, "learning_rate": 7.00859313223955e-06, "loss": 0.1475, "step": 363020 }, { "epoch": 2.15792570929258, "grad_norm": 3.8013572692871094, "learning_rate": 7.008403116866039e-06, "loss": 0.1478, "step": 363030 }, { "epoch": 2.1579851513692483, "grad_norm": 3.9170916080474854, "learning_rate": 7.0082130980338194e-06, "loss": 0.1475, "step": 363040 }, { "epoch": 2.1580445934459167, "grad_norm": 4.831640243530273, "learning_rate": 7.008023075743218e-06, "loss": 0.1781, "step": 363050 }, { "epoch": 2.158104035522585, "grad_norm": 5.190426826477051, "learning_rate": 7.0078330499945615e-06, "loss": 0.1355, "step": 363060 }, { "epoch": 2.1581634775992535, "grad_norm": 5.1630120277404785, "learning_rate": 7.007643020788175e-06, "loss": 0.1607, "step": 363070 }, { "epoch": 2.158222919675922, "grad_norm": 2.8660295009613037, "learning_rate": 7.007452988124388e-06, "loss": 0.1338, "step": 363080 }, { "epoch": 2.1582823617525904, "grad_norm": 5.431210517883301, "learning_rate": 7.007262952003529e-06, "loss": 0.1573, "step": 363090 }, { "epoch": 2.1583418038292588, "grad_norm": 3.8277924060821533, "learning_rate": 7.007072912425923e-06, "loss": 0.1379, "step": 363100 }, { "epoch": 2.158401245905927, "grad_norm": 4.358890056610107, "learning_rate": 7.006882869391898e-06, "loss": 0.161, "step": 363110 }, { "epoch": 2.158460687982595, "grad_norm": 5.024554252624512, "learning_rate": 7.00669282290178e-06, "loss": 0.1619, "step": 363120 }, { "epoch": 2.1585201300592636, "grad_norm": 5.1283745765686035, "learning_rate": 7.006502772955899e-06, "loss": 0.1794, "step": 363130 }, { "epoch": 2.158579572135932, "grad_norm": 3.117142915725708, "learning_rate": 7.006312719554579e-06, "loss": 0.1558, "step": 363140 }, { "epoch": 2.1586390142126004, "grad_norm": 4.775238037109375, "learning_rate": 7.006122662698152e-06, "loss": 0.1402, "step": 363150 }, { "epoch": 2.158698456289269, "grad_norm": 4.0226593017578125, "learning_rate": 7.00593260238694e-06, "loss": 0.1466, "step": 363160 }, { "epoch": 2.1587578983659372, "grad_norm": 3.5024032592773438, "learning_rate": 7.005742538621273e-06, "loss": 0.1513, "step": 363170 }, { "epoch": 2.1588173404426056, "grad_norm": 2.9443211555480957, "learning_rate": 7.005552471401479e-06, "loss": 0.1369, "step": 363180 }, { "epoch": 2.158876782519274, "grad_norm": 4.8462653160095215, "learning_rate": 7.005362400727884e-06, "loss": 0.173, "step": 363190 }, { "epoch": 2.1589362245959425, "grad_norm": 4.462004661560059, "learning_rate": 7.005172326600816e-06, "loss": 0.1522, "step": 363200 }, { "epoch": 2.158995666672611, "grad_norm": 4.06550407409668, "learning_rate": 7.004982249020601e-06, "loss": 0.161, "step": 363210 }, { "epoch": 2.1590551087492793, "grad_norm": 3.8110976219177246, "learning_rate": 7.004792167987569e-06, "loss": 0.1496, "step": 363220 }, { "epoch": 2.1591145508259477, "grad_norm": 4.213616371154785, "learning_rate": 7.004602083502043e-06, "loss": 0.1516, "step": 363230 }, { "epoch": 2.159173992902616, "grad_norm": 4.502831935882568, "learning_rate": 7.004411995564355e-06, "loss": 0.1451, "step": 363240 }, { "epoch": 2.1592334349792845, "grad_norm": 4.350013732910156, "learning_rate": 7.004221904174831e-06, "loss": 0.1487, "step": 363250 }, { "epoch": 2.159292877055953, "grad_norm": 4.117225646972656, "learning_rate": 7.004031809333795e-06, "loss": 0.1531, "step": 363260 }, { "epoch": 2.1593523191326214, "grad_norm": 3.6320347785949707, "learning_rate": 7.003841711041579e-06, "loss": 0.1522, "step": 363270 }, { "epoch": 2.15941176120929, "grad_norm": 4.412671089172363, "learning_rate": 7.003651609298509e-06, "loss": 0.1624, "step": 363280 }, { "epoch": 2.1594712032859578, "grad_norm": 3.9591453075408936, "learning_rate": 7.003461504104911e-06, "loss": 0.1693, "step": 363290 }, { "epoch": 2.1595306453626266, "grad_norm": 4.709050178527832, "learning_rate": 7.003271395461113e-06, "loss": 0.1625, "step": 363300 }, { "epoch": 2.1595900874392946, "grad_norm": 3.2170255184173584, "learning_rate": 7.003081283367444e-06, "loss": 0.1429, "step": 363310 }, { "epoch": 2.159649529515963, "grad_norm": 4.116397857666016, "learning_rate": 7.002891167824229e-06, "loss": 0.1538, "step": 363320 }, { "epoch": 2.1597089715926314, "grad_norm": 3.583986520767212, "learning_rate": 7.002701048831796e-06, "loss": 0.1447, "step": 363330 }, { "epoch": 2.1597684136693, "grad_norm": 4.467812538146973, "learning_rate": 7.002510926390473e-06, "loss": 0.1466, "step": 363340 }, { "epoch": 2.1598278557459683, "grad_norm": 3.5173187255859375, "learning_rate": 7.002320800500588e-06, "loss": 0.16, "step": 363350 }, { "epoch": 2.1598872978226367, "grad_norm": 4.068262577056885, "learning_rate": 7.002130671162468e-06, "loss": 0.1526, "step": 363360 }, { "epoch": 2.159946739899305, "grad_norm": 4.0537214279174805, "learning_rate": 7.0019405383764385e-06, "loss": 0.1776, "step": 363370 }, { "epoch": 2.1600061819759735, "grad_norm": 5.938329219818115, "learning_rate": 7.001750402142829e-06, "loss": 0.1577, "step": 363380 }, { "epoch": 2.160065624052642, "grad_norm": 3.880950689315796, "learning_rate": 7.0015602624619685e-06, "loss": 0.1587, "step": 363390 }, { "epoch": 2.1601250661293103, "grad_norm": 4.085843086242676, "learning_rate": 7.001370119334178e-06, "loss": 0.147, "step": 363400 }, { "epoch": 2.1601845082059787, "grad_norm": 3.400641918182373, "learning_rate": 7.001179972759794e-06, "loss": 0.1516, "step": 363410 }, { "epoch": 2.160243950282647, "grad_norm": 5.245798110961914, "learning_rate": 7.000989822739137e-06, "loss": 0.1551, "step": 363420 }, { "epoch": 2.1603033923593156, "grad_norm": 5.556607723236084, "learning_rate": 7.0007996692725374e-06, "loss": 0.1418, "step": 363430 }, { "epoch": 2.160362834435984, "grad_norm": 4.217055797576904, "learning_rate": 7.000609512360322e-06, "loss": 0.1628, "step": 363440 }, { "epoch": 2.1604222765126524, "grad_norm": 2.988971710205078, "learning_rate": 7.000419352002817e-06, "loss": 0.1556, "step": 363450 }, { "epoch": 2.160481718589321, "grad_norm": 3.7759790420532227, "learning_rate": 7.000229188200354e-06, "loss": 0.1357, "step": 363460 }, { "epoch": 2.1605411606659892, "grad_norm": 5.27698278427124, "learning_rate": 7.0000390209532555e-06, "loss": 0.1689, "step": 363470 }, { "epoch": 2.160600602742657, "grad_norm": 3.915170192718506, "learning_rate": 6.999848850261851e-06, "loss": 0.1372, "step": 363480 }, { "epoch": 2.1606600448193256, "grad_norm": 4.458542346954346, "learning_rate": 6.999658676126469e-06, "loss": 0.1448, "step": 363490 }, { "epoch": 2.160719486895994, "grad_norm": 4.112795829772949, "learning_rate": 6.999468498547436e-06, "loss": 0.1535, "step": 363500 }, { "epoch": 2.1607789289726624, "grad_norm": 3.8390679359436035, "learning_rate": 6.99927831752508e-06, "loss": 0.1703, "step": 363510 }, { "epoch": 2.160838371049331, "grad_norm": 4.064817905426025, "learning_rate": 6.999088133059728e-06, "loss": 0.1461, "step": 363520 }, { "epoch": 2.1608978131259993, "grad_norm": 2.814798355102539, "learning_rate": 6.998897945151707e-06, "loss": 0.1463, "step": 363530 }, { "epoch": 2.1609572552026677, "grad_norm": 4.023253440856934, "learning_rate": 6.998707753801346e-06, "loss": 0.1405, "step": 363540 }, { "epoch": 2.161016697279336, "grad_norm": 3.7572367191314697, "learning_rate": 6.9985175590089725e-06, "loss": 0.1323, "step": 363550 }, { "epoch": 2.1610761393560045, "grad_norm": 4.592740535736084, "learning_rate": 6.998327360774911e-06, "loss": 0.1221, "step": 363560 }, { "epoch": 2.161135581432673, "grad_norm": 4.854550838470459, "learning_rate": 6.998137159099493e-06, "loss": 0.1637, "step": 363570 }, { "epoch": 2.1611950235093413, "grad_norm": 3.1816539764404297, "learning_rate": 6.9979469539830435e-06, "loss": 0.1511, "step": 363580 }, { "epoch": 2.1612544655860098, "grad_norm": 5.265096664428711, "learning_rate": 6.997756745425892e-06, "loss": 0.166, "step": 363590 }, { "epoch": 2.161313907662678, "grad_norm": 3.991907835006714, "learning_rate": 6.997566533428363e-06, "loss": 0.1416, "step": 363600 }, { "epoch": 2.1613733497393466, "grad_norm": 5.02727746963501, "learning_rate": 6.997376317990789e-06, "loss": 0.17, "step": 363610 }, { "epoch": 2.161432791816015, "grad_norm": 5.2018632888793945, "learning_rate": 6.997186099113494e-06, "loss": 0.1499, "step": 363620 }, { "epoch": 2.1614922338926834, "grad_norm": 4.738785266876221, "learning_rate": 6.996995876796805e-06, "loss": 0.1449, "step": 363630 }, { "epoch": 2.161551675969352, "grad_norm": 5.172067642211914, "learning_rate": 6.996805651041052e-06, "loss": 0.1611, "step": 363640 }, { "epoch": 2.1616111180460202, "grad_norm": 3.8198013305664062, "learning_rate": 6.996615421846561e-06, "loss": 0.1429, "step": 363650 }, { "epoch": 2.1616705601226887, "grad_norm": 3.588050127029419, "learning_rate": 6.996425189213659e-06, "loss": 0.1636, "step": 363660 }, { "epoch": 2.1617300021993566, "grad_norm": 3.7025794982910156, "learning_rate": 6.996234953142675e-06, "loss": 0.1414, "step": 363670 }, { "epoch": 2.161789444276025, "grad_norm": 5.540658473968506, "learning_rate": 6.996044713633937e-06, "loss": 0.1533, "step": 363680 }, { "epoch": 2.1618488863526935, "grad_norm": 5.204889297485352, "learning_rate": 6.995854470687771e-06, "loss": 0.1577, "step": 363690 }, { "epoch": 2.161908328429362, "grad_norm": 3.826253890991211, "learning_rate": 6.995664224304506e-06, "loss": 0.1574, "step": 363700 }, { "epoch": 2.1619677705060303, "grad_norm": 4.3642497062683105, "learning_rate": 6.99547397448447e-06, "loss": 0.1351, "step": 363710 }, { "epoch": 2.1620272125826987, "grad_norm": 3.801064968109131, "learning_rate": 6.995283721227988e-06, "loss": 0.1447, "step": 363720 }, { "epoch": 2.162086654659367, "grad_norm": 4.00745153427124, "learning_rate": 6.995093464535391e-06, "loss": 0.1683, "step": 363730 }, { "epoch": 2.1621460967360355, "grad_norm": 5.387965679168701, "learning_rate": 6.994903204407004e-06, "loss": 0.1698, "step": 363740 }, { "epoch": 2.162205538812704, "grad_norm": 4.962249279022217, "learning_rate": 6.9947129408431544e-06, "loss": 0.1539, "step": 363750 }, { "epoch": 2.1622649808893724, "grad_norm": 4.099301815032959, "learning_rate": 6.994522673844173e-06, "loss": 0.1523, "step": 363760 }, { "epoch": 2.1623244229660408, "grad_norm": 3.666673421859741, "learning_rate": 6.994332403410387e-06, "loss": 0.1616, "step": 363770 }, { "epoch": 2.162383865042709, "grad_norm": 3.7285878658294678, "learning_rate": 6.994142129542118e-06, "loss": 0.1628, "step": 363780 }, { "epoch": 2.1624433071193776, "grad_norm": 4.317564010620117, "learning_rate": 6.993951852239701e-06, "loss": 0.1518, "step": 363790 }, { "epoch": 2.162502749196046, "grad_norm": 4.307524681091309, "learning_rate": 6.9937615715034615e-06, "loss": 0.1648, "step": 363800 }, { "epoch": 2.1625621912727144, "grad_norm": 5.436416149139404, "learning_rate": 6.993571287333727e-06, "loss": 0.1563, "step": 363810 }, { "epoch": 2.162621633349383, "grad_norm": 3.947138547897339, "learning_rate": 6.9933809997308235e-06, "loss": 0.1492, "step": 363820 }, { "epoch": 2.1626810754260513, "grad_norm": 5.802157402038574, "learning_rate": 6.993190708695081e-06, "loss": 0.1391, "step": 363830 }, { "epoch": 2.1627405175027197, "grad_norm": 3.47131609916687, "learning_rate": 6.993000414226826e-06, "loss": 0.1481, "step": 363840 }, { "epoch": 2.162799959579388, "grad_norm": 5.0425705909729, "learning_rate": 6.992810116326386e-06, "loss": 0.1421, "step": 363850 }, { "epoch": 2.162859401656056, "grad_norm": 4.446433067321777, "learning_rate": 6.9926198149940904e-06, "loss": 0.1419, "step": 363860 }, { "epoch": 2.1629188437327245, "grad_norm": 5.104457855224609, "learning_rate": 6.992429510230265e-06, "loss": 0.1497, "step": 363870 }, { "epoch": 2.162978285809393, "grad_norm": 4.490411758422852, "learning_rate": 6.992239202035237e-06, "loss": 0.1855, "step": 363880 }, { "epoch": 2.1630377278860613, "grad_norm": 5.42970609664917, "learning_rate": 6.9920488904093365e-06, "loss": 0.1714, "step": 363890 }, { "epoch": 2.1630971699627297, "grad_norm": 4.628313064575195, "learning_rate": 6.99185857535289e-06, "loss": 0.1724, "step": 363900 }, { "epoch": 2.163156612039398, "grad_norm": 4.173427581787109, "learning_rate": 6.991668256866226e-06, "loss": 0.1567, "step": 363910 }, { "epoch": 2.1632160541160665, "grad_norm": 2.911125421524048, "learning_rate": 6.991477934949671e-06, "loss": 0.1303, "step": 363920 }, { "epoch": 2.163275496192735, "grad_norm": 3.917750358581543, "learning_rate": 6.991287609603554e-06, "loss": 0.1559, "step": 363930 }, { "epoch": 2.1633349382694034, "grad_norm": 5.333154201507568, "learning_rate": 6.991097280828202e-06, "loss": 0.1705, "step": 363940 }, { "epoch": 2.163394380346072, "grad_norm": 4.496612548828125, "learning_rate": 6.990906948623941e-06, "loss": 0.1497, "step": 363950 }, { "epoch": 2.16345382242274, "grad_norm": 3.605543375015259, "learning_rate": 6.9907166129911035e-06, "loss": 0.1687, "step": 363960 }, { "epoch": 2.1635132644994086, "grad_norm": 5.440232276916504, "learning_rate": 6.9905262739300135e-06, "loss": 0.1562, "step": 363970 }, { "epoch": 2.163572706576077, "grad_norm": 5.287563800811768, "learning_rate": 6.990335931440999e-06, "loss": 0.1466, "step": 363980 }, { "epoch": 2.1636321486527454, "grad_norm": 3.2916007041931152, "learning_rate": 6.9901455855243895e-06, "loss": 0.1285, "step": 363990 }, { "epoch": 2.163691590729414, "grad_norm": 4.796423435211182, "learning_rate": 6.98995523618051e-06, "loss": 0.1362, "step": 364000 }, { "epoch": 2.1637510328060823, "grad_norm": 4.371261119842529, "learning_rate": 6.989764883409692e-06, "loss": 0.1377, "step": 364010 }, { "epoch": 2.1638104748827507, "grad_norm": 4.552058219909668, "learning_rate": 6.989574527212261e-06, "loss": 0.1677, "step": 364020 }, { "epoch": 2.1638699169594187, "grad_norm": 4.18773078918457, "learning_rate": 6.989384167588546e-06, "loss": 0.1673, "step": 364030 }, { "epoch": 2.1639293590360875, "grad_norm": 4.4797563552856445, "learning_rate": 6.989193804538873e-06, "loss": 0.1341, "step": 364040 }, { "epoch": 2.1639888011127555, "grad_norm": 3.7113208770751953, "learning_rate": 6.989003438063571e-06, "loss": 0.1404, "step": 364050 }, { "epoch": 2.164048243189424, "grad_norm": 4.863835334777832, "learning_rate": 6.988813068162969e-06, "loss": 0.1512, "step": 364060 }, { "epoch": 2.1641076852660923, "grad_norm": 3.8532464504241943, "learning_rate": 6.988622694837393e-06, "loss": 0.1494, "step": 364070 }, { "epoch": 2.1641671273427607, "grad_norm": 3.386977434158325, "learning_rate": 6.9884323180871694e-06, "loss": 0.1655, "step": 364080 }, { "epoch": 2.164226569419429, "grad_norm": 3.7166385650634766, "learning_rate": 6.98824193791263e-06, "loss": 0.1613, "step": 364090 }, { "epoch": 2.1642860114960976, "grad_norm": 5.005005359649658, "learning_rate": 6.988051554314101e-06, "loss": 0.1642, "step": 364100 }, { "epoch": 2.164345453572766, "grad_norm": 5.5478291511535645, "learning_rate": 6.9878611672919095e-06, "loss": 0.1582, "step": 364110 }, { "epoch": 2.1644048956494344, "grad_norm": 4.140139579772949, "learning_rate": 6.987670776846382e-06, "loss": 0.1379, "step": 364120 }, { "epoch": 2.164464337726103, "grad_norm": 3.250570297241211, "learning_rate": 6.987480382977852e-06, "loss": 0.1536, "step": 364130 }, { "epoch": 2.164523779802771, "grad_norm": 3.369300365447998, "learning_rate": 6.987289985686642e-06, "loss": 0.1466, "step": 364140 }, { "epoch": 2.1645832218794396, "grad_norm": 3.8707587718963623, "learning_rate": 6.9870995849730805e-06, "loss": 0.146, "step": 364150 }, { "epoch": 2.164642663956108, "grad_norm": 3.0501906871795654, "learning_rate": 6.986909180837498e-06, "loss": 0.1462, "step": 364160 }, { "epoch": 2.1647021060327765, "grad_norm": 4.064630031585693, "learning_rate": 6.98671877328022e-06, "loss": 0.1488, "step": 364170 }, { "epoch": 2.164761548109445, "grad_norm": 4.593406677246094, "learning_rate": 6.986528362301574e-06, "loss": 0.1377, "step": 364180 }, { "epoch": 2.1648209901861133, "grad_norm": 4.5250749588012695, "learning_rate": 6.986337947901891e-06, "loss": 0.1722, "step": 364190 }, { "epoch": 2.1648804322627817, "grad_norm": 3.6727302074432373, "learning_rate": 6.9861475300814974e-06, "loss": 0.1438, "step": 364200 }, { "epoch": 2.16493987433945, "grad_norm": 4.351736068725586, "learning_rate": 6.985957108840719e-06, "loss": 0.1361, "step": 364210 }, { "epoch": 2.164999316416118, "grad_norm": 5.247288703918457, "learning_rate": 6.985766684179885e-06, "loss": 0.1416, "step": 364220 }, { "epoch": 2.1650587584927865, "grad_norm": 5.148336887359619, "learning_rate": 6.9855762560993256e-06, "loss": 0.1518, "step": 364230 }, { "epoch": 2.165118200569455, "grad_norm": 3.9094059467315674, "learning_rate": 6.985385824599368e-06, "loss": 0.1601, "step": 364240 }, { "epoch": 2.1651776426461233, "grad_norm": 4.925678253173828, "learning_rate": 6.9851953896803374e-06, "loss": 0.1546, "step": 364250 }, { "epoch": 2.1652370847227917, "grad_norm": 3.9075677394866943, "learning_rate": 6.985004951342563e-06, "loss": 0.1508, "step": 364260 }, { "epoch": 2.16529652679946, "grad_norm": 5.466833591461182, "learning_rate": 6.984814509586375e-06, "loss": 0.1661, "step": 364270 }, { "epoch": 2.1653559688761286, "grad_norm": 4.597862720489502, "learning_rate": 6.984624064412098e-06, "loss": 0.1698, "step": 364280 }, { "epoch": 2.165415410952797, "grad_norm": 4.464601516723633, "learning_rate": 6.984433615820062e-06, "loss": 0.1511, "step": 364290 }, { "epoch": 2.1654748530294654, "grad_norm": 4.29233980178833, "learning_rate": 6.984243163810594e-06, "loss": 0.1505, "step": 364300 }, { "epoch": 2.165534295106134, "grad_norm": 3.749612331390381, "learning_rate": 6.984052708384023e-06, "loss": 0.1629, "step": 364310 }, { "epoch": 2.1655937371828022, "grad_norm": 4.022134780883789, "learning_rate": 6.983862249540677e-06, "loss": 0.1661, "step": 364320 }, { "epoch": 2.1656531792594707, "grad_norm": 4.3911542892456055, "learning_rate": 6.983671787280884e-06, "loss": 0.1567, "step": 364330 }, { "epoch": 2.165712621336139, "grad_norm": 5.597476005554199, "learning_rate": 6.983481321604969e-06, "loss": 0.1585, "step": 364340 }, { "epoch": 2.1657720634128075, "grad_norm": 5.162365436553955, "learning_rate": 6.983290852513265e-06, "loss": 0.1785, "step": 364350 }, { "epoch": 2.165831505489476, "grad_norm": 3.807858943939209, "learning_rate": 6.983100380006096e-06, "loss": 0.1479, "step": 364360 }, { "epoch": 2.1658909475661443, "grad_norm": 4.413730144500732, "learning_rate": 6.982909904083792e-06, "loss": 0.1532, "step": 364370 }, { "epoch": 2.1659503896428127, "grad_norm": 5.017527103424072, "learning_rate": 6.982719424746681e-06, "loss": 0.1399, "step": 364380 }, { "epoch": 2.166009831719481, "grad_norm": 4.904662609100342, "learning_rate": 6.98252894199509e-06, "loss": 0.1642, "step": 364390 }, { "epoch": 2.1660692737961496, "grad_norm": 4.946044445037842, "learning_rate": 6.982338455829347e-06, "loss": 0.1546, "step": 364400 }, { "epoch": 2.1661287158728175, "grad_norm": 4.8840765953063965, "learning_rate": 6.9821479662497826e-06, "loss": 0.147, "step": 364410 }, { "epoch": 2.166188157949486, "grad_norm": 4.648124694824219, "learning_rate": 6.981957473256722e-06, "loss": 0.1609, "step": 364420 }, { "epoch": 2.1662476000261544, "grad_norm": 5.3580169677734375, "learning_rate": 6.981766976850495e-06, "loss": 0.1554, "step": 364430 }, { "epoch": 2.1663070421028228, "grad_norm": 4.42763614654541, "learning_rate": 6.981576477031426e-06, "loss": 0.1613, "step": 364440 }, { "epoch": 2.166366484179491, "grad_norm": 4.919143199920654, "learning_rate": 6.981385973799848e-06, "loss": 0.1491, "step": 364450 }, { "epoch": 2.1664259262561596, "grad_norm": 3.486647129058838, "learning_rate": 6.981195467156087e-06, "loss": 0.1429, "step": 364460 }, { "epoch": 2.166485368332828, "grad_norm": 5.529446601867676, "learning_rate": 6.98100495710047e-06, "loss": 0.1741, "step": 364470 }, { "epoch": 2.1665448104094964, "grad_norm": 5.4129719734191895, "learning_rate": 6.980814443633327e-06, "loss": 0.1464, "step": 364480 }, { "epoch": 2.166604252486165, "grad_norm": 3.3104004859924316, "learning_rate": 6.980623926754986e-06, "loss": 0.1322, "step": 364490 }, { "epoch": 2.1666636945628333, "grad_norm": 5.044924736022949, "learning_rate": 6.980433406465772e-06, "loss": 0.1585, "step": 364500 }, { "epoch": 2.1667231366395017, "grad_norm": 3.2101340293884277, "learning_rate": 6.980242882766018e-06, "loss": 0.1502, "step": 364510 }, { "epoch": 2.16678257871617, "grad_norm": 3.9642863273620605, "learning_rate": 6.980052355656048e-06, "loss": 0.1845, "step": 364520 }, { "epoch": 2.1668420207928385, "grad_norm": 3.146592855453491, "learning_rate": 6.979861825136191e-06, "loss": 0.1452, "step": 364530 }, { "epoch": 2.166901462869507, "grad_norm": 3.903167963027954, "learning_rate": 6.9796712912067756e-06, "loss": 0.1485, "step": 364540 }, { "epoch": 2.1669609049461753, "grad_norm": 4.729300498962402, "learning_rate": 6.979480753868131e-06, "loss": 0.1532, "step": 364550 }, { "epoch": 2.1670203470228437, "grad_norm": 4.056873798370361, "learning_rate": 6.979290213120584e-06, "loss": 0.1391, "step": 364560 }, { "epoch": 2.167079789099512, "grad_norm": 3.7615339756011963, "learning_rate": 6.979099668964462e-06, "loss": 0.1637, "step": 364570 }, { "epoch": 2.1671392311761806, "grad_norm": 4.630602836608887, "learning_rate": 6.978909121400096e-06, "loss": 0.1697, "step": 364580 }, { "epoch": 2.167198673252849, "grad_norm": 4.719971179962158, "learning_rate": 6.978718570427813e-06, "loss": 0.174, "step": 364590 }, { "epoch": 2.167258115329517, "grad_norm": 4.34951114654541, "learning_rate": 6.978528016047939e-06, "loss": 0.1802, "step": 364600 }, { "epoch": 2.1673175574061854, "grad_norm": 5.489035606384277, "learning_rate": 6.978337458260803e-06, "loss": 0.143, "step": 364610 }, { "epoch": 2.167376999482854, "grad_norm": 6.050212383270264, "learning_rate": 6.9781468970667355e-06, "loss": 0.1693, "step": 364620 }, { "epoch": 2.167436441559522, "grad_norm": 4.087575435638428, "learning_rate": 6.977956332466062e-06, "loss": 0.1426, "step": 364630 }, { "epoch": 2.1674958836361906, "grad_norm": 4.685608386993408, "learning_rate": 6.9777657644591124e-06, "loss": 0.1481, "step": 364640 }, { "epoch": 2.167555325712859, "grad_norm": 4.36781120300293, "learning_rate": 6.977575193046214e-06, "loss": 0.1665, "step": 364650 }, { "epoch": 2.1676147677895274, "grad_norm": 4.406320571899414, "learning_rate": 6.977384618227694e-06, "loss": 0.1585, "step": 364660 }, { "epoch": 2.167674209866196, "grad_norm": 4.011554718017578, "learning_rate": 6.977194040003883e-06, "loss": 0.1407, "step": 364670 }, { "epoch": 2.1677336519428643, "grad_norm": 4.102643966674805, "learning_rate": 6.977003458375108e-06, "loss": 0.1612, "step": 364680 }, { "epoch": 2.1677930940195327, "grad_norm": 4.87230110168457, "learning_rate": 6.976812873341696e-06, "loss": 0.1444, "step": 364690 }, { "epoch": 2.167852536096201, "grad_norm": 4.6965718269348145, "learning_rate": 6.9766222849039775e-06, "loss": 0.1508, "step": 364700 }, { "epoch": 2.1679119781728695, "grad_norm": 4.3710527420043945, "learning_rate": 6.97643169306228e-06, "loss": 0.1578, "step": 364710 }, { "epoch": 2.167971420249538, "grad_norm": 5.093521595001221, "learning_rate": 6.976241097816931e-06, "loss": 0.1593, "step": 364720 }, { "epoch": 2.1680308623262063, "grad_norm": 4.190333843231201, "learning_rate": 6.976050499168257e-06, "loss": 0.1609, "step": 364730 }, { "epoch": 2.1680903044028748, "grad_norm": 5.5947957038879395, "learning_rate": 6.97585989711659e-06, "loss": 0.1543, "step": 364740 }, { "epoch": 2.168149746479543, "grad_norm": 5.581705093383789, "learning_rate": 6.9756692916622574e-06, "loss": 0.1478, "step": 364750 }, { "epoch": 2.1682091885562116, "grad_norm": 4.392831325531006, "learning_rate": 6.975478682805585e-06, "loss": 0.1499, "step": 364760 }, { "epoch": 2.1682686306328796, "grad_norm": 4.161852836608887, "learning_rate": 6.975288070546901e-06, "loss": 0.145, "step": 364770 }, { "epoch": 2.1683280727095484, "grad_norm": 3.3499250411987305, "learning_rate": 6.975097454886539e-06, "loss": 0.1434, "step": 364780 }, { "epoch": 2.1683875147862164, "grad_norm": 5.557154178619385, "learning_rate": 6.9749068358248215e-06, "loss": 0.1399, "step": 364790 }, { "epoch": 2.168446956862885, "grad_norm": 3.0488433837890625, "learning_rate": 6.974716213362079e-06, "loss": 0.1431, "step": 364800 }, { "epoch": 2.168506398939553, "grad_norm": 4.367676258087158, "learning_rate": 6.97452558749864e-06, "loss": 0.1499, "step": 364810 }, { "epoch": 2.1685658410162216, "grad_norm": 4.573826789855957, "learning_rate": 6.974334958234833e-06, "loss": 0.1356, "step": 364820 }, { "epoch": 2.16862528309289, "grad_norm": 5.215023517608643, "learning_rate": 6.974144325570984e-06, "loss": 0.1736, "step": 364830 }, { "epoch": 2.1686847251695585, "grad_norm": 2.6591503620147705, "learning_rate": 6.973953689507423e-06, "loss": 0.1532, "step": 364840 }, { "epoch": 2.168744167246227, "grad_norm": 3.582428216934204, "learning_rate": 6.97376305004448e-06, "loss": 0.1503, "step": 364850 }, { "epoch": 2.1688036093228953, "grad_norm": 3.602065324783325, "learning_rate": 6.97357240718248e-06, "loss": 0.1582, "step": 364860 }, { "epoch": 2.1688630513995637, "grad_norm": 4.285808086395264, "learning_rate": 6.973381760921754e-06, "loss": 0.1707, "step": 364870 }, { "epoch": 2.168922493476232, "grad_norm": 3.5559914112091064, "learning_rate": 6.973191111262627e-06, "loss": 0.1384, "step": 364880 }, { "epoch": 2.1689819355529005, "grad_norm": 3.4447684288024902, "learning_rate": 6.9730004582054315e-06, "loss": 0.1355, "step": 364890 }, { "epoch": 2.169041377629569, "grad_norm": 3.676238775253296, "learning_rate": 6.972809801750492e-06, "loss": 0.1573, "step": 364900 }, { "epoch": 2.1691008197062374, "grad_norm": 4.516523361206055, "learning_rate": 6.97261914189814e-06, "loss": 0.1508, "step": 364910 }, { "epoch": 2.1691602617829058, "grad_norm": 4.746789932250977, "learning_rate": 6.972428478648703e-06, "loss": 0.1681, "step": 364920 }, { "epoch": 2.169219703859574, "grad_norm": 4.34926700592041, "learning_rate": 6.972237812002507e-06, "loss": 0.1431, "step": 364930 }, { "epoch": 2.1692791459362426, "grad_norm": 5.042492389678955, "learning_rate": 6.972047141959883e-06, "loss": 0.151, "step": 364940 }, { "epoch": 2.169338588012911, "grad_norm": 4.066435813903809, "learning_rate": 6.97185646852116e-06, "loss": 0.1458, "step": 364950 }, { "epoch": 2.169398030089579, "grad_norm": 4.339414119720459, "learning_rate": 6.971665791686662e-06, "loss": 0.1569, "step": 364960 }, { "epoch": 2.1694574721662474, "grad_norm": 5.575465679168701, "learning_rate": 6.971475111456723e-06, "loss": 0.1445, "step": 364970 }, { "epoch": 2.169516914242916, "grad_norm": 4.732605457305908, "learning_rate": 6.971284427831669e-06, "loss": 0.1527, "step": 364980 }, { "epoch": 2.1695763563195842, "grad_norm": 3.943297863006592, "learning_rate": 6.971093740811823e-06, "loss": 0.1508, "step": 364990 }, { "epoch": 2.1696357983962526, "grad_norm": 3.980419397354126, "learning_rate": 6.970903050397523e-06, "loss": 0.1592, "step": 365000 }, { "epoch": 2.169695240472921, "grad_norm": 4.497610092163086, "learning_rate": 6.9707123565890915e-06, "loss": 0.1608, "step": 365010 }, { "epoch": 2.1697546825495895, "grad_norm": 3.519503593444824, "learning_rate": 6.970521659386857e-06, "loss": 0.1602, "step": 365020 }, { "epoch": 2.169814124626258, "grad_norm": 3.7135918140411377, "learning_rate": 6.9703309587911515e-06, "loss": 0.1564, "step": 365030 }, { "epoch": 2.1698735667029263, "grad_norm": 3.1493313312530518, "learning_rate": 6.9701402548023e-06, "loss": 0.1477, "step": 365040 }, { "epoch": 2.1699330087795947, "grad_norm": 3.249502658843994, "learning_rate": 6.969949547420632e-06, "loss": 0.1368, "step": 365050 }, { "epoch": 2.169992450856263, "grad_norm": 4.549564361572266, "learning_rate": 6.969758836646475e-06, "loss": 0.1342, "step": 365060 }, { "epoch": 2.1700518929329315, "grad_norm": 4.634015083312988, "learning_rate": 6.96956812248016e-06, "loss": 0.1545, "step": 365070 }, { "epoch": 2.1701113350096, "grad_norm": 6.1300835609436035, "learning_rate": 6.969377404922012e-06, "loss": 0.1704, "step": 365080 }, { "epoch": 2.1701707770862684, "grad_norm": 4.761530876159668, "learning_rate": 6.969186683972362e-06, "loss": 0.1325, "step": 365090 }, { "epoch": 2.170230219162937, "grad_norm": 3.4966578483581543, "learning_rate": 6.968995959631537e-06, "loss": 0.1431, "step": 365100 }, { "epoch": 2.170289661239605, "grad_norm": 3.928713321685791, "learning_rate": 6.968805231899867e-06, "loss": 0.138, "step": 365110 }, { "epoch": 2.1703491033162736, "grad_norm": 3.328932762145996, "learning_rate": 6.968614500777677e-06, "loss": 0.143, "step": 365120 }, { "epoch": 2.170408545392942, "grad_norm": 3.792259693145752, "learning_rate": 6.9684237662653e-06, "loss": 0.1522, "step": 365130 }, { "epoch": 2.1704679874696104, "grad_norm": 3.708737850189209, "learning_rate": 6.9682330283630625e-06, "loss": 0.1346, "step": 365140 }, { "epoch": 2.1705274295462784, "grad_norm": 3.185540199279785, "learning_rate": 6.968042287071293e-06, "loss": 0.155, "step": 365150 }, { "epoch": 2.170586871622947, "grad_norm": 4.651548862457275, "learning_rate": 6.967851542390319e-06, "loss": 0.1357, "step": 365160 }, { "epoch": 2.1706463136996152, "grad_norm": 4.381086349487305, "learning_rate": 6.96766079432047e-06, "loss": 0.1532, "step": 365170 }, { "epoch": 2.1707057557762837, "grad_norm": 4.207214832305908, "learning_rate": 6.967470042862075e-06, "loss": 0.1657, "step": 365180 }, { "epoch": 2.170765197852952, "grad_norm": 4.223169803619385, "learning_rate": 6.9672792880154605e-06, "loss": 0.1547, "step": 365190 }, { "epoch": 2.1708246399296205, "grad_norm": 3.8421647548675537, "learning_rate": 6.967088529780958e-06, "loss": 0.145, "step": 365200 }, { "epoch": 2.170884082006289, "grad_norm": 4.981534004211426, "learning_rate": 6.966897768158894e-06, "loss": 0.1455, "step": 365210 }, { "epoch": 2.1709435240829573, "grad_norm": 4.972872257232666, "learning_rate": 6.966707003149595e-06, "loss": 0.1644, "step": 365220 }, { "epoch": 2.1710029661596257, "grad_norm": 4.208279132843018, "learning_rate": 6.966516234753395e-06, "loss": 0.1672, "step": 365230 }, { "epoch": 2.171062408236294, "grad_norm": 4.405465602874756, "learning_rate": 6.9663254629706175e-06, "loss": 0.1583, "step": 365240 }, { "epoch": 2.1711218503129626, "grad_norm": 4.300973892211914, "learning_rate": 6.966134687801593e-06, "loss": 0.1558, "step": 365250 }, { "epoch": 2.171181292389631, "grad_norm": 5.017325401306152, "learning_rate": 6.9659439092466505e-06, "loss": 0.1478, "step": 365260 }, { "epoch": 2.1712407344662994, "grad_norm": 4.214532852172852, "learning_rate": 6.96575312730612e-06, "loss": 0.1552, "step": 365270 }, { "epoch": 2.171300176542968, "grad_norm": 4.980140686035156, "learning_rate": 6.965562341980325e-06, "loss": 0.1412, "step": 365280 }, { "epoch": 2.1713596186196362, "grad_norm": 4.753242492675781, "learning_rate": 6.965371553269599e-06, "loss": 0.1562, "step": 365290 }, { "epoch": 2.1714190606963046, "grad_norm": 5.3067240715026855, "learning_rate": 6.965180761174268e-06, "loss": 0.172, "step": 365300 }, { "epoch": 2.171478502772973, "grad_norm": 3.593388080596924, "learning_rate": 6.96498996569466e-06, "loss": 0.16, "step": 365310 }, { "epoch": 2.1715379448496415, "grad_norm": 3.6279678344726562, "learning_rate": 6.964799166831106e-06, "loss": 0.1409, "step": 365320 }, { "epoch": 2.17159738692631, "grad_norm": 4.579128742218018, "learning_rate": 6.964608364583933e-06, "loss": 0.172, "step": 365330 }, { "epoch": 2.171656829002978, "grad_norm": 4.524460315704346, "learning_rate": 6.964417558953471e-06, "loss": 0.1607, "step": 365340 }, { "epoch": 2.1717162710796463, "grad_norm": 3.6056902408599854, "learning_rate": 6.964226749940046e-06, "loss": 0.1528, "step": 365350 }, { "epoch": 2.1717757131563147, "grad_norm": 3.3246095180511475, "learning_rate": 6.96403593754399e-06, "loss": 0.16, "step": 365360 }, { "epoch": 2.171835155232983, "grad_norm": 6.248096466064453, "learning_rate": 6.96384512176563e-06, "loss": 0.1916, "step": 365370 }, { "epoch": 2.1718945973096515, "grad_norm": 4.810830593109131, "learning_rate": 6.963654302605292e-06, "loss": 0.1493, "step": 365380 }, { "epoch": 2.17195403938632, "grad_norm": 2.921703577041626, "learning_rate": 6.963463480063308e-06, "loss": 0.1247, "step": 365390 }, { "epoch": 2.1720134814629883, "grad_norm": 5.675876140594482, "learning_rate": 6.963272654140008e-06, "loss": 0.155, "step": 365400 }, { "epoch": 2.1720729235396568, "grad_norm": 5.417043209075928, "learning_rate": 6.9630818248357145e-06, "loss": 0.1546, "step": 365410 }, { "epoch": 2.172132365616325, "grad_norm": 3.1290905475616455, "learning_rate": 6.962890992150761e-06, "loss": 0.1435, "step": 365420 }, { "epoch": 2.1721918076929936, "grad_norm": 4.727792263031006, "learning_rate": 6.962700156085475e-06, "loss": 0.1613, "step": 365430 }, { "epoch": 2.172251249769662, "grad_norm": 4.029587745666504, "learning_rate": 6.962509316640187e-06, "loss": 0.1434, "step": 365440 }, { "epoch": 2.1723106918463304, "grad_norm": 3.5378146171569824, "learning_rate": 6.962318473815222e-06, "loss": 0.1338, "step": 365450 }, { "epoch": 2.172370133922999, "grad_norm": 5.119649410247803, "learning_rate": 6.962127627610911e-06, "loss": 0.1545, "step": 365460 }, { "epoch": 2.1724295759996672, "grad_norm": 5.407675266265869, "learning_rate": 6.961936778027582e-06, "loss": 0.1567, "step": 365470 }, { "epoch": 2.1724890180763357, "grad_norm": 4.949507236480713, "learning_rate": 6.961745925065564e-06, "loss": 0.1585, "step": 365480 }, { "epoch": 2.172548460153004, "grad_norm": 3.971398115158081, "learning_rate": 6.961555068725185e-06, "loss": 0.1422, "step": 365490 }, { "epoch": 2.1726079022296725, "grad_norm": 4.890377521514893, "learning_rate": 6.961364209006775e-06, "loss": 0.1451, "step": 365500 }, { "epoch": 2.1726673443063405, "grad_norm": 4.7418036460876465, "learning_rate": 6.96117334591066e-06, "loss": 0.1584, "step": 365510 }, { "epoch": 2.1727267863830093, "grad_norm": 3.5670056343078613, "learning_rate": 6.960982479437173e-06, "loss": 0.1429, "step": 365520 }, { "epoch": 2.1727862284596773, "grad_norm": 3.364973306655884, "learning_rate": 6.960791609586639e-06, "loss": 0.1518, "step": 365530 }, { "epoch": 2.1728456705363457, "grad_norm": 4.452674865722656, "learning_rate": 6.960600736359385e-06, "loss": 0.1676, "step": 365540 }, { "epoch": 2.172905112613014, "grad_norm": 4.053283214569092, "learning_rate": 6.960409859755745e-06, "loss": 0.1451, "step": 365550 }, { "epoch": 2.1729645546896825, "grad_norm": 3.62713623046875, "learning_rate": 6.9602189797760476e-06, "loss": 0.1432, "step": 365560 }, { "epoch": 2.173023996766351, "grad_norm": 5.219865322113037, "learning_rate": 6.960028096420617e-06, "loss": 0.1408, "step": 365570 }, { "epoch": 2.1730834388430194, "grad_norm": 3.8431692123413086, "learning_rate": 6.9598372096897834e-06, "loss": 0.1319, "step": 365580 }, { "epoch": 2.1731428809196878, "grad_norm": 6.413296222686768, "learning_rate": 6.959646319583878e-06, "loss": 0.1364, "step": 365590 }, { "epoch": 2.173202322996356, "grad_norm": 4.025759696960449, "learning_rate": 6.959455426103228e-06, "loss": 0.151, "step": 365600 }, { "epoch": 2.1732617650730246, "grad_norm": 4.489630699157715, "learning_rate": 6.9592645292481595e-06, "loss": 0.1531, "step": 365610 }, { "epoch": 2.173321207149693, "grad_norm": 5.6960601806640625, "learning_rate": 6.9590736290190065e-06, "loss": 0.1642, "step": 365620 }, { "epoch": 2.1733806492263614, "grad_norm": 4.842651844024658, "learning_rate": 6.958882725416094e-06, "loss": 0.152, "step": 365630 }, { "epoch": 2.17344009130303, "grad_norm": 3.9468212127685547, "learning_rate": 6.958691818439751e-06, "loss": 0.1339, "step": 365640 }, { "epoch": 2.1734995333796983, "grad_norm": 3.639630079269409, "learning_rate": 6.958500908090306e-06, "loss": 0.1627, "step": 365650 }, { "epoch": 2.1735589754563667, "grad_norm": 3.5958476066589355, "learning_rate": 6.958309994368091e-06, "loss": 0.1408, "step": 365660 }, { "epoch": 2.173618417533035, "grad_norm": 4.566117286682129, "learning_rate": 6.958119077273431e-06, "loss": 0.1596, "step": 365670 }, { "epoch": 2.1736778596097035, "grad_norm": 4.4455485343933105, "learning_rate": 6.957928156806658e-06, "loss": 0.1374, "step": 365680 }, { "epoch": 2.173737301686372, "grad_norm": 6.520760536193848, "learning_rate": 6.957737232968098e-06, "loss": 0.1765, "step": 365690 }, { "epoch": 2.17379674376304, "grad_norm": 2.5385794639587402, "learning_rate": 6.9575463057580805e-06, "loss": 0.1656, "step": 365700 }, { "epoch": 2.1738561858397083, "grad_norm": 3.4218950271606445, "learning_rate": 6.957355375176935e-06, "loss": 0.1686, "step": 365710 }, { "epoch": 2.1739156279163767, "grad_norm": 4.888986110687256, "learning_rate": 6.957164441224991e-06, "loss": 0.1643, "step": 365720 }, { "epoch": 2.173975069993045, "grad_norm": 5.188470840454102, "learning_rate": 6.956973503902575e-06, "loss": 0.1703, "step": 365730 }, { "epoch": 2.1740345120697135, "grad_norm": 3.949572801589966, "learning_rate": 6.956782563210018e-06, "loss": 0.1729, "step": 365740 }, { "epoch": 2.174093954146382, "grad_norm": 4.355407238006592, "learning_rate": 6.956591619147648e-06, "loss": 0.1587, "step": 365750 }, { "epoch": 2.1741533962230504, "grad_norm": 5.012246608734131, "learning_rate": 6.956400671715792e-06, "loss": 0.171, "step": 365760 }, { "epoch": 2.174212838299719, "grad_norm": 3.5718421936035156, "learning_rate": 6.956209720914781e-06, "loss": 0.1401, "step": 365770 }, { "epoch": 2.174272280376387, "grad_norm": 4.075754165649414, "learning_rate": 6.956018766744946e-06, "loss": 0.1526, "step": 365780 }, { "epoch": 2.1743317224530556, "grad_norm": 4.035627365112305, "learning_rate": 6.9558278092066124e-06, "loss": 0.1767, "step": 365790 }, { "epoch": 2.174391164529724, "grad_norm": 5.436389923095703, "learning_rate": 6.955636848300108e-06, "loss": 0.1487, "step": 365800 }, { "epoch": 2.1744506066063924, "grad_norm": 4.0513410568237305, "learning_rate": 6.955445884025765e-06, "loss": 0.1449, "step": 365810 }, { "epoch": 2.174510048683061, "grad_norm": 4.143189907073975, "learning_rate": 6.955254916383911e-06, "loss": 0.1517, "step": 365820 }, { "epoch": 2.1745694907597293, "grad_norm": 3.856811285018921, "learning_rate": 6.955063945374874e-06, "loss": 0.1581, "step": 365830 }, { "epoch": 2.1746289328363977, "grad_norm": 3.3021790981292725, "learning_rate": 6.954872970998985e-06, "loss": 0.1459, "step": 365840 }, { "epoch": 2.174688374913066, "grad_norm": 3.5899829864501953, "learning_rate": 6.954681993256571e-06, "loss": 0.1519, "step": 365850 }, { "epoch": 2.1747478169897345, "grad_norm": 4.751129150390625, "learning_rate": 6.954491012147961e-06, "loss": 0.1625, "step": 365860 }, { "epoch": 2.174807259066403, "grad_norm": 4.714295387268066, "learning_rate": 6.954300027673482e-06, "loss": 0.1448, "step": 365870 }, { "epoch": 2.1748667011430713, "grad_norm": 4.157104969024658, "learning_rate": 6.954109039833468e-06, "loss": 0.1394, "step": 365880 }, { "epoch": 2.1749261432197393, "grad_norm": 3.935931444168091, "learning_rate": 6.953918048628245e-06, "loss": 0.1651, "step": 365890 }, { "epoch": 2.1749855852964077, "grad_norm": 5.4700446128845215, "learning_rate": 6.953727054058141e-06, "loss": 0.1437, "step": 365900 }, { "epoch": 2.175045027373076, "grad_norm": 5.094454288482666, "learning_rate": 6.953536056123486e-06, "loss": 0.1425, "step": 365910 }, { "epoch": 2.1751044694497446, "grad_norm": 3.146615505218506, "learning_rate": 6.95334505482461e-06, "loss": 0.1466, "step": 365920 }, { "epoch": 2.175163911526413, "grad_norm": 3.7181100845336914, "learning_rate": 6.953154050161839e-06, "loss": 0.154, "step": 365930 }, { "epoch": 2.1752233536030814, "grad_norm": 5.487703323364258, "learning_rate": 6.9529630421355055e-06, "loss": 0.1569, "step": 365940 }, { "epoch": 2.17528279567975, "grad_norm": 5.211573600769043, "learning_rate": 6.9527720307459355e-06, "loss": 0.1326, "step": 365950 }, { "epoch": 2.175342237756418, "grad_norm": 3.738999128341675, "learning_rate": 6.952581015993459e-06, "loss": 0.1603, "step": 365960 }, { "epoch": 2.1754016798330866, "grad_norm": 3.521369457244873, "learning_rate": 6.952389997878406e-06, "loss": 0.1532, "step": 365970 }, { "epoch": 2.175461121909755, "grad_norm": 5.547747611999512, "learning_rate": 6.952198976401103e-06, "loss": 0.1646, "step": 365980 }, { "epoch": 2.1755205639864235, "grad_norm": 4.2818498611450195, "learning_rate": 6.952007951561881e-06, "loss": 0.1508, "step": 365990 }, { "epoch": 2.175580006063092, "grad_norm": 5.757599830627441, "learning_rate": 6.951816923361068e-06, "loss": 0.1614, "step": 366000 }, { "epoch": 2.1756394481397603, "grad_norm": 3.926456928253174, "learning_rate": 6.951625891798994e-06, "loss": 0.1515, "step": 366010 }, { "epoch": 2.1756988902164287, "grad_norm": 4.499293327331543, "learning_rate": 6.951434856875988e-06, "loss": 0.126, "step": 366020 }, { "epoch": 2.175758332293097, "grad_norm": 5.464176654815674, "learning_rate": 6.951243818592377e-06, "loss": 0.1422, "step": 366030 }, { "epoch": 2.1758177743697655, "grad_norm": 5.76732873916626, "learning_rate": 6.951052776948492e-06, "loss": 0.1657, "step": 366040 }, { "epoch": 2.175877216446434, "grad_norm": 3.5381247997283936, "learning_rate": 6.950861731944663e-06, "loss": 0.1531, "step": 366050 }, { "epoch": 2.1759366585231024, "grad_norm": 4.6225762367248535, "learning_rate": 6.950670683581214e-06, "loss": 0.184, "step": 366060 }, { "epoch": 2.1759961005997708, "grad_norm": 6.0132975578308105, "learning_rate": 6.95047963185848e-06, "loss": 0.1496, "step": 366070 }, { "epoch": 2.1760555426764387, "grad_norm": 4.129742622375488, "learning_rate": 6.950288576776786e-06, "loss": 0.1452, "step": 366080 }, { "epoch": 2.176114984753107, "grad_norm": 3.8931705951690674, "learning_rate": 6.950097518336461e-06, "loss": 0.1545, "step": 366090 }, { "epoch": 2.1761744268297756, "grad_norm": 5.198654651641846, "learning_rate": 6.949906456537837e-06, "loss": 0.1455, "step": 366100 }, { "epoch": 2.176233868906444, "grad_norm": 4.43426513671875, "learning_rate": 6.949715391381242e-06, "loss": 0.1466, "step": 366110 }, { "epoch": 2.1762933109831124, "grad_norm": 4.109745979309082, "learning_rate": 6.949524322867005e-06, "loss": 0.1607, "step": 366120 }, { "epoch": 2.176352753059781, "grad_norm": 3.9206326007843018, "learning_rate": 6.949333250995452e-06, "loss": 0.1416, "step": 366130 }, { "epoch": 2.1764121951364492, "grad_norm": 3.3078131675720215, "learning_rate": 6.949142175766917e-06, "loss": 0.1525, "step": 366140 }, { "epoch": 2.1764716372131176, "grad_norm": 2.572584867477417, "learning_rate": 6.948951097181726e-06, "loss": 0.1594, "step": 366150 }, { "epoch": 2.176531079289786, "grad_norm": 4.021002292633057, "learning_rate": 6.9487600152402064e-06, "loss": 0.1518, "step": 366160 }, { "epoch": 2.1765905213664545, "grad_norm": 3.2697391510009766, "learning_rate": 6.948568929942693e-06, "loss": 0.143, "step": 366170 }, { "epoch": 2.176649963443123, "grad_norm": 4.606095790863037, "learning_rate": 6.94837784128951e-06, "loss": 0.1644, "step": 366180 }, { "epoch": 2.1767094055197913, "grad_norm": 4.770324230194092, "learning_rate": 6.948186749280987e-06, "loss": 0.1559, "step": 366190 }, { "epoch": 2.1767688475964597, "grad_norm": 4.033041477203369, "learning_rate": 6.947995653917454e-06, "loss": 0.1396, "step": 366200 }, { "epoch": 2.176828289673128, "grad_norm": 3.7079267501831055, "learning_rate": 6.94780455519924e-06, "loss": 0.1465, "step": 366210 }, { "epoch": 2.1768877317497966, "grad_norm": 3.955035924911499, "learning_rate": 6.947613453126674e-06, "loss": 0.1674, "step": 366220 }, { "epoch": 2.176947173826465, "grad_norm": 5.084875583648682, "learning_rate": 6.947422347700088e-06, "loss": 0.1482, "step": 366230 }, { "epoch": 2.1770066159031334, "grad_norm": 3.09999942779541, "learning_rate": 6.947231238919806e-06, "loss": 0.1487, "step": 366240 }, { "epoch": 2.1770660579798014, "grad_norm": 4.068112373352051, "learning_rate": 6.94704012678616e-06, "loss": 0.1522, "step": 366250 }, { "epoch": 2.17712550005647, "grad_norm": 4.566411972045898, "learning_rate": 6.946849011299478e-06, "loss": 0.1761, "step": 366260 }, { "epoch": 2.177184942133138, "grad_norm": 5.567168235778809, "learning_rate": 6.946657892460091e-06, "loss": 0.1654, "step": 366270 }, { "epoch": 2.1772443842098066, "grad_norm": 4.952651023864746, "learning_rate": 6.946466770268326e-06, "loss": 0.1652, "step": 366280 }, { "epoch": 2.177303826286475, "grad_norm": 3.836846113204956, "learning_rate": 6.946275644724513e-06, "loss": 0.1391, "step": 366290 }, { "epoch": 2.1773632683631434, "grad_norm": 5.2073774337768555, "learning_rate": 6.946084515828981e-06, "loss": 0.1577, "step": 366300 }, { "epoch": 2.177422710439812, "grad_norm": 5.38983678817749, "learning_rate": 6.945893383582058e-06, "loss": 0.1523, "step": 366310 }, { "epoch": 2.1774821525164803, "grad_norm": 3.5427160263061523, "learning_rate": 6.9457022479840766e-06, "loss": 0.1467, "step": 366320 }, { "epoch": 2.1775415945931487, "grad_norm": 3.211977481842041, "learning_rate": 6.945511109035362e-06, "loss": 0.155, "step": 366330 }, { "epoch": 2.177601036669817, "grad_norm": 3.811465263366699, "learning_rate": 6.945319966736247e-06, "loss": 0.1498, "step": 366340 }, { "epoch": 2.1776604787464855, "grad_norm": 4.741304874420166, "learning_rate": 6.945128821087057e-06, "loss": 0.1615, "step": 366350 }, { "epoch": 2.177719920823154, "grad_norm": 3.36753249168396, "learning_rate": 6.944937672088125e-06, "loss": 0.1716, "step": 366360 }, { "epoch": 2.1777793628998223, "grad_norm": 3.484945297241211, "learning_rate": 6.944746519739778e-06, "loss": 0.1422, "step": 366370 }, { "epoch": 2.1778388049764907, "grad_norm": 3.5039124488830566, "learning_rate": 6.944555364042344e-06, "loss": 0.1461, "step": 366380 }, { "epoch": 2.177898247053159, "grad_norm": 4.835282325744629, "learning_rate": 6.944364204996155e-06, "loss": 0.1546, "step": 366390 }, { "epoch": 2.1779576891298276, "grad_norm": 4.675716876983643, "learning_rate": 6.944173042601539e-06, "loss": 0.1501, "step": 366400 }, { "epoch": 2.178017131206496, "grad_norm": 4.32124137878418, "learning_rate": 6.943981876858823e-06, "loss": 0.1541, "step": 366410 }, { "epoch": 2.1780765732831644, "grad_norm": 5.506659507751465, "learning_rate": 6.943790707768338e-06, "loss": 0.176, "step": 366420 }, { "epoch": 2.178136015359833, "grad_norm": 4.168977737426758, "learning_rate": 6.943599535330416e-06, "loss": 0.1638, "step": 366430 }, { "epoch": 2.178195457436501, "grad_norm": 4.500205993652344, "learning_rate": 6.943408359545382e-06, "loss": 0.1689, "step": 366440 }, { "epoch": 2.178254899513169, "grad_norm": 5.272002696990967, "learning_rate": 6.943217180413568e-06, "loss": 0.1559, "step": 366450 }, { "epoch": 2.1783143415898376, "grad_norm": 3.7672407627105713, "learning_rate": 6.943025997935302e-06, "loss": 0.1493, "step": 366460 }, { "epoch": 2.178373783666506, "grad_norm": 3.8167853355407715, "learning_rate": 6.942834812110914e-06, "loss": 0.1378, "step": 366470 }, { "epoch": 2.1784332257431744, "grad_norm": 3.347217559814453, "learning_rate": 6.942643622940731e-06, "loss": 0.1428, "step": 366480 }, { "epoch": 2.178492667819843, "grad_norm": 4.315155029296875, "learning_rate": 6.942452430425085e-06, "loss": 0.14, "step": 366490 }, { "epoch": 2.1785521098965113, "grad_norm": 4.03676176071167, "learning_rate": 6.9422612345643046e-06, "loss": 0.1765, "step": 366500 }, { "epoch": 2.1786115519731797, "grad_norm": 4.8382697105407715, "learning_rate": 6.942070035358717e-06, "loss": 0.149, "step": 366510 }, { "epoch": 2.178670994049848, "grad_norm": 4.190456867218018, "learning_rate": 6.9418788328086554e-06, "loss": 0.141, "step": 366520 }, { "epoch": 2.1787304361265165, "grad_norm": 3.804152727127075, "learning_rate": 6.941687626914444e-06, "loss": 0.1409, "step": 366530 }, { "epoch": 2.178789878203185, "grad_norm": 3.6149659156799316, "learning_rate": 6.941496417676416e-06, "loss": 0.1458, "step": 366540 }, { "epoch": 2.1788493202798533, "grad_norm": 4.726515293121338, "learning_rate": 6.941305205094899e-06, "loss": 0.1667, "step": 366550 }, { "epoch": 2.1789087623565218, "grad_norm": 4.037454605102539, "learning_rate": 6.941113989170224e-06, "loss": 0.1668, "step": 366560 }, { "epoch": 2.17896820443319, "grad_norm": 5.2097625732421875, "learning_rate": 6.940922769902719e-06, "loss": 0.1528, "step": 366570 }, { "epoch": 2.1790276465098586, "grad_norm": 4.941280364990234, "learning_rate": 6.940731547292713e-06, "loss": 0.1767, "step": 366580 }, { "epoch": 2.179087088586527, "grad_norm": 4.055499076843262, "learning_rate": 6.940540321340535e-06, "loss": 0.1552, "step": 366590 }, { "epoch": 2.1791465306631954, "grad_norm": 4.195815086364746, "learning_rate": 6.9403490920465166e-06, "loss": 0.1632, "step": 366600 }, { "epoch": 2.179205972739864, "grad_norm": 4.79568338394165, "learning_rate": 6.940157859410984e-06, "loss": 0.1515, "step": 366610 }, { "epoch": 2.1792654148165322, "grad_norm": 3.2080726623535156, "learning_rate": 6.939966623434269e-06, "loss": 0.1411, "step": 366620 }, { "epoch": 2.1793248568932, "grad_norm": 4.077491760253906, "learning_rate": 6.9397753841167005e-06, "loss": 0.1447, "step": 366630 }, { "epoch": 2.1793842989698686, "grad_norm": 5.06390380859375, "learning_rate": 6.939584141458605e-06, "loss": 0.1662, "step": 366640 }, { "epoch": 2.179443741046537, "grad_norm": 4.2692179679870605, "learning_rate": 6.939392895460315e-06, "loss": 0.15, "step": 366650 }, { "epoch": 2.1795031831232055, "grad_norm": 4.251706123352051, "learning_rate": 6.9392016461221614e-06, "loss": 0.1622, "step": 366660 }, { "epoch": 2.179562625199874, "grad_norm": 4.477829933166504, "learning_rate": 6.939010393444469e-06, "loss": 0.1385, "step": 366670 }, { "epoch": 2.1796220672765423, "grad_norm": 4.931601047515869, "learning_rate": 6.938819137427569e-06, "loss": 0.1508, "step": 366680 }, { "epoch": 2.1796815093532107, "grad_norm": 4.218296051025391, "learning_rate": 6.938627878071793e-06, "loss": 0.1551, "step": 366690 }, { "epoch": 2.179740951429879, "grad_norm": 4.611535549163818, "learning_rate": 6.938436615377467e-06, "loss": 0.1508, "step": 366700 }, { "epoch": 2.1798003935065475, "grad_norm": 4.311980724334717, "learning_rate": 6.938245349344923e-06, "loss": 0.1404, "step": 366710 }, { "epoch": 2.179859835583216, "grad_norm": 3.5590925216674805, "learning_rate": 6.938054079974487e-06, "loss": 0.1693, "step": 366720 }, { "epoch": 2.1799192776598844, "grad_norm": 3.0701475143432617, "learning_rate": 6.937862807266493e-06, "loss": 0.1391, "step": 366730 }, { "epoch": 2.1799787197365528, "grad_norm": 3.419403553009033, "learning_rate": 6.937671531221267e-06, "loss": 0.1465, "step": 366740 }, { "epoch": 2.180038161813221, "grad_norm": 3.3071727752685547, "learning_rate": 6.937480251839139e-06, "loss": 0.1442, "step": 366750 }, { "epoch": 2.1800976038898896, "grad_norm": 4.329983711242676, "learning_rate": 6.93728896912044e-06, "loss": 0.1435, "step": 366760 }, { "epoch": 2.180157045966558, "grad_norm": 3.0396127700805664, "learning_rate": 6.937097683065499e-06, "loss": 0.1383, "step": 366770 }, { "epoch": 2.1802164880432264, "grad_norm": 4.574542999267578, "learning_rate": 6.9369063936746425e-06, "loss": 0.1538, "step": 366780 }, { "epoch": 2.180275930119895, "grad_norm": 5.799681663513184, "learning_rate": 6.9367151009482036e-06, "loss": 0.1784, "step": 366790 }, { "epoch": 2.1803353721965633, "grad_norm": 4.8144025802612305, "learning_rate": 6.936523804886509e-06, "loss": 0.1425, "step": 366800 }, { "epoch": 2.1803948142732317, "grad_norm": 4.647202014923096, "learning_rate": 6.93633250548989e-06, "loss": 0.1807, "step": 366810 }, { "epoch": 2.1804542563498996, "grad_norm": 4.7634148597717285, "learning_rate": 6.936141202758675e-06, "loss": 0.1418, "step": 366820 }, { "epoch": 2.180513698426568, "grad_norm": 3.654585123062134, "learning_rate": 6.9359498966931945e-06, "loss": 0.1684, "step": 366830 }, { "epoch": 2.1805731405032365, "grad_norm": 4.094827651977539, "learning_rate": 6.935758587293777e-06, "loss": 0.16, "step": 366840 }, { "epoch": 2.180632582579905, "grad_norm": 3.906797170639038, "learning_rate": 6.9355672745607526e-06, "loss": 0.1572, "step": 366850 }, { "epoch": 2.1806920246565733, "grad_norm": 4.21457052230835, "learning_rate": 6.9353759584944495e-06, "loss": 0.1533, "step": 366860 }, { "epoch": 2.1807514667332417, "grad_norm": 5.617300510406494, "learning_rate": 6.935184639095197e-06, "loss": 0.1643, "step": 366870 }, { "epoch": 2.18081090880991, "grad_norm": 4.6783223152160645, "learning_rate": 6.9349933163633276e-06, "loss": 0.1461, "step": 366880 }, { "epoch": 2.1808703508865785, "grad_norm": 4.579240798950195, "learning_rate": 6.934801990299169e-06, "loss": 0.158, "step": 366890 }, { "epoch": 2.180929792963247, "grad_norm": 5.175801753997803, "learning_rate": 6.93461066090305e-06, "loss": 0.1611, "step": 366900 }, { "epoch": 2.1809892350399154, "grad_norm": 4.813558578491211, "learning_rate": 6.9344193281753e-06, "loss": 0.1551, "step": 366910 }, { "epoch": 2.181048677116584, "grad_norm": 3.970407724380493, "learning_rate": 6.9342279921162505e-06, "loss": 0.1526, "step": 366920 }, { "epoch": 2.181108119193252, "grad_norm": 4.379433631896973, "learning_rate": 6.9340366527262295e-06, "loss": 0.1457, "step": 366930 }, { "epoch": 2.1811675612699206, "grad_norm": 4.287276744842529, "learning_rate": 6.933845310005565e-06, "loss": 0.142, "step": 366940 }, { "epoch": 2.181227003346589, "grad_norm": 2.774722099304199, "learning_rate": 6.933653963954589e-06, "loss": 0.1513, "step": 366950 }, { "epoch": 2.1812864454232574, "grad_norm": 5.448459625244141, "learning_rate": 6.933462614573631e-06, "loss": 0.1558, "step": 366960 }, { "epoch": 2.181345887499926, "grad_norm": 2.5067718029022217, "learning_rate": 6.933271261863017e-06, "loss": 0.1525, "step": 366970 }, { "epoch": 2.1814053295765943, "grad_norm": 3.861506223678589, "learning_rate": 6.933079905823081e-06, "loss": 0.1328, "step": 366980 }, { "epoch": 2.1814647716532622, "grad_norm": 4.614384174346924, "learning_rate": 6.932888546454152e-06, "loss": 0.1316, "step": 366990 }, { "epoch": 2.1815242137299307, "grad_norm": 5.159577369689941, "learning_rate": 6.932697183756556e-06, "loss": 0.1399, "step": 367000 }, { "epoch": 2.181583655806599, "grad_norm": 5.046782970428467, "learning_rate": 6.9325058177306256e-06, "loss": 0.1658, "step": 367010 }, { "epoch": 2.1816430978832675, "grad_norm": 3.585779905319214, "learning_rate": 6.932314448376691e-06, "loss": 0.1502, "step": 367020 }, { "epoch": 2.181702539959936, "grad_norm": 5.086472988128662, "learning_rate": 6.932123075695079e-06, "loss": 0.1508, "step": 367030 }, { "epoch": 2.1817619820366043, "grad_norm": 3.9319417476654053, "learning_rate": 6.931931699686121e-06, "loss": 0.1515, "step": 367040 }, { "epoch": 2.1818214241132727, "grad_norm": 5.139737606048584, "learning_rate": 6.931740320350146e-06, "loss": 0.1691, "step": 367050 }, { "epoch": 2.181880866189941, "grad_norm": 3.6612322330474854, "learning_rate": 6.931548937687484e-06, "loss": 0.1478, "step": 367060 }, { "epoch": 2.1819403082666096, "grad_norm": 6.1138916015625, "learning_rate": 6.9313575516984635e-06, "loss": 0.1613, "step": 367070 }, { "epoch": 2.181999750343278, "grad_norm": 3.8712286949157715, "learning_rate": 6.931166162383415e-06, "loss": 0.1634, "step": 367080 }, { "epoch": 2.1820591924199464, "grad_norm": 3.454228401184082, "learning_rate": 6.930974769742669e-06, "loss": 0.1519, "step": 367090 }, { "epoch": 2.182118634496615, "grad_norm": 4.090106964111328, "learning_rate": 6.930783373776552e-06, "loss": 0.1336, "step": 367100 }, { "epoch": 2.182178076573283, "grad_norm": 5.122014045715332, "learning_rate": 6.9305919744853965e-06, "loss": 0.1504, "step": 367110 }, { "epoch": 2.1822375186499516, "grad_norm": 4.058366298675537, "learning_rate": 6.930400571869532e-06, "loss": 0.1602, "step": 367120 }, { "epoch": 2.18229696072662, "grad_norm": 5.564777374267578, "learning_rate": 6.930209165929287e-06, "loss": 0.1461, "step": 367130 }, { "epoch": 2.1823564028032885, "grad_norm": 4.345403671264648, "learning_rate": 6.930017756664992e-06, "loss": 0.1625, "step": 367140 }, { "epoch": 2.182415844879957, "grad_norm": 5.459379196166992, "learning_rate": 6.929826344076975e-06, "loss": 0.1606, "step": 367150 }, { "epoch": 2.1824752869566253, "grad_norm": 4.353790760040283, "learning_rate": 6.929634928165567e-06, "loss": 0.1399, "step": 367160 }, { "epoch": 2.1825347290332937, "grad_norm": 3.627552032470703, "learning_rate": 6.929443508931098e-06, "loss": 0.1453, "step": 367170 }, { "epoch": 2.1825941711099617, "grad_norm": 5.0645012855529785, "learning_rate": 6.929252086373898e-06, "loss": 0.157, "step": 367180 }, { "epoch": 2.18265361318663, "grad_norm": 3.0837650299072266, "learning_rate": 6.929060660494293e-06, "loss": 0.1419, "step": 367190 }, { "epoch": 2.1827130552632985, "grad_norm": 3.989997625350952, "learning_rate": 6.928869231292617e-06, "loss": 0.1281, "step": 367200 }, { "epoch": 2.182772497339967, "grad_norm": 4.3025689125061035, "learning_rate": 6.928677798769199e-06, "loss": 0.1599, "step": 367210 }, { "epoch": 2.1828319394166353, "grad_norm": 4.117047309875488, "learning_rate": 6.928486362924367e-06, "loss": 0.1464, "step": 367220 }, { "epoch": 2.1828913814933038, "grad_norm": 4.013848781585693, "learning_rate": 6.928294923758451e-06, "loss": 0.1451, "step": 367230 }, { "epoch": 2.182950823569972, "grad_norm": 5.087868690490723, "learning_rate": 6.928103481271781e-06, "loss": 0.1515, "step": 367240 }, { "epoch": 2.1830102656466406, "grad_norm": 3.947873592376709, "learning_rate": 6.927912035464688e-06, "loss": 0.1393, "step": 367250 }, { "epoch": 2.183069707723309, "grad_norm": 4.800354480743408, "learning_rate": 6.927720586337498e-06, "loss": 0.1466, "step": 367260 }, { "epoch": 2.1831291497999774, "grad_norm": 4.769372463226318, "learning_rate": 6.927529133890545e-06, "loss": 0.1632, "step": 367270 }, { "epoch": 2.183188591876646, "grad_norm": 4.145397186279297, "learning_rate": 6.927337678124157e-06, "loss": 0.1352, "step": 367280 }, { "epoch": 2.1832480339533142, "grad_norm": 4.6914591789245605, "learning_rate": 6.927146219038662e-06, "loss": 0.1593, "step": 367290 }, { "epoch": 2.1833074760299827, "grad_norm": 4.294382572174072, "learning_rate": 6.926954756634392e-06, "loss": 0.1477, "step": 367300 }, { "epoch": 2.183366918106651, "grad_norm": 4.549524784088135, "learning_rate": 6.926763290911676e-06, "loss": 0.1592, "step": 367310 }, { "epoch": 2.1834263601833195, "grad_norm": 4.844419956207275, "learning_rate": 6.926571821870845e-06, "loss": 0.1535, "step": 367320 }, { "epoch": 2.183485802259988, "grad_norm": 5.1363749504089355, "learning_rate": 6.9263803495122254e-06, "loss": 0.1607, "step": 367330 }, { "epoch": 2.1835452443366563, "grad_norm": 4.756186008453369, "learning_rate": 6.926188873836149e-06, "loss": 0.1538, "step": 367340 }, { "epoch": 2.1836046864133247, "grad_norm": 5.013829231262207, "learning_rate": 6.925997394842947e-06, "loss": 0.1759, "step": 367350 }, { "epoch": 2.183664128489993, "grad_norm": 4.546229839324951, "learning_rate": 6.9258059125329465e-06, "loss": 0.1293, "step": 367360 }, { "epoch": 2.183723570566661, "grad_norm": 5.848404884338379, "learning_rate": 6.925614426906479e-06, "loss": 0.1758, "step": 367370 }, { "epoch": 2.1837830126433295, "grad_norm": 3.897484540939331, "learning_rate": 6.925422937963875e-06, "loss": 0.1554, "step": 367380 }, { "epoch": 2.183842454719998, "grad_norm": 3.317887544631958, "learning_rate": 6.9252314457054605e-06, "loss": 0.1557, "step": 367390 }, { "epoch": 2.1839018967966664, "grad_norm": 4.525338172912598, "learning_rate": 6.9250399501315705e-06, "loss": 0.1539, "step": 367400 }, { "epoch": 2.1839613388733348, "grad_norm": 3.7878613471984863, "learning_rate": 6.92484845124253e-06, "loss": 0.1506, "step": 367410 }, { "epoch": 2.184020780950003, "grad_norm": 4.056155681610107, "learning_rate": 6.924656949038671e-06, "loss": 0.1486, "step": 367420 }, { "epoch": 2.1840802230266716, "grad_norm": 4.6071953773498535, "learning_rate": 6.924465443520323e-06, "loss": 0.1486, "step": 367430 }, { "epoch": 2.18413966510334, "grad_norm": 4.565104961395264, "learning_rate": 6.924273934687817e-06, "loss": 0.1502, "step": 367440 }, { "epoch": 2.1841991071800084, "grad_norm": 3.3304011821746826, "learning_rate": 6.9240824225414805e-06, "loss": 0.1497, "step": 367450 }, { "epoch": 2.184258549256677, "grad_norm": 3.405111312866211, "learning_rate": 6.923890907081644e-06, "loss": 0.1484, "step": 367460 }, { "epoch": 2.1843179913333453, "grad_norm": 3.56191086769104, "learning_rate": 6.923699388308639e-06, "loss": 0.1517, "step": 367470 }, { "epoch": 2.1843774334100137, "grad_norm": 5.137214660644531, "learning_rate": 6.923507866222794e-06, "loss": 0.1853, "step": 367480 }, { "epoch": 2.184436875486682, "grad_norm": 4.076433181762695, "learning_rate": 6.923316340824438e-06, "loss": 0.161, "step": 367490 }, { "epoch": 2.1844963175633505, "grad_norm": 5.885379791259766, "learning_rate": 6.9231248121139035e-06, "loss": 0.1603, "step": 367500 }, { "epoch": 2.184555759640019, "grad_norm": 5.38567590713501, "learning_rate": 6.9229332800915175e-06, "loss": 0.1531, "step": 367510 }, { "epoch": 2.1846152017166873, "grad_norm": 4.44619607925415, "learning_rate": 6.92274174475761e-06, "loss": 0.1335, "step": 367520 }, { "epoch": 2.1846746437933557, "grad_norm": 4.220575332641602, "learning_rate": 6.922550206112513e-06, "loss": 0.154, "step": 367530 }, { "epoch": 2.184734085870024, "grad_norm": 5.597166061401367, "learning_rate": 6.922358664156555e-06, "loss": 0.1555, "step": 367540 }, { "epoch": 2.1847935279466926, "grad_norm": 4.75788688659668, "learning_rate": 6.922167118890066e-06, "loss": 0.1467, "step": 367550 }, { "epoch": 2.1848529700233605, "grad_norm": 3.9113881587982178, "learning_rate": 6.921975570313376e-06, "loss": 0.1491, "step": 367560 }, { "epoch": 2.184912412100029, "grad_norm": 3.6394691467285156, "learning_rate": 6.921784018426816e-06, "loss": 0.157, "step": 367570 }, { "epoch": 2.1849718541766974, "grad_norm": 4.844901084899902, "learning_rate": 6.921592463230713e-06, "loss": 0.153, "step": 367580 }, { "epoch": 2.185031296253366, "grad_norm": 4.018141746520996, "learning_rate": 6.921400904725398e-06, "loss": 0.1435, "step": 367590 }, { "epoch": 2.185090738330034, "grad_norm": 5.3801140785217285, "learning_rate": 6.921209342911203e-06, "loss": 0.1616, "step": 367600 }, { "epoch": 2.1851501804067026, "grad_norm": 4.203012943267822, "learning_rate": 6.9210177777884554e-06, "loss": 0.1662, "step": 367610 }, { "epoch": 2.185209622483371, "grad_norm": 5.894570827484131, "learning_rate": 6.9208262093574856e-06, "loss": 0.1801, "step": 367620 }, { "epoch": 2.1852690645600394, "grad_norm": 3.9329051971435547, "learning_rate": 6.920634637618624e-06, "loss": 0.1643, "step": 367630 }, { "epoch": 2.185328506636708, "grad_norm": 3.479463577270508, "learning_rate": 6.920443062572201e-06, "loss": 0.155, "step": 367640 }, { "epoch": 2.1853879487133763, "grad_norm": 3.645581007003784, "learning_rate": 6.920251484218544e-06, "loss": 0.1486, "step": 367650 }, { "epoch": 2.1854473907900447, "grad_norm": 3.5363352298736572, "learning_rate": 6.920059902557988e-06, "loss": 0.1455, "step": 367660 }, { "epoch": 2.185506832866713, "grad_norm": 3.566396951675415, "learning_rate": 6.919868317590858e-06, "loss": 0.1401, "step": 367670 }, { "epoch": 2.1855662749433815, "grad_norm": 4.29167366027832, "learning_rate": 6.919676729317485e-06, "loss": 0.1816, "step": 367680 }, { "epoch": 2.18562571702005, "grad_norm": 3.7300491333007812, "learning_rate": 6.919485137738201e-06, "loss": 0.1489, "step": 367690 }, { "epoch": 2.1856851590967183, "grad_norm": 4.416759967803955, "learning_rate": 6.919293542853334e-06, "loss": 0.1526, "step": 367700 }, { "epoch": 2.1857446011733868, "grad_norm": 4.763709545135498, "learning_rate": 6.919101944663214e-06, "loss": 0.1698, "step": 367710 }, { "epoch": 2.185804043250055, "grad_norm": 3.4257540702819824, "learning_rate": 6.918910343168172e-06, "loss": 0.1551, "step": 367720 }, { "epoch": 2.185863485326723, "grad_norm": 3.089747190475464, "learning_rate": 6.9187187383685385e-06, "loss": 0.1585, "step": 367730 }, { "epoch": 2.1859229274033916, "grad_norm": 4.366833686828613, "learning_rate": 6.918527130264641e-06, "loss": 0.1392, "step": 367740 }, { "epoch": 2.18598236948006, "grad_norm": 4.851011753082275, "learning_rate": 6.91833551885681e-06, "loss": 0.1699, "step": 367750 }, { "epoch": 2.1860418115567284, "grad_norm": 4.090959548950195, "learning_rate": 6.918143904145378e-06, "loss": 0.1484, "step": 367760 }, { "epoch": 2.186101253633397, "grad_norm": 4.139373302459717, "learning_rate": 6.917952286130674e-06, "loss": 0.1363, "step": 367770 }, { "epoch": 2.186160695710065, "grad_norm": 3.9598538875579834, "learning_rate": 6.917760664813024e-06, "loss": 0.1359, "step": 367780 }, { "epoch": 2.1862201377867336, "grad_norm": 3.885295867919922, "learning_rate": 6.917569040192764e-06, "loss": 0.1495, "step": 367790 }, { "epoch": 2.186279579863402, "grad_norm": 5.086759090423584, "learning_rate": 6.917377412270222e-06, "loss": 0.149, "step": 367800 }, { "epoch": 2.1863390219400705, "grad_norm": 4.158349990844727, "learning_rate": 6.917185781045726e-06, "loss": 0.1516, "step": 367810 }, { "epoch": 2.186398464016739, "grad_norm": 5.797593593597412, "learning_rate": 6.916994146519607e-06, "loss": 0.1576, "step": 367820 }, { "epoch": 2.1864579060934073, "grad_norm": 3.4593558311462402, "learning_rate": 6.916802508692197e-06, "loss": 0.1459, "step": 367830 }, { "epoch": 2.1865173481700757, "grad_norm": 4.271207809448242, "learning_rate": 6.916610867563822e-06, "loss": 0.1516, "step": 367840 }, { "epoch": 2.186576790246744, "grad_norm": 3.3419201374053955, "learning_rate": 6.916419223134815e-06, "loss": 0.1404, "step": 367850 }, { "epoch": 2.1866362323234125, "grad_norm": 3.7134571075439453, "learning_rate": 6.9162275754055066e-06, "loss": 0.1442, "step": 367860 }, { "epoch": 2.186695674400081, "grad_norm": 4.253664493560791, "learning_rate": 6.916035924376226e-06, "loss": 0.1675, "step": 367870 }, { "epoch": 2.1867551164767494, "grad_norm": 4.169824123382568, "learning_rate": 6.915844270047301e-06, "loss": 0.1497, "step": 367880 }, { "epoch": 2.1868145585534178, "grad_norm": 4.189116477966309, "learning_rate": 6.915652612419065e-06, "loss": 0.1589, "step": 367890 }, { "epoch": 2.186874000630086, "grad_norm": 4.3846755027771, "learning_rate": 6.915460951491846e-06, "loss": 0.1457, "step": 367900 }, { "epoch": 2.1869334427067546, "grad_norm": 5.039647102355957, "learning_rate": 6.915269287265974e-06, "loss": 0.1572, "step": 367910 }, { "epoch": 2.1869928847834226, "grad_norm": 3.9129576683044434, "learning_rate": 6.915077619741781e-06, "loss": 0.1727, "step": 367920 }, { "epoch": 2.187052326860091, "grad_norm": 5.611207485198975, "learning_rate": 6.9148859489195965e-06, "loss": 0.1546, "step": 367930 }, { "epoch": 2.1871117689367594, "grad_norm": 5.330821514129639, "learning_rate": 6.9146942747997484e-06, "loss": 0.1425, "step": 367940 }, { "epoch": 2.187171211013428, "grad_norm": 5.056637287139893, "learning_rate": 6.914502597382569e-06, "loss": 0.1621, "step": 367950 }, { "epoch": 2.1872306530900962, "grad_norm": 5.459407329559326, "learning_rate": 6.914310916668386e-06, "loss": 0.1501, "step": 367960 }, { "epoch": 2.1872900951667646, "grad_norm": 3.421400547027588, "learning_rate": 6.914119232657534e-06, "loss": 0.1392, "step": 367970 }, { "epoch": 2.187349537243433, "grad_norm": 4.532994270324707, "learning_rate": 6.913927545350338e-06, "loss": 0.147, "step": 367980 }, { "epoch": 2.1874089793201015, "grad_norm": 4.416369438171387, "learning_rate": 6.913735854747132e-06, "loss": 0.1445, "step": 367990 }, { "epoch": 2.18746842139677, "grad_norm": 4.0343217849731445, "learning_rate": 6.913544160848244e-06, "loss": 0.1511, "step": 368000 }, { "epoch": 2.1875278634734383, "grad_norm": 4.238912582397461, "learning_rate": 6.913352463654004e-06, "loss": 0.154, "step": 368010 }, { "epoch": 2.1875873055501067, "grad_norm": 3.8523213863372803, "learning_rate": 6.913160763164744e-06, "loss": 0.1369, "step": 368020 }, { "epoch": 2.187646747626775, "grad_norm": 4.9825520515441895, "learning_rate": 6.9129690593807915e-06, "loss": 0.145, "step": 368030 }, { "epoch": 2.1877061897034435, "grad_norm": 3.9573071002960205, "learning_rate": 6.912777352302479e-06, "loss": 0.147, "step": 368040 }, { "epoch": 2.187765631780112, "grad_norm": 4.153215408325195, "learning_rate": 6.912585641930137e-06, "loss": 0.1466, "step": 368050 }, { "epoch": 2.1878250738567804, "grad_norm": 4.539056777954102, "learning_rate": 6.912393928264091e-06, "loss": 0.1541, "step": 368060 }, { "epoch": 2.187884515933449, "grad_norm": 3.7581892013549805, "learning_rate": 6.912202211304676e-06, "loss": 0.1407, "step": 368070 }, { "epoch": 2.187943958010117, "grad_norm": 4.417709827423096, "learning_rate": 6.91201049105222e-06, "loss": 0.1395, "step": 368080 }, { "epoch": 2.1880034000867856, "grad_norm": 4.122827053070068, "learning_rate": 6.911818767507055e-06, "loss": 0.164, "step": 368090 }, { "epoch": 2.188062842163454, "grad_norm": 4.060023307800293, "learning_rate": 6.911627040669511e-06, "loss": 0.1438, "step": 368100 }, { "epoch": 2.188122284240122, "grad_norm": 6.0553741455078125, "learning_rate": 6.911435310539915e-06, "loss": 0.1705, "step": 368110 }, { "epoch": 2.1881817263167904, "grad_norm": 3.502711296081543, "learning_rate": 6.911243577118601e-06, "loss": 0.1436, "step": 368120 }, { "epoch": 2.188241168393459, "grad_norm": 4.220454692840576, "learning_rate": 6.911051840405896e-06, "loss": 0.1574, "step": 368130 }, { "epoch": 2.1883006104701272, "grad_norm": 5.443660736083984, "learning_rate": 6.910860100402131e-06, "loss": 0.163, "step": 368140 }, { "epoch": 2.1883600525467957, "grad_norm": 3.1153645515441895, "learning_rate": 6.910668357107639e-06, "loss": 0.148, "step": 368150 }, { "epoch": 2.188419494623464, "grad_norm": 3.682859420776367, "learning_rate": 6.910476610522747e-06, "loss": 0.1619, "step": 368160 }, { "epoch": 2.1884789367001325, "grad_norm": 4.68411922454834, "learning_rate": 6.9102848606477865e-06, "loss": 0.1574, "step": 368170 }, { "epoch": 2.188538378776801, "grad_norm": 4.086399555206299, "learning_rate": 6.910093107483086e-06, "loss": 0.1264, "step": 368180 }, { "epoch": 2.1885978208534693, "grad_norm": 3.8321287631988525, "learning_rate": 6.9099013510289804e-06, "loss": 0.1552, "step": 368190 }, { "epoch": 2.1886572629301377, "grad_norm": 4.138154983520508, "learning_rate": 6.909709591285795e-06, "loss": 0.1694, "step": 368200 }, { "epoch": 2.188716705006806, "grad_norm": 6.564613342285156, "learning_rate": 6.909517828253862e-06, "loss": 0.1762, "step": 368210 }, { "epoch": 2.1887761470834746, "grad_norm": 5.5894083976745605, "learning_rate": 6.909326061933512e-06, "loss": 0.1583, "step": 368220 }, { "epoch": 2.188835589160143, "grad_norm": 4.144711494445801, "learning_rate": 6.909134292325075e-06, "loss": 0.1562, "step": 368230 }, { "epoch": 2.1888950312368114, "grad_norm": 4.950280666351318, "learning_rate": 6.90894251942888e-06, "loss": 0.1677, "step": 368240 }, { "epoch": 2.18895447331348, "grad_norm": 4.866915702819824, "learning_rate": 6.908750743245258e-06, "loss": 0.1593, "step": 368250 }, { "epoch": 2.1890139153901482, "grad_norm": 4.593710899353027, "learning_rate": 6.908558963774541e-06, "loss": 0.1526, "step": 368260 }, { "epoch": 2.1890733574668166, "grad_norm": 4.294674873352051, "learning_rate": 6.908367181017055e-06, "loss": 0.1485, "step": 368270 }, { "epoch": 2.189132799543485, "grad_norm": 4.800048351287842, "learning_rate": 6.9081753949731355e-06, "loss": 0.1588, "step": 368280 }, { "epoch": 2.1891922416201535, "grad_norm": 5.21403169631958, "learning_rate": 6.907983605643109e-06, "loss": 0.1553, "step": 368290 }, { "epoch": 2.1892516836968214, "grad_norm": 3.6682217121124268, "learning_rate": 6.907791813027307e-06, "loss": 0.1383, "step": 368300 }, { "epoch": 2.18931112577349, "grad_norm": 4.73505163192749, "learning_rate": 6.907600017126061e-06, "loss": 0.1616, "step": 368310 }, { "epoch": 2.1893705678501583, "grad_norm": 4.9621052742004395, "learning_rate": 6.9074082179397e-06, "loss": 0.1676, "step": 368320 }, { "epoch": 2.1894300099268267, "grad_norm": 3.9224295616149902, "learning_rate": 6.907216415468553e-06, "loss": 0.1422, "step": 368330 }, { "epoch": 2.189489452003495, "grad_norm": 3.9246463775634766, "learning_rate": 6.9070246097129535e-06, "loss": 0.1522, "step": 368340 }, { "epoch": 2.1895488940801635, "grad_norm": 3.979903221130371, "learning_rate": 6.906832800673229e-06, "loss": 0.1448, "step": 368350 }, { "epoch": 2.189608336156832, "grad_norm": 4.143773555755615, "learning_rate": 6.906640988349711e-06, "loss": 0.1483, "step": 368360 }, { "epoch": 2.1896677782335003, "grad_norm": 5.285088539123535, "learning_rate": 6.906449172742731e-06, "loss": 0.1706, "step": 368370 }, { "epoch": 2.1897272203101688, "grad_norm": 4.2089080810546875, "learning_rate": 6.906257353852617e-06, "loss": 0.1524, "step": 368380 }, { "epoch": 2.189786662386837, "grad_norm": 5.069377899169922, "learning_rate": 6.9060655316797e-06, "loss": 0.1648, "step": 368390 }, { "epoch": 2.1898461044635056, "grad_norm": 4.943063259124756, "learning_rate": 6.90587370622431e-06, "loss": 0.1589, "step": 368400 }, { "epoch": 2.189905546540174, "grad_norm": 4.141589641571045, "learning_rate": 6.90568187748678e-06, "loss": 0.1725, "step": 368410 }, { "epoch": 2.1899649886168424, "grad_norm": 4.490864276885986, "learning_rate": 6.905490045467438e-06, "loss": 0.1689, "step": 368420 }, { "epoch": 2.190024430693511, "grad_norm": 3.8957157135009766, "learning_rate": 6.905298210166613e-06, "loss": 0.1454, "step": 368430 }, { "epoch": 2.1900838727701792, "grad_norm": 4.891640663146973, "learning_rate": 6.905106371584639e-06, "loss": 0.1527, "step": 368440 }, { "epoch": 2.1901433148468477, "grad_norm": 4.559200286865234, "learning_rate": 6.904914529721844e-06, "loss": 0.1553, "step": 368450 }, { "epoch": 2.190202756923516, "grad_norm": 4.523942470550537, "learning_rate": 6.904722684578559e-06, "loss": 0.1545, "step": 368460 }, { "epoch": 2.190262199000184, "grad_norm": 4.670508861541748, "learning_rate": 6.904530836155115e-06, "loss": 0.1605, "step": 368470 }, { "epoch": 2.1903216410768525, "grad_norm": 5.045973777770996, "learning_rate": 6.904338984451841e-06, "loss": 0.1888, "step": 368480 }, { "epoch": 2.190381083153521, "grad_norm": 3.1050143241882324, "learning_rate": 6.904147129469067e-06, "loss": 0.1467, "step": 368490 }, { "epoch": 2.1904405252301893, "grad_norm": 5.149682998657227, "learning_rate": 6.903955271207125e-06, "loss": 0.1609, "step": 368500 }, { "epoch": 2.1904999673068577, "grad_norm": 4.481997013092041, "learning_rate": 6.903763409666345e-06, "loss": 0.1459, "step": 368510 }, { "epoch": 2.190559409383526, "grad_norm": 3.7108871936798096, "learning_rate": 6.903571544847059e-06, "loss": 0.1537, "step": 368520 }, { "epoch": 2.1906188514601945, "grad_norm": 3.3904073238372803, "learning_rate": 6.903379676749593e-06, "loss": 0.145, "step": 368530 }, { "epoch": 2.190678293536863, "grad_norm": 5.740650653839111, "learning_rate": 6.903187805374282e-06, "loss": 0.1437, "step": 368540 }, { "epoch": 2.1907377356135314, "grad_norm": 3.698671817779541, "learning_rate": 6.902995930721454e-06, "loss": 0.1451, "step": 368550 }, { "epoch": 2.1907971776901998, "grad_norm": 3.811722755432129, "learning_rate": 6.902804052791439e-06, "loss": 0.1429, "step": 368560 }, { "epoch": 2.190856619766868, "grad_norm": 4.627757549285889, "learning_rate": 6.90261217158457e-06, "loss": 0.1506, "step": 368570 }, { "epoch": 2.1909160618435366, "grad_norm": 4.925137519836426, "learning_rate": 6.9024202871011745e-06, "loss": 0.1668, "step": 368580 }, { "epoch": 2.190975503920205, "grad_norm": 3.4331932067871094, "learning_rate": 6.902228399341584e-06, "loss": 0.1576, "step": 368590 }, { "epoch": 2.1910349459968734, "grad_norm": 4.49377965927124, "learning_rate": 6.9020365083061304e-06, "loss": 0.1607, "step": 368600 }, { "epoch": 2.191094388073542, "grad_norm": 5.1970343589782715, "learning_rate": 6.901844613995143e-06, "loss": 0.1562, "step": 368610 }, { "epoch": 2.1911538301502103, "grad_norm": 3.2454073429107666, "learning_rate": 6.901652716408951e-06, "loss": 0.1399, "step": 368620 }, { "epoch": 2.1912132722268787, "grad_norm": 4.573452472686768, "learning_rate": 6.901460815547887e-06, "loss": 0.1492, "step": 368630 }, { "epoch": 2.191272714303547, "grad_norm": 5.573507785797119, "learning_rate": 6.90126891141228e-06, "loss": 0.1724, "step": 368640 }, { "epoch": 2.1913321563802155, "grad_norm": 3.0568466186523438, "learning_rate": 6.901077004002462e-06, "loss": 0.1304, "step": 368650 }, { "epoch": 2.1913915984568835, "grad_norm": 4.016946315765381, "learning_rate": 6.900885093318761e-06, "loss": 0.1499, "step": 368660 }, { "epoch": 2.191451040533552, "grad_norm": 3.6003525257110596, "learning_rate": 6.900693179361511e-06, "loss": 0.1558, "step": 368670 }, { "epoch": 2.1915104826102203, "grad_norm": 4.825428485870361, "learning_rate": 6.900501262131041e-06, "loss": 0.1543, "step": 368680 }, { "epoch": 2.1915699246868887, "grad_norm": 5.235086917877197, "learning_rate": 6.900309341627678e-06, "loss": 0.1563, "step": 368690 }, { "epoch": 2.191629366763557, "grad_norm": 2.8797528743743896, "learning_rate": 6.900117417851758e-06, "loss": 0.1488, "step": 368700 }, { "epoch": 2.1916888088402255, "grad_norm": 3.9323928356170654, "learning_rate": 6.8999254908036095e-06, "loss": 0.1316, "step": 368710 }, { "epoch": 2.191748250916894, "grad_norm": 4.9199371337890625, "learning_rate": 6.89973356048356e-06, "loss": 0.1551, "step": 368720 }, { "epoch": 2.1918076929935624, "grad_norm": 4.088125705718994, "learning_rate": 6.899541626891943e-06, "loss": 0.1783, "step": 368730 }, { "epoch": 2.191867135070231, "grad_norm": 4.384769439697266, "learning_rate": 6.899349690029091e-06, "loss": 0.1464, "step": 368740 }, { "epoch": 2.191926577146899, "grad_norm": 4.9311723709106445, "learning_rate": 6.899157749895331e-06, "loss": 0.1362, "step": 368750 }, { "epoch": 2.1919860192235676, "grad_norm": 4.6180949211120605, "learning_rate": 6.898965806490995e-06, "loss": 0.149, "step": 368760 }, { "epoch": 2.192045461300236, "grad_norm": 3.9165453910827637, "learning_rate": 6.898773859816414e-06, "loss": 0.1291, "step": 368770 }, { "epoch": 2.1921049033769044, "grad_norm": 3.905803918838501, "learning_rate": 6.898581909871916e-06, "loss": 0.1681, "step": 368780 }, { "epoch": 2.192164345453573, "grad_norm": 5.079325199127197, "learning_rate": 6.898389956657834e-06, "loss": 0.1448, "step": 368790 }, { "epoch": 2.1922237875302413, "grad_norm": 4.431026935577393, "learning_rate": 6.898198000174499e-06, "loss": 0.1423, "step": 368800 }, { "epoch": 2.1922832296069097, "grad_norm": 6.814741611480713, "learning_rate": 6.898006040422241e-06, "loss": 0.1678, "step": 368810 }, { "epoch": 2.192342671683578, "grad_norm": 3.5333564281463623, "learning_rate": 6.897814077401388e-06, "loss": 0.1386, "step": 368820 }, { "epoch": 2.1924021137602465, "grad_norm": 4.562617301940918, "learning_rate": 6.897622111112274e-06, "loss": 0.1687, "step": 368830 }, { "epoch": 2.192461555836915, "grad_norm": 4.450722694396973, "learning_rate": 6.897430141555228e-06, "loss": 0.1823, "step": 368840 }, { "epoch": 2.192520997913583, "grad_norm": 7.181494235992432, "learning_rate": 6.89723816873058e-06, "loss": 0.1611, "step": 368850 }, { "epoch": 2.1925804399902513, "grad_norm": 3.4309842586517334, "learning_rate": 6.897046192638664e-06, "loss": 0.1541, "step": 368860 }, { "epoch": 2.1926398820669197, "grad_norm": 3.9223334789276123, "learning_rate": 6.896854213279805e-06, "loss": 0.1272, "step": 368870 }, { "epoch": 2.192699324143588, "grad_norm": 5.003849983215332, "learning_rate": 6.896662230654339e-06, "loss": 0.1437, "step": 368880 }, { "epoch": 2.1927587662202566, "grad_norm": 5.421964168548584, "learning_rate": 6.896470244762593e-06, "loss": 0.1596, "step": 368890 }, { "epoch": 2.192818208296925, "grad_norm": 3.890455722808838, "learning_rate": 6.8962782556049e-06, "loss": 0.135, "step": 368900 }, { "epoch": 2.1928776503735934, "grad_norm": 4.361952304840088, "learning_rate": 6.896086263181589e-06, "loss": 0.1388, "step": 368910 }, { "epoch": 2.192937092450262, "grad_norm": 2.9180572032928467, "learning_rate": 6.895894267492992e-06, "loss": 0.1443, "step": 368920 }, { "epoch": 2.19299653452693, "grad_norm": 5.7581868171691895, "learning_rate": 6.895702268539438e-06, "loss": 0.1423, "step": 368930 }, { "epoch": 2.1930559766035986, "grad_norm": 4.9996418952941895, "learning_rate": 6.895510266321259e-06, "loss": 0.1842, "step": 368940 }, { "epoch": 2.193115418680267, "grad_norm": 3.7659287452697754, "learning_rate": 6.895318260838783e-06, "loss": 0.1582, "step": 368950 }, { "epoch": 2.1931748607569355, "grad_norm": 4.025391578674316, "learning_rate": 6.8951262520923454e-06, "loss": 0.146, "step": 368960 }, { "epoch": 2.193234302833604, "grad_norm": 4.135846138000488, "learning_rate": 6.8949342400822735e-06, "loss": 0.1424, "step": 368970 }, { "epoch": 2.1932937449102723, "grad_norm": 4.681338787078857, "learning_rate": 6.894742224808899e-06, "loss": 0.1522, "step": 368980 }, { "epoch": 2.1933531869869407, "grad_norm": 6.014819145202637, "learning_rate": 6.894550206272552e-06, "loss": 0.1676, "step": 368990 }, { "epoch": 2.193412629063609, "grad_norm": 5.6727519035339355, "learning_rate": 6.894358184473564e-06, "loss": 0.1659, "step": 369000 }, { "epoch": 2.1934720711402775, "grad_norm": 5.9773125648498535, "learning_rate": 6.894166159412264e-06, "loss": 0.1479, "step": 369010 }, { "epoch": 2.193531513216946, "grad_norm": 4.111154079437256, "learning_rate": 6.893974131088985e-06, "loss": 0.1483, "step": 369020 }, { "epoch": 2.1935909552936144, "grad_norm": 3.588611364364624, "learning_rate": 6.893782099504057e-06, "loss": 0.146, "step": 369030 }, { "epoch": 2.1936503973702823, "grad_norm": 3.514385938644409, "learning_rate": 6.893590064657809e-06, "loss": 0.1481, "step": 369040 }, { "epoch": 2.1937098394469507, "grad_norm": 3.2323153018951416, "learning_rate": 6.893398026550574e-06, "loss": 0.1316, "step": 369050 }, { "epoch": 2.193769281523619, "grad_norm": 5.140661716461182, "learning_rate": 6.893205985182681e-06, "loss": 0.166, "step": 369060 }, { "epoch": 2.1938287236002876, "grad_norm": 5.271533966064453, "learning_rate": 6.893013940554462e-06, "loss": 0.1628, "step": 369070 }, { "epoch": 2.193888165676956, "grad_norm": 4.038327217102051, "learning_rate": 6.892821892666246e-06, "loss": 0.134, "step": 369080 }, { "epoch": 2.1939476077536244, "grad_norm": 3.4725215435028076, "learning_rate": 6.8926298415183655e-06, "loss": 0.1639, "step": 369090 }, { "epoch": 2.194007049830293, "grad_norm": 4.134359359741211, "learning_rate": 6.8924377871111504e-06, "loss": 0.168, "step": 369100 }, { "epoch": 2.1940664919069612, "grad_norm": 4.822255611419678, "learning_rate": 6.892245729444932e-06, "loss": 0.1601, "step": 369110 }, { "epoch": 2.1941259339836297, "grad_norm": 3.495906352996826, "learning_rate": 6.89205366852004e-06, "loss": 0.1562, "step": 369120 }, { "epoch": 2.194185376060298, "grad_norm": 4.160705089569092, "learning_rate": 6.891861604336807e-06, "loss": 0.1475, "step": 369130 }, { "epoch": 2.1942448181369665, "grad_norm": 5.313531875610352, "learning_rate": 6.891669536895562e-06, "loss": 0.1589, "step": 369140 }, { "epoch": 2.194304260213635, "grad_norm": 3.7156782150268555, "learning_rate": 6.891477466196636e-06, "loss": 0.1582, "step": 369150 }, { "epoch": 2.1943637022903033, "grad_norm": 4.20058536529541, "learning_rate": 6.891285392240361e-06, "loss": 0.1506, "step": 369160 }, { "epoch": 2.1944231443669717, "grad_norm": 4.194015979766846, "learning_rate": 6.891093315027066e-06, "loss": 0.1693, "step": 369170 }, { "epoch": 2.19448258644364, "grad_norm": 3.0680439472198486, "learning_rate": 6.890901234557081e-06, "loss": 0.164, "step": 369180 }, { "epoch": 2.1945420285203086, "grad_norm": 3.6955950260162354, "learning_rate": 6.8907091508307414e-06, "loss": 0.16, "step": 369190 }, { "epoch": 2.194601470596977, "grad_norm": 4.198369979858398, "learning_rate": 6.890517063848374e-06, "loss": 0.1446, "step": 369200 }, { "epoch": 2.194660912673645, "grad_norm": 5.075761318206787, "learning_rate": 6.890324973610311e-06, "loss": 0.1459, "step": 369210 }, { "epoch": 2.1947203547503134, "grad_norm": 4.428511619567871, "learning_rate": 6.890132880116882e-06, "loss": 0.1541, "step": 369220 }, { "epoch": 2.1947797968269818, "grad_norm": 4.6658806800842285, "learning_rate": 6.8899407833684205e-06, "loss": 0.1566, "step": 369230 }, { "epoch": 2.19483923890365, "grad_norm": 3.941633701324463, "learning_rate": 6.889748683365254e-06, "loss": 0.169, "step": 369240 }, { "epoch": 2.1948986809803186, "grad_norm": 3.9358291625976562, "learning_rate": 6.889556580107714e-06, "loss": 0.1348, "step": 369250 }, { "epoch": 2.194958123056987, "grad_norm": 4.5705485343933105, "learning_rate": 6.889364473596134e-06, "loss": 0.1533, "step": 369260 }, { "epoch": 2.1950175651336554, "grad_norm": 5.166810989379883, "learning_rate": 6.889172363830842e-06, "loss": 0.1562, "step": 369270 }, { "epoch": 2.195077007210324, "grad_norm": 5.6011223793029785, "learning_rate": 6.888980250812168e-06, "loss": 0.1597, "step": 369280 }, { "epoch": 2.1951364492869923, "grad_norm": 3.823206901550293, "learning_rate": 6.888788134540447e-06, "loss": 0.1629, "step": 369290 }, { "epoch": 2.1951958913636607, "grad_norm": 3.497443437576294, "learning_rate": 6.888596015016007e-06, "loss": 0.1405, "step": 369300 }, { "epoch": 2.195255333440329, "grad_norm": 3.2648801803588867, "learning_rate": 6.888403892239179e-06, "loss": 0.1537, "step": 369310 }, { "epoch": 2.1953147755169975, "grad_norm": 4.2445502281188965, "learning_rate": 6.888211766210295e-06, "loss": 0.1347, "step": 369320 }, { "epoch": 2.195374217593666, "grad_norm": 4.310523986816406, "learning_rate": 6.888019636929685e-06, "loss": 0.1529, "step": 369330 }, { "epoch": 2.1954336596703343, "grad_norm": 5.546024799346924, "learning_rate": 6.887827504397678e-06, "loss": 0.1445, "step": 369340 }, { "epoch": 2.1954931017470027, "grad_norm": 5.435585021972656, "learning_rate": 6.887635368614609e-06, "loss": 0.1538, "step": 369350 }, { "epoch": 2.195552543823671, "grad_norm": 4.237165451049805, "learning_rate": 6.887443229580806e-06, "loss": 0.1512, "step": 369360 }, { "epoch": 2.1956119859003396, "grad_norm": 4.798013210296631, "learning_rate": 6.887251087296599e-06, "loss": 0.1513, "step": 369370 }, { "epoch": 2.195671427977008, "grad_norm": 3.5465261936187744, "learning_rate": 6.887058941762323e-06, "loss": 0.1419, "step": 369380 }, { "epoch": 2.1957308700536764, "grad_norm": 3.6234629154205322, "learning_rate": 6.886866792978304e-06, "loss": 0.1562, "step": 369390 }, { "epoch": 2.1957903121303444, "grad_norm": 3.8273026943206787, "learning_rate": 6.886674640944877e-06, "loss": 0.157, "step": 369400 }, { "epoch": 2.195849754207013, "grad_norm": 4.541733741760254, "learning_rate": 6.886482485662369e-06, "loss": 0.1783, "step": 369410 }, { "epoch": 2.195909196283681, "grad_norm": 5.146085262298584, "learning_rate": 6.886290327131115e-06, "loss": 0.1557, "step": 369420 }, { "epoch": 2.1959686383603496, "grad_norm": 4.983515739440918, "learning_rate": 6.886098165351445e-06, "loss": 0.1546, "step": 369430 }, { "epoch": 2.196028080437018, "grad_norm": 4.747948169708252, "learning_rate": 6.885906000323687e-06, "loss": 0.1586, "step": 369440 }, { "epoch": 2.1960875225136864, "grad_norm": 4.672055244445801, "learning_rate": 6.885713832048174e-06, "loss": 0.1449, "step": 369450 }, { "epoch": 2.196146964590355, "grad_norm": 4.913359642028809, "learning_rate": 6.885521660525237e-06, "loss": 0.1533, "step": 369460 }, { "epoch": 2.1962064066670233, "grad_norm": 3.6606245040893555, "learning_rate": 6.885329485755207e-06, "loss": 0.1544, "step": 369470 }, { "epoch": 2.1962658487436917, "grad_norm": 4.852266311645508, "learning_rate": 6.885137307738414e-06, "loss": 0.1581, "step": 369480 }, { "epoch": 2.19632529082036, "grad_norm": 6.737120628356934, "learning_rate": 6.884945126475191e-06, "loss": 0.1678, "step": 369490 }, { "epoch": 2.1963847328970285, "grad_norm": 3.2156946659088135, "learning_rate": 6.884752941965864e-06, "loss": 0.1497, "step": 369500 }, { "epoch": 2.196444174973697, "grad_norm": 3.6583731174468994, "learning_rate": 6.884560754210772e-06, "loss": 0.1387, "step": 369510 }, { "epoch": 2.1965036170503653, "grad_norm": 4.333962917327881, "learning_rate": 6.88436856321024e-06, "loss": 0.1315, "step": 369520 }, { "epoch": 2.1965630591270338, "grad_norm": 4.235694408416748, "learning_rate": 6.884176368964599e-06, "loss": 0.1389, "step": 369530 }, { "epoch": 2.196622501203702, "grad_norm": 3.5201094150543213, "learning_rate": 6.8839841714741825e-06, "loss": 0.1466, "step": 369540 }, { "epoch": 2.1966819432803706, "grad_norm": 4.593558311462402, "learning_rate": 6.883791970739322e-06, "loss": 0.1581, "step": 369550 }, { "epoch": 2.196741385357039, "grad_norm": 5.045040130615234, "learning_rate": 6.883599766760346e-06, "loss": 0.1787, "step": 369560 }, { "epoch": 2.1968008274337074, "grad_norm": 3.525705575942993, "learning_rate": 6.883407559537585e-06, "loss": 0.1576, "step": 369570 }, { "epoch": 2.196860269510376, "grad_norm": 4.640665054321289, "learning_rate": 6.883215349071374e-06, "loss": 0.1583, "step": 369580 }, { "epoch": 2.196919711587044, "grad_norm": 4.910273551940918, "learning_rate": 6.88302313536204e-06, "loss": 0.1551, "step": 369590 }, { "epoch": 2.196979153663712, "grad_norm": 3.9775147438049316, "learning_rate": 6.882830918409915e-06, "loss": 0.1418, "step": 369600 }, { "epoch": 2.1970385957403806, "grad_norm": 3.7657158374786377, "learning_rate": 6.8826386982153305e-06, "loss": 0.164, "step": 369610 }, { "epoch": 2.197098037817049, "grad_norm": 3.4985909461975098, "learning_rate": 6.882446474778618e-06, "loss": 0.1354, "step": 369620 }, { "epoch": 2.1971574798937175, "grad_norm": 5.394742965698242, "learning_rate": 6.882254248100108e-06, "loss": 0.1574, "step": 369630 }, { "epoch": 2.197216921970386, "grad_norm": 5.686940670013428, "learning_rate": 6.8820620181801315e-06, "loss": 0.1687, "step": 369640 }, { "epoch": 2.1972763640470543, "grad_norm": 3.2855100631713867, "learning_rate": 6.881869785019019e-06, "loss": 0.1444, "step": 369650 }, { "epoch": 2.1973358061237227, "grad_norm": 3.302844285964966, "learning_rate": 6.881677548617104e-06, "loss": 0.132, "step": 369660 }, { "epoch": 2.197395248200391, "grad_norm": 4.652605056762695, "learning_rate": 6.8814853089747144e-06, "loss": 0.146, "step": 369670 }, { "epoch": 2.1974546902770595, "grad_norm": 4.709470272064209, "learning_rate": 6.881293066092184e-06, "loss": 0.1361, "step": 369680 }, { "epoch": 2.197514132353728, "grad_norm": 4.251930236816406, "learning_rate": 6.881100819969841e-06, "loss": 0.1379, "step": 369690 }, { "epoch": 2.1975735744303964, "grad_norm": 3.9515609741210938, "learning_rate": 6.880908570608018e-06, "loss": 0.156, "step": 369700 }, { "epoch": 2.1976330165070648, "grad_norm": 5.398130416870117, "learning_rate": 6.880716318007047e-06, "loss": 0.1481, "step": 369710 }, { "epoch": 2.197692458583733, "grad_norm": 4.838656902313232, "learning_rate": 6.8805240621672575e-06, "loss": 0.1604, "step": 369720 }, { "epoch": 2.1977519006604016, "grad_norm": 3.9813520908355713, "learning_rate": 6.88033180308898e-06, "loss": 0.1433, "step": 369730 }, { "epoch": 2.19781134273707, "grad_norm": 4.545829772949219, "learning_rate": 6.880139540772548e-06, "loss": 0.1435, "step": 369740 }, { "epoch": 2.1978707848137384, "grad_norm": 3.1252896785736084, "learning_rate": 6.879947275218293e-06, "loss": 0.165, "step": 369750 }, { "epoch": 2.197930226890407, "grad_norm": 3.698934316635132, "learning_rate": 6.879755006426541e-06, "loss": 0.1508, "step": 369760 }, { "epoch": 2.1979896689670753, "grad_norm": 4.015763282775879, "learning_rate": 6.879562734397629e-06, "loss": 0.1539, "step": 369770 }, { "epoch": 2.1980491110437432, "grad_norm": 4.799238204956055, "learning_rate": 6.879370459131886e-06, "loss": 0.1512, "step": 369780 }, { "epoch": 2.1981085531204116, "grad_norm": 3.753419876098633, "learning_rate": 6.879178180629641e-06, "loss": 0.1495, "step": 369790 }, { "epoch": 2.19816799519708, "grad_norm": 3.860736846923828, "learning_rate": 6.878985898891229e-06, "loss": 0.1299, "step": 369800 }, { "epoch": 2.1982274372737485, "grad_norm": 5.096765518188477, "learning_rate": 6.878793613916977e-06, "loss": 0.164, "step": 369810 }, { "epoch": 2.198286879350417, "grad_norm": 2.928199052810669, "learning_rate": 6.878601325707219e-06, "loss": 0.1508, "step": 369820 }, { "epoch": 2.1983463214270853, "grad_norm": 4.157754421234131, "learning_rate": 6.878409034262286e-06, "loss": 0.1391, "step": 369830 }, { "epoch": 2.1984057635037537, "grad_norm": 4.5226263999938965, "learning_rate": 6.8782167395825074e-06, "loss": 0.1501, "step": 369840 }, { "epoch": 2.198465205580422, "grad_norm": 4.690049171447754, "learning_rate": 6.878024441668216e-06, "loss": 0.1638, "step": 369850 }, { "epoch": 2.1985246476570905, "grad_norm": 5.246072292327881, "learning_rate": 6.8778321405197425e-06, "loss": 0.1501, "step": 369860 }, { "epoch": 2.198584089733759, "grad_norm": 4.985832214355469, "learning_rate": 6.8776398361374185e-06, "loss": 0.1416, "step": 369870 }, { "epoch": 2.1986435318104274, "grad_norm": 3.109316349029541, "learning_rate": 6.877447528521575e-06, "loss": 0.1425, "step": 369880 }, { "epoch": 2.198702973887096, "grad_norm": 6.701322555541992, "learning_rate": 6.877255217672541e-06, "loss": 0.1506, "step": 369890 }, { "epoch": 2.198762415963764, "grad_norm": 4.328039646148682, "learning_rate": 6.877062903590651e-06, "loss": 0.159, "step": 369900 }, { "epoch": 2.1988218580404326, "grad_norm": 5.188860893249512, "learning_rate": 6.876870586276234e-06, "loss": 0.1508, "step": 369910 }, { "epoch": 2.198881300117101, "grad_norm": 5.409935474395752, "learning_rate": 6.8766782657296215e-06, "loss": 0.1536, "step": 369920 }, { "epoch": 2.1989407421937694, "grad_norm": 5.305844306945801, "learning_rate": 6.8764859419511476e-06, "loss": 0.1453, "step": 369930 }, { "epoch": 2.199000184270438, "grad_norm": 4.442651271820068, "learning_rate": 6.876293614941139e-06, "loss": 0.1523, "step": 369940 }, { "epoch": 2.199059626347106, "grad_norm": 3.7724123001098633, "learning_rate": 6.876101284699929e-06, "loss": 0.1397, "step": 369950 }, { "epoch": 2.1991190684237742, "grad_norm": 4.109164237976074, "learning_rate": 6.875908951227847e-06, "loss": 0.1713, "step": 369960 }, { "epoch": 2.1991785105004427, "grad_norm": 4.060272216796875, "learning_rate": 6.8757166145252295e-06, "loss": 0.1393, "step": 369970 }, { "epoch": 2.199237952577111, "grad_norm": 4.453608512878418, "learning_rate": 6.875524274592402e-06, "loss": 0.1478, "step": 369980 }, { "epoch": 2.1992973946537795, "grad_norm": 4.246347427368164, "learning_rate": 6.875331931429698e-06, "loss": 0.1594, "step": 369990 }, { "epoch": 2.199356836730448, "grad_norm": 4.425137996673584, "learning_rate": 6.875139585037449e-06, "loss": 0.1449, "step": 370000 }, { "epoch": 2.1994162788071163, "grad_norm": 5.315793991088867, "learning_rate": 6.8749472354159876e-06, "loss": 0.1587, "step": 370010 }, { "epoch": 2.1994757208837847, "grad_norm": 4.557790279388428, "learning_rate": 6.87475488256564e-06, "loss": 0.1395, "step": 370020 }, { "epoch": 2.199535162960453, "grad_norm": 4.046115875244141, "learning_rate": 6.874562526486743e-06, "loss": 0.1398, "step": 370030 }, { "epoch": 2.1995946050371216, "grad_norm": 5.663796424865723, "learning_rate": 6.874370167179626e-06, "loss": 0.1305, "step": 370040 }, { "epoch": 2.19965404711379, "grad_norm": 3.9311039447784424, "learning_rate": 6.874177804644618e-06, "loss": 0.1607, "step": 370050 }, { "epoch": 2.1997134891904584, "grad_norm": 6.443492889404297, "learning_rate": 6.873985438882054e-06, "loss": 0.1516, "step": 370060 }, { "epoch": 2.199772931267127, "grad_norm": 3.9798765182495117, "learning_rate": 6.873793069892263e-06, "loss": 0.1459, "step": 370070 }, { "epoch": 2.1998323733437952, "grad_norm": 4.491182327270508, "learning_rate": 6.8736006976755766e-06, "loss": 0.1417, "step": 370080 }, { "epoch": 2.1998918154204636, "grad_norm": 5.154512405395508, "learning_rate": 6.8734083222323255e-06, "loss": 0.1548, "step": 370090 }, { "epoch": 2.199951257497132, "grad_norm": 4.96728515625, "learning_rate": 6.873215943562843e-06, "loss": 0.1616, "step": 370100 }, { "epoch": 2.2000106995738005, "grad_norm": 4.982857704162598, "learning_rate": 6.873023561667459e-06, "loss": 0.1552, "step": 370110 }, { "epoch": 2.200070141650469, "grad_norm": 4.12554407119751, "learning_rate": 6.872831176546504e-06, "loss": 0.1497, "step": 370120 }, { "epoch": 2.2001295837271373, "grad_norm": 4.0298848152160645, "learning_rate": 6.872638788200311e-06, "loss": 0.1486, "step": 370130 }, { "epoch": 2.2001890258038053, "grad_norm": 4.545206069946289, "learning_rate": 6.872446396629211e-06, "loss": 0.1601, "step": 370140 }, { "epoch": 2.2002484678804737, "grad_norm": 4.2940168380737305, "learning_rate": 6.872254001833533e-06, "loss": 0.1493, "step": 370150 }, { "epoch": 2.200307909957142, "grad_norm": 3.431816339492798, "learning_rate": 6.872061603813611e-06, "loss": 0.1571, "step": 370160 }, { "epoch": 2.2003673520338105, "grad_norm": 3.7822678089141846, "learning_rate": 6.871869202569776e-06, "loss": 0.1486, "step": 370170 }, { "epoch": 2.200426794110479, "grad_norm": 4.283089637756348, "learning_rate": 6.871676798102358e-06, "loss": 0.151, "step": 370180 }, { "epoch": 2.2004862361871473, "grad_norm": 4.6838698387146, "learning_rate": 6.871484390411692e-06, "loss": 0.1324, "step": 370190 }, { "epoch": 2.2005456782638158, "grad_norm": 6.399623394012451, "learning_rate": 6.871291979498104e-06, "loss": 0.1622, "step": 370200 }, { "epoch": 2.200605120340484, "grad_norm": 4.215905666351318, "learning_rate": 6.871099565361927e-06, "loss": 0.1327, "step": 370210 }, { "epoch": 2.2006645624171526, "grad_norm": 6.147756099700928, "learning_rate": 6.870907148003496e-06, "loss": 0.1697, "step": 370220 }, { "epoch": 2.200724004493821, "grad_norm": 4.424468994140625, "learning_rate": 6.8707147274231386e-06, "loss": 0.1585, "step": 370230 }, { "epoch": 2.2007834465704894, "grad_norm": 3.8802032470703125, "learning_rate": 6.8705223036211875e-06, "loss": 0.1593, "step": 370240 }, { "epoch": 2.200842888647158, "grad_norm": 3.992429733276367, "learning_rate": 6.870329876597973e-06, "loss": 0.1459, "step": 370250 }, { "epoch": 2.2009023307238262, "grad_norm": 4.357156753540039, "learning_rate": 6.870137446353829e-06, "loss": 0.1566, "step": 370260 }, { "epoch": 2.2009617728004947, "grad_norm": 5.31657600402832, "learning_rate": 6.869945012889083e-06, "loss": 0.1547, "step": 370270 }, { "epoch": 2.201021214877163, "grad_norm": 4.162796497344971, "learning_rate": 6.869752576204069e-06, "loss": 0.1546, "step": 370280 }, { "epoch": 2.2010806569538315, "grad_norm": 5.676469802856445, "learning_rate": 6.869560136299118e-06, "loss": 0.1604, "step": 370290 }, { "epoch": 2.2011400990305, "grad_norm": 5.1414265632629395, "learning_rate": 6.869367693174562e-06, "loss": 0.1295, "step": 370300 }, { "epoch": 2.2011995411071683, "grad_norm": 4.398955345153809, "learning_rate": 6.869175246830731e-06, "loss": 0.1536, "step": 370310 }, { "epoch": 2.2012589831838367, "grad_norm": 5.5230817794799805, "learning_rate": 6.868982797267959e-06, "loss": 0.1438, "step": 370320 }, { "epoch": 2.2013184252605047, "grad_norm": 3.8563716411590576, "learning_rate": 6.8687903444865754e-06, "loss": 0.129, "step": 370330 }, { "epoch": 2.201377867337173, "grad_norm": 3.5247981548309326, "learning_rate": 6.86859788848691e-06, "loss": 0.1391, "step": 370340 }, { "epoch": 2.2014373094138415, "grad_norm": 5.819568634033203, "learning_rate": 6.868405429269297e-06, "loss": 0.1666, "step": 370350 }, { "epoch": 2.20149675149051, "grad_norm": 3.760806083679199, "learning_rate": 6.868212966834067e-06, "loss": 0.1335, "step": 370360 }, { "epoch": 2.2015561935671784, "grad_norm": 3.219210147857666, "learning_rate": 6.868020501181551e-06, "loss": 0.1445, "step": 370370 }, { "epoch": 2.2016156356438468, "grad_norm": 4.33305025100708, "learning_rate": 6.8678280323120806e-06, "loss": 0.1467, "step": 370380 }, { "epoch": 2.201675077720515, "grad_norm": 4.846375942230225, "learning_rate": 6.867635560225988e-06, "loss": 0.1549, "step": 370390 }, { "epoch": 2.2017345197971836, "grad_norm": 5.366951942443848, "learning_rate": 6.867443084923605e-06, "loss": 0.1526, "step": 370400 }, { "epoch": 2.201793961873852, "grad_norm": 3.19724440574646, "learning_rate": 6.8672506064052604e-06, "loss": 0.1491, "step": 370410 }, { "epoch": 2.2018534039505204, "grad_norm": 4.350636005401611, "learning_rate": 6.867058124671289e-06, "loss": 0.1573, "step": 370420 }, { "epoch": 2.201912846027189, "grad_norm": 5.415821075439453, "learning_rate": 6.86686563972202e-06, "loss": 0.1748, "step": 370430 }, { "epoch": 2.2019722881038573, "grad_norm": 4.975431442260742, "learning_rate": 6.866673151557786e-06, "loss": 0.1767, "step": 370440 }, { "epoch": 2.2020317301805257, "grad_norm": 4.255501747131348, "learning_rate": 6.866480660178918e-06, "loss": 0.1439, "step": 370450 }, { "epoch": 2.202091172257194, "grad_norm": 5.75584602355957, "learning_rate": 6.866288165585747e-06, "loss": 0.1357, "step": 370460 }, { "epoch": 2.2021506143338625, "grad_norm": 3.7537882328033447, "learning_rate": 6.866095667778605e-06, "loss": 0.1242, "step": 370470 }, { "epoch": 2.202210056410531, "grad_norm": 3.8469743728637695, "learning_rate": 6.865903166757825e-06, "loss": 0.1389, "step": 370480 }, { "epoch": 2.2022694984871993, "grad_norm": 5.3670501708984375, "learning_rate": 6.865710662523735e-06, "loss": 0.1677, "step": 370490 }, { "epoch": 2.2023289405638677, "grad_norm": 5.008141040802002, "learning_rate": 6.8655181550766705e-06, "loss": 0.1537, "step": 370500 }, { "epoch": 2.202388382640536, "grad_norm": 3.2591617107391357, "learning_rate": 6.865325644416959e-06, "loss": 0.1402, "step": 370510 }, { "epoch": 2.202447824717204, "grad_norm": 3.8290023803710938, "learning_rate": 6.865133130544936e-06, "loss": 0.1444, "step": 370520 }, { "epoch": 2.2025072667938725, "grad_norm": 4.349824905395508, "learning_rate": 6.8649406134609316e-06, "loss": 0.156, "step": 370530 }, { "epoch": 2.202566708870541, "grad_norm": 4.106990814208984, "learning_rate": 6.864748093165275e-06, "loss": 0.1618, "step": 370540 }, { "epoch": 2.2026261509472094, "grad_norm": 3.3695218563079834, "learning_rate": 6.8645555696583025e-06, "loss": 0.1425, "step": 370550 }, { "epoch": 2.202685593023878, "grad_norm": 4.732799530029297, "learning_rate": 6.864363042940341e-06, "loss": 0.1672, "step": 370560 }, { "epoch": 2.202745035100546, "grad_norm": 3.695391893386841, "learning_rate": 6.864170513011723e-06, "loss": 0.1459, "step": 370570 }, { "epoch": 2.2028044771772146, "grad_norm": 3.10478138923645, "learning_rate": 6.8639779798727824e-06, "loss": 0.1552, "step": 370580 }, { "epoch": 2.202863919253883, "grad_norm": 5.759566783905029, "learning_rate": 6.863785443523849e-06, "loss": 0.1572, "step": 370590 }, { "epoch": 2.2029233613305514, "grad_norm": 3.7673778533935547, "learning_rate": 6.863592903965255e-06, "loss": 0.1531, "step": 370600 }, { "epoch": 2.20298280340722, "grad_norm": 4.516655445098877, "learning_rate": 6.86340036119733e-06, "loss": 0.1491, "step": 370610 }, { "epoch": 2.2030422454838883, "grad_norm": 3.3332083225250244, "learning_rate": 6.86320781522041e-06, "loss": 0.1356, "step": 370620 }, { "epoch": 2.2031016875605567, "grad_norm": 3.0946295261383057, "learning_rate": 6.863015266034823e-06, "loss": 0.1448, "step": 370630 }, { "epoch": 2.203161129637225, "grad_norm": 3.496431827545166, "learning_rate": 6.8628227136408985e-06, "loss": 0.1516, "step": 370640 }, { "epoch": 2.2032205717138935, "grad_norm": 3.2817389965057373, "learning_rate": 6.862630158038974e-06, "loss": 0.164, "step": 370650 }, { "epoch": 2.203280013790562, "grad_norm": 5.240261077880859, "learning_rate": 6.862437599229378e-06, "loss": 0.171, "step": 370660 }, { "epoch": 2.2033394558672303, "grad_norm": 3.5775632858276367, "learning_rate": 6.862245037212441e-06, "loss": 0.1489, "step": 370670 }, { "epoch": 2.2033988979438988, "grad_norm": 4.958689212799072, "learning_rate": 6.862052471988496e-06, "loss": 0.1563, "step": 370680 }, { "epoch": 2.2034583400205667, "grad_norm": 6.606197357177734, "learning_rate": 6.861859903557876e-06, "loss": 0.153, "step": 370690 }, { "epoch": 2.203517782097235, "grad_norm": 4.515401363372803, "learning_rate": 6.8616673319209095e-06, "loss": 0.1582, "step": 370700 }, { "epoch": 2.2035772241739036, "grad_norm": 4.481985092163086, "learning_rate": 6.86147475707793e-06, "loss": 0.1473, "step": 370710 }, { "epoch": 2.203636666250572, "grad_norm": 5.943055629730225, "learning_rate": 6.86128217902927e-06, "loss": 0.1627, "step": 370720 }, { "epoch": 2.2036961083272404, "grad_norm": 3.6234283447265625, "learning_rate": 6.861089597775259e-06, "loss": 0.1548, "step": 370730 }, { "epoch": 2.203755550403909, "grad_norm": 6.090823173522949, "learning_rate": 6.860897013316229e-06, "loss": 0.1417, "step": 370740 }, { "epoch": 2.203814992480577, "grad_norm": 4.951062202453613, "learning_rate": 6.860704425652513e-06, "loss": 0.1652, "step": 370750 }, { "epoch": 2.2038744345572456, "grad_norm": 2.960014581680298, "learning_rate": 6.8605118347844424e-06, "loss": 0.1555, "step": 370760 }, { "epoch": 2.203933876633914, "grad_norm": 4.635988235473633, "learning_rate": 6.860319240712348e-06, "loss": 0.1386, "step": 370770 }, { "epoch": 2.2039933187105825, "grad_norm": 4.427089691162109, "learning_rate": 6.8601266434365624e-06, "loss": 0.1369, "step": 370780 }, { "epoch": 2.204052760787251, "grad_norm": 4.250783920288086, "learning_rate": 6.859934042957417e-06, "loss": 0.1464, "step": 370790 }, { "epoch": 2.2041122028639193, "grad_norm": 3.573035478591919, "learning_rate": 6.8597414392752415e-06, "loss": 0.1533, "step": 370800 }, { "epoch": 2.2041716449405877, "grad_norm": 3.826036214828491, "learning_rate": 6.859548832390371e-06, "loss": 0.1572, "step": 370810 }, { "epoch": 2.204231087017256, "grad_norm": 4.19044303894043, "learning_rate": 6.859356222303134e-06, "loss": 0.1631, "step": 370820 }, { "epoch": 2.2042905290939245, "grad_norm": 4.3497748374938965, "learning_rate": 6.859163609013865e-06, "loss": 0.1465, "step": 370830 }, { "epoch": 2.204349971170593, "grad_norm": 4.507416725158691, "learning_rate": 6.858970992522894e-06, "loss": 0.1501, "step": 370840 }, { "epoch": 2.2044094132472614, "grad_norm": 5.370971202850342, "learning_rate": 6.858778372830553e-06, "loss": 0.1625, "step": 370850 }, { "epoch": 2.2044688553239298, "grad_norm": 3.3172380924224854, "learning_rate": 6.858585749937175e-06, "loss": 0.1429, "step": 370860 }, { "epoch": 2.204528297400598, "grad_norm": 4.0096821784973145, "learning_rate": 6.858393123843089e-06, "loss": 0.1482, "step": 370870 }, { "epoch": 2.204587739477266, "grad_norm": 5.429602146148682, "learning_rate": 6.85820049454863e-06, "loss": 0.1461, "step": 370880 }, { "epoch": 2.2046471815539346, "grad_norm": 4.67669677734375, "learning_rate": 6.8580078620541256e-06, "loss": 0.1471, "step": 370890 }, { "epoch": 2.204706623630603, "grad_norm": 4.048704147338867, "learning_rate": 6.857815226359912e-06, "loss": 0.1782, "step": 370900 }, { "epoch": 2.2047660657072714, "grad_norm": 3.674333333969116, "learning_rate": 6.85762258746632e-06, "loss": 0.1439, "step": 370910 }, { "epoch": 2.20482550778394, "grad_norm": 4.657708644866943, "learning_rate": 6.857429945373678e-06, "loss": 0.1384, "step": 370920 }, { "epoch": 2.2048849498606082, "grad_norm": 3.455923318862915, "learning_rate": 6.857237300082319e-06, "loss": 0.1288, "step": 370930 }, { "epoch": 2.2049443919372766, "grad_norm": 4.37454080581665, "learning_rate": 6.857044651592577e-06, "loss": 0.1494, "step": 370940 }, { "epoch": 2.205003834013945, "grad_norm": 3.00423264503479, "learning_rate": 6.856851999904783e-06, "loss": 0.1498, "step": 370950 }, { "epoch": 2.2050632760906135, "grad_norm": 3.8383305072784424, "learning_rate": 6.8566593450192685e-06, "loss": 0.1564, "step": 370960 }, { "epoch": 2.205122718167282, "grad_norm": 4.531750202178955, "learning_rate": 6.856466686936365e-06, "loss": 0.1385, "step": 370970 }, { "epoch": 2.2051821602439503, "grad_norm": 3.5952250957489014, "learning_rate": 6.856274025656404e-06, "loss": 0.1402, "step": 370980 }, { "epoch": 2.2052416023206187, "grad_norm": 4.551649570465088, "learning_rate": 6.856081361179718e-06, "loss": 0.1424, "step": 370990 }, { "epoch": 2.205301044397287, "grad_norm": 3.7399117946624756, "learning_rate": 6.855888693506639e-06, "loss": 0.1349, "step": 371000 }, { "epoch": 2.2053604864739556, "grad_norm": 4.699142932891846, "learning_rate": 6.855696022637497e-06, "loss": 0.1629, "step": 371010 }, { "epoch": 2.205419928550624, "grad_norm": 3.7384214401245117, "learning_rate": 6.855503348572625e-06, "loss": 0.1495, "step": 371020 }, { "epoch": 2.2054793706272924, "grad_norm": 4.141142845153809, "learning_rate": 6.855310671312355e-06, "loss": 0.1551, "step": 371030 }, { "epoch": 2.205538812703961, "grad_norm": 3.543820381164551, "learning_rate": 6.855117990857019e-06, "loss": 0.1419, "step": 371040 }, { "epoch": 2.205598254780629, "grad_norm": 4.849778652191162, "learning_rate": 6.854925307206949e-06, "loss": 0.1564, "step": 371050 }, { "epoch": 2.2056576968572976, "grad_norm": 4.320810317993164, "learning_rate": 6.854732620362474e-06, "loss": 0.1608, "step": 371060 }, { "epoch": 2.2057171389339656, "grad_norm": 5.366642951965332, "learning_rate": 6.854539930323932e-06, "loss": 0.1339, "step": 371070 }, { "epoch": 2.205776581010634, "grad_norm": 2.8742644786834717, "learning_rate": 6.854347237091647e-06, "loss": 0.1519, "step": 371080 }, { "epoch": 2.2058360230873024, "grad_norm": 3.1829519271850586, "learning_rate": 6.854154540665957e-06, "loss": 0.1571, "step": 371090 }, { "epoch": 2.205895465163971, "grad_norm": 4.093940734863281, "learning_rate": 6.853961841047192e-06, "loss": 0.1521, "step": 371100 }, { "epoch": 2.2059549072406393, "grad_norm": 3.896531581878662, "learning_rate": 6.853769138235683e-06, "loss": 0.1572, "step": 371110 }, { "epoch": 2.2060143493173077, "grad_norm": 4.294979572296143, "learning_rate": 6.853576432231761e-06, "loss": 0.1659, "step": 371120 }, { "epoch": 2.206073791393976, "grad_norm": 4.026301383972168, "learning_rate": 6.8533837230357616e-06, "loss": 0.1541, "step": 371130 }, { "epoch": 2.2061332334706445, "grad_norm": 4.3769307136535645, "learning_rate": 6.8531910106480125e-06, "loss": 0.1384, "step": 371140 }, { "epoch": 2.206192675547313, "grad_norm": 4.156011581420898, "learning_rate": 6.852998295068848e-06, "loss": 0.154, "step": 371150 }, { "epoch": 2.2062521176239813, "grad_norm": 4.097156047821045, "learning_rate": 6.8528055762985975e-06, "loss": 0.15, "step": 371160 }, { "epoch": 2.2063115597006497, "grad_norm": 8.457905769348145, "learning_rate": 6.852612854337597e-06, "loss": 0.1542, "step": 371170 }, { "epoch": 2.206371001777318, "grad_norm": 4.0727763175964355, "learning_rate": 6.852420129186177e-06, "loss": 0.1505, "step": 371180 }, { "epoch": 2.2064304438539866, "grad_norm": 3.7507989406585693, "learning_rate": 6.852227400844665e-06, "loss": 0.1505, "step": 371190 }, { "epoch": 2.206489885930655, "grad_norm": 5.426113605499268, "learning_rate": 6.8520346693134e-06, "loss": 0.1658, "step": 371200 }, { "epoch": 2.2065493280073234, "grad_norm": 3.6829164028167725, "learning_rate": 6.851841934592709e-06, "loss": 0.1498, "step": 371210 }, { "epoch": 2.206608770083992, "grad_norm": 3.7359533309936523, "learning_rate": 6.851649196682924e-06, "loss": 0.1437, "step": 371220 }, { "epoch": 2.2066682121606602, "grad_norm": 4.6703948974609375, "learning_rate": 6.8514564555843795e-06, "loss": 0.1705, "step": 371230 }, { "epoch": 2.2067276542373286, "grad_norm": 5.507458209991455, "learning_rate": 6.851263711297407e-06, "loss": 0.1459, "step": 371240 }, { "epoch": 2.206787096313997, "grad_norm": 4.140628814697266, "learning_rate": 6.851070963822335e-06, "loss": 0.1355, "step": 371250 }, { "epoch": 2.206846538390665, "grad_norm": 3.062187671661377, "learning_rate": 6.850878213159498e-06, "loss": 0.1637, "step": 371260 }, { "epoch": 2.2069059804673334, "grad_norm": 4.353566646575928, "learning_rate": 6.85068545930923e-06, "loss": 0.1624, "step": 371270 }, { "epoch": 2.206965422544002, "grad_norm": 3.753295660018921, "learning_rate": 6.85049270227186e-06, "loss": 0.1451, "step": 371280 }, { "epoch": 2.2070248646206703, "grad_norm": 5.38344669342041, "learning_rate": 6.8502999420477204e-06, "loss": 0.1783, "step": 371290 }, { "epoch": 2.2070843066973387, "grad_norm": 3.993298292160034, "learning_rate": 6.850107178637144e-06, "loss": 0.146, "step": 371300 }, { "epoch": 2.207143748774007, "grad_norm": 4.067663669586182, "learning_rate": 6.849914412040462e-06, "loss": 0.149, "step": 371310 }, { "epoch": 2.2072031908506755, "grad_norm": 4.057191848754883, "learning_rate": 6.849721642258007e-06, "loss": 0.1473, "step": 371320 }, { "epoch": 2.207262632927344, "grad_norm": 4.0555033683776855, "learning_rate": 6.8495288692901095e-06, "loss": 0.1599, "step": 371330 }, { "epoch": 2.2073220750040123, "grad_norm": 4.743688106536865, "learning_rate": 6.849336093137104e-06, "loss": 0.158, "step": 371340 }, { "epoch": 2.2073815170806808, "grad_norm": 4.34263277053833, "learning_rate": 6.8491433137993205e-06, "loss": 0.1538, "step": 371350 }, { "epoch": 2.207440959157349, "grad_norm": 5.121606349945068, "learning_rate": 6.848950531277092e-06, "loss": 0.1457, "step": 371360 }, { "epoch": 2.2075004012340176, "grad_norm": 3.347820281982422, "learning_rate": 6.8487577455707485e-06, "loss": 0.1694, "step": 371370 }, { "epoch": 2.207559843310686, "grad_norm": 5.416392803192139, "learning_rate": 6.848564956680626e-06, "loss": 0.1804, "step": 371380 }, { "epoch": 2.2076192853873544, "grad_norm": 5.463082790374756, "learning_rate": 6.848372164607051e-06, "loss": 0.1665, "step": 371390 }, { "epoch": 2.207678727464023, "grad_norm": 5.077805042266846, "learning_rate": 6.8481793693503616e-06, "loss": 0.1469, "step": 371400 }, { "epoch": 2.2077381695406912, "grad_norm": 3.2773609161376953, "learning_rate": 6.847986570910886e-06, "loss": 0.1366, "step": 371410 }, { "epoch": 2.2077976116173597, "grad_norm": 2.5896670818328857, "learning_rate": 6.847793769288955e-06, "loss": 0.146, "step": 371420 }, { "epoch": 2.2078570536940276, "grad_norm": 3.4676010608673096, "learning_rate": 6.847600964484905e-06, "loss": 0.1394, "step": 371430 }, { "epoch": 2.207916495770696, "grad_norm": 4.550582408905029, "learning_rate": 6.847408156499066e-06, "loss": 0.159, "step": 371440 }, { "epoch": 2.2079759378473645, "grad_norm": 3.907543182373047, "learning_rate": 6.847215345331768e-06, "loss": 0.1408, "step": 371450 }, { "epoch": 2.208035379924033, "grad_norm": 4.443665504455566, "learning_rate": 6.847022530983346e-06, "loss": 0.1543, "step": 371460 }, { "epoch": 2.2080948220007013, "grad_norm": 3.556323289871216, "learning_rate": 6.846829713454131e-06, "loss": 0.1638, "step": 371470 }, { "epoch": 2.2081542640773697, "grad_norm": 3.3183352947235107, "learning_rate": 6.8466368927444516e-06, "loss": 0.1433, "step": 371480 }, { "epoch": 2.208213706154038, "grad_norm": 3.1721885204315186, "learning_rate": 6.8464440688546465e-06, "loss": 0.1541, "step": 371490 }, { "epoch": 2.2082731482307065, "grad_norm": 5.674263000488281, "learning_rate": 6.846251241785043e-06, "loss": 0.1535, "step": 371500 }, { "epoch": 2.208332590307375, "grad_norm": 5.099046230316162, "learning_rate": 6.846058411535975e-06, "loss": 0.1581, "step": 371510 }, { "epoch": 2.2083920323840434, "grad_norm": 3.778738498687744, "learning_rate": 6.845865578107775e-06, "loss": 0.1552, "step": 371520 }, { "epoch": 2.2084514744607118, "grad_norm": 3.234081506729126, "learning_rate": 6.845672741500774e-06, "loss": 0.1511, "step": 371530 }, { "epoch": 2.20851091653738, "grad_norm": 4.236974716186523, "learning_rate": 6.845479901715303e-06, "loss": 0.1524, "step": 371540 }, { "epoch": 2.2085703586140486, "grad_norm": 4.221427917480469, "learning_rate": 6.8452870587516975e-06, "loss": 0.1474, "step": 371550 }, { "epoch": 2.208629800690717, "grad_norm": 5.300357341766357, "learning_rate": 6.845094212610286e-06, "loss": 0.167, "step": 371560 }, { "epoch": 2.2086892427673854, "grad_norm": 4.869414329528809, "learning_rate": 6.844901363291403e-06, "loss": 0.1512, "step": 371570 }, { "epoch": 2.208748684844054, "grad_norm": 5.42146635055542, "learning_rate": 6.844708510795378e-06, "loss": 0.1558, "step": 371580 }, { "epoch": 2.2088081269207223, "grad_norm": 3.8020894527435303, "learning_rate": 6.844515655122545e-06, "loss": 0.1375, "step": 371590 }, { "epoch": 2.2088675689973907, "grad_norm": 5.255064487457275, "learning_rate": 6.8443227962732375e-06, "loss": 0.1534, "step": 371600 }, { "epoch": 2.208927011074059, "grad_norm": 4.60969877243042, "learning_rate": 6.844129934247785e-06, "loss": 0.1675, "step": 371610 }, { "epoch": 2.208986453150727, "grad_norm": 3.7804296016693115, "learning_rate": 6.843937069046522e-06, "loss": 0.138, "step": 371620 }, { "epoch": 2.2090458952273955, "grad_norm": 6.536563396453857, "learning_rate": 6.843744200669778e-06, "loss": 0.162, "step": 371630 }, { "epoch": 2.209105337304064, "grad_norm": 4.828046798706055, "learning_rate": 6.843551329117888e-06, "loss": 0.1583, "step": 371640 }, { "epoch": 2.2091647793807323, "grad_norm": 2.8219528198242188, "learning_rate": 6.843358454391182e-06, "loss": 0.1485, "step": 371650 }, { "epoch": 2.2092242214574007, "grad_norm": 3.9780588150024414, "learning_rate": 6.843165576489992e-06, "loss": 0.1802, "step": 371660 }, { "epoch": 2.209283663534069, "grad_norm": 4.4363884925842285, "learning_rate": 6.8429726954146515e-06, "loss": 0.1608, "step": 371670 }, { "epoch": 2.2093431056107375, "grad_norm": 3.6968047618865967, "learning_rate": 6.842779811165492e-06, "loss": 0.1304, "step": 371680 }, { "epoch": 2.209402547687406, "grad_norm": 3.925823926925659, "learning_rate": 6.842586923742847e-06, "loss": 0.1336, "step": 371690 }, { "epoch": 2.2094619897640744, "grad_norm": 3.67043399810791, "learning_rate": 6.842394033147045e-06, "loss": 0.1579, "step": 371700 }, { "epoch": 2.209521431840743, "grad_norm": 4.890598773956299, "learning_rate": 6.842201139378422e-06, "loss": 0.1691, "step": 371710 }, { "epoch": 2.209580873917411, "grad_norm": 4.442232608795166, "learning_rate": 6.842008242437308e-06, "loss": 0.15, "step": 371720 }, { "epoch": 2.2096403159940796, "grad_norm": 4.71298360824585, "learning_rate": 6.841815342324038e-06, "loss": 0.1566, "step": 371730 }, { "epoch": 2.209699758070748, "grad_norm": 4.243494987487793, "learning_rate": 6.841622439038939e-06, "loss": 0.158, "step": 371740 }, { "epoch": 2.2097592001474164, "grad_norm": 4.951464653015137, "learning_rate": 6.84142953258235e-06, "loss": 0.1423, "step": 371750 }, { "epoch": 2.209818642224085, "grad_norm": 4.363404750823975, "learning_rate": 6.8412366229545976e-06, "loss": 0.1566, "step": 371760 }, { "epoch": 2.2098780843007533, "grad_norm": 5.012425422668457, "learning_rate": 6.8410437101560165e-06, "loss": 0.1514, "step": 371770 }, { "epoch": 2.2099375263774217, "grad_norm": 4.2378315925598145, "learning_rate": 6.840850794186939e-06, "loss": 0.1495, "step": 371780 }, { "epoch": 2.20999696845409, "grad_norm": 3.4062979221343994, "learning_rate": 6.840657875047696e-06, "loss": 0.1567, "step": 371790 }, { "epoch": 2.2100564105307585, "grad_norm": 4.78860330581665, "learning_rate": 6.840464952738621e-06, "loss": 0.1574, "step": 371800 }, { "epoch": 2.2101158526074265, "grad_norm": 3.3655266761779785, "learning_rate": 6.840272027260044e-06, "loss": 0.1661, "step": 371810 }, { "epoch": 2.210175294684095, "grad_norm": 4.798050403594971, "learning_rate": 6.8400790986123025e-06, "loss": 0.1521, "step": 371820 }, { "epoch": 2.2102347367607633, "grad_norm": 4.789920330047607, "learning_rate": 6.839886166795723e-06, "loss": 0.1333, "step": 371830 }, { "epoch": 2.2102941788374317, "grad_norm": 5.6830339431762695, "learning_rate": 6.839693231810639e-06, "loss": 0.1589, "step": 371840 }, { "epoch": 2.2103536209141, "grad_norm": 2.3316023349761963, "learning_rate": 6.839500293657386e-06, "loss": 0.1303, "step": 371850 }, { "epoch": 2.2104130629907686, "grad_norm": 3.895470142364502, "learning_rate": 6.839307352336293e-06, "loss": 0.1573, "step": 371860 }, { "epoch": 2.210472505067437, "grad_norm": 4.79058313369751, "learning_rate": 6.839114407847693e-06, "loss": 0.1478, "step": 371870 }, { "epoch": 2.2105319471441054, "grad_norm": 3.396054983139038, "learning_rate": 6.838921460191918e-06, "loss": 0.1352, "step": 371880 }, { "epoch": 2.210591389220774, "grad_norm": 4.55754280090332, "learning_rate": 6.838728509369303e-06, "loss": 0.1391, "step": 371890 }, { "epoch": 2.210650831297442, "grad_norm": 4.768013954162598, "learning_rate": 6.8385355553801765e-06, "loss": 0.1529, "step": 371900 }, { "epoch": 2.2107102733741106, "grad_norm": 3.739163637161255, "learning_rate": 6.838342598224873e-06, "loss": 0.1438, "step": 371910 }, { "epoch": 2.210769715450779, "grad_norm": 5.036288261413574, "learning_rate": 6.8381496379037225e-06, "loss": 0.1578, "step": 371920 }, { "epoch": 2.2108291575274475, "grad_norm": 4.878306865692139, "learning_rate": 6.837956674417061e-06, "loss": 0.1543, "step": 371930 }, { "epoch": 2.210888599604116, "grad_norm": 3.137956142425537, "learning_rate": 6.837763707765218e-06, "loss": 0.137, "step": 371940 }, { "epoch": 2.2109480416807843, "grad_norm": 5.144582748413086, "learning_rate": 6.8375707379485266e-06, "loss": 0.1515, "step": 371950 }, { "epoch": 2.2110074837574527, "grad_norm": 3.841323137283325, "learning_rate": 6.83737776496732e-06, "loss": 0.1622, "step": 371960 }, { "epoch": 2.211066925834121, "grad_norm": 4.450618267059326, "learning_rate": 6.837184788821929e-06, "loss": 0.146, "step": 371970 }, { "epoch": 2.2111263679107895, "grad_norm": 2.699558734893799, "learning_rate": 6.836991809512686e-06, "loss": 0.1497, "step": 371980 }, { "epoch": 2.211185809987458, "grad_norm": 2.775290012359619, "learning_rate": 6.836798827039925e-06, "loss": 0.144, "step": 371990 }, { "epoch": 2.211245252064126, "grad_norm": 5.691376686096191, "learning_rate": 6.836605841403976e-06, "loss": 0.1501, "step": 372000 }, { "epoch": 2.2113046941407943, "grad_norm": 4.996270656585693, "learning_rate": 6.8364128526051745e-06, "loss": 0.1413, "step": 372010 }, { "epoch": 2.2113641362174628, "grad_norm": 5.785406112670898, "learning_rate": 6.83621986064385e-06, "loss": 0.1616, "step": 372020 }, { "epoch": 2.211423578294131, "grad_norm": 4.053130626678467, "learning_rate": 6.8360268655203355e-06, "loss": 0.1537, "step": 372030 }, { "epoch": 2.2114830203707996, "grad_norm": 3.0483243465423584, "learning_rate": 6.835833867234962e-06, "loss": 0.1435, "step": 372040 }, { "epoch": 2.211542462447468, "grad_norm": 3.2564456462860107, "learning_rate": 6.8356408657880665e-06, "loss": 0.1706, "step": 372050 }, { "epoch": 2.2116019045241364, "grad_norm": 4.485306739807129, "learning_rate": 6.835447861179978e-06, "loss": 0.1507, "step": 372060 }, { "epoch": 2.211661346600805, "grad_norm": 3.1598379611968994, "learning_rate": 6.835254853411028e-06, "loss": 0.1654, "step": 372070 }, { "epoch": 2.2117207886774732, "grad_norm": 4.98655366897583, "learning_rate": 6.8350618424815495e-06, "loss": 0.1564, "step": 372080 }, { "epoch": 2.2117802307541417, "grad_norm": 4.016284465789795, "learning_rate": 6.8348688283918785e-06, "loss": 0.1378, "step": 372090 }, { "epoch": 2.21183967283081, "grad_norm": 5.626309394836426, "learning_rate": 6.834675811142342e-06, "loss": 0.1456, "step": 372100 }, { "epoch": 2.2118991149074785, "grad_norm": 5.722828388214111, "learning_rate": 6.8344827907332756e-06, "loss": 0.1499, "step": 372110 }, { "epoch": 2.211958556984147, "grad_norm": 3.1507205963134766, "learning_rate": 6.834289767165011e-06, "loss": 0.1508, "step": 372120 }, { "epoch": 2.2120179990608153, "grad_norm": 3.6044838428497314, "learning_rate": 6.8340967404378796e-06, "loss": 0.1415, "step": 372130 }, { "epoch": 2.2120774411374837, "grad_norm": 3.9600305557250977, "learning_rate": 6.833903710552215e-06, "loss": 0.1764, "step": 372140 }, { "epoch": 2.212136883214152, "grad_norm": 2.9550929069519043, "learning_rate": 6.83371067750835e-06, "loss": 0.1505, "step": 372150 }, { "epoch": 2.2121963252908206, "grad_norm": 3.9516749382019043, "learning_rate": 6.8335176413066164e-06, "loss": 0.1403, "step": 372160 }, { "epoch": 2.2122557673674885, "grad_norm": 3.2796807289123535, "learning_rate": 6.833324601947346e-06, "loss": 0.1452, "step": 372170 }, { "epoch": 2.212315209444157, "grad_norm": 4.385898590087891, "learning_rate": 6.8331315594308735e-06, "loss": 0.1414, "step": 372180 }, { "epoch": 2.2123746515208254, "grad_norm": 6.403580188751221, "learning_rate": 6.8329385137575275e-06, "loss": 0.1504, "step": 372190 }, { "epoch": 2.2124340935974938, "grad_norm": 4.76240348815918, "learning_rate": 6.832745464927645e-06, "loss": 0.1745, "step": 372200 }, { "epoch": 2.212493535674162, "grad_norm": 4.8208184242248535, "learning_rate": 6.832552412941555e-06, "loss": 0.1357, "step": 372210 }, { "epoch": 2.2125529777508306, "grad_norm": 4.130444526672363, "learning_rate": 6.8323593577995905e-06, "loss": 0.1594, "step": 372220 }, { "epoch": 2.212612419827499, "grad_norm": 4.665064334869385, "learning_rate": 6.832166299502086e-06, "loss": 0.1382, "step": 372230 }, { "epoch": 2.2126718619041674, "grad_norm": 3.5036356449127197, "learning_rate": 6.831973238049372e-06, "loss": 0.1611, "step": 372240 }, { "epoch": 2.212731303980836, "grad_norm": 4.89813232421875, "learning_rate": 6.831780173441781e-06, "loss": 0.1471, "step": 372250 }, { "epoch": 2.2127907460575043, "grad_norm": 5.140860557556152, "learning_rate": 6.831587105679645e-06, "loss": 0.1418, "step": 372260 }, { "epoch": 2.2128501881341727, "grad_norm": 4.9989495277404785, "learning_rate": 6.831394034763299e-06, "loss": 0.1595, "step": 372270 }, { "epoch": 2.212909630210841, "grad_norm": 5.047868728637695, "learning_rate": 6.831200960693074e-06, "loss": 0.1746, "step": 372280 }, { "epoch": 2.2129690722875095, "grad_norm": 3.8761918544769287, "learning_rate": 6.831007883469301e-06, "loss": 0.1602, "step": 372290 }, { "epoch": 2.213028514364178, "grad_norm": 4.754329681396484, "learning_rate": 6.830814803092316e-06, "loss": 0.1783, "step": 372300 }, { "epoch": 2.2130879564408463, "grad_norm": 4.999950408935547, "learning_rate": 6.830621719562449e-06, "loss": 0.1629, "step": 372310 }, { "epoch": 2.2131473985175147, "grad_norm": 4.879614353179932, "learning_rate": 6.830428632880032e-06, "loss": 0.1455, "step": 372320 }, { "epoch": 2.213206840594183, "grad_norm": 3.7115886211395264, "learning_rate": 6.830235543045399e-06, "loss": 0.1448, "step": 372330 }, { "epoch": 2.2132662826708516, "grad_norm": 5.192708492279053, "learning_rate": 6.830042450058883e-06, "loss": 0.1678, "step": 372340 }, { "epoch": 2.21332572474752, "grad_norm": 3.8088319301605225, "learning_rate": 6.829849353920813e-06, "loss": 0.1606, "step": 372350 }, { "epoch": 2.213385166824188, "grad_norm": 5.791954040527344, "learning_rate": 6.829656254631525e-06, "loss": 0.1544, "step": 372360 }, { "epoch": 2.2134446089008564, "grad_norm": 3.6160995960235596, "learning_rate": 6.829463152191351e-06, "loss": 0.1391, "step": 372370 }, { "epoch": 2.213504050977525, "grad_norm": 5.027228832244873, "learning_rate": 6.829270046600624e-06, "loss": 0.1505, "step": 372380 }, { "epoch": 2.213563493054193, "grad_norm": 4.597326755523682, "learning_rate": 6.829076937859676e-06, "loss": 0.1462, "step": 372390 }, { "epoch": 2.2136229351308616, "grad_norm": 4.303680896759033, "learning_rate": 6.828883825968837e-06, "loss": 0.1389, "step": 372400 }, { "epoch": 2.21368237720753, "grad_norm": 3.908280849456787, "learning_rate": 6.828690710928444e-06, "loss": 0.1426, "step": 372410 }, { "epoch": 2.2137418192841984, "grad_norm": 4.084629058837891, "learning_rate": 6.828497592738827e-06, "loss": 0.1376, "step": 372420 }, { "epoch": 2.213801261360867, "grad_norm": 4.382295608520508, "learning_rate": 6.828304471400318e-06, "loss": 0.1541, "step": 372430 }, { "epoch": 2.2138607034375353, "grad_norm": 2.6349899768829346, "learning_rate": 6.828111346913251e-06, "loss": 0.1567, "step": 372440 }, { "epoch": 2.2139201455142037, "grad_norm": 5.500185012817383, "learning_rate": 6.827918219277958e-06, "loss": 0.1522, "step": 372450 }, { "epoch": 2.213979587590872, "grad_norm": 4.5252461433410645, "learning_rate": 6.8277250884947725e-06, "loss": 0.1551, "step": 372460 }, { "epoch": 2.2140390296675405, "grad_norm": 4.597229957580566, "learning_rate": 6.827531954564025e-06, "loss": 0.1536, "step": 372470 }, { "epoch": 2.214098471744209, "grad_norm": 3.8472397327423096, "learning_rate": 6.827338817486051e-06, "loss": 0.1713, "step": 372480 }, { "epoch": 2.2141579138208773, "grad_norm": 4.700124263763428, "learning_rate": 6.82714567726118e-06, "loss": 0.1427, "step": 372490 }, { "epoch": 2.2142173558975458, "grad_norm": 2.823017120361328, "learning_rate": 6.826952533889747e-06, "loss": 0.1608, "step": 372500 }, { "epoch": 2.214276797974214, "grad_norm": 3.6930928230285645, "learning_rate": 6.8267593873720835e-06, "loss": 0.1472, "step": 372510 }, { "epoch": 2.2143362400508826, "grad_norm": 3.683269500732422, "learning_rate": 6.826566237708523e-06, "loss": 0.1523, "step": 372520 }, { "epoch": 2.214395682127551, "grad_norm": 3.866645574569702, "learning_rate": 6.826373084899397e-06, "loss": 0.1442, "step": 372530 }, { "epoch": 2.2144551242042194, "grad_norm": 4.3226094245910645, "learning_rate": 6.826179928945038e-06, "loss": 0.15, "step": 372540 }, { "epoch": 2.2145145662808874, "grad_norm": 4.984368324279785, "learning_rate": 6.82598676984578e-06, "loss": 0.1547, "step": 372550 }, { "epoch": 2.214574008357556, "grad_norm": 4.019464015960693, "learning_rate": 6.825793607601955e-06, "loss": 0.1533, "step": 372560 }, { "epoch": 2.214633450434224, "grad_norm": 5.484855651855469, "learning_rate": 6.825600442213895e-06, "loss": 0.1679, "step": 372570 }, { "epoch": 2.2146928925108926, "grad_norm": 4.221081256866455, "learning_rate": 6.825407273681933e-06, "loss": 0.1595, "step": 372580 }, { "epoch": 2.214752334587561, "grad_norm": 4.6517205238342285, "learning_rate": 6.825214102006402e-06, "loss": 0.1439, "step": 372590 }, { "epoch": 2.2148117766642295, "grad_norm": 3.569518804550171, "learning_rate": 6.825020927187636e-06, "loss": 0.1461, "step": 372600 }, { "epoch": 2.214871218740898, "grad_norm": 5.314663887023926, "learning_rate": 6.824827749225965e-06, "loss": 0.1569, "step": 372610 }, { "epoch": 2.2149306608175663, "grad_norm": 5.444640159606934, "learning_rate": 6.824634568121722e-06, "loss": 0.1502, "step": 372620 }, { "epoch": 2.2149901028942347, "grad_norm": 4.565602779388428, "learning_rate": 6.824441383875242e-06, "loss": 0.1458, "step": 372630 }, { "epoch": 2.215049544970903, "grad_norm": 4.813772678375244, "learning_rate": 6.8242481964868565e-06, "loss": 0.15, "step": 372640 }, { "epoch": 2.2151089870475715, "grad_norm": 4.067131519317627, "learning_rate": 6.824055005956896e-06, "loss": 0.1511, "step": 372650 }, { "epoch": 2.21516842912424, "grad_norm": 3.435157299041748, "learning_rate": 6.823861812285697e-06, "loss": 0.16, "step": 372660 }, { "epoch": 2.2152278712009084, "grad_norm": 4.983811855316162, "learning_rate": 6.823668615473591e-06, "loss": 0.1589, "step": 372670 }, { "epoch": 2.2152873132775768, "grad_norm": 4.52750301361084, "learning_rate": 6.823475415520909e-06, "loss": 0.1567, "step": 372680 }, { "epoch": 2.215346755354245, "grad_norm": 5.459890365600586, "learning_rate": 6.823282212427983e-06, "loss": 0.1641, "step": 372690 }, { "epoch": 2.2154061974309136, "grad_norm": 4.373749256134033, "learning_rate": 6.82308900619515e-06, "loss": 0.1325, "step": 372700 }, { "epoch": 2.215465639507582, "grad_norm": 4.735830307006836, "learning_rate": 6.822895796822739e-06, "loss": 0.157, "step": 372710 }, { "epoch": 2.2155250815842504, "grad_norm": 5.061331272125244, "learning_rate": 6.822702584311083e-06, "loss": 0.1492, "step": 372720 }, { "epoch": 2.215584523660919, "grad_norm": 4.895712375640869, "learning_rate": 6.822509368660517e-06, "loss": 0.1367, "step": 372730 }, { "epoch": 2.215643965737587, "grad_norm": 4.897103309631348, "learning_rate": 6.822316149871373e-06, "loss": 0.1512, "step": 372740 }, { "epoch": 2.2157034078142552, "grad_norm": 4.796114921569824, "learning_rate": 6.822122927943982e-06, "loss": 0.1455, "step": 372750 }, { "epoch": 2.2157628498909236, "grad_norm": 4.598363399505615, "learning_rate": 6.821929702878679e-06, "loss": 0.1398, "step": 372760 }, { "epoch": 2.215822291967592, "grad_norm": 4.591724872589111, "learning_rate": 6.821736474675795e-06, "loss": 0.1398, "step": 372770 }, { "epoch": 2.2158817340442605, "grad_norm": 3.787611961364746, "learning_rate": 6.821543243335663e-06, "loss": 0.1641, "step": 372780 }, { "epoch": 2.215941176120929, "grad_norm": 2.386859893798828, "learning_rate": 6.821350008858617e-06, "loss": 0.1475, "step": 372790 }, { "epoch": 2.2160006181975973, "grad_norm": 3.913637399673462, "learning_rate": 6.821156771244987e-06, "loss": 0.1575, "step": 372800 }, { "epoch": 2.2160600602742657, "grad_norm": 4.200207710266113, "learning_rate": 6.8209635304951094e-06, "loss": 0.1529, "step": 372810 }, { "epoch": 2.216119502350934, "grad_norm": 5.401439666748047, "learning_rate": 6.820770286609315e-06, "loss": 0.1578, "step": 372820 }, { "epoch": 2.2161789444276025, "grad_norm": 3.5338425636291504, "learning_rate": 6.820577039587938e-06, "loss": 0.1453, "step": 372830 }, { "epoch": 2.216238386504271, "grad_norm": 4.127466201782227, "learning_rate": 6.820383789431309e-06, "loss": 0.159, "step": 372840 }, { "epoch": 2.2162978285809394, "grad_norm": 5.084109306335449, "learning_rate": 6.820190536139762e-06, "loss": 0.1521, "step": 372850 }, { "epoch": 2.216357270657608, "grad_norm": 4.359081745147705, "learning_rate": 6.81999727971363e-06, "loss": 0.137, "step": 372860 }, { "epoch": 2.216416712734276, "grad_norm": 4.425424575805664, "learning_rate": 6.819804020153245e-06, "loss": 0.1676, "step": 372870 }, { "epoch": 2.2164761548109446, "grad_norm": 4.174578666687012, "learning_rate": 6.819610757458941e-06, "loss": 0.1537, "step": 372880 }, { "epoch": 2.216535596887613, "grad_norm": 3.7606709003448486, "learning_rate": 6.819417491631051e-06, "loss": 0.1728, "step": 372890 }, { "epoch": 2.2165950389642814, "grad_norm": 4.91942834854126, "learning_rate": 6.8192242226699055e-06, "loss": 0.1617, "step": 372900 }, { "epoch": 2.2166544810409494, "grad_norm": 4.189225196838379, "learning_rate": 6.819030950575838e-06, "loss": 0.1668, "step": 372910 }, { "epoch": 2.216713923117618, "grad_norm": 3.9382004737854004, "learning_rate": 6.818837675349184e-06, "loss": 0.1696, "step": 372920 }, { "epoch": 2.2167733651942862, "grad_norm": 4.664560317993164, "learning_rate": 6.818644396990274e-06, "loss": 0.1599, "step": 372930 }, { "epoch": 2.2168328072709547, "grad_norm": 3.630167007446289, "learning_rate": 6.81845111549944e-06, "loss": 0.1684, "step": 372940 }, { "epoch": 2.216892249347623, "grad_norm": 4.766557216644287, "learning_rate": 6.818257830877019e-06, "loss": 0.1511, "step": 372950 }, { "epoch": 2.2169516914242915, "grad_norm": 3.989933729171753, "learning_rate": 6.81806454312334e-06, "loss": 0.174, "step": 372960 }, { "epoch": 2.21701113350096, "grad_norm": 2.759495496749878, "learning_rate": 6.817871252238734e-06, "loss": 0.1384, "step": 372970 }, { "epoch": 2.2170705755776283, "grad_norm": 4.257970809936523, "learning_rate": 6.817677958223541e-06, "loss": 0.1358, "step": 372980 }, { "epoch": 2.2171300176542967, "grad_norm": 5.608534812927246, "learning_rate": 6.8174846610780885e-06, "loss": 0.1443, "step": 372990 }, { "epoch": 2.217189459730965, "grad_norm": 4.57273530960083, "learning_rate": 6.817291360802709e-06, "loss": 0.1659, "step": 373000 }, { "epoch": 2.2172489018076336, "grad_norm": 4.762561798095703, "learning_rate": 6.817098057397738e-06, "loss": 0.1452, "step": 373010 }, { "epoch": 2.217308343884302, "grad_norm": 3.369821548461914, "learning_rate": 6.8169047508635064e-06, "loss": 0.1421, "step": 373020 }, { "epoch": 2.2173677859609704, "grad_norm": 5.641117095947266, "learning_rate": 6.81671144120035e-06, "loss": 0.1653, "step": 373030 }, { "epoch": 2.217427228037639, "grad_norm": 5.202966690063477, "learning_rate": 6.816518128408598e-06, "loss": 0.1526, "step": 373040 }, { "epoch": 2.2174866701143072, "grad_norm": 6.276469707489014, "learning_rate": 6.8163248124885865e-06, "loss": 0.1639, "step": 373050 }, { "epoch": 2.2175461121909756, "grad_norm": 3.4392218589782715, "learning_rate": 6.816131493440646e-06, "loss": 0.1307, "step": 373060 }, { "epoch": 2.217605554267644, "grad_norm": 4.122046947479248, "learning_rate": 6.815938171265109e-06, "loss": 0.1592, "step": 373070 }, { "epoch": 2.2176649963443125, "grad_norm": 5.053572654724121, "learning_rate": 6.815744845962312e-06, "loss": 0.1603, "step": 373080 }, { "epoch": 2.217724438420981, "grad_norm": 4.86447286605835, "learning_rate": 6.815551517532586e-06, "loss": 0.1254, "step": 373090 }, { "epoch": 2.217783880497649, "grad_norm": 4.821194648742676, "learning_rate": 6.815358185976262e-06, "loss": 0.1362, "step": 373100 }, { "epoch": 2.2178433225743173, "grad_norm": 4.6330790519714355, "learning_rate": 6.815164851293675e-06, "loss": 0.152, "step": 373110 }, { "epoch": 2.2179027646509857, "grad_norm": 4.11931037902832, "learning_rate": 6.814971513485158e-06, "loss": 0.1486, "step": 373120 }, { "epoch": 2.217962206727654, "grad_norm": 3.8267319202423096, "learning_rate": 6.814778172551043e-06, "loss": 0.1542, "step": 373130 }, { "epoch": 2.2180216488043225, "grad_norm": 4.052694797515869, "learning_rate": 6.814584828491662e-06, "loss": 0.168, "step": 373140 }, { "epoch": 2.218081090880991, "grad_norm": 3.6968088150024414, "learning_rate": 6.814391481307352e-06, "loss": 0.1393, "step": 373150 }, { "epoch": 2.2181405329576593, "grad_norm": 3.7192373275756836, "learning_rate": 6.814198130998444e-06, "loss": 0.1412, "step": 373160 }, { "epoch": 2.2181999750343278, "grad_norm": 5.044282913208008, "learning_rate": 6.814004777565268e-06, "loss": 0.165, "step": 373170 }, { "epoch": 2.218259417110996, "grad_norm": 5.650112628936768, "learning_rate": 6.813811421008161e-06, "loss": 0.1395, "step": 373180 }, { "epoch": 2.2183188591876646, "grad_norm": 4.884186744689941, "learning_rate": 6.813618061327452e-06, "loss": 0.1637, "step": 373190 }, { "epoch": 2.218378301264333, "grad_norm": 3.243175745010376, "learning_rate": 6.8134246985234785e-06, "loss": 0.1493, "step": 373200 }, { "epoch": 2.2184377433410014, "grad_norm": 3.3298182487487793, "learning_rate": 6.81323133259657e-06, "loss": 0.1628, "step": 373210 }, { "epoch": 2.21849718541767, "grad_norm": 5.851485729217529, "learning_rate": 6.813037963547063e-06, "loss": 0.1612, "step": 373220 }, { "epoch": 2.2185566274943382, "grad_norm": 4.651407241821289, "learning_rate": 6.812844591375285e-06, "loss": 0.1573, "step": 373230 }, { "epoch": 2.2186160695710067, "grad_norm": 3.869306802749634, "learning_rate": 6.812651216081574e-06, "loss": 0.146, "step": 373240 }, { "epoch": 2.218675511647675, "grad_norm": 4.35744571685791, "learning_rate": 6.812457837666262e-06, "loss": 0.1514, "step": 373250 }, { "epoch": 2.2187349537243435, "grad_norm": 3.3235554695129395, "learning_rate": 6.8122644561296805e-06, "loss": 0.1319, "step": 373260 }, { "epoch": 2.218794395801012, "grad_norm": 3.209989547729492, "learning_rate": 6.812071071472163e-06, "loss": 0.1315, "step": 373270 }, { "epoch": 2.2188538378776803, "grad_norm": 3.1839404106140137, "learning_rate": 6.811877683694044e-06, "loss": 0.1411, "step": 373280 }, { "epoch": 2.2189132799543483, "grad_norm": 6.542563438415527, "learning_rate": 6.811684292795655e-06, "loss": 0.1441, "step": 373290 }, { "epoch": 2.2189727220310167, "grad_norm": 3.6320741176605225, "learning_rate": 6.811490898777329e-06, "loss": 0.1542, "step": 373300 }, { "epoch": 2.219032164107685, "grad_norm": 5.137261390686035, "learning_rate": 6.8112975016394e-06, "loss": 0.1598, "step": 373310 }, { "epoch": 2.2190916061843535, "grad_norm": 5.424357891082764, "learning_rate": 6.811104101382201e-06, "loss": 0.1434, "step": 373320 }, { "epoch": 2.219151048261022, "grad_norm": 3.952467918395996, "learning_rate": 6.810910698006064e-06, "loss": 0.152, "step": 373330 }, { "epoch": 2.2192104903376904, "grad_norm": 3.6846044063568115, "learning_rate": 6.8107172915113225e-06, "loss": 0.1277, "step": 373340 }, { "epoch": 2.2192699324143588, "grad_norm": 4.6403489112854, "learning_rate": 6.81052388189831e-06, "loss": 0.1586, "step": 373350 }, { "epoch": 2.219329374491027, "grad_norm": 3.392280340194702, "learning_rate": 6.810330469167359e-06, "loss": 0.1556, "step": 373360 }, { "epoch": 2.2193888165676956, "grad_norm": 4.236139297485352, "learning_rate": 6.810137053318804e-06, "loss": 0.1363, "step": 373370 }, { "epoch": 2.219448258644364, "grad_norm": 5.895082950592041, "learning_rate": 6.809943634352976e-06, "loss": 0.1574, "step": 373380 }, { "epoch": 2.2195077007210324, "grad_norm": 4.97098970413208, "learning_rate": 6.80975021227021e-06, "loss": 0.1415, "step": 373390 }, { "epoch": 2.219567142797701, "grad_norm": 4.286693096160889, "learning_rate": 6.8095567870708366e-06, "loss": 0.1504, "step": 373400 }, { "epoch": 2.2196265848743693, "grad_norm": 4.695085525512695, "learning_rate": 6.809363358755192e-06, "loss": 0.1612, "step": 373410 }, { "epoch": 2.2196860269510377, "grad_norm": 4.2542619705200195, "learning_rate": 6.809169927323608e-06, "loss": 0.1441, "step": 373420 }, { "epoch": 2.219745469027706, "grad_norm": 4.722702503204346, "learning_rate": 6.808976492776416e-06, "loss": 0.163, "step": 373430 }, { "epoch": 2.2198049111043745, "grad_norm": 4.860317230224609, "learning_rate": 6.808783055113952e-06, "loss": 0.1537, "step": 373440 }, { "epoch": 2.219864353181043, "grad_norm": 4.406031608581543, "learning_rate": 6.808589614336548e-06, "loss": 0.1497, "step": 373450 }, { "epoch": 2.2199237952577113, "grad_norm": 3.793905258178711, "learning_rate": 6.808396170444534e-06, "loss": 0.1684, "step": 373460 }, { "epoch": 2.2199832373343797, "grad_norm": 3.332326889038086, "learning_rate": 6.808202723438248e-06, "loss": 0.1489, "step": 373470 }, { "epoch": 2.2200426794110477, "grad_norm": 5.139951705932617, "learning_rate": 6.808009273318023e-06, "loss": 0.1341, "step": 373480 }, { "epoch": 2.220102121487716, "grad_norm": 3.152045726776123, "learning_rate": 6.807815820084188e-06, "loss": 0.1531, "step": 373490 }, { "epoch": 2.2201615635643845, "grad_norm": 4.246812343597412, "learning_rate": 6.8076223637370785e-06, "loss": 0.1485, "step": 373500 }, { "epoch": 2.220221005641053, "grad_norm": 3.4150965213775635, "learning_rate": 6.807428904277029e-06, "loss": 0.1454, "step": 373510 }, { "epoch": 2.2202804477177214, "grad_norm": 4.383677005767822, "learning_rate": 6.8072354417043705e-06, "loss": 0.1447, "step": 373520 }, { "epoch": 2.22033988979439, "grad_norm": 3.6096086502075195, "learning_rate": 6.807041976019437e-06, "loss": 0.1568, "step": 373530 }, { "epoch": 2.220399331871058, "grad_norm": 4.343369960784912, "learning_rate": 6.806848507222562e-06, "loss": 0.1486, "step": 373540 }, { "epoch": 2.2204587739477266, "grad_norm": 4.15118932723999, "learning_rate": 6.806655035314077e-06, "loss": 0.1417, "step": 373550 }, { "epoch": 2.220518216024395, "grad_norm": 3.5860795974731445, "learning_rate": 6.806461560294317e-06, "loss": 0.1532, "step": 373560 }, { "epoch": 2.2205776581010634, "grad_norm": 3.7508084774017334, "learning_rate": 6.806268082163615e-06, "loss": 0.1485, "step": 373570 }, { "epoch": 2.220637100177732, "grad_norm": 5.9693284034729, "learning_rate": 6.806074600922305e-06, "loss": 0.1869, "step": 373580 }, { "epoch": 2.2206965422544003, "grad_norm": 3.9029629230499268, "learning_rate": 6.8058811165707164e-06, "loss": 0.1636, "step": 373590 }, { "epoch": 2.2207559843310687, "grad_norm": 3.653730869293213, "learning_rate": 6.805687629109187e-06, "loss": 0.1327, "step": 373600 }, { "epoch": 2.220815426407737, "grad_norm": 4.741940975189209, "learning_rate": 6.805494138538048e-06, "loss": 0.1572, "step": 373610 }, { "epoch": 2.2208748684844055, "grad_norm": 4.974728584289551, "learning_rate": 6.805300644857631e-06, "loss": 0.1468, "step": 373620 }, { "epoch": 2.220934310561074, "grad_norm": 4.069730758666992, "learning_rate": 6.805107148068273e-06, "loss": 0.1664, "step": 373630 }, { "epoch": 2.2209937526377423, "grad_norm": 4.299169063568115, "learning_rate": 6.804913648170304e-06, "loss": 0.1541, "step": 373640 }, { "epoch": 2.2210531947144103, "grad_norm": 3.73429799079895, "learning_rate": 6.804720145164058e-06, "loss": 0.1535, "step": 373650 }, { "epoch": 2.2211126367910787, "grad_norm": 5.3309807777404785, "learning_rate": 6.8045266390498695e-06, "loss": 0.1389, "step": 373660 }, { "epoch": 2.221172078867747, "grad_norm": 3.5910797119140625, "learning_rate": 6.804333129828071e-06, "loss": 0.1282, "step": 373670 }, { "epoch": 2.2212315209444156, "grad_norm": 4.108007907867432, "learning_rate": 6.8041396174989946e-06, "loss": 0.1431, "step": 373680 }, { "epoch": 2.221290963021084, "grad_norm": 5.230546951293945, "learning_rate": 6.8039461020629734e-06, "loss": 0.1583, "step": 373690 }, { "epoch": 2.2213504050977524, "grad_norm": 4.033797740936279, "learning_rate": 6.803752583520345e-06, "loss": 0.1517, "step": 373700 }, { "epoch": 2.221409847174421, "grad_norm": 5.0789570808410645, "learning_rate": 6.803559061871438e-06, "loss": 0.1461, "step": 373710 }, { "epoch": 2.221469289251089, "grad_norm": 3.876030921936035, "learning_rate": 6.803365537116585e-06, "loss": 0.1672, "step": 373720 }, { "epoch": 2.2215287313277576, "grad_norm": 3.582797050476074, "learning_rate": 6.803172009256124e-06, "loss": 0.1581, "step": 373730 }, { "epoch": 2.221588173404426, "grad_norm": 4.4598588943481445, "learning_rate": 6.802978478290385e-06, "loss": 0.1466, "step": 373740 }, { "epoch": 2.2216476154810945, "grad_norm": 4.480381011962891, "learning_rate": 6.802784944219702e-06, "loss": 0.1488, "step": 373750 }, { "epoch": 2.221707057557763, "grad_norm": 4.404667377471924, "learning_rate": 6.802591407044408e-06, "loss": 0.1577, "step": 373760 }, { "epoch": 2.2217664996344313, "grad_norm": 2.8362109661102295, "learning_rate": 6.802397866764836e-06, "loss": 0.1534, "step": 373770 }, { "epoch": 2.2218259417110997, "grad_norm": 5.087228298187256, "learning_rate": 6.802204323381319e-06, "loss": 0.1578, "step": 373780 }, { "epoch": 2.221885383787768, "grad_norm": 3.377807378768921, "learning_rate": 6.802010776894192e-06, "loss": 0.155, "step": 373790 }, { "epoch": 2.2219448258644365, "grad_norm": 5.140325546264648, "learning_rate": 6.801817227303789e-06, "loss": 0.1606, "step": 373800 }, { "epoch": 2.222004267941105, "grad_norm": 4.439418315887451, "learning_rate": 6.80162367461044e-06, "loss": 0.1559, "step": 373810 }, { "epoch": 2.2220637100177734, "grad_norm": 3.9013655185699463, "learning_rate": 6.801430118814481e-06, "loss": 0.1595, "step": 373820 }, { "epoch": 2.222123152094442, "grad_norm": 3.5622878074645996, "learning_rate": 6.801236559916244e-06, "loss": 0.1471, "step": 373830 }, { "epoch": 2.2221825941711097, "grad_norm": 3.8704731464385986, "learning_rate": 6.801042997916063e-06, "loss": 0.152, "step": 373840 }, { "epoch": 2.222242036247778, "grad_norm": 3.6394920349121094, "learning_rate": 6.8008494328142705e-06, "loss": 0.1376, "step": 373850 }, { "epoch": 2.2223014783244466, "grad_norm": 5.046122074127197, "learning_rate": 6.800655864611201e-06, "loss": 0.1506, "step": 373860 }, { "epoch": 2.222360920401115, "grad_norm": 3.34485125541687, "learning_rate": 6.800462293307187e-06, "loss": 0.1528, "step": 373870 }, { "epoch": 2.2224203624777834, "grad_norm": 4.055648326873779, "learning_rate": 6.800268718902562e-06, "loss": 0.1584, "step": 373880 }, { "epoch": 2.222479804554452, "grad_norm": 4.754453182220459, "learning_rate": 6.800075141397658e-06, "loss": 0.1575, "step": 373890 }, { "epoch": 2.2225392466311202, "grad_norm": 3.5935416221618652, "learning_rate": 6.799881560792813e-06, "loss": 0.1442, "step": 373900 }, { "epoch": 2.2225986887077887, "grad_norm": 4.401040554046631, "learning_rate": 6.799687977088355e-06, "loss": 0.1554, "step": 373910 }, { "epoch": 2.222658130784457, "grad_norm": 4.726014614105225, "learning_rate": 6.79949439028462e-06, "loss": 0.1691, "step": 373920 }, { "epoch": 2.2227175728611255, "grad_norm": 4.9018168449401855, "learning_rate": 6.799300800381941e-06, "loss": 0.1563, "step": 373930 }, { "epoch": 2.222777014937794, "grad_norm": 4.404804229736328, "learning_rate": 6.799107207380652e-06, "loss": 0.1635, "step": 373940 }, { "epoch": 2.2228364570144623, "grad_norm": 2.3593883514404297, "learning_rate": 6.798913611281085e-06, "loss": 0.1419, "step": 373950 }, { "epoch": 2.2228958990911307, "grad_norm": 3.5928163528442383, "learning_rate": 6.798720012083574e-06, "loss": 0.1412, "step": 373960 }, { "epoch": 2.222955341167799, "grad_norm": 4.638437747955322, "learning_rate": 6.798526409788453e-06, "loss": 0.1495, "step": 373970 }, { "epoch": 2.2230147832444676, "grad_norm": 4.406301498413086, "learning_rate": 6.7983328043960554e-06, "loss": 0.1349, "step": 373980 }, { "epoch": 2.223074225321136, "grad_norm": 3.819807291030884, "learning_rate": 6.7981391959067125e-06, "loss": 0.1564, "step": 373990 }, { "epoch": 2.2231336673978044, "grad_norm": 3.7576422691345215, "learning_rate": 6.7979455843207594e-06, "loss": 0.1452, "step": 374000 }, { "epoch": 2.223193109474473, "grad_norm": 4.288867950439453, "learning_rate": 6.797751969638531e-06, "loss": 0.1357, "step": 374010 }, { "epoch": 2.223252551551141, "grad_norm": 4.449662208557129, "learning_rate": 6.797558351860359e-06, "loss": 0.1455, "step": 374020 }, { "epoch": 2.223311993627809, "grad_norm": 3.8382346630096436, "learning_rate": 6.797364730986577e-06, "loss": 0.1585, "step": 374030 }, { "epoch": 2.2233714357044776, "grad_norm": 4.433181285858154, "learning_rate": 6.797171107017517e-06, "loss": 0.1456, "step": 374040 }, { "epoch": 2.223430877781146, "grad_norm": 3.6950130462646484, "learning_rate": 6.796977479953515e-06, "loss": 0.1538, "step": 374050 }, { "epoch": 2.2234903198578144, "grad_norm": 4.753787994384766, "learning_rate": 6.796783849794903e-06, "loss": 0.1646, "step": 374060 }, { "epoch": 2.223549761934483, "grad_norm": 3.2740533351898193, "learning_rate": 6.796590216542016e-06, "loss": 0.1343, "step": 374070 }, { "epoch": 2.2236092040111513, "grad_norm": 5.180919647216797, "learning_rate": 6.796396580195185e-06, "loss": 0.1459, "step": 374080 }, { "epoch": 2.2236686460878197, "grad_norm": 4.183154582977295, "learning_rate": 6.796202940754746e-06, "loss": 0.1633, "step": 374090 }, { "epoch": 2.223728088164488, "grad_norm": 6.208778381347656, "learning_rate": 6.79600929822103e-06, "loss": 0.1378, "step": 374100 }, { "epoch": 2.2237875302411565, "grad_norm": 4.670767784118652, "learning_rate": 6.7958156525943705e-06, "loss": 0.1627, "step": 374110 }, { "epoch": 2.223846972317825, "grad_norm": 4.933609962463379, "learning_rate": 6.7956220038751046e-06, "loss": 0.177, "step": 374120 }, { "epoch": 2.2239064143944933, "grad_norm": 3.760098457336426, "learning_rate": 6.795428352063562e-06, "loss": 0.1341, "step": 374130 }, { "epoch": 2.2239658564711617, "grad_norm": 4.412961006164551, "learning_rate": 6.795234697160078e-06, "loss": 0.1618, "step": 374140 }, { "epoch": 2.22402529854783, "grad_norm": 5.596249580383301, "learning_rate": 6.795041039164986e-06, "loss": 0.1485, "step": 374150 }, { "epoch": 2.2240847406244986, "grad_norm": 3.998382806777954, "learning_rate": 6.794847378078619e-06, "loss": 0.1495, "step": 374160 }, { "epoch": 2.224144182701167, "grad_norm": 4.920649528503418, "learning_rate": 6.7946537139013104e-06, "loss": 0.1441, "step": 374170 }, { "epoch": 2.2242036247778354, "grad_norm": 3.409419536590576, "learning_rate": 6.794460046633394e-06, "loss": 0.1436, "step": 374180 }, { "epoch": 2.224263066854504, "grad_norm": 4.209677696228027, "learning_rate": 6.794266376275205e-06, "loss": 0.1324, "step": 374190 }, { "epoch": 2.2243225089311722, "grad_norm": 4.637548446655273, "learning_rate": 6.794072702827073e-06, "loss": 0.1437, "step": 374200 }, { "epoch": 2.2243819510078406, "grad_norm": 5.330814838409424, "learning_rate": 6.793879026289334e-06, "loss": 0.1511, "step": 374210 }, { "epoch": 2.2244413930845086, "grad_norm": 4.203875541687012, "learning_rate": 6.793685346662321e-06, "loss": 0.1613, "step": 374220 }, { "epoch": 2.224500835161177, "grad_norm": 4.003730773925781, "learning_rate": 6.793491663946369e-06, "loss": 0.153, "step": 374230 }, { "epoch": 2.2245602772378454, "grad_norm": 4.63330078125, "learning_rate": 6.793297978141809e-06, "loss": 0.1633, "step": 374240 }, { "epoch": 2.224619719314514, "grad_norm": 4.764114856719971, "learning_rate": 6.793104289248978e-06, "loss": 0.1451, "step": 374250 }, { "epoch": 2.2246791613911823, "grad_norm": 4.721574306488037, "learning_rate": 6.792910597268205e-06, "loss": 0.1453, "step": 374260 }, { "epoch": 2.2247386034678507, "grad_norm": 3.517416000366211, "learning_rate": 6.792716902199828e-06, "loss": 0.148, "step": 374270 }, { "epoch": 2.224798045544519, "grad_norm": 4.459316730499268, "learning_rate": 6.792523204044178e-06, "loss": 0.1461, "step": 374280 }, { "epoch": 2.2248574876211875, "grad_norm": 4.8817138671875, "learning_rate": 6.792329502801589e-06, "loss": 0.1421, "step": 374290 }, { "epoch": 2.224916929697856, "grad_norm": 4.333572864532471, "learning_rate": 6.792135798472395e-06, "loss": 0.1521, "step": 374300 }, { "epoch": 2.2249763717745243, "grad_norm": 3.5864505767822266, "learning_rate": 6.791942091056929e-06, "loss": 0.149, "step": 374310 }, { "epoch": 2.2250358138511928, "grad_norm": 4.198550224304199, "learning_rate": 6.791748380555525e-06, "loss": 0.1356, "step": 374320 }, { "epoch": 2.225095255927861, "grad_norm": 3.861278772354126, "learning_rate": 6.791554666968515e-06, "loss": 0.1638, "step": 374330 }, { "epoch": 2.2251546980045296, "grad_norm": 5.3974809646606445, "learning_rate": 6.791360950296235e-06, "loss": 0.1727, "step": 374340 }, { "epoch": 2.225214140081198, "grad_norm": 4.137059211730957, "learning_rate": 6.791167230539019e-06, "loss": 0.138, "step": 374350 }, { "epoch": 2.2252735821578664, "grad_norm": 3.5667169094085693, "learning_rate": 6.790973507697198e-06, "loss": 0.1671, "step": 374360 }, { "epoch": 2.225333024234535, "grad_norm": 5.031399726867676, "learning_rate": 6.790779781771107e-06, "loss": 0.14, "step": 374370 }, { "epoch": 2.2253924663112032, "grad_norm": 3.297734022140503, "learning_rate": 6.790586052761081e-06, "loss": 0.1346, "step": 374380 }, { "epoch": 2.225451908387871, "grad_norm": 4.199154853820801, "learning_rate": 6.790392320667451e-06, "loss": 0.1421, "step": 374390 }, { "epoch": 2.2255113504645396, "grad_norm": 3.8899905681610107, "learning_rate": 6.790198585490552e-06, "loss": 0.1498, "step": 374400 }, { "epoch": 2.225570792541208, "grad_norm": 4.29383659362793, "learning_rate": 6.790004847230718e-06, "loss": 0.1684, "step": 374410 }, { "epoch": 2.2256302346178765, "grad_norm": 4.105825901031494, "learning_rate": 6.789811105888282e-06, "loss": 0.1516, "step": 374420 }, { "epoch": 2.225689676694545, "grad_norm": 4.845113754272461, "learning_rate": 6.789617361463576e-06, "loss": 0.1303, "step": 374430 }, { "epoch": 2.2257491187712133, "grad_norm": 3.695122718811035, "learning_rate": 6.789423613956936e-06, "loss": 0.1483, "step": 374440 }, { "epoch": 2.2258085608478817, "grad_norm": 4.101828098297119, "learning_rate": 6.789229863368696e-06, "loss": 0.1453, "step": 374450 }, { "epoch": 2.22586800292455, "grad_norm": 3.9123356342315674, "learning_rate": 6.789036109699189e-06, "loss": 0.1531, "step": 374460 }, { "epoch": 2.2259274450012185, "grad_norm": 3.485733985900879, "learning_rate": 6.788842352948747e-06, "loss": 0.1496, "step": 374470 }, { "epoch": 2.225986887077887, "grad_norm": 3.7050206661224365, "learning_rate": 6.788648593117706e-06, "loss": 0.1588, "step": 374480 }, { "epoch": 2.2260463291545554, "grad_norm": 4.5003862380981445, "learning_rate": 6.788454830206399e-06, "loss": 0.1776, "step": 374490 }, { "epoch": 2.2261057712312238, "grad_norm": 4.275544166564941, "learning_rate": 6.788261064215158e-06, "loss": 0.1562, "step": 374500 }, { "epoch": 2.226165213307892, "grad_norm": 4.664395332336426, "learning_rate": 6.788067295144318e-06, "loss": 0.1599, "step": 374510 }, { "epoch": 2.2262246553845606, "grad_norm": 5.574187755584717, "learning_rate": 6.787873522994215e-06, "loss": 0.1462, "step": 374520 }, { "epoch": 2.226284097461229, "grad_norm": 3.4569833278656006, "learning_rate": 6.787679747765178e-06, "loss": 0.1582, "step": 374530 }, { "epoch": 2.2263435395378974, "grad_norm": 3.303044557571411, "learning_rate": 6.787485969457544e-06, "loss": 0.142, "step": 374540 }, { "epoch": 2.226402981614566, "grad_norm": 3.754089117050171, "learning_rate": 6.787292188071646e-06, "loss": 0.1337, "step": 374550 }, { "epoch": 2.2264624236912343, "grad_norm": 3.8407063484191895, "learning_rate": 6.787098403607818e-06, "loss": 0.1329, "step": 374560 }, { "epoch": 2.2265218657679027, "grad_norm": 4.14695930480957, "learning_rate": 6.786904616066393e-06, "loss": 0.1477, "step": 374570 }, { "epoch": 2.2265813078445706, "grad_norm": 3.6588714122772217, "learning_rate": 6.7867108254477056e-06, "loss": 0.1409, "step": 374580 }, { "epoch": 2.226640749921239, "grad_norm": 3.205730438232422, "learning_rate": 6.786517031752089e-06, "loss": 0.1588, "step": 374590 }, { "epoch": 2.2267001919979075, "grad_norm": 4.481370449066162, "learning_rate": 6.786323234979875e-06, "loss": 0.1618, "step": 374600 }, { "epoch": 2.226759634074576, "grad_norm": 4.017410755157471, "learning_rate": 6.786129435131401e-06, "loss": 0.1558, "step": 374610 }, { "epoch": 2.2268190761512443, "grad_norm": 4.047163009643555, "learning_rate": 6.785935632206999e-06, "loss": 0.1437, "step": 374620 }, { "epoch": 2.2268785182279127, "grad_norm": 4.935319423675537, "learning_rate": 6.785741826207002e-06, "loss": 0.15, "step": 374630 }, { "epoch": 2.226937960304581, "grad_norm": 3.7427618503570557, "learning_rate": 6.785548017131745e-06, "loss": 0.1542, "step": 374640 }, { "epoch": 2.2269974023812495, "grad_norm": 3.369403123855591, "learning_rate": 6.785354204981561e-06, "loss": 0.1307, "step": 374650 }, { "epoch": 2.227056844457918, "grad_norm": 4.716217994689941, "learning_rate": 6.785160389756783e-06, "loss": 0.1507, "step": 374660 }, { "epoch": 2.2271162865345864, "grad_norm": 3.7172365188598633, "learning_rate": 6.784966571457747e-06, "loss": 0.1658, "step": 374670 }, { "epoch": 2.227175728611255, "grad_norm": 3.2094883918762207, "learning_rate": 6.784772750084786e-06, "loss": 0.1429, "step": 374680 }, { "epoch": 2.227235170687923, "grad_norm": 3.968041181564331, "learning_rate": 6.7845789256382325e-06, "loss": 0.1554, "step": 374690 }, { "epoch": 2.2272946127645916, "grad_norm": 4.554338455200195, "learning_rate": 6.7843850981184226e-06, "loss": 0.1537, "step": 374700 }, { "epoch": 2.22735405484126, "grad_norm": 3.9588587284088135, "learning_rate": 6.784191267525687e-06, "loss": 0.1679, "step": 374710 }, { "epoch": 2.2274134969179284, "grad_norm": 5.2030181884765625, "learning_rate": 6.783997433860363e-06, "loss": 0.1376, "step": 374720 }, { "epoch": 2.227472938994597, "grad_norm": 3.109191656112671, "learning_rate": 6.78380359712278e-06, "loss": 0.1355, "step": 374730 }, { "epoch": 2.2275323810712653, "grad_norm": 4.02301549911499, "learning_rate": 6.783609757313276e-06, "loss": 0.1693, "step": 374740 }, { "epoch": 2.2275918231479337, "grad_norm": 4.049118518829346, "learning_rate": 6.783415914432183e-06, "loss": 0.1473, "step": 374750 }, { "epoch": 2.227651265224602, "grad_norm": 4.240685939788818, "learning_rate": 6.7832220684798346e-06, "loss": 0.1426, "step": 374760 }, { "epoch": 2.22771070730127, "grad_norm": 4.573006629943848, "learning_rate": 6.783028219456564e-06, "loss": 0.1497, "step": 374770 }, { "epoch": 2.2277701493779385, "grad_norm": 4.2499613761901855, "learning_rate": 6.782834367362708e-06, "loss": 0.1502, "step": 374780 }, { "epoch": 2.227829591454607, "grad_norm": 3.3782432079315186, "learning_rate": 6.7826405121985975e-06, "loss": 0.1526, "step": 374790 }, { "epoch": 2.2278890335312753, "grad_norm": 3.661092758178711, "learning_rate": 6.782446653964568e-06, "loss": 0.1242, "step": 374800 }, { "epoch": 2.2279484756079437, "grad_norm": 3.5288007259368896, "learning_rate": 6.782252792660953e-06, "loss": 0.1492, "step": 374810 }, { "epoch": 2.228007917684612, "grad_norm": 4.679116249084473, "learning_rate": 6.782058928288084e-06, "loss": 0.1598, "step": 374820 }, { "epoch": 2.2280673597612806, "grad_norm": 4.931813716888428, "learning_rate": 6.7818650608462995e-06, "loss": 0.1564, "step": 374830 }, { "epoch": 2.228126801837949, "grad_norm": 4.348132610321045, "learning_rate": 6.78167119033593e-06, "loss": 0.1457, "step": 374840 }, { "epoch": 2.2281862439146174, "grad_norm": 3.369560718536377, "learning_rate": 6.781477316757309e-06, "loss": 0.1466, "step": 374850 }, { "epoch": 2.228245685991286, "grad_norm": 4.550581455230713, "learning_rate": 6.781283440110773e-06, "loss": 0.1562, "step": 374860 }, { "epoch": 2.228305128067954, "grad_norm": 4.986267566680908, "learning_rate": 6.781089560396654e-06, "loss": 0.1417, "step": 374870 }, { "epoch": 2.2283645701446226, "grad_norm": 3.9032142162323, "learning_rate": 6.780895677615285e-06, "loss": 0.1506, "step": 374880 }, { "epoch": 2.228424012221291, "grad_norm": 4.764578342437744, "learning_rate": 6.7807017917670014e-06, "loss": 0.1415, "step": 374890 }, { "epoch": 2.2284834542979595, "grad_norm": 4.705167293548584, "learning_rate": 6.780507902852138e-06, "loss": 0.1481, "step": 374900 }, { "epoch": 2.228542896374628, "grad_norm": 3.361856460571289, "learning_rate": 6.780314010871028e-06, "loss": 0.1518, "step": 374910 }, { "epoch": 2.2286023384512963, "grad_norm": 3.9486958980560303, "learning_rate": 6.780120115824003e-06, "loss": 0.156, "step": 374920 }, { "epoch": 2.2286617805279647, "grad_norm": 5.326202869415283, "learning_rate": 6.779926217711399e-06, "loss": 0.1469, "step": 374930 }, { "epoch": 2.228721222604633, "grad_norm": 4.787135601043701, "learning_rate": 6.779732316533551e-06, "loss": 0.1659, "step": 374940 }, { "epoch": 2.2287806646813015, "grad_norm": 4.916319370269775, "learning_rate": 6.779538412290789e-06, "loss": 0.1541, "step": 374950 }, { "epoch": 2.2288401067579695, "grad_norm": 5.388507843017578, "learning_rate": 6.779344504983453e-06, "loss": 0.155, "step": 374960 }, { "epoch": 2.228899548834638, "grad_norm": 4.602472305297852, "learning_rate": 6.779150594611872e-06, "loss": 0.1288, "step": 374970 }, { "epoch": 2.2289589909113063, "grad_norm": 3.83439040184021, "learning_rate": 6.778956681176381e-06, "loss": 0.1436, "step": 374980 }, { "epoch": 2.2290184329879748, "grad_norm": 3.6401243209838867, "learning_rate": 6.778762764677313e-06, "loss": 0.1581, "step": 374990 }, { "epoch": 2.229077875064643, "grad_norm": 4.134979248046875, "learning_rate": 6.778568845115005e-06, "loss": 0.1377, "step": 375000 }, { "epoch": 2.2291373171413116, "grad_norm": 3.1328909397125244, "learning_rate": 6.77837492248979e-06, "loss": 0.1412, "step": 375010 }, { "epoch": 2.22919675921798, "grad_norm": 4.504980564117432, "learning_rate": 6.7781809968019994e-06, "loss": 0.1371, "step": 375020 }, { "epoch": 2.2292562012946484, "grad_norm": 5.354735374450684, "learning_rate": 6.77798706805197e-06, "loss": 0.1716, "step": 375030 }, { "epoch": 2.229315643371317, "grad_norm": 4.601244926452637, "learning_rate": 6.777793136240035e-06, "loss": 0.1585, "step": 375040 }, { "epoch": 2.2293750854479852, "grad_norm": 4.556898593902588, "learning_rate": 6.777599201366527e-06, "loss": 0.139, "step": 375050 }, { "epoch": 2.2294345275246537, "grad_norm": 4.266128063201904, "learning_rate": 6.7774052634317825e-06, "loss": 0.1494, "step": 375060 }, { "epoch": 2.229493969601322, "grad_norm": 4.287558078765869, "learning_rate": 6.777211322436133e-06, "loss": 0.1354, "step": 375070 }, { "epoch": 2.2295534116779905, "grad_norm": 4.106594562530518, "learning_rate": 6.777017378379913e-06, "loss": 0.1432, "step": 375080 }, { "epoch": 2.229612853754659, "grad_norm": 4.504530906677246, "learning_rate": 6.776823431263459e-06, "loss": 0.1463, "step": 375090 }, { "epoch": 2.2296722958313273, "grad_norm": 5.825259685516357, "learning_rate": 6.776629481087101e-06, "loss": 0.1536, "step": 375100 }, { "epoch": 2.2297317379079957, "grad_norm": 4.091806411743164, "learning_rate": 6.7764355278511765e-06, "loss": 0.1617, "step": 375110 }, { "epoch": 2.229791179984664, "grad_norm": 4.1704511642456055, "learning_rate": 6.776241571556017e-06, "loss": 0.1364, "step": 375120 }, { "epoch": 2.229850622061332, "grad_norm": 5.252626419067383, "learning_rate": 6.776047612201958e-06, "loss": 0.1336, "step": 375130 }, { "epoch": 2.2299100641380005, "grad_norm": 2.8868417739868164, "learning_rate": 6.775853649789334e-06, "loss": 0.1455, "step": 375140 }, { "epoch": 2.229969506214669, "grad_norm": 4.5563554763793945, "learning_rate": 6.775659684318476e-06, "loss": 0.1601, "step": 375150 }, { "epoch": 2.2300289482913374, "grad_norm": 5.308988571166992, "learning_rate": 6.775465715789722e-06, "loss": 0.1629, "step": 375160 }, { "epoch": 2.2300883903680058, "grad_norm": 4.054299354553223, "learning_rate": 6.775271744203404e-06, "loss": 0.1324, "step": 375170 }, { "epoch": 2.230147832444674, "grad_norm": 3.5612540245056152, "learning_rate": 6.775077769559856e-06, "loss": 0.1437, "step": 375180 }, { "epoch": 2.2302072745213426, "grad_norm": 4.697723865509033, "learning_rate": 6.774883791859413e-06, "loss": 0.1458, "step": 375190 }, { "epoch": 2.230266716598011, "grad_norm": 4.206998348236084, "learning_rate": 6.774689811102407e-06, "loss": 0.1638, "step": 375200 }, { "epoch": 2.2303261586746794, "grad_norm": 4.123305797576904, "learning_rate": 6.774495827289174e-06, "loss": 0.1355, "step": 375210 }, { "epoch": 2.230385600751348, "grad_norm": 6.390398025512695, "learning_rate": 6.774301840420046e-06, "loss": 0.1581, "step": 375220 }, { "epoch": 2.2304450428280163, "grad_norm": 2.6388275623321533, "learning_rate": 6.7741078504953605e-06, "loss": 0.1457, "step": 375230 }, { "epoch": 2.2305044849046847, "grad_norm": 4.162267684936523, "learning_rate": 6.773913857515449e-06, "loss": 0.1478, "step": 375240 }, { "epoch": 2.230563926981353, "grad_norm": 4.811756610870361, "learning_rate": 6.7737198614806454e-06, "loss": 0.1637, "step": 375250 }, { "epoch": 2.2306233690580215, "grad_norm": 5.085855484008789, "learning_rate": 6.773525862391286e-06, "loss": 0.1569, "step": 375260 }, { "epoch": 2.23068281113469, "grad_norm": 3.6549036502838135, "learning_rate": 6.773331860247703e-06, "loss": 0.1413, "step": 375270 }, { "epoch": 2.2307422532113583, "grad_norm": 4.202503204345703, "learning_rate": 6.77313785505023e-06, "loss": 0.1596, "step": 375280 }, { "epoch": 2.2308016952880267, "grad_norm": 4.455747604370117, "learning_rate": 6.772943846799203e-06, "loss": 0.1557, "step": 375290 }, { "epoch": 2.230861137364695, "grad_norm": 3.5557007789611816, "learning_rate": 6.772749835494956e-06, "loss": 0.1534, "step": 375300 }, { "epoch": 2.2309205794413636, "grad_norm": 4.194819450378418, "learning_rate": 6.772555821137821e-06, "loss": 0.1456, "step": 375310 }, { "epoch": 2.2309800215180315, "grad_norm": 5.847171306610107, "learning_rate": 6.772361803728132e-06, "loss": 0.1578, "step": 375320 }, { "epoch": 2.2310394635947, "grad_norm": 3.5837690830230713, "learning_rate": 6.772167783266226e-06, "loss": 0.1485, "step": 375330 }, { "epoch": 2.2310989056713684, "grad_norm": 3.9358718395233154, "learning_rate": 6.7719737597524345e-06, "loss": 0.1403, "step": 375340 }, { "epoch": 2.231158347748037, "grad_norm": 3.9253273010253906, "learning_rate": 6.7717797331870945e-06, "loss": 0.139, "step": 375350 }, { "epoch": 2.231217789824705, "grad_norm": 5.3313398361206055, "learning_rate": 6.771585703570539e-06, "loss": 0.1496, "step": 375360 }, { "epoch": 2.2312772319013736, "grad_norm": 3.730433464050293, "learning_rate": 6.7713916709031e-06, "loss": 0.1441, "step": 375370 }, { "epoch": 2.231336673978042, "grad_norm": 4.650086402893066, "learning_rate": 6.771197635185114e-06, "loss": 0.1383, "step": 375380 }, { "epoch": 2.2313961160547104, "grad_norm": 4.5841474533081055, "learning_rate": 6.771003596416914e-06, "loss": 0.1413, "step": 375390 }, { "epoch": 2.231455558131379, "grad_norm": 5.505262851715088, "learning_rate": 6.770809554598834e-06, "loss": 0.1386, "step": 375400 }, { "epoch": 2.2315150002080473, "grad_norm": 6.525976181030273, "learning_rate": 6.770615509731209e-06, "loss": 0.1881, "step": 375410 }, { "epoch": 2.2315744422847157, "grad_norm": 3.526282787322998, "learning_rate": 6.770421461814374e-06, "loss": 0.1475, "step": 375420 }, { "epoch": 2.231633884361384, "grad_norm": 6.799838066101074, "learning_rate": 6.77022741084866e-06, "loss": 0.1458, "step": 375430 }, { "epoch": 2.2316933264380525, "grad_norm": 3.7887794971466064, "learning_rate": 6.770033356834403e-06, "loss": 0.1479, "step": 375440 }, { "epoch": 2.231752768514721, "grad_norm": 5.44864559173584, "learning_rate": 6.769839299771939e-06, "loss": 0.1372, "step": 375450 }, { "epoch": 2.2318122105913893, "grad_norm": 4.70891809463501, "learning_rate": 6.7696452396615995e-06, "loss": 0.162, "step": 375460 }, { "epoch": 2.2318716526680578, "grad_norm": 4.2138285636901855, "learning_rate": 6.7694511765037196e-06, "loss": 0.1471, "step": 375470 }, { "epoch": 2.231931094744726, "grad_norm": 3.530207633972168, "learning_rate": 6.769257110298635e-06, "loss": 0.1468, "step": 375480 }, { "epoch": 2.2319905368213946, "grad_norm": 5.921180248260498, "learning_rate": 6.7690630410466785e-06, "loss": 0.1599, "step": 375490 }, { "epoch": 2.232049978898063, "grad_norm": 4.495898246765137, "learning_rate": 6.768868968748182e-06, "loss": 0.1494, "step": 375500 }, { "epoch": 2.232109420974731, "grad_norm": 3.320802688598633, "learning_rate": 6.768674893403485e-06, "loss": 0.1256, "step": 375510 }, { "epoch": 2.2321688630513994, "grad_norm": 4.0473175048828125, "learning_rate": 6.768480815012918e-06, "loss": 0.1452, "step": 375520 }, { "epoch": 2.232228305128068, "grad_norm": 4.585482597351074, "learning_rate": 6.768286733576814e-06, "loss": 0.1452, "step": 375530 }, { "epoch": 2.232287747204736, "grad_norm": 4.736367702484131, "learning_rate": 6.768092649095511e-06, "loss": 0.1759, "step": 375540 }, { "epoch": 2.2323471892814046, "grad_norm": 3.4248099327087402, "learning_rate": 6.767898561569342e-06, "loss": 0.1617, "step": 375550 }, { "epoch": 2.232406631358073, "grad_norm": 4.105213642120361, "learning_rate": 6.767704470998639e-06, "loss": 0.1614, "step": 375560 }, { "epoch": 2.2324660734347415, "grad_norm": 4.923183917999268, "learning_rate": 6.767510377383739e-06, "loss": 0.1686, "step": 375570 }, { "epoch": 2.23252551551141, "grad_norm": 5.550907135009766, "learning_rate": 6.767316280724976e-06, "loss": 0.1672, "step": 375580 }, { "epoch": 2.2325849575880783, "grad_norm": 4.319040775299072, "learning_rate": 6.7671221810226826e-06, "loss": 0.143, "step": 375590 }, { "epoch": 2.2326443996647467, "grad_norm": 4.015806198120117, "learning_rate": 6.766928078277194e-06, "loss": 0.1677, "step": 375600 }, { "epoch": 2.232703841741415, "grad_norm": 4.696340560913086, "learning_rate": 6.766733972488845e-06, "loss": 0.1336, "step": 375610 }, { "epoch": 2.2327632838180835, "grad_norm": 3.914952516555786, "learning_rate": 6.766539863657969e-06, "loss": 0.1615, "step": 375620 }, { "epoch": 2.232822725894752, "grad_norm": 3.6957881450653076, "learning_rate": 6.766345751784899e-06, "loss": 0.1526, "step": 375630 }, { "epoch": 2.2328821679714204, "grad_norm": 4.577016353607178, "learning_rate": 6.766151636869973e-06, "loss": 0.14, "step": 375640 }, { "epoch": 2.2329416100480888, "grad_norm": 6.311221122741699, "learning_rate": 6.765957518913522e-06, "loss": 0.158, "step": 375650 }, { "epoch": 2.233001052124757, "grad_norm": 3.0686733722686768, "learning_rate": 6.765763397915882e-06, "loss": 0.1324, "step": 375660 }, { "epoch": 2.2330604942014256, "grad_norm": 4.99302864074707, "learning_rate": 6.765569273877386e-06, "loss": 0.1516, "step": 375670 }, { "epoch": 2.2331199362780936, "grad_norm": 4.192450523376465, "learning_rate": 6.765375146798371e-06, "loss": 0.1518, "step": 375680 }, { "epoch": 2.2331793783547624, "grad_norm": 3.8890810012817383, "learning_rate": 6.765181016679168e-06, "loss": 0.1666, "step": 375690 }, { "epoch": 2.2332388204314304, "grad_norm": 4.506772994995117, "learning_rate": 6.764986883520112e-06, "loss": 0.1542, "step": 375700 }, { "epoch": 2.233298262508099, "grad_norm": 5.194519996643066, "learning_rate": 6.764792747321539e-06, "loss": 0.1538, "step": 375710 }, { "epoch": 2.2333577045847672, "grad_norm": 6.713613510131836, "learning_rate": 6.764598608083782e-06, "loss": 0.1621, "step": 375720 }, { "epoch": 2.2334171466614356, "grad_norm": 4.1281418800354, "learning_rate": 6.764404465807175e-06, "loss": 0.1427, "step": 375730 }, { "epoch": 2.233476588738104, "grad_norm": 4.684013843536377, "learning_rate": 6.764210320492054e-06, "loss": 0.1682, "step": 375740 }, { "epoch": 2.2335360308147725, "grad_norm": 5.442378044128418, "learning_rate": 6.764016172138752e-06, "loss": 0.1482, "step": 375750 }, { "epoch": 2.233595472891441, "grad_norm": 3.096736431121826, "learning_rate": 6.763822020747603e-06, "loss": 0.1427, "step": 375760 }, { "epoch": 2.2336549149681093, "grad_norm": 4.519081115722656, "learning_rate": 6.763627866318943e-06, "loss": 0.1295, "step": 375770 }, { "epoch": 2.2337143570447777, "grad_norm": 4.908665180206299, "learning_rate": 6.763433708853105e-06, "loss": 0.1302, "step": 375780 }, { "epoch": 2.233773799121446, "grad_norm": 5.614208221435547, "learning_rate": 6.763239548350424e-06, "loss": 0.1552, "step": 375790 }, { "epoch": 2.2338332411981145, "grad_norm": 5.28400993347168, "learning_rate": 6.763045384811233e-06, "loss": 0.1573, "step": 375800 }, { "epoch": 2.233892683274783, "grad_norm": 4.108134746551514, "learning_rate": 6.762851218235868e-06, "loss": 0.1498, "step": 375810 }, { "epoch": 2.2339521253514514, "grad_norm": 4.014326095581055, "learning_rate": 6.7626570486246645e-06, "loss": 0.143, "step": 375820 }, { "epoch": 2.23401156742812, "grad_norm": 5.010247230529785, "learning_rate": 6.762462875977953e-06, "loss": 0.1471, "step": 375830 }, { "epoch": 2.234071009504788, "grad_norm": 5.137758255004883, "learning_rate": 6.762268700296072e-06, "loss": 0.1423, "step": 375840 }, { "epoch": 2.2341304515814566, "grad_norm": 3.7944412231445312, "learning_rate": 6.762074521579354e-06, "loss": 0.1529, "step": 375850 }, { "epoch": 2.234189893658125, "grad_norm": 4.249939918518066, "learning_rate": 6.761880339828131e-06, "loss": 0.1425, "step": 375860 }, { "epoch": 2.234249335734793, "grad_norm": 4.6351118087768555, "learning_rate": 6.761686155042741e-06, "loss": 0.1563, "step": 375870 }, { "epoch": 2.2343087778114614, "grad_norm": 4.833116054534912, "learning_rate": 6.761491967223518e-06, "loss": 0.1356, "step": 375880 }, { "epoch": 2.23436821988813, "grad_norm": 4.557572364807129, "learning_rate": 6.761297776370796e-06, "loss": 0.1338, "step": 375890 }, { "epoch": 2.2344276619647983, "grad_norm": 4.132071018218994, "learning_rate": 6.761103582484907e-06, "loss": 0.1634, "step": 375900 }, { "epoch": 2.2344871040414667, "grad_norm": 2.905067205429077, "learning_rate": 6.76090938556619e-06, "loss": 0.1521, "step": 375910 }, { "epoch": 2.234546546118135, "grad_norm": 3.59977650642395, "learning_rate": 6.760715185614975e-06, "loss": 0.1512, "step": 375920 }, { "epoch": 2.2346059881948035, "grad_norm": 3.861565589904785, "learning_rate": 6.7605209826315994e-06, "loss": 0.1374, "step": 375930 }, { "epoch": 2.234665430271472, "grad_norm": 3.8402528762817383, "learning_rate": 6.760326776616397e-06, "loss": 0.1475, "step": 375940 }, { "epoch": 2.2347248723481403, "grad_norm": 4.133006572723389, "learning_rate": 6.760132567569702e-06, "loss": 0.1476, "step": 375950 }, { "epoch": 2.2347843144248087, "grad_norm": 4.430222034454346, "learning_rate": 6.759938355491846e-06, "loss": 0.1495, "step": 375960 }, { "epoch": 2.234843756501477, "grad_norm": 4.0724921226501465, "learning_rate": 6.759744140383168e-06, "loss": 0.1533, "step": 375970 }, { "epoch": 2.2349031985781456, "grad_norm": 3.433089256286621, "learning_rate": 6.759549922244001e-06, "loss": 0.1433, "step": 375980 }, { "epoch": 2.234962640654814, "grad_norm": 3.370969295501709, "learning_rate": 6.759355701074678e-06, "loss": 0.1587, "step": 375990 }, { "epoch": 2.2350220827314824, "grad_norm": 4.901422500610352, "learning_rate": 6.759161476875536e-06, "loss": 0.1522, "step": 376000 }, { "epoch": 2.235081524808151, "grad_norm": 5.823450565338135, "learning_rate": 6.758967249646907e-06, "loss": 0.128, "step": 376010 }, { "epoch": 2.2351409668848192, "grad_norm": 3.3169941902160645, "learning_rate": 6.758773019389126e-06, "loss": 0.153, "step": 376020 }, { "epoch": 2.2352004089614876, "grad_norm": 3.5378763675689697, "learning_rate": 6.75857878610253e-06, "loss": 0.1433, "step": 376030 }, { "epoch": 2.235259851038156, "grad_norm": 4.53425407409668, "learning_rate": 6.758384549787451e-06, "loss": 0.1542, "step": 376040 }, { "epoch": 2.2353192931148245, "grad_norm": 4.552994251251221, "learning_rate": 6.758190310444224e-06, "loss": 0.1492, "step": 376050 }, { "epoch": 2.2353787351914924, "grad_norm": 4.464156150817871, "learning_rate": 6.757996068073181e-06, "loss": 0.1462, "step": 376060 }, { "epoch": 2.235438177268161, "grad_norm": 4.492576599121094, "learning_rate": 6.7578018226746625e-06, "loss": 0.1594, "step": 376070 }, { "epoch": 2.2354976193448293, "grad_norm": 5.209679126739502, "learning_rate": 6.757607574248998e-06, "loss": 0.1782, "step": 376080 }, { "epoch": 2.2355570614214977, "grad_norm": 3.6706583499908447, "learning_rate": 6.757413322796522e-06, "loss": 0.1489, "step": 376090 }, { "epoch": 2.235616503498166, "grad_norm": 3.5494022369384766, "learning_rate": 6.757219068317572e-06, "loss": 0.1461, "step": 376100 }, { "epoch": 2.2356759455748345, "grad_norm": 5.126410484313965, "learning_rate": 6.7570248108124815e-06, "loss": 0.1678, "step": 376110 }, { "epoch": 2.235735387651503, "grad_norm": 5.675537586212158, "learning_rate": 6.756830550281584e-06, "loss": 0.1796, "step": 376120 }, { "epoch": 2.2357948297281713, "grad_norm": 4.436142921447754, "learning_rate": 6.756636286725216e-06, "loss": 0.1576, "step": 376130 }, { "epoch": 2.2358542718048398, "grad_norm": 3.963575601577759, "learning_rate": 6.75644202014371e-06, "loss": 0.154, "step": 376140 }, { "epoch": 2.235913713881508, "grad_norm": 3.7779805660247803, "learning_rate": 6.756247750537399e-06, "loss": 0.146, "step": 376150 }, { "epoch": 2.2359731559581766, "grad_norm": 4.58765172958374, "learning_rate": 6.756053477906623e-06, "loss": 0.1455, "step": 376160 }, { "epoch": 2.236032598034845, "grad_norm": 4.704326152801514, "learning_rate": 6.755859202251712e-06, "loss": 0.1493, "step": 376170 }, { "epoch": 2.2360920401115134, "grad_norm": 4.988208770751953, "learning_rate": 6.755664923573002e-06, "loss": 0.1588, "step": 376180 }, { "epoch": 2.236151482188182, "grad_norm": 3.8960464000701904, "learning_rate": 6.7554706418708274e-06, "loss": 0.1386, "step": 376190 }, { "epoch": 2.2362109242648502, "grad_norm": 4.229633331298828, "learning_rate": 6.755276357145523e-06, "loss": 0.1531, "step": 376200 }, { "epoch": 2.2362703663415187, "grad_norm": 4.256810665130615, "learning_rate": 6.755082069397423e-06, "loss": 0.1539, "step": 376210 }, { "epoch": 2.236329808418187, "grad_norm": 3.816638708114624, "learning_rate": 6.754887778626862e-06, "loss": 0.1305, "step": 376220 }, { "epoch": 2.2363892504948555, "grad_norm": 3.8624517917633057, "learning_rate": 6.754693484834176e-06, "loss": 0.1601, "step": 376230 }, { "epoch": 2.236448692571524, "grad_norm": 6.638247013092041, "learning_rate": 6.754499188019699e-06, "loss": 0.1826, "step": 376240 }, { "epoch": 2.236508134648192, "grad_norm": 3.519923686981201, "learning_rate": 6.754304888183763e-06, "loss": 0.1539, "step": 376250 }, { "epoch": 2.2365675767248603, "grad_norm": 6.36019229888916, "learning_rate": 6.754110585326705e-06, "loss": 0.1602, "step": 376260 }, { "epoch": 2.2366270188015287, "grad_norm": 2.6756856441497803, "learning_rate": 6.753916279448861e-06, "loss": 0.1463, "step": 376270 }, { "epoch": 2.236686460878197, "grad_norm": 3.3997561931610107, "learning_rate": 6.753721970550562e-06, "loss": 0.1577, "step": 376280 }, { "epoch": 2.2367459029548655, "grad_norm": 4.552953720092773, "learning_rate": 6.753527658632147e-06, "loss": 0.1505, "step": 376290 }, { "epoch": 2.236805345031534, "grad_norm": 4.455814838409424, "learning_rate": 6.753333343693947e-06, "loss": 0.1429, "step": 376300 }, { "epoch": 2.2368647871082024, "grad_norm": 3.1781506538391113, "learning_rate": 6.753139025736295e-06, "loss": 0.1266, "step": 376310 }, { "epoch": 2.2369242291848708, "grad_norm": 4.849611282348633, "learning_rate": 6.75294470475953e-06, "loss": 0.1502, "step": 376320 }, { "epoch": 2.236983671261539, "grad_norm": 4.490359306335449, "learning_rate": 6.752750380763986e-06, "loss": 0.1437, "step": 376330 }, { "epoch": 2.2370431133382076, "grad_norm": 3.4761054515838623, "learning_rate": 6.752556053749997e-06, "loss": 0.1501, "step": 376340 }, { "epoch": 2.237102555414876, "grad_norm": 3.5045294761657715, "learning_rate": 6.752361723717896e-06, "loss": 0.1453, "step": 376350 }, { "epoch": 2.2371619974915444, "grad_norm": 3.125363826751709, "learning_rate": 6.752167390668021e-06, "loss": 0.1461, "step": 376360 }, { "epoch": 2.237221439568213, "grad_norm": 5.006322860717773, "learning_rate": 6.751973054600704e-06, "loss": 0.1711, "step": 376370 }, { "epoch": 2.2372808816448813, "grad_norm": 4.608162879943848, "learning_rate": 6.7517787155162796e-06, "loss": 0.1625, "step": 376380 }, { "epoch": 2.2373403237215497, "grad_norm": 4.140378475189209, "learning_rate": 6.751584373415083e-06, "loss": 0.1638, "step": 376390 }, { "epoch": 2.237399765798218, "grad_norm": 4.376871109008789, "learning_rate": 6.75139002829745e-06, "loss": 0.1377, "step": 376400 }, { "epoch": 2.2374592078748865, "grad_norm": 4.6289896965026855, "learning_rate": 6.751195680163713e-06, "loss": 0.141, "step": 376410 }, { "epoch": 2.2375186499515545, "grad_norm": 5.285983085632324, "learning_rate": 6.7510013290142084e-06, "loss": 0.1533, "step": 376420 }, { "epoch": 2.2375780920282233, "grad_norm": 3.395367383956909, "learning_rate": 6.750806974849272e-06, "loss": 0.139, "step": 376430 }, { "epoch": 2.2376375341048913, "grad_norm": 4.73589563369751, "learning_rate": 6.750612617669236e-06, "loss": 0.1457, "step": 376440 }, { "epoch": 2.2376969761815597, "grad_norm": 3.9234142303466797, "learning_rate": 6.750418257474437e-06, "loss": 0.1405, "step": 376450 }, { "epoch": 2.237756418258228, "grad_norm": 4.30494499206543, "learning_rate": 6.750223894265208e-06, "loss": 0.1558, "step": 376460 }, { "epoch": 2.2378158603348965, "grad_norm": 4.413114070892334, "learning_rate": 6.750029528041886e-06, "loss": 0.1474, "step": 376470 }, { "epoch": 2.237875302411565, "grad_norm": 5.248721122741699, "learning_rate": 6.7498351588048024e-06, "loss": 0.1614, "step": 376480 }, { "epoch": 2.2379347444882334, "grad_norm": 5.628000736236572, "learning_rate": 6.749640786554296e-06, "loss": 0.1352, "step": 376490 }, { "epoch": 2.237994186564902, "grad_norm": 5.170408248901367, "learning_rate": 6.749446411290699e-06, "loss": 0.1609, "step": 376500 }, { "epoch": 2.23805362864157, "grad_norm": 5.089520454406738, "learning_rate": 6.749252033014345e-06, "loss": 0.1407, "step": 376510 }, { "epoch": 2.2381130707182386, "grad_norm": 4.318954944610596, "learning_rate": 6.749057651725571e-06, "loss": 0.1551, "step": 376520 }, { "epoch": 2.238172512794907, "grad_norm": 3.6849427223205566, "learning_rate": 6.748863267424711e-06, "loss": 0.1644, "step": 376530 }, { "epoch": 2.2382319548715754, "grad_norm": 3.8423829078674316, "learning_rate": 6.748668880112101e-06, "loss": 0.1641, "step": 376540 }, { "epoch": 2.238291396948244, "grad_norm": 5.202905654907227, "learning_rate": 6.748474489788073e-06, "loss": 0.1693, "step": 376550 }, { "epoch": 2.2383508390249123, "grad_norm": 2.909970998764038, "learning_rate": 6.748280096452964e-06, "loss": 0.1361, "step": 376560 }, { "epoch": 2.2384102811015807, "grad_norm": 4.219055652618408, "learning_rate": 6.748085700107107e-06, "loss": 0.175, "step": 376570 }, { "epoch": 2.238469723178249, "grad_norm": 5.459166049957275, "learning_rate": 6.747891300750838e-06, "loss": 0.1487, "step": 376580 }, { "epoch": 2.2385291652549175, "grad_norm": 4.410305976867676, "learning_rate": 6.747696898384493e-06, "loss": 0.1653, "step": 376590 }, { "epoch": 2.238588607331586, "grad_norm": 4.460993766784668, "learning_rate": 6.747502493008406e-06, "loss": 0.1429, "step": 376600 }, { "epoch": 2.238648049408254, "grad_norm": 4.680966854095459, "learning_rate": 6.747308084622909e-06, "loss": 0.1526, "step": 376610 }, { "epoch": 2.2387074914849223, "grad_norm": 4.997206687927246, "learning_rate": 6.747113673228341e-06, "loss": 0.1772, "step": 376620 }, { "epoch": 2.2387669335615907, "grad_norm": 4.982410907745361, "learning_rate": 6.746919258825033e-06, "loss": 0.1695, "step": 376630 }, { "epoch": 2.238826375638259, "grad_norm": 3.674222946166992, "learning_rate": 6.7467248414133215e-06, "loss": 0.1643, "step": 376640 }, { "epoch": 2.2388858177149276, "grad_norm": 3.5489096641540527, "learning_rate": 6.746530420993542e-06, "loss": 0.1424, "step": 376650 }, { "epoch": 2.238945259791596, "grad_norm": 3.6000795364379883, "learning_rate": 6.746335997566029e-06, "loss": 0.1311, "step": 376660 }, { "epoch": 2.2390047018682644, "grad_norm": 4.833616733551025, "learning_rate": 6.746141571131116e-06, "loss": 0.1528, "step": 376670 }, { "epoch": 2.239064143944933, "grad_norm": 5.257813930511475, "learning_rate": 6.745947141689141e-06, "loss": 0.1432, "step": 376680 }, { "epoch": 2.239123586021601, "grad_norm": 3.909990072250366, "learning_rate": 6.745752709240436e-06, "loss": 0.1459, "step": 376690 }, { "epoch": 2.2391830280982696, "grad_norm": 3.7808170318603516, "learning_rate": 6.745558273785337e-06, "loss": 0.1422, "step": 376700 }, { "epoch": 2.239242470174938, "grad_norm": 5.701162338256836, "learning_rate": 6.745363835324176e-06, "loss": 0.1548, "step": 376710 }, { "epoch": 2.2393019122516065, "grad_norm": 3.6931588649749756, "learning_rate": 6.745169393857292e-06, "loss": 0.1632, "step": 376720 }, { "epoch": 2.239361354328275, "grad_norm": 3.6892306804656982, "learning_rate": 6.744974949385018e-06, "loss": 0.1372, "step": 376730 }, { "epoch": 2.2394207964049433, "grad_norm": 3.3727588653564453, "learning_rate": 6.744780501907689e-06, "loss": 0.1482, "step": 376740 }, { "epoch": 2.2394802384816117, "grad_norm": 5.221494197845459, "learning_rate": 6.7445860514256375e-06, "loss": 0.1455, "step": 376750 }, { "epoch": 2.23953968055828, "grad_norm": 4.787774085998535, "learning_rate": 6.744391597939204e-06, "loss": 0.1465, "step": 376760 }, { "epoch": 2.2395991226349485, "grad_norm": 5.084574222564697, "learning_rate": 6.7441971414487185e-06, "loss": 0.1525, "step": 376770 }, { "epoch": 2.239658564711617, "grad_norm": 3.3317036628723145, "learning_rate": 6.744002681954518e-06, "loss": 0.1514, "step": 376780 }, { "epoch": 2.2397180067882854, "grad_norm": 4.896851539611816, "learning_rate": 6.743808219456935e-06, "loss": 0.1615, "step": 376790 }, { "epoch": 2.2397774488649533, "grad_norm": 3.8992393016815186, "learning_rate": 6.743613753956308e-06, "loss": 0.1506, "step": 376800 }, { "epoch": 2.2398368909416217, "grad_norm": 4.279725551605225, "learning_rate": 6.74341928545297e-06, "loss": 0.1503, "step": 376810 }, { "epoch": 2.23989633301829, "grad_norm": 3.7784507274627686, "learning_rate": 6.743224813947256e-06, "loss": 0.1542, "step": 376820 }, { "epoch": 2.2399557750949586, "grad_norm": 3.3913369178771973, "learning_rate": 6.7430303394395005e-06, "loss": 0.1568, "step": 376830 }, { "epoch": 2.240015217171627, "grad_norm": 4.5709381103515625, "learning_rate": 6.742835861930038e-06, "loss": 0.1546, "step": 376840 }, { "epoch": 2.2400746592482954, "grad_norm": 4.8516316413879395, "learning_rate": 6.742641381419206e-06, "loss": 0.1606, "step": 376850 }, { "epoch": 2.240134101324964, "grad_norm": 4.352452754974365, "learning_rate": 6.742446897907335e-06, "loss": 0.1655, "step": 376860 }, { "epoch": 2.2401935434016322, "grad_norm": 3.8643789291381836, "learning_rate": 6.742252411394764e-06, "loss": 0.159, "step": 376870 }, { "epoch": 2.2402529854783007, "grad_norm": 3.1330320835113525, "learning_rate": 6.742057921881827e-06, "loss": 0.1563, "step": 376880 }, { "epoch": 2.240312427554969, "grad_norm": 3.691547155380249, "learning_rate": 6.7418634293688574e-06, "loss": 0.16, "step": 376890 }, { "epoch": 2.2403718696316375, "grad_norm": 5.008042812347412, "learning_rate": 6.741668933856191e-06, "loss": 0.1663, "step": 376900 }, { "epoch": 2.240431311708306, "grad_norm": 5.164281368255615, "learning_rate": 6.741474435344165e-06, "loss": 0.1588, "step": 376910 }, { "epoch": 2.2404907537849743, "grad_norm": 6.016183853149414, "learning_rate": 6.741279933833111e-06, "loss": 0.1429, "step": 376920 }, { "epoch": 2.2405501958616427, "grad_norm": 3.560486078262329, "learning_rate": 6.741085429323364e-06, "loss": 0.1413, "step": 376930 }, { "epoch": 2.240609637938311, "grad_norm": 3.7380268573760986, "learning_rate": 6.740890921815262e-06, "loss": 0.1508, "step": 376940 }, { "epoch": 2.2406690800149796, "grad_norm": 3.6126813888549805, "learning_rate": 6.740696411309138e-06, "loss": 0.1337, "step": 376950 }, { "epoch": 2.240728522091648, "grad_norm": 4.687542915344238, "learning_rate": 6.740501897805325e-06, "loss": 0.14, "step": 376960 }, { "epoch": 2.2407879641683164, "grad_norm": 3.8982067108154297, "learning_rate": 6.740307381304161e-06, "loss": 0.1333, "step": 376970 }, { "epoch": 2.240847406244985, "grad_norm": 3.459585428237915, "learning_rate": 6.740112861805981e-06, "loss": 0.1489, "step": 376980 }, { "epoch": 2.2409068483216528, "grad_norm": 5.833561420440674, "learning_rate": 6.739918339311119e-06, "loss": 0.1491, "step": 376990 }, { "epoch": 2.240966290398321, "grad_norm": 5.105827808380127, "learning_rate": 6.739723813819908e-06, "loss": 0.1506, "step": 377000 }, { "epoch": 2.2410257324749896, "grad_norm": 3.2777099609375, "learning_rate": 6.739529285332687e-06, "loss": 0.1488, "step": 377010 }, { "epoch": 2.241085174551658, "grad_norm": 4.817724704742432, "learning_rate": 6.7393347538497885e-06, "loss": 0.1436, "step": 377020 }, { "epoch": 2.2411446166283264, "grad_norm": 3.9628682136535645, "learning_rate": 6.739140219371548e-06, "loss": 0.1648, "step": 377030 }, { "epoch": 2.241204058704995, "grad_norm": 4.790065288543701, "learning_rate": 6.738945681898301e-06, "loss": 0.1615, "step": 377040 }, { "epoch": 2.2412635007816633, "grad_norm": 3.6013636589050293, "learning_rate": 6.738751141430382e-06, "loss": 0.1495, "step": 377050 }, { "epoch": 2.2413229428583317, "grad_norm": 3.636319398880005, "learning_rate": 6.738556597968126e-06, "loss": 0.1413, "step": 377060 }, { "epoch": 2.241382384935, "grad_norm": 3.1593315601348877, "learning_rate": 6.738362051511867e-06, "loss": 0.1382, "step": 377070 }, { "epoch": 2.2414418270116685, "grad_norm": 5.2058916091918945, "learning_rate": 6.738167502061942e-06, "loss": 0.1602, "step": 377080 }, { "epoch": 2.241501269088337, "grad_norm": 4.736276149749756, "learning_rate": 6.737972949618685e-06, "loss": 0.1484, "step": 377090 }, { "epoch": 2.2415607111650053, "grad_norm": 3.4650678634643555, "learning_rate": 6.73777839418243e-06, "loss": 0.1425, "step": 377100 }, { "epoch": 2.2416201532416737, "grad_norm": 3.519918203353882, "learning_rate": 6.737583835753516e-06, "loss": 0.1418, "step": 377110 }, { "epoch": 2.241679595318342, "grad_norm": 5.727818965911865, "learning_rate": 6.737389274332274e-06, "loss": 0.1562, "step": 377120 }, { "epoch": 2.2417390373950106, "grad_norm": 4.635184288024902, "learning_rate": 6.737194709919039e-06, "loss": 0.1494, "step": 377130 }, { "epoch": 2.241798479471679, "grad_norm": 4.478161811828613, "learning_rate": 6.73700014251415e-06, "loss": 0.1377, "step": 377140 }, { "epoch": 2.2418579215483474, "grad_norm": 4.659494876861572, "learning_rate": 6.736805572117938e-06, "loss": 0.1419, "step": 377150 }, { "epoch": 2.2419173636250154, "grad_norm": 3.343471050262451, "learning_rate": 6.736610998730739e-06, "loss": 0.1425, "step": 377160 }, { "epoch": 2.2419768057016842, "grad_norm": 3.4825990200042725, "learning_rate": 6.736416422352889e-06, "loss": 0.1516, "step": 377170 }, { "epoch": 2.242036247778352, "grad_norm": 4.858438968658447, "learning_rate": 6.736221842984725e-06, "loss": 0.1572, "step": 377180 }, { "epoch": 2.2420956898550206, "grad_norm": 4.225959300994873, "learning_rate": 6.736027260626576e-06, "loss": 0.1635, "step": 377190 }, { "epoch": 2.242155131931689, "grad_norm": 4.114130973815918, "learning_rate": 6.735832675278783e-06, "loss": 0.1458, "step": 377200 }, { "epoch": 2.2422145740083574, "grad_norm": 4.845061302185059, "learning_rate": 6.735638086941679e-06, "loss": 0.1508, "step": 377210 }, { "epoch": 2.242274016085026, "grad_norm": 6.7671427726745605, "learning_rate": 6.735443495615599e-06, "loss": 0.1698, "step": 377220 }, { "epoch": 2.2423334581616943, "grad_norm": 4.848898410797119, "learning_rate": 6.7352489013008785e-06, "loss": 0.1414, "step": 377230 }, { "epoch": 2.2423929002383627, "grad_norm": 5.880833625793457, "learning_rate": 6.735054303997852e-06, "loss": 0.1384, "step": 377240 }, { "epoch": 2.242452342315031, "grad_norm": 4.4589691162109375, "learning_rate": 6.7348597037068555e-06, "loss": 0.1473, "step": 377250 }, { "epoch": 2.2425117843916995, "grad_norm": 4.123988151550293, "learning_rate": 6.734665100428223e-06, "loss": 0.1415, "step": 377260 }, { "epoch": 2.242571226468368, "grad_norm": 4.940415382385254, "learning_rate": 6.734470494162291e-06, "loss": 0.1778, "step": 377270 }, { "epoch": 2.2426306685450363, "grad_norm": 4.4414448738098145, "learning_rate": 6.734275884909393e-06, "loss": 0.1497, "step": 377280 }, { "epoch": 2.2426901106217048, "grad_norm": 4.399129867553711, "learning_rate": 6.7340812726698644e-06, "loss": 0.145, "step": 377290 }, { "epoch": 2.242749552698373, "grad_norm": 4.228752136230469, "learning_rate": 6.733886657444041e-06, "loss": 0.1511, "step": 377300 }, { "epoch": 2.2428089947750416, "grad_norm": 3.350728988647461, "learning_rate": 6.733692039232259e-06, "loss": 0.142, "step": 377310 }, { "epoch": 2.24286843685171, "grad_norm": 4.805546760559082, "learning_rate": 6.733497418034851e-06, "loss": 0.1478, "step": 377320 }, { "epoch": 2.2429278789283784, "grad_norm": 5.484827518463135, "learning_rate": 6.733302793852156e-06, "loss": 0.1439, "step": 377330 }, { "epoch": 2.242987321005047, "grad_norm": 4.11393404006958, "learning_rate": 6.733108166684505e-06, "loss": 0.1461, "step": 377340 }, { "epoch": 2.243046763081715, "grad_norm": 5.075594425201416, "learning_rate": 6.732913536532235e-06, "loss": 0.1903, "step": 377350 }, { "epoch": 2.243106205158383, "grad_norm": 4.962292194366455, "learning_rate": 6.732718903395682e-06, "loss": 0.1665, "step": 377360 }, { "epoch": 2.2431656472350516, "grad_norm": 4.7692437171936035, "learning_rate": 6.73252426727518e-06, "loss": 0.1623, "step": 377370 }, { "epoch": 2.24322508931172, "grad_norm": 5.085434436798096, "learning_rate": 6.7323296281710645e-06, "loss": 0.1619, "step": 377380 }, { "epoch": 2.2432845313883885, "grad_norm": 4.325476169586182, "learning_rate": 6.732134986083671e-06, "loss": 0.1451, "step": 377390 }, { "epoch": 2.243343973465057, "grad_norm": 4.2577595710754395, "learning_rate": 6.7319403410133336e-06, "loss": 0.1434, "step": 377400 }, { "epoch": 2.2434034155417253, "grad_norm": 4.045254230499268, "learning_rate": 6.7317456929603876e-06, "loss": 0.1668, "step": 377410 }, { "epoch": 2.2434628576183937, "grad_norm": 4.445333480834961, "learning_rate": 6.73155104192517e-06, "loss": 0.1658, "step": 377420 }, { "epoch": 2.243522299695062, "grad_norm": 4.199156761169434, "learning_rate": 6.731356387908015e-06, "loss": 0.1583, "step": 377430 }, { "epoch": 2.2435817417717305, "grad_norm": 5.493026256561279, "learning_rate": 6.731161730909257e-06, "loss": 0.1337, "step": 377440 }, { "epoch": 2.243641183848399, "grad_norm": 4.146594047546387, "learning_rate": 6.730967070929232e-06, "loss": 0.1539, "step": 377450 }, { "epoch": 2.2437006259250674, "grad_norm": 5.016752243041992, "learning_rate": 6.730772407968276e-06, "loss": 0.1556, "step": 377460 }, { "epoch": 2.2437600680017358, "grad_norm": 4.07030725479126, "learning_rate": 6.730577742026723e-06, "loss": 0.128, "step": 377470 }, { "epoch": 2.243819510078404, "grad_norm": 4.1041083335876465, "learning_rate": 6.730383073104909e-06, "loss": 0.1371, "step": 377480 }, { "epoch": 2.2438789521550726, "grad_norm": 4.893270969390869, "learning_rate": 6.730188401203169e-06, "loss": 0.1527, "step": 377490 }, { "epoch": 2.243938394231741, "grad_norm": 4.3527398109436035, "learning_rate": 6.729993726321837e-06, "loss": 0.1461, "step": 377500 }, { "epoch": 2.2439978363084094, "grad_norm": 3.7222862243652344, "learning_rate": 6.7297990484612495e-06, "loss": 0.1565, "step": 377510 }, { "epoch": 2.244057278385078, "grad_norm": 3.770338535308838, "learning_rate": 6.729604367621742e-06, "loss": 0.1348, "step": 377520 }, { "epoch": 2.2441167204617463, "grad_norm": 5.667820453643799, "learning_rate": 6.72940968380365e-06, "loss": 0.1724, "step": 377530 }, { "epoch": 2.2441761625384142, "grad_norm": 4.348984241485596, "learning_rate": 6.729214997007307e-06, "loss": 0.1507, "step": 377540 }, { "epoch": 2.2442356046150826, "grad_norm": 4.170713901519775, "learning_rate": 6.7290203072330505e-06, "loss": 0.1396, "step": 377550 }, { "epoch": 2.244295046691751, "grad_norm": 5.024342060089111, "learning_rate": 6.7288256144812145e-06, "loss": 0.1528, "step": 377560 }, { "epoch": 2.2443544887684195, "grad_norm": 3.838466167449951, "learning_rate": 6.728630918752135e-06, "loss": 0.1492, "step": 377570 }, { "epoch": 2.244413930845088, "grad_norm": 4.34700870513916, "learning_rate": 6.728436220046146e-06, "loss": 0.1385, "step": 377580 }, { "epoch": 2.2444733729217563, "grad_norm": 3.3670780658721924, "learning_rate": 6.728241518363584e-06, "loss": 0.1495, "step": 377590 }, { "epoch": 2.2445328149984247, "grad_norm": 3.5826377868652344, "learning_rate": 6.728046813704784e-06, "loss": 0.1619, "step": 377600 }, { "epoch": 2.244592257075093, "grad_norm": 4.250644683837891, "learning_rate": 6.727852106070081e-06, "loss": 0.1478, "step": 377610 }, { "epoch": 2.2446516991517615, "grad_norm": 4.2261786460876465, "learning_rate": 6.72765739545981e-06, "loss": 0.1385, "step": 377620 }, { "epoch": 2.24471114122843, "grad_norm": 3.64123797416687, "learning_rate": 6.727462681874306e-06, "loss": 0.1476, "step": 377630 }, { "epoch": 2.2447705833050984, "grad_norm": 7.14843225479126, "learning_rate": 6.7272679653139075e-06, "loss": 0.1645, "step": 377640 }, { "epoch": 2.244830025381767, "grad_norm": 4.51093864440918, "learning_rate": 6.727073245778946e-06, "loss": 0.1445, "step": 377650 }, { "epoch": 2.244889467458435, "grad_norm": 6.040531158447266, "learning_rate": 6.726878523269759e-06, "loss": 0.1471, "step": 377660 }, { "epoch": 2.2449489095351036, "grad_norm": 5.045338153839111, "learning_rate": 6.726683797786681e-06, "loss": 0.163, "step": 377670 }, { "epoch": 2.245008351611772, "grad_norm": 4.191327095031738, "learning_rate": 6.726489069330046e-06, "loss": 0.1439, "step": 377680 }, { "epoch": 2.2450677936884404, "grad_norm": 4.609468936920166, "learning_rate": 6.726294337900192e-06, "loss": 0.1412, "step": 377690 }, { "epoch": 2.245127235765109, "grad_norm": 3.9646177291870117, "learning_rate": 6.726099603497454e-06, "loss": 0.1494, "step": 377700 }, { "epoch": 2.2451866778417773, "grad_norm": 4.590843677520752, "learning_rate": 6.725904866122166e-06, "loss": 0.1428, "step": 377710 }, { "epoch": 2.2452461199184457, "grad_norm": 5.579615592956543, "learning_rate": 6.725710125774664e-06, "loss": 0.1402, "step": 377720 }, { "epoch": 2.2453055619951137, "grad_norm": 4.689166069030762, "learning_rate": 6.725515382455283e-06, "loss": 0.1508, "step": 377730 }, { "epoch": 2.245365004071782, "grad_norm": 3.297483444213867, "learning_rate": 6.725320636164359e-06, "loss": 0.1276, "step": 377740 }, { "epoch": 2.2454244461484505, "grad_norm": 3.063476324081421, "learning_rate": 6.725125886902225e-06, "loss": 0.1643, "step": 377750 }, { "epoch": 2.245483888225119, "grad_norm": 3.210270643234253, "learning_rate": 6.724931134669221e-06, "loss": 0.1478, "step": 377760 }, { "epoch": 2.2455433303017873, "grad_norm": 4.054274559020996, "learning_rate": 6.7247363794656785e-06, "loss": 0.1539, "step": 377770 }, { "epoch": 2.2456027723784557, "grad_norm": 3.946733236312866, "learning_rate": 6.724541621291933e-06, "loss": 0.1464, "step": 377780 }, { "epoch": 2.245662214455124, "grad_norm": 4.705216884613037, "learning_rate": 6.724346860148323e-06, "loss": 0.1388, "step": 377790 }, { "epoch": 2.2457216565317926, "grad_norm": 3.8535306453704834, "learning_rate": 6.724152096035182e-06, "loss": 0.1505, "step": 377800 }, { "epoch": 2.245781098608461, "grad_norm": 5.031608581542969, "learning_rate": 6.723957328952844e-06, "loss": 0.1599, "step": 377810 }, { "epoch": 2.2458405406851294, "grad_norm": 5.7517991065979, "learning_rate": 6.723762558901648e-06, "loss": 0.1537, "step": 377820 }, { "epoch": 2.245899982761798, "grad_norm": 3.9401330947875977, "learning_rate": 6.723567785881926e-06, "loss": 0.1513, "step": 377830 }, { "epoch": 2.2459594248384662, "grad_norm": 4.957474708557129, "learning_rate": 6.723373009894013e-06, "loss": 0.1527, "step": 377840 }, { "epoch": 2.2460188669151346, "grad_norm": 4.846481800079346, "learning_rate": 6.723178230938247e-06, "loss": 0.1528, "step": 377850 }, { "epoch": 2.246078308991803, "grad_norm": 3.473506212234497, "learning_rate": 6.722983449014964e-06, "loss": 0.1514, "step": 377860 }, { "epoch": 2.2461377510684715, "grad_norm": 4.981658935546875, "learning_rate": 6.722788664124497e-06, "loss": 0.1412, "step": 377870 }, { "epoch": 2.24619719314514, "grad_norm": 4.19507360458374, "learning_rate": 6.7225938762671805e-06, "loss": 0.1529, "step": 377880 }, { "epoch": 2.2462566352218083, "grad_norm": 3.0473670959472656, "learning_rate": 6.722399085443354e-06, "loss": 0.1227, "step": 377890 }, { "epoch": 2.2463160772984763, "grad_norm": 3.6312272548675537, "learning_rate": 6.7222042916533514e-06, "loss": 0.1384, "step": 377900 }, { "epoch": 2.246375519375145, "grad_norm": 4.341896057128906, "learning_rate": 6.722009494897506e-06, "loss": 0.1334, "step": 377910 }, { "epoch": 2.246434961451813, "grad_norm": 5.230700492858887, "learning_rate": 6.721814695176154e-06, "loss": 0.1552, "step": 377920 }, { "epoch": 2.2464944035284815, "grad_norm": 4.253843784332275, "learning_rate": 6.721619892489634e-06, "loss": 0.1366, "step": 377930 }, { "epoch": 2.24655384560515, "grad_norm": 4.1156206130981445, "learning_rate": 6.721425086838277e-06, "loss": 0.1505, "step": 377940 }, { "epoch": 2.2466132876818183, "grad_norm": 5.23291015625, "learning_rate": 6.721230278222422e-06, "loss": 0.1638, "step": 377950 }, { "epoch": 2.2466727297584868, "grad_norm": 4.579747200012207, "learning_rate": 6.721035466642402e-06, "loss": 0.138, "step": 377960 }, { "epoch": 2.246732171835155, "grad_norm": 4.7922821044921875, "learning_rate": 6.720840652098554e-06, "loss": 0.1517, "step": 377970 }, { "epoch": 2.2467916139118236, "grad_norm": 3.9259002208709717, "learning_rate": 6.720645834591213e-06, "loss": 0.1416, "step": 377980 }, { "epoch": 2.246851055988492, "grad_norm": 3.3992390632629395, "learning_rate": 6.720451014120716e-06, "loss": 0.1642, "step": 377990 }, { "epoch": 2.2469104980651604, "grad_norm": 4.001854419708252, "learning_rate": 6.7202561906873956e-06, "loss": 0.1513, "step": 378000 }, { "epoch": 2.246969940141829, "grad_norm": 3.999178647994995, "learning_rate": 6.720061364291588e-06, "loss": 0.1495, "step": 378010 }, { "epoch": 2.2470293822184972, "grad_norm": 4.227504253387451, "learning_rate": 6.719866534933631e-06, "loss": 0.1368, "step": 378020 }, { "epoch": 2.2470888242951657, "grad_norm": 6.437198162078857, "learning_rate": 6.7196717026138595e-06, "loss": 0.173, "step": 378030 }, { "epoch": 2.247148266371834, "grad_norm": 4.429574489593506, "learning_rate": 6.719476867332606e-06, "loss": 0.1786, "step": 378040 }, { "epoch": 2.2472077084485025, "grad_norm": 5.507933139801025, "learning_rate": 6.719282029090209e-06, "loss": 0.148, "step": 378050 }, { "epoch": 2.247267150525171, "grad_norm": 4.182501792907715, "learning_rate": 6.7190871878870036e-06, "loss": 0.1493, "step": 378060 }, { "epoch": 2.2473265926018393, "grad_norm": 3.6134254932403564, "learning_rate": 6.718892343723323e-06, "loss": 0.157, "step": 378070 }, { "epoch": 2.2473860346785077, "grad_norm": 4.239120006561279, "learning_rate": 6.718697496599507e-06, "loss": 0.1334, "step": 378080 }, { "epoch": 2.2474454767551757, "grad_norm": 4.549011707305908, "learning_rate": 6.718502646515888e-06, "loss": 0.1446, "step": 378090 }, { "epoch": 2.247504918831844, "grad_norm": 4.667555809020996, "learning_rate": 6.718307793472802e-06, "loss": 0.1452, "step": 378100 }, { "epoch": 2.2475643609085125, "grad_norm": 3.681973695755005, "learning_rate": 6.718112937470585e-06, "loss": 0.1446, "step": 378110 }, { "epoch": 2.247623802985181, "grad_norm": 4.01566743850708, "learning_rate": 6.717918078509574e-06, "loss": 0.1568, "step": 378120 }, { "epoch": 2.2476832450618494, "grad_norm": 4.937537670135498, "learning_rate": 6.717723216590102e-06, "loss": 0.1691, "step": 378130 }, { "epoch": 2.2477426871385178, "grad_norm": 3.7797365188598633, "learning_rate": 6.717528351712506e-06, "loss": 0.1366, "step": 378140 }, { "epoch": 2.247802129215186, "grad_norm": 4.017991542816162, "learning_rate": 6.717333483877121e-06, "loss": 0.1372, "step": 378150 }, { "epoch": 2.2478615712918546, "grad_norm": 3.2594101428985596, "learning_rate": 6.717138613084282e-06, "loss": 0.1449, "step": 378160 }, { "epoch": 2.247921013368523, "grad_norm": 3.5661890506744385, "learning_rate": 6.716943739334328e-06, "loss": 0.1526, "step": 378170 }, { "epoch": 2.2479804554451914, "grad_norm": 3.191729784011841, "learning_rate": 6.716748862627588e-06, "loss": 0.1282, "step": 378180 }, { "epoch": 2.24803989752186, "grad_norm": 4.902829170227051, "learning_rate": 6.716553982964404e-06, "loss": 0.1528, "step": 378190 }, { "epoch": 2.2480993395985283, "grad_norm": 5.855759143829346, "learning_rate": 6.716359100345109e-06, "loss": 0.1543, "step": 378200 }, { "epoch": 2.2481587816751967, "grad_norm": 2.718970775604248, "learning_rate": 6.716164214770039e-06, "loss": 0.135, "step": 378210 }, { "epoch": 2.248218223751865, "grad_norm": 5.021895408630371, "learning_rate": 6.7159693262395295e-06, "loss": 0.1475, "step": 378220 }, { "epoch": 2.2482776658285335, "grad_norm": 4.625981330871582, "learning_rate": 6.715774434753916e-06, "loss": 0.1374, "step": 378230 }, { "epoch": 2.248337107905202, "grad_norm": 4.334414005279541, "learning_rate": 6.715579540313535e-06, "loss": 0.1547, "step": 378240 }, { "epoch": 2.2483965499818703, "grad_norm": 5.316152095794678, "learning_rate": 6.71538464291872e-06, "loss": 0.1579, "step": 378250 }, { "epoch": 2.2484559920585387, "grad_norm": 3.405514717102051, "learning_rate": 6.7151897425698075e-06, "loss": 0.1449, "step": 378260 }, { "epoch": 2.248515434135207, "grad_norm": 5.038500785827637, "learning_rate": 6.714994839267135e-06, "loss": 0.1384, "step": 378270 }, { "epoch": 2.248574876211875, "grad_norm": 4.977501392364502, "learning_rate": 6.714799933011037e-06, "loss": 0.1538, "step": 378280 }, { "epoch": 2.2486343182885435, "grad_norm": 3.6744561195373535, "learning_rate": 6.714605023801848e-06, "loss": 0.1645, "step": 378290 }, { "epoch": 2.248693760365212, "grad_norm": 5.334933757781982, "learning_rate": 6.714410111639904e-06, "loss": 0.1453, "step": 378300 }, { "epoch": 2.2487532024418804, "grad_norm": 3.359896659851074, "learning_rate": 6.714215196525542e-06, "loss": 0.1492, "step": 378310 }, { "epoch": 2.248812644518549, "grad_norm": 4.49580717086792, "learning_rate": 6.714020278459097e-06, "loss": 0.1417, "step": 378320 }, { "epoch": 2.248872086595217, "grad_norm": 4.34035587310791, "learning_rate": 6.713825357440904e-06, "loss": 0.1313, "step": 378330 }, { "epoch": 2.2489315286718856, "grad_norm": 4.72894811630249, "learning_rate": 6.7136304334712994e-06, "loss": 0.1488, "step": 378340 }, { "epoch": 2.248990970748554, "grad_norm": 4.041496753692627, "learning_rate": 6.71343550655062e-06, "loss": 0.1603, "step": 378350 }, { "epoch": 2.2490504128252224, "grad_norm": 4.27640962600708, "learning_rate": 6.713240576679199e-06, "loss": 0.1658, "step": 378360 }, { "epoch": 2.249109854901891, "grad_norm": 4.534722805023193, "learning_rate": 6.713045643857374e-06, "loss": 0.1469, "step": 378370 }, { "epoch": 2.2491692969785593, "grad_norm": 4.70689058303833, "learning_rate": 6.71285070808548e-06, "loss": 0.1558, "step": 378380 }, { "epoch": 2.2492287390552277, "grad_norm": 4.0601887702941895, "learning_rate": 6.7126557693638516e-06, "loss": 0.1573, "step": 378390 }, { "epoch": 2.249288181131896, "grad_norm": 4.266697406768799, "learning_rate": 6.712460827692826e-06, "loss": 0.1703, "step": 378400 }, { "epoch": 2.2493476232085645, "grad_norm": 4.516666412353516, "learning_rate": 6.712265883072738e-06, "loss": 0.1465, "step": 378410 }, { "epoch": 2.249407065285233, "grad_norm": 5.381933689117432, "learning_rate": 6.712070935503926e-06, "loss": 0.1587, "step": 378420 }, { "epoch": 2.2494665073619013, "grad_norm": 3.5579864978790283, "learning_rate": 6.711875984986721e-06, "loss": 0.1529, "step": 378430 }, { "epoch": 2.2495259494385698, "grad_norm": 4.135868072509766, "learning_rate": 6.711681031521463e-06, "loss": 0.147, "step": 378440 }, { "epoch": 2.249585391515238, "grad_norm": 3.6233766078948975, "learning_rate": 6.711486075108487e-06, "loss": 0.1443, "step": 378450 }, { "epoch": 2.2496448335919066, "grad_norm": 3.970353603363037, "learning_rate": 6.7112911157481246e-06, "loss": 0.1514, "step": 378460 }, { "epoch": 2.2497042756685746, "grad_norm": 4.14969539642334, "learning_rate": 6.711096153440717e-06, "loss": 0.1462, "step": 378470 }, { "epoch": 2.249763717745243, "grad_norm": 3.393361806869507, "learning_rate": 6.710901188186597e-06, "loss": 0.1478, "step": 378480 }, { "epoch": 2.2498231598219114, "grad_norm": 4.718395709991455, "learning_rate": 6.7107062199861e-06, "loss": 0.1587, "step": 378490 }, { "epoch": 2.24988260189858, "grad_norm": 4.602851390838623, "learning_rate": 6.710511248839565e-06, "loss": 0.1353, "step": 378500 }, { "epoch": 2.249942043975248, "grad_norm": 3.2611448764801025, "learning_rate": 6.710316274747324e-06, "loss": 0.1587, "step": 378510 }, { "epoch": 2.2500014860519166, "grad_norm": 4.735354423522949, "learning_rate": 6.710121297709715e-06, "loss": 0.1567, "step": 378520 }, { "epoch": 2.250060928128585, "grad_norm": 3.6954357624053955, "learning_rate": 6.709926317727072e-06, "loss": 0.1609, "step": 378530 }, { "epoch": 2.2501203702052535, "grad_norm": 3.573918342590332, "learning_rate": 6.709731334799733e-06, "loss": 0.1457, "step": 378540 }, { "epoch": 2.250179812281922, "grad_norm": 5.964555740356445, "learning_rate": 6.709536348928033e-06, "loss": 0.1361, "step": 378550 }, { "epoch": 2.2502392543585903, "grad_norm": 3.1466429233551025, "learning_rate": 6.709341360112306e-06, "loss": 0.1294, "step": 378560 }, { "epoch": 2.2502986964352587, "grad_norm": 5.169366836547852, "learning_rate": 6.70914636835289e-06, "loss": 0.1698, "step": 378570 }, { "epoch": 2.250358138511927, "grad_norm": 4.073002338409424, "learning_rate": 6.708951373650121e-06, "loss": 0.1494, "step": 378580 }, { "epoch": 2.2504175805885955, "grad_norm": 6.83300256729126, "learning_rate": 6.708756376004332e-06, "loss": 0.1436, "step": 378590 }, { "epoch": 2.250477022665264, "grad_norm": 3.6439368724823, "learning_rate": 6.708561375415861e-06, "loss": 0.1422, "step": 378600 }, { "epoch": 2.2505364647419324, "grad_norm": 3.283768892288208, "learning_rate": 6.7083663718850445e-06, "loss": 0.1556, "step": 378610 }, { "epoch": 2.2505959068186008, "grad_norm": 3.8347575664520264, "learning_rate": 6.708171365412215e-06, "loss": 0.1475, "step": 378620 }, { "epoch": 2.250655348895269, "grad_norm": 3.4162843227386475, "learning_rate": 6.707976355997713e-06, "loss": 0.1349, "step": 378630 }, { "epoch": 2.250714790971937, "grad_norm": 6.422467231750488, "learning_rate": 6.7077813436418716e-06, "loss": 0.1775, "step": 378640 }, { "epoch": 2.250774233048606, "grad_norm": 5.422761917114258, "learning_rate": 6.707586328345026e-06, "loss": 0.1378, "step": 378650 }, { "epoch": 2.250833675125274, "grad_norm": 6.173637866973877, "learning_rate": 6.707391310107514e-06, "loss": 0.1537, "step": 378660 }, { "epoch": 2.2508931172019424, "grad_norm": 4.972374439239502, "learning_rate": 6.7071962889296695e-06, "loss": 0.1537, "step": 378670 }, { "epoch": 2.250952559278611, "grad_norm": 3.43009614944458, "learning_rate": 6.70700126481183e-06, "loss": 0.1226, "step": 378680 }, { "epoch": 2.2510120013552792, "grad_norm": 4.132068157196045, "learning_rate": 6.70680623775433e-06, "loss": 0.1535, "step": 378690 }, { "epoch": 2.2510714434319476, "grad_norm": 3.833791971206665, "learning_rate": 6.7066112077575075e-06, "loss": 0.1704, "step": 378700 }, { "epoch": 2.251130885508616, "grad_norm": 4.368261337280273, "learning_rate": 6.706416174821695e-06, "loss": 0.1404, "step": 378710 }, { "epoch": 2.2511903275852845, "grad_norm": 4.802757263183594, "learning_rate": 6.706221138947231e-06, "loss": 0.1603, "step": 378720 }, { "epoch": 2.251249769661953, "grad_norm": 3.863027811050415, "learning_rate": 6.70602610013445e-06, "loss": 0.1431, "step": 378730 }, { "epoch": 2.2513092117386213, "grad_norm": 2.9550371170043945, "learning_rate": 6.705831058383689e-06, "loss": 0.1434, "step": 378740 }, { "epoch": 2.2513686538152897, "grad_norm": 4.789045333862305, "learning_rate": 6.705636013695283e-06, "loss": 0.1515, "step": 378750 }, { "epoch": 2.251428095891958, "grad_norm": 4.029314041137695, "learning_rate": 6.705440966069569e-06, "loss": 0.1416, "step": 378760 }, { "epoch": 2.2514875379686266, "grad_norm": 3.4307498931884766, "learning_rate": 6.705245915506883e-06, "loss": 0.1466, "step": 378770 }, { "epoch": 2.251546980045295, "grad_norm": 4.222923278808594, "learning_rate": 6.705050862007558e-06, "loss": 0.1328, "step": 378780 }, { "epoch": 2.2516064221219634, "grad_norm": 3.1572611331939697, "learning_rate": 6.704855805571932e-06, "loss": 0.143, "step": 378790 }, { "epoch": 2.251665864198632, "grad_norm": 4.760048866271973, "learning_rate": 6.704660746200343e-06, "loss": 0.1411, "step": 378800 }, { "epoch": 2.2517253062753, "grad_norm": 4.237227916717529, "learning_rate": 6.7044656838931235e-06, "loss": 0.138, "step": 378810 }, { "epoch": 2.2517847483519686, "grad_norm": 3.283562421798706, "learning_rate": 6.704270618650611e-06, "loss": 0.1542, "step": 378820 }, { "epoch": 2.2518441904286366, "grad_norm": 4.757791519165039, "learning_rate": 6.704075550473141e-06, "loss": 0.1365, "step": 378830 }, { "epoch": 2.2519036325053055, "grad_norm": 5.0724196434021, "learning_rate": 6.703880479361049e-06, "loss": 0.1456, "step": 378840 }, { "epoch": 2.2519630745819734, "grad_norm": 5.119176864624023, "learning_rate": 6.703685405314671e-06, "loss": 0.1492, "step": 378850 }, { "epoch": 2.252022516658642, "grad_norm": 5.698151588439941, "learning_rate": 6.703490328334346e-06, "loss": 0.1475, "step": 378860 }, { "epoch": 2.2520819587353103, "grad_norm": 4.355236530303955, "learning_rate": 6.703295248420406e-06, "loss": 0.1602, "step": 378870 }, { "epoch": 2.2521414008119787, "grad_norm": 5.2756123542785645, "learning_rate": 6.703100165573188e-06, "loss": 0.1663, "step": 378880 }, { "epoch": 2.252200842888647, "grad_norm": 3.392974376678467, "learning_rate": 6.70290507979303e-06, "loss": 0.1405, "step": 378890 }, { "epoch": 2.2522602849653155, "grad_norm": 2.974064826965332, "learning_rate": 6.702709991080264e-06, "loss": 0.1389, "step": 378900 }, { "epoch": 2.252319727041984, "grad_norm": 4.644325256347656, "learning_rate": 6.702514899435228e-06, "loss": 0.1455, "step": 378910 }, { "epoch": 2.2523791691186523, "grad_norm": 3.487621307373047, "learning_rate": 6.702319804858261e-06, "loss": 0.13, "step": 378920 }, { "epoch": 2.2524386111953207, "grad_norm": 3.7124392986297607, "learning_rate": 6.702124707349694e-06, "loss": 0.1404, "step": 378930 }, { "epoch": 2.252498053271989, "grad_norm": 5.6815290451049805, "learning_rate": 6.701929606909865e-06, "loss": 0.1408, "step": 378940 }, { "epoch": 2.2525574953486576, "grad_norm": 3.4996793270111084, "learning_rate": 6.70173450353911e-06, "loss": 0.1498, "step": 378950 }, { "epoch": 2.252616937425326, "grad_norm": 6.072429656982422, "learning_rate": 6.701539397237766e-06, "loss": 0.16, "step": 378960 }, { "epoch": 2.2526763795019944, "grad_norm": 5.291193008422852, "learning_rate": 6.701344288006168e-06, "loss": 0.1655, "step": 378970 }, { "epoch": 2.252735821578663, "grad_norm": 3.1383767127990723, "learning_rate": 6.701149175844652e-06, "loss": 0.1396, "step": 378980 }, { "epoch": 2.2527952636553312, "grad_norm": 3.3520150184631348, "learning_rate": 6.700954060753555e-06, "loss": 0.1309, "step": 378990 }, { "epoch": 2.2528547057319996, "grad_norm": 3.0290887355804443, "learning_rate": 6.700758942733212e-06, "loss": 0.1325, "step": 379000 }, { "epoch": 2.252914147808668, "grad_norm": 3.2372219562530518, "learning_rate": 6.7005638217839584e-06, "loss": 0.1246, "step": 379010 }, { "epoch": 2.252973589885336, "grad_norm": 3.97290301322937, "learning_rate": 6.700368697906131e-06, "loss": 0.1431, "step": 379020 }, { "epoch": 2.2530330319620044, "grad_norm": 4.996606349945068, "learning_rate": 6.700173571100067e-06, "loss": 0.1356, "step": 379030 }, { "epoch": 2.253092474038673, "grad_norm": 5.509712219238281, "learning_rate": 6.6999784413661e-06, "loss": 0.1392, "step": 379040 }, { "epoch": 2.2531519161153413, "grad_norm": 5.0910162925720215, "learning_rate": 6.699783308704567e-06, "loss": 0.1498, "step": 379050 }, { "epoch": 2.2532113581920097, "grad_norm": 4.61470890045166, "learning_rate": 6.699588173115805e-06, "loss": 0.157, "step": 379060 }, { "epoch": 2.253270800268678, "grad_norm": 7.165685176849365, "learning_rate": 6.699393034600149e-06, "loss": 0.1583, "step": 379070 }, { "epoch": 2.2533302423453465, "grad_norm": 3.6238462924957275, "learning_rate": 6.699197893157936e-06, "loss": 0.1454, "step": 379080 }, { "epoch": 2.253389684422015, "grad_norm": 4.151155471801758, "learning_rate": 6.699002748789501e-06, "loss": 0.1499, "step": 379090 }, { "epoch": 2.2534491264986833, "grad_norm": 4.16439962387085, "learning_rate": 6.698807601495181e-06, "loss": 0.1429, "step": 379100 }, { "epoch": 2.2535085685753518, "grad_norm": 3.664592742919922, "learning_rate": 6.69861245127531e-06, "loss": 0.1437, "step": 379110 }, { "epoch": 2.25356801065202, "grad_norm": 5.216277599334717, "learning_rate": 6.698417298130229e-06, "loss": 0.1662, "step": 379120 }, { "epoch": 2.2536274527286886, "grad_norm": 4.64106559753418, "learning_rate": 6.698222142060269e-06, "loss": 0.1445, "step": 379130 }, { "epoch": 2.253686894805357, "grad_norm": 4.166457653045654, "learning_rate": 6.698026983065766e-06, "loss": 0.151, "step": 379140 }, { "epoch": 2.2537463368820254, "grad_norm": 4.717074871063232, "learning_rate": 6.697831821147061e-06, "loss": 0.1397, "step": 379150 }, { "epoch": 2.253805778958694, "grad_norm": 3.8571248054504395, "learning_rate": 6.697636656304485e-06, "loss": 0.1246, "step": 379160 }, { "epoch": 2.2538652210353622, "grad_norm": 4.395264625549316, "learning_rate": 6.697441488538377e-06, "loss": 0.1351, "step": 379170 }, { "epoch": 2.2539246631120307, "grad_norm": 4.50515079498291, "learning_rate": 6.697246317849071e-06, "loss": 0.1461, "step": 379180 }, { "epoch": 2.2539841051886986, "grad_norm": 6.035295486450195, "learning_rate": 6.697051144236905e-06, "loss": 0.1608, "step": 379190 }, { "epoch": 2.2540435472653675, "grad_norm": 4.868759632110596, "learning_rate": 6.696855967702216e-06, "loss": 0.1442, "step": 379200 }, { "epoch": 2.2541029893420355, "grad_norm": 4.793787479400635, "learning_rate": 6.696660788245336e-06, "loss": 0.1436, "step": 379210 }, { "epoch": 2.254162431418704, "grad_norm": 4.384913444519043, "learning_rate": 6.696465605866605e-06, "loss": 0.1365, "step": 379220 }, { "epoch": 2.2542218734953723, "grad_norm": 3.9064009189605713, "learning_rate": 6.696270420566359e-06, "loss": 0.135, "step": 379230 }, { "epoch": 2.2542813155720407, "grad_norm": 4.4469990730285645, "learning_rate": 6.6960752323449305e-06, "loss": 0.1541, "step": 379240 }, { "epoch": 2.254340757648709, "grad_norm": 5.362389087677002, "learning_rate": 6.695880041202661e-06, "loss": 0.1434, "step": 379250 }, { "epoch": 2.2544001997253775, "grad_norm": 4.674605846405029, "learning_rate": 6.6956848471398814e-06, "loss": 0.1373, "step": 379260 }, { "epoch": 2.254459641802046, "grad_norm": 3.5819003582000732, "learning_rate": 6.69548965015693e-06, "loss": 0.1598, "step": 379270 }, { "epoch": 2.2545190838787144, "grad_norm": 3.8854780197143555, "learning_rate": 6.695294450254143e-06, "loss": 0.1539, "step": 379280 }, { "epoch": 2.2545785259553828, "grad_norm": 3.7969677448272705, "learning_rate": 6.695099247431858e-06, "loss": 0.1663, "step": 379290 }, { "epoch": 2.254637968032051, "grad_norm": 5.610929012298584, "learning_rate": 6.694904041690409e-06, "loss": 0.1566, "step": 379300 }, { "epoch": 2.2546974101087196, "grad_norm": 4.157583236694336, "learning_rate": 6.694708833030134e-06, "loss": 0.1588, "step": 379310 }, { "epoch": 2.254756852185388, "grad_norm": 4.088147163391113, "learning_rate": 6.694513621451367e-06, "loss": 0.1557, "step": 379320 }, { "epoch": 2.2548162942620564, "grad_norm": 3.957036018371582, "learning_rate": 6.694318406954446e-06, "loss": 0.1398, "step": 379330 }, { "epoch": 2.254875736338725, "grad_norm": 5.927029609680176, "learning_rate": 6.6941231895397075e-06, "loss": 0.1528, "step": 379340 }, { "epoch": 2.2549351784153933, "grad_norm": 4.872715473175049, "learning_rate": 6.6939279692074855e-06, "loss": 0.1572, "step": 379350 }, { "epoch": 2.2549946204920617, "grad_norm": 4.978342056274414, "learning_rate": 6.693732745958117e-06, "loss": 0.1403, "step": 379360 }, { "epoch": 2.25505406256873, "grad_norm": 3.749675750732422, "learning_rate": 6.693537519791939e-06, "loss": 0.1336, "step": 379370 }, { "epoch": 2.255113504645398, "grad_norm": 5.3602519035339355, "learning_rate": 6.693342290709288e-06, "loss": 0.1622, "step": 379380 }, { "epoch": 2.255172946722067, "grad_norm": 3.782209634780884, "learning_rate": 6.693147058710499e-06, "loss": 0.1415, "step": 379390 }, { "epoch": 2.255232388798735, "grad_norm": 4.007875442504883, "learning_rate": 6.692951823795908e-06, "loss": 0.1577, "step": 379400 }, { "epoch": 2.2552918308754033, "grad_norm": 3.7122814655303955, "learning_rate": 6.692756585965854e-06, "loss": 0.1496, "step": 379410 }, { "epoch": 2.2553512729520717, "grad_norm": 3.511080265045166, "learning_rate": 6.69256134522067e-06, "loss": 0.1382, "step": 379420 }, { "epoch": 2.25541071502874, "grad_norm": 4.43601655960083, "learning_rate": 6.692366101560692e-06, "loss": 0.1441, "step": 379430 }, { "epoch": 2.2554701571054085, "grad_norm": 3.7902274131774902, "learning_rate": 6.692170854986259e-06, "loss": 0.138, "step": 379440 }, { "epoch": 2.255529599182077, "grad_norm": 4.9087748527526855, "learning_rate": 6.691975605497707e-06, "loss": 0.1629, "step": 379450 }, { "epoch": 2.2555890412587454, "grad_norm": 2.940490245819092, "learning_rate": 6.691780353095369e-06, "loss": 0.1529, "step": 379460 }, { "epoch": 2.255648483335414, "grad_norm": 4.2878546714782715, "learning_rate": 6.691585097779585e-06, "loss": 0.1536, "step": 379470 }, { "epoch": 2.255707925412082, "grad_norm": 4.773279666900635, "learning_rate": 6.69138983955069e-06, "loss": 0.1407, "step": 379480 }, { "epoch": 2.2557673674887506, "grad_norm": 3.768275022506714, "learning_rate": 6.691194578409018e-06, "loss": 0.1511, "step": 379490 }, { "epoch": 2.255826809565419, "grad_norm": 4.205913543701172, "learning_rate": 6.690999314354908e-06, "loss": 0.1411, "step": 379500 }, { "epoch": 2.2558862516420874, "grad_norm": 3.641921281814575, "learning_rate": 6.6908040473886944e-06, "loss": 0.1363, "step": 379510 }, { "epoch": 2.255945693718756, "grad_norm": 4.561389446258545, "learning_rate": 6.690608777510717e-06, "loss": 0.1706, "step": 379520 }, { "epoch": 2.2560051357954243, "grad_norm": 3.4169223308563232, "learning_rate": 6.690413504721307e-06, "loss": 0.1409, "step": 379530 }, { "epoch": 2.2560645778720927, "grad_norm": 4.0351080894470215, "learning_rate": 6.690218229020805e-06, "loss": 0.1482, "step": 379540 }, { "epoch": 2.256124019948761, "grad_norm": 4.357969284057617, "learning_rate": 6.690022950409545e-06, "loss": 0.1515, "step": 379550 }, { "epoch": 2.2561834620254295, "grad_norm": 3.7531135082244873, "learning_rate": 6.689827668887864e-06, "loss": 0.1461, "step": 379560 }, { "epoch": 2.2562429041020975, "grad_norm": 4.277556419372559, "learning_rate": 6.689632384456098e-06, "loss": 0.1585, "step": 379570 }, { "epoch": 2.2563023461787663, "grad_norm": 3.2844719886779785, "learning_rate": 6.689437097114584e-06, "loss": 0.1373, "step": 379580 }, { "epoch": 2.2563617882554343, "grad_norm": 2.765082836151123, "learning_rate": 6.689241806863656e-06, "loss": 0.1696, "step": 379590 }, { "epoch": 2.2564212303321027, "grad_norm": 5.467482089996338, "learning_rate": 6.6890465137036534e-06, "loss": 0.1337, "step": 379600 }, { "epoch": 2.256480672408771, "grad_norm": 4.309349536895752, "learning_rate": 6.6888512176349105e-06, "loss": 0.145, "step": 379610 }, { "epoch": 2.2565401144854396, "grad_norm": 4.366636276245117, "learning_rate": 6.688655918657765e-06, "loss": 0.1411, "step": 379620 }, { "epoch": 2.256599556562108, "grad_norm": 5.945245742797852, "learning_rate": 6.6884606167725515e-06, "loss": 0.1698, "step": 379630 }, { "epoch": 2.2566589986387764, "grad_norm": 4.418905258178711, "learning_rate": 6.688265311979608e-06, "loss": 0.1542, "step": 379640 }, { "epoch": 2.256718440715445, "grad_norm": 3.6337249279022217, "learning_rate": 6.688070004279271e-06, "loss": 0.1442, "step": 379650 }, { "epoch": 2.256777882792113, "grad_norm": 3.7942986488342285, "learning_rate": 6.6878746936718745e-06, "loss": 0.1502, "step": 379660 }, { "epoch": 2.2568373248687816, "grad_norm": 7.655693531036377, "learning_rate": 6.687679380157758e-06, "loss": 0.1776, "step": 379670 }, { "epoch": 2.25689676694545, "grad_norm": 3.391390562057495, "learning_rate": 6.687484063737255e-06, "loss": 0.1501, "step": 379680 }, { "epoch": 2.2569562090221185, "grad_norm": 4.753628730773926, "learning_rate": 6.687288744410703e-06, "loss": 0.1424, "step": 379690 }, { "epoch": 2.257015651098787, "grad_norm": 4.605510711669922, "learning_rate": 6.687093422178439e-06, "loss": 0.135, "step": 379700 }, { "epoch": 2.2570750931754553, "grad_norm": 4.105853080749512, "learning_rate": 6.6868980970407995e-06, "loss": 0.1287, "step": 379710 }, { "epoch": 2.2571345352521237, "grad_norm": 4.331269264221191, "learning_rate": 6.686702768998119e-06, "loss": 0.1411, "step": 379720 }, { "epoch": 2.257193977328792, "grad_norm": 4.6392998695373535, "learning_rate": 6.686507438050734e-06, "loss": 0.1706, "step": 379730 }, { "epoch": 2.2572534194054605, "grad_norm": 3.8451671600341797, "learning_rate": 6.686312104198984e-06, "loss": 0.155, "step": 379740 }, { "epoch": 2.257312861482129, "grad_norm": 4.219302654266357, "learning_rate": 6.686116767443204e-06, "loss": 0.153, "step": 379750 }, { "epoch": 2.257372303558797, "grad_norm": 4.925939083099365, "learning_rate": 6.685921427783728e-06, "loss": 0.1532, "step": 379760 }, { "epoch": 2.2574317456354653, "grad_norm": 4.2528228759765625, "learning_rate": 6.685726085220895e-06, "loss": 0.1444, "step": 379770 }, { "epoch": 2.2574911877121338, "grad_norm": 6.090809345245361, "learning_rate": 6.6855307397550405e-06, "loss": 0.1412, "step": 379780 }, { "epoch": 2.257550629788802, "grad_norm": 3.7315890789031982, "learning_rate": 6.685335391386501e-06, "loss": 0.1398, "step": 379790 }, { "epoch": 2.2576100718654706, "grad_norm": 4.197871685028076, "learning_rate": 6.685140040115612e-06, "loss": 0.1534, "step": 379800 }, { "epoch": 2.257669513942139, "grad_norm": 6.01619291305542, "learning_rate": 6.684944685942712e-06, "loss": 0.1447, "step": 379810 }, { "epoch": 2.2577289560188074, "grad_norm": 5.388095855712891, "learning_rate": 6.684749328868135e-06, "loss": 0.1462, "step": 379820 }, { "epoch": 2.257788398095476, "grad_norm": 3.5260262489318848, "learning_rate": 6.684553968892218e-06, "loss": 0.1425, "step": 379830 }, { "epoch": 2.2578478401721442, "grad_norm": 4.165322780609131, "learning_rate": 6.6843586060153e-06, "loss": 0.1451, "step": 379840 }, { "epoch": 2.2579072822488127, "grad_norm": 4.421106815338135, "learning_rate": 6.6841632402377155e-06, "loss": 0.1718, "step": 379850 }, { "epoch": 2.257966724325481, "grad_norm": 3.6399524211883545, "learning_rate": 6.6839678715598e-06, "loss": 0.1538, "step": 379860 }, { "epoch": 2.2580261664021495, "grad_norm": 3.8277525901794434, "learning_rate": 6.683772499981891e-06, "loss": 0.1428, "step": 379870 }, { "epoch": 2.258085608478818, "grad_norm": 3.110056161880493, "learning_rate": 6.683577125504326e-06, "loss": 0.145, "step": 379880 }, { "epoch": 2.2581450505554863, "grad_norm": 3.1111209392547607, "learning_rate": 6.6833817481274375e-06, "loss": 0.165, "step": 379890 }, { "epoch": 2.2582044926321547, "grad_norm": 3.9135401248931885, "learning_rate": 6.683186367851567e-06, "loss": 0.15, "step": 379900 }, { "epoch": 2.258263934708823, "grad_norm": 5.303636074066162, "learning_rate": 6.682990984677049e-06, "loss": 0.1429, "step": 379910 }, { "epoch": 2.2583233767854916, "grad_norm": 4.871828556060791, "learning_rate": 6.682795598604218e-06, "loss": 0.1415, "step": 379920 }, { "epoch": 2.2583828188621595, "grad_norm": 4.882762908935547, "learning_rate": 6.682600209633414e-06, "loss": 0.1459, "step": 379930 }, { "epoch": 2.2584422609388284, "grad_norm": 5.7261481285095215, "learning_rate": 6.6824048177649705e-06, "loss": 0.1385, "step": 379940 }, { "epoch": 2.2585017030154964, "grad_norm": 4.4303107261657715, "learning_rate": 6.682209422999225e-06, "loss": 0.1447, "step": 379950 }, { "epoch": 2.2585611450921648, "grad_norm": 4.880455493927002, "learning_rate": 6.682014025336515e-06, "loss": 0.1444, "step": 379960 }, { "epoch": 2.258620587168833, "grad_norm": 4.100556373596191, "learning_rate": 6.681818624777176e-06, "loss": 0.15, "step": 379970 }, { "epoch": 2.2586800292455016, "grad_norm": 3.931459665298462, "learning_rate": 6.681623221321544e-06, "loss": 0.1534, "step": 379980 }, { "epoch": 2.25873947132217, "grad_norm": 4.281154632568359, "learning_rate": 6.681427814969957e-06, "loss": 0.1466, "step": 379990 }, { "epoch": 2.2587989133988384, "grad_norm": 4.554262638092041, "learning_rate": 6.6812324057227506e-06, "loss": 0.1485, "step": 380000 }, { "epoch": 2.258858355475507, "grad_norm": 3.8838093280792236, "learning_rate": 6.681036993580261e-06, "loss": 0.1686, "step": 380010 }, { "epoch": 2.2589177975521753, "grad_norm": 4.065420627593994, "learning_rate": 6.680841578542825e-06, "loss": 0.1616, "step": 380020 }, { "epoch": 2.2589772396288437, "grad_norm": 5.133329391479492, "learning_rate": 6.68064616061078e-06, "loss": 0.1546, "step": 380030 }, { "epoch": 2.259036681705512, "grad_norm": 3.7305121421813965, "learning_rate": 6.680450739784462e-06, "loss": 0.1454, "step": 380040 }, { "epoch": 2.2590961237821805, "grad_norm": 3.5189220905303955, "learning_rate": 6.680255316064205e-06, "loss": 0.1511, "step": 380050 }, { "epoch": 2.259155565858849, "grad_norm": 3.350700616836548, "learning_rate": 6.68005988945035e-06, "loss": 0.1373, "step": 380060 }, { "epoch": 2.2592150079355173, "grad_norm": 4.254192352294922, "learning_rate": 6.679864459943231e-06, "loss": 0.1437, "step": 380070 }, { "epoch": 2.2592744500121857, "grad_norm": 5.774166107177734, "learning_rate": 6.679669027543184e-06, "loss": 0.1359, "step": 380080 }, { "epoch": 2.259333892088854, "grad_norm": 3.9674253463745117, "learning_rate": 6.679473592250548e-06, "loss": 0.1465, "step": 380090 }, { "epoch": 2.2593933341655226, "grad_norm": 5.283110618591309, "learning_rate": 6.6792781540656585e-06, "loss": 0.1578, "step": 380100 }, { "epoch": 2.259452776242191, "grad_norm": 3.663724660873413, "learning_rate": 6.679082712988849e-06, "loss": 0.1527, "step": 380110 }, { "epoch": 2.259512218318859, "grad_norm": 3.9857261180877686, "learning_rate": 6.678887269020461e-06, "loss": 0.1632, "step": 380120 }, { "epoch": 2.259571660395528, "grad_norm": 4.9818196296691895, "learning_rate": 6.678691822160829e-06, "loss": 0.1612, "step": 380130 }, { "epoch": 2.259631102472196, "grad_norm": 6.306521892547607, "learning_rate": 6.678496372410288e-06, "loss": 0.1433, "step": 380140 }, { "epoch": 2.259690544548864, "grad_norm": 3.769439220428467, "learning_rate": 6.678300919769176e-06, "loss": 0.1323, "step": 380150 }, { "epoch": 2.2597499866255326, "grad_norm": 3.2004570960998535, "learning_rate": 6.67810546423783e-06, "loss": 0.1379, "step": 380160 }, { "epoch": 2.259809428702201, "grad_norm": 4.508895397186279, "learning_rate": 6.677910005816586e-06, "loss": 0.1525, "step": 380170 }, { "epoch": 2.2598688707788694, "grad_norm": 4.232626438140869, "learning_rate": 6.67771454450578e-06, "loss": 0.1556, "step": 380180 }, { "epoch": 2.259928312855538, "grad_norm": 3.87045955657959, "learning_rate": 6.677519080305751e-06, "loss": 0.1522, "step": 380190 }, { "epoch": 2.2599877549322063, "grad_norm": 4.860429763793945, "learning_rate": 6.677323613216834e-06, "loss": 0.1646, "step": 380200 }, { "epoch": 2.2600471970088747, "grad_norm": 4.584956645965576, "learning_rate": 6.677128143239364e-06, "loss": 0.1605, "step": 380210 }, { "epoch": 2.260106639085543, "grad_norm": 3.593864679336548, "learning_rate": 6.676932670373682e-06, "loss": 0.1272, "step": 380220 }, { "epoch": 2.2601660811622115, "grad_norm": 4.39354944229126, "learning_rate": 6.67673719462012e-06, "loss": 0.1667, "step": 380230 }, { "epoch": 2.26022552323888, "grad_norm": 4.972178936004639, "learning_rate": 6.676541715979014e-06, "loss": 0.1561, "step": 380240 }, { "epoch": 2.2602849653155483, "grad_norm": 4.392920970916748, "learning_rate": 6.676346234450707e-06, "loss": 0.1492, "step": 380250 }, { "epoch": 2.2603444073922168, "grad_norm": 4.51698637008667, "learning_rate": 6.6761507500355305e-06, "loss": 0.1472, "step": 380260 }, { "epoch": 2.260403849468885, "grad_norm": 4.520913600921631, "learning_rate": 6.675955262733822e-06, "loss": 0.1466, "step": 380270 }, { "epoch": 2.2604632915455536, "grad_norm": 3.9669485092163086, "learning_rate": 6.675759772545918e-06, "loss": 0.1449, "step": 380280 }, { "epoch": 2.260522733622222, "grad_norm": 5.346999645233154, "learning_rate": 6.675564279472158e-06, "loss": 0.1517, "step": 380290 }, { "epoch": 2.2605821756988904, "grad_norm": 3.276031017303467, "learning_rate": 6.675368783512875e-06, "loss": 0.1433, "step": 380300 }, { "epoch": 2.2606416177755584, "grad_norm": 4.125209808349609, "learning_rate": 6.675173284668406e-06, "loss": 0.1596, "step": 380310 }, { "epoch": 2.2607010598522272, "grad_norm": 3.9128928184509277, "learning_rate": 6.674977782939091e-06, "loss": 0.1384, "step": 380320 }, { "epoch": 2.260760501928895, "grad_norm": 6.9576616287231445, "learning_rate": 6.674782278325263e-06, "loss": 0.1504, "step": 380330 }, { "epoch": 2.2608199440055636, "grad_norm": 2.9242970943450928, "learning_rate": 6.6745867708272595e-06, "loss": 0.1402, "step": 380340 }, { "epoch": 2.260879386082232, "grad_norm": 4.385288715362549, "learning_rate": 6.674391260445418e-06, "loss": 0.1503, "step": 380350 }, { "epoch": 2.2609388281589005, "grad_norm": 3.678424835205078, "learning_rate": 6.674195747180077e-06, "loss": 0.1373, "step": 380360 }, { "epoch": 2.260998270235569, "grad_norm": 6.035873889923096, "learning_rate": 6.6740002310315686e-06, "loss": 0.1665, "step": 380370 }, { "epoch": 2.2610577123122373, "grad_norm": 3.97438645362854, "learning_rate": 6.673804712000233e-06, "loss": 0.1899, "step": 380380 }, { "epoch": 2.2611171543889057, "grad_norm": 5.226827144622803, "learning_rate": 6.6736091900864054e-06, "loss": 0.153, "step": 380390 }, { "epoch": 2.261176596465574, "grad_norm": 4.536026954650879, "learning_rate": 6.673413665290425e-06, "loss": 0.1663, "step": 380400 }, { "epoch": 2.2612360385422425, "grad_norm": 4.792679309844971, "learning_rate": 6.673218137612625e-06, "loss": 0.1539, "step": 380410 }, { "epoch": 2.261295480618911, "grad_norm": 3.8470757007598877, "learning_rate": 6.6730226070533434e-06, "loss": 0.1513, "step": 380420 }, { "epoch": 2.2613549226955794, "grad_norm": 6.704864025115967, "learning_rate": 6.672827073612918e-06, "loss": 0.1632, "step": 380430 }, { "epoch": 2.2614143647722478, "grad_norm": 4.190001010894775, "learning_rate": 6.672631537291685e-06, "loss": 0.1502, "step": 380440 }, { "epoch": 2.261473806848916, "grad_norm": 3.89505672454834, "learning_rate": 6.672435998089981e-06, "loss": 0.154, "step": 380450 }, { "epoch": 2.2615332489255846, "grad_norm": 3.425539493560791, "learning_rate": 6.672240456008142e-06, "loss": 0.1424, "step": 380460 }, { "epoch": 2.261592691002253, "grad_norm": 4.579227447509766, "learning_rate": 6.672044911046506e-06, "loss": 0.1453, "step": 380470 }, { "epoch": 2.2616521330789214, "grad_norm": 3.4781911373138428, "learning_rate": 6.6718493632054095e-06, "loss": 0.1521, "step": 380480 }, { "epoch": 2.26171157515559, "grad_norm": 4.355502128601074, "learning_rate": 6.671653812485187e-06, "loss": 0.1465, "step": 380490 }, { "epoch": 2.261771017232258, "grad_norm": 3.2785377502441406, "learning_rate": 6.671458258886179e-06, "loss": 0.1473, "step": 380500 }, { "epoch": 2.2618304593089262, "grad_norm": 3.534022092819214, "learning_rate": 6.671262702408718e-06, "loss": 0.1447, "step": 380510 }, { "epoch": 2.2618899013855946, "grad_norm": 3.8586854934692383, "learning_rate": 6.671067143053147e-06, "loss": 0.1497, "step": 380520 }, { "epoch": 2.261949343462263, "grad_norm": 4.241779327392578, "learning_rate": 6.670871580819796e-06, "loss": 0.1506, "step": 380530 }, { "epoch": 2.2620087855389315, "grad_norm": 4.544129848480225, "learning_rate": 6.670676015709006e-06, "loss": 0.1418, "step": 380540 }, { "epoch": 2.2620682276156, "grad_norm": 6.004791736602783, "learning_rate": 6.670480447721113e-06, "loss": 0.1496, "step": 380550 }, { "epoch": 2.2621276696922683, "grad_norm": 4.081797122955322, "learning_rate": 6.670284876856453e-06, "loss": 0.1407, "step": 380560 }, { "epoch": 2.2621871117689367, "grad_norm": 5.153275012969971, "learning_rate": 6.670089303115362e-06, "loss": 0.1417, "step": 380570 }, { "epoch": 2.262246553845605, "grad_norm": 3.7426886558532715, "learning_rate": 6.66989372649818e-06, "loss": 0.1417, "step": 380580 }, { "epoch": 2.2623059959222735, "grad_norm": 4.760806560516357, "learning_rate": 6.6696981470052415e-06, "loss": 0.1583, "step": 380590 }, { "epoch": 2.262365437998942, "grad_norm": 3.9648358821868896, "learning_rate": 6.6695025646368805e-06, "loss": 0.142, "step": 380600 }, { "epoch": 2.2624248800756104, "grad_norm": 4.389492988586426, "learning_rate": 6.66930697939344e-06, "loss": 0.133, "step": 380610 }, { "epoch": 2.262484322152279, "grad_norm": 6.289649486541748, "learning_rate": 6.669111391275252e-06, "loss": 0.1483, "step": 380620 }, { "epoch": 2.262543764228947, "grad_norm": 4.366462707519531, "learning_rate": 6.668915800282656e-06, "loss": 0.147, "step": 380630 }, { "epoch": 2.2626032063056156, "grad_norm": 3.269378662109375, "learning_rate": 6.668720206415987e-06, "loss": 0.1406, "step": 380640 }, { "epoch": 2.262662648382284, "grad_norm": 3.632596015930176, "learning_rate": 6.668524609675584e-06, "loss": 0.1372, "step": 380650 }, { "epoch": 2.2627220904589525, "grad_norm": 4.364795207977295, "learning_rate": 6.668329010061781e-06, "loss": 0.1486, "step": 380660 }, { "epoch": 2.2627815325356204, "grad_norm": 5.1209516525268555, "learning_rate": 6.668133407574918e-06, "loss": 0.1344, "step": 380670 }, { "epoch": 2.2628409746122893, "grad_norm": 4.044089317321777, "learning_rate": 6.66793780221533e-06, "loss": 0.1417, "step": 380680 }, { "epoch": 2.2629004166889573, "grad_norm": 3.618943452835083, "learning_rate": 6.667742193983353e-06, "loss": 0.1297, "step": 380690 }, { "epoch": 2.2629598587656257, "grad_norm": 5.4547882080078125, "learning_rate": 6.667546582879326e-06, "loss": 0.1445, "step": 380700 }, { "epoch": 2.263019300842294, "grad_norm": 3.476691722869873, "learning_rate": 6.667350968903583e-06, "loss": 0.14, "step": 380710 }, { "epoch": 2.2630787429189625, "grad_norm": 3.876603841781616, "learning_rate": 6.667155352056465e-06, "loss": 0.1463, "step": 380720 }, { "epoch": 2.263138184995631, "grad_norm": 3.440829038619995, "learning_rate": 6.666959732338305e-06, "loss": 0.1396, "step": 380730 }, { "epoch": 2.2631976270722993, "grad_norm": 3.9162561893463135, "learning_rate": 6.6667641097494425e-06, "loss": 0.15, "step": 380740 }, { "epoch": 2.2632570691489677, "grad_norm": 4.308454513549805, "learning_rate": 6.666568484290213e-06, "loss": 0.1321, "step": 380750 }, { "epoch": 2.263316511225636, "grad_norm": 4.527935981750488, "learning_rate": 6.666372855960953e-06, "loss": 0.1701, "step": 380760 }, { "epoch": 2.2633759533023046, "grad_norm": 4.146481513977051, "learning_rate": 6.666177224762001e-06, "loss": 0.1557, "step": 380770 }, { "epoch": 2.263435395378973, "grad_norm": 3.6879501342773438, "learning_rate": 6.6659815906936934e-06, "loss": 0.1425, "step": 380780 }, { "epoch": 2.2634948374556414, "grad_norm": 3.3718175888061523, "learning_rate": 6.665785953756365e-06, "loss": 0.1425, "step": 380790 }, { "epoch": 2.26355427953231, "grad_norm": 3.699530601501465, "learning_rate": 6.665590313950357e-06, "loss": 0.1708, "step": 380800 }, { "epoch": 2.2636137216089782, "grad_norm": 5.582919597625732, "learning_rate": 6.665394671276002e-06, "loss": 0.1643, "step": 380810 }, { "epoch": 2.2636731636856466, "grad_norm": 5.5161452293396, "learning_rate": 6.6651990257336384e-06, "loss": 0.1444, "step": 380820 }, { "epoch": 2.263732605762315, "grad_norm": 4.761070728302002, "learning_rate": 6.6650033773236034e-06, "loss": 0.1238, "step": 380830 }, { "epoch": 2.2637920478389835, "grad_norm": 5.533894062042236, "learning_rate": 6.664807726046234e-06, "loss": 0.1558, "step": 380840 }, { "epoch": 2.263851489915652, "grad_norm": 4.653940677642822, "learning_rate": 6.664612071901868e-06, "loss": 0.1689, "step": 380850 }, { "epoch": 2.26391093199232, "grad_norm": 5.489431858062744, "learning_rate": 6.664416414890841e-06, "loss": 0.1372, "step": 380860 }, { "epoch": 2.2639703740689887, "grad_norm": 3.92083477973938, "learning_rate": 6.66422075501349e-06, "loss": 0.1636, "step": 380870 }, { "epoch": 2.2640298161456567, "grad_norm": 3.829463005065918, "learning_rate": 6.6640250922701536e-06, "loss": 0.1416, "step": 380880 }, { "epoch": 2.264089258222325, "grad_norm": 3.7656824588775635, "learning_rate": 6.6638294266611645e-06, "loss": 0.1436, "step": 380890 }, { "epoch": 2.2641487002989935, "grad_norm": 4.652585506439209, "learning_rate": 6.663633758186865e-06, "loss": 0.1405, "step": 380900 }, { "epoch": 2.264208142375662, "grad_norm": 4.064049243927002, "learning_rate": 6.66343808684759e-06, "loss": 0.1607, "step": 380910 }, { "epoch": 2.2642675844523303, "grad_norm": 3.6142783164978027, "learning_rate": 6.663242412643675e-06, "loss": 0.1319, "step": 380920 }, { "epoch": 2.2643270265289988, "grad_norm": 5.365147113800049, "learning_rate": 6.663046735575457e-06, "loss": 0.1549, "step": 380930 }, { "epoch": 2.264386468605667, "grad_norm": 4.052027702331543, "learning_rate": 6.662851055643276e-06, "loss": 0.151, "step": 380940 }, { "epoch": 2.2644459106823356, "grad_norm": 4.746528148651123, "learning_rate": 6.662655372847467e-06, "loss": 0.1642, "step": 380950 }, { "epoch": 2.264505352759004, "grad_norm": 6.149040222167969, "learning_rate": 6.662459687188365e-06, "loss": 0.1474, "step": 380960 }, { "epoch": 2.2645647948356724, "grad_norm": 4.47253942489624, "learning_rate": 6.6622639986663115e-06, "loss": 0.1562, "step": 380970 }, { "epoch": 2.264624236912341, "grad_norm": 8.993659973144531, "learning_rate": 6.662068307281641e-06, "loss": 0.1656, "step": 380980 }, { "epoch": 2.2646836789890092, "grad_norm": 4.249186038970947, "learning_rate": 6.661872613034689e-06, "loss": 0.1504, "step": 380990 }, { "epoch": 2.2647431210656777, "grad_norm": 3.8115499019622803, "learning_rate": 6.6616769159257955e-06, "loss": 0.1381, "step": 381000 }, { "epoch": 2.264802563142346, "grad_norm": 4.487789630889893, "learning_rate": 6.6614812159552954e-06, "loss": 0.1517, "step": 381010 }, { "epoch": 2.2648620052190145, "grad_norm": 4.03100061416626, "learning_rate": 6.661285513123526e-06, "loss": 0.159, "step": 381020 }, { "epoch": 2.264921447295683, "grad_norm": 5.448384761810303, "learning_rate": 6.661089807430825e-06, "loss": 0.149, "step": 381030 }, { "epoch": 2.2649808893723513, "grad_norm": 5.354726791381836, "learning_rate": 6.660894098877528e-06, "loss": 0.1614, "step": 381040 }, { "epoch": 2.2650403314490193, "grad_norm": 3.6548707485198975, "learning_rate": 6.660698387463976e-06, "loss": 0.1454, "step": 381050 }, { "epoch": 2.265099773525688, "grad_norm": 4.265453338623047, "learning_rate": 6.660502673190501e-06, "loss": 0.1493, "step": 381060 }, { "epoch": 2.265159215602356, "grad_norm": 4.5309319496154785, "learning_rate": 6.660306956057443e-06, "loss": 0.1551, "step": 381070 }, { "epoch": 2.2652186576790245, "grad_norm": 5.2388691902160645, "learning_rate": 6.660111236065139e-06, "loss": 0.1676, "step": 381080 }, { "epoch": 2.265278099755693, "grad_norm": 3.0911238193511963, "learning_rate": 6.6599155132139235e-06, "loss": 0.1282, "step": 381090 }, { "epoch": 2.2653375418323614, "grad_norm": 3.928385019302368, "learning_rate": 6.659719787504138e-06, "loss": 0.1433, "step": 381100 }, { "epoch": 2.2653969839090298, "grad_norm": 4.153759479522705, "learning_rate": 6.6595240589361156e-06, "loss": 0.1512, "step": 381110 }, { "epoch": 2.265456425985698, "grad_norm": 3.7134814262390137, "learning_rate": 6.659328327510194e-06, "loss": 0.1473, "step": 381120 }, { "epoch": 2.2655158680623666, "grad_norm": 5.1497039794921875, "learning_rate": 6.659132593226711e-06, "loss": 0.1632, "step": 381130 }, { "epoch": 2.265575310139035, "grad_norm": 5.013808250427246, "learning_rate": 6.658936856086006e-06, "loss": 0.1562, "step": 381140 }, { "epoch": 2.2656347522157034, "grad_norm": 4.302413463592529, "learning_rate": 6.65874111608841e-06, "loss": 0.1508, "step": 381150 }, { "epoch": 2.265694194292372, "grad_norm": 3.510373115539551, "learning_rate": 6.6585453732342665e-06, "loss": 0.1402, "step": 381160 }, { "epoch": 2.2657536363690403, "grad_norm": 4.271909236907959, "learning_rate": 6.65834962752391e-06, "loss": 0.1508, "step": 381170 }, { "epoch": 2.2658130784457087, "grad_norm": 4.825737953186035, "learning_rate": 6.658153878957678e-06, "loss": 0.1644, "step": 381180 }, { "epoch": 2.265872520522377, "grad_norm": 4.982625484466553, "learning_rate": 6.657958127535905e-06, "loss": 0.1537, "step": 381190 }, { "epoch": 2.2659319625990455, "grad_norm": 3.297248125076294, "learning_rate": 6.657762373258933e-06, "loss": 0.1378, "step": 381200 }, { "epoch": 2.265991404675714, "grad_norm": 5.050254821777344, "learning_rate": 6.657566616127094e-06, "loss": 0.1368, "step": 381210 }, { "epoch": 2.2660508467523823, "grad_norm": 3.8366785049438477, "learning_rate": 6.657370856140729e-06, "loss": 0.1363, "step": 381220 }, { "epoch": 2.2661102888290507, "grad_norm": 4.203409194946289, "learning_rate": 6.657175093300173e-06, "loss": 0.1403, "step": 381230 }, { "epoch": 2.2661697309057187, "grad_norm": 3.6907336711883545, "learning_rate": 6.656979327605765e-06, "loss": 0.1575, "step": 381240 }, { "epoch": 2.266229172982387, "grad_norm": 3.989919900894165, "learning_rate": 6.6567835590578385e-06, "loss": 0.1438, "step": 381250 }, { "epoch": 2.2662886150590555, "grad_norm": 4.200897693634033, "learning_rate": 6.656587787656734e-06, "loss": 0.134, "step": 381260 }, { "epoch": 2.266348057135724, "grad_norm": 4.731774806976318, "learning_rate": 6.656392013402788e-06, "loss": 0.1779, "step": 381270 }, { "epoch": 2.2664074992123924, "grad_norm": 4.769007682800293, "learning_rate": 6.656196236296337e-06, "loss": 0.1342, "step": 381280 }, { "epoch": 2.266466941289061, "grad_norm": 5.621479034423828, "learning_rate": 6.656000456337719e-06, "loss": 0.1678, "step": 381290 }, { "epoch": 2.266526383365729, "grad_norm": 5.648184776306152, "learning_rate": 6.655804673527271e-06, "loss": 0.141, "step": 381300 }, { "epoch": 2.2665858254423976, "grad_norm": 3.1214487552642822, "learning_rate": 6.655608887865328e-06, "loss": 0.1465, "step": 381310 }, { "epoch": 2.266645267519066, "grad_norm": 4.718627452850342, "learning_rate": 6.655413099352231e-06, "loss": 0.1446, "step": 381320 }, { "epoch": 2.2667047095957344, "grad_norm": 3.9083709716796875, "learning_rate": 6.655217307988315e-06, "loss": 0.1515, "step": 381330 }, { "epoch": 2.266764151672403, "grad_norm": 5.135563373565674, "learning_rate": 6.655021513773916e-06, "loss": 0.1448, "step": 381340 }, { "epoch": 2.2668235937490713, "grad_norm": 4.77571439743042, "learning_rate": 6.654825716709373e-06, "loss": 0.1494, "step": 381350 }, { "epoch": 2.2668830358257397, "grad_norm": 4.993753433227539, "learning_rate": 6.654629916795024e-06, "loss": 0.146, "step": 381360 }, { "epoch": 2.266942477902408, "grad_norm": 4.684832572937012, "learning_rate": 6.654434114031202e-06, "loss": 0.1556, "step": 381370 }, { "epoch": 2.2670019199790765, "grad_norm": 4.857513904571533, "learning_rate": 6.654238308418248e-06, "loss": 0.1458, "step": 381380 }, { "epoch": 2.267061362055745, "grad_norm": 4.485189437866211, "learning_rate": 6.654042499956499e-06, "loss": 0.1381, "step": 381390 }, { "epoch": 2.2671208041324133, "grad_norm": 4.52161169052124, "learning_rate": 6.653846688646293e-06, "loss": 0.1625, "step": 381400 }, { "epoch": 2.2671802462090813, "grad_norm": 4.6117119789123535, "learning_rate": 6.653650874487963e-06, "loss": 0.1532, "step": 381410 }, { "epoch": 2.26723968828575, "grad_norm": 4.148966312408447, "learning_rate": 6.65345505748185e-06, "loss": 0.1474, "step": 381420 }, { "epoch": 2.267299130362418, "grad_norm": 4.635978698730469, "learning_rate": 6.65325923762829e-06, "loss": 0.1696, "step": 381430 }, { "epoch": 2.2673585724390866, "grad_norm": 4.491586685180664, "learning_rate": 6.65306341492762e-06, "loss": 0.1417, "step": 381440 }, { "epoch": 2.267418014515755, "grad_norm": 4.0251007080078125, "learning_rate": 6.652867589380178e-06, "loss": 0.1368, "step": 381450 }, { "epoch": 2.2674774565924234, "grad_norm": 3.921025276184082, "learning_rate": 6.652671760986301e-06, "loss": 0.1641, "step": 381460 }, { "epoch": 2.267536898669092, "grad_norm": 4.762872219085693, "learning_rate": 6.652475929746325e-06, "loss": 0.1555, "step": 381470 }, { "epoch": 2.26759634074576, "grad_norm": 3.7761266231536865, "learning_rate": 6.6522800956605884e-06, "loss": 0.1402, "step": 381480 }, { "epoch": 2.2676557828224286, "grad_norm": 4.617523193359375, "learning_rate": 6.65208425872943e-06, "loss": 0.1398, "step": 381490 }, { "epoch": 2.267715224899097, "grad_norm": 6.944190502166748, "learning_rate": 6.651888418953184e-06, "loss": 0.2072, "step": 381500 }, { "epoch": 2.2677746669757655, "grad_norm": 3.3114802837371826, "learning_rate": 6.651692576332188e-06, "loss": 0.1538, "step": 381510 }, { "epoch": 2.267834109052434, "grad_norm": 4.310798645019531, "learning_rate": 6.651496730866782e-06, "loss": 0.1601, "step": 381520 }, { "epoch": 2.2678935511291023, "grad_norm": 4.504782199859619, "learning_rate": 6.6513008825573026e-06, "loss": 0.1374, "step": 381530 }, { "epoch": 2.2679529932057707, "grad_norm": 3.954665184020996, "learning_rate": 6.651105031404084e-06, "loss": 0.1545, "step": 381540 }, { "epoch": 2.268012435282439, "grad_norm": 4.231101989746094, "learning_rate": 6.650909177407466e-06, "loss": 0.1552, "step": 381550 }, { "epoch": 2.2680718773591075, "grad_norm": 3.815279722213745, "learning_rate": 6.650713320567786e-06, "loss": 0.143, "step": 381560 }, { "epoch": 2.268131319435776, "grad_norm": 3.87431263923645, "learning_rate": 6.650517460885379e-06, "loss": 0.1548, "step": 381570 }, { "epoch": 2.2681907615124444, "grad_norm": 4.342862129211426, "learning_rate": 6.650321598360587e-06, "loss": 0.1411, "step": 381580 }, { "epoch": 2.268250203589113, "grad_norm": 5.7258806228637695, "learning_rate": 6.650125732993742e-06, "loss": 0.1511, "step": 381590 }, { "epoch": 2.2683096456657807, "grad_norm": 3.757033586502075, "learning_rate": 6.649929864785184e-06, "loss": 0.1378, "step": 381600 }, { "epoch": 2.2683690877424496, "grad_norm": 6.528306007385254, "learning_rate": 6.64973399373525e-06, "loss": 0.154, "step": 381610 }, { "epoch": 2.2684285298191176, "grad_norm": 4.611955642700195, "learning_rate": 6.649538119844278e-06, "loss": 0.1502, "step": 381620 }, { "epoch": 2.268487971895786, "grad_norm": 4.911718845367432, "learning_rate": 6.649342243112605e-06, "loss": 0.1582, "step": 381630 }, { "epoch": 2.2685474139724544, "grad_norm": 4.004047393798828, "learning_rate": 6.649146363540565e-06, "loss": 0.149, "step": 381640 }, { "epoch": 2.268606856049123, "grad_norm": 3.800044298171997, "learning_rate": 6.6489504811285e-06, "loss": 0.157, "step": 381650 }, { "epoch": 2.2686662981257912, "grad_norm": 4.00769567489624, "learning_rate": 6.6487545958767455e-06, "loss": 0.1386, "step": 381660 }, { "epoch": 2.2687257402024597, "grad_norm": 4.501867294311523, "learning_rate": 6.648558707785639e-06, "loss": 0.136, "step": 381670 }, { "epoch": 2.268785182279128, "grad_norm": 4.285567760467529, "learning_rate": 6.648362816855517e-06, "loss": 0.1566, "step": 381680 }, { "epoch": 2.2688446243557965, "grad_norm": 5.017813205718994, "learning_rate": 6.648166923086719e-06, "loss": 0.1493, "step": 381690 }, { "epoch": 2.268904066432465, "grad_norm": 3.877833127975464, "learning_rate": 6.647971026479579e-06, "loss": 0.1374, "step": 381700 }, { "epoch": 2.2689635085091333, "grad_norm": 3.914431571960449, "learning_rate": 6.647775127034437e-06, "loss": 0.1292, "step": 381710 }, { "epoch": 2.2690229505858017, "grad_norm": 4.595052242279053, "learning_rate": 6.6475792247516305e-06, "loss": 0.1439, "step": 381720 }, { "epoch": 2.26908239266247, "grad_norm": 3.611262083053589, "learning_rate": 6.6473833196314955e-06, "loss": 0.1465, "step": 381730 }, { "epoch": 2.2691418347391386, "grad_norm": 3.5051348209381104, "learning_rate": 6.6471874116743685e-06, "loss": 0.136, "step": 381740 }, { "epoch": 2.269201276815807, "grad_norm": 3.3025662899017334, "learning_rate": 6.64699150088059e-06, "loss": 0.1383, "step": 381750 }, { "epoch": 2.2692607188924754, "grad_norm": 4.726325035095215, "learning_rate": 6.646795587250495e-06, "loss": 0.149, "step": 381760 }, { "epoch": 2.269320160969144, "grad_norm": 3.77624773979187, "learning_rate": 6.646599670784422e-06, "loss": 0.1423, "step": 381770 }, { "epoch": 2.269379603045812, "grad_norm": 4.001899719238281, "learning_rate": 6.646403751482707e-06, "loss": 0.148, "step": 381780 }, { "epoch": 2.26943904512248, "grad_norm": 3.6980702877044678, "learning_rate": 6.646207829345689e-06, "loss": 0.1493, "step": 381790 }, { "epoch": 2.2694984871991486, "grad_norm": 3.714735746383667, "learning_rate": 6.646011904373704e-06, "loss": 0.1494, "step": 381800 }, { "epoch": 2.269557929275817, "grad_norm": 4.699966907501221, "learning_rate": 6.64581597656709e-06, "loss": 0.149, "step": 381810 }, { "epoch": 2.2696173713524854, "grad_norm": 5.610661029815674, "learning_rate": 6.645620045926186e-06, "loss": 0.1542, "step": 381820 }, { "epoch": 2.269676813429154, "grad_norm": 4.338856220245361, "learning_rate": 6.645424112451326e-06, "loss": 0.1618, "step": 381830 }, { "epoch": 2.2697362555058223, "grad_norm": 4.957662582397461, "learning_rate": 6.6452281761428505e-06, "loss": 0.167, "step": 381840 }, { "epoch": 2.2697956975824907, "grad_norm": 3.958179473876953, "learning_rate": 6.645032237001096e-06, "loss": 0.1609, "step": 381850 }, { "epoch": 2.269855139659159, "grad_norm": 4.304530143737793, "learning_rate": 6.6448362950264e-06, "loss": 0.1494, "step": 381860 }, { "epoch": 2.2699145817358275, "grad_norm": 4.352411270141602, "learning_rate": 6.6446403502190985e-06, "loss": 0.1376, "step": 381870 }, { "epoch": 2.269974023812496, "grad_norm": 4.147041320800781, "learning_rate": 6.644444402579531e-06, "loss": 0.1349, "step": 381880 }, { "epoch": 2.2700334658891643, "grad_norm": 4.000110149383545, "learning_rate": 6.644248452108033e-06, "loss": 0.1437, "step": 381890 }, { "epoch": 2.2700929079658327, "grad_norm": 5.745273113250732, "learning_rate": 6.644052498804943e-06, "loss": 0.147, "step": 381900 }, { "epoch": 2.270152350042501, "grad_norm": 5.47467041015625, "learning_rate": 6.6438565426705995e-06, "loss": 0.1638, "step": 381910 }, { "epoch": 2.2702117921191696, "grad_norm": 5.042054176330566, "learning_rate": 6.643660583705338e-06, "loss": 0.1372, "step": 381920 }, { "epoch": 2.270271234195838, "grad_norm": 5.775252819061279, "learning_rate": 6.643464621909497e-06, "loss": 0.1539, "step": 381930 }, { "epoch": 2.2703306762725064, "grad_norm": 3.9249961376190186, "learning_rate": 6.6432686572834135e-06, "loss": 0.1478, "step": 381940 }, { "epoch": 2.270390118349175, "grad_norm": 3.9624295234680176, "learning_rate": 6.643072689827427e-06, "loss": 0.1597, "step": 381950 }, { "epoch": 2.2704495604258432, "grad_norm": 3.773129463195801, "learning_rate": 6.642876719541871e-06, "loss": 0.137, "step": 381960 }, { "epoch": 2.2705090025025116, "grad_norm": 4.935487270355225, "learning_rate": 6.642680746427087e-06, "loss": 0.1619, "step": 381970 }, { "epoch": 2.2705684445791796, "grad_norm": 4.133431434631348, "learning_rate": 6.642484770483411e-06, "loss": 0.157, "step": 381980 }, { "epoch": 2.270627886655848, "grad_norm": 5.5771894454956055, "learning_rate": 6.642288791711178e-06, "loss": 0.1572, "step": 381990 }, { "epoch": 2.2706873287325164, "grad_norm": 2.9852559566497803, "learning_rate": 6.6420928101107295e-06, "loss": 0.1447, "step": 382000 }, { "epoch": 2.270746770809185, "grad_norm": 3.8431403636932373, "learning_rate": 6.641896825682402e-06, "loss": 0.1565, "step": 382010 }, { "epoch": 2.2708062128858533, "grad_norm": 4.769067287445068, "learning_rate": 6.64170083842653e-06, "loss": 0.1522, "step": 382020 }, { "epoch": 2.2708656549625217, "grad_norm": 4.747661590576172, "learning_rate": 6.641504848343454e-06, "loss": 0.1479, "step": 382030 }, { "epoch": 2.27092509703919, "grad_norm": 4.018467426300049, "learning_rate": 6.641308855433511e-06, "loss": 0.1674, "step": 382040 }, { "epoch": 2.2709845391158585, "grad_norm": 5.059308052062988, "learning_rate": 6.641112859697039e-06, "loss": 0.1506, "step": 382050 }, { "epoch": 2.271043981192527, "grad_norm": 4.289659023284912, "learning_rate": 6.640916861134374e-06, "loss": 0.1627, "step": 382060 }, { "epoch": 2.2711034232691953, "grad_norm": 4.146404266357422, "learning_rate": 6.640720859745855e-06, "loss": 0.1323, "step": 382070 }, { "epoch": 2.2711628653458638, "grad_norm": 3.755312204360962, "learning_rate": 6.640524855531819e-06, "loss": 0.1381, "step": 382080 }, { "epoch": 2.271222307422532, "grad_norm": 4.598997116088867, "learning_rate": 6.640328848492602e-06, "loss": 0.1349, "step": 382090 }, { "epoch": 2.2712817494992006, "grad_norm": 2.8583452701568604, "learning_rate": 6.640132838628544e-06, "loss": 0.157, "step": 382100 }, { "epoch": 2.271341191575869, "grad_norm": 4.415762424468994, "learning_rate": 6.639936825939984e-06, "loss": 0.1419, "step": 382110 }, { "epoch": 2.2714006336525374, "grad_norm": 4.976746559143066, "learning_rate": 6.639740810427253e-06, "loss": 0.1335, "step": 382120 }, { "epoch": 2.271460075729206, "grad_norm": 4.392239570617676, "learning_rate": 6.639544792090696e-06, "loss": 0.1507, "step": 382130 }, { "epoch": 2.2715195178058742, "grad_norm": 2.8101768493652344, "learning_rate": 6.639348770930643e-06, "loss": 0.1533, "step": 382140 }, { "epoch": 2.271578959882542, "grad_norm": 4.275089263916016, "learning_rate": 6.63915274694744e-06, "loss": 0.1429, "step": 382150 }, { "epoch": 2.271638401959211, "grad_norm": 4.971024513244629, "learning_rate": 6.638956720141418e-06, "loss": 0.1754, "step": 382160 }, { "epoch": 2.271697844035879, "grad_norm": 4.615143775939941, "learning_rate": 6.638760690512918e-06, "loss": 0.1495, "step": 382170 }, { "epoch": 2.2717572861125475, "grad_norm": 4.0892438888549805, "learning_rate": 6.638564658062276e-06, "loss": 0.1422, "step": 382180 }, { "epoch": 2.271816728189216, "grad_norm": 3.333739995956421, "learning_rate": 6.63836862278983e-06, "loss": 0.1426, "step": 382190 }, { "epoch": 2.2718761702658843, "grad_norm": 4.756009578704834, "learning_rate": 6.63817258469592e-06, "loss": 0.1613, "step": 382200 }, { "epoch": 2.2719356123425527, "grad_norm": 3.889331817626953, "learning_rate": 6.63797654378088e-06, "loss": 0.1376, "step": 382210 }, { "epoch": 2.271995054419221, "grad_norm": 4.675168037414551, "learning_rate": 6.637780500045048e-06, "loss": 0.1417, "step": 382220 }, { "epoch": 2.2720544964958895, "grad_norm": 5.6182861328125, "learning_rate": 6.6375844534887634e-06, "loss": 0.1652, "step": 382230 }, { "epoch": 2.272113938572558, "grad_norm": 2.9603281021118164, "learning_rate": 6.637388404112362e-06, "loss": 0.139, "step": 382240 }, { "epoch": 2.2721733806492264, "grad_norm": 3.9484400749206543, "learning_rate": 6.637192351916183e-06, "loss": 0.149, "step": 382250 }, { "epoch": 2.2722328227258948, "grad_norm": 3.671541690826416, "learning_rate": 6.636996296900563e-06, "loss": 0.1484, "step": 382260 }, { "epoch": 2.272292264802563, "grad_norm": 5.063896656036377, "learning_rate": 6.636800239065842e-06, "loss": 0.1548, "step": 382270 }, { "epoch": 2.2723517068792316, "grad_norm": 5.349857330322266, "learning_rate": 6.636604178412353e-06, "loss": 0.1468, "step": 382280 }, { "epoch": 2.2724111489559, "grad_norm": 4.402263641357422, "learning_rate": 6.636408114940438e-06, "loss": 0.131, "step": 382290 }, { "epoch": 2.2724705910325684, "grad_norm": 5.431319236755371, "learning_rate": 6.636212048650432e-06, "loss": 0.1442, "step": 382300 }, { "epoch": 2.272530033109237, "grad_norm": 2.808595657348633, "learning_rate": 6.636015979542676e-06, "loss": 0.1434, "step": 382310 }, { "epoch": 2.2725894751859053, "grad_norm": 5.449679374694824, "learning_rate": 6.635819907617503e-06, "loss": 0.1653, "step": 382320 }, { "epoch": 2.2726489172625737, "grad_norm": 5.658459186553955, "learning_rate": 6.635623832875253e-06, "loss": 0.1468, "step": 382330 }, { "epoch": 2.2727083593392416, "grad_norm": 5.839776515960693, "learning_rate": 6.635427755316265e-06, "loss": 0.136, "step": 382340 }, { "epoch": 2.2727678014159105, "grad_norm": 4.3127264976501465, "learning_rate": 6.635231674940873e-06, "loss": 0.1596, "step": 382350 }, { "epoch": 2.2728272434925785, "grad_norm": 4.775185585021973, "learning_rate": 6.635035591749418e-06, "loss": 0.1619, "step": 382360 }, { "epoch": 2.272886685569247, "grad_norm": 4.122631072998047, "learning_rate": 6.634839505742236e-06, "loss": 0.1545, "step": 382370 }, { "epoch": 2.2729461276459153, "grad_norm": 5.578054428100586, "learning_rate": 6.6346434169196685e-06, "loss": 0.1417, "step": 382380 }, { "epoch": 2.2730055697225837, "grad_norm": 4.923769474029541, "learning_rate": 6.634447325282046e-06, "loss": 0.1503, "step": 382390 }, { "epoch": 2.273065011799252, "grad_norm": 3.76889967918396, "learning_rate": 6.6342512308297125e-06, "loss": 0.1377, "step": 382400 }, { "epoch": 2.2731244538759205, "grad_norm": 4.945401191711426, "learning_rate": 6.634055133563004e-06, "loss": 0.1553, "step": 382410 }, { "epoch": 2.273183895952589, "grad_norm": 5.624094486236572, "learning_rate": 6.633859033482255e-06, "loss": 0.1598, "step": 382420 }, { "epoch": 2.2732433380292574, "grad_norm": 3.8398633003234863, "learning_rate": 6.6336629305878075e-06, "loss": 0.1674, "step": 382430 }, { "epoch": 2.273302780105926, "grad_norm": 3.952181577682495, "learning_rate": 6.633466824879997e-06, "loss": 0.1424, "step": 382440 }, { "epoch": 2.273362222182594, "grad_norm": 4.5737199783325195, "learning_rate": 6.633270716359161e-06, "loss": 0.1472, "step": 382450 }, { "epoch": 2.2734216642592626, "grad_norm": 4.019775390625, "learning_rate": 6.63307460502564e-06, "loss": 0.1457, "step": 382460 }, { "epoch": 2.273481106335931, "grad_norm": 4.552779674530029, "learning_rate": 6.6328784908797675e-06, "loss": 0.1424, "step": 382470 }, { "epoch": 2.2735405484125994, "grad_norm": 3.372652053833008, "learning_rate": 6.632682373921884e-06, "loss": 0.1501, "step": 382480 }, { "epoch": 2.273599990489268, "grad_norm": 5.2370500564575195, "learning_rate": 6.632486254152327e-06, "loss": 0.147, "step": 382490 }, { "epoch": 2.2736594325659363, "grad_norm": 4.760511875152588, "learning_rate": 6.6322901315714346e-06, "loss": 0.1572, "step": 382500 }, { "epoch": 2.2737188746426047, "grad_norm": 5.066435813903809, "learning_rate": 6.632094006179544e-06, "loss": 0.1504, "step": 382510 }, { "epoch": 2.273778316719273, "grad_norm": 4.842928886413574, "learning_rate": 6.6318978779769905e-06, "loss": 0.1464, "step": 382520 }, { "epoch": 2.273837758795941, "grad_norm": 3.8326683044433594, "learning_rate": 6.631701746964116e-06, "loss": 0.135, "step": 382530 }, { "epoch": 2.2738972008726095, "grad_norm": 4.245838642120361, "learning_rate": 6.631505613141257e-06, "loss": 0.1436, "step": 382540 }, { "epoch": 2.273956642949278, "grad_norm": 5.120757102966309, "learning_rate": 6.631309476508748e-06, "loss": 0.1529, "step": 382550 }, { "epoch": 2.2740160850259463, "grad_norm": 6.533820152282715, "learning_rate": 6.631113337066932e-06, "loss": 0.1513, "step": 382560 }, { "epoch": 2.2740755271026147, "grad_norm": 3.5043954849243164, "learning_rate": 6.630917194816144e-06, "loss": 0.1501, "step": 382570 }, { "epoch": 2.274134969179283, "grad_norm": 4.428887367248535, "learning_rate": 6.630721049756718e-06, "loss": 0.1451, "step": 382580 }, { "epoch": 2.2741944112559516, "grad_norm": 3.7045931816101074, "learning_rate": 6.630524901889001e-06, "loss": 0.1386, "step": 382590 }, { "epoch": 2.27425385333262, "grad_norm": 4.068859100341797, "learning_rate": 6.630328751213324e-06, "loss": 0.1327, "step": 382600 }, { "epoch": 2.2743132954092884, "grad_norm": 4.398808479309082, "learning_rate": 6.630132597730025e-06, "loss": 0.1571, "step": 382610 }, { "epoch": 2.274372737485957, "grad_norm": 5.820004463195801, "learning_rate": 6.629936441439444e-06, "loss": 0.1695, "step": 382620 }, { "epoch": 2.2744321795626252, "grad_norm": 6.154043197631836, "learning_rate": 6.629740282341919e-06, "loss": 0.1452, "step": 382630 }, { "epoch": 2.2744916216392936, "grad_norm": 3.777247190475464, "learning_rate": 6.629544120437785e-06, "loss": 0.1523, "step": 382640 }, { "epoch": 2.274551063715962, "grad_norm": 3.6127235889434814, "learning_rate": 6.629347955727383e-06, "loss": 0.1511, "step": 382650 }, { "epoch": 2.2746105057926305, "grad_norm": 3.024946451187134, "learning_rate": 6.62915178821105e-06, "loss": 0.1549, "step": 382660 }, { "epoch": 2.274669947869299, "grad_norm": 4.020948886871338, "learning_rate": 6.628955617889121e-06, "loss": 0.1531, "step": 382670 }, { "epoch": 2.2747293899459673, "grad_norm": 5.164966106414795, "learning_rate": 6.628759444761937e-06, "loss": 0.1451, "step": 382680 }, { "epoch": 2.2747888320226357, "grad_norm": 4.595343112945557, "learning_rate": 6.628563268829835e-06, "loss": 0.1565, "step": 382690 }, { "epoch": 2.274848274099304, "grad_norm": 3.250419855117798, "learning_rate": 6.628367090093153e-06, "loss": 0.1282, "step": 382700 }, { "epoch": 2.2749077161759725, "grad_norm": 3.743974208831787, "learning_rate": 6.6281709085522285e-06, "loss": 0.154, "step": 382710 }, { "epoch": 2.2749671582526405, "grad_norm": 3.7711708545684814, "learning_rate": 6.6279747242074e-06, "loss": 0.1707, "step": 382720 }, { "epoch": 2.275026600329309, "grad_norm": 3.7725749015808105, "learning_rate": 6.627778537059004e-06, "loss": 0.1413, "step": 382730 }, { "epoch": 2.2750860424059773, "grad_norm": 7.015056610107422, "learning_rate": 6.627582347107379e-06, "loss": 0.1582, "step": 382740 }, { "epoch": 2.2751454844826458, "grad_norm": 4.570391654968262, "learning_rate": 6.627386154352863e-06, "loss": 0.1591, "step": 382750 }, { "epoch": 2.275204926559314, "grad_norm": 4.378243446350098, "learning_rate": 6.627189958795794e-06, "loss": 0.1543, "step": 382760 }, { "epoch": 2.2752643686359826, "grad_norm": 4.770028114318848, "learning_rate": 6.62699376043651e-06, "loss": 0.1536, "step": 382770 }, { "epoch": 2.275323810712651, "grad_norm": 3.6315479278564453, "learning_rate": 6.626797559275348e-06, "loss": 0.1595, "step": 382780 }, { "epoch": 2.2753832527893194, "grad_norm": 4.2108306884765625, "learning_rate": 6.626601355312648e-06, "loss": 0.1366, "step": 382790 }, { "epoch": 2.275442694865988, "grad_norm": 4.5474066734313965, "learning_rate": 6.626405148548745e-06, "loss": 0.1398, "step": 382800 }, { "epoch": 2.2755021369426562, "grad_norm": 4.456262588500977, "learning_rate": 6.626208938983978e-06, "loss": 0.1506, "step": 382810 }, { "epoch": 2.2755615790193247, "grad_norm": 6.373566627502441, "learning_rate": 6.626012726618686e-06, "loss": 0.1521, "step": 382820 }, { "epoch": 2.275621021095993, "grad_norm": 5.46543025970459, "learning_rate": 6.625816511453205e-06, "loss": 0.1553, "step": 382830 }, { "epoch": 2.2756804631726615, "grad_norm": 6.606616497039795, "learning_rate": 6.625620293487875e-06, "loss": 0.1718, "step": 382840 }, { "epoch": 2.27573990524933, "grad_norm": 4.8837714195251465, "learning_rate": 6.6254240727230335e-06, "loss": 0.1425, "step": 382850 }, { "epoch": 2.2757993473259983, "grad_norm": 5.2738213539123535, "learning_rate": 6.625227849159017e-06, "loss": 0.1443, "step": 382860 }, { "epoch": 2.2758587894026667, "grad_norm": 6.1254096031188965, "learning_rate": 6.625031622796163e-06, "loss": 0.1297, "step": 382870 }, { "epoch": 2.275918231479335, "grad_norm": 3.4442315101623535, "learning_rate": 6.624835393634813e-06, "loss": 0.1412, "step": 382880 }, { "epoch": 2.275977673556003, "grad_norm": 4.404922008514404, "learning_rate": 6.624639161675301e-06, "loss": 0.1521, "step": 382890 }, { "epoch": 2.276037115632672, "grad_norm": 3.929152488708496, "learning_rate": 6.6244429269179666e-06, "loss": 0.1596, "step": 382900 }, { "epoch": 2.27609655770934, "grad_norm": 4.398121356964111, "learning_rate": 6.624246689363147e-06, "loss": 0.1476, "step": 382910 }, { "epoch": 2.2761559997860084, "grad_norm": 5.324554920196533, "learning_rate": 6.624050449011183e-06, "loss": 0.1333, "step": 382920 }, { "epoch": 2.2762154418626768, "grad_norm": 4.468676567077637, "learning_rate": 6.62385420586241e-06, "loss": 0.1619, "step": 382930 }, { "epoch": 2.276274883939345, "grad_norm": 5.078012466430664, "learning_rate": 6.623657959917165e-06, "loss": 0.1611, "step": 382940 }, { "epoch": 2.2763343260160136, "grad_norm": 5.394136428833008, "learning_rate": 6.623461711175788e-06, "loss": 0.1509, "step": 382950 }, { "epoch": 2.276393768092682, "grad_norm": 5.213799953460693, "learning_rate": 6.623265459638616e-06, "loss": 0.1727, "step": 382960 }, { "epoch": 2.2764532101693504, "grad_norm": 4.4910736083984375, "learning_rate": 6.623069205305987e-06, "loss": 0.1545, "step": 382970 }, { "epoch": 2.276512652246019, "grad_norm": 2.4574055671691895, "learning_rate": 6.62287294817824e-06, "loss": 0.1379, "step": 382980 }, { "epoch": 2.2765720943226873, "grad_norm": 4.098728179931641, "learning_rate": 6.622676688255711e-06, "loss": 0.1542, "step": 382990 }, { "epoch": 2.2766315363993557, "grad_norm": 3.832085609436035, "learning_rate": 6.62248042553874e-06, "loss": 0.1512, "step": 383000 }, { "epoch": 2.276690978476024, "grad_norm": 4.248053550720215, "learning_rate": 6.6222841600276635e-06, "loss": 0.1478, "step": 383010 }, { "epoch": 2.2767504205526925, "grad_norm": 4.526878833770752, "learning_rate": 6.62208789172282e-06, "loss": 0.1584, "step": 383020 }, { "epoch": 2.276809862629361, "grad_norm": 6.314445972442627, "learning_rate": 6.621891620624548e-06, "loss": 0.1624, "step": 383030 }, { "epoch": 2.2768693047060293, "grad_norm": 4.459655284881592, "learning_rate": 6.6216953467331844e-06, "loss": 0.1465, "step": 383040 }, { "epoch": 2.2769287467826977, "grad_norm": 5.751693248748779, "learning_rate": 6.621499070049069e-06, "loss": 0.1675, "step": 383050 }, { "epoch": 2.276988188859366, "grad_norm": 4.255797863006592, "learning_rate": 6.621302790572539e-06, "loss": 0.1512, "step": 383060 }, { "epoch": 2.2770476309360346, "grad_norm": 3.3625071048736572, "learning_rate": 6.62110650830393e-06, "loss": 0.1511, "step": 383070 }, { "epoch": 2.2771070730127025, "grad_norm": 3.6548938751220703, "learning_rate": 6.620910223243584e-06, "loss": 0.1497, "step": 383080 }, { "epoch": 2.2771665150893714, "grad_norm": 4.6271538734436035, "learning_rate": 6.6207139353918385e-06, "loss": 0.1537, "step": 383090 }, { "epoch": 2.2772259571660394, "grad_norm": 3.6729772090911865, "learning_rate": 6.6205176447490274e-06, "loss": 0.119, "step": 383100 }, { "epoch": 2.277285399242708, "grad_norm": 4.372413635253906, "learning_rate": 6.620321351315493e-06, "loss": 0.1368, "step": 383110 }, { "epoch": 2.277344841319376, "grad_norm": 3.8981406688690186, "learning_rate": 6.620125055091572e-06, "loss": 0.1489, "step": 383120 }, { "epoch": 2.2774042833960446, "grad_norm": 3.6705703735351562, "learning_rate": 6.6199287560776006e-06, "loss": 0.1534, "step": 383130 }, { "epoch": 2.277463725472713, "grad_norm": 4.908059120178223, "learning_rate": 6.619732454273919e-06, "loss": 0.1727, "step": 383140 }, { "epoch": 2.2775231675493814, "grad_norm": 4.427804470062256, "learning_rate": 6.619536149680868e-06, "loss": 0.1443, "step": 383150 }, { "epoch": 2.27758260962605, "grad_norm": 4.3615617752075195, "learning_rate": 6.61933984229878e-06, "loss": 0.1514, "step": 383160 }, { "epoch": 2.2776420517027183, "grad_norm": 4.104883670806885, "learning_rate": 6.619143532127994e-06, "loss": 0.1443, "step": 383170 }, { "epoch": 2.2777014937793867, "grad_norm": 2.911731243133545, "learning_rate": 6.618947219168852e-06, "loss": 0.1348, "step": 383180 }, { "epoch": 2.277760935856055, "grad_norm": 4.554026126861572, "learning_rate": 6.61875090342169e-06, "loss": 0.138, "step": 383190 }, { "epoch": 2.2778203779327235, "grad_norm": 3.7411630153656006, "learning_rate": 6.618554584886845e-06, "loss": 0.1294, "step": 383200 }, { "epoch": 2.277879820009392, "grad_norm": 5.622870922088623, "learning_rate": 6.618358263564656e-06, "loss": 0.1358, "step": 383210 }, { "epoch": 2.2779392620860603, "grad_norm": 3.015343189239502, "learning_rate": 6.618161939455461e-06, "loss": 0.1442, "step": 383220 }, { "epoch": 2.2779987041627288, "grad_norm": 5.226345539093018, "learning_rate": 6.617965612559597e-06, "loss": 0.1409, "step": 383230 }, { "epoch": 2.278058146239397, "grad_norm": 3.5151312351226807, "learning_rate": 6.617769282877404e-06, "loss": 0.1499, "step": 383240 }, { "epoch": 2.2781175883160656, "grad_norm": 3.962923049926758, "learning_rate": 6.617572950409219e-06, "loss": 0.1507, "step": 383250 }, { "epoch": 2.278177030392734, "grad_norm": 4.5157060623168945, "learning_rate": 6.6173766151553805e-06, "loss": 0.1395, "step": 383260 }, { "epoch": 2.278236472469402, "grad_norm": 4.425089359283447, "learning_rate": 6.617180277116228e-06, "loss": 0.1399, "step": 383270 }, { "epoch": 2.2782959145460704, "grad_norm": 4.776767730712891, "learning_rate": 6.6169839362920964e-06, "loss": 0.1404, "step": 383280 }, { "epoch": 2.278355356622739, "grad_norm": 4.973924160003662, "learning_rate": 6.616787592683325e-06, "loss": 0.1447, "step": 383290 }, { "epoch": 2.278414798699407, "grad_norm": 4.5590643882751465, "learning_rate": 6.616591246290254e-06, "loss": 0.1428, "step": 383300 }, { "epoch": 2.2784742407760756, "grad_norm": 5.673576354980469, "learning_rate": 6.61639489711322e-06, "loss": 0.1505, "step": 383310 }, { "epoch": 2.278533682852744, "grad_norm": 4.625591278076172, "learning_rate": 6.61619854515256e-06, "loss": 0.1492, "step": 383320 }, { "epoch": 2.2785931249294125, "grad_norm": 6.071985244750977, "learning_rate": 6.616002190408615e-06, "loss": 0.1419, "step": 383330 }, { "epoch": 2.278652567006081, "grad_norm": 4.608816623687744, "learning_rate": 6.61580583288172e-06, "loss": 0.1321, "step": 383340 }, { "epoch": 2.2787120090827493, "grad_norm": 4.888574123382568, "learning_rate": 6.615609472572213e-06, "loss": 0.1551, "step": 383350 }, { "epoch": 2.2787714511594177, "grad_norm": 4.9617438316345215, "learning_rate": 6.615413109480436e-06, "loss": 0.1504, "step": 383360 }, { "epoch": 2.278830893236086, "grad_norm": 4.098506927490234, "learning_rate": 6.615216743606725e-06, "loss": 0.1298, "step": 383370 }, { "epoch": 2.2788903353127545, "grad_norm": 2.7925853729248047, "learning_rate": 6.615020374951418e-06, "loss": 0.1585, "step": 383380 }, { "epoch": 2.278949777389423, "grad_norm": 4.541281700134277, "learning_rate": 6.61482400351485e-06, "loss": 0.134, "step": 383390 }, { "epoch": 2.2790092194660914, "grad_norm": 3.378909111022949, "learning_rate": 6.6146276292973665e-06, "loss": 0.1357, "step": 383400 }, { "epoch": 2.2790686615427598, "grad_norm": 4.271066188812256, "learning_rate": 6.614431252299301e-06, "loss": 0.1396, "step": 383410 }, { "epoch": 2.279128103619428, "grad_norm": 4.742268085479736, "learning_rate": 6.61423487252099e-06, "loss": 0.1547, "step": 383420 }, { "epoch": 2.2791875456960966, "grad_norm": 4.5282816886901855, "learning_rate": 6.614038489962775e-06, "loss": 0.1485, "step": 383430 }, { "epoch": 2.279246987772765, "grad_norm": 5.030736446380615, "learning_rate": 6.613842104624995e-06, "loss": 0.154, "step": 383440 }, { "epoch": 2.2793064298494334, "grad_norm": 4.510653495788574, "learning_rate": 6.613645716507983e-06, "loss": 0.1531, "step": 383450 }, { "epoch": 2.2793658719261014, "grad_norm": 4.144858360290527, "learning_rate": 6.613449325612082e-06, "loss": 0.1356, "step": 383460 }, { "epoch": 2.27942531400277, "grad_norm": 2.981504201889038, "learning_rate": 6.613252931937629e-06, "loss": 0.1145, "step": 383470 }, { "epoch": 2.2794847560794382, "grad_norm": 3.470771074295044, "learning_rate": 6.613056535484963e-06, "loss": 0.1334, "step": 383480 }, { "epoch": 2.2795441981561066, "grad_norm": 3.64621639251709, "learning_rate": 6.61286013625442e-06, "loss": 0.1424, "step": 383490 }, { "epoch": 2.279603640232775, "grad_norm": 4.1725616455078125, "learning_rate": 6.612663734246339e-06, "loss": 0.1383, "step": 383500 }, { "epoch": 2.2796630823094435, "grad_norm": 4.060329914093018, "learning_rate": 6.61246732946106e-06, "loss": 0.141, "step": 383510 }, { "epoch": 2.279722524386112, "grad_norm": 3.6647496223449707, "learning_rate": 6.612270921898918e-06, "loss": 0.1504, "step": 383520 }, { "epoch": 2.2797819664627803, "grad_norm": 4.9765849113464355, "learning_rate": 6.612074511560255e-06, "loss": 0.149, "step": 383530 }, { "epoch": 2.2798414085394487, "grad_norm": 4.050083637237549, "learning_rate": 6.6118780984454065e-06, "loss": 0.1532, "step": 383540 }, { "epoch": 2.279900850616117, "grad_norm": 5.232734680175781, "learning_rate": 6.611681682554712e-06, "loss": 0.1593, "step": 383550 }, { "epoch": 2.2799602926927856, "grad_norm": 4.1690850257873535, "learning_rate": 6.6114852638885085e-06, "loss": 0.1378, "step": 383560 }, { "epoch": 2.280019734769454, "grad_norm": 3.4550769329071045, "learning_rate": 6.611288842447135e-06, "loss": 0.1583, "step": 383570 }, { "epoch": 2.2800791768461224, "grad_norm": 5.226698398590088, "learning_rate": 6.611092418230931e-06, "loss": 0.1761, "step": 383580 }, { "epoch": 2.280138618922791, "grad_norm": 5.131811618804932, "learning_rate": 6.610895991240231e-06, "loss": 0.1736, "step": 383590 }, { "epoch": 2.280198060999459, "grad_norm": 4.407598972320557, "learning_rate": 6.610699561475379e-06, "loss": 0.1414, "step": 383600 }, { "epoch": 2.2802575030761276, "grad_norm": 4.475279808044434, "learning_rate": 6.610503128936709e-06, "loss": 0.1384, "step": 383610 }, { "epoch": 2.280316945152796, "grad_norm": 5.637275695800781, "learning_rate": 6.610306693624561e-06, "loss": 0.1494, "step": 383620 }, { "epoch": 2.280376387229464, "grad_norm": 4.106534957885742, "learning_rate": 6.610110255539273e-06, "loss": 0.137, "step": 383630 }, { "epoch": 2.280435829306133, "grad_norm": 3.8025126457214355, "learning_rate": 6.609913814681182e-06, "loss": 0.1487, "step": 383640 }, { "epoch": 2.280495271382801, "grad_norm": 4.210580348968506, "learning_rate": 6.609717371050627e-06, "loss": 0.1381, "step": 383650 }, { "epoch": 2.2805547134594693, "grad_norm": 4.16996955871582, "learning_rate": 6.609520924647947e-06, "loss": 0.1465, "step": 383660 }, { "epoch": 2.2806141555361377, "grad_norm": 4.730727672576904, "learning_rate": 6.609324475473481e-06, "loss": 0.1547, "step": 383670 }, { "epoch": 2.280673597612806, "grad_norm": 4.482288360595703, "learning_rate": 6.609128023527565e-06, "loss": 0.1453, "step": 383680 }, { "epoch": 2.2807330396894745, "grad_norm": 4.083622932434082, "learning_rate": 6.608931568810537e-06, "loss": 0.1237, "step": 383690 }, { "epoch": 2.280792481766143, "grad_norm": 4.820708751678467, "learning_rate": 6.608735111322739e-06, "loss": 0.1537, "step": 383700 }, { "epoch": 2.2808519238428113, "grad_norm": 4.109533786773682, "learning_rate": 6.608538651064509e-06, "loss": 0.1462, "step": 383710 }, { "epoch": 2.2809113659194797, "grad_norm": 3.9117722511291504, "learning_rate": 6.608342188036179e-06, "loss": 0.1542, "step": 383720 }, { "epoch": 2.280970807996148, "grad_norm": 4.906520366668701, "learning_rate": 6.608145722238095e-06, "loss": 0.157, "step": 383730 }, { "epoch": 2.2810302500728166, "grad_norm": 5.531613349914551, "learning_rate": 6.607949253670592e-06, "loss": 0.1557, "step": 383740 }, { "epoch": 2.281089692149485, "grad_norm": 6.004800796508789, "learning_rate": 6.6077527823340085e-06, "loss": 0.1644, "step": 383750 }, { "epoch": 2.2811491342261534, "grad_norm": 3.735605001449585, "learning_rate": 6.607556308228682e-06, "loss": 0.142, "step": 383760 }, { "epoch": 2.281208576302822, "grad_norm": 5.057399272918701, "learning_rate": 6.607359831354953e-06, "loss": 0.1443, "step": 383770 }, { "epoch": 2.2812680183794902, "grad_norm": 4.336805820465088, "learning_rate": 6.6071633517131574e-06, "loss": 0.1731, "step": 383780 }, { "epoch": 2.2813274604561586, "grad_norm": 5.958499431610107, "learning_rate": 6.606966869303634e-06, "loss": 0.1445, "step": 383790 }, { "epoch": 2.281386902532827, "grad_norm": 4.385592460632324, "learning_rate": 6.606770384126724e-06, "loss": 0.1375, "step": 383800 }, { "epoch": 2.2814463446094955, "grad_norm": 4.203357219696045, "learning_rate": 6.6065738961827615e-06, "loss": 0.1493, "step": 383810 }, { "epoch": 2.2815057866861634, "grad_norm": 4.562244415283203, "learning_rate": 6.606377405472089e-06, "loss": 0.141, "step": 383820 }, { "epoch": 2.2815652287628323, "grad_norm": 3.73728609085083, "learning_rate": 6.606180911995041e-06, "loss": 0.1315, "step": 383830 }, { "epoch": 2.2816246708395003, "grad_norm": 3.360560655593872, "learning_rate": 6.60598441575196e-06, "loss": 0.1538, "step": 383840 }, { "epoch": 2.2816841129161687, "grad_norm": 4.0407867431640625, "learning_rate": 6.60578791674318e-06, "loss": 0.1555, "step": 383850 }, { "epoch": 2.281743554992837, "grad_norm": 4.77012300491333, "learning_rate": 6.605591414969043e-06, "loss": 0.1508, "step": 383860 }, { "epoch": 2.2818029970695055, "grad_norm": 6.010210037231445, "learning_rate": 6.605394910429888e-06, "loss": 0.1497, "step": 383870 }, { "epoch": 2.281862439146174, "grad_norm": 4.466095924377441, "learning_rate": 6.605198403126047e-06, "loss": 0.1217, "step": 383880 }, { "epoch": 2.2819218812228423, "grad_norm": 6.239874839782715, "learning_rate": 6.605001893057866e-06, "loss": 0.1295, "step": 383890 }, { "epoch": 2.2819813232995108, "grad_norm": 3.819722890853882, "learning_rate": 6.604805380225679e-06, "loss": 0.1532, "step": 383900 }, { "epoch": 2.282040765376179, "grad_norm": 5.446387767791748, "learning_rate": 6.604608864629824e-06, "loss": 0.1398, "step": 383910 }, { "epoch": 2.2821002074528476, "grad_norm": 2.9275381565093994, "learning_rate": 6.604412346270644e-06, "loss": 0.147, "step": 383920 }, { "epoch": 2.282159649529516, "grad_norm": 3.768562078475952, "learning_rate": 6.604215825148474e-06, "loss": 0.1413, "step": 383930 }, { "epoch": 2.2822190916061844, "grad_norm": 3.0703353881835938, "learning_rate": 6.604019301263652e-06, "loss": 0.1453, "step": 383940 }, { "epoch": 2.282278533682853, "grad_norm": 5.077914714813232, "learning_rate": 6.603822774616518e-06, "loss": 0.1367, "step": 383950 }, { "epoch": 2.2823379757595212, "grad_norm": 3.494431734085083, "learning_rate": 6.60362624520741e-06, "loss": 0.1452, "step": 383960 }, { "epoch": 2.2823974178361897, "grad_norm": 3.1754343509674072, "learning_rate": 6.603429713036665e-06, "loss": 0.143, "step": 383970 }, { "epoch": 2.282456859912858, "grad_norm": 4.212712287902832, "learning_rate": 6.603233178104624e-06, "loss": 0.1359, "step": 383980 }, { "epoch": 2.2825163019895265, "grad_norm": 5.049841403961182, "learning_rate": 6.603036640411624e-06, "loss": 0.148, "step": 383990 }, { "epoch": 2.282575744066195, "grad_norm": 3.4901630878448486, "learning_rate": 6.602840099958003e-06, "loss": 0.1519, "step": 384000 }, { "epoch": 2.282635186142863, "grad_norm": 4.078427791595459, "learning_rate": 6.602643556744101e-06, "loss": 0.1543, "step": 384010 }, { "epoch": 2.2826946282195313, "grad_norm": 4.203804969787598, "learning_rate": 6.602447010770254e-06, "loss": 0.1363, "step": 384020 }, { "epoch": 2.2827540702961997, "grad_norm": 4.241886615753174, "learning_rate": 6.602250462036805e-06, "loss": 0.1257, "step": 384030 }, { "epoch": 2.282813512372868, "grad_norm": 5.2702717781066895, "learning_rate": 6.602053910544086e-06, "loss": 0.1744, "step": 384040 }, { "epoch": 2.2828729544495365, "grad_norm": 4.270732402801514, "learning_rate": 6.601857356292442e-06, "loss": 0.1636, "step": 384050 }, { "epoch": 2.282932396526205, "grad_norm": 5.094958782196045, "learning_rate": 6.6016607992822064e-06, "loss": 0.129, "step": 384060 }, { "epoch": 2.2829918386028734, "grad_norm": 4.581326484680176, "learning_rate": 6.601464239513721e-06, "loss": 0.1437, "step": 384070 }, { "epoch": 2.2830512806795418, "grad_norm": 3.855013847351074, "learning_rate": 6.601267676987323e-06, "loss": 0.1439, "step": 384080 }, { "epoch": 2.28311072275621, "grad_norm": 4.361852645874023, "learning_rate": 6.601071111703351e-06, "loss": 0.1385, "step": 384090 }, { "epoch": 2.2831701648328786, "grad_norm": 5.736958026885986, "learning_rate": 6.600874543662142e-06, "loss": 0.1769, "step": 384100 }, { "epoch": 2.283229606909547, "grad_norm": 3.7637064456939697, "learning_rate": 6.600677972864038e-06, "loss": 0.1249, "step": 384110 }, { "epoch": 2.2832890489862154, "grad_norm": 4.849132061004639, "learning_rate": 6.600481399309374e-06, "loss": 0.1637, "step": 384120 }, { "epoch": 2.283348491062884, "grad_norm": 3.5548346042633057, "learning_rate": 6.60028482299849e-06, "loss": 0.1677, "step": 384130 }, { "epoch": 2.2834079331395523, "grad_norm": 3.5287959575653076, "learning_rate": 6.600088243931726e-06, "loss": 0.1485, "step": 384140 }, { "epoch": 2.2834673752162207, "grad_norm": 4.917255878448486, "learning_rate": 6.599891662109419e-06, "loss": 0.1501, "step": 384150 }, { "epoch": 2.283526817292889, "grad_norm": 3.600935697555542, "learning_rate": 6.5996950775319065e-06, "loss": 0.1371, "step": 384160 }, { "epoch": 2.2835862593695575, "grad_norm": 4.7700653076171875, "learning_rate": 6.59949849019953e-06, "loss": 0.152, "step": 384170 }, { "epoch": 2.283645701446226, "grad_norm": 4.082320213317871, "learning_rate": 6.599301900112624e-06, "loss": 0.1376, "step": 384180 }, { "epoch": 2.2837051435228943, "grad_norm": 2.84237003326416, "learning_rate": 6.599105307271532e-06, "loss": 0.1448, "step": 384190 }, { "epoch": 2.2837645855995623, "grad_norm": 4.630069255828857, "learning_rate": 6.5989087116765875e-06, "loss": 0.1466, "step": 384200 }, { "epoch": 2.2838240276762307, "grad_norm": 5.437228202819824, "learning_rate": 6.5987121133281315e-06, "loss": 0.1505, "step": 384210 }, { "epoch": 2.283883469752899, "grad_norm": 4.918734550476074, "learning_rate": 6.598515512226504e-06, "loss": 0.1445, "step": 384220 }, { "epoch": 2.2839429118295675, "grad_norm": 5.498078346252441, "learning_rate": 6.598318908372041e-06, "loss": 0.1503, "step": 384230 }, { "epoch": 2.284002353906236, "grad_norm": 5.034093379974365, "learning_rate": 6.5981223017650815e-06, "loss": 0.1651, "step": 384240 }, { "epoch": 2.2840617959829044, "grad_norm": 4.683613300323486, "learning_rate": 6.597925692405966e-06, "loss": 0.1417, "step": 384250 }, { "epoch": 2.284121238059573, "grad_norm": 3.576155424118042, "learning_rate": 6.5977290802950326e-06, "loss": 0.1386, "step": 384260 }, { "epoch": 2.284180680136241, "grad_norm": 3.5982747077941895, "learning_rate": 6.5975324654326164e-06, "loss": 0.1322, "step": 384270 }, { "epoch": 2.2842401222129096, "grad_norm": 5.340658664703369, "learning_rate": 6.597335847819061e-06, "loss": 0.1598, "step": 384280 }, { "epoch": 2.284299564289578, "grad_norm": 3.7401511669158936, "learning_rate": 6.597139227454702e-06, "loss": 0.1262, "step": 384290 }, { "epoch": 2.2843590063662464, "grad_norm": 4.998087406158447, "learning_rate": 6.596942604339877e-06, "loss": 0.1468, "step": 384300 }, { "epoch": 2.284418448442915, "grad_norm": 4.21402645111084, "learning_rate": 6.596745978474928e-06, "loss": 0.1618, "step": 384310 }, { "epoch": 2.2844778905195833, "grad_norm": 3.3973066806793213, "learning_rate": 6.596549349860193e-06, "loss": 0.1359, "step": 384320 }, { "epoch": 2.2845373325962517, "grad_norm": 6.1727070808410645, "learning_rate": 6.596352718496007e-06, "loss": 0.1539, "step": 384330 }, { "epoch": 2.28459677467292, "grad_norm": 3.5600504875183105, "learning_rate": 6.596156084382712e-06, "loss": 0.1448, "step": 384340 }, { "epoch": 2.2846562167495885, "grad_norm": 4.213987350463867, "learning_rate": 6.595959447520647e-06, "loss": 0.1675, "step": 384350 }, { "epoch": 2.284715658826257, "grad_norm": 5.683448314666748, "learning_rate": 6.595762807910149e-06, "loss": 0.1452, "step": 384360 }, { "epoch": 2.284775100902925, "grad_norm": 3.925992250442505, "learning_rate": 6.595566165551556e-06, "loss": 0.1522, "step": 384370 }, { "epoch": 2.2848345429795938, "grad_norm": 5.4995527267456055, "learning_rate": 6.595369520445208e-06, "loss": 0.1591, "step": 384380 }, { "epoch": 2.2848939850562617, "grad_norm": 4.072530746459961, "learning_rate": 6.595172872591444e-06, "loss": 0.1528, "step": 384390 }, { "epoch": 2.28495342713293, "grad_norm": 3.435629367828369, "learning_rate": 6.594976221990601e-06, "loss": 0.1527, "step": 384400 }, { "epoch": 2.2850128692095986, "grad_norm": 3.6278011798858643, "learning_rate": 6.59477956864302e-06, "loss": 0.1607, "step": 384410 }, { "epoch": 2.285072311286267, "grad_norm": 4.278061389923096, "learning_rate": 6.594582912549038e-06, "loss": 0.1576, "step": 384420 }, { "epoch": 2.2851317533629354, "grad_norm": 4.53501558303833, "learning_rate": 6.594386253708993e-06, "loss": 0.142, "step": 384430 }, { "epoch": 2.285191195439604, "grad_norm": 5.1258931159973145, "learning_rate": 6.594189592123225e-06, "loss": 0.1483, "step": 384440 }, { "epoch": 2.285250637516272, "grad_norm": 5.00605583190918, "learning_rate": 6.5939929277920725e-06, "loss": 0.1417, "step": 384450 }, { "epoch": 2.2853100795929406, "grad_norm": 2.626750946044922, "learning_rate": 6.593796260715873e-06, "loss": 0.1453, "step": 384460 }, { "epoch": 2.285369521669609, "grad_norm": 3.809570550918579, "learning_rate": 6.593599590894968e-06, "loss": 0.1675, "step": 384470 }, { "epoch": 2.2854289637462775, "grad_norm": 3.5161080360412598, "learning_rate": 6.593402918329693e-06, "loss": 0.1452, "step": 384480 }, { "epoch": 2.285488405822946, "grad_norm": 3.9286396503448486, "learning_rate": 6.593206243020388e-06, "loss": 0.1556, "step": 384490 }, { "epoch": 2.2855478478996143, "grad_norm": 3.685317039489746, "learning_rate": 6.593009564967393e-06, "loss": 0.1265, "step": 384500 }, { "epoch": 2.2856072899762827, "grad_norm": 2.901674270629883, "learning_rate": 6.592812884171045e-06, "loss": 0.15, "step": 384510 }, { "epoch": 2.285666732052951, "grad_norm": 5.237629413604736, "learning_rate": 6.592616200631683e-06, "loss": 0.1576, "step": 384520 }, { "epoch": 2.2857261741296195, "grad_norm": 4.03216028213501, "learning_rate": 6.592419514349645e-06, "loss": 0.1204, "step": 384530 }, { "epoch": 2.285785616206288, "grad_norm": 4.761875152587891, "learning_rate": 6.592222825325272e-06, "loss": 0.1541, "step": 384540 }, { "epoch": 2.2858450582829564, "grad_norm": 5.419618129730225, "learning_rate": 6.592026133558901e-06, "loss": 0.1543, "step": 384550 }, { "epoch": 2.2859045003596243, "grad_norm": 3.190406322479248, "learning_rate": 6.591829439050869e-06, "loss": 0.1555, "step": 384560 }, { "epoch": 2.285963942436293, "grad_norm": 3.8618125915527344, "learning_rate": 6.591632741801519e-06, "loss": 0.1473, "step": 384570 }, { "epoch": 2.286023384512961, "grad_norm": 4.399356365203857, "learning_rate": 6.591436041811188e-06, "loss": 0.1398, "step": 384580 }, { "epoch": 2.2860828265896296, "grad_norm": 3.707448959350586, "learning_rate": 6.591239339080212e-06, "loss": 0.1362, "step": 384590 }, { "epoch": 2.286142268666298, "grad_norm": 4.09210729598999, "learning_rate": 6.591042633608934e-06, "loss": 0.1307, "step": 384600 }, { "epoch": 2.2862017107429664, "grad_norm": 2.9824461936950684, "learning_rate": 6.59084592539769e-06, "loss": 0.1293, "step": 384610 }, { "epoch": 2.286261152819635, "grad_norm": 3.3784468173980713, "learning_rate": 6.590649214446818e-06, "loss": 0.1427, "step": 384620 }, { "epoch": 2.2863205948963032, "grad_norm": 4.036530017852783, "learning_rate": 6.590452500756661e-06, "loss": 0.1669, "step": 384630 }, { "epoch": 2.2863800369729717, "grad_norm": 4.58482551574707, "learning_rate": 6.5902557843275535e-06, "loss": 0.1613, "step": 384640 }, { "epoch": 2.28643947904964, "grad_norm": 3.5917842388153076, "learning_rate": 6.590059065159836e-06, "loss": 0.1362, "step": 384650 }, { "epoch": 2.2864989211263085, "grad_norm": 5.147426128387451, "learning_rate": 6.589862343253848e-06, "loss": 0.1625, "step": 384660 }, { "epoch": 2.286558363202977, "grad_norm": 4.788674354553223, "learning_rate": 6.589665618609925e-06, "loss": 0.1269, "step": 384670 }, { "epoch": 2.2866178052796453, "grad_norm": 4.523647308349609, "learning_rate": 6.58946889122841e-06, "loss": 0.128, "step": 384680 }, { "epoch": 2.2866772473563137, "grad_norm": 4.550589084625244, "learning_rate": 6.589272161109639e-06, "loss": 0.1418, "step": 384690 }, { "epoch": 2.286736689432982, "grad_norm": 4.056159973144531, "learning_rate": 6.589075428253953e-06, "loss": 0.146, "step": 384700 }, { "epoch": 2.2867961315096506, "grad_norm": 3.5407814979553223, "learning_rate": 6.5888786926616885e-06, "loss": 0.1405, "step": 384710 }, { "epoch": 2.286855573586319, "grad_norm": 4.079658031463623, "learning_rate": 6.588681954333185e-06, "loss": 0.1522, "step": 384720 }, { "epoch": 2.2869150156629874, "grad_norm": 4.009207248687744, "learning_rate": 6.588485213268782e-06, "loss": 0.1471, "step": 384730 }, { "epoch": 2.286974457739656, "grad_norm": 3.810678243637085, "learning_rate": 6.588288469468819e-06, "loss": 0.1308, "step": 384740 }, { "epoch": 2.2870338998163238, "grad_norm": 4.762324333190918, "learning_rate": 6.588091722933632e-06, "loss": 0.1582, "step": 384750 }, { "epoch": 2.287093341892992, "grad_norm": 4.30494499206543, "learning_rate": 6.5878949736635634e-06, "loss": 0.1398, "step": 384760 }, { "epoch": 2.2871527839696606, "grad_norm": 4.340300559997559, "learning_rate": 6.587698221658949e-06, "loss": 0.1399, "step": 384770 }, { "epoch": 2.287212226046329, "grad_norm": 5.432977676391602, "learning_rate": 6.5875014669201286e-06, "loss": 0.1486, "step": 384780 }, { "epoch": 2.2872716681229974, "grad_norm": 4.976079940795898, "learning_rate": 6.5873047094474405e-06, "loss": 0.1556, "step": 384790 }, { "epoch": 2.287331110199666, "grad_norm": 5.7821526527404785, "learning_rate": 6.587107949241226e-06, "loss": 0.1492, "step": 384800 }, { "epoch": 2.2873905522763343, "grad_norm": 4.451919078826904, "learning_rate": 6.586911186301822e-06, "loss": 0.1654, "step": 384810 }, { "epoch": 2.2874499943530027, "grad_norm": 4.154632568359375, "learning_rate": 6.586714420629568e-06, "loss": 0.1472, "step": 384820 }, { "epoch": 2.287509436429671, "grad_norm": 4.766653060913086, "learning_rate": 6.5865176522248005e-06, "loss": 0.1501, "step": 384830 }, { "epoch": 2.2875688785063395, "grad_norm": 4.940423011779785, "learning_rate": 6.586320881087862e-06, "loss": 0.1513, "step": 384840 }, { "epoch": 2.287628320583008, "grad_norm": 5.488308906555176, "learning_rate": 6.58612410721909e-06, "loss": 0.1564, "step": 384850 }, { "epoch": 2.2876877626596763, "grad_norm": 4.723276615142822, "learning_rate": 6.585927330618822e-06, "loss": 0.1451, "step": 384860 }, { "epoch": 2.2877472047363447, "grad_norm": 6.072826862335205, "learning_rate": 6.585730551287398e-06, "loss": 0.1558, "step": 384870 }, { "epoch": 2.287806646813013, "grad_norm": 3.6484997272491455, "learning_rate": 6.5855337692251565e-06, "loss": 0.1557, "step": 384880 }, { "epoch": 2.2878660888896816, "grad_norm": 4.5037431716918945, "learning_rate": 6.5853369844324355e-06, "loss": 0.1449, "step": 384890 }, { "epoch": 2.28792553096635, "grad_norm": 4.095650672912598, "learning_rate": 6.585140196909577e-06, "loss": 0.1372, "step": 384900 }, { "epoch": 2.2879849730430184, "grad_norm": 5.113358020782471, "learning_rate": 6.5849434066569185e-06, "loss": 0.1431, "step": 384910 }, { "epoch": 2.288044415119687, "grad_norm": 3.3273494243621826, "learning_rate": 6.5847466136747975e-06, "loss": 0.1465, "step": 384920 }, { "epoch": 2.2881038571963552, "grad_norm": 3.6712450981140137, "learning_rate": 6.584549817963553e-06, "loss": 0.1434, "step": 384930 }, { "epoch": 2.288163299273023, "grad_norm": 2.7796506881713867, "learning_rate": 6.5843530195235264e-06, "loss": 0.1323, "step": 384940 }, { "epoch": 2.2882227413496916, "grad_norm": 4.399876594543457, "learning_rate": 6.584156218355053e-06, "loss": 0.1639, "step": 384950 }, { "epoch": 2.28828218342636, "grad_norm": 3.3261327743530273, "learning_rate": 6.583959414458474e-06, "loss": 0.1502, "step": 384960 }, { "epoch": 2.2883416255030284, "grad_norm": 5.089023113250732, "learning_rate": 6.58376260783413e-06, "loss": 0.15, "step": 384970 }, { "epoch": 2.288401067579697, "grad_norm": 3.4949042797088623, "learning_rate": 6.5835657984823545e-06, "loss": 0.139, "step": 384980 }, { "epoch": 2.2884605096563653, "grad_norm": 3.7619359493255615, "learning_rate": 6.583368986403492e-06, "loss": 0.1699, "step": 384990 }, { "epoch": 2.2885199517330337, "grad_norm": 4.172598361968994, "learning_rate": 6.583172171597878e-06, "loss": 0.1272, "step": 385000 }, { "epoch": 2.288579393809702, "grad_norm": 3.6610565185546875, "learning_rate": 6.582975354065852e-06, "loss": 0.1468, "step": 385010 }, { "epoch": 2.2886388358863705, "grad_norm": 2.212697744369507, "learning_rate": 6.582778533807755e-06, "loss": 0.1369, "step": 385020 }, { "epoch": 2.288698277963039, "grad_norm": 3.4276950359344482, "learning_rate": 6.582581710823925e-06, "loss": 0.1474, "step": 385030 }, { "epoch": 2.2887577200397073, "grad_norm": 4.030539035797119, "learning_rate": 6.5823848851147e-06, "loss": 0.1269, "step": 385040 }, { "epoch": 2.2888171621163758, "grad_norm": 3.6254024505615234, "learning_rate": 6.582188056680418e-06, "loss": 0.1397, "step": 385050 }, { "epoch": 2.288876604193044, "grad_norm": 4.338141918182373, "learning_rate": 6.581991225521421e-06, "loss": 0.1417, "step": 385060 }, { "epoch": 2.2889360462697126, "grad_norm": 4.117762088775635, "learning_rate": 6.581794391638045e-06, "loss": 0.1396, "step": 385070 }, { "epoch": 2.288995488346381, "grad_norm": 4.795278549194336, "learning_rate": 6.5815975550306325e-06, "loss": 0.1432, "step": 385080 }, { "epoch": 2.2890549304230494, "grad_norm": 4.4894208908081055, "learning_rate": 6.581400715699518e-06, "loss": 0.1369, "step": 385090 }, { "epoch": 2.289114372499718, "grad_norm": 4.294475555419922, "learning_rate": 6.581203873645044e-06, "loss": 0.1293, "step": 385100 }, { "epoch": 2.289173814576386, "grad_norm": 4.85162878036499, "learning_rate": 6.581007028867546e-06, "loss": 0.1548, "step": 385110 }, { "epoch": 2.2892332566530547, "grad_norm": 4.661574840545654, "learning_rate": 6.5808101813673685e-06, "loss": 0.1658, "step": 385120 }, { "epoch": 2.2892926987297226, "grad_norm": 3.728294849395752, "learning_rate": 6.580613331144846e-06, "loss": 0.1695, "step": 385130 }, { "epoch": 2.289352140806391, "grad_norm": 3.17498517036438, "learning_rate": 6.580416478200318e-06, "loss": 0.1342, "step": 385140 }, { "epoch": 2.2894115828830595, "grad_norm": 2.8388280868530273, "learning_rate": 6.580219622534125e-06, "loss": 0.1419, "step": 385150 }, { "epoch": 2.289471024959728, "grad_norm": 5.637101173400879, "learning_rate": 6.580022764146607e-06, "loss": 0.1392, "step": 385160 }, { "epoch": 2.2895304670363963, "grad_norm": 2.724750280380249, "learning_rate": 6.579825903038099e-06, "loss": 0.1586, "step": 385170 }, { "epoch": 2.2895899091130647, "grad_norm": 4.060645580291748, "learning_rate": 6.579629039208942e-06, "loss": 0.1423, "step": 385180 }, { "epoch": 2.289649351189733, "grad_norm": 2.9691238403320312, "learning_rate": 6.5794321726594764e-06, "loss": 0.1235, "step": 385190 }, { "epoch": 2.2897087932664015, "grad_norm": 4.45143985748291, "learning_rate": 6.57923530339004e-06, "loss": 0.1591, "step": 385200 }, { "epoch": 2.28976823534307, "grad_norm": 3.5550265312194824, "learning_rate": 6.579038431400971e-06, "loss": 0.166, "step": 385210 }, { "epoch": 2.2898276774197384, "grad_norm": 4.195191383361816, "learning_rate": 6.57884155669261e-06, "loss": 0.1389, "step": 385220 }, { "epoch": 2.2898871194964068, "grad_norm": 4.112754821777344, "learning_rate": 6.578644679265296e-06, "loss": 0.1414, "step": 385230 }, { "epoch": 2.289946561573075, "grad_norm": 5.675502777099609, "learning_rate": 6.578447799119367e-06, "loss": 0.1548, "step": 385240 }, { "epoch": 2.2900060036497436, "grad_norm": 4.833832263946533, "learning_rate": 6.578250916255163e-06, "loss": 0.1364, "step": 385250 }, { "epoch": 2.290065445726412, "grad_norm": 5.99306583404541, "learning_rate": 6.578054030673022e-06, "loss": 0.1469, "step": 385260 }, { "epoch": 2.2901248878030804, "grad_norm": 3.8267390727996826, "learning_rate": 6.577857142373284e-06, "loss": 0.138, "step": 385270 }, { "epoch": 2.290184329879749, "grad_norm": 3.4720585346221924, "learning_rate": 6.577660251356288e-06, "loss": 0.1592, "step": 385280 }, { "epoch": 2.2902437719564173, "grad_norm": 4.919026851654053, "learning_rate": 6.577463357622374e-06, "loss": 0.1612, "step": 385290 }, { "epoch": 2.2903032140330852, "grad_norm": 4.2835307121276855, "learning_rate": 6.577266461171877e-06, "loss": 0.129, "step": 385300 }, { "epoch": 2.290362656109754, "grad_norm": 4.110262393951416, "learning_rate": 6.57706956200514e-06, "loss": 0.1625, "step": 385310 }, { "epoch": 2.290422098186422, "grad_norm": 3.3145909309387207, "learning_rate": 6.576872660122502e-06, "loss": 0.1359, "step": 385320 }, { "epoch": 2.2904815402630905, "grad_norm": 3.19227933883667, "learning_rate": 6.5766757555243e-06, "loss": 0.1445, "step": 385330 }, { "epoch": 2.290540982339759, "grad_norm": 2.9551849365234375, "learning_rate": 6.576478848210875e-06, "loss": 0.1431, "step": 385340 }, { "epoch": 2.2906004244164273, "grad_norm": 5.512312412261963, "learning_rate": 6.576281938182565e-06, "loss": 0.1577, "step": 385350 }, { "epoch": 2.2906598664930957, "grad_norm": 5.032406330108643, "learning_rate": 6.57608502543971e-06, "loss": 0.1532, "step": 385360 }, { "epoch": 2.290719308569764, "grad_norm": 5.155304431915283, "learning_rate": 6.575888109982648e-06, "loss": 0.1508, "step": 385370 }, { "epoch": 2.2907787506464325, "grad_norm": 4.422750473022461, "learning_rate": 6.575691191811718e-06, "loss": 0.1405, "step": 385380 }, { "epoch": 2.290838192723101, "grad_norm": 4.059558391571045, "learning_rate": 6.57549427092726e-06, "loss": 0.1462, "step": 385390 }, { "epoch": 2.2908976347997694, "grad_norm": 4.471458435058594, "learning_rate": 6.575297347329615e-06, "loss": 0.1472, "step": 385400 }, { "epoch": 2.290957076876438, "grad_norm": 4.215343952178955, "learning_rate": 6.575100421019118e-06, "loss": 0.1388, "step": 385410 }, { "epoch": 2.291016518953106, "grad_norm": 5.346301078796387, "learning_rate": 6.574903491996111e-06, "loss": 0.1514, "step": 385420 }, { "epoch": 2.2910759610297746, "grad_norm": 3.8146960735321045, "learning_rate": 6.57470656026093e-06, "loss": 0.1366, "step": 385430 }, { "epoch": 2.291135403106443, "grad_norm": 4.68821907043457, "learning_rate": 6.574509625813918e-06, "loss": 0.1313, "step": 385440 }, { "epoch": 2.2911948451831115, "grad_norm": 4.983796119689941, "learning_rate": 6.574312688655413e-06, "loss": 0.1457, "step": 385450 }, { "epoch": 2.29125428725978, "grad_norm": 3.882441520690918, "learning_rate": 6.574115748785755e-06, "loss": 0.127, "step": 385460 }, { "epoch": 2.2913137293364483, "grad_norm": 5.163957595825195, "learning_rate": 6.57391880620528e-06, "loss": 0.1418, "step": 385470 }, { "epoch": 2.2913731714131167, "grad_norm": 5.118727207183838, "learning_rate": 6.573721860914328e-06, "loss": 0.1603, "step": 385480 }, { "epoch": 2.2914326134897847, "grad_norm": 3.4522480964660645, "learning_rate": 6.573524912913242e-06, "loss": 0.149, "step": 385490 }, { "epoch": 2.291492055566453, "grad_norm": 3.804560899734497, "learning_rate": 6.573327962202356e-06, "loss": 0.1532, "step": 385500 }, { "epoch": 2.2915514976431215, "grad_norm": 4.339995384216309, "learning_rate": 6.573131008782012e-06, "loss": 0.1348, "step": 385510 }, { "epoch": 2.29161093971979, "grad_norm": 4.566874980926514, "learning_rate": 6.57293405265255e-06, "loss": 0.1364, "step": 385520 }, { "epoch": 2.2916703817964583, "grad_norm": 4.781159400939941, "learning_rate": 6.5727370938143065e-06, "loss": 0.1449, "step": 385530 }, { "epoch": 2.2917298238731267, "grad_norm": 3.8045079708099365, "learning_rate": 6.572540132267622e-06, "loss": 0.1553, "step": 385540 }, { "epoch": 2.291789265949795, "grad_norm": 4.595004558563232, "learning_rate": 6.5723431680128356e-06, "loss": 0.1416, "step": 385550 }, { "epoch": 2.2918487080264636, "grad_norm": 5.048311710357666, "learning_rate": 6.572146201050289e-06, "loss": 0.1537, "step": 385560 }, { "epoch": 2.291908150103132, "grad_norm": 4.961184024810791, "learning_rate": 6.571949231380315e-06, "loss": 0.1352, "step": 385570 }, { "epoch": 2.2919675921798004, "grad_norm": 4.338033676147461, "learning_rate": 6.571752259003261e-06, "loss": 0.1468, "step": 385580 }, { "epoch": 2.292027034256469, "grad_norm": 4.25356388092041, "learning_rate": 6.571555283919461e-06, "loss": 0.1496, "step": 385590 }, { "epoch": 2.2920864763331372, "grad_norm": 3.580530881881714, "learning_rate": 6.571358306129253e-06, "loss": 0.1406, "step": 385600 }, { "epoch": 2.2921459184098056, "grad_norm": 5.832493782043457, "learning_rate": 6.571161325632981e-06, "loss": 0.1428, "step": 385610 }, { "epoch": 2.292205360486474, "grad_norm": 3.3808419704437256, "learning_rate": 6.570964342430981e-06, "loss": 0.1427, "step": 385620 }, { "epoch": 2.2922648025631425, "grad_norm": 4.803863525390625, "learning_rate": 6.570767356523592e-06, "loss": 0.136, "step": 385630 }, { "epoch": 2.292324244639811, "grad_norm": 4.136917591094971, "learning_rate": 6.570570367911155e-06, "loss": 0.154, "step": 385640 }, { "epoch": 2.2923836867164793, "grad_norm": 4.06068229675293, "learning_rate": 6.57037337659401e-06, "loss": 0.1573, "step": 385650 }, { "epoch": 2.2924431287931477, "grad_norm": 3.8575313091278076, "learning_rate": 6.570176382572492e-06, "loss": 0.1302, "step": 385660 }, { "epoch": 2.292502570869816, "grad_norm": 5.393610000610352, "learning_rate": 6.569979385846943e-06, "loss": 0.1369, "step": 385670 }, { "epoch": 2.292562012946484, "grad_norm": 3.320891857147217, "learning_rate": 6.569782386417704e-06, "loss": 0.1474, "step": 385680 }, { "epoch": 2.2926214550231525, "grad_norm": 3.9124975204467773, "learning_rate": 6.569585384285112e-06, "loss": 0.1472, "step": 385690 }, { "epoch": 2.292680897099821, "grad_norm": 5.22291898727417, "learning_rate": 6.5693883794495064e-06, "loss": 0.1448, "step": 385700 }, { "epoch": 2.2927403391764893, "grad_norm": 4.871894359588623, "learning_rate": 6.569191371911225e-06, "loss": 0.1533, "step": 385710 }, { "epoch": 2.2927997812531578, "grad_norm": 4.188023090362549, "learning_rate": 6.568994361670612e-06, "loss": 0.1316, "step": 385720 }, { "epoch": 2.292859223329826, "grad_norm": 4.9786176681518555, "learning_rate": 6.568797348728001e-06, "loss": 0.1394, "step": 385730 }, { "epoch": 2.2929186654064946, "grad_norm": 4.016664505004883, "learning_rate": 6.5686003330837355e-06, "loss": 0.1355, "step": 385740 }, { "epoch": 2.292978107483163, "grad_norm": 3.526711940765381, "learning_rate": 6.568403314738152e-06, "loss": 0.1525, "step": 385750 }, { "epoch": 2.2930375495598314, "grad_norm": 4.4800705909729, "learning_rate": 6.568206293691591e-06, "loss": 0.1482, "step": 385760 }, { "epoch": 2.2930969916365, "grad_norm": 3.6802260875701904, "learning_rate": 6.568009269944391e-06, "loss": 0.1375, "step": 385770 }, { "epoch": 2.2931564337131682, "grad_norm": 2.988558769226074, "learning_rate": 6.567812243496894e-06, "loss": 0.1228, "step": 385780 }, { "epoch": 2.2932158757898367, "grad_norm": 4.129560470581055, "learning_rate": 6.567615214349434e-06, "loss": 0.1323, "step": 385790 }, { "epoch": 2.293275317866505, "grad_norm": 4.399479866027832, "learning_rate": 6.567418182502357e-06, "loss": 0.1556, "step": 385800 }, { "epoch": 2.2933347599431735, "grad_norm": 3.4106500148773193, "learning_rate": 6.567221147955998e-06, "loss": 0.1503, "step": 385810 }, { "epoch": 2.293394202019842, "grad_norm": 4.528042793273926, "learning_rate": 6.567024110710696e-06, "loss": 0.1418, "step": 385820 }, { "epoch": 2.2934536440965103, "grad_norm": 6.265697956085205, "learning_rate": 6.566827070766792e-06, "loss": 0.1498, "step": 385830 }, { "epoch": 2.2935130861731787, "grad_norm": 4.381695747375488, "learning_rate": 6.566630028124626e-06, "loss": 0.1352, "step": 385840 }, { "epoch": 2.2935725282498467, "grad_norm": 4.320204734802246, "learning_rate": 6.566432982784535e-06, "loss": 0.1359, "step": 385850 }, { "epoch": 2.2936319703265156, "grad_norm": 5.289201736450195, "learning_rate": 6.566235934746859e-06, "loss": 0.1403, "step": 385860 }, { "epoch": 2.2936914124031835, "grad_norm": 5.408215522766113, "learning_rate": 6.5660388840119384e-06, "loss": 0.1364, "step": 385870 }, { "epoch": 2.293750854479852, "grad_norm": 3.77194881439209, "learning_rate": 6.565841830580112e-06, "loss": 0.135, "step": 385880 }, { "epoch": 2.2938102965565204, "grad_norm": 3.351299524307251, "learning_rate": 6.565644774451718e-06, "loss": 0.1289, "step": 385890 }, { "epoch": 2.2938697386331888, "grad_norm": 3.9963672161102295, "learning_rate": 6.565447715627099e-06, "loss": 0.1484, "step": 385900 }, { "epoch": 2.293929180709857, "grad_norm": 4.348382472991943, "learning_rate": 6.565250654106592e-06, "loss": 0.1317, "step": 385910 }, { "epoch": 2.2939886227865256, "grad_norm": 5.598572731018066, "learning_rate": 6.565053589890535e-06, "loss": 0.1567, "step": 385920 }, { "epoch": 2.294048064863194, "grad_norm": 4.782675743103027, "learning_rate": 6.56485652297927e-06, "loss": 0.1516, "step": 385930 }, { "epoch": 2.2941075069398624, "grad_norm": 3.787794351577759, "learning_rate": 6.564659453373136e-06, "loss": 0.1455, "step": 385940 }, { "epoch": 2.294166949016531, "grad_norm": 4.601298809051514, "learning_rate": 6.56446238107247e-06, "loss": 0.1542, "step": 385950 }, { "epoch": 2.2942263910931993, "grad_norm": 4.622886657714844, "learning_rate": 6.5642653060776155e-06, "loss": 0.1434, "step": 385960 }, { "epoch": 2.2942858331698677, "grad_norm": 4.16740083694458, "learning_rate": 6.564068228388908e-06, "loss": 0.1325, "step": 385970 }, { "epoch": 2.294345275246536, "grad_norm": 4.518539905548096, "learning_rate": 6.563871148006687e-06, "loss": 0.1381, "step": 385980 }, { "epoch": 2.2944047173232045, "grad_norm": 4.777624607086182, "learning_rate": 6.563674064931294e-06, "loss": 0.1419, "step": 385990 }, { "epoch": 2.294464159399873, "grad_norm": 6.064276218414307, "learning_rate": 6.5634769791630695e-06, "loss": 0.1474, "step": 386000 }, { "epoch": 2.2945236014765413, "grad_norm": 4.249246120452881, "learning_rate": 6.5632798907023496e-06, "loss": 0.1398, "step": 386010 }, { "epoch": 2.2945830435532097, "grad_norm": 6.129262924194336, "learning_rate": 6.563082799549476e-06, "loss": 0.1597, "step": 386020 }, { "epoch": 2.294642485629878, "grad_norm": 4.858887672424316, "learning_rate": 6.562885705704787e-06, "loss": 0.1539, "step": 386030 }, { "epoch": 2.294701927706546, "grad_norm": 7.559199810028076, "learning_rate": 6.562688609168623e-06, "loss": 0.1515, "step": 386040 }, { "epoch": 2.294761369783215, "grad_norm": 3.643922805786133, "learning_rate": 6.562491509941321e-06, "loss": 0.1417, "step": 386050 }, { "epoch": 2.294820811859883, "grad_norm": 4.105930805206299, "learning_rate": 6.562294408023225e-06, "loss": 0.157, "step": 386060 }, { "epoch": 2.2948802539365514, "grad_norm": 3.719433546066284, "learning_rate": 6.5620973034146695e-06, "loss": 0.1816, "step": 386070 }, { "epoch": 2.29493969601322, "grad_norm": 4.201535224914551, "learning_rate": 6.561900196115995e-06, "loss": 0.1579, "step": 386080 }, { "epoch": 2.294999138089888, "grad_norm": 4.121950149536133, "learning_rate": 6.561703086127544e-06, "loss": 0.151, "step": 386090 }, { "epoch": 2.2950585801665566, "grad_norm": 4.628490924835205, "learning_rate": 6.5615059734496535e-06, "loss": 0.1448, "step": 386100 }, { "epoch": 2.295118022243225, "grad_norm": 3.9734606742858887, "learning_rate": 6.5613088580826636e-06, "loss": 0.1365, "step": 386110 }, { "epoch": 2.2951774643198934, "grad_norm": 3.4048831462860107, "learning_rate": 6.561111740026912e-06, "loss": 0.1355, "step": 386120 }, { "epoch": 2.295236906396562, "grad_norm": 5.3968071937561035, "learning_rate": 6.560914619282741e-06, "loss": 0.1608, "step": 386130 }, { "epoch": 2.2952963484732303, "grad_norm": 3.807326078414917, "learning_rate": 6.560717495850489e-06, "loss": 0.1599, "step": 386140 }, { "epoch": 2.2953557905498987, "grad_norm": 3.391782522201538, "learning_rate": 6.5605203697304946e-06, "loss": 0.1527, "step": 386150 }, { "epoch": 2.295415232626567, "grad_norm": 3.5556840896606445, "learning_rate": 6.560323240923099e-06, "loss": 0.1296, "step": 386160 }, { "epoch": 2.2954746747032355, "grad_norm": 3.5834853649139404, "learning_rate": 6.560126109428641e-06, "loss": 0.1307, "step": 386170 }, { "epoch": 2.295534116779904, "grad_norm": 4.773859024047852, "learning_rate": 6.559928975247457e-06, "loss": 0.1304, "step": 386180 }, { "epoch": 2.2955935588565723, "grad_norm": 4.134322643280029, "learning_rate": 6.5597318383798915e-06, "loss": 0.1514, "step": 386190 }, { "epoch": 2.2956530009332408, "grad_norm": 3.5984768867492676, "learning_rate": 6.5595346988262806e-06, "loss": 0.1488, "step": 386200 }, { "epoch": 2.295712443009909, "grad_norm": 4.447464466094971, "learning_rate": 6.559337556586965e-06, "loss": 0.1498, "step": 386210 }, { "epoch": 2.2957718850865776, "grad_norm": 3.68245267868042, "learning_rate": 6.559140411662284e-06, "loss": 0.1434, "step": 386220 }, { "epoch": 2.2958313271632456, "grad_norm": 3.7200541496276855, "learning_rate": 6.558943264052577e-06, "loss": 0.1395, "step": 386230 }, { "epoch": 2.295890769239914, "grad_norm": 4.84031343460083, "learning_rate": 6.558746113758185e-06, "loss": 0.152, "step": 386240 }, { "epoch": 2.2959502113165824, "grad_norm": 5.110674858093262, "learning_rate": 6.558548960779445e-06, "loss": 0.1578, "step": 386250 }, { "epoch": 2.296009653393251, "grad_norm": 3.9990320205688477, "learning_rate": 6.5583518051166984e-06, "loss": 0.1525, "step": 386260 }, { "epoch": 2.296069095469919, "grad_norm": 4.3740234375, "learning_rate": 6.558154646770284e-06, "loss": 0.1623, "step": 386270 }, { "epoch": 2.2961285375465876, "grad_norm": 4.6846747398376465, "learning_rate": 6.55795748574054e-06, "loss": 0.1471, "step": 386280 }, { "epoch": 2.296187979623256, "grad_norm": 4.317817687988281, "learning_rate": 6.55776032202781e-06, "loss": 0.1579, "step": 386290 }, { "epoch": 2.2962474216999245, "grad_norm": 3.082327127456665, "learning_rate": 6.5575631556324295e-06, "loss": 0.1613, "step": 386300 }, { "epoch": 2.296306863776593, "grad_norm": 3.5763769149780273, "learning_rate": 6.557365986554738e-06, "loss": 0.1618, "step": 386310 }, { "epoch": 2.2963663058532613, "grad_norm": 4.616753101348877, "learning_rate": 6.557168814795076e-06, "loss": 0.1617, "step": 386320 }, { "epoch": 2.2964257479299297, "grad_norm": 5.060337066650391, "learning_rate": 6.556971640353787e-06, "loss": 0.1555, "step": 386330 }, { "epoch": 2.296485190006598, "grad_norm": 4.142983436584473, "learning_rate": 6.556774463231205e-06, "loss": 0.1696, "step": 386340 }, { "epoch": 2.2965446320832665, "grad_norm": 4.2197957038879395, "learning_rate": 6.556577283427671e-06, "loss": 0.1344, "step": 386350 }, { "epoch": 2.296604074159935, "grad_norm": 4.360745429992676, "learning_rate": 6.556380100943527e-06, "loss": 0.1402, "step": 386360 }, { "epoch": 2.2966635162366034, "grad_norm": 4.415907859802246, "learning_rate": 6.55618291577911e-06, "loss": 0.1557, "step": 386370 }, { "epoch": 2.296722958313272, "grad_norm": 4.9501237869262695, "learning_rate": 6.555985727934759e-06, "loss": 0.1522, "step": 386380 }, { "epoch": 2.29678240038994, "grad_norm": 3.2871899604797363, "learning_rate": 6.555788537410816e-06, "loss": 0.1337, "step": 386390 }, { "epoch": 2.2968418424666086, "grad_norm": 3.5857677459716797, "learning_rate": 6.55559134420762e-06, "loss": 0.166, "step": 386400 }, { "epoch": 2.296901284543277, "grad_norm": 3.731581926345825, "learning_rate": 6.555394148325509e-06, "loss": 0.1357, "step": 386410 }, { "epoch": 2.296960726619945, "grad_norm": 4.458598613739014, "learning_rate": 6.555196949764825e-06, "loss": 0.1594, "step": 386420 }, { "epoch": 2.2970201686966134, "grad_norm": 4.252748489379883, "learning_rate": 6.554999748525905e-06, "loss": 0.1382, "step": 386430 }, { "epoch": 2.297079610773282, "grad_norm": 4.278104305267334, "learning_rate": 6.55480254460909e-06, "loss": 0.1776, "step": 386440 }, { "epoch": 2.2971390528499502, "grad_norm": 3.067716360092163, "learning_rate": 6.55460533801472e-06, "loss": 0.1437, "step": 386450 }, { "epoch": 2.2971984949266187, "grad_norm": 3.5832467079162598, "learning_rate": 6.554408128743135e-06, "loss": 0.1378, "step": 386460 }, { "epoch": 2.297257937003287, "grad_norm": 5.096067905426025, "learning_rate": 6.554210916794672e-06, "loss": 0.1337, "step": 386470 }, { "epoch": 2.2973173790799555, "grad_norm": 4.374378204345703, "learning_rate": 6.554013702169674e-06, "loss": 0.1656, "step": 386480 }, { "epoch": 2.297376821156624, "grad_norm": 4.075075149536133, "learning_rate": 6.553816484868478e-06, "loss": 0.1562, "step": 386490 }, { "epoch": 2.2974362632332923, "grad_norm": 4.237990379333496, "learning_rate": 6.553619264891426e-06, "loss": 0.1503, "step": 386500 }, { "epoch": 2.2974957053099607, "grad_norm": 3.2209205627441406, "learning_rate": 6.553422042238854e-06, "loss": 0.134, "step": 386510 }, { "epoch": 2.297555147386629, "grad_norm": 2.7053799629211426, "learning_rate": 6.5532248169111055e-06, "loss": 0.151, "step": 386520 }, { "epoch": 2.2976145894632976, "grad_norm": 4.463222026824951, "learning_rate": 6.5530275889085185e-06, "loss": 0.1254, "step": 386530 }, { "epoch": 2.297674031539966, "grad_norm": 3.854330062866211, "learning_rate": 6.55283035823143e-06, "loss": 0.1138, "step": 386540 }, { "epoch": 2.2977334736166344, "grad_norm": 3.8926618099212646, "learning_rate": 6.552633124880186e-06, "loss": 0.1602, "step": 386550 }, { "epoch": 2.297792915693303, "grad_norm": 3.7851312160491943, "learning_rate": 6.5524358888551195e-06, "loss": 0.1357, "step": 386560 }, { "epoch": 2.297852357769971, "grad_norm": 4.205565452575684, "learning_rate": 6.552238650156575e-06, "loss": 0.1444, "step": 386570 }, { "epoch": 2.2979117998466396, "grad_norm": 3.936795473098755, "learning_rate": 6.552041408784891e-06, "loss": 0.1533, "step": 386580 }, { "epoch": 2.2979712419233076, "grad_norm": 5.447805881500244, "learning_rate": 6.551844164740405e-06, "loss": 0.1674, "step": 386590 }, { "epoch": 2.2980306839999765, "grad_norm": 4.8973708152771, "learning_rate": 6.551646918023458e-06, "loss": 0.1597, "step": 386600 }, { "epoch": 2.2980901260766444, "grad_norm": 4.515111923217773, "learning_rate": 6.551449668634391e-06, "loss": 0.1543, "step": 386610 }, { "epoch": 2.298149568153313, "grad_norm": 3.3923184871673584, "learning_rate": 6.5512524165735426e-06, "loss": 0.1525, "step": 386620 }, { "epoch": 2.2982090102299813, "grad_norm": 3.868894338607788, "learning_rate": 6.551055161841251e-06, "loss": 0.1519, "step": 386630 }, { "epoch": 2.2982684523066497, "grad_norm": 3.866748809814453, "learning_rate": 6.550857904437859e-06, "loss": 0.1426, "step": 386640 }, { "epoch": 2.298327894383318, "grad_norm": 5.905027389526367, "learning_rate": 6.550660644363703e-06, "loss": 0.1594, "step": 386650 }, { "epoch": 2.2983873364599865, "grad_norm": 5.921548843383789, "learning_rate": 6.550463381619126e-06, "loss": 0.1516, "step": 386660 }, { "epoch": 2.298446778536655, "grad_norm": 4.920907974243164, "learning_rate": 6.5502661162044645e-06, "loss": 0.1693, "step": 386670 }, { "epoch": 2.2985062206133233, "grad_norm": 4.2047505378723145, "learning_rate": 6.550068848120062e-06, "loss": 0.149, "step": 386680 }, { "epoch": 2.2985656626899917, "grad_norm": 4.864356994628906, "learning_rate": 6.549871577366255e-06, "loss": 0.1638, "step": 386690 }, { "epoch": 2.29862510476666, "grad_norm": 3.8460025787353516, "learning_rate": 6.549674303943383e-06, "loss": 0.1597, "step": 386700 }, { "epoch": 2.2986845468433286, "grad_norm": 2.8874499797821045, "learning_rate": 6.5494770278517885e-06, "loss": 0.1455, "step": 386710 }, { "epoch": 2.298743988919997, "grad_norm": 4.7880940437316895, "learning_rate": 6.549279749091809e-06, "loss": 0.1423, "step": 386720 }, { "epoch": 2.2988034309966654, "grad_norm": 3.5190703868865967, "learning_rate": 6.549082467663785e-06, "loss": 0.1421, "step": 386730 }, { "epoch": 2.298862873073334, "grad_norm": 5.04577112197876, "learning_rate": 6.548885183568055e-06, "loss": 0.1365, "step": 386740 }, { "epoch": 2.2989223151500022, "grad_norm": 4.7421088218688965, "learning_rate": 6.5486878968049615e-06, "loss": 0.1349, "step": 386750 }, { "epoch": 2.2989817572266706, "grad_norm": 4.93866491317749, "learning_rate": 6.548490607374842e-06, "loss": 0.1491, "step": 386760 }, { "epoch": 2.299041199303339, "grad_norm": 3.6670327186584473, "learning_rate": 6.548293315278036e-06, "loss": 0.1492, "step": 386770 }, { "epoch": 2.299100641380007, "grad_norm": 3.790895938873291, "learning_rate": 6.5480960205148855e-06, "loss": 0.142, "step": 386780 }, { "epoch": 2.299160083456676, "grad_norm": 4.133942604064941, "learning_rate": 6.547898723085729e-06, "loss": 0.1368, "step": 386790 }, { "epoch": 2.299219525533344, "grad_norm": 4.621363639831543, "learning_rate": 6.547701422990905e-06, "loss": 0.153, "step": 386800 }, { "epoch": 2.2992789676100123, "grad_norm": 3.7648046016693115, "learning_rate": 6.5475041202307565e-06, "loss": 0.1497, "step": 386810 }, { "epoch": 2.2993384096866807, "grad_norm": 4.528446197509766, "learning_rate": 6.547306814805621e-06, "loss": 0.1677, "step": 386820 }, { "epoch": 2.299397851763349, "grad_norm": 3.5012741088867188, "learning_rate": 6.547109506715836e-06, "loss": 0.1381, "step": 386830 }, { "epoch": 2.2994572938400175, "grad_norm": 4.607514381408691, "learning_rate": 6.546912195961745e-06, "loss": 0.1533, "step": 386840 }, { "epoch": 2.299516735916686, "grad_norm": 3.417208671569824, "learning_rate": 6.5467148825436875e-06, "loss": 0.1455, "step": 386850 }, { "epoch": 2.2995761779933543, "grad_norm": 4.347425937652588, "learning_rate": 6.546517566462003e-06, "loss": 0.1366, "step": 386860 }, { "epoch": 2.2996356200700228, "grad_norm": 4.682527542114258, "learning_rate": 6.546320247717028e-06, "loss": 0.1371, "step": 386870 }, { "epoch": 2.299695062146691, "grad_norm": 3.8140132427215576, "learning_rate": 6.546122926309107e-06, "loss": 0.1497, "step": 386880 }, { "epoch": 2.2997545042233596, "grad_norm": 5.216251373291016, "learning_rate": 6.5459256022385785e-06, "loss": 0.15, "step": 386890 }, { "epoch": 2.299813946300028, "grad_norm": 4.3315958976745605, "learning_rate": 6.54572827550578e-06, "loss": 0.1534, "step": 386900 }, { "epoch": 2.2998733883766964, "grad_norm": 6.714107036590576, "learning_rate": 6.545530946111054e-06, "loss": 0.1567, "step": 386910 }, { "epoch": 2.299932830453365, "grad_norm": 3.7547638416290283, "learning_rate": 6.5453336140547395e-06, "loss": 0.1557, "step": 386920 }, { "epoch": 2.2999922725300332, "grad_norm": 4.111057281494141, "learning_rate": 6.545136279337175e-06, "loss": 0.1662, "step": 386930 }, { "epoch": 2.3000517146067017, "grad_norm": 4.405235767364502, "learning_rate": 6.544938941958703e-06, "loss": 0.1246, "step": 386940 }, { "epoch": 2.30011115668337, "grad_norm": 4.419622898101807, "learning_rate": 6.544741601919661e-06, "loss": 0.1542, "step": 386950 }, { "epoch": 2.3001705987600385, "grad_norm": 3.706641674041748, "learning_rate": 6.544544259220389e-06, "loss": 0.1571, "step": 386960 }, { "epoch": 2.3002300408367065, "grad_norm": 6.704535007476807, "learning_rate": 6.544346913861227e-06, "loss": 0.148, "step": 386970 }, { "epoch": 2.300289482913375, "grad_norm": 4.212711811065674, "learning_rate": 6.544149565842517e-06, "loss": 0.1642, "step": 386980 }, { "epoch": 2.3003489249900433, "grad_norm": 3.7294607162475586, "learning_rate": 6.5439522151645975e-06, "loss": 0.1454, "step": 386990 }, { "epoch": 2.3004083670667117, "grad_norm": 4.684296607971191, "learning_rate": 6.543754861827806e-06, "loss": 0.1377, "step": 387000 }, { "epoch": 2.30046780914338, "grad_norm": 4.353626251220703, "learning_rate": 6.543557505832487e-06, "loss": 0.1367, "step": 387010 }, { "epoch": 2.3005272512200485, "grad_norm": 3.7858667373657227, "learning_rate": 6.543360147178976e-06, "loss": 0.1407, "step": 387020 }, { "epoch": 2.300586693296717, "grad_norm": 4.152895927429199, "learning_rate": 6.543162785867614e-06, "loss": 0.1447, "step": 387030 }, { "epoch": 2.3006461353733854, "grad_norm": 4.284115314483643, "learning_rate": 6.542965421898744e-06, "loss": 0.1415, "step": 387040 }, { "epoch": 2.3007055774500538, "grad_norm": 4.064379692077637, "learning_rate": 6.5427680552727015e-06, "loss": 0.1555, "step": 387050 }, { "epoch": 2.300765019526722, "grad_norm": 4.273792266845703, "learning_rate": 6.542570685989828e-06, "loss": 0.1513, "step": 387060 }, { "epoch": 2.3008244616033906, "grad_norm": 5.716587543487549, "learning_rate": 6.542373314050465e-06, "loss": 0.1568, "step": 387070 }, { "epoch": 2.300883903680059, "grad_norm": 3.501465320587158, "learning_rate": 6.5421759394549514e-06, "loss": 0.1352, "step": 387080 }, { "epoch": 2.3009433457567274, "grad_norm": 6.14382791519165, "learning_rate": 6.541978562203624e-06, "loss": 0.1722, "step": 387090 }, { "epoch": 2.301002787833396, "grad_norm": 6.548652172088623, "learning_rate": 6.5417811822968295e-06, "loss": 0.1551, "step": 387100 }, { "epoch": 2.3010622299100643, "grad_norm": 3.7753474712371826, "learning_rate": 6.541583799734902e-06, "loss": 0.1445, "step": 387110 }, { "epoch": 2.3011216719867327, "grad_norm": 4.29647159576416, "learning_rate": 6.541386414518182e-06, "loss": 0.1584, "step": 387120 }, { "epoch": 2.301181114063401, "grad_norm": 4.383085250854492, "learning_rate": 6.541189026647012e-06, "loss": 0.1428, "step": 387130 }, { "epoch": 2.301240556140069, "grad_norm": 4.365519046783447, "learning_rate": 6.540991636121732e-06, "loss": 0.1366, "step": 387140 }, { "epoch": 2.301299998216738, "grad_norm": 4.111293792724609, "learning_rate": 6.540794242942678e-06, "loss": 0.1529, "step": 387150 }, { "epoch": 2.301359440293406, "grad_norm": 5.242635726928711, "learning_rate": 6.5405968471101945e-06, "loss": 0.1515, "step": 387160 }, { "epoch": 2.3014188823700743, "grad_norm": 3.403956651687622, "learning_rate": 6.540399448624618e-06, "loss": 0.1446, "step": 387170 }, { "epoch": 2.3014783244467427, "grad_norm": 4.669024467468262, "learning_rate": 6.54020204748629e-06, "loss": 0.1478, "step": 387180 }, { "epoch": 2.301537766523411, "grad_norm": 2.743004322052002, "learning_rate": 6.54000464369555e-06, "loss": 0.1436, "step": 387190 }, { "epoch": 2.3015972086000795, "grad_norm": 3.431840658187866, "learning_rate": 6.53980723725274e-06, "loss": 0.1289, "step": 387200 }, { "epoch": 2.301656650676748, "grad_norm": 3.690918207168579, "learning_rate": 6.539609828158197e-06, "loss": 0.1438, "step": 387210 }, { "epoch": 2.3017160927534164, "grad_norm": 4.222318172454834, "learning_rate": 6.539412416412261e-06, "loss": 0.1668, "step": 387220 }, { "epoch": 2.301775534830085, "grad_norm": 4.4617838859558105, "learning_rate": 6.539215002015275e-06, "loss": 0.1435, "step": 387230 }, { "epoch": 2.301834976906753, "grad_norm": 4.871435642242432, "learning_rate": 6.539017584967577e-06, "loss": 0.1416, "step": 387240 }, { "epoch": 2.3018944189834216, "grad_norm": 5.01456356048584, "learning_rate": 6.538820165269506e-06, "loss": 0.141, "step": 387250 }, { "epoch": 2.30195386106009, "grad_norm": 3.953423023223877, "learning_rate": 6.538622742921404e-06, "loss": 0.1418, "step": 387260 }, { "epoch": 2.3020133031367584, "grad_norm": 3.739684581756592, "learning_rate": 6.53842531792361e-06, "loss": 0.1383, "step": 387270 }, { "epoch": 2.302072745213427, "grad_norm": 4.366918087005615, "learning_rate": 6.538227890276463e-06, "loss": 0.1505, "step": 387280 }, { "epoch": 2.3021321872900953, "grad_norm": 4.170111179351807, "learning_rate": 6.5380304599803055e-06, "loss": 0.152, "step": 387290 }, { "epoch": 2.3021916293667637, "grad_norm": 4.988673210144043, "learning_rate": 6.537833027035475e-06, "loss": 0.1602, "step": 387300 }, { "epoch": 2.302251071443432, "grad_norm": 4.844240188598633, "learning_rate": 6.537635591442313e-06, "loss": 0.1585, "step": 387310 }, { "epoch": 2.3023105135201005, "grad_norm": 4.064908027648926, "learning_rate": 6.5374381532011586e-06, "loss": 0.1276, "step": 387320 }, { "epoch": 2.3023699555967685, "grad_norm": 4.321427822113037, "learning_rate": 6.537240712312353e-06, "loss": 0.1531, "step": 387330 }, { "epoch": 2.3024293976734374, "grad_norm": 4.514803409576416, "learning_rate": 6.5370432687762355e-06, "loss": 0.1614, "step": 387340 }, { "epoch": 2.3024888397501053, "grad_norm": 5.445954322814941, "learning_rate": 6.536845822593145e-06, "loss": 0.1445, "step": 387350 }, { "epoch": 2.3025482818267737, "grad_norm": 4.609888553619385, "learning_rate": 6.5366483737634234e-06, "loss": 0.1524, "step": 387360 }, { "epoch": 2.302607723903442, "grad_norm": 3.802489995956421, "learning_rate": 6.53645092228741e-06, "loss": 0.1444, "step": 387370 }, { "epoch": 2.3026671659801106, "grad_norm": 5.503286838531494, "learning_rate": 6.536253468165445e-06, "loss": 0.1635, "step": 387380 }, { "epoch": 2.302726608056779, "grad_norm": 4.033763885498047, "learning_rate": 6.536056011397866e-06, "loss": 0.1339, "step": 387390 }, { "epoch": 2.3027860501334474, "grad_norm": 4.325776100158691, "learning_rate": 6.535858551985019e-06, "loss": 0.1697, "step": 387400 }, { "epoch": 2.302845492210116, "grad_norm": 3.283231496810913, "learning_rate": 6.535661089927237e-06, "loss": 0.145, "step": 387410 }, { "epoch": 2.3029049342867842, "grad_norm": 4.460574626922607, "learning_rate": 6.535463625224865e-06, "loss": 0.1499, "step": 387420 }, { "epoch": 2.3029643763634526, "grad_norm": 4.5520782470703125, "learning_rate": 6.535266157878242e-06, "loss": 0.1526, "step": 387430 }, { "epoch": 2.303023818440121, "grad_norm": 5.136464595794678, "learning_rate": 6.5350686878877066e-06, "loss": 0.1491, "step": 387440 }, { "epoch": 2.3030832605167895, "grad_norm": 4.680215358734131, "learning_rate": 6.5348712152535985e-06, "loss": 0.1376, "step": 387450 }, { "epoch": 2.303142702593458, "grad_norm": 3.580702781677246, "learning_rate": 6.5346737399762605e-06, "loss": 0.1561, "step": 387460 }, { "epoch": 2.3032021446701263, "grad_norm": 4.5909423828125, "learning_rate": 6.5344762620560324e-06, "loss": 0.1472, "step": 387470 }, { "epoch": 2.3032615867467947, "grad_norm": 4.443104267120361, "learning_rate": 6.5342787814932504e-06, "loss": 0.1418, "step": 387480 }, { "epoch": 2.303321028823463, "grad_norm": 3.898925542831421, "learning_rate": 6.534081298288259e-06, "loss": 0.1678, "step": 387490 }, { "epoch": 2.3033804709001315, "grad_norm": 5.091342926025391, "learning_rate": 6.533883812441397e-06, "loss": 0.1507, "step": 387500 }, { "epoch": 2.3034399129768, "grad_norm": 3.048079252243042, "learning_rate": 6.533686323953002e-06, "loss": 0.1565, "step": 387510 }, { "epoch": 2.303499355053468, "grad_norm": 4.4794392585754395, "learning_rate": 6.533488832823418e-06, "loss": 0.1474, "step": 387520 }, { "epoch": 2.303558797130137, "grad_norm": 5.23496675491333, "learning_rate": 6.5332913390529826e-06, "loss": 0.1267, "step": 387530 }, { "epoch": 2.3036182392068048, "grad_norm": 3.0952577590942383, "learning_rate": 6.533093842642038e-06, "loss": 0.1412, "step": 387540 }, { "epoch": 2.303677681283473, "grad_norm": 6.039147853851318, "learning_rate": 6.5328963435909195e-06, "loss": 0.1398, "step": 387550 }, { "epoch": 2.3037371233601416, "grad_norm": 3.403960943222046, "learning_rate": 6.532698841899974e-06, "loss": 0.1424, "step": 387560 }, { "epoch": 2.30379656543681, "grad_norm": 7.15775203704834, "learning_rate": 6.532501337569537e-06, "loss": 0.1601, "step": 387570 }, { "epoch": 2.3038560075134784, "grad_norm": 4.476445198059082, "learning_rate": 6.532303830599949e-06, "loss": 0.1444, "step": 387580 }, { "epoch": 2.303915449590147, "grad_norm": 5.674941539764404, "learning_rate": 6.532106320991552e-06, "loss": 0.1466, "step": 387590 }, { "epoch": 2.3039748916668152, "grad_norm": 3.1830894947052, "learning_rate": 6.531908808744685e-06, "loss": 0.139, "step": 387600 }, { "epoch": 2.3040343337434837, "grad_norm": 5.600482940673828, "learning_rate": 6.5317112938596875e-06, "loss": 0.1506, "step": 387610 }, { "epoch": 2.304093775820152, "grad_norm": 3.7032110691070557, "learning_rate": 6.531513776336901e-06, "loss": 0.1441, "step": 387620 }, { "epoch": 2.3041532178968205, "grad_norm": 4.426184177398682, "learning_rate": 6.531316256176664e-06, "loss": 0.1408, "step": 387630 }, { "epoch": 2.304212659973489, "grad_norm": 3.404906749725342, "learning_rate": 6.531118733379319e-06, "loss": 0.1449, "step": 387640 }, { "epoch": 2.3042721020501573, "grad_norm": 4.362661838531494, "learning_rate": 6.530921207945204e-06, "loss": 0.1399, "step": 387650 }, { "epoch": 2.3043315441268257, "grad_norm": 6.159257888793945, "learning_rate": 6.530723679874661e-06, "loss": 0.1516, "step": 387660 }, { "epoch": 2.304390986203494, "grad_norm": 5.087332725524902, "learning_rate": 6.53052614916803e-06, "loss": 0.1744, "step": 387670 }, { "epoch": 2.3044504282801626, "grad_norm": 5.729189395904541, "learning_rate": 6.530328615825647e-06, "loss": 0.157, "step": 387680 }, { "epoch": 2.304509870356831, "grad_norm": 5.108659267425537, "learning_rate": 6.530131079847859e-06, "loss": 0.1425, "step": 387690 }, { "epoch": 2.3045693124334994, "grad_norm": 4.232761859893799, "learning_rate": 6.529933541235e-06, "loss": 0.1365, "step": 387700 }, { "epoch": 2.3046287545101674, "grad_norm": 3.8857529163360596, "learning_rate": 6.5297359999874144e-06, "loss": 0.1447, "step": 387710 }, { "epoch": 2.3046881965868358, "grad_norm": 4.32161808013916, "learning_rate": 6.529538456105441e-06, "loss": 0.1346, "step": 387720 }, { "epoch": 2.304747638663504, "grad_norm": 4.825641632080078, "learning_rate": 6.52934090958942e-06, "loss": 0.1553, "step": 387730 }, { "epoch": 2.3048070807401726, "grad_norm": 3.1633312702178955, "learning_rate": 6.529143360439689e-06, "loss": 0.1421, "step": 387740 }, { "epoch": 2.304866522816841, "grad_norm": 4.559993743896484, "learning_rate": 6.5289458086565924e-06, "loss": 0.1524, "step": 387750 }, { "epoch": 2.3049259648935094, "grad_norm": 4.883482933044434, "learning_rate": 6.52874825424047e-06, "loss": 0.1573, "step": 387760 }, { "epoch": 2.304985406970178, "grad_norm": 4.621656894683838, "learning_rate": 6.528550697191659e-06, "loss": 0.153, "step": 387770 }, { "epoch": 2.3050448490468463, "grad_norm": 4.443795680999756, "learning_rate": 6.528353137510502e-06, "loss": 0.1568, "step": 387780 }, { "epoch": 2.3051042911235147, "grad_norm": 4.506947994232178, "learning_rate": 6.528155575197339e-06, "loss": 0.1499, "step": 387790 }, { "epoch": 2.305163733200183, "grad_norm": 3.688462495803833, "learning_rate": 6.527958010252509e-06, "loss": 0.1668, "step": 387800 }, { "epoch": 2.3052231752768515, "grad_norm": 3.860842227935791, "learning_rate": 6.527760442676354e-06, "loss": 0.1464, "step": 387810 }, { "epoch": 2.30528261735352, "grad_norm": 4.613480567932129, "learning_rate": 6.527562872469213e-06, "loss": 0.1359, "step": 387820 }, { "epoch": 2.3053420594301883, "grad_norm": 3.823720693588257, "learning_rate": 6.527365299631425e-06, "loss": 0.1533, "step": 387830 }, { "epoch": 2.3054015015068567, "grad_norm": 4.260872840881348, "learning_rate": 6.527167724163333e-06, "loss": 0.1404, "step": 387840 }, { "epoch": 2.305460943583525, "grad_norm": 5.113341331481934, "learning_rate": 6.526970146065274e-06, "loss": 0.1495, "step": 387850 }, { "epoch": 2.3055203856601936, "grad_norm": 3.862792491912842, "learning_rate": 6.526772565337594e-06, "loss": 0.155, "step": 387860 }, { "epoch": 2.305579827736862, "grad_norm": 4.507882118225098, "learning_rate": 6.526574981980625e-06, "loss": 0.1526, "step": 387870 }, { "epoch": 2.30563926981353, "grad_norm": 3.4978508949279785, "learning_rate": 6.526377395994715e-06, "loss": 0.1443, "step": 387880 }, { "epoch": 2.305698711890199, "grad_norm": 4.938427448272705, "learning_rate": 6.5261798073802005e-06, "loss": 0.1497, "step": 387890 }, { "epoch": 2.305758153966867, "grad_norm": 3.6369667053222656, "learning_rate": 6.525982216137421e-06, "loss": 0.1684, "step": 387900 }, { "epoch": 2.305817596043535, "grad_norm": 3.4851536750793457, "learning_rate": 6.525784622266719e-06, "loss": 0.1357, "step": 387910 }, { "epoch": 2.3058770381202036, "grad_norm": 4.609744071960449, "learning_rate": 6.525587025768435e-06, "loss": 0.1611, "step": 387920 }, { "epoch": 2.305936480196872, "grad_norm": 3.743835687637329, "learning_rate": 6.525389426642905e-06, "loss": 0.1387, "step": 387930 }, { "epoch": 2.3059959222735404, "grad_norm": 4.809354782104492, "learning_rate": 6.525191824890475e-06, "loss": 0.1735, "step": 387940 }, { "epoch": 2.306055364350209, "grad_norm": 3.7386443614959717, "learning_rate": 6.5249942205114825e-06, "loss": 0.135, "step": 387950 }, { "epoch": 2.3061148064268773, "grad_norm": 4.388959884643555, "learning_rate": 6.524796613506267e-06, "loss": 0.1269, "step": 387960 }, { "epoch": 2.3061742485035457, "grad_norm": 4.595274448394775, "learning_rate": 6.52459900387517e-06, "loss": 0.167, "step": 387970 }, { "epoch": 2.306233690580214, "grad_norm": 3.5992069244384766, "learning_rate": 6.524401391618531e-06, "loss": 0.1316, "step": 387980 }, { "epoch": 2.3062931326568825, "grad_norm": 3.1898317337036133, "learning_rate": 6.524203776736693e-06, "loss": 0.132, "step": 387990 }, { "epoch": 2.306352574733551, "grad_norm": 3.6665244102478027, "learning_rate": 6.524006159229992e-06, "loss": 0.1422, "step": 388000 }, { "epoch": 2.3064120168102193, "grad_norm": 3.3610994815826416, "learning_rate": 6.523808539098772e-06, "loss": 0.1349, "step": 388010 }, { "epoch": 2.3064714588868878, "grad_norm": 3.8730454444885254, "learning_rate": 6.523610916343372e-06, "loss": 0.1527, "step": 388020 }, { "epoch": 2.306530900963556, "grad_norm": 4.936638355255127, "learning_rate": 6.523413290964131e-06, "loss": 0.169, "step": 388030 }, { "epoch": 2.3065903430402246, "grad_norm": 3.313279867172241, "learning_rate": 6.523215662961391e-06, "loss": 0.1278, "step": 388040 }, { "epoch": 2.306649785116893, "grad_norm": 5.141335964202881, "learning_rate": 6.523018032335493e-06, "loss": 0.1441, "step": 388050 }, { "epoch": 2.3067092271935614, "grad_norm": 5.204521179199219, "learning_rate": 6.522820399086775e-06, "loss": 0.1391, "step": 388060 }, { "epoch": 2.3067686692702294, "grad_norm": 4.274316787719727, "learning_rate": 6.522622763215577e-06, "loss": 0.1614, "step": 388070 }, { "epoch": 2.3068281113468982, "grad_norm": 3.5742640495300293, "learning_rate": 6.5224251247222435e-06, "loss": 0.139, "step": 388080 }, { "epoch": 2.306887553423566, "grad_norm": 4.379125118255615, "learning_rate": 6.522227483607112e-06, "loss": 0.1437, "step": 388090 }, { "epoch": 2.3069469955002346, "grad_norm": 5.84907341003418, "learning_rate": 6.522029839870522e-06, "loss": 0.1384, "step": 388100 }, { "epoch": 2.307006437576903, "grad_norm": 4.836632251739502, "learning_rate": 6.521832193512816e-06, "loss": 0.1269, "step": 388110 }, { "epoch": 2.3070658796535715, "grad_norm": 5.037996768951416, "learning_rate": 6.521634544534333e-06, "loss": 0.1625, "step": 388120 }, { "epoch": 2.30712532173024, "grad_norm": 4.224357604980469, "learning_rate": 6.5214368929354136e-06, "loss": 0.1337, "step": 388130 }, { "epoch": 2.3071847638069083, "grad_norm": 3.7795369625091553, "learning_rate": 6.521239238716399e-06, "loss": 0.1666, "step": 388140 }, { "epoch": 2.3072442058835767, "grad_norm": 4.17926025390625, "learning_rate": 6.5210415818776285e-06, "loss": 0.1518, "step": 388150 }, { "epoch": 2.307303647960245, "grad_norm": 4.305144309997559, "learning_rate": 6.520843922419442e-06, "loss": 0.1529, "step": 388160 }, { "epoch": 2.3073630900369135, "grad_norm": 4.91379976272583, "learning_rate": 6.520646260342183e-06, "loss": 0.1518, "step": 388170 }, { "epoch": 2.307422532113582, "grad_norm": 3.6539437770843506, "learning_rate": 6.5204485956461875e-06, "loss": 0.1555, "step": 388180 }, { "epoch": 2.3074819741902504, "grad_norm": 4.722353935241699, "learning_rate": 6.5202509283318e-06, "loss": 0.1323, "step": 388190 }, { "epoch": 2.3075414162669188, "grad_norm": 3.1175379753112793, "learning_rate": 6.520053258399356e-06, "loss": 0.1283, "step": 388200 }, { "epoch": 2.307600858343587, "grad_norm": 4.333893299102783, "learning_rate": 6.5198555858492015e-06, "loss": 0.1529, "step": 388210 }, { "epoch": 2.3076603004202556, "grad_norm": 3.8596198558807373, "learning_rate": 6.519657910681674e-06, "loss": 0.1443, "step": 388220 }, { "epoch": 2.307719742496924, "grad_norm": 2.9093074798583984, "learning_rate": 6.5194602328971135e-06, "loss": 0.1513, "step": 388230 }, { "epoch": 2.3077791845735924, "grad_norm": 4.751795291900635, "learning_rate": 6.519262552495862e-06, "loss": 0.1377, "step": 388240 }, { "epoch": 2.307838626650261, "grad_norm": 5.23760986328125, "learning_rate": 6.519064869478259e-06, "loss": 0.1388, "step": 388250 }, { "epoch": 2.307898068726929, "grad_norm": 4.233001232147217, "learning_rate": 6.518867183844644e-06, "loss": 0.1572, "step": 388260 }, { "epoch": 2.3079575108035977, "grad_norm": 4.982266902923584, "learning_rate": 6.51866949559536e-06, "loss": 0.1415, "step": 388270 }, { "epoch": 2.3080169528802656, "grad_norm": 3.9580724239349365, "learning_rate": 6.518471804730746e-06, "loss": 0.1555, "step": 388280 }, { "epoch": 2.308076394956934, "grad_norm": 4.705195426940918, "learning_rate": 6.518274111251139e-06, "loss": 0.1278, "step": 388290 }, { "epoch": 2.3081358370336025, "grad_norm": 3.442708969116211, "learning_rate": 6.518076415156887e-06, "loss": 0.1246, "step": 388300 }, { "epoch": 2.308195279110271, "grad_norm": 5.543363094329834, "learning_rate": 6.5178787164483246e-06, "loss": 0.1559, "step": 388310 }, { "epoch": 2.3082547211869393, "grad_norm": 6.028523921966553, "learning_rate": 6.517681015125794e-06, "loss": 0.1568, "step": 388320 }, { "epoch": 2.3083141632636077, "grad_norm": 3.549330472946167, "learning_rate": 6.517483311189635e-06, "loss": 0.146, "step": 388330 }, { "epoch": 2.308373605340276, "grad_norm": 3.7467103004455566, "learning_rate": 6.51728560464019e-06, "loss": 0.1506, "step": 388340 }, { "epoch": 2.3084330474169446, "grad_norm": 5.2715163230896, "learning_rate": 6.517087895477797e-06, "loss": 0.1296, "step": 388350 }, { "epoch": 2.308492489493613, "grad_norm": 3.4869136810302734, "learning_rate": 6.5168901837027975e-06, "loss": 0.1463, "step": 388360 }, { "epoch": 2.3085519315702814, "grad_norm": 3.9929299354553223, "learning_rate": 6.516692469315533e-06, "loss": 0.1434, "step": 388370 }, { "epoch": 2.30861137364695, "grad_norm": 3.8258790969848633, "learning_rate": 6.516494752316344e-06, "loss": 0.1606, "step": 388380 }, { "epoch": 2.308670815723618, "grad_norm": 4.996823787689209, "learning_rate": 6.5162970327055674e-06, "loss": 0.1543, "step": 388390 }, { "epoch": 2.3087302578002866, "grad_norm": 4.033003807067871, "learning_rate": 6.516099310483548e-06, "loss": 0.1528, "step": 388400 }, { "epoch": 2.308789699876955, "grad_norm": 5.127874374389648, "learning_rate": 6.5159015856506245e-06, "loss": 0.1588, "step": 388410 }, { "epoch": 2.3088491419536235, "grad_norm": 5.262658596038818, "learning_rate": 6.515703858207137e-06, "loss": 0.1418, "step": 388420 }, { "epoch": 2.308908584030292, "grad_norm": 3.981144666671753, "learning_rate": 6.515506128153428e-06, "loss": 0.1544, "step": 388430 }, { "epoch": 2.3089680261069603, "grad_norm": 3.558344602584839, "learning_rate": 6.515308395489837e-06, "loss": 0.1509, "step": 388440 }, { "epoch": 2.3090274681836283, "grad_norm": 4.124155521392822, "learning_rate": 6.515110660216701e-06, "loss": 0.1497, "step": 388450 }, { "epoch": 2.3090869102602967, "grad_norm": 3.565068006515503, "learning_rate": 6.514912922334366e-06, "loss": 0.1512, "step": 388460 }, { "epoch": 2.309146352336965, "grad_norm": 4.713111400604248, "learning_rate": 6.514715181843171e-06, "loss": 0.1451, "step": 388470 }, { "epoch": 2.3092057944136335, "grad_norm": 5.4283552169799805, "learning_rate": 6.514517438743454e-06, "loss": 0.166, "step": 388480 }, { "epoch": 2.309265236490302, "grad_norm": 4.082490921020508, "learning_rate": 6.514319693035558e-06, "loss": 0.1391, "step": 388490 }, { "epoch": 2.3093246785669703, "grad_norm": 4.128748416900635, "learning_rate": 6.514121944719823e-06, "loss": 0.1496, "step": 388500 }, { "epoch": 2.3093841206436387, "grad_norm": 4.171095371246338, "learning_rate": 6.513924193796588e-06, "loss": 0.1577, "step": 388510 }, { "epoch": 2.309443562720307, "grad_norm": 5.496353626251221, "learning_rate": 6.5137264402661955e-06, "loss": 0.1618, "step": 388520 }, { "epoch": 2.3095030047969756, "grad_norm": 3.8198461532592773, "learning_rate": 6.513528684128987e-06, "loss": 0.1291, "step": 388530 }, { "epoch": 2.309562446873644, "grad_norm": 5.05640172958374, "learning_rate": 6.5133309253853e-06, "loss": 0.1446, "step": 388540 }, { "epoch": 2.3096218889503124, "grad_norm": 4.860316753387451, "learning_rate": 6.513133164035477e-06, "loss": 0.1681, "step": 388550 }, { "epoch": 2.309681331026981, "grad_norm": 5.1787872314453125, "learning_rate": 6.512935400079859e-06, "loss": 0.1708, "step": 388560 }, { "epoch": 2.3097407731036492, "grad_norm": 4.63673734664917, "learning_rate": 6.512737633518784e-06, "loss": 0.1378, "step": 388570 }, { "epoch": 2.3098002151803176, "grad_norm": 3.7056925296783447, "learning_rate": 6.512539864352595e-06, "loss": 0.148, "step": 388580 }, { "epoch": 2.309859657256986, "grad_norm": 4.170291900634766, "learning_rate": 6.512342092581631e-06, "loss": 0.1479, "step": 388590 }, { "epoch": 2.3099190993336545, "grad_norm": 3.999224901199341, "learning_rate": 6.512144318206236e-06, "loss": 0.1411, "step": 388600 }, { "epoch": 2.309978541410323, "grad_norm": 4.159660339355469, "learning_rate": 6.511946541226746e-06, "loss": 0.1503, "step": 388610 }, { "epoch": 2.310037983486991, "grad_norm": 3.669279098510742, "learning_rate": 6.511748761643504e-06, "loss": 0.1466, "step": 388620 }, { "epoch": 2.3100974255636597, "grad_norm": 6.205690860748291, "learning_rate": 6.5115509794568495e-06, "loss": 0.1552, "step": 388630 }, { "epoch": 2.3101568676403277, "grad_norm": 4.93190336227417, "learning_rate": 6.511353194667126e-06, "loss": 0.1483, "step": 388640 }, { "epoch": 2.310216309716996, "grad_norm": 4.24225378036499, "learning_rate": 6.51115540727467e-06, "loss": 0.136, "step": 388650 }, { "epoch": 2.3102757517936645, "grad_norm": 3.469332218170166, "learning_rate": 6.510957617279825e-06, "loss": 0.1449, "step": 388660 }, { "epoch": 2.310335193870333, "grad_norm": 5.455060005187988, "learning_rate": 6.510759824682931e-06, "loss": 0.1392, "step": 388670 }, { "epoch": 2.3103946359470013, "grad_norm": 3.850411891937256, "learning_rate": 6.510562029484328e-06, "loss": 0.1495, "step": 388680 }, { "epoch": 2.3104540780236698, "grad_norm": 3.818498134613037, "learning_rate": 6.510364231684356e-06, "loss": 0.1503, "step": 388690 }, { "epoch": 2.310513520100338, "grad_norm": 3.810978412628174, "learning_rate": 6.510166431283358e-06, "loss": 0.1351, "step": 388700 }, { "epoch": 2.3105729621770066, "grad_norm": 4.213858604431152, "learning_rate": 6.509968628281672e-06, "loss": 0.1595, "step": 388710 }, { "epoch": 2.310632404253675, "grad_norm": 4.238848686218262, "learning_rate": 6.509770822679641e-06, "loss": 0.1413, "step": 388720 }, { "epoch": 2.3106918463303434, "grad_norm": 3.0653622150421143, "learning_rate": 6.509573014477604e-06, "loss": 0.1297, "step": 388730 }, { "epoch": 2.310751288407012, "grad_norm": 5.279775619506836, "learning_rate": 6.509375203675902e-06, "loss": 0.1577, "step": 388740 }, { "epoch": 2.3108107304836802, "grad_norm": 5.0495734214782715, "learning_rate": 6.5091773902748755e-06, "loss": 0.1592, "step": 388750 }, { "epoch": 2.3108701725603487, "grad_norm": 3.403367280960083, "learning_rate": 6.508979574274866e-06, "loss": 0.1362, "step": 388760 }, { "epoch": 2.310929614637017, "grad_norm": 4.2466535568237305, "learning_rate": 6.508781755676215e-06, "loss": 0.1327, "step": 388770 }, { "epoch": 2.3109890567136855, "grad_norm": 4.712085723876953, "learning_rate": 6.508583934479258e-06, "loss": 0.1724, "step": 388780 }, { "epoch": 2.311048498790354, "grad_norm": 4.467284679412842, "learning_rate": 6.5083861106843425e-06, "loss": 0.1283, "step": 388790 }, { "epoch": 2.3111079408670223, "grad_norm": 5.02783203125, "learning_rate": 6.5081882842918055e-06, "loss": 0.1554, "step": 388800 }, { "epoch": 2.3111673829436903, "grad_norm": 4.376713275909424, "learning_rate": 6.5079904553019876e-06, "loss": 0.144, "step": 388810 }, { "epoch": 2.311226825020359, "grad_norm": 2.766528606414795, "learning_rate": 6.507792623715232e-06, "loss": 0.132, "step": 388820 }, { "epoch": 2.311286267097027, "grad_norm": 4.531231880187988, "learning_rate": 6.507594789531877e-06, "loss": 0.1532, "step": 388830 }, { "epoch": 2.3113457091736955, "grad_norm": 5.854112148284912, "learning_rate": 6.5073969527522615e-06, "loss": 0.1662, "step": 388840 }, { "epoch": 2.311405151250364, "grad_norm": 5.017062187194824, "learning_rate": 6.5071991133767295e-06, "loss": 0.1445, "step": 388850 }, { "epoch": 2.3114645933270324, "grad_norm": 4.875837802886963, "learning_rate": 6.507001271405623e-06, "loss": 0.1486, "step": 388860 }, { "epoch": 2.3115240354037008, "grad_norm": 3.4776875972747803, "learning_rate": 6.50680342683928e-06, "loss": 0.1527, "step": 388870 }, { "epoch": 2.311583477480369, "grad_norm": 4.415742874145508, "learning_rate": 6.50660557967804e-06, "loss": 0.1386, "step": 388880 }, { "epoch": 2.3116429195570376, "grad_norm": 5.053014278411865, "learning_rate": 6.506407729922246e-06, "loss": 0.1459, "step": 388890 }, { "epoch": 2.311702361633706, "grad_norm": 4.057370662689209, "learning_rate": 6.506209877572239e-06, "loss": 0.1572, "step": 388900 }, { "epoch": 2.3117618037103744, "grad_norm": 4.09083366394043, "learning_rate": 6.5060120226283585e-06, "loss": 0.1514, "step": 388910 }, { "epoch": 2.311821245787043, "grad_norm": 3.867722749710083, "learning_rate": 6.505814165090946e-06, "loss": 0.1617, "step": 388920 }, { "epoch": 2.3118806878637113, "grad_norm": 3.874002456665039, "learning_rate": 6.50561630496034e-06, "loss": 0.1433, "step": 388930 }, { "epoch": 2.3119401299403797, "grad_norm": 3.8991687297821045, "learning_rate": 6.505418442236885e-06, "loss": 0.1603, "step": 388940 }, { "epoch": 2.311999572017048, "grad_norm": 3.6005003452301025, "learning_rate": 6.505220576920919e-06, "loss": 0.1328, "step": 388950 }, { "epoch": 2.3120590140937165, "grad_norm": 4.093496322631836, "learning_rate": 6.505022709012784e-06, "loss": 0.1431, "step": 388960 }, { "epoch": 2.312118456170385, "grad_norm": 4.396594047546387, "learning_rate": 6.50482483851282e-06, "loss": 0.1464, "step": 388970 }, { "epoch": 2.3121778982470533, "grad_norm": 4.830268383026123, "learning_rate": 6.504626965421368e-06, "loss": 0.13, "step": 388980 }, { "epoch": 2.3122373403237217, "grad_norm": 5.186335563659668, "learning_rate": 6.5044290897387685e-06, "loss": 0.1471, "step": 388990 }, { "epoch": 2.3122967824003897, "grad_norm": 4.2081499099731445, "learning_rate": 6.5042312114653634e-06, "loss": 0.1415, "step": 389000 }, { "epoch": 2.3123562244770586, "grad_norm": 4.583055019378662, "learning_rate": 6.504033330601491e-06, "loss": 0.1546, "step": 389010 }, { "epoch": 2.3124156665537265, "grad_norm": 4.086600303649902, "learning_rate": 6.503835447147496e-06, "loss": 0.1395, "step": 389020 }, { "epoch": 2.312475108630395, "grad_norm": 4.613631248474121, "learning_rate": 6.5036375611037176e-06, "loss": 0.1363, "step": 389030 }, { "epoch": 2.3125345507070634, "grad_norm": 4.329595565795898, "learning_rate": 6.503439672470493e-06, "loss": 0.1315, "step": 389040 }, { "epoch": 2.312593992783732, "grad_norm": 3.89505934715271, "learning_rate": 6.503241781248168e-06, "loss": 0.1448, "step": 389050 }, { "epoch": 2.3126534348604, "grad_norm": 4.356289386749268, "learning_rate": 6.503043887437079e-06, "loss": 0.1426, "step": 389060 }, { "epoch": 2.3127128769370686, "grad_norm": 4.366225719451904, "learning_rate": 6.50284599103757e-06, "loss": 0.1402, "step": 389070 }, { "epoch": 2.312772319013737, "grad_norm": 3.7947936058044434, "learning_rate": 6.502648092049982e-06, "loss": 0.1355, "step": 389080 }, { "epoch": 2.3128317610904054, "grad_norm": 3.7786195278167725, "learning_rate": 6.502450190474655e-06, "loss": 0.1425, "step": 389090 }, { "epoch": 2.312891203167074, "grad_norm": 3.2423219680786133, "learning_rate": 6.502252286311928e-06, "loss": 0.1332, "step": 389100 }, { "epoch": 2.3129506452437423, "grad_norm": 3.139052629470825, "learning_rate": 6.502054379562144e-06, "loss": 0.1547, "step": 389110 }, { "epoch": 2.3130100873204107, "grad_norm": 6.3175201416015625, "learning_rate": 6.501856470225644e-06, "loss": 0.1585, "step": 389120 }, { "epoch": 2.313069529397079, "grad_norm": 5.579424858093262, "learning_rate": 6.501658558302766e-06, "loss": 0.1669, "step": 389130 }, { "epoch": 2.3131289714737475, "grad_norm": 4.17996072769165, "learning_rate": 6.5014606437938545e-06, "loss": 0.1555, "step": 389140 }, { "epoch": 2.313188413550416, "grad_norm": 4.635247230529785, "learning_rate": 6.501262726699248e-06, "loss": 0.1497, "step": 389150 }, { "epoch": 2.3132478556270843, "grad_norm": 3.2339463233947754, "learning_rate": 6.501064807019287e-06, "loss": 0.1484, "step": 389160 }, { "epoch": 2.3133072977037528, "grad_norm": 4.373706340789795, "learning_rate": 6.500866884754315e-06, "loss": 0.1318, "step": 389170 }, { "epoch": 2.313366739780421, "grad_norm": 5.693207740783691, "learning_rate": 6.50066895990467e-06, "loss": 0.1615, "step": 389180 }, { "epoch": 2.313426181857089, "grad_norm": 3.826632022857666, "learning_rate": 6.500471032470694e-06, "loss": 0.1392, "step": 389190 }, { "epoch": 2.3134856239337576, "grad_norm": 5.01457405090332, "learning_rate": 6.5002731024527276e-06, "loss": 0.1499, "step": 389200 }, { "epoch": 2.313545066010426, "grad_norm": 3.3928444385528564, "learning_rate": 6.500075169851113e-06, "loss": 0.1456, "step": 389210 }, { "epoch": 2.3136045080870944, "grad_norm": 4.512001991271973, "learning_rate": 6.499877234666191e-06, "loss": 0.1592, "step": 389220 }, { "epoch": 2.313663950163763, "grad_norm": 4.128976821899414, "learning_rate": 6.499679296898299e-06, "loss": 0.1591, "step": 389230 }, { "epoch": 2.313723392240431, "grad_norm": 4.320391654968262, "learning_rate": 6.499481356547781e-06, "loss": 0.1466, "step": 389240 }, { "epoch": 2.3137828343170996, "grad_norm": 3.415628671646118, "learning_rate": 6.499283413614979e-06, "loss": 0.1551, "step": 389250 }, { "epoch": 2.313842276393768, "grad_norm": 3.932793140411377, "learning_rate": 6.499085468100229e-06, "loss": 0.1481, "step": 389260 }, { "epoch": 2.3139017184704365, "grad_norm": 5.264810085296631, "learning_rate": 6.498887520003877e-06, "loss": 0.163, "step": 389270 }, { "epoch": 2.313961160547105, "grad_norm": 4.428195476531982, "learning_rate": 6.498689569326261e-06, "loss": 0.1506, "step": 389280 }, { "epoch": 2.3140206026237733, "grad_norm": 4.5138444900512695, "learning_rate": 6.4984916160677235e-06, "loss": 0.1553, "step": 389290 }, { "epoch": 2.3140800447004417, "grad_norm": 4.8764424324035645, "learning_rate": 6.498293660228603e-06, "loss": 0.1666, "step": 389300 }, { "epoch": 2.31413948677711, "grad_norm": 5.514697551727295, "learning_rate": 6.4980957018092435e-06, "loss": 0.1497, "step": 389310 }, { "epoch": 2.3141989288537785, "grad_norm": 3.755157232284546, "learning_rate": 6.497897740809985e-06, "loss": 0.1501, "step": 389320 }, { "epoch": 2.314258370930447, "grad_norm": 3.4633193016052246, "learning_rate": 6.497699777231167e-06, "loss": 0.1436, "step": 389330 }, { "epoch": 2.3143178130071154, "grad_norm": 2.2937192916870117, "learning_rate": 6.497501811073131e-06, "loss": 0.1356, "step": 389340 }, { "epoch": 2.314377255083784, "grad_norm": 5.830185890197754, "learning_rate": 6.4973038423362185e-06, "loss": 0.1427, "step": 389350 }, { "epoch": 2.3144366971604518, "grad_norm": 4.137892723083496, "learning_rate": 6.49710587102077e-06, "loss": 0.1361, "step": 389360 }, { "epoch": 2.3144961392371206, "grad_norm": 3.4278922080993652, "learning_rate": 6.496907897127127e-06, "loss": 0.1322, "step": 389370 }, { "epoch": 2.3145555813137886, "grad_norm": 3.439248561859131, "learning_rate": 6.49670992065563e-06, "loss": 0.1577, "step": 389380 }, { "epoch": 2.314615023390457, "grad_norm": 4.613590717315674, "learning_rate": 6.496511941606619e-06, "loss": 0.1446, "step": 389390 }, { "epoch": 2.3146744654671254, "grad_norm": 4.142134189605713, "learning_rate": 6.496313959980436e-06, "loss": 0.1383, "step": 389400 }, { "epoch": 2.314733907543794, "grad_norm": 4.993930339813232, "learning_rate": 6.4961159757774225e-06, "loss": 0.1446, "step": 389410 }, { "epoch": 2.3147933496204622, "grad_norm": 4.377226829528809, "learning_rate": 6.4959179889979195e-06, "loss": 0.1612, "step": 389420 }, { "epoch": 2.3148527916971307, "grad_norm": 3.5536627769470215, "learning_rate": 6.495719999642266e-06, "loss": 0.1531, "step": 389430 }, { "epoch": 2.314912233773799, "grad_norm": 4.669992923736572, "learning_rate": 6.495522007710805e-06, "loss": 0.1613, "step": 389440 }, { "epoch": 2.3149716758504675, "grad_norm": 3.6456801891326904, "learning_rate": 6.495324013203877e-06, "loss": 0.1293, "step": 389450 }, { "epoch": 2.315031117927136, "grad_norm": 4.514181613922119, "learning_rate": 6.495126016121821e-06, "loss": 0.1285, "step": 389460 }, { "epoch": 2.3150905600038043, "grad_norm": 3.991299867630005, "learning_rate": 6.494928016464981e-06, "loss": 0.1262, "step": 389470 }, { "epoch": 2.3151500020804727, "grad_norm": 5.815481662750244, "learning_rate": 6.494730014233697e-06, "loss": 0.1338, "step": 389480 }, { "epoch": 2.315209444157141, "grad_norm": 3.637805223464966, "learning_rate": 6.494532009428307e-06, "loss": 0.1315, "step": 389490 }, { "epoch": 2.3152688862338096, "grad_norm": 4.969464302062988, "learning_rate": 6.494334002049155e-06, "loss": 0.147, "step": 389500 }, { "epoch": 2.315328328310478, "grad_norm": 4.881374835968018, "learning_rate": 6.494135992096584e-06, "loss": 0.1447, "step": 389510 }, { "epoch": 2.3153877703871464, "grad_norm": 3.8268790245056152, "learning_rate": 6.493937979570931e-06, "loss": 0.1393, "step": 389520 }, { "epoch": 2.315447212463815, "grad_norm": 4.135903358459473, "learning_rate": 6.493739964472538e-06, "loss": 0.1394, "step": 389530 }, { "epoch": 2.315506654540483, "grad_norm": 5.349308490753174, "learning_rate": 6.493541946801748e-06, "loss": 0.1597, "step": 389540 }, { "epoch": 2.315566096617151, "grad_norm": 3.3518459796905518, "learning_rate": 6.493343926558901e-06, "loss": 0.1439, "step": 389550 }, { "epoch": 2.31562553869382, "grad_norm": 3.9026103019714355, "learning_rate": 6.493145903744336e-06, "loss": 0.1809, "step": 389560 }, { "epoch": 2.315684980770488, "grad_norm": 3.1332778930664062, "learning_rate": 6.492947878358395e-06, "loss": 0.121, "step": 389570 }, { "epoch": 2.3157444228471564, "grad_norm": 3.2252957820892334, "learning_rate": 6.4927498504014215e-06, "loss": 0.1488, "step": 389580 }, { "epoch": 2.315803864923825, "grad_norm": 4.013742923736572, "learning_rate": 6.492551819873754e-06, "loss": 0.1357, "step": 389590 }, { "epoch": 2.3158633070004933, "grad_norm": 3.8251709938049316, "learning_rate": 6.492353786775734e-06, "loss": 0.1232, "step": 389600 }, { "epoch": 2.3159227490771617, "grad_norm": 3.9287285804748535, "learning_rate": 6.492155751107702e-06, "loss": 0.1514, "step": 389610 }, { "epoch": 2.31598219115383, "grad_norm": 3.804861307144165, "learning_rate": 6.491957712869999e-06, "loss": 0.1532, "step": 389620 }, { "epoch": 2.3160416332304985, "grad_norm": 3.7693848609924316, "learning_rate": 6.49175967206297e-06, "loss": 0.1468, "step": 389630 }, { "epoch": 2.316101075307167, "grad_norm": 3.8475589752197266, "learning_rate": 6.491561628686951e-06, "loss": 0.1343, "step": 389640 }, { "epoch": 2.3161605173838353, "grad_norm": 4.437283992767334, "learning_rate": 6.491363582742285e-06, "loss": 0.1527, "step": 389650 }, { "epoch": 2.3162199594605037, "grad_norm": 4.27617073059082, "learning_rate": 6.491165534229313e-06, "loss": 0.1821, "step": 389660 }, { "epoch": 2.316279401537172, "grad_norm": 4.816722869873047, "learning_rate": 6.490967483148376e-06, "loss": 0.1452, "step": 389670 }, { "epoch": 2.3163388436138406, "grad_norm": 4.491433620452881, "learning_rate": 6.490769429499816e-06, "loss": 0.1527, "step": 389680 }, { "epoch": 2.316398285690509, "grad_norm": 4.043378829956055, "learning_rate": 6.490571373283972e-06, "loss": 0.1538, "step": 389690 }, { "epoch": 2.3164577277671774, "grad_norm": 4.408032417297363, "learning_rate": 6.490373314501186e-06, "loss": 0.1395, "step": 389700 }, { "epoch": 2.316517169843846, "grad_norm": 4.709848403930664, "learning_rate": 6.4901752531518e-06, "loss": 0.1474, "step": 389710 }, { "epoch": 2.3165766119205142, "grad_norm": 5.308887958526611, "learning_rate": 6.489977189236154e-06, "loss": 0.1502, "step": 389720 }, { "epoch": 2.3166360539971826, "grad_norm": 4.656457901000977, "learning_rate": 6.489779122754589e-06, "loss": 0.1375, "step": 389730 }, { "epoch": 2.3166954960738506, "grad_norm": 4.3783698081970215, "learning_rate": 6.489581053707448e-06, "loss": 0.144, "step": 389740 }, { "epoch": 2.3167549381505195, "grad_norm": 3.4901013374328613, "learning_rate": 6.48938298209507e-06, "loss": 0.1309, "step": 389750 }, { "epoch": 2.3168143802271874, "grad_norm": 4.592144966125488, "learning_rate": 6.4891849079177975e-06, "loss": 0.1511, "step": 389760 }, { "epoch": 2.316873822303856, "grad_norm": 4.040950298309326, "learning_rate": 6.48898683117597e-06, "loss": 0.1599, "step": 389770 }, { "epoch": 2.3169332643805243, "grad_norm": 2.722885847091675, "learning_rate": 6.48878875186993e-06, "loss": 0.1274, "step": 389780 }, { "epoch": 2.3169927064571927, "grad_norm": 3.66455078125, "learning_rate": 6.488590670000018e-06, "loss": 0.1406, "step": 389790 }, { "epoch": 2.317052148533861, "grad_norm": 4.94706916809082, "learning_rate": 6.488392585566575e-06, "loss": 0.1397, "step": 389800 }, { "epoch": 2.3171115906105295, "grad_norm": 4.367183208465576, "learning_rate": 6.4881944985699415e-06, "loss": 0.1649, "step": 389810 }, { "epoch": 2.317171032687198, "grad_norm": 4.282546043395996, "learning_rate": 6.487996409010462e-06, "loss": 0.137, "step": 389820 }, { "epoch": 2.3172304747638663, "grad_norm": 5.877692699432373, "learning_rate": 6.4877983168884725e-06, "loss": 0.1431, "step": 389830 }, { "epoch": 2.3172899168405348, "grad_norm": 4.923125267028809, "learning_rate": 6.487600222204318e-06, "loss": 0.1384, "step": 389840 }, { "epoch": 2.317349358917203, "grad_norm": 3.882004737854004, "learning_rate": 6.487402124958338e-06, "loss": 0.1442, "step": 389850 }, { "epoch": 2.3174088009938716, "grad_norm": 2.8871185779571533, "learning_rate": 6.487204025150875e-06, "loss": 0.1673, "step": 389860 }, { "epoch": 2.31746824307054, "grad_norm": 4.177868366241455, "learning_rate": 6.487005922782269e-06, "loss": 0.1478, "step": 389870 }, { "epoch": 2.3175276851472084, "grad_norm": 4.423583984375, "learning_rate": 6.486807817852861e-06, "loss": 0.1652, "step": 389880 }, { "epoch": 2.317587127223877, "grad_norm": 3.009693145751953, "learning_rate": 6.486609710362992e-06, "loss": 0.144, "step": 389890 }, { "epoch": 2.3176465693005452, "grad_norm": 4.283253192901611, "learning_rate": 6.486411600313005e-06, "loss": 0.1512, "step": 389900 }, { "epoch": 2.3177060113772137, "grad_norm": 3.8966891765594482, "learning_rate": 6.486213487703239e-06, "loss": 0.1332, "step": 389910 }, { "epoch": 2.317765453453882, "grad_norm": 4.912392616271973, "learning_rate": 6.486015372534036e-06, "loss": 0.1512, "step": 389920 }, { "epoch": 2.31782489553055, "grad_norm": 3.7537269592285156, "learning_rate": 6.4858172548057375e-06, "loss": 0.1425, "step": 389930 }, { "epoch": 2.3178843376072185, "grad_norm": 5.120469093322754, "learning_rate": 6.4856191345186835e-06, "loss": 0.1587, "step": 389940 }, { "epoch": 2.317943779683887, "grad_norm": 4.994940757751465, "learning_rate": 6.4854210116732166e-06, "loss": 0.172, "step": 389950 }, { "epoch": 2.3180032217605553, "grad_norm": 4.379574298858643, "learning_rate": 6.485222886269679e-06, "loss": 0.1376, "step": 389960 }, { "epoch": 2.3180626638372237, "grad_norm": 3.804100513458252, "learning_rate": 6.485024758308409e-06, "loss": 0.1475, "step": 389970 }, { "epoch": 2.318122105913892, "grad_norm": 4.452564716339111, "learning_rate": 6.484826627789748e-06, "loss": 0.1427, "step": 389980 }, { "epoch": 2.3181815479905605, "grad_norm": 3.8046646118164062, "learning_rate": 6.48462849471404e-06, "loss": 0.1176, "step": 389990 }, { "epoch": 2.318240990067229, "grad_norm": 3.9324417114257812, "learning_rate": 6.484430359081626e-06, "loss": 0.1486, "step": 390000 }, { "epoch": 2.3183004321438974, "grad_norm": 4.119327068328857, "learning_rate": 6.484232220892843e-06, "loss": 0.148, "step": 390010 }, { "epoch": 2.3183598742205658, "grad_norm": 3.4672248363494873, "learning_rate": 6.484034080148036e-06, "loss": 0.1676, "step": 390020 }, { "epoch": 2.318419316297234, "grad_norm": 5.162176609039307, "learning_rate": 6.483835936847546e-06, "loss": 0.1398, "step": 390030 }, { "epoch": 2.3184787583739026, "grad_norm": 3.8471295833587646, "learning_rate": 6.483637790991712e-06, "loss": 0.1416, "step": 390040 }, { "epoch": 2.318538200450571, "grad_norm": 4.126700401306152, "learning_rate": 6.4834396425808775e-06, "loss": 0.1426, "step": 390050 }, { "epoch": 2.3185976425272394, "grad_norm": 4.208444118499756, "learning_rate": 6.483241491615383e-06, "loss": 0.1652, "step": 390060 }, { "epoch": 2.318657084603908, "grad_norm": 4.691653728485107, "learning_rate": 6.483043338095569e-06, "loss": 0.1258, "step": 390070 }, { "epoch": 2.3187165266805763, "grad_norm": 4.78480863571167, "learning_rate": 6.482845182021779e-06, "loss": 0.1453, "step": 390080 }, { "epoch": 2.3187759687572447, "grad_norm": 5.817960262298584, "learning_rate": 6.482647023394352e-06, "loss": 0.1595, "step": 390090 }, { "epoch": 2.3188354108339126, "grad_norm": 5.100444793701172, "learning_rate": 6.48244886221363e-06, "loss": 0.1502, "step": 390100 }, { "epoch": 2.3188948529105815, "grad_norm": 2.956987142562866, "learning_rate": 6.482250698479953e-06, "loss": 0.1553, "step": 390110 }, { "epoch": 2.3189542949872495, "grad_norm": 5.115243434906006, "learning_rate": 6.482052532193664e-06, "loss": 0.1438, "step": 390120 }, { "epoch": 2.319013737063918, "grad_norm": 4.230770587921143, "learning_rate": 6.4818543633551045e-06, "loss": 0.15, "step": 390130 }, { "epoch": 2.3190731791405863, "grad_norm": 3.5370473861694336, "learning_rate": 6.481656191964614e-06, "loss": 0.1671, "step": 390140 }, { "epoch": 2.3191326212172547, "grad_norm": 3.7721710205078125, "learning_rate": 6.481458018022535e-06, "loss": 0.1433, "step": 390150 }, { "epoch": 2.319192063293923, "grad_norm": 4.753731727600098, "learning_rate": 6.481259841529208e-06, "loss": 0.1498, "step": 390160 }, { "epoch": 2.3192515053705915, "grad_norm": 6.067558288574219, "learning_rate": 6.481061662484977e-06, "loss": 0.1709, "step": 390170 }, { "epoch": 2.31931094744726, "grad_norm": 3.8227717876434326, "learning_rate": 6.480863480890178e-06, "loss": 0.1448, "step": 390180 }, { "epoch": 2.3193703895239284, "grad_norm": 4.5024542808532715, "learning_rate": 6.480665296745158e-06, "loss": 0.1414, "step": 390190 }, { "epoch": 2.319429831600597, "grad_norm": 4.850307464599609, "learning_rate": 6.480467110050255e-06, "loss": 0.1557, "step": 390200 }, { "epoch": 2.319489273677265, "grad_norm": 4.007055759429932, "learning_rate": 6.48026892080581e-06, "loss": 0.1473, "step": 390210 }, { "epoch": 2.3195487157539336, "grad_norm": 5.209262371063232, "learning_rate": 6.480070729012167e-06, "loss": 0.1468, "step": 390220 }, { "epoch": 2.319608157830602, "grad_norm": 3.9002552032470703, "learning_rate": 6.479872534669664e-06, "loss": 0.1418, "step": 390230 }, { "epoch": 2.3196675999072704, "grad_norm": 3.6063926219940186, "learning_rate": 6.479674337778644e-06, "loss": 0.1467, "step": 390240 }, { "epoch": 2.319727041983939, "grad_norm": 4.3720855712890625, "learning_rate": 6.4794761383394485e-06, "loss": 0.1532, "step": 390250 }, { "epoch": 2.3197864840606073, "grad_norm": 3.766533851623535, "learning_rate": 6.4792779363524195e-06, "loss": 0.1372, "step": 390260 }, { "epoch": 2.3198459261372757, "grad_norm": 4.411657810211182, "learning_rate": 6.479079731817896e-06, "loss": 0.1473, "step": 390270 }, { "epoch": 2.319905368213944, "grad_norm": 4.973952770233154, "learning_rate": 6.478881524736221e-06, "loss": 0.1491, "step": 390280 }, { "epoch": 2.319964810290612, "grad_norm": 3.6722238063812256, "learning_rate": 6.478683315107737e-06, "loss": 0.1404, "step": 390290 }, { "epoch": 2.320024252367281, "grad_norm": 4.387905120849609, "learning_rate": 6.4784851029327834e-06, "loss": 0.1376, "step": 390300 }, { "epoch": 2.320083694443949, "grad_norm": 4.788249492645264, "learning_rate": 6.4782868882117e-06, "loss": 0.1482, "step": 390310 }, { "epoch": 2.3201431365206173, "grad_norm": 5.483311176300049, "learning_rate": 6.4780886709448335e-06, "loss": 0.1435, "step": 390320 }, { "epoch": 2.3202025785972857, "grad_norm": 5.942733287811279, "learning_rate": 6.4778904511325205e-06, "loss": 0.1509, "step": 390330 }, { "epoch": 2.320262020673954, "grad_norm": 5.496975898742676, "learning_rate": 6.477692228775102e-06, "loss": 0.1824, "step": 390340 }, { "epoch": 2.3203214627506226, "grad_norm": 4.690658092498779, "learning_rate": 6.477494003872923e-06, "loss": 0.1414, "step": 390350 }, { "epoch": 2.320380904827291, "grad_norm": 2.91274356842041, "learning_rate": 6.477295776426323e-06, "loss": 0.1552, "step": 390360 }, { "epoch": 2.3204403469039594, "grad_norm": 4.449074745178223, "learning_rate": 6.477097546435642e-06, "loss": 0.1478, "step": 390370 }, { "epoch": 2.320499788980628, "grad_norm": 3.912421464920044, "learning_rate": 6.476899313901224e-06, "loss": 0.1397, "step": 390380 }, { "epoch": 2.3205592310572962, "grad_norm": 5.497218132019043, "learning_rate": 6.476701078823408e-06, "loss": 0.1575, "step": 390390 }, { "epoch": 2.3206186731339646, "grad_norm": 4.399506568908691, "learning_rate": 6.476502841202538e-06, "loss": 0.1398, "step": 390400 }, { "epoch": 2.320678115210633, "grad_norm": 3.6918678283691406, "learning_rate": 6.476304601038954e-06, "loss": 0.1361, "step": 390410 }, { "epoch": 2.3207375572873015, "grad_norm": 4.693243503570557, "learning_rate": 6.476106358332997e-06, "loss": 0.14, "step": 390420 }, { "epoch": 2.32079699936397, "grad_norm": 4.853455066680908, "learning_rate": 6.475908113085008e-06, "loss": 0.1531, "step": 390430 }, { "epoch": 2.3208564414406383, "grad_norm": 4.4318060874938965, "learning_rate": 6.47570986529533e-06, "loss": 0.1659, "step": 390440 }, { "epoch": 2.3209158835173067, "grad_norm": 4.512042045593262, "learning_rate": 6.475511614964304e-06, "loss": 0.1781, "step": 390450 }, { "epoch": 2.320975325593975, "grad_norm": 6.072170257568359, "learning_rate": 6.4753133620922695e-06, "loss": 0.1551, "step": 390460 }, { "epoch": 2.3210347676706435, "grad_norm": 5.851367950439453, "learning_rate": 6.475115106679571e-06, "loss": 0.1393, "step": 390470 }, { "epoch": 2.3210942097473115, "grad_norm": 4.487708568572998, "learning_rate": 6.4749168487265465e-06, "loss": 0.1326, "step": 390480 }, { "epoch": 2.3211536518239804, "grad_norm": 5.5067362785339355, "learning_rate": 6.47471858823354e-06, "loss": 0.1639, "step": 390490 }, { "epoch": 2.3212130939006483, "grad_norm": 3.3751964569091797, "learning_rate": 6.47452032520089e-06, "loss": 0.1332, "step": 390500 }, { "epoch": 2.3212725359773168, "grad_norm": 5.407454013824463, "learning_rate": 6.474322059628944e-06, "loss": 0.1641, "step": 390510 }, { "epoch": 2.321331978053985, "grad_norm": 3.6572818756103516, "learning_rate": 6.474123791518038e-06, "loss": 0.1459, "step": 390520 }, { "epoch": 2.3213914201306536, "grad_norm": 5.2962751388549805, "learning_rate": 6.473925520868514e-06, "loss": 0.1622, "step": 390530 }, { "epoch": 2.321450862207322, "grad_norm": 5.1321330070495605, "learning_rate": 6.4737272476807144e-06, "loss": 0.1552, "step": 390540 }, { "epoch": 2.3215103042839904, "grad_norm": 4.296731472015381, "learning_rate": 6.473528971954982e-06, "loss": 0.1323, "step": 390550 }, { "epoch": 2.321569746360659, "grad_norm": 6.351116180419922, "learning_rate": 6.4733306936916555e-06, "loss": 0.1483, "step": 390560 }, { "epoch": 2.3216291884373272, "grad_norm": 5.801559925079346, "learning_rate": 6.473132412891079e-06, "loss": 0.1452, "step": 390570 }, { "epoch": 2.3216886305139957, "grad_norm": 4.882193565368652, "learning_rate": 6.472934129553592e-06, "loss": 0.1423, "step": 390580 }, { "epoch": 2.321748072590664, "grad_norm": 4.023202896118164, "learning_rate": 6.472735843679536e-06, "loss": 0.1622, "step": 390590 }, { "epoch": 2.3218075146673325, "grad_norm": 5.635453224182129, "learning_rate": 6.472537555269253e-06, "loss": 0.1697, "step": 390600 }, { "epoch": 2.321866956744001, "grad_norm": 4.325700759887695, "learning_rate": 6.472339264323086e-06, "loss": 0.1412, "step": 390610 }, { "epoch": 2.3219263988206693, "grad_norm": 4.225533485412598, "learning_rate": 6.472140970841376e-06, "loss": 0.1624, "step": 390620 }, { "epoch": 2.3219858408973377, "grad_norm": 3.763803005218506, "learning_rate": 6.471942674824461e-06, "loss": 0.144, "step": 390630 }, { "epoch": 2.322045282974006, "grad_norm": 4.961495399475098, "learning_rate": 6.471744376272687e-06, "loss": 0.1316, "step": 390640 }, { "epoch": 2.3221047250506746, "grad_norm": 3.1528866291046143, "learning_rate": 6.471546075186393e-06, "loss": 0.1467, "step": 390650 }, { "epoch": 2.322164167127343, "grad_norm": 3.7182958126068115, "learning_rate": 6.471347771565921e-06, "loss": 0.1567, "step": 390660 }, { "epoch": 2.322223609204011, "grad_norm": 3.8081586360931396, "learning_rate": 6.471149465411612e-06, "loss": 0.1479, "step": 390670 }, { "epoch": 2.3222830512806794, "grad_norm": 5.42211389541626, "learning_rate": 6.470951156723811e-06, "loss": 0.1519, "step": 390680 }, { "epoch": 2.3223424933573478, "grad_norm": 4.499882698059082, "learning_rate": 6.470752845502852e-06, "loss": 0.1306, "step": 390690 }, { "epoch": 2.322401935434016, "grad_norm": 2.7577176094055176, "learning_rate": 6.4705545317490844e-06, "loss": 0.1452, "step": 390700 }, { "epoch": 2.3224613775106846, "grad_norm": 4.740284442901611, "learning_rate": 6.470356215462845e-06, "loss": 0.1355, "step": 390710 }, { "epoch": 2.322520819587353, "grad_norm": 4.498694896697998, "learning_rate": 6.470157896644478e-06, "loss": 0.1269, "step": 390720 }, { "epoch": 2.3225802616640214, "grad_norm": 4.96042013168335, "learning_rate": 6.469959575294321e-06, "loss": 0.1337, "step": 390730 }, { "epoch": 2.32263970374069, "grad_norm": 3.255828619003296, "learning_rate": 6.469761251412721e-06, "loss": 0.1378, "step": 390740 }, { "epoch": 2.3226991458173583, "grad_norm": 4.318159580230713, "learning_rate": 6.469562925000016e-06, "loss": 0.172, "step": 390750 }, { "epoch": 2.3227585878940267, "grad_norm": 4.5002570152282715, "learning_rate": 6.469364596056547e-06, "loss": 0.1517, "step": 390760 }, { "epoch": 2.322818029970695, "grad_norm": 5.687478065490723, "learning_rate": 6.469166264582659e-06, "loss": 0.1475, "step": 390770 }, { "epoch": 2.3228774720473635, "grad_norm": 4.291879177093506, "learning_rate": 6.468967930578691e-06, "loss": 0.1478, "step": 390780 }, { "epoch": 2.322936914124032, "grad_norm": 5.195651531219482, "learning_rate": 6.468769594044984e-06, "loss": 0.1594, "step": 390790 }, { "epoch": 2.3229963562007003, "grad_norm": 3.910459041595459, "learning_rate": 6.46857125498188e-06, "loss": 0.1431, "step": 390800 }, { "epoch": 2.3230557982773687, "grad_norm": 3.265545606613159, "learning_rate": 6.4683729133897225e-06, "loss": 0.1579, "step": 390810 }, { "epoch": 2.323115240354037, "grad_norm": 4.061892986297607, "learning_rate": 6.4681745692688505e-06, "loss": 0.1453, "step": 390820 }, { "epoch": 2.3231746824307056, "grad_norm": 4.002913475036621, "learning_rate": 6.467976222619607e-06, "loss": 0.135, "step": 390830 }, { "epoch": 2.3232341245073735, "grad_norm": 3.5647425651550293, "learning_rate": 6.467777873442333e-06, "loss": 0.147, "step": 390840 }, { "epoch": 2.3232935665840424, "grad_norm": 5.180851459503174, "learning_rate": 6.467579521737371e-06, "loss": 0.1368, "step": 390850 }, { "epoch": 2.3233530086607104, "grad_norm": 3.9584264755249023, "learning_rate": 6.467381167505062e-06, "loss": 0.1253, "step": 390860 }, { "epoch": 2.323412450737379, "grad_norm": 4.504157543182373, "learning_rate": 6.467182810745748e-06, "loss": 0.1293, "step": 390870 }, { "epoch": 2.323471892814047, "grad_norm": 3.2458102703094482, "learning_rate": 6.46698445145977e-06, "loss": 0.1355, "step": 390880 }, { "epoch": 2.3235313348907156, "grad_norm": 4.181901454925537, "learning_rate": 6.466786089647469e-06, "loss": 0.1364, "step": 390890 }, { "epoch": 2.323590776967384, "grad_norm": 4.271412372589111, "learning_rate": 6.466587725309188e-06, "loss": 0.1242, "step": 390900 }, { "epoch": 2.3236502190440524, "grad_norm": 5.119904041290283, "learning_rate": 6.466389358445268e-06, "loss": 0.1707, "step": 390910 }, { "epoch": 2.323709661120721, "grad_norm": 3.351332902908325, "learning_rate": 6.466190989056049e-06, "loss": 0.1411, "step": 390920 }, { "epoch": 2.3237691031973893, "grad_norm": 3.6422371864318848, "learning_rate": 6.465992617141874e-06, "loss": 0.1364, "step": 390930 }, { "epoch": 2.3238285452740577, "grad_norm": 4.302328109741211, "learning_rate": 6.465794242703087e-06, "loss": 0.1248, "step": 390940 }, { "epoch": 2.323887987350726, "grad_norm": 4.47647762298584, "learning_rate": 6.4655958657400265e-06, "loss": 0.1483, "step": 390950 }, { "epoch": 2.3239474294273945, "grad_norm": 4.185657024383545, "learning_rate": 6.465397486253035e-06, "loss": 0.1447, "step": 390960 }, { "epoch": 2.324006871504063, "grad_norm": 3.241048574447632, "learning_rate": 6.465199104242454e-06, "loss": 0.1473, "step": 390970 }, { "epoch": 2.3240663135807313, "grad_norm": 4.231623649597168, "learning_rate": 6.465000719708627e-06, "loss": 0.1382, "step": 390980 }, { "epoch": 2.3241257556573998, "grad_norm": 3.1071250438690186, "learning_rate": 6.464802332651892e-06, "loss": 0.1436, "step": 390990 }, { "epoch": 2.324185197734068, "grad_norm": 6.382026672363281, "learning_rate": 6.464603943072593e-06, "loss": 0.1655, "step": 391000 }, { "epoch": 2.3242446398107366, "grad_norm": 3.932231903076172, "learning_rate": 6.464405550971071e-06, "loss": 0.1418, "step": 391010 }, { "epoch": 2.324304081887405, "grad_norm": 4.700552463531494, "learning_rate": 6.464207156347668e-06, "loss": 0.1509, "step": 391020 }, { "epoch": 2.324363523964073, "grad_norm": 4.761197090148926, "learning_rate": 6.464008759202727e-06, "loss": 0.1562, "step": 391030 }, { "epoch": 2.324422966040742, "grad_norm": 3.887068033218384, "learning_rate": 6.463810359536587e-06, "loss": 0.1447, "step": 391040 }, { "epoch": 2.32448240811741, "grad_norm": 3.6406261920928955, "learning_rate": 6.4636119573495895e-06, "loss": 0.1527, "step": 391050 }, { "epoch": 2.324541850194078, "grad_norm": 3.4944777488708496, "learning_rate": 6.46341355264208e-06, "loss": 0.1407, "step": 391060 }, { "epoch": 2.3246012922707466, "grad_norm": 5.7027459144592285, "learning_rate": 6.463215145414397e-06, "loss": 0.1586, "step": 391070 }, { "epoch": 2.324660734347415, "grad_norm": 4.154760360717773, "learning_rate": 6.463016735666882e-06, "loss": 0.1371, "step": 391080 }, { "epoch": 2.3247201764240835, "grad_norm": 3.9406394958496094, "learning_rate": 6.462818323399879e-06, "loss": 0.1382, "step": 391090 }, { "epoch": 2.324779618500752, "grad_norm": 3.160675287246704, "learning_rate": 6.4626199086137274e-06, "loss": 0.15, "step": 391100 }, { "epoch": 2.3248390605774203, "grad_norm": 4.310829162597656, "learning_rate": 6.462421491308769e-06, "loss": 0.1548, "step": 391110 }, { "epoch": 2.3248985026540887, "grad_norm": 5.054322242736816, "learning_rate": 6.462223071485348e-06, "loss": 0.1452, "step": 391120 }, { "epoch": 2.324957944730757, "grad_norm": 3.251141309738159, "learning_rate": 6.462024649143804e-06, "loss": 0.1237, "step": 391130 }, { "epoch": 2.3250173868074255, "grad_norm": 3.8354034423828125, "learning_rate": 6.4618262242844785e-06, "loss": 0.1566, "step": 391140 }, { "epoch": 2.325076828884094, "grad_norm": 3.4793972969055176, "learning_rate": 6.461627796907713e-06, "loss": 0.1386, "step": 391150 }, { "epoch": 2.3251362709607624, "grad_norm": 4.669195175170898, "learning_rate": 6.4614293670138515e-06, "loss": 0.1541, "step": 391160 }, { "epoch": 2.325195713037431, "grad_norm": 4.041964530944824, "learning_rate": 6.4612309346032355e-06, "loss": 0.1494, "step": 391170 }, { "epoch": 2.325255155114099, "grad_norm": 4.900271892547607, "learning_rate": 6.461032499676203e-06, "loss": 0.1582, "step": 391180 }, { "epoch": 2.3253145971907676, "grad_norm": 3.7624523639678955, "learning_rate": 6.4608340622330985e-06, "loss": 0.1416, "step": 391190 }, { "epoch": 2.325374039267436, "grad_norm": 3.8974123001098633, "learning_rate": 6.460635622274265e-06, "loss": 0.1441, "step": 391200 }, { "epoch": 2.3254334813441044, "grad_norm": 4.437806606292725, "learning_rate": 6.460437179800042e-06, "loss": 0.1492, "step": 391210 }, { "epoch": 2.3254929234207724, "grad_norm": 4.496057987213135, "learning_rate": 6.460238734810772e-06, "loss": 0.1497, "step": 391220 }, { "epoch": 2.3255523654974413, "grad_norm": 3.1224958896636963, "learning_rate": 6.460040287306797e-06, "loss": 0.1617, "step": 391230 }, { "epoch": 2.3256118075741092, "grad_norm": 3.4840779304504395, "learning_rate": 6.459841837288457e-06, "loss": 0.1486, "step": 391240 }, { "epoch": 2.3256712496507776, "grad_norm": 3.926948308944702, "learning_rate": 6.459643384756096e-06, "loss": 0.1518, "step": 391250 }, { "epoch": 2.325730691727446, "grad_norm": 5.191090106964111, "learning_rate": 6.459444929710054e-06, "loss": 0.1564, "step": 391260 }, { "epoch": 2.3257901338041145, "grad_norm": 5.181568145751953, "learning_rate": 6.459246472150675e-06, "loss": 0.1368, "step": 391270 }, { "epoch": 2.325849575880783, "grad_norm": 3.7781853675842285, "learning_rate": 6.459048012078299e-06, "loss": 0.1396, "step": 391280 }, { "epoch": 2.3259090179574513, "grad_norm": 7.1709465980529785, "learning_rate": 6.458849549493269e-06, "loss": 0.1572, "step": 391290 }, { "epoch": 2.3259684600341197, "grad_norm": 4.752390384674072, "learning_rate": 6.458651084395925e-06, "loss": 0.1523, "step": 391300 }, { "epoch": 2.326027902110788, "grad_norm": 3.8095457553863525, "learning_rate": 6.45845261678661e-06, "loss": 0.1384, "step": 391310 }, { "epoch": 2.3260873441874566, "grad_norm": 5.079068660736084, "learning_rate": 6.458254146665665e-06, "loss": 0.1623, "step": 391320 }, { "epoch": 2.326146786264125, "grad_norm": 5.026574611663818, "learning_rate": 6.458055674033434e-06, "loss": 0.1492, "step": 391330 }, { "epoch": 2.3262062283407934, "grad_norm": 2.545783281326294, "learning_rate": 6.457857198890256e-06, "loss": 0.1461, "step": 391340 }, { "epoch": 2.326265670417462, "grad_norm": 4.592864513397217, "learning_rate": 6.4576587212364735e-06, "loss": 0.1335, "step": 391350 }, { "epoch": 2.32632511249413, "grad_norm": 4.730966091156006, "learning_rate": 6.457460241072431e-06, "loss": 0.1562, "step": 391360 }, { "epoch": 2.3263845545707986, "grad_norm": 4.034989833831787, "learning_rate": 6.457261758398465e-06, "loss": 0.1586, "step": 391370 }, { "epoch": 2.326443996647467, "grad_norm": 5.49904203414917, "learning_rate": 6.457063273214921e-06, "loss": 0.1523, "step": 391380 }, { "epoch": 2.3265034387241355, "grad_norm": 4.244361877441406, "learning_rate": 6.456864785522141e-06, "loss": 0.1663, "step": 391390 }, { "epoch": 2.326562880800804, "grad_norm": 5.235339164733887, "learning_rate": 6.456666295320467e-06, "loss": 0.1549, "step": 391400 }, { "epoch": 2.326622322877472, "grad_norm": 3.757875680923462, "learning_rate": 6.456467802610238e-06, "loss": 0.1427, "step": 391410 }, { "epoch": 2.3266817649541403, "grad_norm": 3.1482038497924805, "learning_rate": 6.456269307391799e-06, "loss": 0.1327, "step": 391420 }, { "epoch": 2.3267412070308087, "grad_norm": 5.500117301940918, "learning_rate": 6.456070809665491e-06, "loss": 0.1399, "step": 391430 }, { "epoch": 2.326800649107477, "grad_norm": 4.960397243499756, "learning_rate": 6.455872309431654e-06, "loss": 0.1437, "step": 391440 }, { "epoch": 2.3268600911841455, "grad_norm": 3.9873342514038086, "learning_rate": 6.455673806690631e-06, "loss": 0.1613, "step": 391450 }, { "epoch": 2.326919533260814, "grad_norm": 4.811002254486084, "learning_rate": 6.455475301442765e-06, "loss": 0.1384, "step": 391460 }, { "epoch": 2.3269789753374823, "grad_norm": 3.8927254676818848, "learning_rate": 6.455276793688396e-06, "loss": 0.147, "step": 391470 }, { "epoch": 2.3270384174141507, "grad_norm": 4.2388715744018555, "learning_rate": 6.455078283427867e-06, "loss": 0.1363, "step": 391480 }, { "epoch": 2.327097859490819, "grad_norm": 3.2402334213256836, "learning_rate": 6.45487977066152e-06, "loss": 0.1342, "step": 391490 }, { "epoch": 2.3271573015674876, "grad_norm": 4.5636305809021, "learning_rate": 6.454681255389697e-06, "loss": 0.1433, "step": 391500 }, { "epoch": 2.327216743644156, "grad_norm": 3.2206666469573975, "learning_rate": 6.454482737612737e-06, "loss": 0.1447, "step": 391510 }, { "epoch": 2.3272761857208244, "grad_norm": 4.566764831542969, "learning_rate": 6.454284217330986e-06, "loss": 0.1409, "step": 391520 }, { "epoch": 2.327335627797493, "grad_norm": 3.772881507873535, "learning_rate": 6.454085694544784e-06, "loss": 0.1423, "step": 391530 }, { "epoch": 2.3273950698741612, "grad_norm": 6.8620171546936035, "learning_rate": 6.453887169254471e-06, "loss": 0.1503, "step": 391540 }, { "epoch": 2.3274545119508296, "grad_norm": 4.432292461395264, "learning_rate": 6.453688641460394e-06, "loss": 0.141, "step": 391550 }, { "epoch": 2.327513954027498, "grad_norm": 4.031671524047852, "learning_rate": 6.45349011116289e-06, "loss": 0.1478, "step": 391560 }, { "epoch": 2.3275733961041665, "grad_norm": 3.8104960918426514, "learning_rate": 6.453291578362302e-06, "loss": 0.1438, "step": 391570 }, { "epoch": 2.3276328381808344, "grad_norm": 4.313210487365723, "learning_rate": 6.453093043058974e-06, "loss": 0.1419, "step": 391580 }, { "epoch": 2.3276922802575033, "grad_norm": 4.412134647369385, "learning_rate": 6.4528945052532454e-06, "loss": 0.1609, "step": 391590 }, { "epoch": 2.3277517223341713, "grad_norm": 5.046944618225098, "learning_rate": 6.452695964945459e-06, "loss": 0.1491, "step": 391600 }, { "epoch": 2.3278111644108397, "grad_norm": 3.6679744720458984, "learning_rate": 6.452497422135957e-06, "loss": 0.1589, "step": 391610 }, { "epoch": 2.327870606487508, "grad_norm": 3.7140088081359863, "learning_rate": 6.452298876825082e-06, "loss": 0.1384, "step": 391620 }, { "epoch": 2.3279300485641765, "grad_norm": 4.812241077423096, "learning_rate": 6.452100329013174e-06, "loss": 0.1444, "step": 391630 }, { "epoch": 2.327989490640845, "grad_norm": 3.763871192932129, "learning_rate": 6.451901778700575e-06, "loss": 0.1445, "step": 391640 }, { "epoch": 2.3280489327175133, "grad_norm": 3.944756269454956, "learning_rate": 6.451703225887631e-06, "loss": 0.142, "step": 391650 }, { "epoch": 2.3281083747941818, "grad_norm": 4.741217613220215, "learning_rate": 6.45150467057468e-06, "loss": 0.1568, "step": 391660 }, { "epoch": 2.32816781687085, "grad_norm": 4.606252670288086, "learning_rate": 6.4513061127620625e-06, "loss": 0.14, "step": 391670 }, { "epoch": 2.3282272589475186, "grad_norm": 3.5997536182403564, "learning_rate": 6.4511075524501246e-06, "loss": 0.1366, "step": 391680 }, { "epoch": 2.328286701024187, "grad_norm": 4.198080062866211, "learning_rate": 6.4509089896392065e-06, "loss": 0.1555, "step": 391690 }, { "epoch": 2.3283461431008554, "grad_norm": 4.113761901855469, "learning_rate": 6.450710424329647e-06, "loss": 0.1512, "step": 391700 }, { "epoch": 2.328405585177524, "grad_norm": 3.824352979660034, "learning_rate": 6.450511856521794e-06, "loss": 0.1378, "step": 391710 }, { "epoch": 2.3284650272541922, "grad_norm": 3.713080883026123, "learning_rate": 6.450313286215986e-06, "loss": 0.1393, "step": 391720 }, { "epoch": 2.3285244693308607, "grad_norm": 4.666935920715332, "learning_rate": 6.450114713412564e-06, "loss": 0.1453, "step": 391730 }, { "epoch": 2.328583911407529, "grad_norm": 4.429858207702637, "learning_rate": 6.449916138111873e-06, "loss": 0.1535, "step": 391740 }, { "epoch": 2.3286433534841975, "grad_norm": 4.303443908691406, "learning_rate": 6.449717560314255e-06, "loss": 0.147, "step": 391750 }, { "epoch": 2.328702795560866, "grad_norm": 3.9733681678771973, "learning_rate": 6.449518980020046e-06, "loss": 0.1378, "step": 391760 }, { "epoch": 2.328762237637534, "grad_norm": 2.985738754272461, "learning_rate": 6.449320397229597e-06, "loss": 0.1379, "step": 391770 }, { "epoch": 2.3288216797142027, "grad_norm": 3.602395534515381, "learning_rate": 6.4491218119432434e-06, "loss": 0.1363, "step": 391780 }, { "epoch": 2.3288811217908707, "grad_norm": 4.559369087219238, "learning_rate": 6.448923224161327e-06, "loss": 0.13, "step": 391790 }, { "epoch": 2.328940563867539, "grad_norm": 3.356797933578491, "learning_rate": 6.448724633884196e-06, "loss": 0.1293, "step": 391800 }, { "epoch": 2.3290000059442075, "grad_norm": 5.687674045562744, "learning_rate": 6.4485260411121845e-06, "loss": 0.1456, "step": 391810 }, { "epoch": 2.329059448020876, "grad_norm": 2.6018638610839844, "learning_rate": 6.448327445845641e-06, "loss": 0.144, "step": 391820 }, { "epoch": 2.3291188900975444, "grad_norm": 4.713635444641113, "learning_rate": 6.448128848084902e-06, "loss": 0.1498, "step": 391830 }, { "epoch": 2.3291783321742128, "grad_norm": 5.164642810821533, "learning_rate": 6.447930247830315e-06, "loss": 0.1449, "step": 391840 }, { "epoch": 2.329237774250881, "grad_norm": 4.158098220825195, "learning_rate": 6.447731645082219e-06, "loss": 0.1347, "step": 391850 }, { "epoch": 2.3292972163275496, "grad_norm": 3.387526750564575, "learning_rate": 6.447533039840956e-06, "loss": 0.1411, "step": 391860 }, { "epoch": 2.329356658404218, "grad_norm": 5.295849323272705, "learning_rate": 6.447334432106869e-06, "loss": 0.1461, "step": 391870 }, { "epoch": 2.3294161004808864, "grad_norm": 4.128274440765381, "learning_rate": 6.447135821880299e-06, "loss": 0.1453, "step": 391880 }, { "epoch": 2.329475542557555, "grad_norm": 5.6274871826171875, "learning_rate": 6.4469372091615875e-06, "loss": 0.1492, "step": 391890 }, { "epoch": 2.3295349846342233, "grad_norm": 3.1900885105133057, "learning_rate": 6.446738593951078e-06, "loss": 0.1504, "step": 391900 }, { "epoch": 2.3295944267108917, "grad_norm": 5.260994911193848, "learning_rate": 6.4465399762491134e-06, "loss": 0.149, "step": 391910 }, { "epoch": 2.32965386878756, "grad_norm": 3.675546169281006, "learning_rate": 6.446341356056031e-06, "loss": 0.1569, "step": 391920 }, { "epoch": 2.3297133108642285, "grad_norm": 3.930549383163452, "learning_rate": 6.4461427333721786e-06, "loss": 0.1338, "step": 391930 }, { "epoch": 2.329772752940897, "grad_norm": 4.947146892547607, "learning_rate": 6.445944108197896e-06, "loss": 0.1384, "step": 391940 }, { "epoch": 2.3298321950175653, "grad_norm": 4.005878448486328, "learning_rate": 6.4457454805335255e-06, "loss": 0.1333, "step": 391950 }, { "epoch": 2.3298916370942333, "grad_norm": 3.7198331356048584, "learning_rate": 6.445546850379407e-06, "loss": 0.14, "step": 391960 }, { "epoch": 2.329951079170902, "grad_norm": 4.1557464599609375, "learning_rate": 6.445348217735885e-06, "loss": 0.1505, "step": 391970 }, { "epoch": 2.33001052124757, "grad_norm": 5.084532737731934, "learning_rate": 6.445149582603303e-06, "loss": 0.1396, "step": 391980 }, { "epoch": 2.3300699633242385, "grad_norm": 4.70026159286499, "learning_rate": 6.444950944981998e-06, "loss": 0.1515, "step": 391990 }, { "epoch": 2.330129405400907, "grad_norm": 4.337115287780762, "learning_rate": 6.444752304872317e-06, "loss": 0.1618, "step": 392000 }, { "epoch": 2.3301888474775754, "grad_norm": 5.612539291381836, "learning_rate": 6.4445536622745995e-06, "loss": 0.1396, "step": 392010 }, { "epoch": 2.330248289554244, "grad_norm": 4.2870917320251465, "learning_rate": 6.444355017189188e-06, "loss": 0.1422, "step": 392020 }, { "epoch": 2.330307731630912, "grad_norm": 4.631669044494629, "learning_rate": 6.444156369616424e-06, "loss": 0.1498, "step": 392030 }, { "epoch": 2.3303671737075806, "grad_norm": 4.480103969573975, "learning_rate": 6.4439577195566515e-06, "loss": 0.1397, "step": 392040 }, { "epoch": 2.330426615784249, "grad_norm": 5.206966400146484, "learning_rate": 6.4437590670102126e-06, "loss": 0.1306, "step": 392050 }, { "epoch": 2.3304860578609174, "grad_norm": 3.5744729042053223, "learning_rate": 6.4435604119774465e-06, "loss": 0.1413, "step": 392060 }, { "epoch": 2.330545499937586, "grad_norm": 3.891810894012451, "learning_rate": 6.443361754458698e-06, "loss": 0.152, "step": 392070 }, { "epoch": 2.3306049420142543, "grad_norm": 4.247141361236572, "learning_rate": 6.4431630944543075e-06, "loss": 0.1608, "step": 392080 }, { "epoch": 2.3306643840909227, "grad_norm": 5.017913818359375, "learning_rate": 6.442964431964619e-06, "loss": 0.157, "step": 392090 }, { "epoch": 2.330723826167591, "grad_norm": 3.7340891361236572, "learning_rate": 6.442765766989973e-06, "loss": 0.1408, "step": 392100 }, { "epoch": 2.3307832682442595, "grad_norm": 4.1870317459106445, "learning_rate": 6.442567099530713e-06, "loss": 0.1432, "step": 392110 }, { "epoch": 2.330842710320928, "grad_norm": 3.9012207984924316, "learning_rate": 6.442368429587179e-06, "loss": 0.1452, "step": 392120 }, { "epoch": 2.3309021523975963, "grad_norm": 3.519578695297241, "learning_rate": 6.442169757159715e-06, "loss": 0.1371, "step": 392130 }, { "epoch": 2.3309615944742648, "grad_norm": 3.2575252056121826, "learning_rate": 6.441971082248663e-06, "loss": 0.134, "step": 392140 }, { "epoch": 2.3310210365509327, "grad_norm": 4.918469429016113, "learning_rate": 6.441772404854365e-06, "loss": 0.1493, "step": 392150 }, { "epoch": 2.331080478627601, "grad_norm": 4.880243301391602, "learning_rate": 6.441573724977161e-06, "loss": 0.1686, "step": 392160 }, { "epoch": 2.3311399207042696, "grad_norm": 3.532496929168701, "learning_rate": 6.441375042617397e-06, "loss": 0.1434, "step": 392170 }, { "epoch": 2.331199362780938, "grad_norm": 4.392403602600098, "learning_rate": 6.441176357775414e-06, "loss": 0.152, "step": 392180 }, { "epoch": 2.3312588048576064, "grad_norm": 3.389786720275879, "learning_rate": 6.44097767045155e-06, "loss": 0.1351, "step": 392190 }, { "epoch": 2.331318246934275, "grad_norm": 3.3098793029785156, "learning_rate": 6.440778980646154e-06, "loss": 0.1305, "step": 392200 }, { "epoch": 2.331377689010943, "grad_norm": 4.403481483459473, "learning_rate": 6.440580288359563e-06, "loss": 0.1279, "step": 392210 }, { "epoch": 2.3314371310876116, "grad_norm": 3.853238105773926, "learning_rate": 6.44038159359212e-06, "loss": 0.1416, "step": 392220 }, { "epoch": 2.33149657316428, "grad_norm": 6.266910076141357, "learning_rate": 6.440182896344169e-06, "loss": 0.1587, "step": 392230 }, { "epoch": 2.3315560152409485, "grad_norm": 3.7514305114746094, "learning_rate": 6.439984196616052e-06, "loss": 0.1479, "step": 392240 }, { "epoch": 2.331615457317617, "grad_norm": 4.301292896270752, "learning_rate": 6.439785494408109e-06, "loss": 0.1458, "step": 392250 }, { "epoch": 2.3316748993942853, "grad_norm": 4.578340530395508, "learning_rate": 6.439586789720684e-06, "loss": 0.1388, "step": 392260 }, { "epoch": 2.3317343414709537, "grad_norm": 2.7841663360595703, "learning_rate": 6.43938808255412e-06, "loss": 0.1442, "step": 392270 }, { "epoch": 2.331793783547622, "grad_norm": 4.366730213165283, "learning_rate": 6.439189372908756e-06, "loss": 0.1432, "step": 392280 }, { "epoch": 2.3318532256242905, "grad_norm": 5.485927104949951, "learning_rate": 6.438990660784939e-06, "loss": 0.1503, "step": 392290 }, { "epoch": 2.331912667700959, "grad_norm": 5.293858051300049, "learning_rate": 6.438791946183005e-06, "loss": 0.1434, "step": 392300 }, { "epoch": 2.3319721097776274, "grad_norm": 5.172492504119873, "learning_rate": 6.438593229103303e-06, "loss": 0.1506, "step": 392310 }, { "epoch": 2.3320315518542953, "grad_norm": 3.954599618911743, "learning_rate": 6.438394509546169e-06, "loss": 0.1352, "step": 392320 }, { "epoch": 2.332090993930964, "grad_norm": 3.69775128364563, "learning_rate": 6.43819578751195e-06, "loss": 0.1251, "step": 392330 }, { "epoch": 2.332150436007632, "grad_norm": 4.394728660583496, "learning_rate": 6.437997063000984e-06, "loss": 0.1467, "step": 392340 }, { "epoch": 2.3322098780843006, "grad_norm": 4.6356987953186035, "learning_rate": 6.437798336013616e-06, "loss": 0.155, "step": 392350 }, { "epoch": 2.332269320160969, "grad_norm": 4.786033630371094, "learning_rate": 6.437599606550189e-06, "loss": 0.1202, "step": 392360 }, { "epoch": 2.3323287622376374, "grad_norm": 5.26800537109375, "learning_rate": 6.437400874611044e-06, "loss": 0.1514, "step": 392370 }, { "epoch": 2.332388204314306, "grad_norm": 3.3007891178131104, "learning_rate": 6.4372021401965215e-06, "loss": 0.1571, "step": 392380 }, { "epoch": 2.3324476463909742, "grad_norm": 5.2751312255859375, "learning_rate": 6.437003403306967e-06, "loss": 0.1425, "step": 392390 }, { "epoch": 2.3325070884676427, "grad_norm": 4.1309404373168945, "learning_rate": 6.436804663942721e-06, "loss": 0.1507, "step": 392400 }, { "epoch": 2.332566530544311, "grad_norm": 4.47817850112915, "learning_rate": 6.4366059221041245e-06, "loss": 0.1399, "step": 392410 }, { "epoch": 2.3326259726209795, "grad_norm": 3.1489851474761963, "learning_rate": 6.4364071777915235e-06, "loss": 0.1447, "step": 392420 }, { "epoch": 2.332685414697648, "grad_norm": 6.003174304962158, "learning_rate": 6.436208431005258e-06, "loss": 0.1461, "step": 392430 }, { "epoch": 2.3327448567743163, "grad_norm": 3.9792239665985107, "learning_rate": 6.436009681745667e-06, "loss": 0.1425, "step": 392440 }, { "epoch": 2.3328042988509847, "grad_norm": 3.6320507526397705, "learning_rate": 6.435810930013099e-06, "loss": 0.1601, "step": 392450 }, { "epoch": 2.332863740927653, "grad_norm": 5.342647552490234, "learning_rate": 6.435612175807893e-06, "loss": 0.1498, "step": 392460 }, { "epoch": 2.3329231830043216, "grad_norm": 3.7184836864471436, "learning_rate": 6.43541341913039e-06, "loss": 0.1531, "step": 392470 }, { "epoch": 2.33298262508099, "grad_norm": 4.7015581130981445, "learning_rate": 6.4352146599809325e-06, "loss": 0.14, "step": 392480 }, { "epoch": 2.3330420671576584, "grad_norm": 2.8130602836608887, "learning_rate": 6.435015898359868e-06, "loss": 0.1317, "step": 392490 }, { "epoch": 2.333101509234327, "grad_norm": 4.252646446228027, "learning_rate": 6.434817134267532e-06, "loss": 0.1342, "step": 392500 }, { "epoch": 2.3331609513109948, "grad_norm": 3.2888894081115723, "learning_rate": 6.43461836770427e-06, "loss": 0.1335, "step": 392510 }, { "epoch": 2.3332203933876636, "grad_norm": 3.167724370956421, "learning_rate": 6.4344195986704265e-06, "loss": 0.158, "step": 392520 }, { "epoch": 2.3332798354643316, "grad_norm": 4.14453125, "learning_rate": 6.43422082716634e-06, "loss": 0.1291, "step": 392530 }, { "epoch": 2.333339277541, "grad_norm": 5.140905380249023, "learning_rate": 6.434022053192353e-06, "loss": 0.1476, "step": 392540 }, { "epoch": 2.3333987196176684, "grad_norm": 3.201493978500366, "learning_rate": 6.43382327674881e-06, "loss": 0.1176, "step": 392550 }, { "epoch": 2.333458161694337, "grad_norm": 4.093249320983887, "learning_rate": 6.433624497836052e-06, "loss": 0.1436, "step": 392560 }, { "epoch": 2.3335176037710053, "grad_norm": 3.683619737625122, "learning_rate": 6.433425716454421e-06, "loss": 0.1398, "step": 392570 }, { "epoch": 2.3335770458476737, "grad_norm": 4.015135765075684, "learning_rate": 6.433226932604259e-06, "loss": 0.1458, "step": 392580 }, { "epoch": 2.333636487924342, "grad_norm": 3.848349094390869, "learning_rate": 6.433028146285911e-06, "loss": 0.1404, "step": 392590 }, { "epoch": 2.3336959300010105, "grad_norm": 3.9966301918029785, "learning_rate": 6.432829357499718e-06, "loss": 0.152, "step": 392600 }, { "epoch": 2.333755372077679, "grad_norm": 4.122873306274414, "learning_rate": 6.43263056624602e-06, "loss": 0.1501, "step": 392610 }, { "epoch": 2.3338148141543473, "grad_norm": 4.994364261627197, "learning_rate": 6.432431772525163e-06, "loss": 0.1344, "step": 392620 }, { "epoch": 2.3338742562310157, "grad_norm": 3.346715211868286, "learning_rate": 6.432232976337487e-06, "loss": 0.1637, "step": 392630 }, { "epoch": 2.333933698307684, "grad_norm": 4.007256031036377, "learning_rate": 6.432034177683334e-06, "loss": 0.1561, "step": 392640 }, { "epoch": 2.3339931403843526, "grad_norm": 3.9406723976135254, "learning_rate": 6.431835376563048e-06, "loss": 0.1487, "step": 392650 }, { "epoch": 2.334052582461021, "grad_norm": 4.222376823425293, "learning_rate": 6.431636572976972e-06, "loss": 0.1522, "step": 392660 }, { "epoch": 2.3341120245376894, "grad_norm": 4.75517463684082, "learning_rate": 6.4314377669254436e-06, "loss": 0.1508, "step": 392670 }, { "epoch": 2.334171466614358, "grad_norm": 5.217906475067139, "learning_rate": 6.4312389584088116e-06, "loss": 0.1508, "step": 392680 }, { "epoch": 2.3342309086910262, "grad_norm": 4.541414260864258, "learning_rate": 6.431040147427413e-06, "loss": 0.1374, "step": 392690 }, { "epoch": 2.334290350767694, "grad_norm": 3.411241054534912, "learning_rate": 6.4308413339815945e-06, "loss": 0.1445, "step": 392700 }, { "epoch": 2.334349792844363, "grad_norm": 4.036042213439941, "learning_rate": 6.430642518071695e-06, "loss": 0.1195, "step": 392710 }, { "epoch": 2.334409234921031, "grad_norm": 3.573404550552368, "learning_rate": 6.43044369969806e-06, "loss": 0.1405, "step": 392720 }, { "epoch": 2.3344686769976994, "grad_norm": 3.8343985080718994, "learning_rate": 6.4302448788610296e-06, "loss": 0.1435, "step": 392730 }, { "epoch": 2.334528119074368, "grad_norm": 3.3827531337738037, "learning_rate": 6.430046055560946e-06, "loss": 0.1241, "step": 392740 }, { "epoch": 2.3345875611510363, "grad_norm": 4.242789268493652, "learning_rate": 6.429847229798154e-06, "loss": 0.1583, "step": 392750 }, { "epoch": 2.3346470032277047, "grad_norm": 4.741529941558838, "learning_rate": 6.429648401572994e-06, "loss": 0.145, "step": 392760 }, { "epoch": 2.334706445304373, "grad_norm": 5.0911970138549805, "learning_rate": 6.429449570885807e-06, "loss": 0.127, "step": 392770 }, { "epoch": 2.3347658873810415, "grad_norm": 4.189460754394531, "learning_rate": 6.42925073773694e-06, "loss": 0.1398, "step": 392780 }, { "epoch": 2.33482532945771, "grad_norm": 3.9749250411987305, "learning_rate": 6.429051902126732e-06, "loss": 0.1573, "step": 392790 }, { "epoch": 2.3348847715343783, "grad_norm": 4.054904460906982, "learning_rate": 6.428853064055524e-06, "loss": 0.1658, "step": 392800 }, { "epoch": 2.3349442136110468, "grad_norm": 4.306774616241455, "learning_rate": 6.4286542235236625e-06, "loss": 0.145, "step": 392810 }, { "epoch": 2.335003655687715, "grad_norm": 6.584295272827148, "learning_rate": 6.428455380531488e-06, "loss": 0.1515, "step": 392820 }, { "epoch": 2.3350630977643836, "grad_norm": 4.4488701820373535, "learning_rate": 6.428256535079343e-06, "loss": 0.1477, "step": 392830 }, { "epoch": 2.335122539841052, "grad_norm": 3.1769394874572754, "learning_rate": 6.428057687167568e-06, "loss": 0.1404, "step": 392840 }, { "epoch": 2.3351819819177204, "grad_norm": 4.528988361358643, "learning_rate": 6.42785883679651e-06, "loss": 0.157, "step": 392850 }, { "epoch": 2.335241423994389, "grad_norm": 4.583196640014648, "learning_rate": 6.4276599839665075e-06, "loss": 0.1553, "step": 392860 }, { "epoch": 2.3353008660710572, "grad_norm": 3.112157106399536, "learning_rate": 6.427461128677903e-06, "loss": 0.1328, "step": 392870 }, { "epoch": 2.3353603081477257, "grad_norm": 2.8655238151550293, "learning_rate": 6.427262270931042e-06, "loss": 0.1335, "step": 392880 }, { "epoch": 2.3354197502243936, "grad_norm": 4.583918571472168, "learning_rate": 6.4270634107262646e-06, "loss": 0.1485, "step": 392890 }, { "epoch": 2.335479192301062, "grad_norm": 4.860657691955566, "learning_rate": 6.426864548063911e-06, "loss": 0.1594, "step": 392900 }, { "epoch": 2.3355386343777305, "grad_norm": 6.783276557922363, "learning_rate": 6.426665682944329e-06, "loss": 0.1527, "step": 392910 }, { "epoch": 2.335598076454399, "grad_norm": 3.654845952987671, "learning_rate": 6.426466815367859e-06, "loss": 0.1341, "step": 392920 }, { "epoch": 2.3356575185310673, "grad_norm": 5.200594902038574, "learning_rate": 6.426267945334841e-06, "loss": 0.1375, "step": 392930 }, { "epoch": 2.3357169606077357, "grad_norm": 4.6235032081604, "learning_rate": 6.426069072845621e-06, "loss": 0.1565, "step": 392940 }, { "epoch": 2.335776402684404, "grad_norm": 3.7770118713378906, "learning_rate": 6.42587019790054e-06, "loss": 0.1503, "step": 392950 }, { "epoch": 2.3358358447610725, "grad_norm": 3.396477460861206, "learning_rate": 6.425671320499939e-06, "loss": 0.1531, "step": 392960 }, { "epoch": 2.335895286837741, "grad_norm": 4.687675476074219, "learning_rate": 6.425472440644162e-06, "loss": 0.1343, "step": 392970 }, { "epoch": 2.3359547289144094, "grad_norm": 4.105836391448975, "learning_rate": 6.425273558333553e-06, "loss": 0.139, "step": 392980 }, { "epoch": 2.3360141709910778, "grad_norm": 4.0147480964660645, "learning_rate": 6.425074673568452e-06, "loss": 0.1418, "step": 392990 }, { "epoch": 2.336073613067746, "grad_norm": 5.109287261962891, "learning_rate": 6.424875786349203e-06, "loss": 0.1632, "step": 393000 }, { "epoch": 2.3361330551444146, "grad_norm": 4.0425872802734375, "learning_rate": 6.424676896676147e-06, "loss": 0.1384, "step": 393010 }, { "epoch": 2.336192497221083, "grad_norm": 3.925276756286621, "learning_rate": 6.424478004549627e-06, "loss": 0.13, "step": 393020 }, { "epoch": 2.3362519392977514, "grad_norm": 3.9492523670196533, "learning_rate": 6.4242791099699865e-06, "loss": 0.1583, "step": 393030 }, { "epoch": 2.33631138137442, "grad_norm": 3.973334789276123, "learning_rate": 6.424080212937567e-06, "loss": 0.1543, "step": 393040 }, { "epoch": 2.3363708234510883, "grad_norm": 4.2365498542785645, "learning_rate": 6.423881313452712e-06, "loss": 0.1352, "step": 393050 }, { "epoch": 2.3364302655277562, "grad_norm": 5.067605495452881, "learning_rate": 6.423682411515763e-06, "loss": 0.153, "step": 393060 }, { "epoch": 2.336489707604425, "grad_norm": 4.3373308181762695, "learning_rate": 6.423483507127064e-06, "loss": 0.1517, "step": 393070 }, { "epoch": 2.336549149681093, "grad_norm": 3.9494566917419434, "learning_rate": 6.423284600286956e-06, "loss": 0.1506, "step": 393080 }, { "epoch": 2.3366085917577615, "grad_norm": 3.6423914432525635, "learning_rate": 6.423085690995782e-06, "loss": 0.1462, "step": 393090 }, { "epoch": 2.33666803383443, "grad_norm": 4.62912654876709, "learning_rate": 6.422886779253885e-06, "loss": 0.1473, "step": 393100 }, { "epoch": 2.3367274759110983, "grad_norm": 4.926106929779053, "learning_rate": 6.422687865061606e-06, "loss": 0.1596, "step": 393110 }, { "epoch": 2.3367869179877667, "grad_norm": 4.551025390625, "learning_rate": 6.42248894841929e-06, "loss": 0.1594, "step": 393120 }, { "epoch": 2.336846360064435, "grad_norm": 5.273491382598877, "learning_rate": 6.422290029327277e-06, "loss": 0.1386, "step": 393130 }, { "epoch": 2.3369058021411035, "grad_norm": 4.110132217407227, "learning_rate": 6.422091107785913e-06, "loss": 0.1316, "step": 393140 }, { "epoch": 2.336965244217772, "grad_norm": 4.517305850982666, "learning_rate": 6.421892183795537e-06, "loss": 0.1436, "step": 393150 }, { "epoch": 2.3370246862944404, "grad_norm": 4.2125468254089355, "learning_rate": 6.421693257356492e-06, "loss": 0.1491, "step": 393160 }, { "epoch": 2.337084128371109, "grad_norm": 3.1558237075805664, "learning_rate": 6.421494328469123e-06, "loss": 0.1239, "step": 393170 }, { "epoch": 2.337143570447777, "grad_norm": 3.918555498123169, "learning_rate": 6.421295397133772e-06, "loss": 0.1556, "step": 393180 }, { "epoch": 2.3372030125244456, "grad_norm": 3.747962236404419, "learning_rate": 6.421096463350779e-06, "loss": 0.1551, "step": 393190 }, { "epoch": 2.337262454601114, "grad_norm": 4.726548671722412, "learning_rate": 6.4208975271204886e-06, "loss": 0.1396, "step": 393200 }, { "epoch": 2.3373218966777825, "grad_norm": 4.372082710266113, "learning_rate": 6.420698588443245e-06, "loss": 0.1496, "step": 393210 }, { "epoch": 2.337381338754451, "grad_norm": 3.805510997772217, "learning_rate": 6.420499647319387e-06, "loss": 0.1477, "step": 393220 }, { "epoch": 2.3374407808311193, "grad_norm": 3.425342082977295, "learning_rate": 6.420300703749259e-06, "loss": 0.1579, "step": 393230 }, { "epoch": 2.3375002229077877, "grad_norm": 4.64467716217041, "learning_rate": 6.420101757733204e-06, "loss": 0.1472, "step": 393240 }, { "epoch": 2.3375596649844557, "grad_norm": 3.4189815521240234, "learning_rate": 6.419902809271565e-06, "loss": 0.1307, "step": 393250 }, { "epoch": 2.3376191070611245, "grad_norm": 2.687246084213257, "learning_rate": 6.419703858364683e-06, "loss": 0.1441, "step": 393260 }, { "epoch": 2.3376785491377925, "grad_norm": 4.490933418273926, "learning_rate": 6.4195049050129024e-06, "loss": 0.1414, "step": 393270 }, { "epoch": 2.337737991214461, "grad_norm": 4.783355236053467, "learning_rate": 6.419305949216565e-06, "loss": 0.1395, "step": 393280 }, { "epoch": 2.3377974332911293, "grad_norm": 4.0262041091918945, "learning_rate": 6.419106990976012e-06, "loss": 0.1431, "step": 393290 }, { "epoch": 2.3378568753677977, "grad_norm": 3.5548293590545654, "learning_rate": 6.41890803029159e-06, "loss": 0.1785, "step": 393300 }, { "epoch": 2.337916317444466, "grad_norm": 4.387754440307617, "learning_rate": 6.4187090671636375e-06, "loss": 0.1505, "step": 393310 }, { "epoch": 2.3379757595211346, "grad_norm": 3.5772151947021484, "learning_rate": 6.418510101592498e-06, "loss": 0.1361, "step": 393320 }, { "epoch": 2.338035201597803, "grad_norm": 7.122754096984863, "learning_rate": 6.418311133578516e-06, "loss": 0.1592, "step": 393330 }, { "epoch": 2.3380946436744714, "grad_norm": 5.689651966094971, "learning_rate": 6.4181121631220335e-06, "loss": 0.1422, "step": 393340 }, { "epoch": 2.33815408575114, "grad_norm": 5.9788312911987305, "learning_rate": 6.41791319022339e-06, "loss": 0.152, "step": 393350 }, { "epoch": 2.3382135278278082, "grad_norm": 4.105445384979248, "learning_rate": 6.417714214882933e-06, "loss": 0.1537, "step": 393360 }, { "epoch": 2.3382729699044766, "grad_norm": 3.3052115440368652, "learning_rate": 6.417515237101003e-06, "loss": 0.1395, "step": 393370 }, { "epoch": 2.338332411981145, "grad_norm": 2.7085390090942383, "learning_rate": 6.417316256877942e-06, "loss": 0.1242, "step": 393380 }, { "epoch": 2.3383918540578135, "grad_norm": 4.9600138664245605, "learning_rate": 6.417117274214093e-06, "loss": 0.1642, "step": 393390 }, { "epoch": 2.338451296134482, "grad_norm": 5.651201248168945, "learning_rate": 6.4169182891098e-06, "loss": 0.152, "step": 393400 }, { "epoch": 2.3385107382111503, "grad_norm": 5.020364284515381, "learning_rate": 6.416719301565404e-06, "loss": 0.1343, "step": 393410 }, { "epoch": 2.3385701802878187, "grad_norm": 4.654606819152832, "learning_rate": 6.416520311581248e-06, "loss": 0.1562, "step": 393420 }, { "epoch": 2.338629622364487, "grad_norm": 4.8252177238464355, "learning_rate": 6.416321319157676e-06, "loss": 0.166, "step": 393430 }, { "epoch": 2.338689064441155, "grad_norm": 3.5714120864868164, "learning_rate": 6.4161223242950296e-06, "loss": 0.1256, "step": 393440 }, { "epoch": 2.338748506517824, "grad_norm": 4.624194622039795, "learning_rate": 6.41592332699365e-06, "loss": 0.1435, "step": 393450 }, { "epoch": 2.338807948594492, "grad_norm": 5.052268028259277, "learning_rate": 6.415724327253883e-06, "loss": 0.1394, "step": 393460 }, { "epoch": 2.3388673906711603, "grad_norm": 4.912839889526367, "learning_rate": 6.415525325076069e-06, "loss": 0.1497, "step": 393470 }, { "epoch": 2.3389268327478288, "grad_norm": 3.9252536296844482, "learning_rate": 6.415326320460552e-06, "loss": 0.1413, "step": 393480 }, { "epoch": 2.338986274824497, "grad_norm": 4.232718467712402, "learning_rate": 6.4151273134076745e-06, "loss": 0.1445, "step": 393490 }, { "epoch": 2.3390457169011656, "grad_norm": 5.916919708251953, "learning_rate": 6.414928303917778e-06, "loss": 0.1504, "step": 393500 }, { "epoch": 2.339105158977834, "grad_norm": 4.057232856750488, "learning_rate": 6.4147292919912075e-06, "loss": 0.1322, "step": 393510 }, { "epoch": 2.3391646010545024, "grad_norm": 3.9038143157958984, "learning_rate": 6.4145302776283026e-06, "loss": 0.1372, "step": 393520 }, { "epoch": 2.339224043131171, "grad_norm": 4.709064960479736, "learning_rate": 6.41433126082941e-06, "loss": 0.1516, "step": 393530 }, { "epoch": 2.3392834852078392, "grad_norm": 5.793304443359375, "learning_rate": 6.414132241594868e-06, "loss": 0.1363, "step": 393540 }, { "epoch": 2.3393429272845077, "grad_norm": 4.434686660766602, "learning_rate": 6.413933219925022e-06, "loss": 0.1379, "step": 393550 }, { "epoch": 2.339402369361176, "grad_norm": 3.813110828399658, "learning_rate": 6.413734195820216e-06, "loss": 0.1551, "step": 393560 }, { "epoch": 2.3394618114378445, "grad_norm": 4.30307149887085, "learning_rate": 6.413535169280789e-06, "loss": 0.1413, "step": 393570 }, { "epoch": 2.339521253514513, "grad_norm": 5.412051677703857, "learning_rate": 6.4133361403070845e-06, "loss": 0.1535, "step": 393580 }, { "epoch": 2.3395806955911813, "grad_norm": 6.3946099281311035, "learning_rate": 6.41313710889945e-06, "loss": 0.1608, "step": 393590 }, { "epoch": 2.3396401376678497, "grad_norm": 5.616839408874512, "learning_rate": 6.4129380750582236e-06, "loss": 0.1664, "step": 393600 }, { "epoch": 2.339699579744518, "grad_norm": 4.229607582092285, "learning_rate": 6.4127390387837485e-06, "loss": 0.1368, "step": 393610 }, { "epoch": 2.3397590218211866, "grad_norm": 3.340759038925171, "learning_rate": 6.412540000076368e-06, "loss": 0.1373, "step": 393620 }, { "epoch": 2.3398184638978545, "grad_norm": 4.155057907104492, "learning_rate": 6.412340958936427e-06, "loss": 0.1568, "step": 393630 }, { "epoch": 2.339877905974523, "grad_norm": 3.084069013595581, "learning_rate": 6.412141915364265e-06, "loss": 0.1293, "step": 393640 }, { "epoch": 2.3399373480511914, "grad_norm": 3.7716798782348633, "learning_rate": 6.411942869360226e-06, "loss": 0.1469, "step": 393650 }, { "epoch": 2.3399967901278598, "grad_norm": 5.001340866088867, "learning_rate": 6.411743820924654e-06, "loss": 0.1399, "step": 393660 }, { "epoch": 2.340056232204528, "grad_norm": 3.1198675632476807, "learning_rate": 6.4115447700578895e-06, "loss": 0.1502, "step": 393670 }, { "epoch": 2.3401156742811966, "grad_norm": 5.303069591522217, "learning_rate": 6.411345716760276e-06, "loss": 0.1585, "step": 393680 }, { "epoch": 2.340175116357865, "grad_norm": 3.013110637664795, "learning_rate": 6.411146661032157e-06, "loss": 0.1195, "step": 393690 }, { "epoch": 2.3402345584345334, "grad_norm": 5.3445940017700195, "learning_rate": 6.410947602873876e-06, "loss": 0.1636, "step": 393700 }, { "epoch": 2.340294000511202, "grad_norm": 3.165530204772949, "learning_rate": 6.410748542285774e-06, "loss": 0.153, "step": 393710 }, { "epoch": 2.3403534425878703, "grad_norm": 6.268900394439697, "learning_rate": 6.410549479268196e-06, "loss": 0.1598, "step": 393720 }, { "epoch": 2.3404128846645387, "grad_norm": 3.1626129150390625, "learning_rate": 6.410350413821483e-06, "loss": 0.1462, "step": 393730 }, { "epoch": 2.340472326741207, "grad_norm": 4.782218933105469, "learning_rate": 6.4101513459459775e-06, "loss": 0.1525, "step": 393740 }, { "epoch": 2.3405317688178755, "grad_norm": 3.782778739929199, "learning_rate": 6.409952275642024e-06, "loss": 0.1252, "step": 393750 }, { "epoch": 2.340591210894544, "grad_norm": 3.66518497467041, "learning_rate": 6.409753202909965e-06, "loss": 0.1377, "step": 393760 }, { "epoch": 2.3406506529712123, "grad_norm": 5.4167256355285645, "learning_rate": 6.4095541277501414e-06, "loss": 0.131, "step": 393770 }, { "epoch": 2.3407100950478807, "grad_norm": 3.0667834281921387, "learning_rate": 6.409355050162897e-06, "loss": 0.14, "step": 393780 }, { "epoch": 2.340769537124549, "grad_norm": 3.920138120651245, "learning_rate": 6.409155970148576e-06, "loss": 0.1507, "step": 393790 }, { "epoch": 2.340828979201217, "grad_norm": 2.9808478355407715, "learning_rate": 6.408956887707521e-06, "loss": 0.1339, "step": 393800 }, { "epoch": 2.340888421277886, "grad_norm": 4.500789642333984, "learning_rate": 6.408757802840073e-06, "loss": 0.1415, "step": 393810 }, { "epoch": 2.340947863354554, "grad_norm": 4.221444606781006, "learning_rate": 6.408558715546577e-06, "loss": 0.1419, "step": 393820 }, { "epoch": 2.3410073054312224, "grad_norm": 3.913630247116089, "learning_rate": 6.408359625827374e-06, "loss": 0.1374, "step": 393830 }, { "epoch": 2.341066747507891, "grad_norm": 4.0072922706604, "learning_rate": 6.408160533682807e-06, "loss": 0.1453, "step": 393840 }, { "epoch": 2.341126189584559, "grad_norm": 3.3224904537200928, "learning_rate": 6.40796143911322e-06, "loss": 0.1427, "step": 393850 }, { "epoch": 2.3411856316612276, "grad_norm": 3.7342209815979004, "learning_rate": 6.407762342118957e-06, "loss": 0.1437, "step": 393860 }, { "epoch": 2.341245073737896, "grad_norm": 5.334358215332031, "learning_rate": 6.407563242700358e-06, "loss": 0.158, "step": 393870 }, { "epoch": 2.3413045158145644, "grad_norm": 5.310302734375, "learning_rate": 6.407364140857767e-06, "loss": 0.1435, "step": 393880 }, { "epoch": 2.341363957891233, "grad_norm": 4.927565097808838, "learning_rate": 6.407165036591527e-06, "loss": 0.1405, "step": 393890 }, { "epoch": 2.3414233999679013, "grad_norm": 3.303760528564453, "learning_rate": 6.406965929901982e-06, "loss": 0.1488, "step": 393900 }, { "epoch": 2.3414828420445697, "grad_norm": 3.9687507152557373, "learning_rate": 6.406766820789472e-06, "loss": 0.1435, "step": 393910 }, { "epoch": 2.341542284121238, "grad_norm": 4.219710826873779, "learning_rate": 6.406567709254342e-06, "loss": 0.1435, "step": 393920 }, { "epoch": 2.3416017261979065, "grad_norm": 5.377466201782227, "learning_rate": 6.406368595296937e-06, "loss": 0.147, "step": 393930 }, { "epoch": 2.341661168274575, "grad_norm": 4.063726902008057, "learning_rate": 6.406169478917594e-06, "loss": 0.1432, "step": 393940 }, { "epoch": 2.3417206103512433, "grad_norm": 3.240483283996582, "learning_rate": 6.405970360116661e-06, "loss": 0.1486, "step": 393950 }, { "epoch": 2.3417800524279118, "grad_norm": 4.3904924392700195, "learning_rate": 6.40577123889448e-06, "loss": 0.1273, "step": 393960 }, { "epoch": 2.34183949450458, "grad_norm": 2.386434316635132, "learning_rate": 6.4055721152513925e-06, "loss": 0.1359, "step": 393970 }, { "epoch": 2.3418989365812486, "grad_norm": 3.418872356414795, "learning_rate": 6.405372989187742e-06, "loss": 0.1395, "step": 393980 }, { "epoch": 2.3419583786579166, "grad_norm": 4.075448989868164, "learning_rate": 6.405173860703873e-06, "loss": 0.141, "step": 393990 }, { "epoch": 2.3420178207345854, "grad_norm": 5.518909931182861, "learning_rate": 6.404974729800124e-06, "loss": 0.1534, "step": 394000 }, { "epoch": 2.3420772628112534, "grad_norm": 2.9477269649505615, "learning_rate": 6.404775596476842e-06, "loss": 0.1232, "step": 394010 }, { "epoch": 2.342136704887922, "grad_norm": 5.773845195770264, "learning_rate": 6.404576460734369e-06, "loss": 0.1445, "step": 394020 }, { "epoch": 2.34219614696459, "grad_norm": 4.647491455078125, "learning_rate": 6.404377322573049e-06, "loss": 0.1444, "step": 394030 }, { "epoch": 2.3422555890412586, "grad_norm": 4.81058931350708, "learning_rate": 6.404178181993222e-06, "loss": 0.1695, "step": 394040 }, { "epoch": 2.342315031117927, "grad_norm": 3.8125288486480713, "learning_rate": 6.403979038995234e-06, "loss": 0.1468, "step": 394050 }, { "epoch": 2.3423744731945955, "grad_norm": 4.107736587524414, "learning_rate": 6.403779893579426e-06, "loss": 0.1353, "step": 394060 }, { "epoch": 2.342433915271264, "grad_norm": 2.767397880554199, "learning_rate": 6.403580745746141e-06, "loss": 0.1293, "step": 394070 }, { "epoch": 2.3424933573479323, "grad_norm": 3.6402642726898193, "learning_rate": 6.403381595495723e-06, "loss": 0.1405, "step": 394080 }, { "epoch": 2.3425527994246007, "grad_norm": 5.184453964233398, "learning_rate": 6.403182442828515e-06, "loss": 0.1453, "step": 394090 }, { "epoch": 2.342612241501269, "grad_norm": 4.9935994148254395, "learning_rate": 6.402983287744858e-06, "loss": 0.1405, "step": 394100 }, { "epoch": 2.3426716835779375, "grad_norm": 3.376471519470215, "learning_rate": 6.402784130245098e-06, "loss": 0.1351, "step": 394110 }, { "epoch": 2.342731125654606, "grad_norm": 3.9253592491149902, "learning_rate": 6.402584970329575e-06, "loss": 0.1471, "step": 394120 }, { "epoch": 2.3427905677312744, "grad_norm": 4.174039840698242, "learning_rate": 6.402385807998635e-06, "loss": 0.1414, "step": 394130 }, { "epoch": 2.342850009807943, "grad_norm": 3.6750917434692383, "learning_rate": 6.402186643252617e-06, "loss": 0.13, "step": 394140 }, { "epoch": 2.342909451884611, "grad_norm": 4.344999313354492, "learning_rate": 6.401987476091866e-06, "loss": 0.147, "step": 394150 }, { "epoch": 2.3429688939612796, "grad_norm": 4.771577835083008, "learning_rate": 6.401788306516728e-06, "loss": 0.1449, "step": 394160 }, { "epoch": 2.343028336037948, "grad_norm": 2.896648406982422, "learning_rate": 6.401589134527542e-06, "loss": 0.1394, "step": 394170 }, { "epoch": 2.343087778114616, "grad_norm": 3.1659295558929443, "learning_rate": 6.401389960124652e-06, "loss": 0.1271, "step": 394180 }, { "epoch": 2.343147220191285, "grad_norm": 4.554666519165039, "learning_rate": 6.401190783308402e-06, "loss": 0.1415, "step": 394190 }, { "epoch": 2.343206662267953, "grad_norm": 3.658460855484009, "learning_rate": 6.400991604079133e-06, "loss": 0.1322, "step": 394200 }, { "epoch": 2.3432661043446212, "grad_norm": 4.649648189544678, "learning_rate": 6.4007924224371906e-06, "loss": 0.1399, "step": 394210 }, { "epoch": 2.3433255464212897, "grad_norm": 3.865159511566162, "learning_rate": 6.400593238382917e-06, "loss": 0.1383, "step": 394220 }, { "epoch": 2.343384988497958, "grad_norm": 4.620284080505371, "learning_rate": 6.400394051916652e-06, "loss": 0.151, "step": 394230 }, { "epoch": 2.3434444305746265, "grad_norm": 4.002974987030029, "learning_rate": 6.400194863038743e-06, "loss": 0.1319, "step": 394240 }, { "epoch": 2.343503872651295, "grad_norm": 4.366780757904053, "learning_rate": 6.3999956717495325e-06, "loss": 0.1645, "step": 394250 }, { "epoch": 2.3435633147279633, "grad_norm": 5.013127326965332, "learning_rate": 6.39979647804936e-06, "loss": 0.1372, "step": 394260 }, { "epoch": 2.3436227568046317, "grad_norm": 3.652391195297241, "learning_rate": 6.399597281938573e-06, "loss": 0.1314, "step": 394270 }, { "epoch": 2.3436821988813, "grad_norm": 3.705284357070923, "learning_rate": 6.399398083417512e-06, "loss": 0.142, "step": 394280 }, { "epoch": 2.3437416409579686, "grad_norm": 4.665991306304932, "learning_rate": 6.39919888248652e-06, "loss": 0.1409, "step": 394290 }, { "epoch": 2.343801083034637, "grad_norm": 5.352303981781006, "learning_rate": 6.398999679145941e-06, "loss": 0.1459, "step": 394300 }, { "epoch": 2.3438605251113054, "grad_norm": 3.2188656330108643, "learning_rate": 6.398800473396118e-06, "loss": 0.1368, "step": 394310 }, { "epoch": 2.343919967187974, "grad_norm": 4.355489730834961, "learning_rate": 6.398601265237394e-06, "loss": 0.1389, "step": 394320 }, { "epoch": 2.343979409264642, "grad_norm": 3.3584160804748535, "learning_rate": 6.398402054670109e-06, "loss": 0.1286, "step": 394330 }, { "epoch": 2.3440388513413106, "grad_norm": 5.573017120361328, "learning_rate": 6.3982028416946115e-06, "loss": 0.1547, "step": 394340 }, { "epoch": 2.344098293417979, "grad_norm": 4.908900737762451, "learning_rate": 6.398003626311242e-06, "loss": 0.1405, "step": 394350 }, { "epoch": 2.3441577354946475, "grad_norm": 6.31593656539917, "learning_rate": 6.3978044085203415e-06, "loss": 0.1472, "step": 394360 }, { "epoch": 2.3442171775713154, "grad_norm": 3.3152308464050293, "learning_rate": 6.397605188322256e-06, "loss": 0.1511, "step": 394370 }, { "epoch": 2.344276619647984, "grad_norm": 4.059660911560059, "learning_rate": 6.39740596571733e-06, "loss": 0.1566, "step": 394380 }, { "epoch": 2.3443360617246523, "grad_norm": 4.322113513946533, "learning_rate": 6.3972067407059e-06, "loss": 0.1506, "step": 394390 }, { "epoch": 2.3443955038013207, "grad_norm": 5.844548225402832, "learning_rate": 6.397007513288316e-06, "loss": 0.1502, "step": 394400 }, { "epoch": 2.344454945877989, "grad_norm": 5.277618885040283, "learning_rate": 6.396808283464917e-06, "loss": 0.1457, "step": 394410 }, { "epoch": 2.3445143879546575, "grad_norm": 4.123104572296143, "learning_rate": 6.3966090512360475e-06, "loss": 0.1449, "step": 394420 }, { "epoch": 2.344573830031326, "grad_norm": 4.372969627380371, "learning_rate": 6.396409816602052e-06, "loss": 0.1552, "step": 394430 }, { "epoch": 2.3446332721079943, "grad_norm": 3.3982632160186768, "learning_rate": 6.396210579563271e-06, "loss": 0.1394, "step": 394440 }, { "epoch": 2.3446927141846627, "grad_norm": 4.627988338470459, "learning_rate": 6.3960113401200494e-06, "loss": 0.1444, "step": 394450 }, { "epoch": 2.344752156261331, "grad_norm": 4.370353698730469, "learning_rate": 6.395812098272729e-06, "loss": 0.1305, "step": 394460 }, { "epoch": 2.3448115983379996, "grad_norm": 3.9726924896240234, "learning_rate": 6.395612854021653e-06, "loss": 0.1464, "step": 394470 }, { "epoch": 2.344871040414668, "grad_norm": 4.61533260345459, "learning_rate": 6.3954136073671665e-06, "loss": 0.1463, "step": 394480 }, { "epoch": 2.3449304824913364, "grad_norm": 4.931821346282959, "learning_rate": 6.395214358309612e-06, "loss": 0.1431, "step": 394490 }, { "epoch": 2.344989924568005, "grad_norm": 3.2448201179504395, "learning_rate": 6.39501510684933e-06, "loss": 0.1397, "step": 394500 }, { "epoch": 2.3450493666446732, "grad_norm": 3.6962578296661377, "learning_rate": 6.394815852986667e-06, "loss": 0.146, "step": 394510 }, { "epoch": 2.3451088087213416, "grad_norm": 3.2502381801605225, "learning_rate": 6.394616596721963e-06, "loss": 0.1301, "step": 394520 }, { "epoch": 2.34516825079801, "grad_norm": 4.52105188369751, "learning_rate": 6.3944173380555655e-06, "loss": 0.1476, "step": 394530 }, { "epoch": 2.345227692874678, "grad_norm": 4.437160015106201, "learning_rate": 6.394218076987813e-06, "loss": 0.1341, "step": 394540 }, { "epoch": 2.345287134951347, "grad_norm": 4.408355236053467, "learning_rate": 6.39401881351905e-06, "loss": 0.1472, "step": 394550 }, { "epoch": 2.345346577028015, "grad_norm": 3.428180694580078, "learning_rate": 6.393819547649621e-06, "loss": 0.1519, "step": 394560 }, { "epoch": 2.3454060191046833, "grad_norm": 3.881828546524048, "learning_rate": 6.3936202793798685e-06, "loss": 0.1477, "step": 394570 }, { "epoch": 2.3454654611813517, "grad_norm": 4.008359909057617, "learning_rate": 6.393421008710137e-06, "loss": 0.1541, "step": 394580 }, { "epoch": 2.34552490325802, "grad_norm": 4.1772942543029785, "learning_rate": 6.393221735640767e-06, "loss": 0.1535, "step": 394590 }, { "epoch": 2.3455843453346885, "grad_norm": 5.319736480712891, "learning_rate": 6.393022460172103e-06, "loss": 0.1605, "step": 394600 }, { "epoch": 2.345643787411357, "grad_norm": 3.5733442306518555, "learning_rate": 6.3928231823044885e-06, "loss": 0.1339, "step": 394610 }, { "epoch": 2.3457032294880253, "grad_norm": 4.9792962074279785, "learning_rate": 6.392623902038264e-06, "loss": 0.1475, "step": 394620 }, { "epoch": 2.3457626715646938, "grad_norm": 4.465094566345215, "learning_rate": 6.392424619373778e-06, "loss": 0.1464, "step": 394630 }, { "epoch": 2.345822113641362, "grad_norm": 3.292121171951294, "learning_rate": 6.3922253343113695e-06, "loss": 0.1538, "step": 394640 }, { "epoch": 2.3458815557180306, "grad_norm": 3.662846803665161, "learning_rate": 6.392026046851383e-06, "loss": 0.1497, "step": 394650 }, { "epoch": 2.345940997794699, "grad_norm": 3.786391019821167, "learning_rate": 6.391826756994161e-06, "loss": 0.146, "step": 394660 }, { "epoch": 2.3460004398713674, "grad_norm": 5.009781837463379, "learning_rate": 6.391627464740046e-06, "loss": 0.1425, "step": 394670 }, { "epoch": 2.346059881948036, "grad_norm": 3.737276077270508, "learning_rate": 6.3914281700893855e-06, "loss": 0.1593, "step": 394680 }, { "epoch": 2.3461193240247042, "grad_norm": 4.055874347686768, "learning_rate": 6.391228873042518e-06, "loss": 0.1435, "step": 394690 }, { "epoch": 2.3461787661013727, "grad_norm": 4.134233474731445, "learning_rate": 6.391029573599788e-06, "loss": 0.1422, "step": 394700 }, { "epoch": 2.346238208178041, "grad_norm": 4.2595391273498535, "learning_rate": 6.390830271761541e-06, "loss": 0.1516, "step": 394710 }, { "epoch": 2.3462976502547095, "grad_norm": 5.136131763458252, "learning_rate": 6.390630967528116e-06, "loss": 0.1581, "step": 394720 }, { "epoch": 2.3463570923313775, "grad_norm": 4.388710975646973, "learning_rate": 6.390431660899861e-06, "loss": 0.1511, "step": 394730 }, { "epoch": 2.3464165344080463, "grad_norm": 4.509921550750732, "learning_rate": 6.390232351877115e-06, "loss": 0.1455, "step": 394740 }, { "epoch": 2.3464759764847143, "grad_norm": 5.331092357635498, "learning_rate": 6.390033040460223e-06, "loss": 0.1449, "step": 394750 }, { "epoch": 2.3465354185613827, "grad_norm": 3.218536138534546, "learning_rate": 6.389833726649529e-06, "loss": 0.1233, "step": 394760 }, { "epoch": 2.346594860638051, "grad_norm": 5.085713863372803, "learning_rate": 6.389634410445376e-06, "loss": 0.1466, "step": 394770 }, { "epoch": 2.3466543027147195, "grad_norm": 4.693580150604248, "learning_rate": 6.389435091848105e-06, "loss": 0.1549, "step": 394780 }, { "epoch": 2.346713744791388, "grad_norm": 5.061334609985352, "learning_rate": 6.389235770858061e-06, "loss": 0.1427, "step": 394790 }, { "epoch": 2.3467731868680564, "grad_norm": 4.284424304962158, "learning_rate": 6.389036447475589e-06, "loss": 0.1298, "step": 394800 }, { "epoch": 2.3468326289447248, "grad_norm": 4.299707412719727, "learning_rate": 6.388837121701029e-06, "loss": 0.1366, "step": 394810 }, { "epoch": 2.346892071021393, "grad_norm": 5.387745380401611, "learning_rate": 6.388637793534726e-06, "loss": 0.1431, "step": 394820 }, { "epoch": 2.3469515130980616, "grad_norm": 3.6902809143066406, "learning_rate": 6.388438462977025e-06, "loss": 0.1366, "step": 394830 }, { "epoch": 2.34701095517473, "grad_norm": 4.377874374389648, "learning_rate": 6.388239130028265e-06, "loss": 0.1344, "step": 394840 }, { "epoch": 2.3470703972513984, "grad_norm": 3.530757188796997, "learning_rate": 6.388039794688792e-06, "loss": 0.1418, "step": 394850 }, { "epoch": 2.347129839328067, "grad_norm": 5.191511631011963, "learning_rate": 6.387840456958949e-06, "loss": 0.1532, "step": 394860 }, { "epoch": 2.3471892814047353, "grad_norm": 3.6532747745513916, "learning_rate": 6.38764111683908e-06, "loss": 0.1246, "step": 394870 }, { "epoch": 2.3472487234814037, "grad_norm": 5.646450996398926, "learning_rate": 6.387441774329526e-06, "loss": 0.1464, "step": 394880 }, { "epoch": 2.347308165558072, "grad_norm": 3.3129684925079346, "learning_rate": 6.387242429430632e-06, "loss": 0.1342, "step": 394890 }, { "epoch": 2.3473676076347405, "grad_norm": 4.963874816894531, "learning_rate": 6.387043082142742e-06, "loss": 0.1446, "step": 394900 }, { "epoch": 2.347427049711409, "grad_norm": 3.5749642848968506, "learning_rate": 6.386843732466197e-06, "loss": 0.148, "step": 394910 }, { "epoch": 2.347486491788077, "grad_norm": 4.245856761932373, "learning_rate": 6.3866443804013424e-06, "loss": 0.161, "step": 394920 }, { "epoch": 2.3475459338647453, "grad_norm": 4.467464923858643, "learning_rate": 6.386445025948521e-06, "loss": 0.1413, "step": 394930 }, { "epoch": 2.3476053759414137, "grad_norm": 4.148828983306885, "learning_rate": 6.386245669108076e-06, "loss": 0.1327, "step": 394940 }, { "epoch": 2.347664818018082, "grad_norm": 2.3451969623565674, "learning_rate": 6.386046309880349e-06, "loss": 0.1254, "step": 394950 }, { "epoch": 2.3477242600947505, "grad_norm": 5.254217147827148, "learning_rate": 6.385846948265687e-06, "loss": 0.1514, "step": 394960 }, { "epoch": 2.347783702171419, "grad_norm": 3.897862195968628, "learning_rate": 6.38564758426443e-06, "loss": 0.1347, "step": 394970 }, { "epoch": 2.3478431442480874, "grad_norm": 5.012956142425537, "learning_rate": 6.385448217876923e-06, "loss": 0.1394, "step": 394980 }, { "epoch": 2.347902586324756, "grad_norm": 5.191203594207764, "learning_rate": 6.385248849103508e-06, "loss": 0.1423, "step": 394990 }, { "epoch": 2.347962028401424, "grad_norm": 5.53385591506958, "learning_rate": 6.3850494779445295e-06, "loss": 0.1421, "step": 395000 }, { "epoch": 2.3480214704780926, "grad_norm": 4.251330375671387, "learning_rate": 6.3848501044003305e-06, "loss": 0.1482, "step": 395010 }, { "epoch": 2.348080912554761, "grad_norm": 4.1383056640625, "learning_rate": 6.3846507284712544e-06, "loss": 0.1547, "step": 395020 }, { "epoch": 2.3481403546314294, "grad_norm": 4.543707847595215, "learning_rate": 6.384451350157646e-06, "loss": 0.1421, "step": 395030 }, { "epoch": 2.348199796708098, "grad_norm": 5.314303874969482, "learning_rate": 6.384251969459845e-06, "loss": 0.1539, "step": 395040 }, { "epoch": 2.3482592387847663, "grad_norm": 3.5907368659973145, "learning_rate": 6.384052586378198e-06, "loss": 0.1398, "step": 395050 }, { "epoch": 2.3483186808614347, "grad_norm": 5.199074745178223, "learning_rate": 6.383853200913049e-06, "loss": 0.1534, "step": 395060 }, { "epoch": 2.348378122938103, "grad_norm": 3.848630905151367, "learning_rate": 6.383653813064737e-06, "loss": 0.1473, "step": 395070 }, { "epoch": 2.3484375650147715, "grad_norm": 4.471967697143555, "learning_rate": 6.383454422833608e-06, "loss": 0.1368, "step": 395080 }, { "epoch": 2.34849700709144, "grad_norm": 4.683719158172607, "learning_rate": 6.383255030220007e-06, "loss": 0.1398, "step": 395090 }, { "epoch": 2.3485564491681084, "grad_norm": 4.011142730712891, "learning_rate": 6.383055635224275e-06, "loss": 0.151, "step": 395100 }, { "epoch": 2.3486158912447763, "grad_norm": 4.165304660797119, "learning_rate": 6.382856237846755e-06, "loss": 0.1572, "step": 395110 }, { "epoch": 2.3486753333214447, "grad_norm": 4.115835666656494, "learning_rate": 6.382656838087793e-06, "loss": 0.1377, "step": 395120 }, { "epoch": 2.348734775398113, "grad_norm": 3.346031904220581, "learning_rate": 6.382457435947732e-06, "loss": 0.1213, "step": 395130 }, { "epoch": 2.3487942174747816, "grad_norm": 4.566869258880615, "learning_rate": 6.382258031426912e-06, "loss": 0.1449, "step": 395140 }, { "epoch": 2.34885365955145, "grad_norm": 5.433873653411865, "learning_rate": 6.38205862452568e-06, "loss": 0.1613, "step": 395150 }, { "epoch": 2.3489131016281184, "grad_norm": 4.247684955596924, "learning_rate": 6.381859215244379e-06, "loss": 0.1303, "step": 395160 }, { "epoch": 2.348972543704787, "grad_norm": 5.277197360992432, "learning_rate": 6.38165980358335e-06, "loss": 0.1444, "step": 395170 }, { "epoch": 2.3490319857814552, "grad_norm": 3.184091329574585, "learning_rate": 6.38146038954294e-06, "loss": 0.1419, "step": 395180 }, { "epoch": 2.3490914278581236, "grad_norm": 4.495543956756592, "learning_rate": 6.381260973123489e-06, "loss": 0.13, "step": 395190 }, { "epoch": 2.349150869934792, "grad_norm": 3.0613503456115723, "learning_rate": 6.381061554325341e-06, "loss": 0.1424, "step": 395200 }, { "epoch": 2.3492103120114605, "grad_norm": 3.7975776195526123, "learning_rate": 6.3808621331488406e-06, "loss": 0.1244, "step": 395210 }, { "epoch": 2.349269754088129, "grad_norm": 3.255732774734497, "learning_rate": 6.380662709594331e-06, "loss": 0.1303, "step": 395220 }, { "epoch": 2.3493291961647973, "grad_norm": 6.408439636230469, "learning_rate": 6.380463283662155e-06, "loss": 0.1335, "step": 395230 }, { "epoch": 2.3493886382414657, "grad_norm": 3.2703213691711426, "learning_rate": 6.3802638553526575e-06, "loss": 0.1546, "step": 395240 }, { "epoch": 2.349448080318134, "grad_norm": 5.32524299621582, "learning_rate": 6.38006442466618e-06, "loss": 0.1778, "step": 395250 }, { "epoch": 2.3495075223948025, "grad_norm": 3.1862499713897705, "learning_rate": 6.379864991603068e-06, "loss": 0.1246, "step": 395260 }, { "epoch": 2.349566964471471, "grad_norm": 3.509539842605591, "learning_rate": 6.379665556163663e-06, "loss": 0.1235, "step": 395270 }, { "epoch": 2.349626406548139, "grad_norm": 3.80029034614563, "learning_rate": 6.37946611834831e-06, "loss": 0.1376, "step": 395280 }, { "epoch": 2.349685848624808, "grad_norm": 4.271268844604492, "learning_rate": 6.379266678157352e-06, "loss": 0.1316, "step": 395290 }, { "epoch": 2.3497452907014758, "grad_norm": 4.126351833343506, "learning_rate": 6.379067235591131e-06, "loss": 0.1518, "step": 395300 }, { "epoch": 2.349804732778144, "grad_norm": 5.206073760986328, "learning_rate": 6.378867790649993e-06, "loss": 0.1538, "step": 395310 }, { "epoch": 2.3498641748548126, "grad_norm": 4.300022602081299, "learning_rate": 6.37866834333428e-06, "loss": 0.1427, "step": 395320 }, { "epoch": 2.349923616931481, "grad_norm": 3.4135918617248535, "learning_rate": 6.378468893644334e-06, "loss": 0.1593, "step": 395330 }, { "epoch": 2.3499830590081494, "grad_norm": 3.550130605697632, "learning_rate": 6.3782694415805005e-06, "loss": 0.1383, "step": 395340 }, { "epoch": 2.350042501084818, "grad_norm": 4.191038608551025, "learning_rate": 6.378069987143123e-06, "loss": 0.1469, "step": 395350 }, { "epoch": 2.3501019431614862, "grad_norm": 4.718743324279785, "learning_rate": 6.377870530332546e-06, "loss": 0.1594, "step": 395360 }, { "epoch": 2.3501613852381547, "grad_norm": 4.975825786590576, "learning_rate": 6.37767107114911e-06, "loss": 0.1553, "step": 395370 }, { "epoch": 2.350220827314823, "grad_norm": 4.974530220031738, "learning_rate": 6.3774716095931596e-06, "loss": 0.1584, "step": 395380 }, { "epoch": 2.3502802693914915, "grad_norm": 4.660994052886963, "learning_rate": 6.37727214566504e-06, "loss": 0.1507, "step": 395390 }, { "epoch": 2.35033971146816, "grad_norm": 4.933505058288574, "learning_rate": 6.377072679365092e-06, "loss": 0.1463, "step": 395400 }, { "epoch": 2.3503991535448283, "grad_norm": 4.505693435668945, "learning_rate": 6.376873210693662e-06, "loss": 0.1469, "step": 395410 }, { "epoch": 2.3504585956214967, "grad_norm": 5.442513942718506, "learning_rate": 6.376673739651092e-06, "loss": 0.1473, "step": 395420 }, { "epoch": 2.350518037698165, "grad_norm": 4.023667335510254, "learning_rate": 6.376474266237724e-06, "loss": 0.143, "step": 395430 }, { "epoch": 2.3505774797748336, "grad_norm": 4.781104564666748, "learning_rate": 6.376274790453904e-06, "loss": 0.1421, "step": 395440 }, { "epoch": 2.350636921851502, "grad_norm": 3.801750421524048, "learning_rate": 6.376075312299975e-06, "loss": 0.1173, "step": 395450 }, { "epoch": 2.3506963639281704, "grad_norm": 4.5395941734313965, "learning_rate": 6.375875831776281e-06, "loss": 0.1427, "step": 395460 }, { "epoch": 2.3507558060048384, "grad_norm": 4.797984600067139, "learning_rate": 6.375676348883162e-06, "loss": 0.1567, "step": 395470 }, { "epoch": 2.350815248081507, "grad_norm": 5.128886699676514, "learning_rate": 6.3754768636209664e-06, "loss": 0.1523, "step": 395480 }, { "epoch": 2.350874690158175, "grad_norm": 3.4056236743927, "learning_rate": 6.375277375990035e-06, "loss": 0.1435, "step": 395490 }, { "epoch": 2.3509341322348436, "grad_norm": 3.7857489585876465, "learning_rate": 6.375077885990711e-06, "loss": 0.1384, "step": 395500 }, { "epoch": 2.350993574311512, "grad_norm": 5.208610534667969, "learning_rate": 6.3748783936233405e-06, "loss": 0.1575, "step": 395510 }, { "epoch": 2.3510530163881804, "grad_norm": 3.8615992069244385, "learning_rate": 6.3746788988882644e-06, "loss": 0.125, "step": 395520 }, { "epoch": 2.351112458464849, "grad_norm": 3.7429730892181396, "learning_rate": 6.374479401785826e-06, "loss": 0.1399, "step": 395530 }, { "epoch": 2.3511719005415173, "grad_norm": 3.5838444232940674, "learning_rate": 6.374279902316371e-06, "loss": 0.1659, "step": 395540 }, { "epoch": 2.3512313426181857, "grad_norm": 3.4833621978759766, "learning_rate": 6.374080400480243e-06, "loss": 0.1418, "step": 395550 }, { "epoch": 2.351290784694854, "grad_norm": 5.338147163391113, "learning_rate": 6.373880896277782e-06, "loss": 0.1433, "step": 395560 }, { "epoch": 2.3513502267715225, "grad_norm": 3.9185454845428467, "learning_rate": 6.3736813897093365e-06, "loss": 0.14, "step": 395570 }, { "epoch": 2.351409668848191, "grad_norm": 3.152873992919922, "learning_rate": 6.373481880775247e-06, "loss": 0.143, "step": 395580 }, { "epoch": 2.3514691109248593, "grad_norm": 4.823245525360107, "learning_rate": 6.373282369475858e-06, "loss": 0.1317, "step": 395590 }, { "epoch": 2.3515285530015277, "grad_norm": 4.631735801696777, "learning_rate": 6.3730828558115145e-06, "loss": 0.1529, "step": 395600 }, { "epoch": 2.351587995078196, "grad_norm": 3.0211892127990723, "learning_rate": 6.372883339782556e-06, "loss": 0.15, "step": 395610 }, { "epoch": 2.3516474371548646, "grad_norm": 4.699766635894775, "learning_rate": 6.372683821389329e-06, "loss": 0.1487, "step": 395620 }, { "epoch": 2.351706879231533, "grad_norm": 4.011874675750732, "learning_rate": 6.372484300632178e-06, "loss": 0.147, "step": 395630 }, { "epoch": 2.3517663213082014, "grad_norm": 4.883833885192871, "learning_rate": 6.3722847775114445e-06, "loss": 0.1358, "step": 395640 }, { "epoch": 2.35182576338487, "grad_norm": 4.112217426300049, "learning_rate": 6.372085252027473e-06, "loss": 0.1455, "step": 395650 }, { "epoch": 2.351885205461538, "grad_norm": 4.647139549255371, "learning_rate": 6.371885724180606e-06, "loss": 0.1567, "step": 395660 }, { "epoch": 2.351944647538206, "grad_norm": 4.292975425720215, "learning_rate": 6.371686193971189e-06, "loss": 0.1761, "step": 395670 }, { "epoch": 2.3520040896148746, "grad_norm": 4.090628147125244, "learning_rate": 6.3714866613995655e-06, "loss": 0.1501, "step": 395680 }, { "epoch": 2.352063531691543, "grad_norm": 4.2303924560546875, "learning_rate": 6.371287126466077e-06, "loss": 0.144, "step": 395690 }, { "epoch": 2.3521229737682114, "grad_norm": 3.887808322906494, "learning_rate": 6.371087589171069e-06, "loss": 0.138, "step": 395700 }, { "epoch": 2.35218241584488, "grad_norm": 5.083089828491211, "learning_rate": 6.370888049514885e-06, "loss": 0.1574, "step": 395710 }, { "epoch": 2.3522418579215483, "grad_norm": 4.340695858001709, "learning_rate": 6.370688507497866e-06, "loss": 0.1403, "step": 395720 }, { "epoch": 2.3523012999982167, "grad_norm": 3.8855838775634766, "learning_rate": 6.37048896312036e-06, "loss": 0.1478, "step": 395730 }, { "epoch": 2.352360742074885, "grad_norm": 3.679384231567383, "learning_rate": 6.370289416382709e-06, "loss": 0.1374, "step": 395740 }, { "epoch": 2.3524201841515535, "grad_norm": 3.2829129695892334, "learning_rate": 6.3700898672852544e-06, "loss": 0.1892, "step": 395750 }, { "epoch": 2.352479626228222, "grad_norm": 3.6027467250823975, "learning_rate": 6.3698903158283435e-06, "loss": 0.1468, "step": 395760 }, { "epoch": 2.3525390683048903, "grad_norm": 3.541916847229004, "learning_rate": 6.369690762012315e-06, "loss": 0.1562, "step": 395770 }, { "epoch": 2.3525985103815588, "grad_norm": 4.0514140129089355, "learning_rate": 6.369491205837518e-06, "loss": 0.1407, "step": 395780 }, { "epoch": 2.352657952458227, "grad_norm": 4.4331231117248535, "learning_rate": 6.369291647304292e-06, "loss": 0.139, "step": 395790 }, { "epoch": 2.3527173945348956, "grad_norm": 5.062521457672119, "learning_rate": 6.3690920864129845e-06, "loss": 0.1441, "step": 395800 }, { "epoch": 2.352776836611564, "grad_norm": 3.97397518157959, "learning_rate": 6.368892523163937e-06, "loss": 0.1397, "step": 395810 }, { "epoch": 2.3528362786882324, "grad_norm": 3.5592739582061768, "learning_rate": 6.368692957557492e-06, "loss": 0.1547, "step": 395820 }, { "epoch": 2.352895720764901, "grad_norm": 3.897129774093628, "learning_rate": 6.368493389593995e-06, "loss": 0.1555, "step": 395830 }, { "epoch": 2.3529551628415692, "grad_norm": 5.146586894989014, "learning_rate": 6.368293819273788e-06, "loss": 0.1383, "step": 395840 }, { "epoch": 2.353014604918237, "grad_norm": 5.165837287902832, "learning_rate": 6.368094246597216e-06, "loss": 0.1463, "step": 395850 }, { "epoch": 2.3530740469949056, "grad_norm": 4.469364166259766, "learning_rate": 6.367894671564625e-06, "loss": 0.149, "step": 395860 }, { "epoch": 2.353133489071574, "grad_norm": 4.2082085609436035, "learning_rate": 6.367695094176354e-06, "loss": 0.1336, "step": 395870 }, { "epoch": 2.3531929311482425, "grad_norm": 6.859708786010742, "learning_rate": 6.367495514432749e-06, "loss": 0.1387, "step": 395880 }, { "epoch": 2.353252373224911, "grad_norm": 4.103846073150635, "learning_rate": 6.367295932334152e-06, "loss": 0.1574, "step": 395890 }, { "epoch": 2.3533118153015793, "grad_norm": 2.7069485187530518, "learning_rate": 6.367096347880911e-06, "loss": 0.1392, "step": 395900 }, { "epoch": 2.3533712573782477, "grad_norm": 4.001315116882324, "learning_rate": 6.366896761073367e-06, "loss": 0.1412, "step": 395910 }, { "epoch": 2.353430699454916, "grad_norm": 4.8814263343811035, "learning_rate": 6.366697171911861e-06, "loss": 0.155, "step": 395920 }, { "epoch": 2.3534901415315845, "grad_norm": 4.219954490661621, "learning_rate": 6.366497580396742e-06, "loss": 0.1243, "step": 395930 }, { "epoch": 2.353549583608253, "grad_norm": 4.27693510055542, "learning_rate": 6.36629798652835e-06, "loss": 0.1574, "step": 395940 }, { "epoch": 2.3536090256849214, "grad_norm": 5.7712202072143555, "learning_rate": 6.366098390307029e-06, "loss": 0.1577, "step": 395950 }, { "epoch": 2.3536684677615898, "grad_norm": 3.8850739002227783, "learning_rate": 6.365898791733125e-06, "loss": 0.1441, "step": 395960 }, { "epoch": 2.353727909838258, "grad_norm": 3.7566871643066406, "learning_rate": 6.365699190806981e-06, "loss": 0.1449, "step": 395970 }, { "epoch": 2.3537873519149266, "grad_norm": 4.702116012573242, "learning_rate": 6.365499587528938e-06, "loss": 0.1305, "step": 395980 }, { "epoch": 2.353846793991595, "grad_norm": 4.612720966339111, "learning_rate": 6.365299981899342e-06, "loss": 0.1429, "step": 395990 }, { "epoch": 2.3539062360682634, "grad_norm": 4.129973411560059, "learning_rate": 6.365100373918538e-06, "loss": 0.1373, "step": 396000 }, { "epoch": 2.353965678144932, "grad_norm": 5.021337985992432, "learning_rate": 6.364900763586868e-06, "loss": 0.1439, "step": 396010 }, { "epoch": 2.3540251202216, "grad_norm": 3.1172611713409424, "learning_rate": 6.364701150904674e-06, "loss": 0.1568, "step": 396020 }, { "epoch": 2.3540845622982687, "grad_norm": 4.792718410491943, "learning_rate": 6.364501535872304e-06, "loss": 0.1372, "step": 396030 }, { "epoch": 2.3541440043749366, "grad_norm": 5.0710129737854, "learning_rate": 6.364301918490099e-06, "loss": 0.1518, "step": 396040 }, { "epoch": 2.354203446451605, "grad_norm": 3.2627718448638916, "learning_rate": 6.364102298758402e-06, "loss": 0.1382, "step": 396050 }, { "epoch": 2.3542628885282735, "grad_norm": 5.247927188873291, "learning_rate": 6.3639026766775604e-06, "loss": 0.1313, "step": 396060 }, { "epoch": 2.354322330604942, "grad_norm": 4.557220458984375, "learning_rate": 6.363703052247915e-06, "loss": 0.1637, "step": 396070 }, { "epoch": 2.3543817726816103, "grad_norm": 3.7184479236602783, "learning_rate": 6.363503425469808e-06, "loss": 0.147, "step": 396080 }, { "epoch": 2.3544412147582787, "grad_norm": 4.014675617218018, "learning_rate": 6.363303796343588e-06, "loss": 0.1439, "step": 396090 }, { "epoch": 2.354500656834947, "grad_norm": 3.602574110031128, "learning_rate": 6.363104164869595e-06, "loss": 0.1511, "step": 396100 }, { "epoch": 2.3545600989116156, "grad_norm": 3.9694154262542725, "learning_rate": 6.362904531048175e-06, "loss": 0.1376, "step": 396110 }, { "epoch": 2.354619540988284, "grad_norm": 3.8929836750030518, "learning_rate": 6.3627048948796685e-06, "loss": 0.1389, "step": 396120 }, { "epoch": 2.3546789830649524, "grad_norm": 5.093876838684082, "learning_rate": 6.362505256364424e-06, "loss": 0.1502, "step": 396130 }, { "epoch": 2.354738425141621, "grad_norm": 3.559438467025757, "learning_rate": 6.362305615502782e-06, "loss": 0.1495, "step": 396140 }, { "epoch": 2.354797867218289, "grad_norm": 3.3973584175109863, "learning_rate": 6.362105972295087e-06, "loss": 0.151, "step": 396150 }, { "epoch": 2.3548573092949576, "grad_norm": 3.835357904434204, "learning_rate": 6.3619063267416835e-06, "loss": 0.1283, "step": 396160 }, { "epoch": 2.354916751371626, "grad_norm": 4.484799861907959, "learning_rate": 6.361706678842915e-06, "loss": 0.14, "step": 396170 }, { "epoch": 2.3549761934482945, "grad_norm": 4.5570969581604, "learning_rate": 6.361507028599125e-06, "loss": 0.1334, "step": 396180 }, { "epoch": 2.355035635524963, "grad_norm": 3.4279263019561768, "learning_rate": 6.3613073760106566e-06, "loss": 0.1435, "step": 396190 }, { "epoch": 2.3550950776016313, "grad_norm": 3.4430274963378906, "learning_rate": 6.3611077210778545e-06, "loss": 0.1262, "step": 396200 }, { "epoch": 2.3551545196782993, "grad_norm": 4.337739944458008, "learning_rate": 6.3609080638010624e-06, "loss": 0.1434, "step": 396210 }, { "epoch": 2.355213961754968, "grad_norm": 3.3294787406921387, "learning_rate": 6.360708404180624e-06, "loss": 0.1402, "step": 396220 }, { "epoch": 2.355273403831636, "grad_norm": 3.4983229637145996, "learning_rate": 6.360508742216885e-06, "loss": 0.1456, "step": 396230 }, { "epoch": 2.3553328459083045, "grad_norm": 3.9073946475982666, "learning_rate": 6.3603090779101866e-06, "loss": 0.1273, "step": 396240 }, { "epoch": 2.355392287984973, "grad_norm": 4.237303733825684, "learning_rate": 6.360109411260874e-06, "loss": 0.15, "step": 396250 }, { "epoch": 2.3554517300616413, "grad_norm": 4.595129489898682, "learning_rate": 6.359909742269291e-06, "loss": 0.1502, "step": 396260 }, { "epoch": 2.3555111721383097, "grad_norm": 3.205934524536133, "learning_rate": 6.35971007093578e-06, "loss": 0.1513, "step": 396270 }, { "epoch": 2.355570614214978, "grad_norm": 4.2151288986206055, "learning_rate": 6.3595103972606864e-06, "loss": 0.1475, "step": 396280 }, { "epoch": 2.3556300562916466, "grad_norm": 4.717517852783203, "learning_rate": 6.359310721244355e-06, "loss": 0.1442, "step": 396290 }, { "epoch": 2.355689498368315, "grad_norm": 3.4513742923736572, "learning_rate": 6.359111042887127e-06, "loss": 0.1381, "step": 396300 }, { "epoch": 2.3557489404449834, "grad_norm": 4.403321266174316, "learning_rate": 6.358911362189348e-06, "loss": 0.1449, "step": 396310 }, { "epoch": 2.355808382521652, "grad_norm": 3.7579967975616455, "learning_rate": 6.358711679151362e-06, "loss": 0.1213, "step": 396320 }, { "epoch": 2.3558678245983202, "grad_norm": 3.8215854167938232, "learning_rate": 6.3585119937735105e-06, "loss": 0.1368, "step": 396330 }, { "epoch": 2.3559272666749886, "grad_norm": 3.670468807220459, "learning_rate": 6.358312306056141e-06, "loss": 0.1491, "step": 396340 }, { "epoch": 2.355986708751657, "grad_norm": 4.294921398162842, "learning_rate": 6.358112615999595e-06, "loss": 0.1316, "step": 396350 }, { "epoch": 2.3560461508283255, "grad_norm": 4.599114418029785, "learning_rate": 6.357912923604218e-06, "loss": 0.1433, "step": 396360 }, { "epoch": 2.356105592904994, "grad_norm": 5.6744256019592285, "learning_rate": 6.357713228870351e-06, "loss": 0.1469, "step": 396370 }, { "epoch": 2.3561650349816623, "grad_norm": 4.243984222412109, "learning_rate": 6.357513531798342e-06, "loss": 0.1301, "step": 396380 }, { "epoch": 2.3562244770583307, "grad_norm": 3.950652599334717, "learning_rate": 6.357313832388532e-06, "loss": 0.1486, "step": 396390 }, { "epoch": 2.3562839191349987, "grad_norm": 4.710860729217529, "learning_rate": 6.357114130641264e-06, "loss": 0.1591, "step": 396400 }, { "epoch": 2.356343361211667, "grad_norm": 5.124824523925781, "learning_rate": 6.356914426556886e-06, "loss": 0.141, "step": 396410 }, { "epoch": 2.3564028032883355, "grad_norm": 4.646284103393555, "learning_rate": 6.356714720135738e-06, "loss": 0.1418, "step": 396420 }, { "epoch": 2.356462245365004, "grad_norm": 3.589341640472412, "learning_rate": 6.356515011378166e-06, "loss": 0.1532, "step": 396430 }, { "epoch": 2.3565216874416723, "grad_norm": 3.232365846633911, "learning_rate": 6.356315300284511e-06, "loss": 0.1378, "step": 396440 }, { "epoch": 2.3565811295183408, "grad_norm": 5.151596546173096, "learning_rate": 6.3561155868551225e-06, "loss": 0.1341, "step": 396450 }, { "epoch": 2.356640571595009, "grad_norm": 4.562568187713623, "learning_rate": 6.35591587109034e-06, "loss": 0.158, "step": 396460 }, { "epoch": 2.3567000136716776, "grad_norm": 3.74064040184021, "learning_rate": 6.355716152990508e-06, "loss": 0.1304, "step": 396470 }, { "epoch": 2.356759455748346, "grad_norm": 3.3696014881134033, "learning_rate": 6.355516432555971e-06, "loss": 0.1405, "step": 396480 }, { "epoch": 2.3568188978250144, "grad_norm": 4.302778720855713, "learning_rate": 6.3553167097870735e-06, "loss": 0.1515, "step": 396490 }, { "epoch": 2.356878339901683, "grad_norm": 4.652613162994385, "learning_rate": 6.355116984684159e-06, "loss": 0.1548, "step": 396500 }, { "epoch": 2.3569377819783512, "grad_norm": 5.075877666473389, "learning_rate": 6.354917257247572e-06, "loss": 0.1618, "step": 396510 }, { "epoch": 2.3569972240550197, "grad_norm": 5.683459281921387, "learning_rate": 6.3547175274776555e-06, "loss": 0.1416, "step": 396520 }, { "epoch": 2.357056666131688, "grad_norm": 5.063992977142334, "learning_rate": 6.354517795374753e-06, "loss": 0.1342, "step": 396530 }, { "epoch": 2.3571161082083565, "grad_norm": 4.299761772155762, "learning_rate": 6.354318060939209e-06, "loss": 0.1239, "step": 396540 }, { "epoch": 2.357175550285025, "grad_norm": 5.101398944854736, "learning_rate": 6.354118324171368e-06, "loss": 0.1567, "step": 396550 }, { "epoch": 2.3572349923616933, "grad_norm": 4.223268508911133, "learning_rate": 6.3539185850715745e-06, "loss": 0.1493, "step": 396560 }, { "epoch": 2.3572944344383617, "grad_norm": 4.917871475219727, "learning_rate": 6.353718843640169e-06, "loss": 0.1337, "step": 396570 }, { "epoch": 2.35735387651503, "grad_norm": 4.587557792663574, "learning_rate": 6.353519099877501e-06, "loss": 0.1348, "step": 396580 }, { "epoch": 2.357413318591698, "grad_norm": 4.970117568969727, "learning_rate": 6.353319353783912e-06, "loss": 0.1302, "step": 396590 }, { "epoch": 2.3574727606683665, "grad_norm": 6.050589084625244, "learning_rate": 6.3531196053597434e-06, "loss": 0.1622, "step": 396600 }, { "epoch": 2.357532202745035, "grad_norm": 3.820540189743042, "learning_rate": 6.352919854605343e-06, "loss": 0.1519, "step": 396610 }, { "epoch": 2.3575916448217034, "grad_norm": 5.356147289276123, "learning_rate": 6.3527201015210525e-06, "loss": 0.143, "step": 396620 }, { "epoch": 2.3576510868983718, "grad_norm": 5.0191264152526855, "learning_rate": 6.352520346107216e-06, "loss": 0.1464, "step": 396630 }, { "epoch": 2.35771052897504, "grad_norm": 3.409701108932495, "learning_rate": 6.352320588364179e-06, "loss": 0.1538, "step": 396640 }, { "epoch": 2.3577699710517086, "grad_norm": 4.33209228515625, "learning_rate": 6.352120828292284e-06, "loss": 0.1475, "step": 396650 }, { "epoch": 2.357829413128377, "grad_norm": 3.8537867069244385, "learning_rate": 6.351921065891876e-06, "loss": 0.1433, "step": 396660 }, { "epoch": 2.3578888552050454, "grad_norm": 4.402422904968262, "learning_rate": 6.351721301163298e-06, "loss": 0.1469, "step": 396670 }, { "epoch": 2.357948297281714, "grad_norm": 3.2422382831573486, "learning_rate": 6.351521534106896e-06, "loss": 0.13, "step": 396680 }, { "epoch": 2.3580077393583823, "grad_norm": 5.025657653808594, "learning_rate": 6.3513217647230115e-06, "loss": 0.1647, "step": 396690 }, { "epoch": 2.3580671814350507, "grad_norm": 3.895026445388794, "learning_rate": 6.35112199301199e-06, "loss": 0.1439, "step": 396700 }, { "epoch": 2.358126623511719, "grad_norm": 4.186173915863037, "learning_rate": 6.3509222189741755e-06, "loss": 0.1412, "step": 396710 }, { "epoch": 2.3581860655883875, "grad_norm": 5.1223931312561035, "learning_rate": 6.350722442609912e-06, "loss": 0.1489, "step": 396720 }, { "epoch": 2.358245507665056, "grad_norm": 4.390471935272217, "learning_rate": 6.3505226639195425e-06, "loss": 0.144, "step": 396730 }, { "epoch": 2.3583049497417243, "grad_norm": 4.724607944488525, "learning_rate": 6.350322882903412e-06, "loss": 0.1431, "step": 396740 }, { "epoch": 2.3583643918183927, "grad_norm": 4.199368476867676, "learning_rate": 6.3501230995618645e-06, "loss": 0.1439, "step": 396750 }, { "epoch": 2.3584238338950607, "grad_norm": 3.3668057918548584, "learning_rate": 6.349923313895243e-06, "loss": 0.1415, "step": 396760 }, { "epoch": 2.3584832759717296, "grad_norm": 5.136226654052734, "learning_rate": 6.3497235259038935e-06, "loss": 0.1579, "step": 396770 }, { "epoch": 2.3585427180483975, "grad_norm": 4.825159072875977, "learning_rate": 6.349523735588159e-06, "loss": 0.1309, "step": 396780 }, { "epoch": 2.358602160125066, "grad_norm": 4.113166332244873, "learning_rate": 6.349323942948384e-06, "loss": 0.1471, "step": 396790 }, { "epoch": 2.3586616022017344, "grad_norm": 2.6125447750091553, "learning_rate": 6.349124147984911e-06, "loss": 0.1392, "step": 396800 }, { "epoch": 2.358721044278403, "grad_norm": 3.646773338317871, "learning_rate": 6.348924350698087e-06, "loss": 0.132, "step": 396810 }, { "epoch": 2.358780486355071, "grad_norm": 4.352684020996094, "learning_rate": 6.348724551088254e-06, "loss": 0.1422, "step": 396820 }, { "epoch": 2.3588399284317396, "grad_norm": 2.9760196208953857, "learning_rate": 6.348524749155754e-06, "loss": 0.1459, "step": 396830 }, { "epoch": 2.358899370508408, "grad_norm": 3.633838415145874, "learning_rate": 6.348324944900936e-06, "loss": 0.1352, "step": 396840 }, { "epoch": 2.3589588125850764, "grad_norm": 3.644155979156494, "learning_rate": 6.3481251383241415e-06, "loss": 0.1466, "step": 396850 }, { "epoch": 2.359018254661745, "grad_norm": 5.136054515838623, "learning_rate": 6.3479253294257125e-06, "loss": 0.1432, "step": 396860 }, { "epoch": 2.3590776967384133, "grad_norm": 3.540802240371704, "learning_rate": 6.347725518205996e-06, "loss": 0.1679, "step": 396870 }, { "epoch": 2.3591371388150817, "grad_norm": 3.369034767150879, "learning_rate": 6.347525704665336e-06, "loss": 0.1418, "step": 396880 }, { "epoch": 2.35919658089175, "grad_norm": 4.747463226318359, "learning_rate": 6.347325888804076e-06, "loss": 0.1532, "step": 396890 }, { "epoch": 2.3592560229684185, "grad_norm": 4.779006004333496, "learning_rate": 6.34712607062256e-06, "loss": 0.1392, "step": 396900 }, { "epoch": 2.359315465045087, "grad_norm": 3.40647029876709, "learning_rate": 6.346926250121133e-06, "loss": 0.135, "step": 396910 }, { "epoch": 2.3593749071217553, "grad_norm": 3.461282253265381, "learning_rate": 6.346726427300136e-06, "loss": 0.1445, "step": 396920 }, { "epoch": 2.3594343491984238, "grad_norm": 3.296865463256836, "learning_rate": 6.346526602159917e-06, "loss": 0.1398, "step": 396930 }, { "epoch": 2.359493791275092, "grad_norm": 5.143491744995117, "learning_rate": 6.3463267747008194e-06, "loss": 0.1687, "step": 396940 }, { "epoch": 2.35955323335176, "grad_norm": 4.098423004150391, "learning_rate": 6.346126944923184e-06, "loss": 0.146, "step": 396950 }, { "epoch": 2.359612675428429, "grad_norm": 4.30057954788208, "learning_rate": 6.34592711282736e-06, "loss": 0.1527, "step": 396960 }, { "epoch": 2.359672117505097, "grad_norm": 4.649419784545898, "learning_rate": 6.3457272784136885e-06, "loss": 0.1457, "step": 396970 }, { "epoch": 2.3597315595817654, "grad_norm": 3.3116822242736816, "learning_rate": 6.345527441682512e-06, "loss": 0.1282, "step": 396980 }, { "epoch": 2.359791001658434, "grad_norm": 4.815757751464844, "learning_rate": 6.345327602634177e-06, "loss": 0.1483, "step": 396990 }, { "epoch": 2.359850443735102, "grad_norm": 4.215317726135254, "learning_rate": 6.34512776126903e-06, "loss": 0.1507, "step": 397000 }, { "epoch": 2.3599098858117706, "grad_norm": 3.936330556869507, "learning_rate": 6.34492791758741e-06, "loss": 0.1464, "step": 397010 }, { "epoch": 2.359969327888439, "grad_norm": 3.224365711212158, "learning_rate": 6.344728071589664e-06, "loss": 0.1501, "step": 397020 }, { "epoch": 2.3600287699651075, "grad_norm": 4.534015655517578, "learning_rate": 6.3445282232761365e-06, "loss": 0.1414, "step": 397030 }, { "epoch": 2.360088212041776, "grad_norm": 3.329218864440918, "learning_rate": 6.344328372647172e-06, "loss": 0.1412, "step": 397040 }, { "epoch": 2.3601476541184443, "grad_norm": 3.4805428981781006, "learning_rate": 6.344128519703111e-06, "loss": 0.1365, "step": 397050 }, { "epoch": 2.3602070961951127, "grad_norm": 4.574225902557373, "learning_rate": 6.343928664444302e-06, "loss": 0.139, "step": 397060 }, { "epoch": 2.360266538271781, "grad_norm": 5.016386985778809, "learning_rate": 6.3437288068710874e-06, "loss": 0.1536, "step": 397070 }, { "epoch": 2.3603259803484495, "grad_norm": 3.731417179107666, "learning_rate": 6.343528946983811e-06, "loss": 0.1364, "step": 397080 }, { "epoch": 2.360385422425118, "grad_norm": 5.078662872314453, "learning_rate": 6.343329084782817e-06, "loss": 0.151, "step": 397090 }, { "epoch": 2.3604448645017864, "grad_norm": 4.273382663726807, "learning_rate": 6.343129220268451e-06, "loss": 0.1388, "step": 397100 }, { "epoch": 2.360504306578455, "grad_norm": 3.8368630409240723, "learning_rate": 6.342929353441056e-06, "loss": 0.149, "step": 397110 }, { "epoch": 2.360563748655123, "grad_norm": 4.006324768066406, "learning_rate": 6.342729484300977e-06, "loss": 0.1437, "step": 397120 }, { "epoch": 2.3606231907317916, "grad_norm": 5.069454193115234, "learning_rate": 6.342529612848557e-06, "loss": 0.1421, "step": 397130 }, { "epoch": 2.3606826328084596, "grad_norm": 3.7510764598846436, "learning_rate": 6.342329739084141e-06, "loss": 0.1519, "step": 397140 }, { "epoch": 2.360742074885128, "grad_norm": 4.1736741065979, "learning_rate": 6.342129863008072e-06, "loss": 0.1484, "step": 397150 }, { "epoch": 2.3608015169617964, "grad_norm": 4.017616271972656, "learning_rate": 6.341929984620696e-06, "loss": 0.1485, "step": 397160 }, { "epoch": 2.360860959038465, "grad_norm": 3.5248889923095703, "learning_rate": 6.341730103922358e-06, "loss": 0.1465, "step": 397170 }, { "epoch": 2.3609204011151332, "grad_norm": 3.784278392791748, "learning_rate": 6.341530220913398e-06, "loss": 0.1346, "step": 397180 }, { "epoch": 2.3609798431918017, "grad_norm": 4.1628804206848145, "learning_rate": 6.341330335594165e-06, "loss": 0.137, "step": 397190 }, { "epoch": 2.36103928526847, "grad_norm": 5.212081432342529, "learning_rate": 6.341130447964999e-06, "loss": 0.1503, "step": 397200 }, { "epoch": 2.3610987273451385, "grad_norm": 4.344911575317383, "learning_rate": 6.3409305580262485e-06, "loss": 0.1345, "step": 397210 }, { "epoch": 2.361158169421807, "grad_norm": 3.832402229309082, "learning_rate": 6.340730665778253e-06, "loss": 0.1274, "step": 397220 }, { "epoch": 2.3612176114984753, "grad_norm": 5.491860389709473, "learning_rate": 6.3405307712213615e-06, "loss": 0.1279, "step": 397230 }, { "epoch": 2.3612770535751437, "grad_norm": 3.623084306716919, "learning_rate": 6.340330874355916e-06, "loss": 0.1521, "step": 397240 }, { "epoch": 2.361336495651812, "grad_norm": 3.5354652404785156, "learning_rate": 6.340130975182259e-06, "loss": 0.1502, "step": 397250 }, { "epoch": 2.3613959377284806, "grad_norm": 3.448554039001465, "learning_rate": 6.339931073700739e-06, "loss": 0.1364, "step": 397260 }, { "epoch": 2.361455379805149, "grad_norm": 3.303459405899048, "learning_rate": 6.339731169911697e-06, "loss": 0.1443, "step": 397270 }, { "epoch": 2.3615148218818174, "grad_norm": 4.279141426086426, "learning_rate": 6.339531263815477e-06, "loss": 0.1437, "step": 397280 }, { "epoch": 2.361574263958486, "grad_norm": 3.4728431701660156, "learning_rate": 6.339331355412426e-06, "loss": 0.1567, "step": 397290 }, { "epoch": 2.361633706035154, "grad_norm": 4.810950756072998, "learning_rate": 6.339131444702886e-06, "loss": 0.1541, "step": 397300 }, { "epoch": 2.3616931481118226, "grad_norm": 3.8232414722442627, "learning_rate": 6.3389315316872e-06, "loss": 0.1433, "step": 397310 }, { "epoch": 2.361752590188491, "grad_norm": 3.38978910446167, "learning_rate": 6.338731616365716e-06, "loss": 0.1356, "step": 397320 }, { "epoch": 2.361812032265159, "grad_norm": 3.284132719039917, "learning_rate": 6.338531698738777e-06, "loss": 0.1438, "step": 397330 }, { "epoch": 2.3618714743418274, "grad_norm": 4.061516761779785, "learning_rate": 6.338331778806726e-06, "loss": 0.146, "step": 397340 }, { "epoch": 2.361930916418496, "grad_norm": 3.8352808952331543, "learning_rate": 6.3381318565699065e-06, "loss": 0.1344, "step": 397350 }, { "epoch": 2.3619903584951643, "grad_norm": 4.948703289031982, "learning_rate": 6.337931932028666e-06, "loss": 0.1515, "step": 397360 }, { "epoch": 2.3620498005718327, "grad_norm": 3.9513425827026367, "learning_rate": 6.3377320051833465e-06, "loss": 0.1478, "step": 397370 }, { "epoch": 2.362109242648501, "grad_norm": 4.119618892669678, "learning_rate": 6.337532076034293e-06, "loss": 0.1472, "step": 397380 }, { "epoch": 2.3621686847251695, "grad_norm": 3.5488483905792236, "learning_rate": 6.337332144581851e-06, "loss": 0.144, "step": 397390 }, { "epoch": 2.362228126801838, "grad_norm": 4.696423530578613, "learning_rate": 6.337132210826362e-06, "loss": 0.1416, "step": 397400 }, { "epoch": 2.3622875688785063, "grad_norm": 4.263408184051514, "learning_rate": 6.33693227476817e-06, "loss": 0.1317, "step": 397410 }, { "epoch": 2.3623470109551747, "grad_norm": 4.50189733505249, "learning_rate": 6.336732336407624e-06, "loss": 0.1326, "step": 397420 }, { "epoch": 2.362406453031843, "grad_norm": 5.279146671295166, "learning_rate": 6.336532395745064e-06, "loss": 0.139, "step": 397430 }, { "epoch": 2.3624658951085116, "grad_norm": 3.4335999488830566, "learning_rate": 6.336332452780837e-06, "loss": 0.1473, "step": 397440 }, { "epoch": 2.36252533718518, "grad_norm": 3.9620556831359863, "learning_rate": 6.3361325075152845e-06, "loss": 0.1283, "step": 397450 }, { "epoch": 2.3625847792618484, "grad_norm": 5.550011157989502, "learning_rate": 6.335932559948755e-06, "loss": 0.1804, "step": 397460 }, { "epoch": 2.362644221338517, "grad_norm": 4.3550286293029785, "learning_rate": 6.335732610081588e-06, "loss": 0.1626, "step": 397470 }, { "epoch": 2.3627036634151852, "grad_norm": 5.480172634124756, "learning_rate": 6.33553265791413e-06, "loss": 0.1486, "step": 397480 }, { "epoch": 2.3627631054918536, "grad_norm": 3.956240653991699, "learning_rate": 6.335332703446726e-06, "loss": 0.1297, "step": 397490 }, { "epoch": 2.3628225475685216, "grad_norm": 4.324453830718994, "learning_rate": 6.33513274667972e-06, "loss": 0.1343, "step": 397500 }, { "epoch": 2.3628819896451905, "grad_norm": 4.090891361236572, "learning_rate": 6.334932787613455e-06, "loss": 0.1384, "step": 397510 }, { "epoch": 2.3629414317218584, "grad_norm": 3.8643386363983154, "learning_rate": 6.334732826248278e-06, "loss": 0.1402, "step": 397520 }, { "epoch": 2.363000873798527, "grad_norm": 6.164905548095703, "learning_rate": 6.334532862584531e-06, "loss": 0.153, "step": 397530 }, { "epoch": 2.3630603158751953, "grad_norm": 5.672802925109863, "learning_rate": 6.334332896622557e-06, "loss": 0.1536, "step": 397540 }, { "epoch": 2.3631197579518637, "grad_norm": 4.306292533874512, "learning_rate": 6.334132928362706e-06, "loss": 0.1406, "step": 397550 }, { "epoch": 2.363179200028532, "grad_norm": 3.888629674911499, "learning_rate": 6.333932957805318e-06, "loss": 0.1389, "step": 397560 }, { "epoch": 2.3632386421052005, "grad_norm": 4.033185958862305, "learning_rate": 6.333732984950738e-06, "loss": 0.1214, "step": 397570 }, { "epoch": 2.363298084181869, "grad_norm": 3.666064739227295, "learning_rate": 6.3335330097993105e-06, "loss": 0.1512, "step": 397580 }, { "epoch": 2.3633575262585373, "grad_norm": 4.797407627105713, "learning_rate": 6.333333032351381e-06, "loss": 0.1559, "step": 397590 }, { "epoch": 2.3634169683352058, "grad_norm": 3.942701578140259, "learning_rate": 6.333133052607291e-06, "loss": 0.1288, "step": 397600 }, { "epoch": 2.363476410411874, "grad_norm": 3.8605329990386963, "learning_rate": 6.332933070567388e-06, "loss": 0.1582, "step": 397610 }, { "epoch": 2.3635358524885426, "grad_norm": 5.201144218444824, "learning_rate": 6.332733086232015e-06, "loss": 0.1412, "step": 397620 }, { "epoch": 2.363595294565211, "grad_norm": 4.392254829406738, "learning_rate": 6.332533099601517e-06, "loss": 0.1602, "step": 397630 }, { "epoch": 2.3636547366418794, "grad_norm": 5.949929237365723, "learning_rate": 6.332333110676237e-06, "loss": 0.1535, "step": 397640 }, { "epoch": 2.363714178718548, "grad_norm": 4.8296098709106445, "learning_rate": 6.332133119456521e-06, "loss": 0.1288, "step": 397650 }, { "epoch": 2.3637736207952162, "grad_norm": 4.010084629058838, "learning_rate": 6.331933125942713e-06, "loss": 0.1475, "step": 397660 }, { "epoch": 2.3638330628718847, "grad_norm": 5.140151500701904, "learning_rate": 6.331733130135157e-06, "loss": 0.1483, "step": 397670 }, { "epoch": 2.363892504948553, "grad_norm": 3.884348154067993, "learning_rate": 6.331533132034199e-06, "loss": 0.1434, "step": 397680 }, { "epoch": 2.363951947025221, "grad_norm": 4.465817451477051, "learning_rate": 6.331333131640181e-06, "loss": 0.1391, "step": 397690 }, { "epoch": 2.36401138910189, "grad_norm": 5.077752590179443, "learning_rate": 6.3311331289534475e-06, "loss": 0.1524, "step": 397700 }, { "epoch": 2.364070831178558, "grad_norm": 3.358163356781006, "learning_rate": 6.330933123974345e-06, "loss": 0.1515, "step": 397710 }, { "epoch": 2.3641302732552263, "grad_norm": 4.493321895599365, "learning_rate": 6.330733116703217e-06, "loss": 0.1467, "step": 397720 }, { "epoch": 2.3641897153318947, "grad_norm": 3.9975545406341553, "learning_rate": 6.330533107140407e-06, "loss": 0.1445, "step": 397730 }, { "epoch": 2.364249157408563, "grad_norm": 5.058176517486572, "learning_rate": 6.330333095286262e-06, "loss": 0.1363, "step": 397740 }, { "epoch": 2.3643085994852315, "grad_norm": 3.8450188636779785, "learning_rate": 6.330133081141122e-06, "loss": 0.1601, "step": 397750 }, { "epoch": 2.3643680415619, "grad_norm": 5.687831878662109, "learning_rate": 6.329933064705336e-06, "loss": 0.1572, "step": 397760 }, { "epoch": 2.3644274836385684, "grad_norm": 4.841399669647217, "learning_rate": 6.329733045979245e-06, "loss": 0.1236, "step": 397770 }, { "epoch": 2.3644869257152368, "grad_norm": 4.008138179779053, "learning_rate": 6.329533024963197e-06, "loss": 0.1407, "step": 397780 }, { "epoch": 2.364546367791905, "grad_norm": 3.937298536300659, "learning_rate": 6.329333001657534e-06, "loss": 0.1408, "step": 397790 }, { "epoch": 2.3646058098685736, "grad_norm": 5.773434638977051, "learning_rate": 6.329132976062599e-06, "loss": 0.1505, "step": 397800 }, { "epoch": 2.364665251945242, "grad_norm": 3.39037823677063, "learning_rate": 6.328932948178741e-06, "loss": 0.1216, "step": 397810 }, { "epoch": 2.3647246940219104, "grad_norm": 4.1732096672058105, "learning_rate": 6.328732918006301e-06, "loss": 0.1479, "step": 397820 }, { "epoch": 2.364784136098579, "grad_norm": 5.174187660217285, "learning_rate": 6.328532885545624e-06, "loss": 0.1353, "step": 397830 }, { "epoch": 2.3648435781752473, "grad_norm": 3.7330377101898193, "learning_rate": 6.328332850797057e-06, "loss": 0.1497, "step": 397840 }, { "epoch": 2.3649030202519157, "grad_norm": 3.2151846885681152, "learning_rate": 6.32813281376094e-06, "loss": 0.1319, "step": 397850 }, { "epoch": 2.364962462328584, "grad_norm": 4.966341018676758, "learning_rate": 6.327932774437619e-06, "loss": 0.157, "step": 397860 }, { "epoch": 2.3650219044052525, "grad_norm": 3.487419843673706, "learning_rate": 6.32773273282744e-06, "loss": 0.1409, "step": 397870 }, { "epoch": 2.3650813464819205, "grad_norm": 4.5130743980407715, "learning_rate": 6.3275326889307486e-06, "loss": 0.125, "step": 397880 }, { "epoch": 2.365140788558589, "grad_norm": 3.8836829662323, "learning_rate": 6.327332642747887e-06, "loss": 0.1435, "step": 397890 }, { "epoch": 2.3652002306352573, "grad_norm": 4.118895530700684, "learning_rate": 6.327132594279198e-06, "loss": 0.1518, "step": 397900 }, { "epoch": 2.3652596727119257, "grad_norm": 5.252467155456543, "learning_rate": 6.32693254352503e-06, "loss": 0.1411, "step": 397910 }, { "epoch": 2.365319114788594, "grad_norm": 3.6853246688842773, "learning_rate": 6.326732490485727e-06, "loss": 0.163, "step": 397920 }, { "epoch": 2.3653785568652625, "grad_norm": 2.449340581893921, "learning_rate": 6.3265324351616295e-06, "loss": 0.1463, "step": 397930 }, { "epoch": 2.365437998941931, "grad_norm": 5.070024013519287, "learning_rate": 6.326332377553087e-06, "loss": 0.1306, "step": 397940 }, { "epoch": 2.3654974410185994, "grad_norm": 5.1255927085876465, "learning_rate": 6.326132317660443e-06, "loss": 0.1389, "step": 397950 }, { "epoch": 2.365556883095268, "grad_norm": 3.9470293521881104, "learning_rate": 6.3259322554840375e-06, "loss": 0.1441, "step": 397960 }, { "epoch": 2.365616325171936, "grad_norm": 5.195026874542236, "learning_rate": 6.32573219102422e-06, "loss": 0.1415, "step": 397970 }, { "epoch": 2.3656757672486046, "grad_norm": 3.8979835510253906, "learning_rate": 6.325532124281334e-06, "loss": 0.1237, "step": 397980 }, { "epoch": 2.365735209325273, "grad_norm": 5.580390930175781, "learning_rate": 6.325332055255724e-06, "loss": 0.1727, "step": 397990 }, { "epoch": 2.3657946514019415, "grad_norm": 3.846406936645508, "learning_rate": 6.325131983947732e-06, "loss": 0.1472, "step": 398000 }, { "epoch": 2.36585409347861, "grad_norm": 3.111116409301758, "learning_rate": 6.3249319103577055e-06, "loss": 0.1433, "step": 398010 }, { "epoch": 2.3659135355552783, "grad_norm": 5.172179222106934, "learning_rate": 6.32473183448599e-06, "loss": 0.1721, "step": 398020 }, { "epoch": 2.3659729776319467, "grad_norm": 4.092661380767822, "learning_rate": 6.324531756332925e-06, "loss": 0.1455, "step": 398030 }, { "epoch": 2.366032419708615, "grad_norm": 4.487878799438477, "learning_rate": 6.324331675898862e-06, "loss": 0.1472, "step": 398040 }, { "epoch": 2.3660918617852835, "grad_norm": 3.975795030593872, "learning_rate": 6.32413159318414e-06, "loss": 0.1458, "step": 398050 }, { "epoch": 2.366151303861952, "grad_norm": 3.904968738555908, "learning_rate": 6.3239315081891036e-06, "loss": 0.1541, "step": 398060 }, { "epoch": 2.36621074593862, "grad_norm": 3.7587456703186035, "learning_rate": 6.323731420914102e-06, "loss": 0.1343, "step": 398070 }, { "epoch": 2.3662701880152883, "grad_norm": 3.907409906387329, "learning_rate": 6.323531331359475e-06, "loss": 0.1473, "step": 398080 }, { "epoch": 2.3663296300919567, "grad_norm": 4.308542728424072, "learning_rate": 6.32333123952557e-06, "loss": 0.1387, "step": 398090 }, { "epoch": 2.366389072168625, "grad_norm": 5.155649185180664, "learning_rate": 6.32313114541273e-06, "loss": 0.136, "step": 398100 }, { "epoch": 2.3664485142452936, "grad_norm": 4.811793804168701, "learning_rate": 6.3229310490213015e-06, "loss": 0.1429, "step": 398110 }, { "epoch": 2.366507956321962, "grad_norm": 3.8057117462158203, "learning_rate": 6.322730950351627e-06, "loss": 0.1402, "step": 398120 }, { "epoch": 2.3665673983986304, "grad_norm": 4.5620269775390625, "learning_rate": 6.322530849404051e-06, "loss": 0.146, "step": 398130 }, { "epoch": 2.366626840475299, "grad_norm": 4.106130599975586, "learning_rate": 6.322330746178922e-06, "loss": 0.128, "step": 398140 }, { "epoch": 2.3666862825519672, "grad_norm": 4.818984508514404, "learning_rate": 6.3221306406765805e-06, "loss": 0.15, "step": 398150 }, { "epoch": 2.3667457246286356, "grad_norm": 4.134039878845215, "learning_rate": 6.321930532897371e-06, "loss": 0.1461, "step": 398160 }, { "epoch": 2.366805166705304, "grad_norm": 4.123600006103516, "learning_rate": 6.321730422841641e-06, "loss": 0.137, "step": 398170 }, { "epoch": 2.3668646087819725, "grad_norm": 5.7772321701049805, "learning_rate": 6.321530310509732e-06, "loss": 0.1662, "step": 398180 }, { "epoch": 2.366924050858641, "grad_norm": 3.7574820518493652, "learning_rate": 6.3213301959019904e-06, "loss": 0.1526, "step": 398190 }, { "epoch": 2.3669834929353093, "grad_norm": 6.149202346801758, "learning_rate": 6.32113007901876e-06, "loss": 0.1476, "step": 398200 }, { "epoch": 2.3670429350119777, "grad_norm": 4.026061058044434, "learning_rate": 6.320929959860388e-06, "loss": 0.1345, "step": 398210 }, { "epoch": 2.367102377088646, "grad_norm": 4.3412065505981445, "learning_rate": 6.320729838427215e-06, "loss": 0.1631, "step": 398220 }, { "epoch": 2.3671618191653145, "grad_norm": 4.417976379394531, "learning_rate": 6.32052971471959e-06, "loss": 0.1458, "step": 398230 }, { "epoch": 2.3672212612419825, "grad_norm": 2.946871757507324, "learning_rate": 6.320329588737853e-06, "loss": 0.1554, "step": 398240 }, { "epoch": 2.3672807033186514, "grad_norm": 4.429662704467773, "learning_rate": 6.320129460482352e-06, "loss": 0.1435, "step": 398250 }, { "epoch": 2.3673401453953193, "grad_norm": 3.6851189136505127, "learning_rate": 6.319929329953431e-06, "loss": 0.1635, "step": 398260 }, { "epoch": 2.3673995874719878, "grad_norm": 5.201138496398926, "learning_rate": 6.319729197151433e-06, "loss": 0.1587, "step": 398270 }, { "epoch": 2.367459029548656, "grad_norm": 4.150579452514648, "learning_rate": 6.319529062076704e-06, "loss": 0.1614, "step": 398280 }, { "epoch": 2.3675184716253246, "grad_norm": 3.5840554237365723, "learning_rate": 6.319328924729589e-06, "loss": 0.1599, "step": 398290 }, { "epoch": 2.367577913701993, "grad_norm": 4.927996635437012, "learning_rate": 6.319128785110431e-06, "loss": 0.1516, "step": 398300 }, { "epoch": 2.3676373557786614, "grad_norm": 4.585511684417725, "learning_rate": 6.318928643219578e-06, "loss": 0.1303, "step": 398310 }, { "epoch": 2.36769679785533, "grad_norm": 4.595261096954346, "learning_rate": 6.318728499057371e-06, "loss": 0.1426, "step": 398320 }, { "epoch": 2.3677562399319982, "grad_norm": 4.209654331207275, "learning_rate": 6.318528352624157e-06, "loss": 0.1572, "step": 398330 }, { "epoch": 2.3678156820086667, "grad_norm": 3.1708528995513916, "learning_rate": 6.31832820392028e-06, "loss": 0.1332, "step": 398340 }, { "epoch": 2.367875124085335, "grad_norm": 4.37683629989624, "learning_rate": 6.3181280529460835e-06, "loss": 0.14, "step": 398350 }, { "epoch": 2.3679345661620035, "grad_norm": 3.8534834384918213, "learning_rate": 6.317927899701913e-06, "loss": 0.1444, "step": 398360 }, { "epoch": 2.367994008238672, "grad_norm": 4.052528381347656, "learning_rate": 6.3177277441881145e-06, "loss": 0.1519, "step": 398370 }, { "epoch": 2.3680534503153403, "grad_norm": 3.1339569091796875, "learning_rate": 6.317527586405031e-06, "loss": 0.1397, "step": 398380 }, { "epoch": 2.3681128923920087, "grad_norm": 5.482481479644775, "learning_rate": 6.317327426353008e-06, "loss": 0.1605, "step": 398390 }, { "epoch": 2.368172334468677, "grad_norm": 4.570099353790283, "learning_rate": 6.31712726403239e-06, "loss": 0.1539, "step": 398400 }, { "epoch": 2.3682317765453456, "grad_norm": 5.448577880859375, "learning_rate": 6.3169270994435215e-06, "loss": 0.1459, "step": 398410 }, { "epoch": 2.368291218622014, "grad_norm": 5.40376615524292, "learning_rate": 6.316726932586746e-06, "loss": 0.1569, "step": 398420 }, { "epoch": 2.368350660698682, "grad_norm": 3.6318047046661377, "learning_rate": 6.3165267634624124e-06, "loss": 0.1481, "step": 398430 }, { "epoch": 2.368410102775351, "grad_norm": 4.025605201721191, "learning_rate": 6.316326592070862e-06, "loss": 0.1455, "step": 398440 }, { "epoch": 2.3684695448520188, "grad_norm": 4.368056774139404, "learning_rate": 6.3161264184124384e-06, "loss": 0.1478, "step": 398450 }, { "epoch": 2.368528986928687, "grad_norm": 4.4455413818359375, "learning_rate": 6.31592624248749e-06, "loss": 0.1531, "step": 398460 }, { "epoch": 2.3685884290053556, "grad_norm": 5.139340877532959, "learning_rate": 6.315726064296359e-06, "loss": 0.167, "step": 398470 }, { "epoch": 2.368647871082024, "grad_norm": 3.3521742820739746, "learning_rate": 6.315525883839389e-06, "loss": 0.1357, "step": 398480 }, { "epoch": 2.3687073131586924, "grad_norm": 4.36658239364624, "learning_rate": 6.315325701116929e-06, "loss": 0.1244, "step": 398490 }, { "epoch": 2.368766755235361, "grad_norm": 3.691136598587036, "learning_rate": 6.315125516129321e-06, "loss": 0.1241, "step": 398500 }, { "epoch": 2.3688261973120293, "grad_norm": 3.757213592529297, "learning_rate": 6.3149253288769085e-06, "loss": 0.1495, "step": 398510 }, { "epoch": 2.3688856393886977, "grad_norm": 5.0481343269348145, "learning_rate": 6.314725139360037e-06, "loss": 0.1555, "step": 398520 }, { "epoch": 2.368945081465366, "grad_norm": 5.0310282707214355, "learning_rate": 6.314524947579054e-06, "loss": 0.1417, "step": 398530 }, { "epoch": 2.3690045235420345, "grad_norm": 3.6513803005218506, "learning_rate": 6.314324753534302e-06, "loss": 0.1318, "step": 398540 }, { "epoch": 2.369063965618703, "grad_norm": 6.149823188781738, "learning_rate": 6.314124557226124e-06, "loss": 0.1554, "step": 398550 }, { "epoch": 2.3691234076953713, "grad_norm": 5.707034587860107, "learning_rate": 6.313924358654869e-06, "loss": 0.1637, "step": 398560 }, { "epoch": 2.3691828497720397, "grad_norm": 3.0699002742767334, "learning_rate": 6.31372415782088e-06, "loss": 0.1341, "step": 398570 }, { "epoch": 2.369242291848708, "grad_norm": 3.8052871227264404, "learning_rate": 6.313523954724499e-06, "loss": 0.1592, "step": 398580 }, { "epoch": 2.3693017339253766, "grad_norm": 3.341667652130127, "learning_rate": 6.313323749366074e-06, "loss": 0.1301, "step": 398590 }, { "epoch": 2.369361176002045, "grad_norm": 4.4333271980285645, "learning_rate": 6.313123541745949e-06, "loss": 0.134, "step": 398600 }, { "epoch": 2.3694206180787134, "grad_norm": 4.1064558029174805, "learning_rate": 6.312923331864467e-06, "loss": 0.1479, "step": 398610 }, { "epoch": 2.3694800601553814, "grad_norm": 3.977630138397217, "learning_rate": 6.312723119721976e-06, "loss": 0.149, "step": 398620 }, { "epoch": 2.36953950223205, "grad_norm": 4.201000690460205, "learning_rate": 6.312522905318819e-06, "loss": 0.1513, "step": 398630 }, { "epoch": 2.369598944308718, "grad_norm": 5.094062805175781, "learning_rate": 6.312322688655342e-06, "loss": 0.1521, "step": 398640 }, { "epoch": 2.3696583863853866, "grad_norm": 3.8918838500976562, "learning_rate": 6.312122469731885e-06, "loss": 0.1437, "step": 398650 }, { "epoch": 2.369717828462055, "grad_norm": 5.03503942489624, "learning_rate": 6.311922248548799e-06, "loss": 0.1587, "step": 398660 }, { "epoch": 2.3697772705387234, "grad_norm": 4.388096809387207, "learning_rate": 6.311722025106428e-06, "loss": 0.1443, "step": 398670 }, { "epoch": 2.369836712615392, "grad_norm": 4.822251796722412, "learning_rate": 6.311521799405113e-06, "loss": 0.1497, "step": 398680 }, { "epoch": 2.3698961546920603, "grad_norm": 3.1948742866516113, "learning_rate": 6.311321571445202e-06, "loss": 0.1387, "step": 398690 }, { "epoch": 2.3699555967687287, "grad_norm": 4.974228858947754, "learning_rate": 6.311121341227038e-06, "loss": 0.1584, "step": 398700 }, { "epoch": 2.370015038845397, "grad_norm": 4.38235330581665, "learning_rate": 6.310921108750966e-06, "loss": 0.1531, "step": 398710 }, { "epoch": 2.3700744809220655, "grad_norm": 4.148723125457764, "learning_rate": 6.310720874017333e-06, "loss": 0.1501, "step": 398720 }, { "epoch": 2.370133922998734, "grad_norm": 5.020260334014893, "learning_rate": 6.310520637026483e-06, "loss": 0.1372, "step": 398730 }, { "epoch": 2.3701933650754023, "grad_norm": 5.175848484039307, "learning_rate": 6.310320397778755e-06, "loss": 0.1419, "step": 398740 }, { "epoch": 2.3702528071520708, "grad_norm": 4.714311122894287, "learning_rate": 6.310120156274504e-06, "loss": 0.1649, "step": 398750 }, { "epoch": 2.370312249228739, "grad_norm": 4.839421272277832, "learning_rate": 6.309919912514068e-06, "loss": 0.1497, "step": 398760 }, { "epoch": 2.3703716913054076, "grad_norm": 4.278447151184082, "learning_rate": 6.309719666497795e-06, "loss": 0.1463, "step": 398770 }, { "epoch": 2.370431133382076, "grad_norm": 5.685857772827148, "learning_rate": 6.309519418226027e-06, "loss": 0.1232, "step": 398780 }, { "epoch": 2.3704905754587444, "grad_norm": 6.719025611877441, "learning_rate": 6.309319167699111e-06, "loss": 0.1315, "step": 398790 }, { "epoch": 2.370550017535413, "grad_norm": 6.968725204467773, "learning_rate": 6.309118914917392e-06, "loss": 0.1587, "step": 398800 }, { "epoch": 2.370609459612081, "grad_norm": 4.56879186630249, "learning_rate": 6.3089186598812115e-06, "loss": 0.1379, "step": 398810 }, { "epoch": 2.370668901688749, "grad_norm": 6.605345249176025, "learning_rate": 6.308718402590919e-06, "loss": 0.1606, "step": 398820 }, { "epoch": 2.3707283437654176, "grad_norm": 5.92034387588501, "learning_rate": 6.308518143046857e-06, "loss": 0.1637, "step": 398830 }, { "epoch": 2.370787785842086, "grad_norm": 3.71897029876709, "learning_rate": 6.308317881249369e-06, "loss": 0.1445, "step": 398840 }, { "epoch": 2.3708472279187545, "grad_norm": 3.7341058254241943, "learning_rate": 6.308117617198803e-06, "loss": 0.1415, "step": 398850 }, { "epoch": 2.370906669995423, "grad_norm": 4.414074420928955, "learning_rate": 6.3079173508955025e-06, "loss": 0.1442, "step": 398860 }, { "epoch": 2.3709661120720913, "grad_norm": 5.021564483642578, "learning_rate": 6.307717082339811e-06, "loss": 0.1519, "step": 398870 }, { "epoch": 2.3710255541487597, "grad_norm": 5.2226762771606445, "learning_rate": 6.307516811532076e-06, "loss": 0.1272, "step": 398880 }, { "epoch": 2.371084996225428, "grad_norm": 3.264788866043091, "learning_rate": 6.307316538472641e-06, "loss": 0.156, "step": 398890 }, { "epoch": 2.3711444383020965, "grad_norm": 4.680814743041992, "learning_rate": 6.30711626316185e-06, "loss": 0.1311, "step": 398900 }, { "epoch": 2.371203880378765, "grad_norm": 3.847262144088745, "learning_rate": 6.3069159856000496e-06, "loss": 0.1458, "step": 398910 }, { "epoch": 2.3712633224554334, "grad_norm": 4.491810321807861, "learning_rate": 6.306715705787584e-06, "loss": 0.1437, "step": 398920 }, { "epoch": 2.371322764532102, "grad_norm": 3.798910617828369, "learning_rate": 6.306515423724797e-06, "loss": 0.1397, "step": 398930 }, { "epoch": 2.37138220660877, "grad_norm": 4.587767124176025, "learning_rate": 6.306315139412036e-06, "loss": 0.1458, "step": 398940 }, { "epoch": 2.3714416486854386, "grad_norm": 3.4228460788726807, "learning_rate": 6.306114852849644e-06, "loss": 0.134, "step": 398950 }, { "epoch": 2.371501090762107, "grad_norm": 5.139676094055176, "learning_rate": 6.305914564037965e-06, "loss": 0.1509, "step": 398960 }, { "epoch": 2.3715605328387754, "grad_norm": 3.389315128326416, "learning_rate": 6.305714272977346e-06, "loss": 0.1394, "step": 398970 }, { "epoch": 2.3716199749154434, "grad_norm": 3.8128204345703125, "learning_rate": 6.305513979668132e-06, "loss": 0.1415, "step": 398980 }, { "epoch": 2.3716794169921123, "grad_norm": 4.257200717926025, "learning_rate": 6.305313684110668e-06, "loss": 0.1262, "step": 398990 }, { "epoch": 2.3717388590687802, "grad_norm": 3.3672935962677, "learning_rate": 6.305113386305296e-06, "loss": 0.1235, "step": 399000 }, { "epoch": 2.3717983011454487, "grad_norm": 4.678786277770996, "learning_rate": 6.304913086252365e-06, "loss": 0.1177, "step": 399010 }, { "epoch": 2.371857743222117, "grad_norm": 4.162293434143066, "learning_rate": 6.304712783952216e-06, "loss": 0.153, "step": 399020 }, { "epoch": 2.3719171852987855, "grad_norm": 3.8066322803497314, "learning_rate": 6.304512479405196e-06, "loss": 0.1395, "step": 399030 }, { "epoch": 2.371976627375454, "grad_norm": 4.042250156402588, "learning_rate": 6.3043121726116514e-06, "loss": 0.1466, "step": 399040 }, { "epoch": 2.3720360694521223, "grad_norm": 5.5280656814575195, "learning_rate": 6.304111863571926e-06, "loss": 0.1615, "step": 399050 }, { "epoch": 2.3720955115287907, "grad_norm": 5.625289440155029, "learning_rate": 6.303911552286362e-06, "loss": 0.1558, "step": 399060 }, { "epoch": 2.372154953605459, "grad_norm": 3.5750553607940674, "learning_rate": 6.303711238755307e-06, "loss": 0.1432, "step": 399070 }, { "epoch": 2.3722143956821276, "grad_norm": 3.869068145751953, "learning_rate": 6.303510922979107e-06, "loss": 0.1394, "step": 399080 }, { "epoch": 2.372273837758796, "grad_norm": 3.2751832008361816, "learning_rate": 6.303310604958106e-06, "loss": 0.1429, "step": 399090 }, { "epoch": 2.3723332798354644, "grad_norm": 5.8718953132629395, "learning_rate": 6.303110284692647e-06, "loss": 0.1454, "step": 399100 }, { "epoch": 2.372392721912133, "grad_norm": 3.6583688259124756, "learning_rate": 6.302909962183078e-06, "loss": 0.146, "step": 399110 }, { "epoch": 2.372452163988801, "grad_norm": 4.0598931312561035, "learning_rate": 6.302709637429742e-06, "loss": 0.134, "step": 399120 }, { "epoch": 2.3725116060654696, "grad_norm": 4.866657733917236, "learning_rate": 6.302509310432985e-06, "loss": 0.1369, "step": 399130 }, { "epoch": 2.372571048142138, "grad_norm": 2.9799463748931885, "learning_rate": 6.3023089811931515e-06, "loss": 0.1441, "step": 399140 }, { "epoch": 2.3726304902188065, "grad_norm": 3.0435945987701416, "learning_rate": 6.302108649710587e-06, "loss": 0.1544, "step": 399150 }, { "epoch": 2.372689932295475, "grad_norm": 3.4281272888183594, "learning_rate": 6.301908315985634e-06, "loss": 0.1474, "step": 399160 }, { "epoch": 2.372749374372143, "grad_norm": 4.997128009796143, "learning_rate": 6.3017079800186405e-06, "loss": 0.1465, "step": 399170 }, { "epoch": 2.3728088164488117, "grad_norm": 3.4486372470855713, "learning_rate": 6.301507641809952e-06, "loss": 0.1308, "step": 399180 }, { "epoch": 2.3728682585254797, "grad_norm": 4.285867691040039, "learning_rate": 6.3013073013599105e-06, "loss": 0.1386, "step": 399190 }, { "epoch": 2.372927700602148, "grad_norm": 4.381394386291504, "learning_rate": 6.301106958668862e-06, "loss": 0.1393, "step": 399200 }, { "epoch": 2.3729871426788165, "grad_norm": 4.400673866271973, "learning_rate": 6.300906613737154e-06, "loss": 0.133, "step": 399210 }, { "epoch": 2.373046584755485, "grad_norm": 3.9006755352020264, "learning_rate": 6.300706266565129e-06, "loss": 0.144, "step": 399220 }, { "epoch": 2.3731060268321533, "grad_norm": 3.785742998123169, "learning_rate": 6.300505917153131e-06, "loss": 0.1321, "step": 399230 }, { "epoch": 2.3731654689088217, "grad_norm": 4.780702114105225, "learning_rate": 6.300305565501509e-06, "loss": 0.1348, "step": 399240 }, { "epoch": 2.37322491098549, "grad_norm": 4.420130729675293, "learning_rate": 6.300105211610605e-06, "loss": 0.1522, "step": 399250 }, { "epoch": 2.3732843530621586, "grad_norm": 3.7038424015045166, "learning_rate": 6.299904855480763e-06, "loss": 0.1363, "step": 399260 }, { "epoch": 2.373343795138827, "grad_norm": 5.636240482330322, "learning_rate": 6.299704497112332e-06, "loss": 0.1318, "step": 399270 }, { "epoch": 2.3734032372154954, "grad_norm": 5.458102226257324, "learning_rate": 6.299504136505654e-06, "loss": 0.1448, "step": 399280 }, { "epoch": 2.373462679292164, "grad_norm": 4.310647010803223, "learning_rate": 6.299303773661074e-06, "loss": 0.1391, "step": 399290 }, { "epoch": 2.3735221213688322, "grad_norm": 4.530151844024658, "learning_rate": 6.299103408578939e-06, "loss": 0.1619, "step": 399300 }, { "epoch": 2.3735815634455006, "grad_norm": 4.372069835662842, "learning_rate": 6.298903041259592e-06, "loss": 0.1311, "step": 399310 }, { "epoch": 2.373641005522169, "grad_norm": 5.616372585296631, "learning_rate": 6.298702671703379e-06, "loss": 0.1433, "step": 399320 }, { "epoch": 2.3737004475988375, "grad_norm": 3.521918773651123, "learning_rate": 6.298502299910645e-06, "loss": 0.129, "step": 399330 }, { "epoch": 2.373759889675506, "grad_norm": 3.909095287322998, "learning_rate": 6.2983019258817355e-06, "loss": 0.1519, "step": 399340 }, { "epoch": 2.3738193317521743, "grad_norm": 4.320423603057861, "learning_rate": 6.298101549616996e-06, "loss": 0.1335, "step": 399350 }, { "epoch": 2.3738787738288423, "grad_norm": 3.0171546936035156, "learning_rate": 6.297901171116769e-06, "loss": 0.1516, "step": 399360 }, { "epoch": 2.3739382159055107, "grad_norm": 3.7367000579833984, "learning_rate": 6.297700790381403e-06, "loss": 0.1347, "step": 399370 }, { "epoch": 2.373997657982179, "grad_norm": 6.615054130554199, "learning_rate": 6.297500407411241e-06, "loss": 0.1612, "step": 399380 }, { "epoch": 2.3740571000588475, "grad_norm": 4.1983466148376465, "learning_rate": 6.297300022206628e-06, "loss": 0.1309, "step": 399390 }, { "epoch": 2.374116542135516, "grad_norm": 4.835452079772949, "learning_rate": 6.2970996347679095e-06, "loss": 0.1377, "step": 399400 }, { "epoch": 2.3741759842121843, "grad_norm": 3.877577781677246, "learning_rate": 6.296899245095431e-06, "loss": 0.1465, "step": 399410 }, { "epoch": 2.3742354262888528, "grad_norm": 3.2639143466949463, "learning_rate": 6.2966988531895365e-06, "loss": 0.1323, "step": 399420 }, { "epoch": 2.374294868365521, "grad_norm": 4.416038990020752, "learning_rate": 6.296498459050573e-06, "loss": 0.1426, "step": 399430 }, { "epoch": 2.3743543104421896, "grad_norm": 4.416753768920898, "learning_rate": 6.2962980626788835e-06, "loss": 0.1451, "step": 399440 }, { "epoch": 2.374413752518858, "grad_norm": 4.345726490020752, "learning_rate": 6.2960976640748165e-06, "loss": 0.1355, "step": 399450 }, { "epoch": 2.3744731945955264, "grad_norm": 4.140035629272461, "learning_rate": 6.295897263238712e-06, "loss": 0.1375, "step": 399460 }, { "epoch": 2.374532636672195, "grad_norm": 4.141488075256348, "learning_rate": 6.2956968601709175e-06, "loss": 0.1471, "step": 399470 }, { "epoch": 2.3745920787488632, "grad_norm": 3.832533121109009, "learning_rate": 6.29549645487178e-06, "loss": 0.1491, "step": 399480 }, { "epoch": 2.3746515208255317, "grad_norm": 4.072381973266602, "learning_rate": 6.2952960473416425e-06, "loss": 0.1325, "step": 399490 }, { "epoch": 2.3747109629022, "grad_norm": 4.285528659820557, "learning_rate": 6.2950956375808506e-06, "loss": 0.1275, "step": 399500 }, { "epoch": 2.3747704049788685, "grad_norm": 3.9895200729370117, "learning_rate": 6.294895225589749e-06, "loss": 0.1377, "step": 399510 }, { "epoch": 2.374829847055537, "grad_norm": 5.328281402587891, "learning_rate": 6.294694811368684e-06, "loss": 0.154, "step": 399520 }, { "epoch": 2.3748892891322053, "grad_norm": 4.287769794464111, "learning_rate": 6.294494394917999e-06, "loss": 0.1514, "step": 399530 }, { "epoch": 2.3749487312088737, "grad_norm": 3.7662978172302246, "learning_rate": 6.294293976238042e-06, "loss": 0.135, "step": 399540 }, { "epoch": 2.3750081732855417, "grad_norm": 3.9628021717071533, "learning_rate": 6.2940935553291545e-06, "loss": 0.134, "step": 399550 }, { "epoch": 2.37506761536221, "grad_norm": 4.038232803344727, "learning_rate": 6.2938931321916845e-06, "loss": 0.1385, "step": 399560 }, { "epoch": 2.3751270574388785, "grad_norm": 4.053262233734131, "learning_rate": 6.2936927068259765e-06, "loss": 0.1399, "step": 399570 }, { "epoch": 2.375186499515547, "grad_norm": 4.5769219398498535, "learning_rate": 6.293492279232374e-06, "loss": 0.1628, "step": 399580 }, { "epoch": 2.3752459415922154, "grad_norm": 4.537307262420654, "learning_rate": 6.293291849411225e-06, "loss": 0.1517, "step": 399590 }, { "epoch": 2.3753053836688838, "grad_norm": 6.0245208740234375, "learning_rate": 6.293091417362874e-06, "loss": 0.1366, "step": 399600 }, { "epoch": 2.375364825745552, "grad_norm": 4.328763961791992, "learning_rate": 6.2928909830876615e-06, "loss": 0.1577, "step": 399610 }, { "epoch": 2.3754242678222206, "grad_norm": 5.092044830322266, "learning_rate": 6.292690546585938e-06, "loss": 0.149, "step": 399620 }, { "epoch": 2.375483709898889, "grad_norm": 4.441192150115967, "learning_rate": 6.292490107858048e-06, "loss": 0.1538, "step": 399630 }, { "epoch": 2.3755431519755574, "grad_norm": 4.081381797790527, "learning_rate": 6.292289666904337e-06, "loss": 0.164, "step": 399640 }, { "epoch": 2.375602594052226, "grad_norm": 4.121767997741699, "learning_rate": 6.2920892237251464e-06, "loss": 0.1533, "step": 399650 }, { "epoch": 2.3756620361288943, "grad_norm": 3.478264808654785, "learning_rate": 6.291888778320825e-06, "loss": 0.1458, "step": 399660 }, { "epoch": 2.3757214782055627, "grad_norm": 4.630496978759766, "learning_rate": 6.2916883306917185e-06, "loss": 0.1414, "step": 399670 }, { "epoch": 2.375780920282231, "grad_norm": 4.407620906829834, "learning_rate": 6.291487880838169e-06, "loss": 0.1491, "step": 399680 }, { "epoch": 2.3758403623588995, "grad_norm": 4.785032272338867, "learning_rate": 6.291287428760523e-06, "loss": 0.1488, "step": 399690 }, { "epoch": 2.375899804435568, "grad_norm": 4.99966287612915, "learning_rate": 6.291086974459126e-06, "loss": 0.1468, "step": 399700 }, { "epoch": 2.3759592465122363, "grad_norm": 4.1705756187438965, "learning_rate": 6.290886517934323e-06, "loss": 0.1404, "step": 399710 }, { "epoch": 2.3760186885889043, "grad_norm": 3.858168601989746, "learning_rate": 6.290686059186462e-06, "loss": 0.1527, "step": 399720 }, { "epoch": 2.376078130665573, "grad_norm": 4.150322914123535, "learning_rate": 6.290485598215883e-06, "loss": 0.1295, "step": 399730 }, { "epoch": 2.376137572742241, "grad_norm": 3.932345151901245, "learning_rate": 6.290285135022934e-06, "loss": 0.1313, "step": 399740 }, { "epoch": 2.3761970148189095, "grad_norm": 4.395033359527588, "learning_rate": 6.29008466960796e-06, "loss": 0.133, "step": 399750 }, { "epoch": 2.376256456895578, "grad_norm": 4.907573223114014, "learning_rate": 6.289884201971308e-06, "loss": 0.1567, "step": 399760 }, { "epoch": 2.3763158989722464, "grad_norm": 4.105598449707031, "learning_rate": 6.289683732113319e-06, "loss": 0.1378, "step": 399770 }, { "epoch": 2.376375341048915, "grad_norm": 6.000143527984619, "learning_rate": 6.2894832600343425e-06, "loss": 0.1432, "step": 399780 }, { "epoch": 2.376434783125583, "grad_norm": 3.6359615325927734, "learning_rate": 6.289282785734721e-06, "loss": 0.1359, "step": 399790 }, { "epoch": 2.3764942252022516, "grad_norm": 4.266162395477295, "learning_rate": 6.289082309214802e-06, "loss": 0.1319, "step": 399800 }, { "epoch": 2.37655366727892, "grad_norm": 5.95850944519043, "learning_rate": 6.288881830474929e-06, "loss": 0.1493, "step": 399810 }, { "epoch": 2.3766131093555884, "grad_norm": 3.302435874938965, "learning_rate": 6.288681349515446e-06, "loss": 0.1435, "step": 399820 }, { "epoch": 2.376672551432257, "grad_norm": 4.568174839019775, "learning_rate": 6.288480866336702e-06, "loss": 0.1524, "step": 399830 }, { "epoch": 2.3767319935089253, "grad_norm": 4.96678352355957, "learning_rate": 6.28828038093904e-06, "loss": 0.147, "step": 399840 }, { "epoch": 2.3767914355855937, "grad_norm": 4.172039031982422, "learning_rate": 6.288079893322804e-06, "loss": 0.137, "step": 399850 }, { "epoch": 2.376850877662262, "grad_norm": 3.719724655151367, "learning_rate": 6.287879403488342e-06, "loss": 0.1282, "step": 399860 }, { "epoch": 2.3769103197389305, "grad_norm": 4.389630317687988, "learning_rate": 6.2876789114359986e-06, "loss": 0.1522, "step": 399870 }, { "epoch": 2.376969761815599, "grad_norm": 3.5329384803771973, "learning_rate": 6.287478417166116e-06, "loss": 0.1453, "step": 399880 }, { "epoch": 2.3770292038922674, "grad_norm": 3.482938289642334, "learning_rate": 6.287277920679045e-06, "loss": 0.1514, "step": 399890 }, { "epoch": 2.3770886459689358, "grad_norm": 3.1817033290863037, "learning_rate": 6.287077421975126e-06, "loss": 0.1513, "step": 399900 }, { "epoch": 2.3771480880456037, "grad_norm": 4.887779712677002, "learning_rate": 6.286876921054705e-06, "loss": 0.1402, "step": 399910 }, { "epoch": 2.3772075301222726, "grad_norm": 5.134922981262207, "learning_rate": 6.286676417918132e-06, "loss": 0.1475, "step": 399920 }, { "epoch": 2.3772669721989406, "grad_norm": 3.582158088684082, "learning_rate": 6.286475912565746e-06, "loss": 0.1349, "step": 399930 }, { "epoch": 2.377326414275609, "grad_norm": 3.985060930252075, "learning_rate": 6.286275404997895e-06, "loss": 0.1637, "step": 399940 }, { "epoch": 2.3773858563522774, "grad_norm": 4.195304870605469, "learning_rate": 6.286074895214924e-06, "loss": 0.1586, "step": 399950 }, { "epoch": 2.377445298428946, "grad_norm": 5.397944450378418, "learning_rate": 6.285874383217179e-06, "loss": 0.1369, "step": 399960 }, { "epoch": 2.3775047405056142, "grad_norm": 3.144958972930908, "learning_rate": 6.285673869005007e-06, "loss": 0.1386, "step": 399970 }, { "epoch": 2.3775641825822826, "grad_norm": 4.242281436920166, "learning_rate": 6.285473352578748e-06, "loss": 0.1412, "step": 399980 }, { "epoch": 2.377623624658951, "grad_norm": 4.576737880706787, "learning_rate": 6.285272833938753e-06, "loss": 0.1441, "step": 399990 }, { "epoch": 2.3776830667356195, "grad_norm": 3.798428773880005, "learning_rate": 6.285072313085364e-06, "loss": 0.1597, "step": 400000 }, { "epoch": 2.377742508812288, "grad_norm": 4.672146320343018, "learning_rate": 6.284871790018926e-06, "loss": 0.1193, "step": 400010 }, { "epoch": 2.3778019508889563, "grad_norm": 5.048120498657227, "learning_rate": 6.284671264739787e-06, "loss": 0.1238, "step": 400020 }, { "epoch": 2.3778613929656247, "grad_norm": 3.991638660430908, "learning_rate": 6.2844707372482905e-06, "loss": 0.127, "step": 400030 }, { "epoch": 2.377920835042293, "grad_norm": 2.934724807739258, "learning_rate": 6.284270207544781e-06, "loss": 0.1434, "step": 400040 }, { "epoch": 2.3779802771189615, "grad_norm": 4.453379154205322, "learning_rate": 6.284069675629606e-06, "loss": 0.1318, "step": 400050 }, { "epoch": 2.37803971919563, "grad_norm": 3.724977970123291, "learning_rate": 6.2838691415031095e-06, "loss": 0.125, "step": 400060 }, { "epoch": 2.3780991612722984, "grad_norm": 4.215514183044434, "learning_rate": 6.283668605165636e-06, "loss": 0.1395, "step": 400070 }, { "epoch": 2.378158603348967, "grad_norm": 3.3052055835723877, "learning_rate": 6.283468066617534e-06, "loss": 0.1486, "step": 400080 }, { "epoch": 2.378218045425635, "grad_norm": 4.116564750671387, "learning_rate": 6.283267525859147e-06, "loss": 0.1488, "step": 400090 }, { "epoch": 2.378277487502303, "grad_norm": 4.267014026641846, "learning_rate": 6.283066982890819e-06, "loss": 0.133, "step": 400100 }, { "epoch": 2.3783369295789716, "grad_norm": 4.168944358825684, "learning_rate": 6.2828664377128965e-06, "loss": 0.1302, "step": 400110 }, { "epoch": 2.37839637165564, "grad_norm": 4.304284572601318, "learning_rate": 6.282665890325725e-06, "loss": 0.1397, "step": 400120 }, { "epoch": 2.3784558137323084, "grad_norm": 4.415174961090088, "learning_rate": 6.282465340729651e-06, "loss": 0.1517, "step": 400130 }, { "epoch": 2.378515255808977, "grad_norm": 4.384090900421143, "learning_rate": 6.2822647889250165e-06, "loss": 0.1398, "step": 400140 }, { "epoch": 2.3785746978856452, "grad_norm": 3.77024245262146, "learning_rate": 6.282064234912171e-06, "loss": 0.1385, "step": 400150 }, { "epoch": 2.3786341399623137, "grad_norm": 3.2990224361419678, "learning_rate": 6.281863678691456e-06, "loss": 0.1391, "step": 400160 }, { "epoch": 2.378693582038982, "grad_norm": 3.610448122024536, "learning_rate": 6.281663120263219e-06, "loss": 0.1468, "step": 400170 }, { "epoch": 2.3787530241156505, "grad_norm": 4.330503940582275, "learning_rate": 6.281462559627807e-06, "loss": 0.1302, "step": 400180 }, { "epoch": 2.378812466192319, "grad_norm": 4.698505401611328, "learning_rate": 6.281261996785564e-06, "loss": 0.1494, "step": 400190 }, { "epoch": 2.3788719082689873, "grad_norm": 5.3834710121154785, "learning_rate": 6.2810614317368325e-06, "loss": 0.168, "step": 400200 }, { "epoch": 2.3789313503456557, "grad_norm": 3.5026323795318604, "learning_rate": 6.280860864481962e-06, "loss": 0.1411, "step": 400210 }, { "epoch": 2.378990792422324, "grad_norm": 4.241110801696777, "learning_rate": 6.280660295021297e-06, "loss": 0.1541, "step": 400220 }, { "epoch": 2.3790502344989926, "grad_norm": 5.146609306335449, "learning_rate": 6.28045972335518e-06, "loss": 0.1368, "step": 400230 }, { "epoch": 2.379109676575661, "grad_norm": 4.423044204711914, "learning_rate": 6.2802591494839605e-06, "loss": 0.1325, "step": 400240 }, { "epoch": 2.3791691186523294, "grad_norm": 5.237143039703369, "learning_rate": 6.280058573407981e-06, "loss": 0.1412, "step": 400250 }, { "epoch": 2.379228560728998, "grad_norm": 4.627911567687988, "learning_rate": 6.279857995127588e-06, "loss": 0.135, "step": 400260 }, { "epoch": 2.3792880028056658, "grad_norm": 4.5366387367248535, "learning_rate": 6.279657414643125e-06, "loss": 0.1636, "step": 400270 }, { "epoch": 2.3793474448823346, "grad_norm": 5.8605146408081055, "learning_rate": 6.279456831954942e-06, "loss": 0.1539, "step": 400280 }, { "epoch": 2.3794068869590026, "grad_norm": 5.035869598388672, "learning_rate": 6.279256247063381e-06, "loss": 0.1548, "step": 400290 }, { "epoch": 2.379466329035671, "grad_norm": 3.67759370803833, "learning_rate": 6.279055659968787e-06, "loss": 0.1508, "step": 400300 }, { "epoch": 2.3795257711123394, "grad_norm": 4.240255355834961, "learning_rate": 6.278855070671508e-06, "loss": 0.1466, "step": 400310 }, { "epoch": 2.379585213189008, "grad_norm": 3.5612704753875732, "learning_rate": 6.278654479171887e-06, "loss": 0.1415, "step": 400320 }, { "epoch": 2.3796446552656763, "grad_norm": 6.102359294891357, "learning_rate": 6.278453885470271e-06, "loss": 0.1559, "step": 400330 }, { "epoch": 2.3797040973423447, "grad_norm": 3.889404296875, "learning_rate": 6.278253289567005e-06, "loss": 0.1305, "step": 400340 }, { "epoch": 2.379763539419013, "grad_norm": 3.869091033935547, "learning_rate": 6.278052691462433e-06, "loss": 0.1393, "step": 400350 }, { "epoch": 2.3798229814956815, "grad_norm": 5.195314884185791, "learning_rate": 6.277852091156903e-06, "loss": 0.1377, "step": 400360 }, { "epoch": 2.37988242357235, "grad_norm": 3.757171630859375, "learning_rate": 6.277651488650759e-06, "loss": 0.1507, "step": 400370 }, { "epoch": 2.3799418656490183, "grad_norm": 4.560580730438232, "learning_rate": 6.277450883944346e-06, "loss": 0.1164, "step": 400380 }, { "epoch": 2.3800013077256867, "grad_norm": 4.203639507293701, "learning_rate": 6.2772502770380106e-06, "loss": 0.1495, "step": 400390 }, { "epoch": 2.380060749802355, "grad_norm": 4.728595733642578, "learning_rate": 6.277049667932098e-06, "loss": 0.1395, "step": 400400 }, { "epoch": 2.3801201918790236, "grad_norm": 4.374917984008789, "learning_rate": 6.276849056626953e-06, "loss": 0.1541, "step": 400410 }, { "epoch": 2.380179633955692, "grad_norm": 3.4010236263275146, "learning_rate": 6.276648443122924e-06, "loss": 0.1246, "step": 400420 }, { "epoch": 2.3802390760323604, "grad_norm": 5.062224864959717, "learning_rate": 6.276447827420351e-06, "loss": 0.1613, "step": 400430 }, { "epoch": 2.380298518109029, "grad_norm": 5.056729316711426, "learning_rate": 6.276247209519583e-06, "loss": 0.1541, "step": 400440 }, { "epoch": 2.3803579601856972, "grad_norm": 3.1640639305114746, "learning_rate": 6.276046589420967e-06, "loss": 0.1549, "step": 400450 }, { "epoch": 2.380417402262365, "grad_norm": 5.333329677581787, "learning_rate": 6.275845967124844e-06, "loss": 0.1407, "step": 400460 }, { "epoch": 2.380476844339034, "grad_norm": 4.8064284324646, "learning_rate": 6.275645342631563e-06, "loss": 0.1603, "step": 400470 }, { "epoch": 2.380536286415702, "grad_norm": 4.449441432952881, "learning_rate": 6.27544471594147e-06, "loss": 0.1403, "step": 400480 }, { "epoch": 2.3805957284923704, "grad_norm": 3.9858570098876953, "learning_rate": 6.275244087054907e-06, "loss": 0.142, "step": 400490 }, { "epoch": 2.380655170569039, "grad_norm": 3.820056438446045, "learning_rate": 6.275043455972222e-06, "loss": 0.1364, "step": 400500 }, { "epoch": 2.3807146126457073, "grad_norm": 3.0767643451690674, "learning_rate": 6.274842822693761e-06, "loss": 0.1479, "step": 400510 }, { "epoch": 2.3807740547223757, "grad_norm": 4.172464370727539, "learning_rate": 6.274642187219867e-06, "loss": 0.134, "step": 400520 }, { "epoch": 2.380833496799044, "grad_norm": 3.7766647338867188, "learning_rate": 6.274441549550887e-06, "loss": 0.1415, "step": 400530 }, { "epoch": 2.3808929388757125, "grad_norm": 4.348869800567627, "learning_rate": 6.274240909687168e-06, "loss": 0.1502, "step": 400540 }, { "epoch": 2.380952380952381, "grad_norm": 5.099135875701904, "learning_rate": 6.274040267629055e-06, "loss": 0.1566, "step": 400550 }, { "epoch": 2.3810118230290493, "grad_norm": 4.383172512054443, "learning_rate": 6.273839623376889e-06, "loss": 0.1485, "step": 400560 }, { "epoch": 2.3810712651057178, "grad_norm": 3.489384174346924, "learning_rate": 6.2736389769310225e-06, "loss": 0.1437, "step": 400570 }, { "epoch": 2.381130707182386, "grad_norm": 4.822574138641357, "learning_rate": 6.273438328291798e-06, "loss": 0.126, "step": 400580 }, { "epoch": 2.3811901492590546, "grad_norm": 5.099684715270996, "learning_rate": 6.273237677459558e-06, "loss": 0.1512, "step": 400590 }, { "epoch": 2.381249591335723, "grad_norm": 4.273253440856934, "learning_rate": 6.273037024434652e-06, "loss": 0.1206, "step": 400600 }, { "epoch": 2.3813090334123914, "grad_norm": 2.570871114730835, "learning_rate": 6.2728363692174245e-06, "loss": 0.1247, "step": 400610 }, { "epoch": 2.38136847548906, "grad_norm": 5.797459125518799, "learning_rate": 6.272635711808221e-06, "loss": 0.153, "step": 400620 }, { "epoch": 2.3814279175657282, "grad_norm": 4.6951751708984375, "learning_rate": 6.272435052207387e-06, "loss": 0.1531, "step": 400630 }, { "epoch": 2.3814873596423967, "grad_norm": 3.57072377204895, "learning_rate": 6.272234390415268e-06, "loss": 0.1292, "step": 400640 }, { "epoch": 2.3815468017190646, "grad_norm": 3.743859052658081, "learning_rate": 6.2720337264322096e-06, "loss": 0.1493, "step": 400650 }, { "epoch": 2.3816062437957335, "grad_norm": 3.9519734382629395, "learning_rate": 6.271833060258557e-06, "loss": 0.1438, "step": 400660 }, { "epoch": 2.3816656858724015, "grad_norm": 5.154002666473389, "learning_rate": 6.271632391894656e-06, "loss": 0.1564, "step": 400670 }, { "epoch": 2.38172512794907, "grad_norm": 2.80538010597229, "learning_rate": 6.271431721340854e-06, "loss": 0.1268, "step": 400680 }, { "epoch": 2.3817845700257383, "grad_norm": 4.257417678833008, "learning_rate": 6.271231048597492e-06, "loss": 0.1429, "step": 400690 }, { "epoch": 2.3818440121024067, "grad_norm": 4.6148176193237305, "learning_rate": 6.2710303736649214e-06, "loss": 0.1277, "step": 400700 }, { "epoch": 2.381903454179075, "grad_norm": 3.0534491539001465, "learning_rate": 6.270829696543482e-06, "loss": 0.1341, "step": 400710 }, { "epoch": 2.3819628962557435, "grad_norm": 3.3049240112304688, "learning_rate": 6.270629017233523e-06, "loss": 0.1321, "step": 400720 }, { "epoch": 2.382022338332412, "grad_norm": 5.006260395050049, "learning_rate": 6.27042833573539e-06, "loss": 0.1368, "step": 400730 }, { "epoch": 2.3820817804090804, "grad_norm": 6.4282355308532715, "learning_rate": 6.270227652049429e-06, "loss": 0.1232, "step": 400740 }, { "epoch": 2.3821412224857488, "grad_norm": 5.369811058044434, "learning_rate": 6.270026966175982e-06, "loss": 0.1407, "step": 400750 }, { "epoch": 2.382200664562417, "grad_norm": 5.122988700866699, "learning_rate": 6.269826278115398e-06, "loss": 0.1361, "step": 400760 }, { "epoch": 2.3822601066390856, "grad_norm": 4.4435930252075195, "learning_rate": 6.269625587868022e-06, "loss": 0.1235, "step": 400770 }, { "epoch": 2.382319548715754, "grad_norm": 2.997260332107544, "learning_rate": 6.2694248954342e-06, "loss": 0.1404, "step": 400780 }, { "epoch": 2.3823789907924224, "grad_norm": 4.854647636413574, "learning_rate": 6.2692242008142745e-06, "loss": 0.1343, "step": 400790 }, { "epoch": 2.382438432869091, "grad_norm": 2.5007457733154297, "learning_rate": 6.269023504008596e-06, "loss": 0.149, "step": 400800 }, { "epoch": 2.3824978749457593, "grad_norm": 5.2395782470703125, "learning_rate": 6.268822805017507e-06, "loss": 0.1456, "step": 400810 }, { "epoch": 2.3825573170224277, "grad_norm": 4.357956886291504, "learning_rate": 6.268622103841351e-06, "loss": 0.1337, "step": 400820 }, { "epoch": 2.382616759099096, "grad_norm": 3.5739831924438477, "learning_rate": 6.268421400480479e-06, "loss": 0.1337, "step": 400830 }, { "epoch": 2.382676201175764, "grad_norm": 3.9034385681152344, "learning_rate": 6.268220694935234e-06, "loss": 0.136, "step": 400840 }, { "epoch": 2.3827356432524325, "grad_norm": 4.814570426940918, "learning_rate": 6.268019987205961e-06, "loss": 0.15, "step": 400850 }, { "epoch": 2.382795085329101, "grad_norm": 3.8794755935668945, "learning_rate": 6.267819277293007e-06, "loss": 0.1333, "step": 400860 }, { "epoch": 2.3828545274057693, "grad_norm": 3.6318037509918213, "learning_rate": 6.267618565196716e-06, "loss": 0.1454, "step": 400870 }, { "epoch": 2.3829139694824377, "grad_norm": 4.841490268707275, "learning_rate": 6.267417850917435e-06, "loss": 0.1438, "step": 400880 }, { "epoch": 2.382973411559106, "grad_norm": 3.6695892810821533, "learning_rate": 6.26721713445551e-06, "loss": 0.1306, "step": 400890 }, { "epoch": 2.3830328536357746, "grad_norm": 4.059703826904297, "learning_rate": 6.267016415811284e-06, "loss": 0.1473, "step": 400900 }, { "epoch": 2.383092295712443, "grad_norm": 4.699084758758545, "learning_rate": 6.266815694985106e-06, "loss": 0.1499, "step": 400910 }, { "epoch": 2.3831517377891114, "grad_norm": 3.021195650100708, "learning_rate": 6.266614971977321e-06, "loss": 0.1375, "step": 400920 }, { "epoch": 2.38321117986578, "grad_norm": 3.6800448894500732, "learning_rate": 6.266414246788272e-06, "loss": 0.1383, "step": 400930 }, { "epoch": 2.383270621942448, "grad_norm": 4.530676364898682, "learning_rate": 6.266213519418307e-06, "loss": 0.15, "step": 400940 }, { "epoch": 2.3833300640191166, "grad_norm": 3.261139154434204, "learning_rate": 6.266012789867771e-06, "loss": 0.1439, "step": 400950 }, { "epoch": 2.383389506095785, "grad_norm": 4.366359710693359, "learning_rate": 6.265812058137011e-06, "loss": 0.1341, "step": 400960 }, { "epoch": 2.3834489481724535, "grad_norm": 4.531769275665283, "learning_rate": 6.265611324226372e-06, "loss": 0.1432, "step": 400970 }, { "epoch": 2.383508390249122, "grad_norm": 4.356931209564209, "learning_rate": 6.265410588136197e-06, "loss": 0.1495, "step": 400980 }, { "epoch": 2.3835678323257903, "grad_norm": 4.182827472686768, "learning_rate": 6.265209849866836e-06, "loss": 0.1523, "step": 400990 }, { "epoch": 2.3836272744024587, "grad_norm": 3.9145896434783936, "learning_rate": 6.2650091094186325e-06, "loss": 0.1514, "step": 401000 }, { "epoch": 2.3836867164791267, "grad_norm": 3.675550937652588, "learning_rate": 6.2648083667919315e-06, "loss": 0.1299, "step": 401010 }, { "epoch": 2.3837461585557955, "grad_norm": 3.2773077487945557, "learning_rate": 6.26460762198708e-06, "loss": 0.1469, "step": 401020 }, { "epoch": 2.3838056006324635, "grad_norm": 5.253991603851318, "learning_rate": 6.264406875004424e-06, "loss": 0.1407, "step": 401030 }, { "epoch": 2.383865042709132, "grad_norm": 4.862598896026611, "learning_rate": 6.264206125844307e-06, "loss": 0.1548, "step": 401040 }, { "epoch": 2.3839244847858003, "grad_norm": 5.4666924476623535, "learning_rate": 6.264005374507076e-06, "loss": 0.1413, "step": 401050 }, { "epoch": 2.3839839268624687, "grad_norm": 6.396439075469971, "learning_rate": 6.2638046209930795e-06, "loss": 0.1606, "step": 401060 }, { "epoch": 2.384043368939137, "grad_norm": 4.9252519607543945, "learning_rate": 6.263603865302659e-06, "loss": 0.1558, "step": 401070 }, { "epoch": 2.3841028110158056, "grad_norm": 3.7697038650512695, "learning_rate": 6.263403107436161e-06, "loss": 0.1558, "step": 401080 }, { "epoch": 2.384162253092474, "grad_norm": 3.5464651584625244, "learning_rate": 6.263202347393933e-06, "loss": 0.1315, "step": 401090 }, { "epoch": 2.3842216951691424, "grad_norm": 4.261017799377441, "learning_rate": 6.26300158517632e-06, "loss": 0.1377, "step": 401100 }, { "epoch": 2.384281137245811, "grad_norm": 3.1077353954315186, "learning_rate": 6.262800820783668e-06, "loss": 0.138, "step": 401110 }, { "epoch": 2.3843405793224792, "grad_norm": 3.614525318145752, "learning_rate": 6.262600054216322e-06, "loss": 0.1399, "step": 401120 }, { "epoch": 2.3844000213991476, "grad_norm": 4.159260272979736, "learning_rate": 6.2623992854746275e-06, "loss": 0.1509, "step": 401130 }, { "epoch": 2.384459463475816, "grad_norm": 4.049018383026123, "learning_rate": 6.26219851455893e-06, "loss": 0.1432, "step": 401140 }, { "epoch": 2.3845189055524845, "grad_norm": 4.801767349243164, "learning_rate": 6.261997741469578e-06, "loss": 0.136, "step": 401150 }, { "epoch": 2.384578347629153, "grad_norm": 3.5527825355529785, "learning_rate": 6.261796966206914e-06, "loss": 0.1541, "step": 401160 }, { "epoch": 2.3846377897058213, "grad_norm": 3.7155141830444336, "learning_rate": 6.261596188771286e-06, "loss": 0.1205, "step": 401170 }, { "epoch": 2.3846972317824897, "grad_norm": 3.6356117725372314, "learning_rate": 6.261395409163038e-06, "loss": 0.1238, "step": 401180 }, { "epoch": 2.384756673859158, "grad_norm": 4.574862957000732, "learning_rate": 6.261194627382517e-06, "loss": 0.1456, "step": 401190 }, { "epoch": 2.384816115935826, "grad_norm": 5.131004333496094, "learning_rate": 6.26099384343007e-06, "loss": 0.1458, "step": 401200 }, { "epoch": 2.384875558012495, "grad_norm": 3.9708986282348633, "learning_rate": 6.260793057306038e-06, "loss": 0.1492, "step": 401210 }, { "epoch": 2.384935000089163, "grad_norm": 4.366743087768555, "learning_rate": 6.260592269010772e-06, "loss": 0.1406, "step": 401220 }, { "epoch": 2.3849944421658313, "grad_norm": 4.213271141052246, "learning_rate": 6.260391478544615e-06, "loss": 0.1395, "step": 401230 }, { "epoch": 2.3850538842424998, "grad_norm": 3.981564521789551, "learning_rate": 6.260190685907913e-06, "loss": 0.1394, "step": 401240 }, { "epoch": 2.385113326319168, "grad_norm": 4.430244445800781, "learning_rate": 6.259989891101014e-06, "loss": 0.1421, "step": 401250 }, { "epoch": 2.3851727683958366, "grad_norm": 3.890620470046997, "learning_rate": 6.25978909412426e-06, "loss": 0.1298, "step": 401260 }, { "epoch": 2.385232210472505, "grad_norm": 5.350127220153809, "learning_rate": 6.259588294978001e-06, "loss": 0.1582, "step": 401270 }, { "epoch": 2.3852916525491734, "grad_norm": 5.149519920349121, "learning_rate": 6.259387493662579e-06, "loss": 0.1548, "step": 401280 }, { "epoch": 2.385351094625842, "grad_norm": 3.1946098804473877, "learning_rate": 6.259186690178342e-06, "loss": 0.1507, "step": 401290 }, { "epoch": 2.3854105367025102, "grad_norm": 3.2449653148651123, "learning_rate": 6.2589858845256345e-06, "loss": 0.1438, "step": 401300 }, { "epoch": 2.3854699787791787, "grad_norm": 4.305583477020264, "learning_rate": 6.258785076704803e-06, "loss": 0.1402, "step": 401310 }, { "epoch": 2.385529420855847, "grad_norm": 4.648379802703857, "learning_rate": 6.258584266716196e-06, "loss": 0.1419, "step": 401320 }, { "epoch": 2.3855888629325155, "grad_norm": 3.7821199893951416, "learning_rate": 6.258383454560155e-06, "loss": 0.1439, "step": 401330 }, { "epoch": 2.385648305009184, "grad_norm": 3.8506555557250977, "learning_rate": 6.258182640237027e-06, "loss": 0.1428, "step": 401340 }, { "epoch": 2.3857077470858523, "grad_norm": 3.6327319145202637, "learning_rate": 6.257981823747159e-06, "loss": 0.1305, "step": 401350 }, { "epoch": 2.3857671891625207, "grad_norm": 5.273071765899658, "learning_rate": 6.257781005090896e-06, "loss": 0.1399, "step": 401360 }, { "epoch": 2.385826631239189, "grad_norm": 4.33749532699585, "learning_rate": 6.2575801842685824e-06, "loss": 0.1518, "step": 401370 }, { "epoch": 2.3858860733158576, "grad_norm": 4.526244640350342, "learning_rate": 6.257379361280567e-06, "loss": 0.1291, "step": 401380 }, { "epoch": 2.3859455153925255, "grad_norm": 4.9336700439453125, "learning_rate": 6.2571785361271965e-06, "loss": 0.1407, "step": 401390 }, { "epoch": 2.3860049574691944, "grad_norm": 3.6190025806427, "learning_rate": 6.256977708808811e-06, "loss": 0.1537, "step": 401400 }, { "epoch": 2.3860643995458624, "grad_norm": 5.058162689208984, "learning_rate": 6.256776879325763e-06, "loss": 0.1557, "step": 401410 }, { "epoch": 2.3861238416225308, "grad_norm": 3.669133186340332, "learning_rate": 6.256576047678394e-06, "loss": 0.1412, "step": 401420 }, { "epoch": 2.386183283699199, "grad_norm": 5.403264045715332, "learning_rate": 6.25637521386705e-06, "loss": 0.1544, "step": 401430 }, { "epoch": 2.3862427257758676, "grad_norm": 4.061774253845215, "learning_rate": 6.256174377892079e-06, "loss": 0.1277, "step": 401440 }, { "epoch": 2.386302167852536, "grad_norm": 3.804518222808838, "learning_rate": 6.255973539753827e-06, "loss": 0.1374, "step": 401450 }, { "epoch": 2.3863616099292044, "grad_norm": 4.4441046714782715, "learning_rate": 6.255772699452638e-06, "loss": 0.1299, "step": 401460 }, { "epoch": 2.386421052005873, "grad_norm": 5.702470779418945, "learning_rate": 6.255571856988857e-06, "loss": 0.131, "step": 401470 }, { "epoch": 2.3864804940825413, "grad_norm": 5.423713207244873, "learning_rate": 6.255371012362832e-06, "loss": 0.1542, "step": 401480 }, { "epoch": 2.3865399361592097, "grad_norm": 4.711405277252197, "learning_rate": 6.25517016557491e-06, "loss": 0.1523, "step": 401490 }, { "epoch": 2.386599378235878, "grad_norm": 4.150332450866699, "learning_rate": 6.2549693166254325e-06, "loss": 0.1446, "step": 401500 }, { "epoch": 2.3866588203125465, "grad_norm": 4.46519136428833, "learning_rate": 6.25476846551475e-06, "loss": 0.1437, "step": 401510 }, { "epoch": 2.386718262389215, "grad_norm": 4.60467004776001, "learning_rate": 6.254567612243208e-06, "loss": 0.1436, "step": 401520 }, { "epoch": 2.3867777044658833, "grad_norm": 3.598384141921997, "learning_rate": 6.2543667568111474e-06, "loss": 0.1497, "step": 401530 }, { "epoch": 2.3868371465425517, "grad_norm": 4.318390846252441, "learning_rate": 6.254165899218919e-06, "loss": 0.1309, "step": 401540 }, { "epoch": 2.38689658861922, "grad_norm": 4.625019550323486, "learning_rate": 6.253965039466868e-06, "loss": 0.1434, "step": 401550 }, { "epoch": 2.3869560306958886, "grad_norm": 4.628068923950195, "learning_rate": 6.2537641775553395e-06, "loss": 0.1747, "step": 401560 }, { "epoch": 2.387015472772557, "grad_norm": 4.886614799499512, "learning_rate": 6.253563313484678e-06, "loss": 0.1237, "step": 401570 }, { "epoch": 2.387074914849225, "grad_norm": 4.016249179840088, "learning_rate": 6.253362447255234e-06, "loss": 0.1432, "step": 401580 }, { "epoch": 2.3871343569258934, "grad_norm": 4.295063495635986, "learning_rate": 6.253161578867346e-06, "loss": 0.1447, "step": 401590 }, { "epoch": 2.387193799002562, "grad_norm": 4.525272369384766, "learning_rate": 6.252960708321367e-06, "loss": 0.1301, "step": 401600 }, { "epoch": 2.38725324107923, "grad_norm": 4.066357135772705, "learning_rate": 6.25275983561764e-06, "loss": 0.1451, "step": 401610 }, { "epoch": 2.3873126831558986, "grad_norm": 4.985657691955566, "learning_rate": 6.252558960756511e-06, "loss": 0.1569, "step": 401620 }, { "epoch": 2.387372125232567, "grad_norm": 4.965877056121826, "learning_rate": 6.252358083738325e-06, "loss": 0.1557, "step": 401630 }, { "epoch": 2.3874315673092354, "grad_norm": 3.9328184127807617, "learning_rate": 6.2521572045634305e-06, "loss": 0.1398, "step": 401640 }, { "epoch": 2.387491009385904, "grad_norm": 5.043257236480713, "learning_rate": 6.251956323232171e-06, "loss": 0.1401, "step": 401650 }, { "epoch": 2.3875504514625723, "grad_norm": 4.015799045562744, "learning_rate": 6.251755439744893e-06, "loss": 0.1434, "step": 401660 }, { "epoch": 2.3876098935392407, "grad_norm": 4.547402381896973, "learning_rate": 6.251554554101944e-06, "loss": 0.142, "step": 401670 }, { "epoch": 2.387669335615909, "grad_norm": 2.5405640602111816, "learning_rate": 6.2513536663036675e-06, "loss": 0.1458, "step": 401680 }, { "epoch": 2.3877287776925775, "grad_norm": 4.156270980834961, "learning_rate": 6.251152776350411e-06, "loss": 0.1353, "step": 401690 }, { "epoch": 2.387788219769246, "grad_norm": 4.758719444274902, "learning_rate": 6.25095188424252e-06, "loss": 0.1521, "step": 401700 }, { "epoch": 2.3878476618459143, "grad_norm": 5.65973424911499, "learning_rate": 6.250750989980341e-06, "loss": 0.1476, "step": 401710 }, { "epoch": 2.3879071039225828, "grad_norm": 4.536719799041748, "learning_rate": 6.25055009356422e-06, "loss": 0.1526, "step": 401720 }, { "epoch": 2.387966545999251, "grad_norm": 4.466021537780762, "learning_rate": 6.2503491949945e-06, "loss": 0.1331, "step": 401730 }, { "epoch": 2.3880259880759196, "grad_norm": 4.292449951171875, "learning_rate": 6.250148294271533e-06, "loss": 0.1288, "step": 401740 }, { "epoch": 2.3880854301525876, "grad_norm": 3.85983943939209, "learning_rate": 6.24994739139566e-06, "loss": 0.1298, "step": 401750 }, { "epoch": 2.3881448722292564, "grad_norm": 4.165205001831055, "learning_rate": 6.249746486367228e-06, "loss": 0.1568, "step": 401760 }, { "epoch": 2.3882043143059244, "grad_norm": 4.833781719207764, "learning_rate": 6.249545579186585e-06, "loss": 0.1353, "step": 401770 }, { "epoch": 2.388263756382593, "grad_norm": 3.9229700565338135, "learning_rate": 6.249344669854074e-06, "loss": 0.1377, "step": 401780 }, { "epoch": 2.388323198459261, "grad_norm": 5.358994483947754, "learning_rate": 6.249143758370042e-06, "loss": 0.1494, "step": 401790 }, { "epoch": 2.3883826405359296, "grad_norm": 4.768904209136963, "learning_rate": 6.248942844734835e-06, "loss": 0.1403, "step": 401800 }, { "epoch": 2.388442082612598, "grad_norm": 3.663670539855957, "learning_rate": 6.2487419289488e-06, "loss": 0.1332, "step": 401810 }, { "epoch": 2.3885015246892665, "grad_norm": 4.568813800811768, "learning_rate": 6.248541011012284e-06, "loss": 0.1253, "step": 401820 }, { "epoch": 2.388560966765935, "grad_norm": 3.650343656539917, "learning_rate": 6.2483400909256295e-06, "loss": 0.1431, "step": 401830 }, { "epoch": 2.3886204088426033, "grad_norm": 4.359482288360596, "learning_rate": 6.248139168689186e-06, "loss": 0.1382, "step": 401840 }, { "epoch": 2.3886798509192717, "grad_norm": 4.521820545196533, "learning_rate": 6.247938244303297e-06, "loss": 0.1347, "step": 401850 }, { "epoch": 2.38873929299594, "grad_norm": 3.26688814163208, "learning_rate": 6.247737317768309e-06, "loss": 0.1337, "step": 401860 }, { "epoch": 2.3887987350726085, "grad_norm": 4.3946533203125, "learning_rate": 6.24753638908457e-06, "loss": 0.138, "step": 401870 }, { "epoch": 2.388858177149277, "grad_norm": 4.39859676361084, "learning_rate": 6.247335458252423e-06, "loss": 0.1287, "step": 401880 }, { "epoch": 2.3889176192259454, "grad_norm": 4.287448883056641, "learning_rate": 6.247134525272216e-06, "loss": 0.1454, "step": 401890 }, { "epoch": 2.388977061302614, "grad_norm": 4.819755554199219, "learning_rate": 6.246933590144294e-06, "loss": 0.1556, "step": 401900 }, { "epoch": 2.389036503379282, "grad_norm": 5.902949333190918, "learning_rate": 6.246732652869005e-06, "loss": 0.1557, "step": 401910 }, { "epoch": 2.3890959454559506, "grad_norm": 3.1475789546966553, "learning_rate": 6.246531713446692e-06, "loss": 0.1218, "step": 401920 }, { "epoch": 2.389155387532619, "grad_norm": 4.584764003753662, "learning_rate": 6.246330771877702e-06, "loss": 0.1429, "step": 401930 }, { "epoch": 2.389214829609287, "grad_norm": 3.9577996730804443, "learning_rate": 6.246129828162384e-06, "loss": 0.151, "step": 401940 }, { "epoch": 2.389274271685956, "grad_norm": 3.5972349643707275, "learning_rate": 6.245928882301081e-06, "loss": 0.1435, "step": 401950 }, { "epoch": 2.389333713762624, "grad_norm": 3.869908571243286, "learning_rate": 6.245727934294139e-06, "loss": 0.1371, "step": 401960 }, { "epoch": 2.3893931558392922, "grad_norm": 4.805239677429199, "learning_rate": 6.245526984141906e-06, "loss": 0.1436, "step": 401970 }, { "epoch": 2.3894525979159607, "grad_norm": 3.7218575477600098, "learning_rate": 6.2453260318447276e-06, "loss": 0.1462, "step": 401980 }, { "epoch": 2.389512039992629, "grad_norm": 3.767451286315918, "learning_rate": 6.245125077402947e-06, "loss": 0.1301, "step": 401990 }, { "epoch": 2.3895714820692975, "grad_norm": 5.391018390655518, "learning_rate": 6.244924120816913e-06, "loss": 0.1331, "step": 402000 }, { "epoch": 2.389630924145966, "grad_norm": 3.0206987857818604, "learning_rate": 6.244723162086972e-06, "loss": 0.1359, "step": 402010 }, { "epoch": 2.3896903662226343, "grad_norm": 4.537403106689453, "learning_rate": 6.244522201213469e-06, "loss": 0.1514, "step": 402020 }, { "epoch": 2.3897498082993027, "grad_norm": 4.93702507019043, "learning_rate": 6.244321238196749e-06, "loss": 0.1451, "step": 402030 }, { "epoch": 2.389809250375971, "grad_norm": 5.299641132354736, "learning_rate": 6.24412027303716e-06, "loss": 0.1386, "step": 402040 }, { "epoch": 2.3898686924526396, "grad_norm": 4.4624128341674805, "learning_rate": 6.243919305735048e-06, "loss": 0.1331, "step": 402050 }, { "epoch": 2.389928134529308, "grad_norm": 3.7292866706848145, "learning_rate": 6.243718336290758e-06, "loss": 0.1358, "step": 402060 }, { "epoch": 2.3899875766059764, "grad_norm": 3.7534914016723633, "learning_rate": 6.243517364704638e-06, "loss": 0.1347, "step": 402070 }, { "epoch": 2.390047018682645, "grad_norm": 6.220953464508057, "learning_rate": 6.243316390977031e-06, "loss": 0.1324, "step": 402080 }, { "epoch": 2.390106460759313, "grad_norm": 4.955694198608398, "learning_rate": 6.2431154151082865e-06, "loss": 0.1457, "step": 402090 }, { "epoch": 2.3901659028359816, "grad_norm": 5.288788318634033, "learning_rate": 6.2429144370987485e-06, "loss": 0.1385, "step": 402100 }, { "epoch": 2.39022534491265, "grad_norm": 4.311511993408203, "learning_rate": 6.2427134569487625e-06, "loss": 0.1335, "step": 402110 }, { "epoch": 2.3902847869893185, "grad_norm": 3.266322374343872, "learning_rate": 6.242512474658675e-06, "loss": 0.1421, "step": 402120 }, { "epoch": 2.3903442290659864, "grad_norm": 3.5788986682891846, "learning_rate": 6.242311490228835e-06, "loss": 0.1394, "step": 402130 }, { "epoch": 2.3904036711426553, "grad_norm": 3.8429293632507324, "learning_rate": 6.242110503659584e-06, "loss": 0.146, "step": 402140 }, { "epoch": 2.3904631132193233, "grad_norm": 4.546383857727051, "learning_rate": 6.241909514951272e-06, "loss": 0.1469, "step": 402150 }, { "epoch": 2.3905225552959917, "grad_norm": 4.1695876121521, "learning_rate": 6.241708524104244e-06, "loss": 0.1253, "step": 402160 }, { "epoch": 2.39058199737266, "grad_norm": 4.451458930969238, "learning_rate": 6.241507531118845e-06, "loss": 0.1506, "step": 402170 }, { "epoch": 2.3906414394493285, "grad_norm": 4.209877967834473, "learning_rate": 6.241306535995422e-06, "loss": 0.1333, "step": 402180 }, { "epoch": 2.390700881525997, "grad_norm": 4.162404537200928, "learning_rate": 6.2411055387343215e-06, "loss": 0.1601, "step": 402190 }, { "epoch": 2.3907603236026653, "grad_norm": 4.085139751434326, "learning_rate": 6.2409045393358895e-06, "loss": 0.1424, "step": 402200 }, { "epoch": 2.3908197656793337, "grad_norm": 4.6707916259765625, "learning_rate": 6.24070353780047e-06, "loss": 0.1567, "step": 402210 }, { "epoch": 2.390879207756002, "grad_norm": 4.081469535827637, "learning_rate": 6.240502534128412e-06, "loss": 0.1537, "step": 402220 }, { "epoch": 2.3909386498326706, "grad_norm": 5.78108549118042, "learning_rate": 6.240301528320062e-06, "loss": 0.1336, "step": 402230 }, { "epoch": 2.390998091909339, "grad_norm": 4.705292701721191, "learning_rate": 6.240100520375762e-06, "loss": 0.132, "step": 402240 }, { "epoch": 2.3910575339860074, "grad_norm": 4.306413650512695, "learning_rate": 6.239899510295861e-06, "loss": 0.1458, "step": 402250 }, { "epoch": 2.391116976062676, "grad_norm": 4.425716400146484, "learning_rate": 6.239698498080709e-06, "loss": 0.138, "step": 402260 }, { "epoch": 2.3911764181393442, "grad_norm": 4.114800453186035, "learning_rate": 6.239497483730645e-06, "loss": 0.1368, "step": 402270 }, { "epoch": 2.3912358602160126, "grad_norm": 4.459019184112549, "learning_rate": 6.239296467246019e-06, "loss": 0.1243, "step": 402280 }, { "epoch": 2.391295302292681, "grad_norm": 4.834836959838867, "learning_rate": 6.239095448627177e-06, "loss": 0.1376, "step": 402290 }, { "epoch": 2.3913547443693495, "grad_norm": 4.722074031829834, "learning_rate": 6.238894427874465e-06, "loss": 0.1457, "step": 402300 }, { "epoch": 2.391414186446018, "grad_norm": 3.5989999771118164, "learning_rate": 6.238693404988228e-06, "loss": 0.1317, "step": 402310 }, { "epoch": 2.391473628522686, "grad_norm": 4.407267093658447, "learning_rate": 6.238492379968814e-06, "loss": 0.1407, "step": 402320 }, { "epoch": 2.3915330705993543, "grad_norm": 3.716740369796753, "learning_rate": 6.238291352816569e-06, "loss": 0.1587, "step": 402330 }, { "epoch": 2.3915925126760227, "grad_norm": 4.174698829650879, "learning_rate": 6.238090323531837e-06, "loss": 0.1301, "step": 402340 }, { "epoch": 2.391651954752691, "grad_norm": 4.889492511749268, "learning_rate": 6.237889292114967e-06, "loss": 0.1318, "step": 402350 }, { "epoch": 2.3917113968293595, "grad_norm": 3.645195484161377, "learning_rate": 6.2376882585663025e-06, "loss": 0.1256, "step": 402360 }, { "epoch": 2.391770838906028, "grad_norm": 3.13150691986084, "learning_rate": 6.237487222886192e-06, "loss": 0.1371, "step": 402370 }, { "epoch": 2.3918302809826963, "grad_norm": 5.111847400665283, "learning_rate": 6.23728618507498e-06, "loss": 0.1437, "step": 402380 }, { "epoch": 2.3918897230593648, "grad_norm": 5.208973407745361, "learning_rate": 6.237085145133015e-06, "loss": 0.1207, "step": 402390 }, { "epoch": 2.391949165136033, "grad_norm": 5.622167587280273, "learning_rate": 6.236884103060642e-06, "loss": 0.1454, "step": 402400 }, { "epoch": 2.3920086072127016, "grad_norm": 5.202962398529053, "learning_rate": 6.236683058858205e-06, "loss": 0.1389, "step": 402410 }, { "epoch": 2.39206804928937, "grad_norm": 4.860553741455078, "learning_rate": 6.236482012526054e-06, "loss": 0.1438, "step": 402420 }, { "epoch": 2.3921274913660384, "grad_norm": 5.2839765548706055, "learning_rate": 6.236280964064533e-06, "loss": 0.132, "step": 402430 }, { "epoch": 2.392186933442707, "grad_norm": 4.04595947265625, "learning_rate": 6.236079913473988e-06, "loss": 0.1496, "step": 402440 }, { "epoch": 2.3922463755193752, "grad_norm": 4.612368583679199, "learning_rate": 6.235878860754767e-06, "loss": 0.1567, "step": 402450 }, { "epoch": 2.3923058175960437, "grad_norm": 4.1108503341674805, "learning_rate": 6.235677805907214e-06, "loss": 0.1314, "step": 402460 }, { "epoch": 2.392365259672712, "grad_norm": 4.082180500030518, "learning_rate": 6.235476748931677e-06, "loss": 0.1408, "step": 402470 }, { "epoch": 2.3924247017493805, "grad_norm": 5.36208438873291, "learning_rate": 6.2352756898285e-06, "loss": 0.126, "step": 402480 }, { "epoch": 2.3924841438260485, "grad_norm": 3.5426864624023438, "learning_rate": 6.235074628598034e-06, "loss": 0.1253, "step": 402490 }, { "epoch": 2.3925435859027173, "grad_norm": 5.039264678955078, "learning_rate": 6.23487356524062e-06, "loss": 0.1399, "step": 402500 }, { "epoch": 2.3926030279793853, "grad_norm": 3.100895881652832, "learning_rate": 6.234672499756606e-06, "loss": 0.124, "step": 402510 }, { "epoch": 2.3926624700560537, "grad_norm": 4.514717102050781, "learning_rate": 6.234471432146341e-06, "loss": 0.1539, "step": 402520 }, { "epoch": 2.392721912132722, "grad_norm": 4.2684102058410645, "learning_rate": 6.234270362410168e-06, "loss": 0.1489, "step": 402530 }, { "epoch": 2.3927813542093905, "grad_norm": 3.6149208545684814, "learning_rate": 6.234069290548432e-06, "loss": 0.136, "step": 402540 }, { "epoch": 2.392840796286059, "grad_norm": 6.569983005523682, "learning_rate": 6.233868216561484e-06, "loss": 0.1165, "step": 402550 }, { "epoch": 2.3929002383627274, "grad_norm": 4.292716979980469, "learning_rate": 6.233667140449666e-06, "loss": 0.1349, "step": 402560 }, { "epoch": 2.3929596804393958, "grad_norm": 5.485591411590576, "learning_rate": 6.2334660622133266e-06, "loss": 0.1525, "step": 402570 }, { "epoch": 2.393019122516064, "grad_norm": 4.549722194671631, "learning_rate": 6.2332649818528114e-06, "loss": 0.1479, "step": 402580 }, { "epoch": 2.3930785645927326, "grad_norm": 4.187106132507324, "learning_rate": 6.233063899368467e-06, "loss": 0.1424, "step": 402590 }, { "epoch": 2.393138006669401, "grad_norm": 5.038313388824463, "learning_rate": 6.23286281476064e-06, "loss": 0.1297, "step": 402600 }, { "epoch": 2.3931974487460694, "grad_norm": 2.9852347373962402, "learning_rate": 6.232661728029674e-06, "loss": 0.1519, "step": 402610 }, { "epoch": 2.393256890822738, "grad_norm": 3.1303458213806152, "learning_rate": 6.23246063917592e-06, "loss": 0.1462, "step": 402620 }, { "epoch": 2.3933163328994063, "grad_norm": 4.110625743865967, "learning_rate": 6.232259548199722e-06, "loss": 0.1489, "step": 402630 }, { "epoch": 2.3933757749760747, "grad_norm": 5.395272254943848, "learning_rate": 6.232058455101423e-06, "loss": 0.1457, "step": 402640 }, { "epoch": 2.393435217052743, "grad_norm": 4.347996234893799, "learning_rate": 6.231857359881375e-06, "loss": 0.1457, "step": 402650 }, { "epoch": 2.3934946591294115, "grad_norm": 6.461598873138428, "learning_rate": 6.23165626253992e-06, "loss": 0.1593, "step": 402660 }, { "epoch": 2.39355410120608, "grad_norm": 3.3269267082214355, "learning_rate": 6.231455163077407e-06, "loss": 0.1519, "step": 402670 }, { "epoch": 2.393613543282748, "grad_norm": 3.306687355041504, "learning_rate": 6.231254061494181e-06, "loss": 0.1377, "step": 402680 }, { "epoch": 2.3936729853594167, "grad_norm": 3.7478129863739014, "learning_rate": 6.231052957790587e-06, "loss": 0.1326, "step": 402690 }, { "epoch": 2.3937324274360847, "grad_norm": 5.908361434936523, "learning_rate": 6.230851851966974e-06, "loss": 0.1341, "step": 402700 }, { "epoch": 2.393791869512753, "grad_norm": 4.262414932250977, "learning_rate": 6.2306507440236885e-06, "loss": 0.1445, "step": 402710 }, { "epoch": 2.3938513115894215, "grad_norm": 5.305954933166504, "learning_rate": 6.230449633961075e-06, "loss": 0.1416, "step": 402720 }, { "epoch": 2.39391075366609, "grad_norm": 4.145165920257568, "learning_rate": 6.23024852177948e-06, "loss": 0.1431, "step": 402730 }, { "epoch": 2.3939701957427584, "grad_norm": 3.9284327030181885, "learning_rate": 6.230047407479251e-06, "loss": 0.1429, "step": 402740 }, { "epoch": 2.394029637819427, "grad_norm": 3.155898332595825, "learning_rate": 6.229846291060733e-06, "loss": 0.1347, "step": 402750 }, { "epoch": 2.394089079896095, "grad_norm": 3.838775634765625, "learning_rate": 6.229645172524272e-06, "loss": 0.1431, "step": 402760 }, { "epoch": 2.3941485219727636, "grad_norm": 3.8348560333251953, "learning_rate": 6.229444051870217e-06, "loss": 0.1339, "step": 402770 }, { "epoch": 2.394207964049432, "grad_norm": 4.60563325881958, "learning_rate": 6.229242929098912e-06, "loss": 0.1438, "step": 402780 }, { "epoch": 2.3942674061261005, "grad_norm": 3.86067271232605, "learning_rate": 6.229041804210705e-06, "loss": 0.1219, "step": 402790 }, { "epoch": 2.394326848202769, "grad_norm": 4.2963032722473145, "learning_rate": 6.228840677205937e-06, "loss": 0.1471, "step": 402800 }, { "epoch": 2.3943862902794373, "grad_norm": 6.362959384918213, "learning_rate": 6.228639548084962e-06, "loss": 0.1695, "step": 402810 }, { "epoch": 2.3944457323561057, "grad_norm": 3.8793394565582275, "learning_rate": 6.228438416848125e-06, "loss": 0.1313, "step": 402820 }, { "epoch": 2.394505174432774, "grad_norm": 3.4937562942504883, "learning_rate": 6.228237283495767e-06, "loss": 0.13, "step": 402830 }, { "epoch": 2.3945646165094425, "grad_norm": 4.454566955566406, "learning_rate": 6.228036148028241e-06, "loss": 0.146, "step": 402840 }, { "epoch": 2.394624058586111, "grad_norm": 4.924375534057617, "learning_rate": 6.227835010445889e-06, "loss": 0.1443, "step": 402850 }, { "epoch": 2.3946835006627794, "grad_norm": 4.537144660949707, "learning_rate": 6.227633870749057e-06, "loss": 0.1518, "step": 402860 }, { "epoch": 2.3947429427394473, "grad_norm": 6.2602057456970215, "learning_rate": 6.227432728938094e-06, "loss": 0.1404, "step": 402870 }, { "epoch": 2.394802384816116, "grad_norm": 4.090665340423584, "learning_rate": 6.227231585013347e-06, "loss": 0.1512, "step": 402880 }, { "epoch": 2.394861826892784, "grad_norm": 3.916564464569092, "learning_rate": 6.227030438975158e-06, "loss": 0.1479, "step": 402890 }, { "epoch": 2.3949212689694526, "grad_norm": 3.491708517074585, "learning_rate": 6.226829290823878e-06, "loss": 0.1347, "step": 402900 }, { "epoch": 2.394980711046121, "grad_norm": 3.8718721866607666, "learning_rate": 6.2266281405598505e-06, "loss": 0.1471, "step": 402910 }, { "epoch": 2.3950401531227894, "grad_norm": 4.344213962554932, "learning_rate": 6.226426988183425e-06, "loss": 0.1377, "step": 402920 }, { "epoch": 2.395099595199458, "grad_norm": 3.2069144248962402, "learning_rate": 6.226225833694943e-06, "loss": 0.1336, "step": 402930 }, { "epoch": 2.3951590372761262, "grad_norm": 3.6131644248962402, "learning_rate": 6.2260246770947565e-06, "loss": 0.1292, "step": 402940 }, { "epoch": 2.3952184793527946, "grad_norm": 3.2410829067230225, "learning_rate": 6.2258235183832084e-06, "loss": 0.1398, "step": 402950 }, { "epoch": 2.395277921429463, "grad_norm": 4.267178535461426, "learning_rate": 6.225622357560644e-06, "loss": 0.1378, "step": 402960 }, { "epoch": 2.3953373635061315, "grad_norm": 5.555066108703613, "learning_rate": 6.225421194627414e-06, "loss": 0.142, "step": 402970 }, { "epoch": 2.3953968055828, "grad_norm": 4.171189308166504, "learning_rate": 6.225220029583863e-06, "loss": 0.1701, "step": 402980 }, { "epoch": 2.3954562476594683, "grad_norm": 4.245860576629639, "learning_rate": 6.225018862430334e-06, "loss": 0.1378, "step": 402990 }, { "epoch": 2.3955156897361367, "grad_norm": 3.651712656021118, "learning_rate": 6.224817693167179e-06, "loss": 0.14, "step": 403000 }, { "epoch": 2.395575131812805, "grad_norm": 3.504591226577759, "learning_rate": 6.224616521794741e-06, "loss": 0.152, "step": 403010 }, { "epoch": 2.3956345738894735, "grad_norm": 3.031622886657715, "learning_rate": 6.224415348313366e-06, "loss": 0.1397, "step": 403020 }, { "epoch": 2.395694015966142, "grad_norm": 5.697730541229248, "learning_rate": 6.2242141727234015e-06, "loss": 0.1572, "step": 403030 }, { "epoch": 2.3957534580428104, "grad_norm": 4.595243453979492, "learning_rate": 6.224012995025197e-06, "loss": 0.1387, "step": 403040 }, { "epoch": 2.395812900119479, "grad_norm": 4.331903457641602, "learning_rate": 6.223811815219094e-06, "loss": 0.1434, "step": 403050 }, { "epoch": 2.3958723421961468, "grad_norm": 4.163175106048584, "learning_rate": 6.223610633305442e-06, "loss": 0.1258, "step": 403060 }, { "epoch": 2.395931784272815, "grad_norm": 3.914738655090332, "learning_rate": 6.2234094492845856e-06, "loss": 0.1297, "step": 403070 }, { "epoch": 2.3959912263494836, "grad_norm": 4.837896347045898, "learning_rate": 6.223208263156872e-06, "loss": 0.1711, "step": 403080 }, { "epoch": 2.396050668426152, "grad_norm": 4.148899555206299, "learning_rate": 6.223007074922648e-06, "loss": 0.1385, "step": 403090 }, { "epoch": 2.3961101105028204, "grad_norm": 4.411248207092285, "learning_rate": 6.222805884582261e-06, "loss": 0.1348, "step": 403100 }, { "epoch": 2.396169552579489, "grad_norm": 6.073668003082275, "learning_rate": 6.222604692136056e-06, "loss": 0.158, "step": 403110 }, { "epoch": 2.3962289946561572, "grad_norm": 4.006023406982422, "learning_rate": 6.222403497584378e-06, "loss": 0.1324, "step": 403120 }, { "epoch": 2.3962884367328257, "grad_norm": 4.001729488372803, "learning_rate": 6.222202300927577e-06, "loss": 0.1331, "step": 403130 }, { "epoch": 2.396347878809494, "grad_norm": 5.4004740715026855, "learning_rate": 6.222001102165998e-06, "loss": 0.1242, "step": 403140 }, { "epoch": 2.3964073208861625, "grad_norm": 3.499377965927124, "learning_rate": 6.2217999012999876e-06, "loss": 0.1384, "step": 403150 }, { "epoch": 2.396466762962831, "grad_norm": 4.002506256103516, "learning_rate": 6.22159869832989e-06, "loss": 0.143, "step": 403160 }, { "epoch": 2.3965262050394993, "grad_norm": 4.278353214263916, "learning_rate": 6.221397493256055e-06, "loss": 0.1406, "step": 403170 }, { "epoch": 2.3965856471161677, "grad_norm": 5.523642063140869, "learning_rate": 6.2211962860788275e-06, "loss": 0.1335, "step": 403180 }, { "epoch": 2.396645089192836, "grad_norm": 4.783105850219727, "learning_rate": 6.220995076798555e-06, "loss": 0.1462, "step": 403190 }, { "epoch": 2.3967045312695046, "grad_norm": 4.850639343261719, "learning_rate": 6.220793865415583e-06, "loss": 0.151, "step": 403200 }, { "epoch": 2.396763973346173, "grad_norm": 3.605222702026367, "learning_rate": 6.220592651930258e-06, "loss": 0.1575, "step": 403210 }, { "epoch": 2.3968234154228414, "grad_norm": 3.0492632389068604, "learning_rate": 6.220391436342926e-06, "loss": 0.1393, "step": 403220 }, { "epoch": 2.3968828574995094, "grad_norm": 4.470458030700684, "learning_rate": 6.220190218653937e-06, "loss": 0.159, "step": 403230 }, { "epoch": 2.396942299576178, "grad_norm": 5.305036544799805, "learning_rate": 6.219988998863631e-06, "loss": 0.1358, "step": 403240 }, { "epoch": 2.397001741652846, "grad_norm": 3.5858631134033203, "learning_rate": 6.2197877769723615e-06, "loss": 0.1366, "step": 403250 }, { "epoch": 2.3970611837295146, "grad_norm": 3.68251895904541, "learning_rate": 6.21958655298047e-06, "loss": 0.1353, "step": 403260 }, { "epoch": 2.397120625806183, "grad_norm": 3.8156700134277344, "learning_rate": 6.219385326888305e-06, "loss": 0.1485, "step": 403270 }, { "epoch": 2.3971800678828514, "grad_norm": 3.3851799964904785, "learning_rate": 6.219184098696215e-06, "loss": 0.1236, "step": 403280 }, { "epoch": 2.39723950995952, "grad_norm": 3.238703489303589, "learning_rate": 6.218982868404543e-06, "loss": 0.1512, "step": 403290 }, { "epoch": 2.3972989520361883, "grad_norm": 4.776743412017822, "learning_rate": 6.218781636013638e-06, "loss": 0.1405, "step": 403300 }, { "epoch": 2.3973583941128567, "grad_norm": 3.895066261291504, "learning_rate": 6.2185804015238446e-06, "loss": 0.1474, "step": 403310 }, { "epoch": 2.397417836189525, "grad_norm": 4.599390029907227, "learning_rate": 6.21837916493551e-06, "loss": 0.1491, "step": 403320 }, { "epoch": 2.3974772782661935, "grad_norm": 6.351352691650391, "learning_rate": 6.218177926248983e-06, "loss": 0.1536, "step": 403330 }, { "epoch": 2.397536720342862, "grad_norm": 4.224558353424072, "learning_rate": 6.2179766854646065e-06, "loss": 0.1244, "step": 403340 }, { "epoch": 2.3975961624195303, "grad_norm": 3.3889248371124268, "learning_rate": 6.217775442582728e-06, "loss": 0.1294, "step": 403350 }, { "epoch": 2.3976556044961987, "grad_norm": 3.4419257640838623, "learning_rate": 6.217574197603696e-06, "loss": 0.1391, "step": 403360 }, { "epoch": 2.397715046572867, "grad_norm": 4.007985591888428, "learning_rate": 6.217372950527857e-06, "loss": 0.1521, "step": 403370 }, { "epoch": 2.3977744886495356, "grad_norm": 3.44313383102417, "learning_rate": 6.217171701355556e-06, "loss": 0.1389, "step": 403380 }, { "epoch": 2.397833930726204, "grad_norm": 3.8384714126586914, "learning_rate": 6.2169704500871395e-06, "loss": 0.1462, "step": 403390 }, { "epoch": 2.3978933728028724, "grad_norm": 3.4481868743896484, "learning_rate": 6.2167691967229545e-06, "loss": 0.1338, "step": 403400 }, { "epoch": 2.397952814879541, "grad_norm": 4.981558322906494, "learning_rate": 6.216567941263348e-06, "loss": 0.1614, "step": 403410 }, { "epoch": 2.398012256956209, "grad_norm": 3.7656846046447754, "learning_rate": 6.216366683708667e-06, "loss": 0.1303, "step": 403420 }, { "epoch": 2.3980716990328776, "grad_norm": 5.97857141494751, "learning_rate": 6.216165424059257e-06, "loss": 0.1449, "step": 403430 }, { "epoch": 2.3981311411095456, "grad_norm": 4.075695991516113, "learning_rate": 6.215964162315467e-06, "loss": 0.1349, "step": 403440 }, { "epoch": 2.398190583186214, "grad_norm": 4.634350776672363, "learning_rate": 6.215762898477638e-06, "loss": 0.1564, "step": 403450 }, { "epoch": 2.3982500252628824, "grad_norm": 3.6377105712890625, "learning_rate": 6.215561632546121e-06, "loss": 0.1374, "step": 403460 }, { "epoch": 2.398309467339551, "grad_norm": 4.877893447875977, "learning_rate": 6.215360364521264e-06, "loss": 0.147, "step": 403470 }, { "epoch": 2.3983689094162193, "grad_norm": 4.385124683380127, "learning_rate": 6.215159094403409e-06, "loss": 0.1485, "step": 403480 }, { "epoch": 2.3984283514928877, "grad_norm": 5.000648498535156, "learning_rate": 6.214957822192906e-06, "loss": 0.1496, "step": 403490 }, { "epoch": 2.398487793569556, "grad_norm": 5.496695518493652, "learning_rate": 6.214756547890101e-06, "loss": 0.1288, "step": 403500 }, { "epoch": 2.3985472356462245, "grad_norm": 3.6307218074798584, "learning_rate": 6.2145552714953404e-06, "loss": 0.1641, "step": 403510 }, { "epoch": 2.398606677722893, "grad_norm": 8.670720100402832, "learning_rate": 6.214353993008971e-06, "loss": 0.1467, "step": 403520 }, { "epoch": 2.3986661197995613, "grad_norm": 4.288856506347656, "learning_rate": 6.214152712431338e-06, "loss": 0.153, "step": 403530 }, { "epoch": 2.3987255618762298, "grad_norm": 5.31270694732666, "learning_rate": 6.2139514297627905e-06, "loss": 0.139, "step": 403540 }, { "epoch": 2.398785003952898, "grad_norm": 3.6723225116729736, "learning_rate": 6.213750145003673e-06, "loss": 0.1276, "step": 403550 }, { "epoch": 2.3988444460295666, "grad_norm": 2.7098329067230225, "learning_rate": 6.2135488581543335e-06, "loss": 0.124, "step": 403560 }, { "epoch": 2.398903888106235, "grad_norm": 3.251897096633911, "learning_rate": 6.213347569215117e-06, "loss": 0.1529, "step": 403570 }, { "epoch": 2.3989633301829034, "grad_norm": 4.1778645515441895, "learning_rate": 6.21314627818637e-06, "loss": 0.1297, "step": 403580 }, { "epoch": 2.399022772259572, "grad_norm": 5.152188301086426, "learning_rate": 6.212944985068443e-06, "loss": 0.1619, "step": 403590 }, { "epoch": 2.3990822143362402, "grad_norm": 5.001978397369385, "learning_rate": 6.21274368986168e-06, "loss": 0.1446, "step": 403600 }, { "epoch": 2.399141656412908, "grad_norm": 5.01414680480957, "learning_rate": 6.212542392566426e-06, "loss": 0.1354, "step": 403610 }, { "epoch": 2.399201098489577, "grad_norm": 4.314084529876709, "learning_rate": 6.212341093183031e-06, "loss": 0.1334, "step": 403620 }, { "epoch": 2.399260540566245, "grad_norm": 3.791452407836914, "learning_rate": 6.212139791711838e-06, "loss": 0.1319, "step": 403630 }, { "epoch": 2.3993199826429135, "grad_norm": 5.995530128479004, "learning_rate": 6.211938488153197e-06, "loss": 0.1592, "step": 403640 }, { "epoch": 2.399379424719582, "grad_norm": 4.538671016693115, "learning_rate": 6.211737182507454e-06, "loss": 0.1583, "step": 403650 }, { "epoch": 2.3994388667962503, "grad_norm": 4.798233509063721, "learning_rate": 6.211535874774955e-06, "loss": 0.1273, "step": 403660 }, { "epoch": 2.3994983088729187, "grad_norm": 5.080207347869873, "learning_rate": 6.211334564956044e-06, "loss": 0.1396, "step": 403670 }, { "epoch": 2.399557750949587, "grad_norm": 5.110815525054932, "learning_rate": 6.211133253051072e-06, "loss": 0.154, "step": 403680 }, { "epoch": 2.3996171930262555, "grad_norm": 4.976311206817627, "learning_rate": 6.210931939060384e-06, "loss": 0.1542, "step": 403690 }, { "epoch": 2.399676635102924, "grad_norm": 3.5277066230773926, "learning_rate": 6.210730622984327e-06, "loss": 0.1452, "step": 403700 }, { "epoch": 2.3997360771795924, "grad_norm": 3.9044511318206787, "learning_rate": 6.210529304823247e-06, "loss": 0.1586, "step": 403710 }, { "epoch": 2.399795519256261, "grad_norm": 3.672424793243408, "learning_rate": 6.210327984577491e-06, "loss": 0.1297, "step": 403720 }, { "epoch": 2.399854961332929, "grad_norm": 4.215322494506836, "learning_rate": 6.210126662247407e-06, "loss": 0.1549, "step": 403730 }, { "epoch": 2.3999144034095976, "grad_norm": 4.9890923500061035, "learning_rate": 6.209925337833339e-06, "loss": 0.1433, "step": 403740 }, { "epoch": 2.399973845486266, "grad_norm": 3.771819591522217, "learning_rate": 6.209724011335636e-06, "loss": 0.1181, "step": 403750 }, { "epoch": 2.4000332875629344, "grad_norm": 6.0813469886779785, "learning_rate": 6.209522682754644e-06, "loss": 0.1496, "step": 403760 }, { "epoch": 2.400092729639603, "grad_norm": 4.748462200164795, "learning_rate": 6.209321352090709e-06, "loss": 0.1359, "step": 403770 }, { "epoch": 2.4001521717162713, "grad_norm": 3.6792259216308594, "learning_rate": 6.209120019344179e-06, "loss": 0.1298, "step": 403780 }, { "epoch": 2.4002116137929397, "grad_norm": 2.8423848152160645, "learning_rate": 6.2089186845154e-06, "loss": 0.1334, "step": 403790 }, { "epoch": 2.4002710558696077, "grad_norm": 4.312655448913574, "learning_rate": 6.208717347604718e-06, "loss": 0.1337, "step": 403800 }, { "epoch": 2.400330497946276, "grad_norm": 5.239438533782959, "learning_rate": 6.208516008612481e-06, "loss": 0.1506, "step": 403810 }, { "epoch": 2.4003899400229445, "grad_norm": 2.858882427215576, "learning_rate": 6.208314667539035e-06, "loss": 0.13, "step": 403820 }, { "epoch": 2.400449382099613, "grad_norm": 3.963132858276367, "learning_rate": 6.208113324384728e-06, "loss": 0.1395, "step": 403830 }, { "epoch": 2.4005088241762813, "grad_norm": 3.4479808807373047, "learning_rate": 6.207911979149904e-06, "loss": 0.1361, "step": 403840 }, { "epoch": 2.4005682662529497, "grad_norm": 4.893983364105225, "learning_rate": 6.207710631834914e-06, "loss": 0.1459, "step": 403850 }, { "epoch": 2.400627708329618, "grad_norm": 4.645545959472656, "learning_rate": 6.2075092824400995e-06, "loss": 0.1399, "step": 403860 }, { "epoch": 2.4006871504062866, "grad_norm": 4.096323013305664, "learning_rate": 6.20730793096581e-06, "loss": 0.1457, "step": 403870 }, { "epoch": 2.400746592482955, "grad_norm": 4.731010437011719, "learning_rate": 6.207106577412394e-06, "loss": 0.147, "step": 403880 }, { "epoch": 2.4008060345596234, "grad_norm": 4.902769565582275, "learning_rate": 6.206905221780196e-06, "loss": 0.1575, "step": 403890 }, { "epoch": 2.400865476636292, "grad_norm": 3.6357109546661377, "learning_rate": 6.206703864069562e-06, "loss": 0.1294, "step": 403900 }, { "epoch": 2.40092491871296, "grad_norm": 3.134514331817627, "learning_rate": 6.20650250428084e-06, "loss": 0.1451, "step": 403910 }, { "epoch": 2.4009843607896286, "grad_norm": 3.540768623352051, "learning_rate": 6.206301142414378e-06, "loss": 0.1384, "step": 403920 }, { "epoch": 2.401043802866297, "grad_norm": 2.7569267749786377, "learning_rate": 6.206099778470522e-06, "loss": 0.1419, "step": 403930 }, { "epoch": 2.4011032449429655, "grad_norm": 3.994323253631592, "learning_rate": 6.205898412449617e-06, "loss": 0.1371, "step": 403940 }, { "epoch": 2.401162687019634, "grad_norm": 4.372976779937744, "learning_rate": 6.205697044352011e-06, "loss": 0.1274, "step": 403950 }, { "epoch": 2.4012221290963023, "grad_norm": 3.9233531951904297, "learning_rate": 6.205495674178053e-06, "loss": 0.1397, "step": 403960 }, { "epoch": 2.4012815711729703, "grad_norm": 3.3977177143096924, "learning_rate": 6.205294301928084e-06, "loss": 0.1385, "step": 403970 }, { "epoch": 2.401341013249639, "grad_norm": 4.2638044357299805, "learning_rate": 6.205092927602456e-06, "loss": 0.1542, "step": 403980 }, { "epoch": 2.401400455326307, "grad_norm": 4.253659725189209, "learning_rate": 6.204891551201515e-06, "loss": 0.1506, "step": 403990 }, { "epoch": 2.4014598974029755, "grad_norm": 3.529076099395752, "learning_rate": 6.204690172725606e-06, "loss": 0.1402, "step": 404000 }, { "epoch": 2.401519339479644, "grad_norm": 4.734960556030273, "learning_rate": 6.204488792175076e-06, "loss": 0.1352, "step": 404010 }, { "epoch": 2.4015787815563123, "grad_norm": 3.9706292152404785, "learning_rate": 6.2042874095502745e-06, "loss": 0.151, "step": 404020 }, { "epoch": 2.4016382236329807, "grad_norm": 8.796929359436035, "learning_rate": 6.204086024851546e-06, "loss": 0.1225, "step": 404030 }, { "epoch": 2.401697665709649, "grad_norm": 4.041538238525391, "learning_rate": 6.203884638079237e-06, "loss": 0.1432, "step": 404040 }, { "epoch": 2.4017571077863176, "grad_norm": 4.432399272918701, "learning_rate": 6.2036832492336965e-06, "loss": 0.1308, "step": 404050 }, { "epoch": 2.401816549862986, "grad_norm": 4.431614398956299, "learning_rate": 6.2034818583152665e-06, "loss": 0.1252, "step": 404060 }, { "epoch": 2.4018759919396544, "grad_norm": 4.660822868347168, "learning_rate": 6.2032804653243e-06, "loss": 0.1406, "step": 404070 }, { "epoch": 2.401935434016323, "grad_norm": 4.284499645233154, "learning_rate": 6.203079070261141e-06, "loss": 0.1462, "step": 404080 }, { "epoch": 2.4019948760929912, "grad_norm": 4.326613426208496, "learning_rate": 6.202877673126135e-06, "loss": 0.1352, "step": 404090 }, { "epoch": 2.4020543181696596, "grad_norm": 3.836866855621338, "learning_rate": 6.202676273919631e-06, "loss": 0.1359, "step": 404100 }, { "epoch": 2.402113760246328, "grad_norm": 5.02409553527832, "learning_rate": 6.2024748726419746e-06, "loss": 0.1407, "step": 404110 }, { "epoch": 2.4021732023229965, "grad_norm": 4.6423845291137695, "learning_rate": 6.202273469293513e-06, "loss": 0.1451, "step": 404120 }, { "epoch": 2.402232644399665, "grad_norm": 4.314769268035889, "learning_rate": 6.202072063874592e-06, "loss": 0.1546, "step": 404130 }, { "epoch": 2.4022920864763333, "grad_norm": 4.3303446769714355, "learning_rate": 6.201870656385561e-06, "loss": 0.1468, "step": 404140 }, { "epoch": 2.4023515285530017, "grad_norm": 3.806825876235962, "learning_rate": 6.201669246826766e-06, "loss": 0.1363, "step": 404150 }, { "epoch": 2.4024109706296697, "grad_norm": 4.302572250366211, "learning_rate": 6.2014678351985514e-06, "loss": 0.1584, "step": 404160 }, { "epoch": 2.4024704127063385, "grad_norm": 4.428564071655273, "learning_rate": 6.201266421501266e-06, "loss": 0.1309, "step": 404170 }, { "epoch": 2.4025298547830065, "grad_norm": 3.113344430923462, "learning_rate": 6.2010650057352574e-06, "loss": 0.1337, "step": 404180 }, { "epoch": 2.402589296859675, "grad_norm": 4.553193092346191, "learning_rate": 6.200863587900871e-06, "loss": 0.1306, "step": 404190 }, { "epoch": 2.4026487389363433, "grad_norm": 5.867978096008301, "learning_rate": 6.200662167998455e-06, "loss": 0.14, "step": 404200 }, { "epoch": 2.4027081810130118, "grad_norm": 3.626803159713745, "learning_rate": 6.200460746028354e-06, "loss": 0.1405, "step": 404210 }, { "epoch": 2.40276762308968, "grad_norm": 4.861451625823975, "learning_rate": 6.200259321990917e-06, "loss": 0.1501, "step": 404220 }, { "epoch": 2.4028270651663486, "grad_norm": 5.438920974731445, "learning_rate": 6.20005789588649e-06, "loss": 0.1476, "step": 404230 }, { "epoch": 2.402886507243017, "grad_norm": 3.663109302520752, "learning_rate": 6.19985646771542e-06, "loss": 0.1528, "step": 404240 }, { "epoch": 2.4029459493196854, "grad_norm": 4.052759647369385, "learning_rate": 6.1996550374780565e-06, "loss": 0.1377, "step": 404250 }, { "epoch": 2.403005391396354, "grad_norm": 4.255884170532227, "learning_rate": 6.19945360517474e-06, "loss": 0.1472, "step": 404260 }, { "epoch": 2.4030648334730222, "grad_norm": 5.261415481567383, "learning_rate": 6.199252170805824e-06, "loss": 0.1818, "step": 404270 }, { "epoch": 2.4031242755496907, "grad_norm": 4.605124473571777, "learning_rate": 6.1990507343716525e-06, "loss": 0.1294, "step": 404280 }, { "epoch": 2.403183717626359, "grad_norm": 4.46469259262085, "learning_rate": 6.198849295872571e-06, "loss": 0.1412, "step": 404290 }, { "epoch": 2.4032431597030275, "grad_norm": 5.100132942199707, "learning_rate": 6.198647855308929e-06, "loss": 0.1393, "step": 404300 }, { "epoch": 2.403302601779696, "grad_norm": 4.089718818664551, "learning_rate": 6.198446412681073e-06, "loss": 0.1411, "step": 404310 }, { "epoch": 2.4033620438563643, "grad_norm": 3.6142385005950928, "learning_rate": 6.198244967989348e-06, "loss": 0.1458, "step": 404320 }, { "epoch": 2.4034214859330327, "grad_norm": 4.509916305541992, "learning_rate": 6.1980435212341025e-06, "loss": 0.1474, "step": 404330 }, { "epoch": 2.403480928009701, "grad_norm": 4.295522689819336, "learning_rate": 6.197842072415683e-06, "loss": 0.1248, "step": 404340 }, { "epoch": 2.403540370086369, "grad_norm": 4.701798915863037, "learning_rate": 6.197640621534438e-06, "loss": 0.1318, "step": 404350 }, { "epoch": 2.403599812163038, "grad_norm": 3.910461664199829, "learning_rate": 6.1974391685907106e-06, "loss": 0.1307, "step": 404360 }, { "epoch": 2.403659254239706, "grad_norm": 3.7597880363464355, "learning_rate": 6.197237713584851e-06, "loss": 0.1515, "step": 404370 }, { "epoch": 2.4037186963163744, "grad_norm": 5.448108196258545, "learning_rate": 6.197036256517206e-06, "loss": 0.1514, "step": 404380 }, { "epoch": 2.4037781383930428, "grad_norm": 5.061917781829834, "learning_rate": 6.19683479738812e-06, "loss": 0.1512, "step": 404390 }, { "epoch": 2.403837580469711, "grad_norm": 3.069334030151367, "learning_rate": 6.196633336197944e-06, "loss": 0.1309, "step": 404400 }, { "epoch": 2.4038970225463796, "grad_norm": 5.192957401275635, "learning_rate": 6.196431872947022e-06, "loss": 0.1377, "step": 404410 }, { "epoch": 2.403956464623048, "grad_norm": 4.043649673461914, "learning_rate": 6.196230407635701e-06, "loss": 0.1473, "step": 404420 }, { "epoch": 2.4040159066997164, "grad_norm": 4.965560436248779, "learning_rate": 6.1960289402643285e-06, "loss": 0.1523, "step": 404430 }, { "epoch": 2.404075348776385, "grad_norm": 5.873175621032715, "learning_rate": 6.1958274708332525e-06, "loss": 0.1509, "step": 404440 }, { "epoch": 2.4041347908530533, "grad_norm": 5.63657808303833, "learning_rate": 6.195625999342817e-06, "loss": 0.1402, "step": 404450 }, { "epoch": 2.4041942329297217, "grad_norm": 3.7793359756469727, "learning_rate": 6.195424525793371e-06, "loss": 0.1509, "step": 404460 }, { "epoch": 2.40425367500639, "grad_norm": 4.317448139190674, "learning_rate": 6.195223050185263e-06, "loss": 0.1561, "step": 404470 }, { "epoch": 2.4043131170830585, "grad_norm": 3.4963996410369873, "learning_rate": 6.195021572518838e-06, "loss": 0.1378, "step": 404480 }, { "epoch": 2.404372559159727, "grad_norm": 3.993905782699585, "learning_rate": 6.1948200927944415e-06, "loss": 0.14, "step": 404490 }, { "epoch": 2.4044320012363953, "grad_norm": 4.439340114593506, "learning_rate": 6.194618611012424e-06, "loss": 0.1602, "step": 404500 }, { "epoch": 2.4044914433130637, "grad_norm": 4.457611560821533, "learning_rate": 6.1944171271731305e-06, "loss": 0.1377, "step": 404510 }, { "epoch": 2.404550885389732, "grad_norm": 4.686793804168701, "learning_rate": 6.194215641276907e-06, "loss": 0.139, "step": 404520 }, { "epoch": 2.4046103274664006, "grad_norm": 4.077563285827637, "learning_rate": 6.194014153324103e-06, "loss": 0.1311, "step": 404530 }, { "epoch": 2.4046697695430685, "grad_norm": 5.013446807861328, "learning_rate": 6.193812663315064e-06, "loss": 0.1368, "step": 404540 }, { "epoch": 2.404729211619737, "grad_norm": 3.4068305492401123, "learning_rate": 6.193611171250136e-06, "loss": 0.1542, "step": 404550 }, { "epoch": 2.4047886536964054, "grad_norm": 3.485585927963257, "learning_rate": 6.193409677129667e-06, "loss": 0.131, "step": 404560 }, { "epoch": 2.404848095773074, "grad_norm": 5.520840644836426, "learning_rate": 6.1932081809540055e-06, "loss": 0.1484, "step": 404570 }, { "epoch": 2.404907537849742, "grad_norm": 3.8148932456970215, "learning_rate": 6.193006682723498e-06, "loss": 0.138, "step": 404580 }, { "epoch": 2.4049669799264106, "grad_norm": 3.7626099586486816, "learning_rate": 6.192805182438488e-06, "loss": 0.1438, "step": 404590 }, { "epoch": 2.405026422003079, "grad_norm": 3.6140334606170654, "learning_rate": 6.192603680099327e-06, "loss": 0.1326, "step": 404600 }, { "epoch": 2.4050858640797474, "grad_norm": 4.989171504974365, "learning_rate": 6.19240217570636e-06, "loss": 0.1519, "step": 404610 }, { "epoch": 2.405145306156416, "grad_norm": 5.146225929260254, "learning_rate": 6.192200669259934e-06, "loss": 0.1356, "step": 404620 }, { "epoch": 2.4052047482330843, "grad_norm": 5.7630438804626465, "learning_rate": 6.1919991607603955e-06, "loss": 0.1455, "step": 404630 }, { "epoch": 2.4052641903097527, "grad_norm": 3.148128032684326, "learning_rate": 6.1917976502080934e-06, "loss": 0.154, "step": 404640 }, { "epoch": 2.405323632386421, "grad_norm": 4.017633438110352, "learning_rate": 6.191596137603373e-06, "loss": 0.1205, "step": 404650 }, { "epoch": 2.4053830744630895, "grad_norm": 7.222095489501953, "learning_rate": 6.191394622946583e-06, "loss": 0.1465, "step": 404660 }, { "epoch": 2.405442516539758, "grad_norm": 5.105534076690674, "learning_rate": 6.191193106238067e-06, "loss": 0.1467, "step": 404670 }, { "epoch": 2.4055019586164264, "grad_norm": 3.240065574645996, "learning_rate": 6.190991587478174e-06, "loss": 0.1137, "step": 404680 }, { "epoch": 2.4055614006930948, "grad_norm": 4.356180191040039, "learning_rate": 6.190790066667254e-06, "loss": 0.1517, "step": 404690 }, { "epoch": 2.405620842769763, "grad_norm": 4.615537643432617, "learning_rate": 6.1905885438056504e-06, "loss": 0.1483, "step": 404700 }, { "epoch": 2.405680284846431, "grad_norm": 4.939194202423096, "learning_rate": 6.190387018893711e-06, "loss": 0.1561, "step": 404710 }, { "epoch": 2.4057397269231, "grad_norm": 5.482823848724365, "learning_rate": 6.1901854919317824e-06, "loss": 0.1554, "step": 404720 }, { "epoch": 2.405799168999768, "grad_norm": 4.756413459777832, "learning_rate": 6.189983962920214e-06, "loss": 0.1429, "step": 404730 }, { "epoch": 2.4058586110764364, "grad_norm": 3.367685317993164, "learning_rate": 6.18978243185935e-06, "loss": 0.1446, "step": 404740 }, { "epoch": 2.405918053153105, "grad_norm": 4.098280906677246, "learning_rate": 6.189580898749539e-06, "loss": 0.1582, "step": 404750 }, { "epoch": 2.405977495229773, "grad_norm": 4.528502941131592, "learning_rate": 6.189379363591129e-06, "loss": 0.1321, "step": 404760 }, { "epoch": 2.4060369373064416, "grad_norm": 4.53788423538208, "learning_rate": 6.189177826384465e-06, "loss": 0.1245, "step": 404770 }, { "epoch": 2.40609637938311, "grad_norm": 5.09696102142334, "learning_rate": 6.188976287129893e-06, "loss": 0.1524, "step": 404780 }, { "epoch": 2.4061558214597785, "grad_norm": 4.49420166015625, "learning_rate": 6.188774745827764e-06, "loss": 0.1463, "step": 404790 }, { "epoch": 2.406215263536447, "grad_norm": 4.830520153045654, "learning_rate": 6.188573202478423e-06, "loss": 0.171, "step": 404800 }, { "epoch": 2.4062747056131153, "grad_norm": 3.356950521469116, "learning_rate": 6.188371657082216e-06, "loss": 0.1303, "step": 404810 }, { "epoch": 2.4063341476897837, "grad_norm": 4.356922626495361, "learning_rate": 6.188170109639493e-06, "loss": 0.1249, "step": 404820 }, { "epoch": 2.406393589766452, "grad_norm": 3.1731715202331543, "learning_rate": 6.1879685601505976e-06, "loss": 0.1466, "step": 404830 }, { "epoch": 2.4064530318431205, "grad_norm": 3.8871309757232666, "learning_rate": 6.187767008615879e-06, "loss": 0.1541, "step": 404840 }, { "epoch": 2.406512473919789, "grad_norm": 5.4651923179626465, "learning_rate": 6.187565455035684e-06, "loss": 0.1474, "step": 404850 }, { "epoch": 2.4065719159964574, "grad_norm": 4.812360763549805, "learning_rate": 6.187363899410361e-06, "loss": 0.141, "step": 404860 }, { "epoch": 2.406631358073126, "grad_norm": 6.249885082244873, "learning_rate": 6.187162341740254e-06, "loss": 0.1516, "step": 404870 }, { "epoch": 2.406690800149794, "grad_norm": 2.958770751953125, "learning_rate": 6.186960782025713e-06, "loss": 0.1443, "step": 404880 }, { "epoch": 2.4067502422264626, "grad_norm": 4.377240180969238, "learning_rate": 6.186759220267083e-06, "loss": 0.1464, "step": 404890 }, { "epoch": 2.4068096843031306, "grad_norm": 3.5761985778808594, "learning_rate": 6.186557656464711e-06, "loss": 0.1378, "step": 404900 }, { "epoch": 2.4068691263797994, "grad_norm": 5.362423419952393, "learning_rate": 6.186356090618946e-06, "loss": 0.1364, "step": 404910 }, { "epoch": 2.4069285684564674, "grad_norm": 3.320446729660034, "learning_rate": 6.186154522730134e-06, "loss": 0.1388, "step": 404920 }, { "epoch": 2.406988010533136, "grad_norm": 4.888016700744629, "learning_rate": 6.185952952798624e-06, "loss": 0.1389, "step": 404930 }, { "epoch": 2.4070474526098042, "grad_norm": 4.067469120025635, "learning_rate": 6.185751380824761e-06, "loss": 0.1535, "step": 404940 }, { "epoch": 2.4071068946864727, "grad_norm": 5.121987342834473, "learning_rate": 6.185549806808892e-06, "loss": 0.1507, "step": 404950 }, { "epoch": 2.407166336763141, "grad_norm": 3.891326665878296, "learning_rate": 6.1853482307513645e-06, "loss": 0.1485, "step": 404960 }, { "epoch": 2.4072257788398095, "grad_norm": 3.7420969009399414, "learning_rate": 6.185146652652526e-06, "loss": 0.1366, "step": 404970 }, { "epoch": 2.407285220916478, "grad_norm": 4.338064670562744, "learning_rate": 6.184945072512725e-06, "loss": 0.1533, "step": 404980 }, { "epoch": 2.4073446629931463, "grad_norm": 4.6292829513549805, "learning_rate": 6.184743490332306e-06, "loss": 0.1324, "step": 404990 }, { "epoch": 2.4074041050698147, "grad_norm": 3.235927104949951, "learning_rate": 6.184541906111616e-06, "loss": 0.1399, "step": 405000 }, { "epoch": 2.407463547146483, "grad_norm": 4.6130051612854, "learning_rate": 6.184340319851004e-06, "loss": 0.1488, "step": 405010 }, { "epoch": 2.4075229892231516, "grad_norm": 4.957174301147461, "learning_rate": 6.1841387315508185e-06, "loss": 0.1516, "step": 405020 }, { "epoch": 2.40758243129982, "grad_norm": 4.303981304168701, "learning_rate": 6.183937141211404e-06, "loss": 0.127, "step": 405030 }, { "epoch": 2.4076418733764884, "grad_norm": 3.4176528453826904, "learning_rate": 6.183735548833107e-06, "loss": 0.1263, "step": 405040 }, { "epoch": 2.407701315453157, "grad_norm": 3.9561917781829834, "learning_rate": 6.183533954416279e-06, "loss": 0.1368, "step": 405050 }, { "epoch": 2.407760757529825, "grad_norm": 3.643664598464966, "learning_rate": 6.183332357961262e-06, "loss": 0.1481, "step": 405060 }, { "epoch": 2.4078201996064936, "grad_norm": 4.338588714599609, "learning_rate": 6.183130759468406e-06, "loss": 0.1457, "step": 405070 }, { "epoch": 2.407879641683162, "grad_norm": 5.433656215667725, "learning_rate": 6.182929158938059e-06, "loss": 0.1268, "step": 405080 }, { "epoch": 2.40793908375983, "grad_norm": 4.710480690002441, "learning_rate": 6.182727556370566e-06, "loss": 0.1289, "step": 405090 }, { "epoch": 2.407998525836499, "grad_norm": 5.342341899871826, "learning_rate": 6.182525951766274e-06, "loss": 0.1546, "step": 405100 }, { "epoch": 2.408057967913167, "grad_norm": 3.9471077919006348, "learning_rate": 6.182324345125532e-06, "loss": 0.1711, "step": 405110 }, { "epoch": 2.4081174099898353, "grad_norm": 3.7501471042633057, "learning_rate": 6.182122736448687e-06, "loss": 0.1638, "step": 405120 }, { "epoch": 2.4081768520665037, "grad_norm": 3.9702188968658447, "learning_rate": 6.1819211257360855e-06, "loss": 0.139, "step": 405130 }, { "epoch": 2.408236294143172, "grad_norm": 4.559635639190674, "learning_rate": 6.181719512988073e-06, "loss": 0.1491, "step": 405140 }, { "epoch": 2.4082957362198405, "grad_norm": 4.361351490020752, "learning_rate": 6.181517898205001e-06, "loss": 0.1378, "step": 405150 }, { "epoch": 2.408355178296509, "grad_norm": 4.343601703643799, "learning_rate": 6.181316281387213e-06, "loss": 0.128, "step": 405160 }, { "epoch": 2.4084146203731773, "grad_norm": 4.158446788787842, "learning_rate": 6.181114662535057e-06, "loss": 0.1421, "step": 405170 }, { "epoch": 2.4084740624498457, "grad_norm": 3.8162641525268555, "learning_rate": 6.180913041648882e-06, "loss": 0.1379, "step": 405180 }, { "epoch": 2.408533504526514, "grad_norm": 3.19506573677063, "learning_rate": 6.180711418729033e-06, "loss": 0.1315, "step": 405190 }, { "epoch": 2.4085929466031826, "grad_norm": 5.199158668518066, "learning_rate": 6.1805097937758566e-06, "loss": 0.1366, "step": 405200 }, { "epoch": 2.408652388679851, "grad_norm": 5.1318864822387695, "learning_rate": 6.180308166789703e-06, "loss": 0.1455, "step": 405210 }, { "epoch": 2.4087118307565194, "grad_norm": 3.1656084060668945, "learning_rate": 6.180106537770918e-06, "loss": 0.1326, "step": 405220 }, { "epoch": 2.408771272833188, "grad_norm": 4.051716327667236, "learning_rate": 6.179904906719848e-06, "loss": 0.1398, "step": 405230 }, { "epoch": 2.4088307149098562, "grad_norm": 3.5616729259490967, "learning_rate": 6.1797032736368415e-06, "loss": 0.1353, "step": 405240 }, { "epoch": 2.4088901569865246, "grad_norm": 4.0865278244018555, "learning_rate": 6.179501638522245e-06, "loss": 0.1453, "step": 405250 }, { "epoch": 2.408949599063193, "grad_norm": 4.262080192565918, "learning_rate": 6.179300001376407e-06, "loss": 0.1344, "step": 405260 }, { "epoch": 2.4090090411398615, "grad_norm": 3.804643392562866, "learning_rate": 6.1790983621996715e-06, "loss": 0.1206, "step": 405270 }, { "epoch": 2.4090684832165294, "grad_norm": 4.719682693481445, "learning_rate": 6.17889672099239e-06, "loss": 0.1327, "step": 405280 }, { "epoch": 2.409127925293198, "grad_norm": 3.1951041221618652, "learning_rate": 6.178695077754907e-06, "loss": 0.1659, "step": 405290 }, { "epoch": 2.4091873673698663, "grad_norm": 6.982308864593506, "learning_rate": 6.17849343248757e-06, "loss": 0.1374, "step": 405300 }, { "epoch": 2.4092468094465347, "grad_norm": 4.233948707580566, "learning_rate": 6.178291785190727e-06, "loss": 0.1267, "step": 405310 }, { "epoch": 2.409306251523203, "grad_norm": 2.9009759426116943, "learning_rate": 6.178090135864726e-06, "loss": 0.1255, "step": 405320 }, { "epoch": 2.4093656935998715, "grad_norm": 4.878723621368408, "learning_rate": 6.1778884845099095e-06, "loss": 0.1398, "step": 405330 }, { "epoch": 2.40942513567654, "grad_norm": 4.821569442749023, "learning_rate": 6.177686831126633e-06, "loss": 0.1425, "step": 405340 }, { "epoch": 2.4094845777532083, "grad_norm": 3.98441743850708, "learning_rate": 6.177485175715236e-06, "loss": 0.1358, "step": 405350 }, { "epoch": 2.4095440198298768, "grad_norm": 4.895867347717285, "learning_rate": 6.177283518276071e-06, "loss": 0.1141, "step": 405360 }, { "epoch": 2.409603461906545, "grad_norm": 3.9721591472625732, "learning_rate": 6.177081858809483e-06, "loss": 0.1604, "step": 405370 }, { "epoch": 2.4096629039832136, "grad_norm": 4.3583831787109375, "learning_rate": 6.17688019731582e-06, "loss": 0.1232, "step": 405380 }, { "epoch": 2.409722346059882, "grad_norm": 4.168235778808594, "learning_rate": 6.176678533795427e-06, "loss": 0.1469, "step": 405390 }, { "epoch": 2.4097817881365504, "grad_norm": 6.407131671905518, "learning_rate": 6.1764768682486554e-06, "loss": 0.1573, "step": 405400 }, { "epoch": 2.409841230213219, "grad_norm": 4.978967189788818, "learning_rate": 6.17627520067585e-06, "loss": 0.1562, "step": 405410 }, { "epoch": 2.4099006722898872, "grad_norm": 4.507656097412109, "learning_rate": 6.176073531077357e-06, "loss": 0.1496, "step": 405420 }, { "epoch": 2.4099601143665557, "grad_norm": 5.842875003814697, "learning_rate": 6.175871859453525e-06, "loss": 0.1502, "step": 405430 }, { "epoch": 2.410019556443224, "grad_norm": 5.221763610839844, "learning_rate": 6.175670185804702e-06, "loss": 0.1372, "step": 405440 }, { "epoch": 2.410078998519892, "grad_norm": 4.748298645019531, "learning_rate": 6.175468510131235e-06, "loss": 0.1521, "step": 405450 }, { "epoch": 2.410138440596561, "grad_norm": 2.954332113265991, "learning_rate": 6.17526683243347e-06, "loss": 0.1425, "step": 405460 }, { "epoch": 2.410197882673229, "grad_norm": 3.9684224128723145, "learning_rate": 6.175065152711757e-06, "loss": 0.1427, "step": 405470 }, { "epoch": 2.4102573247498973, "grad_norm": 5.169844627380371, "learning_rate": 6.17486347096644e-06, "loss": 0.1434, "step": 405480 }, { "epoch": 2.4103167668265657, "grad_norm": 3.700654983520508, "learning_rate": 6.174661787197868e-06, "loss": 0.147, "step": 405490 }, { "epoch": 2.410376208903234, "grad_norm": 4.294189453125, "learning_rate": 6.1744601014063885e-06, "loss": 0.1347, "step": 405500 }, { "epoch": 2.4104356509799025, "grad_norm": 5.277390003204346, "learning_rate": 6.17425841359235e-06, "loss": 0.1513, "step": 405510 }, { "epoch": 2.410495093056571, "grad_norm": 3.4424710273742676, "learning_rate": 6.174056723756097e-06, "loss": 0.1358, "step": 405520 }, { "epoch": 2.4105545351332394, "grad_norm": 4.671746730804443, "learning_rate": 6.173855031897978e-06, "loss": 0.1416, "step": 405530 }, { "epoch": 2.4106139772099078, "grad_norm": 3.4895553588867188, "learning_rate": 6.1736533380183414e-06, "loss": 0.1285, "step": 405540 }, { "epoch": 2.410673419286576, "grad_norm": 5.796676158905029, "learning_rate": 6.1734516421175326e-06, "loss": 0.152, "step": 405550 }, { "epoch": 2.4107328613632446, "grad_norm": 3.21458101272583, "learning_rate": 6.1732499441959005e-06, "loss": 0.1339, "step": 405560 }, { "epoch": 2.410792303439913, "grad_norm": 3.2416675090789795, "learning_rate": 6.173048244253792e-06, "loss": 0.1291, "step": 405570 }, { "epoch": 2.4108517455165814, "grad_norm": 5.079028606414795, "learning_rate": 6.172846542291555e-06, "loss": 0.1488, "step": 405580 }, { "epoch": 2.41091118759325, "grad_norm": 4.767707347869873, "learning_rate": 6.172644838309536e-06, "loss": 0.1446, "step": 405590 }, { "epoch": 2.4109706296699183, "grad_norm": 4.678844928741455, "learning_rate": 6.172443132308083e-06, "loss": 0.147, "step": 405600 }, { "epoch": 2.4110300717465867, "grad_norm": 3.8557517528533936, "learning_rate": 6.172241424287544e-06, "loss": 0.1408, "step": 405610 }, { "epoch": 2.411089513823255, "grad_norm": 4.145968437194824, "learning_rate": 6.172039714248262e-06, "loss": 0.1405, "step": 405620 }, { "epoch": 2.4111489558999235, "grad_norm": 5.4745259284973145, "learning_rate": 6.171838002190591e-06, "loss": 0.1561, "step": 405630 }, { "epoch": 2.4112083979765915, "grad_norm": 3.034555673599243, "learning_rate": 6.171636288114875e-06, "loss": 0.1436, "step": 405640 }, { "epoch": 2.4112678400532603, "grad_norm": 3.618492841720581, "learning_rate": 6.17143457202146e-06, "loss": 0.1274, "step": 405650 }, { "epoch": 2.4113272821299283, "grad_norm": 4.376520156860352, "learning_rate": 6.171232853910695e-06, "loss": 0.1469, "step": 405660 }, { "epoch": 2.4113867242065967, "grad_norm": 3.079967498779297, "learning_rate": 6.171031133782928e-06, "loss": 0.1168, "step": 405670 }, { "epoch": 2.411446166283265, "grad_norm": 3.6692237854003906, "learning_rate": 6.170829411638505e-06, "loss": 0.1171, "step": 405680 }, { "epoch": 2.4115056083599336, "grad_norm": 5.122002601623535, "learning_rate": 6.170627687477774e-06, "loss": 0.1468, "step": 405690 }, { "epoch": 2.411565050436602, "grad_norm": 3.923516035079956, "learning_rate": 6.170425961301083e-06, "loss": 0.1572, "step": 405700 }, { "epoch": 2.4116244925132704, "grad_norm": 5.4402360916137695, "learning_rate": 6.170224233108779e-06, "loss": 0.1432, "step": 405710 }, { "epoch": 2.411683934589939, "grad_norm": 3.2053897380828857, "learning_rate": 6.170022502901208e-06, "loss": 0.1333, "step": 405720 }, { "epoch": 2.411743376666607, "grad_norm": 5.0035014152526855, "learning_rate": 6.16982077067872e-06, "loss": 0.1438, "step": 405730 }, { "epoch": 2.4118028187432756, "grad_norm": 5.231418609619141, "learning_rate": 6.169619036441662e-06, "loss": 0.1461, "step": 405740 }, { "epoch": 2.411862260819944, "grad_norm": 4.6237568855285645, "learning_rate": 6.169417300190378e-06, "loss": 0.152, "step": 405750 }, { "epoch": 2.4119217028966125, "grad_norm": 4.365865707397461, "learning_rate": 6.169215561925219e-06, "loss": 0.1438, "step": 405760 }, { "epoch": 2.411981144973281, "grad_norm": 4.343985080718994, "learning_rate": 6.1690138216465316e-06, "loss": 0.155, "step": 405770 }, { "epoch": 2.4120405870499493, "grad_norm": 4.58917760848999, "learning_rate": 6.1688120793546624e-06, "loss": 0.1603, "step": 405780 }, { "epoch": 2.4121000291266177, "grad_norm": 4.817151069641113, "learning_rate": 6.168610335049959e-06, "loss": 0.1449, "step": 405790 }, { "epoch": 2.412159471203286, "grad_norm": 3.910451650619507, "learning_rate": 6.16840858873277e-06, "loss": 0.1309, "step": 405800 }, { "epoch": 2.4122189132799545, "grad_norm": 3.4050254821777344, "learning_rate": 6.1682068404034425e-06, "loss": 0.14, "step": 405810 }, { "epoch": 2.412278355356623, "grad_norm": 4.7396240234375, "learning_rate": 6.168005090062323e-06, "loss": 0.1341, "step": 405820 }, { "epoch": 2.412337797433291, "grad_norm": 3.544353723526001, "learning_rate": 6.167803337709759e-06, "loss": 0.154, "step": 405830 }, { "epoch": 2.4123972395099598, "grad_norm": 4.60093355178833, "learning_rate": 6.167601583346098e-06, "loss": 0.1632, "step": 405840 }, { "epoch": 2.4124566815866277, "grad_norm": 4.4573750495910645, "learning_rate": 6.167399826971687e-06, "loss": 0.1316, "step": 405850 }, { "epoch": 2.412516123663296, "grad_norm": 5.322955131530762, "learning_rate": 6.167198068586876e-06, "loss": 0.1416, "step": 405860 }, { "epoch": 2.4125755657399646, "grad_norm": 5.388393878936768, "learning_rate": 6.166996308192011e-06, "loss": 0.1392, "step": 405870 }, { "epoch": 2.412635007816633, "grad_norm": 3.779660224914551, "learning_rate": 6.166794545787436e-06, "loss": 0.1463, "step": 405880 }, { "epoch": 2.4126944498933014, "grad_norm": 5.071245193481445, "learning_rate": 6.166592781373504e-06, "loss": 0.154, "step": 405890 }, { "epoch": 2.41275389196997, "grad_norm": 5.480534553527832, "learning_rate": 6.1663910149505605e-06, "loss": 0.1464, "step": 405900 }, { "epoch": 2.4128133340466382, "grad_norm": 4.446824550628662, "learning_rate": 6.166189246518952e-06, "loss": 0.1446, "step": 405910 }, { "epoch": 2.4128727761233066, "grad_norm": 3.9756789207458496, "learning_rate": 6.1659874760790254e-06, "loss": 0.1335, "step": 405920 }, { "epoch": 2.412932218199975, "grad_norm": 3.803115129470825, "learning_rate": 6.165785703631131e-06, "loss": 0.1365, "step": 405930 }, { "epoch": 2.4129916602766435, "grad_norm": 3.8084259033203125, "learning_rate": 6.165583929175614e-06, "loss": 0.1271, "step": 405940 }, { "epoch": 2.413051102353312, "grad_norm": 3.6822776794433594, "learning_rate": 6.16538215271282e-06, "loss": 0.136, "step": 405950 }, { "epoch": 2.4131105444299803, "grad_norm": 4.364902496337891, "learning_rate": 6.165180374243102e-06, "loss": 0.1257, "step": 405960 }, { "epoch": 2.4131699865066487, "grad_norm": 4.660404682159424, "learning_rate": 6.164978593766804e-06, "loss": 0.1368, "step": 405970 }, { "epoch": 2.413229428583317, "grad_norm": 4.815488338470459, "learning_rate": 6.164776811284272e-06, "loss": 0.1323, "step": 405980 }, { "epoch": 2.4132888706599855, "grad_norm": 4.277626991271973, "learning_rate": 6.164575026795856e-06, "loss": 0.1407, "step": 405990 }, { "epoch": 2.413348312736654, "grad_norm": 4.3521833419799805, "learning_rate": 6.164373240301903e-06, "loss": 0.1467, "step": 406000 }, { "epoch": 2.4134077548133224, "grad_norm": 4.364734172821045, "learning_rate": 6.1641714518027595e-06, "loss": 0.1439, "step": 406010 }, { "epoch": 2.4134671968899903, "grad_norm": 4.2648773193359375, "learning_rate": 6.163969661298775e-06, "loss": 0.1408, "step": 406020 }, { "epoch": 2.4135266389666588, "grad_norm": 3.4302124977111816, "learning_rate": 6.163767868790297e-06, "loss": 0.1457, "step": 406030 }, { "epoch": 2.413586081043327, "grad_norm": 5.928555488586426, "learning_rate": 6.16356607427767e-06, "loss": 0.1409, "step": 406040 }, { "epoch": 2.4136455231199956, "grad_norm": 5.3543219566345215, "learning_rate": 6.163364277761245e-06, "loss": 0.152, "step": 406050 }, { "epoch": 2.413704965196664, "grad_norm": 4.5865278244018555, "learning_rate": 6.163162479241367e-06, "loss": 0.1364, "step": 406060 }, { "epoch": 2.4137644072733324, "grad_norm": 5.427489757537842, "learning_rate": 6.162960678718384e-06, "loss": 0.1472, "step": 406070 }, { "epoch": 2.413823849350001, "grad_norm": 3.9363579750061035, "learning_rate": 6.162758876192644e-06, "loss": 0.1349, "step": 406080 }, { "epoch": 2.4138832914266692, "grad_norm": 4.284550666809082, "learning_rate": 6.1625570716644956e-06, "loss": 0.1429, "step": 406090 }, { "epoch": 2.4139427335033377, "grad_norm": 4.986026763916016, "learning_rate": 6.162355265134283e-06, "loss": 0.132, "step": 406100 }, { "epoch": 2.414002175580006, "grad_norm": 3.0779054164886475, "learning_rate": 6.162153456602358e-06, "loss": 0.1315, "step": 406110 }, { "epoch": 2.4140616176566745, "grad_norm": 5.92595100402832, "learning_rate": 6.161951646069065e-06, "loss": 0.1522, "step": 406120 }, { "epoch": 2.414121059733343, "grad_norm": 5.596240520477295, "learning_rate": 6.1617498335347536e-06, "loss": 0.1486, "step": 406130 }, { "epoch": 2.4141805018100113, "grad_norm": 3.416293144226074, "learning_rate": 6.161548018999769e-06, "loss": 0.1442, "step": 406140 }, { "epoch": 2.4142399438866797, "grad_norm": 3.2970001697540283, "learning_rate": 6.161346202464461e-06, "loss": 0.1415, "step": 406150 }, { "epoch": 2.414299385963348, "grad_norm": 4.363722324371338, "learning_rate": 6.161144383929177e-06, "loss": 0.1396, "step": 406160 }, { "epoch": 2.4143588280400166, "grad_norm": 4.11907434463501, "learning_rate": 6.160942563394262e-06, "loss": 0.1538, "step": 406170 }, { "epoch": 2.414418270116685, "grad_norm": 5.605030059814453, "learning_rate": 6.160740740860067e-06, "loss": 0.1426, "step": 406180 }, { "epoch": 2.414477712193353, "grad_norm": 3.505479574203491, "learning_rate": 6.160538916326938e-06, "loss": 0.1257, "step": 406190 }, { "epoch": 2.414537154270022, "grad_norm": 4.365617275238037, "learning_rate": 6.160337089795221e-06, "loss": 0.1562, "step": 406200 }, { "epoch": 2.4145965963466898, "grad_norm": 5.707424640655518, "learning_rate": 6.160135261265266e-06, "loss": 0.1437, "step": 406210 }, { "epoch": 2.414656038423358, "grad_norm": 3.9798827171325684, "learning_rate": 6.159933430737419e-06, "loss": 0.1391, "step": 406220 }, { "epoch": 2.4147154805000266, "grad_norm": 4.203458786010742, "learning_rate": 6.1597315982120294e-06, "loss": 0.1412, "step": 406230 }, { "epoch": 2.414774922576695, "grad_norm": 3.4616754055023193, "learning_rate": 6.159529763689442e-06, "loss": 0.1323, "step": 406240 }, { "epoch": 2.4148343646533634, "grad_norm": 4.591666221618652, "learning_rate": 6.159327927170008e-06, "loss": 0.1406, "step": 406250 }, { "epoch": 2.414893806730032, "grad_norm": 4.452020645141602, "learning_rate": 6.159126088654073e-06, "loss": 0.131, "step": 406260 }, { "epoch": 2.4149532488067003, "grad_norm": 4.129115104675293, "learning_rate": 6.158924248141983e-06, "loss": 0.1653, "step": 406270 }, { "epoch": 2.4150126908833687, "grad_norm": 4.768790245056152, "learning_rate": 6.158722405634088e-06, "loss": 0.135, "step": 406280 }, { "epoch": 2.415072132960037, "grad_norm": 2.752272605895996, "learning_rate": 6.158520561130735e-06, "loss": 0.1139, "step": 406290 }, { "epoch": 2.4151315750367055, "grad_norm": 5.884932041168213, "learning_rate": 6.15831871463227e-06, "loss": 0.1468, "step": 406300 }, { "epoch": 2.415191017113374, "grad_norm": 3.878679037094116, "learning_rate": 6.158116866139043e-06, "loss": 0.1319, "step": 406310 }, { "epoch": 2.4152504591900423, "grad_norm": 4.739161491394043, "learning_rate": 6.1579150156514e-06, "loss": 0.125, "step": 406320 }, { "epoch": 2.4153099012667107, "grad_norm": 4.322960376739502, "learning_rate": 6.1577131631696894e-06, "loss": 0.1261, "step": 406330 }, { "epoch": 2.415369343343379, "grad_norm": 4.900947093963623, "learning_rate": 6.1575113086942585e-06, "loss": 0.1471, "step": 406340 }, { "epoch": 2.4154287854200476, "grad_norm": 4.135875225067139, "learning_rate": 6.157309452225456e-06, "loss": 0.1414, "step": 406350 }, { "epoch": 2.415488227496716, "grad_norm": 5.553462505340576, "learning_rate": 6.157107593763628e-06, "loss": 0.1474, "step": 406360 }, { "epoch": 2.4155476695733844, "grad_norm": 3.118420124053955, "learning_rate": 6.156905733309122e-06, "loss": 0.1133, "step": 406370 }, { "epoch": 2.4156071116500524, "grad_norm": 5.26887845993042, "learning_rate": 6.156703870862287e-06, "loss": 0.1423, "step": 406380 }, { "epoch": 2.4156665537267212, "grad_norm": 4.427414417266846, "learning_rate": 6.15650200642347e-06, "loss": 0.1389, "step": 406390 }, { "epoch": 2.415725995803389, "grad_norm": 5.34157133102417, "learning_rate": 6.156300139993018e-06, "loss": 0.1462, "step": 406400 }, { "epoch": 2.4157854378800576, "grad_norm": 3.19089674949646, "learning_rate": 6.15609827157128e-06, "loss": 0.143, "step": 406410 }, { "epoch": 2.415844879956726, "grad_norm": 3.8369150161743164, "learning_rate": 6.155896401158603e-06, "loss": 0.1336, "step": 406420 }, { "epoch": 2.4159043220333944, "grad_norm": 3.737656593322754, "learning_rate": 6.155694528755333e-06, "loss": 0.1331, "step": 406430 }, { "epoch": 2.415963764110063, "grad_norm": 5.494523048400879, "learning_rate": 6.155492654361819e-06, "loss": 0.1399, "step": 406440 }, { "epoch": 2.4160232061867313, "grad_norm": 3.4897654056549072, "learning_rate": 6.1552907779784095e-06, "loss": 0.1281, "step": 406450 }, { "epoch": 2.4160826482633997, "grad_norm": 3.485398530960083, "learning_rate": 6.155088899605453e-06, "loss": 0.1533, "step": 406460 }, { "epoch": 2.416142090340068, "grad_norm": 4.206061363220215, "learning_rate": 6.154887019243293e-06, "loss": 0.1508, "step": 406470 }, { "epoch": 2.4162015324167365, "grad_norm": 4.379769325256348, "learning_rate": 6.154685136892282e-06, "loss": 0.1409, "step": 406480 }, { "epoch": 2.416260974493405, "grad_norm": 3.8781561851501465, "learning_rate": 6.154483252552764e-06, "loss": 0.1487, "step": 406490 }, { "epoch": 2.4163204165700733, "grad_norm": 4.261367321014404, "learning_rate": 6.154281366225088e-06, "loss": 0.14, "step": 406500 }, { "epoch": 2.4163798586467418, "grad_norm": 4.163271903991699, "learning_rate": 6.1540794779096025e-06, "loss": 0.1507, "step": 406510 }, { "epoch": 2.41643930072341, "grad_norm": 3.9102325439453125, "learning_rate": 6.153877587606655e-06, "loss": 0.1439, "step": 406520 }, { "epoch": 2.4164987428000786, "grad_norm": 4.319405555725098, "learning_rate": 6.153675695316591e-06, "loss": 0.1381, "step": 406530 }, { "epoch": 2.416558184876747, "grad_norm": 4.224910259246826, "learning_rate": 6.1534738010397595e-06, "loss": 0.1454, "step": 406540 }, { "epoch": 2.4166176269534154, "grad_norm": 4.149576663970947, "learning_rate": 6.15327190477651e-06, "loss": 0.1374, "step": 406550 }, { "epoch": 2.416677069030084, "grad_norm": 4.648004531860352, "learning_rate": 6.1530700065271885e-06, "loss": 0.1361, "step": 406560 }, { "epoch": 2.416736511106752, "grad_norm": 4.6483154296875, "learning_rate": 6.152868106292143e-06, "loss": 0.1357, "step": 406570 }, { "epoch": 2.4167959531834207, "grad_norm": 2.9919657707214355, "learning_rate": 6.152666204071721e-06, "loss": 0.1244, "step": 406580 }, { "epoch": 2.4168553952600886, "grad_norm": 3.854309320449829, "learning_rate": 6.15246429986627e-06, "loss": 0.1389, "step": 406590 }, { "epoch": 2.416914837336757, "grad_norm": 3.7726054191589355, "learning_rate": 6.152262393676137e-06, "loss": 0.1254, "step": 406600 }, { "epoch": 2.4169742794134255, "grad_norm": 3.4007363319396973, "learning_rate": 6.152060485501672e-06, "loss": 0.1532, "step": 406610 }, { "epoch": 2.417033721490094, "grad_norm": 4.453877925872803, "learning_rate": 6.151858575343222e-06, "loss": 0.1432, "step": 406620 }, { "epoch": 2.4170931635667623, "grad_norm": 4.783276081085205, "learning_rate": 6.151656663201132e-06, "loss": 0.1443, "step": 406630 }, { "epoch": 2.4171526056434307, "grad_norm": 2.7785143852233887, "learning_rate": 6.151454749075754e-06, "loss": 0.1231, "step": 406640 }, { "epoch": 2.417212047720099, "grad_norm": 4.07545280456543, "learning_rate": 6.151252832967432e-06, "loss": 0.1395, "step": 406650 }, { "epoch": 2.4172714897967675, "grad_norm": 4.271949768066406, "learning_rate": 6.151050914876514e-06, "loss": 0.1361, "step": 406660 }, { "epoch": 2.417330931873436, "grad_norm": 5.8374223709106445, "learning_rate": 6.1508489948033516e-06, "loss": 0.1579, "step": 406670 }, { "epoch": 2.4173903739501044, "grad_norm": 3.328685998916626, "learning_rate": 6.150647072748289e-06, "loss": 0.1431, "step": 406680 }, { "epoch": 2.417449816026773, "grad_norm": 3.662217855453491, "learning_rate": 6.150445148711675e-06, "loss": 0.1406, "step": 406690 }, { "epoch": 2.417509258103441, "grad_norm": 2.963181495666504, "learning_rate": 6.150243222693857e-06, "loss": 0.1385, "step": 406700 }, { "epoch": 2.4175687001801096, "grad_norm": 3.5606439113616943, "learning_rate": 6.1500412946951825e-06, "loss": 0.1426, "step": 406710 }, { "epoch": 2.417628142256778, "grad_norm": 3.831003189086914, "learning_rate": 6.1498393647159995e-06, "loss": 0.1434, "step": 406720 }, { "epoch": 2.4176875843334464, "grad_norm": 6.096010684967041, "learning_rate": 6.149637432756657e-06, "loss": 0.129, "step": 406730 }, { "epoch": 2.417747026410115, "grad_norm": 3.958909034729004, "learning_rate": 6.149435498817502e-06, "loss": 0.1557, "step": 406740 }, { "epoch": 2.4178064684867833, "grad_norm": 4.712631702423096, "learning_rate": 6.14923356289888e-06, "loss": 0.1562, "step": 406750 }, { "epoch": 2.4178659105634512, "grad_norm": 4.623537540435791, "learning_rate": 6.149031625001141e-06, "loss": 0.1385, "step": 406760 }, { "epoch": 2.4179253526401197, "grad_norm": 3.5697684288024902, "learning_rate": 6.148829685124634e-06, "loss": 0.1244, "step": 406770 }, { "epoch": 2.417984794716788, "grad_norm": 4.480966091156006, "learning_rate": 6.148627743269705e-06, "loss": 0.13, "step": 406780 }, { "epoch": 2.4180442367934565, "grad_norm": 3.8976898193359375, "learning_rate": 6.1484257994367e-06, "loss": 0.1251, "step": 406790 }, { "epoch": 2.418103678870125, "grad_norm": 4.262508392333984, "learning_rate": 6.148223853625971e-06, "loss": 0.1403, "step": 406800 }, { "epoch": 2.4181631209467933, "grad_norm": 4.415555953979492, "learning_rate": 6.148021905837863e-06, "loss": 0.1354, "step": 406810 }, { "epoch": 2.4182225630234617, "grad_norm": 4.300629138946533, "learning_rate": 6.1478199560727235e-06, "loss": 0.1433, "step": 406820 }, { "epoch": 2.41828200510013, "grad_norm": 4.825801849365234, "learning_rate": 6.147618004330902e-06, "loss": 0.1661, "step": 406830 }, { "epoch": 2.4183414471767986, "grad_norm": 3.976738929748535, "learning_rate": 6.147416050612745e-06, "loss": 0.1465, "step": 406840 }, { "epoch": 2.418400889253467, "grad_norm": 3.912278413772583, "learning_rate": 6.1472140949185995e-06, "loss": 0.1304, "step": 406850 }, { "epoch": 2.4184603313301354, "grad_norm": 4.35894250869751, "learning_rate": 6.147012137248816e-06, "loss": 0.1333, "step": 406860 }, { "epoch": 2.418519773406804, "grad_norm": 4.146391868591309, "learning_rate": 6.146810177603739e-06, "loss": 0.153, "step": 406870 }, { "epoch": 2.418579215483472, "grad_norm": 4.441240310668945, "learning_rate": 6.146608215983721e-06, "loss": 0.1333, "step": 406880 }, { "epoch": 2.4186386575601406, "grad_norm": 5.898228168487549, "learning_rate": 6.1464062523891044e-06, "loss": 0.1417, "step": 406890 }, { "epoch": 2.418698099636809, "grad_norm": 3.522994041442871, "learning_rate": 6.14620428682024e-06, "loss": 0.1288, "step": 406900 }, { "epoch": 2.4187575417134775, "grad_norm": 4.571454048156738, "learning_rate": 6.146002319277475e-06, "loss": 0.1239, "step": 406910 }, { "epoch": 2.418816983790146, "grad_norm": 4.2887654304504395, "learning_rate": 6.145800349761157e-06, "loss": 0.1368, "step": 406920 }, { "epoch": 2.418876425866814, "grad_norm": 4.338197708129883, "learning_rate": 6.145598378271636e-06, "loss": 0.1291, "step": 406930 }, { "epoch": 2.4189358679434827, "grad_norm": 3.732574701309204, "learning_rate": 6.145396404809256e-06, "loss": 0.1458, "step": 406940 }, { "epoch": 2.4189953100201507, "grad_norm": 4.673095226287842, "learning_rate": 6.1451944293743675e-06, "loss": 0.1314, "step": 406950 }, { "epoch": 2.419054752096819, "grad_norm": 4.844930171966553, "learning_rate": 6.144992451967318e-06, "loss": 0.1373, "step": 406960 }, { "epoch": 2.4191141941734875, "grad_norm": 6.207622051239014, "learning_rate": 6.1447904725884535e-06, "loss": 0.142, "step": 406970 }, { "epoch": 2.419173636250156, "grad_norm": 4.88053560256958, "learning_rate": 6.144588491238124e-06, "loss": 0.1388, "step": 406980 }, { "epoch": 2.4192330783268243, "grad_norm": 4.057521820068359, "learning_rate": 6.1443865079166754e-06, "loss": 0.1358, "step": 406990 }, { "epoch": 2.4192925204034927, "grad_norm": 4.637533664703369, "learning_rate": 6.144184522624458e-06, "loss": 0.1339, "step": 407000 }, { "epoch": 2.419351962480161, "grad_norm": 4.732538223266602, "learning_rate": 6.1439825353618176e-06, "loss": 0.1398, "step": 407010 }, { "epoch": 2.4194114045568296, "grad_norm": 4.478734493255615, "learning_rate": 6.143780546129103e-06, "loss": 0.1434, "step": 407020 }, { "epoch": 2.419470846633498, "grad_norm": 4.2246904373168945, "learning_rate": 6.143578554926662e-06, "loss": 0.1454, "step": 407030 }, { "epoch": 2.4195302887101664, "grad_norm": 4.608737945556641, "learning_rate": 6.143376561754844e-06, "loss": 0.1423, "step": 407040 }, { "epoch": 2.419589730786835, "grad_norm": 3.364586353302002, "learning_rate": 6.143174566613992e-06, "loss": 0.1297, "step": 407050 }, { "epoch": 2.4196491728635032, "grad_norm": 4.781994819641113, "learning_rate": 6.142972569504458e-06, "loss": 0.1261, "step": 407060 }, { "epoch": 2.4197086149401716, "grad_norm": 4.648162841796875, "learning_rate": 6.142770570426591e-06, "loss": 0.1509, "step": 407070 }, { "epoch": 2.41976805701684, "grad_norm": 3.2532217502593994, "learning_rate": 6.142568569380734e-06, "loss": 0.1299, "step": 407080 }, { "epoch": 2.4198274990935085, "grad_norm": 3.4375760555267334, "learning_rate": 6.142366566367237e-06, "loss": 0.1369, "step": 407090 }, { "epoch": 2.419886941170177, "grad_norm": 3.8094427585601807, "learning_rate": 6.142164561386451e-06, "loss": 0.1559, "step": 407100 }, { "epoch": 2.4199463832468453, "grad_norm": 4.650213241577148, "learning_rate": 6.141962554438721e-06, "loss": 0.1414, "step": 407110 }, { "epoch": 2.4200058253235133, "grad_norm": 3.392430067062378, "learning_rate": 6.1417605455243936e-06, "loss": 0.1594, "step": 407120 }, { "epoch": 2.420065267400182, "grad_norm": 3.4626054763793945, "learning_rate": 6.14155853464382e-06, "loss": 0.1265, "step": 407130 }, { "epoch": 2.42012470947685, "grad_norm": 4.161116600036621, "learning_rate": 6.1413565217973455e-06, "loss": 0.1355, "step": 407140 }, { "epoch": 2.4201841515535185, "grad_norm": 4.165637493133545, "learning_rate": 6.141154506985319e-06, "loss": 0.1291, "step": 407150 }, { "epoch": 2.420243593630187, "grad_norm": 4.215747833251953, "learning_rate": 6.1409524902080884e-06, "loss": 0.1475, "step": 407160 }, { "epoch": 2.4203030357068553, "grad_norm": 5.7141313552856445, "learning_rate": 6.140750471466003e-06, "loss": 0.146, "step": 407170 }, { "epoch": 2.4203624777835238, "grad_norm": 4.483105182647705, "learning_rate": 6.140548450759406e-06, "loss": 0.1284, "step": 407180 }, { "epoch": 2.420421919860192, "grad_norm": 3.440762758255005, "learning_rate": 6.14034642808865e-06, "loss": 0.1505, "step": 407190 }, { "epoch": 2.4204813619368606, "grad_norm": 4.010213851928711, "learning_rate": 6.140144403454082e-06, "loss": 0.1481, "step": 407200 }, { "epoch": 2.420540804013529, "grad_norm": 5.777868747711182, "learning_rate": 6.139942376856047e-06, "loss": 0.1795, "step": 407210 }, { "epoch": 2.4206002460901974, "grad_norm": 4.143859386444092, "learning_rate": 6.139740348294898e-06, "loss": 0.141, "step": 407220 }, { "epoch": 2.420659688166866, "grad_norm": 4.163217067718506, "learning_rate": 6.13953831777098e-06, "loss": 0.1376, "step": 407230 }, { "epoch": 2.4207191302435342, "grad_norm": 3.5998008251190186, "learning_rate": 6.13933628528464e-06, "loss": 0.1366, "step": 407240 }, { "epoch": 2.4207785723202027, "grad_norm": 4.163533687591553, "learning_rate": 6.139134250836227e-06, "loss": 0.1603, "step": 407250 }, { "epoch": 2.420838014396871, "grad_norm": 3.779071569442749, "learning_rate": 6.13893221442609e-06, "loss": 0.1389, "step": 407260 }, { "epoch": 2.4208974564735395, "grad_norm": 4.762997150421143, "learning_rate": 6.138730176054575e-06, "loss": 0.1468, "step": 407270 }, { "epoch": 2.420956898550208, "grad_norm": 4.6182379722595215, "learning_rate": 6.138528135722029e-06, "loss": 0.1605, "step": 407280 }, { "epoch": 2.4210163406268763, "grad_norm": 4.3034234046936035, "learning_rate": 6.138326093428804e-06, "loss": 0.1528, "step": 407290 }, { "epoch": 2.4210757827035447, "grad_norm": 3.6324143409729004, "learning_rate": 6.138124049175246e-06, "loss": 0.1521, "step": 407300 }, { "epoch": 2.4211352247802127, "grad_norm": 4.655734539031982, "learning_rate": 6.1379220029617e-06, "loss": 0.1338, "step": 407310 }, { "epoch": 2.4211946668568816, "grad_norm": 4.368134498596191, "learning_rate": 6.137719954788518e-06, "loss": 0.115, "step": 407320 }, { "epoch": 2.4212541089335495, "grad_norm": 4.242708683013916, "learning_rate": 6.137517904656047e-06, "loss": 0.1594, "step": 407330 }, { "epoch": 2.421313551010218, "grad_norm": 3.7324585914611816, "learning_rate": 6.137315852564634e-06, "loss": 0.1533, "step": 407340 }, { "epoch": 2.4213729930868864, "grad_norm": 4.372202396392822, "learning_rate": 6.137113798514628e-06, "loss": 0.1488, "step": 407350 }, { "epoch": 2.4214324351635548, "grad_norm": 3.284250497817993, "learning_rate": 6.136911742506376e-06, "loss": 0.1387, "step": 407360 }, { "epoch": 2.421491877240223, "grad_norm": 4.558399677276611, "learning_rate": 6.136709684540225e-06, "loss": 0.1341, "step": 407370 }, { "epoch": 2.4215513193168916, "grad_norm": 4.5630269050598145, "learning_rate": 6.136507624616527e-06, "loss": 0.1481, "step": 407380 }, { "epoch": 2.42161076139356, "grad_norm": 4.716888427734375, "learning_rate": 6.136305562735625e-06, "loss": 0.1477, "step": 407390 }, { "epoch": 2.4216702034702284, "grad_norm": 3.677504539489746, "learning_rate": 6.1361034988978695e-06, "loss": 0.1392, "step": 407400 }, { "epoch": 2.421729645546897, "grad_norm": 5.358774662017822, "learning_rate": 6.1359014331036095e-06, "loss": 0.1336, "step": 407410 }, { "epoch": 2.4217890876235653, "grad_norm": 4.478745937347412, "learning_rate": 6.13569936535319e-06, "loss": 0.1366, "step": 407420 }, { "epoch": 2.4218485297002337, "grad_norm": 2.862640857696533, "learning_rate": 6.135497295646961e-06, "loss": 0.1189, "step": 407430 }, { "epoch": 2.421907971776902, "grad_norm": 4.765482425689697, "learning_rate": 6.135295223985272e-06, "loss": 0.1391, "step": 407440 }, { "epoch": 2.4219674138535705, "grad_norm": 4.103326797485352, "learning_rate": 6.135093150368468e-06, "loss": 0.1495, "step": 407450 }, { "epoch": 2.422026855930239, "grad_norm": 4.725662708282471, "learning_rate": 6.134891074796898e-06, "loss": 0.1278, "step": 407460 }, { "epoch": 2.4220862980069073, "grad_norm": 4.161613941192627, "learning_rate": 6.1346889972709105e-06, "loss": 0.1409, "step": 407470 }, { "epoch": 2.4221457400835757, "grad_norm": 4.434993267059326, "learning_rate": 6.134486917790852e-06, "loss": 0.1238, "step": 407480 }, { "epoch": 2.422205182160244, "grad_norm": 5.830995559692383, "learning_rate": 6.134284836357073e-06, "loss": 0.1621, "step": 407490 }, { "epoch": 2.422264624236912, "grad_norm": 3.382800340652466, "learning_rate": 6.134082752969918e-06, "loss": 0.136, "step": 407500 }, { "epoch": 2.4223240663135805, "grad_norm": 3.761385679244995, "learning_rate": 6.13388066762974e-06, "loss": 0.1444, "step": 407510 }, { "epoch": 2.422383508390249, "grad_norm": 3.78599214553833, "learning_rate": 6.133678580336884e-06, "loss": 0.1406, "step": 407520 }, { "epoch": 2.4224429504669174, "grad_norm": 6.303254127502441, "learning_rate": 6.133476491091697e-06, "loss": 0.1457, "step": 407530 }, { "epoch": 2.422502392543586, "grad_norm": 4.055797100067139, "learning_rate": 6.133274399894528e-06, "loss": 0.1279, "step": 407540 }, { "epoch": 2.422561834620254, "grad_norm": 4.134913444519043, "learning_rate": 6.133072306745725e-06, "loss": 0.1401, "step": 407550 }, { "epoch": 2.4226212766969226, "grad_norm": 5.2646050453186035, "learning_rate": 6.132870211645639e-06, "loss": 0.1388, "step": 407560 }, { "epoch": 2.422680718773591, "grad_norm": 5.194967746734619, "learning_rate": 6.132668114594612e-06, "loss": 0.1442, "step": 407570 }, { "epoch": 2.4227401608502594, "grad_norm": 4.075958251953125, "learning_rate": 6.132466015592997e-06, "loss": 0.1386, "step": 407580 }, { "epoch": 2.422799602926928, "grad_norm": 4.305830478668213, "learning_rate": 6.132263914641141e-06, "loss": 0.1474, "step": 407590 }, { "epoch": 2.4228590450035963, "grad_norm": 6.144965648651123, "learning_rate": 6.132061811739389e-06, "loss": 0.147, "step": 407600 }, { "epoch": 2.4229184870802647, "grad_norm": 3.461839437484741, "learning_rate": 6.1318597068880936e-06, "loss": 0.1494, "step": 407610 }, { "epoch": 2.422977929156933, "grad_norm": 4.455348968505859, "learning_rate": 6.1316576000876014e-06, "loss": 0.1423, "step": 407620 }, { "epoch": 2.4230373712336015, "grad_norm": 5.3783979415893555, "learning_rate": 6.131455491338258e-06, "loss": 0.1391, "step": 407630 }, { "epoch": 2.42309681331027, "grad_norm": 4.068969249725342, "learning_rate": 6.131253380640413e-06, "loss": 0.1212, "step": 407640 }, { "epoch": 2.4231562553869384, "grad_norm": 4.515283107757568, "learning_rate": 6.131051267994416e-06, "loss": 0.126, "step": 407650 }, { "epoch": 2.4232156974636068, "grad_norm": 4.733911037445068, "learning_rate": 6.130849153400613e-06, "loss": 0.1389, "step": 407660 }, { "epoch": 2.4232751395402747, "grad_norm": 3.271625518798828, "learning_rate": 6.130647036859353e-06, "loss": 0.1489, "step": 407670 }, { "epoch": 2.4233345816169436, "grad_norm": 4.576600074768066, "learning_rate": 6.130444918370985e-06, "loss": 0.1477, "step": 407680 }, { "epoch": 2.4233940236936116, "grad_norm": 4.150426864624023, "learning_rate": 6.130242797935855e-06, "loss": 0.1454, "step": 407690 }, { "epoch": 2.42345346577028, "grad_norm": 4.7356767654418945, "learning_rate": 6.130040675554312e-06, "loss": 0.1267, "step": 407700 }, { "epoch": 2.4235129078469484, "grad_norm": 4.972351551055908, "learning_rate": 6.129838551226703e-06, "loss": 0.1324, "step": 407710 }, { "epoch": 2.423572349923617, "grad_norm": 5.874485015869141, "learning_rate": 6.12963642495338e-06, "loss": 0.1608, "step": 407720 }, { "epoch": 2.4236317920002852, "grad_norm": 3.8049354553222656, "learning_rate": 6.129434296734685e-06, "loss": 0.1373, "step": 407730 }, { "epoch": 2.4236912340769536, "grad_norm": 4.376839637756348, "learning_rate": 6.129232166570972e-06, "loss": 0.1389, "step": 407740 }, { "epoch": 2.423750676153622, "grad_norm": 4.037137031555176, "learning_rate": 6.1290300344625854e-06, "loss": 0.1549, "step": 407750 }, { "epoch": 2.4238101182302905, "grad_norm": 4.928534507751465, "learning_rate": 6.128827900409875e-06, "loss": 0.1581, "step": 407760 }, { "epoch": 2.423869560306959, "grad_norm": 4.752762794494629, "learning_rate": 6.128625764413186e-06, "loss": 0.14, "step": 407770 }, { "epoch": 2.4239290023836273, "grad_norm": 4.39714241027832, "learning_rate": 6.128423626472871e-06, "loss": 0.1398, "step": 407780 }, { "epoch": 2.4239884444602957, "grad_norm": 3.301772356033325, "learning_rate": 6.128221486589276e-06, "loss": 0.1088, "step": 407790 }, { "epoch": 2.424047886536964, "grad_norm": 5.854825973510742, "learning_rate": 6.1280193447627476e-06, "loss": 0.1429, "step": 407800 }, { "epoch": 2.4241073286136325, "grad_norm": 5.294264316558838, "learning_rate": 6.127817200993636e-06, "loss": 0.1314, "step": 407810 }, { "epoch": 2.424166770690301, "grad_norm": 4.687266826629639, "learning_rate": 6.12761505528229e-06, "loss": 0.1681, "step": 407820 }, { "epoch": 2.4242262127669694, "grad_norm": 4.517871379852295, "learning_rate": 6.127412907629054e-06, "loss": 0.138, "step": 407830 }, { "epoch": 2.424285654843638, "grad_norm": 3.137644052505493, "learning_rate": 6.12721075803428e-06, "loss": 0.1419, "step": 407840 }, { "epoch": 2.424345096920306, "grad_norm": 3.80777907371521, "learning_rate": 6.127008606498315e-06, "loss": 0.1369, "step": 407850 }, { "epoch": 2.424404538996974, "grad_norm": 4.451732635498047, "learning_rate": 6.1268064530215036e-06, "loss": 0.1468, "step": 407860 }, { "epoch": 2.424463981073643, "grad_norm": 3.823953151702881, "learning_rate": 6.126604297604199e-06, "loss": 0.142, "step": 407870 }, { "epoch": 2.424523423150311, "grad_norm": 3.8148975372314453, "learning_rate": 6.126402140246749e-06, "loss": 0.134, "step": 407880 }, { "epoch": 2.4245828652269794, "grad_norm": 4.1356048583984375, "learning_rate": 6.126199980949498e-06, "loss": 0.1492, "step": 407890 }, { "epoch": 2.424642307303648, "grad_norm": 4.574592113494873, "learning_rate": 6.125997819712797e-06, "loss": 0.1484, "step": 407900 }, { "epoch": 2.4247017493803162, "grad_norm": 4.635424613952637, "learning_rate": 6.125795656536994e-06, "loss": 0.1395, "step": 407910 }, { "epoch": 2.4247611914569847, "grad_norm": 4.007504463195801, "learning_rate": 6.125593491422436e-06, "loss": 0.138, "step": 407920 }, { "epoch": 2.424820633533653, "grad_norm": 3.9391930103302, "learning_rate": 6.125391324369471e-06, "loss": 0.1335, "step": 407930 }, { "epoch": 2.4248800756103215, "grad_norm": 4.75462007522583, "learning_rate": 6.125189155378448e-06, "loss": 0.1595, "step": 407940 }, { "epoch": 2.42493951768699, "grad_norm": 4.910210609436035, "learning_rate": 6.124986984449717e-06, "loss": 0.1482, "step": 407950 }, { "epoch": 2.4249989597636583, "grad_norm": 3.806737184524536, "learning_rate": 6.124784811583622e-06, "loss": 0.1335, "step": 407960 }, { "epoch": 2.4250584018403267, "grad_norm": 4.122501850128174, "learning_rate": 6.124582636780513e-06, "loss": 0.1583, "step": 407970 }, { "epoch": 2.425117843916995, "grad_norm": 4.164566516876221, "learning_rate": 6.12438046004074e-06, "loss": 0.138, "step": 407980 }, { "epoch": 2.4251772859936636, "grad_norm": 3.2532155513763428, "learning_rate": 6.124178281364648e-06, "loss": 0.1529, "step": 407990 }, { "epoch": 2.425236728070332, "grad_norm": 3.5686209201812744, "learning_rate": 6.123976100752589e-06, "loss": 0.153, "step": 408000 }, { "epoch": 2.4252961701470004, "grad_norm": 3.411646842956543, "learning_rate": 6.1237739182049085e-06, "loss": 0.1405, "step": 408010 }, { "epoch": 2.425355612223669, "grad_norm": 4.117336750030518, "learning_rate": 6.123571733721953e-06, "loss": 0.1412, "step": 408020 }, { "epoch": 2.425415054300337, "grad_norm": 5.211827754974365, "learning_rate": 6.123369547304077e-06, "loss": 0.1516, "step": 408030 }, { "epoch": 2.4254744963770056, "grad_norm": 4.837274074554443, "learning_rate": 6.123167358951622e-06, "loss": 0.1433, "step": 408040 }, { "epoch": 2.4255339384536736, "grad_norm": 4.346046447753906, "learning_rate": 6.122965168664938e-06, "loss": 0.1229, "step": 408050 }, { "epoch": 2.4255933805303425, "grad_norm": 5.336977005004883, "learning_rate": 6.122762976444376e-06, "loss": 0.134, "step": 408060 }, { "epoch": 2.4256528226070104, "grad_norm": 4.086795806884766, "learning_rate": 6.1225607822902815e-06, "loss": 0.1429, "step": 408070 }, { "epoch": 2.425712264683679, "grad_norm": 4.20722770690918, "learning_rate": 6.122358586203004e-06, "loss": 0.1448, "step": 408080 }, { "epoch": 2.4257717067603473, "grad_norm": 3.722618341445923, "learning_rate": 6.122156388182888e-06, "loss": 0.1376, "step": 408090 }, { "epoch": 2.4258311488370157, "grad_norm": 4.580920696258545, "learning_rate": 6.121954188230288e-06, "loss": 0.1299, "step": 408100 }, { "epoch": 2.425890590913684, "grad_norm": 3.5843851566314697, "learning_rate": 6.1217519863455485e-06, "loss": 0.1262, "step": 408110 }, { "epoch": 2.4259500329903525, "grad_norm": 3.92488956451416, "learning_rate": 6.121549782529017e-06, "loss": 0.1408, "step": 408120 }, { "epoch": 2.426009475067021, "grad_norm": 5.2162675857543945, "learning_rate": 6.121347576781045e-06, "loss": 0.1513, "step": 408130 }, { "epoch": 2.4260689171436893, "grad_norm": 3.9436728954315186, "learning_rate": 6.121145369101977e-06, "loss": 0.1519, "step": 408140 }, { "epoch": 2.4261283592203577, "grad_norm": 4.702057361602783, "learning_rate": 6.120943159492163e-06, "loss": 0.1579, "step": 408150 }, { "epoch": 2.426187801297026, "grad_norm": 4.133393287658691, "learning_rate": 6.120740947951952e-06, "loss": 0.121, "step": 408160 }, { "epoch": 2.4262472433736946, "grad_norm": 4.990274429321289, "learning_rate": 6.120538734481692e-06, "loss": 0.1456, "step": 408170 }, { "epoch": 2.426306685450363, "grad_norm": 4.420265197753906, "learning_rate": 6.120336519081727e-06, "loss": 0.1395, "step": 408180 }, { "epoch": 2.4263661275270314, "grad_norm": 4.4518327713012695, "learning_rate": 6.120134301752412e-06, "loss": 0.1403, "step": 408190 }, { "epoch": 2.4264255696037, "grad_norm": 5.267309188842773, "learning_rate": 6.119932082494091e-06, "loss": 0.1287, "step": 408200 }, { "epoch": 2.4264850116803682, "grad_norm": 4.336322784423828, "learning_rate": 6.1197298613071145e-06, "loss": 0.1311, "step": 408210 }, { "epoch": 2.4265444537570366, "grad_norm": 3.4771454334259033, "learning_rate": 6.1195276381918285e-06, "loss": 0.1481, "step": 408220 }, { "epoch": 2.426603895833705, "grad_norm": 3.8004708290100098, "learning_rate": 6.119325413148582e-06, "loss": 0.1368, "step": 408230 }, { "epoch": 2.426663337910373, "grad_norm": 5.64704704284668, "learning_rate": 6.119123186177726e-06, "loss": 0.1261, "step": 408240 }, { "epoch": 2.4267227799870414, "grad_norm": 3.5745253562927246, "learning_rate": 6.1189209572796035e-06, "loss": 0.139, "step": 408250 }, { "epoch": 2.42678222206371, "grad_norm": 3.4878854751586914, "learning_rate": 6.118718726454567e-06, "loss": 0.1291, "step": 408260 }, { "epoch": 2.4268416641403783, "grad_norm": 4.162795543670654, "learning_rate": 6.118516493702964e-06, "loss": 0.1555, "step": 408270 }, { "epoch": 2.4269011062170467, "grad_norm": 3.2801930904388428, "learning_rate": 6.11831425902514e-06, "loss": 0.1362, "step": 408280 }, { "epoch": 2.426960548293715, "grad_norm": 5.586214065551758, "learning_rate": 6.118112022421448e-06, "loss": 0.1426, "step": 408290 }, { "epoch": 2.4270199903703835, "grad_norm": 5.506023406982422, "learning_rate": 6.1179097838922305e-06, "loss": 0.1575, "step": 408300 }, { "epoch": 2.427079432447052, "grad_norm": 5.6750102043151855, "learning_rate": 6.1177075434378405e-06, "loss": 0.1485, "step": 408310 }, { "epoch": 2.4271388745237203, "grad_norm": 4.719399929046631, "learning_rate": 6.117505301058625e-06, "loss": 0.1365, "step": 408320 }, { "epoch": 2.4271983166003888, "grad_norm": 3.674912214279175, "learning_rate": 6.117303056754933e-06, "loss": 0.1498, "step": 408330 }, { "epoch": 2.427257758677057, "grad_norm": 6.088858127593994, "learning_rate": 6.11710081052711e-06, "loss": 0.1282, "step": 408340 }, { "epoch": 2.4273172007537256, "grad_norm": 4.1899542808532715, "learning_rate": 6.116898562375507e-06, "loss": 0.1236, "step": 408350 }, { "epoch": 2.427376642830394, "grad_norm": 3.6587841510772705, "learning_rate": 6.116696312300472e-06, "loss": 0.1505, "step": 408360 }, { "epoch": 2.4274360849070624, "grad_norm": 4.046357154846191, "learning_rate": 6.1164940603023525e-06, "loss": 0.1359, "step": 408370 }, { "epoch": 2.427495526983731, "grad_norm": 5.006257057189941, "learning_rate": 6.1162918063814955e-06, "loss": 0.1373, "step": 408380 }, { "epoch": 2.4275549690603992, "grad_norm": 5.132629871368408, "learning_rate": 6.116089550538252e-06, "loss": 0.144, "step": 408390 }, { "epoch": 2.4276144111370677, "grad_norm": 4.103506088256836, "learning_rate": 6.1158872927729695e-06, "loss": 0.1409, "step": 408400 }, { "epoch": 2.4276738532137356, "grad_norm": 4.045587062835693, "learning_rate": 6.115685033085995e-06, "loss": 0.1451, "step": 408410 }, { "epoch": 2.4277332952904045, "grad_norm": 4.66650390625, "learning_rate": 6.115482771477678e-06, "loss": 0.1325, "step": 408420 }, { "epoch": 2.4277927373670725, "grad_norm": 4.583477973937988, "learning_rate": 6.115280507948367e-06, "loss": 0.1343, "step": 408430 }, { "epoch": 2.427852179443741, "grad_norm": 3.2007925510406494, "learning_rate": 6.11507824249841e-06, "loss": 0.1462, "step": 408440 }, { "epoch": 2.4279116215204093, "grad_norm": 3.9690024852752686, "learning_rate": 6.114875975128154e-06, "loss": 0.1324, "step": 408450 }, { "epoch": 2.4279710635970777, "grad_norm": 4.20497989654541, "learning_rate": 6.11467370583795e-06, "loss": 0.1564, "step": 408460 }, { "epoch": 2.428030505673746, "grad_norm": 3.8391804695129395, "learning_rate": 6.114471434628145e-06, "loss": 0.1253, "step": 408470 }, { "epoch": 2.4280899477504145, "grad_norm": 3.888845205307007, "learning_rate": 6.114269161499086e-06, "loss": 0.1443, "step": 408480 }, { "epoch": 2.428149389827083, "grad_norm": 4.983127117156982, "learning_rate": 6.114066886451123e-06, "loss": 0.1319, "step": 408490 }, { "epoch": 2.4282088319037514, "grad_norm": 4.714468002319336, "learning_rate": 6.113864609484604e-06, "loss": 0.1369, "step": 408500 }, { "epoch": 2.42826827398042, "grad_norm": 5.872633457183838, "learning_rate": 6.113662330599876e-06, "loss": 0.1611, "step": 408510 }, { "epoch": 2.428327716057088, "grad_norm": 5.145710468292236, "learning_rate": 6.11346004979729e-06, "loss": 0.1253, "step": 408520 }, { "epoch": 2.4283871581337566, "grad_norm": 3.8900086879730225, "learning_rate": 6.113257767077193e-06, "loss": 0.145, "step": 408530 }, { "epoch": 2.428446600210425, "grad_norm": 3.988518714904785, "learning_rate": 6.113055482439932e-06, "loss": 0.1318, "step": 408540 }, { "epoch": 2.4285060422870934, "grad_norm": 4.6497907638549805, "learning_rate": 6.112853195885859e-06, "loss": 0.1414, "step": 408550 }, { "epoch": 2.428565484363762, "grad_norm": 3.8092293739318848, "learning_rate": 6.112650907415319e-06, "loss": 0.1304, "step": 408560 }, { "epoch": 2.4286249264404303, "grad_norm": 4.621861934661865, "learning_rate": 6.112448617028661e-06, "loss": 0.1351, "step": 408570 }, { "epoch": 2.4286843685170987, "grad_norm": 3.5302493572235107, "learning_rate": 6.112246324726233e-06, "loss": 0.1395, "step": 408580 }, { "epoch": 2.428743810593767, "grad_norm": 4.582586765289307, "learning_rate": 6.112044030508386e-06, "loss": 0.1541, "step": 408590 }, { "epoch": 2.428803252670435, "grad_norm": 4.404309272766113, "learning_rate": 6.111841734375466e-06, "loss": 0.1516, "step": 408600 }, { "epoch": 2.428862694747104, "grad_norm": 4.532500743865967, "learning_rate": 6.111639436327821e-06, "loss": 0.1593, "step": 408610 }, { "epoch": 2.428922136823772, "grad_norm": 4.533953666687012, "learning_rate": 6.111437136365801e-06, "loss": 0.1393, "step": 408620 }, { "epoch": 2.4289815789004403, "grad_norm": 4.247570037841797, "learning_rate": 6.111234834489752e-06, "loss": 0.1335, "step": 408630 }, { "epoch": 2.4290410209771087, "grad_norm": 4.547585964202881, "learning_rate": 6.111032530700024e-06, "loss": 0.1394, "step": 408640 }, { "epoch": 2.429100463053777, "grad_norm": 4.762936115264893, "learning_rate": 6.1108302249969675e-06, "loss": 0.1276, "step": 408650 }, { "epoch": 2.4291599051304456, "grad_norm": 4.392101764678955, "learning_rate": 6.110627917380928e-06, "loss": 0.1521, "step": 408660 }, { "epoch": 2.429219347207114, "grad_norm": 5.355926513671875, "learning_rate": 6.110425607852254e-06, "loss": 0.16, "step": 408670 }, { "epoch": 2.4292787892837824, "grad_norm": 2.8851070404052734, "learning_rate": 6.1102232964112965e-06, "loss": 0.1405, "step": 408680 }, { "epoch": 2.429338231360451, "grad_norm": 4.893405437469482, "learning_rate": 6.1100209830584e-06, "loss": 0.1358, "step": 408690 }, { "epoch": 2.429397673437119, "grad_norm": 5.722377777099609, "learning_rate": 6.109818667793915e-06, "loss": 0.1635, "step": 408700 }, { "epoch": 2.4294571155137876, "grad_norm": 3.603163480758667, "learning_rate": 6.109616350618192e-06, "loss": 0.1346, "step": 408710 }, { "epoch": 2.429516557590456, "grad_norm": 3.5218772888183594, "learning_rate": 6.109414031531575e-06, "loss": 0.1348, "step": 408720 }, { "epoch": 2.4295759996671245, "grad_norm": 3.912208318710327, "learning_rate": 6.109211710534415e-06, "loss": 0.1397, "step": 408730 }, { "epoch": 2.429635441743793, "grad_norm": 4.962984561920166, "learning_rate": 6.109009387627061e-06, "loss": 0.1495, "step": 408740 }, { "epoch": 2.4296948838204613, "grad_norm": 4.006173610687256, "learning_rate": 6.1088070628098595e-06, "loss": 0.133, "step": 408750 }, { "epoch": 2.4297543258971297, "grad_norm": 4.168211936950684, "learning_rate": 6.108604736083161e-06, "loss": 0.1226, "step": 408760 }, { "epoch": 2.429813767973798, "grad_norm": 5.502830505371094, "learning_rate": 6.108402407447311e-06, "loss": 0.1563, "step": 408770 }, { "epoch": 2.4298732100504665, "grad_norm": 3.386974573135376, "learning_rate": 6.108200076902663e-06, "loss": 0.1494, "step": 408780 }, { "epoch": 2.4299326521271345, "grad_norm": 4.733436584472656, "learning_rate": 6.107997744449561e-06, "loss": 0.1526, "step": 408790 }, { "epoch": 2.429992094203803, "grad_norm": 3.6089839935302734, "learning_rate": 6.107795410088353e-06, "loss": 0.1334, "step": 408800 }, { "epoch": 2.4300515362804713, "grad_norm": 5.027360439300537, "learning_rate": 6.10759307381939e-06, "loss": 0.1584, "step": 408810 }, { "epoch": 2.4301109783571397, "grad_norm": 5.069947242736816, "learning_rate": 6.107390735643021e-06, "loss": 0.1362, "step": 408820 }, { "epoch": 2.430170420433808, "grad_norm": 4.235453128814697, "learning_rate": 6.10718839555959e-06, "loss": 0.1445, "step": 408830 }, { "epoch": 2.4302298625104766, "grad_norm": 3.560434579849243, "learning_rate": 6.106986053569451e-06, "loss": 0.143, "step": 408840 }, { "epoch": 2.430289304587145, "grad_norm": 4.458221435546875, "learning_rate": 6.106783709672949e-06, "loss": 0.1579, "step": 408850 }, { "epoch": 2.4303487466638134, "grad_norm": 4.014659404754639, "learning_rate": 6.106581363870434e-06, "loss": 0.1491, "step": 408860 }, { "epoch": 2.430408188740482, "grad_norm": 3.932171583175659, "learning_rate": 6.106379016162252e-06, "loss": 0.124, "step": 408870 }, { "epoch": 2.4304676308171502, "grad_norm": 3.869732618331909, "learning_rate": 6.106176666548755e-06, "loss": 0.1168, "step": 408880 }, { "epoch": 2.4305270728938186, "grad_norm": 4.18914794921875, "learning_rate": 6.1059743150302905e-06, "loss": 0.1332, "step": 408890 }, { "epoch": 2.430586514970487, "grad_norm": 4.626518249511719, "learning_rate": 6.105771961607205e-06, "loss": 0.1605, "step": 408900 }, { "epoch": 2.4306459570471555, "grad_norm": 5.018415927886963, "learning_rate": 6.105569606279848e-06, "loss": 0.1401, "step": 408910 }, { "epoch": 2.430705399123824, "grad_norm": 3.5909183025360107, "learning_rate": 6.105367249048571e-06, "loss": 0.132, "step": 408920 }, { "epoch": 2.4307648412004923, "grad_norm": 4.221224784851074, "learning_rate": 6.105164889913716e-06, "loss": 0.1394, "step": 408930 }, { "epoch": 2.4308242832771607, "grad_norm": 5.2121500968933105, "learning_rate": 6.104962528875637e-06, "loss": 0.1369, "step": 408940 }, { "epoch": 2.430883725353829, "grad_norm": 4.010108470916748, "learning_rate": 6.10476016593468e-06, "loss": 0.1559, "step": 408950 }, { "epoch": 2.4309431674304975, "grad_norm": 5.194670677185059, "learning_rate": 6.104557801091195e-06, "loss": 0.1375, "step": 408960 }, { "epoch": 2.431002609507166, "grad_norm": 3.30299711227417, "learning_rate": 6.104355434345528e-06, "loss": 0.1243, "step": 408970 }, { "epoch": 2.431062051583834, "grad_norm": 4.669257164001465, "learning_rate": 6.104153065698031e-06, "loss": 0.1486, "step": 408980 }, { "epoch": 2.4311214936605023, "grad_norm": 3.6096107959747314, "learning_rate": 6.10395069514905e-06, "loss": 0.1444, "step": 408990 }, { "epoch": 2.4311809357371708, "grad_norm": 2.606797933578491, "learning_rate": 6.103748322698934e-06, "loss": 0.1175, "step": 409000 }, { "epoch": 2.431240377813839, "grad_norm": 4.205752849578857, "learning_rate": 6.103545948348032e-06, "loss": 0.1486, "step": 409010 }, { "epoch": 2.4312998198905076, "grad_norm": 3.7794618606567383, "learning_rate": 6.103343572096693e-06, "loss": 0.1564, "step": 409020 }, { "epoch": 2.431359261967176, "grad_norm": 4.969024658203125, "learning_rate": 6.103141193945263e-06, "loss": 0.1514, "step": 409030 }, { "epoch": 2.4314187040438444, "grad_norm": 5.295257091522217, "learning_rate": 6.102938813894094e-06, "loss": 0.1502, "step": 409040 }, { "epoch": 2.431478146120513, "grad_norm": 5.009775161743164, "learning_rate": 6.102736431943533e-06, "loss": 0.1371, "step": 409050 }, { "epoch": 2.4315375881971812, "grad_norm": 4.460722923278809, "learning_rate": 6.102534048093925e-06, "loss": 0.1504, "step": 409060 }, { "epoch": 2.4315970302738497, "grad_norm": 2.999246597290039, "learning_rate": 6.102331662345623e-06, "loss": 0.1447, "step": 409070 }, { "epoch": 2.431656472350518, "grad_norm": 3.974271297454834, "learning_rate": 6.1021292746989755e-06, "loss": 0.1397, "step": 409080 }, { "epoch": 2.4317159144271865, "grad_norm": 3.5695598125457764, "learning_rate": 6.101926885154331e-06, "loss": 0.1404, "step": 409090 }, { "epoch": 2.431775356503855, "grad_norm": 3.610377550125122, "learning_rate": 6.101724493712035e-06, "loss": 0.1362, "step": 409100 }, { "epoch": 2.4318347985805233, "grad_norm": 3.8191726207733154, "learning_rate": 6.101522100372439e-06, "loss": 0.1246, "step": 409110 }, { "epoch": 2.4318942406571917, "grad_norm": 4.455204963684082, "learning_rate": 6.1013197051358905e-06, "loss": 0.1253, "step": 409120 }, { "epoch": 2.43195368273386, "grad_norm": 4.633851528167725, "learning_rate": 6.101117308002736e-06, "loss": 0.1387, "step": 409130 }, { "epoch": 2.4320131248105286, "grad_norm": 5.861626625061035, "learning_rate": 6.100914908973329e-06, "loss": 0.1263, "step": 409140 }, { "epoch": 2.4320725668871965, "grad_norm": 4.216809272766113, "learning_rate": 6.100712508048015e-06, "loss": 0.1089, "step": 409150 }, { "epoch": 2.4321320089638654, "grad_norm": 4.915881633758545, "learning_rate": 6.1005101052271395e-06, "loss": 0.1469, "step": 409160 }, { "epoch": 2.4321914510405334, "grad_norm": 4.01206636428833, "learning_rate": 6.100307700511058e-06, "loss": 0.1445, "step": 409170 }, { "epoch": 2.4322508931172018, "grad_norm": 4.92776346206665, "learning_rate": 6.100105293900113e-06, "loss": 0.1458, "step": 409180 }, { "epoch": 2.43231033519387, "grad_norm": 3.9147751331329346, "learning_rate": 6.0999028853946555e-06, "loss": 0.1368, "step": 409190 }, { "epoch": 2.4323697772705386, "grad_norm": 4.915139675140381, "learning_rate": 6.099700474995035e-06, "loss": 0.1337, "step": 409200 }, { "epoch": 2.432429219347207, "grad_norm": 4.905147552490234, "learning_rate": 6.099498062701599e-06, "loss": 0.1331, "step": 409210 }, { "epoch": 2.4324886614238754, "grad_norm": 3.958942413330078, "learning_rate": 6.099295648514696e-06, "loss": 0.1568, "step": 409220 }, { "epoch": 2.432548103500544, "grad_norm": 4.223944664001465, "learning_rate": 6.099093232434674e-06, "loss": 0.1277, "step": 409230 }, { "epoch": 2.4326075455772123, "grad_norm": 4.878054141998291, "learning_rate": 6.098890814461884e-06, "loss": 0.1622, "step": 409240 }, { "epoch": 2.4326669876538807, "grad_norm": 3.875688314437866, "learning_rate": 6.098688394596673e-06, "loss": 0.1342, "step": 409250 }, { "epoch": 2.432726429730549, "grad_norm": 4.343024253845215, "learning_rate": 6.098485972839387e-06, "loss": 0.1471, "step": 409260 }, { "epoch": 2.4327858718072175, "grad_norm": 3.7589879035949707, "learning_rate": 6.098283549190379e-06, "loss": 0.1316, "step": 409270 }, { "epoch": 2.432845313883886, "grad_norm": 4.337382793426514, "learning_rate": 6.098081123649995e-06, "loss": 0.1237, "step": 409280 }, { "epoch": 2.4329047559605543, "grad_norm": 5.276226997375488, "learning_rate": 6.097878696218583e-06, "loss": 0.1472, "step": 409290 }, { "epoch": 2.4329641980372227, "grad_norm": 4.514321804046631, "learning_rate": 6.097676266896495e-06, "loss": 0.1335, "step": 409300 }, { "epoch": 2.433023640113891, "grad_norm": 5.011469841003418, "learning_rate": 6.097473835684077e-06, "loss": 0.1534, "step": 409310 }, { "epoch": 2.4330830821905596, "grad_norm": 3.2297048568725586, "learning_rate": 6.097271402581677e-06, "loss": 0.153, "step": 409320 }, { "epoch": 2.433142524267228, "grad_norm": 3.4021103382110596, "learning_rate": 6.097068967589647e-06, "loss": 0.1489, "step": 409330 }, { "epoch": 2.433201966343896, "grad_norm": 4.178999423980713, "learning_rate": 6.096866530708332e-06, "loss": 0.1377, "step": 409340 }, { "epoch": 2.433261408420565, "grad_norm": 5.528926849365234, "learning_rate": 6.09666409193808e-06, "loss": 0.1362, "step": 409350 }, { "epoch": 2.433320850497233, "grad_norm": 4.482059001922607, "learning_rate": 6.0964616512792455e-06, "loss": 0.1364, "step": 409360 }, { "epoch": 2.433380292573901, "grad_norm": 4.620291233062744, "learning_rate": 6.096259208732172e-06, "loss": 0.143, "step": 409370 }, { "epoch": 2.4334397346505696, "grad_norm": 3.244929313659668, "learning_rate": 6.096056764297207e-06, "loss": 0.1438, "step": 409380 }, { "epoch": 2.433499176727238, "grad_norm": 5.131459712982178, "learning_rate": 6.095854317974703e-06, "loss": 0.1248, "step": 409390 }, { "epoch": 2.4335586188039064, "grad_norm": 5.417518138885498, "learning_rate": 6.095651869765007e-06, "loss": 0.1461, "step": 409400 }, { "epoch": 2.433618060880575, "grad_norm": 4.228542804718018, "learning_rate": 6.095449419668467e-06, "loss": 0.1376, "step": 409410 }, { "epoch": 2.4336775029572433, "grad_norm": 7.466996669769287, "learning_rate": 6.095246967685433e-06, "loss": 0.1465, "step": 409420 }, { "epoch": 2.4337369450339117, "grad_norm": 3.3901214599609375, "learning_rate": 6.0950445138162536e-06, "loss": 0.1204, "step": 409430 }, { "epoch": 2.43379638711058, "grad_norm": 4.4489336013793945, "learning_rate": 6.094842058061277e-06, "loss": 0.1354, "step": 409440 }, { "epoch": 2.4338558291872485, "grad_norm": 3.304490327835083, "learning_rate": 6.094639600420852e-06, "loss": 0.1301, "step": 409450 }, { "epoch": 2.433915271263917, "grad_norm": 3.8832767009735107, "learning_rate": 6.094437140895327e-06, "loss": 0.1294, "step": 409460 }, { "epoch": 2.4339747133405853, "grad_norm": 3.235848903656006, "learning_rate": 6.094234679485049e-06, "loss": 0.1263, "step": 409470 }, { "epoch": 2.4340341554172538, "grad_norm": 3.827785015106201, "learning_rate": 6.094032216190369e-06, "loss": 0.143, "step": 409480 }, { "epoch": 2.434093597493922, "grad_norm": 3.8274786472320557, "learning_rate": 6.0938297510116366e-06, "loss": 0.1287, "step": 409490 }, { "epoch": 2.4341530395705906, "grad_norm": 4.881637096405029, "learning_rate": 6.093627283949197e-06, "loss": 0.1326, "step": 409500 }, { "epoch": 2.434212481647259, "grad_norm": 4.45914363861084, "learning_rate": 6.0934248150034016e-06, "loss": 0.1274, "step": 409510 }, { "epoch": 2.4342719237239274, "grad_norm": 5.097972869873047, "learning_rate": 6.0932223441745965e-06, "loss": 0.141, "step": 409520 }, { "epoch": 2.4343313658005954, "grad_norm": 4.373089790344238, "learning_rate": 6.093019871463134e-06, "loss": 0.1317, "step": 409530 }, { "epoch": 2.434390807877264, "grad_norm": 3.926004409790039, "learning_rate": 6.09281739686936e-06, "loss": 0.1399, "step": 409540 }, { "epoch": 2.434450249953932, "grad_norm": 3.400186777114868, "learning_rate": 6.0926149203936245e-06, "loss": 0.1343, "step": 409550 }, { "epoch": 2.4345096920306006, "grad_norm": 2.953359842300415, "learning_rate": 6.092412442036276e-06, "loss": 0.1384, "step": 409560 }, { "epoch": 2.434569134107269, "grad_norm": 3.9663686752319336, "learning_rate": 6.092209961797663e-06, "loss": 0.1412, "step": 409570 }, { "epoch": 2.4346285761839375, "grad_norm": 3.8849501609802246, "learning_rate": 6.092007479678133e-06, "loss": 0.1342, "step": 409580 }, { "epoch": 2.434688018260606, "grad_norm": 4.903285503387451, "learning_rate": 6.091804995678037e-06, "loss": 0.1505, "step": 409590 }, { "epoch": 2.4347474603372743, "grad_norm": 3.0721545219421387, "learning_rate": 6.091602509797723e-06, "loss": 0.1397, "step": 409600 }, { "epoch": 2.4348069024139427, "grad_norm": 5.640276908874512, "learning_rate": 6.091400022037537e-06, "loss": 0.1683, "step": 409610 }, { "epoch": 2.434866344490611, "grad_norm": 4.322343349456787, "learning_rate": 6.09119753239783e-06, "loss": 0.1586, "step": 409620 }, { "epoch": 2.4349257865672795, "grad_norm": 4.042378902435303, "learning_rate": 6.090995040878953e-06, "loss": 0.1459, "step": 409630 }, { "epoch": 2.434985228643948, "grad_norm": 2.948446035385132, "learning_rate": 6.0907925474812515e-06, "loss": 0.1291, "step": 409640 }, { "epoch": 2.4350446707206164, "grad_norm": 4.17167854309082, "learning_rate": 6.090590052205074e-06, "loss": 0.1483, "step": 409650 }, { "epoch": 2.435104112797285, "grad_norm": 4.300951957702637, "learning_rate": 6.090387555050772e-06, "loss": 0.1398, "step": 409660 }, { "epoch": 2.435163554873953, "grad_norm": 4.582655429840088, "learning_rate": 6.090185056018691e-06, "loss": 0.1397, "step": 409670 }, { "epoch": 2.4352229969506216, "grad_norm": 3.688321113586426, "learning_rate": 6.089982555109182e-06, "loss": 0.1205, "step": 409680 }, { "epoch": 2.43528243902729, "grad_norm": 5.347986221313477, "learning_rate": 6.089780052322594e-06, "loss": 0.1496, "step": 409690 }, { "epoch": 2.4353418811039584, "grad_norm": 3.935231924057007, "learning_rate": 6.089577547659273e-06, "loss": 0.1501, "step": 409700 }, { "epoch": 2.435401323180627, "grad_norm": 4.079252243041992, "learning_rate": 6.08937504111957e-06, "loss": 0.141, "step": 409710 }, { "epoch": 2.435460765257295, "grad_norm": 5.1877617835998535, "learning_rate": 6.0891725327038335e-06, "loss": 0.1505, "step": 409720 }, { "epoch": 2.4355202073339632, "grad_norm": 4.652048587799072, "learning_rate": 6.0889700224124106e-06, "loss": 0.1615, "step": 409730 }, { "epoch": 2.4355796494106317, "grad_norm": 4.040478229522705, "learning_rate": 6.088767510245653e-06, "loss": 0.1623, "step": 409740 }, { "epoch": 2.4356390914873, "grad_norm": 3.90858793258667, "learning_rate": 6.088564996203907e-06, "loss": 0.1447, "step": 409750 }, { "epoch": 2.4356985335639685, "grad_norm": 4.251286029815674, "learning_rate": 6.088362480287523e-06, "loss": 0.1399, "step": 409760 }, { "epoch": 2.435757975640637, "grad_norm": 2.782069683074951, "learning_rate": 6.088159962496849e-06, "loss": 0.1318, "step": 409770 }, { "epoch": 2.4358174177173053, "grad_norm": 3.922189235687256, "learning_rate": 6.087957442832232e-06, "loss": 0.1426, "step": 409780 }, { "epoch": 2.4358768597939737, "grad_norm": 6.699240207672119, "learning_rate": 6.0877549212940244e-06, "loss": 0.1368, "step": 409790 }, { "epoch": 2.435936301870642, "grad_norm": 4.721102237701416, "learning_rate": 6.087552397882573e-06, "loss": 0.1544, "step": 409800 }, { "epoch": 2.4359957439473106, "grad_norm": 4.446881294250488, "learning_rate": 6.087349872598225e-06, "loss": 0.1301, "step": 409810 }, { "epoch": 2.436055186023979, "grad_norm": 3.9385955333709717, "learning_rate": 6.087147345441331e-06, "loss": 0.1314, "step": 409820 }, { "epoch": 2.4361146281006474, "grad_norm": 3.229325771331787, "learning_rate": 6.086944816412242e-06, "loss": 0.1359, "step": 409830 }, { "epoch": 2.436174070177316, "grad_norm": 3.7597453594207764, "learning_rate": 6.0867422855113e-06, "loss": 0.1331, "step": 409840 }, { "epoch": 2.436233512253984, "grad_norm": 3.366741418838501, "learning_rate": 6.086539752738861e-06, "loss": 0.1498, "step": 409850 }, { "epoch": 2.4362929543306526, "grad_norm": 3.316185712814331, "learning_rate": 6.086337218095271e-06, "loss": 0.1379, "step": 409860 }, { "epoch": 2.436352396407321, "grad_norm": 3.5908420085906982, "learning_rate": 6.086134681580877e-06, "loss": 0.1369, "step": 409870 }, { "epoch": 2.4364118384839895, "grad_norm": 3.3347978591918945, "learning_rate": 6.085932143196031e-06, "loss": 0.1313, "step": 409880 }, { "epoch": 2.4364712805606574, "grad_norm": 3.370001792907715, "learning_rate": 6.085729602941082e-06, "loss": 0.1432, "step": 409890 }, { "epoch": 2.4365307226373263, "grad_norm": 3.584653377532959, "learning_rate": 6.0855270608163745e-06, "loss": 0.151, "step": 409900 }, { "epoch": 2.4365901647139943, "grad_norm": 4.0077290534973145, "learning_rate": 6.085324516822259e-06, "loss": 0.1285, "step": 409910 }, { "epoch": 2.4366496067906627, "grad_norm": 3.9656450748443604, "learning_rate": 6.085121970959088e-06, "loss": 0.1338, "step": 409920 }, { "epoch": 2.436709048867331, "grad_norm": 3.453244924545288, "learning_rate": 6.084919423227207e-06, "loss": 0.1538, "step": 409930 }, { "epoch": 2.4367684909439995, "grad_norm": 4.313094615936279, "learning_rate": 6.084716873626964e-06, "loss": 0.1355, "step": 409940 }, { "epoch": 2.436827933020668, "grad_norm": 3.489670991897583, "learning_rate": 6.084514322158708e-06, "loss": 0.1139, "step": 409950 }, { "epoch": 2.4368873750973363, "grad_norm": 3.6549794673919678, "learning_rate": 6.0843117688227915e-06, "loss": 0.1357, "step": 409960 }, { "epoch": 2.4369468171740047, "grad_norm": 4.735940933227539, "learning_rate": 6.084109213619559e-06, "loss": 0.1491, "step": 409970 }, { "epoch": 2.437006259250673, "grad_norm": 4.088582992553711, "learning_rate": 6.083906656549362e-06, "loss": 0.1285, "step": 409980 }, { "epoch": 2.4370657013273416, "grad_norm": 4.758078098297119, "learning_rate": 6.083704097612549e-06, "loss": 0.1216, "step": 409990 }, { "epoch": 2.43712514340401, "grad_norm": 4.8057427406311035, "learning_rate": 6.083501536809466e-06, "loss": 0.1403, "step": 410000 }, { "epoch": 2.4371845854806784, "grad_norm": 4.181425094604492, "learning_rate": 6.083298974140466e-06, "loss": 0.1454, "step": 410010 }, { "epoch": 2.437244027557347, "grad_norm": 3.4056830406188965, "learning_rate": 6.0830964096058965e-06, "loss": 0.1311, "step": 410020 }, { "epoch": 2.4373034696340152, "grad_norm": 3.071408271789551, "learning_rate": 6.082893843206104e-06, "loss": 0.1265, "step": 410030 }, { "epoch": 2.4373629117106836, "grad_norm": 6.319204330444336, "learning_rate": 6.08269127494144e-06, "loss": 0.1562, "step": 410040 }, { "epoch": 2.437422353787352, "grad_norm": 3.896061658859253, "learning_rate": 6.082488704812252e-06, "loss": 0.1512, "step": 410050 }, { "epoch": 2.4374817958640205, "grad_norm": 4.742677688598633, "learning_rate": 6.08228613281889e-06, "loss": 0.1363, "step": 410060 }, { "epoch": 2.437541237940689, "grad_norm": 6.043375492095947, "learning_rate": 6.0820835589617e-06, "loss": 0.1371, "step": 410070 }, { "epoch": 2.437600680017357, "grad_norm": 4.115119934082031, "learning_rate": 6.081880983241035e-06, "loss": 0.1533, "step": 410080 }, { "epoch": 2.4376601220940257, "grad_norm": 4.5523858070373535, "learning_rate": 6.081678405657243e-06, "loss": 0.1218, "step": 410090 }, { "epoch": 2.4377195641706937, "grad_norm": 4.824442386627197, "learning_rate": 6.0814758262106684e-06, "loss": 0.148, "step": 410100 }, { "epoch": 2.437779006247362, "grad_norm": 4.618951797485352, "learning_rate": 6.081273244901666e-06, "loss": 0.1357, "step": 410110 }, { "epoch": 2.4378384483240305, "grad_norm": 3.8717942237854004, "learning_rate": 6.0810706617305815e-06, "loss": 0.1438, "step": 410120 }, { "epoch": 2.437897890400699, "grad_norm": 4.760725498199463, "learning_rate": 6.080868076697763e-06, "loss": 0.1381, "step": 410130 }, { "epoch": 2.4379573324773673, "grad_norm": 5.154508590698242, "learning_rate": 6.080665489803563e-06, "loss": 0.1474, "step": 410140 }, { "epoch": 2.4380167745540358, "grad_norm": 4.692230224609375, "learning_rate": 6.080462901048327e-06, "loss": 0.1296, "step": 410150 }, { "epoch": 2.438076216630704, "grad_norm": 4.480837821960449, "learning_rate": 6.080260310432405e-06, "loss": 0.1541, "step": 410160 }, { "epoch": 2.4381356587073726, "grad_norm": 3.82073712348938, "learning_rate": 6.080057717956145e-06, "loss": 0.1234, "step": 410170 }, { "epoch": 2.438195100784041, "grad_norm": 4.343739032745361, "learning_rate": 6.079855123619898e-06, "loss": 0.1325, "step": 410180 }, { "epoch": 2.4382545428607094, "grad_norm": 5.395694732666016, "learning_rate": 6.079652527424012e-06, "loss": 0.1412, "step": 410190 }, { "epoch": 2.438313984937378, "grad_norm": 3.592122793197632, "learning_rate": 6.079449929368834e-06, "loss": 0.1407, "step": 410200 }, { "epoch": 2.4383734270140462, "grad_norm": 4.0669355392456055, "learning_rate": 6.079247329454715e-06, "loss": 0.1455, "step": 410210 }, { "epoch": 2.4384328690907147, "grad_norm": 6.006577968597412, "learning_rate": 6.079044727682003e-06, "loss": 0.1498, "step": 410220 }, { "epoch": 2.438492311167383, "grad_norm": 4.735743999481201, "learning_rate": 6.078842124051047e-06, "loss": 0.1403, "step": 410230 }, { "epoch": 2.4385517532440515, "grad_norm": 4.533971786499023, "learning_rate": 6.078639518562197e-06, "loss": 0.1431, "step": 410240 }, { "epoch": 2.43861119532072, "grad_norm": 4.533516883850098, "learning_rate": 6.078436911215802e-06, "loss": 0.1433, "step": 410250 }, { "epoch": 2.4386706373973883, "grad_norm": 5.6036176681518555, "learning_rate": 6.078234302012208e-06, "loss": 0.134, "step": 410260 }, { "epoch": 2.4387300794740563, "grad_norm": 3.9115169048309326, "learning_rate": 6.0780316909517665e-06, "loss": 0.1327, "step": 410270 }, { "epoch": 2.4387895215507247, "grad_norm": 4.149916648864746, "learning_rate": 6.077829078034826e-06, "loss": 0.1408, "step": 410280 }, { "epoch": 2.438848963627393, "grad_norm": 4.671107292175293, "learning_rate": 6.077626463261736e-06, "loss": 0.1529, "step": 410290 }, { "epoch": 2.4389084057040615, "grad_norm": 3.3922781944274902, "learning_rate": 6.077423846632843e-06, "loss": 0.1272, "step": 410300 }, { "epoch": 2.43896784778073, "grad_norm": 4.244992733001709, "learning_rate": 6.077221228148498e-06, "loss": 0.1627, "step": 410310 }, { "epoch": 2.4390272898573984, "grad_norm": 3.6497232913970947, "learning_rate": 6.077018607809051e-06, "loss": 0.1293, "step": 410320 }, { "epoch": 2.4390867319340668, "grad_norm": 4.43533992767334, "learning_rate": 6.076815985614847e-06, "loss": 0.1463, "step": 410330 }, { "epoch": 2.439146174010735, "grad_norm": 4.17857027053833, "learning_rate": 6.076613361566239e-06, "loss": 0.1289, "step": 410340 }, { "epoch": 2.4392056160874036, "grad_norm": 3.79853892326355, "learning_rate": 6.0764107356635746e-06, "loss": 0.1375, "step": 410350 }, { "epoch": 2.439265058164072, "grad_norm": 4.642568111419678, "learning_rate": 6.076208107907201e-06, "loss": 0.1419, "step": 410360 }, { "epoch": 2.4393245002407404, "grad_norm": 4.359955310821533, "learning_rate": 6.076005478297471e-06, "loss": 0.1284, "step": 410370 }, { "epoch": 2.439383942317409, "grad_norm": 5.201727867126465, "learning_rate": 6.07580284683473e-06, "loss": 0.1312, "step": 410380 }, { "epoch": 2.4394433843940773, "grad_norm": 3.901606798171997, "learning_rate": 6.075600213519327e-06, "loss": 0.1318, "step": 410390 }, { "epoch": 2.4395028264707457, "grad_norm": 3.5841269493103027, "learning_rate": 6.075397578351612e-06, "loss": 0.1521, "step": 410400 }, { "epoch": 2.439562268547414, "grad_norm": 4.481476783752441, "learning_rate": 6.075194941331935e-06, "loss": 0.1313, "step": 410410 }, { "epoch": 2.4396217106240825, "grad_norm": 4.054304122924805, "learning_rate": 6.074992302460645e-06, "loss": 0.1257, "step": 410420 }, { "epoch": 2.439681152700751, "grad_norm": 3.1952877044677734, "learning_rate": 6.074789661738089e-06, "loss": 0.1507, "step": 410430 }, { "epoch": 2.4397405947774193, "grad_norm": 4.012556552886963, "learning_rate": 6.074587019164617e-06, "loss": 0.1311, "step": 410440 }, { "epoch": 2.4398000368540878, "grad_norm": 3.1846067905426025, "learning_rate": 6.074384374740579e-06, "loss": 0.1313, "step": 410450 }, { "epoch": 2.4398594789307557, "grad_norm": 3.7496938705444336, "learning_rate": 6.0741817284663204e-06, "loss": 0.1353, "step": 410460 }, { "epoch": 2.439918921007424, "grad_norm": 6.3178229331970215, "learning_rate": 6.073979080342195e-06, "loss": 0.1344, "step": 410470 }, { "epoch": 2.4399783630840925, "grad_norm": 4.713691711425781, "learning_rate": 6.073776430368549e-06, "loss": 0.1369, "step": 410480 }, { "epoch": 2.440037805160761, "grad_norm": 4.492689609527588, "learning_rate": 6.073573778545731e-06, "loss": 0.1356, "step": 410490 }, { "epoch": 2.4400972472374294, "grad_norm": 4.232572555541992, "learning_rate": 6.07337112487409e-06, "loss": 0.1483, "step": 410500 }, { "epoch": 2.440156689314098, "grad_norm": 3.991640567779541, "learning_rate": 6.073168469353978e-06, "loss": 0.131, "step": 410510 }, { "epoch": 2.440216131390766, "grad_norm": 3.713212490081787, "learning_rate": 6.07296581198574e-06, "loss": 0.1254, "step": 410520 }, { "epoch": 2.4402755734674346, "grad_norm": 3.7473020553588867, "learning_rate": 6.072763152769728e-06, "loss": 0.1278, "step": 410530 }, { "epoch": 2.440335015544103, "grad_norm": 2.7238056659698486, "learning_rate": 6.072560491706291e-06, "loss": 0.1313, "step": 410540 }, { "epoch": 2.4403944576207715, "grad_norm": 3.6862361431121826, "learning_rate": 6.072357828795774e-06, "loss": 0.1272, "step": 410550 }, { "epoch": 2.44045389969744, "grad_norm": 3.5181097984313965, "learning_rate": 6.072155164038531e-06, "loss": 0.1458, "step": 410560 }, { "epoch": 2.4405133417741083, "grad_norm": 3.932903528213501, "learning_rate": 6.0719524974349095e-06, "loss": 0.1345, "step": 410570 }, { "epoch": 2.4405727838507767, "grad_norm": 3.866936445236206, "learning_rate": 6.0717498289852574e-06, "loss": 0.1397, "step": 410580 }, { "epoch": 2.440632225927445, "grad_norm": 4.902492523193359, "learning_rate": 6.071547158689922e-06, "loss": 0.1215, "step": 410590 }, { "epoch": 2.4406916680041135, "grad_norm": 5.342259883880615, "learning_rate": 6.071344486549256e-06, "loss": 0.1637, "step": 410600 }, { "epoch": 2.440751110080782, "grad_norm": 4.841603755950928, "learning_rate": 6.071141812563608e-06, "loss": 0.1551, "step": 410610 }, { "epoch": 2.4408105521574504, "grad_norm": 4.025302886962891, "learning_rate": 6.070939136733323e-06, "loss": 0.1277, "step": 410620 }, { "epoch": 2.4408699942341183, "grad_norm": 5.020812511444092, "learning_rate": 6.070736459058756e-06, "loss": 0.1331, "step": 410630 }, { "epoch": 2.440929436310787, "grad_norm": 4.097865581512451, "learning_rate": 6.070533779540253e-06, "loss": 0.133, "step": 410640 }, { "epoch": 2.440988878387455, "grad_norm": 6.072423458099365, "learning_rate": 6.070331098178162e-06, "loss": 0.1359, "step": 410650 }, { "epoch": 2.4410483204641236, "grad_norm": 2.8721907138824463, "learning_rate": 6.070128414972833e-06, "loss": 0.1395, "step": 410660 }, { "epoch": 2.441107762540792, "grad_norm": 3.7988030910491943, "learning_rate": 6.069925729924616e-06, "loss": 0.1453, "step": 410670 }, { "epoch": 2.4411672046174604, "grad_norm": 3.9566774368286133, "learning_rate": 6.069723043033858e-06, "loss": 0.1314, "step": 410680 }, { "epoch": 2.441226646694129, "grad_norm": 5.096601963043213, "learning_rate": 6.069520354300911e-06, "loss": 0.1424, "step": 410690 }, { "epoch": 2.4412860887707972, "grad_norm": 4.60183572769165, "learning_rate": 6.069317663726122e-06, "loss": 0.1375, "step": 410700 }, { "epoch": 2.4413455308474656, "grad_norm": 4.222866535186768, "learning_rate": 6.069114971309838e-06, "loss": 0.1504, "step": 410710 }, { "epoch": 2.441404972924134, "grad_norm": 3.3182568550109863, "learning_rate": 6.068912277052412e-06, "loss": 0.1403, "step": 410720 }, { "epoch": 2.4414644150008025, "grad_norm": 3.92322039604187, "learning_rate": 6.068709580954193e-06, "loss": 0.1454, "step": 410730 }, { "epoch": 2.441523857077471, "grad_norm": 5.186154365539551, "learning_rate": 6.068506883015527e-06, "loss": 0.1431, "step": 410740 }, { "epoch": 2.4415832991541393, "grad_norm": 3.9620132446289062, "learning_rate": 6.068304183236765e-06, "loss": 0.1389, "step": 410750 }, { "epoch": 2.4416427412308077, "grad_norm": 4.660873889923096, "learning_rate": 6.068101481618256e-06, "loss": 0.1636, "step": 410760 }, { "epoch": 2.441702183307476, "grad_norm": 3.789789915084839, "learning_rate": 6.067898778160348e-06, "loss": 0.1438, "step": 410770 }, { "epoch": 2.4417616253841445, "grad_norm": 4.204741477966309, "learning_rate": 6.067696072863391e-06, "loss": 0.1409, "step": 410780 }, { "epoch": 2.441821067460813, "grad_norm": 4.767190933227539, "learning_rate": 6.0674933657277355e-06, "loss": 0.1528, "step": 410790 }, { "epoch": 2.4418805095374814, "grad_norm": 3.728131055831909, "learning_rate": 6.067290656753728e-06, "loss": 0.1475, "step": 410800 }, { "epoch": 2.44193995161415, "grad_norm": 4.340936183929443, "learning_rate": 6.067087945941719e-06, "loss": 0.1343, "step": 410810 }, { "epoch": 2.4419993936908178, "grad_norm": 4.427860736846924, "learning_rate": 6.0668852332920565e-06, "loss": 0.1374, "step": 410820 }, { "epoch": 2.4420588357674866, "grad_norm": 4.365115165710449, "learning_rate": 6.066682518805089e-06, "loss": 0.1343, "step": 410830 }, { "epoch": 2.4421182778441546, "grad_norm": 5.117641925811768, "learning_rate": 6.06647980248117e-06, "loss": 0.1353, "step": 410840 }, { "epoch": 2.442177719920823, "grad_norm": 5.714690208435059, "learning_rate": 6.066277084320643e-06, "loss": 0.1367, "step": 410850 }, { "epoch": 2.4422371619974914, "grad_norm": 5.575603008270264, "learning_rate": 6.066074364323861e-06, "loss": 0.1526, "step": 410860 }, { "epoch": 2.44229660407416, "grad_norm": 3.5646204948425293, "learning_rate": 6.0658716424911725e-06, "loss": 0.1284, "step": 410870 }, { "epoch": 2.4423560461508282, "grad_norm": 4.526223182678223, "learning_rate": 6.065668918822924e-06, "loss": 0.1458, "step": 410880 }, { "epoch": 2.4424154882274967, "grad_norm": 3.9191277027130127, "learning_rate": 6.065466193319468e-06, "loss": 0.128, "step": 410890 }, { "epoch": 2.442474930304165, "grad_norm": 4.38231086730957, "learning_rate": 6.065263465981151e-06, "loss": 0.127, "step": 410900 }, { "epoch": 2.4425343723808335, "grad_norm": 2.4652156829833984, "learning_rate": 6.065060736808324e-06, "loss": 0.1424, "step": 410910 }, { "epoch": 2.442593814457502, "grad_norm": 3.944035291671753, "learning_rate": 6.064858005801335e-06, "loss": 0.1596, "step": 410920 }, { "epoch": 2.4426532565341703, "grad_norm": 4.082597732543945, "learning_rate": 6.064655272960534e-06, "loss": 0.1309, "step": 410930 }, { "epoch": 2.4427126986108387, "grad_norm": 3.184898614883423, "learning_rate": 6.064452538286268e-06, "loss": 0.1362, "step": 410940 }, { "epoch": 2.442772140687507, "grad_norm": 4.592405796051025, "learning_rate": 6.0642498017788875e-06, "loss": 0.1412, "step": 410950 }, { "epoch": 2.4428315827641756, "grad_norm": 4.090991973876953, "learning_rate": 6.064047063438744e-06, "loss": 0.1645, "step": 410960 }, { "epoch": 2.442891024840844, "grad_norm": 4.002322196960449, "learning_rate": 6.063844323266184e-06, "loss": 0.1325, "step": 410970 }, { "epoch": 2.4429504669175124, "grad_norm": 3.2550768852233887, "learning_rate": 6.063641581261556e-06, "loss": 0.13, "step": 410980 }, { "epoch": 2.443009908994181, "grad_norm": 4.608033657073975, "learning_rate": 6.063438837425212e-06, "loss": 0.1466, "step": 410990 }, { "epoch": 2.443069351070849, "grad_norm": 5.476050853729248, "learning_rate": 6.063236091757499e-06, "loss": 0.1338, "step": 411000 }, { "epoch": 2.443128793147517, "grad_norm": 4.46807336807251, "learning_rate": 6.063033344258764e-06, "loss": 0.1494, "step": 411010 }, { "epoch": 2.4431882352241856, "grad_norm": 4.047745704650879, "learning_rate": 6.062830594929362e-06, "loss": 0.1473, "step": 411020 }, { "epoch": 2.443247677300854, "grad_norm": 5.229569911956787, "learning_rate": 6.062627843769638e-06, "loss": 0.1476, "step": 411030 }, { "epoch": 2.4433071193775224, "grad_norm": 5.669943332672119, "learning_rate": 6.062425090779941e-06, "loss": 0.1398, "step": 411040 }, { "epoch": 2.443366561454191, "grad_norm": 3.819669008255005, "learning_rate": 6.062222335960621e-06, "loss": 0.1357, "step": 411050 }, { "epoch": 2.4434260035308593, "grad_norm": 4.524560928344727, "learning_rate": 6.062019579312029e-06, "loss": 0.1441, "step": 411060 }, { "epoch": 2.4434854456075277, "grad_norm": 4.126293182373047, "learning_rate": 6.061816820834512e-06, "loss": 0.1485, "step": 411070 }, { "epoch": 2.443544887684196, "grad_norm": 3.282318115234375, "learning_rate": 6.061614060528419e-06, "loss": 0.1439, "step": 411080 }, { "epoch": 2.4436043297608645, "grad_norm": 4.342372417449951, "learning_rate": 6.061411298394101e-06, "loss": 0.1465, "step": 411090 }, { "epoch": 2.443663771837533, "grad_norm": 4.368567943572998, "learning_rate": 6.061208534431906e-06, "loss": 0.129, "step": 411100 }, { "epoch": 2.4437232139142013, "grad_norm": 4.973949432373047, "learning_rate": 6.061005768642183e-06, "loss": 0.1339, "step": 411110 }, { "epoch": 2.4437826559908697, "grad_norm": 3.1040596961975098, "learning_rate": 6.060803001025281e-06, "loss": 0.1273, "step": 411120 }, { "epoch": 2.443842098067538, "grad_norm": 3.5182580947875977, "learning_rate": 6.0606002315815505e-06, "loss": 0.1215, "step": 411130 }, { "epoch": 2.4439015401442066, "grad_norm": 3.1674015522003174, "learning_rate": 6.060397460311339e-06, "loss": 0.1467, "step": 411140 }, { "epoch": 2.443960982220875, "grad_norm": 4.826974868774414, "learning_rate": 6.060194687214997e-06, "loss": 0.1436, "step": 411150 }, { "epoch": 2.4440204242975434, "grad_norm": 4.739911079406738, "learning_rate": 6.059991912292873e-06, "loss": 0.1434, "step": 411160 }, { "epoch": 2.444079866374212, "grad_norm": 4.716278076171875, "learning_rate": 6.0597891355453165e-06, "loss": 0.1727, "step": 411170 }, { "epoch": 2.4441393084508802, "grad_norm": 2.887608051300049, "learning_rate": 6.059586356972676e-06, "loss": 0.1263, "step": 411180 }, { "epoch": 2.4441987505275486, "grad_norm": 5.130666732788086, "learning_rate": 6.059383576575304e-06, "loss": 0.1288, "step": 411190 }, { "epoch": 2.4442581926042166, "grad_norm": 4.579578876495361, "learning_rate": 6.059180794353544e-06, "loss": 0.1412, "step": 411200 }, { "epoch": 2.444317634680885, "grad_norm": 3.4039525985717773, "learning_rate": 6.05897801030775e-06, "loss": 0.1481, "step": 411210 }, { "epoch": 2.4443770767575534, "grad_norm": 3.199251174926758, "learning_rate": 6.0587752244382695e-06, "loss": 0.1416, "step": 411220 }, { "epoch": 2.444436518834222, "grad_norm": 4.101109027862549, "learning_rate": 6.058572436745451e-06, "loss": 0.1359, "step": 411230 }, { "epoch": 2.4444959609108903, "grad_norm": 4.607293605804443, "learning_rate": 6.058369647229645e-06, "loss": 0.1512, "step": 411240 }, { "epoch": 2.4445554029875587, "grad_norm": 4.042903423309326, "learning_rate": 6.0581668558912e-06, "loss": 0.1222, "step": 411250 }, { "epoch": 2.444614845064227, "grad_norm": 4.608302593231201, "learning_rate": 6.057964062730466e-06, "loss": 0.1324, "step": 411260 }, { "epoch": 2.4446742871408955, "grad_norm": 5.106414794921875, "learning_rate": 6.0577612677477895e-06, "loss": 0.1559, "step": 411270 }, { "epoch": 2.444733729217564, "grad_norm": 4.002281665802002, "learning_rate": 6.057558470943523e-06, "loss": 0.138, "step": 411280 }, { "epoch": 2.4447931712942323, "grad_norm": 4.091476917266846, "learning_rate": 6.057355672318016e-06, "loss": 0.1437, "step": 411290 }, { "epoch": 2.4448526133709008, "grad_norm": 4.330977439880371, "learning_rate": 6.057152871871615e-06, "loss": 0.1438, "step": 411300 }, { "epoch": 2.444912055447569, "grad_norm": 3.9385600090026855, "learning_rate": 6.056950069604671e-06, "loss": 0.1327, "step": 411310 }, { "epoch": 2.4449714975242376, "grad_norm": 4.358001232147217, "learning_rate": 6.056747265517533e-06, "loss": 0.1593, "step": 411320 }, { "epoch": 2.445030939600906, "grad_norm": 4.509601593017578, "learning_rate": 6.05654445961055e-06, "loss": 0.1351, "step": 411330 }, { "epoch": 2.4450903816775744, "grad_norm": 4.8187384605407715, "learning_rate": 6.0563416518840715e-06, "loss": 0.1398, "step": 411340 }, { "epoch": 2.445149823754243, "grad_norm": 3.770310878753662, "learning_rate": 6.056138842338447e-06, "loss": 0.1476, "step": 411350 }, { "epoch": 2.4452092658309112, "grad_norm": 4.271846294403076, "learning_rate": 6.055936030974025e-06, "loss": 0.1448, "step": 411360 }, { "epoch": 2.445268707907579, "grad_norm": 4.955462455749512, "learning_rate": 6.055733217791155e-06, "loss": 0.1384, "step": 411370 }, { "epoch": 2.445328149984248, "grad_norm": 4.348530292510986, "learning_rate": 6.055530402790186e-06, "loss": 0.1315, "step": 411380 }, { "epoch": 2.445387592060916, "grad_norm": 3.517117977142334, "learning_rate": 6.055327585971469e-06, "loss": 0.1379, "step": 411390 }, { "epoch": 2.4454470341375845, "grad_norm": 4.274620056152344, "learning_rate": 6.05512476733535e-06, "loss": 0.1333, "step": 411400 }, { "epoch": 2.445506476214253, "grad_norm": 2.795746326446533, "learning_rate": 6.0549219468821815e-06, "loss": 0.1246, "step": 411410 }, { "epoch": 2.4455659182909213, "grad_norm": 4.3017144203186035, "learning_rate": 6.054719124612312e-06, "loss": 0.1191, "step": 411420 }, { "epoch": 2.4456253603675897, "grad_norm": 4.081762790679932, "learning_rate": 6.054516300526088e-06, "loss": 0.1225, "step": 411430 }, { "epoch": 2.445684802444258, "grad_norm": 4.894952774047852, "learning_rate": 6.0543134746238645e-06, "loss": 0.1451, "step": 411440 }, { "epoch": 2.4457442445209265, "grad_norm": 4.174247741699219, "learning_rate": 6.0541106469059865e-06, "loss": 0.1437, "step": 411450 }, { "epoch": 2.445803686597595, "grad_norm": 5.12284517288208, "learning_rate": 6.0539078173728025e-06, "loss": 0.1394, "step": 411460 }, { "epoch": 2.4458631286742634, "grad_norm": 5.125446796417236, "learning_rate": 6.053704986024664e-06, "loss": 0.1434, "step": 411470 }, { "epoch": 2.445922570750932, "grad_norm": 3.431278944015503, "learning_rate": 6.053502152861922e-06, "loss": 0.1139, "step": 411480 }, { "epoch": 2.4459820128276, "grad_norm": 3.0055675506591797, "learning_rate": 6.053299317884921e-06, "loss": 0.1086, "step": 411490 }, { "epoch": 2.4460414549042686, "grad_norm": 3.9534218311309814, "learning_rate": 6.053096481094013e-06, "loss": 0.1464, "step": 411500 }, { "epoch": 2.446100896980937, "grad_norm": 4.061847686767578, "learning_rate": 6.052893642489548e-06, "loss": 0.1497, "step": 411510 }, { "epoch": 2.4461603390576054, "grad_norm": 4.652873992919922, "learning_rate": 6.052690802071876e-06, "loss": 0.1463, "step": 411520 }, { "epoch": 2.446219781134274, "grad_norm": 4.506309509277344, "learning_rate": 6.052487959841342e-06, "loss": 0.1557, "step": 411530 }, { "epoch": 2.4462792232109423, "grad_norm": 5.022301197052002, "learning_rate": 6.0522851157983e-06, "loss": 0.1547, "step": 411540 }, { "epoch": 2.4463386652876107, "grad_norm": 4.634220123291016, "learning_rate": 6.052082269943097e-06, "loss": 0.1411, "step": 411550 }, { "epoch": 2.4463981073642787, "grad_norm": 3.8965353965759277, "learning_rate": 6.0518794222760825e-06, "loss": 0.1329, "step": 411560 }, { "epoch": 2.4464575494409475, "grad_norm": 4.572114944458008, "learning_rate": 6.051676572797607e-06, "loss": 0.1471, "step": 411570 }, { "epoch": 2.4465169915176155, "grad_norm": 4.139667987823486, "learning_rate": 6.051473721508018e-06, "loss": 0.1416, "step": 411580 }, { "epoch": 2.446576433594284, "grad_norm": 4.402398109436035, "learning_rate": 6.051270868407666e-06, "loss": 0.127, "step": 411590 }, { "epoch": 2.4466358756709523, "grad_norm": 4.195700645446777, "learning_rate": 6.0510680134968995e-06, "loss": 0.1287, "step": 411600 }, { "epoch": 2.4466953177476207, "grad_norm": 2.452345609664917, "learning_rate": 6.050865156776069e-06, "loss": 0.1402, "step": 411610 }, { "epoch": 2.446754759824289, "grad_norm": 4.485016345977783, "learning_rate": 6.050662298245524e-06, "loss": 0.1459, "step": 411620 }, { "epoch": 2.4468142019009576, "grad_norm": 4.967614650726318, "learning_rate": 6.050459437905612e-06, "loss": 0.1288, "step": 411630 }, { "epoch": 2.446873643977626, "grad_norm": 3.723127841949463, "learning_rate": 6.050256575756684e-06, "loss": 0.1497, "step": 411640 }, { "epoch": 2.4469330860542944, "grad_norm": 3.3219165802001953, "learning_rate": 6.050053711799091e-06, "loss": 0.1297, "step": 411650 }, { "epoch": 2.446992528130963, "grad_norm": 4.211421489715576, "learning_rate": 6.0498508460331775e-06, "loss": 0.1311, "step": 411660 }, { "epoch": 2.447051970207631, "grad_norm": 7.533438682556152, "learning_rate": 6.049647978459297e-06, "loss": 0.1458, "step": 411670 }, { "epoch": 2.4471114122842996, "grad_norm": 4.878880023956299, "learning_rate": 6.049445109077796e-06, "loss": 0.1533, "step": 411680 }, { "epoch": 2.447170854360968, "grad_norm": 4.257019519805908, "learning_rate": 6.049242237889026e-06, "loss": 0.1386, "step": 411690 }, { "epoch": 2.4472302964376365, "grad_norm": 3.1508424282073975, "learning_rate": 6.049039364893337e-06, "loss": 0.1236, "step": 411700 }, { "epoch": 2.447289738514305, "grad_norm": 4.003654956817627, "learning_rate": 6.048836490091074e-06, "loss": 0.1362, "step": 411710 }, { "epoch": 2.4473491805909733, "grad_norm": 5.555492401123047, "learning_rate": 6.048633613482592e-06, "loss": 0.1588, "step": 411720 }, { "epoch": 2.4474086226676417, "grad_norm": 3.325774669647217, "learning_rate": 6.048430735068236e-06, "loss": 0.1267, "step": 411730 }, { "epoch": 2.44746806474431, "grad_norm": 5.006260395050049, "learning_rate": 6.048227854848359e-06, "loss": 0.1396, "step": 411740 }, { "epoch": 2.447527506820978, "grad_norm": 4.896590709686279, "learning_rate": 6.0480249728233075e-06, "loss": 0.1428, "step": 411750 }, { "epoch": 2.4475869488976465, "grad_norm": 4.487758636474609, "learning_rate": 6.047822088993433e-06, "loss": 0.1386, "step": 411760 }, { "epoch": 2.447646390974315, "grad_norm": 4.003533363342285, "learning_rate": 6.047619203359083e-06, "loss": 0.1399, "step": 411770 }, { "epoch": 2.4477058330509833, "grad_norm": 3.9998250007629395, "learning_rate": 6.047416315920608e-06, "loss": 0.1679, "step": 411780 }, { "epoch": 2.4477652751276517, "grad_norm": 4.504044055938721, "learning_rate": 6.047213426678355e-06, "loss": 0.1331, "step": 411790 }, { "epoch": 2.44782471720432, "grad_norm": 3.940901279449463, "learning_rate": 6.047010535632679e-06, "loss": 0.1195, "step": 411800 }, { "epoch": 2.4478841592809886, "grad_norm": 4.849025249481201, "learning_rate": 6.0468076427839254e-06, "loss": 0.1407, "step": 411810 }, { "epoch": 2.447943601357657, "grad_norm": 6.750794887542725, "learning_rate": 6.046604748132441e-06, "loss": 0.1351, "step": 411820 }, { "epoch": 2.4480030434343254, "grad_norm": 2.885211229324341, "learning_rate": 6.04640185167858e-06, "loss": 0.1287, "step": 411830 }, { "epoch": 2.448062485510994, "grad_norm": 6.675425052642822, "learning_rate": 6.046198953422692e-06, "loss": 0.1424, "step": 411840 }, { "epoch": 2.4481219275876622, "grad_norm": 5.167107105255127, "learning_rate": 6.045996053365122e-06, "loss": 0.1284, "step": 411850 }, { "epoch": 2.4481813696643306, "grad_norm": 5.07210636138916, "learning_rate": 6.045793151506224e-06, "loss": 0.1514, "step": 411860 }, { "epoch": 2.448240811740999, "grad_norm": 4.519863605499268, "learning_rate": 6.045590247846344e-06, "loss": 0.1454, "step": 411870 }, { "epoch": 2.4483002538176675, "grad_norm": 5.275579929351807, "learning_rate": 6.0453873423858335e-06, "loss": 0.1601, "step": 411880 }, { "epoch": 2.448359695894336, "grad_norm": 4.835862636566162, "learning_rate": 6.045184435125041e-06, "loss": 0.1437, "step": 411890 }, { "epoch": 2.4484191379710043, "grad_norm": 3.9665277004241943, "learning_rate": 6.044981526064318e-06, "loss": 0.1393, "step": 411900 }, { "epoch": 2.4484785800476727, "grad_norm": 4.7375383377075195, "learning_rate": 6.04477861520401e-06, "loss": 0.1412, "step": 411910 }, { "epoch": 2.448538022124341, "grad_norm": 4.584240913391113, "learning_rate": 6.044575702544468e-06, "loss": 0.1342, "step": 411920 }, { "epoch": 2.4485974642010095, "grad_norm": 4.961369037628174, "learning_rate": 6.0443727880860425e-06, "loss": 0.1352, "step": 411930 }, { "epoch": 2.4486569062776775, "grad_norm": 4.110854148864746, "learning_rate": 6.0441698718290845e-06, "loss": 0.144, "step": 411940 }, { "epoch": 2.448716348354346, "grad_norm": 4.6571149826049805, "learning_rate": 6.043966953773939e-06, "loss": 0.1454, "step": 411950 }, { "epoch": 2.4487757904310143, "grad_norm": 3.5465123653411865, "learning_rate": 6.043764033920959e-06, "loss": 0.1317, "step": 411960 }, { "epoch": 2.4488352325076828, "grad_norm": 4.318552017211914, "learning_rate": 6.043561112270493e-06, "loss": 0.1286, "step": 411970 }, { "epoch": 2.448894674584351, "grad_norm": 3.6715502738952637, "learning_rate": 6.043358188822889e-06, "loss": 0.1364, "step": 411980 }, { "epoch": 2.4489541166610196, "grad_norm": 4.142407417297363, "learning_rate": 6.043155263578498e-06, "loss": 0.1355, "step": 411990 }, { "epoch": 2.449013558737688, "grad_norm": 3.6214137077331543, "learning_rate": 6.0429523365376706e-06, "loss": 0.1296, "step": 412000 }, { "epoch": 2.4490730008143564, "grad_norm": 3.5751588344573975, "learning_rate": 6.042749407700753e-06, "loss": 0.1409, "step": 412010 }, { "epoch": 2.449132442891025, "grad_norm": 3.755246162414551, "learning_rate": 6.042546477068099e-06, "loss": 0.1408, "step": 412020 }, { "epoch": 2.4491918849676932, "grad_norm": 5.26229190826416, "learning_rate": 6.042343544640054e-06, "loss": 0.1696, "step": 412030 }, { "epoch": 2.4492513270443617, "grad_norm": 3.9979164600372314, "learning_rate": 6.042140610416968e-06, "loss": 0.1446, "step": 412040 }, { "epoch": 2.44931076912103, "grad_norm": 4.1011223793029785, "learning_rate": 6.041937674399192e-06, "loss": 0.1319, "step": 412050 }, { "epoch": 2.4493702111976985, "grad_norm": 4.221124172210693, "learning_rate": 6.041734736587076e-06, "loss": 0.1268, "step": 412060 }, { "epoch": 2.449429653274367, "grad_norm": 4.507111072540283, "learning_rate": 6.0415317969809686e-06, "loss": 0.136, "step": 412070 }, { "epoch": 2.4494890953510353, "grad_norm": 4.34951114654541, "learning_rate": 6.041328855581217e-06, "loss": 0.1315, "step": 412080 }, { "epoch": 2.4495485374277037, "grad_norm": 4.141941070556641, "learning_rate": 6.041125912388176e-06, "loss": 0.1269, "step": 412090 }, { "epoch": 2.449607979504372, "grad_norm": 5.187137126922607, "learning_rate": 6.040922967402191e-06, "loss": 0.1412, "step": 412100 }, { "epoch": 2.44966742158104, "grad_norm": 4.094660758972168, "learning_rate": 6.040720020623611e-06, "loss": 0.1259, "step": 412110 }, { "epoch": 2.449726863657709, "grad_norm": 3.7057650089263916, "learning_rate": 6.040517072052787e-06, "loss": 0.1414, "step": 412120 }, { "epoch": 2.449786305734377, "grad_norm": 4.916333198547363, "learning_rate": 6.04031412169007e-06, "loss": 0.1553, "step": 412130 }, { "epoch": 2.4498457478110454, "grad_norm": 4.063852787017822, "learning_rate": 6.040111169535807e-06, "loss": 0.1219, "step": 412140 }, { "epoch": 2.4499051898877138, "grad_norm": 3.531229019165039, "learning_rate": 6.0399082155903475e-06, "loss": 0.1347, "step": 412150 }, { "epoch": 2.449964631964382, "grad_norm": 3.8456008434295654, "learning_rate": 6.039705259854044e-06, "loss": 0.1338, "step": 412160 }, { "epoch": 2.4500240740410506, "grad_norm": 4.016291618347168, "learning_rate": 6.039502302327244e-06, "loss": 0.1368, "step": 412170 }, { "epoch": 2.450083516117719, "grad_norm": 4.290737628936768, "learning_rate": 6.0392993430102955e-06, "loss": 0.1336, "step": 412180 }, { "epoch": 2.4501429581943874, "grad_norm": 4.089150905609131, "learning_rate": 6.039096381903551e-06, "loss": 0.1425, "step": 412190 }, { "epoch": 2.450202400271056, "grad_norm": 4.806405544281006, "learning_rate": 6.038893419007358e-06, "loss": 0.1383, "step": 412200 }, { "epoch": 2.4502618423477243, "grad_norm": 4.148458003997803, "learning_rate": 6.0386904543220646e-06, "loss": 0.1359, "step": 412210 }, { "epoch": 2.4503212844243927, "grad_norm": 3.938789129257202, "learning_rate": 6.038487487848025e-06, "loss": 0.1359, "step": 412220 }, { "epoch": 2.450380726501061, "grad_norm": 6.394657135009766, "learning_rate": 6.038284519585586e-06, "loss": 0.1379, "step": 412230 }, { "epoch": 2.4504401685777295, "grad_norm": 4.4975056648254395, "learning_rate": 6.038081549535095e-06, "loss": 0.1374, "step": 412240 }, { "epoch": 2.450499610654398, "grad_norm": 4.2617902755737305, "learning_rate": 6.037878577696905e-06, "loss": 0.133, "step": 412250 }, { "epoch": 2.4505590527310663, "grad_norm": 3.9149837493896484, "learning_rate": 6.037675604071363e-06, "loss": 0.1546, "step": 412260 }, { "epoch": 2.4506184948077347, "grad_norm": 5.192152500152588, "learning_rate": 6.037472628658823e-06, "loss": 0.1308, "step": 412270 }, { "epoch": 2.450677936884403, "grad_norm": 5.148738384246826, "learning_rate": 6.037269651459627e-06, "loss": 0.1362, "step": 412280 }, { "epoch": 2.4507373789610716, "grad_norm": 3.7162978649139404, "learning_rate": 6.037066672474132e-06, "loss": 0.1303, "step": 412290 }, { "epoch": 2.4507968210377395, "grad_norm": 4.1078972816467285, "learning_rate": 6.036863691702684e-06, "loss": 0.1493, "step": 412300 }, { "epoch": 2.4508562631144084, "grad_norm": 3.693974018096924, "learning_rate": 6.036660709145632e-06, "loss": 0.1236, "step": 412310 }, { "epoch": 2.4509157051910764, "grad_norm": 4.242241382598877, "learning_rate": 6.036457724803329e-06, "loss": 0.1509, "step": 412320 }, { "epoch": 2.450975147267745, "grad_norm": 5.09080696105957, "learning_rate": 6.0362547386761195e-06, "loss": 0.1322, "step": 412330 }, { "epoch": 2.451034589344413, "grad_norm": 4.805455207824707, "learning_rate": 6.036051750764356e-06, "loss": 0.1388, "step": 412340 }, { "epoch": 2.4510940314210816, "grad_norm": 3.8448381423950195, "learning_rate": 6.0358487610683895e-06, "loss": 0.1383, "step": 412350 }, { "epoch": 2.45115347349775, "grad_norm": 4.510399341583252, "learning_rate": 6.0356457695885665e-06, "loss": 0.1219, "step": 412360 }, { "epoch": 2.4512129155744184, "grad_norm": 4.854739189147949, "learning_rate": 6.035442776325238e-06, "loss": 0.1402, "step": 412370 }, { "epoch": 2.451272357651087, "grad_norm": 5.4969611167907715, "learning_rate": 6.035239781278752e-06, "loss": 0.1406, "step": 412380 }, { "epoch": 2.4513317997277553, "grad_norm": 3.590083360671997, "learning_rate": 6.035036784449461e-06, "loss": 0.1284, "step": 412390 }, { "epoch": 2.4513912418044237, "grad_norm": 3.3317785263061523, "learning_rate": 6.034833785837715e-06, "loss": 0.1228, "step": 412400 }, { "epoch": 2.451450683881092, "grad_norm": 2.6094861030578613, "learning_rate": 6.034630785443859e-06, "loss": 0.1474, "step": 412410 }, { "epoch": 2.4515101259577605, "grad_norm": 4.672428607940674, "learning_rate": 6.034427783268246e-06, "loss": 0.1234, "step": 412420 }, { "epoch": 2.451569568034429, "grad_norm": 4.376087665557861, "learning_rate": 6.034224779311226e-06, "loss": 0.14, "step": 412430 }, { "epoch": 2.4516290101110974, "grad_norm": 4.36870002746582, "learning_rate": 6.034021773573147e-06, "loss": 0.1319, "step": 412440 }, { "epoch": 2.4516884521877658, "grad_norm": 3.693601608276367, "learning_rate": 6.033818766054359e-06, "loss": 0.1261, "step": 412450 }, { "epoch": 2.451747894264434, "grad_norm": 3.714358329772949, "learning_rate": 6.033615756755212e-06, "loss": 0.1224, "step": 412460 }, { "epoch": 2.4518073363411026, "grad_norm": 3.634138822555542, "learning_rate": 6.033412745676055e-06, "loss": 0.1507, "step": 412470 }, { "epoch": 2.451866778417771, "grad_norm": 3.813490867614746, "learning_rate": 6.033209732817237e-06, "loss": 0.1493, "step": 412480 }, { "epoch": 2.451926220494439, "grad_norm": 5.157259464263916, "learning_rate": 6.03300671817911e-06, "loss": 0.1388, "step": 412490 }, { "epoch": 2.4519856625711074, "grad_norm": 4.0290207862854, "learning_rate": 6.032803701762021e-06, "loss": 0.142, "step": 412500 }, { "epoch": 2.452045104647776, "grad_norm": 5.313109397888184, "learning_rate": 6.032600683566322e-06, "loss": 0.1523, "step": 412510 }, { "epoch": 2.4521045467244442, "grad_norm": 3.879880666732788, "learning_rate": 6.032397663592361e-06, "loss": 0.1366, "step": 412520 }, { "epoch": 2.4521639888011126, "grad_norm": 5.2167792320251465, "learning_rate": 6.032194641840488e-06, "loss": 0.1398, "step": 412530 }, { "epoch": 2.452223430877781, "grad_norm": 6.303030967712402, "learning_rate": 6.031991618311052e-06, "loss": 0.1459, "step": 412540 }, { "epoch": 2.4522828729544495, "grad_norm": 4.054365158081055, "learning_rate": 6.031788593004404e-06, "loss": 0.1318, "step": 412550 }, { "epoch": 2.452342315031118, "grad_norm": 4.03867769241333, "learning_rate": 6.0315855659208926e-06, "loss": 0.1445, "step": 412560 }, { "epoch": 2.4524017571077863, "grad_norm": 5.029418468475342, "learning_rate": 6.031382537060868e-06, "loss": 0.1315, "step": 412570 }, { "epoch": 2.4524611991844547, "grad_norm": 3.9869182109832764, "learning_rate": 6.03117950642468e-06, "loss": 0.1347, "step": 412580 }, { "epoch": 2.452520641261123, "grad_norm": 4.731469631195068, "learning_rate": 6.030976474012678e-06, "loss": 0.1146, "step": 412590 }, { "epoch": 2.4525800833377915, "grad_norm": 3.905456066131592, "learning_rate": 6.030773439825209e-06, "loss": 0.144, "step": 412600 }, { "epoch": 2.45263952541446, "grad_norm": 4.069626331329346, "learning_rate": 6.0305704038626275e-06, "loss": 0.141, "step": 412610 }, { "epoch": 2.4526989674911284, "grad_norm": 4.172732353210449, "learning_rate": 6.0303673661252816e-06, "loss": 0.1316, "step": 412620 }, { "epoch": 2.452758409567797, "grad_norm": 4.3759684562683105, "learning_rate": 6.030164326613519e-06, "loss": 0.1269, "step": 412630 }, { "epoch": 2.452817851644465, "grad_norm": 4.804072380065918, "learning_rate": 6.02996128532769e-06, "loss": 0.1433, "step": 412640 }, { "epoch": 2.4528772937211336, "grad_norm": 7.879825592041016, "learning_rate": 6.0297582422681454e-06, "loss": 0.1498, "step": 412650 }, { "epoch": 2.452936735797802, "grad_norm": 5.235122203826904, "learning_rate": 6.029555197435234e-06, "loss": 0.1328, "step": 412660 }, { "epoch": 2.4529961778744704, "grad_norm": 6.08276891708374, "learning_rate": 6.029352150829306e-06, "loss": 0.1454, "step": 412670 }, { "epoch": 2.4530556199511384, "grad_norm": 5.6373419761657715, "learning_rate": 6.029149102450711e-06, "loss": 0.1341, "step": 412680 }, { "epoch": 2.453115062027807, "grad_norm": 4.4364190101623535, "learning_rate": 6.028946052299798e-06, "loss": 0.1469, "step": 412690 }, { "epoch": 2.4531745041044752, "grad_norm": 4.186191082000732, "learning_rate": 6.028743000376917e-06, "loss": 0.13, "step": 412700 }, { "epoch": 2.4532339461811437, "grad_norm": 3.9891409873962402, "learning_rate": 6.028539946682418e-06, "loss": 0.1525, "step": 412710 }, { "epoch": 2.453293388257812, "grad_norm": 4.441660404205322, "learning_rate": 6.02833689121665e-06, "loss": 0.1359, "step": 412720 }, { "epoch": 2.4533528303344805, "grad_norm": 4.092909336090088, "learning_rate": 6.028133833979963e-06, "loss": 0.1304, "step": 412730 }, { "epoch": 2.453412272411149, "grad_norm": 4.399493217468262, "learning_rate": 6.027930774972708e-06, "loss": 0.1361, "step": 412740 }, { "epoch": 2.4534717144878173, "grad_norm": 4.485015869140625, "learning_rate": 6.027727714195234e-06, "loss": 0.1539, "step": 412750 }, { "epoch": 2.4535311565644857, "grad_norm": 5.16624116897583, "learning_rate": 6.027524651647888e-06, "loss": 0.1567, "step": 412760 }, { "epoch": 2.453590598641154, "grad_norm": 4.024168014526367, "learning_rate": 6.027321587331024e-06, "loss": 0.1501, "step": 412770 }, { "epoch": 2.4536500407178226, "grad_norm": 4.2327094078063965, "learning_rate": 6.027118521244989e-06, "loss": 0.1315, "step": 412780 }, { "epoch": 2.453709482794491, "grad_norm": 4.2489142417907715, "learning_rate": 6.026915453390133e-06, "loss": 0.1337, "step": 412790 }, { "epoch": 2.4537689248711594, "grad_norm": 4.602394104003906, "learning_rate": 6.026712383766806e-06, "loss": 0.1432, "step": 412800 }, { "epoch": 2.453828366947828, "grad_norm": 3.2718591690063477, "learning_rate": 6.026509312375358e-06, "loss": 0.1351, "step": 412810 }, { "epoch": 2.453887809024496, "grad_norm": 3.6035332679748535, "learning_rate": 6.026306239216139e-06, "loss": 0.1388, "step": 412820 }, { "epoch": 2.4539472511011646, "grad_norm": 4.169609546661377, "learning_rate": 6.026103164289497e-06, "loss": 0.1326, "step": 412830 }, { "epoch": 2.454006693177833, "grad_norm": 4.916232585906982, "learning_rate": 6.025900087595784e-06, "loss": 0.1523, "step": 412840 }, { "epoch": 2.454066135254501, "grad_norm": 5.559381484985352, "learning_rate": 6.025697009135349e-06, "loss": 0.1406, "step": 412850 }, { "epoch": 2.45412557733117, "grad_norm": 3.302464246749878, "learning_rate": 6.02549392890854e-06, "loss": 0.1311, "step": 412860 }, { "epoch": 2.454185019407838, "grad_norm": 5.036581516265869, "learning_rate": 6.025290846915709e-06, "loss": 0.1168, "step": 412870 }, { "epoch": 2.4542444614845063, "grad_norm": 4.25267219543457, "learning_rate": 6.025087763157205e-06, "loss": 0.1342, "step": 412880 }, { "epoch": 2.4543039035611747, "grad_norm": 3.790921688079834, "learning_rate": 6.024884677633377e-06, "loss": 0.1349, "step": 412890 }, { "epoch": 2.454363345637843, "grad_norm": 3.457888603210449, "learning_rate": 6.024681590344575e-06, "loss": 0.1412, "step": 412900 }, { "epoch": 2.4544227877145115, "grad_norm": 5.042479515075684, "learning_rate": 6.024478501291151e-06, "loss": 0.1422, "step": 412910 }, { "epoch": 2.45448222979118, "grad_norm": 3.7571280002593994, "learning_rate": 6.02427541047345e-06, "loss": 0.1409, "step": 412920 }, { "epoch": 2.4545416718678483, "grad_norm": 4.176924705505371, "learning_rate": 6.024072317891825e-06, "loss": 0.1346, "step": 412930 }, { "epoch": 2.4546011139445167, "grad_norm": 4.153698921203613, "learning_rate": 6.023869223546627e-06, "loss": 0.1474, "step": 412940 }, { "epoch": 2.454660556021185, "grad_norm": 5.350921630859375, "learning_rate": 6.023666127438203e-06, "loss": 0.1403, "step": 412950 }, { "epoch": 2.4547199980978536, "grad_norm": 4.332695484161377, "learning_rate": 6.0234630295669035e-06, "loss": 0.14, "step": 412960 }, { "epoch": 2.454779440174522, "grad_norm": 4.8672614097595215, "learning_rate": 6.02325992993308e-06, "loss": 0.144, "step": 412970 }, { "epoch": 2.4548388822511904, "grad_norm": 3.955561399459839, "learning_rate": 6.0230568285370795e-06, "loss": 0.1368, "step": 412980 }, { "epoch": 2.454898324327859, "grad_norm": 4.3912129402160645, "learning_rate": 6.022853725379253e-06, "loss": 0.1419, "step": 412990 }, { "epoch": 2.4549577664045272, "grad_norm": 4.412570476531982, "learning_rate": 6.022650620459951e-06, "loss": 0.1393, "step": 413000 }, { "epoch": 2.4550172084811956, "grad_norm": 4.111085891723633, "learning_rate": 6.022447513779523e-06, "loss": 0.1326, "step": 413010 }, { "epoch": 2.455076650557864, "grad_norm": 4.3594584465026855, "learning_rate": 6.0222444053383166e-06, "loss": 0.1203, "step": 413020 }, { "epoch": 2.4551360926345325, "grad_norm": 4.07761287689209, "learning_rate": 6.022041295136684e-06, "loss": 0.1514, "step": 413030 }, { "epoch": 2.4551955347112004, "grad_norm": 4.418732643127441, "learning_rate": 6.021838183174975e-06, "loss": 0.1455, "step": 413040 }, { "epoch": 2.4552549767878693, "grad_norm": 4.849247932434082, "learning_rate": 6.021635069453539e-06, "loss": 0.1255, "step": 413050 }, { "epoch": 2.4553144188645373, "grad_norm": 4.585596084594727, "learning_rate": 6.021431953972724e-06, "loss": 0.1442, "step": 413060 }, { "epoch": 2.4553738609412057, "grad_norm": 4.655660152435303, "learning_rate": 6.0212288367328834e-06, "loss": 0.1314, "step": 413070 }, { "epoch": 2.455433303017874, "grad_norm": 4.094162464141846, "learning_rate": 6.021025717734364e-06, "loss": 0.1375, "step": 413080 }, { "epoch": 2.4554927450945425, "grad_norm": 3.9527065753936768, "learning_rate": 6.020822596977516e-06, "loss": 0.149, "step": 413090 }, { "epoch": 2.455552187171211, "grad_norm": 4.9674763679504395, "learning_rate": 6.02061947446269e-06, "loss": 0.1398, "step": 413100 }, { "epoch": 2.4556116292478793, "grad_norm": 4.657966136932373, "learning_rate": 6.020416350190235e-06, "loss": 0.135, "step": 413110 }, { "epoch": 2.4556710713245478, "grad_norm": 3.104586601257324, "learning_rate": 6.020213224160502e-06, "loss": 0.1469, "step": 413120 }, { "epoch": 2.455730513401216, "grad_norm": 4.186812400817871, "learning_rate": 6.020010096373841e-06, "loss": 0.1552, "step": 413130 }, { "epoch": 2.4557899554778846, "grad_norm": 4.685659408569336, "learning_rate": 6.019806966830598e-06, "loss": 0.1535, "step": 413140 }, { "epoch": 2.455849397554553, "grad_norm": 3.20186710357666, "learning_rate": 6.019603835531127e-06, "loss": 0.1269, "step": 413150 }, { "epoch": 2.4559088396312214, "grad_norm": 4.687603950500488, "learning_rate": 6.019400702475777e-06, "loss": 0.1358, "step": 413160 }, { "epoch": 2.45596828170789, "grad_norm": 5.113186836242676, "learning_rate": 6.019197567664898e-06, "loss": 0.1314, "step": 413170 }, { "epoch": 2.4560277237845582, "grad_norm": 4.766371726989746, "learning_rate": 6.018994431098838e-06, "loss": 0.1276, "step": 413180 }, { "epoch": 2.4560871658612267, "grad_norm": 5.627079010009766, "learning_rate": 6.018791292777949e-06, "loss": 0.1521, "step": 413190 }, { "epoch": 2.456146607937895, "grad_norm": 3.030393600463867, "learning_rate": 6.0185881527025804e-06, "loss": 0.1462, "step": 413200 }, { "epoch": 2.4562060500145635, "grad_norm": 7.494840621948242, "learning_rate": 6.018385010873079e-06, "loss": 0.1461, "step": 413210 }, { "epoch": 2.456265492091232, "grad_norm": 4.449626922607422, "learning_rate": 6.018181867289799e-06, "loss": 0.1415, "step": 413220 }, { "epoch": 2.4563249341679, "grad_norm": 5.533055782318115, "learning_rate": 6.017978721953088e-06, "loss": 0.1573, "step": 413230 }, { "epoch": 2.4563843762445683, "grad_norm": 2.5367181301116943, "learning_rate": 6.017775574863297e-06, "loss": 0.1258, "step": 413240 }, { "epoch": 2.4564438183212367, "grad_norm": 4.1896653175354, "learning_rate": 6.017572426020772e-06, "loss": 0.131, "step": 413250 }, { "epoch": 2.456503260397905, "grad_norm": 3.561800241470337, "learning_rate": 6.0173692754258685e-06, "loss": 0.1414, "step": 413260 }, { "epoch": 2.4565627024745735, "grad_norm": 4.146838188171387, "learning_rate": 6.017166123078934e-06, "loss": 0.1226, "step": 413270 }, { "epoch": 2.456622144551242, "grad_norm": 3.6512863636016846, "learning_rate": 6.016962968980317e-06, "loss": 0.136, "step": 413280 }, { "epoch": 2.4566815866279104, "grad_norm": 5.118614196777344, "learning_rate": 6.016759813130368e-06, "loss": 0.1455, "step": 413290 }, { "epoch": 2.4567410287045788, "grad_norm": 3.838881492614746, "learning_rate": 6.016556655529439e-06, "loss": 0.1262, "step": 413300 }, { "epoch": 2.456800470781247, "grad_norm": 3.402132511138916, "learning_rate": 6.016353496177876e-06, "loss": 0.1423, "step": 413310 }, { "epoch": 2.4568599128579156, "grad_norm": 4.558498859405518, "learning_rate": 6.016150335076033e-06, "loss": 0.1367, "step": 413320 }, { "epoch": 2.456919354934584, "grad_norm": 4.128355979919434, "learning_rate": 6.015947172224257e-06, "loss": 0.147, "step": 413330 }, { "epoch": 2.4569787970112524, "grad_norm": 4.934460163116455, "learning_rate": 6.015744007622898e-06, "loss": 0.1444, "step": 413340 }, { "epoch": 2.457038239087921, "grad_norm": 4.207421779632568, "learning_rate": 6.015540841272307e-06, "loss": 0.1466, "step": 413350 }, { "epoch": 2.4570976811645893, "grad_norm": 3.465545177459717, "learning_rate": 6.015337673172834e-06, "loss": 0.1288, "step": 413360 }, { "epoch": 2.4571571232412577, "grad_norm": 4.141208648681641, "learning_rate": 6.015134503324828e-06, "loss": 0.1497, "step": 413370 }, { "epoch": 2.457216565317926, "grad_norm": 4.074256896972656, "learning_rate": 6.01493133172864e-06, "loss": 0.1323, "step": 413380 }, { "epoch": 2.4572760073945945, "grad_norm": 3.8072493076324463, "learning_rate": 6.014728158384618e-06, "loss": 0.1396, "step": 413390 }, { "epoch": 2.4573354494712625, "grad_norm": 3.557058572769165, "learning_rate": 6.014524983293115e-06, "loss": 0.1387, "step": 413400 }, { "epoch": 2.4573948915479313, "grad_norm": 4.741241931915283, "learning_rate": 6.014321806454477e-06, "loss": 0.1442, "step": 413410 }, { "epoch": 2.4574543336245993, "grad_norm": 4.351446628570557, "learning_rate": 6.014118627869056e-06, "loss": 0.1402, "step": 413420 }, { "epoch": 2.4575137757012677, "grad_norm": 6.726425647735596, "learning_rate": 6.013915447537203e-06, "loss": 0.134, "step": 413430 }, { "epoch": 2.457573217777936, "grad_norm": 4.140940189361572, "learning_rate": 6.013712265459265e-06, "loss": 0.137, "step": 413440 }, { "epoch": 2.4576326598546046, "grad_norm": 4.578766822814941, "learning_rate": 6.013509081635596e-06, "loss": 0.1456, "step": 413450 }, { "epoch": 2.457692101931273, "grad_norm": 4.977330207824707, "learning_rate": 6.01330589606654e-06, "loss": 0.1495, "step": 413460 }, { "epoch": 2.4577515440079414, "grad_norm": 2.8774099349975586, "learning_rate": 6.0131027087524526e-06, "loss": 0.133, "step": 413470 }, { "epoch": 2.45781098608461, "grad_norm": 3.7676994800567627, "learning_rate": 6.01289951969368e-06, "loss": 0.1424, "step": 413480 }, { "epoch": 2.457870428161278, "grad_norm": 4.90536642074585, "learning_rate": 6.012696328890575e-06, "loss": 0.14, "step": 413490 }, { "epoch": 2.4579298702379466, "grad_norm": 3.332810878753662, "learning_rate": 6.0124931363434855e-06, "loss": 0.1282, "step": 413500 }, { "epoch": 2.457989312314615, "grad_norm": 3.068446397781372, "learning_rate": 6.012289942052763e-06, "loss": 0.1208, "step": 413510 }, { "epoch": 2.4580487543912835, "grad_norm": 4.409892559051514, "learning_rate": 6.0120867460187546e-06, "loss": 0.1416, "step": 413520 }, { "epoch": 2.458108196467952, "grad_norm": 3.7393996715545654, "learning_rate": 6.0118835482418135e-06, "loss": 0.1251, "step": 413530 }, { "epoch": 2.4581676385446203, "grad_norm": 3.762843608856201, "learning_rate": 6.011680348722288e-06, "loss": 0.1198, "step": 413540 }, { "epoch": 2.4582270806212887, "grad_norm": 5.538349151611328, "learning_rate": 6.011477147460529e-06, "loss": 0.149, "step": 413550 }, { "epoch": 2.458286522697957, "grad_norm": 4.823812007904053, "learning_rate": 6.0112739444568835e-06, "loss": 0.1442, "step": 413560 }, { "epoch": 2.4583459647746255, "grad_norm": 3.0331811904907227, "learning_rate": 6.011070739711704e-06, "loss": 0.1331, "step": 413570 }, { "epoch": 2.458405406851294, "grad_norm": 3.1872003078460693, "learning_rate": 6.010867533225341e-06, "loss": 0.1195, "step": 413580 }, { "epoch": 2.458464848927962, "grad_norm": 4.003246784210205, "learning_rate": 6.010664324998143e-06, "loss": 0.1315, "step": 413590 }, { "epoch": 2.4585242910046308, "grad_norm": 3.8622307777404785, "learning_rate": 6.010461115030462e-06, "loss": 0.1479, "step": 413600 }, { "epoch": 2.4585837330812987, "grad_norm": 4.202556133270264, "learning_rate": 6.0102579033226435e-06, "loss": 0.157, "step": 413610 }, { "epoch": 2.458643175157967, "grad_norm": 3.740574836730957, "learning_rate": 6.010054689875042e-06, "loss": 0.1512, "step": 413620 }, { "epoch": 2.4587026172346356, "grad_norm": 5.597583293914795, "learning_rate": 6.0098514746880065e-06, "loss": 0.1394, "step": 413630 }, { "epoch": 2.458762059311304, "grad_norm": 6.204184055328369, "learning_rate": 6.009648257761884e-06, "loss": 0.1366, "step": 413640 }, { "epoch": 2.4588215013879724, "grad_norm": 4.755027770996094, "learning_rate": 6.009445039097029e-06, "loss": 0.1347, "step": 413650 }, { "epoch": 2.458880943464641, "grad_norm": 5.016472339630127, "learning_rate": 6.009241818693789e-06, "loss": 0.1411, "step": 413660 }, { "epoch": 2.4589403855413092, "grad_norm": 5.428926467895508, "learning_rate": 6.009038596552513e-06, "loss": 0.1463, "step": 413670 }, { "epoch": 2.4589998276179776, "grad_norm": 5.353164196014404, "learning_rate": 6.008835372673551e-06, "loss": 0.1251, "step": 413680 }, { "epoch": 2.459059269694646, "grad_norm": 5.548168182373047, "learning_rate": 6.008632147057257e-06, "loss": 0.147, "step": 413690 }, { "epoch": 2.4591187117713145, "grad_norm": 5.878815174102783, "learning_rate": 6.008428919703978e-06, "loss": 0.148, "step": 413700 }, { "epoch": 2.459178153847983, "grad_norm": 3.3779220581054688, "learning_rate": 6.008225690614063e-06, "loss": 0.1349, "step": 413710 }, { "epoch": 2.4592375959246513, "grad_norm": 4.336618900299072, "learning_rate": 6.008022459787862e-06, "loss": 0.1474, "step": 413720 }, { "epoch": 2.4592970380013197, "grad_norm": 3.019416332244873, "learning_rate": 6.007819227225728e-06, "loss": 0.1458, "step": 413730 }, { "epoch": 2.459356480077988, "grad_norm": 4.461389064788818, "learning_rate": 6.007615992928008e-06, "loss": 0.1442, "step": 413740 }, { "epoch": 2.4594159221546565, "grad_norm": 4.381181240081787, "learning_rate": 6.007412756895053e-06, "loss": 0.1266, "step": 413750 }, { "epoch": 2.459475364231325, "grad_norm": 4.334582805633545, "learning_rate": 6.007209519127214e-06, "loss": 0.1322, "step": 413760 }, { "epoch": 2.4595348063079934, "grad_norm": 4.488528728485107, "learning_rate": 6.007006279624838e-06, "loss": 0.1356, "step": 413770 }, { "epoch": 2.4595942483846613, "grad_norm": 4.114266395568848, "learning_rate": 6.006803038388279e-06, "loss": 0.1395, "step": 413780 }, { "epoch": 2.45965369046133, "grad_norm": 3.3565165996551514, "learning_rate": 6.006599795417883e-06, "loss": 0.1349, "step": 413790 }, { "epoch": 2.459713132537998, "grad_norm": 5.253235340118408, "learning_rate": 6.006396550714003e-06, "loss": 0.1261, "step": 413800 }, { "epoch": 2.4597725746146666, "grad_norm": 4.0896382331848145, "learning_rate": 6.0061933042769896e-06, "loss": 0.1347, "step": 413810 }, { "epoch": 2.459832016691335, "grad_norm": 2.883047103881836, "learning_rate": 6.0059900561071904e-06, "loss": 0.1319, "step": 413820 }, { "epoch": 2.4598914587680034, "grad_norm": 3.8479323387145996, "learning_rate": 6.005786806204955e-06, "loss": 0.143, "step": 413830 }, { "epoch": 2.459950900844672, "grad_norm": 3.848480701446533, "learning_rate": 6.005583554570637e-06, "loss": 0.1316, "step": 413840 }, { "epoch": 2.4600103429213402, "grad_norm": 5.267508029937744, "learning_rate": 6.005380301204582e-06, "loss": 0.1346, "step": 413850 }, { "epoch": 2.4600697849980087, "grad_norm": 3.7985141277313232, "learning_rate": 6.0051770461071425e-06, "loss": 0.1466, "step": 413860 }, { "epoch": 2.460129227074677, "grad_norm": 4.656346321105957, "learning_rate": 6.004973789278669e-06, "loss": 0.145, "step": 413870 }, { "epoch": 2.4601886691513455, "grad_norm": 4.27133846282959, "learning_rate": 6.004770530719511e-06, "loss": 0.1534, "step": 413880 }, { "epoch": 2.460248111228014, "grad_norm": 3.392014265060425, "learning_rate": 6.004567270430018e-06, "loss": 0.138, "step": 413890 }, { "epoch": 2.4603075533046823, "grad_norm": 3.584872007369995, "learning_rate": 6.004364008410538e-06, "loss": 0.1431, "step": 413900 }, { "epoch": 2.4603669953813507, "grad_norm": 5.168735027313232, "learning_rate": 6.004160744661426e-06, "loss": 0.1505, "step": 413910 }, { "epoch": 2.460426437458019, "grad_norm": 3.6068568229675293, "learning_rate": 6.0039574791830295e-06, "loss": 0.1176, "step": 413920 }, { "epoch": 2.4604858795346876, "grad_norm": 4.354321479797363, "learning_rate": 6.0037542119756964e-06, "loss": 0.1248, "step": 413930 }, { "epoch": 2.460545321611356, "grad_norm": 3.8769779205322266, "learning_rate": 6.003550943039781e-06, "loss": 0.1298, "step": 413940 }, { "epoch": 2.4606047636880244, "grad_norm": 3.3609719276428223, "learning_rate": 6.00334767237563e-06, "loss": 0.1254, "step": 413950 }, { "epoch": 2.460664205764693, "grad_norm": 4.203195571899414, "learning_rate": 6.003144399983595e-06, "loss": 0.1376, "step": 413960 }, { "epoch": 2.4607236478413608, "grad_norm": 4.430976390838623, "learning_rate": 6.002941125864026e-06, "loss": 0.1268, "step": 413970 }, { "epoch": 2.460783089918029, "grad_norm": 5.37369966506958, "learning_rate": 6.002737850017272e-06, "loss": 0.1509, "step": 413980 }, { "epoch": 2.4608425319946976, "grad_norm": 4.4436445236206055, "learning_rate": 6.002534572443684e-06, "loss": 0.1552, "step": 413990 }, { "epoch": 2.460901974071366, "grad_norm": 3.5352225303649902, "learning_rate": 6.00233129314361e-06, "loss": 0.1355, "step": 414000 }, { "epoch": 2.4609614161480344, "grad_norm": 4.160285472869873, "learning_rate": 6.002128012117404e-06, "loss": 0.1466, "step": 414010 }, { "epoch": 2.461020858224703, "grad_norm": 4.435483455657959, "learning_rate": 6.001924729365414e-06, "loss": 0.1397, "step": 414020 }, { "epoch": 2.4610803003013713, "grad_norm": 4.939169883728027, "learning_rate": 6.001721444887989e-06, "loss": 0.1262, "step": 414030 }, { "epoch": 2.4611397423780397, "grad_norm": 4.44246768951416, "learning_rate": 6.001518158685481e-06, "loss": 0.1349, "step": 414040 }, { "epoch": 2.461199184454708, "grad_norm": 4.903888702392578, "learning_rate": 6.001314870758241e-06, "loss": 0.1444, "step": 414050 }, { "epoch": 2.4612586265313765, "grad_norm": 2.9113759994506836, "learning_rate": 6.001111581106613e-06, "loss": 0.1269, "step": 414060 }, { "epoch": 2.461318068608045, "grad_norm": 6.408939361572266, "learning_rate": 6.000908289730954e-06, "loss": 0.1508, "step": 414070 }, { "epoch": 2.4613775106847133, "grad_norm": 5.360920429229736, "learning_rate": 6.000704996631612e-06, "loss": 0.121, "step": 414080 }, { "epoch": 2.4614369527613817, "grad_norm": 6.881243705749512, "learning_rate": 6.0005017018089365e-06, "loss": 0.1637, "step": 414090 }, { "epoch": 2.46149639483805, "grad_norm": 4.05666446685791, "learning_rate": 6.0002984052632765e-06, "loss": 0.1404, "step": 414100 }, { "epoch": 2.4615558369147186, "grad_norm": 2.2145628929138184, "learning_rate": 6.000095106994984e-06, "loss": 0.1334, "step": 414110 }, { "epoch": 2.461615278991387, "grad_norm": 4.326861381530762, "learning_rate": 5.9998918070044075e-06, "loss": 0.1527, "step": 414120 }, { "epoch": 2.4616747210680554, "grad_norm": 2.8136637210845947, "learning_rate": 5.999688505291898e-06, "loss": 0.1403, "step": 414130 }, { "epoch": 2.4617341631447234, "grad_norm": 5.812757968902588, "learning_rate": 5.999485201857808e-06, "loss": 0.1491, "step": 414140 }, { "epoch": 2.4617936052213922, "grad_norm": 4.401520729064941, "learning_rate": 5.999281896702483e-06, "loss": 0.1387, "step": 414150 }, { "epoch": 2.46185304729806, "grad_norm": 2.7323455810546875, "learning_rate": 5.999078589826276e-06, "loss": 0.1369, "step": 414160 }, { "epoch": 2.4619124893747286, "grad_norm": 4.423947811126709, "learning_rate": 5.998875281229537e-06, "loss": 0.145, "step": 414170 }, { "epoch": 2.461971931451397, "grad_norm": 4.156898021697998, "learning_rate": 5.998671970912615e-06, "loss": 0.1497, "step": 414180 }, { "epoch": 2.4620313735280654, "grad_norm": 4.3197808265686035, "learning_rate": 5.99846865887586e-06, "loss": 0.1321, "step": 414190 }, { "epoch": 2.462090815604734, "grad_norm": 4.246910095214844, "learning_rate": 5.998265345119624e-06, "loss": 0.1359, "step": 414200 }, { "epoch": 2.4621502576814023, "grad_norm": 4.897005081176758, "learning_rate": 5.998062029644256e-06, "loss": 0.1319, "step": 414210 }, { "epoch": 2.4622096997580707, "grad_norm": 5.3860392570495605, "learning_rate": 5.997858712450106e-06, "loss": 0.1536, "step": 414220 }, { "epoch": 2.462269141834739, "grad_norm": 3.774627208709717, "learning_rate": 5.9976553935375225e-06, "loss": 0.1402, "step": 414230 }, { "epoch": 2.4623285839114075, "grad_norm": 3.960336208343506, "learning_rate": 5.997452072906858e-06, "loss": 0.1442, "step": 414240 }, { "epoch": 2.462388025988076, "grad_norm": 4.123840808868408, "learning_rate": 5.997248750558464e-06, "loss": 0.1561, "step": 414250 }, { "epoch": 2.4624474680647443, "grad_norm": 4.064934730529785, "learning_rate": 5.997045426492687e-06, "loss": 0.1342, "step": 414260 }, { "epoch": 2.4625069101414128, "grad_norm": 4.594724655151367, "learning_rate": 5.9968421007098786e-06, "loss": 0.1262, "step": 414270 }, { "epoch": 2.462566352218081, "grad_norm": 4.358186721801758, "learning_rate": 5.9966387732103905e-06, "loss": 0.1392, "step": 414280 }, { "epoch": 2.4626257942947496, "grad_norm": 4.155345916748047, "learning_rate": 5.996435443994571e-06, "loss": 0.1353, "step": 414290 }, { "epoch": 2.462685236371418, "grad_norm": 3.898218870162964, "learning_rate": 5.99623211306277e-06, "loss": 0.1483, "step": 414300 }, { "epoch": 2.4627446784480864, "grad_norm": 5.422351360321045, "learning_rate": 5.99602878041534e-06, "loss": 0.1518, "step": 414310 }, { "epoch": 2.462804120524755, "grad_norm": 3.9473721981048584, "learning_rate": 5.9958254460526275e-06, "loss": 0.1345, "step": 414320 }, { "epoch": 2.462863562601423, "grad_norm": 3.9022347927093506, "learning_rate": 5.995622109974987e-06, "loss": 0.122, "step": 414330 }, { "epoch": 2.4629230046780917, "grad_norm": 4.920418739318848, "learning_rate": 5.995418772182764e-06, "loss": 0.1504, "step": 414340 }, { "epoch": 2.4629824467547596, "grad_norm": 4.9082159996032715, "learning_rate": 5.995215432676312e-06, "loss": 0.1249, "step": 414350 }, { "epoch": 2.463041888831428, "grad_norm": 3.9961421489715576, "learning_rate": 5.995012091455981e-06, "loss": 0.1329, "step": 414360 }, { "epoch": 2.4631013309080965, "grad_norm": 4.399937629699707, "learning_rate": 5.994808748522121e-06, "loss": 0.133, "step": 414370 }, { "epoch": 2.463160772984765, "grad_norm": 3.977961301803589, "learning_rate": 5.99460540387508e-06, "loss": 0.1359, "step": 414380 }, { "epoch": 2.4632202150614333, "grad_norm": 3.419665813446045, "learning_rate": 5.994402057515209e-06, "loss": 0.1295, "step": 414390 }, { "epoch": 2.4632796571381017, "grad_norm": 3.462526559829712, "learning_rate": 5.994198709442862e-06, "loss": 0.1355, "step": 414400 }, { "epoch": 2.46333909921477, "grad_norm": 5.8264312744140625, "learning_rate": 5.9939953596583855e-06, "loss": 0.1408, "step": 414410 }, { "epoch": 2.4633985412914385, "grad_norm": 3.4573142528533936, "learning_rate": 5.99379200816213e-06, "loss": 0.1287, "step": 414420 }, { "epoch": 2.463457983368107, "grad_norm": 5.63263463973999, "learning_rate": 5.9935886549544454e-06, "loss": 0.1453, "step": 414430 }, { "epoch": 2.4635174254447754, "grad_norm": 4.529386043548584, "learning_rate": 5.9933853000356835e-06, "loss": 0.1425, "step": 414440 }, { "epoch": 2.463576867521444, "grad_norm": 3.8352010250091553, "learning_rate": 5.993181943406191e-06, "loss": 0.1242, "step": 414450 }, { "epoch": 2.463636309598112, "grad_norm": 4.483824729919434, "learning_rate": 5.9929785850663224e-06, "loss": 0.1355, "step": 414460 }, { "epoch": 2.4636957516747806, "grad_norm": 4.561973571777344, "learning_rate": 5.992775225016427e-06, "loss": 0.1336, "step": 414470 }, { "epoch": 2.463755193751449, "grad_norm": 4.003385543823242, "learning_rate": 5.992571863256853e-06, "loss": 0.1314, "step": 414480 }, { "epoch": 2.4638146358281174, "grad_norm": 4.923468589782715, "learning_rate": 5.992368499787953e-06, "loss": 0.1464, "step": 414490 }, { "epoch": 2.463874077904786, "grad_norm": 3.390627861022949, "learning_rate": 5.992165134610076e-06, "loss": 0.1453, "step": 414500 }, { "epoch": 2.4639335199814543, "grad_norm": 3.76941180229187, "learning_rate": 5.9919617677235706e-06, "loss": 0.1401, "step": 414510 }, { "epoch": 2.4639929620581222, "grad_norm": 3.6588168144226074, "learning_rate": 5.991758399128791e-06, "loss": 0.1246, "step": 414520 }, { "epoch": 2.464052404134791, "grad_norm": 4.524592399597168, "learning_rate": 5.9915550288260836e-06, "loss": 0.1323, "step": 414530 }, { "epoch": 2.464111846211459, "grad_norm": 5.483984470367432, "learning_rate": 5.9913516568158e-06, "loss": 0.1453, "step": 414540 }, { "epoch": 2.4641712882881275, "grad_norm": 3.665602207183838, "learning_rate": 5.991148283098292e-06, "loss": 0.1308, "step": 414550 }, { "epoch": 2.464230730364796, "grad_norm": 5.780896186828613, "learning_rate": 5.990944907673907e-06, "loss": 0.14, "step": 414560 }, { "epoch": 2.4642901724414643, "grad_norm": 4.891153812408447, "learning_rate": 5.990741530542997e-06, "loss": 0.1622, "step": 414570 }, { "epoch": 2.4643496145181327, "grad_norm": 4.568581581115723, "learning_rate": 5.990538151705911e-06, "loss": 0.1258, "step": 414580 }, { "epoch": 2.464409056594801, "grad_norm": 4.189233303070068, "learning_rate": 5.990334771163002e-06, "loss": 0.1611, "step": 414590 }, { "epoch": 2.4644684986714696, "grad_norm": 4.653207778930664, "learning_rate": 5.990131388914618e-06, "loss": 0.1504, "step": 414600 }, { "epoch": 2.464527940748138, "grad_norm": 3.920416831970215, "learning_rate": 5.989928004961108e-06, "loss": 0.1435, "step": 414610 }, { "epoch": 2.4645873828248064, "grad_norm": 3.556213140487671, "learning_rate": 5.989724619302826e-06, "loss": 0.133, "step": 414620 }, { "epoch": 2.464646824901475, "grad_norm": 3.634819507598877, "learning_rate": 5.989521231940119e-06, "loss": 0.1377, "step": 414630 }, { "epoch": 2.464706266978143, "grad_norm": 4.3181681632995605, "learning_rate": 5.989317842873338e-06, "loss": 0.1528, "step": 414640 }, { "epoch": 2.4647657090548116, "grad_norm": 4.476346015930176, "learning_rate": 5.989114452102834e-06, "loss": 0.1545, "step": 414650 }, { "epoch": 2.46482515113148, "grad_norm": 2.6104838848114014, "learning_rate": 5.988911059628958e-06, "loss": 0.1279, "step": 414660 }, { "epoch": 2.4648845932081485, "grad_norm": 4.665414333343506, "learning_rate": 5.988707665452057e-06, "loss": 0.1227, "step": 414670 }, { "epoch": 2.464944035284817, "grad_norm": 3.939532518386841, "learning_rate": 5.988504269572484e-06, "loss": 0.1269, "step": 414680 }, { "epoch": 2.4650034773614853, "grad_norm": 4.143331527709961, "learning_rate": 5.98830087199059e-06, "loss": 0.1201, "step": 414690 }, { "epoch": 2.4650629194381537, "grad_norm": 4.438089370727539, "learning_rate": 5.988097472706723e-06, "loss": 0.1278, "step": 414700 }, { "epoch": 2.4651223615148217, "grad_norm": 3.958325147628784, "learning_rate": 5.987894071721234e-06, "loss": 0.1315, "step": 414710 }, { "epoch": 2.46518180359149, "grad_norm": 4.723496437072754, "learning_rate": 5.987690669034474e-06, "loss": 0.129, "step": 414720 }, { "epoch": 2.4652412456681585, "grad_norm": 4.009407997131348, "learning_rate": 5.987487264646794e-06, "loss": 0.1454, "step": 414730 }, { "epoch": 2.465300687744827, "grad_norm": 4.530117034912109, "learning_rate": 5.987283858558541e-06, "loss": 0.1513, "step": 414740 }, { "epoch": 2.4653601298214953, "grad_norm": 2.3499720096588135, "learning_rate": 5.987080450770069e-06, "loss": 0.1302, "step": 414750 }, { "epoch": 2.4654195718981637, "grad_norm": 3.853252410888672, "learning_rate": 5.986877041281726e-06, "loss": 0.1183, "step": 414760 }, { "epoch": 2.465479013974832, "grad_norm": 5.256058216094971, "learning_rate": 5.986673630093862e-06, "loss": 0.1333, "step": 414770 }, { "epoch": 2.4655384560515006, "grad_norm": 3.7600200176239014, "learning_rate": 5.9864702172068286e-06, "loss": 0.15, "step": 414780 }, { "epoch": 2.465597898128169, "grad_norm": 4.150304794311523, "learning_rate": 5.986266802620977e-06, "loss": 0.1378, "step": 414790 }, { "epoch": 2.4656573402048374, "grad_norm": 3.7760488986968994, "learning_rate": 5.986063386336656e-06, "loss": 0.1577, "step": 414800 }, { "epoch": 2.465716782281506, "grad_norm": 4.714687347412109, "learning_rate": 5.985859968354215e-06, "loss": 0.1307, "step": 414810 }, { "epoch": 2.4657762243581742, "grad_norm": 5.772191524505615, "learning_rate": 5.985656548674007e-06, "loss": 0.1407, "step": 414820 }, { "epoch": 2.4658356664348426, "grad_norm": 5.3658671379089355, "learning_rate": 5.9854531272963815e-06, "loss": 0.1405, "step": 414830 }, { "epoch": 2.465895108511511, "grad_norm": 4.44622802734375, "learning_rate": 5.985249704221685e-06, "loss": 0.1325, "step": 414840 }, { "epoch": 2.4659545505881795, "grad_norm": 4.571130275726318, "learning_rate": 5.9850462794502735e-06, "loss": 0.1359, "step": 414850 }, { "epoch": 2.466013992664848, "grad_norm": 4.04919958114624, "learning_rate": 5.984842852982495e-06, "loss": 0.1414, "step": 414860 }, { "epoch": 2.4660734347415163, "grad_norm": 4.573586463928223, "learning_rate": 5.984639424818698e-06, "loss": 0.1324, "step": 414870 }, { "epoch": 2.4661328768181843, "grad_norm": 3.3848557472229004, "learning_rate": 5.984435994959236e-06, "loss": 0.1386, "step": 414880 }, { "epoch": 2.466192318894853, "grad_norm": 2.6974265575408936, "learning_rate": 5.984232563404455e-06, "loss": 0.1231, "step": 414890 }, { "epoch": 2.466251760971521, "grad_norm": 3.3399031162261963, "learning_rate": 5.984029130154711e-06, "loss": 0.1357, "step": 414900 }, { "epoch": 2.4663112030481895, "grad_norm": 3.924038887023926, "learning_rate": 5.983825695210349e-06, "loss": 0.1531, "step": 414910 }, { "epoch": 2.466370645124858, "grad_norm": 4.456248760223389, "learning_rate": 5.983622258571724e-06, "loss": 0.1555, "step": 414920 }, { "epoch": 2.4664300872015263, "grad_norm": 4.016296863555908, "learning_rate": 5.983418820239184e-06, "loss": 0.1218, "step": 414930 }, { "epoch": 2.4664895292781948, "grad_norm": 4.422586441040039, "learning_rate": 5.983215380213078e-06, "loss": 0.1335, "step": 414940 }, { "epoch": 2.466548971354863, "grad_norm": 4.143424034118652, "learning_rate": 5.983011938493759e-06, "loss": 0.1384, "step": 414950 }, { "epoch": 2.4666084134315316, "grad_norm": 5.025363922119141, "learning_rate": 5.982808495081576e-06, "loss": 0.1353, "step": 414960 }, { "epoch": 2.4666678555082, "grad_norm": 4.1374192237854, "learning_rate": 5.982605049976878e-06, "loss": 0.1457, "step": 414970 }, { "epoch": 2.4667272975848684, "grad_norm": 3.8176448345184326, "learning_rate": 5.98240160318002e-06, "loss": 0.1408, "step": 414980 }, { "epoch": 2.466786739661537, "grad_norm": 5.876189231872559, "learning_rate": 5.9821981546913466e-06, "loss": 0.1305, "step": 414990 }, { "epoch": 2.4668461817382052, "grad_norm": 4.632270812988281, "learning_rate": 5.981994704511209e-06, "loss": 0.1461, "step": 415000 }, { "epoch": 2.4669056238148737, "grad_norm": 5.597707748413086, "learning_rate": 5.981791252639962e-06, "loss": 0.1437, "step": 415010 }, { "epoch": 2.466965065891542, "grad_norm": 4.970215320587158, "learning_rate": 5.981587799077955e-06, "loss": 0.1386, "step": 415020 }, { "epoch": 2.4670245079682105, "grad_norm": 3.7773473262786865, "learning_rate": 5.981384343825534e-06, "loss": 0.1321, "step": 415030 }, { "epoch": 2.467083950044879, "grad_norm": 3.0098676681518555, "learning_rate": 5.981180886883052e-06, "loss": 0.1244, "step": 415040 }, { "epoch": 2.4671433921215473, "grad_norm": 4.3308491706848145, "learning_rate": 5.980977428250861e-06, "loss": 0.1444, "step": 415050 }, { "epoch": 2.4672028341982157, "grad_norm": 2.879894971847534, "learning_rate": 5.98077396792931e-06, "loss": 0.1277, "step": 415060 }, { "epoch": 2.4672622762748837, "grad_norm": 3.4018075466156006, "learning_rate": 5.980570505918747e-06, "loss": 0.1508, "step": 415070 }, { "epoch": 2.4673217183515526, "grad_norm": 3.4361014366149902, "learning_rate": 5.980367042219527e-06, "loss": 0.1267, "step": 415080 }, { "epoch": 2.4673811604282205, "grad_norm": 3.294447422027588, "learning_rate": 5.980163576831996e-06, "loss": 0.1317, "step": 415090 }, { "epoch": 2.467440602504889, "grad_norm": 7.006223678588867, "learning_rate": 5.9799601097565075e-06, "loss": 0.1475, "step": 415100 }, { "epoch": 2.4675000445815574, "grad_norm": 4.407613754272461, "learning_rate": 5.97975664099341e-06, "loss": 0.1488, "step": 415110 }, { "epoch": 2.4675594866582258, "grad_norm": 4.172310829162598, "learning_rate": 5.979553170543055e-06, "loss": 0.147, "step": 415120 }, { "epoch": 2.467618928734894, "grad_norm": 3.742541790008545, "learning_rate": 5.979349698405792e-06, "loss": 0.1239, "step": 415130 }, { "epoch": 2.4676783708115626, "grad_norm": 3.4722390174865723, "learning_rate": 5.9791462245819735e-06, "loss": 0.132, "step": 415140 }, { "epoch": 2.467737812888231, "grad_norm": 5.574398040771484, "learning_rate": 5.978942749071947e-06, "loss": 0.1335, "step": 415150 }, { "epoch": 2.4677972549648994, "grad_norm": 3.846667528152466, "learning_rate": 5.978739271876065e-06, "loss": 0.1313, "step": 415160 }, { "epoch": 2.467856697041568, "grad_norm": 4.061619758605957, "learning_rate": 5.978535792994677e-06, "loss": 0.145, "step": 415170 }, { "epoch": 2.4679161391182363, "grad_norm": 3.5980780124664307, "learning_rate": 5.978332312428135e-06, "loss": 0.1411, "step": 415180 }, { "epoch": 2.4679755811949047, "grad_norm": 3.588303804397583, "learning_rate": 5.978128830176786e-06, "loss": 0.1298, "step": 415190 }, { "epoch": 2.468035023271573, "grad_norm": 5.013487339019775, "learning_rate": 5.977925346240984e-06, "loss": 0.1318, "step": 415200 }, { "epoch": 2.4680944653482415, "grad_norm": 3.738083600997925, "learning_rate": 5.977721860621076e-06, "loss": 0.1293, "step": 415210 }, { "epoch": 2.46815390742491, "grad_norm": 4.41330623626709, "learning_rate": 5.977518373317415e-06, "loss": 0.127, "step": 415220 }, { "epoch": 2.4682133495015783, "grad_norm": 5.398355007171631, "learning_rate": 5.977314884330351e-06, "loss": 0.1401, "step": 415230 }, { "epoch": 2.4682727915782467, "grad_norm": 4.179448127746582, "learning_rate": 5.977111393660234e-06, "loss": 0.1296, "step": 415240 }, { "epoch": 2.468332233654915, "grad_norm": 3.940675735473633, "learning_rate": 5.976907901307415e-06, "loss": 0.1374, "step": 415250 }, { "epoch": 2.468391675731583, "grad_norm": 5.095616817474365, "learning_rate": 5.9767044072722435e-06, "loss": 0.1355, "step": 415260 }, { "epoch": 2.468451117808252, "grad_norm": 5.8262410163879395, "learning_rate": 5.976500911555071e-06, "loss": 0.1289, "step": 415270 }, { "epoch": 2.46851055988492, "grad_norm": 4.595582962036133, "learning_rate": 5.976297414156248e-06, "loss": 0.1399, "step": 415280 }, { "epoch": 2.4685700019615884, "grad_norm": 3.4690513610839844, "learning_rate": 5.976093915076122e-06, "loss": 0.1222, "step": 415290 }, { "epoch": 2.468629444038257, "grad_norm": 3.551863670349121, "learning_rate": 5.975890414315049e-06, "loss": 0.1421, "step": 415300 }, { "epoch": 2.468688886114925, "grad_norm": 4.038986682891846, "learning_rate": 5.975686911873374e-06, "loss": 0.1365, "step": 415310 }, { "epoch": 2.4687483281915936, "grad_norm": 3.510646343231201, "learning_rate": 5.97548340775145e-06, "loss": 0.1347, "step": 415320 }, { "epoch": 2.468807770268262, "grad_norm": 4.035999298095703, "learning_rate": 5.9752799019496265e-06, "loss": 0.1367, "step": 415330 }, { "epoch": 2.4688672123449305, "grad_norm": 3.4888570308685303, "learning_rate": 5.975076394468256e-06, "loss": 0.1435, "step": 415340 }, { "epoch": 2.468926654421599, "grad_norm": 2.8344156742095947, "learning_rate": 5.974872885307689e-06, "loss": 0.1303, "step": 415350 }, { "epoch": 2.4689860964982673, "grad_norm": 3.990922451019287, "learning_rate": 5.974669374468272e-06, "loss": 0.1366, "step": 415360 }, { "epoch": 2.4690455385749357, "grad_norm": 3.5745248794555664, "learning_rate": 5.974465861950358e-06, "loss": 0.144, "step": 415370 }, { "epoch": 2.469104980651604, "grad_norm": 4.142235279083252, "learning_rate": 5.974262347754299e-06, "loss": 0.1324, "step": 415380 }, { "epoch": 2.4691644227282725, "grad_norm": 4.561203479766846, "learning_rate": 5.974058831880443e-06, "loss": 0.1384, "step": 415390 }, { "epoch": 2.469223864804941, "grad_norm": 4.016968727111816, "learning_rate": 5.973855314329143e-06, "loss": 0.1461, "step": 415400 }, { "epoch": 2.4692833068816094, "grad_norm": 3.857408285140991, "learning_rate": 5.973651795100747e-06, "loss": 0.1386, "step": 415410 }, { "epoch": 2.4693427489582778, "grad_norm": 4.628454208374023, "learning_rate": 5.973448274195606e-06, "loss": 0.1396, "step": 415420 }, { "epoch": 2.469402191034946, "grad_norm": 4.6477742195129395, "learning_rate": 5.973244751614071e-06, "loss": 0.1342, "step": 415430 }, { "epoch": 2.4694616331116146, "grad_norm": 3.7315900325775146, "learning_rate": 5.9730412273564916e-06, "loss": 0.1188, "step": 415440 }, { "epoch": 2.4695210751882826, "grad_norm": 2.370884895324707, "learning_rate": 5.972837701423221e-06, "loss": 0.1298, "step": 415450 }, { "epoch": 2.469580517264951, "grad_norm": 3.6684396266937256, "learning_rate": 5.9726341738146055e-06, "loss": 0.1224, "step": 415460 }, { "epoch": 2.4696399593416194, "grad_norm": 4.2580695152282715, "learning_rate": 5.972430644531e-06, "loss": 0.1493, "step": 415470 }, { "epoch": 2.469699401418288, "grad_norm": 3.9077091217041016, "learning_rate": 5.972227113572752e-06, "loss": 0.1399, "step": 415480 }, { "epoch": 2.4697588434949562, "grad_norm": 4.780118942260742, "learning_rate": 5.972023580940213e-06, "loss": 0.1435, "step": 415490 }, { "epoch": 2.4698182855716246, "grad_norm": 3.8497941493988037, "learning_rate": 5.971820046633734e-06, "loss": 0.1371, "step": 415500 }, { "epoch": 2.469877727648293, "grad_norm": 5.313230991363525, "learning_rate": 5.971616510653665e-06, "loss": 0.1256, "step": 415510 }, { "epoch": 2.4699371697249615, "grad_norm": 3.7283682823181152, "learning_rate": 5.9714129730003545e-06, "loss": 0.1262, "step": 415520 }, { "epoch": 2.46999661180163, "grad_norm": 4.247288227081299, "learning_rate": 5.971209433674156e-06, "loss": 0.1348, "step": 415530 }, { "epoch": 2.4700560538782983, "grad_norm": 4.311592102050781, "learning_rate": 5.971005892675421e-06, "loss": 0.1393, "step": 415540 }, { "epoch": 2.4701154959549667, "grad_norm": 4.5910725593566895, "learning_rate": 5.970802350004495e-06, "loss": 0.1512, "step": 415550 }, { "epoch": 2.470174938031635, "grad_norm": 5.084352493286133, "learning_rate": 5.9705988056617325e-06, "loss": 0.1391, "step": 415560 }, { "epoch": 2.4702343801083035, "grad_norm": 5.38913106918335, "learning_rate": 5.970395259647483e-06, "loss": 0.1454, "step": 415570 }, { "epoch": 2.470293822184972, "grad_norm": 6.408425331115723, "learning_rate": 5.970191711962099e-06, "loss": 0.1368, "step": 415580 }, { "epoch": 2.4703532642616404, "grad_norm": 3.287036895751953, "learning_rate": 5.969988162605926e-06, "loss": 0.1203, "step": 415590 }, { "epoch": 2.470412706338309, "grad_norm": 3.1344871520996094, "learning_rate": 5.96978461157932e-06, "loss": 0.1333, "step": 415600 }, { "epoch": 2.470472148414977, "grad_norm": 4.6538262367248535, "learning_rate": 5.969581058882629e-06, "loss": 0.1367, "step": 415610 }, { "epoch": 2.470531590491645, "grad_norm": 5.436772346496582, "learning_rate": 5.969377504516203e-06, "loss": 0.1307, "step": 415620 }, { "epoch": 2.470591032568314, "grad_norm": 4.019124507904053, "learning_rate": 5.969173948480393e-06, "loss": 0.1403, "step": 415630 }, { "epoch": 2.470650474644982, "grad_norm": 5.577996730804443, "learning_rate": 5.9689703907755505e-06, "loss": 0.159, "step": 415640 }, { "epoch": 2.4707099167216504, "grad_norm": 4.692906379699707, "learning_rate": 5.968766831402024e-06, "loss": 0.1333, "step": 415650 }, { "epoch": 2.470769358798319, "grad_norm": 3.1551449298858643, "learning_rate": 5.968563270360166e-06, "loss": 0.1367, "step": 415660 }, { "epoch": 2.4708288008749872, "grad_norm": 5.067868709564209, "learning_rate": 5.968359707650327e-06, "loss": 0.1219, "step": 415670 }, { "epoch": 2.4708882429516557, "grad_norm": 4.3427629470825195, "learning_rate": 5.968156143272858e-06, "loss": 0.1523, "step": 415680 }, { "epoch": 2.470947685028324, "grad_norm": 4.9984822273254395, "learning_rate": 5.9679525772281065e-06, "loss": 0.1282, "step": 415690 }, { "epoch": 2.4710071271049925, "grad_norm": 4.230064392089844, "learning_rate": 5.967749009516427e-06, "loss": 0.1444, "step": 415700 }, { "epoch": 2.471066569181661, "grad_norm": 4.431612014770508, "learning_rate": 5.9675454401381686e-06, "loss": 0.1486, "step": 415710 }, { "epoch": 2.4711260112583293, "grad_norm": 3.879007339477539, "learning_rate": 5.967341869093679e-06, "loss": 0.1384, "step": 415720 }, { "epoch": 2.4711854533349977, "grad_norm": 3.508516311645508, "learning_rate": 5.967138296383314e-06, "loss": 0.1333, "step": 415730 }, { "epoch": 2.471244895411666, "grad_norm": 4.1124701499938965, "learning_rate": 5.96693472200742e-06, "loss": 0.1301, "step": 415740 }, { "epoch": 2.4713043374883346, "grad_norm": 2.9911842346191406, "learning_rate": 5.966731145966349e-06, "loss": 0.1208, "step": 415750 }, { "epoch": 2.471363779565003, "grad_norm": 4.035142421722412, "learning_rate": 5.966527568260452e-06, "loss": 0.1489, "step": 415760 }, { "epoch": 2.4714232216416714, "grad_norm": 2.746246337890625, "learning_rate": 5.9663239888900785e-06, "loss": 0.1331, "step": 415770 }, { "epoch": 2.47148266371834, "grad_norm": 3.2406585216522217, "learning_rate": 5.966120407855579e-06, "loss": 0.142, "step": 415780 }, { "epoch": 2.471542105795008, "grad_norm": 3.9195899963378906, "learning_rate": 5.965916825157307e-06, "loss": 0.1458, "step": 415790 }, { "epoch": 2.4716015478716766, "grad_norm": 4.066718101501465, "learning_rate": 5.9657132407956105e-06, "loss": 0.1446, "step": 415800 }, { "epoch": 2.4716609899483446, "grad_norm": 4.5978312492370605, "learning_rate": 5.96550965477084e-06, "loss": 0.1377, "step": 415810 }, { "epoch": 2.4717204320250135, "grad_norm": 3.6331706047058105, "learning_rate": 5.965306067083348e-06, "loss": 0.1232, "step": 415820 }, { "epoch": 2.4717798741016814, "grad_norm": 4.83006477355957, "learning_rate": 5.965102477733482e-06, "loss": 0.127, "step": 415830 }, { "epoch": 2.47183931617835, "grad_norm": 3.191892623901367, "learning_rate": 5.964898886721594e-06, "loss": 0.1285, "step": 415840 }, { "epoch": 2.4718987582550183, "grad_norm": 3.6403191089630127, "learning_rate": 5.964695294048038e-06, "loss": 0.1363, "step": 415850 }, { "epoch": 2.4719582003316867, "grad_norm": 4.05682373046875, "learning_rate": 5.964491699713158e-06, "loss": 0.1345, "step": 415860 }, { "epoch": 2.472017642408355, "grad_norm": 4.04296875, "learning_rate": 5.96428810371731e-06, "loss": 0.1399, "step": 415870 }, { "epoch": 2.4720770844850235, "grad_norm": 4.504594802856445, "learning_rate": 5.964084506060842e-06, "loss": 0.1404, "step": 415880 }, { "epoch": 2.472136526561692, "grad_norm": 3.8995392322540283, "learning_rate": 5.963880906744106e-06, "loss": 0.1434, "step": 415890 }, { "epoch": 2.4721959686383603, "grad_norm": 4.391923427581787, "learning_rate": 5.963677305767454e-06, "loss": 0.1231, "step": 415900 }, { "epoch": 2.4722554107150287, "grad_norm": 3.7829840183258057, "learning_rate": 5.963473703131231e-06, "loss": 0.1191, "step": 415910 }, { "epoch": 2.472314852791697, "grad_norm": 3.236642837524414, "learning_rate": 5.9632700988357936e-06, "loss": 0.1345, "step": 415920 }, { "epoch": 2.4723742948683656, "grad_norm": 3.487901449203491, "learning_rate": 5.963066492881491e-06, "loss": 0.1266, "step": 415930 }, { "epoch": 2.472433736945034, "grad_norm": 3.4304354190826416, "learning_rate": 5.962862885268671e-06, "loss": 0.1482, "step": 415940 }, { "epoch": 2.4724931790217024, "grad_norm": 5.114026069641113, "learning_rate": 5.962659275997687e-06, "loss": 0.1316, "step": 415950 }, { "epoch": 2.472552621098371, "grad_norm": 4.887775897979736, "learning_rate": 5.962455665068889e-06, "loss": 0.1347, "step": 415960 }, { "epoch": 2.4726120631750392, "grad_norm": 5.393407344818115, "learning_rate": 5.9622520524826265e-06, "loss": 0.1393, "step": 415970 }, { "epoch": 2.4726715052517076, "grad_norm": 3.587315320968628, "learning_rate": 5.962048438239253e-06, "loss": 0.1462, "step": 415980 }, { "epoch": 2.472730947328376, "grad_norm": 5.1298089027404785, "learning_rate": 5.961844822339116e-06, "loss": 0.1224, "step": 415990 }, { "epoch": 2.472790389405044, "grad_norm": 4.431290149688721, "learning_rate": 5.961641204782568e-06, "loss": 0.121, "step": 416000 }, { "epoch": 2.472849831481713, "grad_norm": 3.658475875854492, "learning_rate": 5.961437585569958e-06, "loss": 0.1243, "step": 416010 }, { "epoch": 2.472909273558381, "grad_norm": 4.030552864074707, "learning_rate": 5.9612339647016395e-06, "loss": 0.1373, "step": 416020 }, { "epoch": 2.4729687156350493, "grad_norm": 6.165366172790527, "learning_rate": 5.96103034217796e-06, "loss": 0.1497, "step": 416030 }, { "epoch": 2.4730281577117177, "grad_norm": 3.768444776535034, "learning_rate": 5.960826717999272e-06, "loss": 0.1308, "step": 416040 }, { "epoch": 2.473087599788386, "grad_norm": 2.6128222942352295, "learning_rate": 5.960623092165927e-06, "loss": 0.1137, "step": 416050 }, { "epoch": 2.4731470418650545, "grad_norm": 4.298902988433838, "learning_rate": 5.9604194646782735e-06, "loss": 0.1344, "step": 416060 }, { "epoch": 2.473206483941723, "grad_norm": 4.4288105964660645, "learning_rate": 5.960215835536662e-06, "loss": 0.1547, "step": 416070 }, { "epoch": 2.4732659260183913, "grad_norm": 3.1443068981170654, "learning_rate": 5.9600122047414455e-06, "loss": 0.1307, "step": 416080 }, { "epoch": 2.4733253680950598, "grad_norm": 4.061312675476074, "learning_rate": 5.959808572292973e-06, "loss": 0.1256, "step": 416090 }, { "epoch": 2.473384810171728, "grad_norm": 4.548839569091797, "learning_rate": 5.959604938191596e-06, "loss": 0.1238, "step": 416100 }, { "epoch": 2.4734442522483966, "grad_norm": 5.032622337341309, "learning_rate": 5.959401302437663e-06, "loss": 0.1418, "step": 416110 }, { "epoch": 2.473503694325065, "grad_norm": 4.774811744689941, "learning_rate": 5.959197665031529e-06, "loss": 0.1361, "step": 416120 }, { "epoch": 2.4735631364017334, "grad_norm": 4.064143657684326, "learning_rate": 5.958994025973541e-06, "loss": 0.1348, "step": 416130 }, { "epoch": 2.473622578478402, "grad_norm": 5.376293182373047, "learning_rate": 5.9587903852640504e-06, "loss": 0.1501, "step": 416140 }, { "epoch": 2.4736820205550702, "grad_norm": 3.9330499172210693, "learning_rate": 5.958586742903409e-06, "loss": 0.1388, "step": 416150 }, { "epoch": 2.4737414626317387, "grad_norm": 3.7736847400665283, "learning_rate": 5.958383098891968e-06, "loss": 0.1195, "step": 416160 }, { "epoch": 2.473800904708407, "grad_norm": 4.109940528869629, "learning_rate": 5.958179453230075e-06, "loss": 0.1516, "step": 416170 }, { "epoch": 2.4738603467850755, "grad_norm": 5.710039138793945, "learning_rate": 5.9579758059180835e-06, "loss": 0.1443, "step": 416180 }, { "epoch": 2.4739197888617435, "grad_norm": 4.063717365264893, "learning_rate": 5.957772156956344e-06, "loss": 0.13, "step": 416190 }, { "epoch": 2.473979230938412, "grad_norm": 4.6695051193237305, "learning_rate": 5.957568506345205e-06, "loss": 0.1429, "step": 416200 }, { "epoch": 2.4740386730150803, "grad_norm": 3.363198757171631, "learning_rate": 5.957364854085019e-06, "loss": 0.1412, "step": 416210 }, { "epoch": 2.4740981150917487, "grad_norm": 5.117030620574951, "learning_rate": 5.957161200176137e-06, "loss": 0.1394, "step": 416220 }, { "epoch": 2.474157557168417, "grad_norm": 5.278521537780762, "learning_rate": 5.95695754461891e-06, "loss": 0.1508, "step": 416230 }, { "epoch": 2.4742169992450855, "grad_norm": 3.804208517074585, "learning_rate": 5.956753887413686e-06, "loss": 0.1505, "step": 416240 }, { "epoch": 2.474276441321754, "grad_norm": 5.6544036865234375, "learning_rate": 5.95655022856082e-06, "loss": 0.1375, "step": 416250 }, { "epoch": 2.4743358833984224, "grad_norm": 5.9415106773376465, "learning_rate": 5.95634656806066e-06, "loss": 0.1413, "step": 416260 }, { "epoch": 2.474395325475091, "grad_norm": 4.606256008148193, "learning_rate": 5.956142905913555e-06, "loss": 0.1392, "step": 416270 }, { "epoch": 2.474454767551759, "grad_norm": 4.743494033813477, "learning_rate": 5.95593924211986e-06, "loss": 0.1364, "step": 416280 }, { "epoch": 2.4745142096284276, "grad_norm": 5.196335315704346, "learning_rate": 5.955735576679923e-06, "loss": 0.1536, "step": 416290 }, { "epoch": 2.474573651705096, "grad_norm": 3.6407947540283203, "learning_rate": 5.955531909594094e-06, "loss": 0.1426, "step": 416300 }, { "epoch": 2.4746330937817644, "grad_norm": 3.746058702468872, "learning_rate": 5.955328240862726e-06, "loss": 0.137, "step": 416310 }, { "epoch": 2.474692535858433, "grad_norm": 7.070065021514893, "learning_rate": 5.95512457048617e-06, "loss": 0.1426, "step": 416320 }, { "epoch": 2.4747519779351013, "grad_norm": 4.001586437225342, "learning_rate": 5.9549208984647735e-06, "loss": 0.1419, "step": 416330 }, { "epoch": 2.4748114200117697, "grad_norm": 3.8546745777130127, "learning_rate": 5.954717224798891e-06, "loss": 0.1386, "step": 416340 }, { "epoch": 2.474870862088438, "grad_norm": 3.451286792755127, "learning_rate": 5.95451354948887e-06, "loss": 0.1381, "step": 416350 }, { "epoch": 2.474930304165106, "grad_norm": 4.673044681549072, "learning_rate": 5.954309872535063e-06, "loss": 0.1334, "step": 416360 }, { "epoch": 2.474989746241775, "grad_norm": 3.5336837768554688, "learning_rate": 5.954106193937821e-06, "loss": 0.1348, "step": 416370 }, { "epoch": 2.475049188318443, "grad_norm": 3.7666494846343994, "learning_rate": 5.953902513697495e-06, "loss": 0.1284, "step": 416380 }, { "epoch": 2.4751086303951113, "grad_norm": 3.0992496013641357, "learning_rate": 5.953698831814435e-06, "loss": 0.1129, "step": 416390 }, { "epoch": 2.4751680724717797, "grad_norm": 3.7383527755737305, "learning_rate": 5.95349514828899e-06, "loss": 0.1454, "step": 416400 }, { "epoch": 2.475227514548448, "grad_norm": 4.840463638305664, "learning_rate": 5.953291463121515e-06, "loss": 0.1233, "step": 416410 }, { "epoch": 2.4752869566251166, "grad_norm": 5.537791728973389, "learning_rate": 5.953087776312357e-06, "loss": 0.1331, "step": 416420 }, { "epoch": 2.475346398701785, "grad_norm": 4.105307579040527, "learning_rate": 5.952884087861867e-06, "loss": 0.1249, "step": 416430 }, { "epoch": 2.4754058407784534, "grad_norm": 3.726149082183838, "learning_rate": 5.952680397770398e-06, "loss": 0.1308, "step": 416440 }, { "epoch": 2.475465282855122, "grad_norm": 4.451972961425781, "learning_rate": 5.9524767060383005e-06, "loss": 0.1294, "step": 416450 }, { "epoch": 2.47552472493179, "grad_norm": 4.9831132888793945, "learning_rate": 5.9522730126659234e-06, "loss": 0.1501, "step": 416460 }, { "epoch": 2.4755841670084586, "grad_norm": 6.6379570960998535, "learning_rate": 5.9520693176536195e-06, "loss": 0.1521, "step": 416470 }, { "epoch": 2.475643609085127, "grad_norm": 4.079533576965332, "learning_rate": 5.9518656210017375e-06, "loss": 0.1477, "step": 416480 }, { "epoch": 2.4757030511617955, "grad_norm": 4.594627380371094, "learning_rate": 5.95166192271063e-06, "loss": 0.1292, "step": 416490 }, { "epoch": 2.475762493238464, "grad_norm": 4.669851303100586, "learning_rate": 5.9514582227806476e-06, "loss": 0.1365, "step": 416500 }, { "epoch": 2.4758219353151323, "grad_norm": 4.213314533233643, "learning_rate": 5.95125452121214e-06, "loss": 0.1167, "step": 416510 }, { "epoch": 2.4758813773918007, "grad_norm": 4.24247407913208, "learning_rate": 5.951050818005458e-06, "loss": 0.1455, "step": 416520 }, { "epoch": 2.475940819468469, "grad_norm": 4.913145542144775, "learning_rate": 5.950847113160955e-06, "loss": 0.1372, "step": 416530 }, { "epoch": 2.4760002615451375, "grad_norm": 4.238968372344971, "learning_rate": 5.950643406678978e-06, "loss": 0.1242, "step": 416540 }, { "epoch": 2.4760597036218055, "grad_norm": 3.2132675647735596, "learning_rate": 5.95043969855988e-06, "loss": 0.1322, "step": 416550 }, { "epoch": 2.4761191456984744, "grad_norm": 4.213842391967773, "learning_rate": 5.95023598880401e-06, "loss": 0.1296, "step": 416560 }, { "epoch": 2.4761785877751423, "grad_norm": 3.169564962387085, "learning_rate": 5.950032277411722e-06, "loss": 0.1681, "step": 416570 }, { "epoch": 2.4762380298518107, "grad_norm": 5.5840559005737305, "learning_rate": 5.949828564383366e-06, "loss": 0.1564, "step": 416580 }, { "epoch": 2.476297471928479, "grad_norm": 6.099733352661133, "learning_rate": 5.94962484971929e-06, "loss": 0.1576, "step": 416590 }, { "epoch": 2.4763569140051476, "grad_norm": 4.957289695739746, "learning_rate": 5.9494211334198485e-06, "loss": 0.132, "step": 416600 }, { "epoch": 2.476416356081816, "grad_norm": 4.384535312652588, "learning_rate": 5.949217415485389e-06, "loss": 0.1461, "step": 416610 }, { "epoch": 2.4764757981584844, "grad_norm": 4.615909099578857, "learning_rate": 5.949013695916264e-06, "loss": 0.1605, "step": 416620 }, { "epoch": 2.476535240235153, "grad_norm": 6.739172458648682, "learning_rate": 5.9488099747128245e-06, "loss": 0.1705, "step": 416630 }, { "epoch": 2.4765946823118212, "grad_norm": 3.824406147003174, "learning_rate": 5.948606251875422e-06, "loss": 0.1465, "step": 416640 }, { "epoch": 2.4766541243884896, "grad_norm": 4.390427112579346, "learning_rate": 5.948402527404404e-06, "loss": 0.1362, "step": 416650 }, { "epoch": 2.476713566465158, "grad_norm": 4.039249897003174, "learning_rate": 5.948198801300124e-06, "loss": 0.1394, "step": 416660 }, { "epoch": 2.4767730085418265, "grad_norm": 3.5986533164978027, "learning_rate": 5.9479950735629346e-06, "loss": 0.1361, "step": 416670 }, { "epoch": 2.476832450618495, "grad_norm": 4.484147548675537, "learning_rate": 5.9477913441931845e-06, "loss": 0.1367, "step": 416680 }, { "epoch": 2.4768918926951633, "grad_norm": 4.933208465576172, "learning_rate": 5.947587613191222e-06, "loss": 0.1581, "step": 416690 }, { "epoch": 2.4769513347718317, "grad_norm": 4.815191745758057, "learning_rate": 5.9473838805574036e-06, "loss": 0.1441, "step": 416700 }, { "epoch": 2.4770107768485, "grad_norm": 7.310741901397705, "learning_rate": 5.947180146292075e-06, "loss": 0.1552, "step": 416710 }, { "epoch": 2.4770702189251685, "grad_norm": 5.411465644836426, "learning_rate": 5.9469764103955895e-06, "loss": 0.1363, "step": 416720 }, { "epoch": 2.477129661001837, "grad_norm": 3.803049087524414, "learning_rate": 5.9467726728683e-06, "loss": 0.1328, "step": 416730 }, { "epoch": 2.477189103078505, "grad_norm": 3.0291171073913574, "learning_rate": 5.946568933710553e-06, "loss": 0.1241, "step": 416740 }, { "epoch": 2.477248545155174, "grad_norm": 4.241420745849609, "learning_rate": 5.9463651929227e-06, "loss": 0.1303, "step": 416750 }, { "epoch": 2.4773079872318418, "grad_norm": 5.577858924865723, "learning_rate": 5.946161450505094e-06, "loss": 0.1461, "step": 416760 }, { "epoch": 2.47736742930851, "grad_norm": 4.28273868560791, "learning_rate": 5.9459577064580864e-06, "loss": 0.1157, "step": 416770 }, { "epoch": 2.4774268713851786, "grad_norm": 5.1356282234191895, "learning_rate": 5.9457539607820255e-06, "loss": 0.1309, "step": 416780 }, { "epoch": 2.477486313461847, "grad_norm": 4.158588886260986, "learning_rate": 5.945550213477263e-06, "loss": 0.1253, "step": 416790 }, { "epoch": 2.4775457555385154, "grad_norm": 3.9263832569122314, "learning_rate": 5.945346464544153e-06, "loss": 0.1341, "step": 416800 }, { "epoch": 2.477605197615184, "grad_norm": 3.34181547164917, "learning_rate": 5.945142713983042e-06, "loss": 0.1329, "step": 416810 }, { "epoch": 2.4776646396918522, "grad_norm": 4.7815022468566895, "learning_rate": 5.944938961794281e-06, "loss": 0.1435, "step": 416820 }, { "epoch": 2.4777240817685207, "grad_norm": 4.768472194671631, "learning_rate": 5.944735207978225e-06, "loss": 0.1433, "step": 416830 }, { "epoch": 2.477783523845189, "grad_norm": 4.383028984069824, "learning_rate": 5.94453145253522e-06, "loss": 0.1365, "step": 416840 }, { "epoch": 2.4778429659218575, "grad_norm": 3.942404270172119, "learning_rate": 5.94432769546562e-06, "loss": 0.1405, "step": 416850 }, { "epoch": 2.477902407998526, "grad_norm": 2.926955461502075, "learning_rate": 5.944123936769776e-06, "loss": 0.1201, "step": 416860 }, { "epoch": 2.4779618500751943, "grad_norm": 4.782012462615967, "learning_rate": 5.943920176448036e-06, "loss": 0.1307, "step": 416870 }, { "epoch": 2.4780212921518627, "grad_norm": 3.6185271739959717, "learning_rate": 5.943716414500754e-06, "loss": 0.1315, "step": 416880 }, { "epoch": 2.478080734228531, "grad_norm": 3.6836681365966797, "learning_rate": 5.943512650928279e-06, "loss": 0.1194, "step": 416890 }, { "epoch": 2.4781401763051996, "grad_norm": 6.418244361877441, "learning_rate": 5.943308885730964e-06, "loss": 0.125, "step": 416900 }, { "epoch": 2.478199618381868, "grad_norm": 4.663710117340088, "learning_rate": 5.943105118909159e-06, "loss": 0.1268, "step": 416910 }, { "epoch": 2.4782590604585364, "grad_norm": 5.230466365814209, "learning_rate": 5.942901350463211e-06, "loss": 0.1372, "step": 416920 }, { "epoch": 2.4783185025352044, "grad_norm": 4.637701988220215, "learning_rate": 5.942697580393477e-06, "loss": 0.1378, "step": 416930 }, { "epoch": 2.4783779446118728, "grad_norm": 3.878638505935669, "learning_rate": 5.942493808700305e-06, "loss": 0.1333, "step": 416940 }, { "epoch": 2.478437386688541, "grad_norm": 3.6689090728759766, "learning_rate": 5.942290035384047e-06, "loss": 0.1332, "step": 416950 }, { "epoch": 2.4784968287652096, "grad_norm": 3.5234110355377197, "learning_rate": 5.942086260445051e-06, "loss": 0.1355, "step": 416960 }, { "epoch": 2.478556270841878, "grad_norm": 4.494248390197754, "learning_rate": 5.941882483883672e-06, "loss": 0.1349, "step": 416970 }, { "epoch": 2.4786157129185464, "grad_norm": 3.910123825073242, "learning_rate": 5.941678705700257e-06, "loss": 0.1419, "step": 416980 }, { "epoch": 2.478675154995215, "grad_norm": 4.926029682159424, "learning_rate": 5.94147492589516e-06, "loss": 0.1344, "step": 416990 }, { "epoch": 2.4787345970718833, "grad_norm": 4.17297887802124, "learning_rate": 5.941271144468731e-06, "loss": 0.1407, "step": 417000 }, { "epoch": 2.4787940391485517, "grad_norm": 5.291647911071777, "learning_rate": 5.9410673614213195e-06, "loss": 0.1395, "step": 417010 }, { "epoch": 2.47885348122522, "grad_norm": 4.27973747253418, "learning_rate": 5.940863576753279e-06, "loss": 0.1468, "step": 417020 }, { "epoch": 2.4789129233018885, "grad_norm": 3.3351078033447266, "learning_rate": 5.940659790464961e-06, "loss": 0.1281, "step": 417030 }, { "epoch": 2.478972365378557, "grad_norm": 6.431663990020752, "learning_rate": 5.940456002556713e-06, "loss": 0.1602, "step": 417040 }, { "epoch": 2.4790318074552253, "grad_norm": 4.859684944152832, "learning_rate": 5.940252213028886e-06, "loss": 0.1486, "step": 417050 }, { "epoch": 2.4790912495318937, "grad_norm": 3.81600022315979, "learning_rate": 5.940048421881834e-06, "loss": 0.1262, "step": 417060 }, { "epoch": 2.479150691608562, "grad_norm": 4.916164875030518, "learning_rate": 5.9398446291159074e-06, "loss": 0.1435, "step": 417070 }, { "epoch": 2.4792101336852306, "grad_norm": 3.9478330612182617, "learning_rate": 5.939640834731454e-06, "loss": 0.1406, "step": 417080 }, { "epoch": 2.479269575761899, "grad_norm": 4.159738063812256, "learning_rate": 5.939437038728827e-06, "loss": 0.1459, "step": 417090 }, { "epoch": 2.479329017838567, "grad_norm": 4.263319492340088, "learning_rate": 5.939233241108378e-06, "loss": 0.1336, "step": 417100 }, { "epoch": 2.479388459915236, "grad_norm": 4.512517929077148, "learning_rate": 5.939029441870458e-06, "loss": 0.1641, "step": 417110 }, { "epoch": 2.479447901991904, "grad_norm": 4.042238235473633, "learning_rate": 5.938825641015418e-06, "loss": 0.1469, "step": 417120 }, { "epoch": 2.479507344068572, "grad_norm": 3.743436336517334, "learning_rate": 5.938621838543607e-06, "loss": 0.1314, "step": 417130 }, { "epoch": 2.4795667861452406, "grad_norm": 4.887223243713379, "learning_rate": 5.9384180344553765e-06, "loss": 0.1384, "step": 417140 }, { "epoch": 2.479626228221909, "grad_norm": 4.449985504150391, "learning_rate": 5.938214228751079e-06, "loss": 0.1251, "step": 417150 }, { "epoch": 2.4796856702985774, "grad_norm": 4.246354579925537, "learning_rate": 5.938010421431065e-06, "loss": 0.1535, "step": 417160 }, { "epoch": 2.479745112375246, "grad_norm": 3.469066619873047, "learning_rate": 5.9378066124956845e-06, "loss": 0.1398, "step": 417170 }, { "epoch": 2.4798045544519143, "grad_norm": 5.4692463874816895, "learning_rate": 5.937602801945289e-06, "loss": 0.14, "step": 417180 }, { "epoch": 2.4798639965285827, "grad_norm": 4.399780750274658, "learning_rate": 5.9373989897802306e-06, "loss": 0.1354, "step": 417190 }, { "epoch": 2.479923438605251, "grad_norm": 3.042691946029663, "learning_rate": 5.937195176000858e-06, "loss": 0.1295, "step": 417200 }, { "epoch": 2.4799828806819195, "grad_norm": 5.293790340423584, "learning_rate": 5.9369913606075234e-06, "loss": 0.1405, "step": 417210 }, { "epoch": 2.480042322758588, "grad_norm": 4.385308265686035, "learning_rate": 5.936787543600579e-06, "loss": 0.1259, "step": 417220 }, { "epoch": 2.4801017648352564, "grad_norm": 3.696178913116455, "learning_rate": 5.9365837249803744e-06, "loss": 0.1183, "step": 417230 }, { "epoch": 2.4801612069119248, "grad_norm": 4.273238182067871, "learning_rate": 5.9363799047472605e-06, "loss": 0.1418, "step": 417240 }, { "epoch": 2.480220648988593, "grad_norm": 3.9280872344970703, "learning_rate": 5.93617608290159e-06, "loss": 0.1238, "step": 417250 }, { "epoch": 2.4802800910652616, "grad_norm": 3.915329933166504, "learning_rate": 5.935972259443712e-06, "loss": 0.1348, "step": 417260 }, { "epoch": 2.48033953314193, "grad_norm": 3.958223581314087, "learning_rate": 5.9357684343739765e-06, "loss": 0.1413, "step": 417270 }, { "epoch": 2.4803989752185984, "grad_norm": 5.555627346038818, "learning_rate": 5.935564607692738e-06, "loss": 0.1562, "step": 417280 }, { "epoch": 2.4804584172952664, "grad_norm": 4.808783054351807, "learning_rate": 5.935360779400345e-06, "loss": 0.1297, "step": 417290 }, { "epoch": 2.4805178593719353, "grad_norm": 3.37172269821167, "learning_rate": 5.935156949497148e-06, "loss": 0.1285, "step": 417300 }, { "epoch": 2.4805773014486032, "grad_norm": 3.880967378616333, "learning_rate": 5.934953117983499e-06, "loss": 0.1406, "step": 417310 }, { "epoch": 2.4806367435252716, "grad_norm": 4.444943904876709, "learning_rate": 5.934749284859751e-06, "loss": 0.1325, "step": 417320 }, { "epoch": 2.48069618560194, "grad_norm": 4.111896991729736, "learning_rate": 5.934545450126254e-06, "loss": 0.133, "step": 417330 }, { "epoch": 2.4807556276786085, "grad_norm": 3.71002459526062, "learning_rate": 5.934341613783356e-06, "loss": 0.1444, "step": 417340 }, { "epoch": 2.480815069755277, "grad_norm": 3.7335641384124756, "learning_rate": 5.93413777583141e-06, "loss": 0.1284, "step": 417350 }, { "epoch": 2.4808745118319453, "grad_norm": 4.690083026885986, "learning_rate": 5.93393393627077e-06, "loss": 0.1472, "step": 417360 }, { "epoch": 2.4809339539086137, "grad_norm": 4.13106632232666, "learning_rate": 5.933730095101782e-06, "loss": 0.1229, "step": 417370 }, { "epoch": 2.480993395985282, "grad_norm": 4.506782531738281, "learning_rate": 5.933526252324799e-06, "loss": 0.1505, "step": 417380 }, { "epoch": 2.4810528380619505, "grad_norm": 3.257136583328247, "learning_rate": 5.9333224079401745e-06, "loss": 0.1369, "step": 417390 }, { "epoch": 2.481112280138619, "grad_norm": 4.9813313484191895, "learning_rate": 5.933118561948256e-06, "loss": 0.1582, "step": 417400 }, { "epoch": 2.4811717222152874, "grad_norm": 3.7206928730010986, "learning_rate": 5.932914714349396e-06, "loss": 0.1412, "step": 417410 }, { "epoch": 2.481231164291956, "grad_norm": 3.275881290435791, "learning_rate": 5.9327108651439455e-06, "loss": 0.14, "step": 417420 }, { "epoch": 2.481290606368624, "grad_norm": 5.445826530456543, "learning_rate": 5.932507014332256e-06, "loss": 0.1191, "step": 417430 }, { "epoch": 2.4813500484452926, "grad_norm": 3.658118724822998, "learning_rate": 5.932303161914678e-06, "loss": 0.1345, "step": 417440 }, { "epoch": 2.481409490521961, "grad_norm": 3.0286307334899902, "learning_rate": 5.932099307891564e-06, "loss": 0.1365, "step": 417450 }, { "epoch": 2.4814689325986294, "grad_norm": 3.7566165924072266, "learning_rate": 5.931895452263262e-06, "loss": 0.1248, "step": 417460 }, { "epoch": 2.481528374675298, "grad_norm": 3.5317063331604004, "learning_rate": 5.931691595030124e-06, "loss": 0.1395, "step": 417470 }, { "epoch": 2.481587816751966, "grad_norm": 4.224708557128906, "learning_rate": 5.931487736192505e-06, "loss": 0.139, "step": 417480 }, { "epoch": 2.4816472588286347, "grad_norm": 3.988189458847046, "learning_rate": 5.931283875750751e-06, "loss": 0.1388, "step": 417490 }, { "epoch": 2.4817067009053027, "grad_norm": 3.350592613220215, "learning_rate": 5.931080013705215e-06, "loss": 0.1297, "step": 417500 }, { "epoch": 2.481766142981971, "grad_norm": 4.3849406242370605, "learning_rate": 5.930876150056248e-06, "loss": 0.1238, "step": 417510 }, { "epoch": 2.4818255850586395, "grad_norm": 5.460052490234375, "learning_rate": 5.930672284804203e-06, "loss": 0.1351, "step": 417520 }, { "epoch": 2.481885027135308, "grad_norm": 3.641310691833496, "learning_rate": 5.930468417949428e-06, "loss": 0.1272, "step": 417530 }, { "epoch": 2.4819444692119763, "grad_norm": 6.8788251876831055, "learning_rate": 5.930264549492274e-06, "loss": 0.1467, "step": 417540 }, { "epoch": 2.4820039112886447, "grad_norm": 4.571351528167725, "learning_rate": 5.930060679433095e-06, "loss": 0.1424, "step": 417550 }, { "epoch": 2.482063353365313, "grad_norm": 4.3833088874816895, "learning_rate": 5.929856807772241e-06, "loss": 0.1252, "step": 417560 }, { "epoch": 2.4821227954419816, "grad_norm": 3.6732544898986816, "learning_rate": 5.92965293451006e-06, "loss": 0.1391, "step": 417570 }, { "epoch": 2.48218223751865, "grad_norm": 4.072296142578125, "learning_rate": 5.929449059646909e-06, "loss": 0.1174, "step": 417580 }, { "epoch": 2.4822416795953184, "grad_norm": 2.9077885150909424, "learning_rate": 5.929245183183135e-06, "loss": 0.1273, "step": 417590 }, { "epoch": 2.482301121671987, "grad_norm": 5.968339443206787, "learning_rate": 5.929041305119088e-06, "loss": 0.1391, "step": 417600 }, { "epoch": 2.482360563748655, "grad_norm": 3.6506032943725586, "learning_rate": 5.928837425455124e-06, "loss": 0.1432, "step": 417610 }, { "epoch": 2.4824200058253236, "grad_norm": 3.9834229946136475, "learning_rate": 5.9286335441915895e-06, "loss": 0.1411, "step": 417620 }, { "epoch": 2.482479447901992, "grad_norm": 3.0715930461883545, "learning_rate": 5.9284296613288374e-06, "loss": 0.1442, "step": 417630 }, { "epoch": 2.4825388899786605, "grad_norm": 4.2238030433654785, "learning_rate": 5.928225776867217e-06, "loss": 0.1462, "step": 417640 }, { "epoch": 2.482598332055329, "grad_norm": 4.371400356292725, "learning_rate": 5.928021890807083e-06, "loss": 0.153, "step": 417650 }, { "epoch": 2.4826577741319973, "grad_norm": 2.8534650802612305, "learning_rate": 5.927818003148784e-06, "loss": 0.1222, "step": 417660 }, { "epoch": 2.4827172162086653, "grad_norm": 3.995084047317505, "learning_rate": 5.927614113892672e-06, "loss": 0.1605, "step": 417670 }, { "epoch": 2.4827766582853337, "grad_norm": 3.7020885944366455, "learning_rate": 5.927410223039099e-06, "loss": 0.1344, "step": 417680 }, { "epoch": 2.482836100362002, "grad_norm": 3.2305712699890137, "learning_rate": 5.927206330588412e-06, "loss": 0.1228, "step": 417690 }, { "epoch": 2.4828955424386705, "grad_norm": 5.973330497741699, "learning_rate": 5.927002436540967e-06, "loss": 0.1335, "step": 417700 }, { "epoch": 2.482954984515339, "grad_norm": 2.7237465381622314, "learning_rate": 5.926798540897114e-06, "loss": 0.1316, "step": 417710 }, { "epoch": 2.4830144265920073, "grad_norm": 4.040075778961182, "learning_rate": 5.926594643657202e-06, "loss": 0.1405, "step": 417720 }, { "epoch": 2.4830738686686757, "grad_norm": 4.744058609008789, "learning_rate": 5.926390744821583e-06, "loss": 0.1477, "step": 417730 }, { "epoch": 2.483133310745344, "grad_norm": 4.095894813537598, "learning_rate": 5.92618684439061e-06, "loss": 0.1402, "step": 417740 }, { "epoch": 2.4831927528220126, "grad_norm": 4.154844760894775, "learning_rate": 5.925982942364631e-06, "loss": 0.122, "step": 417750 }, { "epoch": 2.483252194898681, "grad_norm": 6.392638206481934, "learning_rate": 5.9257790387439995e-06, "loss": 0.1656, "step": 417760 }, { "epoch": 2.4833116369753494, "grad_norm": 5.775515079498291, "learning_rate": 5.925575133529067e-06, "loss": 0.1479, "step": 417770 }, { "epoch": 2.483371079052018, "grad_norm": 3.9779505729675293, "learning_rate": 5.9253712267201835e-06, "loss": 0.1241, "step": 417780 }, { "epoch": 2.4834305211286862, "grad_norm": 4.7770256996154785, "learning_rate": 5.925167318317699e-06, "loss": 0.1192, "step": 417790 }, { "epoch": 2.4834899632053546, "grad_norm": 4.982776165008545, "learning_rate": 5.924963408321968e-06, "loss": 0.1468, "step": 417800 }, { "epoch": 2.483549405282023, "grad_norm": 5.010716915130615, "learning_rate": 5.924759496733339e-06, "loss": 0.1482, "step": 417810 }, { "epoch": 2.4836088473586915, "grad_norm": 4.01063346862793, "learning_rate": 5.924555583552162e-06, "loss": 0.1316, "step": 417820 }, { "epoch": 2.48366828943536, "grad_norm": 5.25407075881958, "learning_rate": 5.924351668778792e-06, "loss": 0.1376, "step": 417830 }, { "epoch": 2.483727731512028, "grad_norm": 4.406060218811035, "learning_rate": 5.924147752413578e-06, "loss": 0.1291, "step": 417840 }, { "epoch": 2.4837871735886967, "grad_norm": 3.8788363933563232, "learning_rate": 5.92394383445687e-06, "loss": 0.1482, "step": 417850 }, { "epoch": 2.4838466156653647, "grad_norm": 4.420589923858643, "learning_rate": 5.92373991490902e-06, "loss": 0.1395, "step": 417860 }, { "epoch": 2.483906057742033, "grad_norm": 4.116024971008301, "learning_rate": 5.923535993770382e-06, "loss": 0.1346, "step": 417870 }, { "epoch": 2.4839654998187015, "grad_norm": 3.26737642288208, "learning_rate": 5.9233320710413035e-06, "loss": 0.1297, "step": 417880 }, { "epoch": 2.48402494189537, "grad_norm": 4.338714122772217, "learning_rate": 5.923128146722137e-06, "loss": 0.1365, "step": 417890 }, { "epoch": 2.4840843839720383, "grad_norm": 4.485237121582031, "learning_rate": 5.9229242208132345e-06, "loss": 0.154, "step": 417900 }, { "epoch": 2.4841438260487068, "grad_norm": 5.859565734863281, "learning_rate": 5.922720293314946e-06, "loss": 0.1347, "step": 417910 }, { "epoch": 2.484203268125375, "grad_norm": 3.6714255809783936, "learning_rate": 5.922516364227622e-06, "loss": 0.1269, "step": 417920 }, { "epoch": 2.4842627102020436, "grad_norm": 3.518542528152466, "learning_rate": 5.9223124335516155e-06, "loss": 0.1202, "step": 417930 }, { "epoch": 2.484322152278712, "grad_norm": 5.573740482330322, "learning_rate": 5.922108501287278e-06, "loss": 0.1591, "step": 417940 }, { "epoch": 2.4843815943553804, "grad_norm": 4.510697841644287, "learning_rate": 5.921904567434958e-06, "loss": 0.1381, "step": 417950 }, { "epoch": 2.484441036432049, "grad_norm": 4.448423385620117, "learning_rate": 5.92170063199501e-06, "loss": 0.1249, "step": 417960 }, { "epoch": 2.4845004785087172, "grad_norm": 3.6554298400878906, "learning_rate": 5.921496694967781e-06, "loss": 0.1517, "step": 417970 }, { "epoch": 2.4845599205853857, "grad_norm": 3.3920795917510986, "learning_rate": 5.921292756353627e-06, "loss": 0.1281, "step": 417980 }, { "epoch": 2.484619362662054, "grad_norm": 3.4122676849365234, "learning_rate": 5.921088816152895e-06, "loss": 0.1411, "step": 417990 }, { "epoch": 2.4846788047387225, "grad_norm": 6.947255611419678, "learning_rate": 5.920884874365941e-06, "loss": 0.1577, "step": 418000 }, { "epoch": 2.484738246815391, "grad_norm": 4.234717845916748, "learning_rate": 5.920680930993112e-06, "loss": 0.1404, "step": 418010 }, { "epoch": 2.4847976888920593, "grad_norm": 3.9313974380493164, "learning_rate": 5.92047698603476e-06, "loss": 0.1476, "step": 418020 }, { "epoch": 2.4848571309687273, "grad_norm": 4.6657023429870605, "learning_rate": 5.920273039491237e-06, "loss": 0.1317, "step": 418030 }, { "epoch": 2.484916573045396, "grad_norm": 3.258666515350342, "learning_rate": 5.920069091362894e-06, "loss": 0.1357, "step": 418040 }, { "epoch": 2.484976015122064, "grad_norm": 3.7379283905029297, "learning_rate": 5.919865141650083e-06, "loss": 0.1401, "step": 418050 }, { "epoch": 2.4850354571987325, "grad_norm": 4.175926685333252, "learning_rate": 5.919661190353155e-06, "loss": 0.1445, "step": 418060 }, { "epoch": 2.485094899275401, "grad_norm": 5.991044044494629, "learning_rate": 5.919457237472459e-06, "loss": 0.1619, "step": 418070 }, { "epoch": 2.4851543413520694, "grad_norm": 4.759401321411133, "learning_rate": 5.919253283008347e-06, "loss": 0.1489, "step": 418080 }, { "epoch": 2.4852137834287378, "grad_norm": 4.108858108520508, "learning_rate": 5.919049326961172e-06, "loss": 0.127, "step": 418090 }, { "epoch": 2.485273225505406, "grad_norm": 4.81680965423584, "learning_rate": 5.918845369331286e-06, "loss": 0.1292, "step": 418100 }, { "epoch": 2.4853326675820746, "grad_norm": 3.1346428394317627, "learning_rate": 5.918641410119038e-06, "loss": 0.1379, "step": 418110 }, { "epoch": 2.485392109658743, "grad_norm": 4.262000560760498, "learning_rate": 5.9184374493247784e-06, "loss": 0.1461, "step": 418120 }, { "epoch": 2.4854515517354114, "grad_norm": 3.7913002967834473, "learning_rate": 5.9182334869488625e-06, "loss": 0.1108, "step": 418130 }, { "epoch": 2.48551099381208, "grad_norm": 3.135690689086914, "learning_rate": 5.918029522991638e-06, "loss": 0.1262, "step": 418140 }, { "epoch": 2.4855704358887483, "grad_norm": 3.326087474822998, "learning_rate": 5.917825557453456e-06, "loss": 0.1125, "step": 418150 }, { "epoch": 2.4856298779654167, "grad_norm": 3.380871057510376, "learning_rate": 5.91762159033467e-06, "loss": 0.1451, "step": 418160 }, { "epoch": 2.485689320042085, "grad_norm": 3.8919918537139893, "learning_rate": 5.91741762163563e-06, "loss": 0.1286, "step": 418170 }, { "epoch": 2.4857487621187535, "grad_norm": 4.722357273101807, "learning_rate": 5.917213651356686e-06, "loss": 0.1334, "step": 418180 }, { "epoch": 2.485808204195422, "grad_norm": 4.233115196228027, "learning_rate": 5.917009679498191e-06, "loss": 0.1389, "step": 418190 }, { "epoch": 2.4858676462720903, "grad_norm": 4.997707843780518, "learning_rate": 5.916805706060498e-06, "loss": 0.1238, "step": 418200 }, { "epoch": 2.4859270883487588, "grad_norm": 4.262260437011719, "learning_rate": 5.916601731043955e-06, "loss": 0.122, "step": 418210 }, { "epoch": 2.4859865304254267, "grad_norm": 5.044402122497559, "learning_rate": 5.916397754448914e-06, "loss": 0.1585, "step": 418220 }, { "epoch": 2.4860459725020956, "grad_norm": 5.123881816864014, "learning_rate": 5.9161937762757275e-06, "loss": 0.1431, "step": 418230 }, { "epoch": 2.4861054145787636, "grad_norm": 5.125781536102295, "learning_rate": 5.915989796524746e-06, "loss": 0.1613, "step": 418240 }, { "epoch": 2.486164856655432, "grad_norm": 3.5017707347869873, "learning_rate": 5.915785815196319e-06, "loss": 0.13, "step": 418250 }, { "epoch": 2.4862242987321004, "grad_norm": 2.8599445819854736, "learning_rate": 5.915581832290801e-06, "loss": 0.124, "step": 418260 }, { "epoch": 2.486283740808769, "grad_norm": 7.216869354248047, "learning_rate": 5.915377847808542e-06, "loss": 0.1216, "step": 418270 }, { "epoch": 2.486343182885437, "grad_norm": 5.8946380615234375, "learning_rate": 5.915173861749892e-06, "loss": 0.1453, "step": 418280 }, { "epoch": 2.4864026249621056, "grad_norm": 3.516082525253296, "learning_rate": 5.914969874115205e-06, "loss": 0.1248, "step": 418290 }, { "epoch": 2.486462067038774, "grad_norm": 3.4761664867401123, "learning_rate": 5.914765884904829e-06, "loss": 0.1493, "step": 418300 }, { "epoch": 2.4865215091154425, "grad_norm": 3.8914954662323, "learning_rate": 5.9145618941191175e-06, "loss": 0.1367, "step": 418310 }, { "epoch": 2.486580951192111, "grad_norm": 4.537235260009766, "learning_rate": 5.914357901758423e-06, "loss": 0.14, "step": 418320 }, { "epoch": 2.4866403932687793, "grad_norm": 6.511337757110596, "learning_rate": 5.914153907823094e-06, "loss": 0.163, "step": 418330 }, { "epoch": 2.4866998353454477, "grad_norm": 3.9220447540283203, "learning_rate": 5.913949912313481e-06, "loss": 0.1521, "step": 418340 }, { "epoch": 2.486759277422116, "grad_norm": 4.8540754318237305, "learning_rate": 5.91374591522994e-06, "loss": 0.155, "step": 418350 }, { "epoch": 2.4868187194987845, "grad_norm": 4.9849677085876465, "learning_rate": 5.913541916572819e-06, "loss": 0.1372, "step": 418360 }, { "epoch": 2.486878161575453, "grad_norm": 3.4920411109924316, "learning_rate": 5.9133379163424695e-06, "loss": 0.1101, "step": 418370 }, { "epoch": 2.4869376036521214, "grad_norm": 3.8103864192962646, "learning_rate": 5.913133914539243e-06, "loss": 0.1287, "step": 418380 }, { "epoch": 2.4869970457287898, "grad_norm": 3.9181549549102783, "learning_rate": 5.9129299111634904e-06, "loss": 0.1302, "step": 418390 }, { "epoch": 2.487056487805458, "grad_norm": 3.547452926635742, "learning_rate": 5.912725906215565e-06, "loss": 0.1322, "step": 418400 }, { "epoch": 2.487115929882126, "grad_norm": 4.350948810577393, "learning_rate": 5.9125218996958135e-06, "loss": 0.1211, "step": 418410 }, { "epoch": 2.4871753719587946, "grad_norm": 3.530297040939331, "learning_rate": 5.912317891604593e-06, "loss": 0.1414, "step": 418420 }, { "epoch": 2.487234814035463, "grad_norm": 4.354362487792969, "learning_rate": 5.912113881942253e-06, "loss": 0.1432, "step": 418430 }, { "epoch": 2.4872942561121314, "grad_norm": 3.595909833908081, "learning_rate": 5.911909870709142e-06, "loss": 0.149, "step": 418440 }, { "epoch": 2.4873536981888, "grad_norm": 3.6928107738494873, "learning_rate": 5.911705857905614e-06, "loss": 0.1156, "step": 418450 }, { "epoch": 2.4874131402654682, "grad_norm": 3.867356538772583, "learning_rate": 5.9115018435320215e-06, "loss": 0.1365, "step": 418460 }, { "epoch": 2.4874725823421366, "grad_norm": 4.265722751617432, "learning_rate": 5.911297827588711e-06, "loss": 0.1266, "step": 418470 }, { "epoch": 2.487532024418805, "grad_norm": 4.494701862335205, "learning_rate": 5.911093810076039e-06, "loss": 0.1266, "step": 418480 }, { "epoch": 2.4875914664954735, "grad_norm": 3.597871780395508, "learning_rate": 5.910889790994355e-06, "loss": 0.1462, "step": 418490 }, { "epoch": 2.487650908572142, "grad_norm": 4.768195629119873, "learning_rate": 5.910685770344009e-06, "loss": 0.1471, "step": 418500 }, { "epoch": 2.4877103506488103, "grad_norm": 4.718822956085205, "learning_rate": 5.910481748125354e-06, "loss": 0.1441, "step": 418510 }, { "epoch": 2.4877697927254787, "grad_norm": 4.761790752410889, "learning_rate": 5.9102777243387396e-06, "loss": 0.1433, "step": 418520 }, { "epoch": 2.487829234802147, "grad_norm": 4.6835618019104, "learning_rate": 5.91007369898452e-06, "loss": 0.1351, "step": 418530 }, { "epoch": 2.4878886768788155, "grad_norm": 3.7333853244781494, "learning_rate": 5.909869672063043e-06, "loss": 0.1233, "step": 418540 }, { "epoch": 2.487948118955484, "grad_norm": 5.434311866760254, "learning_rate": 5.909665643574664e-06, "loss": 0.1395, "step": 418550 }, { "epoch": 2.4880075610321524, "grad_norm": 4.195230007171631, "learning_rate": 5.909461613519731e-06, "loss": 0.1243, "step": 418560 }, { "epoch": 2.488067003108821, "grad_norm": 3.9737915992736816, "learning_rate": 5.909257581898597e-06, "loss": 0.1334, "step": 418570 }, { "epoch": 2.4881264451854888, "grad_norm": 3.688101291656494, "learning_rate": 5.909053548711613e-06, "loss": 0.145, "step": 418580 }, { "epoch": 2.4881858872621576, "grad_norm": 4.133368968963623, "learning_rate": 5.9088495139591306e-06, "loss": 0.1375, "step": 418590 }, { "epoch": 2.4882453293388256, "grad_norm": 3.990907669067383, "learning_rate": 5.908645477641501e-06, "loss": 0.1334, "step": 418600 }, { "epoch": 2.488304771415494, "grad_norm": 3.6598167419433594, "learning_rate": 5.908441439759074e-06, "loss": 0.1287, "step": 418610 }, { "epoch": 2.4883642134921624, "grad_norm": 4.532447814941406, "learning_rate": 5.908237400312204e-06, "loss": 0.1354, "step": 418620 }, { "epoch": 2.488423655568831, "grad_norm": 4.435238838195801, "learning_rate": 5.908033359301239e-06, "loss": 0.1364, "step": 418630 }, { "epoch": 2.4884830976454992, "grad_norm": 3.540921449661255, "learning_rate": 5.907829316726534e-06, "loss": 0.1378, "step": 418640 }, { "epoch": 2.4885425397221677, "grad_norm": 5.100780487060547, "learning_rate": 5.907625272588437e-06, "loss": 0.1315, "step": 418650 }, { "epoch": 2.488601981798836, "grad_norm": 3.088594675064087, "learning_rate": 5.9074212268873035e-06, "loss": 0.1517, "step": 418660 }, { "epoch": 2.4886614238755045, "grad_norm": 4.212533473968506, "learning_rate": 5.90721717962348e-06, "loss": 0.1339, "step": 418670 }, { "epoch": 2.488720865952173, "grad_norm": 2.4273033142089844, "learning_rate": 5.907013130797321e-06, "loss": 0.1397, "step": 418680 }, { "epoch": 2.4887803080288413, "grad_norm": 3.9920542240142822, "learning_rate": 5.906809080409179e-06, "loss": 0.1183, "step": 418690 }, { "epoch": 2.4888397501055097, "grad_norm": 3.220529794692993, "learning_rate": 5.9066050284594e-06, "loss": 0.1301, "step": 418700 }, { "epoch": 2.488899192182178, "grad_norm": 3.829648017883301, "learning_rate": 5.906400974948342e-06, "loss": 0.1244, "step": 418710 }, { "epoch": 2.4889586342588466, "grad_norm": 3.296234130859375, "learning_rate": 5.906196919876353e-06, "loss": 0.1367, "step": 418720 }, { "epoch": 2.489018076335515, "grad_norm": 4.740233421325684, "learning_rate": 5.905992863243783e-06, "loss": 0.1406, "step": 418730 }, { "epoch": 2.4890775184121834, "grad_norm": 4.146695613861084, "learning_rate": 5.905788805050985e-06, "loss": 0.1275, "step": 418740 }, { "epoch": 2.489136960488852, "grad_norm": 5.381957054138184, "learning_rate": 5.905584745298311e-06, "loss": 0.1366, "step": 418750 }, { "epoch": 2.48919640256552, "grad_norm": 5.397671222686768, "learning_rate": 5.905380683986115e-06, "loss": 0.1255, "step": 418760 }, { "epoch": 2.489255844642188, "grad_norm": 3.2737081050872803, "learning_rate": 5.905176621114742e-06, "loss": 0.1297, "step": 418770 }, { "epoch": 2.489315286718857, "grad_norm": 3.3062386512756348, "learning_rate": 5.9049725566845485e-06, "loss": 0.1256, "step": 418780 }, { "epoch": 2.489374728795525, "grad_norm": 4.2623066902160645, "learning_rate": 5.904768490695885e-06, "loss": 0.1323, "step": 418790 }, { "epoch": 2.4894341708721934, "grad_norm": 6.092298984527588, "learning_rate": 5.904564423149099e-06, "loss": 0.1453, "step": 418800 }, { "epoch": 2.489493612948862, "grad_norm": 4.4274468421936035, "learning_rate": 5.9043603540445486e-06, "loss": 0.1275, "step": 418810 }, { "epoch": 2.4895530550255303, "grad_norm": 4.303726673126221, "learning_rate": 5.90415628338258e-06, "loss": 0.1369, "step": 418820 }, { "epoch": 2.4896124971021987, "grad_norm": 3.946592092514038, "learning_rate": 5.903952211163546e-06, "loss": 0.1457, "step": 418830 }, { "epoch": 2.489671939178867, "grad_norm": 3.850036144256592, "learning_rate": 5.9037481373878e-06, "loss": 0.1278, "step": 418840 }, { "epoch": 2.4897313812555355, "grad_norm": 3.825160503387451, "learning_rate": 5.90354406205569e-06, "loss": 0.1413, "step": 418850 }, { "epoch": 2.489790823332204, "grad_norm": 5.129980087280273, "learning_rate": 5.903339985167571e-06, "loss": 0.134, "step": 418860 }, { "epoch": 2.4898502654088723, "grad_norm": 5.453611850738525, "learning_rate": 5.903135906723791e-06, "loss": 0.1337, "step": 418870 }, { "epoch": 2.4899097074855407, "grad_norm": 3.8826773166656494, "learning_rate": 5.902931826724706e-06, "loss": 0.1499, "step": 418880 }, { "epoch": 2.489969149562209, "grad_norm": 4.307936668395996, "learning_rate": 5.902727745170663e-06, "loss": 0.14, "step": 418890 }, { "epoch": 2.4900285916388776, "grad_norm": 3.5500965118408203, "learning_rate": 5.902523662062014e-06, "loss": 0.1229, "step": 418900 }, { "epoch": 2.490088033715546, "grad_norm": 4.156890392303467, "learning_rate": 5.902319577399114e-06, "loss": 0.1239, "step": 418910 }, { "epoch": 2.4901474757922144, "grad_norm": 4.711849689483643, "learning_rate": 5.9021154911823105e-06, "loss": 0.1538, "step": 418920 }, { "epoch": 2.490206917868883, "grad_norm": 3.898109197616577, "learning_rate": 5.901911403411956e-06, "loss": 0.1249, "step": 418930 }, { "epoch": 2.4902663599455512, "grad_norm": 3.018859624862671, "learning_rate": 5.901707314088404e-06, "loss": 0.1296, "step": 418940 }, { "epoch": 2.4903258020222196, "grad_norm": 4.916834831237793, "learning_rate": 5.9015032232120036e-06, "loss": 0.1511, "step": 418950 }, { "epoch": 2.4903852440988876, "grad_norm": 3.9525582790374756, "learning_rate": 5.901299130783105e-06, "loss": 0.1326, "step": 418960 }, { "epoch": 2.4904446861755565, "grad_norm": 4.234785556793213, "learning_rate": 5.901095036802065e-06, "loss": 0.1382, "step": 418970 }, { "epoch": 2.4905041282522244, "grad_norm": 4.013622760772705, "learning_rate": 5.900890941269231e-06, "loss": 0.1352, "step": 418980 }, { "epoch": 2.490563570328893, "grad_norm": 4.703339099884033, "learning_rate": 5.900686844184954e-06, "loss": 0.1437, "step": 418990 }, { "epoch": 2.4906230124055613, "grad_norm": 4.719426155090332, "learning_rate": 5.900482745549588e-06, "loss": 0.1359, "step": 419000 }, { "epoch": 2.4906824544822297, "grad_norm": 5.5421295166015625, "learning_rate": 5.900278645363484e-06, "loss": 0.1301, "step": 419010 }, { "epoch": 2.490741896558898, "grad_norm": 4.627768516540527, "learning_rate": 5.90007454362699e-06, "loss": 0.1399, "step": 419020 }, { "epoch": 2.4908013386355665, "grad_norm": 3.865689754486084, "learning_rate": 5.899870440340463e-06, "loss": 0.128, "step": 419030 }, { "epoch": 2.490860780712235, "grad_norm": 4.191553115844727, "learning_rate": 5.899666335504251e-06, "loss": 0.1335, "step": 419040 }, { "epoch": 2.4909202227889033, "grad_norm": 3.166038751602173, "learning_rate": 5.899462229118707e-06, "loss": 0.1364, "step": 419050 }, { "epoch": 2.4909796648655718, "grad_norm": 4.856202125549316, "learning_rate": 5.899258121184179e-06, "loss": 0.125, "step": 419060 }, { "epoch": 2.49103910694224, "grad_norm": 4.384254455566406, "learning_rate": 5.899054011701023e-06, "loss": 0.1594, "step": 419070 }, { "epoch": 2.4910985490189086, "grad_norm": 3.7969017028808594, "learning_rate": 5.898849900669588e-06, "loss": 0.1434, "step": 419080 }, { "epoch": 2.491157991095577, "grad_norm": 3.4942593574523926, "learning_rate": 5.898645788090227e-06, "loss": 0.1237, "step": 419090 }, { "epoch": 2.4912174331722454, "grad_norm": 4.0456671714782715, "learning_rate": 5.898441673963291e-06, "loss": 0.1279, "step": 419100 }, { "epoch": 2.491276875248914, "grad_norm": 4.581978797912598, "learning_rate": 5.898237558289132e-06, "loss": 0.1393, "step": 419110 }, { "epoch": 2.4913363173255823, "grad_norm": 3.619128465652466, "learning_rate": 5.898033441068099e-06, "loss": 0.1286, "step": 419120 }, { "epoch": 2.4913957594022507, "grad_norm": 3.8054327964782715, "learning_rate": 5.897829322300546e-06, "loss": 0.1282, "step": 419130 }, { "epoch": 2.491455201478919, "grad_norm": 3.4593729972839355, "learning_rate": 5.897625201986823e-06, "loss": 0.1361, "step": 419140 }, { "epoch": 2.491514643555587, "grad_norm": 4.433602333068848, "learning_rate": 5.897421080127283e-06, "loss": 0.1132, "step": 419150 }, { "epoch": 2.4915740856322555, "grad_norm": 3.8085055351257324, "learning_rate": 5.897216956722276e-06, "loss": 0.1184, "step": 419160 }, { "epoch": 2.491633527708924, "grad_norm": 5.359139442443848, "learning_rate": 5.897012831772156e-06, "loss": 0.1211, "step": 419170 }, { "epoch": 2.4916929697855923, "grad_norm": 5.2033371925354, "learning_rate": 5.896808705277272e-06, "loss": 0.1476, "step": 419180 }, { "epoch": 2.4917524118622607, "grad_norm": 8.37836742401123, "learning_rate": 5.896604577237974e-06, "loss": 0.1366, "step": 419190 }, { "epoch": 2.491811853938929, "grad_norm": 4.523570537567139, "learning_rate": 5.89640044765462e-06, "loss": 0.1414, "step": 419200 }, { "epoch": 2.4918712960155975, "grad_norm": 4.274759769439697, "learning_rate": 5.896196316527556e-06, "loss": 0.1298, "step": 419210 }, { "epoch": 2.491930738092266, "grad_norm": 4.171969890594482, "learning_rate": 5.895992183857133e-06, "loss": 0.1453, "step": 419220 }, { "epoch": 2.4919901801689344, "grad_norm": 4.679347038269043, "learning_rate": 5.895788049643707e-06, "loss": 0.1179, "step": 419230 }, { "epoch": 2.492049622245603, "grad_norm": 4.0621337890625, "learning_rate": 5.895583913887627e-06, "loss": 0.1356, "step": 419240 }, { "epoch": 2.492109064322271, "grad_norm": 3.3897783756256104, "learning_rate": 5.895379776589244e-06, "loss": 0.1544, "step": 419250 }, { "epoch": 2.4921685063989396, "grad_norm": 3.511737823486328, "learning_rate": 5.89517563774891e-06, "loss": 0.1213, "step": 419260 }, { "epoch": 2.492227948475608, "grad_norm": 3.039555072784424, "learning_rate": 5.8949714973669784e-06, "loss": 0.1404, "step": 419270 }, { "epoch": 2.4922873905522764, "grad_norm": 3.779694080352783, "learning_rate": 5.8947673554437954e-06, "loss": 0.1448, "step": 419280 }, { "epoch": 2.492346832628945, "grad_norm": 3.7884466648101807, "learning_rate": 5.894563211979719e-06, "loss": 0.1337, "step": 419290 }, { "epoch": 2.4924062747056133, "grad_norm": 4.076572418212891, "learning_rate": 5.894359066975097e-06, "loss": 0.1307, "step": 419300 }, { "epoch": 2.4924657167822817, "grad_norm": 3.6768927574157715, "learning_rate": 5.894154920430284e-06, "loss": 0.1363, "step": 419310 }, { "epoch": 2.4925251588589497, "grad_norm": 4.607493877410889, "learning_rate": 5.893950772345627e-06, "loss": 0.1268, "step": 419320 }, { "epoch": 2.4925846009356185, "grad_norm": 4.146342754364014, "learning_rate": 5.893746622721481e-06, "loss": 0.1242, "step": 419330 }, { "epoch": 2.4926440430122865, "grad_norm": 3.6681599617004395, "learning_rate": 5.893542471558198e-06, "loss": 0.1288, "step": 419340 }, { "epoch": 2.492703485088955, "grad_norm": 3.9620587825775146, "learning_rate": 5.893338318856125e-06, "loss": 0.1372, "step": 419350 }, { "epoch": 2.4927629271656233, "grad_norm": 3.3526556491851807, "learning_rate": 5.89313416461562e-06, "loss": 0.1413, "step": 419360 }, { "epoch": 2.4928223692422917, "grad_norm": 4.917728900909424, "learning_rate": 5.8929300088370316e-06, "loss": 0.1127, "step": 419370 }, { "epoch": 2.49288181131896, "grad_norm": 3.8734638690948486, "learning_rate": 5.892725851520709e-06, "loss": 0.1259, "step": 419380 }, { "epoch": 2.4929412533956286, "grad_norm": 3.6780078411102295, "learning_rate": 5.892521692667007e-06, "loss": 0.133, "step": 419390 }, { "epoch": 2.493000695472297, "grad_norm": 4.543517589569092, "learning_rate": 5.892317532276275e-06, "loss": 0.1498, "step": 419400 }, { "epoch": 2.4930601375489654, "grad_norm": 3.1830596923828125, "learning_rate": 5.892113370348867e-06, "loss": 0.1225, "step": 419410 }, { "epoch": 2.493119579625634, "grad_norm": 4.0145487785339355, "learning_rate": 5.8919092068851325e-06, "loss": 0.1458, "step": 419420 }, { "epoch": 2.493179021702302, "grad_norm": 4.564702033996582, "learning_rate": 5.8917050418854245e-06, "loss": 0.128, "step": 419430 }, { "epoch": 2.4932384637789706, "grad_norm": 4.563717842102051, "learning_rate": 5.891500875350095e-06, "loss": 0.1464, "step": 419440 }, { "epoch": 2.493297905855639, "grad_norm": 5.464439868927002, "learning_rate": 5.891296707279493e-06, "loss": 0.1216, "step": 419450 }, { "epoch": 2.4933573479323075, "grad_norm": 4.573265075683594, "learning_rate": 5.891092537673973e-06, "loss": 0.1527, "step": 419460 }, { "epoch": 2.493416790008976, "grad_norm": 3.5727601051330566, "learning_rate": 5.890888366533884e-06, "loss": 0.1349, "step": 419470 }, { "epoch": 2.4934762320856443, "grad_norm": 3.5787031650543213, "learning_rate": 5.890684193859579e-06, "loss": 0.1277, "step": 419480 }, { "epoch": 2.4935356741623127, "grad_norm": 4.608006954193115, "learning_rate": 5.890480019651411e-06, "loss": 0.1405, "step": 419490 }, { "epoch": 2.493595116238981, "grad_norm": 4.247978210449219, "learning_rate": 5.890275843909729e-06, "loss": 0.1348, "step": 419500 }, { "epoch": 2.493654558315649, "grad_norm": 4.20860481262207, "learning_rate": 5.890071666634887e-06, "loss": 0.1269, "step": 419510 }, { "epoch": 2.493714000392318, "grad_norm": 4.11531400680542, "learning_rate": 5.889867487827233e-06, "loss": 0.1285, "step": 419520 }, { "epoch": 2.493773442468986, "grad_norm": 4.857875823974609, "learning_rate": 5.889663307487123e-06, "loss": 0.1596, "step": 419530 }, { "epoch": 2.4938328845456543, "grad_norm": 3.8003344535827637, "learning_rate": 5.889459125614907e-06, "loss": 0.1443, "step": 419540 }, { "epoch": 2.4938923266223227, "grad_norm": 2.956465721130371, "learning_rate": 5.889254942210935e-06, "loss": 0.1327, "step": 419550 }, { "epoch": 2.493951768698991, "grad_norm": 4.186097621917725, "learning_rate": 5.889050757275559e-06, "loss": 0.1506, "step": 419560 }, { "epoch": 2.4940112107756596, "grad_norm": 6.099770545959473, "learning_rate": 5.888846570809135e-06, "loss": 0.1573, "step": 419570 }, { "epoch": 2.494070652852328, "grad_norm": 3.548738479614258, "learning_rate": 5.888642382812008e-06, "loss": 0.134, "step": 419580 }, { "epoch": 2.4941300949289964, "grad_norm": 3.220703601837158, "learning_rate": 5.888438193284534e-06, "loss": 0.1308, "step": 419590 }, { "epoch": 2.494189537005665, "grad_norm": 4.02736759185791, "learning_rate": 5.888234002227063e-06, "loss": 0.1533, "step": 419600 }, { "epoch": 2.4942489790823332, "grad_norm": 4.818426609039307, "learning_rate": 5.888029809639947e-06, "loss": 0.1532, "step": 419610 }, { "epoch": 2.4943084211590016, "grad_norm": 3.7696022987365723, "learning_rate": 5.887825615523537e-06, "loss": 0.1201, "step": 419620 }, { "epoch": 2.49436786323567, "grad_norm": 2.981060028076172, "learning_rate": 5.887621419878187e-06, "loss": 0.1383, "step": 419630 }, { "epoch": 2.4944273053123385, "grad_norm": 3.4349443912506104, "learning_rate": 5.887417222704245e-06, "loss": 0.1413, "step": 419640 }, { "epoch": 2.494486747389007, "grad_norm": 4.7367329597473145, "learning_rate": 5.887213024002067e-06, "loss": 0.1513, "step": 419650 }, { "epoch": 2.4945461894656753, "grad_norm": 3.8183634281158447, "learning_rate": 5.887008823772001e-06, "loss": 0.135, "step": 419660 }, { "epoch": 2.4946056315423437, "grad_norm": 4.720698356628418, "learning_rate": 5.886804622014399e-06, "loss": 0.1289, "step": 419670 }, { "epoch": 2.494665073619012, "grad_norm": 3.570908546447754, "learning_rate": 5.886600418729616e-06, "loss": 0.1431, "step": 419680 }, { "epoch": 2.4947245156956805, "grad_norm": 5.431459426879883, "learning_rate": 5.886396213918e-06, "loss": 0.1375, "step": 419690 }, { "epoch": 2.4947839577723485, "grad_norm": 4.079071998596191, "learning_rate": 5.886192007579904e-06, "loss": 0.1483, "step": 419700 }, { "epoch": 2.4948433998490174, "grad_norm": 3.598783016204834, "learning_rate": 5.88598779971568e-06, "loss": 0.1383, "step": 419710 }, { "epoch": 2.4949028419256853, "grad_norm": 3.813023805618286, "learning_rate": 5.885783590325679e-06, "loss": 0.1314, "step": 419720 }, { "epoch": 2.4949622840023538, "grad_norm": 4.058490753173828, "learning_rate": 5.885579379410253e-06, "loss": 0.1278, "step": 419730 }, { "epoch": 2.495021726079022, "grad_norm": 5.407655239105225, "learning_rate": 5.885375166969752e-06, "loss": 0.1278, "step": 419740 }, { "epoch": 2.4950811681556906, "grad_norm": 4.918900489807129, "learning_rate": 5.885170953004532e-06, "loss": 0.1553, "step": 419750 }, { "epoch": 2.495140610232359, "grad_norm": 4.0935468673706055, "learning_rate": 5.884966737514941e-06, "loss": 0.1151, "step": 419760 }, { "epoch": 2.4952000523090274, "grad_norm": 4.092733383178711, "learning_rate": 5.884762520501331e-06, "loss": 0.1333, "step": 419770 }, { "epoch": 2.495259494385696, "grad_norm": 5.061850547790527, "learning_rate": 5.884558301964055e-06, "loss": 0.1445, "step": 419780 }, { "epoch": 2.4953189364623642, "grad_norm": 4.822961330413818, "learning_rate": 5.884354081903465e-06, "loss": 0.1547, "step": 419790 }, { "epoch": 2.4953783785390327, "grad_norm": 3.9126758575439453, "learning_rate": 5.88414986031991e-06, "loss": 0.1196, "step": 419800 }, { "epoch": 2.495437820615701, "grad_norm": 4.588953495025635, "learning_rate": 5.8839456372137445e-06, "loss": 0.1141, "step": 419810 }, { "epoch": 2.4954972626923695, "grad_norm": 3.6186206340789795, "learning_rate": 5.88374141258532e-06, "loss": 0.1499, "step": 419820 }, { "epoch": 2.495556704769038, "grad_norm": 3.6225926876068115, "learning_rate": 5.883537186434986e-06, "loss": 0.1366, "step": 419830 }, { "epoch": 2.4956161468457063, "grad_norm": 3.920788526535034, "learning_rate": 5.883332958763094e-06, "loss": 0.1313, "step": 419840 }, { "epoch": 2.4956755889223747, "grad_norm": 5.19431734085083, "learning_rate": 5.88312872957e-06, "loss": 0.1538, "step": 419850 }, { "epoch": 2.495735030999043, "grad_norm": 4.549718856811523, "learning_rate": 5.882924498856052e-06, "loss": 0.1367, "step": 419860 }, { "epoch": 2.4957944730757116, "grad_norm": 4.246346950531006, "learning_rate": 5.882720266621602e-06, "loss": 0.1518, "step": 419870 }, { "epoch": 2.49585391515238, "grad_norm": 4.276489734649658, "learning_rate": 5.882516032867004e-06, "loss": 0.1438, "step": 419880 }, { "epoch": 2.495913357229048, "grad_norm": 3.4379026889801025, "learning_rate": 5.882311797592607e-06, "loss": 0.1364, "step": 419890 }, { "epoch": 2.4959727993057164, "grad_norm": 3.4115216732025146, "learning_rate": 5.882107560798763e-06, "loss": 0.1573, "step": 419900 }, { "epoch": 2.4960322413823848, "grad_norm": 4.064000606536865, "learning_rate": 5.8819033224858254e-06, "loss": 0.1523, "step": 419910 }, { "epoch": 2.496091683459053, "grad_norm": 4.39392614364624, "learning_rate": 5.881699082654146e-06, "loss": 0.141, "step": 419920 }, { "epoch": 2.4961511255357216, "grad_norm": 3.7396199703216553, "learning_rate": 5.881494841304074e-06, "loss": 0.1405, "step": 419930 }, { "epoch": 2.49621056761239, "grad_norm": 4.553895473480225, "learning_rate": 5.8812905984359635e-06, "loss": 0.1312, "step": 419940 }, { "epoch": 2.4962700096890584, "grad_norm": 3.4666621685028076, "learning_rate": 5.881086354050165e-06, "loss": 0.1167, "step": 419950 }, { "epoch": 2.496329451765727, "grad_norm": 4.6478681564331055, "learning_rate": 5.880882108147031e-06, "loss": 0.1325, "step": 419960 }, { "epoch": 2.4963888938423953, "grad_norm": 3.412966728210449, "learning_rate": 5.8806778607269135e-06, "loss": 0.1339, "step": 419970 }, { "epoch": 2.4964483359190637, "grad_norm": 3.83408522605896, "learning_rate": 5.880473611790163e-06, "loss": 0.1354, "step": 419980 }, { "epoch": 2.496507777995732, "grad_norm": 3.9943034648895264, "learning_rate": 5.880269361337132e-06, "loss": 0.1372, "step": 419990 }, { "epoch": 2.4965672200724005, "grad_norm": 2.769038677215576, "learning_rate": 5.8800651093681715e-06, "loss": 0.1384, "step": 420000 }, { "epoch": 2.496626662149069, "grad_norm": 3.8557345867156982, "learning_rate": 5.879860855883634e-06, "loss": 0.1341, "step": 420010 }, { "epoch": 2.4966861042257373, "grad_norm": 3.6745824813842773, "learning_rate": 5.879656600883873e-06, "loss": 0.1425, "step": 420020 }, { "epoch": 2.4967455463024057, "grad_norm": 3.95756459236145, "learning_rate": 5.879452344369236e-06, "loss": 0.1286, "step": 420030 }, { "epoch": 2.496804988379074, "grad_norm": 4.342988014221191, "learning_rate": 5.879248086340078e-06, "loss": 0.1407, "step": 420040 }, { "epoch": 2.4968644304557426, "grad_norm": 5.489902973175049, "learning_rate": 5.879043826796751e-06, "loss": 0.1278, "step": 420050 }, { "epoch": 2.4969238725324105, "grad_norm": 4.901906490325928, "learning_rate": 5.8788395657396035e-06, "loss": 0.1383, "step": 420060 }, { "epoch": 2.4969833146090794, "grad_norm": 4.601231575012207, "learning_rate": 5.8786353031689905e-06, "loss": 0.1525, "step": 420070 }, { "epoch": 2.4970427566857474, "grad_norm": 3.586289405822754, "learning_rate": 5.878431039085263e-06, "loss": 0.1231, "step": 420080 }, { "epoch": 2.497102198762416, "grad_norm": 4.695707321166992, "learning_rate": 5.878226773488772e-06, "loss": 0.1351, "step": 420090 }, { "epoch": 2.497161640839084, "grad_norm": 3.759399890899658, "learning_rate": 5.878022506379869e-06, "loss": 0.1543, "step": 420100 }, { "epoch": 2.4972210829157526, "grad_norm": 5.116118431091309, "learning_rate": 5.8778182377589075e-06, "loss": 0.1318, "step": 420110 }, { "epoch": 2.497280524992421, "grad_norm": 7.912299156188965, "learning_rate": 5.877613967626239e-06, "loss": 0.1249, "step": 420120 }, { "epoch": 2.4973399670690895, "grad_norm": 4.305804252624512, "learning_rate": 5.877409695982213e-06, "loss": 0.127, "step": 420130 }, { "epoch": 2.497399409145758, "grad_norm": 3.9315223693847656, "learning_rate": 5.877205422827183e-06, "loss": 0.1323, "step": 420140 }, { "epoch": 2.4974588512224263, "grad_norm": 6.48286247253418, "learning_rate": 5.877001148161502e-06, "loss": 0.1226, "step": 420150 }, { "epoch": 2.4975182932990947, "grad_norm": 4.31004524230957, "learning_rate": 5.876796871985518e-06, "loss": 0.1448, "step": 420160 }, { "epoch": 2.497577735375763, "grad_norm": 4.233401775360107, "learning_rate": 5.876592594299586e-06, "loss": 0.1304, "step": 420170 }, { "epoch": 2.4976371774524315, "grad_norm": 4.239774703979492, "learning_rate": 5.876388315104058e-06, "loss": 0.1377, "step": 420180 }, { "epoch": 2.4976966195291, "grad_norm": 5.1034440994262695, "learning_rate": 5.876184034399285e-06, "loss": 0.1504, "step": 420190 }, { "epoch": 2.4977560616057684, "grad_norm": 3.3506736755371094, "learning_rate": 5.875979752185617e-06, "loss": 0.1253, "step": 420200 }, { "epoch": 2.4978155036824368, "grad_norm": 4.638739585876465, "learning_rate": 5.8757754684634084e-06, "loss": 0.1209, "step": 420210 }, { "epoch": 2.497874945759105, "grad_norm": 4.2373199462890625, "learning_rate": 5.87557118323301e-06, "loss": 0.1519, "step": 420220 }, { "epoch": 2.4979343878357736, "grad_norm": 3.9306254386901855, "learning_rate": 5.875366896494773e-06, "loss": 0.136, "step": 420230 }, { "epoch": 2.497993829912442, "grad_norm": 5.095818996429443, "learning_rate": 5.87516260824905e-06, "loss": 0.1516, "step": 420240 }, { "epoch": 2.49805327198911, "grad_norm": 4.743427276611328, "learning_rate": 5.874958318496193e-06, "loss": 0.1475, "step": 420250 }, { "epoch": 2.498112714065779, "grad_norm": 3.4260919094085693, "learning_rate": 5.874754027236552e-06, "loss": 0.1492, "step": 420260 }, { "epoch": 2.498172156142447, "grad_norm": 4.792221546173096, "learning_rate": 5.8745497344704815e-06, "loss": 0.1285, "step": 420270 }, { "epoch": 2.4982315982191152, "grad_norm": 2.601320505142212, "learning_rate": 5.874345440198331e-06, "loss": 0.129, "step": 420280 }, { "epoch": 2.4982910402957836, "grad_norm": 4.597755432128906, "learning_rate": 5.874141144420453e-06, "loss": 0.1627, "step": 420290 }, { "epoch": 2.498350482372452, "grad_norm": 5.169093132019043, "learning_rate": 5.873936847137202e-06, "loss": 0.1194, "step": 420300 }, { "epoch": 2.4984099244491205, "grad_norm": 5.210690021514893, "learning_rate": 5.873732548348926e-06, "loss": 0.1617, "step": 420310 }, { "epoch": 2.498469366525789, "grad_norm": 4.04942512512207, "learning_rate": 5.873528248055978e-06, "loss": 0.1337, "step": 420320 }, { "epoch": 2.4985288086024573, "grad_norm": 4.232375621795654, "learning_rate": 5.873323946258711e-06, "loss": 0.135, "step": 420330 }, { "epoch": 2.4985882506791257, "grad_norm": 3.5050017833709717, "learning_rate": 5.8731196429574755e-06, "loss": 0.1504, "step": 420340 }, { "epoch": 2.498647692755794, "grad_norm": 5.238691329956055, "learning_rate": 5.872915338152623e-06, "loss": 0.1436, "step": 420350 }, { "epoch": 2.4987071348324625, "grad_norm": 4.190171241760254, "learning_rate": 5.872711031844507e-06, "loss": 0.1283, "step": 420360 }, { "epoch": 2.498766576909131, "grad_norm": 3.991912603378296, "learning_rate": 5.8725067240334785e-06, "loss": 0.1393, "step": 420370 }, { "epoch": 2.4988260189857994, "grad_norm": 4.421627044677734, "learning_rate": 5.87230241471989e-06, "loss": 0.1363, "step": 420380 }, { "epoch": 2.498885461062468, "grad_norm": 4.344768524169922, "learning_rate": 5.8720981039040904e-06, "loss": 0.1475, "step": 420390 }, { "epoch": 2.498944903139136, "grad_norm": 3.7367477416992188, "learning_rate": 5.871893791586436e-06, "loss": 0.1348, "step": 420400 }, { "epoch": 2.4990043452158046, "grad_norm": 5.020142555236816, "learning_rate": 5.871689477767275e-06, "loss": 0.1392, "step": 420410 }, { "epoch": 2.499063787292473, "grad_norm": 3.1921403408050537, "learning_rate": 5.871485162446961e-06, "loss": 0.1294, "step": 420420 }, { "epoch": 2.4991232293691414, "grad_norm": 3.6653177738189697, "learning_rate": 5.871280845625846e-06, "loss": 0.1293, "step": 420430 }, { "epoch": 2.4991826714458094, "grad_norm": 2.8571057319641113, "learning_rate": 5.871076527304283e-06, "loss": 0.1359, "step": 420440 }, { "epoch": 2.4992421135224783, "grad_norm": 3.8161168098449707, "learning_rate": 5.8708722074826195e-06, "loss": 0.1328, "step": 420450 }, { "epoch": 2.4993015555991462, "grad_norm": 4.013557434082031, "learning_rate": 5.870667886161212e-06, "loss": 0.1327, "step": 420460 }, { "epoch": 2.4993609976758147, "grad_norm": 4.284398078918457, "learning_rate": 5.870463563340411e-06, "loss": 0.1279, "step": 420470 }, { "epoch": 2.499420439752483, "grad_norm": 5.378366470336914, "learning_rate": 5.870259239020565e-06, "loss": 0.1332, "step": 420480 }, { "epoch": 2.4994798818291515, "grad_norm": 3.9895553588867188, "learning_rate": 5.870054913202031e-06, "loss": 0.1308, "step": 420490 }, { "epoch": 2.49953932390582, "grad_norm": 5.838185787200928, "learning_rate": 5.869850585885157e-06, "loss": 0.1374, "step": 420500 }, { "epoch": 2.4995987659824883, "grad_norm": 4.128244400024414, "learning_rate": 5.869646257070299e-06, "loss": 0.1614, "step": 420510 }, { "epoch": 2.4996582080591567, "grad_norm": 3.737902879714966, "learning_rate": 5.869441926757804e-06, "loss": 0.1454, "step": 420520 }, { "epoch": 2.499717650135825, "grad_norm": 6.04931640625, "learning_rate": 5.8692375949480275e-06, "loss": 0.118, "step": 420530 }, { "epoch": 2.4997770922124936, "grad_norm": 4.9292144775390625, "learning_rate": 5.86903326164132e-06, "loss": 0.1262, "step": 420540 }, { "epoch": 2.499836534289162, "grad_norm": 4.76749324798584, "learning_rate": 5.868828926838033e-06, "loss": 0.1382, "step": 420550 }, { "epoch": 2.4998959763658304, "grad_norm": 3.884752035140991, "learning_rate": 5.8686245905385195e-06, "loss": 0.1474, "step": 420560 }, { "epoch": 2.499955418442499, "grad_norm": 5.000776767730713, "learning_rate": 5.8684202527431314e-06, "loss": 0.1385, "step": 420570 }, { "epoch": 2.500014860519167, "grad_norm": 4.802066802978516, "learning_rate": 5.868215913452219e-06, "loss": 0.121, "step": 420580 }, { "epoch": 2.5000743025958356, "grad_norm": 5.806636810302734, "learning_rate": 5.868011572666136e-06, "loss": 0.1529, "step": 420590 }, { "epoch": 2.500133744672504, "grad_norm": 6.811521530151367, "learning_rate": 5.867807230385233e-06, "loss": 0.136, "step": 420600 }, { "epoch": 2.500193186749172, "grad_norm": 4.614683151245117, "learning_rate": 5.867602886609862e-06, "loss": 0.1532, "step": 420610 }, { "epoch": 2.500252628825841, "grad_norm": 4.54396390914917, "learning_rate": 5.867398541340375e-06, "loss": 0.1137, "step": 420620 }, { "epoch": 2.500312070902509, "grad_norm": 4.262351036071777, "learning_rate": 5.867194194577125e-06, "loss": 0.137, "step": 420630 }, { "epoch": 2.5003715129791777, "grad_norm": 4.094804763793945, "learning_rate": 5.866989846320464e-06, "loss": 0.1299, "step": 420640 }, { "epoch": 2.5004309550558457, "grad_norm": 3.099195957183838, "learning_rate": 5.86678549657074e-06, "loss": 0.1366, "step": 420650 }, { "epoch": 2.500490397132514, "grad_norm": 4.963058948516846, "learning_rate": 5.866581145328312e-06, "loss": 0.1388, "step": 420660 }, { "epoch": 2.5005498392091825, "grad_norm": 3.688944101333618, "learning_rate": 5.866376792593525e-06, "loss": 0.1295, "step": 420670 }, { "epoch": 2.500609281285851, "grad_norm": 4.483710765838623, "learning_rate": 5.866172438366735e-06, "loss": 0.1231, "step": 420680 }, { "epoch": 2.5006687233625193, "grad_norm": 3.399817943572998, "learning_rate": 5.865968082648292e-06, "loss": 0.1314, "step": 420690 }, { "epoch": 2.5007281654391877, "grad_norm": 3.494917869567871, "learning_rate": 5.86576372543855e-06, "loss": 0.1285, "step": 420700 }, { "epoch": 2.500787607515856, "grad_norm": 4.659224510192871, "learning_rate": 5.865559366737858e-06, "loss": 0.1387, "step": 420710 }, { "epoch": 2.5008470495925246, "grad_norm": 4.706691265106201, "learning_rate": 5.8653550065465694e-06, "loss": 0.1461, "step": 420720 }, { "epoch": 2.500906491669193, "grad_norm": 4.928922653198242, "learning_rate": 5.865150644865038e-06, "loss": 0.1339, "step": 420730 }, { "epoch": 2.5009659337458614, "grad_norm": 3.986381769180298, "learning_rate": 5.8649462816936124e-06, "loss": 0.1469, "step": 420740 }, { "epoch": 2.50102537582253, "grad_norm": 4.570530414581299, "learning_rate": 5.864741917032646e-06, "loss": 0.134, "step": 420750 }, { "epoch": 2.5010848178991982, "grad_norm": 3.8688805103302, "learning_rate": 5.864537550882492e-06, "loss": 0.1351, "step": 420760 }, { "epoch": 2.5011442599758666, "grad_norm": 4.756344795227051, "learning_rate": 5.8643331832435005e-06, "loss": 0.1356, "step": 420770 }, { "epoch": 2.501203702052535, "grad_norm": 5.562851905822754, "learning_rate": 5.864128814116023e-06, "loss": 0.1304, "step": 420780 }, { "epoch": 2.5012631441292035, "grad_norm": 3.1503145694732666, "learning_rate": 5.863924443500415e-06, "loss": 0.1214, "step": 420790 }, { "epoch": 2.5013225862058714, "grad_norm": 4.825741291046143, "learning_rate": 5.8637200713970255e-06, "loss": 0.1338, "step": 420800 }, { "epoch": 2.5013820282825403, "grad_norm": 4.649560928344727, "learning_rate": 5.8635156978062055e-06, "loss": 0.1359, "step": 420810 }, { "epoch": 2.5014414703592083, "grad_norm": 4.042854309082031, "learning_rate": 5.86331132272831e-06, "loss": 0.1287, "step": 420820 }, { "epoch": 2.501500912435877, "grad_norm": 4.20686149597168, "learning_rate": 5.863106946163688e-06, "loss": 0.1387, "step": 420830 }, { "epoch": 2.501560354512545, "grad_norm": 3.7662158012390137, "learning_rate": 5.862902568112694e-06, "loss": 0.1246, "step": 420840 }, { "epoch": 2.5016197965892135, "grad_norm": 4.009052276611328, "learning_rate": 5.862698188575677e-06, "loss": 0.1343, "step": 420850 }, { "epoch": 2.501679238665882, "grad_norm": 4.277288913726807, "learning_rate": 5.8624938075529925e-06, "loss": 0.1219, "step": 420860 }, { "epoch": 2.5017386807425503, "grad_norm": 4.6301188468933105, "learning_rate": 5.862289425044992e-06, "loss": 0.1308, "step": 420870 }, { "epoch": 2.5017981228192188, "grad_norm": 4.927999019622803, "learning_rate": 5.862085041052023e-06, "loss": 0.1314, "step": 420880 }, { "epoch": 2.501857564895887, "grad_norm": 3.0837299823760986, "learning_rate": 5.861880655574442e-06, "loss": 0.1425, "step": 420890 }, { "epoch": 2.5019170069725556, "grad_norm": 3.8336238861083984, "learning_rate": 5.8616762686126005e-06, "loss": 0.137, "step": 420900 }, { "epoch": 2.501976449049224, "grad_norm": 3.727656841278076, "learning_rate": 5.861471880166849e-06, "loss": 0.1412, "step": 420910 }, { "epoch": 2.5020358911258924, "grad_norm": 5.09941291809082, "learning_rate": 5.86126749023754e-06, "loss": 0.142, "step": 420920 }, { "epoch": 2.502095333202561, "grad_norm": 3.6579549312591553, "learning_rate": 5.8610630988250265e-06, "loss": 0.1404, "step": 420930 }, { "epoch": 2.5021547752792292, "grad_norm": 3.999166250228882, "learning_rate": 5.860858705929657e-06, "loss": 0.1397, "step": 420940 }, { "epoch": 2.5022142173558977, "grad_norm": 3.2076425552368164, "learning_rate": 5.860654311551789e-06, "loss": 0.1251, "step": 420950 }, { "epoch": 2.502273659432566, "grad_norm": 3.321154832839966, "learning_rate": 5.860449915691771e-06, "loss": 0.1296, "step": 420960 }, { "epoch": 2.5023331015092345, "grad_norm": 4.963196754455566, "learning_rate": 5.860245518349954e-06, "loss": 0.1313, "step": 420970 }, { "epoch": 2.502392543585903, "grad_norm": 5.331099987030029, "learning_rate": 5.860041119526694e-06, "loss": 0.1314, "step": 420980 }, { "epoch": 2.502451985662571, "grad_norm": 4.258309364318848, "learning_rate": 5.8598367192223395e-06, "loss": 0.1161, "step": 420990 }, { "epoch": 2.5025114277392397, "grad_norm": 4.371405124664307, "learning_rate": 5.859632317437243e-06, "loss": 0.1368, "step": 421000 }, { "epoch": 2.5025708698159077, "grad_norm": 2.848367929458618, "learning_rate": 5.859427914171757e-06, "loss": 0.1289, "step": 421010 }, { "epoch": 2.502630311892576, "grad_norm": 3.6935386657714844, "learning_rate": 5.859223509426235e-06, "loss": 0.1099, "step": 421020 }, { "epoch": 2.5026897539692445, "grad_norm": 4.999719619750977, "learning_rate": 5.859019103201026e-06, "loss": 0.1352, "step": 421030 }, { "epoch": 2.502749196045913, "grad_norm": 4.4516987800598145, "learning_rate": 5.858814695496484e-06, "loss": 0.1174, "step": 421040 }, { "epoch": 2.5028086381225814, "grad_norm": 4.372279167175293, "learning_rate": 5.858610286312961e-06, "loss": 0.1256, "step": 421050 }, { "epoch": 2.50286808019925, "grad_norm": 4.840541362762451, "learning_rate": 5.858405875650809e-06, "loss": 0.1126, "step": 421060 }, { "epoch": 2.502927522275918, "grad_norm": 3.739396810531616, "learning_rate": 5.858201463510378e-06, "loss": 0.1216, "step": 421070 }, { "epoch": 2.5029869643525866, "grad_norm": 4.086385726928711, "learning_rate": 5.857997049892023e-06, "loss": 0.1296, "step": 421080 }, { "epoch": 2.503046406429255, "grad_norm": 5.118285179138184, "learning_rate": 5.857792634796096e-06, "loss": 0.1372, "step": 421090 }, { "epoch": 2.5031058485059234, "grad_norm": 4.267511367797852, "learning_rate": 5.857588218222945e-06, "loss": 0.1377, "step": 421100 }, { "epoch": 2.503165290582592, "grad_norm": 5.119570732116699, "learning_rate": 5.8573838001729266e-06, "loss": 0.129, "step": 421110 }, { "epoch": 2.5032247326592603, "grad_norm": 4.825341701507568, "learning_rate": 5.857179380646391e-06, "loss": 0.1243, "step": 421120 }, { "epoch": 2.5032841747359287, "grad_norm": 4.306369781494141, "learning_rate": 5.856974959643689e-06, "loss": 0.1528, "step": 421130 }, { "epoch": 2.503343616812597, "grad_norm": 5.803769588470459, "learning_rate": 5.856770537165175e-06, "loss": 0.1527, "step": 421140 }, { "epoch": 2.5034030588892655, "grad_norm": 4.031641960144043, "learning_rate": 5.856566113211199e-06, "loss": 0.121, "step": 421150 }, { "epoch": 2.5034625009659335, "grad_norm": 4.1122212409973145, "learning_rate": 5.856361687782115e-06, "loss": 0.1599, "step": 421160 }, { "epoch": 2.5035219430426023, "grad_norm": 4.916704177856445, "learning_rate": 5.856157260878273e-06, "loss": 0.1447, "step": 421170 }, { "epoch": 2.5035813851192703, "grad_norm": 3.7850444316864014, "learning_rate": 5.855952832500027e-06, "loss": 0.1598, "step": 421180 }, { "epoch": 2.503640827195939, "grad_norm": 4.510378837585449, "learning_rate": 5.8557484026477275e-06, "loss": 0.137, "step": 421190 }, { "epoch": 2.503700269272607, "grad_norm": 3.7260706424713135, "learning_rate": 5.8555439713217264e-06, "loss": 0.1381, "step": 421200 }, { "epoch": 2.5037597113492756, "grad_norm": 5.025536060333252, "learning_rate": 5.855339538522378e-06, "loss": 0.1303, "step": 421210 }, { "epoch": 2.503819153425944, "grad_norm": 4.9303693771362305, "learning_rate": 5.855135104250033e-06, "loss": 0.1393, "step": 421220 }, { "epoch": 2.5038785955026124, "grad_norm": 2.738874673843384, "learning_rate": 5.854930668505041e-06, "loss": 0.1352, "step": 421230 }, { "epoch": 2.503938037579281, "grad_norm": 3.518612861633301, "learning_rate": 5.854726231287758e-06, "loss": 0.1273, "step": 421240 }, { "epoch": 2.503997479655949, "grad_norm": 3.3988378047943115, "learning_rate": 5.854521792598535e-06, "loss": 0.136, "step": 421250 }, { "epoch": 2.5040569217326176, "grad_norm": 4.002012729644775, "learning_rate": 5.8543173524377215e-06, "loss": 0.1415, "step": 421260 }, { "epoch": 2.504116363809286, "grad_norm": 3.2572500705718994, "learning_rate": 5.854112910805672e-06, "loss": 0.1189, "step": 421270 }, { "epoch": 2.5041758058859545, "grad_norm": 4.340951919555664, "learning_rate": 5.85390846770274e-06, "loss": 0.1496, "step": 421280 }, { "epoch": 2.504235247962623, "grad_norm": 4.596884727478027, "learning_rate": 5.853704023129276e-06, "loss": 0.1423, "step": 421290 }, { "epoch": 2.5042946900392913, "grad_norm": 3.1957390308380127, "learning_rate": 5.8534995770856295e-06, "loss": 0.1333, "step": 421300 }, { "epoch": 2.5043541321159597, "grad_norm": 4.106810092926025, "learning_rate": 5.853295129572156e-06, "loss": 0.1357, "step": 421310 }, { "epoch": 2.504413574192628, "grad_norm": 2.4338533878326416, "learning_rate": 5.853090680589207e-06, "loss": 0.1262, "step": 421320 }, { "epoch": 2.5044730162692965, "grad_norm": 4.344958305358887, "learning_rate": 5.8528862301371335e-06, "loss": 0.1323, "step": 421330 }, { "epoch": 2.504532458345965, "grad_norm": 3.8799502849578857, "learning_rate": 5.852681778216288e-06, "loss": 0.1336, "step": 421340 }, { "epoch": 2.504591900422633, "grad_norm": 3.2903435230255127, "learning_rate": 5.852477324827024e-06, "loss": 0.1238, "step": 421350 }, { "epoch": 2.5046513424993018, "grad_norm": 3.3754782676696777, "learning_rate": 5.8522728699696905e-06, "loss": 0.1365, "step": 421360 }, { "epoch": 2.5047107845759697, "grad_norm": 5.53096342086792, "learning_rate": 5.852068413644643e-06, "loss": 0.1363, "step": 421370 }, { "epoch": 2.5047702266526386, "grad_norm": 4.660731792449951, "learning_rate": 5.851863955852229e-06, "loss": 0.1397, "step": 421380 }, { "epoch": 2.5048296687293066, "grad_norm": 2.8514821529388428, "learning_rate": 5.851659496592808e-06, "loss": 0.1238, "step": 421390 }, { "epoch": 2.504889110805975, "grad_norm": 4.687206745147705, "learning_rate": 5.851455035866724e-06, "loss": 0.1238, "step": 421400 }, { "epoch": 2.5049485528826434, "grad_norm": 4.063599109649658, "learning_rate": 5.851250573674335e-06, "loss": 0.1329, "step": 421410 }, { "epoch": 2.505007994959312, "grad_norm": 4.574462890625, "learning_rate": 5.851046110015991e-06, "loss": 0.141, "step": 421420 }, { "epoch": 2.5050674370359802, "grad_norm": 4.143293857574463, "learning_rate": 5.850841644892042e-06, "loss": 0.1299, "step": 421430 }, { "epoch": 2.5051268791126486, "grad_norm": 3.0834317207336426, "learning_rate": 5.850637178302843e-06, "loss": 0.1203, "step": 421440 }, { "epoch": 2.505186321189317, "grad_norm": 3.4783341884613037, "learning_rate": 5.8504327102487475e-06, "loss": 0.1265, "step": 421450 }, { "epoch": 2.5052457632659855, "grad_norm": 4.559880256652832, "learning_rate": 5.850228240730103e-06, "loss": 0.1303, "step": 421460 }, { "epoch": 2.505305205342654, "grad_norm": 5.264875411987305, "learning_rate": 5.850023769747265e-06, "loss": 0.1248, "step": 421470 }, { "epoch": 2.5053646474193223, "grad_norm": 3.6571452617645264, "learning_rate": 5.849819297300585e-06, "loss": 0.1399, "step": 421480 }, { "epoch": 2.5054240894959907, "grad_norm": 4.102287292480469, "learning_rate": 5.849614823390413e-06, "loss": 0.12, "step": 421490 }, { "epoch": 2.505483531572659, "grad_norm": 4.722625732421875, "learning_rate": 5.849410348017104e-06, "loss": 0.1391, "step": 421500 }, { "epoch": 2.5055429736493275, "grad_norm": 3.073035717010498, "learning_rate": 5.84920587118101e-06, "loss": 0.1389, "step": 421510 }, { "epoch": 2.505602415725996, "grad_norm": 4.8658976554870605, "learning_rate": 5.849001392882481e-06, "loss": 0.1254, "step": 421520 }, { "epoch": 2.5056618578026644, "grad_norm": 3.700751781463623, "learning_rate": 5.84879691312187e-06, "loss": 0.1361, "step": 421530 }, { "epoch": 2.5057212998793323, "grad_norm": 4.112391471862793, "learning_rate": 5.84859243189953e-06, "loss": 0.1638, "step": 421540 }, { "epoch": 2.505780741956001, "grad_norm": 4.525498390197754, "learning_rate": 5.848387949215814e-06, "loss": 0.1444, "step": 421550 }, { "epoch": 2.505840184032669, "grad_norm": 4.08095645904541, "learning_rate": 5.84818346507107e-06, "loss": 0.1441, "step": 421560 }, { "epoch": 2.505899626109338, "grad_norm": 5.936400413513184, "learning_rate": 5.847978979465655e-06, "loss": 0.1409, "step": 421570 }, { "epoch": 2.505959068186006, "grad_norm": 4.024959087371826, "learning_rate": 5.847774492399918e-06, "loss": 0.1339, "step": 421580 }, { "epoch": 2.5060185102626744, "grad_norm": 4.579034328460693, "learning_rate": 5.847570003874212e-06, "loss": 0.1479, "step": 421590 }, { "epoch": 2.506077952339343, "grad_norm": 4.371635437011719, "learning_rate": 5.847365513888889e-06, "loss": 0.1359, "step": 421600 }, { "epoch": 2.5061373944160112, "grad_norm": 4.249048233032227, "learning_rate": 5.847161022444302e-06, "loss": 0.1345, "step": 421610 }, { "epoch": 2.5061968364926797, "grad_norm": 3.4810469150543213, "learning_rate": 5.846956529540803e-06, "loss": 0.1371, "step": 421620 }, { "epoch": 2.506256278569348, "grad_norm": 4.675879001617432, "learning_rate": 5.846752035178743e-06, "loss": 0.1301, "step": 421630 }, { "epoch": 2.5063157206460165, "grad_norm": 4.545862674713135, "learning_rate": 5.846547539358477e-06, "loss": 0.1501, "step": 421640 }, { "epoch": 2.506375162722685, "grad_norm": 4.058514595031738, "learning_rate": 5.846343042080352e-06, "loss": 0.1293, "step": 421650 }, { "epoch": 2.5064346047993533, "grad_norm": 3.6231703758239746, "learning_rate": 5.846138543344726e-06, "loss": 0.1392, "step": 421660 }, { "epoch": 2.5064940468760217, "grad_norm": 3.4777064323425293, "learning_rate": 5.8459340431519485e-06, "loss": 0.1161, "step": 421670 }, { "epoch": 2.50655348895269, "grad_norm": 4.863290786743164, "learning_rate": 5.845729541502369e-06, "loss": 0.1475, "step": 421680 }, { "epoch": 2.5066129310293586, "grad_norm": 3.803300380706787, "learning_rate": 5.845525038396344e-06, "loss": 0.1412, "step": 421690 }, { "epoch": 2.506672373106027, "grad_norm": 5.5052385330200195, "learning_rate": 5.8453205338342246e-06, "loss": 0.128, "step": 421700 }, { "epoch": 2.5067318151826954, "grad_norm": 4.049801349639893, "learning_rate": 5.845116027816361e-06, "loss": 0.1419, "step": 421710 }, { "epoch": 2.506791257259364, "grad_norm": 4.173630237579346, "learning_rate": 5.844911520343108e-06, "loss": 0.134, "step": 421720 }, { "epoch": 2.5068506993360318, "grad_norm": 3.2660746574401855, "learning_rate": 5.844707011414815e-06, "loss": 0.1215, "step": 421730 }, { "epoch": 2.5069101414127006, "grad_norm": 4.2633771896362305, "learning_rate": 5.844502501031838e-06, "loss": 0.1387, "step": 421740 }, { "epoch": 2.5069695834893686, "grad_norm": 4.742764472961426, "learning_rate": 5.844297989194525e-06, "loss": 0.1296, "step": 421750 }, { "epoch": 2.507029025566037, "grad_norm": 4.643767833709717, "learning_rate": 5.844093475903231e-06, "loss": 0.1505, "step": 421760 }, { "epoch": 2.5070884676427054, "grad_norm": 3.6645631790161133, "learning_rate": 5.843888961158307e-06, "loss": 0.1125, "step": 421770 }, { "epoch": 2.507147909719374, "grad_norm": 2.8604466915130615, "learning_rate": 5.843684444960105e-06, "loss": 0.1245, "step": 421780 }, { "epoch": 2.5072073517960423, "grad_norm": 4.1269001960754395, "learning_rate": 5.84347992730898e-06, "loss": 0.1427, "step": 421790 }, { "epoch": 2.5072667938727107, "grad_norm": 3.367159128189087, "learning_rate": 5.84327540820528e-06, "loss": 0.1379, "step": 421800 }, { "epoch": 2.507326235949379, "grad_norm": 4.290978908538818, "learning_rate": 5.843070887649358e-06, "loss": 0.1293, "step": 421810 }, { "epoch": 2.5073856780260475, "grad_norm": 4.260653018951416, "learning_rate": 5.8428663656415684e-06, "loss": 0.1418, "step": 421820 }, { "epoch": 2.507445120102716, "grad_norm": 4.733490467071533, "learning_rate": 5.842661842182263e-06, "loss": 0.1237, "step": 421830 }, { "epoch": 2.5075045621793843, "grad_norm": 3.283883571624756, "learning_rate": 5.842457317271794e-06, "loss": 0.1246, "step": 421840 }, { "epoch": 2.5075640042560527, "grad_norm": 4.316892147064209, "learning_rate": 5.842252790910511e-06, "loss": 0.1334, "step": 421850 }, { "epoch": 2.507623446332721, "grad_norm": 5.641655921936035, "learning_rate": 5.8420482630987695e-06, "loss": 0.1307, "step": 421860 }, { "epoch": 2.5076828884093896, "grad_norm": 4.430103302001953, "learning_rate": 5.841843733836921e-06, "loss": 0.1464, "step": 421870 }, { "epoch": 2.507742330486058, "grad_norm": 4.574542045593262, "learning_rate": 5.841639203125315e-06, "loss": 0.1409, "step": 421880 }, { "epoch": 2.5078017725627264, "grad_norm": 3.543288469314575, "learning_rate": 5.8414346709643075e-06, "loss": 0.1364, "step": 421890 }, { "epoch": 2.5078612146393944, "grad_norm": 6.050087928771973, "learning_rate": 5.84123013735425e-06, "loss": 0.135, "step": 421900 }, { "epoch": 2.5079206567160632, "grad_norm": 3.369645357131958, "learning_rate": 5.841025602295492e-06, "loss": 0.122, "step": 421910 }, { "epoch": 2.507980098792731, "grad_norm": 4.518972873687744, "learning_rate": 5.840821065788388e-06, "loss": 0.1189, "step": 421920 }, { "epoch": 2.5080395408694, "grad_norm": 3.0226542949676514, "learning_rate": 5.840616527833289e-06, "loss": 0.1316, "step": 421930 }, { "epoch": 2.508098982946068, "grad_norm": 2.933405876159668, "learning_rate": 5.84041198843055e-06, "loss": 0.1355, "step": 421940 }, { "epoch": 2.5081584250227364, "grad_norm": 3.6820733547210693, "learning_rate": 5.840207447580519e-06, "loss": 0.1299, "step": 421950 }, { "epoch": 2.508217867099405, "grad_norm": 4.0971999168396, "learning_rate": 5.840002905283553e-06, "loss": 0.1443, "step": 421960 }, { "epoch": 2.5082773091760733, "grad_norm": 4.648573875427246, "learning_rate": 5.839798361540001e-06, "loss": 0.1396, "step": 421970 }, { "epoch": 2.5083367512527417, "grad_norm": 5.039937496185303, "learning_rate": 5.8395938163502155e-06, "loss": 0.1425, "step": 421980 }, { "epoch": 2.50839619332941, "grad_norm": 3.9737818241119385, "learning_rate": 5.83938926971455e-06, "loss": 0.1324, "step": 421990 }, { "epoch": 2.5084556354060785, "grad_norm": 4.608258247375488, "learning_rate": 5.839184721633355e-06, "loss": 0.1317, "step": 422000 }, { "epoch": 2.508515077482747, "grad_norm": 5.144974708557129, "learning_rate": 5.838980172106983e-06, "loss": 0.1482, "step": 422010 }, { "epoch": 2.5085745195594154, "grad_norm": 3.9404540061950684, "learning_rate": 5.838775621135788e-06, "loss": 0.1384, "step": 422020 }, { "epoch": 2.5086339616360838, "grad_norm": 4.158712387084961, "learning_rate": 5.838571068720123e-06, "loss": 0.1288, "step": 422030 }, { "epoch": 2.508693403712752, "grad_norm": 5.165607929229736, "learning_rate": 5.838366514860337e-06, "loss": 0.1371, "step": 422040 }, { "epoch": 2.5087528457894206, "grad_norm": 3.365389823913574, "learning_rate": 5.838161959556783e-06, "loss": 0.1327, "step": 422050 }, { "epoch": 2.508812287866089, "grad_norm": 3.3908193111419678, "learning_rate": 5.837957402809815e-06, "loss": 0.1313, "step": 422060 }, { "epoch": 2.5088717299427574, "grad_norm": 4.1439361572265625, "learning_rate": 5.837752844619784e-06, "loss": 0.1395, "step": 422070 }, { "epoch": 2.508931172019426, "grad_norm": 3.353295087814331, "learning_rate": 5.837548284987042e-06, "loss": 0.1271, "step": 422080 }, { "epoch": 2.508990614096094, "grad_norm": 4.628549575805664, "learning_rate": 5.837343723911943e-06, "loss": 0.1361, "step": 422090 }, { "epoch": 2.5090500561727627, "grad_norm": 4.8992600440979, "learning_rate": 5.837139161394839e-06, "loss": 0.1309, "step": 422100 }, { "epoch": 2.5091094982494306, "grad_norm": 4.167686462402344, "learning_rate": 5.8369345974360805e-06, "loss": 0.1287, "step": 422110 }, { "epoch": 2.5091689403260995, "grad_norm": 3.879079580307007, "learning_rate": 5.836730032036021e-06, "loss": 0.1209, "step": 422120 }, { "epoch": 2.5092283824027675, "grad_norm": 3.7713863849639893, "learning_rate": 5.8365254651950135e-06, "loss": 0.1447, "step": 422130 }, { "epoch": 2.509287824479436, "grad_norm": 4.1499152183532715, "learning_rate": 5.836320896913408e-06, "loss": 0.1379, "step": 422140 }, { "epoch": 2.5093472665561043, "grad_norm": 4.156944274902344, "learning_rate": 5.836116327191557e-06, "loss": 0.1367, "step": 422150 }, { "epoch": 2.5094067086327727, "grad_norm": 4.228731632232666, "learning_rate": 5.835911756029815e-06, "loss": 0.1391, "step": 422160 }, { "epoch": 2.509466150709441, "grad_norm": 4.076024532318115, "learning_rate": 5.835707183428534e-06, "loss": 0.1431, "step": 422170 }, { "epoch": 2.5095255927861095, "grad_norm": 4.722392559051514, "learning_rate": 5.8355026093880655e-06, "loss": 0.1315, "step": 422180 }, { "epoch": 2.509585034862778, "grad_norm": 4.114133834838867, "learning_rate": 5.83529803390876e-06, "loss": 0.1379, "step": 422190 }, { "epoch": 2.5096444769394464, "grad_norm": 3.9990012645721436, "learning_rate": 5.8350934569909746e-06, "loss": 0.1301, "step": 422200 }, { "epoch": 2.509703919016115, "grad_norm": 3.539250612258911, "learning_rate": 5.8348888786350565e-06, "loss": 0.1269, "step": 422210 }, { "epoch": 2.509763361092783, "grad_norm": 4.022566795349121, "learning_rate": 5.834684298841361e-06, "loss": 0.1352, "step": 422220 }, { "epoch": 2.5098228031694516, "grad_norm": 4.291481018066406, "learning_rate": 5.83447971761024e-06, "loss": 0.1501, "step": 422230 }, { "epoch": 2.50988224524612, "grad_norm": 4.164892673492432, "learning_rate": 5.834275134942044e-06, "loss": 0.1462, "step": 422240 }, { "epoch": 2.5099416873227884, "grad_norm": 4.251481056213379, "learning_rate": 5.834070550837127e-06, "loss": 0.138, "step": 422250 }, { "epoch": 2.510001129399457, "grad_norm": 4.374251365661621, "learning_rate": 5.833865965295839e-06, "loss": 0.1351, "step": 422260 }, { "epoch": 2.5100605714761253, "grad_norm": 4.487296104431152, "learning_rate": 5.833661378318537e-06, "loss": 0.1259, "step": 422270 }, { "epoch": 2.5101200135527932, "grad_norm": 3.694823741912842, "learning_rate": 5.8334567899055705e-06, "loss": 0.1325, "step": 422280 }, { "epoch": 2.510179455629462, "grad_norm": 3.6737632751464844, "learning_rate": 5.833252200057292e-06, "loss": 0.1292, "step": 422290 }, { "epoch": 2.51023889770613, "grad_norm": 3.3643429279327393, "learning_rate": 5.833047608774053e-06, "loss": 0.1254, "step": 422300 }, { "epoch": 2.510298339782799, "grad_norm": 3.335357666015625, "learning_rate": 5.832843016056206e-06, "loss": 0.1242, "step": 422310 }, { "epoch": 2.510357781859467, "grad_norm": 3.6995036602020264, "learning_rate": 5.832638421904106e-06, "loss": 0.1507, "step": 422320 }, { "epoch": 2.5104172239361353, "grad_norm": 4.760658264160156, "learning_rate": 5.832433826318102e-06, "loss": 0.1419, "step": 422330 }, { "epoch": 2.5104766660128037, "grad_norm": 3.5481364727020264, "learning_rate": 5.8322292292985485e-06, "loss": 0.1284, "step": 422340 }, { "epoch": 2.510536108089472, "grad_norm": 3.5659070014953613, "learning_rate": 5.832024630845796e-06, "loss": 0.1359, "step": 422350 }, { "epoch": 2.5105955501661406, "grad_norm": 3.772921085357666, "learning_rate": 5.831820030960198e-06, "loss": 0.1273, "step": 422360 }, { "epoch": 2.510654992242809, "grad_norm": 3.5033037662506104, "learning_rate": 5.831615429642105e-06, "loss": 0.1471, "step": 422370 }, { "epoch": 2.5107144343194774, "grad_norm": 4.793010711669922, "learning_rate": 5.831410826891875e-06, "loss": 0.1218, "step": 422380 }, { "epoch": 2.510773876396146, "grad_norm": 3.3155219554901123, "learning_rate": 5.831206222709854e-06, "loss": 0.1261, "step": 422390 }, { "epoch": 2.510833318472814, "grad_norm": 4.405441761016846, "learning_rate": 5.831001617096396e-06, "loss": 0.1286, "step": 422400 }, { "epoch": 2.5108927605494826, "grad_norm": 5.186681270599365, "learning_rate": 5.8307970100518555e-06, "loss": 0.1335, "step": 422410 }, { "epoch": 2.510952202626151, "grad_norm": 4.780592918395996, "learning_rate": 5.830592401576583e-06, "loss": 0.136, "step": 422420 }, { "epoch": 2.5110116447028195, "grad_norm": 4.0400309562683105, "learning_rate": 5.830387791670931e-06, "loss": 0.1326, "step": 422430 }, { "epoch": 2.511071086779488, "grad_norm": 3.7232632637023926, "learning_rate": 5.830183180335252e-06, "loss": 0.1381, "step": 422440 }, { "epoch": 2.511130528856156, "grad_norm": 4.835684776306152, "learning_rate": 5.8299785675699e-06, "loss": 0.139, "step": 422450 }, { "epoch": 2.5111899709328247, "grad_norm": 4.04802131652832, "learning_rate": 5.829773953375224e-06, "loss": 0.1475, "step": 422460 }, { "epoch": 2.5112494130094927, "grad_norm": 3.7410216331481934, "learning_rate": 5.829569337751579e-06, "loss": 0.1653, "step": 422470 }, { "epoch": 2.5113088550861615, "grad_norm": 3.827162742614746, "learning_rate": 5.829364720699315e-06, "loss": 0.1211, "step": 422480 }, { "epoch": 2.5113682971628295, "grad_norm": 3.860762119293213, "learning_rate": 5.829160102218788e-06, "loss": 0.1313, "step": 422490 }, { "epoch": 2.511427739239498, "grad_norm": 4.147613525390625, "learning_rate": 5.8289554823103475e-06, "loss": 0.1261, "step": 422500 }, { "epoch": 2.5114871813161663, "grad_norm": 4.659273147583008, "learning_rate": 5.828750860974348e-06, "loss": 0.1405, "step": 422510 }, { "epoch": 2.5115466233928347, "grad_norm": 3.8877415657043457, "learning_rate": 5.82854623821114e-06, "loss": 0.1456, "step": 422520 }, { "epoch": 2.511606065469503, "grad_norm": 4.159175395965576, "learning_rate": 5.828341614021076e-06, "loss": 0.1282, "step": 422530 }, { "epoch": 2.5116655075461716, "grad_norm": 2.8996944427490234, "learning_rate": 5.828136988404509e-06, "loss": 0.1283, "step": 422540 }, { "epoch": 2.51172494962284, "grad_norm": 5.459781169891357, "learning_rate": 5.827932361361792e-06, "loss": 0.1309, "step": 422550 }, { "epoch": 2.5117843916995084, "grad_norm": 3.6733837127685547, "learning_rate": 5.827727732893275e-06, "loss": 0.1368, "step": 422560 }, { "epoch": 2.511843833776177, "grad_norm": 5.677846431732178, "learning_rate": 5.827523102999314e-06, "loss": 0.1288, "step": 422570 }, { "epoch": 2.5119032758528452, "grad_norm": 4.441728115081787, "learning_rate": 5.827318471680259e-06, "loss": 0.1342, "step": 422580 }, { "epoch": 2.5119627179295136, "grad_norm": 4.495382785797119, "learning_rate": 5.827113838936462e-06, "loss": 0.143, "step": 422590 }, { "epoch": 2.512022160006182, "grad_norm": 4.213431358337402, "learning_rate": 5.826909204768277e-06, "loss": 0.1289, "step": 422600 }, { "epoch": 2.5120816020828505, "grad_norm": 3.302903175354004, "learning_rate": 5.826704569176056e-06, "loss": 0.1229, "step": 422610 }, { "epoch": 2.512141044159519, "grad_norm": 4.454755783081055, "learning_rate": 5.8264999321601504e-06, "loss": 0.123, "step": 422620 }, { "epoch": 2.5122004862361873, "grad_norm": 5.487758159637451, "learning_rate": 5.8262952937209125e-06, "loss": 0.1338, "step": 422630 }, { "epoch": 2.5122599283128553, "grad_norm": 3.301500082015991, "learning_rate": 5.826090653858697e-06, "loss": 0.1412, "step": 422640 }, { "epoch": 2.512319370389524, "grad_norm": 4.659424781799316, "learning_rate": 5.825886012573855e-06, "loss": 0.1256, "step": 422650 }, { "epoch": 2.512378812466192, "grad_norm": 3.690809726715088, "learning_rate": 5.825681369866738e-06, "loss": 0.1426, "step": 422660 }, { "epoch": 2.512438254542861, "grad_norm": 4.523086071014404, "learning_rate": 5.8254767257377e-06, "loss": 0.1379, "step": 422670 }, { "epoch": 2.512497696619529, "grad_norm": 5.094354152679443, "learning_rate": 5.825272080187092e-06, "loss": 0.1507, "step": 422680 }, { "epoch": 2.5125571386961973, "grad_norm": 4.17811918258667, "learning_rate": 5.825067433215266e-06, "loss": 0.1345, "step": 422690 }, { "epoch": 2.5126165807728658, "grad_norm": 3.206540584564209, "learning_rate": 5.824862784822576e-06, "loss": 0.1255, "step": 422700 }, { "epoch": 2.512676022849534, "grad_norm": 4.2507805824279785, "learning_rate": 5.824658135009375e-06, "loss": 0.1289, "step": 422710 }, { "epoch": 2.5127354649262026, "grad_norm": 4.134845733642578, "learning_rate": 5.824453483776013e-06, "loss": 0.123, "step": 422720 }, { "epoch": 2.512794907002871, "grad_norm": 3.787724733352661, "learning_rate": 5.824248831122844e-06, "loss": 0.1475, "step": 422730 }, { "epoch": 2.5128543490795394, "grad_norm": 5.1302008628845215, "learning_rate": 5.824044177050221e-06, "loss": 0.1398, "step": 422740 }, { "epoch": 2.512913791156208, "grad_norm": 3.5979976654052734, "learning_rate": 5.823839521558494e-06, "loss": 0.1229, "step": 422750 }, { "epoch": 2.5129732332328762, "grad_norm": 3.4486889839172363, "learning_rate": 5.823634864648018e-06, "loss": 0.1249, "step": 422760 }, { "epoch": 2.5130326753095447, "grad_norm": 2.781080484390259, "learning_rate": 5.823430206319145e-06, "loss": 0.1116, "step": 422770 }, { "epoch": 2.513092117386213, "grad_norm": 3.342160940170288, "learning_rate": 5.823225546572226e-06, "loss": 0.1219, "step": 422780 }, { "epoch": 2.5131515594628815, "grad_norm": 4.290223598480225, "learning_rate": 5.823020885407615e-06, "loss": 0.1428, "step": 422790 }, { "epoch": 2.51321100153955, "grad_norm": 3.6345930099487305, "learning_rate": 5.822816222825665e-06, "loss": 0.1398, "step": 422800 }, { "epoch": 2.5132704436162183, "grad_norm": 5.843358993530273, "learning_rate": 5.822611558826724e-06, "loss": 0.1345, "step": 422810 }, { "epoch": 2.5133298856928867, "grad_norm": 3.879737377166748, "learning_rate": 5.82240689341115e-06, "loss": 0.1408, "step": 422820 }, { "epoch": 2.5133893277695547, "grad_norm": 4.246943950653076, "learning_rate": 5.822202226579292e-06, "loss": 0.146, "step": 422830 }, { "epoch": 2.5134487698462236, "grad_norm": 3.518991231918335, "learning_rate": 5.821997558331506e-06, "loss": 0.1268, "step": 422840 }, { "epoch": 2.5135082119228915, "grad_norm": 4.028946876525879, "learning_rate": 5.821792888668141e-06, "loss": 0.1428, "step": 422850 }, { "epoch": 2.5135676539995604, "grad_norm": 4.840189456939697, "learning_rate": 5.821588217589549e-06, "loss": 0.1349, "step": 422860 }, { "epoch": 2.5136270960762284, "grad_norm": 4.3650383949279785, "learning_rate": 5.821383545096086e-06, "loss": 0.1215, "step": 422870 }, { "epoch": 2.5136865381528968, "grad_norm": 4.602052211761475, "learning_rate": 5.821178871188103e-06, "loss": 0.1316, "step": 422880 }, { "epoch": 2.513745980229565, "grad_norm": 4.292984962463379, "learning_rate": 5.820974195865949e-06, "loss": 0.1462, "step": 422890 }, { "epoch": 2.5138054223062336, "grad_norm": 5.120357036590576, "learning_rate": 5.820769519129983e-06, "loss": 0.1548, "step": 422900 }, { "epoch": 2.513864864382902, "grad_norm": 3.860750913619995, "learning_rate": 5.820564840980552e-06, "loss": 0.1262, "step": 422910 }, { "epoch": 2.5139243064595704, "grad_norm": 3.8539228439331055, "learning_rate": 5.820360161418009e-06, "loss": 0.1238, "step": 422920 }, { "epoch": 2.513983748536239, "grad_norm": 4.740251541137695, "learning_rate": 5.820155480442711e-06, "loss": 0.1531, "step": 422930 }, { "epoch": 2.5140431906129073, "grad_norm": 4.303319931030273, "learning_rate": 5.819950798055005e-06, "loss": 0.1342, "step": 422940 }, { "epoch": 2.5141026326895757, "grad_norm": 4.679681777954102, "learning_rate": 5.819746114255247e-06, "loss": 0.1321, "step": 422950 }, { "epoch": 2.514162074766244, "grad_norm": 3.749622106552124, "learning_rate": 5.819541429043789e-06, "loss": 0.1495, "step": 422960 }, { "epoch": 2.5142215168429125, "grad_norm": 4.076875686645508, "learning_rate": 5.819336742420982e-06, "loss": 0.1345, "step": 422970 }, { "epoch": 2.514280958919581, "grad_norm": 4.704698085784912, "learning_rate": 5.819132054387179e-06, "loss": 0.1368, "step": 422980 }, { "epoch": 2.5143404009962493, "grad_norm": 6.063048839569092, "learning_rate": 5.818927364942733e-06, "loss": 0.1395, "step": 422990 }, { "epoch": 2.5143998430729178, "grad_norm": 4.064740180969238, "learning_rate": 5.818722674087998e-06, "loss": 0.1266, "step": 423000 }, { "epoch": 2.514459285149586, "grad_norm": 5.447604656219482, "learning_rate": 5.818517981823323e-06, "loss": 0.1329, "step": 423010 }, { "epoch": 2.514518727226254, "grad_norm": 6.011131286621094, "learning_rate": 5.818313288149063e-06, "loss": 0.1497, "step": 423020 }, { "epoch": 2.514578169302923, "grad_norm": 3.4548065662384033, "learning_rate": 5.81810859306557e-06, "loss": 0.1362, "step": 423030 }, { "epoch": 2.514637611379591, "grad_norm": 5.36921501159668, "learning_rate": 5.817903896573196e-06, "loss": 0.1257, "step": 423040 }, { "epoch": 2.51469705345626, "grad_norm": 5.075899600982666, "learning_rate": 5.817699198672294e-06, "loss": 0.1372, "step": 423050 }, { "epoch": 2.514756495532928, "grad_norm": 4.133786678314209, "learning_rate": 5.8174944993632165e-06, "loss": 0.1595, "step": 423060 }, { "epoch": 2.514815937609596, "grad_norm": 4.358149528503418, "learning_rate": 5.817289798646317e-06, "loss": 0.1213, "step": 423070 }, { "epoch": 2.5148753796862646, "grad_norm": 4.204240798950195, "learning_rate": 5.817085096521945e-06, "loss": 0.1313, "step": 423080 }, { "epoch": 2.514934821762933, "grad_norm": 3.6676406860351562, "learning_rate": 5.816880392990457e-06, "loss": 0.1149, "step": 423090 }, { "epoch": 2.5149942638396015, "grad_norm": 5.2373762130737305, "learning_rate": 5.816675688052202e-06, "loss": 0.1195, "step": 423100 }, { "epoch": 2.51505370591627, "grad_norm": 3.6182608604431152, "learning_rate": 5.816470981707535e-06, "loss": 0.1229, "step": 423110 }, { "epoch": 2.5151131479929383, "grad_norm": 4.602320671081543, "learning_rate": 5.816266273956806e-06, "loss": 0.1391, "step": 423120 }, { "epoch": 2.5151725900696067, "grad_norm": 3.7177562713623047, "learning_rate": 5.816061564800372e-06, "loss": 0.1331, "step": 423130 }, { "epoch": 2.515232032146275, "grad_norm": 3.719362497329712, "learning_rate": 5.81585685423858e-06, "loss": 0.12, "step": 423140 }, { "epoch": 2.5152914742229435, "grad_norm": 5.890016078948975, "learning_rate": 5.815652142271785e-06, "loss": 0.1525, "step": 423150 }, { "epoch": 2.515350916299612, "grad_norm": 4.488476276397705, "learning_rate": 5.81544742890034e-06, "loss": 0.148, "step": 423160 }, { "epoch": 2.5154103583762804, "grad_norm": 5.631066799163818, "learning_rate": 5.815242714124599e-06, "loss": 0.135, "step": 423170 }, { "epoch": 2.5154698004529488, "grad_norm": 4.015205383300781, "learning_rate": 5.815037997944911e-06, "loss": 0.1265, "step": 423180 }, { "epoch": 2.5155292425296167, "grad_norm": 4.448636054992676, "learning_rate": 5.814833280361632e-06, "loss": 0.1409, "step": 423190 }, { "epoch": 2.5155886846062856, "grad_norm": 4.344768047332764, "learning_rate": 5.814628561375111e-06, "loss": 0.1349, "step": 423200 }, { "epoch": 2.5156481266829536, "grad_norm": 4.684383869171143, "learning_rate": 5.814423840985702e-06, "loss": 0.121, "step": 423210 }, { "epoch": 2.5157075687596224, "grad_norm": 3.626328229904175, "learning_rate": 5.81421911919376e-06, "loss": 0.1301, "step": 423220 }, { "epoch": 2.5157670108362904, "grad_norm": 4.313182830810547, "learning_rate": 5.814014395999636e-06, "loss": 0.1551, "step": 423230 }, { "epoch": 2.515826452912959, "grad_norm": 4.137144088745117, "learning_rate": 5.81380967140368e-06, "loss": 0.1352, "step": 423240 }, { "epoch": 2.5158858949896272, "grad_norm": 5.494909286499023, "learning_rate": 5.813604945406246e-06, "loss": 0.1452, "step": 423250 }, { "epoch": 2.5159453370662956, "grad_norm": 4.306711673736572, "learning_rate": 5.813400218007688e-06, "loss": 0.1551, "step": 423260 }, { "epoch": 2.516004779142964, "grad_norm": 5.179164409637451, "learning_rate": 5.81319548920836e-06, "loss": 0.1445, "step": 423270 }, { "epoch": 2.5160642212196325, "grad_norm": 6.223274230957031, "learning_rate": 5.81299075900861e-06, "loss": 0.1335, "step": 423280 }, { "epoch": 2.516123663296301, "grad_norm": 4.238775730133057, "learning_rate": 5.812786027408794e-06, "loss": 0.1445, "step": 423290 }, { "epoch": 2.5161831053729693, "grad_norm": 3.324901580810547, "learning_rate": 5.812581294409263e-06, "loss": 0.1246, "step": 423300 }, { "epoch": 2.5162425474496377, "grad_norm": 3.101799964904785, "learning_rate": 5.8123765600103695e-06, "loss": 0.1285, "step": 423310 }, { "epoch": 2.516301989526306, "grad_norm": 4.257949352264404, "learning_rate": 5.812171824212468e-06, "loss": 0.1383, "step": 423320 }, { "epoch": 2.5163614316029745, "grad_norm": 4.483798027038574, "learning_rate": 5.811967087015909e-06, "loss": 0.1326, "step": 423330 }, { "epoch": 2.516420873679643, "grad_norm": 4.192737102508545, "learning_rate": 5.811762348421046e-06, "loss": 0.1413, "step": 423340 }, { "epoch": 2.5164803157563114, "grad_norm": 4.20967435836792, "learning_rate": 5.811557608428231e-06, "loss": 0.143, "step": 423350 }, { "epoch": 2.51653975783298, "grad_norm": 4.220573902130127, "learning_rate": 5.811352867037817e-06, "loss": 0.1316, "step": 423360 }, { "epoch": 2.516599199909648, "grad_norm": 4.349696636199951, "learning_rate": 5.811148124250157e-06, "loss": 0.1211, "step": 423370 }, { "epoch": 2.516658641986316, "grad_norm": 4.330495834350586, "learning_rate": 5.810943380065603e-06, "loss": 0.1548, "step": 423380 }, { "epoch": 2.516718084062985, "grad_norm": 4.443938732147217, "learning_rate": 5.810738634484507e-06, "loss": 0.1314, "step": 423390 }, { "epoch": 2.516777526139653, "grad_norm": 4.633282661437988, "learning_rate": 5.810533887507224e-06, "loss": 0.1311, "step": 423400 }, { "epoch": 2.516836968216322, "grad_norm": 4.428576469421387, "learning_rate": 5.810329139134102e-06, "loss": 0.1414, "step": 423410 }, { "epoch": 2.51689641029299, "grad_norm": 3.8165535926818848, "learning_rate": 5.810124389365499e-06, "loss": 0.1131, "step": 423420 }, { "epoch": 2.5169558523696582, "grad_norm": 3.6714563369750977, "learning_rate": 5.809919638201765e-06, "loss": 0.1411, "step": 423430 }, { "epoch": 2.5170152944463267, "grad_norm": 4.692996025085449, "learning_rate": 5.809714885643251e-06, "loss": 0.1432, "step": 423440 }, { "epoch": 2.517074736522995, "grad_norm": 4.125595569610596, "learning_rate": 5.809510131690314e-06, "loss": 0.1453, "step": 423450 }, { "epoch": 2.5171341785996635, "grad_norm": 3.648756980895996, "learning_rate": 5.809305376343303e-06, "loss": 0.1201, "step": 423460 }, { "epoch": 2.517193620676332, "grad_norm": 3.882648229598999, "learning_rate": 5.809100619602569e-06, "loss": 0.1559, "step": 423470 }, { "epoch": 2.5172530627530003, "grad_norm": 4.742065906524658, "learning_rate": 5.80889586146847e-06, "loss": 0.141, "step": 423480 }, { "epoch": 2.5173125048296687, "grad_norm": 3.490640878677368, "learning_rate": 5.808691101941356e-06, "loss": 0.1234, "step": 423490 }, { "epoch": 2.517371946906337, "grad_norm": 3.1483042240142822, "learning_rate": 5.808486341021577e-06, "loss": 0.1358, "step": 423500 }, { "epoch": 2.5174313889830056, "grad_norm": 4.283081531524658, "learning_rate": 5.808281578709491e-06, "loss": 0.1366, "step": 423510 }, { "epoch": 2.517490831059674, "grad_norm": 4.459657669067383, "learning_rate": 5.808076815005447e-06, "loss": 0.1516, "step": 423520 }, { "epoch": 2.5175502731363424, "grad_norm": 3.9248526096343994, "learning_rate": 5.807872049909798e-06, "loss": 0.1292, "step": 423530 }, { "epoch": 2.517609715213011, "grad_norm": 3.4913997650146484, "learning_rate": 5.807667283422895e-06, "loss": 0.123, "step": 423540 }, { "epoch": 2.517669157289679, "grad_norm": 3.412381649017334, "learning_rate": 5.807462515545095e-06, "loss": 0.1291, "step": 423550 }, { "epoch": 2.5177285993663476, "grad_norm": 5.478855133056641, "learning_rate": 5.807257746276748e-06, "loss": 0.1319, "step": 423560 }, { "epoch": 2.5177880414430156, "grad_norm": 3.95851993560791, "learning_rate": 5.8070529756182045e-06, "loss": 0.1283, "step": 423570 }, { "epoch": 2.5178474835196845, "grad_norm": 6.332110404968262, "learning_rate": 5.806848203569822e-06, "loss": 0.1289, "step": 423580 }, { "epoch": 2.5179069255963524, "grad_norm": 3.87113881111145, "learning_rate": 5.80664343013195e-06, "loss": 0.1323, "step": 423590 }, { "epoch": 2.5179663676730213, "grad_norm": 3.8338186740875244, "learning_rate": 5.8064386553049405e-06, "loss": 0.147, "step": 423600 }, { "epoch": 2.5180258097496893, "grad_norm": 4.616866588592529, "learning_rate": 5.806233879089148e-06, "loss": 0.142, "step": 423610 }, { "epoch": 2.5180852518263577, "grad_norm": 3.4895148277282715, "learning_rate": 5.806029101484926e-06, "loss": 0.1209, "step": 423620 }, { "epoch": 2.518144693903026, "grad_norm": 5.217791557312012, "learning_rate": 5.805824322492624e-06, "loss": 0.1394, "step": 423630 }, { "epoch": 2.5182041359796945, "grad_norm": 3.377694606781006, "learning_rate": 5.805619542112597e-06, "loss": 0.1295, "step": 423640 }, { "epoch": 2.518263578056363, "grad_norm": 6.0166335105896, "learning_rate": 5.805414760345199e-06, "loss": 0.1417, "step": 423650 }, { "epoch": 2.5183230201330313, "grad_norm": 4.781869411468506, "learning_rate": 5.805209977190778e-06, "loss": 0.1426, "step": 423660 }, { "epoch": 2.5183824622096997, "grad_norm": 3.860417366027832, "learning_rate": 5.80500519264969e-06, "loss": 0.1228, "step": 423670 }, { "epoch": 2.518441904286368, "grad_norm": 5.085161209106445, "learning_rate": 5.804800406722288e-06, "loss": 0.1368, "step": 423680 }, { "epoch": 2.5185013463630366, "grad_norm": 3.7066566944122314, "learning_rate": 5.804595619408922e-06, "loss": 0.1207, "step": 423690 }, { "epoch": 2.518560788439705, "grad_norm": 6.78317928314209, "learning_rate": 5.8043908307099464e-06, "loss": 0.1571, "step": 423700 }, { "epoch": 2.5186202305163734, "grad_norm": 3.543555498123169, "learning_rate": 5.804186040625715e-06, "loss": 0.1363, "step": 423710 }, { "epoch": 2.518679672593042, "grad_norm": 3.665588140487671, "learning_rate": 5.803981249156578e-06, "loss": 0.1505, "step": 423720 }, { "epoch": 2.5187391146697102, "grad_norm": 4.253260135650635, "learning_rate": 5.803776456302891e-06, "loss": 0.1212, "step": 423730 }, { "epoch": 2.5187985567463786, "grad_norm": 3.573899745941162, "learning_rate": 5.803571662065004e-06, "loss": 0.12, "step": 423740 }, { "epoch": 2.518857998823047, "grad_norm": 4.728567123413086, "learning_rate": 5.803366866443272e-06, "loss": 0.1516, "step": 423750 }, { "epoch": 2.518917440899715, "grad_norm": 5.59998083114624, "learning_rate": 5.803162069438044e-06, "loss": 0.1311, "step": 423760 }, { "epoch": 2.518976882976384, "grad_norm": 3.3494462966918945, "learning_rate": 5.8029572710496775e-06, "loss": 0.1193, "step": 423770 }, { "epoch": 2.519036325053052, "grad_norm": 5.024390697479248, "learning_rate": 5.802752471278522e-06, "loss": 0.1332, "step": 423780 }, { "epoch": 2.5190957671297207, "grad_norm": 4.332255840301514, "learning_rate": 5.802547670124929e-06, "loss": 0.1298, "step": 423790 }, { "epoch": 2.5191552092063887, "grad_norm": 4.131478786468506, "learning_rate": 5.802342867589255e-06, "loss": 0.1275, "step": 423800 }, { "epoch": 2.519214651283057, "grad_norm": 4.745703220367432, "learning_rate": 5.802138063671852e-06, "loss": 0.1308, "step": 423810 }, { "epoch": 2.5192740933597255, "grad_norm": 2.652317762374878, "learning_rate": 5.80193325837307e-06, "loss": 0.1209, "step": 423820 }, { "epoch": 2.519333535436394, "grad_norm": 3.252349615097046, "learning_rate": 5.8017284516932624e-06, "loss": 0.1363, "step": 423830 }, { "epoch": 2.5193929775130623, "grad_norm": 3.881150960922241, "learning_rate": 5.801523643632785e-06, "loss": 0.1306, "step": 423840 }, { "epoch": 2.5194524195897308, "grad_norm": 5.159377574920654, "learning_rate": 5.801318834191987e-06, "loss": 0.1162, "step": 423850 }, { "epoch": 2.519511861666399, "grad_norm": 5.692754745483398, "learning_rate": 5.8011140233712215e-06, "loss": 0.1481, "step": 423860 }, { "epoch": 2.5195713037430676, "grad_norm": 3.7185261249542236, "learning_rate": 5.800909211170844e-06, "loss": 0.1257, "step": 423870 }, { "epoch": 2.519630745819736, "grad_norm": 4.220062732696533, "learning_rate": 5.800704397591204e-06, "loss": 0.1383, "step": 423880 }, { "epoch": 2.5196901878964044, "grad_norm": 4.396503925323486, "learning_rate": 5.800499582632655e-06, "loss": 0.1548, "step": 423890 }, { "epoch": 2.519749629973073, "grad_norm": 5.615426063537598, "learning_rate": 5.800294766295552e-06, "loss": 0.1558, "step": 423900 }, { "epoch": 2.5198090720497412, "grad_norm": 4.378313064575195, "learning_rate": 5.800089948580244e-06, "loss": 0.1328, "step": 423910 }, { "epoch": 2.5198685141264097, "grad_norm": 3.4081342220306396, "learning_rate": 5.799885129487087e-06, "loss": 0.157, "step": 423920 }, { "epoch": 2.5199279562030776, "grad_norm": 3.2251484394073486, "learning_rate": 5.799680309016431e-06, "loss": 0.1241, "step": 423930 }, { "epoch": 2.5199873982797465, "grad_norm": 3.272982358932495, "learning_rate": 5.799475487168632e-06, "loss": 0.1191, "step": 423940 }, { "epoch": 2.5200468403564145, "grad_norm": 6.083034515380859, "learning_rate": 5.79927066394404e-06, "loss": 0.1325, "step": 423950 }, { "epoch": 2.5201062824330833, "grad_norm": 3.519139051437378, "learning_rate": 5.799065839343008e-06, "loss": 0.1334, "step": 423960 }, { "epoch": 2.5201657245097513, "grad_norm": 3.4216926097869873, "learning_rate": 5.79886101336589e-06, "loss": 0.1295, "step": 423970 }, { "epoch": 2.5202251665864197, "grad_norm": 4.1142377853393555, "learning_rate": 5.798656186013038e-06, "loss": 0.1538, "step": 423980 }, { "epoch": 2.520284608663088, "grad_norm": 4.840433120727539, "learning_rate": 5.798451357284803e-06, "loss": 0.1371, "step": 423990 }, { "epoch": 2.5203440507397565, "grad_norm": 4.078242778778076, "learning_rate": 5.798246527181542e-06, "loss": 0.1198, "step": 424000 }, { "epoch": 2.520403492816425, "grad_norm": 3.1198439598083496, "learning_rate": 5.798041695703604e-06, "loss": 0.1277, "step": 424010 }, { "epoch": 2.5204629348930934, "grad_norm": 3.224944829940796, "learning_rate": 5.7978368628513425e-06, "loss": 0.1318, "step": 424020 }, { "epoch": 2.520522376969762, "grad_norm": 5.179904460906982, "learning_rate": 5.797632028625111e-06, "loss": 0.1422, "step": 424030 }, { "epoch": 2.52058181904643, "grad_norm": 5.13437032699585, "learning_rate": 5.797427193025262e-06, "loss": 0.1388, "step": 424040 }, { "epoch": 2.5206412611230986, "grad_norm": 4.0807108879089355, "learning_rate": 5.7972223560521505e-06, "loss": 0.1282, "step": 424050 }, { "epoch": 2.520700703199767, "grad_norm": 4.481277942657471, "learning_rate": 5.7970175177061236e-06, "loss": 0.1466, "step": 424060 }, { "epoch": 2.5207601452764354, "grad_norm": 4.296369552612305, "learning_rate": 5.796812677987539e-06, "loss": 0.1386, "step": 424070 }, { "epoch": 2.520819587353104, "grad_norm": 5.34745979309082, "learning_rate": 5.7966078368967484e-06, "loss": 0.1319, "step": 424080 }, { "epoch": 2.5208790294297723, "grad_norm": 4.017663955688477, "learning_rate": 5.7964029944341024e-06, "loss": 0.1356, "step": 424090 }, { "epoch": 2.5209384715064407, "grad_norm": 3.7885022163391113, "learning_rate": 5.796198150599958e-06, "loss": 0.1434, "step": 424100 }, { "epoch": 2.520997913583109, "grad_norm": 3.7554385662078857, "learning_rate": 5.795993305394664e-06, "loss": 0.1341, "step": 424110 }, { "epoch": 2.521057355659777, "grad_norm": 3.237952470779419, "learning_rate": 5.795788458818573e-06, "loss": 0.1354, "step": 424120 }, { "epoch": 2.521116797736446, "grad_norm": 4.280918598175049, "learning_rate": 5.7955836108720396e-06, "loss": 0.1309, "step": 424130 }, { "epoch": 2.521176239813114, "grad_norm": 3.6893653869628906, "learning_rate": 5.795378761555418e-06, "loss": 0.1366, "step": 424140 }, { "epoch": 2.5212356818897828, "grad_norm": 4.280604362487793, "learning_rate": 5.795173910869059e-06, "loss": 0.1297, "step": 424150 }, { "epoch": 2.5212951239664507, "grad_norm": 3.1698641777038574, "learning_rate": 5.794969058813316e-06, "loss": 0.1379, "step": 424160 }, { "epoch": 2.521354566043119, "grad_norm": 3.6981191635131836, "learning_rate": 5.79476420538854e-06, "loss": 0.128, "step": 424170 }, { "epoch": 2.5214140081197876, "grad_norm": 4.1980085372924805, "learning_rate": 5.794559350595087e-06, "loss": 0.125, "step": 424180 }, { "epoch": 2.521473450196456, "grad_norm": 4.237000942230225, "learning_rate": 5.794354494433307e-06, "loss": 0.1494, "step": 424190 }, { "epoch": 2.5215328922731244, "grad_norm": 3.766951560974121, "learning_rate": 5.794149636903553e-06, "loss": 0.1305, "step": 424200 }, { "epoch": 2.521592334349793, "grad_norm": 4.721564769744873, "learning_rate": 5.79394477800618e-06, "loss": 0.1408, "step": 424210 }, { "epoch": 2.521651776426461, "grad_norm": 3.4793508052825928, "learning_rate": 5.7937399177415375e-06, "loss": 0.1285, "step": 424220 }, { "epoch": 2.5217112185031296, "grad_norm": 4.242506980895996, "learning_rate": 5.793535056109982e-06, "loss": 0.1284, "step": 424230 }, { "epoch": 2.521770660579798, "grad_norm": 3.397564172744751, "learning_rate": 5.793330193111863e-06, "loss": 0.129, "step": 424240 }, { "epoch": 2.5218301026564665, "grad_norm": 3.323606014251709, "learning_rate": 5.793125328747535e-06, "loss": 0.1316, "step": 424250 }, { "epoch": 2.521889544733135, "grad_norm": 3.0343825817108154, "learning_rate": 5.792920463017351e-06, "loss": 0.1392, "step": 424260 }, { "epoch": 2.5219489868098033, "grad_norm": 4.026595592498779, "learning_rate": 5.792715595921664e-06, "loss": 0.133, "step": 424270 }, { "epoch": 2.5220084288864717, "grad_norm": 3.936664342880249, "learning_rate": 5.792510727460825e-06, "loss": 0.1243, "step": 424280 }, { "epoch": 2.52206787096314, "grad_norm": 4.5027923583984375, "learning_rate": 5.792305857635189e-06, "loss": 0.1303, "step": 424290 }, { "epoch": 2.5221273130398085, "grad_norm": 3.645803689956665, "learning_rate": 5.792100986445107e-06, "loss": 0.1314, "step": 424300 }, { "epoch": 2.5221867551164765, "grad_norm": 4.371119976043701, "learning_rate": 5.791896113890932e-06, "loss": 0.1477, "step": 424310 }, { "epoch": 2.5222461971931454, "grad_norm": 4.443108558654785, "learning_rate": 5.79169123997302e-06, "loss": 0.1355, "step": 424320 }, { "epoch": 2.5223056392698133, "grad_norm": 3.422731399536133, "learning_rate": 5.79148636469172e-06, "loss": 0.1312, "step": 424330 }, { "epoch": 2.522365081346482, "grad_norm": 3.700662851333618, "learning_rate": 5.791281488047384e-06, "loss": 0.1289, "step": 424340 }, { "epoch": 2.52242452342315, "grad_norm": 4.469148635864258, "learning_rate": 5.791076610040368e-06, "loss": 0.1345, "step": 424350 }, { "epoch": 2.5224839654998186, "grad_norm": 4.907576084136963, "learning_rate": 5.790871730671025e-06, "loss": 0.1327, "step": 424360 }, { "epoch": 2.522543407576487, "grad_norm": 3.498399496078491, "learning_rate": 5.790666849939706e-06, "loss": 0.1394, "step": 424370 }, { "epoch": 2.5226028496531554, "grad_norm": 3.4017608165740967, "learning_rate": 5.790461967846763e-06, "loss": 0.1363, "step": 424380 }, { "epoch": 2.522662291729824, "grad_norm": 4.9565110206604, "learning_rate": 5.790257084392552e-06, "loss": 0.1169, "step": 424390 }, { "epoch": 2.5227217338064922, "grad_norm": 3.9978816509246826, "learning_rate": 5.790052199577423e-06, "loss": 0.1557, "step": 424400 }, { "epoch": 2.5227811758831606, "grad_norm": 3.855466604232788, "learning_rate": 5.78984731340173e-06, "loss": 0.1331, "step": 424410 }, { "epoch": 2.522840617959829, "grad_norm": 3.463059186935425, "learning_rate": 5.789642425865826e-06, "loss": 0.1258, "step": 424420 }, { "epoch": 2.5229000600364975, "grad_norm": 2.742640495300293, "learning_rate": 5.789437536970063e-06, "loss": 0.1268, "step": 424430 }, { "epoch": 2.522959502113166, "grad_norm": 3.629147529602051, "learning_rate": 5.789232646714794e-06, "loss": 0.1431, "step": 424440 }, { "epoch": 2.5230189441898343, "grad_norm": 4.9366559982299805, "learning_rate": 5.789027755100373e-06, "loss": 0.1551, "step": 424450 }, { "epoch": 2.5230783862665027, "grad_norm": 4.714129447937012, "learning_rate": 5.788822862127151e-06, "loss": 0.1203, "step": 424460 }, { "epoch": 2.523137828343171, "grad_norm": 5.610133647918701, "learning_rate": 5.788617967795484e-06, "loss": 0.114, "step": 424470 }, { "epoch": 2.5231972704198395, "grad_norm": 3.9169368743896484, "learning_rate": 5.788413072105721e-06, "loss": 0.141, "step": 424480 }, { "epoch": 2.523256712496508, "grad_norm": 6.951335906982422, "learning_rate": 5.788208175058216e-06, "loss": 0.1412, "step": 424490 }, { "epoch": 2.523316154573176, "grad_norm": 4.258957386016846, "learning_rate": 5.788003276653325e-06, "loss": 0.1199, "step": 424500 }, { "epoch": 2.523375596649845, "grad_norm": 3.5441906452178955, "learning_rate": 5.787798376891396e-06, "loss": 0.1455, "step": 424510 }, { "epoch": 2.5234350387265128, "grad_norm": 5.104649543762207, "learning_rate": 5.787593475772786e-06, "loss": 0.1279, "step": 424520 }, { "epoch": 2.5234944808031816, "grad_norm": 4.178398609161377, "learning_rate": 5.787388573297845e-06, "loss": 0.1388, "step": 424530 }, { "epoch": 2.5235539228798496, "grad_norm": 4.109703063964844, "learning_rate": 5.787183669466927e-06, "loss": 0.1499, "step": 424540 }, { "epoch": 2.523613364956518, "grad_norm": 3.812814712524414, "learning_rate": 5.786978764280385e-06, "loss": 0.127, "step": 424550 }, { "epoch": 2.5236728070331864, "grad_norm": 3.646198272705078, "learning_rate": 5.786773857738573e-06, "loss": 0.1331, "step": 424560 }, { "epoch": 2.523732249109855, "grad_norm": 4.311239242553711, "learning_rate": 5.7865689498418395e-06, "loss": 0.1296, "step": 424570 }, { "epoch": 2.5237916911865232, "grad_norm": 4.873751163482666, "learning_rate": 5.786364040590542e-06, "loss": 0.1179, "step": 424580 }, { "epoch": 2.5238511332631917, "grad_norm": 3.485330104827881, "learning_rate": 5.786159129985032e-06, "loss": 0.1285, "step": 424590 }, { "epoch": 2.52391057533986, "grad_norm": 4.623011112213135, "learning_rate": 5.7859542180256625e-06, "loss": 0.1345, "step": 424600 }, { "epoch": 2.5239700174165285, "grad_norm": 4.376277446746826, "learning_rate": 5.785749304712785e-06, "loss": 0.15, "step": 424610 }, { "epoch": 2.524029459493197, "grad_norm": 4.005512237548828, "learning_rate": 5.785544390046755e-06, "loss": 0.1347, "step": 424620 }, { "epoch": 2.5240889015698653, "grad_norm": 5.7041239738464355, "learning_rate": 5.785339474027923e-06, "loss": 0.1376, "step": 424630 }, { "epoch": 2.5241483436465337, "grad_norm": 4.149172782897949, "learning_rate": 5.7851345566566406e-06, "loss": 0.1354, "step": 424640 }, { "epoch": 2.524207785723202, "grad_norm": 3.291264295578003, "learning_rate": 5.784929637933265e-06, "loss": 0.123, "step": 424650 }, { "epoch": 2.5242672277998706, "grad_norm": 4.379364013671875, "learning_rate": 5.784724717858148e-06, "loss": 0.1435, "step": 424660 }, { "epoch": 2.5243266698765385, "grad_norm": 4.16773796081543, "learning_rate": 5.784519796431639e-06, "loss": 0.1223, "step": 424670 }, { "epoch": 2.5243861119532074, "grad_norm": 5.468937397003174, "learning_rate": 5.784314873654094e-06, "loss": 0.143, "step": 424680 }, { "epoch": 2.5244455540298754, "grad_norm": 3.5872271060943604, "learning_rate": 5.784109949525866e-06, "loss": 0.1418, "step": 424690 }, { "epoch": 2.524504996106544, "grad_norm": 5.434750556945801, "learning_rate": 5.783905024047307e-06, "loss": 0.1456, "step": 424700 }, { "epoch": 2.524564438183212, "grad_norm": 4.500215530395508, "learning_rate": 5.783700097218769e-06, "loss": 0.1325, "step": 424710 }, { "epoch": 2.5246238802598806, "grad_norm": 4.1099700927734375, "learning_rate": 5.783495169040607e-06, "loss": 0.1442, "step": 424720 }, { "epoch": 2.524683322336549, "grad_norm": 4.950239181518555, "learning_rate": 5.783290239513173e-06, "loss": 0.1457, "step": 424730 }, { "epoch": 2.5247427644132174, "grad_norm": 3.600623846054077, "learning_rate": 5.783085308636819e-06, "loss": 0.1424, "step": 424740 }, { "epoch": 2.524802206489886, "grad_norm": 4.804495811462402, "learning_rate": 5.782880376411899e-06, "loss": 0.1521, "step": 424750 }, { "epoch": 2.5248616485665543, "grad_norm": 3.3728320598602295, "learning_rate": 5.782675442838765e-06, "loss": 0.1155, "step": 424760 }, { "epoch": 2.5249210906432227, "grad_norm": 3.1227567195892334, "learning_rate": 5.782470507917771e-06, "loss": 0.1407, "step": 424770 }, { "epoch": 2.524980532719891, "grad_norm": 5.2825493812561035, "learning_rate": 5.7822655716492705e-06, "loss": 0.1415, "step": 424780 }, { "epoch": 2.5250399747965595, "grad_norm": 5.267899990081787, "learning_rate": 5.782060634033613e-06, "loss": 0.1396, "step": 424790 }, { "epoch": 2.525099416873228, "grad_norm": 3.8157334327697754, "learning_rate": 5.7818556950711546e-06, "loss": 0.1241, "step": 424800 }, { "epoch": 2.5251588589498963, "grad_norm": 4.5087971687316895, "learning_rate": 5.781650754762248e-06, "loss": 0.1476, "step": 424810 }, { "epoch": 2.5252183010265647, "grad_norm": 3.272780179977417, "learning_rate": 5.781445813107246e-06, "loss": 0.1074, "step": 424820 }, { "epoch": 2.525277743103233, "grad_norm": 3.7094430923461914, "learning_rate": 5.781240870106499e-06, "loss": 0.1255, "step": 424830 }, { "epoch": 2.5253371851799016, "grad_norm": 3.7520225048065186, "learning_rate": 5.7810359257603645e-06, "loss": 0.1364, "step": 424840 }, { "epoch": 2.52539662725657, "grad_norm": 3.9681105613708496, "learning_rate": 5.780830980069192e-06, "loss": 0.1268, "step": 424850 }, { "epoch": 2.525456069333238, "grad_norm": 4.12009859085083, "learning_rate": 5.780626033033337e-06, "loss": 0.128, "step": 424860 }, { "epoch": 2.525515511409907, "grad_norm": 4.790714263916016, "learning_rate": 5.7804210846531475e-06, "loss": 0.1507, "step": 424870 }, { "epoch": 2.525574953486575, "grad_norm": 4.524896621704102, "learning_rate": 5.780216134928982e-06, "loss": 0.1545, "step": 424880 }, { "epoch": 2.5256343955632437, "grad_norm": 4.003457546234131, "learning_rate": 5.78001118386119e-06, "loss": 0.1308, "step": 424890 }, { "epoch": 2.5256938376399116, "grad_norm": 5.297300815582275, "learning_rate": 5.779806231450125e-06, "loss": 0.1236, "step": 424900 }, { "epoch": 2.52575327971658, "grad_norm": 4.237571716308594, "learning_rate": 5.779601277696143e-06, "loss": 0.1283, "step": 424910 }, { "epoch": 2.5258127217932484, "grad_norm": 3.3299150466918945, "learning_rate": 5.779396322599593e-06, "loss": 0.1534, "step": 424920 }, { "epoch": 2.525872163869917, "grad_norm": 3.7765777111053467, "learning_rate": 5.77919136616083e-06, "loss": 0.1433, "step": 424930 }, { "epoch": 2.5259316059465853, "grad_norm": 5.711058616638184, "learning_rate": 5.778986408380206e-06, "loss": 0.1305, "step": 424940 }, { "epoch": 2.5259910480232537, "grad_norm": 5.013721466064453, "learning_rate": 5.778781449258076e-06, "loss": 0.1372, "step": 424950 }, { "epoch": 2.526050490099922, "grad_norm": 4.399056911468506, "learning_rate": 5.778576488794789e-06, "loss": 0.1359, "step": 424960 }, { "epoch": 2.5261099321765905, "grad_norm": 3.6305294036865234, "learning_rate": 5.778371526990702e-06, "loss": 0.1217, "step": 424970 }, { "epoch": 2.526169374253259, "grad_norm": 3.9372291564941406, "learning_rate": 5.778166563846167e-06, "loss": 0.1417, "step": 424980 }, { "epoch": 2.5262288163299274, "grad_norm": 4.459066867828369, "learning_rate": 5.7779615993615345e-06, "loss": 0.1222, "step": 424990 }, { "epoch": 2.5262882584065958, "grad_norm": 3.605966329574585, "learning_rate": 5.777756633537162e-06, "loss": 0.14, "step": 425000 }, { "epoch": 2.526347700483264, "grad_norm": 3.179250717163086, "learning_rate": 5.777551666373397e-06, "loss": 0.1276, "step": 425010 }, { "epoch": 2.5264071425599326, "grad_norm": 4.519404411315918, "learning_rate": 5.777346697870596e-06, "loss": 0.1422, "step": 425020 }, { "epoch": 2.526466584636601, "grad_norm": 4.050887107849121, "learning_rate": 5.777141728029111e-06, "loss": 0.1367, "step": 425030 }, { "epoch": 2.5265260267132694, "grad_norm": 4.816746234893799, "learning_rate": 5.776936756849296e-06, "loss": 0.1298, "step": 425040 }, { "epoch": 2.5265854687899374, "grad_norm": 3.1001975536346436, "learning_rate": 5.776731784331504e-06, "loss": 0.118, "step": 425050 }, { "epoch": 2.5266449108666063, "grad_norm": 5.12125825881958, "learning_rate": 5.776526810476085e-06, "loss": 0.1245, "step": 425060 }, { "epoch": 2.5267043529432742, "grad_norm": 6.665688514709473, "learning_rate": 5.776321835283396e-06, "loss": 0.1276, "step": 425070 }, { "epoch": 2.526763795019943, "grad_norm": 3.562278985977173, "learning_rate": 5.776116858753788e-06, "loss": 0.1451, "step": 425080 }, { "epoch": 2.526823237096611, "grad_norm": 4.7064208984375, "learning_rate": 5.7759118808876125e-06, "loss": 0.137, "step": 425090 }, { "epoch": 2.5268826791732795, "grad_norm": 4.7311272621154785, "learning_rate": 5.775706901685225e-06, "loss": 0.139, "step": 425100 }, { "epoch": 2.526942121249948, "grad_norm": 5.736711025238037, "learning_rate": 5.7755019211469785e-06, "loss": 0.1384, "step": 425110 }, { "epoch": 2.5270015633266163, "grad_norm": 5.5191426277160645, "learning_rate": 5.775296939273225e-06, "loss": 0.1312, "step": 425120 }, { "epoch": 2.5270610054032847, "grad_norm": 4.262577056884766, "learning_rate": 5.775091956064316e-06, "loss": 0.1415, "step": 425130 }, { "epoch": 2.527120447479953, "grad_norm": 4.626491069793701, "learning_rate": 5.774886971520608e-06, "loss": 0.1268, "step": 425140 }, { "epoch": 2.5271798895566215, "grad_norm": 4.051098823547363, "learning_rate": 5.774681985642452e-06, "loss": 0.1283, "step": 425150 }, { "epoch": 2.52723933163329, "grad_norm": 5.485699653625488, "learning_rate": 5.7744769984302006e-06, "loss": 0.1319, "step": 425160 }, { "epoch": 2.5272987737099584, "grad_norm": 4.989028453826904, "learning_rate": 5.774272009884208e-06, "loss": 0.1309, "step": 425170 }, { "epoch": 2.527358215786627, "grad_norm": 4.339657306671143, "learning_rate": 5.774067020004827e-06, "loss": 0.1438, "step": 425180 }, { "epoch": 2.527417657863295, "grad_norm": 4.705045700073242, "learning_rate": 5.7738620287924084e-06, "loss": 0.1335, "step": 425190 }, { "epoch": 2.5274770999399636, "grad_norm": 4.420077800750732, "learning_rate": 5.773657036247309e-06, "loss": 0.1448, "step": 425200 }, { "epoch": 2.527536542016632, "grad_norm": 4.393096446990967, "learning_rate": 5.773452042369878e-06, "loss": 0.1362, "step": 425210 }, { "epoch": 2.5275959840933004, "grad_norm": 4.02016544342041, "learning_rate": 5.7732470471604705e-06, "loss": 0.1275, "step": 425220 }, { "epoch": 2.527655426169969, "grad_norm": 5.224916458129883, "learning_rate": 5.77304205061944e-06, "loss": 0.1281, "step": 425230 }, { "epoch": 2.527714868246637, "grad_norm": 5.081454277038574, "learning_rate": 5.77283705274714e-06, "loss": 0.1333, "step": 425240 }, { "epoch": 2.5277743103233057, "grad_norm": 4.714267730712891, "learning_rate": 5.772632053543921e-06, "loss": 0.1401, "step": 425250 }, { "epoch": 2.5278337523999737, "grad_norm": 4.710804462432861, "learning_rate": 5.772427053010137e-06, "loss": 0.1434, "step": 425260 }, { "epoch": 2.5278931944766425, "grad_norm": 5.128723621368408, "learning_rate": 5.772222051146142e-06, "loss": 0.1425, "step": 425270 }, { "epoch": 2.5279526365533105, "grad_norm": 3.9906458854675293, "learning_rate": 5.77201704795229e-06, "loss": 0.1274, "step": 425280 }, { "epoch": 2.528012078629979, "grad_norm": 4.184140682220459, "learning_rate": 5.771812043428931e-06, "loss": 0.1176, "step": 425290 }, { "epoch": 2.5280715207066473, "grad_norm": 4.897065162658691, "learning_rate": 5.77160703757642e-06, "loss": 0.1311, "step": 425300 }, { "epoch": 2.5281309627833157, "grad_norm": 3.836082696914673, "learning_rate": 5.77140203039511e-06, "loss": 0.1387, "step": 425310 }, { "epoch": 2.528190404859984, "grad_norm": 3.4633898735046387, "learning_rate": 5.771197021885352e-06, "loss": 0.1336, "step": 425320 }, { "epoch": 2.5282498469366526, "grad_norm": 3.86407470703125, "learning_rate": 5.770992012047503e-06, "loss": 0.1232, "step": 425330 }, { "epoch": 2.528309289013321, "grad_norm": 4.910133361816406, "learning_rate": 5.770787000881911e-06, "loss": 0.1523, "step": 425340 }, { "epoch": 2.5283687310899894, "grad_norm": 4.054984092712402, "learning_rate": 5.7705819883889336e-06, "loss": 0.1456, "step": 425350 }, { "epoch": 2.528428173166658, "grad_norm": 4.548264980316162, "learning_rate": 5.770376974568921e-06, "loss": 0.1445, "step": 425360 }, { "epoch": 2.528487615243326, "grad_norm": 4.538839340209961, "learning_rate": 5.770171959422228e-06, "loss": 0.1404, "step": 425370 }, { "epoch": 2.5285470573199946, "grad_norm": 4.3039374351501465, "learning_rate": 5.7699669429492075e-06, "loss": 0.1373, "step": 425380 }, { "epoch": 2.528606499396663, "grad_norm": 7.702332019805908, "learning_rate": 5.769761925150212e-06, "loss": 0.136, "step": 425390 }, { "epoch": 2.5286659414733315, "grad_norm": 4.53765869140625, "learning_rate": 5.769556906025595e-06, "loss": 0.1326, "step": 425400 }, { "epoch": 2.5287253835499994, "grad_norm": 3.977749824523926, "learning_rate": 5.769351885575709e-06, "loss": 0.1298, "step": 425410 }, { "epoch": 2.5287848256266683, "grad_norm": 4.051115989685059, "learning_rate": 5.769146863800905e-06, "loss": 0.1401, "step": 425420 }, { "epoch": 2.5288442677033363, "grad_norm": 3.797992706298828, "learning_rate": 5.768941840701541e-06, "loss": 0.1205, "step": 425430 }, { "epoch": 2.528903709780005, "grad_norm": 3.9286956787109375, "learning_rate": 5.768736816277967e-06, "loss": 0.1309, "step": 425440 }, { "epoch": 2.528963151856673, "grad_norm": 3.1546969413757324, "learning_rate": 5.768531790530533e-06, "loss": 0.1204, "step": 425450 }, { "epoch": 2.5290225939333415, "grad_norm": 4.018196105957031, "learning_rate": 5.768326763459599e-06, "loss": 0.1398, "step": 425460 }, { "epoch": 2.52908203601001, "grad_norm": 4.267498970031738, "learning_rate": 5.768121735065516e-06, "loss": 0.1412, "step": 425470 }, { "epoch": 2.5291414780866783, "grad_norm": 5.707125663757324, "learning_rate": 5.767916705348633e-06, "loss": 0.1401, "step": 425480 }, { "epoch": 2.5292009201633467, "grad_norm": 4.74653959274292, "learning_rate": 5.767711674309306e-06, "loss": 0.1457, "step": 425490 }, { "epoch": 2.529260362240015, "grad_norm": 4.662486553192139, "learning_rate": 5.76750664194789e-06, "loss": 0.1312, "step": 425500 }, { "epoch": 2.5293198043166836, "grad_norm": 3.7257204055786133, "learning_rate": 5.767301608264735e-06, "loss": 0.1241, "step": 425510 }, { "epoch": 2.529379246393352, "grad_norm": 4.920075416564941, "learning_rate": 5.767096573260194e-06, "loss": 0.1298, "step": 425520 }, { "epoch": 2.5294386884700204, "grad_norm": 3.9355430603027344, "learning_rate": 5.7668915369346225e-06, "loss": 0.1301, "step": 425530 }, { "epoch": 2.529498130546689, "grad_norm": 5.636873722076416, "learning_rate": 5.766686499288372e-06, "loss": 0.1266, "step": 425540 }, { "epoch": 2.5295575726233572, "grad_norm": 3.5969550609588623, "learning_rate": 5.7664814603217944e-06, "loss": 0.1352, "step": 425550 }, { "epoch": 2.5296170147000256, "grad_norm": 3.8395988941192627, "learning_rate": 5.766276420035245e-06, "loss": 0.1379, "step": 425560 }, { "epoch": 2.529676456776694, "grad_norm": 5.100146293640137, "learning_rate": 5.766071378429077e-06, "loss": 0.1308, "step": 425570 }, { "epoch": 2.5297358988533625, "grad_norm": 4.120405197143555, "learning_rate": 5.765866335503641e-06, "loss": 0.1313, "step": 425580 }, { "epoch": 2.529795340930031, "grad_norm": 4.807340145111084, "learning_rate": 5.765661291259294e-06, "loss": 0.1331, "step": 425590 }, { "epoch": 2.529854783006699, "grad_norm": 2.888453722000122, "learning_rate": 5.765456245696386e-06, "loss": 0.1383, "step": 425600 }, { "epoch": 2.5299142250833677, "grad_norm": 4.477590560913086, "learning_rate": 5.765251198815269e-06, "loss": 0.1282, "step": 425610 }, { "epoch": 2.5299736671600357, "grad_norm": 4.978386878967285, "learning_rate": 5.765046150616301e-06, "loss": 0.1345, "step": 425620 }, { "epoch": 2.5300331092367045, "grad_norm": 3.470170259475708, "learning_rate": 5.7648411010998315e-06, "loss": 0.1242, "step": 425630 }, { "epoch": 2.5300925513133725, "grad_norm": 3.87748384475708, "learning_rate": 5.764636050266214e-06, "loss": 0.1333, "step": 425640 }, { "epoch": 2.530151993390041, "grad_norm": 4.28475284576416, "learning_rate": 5.764430998115802e-06, "loss": 0.1313, "step": 425650 }, { "epoch": 2.5302114354667093, "grad_norm": 4.8108229637146, "learning_rate": 5.764225944648949e-06, "loss": 0.1389, "step": 425660 }, { "epoch": 2.5302708775433778, "grad_norm": 5.160974502563477, "learning_rate": 5.764020889866007e-06, "loss": 0.1308, "step": 425670 }, { "epoch": 2.530330319620046, "grad_norm": 4.027706623077393, "learning_rate": 5.76381583376733e-06, "loss": 0.1266, "step": 425680 }, { "epoch": 2.5303897616967146, "grad_norm": 5.450916767120361, "learning_rate": 5.763610776353272e-06, "loss": 0.1278, "step": 425690 }, { "epoch": 2.530449203773383, "grad_norm": 4.469828128814697, "learning_rate": 5.7634057176241846e-06, "loss": 0.1216, "step": 425700 }, { "epoch": 2.5305086458500514, "grad_norm": 4.027822971343994, "learning_rate": 5.763200657580421e-06, "loss": 0.1121, "step": 425710 }, { "epoch": 2.53056808792672, "grad_norm": 4.0763258934021, "learning_rate": 5.7629955962223345e-06, "loss": 0.1411, "step": 425720 }, { "epoch": 2.5306275300033882, "grad_norm": 5.0393500328063965, "learning_rate": 5.76279053355028e-06, "loss": 0.1487, "step": 425730 }, { "epoch": 2.5306869720800567, "grad_norm": 4.567573547363281, "learning_rate": 5.762585469564608e-06, "loss": 0.1452, "step": 425740 }, { "epoch": 2.530746414156725, "grad_norm": 5.928071022033691, "learning_rate": 5.7623804042656725e-06, "loss": 0.1586, "step": 425750 }, { "epoch": 2.5308058562333935, "grad_norm": 3.653428077697754, "learning_rate": 5.762175337653829e-06, "loss": 0.1189, "step": 425760 }, { "epoch": 2.530865298310062, "grad_norm": 3.765979528427124, "learning_rate": 5.761970269729426e-06, "loss": 0.135, "step": 425770 }, { "epoch": 2.5309247403867303, "grad_norm": 4.800744533538818, "learning_rate": 5.76176520049282e-06, "loss": 0.1335, "step": 425780 }, { "epoch": 2.5309841824633983, "grad_norm": 6.20220422744751, "learning_rate": 5.761560129944364e-06, "loss": 0.1462, "step": 425790 }, { "epoch": 2.531043624540067, "grad_norm": 4.773742198944092, "learning_rate": 5.761355058084413e-06, "loss": 0.1195, "step": 425800 }, { "epoch": 2.531103066616735, "grad_norm": 4.959650993347168, "learning_rate": 5.761149984913313e-06, "loss": 0.1407, "step": 425810 }, { "epoch": 2.531162508693404, "grad_norm": 4.816728115081787, "learning_rate": 5.760944910431425e-06, "loss": 0.1279, "step": 425820 }, { "epoch": 2.531221950770072, "grad_norm": 5.1166510581970215, "learning_rate": 5.760739834639098e-06, "loss": 0.1229, "step": 425830 }, { "epoch": 2.5312813928467404, "grad_norm": 5.257776737213135, "learning_rate": 5.760534757536687e-06, "loss": 0.1271, "step": 425840 }, { "epoch": 2.531340834923409, "grad_norm": 3.7549502849578857, "learning_rate": 5.760329679124545e-06, "loss": 0.129, "step": 425850 }, { "epoch": 2.531400277000077, "grad_norm": 4.396271228790283, "learning_rate": 5.7601245994030235e-06, "loss": 0.1363, "step": 425860 }, { "epoch": 2.5314597190767456, "grad_norm": 2.963020086288452, "learning_rate": 5.7599195183724755e-06, "loss": 0.1311, "step": 425870 }, { "epoch": 2.531519161153414, "grad_norm": 4.455670356750488, "learning_rate": 5.759714436033257e-06, "loss": 0.1439, "step": 425880 }, { "epoch": 2.5315786032300824, "grad_norm": 4.392596244812012, "learning_rate": 5.759509352385719e-06, "loss": 0.1522, "step": 425890 }, { "epoch": 2.531638045306751, "grad_norm": 4.222307205200195, "learning_rate": 5.759304267430216e-06, "loss": 0.1268, "step": 425900 }, { "epoch": 2.5316974873834193, "grad_norm": 4.8331298828125, "learning_rate": 5.759099181167099e-06, "loss": 0.1359, "step": 425910 }, { "epoch": 2.5317569294600877, "grad_norm": 5.238926410675049, "learning_rate": 5.758894093596724e-06, "loss": 0.1419, "step": 425920 }, { "epoch": 2.531816371536756, "grad_norm": 3.2673563957214355, "learning_rate": 5.7586890047194435e-06, "loss": 0.1207, "step": 425930 }, { "epoch": 2.5318758136134245, "grad_norm": 4.167824745178223, "learning_rate": 5.758483914535608e-06, "loss": 0.1149, "step": 425940 }, { "epoch": 2.531935255690093, "grad_norm": 5.769572734832764, "learning_rate": 5.758278823045573e-06, "loss": 0.1471, "step": 425950 }, { "epoch": 2.5319946977667613, "grad_norm": 2.770129919052124, "learning_rate": 5.758073730249694e-06, "loss": 0.1315, "step": 425960 }, { "epoch": 2.5320541398434298, "grad_norm": 4.304275989532471, "learning_rate": 5.7578686361483185e-06, "loss": 0.1385, "step": 425970 }, { "epoch": 2.5321135819200977, "grad_norm": 3.8859074115753174, "learning_rate": 5.757663540741804e-06, "loss": 0.1384, "step": 425980 }, { "epoch": 2.5321730239967666, "grad_norm": 3.7432703971862793, "learning_rate": 5.7574584440305025e-06, "loss": 0.1406, "step": 425990 }, { "epoch": 2.5322324660734346, "grad_norm": 4.037702560424805, "learning_rate": 5.757253346014766e-06, "loss": 0.1314, "step": 426000 }, { "epoch": 2.532291908150103, "grad_norm": 4.429214954376221, "learning_rate": 5.75704824669495e-06, "loss": 0.1399, "step": 426010 }, { "epoch": 2.5323513502267714, "grad_norm": 3.4539406299591064, "learning_rate": 5.756843146071407e-06, "loss": 0.1433, "step": 426020 }, { "epoch": 2.53241079230344, "grad_norm": 4.639430046081543, "learning_rate": 5.756638044144489e-06, "loss": 0.1297, "step": 426030 }, { "epoch": 2.532470234380108, "grad_norm": 4.1183552742004395, "learning_rate": 5.75643294091455e-06, "loss": 0.128, "step": 426040 }, { "epoch": 2.5325296764567766, "grad_norm": 3.844806671142578, "learning_rate": 5.756227836381945e-06, "loss": 0.1175, "step": 426050 }, { "epoch": 2.532589118533445, "grad_norm": 3.8431801795959473, "learning_rate": 5.756022730547024e-06, "loss": 0.1411, "step": 426060 }, { "epoch": 2.5326485606101135, "grad_norm": 4.255753993988037, "learning_rate": 5.75581762341014e-06, "loss": 0.156, "step": 426070 }, { "epoch": 2.532708002686782, "grad_norm": 4.527753829956055, "learning_rate": 5.75561251497165e-06, "loss": 0.1485, "step": 426080 }, { "epoch": 2.5327674447634503, "grad_norm": 3.678495407104492, "learning_rate": 5.755407405231905e-06, "loss": 0.1238, "step": 426090 }, { "epoch": 2.5328268868401187, "grad_norm": 3.61618709564209, "learning_rate": 5.755202294191258e-06, "loss": 0.1416, "step": 426100 }, { "epoch": 2.532886328916787, "grad_norm": 4.394599437713623, "learning_rate": 5.754997181850062e-06, "loss": 0.1244, "step": 426110 }, { "epoch": 2.5329457709934555, "grad_norm": 4.1890082359313965, "learning_rate": 5.754792068208671e-06, "loss": 0.1304, "step": 426120 }, { "epoch": 2.533005213070124, "grad_norm": 3.7706642150878906, "learning_rate": 5.754586953267438e-06, "loss": 0.1329, "step": 426130 }, { "epoch": 2.5330646551467924, "grad_norm": 3.999211072921753, "learning_rate": 5.754381837026717e-06, "loss": 0.1455, "step": 426140 }, { "epoch": 2.5331240972234603, "grad_norm": 5.3763108253479, "learning_rate": 5.75417671948686e-06, "loss": 0.1337, "step": 426150 }, { "epoch": 2.533183539300129, "grad_norm": 4.4134955406188965, "learning_rate": 5.7539716006482205e-06, "loss": 0.1357, "step": 426160 }, { "epoch": 2.533242981376797, "grad_norm": 4.316518783569336, "learning_rate": 5.753766480511152e-06, "loss": 0.1327, "step": 426170 }, { "epoch": 2.533302423453466, "grad_norm": 4.284608364105225, "learning_rate": 5.753561359076009e-06, "loss": 0.1265, "step": 426180 }, { "epoch": 2.533361865530134, "grad_norm": 4.390176773071289, "learning_rate": 5.753356236343141e-06, "loss": 0.1389, "step": 426190 }, { "epoch": 2.5334213076068024, "grad_norm": 3.8305578231811523, "learning_rate": 5.753151112312905e-06, "loss": 0.1218, "step": 426200 }, { "epoch": 2.533480749683471, "grad_norm": 3.049771785736084, "learning_rate": 5.752945986985653e-06, "loss": 0.1094, "step": 426210 }, { "epoch": 2.5335401917601392, "grad_norm": 4.76485538482666, "learning_rate": 5.752740860361738e-06, "loss": 0.1492, "step": 426220 }, { "epoch": 2.5335996338368076, "grad_norm": 2.682619571685791, "learning_rate": 5.752535732441512e-06, "loss": 0.1156, "step": 426230 }, { "epoch": 2.533659075913476, "grad_norm": 2.925537347793579, "learning_rate": 5.752330603225331e-06, "loss": 0.1211, "step": 426240 }, { "epoch": 2.5337185179901445, "grad_norm": 4.306481838226318, "learning_rate": 5.752125472713548e-06, "loss": 0.1299, "step": 426250 }, { "epoch": 2.533777960066813, "grad_norm": 4.543624401092529, "learning_rate": 5.751920340906514e-06, "loss": 0.1224, "step": 426260 }, { "epoch": 2.5338374021434813, "grad_norm": 5.924800872802734, "learning_rate": 5.751715207804583e-06, "loss": 0.1486, "step": 426270 }, { "epoch": 2.5338968442201497, "grad_norm": 3.147397518157959, "learning_rate": 5.751510073408111e-06, "loss": 0.1163, "step": 426280 }, { "epoch": 2.533956286296818, "grad_norm": 6.1690545082092285, "learning_rate": 5.751304937717445e-06, "loss": 0.1267, "step": 426290 }, { "epoch": 2.5340157283734865, "grad_norm": 4.69603967666626, "learning_rate": 5.751099800732945e-06, "loss": 0.1219, "step": 426300 }, { "epoch": 2.534075170450155, "grad_norm": 4.8994526863098145, "learning_rate": 5.750894662454962e-06, "loss": 0.1475, "step": 426310 }, { "epoch": 2.5341346125268234, "grad_norm": 5.310569763183594, "learning_rate": 5.750689522883848e-06, "loss": 0.1468, "step": 426320 }, { "epoch": 2.534194054603492, "grad_norm": 4.402876377105713, "learning_rate": 5.750484382019957e-06, "loss": 0.1104, "step": 426330 }, { "epoch": 2.5342534966801598, "grad_norm": 4.3069376945495605, "learning_rate": 5.750279239863642e-06, "loss": 0.1236, "step": 426340 }, { "epoch": 2.5343129387568286, "grad_norm": 3.9108798503875732, "learning_rate": 5.7500740964152565e-06, "loss": 0.1355, "step": 426350 }, { "epoch": 2.5343723808334966, "grad_norm": 5.038203716278076, "learning_rate": 5.749868951675155e-06, "loss": 0.1444, "step": 426360 }, { "epoch": 2.5344318229101654, "grad_norm": 4.283570289611816, "learning_rate": 5.749663805643688e-06, "loss": 0.1407, "step": 426370 }, { "epoch": 2.5344912649868334, "grad_norm": 4.2856574058532715, "learning_rate": 5.749458658321213e-06, "loss": 0.14, "step": 426380 }, { "epoch": 2.534550707063502, "grad_norm": 4.032532691955566, "learning_rate": 5.749253509708078e-06, "loss": 0.1407, "step": 426390 }, { "epoch": 2.5346101491401702, "grad_norm": 4.2491254806518555, "learning_rate": 5.749048359804641e-06, "loss": 0.117, "step": 426400 }, { "epoch": 2.5346695912168387, "grad_norm": 3.231118679046631, "learning_rate": 5.748843208611254e-06, "loss": 0.1409, "step": 426410 }, { "epoch": 2.534729033293507, "grad_norm": 3.415555715560913, "learning_rate": 5.748638056128267e-06, "loss": 0.1108, "step": 426420 }, { "epoch": 2.5347884753701755, "grad_norm": 5.6467814445495605, "learning_rate": 5.7484329023560385e-06, "loss": 0.13, "step": 426430 }, { "epoch": 2.534847917446844, "grad_norm": 4.577996253967285, "learning_rate": 5.748227747294917e-06, "loss": 0.1391, "step": 426440 }, { "epoch": 2.5349073595235123, "grad_norm": 4.170571327209473, "learning_rate": 5.748022590945259e-06, "loss": 0.1406, "step": 426450 }, { "epoch": 2.5349668016001807, "grad_norm": 3.754634141921997, "learning_rate": 5.7478174333074165e-06, "loss": 0.1202, "step": 426460 }, { "epoch": 2.535026243676849, "grad_norm": 4.495971202850342, "learning_rate": 5.747612274381744e-06, "loss": 0.1223, "step": 426470 }, { "epoch": 2.5350856857535176, "grad_norm": 4.1321539878845215, "learning_rate": 5.747407114168594e-06, "loss": 0.1518, "step": 426480 }, { "epoch": 2.535145127830186, "grad_norm": 4.507157325744629, "learning_rate": 5.7472019526683176e-06, "loss": 0.1242, "step": 426490 }, { "epoch": 2.5352045699068544, "grad_norm": 3.543248176574707, "learning_rate": 5.746996789881273e-06, "loss": 0.1175, "step": 426500 }, { "epoch": 2.535264011983523, "grad_norm": 4.649399280548096, "learning_rate": 5.7467916258078104e-06, "loss": 0.1378, "step": 426510 }, { "epoch": 2.535323454060191, "grad_norm": 5.612658977508545, "learning_rate": 5.746586460448283e-06, "loss": 0.1262, "step": 426520 }, { "epoch": 2.535382896136859, "grad_norm": 2.829864025115967, "learning_rate": 5.7463812938030435e-06, "loss": 0.1353, "step": 426530 }, { "epoch": 2.535442338213528, "grad_norm": 5.08721399307251, "learning_rate": 5.746176125872447e-06, "loss": 0.138, "step": 426540 }, { "epoch": 2.535501780290196, "grad_norm": 3.5222115516662598, "learning_rate": 5.745970956656847e-06, "loss": 0.1354, "step": 426550 }, { "epoch": 2.535561222366865, "grad_norm": 4.0256452560424805, "learning_rate": 5.7457657861565955e-06, "loss": 0.1347, "step": 426560 }, { "epoch": 2.535620664443533, "grad_norm": 4.804675102233887, "learning_rate": 5.745560614372047e-06, "loss": 0.1328, "step": 426570 }, { "epoch": 2.5356801065202013, "grad_norm": 3.5990428924560547, "learning_rate": 5.745355441303553e-06, "loss": 0.1428, "step": 426580 }, { "epoch": 2.5357395485968697, "grad_norm": 4.79874849319458, "learning_rate": 5.745150266951468e-06, "loss": 0.1305, "step": 426590 }, { "epoch": 2.535798990673538, "grad_norm": 5.355947017669678, "learning_rate": 5.744945091316147e-06, "loss": 0.1346, "step": 426600 }, { "epoch": 2.5358584327502065, "grad_norm": 3.7559707164764404, "learning_rate": 5.744739914397941e-06, "loss": 0.1306, "step": 426610 }, { "epoch": 2.535917874826875, "grad_norm": 5.334468364715576, "learning_rate": 5.744534736197202e-06, "loss": 0.1265, "step": 426620 }, { "epoch": 2.5359773169035433, "grad_norm": 4.659782886505127, "learning_rate": 5.744329556714288e-06, "loss": 0.159, "step": 426630 }, { "epoch": 2.5360367589802117, "grad_norm": 3.0896403789520264, "learning_rate": 5.744124375949549e-06, "loss": 0.1084, "step": 426640 }, { "epoch": 2.53609620105688, "grad_norm": 4.7916259765625, "learning_rate": 5.743919193903338e-06, "loss": 0.147, "step": 426650 }, { "epoch": 2.5361556431335486, "grad_norm": 4.8135085105896, "learning_rate": 5.743714010576009e-06, "loss": 0.1299, "step": 426660 }, { "epoch": 2.536215085210217, "grad_norm": 4.023975372314453, "learning_rate": 5.7435088259679175e-06, "loss": 0.1438, "step": 426670 }, { "epoch": 2.5362745272868854, "grad_norm": 6.6073198318481445, "learning_rate": 5.743303640079414e-06, "loss": 0.1371, "step": 426680 }, { "epoch": 2.536333969363554, "grad_norm": 4.736799240112305, "learning_rate": 5.7430984529108535e-06, "loss": 0.1341, "step": 426690 }, { "epoch": 2.5363934114402222, "grad_norm": 4.7551116943359375, "learning_rate": 5.742893264462589e-06, "loss": 0.1321, "step": 426700 }, { "epoch": 2.5364528535168906, "grad_norm": 4.894139289855957, "learning_rate": 5.742688074734974e-06, "loss": 0.1355, "step": 426710 }, { "epoch": 2.5365122955935586, "grad_norm": 5.226573944091797, "learning_rate": 5.74248288372836e-06, "loss": 0.1254, "step": 426720 }, { "epoch": 2.5365717376702275, "grad_norm": 3.210350751876831, "learning_rate": 5.742277691443102e-06, "loss": 0.1216, "step": 426730 }, { "epoch": 2.5366311797468954, "grad_norm": 4.155989170074463, "learning_rate": 5.742072497879555e-06, "loss": 0.1287, "step": 426740 }, { "epoch": 2.536690621823564, "grad_norm": 3.1761362552642822, "learning_rate": 5.741867303038069e-06, "loss": 0.1234, "step": 426750 }, { "epoch": 2.5367500639002323, "grad_norm": 4.330911159515381, "learning_rate": 5.7416621069189985e-06, "loss": 0.1237, "step": 426760 }, { "epoch": 2.5368095059769007, "grad_norm": 4.394715785980225, "learning_rate": 5.741456909522699e-06, "loss": 0.129, "step": 426770 }, { "epoch": 2.536868948053569, "grad_norm": 4.6407976150512695, "learning_rate": 5.741251710849521e-06, "loss": 0.1277, "step": 426780 }, { "epoch": 2.5369283901302375, "grad_norm": 4.797828197479248, "learning_rate": 5.741046510899819e-06, "loss": 0.1374, "step": 426790 }, { "epoch": 2.536987832206906, "grad_norm": 3.4354500770568848, "learning_rate": 5.740841309673948e-06, "loss": 0.1473, "step": 426800 }, { "epoch": 2.5370472742835743, "grad_norm": 4.152107238769531, "learning_rate": 5.740636107172258e-06, "loss": 0.1227, "step": 426810 }, { "epoch": 2.5371067163602428, "grad_norm": 4.122386932373047, "learning_rate": 5.740430903395106e-06, "loss": 0.1287, "step": 426820 }, { "epoch": 2.537166158436911, "grad_norm": 3.9315714836120605, "learning_rate": 5.740225698342844e-06, "loss": 0.1352, "step": 426830 }, { "epoch": 2.5372256005135796, "grad_norm": 4.568610191345215, "learning_rate": 5.740020492015825e-06, "loss": 0.1662, "step": 426840 }, { "epoch": 2.537285042590248, "grad_norm": 4.563724040985107, "learning_rate": 5.7398152844143995e-06, "loss": 0.136, "step": 426850 }, { "epoch": 2.5373444846669164, "grad_norm": 3.8186888694763184, "learning_rate": 5.739610075538926e-06, "loss": 0.1398, "step": 426860 }, { "epoch": 2.537403926743585, "grad_norm": 4.285510540008545, "learning_rate": 5.739404865389755e-06, "loss": 0.1388, "step": 426870 }, { "epoch": 2.5374633688202533, "grad_norm": 5.604804039001465, "learning_rate": 5.73919965396724e-06, "loss": 0.1441, "step": 426880 }, { "epoch": 2.537522810896921, "grad_norm": 4.459117889404297, "learning_rate": 5.738994441271737e-06, "loss": 0.1447, "step": 426890 }, { "epoch": 2.53758225297359, "grad_norm": 4.183463096618652, "learning_rate": 5.738789227303596e-06, "loss": 0.1251, "step": 426900 }, { "epoch": 2.537641695050258, "grad_norm": 3.5146379470825195, "learning_rate": 5.738584012063172e-06, "loss": 0.1218, "step": 426910 }, { "epoch": 2.537701137126927, "grad_norm": 3.207237720489502, "learning_rate": 5.738378795550818e-06, "loss": 0.1113, "step": 426920 }, { "epoch": 2.537760579203595, "grad_norm": 4.041303634643555, "learning_rate": 5.738173577766889e-06, "loss": 0.1385, "step": 426930 }, { "epoch": 2.5378200212802633, "grad_norm": 3.522116184234619, "learning_rate": 5.737968358711735e-06, "loss": 0.1285, "step": 426940 }, { "epoch": 2.5378794633569317, "grad_norm": 5.066063404083252, "learning_rate": 5.737763138385714e-06, "loss": 0.1394, "step": 426950 }, { "epoch": 2.5379389054336, "grad_norm": 4.053779602050781, "learning_rate": 5.737557916789175e-06, "loss": 0.1379, "step": 426960 }, { "epoch": 2.5379983475102685, "grad_norm": 4.175118923187256, "learning_rate": 5.737352693922474e-06, "loss": 0.127, "step": 426970 }, { "epoch": 2.538057789586937, "grad_norm": 4.778088092803955, "learning_rate": 5.737147469785962e-06, "loss": 0.1363, "step": 426980 }, { "epoch": 2.5381172316636054, "grad_norm": 4.217972755432129, "learning_rate": 5.736942244379995e-06, "loss": 0.1363, "step": 426990 }, { "epoch": 2.538176673740274, "grad_norm": 4.188737392425537, "learning_rate": 5.736737017704927e-06, "loss": 0.1536, "step": 427000 }, { "epoch": 2.538236115816942, "grad_norm": 5.156895637512207, "learning_rate": 5.736531789761108e-06, "loss": 0.1426, "step": 427010 }, { "epoch": 2.5382955578936106, "grad_norm": 4.430455207824707, "learning_rate": 5.7363265605488945e-06, "loss": 0.133, "step": 427020 }, { "epoch": 2.538354999970279, "grad_norm": 5.905179500579834, "learning_rate": 5.736121330068639e-06, "loss": 0.1306, "step": 427030 }, { "epoch": 2.5384144420469474, "grad_norm": 3.945819854736328, "learning_rate": 5.735916098320693e-06, "loss": 0.1477, "step": 427040 }, { "epoch": 2.538473884123616, "grad_norm": 5.398479461669922, "learning_rate": 5.735710865305414e-06, "loss": 0.1344, "step": 427050 }, { "epoch": 2.5385333262002843, "grad_norm": 2.673461675643921, "learning_rate": 5.735505631023153e-06, "loss": 0.1321, "step": 427060 }, { "epoch": 2.5385927682769527, "grad_norm": 3.9123120307922363, "learning_rate": 5.735300395474261e-06, "loss": 0.1411, "step": 427070 }, { "epoch": 2.5386522103536207, "grad_norm": 2.9546620845794678, "learning_rate": 5.735095158659097e-06, "loss": 0.1293, "step": 427080 }, { "epoch": 2.5387116524302895, "grad_norm": 4.788215160369873, "learning_rate": 5.734889920578008e-06, "loss": 0.1422, "step": 427090 }, { "epoch": 2.5387710945069575, "grad_norm": 4.833617687225342, "learning_rate": 5.734684681231354e-06, "loss": 0.1315, "step": 427100 }, { "epoch": 2.5388305365836263, "grad_norm": 3.368609666824341, "learning_rate": 5.7344794406194825e-06, "loss": 0.1314, "step": 427110 }, { "epoch": 2.5388899786602943, "grad_norm": 3.3469300270080566, "learning_rate": 5.734274198742753e-06, "loss": 0.111, "step": 427120 }, { "epoch": 2.5389494207369627, "grad_norm": 4.550344467163086, "learning_rate": 5.734068955601514e-06, "loss": 0.1184, "step": 427130 }, { "epoch": 2.539008862813631, "grad_norm": 4.719962120056152, "learning_rate": 5.733863711196121e-06, "loss": 0.152, "step": 427140 }, { "epoch": 2.5390683048902996, "grad_norm": 4.736756801605225, "learning_rate": 5.733658465526927e-06, "loss": 0.131, "step": 427150 }, { "epoch": 2.539127746966968, "grad_norm": 4.172445774078369, "learning_rate": 5.733453218594286e-06, "loss": 0.1215, "step": 427160 }, { "epoch": 2.5391871890436364, "grad_norm": 3.5728418827056885, "learning_rate": 5.73324797039855e-06, "loss": 0.1296, "step": 427170 }, { "epoch": 2.539246631120305, "grad_norm": 4.812557220458984, "learning_rate": 5.733042720940074e-06, "loss": 0.1394, "step": 427180 }, { "epoch": 2.539306073196973, "grad_norm": 4.797845363616943, "learning_rate": 5.7328374702192114e-06, "loss": 0.1335, "step": 427190 }, { "epoch": 2.5393655152736416, "grad_norm": 6.554946422576904, "learning_rate": 5.7326322182363135e-06, "loss": 0.1294, "step": 427200 }, { "epoch": 2.53942495735031, "grad_norm": 4.821689128875732, "learning_rate": 5.732426964991738e-06, "loss": 0.1532, "step": 427210 }, { "epoch": 2.5394843994269785, "grad_norm": 3.6954071521759033, "learning_rate": 5.7322217104858345e-06, "loss": 0.135, "step": 427220 }, { "epoch": 2.539543841503647, "grad_norm": 4.6478271484375, "learning_rate": 5.732016454718958e-06, "loss": 0.1418, "step": 427230 }, { "epoch": 2.5396032835803153, "grad_norm": 6.351283550262451, "learning_rate": 5.7318111976914616e-06, "loss": 0.1518, "step": 427240 }, { "epoch": 2.5396627256569837, "grad_norm": 4.969747543334961, "learning_rate": 5.731605939403699e-06, "loss": 0.1397, "step": 427250 }, { "epoch": 2.539722167733652, "grad_norm": 3.975670337677002, "learning_rate": 5.731400679856025e-06, "loss": 0.1347, "step": 427260 }, { "epoch": 2.53978160981032, "grad_norm": 3.9436800479888916, "learning_rate": 5.73119541904879e-06, "loss": 0.1262, "step": 427270 }, { "epoch": 2.539841051886989, "grad_norm": 3.304288387298584, "learning_rate": 5.73099015698235e-06, "loss": 0.1472, "step": 427280 }, { "epoch": 2.539900493963657, "grad_norm": 3.440476417541504, "learning_rate": 5.730784893657059e-06, "loss": 0.1396, "step": 427290 }, { "epoch": 2.5399599360403258, "grad_norm": 4.761610984802246, "learning_rate": 5.730579629073267e-06, "loss": 0.1401, "step": 427300 }, { "epoch": 2.5400193781169937, "grad_norm": 5.7417449951171875, "learning_rate": 5.73037436323133e-06, "loss": 0.1261, "step": 427310 }, { "epoch": 2.540078820193662, "grad_norm": 3.736673355102539, "learning_rate": 5.730169096131602e-06, "loss": 0.1406, "step": 427320 }, { "epoch": 2.5401382622703306, "grad_norm": 4.852705001831055, "learning_rate": 5.729963827774437e-06, "loss": 0.1356, "step": 427330 }, { "epoch": 2.540197704346999, "grad_norm": 3.8162693977355957, "learning_rate": 5.7297585581601845e-06, "loss": 0.1156, "step": 427340 }, { "epoch": 2.5402571464236674, "grad_norm": 3.280574083328247, "learning_rate": 5.729553287289202e-06, "loss": 0.1272, "step": 427350 }, { "epoch": 2.540316588500336, "grad_norm": 4.566014766693115, "learning_rate": 5.729348015161842e-06, "loss": 0.1269, "step": 427360 }, { "epoch": 2.5403760305770042, "grad_norm": 6.078998565673828, "learning_rate": 5.729142741778457e-06, "loss": 0.1216, "step": 427370 }, { "epoch": 2.5404354726536726, "grad_norm": 3.4978580474853516, "learning_rate": 5.728937467139401e-06, "loss": 0.1101, "step": 427380 }, { "epoch": 2.540494914730341, "grad_norm": 4.383800983428955, "learning_rate": 5.728732191245029e-06, "loss": 0.1169, "step": 427390 }, { "epoch": 2.5405543568070095, "grad_norm": 3.974097490310669, "learning_rate": 5.728526914095692e-06, "loss": 0.1261, "step": 427400 }, { "epoch": 2.540613798883678, "grad_norm": 5.057514667510986, "learning_rate": 5.728321635691746e-06, "loss": 0.1285, "step": 427410 }, { "epoch": 2.5406732409603463, "grad_norm": 3.864169120788574, "learning_rate": 5.7281163560335415e-06, "loss": 0.1208, "step": 427420 }, { "epoch": 2.5407326830370147, "grad_norm": 4.811700820922852, "learning_rate": 5.727911075121434e-06, "loss": 0.1367, "step": 427430 }, { "epoch": 2.540792125113683, "grad_norm": 4.175167083740234, "learning_rate": 5.727705792955778e-06, "loss": 0.1229, "step": 427440 }, { "epoch": 2.5408515671903515, "grad_norm": 3.2481911182403564, "learning_rate": 5.7275005095369256e-06, "loss": 0.1309, "step": 427450 }, { "epoch": 2.5409110092670195, "grad_norm": 5.524938583374023, "learning_rate": 5.727295224865229e-06, "loss": 0.1473, "step": 427460 }, { "epoch": 2.5409704513436884, "grad_norm": 3.590824842453003, "learning_rate": 5.7270899389410455e-06, "loss": 0.1423, "step": 427470 }, { "epoch": 2.5410298934203563, "grad_norm": 3.2526350021362305, "learning_rate": 5.7268846517647256e-06, "loss": 0.1503, "step": 427480 }, { "epoch": 2.5410893354970248, "grad_norm": 3.4607346057891846, "learning_rate": 5.726679363336622e-06, "loss": 0.1323, "step": 427490 }, { "epoch": 2.541148777573693, "grad_norm": 4.3337721824646, "learning_rate": 5.726474073657091e-06, "loss": 0.149, "step": 427500 }, { "epoch": 2.5412082196503616, "grad_norm": 4.66554594039917, "learning_rate": 5.726268782726486e-06, "loss": 0.1154, "step": 427510 }, { "epoch": 2.54126766172703, "grad_norm": 4.336235523223877, "learning_rate": 5.726063490545159e-06, "loss": 0.1485, "step": 427520 }, { "epoch": 2.5413271038036984, "grad_norm": 6.61737585067749, "learning_rate": 5.725858197113462e-06, "loss": 0.1341, "step": 427530 }, { "epoch": 2.541386545880367, "grad_norm": 4.022999286651611, "learning_rate": 5.725652902431753e-06, "loss": 0.1523, "step": 427540 }, { "epoch": 2.5414459879570352, "grad_norm": 3.6040048599243164, "learning_rate": 5.7254476065003826e-06, "loss": 0.1242, "step": 427550 }, { "epoch": 2.5415054300337037, "grad_norm": 5.222046375274658, "learning_rate": 5.725242309319704e-06, "loss": 0.1477, "step": 427560 }, { "epoch": 2.541564872110372, "grad_norm": 4.6597161293029785, "learning_rate": 5.725037010890072e-06, "loss": 0.1283, "step": 427570 }, { "epoch": 2.5416243141870405, "grad_norm": 4.680283546447754, "learning_rate": 5.72483171121184e-06, "loss": 0.1251, "step": 427580 }, { "epoch": 2.541683756263709, "grad_norm": 3.4811792373657227, "learning_rate": 5.724626410285361e-06, "loss": 0.1259, "step": 427590 }, { "epoch": 2.5417431983403773, "grad_norm": 4.444858551025391, "learning_rate": 5.724421108110989e-06, "loss": 0.1227, "step": 427600 }, { "epoch": 2.5418026404170457, "grad_norm": 3.4044322967529297, "learning_rate": 5.724215804689079e-06, "loss": 0.1252, "step": 427610 }, { "epoch": 2.541862082493714, "grad_norm": 4.337608337402344, "learning_rate": 5.724010500019981e-06, "loss": 0.136, "step": 427620 }, { "epoch": 2.541921524570382, "grad_norm": 3.7747864723205566, "learning_rate": 5.7238051941040505e-06, "loss": 0.1389, "step": 427630 }, { "epoch": 2.541980966647051, "grad_norm": 4.239852428436279, "learning_rate": 5.723599886941641e-06, "loss": 0.1352, "step": 427640 }, { "epoch": 2.542040408723719, "grad_norm": 4.3486785888671875, "learning_rate": 5.723394578533108e-06, "loss": 0.1342, "step": 427650 }, { "epoch": 2.542099850800388, "grad_norm": 6.403343200683594, "learning_rate": 5.7231892688788e-06, "loss": 0.1552, "step": 427660 }, { "epoch": 2.5421592928770558, "grad_norm": 4.264227390289307, "learning_rate": 5.722983957979077e-06, "loss": 0.1256, "step": 427670 }, { "epoch": 2.542218734953724, "grad_norm": 5.180405139923096, "learning_rate": 5.7227786458342885e-06, "loss": 0.138, "step": 427680 }, { "epoch": 2.5422781770303926, "grad_norm": 3.106173276901245, "learning_rate": 5.7225733324447875e-06, "loss": 0.1419, "step": 427690 }, { "epoch": 2.542337619107061, "grad_norm": 4.29403018951416, "learning_rate": 5.722368017810931e-06, "loss": 0.1259, "step": 427700 }, { "epoch": 2.5423970611837294, "grad_norm": 4.095868110656738, "learning_rate": 5.72216270193307e-06, "loss": 0.1349, "step": 427710 }, { "epoch": 2.542456503260398, "grad_norm": 3.9885354042053223, "learning_rate": 5.7219573848115575e-06, "loss": 0.125, "step": 427720 }, { "epoch": 2.5425159453370663, "grad_norm": 4.38189697265625, "learning_rate": 5.721752066446749e-06, "loss": 0.1203, "step": 427730 }, { "epoch": 2.5425753874137347, "grad_norm": 3.100618600845337, "learning_rate": 5.721546746838998e-06, "loss": 0.1362, "step": 427740 }, { "epoch": 2.542634829490403, "grad_norm": 4.219550132751465, "learning_rate": 5.7213414259886564e-06, "loss": 0.1413, "step": 427750 }, { "epoch": 2.5426942715670715, "grad_norm": 4.074190139770508, "learning_rate": 5.721136103896079e-06, "loss": 0.1487, "step": 427760 }, { "epoch": 2.54275371364374, "grad_norm": 4.866973876953125, "learning_rate": 5.72093078056162e-06, "loss": 0.1225, "step": 427770 }, { "epoch": 2.5428131557204083, "grad_norm": 4.730501174926758, "learning_rate": 5.720725455985632e-06, "loss": 0.1473, "step": 427780 }, { "epoch": 2.5428725977970768, "grad_norm": 4.128056049346924, "learning_rate": 5.720520130168467e-06, "loss": 0.1356, "step": 427790 }, { "epoch": 2.542932039873745, "grad_norm": 4.72649621963501, "learning_rate": 5.720314803110482e-06, "loss": 0.1277, "step": 427800 }, { "epoch": 2.5429914819504136, "grad_norm": 5.071310997009277, "learning_rate": 5.720109474812029e-06, "loss": 0.1232, "step": 427810 }, { "epoch": 2.5430509240270815, "grad_norm": 4.747589111328125, "learning_rate": 5.7199041452734605e-06, "loss": 0.1346, "step": 427820 }, { "epoch": 2.5431103661037504, "grad_norm": 5.4277873039245605, "learning_rate": 5.719698814495133e-06, "loss": 0.1274, "step": 427830 }, { "epoch": 2.5431698081804184, "grad_norm": 5.397796630859375, "learning_rate": 5.719493482477397e-06, "loss": 0.1323, "step": 427840 }, { "epoch": 2.5432292502570872, "grad_norm": 3.162445068359375, "learning_rate": 5.719288149220607e-06, "loss": 0.1302, "step": 427850 }, { "epoch": 2.543288692333755, "grad_norm": 3.571357488632202, "learning_rate": 5.719082814725117e-06, "loss": 0.1291, "step": 427860 }, { "epoch": 2.5433481344104236, "grad_norm": 5.266498565673828, "learning_rate": 5.71887747899128e-06, "loss": 0.1443, "step": 427870 }, { "epoch": 2.543407576487092, "grad_norm": 3.284898519515991, "learning_rate": 5.718672142019452e-06, "loss": 0.1182, "step": 427880 }, { "epoch": 2.5434670185637605, "grad_norm": 3.9089691638946533, "learning_rate": 5.718466803809984e-06, "loss": 0.1529, "step": 427890 }, { "epoch": 2.543526460640429, "grad_norm": 5.7091546058654785, "learning_rate": 5.7182614643632305e-06, "loss": 0.1281, "step": 427900 }, { "epoch": 2.5435859027170973, "grad_norm": 4.158483028411865, "learning_rate": 5.718056123679546e-06, "loss": 0.1452, "step": 427910 }, { "epoch": 2.5436453447937657, "grad_norm": 4.02257776260376, "learning_rate": 5.717850781759282e-06, "loss": 0.1372, "step": 427920 }, { "epoch": 2.543704786870434, "grad_norm": 4.69411563873291, "learning_rate": 5.7176454386027935e-06, "loss": 0.141, "step": 427930 }, { "epoch": 2.5437642289471025, "grad_norm": 4.2753825187683105, "learning_rate": 5.717440094210435e-06, "loss": 0.1356, "step": 427940 }, { "epoch": 2.543823671023771, "grad_norm": 4.767613410949707, "learning_rate": 5.717234748582557e-06, "loss": 0.1371, "step": 427950 }, { "epoch": 2.5438831131004394, "grad_norm": 3.736293315887451, "learning_rate": 5.717029401719517e-06, "loss": 0.1189, "step": 427960 }, { "epoch": 2.5439425551771078, "grad_norm": 5.238807678222656, "learning_rate": 5.716824053621665e-06, "loss": 0.1244, "step": 427970 }, { "epoch": 2.544001997253776, "grad_norm": 4.573859691619873, "learning_rate": 5.716618704289358e-06, "loss": 0.133, "step": 427980 }, { "epoch": 2.5440614393304446, "grad_norm": 3.4566233158111572, "learning_rate": 5.716413353722947e-06, "loss": 0.1316, "step": 427990 }, { "epoch": 2.544120881407113, "grad_norm": 3.9977121353149414, "learning_rate": 5.7162080019227875e-06, "loss": 0.1206, "step": 428000 }, { "epoch": 2.544180323483781, "grad_norm": 4.598130702972412, "learning_rate": 5.716002648889233e-06, "loss": 0.1265, "step": 428010 }, { "epoch": 2.54423976556045, "grad_norm": 4.5432257652282715, "learning_rate": 5.7157972946226346e-06, "loss": 0.1322, "step": 428020 }, { "epoch": 2.544299207637118, "grad_norm": 4.3570780754089355, "learning_rate": 5.71559193912335e-06, "loss": 0.1289, "step": 428030 }, { "epoch": 2.5443586497137867, "grad_norm": 4.547272682189941, "learning_rate": 5.71538658239173e-06, "loss": 0.1414, "step": 428040 }, { "epoch": 2.5444180917904546, "grad_norm": 3.061117172241211, "learning_rate": 5.715181224428128e-06, "loss": 0.1388, "step": 428050 }, { "epoch": 2.544477533867123, "grad_norm": 4.861693382263184, "learning_rate": 5.714975865232899e-06, "loss": 0.1193, "step": 428060 }, { "epoch": 2.5445369759437915, "grad_norm": 3.9017415046691895, "learning_rate": 5.714770504806397e-06, "loss": 0.15, "step": 428070 }, { "epoch": 2.54459641802046, "grad_norm": 3.4749648571014404, "learning_rate": 5.7145651431489725e-06, "loss": 0.131, "step": 428080 }, { "epoch": 2.5446558600971283, "grad_norm": 5.878370761871338, "learning_rate": 5.714359780260984e-06, "loss": 0.122, "step": 428090 }, { "epoch": 2.5447153021737967, "grad_norm": 4.605624675750732, "learning_rate": 5.714154416142782e-06, "loss": 0.1292, "step": 428100 }, { "epoch": 2.544774744250465, "grad_norm": 4.698093891143799, "learning_rate": 5.7139490507947205e-06, "loss": 0.134, "step": 428110 }, { "epoch": 2.5448341863271335, "grad_norm": 5.300337791442871, "learning_rate": 5.713743684217154e-06, "loss": 0.1285, "step": 428120 }, { "epoch": 2.544893628403802, "grad_norm": 4.673430442810059, "learning_rate": 5.713538316410437e-06, "loss": 0.1271, "step": 428130 }, { "epoch": 2.5449530704804704, "grad_norm": 5.181336402893066, "learning_rate": 5.71333294737492e-06, "loss": 0.1326, "step": 428140 }, { "epoch": 2.545012512557139, "grad_norm": 3.860788345336914, "learning_rate": 5.71312757711096e-06, "loss": 0.1198, "step": 428150 }, { "epoch": 2.545071954633807, "grad_norm": 3.9126362800598145, "learning_rate": 5.712922205618908e-06, "loss": 0.1269, "step": 428160 }, { "epoch": 2.5451313967104756, "grad_norm": 4.110113620758057, "learning_rate": 5.712716832899119e-06, "loss": 0.1422, "step": 428170 }, { "epoch": 2.545190838787144, "grad_norm": 3.0172531604766846, "learning_rate": 5.712511458951947e-06, "loss": 0.1302, "step": 428180 }, { "epoch": 2.5452502808638124, "grad_norm": 4.937376022338867, "learning_rate": 5.7123060837777445e-06, "loss": 0.1293, "step": 428190 }, { "epoch": 2.5453097229404804, "grad_norm": 4.763815879821777, "learning_rate": 5.712100707376868e-06, "loss": 0.113, "step": 428200 }, { "epoch": 2.5453691650171493, "grad_norm": 3.4570860862731934, "learning_rate": 5.711895329749666e-06, "loss": 0.1256, "step": 428210 }, { "epoch": 2.5454286070938172, "grad_norm": 5.034935474395752, "learning_rate": 5.711689950896497e-06, "loss": 0.1558, "step": 428220 }, { "epoch": 2.5454880491704857, "grad_norm": 4.916110992431641, "learning_rate": 5.711484570817714e-06, "loss": 0.1201, "step": 428230 }, { "epoch": 2.545547491247154, "grad_norm": 3.8105974197387695, "learning_rate": 5.7112791895136675e-06, "loss": 0.1326, "step": 428240 }, { "epoch": 2.5456069333238225, "grad_norm": 4.3307061195373535, "learning_rate": 5.711073806984716e-06, "loss": 0.1342, "step": 428250 }, { "epoch": 2.545666375400491, "grad_norm": 3.6306278705596924, "learning_rate": 5.71086842323121e-06, "loss": 0.1245, "step": 428260 }, { "epoch": 2.5457258174771593, "grad_norm": 3.908024311065674, "learning_rate": 5.710663038253501e-06, "loss": 0.1455, "step": 428270 }, { "epoch": 2.5457852595538277, "grad_norm": 4.524080753326416, "learning_rate": 5.7104576520519484e-06, "loss": 0.1276, "step": 428280 }, { "epoch": 2.545844701630496, "grad_norm": 3.7581114768981934, "learning_rate": 5.7102522646269025e-06, "loss": 0.1281, "step": 428290 }, { "epoch": 2.5459041437071646, "grad_norm": 4.382614612579346, "learning_rate": 5.7100468759787155e-06, "loss": 0.1362, "step": 428300 }, { "epoch": 2.545963585783833, "grad_norm": 3.8889987468719482, "learning_rate": 5.709841486107743e-06, "loss": 0.1223, "step": 428310 }, { "epoch": 2.5460230278605014, "grad_norm": 5.208288669586182, "learning_rate": 5.709636095014342e-06, "loss": 0.1201, "step": 428320 }, { "epoch": 2.54608246993717, "grad_norm": 4.028200626373291, "learning_rate": 5.70943070269886e-06, "loss": 0.1257, "step": 428330 }, { "epoch": 2.546141912013838, "grad_norm": 3.9450395107269287, "learning_rate": 5.709225309161654e-06, "loss": 0.1437, "step": 428340 }, { "epoch": 2.5462013540905066, "grad_norm": 3.9815871715545654, "learning_rate": 5.70901991440308e-06, "loss": 0.1215, "step": 428350 }, { "epoch": 2.546260796167175, "grad_norm": 5.329697132110596, "learning_rate": 5.708814518423487e-06, "loss": 0.1305, "step": 428360 }, { "epoch": 2.546320238243843, "grad_norm": 3.5668256282806396, "learning_rate": 5.708609121223231e-06, "loss": 0.1346, "step": 428370 }, { "epoch": 2.546379680320512, "grad_norm": 4.847788333892822, "learning_rate": 5.708403722802665e-06, "loss": 0.1213, "step": 428380 }, { "epoch": 2.54643912239718, "grad_norm": 4.0430192947387695, "learning_rate": 5.708198323162145e-06, "loss": 0.1425, "step": 428390 }, { "epoch": 2.5464985644738487, "grad_norm": 3.6909663677215576, "learning_rate": 5.707992922302021e-06, "loss": 0.1352, "step": 428400 }, { "epoch": 2.5465580065505167, "grad_norm": 3.4171459674835205, "learning_rate": 5.70778752022265e-06, "loss": 0.119, "step": 428410 }, { "epoch": 2.546617448627185, "grad_norm": 4.346114158630371, "learning_rate": 5.707582116924384e-06, "loss": 0.125, "step": 428420 }, { "epoch": 2.5466768907038535, "grad_norm": 3.6757090091705322, "learning_rate": 5.707376712407577e-06, "loss": 0.1485, "step": 428430 }, { "epoch": 2.546736332780522, "grad_norm": 3.8883135318756104, "learning_rate": 5.707171306672583e-06, "loss": 0.1259, "step": 428440 }, { "epoch": 2.5467957748571903, "grad_norm": 3.6136090755462646, "learning_rate": 5.706965899719757e-06, "loss": 0.129, "step": 428450 }, { "epoch": 2.5468552169338587, "grad_norm": 5.120695114135742, "learning_rate": 5.706760491549449e-06, "loss": 0.1508, "step": 428460 }, { "epoch": 2.546914659010527, "grad_norm": 4.569153785705566, "learning_rate": 5.706555082162016e-06, "loss": 0.1286, "step": 428470 }, { "epoch": 2.5469741010871956, "grad_norm": 3.332681894302368, "learning_rate": 5.706349671557811e-06, "loss": 0.1443, "step": 428480 }, { "epoch": 2.547033543163864, "grad_norm": 4.254669189453125, "learning_rate": 5.706144259737189e-06, "loss": 0.1429, "step": 428490 }, { "epoch": 2.5470929852405324, "grad_norm": 2.9402575492858887, "learning_rate": 5.705938846700499e-06, "loss": 0.1327, "step": 428500 }, { "epoch": 2.547152427317201, "grad_norm": 6.150468349456787, "learning_rate": 5.705733432448102e-06, "loss": 0.1248, "step": 428510 }, { "epoch": 2.5472118693938692, "grad_norm": 3.7098147869110107, "learning_rate": 5.705528016980344e-06, "loss": 0.1213, "step": 428520 }, { "epoch": 2.5472713114705376, "grad_norm": 4.638759613037109, "learning_rate": 5.705322600297585e-06, "loss": 0.1279, "step": 428530 }, { "epoch": 2.547330753547206, "grad_norm": 4.761119842529297, "learning_rate": 5.705117182400175e-06, "loss": 0.126, "step": 428540 }, { "epoch": 2.5473901956238745, "grad_norm": 4.428593158721924, "learning_rate": 5.704911763288471e-06, "loss": 0.1255, "step": 428550 }, { "epoch": 2.5474496377005424, "grad_norm": 4.633194923400879, "learning_rate": 5.704706342962823e-06, "loss": 0.128, "step": 428560 }, { "epoch": 2.5475090797772113, "grad_norm": 4.416794776916504, "learning_rate": 5.704500921423588e-06, "loss": 0.1123, "step": 428570 }, { "epoch": 2.5475685218538793, "grad_norm": 3.181715250015259, "learning_rate": 5.704295498671117e-06, "loss": 0.1161, "step": 428580 }, { "epoch": 2.547627963930548, "grad_norm": 3.7342886924743652, "learning_rate": 5.704090074705767e-06, "loss": 0.1172, "step": 428590 }, { "epoch": 2.547687406007216, "grad_norm": 4.837623596191406, "learning_rate": 5.703884649527887e-06, "loss": 0.1254, "step": 428600 }, { "epoch": 2.5477468480838845, "grad_norm": 3.8421409130096436, "learning_rate": 5.703679223137837e-06, "loss": 0.1256, "step": 428610 }, { "epoch": 2.547806290160553, "grad_norm": 3.435666799545288, "learning_rate": 5.703473795535966e-06, "loss": 0.1481, "step": 428620 }, { "epoch": 2.5478657322372213, "grad_norm": 4.048201084136963, "learning_rate": 5.703268366722627e-06, "loss": 0.1356, "step": 428630 }, { "epoch": 2.5479251743138898, "grad_norm": 3.0349080562591553, "learning_rate": 5.703062936698179e-06, "loss": 0.1241, "step": 428640 }, { "epoch": 2.547984616390558, "grad_norm": 2.997101068496704, "learning_rate": 5.702857505462971e-06, "loss": 0.1245, "step": 428650 }, { "epoch": 2.5480440584672266, "grad_norm": 3.9956655502319336, "learning_rate": 5.70265207301736e-06, "loss": 0.1229, "step": 428660 }, { "epoch": 2.548103500543895, "grad_norm": 3.467884063720703, "learning_rate": 5.702446639361696e-06, "loss": 0.1371, "step": 428670 }, { "epoch": 2.5481629426205634, "grad_norm": 2.8753864765167236, "learning_rate": 5.702241204496337e-06, "loss": 0.1332, "step": 428680 }, { "epoch": 2.548222384697232, "grad_norm": 4.596390724182129, "learning_rate": 5.702035768421634e-06, "loss": 0.1093, "step": 428690 }, { "epoch": 2.5482818267739002, "grad_norm": 4.955887794494629, "learning_rate": 5.701830331137942e-06, "loss": 0.1317, "step": 428700 }, { "epoch": 2.5483412688505687, "grad_norm": 6.377718448638916, "learning_rate": 5.701624892645614e-06, "loss": 0.1477, "step": 428710 }, { "epoch": 2.548400710927237, "grad_norm": 5.3223347663879395, "learning_rate": 5.701419452945005e-06, "loss": 0.134, "step": 428720 }, { "epoch": 2.5484601530039055, "grad_norm": 4.630298614501953, "learning_rate": 5.7012140120364675e-06, "loss": 0.1315, "step": 428730 }, { "epoch": 2.548519595080574, "grad_norm": 4.980646133422852, "learning_rate": 5.701008569920356e-06, "loss": 0.1193, "step": 428740 }, { "epoch": 2.548579037157242, "grad_norm": 4.6627421379089355, "learning_rate": 5.700803126597023e-06, "loss": 0.1077, "step": 428750 }, { "epoch": 2.5486384792339107, "grad_norm": 3.840449810028076, "learning_rate": 5.700597682066824e-06, "loss": 0.1354, "step": 428760 }, { "epoch": 2.5486979213105787, "grad_norm": 4.891523361206055, "learning_rate": 5.700392236330113e-06, "loss": 0.1246, "step": 428770 }, { "epoch": 2.5487573633872476, "grad_norm": 3.8730528354644775, "learning_rate": 5.7001867893872435e-06, "loss": 0.1207, "step": 428780 }, { "epoch": 2.5488168054639155, "grad_norm": 3.9022302627563477, "learning_rate": 5.699981341238567e-06, "loss": 0.1317, "step": 428790 }, { "epoch": 2.548876247540584, "grad_norm": 4.760786533355713, "learning_rate": 5.69977589188444e-06, "loss": 0.1286, "step": 428800 }, { "epoch": 2.5489356896172524, "grad_norm": 3.2473626136779785, "learning_rate": 5.699570441325216e-06, "loss": 0.13, "step": 428810 }, { "epoch": 2.548995131693921, "grad_norm": 3.5719387531280518, "learning_rate": 5.699364989561248e-06, "loss": 0.1219, "step": 428820 }, { "epoch": 2.549054573770589, "grad_norm": 5.444092273712158, "learning_rate": 5.69915953659289e-06, "loss": 0.1279, "step": 428830 }, { "epoch": 2.5491140158472576, "grad_norm": 4.3139214515686035, "learning_rate": 5.698954082420496e-06, "loss": 0.1185, "step": 428840 }, { "epoch": 2.549173457923926, "grad_norm": 2.719052791595459, "learning_rate": 5.698748627044418e-06, "loss": 0.124, "step": 428850 }, { "epoch": 2.5492329000005944, "grad_norm": 4.4473185539245605, "learning_rate": 5.698543170465012e-06, "loss": 0.1407, "step": 428860 }, { "epoch": 2.549292342077263, "grad_norm": 3.478583335876465, "learning_rate": 5.698337712682634e-06, "loss": 0.1321, "step": 428870 }, { "epoch": 2.5493517841539313, "grad_norm": 2.8354909420013428, "learning_rate": 5.698132253697632e-06, "loss": 0.1367, "step": 428880 }, { "epoch": 2.5494112262305997, "grad_norm": 3.6041321754455566, "learning_rate": 5.697926793510365e-06, "loss": 0.131, "step": 428890 }, { "epoch": 2.549470668307268, "grad_norm": 3.4831998348236084, "learning_rate": 5.697721332121183e-06, "loss": 0.1201, "step": 428900 }, { "epoch": 2.5495301103839365, "grad_norm": 4.254711151123047, "learning_rate": 5.697515869530443e-06, "loss": 0.1115, "step": 428910 }, { "epoch": 2.549589552460605, "grad_norm": 4.691204071044922, "learning_rate": 5.697310405738497e-06, "loss": 0.1443, "step": 428920 }, { "epoch": 2.5496489945372733, "grad_norm": 4.031793117523193, "learning_rate": 5.697104940745699e-06, "loss": 0.1269, "step": 428930 }, { "epoch": 2.5497084366139413, "grad_norm": 2.6716485023498535, "learning_rate": 5.6968994745524044e-06, "loss": 0.1274, "step": 428940 }, { "epoch": 2.54976787869061, "grad_norm": 4.637323379516602, "learning_rate": 5.6966940071589635e-06, "loss": 0.1249, "step": 428950 }, { "epoch": 2.549827320767278, "grad_norm": 3.4944417476654053, "learning_rate": 5.6964885385657335e-06, "loss": 0.1366, "step": 428960 }, { "epoch": 2.5498867628439466, "grad_norm": 5.034521579742432, "learning_rate": 5.6962830687730675e-06, "loss": 0.1354, "step": 428970 }, { "epoch": 2.549946204920615, "grad_norm": 4.987149238586426, "learning_rate": 5.696077597781319e-06, "loss": 0.1427, "step": 428980 }, { "epoch": 2.5500056469972834, "grad_norm": 4.061624526977539, "learning_rate": 5.69587212559084e-06, "loss": 0.1259, "step": 428990 }, { "epoch": 2.550065089073952, "grad_norm": 8.130064010620117, "learning_rate": 5.695666652201989e-06, "loss": 0.1377, "step": 429000 }, { "epoch": 2.55012453115062, "grad_norm": 4.2331366539001465, "learning_rate": 5.695461177615116e-06, "loss": 0.1412, "step": 429010 }, { "epoch": 2.5501839732272886, "grad_norm": 3.0551772117614746, "learning_rate": 5.6952557018305756e-06, "loss": 0.1191, "step": 429020 }, { "epoch": 2.550243415303957, "grad_norm": 3.7218732833862305, "learning_rate": 5.695050224848722e-06, "loss": 0.137, "step": 429030 }, { "epoch": 2.5503028573806255, "grad_norm": 6.393449783325195, "learning_rate": 5.694844746669909e-06, "loss": 0.1244, "step": 429040 }, { "epoch": 2.550362299457294, "grad_norm": 3.141420364379883, "learning_rate": 5.6946392672944895e-06, "loss": 0.129, "step": 429050 }, { "epoch": 2.5504217415339623, "grad_norm": 4.875090599060059, "learning_rate": 5.694433786722819e-06, "loss": 0.1187, "step": 429060 }, { "epoch": 2.5504811836106307, "grad_norm": 4.646444320678711, "learning_rate": 5.6942283049552505e-06, "loss": 0.1431, "step": 429070 }, { "epoch": 2.550540625687299, "grad_norm": 5.178183078765869, "learning_rate": 5.694022821992139e-06, "loss": 0.1408, "step": 429080 }, { "epoch": 2.5506000677639675, "grad_norm": 4.594488620758057, "learning_rate": 5.6938173378338354e-06, "loss": 0.1245, "step": 429090 }, { "epoch": 2.550659509840636, "grad_norm": 3.846384048461914, "learning_rate": 5.693611852480698e-06, "loss": 0.1195, "step": 429100 }, { "epoch": 2.550718951917304, "grad_norm": 4.1730875968933105, "learning_rate": 5.693406365933078e-06, "loss": 0.1243, "step": 429110 }, { "epoch": 2.5507783939939728, "grad_norm": 4.221201419830322, "learning_rate": 5.693200878191327e-06, "loss": 0.1336, "step": 429120 }, { "epoch": 2.5508378360706407, "grad_norm": 4.132716655731201, "learning_rate": 5.6929953892558044e-06, "loss": 0.1314, "step": 429130 }, { "epoch": 2.5508972781473096, "grad_norm": 4.939320087432861, "learning_rate": 5.692789899126859e-06, "loss": 0.1416, "step": 429140 }, { "epoch": 2.5509567202239776, "grad_norm": 3.6198415756225586, "learning_rate": 5.6925844078048475e-06, "loss": 0.1299, "step": 429150 }, { "epoch": 2.551016162300646, "grad_norm": 4.147778034210205, "learning_rate": 5.692378915290123e-06, "loss": 0.1351, "step": 429160 }, { "epoch": 2.5510756043773144, "grad_norm": 5.162196636199951, "learning_rate": 5.69217342158304e-06, "loss": 0.1291, "step": 429170 }, { "epoch": 2.551135046453983, "grad_norm": 3.0311129093170166, "learning_rate": 5.69196792668395e-06, "loss": 0.1325, "step": 429180 }, { "epoch": 2.5511944885306512, "grad_norm": 3.181994915008545, "learning_rate": 5.69176243059321e-06, "loss": 0.1337, "step": 429190 }, { "epoch": 2.5512539306073196, "grad_norm": 4.694454669952393, "learning_rate": 5.691556933311172e-06, "loss": 0.1266, "step": 429200 }, { "epoch": 2.551313372683988, "grad_norm": 4.901909351348877, "learning_rate": 5.691351434838192e-06, "loss": 0.1279, "step": 429210 }, { "epoch": 2.5513728147606565, "grad_norm": 7.900114059448242, "learning_rate": 5.69114593517462e-06, "loss": 0.1534, "step": 429220 }, { "epoch": 2.551432256837325, "grad_norm": 4.245265483856201, "learning_rate": 5.690940434320813e-06, "loss": 0.1356, "step": 429230 }, { "epoch": 2.5514916989139933, "grad_norm": 4.694063663482666, "learning_rate": 5.690734932277125e-06, "loss": 0.1417, "step": 429240 }, { "epoch": 2.5515511409906617, "grad_norm": 4.523625373840332, "learning_rate": 5.6905294290439075e-06, "loss": 0.1199, "step": 429250 }, { "epoch": 2.55161058306733, "grad_norm": 4.489651679992676, "learning_rate": 5.690323924621518e-06, "loss": 0.1415, "step": 429260 }, { "epoch": 2.5516700251439985, "grad_norm": 4.439248085021973, "learning_rate": 5.6901184190103075e-06, "loss": 0.1295, "step": 429270 }, { "epoch": 2.551729467220667, "grad_norm": 5.410783767700195, "learning_rate": 5.68991291221063e-06, "loss": 0.1381, "step": 429280 }, { "epoch": 2.5517889092973354, "grad_norm": 4.338199138641357, "learning_rate": 5.689707404222839e-06, "loss": 0.1375, "step": 429290 }, { "epoch": 2.5518483513740033, "grad_norm": 4.576562404632568, "learning_rate": 5.6895018950472925e-06, "loss": 0.1364, "step": 429300 }, { "epoch": 2.551907793450672, "grad_norm": 5.5923967361450195, "learning_rate": 5.689296384684339e-06, "loss": 0.1425, "step": 429310 }, { "epoch": 2.55196723552734, "grad_norm": 4.284045219421387, "learning_rate": 5.689090873134337e-06, "loss": 0.1227, "step": 429320 }, { "epoch": 2.552026677604009, "grad_norm": 4.462606430053711, "learning_rate": 5.688885360397637e-06, "loss": 0.142, "step": 429330 }, { "epoch": 2.552086119680677, "grad_norm": 5.1092023849487305, "learning_rate": 5.688679846474595e-06, "loss": 0.1432, "step": 429340 }, { "epoch": 2.5521455617573454, "grad_norm": 3.7478554248809814, "learning_rate": 5.688474331365563e-06, "loss": 0.1499, "step": 429350 }, { "epoch": 2.552205003834014, "grad_norm": 4.465016841888428, "learning_rate": 5.688268815070898e-06, "loss": 0.1558, "step": 429360 }, { "epoch": 2.5522644459106822, "grad_norm": 3.4111592769622803, "learning_rate": 5.68806329759095e-06, "loss": 0.1342, "step": 429370 }, { "epoch": 2.5523238879873507, "grad_norm": 5.210294246673584, "learning_rate": 5.687857778926076e-06, "loss": 0.1294, "step": 429380 }, { "epoch": 2.552383330064019, "grad_norm": 4.654959201812744, "learning_rate": 5.687652259076628e-06, "loss": 0.1346, "step": 429390 }, { "epoch": 2.5524427721406875, "grad_norm": 5.008784770965576, "learning_rate": 5.687446738042961e-06, "loss": 0.1185, "step": 429400 }, { "epoch": 2.552502214217356, "grad_norm": 4.365078449249268, "learning_rate": 5.687241215825427e-06, "loss": 0.1374, "step": 429410 }, { "epoch": 2.5525616562940243, "grad_norm": 5.972799301147461, "learning_rate": 5.687035692424385e-06, "loss": 0.1449, "step": 429420 }, { "epoch": 2.5526210983706927, "grad_norm": 2.736737012863159, "learning_rate": 5.686830167840184e-06, "loss": 0.1231, "step": 429430 }, { "epoch": 2.552680540447361, "grad_norm": 4.508039951324463, "learning_rate": 5.6866246420731795e-06, "loss": 0.1444, "step": 429440 }, { "epoch": 2.5527399825240296, "grad_norm": 5.119098663330078, "learning_rate": 5.6864191151237256e-06, "loss": 0.1254, "step": 429450 }, { "epoch": 2.552799424600698, "grad_norm": 4.403590679168701, "learning_rate": 5.686213586992176e-06, "loss": 0.1264, "step": 429460 }, { "epoch": 2.5528588666773664, "grad_norm": 3.4814438819885254, "learning_rate": 5.686008057678884e-06, "loss": 0.1282, "step": 429470 }, { "epoch": 2.552918308754035, "grad_norm": 5.037406921386719, "learning_rate": 5.685802527184205e-06, "loss": 0.1376, "step": 429480 }, { "epoch": 2.5529777508307028, "grad_norm": 3.415039300918579, "learning_rate": 5.685596995508493e-06, "loss": 0.1381, "step": 429490 }, { "epoch": 2.5530371929073716, "grad_norm": 3.703282594680786, "learning_rate": 5.6853914626521e-06, "loss": 0.1147, "step": 429500 }, { "epoch": 2.5530966349840396, "grad_norm": 5.715158939361572, "learning_rate": 5.685185928615381e-06, "loss": 0.1299, "step": 429510 }, { "epoch": 2.5531560770607085, "grad_norm": 5.846882343292236, "learning_rate": 5.684980393398692e-06, "loss": 0.1163, "step": 429520 }, { "epoch": 2.5532155191373764, "grad_norm": 4.357556343078613, "learning_rate": 5.6847748570023835e-06, "loss": 0.1205, "step": 429530 }, { "epoch": 2.553274961214045, "grad_norm": 2.9765474796295166, "learning_rate": 5.684569319426809e-06, "loss": 0.138, "step": 429540 }, { "epoch": 2.5533344032907133, "grad_norm": 3.1586170196533203, "learning_rate": 5.684363780672329e-06, "loss": 0.1229, "step": 429550 }, { "epoch": 2.5533938453673817, "grad_norm": 4.816232204437256, "learning_rate": 5.684158240739289e-06, "loss": 0.1297, "step": 429560 }, { "epoch": 2.55345328744405, "grad_norm": 5.07641077041626, "learning_rate": 5.683952699628048e-06, "loss": 0.1165, "step": 429570 }, { "epoch": 2.5535127295207185, "grad_norm": 4.727410793304443, "learning_rate": 5.68374715733896e-06, "loss": 0.1295, "step": 429580 }, { "epoch": 2.553572171597387, "grad_norm": 3.06868839263916, "learning_rate": 5.683541613872378e-06, "loss": 0.127, "step": 429590 }, { "epoch": 2.5536316136740553, "grad_norm": 5.193872928619385, "learning_rate": 5.683336069228653e-06, "loss": 0.1469, "step": 429600 }, { "epoch": 2.5536910557507237, "grad_norm": 3.259521245956421, "learning_rate": 5.683130523408144e-06, "loss": 0.1046, "step": 429610 }, { "epoch": 2.553750497827392, "grad_norm": 4.090785503387451, "learning_rate": 5.682924976411202e-06, "loss": 0.1525, "step": 429620 }, { "epoch": 2.5538099399040606, "grad_norm": 3.6201069355010986, "learning_rate": 5.682719428238183e-06, "loss": 0.1314, "step": 429630 }, { "epoch": 2.553869381980729, "grad_norm": 4.086658954620361, "learning_rate": 5.682513878889437e-06, "loss": 0.1134, "step": 429640 }, { "epoch": 2.5539288240573974, "grad_norm": 4.67548131942749, "learning_rate": 5.682308328365322e-06, "loss": 0.1338, "step": 429650 }, { "epoch": 2.553988266134066, "grad_norm": 3.8417208194732666, "learning_rate": 5.6821027766661915e-06, "loss": 0.1158, "step": 429660 }, { "epoch": 2.5540477082107342, "grad_norm": 5.149138927459717, "learning_rate": 5.681897223792399e-06, "loss": 0.1199, "step": 429670 }, { "epoch": 2.554107150287402, "grad_norm": 4.934545993804932, "learning_rate": 5.681691669744297e-06, "loss": 0.1215, "step": 429680 }, { "epoch": 2.554166592364071, "grad_norm": 4.9210309982299805, "learning_rate": 5.681486114522241e-06, "loss": 0.1248, "step": 429690 }, { "epoch": 2.554226034440739, "grad_norm": 4.245359420776367, "learning_rate": 5.681280558126584e-06, "loss": 0.1169, "step": 429700 }, { "epoch": 2.5542854765174074, "grad_norm": 4.797509670257568, "learning_rate": 5.681075000557681e-06, "loss": 0.15, "step": 429710 }, { "epoch": 2.554344918594076, "grad_norm": 3.790461540222168, "learning_rate": 5.680869441815886e-06, "loss": 0.127, "step": 429720 }, { "epoch": 2.5544043606707443, "grad_norm": 4.047729969024658, "learning_rate": 5.680663881901552e-06, "loss": 0.1516, "step": 429730 }, { "epoch": 2.5544638027474127, "grad_norm": 3.8759982585906982, "learning_rate": 5.680458320815033e-06, "loss": 0.1464, "step": 429740 }, { "epoch": 2.554523244824081, "grad_norm": 4.855630397796631, "learning_rate": 5.680252758556685e-06, "loss": 0.1465, "step": 429750 }, { "epoch": 2.5545826869007495, "grad_norm": 6.0679168701171875, "learning_rate": 5.68004719512686e-06, "loss": 0.1387, "step": 429760 }, { "epoch": 2.554642128977418, "grad_norm": 4.720613479614258, "learning_rate": 5.679841630525912e-06, "loss": 0.1268, "step": 429770 }, { "epoch": 2.5547015710540864, "grad_norm": 4.083984851837158, "learning_rate": 5.679636064754196e-06, "loss": 0.1327, "step": 429780 }, { "epoch": 2.5547610131307548, "grad_norm": 4.709156036376953, "learning_rate": 5.679430497812066e-06, "loss": 0.1335, "step": 429790 }, { "epoch": 2.554820455207423, "grad_norm": 4.632808208465576, "learning_rate": 5.679224929699874e-06, "loss": 0.1345, "step": 429800 }, { "epoch": 2.5548798972840916, "grad_norm": 5.416300296783447, "learning_rate": 5.679019360417979e-06, "loss": 0.1329, "step": 429810 }, { "epoch": 2.55493933936076, "grad_norm": 5.8692402839660645, "learning_rate": 5.678813789966729e-06, "loss": 0.1566, "step": 429820 }, { "epoch": 2.5549987814374284, "grad_norm": 3.875316619873047, "learning_rate": 5.678608218346481e-06, "loss": 0.1149, "step": 429830 }, { "epoch": 2.555058223514097, "grad_norm": 6.622607231140137, "learning_rate": 5.678402645557588e-06, "loss": 0.1451, "step": 429840 }, { "epoch": 2.555117665590765, "grad_norm": 3.033898115158081, "learning_rate": 5.678197071600407e-06, "loss": 0.1142, "step": 429850 }, { "epoch": 2.5551771076674337, "grad_norm": 5.618076324462891, "learning_rate": 5.677991496475288e-06, "loss": 0.1363, "step": 429860 }, { "epoch": 2.5552365497441016, "grad_norm": 3.0990207195281982, "learning_rate": 5.677785920182585e-06, "loss": 0.1441, "step": 429870 }, { "epoch": 2.5552959918207705, "grad_norm": 4.586081027984619, "learning_rate": 5.677580342722657e-06, "loss": 0.132, "step": 429880 }, { "epoch": 2.5553554338974385, "grad_norm": 3.3952765464782715, "learning_rate": 5.677374764095854e-06, "loss": 0.121, "step": 429890 }, { "epoch": 2.555414875974107, "grad_norm": 3.5558130741119385, "learning_rate": 5.67716918430253e-06, "loss": 0.1219, "step": 429900 }, { "epoch": 2.5554743180507753, "grad_norm": 4.429919719696045, "learning_rate": 5.676963603343041e-06, "loss": 0.1368, "step": 429910 }, { "epoch": 2.5555337601274437, "grad_norm": 3.671085834503174, "learning_rate": 5.67675802121774e-06, "loss": 0.1324, "step": 429920 }, { "epoch": 2.555593202204112, "grad_norm": 4.373539447784424, "learning_rate": 5.676552437926979e-06, "loss": 0.1262, "step": 429930 }, { "epoch": 2.5556526442807805, "grad_norm": 3.2619805335998535, "learning_rate": 5.676346853471116e-06, "loss": 0.1213, "step": 429940 }, { "epoch": 2.555712086357449, "grad_norm": 4.644970893859863, "learning_rate": 5.676141267850501e-06, "loss": 0.1287, "step": 429950 }, { "epoch": 2.5557715284341174, "grad_norm": 5.030240535736084, "learning_rate": 5.675935681065491e-06, "loss": 0.1313, "step": 429960 }, { "epoch": 2.555830970510786, "grad_norm": 4.846199035644531, "learning_rate": 5.6757300931164394e-06, "loss": 0.1401, "step": 429970 }, { "epoch": 2.555890412587454, "grad_norm": 3.0993850231170654, "learning_rate": 5.675524504003701e-06, "loss": 0.1259, "step": 429980 }, { "epoch": 2.5559498546641226, "grad_norm": 4.138189792633057, "learning_rate": 5.6753189137276276e-06, "loss": 0.141, "step": 429990 }, { "epoch": 2.556009296740791, "grad_norm": 3.4439544677734375, "learning_rate": 5.675113322288575e-06, "loss": 0.1318, "step": 430000 }, { "epoch": 2.5560687388174594, "grad_norm": 3.252180337905884, "learning_rate": 5.674907729686896e-06, "loss": 0.135, "step": 430010 }, { "epoch": 2.556128180894128, "grad_norm": 4.353753566741943, "learning_rate": 5.674702135922946e-06, "loss": 0.1326, "step": 430020 }, { "epoch": 2.5561876229707963, "grad_norm": 5.157242298126221, "learning_rate": 5.674496540997077e-06, "loss": 0.1309, "step": 430030 }, { "epoch": 2.5562470650474642, "grad_norm": 3.2627718448638916, "learning_rate": 5.674290944909646e-06, "loss": 0.1462, "step": 430040 }, { "epoch": 2.556306507124133, "grad_norm": 3.160912036895752, "learning_rate": 5.674085347661006e-06, "loss": 0.1132, "step": 430050 }, { "epoch": 2.556365949200801, "grad_norm": 5.021510124206543, "learning_rate": 5.673879749251507e-06, "loss": 0.1305, "step": 430060 }, { "epoch": 2.55642539127747, "grad_norm": 5.782437324523926, "learning_rate": 5.6736741496815106e-06, "loss": 0.1195, "step": 430070 }, { "epoch": 2.556484833354138, "grad_norm": 4.756617069244385, "learning_rate": 5.673468548951365e-06, "loss": 0.1343, "step": 430080 }, { "epoch": 2.5565442754308063, "grad_norm": 3.054224729537964, "learning_rate": 5.673262947061427e-06, "loss": 0.1179, "step": 430090 }, { "epoch": 2.5566037175074747, "grad_norm": 4.9667863845825195, "learning_rate": 5.673057344012049e-06, "loss": 0.1274, "step": 430100 }, { "epoch": 2.556663159584143, "grad_norm": 5.234697341918945, "learning_rate": 5.6728517398035885e-06, "loss": 0.15, "step": 430110 }, { "epoch": 2.5567226016608116, "grad_norm": 3.6385843753814697, "learning_rate": 5.6726461344363935e-06, "loss": 0.1518, "step": 430120 }, { "epoch": 2.55678204373748, "grad_norm": 5.0018744468688965, "learning_rate": 5.672440527910824e-06, "loss": 0.1496, "step": 430130 }, { "epoch": 2.5568414858141484, "grad_norm": 4.130731582641602, "learning_rate": 5.672234920227232e-06, "loss": 0.1388, "step": 430140 }, { "epoch": 2.556900927890817, "grad_norm": 3.735874652862549, "learning_rate": 5.672029311385969e-06, "loss": 0.1419, "step": 430150 }, { "epoch": 2.556960369967485, "grad_norm": 4.148534774780273, "learning_rate": 5.671823701387393e-06, "loss": 0.1339, "step": 430160 }, { "epoch": 2.5570198120441536, "grad_norm": 4.277891635894775, "learning_rate": 5.671618090231855e-06, "loss": 0.13, "step": 430170 }, { "epoch": 2.557079254120822, "grad_norm": 5.203065872192383, "learning_rate": 5.6714124779197125e-06, "loss": 0.1391, "step": 430180 }, { "epoch": 2.5571386961974905, "grad_norm": 3.7272884845733643, "learning_rate": 5.6712068644513164e-06, "loss": 0.1443, "step": 430190 }, { "epoch": 2.557198138274159, "grad_norm": 4.08543586730957, "learning_rate": 5.671001249827022e-06, "loss": 0.153, "step": 430200 }, { "epoch": 2.5572575803508273, "grad_norm": 4.065603733062744, "learning_rate": 5.670795634047184e-06, "loss": 0.1455, "step": 430210 }, { "epoch": 2.5573170224274957, "grad_norm": 3.7742815017700195, "learning_rate": 5.670590017112156e-06, "loss": 0.1312, "step": 430220 }, { "epoch": 2.5573764645041637, "grad_norm": 4.075835704803467, "learning_rate": 5.67038439902229e-06, "loss": 0.144, "step": 430230 }, { "epoch": 2.5574359065808325, "grad_norm": 4.753871440887451, "learning_rate": 5.670178779777945e-06, "loss": 0.1467, "step": 430240 }, { "epoch": 2.5574953486575005, "grad_norm": 4.064786911010742, "learning_rate": 5.6699731593794696e-06, "loss": 0.1356, "step": 430250 }, { "epoch": 2.5575547907341694, "grad_norm": 4.717976093292236, "learning_rate": 5.669767537827222e-06, "loss": 0.1363, "step": 430260 }, { "epoch": 2.5576142328108373, "grad_norm": 5.3075079917907715, "learning_rate": 5.669561915121555e-06, "loss": 0.1374, "step": 430270 }, { "epoch": 2.5576736748875057, "grad_norm": 4.084413051605225, "learning_rate": 5.669356291262821e-06, "loss": 0.1278, "step": 430280 }, { "epoch": 2.557733116964174, "grad_norm": 3.5664327144622803, "learning_rate": 5.669150666251376e-06, "loss": 0.1385, "step": 430290 }, { "epoch": 2.5577925590408426, "grad_norm": 3.692866086959839, "learning_rate": 5.668945040087575e-06, "loss": 0.1406, "step": 430300 }, { "epoch": 2.557852001117511, "grad_norm": 4.728426933288574, "learning_rate": 5.66873941277177e-06, "loss": 0.1195, "step": 430310 }, { "epoch": 2.5579114431941794, "grad_norm": 5.154942512512207, "learning_rate": 5.668533784304315e-06, "loss": 0.1164, "step": 430320 }, { "epoch": 2.557970885270848, "grad_norm": 4.035182476043701, "learning_rate": 5.668328154685566e-06, "loss": 0.1382, "step": 430330 }, { "epoch": 2.5580303273475162, "grad_norm": 3.426870346069336, "learning_rate": 5.668122523915878e-06, "loss": 0.1549, "step": 430340 }, { "epoch": 2.5580897694241846, "grad_norm": 5.887280464172363, "learning_rate": 5.6679168919956e-06, "loss": 0.1383, "step": 430350 }, { "epoch": 2.558149211500853, "grad_norm": 4.035801410675049, "learning_rate": 5.667711258925091e-06, "loss": 0.1222, "step": 430360 }, { "epoch": 2.5582086535775215, "grad_norm": 4.0877203941345215, "learning_rate": 5.667505624704705e-06, "loss": 0.1315, "step": 430370 }, { "epoch": 2.55826809565419, "grad_norm": 3.67838716506958, "learning_rate": 5.667299989334791e-06, "loss": 0.115, "step": 430380 }, { "epoch": 2.5583275377308583, "grad_norm": 4.003759384155273, "learning_rate": 5.667094352815708e-06, "loss": 0.1221, "step": 430390 }, { "epoch": 2.5583869798075267, "grad_norm": 4.243391513824463, "learning_rate": 5.666888715147811e-06, "loss": 0.1357, "step": 430400 }, { "epoch": 2.558446421884195, "grad_norm": 3.416168451309204, "learning_rate": 5.666683076331452e-06, "loss": 0.1294, "step": 430410 }, { "epoch": 2.558505863960863, "grad_norm": 4.875685214996338, "learning_rate": 5.666477436366983e-06, "loss": 0.1468, "step": 430420 }, { "epoch": 2.558565306037532, "grad_norm": 4.652069568634033, "learning_rate": 5.666271795254761e-06, "loss": 0.1315, "step": 430430 }, { "epoch": 2.5586247481142, "grad_norm": 4.28640079498291, "learning_rate": 5.666066152995141e-06, "loss": 0.1358, "step": 430440 }, { "epoch": 2.5586841901908683, "grad_norm": 3.879852056503296, "learning_rate": 5.665860509588474e-06, "loss": 0.1234, "step": 430450 }, { "epoch": 2.5587436322675368, "grad_norm": 4.983221530914307, "learning_rate": 5.665654865035116e-06, "loss": 0.1363, "step": 430460 }, { "epoch": 2.558803074344205, "grad_norm": 5.089194297790527, "learning_rate": 5.665449219335422e-06, "loss": 0.1237, "step": 430470 }, { "epoch": 2.5588625164208736, "grad_norm": 3.022878885269165, "learning_rate": 5.665243572489742e-06, "loss": 0.1034, "step": 430480 }, { "epoch": 2.558921958497542, "grad_norm": 4.040665149688721, "learning_rate": 5.6650379244984364e-06, "loss": 0.1277, "step": 430490 }, { "epoch": 2.5589814005742104, "grad_norm": 6.1955742835998535, "learning_rate": 5.664832275361855e-06, "loss": 0.132, "step": 430500 }, { "epoch": 2.559040842650879, "grad_norm": 3.5187442302703857, "learning_rate": 5.664626625080354e-06, "loss": 0.1261, "step": 430510 }, { "epoch": 2.5591002847275472, "grad_norm": 4.58165979385376, "learning_rate": 5.664420973654285e-06, "loss": 0.1204, "step": 430520 }, { "epoch": 2.5591597268042157, "grad_norm": 5.88557243347168, "learning_rate": 5.664215321084004e-06, "loss": 0.1218, "step": 430530 }, { "epoch": 2.559219168880884, "grad_norm": 3.9539809226989746, "learning_rate": 5.664009667369866e-06, "loss": 0.1272, "step": 430540 }, { "epoch": 2.5592786109575525, "grad_norm": 5.608509540557861, "learning_rate": 5.663804012512224e-06, "loss": 0.1357, "step": 430550 }, { "epoch": 2.559338053034221, "grad_norm": 3.986984968185425, "learning_rate": 5.663598356511432e-06, "loss": 0.1279, "step": 430560 }, { "epoch": 2.5593974951108893, "grad_norm": 6.123462200164795, "learning_rate": 5.663392699367846e-06, "loss": 0.1335, "step": 430570 }, { "epoch": 2.5594569371875577, "grad_norm": 4.240397930145264, "learning_rate": 5.663187041081816e-06, "loss": 0.1292, "step": 430580 }, { "epoch": 2.5595163792642257, "grad_norm": 5.177427291870117, "learning_rate": 5.6629813816537e-06, "loss": 0.1278, "step": 430590 }, { "epoch": 2.5595758213408946, "grad_norm": 5.028004169464111, "learning_rate": 5.662775721083851e-06, "loss": 0.1221, "step": 430600 }, { "epoch": 2.5596352634175625, "grad_norm": 5.716043949127197, "learning_rate": 5.662570059372622e-06, "loss": 0.1246, "step": 430610 }, { "epoch": 2.5596947054942314, "grad_norm": 3.2284393310546875, "learning_rate": 5.662364396520369e-06, "loss": 0.1236, "step": 430620 }, { "epoch": 2.5597541475708994, "grad_norm": 2.802074432373047, "learning_rate": 5.662158732527446e-06, "loss": 0.1174, "step": 430630 }, { "epoch": 2.5598135896475678, "grad_norm": 5.422088146209717, "learning_rate": 5.661953067394207e-06, "loss": 0.1382, "step": 430640 }, { "epoch": 2.559873031724236, "grad_norm": 4.833362102508545, "learning_rate": 5.661747401121005e-06, "loss": 0.1312, "step": 430650 }, { "epoch": 2.5599324738009046, "grad_norm": 5.951923847198486, "learning_rate": 5.661541733708195e-06, "loss": 0.1288, "step": 430660 }, { "epoch": 2.559991915877573, "grad_norm": 3.3171780109405518, "learning_rate": 5.661336065156132e-06, "loss": 0.1287, "step": 430670 }, { "epoch": 2.5600513579542414, "grad_norm": 2.9369735717773438, "learning_rate": 5.661130395465169e-06, "loss": 0.1239, "step": 430680 }, { "epoch": 2.56011080003091, "grad_norm": 4.045560836791992, "learning_rate": 5.66092472463566e-06, "loss": 0.1457, "step": 430690 }, { "epoch": 2.5601702421075783, "grad_norm": 3.299992322921753, "learning_rate": 5.660719052667961e-06, "loss": 0.1343, "step": 430700 }, { "epoch": 2.5602296841842467, "grad_norm": 5.886490821838379, "learning_rate": 5.660513379562424e-06, "loss": 0.1367, "step": 430710 }, { "epoch": 2.560289126260915, "grad_norm": 6.319385528564453, "learning_rate": 5.6603077053194036e-06, "loss": 0.1313, "step": 430720 }, { "epoch": 2.5603485683375835, "grad_norm": 4.000094413757324, "learning_rate": 5.660102029939255e-06, "loss": 0.132, "step": 430730 }, { "epoch": 2.560408010414252, "grad_norm": 4.383962631225586, "learning_rate": 5.659896353422332e-06, "loss": 0.1422, "step": 430740 }, { "epoch": 2.5604674524909203, "grad_norm": 4.240017414093018, "learning_rate": 5.6596906757689885e-06, "loss": 0.1215, "step": 430750 }, { "epoch": 2.5605268945675888, "grad_norm": 2.915421962738037, "learning_rate": 5.659484996979579e-06, "loss": 0.1379, "step": 430760 }, { "epoch": 2.560586336644257, "grad_norm": 4.543438911437988, "learning_rate": 5.659279317054458e-06, "loss": 0.1402, "step": 430770 }, { "epoch": 2.560645778720925, "grad_norm": 2.8992972373962402, "learning_rate": 5.65907363599398e-06, "loss": 0.1212, "step": 430780 }, { "epoch": 2.560705220797594, "grad_norm": 4.67785120010376, "learning_rate": 5.658867953798498e-06, "loss": 0.1173, "step": 430790 }, { "epoch": 2.560764662874262, "grad_norm": 4.4767045974731445, "learning_rate": 5.658662270468367e-06, "loss": 0.1118, "step": 430800 }, { "epoch": 2.560824104950931, "grad_norm": 3.413470506668091, "learning_rate": 5.658456586003941e-06, "loss": 0.121, "step": 430810 }, { "epoch": 2.560883547027599, "grad_norm": 3.2796037197113037, "learning_rate": 5.6582509004055745e-06, "loss": 0.1228, "step": 430820 }, { "epoch": 2.560942989104267, "grad_norm": 5.550848960876465, "learning_rate": 5.658045213673619e-06, "loss": 0.1307, "step": 430830 }, { "epoch": 2.5610024311809356, "grad_norm": 3.54262113571167, "learning_rate": 5.657839525808433e-06, "loss": 0.1309, "step": 430840 }, { "epoch": 2.561061873257604, "grad_norm": 4.213610649108887, "learning_rate": 5.657633836810369e-06, "loss": 0.1215, "step": 430850 }, { "epoch": 2.5611213153342725, "grad_norm": 2.552701473236084, "learning_rate": 5.657428146679781e-06, "loss": 0.1326, "step": 430860 }, { "epoch": 2.561180757410941, "grad_norm": 2.8964335918426514, "learning_rate": 5.657222455417022e-06, "loss": 0.122, "step": 430870 }, { "epoch": 2.5612401994876093, "grad_norm": 4.043159484863281, "learning_rate": 5.657016763022449e-06, "loss": 0.1255, "step": 430880 }, { "epoch": 2.5612996415642777, "grad_norm": 3.5182180404663086, "learning_rate": 5.6568110694964155e-06, "loss": 0.13, "step": 430890 }, { "epoch": 2.561359083640946, "grad_norm": 4.162075042724609, "learning_rate": 5.656605374839272e-06, "loss": 0.1288, "step": 430900 }, { "epoch": 2.5614185257176145, "grad_norm": 3.616365909576416, "learning_rate": 5.6563996790513784e-06, "loss": 0.1336, "step": 430910 }, { "epoch": 2.561477967794283, "grad_norm": 3.644300937652588, "learning_rate": 5.6561939821330855e-06, "loss": 0.1468, "step": 430920 }, { "epoch": 2.5615374098709514, "grad_norm": 3.77065110206604, "learning_rate": 5.655988284084748e-06, "loss": 0.1324, "step": 430930 }, { "epoch": 2.5615968519476198, "grad_norm": 3.7353522777557373, "learning_rate": 5.65578258490672e-06, "loss": 0.1446, "step": 430940 }, { "epoch": 2.561656294024288, "grad_norm": 3.3213694095611572, "learning_rate": 5.655576884599356e-06, "loss": 0.1362, "step": 430950 }, { "epoch": 2.5617157361009566, "grad_norm": 5.032522201538086, "learning_rate": 5.655371183163012e-06, "loss": 0.1268, "step": 430960 }, { "epoch": 2.5617751781776246, "grad_norm": 3.829742908477783, "learning_rate": 5.65516548059804e-06, "loss": 0.1531, "step": 430970 }, { "epoch": 2.5618346202542934, "grad_norm": 6.131237983703613, "learning_rate": 5.654959776904794e-06, "loss": 0.1293, "step": 430980 }, { "epoch": 2.5618940623309614, "grad_norm": 5.989782333374023, "learning_rate": 5.65475407208363e-06, "loss": 0.1185, "step": 430990 }, { "epoch": 2.5619535044076303, "grad_norm": 5.2395100593566895, "learning_rate": 5.654548366134901e-06, "loss": 0.1309, "step": 431000 }, { "epoch": 2.5620129464842982, "grad_norm": 4.953671932220459, "learning_rate": 5.654342659058962e-06, "loss": 0.1521, "step": 431010 }, { "epoch": 2.5620723885609666, "grad_norm": 4.032419204711914, "learning_rate": 5.654136950856166e-06, "loss": 0.1193, "step": 431020 }, { "epoch": 2.562131830637635, "grad_norm": 4.92439079284668, "learning_rate": 5.653931241526868e-06, "loss": 0.1306, "step": 431030 }, { "epoch": 2.5621912727143035, "grad_norm": 3.937500476837158, "learning_rate": 5.653725531071424e-06, "loss": 0.1012, "step": 431040 }, { "epoch": 2.562250714790972, "grad_norm": 3.808964252471924, "learning_rate": 5.653519819490185e-06, "loss": 0.132, "step": 431050 }, { "epoch": 2.5623101568676403, "grad_norm": 4.109949111938477, "learning_rate": 5.653314106783507e-06, "loss": 0.1426, "step": 431060 }, { "epoch": 2.5623695989443087, "grad_norm": 4.570250511169434, "learning_rate": 5.653108392951745e-06, "loss": 0.1274, "step": 431070 }, { "epoch": 2.562429041020977, "grad_norm": 5.0650954246521, "learning_rate": 5.652902677995253e-06, "loss": 0.1442, "step": 431080 }, { "epoch": 2.5624884830976455, "grad_norm": 4.860372066497803, "learning_rate": 5.6526969619143835e-06, "loss": 0.1337, "step": 431090 }, { "epoch": 2.562547925174314, "grad_norm": 3.679818868637085, "learning_rate": 5.652491244709491e-06, "loss": 0.1268, "step": 431100 }, { "epoch": 2.5626073672509824, "grad_norm": 3.75134539604187, "learning_rate": 5.652285526380933e-06, "loss": 0.1114, "step": 431110 }, { "epoch": 2.562666809327651, "grad_norm": 3.5437543392181396, "learning_rate": 5.652079806929061e-06, "loss": 0.1402, "step": 431120 }, { "epoch": 2.562726251404319, "grad_norm": 3.02987003326416, "learning_rate": 5.651874086354229e-06, "loss": 0.1241, "step": 431130 }, { "epoch": 2.5627856934809876, "grad_norm": 3.9874985218048096, "learning_rate": 5.6516683646567915e-06, "loss": 0.1412, "step": 431140 }, { "epoch": 2.562845135557656, "grad_norm": 4.533322811126709, "learning_rate": 5.651462641837105e-06, "loss": 0.1289, "step": 431150 }, { "epoch": 2.562904577634324, "grad_norm": 3.5433897972106934, "learning_rate": 5.65125691789552e-06, "loss": 0.1376, "step": 431160 }, { "epoch": 2.562964019710993, "grad_norm": 4.360489845275879, "learning_rate": 5.6510511928323945e-06, "loss": 0.1375, "step": 431170 }, { "epoch": 2.563023461787661, "grad_norm": 5.009294033050537, "learning_rate": 5.650845466648081e-06, "loss": 0.1126, "step": 431180 }, { "epoch": 2.5630829038643292, "grad_norm": 3.9392571449279785, "learning_rate": 5.650639739342933e-06, "loss": 0.1348, "step": 431190 }, { "epoch": 2.5631423459409977, "grad_norm": 4.445783615112305, "learning_rate": 5.650434010917306e-06, "loss": 0.1282, "step": 431200 }, { "epoch": 2.563201788017666, "grad_norm": 3.3603503704071045, "learning_rate": 5.6502282813715545e-06, "loss": 0.1329, "step": 431210 }, { "epoch": 2.5632612300943345, "grad_norm": 3.8356986045837402, "learning_rate": 5.650022550706033e-06, "loss": 0.1301, "step": 431220 }, { "epoch": 2.563320672171003, "grad_norm": 4.155151844024658, "learning_rate": 5.6498168189210945e-06, "loss": 0.1292, "step": 431230 }, { "epoch": 2.5633801142476713, "grad_norm": 4.387441158294678, "learning_rate": 5.649611086017094e-06, "loss": 0.1248, "step": 431240 }, { "epoch": 2.5634395563243397, "grad_norm": 4.011617660522461, "learning_rate": 5.649405351994386e-06, "loss": 0.1078, "step": 431250 }, { "epoch": 2.563498998401008, "grad_norm": 4.64594841003418, "learning_rate": 5.6491996168533225e-06, "loss": 0.1312, "step": 431260 }, { "epoch": 2.5635584404776766, "grad_norm": 4.992101192474365, "learning_rate": 5.648993880594261e-06, "loss": 0.121, "step": 431270 }, { "epoch": 2.563617882554345, "grad_norm": 2.948863983154297, "learning_rate": 5.648788143217555e-06, "loss": 0.1282, "step": 431280 }, { "epoch": 2.5636773246310134, "grad_norm": 5.254537582397461, "learning_rate": 5.648582404723558e-06, "loss": 0.1137, "step": 431290 }, { "epoch": 2.563736766707682, "grad_norm": 4.251876354217529, "learning_rate": 5.648376665112625e-06, "loss": 0.1192, "step": 431300 }, { "epoch": 2.56379620878435, "grad_norm": 4.974514007568359, "learning_rate": 5.64817092438511e-06, "loss": 0.1296, "step": 431310 }, { "epoch": 2.5638556508610186, "grad_norm": 6.283409595489502, "learning_rate": 5.6479651825413685e-06, "loss": 0.1487, "step": 431320 }, { "epoch": 2.5639150929376866, "grad_norm": 4.407951831817627, "learning_rate": 5.647759439581752e-06, "loss": 0.1413, "step": 431330 }, { "epoch": 2.5639745350143555, "grad_norm": 3.771031379699707, "learning_rate": 5.6475536955066165e-06, "loss": 0.1331, "step": 431340 }, { "epoch": 2.5640339770910234, "grad_norm": 5.3376030921936035, "learning_rate": 5.6473479503163175e-06, "loss": 0.1318, "step": 431350 }, { "epoch": 2.5640934191676923, "grad_norm": 2.7989699840545654, "learning_rate": 5.647142204011207e-06, "loss": 0.1158, "step": 431360 }, { "epoch": 2.5641528612443603, "grad_norm": 4.587796688079834, "learning_rate": 5.646936456591641e-06, "loss": 0.1192, "step": 431370 }, { "epoch": 2.5642123033210287, "grad_norm": 4.347885608673096, "learning_rate": 5.646730708057972e-06, "loss": 0.1429, "step": 431380 }, { "epoch": 2.564271745397697, "grad_norm": 4.4978461265563965, "learning_rate": 5.646524958410555e-06, "loss": 0.1466, "step": 431390 }, { "epoch": 2.5643311874743655, "grad_norm": 4.347461223602295, "learning_rate": 5.6463192076497475e-06, "loss": 0.1302, "step": 431400 }, { "epoch": 2.564390629551034, "grad_norm": 2.9304466247558594, "learning_rate": 5.6461134557759e-06, "loss": 0.1474, "step": 431410 }, { "epoch": 2.5644500716277023, "grad_norm": 4.271335601806641, "learning_rate": 5.6459077027893684e-06, "loss": 0.1293, "step": 431420 }, { "epoch": 2.5645095137043707, "grad_norm": 4.3540754318237305, "learning_rate": 5.645701948690506e-06, "loss": 0.1386, "step": 431430 }, { "epoch": 2.564568955781039, "grad_norm": 4.3197736740112305, "learning_rate": 5.645496193479669e-06, "loss": 0.1444, "step": 431440 }, { "epoch": 2.5646283978577076, "grad_norm": 3.239307403564453, "learning_rate": 5.645290437157209e-06, "loss": 0.1496, "step": 431450 }, { "epoch": 2.564687839934376, "grad_norm": 4.664891719818115, "learning_rate": 5.6450846797234826e-06, "loss": 0.1199, "step": 431460 }, { "epoch": 2.5647472820110444, "grad_norm": 3.6665937900543213, "learning_rate": 5.644878921178844e-06, "loss": 0.1377, "step": 431470 }, { "epoch": 2.564806724087713, "grad_norm": 2.974365711212158, "learning_rate": 5.644673161523646e-06, "loss": 0.1304, "step": 431480 }, { "epoch": 2.5648661661643812, "grad_norm": 3.8683629035949707, "learning_rate": 5.644467400758244e-06, "loss": 0.1527, "step": 431490 }, { "epoch": 2.5649256082410496, "grad_norm": 4.9272027015686035, "learning_rate": 5.6442616388829915e-06, "loss": 0.1247, "step": 431500 }, { "epoch": 2.564985050317718, "grad_norm": 5.621737957000732, "learning_rate": 5.644055875898245e-06, "loss": 0.1347, "step": 431510 }, { "epoch": 2.565044492394386, "grad_norm": 3.7722229957580566, "learning_rate": 5.643850111804356e-06, "loss": 0.1317, "step": 431520 }, { "epoch": 2.565103934471055, "grad_norm": 3.605997085571289, "learning_rate": 5.6436443466016824e-06, "loss": 0.1288, "step": 431530 }, { "epoch": 2.565163376547723, "grad_norm": 3.138927459716797, "learning_rate": 5.643438580290575e-06, "loss": 0.1233, "step": 431540 }, { "epoch": 2.5652228186243917, "grad_norm": 3.5250120162963867, "learning_rate": 5.64323281287139e-06, "loss": 0.1281, "step": 431550 }, { "epoch": 2.5652822607010597, "grad_norm": 3.7978105545043945, "learning_rate": 5.643027044344483e-06, "loss": 0.1358, "step": 431560 }, { "epoch": 2.565341702777728, "grad_norm": 3.6871862411499023, "learning_rate": 5.642821274710204e-06, "loss": 0.1285, "step": 431570 }, { "epoch": 2.5654011448543965, "grad_norm": 3.216981887817383, "learning_rate": 5.64261550396891e-06, "loss": 0.1233, "step": 431580 }, { "epoch": 2.565460586931065, "grad_norm": 3.6714165210723877, "learning_rate": 5.642409732120957e-06, "loss": 0.1265, "step": 431590 }, { "epoch": 2.5655200290077333, "grad_norm": 5.931870460510254, "learning_rate": 5.6422039591666965e-06, "loss": 0.1487, "step": 431600 }, { "epoch": 2.5655794710844018, "grad_norm": 3.6790525913238525, "learning_rate": 5.641998185106486e-06, "loss": 0.1218, "step": 431610 }, { "epoch": 2.56563891316107, "grad_norm": 3.0202670097351074, "learning_rate": 5.6417924099406765e-06, "loss": 0.1536, "step": 431620 }, { "epoch": 2.5656983552377386, "grad_norm": 3.612999200820923, "learning_rate": 5.641586633669625e-06, "loss": 0.1258, "step": 431630 }, { "epoch": 2.565757797314407, "grad_norm": 4.359221458435059, "learning_rate": 5.641380856293683e-06, "loss": 0.1362, "step": 431640 }, { "epoch": 2.5658172393910754, "grad_norm": 3.9098105430603027, "learning_rate": 5.641175077813208e-06, "loss": 0.1179, "step": 431650 }, { "epoch": 2.565876681467744, "grad_norm": 3.9585819244384766, "learning_rate": 5.6409692982285524e-06, "loss": 0.1406, "step": 431660 }, { "epoch": 2.5659361235444123, "grad_norm": 4.60221004486084, "learning_rate": 5.640763517540072e-06, "loss": 0.1217, "step": 431670 }, { "epoch": 2.5659955656210807, "grad_norm": 3.736191511154175, "learning_rate": 5.64055773574812e-06, "loss": 0.1135, "step": 431680 }, { "epoch": 2.566055007697749, "grad_norm": 4.94210147857666, "learning_rate": 5.6403519528530516e-06, "loss": 0.1143, "step": 431690 }, { "epoch": 2.5661144497744175, "grad_norm": 3.90087890625, "learning_rate": 5.6401461688552206e-06, "loss": 0.1177, "step": 431700 }, { "epoch": 2.5661738918510855, "grad_norm": 4.27081298828125, "learning_rate": 5.63994038375498e-06, "loss": 0.1398, "step": 431710 }, { "epoch": 2.5662333339277543, "grad_norm": 2.706474542617798, "learning_rate": 5.639734597552686e-06, "loss": 0.1475, "step": 431720 }, { "epoch": 2.5662927760044223, "grad_norm": 4.882025718688965, "learning_rate": 5.639528810248693e-06, "loss": 0.13, "step": 431730 }, { "epoch": 2.566352218081091, "grad_norm": 3.2171831130981445, "learning_rate": 5.639323021843357e-06, "loss": 0.1524, "step": 431740 }, { "epoch": 2.566411660157759, "grad_norm": 3.7109792232513428, "learning_rate": 5.639117232337028e-06, "loss": 0.1393, "step": 431750 }, { "epoch": 2.5664711022344275, "grad_norm": 4.610624313354492, "learning_rate": 5.638911441730064e-06, "loss": 0.1488, "step": 431760 }, { "epoch": 2.566530544311096, "grad_norm": 3.5949625968933105, "learning_rate": 5.638705650022819e-06, "loss": 0.1161, "step": 431770 }, { "epoch": 2.5665899863877644, "grad_norm": 3.5786216259002686, "learning_rate": 5.6384998572156445e-06, "loss": 0.1144, "step": 431780 }, { "epoch": 2.566649428464433, "grad_norm": 2.876004219055176, "learning_rate": 5.6382940633089e-06, "loss": 0.1257, "step": 431790 }, { "epoch": 2.566708870541101, "grad_norm": 4.401449203491211, "learning_rate": 5.638088268302935e-06, "loss": 0.1313, "step": 431800 }, { "epoch": 2.5667683126177696, "grad_norm": 4.960287570953369, "learning_rate": 5.637882472198106e-06, "loss": 0.1255, "step": 431810 }, { "epoch": 2.566827754694438, "grad_norm": 3.8828608989715576, "learning_rate": 5.637676674994767e-06, "loss": 0.1328, "step": 431820 }, { "epoch": 2.5668871967711064, "grad_norm": 3.879089593887329, "learning_rate": 5.637470876693273e-06, "loss": 0.1298, "step": 431830 }, { "epoch": 2.566946638847775, "grad_norm": 5.398861408233643, "learning_rate": 5.6372650772939785e-06, "loss": 0.1427, "step": 431840 }, { "epoch": 2.5670060809244433, "grad_norm": 5.478392601013184, "learning_rate": 5.637059276797237e-06, "loss": 0.1441, "step": 431850 }, { "epoch": 2.5670655230011117, "grad_norm": 4.736297607421875, "learning_rate": 5.636853475203404e-06, "loss": 0.1354, "step": 431860 }, { "epoch": 2.56712496507778, "grad_norm": 5.255619049072266, "learning_rate": 5.636647672512834e-06, "loss": 0.1256, "step": 431870 }, { "epoch": 2.5671844071544485, "grad_norm": 3.8070335388183594, "learning_rate": 5.636441868725878e-06, "loss": 0.1359, "step": 431880 }, { "epoch": 2.567243849231117, "grad_norm": 4.901332855224609, "learning_rate": 5.636236063842896e-06, "loss": 0.1248, "step": 431890 }, { "epoch": 2.567303291307785, "grad_norm": 5.475710868835449, "learning_rate": 5.636030257864239e-06, "loss": 0.1465, "step": 431900 }, { "epoch": 2.5673627333844538, "grad_norm": 3.773057222366333, "learning_rate": 5.6358244507902604e-06, "loss": 0.1197, "step": 431910 }, { "epoch": 2.5674221754611217, "grad_norm": 4.018824577331543, "learning_rate": 5.635618642621318e-06, "loss": 0.1187, "step": 431920 }, { "epoch": 2.56748161753779, "grad_norm": 5.260154724121094, "learning_rate": 5.635412833357763e-06, "loss": 0.1443, "step": 431930 }, { "epoch": 2.5675410596144586, "grad_norm": 4.113763809204102, "learning_rate": 5.635207022999951e-06, "loss": 0.1341, "step": 431940 }, { "epoch": 2.567600501691127, "grad_norm": 3.437542676925659, "learning_rate": 5.635001211548239e-06, "loss": 0.1264, "step": 431950 }, { "epoch": 2.5676599437677954, "grad_norm": 2.840926170349121, "learning_rate": 5.634795399002978e-06, "loss": 0.1135, "step": 431960 }, { "epoch": 2.567719385844464, "grad_norm": 3.730287790298462, "learning_rate": 5.634589585364524e-06, "loss": 0.1135, "step": 431970 }, { "epoch": 2.567778827921132, "grad_norm": 4.705558776855469, "learning_rate": 5.634383770633229e-06, "loss": 0.1369, "step": 431980 }, { "epoch": 2.5678382699978006, "grad_norm": 4.7793192863464355, "learning_rate": 5.634177954809452e-06, "loss": 0.1364, "step": 431990 }, { "epoch": 2.567897712074469, "grad_norm": 3.969543218612671, "learning_rate": 5.633972137893544e-06, "loss": 0.119, "step": 432000 }, { "epoch": 2.5679571541511375, "grad_norm": 4.939060211181641, "learning_rate": 5.63376631988586e-06, "loss": 0.1342, "step": 432010 }, { "epoch": 2.568016596227806, "grad_norm": 4.412586212158203, "learning_rate": 5.633560500786755e-06, "loss": 0.13, "step": 432020 }, { "epoch": 2.5680760383044743, "grad_norm": 5.789025783538818, "learning_rate": 5.633354680596583e-06, "loss": 0.1223, "step": 432030 }, { "epoch": 2.5681354803811427, "grad_norm": 2.7699131965637207, "learning_rate": 5.633148859315698e-06, "loss": 0.1193, "step": 432040 }, { "epoch": 2.568194922457811, "grad_norm": 4.7352519035339355, "learning_rate": 5.632943036944456e-06, "loss": 0.1434, "step": 432050 }, { "epoch": 2.5682543645344795, "grad_norm": 3.919349193572998, "learning_rate": 5.632737213483212e-06, "loss": 0.114, "step": 432060 }, { "epoch": 2.5683138066111475, "grad_norm": 2.879607677459717, "learning_rate": 5.632531388932316e-06, "loss": 0.1204, "step": 432070 }, { "epoch": 2.5683732486878164, "grad_norm": 4.3454766273498535, "learning_rate": 5.632325563292127e-06, "loss": 0.1333, "step": 432080 }, { "epoch": 2.5684326907644843, "grad_norm": 3.360163688659668, "learning_rate": 5.6321197365629985e-06, "loss": 0.1294, "step": 432090 }, { "epoch": 2.568492132841153, "grad_norm": 3.2158191204071045, "learning_rate": 5.631913908745283e-06, "loss": 0.1221, "step": 432100 }, { "epoch": 2.568551574917821, "grad_norm": 4.672852516174316, "learning_rate": 5.631708079839338e-06, "loss": 0.1393, "step": 432110 }, { "epoch": 2.5686110169944896, "grad_norm": 4.078417778015137, "learning_rate": 5.631502249845516e-06, "loss": 0.1469, "step": 432120 }, { "epoch": 2.568670459071158, "grad_norm": 3.8460757732391357, "learning_rate": 5.63129641876417e-06, "loss": 0.1323, "step": 432130 }, { "epoch": 2.5687299011478264, "grad_norm": 3.689192533493042, "learning_rate": 5.631090586595659e-06, "loss": 0.1471, "step": 432140 }, { "epoch": 2.568789343224495, "grad_norm": 3.9872992038726807, "learning_rate": 5.630884753340332e-06, "loss": 0.125, "step": 432150 }, { "epoch": 2.5688487853011632, "grad_norm": 5.068477630615234, "learning_rate": 5.630678918998548e-06, "loss": 0.1298, "step": 432160 }, { "epoch": 2.5689082273778316, "grad_norm": 4.909895896911621, "learning_rate": 5.630473083570659e-06, "loss": 0.1359, "step": 432170 }, { "epoch": 2.5689676694545, "grad_norm": 3.530663013458252, "learning_rate": 5.630267247057019e-06, "loss": 0.1485, "step": 432180 }, { "epoch": 2.5690271115311685, "grad_norm": 4.161256790161133, "learning_rate": 5.630061409457986e-06, "loss": 0.106, "step": 432190 }, { "epoch": 2.569086553607837, "grad_norm": 4.606829643249512, "learning_rate": 5.62985557077391e-06, "loss": 0.1386, "step": 432200 }, { "epoch": 2.5691459956845053, "grad_norm": 4.460813999176025, "learning_rate": 5.629649731005149e-06, "loss": 0.1487, "step": 432210 }, { "epoch": 2.5692054377611737, "grad_norm": 3.6907236576080322, "learning_rate": 5.629443890152056e-06, "loss": 0.1261, "step": 432220 }, { "epoch": 2.569264879837842, "grad_norm": 3.5256738662719727, "learning_rate": 5.629238048214985e-06, "loss": 0.1274, "step": 432230 }, { "epoch": 2.5693243219145105, "grad_norm": 3.4375665187835693, "learning_rate": 5.629032205194291e-06, "loss": 0.1342, "step": 432240 }, { "epoch": 2.569383763991179, "grad_norm": 3.9238855838775635, "learning_rate": 5.62882636109033e-06, "loss": 0.1424, "step": 432250 }, { "epoch": 2.569443206067847, "grad_norm": 5.694591999053955, "learning_rate": 5.628620515903451e-06, "loss": 0.1424, "step": 432260 }, { "epoch": 2.569502648144516, "grad_norm": 3.830629587173462, "learning_rate": 5.628414669634015e-06, "loss": 0.1273, "step": 432270 }, { "epoch": 2.5695620902211838, "grad_norm": 4.602685928344727, "learning_rate": 5.6282088222823735e-06, "loss": 0.1253, "step": 432280 }, { "epoch": 2.5696215322978526, "grad_norm": 4.082618236541748, "learning_rate": 5.628002973848883e-06, "loss": 0.1288, "step": 432290 }, { "epoch": 2.5696809743745206, "grad_norm": 4.445963382720947, "learning_rate": 5.627797124333894e-06, "loss": 0.1355, "step": 432300 }, { "epoch": 2.569740416451189, "grad_norm": 3.792038679122925, "learning_rate": 5.627591273737766e-06, "loss": 0.1545, "step": 432310 }, { "epoch": 2.5697998585278574, "grad_norm": 4.305425643920898, "learning_rate": 5.6273854220608495e-06, "loss": 0.1434, "step": 432320 }, { "epoch": 2.569859300604526, "grad_norm": 4.258251190185547, "learning_rate": 5.6271795693035e-06, "loss": 0.1305, "step": 432330 }, { "epoch": 2.5699187426811942, "grad_norm": 3.941072940826416, "learning_rate": 5.626973715466074e-06, "loss": 0.1276, "step": 432340 }, { "epoch": 2.5699781847578627, "grad_norm": 5.192072868347168, "learning_rate": 5.626767860548924e-06, "loss": 0.1454, "step": 432350 }, { "epoch": 2.570037626834531, "grad_norm": 3.665567398071289, "learning_rate": 5.626562004552404e-06, "loss": 0.119, "step": 432360 }, { "epoch": 2.5700970689111995, "grad_norm": 3.46677303314209, "learning_rate": 5.626356147476869e-06, "loss": 0.1321, "step": 432370 }, { "epoch": 2.570156510987868, "grad_norm": 5.017739295959473, "learning_rate": 5.626150289322675e-06, "loss": 0.1259, "step": 432380 }, { "epoch": 2.5702159530645363, "grad_norm": 3.548827886581421, "learning_rate": 5.625944430090175e-06, "loss": 0.1241, "step": 432390 }, { "epoch": 2.5702753951412047, "grad_norm": 4.369504451751709, "learning_rate": 5.625738569779724e-06, "loss": 0.1269, "step": 432400 }, { "epoch": 2.570334837217873, "grad_norm": 3.722078323364258, "learning_rate": 5.625532708391678e-06, "loss": 0.1203, "step": 432410 }, { "epoch": 2.5703942792945416, "grad_norm": 4.547059535980225, "learning_rate": 5.625326845926389e-06, "loss": 0.129, "step": 432420 }, { "epoch": 2.57045372137121, "grad_norm": 4.785905361175537, "learning_rate": 5.625120982384212e-06, "loss": 0.1189, "step": 432430 }, { "epoch": 2.5705131634478784, "grad_norm": 3.366889476776123, "learning_rate": 5.624915117765503e-06, "loss": 0.1321, "step": 432440 }, { "epoch": 2.5705726055245464, "grad_norm": 4.307246685028076, "learning_rate": 5.624709252070616e-06, "loss": 0.1255, "step": 432450 }, { "epoch": 2.570632047601215, "grad_norm": 3.454571008682251, "learning_rate": 5.624503385299903e-06, "loss": 0.1422, "step": 432460 }, { "epoch": 2.570691489677883, "grad_norm": 4.808812618255615, "learning_rate": 5.624297517453723e-06, "loss": 0.142, "step": 432470 }, { "epoch": 2.570750931754552, "grad_norm": 4.119786739349365, "learning_rate": 5.624091648532426e-06, "loss": 0.1189, "step": 432480 }, { "epoch": 2.57081037383122, "grad_norm": 4.429961204528809, "learning_rate": 5.623885778536371e-06, "loss": 0.1328, "step": 432490 }, { "epoch": 2.5708698159078884, "grad_norm": 5.150171756744385, "learning_rate": 5.623679907465909e-06, "loss": 0.1259, "step": 432500 }, { "epoch": 2.570929257984557, "grad_norm": 5.21988582611084, "learning_rate": 5.623474035321396e-06, "loss": 0.159, "step": 432510 }, { "epoch": 2.5709887000612253, "grad_norm": 4.055825710296631, "learning_rate": 5.623268162103186e-06, "loss": 0.1258, "step": 432520 }, { "epoch": 2.5710481421378937, "grad_norm": 3.908982992172241, "learning_rate": 5.623062287811633e-06, "loss": 0.1284, "step": 432530 }, { "epoch": 2.571107584214562, "grad_norm": 3.3997130393981934, "learning_rate": 5.622856412447094e-06, "loss": 0.1246, "step": 432540 }, { "epoch": 2.5711670262912305, "grad_norm": 2.9627928733825684, "learning_rate": 5.622650536009923e-06, "loss": 0.1052, "step": 432550 }, { "epoch": 2.571226468367899, "grad_norm": 4.370202541351318, "learning_rate": 5.622444658500471e-06, "loss": 0.1365, "step": 432560 }, { "epoch": 2.5712859104445673, "grad_norm": 4.437807083129883, "learning_rate": 5.6222387799190954e-06, "loss": 0.1269, "step": 432570 }, { "epoch": 2.5713453525212357, "grad_norm": 4.052347183227539, "learning_rate": 5.622032900266152e-06, "loss": 0.1314, "step": 432580 }, { "epoch": 2.571404794597904, "grad_norm": 3.834080934524536, "learning_rate": 5.621827019541991e-06, "loss": 0.1445, "step": 432590 }, { "epoch": 2.5714642366745726, "grad_norm": 4.223923206329346, "learning_rate": 5.621621137746972e-06, "loss": 0.1195, "step": 432600 }, { "epoch": 2.571523678751241, "grad_norm": 4.416631698608398, "learning_rate": 5.621415254881447e-06, "loss": 0.1316, "step": 432610 }, { "epoch": 2.5715831208279094, "grad_norm": 4.193567752838135, "learning_rate": 5.6212093709457694e-06, "loss": 0.1229, "step": 432620 }, { "epoch": 2.571642562904578, "grad_norm": 4.031912803649902, "learning_rate": 5.621003485940296e-06, "loss": 0.1202, "step": 432630 }, { "epoch": 2.571702004981246, "grad_norm": 4.490842819213867, "learning_rate": 5.620797599865382e-06, "loss": 0.1392, "step": 432640 }, { "epoch": 2.5717614470579147, "grad_norm": 4.2987961769104, "learning_rate": 5.6205917127213794e-06, "loss": 0.1219, "step": 432650 }, { "epoch": 2.5718208891345826, "grad_norm": 4.194437503814697, "learning_rate": 5.620385824508643e-06, "loss": 0.1247, "step": 432660 }, { "epoch": 2.571880331211251, "grad_norm": 3.9696669578552246, "learning_rate": 5.620179935227529e-06, "loss": 0.1393, "step": 432670 }, { "epoch": 2.5719397732879195, "grad_norm": 4.124935150146484, "learning_rate": 5.61997404487839e-06, "loss": 0.1305, "step": 432680 }, { "epoch": 2.571999215364588, "grad_norm": 3.9723188877105713, "learning_rate": 5.619768153461582e-06, "loss": 0.1386, "step": 432690 }, { "epoch": 2.5720586574412563, "grad_norm": 4.141820430755615, "learning_rate": 5.619562260977459e-06, "loss": 0.1278, "step": 432700 }, { "epoch": 2.5721180995179247, "grad_norm": 4.218011379241943, "learning_rate": 5.6193563674263775e-06, "loss": 0.1178, "step": 432710 }, { "epoch": 2.572177541594593, "grad_norm": 4.410406112670898, "learning_rate": 5.619150472808689e-06, "loss": 0.1211, "step": 432720 }, { "epoch": 2.5722369836712615, "grad_norm": 3.629657506942749, "learning_rate": 5.618944577124751e-06, "loss": 0.1382, "step": 432730 }, { "epoch": 2.57229642574793, "grad_norm": 4.012465476989746, "learning_rate": 5.618738680374915e-06, "loss": 0.1171, "step": 432740 }, { "epoch": 2.5723558678245984, "grad_norm": 4.614999294281006, "learning_rate": 5.618532782559538e-06, "loss": 0.1177, "step": 432750 }, { "epoch": 2.5724153099012668, "grad_norm": 4.9930100440979, "learning_rate": 5.618326883678974e-06, "loss": 0.1359, "step": 432760 }, { "epoch": 2.572474751977935, "grad_norm": 4.716864109039307, "learning_rate": 5.618120983733577e-06, "loss": 0.129, "step": 432770 }, { "epoch": 2.5725341940546036, "grad_norm": 3.414947032928467, "learning_rate": 5.617915082723702e-06, "loss": 0.1453, "step": 432780 }, { "epoch": 2.572593636131272, "grad_norm": 4.853649616241455, "learning_rate": 5.617709180649703e-06, "loss": 0.1124, "step": 432790 }, { "epoch": 2.5726530782079404, "grad_norm": 4.6940484046936035, "learning_rate": 5.6175032775119365e-06, "loss": 0.126, "step": 432800 }, { "epoch": 2.5727125202846084, "grad_norm": 3.9399189949035645, "learning_rate": 5.617297373310754e-06, "loss": 0.1258, "step": 432810 }, { "epoch": 2.5727719623612773, "grad_norm": 3.7270548343658447, "learning_rate": 5.617091468046511e-06, "loss": 0.1304, "step": 432820 }, { "epoch": 2.5728314044379452, "grad_norm": 4.214466571807861, "learning_rate": 5.616885561719565e-06, "loss": 0.1341, "step": 432830 }, { "epoch": 2.572890846514614, "grad_norm": 4.356970310211182, "learning_rate": 5.616679654330268e-06, "loss": 0.1304, "step": 432840 }, { "epoch": 2.572950288591282, "grad_norm": 3.807387113571167, "learning_rate": 5.616473745878974e-06, "loss": 0.1276, "step": 432850 }, { "epoch": 2.5730097306679505, "grad_norm": 3.852470636367798, "learning_rate": 5.616267836366041e-06, "loss": 0.1208, "step": 432860 }, { "epoch": 2.573069172744619, "grad_norm": 5.29075288772583, "learning_rate": 5.616061925791819e-06, "loss": 0.1261, "step": 432870 }, { "epoch": 2.5731286148212873, "grad_norm": 4.389653205871582, "learning_rate": 5.615856014156665e-06, "loss": 0.1259, "step": 432880 }, { "epoch": 2.5731880568979557, "grad_norm": 4.445211887359619, "learning_rate": 5.615650101460935e-06, "loss": 0.1377, "step": 432890 }, { "epoch": 2.573247498974624, "grad_norm": 4.508301258087158, "learning_rate": 5.615444187704981e-06, "loss": 0.1155, "step": 432900 }, { "epoch": 2.5733069410512925, "grad_norm": 3.2997565269470215, "learning_rate": 5.615238272889158e-06, "loss": 0.1137, "step": 432910 }, { "epoch": 2.573366383127961, "grad_norm": 4.399550914764404, "learning_rate": 5.615032357013822e-06, "loss": 0.1256, "step": 432920 }, { "epoch": 2.5734258252046294, "grad_norm": 4.283389091491699, "learning_rate": 5.614826440079327e-06, "loss": 0.1367, "step": 432930 }, { "epoch": 2.573485267281298, "grad_norm": 3.5838942527770996, "learning_rate": 5.614620522086028e-06, "loss": 0.1327, "step": 432940 }, { "epoch": 2.573544709357966, "grad_norm": 4.6723175048828125, "learning_rate": 5.6144146030342774e-06, "loss": 0.1376, "step": 432950 }, { "epoch": 2.5736041514346346, "grad_norm": 4.13875150680542, "learning_rate": 5.6142086829244335e-06, "loss": 0.1432, "step": 432960 }, { "epoch": 2.573663593511303, "grad_norm": 4.232148170471191, "learning_rate": 5.614002761756849e-06, "loss": 0.1243, "step": 432970 }, { "epoch": 2.5737230355879714, "grad_norm": 3.8331387042999268, "learning_rate": 5.613796839531876e-06, "loss": 0.1293, "step": 432980 }, { "epoch": 2.57378247766464, "grad_norm": 3.61633038520813, "learning_rate": 5.613590916249875e-06, "loss": 0.1516, "step": 432990 }, { "epoch": 2.573841919741308, "grad_norm": 4.520107746124268, "learning_rate": 5.613384991911195e-06, "loss": 0.1352, "step": 433000 }, { "epoch": 2.5739013618179767, "grad_norm": 3.120391607284546, "learning_rate": 5.613179066516192e-06, "loss": 0.1405, "step": 433010 }, { "epoch": 2.5739608038946447, "grad_norm": 4.877941608428955, "learning_rate": 5.612973140065224e-06, "loss": 0.1428, "step": 433020 }, { "epoch": 2.5740202459713135, "grad_norm": 5.376482009887695, "learning_rate": 5.612767212558641e-06, "loss": 0.135, "step": 433030 }, { "epoch": 2.5740796880479815, "grad_norm": 5.530877113342285, "learning_rate": 5.612561283996802e-06, "loss": 0.1222, "step": 433040 }, { "epoch": 2.57413913012465, "grad_norm": 3.5239744186401367, "learning_rate": 5.612355354380057e-06, "loss": 0.153, "step": 433050 }, { "epoch": 2.5741985722013183, "grad_norm": 3.6395866870880127, "learning_rate": 5.612149423708764e-06, "loss": 0.1221, "step": 433060 }, { "epoch": 2.5742580142779867, "grad_norm": 4.242108345031738, "learning_rate": 5.611943491983277e-06, "loss": 0.1328, "step": 433070 }, { "epoch": 2.574317456354655, "grad_norm": 3.75356388092041, "learning_rate": 5.61173755920395e-06, "loss": 0.1274, "step": 433080 }, { "epoch": 2.5743768984313236, "grad_norm": 5.241911888122559, "learning_rate": 5.611531625371138e-06, "loss": 0.1302, "step": 433090 }, { "epoch": 2.574436340507992, "grad_norm": 4.3237504959106445, "learning_rate": 5.611325690485196e-06, "loss": 0.1314, "step": 433100 }, { "epoch": 2.5744957825846604, "grad_norm": 3.5317535400390625, "learning_rate": 5.611119754546477e-06, "loss": 0.1469, "step": 433110 }, { "epoch": 2.574555224661329, "grad_norm": 3.4856903553009033, "learning_rate": 5.610913817555338e-06, "loss": 0.1347, "step": 433120 }, { "epoch": 2.574614666737997, "grad_norm": 2.979576587677002, "learning_rate": 5.610707879512133e-06, "loss": 0.1184, "step": 433130 }, { "epoch": 2.5746741088146656, "grad_norm": 4.166484355926514, "learning_rate": 5.610501940417214e-06, "loss": 0.1266, "step": 433140 }, { "epoch": 2.574733550891334, "grad_norm": 4.536593437194824, "learning_rate": 5.610296000270938e-06, "loss": 0.1299, "step": 433150 }, { "epoch": 2.5747929929680025, "grad_norm": 3.658721685409546, "learning_rate": 5.610090059073662e-06, "loss": 0.1196, "step": 433160 }, { "epoch": 2.574852435044671, "grad_norm": 4.8136210441589355, "learning_rate": 5.609884116825737e-06, "loss": 0.1332, "step": 433170 }, { "epoch": 2.5749118771213393, "grad_norm": 4.4045090675354, "learning_rate": 5.609678173527517e-06, "loss": 0.1335, "step": 433180 }, { "epoch": 2.5749713191980073, "grad_norm": 4.222239971160889, "learning_rate": 5.609472229179361e-06, "loss": 0.1325, "step": 433190 }, { "epoch": 2.575030761274676, "grad_norm": 3.540606737136841, "learning_rate": 5.60926628378162e-06, "loss": 0.1383, "step": 433200 }, { "epoch": 2.575090203351344, "grad_norm": 4.023784637451172, "learning_rate": 5.60906033733465e-06, "loss": 0.136, "step": 433210 }, { "epoch": 2.575149645428013, "grad_norm": 4.515750885009766, "learning_rate": 5.608854389838805e-06, "loss": 0.1342, "step": 433220 }, { "epoch": 2.575209087504681, "grad_norm": 4.446700096130371, "learning_rate": 5.608648441294441e-06, "loss": 0.1379, "step": 433230 }, { "epoch": 2.5752685295813493, "grad_norm": 4.758255958557129, "learning_rate": 5.608442491701911e-06, "loss": 0.1174, "step": 433240 }, { "epoch": 2.5753279716580177, "grad_norm": 4.302454948425293, "learning_rate": 5.608236541061569e-06, "loss": 0.1293, "step": 433250 }, { "epoch": 2.575387413734686, "grad_norm": 4.578180313110352, "learning_rate": 5.608030589373773e-06, "loss": 0.1445, "step": 433260 }, { "epoch": 2.5754468558113546, "grad_norm": 2.8524415493011475, "learning_rate": 5.6078246366388745e-06, "loss": 0.1106, "step": 433270 }, { "epoch": 2.575506297888023, "grad_norm": 5.390223503112793, "learning_rate": 5.607618682857231e-06, "loss": 0.136, "step": 433280 }, { "epoch": 2.5755657399646914, "grad_norm": 5.070078372955322, "learning_rate": 5.607412728029196e-06, "loss": 0.1319, "step": 433290 }, { "epoch": 2.57562518204136, "grad_norm": 5.715832233428955, "learning_rate": 5.607206772155121e-06, "loss": 0.1314, "step": 433300 }, { "epoch": 2.5756846241180282, "grad_norm": 3.9695756435394287, "learning_rate": 5.607000815235366e-06, "loss": 0.156, "step": 433310 }, { "epoch": 2.5757440661946966, "grad_norm": 4.714999198913574, "learning_rate": 5.606794857270284e-06, "loss": 0.1279, "step": 433320 }, { "epoch": 2.575803508271365, "grad_norm": 4.707054138183594, "learning_rate": 5.606588898260227e-06, "loss": 0.1407, "step": 433330 }, { "epoch": 2.5758629503480335, "grad_norm": 4.459970951080322, "learning_rate": 5.606382938205551e-06, "loss": 0.114, "step": 433340 }, { "epoch": 2.575922392424702, "grad_norm": 6.445896148681641, "learning_rate": 5.606176977106612e-06, "loss": 0.1176, "step": 433350 }, { "epoch": 2.5759818345013703, "grad_norm": 3.1558961868286133, "learning_rate": 5.605971014963764e-06, "loss": 0.122, "step": 433360 }, { "epoch": 2.5760412765780387, "grad_norm": 3.2910380363464355, "learning_rate": 5.605765051777361e-06, "loss": 0.1371, "step": 433370 }, { "epoch": 2.5761007186547067, "grad_norm": 5.005095958709717, "learning_rate": 5.605559087547758e-06, "loss": 0.1099, "step": 433380 }, { "epoch": 2.5761601607313755, "grad_norm": 5.350997447967529, "learning_rate": 5.6053531222753125e-06, "loss": 0.1264, "step": 433390 }, { "epoch": 2.5762196028080435, "grad_norm": 4.70036506652832, "learning_rate": 5.605147155960374e-06, "loss": 0.1509, "step": 433400 }, { "epoch": 2.576279044884712, "grad_norm": 4.879676818847656, "learning_rate": 5.604941188603301e-06, "loss": 0.1423, "step": 433410 }, { "epoch": 2.5763384869613803, "grad_norm": 4.139851093292236, "learning_rate": 5.604735220204448e-06, "loss": 0.1298, "step": 433420 }, { "epoch": 2.5763979290380488, "grad_norm": 3.9007365703582764, "learning_rate": 5.604529250764167e-06, "loss": 0.1159, "step": 433430 }, { "epoch": 2.576457371114717, "grad_norm": 3.935001850128174, "learning_rate": 5.6043232802828154e-06, "loss": 0.1238, "step": 433440 }, { "epoch": 2.5765168131913856, "grad_norm": 3.0702998638153076, "learning_rate": 5.604117308760748e-06, "loss": 0.1369, "step": 433450 }, { "epoch": 2.576576255268054, "grad_norm": 4.116527557373047, "learning_rate": 5.603911336198317e-06, "loss": 0.1156, "step": 433460 }, { "epoch": 2.5766356973447224, "grad_norm": 3.8705227375030518, "learning_rate": 5.603705362595878e-06, "loss": 0.1345, "step": 433470 }, { "epoch": 2.576695139421391, "grad_norm": 4.591357231140137, "learning_rate": 5.603499387953788e-06, "loss": 0.1134, "step": 433480 }, { "epoch": 2.5767545814980592, "grad_norm": 3.968855857849121, "learning_rate": 5.6032934122723995e-06, "loss": 0.1224, "step": 433490 }, { "epoch": 2.5768140235747277, "grad_norm": 5.395203590393066, "learning_rate": 5.603087435552067e-06, "loss": 0.1438, "step": 433500 }, { "epoch": 2.576873465651396, "grad_norm": 3.405682325363159, "learning_rate": 5.6028814577931466e-06, "loss": 0.1202, "step": 433510 }, { "epoch": 2.5769329077280645, "grad_norm": 5.147630214691162, "learning_rate": 5.602675478995994e-06, "loss": 0.1256, "step": 433520 }, { "epoch": 2.576992349804733, "grad_norm": 4.362753391265869, "learning_rate": 5.60246949916096e-06, "loss": 0.1375, "step": 433530 }, { "epoch": 2.5770517918814013, "grad_norm": 3.7600767612457275, "learning_rate": 5.602263518288403e-06, "loss": 0.1277, "step": 433540 }, { "epoch": 2.5771112339580693, "grad_norm": 4.029540061950684, "learning_rate": 5.602057536378676e-06, "loss": 0.1125, "step": 433550 }, { "epoch": 2.577170676034738, "grad_norm": 3.8238728046417236, "learning_rate": 5.601851553432133e-06, "loss": 0.1281, "step": 433560 }, { "epoch": 2.577230118111406, "grad_norm": 3.8961546421051025, "learning_rate": 5.601645569449131e-06, "loss": 0.1299, "step": 433570 }, { "epoch": 2.577289560188075, "grad_norm": 3.959838390350342, "learning_rate": 5.601439584430023e-06, "loss": 0.1182, "step": 433580 }, { "epoch": 2.577349002264743, "grad_norm": 8.257784843444824, "learning_rate": 5.601233598375164e-06, "loss": 0.1218, "step": 433590 }, { "epoch": 2.5774084443414114, "grad_norm": 4.252747535705566, "learning_rate": 5.601027611284909e-06, "loss": 0.1565, "step": 433600 }, { "epoch": 2.57746788641808, "grad_norm": 4.748796463012695, "learning_rate": 5.600821623159613e-06, "loss": 0.1284, "step": 433610 }, { "epoch": 2.577527328494748, "grad_norm": 4.840030670166016, "learning_rate": 5.600615633999632e-06, "loss": 0.1466, "step": 433620 }, { "epoch": 2.5775867705714166, "grad_norm": 3.6126251220703125, "learning_rate": 5.6004096438053176e-06, "loss": 0.1363, "step": 433630 }, { "epoch": 2.577646212648085, "grad_norm": 5.202917575836182, "learning_rate": 5.600203652577026e-06, "loss": 0.1431, "step": 433640 }, { "epoch": 2.5777056547247534, "grad_norm": 5.565506935119629, "learning_rate": 5.599997660315114e-06, "loss": 0.1293, "step": 433650 }, { "epoch": 2.577765096801422, "grad_norm": 3.8693487644195557, "learning_rate": 5.599791667019933e-06, "loss": 0.1344, "step": 433660 }, { "epoch": 2.5778245388780903, "grad_norm": 2.8494410514831543, "learning_rate": 5.599585672691838e-06, "loss": 0.1539, "step": 433670 }, { "epoch": 2.5778839809547587, "grad_norm": 3.5675039291381836, "learning_rate": 5.599379677331187e-06, "loss": 0.1212, "step": 433680 }, { "epoch": 2.577943423031427, "grad_norm": 4.4236321449279785, "learning_rate": 5.599173680938331e-06, "loss": 0.1277, "step": 433690 }, { "epoch": 2.5780028651080955, "grad_norm": 5.4271697998046875, "learning_rate": 5.598967683513628e-06, "loss": 0.1411, "step": 433700 }, { "epoch": 2.578062307184764, "grad_norm": 3.420750856399536, "learning_rate": 5.59876168505743e-06, "loss": 0.1296, "step": 433710 }, { "epoch": 2.5781217492614323, "grad_norm": 5.022911071777344, "learning_rate": 5.598555685570094e-06, "loss": 0.1463, "step": 433720 }, { "epoch": 2.5781811913381008, "grad_norm": 3.012108564376831, "learning_rate": 5.598349685051972e-06, "loss": 0.1222, "step": 433730 }, { "epoch": 2.5782406334147687, "grad_norm": 4.387210845947266, "learning_rate": 5.598143683503422e-06, "loss": 0.1256, "step": 433740 }, { "epoch": 2.5783000754914376, "grad_norm": 3.4886255264282227, "learning_rate": 5.597937680924798e-06, "loss": 0.122, "step": 433750 }, { "epoch": 2.5783595175681056, "grad_norm": 4.391151428222656, "learning_rate": 5.597731677316452e-06, "loss": 0.1325, "step": 433760 }, { "epoch": 2.5784189596447744, "grad_norm": 3.3579652309417725, "learning_rate": 5.597525672678741e-06, "loss": 0.1179, "step": 433770 }, { "epoch": 2.5784784017214424, "grad_norm": 3.5820510387420654, "learning_rate": 5.59731966701202e-06, "loss": 0.1376, "step": 433780 }, { "epoch": 2.578537843798111, "grad_norm": 3.653130292892456, "learning_rate": 5.597113660316643e-06, "loss": 0.1181, "step": 433790 }, { "epoch": 2.578597285874779, "grad_norm": 3.688643455505371, "learning_rate": 5.5969076525929645e-06, "loss": 0.1295, "step": 433800 }, { "epoch": 2.5786567279514476, "grad_norm": 4.103010654449463, "learning_rate": 5.596701643841341e-06, "loss": 0.109, "step": 433810 }, { "epoch": 2.578716170028116, "grad_norm": 4.749273300170898, "learning_rate": 5.596495634062125e-06, "loss": 0.1272, "step": 433820 }, { "epoch": 2.5787756121047845, "grad_norm": 4.372650146484375, "learning_rate": 5.596289623255673e-06, "loss": 0.134, "step": 433830 }, { "epoch": 2.578835054181453, "grad_norm": 4.737811088562012, "learning_rate": 5.5960836114223396e-06, "loss": 0.1417, "step": 433840 }, { "epoch": 2.5788944962581213, "grad_norm": 2.840574026107788, "learning_rate": 5.595877598562479e-06, "loss": 0.1278, "step": 433850 }, { "epoch": 2.5789539383347897, "grad_norm": 3.0408084392547607, "learning_rate": 5.5956715846764455e-06, "loss": 0.1204, "step": 433860 }, { "epoch": 2.579013380411458, "grad_norm": 4.220968246459961, "learning_rate": 5.595465569764595e-06, "loss": 0.1385, "step": 433870 }, { "epoch": 2.5790728224881265, "grad_norm": 2.834491014480591, "learning_rate": 5.5952595538272816e-06, "loss": 0.1198, "step": 433880 }, { "epoch": 2.579132264564795, "grad_norm": 4.853050708770752, "learning_rate": 5.595053536864859e-06, "loss": 0.1376, "step": 433890 }, { "epoch": 2.5791917066414634, "grad_norm": 4.458611011505127, "learning_rate": 5.594847518877684e-06, "loss": 0.1206, "step": 433900 }, { "epoch": 2.5792511487181318, "grad_norm": 4.417510032653809, "learning_rate": 5.59464149986611e-06, "loss": 0.1402, "step": 433910 }, { "epoch": 2.5793105907948, "grad_norm": 4.098124027252197, "learning_rate": 5.594435479830494e-06, "loss": 0.1465, "step": 433920 }, { "epoch": 2.579370032871468, "grad_norm": 4.202336311340332, "learning_rate": 5.594229458771188e-06, "loss": 0.1317, "step": 433930 }, { "epoch": 2.579429474948137, "grad_norm": 4.534457206726074, "learning_rate": 5.594023436688548e-06, "loss": 0.1324, "step": 433940 }, { "epoch": 2.579488917024805, "grad_norm": 5.384337902069092, "learning_rate": 5.593817413582928e-06, "loss": 0.1386, "step": 433950 }, { "epoch": 2.579548359101474, "grad_norm": 4.933804512023926, "learning_rate": 5.593611389454686e-06, "loss": 0.1372, "step": 433960 }, { "epoch": 2.579607801178142, "grad_norm": 3.418180227279663, "learning_rate": 5.593405364304173e-06, "loss": 0.1353, "step": 433970 }, { "epoch": 2.5796672432548102, "grad_norm": 3.9649572372436523, "learning_rate": 5.593199338131745e-06, "loss": 0.1208, "step": 433980 }, { "epoch": 2.5797266853314786, "grad_norm": 5.217062473297119, "learning_rate": 5.592993310937756e-06, "loss": 0.1489, "step": 433990 }, { "epoch": 2.579786127408147, "grad_norm": 4.8109917640686035, "learning_rate": 5.5927872827225634e-06, "loss": 0.1329, "step": 434000 }, { "epoch": 2.5798455694848155, "grad_norm": 4.938746929168701, "learning_rate": 5.592581253486521e-06, "loss": 0.1198, "step": 434010 }, { "epoch": 2.579905011561484, "grad_norm": 4.32988977432251, "learning_rate": 5.59237522322998e-06, "loss": 0.1448, "step": 434020 }, { "epoch": 2.5799644536381523, "grad_norm": 3.7908973693847656, "learning_rate": 5.5921691919533e-06, "loss": 0.1298, "step": 434030 }, { "epoch": 2.5800238957148207, "grad_norm": 3.470424175262451, "learning_rate": 5.591963159656835e-06, "loss": 0.1301, "step": 434040 }, { "epoch": 2.580083337791489, "grad_norm": 4.072452545166016, "learning_rate": 5.591757126340937e-06, "loss": 0.1364, "step": 434050 }, { "epoch": 2.5801427798681575, "grad_norm": 3.949669599533081, "learning_rate": 5.591551092005963e-06, "loss": 0.1313, "step": 434060 }, { "epoch": 2.580202221944826, "grad_norm": 4.430253505706787, "learning_rate": 5.591345056652269e-06, "loss": 0.1246, "step": 434070 }, { "epoch": 2.5802616640214944, "grad_norm": 5.0801777839660645, "learning_rate": 5.591139020280206e-06, "loss": 0.1333, "step": 434080 }, { "epoch": 2.580321106098163, "grad_norm": 3.4660561084747314, "learning_rate": 5.590932982890132e-06, "loss": 0.1116, "step": 434090 }, { "epoch": 2.580380548174831, "grad_norm": 3.2970387935638428, "learning_rate": 5.590726944482403e-06, "loss": 0.1112, "step": 434100 }, { "epoch": 2.5804399902514996, "grad_norm": 4.882510185241699, "learning_rate": 5.590520905057369e-06, "loss": 0.1229, "step": 434110 }, { "epoch": 2.5804994323281676, "grad_norm": 5.954165935516357, "learning_rate": 5.590314864615388e-06, "loss": 0.1192, "step": 434120 }, { "epoch": 2.5805588744048364, "grad_norm": 3.828503131866455, "learning_rate": 5.590108823156814e-06, "loss": 0.137, "step": 434130 }, { "epoch": 2.5806183164815044, "grad_norm": 6.463878154754639, "learning_rate": 5.589902780682004e-06, "loss": 0.1406, "step": 434140 }, { "epoch": 2.580677758558173, "grad_norm": 4.077917098999023, "learning_rate": 5.5896967371913095e-06, "loss": 0.1374, "step": 434150 }, { "epoch": 2.5807372006348412, "grad_norm": 4.7020583152771, "learning_rate": 5.589490692685086e-06, "loss": 0.1373, "step": 434160 }, { "epoch": 2.5807966427115097, "grad_norm": 3.6629929542541504, "learning_rate": 5.5892846471636916e-06, "loss": 0.1281, "step": 434170 }, { "epoch": 2.580856084788178, "grad_norm": 4.3756327629089355, "learning_rate": 5.589078600627478e-06, "loss": 0.1423, "step": 434180 }, { "epoch": 2.5809155268648465, "grad_norm": 3.9753835201263428, "learning_rate": 5.5888725530767995e-06, "loss": 0.1204, "step": 434190 }, { "epoch": 2.580974968941515, "grad_norm": 4.4463300704956055, "learning_rate": 5.588666504512014e-06, "loss": 0.141, "step": 434200 }, { "epoch": 2.5810344110181833, "grad_norm": 6.08508825302124, "learning_rate": 5.588460454933473e-06, "loss": 0.1328, "step": 434210 }, { "epoch": 2.5810938530948517, "grad_norm": 5.012740612030029, "learning_rate": 5.5882544043415335e-06, "loss": 0.0972, "step": 434220 }, { "epoch": 2.58115329517152, "grad_norm": 4.3989105224609375, "learning_rate": 5.58804835273655e-06, "loss": 0.144, "step": 434230 }, { "epoch": 2.5812127372481886, "grad_norm": 3.944032907485962, "learning_rate": 5.587842300118877e-06, "loss": 0.1332, "step": 434240 }, { "epoch": 2.581272179324857, "grad_norm": 3.9727511405944824, "learning_rate": 5.587636246488868e-06, "loss": 0.1383, "step": 434250 }, { "epoch": 2.5813316214015254, "grad_norm": 3.396304130554199, "learning_rate": 5.587430191846881e-06, "loss": 0.1128, "step": 434260 }, { "epoch": 2.581391063478194, "grad_norm": 4.286706924438477, "learning_rate": 5.587224136193269e-06, "loss": 0.1178, "step": 434270 }, { "epoch": 2.581450505554862, "grad_norm": 3.6811649799346924, "learning_rate": 5.587018079528386e-06, "loss": 0.1237, "step": 434280 }, { "epoch": 2.58150994763153, "grad_norm": 4.8143510818481445, "learning_rate": 5.586812021852589e-06, "loss": 0.1198, "step": 434290 }, { "epoch": 2.581569389708199, "grad_norm": 4.703845977783203, "learning_rate": 5.586605963166231e-06, "loss": 0.1455, "step": 434300 }, { "epoch": 2.581628831784867, "grad_norm": 4.315609931945801, "learning_rate": 5.586399903469667e-06, "loss": 0.1565, "step": 434310 }, { "epoch": 2.581688273861536, "grad_norm": 2.8168931007385254, "learning_rate": 5.586193842763253e-06, "loss": 0.1155, "step": 434320 }, { "epoch": 2.581747715938204, "grad_norm": 3.533489942550659, "learning_rate": 5.585987781047344e-06, "loss": 0.1298, "step": 434330 }, { "epoch": 2.5818071580148723, "grad_norm": 3.8725709915161133, "learning_rate": 5.5857817183222926e-06, "loss": 0.1164, "step": 434340 }, { "epoch": 2.5818666000915407, "grad_norm": 2.9129772186279297, "learning_rate": 5.585575654588455e-06, "loss": 0.1423, "step": 434350 }, { "epoch": 2.581926042168209, "grad_norm": 4.4150800704956055, "learning_rate": 5.585369589846188e-06, "loss": 0.138, "step": 434360 }, { "epoch": 2.5819854842448775, "grad_norm": 3.290471076965332, "learning_rate": 5.585163524095845e-06, "loss": 0.1205, "step": 434370 }, { "epoch": 2.582044926321546, "grad_norm": 2.9253177642822266, "learning_rate": 5.584957457337778e-06, "loss": 0.1243, "step": 434380 }, { "epoch": 2.5821043683982143, "grad_norm": 4.5514235496521, "learning_rate": 5.584751389572346e-06, "loss": 0.1265, "step": 434390 }, { "epoch": 2.5821638104748827, "grad_norm": 4.107680320739746, "learning_rate": 5.584545320799904e-06, "loss": 0.123, "step": 434400 }, { "epoch": 2.582223252551551, "grad_norm": 5.15540075302124, "learning_rate": 5.584339251020802e-06, "loss": 0.1513, "step": 434410 }, { "epoch": 2.5822826946282196, "grad_norm": 4.300881385803223, "learning_rate": 5.584133180235401e-06, "loss": 0.1308, "step": 434420 }, { "epoch": 2.582342136704888, "grad_norm": 3.0859241485595703, "learning_rate": 5.583927108444052e-06, "loss": 0.1324, "step": 434430 }, { "epoch": 2.5824015787815564, "grad_norm": 3.2739195823669434, "learning_rate": 5.583721035647108e-06, "loss": 0.1203, "step": 434440 }, { "epoch": 2.582461020858225, "grad_norm": 4.711581230163574, "learning_rate": 5.58351496184493e-06, "loss": 0.1295, "step": 434450 }, { "epoch": 2.5825204629348932, "grad_norm": 4.470777988433838, "learning_rate": 5.5833088870378684e-06, "loss": 0.1406, "step": 434460 }, { "epoch": 2.5825799050115616, "grad_norm": 2.7465803623199463, "learning_rate": 5.58310281122628e-06, "loss": 0.12, "step": 434470 }, { "epoch": 2.5826393470882296, "grad_norm": 4.75018310546875, "learning_rate": 5.582896734410518e-06, "loss": 0.1212, "step": 434480 }, { "epoch": 2.5826987891648985, "grad_norm": 4.381417274475098, "learning_rate": 5.582690656590939e-06, "loss": 0.1094, "step": 434490 }, { "epoch": 2.5827582312415664, "grad_norm": 4.543011665344238, "learning_rate": 5.582484577767898e-06, "loss": 0.1282, "step": 434500 }, { "epoch": 2.5828176733182353, "grad_norm": 5.477899551391602, "learning_rate": 5.5822784979417475e-06, "loss": 0.1415, "step": 434510 }, { "epoch": 2.5828771153949033, "grad_norm": 3.6990675926208496, "learning_rate": 5.582072417112845e-06, "loss": 0.1249, "step": 434520 }, { "epoch": 2.5829365574715717, "grad_norm": 5.243750095367432, "learning_rate": 5.581866335281544e-06, "loss": 0.1549, "step": 434530 }, { "epoch": 2.58299599954824, "grad_norm": 3.6300947666168213, "learning_rate": 5.581660252448199e-06, "loss": 0.1355, "step": 434540 }, { "epoch": 2.5830554416249085, "grad_norm": 5.193722724914551, "learning_rate": 5.581454168613168e-06, "loss": 0.1333, "step": 434550 }, { "epoch": 2.583114883701577, "grad_norm": 4.062647819519043, "learning_rate": 5.581248083776801e-06, "loss": 0.1273, "step": 434560 }, { "epoch": 2.5831743257782454, "grad_norm": 5.307208061218262, "learning_rate": 5.581041997939455e-06, "loss": 0.1266, "step": 434570 }, { "epoch": 2.5832337678549138, "grad_norm": 4.167109966278076, "learning_rate": 5.580835911101487e-06, "loss": 0.1324, "step": 434580 }, { "epoch": 2.583293209931582, "grad_norm": 3.780686378479004, "learning_rate": 5.580629823263251e-06, "loss": 0.1318, "step": 434590 }, { "epoch": 2.5833526520082506, "grad_norm": 4.196858882904053, "learning_rate": 5.580423734425099e-06, "loss": 0.1443, "step": 434600 }, { "epoch": 2.583412094084919, "grad_norm": 4.695959091186523, "learning_rate": 5.580217644587389e-06, "loss": 0.1224, "step": 434610 }, { "epoch": 2.5834715361615874, "grad_norm": 3.2779653072357178, "learning_rate": 5.580011553750476e-06, "loss": 0.1302, "step": 434620 }, { "epoch": 2.583530978238256, "grad_norm": 4.427731990814209, "learning_rate": 5.579805461914712e-06, "loss": 0.1216, "step": 434630 }, { "epoch": 2.5835904203149243, "grad_norm": 3.572286367416382, "learning_rate": 5.579599369080455e-06, "loss": 0.1249, "step": 434640 }, { "epoch": 2.5836498623915927, "grad_norm": 5.565298080444336, "learning_rate": 5.579393275248059e-06, "loss": 0.1256, "step": 434650 }, { "epoch": 2.583709304468261, "grad_norm": 4.866931438446045, "learning_rate": 5.579187180417879e-06, "loss": 0.113, "step": 434660 }, { "epoch": 2.583768746544929, "grad_norm": 5.03213357925415, "learning_rate": 5.578981084590268e-06, "loss": 0.1148, "step": 434670 }, { "epoch": 2.583828188621598, "grad_norm": 4.565244674682617, "learning_rate": 5.578774987765583e-06, "loss": 0.1294, "step": 434680 }, { "epoch": 2.583887630698266, "grad_norm": 4.664847373962402, "learning_rate": 5.5785688899441795e-06, "loss": 0.1302, "step": 434690 }, { "epoch": 2.5839470727749347, "grad_norm": 3.0917792320251465, "learning_rate": 5.5783627911264096e-06, "loss": 0.1311, "step": 434700 }, { "epoch": 2.5840065148516027, "grad_norm": 4.050395965576172, "learning_rate": 5.5781566913126305e-06, "loss": 0.1344, "step": 434710 }, { "epoch": 2.584065956928271, "grad_norm": 4.566941261291504, "learning_rate": 5.577950590503198e-06, "loss": 0.1125, "step": 434720 }, { "epoch": 2.5841253990049395, "grad_norm": 5.0833587646484375, "learning_rate": 5.577744488698465e-06, "loss": 0.1336, "step": 434730 }, { "epoch": 2.584184841081608, "grad_norm": 3.871284246444702, "learning_rate": 5.577538385898786e-06, "loss": 0.1174, "step": 434740 }, { "epoch": 2.5842442831582764, "grad_norm": 4.791864395141602, "learning_rate": 5.577332282104519e-06, "loss": 0.1389, "step": 434750 }, { "epoch": 2.584303725234945, "grad_norm": 3.9544758796691895, "learning_rate": 5.5771261773160135e-06, "loss": 0.1182, "step": 434760 }, { "epoch": 2.584363167311613, "grad_norm": 4.062173843383789, "learning_rate": 5.576920071533631e-06, "loss": 0.1289, "step": 434770 }, { "epoch": 2.5844226093882816, "grad_norm": 2.6716220378875732, "learning_rate": 5.576713964757723e-06, "loss": 0.1148, "step": 434780 }, { "epoch": 2.58448205146495, "grad_norm": 6.4332122802734375, "learning_rate": 5.576507856988643e-06, "loss": 0.1505, "step": 434790 }, { "epoch": 2.5845414935416184, "grad_norm": 3.5578768253326416, "learning_rate": 5.576301748226748e-06, "loss": 0.1056, "step": 434800 }, { "epoch": 2.584600935618287, "grad_norm": 6.709941387176514, "learning_rate": 5.576095638472394e-06, "loss": 0.1343, "step": 434810 }, { "epoch": 2.5846603776949553, "grad_norm": 4.062369346618652, "learning_rate": 5.5758895277259336e-06, "loss": 0.1355, "step": 434820 }, { "epoch": 2.5847198197716237, "grad_norm": 3.5242183208465576, "learning_rate": 5.575683415987723e-06, "loss": 0.1244, "step": 434830 }, { "epoch": 2.584779261848292, "grad_norm": 3.249732732772827, "learning_rate": 5.575477303258117e-06, "loss": 0.1382, "step": 434840 }, { "epoch": 2.5848387039249605, "grad_norm": 4.128085136413574, "learning_rate": 5.57527118953747e-06, "loss": 0.1049, "step": 434850 }, { "epoch": 2.5848981460016285, "grad_norm": 3.6843173503875732, "learning_rate": 5.575065074826137e-06, "loss": 0.1214, "step": 434860 }, { "epoch": 2.5849575880782973, "grad_norm": 3.6480894088745117, "learning_rate": 5.574858959124475e-06, "loss": 0.1256, "step": 434870 }, { "epoch": 2.5850170301549653, "grad_norm": 3.670039653778076, "learning_rate": 5.574652842432836e-06, "loss": 0.141, "step": 434880 }, { "epoch": 2.5850764722316337, "grad_norm": 5.402676582336426, "learning_rate": 5.574446724751577e-06, "loss": 0.1319, "step": 434890 }, { "epoch": 2.585135914308302, "grad_norm": 4.829448223114014, "learning_rate": 5.574240606081051e-06, "loss": 0.1418, "step": 434900 }, { "epoch": 2.5851953563849706, "grad_norm": 3.3960092067718506, "learning_rate": 5.574034486421614e-06, "loss": 0.1254, "step": 434910 }, { "epoch": 2.585254798461639, "grad_norm": 3.0410501956939697, "learning_rate": 5.573828365773623e-06, "loss": 0.125, "step": 434920 }, { "epoch": 2.5853142405383074, "grad_norm": 3.676722288131714, "learning_rate": 5.5736222441374295e-06, "loss": 0.1099, "step": 434930 }, { "epoch": 2.585373682614976, "grad_norm": 4.074526309967041, "learning_rate": 5.573416121513391e-06, "loss": 0.1474, "step": 434940 }, { "epoch": 2.585433124691644, "grad_norm": 4.554162979125977, "learning_rate": 5.573209997901861e-06, "loss": 0.1174, "step": 434950 }, { "epoch": 2.5854925667683126, "grad_norm": 3.9971089363098145, "learning_rate": 5.573003873303195e-06, "loss": 0.1319, "step": 434960 }, { "epoch": 2.585552008844981, "grad_norm": 3.9184491634368896, "learning_rate": 5.572797747717748e-06, "loss": 0.1402, "step": 434970 }, { "epoch": 2.5856114509216495, "grad_norm": 4.144535541534424, "learning_rate": 5.572591621145877e-06, "loss": 0.1248, "step": 434980 }, { "epoch": 2.585670892998318, "grad_norm": 3.9561657905578613, "learning_rate": 5.572385493587931e-06, "loss": 0.1364, "step": 434990 }, { "epoch": 2.5857303350749863, "grad_norm": 4.338346481323242, "learning_rate": 5.572179365044271e-06, "loss": 0.1375, "step": 435000 }, { "epoch": 2.5857897771516547, "grad_norm": 5.0998334884643555, "learning_rate": 5.571973235515249e-06, "loss": 0.1348, "step": 435010 }, { "epoch": 2.585849219228323, "grad_norm": 3.3736634254455566, "learning_rate": 5.5717671050012224e-06, "loss": 0.1398, "step": 435020 }, { "epoch": 2.585908661304991, "grad_norm": 4.1440300941467285, "learning_rate": 5.571560973502544e-06, "loss": 0.1224, "step": 435030 }, { "epoch": 2.58596810338166, "grad_norm": 4.124042510986328, "learning_rate": 5.571354841019569e-06, "loss": 0.138, "step": 435040 }, { "epoch": 2.586027545458328, "grad_norm": 2.7015435695648193, "learning_rate": 5.571148707552653e-06, "loss": 0.1215, "step": 435050 }, { "epoch": 2.5860869875349968, "grad_norm": 4.937295436859131, "learning_rate": 5.570942573102149e-06, "loss": 0.1146, "step": 435060 }, { "epoch": 2.5861464296116647, "grad_norm": 4.832144737243652, "learning_rate": 5.570736437668417e-06, "loss": 0.1185, "step": 435070 }, { "epoch": 2.586205871688333, "grad_norm": 4.4398393630981445, "learning_rate": 5.570530301251808e-06, "loss": 0.1212, "step": 435080 }, { "epoch": 2.5862653137650016, "grad_norm": 4.073593616485596, "learning_rate": 5.570324163852676e-06, "loss": 0.1293, "step": 435090 }, { "epoch": 2.58632475584167, "grad_norm": 5.289402961730957, "learning_rate": 5.57011802547138e-06, "loss": 0.1446, "step": 435100 }, { "epoch": 2.5863841979183384, "grad_norm": 3.506319522857666, "learning_rate": 5.56991188610827e-06, "loss": 0.1607, "step": 435110 }, { "epoch": 2.586443639995007, "grad_norm": 4.009936332702637, "learning_rate": 5.569705745763705e-06, "loss": 0.1141, "step": 435120 }, { "epoch": 2.5865030820716752, "grad_norm": 5.315621376037598, "learning_rate": 5.569499604438039e-06, "loss": 0.1188, "step": 435130 }, { "epoch": 2.5865625241483436, "grad_norm": 3.97788405418396, "learning_rate": 5.569293462131626e-06, "loss": 0.126, "step": 435140 }, { "epoch": 2.586621966225012, "grad_norm": 4.754942893981934, "learning_rate": 5.569087318844824e-06, "loss": 0.1444, "step": 435150 }, { "epoch": 2.5866814083016805, "grad_norm": 4.458179950714111, "learning_rate": 5.568881174577982e-06, "loss": 0.1371, "step": 435160 }, { "epoch": 2.586740850378349, "grad_norm": 3.4051969051361084, "learning_rate": 5.5686750293314614e-06, "loss": 0.1359, "step": 435170 }, { "epoch": 2.5868002924550173, "grad_norm": 5.56350040435791, "learning_rate": 5.568468883105616e-06, "loss": 0.1513, "step": 435180 }, { "epoch": 2.5868597345316857, "grad_norm": 4.589524269104004, "learning_rate": 5.5682627359007955e-06, "loss": 0.1349, "step": 435190 }, { "epoch": 2.586919176608354, "grad_norm": 3.477752447128296, "learning_rate": 5.568056587717361e-06, "loss": 0.1343, "step": 435200 }, { "epoch": 2.5869786186850225, "grad_norm": 4.268390655517578, "learning_rate": 5.567850438555665e-06, "loss": 0.1326, "step": 435210 }, { "epoch": 2.5870380607616905, "grad_norm": 5.1349382400512695, "learning_rate": 5.567644288416063e-06, "loss": 0.128, "step": 435220 }, { "epoch": 2.5870975028383594, "grad_norm": 4.065554141998291, "learning_rate": 5.567438137298909e-06, "loss": 0.1331, "step": 435230 }, { "epoch": 2.5871569449150273, "grad_norm": 3.340095281600952, "learning_rate": 5.567231985204559e-06, "loss": 0.1314, "step": 435240 }, { "epoch": 2.587216386991696, "grad_norm": 4.424004554748535, "learning_rate": 5.567025832133368e-06, "loss": 0.1213, "step": 435250 }, { "epoch": 2.587275829068364, "grad_norm": 4.530015468597412, "learning_rate": 5.566819678085691e-06, "loss": 0.1212, "step": 435260 }, { "epoch": 2.5873352711450326, "grad_norm": 3.1831095218658447, "learning_rate": 5.566613523061884e-06, "loss": 0.1237, "step": 435270 }, { "epoch": 2.587394713221701, "grad_norm": 3.3339405059814453, "learning_rate": 5.566407367062298e-06, "loss": 0.1105, "step": 435280 }, { "epoch": 2.5874541552983694, "grad_norm": 4.741671085357666, "learning_rate": 5.566201210087293e-06, "loss": 0.1194, "step": 435290 }, { "epoch": 2.587513597375038, "grad_norm": 3.744788646697998, "learning_rate": 5.565995052137223e-06, "loss": 0.1167, "step": 435300 }, { "epoch": 2.5875730394517062, "grad_norm": 3.6985883712768555, "learning_rate": 5.5657888932124405e-06, "loss": 0.1185, "step": 435310 }, { "epoch": 2.5876324815283747, "grad_norm": 4.981283664703369, "learning_rate": 5.565582733313302e-06, "loss": 0.122, "step": 435320 }, { "epoch": 2.587691923605043, "grad_norm": 4.045053005218506, "learning_rate": 5.5653765724401635e-06, "loss": 0.1306, "step": 435330 }, { "epoch": 2.5877513656817115, "grad_norm": 4.307138442993164, "learning_rate": 5.565170410593377e-06, "loss": 0.1254, "step": 435340 }, { "epoch": 2.58781080775838, "grad_norm": 4.171836853027344, "learning_rate": 5.5649642477733e-06, "loss": 0.13, "step": 435350 }, { "epoch": 2.5878702498350483, "grad_norm": 3.512465476989746, "learning_rate": 5.564758083980288e-06, "loss": 0.1238, "step": 435360 }, { "epoch": 2.5879296919117167, "grad_norm": 3.6851449012756348, "learning_rate": 5.564551919214697e-06, "loss": 0.1221, "step": 435370 }, { "epoch": 2.587989133988385, "grad_norm": 3.9805688858032227, "learning_rate": 5.5643457534768775e-06, "loss": 0.1274, "step": 435380 }, { "epoch": 2.5880485760650536, "grad_norm": 4.164831161499023, "learning_rate": 5.564139586767189e-06, "loss": 0.1355, "step": 435390 }, { "epoch": 2.588108018141722, "grad_norm": 3.538139820098877, "learning_rate": 5.563933419085984e-06, "loss": 0.1253, "step": 435400 }, { "epoch": 2.58816746021839, "grad_norm": 5.302839756011963, "learning_rate": 5.563727250433618e-06, "loss": 0.1317, "step": 435410 }, { "epoch": 2.588226902295059, "grad_norm": 5.163024425506592, "learning_rate": 5.563521080810447e-06, "loss": 0.1236, "step": 435420 }, { "epoch": 2.5882863443717268, "grad_norm": 4.56831693649292, "learning_rate": 5.563314910216826e-06, "loss": 0.1357, "step": 435430 }, { "epoch": 2.5883457864483956, "grad_norm": 3.422802209854126, "learning_rate": 5.563108738653108e-06, "loss": 0.1197, "step": 435440 }, { "epoch": 2.5884052285250636, "grad_norm": 3.772212505340576, "learning_rate": 5.56290256611965e-06, "loss": 0.1038, "step": 435450 }, { "epoch": 2.588464670601732, "grad_norm": 4.671046733856201, "learning_rate": 5.5626963926168074e-06, "loss": 0.1315, "step": 435460 }, { "epoch": 2.5885241126784004, "grad_norm": 3.0580694675445557, "learning_rate": 5.5624902181449345e-06, "loss": 0.1347, "step": 435470 }, { "epoch": 2.588583554755069, "grad_norm": 3.645005226135254, "learning_rate": 5.562284042704385e-06, "loss": 0.133, "step": 435480 }, { "epoch": 2.5886429968317373, "grad_norm": 3.2703566551208496, "learning_rate": 5.562077866295517e-06, "loss": 0.1296, "step": 435490 }, { "epoch": 2.5887024389084057, "grad_norm": 4.439022064208984, "learning_rate": 5.561871688918683e-06, "loss": 0.1197, "step": 435500 }, { "epoch": 2.588761880985074, "grad_norm": 3.270688056945801, "learning_rate": 5.561665510574239e-06, "loss": 0.1267, "step": 435510 }, { "epoch": 2.5888213230617425, "grad_norm": 4.285954475402832, "learning_rate": 5.5614593312625395e-06, "loss": 0.123, "step": 435520 }, { "epoch": 2.588880765138411, "grad_norm": 3.2835333347320557, "learning_rate": 5.5612531509839415e-06, "loss": 0.1259, "step": 435530 }, { "epoch": 2.5889402072150793, "grad_norm": 3.9027211666107178, "learning_rate": 5.561046969738797e-06, "loss": 0.119, "step": 435540 }, { "epoch": 2.5889996492917478, "grad_norm": 4.101585865020752, "learning_rate": 5.5608407875274635e-06, "loss": 0.1294, "step": 435550 }, { "epoch": 2.589059091368416, "grad_norm": 4.095051288604736, "learning_rate": 5.560634604350294e-06, "loss": 0.1331, "step": 435560 }, { "epoch": 2.5891185334450846, "grad_norm": 3.895939826965332, "learning_rate": 5.560428420207646e-06, "loss": 0.1369, "step": 435570 }, { "epoch": 2.5891779755217526, "grad_norm": 3.0043768882751465, "learning_rate": 5.560222235099874e-06, "loss": 0.1372, "step": 435580 }, { "epoch": 2.5892374175984214, "grad_norm": 4.412694931030273, "learning_rate": 5.5600160490273314e-06, "loss": 0.1576, "step": 435590 }, { "epoch": 2.5892968596750894, "grad_norm": 4.52779483795166, "learning_rate": 5.559809861990375e-06, "loss": 0.1176, "step": 435600 }, { "epoch": 2.5893563017517582, "grad_norm": 2.945866346359253, "learning_rate": 5.559603673989359e-06, "loss": 0.1189, "step": 435610 }, { "epoch": 2.589415743828426, "grad_norm": 5.366382122039795, "learning_rate": 5.559397485024638e-06, "loss": 0.162, "step": 435620 }, { "epoch": 2.5894751859050946, "grad_norm": 4.336907386779785, "learning_rate": 5.559191295096569e-06, "loss": 0.1288, "step": 435630 }, { "epoch": 2.589534627981763, "grad_norm": 4.252327919006348, "learning_rate": 5.558985104205504e-06, "loss": 0.118, "step": 435640 }, { "epoch": 2.5895940700584315, "grad_norm": 4.664351940155029, "learning_rate": 5.558778912351802e-06, "loss": 0.1439, "step": 435650 }, { "epoch": 2.5896535121351, "grad_norm": 3.546579360961914, "learning_rate": 5.558572719535816e-06, "loss": 0.1092, "step": 435660 }, { "epoch": 2.5897129542117683, "grad_norm": 4.490581512451172, "learning_rate": 5.5583665257579e-06, "loss": 0.1195, "step": 435670 }, { "epoch": 2.5897723962884367, "grad_norm": 3.39435076713562, "learning_rate": 5.558160331018409e-06, "loss": 0.134, "step": 435680 }, { "epoch": 2.589831838365105, "grad_norm": 4.566366672515869, "learning_rate": 5.557954135317701e-06, "loss": 0.1309, "step": 435690 }, { "epoch": 2.5898912804417735, "grad_norm": 5.498653411865234, "learning_rate": 5.5577479386561306e-06, "loss": 0.1249, "step": 435700 }, { "epoch": 2.589950722518442, "grad_norm": 5.100625038146973, "learning_rate": 5.557541741034049e-06, "loss": 0.1462, "step": 435710 }, { "epoch": 2.5900101645951104, "grad_norm": 5.171601295471191, "learning_rate": 5.557335542451816e-06, "loss": 0.1321, "step": 435720 }, { "epoch": 2.5900696066717788, "grad_norm": 4.998950481414795, "learning_rate": 5.557129342909785e-06, "loss": 0.136, "step": 435730 }, { "epoch": 2.590129048748447, "grad_norm": 4.036279678344727, "learning_rate": 5.556923142408309e-06, "loss": 0.1295, "step": 435740 }, { "epoch": 2.5901884908251156, "grad_norm": 4.09942626953125, "learning_rate": 5.5567169409477466e-06, "loss": 0.1169, "step": 435750 }, { "epoch": 2.590247932901784, "grad_norm": 4.035214424133301, "learning_rate": 5.55651073852845e-06, "loss": 0.1109, "step": 435760 }, { "epoch": 2.590307374978452, "grad_norm": 4.498166084289551, "learning_rate": 5.556304535150776e-06, "loss": 0.1281, "step": 435770 }, { "epoch": 2.590366817055121, "grad_norm": 2.619506597518921, "learning_rate": 5.556098330815078e-06, "loss": 0.1156, "step": 435780 }, { "epoch": 2.590426259131789, "grad_norm": 4.377187252044678, "learning_rate": 5.555892125521714e-06, "loss": 0.1171, "step": 435790 }, { "epoch": 2.5904857012084577, "grad_norm": 5.275275230407715, "learning_rate": 5.555685919271038e-06, "loss": 0.1276, "step": 435800 }, { "epoch": 2.5905451432851256, "grad_norm": 4.440750598907471, "learning_rate": 5.555479712063402e-06, "loss": 0.137, "step": 435810 }, { "epoch": 2.590604585361794, "grad_norm": 4.604602336883545, "learning_rate": 5.555273503899165e-06, "loss": 0.1188, "step": 435820 }, { "epoch": 2.5906640274384625, "grad_norm": 3.3197944164276123, "learning_rate": 5.555067294778682e-06, "loss": 0.1338, "step": 435830 }, { "epoch": 2.590723469515131, "grad_norm": 3.4436771869659424, "learning_rate": 5.5548610847023045e-06, "loss": 0.1235, "step": 435840 }, { "epoch": 2.5907829115917993, "grad_norm": 3.8604001998901367, "learning_rate": 5.554654873670392e-06, "loss": 0.1344, "step": 435850 }, { "epoch": 2.5908423536684677, "grad_norm": 4.035430431365967, "learning_rate": 5.554448661683297e-06, "loss": 0.1306, "step": 435860 }, { "epoch": 2.590901795745136, "grad_norm": 3.553278684616089, "learning_rate": 5.554242448741375e-06, "loss": 0.1294, "step": 435870 }, { "epoch": 2.5909612378218045, "grad_norm": 3.5169999599456787, "learning_rate": 5.554036234844982e-06, "loss": 0.1233, "step": 435880 }, { "epoch": 2.591020679898473, "grad_norm": 3.2246952056884766, "learning_rate": 5.553830019994471e-06, "loss": 0.1206, "step": 435890 }, { "epoch": 2.5910801219751414, "grad_norm": 4.602660655975342, "learning_rate": 5.553623804190199e-06, "loss": 0.1237, "step": 435900 }, { "epoch": 2.59113956405181, "grad_norm": 5.152256011962891, "learning_rate": 5.553417587432522e-06, "loss": 0.1188, "step": 435910 }, { "epoch": 2.591199006128478, "grad_norm": 4.94959831237793, "learning_rate": 5.553211369721793e-06, "loss": 0.1324, "step": 435920 }, { "epoch": 2.5912584482051466, "grad_norm": 6.6155476570129395, "learning_rate": 5.553005151058367e-06, "loss": 0.144, "step": 435930 }, { "epoch": 2.591317890281815, "grad_norm": 4.049850940704346, "learning_rate": 5.552798931442602e-06, "loss": 0.1248, "step": 435940 }, { "epoch": 2.5913773323584834, "grad_norm": 3.348266363143921, "learning_rate": 5.552592710874851e-06, "loss": 0.1194, "step": 435950 }, { "epoch": 2.5914367744351514, "grad_norm": 4.9746994972229, "learning_rate": 5.552386489355469e-06, "loss": 0.1251, "step": 435960 }, { "epoch": 2.5914962165118203, "grad_norm": 4.185960292816162, "learning_rate": 5.5521802668848125e-06, "loss": 0.1234, "step": 435970 }, { "epoch": 2.5915556585884882, "grad_norm": 4.50393533706665, "learning_rate": 5.551974043463234e-06, "loss": 0.1306, "step": 435980 }, { "epoch": 2.591615100665157, "grad_norm": 4.7834086418151855, "learning_rate": 5.551767819091092e-06, "loss": 0.1358, "step": 435990 }, { "epoch": 2.591674542741825, "grad_norm": 3.6308889389038086, "learning_rate": 5.551561593768737e-06, "loss": 0.1337, "step": 436000 }, { "epoch": 2.5917339848184935, "grad_norm": 4.226158618927002, "learning_rate": 5.55135536749653e-06, "loss": 0.1262, "step": 436010 }, { "epoch": 2.591793426895162, "grad_norm": 3.1536083221435547, "learning_rate": 5.551149140274823e-06, "loss": 0.1304, "step": 436020 }, { "epoch": 2.5918528689718303, "grad_norm": 3.101412057876587, "learning_rate": 5.55094291210397e-06, "loss": 0.1192, "step": 436030 }, { "epoch": 2.5919123110484987, "grad_norm": 3.95548677444458, "learning_rate": 5.550736682984329e-06, "loss": 0.1263, "step": 436040 }, { "epoch": 2.591971753125167, "grad_norm": 4.604774475097656, "learning_rate": 5.550530452916254e-06, "loss": 0.1321, "step": 436050 }, { "epoch": 2.5920311952018356, "grad_norm": 4.60419225692749, "learning_rate": 5.550324221900098e-06, "loss": 0.1345, "step": 436060 }, { "epoch": 2.592090637278504, "grad_norm": 3.96016001701355, "learning_rate": 5.55011798993622e-06, "loss": 0.1234, "step": 436070 }, { "epoch": 2.5921500793551724, "grad_norm": 3.56599497795105, "learning_rate": 5.549911757024972e-06, "loss": 0.1384, "step": 436080 }, { "epoch": 2.592209521431841, "grad_norm": 4.0956130027771, "learning_rate": 5.549705523166711e-06, "loss": 0.1104, "step": 436090 }, { "epoch": 2.592268963508509, "grad_norm": 5.093173980712891, "learning_rate": 5.549499288361791e-06, "loss": 0.13, "step": 436100 }, { "epoch": 2.5923284055851776, "grad_norm": 3.229541301727295, "learning_rate": 5.549293052610567e-06, "loss": 0.1221, "step": 436110 }, { "epoch": 2.592387847661846, "grad_norm": 5.095205783843994, "learning_rate": 5.549086815913397e-06, "loss": 0.1402, "step": 436120 }, { "epoch": 2.5924472897385145, "grad_norm": 2.557624578475952, "learning_rate": 5.548880578270631e-06, "loss": 0.1102, "step": 436130 }, { "epoch": 2.592506731815183, "grad_norm": 6.996835231781006, "learning_rate": 5.548674339682629e-06, "loss": 0.1277, "step": 436140 }, { "epoch": 2.592566173891851, "grad_norm": 3.071974992752075, "learning_rate": 5.5484681001497455e-06, "loss": 0.1261, "step": 436150 }, { "epoch": 2.5926256159685197, "grad_norm": 3.429133892059326, "learning_rate": 5.548261859672333e-06, "loss": 0.1392, "step": 436160 }, { "epoch": 2.5926850580451877, "grad_norm": 3.897054672241211, "learning_rate": 5.548055618250748e-06, "loss": 0.1246, "step": 436170 }, { "epoch": 2.5927445001218565, "grad_norm": 4.604673862457275, "learning_rate": 5.5478493758853465e-06, "loss": 0.1399, "step": 436180 }, { "epoch": 2.5928039421985245, "grad_norm": 5.382920742034912, "learning_rate": 5.547643132576482e-06, "loss": 0.1231, "step": 436190 }, { "epoch": 2.592863384275193, "grad_norm": 3.6118807792663574, "learning_rate": 5.5474368883245115e-06, "loss": 0.114, "step": 436200 }, { "epoch": 2.5929228263518613, "grad_norm": 3.5740725994110107, "learning_rate": 5.5472306431297895e-06, "loss": 0.1058, "step": 436210 }, { "epoch": 2.5929822684285297, "grad_norm": 4.283482074737549, "learning_rate": 5.54702439699267e-06, "loss": 0.1385, "step": 436220 }, { "epoch": 2.593041710505198, "grad_norm": 4.007238864898682, "learning_rate": 5.546818149913509e-06, "loss": 0.1358, "step": 436230 }, { "epoch": 2.5931011525818666, "grad_norm": 3.2233314514160156, "learning_rate": 5.546611901892664e-06, "loss": 0.1368, "step": 436240 }, { "epoch": 2.593160594658535, "grad_norm": 4.755790710449219, "learning_rate": 5.5464056529304866e-06, "loss": 0.1329, "step": 436250 }, { "epoch": 2.5932200367352034, "grad_norm": 4.138226509094238, "learning_rate": 5.546199403027334e-06, "loss": 0.1321, "step": 436260 }, { "epoch": 2.593279478811872, "grad_norm": 3.5789003372192383, "learning_rate": 5.545993152183561e-06, "loss": 0.1247, "step": 436270 }, { "epoch": 2.5933389208885402, "grad_norm": 3.763148784637451, "learning_rate": 5.545786900399522e-06, "loss": 0.12, "step": 436280 }, { "epoch": 2.5933983629652086, "grad_norm": 4.50231409072876, "learning_rate": 5.545580647675573e-06, "loss": 0.1255, "step": 436290 }, { "epoch": 2.593457805041877, "grad_norm": 3.220806121826172, "learning_rate": 5.545374394012069e-06, "loss": 0.1241, "step": 436300 }, { "epoch": 2.5935172471185455, "grad_norm": 3.853351354598999, "learning_rate": 5.5451681394093655e-06, "loss": 0.1071, "step": 436310 }, { "epoch": 2.5935766891952134, "grad_norm": 3.7898612022399902, "learning_rate": 5.544961883867817e-06, "loss": 0.1218, "step": 436320 }, { "epoch": 2.5936361312718823, "grad_norm": 3.689026355743408, "learning_rate": 5.544755627387779e-06, "loss": 0.1243, "step": 436330 }, { "epoch": 2.5936955733485503, "grad_norm": 3.1667468547821045, "learning_rate": 5.544549369969607e-06, "loss": 0.1219, "step": 436340 }, { "epoch": 2.593755015425219, "grad_norm": 4.173980236053467, "learning_rate": 5.544343111613657e-06, "loss": 0.1161, "step": 436350 }, { "epoch": 2.593814457501887, "grad_norm": 3.6798503398895264, "learning_rate": 5.544136852320281e-06, "loss": 0.1318, "step": 436360 }, { "epoch": 2.5938738995785555, "grad_norm": 4.203502655029297, "learning_rate": 5.543930592089839e-06, "loss": 0.1233, "step": 436370 }, { "epoch": 2.593933341655224, "grad_norm": 4.989810466766357, "learning_rate": 5.543724330922683e-06, "loss": 0.1423, "step": 436380 }, { "epoch": 2.5939927837318923, "grad_norm": 4.949686527252197, "learning_rate": 5.543518068819167e-06, "loss": 0.1191, "step": 436390 }, { "epoch": 2.5940522258085608, "grad_norm": 4.336322784423828, "learning_rate": 5.54331180577965e-06, "loss": 0.1196, "step": 436400 }, { "epoch": 2.594111667885229, "grad_norm": 4.63870096206665, "learning_rate": 5.543105541804484e-06, "loss": 0.1219, "step": 436410 }, { "epoch": 2.5941711099618976, "grad_norm": 3.3377225399017334, "learning_rate": 5.542899276894026e-06, "loss": 0.1143, "step": 436420 }, { "epoch": 2.594230552038566, "grad_norm": 4.53874397277832, "learning_rate": 5.542693011048631e-06, "loss": 0.1128, "step": 436430 }, { "epoch": 2.5942899941152344, "grad_norm": 3.603060483932495, "learning_rate": 5.542486744268653e-06, "loss": 0.1253, "step": 436440 }, { "epoch": 2.594349436191903, "grad_norm": 4.9721550941467285, "learning_rate": 5.542280476554449e-06, "loss": 0.1123, "step": 436450 }, { "epoch": 2.5944088782685713, "grad_norm": 4.60325813293457, "learning_rate": 5.542074207906373e-06, "loss": 0.1349, "step": 436460 }, { "epoch": 2.5944683203452397, "grad_norm": 4.6489996910095215, "learning_rate": 5.54186793832478e-06, "loss": 0.1219, "step": 436470 }, { "epoch": 2.594527762421908, "grad_norm": 4.762078285217285, "learning_rate": 5.541661667810027e-06, "loss": 0.1398, "step": 436480 }, { "epoch": 2.5945872044985765, "grad_norm": 4.821825981140137, "learning_rate": 5.541455396362466e-06, "loss": 0.1475, "step": 436490 }, { "epoch": 2.594646646575245, "grad_norm": 4.1308159828186035, "learning_rate": 5.5412491239824566e-06, "loss": 0.1353, "step": 436500 }, { "epoch": 2.594706088651913, "grad_norm": 4.068996906280518, "learning_rate": 5.5410428506703505e-06, "loss": 0.1418, "step": 436510 }, { "epoch": 2.5947655307285817, "grad_norm": 4.019237041473389, "learning_rate": 5.540836576426504e-06, "loss": 0.1348, "step": 436520 }, { "epoch": 2.5948249728052497, "grad_norm": 4.569777488708496, "learning_rate": 5.540630301251272e-06, "loss": 0.1255, "step": 436530 }, { "epoch": 2.5948844148819186, "grad_norm": 3.955533027648926, "learning_rate": 5.540424025145012e-06, "loss": 0.1249, "step": 436540 }, { "epoch": 2.5949438569585865, "grad_norm": 4.707529067993164, "learning_rate": 5.540217748108073e-06, "loss": 0.1277, "step": 436550 }, { "epoch": 2.595003299035255, "grad_norm": 4.870513439178467, "learning_rate": 5.540011470140818e-06, "loss": 0.1508, "step": 436560 }, { "epoch": 2.5950627411119234, "grad_norm": 3.4397640228271484, "learning_rate": 5.539805191243599e-06, "loss": 0.1323, "step": 436570 }, { "epoch": 2.595122183188592, "grad_norm": 5.203049182891846, "learning_rate": 5.539598911416769e-06, "loss": 0.1247, "step": 436580 }, { "epoch": 2.59518162526526, "grad_norm": 3.4833498001098633, "learning_rate": 5.539392630660687e-06, "loss": 0.1231, "step": 436590 }, { "epoch": 2.5952410673419286, "grad_norm": 3.8032498359680176, "learning_rate": 5.539186348975707e-06, "loss": 0.133, "step": 436600 }, { "epoch": 2.595300509418597, "grad_norm": 5.225249767303467, "learning_rate": 5.538980066362182e-06, "loss": 0.1404, "step": 436610 }, { "epoch": 2.5953599514952654, "grad_norm": 5.180176734924316, "learning_rate": 5.53877378282047e-06, "loss": 0.1167, "step": 436620 }, { "epoch": 2.595419393571934, "grad_norm": 4.036447048187256, "learning_rate": 5.538567498350926e-06, "loss": 0.1512, "step": 436630 }, { "epoch": 2.5954788356486023, "grad_norm": 5.048245906829834, "learning_rate": 5.538361212953904e-06, "loss": 0.1329, "step": 436640 }, { "epoch": 2.5955382777252707, "grad_norm": 5.488924026489258, "learning_rate": 5.538154926629759e-06, "loss": 0.1257, "step": 436650 }, { "epoch": 2.595597719801939, "grad_norm": 4.423870086669922, "learning_rate": 5.537948639378846e-06, "loss": 0.116, "step": 436660 }, { "epoch": 2.5956571618786075, "grad_norm": 2.8798294067382812, "learning_rate": 5.537742351201524e-06, "loss": 0.1275, "step": 436670 }, { "epoch": 2.595716603955276, "grad_norm": 3.561660051345825, "learning_rate": 5.537536062098144e-06, "loss": 0.1407, "step": 436680 }, { "epoch": 2.5957760460319443, "grad_norm": 3.887479543685913, "learning_rate": 5.537329772069062e-06, "loss": 0.1342, "step": 436690 }, { "epoch": 2.5958354881086123, "grad_norm": 4.732767581939697, "learning_rate": 5.537123481114636e-06, "loss": 0.1382, "step": 436700 }, { "epoch": 2.595894930185281, "grad_norm": 3.2606852054595947, "learning_rate": 5.536917189235217e-06, "loss": 0.1259, "step": 436710 }, { "epoch": 2.595954372261949, "grad_norm": 3.5381569862365723, "learning_rate": 5.536710896431165e-06, "loss": 0.1237, "step": 436720 }, { "epoch": 2.596013814338618, "grad_norm": 4.53934907913208, "learning_rate": 5.536504602702831e-06, "loss": 0.1208, "step": 436730 }, { "epoch": 2.596073256415286, "grad_norm": 3.5179319381713867, "learning_rate": 5.536298308050573e-06, "loss": 0.1277, "step": 436740 }, { "epoch": 2.5961326984919544, "grad_norm": 5.420029640197754, "learning_rate": 5.5360920124747455e-06, "loss": 0.1367, "step": 436750 }, { "epoch": 2.596192140568623, "grad_norm": 3.423971176147461, "learning_rate": 5.535885715975703e-06, "loss": 0.1149, "step": 436760 }, { "epoch": 2.596251582645291, "grad_norm": 5.020227909088135, "learning_rate": 5.535679418553801e-06, "loss": 0.1182, "step": 436770 }, { "epoch": 2.5963110247219596, "grad_norm": 4.045440196990967, "learning_rate": 5.535473120209395e-06, "loss": 0.1147, "step": 436780 }, { "epoch": 2.596370466798628, "grad_norm": 3.3291873931884766, "learning_rate": 5.5352668209428405e-06, "loss": 0.1192, "step": 436790 }, { "epoch": 2.5964299088752965, "grad_norm": 4.721732139587402, "learning_rate": 5.5350605207544934e-06, "loss": 0.1229, "step": 436800 }, { "epoch": 2.596489350951965, "grad_norm": 4.687738418579102, "learning_rate": 5.5348542196447075e-06, "loss": 0.1415, "step": 436810 }, { "epoch": 2.5965487930286333, "grad_norm": 4.341762065887451, "learning_rate": 5.53464791761384e-06, "loss": 0.1308, "step": 436820 }, { "epoch": 2.5966082351053017, "grad_norm": 4.9215474128723145, "learning_rate": 5.5344416146622445e-06, "loss": 0.1444, "step": 436830 }, { "epoch": 2.59666767718197, "grad_norm": 3.3146567344665527, "learning_rate": 5.534235310790276e-06, "loss": 0.1116, "step": 436840 }, { "epoch": 2.5967271192586385, "grad_norm": 6.1768341064453125, "learning_rate": 5.534029005998292e-06, "loss": 0.13, "step": 436850 }, { "epoch": 2.596786561335307, "grad_norm": 5.0828094482421875, "learning_rate": 5.533822700286645e-06, "loss": 0.1297, "step": 436860 }, { "epoch": 2.5968460034119754, "grad_norm": 4.0136518478393555, "learning_rate": 5.533616393655692e-06, "loss": 0.1246, "step": 436870 }, { "epoch": 2.5969054454886438, "grad_norm": 5.905269622802734, "learning_rate": 5.533410086105787e-06, "loss": 0.1276, "step": 436880 }, { "epoch": 2.5969648875653117, "grad_norm": 3.83656907081604, "learning_rate": 5.533203777637287e-06, "loss": 0.1387, "step": 436890 }, { "epoch": 2.5970243296419806, "grad_norm": 3.654675245285034, "learning_rate": 5.532997468250547e-06, "loss": 0.118, "step": 436900 }, { "epoch": 2.5970837717186486, "grad_norm": 6.225234031677246, "learning_rate": 5.532791157945921e-06, "loss": 0.121, "step": 436910 }, { "epoch": 2.5971432137953174, "grad_norm": 4.030904293060303, "learning_rate": 5.532584846723766e-06, "loss": 0.1261, "step": 436920 }, { "epoch": 2.5972026558719854, "grad_norm": 5.0749030113220215, "learning_rate": 5.532378534584436e-06, "loss": 0.1386, "step": 436930 }, { "epoch": 2.597262097948654, "grad_norm": 3.7334370613098145, "learning_rate": 5.532172221528286e-06, "loss": 0.1332, "step": 436940 }, { "epoch": 2.5973215400253222, "grad_norm": 3.76123309135437, "learning_rate": 5.531965907555673e-06, "loss": 0.148, "step": 436950 }, { "epoch": 2.5973809821019906, "grad_norm": 3.14451003074646, "learning_rate": 5.531759592666951e-06, "loss": 0.1243, "step": 436960 }, { "epoch": 2.597440424178659, "grad_norm": 3.0299506187438965, "learning_rate": 5.5315532768624735e-06, "loss": 0.1326, "step": 436970 }, { "epoch": 2.5974998662553275, "grad_norm": 3.591296672821045, "learning_rate": 5.5313469601426005e-06, "loss": 0.134, "step": 436980 }, { "epoch": 2.597559308331996, "grad_norm": 5.267984867095947, "learning_rate": 5.531140642507683e-06, "loss": 0.1278, "step": 436990 }, { "epoch": 2.5976187504086643, "grad_norm": 3.9145753383636475, "learning_rate": 5.530934323958078e-06, "loss": 0.1279, "step": 437000 }, { "epoch": 2.5976781924853327, "grad_norm": 3.814924955368042, "learning_rate": 5.530728004494141e-06, "loss": 0.1134, "step": 437010 }, { "epoch": 2.597737634562001, "grad_norm": 4.082927227020264, "learning_rate": 5.530521684116228e-06, "loss": 0.1358, "step": 437020 }, { "epoch": 2.5977970766386695, "grad_norm": 5.4694504737854, "learning_rate": 5.530315362824693e-06, "loss": 0.1311, "step": 437030 }, { "epoch": 2.597856518715338, "grad_norm": 4.028539657592773, "learning_rate": 5.530109040619891e-06, "loss": 0.141, "step": 437040 }, { "epoch": 2.5979159607920064, "grad_norm": 5.222851276397705, "learning_rate": 5.529902717502178e-06, "loss": 0.131, "step": 437050 }, { "epoch": 2.5979754028686743, "grad_norm": 4.226335048675537, "learning_rate": 5.5296963934719106e-06, "loss": 0.1306, "step": 437060 }, { "epoch": 2.598034844945343, "grad_norm": 3.5214109420776367, "learning_rate": 5.529490068529441e-06, "loss": 0.1382, "step": 437070 }, { "epoch": 2.598094287022011, "grad_norm": 4.7893900871276855, "learning_rate": 5.529283742675128e-06, "loss": 0.1279, "step": 437080 }, { "epoch": 2.59815372909868, "grad_norm": 4.094331741333008, "learning_rate": 5.529077415909324e-06, "loss": 0.1418, "step": 437090 }, { "epoch": 2.598213171175348, "grad_norm": 4.285598278045654, "learning_rate": 5.528871088232385e-06, "loss": 0.1203, "step": 437100 }, { "epoch": 2.5982726132520164, "grad_norm": 5.768857002258301, "learning_rate": 5.528664759644667e-06, "loss": 0.1289, "step": 437110 }, { "epoch": 2.598332055328685, "grad_norm": 3.33862042427063, "learning_rate": 5.528458430146527e-06, "loss": 0.1286, "step": 437120 }, { "epoch": 2.5983914974053532, "grad_norm": 4.908362865447998, "learning_rate": 5.528252099738318e-06, "loss": 0.1141, "step": 437130 }, { "epoch": 2.5984509394820217, "grad_norm": 3.196300745010376, "learning_rate": 5.528045768420395e-06, "loss": 0.123, "step": 437140 }, { "epoch": 2.59851038155869, "grad_norm": 3.6262412071228027, "learning_rate": 5.527839436193115e-06, "loss": 0.1189, "step": 437150 }, { "epoch": 2.5985698236353585, "grad_norm": 4.602245330810547, "learning_rate": 5.527633103056832e-06, "loss": 0.1409, "step": 437160 }, { "epoch": 2.598629265712027, "grad_norm": 2.9249916076660156, "learning_rate": 5.527426769011902e-06, "loss": 0.1227, "step": 437170 }, { "epoch": 2.5986887077886953, "grad_norm": 4.504582405090332, "learning_rate": 5.52722043405868e-06, "loss": 0.119, "step": 437180 }, { "epoch": 2.5987481498653637, "grad_norm": 4.937666416168213, "learning_rate": 5.527014098197522e-06, "loss": 0.1416, "step": 437190 }, { "epoch": 2.598807591942032, "grad_norm": 4.311572074890137, "learning_rate": 5.5268077614287815e-06, "loss": 0.1122, "step": 437200 }, { "epoch": 2.5988670340187006, "grad_norm": 3.979991912841797, "learning_rate": 5.526601423752815e-06, "loss": 0.1317, "step": 437210 }, { "epoch": 2.598926476095369, "grad_norm": 3.410571336746216, "learning_rate": 5.52639508516998e-06, "loss": 0.1199, "step": 437220 }, { "epoch": 2.5989859181720374, "grad_norm": 3.938929796218872, "learning_rate": 5.526188745680628e-06, "loss": 0.1369, "step": 437230 }, { "epoch": 2.599045360248706, "grad_norm": 3.823699712753296, "learning_rate": 5.525982405285119e-06, "loss": 0.1323, "step": 437240 }, { "epoch": 2.5991048023253738, "grad_norm": 3.6459314823150635, "learning_rate": 5.525776063983803e-06, "loss": 0.1163, "step": 437250 }, { "epoch": 2.5991642444020426, "grad_norm": 4.300806522369385, "learning_rate": 5.525569721777039e-06, "loss": 0.1402, "step": 437260 }, { "epoch": 2.5992236864787106, "grad_norm": 3.843726396560669, "learning_rate": 5.5253633786651805e-06, "loss": 0.1284, "step": 437270 }, { "epoch": 2.5992831285553795, "grad_norm": 5.769493103027344, "learning_rate": 5.525157034648585e-06, "loss": 0.1281, "step": 437280 }, { "epoch": 2.5993425706320474, "grad_norm": 4.280086040496826, "learning_rate": 5.524950689727604e-06, "loss": 0.1301, "step": 437290 }, { "epoch": 2.599402012708716, "grad_norm": 3.8985955715179443, "learning_rate": 5.524744343902597e-06, "loss": 0.1225, "step": 437300 }, { "epoch": 2.5994614547853843, "grad_norm": 3.4021031856536865, "learning_rate": 5.524537997173918e-06, "loss": 0.1288, "step": 437310 }, { "epoch": 2.5995208968620527, "grad_norm": 5.86162805557251, "learning_rate": 5.524331649541921e-06, "loss": 0.1432, "step": 437320 }, { "epoch": 2.599580338938721, "grad_norm": 5.48725700378418, "learning_rate": 5.524125301006962e-06, "loss": 0.133, "step": 437330 }, { "epoch": 2.5996397810153895, "grad_norm": 4.564262390136719, "learning_rate": 5.523918951569397e-06, "loss": 0.1461, "step": 437340 }, { "epoch": 2.599699223092058, "grad_norm": 4.3448405265808105, "learning_rate": 5.523712601229582e-06, "loss": 0.1306, "step": 437350 }, { "epoch": 2.5997586651687263, "grad_norm": 4.758390426635742, "learning_rate": 5.52350624998787e-06, "loss": 0.1165, "step": 437360 }, { "epoch": 2.5998181072453947, "grad_norm": 4.497148036956787, "learning_rate": 5.523299897844618e-06, "loss": 0.1235, "step": 437370 }, { "epoch": 2.599877549322063, "grad_norm": 5.105177879333496, "learning_rate": 5.5230935448001835e-06, "loss": 0.1107, "step": 437380 }, { "epoch": 2.5999369913987316, "grad_norm": 5.161106586456299, "learning_rate": 5.522887190854917e-06, "loss": 0.126, "step": 437390 }, { "epoch": 2.5999964334754, "grad_norm": 3.56536865234375, "learning_rate": 5.522680836009177e-06, "loss": 0.1489, "step": 437400 }, { "epoch": 2.6000558755520684, "grad_norm": 2.7294232845306396, "learning_rate": 5.522474480263319e-06, "loss": 0.1106, "step": 437410 }, { "epoch": 2.600115317628737, "grad_norm": 4.195905685424805, "learning_rate": 5.5222681236176955e-06, "loss": 0.1379, "step": 437420 }, { "epoch": 2.6001747597054052, "grad_norm": 4.696479797363281, "learning_rate": 5.522061766072665e-06, "loss": 0.1288, "step": 437430 }, { "epoch": 2.600234201782073, "grad_norm": 3.398296356201172, "learning_rate": 5.5218554076285825e-06, "loss": 0.1106, "step": 437440 }, { "epoch": 2.600293643858742, "grad_norm": 4.4879374504089355, "learning_rate": 5.521649048285803e-06, "loss": 0.1279, "step": 437450 }, { "epoch": 2.60035308593541, "grad_norm": 3.067645311355591, "learning_rate": 5.52144268804468e-06, "loss": 0.1263, "step": 437460 }, { "epoch": 2.600412528012079, "grad_norm": 4.720955848693848, "learning_rate": 5.521236326905573e-06, "loss": 0.1247, "step": 437470 }, { "epoch": 2.600471970088747, "grad_norm": 4.648492336273193, "learning_rate": 5.521029964868832e-06, "loss": 0.1249, "step": 437480 }, { "epoch": 2.6005314121654153, "grad_norm": 4.195154666900635, "learning_rate": 5.520823601934817e-06, "loss": 0.1198, "step": 437490 }, { "epoch": 2.6005908542420837, "grad_norm": 5.401759147644043, "learning_rate": 5.520617238103881e-06, "loss": 0.1265, "step": 437500 }, { "epoch": 2.600650296318752, "grad_norm": 3.7515347003936768, "learning_rate": 5.5204108733763804e-06, "loss": 0.1188, "step": 437510 }, { "epoch": 2.6007097383954205, "grad_norm": 3.780090808868408, "learning_rate": 5.52020450775267e-06, "loss": 0.1225, "step": 437520 }, { "epoch": 2.600769180472089, "grad_norm": 4.273782730102539, "learning_rate": 5.519998141233105e-06, "loss": 0.1204, "step": 437530 }, { "epoch": 2.6008286225487574, "grad_norm": 4.1763105392456055, "learning_rate": 5.5197917738180405e-06, "loss": 0.1327, "step": 437540 }, { "epoch": 2.6008880646254258, "grad_norm": 7.546504020690918, "learning_rate": 5.519585405507834e-06, "loss": 0.1383, "step": 437550 }, { "epoch": 2.600947506702094, "grad_norm": 2.9727325439453125, "learning_rate": 5.519379036302839e-06, "loss": 0.1159, "step": 437560 }, { "epoch": 2.6010069487787626, "grad_norm": 4.761368274688721, "learning_rate": 5.519172666203412e-06, "loss": 0.1269, "step": 437570 }, { "epoch": 2.601066390855431, "grad_norm": 5.253383636474609, "learning_rate": 5.518966295209907e-06, "loss": 0.1375, "step": 437580 }, { "epoch": 2.6011258329320994, "grad_norm": 4.479281902313232, "learning_rate": 5.51875992332268e-06, "loss": 0.1061, "step": 437590 }, { "epoch": 2.601185275008768, "grad_norm": 4.180286884307861, "learning_rate": 5.518553550542086e-06, "loss": 0.13, "step": 437600 }, { "epoch": 2.6012447170854363, "grad_norm": 3.7887585163116455, "learning_rate": 5.5183471768684826e-06, "loss": 0.1218, "step": 437610 }, { "epoch": 2.6013041591621047, "grad_norm": 2.941269874572754, "learning_rate": 5.518140802302222e-06, "loss": 0.1244, "step": 437620 }, { "epoch": 2.6013636012387726, "grad_norm": 3.864370822906494, "learning_rate": 5.517934426843662e-06, "loss": 0.1265, "step": 437630 }, { "epoch": 2.6014230433154415, "grad_norm": 4.018725872039795, "learning_rate": 5.517728050493157e-06, "loss": 0.1233, "step": 437640 }, { "epoch": 2.6014824853921095, "grad_norm": 4.905093193054199, "learning_rate": 5.517521673251062e-06, "loss": 0.1307, "step": 437650 }, { "epoch": 2.6015419274687783, "grad_norm": 3.989638328552246, "learning_rate": 5.5173152951177314e-06, "loss": 0.1321, "step": 437660 }, { "epoch": 2.6016013695454463, "grad_norm": 4.088414192199707, "learning_rate": 5.517108916093524e-06, "loss": 0.1161, "step": 437670 }, { "epoch": 2.6016608116221147, "grad_norm": 3.2828383445739746, "learning_rate": 5.516902536178795e-06, "loss": 0.125, "step": 437680 }, { "epoch": 2.601720253698783, "grad_norm": 4.947394847869873, "learning_rate": 5.516696155373895e-06, "loss": 0.1206, "step": 437690 }, { "epoch": 2.6017796957754515, "grad_norm": 4.5685133934021, "learning_rate": 5.516489773679185e-06, "loss": 0.134, "step": 437700 }, { "epoch": 2.60183913785212, "grad_norm": 6.144350051879883, "learning_rate": 5.516283391095016e-06, "loss": 0.1206, "step": 437710 }, { "epoch": 2.6018985799287884, "grad_norm": 3.655601739883423, "learning_rate": 5.5160770076217465e-06, "loss": 0.1309, "step": 437720 }, { "epoch": 2.601958022005457, "grad_norm": 3.5459506511688232, "learning_rate": 5.5158706232597315e-06, "loss": 0.1216, "step": 437730 }, { "epoch": 2.602017464082125, "grad_norm": 2.71834397315979, "learning_rate": 5.5156642380093255e-06, "loss": 0.1198, "step": 437740 }, { "epoch": 2.6020769061587936, "grad_norm": 3.71962833404541, "learning_rate": 5.5154578518708825e-06, "loss": 0.1349, "step": 437750 }, { "epoch": 2.602136348235462, "grad_norm": 4.396364212036133, "learning_rate": 5.51525146484476e-06, "loss": 0.1167, "step": 437760 }, { "epoch": 2.6021957903121304, "grad_norm": 5.832648754119873, "learning_rate": 5.515045076931314e-06, "loss": 0.1262, "step": 437770 }, { "epoch": 2.602255232388799, "grad_norm": 4.303211212158203, "learning_rate": 5.5148386881308995e-06, "loss": 0.1401, "step": 437780 }, { "epoch": 2.6023146744654673, "grad_norm": 3.9288840293884277, "learning_rate": 5.514632298443868e-06, "loss": 0.1246, "step": 437790 }, { "epoch": 2.6023741165421352, "grad_norm": 4.881416320800781, "learning_rate": 5.514425907870582e-06, "loss": 0.1231, "step": 437800 }, { "epoch": 2.602433558618804, "grad_norm": 3.857387065887451, "learning_rate": 5.514219516411392e-06, "loss": 0.1216, "step": 437810 }, { "epoch": 2.602493000695472, "grad_norm": 3.566977024078369, "learning_rate": 5.514013124066654e-06, "loss": 0.1169, "step": 437820 }, { "epoch": 2.602552442772141, "grad_norm": 3.8167901039123535, "learning_rate": 5.513806730836725e-06, "loss": 0.1206, "step": 437830 }, { "epoch": 2.602611884848809, "grad_norm": 3.1435744762420654, "learning_rate": 5.51360033672196e-06, "loss": 0.1144, "step": 437840 }, { "epoch": 2.6026713269254773, "grad_norm": 4.0074687004089355, "learning_rate": 5.513393941722711e-06, "loss": 0.1326, "step": 437850 }, { "epoch": 2.6027307690021457, "grad_norm": 4.250460147857666, "learning_rate": 5.513187545839339e-06, "loss": 0.13, "step": 437860 }, { "epoch": 2.602790211078814, "grad_norm": 4.359084606170654, "learning_rate": 5.5129811490721965e-06, "loss": 0.1139, "step": 437870 }, { "epoch": 2.6028496531554826, "grad_norm": 4.405063629150391, "learning_rate": 5.512774751421638e-06, "loss": 0.1193, "step": 437880 }, { "epoch": 2.602909095232151, "grad_norm": 4.6211628913879395, "learning_rate": 5.512568352888022e-06, "loss": 0.1327, "step": 437890 }, { "epoch": 2.6029685373088194, "grad_norm": 3.17050838470459, "learning_rate": 5.512361953471701e-06, "loss": 0.1191, "step": 437900 }, { "epoch": 2.603027979385488, "grad_norm": 4.54079532623291, "learning_rate": 5.5121555531730306e-06, "loss": 0.1232, "step": 437910 }, { "epoch": 2.603087421462156, "grad_norm": 3.7565131187438965, "learning_rate": 5.511949151992369e-06, "loss": 0.1414, "step": 437920 }, { "epoch": 2.6031468635388246, "grad_norm": 3.413480281829834, "learning_rate": 5.51174274993007e-06, "loss": 0.1181, "step": 437930 }, { "epoch": 2.603206305615493, "grad_norm": 4.429792404174805, "learning_rate": 5.511536346986488e-06, "loss": 0.117, "step": 437940 }, { "epoch": 2.6032657476921615, "grad_norm": 4.595505714416504, "learning_rate": 5.511329943161981e-06, "loss": 0.1247, "step": 437950 }, { "epoch": 2.60332518976883, "grad_norm": 4.757693290710449, "learning_rate": 5.511123538456901e-06, "loss": 0.1356, "step": 437960 }, { "epoch": 2.6033846318454983, "grad_norm": 5.456113815307617, "learning_rate": 5.510917132871605e-06, "loss": 0.1298, "step": 437970 }, { "epoch": 2.6034440739221667, "grad_norm": 4.595532417297363, "learning_rate": 5.5107107264064485e-06, "loss": 0.1302, "step": 437980 }, { "epoch": 2.6035035159988347, "grad_norm": 4.778038501739502, "learning_rate": 5.5105043190617895e-06, "loss": 0.129, "step": 437990 }, { "epoch": 2.6035629580755035, "grad_norm": 3.480356216430664, "learning_rate": 5.51029791083798e-06, "loss": 0.1119, "step": 438000 }, { "epoch": 2.6036224001521715, "grad_norm": 5.432860851287842, "learning_rate": 5.510091501735375e-06, "loss": 0.1307, "step": 438010 }, { "epoch": 2.6036818422288404, "grad_norm": 4.874785423278809, "learning_rate": 5.509885091754334e-06, "loss": 0.1257, "step": 438020 }, { "epoch": 2.6037412843055083, "grad_norm": 4.033073425292969, "learning_rate": 5.509678680895209e-06, "loss": 0.1539, "step": 438030 }, { "epoch": 2.6038007263821767, "grad_norm": 3.8139631748199463, "learning_rate": 5.509472269158357e-06, "loss": 0.1194, "step": 438040 }, { "epoch": 2.603860168458845, "grad_norm": 3.5514206886291504, "learning_rate": 5.509265856544133e-06, "loss": 0.1166, "step": 438050 }, { "epoch": 2.6039196105355136, "grad_norm": 3.061584949493408, "learning_rate": 5.509059443052892e-06, "loss": 0.1278, "step": 438060 }, { "epoch": 2.603979052612182, "grad_norm": 4.571268081665039, "learning_rate": 5.50885302868499e-06, "loss": 0.1432, "step": 438070 }, { "epoch": 2.6040384946888504, "grad_norm": 3.009427309036255, "learning_rate": 5.508646613440781e-06, "loss": 0.1234, "step": 438080 }, { "epoch": 2.604097936765519, "grad_norm": 3.1367080211639404, "learning_rate": 5.508440197320624e-06, "loss": 0.1251, "step": 438090 }, { "epoch": 2.6041573788421872, "grad_norm": 3.9224181175231934, "learning_rate": 5.508233780324871e-06, "loss": 0.1357, "step": 438100 }, { "epoch": 2.6042168209188556, "grad_norm": 4.264873504638672, "learning_rate": 5.508027362453878e-06, "loss": 0.1233, "step": 438110 }, { "epoch": 2.604276262995524, "grad_norm": 4.932721138000488, "learning_rate": 5.507820943708003e-06, "loss": 0.1168, "step": 438120 }, { "epoch": 2.6043357050721925, "grad_norm": 3.5210323333740234, "learning_rate": 5.5076145240876e-06, "loss": 0.1368, "step": 438130 }, { "epoch": 2.604395147148861, "grad_norm": 4.941173076629639, "learning_rate": 5.5074081035930224e-06, "loss": 0.1378, "step": 438140 }, { "epoch": 2.6044545892255293, "grad_norm": 3.616421699523926, "learning_rate": 5.507201682224628e-06, "loss": 0.1447, "step": 438150 }, { "epoch": 2.6045140313021977, "grad_norm": 3.8227665424346924, "learning_rate": 5.506995259982774e-06, "loss": 0.1231, "step": 438160 }, { "epoch": 2.604573473378866, "grad_norm": 4.90224027633667, "learning_rate": 5.506788836867812e-06, "loss": 0.1217, "step": 438170 }, { "epoch": 2.604632915455534, "grad_norm": 3.908071279525757, "learning_rate": 5.506582412880098e-06, "loss": 0.1367, "step": 438180 }, { "epoch": 2.604692357532203, "grad_norm": 4.538731575012207, "learning_rate": 5.506375988019991e-06, "loss": 0.1188, "step": 438190 }, { "epoch": 2.604751799608871, "grad_norm": 5.3102006912231445, "learning_rate": 5.506169562287842e-06, "loss": 0.1125, "step": 438200 }, { "epoch": 2.60481124168554, "grad_norm": 5.300466537475586, "learning_rate": 5.50596313568401e-06, "loss": 0.1304, "step": 438210 }, { "epoch": 2.6048706837622078, "grad_norm": 3.424260139465332, "learning_rate": 5.505756708208848e-06, "loss": 0.1346, "step": 438220 }, { "epoch": 2.604930125838876, "grad_norm": 4.440079689025879, "learning_rate": 5.505550279862713e-06, "loss": 0.1284, "step": 438230 }, { "epoch": 2.6049895679155446, "grad_norm": 4.045546531677246, "learning_rate": 5.50534385064596e-06, "loss": 0.127, "step": 438240 }, { "epoch": 2.605049009992213, "grad_norm": 4.005752086639404, "learning_rate": 5.505137420558946e-06, "loss": 0.1175, "step": 438250 }, { "epoch": 2.6051084520688814, "grad_norm": 4.783471584320068, "learning_rate": 5.5049309896020245e-06, "loss": 0.129, "step": 438260 }, { "epoch": 2.60516789414555, "grad_norm": 3.7382030487060547, "learning_rate": 5.50472455777555e-06, "loss": 0.1251, "step": 438270 }, { "epoch": 2.6052273362222182, "grad_norm": 4.008531093597412, "learning_rate": 5.504518125079881e-06, "loss": 0.1167, "step": 438280 }, { "epoch": 2.6052867782988867, "grad_norm": 3.7575409412384033, "learning_rate": 5.504311691515371e-06, "loss": 0.1238, "step": 438290 }, { "epoch": 2.605346220375555, "grad_norm": 3.701462507247925, "learning_rate": 5.504105257082376e-06, "loss": 0.1219, "step": 438300 }, { "epoch": 2.6054056624522235, "grad_norm": 3.274186849594116, "learning_rate": 5.503898821781251e-06, "loss": 0.1284, "step": 438310 }, { "epoch": 2.605465104528892, "grad_norm": 3.9926116466522217, "learning_rate": 5.503692385612353e-06, "loss": 0.117, "step": 438320 }, { "epoch": 2.6055245466055603, "grad_norm": 3.451258659362793, "learning_rate": 5.5034859485760385e-06, "loss": 0.1337, "step": 438330 }, { "epoch": 2.6055839886822287, "grad_norm": 5.226284980773926, "learning_rate": 5.503279510672659e-06, "loss": 0.1374, "step": 438340 }, { "epoch": 2.605643430758897, "grad_norm": 4.712377548217773, "learning_rate": 5.503073071902571e-06, "loss": 0.1188, "step": 438350 }, { "epoch": 2.6057028728355656, "grad_norm": 4.267073154449463, "learning_rate": 5.502866632266134e-06, "loss": 0.1104, "step": 438360 }, { "epoch": 2.6057623149122335, "grad_norm": 3.7701988220214844, "learning_rate": 5.502660191763699e-06, "loss": 0.1218, "step": 438370 }, { "epoch": 2.6058217569889024, "grad_norm": 2.672605037689209, "learning_rate": 5.502453750395623e-06, "loss": 0.1081, "step": 438380 }, { "epoch": 2.6058811990655704, "grad_norm": 3.003101348876953, "learning_rate": 5.502247308162263e-06, "loss": 0.1402, "step": 438390 }, { "epoch": 2.6059406411422392, "grad_norm": 4.02577018737793, "learning_rate": 5.502040865063971e-06, "loss": 0.1223, "step": 438400 }, { "epoch": 2.606000083218907, "grad_norm": 3.346003532409668, "learning_rate": 5.501834421101107e-06, "loss": 0.1108, "step": 438410 }, { "epoch": 2.6060595252955756, "grad_norm": 2.9469754695892334, "learning_rate": 5.501627976274022e-06, "loss": 0.1141, "step": 438420 }, { "epoch": 2.606118967372244, "grad_norm": 5.213244438171387, "learning_rate": 5.501421530583075e-06, "loss": 0.1514, "step": 438430 }, { "epoch": 2.6061784094489124, "grad_norm": 3.51615309715271, "learning_rate": 5.5012150840286204e-06, "loss": 0.1357, "step": 438440 }, { "epoch": 2.606237851525581, "grad_norm": 3.969888210296631, "learning_rate": 5.501008636611015e-06, "loss": 0.1401, "step": 438450 }, { "epoch": 2.6062972936022493, "grad_norm": 4.942621231079102, "learning_rate": 5.500802188330612e-06, "loss": 0.1122, "step": 438460 }, { "epoch": 2.6063567356789177, "grad_norm": 4.543419361114502, "learning_rate": 5.500595739187766e-06, "loss": 0.1246, "step": 438470 }, { "epoch": 2.606416177755586, "grad_norm": 3.047428607940674, "learning_rate": 5.500389289182836e-06, "loss": 0.1266, "step": 438480 }, { "epoch": 2.6064756198322545, "grad_norm": 4.519981861114502, "learning_rate": 5.500182838316176e-06, "loss": 0.1198, "step": 438490 }, { "epoch": 2.606535061908923, "grad_norm": 3.741515874862671, "learning_rate": 5.49997638658814e-06, "loss": 0.128, "step": 438500 }, { "epoch": 2.6065945039855913, "grad_norm": 3.727532386779785, "learning_rate": 5.499769933999088e-06, "loss": 0.1201, "step": 438510 }, { "epoch": 2.6066539460622598, "grad_norm": 3.0441884994506836, "learning_rate": 5.499563480549371e-06, "loss": 0.1232, "step": 438520 }, { "epoch": 2.606713388138928, "grad_norm": 5.413633346557617, "learning_rate": 5.4993570262393435e-06, "loss": 0.1369, "step": 438530 }, { "epoch": 2.606772830215596, "grad_norm": 4.466481685638428, "learning_rate": 5.499150571069367e-06, "loss": 0.13, "step": 438540 }, { "epoch": 2.606832272292265, "grad_norm": 3.535632371902466, "learning_rate": 5.498944115039793e-06, "loss": 0.1136, "step": 438550 }, { "epoch": 2.606891714368933, "grad_norm": 6.367528438568115, "learning_rate": 5.498737658150976e-06, "loss": 0.1435, "step": 438560 }, { "epoch": 2.606951156445602, "grad_norm": 3.5960543155670166, "learning_rate": 5.498531200403275e-06, "loss": 0.145, "step": 438570 }, { "epoch": 2.60701059852227, "grad_norm": 3.674732208251953, "learning_rate": 5.498324741797044e-06, "loss": 0.1097, "step": 438580 }, { "epoch": 2.607070040598938, "grad_norm": 4.803278923034668, "learning_rate": 5.4981182823326374e-06, "loss": 0.1183, "step": 438590 }, { "epoch": 2.6071294826756066, "grad_norm": 4.236359119415283, "learning_rate": 5.497911822010412e-06, "loss": 0.1219, "step": 438600 }, { "epoch": 2.607188924752275, "grad_norm": 4.854487419128418, "learning_rate": 5.497705360830724e-06, "loss": 0.12, "step": 438610 }, { "epoch": 2.6072483668289435, "grad_norm": 2.8516204357147217, "learning_rate": 5.497498898793926e-06, "loss": 0.1266, "step": 438620 }, { "epoch": 2.607307808905612, "grad_norm": 3.79331636428833, "learning_rate": 5.497292435900376e-06, "loss": 0.1351, "step": 438630 }, { "epoch": 2.6073672509822803, "grad_norm": 3.3259310722351074, "learning_rate": 5.49708597215043e-06, "loss": 0.1232, "step": 438640 }, { "epoch": 2.6074266930589487, "grad_norm": 4.218900203704834, "learning_rate": 5.4968795075444424e-06, "loss": 0.117, "step": 438650 }, { "epoch": 2.607486135135617, "grad_norm": 3.215975284576416, "learning_rate": 5.496673042082768e-06, "loss": 0.1198, "step": 438660 }, { "epoch": 2.6075455772122855, "grad_norm": 3.0348968505859375, "learning_rate": 5.496466575765765e-06, "loss": 0.1307, "step": 438670 }, { "epoch": 2.607605019288954, "grad_norm": 4.2419610023498535, "learning_rate": 5.496260108593787e-06, "loss": 0.1135, "step": 438680 }, { "epoch": 2.6076644613656224, "grad_norm": 4.811357021331787, "learning_rate": 5.496053640567189e-06, "loss": 0.1207, "step": 438690 }, { "epoch": 2.6077239034422908, "grad_norm": 3.442126512527466, "learning_rate": 5.495847171686328e-06, "loss": 0.1238, "step": 438700 }, { "epoch": 2.607783345518959, "grad_norm": 3.3609800338745117, "learning_rate": 5.495640701951559e-06, "loss": 0.1128, "step": 438710 }, { "epoch": 2.6078427875956276, "grad_norm": 4.091872215270996, "learning_rate": 5.495434231363237e-06, "loss": 0.1226, "step": 438720 }, { "epoch": 2.6079022296722956, "grad_norm": 5.655437469482422, "learning_rate": 5.495227759921718e-06, "loss": 0.1341, "step": 438730 }, { "epoch": 2.6079616717489644, "grad_norm": 5.0598063468933105, "learning_rate": 5.49502128762736e-06, "loss": 0.1303, "step": 438740 }, { "epoch": 2.6080211138256324, "grad_norm": 3.3561723232269287, "learning_rate": 5.494814814480513e-06, "loss": 0.1333, "step": 438750 }, { "epoch": 2.6080805559023013, "grad_norm": 4.674415588378906, "learning_rate": 5.4946083404815374e-06, "loss": 0.1111, "step": 438760 }, { "epoch": 2.6081399979789692, "grad_norm": 4.268026351928711, "learning_rate": 5.494401865630788e-06, "loss": 0.1164, "step": 438770 }, { "epoch": 2.6081994400556376, "grad_norm": 4.564173221588135, "learning_rate": 5.494195389928618e-06, "loss": 0.1119, "step": 438780 }, { "epoch": 2.608258882132306, "grad_norm": 4.009998321533203, "learning_rate": 5.493988913375386e-06, "loss": 0.1222, "step": 438790 }, { "epoch": 2.6083183242089745, "grad_norm": 3.3154687881469727, "learning_rate": 5.493782435971446e-06, "loss": 0.1431, "step": 438800 }, { "epoch": 2.608377766285643, "grad_norm": 3.6598751544952393, "learning_rate": 5.493575957717153e-06, "loss": 0.1177, "step": 438810 }, { "epoch": 2.6084372083623113, "grad_norm": 4.660370349884033, "learning_rate": 5.493369478612863e-06, "loss": 0.1328, "step": 438820 }, { "epoch": 2.6084966504389797, "grad_norm": 4.839474678039551, "learning_rate": 5.493162998658933e-06, "loss": 0.1377, "step": 438830 }, { "epoch": 2.608556092515648, "grad_norm": 4.645291328430176, "learning_rate": 5.492956517855718e-06, "loss": 0.1173, "step": 438840 }, { "epoch": 2.6086155345923165, "grad_norm": 4.35941219329834, "learning_rate": 5.492750036203571e-06, "loss": 0.1308, "step": 438850 }, { "epoch": 2.608674976668985, "grad_norm": 3.5714211463928223, "learning_rate": 5.4925435537028496e-06, "loss": 0.1194, "step": 438860 }, { "epoch": 2.6087344187456534, "grad_norm": 3.5246546268463135, "learning_rate": 5.492337070353911e-06, "loss": 0.1304, "step": 438870 }, { "epoch": 2.608793860822322, "grad_norm": 4.265659332275391, "learning_rate": 5.4921305861571095e-06, "loss": 0.1303, "step": 438880 }, { "epoch": 2.60885330289899, "grad_norm": 3.825655460357666, "learning_rate": 5.4919241011127985e-06, "loss": 0.1261, "step": 438890 }, { "epoch": 2.6089127449756586, "grad_norm": 5.056695461273193, "learning_rate": 5.491717615221337e-06, "loss": 0.1499, "step": 438900 }, { "epoch": 2.608972187052327, "grad_norm": 4.156674861907959, "learning_rate": 5.491511128483079e-06, "loss": 0.126, "step": 438910 }, { "epoch": 2.609031629128995, "grad_norm": 3.8983614444732666, "learning_rate": 5.491304640898379e-06, "loss": 0.1233, "step": 438920 }, { "epoch": 2.609091071205664, "grad_norm": 3.360551357269287, "learning_rate": 5.491098152467595e-06, "loss": 0.1294, "step": 438930 }, { "epoch": 2.609150513282332, "grad_norm": 4.964274883270264, "learning_rate": 5.4908916631910815e-06, "loss": 0.1375, "step": 438940 }, { "epoch": 2.6092099553590007, "grad_norm": 4.685801982879639, "learning_rate": 5.490685173069193e-06, "loss": 0.1216, "step": 438950 }, { "epoch": 2.6092693974356687, "grad_norm": 4.728480339050293, "learning_rate": 5.4904786821022874e-06, "loss": 0.1166, "step": 438960 }, { "epoch": 2.609328839512337, "grad_norm": 5.75864315032959, "learning_rate": 5.490272190290718e-06, "loss": 0.117, "step": 438970 }, { "epoch": 2.6093882815890055, "grad_norm": 3.7517271041870117, "learning_rate": 5.490065697634841e-06, "loss": 0.1331, "step": 438980 }, { "epoch": 2.609447723665674, "grad_norm": 3.222696542739868, "learning_rate": 5.489859204135013e-06, "loss": 0.1147, "step": 438990 }, { "epoch": 2.6095071657423423, "grad_norm": 3.296344518661499, "learning_rate": 5.48965270979159e-06, "loss": 0.1175, "step": 439000 }, { "epoch": 2.6095666078190107, "grad_norm": 4.999359607696533, "learning_rate": 5.489446214604925e-06, "loss": 0.1171, "step": 439010 }, { "epoch": 2.609626049895679, "grad_norm": 5.113401889801025, "learning_rate": 5.489239718575375e-06, "loss": 0.1247, "step": 439020 }, { "epoch": 2.6096854919723476, "grad_norm": 4.368971824645996, "learning_rate": 5.489033221703297e-06, "loss": 0.1209, "step": 439030 }, { "epoch": 2.609744934049016, "grad_norm": 3.429845094680786, "learning_rate": 5.488826723989046e-06, "loss": 0.1174, "step": 439040 }, { "epoch": 2.6098043761256844, "grad_norm": 4.0040059089660645, "learning_rate": 5.4886202254329756e-06, "loss": 0.1143, "step": 439050 }, { "epoch": 2.609863818202353, "grad_norm": 4.272156715393066, "learning_rate": 5.488413726035444e-06, "loss": 0.1208, "step": 439060 }, { "epoch": 2.609923260279021, "grad_norm": 3.9539453983306885, "learning_rate": 5.488207225796805e-06, "loss": 0.1075, "step": 439070 }, { "epoch": 2.6099827023556896, "grad_norm": 4.324853420257568, "learning_rate": 5.4880007247174135e-06, "loss": 0.1441, "step": 439080 }, { "epoch": 2.610042144432358, "grad_norm": 4.267782211303711, "learning_rate": 5.487794222797629e-06, "loss": 0.134, "step": 439090 }, { "epoch": 2.6101015865090265, "grad_norm": 3.0655314922332764, "learning_rate": 5.487587720037803e-06, "loss": 0.12, "step": 439100 }, { "epoch": 2.6101610285856944, "grad_norm": 3.2362589836120605, "learning_rate": 5.4873812164382945e-06, "loss": 0.1195, "step": 439110 }, { "epoch": 2.6102204706623633, "grad_norm": 3.0437371730804443, "learning_rate": 5.487174711999456e-06, "loss": 0.115, "step": 439120 }, { "epoch": 2.6102799127390313, "grad_norm": 3.809145212173462, "learning_rate": 5.486968206721646e-06, "loss": 0.1417, "step": 439130 }, { "epoch": 2.6103393548156997, "grad_norm": 4.5548787117004395, "learning_rate": 5.486761700605216e-06, "loss": 0.1331, "step": 439140 }, { "epoch": 2.610398796892368, "grad_norm": 4.235852241516113, "learning_rate": 5.486555193650526e-06, "loss": 0.1329, "step": 439150 }, { "epoch": 2.6104582389690365, "grad_norm": 3.5861406326293945, "learning_rate": 5.486348685857931e-06, "loss": 0.1268, "step": 439160 }, { "epoch": 2.610517681045705, "grad_norm": 5.012563705444336, "learning_rate": 5.486142177227783e-06, "loss": 0.1203, "step": 439170 }, { "epoch": 2.6105771231223733, "grad_norm": 3.596132278442383, "learning_rate": 5.485935667760442e-06, "loss": 0.1393, "step": 439180 }, { "epoch": 2.6106365651990417, "grad_norm": 4.191859245300293, "learning_rate": 5.48572915745626e-06, "loss": 0.1443, "step": 439190 }, { "epoch": 2.61069600727571, "grad_norm": 4.289667129516602, "learning_rate": 5.4855226463155965e-06, "loss": 0.1258, "step": 439200 }, { "epoch": 2.6107554493523786, "grad_norm": 3.330918073654175, "learning_rate": 5.485316134338803e-06, "loss": 0.1149, "step": 439210 }, { "epoch": 2.610814891429047, "grad_norm": 3.3905768394470215, "learning_rate": 5.485109621526239e-06, "loss": 0.1143, "step": 439220 }, { "epoch": 2.6108743335057154, "grad_norm": 4.724620342254639, "learning_rate": 5.484903107878258e-06, "loss": 0.1455, "step": 439230 }, { "epoch": 2.610933775582384, "grad_norm": 4.373110294342041, "learning_rate": 5.484696593395215e-06, "loss": 0.1274, "step": 439240 }, { "epoch": 2.6109932176590522, "grad_norm": 3.414158821105957, "learning_rate": 5.484490078077468e-06, "loss": 0.1181, "step": 439250 }, { "epoch": 2.6110526597357206, "grad_norm": 2.9675638675689697, "learning_rate": 5.484283561925371e-06, "loss": 0.129, "step": 439260 }, { "epoch": 2.611112101812389, "grad_norm": 4.7035298347473145, "learning_rate": 5.484077044939279e-06, "loss": 0.1231, "step": 439270 }, { "epoch": 2.611171543889057, "grad_norm": 4.314562797546387, "learning_rate": 5.48387052711955e-06, "loss": 0.1393, "step": 439280 }, { "epoch": 2.611230985965726, "grad_norm": 5.142609119415283, "learning_rate": 5.483664008466537e-06, "loss": 0.123, "step": 439290 }, { "epoch": 2.611290428042394, "grad_norm": 5.174337863922119, "learning_rate": 5.4834574889805965e-06, "loss": 0.1292, "step": 439300 }, { "epoch": 2.6113498701190627, "grad_norm": 3.583946943283081, "learning_rate": 5.483250968662085e-06, "loss": 0.1318, "step": 439310 }, { "epoch": 2.6114093121957307, "grad_norm": 7.26026725769043, "learning_rate": 5.483044447511359e-06, "loss": 0.1375, "step": 439320 }, { "epoch": 2.611468754272399, "grad_norm": 3.6419878005981445, "learning_rate": 5.482837925528771e-06, "loss": 0.1284, "step": 439330 }, { "epoch": 2.6115281963490675, "grad_norm": 3.4491493701934814, "learning_rate": 5.482631402714679e-06, "loss": 0.1216, "step": 439340 }, { "epoch": 2.611587638425736, "grad_norm": 3.9608373641967773, "learning_rate": 5.482424879069439e-06, "loss": 0.1274, "step": 439350 }, { "epoch": 2.6116470805024043, "grad_norm": 3.591111898422241, "learning_rate": 5.482218354593406e-06, "loss": 0.1169, "step": 439360 }, { "epoch": 2.6117065225790728, "grad_norm": 3.527017116546631, "learning_rate": 5.482011829286934e-06, "loss": 0.1196, "step": 439370 }, { "epoch": 2.611765964655741, "grad_norm": 4.437491416931152, "learning_rate": 5.481805303150381e-06, "loss": 0.1287, "step": 439380 }, { "epoch": 2.6118254067324096, "grad_norm": 4.421822547912598, "learning_rate": 5.481598776184102e-06, "loss": 0.132, "step": 439390 }, { "epoch": 2.611884848809078, "grad_norm": 3.8209102153778076, "learning_rate": 5.4813922483884506e-06, "loss": 0.1313, "step": 439400 }, { "epoch": 2.6119442908857464, "grad_norm": 3.710726022720337, "learning_rate": 5.481185719763785e-06, "loss": 0.1305, "step": 439410 }, { "epoch": 2.612003732962415, "grad_norm": 3.444326639175415, "learning_rate": 5.480979190310461e-06, "loss": 0.1307, "step": 439420 }, { "epoch": 2.6120631750390833, "grad_norm": 5.491133689880371, "learning_rate": 5.480772660028834e-06, "loss": 0.1377, "step": 439430 }, { "epoch": 2.6121226171157517, "grad_norm": 3.2912981510162354, "learning_rate": 5.480566128919258e-06, "loss": 0.134, "step": 439440 }, { "epoch": 2.61218205919242, "grad_norm": 4.266628742218018, "learning_rate": 5.480359596982091e-06, "loss": 0.1339, "step": 439450 }, { "epoch": 2.6122415012690885, "grad_norm": 4.072055339813232, "learning_rate": 5.480153064217687e-06, "loss": 0.1553, "step": 439460 }, { "epoch": 2.6123009433457565, "grad_norm": 4.7631330490112305, "learning_rate": 5.479946530626401e-06, "loss": 0.126, "step": 439470 }, { "epoch": 2.6123603854224253, "grad_norm": 4.006381511688232, "learning_rate": 5.47973999620859e-06, "loss": 0.1304, "step": 439480 }, { "epoch": 2.6124198274990933, "grad_norm": 3.9704749584198, "learning_rate": 5.479533460964611e-06, "loss": 0.1267, "step": 439490 }, { "epoch": 2.612479269575762, "grad_norm": 3.46791934967041, "learning_rate": 5.479326924894817e-06, "loss": 0.1092, "step": 439500 }, { "epoch": 2.61253871165243, "grad_norm": 3.0803017616271973, "learning_rate": 5.479120387999566e-06, "loss": 0.1167, "step": 439510 }, { "epoch": 2.6125981537290985, "grad_norm": 6.0634446144104, "learning_rate": 5.47891385027921e-06, "loss": 0.1173, "step": 439520 }, { "epoch": 2.612657595805767, "grad_norm": 3.4286701679229736, "learning_rate": 5.47870731173411e-06, "loss": 0.1112, "step": 439530 }, { "epoch": 2.6127170378824354, "grad_norm": 4.535131931304932, "learning_rate": 5.478500772364616e-06, "loss": 0.1205, "step": 439540 }, { "epoch": 2.612776479959104, "grad_norm": 4.656155586242676, "learning_rate": 5.47829423217109e-06, "loss": 0.1314, "step": 439550 }, { "epoch": 2.612835922035772, "grad_norm": 4.359948635101318, "learning_rate": 5.478087691153883e-06, "loss": 0.1219, "step": 439560 }, { "epoch": 2.6128953641124406, "grad_norm": 3.7514989376068115, "learning_rate": 5.47788114931335e-06, "loss": 0.1392, "step": 439570 }, { "epoch": 2.612954806189109, "grad_norm": 4.061573505401611, "learning_rate": 5.477674606649851e-06, "loss": 0.1323, "step": 439580 }, { "epoch": 2.6130142482657774, "grad_norm": 5.006999969482422, "learning_rate": 5.477468063163739e-06, "loss": 0.1389, "step": 439590 }, { "epoch": 2.613073690342446, "grad_norm": 5.735176086425781, "learning_rate": 5.477261518855368e-06, "loss": 0.1276, "step": 439600 }, { "epoch": 2.6131331324191143, "grad_norm": 3.4565470218658447, "learning_rate": 5.477054973725098e-06, "loss": 0.137, "step": 439610 }, { "epoch": 2.6131925744957827, "grad_norm": 3.7323906421661377, "learning_rate": 5.476848427773281e-06, "loss": 0.1304, "step": 439620 }, { "epoch": 2.613252016572451, "grad_norm": 3.856428861618042, "learning_rate": 5.476641881000275e-06, "loss": 0.1266, "step": 439630 }, { "epoch": 2.6133114586491195, "grad_norm": 3.6533291339874268, "learning_rate": 5.4764353334064335e-06, "loss": 0.1257, "step": 439640 }, { "epoch": 2.613370900725788, "grad_norm": 3.984467029571533, "learning_rate": 5.476228784992116e-06, "loss": 0.1099, "step": 439650 }, { "epoch": 2.613430342802456, "grad_norm": 4.831568241119385, "learning_rate": 5.476022235757674e-06, "loss": 0.13, "step": 439660 }, { "epoch": 2.6134897848791248, "grad_norm": 4.373167037963867, "learning_rate": 5.475815685703465e-06, "loss": 0.1208, "step": 439670 }, { "epoch": 2.6135492269557927, "grad_norm": 4.461938381195068, "learning_rate": 5.475609134829845e-06, "loss": 0.1128, "step": 439680 }, { "epoch": 2.6136086690324616, "grad_norm": 3.6809191703796387, "learning_rate": 5.475402583137169e-06, "loss": 0.1243, "step": 439690 }, { "epoch": 2.6136681111091296, "grad_norm": 4.389667987823486, "learning_rate": 5.475196030625794e-06, "loss": 0.131, "step": 439700 }, { "epoch": 2.613727553185798, "grad_norm": 7.279932022094727, "learning_rate": 5.4749894772960735e-06, "loss": 0.1466, "step": 439710 }, { "epoch": 2.6137869952624664, "grad_norm": 4.452139377593994, "learning_rate": 5.474782923148365e-06, "loss": 0.1363, "step": 439720 }, { "epoch": 2.613846437339135, "grad_norm": 3.1525092124938965, "learning_rate": 5.474576368183021e-06, "loss": 0.1404, "step": 439730 }, { "epoch": 2.613905879415803, "grad_norm": 5.299259185791016, "learning_rate": 5.474369812400403e-06, "loss": 0.1307, "step": 439740 }, { "epoch": 2.6139653214924716, "grad_norm": 4.241366386413574, "learning_rate": 5.474163255800864e-06, "loss": 0.1248, "step": 439750 }, { "epoch": 2.61402476356914, "grad_norm": 3.5482919216156006, "learning_rate": 5.473956698384757e-06, "loss": 0.1415, "step": 439760 }, { "epoch": 2.6140842056458085, "grad_norm": 4.716700553894043, "learning_rate": 5.473750140152442e-06, "loss": 0.123, "step": 439770 }, { "epoch": 2.614143647722477, "grad_norm": 5.572317123413086, "learning_rate": 5.473543581104273e-06, "loss": 0.1278, "step": 439780 }, { "epoch": 2.6142030897991453, "grad_norm": 3.683650016784668, "learning_rate": 5.473337021240605e-06, "loss": 0.1315, "step": 439790 }, { "epoch": 2.6142625318758137, "grad_norm": 2.927546739578247, "learning_rate": 5.473130460561792e-06, "loss": 0.1419, "step": 439800 }, { "epoch": 2.614321973952482, "grad_norm": 3.566358804702759, "learning_rate": 5.472923899068194e-06, "loss": 0.126, "step": 439810 }, { "epoch": 2.6143814160291505, "grad_norm": 3.462404727935791, "learning_rate": 5.472717336760165e-06, "loss": 0.1296, "step": 439820 }, { "epoch": 2.614440858105819, "grad_norm": 4.0793561935424805, "learning_rate": 5.472510773638058e-06, "loss": 0.1302, "step": 439830 }, { "epoch": 2.6145003001824874, "grad_norm": 4.210019588470459, "learning_rate": 5.472304209702231e-06, "loss": 0.1499, "step": 439840 }, { "epoch": 2.6145597422591553, "grad_norm": 3.914437770843506, "learning_rate": 5.4720976449530425e-06, "loss": 0.13, "step": 439850 }, { "epoch": 2.614619184335824, "grad_norm": 3.5887503623962402, "learning_rate": 5.471891079390844e-06, "loss": 0.1148, "step": 439860 }, { "epoch": 2.614678626412492, "grad_norm": 4.222350120544434, "learning_rate": 5.471684513015993e-06, "loss": 0.1407, "step": 439870 }, { "epoch": 2.6147380684891606, "grad_norm": 4.083864688873291, "learning_rate": 5.4714779458288454e-06, "loss": 0.1242, "step": 439880 }, { "epoch": 2.614797510565829, "grad_norm": 3.2922990322113037, "learning_rate": 5.471271377829756e-06, "loss": 0.1221, "step": 439890 }, { "epoch": 2.6148569526424974, "grad_norm": 4.870198726654053, "learning_rate": 5.471064809019082e-06, "loss": 0.1314, "step": 439900 }, { "epoch": 2.614916394719166, "grad_norm": 4.0672712326049805, "learning_rate": 5.470858239397177e-06, "loss": 0.1293, "step": 439910 }, { "epoch": 2.6149758367958342, "grad_norm": 4.5933074951171875, "learning_rate": 5.470651668964398e-06, "loss": 0.1174, "step": 439920 }, { "epoch": 2.6150352788725026, "grad_norm": 3.070136070251465, "learning_rate": 5.470445097721102e-06, "loss": 0.1363, "step": 439930 }, { "epoch": 2.615094720949171, "grad_norm": 4.0587921142578125, "learning_rate": 5.470238525667643e-06, "loss": 0.1296, "step": 439940 }, { "epoch": 2.6151541630258395, "grad_norm": 3.243567705154419, "learning_rate": 5.4700319528043755e-06, "loss": 0.1268, "step": 439950 }, { "epoch": 2.615213605102508, "grad_norm": 4.1534600257873535, "learning_rate": 5.469825379131658e-06, "loss": 0.1369, "step": 439960 }, { "epoch": 2.6152730471791763, "grad_norm": 4.351174354553223, "learning_rate": 5.4696188046498455e-06, "loss": 0.1311, "step": 439970 }, { "epoch": 2.6153324892558447, "grad_norm": 4.552011489868164, "learning_rate": 5.4694122293592935e-06, "loss": 0.1253, "step": 439980 }, { "epoch": 2.615391931332513, "grad_norm": 3.7387874126434326, "learning_rate": 5.469205653260357e-06, "loss": 0.1287, "step": 439990 }, { "epoch": 2.6154513734091815, "grad_norm": 3.3539023399353027, "learning_rate": 5.4689990763533916e-06, "loss": 0.1109, "step": 440000 }, { "epoch": 2.61551081548585, "grad_norm": 3.255692481994629, "learning_rate": 5.468792498638755e-06, "loss": 0.1253, "step": 440010 }, { "epoch": 2.615570257562518, "grad_norm": 3.3122406005859375, "learning_rate": 5.468585920116801e-06, "loss": 0.1225, "step": 440020 }, { "epoch": 2.615629699639187, "grad_norm": 3.2627220153808594, "learning_rate": 5.468379340787887e-06, "loss": 0.123, "step": 440030 }, { "epoch": 2.6156891417158548, "grad_norm": 4.655893802642822, "learning_rate": 5.4681727606523686e-06, "loss": 0.1242, "step": 440040 }, { "epoch": 2.6157485837925236, "grad_norm": 4.062243938446045, "learning_rate": 5.467966179710599e-06, "loss": 0.1185, "step": 440050 }, { "epoch": 2.6158080258691916, "grad_norm": 3.4056406021118164, "learning_rate": 5.467759597962936e-06, "loss": 0.1226, "step": 440060 }, { "epoch": 2.61586746794586, "grad_norm": 4.051650524139404, "learning_rate": 5.467553015409736e-06, "loss": 0.1243, "step": 440070 }, { "epoch": 2.6159269100225284, "grad_norm": 3.814676284790039, "learning_rate": 5.467346432051355e-06, "loss": 0.143, "step": 440080 }, { "epoch": 2.615986352099197, "grad_norm": 4.45195198059082, "learning_rate": 5.467139847888145e-06, "loss": 0.1365, "step": 440090 }, { "epoch": 2.6160457941758652, "grad_norm": 4.3845038414001465, "learning_rate": 5.466933262920466e-06, "loss": 0.1504, "step": 440100 }, { "epoch": 2.6161052362525337, "grad_norm": 4.7140069007873535, "learning_rate": 5.466726677148673e-06, "loss": 0.1419, "step": 440110 }, { "epoch": 2.616164678329202, "grad_norm": 3.6642935276031494, "learning_rate": 5.466520090573119e-06, "loss": 0.1227, "step": 440120 }, { "epoch": 2.6162241204058705, "grad_norm": 5.8210015296936035, "learning_rate": 5.466313503194164e-06, "loss": 0.1519, "step": 440130 }, { "epoch": 2.616283562482539, "grad_norm": 4.464958667755127, "learning_rate": 5.466106915012161e-06, "loss": 0.1351, "step": 440140 }, { "epoch": 2.6163430045592073, "grad_norm": 3.752023696899414, "learning_rate": 5.4659003260274635e-06, "loss": 0.1068, "step": 440150 }, { "epoch": 2.6164024466358757, "grad_norm": 3.2591757774353027, "learning_rate": 5.465693736240433e-06, "loss": 0.1318, "step": 440160 }, { "epoch": 2.616461888712544, "grad_norm": 5.767804145812988, "learning_rate": 5.46548714565142e-06, "loss": 0.1359, "step": 440170 }, { "epoch": 2.6165213307892126, "grad_norm": 4.454579830169678, "learning_rate": 5.465280554260786e-06, "loss": 0.1243, "step": 440180 }, { "epoch": 2.616580772865881, "grad_norm": 3.4111180305480957, "learning_rate": 5.46507396206888e-06, "loss": 0.1502, "step": 440190 }, { "epoch": 2.6166402149425494, "grad_norm": 4.778927326202393, "learning_rate": 5.464867369076062e-06, "loss": 0.1266, "step": 440200 }, { "epoch": 2.6166996570192174, "grad_norm": 6.259980201721191, "learning_rate": 5.464660775282689e-06, "loss": 0.1334, "step": 440210 }, { "epoch": 2.616759099095886, "grad_norm": 3.513767957687378, "learning_rate": 5.4644541806891115e-06, "loss": 0.1092, "step": 440220 }, { "epoch": 2.616818541172554, "grad_norm": 4.684832572937012, "learning_rate": 5.464247585295691e-06, "loss": 0.125, "step": 440230 }, { "epoch": 2.616877983249223, "grad_norm": 3.651636838912964, "learning_rate": 5.46404098910278e-06, "loss": 0.1147, "step": 440240 }, { "epoch": 2.616937425325891, "grad_norm": 3.8527350425720215, "learning_rate": 5.463834392110735e-06, "loss": 0.1112, "step": 440250 }, { "epoch": 2.6169968674025594, "grad_norm": 4.212993621826172, "learning_rate": 5.463627794319912e-06, "loss": 0.1292, "step": 440260 }, { "epoch": 2.617056309479228, "grad_norm": 4.621832847595215, "learning_rate": 5.463421195730667e-06, "loss": 0.1373, "step": 440270 }, { "epoch": 2.6171157515558963, "grad_norm": 4.448305130004883, "learning_rate": 5.463214596343354e-06, "loss": 0.1114, "step": 440280 }, { "epoch": 2.6171751936325647, "grad_norm": 4.000188827514648, "learning_rate": 5.463007996158331e-06, "loss": 0.1186, "step": 440290 }, { "epoch": 2.617234635709233, "grad_norm": 3.9048755168914795, "learning_rate": 5.462801395175953e-06, "loss": 0.1211, "step": 440300 }, { "epoch": 2.6172940777859015, "grad_norm": 5.680490493774414, "learning_rate": 5.462594793396576e-06, "loss": 0.131, "step": 440310 }, { "epoch": 2.61735351986257, "grad_norm": 3.821269989013672, "learning_rate": 5.462388190820555e-06, "loss": 0.116, "step": 440320 }, { "epoch": 2.6174129619392383, "grad_norm": 4.391424655914307, "learning_rate": 5.462181587448247e-06, "loss": 0.1443, "step": 440330 }, { "epoch": 2.6174724040159068, "grad_norm": 4.487902641296387, "learning_rate": 5.461974983280006e-06, "loss": 0.1249, "step": 440340 }, { "epoch": 2.617531846092575, "grad_norm": 3.617579698562622, "learning_rate": 5.46176837831619e-06, "loss": 0.1236, "step": 440350 }, { "epoch": 2.6175912881692436, "grad_norm": 3.407763957977295, "learning_rate": 5.461561772557154e-06, "loss": 0.1305, "step": 440360 }, { "epoch": 2.617650730245912, "grad_norm": 4.395771026611328, "learning_rate": 5.461355166003254e-06, "loss": 0.1192, "step": 440370 }, { "epoch": 2.6177101723225804, "grad_norm": 3.8987536430358887, "learning_rate": 5.461148558654843e-06, "loss": 0.1133, "step": 440380 }, { "epoch": 2.617769614399249, "grad_norm": 4.0893025398254395, "learning_rate": 5.460941950512279e-06, "loss": 0.1301, "step": 440390 }, { "epoch": 2.617829056475917, "grad_norm": 4.677773952484131, "learning_rate": 5.460735341575921e-06, "loss": 0.123, "step": 440400 }, { "epoch": 2.6178884985525857, "grad_norm": 3.0471417903900146, "learning_rate": 5.46052873184612e-06, "loss": 0.122, "step": 440410 }, { "epoch": 2.6179479406292536, "grad_norm": 2.638070583343506, "learning_rate": 5.460322121323234e-06, "loss": 0.1363, "step": 440420 }, { "epoch": 2.6180073827059225, "grad_norm": 4.760919570922852, "learning_rate": 5.460115510007618e-06, "loss": 0.1422, "step": 440430 }, { "epoch": 2.6180668247825905, "grad_norm": 3.828591823577881, "learning_rate": 5.45990889789963e-06, "loss": 0.1272, "step": 440440 }, { "epoch": 2.618126266859259, "grad_norm": 3.8614816665649414, "learning_rate": 5.4597022849996215e-06, "loss": 0.1338, "step": 440450 }, { "epoch": 2.6181857089359273, "grad_norm": 3.667736530303955, "learning_rate": 5.4594956713079524e-06, "loss": 0.1176, "step": 440460 }, { "epoch": 2.6182451510125957, "grad_norm": 4.1880106925964355, "learning_rate": 5.459289056824977e-06, "loss": 0.1117, "step": 440470 }, { "epoch": 2.618304593089264, "grad_norm": 4.049042701721191, "learning_rate": 5.459082441551049e-06, "loss": 0.116, "step": 440480 }, { "epoch": 2.6183640351659325, "grad_norm": 3.875943422317505, "learning_rate": 5.458875825486528e-06, "loss": 0.1231, "step": 440490 }, { "epoch": 2.618423477242601, "grad_norm": 2.7177321910858154, "learning_rate": 5.458669208631767e-06, "loss": 0.1135, "step": 440500 }, { "epoch": 2.6184829193192694, "grad_norm": 4.489657878875732, "learning_rate": 5.458462590987123e-06, "loss": 0.1368, "step": 440510 }, { "epoch": 2.6185423613959378, "grad_norm": 2.7871673107147217, "learning_rate": 5.458255972552952e-06, "loss": 0.1212, "step": 440520 }, { "epoch": 2.618601803472606, "grad_norm": 5.271151542663574, "learning_rate": 5.458049353329612e-06, "loss": 0.1263, "step": 440530 }, { "epoch": 2.6186612455492746, "grad_norm": 4.451164722442627, "learning_rate": 5.457842733317453e-06, "loss": 0.1335, "step": 440540 }, { "epoch": 2.618720687625943, "grad_norm": 3.265530586242676, "learning_rate": 5.4576361125168356e-06, "loss": 0.1116, "step": 440550 }, { "epoch": 2.6187801297026114, "grad_norm": 2.742934226989746, "learning_rate": 5.457429490928115e-06, "loss": 0.112, "step": 440560 }, { "epoch": 2.61883957177928, "grad_norm": 3.198626756668091, "learning_rate": 5.457222868551645e-06, "loss": 0.1186, "step": 440570 }, { "epoch": 2.6188990138559483, "grad_norm": 4.3210954666137695, "learning_rate": 5.457016245387783e-06, "loss": 0.1136, "step": 440580 }, { "epoch": 2.6189584559326162, "grad_norm": 4.610243797302246, "learning_rate": 5.456809621436885e-06, "loss": 0.1243, "step": 440590 }, { "epoch": 2.619017898009285, "grad_norm": 4.117882251739502, "learning_rate": 5.456602996699305e-06, "loss": 0.1285, "step": 440600 }, { "epoch": 2.619077340085953, "grad_norm": 4.259514331817627, "learning_rate": 5.4563963711754e-06, "loss": 0.1212, "step": 440610 }, { "epoch": 2.6191367821626215, "grad_norm": 4.619926929473877, "learning_rate": 5.4561897448655275e-06, "loss": 0.137, "step": 440620 }, { "epoch": 2.61919622423929, "grad_norm": 3.4438397884368896, "learning_rate": 5.4559831177700415e-06, "loss": 0.1236, "step": 440630 }, { "epoch": 2.6192556663159583, "grad_norm": 4.513748645782471, "learning_rate": 5.4557764898892974e-06, "loss": 0.1201, "step": 440640 }, { "epoch": 2.6193151083926267, "grad_norm": 4.799737930297852, "learning_rate": 5.455569861223653e-06, "loss": 0.1112, "step": 440650 }, { "epoch": 2.619374550469295, "grad_norm": 2.880803108215332, "learning_rate": 5.455363231773462e-06, "loss": 0.1111, "step": 440660 }, { "epoch": 2.6194339925459635, "grad_norm": 4.182174205780029, "learning_rate": 5.455156601539081e-06, "loss": 0.1151, "step": 440670 }, { "epoch": 2.619493434622632, "grad_norm": 4.0528059005737305, "learning_rate": 5.454949970520867e-06, "loss": 0.1289, "step": 440680 }, { "epoch": 2.6195528766993004, "grad_norm": 4.241906642913818, "learning_rate": 5.454743338719174e-06, "loss": 0.1284, "step": 440690 }, { "epoch": 2.619612318775969, "grad_norm": 4.71942138671875, "learning_rate": 5.454536706134359e-06, "loss": 0.1281, "step": 440700 }, { "epoch": 2.619671760852637, "grad_norm": 4.501047611236572, "learning_rate": 5.454330072766778e-06, "loss": 0.1369, "step": 440710 }, { "epoch": 2.6197312029293056, "grad_norm": 6.498095512390137, "learning_rate": 5.454123438616785e-06, "loss": 0.1242, "step": 440720 }, { "epoch": 2.619790645005974, "grad_norm": 3.218444585800171, "learning_rate": 5.453916803684739e-06, "loss": 0.1157, "step": 440730 }, { "epoch": 2.6198500870826424, "grad_norm": 4.133509159088135, "learning_rate": 5.453710167970992e-06, "loss": 0.1278, "step": 440740 }, { "epoch": 2.619909529159311, "grad_norm": 4.366571426391602, "learning_rate": 5.453503531475904e-06, "loss": 0.123, "step": 440750 }, { "epoch": 2.619968971235979, "grad_norm": 4.581612586975098, "learning_rate": 5.4532968941998285e-06, "loss": 0.1379, "step": 440760 }, { "epoch": 2.6200284133126477, "grad_norm": 4.026790618896484, "learning_rate": 5.453090256143121e-06, "loss": 0.1292, "step": 440770 }, { "epoch": 2.6200878553893157, "grad_norm": 2.950190305709839, "learning_rate": 5.452883617306138e-06, "loss": 0.1282, "step": 440780 }, { "epoch": 2.6201472974659845, "grad_norm": 3.91672945022583, "learning_rate": 5.452676977689236e-06, "loss": 0.1312, "step": 440790 }, { "epoch": 2.6202067395426525, "grad_norm": 3.7106292247772217, "learning_rate": 5.45247033729277e-06, "loss": 0.1302, "step": 440800 }, { "epoch": 2.620266181619321, "grad_norm": 5.499980449676514, "learning_rate": 5.452263696117096e-06, "loss": 0.139, "step": 440810 }, { "epoch": 2.6203256236959893, "grad_norm": 4.070193290710449, "learning_rate": 5.45205705416257e-06, "loss": 0.1128, "step": 440820 }, { "epoch": 2.6203850657726577, "grad_norm": 3.4061458110809326, "learning_rate": 5.451850411429548e-06, "loss": 0.1118, "step": 440830 }, { "epoch": 2.620444507849326, "grad_norm": 3.1161208152770996, "learning_rate": 5.451643767918384e-06, "loss": 0.1222, "step": 440840 }, { "epoch": 2.6205039499259946, "grad_norm": 4.76624870300293, "learning_rate": 5.451437123629437e-06, "loss": 0.1359, "step": 440850 }, { "epoch": 2.620563392002663, "grad_norm": 3.932513475418091, "learning_rate": 5.451230478563062e-06, "loss": 0.1343, "step": 440860 }, { "epoch": 2.6206228340793314, "grad_norm": 3.789555072784424, "learning_rate": 5.451023832719613e-06, "loss": 0.1263, "step": 440870 }, { "epoch": 2.620682276156, "grad_norm": 3.422978639602661, "learning_rate": 5.450817186099448e-06, "loss": 0.107, "step": 440880 }, { "epoch": 2.620741718232668, "grad_norm": 3.1771602630615234, "learning_rate": 5.450610538702923e-06, "loss": 0.1183, "step": 440890 }, { "epoch": 2.6208011603093366, "grad_norm": 4.199862480163574, "learning_rate": 5.4504038905303916e-06, "loss": 0.1182, "step": 440900 }, { "epoch": 2.620860602386005, "grad_norm": 4.144426345825195, "learning_rate": 5.450197241582211e-06, "loss": 0.1333, "step": 440910 }, { "epoch": 2.6209200444626735, "grad_norm": 3.989366292953491, "learning_rate": 5.449990591858737e-06, "loss": 0.1281, "step": 440920 }, { "epoch": 2.620979486539342, "grad_norm": 4.265218257904053, "learning_rate": 5.449783941360325e-06, "loss": 0.1229, "step": 440930 }, { "epoch": 2.6210389286160103, "grad_norm": 4.696815013885498, "learning_rate": 5.4495772900873315e-06, "loss": 0.1345, "step": 440940 }, { "epoch": 2.6210983706926783, "grad_norm": 3.876255512237549, "learning_rate": 5.449370638040113e-06, "loss": 0.1255, "step": 440950 }, { "epoch": 2.621157812769347, "grad_norm": 4.759334087371826, "learning_rate": 5.4491639852190245e-06, "loss": 0.1405, "step": 440960 }, { "epoch": 2.621217254846015, "grad_norm": 4.017645359039307, "learning_rate": 5.448957331624422e-06, "loss": 0.125, "step": 440970 }, { "epoch": 2.621276696922684, "grad_norm": 3.337695837020874, "learning_rate": 5.448750677256661e-06, "loss": 0.1086, "step": 440980 }, { "epoch": 2.621336138999352, "grad_norm": 4.694770812988281, "learning_rate": 5.448544022116099e-06, "loss": 0.1159, "step": 440990 }, { "epoch": 2.6213955810760203, "grad_norm": 4.197475910186768, "learning_rate": 5.448337366203089e-06, "loss": 0.1262, "step": 441000 }, { "epoch": 2.6214550231526887, "grad_norm": 3.613448143005371, "learning_rate": 5.44813070951799e-06, "loss": 0.1152, "step": 441010 }, { "epoch": 2.621514465229357, "grad_norm": 3.4148309230804443, "learning_rate": 5.447924052061156e-06, "loss": 0.1398, "step": 441020 }, { "epoch": 2.6215739073060256, "grad_norm": 5.7756476402282715, "learning_rate": 5.447717393832943e-06, "loss": 0.1324, "step": 441030 }, { "epoch": 2.621633349382694, "grad_norm": 4.623559474945068, "learning_rate": 5.4475107348337075e-06, "loss": 0.133, "step": 441040 }, { "epoch": 2.6216927914593624, "grad_norm": 4.353029727935791, "learning_rate": 5.447304075063804e-06, "loss": 0.1238, "step": 441050 }, { "epoch": 2.621752233536031, "grad_norm": 4.246432304382324, "learning_rate": 5.44709741452359e-06, "loss": 0.1147, "step": 441060 }, { "epoch": 2.6218116756126992, "grad_norm": 3.601043462753296, "learning_rate": 5.446890753213422e-06, "loss": 0.1293, "step": 441070 }, { "epoch": 2.6218711176893676, "grad_norm": 4.202717304229736, "learning_rate": 5.446684091133655e-06, "loss": 0.1274, "step": 441080 }, { "epoch": 2.621930559766036, "grad_norm": 3.822864294052124, "learning_rate": 5.446477428284642e-06, "loss": 0.1234, "step": 441090 }, { "epoch": 2.6219900018427045, "grad_norm": 3.901456594467163, "learning_rate": 5.446270764666745e-06, "loss": 0.1251, "step": 441100 }, { "epoch": 2.622049443919373, "grad_norm": 4.836416721343994, "learning_rate": 5.446064100280315e-06, "loss": 0.1289, "step": 441110 }, { "epoch": 2.6221088859960413, "grad_norm": 3.683724880218506, "learning_rate": 5.4458574351257095e-06, "loss": 0.127, "step": 441120 }, { "epoch": 2.6221683280727097, "grad_norm": 4.040224552154541, "learning_rate": 5.4456507692032835e-06, "loss": 0.1385, "step": 441130 }, { "epoch": 2.6222277701493777, "grad_norm": 7.164026737213135, "learning_rate": 5.445444102513396e-06, "loss": 0.1262, "step": 441140 }, { "epoch": 2.6222872122260465, "grad_norm": 3.76300048828125, "learning_rate": 5.445237435056398e-06, "loss": 0.1266, "step": 441150 }, { "epoch": 2.6223466543027145, "grad_norm": 4.566746711730957, "learning_rate": 5.445030766832647e-06, "loss": 0.1249, "step": 441160 }, { "epoch": 2.6224060963793834, "grad_norm": 2.9426052570343018, "learning_rate": 5.444824097842503e-06, "loss": 0.1385, "step": 441170 }, { "epoch": 2.6224655384560513, "grad_norm": 4.27315616607666, "learning_rate": 5.444617428086318e-06, "loss": 0.1317, "step": 441180 }, { "epoch": 2.6225249805327198, "grad_norm": 3.897651433944702, "learning_rate": 5.444410757564448e-06, "loss": 0.1286, "step": 441190 }, { "epoch": 2.622584422609388, "grad_norm": 3.936880111694336, "learning_rate": 5.44420408627725e-06, "loss": 0.1237, "step": 441200 }, { "epoch": 2.6226438646860566, "grad_norm": 4.290878772735596, "learning_rate": 5.44399741422508e-06, "loss": 0.1201, "step": 441210 }, { "epoch": 2.622703306762725, "grad_norm": 4.312650203704834, "learning_rate": 5.443790741408293e-06, "loss": 0.1144, "step": 441220 }, { "epoch": 2.6227627488393934, "grad_norm": 6.538777828216553, "learning_rate": 5.443584067827247e-06, "loss": 0.1307, "step": 441230 }, { "epoch": 2.622822190916062, "grad_norm": 3.4072279930114746, "learning_rate": 5.4433773934822945e-06, "loss": 0.1294, "step": 441240 }, { "epoch": 2.6228816329927302, "grad_norm": 3.619661331176758, "learning_rate": 5.443170718373793e-06, "loss": 0.1329, "step": 441250 }, { "epoch": 2.6229410750693987, "grad_norm": 4.9797773361206055, "learning_rate": 5.442964042502099e-06, "loss": 0.1405, "step": 441260 }, { "epoch": 2.623000517146067, "grad_norm": 4.080059051513672, "learning_rate": 5.4427573658675685e-06, "loss": 0.1202, "step": 441270 }, { "epoch": 2.6230599592227355, "grad_norm": 4.887577533721924, "learning_rate": 5.442550688470557e-06, "loss": 0.1303, "step": 441280 }, { "epoch": 2.623119401299404, "grad_norm": 3.453118085861206, "learning_rate": 5.44234401031142e-06, "loss": 0.1061, "step": 441290 }, { "epoch": 2.6231788433760723, "grad_norm": 4.7491278648376465, "learning_rate": 5.4421373313905135e-06, "loss": 0.1375, "step": 441300 }, { "epoch": 2.6232382854527407, "grad_norm": 5.786327362060547, "learning_rate": 5.441930651708195e-06, "loss": 0.1249, "step": 441310 }, { "epoch": 2.623297727529409, "grad_norm": 3.941385507583618, "learning_rate": 5.441723971264819e-06, "loss": 0.1285, "step": 441320 }, { "epoch": 2.623357169606077, "grad_norm": 3.643364429473877, "learning_rate": 5.441517290060741e-06, "loss": 0.1219, "step": 441330 }, { "epoch": 2.623416611682746, "grad_norm": 4.685299396514893, "learning_rate": 5.441310608096317e-06, "loss": 0.1419, "step": 441340 }, { "epoch": 2.623476053759414, "grad_norm": 4.566357135772705, "learning_rate": 5.441103925371904e-06, "loss": 0.1382, "step": 441350 }, { "epoch": 2.6235354958360824, "grad_norm": 4.50856876373291, "learning_rate": 5.440897241887858e-06, "loss": 0.1228, "step": 441360 }, { "epoch": 2.623594937912751, "grad_norm": 4.6362714767456055, "learning_rate": 5.440690557644534e-06, "loss": 0.1269, "step": 441370 }, { "epoch": 2.623654379989419, "grad_norm": 4.470670223236084, "learning_rate": 5.440483872642288e-06, "loss": 0.1373, "step": 441380 }, { "epoch": 2.6237138220660876, "grad_norm": 2.9062066078186035, "learning_rate": 5.440277186881475e-06, "loss": 0.125, "step": 441390 }, { "epoch": 2.623773264142756, "grad_norm": 5.2637128829956055, "learning_rate": 5.440070500362455e-06, "loss": 0.119, "step": 441400 }, { "epoch": 2.6238327062194244, "grad_norm": 4.585862636566162, "learning_rate": 5.439863813085579e-06, "loss": 0.1013, "step": 441410 }, { "epoch": 2.623892148296093, "grad_norm": 4.788842678070068, "learning_rate": 5.439657125051206e-06, "loss": 0.1346, "step": 441420 }, { "epoch": 2.6239515903727613, "grad_norm": 3.2996597290039062, "learning_rate": 5.43945043625969e-06, "loss": 0.1467, "step": 441430 }, { "epoch": 2.6240110324494297, "grad_norm": 3.765613555908203, "learning_rate": 5.439243746711389e-06, "loss": 0.1366, "step": 441440 }, { "epoch": 2.624070474526098, "grad_norm": 3.2207839488983154, "learning_rate": 5.439037056406658e-06, "loss": 0.1245, "step": 441450 }, { "epoch": 2.6241299166027665, "grad_norm": 4.61435604095459, "learning_rate": 5.4388303653458514e-06, "loss": 0.1396, "step": 441460 }, { "epoch": 2.624189358679435, "grad_norm": 4.349207878112793, "learning_rate": 5.4386236735293275e-06, "loss": 0.1377, "step": 441470 }, { "epoch": 2.6242488007561033, "grad_norm": 5.434690952301025, "learning_rate": 5.438416980957441e-06, "loss": 0.1321, "step": 441480 }, { "epoch": 2.6243082428327718, "grad_norm": 3.5936803817749023, "learning_rate": 5.438210287630548e-06, "loss": 0.1297, "step": 441490 }, { "epoch": 2.6243676849094397, "grad_norm": 4.264801979064941, "learning_rate": 5.438003593549005e-06, "loss": 0.1155, "step": 441500 }, { "epoch": 2.6244271269861086, "grad_norm": 3.98947811126709, "learning_rate": 5.437796898713168e-06, "loss": 0.1153, "step": 441510 }, { "epoch": 2.6244865690627766, "grad_norm": 3.275073289871216, "learning_rate": 5.437590203123391e-06, "loss": 0.107, "step": 441520 }, { "epoch": 2.6245460111394454, "grad_norm": 3.0135161876678467, "learning_rate": 5.4373835067800325e-06, "loss": 0.1351, "step": 441530 }, { "epoch": 2.6246054532161134, "grad_norm": 4.446418285369873, "learning_rate": 5.4371768096834474e-06, "loss": 0.1155, "step": 441540 }, { "epoch": 2.624664895292782, "grad_norm": 3.4365804195404053, "learning_rate": 5.4369701118339915e-06, "loss": 0.1119, "step": 441550 }, { "epoch": 2.62472433736945, "grad_norm": 4.599764823913574, "learning_rate": 5.436763413232021e-06, "loss": 0.1468, "step": 441560 }, { "epoch": 2.6247837794461186, "grad_norm": 5.835772514343262, "learning_rate": 5.436556713877893e-06, "loss": 0.134, "step": 441570 }, { "epoch": 2.624843221522787, "grad_norm": 3.4145803451538086, "learning_rate": 5.43635001377196e-06, "loss": 0.1287, "step": 441580 }, { "epoch": 2.6249026635994555, "grad_norm": 2.7638049125671387, "learning_rate": 5.436143312914581e-06, "loss": 0.1144, "step": 441590 }, { "epoch": 2.624962105676124, "grad_norm": 4.136035442352295, "learning_rate": 5.435936611306112e-06, "loss": 0.1186, "step": 441600 }, { "epoch": 2.6250215477527923, "grad_norm": 4.939313888549805, "learning_rate": 5.435729908946907e-06, "loss": 0.1535, "step": 441610 }, { "epoch": 2.6250809898294607, "grad_norm": 3.873575448989868, "learning_rate": 5.435523205837323e-06, "loss": 0.1457, "step": 441620 }, { "epoch": 2.625140431906129, "grad_norm": 4.704465389251709, "learning_rate": 5.435316501977717e-06, "loss": 0.1261, "step": 441630 }, { "epoch": 2.6251998739827975, "grad_norm": 4.968201637268066, "learning_rate": 5.4351097973684455e-06, "loss": 0.1359, "step": 441640 }, { "epoch": 2.625259316059466, "grad_norm": 4.23713493347168, "learning_rate": 5.43490309200986e-06, "loss": 0.1247, "step": 441650 }, { "epoch": 2.6253187581361344, "grad_norm": 3.8541903495788574, "learning_rate": 5.43469638590232e-06, "loss": 0.1226, "step": 441660 }, { "epoch": 2.6253782002128028, "grad_norm": 4.969883441925049, "learning_rate": 5.434489679046183e-06, "loss": 0.1324, "step": 441670 }, { "epoch": 2.625437642289471, "grad_norm": 4.43595027923584, "learning_rate": 5.434282971441801e-06, "loss": 0.1313, "step": 441680 }, { "epoch": 2.625497084366139, "grad_norm": 3.140634059906006, "learning_rate": 5.434076263089532e-06, "loss": 0.1264, "step": 441690 }, { "epoch": 2.625556526442808, "grad_norm": 4.264312267303467, "learning_rate": 5.433869553989735e-06, "loss": 0.1226, "step": 441700 }, { "epoch": 2.625615968519476, "grad_norm": 4.943999290466309, "learning_rate": 5.433662844142758e-06, "loss": 0.1463, "step": 441710 }, { "epoch": 2.625675410596145, "grad_norm": 3.51296329498291, "learning_rate": 5.433456133548964e-06, "loss": 0.1132, "step": 441720 }, { "epoch": 2.625734852672813, "grad_norm": 4.478948593139648, "learning_rate": 5.433249422208707e-06, "loss": 0.1333, "step": 441730 }, { "epoch": 2.6257942947494812, "grad_norm": 4.432088851928711, "learning_rate": 5.4330427101223425e-06, "loss": 0.1215, "step": 441740 }, { "epoch": 2.6258537368261496, "grad_norm": 4.929368019104004, "learning_rate": 5.432835997290228e-06, "loss": 0.118, "step": 441750 }, { "epoch": 2.625913178902818, "grad_norm": 3.690690040588379, "learning_rate": 5.432629283712717e-06, "loss": 0.1209, "step": 441760 }, { "epoch": 2.6259726209794865, "grad_norm": 2.8730578422546387, "learning_rate": 5.432422569390167e-06, "loss": 0.1311, "step": 441770 }, { "epoch": 2.626032063056155, "grad_norm": 5.22221565246582, "learning_rate": 5.432215854322934e-06, "loss": 0.1331, "step": 441780 }, { "epoch": 2.6260915051328233, "grad_norm": 5.021297454833984, "learning_rate": 5.432009138511374e-06, "loss": 0.1174, "step": 441790 }, { "epoch": 2.6261509472094917, "grad_norm": 3.354672431945801, "learning_rate": 5.431802421955843e-06, "loss": 0.1233, "step": 441800 }, { "epoch": 2.62621038928616, "grad_norm": 5.073788642883301, "learning_rate": 5.431595704656695e-06, "loss": 0.1353, "step": 441810 }, { "epoch": 2.6262698313628285, "grad_norm": 4.301145553588867, "learning_rate": 5.431388986614288e-06, "loss": 0.1242, "step": 441820 }, { "epoch": 2.626329273439497, "grad_norm": 4.054189205169678, "learning_rate": 5.431182267828978e-06, "loss": 0.1236, "step": 441830 }, { "epoch": 2.6263887155161654, "grad_norm": 3.627657890319824, "learning_rate": 5.430975548301122e-06, "loss": 0.1316, "step": 441840 }, { "epoch": 2.626448157592834, "grad_norm": 4.183353424072266, "learning_rate": 5.430768828031073e-06, "loss": 0.1214, "step": 441850 }, { "epoch": 2.626507599669502, "grad_norm": 4.881599426269531, "learning_rate": 5.43056210701919e-06, "loss": 0.1119, "step": 441860 }, { "epoch": 2.6265670417461706, "grad_norm": 4.528415203094482, "learning_rate": 5.430355385265826e-06, "loss": 0.1248, "step": 441870 }, { "epoch": 2.6266264838228386, "grad_norm": 3.626903533935547, "learning_rate": 5.430148662771341e-06, "loss": 0.1188, "step": 441880 }, { "epoch": 2.6266859258995074, "grad_norm": 3.2928476333618164, "learning_rate": 5.429941939536087e-06, "loss": 0.1257, "step": 441890 }, { "epoch": 2.6267453679761754, "grad_norm": 4.616174697875977, "learning_rate": 5.429735215560422e-06, "loss": 0.1306, "step": 441900 }, { "epoch": 2.6268048100528443, "grad_norm": 3.908950090408325, "learning_rate": 5.429528490844702e-06, "loss": 0.122, "step": 441910 }, { "epoch": 2.6268642521295122, "grad_norm": 5.541798114776611, "learning_rate": 5.4293217653892835e-06, "loss": 0.1464, "step": 441920 }, { "epoch": 2.6269236942061807, "grad_norm": 5.044025897979736, "learning_rate": 5.4291150391945205e-06, "loss": 0.1178, "step": 441930 }, { "epoch": 2.626983136282849, "grad_norm": 5.280254364013672, "learning_rate": 5.428908312260769e-06, "loss": 0.1256, "step": 441940 }, { "epoch": 2.6270425783595175, "grad_norm": 4.8026933670043945, "learning_rate": 5.428701584588388e-06, "loss": 0.1226, "step": 441950 }, { "epoch": 2.627102020436186, "grad_norm": 4.564424514770508, "learning_rate": 5.428494856177732e-06, "loss": 0.1192, "step": 441960 }, { "epoch": 2.6271614625128543, "grad_norm": 4.364817142486572, "learning_rate": 5.428288127029156e-06, "loss": 0.1154, "step": 441970 }, { "epoch": 2.6272209045895227, "grad_norm": 5.169671058654785, "learning_rate": 5.428081397143017e-06, "loss": 0.116, "step": 441980 }, { "epoch": 2.627280346666191, "grad_norm": 3.761078119277954, "learning_rate": 5.42787466651967e-06, "loss": 0.1203, "step": 441990 }, { "epoch": 2.6273397887428596, "grad_norm": 4.331447601318359, "learning_rate": 5.427667935159472e-06, "loss": 0.1156, "step": 442000 }, { "epoch": 2.627399230819528, "grad_norm": 3.152751922607422, "learning_rate": 5.42746120306278e-06, "loss": 0.1301, "step": 442010 }, { "epoch": 2.6274586728961964, "grad_norm": 5.149926662445068, "learning_rate": 5.427254470229948e-06, "loss": 0.1294, "step": 442020 }, { "epoch": 2.627518114972865, "grad_norm": 3.6145448684692383, "learning_rate": 5.427047736661331e-06, "loss": 0.1288, "step": 442030 }, { "epoch": 2.627577557049533, "grad_norm": 4.520243167877197, "learning_rate": 5.426841002357289e-06, "loss": 0.1007, "step": 442040 }, { "epoch": 2.6276369991262016, "grad_norm": 3.5913214683532715, "learning_rate": 5.426634267318176e-06, "loss": 0.1327, "step": 442050 }, { "epoch": 2.62769644120287, "grad_norm": 4.1501970291137695, "learning_rate": 5.426427531544347e-06, "loss": 0.1259, "step": 442060 }, { "epoch": 2.627755883279538, "grad_norm": 4.572415351867676, "learning_rate": 5.426220795036159e-06, "loss": 0.1211, "step": 442070 }, { "epoch": 2.627815325356207, "grad_norm": 4.834953308105469, "learning_rate": 5.426014057793969e-06, "loss": 0.1136, "step": 442080 }, { "epoch": 2.627874767432875, "grad_norm": 3.676583766937256, "learning_rate": 5.425807319818132e-06, "loss": 0.1262, "step": 442090 }, { "epoch": 2.6279342095095433, "grad_norm": 5.269718647003174, "learning_rate": 5.425600581109002e-06, "loss": 0.1241, "step": 442100 }, { "epoch": 2.6279936515862117, "grad_norm": 3.9332520961761475, "learning_rate": 5.425393841666938e-06, "loss": 0.1265, "step": 442110 }, { "epoch": 2.62805309366288, "grad_norm": 3.040614604949951, "learning_rate": 5.425187101492296e-06, "loss": 0.1318, "step": 442120 }, { "epoch": 2.6281125357395485, "grad_norm": 4.360426425933838, "learning_rate": 5.42498036058543e-06, "loss": 0.1572, "step": 442130 }, { "epoch": 2.628171977816217, "grad_norm": 3.58772611618042, "learning_rate": 5.424773618946697e-06, "loss": 0.1185, "step": 442140 }, { "epoch": 2.6282314198928853, "grad_norm": 3.6290409564971924, "learning_rate": 5.424566876576454e-06, "loss": 0.1307, "step": 442150 }, { "epoch": 2.6282908619695537, "grad_norm": 5.7440900802612305, "learning_rate": 5.424360133475055e-06, "loss": 0.1298, "step": 442160 }, { "epoch": 2.628350304046222, "grad_norm": 4.581757068634033, "learning_rate": 5.424153389642858e-06, "loss": 0.1369, "step": 442170 }, { "epoch": 2.6284097461228906, "grad_norm": 4.185320854187012, "learning_rate": 5.423946645080218e-06, "loss": 0.1344, "step": 442180 }, { "epoch": 2.628469188199559, "grad_norm": 3.1486406326293945, "learning_rate": 5.423739899787493e-06, "loss": 0.1352, "step": 442190 }, { "epoch": 2.6285286302762274, "grad_norm": 4.190528392791748, "learning_rate": 5.4235331537650335e-06, "loss": 0.1186, "step": 442200 }, { "epoch": 2.628588072352896, "grad_norm": 3.0035994052886963, "learning_rate": 5.423326407013203e-06, "loss": 0.1265, "step": 442210 }, { "epoch": 2.6286475144295642, "grad_norm": 4.155712127685547, "learning_rate": 5.4231196595323535e-06, "loss": 0.1079, "step": 442220 }, { "epoch": 2.6287069565062327, "grad_norm": 2.5576751232147217, "learning_rate": 5.42291291132284e-06, "loss": 0.1282, "step": 442230 }, { "epoch": 2.6287663985829006, "grad_norm": 4.694210052490234, "learning_rate": 5.4227061623850196e-06, "loss": 0.1203, "step": 442240 }, { "epoch": 2.6288258406595695, "grad_norm": 5.6391167640686035, "learning_rate": 5.4224994127192506e-06, "loss": 0.1385, "step": 442250 }, { "epoch": 2.6288852827362374, "grad_norm": 5.14245080947876, "learning_rate": 5.422292662325885e-06, "loss": 0.1364, "step": 442260 }, { "epoch": 2.6289447248129063, "grad_norm": 3.5664687156677246, "learning_rate": 5.422085911205282e-06, "loss": 0.1206, "step": 442270 }, { "epoch": 2.6290041668895743, "grad_norm": 3.20261812210083, "learning_rate": 5.421879159357798e-06, "loss": 0.1306, "step": 442280 }, { "epoch": 2.6290636089662427, "grad_norm": 3.6286823749542236, "learning_rate": 5.421672406783787e-06, "loss": 0.1221, "step": 442290 }, { "epoch": 2.629123051042911, "grad_norm": 4.690208435058594, "learning_rate": 5.421465653483605e-06, "loss": 0.1196, "step": 442300 }, { "epoch": 2.6291824931195795, "grad_norm": 4.107212543487549, "learning_rate": 5.42125889945761e-06, "loss": 0.1195, "step": 442310 }, { "epoch": 2.629241935196248, "grad_norm": 5.130527019500732, "learning_rate": 5.421052144706157e-06, "loss": 0.1226, "step": 442320 }, { "epoch": 2.6293013772729164, "grad_norm": 3.3306350708007812, "learning_rate": 5.420845389229601e-06, "loss": 0.1289, "step": 442330 }, { "epoch": 2.6293608193495848, "grad_norm": 4.0823540687561035, "learning_rate": 5.420638633028299e-06, "loss": 0.1437, "step": 442340 }, { "epoch": 2.629420261426253, "grad_norm": 3.733104944229126, "learning_rate": 5.420431876102608e-06, "loss": 0.1101, "step": 442350 }, { "epoch": 2.6294797035029216, "grad_norm": 3.6258397102355957, "learning_rate": 5.420225118452882e-06, "loss": 0.1257, "step": 442360 }, { "epoch": 2.62953914557959, "grad_norm": 3.839308261871338, "learning_rate": 5.420018360079479e-06, "loss": 0.1366, "step": 442370 }, { "epoch": 2.6295985876562584, "grad_norm": 4.331686973571777, "learning_rate": 5.419811600982754e-06, "loss": 0.1077, "step": 442380 }, { "epoch": 2.629658029732927, "grad_norm": 2.8142285346984863, "learning_rate": 5.419604841163062e-06, "loss": 0.1239, "step": 442390 }, { "epoch": 2.6297174718095953, "grad_norm": 3.6325087547302246, "learning_rate": 5.4193980806207625e-06, "loss": 0.1256, "step": 442400 }, { "epoch": 2.6297769138862637, "grad_norm": 4.378222465515137, "learning_rate": 5.41919131935621e-06, "loss": 0.1336, "step": 442410 }, { "epoch": 2.629836355962932, "grad_norm": 3.5839176177978516, "learning_rate": 5.418984557369758e-06, "loss": 0.1382, "step": 442420 }, { "epoch": 2.6298957980396, "grad_norm": 5.359278678894043, "learning_rate": 5.418777794661765e-06, "loss": 0.1399, "step": 442430 }, { "epoch": 2.629955240116269, "grad_norm": 4.766524791717529, "learning_rate": 5.418571031232588e-06, "loss": 0.1427, "step": 442440 }, { "epoch": 2.630014682192937, "grad_norm": 3.9132723808288574, "learning_rate": 5.418364267082581e-06, "loss": 0.1242, "step": 442450 }, { "epoch": 2.6300741242696057, "grad_norm": 3.7259130477905273, "learning_rate": 5.4181575022121e-06, "loss": 0.126, "step": 442460 }, { "epoch": 2.6301335663462737, "grad_norm": 4.250237464904785, "learning_rate": 5.417950736621503e-06, "loss": 0.1204, "step": 442470 }, { "epoch": 2.630193008422942, "grad_norm": 3.743940830230713, "learning_rate": 5.417743970311143e-06, "loss": 0.1404, "step": 442480 }, { "epoch": 2.6302524504996105, "grad_norm": 4.231568336486816, "learning_rate": 5.41753720328138e-06, "loss": 0.136, "step": 442490 }, { "epoch": 2.630311892576279, "grad_norm": 3.982469320297241, "learning_rate": 5.417330435532567e-06, "loss": 0.1269, "step": 442500 }, { "epoch": 2.6303713346529474, "grad_norm": 4.000174045562744, "learning_rate": 5.417123667065063e-06, "loss": 0.1201, "step": 442510 }, { "epoch": 2.630430776729616, "grad_norm": 3.637028217315674, "learning_rate": 5.416916897879221e-06, "loss": 0.1235, "step": 442520 }, { "epoch": 2.630490218806284, "grad_norm": 3.5815248489379883, "learning_rate": 5.4167101279753976e-06, "loss": 0.1131, "step": 442530 }, { "epoch": 2.6305496608829526, "grad_norm": 3.6486284732818604, "learning_rate": 5.416503357353951e-06, "loss": 0.1194, "step": 442540 }, { "epoch": 2.630609102959621, "grad_norm": 4.178891181945801, "learning_rate": 5.416296586015235e-06, "loss": 0.1213, "step": 442550 }, { "epoch": 2.6306685450362894, "grad_norm": 5.29690408706665, "learning_rate": 5.416089813959608e-06, "loss": 0.1291, "step": 442560 }, { "epoch": 2.630727987112958, "grad_norm": 4.158326625823975, "learning_rate": 5.4158830411874246e-06, "loss": 0.1499, "step": 442570 }, { "epoch": 2.6307874291896263, "grad_norm": 4.601527214050293, "learning_rate": 5.415676267699039e-06, "loss": 0.117, "step": 442580 }, { "epoch": 2.6308468712662947, "grad_norm": 4.162765026092529, "learning_rate": 5.415469493494809e-06, "loss": 0.1139, "step": 442590 }, { "epoch": 2.630906313342963, "grad_norm": 5.275815486907959, "learning_rate": 5.415262718575093e-06, "loss": 0.1343, "step": 442600 }, { "epoch": 2.6309657554196315, "grad_norm": 4.177746772766113, "learning_rate": 5.415055942940245e-06, "loss": 0.1252, "step": 442610 }, { "epoch": 2.6310251974962995, "grad_norm": 3.4886209964752197, "learning_rate": 5.41484916659062e-06, "loss": 0.1275, "step": 442620 }, { "epoch": 2.6310846395729683, "grad_norm": 3.7589094638824463, "learning_rate": 5.414642389526575e-06, "loss": 0.1149, "step": 442630 }, { "epoch": 2.6311440816496363, "grad_norm": 3.0452558994293213, "learning_rate": 5.414435611748469e-06, "loss": 0.1333, "step": 442640 }, { "epoch": 2.631203523726305, "grad_norm": 4.402944087982178, "learning_rate": 5.4142288332566515e-06, "loss": 0.1274, "step": 442650 }, { "epoch": 2.631262965802973, "grad_norm": 5.418859004974365, "learning_rate": 5.414022054051485e-06, "loss": 0.1141, "step": 442660 }, { "epoch": 2.6313224078796416, "grad_norm": 4.7837982177734375, "learning_rate": 5.413815274133324e-06, "loss": 0.1102, "step": 442670 }, { "epoch": 2.63138184995631, "grad_norm": 3.864631414413452, "learning_rate": 5.413608493502521e-06, "loss": 0.1207, "step": 442680 }, { "epoch": 2.6314412920329784, "grad_norm": 4.701960563659668, "learning_rate": 5.413401712159437e-06, "loss": 0.12, "step": 442690 }, { "epoch": 2.631500734109647, "grad_norm": 4.217090606689453, "learning_rate": 5.413194930104424e-06, "loss": 0.1297, "step": 442700 }, { "epoch": 2.631560176186315, "grad_norm": 5.753244876861572, "learning_rate": 5.4129881473378425e-06, "loss": 0.1295, "step": 442710 }, { "epoch": 2.6316196182629836, "grad_norm": 2.9827768802642822, "learning_rate": 5.412781363860044e-06, "loss": 0.1121, "step": 442720 }, { "epoch": 2.631679060339652, "grad_norm": 4.183511257171631, "learning_rate": 5.412574579671388e-06, "loss": 0.1103, "step": 442730 }, { "epoch": 2.6317385024163205, "grad_norm": 4.298983097076416, "learning_rate": 5.412367794772229e-06, "loss": 0.1137, "step": 442740 }, { "epoch": 2.631797944492989, "grad_norm": 5.131687164306641, "learning_rate": 5.4121610091629225e-06, "loss": 0.1458, "step": 442750 }, { "epoch": 2.6318573865696573, "grad_norm": 4.470088481903076, "learning_rate": 5.411954222843827e-06, "loss": 0.1185, "step": 442760 }, { "epoch": 2.6319168286463257, "grad_norm": 5.0877203941345215, "learning_rate": 5.411747435815297e-06, "loss": 0.1336, "step": 442770 }, { "epoch": 2.631976270722994, "grad_norm": 4.986572265625, "learning_rate": 5.411540648077688e-06, "loss": 0.1281, "step": 442780 }, { "epoch": 2.6320357127996625, "grad_norm": 3.3159360885620117, "learning_rate": 5.411333859631357e-06, "loss": 0.1344, "step": 442790 }, { "epoch": 2.632095154876331, "grad_norm": 3.7474405765533447, "learning_rate": 5.411127070476661e-06, "loss": 0.1224, "step": 442800 }, { "epoch": 2.632154596952999, "grad_norm": 5.391785621643066, "learning_rate": 5.410920280613954e-06, "loss": 0.1176, "step": 442810 }, { "epoch": 2.6322140390296678, "grad_norm": 4.88923454284668, "learning_rate": 5.4107134900435936e-06, "loss": 0.141, "step": 442820 }, { "epoch": 2.6322734811063357, "grad_norm": 3.1035070419311523, "learning_rate": 5.410506698765935e-06, "loss": 0.1248, "step": 442830 }, { "epoch": 2.632332923183004, "grad_norm": 4.630716323852539, "learning_rate": 5.410299906781335e-06, "loss": 0.1084, "step": 442840 }, { "epoch": 2.6323923652596726, "grad_norm": 3.7683181762695312, "learning_rate": 5.41009311409015e-06, "loss": 0.1215, "step": 442850 }, { "epoch": 2.632451807336341, "grad_norm": 5.989762783050537, "learning_rate": 5.409886320692737e-06, "loss": 0.1477, "step": 442860 }, { "epoch": 2.6325112494130094, "grad_norm": 4.3626556396484375, "learning_rate": 5.40967952658945e-06, "loss": 0.1294, "step": 442870 }, { "epoch": 2.632570691489678, "grad_norm": 3.9028899669647217, "learning_rate": 5.409472731780645e-06, "loss": 0.0988, "step": 442880 }, { "epoch": 2.6326301335663462, "grad_norm": 3.895878314971924, "learning_rate": 5.40926593626668e-06, "loss": 0.1239, "step": 442890 }, { "epoch": 2.6326895756430146, "grad_norm": 3.6322591304779053, "learning_rate": 5.40905914004791e-06, "loss": 0.132, "step": 442900 }, { "epoch": 2.632749017719683, "grad_norm": 5.355371475219727, "learning_rate": 5.4088523431246905e-06, "loss": 0.1412, "step": 442910 }, { "epoch": 2.6328084597963515, "grad_norm": 4.91279411315918, "learning_rate": 5.40864554549738e-06, "loss": 0.1178, "step": 442920 }, { "epoch": 2.63286790187302, "grad_norm": 4.80894136428833, "learning_rate": 5.4084387471663325e-06, "loss": 0.1455, "step": 442930 }, { "epoch": 2.6329273439496883, "grad_norm": 3.247710704803467, "learning_rate": 5.408231948131905e-06, "loss": 0.1196, "step": 442940 }, { "epoch": 2.6329867860263567, "grad_norm": 5.2332539558410645, "learning_rate": 5.408025148394452e-06, "loss": 0.1327, "step": 442950 }, { "epoch": 2.633046228103025, "grad_norm": 3.784322738647461, "learning_rate": 5.407818347954332e-06, "loss": 0.1146, "step": 442960 }, { "epoch": 2.6331056701796935, "grad_norm": 5.304728984832764, "learning_rate": 5.4076115468119e-06, "loss": 0.1228, "step": 442970 }, { "epoch": 2.6331651122563615, "grad_norm": 3.6930925846099854, "learning_rate": 5.407404744967513e-06, "loss": 0.1216, "step": 442980 }, { "epoch": 2.6332245543330304, "grad_norm": 6.8511481285095215, "learning_rate": 5.407197942421526e-06, "loss": 0.1199, "step": 442990 }, { "epoch": 2.6332839964096983, "grad_norm": 3.9773950576782227, "learning_rate": 5.406991139174296e-06, "loss": 0.1081, "step": 443000 }, { "epoch": 2.633343438486367, "grad_norm": 3.640211582183838, "learning_rate": 5.406784335226177e-06, "loss": 0.1119, "step": 443010 }, { "epoch": 2.633402880563035, "grad_norm": 3.469532012939453, "learning_rate": 5.4065775305775296e-06, "loss": 0.1207, "step": 443020 }, { "epoch": 2.6334623226397036, "grad_norm": 4.909849643707275, "learning_rate": 5.406370725228705e-06, "loss": 0.1225, "step": 443030 }, { "epoch": 2.633521764716372, "grad_norm": 4.824661731719971, "learning_rate": 5.406163919180061e-06, "loss": 0.126, "step": 443040 }, { "epoch": 2.6335812067930404, "grad_norm": 4.8631768226623535, "learning_rate": 5.405957112431955e-06, "loss": 0.137, "step": 443050 }, { "epoch": 2.633640648869709, "grad_norm": 4.306930065155029, "learning_rate": 5.405750304984744e-06, "loss": 0.1272, "step": 443060 }, { "epoch": 2.6337000909463772, "grad_norm": 3.8437769412994385, "learning_rate": 5.40554349683878e-06, "loss": 0.1141, "step": 443070 }, { "epoch": 2.6337595330230457, "grad_norm": 3.7187156677246094, "learning_rate": 5.405336687994424e-06, "loss": 0.1136, "step": 443080 }, { "epoch": 2.633818975099714, "grad_norm": 4.426726341247559, "learning_rate": 5.405129878452029e-06, "loss": 0.1289, "step": 443090 }, { "epoch": 2.6338784171763825, "grad_norm": 3.3563363552093506, "learning_rate": 5.404923068211951e-06, "loss": 0.1107, "step": 443100 }, { "epoch": 2.633937859253051, "grad_norm": 3.509066581726074, "learning_rate": 5.404716257274548e-06, "loss": 0.1353, "step": 443110 }, { "epoch": 2.6339973013297193, "grad_norm": 4.001096248626709, "learning_rate": 5.404509445640176e-06, "loss": 0.1199, "step": 443120 }, { "epoch": 2.6340567434063877, "grad_norm": 4.10197639465332, "learning_rate": 5.4043026333091905e-06, "loss": 0.1157, "step": 443130 }, { "epoch": 2.634116185483056, "grad_norm": 3.4804885387420654, "learning_rate": 5.404095820281945e-06, "loss": 0.1278, "step": 443140 }, { "epoch": 2.6341756275597246, "grad_norm": 3.881103038787842, "learning_rate": 5.403889006558801e-06, "loss": 0.1341, "step": 443150 }, { "epoch": 2.634235069636393, "grad_norm": 2.952977418899536, "learning_rate": 5.403682192140111e-06, "loss": 0.1248, "step": 443160 }, { "epoch": 2.634294511713061, "grad_norm": 3.574063301086426, "learning_rate": 5.4034753770262326e-06, "loss": 0.1344, "step": 443170 }, { "epoch": 2.63435395378973, "grad_norm": 4.284605503082275, "learning_rate": 5.403268561217522e-06, "loss": 0.1332, "step": 443180 }, { "epoch": 2.6344133958663978, "grad_norm": 5.183691024780273, "learning_rate": 5.403061744714334e-06, "loss": 0.1223, "step": 443190 }, { "epoch": 2.6344728379430666, "grad_norm": 3.089350700378418, "learning_rate": 5.402854927517025e-06, "loss": 0.1257, "step": 443200 }, { "epoch": 2.6345322800197346, "grad_norm": 4.017244338989258, "learning_rate": 5.402648109625952e-06, "loss": 0.1133, "step": 443210 }, { "epoch": 2.634591722096403, "grad_norm": 3.661539077758789, "learning_rate": 5.4024412910414725e-06, "loss": 0.1154, "step": 443220 }, { "epoch": 2.6346511641730714, "grad_norm": 3.583557367324829, "learning_rate": 5.402234471763939e-06, "loss": 0.1189, "step": 443230 }, { "epoch": 2.63471060624974, "grad_norm": 3.6043176651000977, "learning_rate": 5.402027651793711e-06, "loss": 0.1184, "step": 443240 }, { "epoch": 2.6347700483264083, "grad_norm": 4.880466461181641, "learning_rate": 5.401820831131141e-06, "loss": 0.1333, "step": 443250 }, { "epoch": 2.6348294904030767, "grad_norm": 3.8911280632019043, "learning_rate": 5.4016140097765915e-06, "loss": 0.1155, "step": 443260 }, { "epoch": 2.634888932479745, "grad_norm": 3.9842658042907715, "learning_rate": 5.401407187730412e-06, "loss": 0.1223, "step": 443270 }, { "epoch": 2.6349483745564135, "grad_norm": 4.002656936645508, "learning_rate": 5.4012003649929624e-06, "loss": 0.1238, "step": 443280 }, { "epoch": 2.635007816633082, "grad_norm": 3.104727029800415, "learning_rate": 5.400993541564597e-06, "loss": 0.1083, "step": 443290 }, { "epoch": 2.6350672587097503, "grad_norm": 4.832464694976807, "learning_rate": 5.400786717445674e-06, "loss": 0.1506, "step": 443300 }, { "epoch": 2.6351267007864188, "grad_norm": 3.901001453399658, "learning_rate": 5.4005798926365486e-06, "loss": 0.1234, "step": 443310 }, { "epoch": 2.635186142863087, "grad_norm": 3.7194058895111084, "learning_rate": 5.400373067137577e-06, "loss": 0.1215, "step": 443320 }, { "epoch": 2.6352455849397556, "grad_norm": 4.259245872497559, "learning_rate": 5.400166240949113e-06, "loss": 0.1164, "step": 443330 }, { "epoch": 2.635305027016424, "grad_norm": 3.353253126144409, "learning_rate": 5.399959414071517e-06, "loss": 0.1221, "step": 443340 }, { "epoch": 2.6353644690930924, "grad_norm": 3.31067156791687, "learning_rate": 5.3997525865051435e-06, "loss": 0.115, "step": 443350 }, { "epoch": 2.6354239111697604, "grad_norm": 3.1237192153930664, "learning_rate": 5.399545758250346e-06, "loss": 0.1162, "step": 443360 }, { "epoch": 2.6354833532464292, "grad_norm": 3.3915092945098877, "learning_rate": 5.399338929307484e-06, "loss": 0.1124, "step": 443370 }, { "epoch": 2.635542795323097, "grad_norm": 3.955317974090576, "learning_rate": 5.399132099676913e-06, "loss": 0.1248, "step": 443380 }, { "epoch": 2.635602237399766, "grad_norm": 3.803016424179077, "learning_rate": 5.39892526935899e-06, "loss": 0.1236, "step": 443390 }, { "epoch": 2.635661679476434, "grad_norm": 3.4041075706481934, "learning_rate": 5.398718438354069e-06, "loss": 0.1169, "step": 443400 }, { "epoch": 2.6357211215531025, "grad_norm": 3.1935300827026367, "learning_rate": 5.398511606662508e-06, "loss": 0.1132, "step": 443410 }, { "epoch": 2.635780563629771, "grad_norm": 4.665421009063721, "learning_rate": 5.398304774284663e-06, "loss": 0.1397, "step": 443420 }, { "epoch": 2.6358400057064393, "grad_norm": 5.196128845214844, "learning_rate": 5.398097941220888e-06, "loss": 0.1289, "step": 443430 }, { "epoch": 2.6358994477831077, "grad_norm": 3.950970411300659, "learning_rate": 5.397891107471541e-06, "loss": 0.1232, "step": 443440 }, { "epoch": 2.635958889859776, "grad_norm": 3.548654079437256, "learning_rate": 5.39768427303698e-06, "loss": 0.1201, "step": 443450 }, { "epoch": 2.6360183319364445, "grad_norm": 3.6729042530059814, "learning_rate": 5.397477437917557e-06, "loss": 0.1324, "step": 443460 }, { "epoch": 2.636077774013113, "grad_norm": 3.565141201019287, "learning_rate": 5.39727060211363e-06, "loss": 0.1348, "step": 443470 }, { "epoch": 2.6361372160897814, "grad_norm": 5.792318344116211, "learning_rate": 5.397063765625557e-06, "loss": 0.1485, "step": 443480 }, { "epoch": 2.6361966581664498, "grad_norm": 4.104966640472412, "learning_rate": 5.396856928453693e-06, "loss": 0.1024, "step": 443490 }, { "epoch": 2.636256100243118, "grad_norm": 3.4750308990478516, "learning_rate": 5.3966500905983936e-06, "loss": 0.1343, "step": 443500 }, { "epoch": 2.6363155423197866, "grad_norm": 4.2684712409973145, "learning_rate": 5.396443252060015e-06, "loss": 0.1235, "step": 443510 }, { "epoch": 2.636374984396455, "grad_norm": 6.091851234436035, "learning_rate": 5.396236412838915e-06, "loss": 0.1227, "step": 443520 }, { "epoch": 2.6364344264731234, "grad_norm": 6.094639301300049, "learning_rate": 5.396029572935447e-06, "loss": 0.1387, "step": 443530 }, { "epoch": 2.636493868549792, "grad_norm": 5.073897838592529, "learning_rate": 5.39582273234997e-06, "loss": 0.1109, "step": 443540 }, { "epoch": 2.63655331062646, "grad_norm": 4.40936803817749, "learning_rate": 5.39561589108284e-06, "loss": 0.1328, "step": 443550 }, { "epoch": 2.6366127527031287, "grad_norm": 5.155818939208984, "learning_rate": 5.395409049134409e-06, "loss": 0.1211, "step": 443560 }, { "epoch": 2.6366721947797966, "grad_norm": 5.2876996994018555, "learning_rate": 5.395202206505039e-06, "loss": 0.12, "step": 443570 }, { "epoch": 2.636731636856465, "grad_norm": 4.5368123054504395, "learning_rate": 5.394995363195082e-06, "loss": 0.1267, "step": 443580 }, { "epoch": 2.6367910789331335, "grad_norm": 4.7134504318237305, "learning_rate": 5.394788519204897e-06, "loss": 0.1273, "step": 443590 }, { "epoch": 2.636850521009802, "grad_norm": 5.554650783538818, "learning_rate": 5.394581674534839e-06, "loss": 0.1254, "step": 443600 }, { "epoch": 2.6369099630864703, "grad_norm": 4.445052146911621, "learning_rate": 5.394374829185265e-06, "loss": 0.1179, "step": 443610 }, { "epoch": 2.6369694051631387, "grad_norm": 4.282166957855225, "learning_rate": 5.3941679831565295e-06, "loss": 0.1242, "step": 443620 }, { "epoch": 2.637028847239807, "grad_norm": 2.8408281803131104, "learning_rate": 5.393961136448989e-06, "loss": 0.1128, "step": 443630 }, { "epoch": 2.6370882893164755, "grad_norm": 4.530023097991943, "learning_rate": 5.393754289063003e-06, "loss": 0.1118, "step": 443640 }, { "epoch": 2.637147731393144, "grad_norm": 5.133969783782959, "learning_rate": 5.393547440998923e-06, "loss": 0.1456, "step": 443650 }, { "epoch": 2.6372071734698124, "grad_norm": 5.0304107666015625, "learning_rate": 5.393340592257108e-06, "loss": 0.1221, "step": 443660 }, { "epoch": 2.637266615546481, "grad_norm": 3.486624240875244, "learning_rate": 5.393133742837914e-06, "loss": 0.1319, "step": 443670 }, { "epoch": 2.637326057623149, "grad_norm": 4.253488063812256, "learning_rate": 5.392926892741695e-06, "loss": 0.1263, "step": 443680 }, { "epoch": 2.6373854996998176, "grad_norm": 4.994779109954834, "learning_rate": 5.392720041968809e-06, "loss": 0.1293, "step": 443690 }, { "epoch": 2.637444941776486, "grad_norm": 4.192081451416016, "learning_rate": 5.3925131905196134e-06, "loss": 0.1214, "step": 443700 }, { "epoch": 2.6375043838531544, "grad_norm": 4.941313743591309, "learning_rate": 5.392306338394464e-06, "loss": 0.143, "step": 443710 }, { "epoch": 2.6375638259298224, "grad_norm": 6.556672096252441, "learning_rate": 5.392099485593716e-06, "loss": 0.1243, "step": 443720 }, { "epoch": 2.6376232680064913, "grad_norm": 4.883431434631348, "learning_rate": 5.391892632117725e-06, "loss": 0.1369, "step": 443730 }, { "epoch": 2.6376827100831592, "grad_norm": 3.247795343399048, "learning_rate": 5.391685777966848e-06, "loss": 0.1331, "step": 443740 }, { "epoch": 2.637742152159828, "grad_norm": 3.8707151412963867, "learning_rate": 5.3914789231414425e-06, "loss": 0.1203, "step": 443750 }, { "epoch": 2.637801594236496, "grad_norm": 4.402093887329102, "learning_rate": 5.391272067641863e-06, "loss": 0.1334, "step": 443760 }, { "epoch": 2.6378610363131645, "grad_norm": 5.05568265914917, "learning_rate": 5.391065211468467e-06, "loss": 0.1255, "step": 443770 }, { "epoch": 2.637920478389833, "grad_norm": 5.31989049911499, "learning_rate": 5.390858354621609e-06, "loss": 0.1291, "step": 443780 }, { "epoch": 2.6379799204665013, "grad_norm": 4.663416862487793, "learning_rate": 5.390651497101647e-06, "loss": 0.1111, "step": 443790 }, { "epoch": 2.6380393625431697, "grad_norm": 5.18368673324585, "learning_rate": 5.3904446389089346e-06, "loss": 0.1453, "step": 443800 }, { "epoch": 2.638098804619838, "grad_norm": 3.8332607746124268, "learning_rate": 5.390237780043832e-06, "loss": 0.1396, "step": 443810 }, { "epoch": 2.6381582466965066, "grad_norm": 3.705397605895996, "learning_rate": 5.390030920506692e-06, "loss": 0.1272, "step": 443820 }, { "epoch": 2.638217688773175, "grad_norm": 4.552242279052734, "learning_rate": 5.3898240602978745e-06, "loss": 0.1239, "step": 443830 }, { "epoch": 2.6382771308498434, "grad_norm": 3.4417035579681396, "learning_rate": 5.389617199417732e-06, "loss": 0.1213, "step": 443840 }, { "epoch": 2.638336572926512, "grad_norm": 5.167121887207031, "learning_rate": 5.3894103378666216e-06, "loss": 0.1348, "step": 443850 }, { "epoch": 2.63839601500318, "grad_norm": 3.63907790184021, "learning_rate": 5.389203475644902e-06, "loss": 0.1255, "step": 443860 }, { "epoch": 2.6384554570798486, "grad_norm": 3.8515825271606445, "learning_rate": 5.3889966127529254e-06, "loss": 0.1223, "step": 443870 }, { "epoch": 2.638514899156517, "grad_norm": 4.182020664215088, "learning_rate": 5.388789749191052e-06, "loss": 0.1336, "step": 443880 }, { "epoch": 2.6385743412331855, "grad_norm": 4.996339797973633, "learning_rate": 5.3885828849596355e-06, "loss": 0.1025, "step": 443890 }, { "epoch": 2.638633783309854, "grad_norm": 4.135436058044434, "learning_rate": 5.388376020059033e-06, "loss": 0.1385, "step": 443900 }, { "epoch": 2.638693225386522, "grad_norm": 3.2713091373443604, "learning_rate": 5.3881691544895995e-06, "loss": 0.1224, "step": 443910 }, { "epoch": 2.6387526674631907, "grad_norm": 4.743616580963135, "learning_rate": 5.387962288251693e-06, "loss": 0.1163, "step": 443920 }, { "epoch": 2.6388121095398587, "grad_norm": 4.254796504974365, "learning_rate": 5.387755421345669e-06, "loss": 0.127, "step": 443930 }, { "epoch": 2.6388715516165275, "grad_norm": 5.049356937408447, "learning_rate": 5.387548553771885e-06, "loss": 0.1391, "step": 443940 }, { "epoch": 2.6389309936931955, "grad_norm": 4.01011323928833, "learning_rate": 5.387341685530696e-06, "loss": 0.1229, "step": 443950 }, { "epoch": 2.638990435769864, "grad_norm": 4.9730119705200195, "learning_rate": 5.387134816622458e-06, "loss": 0.1405, "step": 443960 }, { "epoch": 2.6390498778465323, "grad_norm": 6.1440653800964355, "learning_rate": 5.386927947047528e-06, "loss": 0.1314, "step": 443970 }, { "epoch": 2.6391093199232007, "grad_norm": 4.1666951179504395, "learning_rate": 5.38672107680626e-06, "loss": 0.114, "step": 443980 }, { "epoch": 2.639168761999869, "grad_norm": 3.4528839588165283, "learning_rate": 5.386514205899015e-06, "loss": 0.1326, "step": 443990 }, { "epoch": 2.6392282040765376, "grad_norm": 4.056468486785889, "learning_rate": 5.386307334326145e-06, "loss": 0.109, "step": 444000 }, { "epoch": 2.639287646153206, "grad_norm": 3.936339855194092, "learning_rate": 5.386100462088008e-06, "loss": 0.1259, "step": 444010 }, { "epoch": 2.6393470882298744, "grad_norm": 4.0325422286987305, "learning_rate": 5.385893589184958e-06, "loss": 0.132, "step": 444020 }, { "epoch": 2.639406530306543, "grad_norm": 4.477118968963623, "learning_rate": 5.385686715617357e-06, "loss": 0.1325, "step": 444030 }, { "epoch": 2.6394659723832112, "grad_norm": 4.333578109741211, "learning_rate": 5.3854798413855545e-06, "loss": 0.1192, "step": 444040 }, { "epoch": 2.6395254144598796, "grad_norm": 4.066769123077393, "learning_rate": 5.385272966489911e-06, "loss": 0.1244, "step": 444050 }, { "epoch": 2.639584856536548, "grad_norm": 3.902329921722412, "learning_rate": 5.385066090930781e-06, "loss": 0.1233, "step": 444060 }, { "epoch": 2.6396442986132165, "grad_norm": 4.089261531829834, "learning_rate": 5.384859214708522e-06, "loss": 0.1303, "step": 444070 }, { "epoch": 2.639703740689885, "grad_norm": 4.179792404174805, "learning_rate": 5.3846523378234885e-06, "loss": 0.125, "step": 444080 }, { "epoch": 2.6397631827665533, "grad_norm": 3.618438720703125, "learning_rate": 5.384445460276038e-06, "loss": 0.1178, "step": 444090 }, { "epoch": 2.6398226248432213, "grad_norm": 5.1462626457214355, "learning_rate": 5.3842385820665264e-06, "loss": 0.1369, "step": 444100 }, { "epoch": 2.63988206691989, "grad_norm": 5.525416374206543, "learning_rate": 5.3840317031953105e-06, "loss": 0.1074, "step": 444110 }, { "epoch": 2.639941508996558, "grad_norm": 2.8363149166107178, "learning_rate": 5.3838248236627465e-06, "loss": 0.11, "step": 444120 }, { "epoch": 2.640000951073227, "grad_norm": 4.45194673538208, "learning_rate": 5.383617943469189e-06, "loss": 0.1097, "step": 444130 }, { "epoch": 2.640060393149895, "grad_norm": 3.9364140033721924, "learning_rate": 5.383411062614997e-06, "loss": 0.1314, "step": 444140 }, { "epoch": 2.6401198352265633, "grad_norm": 4.777761936187744, "learning_rate": 5.383204181100524e-06, "loss": 0.128, "step": 444150 }, { "epoch": 2.6401792773032318, "grad_norm": 5.141353607177734, "learning_rate": 5.382997298926129e-06, "loss": 0.1339, "step": 444160 }, { "epoch": 2.6402387193799, "grad_norm": 4.926546573638916, "learning_rate": 5.382790416092168e-06, "loss": 0.1361, "step": 444170 }, { "epoch": 2.6402981614565686, "grad_norm": 3.923321008682251, "learning_rate": 5.382583532598994e-06, "loss": 0.1391, "step": 444180 }, { "epoch": 2.640357603533237, "grad_norm": 3.757474422454834, "learning_rate": 5.382376648446966e-06, "loss": 0.1121, "step": 444190 }, { "epoch": 2.6404170456099054, "grad_norm": 4.447466850280762, "learning_rate": 5.3821697636364415e-06, "loss": 0.1222, "step": 444200 }, { "epoch": 2.640476487686574, "grad_norm": 4.387967586517334, "learning_rate": 5.381962878167772e-06, "loss": 0.1245, "step": 444210 }, { "epoch": 2.6405359297632423, "grad_norm": 3.885775089263916, "learning_rate": 5.3817559920413194e-06, "loss": 0.1296, "step": 444220 }, { "epoch": 2.6405953718399107, "grad_norm": 3.978243112564087, "learning_rate": 5.381549105257437e-06, "loss": 0.1227, "step": 444230 }, { "epoch": 2.640654813916579, "grad_norm": 4.16562557220459, "learning_rate": 5.381342217816479e-06, "loss": 0.1294, "step": 444240 }, { "epoch": 2.6407142559932475, "grad_norm": 4.485727310180664, "learning_rate": 5.381135329718807e-06, "loss": 0.1204, "step": 444250 }, { "epoch": 2.640773698069916, "grad_norm": 2.784390926361084, "learning_rate": 5.380928440964774e-06, "loss": 0.1224, "step": 444260 }, { "epoch": 2.6408331401465843, "grad_norm": 5.690128326416016, "learning_rate": 5.380721551554737e-06, "loss": 0.1245, "step": 444270 }, { "epoch": 2.6408925822232527, "grad_norm": 4.300866603851318, "learning_rate": 5.3805146614890515e-06, "loss": 0.1179, "step": 444280 }, { "epoch": 2.6409520242999207, "grad_norm": 3.4695427417755127, "learning_rate": 5.380307770768074e-06, "loss": 0.1176, "step": 444290 }, { "epoch": 2.6410114663765896, "grad_norm": 5.883413791656494, "learning_rate": 5.3801008793921626e-06, "loss": 0.1258, "step": 444300 }, { "epoch": 2.6410709084532575, "grad_norm": 4.017064094543457, "learning_rate": 5.379893987361671e-06, "loss": 0.1089, "step": 444310 }, { "epoch": 2.641130350529926, "grad_norm": 4.255885124206543, "learning_rate": 5.379687094676957e-06, "loss": 0.1196, "step": 444320 }, { "epoch": 2.6411897926065944, "grad_norm": 3.6164615154266357, "learning_rate": 5.3794802013383765e-06, "loss": 0.1398, "step": 444330 }, { "epoch": 2.641249234683263, "grad_norm": 5.722125053405762, "learning_rate": 5.379273307346284e-06, "loss": 0.1352, "step": 444340 }, { "epoch": 2.641308676759931, "grad_norm": 4.839090347290039, "learning_rate": 5.37906641270104e-06, "loss": 0.1315, "step": 444350 }, { "epoch": 2.6413681188365996, "grad_norm": 3.895900011062622, "learning_rate": 5.378859517402997e-06, "loss": 0.1264, "step": 444360 }, { "epoch": 2.641427560913268, "grad_norm": 3.676100969314575, "learning_rate": 5.378652621452513e-06, "loss": 0.1212, "step": 444370 }, { "epoch": 2.6414870029899364, "grad_norm": 3.8180034160614014, "learning_rate": 5.3784457248499445e-06, "loss": 0.1162, "step": 444380 }, { "epoch": 2.641546445066605, "grad_norm": 3.2945711612701416, "learning_rate": 5.378238827595648e-06, "loss": 0.1141, "step": 444390 }, { "epoch": 2.6416058871432733, "grad_norm": 4.152255535125732, "learning_rate": 5.378031929689977e-06, "loss": 0.1186, "step": 444400 }, { "epoch": 2.6416653292199417, "grad_norm": 4.789399147033691, "learning_rate": 5.377825031133291e-06, "loss": 0.1255, "step": 444410 }, { "epoch": 2.64172477129661, "grad_norm": 4.110644340515137, "learning_rate": 5.3776181319259466e-06, "loss": 0.149, "step": 444420 }, { "epoch": 2.6417842133732785, "grad_norm": 3.5537164211273193, "learning_rate": 5.377411232068297e-06, "loss": 0.1053, "step": 444430 }, { "epoch": 2.641843655449947, "grad_norm": 4.5820231437683105, "learning_rate": 5.3772043315607e-06, "loss": 0.1412, "step": 444440 }, { "epoch": 2.6419030975266153, "grad_norm": 3.247661590576172, "learning_rate": 5.376997430403514e-06, "loss": 0.1156, "step": 444450 }, { "epoch": 2.6419625396032833, "grad_norm": 4.102850437164307, "learning_rate": 5.376790528597091e-06, "loss": 0.1236, "step": 444460 }, { "epoch": 2.642021981679952, "grad_norm": 3.3849246501922607, "learning_rate": 5.376583626141792e-06, "loss": 0.1121, "step": 444470 }, { "epoch": 2.64208142375662, "grad_norm": 3.950932264328003, "learning_rate": 5.376376723037969e-06, "loss": 0.1158, "step": 444480 }, { "epoch": 2.642140865833289, "grad_norm": 4.691024303436279, "learning_rate": 5.376169819285982e-06, "loss": 0.1138, "step": 444490 }, { "epoch": 2.642200307909957, "grad_norm": 4.677373886108398, "learning_rate": 5.375962914886184e-06, "loss": 0.1305, "step": 444500 }, { "epoch": 2.6422597499866254, "grad_norm": 3.212092638015747, "learning_rate": 5.375756009838935e-06, "loss": 0.1154, "step": 444510 }, { "epoch": 2.642319192063294, "grad_norm": 4.313652515411377, "learning_rate": 5.375549104144589e-06, "loss": 0.1241, "step": 444520 }, { "epoch": 2.642378634139962, "grad_norm": 3.79085111618042, "learning_rate": 5.375342197803501e-06, "loss": 0.1348, "step": 444530 }, { "epoch": 2.6424380762166306, "grad_norm": 3.65450382232666, "learning_rate": 5.375135290816032e-06, "loss": 0.1327, "step": 444540 }, { "epoch": 2.642497518293299, "grad_norm": 4.731906890869141, "learning_rate": 5.374928383182532e-06, "loss": 0.1474, "step": 444550 }, { "epoch": 2.6425569603699675, "grad_norm": 4.944207191467285, "learning_rate": 5.374721474903362e-06, "loss": 0.1262, "step": 444560 }, { "epoch": 2.642616402446636, "grad_norm": 3.534620761871338, "learning_rate": 5.374514565978876e-06, "loss": 0.103, "step": 444570 }, { "epoch": 2.6426758445233043, "grad_norm": 4.441939830780029, "learning_rate": 5.374307656409433e-06, "loss": 0.1284, "step": 444580 }, { "epoch": 2.6427352865999727, "grad_norm": 3.46954083442688, "learning_rate": 5.374100746195387e-06, "loss": 0.1208, "step": 444590 }, { "epoch": 2.642794728676641, "grad_norm": 3.68117094039917, "learning_rate": 5.373893835337094e-06, "loss": 0.1252, "step": 444600 }, { "epoch": 2.6428541707533095, "grad_norm": 3.5180296897888184, "learning_rate": 5.373686923834912e-06, "loss": 0.1292, "step": 444610 }, { "epoch": 2.642913612829978, "grad_norm": 4.925514221191406, "learning_rate": 5.373480011689196e-06, "loss": 0.119, "step": 444620 }, { "epoch": 2.6429730549066464, "grad_norm": 3.4122514724731445, "learning_rate": 5.373273098900302e-06, "loss": 0.1205, "step": 444630 }, { "epoch": 2.6430324969833148, "grad_norm": 4.56444787979126, "learning_rate": 5.3730661854685895e-06, "loss": 0.1322, "step": 444640 }, { "epoch": 2.6430919390599827, "grad_norm": 4.447275161743164, "learning_rate": 5.372859271394412e-06, "loss": 0.1285, "step": 444650 }, { "epoch": 2.6431513811366516, "grad_norm": 4.382448673248291, "learning_rate": 5.372652356678124e-06, "loss": 0.1284, "step": 444660 }, { "epoch": 2.6432108232133196, "grad_norm": 5.117504119873047, "learning_rate": 5.3724454413200865e-06, "loss": 0.1173, "step": 444670 }, { "epoch": 2.6432702652899884, "grad_norm": 5.373368263244629, "learning_rate": 5.372238525320652e-06, "loss": 0.1226, "step": 444680 }, { "epoch": 2.6433297073666564, "grad_norm": 5.665838718414307, "learning_rate": 5.372031608680181e-06, "loss": 0.1405, "step": 444690 }, { "epoch": 2.643389149443325, "grad_norm": 6.283038139343262, "learning_rate": 5.3718246913990235e-06, "loss": 0.1238, "step": 444700 }, { "epoch": 2.6434485915199932, "grad_norm": 2.899411678314209, "learning_rate": 5.371617773477542e-06, "loss": 0.1082, "step": 444710 }, { "epoch": 2.6435080335966616, "grad_norm": 4.459342956542969, "learning_rate": 5.37141085491609e-06, "loss": 0.123, "step": 444720 }, { "epoch": 2.64356747567333, "grad_norm": 4.917142868041992, "learning_rate": 5.371203935715024e-06, "loss": 0.1222, "step": 444730 }, { "epoch": 2.6436269177499985, "grad_norm": 4.271800994873047, "learning_rate": 5.3709970158747e-06, "loss": 0.1153, "step": 444740 }, { "epoch": 2.643686359826667, "grad_norm": 3.765594244003296, "learning_rate": 5.370790095395476e-06, "loss": 0.1193, "step": 444750 }, { "epoch": 2.6437458019033353, "grad_norm": 5.903067111968994, "learning_rate": 5.370583174277706e-06, "loss": 0.1259, "step": 444760 }, { "epoch": 2.6438052439800037, "grad_norm": 4.551441192626953, "learning_rate": 5.370376252521749e-06, "loss": 0.116, "step": 444770 }, { "epoch": 2.643864686056672, "grad_norm": 4.007399559020996, "learning_rate": 5.370169330127959e-06, "loss": 0.1259, "step": 444780 }, { "epoch": 2.6439241281333405, "grad_norm": 4.845282077789307, "learning_rate": 5.369962407096691e-06, "loss": 0.1189, "step": 444790 }, { "epoch": 2.643983570210009, "grad_norm": 3.8403823375701904, "learning_rate": 5.369755483428306e-06, "loss": 0.1242, "step": 444800 }, { "epoch": 2.6440430122866774, "grad_norm": 4.881354331970215, "learning_rate": 5.369548559123159e-06, "loss": 0.1406, "step": 444810 }, { "epoch": 2.644102454363346, "grad_norm": 2.887528657913208, "learning_rate": 5.369341634181604e-06, "loss": 0.1164, "step": 444820 }, { "epoch": 2.644161896440014, "grad_norm": 4.008625507354736, "learning_rate": 5.369134708603998e-06, "loss": 0.1243, "step": 444830 }, { "epoch": 2.644221338516682, "grad_norm": 4.894025802612305, "learning_rate": 5.3689277823907e-06, "loss": 0.1218, "step": 444840 }, { "epoch": 2.644280780593351, "grad_norm": 3.4461302757263184, "learning_rate": 5.368720855542062e-06, "loss": 0.125, "step": 444850 }, { "epoch": 2.644340222670019, "grad_norm": 4.190382480621338, "learning_rate": 5.368513928058443e-06, "loss": 0.1149, "step": 444860 }, { "epoch": 2.644399664746688, "grad_norm": 3.8552932739257812, "learning_rate": 5.3683069999402e-06, "loss": 0.1373, "step": 444870 }, { "epoch": 2.644459106823356, "grad_norm": 3.6978919506073, "learning_rate": 5.368100071187689e-06, "loss": 0.1359, "step": 444880 }, { "epoch": 2.6445185489000242, "grad_norm": 3.7563700675964355, "learning_rate": 5.367893141801265e-06, "loss": 0.1403, "step": 444890 }, { "epoch": 2.6445779909766927, "grad_norm": 4.705771446228027, "learning_rate": 5.367686211781283e-06, "loss": 0.1184, "step": 444900 }, { "epoch": 2.644637433053361, "grad_norm": 3.62569522857666, "learning_rate": 5.367479281128104e-06, "loss": 0.1205, "step": 444910 }, { "epoch": 2.6446968751300295, "grad_norm": 4.026097774505615, "learning_rate": 5.367272349842082e-06, "loss": 0.1076, "step": 444920 }, { "epoch": 2.644756317206698, "grad_norm": 5.468742847442627, "learning_rate": 5.367065417923572e-06, "loss": 0.1351, "step": 444930 }, { "epoch": 2.6448157592833663, "grad_norm": 8.220304489135742, "learning_rate": 5.366858485372932e-06, "loss": 0.1326, "step": 444940 }, { "epoch": 2.6448752013600347, "grad_norm": 5.304778575897217, "learning_rate": 5.366651552190519e-06, "loss": 0.1107, "step": 444950 }, { "epoch": 2.644934643436703, "grad_norm": 4.568676948547363, "learning_rate": 5.366444618376686e-06, "loss": 0.1243, "step": 444960 }, { "epoch": 2.6449940855133716, "grad_norm": 3.505472183227539, "learning_rate": 5.366237683931794e-06, "loss": 0.1207, "step": 444970 }, { "epoch": 2.64505352759004, "grad_norm": 5.494222164154053, "learning_rate": 5.366030748856195e-06, "loss": 0.145, "step": 444980 }, { "epoch": 2.6451129696667084, "grad_norm": 4.111764907836914, "learning_rate": 5.365823813150249e-06, "loss": 0.1332, "step": 444990 }, { "epoch": 2.645172411743377, "grad_norm": 3.7550790309906006, "learning_rate": 5.36561687681431e-06, "loss": 0.1099, "step": 445000 }, { "epoch": 2.645231853820045, "grad_norm": 4.37418270111084, "learning_rate": 5.365409939848735e-06, "loss": 0.1311, "step": 445010 }, { "epoch": 2.6452912958967136, "grad_norm": 4.684776782989502, "learning_rate": 5.365203002253879e-06, "loss": 0.1399, "step": 445020 }, { "epoch": 2.6453507379733816, "grad_norm": 3.664865016937256, "learning_rate": 5.364996064030102e-06, "loss": 0.1404, "step": 445030 }, { "epoch": 2.6454101800500505, "grad_norm": 5.0956010818481445, "learning_rate": 5.3647891251777585e-06, "loss": 0.139, "step": 445040 }, { "epoch": 2.6454696221267184, "grad_norm": 4.516130447387695, "learning_rate": 5.364582185697203e-06, "loss": 0.1281, "step": 445050 }, { "epoch": 2.645529064203387, "grad_norm": 4.586869239807129, "learning_rate": 5.364375245588795e-06, "loss": 0.1244, "step": 445060 }, { "epoch": 2.6455885062800553, "grad_norm": 4.435517311096191, "learning_rate": 5.364168304852889e-06, "loss": 0.1192, "step": 445070 }, { "epoch": 2.6456479483567237, "grad_norm": 5.017059803009033, "learning_rate": 5.36396136348984e-06, "loss": 0.1279, "step": 445080 }, { "epoch": 2.645707390433392, "grad_norm": 5.035741329193115, "learning_rate": 5.363754421500008e-06, "loss": 0.13, "step": 445090 }, { "epoch": 2.6457668325100605, "grad_norm": 4.748857021331787, "learning_rate": 5.3635474788837485e-06, "loss": 0.1406, "step": 445100 }, { "epoch": 2.645826274586729, "grad_norm": 4.655964374542236, "learning_rate": 5.363340535641413e-06, "loss": 0.1395, "step": 445110 }, { "epoch": 2.6458857166633973, "grad_norm": 3.7872226238250732, "learning_rate": 5.363133591773364e-06, "loss": 0.1186, "step": 445120 }, { "epoch": 2.6459451587400658, "grad_norm": 4.974732398986816, "learning_rate": 5.362926647279957e-06, "loss": 0.1299, "step": 445130 }, { "epoch": 2.646004600816734, "grad_norm": 4.377861499786377, "learning_rate": 5.362719702161545e-06, "loss": 0.1334, "step": 445140 }, { "epoch": 2.6460640428934026, "grad_norm": 3.7787680625915527, "learning_rate": 5.362512756418487e-06, "loss": 0.1203, "step": 445150 }, { "epoch": 2.646123484970071, "grad_norm": 7.208616256713867, "learning_rate": 5.36230581005114e-06, "loss": 0.1473, "step": 445160 }, { "epoch": 2.6461829270467394, "grad_norm": 4.765687465667725, "learning_rate": 5.362098863059858e-06, "loss": 0.1244, "step": 445170 }, { "epoch": 2.646242369123408, "grad_norm": 3.6878249645233154, "learning_rate": 5.361891915444998e-06, "loss": 0.1099, "step": 445180 }, { "epoch": 2.6463018112000762, "grad_norm": 4.705924034118652, "learning_rate": 5.3616849672069175e-06, "loss": 0.1327, "step": 445190 }, { "epoch": 2.646361253276744, "grad_norm": 3.446958541870117, "learning_rate": 5.361478018345972e-06, "loss": 0.122, "step": 445200 }, { "epoch": 2.646420695353413, "grad_norm": 3.2471961975097656, "learning_rate": 5.361271068862519e-06, "loss": 0.1256, "step": 445210 }, { "epoch": 2.646480137430081, "grad_norm": 3.970364809036255, "learning_rate": 5.361064118756914e-06, "loss": 0.1216, "step": 445220 }, { "epoch": 2.64653957950675, "grad_norm": 4.601900100708008, "learning_rate": 5.360857168029512e-06, "loss": 0.1238, "step": 445230 }, { "epoch": 2.646599021583418, "grad_norm": 4.355311393737793, "learning_rate": 5.360650216680673e-06, "loss": 0.1321, "step": 445240 }, { "epoch": 2.6466584636600863, "grad_norm": 4.738831520080566, "learning_rate": 5.360443264710749e-06, "loss": 0.1375, "step": 445250 }, { "epoch": 2.6467179057367547, "grad_norm": 4.428850173950195, "learning_rate": 5.3602363121201e-06, "loss": 0.1271, "step": 445260 }, { "epoch": 2.646777347813423, "grad_norm": 4.68334436416626, "learning_rate": 5.360029358909083e-06, "loss": 0.1373, "step": 445270 }, { "epoch": 2.6468367898900915, "grad_norm": 4.395130634307861, "learning_rate": 5.3598224050780505e-06, "loss": 0.1228, "step": 445280 }, { "epoch": 2.64689623196676, "grad_norm": 5.193959712982178, "learning_rate": 5.35961545062736e-06, "loss": 0.1308, "step": 445290 }, { "epoch": 2.6469556740434284, "grad_norm": 4.319119453430176, "learning_rate": 5.359408495557371e-06, "loss": 0.1276, "step": 445300 }, { "epoch": 2.6470151161200968, "grad_norm": 4.7670488357543945, "learning_rate": 5.359201539868435e-06, "loss": 0.1269, "step": 445310 }, { "epoch": 2.647074558196765, "grad_norm": 3.843959331512451, "learning_rate": 5.358994583560914e-06, "loss": 0.1043, "step": 445320 }, { "epoch": 2.6471340002734336, "grad_norm": 4.5235981941223145, "learning_rate": 5.35878762663516e-06, "loss": 0.132, "step": 445330 }, { "epoch": 2.647193442350102, "grad_norm": 3.6178276538848877, "learning_rate": 5.3585806690915294e-06, "loss": 0.1303, "step": 445340 }, { "epoch": 2.6472528844267704, "grad_norm": 5.14035177230835, "learning_rate": 5.358373710930383e-06, "loss": 0.1393, "step": 445350 }, { "epoch": 2.647312326503439, "grad_norm": 5.253393173217773, "learning_rate": 5.3581667521520715e-06, "loss": 0.1304, "step": 445360 }, { "epoch": 2.6473717685801073, "grad_norm": 4.404683589935303, "learning_rate": 5.357959792756957e-06, "loss": 0.1173, "step": 445370 }, { "epoch": 2.6474312106567757, "grad_norm": 3.10246205329895, "learning_rate": 5.357752832745391e-06, "loss": 0.1083, "step": 445380 }, { "epoch": 2.6474906527334436, "grad_norm": 3.867642641067505, "learning_rate": 5.357545872117733e-06, "loss": 0.1231, "step": 445390 }, { "epoch": 2.6475500948101125, "grad_norm": 2.7781593799591064, "learning_rate": 5.357338910874338e-06, "loss": 0.1256, "step": 445400 }, { "epoch": 2.6476095368867805, "grad_norm": 2.9914660453796387, "learning_rate": 5.357131949015563e-06, "loss": 0.1036, "step": 445410 }, { "epoch": 2.6476689789634493, "grad_norm": 3.466641426086426, "learning_rate": 5.356924986541764e-06, "loss": 0.1239, "step": 445420 }, { "epoch": 2.6477284210401173, "grad_norm": 4.808537483215332, "learning_rate": 5.356718023453298e-06, "loss": 0.1107, "step": 445430 }, { "epoch": 2.6477878631167857, "grad_norm": 3.7698440551757812, "learning_rate": 5.3565110597505185e-06, "loss": 0.1423, "step": 445440 }, { "epoch": 2.647847305193454, "grad_norm": 5.988867282867432, "learning_rate": 5.356304095433787e-06, "loss": 0.1424, "step": 445450 }, { "epoch": 2.6479067472701225, "grad_norm": 3.34861159324646, "learning_rate": 5.356097130503456e-06, "loss": 0.1213, "step": 445460 }, { "epoch": 2.647966189346791, "grad_norm": 4.272722244262695, "learning_rate": 5.355890164959885e-06, "loss": 0.1228, "step": 445470 }, { "epoch": 2.6480256314234594, "grad_norm": 4.333292484283447, "learning_rate": 5.3556831988034265e-06, "loss": 0.106, "step": 445480 }, { "epoch": 2.648085073500128, "grad_norm": 5.339679718017578, "learning_rate": 5.355476232034441e-06, "loss": 0.1086, "step": 445490 }, { "epoch": 2.648144515576796, "grad_norm": 5.236109733581543, "learning_rate": 5.355269264653282e-06, "loss": 0.1332, "step": 445500 }, { "epoch": 2.6482039576534646, "grad_norm": 3.6854617595672607, "learning_rate": 5.355062296660307e-06, "loss": 0.1301, "step": 445510 }, { "epoch": 2.648263399730133, "grad_norm": 4.698176383972168, "learning_rate": 5.354855328055873e-06, "loss": 0.1262, "step": 445520 }, { "epoch": 2.6483228418068014, "grad_norm": 4.650947570800781, "learning_rate": 5.354648358840335e-06, "loss": 0.1209, "step": 445530 }, { "epoch": 2.64838228388347, "grad_norm": 4.382195949554443, "learning_rate": 5.35444138901405e-06, "loss": 0.1199, "step": 445540 }, { "epoch": 2.6484417259601383, "grad_norm": 4.405927658081055, "learning_rate": 5.354234418577376e-06, "loss": 0.1175, "step": 445550 }, { "epoch": 2.6485011680368067, "grad_norm": 4.095353603363037, "learning_rate": 5.354027447530666e-06, "loss": 0.124, "step": 445560 }, { "epoch": 2.648560610113475, "grad_norm": 4.65571928024292, "learning_rate": 5.3538204758742805e-06, "loss": 0.1163, "step": 445570 }, { "epoch": 2.648620052190143, "grad_norm": 3.3285157680511475, "learning_rate": 5.353613503608572e-06, "loss": 0.1342, "step": 445580 }, { "epoch": 2.648679494266812, "grad_norm": 4.564795017242432, "learning_rate": 5.3534065307339016e-06, "loss": 0.1222, "step": 445590 }, { "epoch": 2.64873893634348, "grad_norm": 2.9802396297454834, "learning_rate": 5.353199557250622e-06, "loss": 0.1056, "step": 445600 }, { "epoch": 2.6487983784201488, "grad_norm": 4.314162254333496, "learning_rate": 5.352992583159089e-06, "loss": 0.1407, "step": 445610 }, { "epoch": 2.6488578204968167, "grad_norm": 4.45026969909668, "learning_rate": 5.352785608459662e-06, "loss": 0.1299, "step": 445620 }, { "epoch": 2.648917262573485, "grad_norm": 3.6626315116882324, "learning_rate": 5.352578633152696e-06, "loss": 0.1299, "step": 445630 }, { "epoch": 2.6489767046501536, "grad_norm": 4.955300331115723, "learning_rate": 5.352371657238546e-06, "loss": 0.1123, "step": 445640 }, { "epoch": 2.649036146726822, "grad_norm": 4.526237964630127, "learning_rate": 5.352164680717572e-06, "loss": 0.1222, "step": 445650 }, { "epoch": 2.6490955888034904, "grad_norm": 4.190332412719727, "learning_rate": 5.351957703590128e-06, "loss": 0.1103, "step": 445660 }, { "epoch": 2.649155030880159, "grad_norm": 4.440820217132568, "learning_rate": 5.351750725856568e-06, "loss": 0.1229, "step": 445670 }, { "epoch": 2.649214472956827, "grad_norm": 5.229014873504639, "learning_rate": 5.351543747517255e-06, "loss": 0.1482, "step": 445680 }, { "epoch": 2.6492739150334956, "grad_norm": 3.223071813583374, "learning_rate": 5.35133676857254e-06, "loss": 0.1133, "step": 445690 }, { "epoch": 2.649333357110164, "grad_norm": 3.317434072494507, "learning_rate": 5.351129789022782e-06, "loss": 0.1492, "step": 445700 }, { "epoch": 2.6493927991868325, "grad_norm": 4.168214797973633, "learning_rate": 5.350922808868336e-06, "loss": 0.1243, "step": 445710 }, { "epoch": 2.649452241263501, "grad_norm": 3.162539005279541, "learning_rate": 5.350715828109559e-06, "loss": 0.1236, "step": 445720 }, { "epoch": 2.6495116833401693, "grad_norm": 4.5866007804870605, "learning_rate": 5.350508846746808e-06, "loss": 0.1255, "step": 445730 }, { "epoch": 2.6495711254168377, "grad_norm": 4.785390377044678, "learning_rate": 5.3503018647804395e-06, "loss": 0.1085, "step": 445740 }, { "epoch": 2.649630567493506, "grad_norm": 3.8827781677246094, "learning_rate": 5.350094882210809e-06, "loss": 0.1158, "step": 445750 }, { "epoch": 2.6496900095701745, "grad_norm": 4.344804286956787, "learning_rate": 5.349887899038272e-06, "loss": 0.1329, "step": 445760 }, { "epoch": 2.6497494516468425, "grad_norm": 5.304098606109619, "learning_rate": 5.349680915263188e-06, "loss": 0.1231, "step": 445770 }, { "epoch": 2.6498088937235114, "grad_norm": 4.392524242401123, "learning_rate": 5.34947393088591e-06, "loss": 0.1253, "step": 445780 }, { "epoch": 2.6498683358001793, "grad_norm": 3.55800724029541, "learning_rate": 5.349266945906798e-06, "loss": 0.1329, "step": 445790 }, { "epoch": 2.6499277778768477, "grad_norm": 4.4748382568359375, "learning_rate": 5.349059960326205e-06, "loss": 0.1568, "step": 445800 }, { "epoch": 2.649987219953516, "grad_norm": 4.751735210418701, "learning_rate": 5.348852974144491e-06, "loss": 0.1321, "step": 445810 }, { "epoch": 2.6500466620301846, "grad_norm": 3.9888455867767334, "learning_rate": 5.348645987362009e-06, "loss": 0.1195, "step": 445820 }, { "epoch": 2.650106104106853, "grad_norm": 4.019933223724365, "learning_rate": 5.348438999979117e-06, "loss": 0.1251, "step": 445830 }, { "epoch": 2.6501655461835214, "grad_norm": 3.8615291118621826, "learning_rate": 5.348232011996172e-06, "loss": 0.1214, "step": 445840 }, { "epoch": 2.65022498826019, "grad_norm": 3.859744071960449, "learning_rate": 5.34802502341353e-06, "loss": 0.1434, "step": 445850 }, { "epoch": 2.6502844303368582, "grad_norm": 3.2965869903564453, "learning_rate": 5.3478180342315465e-06, "loss": 0.1107, "step": 445860 }, { "epoch": 2.6503438724135266, "grad_norm": 4.978770732879639, "learning_rate": 5.34761104445058e-06, "loss": 0.1117, "step": 445870 }, { "epoch": 2.650403314490195, "grad_norm": 4.781096935272217, "learning_rate": 5.347404054070986e-06, "loss": 0.1213, "step": 445880 }, { "epoch": 2.6504627565668635, "grad_norm": 4.649151802062988, "learning_rate": 5.3471970630931205e-06, "loss": 0.1422, "step": 445890 }, { "epoch": 2.650522198643532, "grad_norm": 4.439919471740723, "learning_rate": 5.346990071517339e-06, "loss": 0.1282, "step": 445900 }, { "epoch": 2.6505816407202003, "grad_norm": 3.092245578765869, "learning_rate": 5.346783079344e-06, "loss": 0.1183, "step": 445910 }, { "epoch": 2.6506410827968687, "grad_norm": 4.2643866539001465, "learning_rate": 5.3465760865734596e-06, "loss": 0.1206, "step": 445920 }, { "epoch": 2.650700524873537, "grad_norm": 3.261899948120117, "learning_rate": 5.346369093206073e-06, "loss": 0.1148, "step": 445930 }, { "epoch": 2.650759966950205, "grad_norm": 4.15261173248291, "learning_rate": 5.3461620992421985e-06, "loss": 0.1228, "step": 445940 }, { "epoch": 2.650819409026874, "grad_norm": 4.669075012207031, "learning_rate": 5.345955104682191e-06, "loss": 0.1332, "step": 445950 }, { "epoch": 2.650878851103542, "grad_norm": 4.638965129852295, "learning_rate": 5.3457481095264075e-06, "loss": 0.1246, "step": 445960 }, { "epoch": 2.650938293180211, "grad_norm": 4.025094985961914, "learning_rate": 5.345541113775205e-06, "loss": 0.1236, "step": 445970 }, { "epoch": 2.6509977352568788, "grad_norm": 3.3516173362731934, "learning_rate": 5.3453341174289395e-06, "loss": 0.1171, "step": 445980 }, { "epoch": 2.651057177333547, "grad_norm": 4.676964282989502, "learning_rate": 5.345127120487966e-06, "loss": 0.1568, "step": 445990 }, { "epoch": 2.6511166194102156, "grad_norm": 4.5605316162109375, "learning_rate": 5.344920122952643e-06, "loss": 0.1157, "step": 446000 }, { "epoch": 2.651176061486884, "grad_norm": 4.114421367645264, "learning_rate": 5.3447131248233275e-06, "loss": 0.1265, "step": 446010 }, { "epoch": 2.6512355035635524, "grad_norm": 4.870850086212158, "learning_rate": 5.344506126100374e-06, "loss": 0.1284, "step": 446020 }, { "epoch": 2.651294945640221, "grad_norm": 4.4040422439575195, "learning_rate": 5.344299126784139e-06, "loss": 0.1308, "step": 446030 }, { "epoch": 2.6513543877168892, "grad_norm": 3.405893087387085, "learning_rate": 5.3440921268749815e-06, "loss": 0.1066, "step": 446040 }, { "epoch": 2.6514138297935577, "grad_norm": 4.531327247619629, "learning_rate": 5.343885126373256e-06, "loss": 0.1035, "step": 446050 }, { "epoch": 2.651473271870226, "grad_norm": 3.8811073303222656, "learning_rate": 5.343678125279319e-06, "loss": 0.1389, "step": 446060 }, { "epoch": 2.6515327139468945, "grad_norm": 2.3739469051361084, "learning_rate": 5.343471123593526e-06, "loss": 0.1245, "step": 446070 }, { "epoch": 2.651592156023563, "grad_norm": 4.288135528564453, "learning_rate": 5.343264121316237e-06, "loss": 0.1127, "step": 446080 }, { "epoch": 2.6516515981002313, "grad_norm": 4.282166004180908, "learning_rate": 5.343057118447805e-06, "loss": 0.1227, "step": 446090 }, { "epoch": 2.6517110401768997, "grad_norm": 4.195146083831787, "learning_rate": 5.3428501149885885e-06, "loss": 0.1364, "step": 446100 }, { "epoch": 2.651770482253568, "grad_norm": 3.892376661300659, "learning_rate": 5.342643110938942e-06, "loss": 0.1247, "step": 446110 }, { "epoch": 2.6518299243302366, "grad_norm": 5.064825057983398, "learning_rate": 5.342436106299224e-06, "loss": 0.1329, "step": 446120 }, { "epoch": 2.6518893664069045, "grad_norm": 3.77148699760437, "learning_rate": 5.3422291010697894e-06, "loss": 0.1248, "step": 446130 }, { "epoch": 2.6519488084835734, "grad_norm": 4.202628135681152, "learning_rate": 5.342022095250996e-06, "loss": 0.1381, "step": 446140 }, { "epoch": 2.6520082505602414, "grad_norm": 3.9365625381469727, "learning_rate": 5.3418150888432e-06, "loss": 0.1254, "step": 446150 }, { "epoch": 2.6520676926369102, "grad_norm": 3.6565487384796143, "learning_rate": 5.341608081846757e-06, "loss": 0.1227, "step": 446160 }, { "epoch": 2.652127134713578, "grad_norm": 3.7825725078582764, "learning_rate": 5.341401074262025e-06, "loss": 0.1261, "step": 446170 }, { "epoch": 2.6521865767902466, "grad_norm": 3.3065905570983887, "learning_rate": 5.3411940660893595e-06, "loss": 0.1215, "step": 446180 }, { "epoch": 2.652246018866915, "grad_norm": 5.991588592529297, "learning_rate": 5.340987057329116e-06, "loss": 0.1268, "step": 446190 }, { "epoch": 2.6523054609435834, "grad_norm": 3.9923200607299805, "learning_rate": 5.340780047981653e-06, "loss": 0.1422, "step": 446200 }, { "epoch": 2.652364903020252, "grad_norm": 4.183426856994629, "learning_rate": 5.340573038047326e-06, "loss": 0.1431, "step": 446210 }, { "epoch": 2.6524243450969203, "grad_norm": 3.817422389984131, "learning_rate": 5.3403660275264905e-06, "loss": 0.1341, "step": 446220 }, { "epoch": 2.6524837871735887, "grad_norm": 3.737006187438965, "learning_rate": 5.340159016419505e-06, "loss": 0.1016, "step": 446230 }, { "epoch": 2.652543229250257, "grad_norm": 4.884835720062256, "learning_rate": 5.339952004726725e-06, "loss": 0.1066, "step": 446240 }, { "epoch": 2.6526026713269255, "grad_norm": 4.504172325134277, "learning_rate": 5.339744992448508e-06, "loss": 0.1263, "step": 446250 }, { "epoch": 2.652662113403594, "grad_norm": 4.73788595199585, "learning_rate": 5.3395379795852075e-06, "loss": 0.1114, "step": 446260 }, { "epoch": 2.6527215554802623, "grad_norm": 5.422982692718506, "learning_rate": 5.339330966137184e-06, "loss": 0.1368, "step": 446270 }, { "epoch": 2.6527809975569308, "grad_norm": 5.817690372467041, "learning_rate": 5.339123952104792e-06, "loss": 0.1223, "step": 446280 }, { "epoch": 2.652840439633599, "grad_norm": 4.292321681976318, "learning_rate": 5.338916937488388e-06, "loss": 0.1345, "step": 446290 }, { "epoch": 2.6528998817102676, "grad_norm": 3.32110595703125, "learning_rate": 5.338709922288328e-06, "loss": 0.1322, "step": 446300 }, { "epoch": 2.652959323786936, "grad_norm": 4.006588459014893, "learning_rate": 5.33850290650497e-06, "loss": 0.1306, "step": 446310 }, { "epoch": 2.653018765863604, "grad_norm": 3.9448795318603516, "learning_rate": 5.338295890138667e-06, "loss": 0.1225, "step": 446320 }, { "epoch": 2.653078207940273, "grad_norm": 3.521987199783325, "learning_rate": 5.33808887318978e-06, "loss": 0.1225, "step": 446330 }, { "epoch": 2.653137650016941, "grad_norm": 4.462280750274658, "learning_rate": 5.337881855658664e-06, "loss": 0.1229, "step": 446340 }, { "epoch": 2.6531970920936097, "grad_norm": 3.844303846359253, "learning_rate": 5.3376748375456745e-06, "loss": 0.1117, "step": 446350 }, { "epoch": 2.6532565341702776, "grad_norm": 3.3270256519317627, "learning_rate": 5.337467818851168e-06, "loss": 0.1109, "step": 446360 }, { "epoch": 2.653315976246946, "grad_norm": 4.797720432281494, "learning_rate": 5.337260799575504e-06, "loss": 0.1387, "step": 446370 }, { "epoch": 2.6533754183236145, "grad_norm": 2.8126282691955566, "learning_rate": 5.337053779719035e-06, "loss": 0.1195, "step": 446380 }, { "epoch": 2.653434860400283, "grad_norm": 3.4642205238342285, "learning_rate": 5.33684675928212e-06, "loss": 0.1013, "step": 446390 }, { "epoch": 2.6534943024769513, "grad_norm": 3.8074121475219727, "learning_rate": 5.3366397382651135e-06, "loss": 0.126, "step": 446400 }, { "epoch": 2.6535537445536197, "grad_norm": 6.002805233001709, "learning_rate": 5.3364327166683725e-06, "loss": 0.1208, "step": 446410 }, { "epoch": 2.653613186630288, "grad_norm": 3.237107992172241, "learning_rate": 5.336225694492257e-06, "loss": 0.1135, "step": 446420 }, { "epoch": 2.6536726287069565, "grad_norm": 4.642434120178223, "learning_rate": 5.33601867173712e-06, "loss": 0.1113, "step": 446430 }, { "epoch": 2.653732070783625, "grad_norm": 4.384584903717041, "learning_rate": 5.335811648403316e-06, "loss": 0.1312, "step": 446440 }, { "epoch": 2.6537915128602934, "grad_norm": 3.236027240753174, "learning_rate": 5.335604624491206e-06, "loss": 0.1024, "step": 446450 }, { "epoch": 2.6538509549369618, "grad_norm": 3.722384452819824, "learning_rate": 5.3353976000011456e-06, "loss": 0.117, "step": 446460 }, { "epoch": 2.65391039701363, "grad_norm": 4.0691399574279785, "learning_rate": 5.3351905749334905e-06, "loss": 0.1211, "step": 446470 }, { "epoch": 2.6539698390902986, "grad_norm": 4.3666462898254395, "learning_rate": 5.334983549288596e-06, "loss": 0.1069, "step": 446480 }, { "epoch": 2.654029281166967, "grad_norm": 4.732704162597656, "learning_rate": 5.3347765230668205e-06, "loss": 0.1173, "step": 446490 }, { "epoch": 2.6540887232436354, "grad_norm": 3.5473780632019043, "learning_rate": 5.3345694962685205e-06, "loss": 0.1295, "step": 446500 }, { "epoch": 2.6541481653203034, "grad_norm": 4.254431247711182, "learning_rate": 5.334362468894051e-06, "loss": 0.1248, "step": 446510 }, { "epoch": 2.6542076073969723, "grad_norm": 3.920048713684082, "learning_rate": 5.33415544094377e-06, "loss": 0.1257, "step": 446520 }, { "epoch": 2.6542670494736402, "grad_norm": 3.482909679412842, "learning_rate": 5.333948412418034e-06, "loss": 0.1213, "step": 446530 }, { "epoch": 2.6543264915503086, "grad_norm": 3.9370734691619873, "learning_rate": 5.333741383317197e-06, "loss": 0.1341, "step": 446540 }, { "epoch": 2.654385933626977, "grad_norm": 3.351193904876709, "learning_rate": 5.333534353641618e-06, "loss": 0.1243, "step": 446550 }, { "epoch": 2.6544453757036455, "grad_norm": 4.409763336181641, "learning_rate": 5.333327323391655e-06, "loss": 0.1282, "step": 446560 }, { "epoch": 2.654504817780314, "grad_norm": 5.747643947601318, "learning_rate": 5.333120292567661e-06, "loss": 0.1306, "step": 446570 }, { "epoch": 2.6545642598569823, "grad_norm": 3.9086875915527344, "learning_rate": 5.332913261169994e-06, "loss": 0.1239, "step": 446580 }, { "epoch": 2.6546237019336507, "grad_norm": 3.560784101486206, "learning_rate": 5.3327062291990115e-06, "loss": 0.1137, "step": 446590 }, { "epoch": 2.654683144010319, "grad_norm": 3.425764322280884, "learning_rate": 5.332499196655068e-06, "loss": 0.1234, "step": 446600 }, { "epoch": 2.6547425860869875, "grad_norm": 3.492382287979126, "learning_rate": 5.332292163538523e-06, "loss": 0.11, "step": 446610 }, { "epoch": 2.654802028163656, "grad_norm": 4.161782741546631, "learning_rate": 5.33208512984973e-06, "loss": 0.1215, "step": 446620 }, { "epoch": 2.6548614702403244, "grad_norm": 5.378103256225586, "learning_rate": 5.331878095589047e-06, "loss": 0.1175, "step": 446630 }, { "epoch": 2.654920912316993, "grad_norm": 4.091468334197998, "learning_rate": 5.3316710607568305e-06, "loss": 0.1022, "step": 446640 }, { "epoch": 2.654980354393661, "grad_norm": 3.7753782272338867, "learning_rate": 5.331464025353436e-06, "loss": 0.13, "step": 446650 }, { "epoch": 2.6550397964703296, "grad_norm": 3.9193246364593506, "learning_rate": 5.331256989379222e-06, "loss": 0.1311, "step": 446660 }, { "epoch": 2.655099238546998, "grad_norm": 3.758575439453125, "learning_rate": 5.331049952834544e-06, "loss": 0.1161, "step": 446670 }, { "epoch": 2.655158680623666, "grad_norm": 4.199210166931152, "learning_rate": 5.3308429157197576e-06, "loss": 0.1168, "step": 446680 }, { "epoch": 2.655218122700335, "grad_norm": 3.4414265155792236, "learning_rate": 5.330635878035221e-06, "loss": 0.1131, "step": 446690 }, { "epoch": 2.655277564777003, "grad_norm": 4.411153316497803, "learning_rate": 5.3304288397812896e-06, "loss": 0.1047, "step": 446700 }, { "epoch": 2.6553370068536717, "grad_norm": 4.699330806732178, "learning_rate": 5.330221800958319e-06, "loss": 0.1192, "step": 446710 }, { "epoch": 2.6553964489303397, "grad_norm": 4.459417343139648, "learning_rate": 5.3300147615666696e-06, "loss": 0.1231, "step": 446720 }, { "epoch": 2.655455891007008, "grad_norm": 5.981222152709961, "learning_rate": 5.329807721606695e-06, "loss": 0.1323, "step": 446730 }, { "epoch": 2.6555153330836765, "grad_norm": 3.6862399578094482, "learning_rate": 5.32960068107875e-06, "loss": 0.1131, "step": 446740 }, { "epoch": 2.655574775160345, "grad_norm": 3.6822144985198975, "learning_rate": 5.329393639983195e-06, "loss": 0.1057, "step": 446750 }, { "epoch": 2.6556342172370133, "grad_norm": 5.120001792907715, "learning_rate": 5.329186598320385e-06, "loss": 0.1049, "step": 446760 }, { "epoch": 2.6556936593136817, "grad_norm": 2.721566677093506, "learning_rate": 5.328979556090676e-06, "loss": 0.1126, "step": 446770 }, { "epoch": 2.65575310139035, "grad_norm": 4.028146743774414, "learning_rate": 5.328772513294424e-06, "loss": 0.1229, "step": 446780 }, { "epoch": 2.6558125434670186, "grad_norm": 3.228884220123291, "learning_rate": 5.328565469931987e-06, "loss": 0.1092, "step": 446790 }, { "epoch": 2.655871985543687, "grad_norm": 4.456272125244141, "learning_rate": 5.328358426003721e-06, "loss": 0.1452, "step": 446800 }, { "epoch": 2.6559314276203554, "grad_norm": 4.355833053588867, "learning_rate": 5.328151381509983e-06, "loss": 0.1311, "step": 446810 }, { "epoch": 2.655990869697024, "grad_norm": 3.801680326461792, "learning_rate": 5.32794433645113e-06, "loss": 0.112, "step": 446820 }, { "epoch": 2.656050311773692, "grad_norm": 5.027820110321045, "learning_rate": 5.3277372908275175e-06, "loss": 0.1121, "step": 446830 }, { "epoch": 2.6561097538503606, "grad_norm": 5.225557804107666, "learning_rate": 5.327530244639501e-06, "loss": 0.1278, "step": 446840 }, { "epoch": 2.656169195927029, "grad_norm": 4.465738773345947, "learning_rate": 5.32732319788744e-06, "loss": 0.1188, "step": 446850 }, { "epoch": 2.6562286380036975, "grad_norm": 4.201001167297363, "learning_rate": 5.327116150571688e-06, "loss": 0.1136, "step": 446860 }, { "epoch": 2.6562880800803654, "grad_norm": 5.328307628631592, "learning_rate": 5.326909102692603e-06, "loss": 0.1047, "step": 446870 }, { "epoch": 2.6563475221570343, "grad_norm": 3.238093137741089, "learning_rate": 5.326702054250541e-06, "loss": 0.1157, "step": 446880 }, { "epoch": 2.6564069642337023, "grad_norm": 5.495067119598389, "learning_rate": 5.32649500524586e-06, "loss": 0.1385, "step": 446890 }, { "epoch": 2.656466406310371, "grad_norm": 3.6566669940948486, "learning_rate": 5.326287955678915e-06, "loss": 0.1096, "step": 446900 }, { "epoch": 2.656525848387039, "grad_norm": 4.996544361114502, "learning_rate": 5.326080905550064e-06, "loss": 0.1208, "step": 446910 }, { "epoch": 2.6565852904637075, "grad_norm": 4.0886430740356445, "learning_rate": 5.325873854859663e-06, "loss": 0.1226, "step": 446920 }, { "epoch": 2.656644732540376, "grad_norm": 3.9958629608154297, "learning_rate": 5.3256668036080685e-06, "loss": 0.1176, "step": 446930 }, { "epoch": 2.6567041746170443, "grad_norm": 4.028951168060303, "learning_rate": 5.325459751795636e-06, "loss": 0.1247, "step": 446940 }, { "epoch": 2.6567636166937127, "grad_norm": 2.738722085952759, "learning_rate": 5.325252699422724e-06, "loss": 0.1233, "step": 446950 }, { "epoch": 2.656823058770381, "grad_norm": 3.755171775817871, "learning_rate": 5.325045646489687e-06, "loss": 0.118, "step": 446960 }, { "epoch": 2.6568825008470496, "grad_norm": 4.243041038513184, "learning_rate": 5.324838592996883e-06, "loss": 0.1197, "step": 446970 }, { "epoch": 2.656941942923718, "grad_norm": 2.983757972717285, "learning_rate": 5.3246315389446675e-06, "loss": 0.125, "step": 446980 }, { "epoch": 2.6570013850003864, "grad_norm": 3.34124493598938, "learning_rate": 5.324424484333398e-06, "loss": 0.1147, "step": 446990 }, { "epoch": 2.657060827077055, "grad_norm": 4.650348663330078, "learning_rate": 5.324217429163431e-06, "loss": 0.1234, "step": 447000 }, { "epoch": 2.6571202691537232, "grad_norm": 5.555801868438721, "learning_rate": 5.324010373435124e-06, "loss": 0.1312, "step": 447010 }, { "epoch": 2.6571797112303916, "grad_norm": 3.556403160095215, "learning_rate": 5.323803317148831e-06, "loss": 0.1195, "step": 447020 }, { "epoch": 2.65723915330706, "grad_norm": 4.102579593658447, "learning_rate": 5.32359626030491e-06, "loss": 0.1194, "step": 447030 }, { "epoch": 2.6572985953837285, "grad_norm": 4.221880912780762, "learning_rate": 5.323389202903719e-06, "loss": 0.1432, "step": 447040 }, { "epoch": 2.657358037460397, "grad_norm": 3.9572372436523438, "learning_rate": 5.323182144945614e-06, "loss": 0.1188, "step": 447050 }, { "epoch": 2.657417479537065, "grad_norm": 5.481496334075928, "learning_rate": 5.3229750864309485e-06, "loss": 0.129, "step": 447060 }, { "epoch": 2.6574769216137337, "grad_norm": 5.161598205566406, "learning_rate": 5.322768027360082e-06, "loss": 0.129, "step": 447070 }, { "epoch": 2.6575363636904017, "grad_norm": 4.50380277633667, "learning_rate": 5.322560967733371e-06, "loss": 0.1249, "step": 447080 }, { "epoch": 2.6575958057670706, "grad_norm": 3.4274373054504395, "learning_rate": 5.32235390755117e-06, "loss": 0.1156, "step": 447090 }, { "epoch": 2.6576552478437385, "grad_norm": 4.478356838226318, "learning_rate": 5.322146846813838e-06, "loss": 0.1236, "step": 447100 }, { "epoch": 2.657714689920407, "grad_norm": 4.240091323852539, "learning_rate": 5.321939785521731e-06, "loss": 0.1216, "step": 447110 }, { "epoch": 2.6577741319970754, "grad_norm": 3.973771095275879, "learning_rate": 5.321732723675206e-06, "loss": 0.1318, "step": 447120 }, { "epoch": 2.6578335740737438, "grad_norm": 4.814658164978027, "learning_rate": 5.321525661274617e-06, "loss": 0.1094, "step": 447130 }, { "epoch": 2.657893016150412, "grad_norm": 4.199897289276123, "learning_rate": 5.321318598320324e-06, "loss": 0.1155, "step": 447140 }, { "epoch": 2.6579524582270806, "grad_norm": 2.7850701808929443, "learning_rate": 5.321111534812682e-06, "loss": 0.1189, "step": 447150 }, { "epoch": 2.658011900303749, "grad_norm": 4.957127094268799, "learning_rate": 5.320904470752046e-06, "loss": 0.1251, "step": 447160 }, { "epoch": 2.6580713423804174, "grad_norm": 4.736194610595703, "learning_rate": 5.320697406138776e-06, "loss": 0.1274, "step": 447170 }, { "epoch": 2.658130784457086, "grad_norm": 3.8884775638580322, "learning_rate": 5.320490340973227e-06, "loss": 0.1342, "step": 447180 }, { "epoch": 2.6581902265337543, "grad_norm": 3.5317764282226562, "learning_rate": 5.320283275255754e-06, "loss": 0.1154, "step": 447190 }, { "epoch": 2.6582496686104227, "grad_norm": 4.387539863586426, "learning_rate": 5.320076208986716e-06, "loss": 0.1276, "step": 447200 }, { "epoch": 2.658309110687091, "grad_norm": 3.6272847652435303, "learning_rate": 5.319869142166467e-06, "loss": 0.1262, "step": 447210 }, { "epoch": 2.6583685527637595, "grad_norm": 4.434541702270508, "learning_rate": 5.319662074795367e-06, "loss": 0.142, "step": 447220 }, { "epoch": 2.658427994840428, "grad_norm": 4.579322814941406, "learning_rate": 5.31945500687377e-06, "loss": 0.1264, "step": 447230 }, { "epoch": 2.6584874369170963, "grad_norm": 4.280593395233154, "learning_rate": 5.319247938402033e-06, "loss": 0.1307, "step": 447240 }, { "epoch": 2.6585468789937643, "grad_norm": 4.155879020690918, "learning_rate": 5.319040869380514e-06, "loss": 0.126, "step": 447250 }, { "epoch": 2.658606321070433, "grad_norm": 4.61094331741333, "learning_rate": 5.318833799809567e-06, "loss": 0.1277, "step": 447260 }, { "epoch": 2.658665763147101, "grad_norm": 4.8318257331848145, "learning_rate": 5.318626729689552e-06, "loss": 0.1296, "step": 447270 }, { "epoch": 2.6587252052237695, "grad_norm": 5.78536319732666, "learning_rate": 5.318419659020823e-06, "loss": 0.1361, "step": 447280 }, { "epoch": 2.658784647300438, "grad_norm": 3.188842296600342, "learning_rate": 5.318212587803737e-06, "loss": 0.1063, "step": 447290 }, { "epoch": 2.6588440893771064, "grad_norm": 3.621328115463257, "learning_rate": 5.318005516038652e-06, "loss": 0.1181, "step": 447300 }, { "epoch": 2.658903531453775, "grad_norm": 4.050988674163818, "learning_rate": 5.317798443725922e-06, "loss": 0.123, "step": 447310 }, { "epoch": 2.658962973530443, "grad_norm": 3.0002496242523193, "learning_rate": 5.317591370865905e-06, "loss": 0.1224, "step": 447320 }, { "epoch": 2.6590224156071116, "grad_norm": 5.535968780517578, "learning_rate": 5.317384297458958e-06, "loss": 0.1405, "step": 447330 }, { "epoch": 2.65908185768378, "grad_norm": 4.4155402183532715, "learning_rate": 5.317177223505439e-06, "loss": 0.1305, "step": 447340 }, { "epoch": 2.6591412997604484, "grad_norm": 2.482276201248169, "learning_rate": 5.316970149005702e-06, "loss": 0.1273, "step": 447350 }, { "epoch": 2.659200741837117, "grad_norm": 4.217694282531738, "learning_rate": 5.316763073960104e-06, "loss": 0.1325, "step": 447360 }, { "epoch": 2.6592601839137853, "grad_norm": 4.21707010269165, "learning_rate": 5.316555998369003e-06, "loss": 0.1226, "step": 447370 }, { "epoch": 2.6593196259904537, "grad_norm": 3.6981563568115234, "learning_rate": 5.316348922232756e-06, "loss": 0.1118, "step": 447380 }, { "epoch": 2.659379068067122, "grad_norm": 4.473934650421143, "learning_rate": 5.316141845551716e-06, "loss": 0.1256, "step": 447390 }, { "epoch": 2.6594385101437905, "grad_norm": 3.093343734741211, "learning_rate": 5.315934768326243e-06, "loss": 0.1217, "step": 447400 }, { "epoch": 2.659497952220459, "grad_norm": 4.385798931121826, "learning_rate": 5.315727690556694e-06, "loss": 0.1123, "step": 447410 }, { "epoch": 2.659557394297127, "grad_norm": 5.533206939697266, "learning_rate": 5.315520612243421e-06, "loss": 0.1213, "step": 447420 }, { "epoch": 2.6596168363737958, "grad_norm": 4.460880279541016, "learning_rate": 5.315313533386785e-06, "loss": 0.1362, "step": 447430 }, { "epoch": 2.6596762784504637, "grad_norm": 5.349857807159424, "learning_rate": 5.315106453987143e-06, "loss": 0.1305, "step": 447440 }, { "epoch": 2.6597357205271326, "grad_norm": 3.650202751159668, "learning_rate": 5.31489937404485e-06, "loss": 0.1276, "step": 447450 }, { "epoch": 2.6597951626038006, "grad_norm": 4.361542224884033, "learning_rate": 5.314692293560261e-06, "loss": 0.1259, "step": 447460 }, { "epoch": 2.659854604680469, "grad_norm": 3.055712938308716, "learning_rate": 5.314485212533736e-06, "loss": 0.1129, "step": 447470 }, { "epoch": 2.6599140467571374, "grad_norm": 3.3514113426208496, "learning_rate": 5.31427813096563e-06, "loss": 0.1132, "step": 447480 }, { "epoch": 2.659973488833806, "grad_norm": 4.349278926849365, "learning_rate": 5.3140710488562975e-06, "loss": 0.1221, "step": 447490 }, { "epoch": 2.660032930910474, "grad_norm": 3.9121627807617188, "learning_rate": 5.313863966206098e-06, "loss": 0.1159, "step": 447500 }, { "epoch": 2.6600923729871426, "grad_norm": 5.509382247924805, "learning_rate": 5.313656883015389e-06, "loss": 0.1265, "step": 447510 }, { "epoch": 2.660151815063811, "grad_norm": 5.193819046020508, "learning_rate": 5.313449799284523e-06, "loss": 0.1353, "step": 447520 }, { "epoch": 2.6602112571404795, "grad_norm": 3.8344333171844482, "learning_rate": 5.313242715013861e-06, "loss": 0.1193, "step": 447530 }, { "epoch": 2.660270699217148, "grad_norm": 4.145510196685791, "learning_rate": 5.313035630203757e-06, "loss": 0.1241, "step": 447540 }, { "epoch": 2.6603301412938163, "grad_norm": 5.276274681091309, "learning_rate": 5.312828544854567e-06, "loss": 0.1253, "step": 447550 }, { "epoch": 2.6603895833704847, "grad_norm": 3.736783981323242, "learning_rate": 5.312621458966651e-06, "loss": 0.1131, "step": 447560 }, { "epoch": 2.660449025447153, "grad_norm": 3.22817063331604, "learning_rate": 5.312414372540363e-06, "loss": 0.1088, "step": 447570 }, { "epoch": 2.6605084675238215, "grad_norm": 3.4209351539611816, "learning_rate": 5.31220728557606e-06, "loss": 0.1191, "step": 447580 }, { "epoch": 2.66056790960049, "grad_norm": 4.131827354431152, "learning_rate": 5.312000198074099e-06, "loss": 0.129, "step": 447590 }, { "epoch": 2.6606273516771584, "grad_norm": 3.375145196914673, "learning_rate": 5.311793110034835e-06, "loss": 0.1233, "step": 447600 }, { "epoch": 2.6606867937538263, "grad_norm": 3.876950263977051, "learning_rate": 5.311586021458628e-06, "loss": 0.1337, "step": 447610 }, { "epoch": 2.660746235830495, "grad_norm": 4.292958736419678, "learning_rate": 5.3113789323458324e-06, "loss": 0.1371, "step": 447620 }, { "epoch": 2.660805677907163, "grad_norm": 3.9403414726257324, "learning_rate": 5.311171842696804e-06, "loss": 0.1032, "step": 447630 }, { "epoch": 2.660865119983832, "grad_norm": 4.226943016052246, "learning_rate": 5.3109647525119015e-06, "loss": 0.0997, "step": 447640 }, { "epoch": 2.6609245620605, "grad_norm": 4.646777629852295, "learning_rate": 5.310757661791479e-06, "loss": 0.1114, "step": 447650 }, { "epoch": 2.6609840041371684, "grad_norm": 3.6613962650299072, "learning_rate": 5.310550570535896e-06, "loss": 0.1102, "step": 447660 }, { "epoch": 2.661043446213837, "grad_norm": 4.643214225769043, "learning_rate": 5.310343478745508e-06, "loss": 0.1172, "step": 447670 }, { "epoch": 2.6611028882905052, "grad_norm": 4.332196235656738, "learning_rate": 5.310136386420671e-06, "loss": 0.1294, "step": 447680 }, { "epoch": 2.6611623303671736, "grad_norm": 3.660635471343994, "learning_rate": 5.309929293561743e-06, "loss": 0.1284, "step": 447690 }, { "epoch": 2.661221772443842, "grad_norm": 3.8335108757019043, "learning_rate": 5.30972220016908e-06, "loss": 0.1425, "step": 447700 }, { "epoch": 2.6612812145205105, "grad_norm": 4.083949565887451, "learning_rate": 5.309515106243036e-06, "loss": 0.1348, "step": 447710 }, { "epoch": 2.661340656597179, "grad_norm": 3.5086164474487305, "learning_rate": 5.309308011783973e-06, "loss": 0.1179, "step": 447720 }, { "epoch": 2.6614000986738473, "grad_norm": 5.544813632965088, "learning_rate": 5.3091009167922435e-06, "loss": 0.1415, "step": 447730 }, { "epoch": 2.6614595407505157, "grad_norm": 4.790763854980469, "learning_rate": 5.308893821268204e-06, "loss": 0.1203, "step": 447740 }, { "epoch": 2.661518982827184, "grad_norm": 3.810037136077881, "learning_rate": 5.3086867252122145e-06, "loss": 0.1022, "step": 447750 }, { "epoch": 2.6615784249038525, "grad_norm": 3.2464914321899414, "learning_rate": 5.308479628624629e-06, "loss": 0.1287, "step": 447760 }, { "epoch": 2.661637866980521, "grad_norm": 4.42368221282959, "learning_rate": 5.308272531505805e-06, "loss": 0.1091, "step": 447770 }, { "epoch": 2.6616973090571894, "grad_norm": 4.0285234451293945, "learning_rate": 5.308065433856097e-06, "loss": 0.1144, "step": 447780 }, { "epoch": 2.661756751133858, "grad_norm": 4.734554767608643, "learning_rate": 5.307858335675866e-06, "loss": 0.1217, "step": 447790 }, { "epoch": 2.6618161932105258, "grad_norm": 3.4741997718811035, "learning_rate": 5.307651236965466e-06, "loss": 0.1249, "step": 447800 }, { "epoch": 2.6618756352871946, "grad_norm": 4.247694969177246, "learning_rate": 5.307444137725251e-06, "loss": 0.1125, "step": 447810 }, { "epoch": 2.6619350773638626, "grad_norm": 3.6439614295959473, "learning_rate": 5.307237037955584e-06, "loss": 0.1188, "step": 447820 }, { "epoch": 2.6619945194405314, "grad_norm": 3.436922311782837, "learning_rate": 5.307029937656818e-06, "loss": 0.1055, "step": 447830 }, { "epoch": 2.6620539615171994, "grad_norm": 3.8839573860168457, "learning_rate": 5.306822836829307e-06, "loss": 0.1091, "step": 447840 }, { "epoch": 2.662113403593868, "grad_norm": 4.57455587387085, "learning_rate": 5.306615735473413e-06, "loss": 0.1293, "step": 447850 }, { "epoch": 2.6621728456705362, "grad_norm": 3.6019508838653564, "learning_rate": 5.306408633589489e-06, "loss": 0.1224, "step": 447860 }, { "epoch": 2.6622322877472047, "grad_norm": 3.855010747909546, "learning_rate": 5.306201531177893e-06, "loss": 0.1165, "step": 447870 }, { "epoch": 2.662291729823873, "grad_norm": 4.551698207855225, "learning_rate": 5.30599442823898e-06, "loss": 0.1203, "step": 447880 }, { "epoch": 2.6623511719005415, "grad_norm": 3.1565873622894287, "learning_rate": 5.305787324773111e-06, "loss": 0.1234, "step": 447890 }, { "epoch": 2.66241061397721, "grad_norm": 5.138214588165283, "learning_rate": 5.305580220780639e-06, "loss": 0.1334, "step": 447900 }, { "epoch": 2.6624700560538783, "grad_norm": 3.758090019226074, "learning_rate": 5.305373116261919e-06, "loss": 0.1128, "step": 447910 }, { "epoch": 2.6625294981305467, "grad_norm": 5.001094341278076, "learning_rate": 5.305166011217313e-06, "loss": 0.1134, "step": 447920 }, { "epoch": 2.662588940207215, "grad_norm": 3.98287296295166, "learning_rate": 5.304958905647174e-06, "loss": 0.1326, "step": 447930 }, { "epoch": 2.6626483822838836, "grad_norm": 4.730649471282959, "learning_rate": 5.304751799551857e-06, "loss": 0.1258, "step": 447940 }, { "epoch": 2.662707824360552, "grad_norm": 4.175243377685547, "learning_rate": 5.304544692931723e-06, "loss": 0.115, "step": 447950 }, { "epoch": 2.6627672664372204, "grad_norm": 4.006430149078369, "learning_rate": 5.304337585787128e-06, "loss": 0.1175, "step": 447960 }, { "epoch": 2.662826708513889, "grad_norm": 3.363600969314575, "learning_rate": 5.304130478118426e-06, "loss": 0.1185, "step": 447970 }, { "epoch": 2.662886150590557, "grad_norm": 3.4796993732452393, "learning_rate": 5.303923369925974e-06, "loss": 0.1236, "step": 447980 }, { "epoch": 2.662945592667225, "grad_norm": 5.139811992645264, "learning_rate": 5.30371626121013e-06, "loss": 0.1365, "step": 447990 }, { "epoch": 2.663005034743894, "grad_norm": 4.974935054779053, "learning_rate": 5.303509151971252e-06, "loss": 0.1076, "step": 448000 }, { "epoch": 2.663064476820562, "grad_norm": 4.010995388031006, "learning_rate": 5.303302042209693e-06, "loss": 0.1199, "step": 448010 }, { "epoch": 2.6631239188972304, "grad_norm": 3.6045875549316406, "learning_rate": 5.303094931925814e-06, "loss": 0.1093, "step": 448020 }, { "epoch": 2.663183360973899, "grad_norm": 5.611828327178955, "learning_rate": 5.302887821119969e-06, "loss": 0.1291, "step": 448030 }, { "epoch": 2.6632428030505673, "grad_norm": 3.3534016609191895, "learning_rate": 5.302680709792512e-06, "loss": 0.1154, "step": 448040 }, { "epoch": 2.6633022451272357, "grad_norm": 3.9586637020111084, "learning_rate": 5.302473597943806e-06, "loss": 0.1261, "step": 448050 }, { "epoch": 2.663361687203904, "grad_norm": 3.1530587673187256, "learning_rate": 5.302266485574203e-06, "loss": 0.1202, "step": 448060 }, { "epoch": 2.6634211292805725, "grad_norm": 2.8588080406188965, "learning_rate": 5.3020593726840604e-06, "loss": 0.1162, "step": 448070 }, { "epoch": 2.663480571357241, "grad_norm": 4.95117712020874, "learning_rate": 5.301852259273738e-06, "loss": 0.1266, "step": 448080 }, { "epoch": 2.6635400134339093, "grad_norm": 4.292497634887695, "learning_rate": 5.301645145343587e-06, "loss": 0.1187, "step": 448090 }, { "epoch": 2.6635994555105778, "grad_norm": 3.6661999225616455, "learning_rate": 5.301438030893969e-06, "loss": 0.114, "step": 448100 }, { "epoch": 2.663658897587246, "grad_norm": 3.6621949672698975, "learning_rate": 5.3012309159252376e-06, "loss": 0.1147, "step": 448110 }, { "epoch": 2.6637183396639146, "grad_norm": 3.3002235889434814, "learning_rate": 5.301023800437751e-06, "loss": 0.1329, "step": 448120 }, { "epoch": 2.663777781740583, "grad_norm": 3.4142229557037354, "learning_rate": 5.300816684431867e-06, "loss": 0.1222, "step": 448130 }, { "epoch": 2.6638372238172514, "grad_norm": 4.6569318771362305, "learning_rate": 5.300609567907938e-06, "loss": 0.1224, "step": 448140 }, { "epoch": 2.66389666589392, "grad_norm": 3.7611007690429688, "learning_rate": 5.300402450866325e-06, "loss": 0.1065, "step": 448150 }, { "epoch": 2.663956107970588, "grad_norm": 3.2179670333862305, "learning_rate": 5.3001953333073844e-06, "loss": 0.1145, "step": 448160 }, { "epoch": 2.6640155500472567, "grad_norm": 4.153285026550293, "learning_rate": 5.29998821523147e-06, "loss": 0.1183, "step": 448170 }, { "epoch": 2.6640749921239246, "grad_norm": 2.932093620300293, "learning_rate": 5.29978109663894e-06, "loss": 0.1155, "step": 448180 }, { "epoch": 2.6641344342005935, "grad_norm": 3.215940237045288, "learning_rate": 5.299573977530153e-06, "loss": 0.1327, "step": 448190 }, { "epoch": 2.6641938762772615, "grad_norm": 4.175328254699707, "learning_rate": 5.29936685790546e-06, "loss": 0.114, "step": 448200 }, { "epoch": 2.66425331835393, "grad_norm": 3.0314126014709473, "learning_rate": 5.299159737765224e-06, "loss": 0.1086, "step": 448210 }, { "epoch": 2.6643127604305983, "grad_norm": 4.405686855316162, "learning_rate": 5.298952617109799e-06, "loss": 0.1156, "step": 448220 }, { "epoch": 2.6643722025072667, "grad_norm": 5.096059799194336, "learning_rate": 5.298745495939543e-06, "loss": 0.1228, "step": 448230 }, { "epoch": 2.664431644583935, "grad_norm": 5.044579029083252, "learning_rate": 5.29853837425481e-06, "loss": 0.1189, "step": 448240 }, { "epoch": 2.6644910866606035, "grad_norm": 3.688175678253174, "learning_rate": 5.29833125205596e-06, "loss": 0.1051, "step": 448250 }, { "epoch": 2.664550528737272, "grad_norm": 3.8924834728240967, "learning_rate": 5.298124129343347e-06, "loss": 0.1155, "step": 448260 }, { "epoch": 2.6646099708139404, "grad_norm": 4.146648406982422, "learning_rate": 5.297917006117328e-06, "loss": 0.1174, "step": 448270 }, { "epoch": 2.6646694128906088, "grad_norm": 3.239168643951416, "learning_rate": 5.297709882378262e-06, "loss": 0.1365, "step": 448280 }, { "epoch": 2.664728854967277, "grad_norm": 3.960350513458252, "learning_rate": 5.297502758126504e-06, "loss": 0.1292, "step": 448290 }, { "epoch": 2.6647882970439456, "grad_norm": 3.2920210361480713, "learning_rate": 5.29729563336241e-06, "loss": 0.1317, "step": 448300 }, { "epoch": 2.664847739120614, "grad_norm": 3.20206880569458, "learning_rate": 5.297088508086335e-06, "loss": 0.1308, "step": 448310 }, { "epoch": 2.6649071811972824, "grad_norm": 3.2642822265625, "learning_rate": 5.296881382298641e-06, "loss": 0.1205, "step": 448320 }, { "epoch": 2.664966623273951, "grad_norm": 2.4328322410583496, "learning_rate": 5.296674255999681e-06, "loss": 0.1043, "step": 448330 }, { "epoch": 2.6650260653506193, "grad_norm": 3.130950689315796, "learning_rate": 5.296467129189813e-06, "loss": 0.1318, "step": 448340 }, { "epoch": 2.6650855074272872, "grad_norm": 4.073423862457275, "learning_rate": 5.296260001869393e-06, "loss": 0.1269, "step": 448350 }, { "epoch": 2.665144949503956, "grad_norm": 3.4445605278015137, "learning_rate": 5.296052874038779e-06, "loss": 0.1105, "step": 448360 }, { "epoch": 2.665204391580624, "grad_norm": 4.205972671508789, "learning_rate": 5.295845745698325e-06, "loss": 0.1222, "step": 448370 }, { "epoch": 2.665263833657293, "grad_norm": 5.085396766662598, "learning_rate": 5.295638616848391e-06, "loss": 0.1293, "step": 448380 }, { "epoch": 2.665323275733961, "grad_norm": 5.653084754943848, "learning_rate": 5.29543148748933e-06, "loss": 0.134, "step": 448390 }, { "epoch": 2.6653827178106293, "grad_norm": 4.2901611328125, "learning_rate": 5.295224357621503e-06, "loss": 0.1191, "step": 448400 }, { "epoch": 2.6654421598872977, "grad_norm": 5.329747676849365, "learning_rate": 5.295017227245263e-06, "loss": 0.1227, "step": 448410 }, { "epoch": 2.665501601963966, "grad_norm": 5.408218860626221, "learning_rate": 5.294810096360967e-06, "loss": 0.1326, "step": 448420 }, { "epoch": 2.6655610440406345, "grad_norm": 4.542757511138916, "learning_rate": 5.294602964968974e-06, "loss": 0.1033, "step": 448430 }, { "epoch": 2.665620486117303, "grad_norm": 3.1266539096832275, "learning_rate": 5.29439583306964e-06, "loss": 0.1263, "step": 448440 }, { "epoch": 2.6656799281939714, "grad_norm": 3.3116109371185303, "learning_rate": 5.294188700663321e-06, "loss": 0.1181, "step": 448450 }, { "epoch": 2.66573937027064, "grad_norm": 5.230266571044922, "learning_rate": 5.293981567750374e-06, "loss": 0.1211, "step": 448460 }, { "epoch": 2.665798812347308, "grad_norm": 3.000030517578125, "learning_rate": 5.2937744343311546e-06, "loss": 0.1035, "step": 448470 }, { "epoch": 2.6658582544239766, "grad_norm": 3.0460665225982666, "learning_rate": 5.293567300406023e-06, "loss": 0.106, "step": 448480 }, { "epoch": 2.665917696500645, "grad_norm": 4.041134357452393, "learning_rate": 5.293360165975331e-06, "loss": 0.1368, "step": 448490 }, { "epoch": 2.6659771385773134, "grad_norm": 3.028677463531494, "learning_rate": 5.293153031039439e-06, "loss": 0.1101, "step": 448500 }, { "epoch": 2.666036580653982, "grad_norm": 3.8623509407043457, "learning_rate": 5.292945895598702e-06, "loss": 0.1421, "step": 448510 }, { "epoch": 2.6660960227306503, "grad_norm": 5.034003734588623, "learning_rate": 5.292738759653477e-06, "loss": 0.1353, "step": 448520 }, { "epoch": 2.6661554648073187, "grad_norm": 5.02713680267334, "learning_rate": 5.292531623204121e-06, "loss": 0.1218, "step": 448530 }, { "epoch": 2.6662149068839867, "grad_norm": 4.384274005889893, "learning_rate": 5.292324486250991e-06, "loss": 0.1169, "step": 448540 }, { "epoch": 2.6662743489606555, "grad_norm": 4.056649208068848, "learning_rate": 5.2921173487944444e-06, "loss": 0.1146, "step": 448550 }, { "epoch": 2.6663337910373235, "grad_norm": 4.073828220367432, "learning_rate": 5.291910210834835e-06, "loss": 0.1379, "step": 448560 }, { "epoch": 2.6663932331139923, "grad_norm": 3.9781222343444824, "learning_rate": 5.291703072372522e-06, "loss": 0.1289, "step": 448570 }, { "epoch": 2.6664526751906603, "grad_norm": 3.0026204586029053, "learning_rate": 5.291495933407863e-06, "loss": 0.1324, "step": 448580 }, { "epoch": 2.6665121172673287, "grad_norm": 3.1885838508605957, "learning_rate": 5.291288793941212e-06, "loss": 0.1168, "step": 448590 }, { "epoch": 2.666571559343997, "grad_norm": 4.3904876708984375, "learning_rate": 5.291081653972927e-06, "loss": 0.1125, "step": 448600 }, { "epoch": 2.6666310014206656, "grad_norm": 4.142580032348633, "learning_rate": 5.290874513503364e-06, "loss": 0.1179, "step": 448610 }, { "epoch": 2.666690443497334, "grad_norm": 3.1976659297943115, "learning_rate": 5.290667372532882e-06, "loss": 0.1237, "step": 448620 }, { "epoch": 2.6667498855740024, "grad_norm": 4.403047561645508, "learning_rate": 5.290460231061835e-06, "loss": 0.1167, "step": 448630 }, { "epoch": 2.666809327650671, "grad_norm": 4.171753883361816, "learning_rate": 5.29025308909058e-06, "loss": 0.1146, "step": 448640 }, { "epoch": 2.666868769727339, "grad_norm": 3.265839099884033, "learning_rate": 5.2900459466194765e-06, "loss": 0.1164, "step": 448650 }, { "epoch": 2.6669282118040076, "grad_norm": 3.888190269470215, "learning_rate": 5.289838803648877e-06, "loss": 0.1241, "step": 448660 }, { "epoch": 2.666987653880676, "grad_norm": 4.444847583770752, "learning_rate": 5.289631660179142e-06, "loss": 0.1144, "step": 448670 }, { "epoch": 2.6670470959573445, "grad_norm": 4.824432849884033, "learning_rate": 5.2894245162106276e-06, "loss": 0.1311, "step": 448680 }, { "epoch": 2.667106538034013, "grad_norm": 2.666527509689331, "learning_rate": 5.289217371743687e-06, "loss": 0.1146, "step": 448690 }, { "epoch": 2.6671659801106813, "grad_norm": 3.238952159881592, "learning_rate": 5.289010226778682e-06, "loss": 0.1229, "step": 448700 }, { "epoch": 2.6672254221873497, "grad_norm": 3.9226772785186768, "learning_rate": 5.288803081315967e-06, "loss": 0.1306, "step": 448710 }, { "epoch": 2.667284864264018, "grad_norm": 4.491520404815674, "learning_rate": 5.288595935355896e-06, "loss": 0.1197, "step": 448720 }, { "epoch": 2.667344306340686, "grad_norm": 3.5477659702301025, "learning_rate": 5.28838878889883e-06, "loss": 0.1278, "step": 448730 }, { "epoch": 2.667403748417355, "grad_norm": 4.868275165557861, "learning_rate": 5.288181641945125e-06, "loss": 0.1189, "step": 448740 }, { "epoch": 2.667463190494023, "grad_norm": 4.232863903045654, "learning_rate": 5.287974494495135e-06, "loss": 0.1302, "step": 448750 }, { "epoch": 2.6675226325706913, "grad_norm": 5.042425155639648, "learning_rate": 5.287767346549218e-06, "loss": 0.1074, "step": 448760 }, { "epoch": 2.6675820746473597, "grad_norm": 3.128192663192749, "learning_rate": 5.287560198107734e-06, "loss": 0.1312, "step": 448770 }, { "epoch": 2.667641516724028, "grad_norm": 3.691847085952759, "learning_rate": 5.287353049171037e-06, "loss": 0.1114, "step": 448780 }, { "epoch": 2.6677009588006966, "grad_norm": 4.907653331756592, "learning_rate": 5.287145899739481e-06, "loss": 0.1283, "step": 448790 }, { "epoch": 2.667760400877365, "grad_norm": 3.6919353008270264, "learning_rate": 5.286938749813427e-06, "loss": 0.1198, "step": 448800 }, { "epoch": 2.6678198429540334, "grad_norm": 3.847010612487793, "learning_rate": 5.286731599393231e-06, "loss": 0.1356, "step": 448810 }, { "epoch": 2.667879285030702, "grad_norm": 4.116649150848389, "learning_rate": 5.286524448479248e-06, "loss": 0.121, "step": 448820 }, { "epoch": 2.6679387271073702, "grad_norm": 5.701637268066406, "learning_rate": 5.286317297071837e-06, "loss": 0.1333, "step": 448830 }, { "epoch": 2.6679981691840386, "grad_norm": 4.6292500495910645, "learning_rate": 5.286110145171352e-06, "loss": 0.1216, "step": 448840 }, { "epoch": 2.668057611260707, "grad_norm": 3.9814727306365967, "learning_rate": 5.285902992778152e-06, "loss": 0.1352, "step": 448850 }, { "epoch": 2.6681170533373755, "grad_norm": 4.5050177574157715, "learning_rate": 5.2856958398925905e-06, "loss": 0.1331, "step": 448860 }, { "epoch": 2.668176495414044, "grad_norm": 3.751347780227661, "learning_rate": 5.28548868651503e-06, "loss": 0.1084, "step": 448870 }, { "epoch": 2.6682359374907123, "grad_norm": 4.596189022064209, "learning_rate": 5.2852815326458215e-06, "loss": 0.1198, "step": 448880 }, { "epoch": 2.6682953795673807, "grad_norm": 5.390028953552246, "learning_rate": 5.285074378285325e-06, "loss": 0.1296, "step": 448890 }, { "epoch": 2.6683548216440487, "grad_norm": 4.330114841461182, "learning_rate": 5.284867223433898e-06, "loss": 0.1154, "step": 448900 }, { "epoch": 2.6684142637207175, "grad_norm": 4.442619323730469, "learning_rate": 5.284660068091895e-06, "loss": 0.1199, "step": 448910 }, { "epoch": 2.6684737057973855, "grad_norm": 3.7941110134124756, "learning_rate": 5.284452912259672e-06, "loss": 0.1125, "step": 448920 }, { "epoch": 2.6685331478740544, "grad_norm": 3.0943219661712646, "learning_rate": 5.284245755937588e-06, "loss": 0.1129, "step": 448930 }, { "epoch": 2.6685925899507223, "grad_norm": 3.7973337173461914, "learning_rate": 5.284038599125999e-06, "loss": 0.1154, "step": 448940 }, { "epoch": 2.6686520320273908, "grad_norm": 3.6510725021362305, "learning_rate": 5.283831441825261e-06, "loss": 0.1314, "step": 448950 }, { "epoch": 2.668711474104059, "grad_norm": 4.036163806915283, "learning_rate": 5.283624284035732e-06, "loss": 0.1263, "step": 448960 }, { "epoch": 2.6687709161807276, "grad_norm": 3.7667276859283447, "learning_rate": 5.283417125757767e-06, "loss": 0.1184, "step": 448970 }, { "epoch": 2.668830358257396, "grad_norm": 5.585535049438477, "learning_rate": 5.283209966991724e-06, "loss": 0.1221, "step": 448980 }, { "epoch": 2.6688898003340644, "grad_norm": 3.9944469928741455, "learning_rate": 5.283002807737961e-06, "loss": 0.1179, "step": 448990 }, { "epoch": 2.668949242410733, "grad_norm": 5.272929668426514, "learning_rate": 5.282795647996835e-06, "loss": 0.1265, "step": 449000 }, { "epoch": 2.6690086844874013, "grad_norm": 4.194314479827881, "learning_rate": 5.282588487768697e-06, "loss": 0.1183, "step": 449010 }, { "epoch": 2.6690681265640697, "grad_norm": 5.552199363708496, "learning_rate": 5.28238132705391e-06, "loss": 0.1256, "step": 449020 }, { "epoch": 2.669127568640738, "grad_norm": 5.236148357391357, "learning_rate": 5.28217416585283e-06, "loss": 0.1134, "step": 449030 }, { "epoch": 2.6691870107174065, "grad_norm": 4.413885593414307, "learning_rate": 5.28196700416581e-06, "loss": 0.1232, "step": 449040 }, { "epoch": 2.669246452794075, "grad_norm": 4.242066383361816, "learning_rate": 5.28175984199321e-06, "loss": 0.1469, "step": 449050 }, { "epoch": 2.6693058948707433, "grad_norm": 3.8565006256103516, "learning_rate": 5.281552679335388e-06, "loss": 0.1142, "step": 449060 }, { "epoch": 2.6693653369474117, "grad_norm": 3.957920789718628, "learning_rate": 5.281345516192695e-06, "loss": 0.1219, "step": 449070 }, { "epoch": 2.66942477902408, "grad_norm": 2.638993740081787, "learning_rate": 5.281138352565494e-06, "loss": 0.122, "step": 449080 }, { "epoch": 2.669484221100748, "grad_norm": 3.45600962638855, "learning_rate": 5.280931188454138e-06, "loss": 0.1274, "step": 449090 }, { "epoch": 2.669543663177417, "grad_norm": 3.6760170459747314, "learning_rate": 5.280724023858986e-06, "loss": 0.1289, "step": 449100 }, { "epoch": 2.669603105254085, "grad_norm": 3.1552178859710693, "learning_rate": 5.280516858780392e-06, "loss": 0.1114, "step": 449110 }, { "epoch": 2.669662547330754, "grad_norm": 3.1781556606292725, "learning_rate": 5.280309693218717e-06, "loss": 0.1181, "step": 449120 }, { "epoch": 2.669721989407422, "grad_norm": 4.485543727874756, "learning_rate": 5.280102527174314e-06, "loss": 0.1161, "step": 449130 }, { "epoch": 2.66978143148409, "grad_norm": 3.6741480827331543, "learning_rate": 5.27989536064754e-06, "loss": 0.1113, "step": 449140 }, { "epoch": 2.6698408735607586, "grad_norm": 3.66412091255188, "learning_rate": 5.279688193638755e-06, "loss": 0.1282, "step": 449150 }, { "epoch": 2.669900315637427, "grad_norm": 3.5466389656066895, "learning_rate": 5.279481026148312e-06, "loss": 0.0974, "step": 449160 }, { "epoch": 2.6699597577140954, "grad_norm": 3.546215057373047, "learning_rate": 5.279273858176569e-06, "loss": 0.1253, "step": 449170 }, { "epoch": 2.670019199790764, "grad_norm": 3.3612358570098877, "learning_rate": 5.279066689723884e-06, "loss": 0.1262, "step": 449180 }, { "epoch": 2.6700786418674323, "grad_norm": 2.779542922973633, "learning_rate": 5.278859520790612e-06, "loss": 0.1143, "step": 449190 }, { "epoch": 2.6701380839441007, "grad_norm": 4.440036773681641, "learning_rate": 5.278652351377112e-06, "loss": 0.1308, "step": 449200 }, { "epoch": 2.670197526020769, "grad_norm": 3.7804276943206787, "learning_rate": 5.278445181483738e-06, "loss": 0.1329, "step": 449210 }, { "epoch": 2.6702569680974375, "grad_norm": 3.6081130504608154, "learning_rate": 5.278238011110849e-06, "loss": 0.1075, "step": 449220 }, { "epoch": 2.670316410174106, "grad_norm": 5.2218918800354, "learning_rate": 5.278030840258802e-06, "loss": 0.1294, "step": 449230 }, { "epoch": 2.6703758522507743, "grad_norm": 4.649643421173096, "learning_rate": 5.27782366892795e-06, "loss": 0.1213, "step": 449240 }, { "epoch": 2.6704352943274428, "grad_norm": 4.861642360687256, "learning_rate": 5.277616497118655e-06, "loss": 0.132, "step": 449250 }, { "epoch": 2.670494736404111, "grad_norm": 3.2720131874084473, "learning_rate": 5.2774093248312705e-06, "loss": 0.1409, "step": 449260 }, { "epoch": 2.6705541784807796, "grad_norm": 4.458037853240967, "learning_rate": 5.2772021520661535e-06, "loss": 0.1039, "step": 449270 }, { "epoch": 2.6706136205574476, "grad_norm": 4.610779285430908, "learning_rate": 5.2769949788236614e-06, "loss": 0.1158, "step": 449280 }, { "epoch": 2.6706730626341164, "grad_norm": 3.496680498123169, "learning_rate": 5.276787805104152e-06, "loss": 0.1144, "step": 449290 }, { "epoch": 2.6707325047107844, "grad_norm": 4.043439865112305, "learning_rate": 5.276580630907979e-06, "loss": 0.1195, "step": 449300 }, { "epoch": 2.6707919467874532, "grad_norm": 4.062553405761719, "learning_rate": 5.276373456235502e-06, "loss": 0.1198, "step": 449310 }, { "epoch": 2.670851388864121, "grad_norm": 4.318353176116943, "learning_rate": 5.276166281087077e-06, "loss": 0.12, "step": 449320 }, { "epoch": 2.6709108309407896, "grad_norm": 4.009129524230957, "learning_rate": 5.275959105463062e-06, "loss": 0.1174, "step": 449330 }, { "epoch": 2.670970273017458, "grad_norm": 3.7354555130004883, "learning_rate": 5.275751929363811e-06, "loss": 0.1298, "step": 449340 }, { "epoch": 2.6710297150941265, "grad_norm": 2.7475719451904297, "learning_rate": 5.275544752789683e-06, "loss": 0.1139, "step": 449350 }, { "epoch": 2.671089157170795, "grad_norm": 3.169009208679199, "learning_rate": 5.275337575741034e-06, "loss": 0.1058, "step": 449360 }, { "epoch": 2.6711485992474633, "grad_norm": 4.267276287078857, "learning_rate": 5.27513039821822e-06, "loss": 0.1233, "step": 449370 }, { "epoch": 2.6712080413241317, "grad_norm": 4.241061210632324, "learning_rate": 5.274923220221599e-06, "loss": 0.1391, "step": 449380 }, { "epoch": 2.6712674834008, "grad_norm": 4.177978515625, "learning_rate": 5.274716041751529e-06, "loss": 0.1132, "step": 449390 }, { "epoch": 2.6713269254774685, "grad_norm": 3.856055736541748, "learning_rate": 5.274508862808362e-06, "loss": 0.1226, "step": 449400 }, { "epoch": 2.671386367554137, "grad_norm": 4.764235496520996, "learning_rate": 5.27430168339246e-06, "loss": 0.1255, "step": 449410 }, { "epoch": 2.6714458096308054, "grad_norm": 4.9758195877075195, "learning_rate": 5.274094503504177e-06, "loss": 0.1229, "step": 449420 }, { "epoch": 2.6715052517074738, "grad_norm": 4.71953821182251, "learning_rate": 5.273887323143871e-06, "loss": 0.1253, "step": 449430 }, { "epoch": 2.671564693784142, "grad_norm": 4.798566818237305, "learning_rate": 5.273680142311899e-06, "loss": 0.1256, "step": 449440 }, { "epoch": 2.67162413586081, "grad_norm": 4.254758834838867, "learning_rate": 5.273472961008617e-06, "loss": 0.1235, "step": 449450 }, { "epoch": 2.671683577937479, "grad_norm": 5.280463218688965, "learning_rate": 5.273265779234381e-06, "loss": 0.1179, "step": 449460 }, { "epoch": 2.671743020014147, "grad_norm": 4.137060165405273, "learning_rate": 5.2730585969895485e-06, "loss": 0.1243, "step": 449470 }, { "epoch": 2.671802462090816, "grad_norm": 3.7651634216308594, "learning_rate": 5.272851414274478e-06, "loss": 0.1359, "step": 449480 }, { "epoch": 2.671861904167484, "grad_norm": 3.293299436569214, "learning_rate": 5.272644231089526e-06, "loss": 0.117, "step": 449490 }, { "epoch": 2.6719213462441522, "grad_norm": 4.154273986816406, "learning_rate": 5.272437047435044e-06, "loss": 0.1263, "step": 449500 }, { "epoch": 2.6719807883208206, "grad_norm": 4.048477649688721, "learning_rate": 5.272229863311395e-06, "loss": 0.1133, "step": 449510 }, { "epoch": 2.672040230397489, "grad_norm": 4.270201683044434, "learning_rate": 5.2720226787189344e-06, "loss": 0.1166, "step": 449520 }, { "epoch": 2.6720996724741575, "grad_norm": 4.813464164733887, "learning_rate": 5.271815493658017e-06, "loss": 0.1311, "step": 449530 }, { "epoch": 2.672159114550826, "grad_norm": 2.73803973197937, "learning_rate": 5.271608308129001e-06, "loss": 0.1101, "step": 449540 }, { "epoch": 2.6722185566274943, "grad_norm": 3.763201951980591, "learning_rate": 5.271401122132244e-06, "loss": 0.1217, "step": 449550 }, { "epoch": 2.6722779987041627, "grad_norm": 3.8985509872436523, "learning_rate": 5.271193935668102e-06, "loss": 0.1336, "step": 449560 }, { "epoch": 2.672337440780831, "grad_norm": 3.4994211196899414, "learning_rate": 5.270986748736931e-06, "loss": 0.1134, "step": 449570 }, { "epoch": 2.6723968828574995, "grad_norm": 4.235503673553467, "learning_rate": 5.270779561339089e-06, "loss": 0.1327, "step": 449580 }, { "epoch": 2.672456324934168, "grad_norm": 3.8332724571228027, "learning_rate": 5.270572373474933e-06, "loss": 0.1157, "step": 449590 }, { "epoch": 2.6725157670108364, "grad_norm": 3.7217459678649902, "learning_rate": 5.270365185144817e-06, "loss": 0.1265, "step": 449600 }, { "epoch": 2.672575209087505, "grad_norm": 4.153478145599365, "learning_rate": 5.270157996349101e-06, "loss": 0.1139, "step": 449610 }, { "epoch": 2.672634651164173, "grad_norm": 5.114652633666992, "learning_rate": 5.269950807088141e-06, "loss": 0.1182, "step": 449620 }, { "epoch": 2.6726940932408416, "grad_norm": 3.9544341564178467, "learning_rate": 5.269743617362292e-06, "loss": 0.1404, "step": 449630 }, { "epoch": 2.6727535353175096, "grad_norm": 4.086296558380127, "learning_rate": 5.269536427171914e-06, "loss": 0.1282, "step": 449640 }, { "epoch": 2.6728129773941784, "grad_norm": 4.1024580001831055, "learning_rate": 5.269329236517362e-06, "loss": 0.1168, "step": 449650 }, { "epoch": 2.6728724194708464, "grad_norm": 4.551212310791016, "learning_rate": 5.269122045398991e-06, "loss": 0.1263, "step": 449660 }, { "epoch": 2.6729318615475153, "grad_norm": 4.903112888336182, "learning_rate": 5.2689148538171615e-06, "loss": 0.1396, "step": 449670 }, { "epoch": 2.6729913036241832, "grad_norm": 3.7222819328308105, "learning_rate": 5.268707661772229e-06, "loss": 0.1228, "step": 449680 }, { "epoch": 2.6730507457008517, "grad_norm": 4.407675266265869, "learning_rate": 5.268500469264549e-06, "loss": 0.1182, "step": 449690 }, { "epoch": 2.67311018777752, "grad_norm": 4.555253028869629, "learning_rate": 5.268293276294479e-06, "loss": 0.136, "step": 449700 }, { "epoch": 2.6731696298541885, "grad_norm": 4.222815036773682, "learning_rate": 5.268086082862377e-06, "loss": 0.1384, "step": 449710 }, { "epoch": 2.673229071930857, "grad_norm": 5.074131011962891, "learning_rate": 5.267878888968597e-06, "loss": 0.1197, "step": 449720 }, { "epoch": 2.6732885140075253, "grad_norm": 3.8166797161102295, "learning_rate": 5.2676716946135e-06, "loss": 0.106, "step": 449730 }, { "epoch": 2.6733479560841937, "grad_norm": 4.862676620483398, "learning_rate": 5.2674644997974375e-06, "loss": 0.1319, "step": 449740 }, { "epoch": 2.673407398160862, "grad_norm": 3.0907859802246094, "learning_rate": 5.267257304520771e-06, "loss": 0.12, "step": 449750 }, { "epoch": 2.6734668402375306, "grad_norm": 4.273707866668701, "learning_rate": 5.267050108783854e-06, "loss": 0.1195, "step": 449760 }, { "epoch": 2.673526282314199, "grad_norm": 3.379716396331787, "learning_rate": 5.266842912587047e-06, "loss": 0.1078, "step": 449770 }, { "epoch": 2.6735857243908674, "grad_norm": 3.108980178833008, "learning_rate": 5.266635715930704e-06, "loss": 0.1103, "step": 449780 }, { "epoch": 2.673645166467536, "grad_norm": 4.331262111663818, "learning_rate": 5.266428518815182e-06, "loss": 0.1318, "step": 449790 }, { "epoch": 2.673704608544204, "grad_norm": 3.133704662322998, "learning_rate": 5.266221321240839e-06, "loss": 0.1254, "step": 449800 }, { "epoch": 2.6737640506208726, "grad_norm": 3.669689655303955, "learning_rate": 5.266014123208031e-06, "loss": 0.1093, "step": 449810 }, { "epoch": 2.673823492697541, "grad_norm": 4.070931911468506, "learning_rate": 5.265806924717114e-06, "loss": 0.1222, "step": 449820 }, { "epoch": 2.673882934774209, "grad_norm": 3.4148688316345215, "learning_rate": 5.265599725768447e-06, "loss": 0.1258, "step": 449830 }, { "epoch": 2.673942376850878, "grad_norm": 6.3735456466674805, "learning_rate": 5.265392526362385e-06, "loss": 0.1349, "step": 449840 }, { "epoch": 2.674001818927546, "grad_norm": 4.696721076965332, "learning_rate": 5.265185326499285e-06, "loss": 0.1471, "step": 449850 }, { "epoch": 2.6740612610042147, "grad_norm": 4.782616138458252, "learning_rate": 5.264978126179504e-06, "loss": 0.141, "step": 449860 }, { "epoch": 2.6741207030808827, "grad_norm": 4.774674892425537, "learning_rate": 5.2647709254034e-06, "loss": 0.1436, "step": 449870 }, { "epoch": 2.674180145157551, "grad_norm": 4.4052228927612305, "learning_rate": 5.264563724171329e-06, "loss": 0.1458, "step": 449880 }, { "epoch": 2.6742395872342195, "grad_norm": 4.133815765380859, "learning_rate": 5.264356522483646e-06, "loss": 0.1226, "step": 449890 }, { "epoch": 2.674299029310888, "grad_norm": 3.9260077476501465, "learning_rate": 5.264149320340711e-06, "loss": 0.1236, "step": 449900 }, { "epoch": 2.6743584713875563, "grad_norm": 3.5403504371643066, "learning_rate": 5.263942117742879e-06, "loss": 0.1162, "step": 449910 }, { "epoch": 2.6744179134642247, "grad_norm": 3.912597179412842, "learning_rate": 5.263734914690507e-06, "loss": 0.1171, "step": 449920 }, { "epoch": 2.674477355540893, "grad_norm": 4.075582504272461, "learning_rate": 5.2635277111839535e-06, "loss": 0.1258, "step": 449930 }, { "epoch": 2.6745367976175616, "grad_norm": 4.010508060455322, "learning_rate": 5.263320507223573e-06, "loss": 0.1327, "step": 449940 }, { "epoch": 2.67459623969423, "grad_norm": 3.726925849914551, "learning_rate": 5.263113302809722e-06, "loss": 0.1169, "step": 449950 }, { "epoch": 2.6746556817708984, "grad_norm": 4.513101100921631, "learning_rate": 5.262906097942758e-06, "loss": 0.1335, "step": 449960 }, { "epoch": 2.674715123847567, "grad_norm": 4.656280517578125, "learning_rate": 5.26269889262304e-06, "loss": 0.1305, "step": 449970 }, { "epoch": 2.6747745659242352, "grad_norm": 3.5803298950195312, "learning_rate": 5.262491686850923e-06, "loss": 0.1466, "step": 449980 }, { "epoch": 2.6748340080009037, "grad_norm": 3.743053913116455, "learning_rate": 5.262284480626764e-06, "loss": 0.1282, "step": 449990 }, { "epoch": 2.674893450077572, "grad_norm": 4.117819309234619, "learning_rate": 5.26207727395092e-06, "loss": 0.1178, "step": 450000 }, { "epoch": 2.6749528921542405, "grad_norm": 3.9327714443206787, "learning_rate": 5.261870066823748e-06, "loss": 0.105, "step": 450010 }, { "epoch": 2.6750123342309085, "grad_norm": 3.847121238708496, "learning_rate": 5.261662859245602e-06, "loss": 0.1246, "step": 450020 }, { "epoch": 2.6750717763075773, "grad_norm": 4.529261589050293, "learning_rate": 5.2614556512168435e-06, "loss": 0.122, "step": 450030 }, { "epoch": 2.6751312183842453, "grad_norm": 4.575002670288086, "learning_rate": 5.261248442737827e-06, "loss": 0.1176, "step": 450040 }, { "epoch": 2.675190660460914, "grad_norm": 4.0286736488342285, "learning_rate": 5.261041233808909e-06, "loss": 0.1021, "step": 450050 }, { "epoch": 2.675250102537582, "grad_norm": 4.374500751495361, "learning_rate": 5.260834024430448e-06, "loss": 0.1261, "step": 450060 }, { "epoch": 2.6753095446142505, "grad_norm": 2.966951847076416, "learning_rate": 5.260626814602797e-06, "loss": 0.1107, "step": 450070 }, { "epoch": 2.675368986690919, "grad_norm": 3.1168253421783447, "learning_rate": 5.260419604326319e-06, "loss": 0.1286, "step": 450080 }, { "epoch": 2.6754284287675874, "grad_norm": 4.035379409790039, "learning_rate": 5.260212393601365e-06, "loss": 0.1114, "step": 450090 }, { "epoch": 2.6754878708442558, "grad_norm": 3.906062126159668, "learning_rate": 5.2600051824282946e-06, "loss": 0.1219, "step": 450100 }, { "epoch": 2.675547312920924, "grad_norm": 4.361017227172852, "learning_rate": 5.2597979708074656e-06, "loss": 0.1195, "step": 450110 }, { "epoch": 2.6756067549975926, "grad_norm": 3.7602698802948, "learning_rate": 5.259590758739231e-06, "loss": 0.1134, "step": 450120 }, { "epoch": 2.675666197074261, "grad_norm": 5.4587297439575195, "learning_rate": 5.259383546223953e-06, "loss": 0.1205, "step": 450130 }, { "epoch": 2.6757256391509294, "grad_norm": 3.0953450202941895, "learning_rate": 5.259176333261984e-06, "loss": 0.1251, "step": 450140 }, { "epoch": 2.675785081227598, "grad_norm": 3.7209157943725586, "learning_rate": 5.258969119853682e-06, "loss": 0.1475, "step": 450150 }, { "epoch": 2.6758445233042663, "grad_norm": 5.4457550048828125, "learning_rate": 5.258761905999405e-06, "loss": 0.1282, "step": 450160 }, { "epoch": 2.6759039653809347, "grad_norm": 5.886636257171631, "learning_rate": 5.25855469169951e-06, "loss": 0.1303, "step": 450170 }, { "epoch": 2.675963407457603, "grad_norm": 3.1239397525787354, "learning_rate": 5.2583474769543494e-06, "loss": 0.1197, "step": 450180 }, { "epoch": 2.676022849534271, "grad_norm": 4.598695755004883, "learning_rate": 5.258140261764287e-06, "loss": 0.1256, "step": 450190 }, { "epoch": 2.67608229161094, "grad_norm": 3.833594560623169, "learning_rate": 5.257933046129676e-06, "loss": 0.1186, "step": 450200 }, { "epoch": 2.676141733687608, "grad_norm": 4.55273962020874, "learning_rate": 5.257725830050872e-06, "loss": 0.1154, "step": 450210 }, { "epoch": 2.6762011757642767, "grad_norm": 4.124439239501953, "learning_rate": 5.257518613528235e-06, "loss": 0.1287, "step": 450220 }, { "epoch": 2.6762606178409447, "grad_norm": 3.1990833282470703, "learning_rate": 5.257311396562121e-06, "loss": 0.1021, "step": 450230 }, { "epoch": 2.676320059917613, "grad_norm": 3.427593231201172, "learning_rate": 5.2571041791528836e-06, "loss": 0.119, "step": 450240 }, { "epoch": 2.6763795019942815, "grad_norm": 5.494658946990967, "learning_rate": 5.256896961300882e-06, "loss": 0.1204, "step": 450250 }, { "epoch": 2.67643894407095, "grad_norm": 4.496128082275391, "learning_rate": 5.256689743006475e-06, "loss": 0.1208, "step": 450260 }, { "epoch": 2.6764983861476184, "grad_norm": 3.492220401763916, "learning_rate": 5.256482524270018e-06, "loss": 0.1141, "step": 450270 }, { "epoch": 2.676557828224287, "grad_norm": 4.535720348358154, "learning_rate": 5.2562753050918655e-06, "loss": 0.1168, "step": 450280 }, { "epoch": 2.676617270300955, "grad_norm": 5.7718281745910645, "learning_rate": 5.256068085472376e-06, "loss": 0.1145, "step": 450290 }, { "epoch": 2.6766767123776236, "grad_norm": 3.895615339279175, "learning_rate": 5.255860865411909e-06, "loss": 0.1259, "step": 450300 }, { "epoch": 2.676736154454292, "grad_norm": 3.945610284805298, "learning_rate": 5.255653644910817e-06, "loss": 0.1288, "step": 450310 }, { "epoch": 2.6767955965309604, "grad_norm": 3.4781832695007324, "learning_rate": 5.2554464239694615e-06, "loss": 0.1374, "step": 450320 }, { "epoch": 2.676855038607629, "grad_norm": 3.296245574951172, "learning_rate": 5.2552392025881956e-06, "loss": 0.1266, "step": 450330 }, { "epoch": 2.6769144806842973, "grad_norm": 3.786600112915039, "learning_rate": 5.255031980767376e-06, "loss": 0.1328, "step": 450340 }, { "epoch": 2.6769739227609657, "grad_norm": 4.89778470993042, "learning_rate": 5.254824758507363e-06, "loss": 0.1279, "step": 450350 }, { "epoch": 2.677033364837634, "grad_norm": 4.240388870239258, "learning_rate": 5.25461753580851e-06, "loss": 0.1393, "step": 450360 }, { "epoch": 2.6770928069143025, "grad_norm": 6.05923318862915, "learning_rate": 5.2544103126711755e-06, "loss": 0.1307, "step": 450370 }, { "epoch": 2.6771522489909705, "grad_norm": 3.739835023880005, "learning_rate": 5.2542030890957165e-06, "loss": 0.1306, "step": 450380 }, { "epoch": 2.6772116910676393, "grad_norm": 2.5088448524475098, "learning_rate": 5.25399586508249e-06, "loss": 0.1144, "step": 450390 }, { "epoch": 2.6772711331443073, "grad_norm": 4.452045917510986, "learning_rate": 5.253788640631849e-06, "loss": 0.1197, "step": 450400 }, { "epoch": 2.677330575220976, "grad_norm": 3.2008378505706787, "learning_rate": 5.2535814157441566e-06, "loss": 0.1172, "step": 450410 }, { "epoch": 2.677390017297644, "grad_norm": 3.5633602142333984, "learning_rate": 5.253374190419767e-06, "loss": 0.1255, "step": 450420 }, { "epoch": 2.6774494593743126, "grad_norm": 4.517989635467529, "learning_rate": 5.253166964659036e-06, "loss": 0.1092, "step": 450430 }, { "epoch": 2.677508901450981, "grad_norm": 3.646712303161621, "learning_rate": 5.25295973846232e-06, "loss": 0.1238, "step": 450440 }, { "epoch": 2.6775683435276494, "grad_norm": 4.977001190185547, "learning_rate": 5.25275251182998e-06, "loss": 0.1064, "step": 450450 }, { "epoch": 2.677627785604318, "grad_norm": 3.303241491317749, "learning_rate": 5.252545284762368e-06, "loss": 0.1118, "step": 450460 }, { "epoch": 2.677687227680986, "grad_norm": 4.086099624633789, "learning_rate": 5.252338057259843e-06, "loss": 0.1449, "step": 450470 }, { "epoch": 2.6777466697576546, "grad_norm": 4.013352870941162, "learning_rate": 5.252130829322763e-06, "loss": 0.1134, "step": 450480 }, { "epoch": 2.677806111834323, "grad_norm": 4.452864170074463, "learning_rate": 5.251923600951482e-06, "loss": 0.1187, "step": 450490 }, { "epoch": 2.6778655539109915, "grad_norm": 4.222866058349609, "learning_rate": 5.2517163721463585e-06, "loss": 0.1324, "step": 450500 }, { "epoch": 2.67792499598766, "grad_norm": 3.696106195449829, "learning_rate": 5.251509142907749e-06, "loss": 0.1058, "step": 450510 }, { "epoch": 2.6779844380643283, "grad_norm": 2.7876486778259277, "learning_rate": 5.2513019132360135e-06, "loss": 0.1243, "step": 450520 }, { "epoch": 2.6780438801409967, "grad_norm": 3.7090845108032227, "learning_rate": 5.251094683131504e-06, "loss": 0.1178, "step": 450530 }, { "epoch": 2.678103322217665, "grad_norm": 4.270148754119873, "learning_rate": 5.25088745259458e-06, "loss": 0.1259, "step": 450540 }, { "epoch": 2.6781627642943335, "grad_norm": 3.8564646244049072, "learning_rate": 5.250680221625598e-06, "loss": 0.1259, "step": 450550 }, { "epoch": 2.678222206371002, "grad_norm": 3.5732486248016357, "learning_rate": 5.250472990224915e-06, "loss": 0.1197, "step": 450560 }, { "epoch": 2.67828164844767, "grad_norm": 3.2600901126861572, "learning_rate": 5.250265758392886e-06, "loss": 0.1212, "step": 450570 }, { "epoch": 2.6783410905243388, "grad_norm": 4.68262243270874, "learning_rate": 5.250058526129871e-06, "loss": 0.114, "step": 450580 }, { "epoch": 2.6784005326010067, "grad_norm": 3.223893404006958, "learning_rate": 5.249851293436226e-06, "loss": 0.1167, "step": 450590 }, { "epoch": 2.6784599746776756, "grad_norm": 3.2889842987060547, "learning_rate": 5.249644060312306e-06, "loss": 0.125, "step": 450600 }, { "epoch": 2.6785194167543436, "grad_norm": 4.34595251083374, "learning_rate": 5.249436826758469e-06, "loss": 0.113, "step": 450610 }, { "epoch": 2.678578858831012, "grad_norm": 5.070379257202148, "learning_rate": 5.249229592775073e-06, "loss": 0.1219, "step": 450620 }, { "epoch": 2.6786383009076804, "grad_norm": 4.610408306121826, "learning_rate": 5.249022358362473e-06, "loss": 0.1229, "step": 450630 }, { "epoch": 2.678697742984349, "grad_norm": 3.5695912837982178, "learning_rate": 5.2488151235210264e-06, "loss": 0.108, "step": 450640 }, { "epoch": 2.6787571850610172, "grad_norm": 4.201398849487305, "learning_rate": 5.248607888251092e-06, "loss": 0.1182, "step": 450650 }, { "epoch": 2.6788166271376856, "grad_norm": 4.85791540145874, "learning_rate": 5.248400652553025e-06, "loss": 0.1371, "step": 450660 }, { "epoch": 2.678876069214354, "grad_norm": 4.196774005889893, "learning_rate": 5.2481934164271806e-06, "loss": 0.1271, "step": 450670 }, { "epoch": 2.6789355112910225, "grad_norm": 5.193627834320068, "learning_rate": 5.24798617987392e-06, "loss": 0.1383, "step": 450680 }, { "epoch": 2.678994953367691, "grad_norm": 5.147282600402832, "learning_rate": 5.247778942893597e-06, "loss": 0.1224, "step": 450690 }, { "epoch": 2.6790543954443593, "grad_norm": 2.987208843231201, "learning_rate": 5.247571705486567e-06, "loss": 0.116, "step": 450700 }, { "epoch": 2.6791138375210277, "grad_norm": 3.352707624435425, "learning_rate": 5.247364467653191e-06, "loss": 0.1103, "step": 450710 }, { "epoch": 2.679173279597696, "grad_norm": 4.843588352203369, "learning_rate": 5.247157229393823e-06, "loss": 0.1179, "step": 450720 }, { "epoch": 2.6792327216743645, "grad_norm": 5.448019504547119, "learning_rate": 5.246949990708821e-06, "loss": 0.1231, "step": 450730 }, { "epoch": 2.679292163751033, "grad_norm": 3.806049346923828, "learning_rate": 5.246742751598541e-06, "loss": 0.1195, "step": 450740 }, { "epoch": 2.6793516058277014, "grad_norm": 3.2776808738708496, "learning_rate": 5.246535512063342e-06, "loss": 0.1146, "step": 450750 }, { "epoch": 2.6794110479043693, "grad_norm": 3.024965286254883, "learning_rate": 5.246328272103579e-06, "loss": 0.1062, "step": 450760 }, { "epoch": 2.679470489981038, "grad_norm": 4.74038028717041, "learning_rate": 5.246121031719609e-06, "loss": 0.1096, "step": 450770 }, { "epoch": 2.679529932057706, "grad_norm": 3.0809476375579834, "learning_rate": 5.245913790911789e-06, "loss": 0.1109, "step": 450780 }, { "epoch": 2.679589374134375, "grad_norm": 3.8954856395721436, "learning_rate": 5.245706549680477e-06, "loss": 0.1097, "step": 450790 }, { "epoch": 2.679648816211043, "grad_norm": 4.4928107261657715, "learning_rate": 5.245499308026027e-06, "loss": 0.0996, "step": 450800 }, { "epoch": 2.6797082582877114, "grad_norm": 4.505484580993652, "learning_rate": 5.2452920659488005e-06, "loss": 0.1315, "step": 450810 }, { "epoch": 2.67976770036438, "grad_norm": 3.2449214458465576, "learning_rate": 5.24508482344915e-06, "loss": 0.1107, "step": 450820 }, { "epoch": 2.6798271424410482, "grad_norm": 4.400692939758301, "learning_rate": 5.244877580527435e-06, "loss": 0.1234, "step": 450830 }, { "epoch": 2.6798865845177167, "grad_norm": 4.2367024421691895, "learning_rate": 5.2446703371840105e-06, "loss": 0.1098, "step": 450840 }, { "epoch": 2.679946026594385, "grad_norm": 2.844067096710205, "learning_rate": 5.244463093419235e-06, "loss": 0.1266, "step": 450850 }, { "epoch": 2.6800054686710535, "grad_norm": 4.231361389160156, "learning_rate": 5.244255849233465e-06, "loss": 0.1207, "step": 450860 }, { "epoch": 2.680064910747722, "grad_norm": 3.13437819480896, "learning_rate": 5.2440486046270575e-06, "loss": 0.1185, "step": 450870 }, { "epoch": 2.6801243528243903, "grad_norm": 3.7680423259735107, "learning_rate": 5.2438413596003705e-06, "loss": 0.1088, "step": 450880 }, { "epoch": 2.6801837949010587, "grad_norm": 4.789063930511475, "learning_rate": 5.243634114153758e-06, "loss": 0.1155, "step": 450890 }, { "epoch": 2.680243236977727, "grad_norm": 4.504537105560303, "learning_rate": 5.243426868287578e-06, "loss": 0.1307, "step": 450900 }, { "epoch": 2.6803026790543956, "grad_norm": 2.7054014205932617, "learning_rate": 5.243219622002189e-06, "loss": 0.1155, "step": 450910 }, { "epoch": 2.680362121131064, "grad_norm": 2.985450506210327, "learning_rate": 5.2430123752979465e-06, "loss": 0.1146, "step": 450920 }, { "epoch": 2.680421563207732, "grad_norm": 4.063398361206055, "learning_rate": 5.242805128175208e-06, "loss": 0.1306, "step": 450930 }, { "epoch": 2.680481005284401, "grad_norm": 3.054088830947876, "learning_rate": 5.242597880634331e-06, "loss": 0.1318, "step": 450940 }, { "epoch": 2.680540447361069, "grad_norm": 3.9499549865722656, "learning_rate": 5.242390632675668e-06, "loss": 0.1296, "step": 450950 }, { "epoch": 2.6805998894377376, "grad_norm": 3.8142893314361572, "learning_rate": 5.242183384299581e-06, "loss": 0.1265, "step": 450960 }, { "epoch": 2.6806593315144056, "grad_norm": 3.807082176208496, "learning_rate": 5.241976135506427e-06, "loss": 0.1247, "step": 450970 }, { "epoch": 2.680718773591074, "grad_norm": 4.1203293800354, "learning_rate": 5.24176888629656e-06, "loss": 0.1228, "step": 450980 }, { "epoch": 2.6807782156677424, "grad_norm": 4.35965633392334, "learning_rate": 5.241561636670338e-06, "loss": 0.1107, "step": 450990 }, { "epoch": 2.680837657744411, "grad_norm": 4.277345657348633, "learning_rate": 5.241354386628119e-06, "loss": 0.108, "step": 451000 }, { "epoch": 2.6808970998210793, "grad_norm": 4.336202621459961, "learning_rate": 5.241147136170258e-06, "loss": 0.1148, "step": 451010 }, { "epoch": 2.6809565418977477, "grad_norm": 3.2914531230926514, "learning_rate": 5.240939885297113e-06, "loss": 0.1076, "step": 451020 }, { "epoch": 2.681015983974416, "grad_norm": 4.1027631759643555, "learning_rate": 5.240732634009041e-06, "loss": 0.1168, "step": 451030 }, { "epoch": 2.6810754260510845, "grad_norm": 3.219616413116455, "learning_rate": 5.2405253823064e-06, "loss": 0.1176, "step": 451040 }, { "epoch": 2.681134868127753, "grad_norm": 2.737715721130371, "learning_rate": 5.240318130189542e-06, "loss": 0.1255, "step": 451050 }, { "epoch": 2.6811943102044213, "grad_norm": 4.750751972198486, "learning_rate": 5.240110877658829e-06, "loss": 0.1091, "step": 451060 }, { "epoch": 2.6812537522810898, "grad_norm": 5.2406768798828125, "learning_rate": 5.239903624714619e-06, "loss": 0.1144, "step": 451070 }, { "epoch": 2.681313194357758, "grad_norm": 4.151825904846191, "learning_rate": 5.239696371357264e-06, "loss": 0.1209, "step": 451080 }, { "epoch": 2.6813726364344266, "grad_norm": 4.557450294494629, "learning_rate": 5.239489117587123e-06, "loss": 0.1146, "step": 451090 }, { "epoch": 2.681432078511095, "grad_norm": 4.021610736846924, "learning_rate": 5.239281863404554e-06, "loss": 0.1336, "step": 451100 }, { "epoch": 2.6814915205877634, "grad_norm": 3.354323625564575, "learning_rate": 5.239074608809913e-06, "loss": 0.1307, "step": 451110 }, { "epoch": 2.6815509626644314, "grad_norm": 3.6995413303375244, "learning_rate": 5.238867353803557e-06, "loss": 0.1251, "step": 451120 }, { "epoch": 2.6816104047411002, "grad_norm": 6.350208282470703, "learning_rate": 5.238660098385842e-06, "loss": 0.135, "step": 451130 }, { "epoch": 2.681669846817768, "grad_norm": 3.6714961528778076, "learning_rate": 5.238452842557128e-06, "loss": 0.1189, "step": 451140 }, { "epoch": 2.681729288894437, "grad_norm": 3.6369290351867676, "learning_rate": 5.238245586317769e-06, "loss": 0.12, "step": 451150 }, { "epoch": 2.681788730971105, "grad_norm": 3.0464859008789062, "learning_rate": 5.238038329668121e-06, "loss": 0.1204, "step": 451160 }, { "epoch": 2.6818481730477735, "grad_norm": 4.296825885772705, "learning_rate": 5.237831072608543e-06, "loss": 0.1204, "step": 451170 }, { "epoch": 2.681907615124442, "grad_norm": 5.561535358428955, "learning_rate": 5.237623815139393e-06, "loss": 0.1153, "step": 451180 }, { "epoch": 2.6819670572011103, "grad_norm": 4.178019046783447, "learning_rate": 5.237416557261025e-06, "loss": 0.136, "step": 451190 }, { "epoch": 2.6820264992777787, "grad_norm": 4.694597244262695, "learning_rate": 5.237209298973799e-06, "loss": 0.1286, "step": 451200 }, { "epoch": 2.682085941354447, "grad_norm": 4.51280403137207, "learning_rate": 5.23700204027807e-06, "loss": 0.1241, "step": 451210 }, { "epoch": 2.6821453834311155, "grad_norm": 3.360460042953491, "learning_rate": 5.236794781174194e-06, "loss": 0.1133, "step": 451220 }, { "epoch": 2.682204825507784, "grad_norm": 3.307546377182007, "learning_rate": 5.23658752166253e-06, "loss": 0.1022, "step": 451230 }, { "epoch": 2.6822642675844524, "grad_norm": 3.5606610774993896, "learning_rate": 5.236380261743433e-06, "loss": 0.1092, "step": 451240 }, { "epoch": 2.6823237096611208, "grad_norm": 2.543071985244751, "learning_rate": 5.236173001417262e-06, "loss": 0.1264, "step": 451250 }, { "epoch": 2.682383151737789, "grad_norm": 4.426144599914551, "learning_rate": 5.235965740684372e-06, "loss": 0.1295, "step": 451260 }, { "epoch": 2.6824425938144576, "grad_norm": 4.863842964172363, "learning_rate": 5.235758479545122e-06, "loss": 0.1138, "step": 451270 }, { "epoch": 2.682502035891126, "grad_norm": 3.1582844257354736, "learning_rate": 5.235551217999867e-06, "loss": 0.1126, "step": 451280 }, { "epoch": 2.6825614779677944, "grad_norm": 3.9261794090270996, "learning_rate": 5.235343956048964e-06, "loss": 0.1326, "step": 451290 }, { "epoch": 2.682620920044463, "grad_norm": 3.731595277786255, "learning_rate": 5.235136693692771e-06, "loss": 0.1262, "step": 451300 }, { "epoch": 2.682680362121131, "grad_norm": 4.599236965179443, "learning_rate": 5.234929430931646e-06, "loss": 0.1183, "step": 451310 }, { "epoch": 2.6827398041977997, "grad_norm": 4.307559967041016, "learning_rate": 5.234722167765944e-06, "loss": 0.1374, "step": 451320 }, { "epoch": 2.6827992462744676, "grad_norm": 4.817930221557617, "learning_rate": 5.2345149041960215e-06, "loss": 0.1329, "step": 451330 }, { "epoch": 2.6828586883511365, "grad_norm": 3.408942222595215, "learning_rate": 5.234307640222238e-06, "loss": 0.114, "step": 451340 }, { "epoch": 2.6829181304278045, "grad_norm": 3.897681713104248, "learning_rate": 5.234100375844946e-06, "loss": 0.1068, "step": 451350 }, { "epoch": 2.682977572504473, "grad_norm": 3.9247260093688965, "learning_rate": 5.2338931110645076e-06, "loss": 0.111, "step": 451360 }, { "epoch": 2.6830370145811413, "grad_norm": 3.8255770206451416, "learning_rate": 5.2336858458812766e-06, "loss": 0.1185, "step": 451370 }, { "epoch": 2.6830964566578097, "grad_norm": 4.105345249176025, "learning_rate": 5.233478580295611e-06, "loss": 0.1185, "step": 451380 }, { "epoch": 2.683155898734478, "grad_norm": 3.810359239578247, "learning_rate": 5.233271314307866e-06, "loss": 0.1196, "step": 451390 }, { "epoch": 2.6832153408111465, "grad_norm": 3.3501341342926025, "learning_rate": 5.233064047918401e-06, "loss": 0.1285, "step": 451400 }, { "epoch": 2.683274782887815, "grad_norm": 4.243257522583008, "learning_rate": 5.2328567811275735e-06, "loss": 0.1217, "step": 451410 }, { "epoch": 2.6833342249644834, "grad_norm": 4.720384120941162, "learning_rate": 5.232649513935736e-06, "loss": 0.1367, "step": 451420 }, { "epoch": 2.683393667041152, "grad_norm": 3.759845018386841, "learning_rate": 5.23244224634325e-06, "loss": 0.125, "step": 451430 }, { "epoch": 2.68345310911782, "grad_norm": 3.047168016433716, "learning_rate": 5.232234978350471e-06, "loss": 0.0933, "step": 451440 }, { "epoch": 2.6835125511944886, "grad_norm": 4.312002658843994, "learning_rate": 5.232027709957754e-06, "loss": 0.1098, "step": 451450 }, { "epoch": 2.683571993271157, "grad_norm": 3.743420124053955, "learning_rate": 5.23182044116546e-06, "loss": 0.1202, "step": 451460 }, { "epoch": 2.6836314353478254, "grad_norm": 4.188697814941406, "learning_rate": 5.231613171973942e-06, "loss": 0.1256, "step": 451470 }, { "epoch": 2.683690877424494, "grad_norm": 2.9199581146240234, "learning_rate": 5.231405902383557e-06, "loss": 0.1324, "step": 451480 }, { "epoch": 2.6837503195011623, "grad_norm": 3.7869246006011963, "learning_rate": 5.231198632394666e-06, "loss": 0.1151, "step": 451490 }, { "epoch": 2.6838097615778302, "grad_norm": 2.5133492946624756, "learning_rate": 5.230991362007621e-06, "loss": 0.0908, "step": 451500 }, { "epoch": 2.683869203654499, "grad_norm": 4.254758358001709, "learning_rate": 5.230784091222782e-06, "loss": 0.1169, "step": 451510 }, { "epoch": 2.683928645731167, "grad_norm": 4.386651992797852, "learning_rate": 5.230576820040507e-06, "loss": 0.1285, "step": 451520 }, { "epoch": 2.683988087807836, "grad_norm": 5.222163677215576, "learning_rate": 5.23036954846115e-06, "loss": 0.1278, "step": 451530 }, { "epoch": 2.684047529884504, "grad_norm": 4.881356239318848, "learning_rate": 5.230162276485069e-06, "loss": 0.1338, "step": 451540 }, { "epoch": 2.6841069719611723, "grad_norm": 3.5757253170013428, "learning_rate": 5.229955004112622e-06, "loss": 0.1269, "step": 451550 }, { "epoch": 2.6841664140378407, "grad_norm": 3.9206249713897705, "learning_rate": 5.229747731344166e-06, "loss": 0.1214, "step": 451560 }, { "epoch": 2.684225856114509, "grad_norm": 5.548130035400391, "learning_rate": 5.2295404581800535e-06, "loss": 0.1177, "step": 451570 }, { "epoch": 2.6842852981911776, "grad_norm": 4.370399475097656, "learning_rate": 5.2293331846206475e-06, "loss": 0.1351, "step": 451580 }, { "epoch": 2.684344740267846, "grad_norm": 3.1571476459503174, "learning_rate": 5.229125910666303e-06, "loss": 0.1377, "step": 451590 }, { "epoch": 2.6844041823445144, "grad_norm": 3.572291612625122, "learning_rate": 5.228918636317375e-06, "loss": 0.1103, "step": 451600 }, { "epoch": 2.684463624421183, "grad_norm": 4.0366973876953125, "learning_rate": 5.22871136157422e-06, "loss": 0.1189, "step": 451610 }, { "epoch": 2.684523066497851, "grad_norm": 3.3847272396087646, "learning_rate": 5.228504086437199e-06, "loss": 0.116, "step": 451620 }, { "epoch": 2.6845825085745196, "grad_norm": 3.5828824043273926, "learning_rate": 5.228296810906667e-06, "loss": 0.1126, "step": 451630 }, { "epoch": 2.684641950651188, "grad_norm": 5.593806743621826, "learning_rate": 5.2280895349829795e-06, "loss": 0.1416, "step": 451640 }, { "epoch": 2.6847013927278565, "grad_norm": 3.8037819862365723, "learning_rate": 5.227882258666496e-06, "loss": 0.1238, "step": 451650 }, { "epoch": 2.684760834804525, "grad_norm": 4.652464866638184, "learning_rate": 5.227674981957571e-06, "loss": 0.1178, "step": 451660 }, { "epoch": 2.684820276881193, "grad_norm": 4.40337610244751, "learning_rate": 5.227467704856562e-06, "loss": 0.1328, "step": 451670 }, { "epoch": 2.6848797189578617, "grad_norm": 4.8399553298950195, "learning_rate": 5.227260427363828e-06, "loss": 0.125, "step": 451680 }, { "epoch": 2.6849391610345297, "grad_norm": 3.557255983352661, "learning_rate": 5.2270531494797236e-06, "loss": 0.1265, "step": 451690 }, { "epoch": 2.6849986031111985, "grad_norm": 3.165404796600342, "learning_rate": 5.2268458712046065e-06, "loss": 0.1098, "step": 451700 }, { "epoch": 2.6850580451878665, "grad_norm": 5.088489055633545, "learning_rate": 5.226638592538834e-06, "loss": 0.1313, "step": 451710 }, { "epoch": 2.685117487264535, "grad_norm": 4.075348854064941, "learning_rate": 5.226431313482761e-06, "loss": 0.1159, "step": 451720 }, { "epoch": 2.6851769293412033, "grad_norm": 3.1311209201812744, "learning_rate": 5.226224034036749e-06, "loss": 0.1198, "step": 451730 }, { "epoch": 2.6852363714178717, "grad_norm": 3.4847540855407715, "learning_rate": 5.226016754201151e-06, "loss": 0.1115, "step": 451740 }, { "epoch": 2.68529581349454, "grad_norm": 3.9063189029693604, "learning_rate": 5.225809473976326e-06, "loss": 0.1233, "step": 451750 }, { "epoch": 2.6853552555712086, "grad_norm": 3.7838568687438965, "learning_rate": 5.225602193362629e-06, "loss": 0.116, "step": 451760 }, { "epoch": 2.685414697647877, "grad_norm": 3.8667471408843994, "learning_rate": 5.225394912360419e-06, "loss": 0.1165, "step": 451770 }, { "epoch": 2.6854741397245454, "grad_norm": 3.1700594425201416, "learning_rate": 5.225187630970051e-06, "loss": 0.1235, "step": 451780 }, { "epoch": 2.685533581801214, "grad_norm": 3.8105461597442627, "learning_rate": 5.224980349191884e-06, "loss": 0.1135, "step": 451790 }, { "epoch": 2.6855930238778822, "grad_norm": 6.068267822265625, "learning_rate": 5.2247730670262734e-06, "loss": 0.1127, "step": 451800 }, { "epoch": 2.6856524659545506, "grad_norm": 3.9743287563323975, "learning_rate": 5.224565784473577e-06, "loss": 0.1152, "step": 451810 }, { "epoch": 2.685711908031219, "grad_norm": 3.0591681003570557, "learning_rate": 5.224358501534152e-06, "loss": 0.1374, "step": 451820 }, { "epoch": 2.6857713501078875, "grad_norm": 3.8258769512176514, "learning_rate": 5.224151218208355e-06, "loss": 0.1136, "step": 451830 }, { "epoch": 2.685830792184556, "grad_norm": 4.1137824058532715, "learning_rate": 5.2239439344965404e-06, "loss": 0.1123, "step": 451840 }, { "epoch": 2.6858902342612243, "grad_norm": 3.175724506378174, "learning_rate": 5.22373665039907e-06, "loss": 0.1207, "step": 451850 }, { "epoch": 2.6859496763378923, "grad_norm": 3.514354944229126, "learning_rate": 5.223529365916298e-06, "loss": 0.1213, "step": 451860 }, { "epoch": 2.686009118414561, "grad_norm": 5.2551398277282715, "learning_rate": 5.223322081048581e-06, "loss": 0.1103, "step": 451870 }, { "epoch": 2.686068560491229, "grad_norm": 5.354016304016113, "learning_rate": 5.223114795796278e-06, "loss": 0.1292, "step": 451880 }, { "epoch": 2.686128002567898, "grad_norm": 4.679574489593506, "learning_rate": 5.222907510159745e-06, "loss": 0.1309, "step": 451890 }, { "epoch": 2.686187444644566, "grad_norm": 3.482827663421631, "learning_rate": 5.222700224139337e-06, "loss": 0.1007, "step": 451900 }, { "epoch": 2.6862468867212344, "grad_norm": 4.739678382873535, "learning_rate": 5.222492937735414e-06, "loss": 0.1261, "step": 451910 }, { "epoch": 2.6863063287979028, "grad_norm": 6.854018211364746, "learning_rate": 5.222285650948331e-06, "loss": 0.1331, "step": 451920 }, { "epoch": 2.686365770874571, "grad_norm": 3.5244696140289307, "learning_rate": 5.222078363778444e-06, "loss": 0.1226, "step": 451930 }, { "epoch": 2.6864252129512396, "grad_norm": 5.2599310874938965, "learning_rate": 5.2218710762261125e-06, "loss": 0.1264, "step": 451940 }, { "epoch": 2.686484655027908, "grad_norm": 5.297451496124268, "learning_rate": 5.221663788291694e-06, "loss": 0.1279, "step": 451950 }, { "epoch": 2.6865440971045764, "grad_norm": 4.861212253570557, "learning_rate": 5.221456499975544e-06, "loss": 0.1103, "step": 451960 }, { "epoch": 2.686603539181245, "grad_norm": 3.0725388526916504, "learning_rate": 5.221249211278017e-06, "loss": 0.1261, "step": 451970 }, { "epoch": 2.6866629812579133, "grad_norm": 4.018975734710693, "learning_rate": 5.221041922199475e-06, "loss": 0.1194, "step": 451980 }, { "epoch": 2.6867224233345817, "grad_norm": 3.9821414947509766, "learning_rate": 5.220834632740272e-06, "loss": 0.1177, "step": 451990 }, { "epoch": 2.68678186541125, "grad_norm": 4.111435413360596, "learning_rate": 5.220627342900764e-06, "loss": 0.1159, "step": 452000 }, { "epoch": 2.6868413074879185, "grad_norm": 5.014379501342773, "learning_rate": 5.220420052681312e-06, "loss": 0.1294, "step": 452010 }, { "epoch": 2.686900749564587, "grad_norm": 4.764140605926514, "learning_rate": 5.220212762082269e-06, "loss": 0.1147, "step": 452020 }, { "epoch": 2.6869601916412553, "grad_norm": 3.002986431121826, "learning_rate": 5.220005471103993e-06, "loss": 0.1182, "step": 452030 }, { "epoch": 2.6870196337179237, "grad_norm": 4.409740447998047, "learning_rate": 5.2197981797468415e-06, "loss": 0.126, "step": 452040 }, { "epoch": 2.6870790757945917, "grad_norm": 4.731398105621338, "learning_rate": 5.21959088801117e-06, "loss": 0.11, "step": 452050 }, { "epoch": 2.6871385178712606, "grad_norm": 4.043604373931885, "learning_rate": 5.2193835958973385e-06, "loss": 0.1229, "step": 452060 }, { "epoch": 2.6871979599479285, "grad_norm": 4.4610090255737305, "learning_rate": 5.219176303405701e-06, "loss": 0.1227, "step": 452070 }, { "epoch": 2.6872574020245974, "grad_norm": 4.395990371704102, "learning_rate": 5.218969010536618e-06, "loss": 0.1162, "step": 452080 }, { "epoch": 2.6873168441012654, "grad_norm": 4.54715633392334, "learning_rate": 5.218761717290442e-06, "loss": 0.1251, "step": 452090 }, { "epoch": 2.687376286177934, "grad_norm": 3.0856032371520996, "learning_rate": 5.218554423667532e-06, "loss": 0.1127, "step": 452100 }, { "epoch": 2.687435728254602, "grad_norm": 4.439746379852295, "learning_rate": 5.218347129668248e-06, "loss": 0.1323, "step": 452110 }, { "epoch": 2.6874951703312706, "grad_norm": 4.274438381195068, "learning_rate": 5.218139835292943e-06, "loss": 0.1189, "step": 452120 }, { "epoch": 2.687554612407939, "grad_norm": 3.9627163410186768, "learning_rate": 5.2179325405419735e-06, "loss": 0.1176, "step": 452130 }, { "epoch": 2.6876140544846074, "grad_norm": 3.836176872253418, "learning_rate": 5.217725245415699e-06, "loss": 0.1279, "step": 452140 }, { "epoch": 2.687673496561276, "grad_norm": 3.4975311756134033, "learning_rate": 5.2175179499144765e-06, "loss": 0.1155, "step": 452150 }, { "epoch": 2.6877329386379443, "grad_norm": 3.4562933444976807, "learning_rate": 5.21731065403866e-06, "loss": 0.1089, "step": 452160 }, { "epoch": 2.6877923807146127, "grad_norm": 3.692943811416626, "learning_rate": 5.2171033577886095e-06, "loss": 0.1162, "step": 452170 }, { "epoch": 2.687851822791281, "grad_norm": 3.6354470252990723, "learning_rate": 5.216896061164683e-06, "loss": 0.1087, "step": 452180 }, { "epoch": 2.6879112648679495, "grad_norm": 4.162670612335205, "learning_rate": 5.216688764167234e-06, "loss": 0.1201, "step": 452190 }, { "epoch": 2.687970706944618, "grad_norm": 3.2012081146240234, "learning_rate": 5.216481466796621e-06, "loss": 0.1054, "step": 452200 }, { "epoch": 2.6880301490212863, "grad_norm": 4.1797285079956055, "learning_rate": 5.216274169053202e-06, "loss": 0.1061, "step": 452210 }, { "epoch": 2.6880895910979548, "grad_norm": 4.089295387268066, "learning_rate": 5.216066870937332e-06, "loss": 0.118, "step": 452220 }, { "epoch": 2.688149033174623, "grad_norm": 4.861717700958252, "learning_rate": 5.21585957244937e-06, "loss": 0.1318, "step": 452230 }, { "epoch": 2.688208475251291, "grad_norm": 3.427962303161621, "learning_rate": 5.215652273589673e-06, "loss": 0.1076, "step": 452240 }, { "epoch": 2.68826791732796, "grad_norm": 3.3336591720581055, "learning_rate": 5.215444974358596e-06, "loss": 0.1394, "step": 452250 }, { "epoch": 2.688327359404628, "grad_norm": 5.8441009521484375, "learning_rate": 5.215237674756496e-06, "loss": 0.1199, "step": 452260 }, { "epoch": 2.6883868014812964, "grad_norm": 2.3585023880004883, "learning_rate": 5.215030374783732e-06, "loss": 0.1145, "step": 452270 }, { "epoch": 2.688446243557965, "grad_norm": 3.97171950340271, "learning_rate": 5.214823074440659e-06, "loss": 0.1291, "step": 452280 }, { "epoch": 2.688505685634633, "grad_norm": 4.476930618286133, "learning_rate": 5.2146157737276356e-06, "loss": 0.1186, "step": 452290 }, { "epoch": 2.6885651277113016, "grad_norm": 4.274967193603516, "learning_rate": 5.21440847264502e-06, "loss": 0.1076, "step": 452300 }, { "epoch": 2.68862456978797, "grad_norm": 5.027182579040527, "learning_rate": 5.214201171193165e-06, "loss": 0.1377, "step": 452310 }, { "epoch": 2.6886840118646385, "grad_norm": 6.4617180824279785, "learning_rate": 5.213993869372431e-06, "loss": 0.13, "step": 452320 }, { "epoch": 2.688743453941307, "grad_norm": 4.643671035766602, "learning_rate": 5.213786567183174e-06, "loss": 0.1184, "step": 452330 }, { "epoch": 2.6888028960179753, "grad_norm": 4.478439807891846, "learning_rate": 5.213579264625752e-06, "loss": 0.1356, "step": 452340 }, { "epoch": 2.6888623380946437, "grad_norm": 5.4397125244140625, "learning_rate": 5.213371961700519e-06, "loss": 0.1326, "step": 452350 }, { "epoch": 2.688921780171312, "grad_norm": 3.6237616539001465, "learning_rate": 5.213164658407835e-06, "loss": 0.1329, "step": 452360 }, { "epoch": 2.6889812222479805, "grad_norm": 3.991623640060425, "learning_rate": 5.212957354748057e-06, "loss": 0.1203, "step": 452370 }, { "epoch": 2.689040664324649, "grad_norm": 4.735132694244385, "learning_rate": 5.21275005072154e-06, "loss": 0.1153, "step": 452380 }, { "epoch": 2.6891001064013174, "grad_norm": 4.516086101531982, "learning_rate": 5.2125427463286415e-06, "loss": 0.1192, "step": 452390 }, { "epoch": 2.6891595484779858, "grad_norm": 4.347973823547363, "learning_rate": 5.2123354415697205e-06, "loss": 0.1271, "step": 452400 }, { "epoch": 2.6892189905546537, "grad_norm": 3.106146812438965, "learning_rate": 5.212128136445131e-06, "loss": 0.1335, "step": 452410 }, { "epoch": 2.6892784326313226, "grad_norm": 3.987293243408203, "learning_rate": 5.2119208309552325e-06, "loss": 0.115, "step": 452420 }, { "epoch": 2.6893378747079906, "grad_norm": 3.597966432571411, "learning_rate": 5.211713525100381e-06, "loss": 0.1074, "step": 452430 }, { "epoch": 2.6893973167846594, "grad_norm": 4.384334564208984, "learning_rate": 5.211506218880934e-06, "loss": 0.1291, "step": 452440 }, { "epoch": 2.6894567588613274, "grad_norm": 3.9981234073638916, "learning_rate": 5.2112989122972466e-06, "loss": 0.1225, "step": 452450 }, { "epoch": 2.689516200937996, "grad_norm": 5.049534320831299, "learning_rate": 5.211091605349679e-06, "loss": 0.1161, "step": 452460 }, { "epoch": 2.6895756430146642, "grad_norm": 4.08536434173584, "learning_rate": 5.210884298038586e-06, "loss": 0.1501, "step": 452470 }, { "epoch": 2.6896350850913326, "grad_norm": 4.200374126434326, "learning_rate": 5.210676990364324e-06, "loss": 0.1301, "step": 452480 }, { "epoch": 2.689694527168001, "grad_norm": 3.522941827774048, "learning_rate": 5.210469682327251e-06, "loss": 0.1213, "step": 452490 }, { "epoch": 2.6897539692446695, "grad_norm": 5.37102746963501, "learning_rate": 5.210262373927724e-06, "loss": 0.1278, "step": 452500 }, { "epoch": 2.689813411321338, "grad_norm": 4.468166351318359, "learning_rate": 5.210055065166102e-06, "loss": 0.1183, "step": 452510 }, { "epoch": 2.6898728533980063, "grad_norm": 4.9272685050964355, "learning_rate": 5.209847756042738e-06, "loss": 0.1157, "step": 452520 }, { "epoch": 2.6899322954746747, "grad_norm": 3.1275718212127686, "learning_rate": 5.209640446557993e-06, "loss": 0.1087, "step": 452530 }, { "epoch": 2.689991737551343, "grad_norm": 2.883686065673828, "learning_rate": 5.209433136712222e-06, "loss": 0.1147, "step": 452540 }, { "epoch": 2.6900511796280115, "grad_norm": 3.538724660873413, "learning_rate": 5.209225826505781e-06, "loss": 0.1197, "step": 452550 }, { "epoch": 2.69011062170468, "grad_norm": 4.393468856811523, "learning_rate": 5.209018515939029e-06, "loss": 0.1086, "step": 452560 }, { "epoch": 2.6901700637813484, "grad_norm": 4.4305315017700195, "learning_rate": 5.208811205012322e-06, "loss": 0.1528, "step": 452570 }, { "epoch": 2.690229505858017, "grad_norm": 4.497025012969971, "learning_rate": 5.2086038937260165e-06, "loss": 0.1239, "step": 452580 }, { "epoch": 2.690288947934685, "grad_norm": 4.206979751586914, "learning_rate": 5.208396582080472e-06, "loss": 0.1206, "step": 452590 }, { "epoch": 2.690348390011353, "grad_norm": 3.5689268112182617, "learning_rate": 5.2081892700760405e-06, "loss": 0.1229, "step": 452600 }, { "epoch": 2.690407832088022, "grad_norm": 4.326128005981445, "learning_rate": 5.207981957713085e-06, "loss": 0.1155, "step": 452610 }, { "epoch": 2.69046727416469, "grad_norm": 3.6677420139312744, "learning_rate": 5.207774644991959e-06, "loss": 0.1335, "step": 452620 }, { "epoch": 2.690526716241359, "grad_norm": 3.5833818912506104, "learning_rate": 5.2075673319130195e-06, "loss": 0.1172, "step": 452630 }, { "epoch": 2.690586158318027, "grad_norm": 4.437132835388184, "learning_rate": 5.207360018476626e-06, "loss": 0.1408, "step": 452640 }, { "epoch": 2.6906456003946952, "grad_norm": 4.168378829956055, "learning_rate": 5.2071527046831315e-06, "loss": 0.1209, "step": 452650 }, { "epoch": 2.6907050424713637, "grad_norm": 3.565502643585205, "learning_rate": 5.206945390532897e-06, "loss": 0.1202, "step": 452660 }, { "epoch": 2.690764484548032, "grad_norm": 4.782174110412598, "learning_rate": 5.2067380760262785e-06, "loss": 0.0977, "step": 452670 }, { "epoch": 2.6908239266247005, "grad_norm": 4.520277500152588, "learning_rate": 5.206530761163631e-06, "loss": 0.1255, "step": 452680 }, { "epoch": 2.690883368701369, "grad_norm": 3.6503729820251465, "learning_rate": 5.206323445945312e-06, "loss": 0.1346, "step": 452690 }, { "epoch": 2.6909428107780373, "grad_norm": 3.525599241256714, "learning_rate": 5.206116130371682e-06, "loss": 0.1133, "step": 452700 }, { "epoch": 2.6910022528547057, "grad_norm": 3.5309464931488037, "learning_rate": 5.2059088144430935e-06, "loss": 0.1513, "step": 452710 }, { "epoch": 2.691061694931374, "grad_norm": 5.141923904418945, "learning_rate": 5.2057014981599055e-06, "loss": 0.1239, "step": 452720 }, { "epoch": 2.6911211370080426, "grad_norm": 4.174320220947266, "learning_rate": 5.205494181522476e-06, "loss": 0.1331, "step": 452730 }, { "epoch": 2.691180579084711, "grad_norm": 5.261003494262695, "learning_rate": 5.2052868645311605e-06, "loss": 0.1193, "step": 452740 }, { "epoch": 2.6912400211613794, "grad_norm": 3.601043939590454, "learning_rate": 5.205079547186316e-06, "loss": 0.1226, "step": 452750 }, { "epoch": 2.691299463238048, "grad_norm": 3.779301404953003, "learning_rate": 5.2048722294883e-06, "loss": 0.1171, "step": 452760 }, { "epoch": 2.691358905314716, "grad_norm": 4.838902950286865, "learning_rate": 5.204664911437471e-06, "loss": 0.1119, "step": 452770 }, { "epoch": 2.6914183473913846, "grad_norm": 5.1105780601501465, "learning_rate": 5.204457593034183e-06, "loss": 0.1413, "step": 452780 }, { "epoch": 2.6914777894680526, "grad_norm": 5.311872959136963, "learning_rate": 5.204250274278796e-06, "loss": 0.1204, "step": 452790 }, { "epoch": 2.6915372315447215, "grad_norm": 3.521439552307129, "learning_rate": 5.204042955171665e-06, "loss": 0.1118, "step": 452800 }, { "epoch": 2.6915966736213894, "grad_norm": 4.452358245849609, "learning_rate": 5.203835635713146e-06, "loss": 0.1098, "step": 452810 }, { "epoch": 2.6916561156980583, "grad_norm": 3.927173614501953, "learning_rate": 5.2036283159036e-06, "loss": 0.1186, "step": 452820 }, { "epoch": 2.6917155577747263, "grad_norm": 4.024970531463623, "learning_rate": 5.2034209957433824e-06, "loss": 0.1202, "step": 452830 }, { "epoch": 2.6917749998513947, "grad_norm": 3.4523720741271973, "learning_rate": 5.203213675232847e-06, "loss": 0.1287, "step": 452840 }, { "epoch": 2.691834441928063, "grad_norm": 4.251051902770996, "learning_rate": 5.203006354372356e-06, "loss": 0.1287, "step": 452850 }, { "epoch": 2.6918938840047315, "grad_norm": 2.8890092372894287, "learning_rate": 5.2027990331622625e-06, "loss": 0.1037, "step": 452860 }, { "epoch": 2.6919533260814, "grad_norm": 3.9804749488830566, "learning_rate": 5.202591711602923e-06, "loss": 0.1149, "step": 452870 }, { "epoch": 2.6920127681580683, "grad_norm": 4.697906494140625, "learning_rate": 5.2023843896947e-06, "loss": 0.1235, "step": 452880 }, { "epoch": 2.6920722102347368, "grad_norm": 4.639497756958008, "learning_rate": 5.2021770674379455e-06, "loss": 0.1113, "step": 452890 }, { "epoch": 2.692131652311405, "grad_norm": 4.4960856437683105, "learning_rate": 5.201969744833016e-06, "loss": 0.1239, "step": 452900 }, { "epoch": 2.6921910943880736, "grad_norm": 4.304039001464844, "learning_rate": 5.201762421880273e-06, "loss": 0.1143, "step": 452910 }, { "epoch": 2.692250536464742, "grad_norm": 4.7630486488342285, "learning_rate": 5.20155509858007e-06, "loss": 0.1247, "step": 452920 }, { "epoch": 2.6923099785414104, "grad_norm": 3.3478705883026123, "learning_rate": 5.201347774932766e-06, "loss": 0.1001, "step": 452930 }, { "epoch": 2.692369420618079, "grad_norm": 4.218581676483154, "learning_rate": 5.201140450938715e-06, "loss": 0.1002, "step": 452940 }, { "epoch": 2.6924288626947472, "grad_norm": 3.7656235694885254, "learning_rate": 5.2009331265982786e-06, "loss": 0.1162, "step": 452950 }, { "epoch": 2.6924883047714157, "grad_norm": 4.787963390350342, "learning_rate": 5.200725801911811e-06, "loss": 0.1165, "step": 452960 }, { "epoch": 2.692547746848084, "grad_norm": 4.248808860778809, "learning_rate": 5.2005184768796676e-06, "loss": 0.1168, "step": 452970 }, { "epoch": 2.692607188924752, "grad_norm": 3.828920841217041, "learning_rate": 5.2003111515022095e-06, "loss": 0.112, "step": 452980 }, { "epoch": 2.692666631001421, "grad_norm": 3.046304702758789, "learning_rate": 5.200103825779792e-06, "loss": 0.1181, "step": 452990 }, { "epoch": 2.692726073078089, "grad_norm": 3.576620101928711, "learning_rate": 5.19989649971277e-06, "loss": 0.1067, "step": 453000 }, { "epoch": 2.6927855151547573, "grad_norm": 4.063873291015625, "learning_rate": 5.199689173301504e-06, "loss": 0.117, "step": 453010 }, { "epoch": 2.6928449572314257, "grad_norm": 4.529353618621826, "learning_rate": 5.199481846546349e-06, "loss": 0.1329, "step": 453020 }, { "epoch": 2.692904399308094, "grad_norm": 4.059128761291504, "learning_rate": 5.199274519447661e-06, "loss": 0.1264, "step": 453030 }, { "epoch": 2.6929638413847625, "grad_norm": 4.860723972320557, "learning_rate": 5.199067192005799e-06, "loss": 0.1328, "step": 453040 }, { "epoch": 2.693023283461431, "grad_norm": 4.336673259735107, "learning_rate": 5.198859864221121e-06, "loss": 0.1275, "step": 453050 }, { "epoch": 2.6930827255380994, "grad_norm": 3.7217905521392822, "learning_rate": 5.198652536093982e-06, "loss": 0.1161, "step": 453060 }, { "epoch": 2.6931421676147678, "grad_norm": 3.6656832695007324, "learning_rate": 5.198445207624738e-06, "loss": 0.1167, "step": 453070 }, { "epoch": 2.693201609691436, "grad_norm": 3.715660572052002, "learning_rate": 5.19823787881375e-06, "loss": 0.1262, "step": 453080 }, { "epoch": 2.6932610517681046, "grad_norm": 3.887035369873047, "learning_rate": 5.1980305496613724e-06, "loss": 0.1202, "step": 453090 }, { "epoch": 2.693320493844773, "grad_norm": 4.4171223640441895, "learning_rate": 5.197823220167961e-06, "loss": 0.126, "step": 453100 }, { "epoch": 2.6933799359214414, "grad_norm": 4.820267200469971, "learning_rate": 5.197615890333876e-06, "loss": 0.1056, "step": 453110 }, { "epoch": 2.69343937799811, "grad_norm": 4.247493743896484, "learning_rate": 5.197408560159473e-06, "loss": 0.11, "step": 453120 }, { "epoch": 2.6934988200747783, "grad_norm": 3.782078981399536, "learning_rate": 5.197201229645107e-06, "loss": 0.1136, "step": 453130 }, { "epoch": 2.6935582621514467, "grad_norm": 4.5049567222595215, "learning_rate": 5.196993898791137e-06, "loss": 0.1127, "step": 453140 }, { "epoch": 2.6936177042281146, "grad_norm": 4.587265491485596, "learning_rate": 5.196786567597922e-06, "loss": 0.1227, "step": 453150 }, { "epoch": 2.6936771463047835, "grad_norm": 4.70291805267334, "learning_rate": 5.196579236065816e-06, "loss": 0.1151, "step": 453160 }, { "epoch": 2.6937365883814515, "grad_norm": 4.235290050506592, "learning_rate": 5.196371904195176e-06, "loss": 0.1258, "step": 453170 }, { "epoch": 2.6937960304581203, "grad_norm": 4.63624906539917, "learning_rate": 5.196164571986363e-06, "loss": 0.1313, "step": 453180 }, { "epoch": 2.6938554725347883, "grad_norm": 4.2591142654418945, "learning_rate": 5.19595723943973e-06, "loss": 0.1218, "step": 453190 }, { "epoch": 2.6939149146114567, "grad_norm": 5.637650012969971, "learning_rate": 5.195749906555634e-06, "loss": 0.113, "step": 453200 }, { "epoch": 2.693974356688125, "grad_norm": 5.351319789886475, "learning_rate": 5.195542573334435e-06, "loss": 0.121, "step": 453210 }, { "epoch": 2.6940337987647935, "grad_norm": 5.319785118103027, "learning_rate": 5.1953352397764875e-06, "loss": 0.1309, "step": 453220 }, { "epoch": 2.694093240841462, "grad_norm": 3.296726703643799, "learning_rate": 5.195127905882149e-06, "loss": 0.1232, "step": 453230 }, { "epoch": 2.6941526829181304, "grad_norm": 3.4891695976257324, "learning_rate": 5.194920571651777e-06, "loss": 0.1024, "step": 453240 }, { "epoch": 2.694212124994799, "grad_norm": 3.765974521636963, "learning_rate": 5.194713237085729e-06, "loss": 0.1007, "step": 453250 }, { "epoch": 2.694271567071467, "grad_norm": 6.078275680541992, "learning_rate": 5.194505902184361e-06, "loss": 0.1252, "step": 453260 }, { "epoch": 2.6943310091481356, "grad_norm": 3.567439556121826, "learning_rate": 5.19429856694803e-06, "loss": 0.1031, "step": 453270 }, { "epoch": 2.694390451224804, "grad_norm": 4.152406692504883, "learning_rate": 5.1940912313770965e-06, "loss": 0.127, "step": 453280 }, { "epoch": 2.6944498933014724, "grad_norm": 4.8889923095703125, "learning_rate": 5.193883895471913e-06, "loss": 0.1032, "step": 453290 }, { "epoch": 2.694509335378141, "grad_norm": 2.7430419921875, "learning_rate": 5.193676559232838e-06, "loss": 0.1117, "step": 453300 }, { "epoch": 2.6945687774548093, "grad_norm": 3.7773149013519287, "learning_rate": 5.193469222660229e-06, "loss": 0.1237, "step": 453310 }, { "epoch": 2.6946282195314777, "grad_norm": 4.262352466583252, "learning_rate": 5.193261885754443e-06, "loss": 0.1175, "step": 453320 }, { "epoch": 2.694687661608146, "grad_norm": 4.216592311859131, "learning_rate": 5.1930545485158365e-06, "loss": 0.1366, "step": 453330 }, { "epoch": 2.694747103684814, "grad_norm": 2.876146078109741, "learning_rate": 5.192847210944769e-06, "loss": 0.12, "step": 453340 }, { "epoch": 2.694806545761483, "grad_norm": 4.251412391662598, "learning_rate": 5.192639873041594e-06, "loss": 0.1113, "step": 453350 }, { "epoch": 2.694865987838151, "grad_norm": 5.089477062225342, "learning_rate": 5.1924325348066685e-06, "loss": 0.1097, "step": 453360 }, { "epoch": 2.6949254299148198, "grad_norm": 4.646256923675537, "learning_rate": 5.192225196240354e-06, "loss": 0.1249, "step": 453370 }, { "epoch": 2.6949848719914877, "grad_norm": 3.6670117378234863, "learning_rate": 5.192017857343004e-06, "loss": 0.1061, "step": 453380 }, { "epoch": 2.695044314068156, "grad_norm": 2.821995258331299, "learning_rate": 5.191810518114977e-06, "loss": 0.1202, "step": 453390 }, { "epoch": 2.6951037561448246, "grad_norm": 5.370577335357666, "learning_rate": 5.1916031785566276e-06, "loss": 0.1348, "step": 453400 }, { "epoch": 2.695163198221493, "grad_norm": 4.368792533874512, "learning_rate": 5.191395838668316e-06, "loss": 0.119, "step": 453410 }, { "epoch": 2.6952226402981614, "grad_norm": 4.2978105545043945, "learning_rate": 5.191188498450398e-06, "loss": 0.1039, "step": 453420 }, { "epoch": 2.69528208237483, "grad_norm": 3.4299185276031494, "learning_rate": 5.19098115790323e-06, "loss": 0.1183, "step": 453430 }, { "epoch": 2.695341524451498, "grad_norm": 3.694183349609375, "learning_rate": 5.190773817027169e-06, "loss": 0.1333, "step": 453440 }, { "epoch": 2.6954009665281666, "grad_norm": 3.3684639930725098, "learning_rate": 5.190566475822575e-06, "loss": 0.0946, "step": 453450 }, { "epoch": 2.695460408604835, "grad_norm": 3.490335702896118, "learning_rate": 5.190359134289799e-06, "loss": 0.1147, "step": 453460 }, { "epoch": 2.6955198506815035, "grad_norm": 4.150783538818359, "learning_rate": 5.190151792429205e-06, "loss": 0.1339, "step": 453470 }, { "epoch": 2.695579292758172, "grad_norm": 3.948479175567627, "learning_rate": 5.189944450241147e-06, "loss": 0.1181, "step": 453480 }, { "epoch": 2.6956387348348403, "grad_norm": 2.7876620292663574, "learning_rate": 5.18973710772598e-06, "loss": 0.1078, "step": 453490 }, { "epoch": 2.6956981769115087, "grad_norm": 4.422582149505615, "learning_rate": 5.1895297648840635e-06, "loss": 0.1193, "step": 453500 }, { "epoch": 2.695757618988177, "grad_norm": 4.683566093444824, "learning_rate": 5.189322421715756e-06, "loss": 0.111, "step": 453510 }, { "epoch": 2.6958170610648455, "grad_norm": 4.494603157043457, "learning_rate": 5.189115078221411e-06, "loss": 0.1155, "step": 453520 }, { "epoch": 2.6958765031415135, "grad_norm": 3.9635226726531982, "learning_rate": 5.1889077344013885e-06, "loss": 0.12, "step": 453530 }, { "epoch": 2.6959359452181824, "grad_norm": 3.9537389278411865, "learning_rate": 5.188700390256043e-06, "loss": 0.1142, "step": 453540 }, { "epoch": 2.6959953872948503, "grad_norm": 4.048332214355469, "learning_rate": 5.188493045785733e-06, "loss": 0.1413, "step": 453550 }, { "epoch": 2.696054829371519, "grad_norm": 3.2233753204345703, "learning_rate": 5.188285700990817e-06, "loss": 0.1134, "step": 453560 }, { "epoch": 2.696114271448187, "grad_norm": 4.134605884552002, "learning_rate": 5.188078355871649e-06, "loss": 0.1321, "step": 453570 }, { "epoch": 2.6961737135248556, "grad_norm": 4.006276607513428, "learning_rate": 5.187871010428588e-06, "loss": 0.1113, "step": 453580 }, { "epoch": 2.696233155601524, "grad_norm": 4.620762825012207, "learning_rate": 5.187663664661991e-06, "loss": 0.1158, "step": 453590 }, { "epoch": 2.6962925976781924, "grad_norm": 4.120955467224121, "learning_rate": 5.187456318572215e-06, "loss": 0.1287, "step": 453600 }, { "epoch": 2.696352039754861, "grad_norm": 4.187565326690674, "learning_rate": 5.187248972159617e-06, "loss": 0.1207, "step": 453610 }, { "epoch": 2.6964114818315292, "grad_norm": 4.428642272949219, "learning_rate": 5.1870416254245526e-06, "loss": 0.1123, "step": 453620 }, { "epoch": 2.6964709239081976, "grad_norm": 3.9092299938201904, "learning_rate": 5.186834278367381e-06, "loss": 0.1076, "step": 453630 }, { "epoch": 2.696530365984866, "grad_norm": 2.779090404510498, "learning_rate": 5.186626930988458e-06, "loss": 0.1262, "step": 453640 }, { "epoch": 2.6965898080615345, "grad_norm": 3.195469379425049, "learning_rate": 5.1864195832881416e-06, "loss": 0.1165, "step": 453650 }, { "epoch": 2.696649250138203, "grad_norm": 4.079736232757568, "learning_rate": 5.18621223526679e-06, "loss": 0.105, "step": 453660 }, { "epoch": 2.6967086922148713, "grad_norm": 3.273113489151001, "learning_rate": 5.186004886924757e-06, "loss": 0.1113, "step": 453670 }, { "epoch": 2.6967681342915397, "grad_norm": 4.109621524810791, "learning_rate": 5.1857975382624e-06, "loss": 0.1428, "step": 453680 }, { "epoch": 2.696827576368208, "grad_norm": 5.407296180725098, "learning_rate": 5.18559018928008e-06, "loss": 0.1103, "step": 453690 }, { "epoch": 2.6968870184448765, "grad_norm": 4.299729824066162, "learning_rate": 5.18538283997815e-06, "loss": 0.1186, "step": 453700 }, { "epoch": 2.696946460521545, "grad_norm": 4.0756306648254395, "learning_rate": 5.185175490356971e-06, "loss": 0.1097, "step": 453710 }, { "epoch": 2.697005902598213, "grad_norm": 2.8516135215759277, "learning_rate": 5.184968140416894e-06, "loss": 0.1237, "step": 453720 }, { "epoch": 2.697065344674882, "grad_norm": 3.705158233642578, "learning_rate": 5.184760790158283e-06, "loss": 0.125, "step": 453730 }, { "epoch": 2.6971247867515498, "grad_norm": 3.760932445526123, "learning_rate": 5.184553439581491e-06, "loss": 0.1135, "step": 453740 }, { "epoch": 2.697184228828218, "grad_norm": 2.7985987663269043, "learning_rate": 5.184346088686874e-06, "loss": 0.1102, "step": 453750 }, { "epoch": 2.6972436709048866, "grad_norm": 4.720755100250244, "learning_rate": 5.184138737474793e-06, "loss": 0.1155, "step": 453760 }, { "epoch": 2.697303112981555, "grad_norm": 3.981951951980591, "learning_rate": 5.183931385945604e-06, "loss": 0.123, "step": 453770 }, { "epoch": 2.6973625550582234, "grad_norm": 4.336905479431152, "learning_rate": 5.183724034099661e-06, "loss": 0.1288, "step": 453780 }, { "epoch": 2.697421997134892, "grad_norm": 4.200061798095703, "learning_rate": 5.183516681937325e-06, "loss": 0.145, "step": 453790 }, { "epoch": 2.6974814392115603, "grad_norm": 4.251269817352295, "learning_rate": 5.18330932945895e-06, "loss": 0.1188, "step": 453800 }, { "epoch": 2.6975408812882287, "grad_norm": 4.504811763763428, "learning_rate": 5.1831019766648946e-06, "loss": 0.1199, "step": 453810 }, { "epoch": 2.697600323364897, "grad_norm": 5.5261030197143555, "learning_rate": 5.182894623555517e-06, "loss": 0.1372, "step": 453820 }, { "epoch": 2.6976597654415655, "grad_norm": 4.231286525726318, "learning_rate": 5.1826872701311725e-06, "loss": 0.117, "step": 453830 }, { "epoch": 2.697719207518234, "grad_norm": 4.653543472290039, "learning_rate": 5.182479916392218e-06, "loss": 0.1235, "step": 453840 }, { "epoch": 2.6977786495949023, "grad_norm": 5.590449333190918, "learning_rate": 5.182272562339011e-06, "loss": 0.1354, "step": 453850 }, { "epoch": 2.6978380916715707, "grad_norm": 2.88818097114563, "learning_rate": 5.182065207971911e-06, "loss": 0.122, "step": 453860 }, { "epoch": 2.697897533748239, "grad_norm": 3.8070485591888428, "learning_rate": 5.181857853291272e-06, "loss": 0.1249, "step": 453870 }, { "epoch": 2.6979569758249076, "grad_norm": 6.1489481925964355, "learning_rate": 5.181650498297451e-06, "loss": 0.1097, "step": 453880 }, { "epoch": 2.6980164179015755, "grad_norm": 5.480122089385986, "learning_rate": 5.1814431429908075e-06, "loss": 0.1341, "step": 453890 }, { "epoch": 2.6980758599782444, "grad_norm": 3.760181188583374, "learning_rate": 5.181235787371697e-06, "loss": 0.1141, "step": 453900 }, { "epoch": 2.6981353020549124, "grad_norm": 3.817624807357788, "learning_rate": 5.181028431440476e-06, "loss": 0.123, "step": 453910 }, { "epoch": 2.6981947441315812, "grad_norm": 3.130775213241577, "learning_rate": 5.180821075197502e-06, "loss": 0.0979, "step": 453920 }, { "epoch": 2.698254186208249, "grad_norm": 2.908278703689575, "learning_rate": 5.1806137186431335e-06, "loss": 0.1045, "step": 453930 }, { "epoch": 2.6983136282849176, "grad_norm": 3.333282470703125, "learning_rate": 5.180406361777728e-06, "loss": 0.105, "step": 453940 }, { "epoch": 2.698373070361586, "grad_norm": 4.505318641662598, "learning_rate": 5.180199004601639e-06, "loss": 0.1103, "step": 453950 }, { "epoch": 2.6984325124382544, "grad_norm": 3.6424968242645264, "learning_rate": 5.179991647115226e-06, "loss": 0.1173, "step": 453960 }, { "epoch": 2.698491954514923, "grad_norm": 3.386483669281006, "learning_rate": 5.179784289318848e-06, "loss": 0.1011, "step": 453970 }, { "epoch": 2.6985513965915913, "grad_norm": 4.491494178771973, "learning_rate": 5.179576931212858e-06, "loss": 0.1234, "step": 453980 }, { "epoch": 2.6986108386682597, "grad_norm": 3.016901731491089, "learning_rate": 5.179369572797615e-06, "loss": 0.1204, "step": 453990 }, { "epoch": 2.698670280744928, "grad_norm": 4.893387794494629, "learning_rate": 5.179162214073479e-06, "loss": 0.1307, "step": 454000 }, { "epoch": 2.6987297228215965, "grad_norm": 2.94655179977417, "learning_rate": 5.178954855040801e-06, "loss": 0.107, "step": 454010 }, { "epoch": 2.698789164898265, "grad_norm": 4.311132907867432, "learning_rate": 5.1787474956999415e-06, "loss": 0.1363, "step": 454020 }, { "epoch": 2.6988486069749333, "grad_norm": 4.54926872253418, "learning_rate": 5.17854013605126e-06, "loss": 0.118, "step": 454030 }, { "epoch": 2.6989080490516018, "grad_norm": 4.779823303222656, "learning_rate": 5.1783327760951094e-06, "loss": 0.1122, "step": 454040 }, { "epoch": 2.69896749112827, "grad_norm": 3.543222188949585, "learning_rate": 5.178125415831848e-06, "loss": 0.1198, "step": 454050 }, { "epoch": 2.6990269332049386, "grad_norm": 3.9232707023620605, "learning_rate": 5.177918055261835e-06, "loss": 0.1064, "step": 454060 }, { "epoch": 2.699086375281607, "grad_norm": 3.7340593338012695, "learning_rate": 5.177710694385425e-06, "loss": 0.1043, "step": 454070 }, { "epoch": 2.699145817358275, "grad_norm": 3.902242422103882, "learning_rate": 5.1775033332029755e-06, "loss": 0.1238, "step": 454080 }, { "epoch": 2.699205259434944, "grad_norm": 4.311630725860596, "learning_rate": 5.177295971714845e-06, "loss": 0.1067, "step": 454090 }, { "epoch": 2.699264701511612, "grad_norm": 4.206586837768555, "learning_rate": 5.177088609921389e-06, "loss": 0.1058, "step": 454100 }, { "epoch": 2.6993241435882807, "grad_norm": 3.390272855758667, "learning_rate": 5.176881247822966e-06, "loss": 0.1273, "step": 454110 }, { "epoch": 2.6993835856649486, "grad_norm": 3.5676002502441406, "learning_rate": 5.176673885419932e-06, "loss": 0.1144, "step": 454120 }, { "epoch": 2.699443027741617, "grad_norm": 4.3100152015686035, "learning_rate": 5.176466522712643e-06, "loss": 0.1322, "step": 454130 }, { "epoch": 2.6995024698182855, "grad_norm": 5.509113788604736, "learning_rate": 5.176259159701459e-06, "loss": 0.1446, "step": 454140 }, { "epoch": 2.699561911894954, "grad_norm": 4.798559665679932, "learning_rate": 5.176051796386735e-06, "loss": 0.1238, "step": 454150 }, { "epoch": 2.6996213539716223, "grad_norm": 4.1223368644714355, "learning_rate": 5.1758444327688305e-06, "loss": 0.1149, "step": 454160 }, { "epoch": 2.6996807960482907, "grad_norm": 3.4968454837799072, "learning_rate": 5.1756370688481e-06, "loss": 0.1116, "step": 454170 }, { "epoch": 2.699740238124959, "grad_norm": 3.346782922744751, "learning_rate": 5.175429704624902e-06, "loss": 0.1299, "step": 454180 }, { "epoch": 2.6997996802016275, "grad_norm": 4.2579779624938965, "learning_rate": 5.175222340099592e-06, "loss": 0.1137, "step": 454190 }, { "epoch": 2.699859122278296, "grad_norm": 4.169290065765381, "learning_rate": 5.175014975272528e-06, "loss": 0.1293, "step": 454200 }, { "epoch": 2.6999185643549644, "grad_norm": 5.389883518218994, "learning_rate": 5.174807610144068e-06, "loss": 0.1097, "step": 454210 }, { "epoch": 2.6999780064316328, "grad_norm": 3.2914984226226807, "learning_rate": 5.17460024471457e-06, "loss": 0.1371, "step": 454220 }, { "epoch": 2.700037448508301, "grad_norm": 4.616855144500732, "learning_rate": 5.174392878984387e-06, "loss": 0.1061, "step": 454230 }, { "epoch": 2.7000968905849696, "grad_norm": 4.413349151611328, "learning_rate": 5.174185512953879e-06, "loss": 0.1248, "step": 454240 }, { "epoch": 2.700156332661638, "grad_norm": 3.7574689388275146, "learning_rate": 5.173978146623404e-06, "loss": 0.1089, "step": 454250 }, { "epoch": 2.7002157747383064, "grad_norm": 3.3228209018707275, "learning_rate": 5.1737707799933176e-06, "loss": 0.1025, "step": 454260 }, { "epoch": 2.7002752168149744, "grad_norm": 3.3477115631103516, "learning_rate": 5.173563413063976e-06, "loss": 0.1286, "step": 454270 }, { "epoch": 2.7003346588916433, "grad_norm": 4.4492506980896, "learning_rate": 5.173356045835739e-06, "loss": 0.1219, "step": 454280 }, { "epoch": 2.7003941009683112, "grad_norm": 3.55471134185791, "learning_rate": 5.173148678308962e-06, "loss": 0.122, "step": 454290 }, { "epoch": 2.70045354304498, "grad_norm": 4.308096885681152, "learning_rate": 5.172941310484001e-06, "loss": 0.1244, "step": 454300 }, { "epoch": 2.700512985121648, "grad_norm": 3.686138868331909, "learning_rate": 5.1727339423612165e-06, "loss": 0.1126, "step": 454310 }, { "epoch": 2.7005724271983165, "grad_norm": 3.4414727687835693, "learning_rate": 5.172526573940963e-06, "loss": 0.1185, "step": 454320 }, { "epoch": 2.700631869274985, "grad_norm": 5.5374531745910645, "learning_rate": 5.172319205223596e-06, "loss": 0.135, "step": 454330 }, { "epoch": 2.7006913113516533, "grad_norm": 3.3973278999328613, "learning_rate": 5.1721118362094765e-06, "loss": 0.108, "step": 454340 }, { "epoch": 2.7007507534283217, "grad_norm": 4.19244384765625, "learning_rate": 5.171904466898959e-06, "loss": 0.1305, "step": 454350 }, { "epoch": 2.70081019550499, "grad_norm": 3.7487809658050537, "learning_rate": 5.171697097292403e-06, "loss": 0.1066, "step": 454360 }, { "epoch": 2.7008696375816585, "grad_norm": 3.9549176692962646, "learning_rate": 5.171489727390163e-06, "loss": 0.1222, "step": 454370 }, { "epoch": 2.700929079658327, "grad_norm": 4.6057538986206055, "learning_rate": 5.171282357192598e-06, "loss": 0.1173, "step": 454380 }, { "epoch": 2.7009885217349954, "grad_norm": 5.082010269165039, "learning_rate": 5.171074986700064e-06, "loss": 0.1473, "step": 454390 }, { "epoch": 2.701047963811664, "grad_norm": 4.4464802742004395, "learning_rate": 5.1708676159129176e-06, "loss": 0.1135, "step": 454400 }, { "epoch": 2.701107405888332, "grad_norm": 6.261504173278809, "learning_rate": 5.170660244831518e-06, "loss": 0.1073, "step": 454410 }, { "epoch": 2.7011668479650006, "grad_norm": 3.0924086570739746, "learning_rate": 5.170452873456221e-06, "loss": 0.1335, "step": 454420 }, { "epoch": 2.701226290041669, "grad_norm": 5.088602542877197, "learning_rate": 5.170245501787383e-06, "loss": 0.1196, "step": 454430 }, { "epoch": 2.7012857321183374, "grad_norm": 4.164803981781006, "learning_rate": 5.1700381298253635e-06, "loss": 0.1098, "step": 454440 }, { "epoch": 2.701345174195006, "grad_norm": 4.765583515167236, "learning_rate": 5.169830757570516e-06, "loss": 0.1379, "step": 454450 }, { "epoch": 2.701404616271674, "grad_norm": 4.794418811798096, "learning_rate": 5.1696233850232e-06, "loss": 0.121, "step": 454460 }, { "epoch": 2.7014640583483427, "grad_norm": 5.693179130554199, "learning_rate": 5.169416012183772e-06, "loss": 0.1191, "step": 454470 }, { "epoch": 2.7015235004250107, "grad_norm": 3.9716968536376953, "learning_rate": 5.169208639052591e-06, "loss": 0.1371, "step": 454480 }, { "epoch": 2.701582942501679, "grad_norm": 3.6849961280822754, "learning_rate": 5.169001265630013e-06, "loss": 0.1082, "step": 454490 }, { "epoch": 2.7016423845783475, "grad_norm": 5.300126552581787, "learning_rate": 5.168793891916393e-06, "loss": 0.1144, "step": 454500 }, { "epoch": 2.701701826655016, "grad_norm": 5.8904876708984375, "learning_rate": 5.168586517912089e-06, "loss": 0.1267, "step": 454510 }, { "epoch": 2.7017612687316843, "grad_norm": 5.659598350524902, "learning_rate": 5.168379143617461e-06, "loss": 0.1167, "step": 454520 }, { "epoch": 2.7018207108083527, "grad_norm": 4.3338823318481445, "learning_rate": 5.1681717690328635e-06, "loss": 0.1099, "step": 454530 }, { "epoch": 2.701880152885021, "grad_norm": 4.280389308929443, "learning_rate": 5.167964394158654e-06, "loss": 0.134, "step": 454540 }, { "epoch": 2.7019395949616896, "grad_norm": 4.591339111328125, "learning_rate": 5.16775701899519e-06, "loss": 0.1267, "step": 454550 }, { "epoch": 2.701999037038358, "grad_norm": 4.174678325653076, "learning_rate": 5.167549643542828e-06, "loss": 0.1061, "step": 454560 }, { "epoch": 2.7020584791150264, "grad_norm": 4.275284767150879, "learning_rate": 5.167342267801924e-06, "loss": 0.1192, "step": 454570 }, { "epoch": 2.702117921191695, "grad_norm": 2.7591795921325684, "learning_rate": 5.167134891772839e-06, "loss": 0.1007, "step": 454580 }, { "epoch": 2.702177363268363, "grad_norm": 4.803160667419434, "learning_rate": 5.166927515455927e-06, "loss": 0.1257, "step": 454590 }, { "epoch": 2.7022368053450316, "grad_norm": 5.0621771812438965, "learning_rate": 5.166720138851545e-06, "loss": 0.129, "step": 454600 }, { "epoch": 2.7022962474217, "grad_norm": 3.0421249866485596, "learning_rate": 5.166512761960053e-06, "loss": 0.0959, "step": 454610 }, { "epoch": 2.7023556894983685, "grad_norm": 4.048879146575928, "learning_rate": 5.166305384781805e-06, "loss": 0.1227, "step": 454620 }, { "epoch": 2.7024151315750364, "grad_norm": 4.550264835357666, "learning_rate": 5.166098007317158e-06, "loss": 0.1151, "step": 454630 }, { "epoch": 2.7024745736517053, "grad_norm": 5.239680767059326, "learning_rate": 5.1658906295664725e-06, "loss": 0.1337, "step": 454640 }, { "epoch": 2.7025340157283733, "grad_norm": 3.708172082901001, "learning_rate": 5.1656832515301036e-06, "loss": 0.1152, "step": 454650 }, { "epoch": 2.702593457805042, "grad_norm": 3.9644529819488525, "learning_rate": 5.1654758732084065e-06, "loss": 0.1255, "step": 454660 }, { "epoch": 2.70265289988171, "grad_norm": 3.719059467315674, "learning_rate": 5.165268494601742e-06, "loss": 0.1168, "step": 454670 }, { "epoch": 2.7027123419583785, "grad_norm": 4.0257110595703125, "learning_rate": 5.165061115710464e-06, "loss": 0.1235, "step": 454680 }, { "epoch": 2.702771784035047, "grad_norm": 3.4471795558929443, "learning_rate": 5.16485373653493e-06, "loss": 0.1451, "step": 454690 }, { "epoch": 2.7028312261117153, "grad_norm": 3.009296178817749, "learning_rate": 5.164646357075501e-06, "loss": 0.1215, "step": 454700 }, { "epoch": 2.7028906681883837, "grad_norm": 4.716309070587158, "learning_rate": 5.164438977332531e-06, "loss": 0.1157, "step": 454710 }, { "epoch": 2.702950110265052, "grad_norm": 5.255038738250732, "learning_rate": 5.1642315973063775e-06, "loss": 0.1233, "step": 454720 }, { "epoch": 2.7030095523417206, "grad_norm": 5.522502422332764, "learning_rate": 5.1640242169973955e-06, "loss": 0.1146, "step": 454730 }, { "epoch": 2.703068994418389, "grad_norm": 5.428505897521973, "learning_rate": 5.163816836405946e-06, "loss": 0.1207, "step": 454740 }, { "epoch": 2.7031284364950574, "grad_norm": 6.3837761878967285, "learning_rate": 5.163609455532385e-06, "loss": 0.116, "step": 454750 }, { "epoch": 2.703187878571726, "grad_norm": 6.07673978805542, "learning_rate": 5.163402074377066e-06, "loss": 0.1158, "step": 454760 }, { "epoch": 2.7032473206483942, "grad_norm": 3.4075334072113037, "learning_rate": 5.163194692940352e-06, "loss": 0.1425, "step": 454770 }, { "epoch": 2.7033067627250627, "grad_norm": 3.7820749282836914, "learning_rate": 5.162987311222597e-06, "loss": 0.1303, "step": 454780 }, { "epoch": 2.703366204801731, "grad_norm": 4.543428897857666, "learning_rate": 5.162779929224156e-06, "loss": 0.1226, "step": 454790 }, { "epoch": 2.7034256468783995, "grad_norm": 4.123680114746094, "learning_rate": 5.16257254694539e-06, "loss": 0.1139, "step": 454800 }, { "epoch": 2.703485088955068, "grad_norm": 3.6852664947509766, "learning_rate": 5.1623651643866555e-06, "loss": 0.1082, "step": 454810 }, { "epoch": 2.703544531031736, "grad_norm": 4.48399019241333, "learning_rate": 5.1621577815483085e-06, "loss": 0.1186, "step": 454820 }, { "epoch": 2.7036039731084047, "grad_norm": 4.12314510345459, "learning_rate": 5.161950398430706e-06, "loss": 0.1061, "step": 454830 }, { "epoch": 2.7036634151850727, "grad_norm": 4.4741997718811035, "learning_rate": 5.1617430150342065e-06, "loss": 0.1231, "step": 454840 }, { "epoch": 2.7037228572617416, "grad_norm": 4.350216388702393, "learning_rate": 5.161535631359165e-06, "loss": 0.1134, "step": 454850 }, { "epoch": 2.7037822993384095, "grad_norm": 4.198925495147705, "learning_rate": 5.16132824740594e-06, "loss": 0.1275, "step": 454860 }, { "epoch": 2.703841741415078, "grad_norm": 4.464921474456787, "learning_rate": 5.16112086317489e-06, "loss": 0.1146, "step": 454870 }, { "epoch": 2.7039011834917464, "grad_norm": 3.3548388481140137, "learning_rate": 5.160913478666368e-06, "loss": 0.1319, "step": 454880 }, { "epoch": 2.7039606255684148, "grad_norm": 4.128235340118408, "learning_rate": 5.160706093880736e-06, "loss": 0.1141, "step": 454890 }, { "epoch": 2.704020067645083, "grad_norm": 3.455780267715454, "learning_rate": 5.160498708818348e-06, "loss": 0.1286, "step": 454900 }, { "epoch": 2.7040795097217516, "grad_norm": 3.419560670852661, "learning_rate": 5.1602913234795625e-06, "loss": 0.1099, "step": 454910 }, { "epoch": 2.70413895179842, "grad_norm": 4.704395771026611, "learning_rate": 5.160083937864736e-06, "loss": 0.1145, "step": 454920 }, { "epoch": 2.7041983938750884, "grad_norm": 3.2058374881744385, "learning_rate": 5.159876551974226e-06, "loss": 0.1227, "step": 454930 }, { "epoch": 2.704257835951757, "grad_norm": 3.6249189376831055, "learning_rate": 5.159669165808389e-06, "loss": 0.1278, "step": 454940 }, { "epoch": 2.7043172780284253, "grad_norm": 3.476318359375, "learning_rate": 5.1594617793675825e-06, "loss": 0.1171, "step": 454950 }, { "epoch": 2.7043767201050937, "grad_norm": 3.98289155960083, "learning_rate": 5.159254392652166e-06, "loss": 0.1271, "step": 454960 }, { "epoch": 2.704436162181762, "grad_norm": 4.655350208282471, "learning_rate": 5.159047005662492e-06, "loss": 0.1312, "step": 454970 }, { "epoch": 2.7044956042584305, "grad_norm": 3.4394662380218506, "learning_rate": 5.158839618398921e-06, "loss": 0.1156, "step": 454980 }, { "epoch": 2.704555046335099, "grad_norm": 4.163001537322998, "learning_rate": 5.158632230861809e-06, "loss": 0.1257, "step": 454990 }, { "epoch": 2.7046144884117673, "grad_norm": 3.195380210876465, "learning_rate": 5.158424843051514e-06, "loss": 0.1212, "step": 455000 }, { "epoch": 2.7046739304884353, "grad_norm": 3.7238082885742188, "learning_rate": 5.158217454968392e-06, "loss": 0.1207, "step": 455010 }, { "epoch": 2.704733372565104, "grad_norm": 4.357193470001221, "learning_rate": 5.1580100666128e-06, "loss": 0.1196, "step": 455020 }, { "epoch": 2.704792814641772, "grad_norm": 3.982503890991211, "learning_rate": 5.157802677985096e-06, "loss": 0.1175, "step": 455030 }, { "epoch": 2.704852256718441, "grad_norm": 4.767180442810059, "learning_rate": 5.157595289085638e-06, "loss": 0.1216, "step": 455040 }, { "epoch": 2.704911698795109, "grad_norm": 4.232142925262451, "learning_rate": 5.1573878999147805e-06, "loss": 0.1344, "step": 455050 }, { "epoch": 2.7049711408717774, "grad_norm": 3.9074714183807373, "learning_rate": 5.1571805104728834e-06, "loss": 0.1103, "step": 455060 }, { "epoch": 2.705030582948446, "grad_norm": 3.799455404281616, "learning_rate": 5.156973120760303e-06, "loss": 0.1058, "step": 455070 }, { "epoch": 2.705090025025114, "grad_norm": 3.48417592048645, "learning_rate": 5.156765730777395e-06, "loss": 0.1163, "step": 455080 }, { "epoch": 2.7051494671017826, "grad_norm": 3.4388275146484375, "learning_rate": 5.156558340524519e-06, "loss": 0.1157, "step": 455090 }, { "epoch": 2.705208909178451, "grad_norm": 3.889949321746826, "learning_rate": 5.156350950002032e-06, "loss": 0.1304, "step": 455100 }, { "epoch": 2.7052683512551194, "grad_norm": 3.0911903381347656, "learning_rate": 5.156143559210287e-06, "loss": 0.1184, "step": 455110 }, { "epoch": 2.705327793331788, "grad_norm": 4.090884685516357, "learning_rate": 5.1559361681496444e-06, "loss": 0.1185, "step": 455120 }, { "epoch": 2.7053872354084563, "grad_norm": 3.5708200931549072, "learning_rate": 5.155728776820462e-06, "loss": 0.1253, "step": 455130 }, { "epoch": 2.7054466774851247, "grad_norm": 3.679429531097412, "learning_rate": 5.1555213852230975e-06, "loss": 0.1136, "step": 455140 }, { "epoch": 2.705506119561793, "grad_norm": 2.8817808628082275, "learning_rate": 5.155313993357904e-06, "loss": 0.1182, "step": 455150 }, { "epoch": 2.7055655616384615, "grad_norm": 5.400149345397949, "learning_rate": 5.1551066012252435e-06, "loss": 0.1197, "step": 455160 }, { "epoch": 2.70562500371513, "grad_norm": 3.2379813194274902, "learning_rate": 5.15489920882547e-06, "loss": 0.1133, "step": 455170 }, { "epoch": 2.7056844457917983, "grad_norm": 4.822900295257568, "learning_rate": 5.1546918161589406e-06, "loss": 0.1193, "step": 455180 }, { "epoch": 2.7057438878684668, "grad_norm": 4.529621601104736, "learning_rate": 5.154484423226016e-06, "loss": 0.1223, "step": 455190 }, { "epoch": 2.7058033299451347, "grad_norm": 3.7090182304382324, "learning_rate": 5.15427703002705e-06, "loss": 0.1387, "step": 455200 }, { "epoch": 2.7058627720218036, "grad_norm": 3.5742719173431396, "learning_rate": 5.154069636562398e-06, "loss": 0.1235, "step": 455210 }, { "epoch": 2.7059222140984716, "grad_norm": 5.68756103515625, "learning_rate": 5.153862242832422e-06, "loss": 0.1074, "step": 455220 }, { "epoch": 2.70598165617514, "grad_norm": 3.1867353916168213, "learning_rate": 5.153654848837476e-06, "loss": 0.1267, "step": 455230 }, { "epoch": 2.7060410982518084, "grad_norm": 4.176956653594971, "learning_rate": 5.153447454577919e-06, "loss": 0.1169, "step": 455240 }, { "epoch": 2.706100540328477, "grad_norm": 5.228001594543457, "learning_rate": 5.153240060054105e-06, "loss": 0.1306, "step": 455250 }, { "epoch": 2.706159982405145, "grad_norm": 3.9231884479522705, "learning_rate": 5.153032665266397e-06, "loss": 0.101, "step": 455260 }, { "epoch": 2.7062194244818136, "grad_norm": 3.3647844791412354, "learning_rate": 5.152825270215146e-06, "loss": 0.1124, "step": 455270 }, { "epoch": 2.706278866558482, "grad_norm": 3.7642147541046143, "learning_rate": 5.152617874900712e-06, "loss": 0.1129, "step": 455280 }, { "epoch": 2.7063383086351505, "grad_norm": 4.259006977081299, "learning_rate": 5.152410479323452e-06, "loss": 0.1195, "step": 455290 }, { "epoch": 2.706397750711819, "grad_norm": 3.2486140727996826, "learning_rate": 5.152203083483723e-06, "loss": 0.1187, "step": 455300 }, { "epoch": 2.7064571927884873, "grad_norm": 5.438483715057373, "learning_rate": 5.151995687381881e-06, "loss": 0.1316, "step": 455310 }, { "epoch": 2.7065166348651557, "grad_norm": 4.004903793334961, "learning_rate": 5.151788291018286e-06, "loss": 0.1157, "step": 455320 }, { "epoch": 2.706576076941824, "grad_norm": 4.115816593170166, "learning_rate": 5.151580894393293e-06, "loss": 0.1179, "step": 455330 }, { "epoch": 2.7066355190184925, "grad_norm": 3.817232370376587, "learning_rate": 5.151373497507257e-06, "loss": 0.124, "step": 455340 }, { "epoch": 2.706694961095161, "grad_norm": 3.4413363933563232, "learning_rate": 5.151166100360541e-06, "loss": 0.1298, "step": 455350 }, { "epoch": 2.7067544031718294, "grad_norm": 3.574578046798706, "learning_rate": 5.150958702953498e-06, "loss": 0.1063, "step": 455360 }, { "epoch": 2.7068138452484973, "grad_norm": 3.6289007663726807, "learning_rate": 5.150751305286486e-06, "loss": 0.1092, "step": 455370 }, { "epoch": 2.706873287325166, "grad_norm": 3.6294755935668945, "learning_rate": 5.150543907359863e-06, "loss": 0.1046, "step": 455380 }, { "epoch": 2.706932729401834, "grad_norm": 5.128561496734619, "learning_rate": 5.150336509173985e-06, "loss": 0.1083, "step": 455390 }, { "epoch": 2.706992171478503, "grad_norm": 3.4328653812408447, "learning_rate": 5.15012911072921e-06, "loss": 0.126, "step": 455400 }, { "epoch": 2.707051613555171, "grad_norm": 3.380439519882202, "learning_rate": 5.1499217120258925e-06, "loss": 0.1401, "step": 455410 }, { "epoch": 2.7071110556318394, "grad_norm": 2.8419573307037354, "learning_rate": 5.1497143130643946e-06, "loss": 0.1107, "step": 455420 }, { "epoch": 2.707170497708508, "grad_norm": 4.1365814208984375, "learning_rate": 5.149506913845071e-06, "loss": 0.1184, "step": 455430 }, { "epoch": 2.7072299397851762, "grad_norm": 4.3077778816223145, "learning_rate": 5.149299514368275e-06, "loss": 0.1231, "step": 455440 }, { "epoch": 2.7072893818618446, "grad_norm": 4.058459758758545, "learning_rate": 5.14909211463437e-06, "loss": 0.1205, "step": 455450 }, { "epoch": 2.707348823938513, "grad_norm": 3.868927001953125, "learning_rate": 5.1488847146437105e-06, "loss": 0.1152, "step": 455460 }, { "epoch": 2.7074082660151815, "grad_norm": 4.516361713409424, "learning_rate": 5.148677314396653e-06, "loss": 0.1449, "step": 455470 }, { "epoch": 2.70746770809185, "grad_norm": 5.324409008026123, "learning_rate": 5.148469913893557e-06, "loss": 0.1206, "step": 455480 }, { "epoch": 2.7075271501685183, "grad_norm": 2.997727870941162, "learning_rate": 5.1482625131347775e-06, "loss": 0.1204, "step": 455490 }, { "epoch": 2.7075865922451867, "grad_norm": 3.8542611598968506, "learning_rate": 5.148055112120671e-06, "loss": 0.1096, "step": 455500 }, { "epoch": 2.707646034321855, "grad_norm": 4.732856750488281, "learning_rate": 5.147847710851598e-06, "loss": 0.1245, "step": 455510 }, { "epoch": 2.7077054763985235, "grad_norm": 2.84976863861084, "learning_rate": 5.147640309327913e-06, "loss": 0.1159, "step": 455520 }, { "epoch": 2.707764918475192, "grad_norm": 2.8597934246063232, "learning_rate": 5.147432907549972e-06, "loss": 0.1053, "step": 455530 }, { "epoch": 2.7078243605518604, "grad_norm": 3.920407772064209, "learning_rate": 5.147225505518136e-06, "loss": 0.1239, "step": 455540 }, { "epoch": 2.707883802628529, "grad_norm": 4.146851539611816, "learning_rate": 5.14701810323276e-06, "loss": 0.1153, "step": 455550 }, { "epoch": 2.7079432447051968, "grad_norm": 4.370916366577148, "learning_rate": 5.146810700694199e-06, "loss": 0.1093, "step": 455560 }, { "epoch": 2.7080026867818656, "grad_norm": 3.787710189819336, "learning_rate": 5.146603297902814e-06, "loss": 0.1087, "step": 455570 }, { "epoch": 2.7080621288585336, "grad_norm": 4.457096099853516, "learning_rate": 5.146395894858961e-06, "loss": 0.1125, "step": 455580 }, { "epoch": 2.7081215709352024, "grad_norm": 4.18076229095459, "learning_rate": 5.146188491562996e-06, "loss": 0.1232, "step": 455590 }, { "epoch": 2.7081810130118704, "grad_norm": 3.821913003921509, "learning_rate": 5.1459810880152775e-06, "loss": 0.1172, "step": 455600 }, { "epoch": 2.708240455088539, "grad_norm": 3.8933112621307373, "learning_rate": 5.145773684216163e-06, "loss": 0.1153, "step": 455610 }, { "epoch": 2.7082998971652072, "grad_norm": 3.223264694213867, "learning_rate": 5.1455662801660074e-06, "loss": 0.1211, "step": 455620 }, { "epoch": 2.7083593392418757, "grad_norm": 4.304360389709473, "learning_rate": 5.1453588758651695e-06, "loss": 0.132, "step": 455630 }, { "epoch": 2.708418781318544, "grad_norm": 3.689882278442383, "learning_rate": 5.145151471314007e-06, "loss": 0.1175, "step": 455640 }, { "epoch": 2.7084782233952125, "grad_norm": 3.5149192810058594, "learning_rate": 5.144944066512877e-06, "loss": 0.1, "step": 455650 }, { "epoch": 2.708537665471881, "grad_norm": 5.4357008934021, "learning_rate": 5.144736661462134e-06, "loss": 0.1175, "step": 455660 }, { "epoch": 2.7085971075485493, "grad_norm": 2.7435481548309326, "learning_rate": 5.144529256162137e-06, "loss": 0.1299, "step": 455670 }, { "epoch": 2.7086565496252177, "grad_norm": 3.523010015487671, "learning_rate": 5.144321850613245e-06, "loss": 0.122, "step": 455680 }, { "epoch": 2.708715991701886, "grad_norm": 5.111797332763672, "learning_rate": 5.144114444815815e-06, "loss": 0.1145, "step": 455690 }, { "epoch": 2.7087754337785546, "grad_norm": 4.1590375900268555, "learning_rate": 5.1439070387702e-06, "loss": 0.1394, "step": 455700 }, { "epoch": 2.708834875855223, "grad_norm": 3.48691463470459, "learning_rate": 5.143699632476761e-06, "loss": 0.1047, "step": 455710 }, { "epoch": 2.7088943179318914, "grad_norm": 3.3327996730804443, "learning_rate": 5.143492225935854e-06, "loss": 0.124, "step": 455720 }, { "epoch": 2.70895376000856, "grad_norm": 4.774662494659424, "learning_rate": 5.143284819147836e-06, "loss": 0.105, "step": 455730 }, { "epoch": 2.7090132020852282, "grad_norm": 2.4078662395477295, "learning_rate": 5.143077412113064e-06, "loss": 0.1104, "step": 455740 }, { "epoch": 2.709072644161896, "grad_norm": 2.7521281242370605, "learning_rate": 5.142870004831897e-06, "loss": 0.1088, "step": 455750 }, { "epoch": 2.709132086238565, "grad_norm": 3.473635196685791, "learning_rate": 5.142662597304689e-06, "loss": 0.1218, "step": 455760 }, { "epoch": 2.709191528315233, "grad_norm": 3.297300100326538, "learning_rate": 5.142455189531801e-06, "loss": 0.0998, "step": 455770 }, { "epoch": 2.709250970391902, "grad_norm": 2.8216681480407715, "learning_rate": 5.142247781513587e-06, "loss": 0.1177, "step": 455780 }, { "epoch": 2.70931041246857, "grad_norm": 4.207326412200928, "learning_rate": 5.142040373250404e-06, "loss": 0.1313, "step": 455790 }, { "epoch": 2.7093698545452383, "grad_norm": 3.088054656982422, "learning_rate": 5.141832964742613e-06, "loss": 0.0991, "step": 455800 }, { "epoch": 2.7094292966219067, "grad_norm": 2.9351987838745117, "learning_rate": 5.1416255559905674e-06, "loss": 0.1162, "step": 455810 }, { "epoch": 2.709488738698575, "grad_norm": 4.062375545501709, "learning_rate": 5.141418146994627e-06, "loss": 0.1183, "step": 455820 }, { "epoch": 2.7095481807752435, "grad_norm": 4.434260368347168, "learning_rate": 5.1412107377551454e-06, "loss": 0.1206, "step": 455830 }, { "epoch": 2.709607622851912, "grad_norm": 3.9091265201568604, "learning_rate": 5.1410033282724835e-06, "loss": 0.1142, "step": 455840 }, { "epoch": 2.7096670649285803, "grad_norm": 3.114976644515991, "learning_rate": 5.140795918546998e-06, "loss": 0.1242, "step": 455850 }, { "epoch": 2.7097265070052488, "grad_norm": 4.127509593963623, "learning_rate": 5.140588508579043e-06, "loss": 0.1292, "step": 455860 }, { "epoch": 2.709785949081917, "grad_norm": 4.512609004974365, "learning_rate": 5.140381098368979e-06, "loss": 0.1295, "step": 455870 }, { "epoch": 2.7098453911585856, "grad_norm": 3.5590431690216064, "learning_rate": 5.1401736879171625e-06, "loss": 0.1131, "step": 455880 }, { "epoch": 2.709904833235254, "grad_norm": 3.3712685108184814, "learning_rate": 5.139966277223949e-06, "loss": 0.1144, "step": 455890 }, { "epoch": 2.7099642753119224, "grad_norm": 4.834076404571533, "learning_rate": 5.139758866289697e-06, "loss": 0.1174, "step": 455900 }, { "epoch": 2.710023717388591, "grad_norm": 4.834557056427002, "learning_rate": 5.139551455114764e-06, "loss": 0.1228, "step": 455910 }, { "epoch": 2.7100831594652592, "grad_norm": 4.709612846374512, "learning_rate": 5.139344043699507e-06, "loss": 0.1209, "step": 455920 }, { "epoch": 2.7101426015419277, "grad_norm": 4.554192543029785, "learning_rate": 5.1391366320442816e-06, "loss": 0.1222, "step": 455930 }, { "epoch": 2.7102020436185956, "grad_norm": 4.645953178405762, "learning_rate": 5.138929220149448e-06, "loss": 0.1082, "step": 455940 }, { "epoch": 2.7102614856952645, "grad_norm": 4.744140625, "learning_rate": 5.138721808015361e-06, "loss": 0.1385, "step": 455950 }, { "epoch": 2.7103209277719325, "grad_norm": 3.5303964614868164, "learning_rate": 5.138514395642378e-06, "loss": 0.1465, "step": 455960 }, { "epoch": 2.710380369848601, "grad_norm": 5.4338884353637695, "learning_rate": 5.1383069830308574e-06, "loss": 0.137, "step": 455970 }, { "epoch": 2.7104398119252693, "grad_norm": 4.647114276885986, "learning_rate": 5.1380995701811565e-06, "loss": 0.1191, "step": 455980 }, { "epoch": 2.7104992540019377, "grad_norm": 4.4435648918151855, "learning_rate": 5.13789215709363e-06, "loss": 0.146, "step": 455990 }, { "epoch": 2.710558696078606, "grad_norm": 3.8799548149108887, "learning_rate": 5.137684743768636e-06, "loss": 0.1059, "step": 456000 }, { "epoch": 2.7106181381552745, "grad_norm": 6.720865249633789, "learning_rate": 5.137477330206535e-06, "loss": 0.1329, "step": 456010 }, { "epoch": 2.710677580231943, "grad_norm": 4.514856815338135, "learning_rate": 5.13726991640768e-06, "loss": 0.111, "step": 456020 }, { "epoch": 2.7107370223086114, "grad_norm": 4.1428914070129395, "learning_rate": 5.137062502372431e-06, "loss": 0.1143, "step": 456030 }, { "epoch": 2.7107964643852798, "grad_norm": 4.942325592041016, "learning_rate": 5.136855088101144e-06, "loss": 0.137, "step": 456040 }, { "epoch": 2.710855906461948, "grad_norm": 5.1079583168029785, "learning_rate": 5.136647673594175e-06, "loss": 0.1102, "step": 456050 }, { "epoch": 2.7109153485386166, "grad_norm": 3.1363322734832764, "learning_rate": 5.136440258851883e-06, "loss": 0.1219, "step": 456060 }, { "epoch": 2.710974790615285, "grad_norm": 4.7184882164001465, "learning_rate": 5.136232843874625e-06, "loss": 0.1111, "step": 456070 }, { "epoch": 2.7110342326919534, "grad_norm": 4.53878116607666, "learning_rate": 5.1360254286627575e-06, "loss": 0.1422, "step": 456080 }, { "epoch": 2.711093674768622, "grad_norm": 4.555832862854004, "learning_rate": 5.135818013216637e-06, "loss": 0.1235, "step": 456090 }, { "epoch": 2.7111531168452903, "grad_norm": 2.863321542739868, "learning_rate": 5.135610597536622e-06, "loss": 0.1116, "step": 456100 }, { "epoch": 2.7112125589219582, "grad_norm": 3.2363078594207764, "learning_rate": 5.13540318162307e-06, "loss": 0.1219, "step": 456110 }, { "epoch": 2.711272000998627, "grad_norm": 3.6301746368408203, "learning_rate": 5.135195765476336e-06, "loss": 0.1169, "step": 456120 }, { "epoch": 2.711331443075295, "grad_norm": 3.701292037963867, "learning_rate": 5.134988349096781e-06, "loss": 0.1237, "step": 456130 }, { "epoch": 2.711390885151964, "grad_norm": 3.685377597808838, "learning_rate": 5.13478093248476e-06, "loss": 0.1159, "step": 456140 }, { "epoch": 2.711450327228632, "grad_norm": 4.635526180267334, "learning_rate": 5.1345735156406285e-06, "loss": 0.1134, "step": 456150 }, { "epoch": 2.7115097693053003, "grad_norm": 4.147059917449951, "learning_rate": 5.134366098564746e-06, "loss": 0.1148, "step": 456160 }, { "epoch": 2.7115692113819687, "grad_norm": 4.387980937957764, "learning_rate": 5.1341586812574695e-06, "loss": 0.1062, "step": 456170 }, { "epoch": 2.711628653458637, "grad_norm": 4.126683712005615, "learning_rate": 5.133951263719155e-06, "loss": 0.1214, "step": 456180 }, { "epoch": 2.7116880955353055, "grad_norm": 3.5448362827301025, "learning_rate": 5.133743845950161e-06, "loss": 0.1082, "step": 456190 }, { "epoch": 2.711747537611974, "grad_norm": 4.108394145965576, "learning_rate": 5.133536427950845e-06, "loss": 0.1089, "step": 456200 }, { "epoch": 2.7118069796886424, "grad_norm": 4.409384727478027, "learning_rate": 5.133329009721561e-06, "loss": 0.1152, "step": 456210 }, { "epoch": 2.711866421765311, "grad_norm": 4.607983112335205, "learning_rate": 5.13312159126267e-06, "loss": 0.1186, "step": 456220 }, { "epoch": 2.711925863841979, "grad_norm": 3.5185165405273438, "learning_rate": 5.132914172574528e-06, "loss": 0.1025, "step": 456230 }, { "epoch": 2.7119853059186476, "grad_norm": 4.867253303527832, "learning_rate": 5.132706753657492e-06, "loss": 0.1168, "step": 456240 }, { "epoch": 2.712044747995316, "grad_norm": 5.248038291931152, "learning_rate": 5.132499334511918e-06, "loss": 0.1025, "step": 456250 }, { "epoch": 2.7121041900719844, "grad_norm": 4.798639297485352, "learning_rate": 5.132291915138166e-06, "loss": 0.1256, "step": 456260 }, { "epoch": 2.712163632148653, "grad_norm": 4.380397796630859, "learning_rate": 5.13208449553659e-06, "loss": 0.1433, "step": 456270 }, { "epoch": 2.7122230742253213, "grad_norm": 3.5912845134735107, "learning_rate": 5.1318770757075485e-06, "loss": 0.1136, "step": 456280 }, { "epoch": 2.7122825163019897, "grad_norm": 3.583940267562866, "learning_rate": 5.1316696556514e-06, "loss": 0.1078, "step": 456290 }, { "epoch": 2.7123419583786577, "grad_norm": 5.698383808135986, "learning_rate": 5.131462235368502e-06, "loss": 0.1313, "step": 456300 }, { "epoch": 2.7124014004553265, "grad_norm": 4.606791973114014, "learning_rate": 5.131254814859207e-06, "loss": 0.1191, "step": 456310 }, { "epoch": 2.7124608425319945, "grad_norm": 4.254667282104492, "learning_rate": 5.131047394123878e-06, "loss": 0.1295, "step": 456320 }, { "epoch": 2.7125202846086633, "grad_norm": 3.0813939571380615, "learning_rate": 5.130839973162868e-06, "loss": 0.1221, "step": 456330 }, { "epoch": 2.7125797266853313, "grad_norm": 3.7943334579467773, "learning_rate": 5.130632551976538e-06, "loss": 0.113, "step": 456340 }, { "epoch": 2.7126391687619997, "grad_norm": 4.255148410797119, "learning_rate": 5.130425130565241e-06, "loss": 0.1131, "step": 456350 }, { "epoch": 2.712698610838668, "grad_norm": 2.718618154525757, "learning_rate": 5.130217708929338e-06, "loss": 0.104, "step": 456360 }, { "epoch": 2.7127580529153366, "grad_norm": 5.462699890136719, "learning_rate": 5.1300102870691845e-06, "loss": 0.115, "step": 456370 }, { "epoch": 2.712817494992005, "grad_norm": 2.950345993041992, "learning_rate": 5.129802864985136e-06, "loss": 0.1208, "step": 456380 }, { "epoch": 2.7128769370686734, "grad_norm": 3.1085991859436035, "learning_rate": 5.129595442677554e-06, "loss": 0.1221, "step": 456390 }, { "epoch": 2.712936379145342, "grad_norm": 5.077539443969727, "learning_rate": 5.129388020146793e-06, "loss": 0.121, "step": 456400 }, { "epoch": 2.71299582122201, "grad_norm": 4.765899658203125, "learning_rate": 5.1291805973932086e-06, "loss": 0.1355, "step": 456410 }, { "epoch": 2.7130552632986786, "grad_norm": 4.77565860748291, "learning_rate": 5.12897317441716e-06, "loss": 0.1206, "step": 456420 }, { "epoch": 2.713114705375347, "grad_norm": 3.6726160049438477, "learning_rate": 5.128765751219006e-06, "loss": 0.11, "step": 456430 }, { "epoch": 2.7131741474520155, "grad_norm": 4.570242404937744, "learning_rate": 5.1285583277991e-06, "loss": 0.1411, "step": 456440 }, { "epoch": 2.713233589528684, "grad_norm": 5.546513557434082, "learning_rate": 5.128350904157802e-06, "loss": 0.1159, "step": 456450 }, { "epoch": 2.7132930316053523, "grad_norm": 3.050896167755127, "learning_rate": 5.128143480295467e-06, "loss": 0.1154, "step": 456460 }, { "epoch": 2.7133524736820207, "grad_norm": 3.0817713737487793, "learning_rate": 5.127936056212457e-06, "loss": 0.1263, "step": 456470 }, { "epoch": 2.713411915758689, "grad_norm": 4.319793701171875, "learning_rate": 5.127728631909122e-06, "loss": 0.1229, "step": 456480 }, { "epoch": 2.713471357835357, "grad_norm": 5.61590576171875, "learning_rate": 5.127521207385826e-06, "loss": 0.1095, "step": 456490 }, { "epoch": 2.713530799912026, "grad_norm": 3.8509488105773926, "learning_rate": 5.127313782642923e-06, "loss": 0.1095, "step": 456500 }, { "epoch": 2.713590241988694, "grad_norm": 4.380726337432861, "learning_rate": 5.1271063576807685e-06, "loss": 0.1167, "step": 456510 }, { "epoch": 2.7136496840653628, "grad_norm": 4.786896705627441, "learning_rate": 5.126898932499724e-06, "loss": 0.1117, "step": 456520 }, { "epoch": 2.7137091261420307, "grad_norm": 4.6431498527526855, "learning_rate": 5.126691507100143e-06, "loss": 0.1219, "step": 456530 }, { "epoch": 2.713768568218699, "grad_norm": 3.9406588077545166, "learning_rate": 5.1264840814823845e-06, "loss": 0.1026, "step": 456540 }, { "epoch": 2.7138280102953676, "grad_norm": 4.645840644836426, "learning_rate": 5.126276655646805e-06, "loss": 0.1326, "step": 456550 }, { "epoch": 2.713887452372036, "grad_norm": 5.423563480377197, "learning_rate": 5.126069229593762e-06, "loss": 0.1224, "step": 456560 }, { "epoch": 2.7139468944487044, "grad_norm": 4.142381191253662, "learning_rate": 5.125861803323614e-06, "loss": 0.1077, "step": 456570 }, { "epoch": 2.714006336525373, "grad_norm": 3.775517702102661, "learning_rate": 5.125654376836715e-06, "loss": 0.1221, "step": 456580 }, { "epoch": 2.7140657786020412, "grad_norm": 4.91169548034668, "learning_rate": 5.125446950133426e-06, "loss": 0.1347, "step": 456590 }, { "epoch": 2.7141252206787096, "grad_norm": 4.2074666023254395, "learning_rate": 5.125239523214102e-06, "loss": 0.1299, "step": 456600 }, { "epoch": 2.714184662755378, "grad_norm": 2.8266661167144775, "learning_rate": 5.125032096079099e-06, "loss": 0.1159, "step": 456610 }, { "epoch": 2.7142441048320465, "grad_norm": 4.130618572235107, "learning_rate": 5.1248246687287776e-06, "loss": 0.1266, "step": 456620 }, { "epoch": 2.714303546908715, "grad_norm": 4.647802352905273, "learning_rate": 5.124617241163492e-06, "loss": 0.124, "step": 456630 }, { "epoch": 2.7143629889853833, "grad_norm": 4.517677307128906, "learning_rate": 5.1244098133836e-06, "loss": 0.1264, "step": 456640 }, { "epoch": 2.7144224310620517, "grad_norm": 3.2958521842956543, "learning_rate": 5.124202385389462e-06, "loss": 0.1169, "step": 456650 }, { "epoch": 2.71448187313872, "grad_norm": 3.2792162895202637, "learning_rate": 5.123994957181431e-06, "loss": 0.1224, "step": 456660 }, { "epoch": 2.7145413152153886, "grad_norm": 3.6089327335357666, "learning_rate": 5.123787528759865e-06, "loss": 0.1115, "step": 456670 }, { "epoch": 2.7146007572920565, "grad_norm": 3.6248908042907715, "learning_rate": 5.123580100125124e-06, "loss": 0.1178, "step": 456680 }, { "epoch": 2.7146601993687254, "grad_norm": 4.012885093688965, "learning_rate": 5.123372671277563e-06, "loss": 0.1208, "step": 456690 }, { "epoch": 2.7147196414453933, "grad_norm": 4.658036708831787, "learning_rate": 5.1231652422175395e-06, "loss": 0.1193, "step": 456700 }, { "epoch": 2.7147790835220618, "grad_norm": 5.393016815185547, "learning_rate": 5.1229578129454105e-06, "loss": 0.1226, "step": 456710 }, { "epoch": 2.71483852559873, "grad_norm": 3.5071489810943604, "learning_rate": 5.1227503834615334e-06, "loss": 0.1192, "step": 456720 }, { "epoch": 2.7148979676753986, "grad_norm": 3.368311643600464, "learning_rate": 5.122542953766267e-06, "loss": 0.1182, "step": 456730 }, { "epoch": 2.714957409752067, "grad_norm": 3.675311803817749, "learning_rate": 5.122335523859964e-06, "loss": 0.1251, "step": 456740 }, { "epoch": 2.7150168518287354, "grad_norm": 3.2303683757781982, "learning_rate": 5.122128093742987e-06, "loss": 0.1131, "step": 456750 }, { "epoch": 2.715076293905404, "grad_norm": 3.9994406700134277, "learning_rate": 5.12192066341569e-06, "loss": 0.1253, "step": 456760 }, { "epoch": 2.7151357359820723, "grad_norm": 3.3406925201416016, "learning_rate": 5.121713232878429e-06, "loss": 0.1255, "step": 456770 }, { "epoch": 2.7151951780587407, "grad_norm": 3.8308422565460205, "learning_rate": 5.121505802131566e-06, "loss": 0.1267, "step": 456780 }, { "epoch": 2.715254620135409, "grad_norm": 3.2950966358184814, "learning_rate": 5.121298371175455e-06, "loss": 0.0974, "step": 456790 }, { "epoch": 2.7153140622120775, "grad_norm": 3.1583001613616943, "learning_rate": 5.121090940010454e-06, "loss": 0.1272, "step": 456800 }, { "epoch": 2.715373504288746, "grad_norm": 4.090145111083984, "learning_rate": 5.120883508636919e-06, "loss": 0.1088, "step": 456810 }, { "epoch": 2.7154329463654143, "grad_norm": 3.2438087463378906, "learning_rate": 5.12067607705521e-06, "loss": 0.1208, "step": 456820 }, { "epoch": 2.7154923884420827, "grad_norm": 3.73321533203125, "learning_rate": 5.12046864526568e-06, "loss": 0.1036, "step": 456830 }, { "epoch": 2.715551830518751, "grad_norm": 5.310997009277344, "learning_rate": 5.1202612132686904e-06, "loss": 0.1188, "step": 456840 }, { "epoch": 2.715611272595419, "grad_norm": 3.2557451725006104, "learning_rate": 5.120053781064596e-06, "loss": 0.1161, "step": 456850 }, { "epoch": 2.715670714672088, "grad_norm": 4.78356409072876, "learning_rate": 5.119846348653754e-06, "loss": 0.13, "step": 456860 }, { "epoch": 2.715730156748756, "grad_norm": 3.379845142364502, "learning_rate": 5.1196389160365234e-06, "loss": 0.1177, "step": 456870 }, { "epoch": 2.715789598825425, "grad_norm": 4.040145397186279, "learning_rate": 5.11943148321326e-06, "loss": 0.1078, "step": 456880 }, { "epoch": 2.715849040902093, "grad_norm": 3.3018486499786377, "learning_rate": 5.11922405018432e-06, "loss": 0.116, "step": 456890 }, { "epoch": 2.715908482978761, "grad_norm": 5.051611423492432, "learning_rate": 5.119016616950063e-06, "loss": 0.1411, "step": 456900 }, { "epoch": 2.7159679250554296, "grad_norm": 3.390211820602417, "learning_rate": 5.118809183510846e-06, "loss": 0.1192, "step": 456910 }, { "epoch": 2.716027367132098, "grad_norm": 3.622868061065674, "learning_rate": 5.1186017498670245e-06, "loss": 0.1099, "step": 456920 }, { "epoch": 2.7160868092087664, "grad_norm": 3.2277169227600098, "learning_rate": 5.1183943160189576e-06, "loss": 0.1198, "step": 456930 }, { "epoch": 2.716146251285435, "grad_norm": 4.449317455291748, "learning_rate": 5.118186881967001e-06, "loss": 0.1257, "step": 456940 }, { "epoch": 2.7162056933621033, "grad_norm": 4.48984956741333, "learning_rate": 5.117979447711513e-06, "loss": 0.127, "step": 456950 }, { "epoch": 2.7162651354387717, "grad_norm": 6.244026184082031, "learning_rate": 5.117772013252848e-06, "loss": 0.1131, "step": 456960 }, { "epoch": 2.71632457751544, "grad_norm": 3.8826818466186523, "learning_rate": 5.117564578591369e-06, "loss": 0.1114, "step": 456970 }, { "epoch": 2.7163840195921085, "grad_norm": 3.938516139984131, "learning_rate": 5.117357143727427e-06, "loss": 0.1048, "step": 456980 }, { "epoch": 2.716443461668777, "grad_norm": 4.412045478820801, "learning_rate": 5.117149708661383e-06, "loss": 0.1155, "step": 456990 }, { "epoch": 2.7165029037454453, "grad_norm": 5.562795162200928, "learning_rate": 5.116942273393593e-06, "loss": 0.1143, "step": 457000 }, { "epoch": 2.7165623458221138, "grad_norm": 3.485628128051758, "learning_rate": 5.116734837924414e-06, "loss": 0.1174, "step": 457010 }, { "epoch": 2.716621787898782, "grad_norm": 3.7405452728271484, "learning_rate": 5.116527402254206e-06, "loss": 0.1094, "step": 457020 }, { "epoch": 2.7166812299754506, "grad_norm": 3.8148813247680664, "learning_rate": 5.116319966383321e-06, "loss": 0.1094, "step": 457030 }, { "epoch": 2.7167406720521186, "grad_norm": 4.262434005737305, "learning_rate": 5.116112530312121e-06, "loss": 0.1106, "step": 457040 }, { "epoch": 2.7168001141287874, "grad_norm": 3.8602025508880615, "learning_rate": 5.1159050940409605e-06, "loss": 0.1223, "step": 457050 }, { "epoch": 2.7168595562054554, "grad_norm": 2.773984670639038, "learning_rate": 5.1156976575701975e-06, "loss": 0.115, "step": 457060 }, { "epoch": 2.7169189982821242, "grad_norm": 4.7555251121521, "learning_rate": 5.11549022090019e-06, "loss": 0.1261, "step": 457070 }, { "epoch": 2.716978440358792, "grad_norm": 4.831227779388428, "learning_rate": 5.115282784031295e-06, "loss": 0.1224, "step": 457080 }, { "epoch": 2.7170378824354606, "grad_norm": 4.062188148498535, "learning_rate": 5.115075346963867e-06, "loss": 0.1075, "step": 457090 }, { "epoch": 2.717097324512129, "grad_norm": 3.1440024375915527, "learning_rate": 5.114867909698266e-06, "loss": 0.1016, "step": 457100 }, { "epoch": 2.7171567665887975, "grad_norm": 4.6492486000061035, "learning_rate": 5.11466047223485e-06, "loss": 0.1165, "step": 457110 }, { "epoch": 2.717216208665466, "grad_norm": 4.2059221267700195, "learning_rate": 5.114453034573976e-06, "loss": 0.1219, "step": 457120 }, { "epoch": 2.7172756507421343, "grad_norm": 3.232837200164795, "learning_rate": 5.1142455967159985e-06, "loss": 0.1398, "step": 457130 }, { "epoch": 2.7173350928188027, "grad_norm": 3.835064172744751, "learning_rate": 5.114038158661277e-06, "loss": 0.1114, "step": 457140 }, { "epoch": 2.717394534895471, "grad_norm": 5.2658820152282715, "learning_rate": 5.113830720410169e-06, "loss": 0.1036, "step": 457150 }, { "epoch": 2.7174539769721395, "grad_norm": 4.303967475891113, "learning_rate": 5.1136232819630296e-06, "loss": 0.1192, "step": 457160 }, { "epoch": 2.717513419048808, "grad_norm": 4.816104888916016, "learning_rate": 5.1134158433202174e-06, "loss": 0.1284, "step": 457170 }, { "epoch": 2.7175728611254764, "grad_norm": 5.1166863441467285, "learning_rate": 5.1132084044820905e-06, "loss": 0.1128, "step": 457180 }, { "epoch": 2.7176323032021448, "grad_norm": 3.909573554992676, "learning_rate": 5.1130009654490046e-06, "loss": 0.1169, "step": 457190 }, { "epoch": 2.717691745278813, "grad_norm": 5.255630970001221, "learning_rate": 5.112793526221318e-06, "loss": 0.1229, "step": 457200 }, { "epoch": 2.7177511873554816, "grad_norm": 4.466607093811035, "learning_rate": 5.112586086799386e-06, "loss": 0.1162, "step": 457210 }, { "epoch": 2.71781062943215, "grad_norm": 4.8379669189453125, "learning_rate": 5.112378647183569e-06, "loss": 0.1209, "step": 457220 }, { "epoch": 2.717870071508818, "grad_norm": 4.855973243713379, "learning_rate": 5.112171207374221e-06, "loss": 0.1219, "step": 457230 }, { "epoch": 2.717929513585487, "grad_norm": 5.091036796569824, "learning_rate": 5.1119637673717025e-06, "loss": 0.1192, "step": 457240 }, { "epoch": 2.717988955662155, "grad_norm": 3.559582233428955, "learning_rate": 5.11175632717637e-06, "loss": 0.116, "step": 457250 }, { "epoch": 2.7180483977388237, "grad_norm": 3.4152145385742188, "learning_rate": 5.1115488867885764e-06, "loss": 0.112, "step": 457260 }, { "epoch": 2.7181078398154916, "grad_norm": 4.4676618576049805, "learning_rate": 5.111341446208684e-06, "loss": 0.1179, "step": 457270 }, { "epoch": 2.71816728189216, "grad_norm": 3.5453639030456543, "learning_rate": 5.111134005437049e-06, "loss": 0.1394, "step": 457280 }, { "epoch": 2.7182267239688285, "grad_norm": 4.655712127685547, "learning_rate": 5.110926564474027e-06, "loss": 0.1137, "step": 457290 }, { "epoch": 2.718286166045497, "grad_norm": 3.5668392181396484, "learning_rate": 5.110719123319977e-06, "loss": 0.1379, "step": 457300 }, { "epoch": 2.7183456081221653, "grad_norm": 5.220111846923828, "learning_rate": 5.110511681975255e-06, "loss": 0.1254, "step": 457310 }, { "epoch": 2.7184050501988337, "grad_norm": 3.065640687942505, "learning_rate": 5.110304240440217e-06, "loss": 0.1026, "step": 457320 }, { "epoch": 2.718464492275502, "grad_norm": 5.125761032104492, "learning_rate": 5.110096798715225e-06, "loss": 0.1273, "step": 457330 }, { "epoch": 2.7185239343521705, "grad_norm": 4.144298076629639, "learning_rate": 5.1098893568006315e-06, "loss": 0.1162, "step": 457340 }, { "epoch": 2.718583376428839, "grad_norm": 3.801009178161621, "learning_rate": 5.109681914696795e-06, "loss": 0.1069, "step": 457350 }, { "epoch": 2.7186428185055074, "grad_norm": 3.2222795486450195, "learning_rate": 5.109474472404074e-06, "loss": 0.1254, "step": 457360 }, { "epoch": 2.718702260582176, "grad_norm": 4.288032531738281, "learning_rate": 5.109267029922826e-06, "loss": 0.1489, "step": 457370 }, { "epoch": 2.718761702658844, "grad_norm": 3.4810352325439453, "learning_rate": 5.109059587253407e-06, "loss": 0.1131, "step": 457380 }, { "epoch": 2.7188211447355126, "grad_norm": 5.491683006286621, "learning_rate": 5.108852144396172e-06, "loss": 0.126, "step": 457390 }, { "epoch": 2.718880586812181, "grad_norm": 5.862843990325928, "learning_rate": 5.108644701351483e-06, "loss": 0.1217, "step": 457400 }, { "epoch": 2.7189400288888494, "grad_norm": 5.452915668487549, "learning_rate": 5.108437258119694e-06, "loss": 0.1222, "step": 457410 }, { "epoch": 2.7189994709655174, "grad_norm": 3.9671742916107178, "learning_rate": 5.1082298147011624e-06, "loss": 0.0983, "step": 457420 }, { "epoch": 2.7190589130421863, "grad_norm": 4.204132080078125, "learning_rate": 5.108022371096245e-06, "loss": 0.1082, "step": 457430 }, { "epoch": 2.7191183551188542, "grad_norm": 3.935878038406372, "learning_rate": 5.107814927305302e-06, "loss": 0.1172, "step": 457440 }, { "epoch": 2.7191777971955227, "grad_norm": 3.41252064704895, "learning_rate": 5.107607483328688e-06, "loss": 0.1163, "step": 457450 }, { "epoch": 2.719237239272191, "grad_norm": 3.6560585498809814, "learning_rate": 5.107400039166763e-06, "loss": 0.099, "step": 457460 }, { "epoch": 2.7192966813488595, "grad_norm": 4.420622825622559, "learning_rate": 5.1071925948198805e-06, "loss": 0.1257, "step": 457470 }, { "epoch": 2.719356123425528, "grad_norm": 4.0642409324646, "learning_rate": 5.1069851502884004e-06, "loss": 0.1253, "step": 457480 }, { "epoch": 2.7194155655021963, "grad_norm": 3.5225226879119873, "learning_rate": 5.10677770557268e-06, "loss": 0.1257, "step": 457490 }, { "epoch": 2.7194750075788647, "grad_norm": 3.7648823261260986, "learning_rate": 5.106570260673074e-06, "loss": 0.1142, "step": 457500 }, { "epoch": 2.719534449655533, "grad_norm": 3.4638962745666504, "learning_rate": 5.106362815589942e-06, "loss": 0.1308, "step": 457510 }, { "epoch": 2.7195938917322016, "grad_norm": 3.270639657974243, "learning_rate": 5.10615537032364e-06, "loss": 0.1146, "step": 457520 }, { "epoch": 2.71965333380887, "grad_norm": 5.384317874908447, "learning_rate": 5.105947924874527e-06, "loss": 0.1334, "step": 457530 }, { "epoch": 2.7197127758855384, "grad_norm": 4.926864147186279, "learning_rate": 5.105740479242956e-06, "loss": 0.1071, "step": 457540 }, { "epoch": 2.719772217962207, "grad_norm": 3.3188700675964355, "learning_rate": 5.105533033429289e-06, "loss": 0.123, "step": 457550 }, { "epoch": 2.719831660038875, "grad_norm": 3.3969016075134277, "learning_rate": 5.105325587433882e-06, "loss": 0.1215, "step": 457560 }, { "epoch": 2.7198911021155436, "grad_norm": 3.578442335128784, "learning_rate": 5.105118141257092e-06, "loss": 0.1028, "step": 457570 }, { "epoch": 2.719950544192212, "grad_norm": 3.178165912628174, "learning_rate": 5.104910694899276e-06, "loss": 0.1119, "step": 457580 }, { "epoch": 2.72000998626888, "grad_norm": 3.431605339050293, "learning_rate": 5.1047032483607915e-06, "loss": 0.1068, "step": 457590 }, { "epoch": 2.720069428345549, "grad_norm": 3.315396785736084, "learning_rate": 5.104495801641995e-06, "loss": 0.0985, "step": 457600 }, { "epoch": 2.720128870422217, "grad_norm": 3.6519505977630615, "learning_rate": 5.104288354743245e-06, "loss": 0.1196, "step": 457610 }, { "epoch": 2.7201883124988857, "grad_norm": 3.151970148086548, "learning_rate": 5.1040809076648966e-06, "loss": 0.1204, "step": 457620 }, { "epoch": 2.7202477545755537, "grad_norm": 4.601655006408691, "learning_rate": 5.1038734604073104e-06, "loss": 0.1096, "step": 457630 }, { "epoch": 2.720307196652222, "grad_norm": 6.12257719039917, "learning_rate": 5.103666012970839e-06, "loss": 0.1289, "step": 457640 }, { "epoch": 2.7203666387288905, "grad_norm": 2.7884459495544434, "learning_rate": 5.1034585653558435e-06, "loss": 0.1184, "step": 457650 }, { "epoch": 2.720426080805559, "grad_norm": 3.9590938091278076, "learning_rate": 5.103251117562681e-06, "loss": 0.1139, "step": 457660 }, { "epoch": 2.7204855228822273, "grad_norm": 3.914252758026123, "learning_rate": 5.103043669591708e-06, "loss": 0.1294, "step": 457670 }, { "epoch": 2.7205449649588958, "grad_norm": 3.9759042263031006, "learning_rate": 5.102836221443279e-06, "loss": 0.1165, "step": 457680 }, { "epoch": 2.720604407035564, "grad_norm": 4.837701797485352, "learning_rate": 5.102628773117756e-06, "loss": 0.1154, "step": 457690 }, { "epoch": 2.7206638491122326, "grad_norm": 4.1726555824279785, "learning_rate": 5.102421324615494e-06, "loss": 0.13, "step": 457700 }, { "epoch": 2.720723291188901, "grad_norm": 3.838905096054077, "learning_rate": 5.102213875936849e-06, "loss": 0.12, "step": 457710 }, { "epoch": 2.7207827332655694, "grad_norm": 3.972822427749634, "learning_rate": 5.10200642708218e-06, "loss": 0.1092, "step": 457720 }, { "epoch": 2.720842175342238, "grad_norm": 3.58164644241333, "learning_rate": 5.101798978051844e-06, "loss": 0.1067, "step": 457730 }, { "epoch": 2.7209016174189062, "grad_norm": 4.774955749511719, "learning_rate": 5.101591528846197e-06, "loss": 0.1512, "step": 457740 }, { "epoch": 2.7209610594955747, "grad_norm": 4.298837184906006, "learning_rate": 5.101384079465599e-06, "loss": 0.1201, "step": 457750 }, { "epoch": 2.721020501572243, "grad_norm": 4.00153923034668, "learning_rate": 5.101176629910404e-06, "loss": 0.1233, "step": 457760 }, { "epoch": 2.7210799436489115, "grad_norm": 5.654649257659912, "learning_rate": 5.100969180180972e-06, "loss": 0.1042, "step": 457770 }, { "epoch": 2.7211393857255795, "grad_norm": 4.362593650817871, "learning_rate": 5.100761730277658e-06, "loss": 0.136, "step": 457780 }, { "epoch": 2.7211988278022483, "grad_norm": 4.843892574310303, "learning_rate": 5.1005542802008214e-06, "loss": 0.1085, "step": 457790 }, { "epoch": 2.7212582698789163, "grad_norm": 3.6044669151306152, "learning_rate": 5.100346829950818e-06, "loss": 0.1017, "step": 457800 }, { "epoch": 2.721317711955585, "grad_norm": 3.900186061859131, "learning_rate": 5.100139379528004e-06, "loss": 0.1048, "step": 457810 }, { "epoch": 2.721377154032253, "grad_norm": 5.053856372833252, "learning_rate": 5.09993192893274e-06, "loss": 0.1072, "step": 457820 }, { "epoch": 2.7214365961089215, "grad_norm": 5.073493003845215, "learning_rate": 5.0997244781653795e-06, "loss": 0.1222, "step": 457830 }, { "epoch": 2.72149603818559, "grad_norm": 3.644744396209717, "learning_rate": 5.099517027226283e-06, "loss": 0.1163, "step": 457840 }, { "epoch": 2.7215554802622584, "grad_norm": 4.063322067260742, "learning_rate": 5.099309576115806e-06, "loss": 0.1092, "step": 457850 }, { "epoch": 2.7216149223389268, "grad_norm": 3.271448850631714, "learning_rate": 5.099102124834307e-06, "loss": 0.1109, "step": 457860 }, { "epoch": 2.721674364415595, "grad_norm": 4.455630302429199, "learning_rate": 5.09889467338214e-06, "loss": 0.1143, "step": 457870 }, { "epoch": 2.7217338064922636, "grad_norm": 4.300306797027588, "learning_rate": 5.098687221759664e-06, "loss": 0.1222, "step": 457880 }, { "epoch": 2.721793248568932, "grad_norm": 4.1392340660095215, "learning_rate": 5.09847976996724e-06, "loss": 0.12, "step": 457890 }, { "epoch": 2.7218526906456004, "grad_norm": 4.519568920135498, "learning_rate": 5.098272318005221e-06, "loss": 0.104, "step": 457900 }, { "epoch": 2.721912132722269, "grad_norm": 4.024969100952148, "learning_rate": 5.098064865873964e-06, "loss": 0.1136, "step": 457910 }, { "epoch": 2.7219715747989373, "grad_norm": 5.665897369384766, "learning_rate": 5.097857413573829e-06, "loss": 0.1172, "step": 457920 }, { "epoch": 2.7220310168756057, "grad_norm": 4.62051248550415, "learning_rate": 5.097649961105171e-06, "loss": 0.1065, "step": 457930 }, { "epoch": 2.722090458952274, "grad_norm": 3.217315673828125, "learning_rate": 5.097442508468348e-06, "loss": 0.1222, "step": 457940 }, { "epoch": 2.7221499010289425, "grad_norm": 5.6425323486328125, "learning_rate": 5.097235055663719e-06, "loss": 0.1112, "step": 457950 }, { "epoch": 2.722209343105611, "grad_norm": 3.988229274749756, "learning_rate": 5.0970276026916384e-06, "loss": 0.1154, "step": 457960 }, { "epoch": 2.722268785182279, "grad_norm": 3.4928929805755615, "learning_rate": 5.096820149552464e-06, "loss": 0.12, "step": 457970 }, { "epoch": 2.7223282272589477, "grad_norm": 4.162039756774902, "learning_rate": 5.096612696246554e-06, "loss": 0.1126, "step": 457980 }, { "epoch": 2.7223876693356157, "grad_norm": 4.7362895011901855, "learning_rate": 5.096405242774267e-06, "loss": 0.1063, "step": 457990 }, { "epoch": 2.7224471114122846, "grad_norm": 4.005856990814209, "learning_rate": 5.096197789135957e-06, "loss": 0.0918, "step": 458000 }, { "epoch": 2.7225065534889525, "grad_norm": 4.911333084106445, "learning_rate": 5.095990335331984e-06, "loss": 0.1192, "step": 458010 }, { "epoch": 2.722565995565621, "grad_norm": 2.6160168647766113, "learning_rate": 5.095782881362704e-06, "loss": 0.1061, "step": 458020 }, { "epoch": 2.7226254376422894, "grad_norm": 4.587850570678711, "learning_rate": 5.095575427228473e-06, "loss": 0.1261, "step": 458030 }, { "epoch": 2.722684879718958, "grad_norm": 3.9350337982177734, "learning_rate": 5.0953679729296515e-06, "loss": 0.1037, "step": 458040 }, { "epoch": 2.722744321795626, "grad_norm": 3.391573905944824, "learning_rate": 5.095160518466595e-06, "loss": 0.1139, "step": 458050 }, { "epoch": 2.7228037638722946, "grad_norm": 4.433874130249023, "learning_rate": 5.09495306383966e-06, "loss": 0.1157, "step": 458060 }, { "epoch": 2.722863205948963, "grad_norm": 4.343129634857178, "learning_rate": 5.0947456090492044e-06, "loss": 0.1245, "step": 458070 }, { "epoch": 2.7229226480256314, "grad_norm": 4.140032768249512, "learning_rate": 5.094538154095586e-06, "loss": 0.107, "step": 458080 }, { "epoch": 2.7229820901023, "grad_norm": 4.862587928771973, "learning_rate": 5.094330698979161e-06, "loss": 0.1089, "step": 458090 }, { "epoch": 2.7230415321789683, "grad_norm": 4.536683082580566, "learning_rate": 5.094123243700288e-06, "loss": 0.1131, "step": 458100 }, { "epoch": 2.7231009742556367, "grad_norm": 4.108248233795166, "learning_rate": 5.093915788259322e-06, "loss": 0.118, "step": 458110 }, { "epoch": 2.723160416332305, "grad_norm": 4.146661758422852, "learning_rate": 5.0937083326566235e-06, "loss": 0.1277, "step": 458120 }, { "epoch": 2.7232198584089735, "grad_norm": 3.4550724029541016, "learning_rate": 5.093500876892547e-06, "loss": 0.1241, "step": 458130 }, { "epoch": 2.723279300485642, "grad_norm": 6.057010173797607, "learning_rate": 5.0932934209674525e-06, "loss": 0.1431, "step": 458140 }, { "epoch": 2.7233387425623103, "grad_norm": 4.29095983505249, "learning_rate": 5.093085964881695e-06, "loss": 0.1132, "step": 458150 }, { "epoch": 2.7233981846389783, "grad_norm": 4.013911247253418, "learning_rate": 5.092878508635632e-06, "loss": 0.1117, "step": 458160 }, { "epoch": 2.723457626715647, "grad_norm": 3.4372823238372803, "learning_rate": 5.0926710522296205e-06, "loss": 0.1208, "step": 458170 }, { "epoch": 2.723517068792315, "grad_norm": 3.6021363735198975, "learning_rate": 5.09246359566402e-06, "loss": 0.1047, "step": 458180 }, { "epoch": 2.7235765108689836, "grad_norm": 3.538867473602295, "learning_rate": 5.0922561389391845e-06, "loss": 0.1208, "step": 458190 }, { "epoch": 2.723635952945652, "grad_norm": 4.968336582183838, "learning_rate": 5.092048682055473e-06, "loss": 0.1184, "step": 458200 }, { "epoch": 2.7236953950223204, "grad_norm": 4.4252166748046875, "learning_rate": 5.091841225013243e-06, "loss": 0.1144, "step": 458210 }, { "epoch": 2.723754837098989, "grad_norm": 5.435574054718018, "learning_rate": 5.091633767812852e-06, "loss": 0.1324, "step": 458220 }, { "epoch": 2.723814279175657, "grad_norm": 3.7872300148010254, "learning_rate": 5.091426310454656e-06, "loss": 0.1029, "step": 458230 }, { "epoch": 2.7238737212523256, "grad_norm": 3.931568145751953, "learning_rate": 5.091218852939014e-06, "loss": 0.1136, "step": 458240 }, { "epoch": 2.723933163328994, "grad_norm": 5.620070457458496, "learning_rate": 5.091011395266281e-06, "loss": 0.132, "step": 458250 }, { "epoch": 2.7239926054056625, "grad_norm": 3.6922380924224854, "learning_rate": 5.0908039374368155e-06, "loss": 0.1128, "step": 458260 }, { "epoch": 2.724052047482331, "grad_norm": 4.567165851593018, "learning_rate": 5.090596479450977e-06, "loss": 0.1138, "step": 458270 }, { "epoch": 2.7241114895589993, "grad_norm": 3.2913870811462402, "learning_rate": 5.090389021309119e-06, "loss": 0.1113, "step": 458280 }, { "epoch": 2.7241709316356677, "grad_norm": 3.325086832046509, "learning_rate": 5.090181563011599e-06, "loss": 0.1202, "step": 458290 }, { "epoch": 2.724230373712336, "grad_norm": 2.5773634910583496, "learning_rate": 5.089974104558777e-06, "loss": 0.1039, "step": 458300 }, { "epoch": 2.7242898157890045, "grad_norm": 3.6112003326416016, "learning_rate": 5.089766645951009e-06, "loss": 0.1121, "step": 458310 }, { "epoch": 2.724349257865673, "grad_norm": 5.5535383224487305, "learning_rate": 5.089559187188652e-06, "loss": 0.1199, "step": 458320 }, { "epoch": 2.724408699942341, "grad_norm": 3.025026559829712, "learning_rate": 5.089351728272062e-06, "loss": 0.1174, "step": 458330 }, { "epoch": 2.7244681420190098, "grad_norm": 4.323320388793945, "learning_rate": 5.0891442692015994e-06, "loss": 0.1104, "step": 458340 }, { "epoch": 2.7245275840956777, "grad_norm": 3.5633492469787598, "learning_rate": 5.08893680997762e-06, "loss": 0.1107, "step": 458350 }, { "epoch": 2.7245870261723466, "grad_norm": 3.5623862743377686, "learning_rate": 5.088729350600479e-06, "loss": 0.1103, "step": 458360 }, { "epoch": 2.7246464682490146, "grad_norm": 6.005043983459473, "learning_rate": 5.088521891070537e-06, "loss": 0.1296, "step": 458370 }, { "epoch": 2.724705910325683, "grad_norm": 4.06581974029541, "learning_rate": 5.088314431388149e-06, "loss": 0.1387, "step": 458380 }, { "epoch": 2.7247653524023514, "grad_norm": 5.539242744445801, "learning_rate": 5.088106971553674e-06, "loss": 0.1207, "step": 458390 }, { "epoch": 2.72482479447902, "grad_norm": 4.999311447143555, "learning_rate": 5.087899511567467e-06, "loss": 0.1223, "step": 458400 }, { "epoch": 2.7248842365556882, "grad_norm": 3.793668508529663, "learning_rate": 5.0876920514298875e-06, "loss": 0.1111, "step": 458410 }, { "epoch": 2.7249436786323566, "grad_norm": 3.9532310962677, "learning_rate": 5.087484591141291e-06, "loss": 0.1243, "step": 458420 }, { "epoch": 2.725003120709025, "grad_norm": 6.318201541900635, "learning_rate": 5.0872771307020355e-06, "loss": 0.123, "step": 458430 }, { "epoch": 2.7250625627856935, "grad_norm": 3.2187063694000244, "learning_rate": 5.087069670112479e-06, "loss": 0.1004, "step": 458440 }, { "epoch": 2.725122004862362, "grad_norm": 4.556601047515869, "learning_rate": 5.086862209372978e-06, "loss": 0.1187, "step": 458450 }, { "epoch": 2.7251814469390303, "grad_norm": 4.8406782150268555, "learning_rate": 5.086654748483889e-06, "loss": 0.1172, "step": 458460 }, { "epoch": 2.7252408890156987, "grad_norm": 4.042184352874756, "learning_rate": 5.086447287445572e-06, "loss": 0.1174, "step": 458470 }, { "epoch": 2.725300331092367, "grad_norm": 4.185391902923584, "learning_rate": 5.086239826258382e-06, "loss": 0.1136, "step": 458480 }, { "epoch": 2.7253597731690355, "grad_norm": 4.871909141540527, "learning_rate": 5.0860323649226766e-06, "loss": 0.1245, "step": 458490 }, { "epoch": 2.725419215245704, "grad_norm": 2.959845542907715, "learning_rate": 5.085824903438813e-06, "loss": 0.1033, "step": 458500 }, { "epoch": 2.7254786573223724, "grad_norm": 3.399444103240967, "learning_rate": 5.085617441807148e-06, "loss": 0.1023, "step": 458510 }, { "epoch": 2.7255380993990403, "grad_norm": 3.494870185852051, "learning_rate": 5.08540998002804e-06, "loss": 0.1097, "step": 458520 }, { "epoch": 2.725597541475709, "grad_norm": 4.340915203094482, "learning_rate": 5.085202518101845e-06, "loss": 0.1152, "step": 458530 }, { "epoch": 2.725656983552377, "grad_norm": 4.125479698181152, "learning_rate": 5.084995056028923e-06, "loss": 0.1169, "step": 458540 }, { "epoch": 2.725716425629046, "grad_norm": 3.3840136528015137, "learning_rate": 5.084787593809628e-06, "loss": 0.1072, "step": 458550 }, { "epoch": 2.725775867705714, "grad_norm": 4.514918327331543, "learning_rate": 5.084580131444319e-06, "loss": 0.1114, "step": 458560 }, { "epoch": 2.7258353097823824, "grad_norm": 3.451693296432495, "learning_rate": 5.084372668933353e-06, "loss": 0.098, "step": 458570 }, { "epoch": 2.725894751859051, "grad_norm": 4.946988582611084, "learning_rate": 5.084165206277087e-06, "loss": 0.1318, "step": 458580 }, { "epoch": 2.7259541939357192, "grad_norm": 3.2504451274871826, "learning_rate": 5.083957743475879e-06, "loss": 0.1278, "step": 458590 }, { "epoch": 2.7260136360123877, "grad_norm": 4.837338924407959, "learning_rate": 5.0837502805300855e-06, "loss": 0.1159, "step": 458600 }, { "epoch": 2.726073078089056, "grad_norm": 4.2791571617126465, "learning_rate": 5.0835428174400644e-06, "loss": 0.1174, "step": 458610 }, { "epoch": 2.7261325201657245, "grad_norm": 4.053732872009277, "learning_rate": 5.0833353542061714e-06, "loss": 0.0983, "step": 458620 }, { "epoch": 2.726191962242393, "grad_norm": 3.6972975730895996, "learning_rate": 5.0831278908287665e-06, "loss": 0.1248, "step": 458630 }, { "epoch": 2.7262514043190613, "grad_norm": 3.6909468173980713, "learning_rate": 5.082920427308204e-06, "loss": 0.1199, "step": 458640 }, { "epoch": 2.7263108463957297, "grad_norm": 4.276751518249512, "learning_rate": 5.082712963644842e-06, "loss": 0.1206, "step": 458650 }, { "epoch": 2.726370288472398, "grad_norm": 4.56895637512207, "learning_rate": 5.08250549983904e-06, "loss": 0.1147, "step": 458660 }, { "epoch": 2.7264297305490666, "grad_norm": 4.839570999145508, "learning_rate": 5.082298035891154e-06, "loss": 0.1091, "step": 458670 }, { "epoch": 2.726489172625735, "grad_norm": 4.3839616775512695, "learning_rate": 5.08209057180154e-06, "loss": 0.1092, "step": 458680 }, { "epoch": 2.7265486147024034, "grad_norm": 4.90289306640625, "learning_rate": 5.0818831075705565e-06, "loss": 0.1089, "step": 458690 }, { "epoch": 2.726608056779072, "grad_norm": 3.616183042526245, "learning_rate": 5.081675643198561e-06, "loss": 0.1256, "step": 458700 }, { "epoch": 2.72666749885574, "grad_norm": 3.4214718341827393, "learning_rate": 5.08146817868591e-06, "loss": 0.1082, "step": 458710 }, { "epoch": 2.7267269409324086, "grad_norm": 3.255646228790283, "learning_rate": 5.081260714032961e-06, "loss": 0.1052, "step": 458720 }, { "epoch": 2.7267863830090766, "grad_norm": 5.282569885253906, "learning_rate": 5.0810532492400725e-06, "loss": 0.1102, "step": 458730 }, { "epoch": 2.7268458250857455, "grad_norm": 4.189278602600098, "learning_rate": 5.080845784307599e-06, "loss": 0.1171, "step": 458740 }, { "epoch": 2.7269052671624134, "grad_norm": 6.259443759918213, "learning_rate": 5.080638319235898e-06, "loss": 0.1299, "step": 458750 }, { "epoch": 2.726964709239082, "grad_norm": 3.4992592334747314, "learning_rate": 5.080430854025331e-06, "loss": 0.1265, "step": 458760 }, { "epoch": 2.7270241513157503, "grad_norm": 3.9570376873016357, "learning_rate": 5.080223388676252e-06, "loss": 0.1124, "step": 458770 }, { "epoch": 2.7270835933924187, "grad_norm": 2.6047565937042236, "learning_rate": 5.080015923189017e-06, "loss": 0.12, "step": 458780 }, { "epoch": 2.727143035469087, "grad_norm": 3.9827487468719482, "learning_rate": 5.079808457563987e-06, "loss": 0.1134, "step": 458790 }, { "epoch": 2.7272024775457555, "grad_norm": 2.758782148361206, "learning_rate": 5.079600991801516e-06, "loss": 0.1068, "step": 458800 }, { "epoch": 2.727261919622424, "grad_norm": 5.922699928283691, "learning_rate": 5.079393525901963e-06, "loss": 0.1163, "step": 458810 }, { "epoch": 2.7273213616990923, "grad_norm": 3.0006680488586426, "learning_rate": 5.079186059865686e-06, "loss": 0.0968, "step": 458820 }, { "epoch": 2.7273808037757608, "grad_norm": 3.850116729736328, "learning_rate": 5.07897859369304e-06, "loss": 0.1018, "step": 458830 }, { "epoch": 2.727440245852429, "grad_norm": 3.554326295852661, "learning_rate": 5.078771127384383e-06, "loss": 0.1035, "step": 458840 }, { "epoch": 2.7274996879290976, "grad_norm": 3.3892786502838135, "learning_rate": 5.078563660940074e-06, "loss": 0.0944, "step": 458850 }, { "epoch": 2.727559130005766, "grad_norm": 3.322796106338501, "learning_rate": 5.078356194360469e-06, "loss": 0.092, "step": 458860 }, { "epoch": 2.7276185720824344, "grad_norm": 3.9514927864074707, "learning_rate": 5.0781487276459244e-06, "loss": 0.1248, "step": 458870 }, { "epoch": 2.727678014159103, "grad_norm": 3.306226968765259, "learning_rate": 5.077941260796798e-06, "loss": 0.1119, "step": 458880 }, { "epoch": 2.7277374562357712, "grad_norm": 4.002697944641113, "learning_rate": 5.077733793813449e-06, "loss": 0.105, "step": 458890 }, { "epoch": 2.727796898312439, "grad_norm": 4.960388660430908, "learning_rate": 5.077526326696232e-06, "loss": 0.1154, "step": 458900 }, { "epoch": 2.727856340389108, "grad_norm": 4.1331071853637695, "learning_rate": 5.077318859445505e-06, "loss": 0.1253, "step": 458910 }, { "epoch": 2.727915782465776, "grad_norm": 5.3571343421936035, "learning_rate": 5.077111392061627e-06, "loss": 0.1132, "step": 458920 }, { "epoch": 2.7279752245424445, "grad_norm": 4.0039591789245605, "learning_rate": 5.076903924544954e-06, "loss": 0.1084, "step": 458930 }, { "epoch": 2.728034666619113, "grad_norm": 3.577486515045166, "learning_rate": 5.076696456895842e-06, "loss": 0.1151, "step": 458940 }, { "epoch": 2.7280941086957813, "grad_norm": 4.465561866760254, "learning_rate": 5.07648898911465e-06, "loss": 0.1229, "step": 458950 }, { "epoch": 2.7281535507724497, "grad_norm": 4.293549060821533, "learning_rate": 5.0762815212017355e-06, "loss": 0.1106, "step": 458960 }, { "epoch": 2.728212992849118, "grad_norm": 3.9889631271362305, "learning_rate": 5.0760740531574535e-06, "loss": 0.12, "step": 458970 }, { "epoch": 2.7282724349257865, "grad_norm": 4.035892009735107, "learning_rate": 5.075866584982164e-06, "loss": 0.1098, "step": 458980 }, { "epoch": 2.728331877002455, "grad_norm": 3.864133596420288, "learning_rate": 5.0756591166762236e-06, "loss": 0.1068, "step": 458990 }, { "epoch": 2.7283913190791234, "grad_norm": 4.517780303955078, "learning_rate": 5.07545164823999e-06, "loss": 0.1138, "step": 459000 }, { "epoch": 2.7284507611557918, "grad_norm": 4.796818733215332, "learning_rate": 5.075244179673817e-06, "loss": 0.123, "step": 459010 }, { "epoch": 2.72851020323246, "grad_norm": 5.709944725036621, "learning_rate": 5.0750367109780665e-06, "loss": 0.1096, "step": 459020 }, { "epoch": 2.7285696453091286, "grad_norm": 4.7058796882629395, "learning_rate": 5.074829242153093e-06, "loss": 0.1094, "step": 459030 }, { "epoch": 2.728629087385797, "grad_norm": 3.6961472034454346, "learning_rate": 5.074621773199255e-06, "loss": 0.1117, "step": 459040 }, { "epoch": 2.7286885294624654, "grad_norm": 4.837869644165039, "learning_rate": 5.0744143041169095e-06, "loss": 0.1216, "step": 459050 }, { "epoch": 2.728747971539134, "grad_norm": 4.798515319824219, "learning_rate": 5.074206834906415e-06, "loss": 0.1328, "step": 459060 }, { "epoch": 2.728807413615802, "grad_norm": 4.120455741882324, "learning_rate": 5.073999365568124e-06, "loss": 0.1066, "step": 459070 }, { "epoch": 2.7288668556924707, "grad_norm": 4.068053245544434, "learning_rate": 5.073791896102399e-06, "loss": 0.1071, "step": 459080 }, { "epoch": 2.7289262977691386, "grad_norm": 3.96455979347229, "learning_rate": 5.073584426509595e-06, "loss": 0.1154, "step": 459090 }, { "epoch": 2.7289857398458075, "grad_norm": 4.209031105041504, "learning_rate": 5.073376956790073e-06, "loss": 0.1098, "step": 459100 }, { "epoch": 2.7290451819224755, "grad_norm": 4.354580879211426, "learning_rate": 5.073169486944183e-06, "loss": 0.1206, "step": 459110 }, { "epoch": 2.729104623999144, "grad_norm": 4.664546012878418, "learning_rate": 5.0729620169722895e-06, "loss": 0.1136, "step": 459120 }, { "epoch": 2.7291640660758123, "grad_norm": 3.6799216270446777, "learning_rate": 5.072754546874745e-06, "loss": 0.1102, "step": 459130 }, { "epoch": 2.7292235081524807, "grad_norm": 6.000127792358398, "learning_rate": 5.072547076651908e-06, "loss": 0.1258, "step": 459140 }, { "epoch": 2.729282950229149, "grad_norm": 3.672982931137085, "learning_rate": 5.072339606304138e-06, "loss": 0.106, "step": 459150 }, { "epoch": 2.7293423923058175, "grad_norm": 3.3932855129241943, "learning_rate": 5.07213213583179e-06, "loss": 0.1083, "step": 459160 }, { "epoch": 2.729401834382486, "grad_norm": 3.302267074584961, "learning_rate": 5.071924665235221e-06, "loss": 0.1244, "step": 459170 }, { "epoch": 2.7294612764591544, "grad_norm": 2.562257766723633, "learning_rate": 5.071717194514791e-06, "loss": 0.1012, "step": 459180 }, { "epoch": 2.729520718535823, "grad_norm": 5.671909809112549, "learning_rate": 5.071509723670852e-06, "loss": 0.1405, "step": 459190 }, { "epoch": 2.729580160612491, "grad_norm": 3.8752799034118652, "learning_rate": 5.071302252703768e-06, "loss": 0.1032, "step": 459200 }, { "epoch": 2.7296396026891596, "grad_norm": 4.485190391540527, "learning_rate": 5.071094781613891e-06, "loss": 0.1209, "step": 459210 }, { "epoch": 2.729699044765828, "grad_norm": 4.902957439422607, "learning_rate": 5.0708873104015825e-06, "loss": 0.1099, "step": 459220 }, { "epoch": 2.7297584868424964, "grad_norm": 2.90898060798645, "learning_rate": 5.070679839067197e-06, "loss": 0.1233, "step": 459230 }, { "epoch": 2.729817928919165, "grad_norm": 4.559716701507568, "learning_rate": 5.0704723676110905e-06, "loss": 0.1193, "step": 459240 }, { "epoch": 2.7298773709958333, "grad_norm": 4.821516990661621, "learning_rate": 5.070264896033623e-06, "loss": 0.1175, "step": 459250 }, { "epoch": 2.7299368130725012, "grad_norm": 3.3343710899353027, "learning_rate": 5.070057424335152e-06, "loss": 0.1148, "step": 459260 }, { "epoch": 2.72999625514917, "grad_norm": 3.7837181091308594, "learning_rate": 5.069849952516033e-06, "loss": 0.1237, "step": 459270 }, { "epoch": 2.730055697225838, "grad_norm": 3.65796160697937, "learning_rate": 5.069642480576624e-06, "loss": 0.1152, "step": 459280 }, { "epoch": 2.730115139302507, "grad_norm": 3.427673101425171, "learning_rate": 5.069435008517283e-06, "loss": 0.1105, "step": 459290 }, { "epoch": 2.730174581379175, "grad_norm": 5.2210307121276855, "learning_rate": 5.069227536338364e-06, "loss": 0.1067, "step": 459300 }, { "epoch": 2.7302340234558433, "grad_norm": 4.478734493255615, "learning_rate": 5.06902006404023e-06, "loss": 0.1157, "step": 459310 }, { "epoch": 2.7302934655325117, "grad_norm": 6.267200946807861, "learning_rate": 5.068812591623234e-06, "loss": 0.1319, "step": 459320 }, { "epoch": 2.73035290760918, "grad_norm": 5.083381652832031, "learning_rate": 5.068605119087734e-06, "loss": 0.1192, "step": 459330 }, { "epoch": 2.7304123496858486, "grad_norm": 5.478278160095215, "learning_rate": 5.068397646434089e-06, "loss": 0.119, "step": 459340 }, { "epoch": 2.730471791762517, "grad_norm": 4.270440101623535, "learning_rate": 5.068190173662655e-06, "loss": 0.1235, "step": 459350 }, { "epoch": 2.7305312338391854, "grad_norm": 3.416815996170044, "learning_rate": 5.067982700773788e-06, "loss": 0.116, "step": 459360 }, { "epoch": 2.730590675915854, "grad_norm": 4.088326454162598, "learning_rate": 5.067775227767848e-06, "loss": 0.1095, "step": 459370 }, { "epoch": 2.730650117992522, "grad_norm": 3.967745304107666, "learning_rate": 5.067567754645192e-06, "loss": 0.1247, "step": 459380 }, { "epoch": 2.7307095600691906, "grad_norm": 5.203996658325195, "learning_rate": 5.067360281406175e-06, "loss": 0.1302, "step": 459390 }, { "epoch": 2.730769002145859, "grad_norm": 4.4876933097839355, "learning_rate": 5.067152808051154e-06, "loss": 0.1199, "step": 459400 }, { "epoch": 2.7308284442225275, "grad_norm": 4.720282554626465, "learning_rate": 5.0669453345804895e-06, "loss": 0.1241, "step": 459410 }, { "epoch": 2.730887886299196, "grad_norm": 4.411057949066162, "learning_rate": 5.066737860994538e-06, "loss": 0.1387, "step": 459420 }, { "epoch": 2.7309473283758643, "grad_norm": 4.026258945465088, "learning_rate": 5.0665303872936535e-06, "loss": 0.111, "step": 459430 }, { "epoch": 2.7310067704525327, "grad_norm": 3.2471635341644287, "learning_rate": 5.066322913478198e-06, "loss": 0.1137, "step": 459440 }, { "epoch": 2.7310662125292007, "grad_norm": 5.261726379394531, "learning_rate": 5.066115439548525e-06, "loss": 0.1141, "step": 459450 }, { "epoch": 2.7311256546058695, "grad_norm": 3.18273663520813, "learning_rate": 5.0659079655049935e-06, "loss": 0.1166, "step": 459460 }, { "epoch": 2.7311850966825375, "grad_norm": 4.583232879638672, "learning_rate": 5.065700491347963e-06, "loss": 0.1146, "step": 459470 }, { "epoch": 2.7312445387592064, "grad_norm": 3.1889235973358154, "learning_rate": 5.065493017077786e-06, "loss": 0.1193, "step": 459480 }, { "epoch": 2.7313039808358743, "grad_norm": 4.370846748352051, "learning_rate": 5.065285542694822e-06, "loss": 0.1087, "step": 459490 }, { "epoch": 2.7313634229125427, "grad_norm": 3.6162445545196533, "learning_rate": 5.065078068199429e-06, "loss": 0.1119, "step": 459500 }, { "epoch": 2.731422864989211, "grad_norm": 3.8344368934631348, "learning_rate": 5.064870593591965e-06, "loss": 0.1046, "step": 459510 }, { "epoch": 2.7314823070658796, "grad_norm": 4.06081485748291, "learning_rate": 5.064663118872785e-06, "loss": 0.1165, "step": 459520 }, { "epoch": 2.731541749142548, "grad_norm": 4.134736061096191, "learning_rate": 5.064455644042247e-06, "loss": 0.1091, "step": 459530 }, { "epoch": 2.7316011912192164, "grad_norm": 5.113051414489746, "learning_rate": 5.064248169100709e-06, "loss": 0.1147, "step": 459540 }, { "epoch": 2.731660633295885, "grad_norm": 4.0886993408203125, "learning_rate": 5.064040694048529e-06, "loss": 0.1128, "step": 459550 }, { "epoch": 2.7317200753725532, "grad_norm": 3.052682399749756, "learning_rate": 5.063833218886061e-06, "loss": 0.1283, "step": 459560 }, { "epoch": 2.7317795174492217, "grad_norm": 5.0574517250061035, "learning_rate": 5.063625743613667e-06, "loss": 0.1255, "step": 459570 }, { "epoch": 2.73183895952589, "grad_norm": 3.294790744781494, "learning_rate": 5.063418268231701e-06, "loss": 0.114, "step": 459580 }, { "epoch": 2.7318984016025585, "grad_norm": 4.653475761413574, "learning_rate": 5.063210792740521e-06, "loss": 0.0961, "step": 459590 }, { "epoch": 2.731957843679227, "grad_norm": 3.6557042598724365, "learning_rate": 5.063003317140484e-06, "loss": 0.1173, "step": 459600 }, { "epoch": 2.7320172857558953, "grad_norm": 3.5085856914520264, "learning_rate": 5.06279584143195e-06, "loss": 0.1057, "step": 459610 }, { "epoch": 2.7320767278325637, "grad_norm": 3.7155585289001465, "learning_rate": 5.062588365615272e-06, "loss": 0.1111, "step": 459620 }, { "epoch": 2.732136169909232, "grad_norm": 2.579437255859375, "learning_rate": 5.062380889690809e-06, "loss": 0.106, "step": 459630 }, { "epoch": 2.7321956119859, "grad_norm": 3.050142765045166, "learning_rate": 5.062173413658919e-06, "loss": 0.1143, "step": 459640 }, { "epoch": 2.732255054062569, "grad_norm": 4.660475254058838, "learning_rate": 5.06196593751996e-06, "loss": 0.1291, "step": 459650 }, { "epoch": 2.732314496139237, "grad_norm": 4.741463661193848, "learning_rate": 5.0617584612742874e-06, "loss": 0.1231, "step": 459660 }, { "epoch": 2.7323739382159054, "grad_norm": 3.3687078952789307, "learning_rate": 5.06155098492226e-06, "loss": 0.109, "step": 459670 }, { "epoch": 2.7324333802925738, "grad_norm": 3.1743571758270264, "learning_rate": 5.061343508464235e-06, "loss": 0.105, "step": 459680 }, { "epoch": 2.732492822369242, "grad_norm": 4.112597465515137, "learning_rate": 5.061136031900568e-06, "loss": 0.1357, "step": 459690 }, { "epoch": 2.7325522644459106, "grad_norm": 4.178178787231445, "learning_rate": 5.060928555231618e-06, "loss": 0.1276, "step": 459700 }, { "epoch": 2.732611706522579, "grad_norm": 4.549190044403076, "learning_rate": 5.060721078457742e-06, "loss": 0.1315, "step": 459710 }, { "epoch": 2.7326711485992474, "grad_norm": 5.239747047424316, "learning_rate": 5.060513601579296e-06, "loss": 0.106, "step": 459720 }, { "epoch": 2.732730590675916, "grad_norm": 4.251439094543457, "learning_rate": 5.060306124596639e-06, "loss": 0.1042, "step": 459730 }, { "epoch": 2.7327900327525843, "grad_norm": 3.140671491622925, "learning_rate": 5.060098647510126e-06, "loss": 0.1238, "step": 459740 }, { "epoch": 2.7328494748292527, "grad_norm": 4.886757850646973, "learning_rate": 5.059891170320118e-06, "loss": 0.1219, "step": 459750 }, { "epoch": 2.732908916905921, "grad_norm": 3.8973171710968018, "learning_rate": 5.05968369302697e-06, "loss": 0.122, "step": 459760 }, { "epoch": 2.7329683589825895, "grad_norm": 4.045515537261963, "learning_rate": 5.05947621563104e-06, "loss": 0.1565, "step": 459770 }, { "epoch": 2.733027801059258, "grad_norm": 3.591895341873169, "learning_rate": 5.059268738132684e-06, "loss": 0.1121, "step": 459780 }, { "epoch": 2.7330872431359263, "grad_norm": 4.939784049987793, "learning_rate": 5.0590612605322595e-06, "loss": 0.1224, "step": 459790 }, { "epoch": 2.7331466852125947, "grad_norm": 5.746371746063232, "learning_rate": 5.058853782830126e-06, "loss": 0.1227, "step": 459800 }, { "epoch": 2.7332061272892627, "grad_norm": 4.034816265106201, "learning_rate": 5.058646305026639e-06, "loss": 0.1326, "step": 459810 }, { "epoch": 2.7332655693659316, "grad_norm": 3.5870521068573, "learning_rate": 5.058438827122155e-06, "loss": 0.1077, "step": 459820 }, { "epoch": 2.7333250114425995, "grad_norm": 2.9141199588775635, "learning_rate": 5.058231349117033e-06, "loss": 0.1237, "step": 459830 }, { "epoch": 2.7333844535192684, "grad_norm": 4.014186382293701, "learning_rate": 5.05802387101163e-06, "loss": 0.1051, "step": 459840 }, { "epoch": 2.7334438955959364, "grad_norm": 3.4204559326171875, "learning_rate": 5.057816392806303e-06, "loss": 0.1093, "step": 459850 }, { "epoch": 2.733503337672605, "grad_norm": 3.219768524169922, "learning_rate": 5.057608914501408e-06, "loss": 0.1226, "step": 459860 }, { "epoch": 2.733562779749273, "grad_norm": 5.290712356567383, "learning_rate": 5.057401436097304e-06, "loss": 0.1178, "step": 459870 }, { "epoch": 2.7336222218259416, "grad_norm": 4.157315731048584, "learning_rate": 5.05719395759435e-06, "loss": 0.1164, "step": 459880 }, { "epoch": 2.73368166390261, "grad_norm": 3.4141476154327393, "learning_rate": 5.056986478992899e-06, "loss": 0.1289, "step": 459890 }, { "epoch": 2.7337411059792784, "grad_norm": 4.976940155029297, "learning_rate": 5.056779000293311e-06, "loss": 0.1046, "step": 459900 }, { "epoch": 2.733800548055947, "grad_norm": 4.497786045074463, "learning_rate": 5.056571521495943e-06, "loss": 0.1033, "step": 459910 }, { "epoch": 2.7338599901326153, "grad_norm": 4.333045959472656, "learning_rate": 5.056364042601151e-06, "loss": 0.124, "step": 459920 }, { "epoch": 2.7339194322092837, "grad_norm": 3.7566161155700684, "learning_rate": 5.056156563609295e-06, "loss": 0.1146, "step": 459930 }, { "epoch": 2.733978874285952, "grad_norm": 3.984222888946533, "learning_rate": 5.05594908452073e-06, "loss": 0.1123, "step": 459940 }, { "epoch": 2.7340383163626205, "grad_norm": 3.7262606620788574, "learning_rate": 5.0557416053358144e-06, "loss": 0.1179, "step": 459950 }, { "epoch": 2.734097758439289, "grad_norm": 4.477441310882568, "learning_rate": 5.055534126054904e-06, "loss": 0.0988, "step": 459960 }, { "epoch": 2.7341572005159573, "grad_norm": 3.969531297683716, "learning_rate": 5.055326646678358e-06, "loss": 0.1192, "step": 459970 }, { "epoch": 2.7342166425926258, "grad_norm": 4.9372878074646, "learning_rate": 5.055119167206533e-06, "loss": 0.1188, "step": 459980 }, { "epoch": 2.734276084669294, "grad_norm": 3.6187100410461426, "learning_rate": 5.054911687639786e-06, "loss": 0.1105, "step": 459990 }, { "epoch": 2.734335526745962, "grad_norm": 4.105423450469971, "learning_rate": 5.0547042079784744e-06, "loss": 0.112, "step": 460000 }, { "epoch": 2.734394968822631, "grad_norm": 4.151620864868164, "learning_rate": 5.054496728222955e-06, "loss": 0.1243, "step": 460010 }, { "epoch": 2.734454410899299, "grad_norm": 4.056733131408691, "learning_rate": 5.054289248373587e-06, "loss": 0.1109, "step": 460020 }, { "epoch": 2.734513852975968, "grad_norm": 3.429478883743286, "learning_rate": 5.054081768430728e-06, "loss": 0.113, "step": 460030 }, { "epoch": 2.734573295052636, "grad_norm": 4.746133804321289, "learning_rate": 5.05387428839473e-06, "loss": 0.1126, "step": 460040 }, { "epoch": 2.734632737129304, "grad_norm": 4.889364719390869, "learning_rate": 5.053666808265957e-06, "loss": 0.1196, "step": 460050 }, { "epoch": 2.7346921792059726, "grad_norm": 3.9610280990600586, "learning_rate": 5.053459328044762e-06, "loss": 0.1499, "step": 460060 }, { "epoch": 2.734751621282641, "grad_norm": 4.177193641662598, "learning_rate": 5.053251847731503e-06, "loss": 0.1211, "step": 460070 }, { "epoch": 2.7348110633593095, "grad_norm": 4.101357936859131, "learning_rate": 5.053044367326538e-06, "loss": 0.1035, "step": 460080 }, { "epoch": 2.734870505435978, "grad_norm": 3.2342655658721924, "learning_rate": 5.052836886830226e-06, "loss": 0.1228, "step": 460090 }, { "epoch": 2.7349299475126463, "grad_norm": 3.5885701179504395, "learning_rate": 5.052629406242921e-06, "loss": 0.1119, "step": 460100 }, { "epoch": 2.7349893895893147, "grad_norm": 3.7176547050476074, "learning_rate": 5.052421925564982e-06, "loss": 0.1165, "step": 460110 }, { "epoch": 2.735048831665983, "grad_norm": 3.3417861461639404, "learning_rate": 5.052214444796767e-06, "loss": 0.1091, "step": 460120 }, { "epoch": 2.7351082737426515, "grad_norm": 5.216740608215332, "learning_rate": 5.052006963938633e-06, "loss": 0.1249, "step": 460130 }, { "epoch": 2.73516771581932, "grad_norm": 4.382697582244873, "learning_rate": 5.0517994829909355e-06, "loss": 0.1038, "step": 460140 }, { "epoch": 2.7352271578959884, "grad_norm": 4.210909366607666, "learning_rate": 5.0515920019540345e-06, "loss": 0.1072, "step": 460150 }, { "epoch": 2.7352865999726568, "grad_norm": 4.603285312652588, "learning_rate": 5.051384520828285e-06, "loss": 0.1187, "step": 460160 }, { "epoch": 2.735346042049325, "grad_norm": 3.665774345397949, "learning_rate": 5.051177039614045e-06, "loss": 0.1079, "step": 460170 }, { "epoch": 2.7354054841259936, "grad_norm": 6.611301898956299, "learning_rate": 5.050969558311671e-06, "loss": 0.1267, "step": 460180 }, { "epoch": 2.7354649262026616, "grad_norm": 3.6262686252593994, "learning_rate": 5.050762076921523e-06, "loss": 0.1154, "step": 460190 }, { "epoch": 2.7355243682793304, "grad_norm": 3.0810396671295166, "learning_rate": 5.050554595443956e-06, "loss": 0.1018, "step": 460200 }, { "epoch": 2.7355838103559984, "grad_norm": 3.3462393283843994, "learning_rate": 5.0503471138793285e-06, "loss": 0.1155, "step": 460210 }, { "epoch": 2.7356432524326673, "grad_norm": 4.564367771148682, "learning_rate": 5.0501396322279975e-06, "loss": 0.1232, "step": 460220 }, { "epoch": 2.7357026945093352, "grad_norm": 3.0631496906280518, "learning_rate": 5.04993215049032e-06, "loss": 0.1255, "step": 460230 }, { "epoch": 2.7357621365860036, "grad_norm": 2.7078943252563477, "learning_rate": 5.049724668666652e-06, "loss": 0.1075, "step": 460240 }, { "epoch": 2.735821578662672, "grad_norm": 3.7151591777801514, "learning_rate": 5.049517186757353e-06, "loss": 0.1068, "step": 460250 }, { "epoch": 2.7358810207393405, "grad_norm": 3.881649971008301, "learning_rate": 5.04930970476278e-06, "loss": 0.127, "step": 460260 }, { "epoch": 2.735940462816009, "grad_norm": 3.260444164276123, "learning_rate": 5.049102222683288e-06, "loss": 0.095, "step": 460270 }, { "epoch": 2.7359999048926773, "grad_norm": 3.8042280673980713, "learning_rate": 5.048894740519239e-06, "loss": 0.1156, "step": 460280 }, { "epoch": 2.7360593469693457, "grad_norm": 5.126985549926758, "learning_rate": 5.048687258270984e-06, "loss": 0.1132, "step": 460290 }, { "epoch": 2.736118789046014, "grad_norm": 3.9793121814727783, "learning_rate": 5.048479775938887e-06, "loss": 0.1151, "step": 460300 }, { "epoch": 2.7361782311226825, "grad_norm": 4.410221576690674, "learning_rate": 5.0482722935233e-06, "loss": 0.1329, "step": 460310 }, { "epoch": 2.736237673199351, "grad_norm": 3.911259889602661, "learning_rate": 5.048064811024583e-06, "loss": 0.121, "step": 460320 }, { "epoch": 2.7362971152760194, "grad_norm": 3.288700819015503, "learning_rate": 5.047857328443093e-06, "loss": 0.1272, "step": 460330 }, { "epoch": 2.736356557352688, "grad_norm": 4.454708576202393, "learning_rate": 5.0476498457791865e-06, "loss": 0.1263, "step": 460340 }, { "epoch": 2.736415999429356, "grad_norm": 5.3414387702941895, "learning_rate": 5.047442363033223e-06, "loss": 0.1285, "step": 460350 }, { "epoch": 2.7364754415060246, "grad_norm": 3.375563621520996, "learning_rate": 5.047234880205556e-06, "loss": 0.1102, "step": 460360 }, { "epoch": 2.736534883582693, "grad_norm": 3.1068050861358643, "learning_rate": 5.047027397296545e-06, "loss": 0.0993, "step": 460370 }, { "epoch": 2.736594325659361, "grad_norm": 3.85310435295105, "learning_rate": 5.046819914306548e-06, "loss": 0.1321, "step": 460380 }, { "epoch": 2.73665376773603, "grad_norm": 3.02770733833313, "learning_rate": 5.046612431235921e-06, "loss": 0.1095, "step": 460390 }, { "epoch": 2.736713209812698, "grad_norm": 4.490652561187744, "learning_rate": 5.046404948085022e-06, "loss": 0.1107, "step": 460400 }, { "epoch": 2.7367726518893662, "grad_norm": 3.812880039215088, "learning_rate": 5.0461974648542075e-06, "loss": 0.1094, "step": 460410 }, { "epoch": 2.7368320939660347, "grad_norm": 5.948380470275879, "learning_rate": 5.045989981543836e-06, "loss": 0.1088, "step": 460420 }, { "epoch": 2.736891536042703, "grad_norm": 4.627878665924072, "learning_rate": 5.045782498154266e-06, "loss": 0.1163, "step": 460430 }, { "epoch": 2.7369509781193715, "grad_norm": 4.569438457489014, "learning_rate": 5.045575014685849e-06, "loss": 0.1085, "step": 460440 }, { "epoch": 2.73701042019604, "grad_norm": 3.895460844039917, "learning_rate": 5.045367531138951e-06, "loss": 0.1281, "step": 460450 }, { "epoch": 2.7370698622727083, "grad_norm": 5.677988529205322, "learning_rate": 5.045160047513922e-06, "loss": 0.0929, "step": 460460 }, { "epoch": 2.7371293043493767, "grad_norm": 3.4227676391601562, "learning_rate": 5.044952563811122e-06, "loss": 0.1166, "step": 460470 }, { "epoch": 2.737188746426045, "grad_norm": 2.5804712772369385, "learning_rate": 5.044745080030909e-06, "loss": 0.1229, "step": 460480 }, { "epoch": 2.7372481885027136, "grad_norm": 3.191612482070923, "learning_rate": 5.04453759617364e-06, "loss": 0.104, "step": 460490 }, { "epoch": 2.737307630579382, "grad_norm": 4.420835971832275, "learning_rate": 5.0443301122396715e-06, "loss": 0.1193, "step": 460500 }, { "epoch": 2.7373670726560504, "grad_norm": 3.4205129146575928, "learning_rate": 5.04412262822936e-06, "loss": 0.1063, "step": 460510 }, { "epoch": 2.737426514732719, "grad_norm": 3.5452301502227783, "learning_rate": 5.0439151441430655e-06, "loss": 0.1237, "step": 460520 }, { "epoch": 2.737485956809387, "grad_norm": 3.060716152191162, "learning_rate": 5.043707659981144e-06, "loss": 0.1044, "step": 460530 }, { "epoch": 2.7375453988860556, "grad_norm": 4.654415607452393, "learning_rate": 5.043500175743952e-06, "loss": 0.1144, "step": 460540 }, { "epoch": 2.7376048409627236, "grad_norm": 3.5903122425079346, "learning_rate": 5.043292691431848e-06, "loss": 0.1248, "step": 460550 }, { "epoch": 2.7376642830393925, "grad_norm": 3.830703020095825, "learning_rate": 5.0430852070451895e-06, "loss": 0.1132, "step": 460560 }, { "epoch": 2.7377237251160604, "grad_norm": 4.849466800689697, "learning_rate": 5.0428777225843315e-06, "loss": 0.104, "step": 460570 }, { "epoch": 2.7377831671927293, "grad_norm": 4.672886848449707, "learning_rate": 5.042670238049634e-06, "loss": 0.1285, "step": 460580 }, { "epoch": 2.7378426092693973, "grad_norm": 5.051704406738281, "learning_rate": 5.0424627534414536e-06, "loss": 0.1171, "step": 460590 }, { "epoch": 2.7379020513460657, "grad_norm": 8.205439567565918, "learning_rate": 5.042255268760146e-06, "loss": 0.1252, "step": 460600 }, { "epoch": 2.737961493422734, "grad_norm": 3.948784589767456, "learning_rate": 5.042047784006071e-06, "loss": 0.1534, "step": 460610 }, { "epoch": 2.7380209354994025, "grad_norm": 5.494750499725342, "learning_rate": 5.041840299179583e-06, "loss": 0.1178, "step": 460620 }, { "epoch": 2.738080377576071, "grad_norm": 3.9105780124664307, "learning_rate": 5.041632814281042e-06, "loss": 0.1334, "step": 460630 }, { "epoch": 2.7381398196527393, "grad_norm": 3.7684271335601807, "learning_rate": 5.041425329310805e-06, "loss": 0.1369, "step": 460640 }, { "epoch": 2.7381992617294078, "grad_norm": 4.371000289916992, "learning_rate": 5.041217844269229e-06, "loss": 0.118, "step": 460650 }, { "epoch": 2.738258703806076, "grad_norm": 4.317868709564209, "learning_rate": 5.041010359156669e-06, "loss": 0.1093, "step": 460660 }, { "epoch": 2.7383181458827446, "grad_norm": 4.448643207550049, "learning_rate": 5.040802873973486e-06, "loss": 0.1182, "step": 460670 }, { "epoch": 2.738377587959413, "grad_norm": 3.760817527770996, "learning_rate": 5.040595388720035e-06, "loss": 0.1053, "step": 460680 }, { "epoch": 2.7384370300360814, "grad_norm": 5.014080047607422, "learning_rate": 5.040387903396673e-06, "loss": 0.1229, "step": 460690 }, { "epoch": 2.73849647211275, "grad_norm": 3.888660430908203, "learning_rate": 5.0401804180037595e-06, "loss": 0.1157, "step": 460700 }, { "epoch": 2.7385559141894182, "grad_norm": 4.095848560333252, "learning_rate": 5.039972932541651e-06, "loss": 0.1131, "step": 460710 }, { "epoch": 2.7386153562660867, "grad_norm": 4.977099418640137, "learning_rate": 5.039765447010704e-06, "loss": 0.1234, "step": 460720 }, { "epoch": 2.738674798342755, "grad_norm": 3.450702667236328, "learning_rate": 5.039557961411273e-06, "loss": 0.1026, "step": 460730 }, { "epoch": 2.738734240419423, "grad_norm": 4.576576232910156, "learning_rate": 5.039350475743722e-06, "loss": 0.1231, "step": 460740 }, { "epoch": 2.738793682496092, "grad_norm": 4.639109134674072, "learning_rate": 5.039142990008404e-06, "loss": 0.122, "step": 460750 }, { "epoch": 2.73885312457276, "grad_norm": 3.7389795780181885, "learning_rate": 5.038935504205677e-06, "loss": 0.1178, "step": 460760 }, { "epoch": 2.7389125666494287, "grad_norm": 2.7403903007507324, "learning_rate": 5.038728018335898e-06, "loss": 0.1036, "step": 460770 }, { "epoch": 2.7389720087260967, "grad_norm": 3.420600175857544, "learning_rate": 5.038520532399426e-06, "loss": 0.1121, "step": 460780 }, { "epoch": 2.739031450802765, "grad_norm": 6.027146816253662, "learning_rate": 5.038313046396615e-06, "loss": 0.1425, "step": 460790 }, { "epoch": 2.7390908928794335, "grad_norm": 3.9774155616760254, "learning_rate": 5.038105560327826e-06, "loss": 0.111, "step": 460800 }, { "epoch": 2.739150334956102, "grad_norm": 3.19205641746521, "learning_rate": 5.037898074193415e-06, "loss": 0.1104, "step": 460810 }, { "epoch": 2.7392097770327704, "grad_norm": 4.033547401428223, "learning_rate": 5.037690587993737e-06, "loss": 0.1128, "step": 460820 }, { "epoch": 2.7392692191094388, "grad_norm": 3.2230799198150635, "learning_rate": 5.037483101729154e-06, "loss": 0.1153, "step": 460830 }, { "epoch": 2.739328661186107, "grad_norm": 4.345091819763184, "learning_rate": 5.037275615400018e-06, "loss": 0.1169, "step": 460840 }, { "epoch": 2.7393881032627756, "grad_norm": 2.749990224838257, "learning_rate": 5.03706812900669e-06, "loss": 0.1198, "step": 460850 }, { "epoch": 2.739447545339444, "grad_norm": 3.664100170135498, "learning_rate": 5.0368606425495255e-06, "loss": 0.1141, "step": 460860 }, { "epoch": 2.7395069874161124, "grad_norm": 5.0579657554626465, "learning_rate": 5.036653156028884e-06, "loss": 0.1131, "step": 460870 }, { "epoch": 2.739566429492781, "grad_norm": 4.413315296173096, "learning_rate": 5.036445669445121e-06, "loss": 0.1119, "step": 460880 }, { "epoch": 2.7396258715694493, "grad_norm": 3.982745885848999, "learning_rate": 5.036238182798594e-06, "loss": 0.1213, "step": 460890 }, { "epoch": 2.7396853136461177, "grad_norm": 5.46834659576416, "learning_rate": 5.036030696089661e-06, "loss": 0.1297, "step": 460900 }, { "epoch": 2.739744755722786, "grad_norm": 3.6312332153320312, "learning_rate": 5.035823209318679e-06, "loss": 0.1065, "step": 460910 }, { "epoch": 2.7398041977994545, "grad_norm": 4.005208492279053, "learning_rate": 5.0356157224860036e-06, "loss": 0.1185, "step": 460920 }, { "epoch": 2.7398636398761225, "grad_norm": 6.801260948181152, "learning_rate": 5.035408235591994e-06, "loss": 0.1323, "step": 460930 }, { "epoch": 2.7399230819527913, "grad_norm": 3.181439161300659, "learning_rate": 5.035200748637009e-06, "loss": 0.1177, "step": 460940 }, { "epoch": 2.7399825240294593, "grad_norm": 5.321863651275635, "learning_rate": 5.034993261621401e-06, "loss": 0.1231, "step": 460950 }, { "epoch": 2.740041966106128, "grad_norm": 3.316931962966919, "learning_rate": 5.034785774545533e-06, "loss": 0.1118, "step": 460960 }, { "epoch": 2.740101408182796, "grad_norm": 3.8249146938323975, "learning_rate": 5.0345782874097595e-06, "loss": 0.1166, "step": 460970 }, { "epoch": 2.7401608502594645, "grad_norm": 2.751734733581543, "learning_rate": 5.034370800214438e-06, "loss": 0.1332, "step": 460980 }, { "epoch": 2.740220292336133, "grad_norm": 3.601304054260254, "learning_rate": 5.0341633129599246e-06, "loss": 0.1266, "step": 460990 }, { "epoch": 2.7402797344128014, "grad_norm": 3.3735721111297607, "learning_rate": 5.033955825646579e-06, "loss": 0.1123, "step": 461000 }, { "epoch": 2.74033917648947, "grad_norm": 3.4762449264526367, "learning_rate": 5.0337483382747576e-06, "loss": 0.1163, "step": 461010 }, { "epoch": 2.740398618566138, "grad_norm": 4.216538906097412, "learning_rate": 5.033540850844817e-06, "loss": 0.1065, "step": 461020 }, { "epoch": 2.7404580606428066, "grad_norm": 4.354730129241943, "learning_rate": 5.033333363357116e-06, "loss": 0.1308, "step": 461030 }, { "epoch": 2.740517502719475, "grad_norm": 4.098922252655029, "learning_rate": 5.033125875812009e-06, "loss": 0.1184, "step": 461040 }, { "epoch": 2.7405769447961434, "grad_norm": 3.4864957332611084, "learning_rate": 5.0329183882098566e-06, "loss": 0.0972, "step": 461050 }, { "epoch": 2.740636386872812, "grad_norm": 4.338537216186523, "learning_rate": 5.032710900551015e-06, "loss": 0.1196, "step": 461060 }, { "epoch": 2.7406958289494803, "grad_norm": 4.696691036224365, "learning_rate": 5.032503412835841e-06, "loss": 0.1246, "step": 461070 }, { "epoch": 2.7407552710261487, "grad_norm": 3.528902769088745, "learning_rate": 5.032295925064692e-06, "loss": 0.1036, "step": 461080 }, { "epoch": 2.740814713102817, "grad_norm": 3.2450687885284424, "learning_rate": 5.0320884372379256e-06, "loss": 0.1068, "step": 461090 }, { "epoch": 2.7408741551794855, "grad_norm": 4.876795291900635, "learning_rate": 5.0318809493559e-06, "loss": 0.1154, "step": 461100 }, { "epoch": 2.740933597256154, "grad_norm": 3.9345266819000244, "learning_rate": 5.031673461418971e-06, "loss": 0.1108, "step": 461110 }, { "epoch": 2.740993039332822, "grad_norm": 4.424018383026123, "learning_rate": 5.031465973427495e-06, "loss": 0.1247, "step": 461120 }, { "epoch": 2.7410524814094908, "grad_norm": 3.175575017929077, "learning_rate": 5.031258485381834e-06, "loss": 0.1151, "step": 461130 }, { "epoch": 2.7411119234861587, "grad_norm": 2.889392375946045, "learning_rate": 5.03105099728234e-06, "loss": 0.1162, "step": 461140 }, { "epoch": 2.741171365562827, "grad_norm": 4.477844715118408, "learning_rate": 5.030843509129373e-06, "loss": 0.123, "step": 461150 }, { "epoch": 2.7412308076394956, "grad_norm": 4.349400520324707, "learning_rate": 5.03063602092329e-06, "loss": 0.1104, "step": 461160 }, { "epoch": 2.741290249716164, "grad_norm": 4.807675838470459, "learning_rate": 5.030428532664446e-06, "loss": 0.1205, "step": 461170 }, { "epoch": 2.7413496917928324, "grad_norm": 4.840148448944092, "learning_rate": 5.030221044353203e-06, "loss": 0.1247, "step": 461180 }, { "epoch": 2.741409133869501, "grad_norm": 4.321887969970703, "learning_rate": 5.030013555989914e-06, "loss": 0.1135, "step": 461190 }, { "epoch": 2.741468575946169, "grad_norm": 4.3710479736328125, "learning_rate": 5.02980606757494e-06, "loss": 0.1125, "step": 461200 }, { "epoch": 2.7415280180228376, "grad_norm": 3.176577568054199, "learning_rate": 5.0295985791086355e-06, "loss": 0.127, "step": 461210 }, { "epoch": 2.741587460099506, "grad_norm": 3.825098752975464, "learning_rate": 5.029391090591359e-06, "loss": 0.1104, "step": 461220 }, { "epoch": 2.7416469021761745, "grad_norm": 4.455460548400879, "learning_rate": 5.0291836020234676e-06, "loss": 0.1221, "step": 461230 }, { "epoch": 2.741706344252843, "grad_norm": 4.123999118804932, "learning_rate": 5.0289761134053185e-06, "loss": 0.1183, "step": 461240 }, { "epoch": 2.7417657863295113, "grad_norm": 4.097172737121582, "learning_rate": 5.028768624737268e-06, "loss": 0.1045, "step": 461250 }, { "epoch": 2.7418252284061797, "grad_norm": 2.7552359104156494, "learning_rate": 5.028561136019675e-06, "loss": 0.1196, "step": 461260 }, { "epoch": 2.741884670482848, "grad_norm": 4.446681022644043, "learning_rate": 5.028353647252897e-06, "loss": 0.1215, "step": 461270 }, { "epoch": 2.7419441125595165, "grad_norm": 4.158179759979248, "learning_rate": 5.028146158437289e-06, "loss": 0.0969, "step": 461280 }, { "epoch": 2.7420035546361845, "grad_norm": 4.235671043395996, "learning_rate": 5.027938669573211e-06, "loss": 0.1094, "step": 461290 }, { "epoch": 2.7420629967128534, "grad_norm": 3.5479369163513184, "learning_rate": 5.0277311806610205e-06, "loss": 0.1283, "step": 461300 }, { "epoch": 2.7421224387895213, "grad_norm": 5.457340717315674, "learning_rate": 5.027523691701072e-06, "loss": 0.1061, "step": 461310 }, { "epoch": 2.74218188086619, "grad_norm": 5.108499526977539, "learning_rate": 5.027316202693725e-06, "loss": 0.1055, "step": 461320 }, { "epoch": 2.742241322942858, "grad_norm": 4.111774921417236, "learning_rate": 5.027108713639337e-06, "loss": 0.1145, "step": 461330 }, { "epoch": 2.7423007650195266, "grad_norm": 4.152510643005371, "learning_rate": 5.0269012245382635e-06, "loss": 0.1109, "step": 461340 }, { "epoch": 2.742360207096195, "grad_norm": 4.34279727935791, "learning_rate": 5.026693735390863e-06, "loss": 0.1214, "step": 461350 }, { "epoch": 2.7424196491728634, "grad_norm": 4.37841796875, "learning_rate": 5.026486246197493e-06, "loss": 0.1109, "step": 461360 }, { "epoch": 2.742479091249532, "grad_norm": 4.709911346435547, "learning_rate": 5.026278756958509e-06, "loss": 0.1234, "step": 461370 }, { "epoch": 2.7425385333262002, "grad_norm": 3.1537351608276367, "learning_rate": 5.026071267674271e-06, "loss": 0.1053, "step": 461380 }, { "epoch": 2.7425979754028686, "grad_norm": 3.69905424118042, "learning_rate": 5.0258637783451356e-06, "loss": 0.1008, "step": 461390 }, { "epoch": 2.742657417479537, "grad_norm": 5.062128067016602, "learning_rate": 5.02565628897146e-06, "loss": 0.1089, "step": 461400 }, { "epoch": 2.7427168595562055, "grad_norm": 3.412184476852417, "learning_rate": 5.0254487995536e-06, "loss": 0.1017, "step": 461410 }, { "epoch": 2.742776301632874, "grad_norm": 2.5908384323120117, "learning_rate": 5.025241310091915e-06, "loss": 0.1034, "step": 461420 }, { "epoch": 2.7428357437095423, "grad_norm": 4.388802528381348, "learning_rate": 5.025033820586762e-06, "loss": 0.1331, "step": 461430 }, { "epoch": 2.7428951857862107, "grad_norm": 4.349129676818848, "learning_rate": 5.024826331038497e-06, "loss": 0.1068, "step": 461440 }, { "epoch": 2.742954627862879, "grad_norm": 4.862407684326172, "learning_rate": 5.024618841447478e-06, "loss": 0.1089, "step": 461450 }, { "epoch": 2.7430140699395476, "grad_norm": 3.5917999744415283, "learning_rate": 5.024411351814062e-06, "loss": 0.0988, "step": 461460 }, { "epoch": 2.743073512016216, "grad_norm": 3.1280055046081543, "learning_rate": 5.024203862138608e-06, "loss": 0.113, "step": 461470 }, { "epoch": 2.743132954092884, "grad_norm": 4.335188388824463, "learning_rate": 5.023996372421471e-06, "loss": 0.1381, "step": 461480 }, { "epoch": 2.743192396169553, "grad_norm": 3.636240243911743, "learning_rate": 5.023788882663011e-06, "loss": 0.1162, "step": 461490 }, { "epoch": 2.7432518382462208, "grad_norm": 4.035651683807373, "learning_rate": 5.023581392863581e-06, "loss": 0.1045, "step": 461500 }, { "epoch": 2.7433112803228896, "grad_norm": 3.5652265548706055, "learning_rate": 5.0233739030235415e-06, "loss": 0.1107, "step": 461510 }, { "epoch": 2.7433707223995576, "grad_norm": 3.719252347946167, "learning_rate": 5.0231664131432515e-06, "loss": 0.1148, "step": 461520 }, { "epoch": 2.743430164476226, "grad_norm": 3.924712657928467, "learning_rate": 5.022958923223065e-06, "loss": 0.1057, "step": 461530 }, { "epoch": 2.7434896065528944, "grad_norm": 5.488767623901367, "learning_rate": 5.02275143326334e-06, "loss": 0.1132, "step": 461540 }, { "epoch": 2.743549048629563, "grad_norm": 3.73410964012146, "learning_rate": 5.022543943264435e-06, "loss": 0.1235, "step": 461550 }, { "epoch": 2.7436084907062313, "grad_norm": 3.6279187202453613, "learning_rate": 5.022336453226707e-06, "loss": 0.1101, "step": 461560 }, { "epoch": 2.7436679327828997, "grad_norm": 4.795326232910156, "learning_rate": 5.0221289631505125e-06, "loss": 0.1202, "step": 461570 }, { "epoch": 2.743727374859568, "grad_norm": 3.8989648818969727, "learning_rate": 5.0219214730362085e-06, "loss": 0.1095, "step": 461580 }, { "epoch": 2.7437868169362365, "grad_norm": 3.2953736782073975, "learning_rate": 5.021713982884154e-06, "loss": 0.1046, "step": 461590 }, { "epoch": 2.743846259012905, "grad_norm": 4.500352382659912, "learning_rate": 5.0215064926947055e-06, "loss": 0.1235, "step": 461600 }, { "epoch": 2.7439057010895733, "grad_norm": 3.6234288215637207, "learning_rate": 5.021299002468219e-06, "loss": 0.1225, "step": 461610 }, { "epoch": 2.7439651431662417, "grad_norm": 2.52284836769104, "learning_rate": 5.021091512205054e-06, "loss": 0.1055, "step": 461620 }, { "epoch": 2.74402458524291, "grad_norm": 3.193061113357544, "learning_rate": 5.020884021905568e-06, "loss": 0.1177, "step": 461630 }, { "epoch": 2.7440840273195786, "grad_norm": 2.844496011734009, "learning_rate": 5.020676531570116e-06, "loss": 0.1055, "step": 461640 }, { "epoch": 2.744143469396247, "grad_norm": 3.8039052486419678, "learning_rate": 5.020469041199056e-06, "loss": 0.1251, "step": 461650 }, { "epoch": 2.7442029114729154, "grad_norm": 4.017578125, "learning_rate": 5.020261550792748e-06, "loss": 0.1062, "step": 461660 }, { "epoch": 2.7442623535495834, "grad_norm": 3.4826533794403076, "learning_rate": 5.020054060351544e-06, "loss": 0.1227, "step": 461670 }, { "epoch": 2.7443217956262522, "grad_norm": 3.464148998260498, "learning_rate": 5.019846569875807e-06, "loss": 0.1079, "step": 461680 }, { "epoch": 2.74438123770292, "grad_norm": 4.445782661437988, "learning_rate": 5.019639079365892e-06, "loss": 0.12, "step": 461690 }, { "epoch": 2.744440679779589, "grad_norm": 3.657984733581543, "learning_rate": 5.019431588822154e-06, "loss": 0.1116, "step": 461700 }, { "epoch": 2.744500121856257, "grad_norm": 3.761199474334717, "learning_rate": 5.019224098244954e-06, "loss": 0.1242, "step": 461710 }, { "epoch": 2.7445595639329254, "grad_norm": 5.016332626342773, "learning_rate": 5.019016607634648e-06, "loss": 0.1192, "step": 461720 }, { "epoch": 2.744619006009594, "grad_norm": 3.6441242694854736, "learning_rate": 5.018809116991593e-06, "loss": 0.1104, "step": 461730 }, { "epoch": 2.7446784480862623, "grad_norm": 3.8815791606903076, "learning_rate": 5.018601626316145e-06, "loss": 0.1126, "step": 461740 }, { "epoch": 2.7447378901629307, "grad_norm": 2.947597026824951, "learning_rate": 5.018394135608664e-06, "loss": 0.1059, "step": 461750 }, { "epoch": 2.744797332239599, "grad_norm": 4.726532459259033, "learning_rate": 5.018186644869507e-06, "loss": 0.1226, "step": 461760 }, { "epoch": 2.7448567743162675, "grad_norm": 5.385763168334961, "learning_rate": 5.017979154099029e-06, "loss": 0.1159, "step": 461770 }, { "epoch": 2.744916216392936, "grad_norm": 4.05314826965332, "learning_rate": 5.01777166329759e-06, "loss": 0.1249, "step": 461780 }, { "epoch": 2.7449756584696043, "grad_norm": 3.1916236877441406, "learning_rate": 5.0175641724655455e-06, "loss": 0.1258, "step": 461790 }, { "epoch": 2.7450351005462728, "grad_norm": 3.8215601444244385, "learning_rate": 5.017356681603253e-06, "loss": 0.1251, "step": 461800 }, { "epoch": 2.745094542622941, "grad_norm": 4.654063701629639, "learning_rate": 5.01714919071107e-06, "loss": 0.1269, "step": 461810 }, { "epoch": 2.7451539846996096, "grad_norm": 4.334448337554932, "learning_rate": 5.016941699789355e-06, "loss": 0.0997, "step": 461820 }, { "epoch": 2.745213426776278, "grad_norm": 5.5012006759643555, "learning_rate": 5.016734208838462e-06, "loss": 0.1303, "step": 461830 }, { "epoch": 2.7452728688529464, "grad_norm": 3.6866233348846436, "learning_rate": 5.016526717858753e-06, "loss": 0.0989, "step": 461840 }, { "epoch": 2.745332310929615, "grad_norm": 5.35675573348999, "learning_rate": 5.0163192268505835e-06, "loss": 0.1206, "step": 461850 }, { "epoch": 2.745391753006283, "grad_norm": 6.049178123474121, "learning_rate": 5.0161117358143096e-06, "loss": 0.1165, "step": 461860 }, { "epoch": 2.7454511950829517, "grad_norm": 4.537216663360596, "learning_rate": 5.0159042447502885e-06, "loss": 0.1232, "step": 461870 }, { "epoch": 2.7455106371596196, "grad_norm": 3.132796287536621, "learning_rate": 5.0156967536588795e-06, "loss": 0.1174, "step": 461880 }, { "epoch": 2.745570079236288, "grad_norm": 4.596715927124023, "learning_rate": 5.015489262540438e-06, "loss": 0.1199, "step": 461890 }, { "epoch": 2.7456295213129565, "grad_norm": 4.130715847015381, "learning_rate": 5.015281771395323e-06, "loss": 0.124, "step": 461900 }, { "epoch": 2.745688963389625, "grad_norm": 5.169002056121826, "learning_rate": 5.015074280223891e-06, "loss": 0.1175, "step": 461910 }, { "epoch": 2.7457484054662933, "grad_norm": 4.336963653564453, "learning_rate": 5.014866789026499e-06, "loss": 0.1223, "step": 461920 }, { "epoch": 2.7458078475429617, "grad_norm": 3.598065137863159, "learning_rate": 5.014659297803504e-06, "loss": 0.116, "step": 461930 }, { "epoch": 2.74586728961963, "grad_norm": 4.948993682861328, "learning_rate": 5.014451806555263e-06, "loss": 0.1177, "step": 461940 }, { "epoch": 2.7459267316962985, "grad_norm": 4.061609745025635, "learning_rate": 5.014244315282137e-06, "loss": 0.0979, "step": 461950 }, { "epoch": 2.745986173772967, "grad_norm": 2.508270025253296, "learning_rate": 5.014036823984478e-06, "loss": 0.1303, "step": 461960 }, { "epoch": 2.7460456158496354, "grad_norm": 2.8022425174713135, "learning_rate": 5.013829332662648e-06, "loss": 0.1078, "step": 461970 }, { "epoch": 2.7461050579263038, "grad_norm": 4.030983924865723, "learning_rate": 5.013621841317001e-06, "loss": 0.1123, "step": 461980 }, { "epoch": 2.746164500002972, "grad_norm": 3.6448540687561035, "learning_rate": 5.013414349947895e-06, "loss": 0.1189, "step": 461990 }, { "epoch": 2.7462239420796406, "grad_norm": 4.179961681365967, "learning_rate": 5.013206858555689e-06, "loss": 0.1017, "step": 462000 }, { "epoch": 2.746283384156309, "grad_norm": 3.7693350315093994, "learning_rate": 5.01299936714074e-06, "loss": 0.1188, "step": 462010 }, { "epoch": 2.7463428262329774, "grad_norm": 3.7995076179504395, "learning_rate": 5.012791875703402e-06, "loss": 0.1109, "step": 462020 }, { "epoch": 2.7464022683096454, "grad_norm": 4.579561233520508, "learning_rate": 5.012584384244038e-06, "loss": 0.1153, "step": 462030 }, { "epoch": 2.7464617103863143, "grad_norm": 3.4292500019073486, "learning_rate": 5.012376892763e-06, "loss": 0.1121, "step": 462040 }, { "epoch": 2.7465211524629822, "grad_norm": 4.517768383026123, "learning_rate": 5.0121694012606485e-06, "loss": 0.1381, "step": 462050 }, { "epoch": 2.746580594539651, "grad_norm": 3.5056941509246826, "learning_rate": 5.011961909737338e-06, "loss": 0.1241, "step": 462060 }, { "epoch": 2.746640036616319, "grad_norm": 2.716771125793457, "learning_rate": 5.01175441819343e-06, "loss": 0.1247, "step": 462070 }, { "epoch": 2.7466994786929875, "grad_norm": 3.8464913368225098, "learning_rate": 5.011546926629279e-06, "loss": 0.1102, "step": 462080 }, { "epoch": 2.746758920769656, "grad_norm": 3.2589926719665527, "learning_rate": 5.0113394350452415e-06, "loss": 0.1186, "step": 462090 }, { "epoch": 2.7468183628463243, "grad_norm": 3.112022876739502, "learning_rate": 5.011131943441677e-06, "loss": 0.1224, "step": 462100 }, { "epoch": 2.7468778049229927, "grad_norm": 3.894770860671997, "learning_rate": 5.010924451818942e-06, "loss": 0.1136, "step": 462110 }, { "epoch": 2.746937246999661, "grad_norm": 4.526701927185059, "learning_rate": 5.010716960177394e-06, "loss": 0.1198, "step": 462120 }, { "epoch": 2.7469966890763295, "grad_norm": 4.159241199493408, "learning_rate": 5.01050946851739e-06, "loss": 0.1194, "step": 462130 }, { "epoch": 2.747056131152998, "grad_norm": 4.38124418258667, "learning_rate": 5.010301976839288e-06, "loss": 0.1102, "step": 462140 }, { "epoch": 2.7471155732296664, "grad_norm": 3.4219143390655518, "learning_rate": 5.010094485143444e-06, "loss": 0.1025, "step": 462150 }, { "epoch": 2.747175015306335, "grad_norm": 5.467381477355957, "learning_rate": 5.0098869934302155e-06, "loss": 0.1221, "step": 462160 }, { "epoch": 2.747234457383003, "grad_norm": 5.581108570098877, "learning_rate": 5.0096795016999615e-06, "loss": 0.1184, "step": 462170 }, { "epoch": 2.7472938994596716, "grad_norm": 4.000759601593018, "learning_rate": 5.009472009953038e-06, "loss": 0.1173, "step": 462180 }, { "epoch": 2.74735334153634, "grad_norm": 4.656409740447998, "learning_rate": 5.009264518189802e-06, "loss": 0.1132, "step": 462190 }, { "epoch": 2.7474127836130084, "grad_norm": 5.08545446395874, "learning_rate": 5.009057026410612e-06, "loss": 0.1178, "step": 462200 }, { "epoch": 2.747472225689677, "grad_norm": 4.3869428634643555, "learning_rate": 5.008849534615825e-06, "loss": 0.1218, "step": 462210 }, { "epoch": 2.747531667766345, "grad_norm": 4.164239883422852, "learning_rate": 5.008642042805798e-06, "loss": 0.1173, "step": 462220 }, { "epoch": 2.7475911098430137, "grad_norm": 3.6373438835144043, "learning_rate": 5.008434550980887e-06, "loss": 0.0998, "step": 462230 }, { "epoch": 2.7476505519196817, "grad_norm": 4.745659828186035, "learning_rate": 5.0082270591414526e-06, "loss": 0.1167, "step": 462240 }, { "epoch": 2.7477099939963505, "grad_norm": 3.9630138874053955, "learning_rate": 5.008019567287849e-06, "loss": 0.1201, "step": 462250 }, { "epoch": 2.7477694360730185, "grad_norm": 4.180081844329834, "learning_rate": 5.007812075420435e-06, "loss": 0.1177, "step": 462260 }, { "epoch": 2.747828878149687, "grad_norm": 4.46693229675293, "learning_rate": 5.007604583539568e-06, "loss": 0.1307, "step": 462270 }, { "epoch": 2.7478883202263553, "grad_norm": 4.3969197273254395, "learning_rate": 5.0073970916456045e-06, "loss": 0.1256, "step": 462280 }, { "epoch": 2.7479477623030237, "grad_norm": 4.655678749084473, "learning_rate": 5.007189599738902e-06, "loss": 0.1068, "step": 462290 }, { "epoch": 2.748007204379692, "grad_norm": 2.54841685295105, "learning_rate": 5.006982107819819e-06, "loss": 0.1043, "step": 462300 }, { "epoch": 2.7480666464563606, "grad_norm": 3.659838914871216, "learning_rate": 5.006774615888712e-06, "loss": 0.1169, "step": 462310 }, { "epoch": 2.748126088533029, "grad_norm": 4.33980131149292, "learning_rate": 5.0065671239459375e-06, "loss": 0.1345, "step": 462320 }, { "epoch": 2.7481855306096974, "grad_norm": 3.559554100036621, "learning_rate": 5.006359631991855e-06, "loss": 0.1015, "step": 462330 }, { "epoch": 2.748244972686366, "grad_norm": 3.8587286472320557, "learning_rate": 5.00615214002682e-06, "loss": 0.1102, "step": 462340 }, { "epoch": 2.748304414763034, "grad_norm": 3.0705907344818115, "learning_rate": 5.005944648051189e-06, "loss": 0.1201, "step": 462350 }, { "epoch": 2.7483638568397026, "grad_norm": 4.233558654785156, "learning_rate": 5.005737156065322e-06, "loss": 0.1173, "step": 462360 }, { "epoch": 2.748423298916371, "grad_norm": 5.088522434234619, "learning_rate": 5.005529664069575e-06, "loss": 0.1198, "step": 462370 }, { "epoch": 2.7484827409930395, "grad_norm": 5.030007362365723, "learning_rate": 5.005322172064304e-06, "loss": 0.1151, "step": 462380 }, { "epoch": 2.748542183069708, "grad_norm": 4.285737037658691, "learning_rate": 5.005114680049867e-06, "loss": 0.1183, "step": 462390 }, { "epoch": 2.7486016251463763, "grad_norm": 3.161376953125, "learning_rate": 5.004907188026624e-06, "loss": 0.1079, "step": 462400 }, { "epoch": 2.7486610672230443, "grad_norm": 3.3148891925811768, "learning_rate": 5.00469969599493e-06, "loss": 0.1179, "step": 462410 }, { "epoch": 2.748720509299713, "grad_norm": 4.104884147644043, "learning_rate": 5.004492203955141e-06, "loss": 0.1103, "step": 462420 }, { "epoch": 2.748779951376381, "grad_norm": 3.8017349243164062, "learning_rate": 5.004284711907618e-06, "loss": 0.1146, "step": 462430 }, { "epoch": 2.74883939345305, "grad_norm": 4.685970306396484, "learning_rate": 5.0040772198527146e-06, "loss": 0.1112, "step": 462440 }, { "epoch": 2.748898835529718, "grad_norm": 3.520219087600708, "learning_rate": 5.00386972779079e-06, "loss": 0.1206, "step": 462450 }, { "epoch": 2.7489582776063863, "grad_norm": 4.301993370056152, "learning_rate": 5.003662235722202e-06, "loss": 0.1165, "step": 462460 }, { "epoch": 2.7490177196830548, "grad_norm": 4.134410381317139, "learning_rate": 5.003454743647307e-06, "loss": 0.1103, "step": 462470 }, { "epoch": 2.749077161759723, "grad_norm": 5.205874919891357, "learning_rate": 5.003247251566461e-06, "loss": 0.1076, "step": 462480 }, { "epoch": 2.7491366038363916, "grad_norm": 3.6092405319213867, "learning_rate": 5.003039759480024e-06, "loss": 0.1258, "step": 462490 }, { "epoch": 2.74919604591306, "grad_norm": 5.338157653808594, "learning_rate": 5.002832267388352e-06, "loss": 0.1176, "step": 462500 }, { "epoch": 2.7492554879897284, "grad_norm": 3.835716485977173, "learning_rate": 5.002624775291804e-06, "loss": 0.1147, "step": 462510 }, { "epoch": 2.749314930066397, "grad_norm": 3.891305446624756, "learning_rate": 5.002417283190734e-06, "loss": 0.128, "step": 462520 }, { "epoch": 2.7493743721430652, "grad_norm": 4.579814434051514, "learning_rate": 5.002209791085502e-06, "loss": 0.1161, "step": 462530 }, { "epoch": 2.7494338142197337, "grad_norm": 5.151341438293457, "learning_rate": 5.002002298976464e-06, "loss": 0.1121, "step": 462540 }, { "epoch": 2.749493256296402, "grad_norm": 3.451082944869995, "learning_rate": 5.001794806863978e-06, "loss": 0.1179, "step": 462550 }, { "epoch": 2.7495526983730705, "grad_norm": 4.812743186950684, "learning_rate": 5.0015873147484e-06, "loss": 0.1234, "step": 462560 }, { "epoch": 2.749612140449739, "grad_norm": 4.578373432159424, "learning_rate": 5.00137982263009e-06, "loss": 0.1129, "step": 462570 }, { "epoch": 2.749671582526407, "grad_norm": 4.622443199157715, "learning_rate": 5.001172330509403e-06, "loss": 0.1196, "step": 462580 }, { "epoch": 2.7497310246030757, "grad_norm": 3.288731813430786, "learning_rate": 5.000964838386698e-06, "loss": 0.1131, "step": 462590 }, { "epoch": 2.7497904666797437, "grad_norm": 4.322667121887207, "learning_rate": 5.00075734626233e-06, "loss": 0.1216, "step": 462600 }, { "epoch": 2.7498499087564126, "grad_norm": 4.882163047790527, "learning_rate": 5.000549854136658e-06, "loss": 0.1109, "step": 462610 }, { "epoch": 2.7499093508330805, "grad_norm": 4.230106830596924, "learning_rate": 5.00034236201004e-06, "loss": 0.1079, "step": 462620 }, { "epoch": 2.749968792909749, "grad_norm": 4.185079097747803, "learning_rate": 5.000134869882834e-06, "loss": 0.1046, "step": 462630 }, { "epoch": 2.7500282349864174, "grad_norm": 4.787720680236816, "learning_rate": 4.999927377755392e-06, "loss": 0.1203, "step": 462640 }, { "epoch": 2.7500876770630858, "grad_norm": 5.469878673553467, "learning_rate": 4.999719885628077e-06, "loss": 0.1043, "step": 462650 }, { "epoch": 2.750147119139754, "grad_norm": 2.686938524246216, "learning_rate": 4.999512393501245e-06, "loss": 0.1191, "step": 462660 }, { "epoch": 2.7502065612164226, "grad_norm": 4.635140895843506, "learning_rate": 4.999304901375251e-06, "loss": 0.1375, "step": 462670 }, { "epoch": 2.750266003293091, "grad_norm": 3.720085859298706, "learning_rate": 4.999097409250455e-06, "loss": 0.1179, "step": 462680 }, { "epoch": 2.7503254453697594, "grad_norm": 4.196354389190674, "learning_rate": 4.9988899171272145e-06, "loss": 0.1043, "step": 462690 }, { "epoch": 2.750384887446428, "grad_norm": 4.030958652496338, "learning_rate": 4.998682425005884e-06, "loss": 0.1192, "step": 462700 }, { "epoch": 2.7504443295230963, "grad_norm": 3.6194047927856445, "learning_rate": 4.998474932886824e-06, "loss": 0.1138, "step": 462710 }, { "epoch": 2.7505037715997647, "grad_norm": 4.864081382751465, "learning_rate": 4.99826744077039e-06, "loss": 0.1179, "step": 462720 }, { "epoch": 2.750563213676433, "grad_norm": 4.771754264831543, "learning_rate": 4.998059948656939e-06, "loss": 0.1297, "step": 462730 }, { "epoch": 2.7506226557531015, "grad_norm": 3.5305004119873047, "learning_rate": 4.997852456546829e-06, "loss": 0.1115, "step": 462740 }, { "epoch": 2.75068209782977, "grad_norm": 3.0865373611450195, "learning_rate": 4.997644964440418e-06, "loss": 0.1219, "step": 462750 }, { "epoch": 2.7507415399064383, "grad_norm": 4.920345783233643, "learning_rate": 4.99743747233806e-06, "loss": 0.1141, "step": 462760 }, { "epoch": 2.7508009819831063, "grad_norm": 3.341268301010132, "learning_rate": 4.997229980240118e-06, "loss": 0.1242, "step": 462770 }, { "epoch": 2.750860424059775, "grad_norm": 3.108987808227539, "learning_rate": 4.997022488146944e-06, "loss": 0.1109, "step": 462780 }, { "epoch": 2.750919866136443, "grad_norm": 3.338027238845825, "learning_rate": 4.996814996058899e-06, "loss": 0.1087, "step": 462790 }, { "epoch": 2.750979308213112, "grad_norm": 3.5190160274505615, "learning_rate": 4.99660750397634e-06, "loss": 0.1146, "step": 462800 }, { "epoch": 2.75103875028978, "grad_norm": 3.627732753753662, "learning_rate": 4.996400011899622e-06, "loss": 0.1196, "step": 462810 }, { "epoch": 2.7510981923664484, "grad_norm": 4.049156665802002, "learning_rate": 4.996192519829105e-06, "loss": 0.1181, "step": 462820 }, { "epoch": 2.751157634443117, "grad_norm": 3.9940781593322754, "learning_rate": 4.995985027765144e-06, "loss": 0.1026, "step": 462830 }, { "epoch": 2.751217076519785, "grad_norm": 5.133448123931885, "learning_rate": 4.995777535708096e-06, "loss": 0.127, "step": 462840 }, { "epoch": 2.7512765185964536, "grad_norm": 3.8417887687683105, "learning_rate": 4.995570043658321e-06, "loss": 0.1171, "step": 462850 }, { "epoch": 2.751335960673122, "grad_norm": 4.279979228973389, "learning_rate": 4.995362551616175e-06, "loss": 0.1181, "step": 462860 }, { "epoch": 2.7513954027497904, "grad_norm": 5.168973445892334, "learning_rate": 4.995155059582014e-06, "loss": 0.1323, "step": 462870 }, { "epoch": 2.751454844826459, "grad_norm": 2.9985389709472656, "learning_rate": 4.994947567556198e-06, "loss": 0.1017, "step": 462880 }, { "epoch": 2.7515142869031273, "grad_norm": 3.988675355911255, "learning_rate": 4.994740075539083e-06, "loss": 0.1138, "step": 462890 }, { "epoch": 2.7515737289797957, "grad_norm": 3.369960069656372, "learning_rate": 4.994532583531025e-06, "loss": 0.1117, "step": 462900 }, { "epoch": 2.751633171056464, "grad_norm": 4.2293009757995605, "learning_rate": 4.994325091532383e-06, "loss": 0.1028, "step": 462910 }, { "epoch": 2.7516926131331325, "grad_norm": 3.949923515319824, "learning_rate": 4.994117599543515e-06, "loss": 0.1228, "step": 462920 }, { "epoch": 2.751752055209801, "grad_norm": 2.961456060409546, "learning_rate": 4.993910107564775e-06, "loss": 0.1121, "step": 462930 }, { "epoch": 2.7518114972864693, "grad_norm": 4.248546600341797, "learning_rate": 4.993702615596524e-06, "loss": 0.1273, "step": 462940 }, { "epoch": 2.7518709393631378, "grad_norm": 3.5516886711120605, "learning_rate": 4.9934951236391185e-06, "loss": 0.105, "step": 462950 }, { "epoch": 2.7519303814398057, "grad_norm": 4.364484786987305, "learning_rate": 4.993287631692913e-06, "loss": 0.1269, "step": 462960 }, { "epoch": 2.7519898235164746, "grad_norm": 5.175919532775879, "learning_rate": 4.993080139758269e-06, "loss": 0.1101, "step": 462970 }, { "epoch": 2.7520492655931426, "grad_norm": 4.312652587890625, "learning_rate": 4.992872647835539e-06, "loss": 0.1275, "step": 462980 }, { "epoch": 2.7521087076698114, "grad_norm": 4.384477615356445, "learning_rate": 4.992665155925086e-06, "loss": 0.1149, "step": 462990 }, { "epoch": 2.7521681497464794, "grad_norm": 4.616842746734619, "learning_rate": 4.992457664027264e-06, "loss": 0.1284, "step": 463000 }, { "epoch": 2.752227591823148, "grad_norm": 3.891850471496582, "learning_rate": 4.992250172142429e-06, "loss": 0.1003, "step": 463010 }, { "epoch": 2.752287033899816, "grad_norm": 4.661273002624512, "learning_rate": 4.992042680270942e-06, "loss": 0.11, "step": 463020 }, { "epoch": 2.7523464759764846, "grad_norm": 4.284057140350342, "learning_rate": 4.9918351884131585e-06, "loss": 0.1306, "step": 463030 }, { "epoch": 2.752405918053153, "grad_norm": 2.9607017040252686, "learning_rate": 4.991627696569435e-06, "loss": 0.1073, "step": 463040 }, { "epoch": 2.7524653601298215, "grad_norm": 4.274081707000732, "learning_rate": 4.99142020474013e-06, "loss": 0.1121, "step": 463050 }, { "epoch": 2.75252480220649, "grad_norm": 4.070682048797607, "learning_rate": 4.991212712925601e-06, "loss": 0.1111, "step": 463060 }, { "epoch": 2.7525842442831583, "grad_norm": 2.6896464824676514, "learning_rate": 4.991005221126203e-06, "loss": 0.0922, "step": 463070 }, { "epoch": 2.7526436863598267, "grad_norm": 3.537356376647949, "learning_rate": 4.9907977293422964e-06, "loss": 0.1037, "step": 463080 }, { "epoch": 2.752703128436495, "grad_norm": 3.592233419418335, "learning_rate": 4.990590237574238e-06, "loss": 0.114, "step": 463090 }, { "epoch": 2.7527625705131635, "grad_norm": 3.571727752685547, "learning_rate": 4.990382745822383e-06, "loss": 0.1077, "step": 463100 }, { "epoch": 2.752822012589832, "grad_norm": 3.7139382362365723, "learning_rate": 4.99017525408709e-06, "loss": 0.1022, "step": 463110 }, { "epoch": 2.7528814546665004, "grad_norm": 4.0005292892456055, "learning_rate": 4.989967762368718e-06, "loss": 0.0999, "step": 463120 }, { "epoch": 2.7529408967431688, "grad_norm": 4.209532737731934, "learning_rate": 4.9897602706676205e-06, "loss": 0.1033, "step": 463130 }, { "epoch": 2.753000338819837, "grad_norm": 5.588988304138184, "learning_rate": 4.989552778984158e-06, "loss": 0.1125, "step": 463140 }, { "epoch": 2.753059780896505, "grad_norm": 4.042013645172119, "learning_rate": 4.989345287318688e-06, "loss": 0.1196, "step": 463150 }, { "epoch": 2.753119222973174, "grad_norm": 4.3090667724609375, "learning_rate": 4.989137795671564e-06, "loss": 0.1164, "step": 463160 }, { "epoch": 2.753178665049842, "grad_norm": 2.945852756500244, "learning_rate": 4.988930304043148e-06, "loss": 0.1123, "step": 463170 }, { "epoch": 2.753238107126511, "grad_norm": 4.632516384124756, "learning_rate": 4.988722812433796e-06, "loss": 0.1319, "step": 463180 }, { "epoch": 2.753297549203179, "grad_norm": 2.809631824493408, "learning_rate": 4.988515320843863e-06, "loss": 0.1133, "step": 463190 }, { "epoch": 2.7533569912798472, "grad_norm": 2.969653844833374, "learning_rate": 4.9883078292737065e-06, "loss": 0.12, "step": 463200 }, { "epoch": 2.7534164333565156, "grad_norm": 4.632911205291748, "learning_rate": 4.988100337723688e-06, "loss": 0.1098, "step": 463210 }, { "epoch": 2.753475875433184, "grad_norm": 3.0396196842193604, "learning_rate": 4.987892846194161e-06, "loss": 0.1137, "step": 463220 }, { "epoch": 2.7535353175098525, "grad_norm": 4.054186820983887, "learning_rate": 4.987685354685484e-06, "loss": 0.1215, "step": 463230 }, { "epoch": 2.753594759586521, "grad_norm": 6.174600601196289, "learning_rate": 4.987477863198015e-06, "loss": 0.1075, "step": 463240 }, { "epoch": 2.7536542016631893, "grad_norm": 4.058592796325684, "learning_rate": 4.987270371732112e-06, "loss": 0.1162, "step": 463250 }, { "epoch": 2.7537136437398577, "grad_norm": 3.927459239959717, "learning_rate": 4.987062880288128e-06, "loss": 0.1306, "step": 463260 }, { "epoch": 2.753773085816526, "grad_norm": 3.1520533561706543, "learning_rate": 4.986855388866424e-06, "loss": 0.1414, "step": 463270 }, { "epoch": 2.7538325278931945, "grad_norm": 3.460340976715088, "learning_rate": 4.986647897467358e-06, "loss": 0.1108, "step": 463280 }, { "epoch": 2.753891969969863, "grad_norm": 4.117584705352783, "learning_rate": 4.986440406091284e-06, "loss": 0.1137, "step": 463290 }, { "epoch": 2.7539514120465314, "grad_norm": 3.9979989528656006, "learning_rate": 4.986232914738563e-06, "loss": 0.1291, "step": 463300 }, { "epoch": 2.7540108541232, "grad_norm": 4.981714725494385, "learning_rate": 4.98602542340955e-06, "loss": 0.1313, "step": 463310 }, { "epoch": 2.7540702961998678, "grad_norm": 3.941006898880005, "learning_rate": 4.985817932104603e-06, "loss": 0.1144, "step": 463320 }, { "epoch": 2.7541297382765366, "grad_norm": 3.6829276084899902, "learning_rate": 4.985610440824079e-06, "loss": 0.1225, "step": 463330 }, { "epoch": 2.7541891803532046, "grad_norm": 3.283912181854248, "learning_rate": 4.9854029495683356e-06, "loss": 0.1236, "step": 463340 }, { "epoch": 2.7542486224298734, "grad_norm": 4.698734283447266, "learning_rate": 4.98519545833773e-06, "loss": 0.1279, "step": 463350 }, { "epoch": 2.7543080645065414, "grad_norm": 5.143615245819092, "learning_rate": 4.98498796713262e-06, "loss": 0.1095, "step": 463360 }, { "epoch": 2.75436750658321, "grad_norm": 3.7581965923309326, "learning_rate": 4.984780475953362e-06, "loss": 0.1098, "step": 463370 }, { "epoch": 2.7544269486598782, "grad_norm": 3.360381841659546, "learning_rate": 4.984572984800314e-06, "loss": 0.1079, "step": 463380 }, { "epoch": 2.7544863907365467, "grad_norm": 6.003742218017578, "learning_rate": 4.984365493673833e-06, "loss": 0.1328, "step": 463390 }, { "epoch": 2.754545832813215, "grad_norm": 3.2282400131225586, "learning_rate": 4.984158002574277e-06, "loss": 0.0984, "step": 463400 }, { "epoch": 2.7546052748898835, "grad_norm": 4.704853534698486, "learning_rate": 4.983950511502002e-06, "loss": 0.1344, "step": 463410 }, { "epoch": 2.754664716966552, "grad_norm": 5.026515960693359, "learning_rate": 4.983743020457366e-06, "loss": 0.1307, "step": 463420 }, { "epoch": 2.7547241590432203, "grad_norm": 4.89164924621582, "learning_rate": 4.983535529440726e-06, "loss": 0.1168, "step": 463430 }, { "epoch": 2.7547836011198887, "grad_norm": 2.960540294647217, "learning_rate": 4.983328038452441e-06, "loss": 0.1217, "step": 463440 }, { "epoch": 2.754843043196557, "grad_norm": 3.452779769897461, "learning_rate": 4.983120547492867e-06, "loss": 0.1186, "step": 463450 }, { "epoch": 2.7549024852732256, "grad_norm": 3.8646750450134277, "learning_rate": 4.9829130565623605e-06, "loss": 0.1279, "step": 463460 }, { "epoch": 2.754961927349894, "grad_norm": 3.6323537826538086, "learning_rate": 4.982705565661281e-06, "loss": 0.1046, "step": 463470 }, { "epoch": 2.7550213694265624, "grad_norm": 4.733448505401611, "learning_rate": 4.982498074789985e-06, "loss": 0.1284, "step": 463480 }, { "epoch": 2.755080811503231, "grad_norm": 3.016469717025757, "learning_rate": 4.982290583948828e-06, "loss": 0.1055, "step": 463490 }, { "epoch": 2.7551402535798992, "grad_norm": 3.6569201946258545, "learning_rate": 4.982083093138169e-06, "loss": 0.131, "step": 463500 }, { "epoch": 2.755199695656567, "grad_norm": 4.577035903930664, "learning_rate": 4.981875602358366e-06, "loss": 0.1142, "step": 463510 }, { "epoch": 2.755259137733236, "grad_norm": 4.503368377685547, "learning_rate": 4.981668111609774e-06, "loss": 0.1299, "step": 463520 }, { "epoch": 2.755318579809904, "grad_norm": 3.2759201526641846, "learning_rate": 4.981460620892753e-06, "loss": 0.1011, "step": 463530 }, { "epoch": 2.755378021886573, "grad_norm": 4.355161190032959, "learning_rate": 4.981253130207659e-06, "loss": 0.1326, "step": 463540 }, { "epoch": 2.755437463963241, "grad_norm": 3.868480920791626, "learning_rate": 4.9810456395548476e-06, "loss": 0.1199, "step": 463550 }, { "epoch": 2.7554969060399093, "grad_norm": 2.862125873565674, "learning_rate": 4.980838148934679e-06, "loss": 0.1152, "step": 463560 }, { "epoch": 2.7555563481165777, "grad_norm": 4.726603031158447, "learning_rate": 4.980630658347511e-06, "loss": 0.1154, "step": 463570 }, { "epoch": 2.755615790193246, "grad_norm": 3.029527425765991, "learning_rate": 4.980423167793697e-06, "loss": 0.1029, "step": 463580 }, { "epoch": 2.7556752322699145, "grad_norm": 4.63792610168457, "learning_rate": 4.980215677273597e-06, "loss": 0.1075, "step": 463590 }, { "epoch": 2.755734674346583, "grad_norm": 2.640425205230713, "learning_rate": 4.980008186787569e-06, "loss": 0.1043, "step": 463600 }, { "epoch": 2.7557941164232513, "grad_norm": 3.471543550491333, "learning_rate": 4.979800696335968e-06, "loss": 0.1166, "step": 463610 }, { "epoch": 2.7558535584999198, "grad_norm": 4.810863971710205, "learning_rate": 4.979593205919154e-06, "loss": 0.1057, "step": 463620 }, { "epoch": 2.755913000576588, "grad_norm": 3.466416358947754, "learning_rate": 4.979385715537482e-06, "loss": 0.1116, "step": 463630 }, { "epoch": 2.7559724426532566, "grad_norm": 5.240804195404053, "learning_rate": 4.979178225191308e-06, "loss": 0.1171, "step": 463640 }, { "epoch": 2.756031884729925, "grad_norm": 3.9290459156036377, "learning_rate": 4.978970734880995e-06, "loss": 0.1104, "step": 463650 }, { "epoch": 2.7560913268065934, "grad_norm": 3.5538201332092285, "learning_rate": 4.9787632446068955e-06, "loss": 0.1125, "step": 463660 }, { "epoch": 2.756150768883262, "grad_norm": 3.263518810272217, "learning_rate": 4.978555754369369e-06, "loss": 0.1137, "step": 463670 }, { "epoch": 2.7562102109599302, "grad_norm": 3.9914309978485107, "learning_rate": 4.978348264168772e-06, "loss": 0.1071, "step": 463680 }, { "epoch": 2.7562696530365987, "grad_norm": 4.55457878112793, "learning_rate": 4.978140774005461e-06, "loss": 0.1085, "step": 463690 }, { "epoch": 2.7563290951132666, "grad_norm": 3.0621628761291504, "learning_rate": 4.977933283879795e-06, "loss": 0.1166, "step": 463700 }, { "epoch": 2.7563885371899355, "grad_norm": 3.72780704498291, "learning_rate": 4.9777257937921305e-06, "loss": 0.1156, "step": 463710 }, { "epoch": 2.7564479792666035, "grad_norm": 3.3749637603759766, "learning_rate": 4.977518303742824e-06, "loss": 0.1167, "step": 463720 }, { "epoch": 2.7565074213432723, "grad_norm": 4.486475944519043, "learning_rate": 4.9773108137322345e-06, "loss": 0.1172, "step": 463730 }, { "epoch": 2.7565668634199403, "grad_norm": 3.130993366241455, "learning_rate": 4.977103323760719e-06, "loss": 0.118, "step": 463740 }, { "epoch": 2.7566263054966087, "grad_norm": 3.478548288345337, "learning_rate": 4.976895833828633e-06, "loss": 0.1065, "step": 463750 }, { "epoch": 2.756685747573277, "grad_norm": 4.658053398132324, "learning_rate": 4.976688343936336e-06, "loss": 0.1108, "step": 463760 }, { "epoch": 2.7567451896499455, "grad_norm": 4.122981548309326, "learning_rate": 4.976480854084185e-06, "loss": 0.1143, "step": 463770 }, { "epoch": 2.756804631726614, "grad_norm": 4.27175760269165, "learning_rate": 4.976273364272535e-06, "loss": 0.1187, "step": 463780 }, { "epoch": 2.7568640738032824, "grad_norm": 4.357994556427002, "learning_rate": 4.976065874501746e-06, "loss": 0.1083, "step": 463790 }, { "epoch": 2.7569235158799508, "grad_norm": 4.342538356781006, "learning_rate": 4.9758583847721755e-06, "loss": 0.1197, "step": 463800 }, { "epoch": 2.756982957956619, "grad_norm": 5.022696495056152, "learning_rate": 4.975650895084177e-06, "loss": 0.0949, "step": 463810 }, { "epoch": 2.7570424000332876, "grad_norm": 4.12512731552124, "learning_rate": 4.975443405438113e-06, "loss": 0.1283, "step": 463820 }, { "epoch": 2.757101842109956, "grad_norm": 4.168949127197266, "learning_rate": 4.975235915834339e-06, "loss": 0.112, "step": 463830 }, { "epoch": 2.7571612841866244, "grad_norm": 3.2657558917999268, "learning_rate": 4.975028426273209e-06, "loss": 0.1049, "step": 463840 }, { "epoch": 2.757220726263293, "grad_norm": 4.69051456451416, "learning_rate": 4.974820936755085e-06, "loss": 0.1235, "step": 463850 }, { "epoch": 2.7572801683399613, "grad_norm": 4.589540958404541, "learning_rate": 4.9746134472803196e-06, "loss": 0.1144, "step": 463860 }, { "epoch": 2.7573396104166297, "grad_norm": 3.619547128677368, "learning_rate": 4.9744059578492756e-06, "loss": 0.1157, "step": 463870 }, { "epoch": 2.757399052493298, "grad_norm": 5.4475250244140625, "learning_rate": 4.974198468462306e-06, "loss": 0.1091, "step": 463880 }, { "epoch": 2.757458494569966, "grad_norm": 3.446617841720581, "learning_rate": 4.973990979119772e-06, "loss": 0.1174, "step": 463890 }, { "epoch": 2.757517936646635, "grad_norm": 4.407188892364502, "learning_rate": 4.973783489822027e-06, "loss": 0.1252, "step": 463900 }, { "epoch": 2.757577378723303, "grad_norm": 3.0741770267486572, "learning_rate": 4.973576000569429e-06, "loss": 0.112, "step": 463910 }, { "epoch": 2.7576368207999717, "grad_norm": 5.010728359222412, "learning_rate": 4.973368511362339e-06, "loss": 0.1176, "step": 463920 }, { "epoch": 2.7576962628766397, "grad_norm": 3.7932276725769043, "learning_rate": 4.97316102220111e-06, "loss": 0.1171, "step": 463930 }, { "epoch": 2.757755704953308, "grad_norm": 3.9984700679779053, "learning_rate": 4.9729535330861004e-06, "loss": 0.112, "step": 463940 }, { "epoch": 2.7578151470299765, "grad_norm": 4.0409746170043945, "learning_rate": 4.9727460440176695e-06, "loss": 0.1221, "step": 463950 }, { "epoch": 2.757874589106645, "grad_norm": 4.590525150299072, "learning_rate": 4.972538554996173e-06, "loss": 0.1198, "step": 463960 }, { "epoch": 2.7579340311833134, "grad_norm": 4.526882171630859, "learning_rate": 4.9723310660219674e-06, "loss": 0.1142, "step": 463970 }, { "epoch": 2.757993473259982, "grad_norm": 3.7670273780822754, "learning_rate": 4.972123577095411e-06, "loss": 0.1244, "step": 463980 }, { "epoch": 2.75805291533665, "grad_norm": 3.831883668899536, "learning_rate": 4.971916088216862e-06, "loss": 0.1281, "step": 463990 }, { "epoch": 2.7581123574133186, "grad_norm": 3.0464351177215576, "learning_rate": 4.971708599386676e-06, "loss": 0.1204, "step": 464000 }, { "epoch": 2.758171799489987, "grad_norm": 3.446035623550415, "learning_rate": 4.9715011106052116e-06, "loss": 0.0957, "step": 464010 }, { "epoch": 2.7582312415666554, "grad_norm": 2.940119504928589, "learning_rate": 4.971293621872827e-06, "loss": 0.1103, "step": 464020 }, { "epoch": 2.758290683643324, "grad_norm": 4.383218288421631, "learning_rate": 4.971086133189876e-06, "loss": 0.1224, "step": 464030 }, { "epoch": 2.7583501257199923, "grad_norm": 3.5947647094726562, "learning_rate": 4.970878644556719e-06, "loss": 0.1131, "step": 464040 }, { "epoch": 2.7584095677966607, "grad_norm": 4.509481430053711, "learning_rate": 4.970671155973713e-06, "loss": 0.1191, "step": 464050 }, { "epoch": 2.7584690098733287, "grad_norm": 4.430421829223633, "learning_rate": 4.970463667441214e-06, "loss": 0.1133, "step": 464060 }, { "epoch": 2.7585284519499975, "grad_norm": 4.987292766571045, "learning_rate": 4.97025617895958e-06, "loss": 0.1165, "step": 464070 }, { "epoch": 2.7585878940266655, "grad_norm": 4.133506774902344, "learning_rate": 4.970048690529167e-06, "loss": 0.1213, "step": 464080 }, { "epoch": 2.7586473361033343, "grad_norm": 3.788158655166626, "learning_rate": 4.969841202150335e-06, "loss": 0.1243, "step": 464090 }, { "epoch": 2.7587067781800023, "grad_norm": 4.5918121337890625, "learning_rate": 4.969633713823442e-06, "loss": 0.114, "step": 464100 }, { "epoch": 2.7587662202566707, "grad_norm": 3.365973472595215, "learning_rate": 4.969426225548841e-06, "loss": 0.1382, "step": 464110 }, { "epoch": 2.758825662333339, "grad_norm": 3.7101995944976807, "learning_rate": 4.969218737326893e-06, "loss": 0.1173, "step": 464120 }, { "epoch": 2.7588851044100076, "grad_norm": 3.2433037757873535, "learning_rate": 4.969011249157954e-06, "loss": 0.0945, "step": 464130 }, { "epoch": 2.758944546486676, "grad_norm": 4.04192590713501, "learning_rate": 4.96880376104238e-06, "loss": 0.1235, "step": 464140 }, { "epoch": 2.7590039885633444, "grad_norm": 4.817596912384033, "learning_rate": 4.968596272980531e-06, "loss": 0.1115, "step": 464150 }, { "epoch": 2.759063430640013, "grad_norm": 3.6464121341705322, "learning_rate": 4.968388784972763e-06, "loss": 0.1217, "step": 464160 }, { "epoch": 2.759122872716681, "grad_norm": 3.948936939239502, "learning_rate": 4.968181297019431e-06, "loss": 0.1268, "step": 464170 }, { "epoch": 2.7591823147933496, "grad_norm": 2.997737407684326, "learning_rate": 4.967973809120898e-06, "loss": 0.1282, "step": 464180 }, { "epoch": 2.759241756870018, "grad_norm": 3.960954189300537, "learning_rate": 4.967766321277516e-06, "loss": 0.1112, "step": 464190 }, { "epoch": 2.7593011989466865, "grad_norm": 3.7741172313690186, "learning_rate": 4.967558833489644e-06, "loss": 0.1191, "step": 464200 }, { "epoch": 2.759360641023355, "grad_norm": 3.151503324508667, "learning_rate": 4.9673513457576406e-06, "loss": 0.1266, "step": 464210 }, { "epoch": 2.7594200831000233, "grad_norm": 4.64528226852417, "learning_rate": 4.967143858081862e-06, "loss": 0.1126, "step": 464220 }, { "epoch": 2.7594795251766917, "grad_norm": 3.275392532348633, "learning_rate": 4.966936370462664e-06, "loss": 0.1068, "step": 464230 }, { "epoch": 2.75953896725336, "grad_norm": 3.021906614303589, "learning_rate": 4.966728882900408e-06, "loss": 0.1238, "step": 464240 }, { "epoch": 2.759598409330028, "grad_norm": 4.031747817993164, "learning_rate": 4.966521395395447e-06, "loss": 0.1119, "step": 464250 }, { "epoch": 2.759657851406697, "grad_norm": 4.942668914794922, "learning_rate": 4.966313907948141e-06, "loss": 0.1266, "step": 464260 }, { "epoch": 2.759717293483365, "grad_norm": 4.061032772064209, "learning_rate": 4.966106420558846e-06, "loss": 0.1001, "step": 464270 }, { "epoch": 2.759776735560034, "grad_norm": 4.492160320281982, "learning_rate": 4.96589893322792e-06, "loss": 0.1232, "step": 464280 }, { "epoch": 2.7598361776367017, "grad_norm": 4.377471923828125, "learning_rate": 4.965691445955719e-06, "loss": 0.1182, "step": 464290 }, { "epoch": 2.75989561971337, "grad_norm": 5.3857245445251465, "learning_rate": 4.965483958742601e-06, "loss": 0.1174, "step": 464300 }, { "epoch": 2.7599550617900386, "grad_norm": 6.08078670501709, "learning_rate": 4.9652764715889255e-06, "loss": 0.1179, "step": 464310 }, { "epoch": 2.760014503866707, "grad_norm": 4.837711811065674, "learning_rate": 4.965068984495049e-06, "loss": 0.1113, "step": 464320 }, { "epoch": 2.7600739459433754, "grad_norm": 2.878603219985962, "learning_rate": 4.964861497461326e-06, "loss": 0.1075, "step": 464330 }, { "epoch": 2.760133388020044, "grad_norm": 3.9974844455718994, "learning_rate": 4.964654010488116e-06, "loss": 0.1118, "step": 464340 }, { "epoch": 2.7601928300967122, "grad_norm": 4.194814205169678, "learning_rate": 4.964446523575776e-06, "loss": 0.1227, "step": 464350 }, { "epoch": 2.7602522721733806, "grad_norm": 3.752138376235962, "learning_rate": 4.964239036724664e-06, "loss": 0.1208, "step": 464360 }, { "epoch": 2.760311714250049, "grad_norm": 4.113396167755127, "learning_rate": 4.9640315499351365e-06, "loss": 0.1322, "step": 464370 }, { "epoch": 2.7603711563267175, "grad_norm": 3.5541188716888428, "learning_rate": 4.963824063207551e-06, "loss": 0.0996, "step": 464380 }, { "epoch": 2.760430598403386, "grad_norm": 4.423258304595947, "learning_rate": 4.963616576542265e-06, "loss": 0.0951, "step": 464390 }, { "epoch": 2.7604900404800543, "grad_norm": 4.497560024261475, "learning_rate": 4.963409089939634e-06, "loss": 0.1205, "step": 464400 }, { "epoch": 2.7605494825567227, "grad_norm": 4.2684245109558105, "learning_rate": 4.963201603400019e-06, "loss": 0.104, "step": 464410 }, { "epoch": 2.760608924633391, "grad_norm": 3.8799567222595215, "learning_rate": 4.962994116923774e-06, "loss": 0.1169, "step": 464420 }, { "epoch": 2.7606683667100596, "grad_norm": 5.515173435211182, "learning_rate": 4.962786630511257e-06, "loss": 0.1032, "step": 464430 }, { "epoch": 2.7607278087867275, "grad_norm": 3.3688759803771973, "learning_rate": 4.962579144162828e-06, "loss": 0.1167, "step": 464440 }, { "epoch": 2.7607872508633964, "grad_norm": 4.057765007019043, "learning_rate": 4.962371657878841e-06, "loss": 0.106, "step": 464450 }, { "epoch": 2.7608466929400644, "grad_norm": 4.4930100440979, "learning_rate": 4.9621641716596534e-06, "loss": 0.1252, "step": 464460 }, { "epoch": 2.760906135016733, "grad_norm": 3.4386117458343506, "learning_rate": 4.961956685505626e-06, "loss": 0.1039, "step": 464470 }, { "epoch": 2.760965577093401, "grad_norm": 3.9759013652801514, "learning_rate": 4.961749199417112e-06, "loss": 0.1245, "step": 464480 }, { "epoch": 2.7610250191700696, "grad_norm": 4.345991611480713, "learning_rate": 4.96154171339447e-06, "loss": 0.1247, "step": 464490 }, { "epoch": 2.761084461246738, "grad_norm": 3.403287410736084, "learning_rate": 4.961334227438059e-06, "loss": 0.112, "step": 464500 }, { "epoch": 2.7611439033234064, "grad_norm": 3.761030435562134, "learning_rate": 4.9611267415482354e-06, "loss": 0.112, "step": 464510 }, { "epoch": 2.761203345400075, "grad_norm": 5.7647624015808105, "learning_rate": 4.9609192557253536e-06, "loss": 0.1261, "step": 464520 }, { "epoch": 2.7612627874767433, "grad_norm": 3.6062815189361572, "learning_rate": 4.960711769969774e-06, "loss": 0.1048, "step": 464530 }, { "epoch": 2.7613222295534117, "grad_norm": 4.119564533233643, "learning_rate": 4.960504284281855e-06, "loss": 0.1218, "step": 464540 }, { "epoch": 2.76138167163008, "grad_norm": 3.982712984085083, "learning_rate": 4.960296798661953e-06, "loss": 0.1056, "step": 464550 }, { "epoch": 2.7614411137067485, "grad_norm": 3.778921365737915, "learning_rate": 4.9600893131104224e-06, "loss": 0.1052, "step": 464560 }, { "epoch": 2.761500555783417, "grad_norm": 5.979579925537109, "learning_rate": 4.959881827627624e-06, "loss": 0.1089, "step": 464570 }, { "epoch": 2.7615599978600853, "grad_norm": 3.79254412651062, "learning_rate": 4.959674342213915e-06, "loss": 0.0972, "step": 464580 }, { "epoch": 2.7616194399367537, "grad_norm": 4.356969833374023, "learning_rate": 4.959466856869649e-06, "loss": 0.1157, "step": 464590 }, { "epoch": 2.761678882013422, "grad_norm": 3.2168641090393066, "learning_rate": 4.959259371595189e-06, "loss": 0.1236, "step": 464600 }, { "epoch": 2.7617383240900906, "grad_norm": 4.044371604919434, "learning_rate": 4.959051886390888e-06, "loss": 0.119, "step": 464610 }, { "epoch": 2.761797766166759, "grad_norm": 3.189516305923462, "learning_rate": 4.958844401257103e-06, "loss": 0.1075, "step": 464620 }, { "epoch": 2.761857208243427, "grad_norm": 3.052752733230591, "learning_rate": 4.958636916194194e-06, "loss": 0.1093, "step": 464630 }, { "epoch": 2.761916650320096, "grad_norm": 4.475424289703369, "learning_rate": 4.958429431202518e-06, "loss": 0.1143, "step": 464640 }, { "epoch": 2.761976092396764, "grad_norm": 3.4382054805755615, "learning_rate": 4.9582219462824304e-06, "loss": 0.1258, "step": 464650 }, { "epoch": 2.7620355344734326, "grad_norm": 3.753913640975952, "learning_rate": 4.95801446143429e-06, "loss": 0.1052, "step": 464660 }, { "epoch": 2.7620949765501006, "grad_norm": 3.963514566421509, "learning_rate": 4.957806976658454e-06, "loss": 0.1085, "step": 464670 }, { "epoch": 2.762154418626769, "grad_norm": 3.8758704662323, "learning_rate": 4.957599491955278e-06, "loss": 0.1029, "step": 464680 }, { "epoch": 2.7622138607034374, "grad_norm": 3.958648443222046, "learning_rate": 4.957392007325122e-06, "loss": 0.1085, "step": 464690 }, { "epoch": 2.762273302780106, "grad_norm": 4.006878852844238, "learning_rate": 4.957184522768343e-06, "loss": 0.1021, "step": 464700 }, { "epoch": 2.7623327448567743, "grad_norm": 4.879028797149658, "learning_rate": 4.956977038285295e-06, "loss": 0.1268, "step": 464710 }, { "epoch": 2.7623921869334427, "grad_norm": 4.40894889831543, "learning_rate": 4.956769553876339e-06, "loss": 0.1282, "step": 464720 }, { "epoch": 2.762451629010111, "grad_norm": 5.636590957641602, "learning_rate": 4.956562069541831e-06, "loss": 0.1218, "step": 464730 }, { "epoch": 2.7625110710867795, "grad_norm": 4.701584339141846, "learning_rate": 4.956354585282127e-06, "loss": 0.1127, "step": 464740 }, { "epoch": 2.762570513163448, "grad_norm": 4.06414794921875, "learning_rate": 4.956147101097587e-06, "loss": 0.129, "step": 464750 }, { "epoch": 2.7626299552401163, "grad_norm": 3.1918227672576904, "learning_rate": 4.955939616988566e-06, "loss": 0.1107, "step": 464760 }, { "epoch": 2.7626893973167848, "grad_norm": 5.990577697753906, "learning_rate": 4.9557321329554234e-06, "loss": 0.1291, "step": 464770 }, { "epoch": 2.762748839393453, "grad_norm": 5.126079559326172, "learning_rate": 4.955524648998515e-06, "loss": 0.1186, "step": 464780 }, { "epoch": 2.7628082814701216, "grad_norm": 3.1648669242858887, "learning_rate": 4.955317165118198e-06, "loss": 0.1091, "step": 464790 }, { "epoch": 2.7628677235467896, "grad_norm": 2.8592939376831055, "learning_rate": 4.955109681314831e-06, "loss": 0.1064, "step": 464800 }, { "epoch": 2.7629271656234584, "grad_norm": 4.152831554412842, "learning_rate": 4.95490219758877e-06, "loss": 0.1243, "step": 464810 }, { "epoch": 2.7629866077001264, "grad_norm": 4.539127826690674, "learning_rate": 4.9546947139403725e-06, "loss": 0.1299, "step": 464820 }, { "epoch": 2.7630460497767952, "grad_norm": 3.5730137825012207, "learning_rate": 4.954487230369996e-06, "loss": 0.112, "step": 464830 }, { "epoch": 2.763105491853463, "grad_norm": 4.722827911376953, "learning_rate": 4.954279746877999e-06, "loss": 0.0984, "step": 464840 }, { "epoch": 2.7631649339301316, "grad_norm": 4.093737602233887, "learning_rate": 4.954072263464736e-06, "loss": 0.1058, "step": 464850 }, { "epoch": 2.7632243760068, "grad_norm": 4.226071357727051, "learning_rate": 4.9538647801305674e-06, "loss": 0.1147, "step": 464860 }, { "epoch": 2.7632838180834685, "grad_norm": 4.511297702789307, "learning_rate": 4.95365729687585e-06, "loss": 0.1114, "step": 464870 }, { "epoch": 2.763343260160137, "grad_norm": 3.7332489490509033, "learning_rate": 4.953449813700938e-06, "loss": 0.1195, "step": 464880 }, { "epoch": 2.7634027022368053, "grad_norm": 4.661398887634277, "learning_rate": 4.953242330606192e-06, "loss": 0.1048, "step": 464890 }, { "epoch": 2.7634621443134737, "grad_norm": 4.208558559417725, "learning_rate": 4.953034847591969e-06, "loss": 0.0986, "step": 464900 }, { "epoch": 2.763521586390142, "grad_norm": 3.923978805541992, "learning_rate": 4.952827364658625e-06, "loss": 0.1042, "step": 464910 }, { "epoch": 2.7635810284668105, "grad_norm": 2.9166738986968994, "learning_rate": 4.952619881806517e-06, "loss": 0.1099, "step": 464920 }, { "epoch": 2.763640470543479, "grad_norm": 4.206735610961914, "learning_rate": 4.952412399036005e-06, "loss": 0.1254, "step": 464930 }, { "epoch": 2.7636999126201474, "grad_norm": 4.768402099609375, "learning_rate": 4.952204916347443e-06, "loss": 0.111, "step": 464940 }, { "epoch": 2.7637593546968158, "grad_norm": 4.6124114990234375, "learning_rate": 4.951997433741191e-06, "loss": 0.1114, "step": 464950 }, { "epoch": 2.763818796773484, "grad_norm": 4.1968841552734375, "learning_rate": 4.951789951217603e-06, "loss": 0.1178, "step": 464960 }, { "epoch": 2.7638782388501526, "grad_norm": 4.241523265838623, "learning_rate": 4.95158246877704e-06, "loss": 0.11, "step": 464970 }, { "epoch": 2.763937680926821, "grad_norm": 3.8958308696746826, "learning_rate": 4.9513749864198575e-06, "loss": 0.1102, "step": 464980 }, { "epoch": 2.763997123003489, "grad_norm": 5.97676944732666, "learning_rate": 4.951167504146413e-06, "loss": 0.1071, "step": 464990 }, { "epoch": 2.764056565080158, "grad_norm": 4.6456618309021, "learning_rate": 4.9509600219570645e-06, "loss": 0.114, "step": 465000 }, { "epoch": 2.764116007156826, "grad_norm": 3.5808987617492676, "learning_rate": 4.9507525398521685e-06, "loss": 0.1165, "step": 465010 }, { "epoch": 2.7641754492334947, "grad_norm": 3.596747875213623, "learning_rate": 4.9505450578320825e-06, "loss": 0.1061, "step": 465020 }, { "epoch": 2.7642348913101626, "grad_norm": 3.6468605995178223, "learning_rate": 4.950337575897164e-06, "loss": 0.127, "step": 465030 }, { "epoch": 2.764294333386831, "grad_norm": 4.8466644287109375, "learning_rate": 4.9501300940477705e-06, "loss": 0.1223, "step": 465040 }, { "epoch": 2.7643537754634995, "grad_norm": 3.1793019771575928, "learning_rate": 4.949922612284258e-06, "loss": 0.109, "step": 465050 }, { "epoch": 2.764413217540168, "grad_norm": 3.5912115573883057, "learning_rate": 4.9497151306069845e-06, "loss": 0.1047, "step": 465060 }, { "epoch": 2.7644726596168363, "grad_norm": 5.152711391448975, "learning_rate": 4.949507649016309e-06, "loss": 0.1139, "step": 465070 }, { "epoch": 2.7645321016935047, "grad_norm": 6.25532865524292, "learning_rate": 4.949300167512586e-06, "loss": 0.1146, "step": 465080 }, { "epoch": 2.764591543770173, "grad_norm": 5.541429042816162, "learning_rate": 4.949092686096174e-06, "loss": 0.1091, "step": 465090 }, { "epoch": 2.7646509858468415, "grad_norm": 2.419656753540039, "learning_rate": 4.948885204767432e-06, "loss": 0.1096, "step": 465100 }, { "epoch": 2.76471042792351, "grad_norm": 4.048853397369385, "learning_rate": 4.948677723526714e-06, "loss": 0.1072, "step": 465110 }, { "epoch": 2.7647698700001784, "grad_norm": 3.8609883785247803, "learning_rate": 4.9484702423743805e-06, "loss": 0.1283, "step": 465120 }, { "epoch": 2.764829312076847, "grad_norm": 2.876857280731201, "learning_rate": 4.948262761310787e-06, "loss": 0.1141, "step": 465130 }, { "epoch": 2.764888754153515, "grad_norm": 3.7406809329986572, "learning_rate": 4.94805528033629e-06, "loss": 0.101, "step": 465140 }, { "epoch": 2.7649481962301836, "grad_norm": 3.7298173904418945, "learning_rate": 4.94784779945125e-06, "loss": 0.1108, "step": 465150 }, { "epoch": 2.765007638306852, "grad_norm": 2.921405076980591, "learning_rate": 4.947640318656022e-06, "loss": 0.1239, "step": 465160 }, { "epoch": 2.7650670803835204, "grad_norm": 5.5196404457092285, "learning_rate": 4.947432837950962e-06, "loss": 0.1288, "step": 465170 }, { "epoch": 2.7651265224601884, "grad_norm": 3.229025363922119, "learning_rate": 4.947225357336427e-06, "loss": 0.122, "step": 465180 }, { "epoch": 2.7651859645368573, "grad_norm": 5.072630882263184, "learning_rate": 4.94701787681278e-06, "loss": 0.1145, "step": 465190 }, { "epoch": 2.7652454066135252, "grad_norm": 4.474319934844971, "learning_rate": 4.946810396380374e-06, "loss": 0.1011, "step": 465200 }, { "epoch": 2.765304848690194, "grad_norm": 4.299795150756836, "learning_rate": 4.946602916039566e-06, "loss": 0.1087, "step": 465210 }, { "epoch": 2.765364290766862, "grad_norm": 5.176789283752441, "learning_rate": 4.946395435790715e-06, "loss": 0.1261, "step": 465220 }, { "epoch": 2.7654237328435305, "grad_norm": 3.542224168777466, "learning_rate": 4.946187955634178e-06, "loss": 0.118, "step": 465230 }, { "epoch": 2.765483174920199, "grad_norm": 5.1372857093811035, "learning_rate": 4.94598047557031e-06, "loss": 0.1333, "step": 465240 }, { "epoch": 2.7655426169968673, "grad_norm": 4.500077724456787, "learning_rate": 4.945772995599471e-06, "loss": 0.1088, "step": 465250 }, { "epoch": 2.7656020590735357, "grad_norm": 3.507596015930176, "learning_rate": 4.945565515722018e-06, "loss": 0.1189, "step": 465260 }, { "epoch": 2.765661501150204, "grad_norm": 3.3235256671905518, "learning_rate": 4.945358035938306e-06, "loss": 0.1167, "step": 465270 }, { "epoch": 2.7657209432268726, "grad_norm": 2.5988261699676514, "learning_rate": 4.945150556248696e-06, "loss": 0.1044, "step": 465280 }, { "epoch": 2.765780385303541, "grad_norm": 2.9217374324798584, "learning_rate": 4.9449430766535425e-06, "loss": 0.1055, "step": 465290 }, { "epoch": 2.7658398273802094, "grad_norm": 4.0870490074157715, "learning_rate": 4.9447355971532026e-06, "loss": 0.1017, "step": 465300 }, { "epoch": 2.765899269456878, "grad_norm": 3.4165735244750977, "learning_rate": 4.944528117748035e-06, "loss": 0.1026, "step": 465310 }, { "epoch": 2.765958711533546, "grad_norm": 3.9541664123535156, "learning_rate": 4.944320638438398e-06, "loss": 0.1147, "step": 465320 }, { "epoch": 2.7660181536102146, "grad_norm": 4.517564296722412, "learning_rate": 4.944113159224646e-06, "loss": 0.1091, "step": 465330 }, { "epoch": 2.766077595686883, "grad_norm": 4.191429615020752, "learning_rate": 4.943905680107138e-06, "loss": 0.1108, "step": 465340 }, { "epoch": 2.7661370377635515, "grad_norm": 2.9997379779815674, "learning_rate": 4.943698201086232e-06, "loss": 0.1015, "step": 465350 }, { "epoch": 2.76619647984022, "grad_norm": 4.029117107391357, "learning_rate": 4.943490722162283e-06, "loss": 0.1201, "step": 465360 }, { "epoch": 2.766255921916888, "grad_norm": 4.376282215118408, "learning_rate": 4.943283243335651e-06, "loss": 0.1177, "step": 465370 }, { "epoch": 2.7663153639935567, "grad_norm": 4.474968910217285, "learning_rate": 4.9430757646066915e-06, "loss": 0.1224, "step": 465380 }, { "epoch": 2.7663748060702247, "grad_norm": 3.9374043941497803, "learning_rate": 4.942868285975762e-06, "loss": 0.1145, "step": 465390 }, { "epoch": 2.766434248146893, "grad_norm": 3.6200053691864014, "learning_rate": 4.94266080744322e-06, "loss": 0.1089, "step": 465400 }, { "epoch": 2.7664936902235615, "grad_norm": 3.5450050830841064, "learning_rate": 4.9424533290094225e-06, "loss": 0.1185, "step": 465410 }, { "epoch": 2.76655313230023, "grad_norm": 3.4573349952697754, "learning_rate": 4.942245850674729e-06, "loss": 0.0979, "step": 465420 }, { "epoch": 2.7666125743768983, "grad_norm": 2.912881374359131, "learning_rate": 4.942038372439494e-06, "loss": 0.1113, "step": 465430 }, { "epoch": 2.7666720164535668, "grad_norm": 4.191665172576904, "learning_rate": 4.941830894304075e-06, "loss": 0.0962, "step": 465440 }, { "epoch": 2.766731458530235, "grad_norm": 3.6919565200805664, "learning_rate": 4.941623416268832e-06, "loss": 0.1054, "step": 465450 }, { "epoch": 2.7667909006069036, "grad_norm": 3.3357319831848145, "learning_rate": 4.94141593833412e-06, "loss": 0.1086, "step": 465460 }, { "epoch": 2.766850342683572, "grad_norm": 3.6597557067871094, "learning_rate": 4.941208460500295e-06, "loss": 0.0972, "step": 465470 }, { "epoch": 2.7669097847602404, "grad_norm": 3.6672351360321045, "learning_rate": 4.941000982767718e-06, "loss": 0.1382, "step": 465480 }, { "epoch": 2.766969226836909, "grad_norm": 4.260461330413818, "learning_rate": 4.940793505136744e-06, "loss": 0.1158, "step": 465490 }, { "epoch": 2.7670286689135772, "grad_norm": 3.85384464263916, "learning_rate": 4.94058602760773e-06, "loss": 0.12, "step": 465500 }, { "epoch": 2.7670881109902457, "grad_norm": 3.866746664047241, "learning_rate": 4.940378550181035e-06, "loss": 0.123, "step": 465510 }, { "epoch": 2.767147553066914, "grad_norm": 3.705155611038208, "learning_rate": 4.940171072857014e-06, "loss": 0.1124, "step": 465520 }, { "epoch": 2.7672069951435825, "grad_norm": 2.948019504547119, "learning_rate": 4.9399635956360255e-06, "loss": 0.1194, "step": 465530 }, { "epoch": 2.7672664372202505, "grad_norm": 4.056697368621826, "learning_rate": 4.939756118518428e-06, "loss": 0.1101, "step": 465540 }, { "epoch": 2.7673258792969193, "grad_norm": 3.6766357421875, "learning_rate": 4.939548641504578e-06, "loss": 0.1076, "step": 465550 }, { "epoch": 2.7673853213735873, "grad_norm": 4.594836235046387, "learning_rate": 4.939341164594831e-06, "loss": 0.123, "step": 465560 }, { "epoch": 2.767444763450256, "grad_norm": 4.060235500335693, "learning_rate": 4.939133687789546e-06, "loss": 0.1224, "step": 465570 }, { "epoch": 2.767504205526924, "grad_norm": 2.8397555351257324, "learning_rate": 4.938926211089081e-06, "loss": 0.1081, "step": 465580 }, { "epoch": 2.7675636476035925, "grad_norm": 3.918396472930908, "learning_rate": 4.938718734493791e-06, "loss": 0.1121, "step": 465590 }, { "epoch": 2.767623089680261, "grad_norm": 3.830836057662964, "learning_rate": 4.938511258004036e-06, "loss": 0.114, "step": 465600 }, { "epoch": 2.7676825317569294, "grad_norm": 4.382833480834961, "learning_rate": 4.938303781620172e-06, "loss": 0.1143, "step": 465610 }, { "epoch": 2.7677419738335978, "grad_norm": 5.990304470062256, "learning_rate": 4.9380963053425535e-06, "loss": 0.1358, "step": 465620 }, { "epoch": 2.767801415910266, "grad_norm": 3.964038372039795, "learning_rate": 4.937888829171542e-06, "loss": 0.1257, "step": 465630 }, { "epoch": 2.7678608579869346, "grad_norm": 3.643174648284912, "learning_rate": 4.937681353107494e-06, "loss": 0.1099, "step": 465640 }, { "epoch": 2.767920300063603, "grad_norm": 3.7901666164398193, "learning_rate": 4.9374738771507665e-06, "loss": 0.1082, "step": 465650 }, { "epoch": 2.7679797421402714, "grad_norm": 3.384716272354126, "learning_rate": 4.937266401301717e-06, "loss": 0.1076, "step": 465660 }, { "epoch": 2.76803918421694, "grad_norm": 3.634899139404297, "learning_rate": 4.937058925560701e-06, "loss": 0.1121, "step": 465670 }, { "epoch": 2.7680986262936083, "grad_norm": 4.029586315155029, "learning_rate": 4.9368514499280776e-06, "loss": 0.1017, "step": 465680 }, { "epoch": 2.7681580683702767, "grad_norm": 4.466455936431885, "learning_rate": 4.936643974404203e-06, "loss": 0.0928, "step": 465690 }, { "epoch": 2.768217510446945, "grad_norm": 3.98720121383667, "learning_rate": 4.936436498989435e-06, "loss": 0.1114, "step": 465700 }, { "epoch": 2.7682769525236135, "grad_norm": 3.822650671005249, "learning_rate": 4.936229023684132e-06, "loss": 0.1258, "step": 465710 }, { "epoch": 2.768336394600282, "grad_norm": 2.9619619846343994, "learning_rate": 4.9360215484886496e-06, "loss": 0.1138, "step": 465720 }, { "epoch": 2.76839583667695, "grad_norm": 4.617504596710205, "learning_rate": 4.935814073403344e-06, "loss": 0.1222, "step": 465730 }, { "epoch": 2.7684552787536187, "grad_norm": 3.419498920440674, "learning_rate": 4.935606598428577e-06, "loss": 0.1178, "step": 465740 }, { "epoch": 2.7685147208302867, "grad_norm": 3.2001984119415283, "learning_rate": 4.935399123564702e-06, "loss": 0.1115, "step": 465750 }, { "epoch": 2.7685741629069556, "grad_norm": 4.148805141448975, "learning_rate": 4.935191648812077e-06, "loss": 0.1131, "step": 465760 }, { "epoch": 2.7686336049836235, "grad_norm": 5.597724914550781, "learning_rate": 4.934984174171061e-06, "loss": 0.1127, "step": 465770 }, { "epoch": 2.768693047060292, "grad_norm": 6.045796871185303, "learning_rate": 4.934776699642009e-06, "loss": 0.136, "step": 465780 }, { "epoch": 2.7687524891369604, "grad_norm": 3.8260600566864014, "learning_rate": 4.934569225225278e-06, "loss": 0.1046, "step": 465790 }, { "epoch": 2.768811931213629, "grad_norm": 3.580989360809326, "learning_rate": 4.934361750921229e-06, "loss": 0.1176, "step": 465800 }, { "epoch": 2.768871373290297, "grad_norm": 3.85693621635437, "learning_rate": 4.934154276730217e-06, "loss": 0.1073, "step": 465810 }, { "epoch": 2.7689308153669656, "grad_norm": 4.942022800445557, "learning_rate": 4.933946802652597e-06, "loss": 0.1213, "step": 465820 }, { "epoch": 2.768990257443634, "grad_norm": 3.7374320030212402, "learning_rate": 4.9337393286887295e-06, "loss": 0.1073, "step": 465830 }, { "epoch": 2.7690496995203024, "grad_norm": 5.661598205566406, "learning_rate": 4.933531854838969e-06, "loss": 0.1143, "step": 465840 }, { "epoch": 2.769109141596971, "grad_norm": 3.951411724090576, "learning_rate": 4.933324381103677e-06, "loss": 0.1043, "step": 465850 }, { "epoch": 2.7691685836736393, "grad_norm": 3.2074592113494873, "learning_rate": 4.933116907483207e-06, "loss": 0.1077, "step": 465860 }, { "epoch": 2.7692280257503077, "grad_norm": 4.6621294021606445, "learning_rate": 4.9329094339779195e-06, "loss": 0.1068, "step": 465870 }, { "epoch": 2.769287467826976, "grad_norm": 2.914048910140991, "learning_rate": 4.932701960588168e-06, "loss": 0.1039, "step": 465880 }, { "epoch": 2.7693469099036445, "grad_norm": 4.097919464111328, "learning_rate": 4.9324944873143125e-06, "loss": 0.1083, "step": 465890 }, { "epoch": 2.769406351980313, "grad_norm": 3.322187662124634, "learning_rate": 4.93228701415671e-06, "loss": 0.1245, "step": 465900 }, { "epoch": 2.7694657940569813, "grad_norm": 4.764212131500244, "learning_rate": 4.932079541115718e-06, "loss": 0.1462, "step": 465910 }, { "epoch": 2.7695252361336493, "grad_norm": 4.607606887817383, "learning_rate": 4.931872068191691e-06, "loss": 0.111, "step": 465920 }, { "epoch": 2.769584678210318, "grad_norm": 5.140447616577148, "learning_rate": 4.931664595384991e-06, "loss": 0.1141, "step": 465930 }, { "epoch": 2.769644120286986, "grad_norm": 4.249772071838379, "learning_rate": 4.931457122695972e-06, "loss": 0.1051, "step": 465940 }, { "epoch": 2.769703562363655, "grad_norm": 3.607386350631714, "learning_rate": 4.9312496501249905e-06, "loss": 0.1048, "step": 465950 }, { "epoch": 2.769763004440323, "grad_norm": 3.7316970825195312, "learning_rate": 4.931042177672406e-06, "loss": 0.1137, "step": 465960 }, { "epoch": 2.7698224465169914, "grad_norm": 3.4224050045013428, "learning_rate": 4.9308347053385755e-06, "loss": 0.0942, "step": 465970 }, { "epoch": 2.76988188859366, "grad_norm": 3.49396014213562, "learning_rate": 4.9306272331238556e-06, "loss": 0.1064, "step": 465980 }, { "epoch": 2.769941330670328, "grad_norm": 2.645254135131836, "learning_rate": 4.9304197610286046e-06, "loss": 0.0857, "step": 465990 }, { "epoch": 2.7700007727469966, "grad_norm": 4.300670623779297, "learning_rate": 4.930212289053178e-06, "loss": 0.1106, "step": 466000 }, { "epoch": 2.770060214823665, "grad_norm": 2.815953493118286, "learning_rate": 4.930004817197934e-06, "loss": 0.1016, "step": 466010 }, { "epoch": 2.7701196569003335, "grad_norm": 3.893904209136963, "learning_rate": 4.929797345463231e-06, "loss": 0.1206, "step": 466020 }, { "epoch": 2.770179098977002, "grad_norm": 4.1336798667907715, "learning_rate": 4.929589873849426e-06, "loss": 0.1146, "step": 466030 }, { "epoch": 2.7702385410536703, "grad_norm": 5.112504005432129, "learning_rate": 4.929382402356874e-06, "loss": 0.1232, "step": 466040 }, { "epoch": 2.7702979831303387, "grad_norm": 4.891811847686768, "learning_rate": 4.929174930985934e-06, "loss": 0.1103, "step": 466050 }, { "epoch": 2.770357425207007, "grad_norm": 3.271472215652466, "learning_rate": 4.928967459736962e-06, "loss": 0.1209, "step": 466060 }, { "epoch": 2.7704168672836755, "grad_norm": 3.660926103591919, "learning_rate": 4.92875998861032e-06, "loss": 0.1142, "step": 466070 }, { "epoch": 2.770476309360344, "grad_norm": 2.900543212890625, "learning_rate": 4.92855251760636e-06, "loss": 0.1094, "step": 466080 }, { "epoch": 2.7705357514370124, "grad_norm": 3.5938899517059326, "learning_rate": 4.92834504672544e-06, "loss": 0.1198, "step": 466090 }, { "epoch": 2.7705951935136808, "grad_norm": 4.079477787017822, "learning_rate": 4.92813757596792e-06, "loss": 0.1112, "step": 466100 }, { "epoch": 2.7706546355903487, "grad_norm": 3.613903284072876, "learning_rate": 4.9279301053341555e-06, "loss": 0.1169, "step": 466110 }, { "epoch": 2.7707140776670176, "grad_norm": 3.363215684890747, "learning_rate": 4.9277226348245036e-06, "loss": 0.1162, "step": 466120 }, { "epoch": 2.7707735197436856, "grad_norm": 3.4485743045806885, "learning_rate": 4.927515164439322e-06, "loss": 0.1014, "step": 466130 }, { "epoch": 2.770832961820354, "grad_norm": 2.7781875133514404, "learning_rate": 4.927307694178968e-06, "loss": 0.108, "step": 466140 }, { "epoch": 2.7708924038970224, "grad_norm": 3.5815722942352295, "learning_rate": 4.927100224043798e-06, "loss": 0.1124, "step": 466150 }, { "epoch": 2.770951845973691, "grad_norm": 4.058068752288818, "learning_rate": 4.926892754034172e-06, "loss": 0.1156, "step": 466160 }, { "epoch": 2.7710112880503592, "grad_norm": 4.6447434425354, "learning_rate": 4.926685284150444e-06, "loss": 0.1168, "step": 466170 }, { "epoch": 2.7710707301270276, "grad_norm": 5.196345806121826, "learning_rate": 4.926477814392973e-06, "loss": 0.1232, "step": 466180 }, { "epoch": 2.771130172203696, "grad_norm": 4.279179573059082, "learning_rate": 4.926270344762116e-06, "loss": 0.1142, "step": 466190 }, { "epoch": 2.7711896142803645, "grad_norm": 3.8644559383392334, "learning_rate": 4.926062875258231e-06, "loss": 0.1199, "step": 466200 }, { "epoch": 2.771249056357033, "grad_norm": 5.109377384185791, "learning_rate": 4.925855405881673e-06, "loss": 0.1159, "step": 466210 }, { "epoch": 2.7713084984337013, "grad_norm": 3.5883383750915527, "learning_rate": 4.9256479366328015e-06, "loss": 0.0933, "step": 466220 }, { "epoch": 2.7713679405103697, "grad_norm": 5.1999077796936035, "learning_rate": 4.925440467511974e-06, "loss": 0.1134, "step": 466230 }, { "epoch": 2.771427382587038, "grad_norm": 4.837931156158447, "learning_rate": 4.925232998519545e-06, "loss": 0.1141, "step": 466240 }, { "epoch": 2.7714868246637065, "grad_norm": 4.614994049072266, "learning_rate": 4.9250255296558754e-06, "loss": 0.1055, "step": 466250 }, { "epoch": 2.771546266740375, "grad_norm": 3.6585679054260254, "learning_rate": 4.924818060921321e-06, "loss": 0.115, "step": 466260 }, { "epoch": 2.7716057088170434, "grad_norm": 4.137085914611816, "learning_rate": 4.924610592316238e-06, "loss": 0.1159, "step": 466270 }, { "epoch": 2.7716651508937113, "grad_norm": 3.1459012031555176, "learning_rate": 4.924403123840982e-06, "loss": 0.1036, "step": 466280 }, { "epoch": 2.77172459297038, "grad_norm": 4.312201976776123, "learning_rate": 4.924195655495916e-06, "loss": 0.1128, "step": 466290 }, { "epoch": 2.771784035047048, "grad_norm": 4.2104878425598145, "learning_rate": 4.923988187281394e-06, "loss": 0.1109, "step": 466300 }, { "epoch": 2.771843477123717, "grad_norm": 3.9861435890197754, "learning_rate": 4.923780719197774e-06, "loss": 0.1045, "step": 466310 }, { "epoch": 2.771902919200385, "grad_norm": 3.5046160221099854, "learning_rate": 4.92357325124541e-06, "loss": 0.1281, "step": 466320 }, { "epoch": 2.7719623612770534, "grad_norm": 4.910998821258545, "learning_rate": 4.9233657834246644e-06, "loss": 0.1063, "step": 466330 }, { "epoch": 2.772021803353722, "grad_norm": 3.8199284076690674, "learning_rate": 4.923158315735892e-06, "loss": 0.1201, "step": 466340 }, { "epoch": 2.7720812454303903, "grad_norm": 3.8975813388824463, "learning_rate": 4.922950848179449e-06, "loss": 0.1263, "step": 466350 }, { "epoch": 2.7721406875070587, "grad_norm": 3.82102108001709, "learning_rate": 4.9227433807556946e-06, "loss": 0.1015, "step": 466360 }, { "epoch": 2.772200129583727, "grad_norm": 4.011967182159424, "learning_rate": 4.9225359134649855e-06, "loss": 0.1348, "step": 466370 }, { "epoch": 2.7722595716603955, "grad_norm": 3.3867714405059814, "learning_rate": 4.9223284463076774e-06, "loss": 0.1125, "step": 466380 }, { "epoch": 2.772319013737064, "grad_norm": 5.647648811340332, "learning_rate": 4.922120979284131e-06, "loss": 0.1176, "step": 466390 }, { "epoch": 2.7723784558137323, "grad_norm": 6.564865589141846, "learning_rate": 4.9219135123947006e-06, "loss": 0.1168, "step": 466400 }, { "epoch": 2.7724378978904007, "grad_norm": 3.634675979614258, "learning_rate": 4.921706045639743e-06, "loss": 0.1215, "step": 466410 }, { "epoch": 2.772497339967069, "grad_norm": 4.467921257019043, "learning_rate": 4.921498579019619e-06, "loss": 0.1196, "step": 466420 }, { "epoch": 2.7725567820437376, "grad_norm": 3.8716323375701904, "learning_rate": 4.921291112534684e-06, "loss": 0.1053, "step": 466430 }, { "epoch": 2.772616224120406, "grad_norm": 3.730250835418701, "learning_rate": 4.921083646185293e-06, "loss": 0.1182, "step": 466440 }, { "epoch": 2.7726756661970744, "grad_norm": 4.648647308349609, "learning_rate": 4.9208761799718075e-06, "loss": 0.1286, "step": 466450 }, { "epoch": 2.772735108273743, "grad_norm": 3.033435583114624, "learning_rate": 4.920668713894582e-06, "loss": 0.1152, "step": 466460 }, { "epoch": 2.772794550350411, "grad_norm": 3.5538322925567627, "learning_rate": 4.920461247953974e-06, "loss": 0.1106, "step": 466470 }, { "epoch": 2.7728539924270796, "grad_norm": 3.3880062103271484, "learning_rate": 4.920253782150341e-06, "loss": 0.1249, "step": 466480 }, { "epoch": 2.7729134345037476, "grad_norm": 3.581987142562866, "learning_rate": 4.920046316484041e-06, "loss": 0.1079, "step": 466490 }, { "epoch": 2.7729728765804165, "grad_norm": 3.933905839920044, "learning_rate": 4.9198388509554294e-06, "loss": 0.0984, "step": 466500 }, { "epoch": 2.7730323186570844, "grad_norm": 3.869732618331909, "learning_rate": 4.919631385564866e-06, "loss": 0.1135, "step": 466510 }, { "epoch": 2.773091760733753, "grad_norm": 2.8147497177124023, "learning_rate": 4.919423920312707e-06, "loss": 0.1218, "step": 466520 }, { "epoch": 2.7731512028104213, "grad_norm": 2.196939706802368, "learning_rate": 4.919216455199311e-06, "loss": 0.1068, "step": 466530 }, { "epoch": 2.7732106448870897, "grad_norm": 4.250954627990723, "learning_rate": 4.919008990225032e-06, "loss": 0.1185, "step": 466540 }, { "epoch": 2.773270086963758, "grad_norm": 4.712130546569824, "learning_rate": 4.9188015253902295e-06, "loss": 0.1133, "step": 466550 }, { "epoch": 2.7733295290404265, "grad_norm": 5.460550308227539, "learning_rate": 4.918594060695261e-06, "loss": 0.1036, "step": 466560 }, { "epoch": 2.773388971117095, "grad_norm": 3.9758682250976562, "learning_rate": 4.918386596140482e-06, "loss": 0.1135, "step": 466570 }, { "epoch": 2.7734484131937633, "grad_norm": 3.4106554985046387, "learning_rate": 4.918179131726253e-06, "loss": 0.1069, "step": 466580 }, { "epoch": 2.7735078552704318, "grad_norm": 3.2793922424316406, "learning_rate": 4.917971667452929e-06, "loss": 0.1034, "step": 466590 }, { "epoch": 2.7735672973471, "grad_norm": 4.929951190948486, "learning_rate": 4.917764203320866e-06, "loss": 0.1205, "step": 466600 }, { "epoch": 2.7736267394237686, "grad_norm": 4.059508323669434, "learning_rate": 4.917556739330424e-06, "loss": 0.0942, "step": 466610 }, { "epoch": 2.773686181500437, "grad_norm": 4.251457691192627, "learning_rate": 4.91734927548196e-06, "loss": 0.1119, "step": 466620 }, { "epoch": 2.7737456235771054, "grad_norm": 3.896437406539917, "learning_rate": 4.917141811775828e-06, "loss": 0.094, "step": 466630 }, { "epoch": 2.773805065653774, "grad_norm": 4.862120628356934, "learning_rate": 4.916934348212389e-06, "loss": 0.142, "step": 466640 }, { "epoch": 2.7738645077304422, "grad_norm": 3.6470322608947754, "learning_rate": 4.916726884792e-06, "loss": 0.1147, "step": 466650 }, { "epoch": 2.77392394980711, "grad_norm": 4.958187103271484, "learning_rate": 4.916519421515015e-06, "loss": 0.1048, "step": 466660 }, { "epoch": 2.773983391883779, "grad_norm": 4.7036051750183105, "learning_rate": 4.916311958381795e-06, "loss": 0.1198, "step": 466670 }, { "epoch": 2.774042833960447, "grad_norm": 3.761791229248047, "learning_rate": 4.9161044953926965e-06, "loss": 0.1012, "step": 466680 }, { "epoch": 2.774102276037116, "grad_norm": 4.845783233642578, "learning_rate": 4.915897032548074e-06, "loss": 0.1026, "step": 466690 }, { "epoch": 2.774161718113784, "grad_norm": 3.575956344604492, "learning_rate": 4.915689569848289e-06, "loss": 0.1071, "step": 466700 }, { "epoch": 2.7742211601904523, "grad_norm": 3.4286725521087646, "learning_rate": 4.915482107293695e-06, "loss": 0.1017, "step": 466710 }, { "epoch": 2.7742806022671207, "grad_norm": 3.571531057357788, "learning_rate": 4.91527464488465e-06, "loss": 0.1095, "step": 466720 }, { "epoch": 2.774340044343789, "grad_norm": 4.204495906829834, "learning_rate": 4.915067182621514e-06, "loss": 0.109, "step": 466730 }, { "epoch": 2.7743994864204575, "grad_norm": 3.956326484680176, "learning_rate": 4.914859720504641e-06, "loss": 0.1029, "step": 466740 }, { "epoch": 2.774458928497126, "grad_norm": 4.176898002624512, "learning_rate": 4.914652258534391e-06, "loss": 0.1141, "step": 466750 }, { "epoch": 2.7745183705737944, "grad_norm": 3.60172700881958, "learning_rate": 4.914444796711121e-06, "loss": 0.1094, "step": 466760 }, { "epoch": 2.7745778126504628, "grad_norm": 3.2865636348724365, "learning_rate": 4.914237335035185e-06, "loss": 0.1188, "step": 466770 }, { "epoch": 2.774637254727131, "grad_norm": 3.4726202487945557, "learning_rate": 4.914029873506944e-06, "loss": 0.1056, "step": 466780 }, { "epoch": 2.7746966968037996, "grad_norm": 4.146294116973877, "learning_rate": 4.913822412126753e-06, "loss": 0.1027, "step": 466790 }, { "epoch": 2.774756138880468, "grad_norm": 3.9936535358428955, "learning_rate": 4.91361495089497e-06, "loss": 0.1158, "step": 466800 }, { "epoch": 2.7748155809571364, "grad_norm": 3.686234474182129, "learning_rate": 4.913407489811954e-06, "loss": 0.119, "step": 466810 }, { "epoch": 2.774875023033805, "grad_norm": 3.203723907470703, "learning_rate": 4.913200028878059e-06, "loss": 0.117, "step": 466820 }, { "epoch": 2.7749344651104733, "grad_norm": 4.031996250152588, "learning_rate": 4.912992568093645e-06, "loss": 0.1041, "step": 466830 }, { "epoch": 2.7749939071871417, "grad_norm": 3.8766579627990723, "learning_rate": 4.912785107459067e-06, "loss": 0.1243, "step": 466840 }, { "epoch": 2.7750533492638096, "grad_norm": 4.678055286407471, "learning_rate": 4.912577646974685e-06, "loss": 0.1027, "step": 466850 }, { "epoch": 2.7751127913404785, "grad_norm": 3.600898027420044, "learning_rate": 4.912370186640853e-06, "loss": 0.1173, "step": 466860 }, { "epoch": 2.7751722334171465, "grad_norm": 3.867776393890381, "learning_rate": 4.91216272645793e-06, "loss": 0.1143, "step": 466870 }, { "epoch": 2.775231675493815, "grad_norm": 4.34747838973999, "learning_rate": 4.911955266426275e-06, "loss": 0.1157, "step": 466880 }, { "epoch": 2.7752911175704833, "grad_norm": 4.321902751922607, "learning_rate": 4.911747806546242e-06, "loss": 0.1198, "step": 466890 }, { "epoch": 2.7753505596471517, "grad_norm": 6.674001693725586, "learning_rate": 4.911540346818191e-06, "loss": 0.1202, "step": 466900 }, { "epoch": 2.77541000172382, "grad_norm": 3.972520112991333, "learning_rate": 4.911332887242478e-06, "loss": 0.1212, "step": 466910 }, { "epoch": 2.7754694438004885, "grad_norm": 4.4612603187561035, "learning_rate": 4.911125427819459e-06, "loss": 0.1117, "step": 466920 }, { "epoch": 2.775528885877157, "grad_norm": 4.731198787689209, "learning_rate": 4.910917968549494e-06, "loss": 0.1405, "step": 466930 }, { "epoch": 2.7755883279538254, "grad_norm": 4.262990474700928, "learning_rate": 4.910710509432936e-06, "loss": 0.1086, "step": 466940 }, { "epoch": 2.775647770030494, "grad_norm": 2.657329559326172, "learning_rate": 4.910503050470148e-06, "loss": 0.1006, "step": 466950 }, { "epoch": 2.775707212107162, "grad_norm": 4.654330253601074, "learning_rate": 4.910295591661483e-06, "loss": 0.1294, "step": 466960 }, { "epoch": 2.7757666541838306, "grad_norm": 4.243803977966309, "learning_rate": 4.910088133007301e-06, "loss": 0.1117, "step": 466970 }, { "epoch": 2.775826096260499, "grad_norm": 5.330277919769287, "learning_rate": 4.909880674507958e-06, "loss": 0.1007, "step": 466980 }, { "epoch": 2.7758855383371674, "grad_norm": 4.274940013885498, "learning_rate": 4.909673216163811e-06, "loss": 0.1045, "step": 466990 }, { "epoch": 2.775944980413836, "grad_norm": 4.096452236175537, "learning_rate": 4.909465757975217e-06, "loss": 0.1213, "step": 467000 }, { "epoch": 2.7760044224905043, "grad_norm": 5.80108118057251, "learning_rate": 4.909258299942534e-06, "loss": 0.1193, "step": 467010 }, { "epoch": 2.7760638645671722, "grad_norm": 3.894223690032959, "learning_rate": 4.90905084206612e-06, "loss": 0.113, "step": 467020 }, { "epoch": 2.776123306643841, "grad_norm": 3.258854866027832, "learning_rate": 4.908843384346329e-06, "loss": 0.1173, "step": 467030 }, { "epoch": 2.776182748720509, "grad_norm": 4.93324089050293, "learning_rate": 4.908635926783522e-06, "loss": 0.127, "step": 467040 }, { "epoch": 2.776242190797178, "grad_norm": 6.281327247619629, "learning_rate": 4.908428469378056e-06, "loss": 0.122, "step": 467050 }, { "epoch": 2.776301632873846, "grad_norm": 3.320019006729126, "learning_rate": 4.908221012130285e-06, "loss": 0.1124, "step": 467060 }, { "epoch": 2.7763610749505143, "grad_norm": 4.680756092071533, "learning_rate": 4.908013555040569e-06, "loss": 0.1068, "step": 467070 }, { "epoch": 2.7764205170271827, "grad_norm": 4.50827169418335, "learning_rate": 4.907806098109265e-06, "loss": 0.1046, "step": 467080 }, { "epoch": 2.776479959103851, "grad_norm": 3.6752185821533203, "learning_rate": 4.90759864133673e-06, "loss": 0.1033, "step": 467090 }, { "epoch": 2.7765394011805196, "grad_norm": 3.375086784362793, "learning_rate": 4.907391184723321e-06, "loss": 0.1057, "step": 467100 }, { "epoch": 2.776598843257188, "grad_norm": 3.6213884353637695, "learning_rate": 4.907183728269396e-06, "loss": 0.1051, "step": 467110 }, { "epoch": 2.7766582853338564, "grad_norm": 4.072994709014893, "learning_rate": 4.90697627197531e-06, "loss": 0.1256, "step": 467120 }, { "epoch": 2.776717727410525, "grad_norm": 3.6825082302093506, "learning_rate": 4.906768815841423e-06, "loss": 0.1329, "step": 467130 }, { "epoch": 2.776777169487193, "grad_norm": 4.505693435668945, "learning_rate": 4.906561359868093e-06, "loss": 0.1144, "step": 467140 }, { "epoch": 2.7768366115638616, "grad_norm": 4.371670246124268, "learning_rate": 4.906353904055673e-06, "loss": 0.1016, "step": 467150 }, { "epoch": 2.77689605364053, "grad_norm": 3.8683292865753174, "learning_rate": 4.90614644840452e-06, "loss": 0.1252, "step": 467160 }, { "epoch": 2.7769554957171985, "grad_norm": 4.255249977111816, "learning_rate": 4.905938992914999e-06, "loss": 0.1205, "step": 467170 }, { "epoch": 2.777014937793867, "grad_norm": 4.897097587585449, "learning_rate": 4.905731537587461e-06, "loss": 0.1264, "step": 467180 }, { "epoch": 2.7770743798705353, "grad_norm": 3.3065547943115234, "learning_rate": 4.9055240824222635e-06, "loss": 0.1094, "step": 467190 }, { "epoch": 2.7771338219472037, "grad_norm": 4.51890230178833, "learning_rate": 4.905316627419766e-06, "loss": 0.118, "step": 467200 }, { "epoch": 2.7771932640238717, "grad_norm": 4.410037517547607, "learning_rate": 4.905109172580325e-06, "loss": 0.1113, "step": 467210 }, { "epoch": 2.7772527061005405, "grad_norm": 4.203620433807373, "learning_rate": 4.904901717904295e-06, "loss": 0.1157, "step": 467220 }, { "epoch": 2.7773121481772085, "grad_norm": 4.199764728546143, "learning_rate": 4.904694263392038e-06, "loss": 0.1232, "step": 467230 }, { "epoch": 2.7773715902538774, "grad_norm": 5.6995673179626465, "learning_rate": 4.904486809043909e-06, "loss": 0.1256, "step": 467240 }, { "epoch": 2.7774310323305453, "grad_norm": 3.9175093173980713, "learning_rate": 4.904279354860263e-06, "loss": 0.1126, "step": 467250 }, { "epoch": 2.7774904744072137, "grad_norm": 5.378482341766357, "learning_rate": 4.904071900841461e-06, "loss": 0.1229, "step": 467260 }, { "epoch": 2.777549916483882, "grad_norm": 4.668127059936523, "learning_rate": 4.903864446987858e-06, "loss": 0.1017, "step": 467270 }, { "epoch": 2.7776093585605506, "grad_norm": 4.24578857421875, "learning_rate": 4.903656993299811e-06, "loss": 0.1192, "step": 467280 }, { "epoch": 2.777668800637219, "grad_norm": 4.901589393615723, "learning_rate": 4.903449539777679e-06, "loss": 0.1206, "step": 467290 }, { "epoch": 2.7777282427138874, "grad_norm": 3.4310660362243652, "learning_rate": 4.903242086421819e-06, "loss": 0.0977, "step": 467300 }, { "epoch": 2.777787684790556, "grad_norm": 3.933945417404175, "learning_rate": 4.903034633232587e-06, "loss": 0.1045, "step": 467310 }, { "epoch": 2.7778471268672242, "grad_norm": 3.9426190853118896, "learning_rate": 4.902827180210342e-06, "loss": 0.1026, "step": 467320 }, { "epoch": 2.7779065689438927, "grad_norm": 3.480513572692871, "learning_rate": 4.902619727355439e-06, "loss": 0.115, "step": 467330 }, { "epoch": 2.777966011020561, "grad_norm": 5.036212921142578, "learning_rate": 4.902412274668236e-06, "loss": 0.1329, "step": 467340 }, { "epoch": 2.7780254530972295, "grad_norm": 4.141851902008057, "learning_rate": 4.902204822149092e-06, "loss": 0.0954, "step": 467350 }, { "epoch": 2.778084895173898, "grad_norm": 3.4970943927764893, "learning_rate": 4.901997369798363e-06, "loss": 0.1007, "step": 467360 }, { "epoch": 2.7781443372505663, "grad_norm": 4.844405174255371, "learning_rate": 4.9017899176164045e-06, "loss": 0.1147, "step": 467370 }, { "epoch": 2.7782037793272347, "grad_norm": 3.8930346965789795, "learning_rate": 4.901582465603576e-06, "loss": 0.1115, "step": 467380 }, { "epoch": 2.778263221403903, "grad_norm": 2.9397711753845215, "learning_rate": 4.901375013760234e-06, "loss": 0.1108, "step": 467390 }, { "epoch": 2.778322663480571, "grad_norm": 3.8339455127716064, "learning_rate": 4.9011675620867375e-06, "loss": 0.125, "step": 467400 }, { "epoch": 2.77838210555724, "grad_norm": 5.303319454193115, "learning_rate": 4.900960110583442e-06, "loss": 0.1156, "step": 467410 }, { "epoch": 2.778441547633908, "grad_norm": 6.265697956085205, "learning_rate": 4.900752659250704e-06, "loss": 0.1327, "step": 467420 }, { "epoch": 2.778500989710577, "grad_norm": 4.306171417236328, "learning_rate": 4.900545208088883e-06, "loss": 0.1096, "step": 467430 }, { "epoch": 2.7785604317872448, "grad_norm": 3.894578456878662, "learning_rate": 4.9003377570983346e-06, "loss": 0.1078, "step": 467440 }, { "epoch": 2.778619873863913, "grad_norm": 3.7162575721740723, "learning_rate": 4.900130306279416e-06, "loss": 0.1034, "step": 467450 }, { "epoch": 2.7786793159405816, "grad_norm": 3.2305705547332764, "learning_rate": 4.899922855632485e-06, "loss": 0.1014, "step": 467460 }, { "epoch": 2.77873875801725, "grad_norm": 3.2689714431762695, "learning_rate": 4.8997154051579e-06, "loss": 0.1037, "step": 467470 }, { "epoch": 2.7787982000939184, "grad_norm": 3.0029749870300293, "learning_rate": 4.899507954856015e-06, "loss": 0.1035, "step": 467480 }, { "epoch": 2.778857642170587, "grad_norm": 3.651029586791992, "learning_rate": 4.8993005047271905e-06, "loss": 0.1189, "step": 467490 }, { "epoch": 2.7789170842472553, "grad_norm": 3.856149435043335, "learning_rate": 4.899093054771783e-06, "loss": 0.119, "step": 467500 }, { "epoch": 2.7789765263239237, "grad_norm": 4.817999362945557, "learning_rate": 4.898885604990148e-06, "loss": 0.1165, "step": 467510 }, { "epoch": 2.779035968400592, "grad_norm": 5.0520548820495605, "learning_rate": 4.898678155382645e-06, "loss": 0.1206, "step": 467520 }, { "epoch": 2.7790954104772605, "grad_norm": 4.419726848602295, "learning_rate": 4.89847070594963e-06, "loss": 0.103, "step": 467530 }, { "epoch": 2.779154852553929, "grad_norm": 3.6506600379943848, "learning_rate": 4.89826325669146e-06, "loss": 0.1005, "step": 467540 }, { "epoch": 2.7792142946305973, "grad_norm": 5.021672248840332, "learning_rate": 4.898055807608494e-06, "loss": 0.1038, "step": 467550 }, { "epoch": 2.7792737367072657, "grad_norm": 4.210975646972656, "learning_rate": 4.897848358701088e-06, "loss": 0.1044, "step": 467560 }, { "epoch": 2.779333178783934, "grad_norm": 2.95284366607666, "learning_rate": 4.897640909969598e-06, "loss": 0.1025, "step": 467570 }, { "epoch": 2.7793926208606026, "grad_norm": 3.2989072799682617, "learning_rate": 4.897433461414384e-06, "loss": 0.1039, "step": 467580 }, { "epoch": 2.7794520629372705, "grad_norm": 5.375068187713623, "learning_rate": 4.897226013035801e-06, "loss": 0.1221, "step": 467590 }, { "epoch": 2.7795115050139394, "grad_norm": 3.510711193084717, "learning_rate": 4.897018564834205e-06, "loss": 0.1022, "step": 467600 }, { "epoch": 2.7795709470906074, "grad_norm": 4.428198337554932, "learning_rate": 4.896811116809958e-06, "loss": 0.1115, "step": 467610 }, { "epoch": 2.779630389167276, "grad_norm": 3.4731054306030273, "learning_rate": 4.896603668963414e-06, "loss": 0.1223, "step": 467620 }, { "epoch": 2.779689831243944, "grad_norm": 4.479861259460449, "learning_rate": 4.896396221294931e-06, "loss": 0.1209, "step": 467630 }, { "epoch": 2.7797492733206126, "grad_norm": 4.001132965087891, "learning_rate": 4.896188773804867e-06, "loss": 0.103, "step": 467640 }, { "epoch": 2.779808715397281, "grad_norm": 3.8650062084198, "learning_rate": 4.895981326493576e-06, "loss": 0.1089, "step": 467650 }, { "epoch": 2.7798681574739494, "grad_norm": 3.624382972717285, "learning_rate": 4.895773879361419e-06, "loss": 0.1223, "step": 467660 }, { "epoch": 2.779927599550618, "grad_norm": 4.973717212677002, "learning_rate": 4.895566432408752e-06, "loss": 0.1193, "step": 467670 }, { "epoch": 2.7799870416272863, "grad_norm": 4.176441192626953, "learning_rate": 4.8953589856359315e-06, "loss": 0.1176, "step": 467680 }, { "epoch": 2.7800464837039547, "grad_norm": 4.154496669769287, "learning_rate": 4.895151539043316e-06, "loss": 0.1064, "step": 467690 }, { "epoch": 2.780105925780623, "grad_norm": 2.8819773197174072, "learning_rate": 4.894944092631262e-06, "loss": 0.1082, "step": 467700 }, { "epoch": 2.7801653678572915, "grad_norm": 5.120970726013184, "learning_rate": 4.894736646400126e-06, "loss": 0.1119, "step": 467710 }, { "epoch": 2.78022480993396, "grad_norm": 4.782548427581787, "learning_rate": 4.894529200350267e-06, "loss": 0.1173, "step": 467720 }, { "epoch": 2.7802842520106283, "grad_norm": 3.2465031147003174, "learning_rate": 4.894321754482041e-06, "loss": 0.102, "step": 467730 }, { "epoch": 2.7803436940872968, "grad_norm": 5.576354026794434, "learning_rate": 4.8941143087958045e-06, "loss": 0.1203, "step": 467740 }, { "epoch": 2.780403136163965, "grad_norm": 2.614464521408081, "learning_rate": 4.893906863291917e-06, "loss": 0.1104, "step": 467750 }, { "epoch": 2.780462578240633, "grad_norm": 4.485827445983887, "learning_rate": 4.893699417970735e-06, "loss": 0.1139, "step": 467760 }, { "epoch": 2.780522020317302, "grad_norm": 3.951564311981201, "learning_rate": 4.893491972832614e-06, "loss": 0.1127, "step": 467770 }, { "epoch": 2.78058146239397, "grad_norm": 3.345280885696411, "learning_rate": 4.893284527877913e-06, "loss": 0.1094, "step": 467780 }, { "epoch": 2.780640904470639, "grad_norm": 3.401641607284546, "learning_rate": 4.893077083106989e-06, "loss": 0.1208, "step": 467790 }, { "epoch": 2.780700346547307, "grad_norm": 4.565747261047363, "learning_rate": 4.892869638520199e-06, "loss": 0.1242, "step": 467800 }, { "epoch": 2.780759788623975, "grad_norm": 3.6210548877716064, "learning_rate": 4.8926621941179e-06, "loss": 0.1151, "step": 467810 }, { "epoch": 2.7808192307006436, "grad_norm": 5.296708106994629, "learning_rate": 4.892454749900448e-06, "loss": 0.1092, "step": 467820 }, { "epoch": 2.780878672777312, "grad_norm": 4.447207927703857, "learning_rate": 4.892247305868203e-06, "loss": 0.1185, "step": 467830 }, { "epoch": 2.7809381148539805, "grad_norm": 4.874751091003418, "learning_rate": 4.892039862021521e-06, "loss": 0.1074, "step": 467840 }, { "epoch": 2.780997556930649, "grad_norm": 4.7215166091918945, "learning_rate": 4.89183241836076e-06, "loss": 0.1102, "step": 467850 }, { "epoch": 2.7810569990073173, "grad_norm": 5.531233310699463, "learning_rate": 4.891624974886276e-06, "loss": 0.1114, "step": 467860 }, { "epoch": 2.7811164410839857, "grad_norm": 3.358769178390503, "learning_rate": 4.891417531598427e-06, "loss": 0.1118, "step": 467870 }, { "epoch": 2.781175883160654, "grad_norm": 4.5842766761779785, "learning_rate": 4.891210088497569e-06, "loss": 0.11, "step": 467880 }, { "epoch": 2.7812353252373225, "grad_norm": 3.819079637527466, "learning_rate": 4.891002645584062e-06, "loss": 0.1143, "step": 467890 }, { "epoch": 2.781294767313991, "grad_norm": 3.8716530799865723, "learning_rate": 4.8907952028582595e-06, "loss": 0.1135, "step": 467900 }, { "epoch": 2.7813542093906594, "grad_norm": 4.047731399536133, "learning_rate": 4.890587760320522e-06, "loss": 0.1307, "step": 467910 }, { "epoch": 2.7814136514673278, "grad_norm": 3.0948550701141357, "learning_rate": 4.890380317971205e-06, "loss": 0.1025, "step": 467920 }, { "epoch": 2.781473093543996, "grad_norm": 5.122787952423096, "learning_rate": 4.890172875810666e-06, "loss": 0.1212, "step": 467930 }, { "epoch": 2.7815325356206646, "grad_norm": 3.7212576866149902, "learning_rate": 4.889965433839262e-06, "loss": 0.1125, "step": 467940 }, { "epoch": 2.7815919776973326, "grad_norm": 2.9875478744506836, "learning_rate": 4.889757992057352e-06, "loss": 0.1112, "step": 467950 }, { "epoch": 2.7816514197740014, "grad_norm": 4.508127689361572, "learning_rate": 4.889550550465291e-06, "loss": 0.1129, "step": 467960 }, { "epoch": 2.7817108618506694, "grad_norm": 4.123607158660889, "learning_rate": 4.889343109063437e-06, "loss": 0.1049, "step": 467970 }, { "epoch": 2.7817703039273383, "grad_norm": 3.57476806640625, "learning_rate": 4.889135667852148e-06, "loss": 0.1074, "step": 467980 }, { "epoch": 2.7818297460040062, "grad_norm": 3.5818123817443848, "learning_rate": 4.88892822683178e-06, "loss": 0.1099, "step": 467990 }, { "epoch": 2.7818891880806746, "grad_norm": 4.0072550773620605, "learning_rate": 4.888720786002691e-06, "loss": 0.1009, "step": 468000 }, { "epoch": 2.781948630157343, "grad_norm": 3.7994542121887207, "learning_rate": 4.888513345365239e-06, "loss": 0.1106, "step": 468010 }, { "epoch": 2.7820080722340115, "grad_norm": 2.9022955894470215, "learning_rate": 4.888305904919779e-06, "loss": 0.1158, "step": 468020 }, { "epoch": 2.78206751431068, "grad_norm": 4.963068008422852, "learning_rate": 4.88809846466667e-06, "loss": 0.0998, "step": 468030 }, { "epoch": 2.7821269563873483, "grad_norm": 4.071284294128418, "learning_rate": 4.887891024606267e-06, "loss": 0.1016, "step": 468040 }, { "epoch": 2.7821863984640167, "grad_norm": 4.15974235534668, "learning_rate": 4.887683584738932e-06, "loss": 0.1239, "step": 468050 }, { "epoch": 2.782245840540685, "grad_norm": 4.39642858505249, "learning_rate": 4.887476145065018e-06, "loss": 0.1156, "step": 468060 }, { "epoch": 2.7823052826173535, "grad_norm": 4.40395975112915, "learning_rate": 4.887268705584883e-06, "loss": 0.1103, "step": 468070 }, { "epoch": 2.782364724694022, "grad_norm": 3.7120938301086426, "learning_rate": 4.887061266298886e-06, "loss": 0.1246, "step": 468080 }, { "epoch": 2.7824241667706904, "grad_norm": 3.740508794784546, "learning_rate": 4.8868538272073825e-06, "loss": 0.0998, "step": 468090 }, { "epoch": 2.782483608847359, "grad_norm": 4.465287208557129, "learning_rate": 4.88664638831073e-06, "loss": 0.1087, "step": 468100 }, { "epoch": 2.782543050924027, "grad_norm": 4.54323673248291, "learning_rate": 4.886438949609286e-06, "loss": 0.107, "step": 468110 }, { "epoch": 2.7826024930006956, "grad_norm": 3.1801280975341797, "learning_rate": 4.886231511103408e-06, "loss": 0.1125, "step": 468120 }, { "epoch": 2.782661935077364, "grad_norm": 3.9672279357910156, "learning_rate": 4.886024072793452e-06, "loss": 0.1196, "step": 468130 }, { "epoch": 2.782721377154032, "grad_norm": 3.5961813926696777, "learning_rate": 4.885816634679777e-06, "loss": 0.1068, "step": 468140 }, { "epoch": 2.782780819230701, "grad_norm": 3.6288177967071533, "learning_rate": 4.88560919676274e-06, "loss": 0.1156, "step": 468150 }, { "epoch": 2.782840261307369, "grad_norm": 3.9617695808410645, "learning_rate": 4.8854017590426955e-06, "loss": 0.1397, "step": 468160 }, { "epoch": 2.7828997033840377, "grad_norm": 4.844553470611572, "learning_rate": 4.885194321520005e-06, "loss": 0.1016, "step": 468170 }, { "epoch": 2.7829591454607057, "grad_norm": 3.978938341140747, "learning_rate": 4.884986884195023e-06, "loss": 0.1147, "step": 468180 }, { "epoch": 2.783018587537374, "grad_norm": 3.8824100494384766, "learning_rate": 4.8847794470681056e-06, "loss": 0.1118, "step": 468190 }, { "epoch": 2.7830780296140425, "grad_norm": 4.198099136352539, "learning_rate": 4.884572010139614e-06, "loss": 0.1227, "step": 468200 }, { "epoch": 2.783137471690711, "grad_norm": 4.517045021057129, "learning_rate": 4.8843645734099024e-06, "loss": 0.1154, "step": 468210 }, { "epoch": 2.7831969137673793, "grad_norm": 4.849107265472412, "learning_rate": 4.884157136879329e-06, "loss": 0.1185, "step": 468220 }, { "epoch": 2.7832563558440477, "grad_norm": 3.3198022842407227, "learning_rate": 4.88394970054825e-06, "loss": 0.1151, "step": 468230 }, { "epoch": 2.783315797920716, "grad_norm": 3.9695074558258057, "learning_rate": 4.883742264417024e-06, "loss": 0.1193, "step": 468240 }, { "epoch": 2.7833752399973846, "grad_norm": 4.32492733001709, "learning_rate": 4.883534828486008e-06, "loss": 0.114, "step": 468250 }, { "epoch": 2.783434682074053, "grad_norm": 4.103063583374023, "learning_rate": 4.8833273927555565e-06, "loss": 0.1079, "step": 468260 }, { "epoch": 2.7834941241507214, "grad_norm": 4.184012413024902, "learning_rate": 4.883119957226032e-06, "loss": 0.113, "step": 468270 }, { "epoch": 2.78355356622739, "grad_norm": 3.636484146118164, "learning_rate": 4.882912521897788e-06, "loss": 0.1185, "step": 468280 }, { "epoch": 2.7836130083040582, "grad_norm": 4.609264373779297, "learning_rate": 4.882705086771182e-06, "loss": 0.1136, "step": 468290 }, { "epoch": 2.7836724503807266, "grad_norm": 5.415352821350098, "learning_rate": 4.882497651846573e-06, "loss": 0.1312, "step": 468300 }, { "epoch": 2.783731892457395, "grad_norm": 4.624558925628662, "learning_rate": 4.882290217124317e-06, "loss": 0.1078, "step": 468310 }, { "epoch": 2.7837913345340635, "grad_norm": 3.740729331970215, "learning_rate": 4.882082782604772e-06, "loss": 0.1161, "step": 468320 }, { "epoch": 2.7838507766107314, "grad_norm": 2.9812638759613037, "learning_rate": 4.8818753482882925e-06, "loss": 0.1086, "step": 468330 }, { "epoch": 2.7839102186874003, "grad_norm": 5.361647605895996, "learning_rate": 4.881667914175239e-06, "loss": 0.0978, "step": 468340 }, { "epoch": 2.7839696607640683, "grad_norm": 4.184146404266357, "learning_rate": 4.881460480265968e-06, "loss": 0.1143, "step": 468350 }, { "epoch": 2.7840291028407367, "grad_norm": 4.1712727546691895, "learning_rate": 4.881253046560834e-06, "loss": 0.1029, "step": 468360 }, { "epoch": 2.784088544917405, "grad_norm": 5.369566917419434, "learning_rate": 4.881045613060198e-06, "loss": 0.1114, "step": 468370 }, { "epoch": 2.7841479869940735, "grad_norm": 3.8549957275390625, "learning_rate": 4.880838179764416e-06, "loss": 0.113, "step": 468380 }, { "epoch": 2.784207429070742, "grad_norm": 3.805480718612671, "learning_rate": 4.880630746673843e-06, "loss": 0.1259, "step": 468390 }, { "epoch": 2.7842668711474103, "grad_norm": 5.111527442932129, "learning_rate": 4.880423313788841e-06, "loss": 0.1181, "step": 468400 }, { "epoch": 2.7843263132240788, "grad_norm": 4.48232889175415, "learning_rate": 4.8802158811097625e-06, "loss": 0.1209, "step": 468410 }, { "epoch": 2.784385755300747, "grad_norm": 4.76036262512207, "learning_rate": 4.880008448636966e-06, "loss": 0.114, "step": 468420 }, { "epoch": 2.7844451973774156, "grad_norm": 4.720437049865723, "learning_rate": 4.87980101637081e-06, "loss": 0.1117, "step": 468430 }, { "epoch": 2.784504639454084, "grad_norm": 4.846737861633301, "learning_rate": 4.8795935843116525e-06, "loss": 0.1115, "step": 468440 }, { "epoch": 2.7845640815307524, "grad_norm": 2.813091516494751, "learning_rate": 4.8793861524598465e-06, "loss": 0.1075, "step": 468450 }, { "epoch": 2.784623523607421, "grad_norm": 2.7290921211242676, "learning_rate": 4.879178720815753e-06, "loss": 0.1198, "step": 468460 }, { "epoch": 2.7846829656840892, "grad_norm": 2.8761208057403564, "learning_rate": 4.878971289379729e-06, "loss": 0.1289, "step": 468470 }, { "epoch": 2.7847424077607577, "grad_norm": 3.846615791320801, "learning_rate": 4.878763858152129e-06, "loss": 0.1109, "step": 468480 }, { "epoch": 2.784801849837426, "grad_norm": 3.8540260791778564, "learning_rate": 4.878556427133313e-06, "loss": 0.1148, "step": 468490 }, { "epoch": 2.784861291914094, "grad_norm": 4.196475028991699, "learning_rate": 4.8783489963236375e-06, "loss": 0.1208, "step": 468500 }, { "epoch": 2.784920733990763, "grad_norm": 3.5140998363494873, "learning_rate": 4.87814156572346e-06, "loss": 0.1053, "step": 468510 }, { "epoch": 2.784980176067431, "grad_norm": 4.0235419273376465, "learning_rate": 4.877934135333136e-06, "loss": 0.1155, "step": 468520 }, { "epoch": 2.7850396181440997, "grad_norm": 4.06764554977417, "learning_rate": 4.8777267051530255e-06, "loss": 0.1085, "step": 468530 }, { "epoch": 2.7850990602207677, "grad_norm": 3.544017791748047, "learning_rate": 4.877519275183484e-06, "loss": 0.132, "step": 468540 }, { "epoch": 2.785158502297436, "grad_norm": 4.506570816040039, "learning_rate": 4.877311845424868e-06, "loss": 0.1254, "step": 468550 }, { "epoch": 2.7852179443741045, "grad_norm": 4.053557872772217, "learning_rate": 4.877104415877536e-06, "loss": 0.1105, "step": 468560 }, { "epoch": 2.785277386450773, "grad_norm": 5.173896312713623, "learning_rate": 4.876896986541846e-06, "loss": 0.1364, "step": 468570 }, { "epoch": 2.7853368285274414, "grad_norm": 3.4226245880126953, "learning_rate": 4.876689557418153e-06, "loss": 0.1012, "step": 468580 }, { "epoch": 2.7853962706041098, "grad_norm": 4.207767009735107, "learning_rate": 4.876482128506816e-06, "loss": 0.1082, "step": 468590 }, { "epoch": 2.785455712680778, "grad_norm": 3.3926093578338623, "learning_rate": 4.876274699808191e-06, "loss": 0.1167, "step": 468600 }, { "epoch": 2.7855151547574466, "grad_norm": 5.0362749099731445, "learning_rate": 4.876067271322635e-06, "loss": 0.1144, "step": 468610 }, { "epoch": 2.785574596834115, "grad_norm": 2.8569135665893555, "learning_rate": 4.875859843050506e-06, "loss": 0.1045, "step": 468620 }, { "epoch": 2.7856340389107834, "grad_norm": 4.519301414489746, "learning_rate": 4.875652414992163e-06, "loss": 0.1306, "step": 468630 }, { "epoch": 2.785693480987452, "grad_norm": 3.390329599380493, "learning_rate": 4.8754449871479595e-06, "loss": 0.1038, "step": 468640 }, { "epoch": 2.7857529230641203, "grad_norm": 5.047579288482666, "learning_rate": 4.875237559518255e-06, "loss": 0.1269, "step": 468650 }, { "epoch": 2.7858123651407887, "grad_norm": 4.457874298095703, "learning_rate": 4.875030132103408e-06, "loss": 0.135, "step": 468660 }, { "epoch": 2.785871807217457, "grad_norm": 3.9339990615844727, "learning_rate": 4.874822704903772e-06, "loss": 0.1164, "step": 468670 }, { "epoch": 2.7859312492941255, "grad_norm": 4.2097978591918945, "learning_rate": 4.874615277919707e-06, "loss": 0.102, "step": 468680 }, { "epoch": 2.7859906913707935, "grad_norm": 2.844043493270874, "learning_rate": 4.874407851151569e-06, "loss": 0.1221, "step": 468690 }, { "epoch": 2.7860501334474623, "grad_norm": 3.800412178039551, "learning_rate": 4.874200424599714e-06, "loss": 0.1194, "step": 468700 }, { "epoch": 2.7861095755241303, "grad_norm": 3.492879629135132, "learning_rate": 4.8739929982645035e-06, "loss": 0.1243, "step": 468710 }, { "epoch": 2.786169017600799, "grad_norm": 4.0204315185546875, "learning_rate": 4.873785572146291e-06, "loss": 0.1028, "step": 468720 }, { "epoch": 2.786228459677467, "grad_norm": 4.078978061676025, "learning_rate": 4.873578146245436e-06, "loss": 0.1217, "step": 468730 }, { "epoch": 2.7862879017541355, "grad_norm": 3.7443459033966064, "learning_rate": 4.873370720562294e-06, "loss": 0.109, "step": 468740 }, { "epoch": 2.786347343830804, "grad_norm": 4.612126350402832, "learning_rate": 4.873163295097221e-06, "loss": 0.1048, "step": 468750 }, { "epoch": 2.7864067859074724, "grad_norm": 3.7317099571228027, "learning_rate": 4.872955869850578e-06, "loss": 0.0963, "step": 468760 }, { "epoch": 2.786466227984141, "grad_norm": 3.5852952003479004, "learning_rate": 4.8727484448227205e-06, "loss": 0.0967, "step": 468770 }, { "epoch": 2.786525670060809, "grad_norm": 3.9274439811706543, "learning_rate": 4.872541020014004e-06, "loss": 0.1149, "step": 468780 }, { "epoch": 2.7865851121374776, "grad_norm": 5.00513219833374, "learning_rate": 4.872333595424788e-06, "loss": 0.114, "step": 468790 }, { "epoch": 2.786644554214146, "grad_norm": 4.746484756469727, "learning_rate": 4.872126171055428e-06, "loss": 0.118, "step": 468800 }, { "epoch": 2.7867039962908144, "grad_norm": 4.1536760330200195, "learning_rate": 4.871918746906282e-06, "loss": 0.1191, "step": 468810 }, { "epoch": 2.786763438367483, "grad_norm": 2.7458910942077637, "learning_rate": 4.871711322977708e-06, "loss": 0.1044, "step": 468820 }, { "epoch": 2.7868228804441513, "grad_norm": 3.842580795288086, "learning_rate": 4.871503899270062e-06, "loss": 0.1106, "step": 468830 }, { "epoch": 2.7868823225208197, "grad_norm": 2.8750956058502197, "learning_rate": 4.871296475783701e-06, "loss": 0.0983, "step": 468840 }, { "epoch": 2.786941764597488, "grad_norm": 4.162415027618408, "learning_rate": 4.871089052518983e-06, "loss": 0.1084, "step": 468850 }, { "epoch": 2.7870012066741565, "grad_norm": 4.6605095863342285, "learning_rate": 4.870881629476266e-06, "loss": 0.1087, "step": 468860 }, { "epoch": 2.787060648750825, "grad_norm": 3.6242825984954834, "learning_rate": 4.870674206655905e-06, "loss": 0.1215, "step": 468870 }, { "epoch": 2.787120090827493, "grad_norm": 3.63278865814209, "learning_rate": 4.870466784058259e-06, "loss": 0.1092, "step": 468880 }, { "epoch": 2.7871795329041618, "grad_norm": 4.932302474975586, "learning_rate": 4.870259361683685e-06, "loss": 0.1166, "step": 468890 }, { "epoch": 2.7872389749808297, "grad_norm": 5.1579084396362305, "learning_rate": 4.870051939532539e-06, "loss": 0.128, "step": 468900 }, { "epoch": 2.7872984170574986, "grad_norm": 3.6069905757904053, "learning_rate": 4.8698445176051804e-06, "loss": 0.0979, "step": 468910 }, { "epoch": 2.7873578591341666, "grad_norm": 5.092668056488037, "learning_rate": 4.8696370959019625e-06, "loss": 0.0979, "step": 468920 }, { "epoch": 2.787417301210835, "grad_norm": 3.276169776916504, "learning_rate": 4.869429674423247e-06, "loss": 0.1194, "step": 468930 }, { "epoch": 2.7874767432875034, "grad_norm": 3.0616390705108643, "learning_rate": 4.869222253169388e-06, "loss": 0.1095, "step": 468940 }, { "epoch": 2.787536185364172, "grad_norm": 6.126681327819824, "learning_rate": 4.8690148321407454e-06, "loss": 0.1143, "step": 468950 }, { "epoch": 2.78759562744084, "grad_norm": 2.5686304569244385, "learning_rate": 4.8688074113376745e-06, "loss": 0.1032, "step": 468960 }, { "epoch": 2.7876550695175086, "grad_norm": 3.4062445163726807, "learning_rate": 4.868599990760533e-06, "loss": 0.1018, "step": 468970 }, { "epoch": 2.787714511594177, "grad_norm": 4.487679481506348, "learning_rate": 4.868392570409678e-06, "loss": 0.1081, "step": 468980 }, { "epoch": 2.7877739536708455, "grad_norm": 4.028254985809326, "learning_rate": 4.868185150285466e-06, "loss": 0.1148, "step": 468990 }, { "epoch": 2.787833395747514, "grad_norm": 5.613663196563721, "learning_rate": 4.867977730388256e-06, "loss": 0.1065, "step": 469000 }, { "epoch": 2.7878928378241823, "grad_norm": 3.3560402393341064, "learning_rate": 4.867770310718403e-06, "loss": 0.1094, "step": 469010 }, { "epoch": 2.7879522799008507, "grad_norm": 3.808943748474121, "learning_rate": 4.8675628912762665e-06, "loss": 0.1203, "step": 469020 }, { "epoch": 2.788011721977519, "grad_norm": 4.061663627624512, "learning_rate": 4.867355472062202e-06, "loss": 0.1165, "step": 469030 }, { "epoch": 2.7880711640541875, "grad_norm": 3.251969814300537, "learning_rate": 4.867148053076566e-06, "loss": 0.1031, "step": 469040 }, { "epoch": 2.788130606130856, "grad_norm": 3.808680534362793, "learning_rate": 4.866940634319719e-06, "loss": 0.107, "step": 469050 }, { "epoch": 2.7881900482075244, "grad_norm": 3.7311112880706787, "learning_rate": 4.866733215792016e-06, "loss": 0.124, "step": 469060 }, { "epoch": 2.7882494902841923, "grad_norm": 3.282836437225342, "learning_rate": 4.866525797493812e-06, "loss": 0.1066, "step": 469070 }, { "epoch": 2.788308932360861, "grad_norm": 3.0382773876190186, "learning_rate": 4.866318379425468e-06, "loss": 0.0923, "step": 469080 }, { "epoch": 2.788368374437529, "grad_norm": 3.511776924133301, "learning_rate": 4.86611096158734e-06, "loss": 0.1054, "step": 469090 }, { "epoch": 2.7884278165141976, "grad_norm": 5.121464252471924, "learning_rate": 4.8659035439797835e-06, "loss": 0.1037, "step": 469100 }, { "epoch": 2.788487258590866, "grad_norm": 4.714363098144531, "learning_rate": 4.865696126603159e-06, "loss": 0.1257, "step": 469110 }, { "epoch": 2.7885467006675344, "grad_norm": 3.6925153732299805, "learning_rate": 4.86548870945782e-06, "loss": 0.1168, "step": 469120 }, { "epoch": 2.788606142744203, "grad_norm": 3.151111602783203, "learning_rate": 4.8652812925441265e-06, "loss": 0.1014, "step": 469130 }, { "epoch": 2.7886655848208712, "grad_norm": 6.181517601013184, "learning_rate": 4.8650738758624324e-06, "loss": 0.1216, "step": 469140 }, { "epoch": 2.7887250268975396, "grad_norm": 5.033046245574951, "learning_rate": 4.8648664594131e-06, "loss": 0.0949, "step": 469150 }, { "epoch": 2.788784468974208, "grad_norm": 3.5270798206329346, "learning_rate": 4.864659043196484e-06, "loss": 0.1284, "step": 469160 }, { "epoch": 2.7888439110508765, "grad_norm": 3.3047897815704346, "learning_rate": 4.864451627212939e-06, "loss": 0.1015, "step": 469170 }, { "epoch": 2.788903353127545, "grad_norm": 5.207473278045654, "learning_rate": 4.864244211462826e-06, "loss": 0.1138, "step": 469180 }, { "epoch": 2.7889627952042133, "grad_norm": 3.3500945568084717, "learning_rate": 4.864036795946501e-06, "loss": 0.1233, "step": 469190 }, { "epoch": 2.7890222372808817, "grad_norm": 4.538349151611328, "learning_rate": 4.86382938066432e-06, "loss": 0.1109, "step": 469200 }, { "epoch": 2.78908167935755, "grad_norm": 3.4078168869018555, "learning_rate": 4.863621965616641e-06, "loss": 0.1166, "step": 469210 }, { "epoch": 2.7891411214342186, "grad_norm": 3.186992645263672, "learning_rate": 4.863414550803822e-06, "loss": 0.1115, "step": 469220 }, { "epoch": 2.789200563510887, "grad_norm": 3.9085237979888916, "learning_rate": 4.863207136226218e-06, "loss": 0.1206, "step": 469230 }, { "epoch": 2.789260005587555, "grad_norm": 3.271170139312744, "learning_rate": 4.862999721884189e-06, "loss": 0.1162, "step": 469240 }, { "epoch": 2.789319447664224, "grad_norm": 3.1799349784851074, "learning_rate": 4.862792307778091e-06, "loss": 0.1128, "step": 469250 }, { "epoch": 2.7893788897408918, "grad_norm": 2.5272107124328613, "learning_rate": 4.86258489390828e-06, "loss": 0.0958, "step": 469260 }, { "epoch": 2.7894383318175606, "grad_norm": 3.743987798690796, "learning_rate": 4.862377480275115e-06, "loss": 0.0959, "step": 469270 }, { "epoch": 2.7894977738942286, "grad_norm": 4.178755760192871, "learning_rate": 4.862170066878952e-06, "loss": 0.121, "step": 469280 }, { "epoch": 2.789557215970897, "grad_norm": 4.8327107429504395, "learning_rate": 4.861962653720148e-06, "loss": 0.1156, "step": 469290 }, { "epoch": 2.7896166580475654, "grad_norm": 2.744544744491577, "learning_rate": 4.861755240799062e-06, "loss": 0.1051, "step": 469300 }, { "epoch": 2.789676100124234, "grad_norm": 4.182109832763672, "learning_rate": 4.86154782811605e-06, "loss": 0.109, "step": 469310 }, { "epoch": 2.7897355422009023, "grad_norm": 4.642516136169434, "learning_rate": 4.861340415671468e-06, "loss": 0.1172, "step": 469320 }, { "epoch": 2.7897949842775707, "grad_norm": 3.1398844718933105, "learning_rate": 4.861133003465675e-06, "loss": 0.123, "step": 469330 }, { "epoch": 2.789854426354239, "grad_norm": 3.7716763019561768, "learning_rate": 4.8609255914990274e-06, "loss": 0.1171, "step": 469340 }, { "epoch": 2.7899138684309075, "grad_norm": 4.050588607788086, "learning_rate": 4.860718179771882e-06, "loss": 0.116, "step": 469350 }, { "epoch": 2.789973310507576, "grad_norm": 3.7709178924560547, "learning_rate": 4.860510768284597e-06, "loss": 0.1021, "step": 469360 }, { "epoch": 2.7900327525842443, "grad_norm": 3.9179089069366455, "learning_rate": 4.860303357037528e-06, "loss": 0.1134, "step": 469370 }, { "epoch": 2.7900921946609127, "grad_norm": 4.126029014587402, "learning_rate": 4.860095946031035e-06, "loss": 0.1039, "step": 469380 }, { "epoch": 2.790151636737581, "grad_norm": 4.168161869049072, "learning_rate": 4.859888535265473e-06, "loss": 0.1212, "step": 469390 }, { "epoch": 2.7902110788142496, "grad_norm": 3.3049206733703613, "learning_rate": 4.859681124741199e-06, "loss": 0.1165, "step": 469400 }, { "epoch": 2.790270520890918, "grad_norm": 3.0703186988830566, "learning_rate": 4.859473714458572e-06, "loss": 0.1089, "step": 469410 }, { "epoch": 2.7903299629675864, "grad_norm": 4.91261100769043, "learning_rate": 4.859266304417948e-06, "loss": 0.1103, "step": 469420 }, { "epoch": 2.7903894050442544, "grad_norm": 4.584282398223877, "learning_rate": 4.859058894619683e-06, "loss": 0.1015, "step": 469430 }, { "epoch": 2.7904488471209232, "grad_norm": 3.9534754753112793, "learning_rate": 4.858851485064137e-06, "loss": 0.1076, "step": 469440 }, { "epoch": 2.790508289197591, "grad_norm": 2.7603557109832764, "learning_rate": 4.858644075751665e-06, "loss": 0.1084, "step": 469450 }, { "epoch": 2.79056773127426, "grad_norm": 3.1961679458618164, "learning_rate": 4.858436666682624e-06, "loss": 0.0908, "step": 469460 }, { "epoch": 2.790627173350928, "grad_norm": 3.6882691383361816, "learning_rate": 4.858229257857372e-06, "loss": 0.1214, "step": 469470 }, { "epoch": 2.7906866154275964, "grad_norm": 4.201930999755859, "learning_rate": 4.858021849276267e-06, "loss": 0.0982, "step": 469480 }, { "epoch": 2.790746057504265, "grad_norm": 3.6549460887908936, "learning_rate": 4.857814440939665e-06, "loss": 0.0936, "step": 469490 }, { "epoch": 2.7908054995809333, "grad_norm": 2.6778600215911865, "learning_rate": 4.857607032847923e-06, "loss": 0.1156, "step": 469500 }, { "epoch": 2.7908649416576017, "grad_norm": 3.4864273071289062, "learning_rate": 4.857399625001399e-06, "loss": 0.1033, "step": 469510 }, { "epoch": 2.79092438373427, "grad_norm": 5.226397514343262, "learning_rate": 4.857192217400449e-06, "loss": 0.1009, "step": 469520 }, { "epoch": 2.7909838258109385, "grad_norm": 3.3073570728302, "learning_rate": 4.856984810045433e-06, "loss": 0.1131, "step": 469530 }, { "epoch": 2.791043267887607, "grad_norm": 4.481941223144531, "learning_rate": 4.8567774029367056e-06, "loss": 0.1126, "step": 469540 }, { "epoch": 2.7911027099642753, "grad_norm": 3.7664809226989746, "learning_rate": 4.856569996074623e-06, "loss": 0.1051, "step": 469550 }, { "epoch": 2.7911621520409438, "grad_norm": 4.328706741333008, "learning_rate": 4.856362589459545e-06, "loss": 0.0996, "step": 469560 }, { "epoch": 2.791221594117612, "grad_norm": 3.9823553562164307, "learning_rate": 4.856155183091829e-06, "loss": 0.1197, "step": 469570 }, { "epoch": 2.7912810361942806, "grad_norm": 3.9945566654205322, "learning_rate": 4.855947776971828e-06, "loss": 0.1138, "step": 469580 }, { "epoch": 2.791340478270949, "grad_norm": 3.7503662109375, "learning_rate": 4.855740371099903e-06, "loss": 0.0977, "step": 469590 }, { "epoch": 2.7913999203476174, "grad_norm": 3.155839681625366, "learning_rate": 4.855532965476412e-06, "loss": 0.1218, "step": 469600 }, { "epoch": 2.791459362424286, "grad_norm": 4.710232734680176, "learning_rate": 4.85532556010171e-06, "loss": 0.1128, "step": 469610 }, { "epoch": 2.791518804500954, "grad_norm": 3.69851016998291, "learning_rate": 4.855118154976154e-06, "loss": 0.1083, "step": 469620 }, { "epoch": 2.7915782465776227, "grad_norm": 3.823035717010498, "learning_rate": 4.8549107501001025e-06, "loss": 0.1035, "step": 469630 }, { "epoch": 2.7916376886542906, "grad_norm": 4.089710235595703, "learning_rate": 4.854703345473912e-06, "loss": 0.1007, "step": 469640 }, { "epoch": 2.7916971307309595, "grad_norm": 5.394557952880859, "learning_rate": 4.85449594109794e-06, "loss": 0.12, "step": 469650 }, { "epoch": 2.7917565728076275, "grad_norm": 4.152298450469971, "learning_rate": 4.854288536972541e-06, "loss": 0.1074, "step": 469660 }, { "epoch": 2.791816014884296, "grad_norm": 3.649029016494751, "learning_rate": 4.854081133098078e-06, "loss": 0.1133, "step": 469670 }, { "epoch": 2.7918754569609643, "grad_norm": 3.9586501121520996, "learning_rate": 4.853873729474903e-06, "loss": 0.1134, "step": 469680 }, { "epoch": 2.7919348990376327, "grad_norm": 3.870898723602295, "learning_rate": 4.853666326103374e-06, "loss": 0.1247, "step": 469690 }, { "epoch": 2.791994341114301, "grad_norm": 4.280320644378662, "learning_rate": 4.85345892298385e-06, "loss": 0.1056, "step": 469700 }, { "epoch": 2.7920537831909695, "grad_norm": 5.076141357421875, "learning_rate": 4.853251520116687e-06, "loss": 0.1053, "step": 469710 }, { "epoch": 2.792113225267638, "grad_norm": 6.731556415557861, "learning_rate": 4.853044117502242e-06, "loss": 0.1131, "step": 469720 }, { "epoch": 2.7921726673443064, "grad_norm": 3.8524491786956787, "learning_rate": 4.852836715140874e-06, "loss": 0.1112, "step": 469730 }, { "epoch": 2.7922321094209748, "grad_norm": 5.081223964691162, "learning_rate": 4.8526293130329376e-06, "loss": 0.1097, "step": 469740 }, { "epoch": 2.792291551497643, "grad_norm": 3.6250932216644287, "learning_rate": 4.852421911178791e-06, "loss": 0.1108, "step": 469750 }, { "epoch": 2.7923509935743116, "grad_norm": 3.5846240520477295, "learning_rate": 4.852214509578792e-06, "loss": 0.0992, "step": 469760 }, { "epoch": 2.79241043565098, "grad_norm": 5.7370076179504395, "learning_rate": 4.852007108233298e-06, "loss": 0.1172, "step": 469770 }, { "epoch": 2.7924698777276484, "grad_norm": 3.232931613922119, "learning_rate": 4.851799707142663e-06, "loss": 0.1105, "step": 469780 }, { "epoch": 2.792529319804317, "grad_norm": 3.5208845138549805, "learning_rate": 4.851592306307249e-06, "loss": 0.1045, "step": 469790 }, { "epoch": 2.7925887618809853, "grad_norm": 4.034358978271484, "learning_rate": 4.851384905727408e-06, "loss": 0.1144, "step": 469800 }, { "epoch": 2.7926482039576532, "grad_norm": 6.345334529876709, "learning_rate": 4.851177505403501e-06, "loss": 0.1211, "step": 469810 }, { "epoch": 2.792707646034322, "grad_norm": 3.9463517665863037, "learning_rate": 4.850970105335885e-06, "loss": 0.1133, "step": 469820 }, { "epoch": 2.79276708811099, "grad_norm": 3.836167335510254, "learning_rate": 4.850762705524916e-06, "loss": 0.1051, "step": 469830 }, { "epoch": 2.7928265301876585, "grad_norm": 4.371035575866699, "learning_rate": 4.850555305970952e-06, "loss": 0.1156, "step": 469840 }, { "epoch": 2.792885972264327, "grad_norm": 3.0928115844726562, "learning_rate": 4.850347906674348e-06, "loss": 0.1218, "step": 469850 }, { "epoch": 2.7929454143409953, "grad_norm": 5.0688066482543945, "learning_rate": 4.8501405076354645e-06, "loss": 0.1138, "step": 469860 }, { "epoch": 2.7930048564176637, "grad_norm": 4.975956916809082, "learning_rate": 4.849933108854657e-06, "loss": 0.1136, "step": 469870 }, { "epoch": 2.793064298494332, "grad_norm": 3.1879167556762695, "learning_rate": 4.849725710332281e-06, "loss": 0.1058, "step": 469880 }, { "epoch": 2.7931237405710005, "grad_norm": 3.5585479736328125, "learning_rate": 4.849518312068696e-06, "loss": 0.1135, "step": 469890 }, { "epoch": 2.793183182647669, "grad_norm": 3.824392557144165, "learning_rate": 4.849310914064259e-06, "loss": 0.1124, "step": 469900 }, { "epoch": 2.7932426247243374, "grad_norm": 3.8193929195404053, "learning_rate": 4.849103516319326e-06, "loss": 0.1122, "step": 469910 }, { "epoch": 2.793302066801006, "grad_norm": 3.4456686973571777, "learning_rate": 4.8488961188342546e-06, "loss": 0.1121, "step": 469920 }, { "epoch": 2.793361508877674, "grad_norm": 3.6148455142974854, "learning_rate": 4.848688721609403e-06, "loss": 0.1184, "step": 469930 }, { "epoch": 2.7934209509543426, "grad_norm": 3.8714823722839355, "learning_rate": 4.848481324645126e-06, "loss": 0.1106, "step": 469940 }, { "epoch": 2.793480393031011, "grad_norm": 4.6355366706848145, "learning_rate": 4.848273927941784e-06, "loss": 0.1091, "step": 469950 }, { "epoch": 2.7935398351076794, "grad_norm": 3.6379144191741943, "learning_rate": 4.848066531499732e-06, "loss": 0.1058, "step": 469960 }, { "epoch": 2.793599277184348, "grad_norm": 3.6368746757507324, "learning_rate": 4.847859135319326e-06, "loss": 0.0955, "step": 469970 }, { "epoch": 2.793658719261016, "grad_norm": 5.0986433029174805, "learning_rate": 4.847651739400926e-06, "loss": 0.1175, "step": 469980 }, { "epoch": 2.7937181613376847, "grad_norm": 3.932925224304199, "learning_rate": 4.847444343744888e-06, "loss": 0.107, "step": 469990 }, { "epoch": 2.7937776034143527, "grad_norm": 3.149933099746704, "learning_rate": 4.847236948351568e-06, "loss": 0.1016, "step": 470000 }, { "epoch": 2.7938370454910215, "grad_norm": 3.866093873977661, "learning_rate": 4.847029553221326e-06, "loss": 0.115, "step": 470010 }, { "epoch": 2.7938964875676895, "grad_norm": 3.1081321239471436, "learning_rate": 4.846822158354514e-06, "loss": 0.1137, "step": 470020 }, { "epoch": 2.793955929644358, "grad_norm": 5.176985263824463, "learning_rate": 4.846614763751495e-06, "loss": 0.0983, "step": 470030 }, { "epoch": 2.7940153717210263, "grad_norm": 3.854222059249878, "learning_rate": 4.846407369412624e-06, "loss": 0.1026, "step": 470040 }, { "epoch": 2.7940748137976947, "grad_norm": 3.9732308387756348, "learning_rate": 4.8461999753382566e-06, "loss": 0.1095, "step": 470050 }, { "epoch": 2.794134255874363, "grad_norm": 3.5120863914489746, "learning_rate": 4.845992581528753e-06, "loss": 0.0973, "step": 470060 }, { "epoch": 2.7941936979510316, "grad_norm": 4.253885269165039, "learning_rate": 4.845785187984467e-06, "loss": 0.1258, "step": 470070 }, { "epoch": 2.7942531400277, "grad_norm": 4.191697120666504, "learning_rate": 4.845577794705757e-06, "loss": 0.1031, "step": 470080 }, { "epoch": 2.7943125821043684, "grad_norm": 3.598130226135254, "learning_rate": 4.845370401692982e-06, "loss": 0.1185, "step": 470090 }, { "epoch": 2.794372024181037, "grad_norm": 4.700992107391357, "learning_rate": 4.845163008946497e-06, "loss": 0.1185, "step": 470100 }, { "epoch": 2.794431466257705, "grad_norm": 3.6004512310028076, "learning_rate": 4.8449556164666585e-06, "loss": 0.1169, "step": 470110 }, { "epoch": 2.7944909083343736, "grad_norm": 4.861447811126709, "learning_rate": 4.844748224253827e-06, "loss": 0.1131, "step": 470120 }, { "epoch": 2.794550350411042, "grad_norm": 4.552366256713867, "learning_rate": 4.844540832308357e-06, "loss": 0.1188, "step": 470130 }, { "epoch": 2.7946097924877105, "grad_norm": 4.297874450683594, "learning_rate": 4.844333440630605e-06, "loss": 0.1152, "step": 470140 }, { "epoch": 2.794669234564379, "grad_norm": 5.520726203918457, "learning_rate": 4.844126049220931e-06, "loss": 0.1095, "step": 470150 }, { "epoch": 2.7947286766410473, "grad_norm": 3.796264171600342, "learning_rate": 4.84391865807969e-06, "loss": 0.1099, "step": 470160 }, { "epoch": 2.7947881187177153, "grad_norm": 3.826035737991333, "learning_rate": 4.843711267207239e-06, "loss": 0.1139, "step": 470170 }, { "epoch": 2.794847560794384, "grad_norm": 3.6290111541748047, "learning_rate": 4.843503876603936e-06, "loss": 0.1031, "step": 470180 }, { "epoch": 2.794907002871052, "grad_norm": 4.624109268188477, "learning_rate": 4.843296486270138e-06, "loss": 0.1187, "step": 470190 }, { "epoch": 2.794966444947721, "grad_norm": 3.6131508350372314, "learning_rate": 4.843089096206203e-06, "loss": 0.1107, "step": 470200 }, { "epoch": 2.795025887024389, "grad_norm": 4.812463283538818, "learning_rate": 4.842881706412487e-06, "loss": 0.0977, "step": 470210 }, { "epoch": 2.7950853291010573, "grad_norm": 5.013030052185059, "learning_rate": 4.842674316889347e-06, "loss": 0.1208, "step": 470220 }, { "epoch": 2.7951447711777258, "grad_norm": 4.423101902008057, "learning_rate": 4.8424669276371405e-06, "loss": 0.1151, "step": 470230 }, { "epoch": 2.795204213254394, "grad_norm": 4.350339412689209, "learning_rate": 4.842259538656223e-06, "loss": 0.117, "step": 470240 }, { "epoch": 2.7952636553310626, "grad_norm": 4.06040620803833, "learning_rate": 4.842052149946956e-06, "loss": 0.1014, "step": 470250 }, { "epoch": 2.795323097407731, "grad_norm": 4.347829341888428, "learning_rate": 4.8418447615096945e-06, "loss": 0.0941, "step": 470260 }, { "epoch": 2.7953825394843994, "grad_norm": 3.3708677291870117, "learning_rate": 4.841637373344793e-06, "loss": 0.1104, "step": 470270 }, { "epoch": 2.795441981561068, "grad_norm": 3.4598164558410645, "learning_rate": 4.841429985452613e-06, "loss": 0.134, "step": 470280 }, { "epoch": 2.7955014236377362, "grad_norm": 3.188067674636841, "learning_rate": 4.841222597833508e-06, "loss": 0.0939, "step": 470290 }, { "epoch": 2.7955608657144047, "grad_norm": 4.39289665222168, "learning_rate": 4.8410152104878366e-06, "loss": 0.1124, "step": 470300 }, { "epoch": 2.795620307791073, "grad_norm": 4.594886302947998, "learning_rate": 4.840807823415957e-06, "loss": 0.1363, "step": 470310 }, { "epoch": 2.7956797498677415, "grad_norm": 3.26363468170166, "learning_rate": 4.840600436618225e-06, "loss": 0.1101, "step": 470320 }, { "epoch": 2.79573919194441, "grad_norm": 4.709174156188965, "learning_rate": 4.840393050094998e-06, "loss": 0.1196, "step": 470330 }, { "epoch": 2.7957986340210783, "grad_norm": 4.031081676483154, "learning_rate": 4.840185663846633e-06, "loss": 0.1035, "step": 470340 }, { "epoch": 2.7958580760977467, "grad_norm": 3.722635269165039, "learning_rate": 4.839978277873488e-06, "loss": 0.1165, "step": 470350 }, { "epoch": 2.7959175181744147, "grad_norm": 4.033776760101318, "learning_rate": 4.83977089217592e-06, "loss": 0.0974, "step": 470360 }, { "epoch": 2.7959769602510836, "grad_norm": 3.3418211936950684, "learning_rate": 4.8395635067542834e-06, "loss": 0.1057, "step": 470370 }, { "epoch": 2.7960364023277515, "grad_norm": 5.872779369354248, "learning_rate": 4.839356121608939e-06, "loss": 0.1109, "step": 470380 }, { "epoch": 2.7960958444044204, "grad_norm": 4.604584217071533, "learning_rate": 4.839148736740243e-06, "loss": 0.1166, "step": 470390 }, { "epoch": 2.7961552864810884, "grad_norm": 3.4474449157714844, "learning_rate": 4.8389413521485506e-06, "loss": 0.1106, "step": 470400 }, { "epoch": 2.7962147285577568, "grad_norm": 4.020175933837891, "learning_rate": 4.838733967834222e-06, "loss": 0.1227, "step": 470410 }, { "epoch": 2.796274170634425, "grad_norm": 3.8018927574157715, "learning_rate": 4.838526583797612e-06, "loss": 0.107, "step": 470420 }, { "epoch": 2.7963336127110936, "grad_norm": 3.7313222885131836, "learning_rate": 4.838319200039078e-06, "loss": 0.1115, "step": 470430 }, { "epoch": 2.796393054787762, "grad_norm": 2.808992862701416, "learning_rate": 4.838111816558978e-06, "loss": 0.1084, "step": 470440 }, { "epoch": 2.7964524968644304, "grad_norm": 3.1439695358276367, "learning_rate": 4.837904433357669e-06, "loss": 0.1155, "step": 470450 }, { "epoch": 2.796511938941099, "grad_norm": 3.1188204288482666, "learning_rate": 4.837697050435507e-06, "loss": 0.1069, "step": 470460 }, { "epoch": 2.7965713810177673, "grad_norm": 3.578718662261963, "learning_rate": 4.837489667792849e-06, "loss": 0.108, "step": 470470 }, { "epoch": 2.7966308230944357, "grad_norm": 3.956650495529175, "learning_rate": 4.837282285430056e-06, "loss": 0.1073, "step": 470480 }, { "epoch": 2.796690265171104, "grad_norm": 3.3406267166137695, "learning_rate": 4.837074903347481e-06, "loss": 0.107, "step": 470490 }, { "epoch": 2.7967497072477725, "grad_norm": 3.665963888168335, "learning_rate": 4.836867521545482e-06, "loss": 0.1189, "step": 470500 }, { "epoch": 2.796809149324441, "grad_norm": 3.6995317935943604, "learning_rate": 4.836660140024418e-06, "loss": 0.117, "step": 470510 }, { "epoch": 2.7968685914011093, "grad_norm": 3.5647573471069336, "learning_rate": 4.836452758784644e-06, "loss": 0.0917, "step": 470520 }, { "epoch": 2.7969280334777777, "grad_norm": 4.038122177124023, "learning_rate": 4.836245377826518e-06, "loss": 0.1102, "step": 470530 }, { "epoch": 2.796987475554446, "grad_norm": 4.852092266082764, "learning_rate": 4.836037997150397e-06, "loss": 0.1096, "step": 470540 }, { "epoch": 2.797046917631114, "grad_norm": 4.933637619018555, "learning_rate": 4.835830616756639e-06, "loss": 0.1125, "step": 470550 }, { "epoch": 2.797106359707783, "grad_norm": 3.190068483352661, "learning_rate": 4.835623236645598e-06, "loss": 0.1058, "step": 470560 }, { "epoch": 2.797165801784451, "grad_norm": 3.4283690452575684, "learning_rate": 4.835415856817635e-06, "loss": 0.1027, "step": 470570 }, { "epoch": 2.7972252438611194, "grad_norm": 4.631429672241211, "learning_rate": 4.835208477273106e-06, "loss": 0.1069, "step": 470580 }, { "epoch": 2.797284685937788, "grad_norm": 3.7598512172698975, "learning_rate": 4.8350010980123665e-06, "loss": 0.1074, "step": 470590 }, { "epoch": 2.797344128014456, "grad_norm": 4.381142616271973, "learning_rate": 4.834793719035775e-06, "loss": 0.1046, "step": 470600 }, { "epoch": 2.7974035700911246, "grad_norm": 3.0371060371398926, "learning_rate": 4.834586340343689e-06, "loss": 0.1062, "step": 470610 }, { "epoch": 2.797463012167793, "grad_norm": 4.092597007751465, "learning_rate": 4.8343789619364644e-06, "loss": 0.1258, "step": 470620 }, { "epoch": 2.7975224542444614, "grad_norm": 4.181702136993408, "learning_rate": 4.83417158381446e-06, "loss": 0.1128, "step": 470630 }, { "epoch": 2.79758189632113, "grad_norm": 3.4972589015960693, "learning_rate": 4.833964205978031e-06, "loss": 0.1028, "step": 470640 }, { "epoch": 2.7976413383977983, "grad_norm": 3.4505698680877686, "learning_rate": 4.8337568284275355e-06, "loss": 0.115, "step": 470650 }, { "epoch": 2.7977007804744667, "grad_norm": 4.790375232696533, "learning_rate": 4.833549451163331e-06, "loss": 0.1198, "step": 470660 }, { "epoch": 2.797760222551135, "grad_norm": 3.7378711700439453, "learning_rate": 4.8333420741857746e-06, "loss": 0.0988, "step": 470670 }, { "epoch": 2.7978196646278035, "grad_norm": 4.106987953186035, "learning_rate": 4.833134697495221e-06, "loss": 0.1129, "step": 470680 }, { "epoch": 2.797879106704472, "grad_norm": 3.0791616439819336, "learning_rate": 4.83292732109203e-06, "loss": 0.1007, "step": 470690 }, { "epoch": 2.7979385487811403, "grad_norm": 4.415783882141113, "learning_rate": 4.8327199449765585e-06, "loss": 0.1174, "step": 470700 }, { "epoch": 2.7979979908578088, "grad_norm": 3.2716026306152344, "learning_rate": 4.832512569149163e-06, "loss": 0.1033, "step": 470710 }, { "epoch": 2.7980574329344767, "grad_norm": 4.505753993988037, "learning_rate": 4.8323051936102025e-06, "loss": 0.1039, "step": 470720 }, { "epoch": 2.7981168750111456, "grad_norm": 8.450678825378418, "learning_rate": 4.832097818360031e-06, "loss": 0.1023, "step": 470730 }, { "epoch": 2.7981763170878136, "grad_norm": 3.558584213256836, "learning_rate": 4.831890443399008e-06, "loss": 0.1151, "step": 470740 }, { "epoch": 2.7982357591644824, "grad_norm": 2.324634075164795, "learning_rate": 4.831683068727489e-06, "loss": 0.1002, "step": 470750 }, { "epoch": 2.7982952012411504, "grad_norm": 3.901925802230835, "learning_rate": 4.831475694345831e-06, "loss": 0.1118, "step": 470760 }, { "epoch": 2.798354643317819, "grad_norm": 3.990870475769043, "learning_rate": 4.8312683202543946e-06, "loss": 0.1119, "step": 470770 }, { "epoch": 2.798414085394487, "grad_norm": 3.9664342403411865, "learning_rate": 4.8310609464535326e-06, "loss": 0.1191, "step": 470780 }, { "epoch": 2.7984735274711556, "grad_norm": 4.293959617614746, "learning_rate": 4.830853572943603e-06, "loss": 0.1144, "step": 470790 }, { "epoch": 2.798532969547824, "grad_norm": 5.464455604553223, "learning_rate": 4.830646199724965e-06, "loss": 0.1058, "step": 470800 }, { "epoch": 2.7985924116244925, "grad_norm": 5.475970268249512, "learning_rate": 4.830438826797974e-06, "loss": 0.1099, "step": 470810 }, { "epoch": 2.798651853701161, "grad_norm": 3.842196464538574, "learning_rate": 4.830231454162988e-06, "loss": 0.1228, "step": 470820 }, { "epoch": 2.7987112957778293, "grad_norm": 5.162324905395508, "learning_rate": 4.830024081820363e-06, "loss": 0.1346, "step": 470830 }, { "epoch": 2.7987707378544977, "grad_norm": 4.071352005004883, "learning_rate": 4.829816709770457e-06, "loss": 0.1018, "step": 470840 }, { "epoch": 2.798830179931166, "grad_norm": 4.5849103927612305, "learning_rate": 4.829609338013626e-06, "loss": 0.1044, "step": 470850 }, { "epoch": 2.7988896220078345, "grad_norm": 4.281346797943115, "learning_rate": 4.8294019665502305e-06, "loss": 0.0942, "step": 470860 }, { "epoch": 2.798949064084503, "grad_norm": 3.581416606903076, "learning_rate": 4.829194595380624e-06, "loss": 0.123, "step": 470870 }, { "epoch": 2.7990085061611714, "grad_norm": 4.740419864654541, "learning_rate": 4.828987224505164e-06, "loss": 0.1068, "step": 470880 }, { "epoch": 2.7990679482378398, "grad_norm": 3.70293927192688, "learning_rate": 4.828779853924209e-06, "loss": 0.1012, "step": 470890 }, { "epoch": 2.799127390314508, "grad_norm": 3.7045528888702393, "learning_rate": 4.828572483638114e-06, "loss": 0.1141, "step": 470900 }, { "epoch": 2.799186832391176, "grad_norm": 4.953326225280762, "learning_rate": 4.828365113647239e-06, "loss": 0.1114, "step": 470910 }, { "epoch": 2.799246274467845, "grad_norm": 5.174039840698242, "learning_rate": 4.828157743951939e-06, "loss": 0.1142, "step": 470920 }, { "epoch": 2.799305716544513, "grad_norm": 4.161459445953369, "learning_rate": 4.827950374552574e-06, "loss": 0.1297, "step": 470930 }, { "epoch": 2.799365158621182, "grad_norm": 3.408254861831665, "learning_rate": 4.827743005449498e-06, "loss": 0.1134, "step": 470940 }, { "epoch": 2.79942460069785, "grad_norm": 3.16029953956604, "learning_rate": 4.8275356366430675e-06, "loss": 0.1103, "step": 470950 }, { "epoch": 2.7994840427745182, "grad_norm": 5.016572952270508, "learning_rate": 4.827328268133643e-06, "loss": 0.1318, "step": 470960 }, { "epoch": 2.7995434848511866, "grad_norm": 3.8535008430480957, "learning_rate": 4.82712089992158e-06, "loss": 0.0958, "step": 470970 }, { "epoch": 2.799602926927855, "grad_norm": 4.219379901885986, "learning_rate": 4.826913532007235e-06, "loss": 0.1034, "step": 470980 }, { "epoch": 2.7996623690045235, "grad_norm": 4.5218424797058105, "learning_rate": 4.826706164390965e-06, "loss": 0.1021, "step": 470990 }, { "epoch": 2.799721811081192, "grad_norm": 4.125161647796631, "learning_rate": 4.826498797073128e-06, "loss": 0.1106, "step": 471000 }, { "epoch": 2.7997812531578603, "grad_norm": 3.1974382400512695, "learning_rate": 4.826291430054082e-06, "loss": 0.1048, "step": 471010 }, { "epoch": 2.7998406952345287, "grad_norm": 3.681319236755371, "learning_rate": 4.8260840633341805e-06, "loss": 0.1026, "step": 471020 }, { "epoch": 2.799900137311197, "grad_norm": 4.300062656402588, "learning_rate": 4.825876696913784e-06, "loss": 0.1173, "step": 471030 }, { "epoch": 2.7999595793878655, "grad_norm": 5.406060695648193, "learning_rate": 4.8256693307932495e-06, "loss": 0.0836, "step": 471040 }, { "epoch": 2.800019021464534, "grad_norm": 4.992991924285889, "learning_rate": 4.825461964972932e-06, "loss": 0.1147, "step": 471050 }, { "epoch": 2.8000784635412024, "grad_norm": 4.320825576782227, "learning_rate": 4.825254599453191e-06, "loss": 0.1006, "step": 471060 }, { "epoch": 2.800137905617871, "grad_norm": 3.2812764644622803, "learning_rate": 4.825047234234382e-06, "loss": 0.1119, "step": 471070 }, { "epoch": 2.800197347694539, "grad_norm": 3.8031578063964844, "learning_rate": 4.824839869316861e-06, "loss": 0.0958, "step": 471080 }, { "epoch": 2.8002567897712076, "grad_norm": 5.162812232971191, "learning_rate": 4.824632504700988e-06, "loss": 0.1271, "step": 471090 }, { "epoch": 2.8003162318478756, "grad_norm": 3.6224424839019775, "learning_rate": 4.8244251403871195e-06, "loss": 0.1087, "step": 471100 }, { "epoch": 2.8003756739245445, "grad_norm": 3.842956304550171, "learning_rate": 4.82421777637561e-06, "loss": 0.0977, "step": 471110 }, { "epoch": 2.8004351160012124, "grad_norm": 5.307653903961182, "learning_rate": 4.824010412666818e-06, "loss": 0.101, "step": 471120 }, { "epoch": 2.8004945580778813, "grad_norm": 3.9449875354766846, "learning_rate": 4.823803049261103e-06, "loss": 0.109, "step": 471130 }, { "epoch": 2.8005540001545493, "grad_norm": 3.4852612018585205, "learning_rate": 4.82359568615882e-06, "loss": 0.1133, "step": 471140 }, { "epoch": 2.8006134422312177, "grad_norm": 2.313663959503174, "learning_rate": 4.823388323360325e-06, "loss": 0.1086, "step": 471150 }, { "epoch": 2.800672884307886, "grad_norm": 3.5968122482299805, "learning_rate": 4.823180960865978e-06, "loss": 0.1039, "step": 471160 }, { "epoch": 2.8007323263845545, "grad_norm": 3.5561416149139404, "learning_rate": 4.822973598676134e-06, "loss": 0.097, "step": 471170 }, { "epoch": 2.800791768461223, "grad_norm": 3.7313904762268066, "learning_rate": 4.82276623679115e-06, "loss": 0.1141, "step": 471180 }, { "epoch": 2.8008512105378913, "grad_norm": 6.0208916664123535, "learning_rate": 4.822558875211384e-06, "loss": 0.1147, "step": 471190 }, { "epoch": 2.8009106526145597, "grad_norm": 3.9529402256011963, "learning_rate": 4.822351513937194e-06, "loss": 0.1098, "step": 471200 }, { "epoch": 2.800970094691228, "grad_norm": 3.9248299598693848, "learning_rate": 4.822144152968934e-06, "loss": 0.1091, "step": 471210 }, { "epoch": 2.8010295367678966, "grad_norm": 3.3098511695861816, "learning_rate": 4.821936792306965e-06, "loss": 0.1113, "step": 471220 }, { "epoch": 2.801088978844565, "grad_norm": 3.5529797077178955, "learning_rate": 4.82172943195164e-06, "loss": 0.1101, "step": 471230 }, { "epoch": 2.8011484209212334, "grad_norm": 4.6304192543029785, "learning_rate": 4.821522071903319e-06, "loss": 0.1106, "step": 471240 }, { "epoch": 2.801207862997902, "grad_norm": 5.007867813110352, "learning_rate": 4.821314712162359e-06, "loss": 0.1061, "step": 471250 }, { "epoch": 2.8012673050745702, "grad_norm": 5.5844011306762695, "learning_rate": 4.821107352729116e-06, "loss": 0.1039, "step": 471260 }, { "epoch": 2.8013267471512386, "grad_norm": 3.536191463470459, "learning_rate": 4.8208999936039465e-06, "loss": 0.1162, "step": 471270 }, { "epoch": 2.801386189227907, "grad_norm": 3.018320322036743, "learning_rate": 4.82069263478721e-06, "loss": 0.1088, "step": 471280 }, { "epoch": 2.801445631304575, "grad_norm": 4.004151821136475, "learning_rate": 4.820485276279261e-06, "loss": 0.1101, "step": 471290 }, { "epoch": 2.801505073381244, "grad_norm": 4.354754447937012, "learning_rate": 4.820277918080458e-06, "loss": 0.1186, "step": 471300 }, { "epoch": 2.801564515457912, "grad_norm": 3.0614750385284424, "learning_rate": 4.820070560191158e-06, "loss": 0.1117, "step": 471310 }, { "epoch": 2.8016239575345803, "grad_norm": 4.807477951049805, "learning_rate": 4.819863202611719e-06, "loss": 0.1051, "step": 471320 }, { "epoch": 2.8016833996112487, "grad_norm": 3.1105287075042725, "learning_rate": 4.819655845342496e-06, "loss": 0.1292, "step": 471330 }, { "epoch": 2.801742841687917, "grad_norm": 5.294293403625488, "learning_rate": 4.819448488383846e-06, "loss": 0.0982, "step": 471340 }, { "epoch": 2.8018022837645855, "grad_norm": 3.3459770679473877, "learning_rate": 4.819241131736128e-06, "loss": 0.1223, "step": 471350 }, { "epoch": 2.801861725841254, "grad_norm": 4.033314228057861, "learning_rate": 4.819033775399699e-06, "loss": 0.1109, "step": 471360 }, { "epoch": 2.8019211679179223, "grad_norm": 4.7398681640625, "learning_rate": 4.818826419374916e-06, "loss": 0.0995, "step": 471370 }, { "epoch": 2.8019806099945908, "grad_norm": 2.517887592315674, "learning_rate": 4.818619063662133e-06, "loss": 0.1102, "step": 471380 }, { "epoch": 2.802040052071259, "grad_norm": 4.863165855407715, "learning_rate": 4.818411708261713e-06, "loss": 0.1121, "step": 471390 }, { "epoch": 2.8020994941479276, "grad_norm": 3.0067551136016846, "learning_rate": 4.818204353174008e-06, "loss": 0.0891, "step": 471400 }, { "epoch": 2.802158936224596, "grad_norm": 3.6068966388702393, "learning_rate": 4.817996998399377e-06, "loss": 0.1125, "step": 471410 }, { "epoch": 2.8022183783012644, "grad_norm": 3.846571922302246, "learning_rate": 4.817789643938178e-06, "loss": 0.1114, "step": 471420 }, { "epoch": 2.802277820377933, "grad_norm": 3.7552804946899414, "learning_rate": 4.817582289790765e-06, "loss": 0.1061, "step": 471430 }, { "epoch": 2.8023372624546012, "grad_norm": 3.635530471801758, "learning_rate": 4.817374935957497e-06, "loss": 0.1012, "step": 471440 }, { "epoch": 2.8023967045312697, "grad_norm": 4.515389919281006, "learning_rate": 4.817167582438732e-06, "loss": 0.1172, "step": 471450 }, { "epoch": 2.8024561466079376, "grad_norm": 4.015065670013428, "learning_rate": 4.8169602292348274e-06, "loss": 0.1225, "step": 471460 }, { "epoch": 2.8025155886846065, "grad_norm": 4.218104839324951, "learning_rate": 4.816752876346137e-06, "loss": 0.1033, "step": 471470 }, { "epoch": 2.8025750307612745, "grad_norm": 2.901305675506592, "learning_rate": 4.816545523773022e-06, "loss": 0.1124, "step": 471480 }, { "epoch": 2.8026344728379433, "grad_norm": 3.773621082305908, "learning_rate": 4.816338171515837e-06, "loss": 0.0966, "step": 471490 }, { "epoch": 2.8026939149146113, "grad_norm": 3.9254343509674072, "learning_rate": 4.816130819574938e-06, "loss": 0.133, "step": 471500 }, { "epoch": 2.8027533569912797, "grad_norm": 4.8253679275512695, "learning_rate": 4.815923467950686e-06, "loss": 0.1261, "step": 471510 }, { "epoch": 2.802812799067948, "grad_norm": 4.221158981323242, "learning_rate": 4.815716116643434e-06, "loss": 0.1245, "step": 471520 }, { "epoch": 2.8028722411446165, "grad_norm": 2.9540348052978516, "learning_rate": 4.815508765653541e-06, "loss": 0.1121, "step": 471530 }, { "epoch": 2.802931683221285, "grad_norm": 3.6978070735931396, "learning_rate": 4.8153014149813645e-06, "loss": 0.1184, "step": 471540 }, { "epoch": 2.8029911252979534, "grad_norm": 6.11690616607666, "learning_rate": 4.815094064627261e-06, "loss": 0.1213, "step": 471550 }, { "epoch": 2.8030505673746218, "grad_norm": 4.284584045410156, "learning_rate": 4.814886714591586e-06, "loss": 0.117, "step": 471560 }, { "epoch": 2.80311000945129, "grad_norm": 4.484671592712402, "learning_rate": 4.814679364874699e-06, "loss": 0.1119, "step": 471570 }, { "epoch": 2.8031694515279586, "grad_norm": 2.893254041671753, "learning_rate": 4.814472015476957e-06, "loss": 0.1221, "step": 471580 }, { "epoch": 2.803228893604627, "grad_norm": 3.6067469120025635, "learning_rate": 4.814264666398716e-06, "loss": 0.1163, "step": 471590 }, { "epoch": 2.8032883356812954, "grad_norm": 3.9178671836853027, "learning_rate": 4.8140573176403335e-06, "loss": 0.1109, "step": 471600 }, { "epoch": 2.803347777757964, "grad_norm": 3.9691367149353027, "learning_rate": 4.813849969202166e-06, "loss": 0.113, "step": 471610 }, { "epoch": 2.8034072198346323, "grad_norm": 3.991759777069092, "learning_rate": 4.813642621084572e-06, "loss": 0.1066, "step": 471620 }, { "epoch": 2.8034666619113007, "grad_norm": 4.655475616455078, "learning_rate": 4.813435273287907e-06, "loss": 0.1188, "step": 471630 }, { "epoch": 2.803526103987969, "grad_norm": 4.826840877532959, "learning_rate": 4.813227925812529e-06, "loss": 0.118, "step": 471640 }, { "epoch": 2.803585546064637, "grad_norm": 4.257619857788086, "learning_rate": 4.813020578658795e-06, "loss": 0.1206, "step": 471650 }, { "epoch": 2.803644988141306, "grad_norm": 4.567399978637695, "learning_rate": 4.812813231827062e-06, "loss": 0.119, "step": 471660 }, { "epoch": 2.803704430217974, "grad_norm": 3.5616848468780518, "learning_rate": 4.812605885317686e-06, "loss": 0.1035, "step": 471670 }, { "epoch": 2.8037638722946427, "grad_norm": 4.548954963684082, "learning_rate": 4.812398539131026e-06, "loss": 0.1099, "step": 471680 }, { "epoch": 2.8038233143713107, "grad_norm": 4.853919982910156, "learning_rate": 4.812191193267438e-06, "loss": 0.1197, "step": 471690 }, { "epoch": 2.803882756447979, "grad_norm": 3.1786751747131348, "learning_rate": 4.811983847727278e-06, "loss": 0.1062, "step": 471700 }, { "epoch": 2.8039421985246475, "grad_norm": 4.01249885559082, "learning_rate": 4.811776502510906e-06, "loss": 0.1191, "step": 471710 }, { "epoch": 2.804001640601316, "grad_norm": 3.9967563152313232, "learning_rate": 4.811569157618676e-06, "loss": 0.1096, "step": 471720 }, { "epoch": 2.8040610826779844, "grad_norm": 4.495790481567383, "learning_rate": 4.811361813050946e-06, "loss": 0.1105, "step": 471730 }, { "epoch": 2.804120524754653, "grad_norm": 4.2396321296691895, "learning_rate": 4.8111544688080756e-06, "loss": 0.1123, "step": 471740 }, { "epoch": 2.804179966831321, "grad_norm": 4.562405586242676, "learning_rate": 4.810947124890418e-06, "loss": 0.1178, "step": 471750 }, { "epoch": 2.8042394089079896, "grad_norm": 5.603398323059082, "learning_rate": 4.810739781298332e-06, "loss": 0.1218, "step": 471760 }, { "epoch": 2.804298850984658, "grad_norm": 4.122417449951172, "learning_rate": 4.8105324380321755e-06, "loss": 0.126, "step": 471770 }, { "epoch": 2.8043582930613264, "grad_norm": 4.2526116371154785, "learning_rate": 4.8103250950923025e-06, "loss": 0.1113, "step": 471780 }, { "epoch": 2.804417735137995, "grad_norm": 5.2959370613098145, "learning_rate": 4.810117752479074e-06, "loss": 0.1346, "step": 471790 }, { "epoch": 2.8044771772146633, "grad_norm": 3.2990195751190186, "learning_rate": 4.8099104101928454e-06, "loss": 0.1125, "step": 471800 }, { "epoch": 2.8045366192913317, "grad_norm": 3.2437264919281006, "learning_rate": 4.809703068233974e-06, "loss": 0.1278, "step": 471810 }, { "epoch": 2.804596061368, "grad_norm": 4.27172327041626, "learning_rate": 4.809495726602817e-06, "loss": 0.1059, "step": 471820 }, { "epoch": 2.8046555034446685, "grad_norm": 3.427365779876709, "learning_rate": 4.80928838529973e-06, "loss": 0.1228, "step": 471830 }, { "epoch": 2.8047149455213365, "grad_norm": 2.780421495437622, "learning_rate": 4.809081044325072e-06, "loss": 0.106, "step": 471840 }, { "epoch": 2.8047743875980053, "grad_norm": 3.748779296875, "learning_rate": 4.808873703679199e-06, "loss": 0.1094, "step": 471850 }, { "epoch": 2.8048338296746733, "grad_norm": 3.331155776977539, "learning_rate": 4.808666363362468e-06, "loss": 0.1204, "step": 471860 }, { "epoch": 2.804893271751342, "grad_norm": 3.6708834171295166, "learning_rate": 4.808459023375237e-06, "loss": 0.1134, "step": 471870 }, { "epoch": 2.80495271382801, "grad_norm": 3.042985677719116, "learning_rate": 4.8082516837178625e-06, "loss": 0.1002, "step": 471880 }, { "epoch": 2.8050121559046786, "grad_norm": 2.879901885986328, "learning_rate": 4.8080443443907e-06, "loss": 0.0952, "step": 471890 }, { "epoch": 2.805071597981347, "grad_norm": 3.0723397731781006, "learning_rate": 4.8078370053941094e-06, "loss": 0.1106, "step": 471900 }, { "epoch": 2.8051310400580154, "grad_norm": 4.554652214050293, "learning_rate": 4.807629666728447e-06, "loss": 0.1151, "step": 471910 }, { "epoch": 2.805190482134684, "grad_norm": 4.124648094177246, "learning_rate": 4.807422328394067e-06, "loss": 0.1053, "step": 471920 }, { "epoch": 2.805249924211352, "grad_norm": 4.380887031555176, "learning_rate": 4.807214990391332e-06, "loss": 0.1133, "step": 471930 }, { "epoch": 2.8053093662880206, "grad_norm": 3.234137535095215, "learning_rate": 4.807007652720593e-06, "loss": 0.1087, "step": 471940 }, { "epoch": 2.805368808364689, "grad_norm": 4.854114055633545, "learning_rate": 4.80680031538221e-06, "loss": 0.1288, "step": 471950 }, { "epoch": 2.8054282504413575, "grad_norm": 3.615334987640381, "learning_rate": 4.806592978376541e-06, "loss": 0.1239, "step": 471960 }, { "epoch": 2.805487692518026, "grad_norm": 6.381491661071777, "learning_rate": 4.806385641703942e-06, "loss": 0.1251, "step": 471970 }, { "epoch": 2.8055471345946943, "grad_norm": 3.1557366847991943, "learning_rate": 4.806178305364769e-06, "loss": 0.1055, "step": 471980 }, { "epoch": 2.8056065766713627, "grad_norm": 4.9458746910095215, "learning_rate": 4.805970969359381e-06, "loss": 0.1189, "step": 471990 }, { "epoch": 2.805666018748031, "grad_norm": 3.7137441635131836, "learning_rate": 4.805763633688132e-06, "loss": 0.087, "step": 472000 }, { "epoch": 2.8057254608246995, "grad_norm": 3.828826427459717, "learning_rate": 4.805556298351384e-06, "loss": 0.1087, "step": 472010 }, { "epoch": 2.805784902901368, "grad_norm": 2.906407594680786, "learning_rate": 4.80534896334949e-06, "loss": 0.1026, "step": 472020 }, { "epoch": 2.805844344978036, "grad_norm": 2.984342098236084, "learning_rate": 4.805141628682808e-06, "loss": 0.1189, "step": 472030 }, { "epoch": 2.805903787054705, "grad_norm": 4.452968120574951, "learning_rate": 4.804934294351696e-06, "loss": 0.1246, "step": 472040 }, { "epoch": 2.8059632291313727, "grad_norm": 8.066940307617188, "learning_rate": 4.804726960356511e-06, "loss": 0.11, "step": 472050 }, { "epoch": 2.806022671208041, "grad_norm": 4.275063991546631, "learning_rate": 4.804519626697609e-06, "loss": 0.1293, "step": 472060 }, { "epoch": 2.8060821132847096, "grad_norm": 4.598329544067383, "learning_rate": 4.804312293375347e-06, "loss": 0.1122, "step": 472070 }, { "epoch": 2.806141555361378, "grad_norm": 4.600429058074951, "learning_rate": 4.804104960390084e-06, "loss": 0.1153, "step": 472080 }, { "epoch": 2.8062009974380464, "grad_norm": 4.194091320037842, "learning_rate": 4.8038976277421735e-06, "loss": 0.1021, "step": 472090 }, { "epoch": 2.806260439514715, "grad_norm": 4.34041166305542, "learning_rate": 4.803690295431976e-06, "loss": 0.1228, "step": 472100 }, { "epoch": 2.8063198815913832, "grad_norm": 5.181644916534424, "learning_rate": 4.803482963459847e-06, "loss": 0.1302, "step": 472110 }, { "epoch": 2.8063793236680517, "grad_norm": 3.4463181495666504, "learning_rate": 4.803275631826144e-06, "loss": 0.1136, "step": 472120 }, { "epoch": 2.80643876574472, "grad_norm": 5.43053674697876, "learning_rate": 4.803068300531223e-06, "loss": 0.1092, "step": 472130 }, { "epoch": 2.8064982078213885, "grad_norm": 3.2102859020233154, "learning_rate": 4.802860969575443e-06, "loss": 0.1033, "step": 472140 }, { "epoch": 2.806557649898057, "grad_norm": 3.5746800899505615, "learning_rate": 4.802653638959159e-06, "loss": 0.1141, "step": 472150 }, { "epoch": 2.8066170919747253, "grad_norm": 3.967280864715576, "learning_rate": 4.80244630868273e-06, "loss": 0.1152, "step": 472160 }, { "epoch": 2.8066765340513937, "grad_norm": 4.234134674072266, "learning_rate": 4.802238978746511e-06, "loss": 0.1108, "step": 472170 }, { "epoch": 2.806735976128062, "grad_norm": 3.8753044605255127, "learning_rate": 4.802031649150861e-06, "loss": 0.1271, "step": 472180 }, { "epoch": 2.8067954182047306, "grad_norm": 4.0197248458862305, "learning_rate": 4.801824319896136e-06, "loss": 0.1178, "step": 472190 }, { "epoch": 2.8068548602813985, "grad_norm": 3.80598783493042, "learning_rate": 4.801616990982693e-06, "loss": 0.1054, "step": 472200 }, { "epoch": 2.8069143023580674, "grad_norm": 3.623941421508789, "learning_rate": 4.801409662410889e-06, "loss": 0.1066, "step": 472210 }, { "epoch": 2.8069737444347354, "grad_norm": 3.418365955352783, "learning_rate": 4.801202334181079e-06, "loss": 0.0987, "step": 472220 }, { "epoch": 2.807033186511404, "grad_norm": 4.077493190765381, "learning_rate": 4.800995006293624e-06, "loss": 0.1099, "step": 472230 }, { "epoch": 2.807092628588072, "grad_norm": 4.463054180145264, "learning_rate": 4.800787678748881e-06, "loss": 0.1149, "step": 472240 }, { "epoch": 2.8071520706647406, "grad_norm": 4.128741264343262, "learning_rate": 4.800580351547203e-06, "loss": 0.1053, "step": 472250 }, { "epoch": 2.807211512741409, "grad_norm": 3.318603992462158, "learning_rate": 4.800373024688952e-06, "loss": 0.1001, "step": 472260 }, { "epoch": 2.8072709548180774, "grad_norm": 4.458858966827393, "learning_rate": 4.800165698174481e-06, "loss": 0.1178, "step": 472270 }, { "epoch": 2.807330396894746, "grad_norm": 3.6496806144714355, "learning_rate": 4.799958372004149e-06, "loss": 0.1064, "step": 472280 }, { "epoch": 2.8073898389714143, "grad_norm": 3.738926887512207, "learning_rate": 4.799751046178312e-06, "loss": 0.0972, "step": 472290 }, { "epoch": 2.8074492810480827, "grad_norm": 4.112377643585205, "learning_rate": 4.799543720697328e-06, "loss": 0.1029, "step": 472300 }, { "epoch": 2.807508723124751, "grad_norm": 3.841829776763916, "learning_rate": 4.799336395561553e-06, "loss": 0.1069, "step": 472310 }, { "epoch": 2.8075681652014195, "grad_norm": 4.323728084564209, "learning_rate": 4.799129070771346e-06, "loss": 0.1191, "step": 472320 }, { "epoch": 2.807627607278088, "grad_norm": 4.035754203796387, "learning_rate": 4.798921746327062e-06, "loss": 0.1144, "step": 472330 }, { "epoch": 2.8076870493547563, "grad_norm": 4.50086784362793, "learning_rate": 4.798714422229059e-06, "loss": 0.1161, "step": 472340 }, { "epoch": 2.8077464914314247, "grad_norm": 3.24399995803833, "learning_rate": 4.798507098477693e-06, "loss": 0.101, "step": 472350 }, { "epoch": 2.807805933508093, "grad_norm": 4.789987564086914, "learning_rate": 4.7982997750733226e-06, "loss": 0.105, "step": 472360 }, { "epoch": 2.8078653755847616, "grad_norm": 4.488195419311523, "learning_rate": 4.798092452016304e-06, "loss": 0.1067, "step": 472370 }, { "epoch": 2.80792481766143, "grad_norm": 3.7663841247558594, "learning_rate": 4.797885129306993e-06, "loss": 0.1286, "step": 472380 }, { "epoch": 2.807984259738098, "grad_norm": 3.733778953552246, "learning_rate": 4.7976778069457495e-06, "loss": 0.1137, "step": 472390 }, { "epoch": 2.808043701814767, "grad_norm": 4.785774230957031, "learning_rate": 4.797470484932928e-06, "loss": 0.1197, "step": 472400 }, { "epoch": 2.808103143891435, "grad_norm": 5.205786228179932, "learning_rate": 4.7972631632688865e-06, "loss": 0.0986, "step": 472410 }, { "epoch": 2.8081625859681036, "grad_norm": 5.610711097717285, "learning_rate": 4.797055841953983e-06, "loss": 0.1214, "step": 472420 }, { "epoch": 2.8082220280447716, "grad_norm": 5.193997859954834, "learning_rate": 4.796848520988573e-06, "loss": 0.1154, "step": 472430 }, { "epoch": 2.80828147012144, "grad_norm": 3.889500856399536, "learning_rate": 4.7966412003730125e-06, "loss": 0.1, "step": 472440 }, { "epoch": 2.8083409121981084, "grad_norm": 3.5303635597229004, "learning_rate": 4.796433880107661e-06, "loss": 0.123, "step": 472450 }, { "epoch": 2.808400354274777, "grad_norm": 4.108987808227539, "learning_rate": 4.796226560192875e-06, "loss": 0.1229, "step": 472460 }, { "epoch": 2.8084597963514453, "grad_norm": 3.324540138244629, "learning_rate": 4.796019240629012e-06, "loss": 0.0996, "step": 472470 }, { "epoch": 2.8085192384281137, "grad_norm": 3.2383415699005127, "learning_rate": 4.795811921416427e-06, "loss": 0.1077, "step": 472480 }, { "epoch": 2.808578680504782, "grad_norm": 4.963465213775635, "learning_rate": 4.79560460255548e-06, "loss": 0.1141, "step": 472490 }, { "epoch": 2.8086381225814505, "grad_norm": 3.8037972450256348, "learning_rate": 4.7953972840465256e-06, "loss": 0.1016, "step": 472500 }, { "epoch": 2.808697564658119, "grad_norm": 4.697783946990967, "learning_rate": 4.79518996588992e-06, "loss": 0.1198, "step": 472510 }, { "epoch": 2.8087570067347873, "grad_norm": 4.294540882110596, "learning_rate": 4.7949826480860225e-06, "loss": 0.0991, "step": 472520 }, { "epoch": 2.8088164488114558, "grad_norm": 3.776401996612549, "learning_rate": 4.79477533063519e-06, "loss": 0.1156, "step": 472530 }, { "epoch": 2.808875890888124, "grad_norm": 3.0688560009002686, "learning_rate": 4.794568013537778e-06, "loss": 0.1076, "step": 472540 }, { "epoch": 2.8089353329647926, "grad_norm": 4.031825065612793, "learning_rate": 4.794360696794146e-06, "loss": 0.1153, "step": 472550 }, { "epoch": 2.808994775041461, "grad_norm": 4.820246696472168, "learning_rate": 4.7941533804046485e-06, "loss": 0.1091, "step": 472560 }, { "epoch": 2.8090542171181294, "grad_norm": 3.526491403579712, "learning_rate": 4.793946064369642e-06, "loss": 0.1153, "step": 472570 }, { "epoch": 2.8091136591947974, "grad_norm": 4.644326686859131, "learning_rate": 4.793738748689487e-06, "loss": 0.1048, "step": 472580 }, { "epoch": 2.8091731012714662, "grad_norm": 4.18638277053833, "learning_rate": 4.7935314333645375e-06, "loss": 0.1204, "step": 472590 }, { "epoch": 2.809232543348134, "grad_norm": 2.8071794509887695, "learning_rate": 4.793324118395151e-06, "loss": 0.1135, "step": 472600 }, { "epoch": 2.809291985424803, "grad_norm": 4.237844467163086, "learning_rate": 4.793116803781687e-06, "loss": 0.1006, "step": 472610 }, { "epoch": 2.809351427501471, "grad_norm": 3.9026615619659424, "learning_rate": 4.792909489524499e-06, "loss": 0.1077, "step": 472620 }, { "epoch": 2.8094108695781395, "grad_norm": 3.4483397006988525, "learning_rate": 4.792702175623945e-06, "loss": 0.1016, "step": 472630 }, { "epoch": 2.809470311654808, "grad_norm": 4.120546340942383, "learning_rate": 4.792494862080384e-06, "loss": 0.1072, "step": 472640 }, { "epoch": 2.8095297537314763, "grad_norm": 3.131408452987671, "learning_rate": 4.792287548894169e-06, "loss": 0.1029, "step": 472650 }, { "epoch": 2.8095891958081447, "grad_norm": 4.0643510818481445, "learning_rate": 4.792080236065662e-06, "loss": 0.1131, "step": 472660 }, { "epoch": 2.809648637884813, "grad_norm": 3.1260643005371094, "learning_rate": 4.791872923595218e-06, "loss": 0.0975, "step": 472670 }, { "epoch": 2.8097080799614815, "grad_norm": 4.139054298400879, "learning_rate": 4.791665611483193e-06, "loss": 0.1147, "step": 472680 }, { "epoch": 2.80976752203815, "grad_norm": 3.7355074882507324, "learning_rate": 4.7914582997299444e-06, "loss": 0.103, "step": 472690 }, { "epoch": 2.8098269641148184, "grad_norm": 3.5349888801574707, "learning_rate": 4.79125098833583e-06, "loss": 0.1139, "step": 472700 }, { "epoch": 2.8098864061914868, "grad_norm": 3.956486940383911, "learning_rate": 4.791043677301205e-06, "loss": 0.1128, "step": 472710 }, { "epoch": 2.809945848268155, "grad_norm": 3.6662485599517822, "learning_rate": 4.790836366626429e-06, "loss": 0.1125, "step": 472720 }, { "epoch": 2.8100052903448236, "grad_norm": 3.0314579010009766, "learning_rate": 4.790629056311858e-06, "loss": 0.1082, "step": 472730 }, { "epoch": 2.810064732421492, "grad_norm": 3.4584484100341797, "learning_rate": 4.7904217463578475e-06, "loss": 0.1059, "step": 472740 }, { "epoch": 2.8101241744981604, "grad_norm": 5.164830684661865, "learning_rate": 4.790214436764757e-06, "loss": 0.123, "step": 472750 }, { "epoch": 2.810183616574829, "grad_norm": 4.23685884475708, "learning_rate": 4.790007127532942e-06, "loss": 0.1045, "step": 472760 }, { "epoch": 2.810243058651497, "grad_norm": 1.9336750507354736, "learning_rate": 4.789799818662759e-06, "loss": 0.1106, "step": 472770 }, { "epoch": 2.8103025007281657, "grad_norm": 3.6903445720672607, "learning_rate": 4.7895925101545666e-06, "loss": 0.0992, "step": 472780 }, { "epoch": 2.8103619428048336, "grad_norm": 2.824525833129883, "learning_rate": 4.789385202008721e-06, "loss": 0.1062, "step": 472790 }, { "epoch": 2.810421384881502, "grad_norm": 4.487327575683594, "learning_rate": 4.789177894225579e-06, "loss": 0.104, "step": 472800 }, { "epoch": 2.8104808269581705, "grad_norm": 5.01832914352417, "learning_rate": 4.788970586805498e-06, "loss": 0.1074, "step": 472810 }, { "epoch": 2.810540269034839, "grad_norm": 4.249783992767334, "learning_rate": 4.788763279748834e-06, "loss": 0.1218, "step": 472820 }, { "epoch": 2.8105997111115073, "grad_norm": 2.7840754985809326, "learning_rate": 4.788555973055945e-06, "loss": 0.1044, "step": 472830 }, { "epoch": 2.8106591531881757, "grad_norm": 3.497905969619751, "learning_rate": 4.7883486667271885e-06, "loss": 0.1076, "step": 472840 }, { "epoch": 2.810718595264844, "grad_norm": 4.638433933258057, "learning_rate": 4.788141360762921e-06, "loss": 0.1013, "step": 472850 }, { "epoch": 2.8107780373415125, "grad_norm": 4.185982704162598, "learning_rate": 4.7879340551634984e-06, "loss": 0.1201, "step": 472860 }, { "epoch": 2.810837479418181, "grad_norm": 2.014439821243286, "learning_rate": 4.787726749929278e-06, "loss": 0.109, "step": 472870 }, { "epoch": 2.8108969214948494, "grad_norm": 3.373046875, "learning_rate": 4.787519445060619e-06, "loss": 0.1175, "step": 472880 }, { "epoch": 2.810956363571518, "grad_norm": 5.088770389556885, "learning_rate": 4.7873121405578765e-06, "loss": 0.1099, "step": 472890 }, { "epoch": 2.811015805648186, "grad_norm": 4.642082214355469, "learning_rate": 4.787104836421407e-06, "loss": 0.0974, "step": 472900 }, { "epoch": 2.8110752477248546, "grad_norm": 5.013284683227539, "learning_rate": 4.78689753265157e-06, "loss": 0.1236, "step": 472910 }, { "epoch": 2.811134689801523, "grad_norm": 4.379352569580078, "learning_rate": 4.7866902292487205e-06, "loss": 0.1011, "step": 472920 }, { "epoch": 2.8111941318781914, "grad_norm": 4.536629676818848, "learning_rate": 4.786482926213215e-06, "loss": 0.1045, "step": 472930 }, { "epoch": 2.8112535739548594, "grad_norm": 4.875397205352783, "learning_rate": 4.7862756235454126e-06, "loss": 0.0943, "step": 472940 }, { "epoch": 2.8113130160315283, "grad_norm": 6.353798866271973, "learning_rate": 4.786068321245668e-06, "loss": 0.1119, "step": 472950 }, { "epoch": 2.8113724581081962, "grad_norm": 4.981523513793945, "learning_rate": 4.785861019314339e-06, "loss": 0.1117, "step": 472960 }, { "epoch": 2.811431900184865, "grad_norm": 4.131721496582031, "learning_rate": 4.785653717751784e-06, "loss": 0.1143, "step": 472970 }, { "epoch": 2.811491342261533, "grad_norm": 3.2336573600769043, "learning_rate": 4.785446416558359e-06, "loss": 0.1159, "step": 472980 }, { "epoch": 2.8115507843382015, "grad_norm": 4.569096565246582, "learning_rate": 4.785239115734421e-06, "loss": 0.1042, "step": 472990 }, { "epoch": 2.81161022641487, "grad_norm": 3.760765314102173, "learning_rate": 4.785031815280325e-06, "loss": 0.0919, "step": 473000 }, { "epoch": 2.8116696684915383, "grad_norm": 3.735252857208252, "learning_rate": 4.784824515196432e-06, "loss": 0.1136, "step": 473010 }, { "epoch": 2.8117291105682067, "grad_norm": 5.4693684577941895, "learning_rate": 4.784617215483096e-06, "loss": 0.0981, "step": 473020 }, { "epoch": 2.811788552644875, "grad_norm": 4.1918721199035645, "learning_rate": 4.784409916140675e-06, "loss": 0.0962, "step": 473030 }, { "epoch": 2.8118479947215436, "grad_norm": 3.8192975521087646, "learning_rate": 4.784202617169525e-06, "loss": 0.13, "step": 473040 }, { "epoch": 2.811907436798212, "grad_norm": 5.019335746765137, "learning_rate": 4.783995318570005e-06, "loss": 0.1045, "step": 473050 }, { "epoch": 2.8119668788748804, "grad_norm": 4.820603847503662, "learning_rate": 4.78378802034247e-06, "loss": 0.1088, "step": 473060 }, { "epoch": 2.812026320951549, "grad_norm": 3.8854825496673584, "learning_rate": 4.783580722487278e-06, "loss": 0.0956, "step": 473070 }, { "epoch": 2.8120857630282172, "grad_norm": 3.1186583042144775, "learning_rate": 4.783373425004786e-06, "loss": 0.0964, "step": 473080 }, { "epoch": 2.8121452051048856, "grad_norm": 3.466588020324707, "learning_rate": 4.783166127895349e-06, "loss": 0.1135, "step": 473090 }, { "epoch": 2.812204647181554, "grad_norm": 3.4415929317474365, "learning_rate": 4.782958831159327e-06, "loss": 0.0988, "step": 473100 }, { "epoch": 2.8122640892582225, "grad_norm": 3.881869316101074, "learning_rate": 4.7827515347970766e-06, "loss": 0.1062, "step": 473110 }, { "epoch": 2.812323531334891, "grad_norm": 4.566694259643555, "learning_rate": 4.782544238808955e-06, "loss": 0.1106, "step": 473120 }, { "epoch": 2.812382973411559, "grad_norm": 2.8937625885009766, "learning_rate": 4.7823369431953154e-06, "loss": 0.1025, "step": 473130 }, { "epoch": 2.8124424154882277, "grad_norm": 3.1575987339019775, "learning_rate": 4.7821296479565196e-06, "loss": 0.104, "step": 473140 }, { "epoch": 2.8125018575648957, "grad_norm": 5.122725486755371, "learning_rate": 4.781922353092922e-06, "loss": 0.132, "step": 473150 }, { "epoch": 2.8125612996415645, "grad_norm": 3.893686294555664, "learning_rate": 4.7817150586048794e-06, "loss": 0.1211, "step": 473160 }, { "epoch": 2.8126207417182325, "grad_norm": 3.370490312576294, "learning_rate": 4.781507764492751e-06, "loss": 0.1084, "step": 473170 }, { "epoch": 2.812680183794901, "grad_norm": 3.132629632949829, "learning_rate": 4.781300470756891e-06, "loss": 0.1007, "step": 473180 }, { "epoch": 2.8127396258715693, "grad_norm": 3.6418182849884033, "learning_rate": 4.781093177397658e-06, "loss": 0.1041, "step": 473190 }, { "epoch": 2.8127990679482378, "grad_norm": 4.212584972381592, "learning_rate": 4.780885884415409e-06, "loss": 0.1353, "step": 473200 }, { "epoch": 2.812858510024906, "grad_norm": 4.191039562225342, "learning_rate": 4.780678591810501e-06, "loss": 0.1185, "step": 473210 }, { "epoch": 2.8129179521015746, "grad_norm": 4.617316246032715, "learning_rate": 4.780471299583289e-06, "loss": 0.107, "step": 473220 }, { "epoch": 2.812977394178243, "grad_norm": 4.185258865356445, "learning_rate": 4.780264007734134e-06, "loss": 0.1159, "step": 473230 }, { "epoch": 2.8130368362549114, "grad_norm": 3.5854861736297607, "learning_rate": 4.7800567162633894e-06, "loss": 0.096, "step": 473240 }, { "epoch": 2.81309627833158, "grad_norm": 2.8606925010681152, "learning_rate": 4.779849425171413e-06, "loss": 0.1028, "step": 473250 }, { "epoch": 2.8131557204082482, "grad_norm": 5.209929943084717, "learning_rate": 4.779642134458563e-06, "loss": 0.1054, "step": 473260 }, { "epoch": 2.8132151624849167, "grad_norm": 4.089043617248535, "learning_rate": 4.779434844125195e-06, "loss": 0.115, "step": 473270 }, { "epoch": 2.813274604561585, "grad_norm": 2.841878652572632, "learning_rate": 4.779227554171666e-06, "loss": 0.1071, "step": 473280 }, { "epoch": 2.8133340466382535, "grad_norm": 4.413088798522949, "learning_rate": 4.779020264598335e-06, "loss": 0.1262, "step": 473290 }, { "epoch": 2.813393488714922, "grad_norm": 4.1047797203063965, "learning_rate": 4.778812975405556e-06, "loss": 0.1104, "step": 473300 }, { "epoch": 2.8134529307915903, "grad_norm": 3.0675089359283447, "learning_rate": 4.778605686593686e-06, "loss": 0.1175, "step": 473310 }, { "epoch": 2.8135123728682583, "grad_norm": 4.300987720489502, "learning_rate": 4.778398398163086e-06, "loss": 0.1029, "step": 473320 }, { "epoch": 2.813571814944927, "grad_norm": 3.370497465133667, "learning_rate": 4.778191110114109e-06, "loss": 0.1071, "step": 473330 }, { "epoch": 2.813631257021595, "grad_norm": 4.041350364685059, "learning_rate": 4.777983822447115e-06, "loss": 0.1268, "step": 473340 }, { "epoch": 2.813690699098264, "grad_norm": 3.785074472427368, "learning_rate": 4.777776535162459e-06, "loss": 0.1162, "step": 473350 }, { "epoch": 2.813750141174932, "grad_norm": 3.4143505096435547, "learning_rate": 4.7775692482604966e-06, "loss": 0.0965, "step": 473360 }, { "epoch": 2.8138095832516004, "grad_norm": 4.505216121673584, "learning_rate": 4.777361961741588e-06, "loss": 0.1008, "step": 473370 }, { "epoch": 2.8138690253282688, "grad_norm": 3.6688015460968018, "learning_rate": 4.777154675606089e-06, "loss": 0.094, "step": 473380 }, { "epoch": 2.813928467404937, "grad_norm": 4.982427597045898, "learning_rate": 4.776947389854355e-06, "loss": 0.1158, "step": 473390 }, { "epoch": 2.8139879094816056, "grad_norm": 3.979102849960327, "learning_rate": 4.776740104486746e-06, "loss": 0.1065, "step": 473400 }, { "epoch": 2.814047351558274, "grad_norm": 3.019991636276245, "learning_rate": 4.776532819503616e-06, "loss": 0.1034, "step": 473410 }, { "epoch": 2.8141067936349424, "grad_norm": 5.265843391418457, "learning_rate": 4.776325534905322e-06, "loss": 0.1023, "step": 473420 }, { "epoch": 2.814166235711611, "grad_norm": 2.9774582386016846, "learning_rate": 4.776118250692224e-06, "loss": 0.1019, "step": 473430 }, { "epoch": 2.8142256777882793, "grad_norm": 3.2090983390808105, "learning_rate": 4.775910966864677e-06, "loss": 0.1058, "step": 473440 }, { "epoch": 2.8142851198649477, "grad_norm": 3.9241483211517334, "learning_rate": 4.775703683423036e-06, "loss": 0.1194, "step": 473450 }, { "epoch": 2.814344561941616, "grad_norm": 4.241925239562988, "learning_rate": 4.775496400367662e-06, "loss": 0.109, "step": 473460 }, { "epoch": 2.8144040040182845, "grad_norm": 3.6404612064361572, "learning_rate": 4.77528911769891e-06, "loss": 0.1007, "step": 473470 }, { "epoch": 2.814463446094953, "grad_norm": 4.1625566482543945, "learning_rate": 4.7750818354171354e-06, "loss": 0.1096, "step": 473480 }, { "epoch": 2.8145228881716213, "grad_norm": 3.7432971000671387, "learning_rate": 4.774874553522698e-06, "loss": 0.1076, "step": 473490 }, { "epoch": 2.8145823302482897, "grad_norm": 3.782106399536133, "learning_rate": 4.774667272015954e-06, "loss": 0.1091, "step": 473500 }, { "epoch": 2.8146417723249577, "grad_norm": 4.349160671234131, "learning_rate": 4.774459990897258e-06, "loss": 0.098, "step": 473510 }, { "epoch": 2.8147012144016266, "grad_norm": 3.0764517784118652, "learning_rate": 4.7742527101669705e-06, "loss": 0.1068, "step": 473520 }, { "epoch": 2.8147606564782945, "grad_norm": 5.499690055847168, "learning_rate": 4.774045429825444e-06, "loss": 0.1042, "step": 473530 }, { "epoch": 2.814820098554963, "grad_norm": 3.3188207149505615, "learning_rate": 4.77383814987304e-06, "loss": 0.1215, "step": 473540 }, { "epoch": 2.8148795406316314, "grad_norm": 3.1105966567993164, "learning_rate": 4.773630870310114e-06, "loss": 0.0937, "step": 473550 }, { "epoch": 2.8149389827083, "grad_norm": 4.667645454406738, "learning_rate": 4.773423591137023e-06, "loss": 0.1177, "step": 473560 }, { "epoch": 2.814998424784968, "grad_norm": 5.328487396240234, "learning_rate": 4.773216312354124e-06, "loss": 0.0939, "step": 473570 }, { "epoch": 2.8150578668616366, "grad_norm": 2.821045398712158, "learning_rate": 4.773009033961772e-06, "loss": 0.1068, "step": 473580 }, { "epoch": 2.815117308938305, "grad_norm": 4.245691299438477, "learning_rate": 4.772801755960327e-06, "loss": 0.1007, "step": 473590 }, { "epoch": 2.8151767510149734, "grad_norm": 4.986326217651367, "learning_rate": 4.772594478350144e-06, "loss": 0.1156, "step": 473600 }, { "epoch": 2.815236193091642, "grad_norm": 3.779350519180298, "learning_rate": 4.77238720113158e-06, "loss": 0.1233, "step": 473610 }, { "epoch": 2.8152956351683103, "grad_norm": 4.53007698059082, "learning_rate": 4.772179924304992e-06, "loss": 0.0991, "step": 473620 }, { "epoch": 2.8153550772449787, "grad_norm": 3.492083787918091, "learning_rate": 4.7719726478707395e-06, "loss": 0.1035, "step": 473630 }, { "epoch": 2.815414519321647, "grad_norm": 4.3103556632995605, "learning_rate": 4.7717653718291754e-06, "loss": 0.1101, "step": 473640 }, { "epoch": 2.8154739613983155, "grad_norm": 4.36736536026001, "learning_rate": 4.771558096180659e-06, "loss": 0.098, "step": 473650 }, { "epoch": 2.815533403474984, "grad_norm": 4.067546367645264, "learning_rate": 4.7713508209255475e-06, "loss": 0.1056, "step": 473660 }, { "epoch": 2.8155928455516523, "grad_norm": 3.6473846435546875, "learning_rate": 4.771143546064197e-06, "loss": 0.1089, "step": 473670 }, { "epoch": 2.8156522876283203, "grad_norm": 4.6240739822387695, "learning_rate": 4.770936271596963e-06, "loss": 0.1189, "step": 473680 }, { "epoch": 2.815711729704989, "grad_norm": 4.169110298156738, "learning_rate": 4.770728997524206e-06, "loss": 0.1138, "step": 473690 }, { "epoch": 2.815771171781657, "grad_norm": 4.44838285446167, "learning_rate": 4.77052172384628e-06, "loss": 0.1178, "step": 473700 }, { "epoch": 2.815830613858326, "grad_norm": 4.280568599700928, "learning_rate": 4.7703144505635424e-06, "loss": 0.0979, "step": 473710 }, { "epoch": 2.815890055934994, "grad_norm": 2.9787590503692627, "learning_rate": 4.770107177676352e-06, "loss": 0.0999, "step": 473720 }, { "epoch": 2.8159494980116624, "grad_norm": 4.3117756843566895, "learning_rate": 4.769899905185065e-06, "loss": 0.1111, "step": 473730 }, { "epoch": 2.816008940088331, "grad_norm": 7.3819427490234375, "learning_rate": 4.7696926330900355e-06, "loss": 0.1194, "step": 473740 }, { "epoch": 2.816068382164999, "grad_norm": 3.5526740550994873, "learning_rate": 4.769485361391623e-06, "loss": 0.1158, "step": 473750 }, { "epoch": 2.8161278242416676, "grad_norm": 3.398935317993164, "learning_rate": 4.7692780900901855e-06, "loss": 0.1047, "step": 473760 }, { "epoch": 2.816187266318336, "grad_norm": 2.663926124572754, "learning_rate": 4.769070819186079e-06, "loss": 0.1013, "step": 473770 }, { "epoch": 2.8162467083950045, "grad_norm": 4.187434196472168, "learning_rate": 4.768863548679658e-06, "loss": 0.1054, "step": 473780 }, { "epoch": 2.816306150471673, "grad_norm": 4.279110431671143, "learning_rate": 4.768656278571284e-06, "loss": 0.0985, "step": 473790 }, { "epoch": 2.8163655925483413, "grad_norm": 4.062070369720459, "learning_rate": 4.76844900886131e-06, "loss": 0.1173, "step": 473800 }, { "epoch": 2.8164250346250097, "grad_norm": 4.260349750518799, "learning_rate": 4.768241739550095e-06, "loss": 0.1214, "step": 473810 }, { "epoch": 2.816484476701678, "grad_norm": 4.771671295166016, "learning_rate": 4.768034470637995e-06, "loss": 0.1007, "step": 473820 }, { "epoch": 2.8165439187783465, "grad_norm": 3.224249839782715, "learning_rate": 4.767827202125369e-06, "loss": 0.1032, "step": 473830 }, { "epoch": 2.816603360855015, "grad_norm": 4.5814738273620605, "learning_rate": 4.76761993401257e-06, "loss": 0.1078, "step": 473840 }, { "epoch": 2.8166628029316834, "grad_norm": 3.207521915435791, "learning_rate": 4.767412666299958e-06, "loss": 0.1091, "step": 473850 }, { "epoch": 2.8167222450083518, "grad_norm": 4.620195388793945, "learning_rate": 4.7672053989878905e-06, "loss": 0.1065, "step": 473860 }, { "epoch": 2.8167816870850197, "grad_norm": 3.2584095001220703, "learning_rate": 4.7669981320767215e-06, "loss": 0.1138, "step": 473870 }, { "epoch": 2.8168411291616886, "grad_norm": 3.530766725540161, "learning_rate": 4.76679086556681e-06, "loss": 0.1088, "step": 473880 }, { "epoch": 2.8169005712383566, "grad_norm": 3.4511923789978027, "learning_rate": 4.766583599458512e-06, "loss": 0.0995, "step": 473890 }, { "epoch": 2.8169600133150254, "grad_norm": 5.82090950012207, "learning_rate": 4.766376333752185e-06, "loss": 0.1178, "step": 473900 }, { "epoch": 2.8170194553916934, "grad_norm": 3.514739751815796, "learning_rate": 4.7661690684481865e-06, "loss": 0.1041, "step": 473910 }, { "epoch": 2.817078897468362, "grad_norm": 3.6218020915985107, "learning_rate": 4.765961803546873e-06, "loss": 0.1163, "step": 473920 }, { "epoch": 2.8171383395450302, "grad_norm": 3.7364308834075928, "learning_rate": 4.7657545390486e-06, "loss": 0.1058, "step": 473930 }, { "epoch": 2.8171977816216986, "grad_norm": 4.786831378936768, "learning_rate": 4.765547274953727e-06, "loss": 0.1127, "step": 473940 }, { "epoch": 2.817257223698367, "grad_norm": 3.753734827041626, "learning_rate": 4.7653400112626085e-06, "loss": 0.1051, "step": 473950 }, { "epoch": 2.8173166657750355, "grad_norm": 5.343455791473389, "learning_rate": 4.765132747975602e-06, "loss": 0.1016, "step": 473960 }, { "epoch": 2.817376107851704, "grad_norm": 3.3569300174713135, "learning_rate": 4.764925485093065e-06, "loss": 0.1169, "step": 473970 }, { "epoch": 2.8174355499283723, "grad_norm": 4.772582530975342, "learning_rate": 4.764718222615355e-06, "loss": 0.1059, "step": 473980 }, { "epoch": 2.8174949920050407, "grad_norm": 3.257798433303833, "learning_rate": 4.764510960542828e-06, "loss": 0.0908, "step": 473990 }, { "epoch": 2.817554434081709, "grad_norm": 3.3745317459106445, "learning_rate": 4.764303698875842e-06, "loss": 0.1055, "step": 474000 }, { "epoch": 2.8176138761583776, "grad_norm": 3.6858434677124023, "learning_rate": 4.764096437614752e-06, "loss": 0.1253, "step": 474010 }, { "epoch": 2.817673318235046, "grad_norm": 3.9360671043395996, "learning_rate": 4.763889176759917e-06, "loss": 0.1051, "step": 474020 }, { "epoch": 2.8177327603117144, "grad_norm": 4.387058258056641, "learning_rate": 4.763681916311694e-06, "loss": 0.1217, "step": 474030 }, { "epoch": 2.817792202388383, "grad_norm": 3.921931266784668, "learning_rate": 4.763474656270436e-06, "loss": 0.1072, "step": 474040 }, { "epoch": 2.817851644465051, "grad_norm": 3.2925472259521484, "learning_rate": 4.763267396636506e-06, "loss": 0.1034, "step": 474050 }, { "epoch": 2.817911086541719, "grad_norm": 4.802941799163818, "learning_rate": 4.763060137410256e-06, "loss": 0.1048, "step": 474060 }, { "epoch": 2.817970528618388, "grad_norm": 3.451704502105713, "learning_rate": 4.762852878592045e-06, "loss": 0.1231, "step": 474070 }, { "epoch": 2.818029970695056, "grad_norm": 3.7849490642547607, "learning_rate": 4.76264562018223e-06, "loss": 0.1322, "step": 474080 }, { "epoch": 2.818089412771725, "grad_norm": 3.2290642261505127, "learning_rate": 4.762438362181168e-06, "loss": 0.106, "step": 474090 }, { "epoch": 2.818148854848393, "grad_norm": 4.884552478790283, "learning_rate": 4.762231104589213e-06, "loss": 0.1122, "step": 474100 }, { "epoch": 2.8182082969250613, "grad_norm": 4.011587619781494, "learning_rate": 4.762023847406727e-06, "loss": 0.1131, "step": 474110 }, { "epoch": 2.8182677390017297, "grad_norm": 3.6763741970062256, "learning_rate": 4.7618165906340644e-06, "loss": 0.1027, "step": 474120 }, { "epoch": 2.818327181078398, "grad_norm": 4.3453803062438965, "learning_rate": 4.76160933427158e-06, "loss": 0.1006, "step": 474130 }, { "epoch": 2.8183866231550665, "grad_norm": 4.790682315826416, "learning_rate": 4.761402078319635e-06, "loss": 0.1226, "step": 474140 }, { "epoch": 2.818446065231735, "grad_norm": 4.176286697387695, "learning_rate": 4.761194822778583e-06, "loss": 0.105, "step": 474150 }, { "epoch": 2.8185055073084033, "grad_norm": 2.861565351486206, "learning_rate": 4.760987567648782e-06, "loss": 0.1117, "step": 474160 }, { "epoch": 2.8185649493850717, "grad_norm": 3.7526872158050537, "learning_rate": 4.7607803129305885e-06, "loss": 0.1099, "step": 474170 }, { "epoch": 2.81862439146174, "grad_norm": 4.394618034362793, "learning_rate": 4.760573058624361e-06, "loss": 0.113, "step": 474180 }, { "epoch": 2.8186838335384086, "grad_norm": 4.050054550170898, "learning_rate": 4.760365804730453e-06, "loss": 0.1247, "step": 474190 }, { "epoch": 2.818743275615077, "grad_norm": 4.671175003051758, "learning_rate": 4.760158551249224e-06, "loss": 0.1189, "step": 474200 }, { "epoch": 2.8188027176917454, "grad_norm": 4.6912713050842285, "learning_rate": 4.7599512981810324e-06, "loss": 0.1064, "step": 474210 }, { "epoch": 2.818862159768414, "grad_norm": 3.128141403198242, "learning_rate": 4.7597440455262336e-06, "loss": 0.1025, "step": 474220 }, { "epoch": 2.8189216018450822, "grad_norm": 4.876981735229492, "learning_rate": 4.759536793285182e-06, "loss": 0.1087, "step": 474230 }, { "epoch": 2.8189810439217506, "grad_norm": 3.559847354888916, "learning_rate": 4.759329541458239e-06, "loss": 0.1164, "step": 474240 }, { "epoch": 2.8190404859984186, "grad_norm": 3.820124387741089, "learning_rate": 4.759122290045759e-06, "loss": 0.103, "step": 474250 }, { "epoch": 2.8190999280750875, "grad_norm": 4.624842643737793, "learning_rate": 4.758915039048097e-06, "loss": 0.1006, "step": 474260 }, { "epoch": 2.8191593701517554, "grad_norm": 4.028779029846191, "learning_rate": 4.758707788465615e-06, "loss": 0.1171, "step": 474270 }, { "epoch": 2.819218812228424, "grad_norm": 2.9335711002349854, "learning_rate": 4.758500538298666e-06, "loss": 0.1028, "step": 474280 }, { "epoch": 2.8192782543050923, "grad_norm": 3.543741226196289, "learning_rate": 4.758293288547606e-06, "loss": 0.1169, "step": 474290 }, { "epoch": 2.8193376963817607, "grad_norm": 4.529980182647705, "learning_rate": 4.758086039212796e-06, "loss": 0.1165, "step": 474300 }, { "epoch": 2.819397138458429, "grad_norm": 3.8391075134277344, "learning_rate": 4.75787879029459e-06, "loss": 0.1015, "step": 474310 }, { "epoch": 2.8194565805350975, "grad_norm": 3.526907444000244, "learning_rate": 4.7576715417933465e-06, "loss": 0.1056, "step": 474320 }, { "epoch": 2.819516022611766, "grad_norm": 3.7981157302856445, "learning_rate": 4.7574642937094195e-06, "loss": 0.1083, "step": 474330 }, { "epoch": 2.8195754646884343, "grad_norm": 2.618926525115967, "learning_rate": 4.7572570460431695e-06, "loss": 0.1103, "step": 474340 }, { "epoch": 2.8196349067651028, "grad_norm": 4.170910835266113, "learning_rate": 4.757049798794951e-06, "loss": 0.1173, "step": 474350 }, { "epoch": 2.819694348841771, "grad_norm": 3.8493192195892334, "learning_rate": 4.756842551965123e-06, "loss": 0.1079, "step": 474360 }, { "epoch": 2.8197537909184396, "grad_norm": 5.648859977722168, "learning_rate": 4.75663530555404e-06, "loss": 0.1245, "step": 474370 }, { "epoch": 2.819813232995108, "grad_norm": 3.5394797325134277, "learning_rate": 4.756428059562061e-06, "loss": 0.1038, "step": 474380 }, { "epoch": 2.8198726750717764, "grad_norm": 3.757838487625122, "learning_rate": 4.75622081398954e-06, "loss": 0.1093, "step": 474390 }, { "epoch": 2.819932117148445, "grad_norm": 4.2640485763549805, "learning_rate": 4.756013568836837e-06, "loss": 0.1309, "step": 474400 }, { "epoch": 2.8199915592251132, "grad_norm": 4.410687446594238, "learning_rate": 4.755806324104306e-06, "loss": 0.1062, "step": 474410 }, { "epoch": 2.820051001301781, "grad_norm": 3.8262946605682373, "learning_rate": 4.755599079792308e-06, "loss": 0.1157, "step": 474420 }, { "epoch": 2.82011044337845, "grad_norm": 4.182009696960449, "learning_rate": 4.755391835901196e-06, "loss": 0.1197, "step": 474430 }, { "epoch": 2.820169885455118, "grad_norm": 4.63845682144165, "learning_rate": 4.75518459243133e-06, "loss": 0.1151, "step": 474440 }, { "epoch": 2.820229327531787, "grad_norm": 4.494723320007324, "learning_rate": 4.754977349383066e-06, "loss": 0.1028, "step": 474450 }, { "epoch": 2.820288769608455, "grad_norm": 3.6322696208953857, "learning_rate": 4.754770106756757e-06, "loss": 0.1168, "step": 474460 }, { "epoch": 2.8203482116851233, "grad_norm": 4.4639081954956055, "learning_rate": 4.754562864552766e-06, "loss": 0.0885, "step": 474470 }, { "epoch": 2.8204076537617917, "grad_norm": 3.5917365550994873, "learning_rate": 4.754355622771447e-06, "loss": 0.1015, "step": 474480 }, { "epoch": 2.82046709583846, "grad_norm": 3.8123559951782227, "learning_rate": 4.7541483814131556e-06, "loss": 0.1022, "step": 474490 }, { "epoch": 2.8205265379151285, "grad_norm": 5.26992130279541, "learning_rate": 4.753941140478251e-06, "loss": 0.1065, "step": 474500 }, { "epoch": 2.820585979991797, "grad_norm": 3.4830944538116455, "learning_rate": 4.753733899967089e-06, "loss": 0.101, "step": 474510 }, { "epoch": 2.8206454220684654, "grad_norm": 3.592355966567993, "learning_rate": 4.7535266598800254e-06, "loss": 0.0975, "step": 474520 }, { "epoch": 2.8207048641451338, "grad_norm": 4.377410411834717, "learning_rate": 4.753319420217419e-06, "loss": 0.1049, "step": 474530 }, { "epoch": 2.820764306221802, "grad_norm": 3.1793177127838135, "learning_rate": 4.7531121809796275e-06, "loss": 0.0987, "step": 474540 }, { "epoch": 2.8208237482984706, "grad_norm": 3.955942153930664, "learning_rate": 4.752904942167004e-06, "loss": 0.1063, "step": 474550 }, { "epoch": 2.820883190375139, "grad_norm": 3.471295118331909, "learning_rate": 4.752697703779909e-06, "loss": 0.1191, "step": 474560 }, { "epoch": 2.8209426324518074, "grad_norm": 5.285064220428467, "learning_rate": 4.7524904658186974e-06, "loss": 0.111, "step": 474570 }, { "epoch": 2.821002074528476, "grad_norm": 6.159986972808838, "learning_rate": 4.752283228283726e-06, "loss": 0.1083, "step": 474580 }, { "epoch": 2.8210615166051443, "grad_norm": 3.0046818256378174, "learning_rate": 4.752075991175354e-06, "loss": 0.1091, "step": 474590 }, { "epoch": 2.8211209586818127, "grad_norm": 3.7572576999664307, "learning_rate": 4.751868754493937e-06, "loss": 0.105, "step": 474600 }, { "epoch": 2.8211804007584806, "grad_norm": 4.251533508300781, "learning_rate": 4.75166151823983e-06, "loss": 0.105, "step": 474610 }, { "epoch": 2.8212398428351495, "grad_norm": 4.133607387542725, "learning_rate": 4.751454282413393e-06, "loss": 0.1061, "step": 474620 }, { "epoch": 2.8212992849118175, "grad_norm": 3.68538498878479, "learning_rate": 4.7512470470149785e-06, "loss": 0.109, "step": 474630 }, { "epoch": 2.8213587269884863, "grad_norm": 3.671818971633911, "learning_rate": 4.751039812044949e-06, "loss": 0.1287, "step": 474640 }, { "epoch": 2.8214181690651543, "grad_norm": 2.9775705337524414, "learning_rate": 4.750832577503659e-06, "loss": 0.1243, "step": 474650 }, { "epoch": 2.8214776111418227, "grad_norm": 3.376596212387085, "learning_rate": 4.750625343391463e-06, "loss": 0.1138, "step": 474660 }, { "epoch": 2.821537053218491, "grad_norm": 2.6445329189300537, "learning_rate": 4.750418109708722e-06, "loss": 0.115, "step": 474670 }, { "epoch": 2.8215964952951595, "grad_norm": 4.086888790130615, "learning_rate": 4.75021087645579e-06, "loss": 0.1083, "step": 474680 }, { "epoch": 2.821655937371828, "grad_norm": 3.5851173400878906, "learning_rate": 4.750003643633023e-06, "loss": 0.1189, "step": 474690 }, { "epoch": 2.8217153794484964, "grad_norm": 3.054267168045044, "learning_rate": 4.7497964112407814e-06, "loss": 0.1134, "step": 474700 }, { "epoch": 2.821774821525165, "grad_norm": 3.273977041244507, "learning_rate": 4.749589179279421e-06, "loss": 0.108, "step": 474710 }, { "epoch": 2.821834263601833, "grad_norm": 3.6032681465148926, "learning_rate": 4.749381947749296e-06, "loss": 0.1064, "step": 474720 }, { "epoch": 2.8218937056785016, "grad_norm": 3.1265978813171387, "learning_rate": 4.7491747166507665e-06, "loss": 0.1074, "step": 474730 }, { "epoch": 2.82195314775517, "grad_norm": 3.759178400039673, "learning_rate": 4.748967485984187e-06, "loss": 0.1066, "step": 474740 }, { "epoch": 2.8220125898318384, "grad_norm": 2.746861219406128, "learning_rate": 4.748760255749916e-06, "loss": 0.1061, "step": 474750 }, { "epoch": 2.822072031908507, "grad_norm": 3.528618335723877, "learning_rate": 4.74855302594831e-06, "loss": 0.1069, "step": 474760 }, { "epoch": 2.8221314739851753, "grad_norm": 3.9483163356781006, "learning_rate": 4.748345796579727e-06, "loss": 0.1089, "step": 474770 }, { "epoch": 2.8221909160618437, "grad_norm": 2.954948663711548, "learning_rate": 4.748138567644519e-06, "loss": 0.1162, "step": 474780 }, { "epoch": 2.822250358138512, "grad_norm": 3.582103967666626, "learning_rate": 4.74793133914305e-06, "loss": 0.1064, "step": 474790 }, { "epoch": 2.82230980021518, "grad_norm": 2.9468677043914795, "learning_rate": 4.747724111075672e-06, "loss": 0.107, "step": 474800 }, { "epoch": 2.822369242291849, "grad_norm": 3.3168392181396484, "learning_rate": 4.747516883442742e-06, "loss": 0.1023, "step": 474810 }, { "epoch": 2.822428684368517, "grad_norm": 4.821378707885742, "learning_rate": 4.7473096562446194e-06, "loss": 0.1272, "step": 474820 }, { "epoch": 2.8224881264451858, "grad_norm": 4.151773452758789, "learning_rate": 4.747102429481659e-06, "loss": 0.1028, "step": 474830 }, { "epoch": 2.8225475685218537, "grad_norm": 3.463245153427124, "learning_rate": 4.746895203154218e-06, "loss": 0.11, "step": 474840 }, { "epoch": 2.822607010598522, "grad_norm": 3.9813992977142334, "learning_rate": 4.746687977262654e-06, "loss": 0.1164, "step": 474850 }, { "epoch": 2.8226664526751906, "grad_norm": 5.533403396606445, "learning_rate": 4.7464807518073236e-06, "loss": 0.1125, "step": 474860 }, { "epoch": 2.822725894751859, "grad_norm": 3.5533289909362793, "learning_rate": 4.746273526788585e-06, "loss": 0.1204, "step": 474870 }, { "epoch": 2.8227853368285274, "grad_norm": 5.707085132598877, "learning_rate": 4.746066302206791e-06, "loss": 0.1257, "step": 474880 }, { "epoch": 2.822844778905196, "grad_norm": 4.0992326736450195, "learning_rate": 4.745859078062304e-06, "loss": 0.0931, "step": 474890 }, { "epoch": 2.822904220981864, "grad_norm": 3.023733615875244, "learning_rate": 4.745651854355477e-06, "loss": 0.0969, "step": 474900 }, { "epoch": 2.8229636630585326, "grad_norm": 4.841632843017578, "learning_rate": 4.745444631086666e-06, "loss": 0.1113, "step": 474910 }, { "epoch": 2.823023105135201, "grad_norm": 3.3389945030212402, "learning_rate": 4.745237408256233e-06, "loss": 0.1105, "step": 474920 }, { "epoch": 2.8230825472118695, "grad_norm": 4.497150897979736, "learning_rate": 4.74503018586453e-06, "loss": 0.1106, "step": 474930 }, { "epoch": 2.823141989288538, "grad_norm": 4.341802597045898, "learning_rate": 4.744822963911914e-06, "loss": 0.1092, "step": 474940 }, { "epoch": 2.8232014313652063, "grad_norm": 4.388430118560791, "learning_rate": 4.744615742398746e-06, "loss": 0.1148, "step": 474950 }, { "epoch": 2.8232608734418747, "grad_norm": 4.345156192779541, "learning_rate": 4.744408521325378e-06, "loss": 0.112, "step": 474960 }, { "epoch": 2.823320315518543, "grad_norm": 3.7188544273376465, "learning_rate": 4.744201300692169e-06, "loss": 0.1075, "step": 474970 }, { "epoch": 2.8233797575952115, "grad_norm": 3.165951728820801, "learning_rate": 4.743994080499478e-06, "loss": 0.117, "step": 474980 }, { "epoch": 2.8234391996718795, "grad_norm": 4.393731594085693, "learning_rate": 4.743786860747659e-06, "loss": 0.0965, "step": 474990 }, { "epoch": 2.8234986417485484, "grad_norm": 4.159249782562256, "learning_rate": 4.743579641437069e-06, "loss": 0.1065, "step": 475000 }, { "epoch": 2.8235580838252163, "grad_norm": 3.348844051361084, "learning_rate": 4.743372422568065e-06, "loss": 0.1034, "step": 475010 }, { "epoch": 2.8236175259018848, "grad_norm": 3.529158592224121, "learning_rate": 4.743165204141005e-06, "loss": 0.1118, "step": 475020 }, { "epoch": 2.823676967978553, "grad_norm": 4.331596374511719, "learning_rate": 4.742957986156245e-06, "loss": 0.108, "step": 475030 }, { "epoch": 2.8237364100552216, "grad_norm": 4.770846843719482, "learning_rate": 4.742750768614142e-06, "loss": 0.1096, "step": 475040 }, { "epoch": 2.82379585213189, "grad_norm": 5.382373332977295, "learning_rate": 4.742543551515053e-06, "loss": 0.1299, "step": 475050 }, { "epoch": 2.8238552942085584, "grad_norm": 4.005972385406494, "learning_rate": 4.742336334859335e-06, "loss": 0.1118, "step": 475060 }, { "epoch": 2.823914736285227, "grad_norm": 4.315338134765625, "learning_rate": 4.742129118647342e-06, "loss": 0.0909, "step": 475070 }, { "epoch": 2.8239741783618952, "grad_norm": 4.656404495239258, "learning_rate": 4.741921902879435e-06, "loss": 0.1225, "step": 475080 }, { "epoch": 2.8240336204385637, "grad_norm": 4.292752742767334, "learning_rate": 4.74171468755597e-06, "loss": 0.1111, "step": 475090 }, { "epoch": 2.824093062515232, "grad_norm": 3.2411365509033203, "learning_rate": 4.741507472677304e-06, "loss": 0.1122, "step": 475100 }, { "epoch": 2.8241525045919005, "grad_norm": 4.504713535308838, "learning_rate": 4.74130025824379e-06, "loss": 0.1101, "step": 475110 }, { "epoch": 2.824211946668569, "grad_norm": 5.380188941955566, "learning_rate": 4.741093044255791e-06, "loss": 0.0966, "step": 475120 }, { "epoch": 2.8242713887452373, "grad_norm": 3.5074896812438965, "learning_rate": 4.740885830713659e-06, "loss": 0.0991, "step": 475130 }, { "epoch": 2.8243308308219057, "grad_norm": 5.445114612579346, "learning_rate": 4.740678617617753e-06, "loss": 0.1028, "step": 475140 }, { "epoch": 2.824390272898574, "grad_norm": 3.4515464305877686, "learning_rate": 4.7404714049684295e-06, "loss": 0.0983, "step": 475150 }, { "epoch": 2.824449714975242, "grad_norm": 3.8987879753112793, "learning_rate": 4.7402641927660455e-06, "loss": 0.1125, "step": 475160 }, { "epoch": 2.824509157051911, "grad_norm": 4.33411979675293, "learning_rate": 4.740056981010957e-06, "loss": 0.0993, "step": 475170 }, { "epoch": 2.824568599128579, "grad_norm": 3.8029797077178955, "learning_rate": 4.739849769703521e-06, "loss": 0.1047, "step": 475180 }, { "epoch": 2.824628041205248, "grad_norm": 4.954029560089111, "learning_rate": 4.739642558844096e-06, "loss": 0.1215, "step": 475190 }, { "epoch": 2.8246874832819158, "grad_norm": 5.3823723793029785, "learning_rate": 4.739435348433036e-06, "loss": 0.1199, "step": 475200 }, { "epoch": 2.824746925358584, "grad_norm": 3.455705165863037, "learning_rate": 4.739228138470701e-06, "loss": 0.098, "step": 475210 }, { "epoch": 2.8248063674352526, "grad_norm": 4.178382396697998, "learning_rate": 4.739020928957446e-06, "loss": 0.1079, "step": 475220 }, { "epoch": 2.824865809511921, "grad_norm": 4.546302795410156, "learning_rate": 4.738813719893627e-06, "loss": 0.12, "step": 475230 }, { "epoch": 2.8249252515885894, "grad_norm": 4.706247329711914, "learning_rate": 4.7386065112796024e-06, "loss": 0.1039, "step": 475240 }, { "epoch": 2.824984693665258, "grad_norm": 4.963430404663086, "learning_rate": 4.738399303115729e-06, "loss": 0.1032, "step": 475250 }, { "epoch": 2.8250441357419263, "grad_norm": 3.7727909088134766, "learning_rate": 4.738192095402362e-06, "loss": 0.1159, "step": 475260 }, { "epoch": 2.8251035778185947, "grad_norm": 3.802877426147461, "learning_rate": 4.737984888139861e-06, "loss": 0.0939, "step": 475270 }, { "epoch": 2.825163019895263, "grad_norm": 4.241728782653809, "learning_rate": 4.7377776813285815e-06, "loss": 0.1427, "step": 475280 }, { "epoch": 2.8252224619719315, "grad_norm": 2.608165979385376, "learning_rate": 4.737570474968877e-06, "loss": 0.1072, "step": 475290 }, { "epoch": 2.8252819040486, "grad_norm": 4.225358963012695, "learning_rate": 4.73736326906111e-06, "loss": 0.1124, "step": 475300 }, { "epoch": 2.8253413461252683, "grad_norm": 3.2408974170684814, "learning_rate": 4.737156063605634e-06, "loss": 0.1218, "step": 475310 }, { "epoch": 2.8254007882019367, "grad_norm": 4.19413423538208, "learning_rate": 4.736948858602807e-06, "loss": 0.1033, "step": 475320 }, { "epoch": 2.825460230278605, "grad_norm": 4.600121974945068, "learning_rate": 4.736741654052987e-06, "loss": 0.106, "step": 475330 }, { "epoch": 2.8255196723552736, "grad_norm": 3.457991123199463, "learning_rate": 4.736534449956527e-06, "loss": 0.1129, "step": 475340 }, { "epoch": 2.8255791144319415, "grad_norm": 3.8856494426727295, "learning_rate": 4.736327246313787e-06, "loss": 0.1129, "step": 475350 }, { "epoch": 2.8256385565086104, "grad_norm": 3.280487060546875, "learning_rate": 4.736120043125123e-06, "loss": 0.1146, "step": 475360 }, { "epoch": 2.8256979985852784, "grad_norm": 3.1070828437805176, "learning_rate": 4.735912840390891e-06, "loss": 0.093, "step": 475370 }, { "epoch": 2.8257574406619472, "grad_norm": 4.064425945281982, "learning_rate": 4.73570563811145e-06, "loss": 0.0923, "step": 475380 }, { "epoch": 2.825816882738615, "grad_norm": 3.787184238433838, "learning_rate": 4.735498436287155e-06, "loss": 0.1213, "step": 475390 }, { "epoch": 2.8258763248152836, "grad_norm": 3.325977087020874, "learning_rate": 4.735291234918362e-06, "loss": 0.1064, "step": 475400 }, { "epoch": 2.825935766891952, "grad_norm": 5.018526077270508, "learning_rate": 4.73508403400543e-06, "loss": 0.1042, "step": 475410 }, { "epoch": 2.8259952089686204, "grad_norm": 4.1516289710998535, "learning_rate": 4.734876833548716e-06, "loss": 0.1084, "step": 475420 }, { "epoch": 2.826054651045289, "grad_norm": 3.097346067428589, "learning_rate": 4.734669633548574e-06, "loss": 0.1163, "step": 475430 }, { "epoch": 2.8261140931219573, "grad_norm": 3.163057804107666, "learning_rate": 4.7344624340053635e-06, "loss": 0.1247, "step": 475440 }, { "epoch": 2.8261735351986257, "grad_norm": 3.328409433364868, "learning_rate": 4.7342552349194405e-06, "loss": 0.1131, "step": 475450 }, { "epoch": 2.826232977275294, "grad_norm": 4.351337909698486, "learning_rate": 4.734048036291161e-06, "loss": 0.0986, "step": 475460 }, { "epoch": 2.8262924193519625, "grad_norm": 3.9239821434020996, "learning_rate": 4.733840838120883e-06, "loss": 0.1123, "step": 475470 }, { "epoch": 2.826351861428631, "grad_norm": 3.2235052585601807, "learning_rate": 4.733633640408963e-06, "loss": 0.1112, "step": 475480 }, { "epoch": 2.8264113035052993, "grad_norm": 3.5838921070098877, "learning_rate": 4.733426443155756e-06, "loss": 0.1057, "step": 475490 }, { "epoch": 2.8264707455819678, "grad_norm": 4.467966556549072, "learning_rate": 4.7332192463616225e-06, "loss": 0.118, "step": 475500 }, { "epoch": 2.826530187658636, "grad_norm": 3.6563186645507812, "learning_rate": 4.733012050026915e-06, "loss": 0.0961, "step": 475510 }, { "epoch": 2.8265896297353046, "grad_norm": 4.500316619873047, "learning_rate": 4.732804854151995e-06, "loss": 0.1011, "step": 475520 }, { "epoch": 2.826649071811973, "grad_norm": 4.880105495452881, "learning_rate": 4.732597658737214e-06, "loss": 0.1135, "step": 475530 }, { "epoch": 2.826708513888641, "grad_norm": 3.420393705368042, "learning_rate": 4.732390463782935e-06, "loss": 0.1029, "step": 475540 }, { "epoch": 2.82676795596531, "grad_norm": 3.487236738204956, "learning_rate": 4.732183269289511e-06, "loss": 0.1236, "step": 475550 }, { "epoch": 2.826827398041978, "grad_norm": 4.334819793701172, "learning_rate": 4.731976075257298e-06, "loss": 0.1093, "step": 475560 }, { "epoch": 2.8268868401186467, "grad_norm": 3.3342154026031494, "learning_rate": 4.731768881686655e-06, "loss": 0.1106, "step": 475570 }, { "epoch": 2.8269462821953146, "grad_norm": 3.2625606060028076, "learning_rate": 4.731561688577939e-06, "loss": 0.1064, "step": 475580 }, { "epoch": 2.827005724271983, "grad_norm": 3.9983105659484863, "learning_rate": 4.731354495931503e-06, "loss": 0.1052, "step": 475590 }, { "epoch": 2.8270651663486515, "grad_norm": 2.7921292781829834, "learning_rate": 4.731147303747709e-06, "loss": 0.1021, "step": 475600 }, { "epoch": 2.82712460842532, "grad_norm": 4.815619945526123, "learning_rate": 4.730940112026912e-06, "loss": 0.1068, "step": 475610 }, { "epoch": 2.8271840505019883, "grad_norm": 3.951918840408325, "learning_rate": 4.730732920769466e-06, "loss": 0.1256, "step": 475620 }, { "epoch": 2.8272434925786567, "grad_norm": 3.341111421585083, "learning_rate": 4.7305257299757315e-06, "loss": 0.1267, "step": 475630 }, { "epoch": 2.827302934655325, "grad_norm": 4.256954193115234, "learning_rate": 4.730318539646063e-06, "loss": 0.1117, "step": 475640 }, { "epoch": 2.8273623767319935, "grad_norm": 4.977780342102051, "learning_rate": 4.730111349780819e-06, "loss": 0.1482, "step": 475650 }, { "epoch": 2.827421818808662, "grad_norm": 5.860856533050537, "learning_rate": 4.729904160380354e-06, "loss": 0.103, "step": 475660 }, { "epoch": 2.8274812608853304, "grad_norm": 4.540063858032227, "learning_rate": 4.729696971445028e-06, "loss": 0.0982, "step": 475670 }, { "epoch": 2.8275407029619988, "grad_norm": 4.408272743225098, "learning_rate": 4.729489782975196e-06, "loss": 0.102, "step": 475680 }, { "epoch": 2.827600145038667, "grad_norm": 5.181882381439209, "learning_rate": 4.729282594971213e-06, "loss": 0.1109, "step": 475690 }, { "epoch": 2.8276595871153356, "grad_norm": 4.176555633544922, "learning_rate": 4.729075407433439e-06, "loss": 0.1053, "step": 475700 }, { "epoch": 2.8277190291920036, "grad_norm": 4.067418575286865, "learning_rate": 4.72886822036223e-06, "loss": 0.1103, "step": 475710 }, { "epoch": 2.8277784712686724, "grad_norm": 4.216155052185059, "learning_rate": 4.728661033757941e-06, "loss": 0.1036, "step": 475720 }, { "epoch": 2.8278379133453404, "grad_norm": 4.341436862945557, "learning_rate": 4.728453847620929e-06, "loss": 0.1066, "step": 475730 }, { "epoch": 2.8278973554220093, "grad_norm": 3.323260545730591, "learning_rate": 4.728246661951554e-06, "loss": 0.0935, "step": 475740 }, { "epoch": 2.8279567974986772, "grad_norm": 3.7727479934692383, "learning_rate": 4.7280394767501704e-06, "loss": 0.1031, "step": 475750 }, { "epoch": 2.8280162395753456, "grad_norm": 3.9505045413970947, "learning_rate": 4.727832292017134e-06, "loss": 0.1088, "step": 475760 }, { "epoch": 2.828075681652014, "grad_norm": 3.8868372440338135, "learning_rate": 4.727625107752805e-06, "loss": 0.1137, "step": 475770 }, { "epoch": 2.8281351237286825, "grad_norm": 4.993115425109863, "learning_rate": 4.727417923957537e-06, "loss": 0.1072, "step": 475780 }, { "epoch": 2.828194565805351, "grad_norm": 3.7854652404785156, "learning_rate": 4.727210740631687e-06, "loss": 0.11, "step": 475790 }, { "epoch": 2.8282540078820193, "grad_norm": 2.99977445602417, "learning_rate": 4.727003557775614e-06, "loss": 0.0946, "step": 475800 }, { "epoch": 2.8283134499586877, "grad_norm": 4.096765041351318, "learning_rate": 4.7267963753896736e-06, "loss": 0.0961, "step": 475810 }, { "epoch": 2.828372892035356, "grad_norm": 3.47501540184021, "learning_rate": 4.7265891934742206e-06, "loss": 0.1179, "step": 475820 }, { "epoch": 2.8284323341120245, "grad_norm": 2.9526193141937256, "learning_rate": 4.726382012029615e-06, "loss": 0.1057, "step": 475830 }, { "epoch": 2.828491776188693, "grad_norm": 2.654876708984375, "learning_rate": 4.726174831056213e-06, "loss": 0.1035, "step": 475840 }, { "epoch": 2.8285512182653614, "grad_norm": 2.981370449066162, "learning_rate": 4.72596765055437e-06, "loss": 0.1181, "step": 475850 }, { "epoch": 2.82861066034203, "grad_norm": 4.118561267852783, "learning_rate": 4.725760470524443e-06, "loss": 0.0948, "step": 475860 }, { "epoch": 2.828670102418698, "grad_norm": 4.476684093475342, "learning_rate": 4.72555329096679e-06, "loss": 0.1152, "step": 475870 }, { "epoch": 2.8287295444953666, "grad_norm": 3.7481091022491455, "learning_rate": 4.725346111881765e-06, "loss": 0.1102, "step": 475880 }, { "epoch": 2.828788986572035, "grad_norm": 4.423442363739014, "learning_rate": 4.725138933269729e-06, "loss": 0.1028, "step": 475890 }, { "epoch": 2.828848428648703, "grad_norm": 4.895909786224365, "learning_rate": 4.7249317551310355e-06, "loss": 0.1128, "step": 475900 }, { "epoch": 2.828907870725372, "grad_norm": 4.822875499725342, "learning_rate": 4.724724577466041e-06, "loss": 0.1016, "step": 475910 }, { "epoch": 2.82896731280204, "grad_norm": 4.004491329193115, "learning_rate": 4.724517400275106e-06, "loss": 0.1056, "step": 475920 }, { "epoch": 2.8290267548787087, "grad_norm": 3.7920894622802734, "learning_rate": 4.7243102235585845e-06, "loss": 0.113, "step": 475930 }, { "epoch": 2.8290861969553767, "grad_norm": 3.766552448272705, "learning_rate": 4.724103047316832e-06, "loss": 0.1056, "step": 475940 }, { "epoch": 2.829145639032045, "grad_norm": 2.551703929901123, "learning_rate": 4.723895871550208e-06, "loss": 0.0933, "step": 475950 }, { "epoch": 2.8292050811087135, "grad_norm": 3.957681179046631, "learning_rate": 4.723688696259067e-06, "loss": 0.1099, "step": 475960 }, { "epoch": 2.829264523185382, "grad_norm": 3.9771218299865723, "learning_rate": 4.723481521443769e-06, "loss": 0.1039, "step": 475970 }, { "epoch": 2.8293239652620503, "grad_norm": 5.064356327056885, "learning_rate": 4.723274347104669e-06, "loss": 0.1314, "step": 475980 }, { "epoch": 2.8293834073387187, "grad_norm": 2.7952322959899902, "learning_rate": 4.723067173242122e-06, "loss": 0.0979, "step": 475990 }, { "epoch": 2.829442849415387, "grad_norm": 3.2258241176605225, "learning_rate": 4.722859999856487e-06, "loss": 0.1012, "step": 476000 }, { "epoch": 2.8295022914920556, "grad_norm": 4.550058841705322, "learning_rate": 4.722652826948121e-06, "loss": 0.1257, "step": 476010 }, { "epoch": 2.829561733568724, "grad_norm": 3.4695615768432617, "learning_rate": 4.722445654517378e-06, "loss": 0.1062, "step": 476020 }, { "epoch": 2.8296211756453924, "grad_norm": 3.182394027709961, "learning_rate": 4.7222384825646185e-06, "loss": 0.0932, "step": 476030 }, { "epoch": 2.829680617722061, "grad_norm": 3.8241539001464844, "learning_rate": 4.722031311090198e-06, "loss": 0.127, "step": 476040 }, { "epoch": 2.8297400597987292, "grad_norm": 3.565988302230835, "learning_rate": 4.721824140094471e-06, "loss": 0.1031, "step": 476050 }, { "epoch": 2.8297995018753976, "grad_norm": 3.4760172367095947, "learning_rate": 4.721616969577797e-06, "loss": 0.1041, "step": 476060 }, { "epoch": 2.829858943952066, "grad_norm": 3.903402328491211, "learning_rate": 4.721409799540531e-06, "loss": 0.0985, "step": 476070 }, { "epoch": 2.8299183860287345, "grad_norm": 3.8591315746307373, "learning_rate": 4.721202629983031e-06, "loss": 0.1036, "step": 476080 }, { "epoch": 2.8299778281054024, "grad_norm": 4.229403018951416, "learning_rate": 4.720995460905654e-06, "loss": 0.0926, "step": 476090 }, { "epoch": 2.8300372701820713, "grad_norm": 5.771942615509033, "learning_rate": 4.7207882923087554e-06, "loss": 0.1241, "step": 476100 }, { "epoch": 2.8300967122587393, "grad_norm": 4.039346218109131, "learning_rate": 4.720581124192692e-06, "loss": 0.1122, "step": 476110 }, { "epoch": 2.830156154335408, "grad_norm": 3.6521685123443604, "learning_rate": 4.7203739565578226e-06, "loss": 0.1034, "step": 476120 }, { "epoch": 2.830215596412076, "grad_norm": 3.7784721851348877, "learning_rate": 4.720166789404502e-06, "loss": 0.1181, "step": 476130 }, { "epoch": 2.8302750384887445, "grad_norm": 3.5246007442474365, "learning_rate": 4.7199596227330875e-06, "loss": 0.1009, "step": 476140 }, { "epoch": 2.830334480565413, "grad_norm": 3.1127467155456543, "learning_rate": 4.719752456543936e-06, "loss": 0.1076, "step": 476150 }, { "epoch": 2.8303939226420813, "grad_norm": 4.198526859283447, "learning_rate": 4.719545290837405e-06, "loss": 0.1076, "step": 476160 }, { "epoch": 2.8304533647187498, "grad_norm": 3.49873948097229, "learning_rate": 4.719338125613847e-06, "loss": 0.1183, "step": 476170 }, { "epoch": 2.830512806795418, "grad_norm": 3.822237968444824, "learning_rate": 4.7191309608736255e-06, "loss": 0.1114, "step": 476180 }, { "epoch": 2.8305722488720866, "grad_norm": 3.0665481090545654, "learning_rate": 4.718923796617093e-06, "loss": 0.1025, "step": 476190 }, { "epoch": 2.830631690948755, "grad_norm": 4.358186721801758, "learning_rate": 4.718716632844609e-06, "loss": 0.1097, "step": 476200 }, { "epoch": 2.8306911330254234, "grad_norm": 3.8292319774627686, "learning_rate": 4.718509469556526e-06, "loss": 0.1104, "step": 476210 }, { "epoch": 2.830750575102092, "grad_norm": 5.337949275970459, "learning_rate": 4.718302306753205e-06, "loss": 0.1055, "step": 476220 }, { "epoch": 2.8308100171787602, "grad_norm": 4.765507698059082, "learning_rate": 4.718095144435001e-06, "loss": 0.1192, "step": 476230 }, { "epoch": 2.8308694592554287, "grad_norm": 4.514401912689209, "learning_rate": 4.717887982602269e-06, "loss": 0.1144, "step": 476240 }, { "epoch": 2.830928901332097, "grad_norm": 3.2437446117401123, "learning_rate": 4.71768082125537e-06, "loss": 0.1093, "step": 476250 }, { "epoch": 2.8309883434087655, "grad_norm": 3.0290029048919678, "learning_rate": 4.717473660394657e-06, "loss": 0.1124, "step": 476260 }, { "epoch": 2.831047785485434, "grad_norm": 4.548487663269043, "learning_rate": 4.717266500020488e-06, "loss": 0.0882, "step": 476270 }, { "epoch": 2.831107227562102, "grad_norm": 2.7207157611846924, "learning_rate": 4.71705934013322e-06, "loss": 0.1017, "step": 476280 }, { "epoch": 2.8311666696387707, "grad_norm": 3.993246078491211, "learning_rate": 4.716852180733211e-06, "loss": 0.1081, "step": 476290 }, { "epoch": 2.8312261117154387, "grad_norm": 3.8782496452331543, "learning_rate": 4.716645021820814e-06, "loss": 0.0945, "step": 476300 }, { "epoch": 2.8312855537921076, "grad_norm": 3.593336343765259, "learning_rate": 4.7164378633963895e-06, "loss": 0.098, "step": 476310 }, { "epoch": 2.8313449958687755, "grad_norm": 4.93858003616333, "learning_rate": 4.716230705460293e-06, "loss": 0.1045, "step": 476320 }, { "epoch": 2.831404437945444, "grad_norm": 3.591219902038574, "learning_rate": 4.7160235480128805e-06, "loss": 0.1035, "step": 476330 }, { "epoch": 2.8314638800221124, "grad_norm": 4.804654121398926, "learning_rate": 4.715816391054509e-06, "loss": 0.1041, "step": 476340 }, { "epoch": 2.8315233220987808, "grad_norm": 4.605743408203125, "learning_rate": 4.7156092345855366e-06, "loss": 0.1007, "step": 476350 }, { "epoch": 2.831582764175449, "grad_norm": 3.601735830307007, "learning_rate": 4.715402078606318e-06, "loss": 0.1067, "step": 476360 }, { "epoch": 2.8316422062521176, "grad_norm": 3.7347915172576904, "learning_rate": 4.715194923117211e-06, "loss": 0.111, "step": 476370 }, { "epoch": 2.831701648328786, "grad_norm": 3.811351776123047, "learning_rate": 4.714987768118573e-06, "loss": 0.11, "step": 476380 }, { "epoch": 2.8317610904054544, "grad_norm": 4.203622817993164, "learning_rate": 4.714780613610758e-06, "loss": 0.1136, "step": 476390 }, { "epoch": 2.831820532482123, "grad_norm": 2.5791537761688232, "learning_rate": 4.714573459594128e-06, "loss": 0.1051, "step": 476400 }, { "epoch": 2.8318799745587913, "grad_norm": 3.720644474029541, "learning_rate": 4.714366306069034e-06, "loss": 0.1164, "step": 476410 }, { "epoch": 2.8319394166354597, "grad_norm": 4.188634395599365, "learning_rate": 4.714159153035836e-06, "loss": 0.1064, "step": 476420 }, { "epoch": 2.831998858712128, "grad_norm": 3.041182518005371, "learning_rate": 4.713952000494891e-06, "loss": 0.1037, "step": 476430 }, { "epoch": 2.8320583007887965, "grad_norm": 3.9216854572296143, "learning_rate": 4.7137448484465536e-06, "loss": 0.1064, "step": 476440 }, { "epoch": 2.8321177428654645, "grad_norm": 3.6230504512786865, "learning_rate": 4.713537696891183e-06, "loss": 0.0904, "step": 476450 }, { "epoch": 2.8321771849421333, "grad_norm": 2.6780810356140137, "learning_rate": 4.713330545829134e-06, "loss": 0.1107, "step": 476460 }, { "epoch": 2.8322366270188013, "grad_norm": 4.758692741394043, "learning_rate": 4.713123395260763e-06, "loss": 0.1059, "step": 476470 }, { "epoch": 2.83229606909547, "grad_norm": 4.269704341888428, "learning_rate": 4.71291624518643e-06, "loss": 0.1118, "step": 476480 }, { "epoch": 2.832355511172138, "grad_norm": 5.542088985443115, "learning_rate": 4.7127090956064886e-06, "loss": 0.1097, "step": 476490 }, { "epoch": 2.8324149532488065, "grad_norm": 2.2664880752563477, "learning_rate": 4.712501946521295e-06, "loss": 0.1026, "step": 476500 }, { "epoch": 2.832474395325475, "grad_norm": 3.2348263263702393, "learning_rate": 4.712294797931209e-06, "loss": 0.0947, "step": 476510 }, { "epoch": 2.8325338374021434, "grad_norm": 4.475553035736084, "learning_rate": 4.712087649836585e-06, "loss": 0.1131, "step": 476520 }, { "epoch": 2.832593279478812, "grad_norm": 4.488205909729004, "learning_rate": 4.71188050223778e-06, "loss": 0.1126, "step": 476530 }, { "epoch": 2.83265272155548, "grad_norm": 5.827805995941162, "learning_rate": 4.711673355135153e-06, "loss": 0.1054, "step": 476540 }, { "epoch": 2.8327121636321486, "grad_norm": 5.173871040344238, "learning_rate": 4.7114662085290576e-06, "loss": 0.0979, "step": 476550 }, { "epoch": 2.832771605708817, "grad_norm": 4.220853805541992, "learning_rate": 4.7112590624198506e-06, "loss": 0.1072, "step": 476560 }, { "epoch": 2.8328310477854854, "grad_norm": 3.7633626461029053, "learning_rate": 4.711051916807892e-06, "loss": 0.1125, "step": 476570 }, { "epoch": 2.832890489862154, "grad_norm": 2.4249799251556396, "learning_rate": 4.710844771693536e-06, "loss": 0.1179, "step": 476580 }, { "epoch": 2.8329499319388223, "grad_norm": 3.4140756130218506, "learning_rate": 4.710637627077139e-06, "loss": 0.1105, "step": 476590 }, { "epoch": 2.8330093740154907, "grad_norm": 4.962898254394531, "learning_rate": 4.710430482959059e-06, "loss": 0.1176, "step": 476600 }, { "epoch": 2.833068816092159, "grad_norm": 4.701440334320068, "learning_rate": 4.71022333933965e-06, "loss": 0.1134, "step": 476610 }, { "epoch": 2.8331282581688275, "grad_norm": 4.918734073638916, "learning_rate": 4.710016196219274e-06, "loss": 0.1002, "step": 476620 }, { "epoch": 2.833187700245496, "grad_norm": 4.358545780181885, "learning_rate": 4.709809053598285e-06, "loss": 0.1118, "step": 476630 }, { "epoch": 2.833247142322164, "grad_norm": 3.935581684112549, "learning_rate": 4.709601911477037e-06, "loss": 0.1002, "step": 476640 }, { "epoch": 2.8333065843988328, "grad_norm": 3.881145477294922, "learning_rate": 4.7093947698558905e-06, "loss": 0.1082, "step": 476650 }, { "epoch": 2.8333660264755007, "grad_norm": 3.7393131256103516, "learning_rate": 4.709187628735202e-06, "loss": 0.1178, "step": 476660 }, { "epoch": 2.8334254685521696, "grad_norm": 4.007824420928955, "learning_rate": 4.708980488115325e-06, "loss": 0.1062, "step": 476670 }, { "epoch": 2.8334849106288376, "grad_norm": 4.382791042327881, "learning_rate": 4.7087733479966195e-06, "loss": 0.1046, "step": 476680 }, { "epoch": 2.833544352705506, "grad_norm": 4.880180358886719, "learning_rate": 4.7085662083794415e-06, "loss": 0.1034, "step": 476690 }, { "epoch": 2.8336037947821744, "grad_norm": 4.191766738891602, "learning_rate": 4.708359069264146e-06, "loss": 0.1004, "step": 476700 }, { "epoch": 2.833663236858843, "grad_norm": 4.415421485900879, "learning_rate": 4.708151930651091e-06, "loss": 0.1259, "step": 476710 }, { "epoch": 2.833722678935511, "grad_norm": 4.599427223205566, "learning_rate": 4.707944792540635e-06, "loss": 0.1005, "step": 476720 }, { "epoch": 2.8337821210121796, "grad_norm": 3.1532747745513916, "learning_rate": 4.707737654933131e-06, "loss": 0.1043, "step": 476730 }, { "epoch": 2.833841563088848, "grad_norm": 4.0415520668029785, "learning_rate": 4.7075305178289385e-06, "loss": 0.0935, "step": 476740 }, { "epoch": 2.8339010051655165, "grad_norm": 4.683077812194824, "learning_rate": 4.707323381228413e-06, "loss": 0.0976, "step": 476750 }, { "epoch": 2.833960447242185, "grad_norm": 3.6670994758605957, "learning_rate": 4.7071162451319116e-06, "loss": 0.1114, "step": 476760 }, { "epoch": 2.8340198893188533, "grad_norm": 4.493033409118652, "learning_rate": 4.706909109539792e-06, "loss": 0.0992, "step": 476770 }, { "epoch": 2.8340793313955217, "grad_norm": 3.3867640495300293, "learning_rate": 4.706701974452409e-06, "loss": 0.0905, "step": 476780 }, { "epoch": 2.83413877347219, "grad_norm": 4.069035053253174, "learning_rate": 4.706494839870119e-06, "loss": 0.1113, "step": 476790 }, { "epoch": 2.8341982155488585, "grad_norm": 5.50670862197876, "learning_rate": 4.706287705793282e-06, "loss": 0.1078, "step": 476800 }, { "epoch": 2.834257657625527, "grad_norm": 4.851612091064453, "learning_rate": 4.706080572222252e-06, "loss": 0.1088, "step": 476810 }, { "epoch": 2.8343170997021954, "grad_norm": 3.6021292209625244, "learning_rate": 4.7058734391573855e-06, "loss": 0.1026, "step": 476820 }, { "epoch": 2.8343765417788633, "grad_norm": 3.957221031188965, "learning_rate": 4.705666306599039e-06, "loss": 0.1156, "step": 476830 }, { "epoch": 2.834435983855532, "grad_norm": 3.17219614982605, "learning_rate": 4.705459174547572e-06, "loss": 0.1177, "step": 476840 }, { "epoch": 2.8344954259322, "grad_norm": 4.162848949432373, "learning_rate": 4.705252043003339e-06, "loss": 0.1095, "step": 476850 }, { "epoch": 2.834554868008869, "grad_norm": 4.276887893676758, "learning_rate": 4.705044911966697e-06, "loss": 0.1061, "step": 476860 }, { "epoch": 2.834614310085537, "grad_norm": 3.2920374870300293, "learning_rate": 4.704837781438004e-06, "loss": 0.107, "step": 476870 }, { "epoch": 2.8346737521622054, "grad_norm": 5.66179084777832, "learning_rate": 4.7046306514176145e-06, "loss": 0.1271, "step": 476880 }, { "epoch": 2.834733194238874, "grad_norm": 4.57274055480957, "learning_rate": 4.704423521905887e-06, "loss": 0.1056, "step": 476890 }, { "epoch": 2.8347926363155422, "grad_norm": 4.2998199462890625, "learning_rate": 4.704216392903177e-06, "loss": 0.0975, "step": 476900 }, { "epoch": 2.8348520783922107, "grad_norm": 3.433673143386841, "learning_rate": 4.704009264409842e-06, "loss": 0.0983, "step": 476910 }, { "epoch": 2.834911520468879, "grad_norm": 2.394717216491699, "learning_rate": 4.703802136426238e-06, "loss": 0.0954, "step": 476920 }, { "epoch": 2.8349709625455475, "grad_norm": 2.8082220554351807, "learning_rate": 4.703595008952722e-06, "loss": 0.1083, "step": 476930 }, { "epoch": 2.835030404622216, "grad_norm": 4.650120258331299, "learning_rate": 4.703387881989651e-06, "loss": 0.1053, "step": 476940 }, { "epoch": 2.8350898466988843, "grad_norm": 3.2797791957855225, "learning_rate": 4.703180755537381e-06, "loss": 0.1042, "step": 476950 }, { "epoch": 2.8351492887755527, "grad_norm": 4.816488265991211, "learning_rate": 4.702973629596269e-06, "loss": 0.1209, "step": 476960 }, { "epoch": 2.835208730852221, "grad_norm": 5.136066913604736, "learning_rate": 4.702766504166674e-06, "loss": 0.1159, "step": 476970 }, { "epoch": 2.8352681729288896, "grad_norm": 4.193192958831787, "learning_rate": 4.702559379248948e-06, "loss": 0.0944, "step": 476980 }, { "epoch": 2.835327615005558, "grad_norm": 3.8959507942199707, "learning_rate": 4.7023522548434516e-06, "loss": 0.1023, "step": 476990 }, { "epoch": 2.8353870570822264, "grad_norm": 3.485764980316162, "learning_rate": 4.70214513095054e-06, "loss": 0.0999, "step": 477000 }, { "epoch": 2.835446499158895, "grad_norm": 3.1444857120513916, "learning_rate": 4.70193800757057e-06, "loss": 0.099, "step": 477010 }, { "epoch": 2.8355059412355628, "grad_norm": 4.335665702819824, "learning_rate": 4.701730884703897e-06, "loss": 0.1132, "step": 477020 }, { "epoch": 2.8355653833122316, "grad_norm": 3.877420425415039, "learning_rate": 4.701523762350881e-06, "loss": 0.1135, "step": 477030 }, { "epoch": 2.8356248253888996, "grad_norm": 4.758901596069336, "learning_rate": 4.701316640511876e-06, "loss": 0.1035, "step": 477040 }, { "epoch": 2.8356842674655685, "grad_norm": 3.1957452297210693, "learning_rate": 4.701109519187237e-06, "loss": 0.0987, "step": 477050 }, { "epoch": 2.8357437095422364, "grad_norm": 4.458977699279785, "learning_rate": 4.700902398377324e-06, "loss": 0.0949, "step": 477060 }, { "epoch": 2.835803151618905, "grad_norm": 4.782702445983887, "learning_rate": 4.700695278082495e-06, "loss": 0.1046, "step": 477070 }, { "epoch": 2.8358625936955733, "grad_norm": 5.857643127441406, "learning_rate": 4.700488158303104e-06, "loss": 0.1088, "step": 477080 }, { "epoch": 2.8359220357722417, "grad_norm": 4.039458274841309, "learning_rate": 4.7002810390395065e-06, "loss": 0.1102, "step": 477090 }, { "epoch": 2.83598147784891, "grad_norm": 3.043435573577881, "learning_rate": 4.700073920292062e-06, "loss": 0.0969, "step": 477100 }, { "epoch": 2.8360409199255785, "grad_norm": 3.7840218544006348, "learning_rate": 4.699866802061126e-06, "loss": 0.1022, "step": 477110 }, { "epoch": 2.836100362002247, "grad_norm": 4.887964725494385, "learning_rate": 4.699659684347054e-06, "loss": 0.1262, "step": 477120 }, { "epoch": 2.8361598040789153, "grad_norm": 5.393960952758789, "learning_rate": 4.699452567150205e-06, "loss": 0.1061, "step": 477130 }, { "epoch": 2.8362192461555837, "grad_norm": 3.1184067726135254, "learning_rate": 4.699245450470935e-06, "loss": 0.0975, "step": 477140 }, { "epoch": 2.836278688232252, "grad_norm": 4.172455787658691, "learning_rate": 4.6990383343096e-06, "loss": 0.1051, "step": 477150 }, { "epoch": 2.8363381303089206, "grad_norm": 5.532349586486816, "learning_rate": 4.698831218666557e-06, "loss": 0.1139, "step": 477160 }, { "epoch": 2.836397572385589, "grad_norm": 4.27547550201416, "learning_rate": 4.698624103542162e-06, "loss": 0.1237, "step": 477170 }, { "epoch": 2.8364570144622574, "grad_norm": 3.452479839324951, "learning_rate": 4.698416988936772e-06, "loss": 0.1146, "step": 477180 }, { "epoch": 2.8365164565389254, "grad_norm": 4.6763715744018555, "learning_rate": 4.698209874850744e-06, "loss": 0.1204, "step": 477190 }, { "epoch": 2.8365758986155942, "grad_norm": 4.901756763458252, "learning_rate": 4.698002761284435e-06, "loss": 0.1123, "step": 477200 }, { "epoch": 2.836635340692262, "grad_norm": 3.998847007751465, "learning_rate": 4.6977956482382005e-06, "loss": 0.1088, "step": 477210 }, { "epoch": 2.836694782768931, "grad_norm": 2.8174493312835693, "learning_rate": 4.6975885357124e-06, "loss": 0.1021, "step": 477220 }, { "epoch": 2.836754224845599, "grad_norm": 3.804020404815674, "learning_rate": 4.697381423707387e-06, "loss": 0.0931, "step": 477230 }, { "epoch": 2.8368136669222674, "grad_norm": 3.7858550548553467, "learning_rate": 4.697174312223518e-06, "loss": 0.1113, "step": 477240 }, { "epoch": 2.836873108998936, "grad_norm": 5.294626235961914, "learning_rate": 4.696967201261152e-06, "loss": 0.1243, "step": 477250 }, { "epoch": 2.8369325510756043, "grad_norm": 4.2465410232543945, "learning_rate": 4.696760090820645e-06, "loss": 0.1109, "step": 477260 }, { "epoch": 2.8369919931522727, "grad_norm": 2.8319923877716064, "learning_rate": 4.696552980902351e-06, "loss": 0.0996, "step": 477270 }, { "epoch": 2.837051435228941, "grad_norm": 2.4174492359161377, "learning_rate": 4.696345871506632e-06, "loss": 0.1011, "step": 477280 }, { "epoch": 2.8371108773056095, "grad_norm": 4.037694931030273, "learning_rate": 4.6961387626338394e-06, "loss": 0.0897, "step": 477290 }, { "epoch": 2.837170319382278, "grad_norm": 3.7159271240234375, "learning_rate": 4.695931654284334e-06, "loss": 0.1144, "step": 477300 }, { "epoch": 2.8372297614589463, "grad_norm": 4.051205635070801, "learning_rate": 4.69572454645847e-06, "loss": 0.1011, "step": 477310 }, { "epoch": 2.8372892035356148, "grad_norm": 3.494792938232422, "learning_rate": 4.695517439156604e-06, "loss": 0.1187, "step": 477320 }, { "epoch": 2.837348645612283, "grad_norm": 4.24592399597168, "learning_rate": 4.695310332379094e-06, "loss": 0.1151, "step": 477330 }, { "epoch": 2.8374080876889516, "grad_norm": 4.4830427169799805, "learning_rate": 4.695103226126296e-06, "loss": 0.1271, "step": 477340 }, { "epoch": 2.83746752976562, "grad_norm": 3.6448230743408203, "learning_rate": 4.6948961203985655e-06, "loss": 0.103, "step": 477350 }, { "epoch": 2.8375269718422884, "grad_norm": 3.757199287414551, "learning_rate": 4.6946890151962615e-06, "loss": 0.1158, "step": 477360 }, { "epoch": 2.837586413918957, "grad_norm": 3.770097255706787, "learning_rate": 4.69448191051974e-06, "loss": 0.0949, "step": 477370 }, { "epoch": 2.837645855995625, "grad_norm": 4.608975887298584, "learning_rate": 4.694274806369355e-06, "loss": 0.1218, "step": 477380 }, { "epoch": 2.8377052980722937, "grad_norm": 3.796684741973877, "learning_rate": 4.6940677027454665e-06, "loss": 0.1051, "step": 477390 }, { "epoch": 2.8377647401489616, "grad_norm": 3.754986524581909, "learning_rate": 4.693860599648431e-06, "loss": 0.084, "step": 477400 }, { "epoch": 2.8378241822256305, "grad_norm": 6.147909641265869, "learning_rate": 4.693653497078602e-06, "loss": 0.1146, "step": 477410 }, { "epoch": 2.8378836243022985, "grad_norm": 3.654778003692627, "learning_rate": 4.69344639503634e-06, "loss": 0.1099, "step": 477420 }, { "epoch": 2.837943066378967, "grad_norm": 6.2516374588012695, "learning_rate": 4.693239293521999e-06, "loss": 0.0901, "step": 477430 }, { "epoch": 2.8380025084556353, "grad_norm": 4.490063190460205, "learning_rate": 4.693032192535936e-06, "loss": 0.1188, "step": 477440 }, { "epoch": 2.8380619505323037, "grad_norm": 4.186642646789551, "learning_rate": 4.692825092078509e-06, "loss": 0.1128, "step": 477450 }, { "epoch": 2.838121392608972, "grad_norm": 4.603583812713623, "learning_rate": 4.6926179921500746e-06, "loss": 0.1128, "step": 477460 }, { "epoch": 2.8381808346856405, "grad_norm": 4.872081756591797, "learning_rate": 4.6924108927509865e-06, "loss": 0.1071, "step": 477470 }, { "epoch": 2.838240276762309, "grad_norm": 5.195791721343994, "learning_rate": 4.692203793881605e-06, "loss": 0.1019, "step": 477480 }, { "epoch": 2.8382997188389774, "grad_norm": 4.2319416999816895, "learning_rate": 4.691996695542284e-06, "loss": 0.1039, "step": 477490 }, { "epoch": 2.8383591609156458, "grad_norm": 3.794447660446167, "learning_rate": 4.691789597733382e-06, "loss": 0.0985, "step": 477500 }, { "epoch": 2.838418602992314, "grad_norm": 4.5347771644592285, "learning_rate": 4.691582500455255e-06, "loss": 0.1123, "step": 477510 }, { "epoch": 2.8384780450689826, "grad_norm": 4.417347431182861, "learning_rate": 4.691375403708261e-06, "loss": 0.0982, "step": 477520 }, { "epoch": 2.838537487145651, "grad_norm": 3.984671115875244, "learning_rate": 4.691168307492755e-06, "loss": 0.0996, "step": 477530 }, { "epoch": 2.8385969292223194, "grad_norm": 4.701215744018555, "learning_rate": 4.690961211809093e-06, "loss": 0.1045, "step": 477540 }, { "epoch": 2.838656371298988, "grad_norm": 4.4573493003845215, "learning_rate": 4.690754116657634e-06, "loss": 0.1014, "step": 477550 }, { "epoch": 2.8387158133756563, "grad_norm": 2.943467617034912, "learning_rate": 4.690547022038733e-06, "loss": 0.0947, "step": 477560 }, { "epoch": 2.8387752554523242, "grad_norm": 4.007503032684326, "learning_rate": 4.6903399279527455e-06, "loss": 0.116, "step": 477570 }, { "epoch": 2.838834697528993, "grad_norm": 3.0599169731140137, "learning_rate": 4.690132834400031e-06, "loss": 0.0972, "step": 477580 }, { "epoch": 2.838894139605661, "grad_norm": 4.15785026550293, "learning_rate": 4.689925741380945e-06, "loss": 0.1083, "step": 477590 }, { "epoch": 2.83895358168233, "grad_norm": 3.807950496673584, "learning_rate": 4.689718648895843e-06, "loss": 0.1167, "step": 477600 }, { "epoch": 2.839013023758998, "grad_norm": 4.595221996307373, "learning_rate": 4.6895115569450835e-06, "loss": 0.1073, "step": 477610 }, { "epoch": 2.8390724658356663, "grad_norm": 3.6299757957458496, "learning_rate": 4.689304465529022e-06, "loss": 0.1197, "step": 477620 }, { "epoch": 2.8391319079123347, "grad_norm": 3.4642724990844727, "learning_rate": 4.689097374648014e-06, "loss": 0.1051, "step": 477630 }, { "epoch": 2.839191349989003, "grad_norm": 3.653548002243042, "learning_rate": 4.688890284302418e-06, "loss": 0.1206, "step": 477640 }, { "epoch": 2.8392507920656715, "grad_norm": 4.302069664001465, "learning_rate": 4.688683194492591e-06, "loss": 0.1224, "step": 477650 }, { "epoch": 2.83931023414234, "grad_norm": 3.2831997871398926, "learning_rate": 4.688476105218888e-06, "loss": 0.0972, "step": 477660 }, { "epoch": 2.8393696762190084, "grad_norm": 2.9524426460266113, "learning_rate": 4.688269016481666e-06, "loss": 0.1145, "step": 477670 }, { "epoch": 2.839429118295677, "grad_norm": 4.747842788696289, "learning_rate": 4.688061928281282e-06, "loss": 0.1117, "step": 477680 }, { "epoch": 2.839488560372345, "grad_norm": 3.694434404373169, "learning_rate": 4.687854840618094e-06, "loss": 0.1081, "step": 477690 }, { "epoch": 2.8395480024490136, "grad_norm": 2.9375998973846436, "learning_rate": 4.6876477534924545e-06, "loss": 0.0972, "step": 477700 }, { "epoch": 2.839607444525682, "grad_norm": 3.7503767013549805, "learning_rate": 4.687440666904723e-06, "loss": 0.0959, "step": 477710 }, { "epoch": 2.8396668866023504, "grad_norm": 4.519845485687256, "learning_rate": 4.687233580855257e-06, "loss": 0.1138, "step": 477720 }, { "epoch": 2.839726328679019, "grad_norm": 3.6585452556610107, "learning_rate": 4.687026495344413e-06, "loss": 0.1067, "step": 477730 }, { "epoch": 2.8397857707556873, "grad_norm": 2.7053959369659424, "learning_rate": 4.686819410372546e-06, "loss": 0.0926, "step": 477740 }, { "epoch": 2.8398452128323557, "grad_norm": 4.148777961730957, "learning_rate": 4.686612325940013e-06, "loss": 0.107, "step": 477750 }, { "epoch": 2.8399046549090237, "grad_norm": 7.583125114440918, "learning_rate": 4.686405242047172e-06, "loss": 0.1293, "step": 477760 }, { "epoch": 2.8399640969856925, "grad_norm": 3.553774833679199, "learning_rate": 4.686198158694378e-06, "loss": 0.1198, "step": 477770 }, { "epoch": 2.8400235390623605, "grad_norm": 3.5143539905548096, "learning_rate": 4.685991075881988e-06, "loss": 0.1187, "step": 477780 }, { "epoch": 2.8400829811390294, "grad_norm": 3.9196531772613525, "learning_rate": 4.685783993610359e-06, "loss": 0.0978, "step": 477790 }, { "epoch": 2.8401424232156973, "grad_norm": 4.637929439544678, "learning_rate": 4.685576911879847e-06, "loss": 0.1029, "step": 477800 }, { "epoch": 2.8402018652923657, "grad_norm": 4.690952301025391, "learning_rate": 4.6853698306908105e-06, "loss": 0.1062, "step": 477810 }, { "epoch": 2.840261307369034, "grad_norm": 4.775407314300537, "learning_rate": 4.685162750043604e-06, "loss": 0.1155, "step": 477820 }, { "epoch": 2.8403207494457026, "grad_norm": 4.363637924194336, "learning_rate": 4.684955669938584e-06, "loss": 0.1154, "step": 477830 }, { "epoch": 2.840380191522371, "grad_norm": 4.396363735198975, "learning_rate": 4.6847485903761086e-06, "loss": 0.1055, "step": 477840 }, { "epoch": 2.8404396335990394, "grad_norm": 3.866872787475586, "learning_rate": 4.684541511356534e-06, "loss": 0.1115, "step": 477850 }, { "epoch": 2.840499075675708, "grad_norm": 4.218038082122803, "learning_rate": 4.684334432880216e-06, "loss": 0.1021, "step": 477860 }, { "epoch": 2.840558517752376, "grad_norm": 2.7578046321868896, "learning_rate": 4.684127354947512e-06, "loss": 0.1139, "step": 477870 }, { "epoch": 2.8406179598290446, "grad_norm": 3.829500913619995, "learning_rate": 4.683920277558779e-06, "loss": 0.1049, "step": 477880 }, { "epoch": 2.840677401905713, "grad_norm": 3.4286811351776123, "learning_rate": 4.683713200714372e-06, "loss": 0.0991, "step": 477890 }, { "epoch": 2.8407368439823815, "grad_norm": 3.6378540992736816, "learning_rate": 4.683506124414649e-06, "loss": 0.11, "step": 477900 }, { "epoch": 2.84079628605905, "grad_norm": 3.991274833679199, "learning_rate": 4.683299048659967e-06, "loss": 0.1137, "step": 477910 }, { "epoch": 2.8408557281357183, "grad_norm": 3.579193592071533, "learning_rate": 4.68309197345068e-06, "loss": 0.0989, "step": 477920 }, { "epoch": 2.8409151702123863, "grad_norm": 3.599113702774048, "learning_rate": 4.682884898787147e-06, "loss": 0.1115, "step": 477930 }, { "epoch": 2.840974612289055, "grad_norm": 5.130702972412109, "learning_rate": 4.682677824669724e-06, "loss": 0.1069, "step": 477940 }, { "epoch": 2.841034054365723, "grad_norm": 4.056717872619629, "learning_rate": 4.682470751098767e-06, "loss": 0.1164, "step": 477950 }, { "epoch": 2.841093496442392, "grad_norm": 3.9681358337402344, "learning_rate": 4.682263678074635e-06, "loss": 0.113, "step": 477960 }, { "epoch": 2.84115293851906, "grad_norm": 5.397768974304199, "learning_rate": 4.682056605597682e-06, "loss": 0.1074, "step": 477970 }, { "epoch": 2.8412123805957283, "grad_norm": 4.118869304656982, "learning_rate": 4.6818495336682664e-06, "loss": 0.0909, "step": 477980 }, { "epoch": 2.8412718226723968, "grad_norm": 4.271079063415527, "learning_rate": 4.681642462286744e-06, "loss": 0.1089, "step": 477990 }, { "epoch": 2.841331264749065, "grad_norm": 3.3661606311798096, "learning_rate": 4.681435391453469e-06, "loss": 0.1009, "step": 478000 }, { "epoch": 2.8413907068257336, "grad_norm": 4.534430027008057, "learning_rate": 4.6812283211688025e-06, "loss": 0.1076, "step": 478010 }, { "epoch": 2.841450148902402, "grad_norm": 4.2631402015686035, "learning_rate": 4.681021251433098e-06, "loss": 0.0978, "step": 478020 }, { "epoch": 2.8415095909790704, "grad_norm": 2.8593413829803467, "learning_rate": 4.680814182246712e-06, "loss": 0.1133, "step": 478030 }, { "epoch": 2.841569033055739, "grad_norm": 5.278101921081543, "learning_rate": 4.680607113610004e-06, "loss": 0.1127, "step": 478040 }, { "epoch": 2.8416284751324072, "grad_norm": 4.707160949707031, "learning_rate": 4.6804000455233285e-06, "loss": 0.1071, "step": 478050 }, { "epoch": 2.8416879172090757, "grad_norm": 5.115980625152588, "learning_rate": 4.680192977987041e-06, "loss": 0.1204, "step": 478060 }, { "epoch": 2.841747359285744, "grad_norm": 3.9061052799224854, "learning_rate": 4.6799859110015004e-06, "loss": 0.1079, "step": 478070 }, { "epoch": 2.8418068013624125, "grad_norm": 4.337467193603516, "learning_rate": 4.679778844567062e-06, "loss": 0.0953, "step": 478080 }, { "epoch": 2.841866243439081, "grad_norm": 5.134036064147949, "learning_rate": 4.679571778684081e-06, "loss": 0.1009, "step": 478090 }, { "epoch": 2.8419256855157493, "grad_norm": 3.7745132446289062, "learning_rate": 4.679364713352918e-06, "loss": 0.0918, "step": 478100 }, { "epoch": 2.8419851275924177, "grad_norm": 3.839184045791626, "learning_rate": 4.679157648573926e-06, "loss": 0.0923, "step": 478110 }, { "epoch": 2.8420445696690857, "grad_norm": 4.708909511566162, "learning_rate": 4.678950584347462e-06, "loss": 0.1174, "step": 478120 }, { "epoch": 2.8421040117457546, "grad_norm": 6.33848237991333, "learning_rate": 4.678743520673885e-06, "loss": 0.1328, "step": 478130 }, { "epoch": 2.8421634538224225, "grad_norm": 3.434408187866211, "learning_rate": 4.67853645755355e-06, "loss": 0.1118, "step": 478140 }, { "epoch": 2.8422228958990914, "grad_norm": 5.296510219573975, "learning_rate": 4.6783293949868115e-06, "loss": 0.0959, "step": 478150 }, { "epoch": 2.8422823379757594, "grad_norm": 3.1821744441986084, "learning_rate": 4.678122332974029e-06, "loss": 0.1025, "step": 478160 }, { "epoch": 2.8423417800524278, "grad_norm": 4.413675308227539, "learning_rate": 4.677915271515559e-06, "loss": 0.1096, "step": 478170 }, { "epoch": 2.842401222129096, "grad_norm": 3.6485416889190674, "learning_rate": 4.677708210611758e-06, "loss": 0.0888, "step": 478180 }, { "epoch": 2.8424606642057646, "grad_norm": 2.9190962314605713, "learning_rate": 4.67750115026298e-06, "loss": 0.1069, "step": 478190 }, { "epoch": 2.842520106282433, "grad_norm": 4.318924903869629, "learning_rate": 4.677294090469585e-06, "loss": 0.1036, "step": 478200 }, { "epoch": 2.8425795483591014, "grad_norm": 3.231973171234131, "learning_rate": 4.677087031231928e-06, "loss": 0.0967, "step": 478210 }, { "epoch": 2.84263899043577, "grad_norm": 3.687253952026367, "learning_rate": 4.6768799725503646e-06, "loss": 0.1, "step": 478220 }, { "epoch": 2.8426984325124383, "grad_norm": 4.489024639129639, "learning_rate": 4.676672914425254e-06, "loss": 0.1164, "step": 478230 }, { "epoch": 2.8427578745891067, "grad_norm": 4.1450090408325195, "learning_rate": 4.676465856856951e-06, "loss": 0.1073, "step": 478240 }, { "epoch": 2.842817316665775, "grad_norm": 5.92892599105835, "learning_rate": 4.676258799845811e-06, "loss": 0.1319, "step": 478250 }, { "epoch": 2.8428767587424435, "grad_norm": 3.0793349742889404, "learning_rate": 4.676051743392193e-06, "loss": 0.1167, "step": 478260 }, { "epoch": 2.842936200819112, "grad_norm": 4.83029317855835, "learning_rate": 4.675844687496453e-06, "loss": 0.107, "step": 478270 }, { "epoch": 2.8429956428957803, "grad_norm": 4.097120761871338, "learning_rate": 4.675637632158946e-06, "loss": 0.1103, "step": 478280 }, { "epoch": 2.8430550849724487, "grad_norm": 4.280012607574463, "learning_rate": 4.67543057738003e-06, "loss": 0.1226, "step": 478290 }, { "epoch": 2.843114527049117, "grad_norm": 3.9919655323028564, "learning_rate": 4.675223523160062e-06, "loss": 0.1124, "step": 478300 }, { "epoch": 2.843173969125785, "grad_norm": 3.8206183910369873, "learning_rate": 4.675016469499397e-06, "loss": 0.0969, "step": 478310 }, { "epoch": 2.843233411202454, "grad_norm": 3.2061078548431396, "learning_rate": 4.674809416398393e-06, "loss": 0.1301, "step": 478320 }, { "epoch": 2.843292853279122, "grad_norm": 4.0193023681640625, "learning_rate": 4.674602363857406e-06, "loss": 0.1017, "step": 478330 }, { "epoch": 2.843352295355791, "grad_norm": 3.3523707389831543, "learning_rate": 4.674395311876793e-06, "loss": 0.1064, "step": 478340 }, { "epoch": 2.843411737432459, "grad_norm": 3.443025588989258, "learning_rate": 4.6741882604569085e-06, "loss": 0.1098, "step": 478350 }, { "epoch": 2.843471179509127, "grad_norm": 4.887172222137451, "learning_rate": 4.6739812095981115e-06, "loss": 0.1024, "step": 478360 }, { "epoch": 2.8435306215857956, "grad_norm": 3.7353177070617676, "learning_rate": 4.673774159300756e-06, "loss": 0.0968, "step": 478370 }, { "epoch": 2.843590063662464, "grad_norm": 5.702771186828613, "learning_rate": 4.673567109565203e-06, "loss": 0.1055, "step": 478380 }, { "epoch": 2.8436495057391324, "grad_norm": 5.32142972946167, "learning_rate": 4.673360060391805e-06, "loss": 0.0945, "step": 478390 }, { "epoch": 2.843708947815801, "grad_norm": 3.5187864303588867, "learning_rate": 4.673153011780921e-06, "loss": 0.0995, "step": 478400 }, { "epoch": 2.8437683898924693, "grad_norm": 4.355037689208984, "learning_rate": 4.672945963732906e-06, "loss": 0.1191, "step": 478410 }, { "epoch": 2.8438278319691377, "grad_norm": 5.094008445739746, "learning_rate": 4.672738916248117e-06, "loss": 0.1068, "step": 478420 }, { "epoch": 2.843887274045806, "grad_norm": 3.2630863189697266, "learning_rate": 4.672531869326911e-06, "loss": 0.1052, "step": 478430 }, { "epoch": 2.8439467161224745, "grad_norm": 4.551081657409668, "learning_rate": 4.672324822969644e-06, "loss": 0.1112, "step": 478440 }, { "epoch": 2.844006158199143, "grad_norm": 2.4648241996765137, "learning_rate": 4.672117777176672e-06, "loss": 0.0964, "step": 478450 }, { "epoch": 2.8440656002758113, "grad_norm": 4.4399614334106445, "learning_rate": 4.6719107319483535e-06, "loss": 0.119, "step": 478460 }, { "epoch": 2.8441250423524798, "grad_norm": 4.128759384155273, "learning_rate": 4.671703687285043e-06, "loss": 0.1163, "step": 478470 }, { "epoch": 2.844184484429148, "grad_norm": 3.8469858169555664, "learning_rate": 4.671496643187098e-06, "loss": 0.1218, "step": 478480 }, { "epoch": 2.8442439265058166, "grad_norm": 4.058481693267822, "learning_rate": 4.671289599654876e-06, "loss": 0.1082, "step": 478490 }, { "epoch": 2.8443033685824846, "grad_norm": 3.6329398155212402, "learning_rate": 4.671082556688732e-06, "loss": 0.1255, "step": 478500 }, { "epoch": 2.8443628106591534, "grad_norm": 4.089110851287842, "learning_rate": 4.6708755142890216e-06, "loss": 0.098, "step": 478510 }, { "epoch": 2.8444222527358214, "grad_norm": 2.1358773708343506, "learning_rate": 4.670668472456104e-06, "loss": 0.103, "step": 478520 }, { "epoch": 2.8444816948124902, "grad_norm": 3.6169369220733643, "learning_rate": 4.670461431190336e-06, "loss": 0.0945, "step": 478530 }, { "epoch": 2.844541136889158, "grad_norm": 4.848438262939453, "learning_rate": 4.67025439049207e-06, "loss": 0.1151, "step": 478540 }, { "epoch": 2.8446005789658266, "grad_norm": 3.3644142150878906, "learning_rate": 4.670047350361667e-06, "loss": 0.1045, "step": 478550 }, { "epoch": 2.844660021042495, "grad_norm": 4.045176029205322, "learning_rate": 4.669840310799482e-06, "loss": 0.11, "step": 478560 }, { "epoch": 2.8447194631191635, "grad_norm": 3.5575876235961914, "learning_rate": 4.669633271805871e-06, "loss": 0.099, "step": 478570 }, { "epoch": 2.844778905195832, "grad_norm": 3.5124518871307373, "learning_rate": 4.6694262333811906e-06, "loss": 0.1219, "step": 478580 }, { "epoch": 2.8448383472725003, "grad_norm": 3.2238376140594482, "learning_rate": 4.669219195525796e-06, "loss": 0.11, "step": 478590 }, { "epoch": 2.8448977893491687, "grad_norm": 3.5004196166992188, "learning_rate": 4.669012158240048e-06, "loss": 0.1065, "step": 478600 }, { "epoch": 2.844957231425837, "grad_norm": 4.469337463378906, "learning_rate": 4.6688051215243e-06, "loss": 0.0927, "step": 478610 }, { "epoch": 2.8450166735025055, "grad_norm": 7.121333122253418, "learning_rate": 4.6685980853789086e-06, "loss": 0.1047, "step": 478620 }, { "epoch": 2.845076115579174, "grad_norm": 4.723859786987305, "learning_rate": 4.668391049804232e-06, "loss": 0.1173, "step": 478630 }, { "epoch": 2.8451355576558424, "grad_norm": 5.016551971435547, "learning_rate": 4.668184014800624e-06, "loss": 0.127, "step": 478640 }, { "epoch": 2.8451949997325108, "grad_norm": 5.062928199768066, "learning_rate": 4.667976980368443e-06, "loss": 0.1139, "step": 478650 }, { "epoch": 2.845254441809179, "grad_norm": 3.3986010551452637, "learning_rate": 4.667769946508047e-06, "loss": 0.1014, "step": 478660 }, { "epoch": 2.845313883885847, "grad_norm": 3.3063480854034424, "learning_rate": 4.667562913219789e-06, "loss": 0.1143, "step": 478670 }, { "epoch": 2.845373325962516, "grad_norm": 4.693412780761719, "learning_rate": 4.667355880504027e-06, "loss": 0.1093, "step": 478680 }, { "epoch": 2.845432768039184, "grad_norm": 4.505061626434326, "learning_rate": 4.66714884836112e-06, "loss": 0.0891, "step": 478690 }, { "epoch": 2.845492210115853, "grad_norm": 3.362633228302002, "learning_rate": 4.666941816791421e-06, "loss": 0.1031, "step": 478700 }, { "epoch": 2.845551652192521, "grad_norm": 4.528918266296387, "learning_rate": 4.666734785795288e-06, "loss": 0.1071, "step": 478710 }, { "epoch": 2.8456110942691892, "grad_norm": 4.377056121826172, "learning_rate": 4.6665277553730775e-06, "loss": 0.0951, "step": 478720 }, { "epoch": 2.8456705363458576, "grad_norm": 3.98565673828125, "learning_rate": 4.666320725525147e-06, "loss": 0.1223, "step": 478730 }, { "epoch": 2.845729978422526, "grad_norm": 3.312962532043457, "learning_rate": 4.66611369625185e-06, "loss": 0.119, "step": 478740 }, { "epoch": 2.8457894204991945, "grad_norm": 4.573657035827637, "learning_rate": 4.6659066675535464e-06, "loss": 0.097, "step": 478750 }, { "epoch": 2.845848862575863, "grad_norm": 3.83188796043396, "learning_rate": 4.665699639430592e-06, "loss": 0.0932, "step": 478760 }, { "epoch": 2.8459083046525313, "grad_norm": 3.2186319828033447, "learning_rate": 4.665492611883341e-06, "loss": 0.1035, "step": 478770 }, { "epoch": 2.8459677467291997, "grad_norm": 3.2771553993225098, "learning_rate": 4.665285584912152e-06, "loss": 0.1186, "step": 478780 }, { "epoch": 2.846027188805868, "grad_norm": 4.13056755065918, "learning_rate": 4.665078558517382e-06, "loss": 0.103, "step": 478790 }, { "epoch": 2.8460866308825366, "grad_norm": 5.575405120849609, "learning_rate": 4.664871532699386e-06, "loss": 0.0985, "step": 478800 }, { "epoch": 2.846146072959205, "grad_norm": 3.0111091136932373, "learning_rate": 4.66466450745852e-06, "loss": 0.1061, "step": 478810 }, { "epoch": 2.8462055150358734, "grad_norm": 3.900526523590088, "learning_rate": 4.664457482795143e-06, "loss": 0.1102, "step": 478820 }, { "epoch": 2.846264957112542, "grad_norm": 4.33398962020874, "learning_rate": 4.664250458709611e-06, "loss": 0.1154, "step": 478830 }, { "epoch": 2.84632439918921, "grad_norm": 3.852555990219116, "learning_rate": 4.664043435202279e-06, "loss": 0.111, "step": 478840 }, { "epoch": 2.8463838412658786, "grad_norm": 4.907436370849609, "learning_rate": 4.663836412273505e-06, "loss": 0.0978, "step": 478850 }, { "epoch": 2.8464432833425466, "grad_norm": 2.6346585750579834, "learning_rate": 4.663629389923645e-06, "loss": 0.1102, "step": 478860 }, { "epoch": 2.8465027254192155, "grad_norm": 2.9448583126068115, "learning_rate": 4.663422368153053e-06, "loss": 0.0913, "step": 478870 }, { "epoch": 2.8465621674958834, "grad_norm": 6.563435077667236, "learning_rate": 4.663215346962091e-06, "loss": 0.1063, "step": 478880 }, { "epoch": 2.8466216095725523, "grad_norm": 3.8368444442749023, "learning_rate": 4.66300832635111e-06, "loss": 0.1015, "step": 478890 }, { "epoch": 2.8466810516492203, "grad_norm": 3.594113826751709, "learning_rate": 4.66280130632047e-06, "loss": 0.1061, "step": 478900 }, { "epoch": 2.8467404937258887, "grad_norm": 4.841944217681885, "learning_rate": 4.662594286870526e-06, "loss": 0.1175, "step": 478910 }, { "epoch": 2.846799935802557, "grad_norm": 4.762755393981934, "learning_rate": 4.662387268001636e-06, "loss": 0.1026, "step": 478920 }, { "epoch": 2.8468593778792255, "grad_norm": 3.0020995140075684, "learning_rate": 4.662180249714154e-06, "loss": 0.105, "step": 478930 }, { "epoch": 2.846918819955894, "grad_norm": 3.2544829845428467, "learning_rate": 4.661973232008438e-06, "loss": 0.1082, "step": 478940 }, { "epoch": 2.8469782620325623, "grad_norm": 3.7451226711273193, "learning_rate": 4.661766214884845e-06, "loss": 0.1049, "step": 478950 }, { "epoch": 2.8470377041092307, "grad_norm": 5.00754976272583, "learning_rate": 4.66155919834373e-06, "loss": 0.0948, "step": 478960 }, { "epoch": 2.847097146185899, "grad_norm": 3.4865493774414062, "learning_rate": 4.661352182385452e-06, "loss": 0.0991, "step": 478970 }, { "epoch": 2.8471565882625676, "grad_norm": 3.4382271766662598, "learning_rate": 4.661145167010365e-06, "loss": 0.104, "step": 478980 }, { "epoch": 2.847216030339236, "grad_norm": 4.0447492599487305, "learning_rate": 4.660938152218827e-06, "loss": 0.1077, "step": 478990 }, { "epoch": 2.8472754724159044, "grad_norm": 2.880143880844116, "learning_rate": 4.660731138011193e-06, "loss": 0.1119, "step": 479000 }, { "epoch": 2.847334914492573, "grad_norm": 4.1245317459106445, "learning_rate": 4.660524124387821e-06, "loss": 0.1075, "step": 479010 }, { "epoch": 2.8473943565692412, "grad_norm": 4.018608093261719, "learning_rate": 4.660317111349067e-06, "loss": 0.0968, "step": 479020 }, { "epoch": 2.8474537986459096, "grad_norm": 3.864044427871704, "learning_rate": 4.660110098895286e-06, "loss": 0.1089, "step": 479030 }, { "epoch": 2.847513240722578, "grad_norm": 4.866636753082275, "learning_rate": 4.659903087026837e-06, "loss": 0.1184, "step": 479040 }, { "epoch": 2.847572682799246, "grad_norm": 4.456888675689697, "learning_rate": 4.659696075744076e-06, "loss": 0.1114, "step": 479050 }, { "epoch": 2.847632124875915, "grad_norm": 4.520426273345947, "learning_rate": 4.659489065047359e-06, "loss": 0.1188, "step": 479060 }, { "epoch": 2.847691566952583, "grad_norm": 3.409862995147705, "learning_rate": 4.659282054937041e-06, "loss": 0.0992, "step": 479070 }, { "epoch": 2.8477510090292517, "grad_norm": 4.729298114776611, "learning_rate": 4.6590750454134825e-06, "loss": 0.1247, "step": 479080 }, { "epoch": 2.8478104511059197, "grad_norm": 4.9949631690979, "learning_rate": 4.658868036477036e-06, "loss": 0.0931, "step": 479090 }, { "epoch": 2.847869893182588, "grad_norm": 4.1715569496154785, "learning_rate": 4.658661028128059e-06, "loss": 0.1099, "step": 479100 }, { "epoch": 2.8479293352592565, "grad_norm": 3.1144351959228516, "learning_rate": 4.65845402036691e-06, "loss": 0.098, "step": 479110 }, { "epoch": 2.847988777335925, "grad_norm": 4.081647872924805, "learning_rate": 4.658247013193943e-06, "loss": 0.1125, "step": 479120 }, { "epoch": 2.8480482194125933, "grad_norm": 4.827587127685547, "learning_rate": 4.658040006609515e-06, "loss": 0.1167, "step": 479130 }, { "epoch": 2.8481076614892618, "grad_norm": 3.6815900802612305, "learning_rate": 4.657833000613984e-06, "loss": 0.1056, "step": 479140 }, { "epoch": 2.84816710356593, "grad_norm": 4.615931987762451, "learning_rate": 4.657625995207705e-06, "loss": 0.1095, "step": 479150 }, { "epoch": 2.8482265456425986, "grad_norm": 4.552844047546387, "learning_rate": 4.657418990391033e-06, "loss": 0.1073, "step": 479160 }, { "epoch": 2.848285987719267, "grad_norm": 4.6216654777526855, "learning_rate": 4.657211986164329e-06, "loss": 0.1047, "step": 479170 }, { "epoch": 2.8483454297959354, "grad_norm": 4.578497886657715, "learning_rate": 4.6570049825279464e-06, "loss": 0.0965, "step": 479180 }, { "epoch": 2.848404871872604, "grad_norm": 5.2083048820495605, "learning_rate": 4.656797979482241e-06, "loss": 0.1204, "step": 479190 }, { "epoch": 2.8484643139492722, "grad_norm": 3.801304817199707, "learning_rate": 4.656590977027571e-06, "loss": 0.1075, "step": 479200 }, { "epoch": 2.8485237560259407, "grad_norm": 4.928498268127441, "learning_rate": 4.656383975164292e-06, "loss": 0.1048, "step": 479210 }, { "epoch": 2.848583198102609, "grad_norm": 3.445611000061035, "learning_rate": 4.656176973892761e-06, "loss": 0.1125, "step": 479220 }, { "epoch": 2.8486426401792775, "grad_norm": 4.410313129425049, "learning_rate": 4.655969973213335e-06, "loss": 0.117, "step": 479230 }, { "epoch": 2.8487020822559455, "grad_norm": 4.012534141540527, "learning_rate": 4.6557629731263695e-06, "loss": 0.1044, "step": 479240 }, { "epoch": 2.8487615243326143, "grad_norm": 3.3696248531341553, "learning_rate": 4.655555973632219e-06, "loss": 0.1146, "step": 479250 }, { "epoch": 2.8488209664092823, "grad_norm": 3.7336745262145996, "learning_rate": 4.6553489747312445e-06, "loss": 0.1128, "step": 479260 }, { "epoch": 2.8488804084859507, "grad_norm": 4.7745795249938965, "learning_rate": 4.655141976423799e-06, "loss": 0.111, "step": 479270 }, { "epoch": 2.848939850562619, "grad_norm": 4.215087413787842, "learning_rate": 4.654934978710241e-06, "loss": 0.104, "step": 479280 }, { "epoch": 2.8489992926392875, "grad_norm": 3.6982803344726562, "learning_rate": 4.654727981590926e-06, "loss": 0.1088, "step": 479290 }, { "epoch": 2.849058734715956, "grad_norm": 4.731627464294434, "learning_rate": 4.65452098506621e-06, "loss": 0.1105, "step": 479300 }, { "epoch": 2.8491181767926244, "grad_norm": 4.426949977874756, "learning_rate": 4.654313989136452e-06, "loss": 0.0948, "step": 479310 }, { "epoch": 2.8491776188692928, "grad_norm": 3.325395345687866, "learning_rate": 4.654106993802006e-06, "loss": 0.106, "step": 479320 }, { "epoch": 2.849237060945961, "grad_norm": 4.924966335296631, "learning_rate": 4.653899999063227e-06, "loss": 0.1311, "step": 479330 }, { "epoch": 2.8492965030226296, "grad_norm": 3.917623996734619, "learning_rate": 4.653693004920475e-06, "loss": 0.1045, "step": 479340 }, { "epoch": 2.849355945099298, "grad_norm": 3.8986635208129883, "learning_rate": 4.653486011374105e-06, "loss": 0.0981, "step": 479350 }, { "epoch": 2.8494153871759664, "grad_norm": 2.9019839763641357, "learning_rate": 4.653279018424473e-06, "loss": 0.108, "step": 479360 }, { "epoch": 2.849474829252635, "grad_norm": 4.431008815765381, "learning_rate": 4.653072026071936e-06, "loss": 0.1173, "step": 479370 }, { "epoch": 2.8495342713293033, "grad_norm": 5.0186543464660645, "learning_rate": 4.652865034316851e-06, "loss": 0.1086, "step": 479380 }, { "epoch": 2.8495937134059717, "grad_norm": 4.098037242889404, "learning_rate": 4.652658043159573e-06, "loss": 0.1119, "step": 479390 }, { "epoch": 2.84965315548264, "grad_norm": 3.3227381706237793, "learning_rate": 4.65245105260046e-06, "loss": 0.0925, "step": 479400 }, { "epoch": 2.849712597559308, "grad_norm": 4.656549453735352, "learning_rate": 4.652244062639868e-06, "loss": 0.1229, "step": 479410 }, { "epoch": 2.849772039635977, "grad_norm": 3.988231897354126, "learning_rate": 4.652037073278152e-06, "loss": 0.1008, "step": 479420 }, { "epoch": 2.849831481712645, "grad_norm": 3.5805470943450928, "learning_rate": 4.651830084515671e-06, "loss": 0.1027, "step": 479430 }, { "epoch": 2.8498909237893137, "grad_norm": 3.695528984069824, "learning_rate": 4.6516230963527795e-06, "loss": 0.1417, "step": 479440 }, { "epoch": 2.8499503658659817, "grad_norm": 4.468798637390137, "learning_rate": 4.651416108789833e-06, "loss": 0.1095, "step": 479450 }, { "epoch": 2.85000980794265, "grad_norm": 4.603463172912598, "learning_rate": 4.651209121827192e-06, "loss": 0.1045, "step": 479460 }, { "epoch": 2.8500692500193185, "grad_norm": 3.364640951156616, "learning_rate": 4.651002135465208e-06, "loss": 0.107, "step": 479470 }, { "epoch": 2.850128692095987, "grad_norm": 2.850151538848877, "learning_rate": 4.650795149704242e-06, "loss": 0.1139, "step": 479480 }, { "epoch": 2.8501881341726554, "grad_norm": 5.0119524002075195, "learning_rate": 4.650588164544647e-06, "loss": 0.1205, "step": 479490 }, { "epoch": 2.850247576249324, "grad_norm": 4.707738399505615, "learning_rate": 4.650381179986782e-06, "loss": 0.114, "step": 479500 }, { "epoch": 2.850307018325992, "grad_norm": 3.885679244995117, "learning_rate": 4.650174196031003e-06, "loss": 0.0947, "step": 479510 }, { "epoch": 2.8503664604026606, "grad_norm": 3.226961612701416, "learning_rate": 4.649967212677664e-06, "loss": 0.1044, "step": 479520 }, { "epoch": 2.850425902479329, "grad_norm": 4.8442182540893555, "learning_rate": 4.6497602299271245e-06, "loss": 0.1256, "step": 479530 }, { "epoch": 2.8504853445559974, "grad_norm": 2.3189125061035156, "learning_rate": 4.64955324777974e-06, "loss": 0.1072, "step": 479540 }, { "epoch": 2.850544786632666, "grad_norm": 3.558344841003418, "learning_rate": 4.649346266235865e-06, "loss": 0.1049, "step": 479550 }, { "epoch": 2.8506042287093343, "grad_norm": 5.2265305519104, "learning_rate": 4.6491392852958595e-06, "loss": 0.1209, "step": 479560 }, { "epoch": 2.8506636707860027, "grad_norm": 3.2060747146606445, "learning_rate": 4.648932304960077e-06, "loss": 0.1107, "step": 479570 }, { "epoch": 2.850723112862671, "grad_norm": 4.431966304779053, "learning_rate": 4.6487253252288746e-06, "loss": 0.1058, "step": 479580 }, { "epoch": 2.8507825549393395, "grad_norm": 4.137667179107666, "learning_rate": 4.6485183461026095e-06, "loss": 0.1132, "step": 479590 }, { "epoch": 2.8508419970160075, "grad_norm": 3.8826394081115723, "learning_rate": 4.648311367581638e-06, "loss": 0.11, "step": 479600 }, { "epoch": 2.8509014390926763, "grad_norm": 3.5720953941345215, "learning_rate": 4.648104389666316e-06, "loss": 0.1056, "step": 479610 }, { "epoch": 2.8509608811693443, "grad_norm": 4.887187480926514, "learning_rate": 4.647897412357e-06, "loss": 0.1007, "step": 479620 }, { "epoch": 2.851020323246013, "grad_norm": 4.652035713195801, "learning_rate": 4.647690435654047e-06, "loss": 0.124, "step": 479630 }, { "epoch": 2.851079765322681, "grad_norm": 5.38639497756958, "learning_rate": 4.647483459557813e-06, "loss": 0.1036, "step": 479640 }, { "epoch": 2.8511392073993496, "grad_norm": 3.7602109909057617, "learning_rate": 4.647276484068655e-06, "loss": 0.0912, "step": 479650 }, { "epoch": 2.851198649476018, "grad_norm": 3.0989186763763428, "learning_rate": 4.6470695091869285e-06, "loss": 0.1015, "step": 479660 }, { "epoch": 2.8512580915526864, "grad_norm": 3.3239264488220215, "learning_rate": 4.646862534912992e-06, "loss": 0.0975, "step": 479670 }, { "epoch": 2.851317533629355, "grad_norm": 4.491357326507568, "learning_rate": 4.646655561247197e-06, "loss": 0.0863, "step": 479680 }, { "epoch": 2.851376975706023, "grad_norm": 4.299028396606445, "learning_rate": 4.646448588189904e-06, "loss": 0.118, "step": 479690 }, { "epoch": 2.8514364177826916, "grad_norm": 3.836163282394409, "learning_rate": 4.64624161574147e-06, "loss": 0.0986, "step": 479700 }, { "epoch": 2.85149585985936, "grad_norm": 3.6621851921081543, "learning_rate": 4.64603464390225e-06, "loss": 0.0968, "step": 479710 }, { "epoch": 2.8515553019360285, "grad_norm": 4.191164493560791, "learning_rate": 4.6458276726726e-06, "loss": 0.0977, "step": 479720 }, { "epoch": 2.851614744012697, "grad_norm": 4.351332187652588, "learning_rate": 4.6456207020528785e-06, "loss": 0.1093, "step": 479730 }, { "epoch": 2.8516741860893653, "grad_norm": 4.551925182342529, "learning_rate": 4.645413732043439e-06, "loss": 0.1057, "step": 479740 }, { "epoch": 2.8517336281660337, "grad_norm": 4.068215847015381, "learning_rate": 4.645206762644639e-06, "loss": 0.1063, "step": 479750 }, { "epoch": 2.851793070242702, "grad_norm": 3.5996451377868652, "learning_rate": 4.644999793856837e-06, "loss": 0.1105, "step": 479760 }, { "epoch": 2.8518525123193705, "grad_norm": 3.9836621284484863, "learning_rate": 4.644792825680387e-06, "loss": 0.1196, "step": 479770 }, { "epoch": 2.851911954396039, "grad_norm": 2.4567861557006836, "learning_rate": 4.644585858115646e-06, "loss": 0.0983, "step": 479780 }, { "epoch": 2.851971396472707, "grad_norm": 3.328829765319824, "learning_rate": 4.6443788911629706e-06, "loss": 0.1172, "step": 479790 }, { "epoch": 2.852030838549376, "grad_norm": 4.402336120605469, "learning_rate": 4.644171924822718e-06, "loss": 0.1044, "step": 479800 }, { "epoch": 2.8520902806260438, "grad_norm": 3.4139764308929443, "learning_rate": 4.643964959095242e-06, "loss": 0.1014, "step": 479810 }, { "epoch": 2.8521497227027126, "grad_norm": 6.468888282775879, "learning_rate": 4.643757993980902e-06, "loss": 0.1201, "step": 479820 }, { "epoch": 2.8522091647793806, "grad_norm": 3.4184863567352295, "learning_rate": 4.643551029480053e-06, "loss": 0.1193, "step": 479830 }, { "epoch": 2.852268606856049, "grad_norm": 3.3435730934143066, "learning_rate": 4.643344065593052e-06, "loss": 0.1208, "step": 479840 }, { "epoch": 2.8523280489327174, "grad_norm": 3.45428466796875, "learning_rate": 4.6431371023202544e-06, "loss": 0.1102, "step": 479850 }, { "epoch": 2.852387491009386, "grad_norm": 3.5206453800201416, "learning_rate": 4.642930139662018e-06, "loss": 0.1034, "step": 479860 }, { "epoch": 2.8524469330860542, "grad_norm": 3.0685689449310303, "learning_rate": 4.6427231776186976e-06, "loss": 0.0983, "step": 479870 }, { "epoch": 2.8525063751627227, "grad_norm": 3.057774543762207, "learning_rate": 4.642516216190651e-06, "loss": 0.099, "step": 479880 }, { "epoch": 2.852565817239391, "grad_norm": 3.3651678562164307, "learning_rate": 4.642309255378235e-06, "loss": 0.1227, "step": 479890 }, { "epoch": 2.8526252593160595, "grad_norm": 4.274513244628906, "learning_rate": 4.642102295181804e-06, "loss": 0.1003, "step": 479900 }, { "epoch": 2.852684701392728, "grad_norm": 5.077764511108398, "learning_rate": 4.6418953356017145e-06, "loss": 0.1053, "step": 479910 }, { "epoch": 2.8527441434693963, "grad_norm": 3.401926040649414, "learning_rate": 4.641688376638325e-06, "loss": 0.1008, "step": 479920 }, { "epoch": 2.8528035855460647, "grad_norm": 3.780601739883423, "learning_rate": 4.641481418291991e-06, "loss": 0.1159, "step": 479930 }, { "epoch": 2.852863027622733, "grad_norm": 3.772165298461914, "learning_rate": 4.64127446056307e-06, "loss": 0.1053, "step": 479940 }, { "epoch": 2.8529224696994016, "grad_norm": 3.032395362854004, "learning_rate": 4.641067503451916e-06, "loss": 0.1067, "step": 479950 }, { "epoch": 2.85298191177607, "grad_norm": 3.6718757152557373, "learning_rate": 4.640860546958887e-06, "loss": 0.1012, "step": 479960 }, { "epoch": 2.8530413538527384, "grad_norm": 5.380540370941162, "learning_rate": 4.6406535910843384e-06, "loss": 0.1149, "step": 479970 }, { "epoch": 2.8531007959294064, "grad_norm": 4.15579891204834, "learning_rate": 4.640446635828627e-06, "loss": 0.112, "step": 479980 }, { "epoch": 2.853160238006075, "grad_norm": 3.3119304180145264, "learning_rate": 4.640239681192111e-06, "loss": 0.108, "step": 479990 }, { "epoch": 2.853219680082743, "grad_norm": 4.299022674560547, "learning_rate": 4.640032727175144e-06, "loss": 0.1177, "step": 480000 }, { "epoch": 2.8532791221594116, "grad_norm": 4.3397040367126465, "learning_rate": 4.639825773778083e-06, "loss": 0.1105, "step": 480010 }, { "epoch": 2.85333856423608, "grad_norm": 3.8858845233917236, "learning_rate": 4.639618821001286e-06, "loss": 0.1176, "step": 480020 }, { "epoch": 2.8533980063127484, "grad_norm": 3.4636738300323486, "learning_rate": 4.639411868845109e-06, "loss": 0.1172, "step": 480030 }, { "epoch": 2.853457448389417, "grad_norm": 3.252084732055664, "learning_rate": 4.639204917309906e-06, "loss": 0.1027, "step": 480040 }, { "epoch": 2.8535168904660853, "grad_norm": 4.556746959686279, "learning_rate": 4.638997966396036e-06, "loss": 0.107, "step": 480050 }, { "epoch": 2.8535763325427537, "grad_norm": 4.370289325714111, "learning_rate": 4.6387910161038555e-06, "loss": 0.1101, "step": 480060 }, { "epoch": 2.853635774619422, "grad_norm": 3.384971857070923, "learning_rate": 4.6385840664337185e-06, "loss": 0.1025, "step": 480070 }, { "epoch": 2.8536952166960905, "grad_norm": 5.233248233795166, "learning_rate": 4.638377117385984e-06, "loss": 0.1005, "step": 480080 }, { "epoch": 2.853754658772759, "grad_norm": 3.5443644523620605, "learning_rate": 4.638170168961007e-06, "loss": 0.0999, "step": 480090 }, { "epoch": 2.8538141008494273, "grad_norm": 3.637462854385376, "learning_rate": 4.637963221159143e-06, "loss": 0.1185, "step": 480100 }, { "epoch": 2.8538735429260957, "grad_norm": 3.259124517440796, "learning_rate": 4.637756273980751e-06, "loss": 0.1054, "step": 480110 }, { "epoch": 2.853932985002764, "grad_norm": 4.030368804931641, "learning_rate": 4.6375493274261854e-06, "loss": 0.1103, "step": 480120 }, { "epoch": 2.8539924270794326, "grad_norm": 3.6984238624572754, "learning_rate": 4.637342381495801e-06, "loss": 0.1002, "step": 480130 }, { "epoch": 2.854051869156101, "grad_norm": 4.531678676605225, "learning_rate": 4.6371354361899576e-06, "loss": 0.111, "step": 480140 }, { "epoch": 2.854111311232769, "grad_norm": 3.471266746520996, "learning_rate": 4.6369284915090115e-06, "loss": 0.1031, "step": 480150 }, { "epoch": 2.854170753309438, "grad_norm": 3.9940950870513916, "learning_rate": 4.636721547453318e-06, "loss": 0.1094, "step": 480160 }, { "epoch": 2.854230195386106, "grad_norm": 2.919675350189209, "learning_rate": 4.636514604023232e-06, "loss": 0.0937, "step": 480170 }, { "epoch": 2.8542896374627746, "grad_norm": 3.767524242401123, "learning_rate": 4.636307661219112e-06, "loss": 0.0963, "step": 480180 }, { "epoch": 2.8543490795394426, "grad_norm": 4.204931735992432, "learning_rate": 4.636100719041314e-06, "loss": 0.1074, "step": 480190 }, { "epoch": 2.854408521616111, "grad_norm": 3.5610671043395996, "learning_rate": 4.635893777490193e-06, "loss": 0.1064, "step": 480200 }, { "epoch": 2.8544679636927794, "grad_norm": 4.990267276763916, "learning_rate": 4.6356868365661065e-06, "loss": 0.1252, "step": 480210 }, { "epoch": 2.854527405769448, "grad_norm": 2.983517646789551, "learning_rate": 4.635479896269412e-06, "loss": 0.1055, "step": 480220 }, { "epoch": 2.8545868478461163, "grad_norm": 4.1273016929626465, "learning_rate": 4.6352729566004626e-06, "loss": 0.1061, "step": 480230 }, { "epoch": 2.8546462899227847, "grad_norm": 3.5602896213531494, "learning_rate": 4.635066017559618e-06, "loss": 0.1031, "step": 480240 }, { "epoch": 2.854705731999453, "grad_norm": 3.2145273685455322, "learning_rate": 4.6348590791472344e-06, "loss": 0.1004, "step": 480250 }, { "epoch": 2.8547651740761215, "grad_norm": 3.783266544342041, "learning_rate": 4.634652141363665e-06, "loss": 0.1055, "step": 480260 }, { "epoch": 2.85482461615279, "grad_norm": 4.7940263748168945, "learning_rate": 4.634445204209269e-06, "loss": 0.0984, "step": 480270 }, { "epoch": 2.8548840582294583, "grad_norm": 4.186092376708984, "learning_rate": 4.634238267684402e-06, "loss": 0.1061, "step": 480280 }, { "epoch": 2.8549435003061268, "grad_norm": 3.019092559814453, "learning_rate": 4.63403133178942e-06, "loss": 0.1099, "step": 480290 }, { "epoch": 2.855002942382795, "grad_norm": 3.2878873348236084, "learning_rate": 4.63382439652468e-06, "loss": 0.1086, "step": 480300 }, { "epoch": 2.8550623844594636, "grad_norm": 4.5541462898254395, "learning_rate": 4.633617461890538e-06, "loss": 0.1114, "step": 480310 }, { "epoch": 2.855121826536132, "grad_norm": 5.023230075836182, "learning_rate": 4.63341052788735e-06, "loss": 0.114, "step": 480320 }, { "epoch": 2.8551812686128004, "grad_norm": 4.365336894989014, "learning_rate": 4.633203594515474e-06, "loss": 0.1146, "step": 480330 }, { "epoch": 2.8552407106894684, "grad_norm": 4.062175273895264, "learning_rate": 4.632996661775265e-06, "loss": 0.0972, "step": 480340 }, { "epoch": 2.8553001527661372, "grad_norm": 5.006587505340576, "learning_rate": 4.632789729667077e-06, "loss": 0.0973, "step": 480350 }, { "epoch": 2.855359594842805, "grad_norm": 4.308644771575928, "learning_rate": 4.632582798191271e-06, "loss": 0.1049, "step": 480360 }, { "epoch": 2.855419036919474, "grad_norm": 3.8145406246185303, "learning_rate": 4.6323758673482005e-06, "loss": 0.1089, "step": 480370 }, { "epoch": 2.855478478996142, "grad_norm": 4.834790229797363, "learning_rate": 4.632168937138224e-06, "loss": 0.112, "step": 480380 }, { "epoch": 2.8555379210728105, "grad_norm": 4.217212200164795, "learning_rate": 4.631962007561695e-06, "loss": 0.1118, "step": 480390 }, { "epoch": 2.855597363149479, "grad_norm": 5.752181529998779, "learning_rate": 4.631755078618972e-06, "loss": 0.1167, "step": 480400 }, { "epoch": 2.8556568052261473, "grad_norm": 4.441911220550537, "learning_rate": 4.631548150310411e-06, "loss": 0.0979, "step": 480410 }, { "epoch": 2.8557162473028157, "grad_norm": 4.292386531829834, "learning_rate": 4.631341222636369e-06, "loss": 0.105, "step": 480420 }, { "epoch": 2.855775689379484, "grad_norm": 6.452154636383057, "learning_rate": 4.631134295597199e-06, "loss": 0.1234, "step": 480430 }, { "epoch": 2.8558351314561525, "grad_norm": 3.035600423812866, "learning_rate": 4.630927369193261e-06, "loss": 0.1011, "step": 480440 }, { "epoch": 2.855894573532821, "grad_norm": 3.8714406490325928, "learning_rate": 4.630720443424911e-06, "loss": 0.105, "step": 480450 }, { "epoch": 2.8559540156094894, "grad_norm": 4.602978229522705, "learning_rate": 4.630513518292503e-06, "loss": 0.1017, "step": 480460 }, { "epoch": 2.8560134576861578, "grad_norm": 3.2621493339538574, "learning_rate": 4.630306593796396e-06, "loss": 0.119, "step": 480470 }, { "epoch": 2.856072899762826, "grad_norm": 4.063016891479492, "learning_rate": 4.630099669936944e-06, "loss": 0.0967, "step": 480480 }, { "epoch": 2.8561323418394946, "grad_norm": 3.2724225521087646, "learning_rate": 4.6298927467145046e-06, "loss": 0.1099, "step": 480490 }, { "epoch": 2.856191783916163, "grad_norm": 3.9051690101623535, "learning_rate": 4.629685824129434e-06, "loss": 0.1041, "step": 480500 }, { "epoch": 2.8562512259928314, "grad_norm": 3.789886713027954, "learning_rate": 4.62947890218209e-06, "loss": 0.1122, "step": 480510 }, { "epoch": 2.8563106680695, "grad_norm": 5.7254319190979, "learning_rate": 4.629271980872826e-06, "loss": 0.0988, "step": 480520 }, { "epoch": 2.856370110146168, "grad_norm": 3.9902095794677734, "learning_rate": 4.629065060202001e-06, "loss": 0.1085, "step": 480530 }, { "epoch": 2.8564295522228367, "grad_norm": 2.7518274784088135, "learning_rate": 4.62885814016997e-06, "loss": 0.1102, "step": 480540 }, { "epoch": 2.8564889942995046, "grad_norm": 3.1282989978790283, "learning_rate": 4.628651220777088e-06, "loss": 0.0896, "step": 480550 }, { "epoch": 2.8565484363761735, "grad_norm": 3.5656380653381348, "learning_rate": 4.628444302023715e-06, "loss": 0.1032, "step": 480560 }, { "epoch": 2.8566078784528415, "grad_norm": 4.3090009689331055, "learning_rate": 4.628237383910203e-06, "loss": 0.1163, "step": 480570 }, { "epoch": 2.85666732052951, "grad_norm": 3.475543975830078, "learning_rate": 4.628030466436912e-06, "loss": 0.0917, "step": 480580 }, { "epoch": 2.8567267626061783, "grad_norm": 3.9046053886413574, "learning_rate": 4.627823549604198e-06, "loss": 0.1112, "step": 480590 }, { "epoch": 2.8567862046828467, "grad_norm": 3.9351212978363037, "learning_rate": 4.627616633412414e-06, "loss": 0.1102, "step": 480600 }, { "epoch": 2.856845646759515, "grad_norm": 5.056687831878662, "learning_rate": 4.627409717861921e-06, "loss": 0.1025, "step": 480610 }, { "epoch": 2.8569050888361835, "grad_norm": 3.7941908836364746, "learning_rate": 4.6272028029530714e-06, "loss": 0.0975, "step": 480620 }, { "epoch": 2.856964530912852, "grad_norm": 2.53922700881958, "learning_rate": 4.626995888686222e-06, "loss": 0.0984, "step": 480630 }, { "epoch": 2.8570239729895204, "grad_norm": 3.1124606132507324, "learning_rate": 4.6267889750617324e-06, "loss": 0.113, "step": 480640 }, { "epoch": 2.857083415066189, "grad_norm": 3.4271745681762695, "learning_rate": 4.626582062079956e-06, "loss": 0.0932, "step": 480650 }, { "epoch": 2.857142857142857, "grad_norm": 3.7025821208953857, "learning_rate": 4.626375149741249e-06, "loss": 0.1065, "step": 480660 }, { "epoch": 2.8572022992195256, "grad_norm": 3.7089157104492188, "learning_rate": 4.62616823804597e-06, "loss": 0.113, "step": 480670 }, { "epoch": 2.857261741296194, "grad_norm": 4.235407829284668, "learning_rate": 4.625961326994473e-06, "loss": 0.1106, "step": 480680 }, { "epoch": 2.8573211833728624, "grad_norm": 3.22831392288208, "learning_rate": 4.625754416587115e-06, "loss": 0.1113, "step": 480690 }, { "epoch": 2.857380625449531, "grad_norm": 5.00730562210083, "learning_rate": 4.625547506824253e-06, "loss": 0.0934, "step": 480700 }, { "epoch": 2.8574400675261993, "grad_norm": 2.719454288482666, "learning_rate": 4.6253405977062436e-06, "loss": 0.1046, "step": 480710 }, { "epoch": 2.8574995096028672, "grad_norm": 3.0559568405151367, "learning_rate": 4.625133689233441e-06, "loss": 0.0938, "step": 480720 }, { "epoch": 2.857558951679536, "grad_norm": 3.7072956562042236, "learning_rate": 4.624926781406204e-06, "loss": 0.1077, "step": 480730 }, { "epoch": 2.857618393756204, "grad_norm": 4.6586833000183105, "learning_rate": 4.624719874224888e-06, "loss": 0.1148, "step": 480740 }, { "epoch": 2.8576778358328725, "grad_norm": 4.813642501831055, "learning_rate": 4.624512967689848e-06, "loss": 0.1203, "step": 480750 }, { "epoch": 2.857737277909541, "grad_norm": 4.088126182556152, "learning_rate": 4.624306061801442e-06, "loss": 0.0997, "step": 480760 }, { "epoch": 2.8577967199862093, "grad_norm": 3.1640262603759766, "learning_rate": 4.624099156560025e-06, "loss": 0.0917, "step": 480770 }, { "epoch": 2.8578561620628777, "grad_norm": 4.667234420776367, "learning_rate": 4.623892251965955e-06, "loss": 0.1044, "step": 480780 }, { "epoch": 2.857915604139546, "grad_norm": 3.858764171600342, "learning_rate": 4.623685348019585e-06, "loss": 0.1112, "step": 480790 }, { "epoch": 2.8579750462162146, "grad_norm": 4.285301685333252, "learning_rate": 4.623478444721277e-06, "loss": 0.1098, "step": 480800 }, { "epoch": 2.858034488292883, "grad_norm": 4.237398624420166, "learning_rate": 4.6232715420713834e-06, "loss": 0.1004, "step": 480810 }, { "epoch": 2.8580939303695514, "grad_norm": 3.65301775932312, "learning_rate": 4.62306464007026e-06, "loss": 0.1131, "step": 480820 }, { "epoch": 2.85815337244622, "grad_norm": 3.6659841537475586, "learning_rate": 4.622857738718265e-06, "loss": 0.1062, "step": 480830 }, { "epoch": 2.8582128145228882, "grad_norm": 3.0019378662109375, "learning_rate": 4.622650838015755e-06, "loss": 0.0926, "step": 480840 }, { "epoch": 2.8582722565995566, "grad_norm": 3.0298337936401367, "learning_rate": 4.622443937963084e-06, "loss": 0.1041, "step": 480850 }, { "epoch": 2.858331698676225, "grad_norm": 4.071066856384277, "learning_rate": 4.62223703856061e-06, "loss": 0.1113, "step": 480860 }, { "epoch": 2.8583911407528935, "grad_norm": 2.875659942626953, "learning_rate": 4.62203013980869e-06, "loss": 0.087, "step": 480870 }, { "epoch": 2.858450582829562, "grad_norm": 3.8102517127990723, "learning_rate": 4.621823241707676e-06, "loss": 0.112, "step": 480880 }, { "epoch": 2.85851002490623, "grad_norm": 3.586169719696045, "learning_rate": 4.621616344257931e-06, "loss": 0.107, "step": 480890 }, { "epoch": 2.8585694669828987, "grad_norm": 5.561441898345947, "learning_rate": 4.621409447459806e-06, "loss": 0.1209, "step": 480900 }, { "epoch": 2.8586289090595667, "grad_norm": 3.998509645462036, "learning_rate": 4.621202551313659e-06, "loss": 0.1139, "step": 480910 }, { "epoch": 2.8586883511362355, "grad_norm": 3.6720633506774902, "learning_rate": 4.620995655819847e-06, "loss": 0.1187, "step": 480920 }, { "epoch": 2.8587477932129035, "grad_norm": 4.031639575958252, "learning_rate": 4.620788760978726e-06, "loss": 0.1027, "step": 480930 }, { "epoch": 2.858807235289572, "grad_norm": 4.39021635055542, "learning_rate": 4.620581866790651e-06, "loss": 0.1119, "step": 480940 }, { "epoch": 2.8588666773662403, "grad_norm": 4.160181999206543, "learning_rate": 4.62037497325598e-06, "loss": 0.1072, "step": 480950 }, { "epoch": 2.8589261194429088, "grad_norm": 3.4904818534851074, "learning_rate": 4.620168080375068e-06, "loss": 0.0978, "step": 480960 }, { "epoch": 2.858985561519577, "grad_norm": 4.369945049285889, "learning_rate": 4.619961188148272e-06, "loss": 0.1104, "step": 480970 }, { "epoch": 2.8590450035962456, "grad_norm": 5.264806747436523, "learning_rate": 4.61975429657595e-06, "loss": 0.1125, "step": 480980 }, { "epoch": 2.859104445672914, "grad_norm": 3.797868013381958, "learning_rate": 4.619547405658455e-06, "loss": 0.089, "step": 480990 }, { "epoch": 2.8591638877495824, "grad_norm": 4.161798477172852, "learning_rate": 4.619340515396145e-06, "loss": 0.1007, "step": 481000 }, { "epoch": 2.859223329826251, "grad_norm": 4.458044528961182, "learning_rate": 4.6191336257893736e-06, "loss": 0.1082, "step": 481010 }, { "epoch": 2.8592827719029192, "grad_norm": 4.795262336730957, "learning_rate": 4.618926736838501e-06, "loss": 0.1214, "step": 481020 }, { "epoch": 2.8593422139795877, "grad_norm": 3.507451057434082, "learning_rate": 4.618719848543884e-06, "loss": 0.1073, "step": 481030 }, { "epoch": 2.859401656056256, "grad_norm": 3.787409543991089, "learning_rate": 4.618512960905876e-06, "loss": 0.107, "step": 481040 }, { "epoch": 2.8594610981329245, "grad_norm": 3.9787027835845947, "learning_rate": 4.618306073924833e-06, "loss": 0.1105, "step": 481050 }, { "epoch": 2.859520540209593, "grad_norm": 4.168951988220215, "learning_rate": 4.6180991876011135e-06, "loss": 0.1091, "step": 481060 }, { "epoch": 2.8595799822862613, "grad_norm": 3.5046985149383545, "learning_rate": 4.617892301935073e-06, "loss": 0.1173, "step": 481070 }, { "epoch": 2.8596394243629293, "grad_norm": 5.064382076263428, "learning_rate": 4.617685416927066e-06, "loss": 0.0931, "step": 481080 }, { "epoch": 2.859698866439598, "grad_norm": 5.40928840637207, "learning_rate": 4.617478532577453e-06, "loss": 0.1307, "step": 481090 }, { "epoch": 2.859758308516266, "grad_norm": 4.899023056030273, "learning_rate": 4.6172716488865855e-06, "loss": 0.1102, "step": 481100 }, { "epoch": 2.859817750592935, "grad_norm": 3.7660820484161377, "learning_rate": 4.617064765854822e-06, "loss": 0.1135, "step": 481110 }, { "epoch": 2.859877192669603, "grad_norm": 3.479900360107422, "learning_rate": 4.6168578834825195e-06, "loss": 0.1011, "step": 481120 }, { "epoch": 2.8599366347462714, "grad_norm": 4.307221412658691, "learning_rate": 4.616651001770033e-06, "loss": 0.1, "step": 481130 }, { "epoch": 2.8599960768229398, "grad_norm": 4.906456470489502, "learning_rate": 4.616444120717719e-06, "loss": 0.1161, "step": 481140 }, { "epoch": 2.860055518899608, "grad_norm": 5.040846824645996, "learning_rate": 4.616237240325934e-06, "loss": 0.1175, "step": 481150 }, { "epoch": 2.8601149609762766, "grad_norm": 3.2666871547698975, "learning_rate": 4.616030360595036e-06, "loss": 0.097, "step": 481160 }, { "epoch": 2.860174403052945, "grad_norm": 4.072064399719238, "learning_rate": 4.615823481525377e-06, "loss": 0.1094, "step": 481170 }, { "epoch": 2.8602338451296134, "grad_norm": 6.159080505371094, "learning_rate": 4.615616603117317e-06, "loss": 0.109, "step": 481180 }, { "epoch": 2.860293287206282, "grad_norm": 6.771674633026123, "learning_rate": 4.615409725371212e-06, "loss": 0.1024, "step": 481190 }, { "epoch": 2.8603527292829503, "grad_norm": 3.428741693496704, "learning_rate": 4.615202848287416e-06, "loss": 0.1189, "step": 481200 }, { "epoch": 2.8604121713596187, "grad_norm": 3.857351064682007, "learning_rate": 4.614995971866287e-06, "loss": 0.1083, "step": 481210 }, { "epoch": 2.860471613436287, "grad_norm": 2.9601657390594482, "learning_rate": 4.614789096108181e-06, "loss": 0.1049, "step": 481220 }, { "epoch": 2.8605310555129555, "grad_norm": 3.5159945487976074, "learning_rate": 4.614582221013451e-06, "loss": 0.0935, "step": 481230 }, { "epoch": 2.860590497589624, "grad_norm": 4.167168617248535, "learning_rate": 4.61437534658246e-06, "loss": 0.1146, "step": 481240 }, { "epoch": 2.8606499396662923, "grad_norm": 3.55167818069458, "learning_rate": 4.61416847281556e-06, "loss": 0.1073, "step": 481250 }, { "epoch": 2.8607093817429607, "grad_norm": 3.016746759414673, "learning_rate": 4.613961599713108e-06, "loss": 0.099, "step": 481260 }, { "epoch": 2.8607688238196287, "grad_norm": 6.101194858551025, "learning_rate": 4.613754727275461e-06, "loss": 0.0996, "step": 481270 }, { "epoch": 2.8608282658962976, "grad_norm": 3.8661670684814453, "learning_rate": 4.613547855502973e-06, "loss": 0.1001, "step": 481280 }, { "epoch": 2.8608877079729655, "grad_norm": 3.392110586166382, "learning_rate": 4.613340984396002e-06, "loss": 0.1031, "step": 481290 }, { "epoch": 2.8609471500496344, "grad_norm": 3.627119302749634, "learning_rate": 4.613134113954905e-06, "loss": 0.1132, "step": 481300 }, { "epoch": 2.8610065921263024, "grad_norm": 4.59704065322876, "learning_rate": 4.612927244180036e-06, "loss": 0.1036, "step": 481310 }, { "epoch": 2.861066034202971, "grad_norm": 3.681119203567505, "learning_rate": 4.612720375071753e-06, "loss": 0.099, "step": 481320 }, { "epoch": 2.861125476279639, "grad_norm": 3.2103514671325684, "learning_rate": 4.612513506630412e-06, "loss": 0.1196, "step": 481330 }, { "epoch": 2.8611849183563076, "grad_norm": 4.234982967376709, "learning_rate": 4.612306638856368e-06, "loss": 0.1101, "step": 481340 }, { "epoch": 2.861244360432976, "grad_norm": 3.4265828132629395, "learning_rate": 4.612099771749979e-06, "loss": 0.1017, "step": 481350 }, { "epoch": 2.8613038025096444, "grad_norm": 4.4527668952941895, "learning_rate": 4.6118929053116e-06, "loss": 0.1077, "step": 481360 }, { "epoch": 2.861363244586313, "grad_norm": 4.659934043884277, "learning_rate": 4.611686039541588e-06, "loss": 0.1105, "step": 481370 }, { "epoch": 2.8614226866629813, "grad_norm": 4.080696105957031, "learning_rate": 4.6114791744402994e-06, "loss": 0.1243, "step": 481380 }, { "epoch": 2.8614821287396497, "grad_norm": 3.5739879608154297, "learning_rate": 4.61127231000809e-06, "loss": 0.11, "step": 481390 }, { "epoch": 2.861541570816318, "grad_norm": 3.4836201667785645, "learning_rate": 4.611065446245315e-06, "loss": 0.1001, "step": 481400 }, { "epoch": 2.8616010128929865, "grad_norm": 3.4227659702301025, "learning_rate": 4.6108585831523325e-06, "loss": 0.0949, "step": 481410 }, { "epoch": 2.861660454969655, "grad_norm": 3.221411943435669, "learning_rate": 4.610651720729499e-06, "loss": 0.097, "step": 481420 }, { "epoch": 2.8617198970463233, "grad_norm": 3.2626025676727295, "learning_rate": 4.6104448589771675e-06, "loss": 0.1134, "step": 481430 }, { "epoch": 2.8617793391229918, "grad_norm": 3.7252275943756104, "learning_rate": 4.6102379978956975e-06, "loss": 0.0904, "step": 481440 }, { "epoch": 2.86183878119966, "grad_norm": 3.519937753677368, "learning_rate": 4.610031137485443e-06, "loss": 0.1015, "step": 481450 }, { "epoch": 2.861898223276328, "grad_norm": 3.0905849933624268, "learning_rate": 4.609824277746763e-06, "loss": 0.1195, "step": 481460 }, { "epoch": 2.861957665352997, "grad_norm": 4.880580902099609, "learning_rate": 4.609617418680011e-06, "loss": 0.1106, "step": 481470 }, { "epoch": 2.862017107429665, "grad_norm": 3.3222618103027344, "learning_rate": 4.609410560285545e-06, "loss": 0.1066, "step": 481480 }, { "epoch": 2.8620765495063334, "grad_norm": 4.510812282562256, "learning_rate": 4.609203702563721e-06, "loss": 0.1278, "step": 481490 }, { "epoch": 2.862135991583002, "grad_norm": 4.255682945251465, "learning_rate": 4.608996845514894e-06, "loss": 0.1277, "step": 481500 }, { "epoch": 2.86219543365967, "grad_norm": 5.442067623138428, "learning_rate": 4.608789989139422e-06, "loss": 0.0982, "step": 481510 }, { "epoch": 2.8622548757363386, "grad_norm": 2.994006395339966, "learning_rate": 4.608583133437661e-06, "loss": 0.1197, "step": 481520 }, { "epoch": 2.862314317813007, "grad_norm": 5.072788715362549, "learning_rate": 4.608376278409964e-06, "loss": 0.1101, "step": 481530 }, { "epoch": 2.8623737598896755, "grad_norm": 2.503199577331543, "learning_rate": 4.608169424056692e-06, "loss": 0.0882, "step": 481540 }, { "epoch": 2.862433201966344, "grad_norm": 3.7360382080078125, "learning_rate": 4.607962570378199e-06, "loss": 0.1085, "step": 481550 }, { "epoch": 2.8624926440430123, "grad_norm": 3.257155179977417, "learning_rate": 4.6077557173748395e-06, "loss": 0.1089, "step": 481560 }, { "epoch": 2.8625520861196807, "grad_norm": 3.6320996284484863, "learning_rate": 4.607548865046973e-06, "loss": 0.0904, "step": 481570 }, { "epoch": 2.862611528196349, "grad_norm": 3.9312691688537598, "learning_rate": 4.607342013394953e-06, "loss": 0.0972, "step": 481580 }, { "epoch": 2.8626709702730175, "grad_norm": 3.5822627544403076, "learning_rate": 4.607135162419138e-06, "loss": 0.0983, "step": 481590 }, { "epoch": 2.862730412349686, "grad_norm": 4.435862064361572, "learning_rate": 4.606928312119882e-06, "loss": 0.0917, "step": 481600 }, { "epoch": 2.8627898544263544, "grad_norm": 4.923537254333496, "learning_rate": 4.606721462497544e-06, "loss": 0.1142, "step": 481610 }, { "epoch": 2.8628492965030228, "grad_norm": 4.099438190460205, "learning_rate": 4.6065146135524775e-06, "loss": 0.1126, "step": 481620 }, { "epoch": 2.8629087385796907, "grad_norm": 3.4730894565582275, "learning_rate": 4.6063077652850405e-06, "loss": 0.0963, "step": 481630 }, { "epoch": 2.8629681806563596, "grad_norm": 3.5928544998168945, "learning_rate": 4.606100917695588e-06, "loss": 0.0927, "step": 481640 }, { "epoch": 2.8630276227330276, "grad_norm": 4.626385688781738, "learning_rate": 4.6058940707844754e-06, "loss": 0.1053, "step": 481650 }, { "epoch": 2.8630870648096964, "grad_norm": 3.755366563796997, "learning_rate": 4.605687224552062e-06, "loss": 0.0875, "step": 481660 }, { "epoch": 2.8631465068863644, "grad_norm": 3.9331371784210205, "learning_rate": 4.6054803789987e-06, "loss": 0.1016, "step": 481670 }, { "epoch": 2.863205948963033, "grad_norm": 3.724052906036377, "learning_rate": 4.60527353412475e-06, "loss": 0.0999, "step": 481680 }, { "epoch": 2.8632653910397012, "grad_norm": 5.443775177001953, "learning_rate": 4.6050666899305664e-06, "loss": 0.1166, "step": 481690 }, { "epoch": 2.8633248331163696, "grad_norm": 3.4721665382385254, "learning_rate": 4.604859846416503e-06, "loss": 0.0978, "step": 481700 }, { "epoch": 2.863384275193038, "grad_norm": 3.873424530029297, "learning_rate": 4.6046530035829205e-06, "loss": 0.111, "step": 481710 }, { "epoch": 2.8634437172697065, "grad_norm": 3.810035228729248, "learning_rate": 4.604446161430172e-06, "loss": 0.114, "step": 481720 }, { "epoch": 2.863503159346375, "grad_norm": 5.0289626121521, "learning_rate": 4.6042393199586125e-06, "loss": 0.1086, "step": 481730 }, { "epoch": 2.8635626014230433, "grad_norm": 4.951091766357422, "learning_rate": 4.604032479168603e-06, "loss": 0.1071, "step": 481740 }, { "epoch": 2.8636220434997117, "grad_norm": 4.5864481925964355, "learning_rate": 4.603825639060495e-06, "loss": 0.1055, "step": 481750 }, { "epoch": 2.86368148557638, "grad_norm": 3.8692054748535156, "learning_rate": 4.603618799634647e-06, "loss": 0.0984, "step": 481760 }, { "epoch": 2.8637409276530486, "grad_norm": 3.2628374099731445, "learning_rate": 4.603411960891415e-06, "loss": 0.1075, "step": 481770 }, { "epoch": 2.863800369729717, "grad_norm": 5.132266044616699, "learning_rate": 4.6032051228311544e-06, "loss": 0.1127, "step": 481780 }, { "epoch": 2.8638598118063854, "grad_norm": 4.456677436828613, "learning_rate": 4.602998285454222e-06, "loss": 0.1234, "step": 481790 }, { "epoch": 2.863919253883054, "grad_norm": 4.318667411804199, "learning_rate": 4.602791448760974e-06, "loss": 0.1119, "step": 481800 }, { "epoch": 2.863978695959722, "grad_norm": 4.438046932220459, "learning_rate": 4.6025846127517674e-06, "loss": 0.1042, "step": 481810 }, { "epoch": 2.86403813803639, "grad_norm": 2.577521562576294, "learning_rate": 4.602377777426956e-06, "loss": 0.1011, "step": 481820 }, { "epoch": 2.864097580113059, "grad_norm": 4.190257549285889, "learning_rate": 4.602170942786898e-06, "loss": 0.1158, "step": 481830 }, { "epoch": 2.864157022189727, "grad_norm": 4.76839542388916, "learning_rate": 4.60196410883195e-06, "loss": 0.1073, "step": 481840 }, { "epoch": 2.864216464266396, "grad_norm": 5.427594184875488, "learning_rate": 4.601757275562465e-06, "loss": 0.128, "step": 481850 }, { "epoch": 2.864275906343064, "grad_norm": 4.255260467529297, "learning_rate": 4.601550442978805e-06, "loss": 0.0987, "step": 481860 }, { "epoch": 2.8643353484197323, "grad_norm": 4.92947244644165, "learning_rate": 4.6013436110813205e-06, "loss": 0.115, "step": 481870 }, { "epoch": 2.8643947904964007, "grad_norm": 3.1014978885650635, "learning_rate": 4.601136779870369e-06, "loss": 0.1049, "step": 481880 }, { "epoch": 2.864454232573069, "grad_norm": 4.2786712646484375, "learning_rate": 4.600929949346307e-06, "loss": 0.1074, "step": 481890 }, { "epoch": 2.8645136746497375, "grad_norm": 3.5294151306152344, "learning_rate": 4.600723119509494e-06, "loss": 0.1067, "step": 481900 }, { "epoch": 2.864573116726406, "grad_norm": 2.907834768295288, "learning_rate": 4.600516290360283e-06, "loss": 0.0931, "step": 481910 }, { "epoch": 2.8646325588030743, "grad_norm": 4.133309364318848, "learning_rate": 4.60030946189903e-06, "loss": 0.121, "step": 481920 }, { "epoch": 2.8646920008797427, "grad_norm": 3.8625190258026123, "learning_rate": 4.60010263412609e-06, "loss": 0.1022, "step": 481930 }, { "epoch": 2.864751442956411, "grad_norm": 3.003286361694336, "learning_rate": 4.5998958070418234e-06, "loss": 0.105, "step": 481940 }, { "epoch": 2.8648108850330796, "grad_norm": 3.9664013385772705, "learning_rate": 4.599688980646584e-06, "loss": 0.1206, "step": 481950 }, { "epoch": 2.864870327109748, "grad_norm": 3.126054286956787, "learning_rate": 4.599482154940727e-06, "loss": 0.0945, "step": 481960 }, { "epoch": 2.8649297691864164, "grad_norm": 4.2788472175598145, "learning_rate": 4.59927532992461e-06, "loss": 0.1149, "step": 481970 }, { "epoch": 2.864989211263085, "grad_norm": 3.986743211746216, "learning_rate": 4.599068505598589e-06, "loss": 0.1005, "step": 481980 }, { "epoch": 2.8650486533397532, "grad_norm": 3.9948854446411133, "learning_rate": 4.598861681963018e-06, "loss": 0.1018, "step": 481990 }, { "epoch": 2.8651080954164216, "grad_norm": 4.483389854431152, "learning_rate": 4.598654859018257e-06, "loss": 0.1194, "step": 482000 }, { "epoch": 2.8651675374930896, "grad_norm": 4.313501834869385, "learning_rate": 4.59844803676466e-06, "loss": 0.0936, "step": 482010 }, { "epoch": 2.8652269795697585, "grad_norm": 3.906245231628418, "learning_rate": 4.598241215202583e-06, "loss": 0.1082, "step": 482020 }, { "epoch": 2.8652864216464264, "grad_norm": 3.8412985801696777, "learning_rate": 4.598034394332382e-06, "loss": 0.1009, "step": 482030 }, { "epoch": 2.8653458637230953, "grad_norm": 3.554433584213257, "learning_rate": 4.5978275741544155e-06, "loss": 0.0977, "step": 482040 }, { "epoch": 2.8654053057997633, "grad_norm": 3.729191780090332, "learning_rate": 4.597620754669035e-06, "loss": 0.1163, "step": 482050 }, { "epoch": 2.8654647478764317, "grad_norm": 3.1254653930664062, "learning_rate": 4.5974139358766025e-06, "loss": 0.114, "step": 482060 }, { "epoch": 2.8655241899531, "grad_norm": 4.488893032073975, "learning_rate": 4.5972071177774705e-06, "loss": 0.1098, "step": 482070 }, { "epoch": 2.8655836320297685, "grad_norm": 5.305311679840088, "learning_rate": 4.597000300371994e-06, "loss": 0.1108, "step": 482080 }, { "epoch": 2.865643074106437, "grad_norm": 4.72365665435791, "learning_rate": 4.596793483660533e-06, "loss": 0.1005, "step": 482090 }, { "epoch": 2.8657025161831053, "grad_norm": 3.8907155990600586, "learning_rate": 4.596586667643442e-06, "loss": 0.1057, "step": 482100 }, { "epoch": 2.8657619582597738, "grad_norm": 4.220077991485596, "learning_rate": 4.596379852321074e-06, "loss": 0.1005, "step": 482110 }, { "epoch": 2.865821400336442, "grad_norm": 3.974482774734497, "learning_rate": 4.59617303769379e-06, "loss": 0.1104, "step": 482120 }, { "epoch": 2.8658808424131106, "grad_norm": 4.316842079162598, "learning_rate": 4.595966223761945e-06, "loss": 0.1105, "step": 482130 }, { "epoch": 2.865940284489779, "grad_norm": 4.0589118003845215, "learning_rate": 4.595759410525893e-06, "loss": 0.1202, "step": 482140 }, { "epoch": 2.8659997265664474, "grad_norm": 4.772486209869385, "learning_rate": 4.5955525979859925e-06, "loss": 0.1143, "step": 482150 }, { "epoch": 2.866059168643116, "grad_norm": 4.636096477508545, "learning_rate": 4.5953457861425986e-06, "loss": 0.0969, "step": 482160 }, { "epoch": 2.8661186107197842, "grad_norm": 5.646778583526611, "learning_rate": 4.595138974996068e-06, "loss": 0.1084, "step": 482170 }, { "epoch": 2.8661780527964527, "grad_norm": 3.8812053203582764, "learning_rate": 4.594932164546755e-06, "loss": 0.1157, "step": 482180 }, { "epoch": 2.866237494873121, "grad_norm": 5.030844211578369, "learning_rate": 4.594725354795018e-06, "loss": 0.093, "step": 482190 }, { "epoch": 2.866296936949789, "grad_norm": 4.011720180511475, "learning_rate": 4.594518545741213e-06, "loss": 0.1054, "step": 482200 }, { "epoch": 2.866356379026458, "grad_norm": 4.3761420249938965, "learning_rate": 4.594311737385694e-06, "loss": 0.1229, "step": 482210 }, { "epoch": 2.866415821103126, "grad_norm": 4.400359630584717, "learning_rate": 4.5941049297288195e-06, "loss": 0.0909, "step": 482220 }, { "epoch": 2.8664752631797943, "grad_norm": 4.365485191345215, "learning_rate": 4.593898122770945e-06, "loss": 0.1092, "step": 482230 }, { "epoch": 2.8665347052564627, "grad_norm": 4.020989894866943, "learning_rate": 4.593691316512425e-06, "loss": 0.1046, "step": 482240 }, { "epoch": 2.866594147333131, "grad_norm": 3.7051777839660645, "learning_rate": 4.5934845109536186e-06, "loss": 0.0857, "step": 482250 }, { "epoch": 2.8666535894097995, "grad_norm": 3.3799479007720947, "learning_rate": 4.5932777060948795e-06, "loss": 0.1069, "step": 482260 }, { "epoch": 2.866713031486468, "grad_norm": 3.7095232009887695, "learning_rate": 4.593070901936565e-06, "loss": 0.0993, "step": 482270 }, { "epoch": 2.8667724735631364, "grad_norm": 4.076930046081543, "learning_rate": 4.592864098479031e-06, "loss": 0.1164, "step": 482280 }, { "epoch": 2.8668319156398048, "grad_norm": 4.289403438568115, "learning_rate": 4.592657295722633e-06, "loss": 0.107, "step": 482290 }, { "epoch": 2.866891357716473, "grad_norm": 4.6983466148376465, "learning_rate": 4.592450493667728e-06, "loss": 0.1203, "step": 482300 }, { "epoch": 2.8669507997931416, "grad_norm": 4.749089241027832, "learning_rate": 4.592243692314673e-06, "loss": 0.1042, "step": 482310 }, { "epoch": 2.86701024186981, "grad_norm": 4.556164264678955, "learning_rate": 4.592036891663823e-06, "loss": 0.1043, "step": 482320 }, { "epoch": 2.8670696839464784, "grad_norm": 3.800255537033081, "learning_rate": 4.591830091715531e-06, "loss": 0.1119, "step": 482330 }, { "epoch": 2.867129126023147, "grad_norm": 4.548090934753418, "learning_rate": 4.591623292470159e-06, "loss": 0.1051, "step": 482340 }, { "epoch": 2.8671885680998153, "grad_norm": 3.204068422317505, "learning_rate": 4.5914164939280595e-06, "loss": 0.1169, "step": 482350 }, { "epoch": 2.8672480101764837, "grad_norm": 3.6744344234466553, "learning_rate": 4.59120969608959e-06, "loss": 0.1006, "step": 482360 }, { "epoch": 2.8673074522531516, "grad_norm": 3.525505304336548, "learning_rate": 4.591002898955107e-06, "loss": 0.1067, "step": 482370 }, { "epoch": 2.8673668943298205, "grad_norm": 4.100152492523193, "learning_rate": 4.590796102524964e-06, "loss": 0.1085, "step": 482380 }, { "epoch": 2.8674263364064885, "grad_norm": 6.895748615264893, "learning_rate": 4.59058930679952e-06, "loss": 0.1004, "step": 482390 }, { "epoch": 2.8674857784831573, "grad_norm": 2.804225206375122, "learning_rate": 4.5903825117791304e-06, "loss": 0.1169, "step": 482400 }, { "epoch": 2.8675452205598253, "grad_norm": 5.217176914215088, "learning_rate": 4.59017571746415e-06, "loss": 0.1067, "step": 482410 }, { "epoch": 2.8676046626364937, "grad_norm": 2.977919816970825, "learning_rate": 4.589968923854938e-06, "loss": 0.1059, "step": 482420 }, { "epoch": 2.867664104713162, "grad_norm": 4.133481025695801, "learning_rate": 4.589762130951847e-06, "loss": 0.1098, "step": 482430 }, { "epoch": 2.8677235467898305, "grad_norm": 4.1873321533203125, "learning_rate": 4.589555338755234e-06, "loss": 0.1168, "step": 482440 }, { "epoch": 2.867782988866499, "grad_norm": 3.515528917312622, "learning_rate": 4.589348547265456e-06, "loss": 0.0963, "step": 482450 }, { "epoch": 2.8678424309431674, "grad_norm": 4.4311628341674805, "learning_rate": 4.589141756482869e-06, "loss": 0.0885, "step": 482460 }, { "epoch": 2.867901873019836, "grad_norm": 3.93743634223938, "learning_rate": 4.588934966407828e-06, "loss": 0.1102, "step": 482470 }, { "epoch": 2.867961315096504, "grad_norm": 3.390324354171753, "learning_rate": 4.588728177040691e-06, "loss": 0.109, "step": 482480 }, { "epoch": 2.8680207571731726, "grad_norm": 2.520282030105591, "learning_rate": 4.588521388381814e-06, "loss": 0.103, "step": 482490 }, { "epoch": 2.868080199249841, "grad_norm": 3.5528366565704346, "learning_rate": 4.588314600431551e-06, "loss": 0.1036, "step": 482500 }, { "epoch": 2.8681396413265094, "grad_norm": 3.6612489223480225, "learning_rate": 4.58810781319026e-06, "loss": 0.1152, "step": 482510 }, { "epoch": 2.868199083403178, "grad_norm": 4.458771705627441, "learning_rate": 4.587901026658296e-06, "loss": 0.0986, "step": 482520 }, { "epoch": 2.8682585254798463, "grad_norm": 3.942216634750366, "learning_rate": 4.587694240836016e-06, "loss": 0.105, "step": 482530 }, { "epoch": 2.8683179675565147, "grad_norm": 4.512298107147217, "learning_rate": 4.587487455723776e-06, "loss": 0.1201, "step": 482540 }, { "epoch": 2.868377409633183, "grad_norm": 2.6218791007995605, "learning_rate": 4.587280671321929e-06, "loss": 0.0993, "step": 482550 }, { "epoch": 2.868436851709851, "grad_norm": 3.9999563694000244, "learning_rate": 4.587073887630837e-06, "loss": 0.1069, "step": 482560 }, { "epoch": 2.86849629378652, "grad_norm": 5.14528751373291, "learning_rate": 4.586867104650852e-06, "loss": 0.0939, "step": 482570 }, { "epoch": 2.868555735863188, "grad_norm": 4.48753023147583, "learning_rate": 4.5866603223823315e-06, "loss": 0.1038, "step": 482580 }, { "epoch": 2.8686151779398568, "grad_norm": 4.0358381271362305, "learning_rate": 4.5864535408256315e-06, "loss": 0.1136, "step": 482590 }, { "epoch": 2.8686746200165247, "grad_norm": 4.967124938964844, "learning_rate": 4.586246759981107e-06, "loss": 0.1002, "step": 482600 }, { "epoch": 2.868734062093193, "grad_norm": 4.154544353485107, "learning_rate": 4.586039979849116e-06, "loss": 0.1068, "step": 482610 }, { "epoch": 2.8687935041698616, "grad_norm": 3.6468660831451416, "learning_rate": 4.585833200430014e-06, "loss": 0.1237, "step": 482620 }, { "epoch": 2.86885294624653, "grad_norm": 3.8761935234069824, "learning_rate": 4.585626421724155e-06, "loss": 0.0942, "step": 482630 }, { "epoch": 2.8689123883231984, "grad_norm": 3.8691656589508057, "learning_rate": 4.585419643731897e-06, "loss": 0.108, "step": 482640 }, { "epoch": 2.868971830399867, "grad_norm": 4.44752311706543, "learning_rate": 4.585212866453597e-06, "loss": 0.0979, "step": 482650 }, { "epoch": 2.869031272476535, "grad_norm": 3.251450538635254, "learning_rate": 4.58500608988961e-06, "loss": 0.0875, "step": 482660 }, { "epoch": 2.8690907145532036, "grad_norm": 3.0097672939300537, "learning_rate": 4.5847993140402895e-06, "loss": 0.0998, "step": 482670 }, { "epoch": 2.869150156629872, "grad_norm": 3.7600135803222656, "learning_rate": 4.5845925389059965e-06, "loss": 0.1048, "step": 482680 }, { "epoch": 2.8692095987065405, "grad_norm": 3.378880023956299, "learning_rate": 4.584385764487085e-06, "loss": 0.1017, "step": 482690 }, { "epoch": 2.869269040783209, "grad_norm": 5.032408237457275, "learning_rate": 4.584178990783909e-06, "loss": 0.1053, "step": 482700 }, { "epoch": 2.8693284828598773, "grad_norm": 4.202997207641602, "learning_rate": 4.583972217796828e-06, "loss": 0.1042, "step": 482710 }, { "epoch": 2.8693879249365457, "grad_norm": 4.150827407836914, "learning_rate": 4.583765445526196e-06, "loss": 0.1067, "step": 482720 }, { "epoch": 2.869447367013214, "grad_norm": 3.622755289077759, "learning_rate": 4.583558673972368e-06, "loss": 0.1041, "step": 482730 }, { "epoch": 2.8695068090898825, "grad_norm": 7.78898286819458, "learning_rate": 4.583351903135704e-06, "loss": 0.1101, "step": 482740 }, { "epoch": 2.8695662511665505, "grad_norm": 3.533798933029175, "learning_rate": 4.5831451330165565e-06, "loss": 0.118, "step": 482750 }, { "epoch": 2.8696256932432194, "grad_norm": 3.911637783050537, "learning_rate": 4.582938363615282e-06, "loss": 0.0967, "step": 482760 }, { "epoch": 2.8696851353198873, "grad_norm": 5.41463565826416, "learning_rate": 4.582731594932237e-06, "loss": 0.1094, "step": 482770 }, { "epoch": 2.869744577396556, "grad_norm": 4.2377610206604, "learning_rate": 4.58252482696778e-06, "loss": 0.0876, "step": 482780 }, { "epoch": 2.869804019473224, "grad_norm": 4.6043596267700195, "learning_rate": 4.582318059722265e-06, "loss": 0.1195, "step": 482790 }, { "epoch": 2.8698634615498926, "grad_norm": 4.444585800170898, "learning_rate": 4.582111293196047e-06, "loss": 0.1284, "step": 482800 }, { "epoch": 2.869922903626561, "grad_norm": 3.3975987434387207, "learning_rate": 4.5819045273894845e-06, "loss": 0.1057, "step": 482810 }, { "epoch": 2.8699823457032294, "grad_norm": 5.319841384887695, "learning_rate": 4.581697762302932e-06, "loss": 0.1055, "step": 482820 }, { "epoch": 2.870041787779898, "grad_norm": 4.7135162353515625, "learning_rate": 4.581490997936744e-06, "loss": 0.1067, "step": 482830 }, { "epoch": 2.8701012298565662, "grad_norm": 4.5418782234191895, "learning_rate": 4.581284234291281e-06, "loss": 0.1098, "step": 482840 }, { "epoch": 2.8701606719332347, "grad_norm": 4.32956075668335, "learning_rate": 4.581077471366895e-06, "loss": 0.0997, "step": 482850 }, { "epoch": 2.870220114009903, "grad_norm": 2.9539804458618164, "learning_rate": 4.580870709163944e-06, "loss": 0.1067, "step": 482860 }, { "epoch": 2.8702795560865715, "grad_norm": 4.055070400238037, "learning_rate": 4.580663947682784e-06, "loss": 0.1213, "step": 482870 }, { "epoch": 2.87033899816324, "grad_norm": 3.7017805576324463, "learning_rate": 4.580457186923771e-06, "loss": 0.1116, "step": 482880 }, { "epoch": 2.8703984402399083, "grad_norm": 3.3535804748535156, "learning_rate": 4.58025042688726e-06, "loss": 0.0973, "step": 482890 }, { "epoch": 2.8704578823165767, "grad_norm": 2.822495222091675, "learning_rate": 4.580043667573608e-06, "loss": 0.096, "step": 482900 }, { "epoch": 2.870517324393245, "grad_norm": 3.8335893154144287, "learning_rate": 4.579836908983171e-06, "loss": 0.1093, "step": 482910 }, { "epoch": 2.8705767664699136, "grad_norm": 3.653700351715088, "learning_rate": 4.579630151116304e-06, "loss": 0.1053, "step": 482920 }, { "epoch": 2.870636208546582, "grad_norm": 2.889796018600464, "learning_rate": 4.5794233939733656e-06, "loss": 0.1149, "step": 482930 }, { "epoch": 2.87069565062325, "grad_norm": 3.813772201538086, "learning_rate": 4.579216637554709e-06, "loss": 0.1075, "step": 482940 }, { "epoch": 2.870755092699919, "grad_norm": 3.8308677673339844, "learning_rate": 4.5790098818606925e-06, "loss": 0.105, "step": 482950 }, { "epoch": 2.8708145347765868, "grad_norm": 3.2864062786102295, "learning_rate": 4.578803126891671e-06, "loss": 0.1071, "step": 482960 }, { "epoch": 2.870873976853255, "grad_norm": 3.3214869499206543, "learning_rate": 4.578596372648002e-06, "loss": 0.1006, "step": 482970 }, { "epoch": 2.8709334189299236, "grad_norm": 4.051360607147217, "learning_rate": 4.578389619130037e-06, "loss": 0.098, "step": 482980 }, { "epoch": 2.870992861006592, "grad_norm": 3.003701686859131, "learning_rate": 4.578182866338137e-06, "loss": 0.1075, "step": 482990 }, { "epoch": 2.8710523030832604, "grad_norm": 4.442694187164307, "learning_rate": 4.577976114272656e-06, "loss": 0.103, "step": 483000 }, { "epoch": 2.871111745159929, "grad_norm": 4.719616413116455, "learning_rate": 4.577769362933952e-06, "loss": 0.1172, "step": 483010 }, { "epoch": 2.8711711872365973, "grad_norm": 3.897372245788574, "learning_rate": 4.577562612322379e-06, "loss": 0.0944, "step": 483020 }, { "epoch": 2.8712306293132657, "grad_norm": 3.5820276737213135, "learning_rate": 4.577355862438293e-06, "loss": 0.1144, "step": 483030 }, { "epoch": 2.871290071389934, "grad_norm": 4.098637104034424, "learning_rate": 4.577149113282051e-06, "loss": 0.0944, "step": 483040 }, { "epoch": 2.8713495134666025, "grad_norm": 4.274289608001709, "learning_rate": 4.576942364854009e-06, "loss": 0.1103, "step": 483050 }, { "epoch": 2.871408955543271, "grad_norm": 2.4490110874176025, "learning_rate": 4.576735617154522e-06, "loss": 0.0925, "step": 483060 }, { "epoch": 2.8714683976199393, "grad_norm": 4.840236186981201, "learning_rate": 4.5765288701839485e-06, "loss": 0.1102, "step": 483070 }, { "epoch": 2.8715278396966077, "grad_norm": 3.7609546184539795, "learning_rate": 4.576322123942641e-06, "loss": 0.1012, "step": 483080 }, { "epoch": 2.871587281773276, "grad_norm": 3.231687307357788, "learning_rate": 4.5761153784309574e-06, "loss": 0.1039, "step": 483090 }, { "epoch": 2.8716467238499446, "grad_norm": 4.405198097229004, "learning_rate": 4.575908633649255e-06, "loss": 0.1045, "step": 483100 }, { "epoch": 2.8717061659266125, "grad_norm": 2.3082144260406494, "learning_rate": 4.575701889597888e-06, "loss": 0.0977, "step": 483110 }, { "epoch": 2.8717656080032814, "grad_norm": 3.544992446899414, "learning_rate": 4.575495146277212e-06, "loss": 0.0896, "step": 483120 }, { "epoch": 2.8718250500799494, "grad_norm": 3.820127010345459, "learning_rate": 4.575288403687585e-06, "loss": 0.1005, "step": 483130 }, { "epoch": 2.8718844921566182, "grad_norm": 4.707659721374512, "learning_rate": 4.575081661829363e-06, "loss": 0.1146, "step": 483140 }, { "epoch": 2.871943934233286, "grad_norm": 4.687685966491699, "learning_rate": 4.574874920702899e-06, "loss": 0.097, "step": 483150 }, { "epoch": 2.8720033763099546, "grad_norm": 4.119755268096924, "learning_rate": 4.574668180308552e-06, "loss": 0.106, "step": 483160 }, { "epoch": 2.872062818386623, "grad_norm": 4.461797714233398, "learning_rate": 4.574461440646677e-06, "loss": 0.1183, "step": 483170 }, { "epoch": 2.8721222604632914, "grad_norm": 4.880039215087891, "learning_rate": 4.57425470171763e-06, "loss": 0.1104, "step": 483180 }, { "epoch": 2.87218170253996, "grad_norm": 2.5431995391845703, "learning_rate": 4.574047963521768e-06, "loss": 0.1139, "step": 483190 }, { "epoch": 2.8722411446166283, "grad_norm": 3.302870035171509, "learning_rate": 4.573841226059446e-06, "loss": 0.1151, "step": 483200 }, { "epoch": 2.8723005866932967, "grad_norm": 4.653000354766846, "learning_rate": 4.573634489331018e-06, "loss": 0.1112, "step": 483210 }, { "epoch": 2.872360028769965, "grad_norm": 4.306089401245117, "learning_rate": 4.573427753336844e-06, "loss": 0.0961, "step": 483220 }, { "epoch": 2.8724194708466335, "grad_norm": 3.986391305923462, "learning_rate": 4.5732210180772785e-06, "loss": 0.1009, "step": 483230 }, { "epoch": 2.872478912923302, "grad_norm": 3.246778964996338, "learning_rate": 4.573014283552678e-06, "loss": 0.1104, "step": 483240 }, { "epoch": 2.8725383549999703, "grad_norm": 3.263810396194458, "learning_rate": 4.572807549763398e-06, "loss": 0.1022, "step": 483250 }, { "epoch": 2.8725977970766388, "grad_norm": 4.557321071624756, "learning_rate": 4.572600816709792e-06, "loss": 0.113, "step": 483260 }, { "epoch": 2.872657239153307, "grad_norm": 4.337218284606934, "learning_rate": 4.572394084392221e-06, "loss": 0.1083, "step": 483270 }, { "epoch": 2.8727166812299756, "grad_norm": 5.471784591674805, "learning_rate": 4.572187352811038e-06, "loss": 0.1072, "step": 483280 }, { "epoch": 2.872776123306644, "grad_norm": 3.6481106281280518, "learning_rate": 4.571980621966598e-06, "loss": 0.0913, "step": 483290 }, { "epoch": 2.872835565383312, "grad_norm": 3.725908041000366, "learning_rate": 4.571773891859259e-06, "loss": 0.1114, "step": 483300 }, { "epoch": 2.872895007459981, "grad_norm": 3.5114309787750244, "learning_rate": 4.571567162489377e-06, "loss": 0.1016, "step": 483310 }, { "epoch": 2.872954449536649, "grad_norm": 4.135091304779053, "learning_rate": 4.571360433857307e-06, "loss": 0.0982, "step": 483320 }, { "epoch": 2.8730138916133177, "grad_norm": 4.740189075469971, "learning_rate": 4.5711537059634064e-06, "loss": 0.1158, "step": 483330 }, { "epoch": 2.8730733336899856, "grad_norm": 6.40292501449585, "learning_rate": 4.570946978808029e-06, "loss": 0.1176, "step": 483340 }, { "epoch": 2.873132775766654, "grad_norm": 4.6609697341918945, "learning_rate": 4.5707402523915325e-06, "loss": 0.1016, "step": 483350 }, { "epoch": 2.8731922178433225, "grad_norm": 4.562020778656006, "learning_rate": 4.570533526714273e-06, "loss": 0.1069, "step": 483360 }, { "epoch": 2.873251659919991, "grad_norm": 4.7112579345703125, "learning_rate": 4.570326801776606e-06, "loss": 0.1045, "step": 483370 }, { "epoch": 2.8733111019966593, "grad_norm": 4.475491046905518, "learning_rate": 4.570120077578886e-06, "loss": 0.0966, "step": 483380 }, { "epoch": 2.8733705440733277, "grad_norm": 3.9126665592193604, "learning_rate": 4.569913354121473e-06, "loss": 0.1147, "step": 483390 }, { "epoch": 2.873429986149996, "grad_norm": 4.010863304138184, "learning_rate": 4.56970663140472e-06, "loss": 0.1023, "step": 483400 }, { "epoch": 2.8734894282266645, "grad_norm": 3.349547863006592, "learning_rate": 4.569499909428982e-06, "loss": 0.1089, "step": 483410 }, { "epoch": 2.873548870303333, "grad_norm": 3.6102590560913086, "learning_rate": 4.5692931881946176e-06, "loss": 0.1004, "step": 483420 }, { "epoch": 2.8736083123800014, "grad_norm": 4.584761142730713, "learning_rate": 4.5690864677019796e-06, "loss": 0.1111, "step": 483430 }, { "epoch": 2.8736677544566698, "grad_norm": 3.6852152347564697, "learning_rate": 4.568879747951428e-06, "loss": 0.0919, "step": 483440 }, { "epoch": 2.873727196533338, "grad_norm": 4.471085548400879, "learning_rate": 4.568673028943316e-06, "loss": 0.1087, "step": 483450 }, { "epoch": 2.8737866386100066, "grad_norm": 2.938133716583252, "learning_rate": 4.568466310678002e-06, "loss": 0.1086, "step": 483460 }, { "epoch": 2.873846080686675, "grad_norm": 3.863344669342041, "learning_rate": 4.56825959315584e-06, "loss": 0.1039, "step": 483470 }, { "epoch": 2.8739055227633434, "grad_norm": 4.556649208068848, "learning_rate": 4.5680528763771856e-06, "loss": 0.1166, "step": 483480 }, { "epoch": 2.8739649648400114, "grad_norm": 4.260883808135986, "learning_rate": 4.567846160342396e-06, "loss": 0.1103, "step": 483490 }, { "epoch": 2.8740244069166803, "grad_norm": 3.5669307708740234, "learning_rate": 4.567639445051828e-06, "loss": 0.0955, "step": 483500 }, { "epoch": 2.8740838489933482, "grad_norm": 3.268120765686035, "learning_rate": 4.567432730505835e-06, "loss": 0.0952, "step": 483510 }, { "epoch": 2.874143291070017, "grad_norm": 5.067347526550293, "learning_rate": 4.567226016704776e-06, "loss": 0.0964, "step": 483520 }, { "epoch": 2.874202733146685, "grad_norm": 5.744348526000977, "learning_rate": 4.567019303649005e-06, "loss": 0.1163, "step": 483530 }, { "epoch": 2.8742621752233535, "grad_norm": 4.497628211975098, "learning_rate": 4.566812591338878e-06, "loss": 0.0875, "step": 483540 }, { "epoch": 2.874321617300022, "grad_norm": 3.044511318206787, "learning_rate": 4.566605879774752e-06, "loss": 0.1059, "step": 483550 }, { "epoch": 2.8743810593766903, "grad_norm": 4.5694169998168945, "learning_rate": 4.566399168956982e-06, "loss": 0.0975, "step": 483560 }, { "epoch": 2.8744405014533587, "grad_norm": 3.2778384685516357, "learning_rate": 4.566192458885923e-06, "loss": 0.0996, "step": 483570 }, { "epoch": 2.874499943530027, "grad_norm": 3.7941479682922363, "learning_rate": 4.565985749561934e-06, "loss": 0.1097, "step": 483580 }, { "epoch": 2.8745593856066955, "grad_norm": 3.843949317932129, "learning_rate": 4.56577904098537e-06, "loss": 0.1015, "step": 483590 }, { "epoch": 2.874618827683364, "grad_norm": 3.2946395874023438, "learning_rate": 4.565572333156584e-06, "loss": 0.1006, "step": 483600 }, { "epoch": 2.8746782697600324, "grad_norm": 4.447619438171387, "learning_rate": 4.565365626075936e-06, "loss": 0.1078, "step": 483610 }, { "epoch": 2.874737711836701, "grad_norm": 3.089688301086426, "learning_rate": 4.56515891974378e-06, "loss": 0.1025, "step": 483620 }, { "epoch": 2.874797153913369, "grad_norm": 3.917818784713745, "learning_rate": 4.564952214160471e-06, "loss": 0.1078, "step": 483630 }, { "epoch": 2.8748565959900376, "grad_norm": 4.181156158447266, "learning_rate": 4.564745509326367e-06, "loss": 0.1073, "step": 483640 }, { "epoch": 2.874916038066706, "grad_norm": 3.8427746295928955, "learning_rate": 4.564538805241822e-06, "loss": 0.1025, "step": 483650 }, { "epoch": 2.8749754801433745, "grad_norm": 4.377549648284912, "learning_rate": 4.564332101907195e-06, "loss": 0.1047, "step": 483660 }, { "epoch": 2.875034922220043, "grad_norm": 3.324625015258789, "learning_rate": 4.56412539932284e-06, "loss": 0.1157, "step": 483670 }, { "epoch": 2.875094364296711, "grad_norm": 3.828892707824707, "learning_rate": 4.563918697489112e-06, "loss": 0.1073, "step": 483680 }, { "epoch": 2.8751538063733797, "grad_norm": 3.713338613510132, "learning_rate": 4.563711996406369e-06, "loss": 0.1053, "step": 483690 }, { "epoch": 2.8752132484500477, "grad_norm": 3.1350576877593994, "learning_rate": 4.563505296074966e-06, "loss": 0.101, "step": 483700 }, { "epoch": 2.875272690526716, "grad_norm": 3.9845871925354004, "learning_rate": 4.563298596495258e-06, "loss": 0.0897, "step": 483710 }, { "epoch": 2.8753321326033845, "grad_norm": 4.066682815551758, "learning_rate": 4.563091897667603e-06, "loss": 0.0966, "step": 483720 }, { "epoch": 2.875391574680053, "grad_norm": 4.48593282699585, "learning_rate": 4.562885199592356e-06, "loss": 0.1316, "step": 483730 }, { "epoch": 2.8754510167567213, "grad_norm": 3.9981532096862793, "learning_rate": 4.562678502269871e-06, "loss": 0.0983, "step": 483740 }, { "epoch": 2.8755104588333897, "grad_norm": 4.389303684234619, "learning_rate": 4.562471805700508e-06, "loss": 0.0992, "step": 483750 }, { "epoch": 2.875569900910058, "grad_norm": 3.6801018714904785, "learning_rate": 4.56226510988462e-06, "loss": 0.0964, "step": 483760 }, { "epoch": 2.8756293429867266, "grad_norm": 3.774913787841797, "learning_rate": 4.562058414822563e-06, "loss": 0.1072, "step": 483770 }, { "epoch": 2.875688785063395, "grad_norm": 5.230764865875244, "learning_rate": 4.561851720514694e-06, "loss": 0.1059, "step": 483780 }, { "epoch": 2.8757482271400634, "grad_norm": 3.3480021953582764, "learning_rate": 4.561645026961369e-06, "loss": 0.0981, "step": 483790 }, { "epoch": 2.875807669216732, "grad_norm": 2.837005376815796, "learning_rate": 4.561438334162943e-06, "loss": 0.1091, "step": 483800 }, { "epoch": 2.8758671112934002, "grad_norm": 3.1472198963165283, "learning_rate": 4.561231642119774e-06, "loss": 0.0914, "step": 483810 }, { "epoch": 2.8759265533700686, "grad_norm": 5.370146751403809, "learning_rate": 4.561024950832215e-06, "loss": 0.1091, "step": 483820 }, { "epoch": 2.875985995446737, "grad_norm": 4.225203037261963, "learning_rate": 4.560818260300623e-06, "loss": 0.1128, "step": 483830 }, { "epoch": 2.8760454375234055, "grad_norm": 3.1236886978149414, "learning_rate": 4.5606115705253555e-06, "loss": 0.1141, "step": 483840 }, { "epoch": 2.8761048796000734, "grad_norm": 4.3962788581848145, "learning_rate": 4.560404881506768e-06, "loss": 0.1206, "step": 483850 }, { "epoch": 2.8761643216767423, "grad_norm": 3.65767502784729, "learning_rate": 4.560198193245214e-06, "loss": 0.1111, "step": 483860 }, { "epoch": 2.8762237637534103, "grad_norm": 4.373030662536621, "learning_rate": 4.55999150574105e-06, "loss": 0.0969, "step": 483870 }, { "epoch": 2.876283205830079, "grad_norm": 3.1619536876678467, "learning_rate": 4.559784818994635e-06, "loss": 0.1115, "step": 483880 }, { "epoch": 2.876342647906747, "grad_norm": 4.9755401611328125, "learning_rate": 4.559578133006324e-06, "loss": 0.1101, "step": 483890 }, { "epoch": 2.8764020899834155, "grad_norm": 5.216583251953125, "learning_rate": 4.55937144777647e-06, "loss": 0.1041, "step": 483900 }, { "epoch": 2.876461532060084, "grad_norm": 5.87555456161499, "learning_rate": 4.559164763305433e-06, "loss": 0.1002, "step": 483910 }, { "epoch": 2.8765209741367523, "grad_norm": 3.730869770050049, "learning_rate": 4.558958079593566e-06, "loss": 0.1109, "step": 483920 }, { "epoch": 2.8765804162134208, "grad_norm": 3.9117238521575928, "learning_rate": 4.558751396641226e-06, "loss": 0.1013, "step": 483930 }, { "epoch": 2.876639858290089, "grad_norm": 3.2986865043640137, "learning_rate": 4.558544714448768e-06, "loss": 0.0901, "step": 483940 }, { "epoch": 2.8766993003667576, "grad_norm": 3.2524335384368896, "learning_rate": 4.558338033016549e-06, "loss": 0.095, "step": 483950 }, { "epoch": 2.876758742443426, "grad_norm": 3.716534376144409, "learning_rate": 4.558131352344925e-06, "loss": 0.109, "step": 483960 }, { "epoch": 2.8768181845200944, "grad_norm": 3.4168426990509033, "learning_rate": 4.557924672434251e-06, "loss": 0.1128, "step": 483970 }, { "epoch": 2.876877626596763, "grad_norm": 3.5020759105682373, "learning_rate": 4.557717993284883e-06, "loss": 0.1061, "step": 483980 }, { "epoch": 2.8769370686734312, "grad_norm": 4.120064735412598, "learning_rate": 4.557511314897179e-06, "loss": 0.1127, "step": 483990 }, { "epoch": 2.8769965107500997, "grad_norm": 2.7051124572753906, "learning_rate": 4.557304637271492e-06, "loss": 0.1113, "step": 484000 }, { "epoch": 2.877055952826768, "grad_norm": 3.5453598499298096, "learning_rate": 4.55709796040818e-06, "loss": 0.0841, "step": 484010 }, { "epoch": 2.8771153949034365, "grad_norm": 4.813670635223389, "learning_rate": 4.556891284307599e-06, "loss": 0.1184, "step": 484020 }, { "epoch": 2.877174836980105, "grad_norm": 2.6584365367889404, "learning_rate": 4.556684608970101e-06, "loss": 0.1246, "step": 484030 }, { "epoch": 2.877234279056773, "grad_norm": 2.724689245223999, "learning_rate": 4.556477934396047e-06, "loss": 0.0992, "step": 484040 }, { "epoch": 2.8772937211334417, "grad_norm": 3.8798437118530273, "learning_rate": 4.556271260585792e-06, "loss": 0.1019, "step": 484050 }, { "epoch": 2.8773531632101097, "grad_norm": 4.4509429931640625, "learning_rate": 4.556064587539689e-06, "loss": 0.0921, "step": 484060 }, { "epoch": 2.8774126052867786, "grad_norm": 4.482614040374756, "learning_rate": 4.555857915258097e-06, "loss": 0.101, "step": 484070 }, { "epoch": 2.8774720473634465, "grad_norm": 4.4361467361450195, "learning_rate": 4.55565124374137e-06, "loss": 0.1003, "step": 484080 }, { "epoch": 2.877531489440115, "grad_norm": 3.776545286178589, "learning_rate": 4.555444572989863e-06, "loss": 0.0983, "step": 484090 }, { "epoch": 2.8775909315167834, "grad_norm": 4.108487606048584, "learning_rate": 4.5552379030039344e-06, "loss": 0.114, "step": 484100 }, { "epoch": 2.8776503735934518, "grad_norm": 3.219351053237915, "learning_rate": 4.5550312337839406e-06, "loss": 0.0991, "step": 484110 }, { "epoch": 2.87770981567012, "grad_norm": 4.272970676422119, "learning_rate": 4.554824565330235e-06, "loss": 0.1021, "step": 484120 }, { "epoch": 2.8777692577467886, "grad_norm": 4.5223774909973145, "learning_rate": 4.5546178976431746e-06, "loss": 0.0972, "step": 484130 }, { "epoch": 2.877828699823457, "grad_norm": 3.7143824100494385, "learning_rate": 4.5544112307231165e-06, "loss": 0.1163, "step": 484140 }, { "epoch": 2.8778881419001254, "grad_norm": 4.089674949645996, "learning_rate": 4.554204564570414e-06, "loss": 0.1231, "step": 484150 }, { "epoch": 2.877947583976794, "grad_norm": 3.10825252532959, "learning_rate": 4.553997899185426e-06, "loss": 0.0992, "step": 484160 }, { "epoch": 2.8780070260534623, "grad_norm": 5.175279140472412, "learning_rate": 4.553791234568506e-06, "loss": 0.1038, "step": 484170 }, { "epoch": 2.8780664681301307, "grad_norm": 3.613100290298462, "learning_rate": 4.553584570720011e-06, "loss": 0.0987, "step": 484180 }, { "epoch": 2.878125910206799, "grad_norm": 2.945298910140991, "learning_rate": 4.553377907640296e-06, "loss": 0.112, "step": 484190 }, { "epoch": 2.8781853522834675, "grad_norm": 3.4591362476348877, "learning_rate": 4.553171245329717e-06, "loss": 0.1071, "step": 484200 }, { "epoch": 2.878244794360136, "grad_norm": 3.8071746826171875, "learning_rate": 4.552964583788633e-06, "loss": 0.1116, "step": 484210 }, { "epoch": 2.8783042364368043, "grad_norm": 3.764976739883423, "learning_rate": 4.5527579230173945e-06, "loss": 0.1088, "step": 484220 }, { "epoch": 2.8783636785134723, "grad_norm": 3.3755698204040527, "learning_rate": 4.5525512630163615e-06, "loss": 0.0895, "step": 484230 }, { "epoch": 2.878423120590141, "grad_norm": 2.7772717475891113, "learning_rate": 4.552344603785889e-06, "loss": 0.1005, "step": 484240 }, { "epoch": 2.878482562666809, "grad_norm": 3.166433811187744, "learning_rate": 4.552137945326331e-06, "loss": 0.0865, "step": 484250 }, { "epoch": 2.878542004743478, "grad_norm": 3.050987958908081, "learning_rate": 4.551931287638046e-06, "loss": 0.0987, "step": 484260 }, { "epoch": 2.878601446820146, "grad_norm": 3.932129144668579, "learning_rate": 4.55172463072139e-06, "loss": 0.1121, "step": 484270 }, { "epoch": 2.8786608888968144, "grad_norm": 5.0733819007873535, "learning_rate": 4.551517974576715e-06, "loss": 0.107, "step": 484280 }, { "epoch": 2.878720330973483, "grad_norm": 3.910738945007324, "learning_rate": 4.5513113192043815e-06, "loss": 0.0978, "step": 484290 }, { "epoch": 2.878779773050151, "grad_norm": 3.2912888526916504, "learning_rate": 4.551104664604743e-06, "loss": 0.0876, "step": 484300 }, { "epoch": 2.8788392151268196, "grad_norm": 4.824456214904785, "learning_rate": 4.550898010778154e-06, "loss": 0.1097, "step": 484310 }, { "epoch": 2.878898657203488, "grad_norm": 3.5026912689208984, "learning_rate": 4.550691357724974e-06, "loss": 0.1149, "step": 484320 }, { "epoch": 2.8789580992801564, "grad_norm": 3.9594922065734863, "learning_rate": 4.550484705445556e-06, "loss": 0.1051, "step": 484330 }, { "epoch": 2.879017541356825, "grad_norm": 4.044188976287842, "learning_rate": 4.5502780539402584e-06, "loss": 0.0959, "step": 484340 }, { "epoch": 2.8790769834334933, "grad_norm": 3.080435037612915, "learning_rate": 4.550071403209436e-06, "loss": 0.1108, "step": 484350 }, { "epoch": 2.8791364255101617, "grad_norm": 3.577836275100708, "learning_rate": 4.549864753253443e-06, "loss": 0.1223, "step": 484360 }, { "epoch": 2.87919586758683, "grad_norm": 3.2072534561157227, "learning_rate": 4.549658104072638e-06, "loss": 0.1074, "step": 484370 }, { "epoch": 2.8792553096634985, "grad_norm": 3.3180534839630127, "learning_rate": 4.549451455667374e-06, "loss": 0.0975, "step": 484380 }, { "epoch": 2.879314751740167, "grad_norm": 3.881221055984497, "learning_rate": 4.549244808038008e-06, "loss": 0.0971, "step": 484390 }, { "epoch": 2.8793741938168353, "grad_norm": 4.285085678100586, "learning_rate": 4.549038161184898e-06, "loss": 0.0992, "step": 484400 }, { "epoch": 2.8794336358935038, "grad_norm": 2.7596042156219482, "learning_rate": 4.548831515108398e-06, "loss": 0.0797, "step": 484410 }, { "epoch": 2.8794930779701717, "grad_norm": 4.160064697265625, "learning_rate": 4.548624869808862e-06, "loss": 0.1157, "step": 484420 }, { "epoch": 2.8795525200468406, "grad_norm": 3.917664051055908, "learning_rate": 4.548418225286649e-06, "loss": 0.0898, "step": 484430 }, { "epoch": 2.8796119621235086, "grad_norm": 3.5443382263183594, "learning_rate": 4.548211581542115e-06, "loss": 0.1058, "step": 484440 }, { "epoch": 2.879671404200177, "grad_norm": 5.198221683502197, "learning_rate": 4.5480049385756125e-06, "loss": 0.0989, "step": 484450 }, { "epoch": 2.8797308462768454, "grad_norm": 3.5189805030822754, "learning_rate": 4.5477982963875e-06, "loss": 0.0806, "step": 484460 }, { "epoch": 2.879790288353514, "grad_norm": 2.9075701236724854, "learning_rate": 4.547591654978134e-06, "loss": 0.0842, "step": 484470 }, { "epoch": 2.879849730430182, "grad_norm": 3.624906301498413, "learning_rate": 4.547385014347868e-06, "loss": 0.1087, "step": 484480 }, { "epoch": 2.8799091725068506, "grad_norm": 4.082132816314697, "learning_rate": 4.547178374497058e-06, "loss": 0.1087, "step": 484490 }, { "epoch": 2.879968614583519, "grad_norm": 3.9571144580841064, "learning_rate": 4.546971735426064e-06, "loss": 0.1003, "step": 484500 }, { "epoch": 2.8800280566601875, "grad_norm": 4.133387565612793, "learning_rate": 4.546765097135236e-06, "loss": 0.1049, "step": 484510 }, { "epoch": 2.880087498736856, "grad_norm": 3.7086143493652344, "learning_rate": 4.546558459624933e-06, "loss": 0.109, "step": 484520 }, { "epoch": 2.8801469408135243, "grad_norm": 4.8350324630737305, "learning_rate": 4.54635182289551e-06, "loss": 0.1151, "step": 484530 }, { "epoch": 2.8802063828901927, "grad_norm": 3.5087099075317383, "learning_rate": 4.546145186947324e-06, "loss": 0.0989, "step": 484540 }, { "epoch": 2.880265824966861, "grad_norm": 3.733339548110962, "learning_rate": 4.5459385517807295e-06, "loss": 0.1024, "step": 484550 }, { "epoch": 2.8803252670435295, "grad_norm": 4.721045017242432, "learning_rate": 4.545731917396084e-06, "loss": 0.0989, "step": 484560 }, { "epoch": 2.880384709120198, "grad_norm": 3.159085273742676, "learning_rate": 4.545525283793742e-06, "loss": 0.0995, "step": 484570 }, { "epoch": 2.8804441511968664, "grad_norm": 4.279050350189209, "learning_rate": 4.545318650974061e-06, "loss": 0.1146, "step": 484580 }, { "epoch": 2.8805035932735343, "grad_norm": 4.977304458618164, "learning_rate": 4.545112018937393e-06, "loss": 0.1016, "step": 484590 }, { "epoch": 2.880563035350203, "grad_norm": 5.081200122833252, "learning_rate": 4.544905387684098e-06, "loss": 0.114, "step": 484600 }, { "epoch": 2.880622477426871, "grad_norm": 2.7834484577178955, "learning_rate": 4.544698757214531e-06, "loss": 0.1015, "step": 484610 }, { "epoch": 2.88068191950354, "grad_norm": 5.29593563079834, "learning_rate": 4.544492127529045e-06, "loss": 0.102, "step": 484620 }, { "epoch": 2.880741361580208, "grad_norm": 4.499988079071045, "learning_rate": 4.544285498627999e-06, "loss": 0.1039, "step": 484630 }, { "epoch": 2.8808008036568764, "grad_norm": 4.144277572631836, "learning_rate": 4.544078870511748e-06, "loss": 0.1062, "step": 484640 }, { "epoch": 2.880860245733545, "grad_norm": 3.7087016105651855, "learning_rate": 4.543872243180647e-06, "loss": 0.1244, "step": 484650 }, { "epoch": 2.8809196878102132, "grad_norm": 2.7043275833129883, "learning_rate": 4.543665616635052e-06, "loss": 0.1013, "step": 484660 }, { "epoch": 2.8809791298868817, "grad_norm": 2.668678045272827, "learning_rate": 4.543458990875321e-06, "loss": 0.104, "step": 484670 }, { "epoch": 2.88103857196355, "grad_norm": 2.7994496822357178, "learning_rate": 4.5432523659018056e-06, "loss": 0.1027, "step": 484680 }, { "epoch": 2.8810980140402185, "grad_norm": 4.8519368171691895, "learning_rate": 4.543045741714866e-06, "loss": 0.1065, "step": 484690 }, { "epoch": 2.881157456116887, "grad_norm": 5.667823314666748, "learning_rate": 4.542839118314856e-06, "loss": 0.0996, "step": 484700 }, { "epoch": 2.8812168981935553, "grad_norm": 4.0602803230285645, "learning_rate": 4.54263249570213e-06, "loss": 0.109, "step": 484710 }, { "epoch": 2.8812763402702237, "grad_norm": 4.719191074371338, "learning_rate": 4.542425873877048e-06, "loss": 0.0961, "step": 484720 }, { "epoch": 2.881335782346892, "grad_norm": 3.719404935836792, "learning_rate": 4.542219252839962e-06, "loss": 0.0933, "step": 484730 }, { "epoch": 2.8813952244235606, "grad_norm": 3.7099483013153076, "learning_rate": 4.542012632591228e-06, "loss": 0.1041, "step": 484740 }, { "epoch": 2.881454666500229, "grad_norm": 3.7561802864074707, "learning_rate": 4.541806013131203e-06, "loss": 0.1124, "step": 484750 }, { "epoch": 2.8815141085768974, "grad_norm": 3.2179312705993652, "learning_rate": 4.541599394460243e-06, "loss": 0.0963, "step": 484760 }, { "epoch": 2.881573550653566, "grad_norm": 4.713210582733154, "learning_rate": 4.541392776578705e-06, "loss": 0.1042, "step": 484770 }, { "epoch": 2.8816329927302338, "grad_norm": 5.243605613708496, "learning_rate": 4.5411861594869416e-06, "loss": 0.117, "step": 484780 }, { "epoch": 2.8816924348069026, "grad_norm": 4.205941677093506, "learning_rate": 4.5409795431853116e-06, "loss": 0.1141, "step": 484790 }, { "epoch": 2.8817518768835706, "grad_norm": 4.8561248779296875, "learning_rate": 4.54077292767417e-06, "loss": 0.0961, "step": 484800 }, { "epoch": 2.8818113189602395, "grad_norm": 3.3807742595672607, "learning_rate": 4.540566312953871e-06, "loss": 0.1044, "step": 484810 }, { "epoch": 2.8818707610369074, "grad_norm": 4.179859161376953, "learning_rate": 4.5403596990247725e-06, "loss": 0.0977, "step": 484820 }, { "epoch": 2.881930203113576, "grad_norm": 4.573582172393799, "learning_rate": 4.540153085887229e-06, "loss": 0.1077, "step": 484830 }, { "epoch": 2.8819896451902443, "grad_norm": 3.6414785385131836, "learning_rate": 4.539946473541596e-06, "loss": 0.1097, "step": 484840 }, { "epoch": 2.8820490872669127, "grad_norm": 4.134151458740234, "learning_rate": 4.539739861988231e-06, "loss": 0.1019, "step": 484850 }, { "epoch": 2.882108529343581, "grad_norm": 5.044403553009033, "learning_rate": 4.539533251227489e-06, "loss": 0.1028, "step": 484860 }, { "epoch": 2.8821679714202495, "grad_norm": 5.35257625579834, "learning_rate": 4.539326641259725e-06, "loss": 0.1113, "step": 484870 }, { "epoch": 2.882227413496918, "grad_norm": 4.3793535232543945, "learning_rate": 4.539120032085296e-06, "loss": 0.1024, "step": 484880 }, { "epoch": 2.8822868555735863, "grad_norm": 4.69497013092041, "learning_rate": 4.538913423704558e-06, "loss": 0.1267, "step": 484890 }, { "epoch": 2.8823462976502547, "grad_norm": 4.150515556335449, "learning_rate": 4.538706816117864e-06, "loss": 0.1132, "step": 484900 }, { "epoch": 2.882405739726923, "grad_norm": 3.5116450786590576, "learning_rate": 4.538500209325574e-06, "loss": 0.0966, "step": 484910 }, { "epoch": 2.8824651818035916, "grad_norm": 4.481698989868164, "learning_rate": 4.5382936033280415e-06, "loss": 0.0891, "step": 484920 }, { "epoch": 2.88252462388026, "grad_norm": 3.5145039558410645, "learning_rate": 4.538086998125621e-06, "loss": 0.0987, "step": 484930 }, { "epoch": 2.8825840659569284, "grad_norm": 4.189977645874023, "learning_rate": 4.537880393718671e-06, "loss": 0.1103, "step": 484940 }, { "epoch": 2.882643508033597, "grad_norm": 4.400463104248047, "learning_rate": 4.537673790107546e-06, "loss": 0.1104, "step": 484950 }, { "epoch": 2.8827029501102652, "grad_norm": 4.910618305206299, "learning_rate": 4.5374671872926014e-06, "loss": 0.1066, "step": 484960 }, { "epoch": 2.882762392186933, "grad_norm": 4.056026935577393, "learning_rate": 4.537260585274193e-06, "loss": 0.1038, "step": 484970 }, { "epoch": 2.882821834263602, "grad_norm": 3.9235994815826416, "learning_rate": 4.537053984052677e-06, "loss": 0.1061, "step": 484980 }, { "epoch": 2.88288127634027, "grad_norm": 5.1822004318237305, "learning_rate": 4.53684738362841e-06, "loss": 0.1113, "step": 484990 }, { "epoch": 2.882940718416939, "grad_norm": 3.372647285461426, "learning_rate": 4.536640784001749e-06, "loss": 0.0939, "step": 485000 }, { "epoch": 2.883000160493607, "grad_norm": 3.554330587387085, "learning_rate": 4.536434185173045e-06, "loss": 0.1046, "step": 485010 }, { "epoch": 2.8830596025702753, "grad_norm": 3.5584850311279297, "learning_rate": 4.536227587142657e-06, "loss": 0.0906, "step": 485020 }, { "epoch": 2.8831190446469437, "grad_norm": 4.252330780029297, "learning_rate": 4.5360209899109425e-06, "loss": 0.1115, "step": 485030 }, { "epoch": 2.883178486723612, "grad_norm": 4.685732841491699, "learning_rate": 4.5358143934782524e-06, "loss": 0.0975, "step": 485040 }, { "epoch": 2.8832379288002805, "grad_norm": 4.8796796798706055, "learning_rate": 4.535607797844947e-06, "loss": 0.0974, "step": 485050 }, { "epoch": 2.883297370876949, "grad_norm": 3.71809983253479, "learning_rate": 4.535401203011382e-06, "loss": 0.1002, "step": 485060 }, { "epoch": 2.8833568129536173, "grad_norm": 4.001243591308594, "learning_rate": 4.535194608977909e-06, "loss": 0.0953, "step": 485070 }, { "epoch": 2.8834162550302858, "grad_norm": 3.5051839351654053, "learning_rate": 4.534988015744887e-06, "loss": 0.1039, "step": 485080 }, { "epoch": 2.883475697106954, "grad_norm": 2.5358779430389404, "learning_rate": 4.5347814233126714e-06, "loss": 0.097, "step": 485090 }, { "epoch": 2.8835351391836226, "grad_norm": 4.4916558265686035, "learning_rate": 4.534574831681617e-06, "loss": 0.1095, "step": 485100 }, { "epoch": 2.883594581260291, "grad_norm": 3.803177833557129, "learning_rate": 4.5343682408520806e-06, "loss": 0.1085, "step": 485110 }, { "epoch": 2.8836540233369594, "grad_norm": 3.182389259338379, "learning_rate": 4.534161650824418e-06, "loss": 0.1164, "step": 485120 }, { "epoch": 2.883713465413628, "grad_norm": 3.35933256149292, "learning_rate": 4.533955061598984e-06, "loss": 0.0963, "step": 485130 }, { "epoch": 2.8837729074902962, "grad_norm": 3.250439167022705, "learning_rate": 4.533748473176136e-06, "loss": 0.1031, "step": 485140 }, { "epoch": 2.8838323495669647, "grad_norm": 4.234126091003418, "learning_rate": 4.533541885556229e-06, "loss": 0.1084, "step": 485150 }, { "epoch": 2.8838917916436326, "grad_norm": 4.9534101486206055, "learning_rate": 4.533335298739617e-06, "loss": 0.1028, "step": 485160 }, { "epoch": 2.8839512337203015, "grad_norm": 3.4682600498199463, "learning_rate": 4.533128712726658e-06, "loss": 0.0978, "step": 485170 }, { "epoch": 2.8840106757969695, "grad_norm": 4.304834365844727, "learning_rate": 4.532922127517708e-06, "loss": 0.1036, "step": 485180 }, { "epoch": 2.884070117873638, "grad_norm": 5.000932216644287, "learning_rate": 4.532715543113119e-06, "loss": 0.1089, "step": 485190 }, { "epoch": 2.8841295599503063, "grad_norm": 3.8182103633880615, "learning_rate": 4.5325089595132505e-06, "loss": 0.0948, "step": 485200 }, { "epoch": 2.8841890020269747, "grad_norm": 3.38824462890625, "learning_rate": 4.532302376718458e-06, "loss": 0.1044, "step": 485210 }, { "epoch": 2.884248444103643, "grad_norm": 2.9828832149505615, "learning_rate": 4.532095794729098e-06, "loss": 0.1052, "step": 485220 }, { "epoch": 2.8843078861803115, "grad_norm": 3.2646565437316895, "learning_rate": 4.531889213545523e-06, "loss": 0.0866, "step": 485230 }, { "epoch": 2.88436732825698, "grad_norm": 6.0626020431518555, "learning_rate": 4.531682633168092e-06, "loss": 0.1137, "step": 485240 }, { "epoch": 2.8844267703336484, "grad_norm": 4.711611747741699, "learning_rate": 4.531476053597159e-06, "loss": 0.1081, "step": 485250 }, { "epoch": 2.8844862124103168, "grad_norm": 3.537332534790039, "learning_rate": 4.531269474833081e-06, "loss": 0.124, "step": 485260 }, { "epoch": 2.884545654486985, "grad_norm": 3.567673444747925, "learning_rate": 4.5310628968762105e-06, "loss": 0.1064, "step": 485270 }, { "epoch": 2.8846050965636536, "grad_norm": 3.4960224628448486, "learning_rate": 4.530856319726907e-06, "loss": 0.0844, "step": 485280 }, { "epoch": 2.884664538640322, "grad_norm": 4.333490371704102, "learning_rate": 4.530649743385525e-06, "loss": 0.0989, "step": 485290 }, { "epoch": 2.8847239807169904, "grad_norm": 2.982863664627075, "learning_rate": 4.53044316785242e-06, "loss": 0.095, "step": 485300 }, { "epoch": 2.884783422793659, "grad_norm": 2.8760323524475098, "learning_rate": 4.530236593127949e-06, "loss": 0.1029, "step": 485310 }, { "epoch": 2.8848428648703273, "grad_norm": 4.793490886688232, "learning_rate": 4.530030019212465e-06, "loss": 0.1079, "step": 485320 }, { "epoch": 2.8849023069469952, "grad_norm": 3.0939698219299316, "learning_rate": 4.5298234461063255e-06, "loss": 0.1056, "step": 485330 }, { "epoch": 2.884961749023664, "grad_norm": 3.2107324600219727, "learning_rate": 4.5296168738098875e-06, "loss": 0.1068, "step": 485340 }, { "epoch": 2.885021191100332, "grad_norm": 7.2145490646362305, "learning_rate": 4.529410302323504e-06, "loss": 0.1146, "step": 485350 }, { "epoch": 2.885080633177001, "grad_norm": 3.578372001647949, "learning_rate": 4.529203731647532e-06, "loss": 0.1103, "step": 485360 }, { "epoch": 2.885140075253669, "grad_norm": 3.0939784049987793, "learning_rate": 4.5289971617823285e-06, "loss": 0.0917, "step": 485370 }, { "epoch": 2.8851995173303373, "grad_norm": 3.592130661010742, "learning_rate": 4.528790592728248e-06, "loss": 0.1009, "step": 485380 }, { "epoch": 2.8852589594070057, "grad_norm": 3.7581093311309814, "learning_rate": 4.528584024485645e-06, "loss": 0.0867, "step": 485390 }, { "epoch": 2.885318401483674, "grad_norm": 3.513751983642578, "learning_rate": 4.528377457054878e-06, "loss": 0.0909, "step": 485400 }, { "epoch": 2.8853778435603425, "grad_norm": 3.606088638305664, "learning_rate": 4.528170890436298e-06, "loss": 0.1117, "step": 485410 }, { "epoch": 2.885437285637011, "grad_norm": 3.831430435180664, "learning_rate": 4.527964324630268e-06, "loss": 0.1156, "step": 485420 }, { "epoch": 2.8854967277136794, "grad_norm": 2.3608198165893555, "learning_rate": 4.527757759637137e-06, "loss": 0.1127, "step": 485430 }, { "epoch": 2.885556169790348, "grad_norm": 4.8304877281188965, "learning_rate": 4.527551195457266e-06, "loss": 0.1007, "step": 485440 }, { "epoch": 2.885615611867016, "grad_norm": 5.896290302276611, "learning_rate": 4.527344632091008e-06, "loss": 0.1079, "step": 485450 }, { "epoch": 2.8856750539436846, "grad_norm": 4.804624080657959, "learning_rate": 4.5271380695387165e-06, "loss": 0.1071, "step": 485460 }, { "epoch": 2.885734496020353, "grad_norm": 3.924227714538574, "learning_rate": 4.526931507800752e-06, "loss": 0.1141, "step": 485470 }, { "epoch": 2.8857939380970214, "grad_norm": 4.422688961029053, "learning_rate": 4.5267249468774675e-06, "loss": 0.1107, "step": 485480 }, { "epoch": 2.88585338017369, "grad_norm": 3.9402987957000732, "learning_rate": 4.526518386769218e-06, "loss": 0.1005, "step": 485490 }, { "epoch": 2.8859128222503583, "grad_norm": 3.5002267360687256, "learning_rate": 4.526311827476362e-06, "loss": 0.099, "step": 485500 }, { "epoch": 2.8859722643270267, "grad_norm": 3.6606669425964355, "learning_rate": 4.526105268999252e-06, "loss": 0.1012, "step": 485510 }, { "epoch": 2.8860317064036947, "grad_norm": 3.483074188232422, "learning_rate": 4.525898711338246e-06, "loss": 0.1102, "step": 485520 }, { "epoch": 2.8860911484803635, "grad_norm": 4.0778889656066895, "learning_rate": 4.5256921544937e-06, "loss": 0.103, "step": 485530 }, { "epoch": 2.8861505905570315, "grad_norm": 4.022551536560059, "learning_rate": 4.525485598465967e-06, "loss": 0.0997, "step": 485540 }, { "epoch": 2.8862100326337004, "grad_norm": 3.3620269298553467, "learning_rate": 4.525279043255404e-06, "loss": 0.1055, "step": 485550 }, { "epoch": 2.8862694747103683, "grad_norm": 2.7517619132995605, "learning_rate": 4.525072488862369e-06, "loss": 0.0963, "step": 485560 }, { "epoch": 2.8863289167870367, "grad_norm": 5.13686990737915, "learning_rate": 4.524865935287216e-06, "loss": 0.121, "step": 485570 }, { "epoch": 2.886388358863705, "grad_norm": 2.9021759033203125, "learning_rate": 4.524659382530298e-06, "loss": 0.0951, "step": 485580 }, { "epoch": 2.8864478009403736, "grad_norm": 3.1401891708374023, "learning_rate": 4.524452830591976e-06, "loss": 0.1003, "step": 485590 }, { "epoch": 2.886507243017042, "grad_norm": 2.879230499267578, "learning_rate": 4.524246279472602e-06, "loss": 0.102, "step": 485600 }, { "epoch": 2.8865666850937104, "grad_norm": 4.555696964263916, "learning_rate": 4.524039729172531e-06, "loss": 0.1033, "step": 485610 }, { "epoch": 2.886626127170379, "grad_norm": 3.651613235473633, "learning_rate": 4.5238331796921224e-06, "loss": 0.0971, "step": 485620 }, { "epoch": 2.8866855692470472, "grad_norm": 3.8730764389038086, "learning_rate": 4.523626631031728e-06, "loss": 0.084, "step": 485630 }, { "epoch": 2.8867450113237156, "grad_norm": 3.105252504348755, "learning_rate": 4.523420083191706e-06, "loss": 0.1056, "step": 485640 }, { "epoch": 2.886804453400384, "grad_norm": 3.480520248413086, "learning_rate": 4.523213536172414e-06, "loss": 0.0985, "step": 485650 }, { "epoch": 2.8868638954770525, "grad_norm": 4.114909648895264, "learning_rate": 4.523006989974202e-06, "loss": 0.1129, "step": 485660 }, { "epoch": 2.886923337553721, "grad_norm": 3.647599220275879, "learning_rate": 4.522800444597431e-06, "loss": 0.1047, "step": 485670 }, { "epoch": 2.8869827796303893, "grad_norm": 3.5156116485595703, "learning_rate": 4.522593900042453e-06, "loss": 0.0934, "step": 485680 }, { "epoch": 2.8870422217070577, "grad_norm": 3.965294599533081, "learning_rate": 4.522387356309626e-06, "loss": 0.0983, "step": 485690 }, { "epoch": 2.887101663783726, "grad_norm": 4.137448310852051, "learning_rate": 4.522180813399306e-06, "loss": 0.0959, "step": 485700 }, { "epoch": 2.887161105860394, "grad_norm": 3.882587432861328, "learning_rate": 4.521974271311847e-06, "loss": 0.1037, "step": 485710 }, { "epoch": 2.887220547937063, "grad_norm": 4.439187526702881, "learning_rate": 4.521767730047603e-06, "loss": 0.102, "step": 485720 }, { "epoch": 2.887279990013731, "grad_norm": 3.63271427154541, "learning_rate": 4.521561189606935e-06, "loss": 0.1247, "step": 485730 }, { "epoch": 2.8873394320904, "grad_norm": 3.779775857925415, "learning_rate": 4.521354649990195e-06, "loss": 0.0882, "step": 485740 }, { "epoch": 2.8873988741670678, "grad_norm": 6.278820991516113, "learning_rate": 4.521148111197739e-06, "loss": 0.0963, "step": 485750 }, { "epoch": 2.887458316243736, "grad_norm": 4.592043399810791, "learning_rate": 4.520941573229923e-06, "loss": 0.1077, "step": 485760 }, { "epoch": 2.8875177583204046, "grad_norm": 3.8745129108428955, "learning_rate": 4.520735036087104e-06, "loss": 0.096, "step": 485770 }, { "epoch": 2.887577200397073, "grad_norm": 3.3320600986480713, "learning_rate": 4.520528499769635e-06, "loss": 0.1113, "step": 485780 }, { "epoch": 2.8876366424737414, "grad_norm": 3.512260913848877, "learning_rate": 4.520321964277874e-06, "loss": 0.0786, "step": 485790 }, { "epoch": 2.88769608455041, "grad_norm": 4.747344017028809, "learning_rate": 4.520115429612175e-06, "loss": 0.1028, "step": 485800 }, { "epoch": 2.8877555266270782, "grad_norm": 4.534707546234131, "learning_rate": 4.519908895772895e-06, "loss": 0.1021, "step": 485810 }, { "epoch": 2.8878149687037467, "grad_norm": 3.443129539489746, "learning_rate": 4.519702362760389e-06, "loss": 0.0851, "step": 485820 }, { "epoch": 2.887874410780415, "grad_norm": 3.676616668701172, "learning_rate": 4.519495830575013e-06, "loss": 0.1094, "step": 485830 }, { "epoch": 2.8879338528570835, "grad_norm": 5.078441619873047, "learning_rate": 4.519289299217121e-06, "loss": 0.1055, "step": 485840 }, { "epoch": 2.887993294933752, "grad_norm": 3.8094370365142822, "learning_rate": 4.519082768687071e-06, "loss": 0.1077, "step": 485850 }, { "epoch": 2.8880527370104203, "grad_norm": 4.421792507171631, "learning_rate": 4.518876238985218e-06, "loss": 0.0898, "step": 485860 }, { "epoch": 2.8881121790870887, "grad_norm": 4.282370090484619, "learning_rate": 4.518669710111919e-06, "loss": 0.1069, "step": 485870 }, { "epoch": 2.888171621163757, "grad_norm": 3.6270458698272705, "learning_rate": 4.518463182067527e-06, "loss": 0.1021, "step": 485880 }, { "epoch": 2.8882310632404256, "grad_norm": 4.497274875640869, "learning_rate": 4.518256654852399e-06, "loss": 0.1007, "step": 485890 }, { "epoch": 2.8882905053170935, "grad_norm": 4.159172058105469, "learning_rate": 4.518050128466891e-06, "loss": 0.1007, "step": 485900 }, { "epoch": 2.8883499473937624, "grad_norm": 4.483720302581787, "learning_rate": 4.517843602911357e-06, "loss": 0.1097, "step": 485910 }, { "epoch": 2.8884093894704304, "grad_norm": 3.279721260070801, "learning_rate": 4.517637078186155e-06, "loss": 0.1111, "step": 485920 }, { "epoch": 2.8884688315470988, "grad_norm": 4.635118007659912, "learning_rate": 4.51743055429164e-06, "loss": 0.1035, "step": 485930 }, { "epoch": 2.888528273623767, "grad_norm": 2.812235116958618, "learning_rate": 4.517224031228166e-06, "loss": 0.1001, "step": 485940 }, { "epoch": 2.8885877157004356, "grad_norm": 3.403419256210327, "learning_rate": 4.517017508996089e-06, "loss": 0.0999, "step": 485950 }, { "epoch": 2.888647157777104, "grad_norm": 4.128116607666016, "learning_rate": 4.516810987595768e-06, "loss": 0.0982, "step": 485960 }, { "epoch": 2.8887065998537724, "grad_norm": 3.199918508529663, "learning_rate": 4.516604467027554e-06, "loss": 0.0995, "step": 485970 }, { "epoch": 2.888766041930441, "grad_norm": 3.660299777984619, "learning_rate": 4.516397947291805e-06, "loss": 0.0944, "step": 485980 }, { "epoch": 2.8888254840071093, "grad_norm": 3.5473411083221436, "learning_rate": 4.516191428388878e-06, "loss": 0.1138, "step": 485990 }, { "epoch": 2.8888849260837777, "grad_norm": 3.1268715858459473, "learning_rate": 4.515984910319126e-06, "loss": 0.0909, "step": 486000 }, { "epoch": 2.888944368160446, "grad_norm": 4.492022514343262, "learning_rate": 4.515778393082905e-06, "loss": 0.0927, "step": 486010 }, { "epoch": 2.8890038102371145, "grad_norm": 4.744694709777832, "learning_rate": 4.515571876680573e-06, "loss": 0.0996, "step": 486020 }, { "epoch": 2.889063252313783, "grad_norm": 5.206240177154541, "learning_rate": 4.5153653611124835e-06, "loss": 0.1138, "step": 486030 }, { "epoch": 2.8891226943904513, "grad_norm": 4.738826751708984, "learning_rate": 4.515158846378992e-06, "loss": 0.1141, "step": 486040 }, { "epoch": 2.8891821364671197, "grad_norm": 4.248927116394043, "learning_rate": 4.514952332480455e-06, "loss": 0.1175, "step": 486050 }, { "epoch": 2.889241578543788, "grad_norm": 4.52132511138916, "learning_rate": 4.514745819417226e-06, "loss": 0.0944, "step": 486060 }, { "epoch": 2.889301020620456, "grad_norm": 5.2891740798950195, "learning_rate": 4.514539307189665e-06, "loss": 0.102, "step": 486070 }, { "epoch": 2.889360462697125, "grad_norm": 3.3669283390045166, "learning_rate": 4.514332795798124e-06, "loss": 0.0925, "step": 486080 }, { "epoch": 2.889419904773793, "grad_norm": 4.702332496643066, "learning_rate": 4.514126285242962e-06, "loss": 0.1015, "step": 486090 }, { "epoch": 2.889479346850462, "grad_norm": 4.6772141456604, "learning_rate": 4.5139197755245314e-06, "loss": 0.0984, "step": 486100 }, { "epoch": 2.88953878892713, "grad_norm": 3.1134071350097656, "learning_rate": 4.513713266643188e-06, "loss": 0.0928, "step": 486110 }, { "epoch": 2.889598231003798, "grad_norm": 4.056644916534424, "learning_rate": 4.51350675859929e-06, "loss": 0.1174, "step": 486120 }, { "epoch": 2.8896576730804666, "grad_norm": 4.877168655395508, "learning_rate": 4.513300251393191e-06, "loss": 0.0987, "step": 486130 }, { "epoch": 2.889717115157135, "grad_norm": 3.813593864440918, "learning_rate": 4.513093745025246e-06, "loss": 0.0911, "step": 486140 }, { "epoch": 2.8897765572338034, "grad_norm": 3.3641974925994873, "learning_rate": 4.512887239495812e-06, "loss": 0.0979, "step": 486150 }, { "epoch": 2.889835999310472, "grad_norm": 2.7162277698516846, "learning_rate": 4.512680734805245e-06, "loss": 0.0879, "step": 486160 }, { "epoch": 2.8898954413871403, "grad_norm": 4.387521743774414, "learning_rate": 4.512474230953899e-06, "loss": 0.1056, "step": 486170 }, { "epoch": 2.8899548834638087, "grad_norm": 4.7181501388549805, "learning_rate": 4.512267727942131e-06, "loss": 0.1021, "step": 486180 }, { "epoch": 2.890014325540477, "grad_norm": 3.4863924980163574, "learning_rate": 4.5120612257702975e-06, "loss": 0.1047, "step": 486190 }, { "epoch": 2.8900737676171455, "grad_norm": 3.360816717147827, "learning_rate": 4.511854724438751e-06, "loss": 0.1025, "step": 486200 }, { "epoch": 2.890133209693814, "grad_norm": 3.971351146697998, "learning_rate": 4.51164822394785e-06, "loss": 0.112, "step": 486210 }, { "epoch": 2.8901926517704823, "grad_norm": 3.630734920501709, "learning_rate": 4.511441724297949e-06, "loss": 0.102, "step": 486220 }, { "epoch": 2.8902520938471508, "grad_norm": 3.385317087173462, "learning_rate": 4.511235225489402e-06, "loss": 0.1013, "step": 486230 }, { "epoch": 2.890311535923819, "grad_norm": 3.865236282348633, "learning_rate": 4.511028727522568e-06, "loss": 0.1029, "step": 486240 }, { "epoch": 2.8903709780004876, "grad_norm": 3.8311691284179688, "learning_rate": 4.5108222303978e-06, "loss": 0.1149, "step": 486250 }, { "epoch": 2.8904304200771556, "grad_norm": 4.406037330627441, "learning_rate": 4.510615734115455e-06, "loss": 0.1126, "step": 486260 }, { "epoch": 2.8904898621538244, "grad_norm": 4.858403205871582, "learning_rate": 4.510409238675888e-06, "loss": 0.1074, "step": 486270 }, { "epoch": 2.8905493042304924, "grad_norm": 4.242286205291748, "learning_rate": 4.510202744079453e-06, "loss": 0.1022, "step": 486280 }, { "epoch": 2.8906087463071612, "grad_norm": 3.405208110809326, "learning_rate": 4.509996250326509e-06, "loss": 0.103, "step": 486290 }, { "epoch": 2.890668188383829, "grad_norm": 4.791610240936279, "learning_rate": 4.509789757417411e-06, "loss": 0.0969, "step": 486300 }, { "epoch": 2.8907276304604976, "grad_norm": 2.4128642082214355, "learning_rate": 4.509583265352511e-06, "loss": 0.0989, "step": 486310 }, { "epoch": 2.890787072537166, "grad_norm": 3.8887460231781006, "learning_rate": 4.509376774132169e-06, "loss": 0.1016, "step": 486320 }, { "epoch": 2.8908465146138345, "grad_norm": 3.759761095046997, "learning_rate": 4.509170283756738e-06, "loss": 0.1083, "step": 486330 }, { "epoch": 2.890905956690503, "grad_norm": 3.8219430446624756, "learning_rate": 4.508963794226574e-06, "loss": 0.1009, "step": 486340 }, { "epoch": 2.8909653987671713, "grad_norm": 4.138752460479736, "learning_rate": 4.5087573055420345e-06, "loss": 0.1155, "step": 486350 }, { "epoch": 2.8910248408438397, "grad_norm": 4.268754482269287, "learning_rate": 4.508550817703473e-06, "loss": 0.0978, "step": 486360 }, { "epoch": 2.891084282920508, "grad_norm": 3.9946064949035645, "learning_rate": 4.508344330711244e-06, "loss": 0.1033, "step": 486370 }, { "epoch": 2.8911437249971765, "grad_norm": 4.749999046325684, "learning_rate": 4.508137844565707e-06, "loss": 0.0994, "step": 486380 }, { "epoch": 2.891203167073845, "grad_norm": 3.845366954803467, "learning_rate": 4.507931359267214e-06, "loss": 0.0864, "step": 486390 }, { "epoch": 2.8912626091505134, "grad_norm": 2.8545572757720947, "learning_rate": 4.507724874816122e-06, "loss": 0.1013, "step": 486400 }, { "epoch": 2.8913220512271818, "grad_norm": 4.2744460105896, "learning_rate": 4.5075183912127865e-06, "loss": 0.099, "step": 486410 }, { "epoch": 2.89138149330385, "grad_norm": 3.579350233078003, "learning_rate": 4.507311908457563e-06, "loss": 0.115, "step": 486420 }, { "epoch": 2.8914409353805186, "grad_norm": 3.362790584564209, "learning_rate": 4.507105426550807e-06, "loss": 0.1063, "step": 486430 }, { "epoch": 2.891500377457187, "grad_norm": 3.6814775466918945, "learning_rate": 4.506898945492875e-06, "loss": 0.0868, "step": 486440 }, { "epoch": 2.891559819533855, "grad_norm": 3.647278308868408, "learning_rate": 4.5066924652841225e-06, "loss": 0.0993, "step": 486450 }, { "epoch": 2.891619261610524, "grad_norm": 4.958314418792725, "learning_rate": 4.506485985924902e-06, "loss": 0.0987, "step": 486460 }, { "epoch": 2.891678703687192, "grad_norm": 3.8289477825164795, "learning_rate": 4.506279507415574e-06, "loss": 0.1126, "step": 486470 }, { "epoch": 2.8917381457638607, "grad_norm": 3.680654287338257, "learning_rate": 4.5060730297564905e-06, "loss": 0.1015, "step": 486480 }, { "epoch": 2.8917975878405286, "grad_norm": 3.799999713897705, "learning_rate": 4.505866552948008e-06, "loss": 0.0949, "step": 486490 }, { "epoch": 2.891857029917197, "grad_norm": 3.760495662689209, "learning_rate": 4.50566007699048e-06, "loss": 0.0964, "step": 486500 }, { "epoch": 2.8919164719938655, "grad_norm": 3.81192946434021, "learning_rate": 4.505453601884268e-06, "loss": 0.1028, "step": 486510 }, { "epoch": 2.891975914070534, "grad_norm": 6.0018439292907715, "learning_rate": 4.5052471276297224e-06, "loss": 0.1123, "step": 486520 }, { "epoch": 2.8920353561472023, "grad_norm": 2.69177508354187, "learning_rate": 4.5050406542272e-06, "loss": 0.1158, "step": 486530 }, { "epoch": 2.8920947982238707, "grad_norm": 3.34516978263855, "learning_rate": 4.504834181677058e-06, "loss": 0.1071, "step": 486540 }, { "epoch": 2.892154240300539, "grad_norm": 3.2213656902313232, "learning_rate": 4.50462770997965e-06, "loss": 0.104, "step": 486550 }, { "epoch": 2.8922136823772076, "grad_norm": 3.288254976272583, "learning_rate": 4.504421239135331e-06, "loss": 0.1035, "step": 486560 }, { "epoch": 2.892273124453876, "grad_norm": 3.364421844482422, "learning_rate": 4.5042147691444595e-06, "loss": 0.1013, "step": 486570 }, { "epoch": 2.8923325665305444, "grad_norm": 3.9304256439208984, "learning_rate": 4.504008300007389e-06, "loss": 0.0939, "step": 486580 }, { "epoch": 2.892392008607213, "grad_norm": 4.837167739868164, "learning_rate": 4.503801831724476e-06, "loss": 0.1044, "step": 486590 }, { "epoch": 2.892451450683881, "grad_norm": 5.763056755065918, "learning_rate": 4.503595364296074e-06, "loss": 0.1224, "step": 486600 }, { "epoch": 2.8925108927605496, "grad_norm": 3.577624797821045, "learning_rate": 4.50338889772254e-06, "loss": 0.1043, "step": 486610 }, { "epoch": 2.892570334837218, "grad_norm": 5.313592910766602, "learning_rate": 4.503182432004231e-06, "loss": 0.1065, "step": 486620 }, { "epoch": 2.8926297769138865, "grad_norm": 3.4972691535949707, "learning_rate": 4.5029759671415e-06, "loss": 0.0997, "step": 486630 }, { "epoch": 2.8926892189905544, "grad_norm": 4.327459812164307, "learning_rate": 4.502769503134703e-06, "loss": 0.0929, "step": 486640 }, { "epoch": 2.8927486610672233, "grad_norm": 2.852614164352417, "learning_rate": 4.502563039984198e-06, "loss": 0.1058, "step": 486650 }, { "epoch": 2.8928081031438913, "grad_norm": 3.336723566055298, "learning_rate": 4.502356577690338e-06, "loss": 0.109, "step": 486660 }, { "epoch": 2.8928675452205597, "grad_norm": 3.2419402599334717, "learning_rate": 4.5021501162534794e-06, "loss": 0.1185, "step": 486670 }, { "epoch": 2.892926987297228, "grad_norm": 4.469969749450684, "learning_rate": 4.501943655673978e-06, "loss": 0.1076, "step": 486680 }, { "epoch": 2.8929864293738965, "grad_norm": 3.8336102962493896, "learning_rate": 4.501737195952188e-06, "loss": 0.1078, "step": 486690 }, { "epoch": 2.893045871450565, "grad_norm": 4.372313022613525, "learning_rate": 4.501530737088467e-06, "loss": 0.1075, "step": 486700 }, { "epoch": 2.8931053135272333, "grad_norm": 3.978792667388916, "learning_rate": 4.501324279083169e-06, "loss": 0.1028, "step": 486710 }, { "epoch": 2.8931647556039017, "grad_norm": 4.226162910461426, "learning_rate": 4.501117821936648e-06, "loss": 0.1041, "step": 486720 }, { "epoch": 2.89322419768057, "grad_norm": 4.365133285522461, "learning_rate": 4.500911365649264e-06, "loss": 0.0823, "step": 486730 }, { "epoch": 2.8932836397572386, "grad_norm": 5.060274600982666, "learning_rate": 4.5007049102213706e-06, "loss": 0.121, "step": 486740 }, { "epoch": 2.893343081833907, "grad_norm": 5.447750568389893, "learning_rate": 4.500498455653323e-06, "loss": 0.0927, "step": 486750 }, { "epoch": 2.8934025239105754, "grad_norm": 3.9397692680358887, "learning_rate": 4.500292001945475e-06, "loss": 0.0909, "step": 486760 }, { "epoch": 2.893461965987244, "grad_norm": 3.3225958347320557, "learning_rate": 4.500085549098185e-06, "loss": 0.0961, "step": 486770 }, { "epoch": 2.8935214080639122, "grad_norm": 3.911226511001587, "learning_rate": 4.499879097111808e-06, "loss": 0.1083, "step": 486780 }, { "epoch": 2.8935808501405806, "grad_norm": 4.402884006500244, "learning_rate": 4.499672645986698e-06, "loss": 0.1075, "step": 486790 }, { "epoch": 2.893640292217249, "grad_norm": 3.202869176864624, "learning_rate": 4.499466195723211e-06, "loss": 0.1042, "step": 486800 }, { "epoch": 2.893699734293917, "grad_norm": 2.7667500972747803, "learning_rate": 4.4992597463217045e-06, "loss": 0.0994, "step": 486810 }, { "epoch": 2.893759176370586, "grad_norm": 5.73385763168335, "learning_rate": 4.49905329778253e-06, "loss": 0.1115, "step": 486820 }, { "epoch": 2.893818618447254, "grad_norm": 3.3778512477874756, "learning_rate": 4.498846850106047e-06, "loss": 0.1024, "step": 486830 }, { "epoch": 2.8938780605239227, "grad_norm": 4.11625862121582, "learning_rate": 4.49864040329261e-06, "loss": 0.0999, "step": 486840 }, { "epoch": 2.8939375026005907, "grad_norm": 4.571444988250732, "learning_rate": 4.4984339573425726e-06, "loss": 0.1072, "step": 486850 }, { "epoch": 2.893996944677259, "grad_norm": 3.6762750148773193, "learning_rate": 4.498227512256294e-06, "loss": 0.1145, "step": 486860 }, { "epoch": 2.8940563867539275, "grad_norm": 6.1347975730896, "learning_rate": 4.498021068034126e-06, "loss": 0.1065, "step": 486870 }, { "epoch": 2.894115828830596, "grad_norm": 2.949921131134033, "learning_rate": 4.4978146246764245e-06, "loss": 0.101, "step": 486880 }, { "epoch": 2.8941752709072643, "grad_norm": 4.901803016662598, "learning_rate": 4.497608182183548e-06, "loss": 0.0952, "step": 486890 }, { "epoch": 2.8942347129839328, "grad_norm": 4.049198627471924, "learning_rate": 4.4974017405558504e-06, "loss": 0.1118, "step": 486900 }, { "epoch": 2.894294155060601, "grad_norm": 3.8294081687927246, "learning_rate": 4.497195299793685e-06, "loss": 0.1014, "step": 486910 }, { "epoch": 2.8943535971372696, "grad_norm": 3.4386541843414307, "learning_rate": 4.496988859897411e-06, "loss": 0.095, "step": 486920 }, { "epoch": 2.894413039213938, "grad_norm": 2.804584503173828, "learning_rate": 4.496782420867381e-06, "loss": 0.0981, "step": 486930 }, { "epoch": 2.8944724812906064, "grad_norm": 7.065791606903076, "learning_rate": 4.496575982703951e-06, "loss": 0.1104, "step": 486940 }, { "epoch": 2.894531923367275, "grad_norm": 3.5705978870391846, "learning_rate": 4.496369545407479e-06, "loss": 0.1078, "step": 486950 }, { "epoch": 2.8945913654439432, "grad_norm": 4.325011730194092, "learning_rate": 4.496163108978318e-06, "loss": 0.0967, "step": 486960 }, { "epoch": 2.8946508075206117, "grad_norm": 3.334934711456299, "learning_rate": 4.495956673416825e-06, "loss": 0.0997, "step": 486970 }, { "epoch": 2.89471024959728, "grad_norm": 3.689495325088501, "learning_rate": 4.495750238723355e-06, "loss": 0.1038, "step": 486980 }, { "epoch": 2.8947696916739485, "grad_norm": 3.682612419128418, "learning_rate": 4.495543804898261e-06, "loss": 0.1015, "step": 486990 }, { "epoch": 2.8948291337506165, "grad_norm": 4.698536396026611, "learning_rate": 4.4953373719419024e-06, "loss": 0.1159, "step": 487000 }, { "epoch": 2.8948885758272853, "grad_norm": 4.03769063949585, "learning_rate": 4.4951309398546334e-06, "loss": 0.0987, "step": 487010 }, { "epoch": 2.8949480179039533, "grad_norm": 4.0676350593566895, "learning_rate": 4.494924508636808e-06, "loss": 0.0926, "step": 487020 }, { "epoch": 2.895007459980622, "grad_norm": 3.6286067962646484, "learning_rate": 4.494718078288784e-06, "loss": 0.0999, "step": 487030 }, { "epoch": 2.89506690205729, "grad_norm": 3.141899824142456, "learning_rate": 4.494511648810916e-06, "loss": 0.1073, "step": 487040 }, { "epoch": 2.8951263441339585, "grad_norm": 3.0327436923980713, "learning_rate": 4.4943052202035575e-06, "loss": 0.1075, "step": 487050 }, { "epoch": 2.895185786210627, "grad_norm": 2.7656335830688477, "learning_rate": 4.494098792467067e-06, "loss": 0.109, "step": 487060 }, { "epoch": 2.8952452282872954, "grad_norm": 3.8456881046295166, "learning_rate": 4.493892365601799e-06, "loss": 0.0958, "step": 487070 }, { "epoch": 2.8953046703639638, "grad_norm": 3.988334894180298, "learning_rate": 4.493685939608108e-06, "loss": 0.0973, "step": 487080 }, { "epoch": 2.895364112440632, "grad_norm": 3.6501128673553467, "learning_rate": 4.4934795144863505e-06, "loss": 0.098, "step": 487090 }, { "epoch": 2.8954235545173006, "grad_norm": 3.8031787872314453, "learning_rate": 4.493273090236882e-06, "loss": 0.0894, "step": 487100 }, { "epoch": 2.895482996593969, "grad_norm": 3.9936656951904297, "learning_rate": 4.493066666860057e-06, "loss": 0.1185, "step": 487110 }, { "epoch": 2.8955424386706374, "grad_norm": 3.731534004211426, "learning_rate": 4.492860244356232e-06, "loss": 0.0968, "step": 487120 }, { "epoch": 2.895601880747306, "grad_norm": 1.7364813089370728, "learning_rate": 4.492653822725763e-06, "loss": 0.1048, "step": 487130 }, { "epoch": 2.8956613228239743, "grad_norm": 5.334351062774658, "learning_rate": 4.492447401969003e-06, "loss": 0.1141, "step": 487140 }, { "epoch": 2.8957207649006427, "grad_norm": 4.186929702758789, "learning_rate": 4.492240982086311e-06, "loss": 0.1012, "step": 487150 }, { "epoch": 2.895780206977311, "grad_norm": 3.374380350112915, "learning_rate": 4.492034563078038e-06, "loss": 0.0886, "step": 487160 }, { "epoch": 2.8958396490539795, "grad_norm": 4.976779460906982, "learning_rate": 4.491828144944544e-06, "loss": 0.1188, "step": 487170 }, { "epoch": 2.895899091130648, "grad_norm": 4.149065017700195, "learning_rate": 4.4916217276861814e-06, "loss": 0.1009, "step": 487180 }, { "epoch": 2.895958533207316, "grad_norm": 4.22383975982666, "learning_rate": 4.491415311303308e-06, "loss": 0.0904, "step": 487190 }, { "epoch": 2.8960179752839847, "grad_norm": 4.107625961303711, "learning_rate": 4.491208895796279e-06, "loss": 0.1044, "step": 487200 }, { "epoch": 2.8960774173606527, "grad_norm": 4.799584865570068, "learning_rate": 4.4910024811654466e-06, "loss": 0.1077, "step": 487210 }, { "epoch": 2.8961368594373216, "grad_norm": 3.550097942352295, "learning_rate": 4.49079606741117e-06, "loss": 0.1121, "step": 487220 }, { "epoch": 2.8961963015139895, "grad_norm": 4.392142295837402, "learning_rate": 4.490589654533804e-06, "loss": 0.0959, "step": 487230 }, { "epoch": 2.896255743590658, "grad_norm": 4.58260440826416, "learning_rate": 4.490383242533702e-06, "loss": 0.0961, "step": 487240 }, { "epoch": 2.8963151856673264, "grad_norm": 3.8142595291137695, "learning_rate": 4.490176831411222e-06, "loss": 0.1107, "step": 487250 }, { "epoch": 2.896374627743995, "grad_norm": 4.1173200607299805, "learning_rate": 4.489970421166718e-06, "loss": 0.1168, "step": 487260 }, { "epoch": 2.896434069820663, "grad_norm": 3.3745367527008057, "learning_rate": 4.489764011800546e-06, "loss": 0.1015, "step": 487270 }, { "epoch": 2.8964935118973316, "grad_norm": 5.374632358551025, "learning_rate": 4.48955760331306e-06, "loss": 0.0936, "step": 487280 }, { "epoch": 2.896552953974, "grad_norm": 3.937011480331421, "learning_rate": 4.489351195704619e-06, "loss": 0.0975, "step": 487290 }, { "epoch": 2.8966123960506684, "grad_norm": 3.4439268112182617, "learning_rate": 4.489144788975575e-06, "loss": 0.0812, "step": 487300 }, { "epoch": 2.896671838127337, "grad_norm": 3.112417697906494, "learning_rate": 4.488938383126284e-06, "loss": 0.1074, "step": 487310 }, { "epoch": 2.8967312802040053, "grad_norm": 3.8560562133789062, "learning_rate": 4.488731978157102e-06, "loss": 0.1163, "step": 487320 }, { "epoch": 2.8967907222806737, "grad_norm": 5.965452671051025, "learning_rate": 4.488525574068385e-06, "loss": 0.0999, "step": 487330 }, { "epoch": 2.896850164357342, "grad_norm": 3.9920716285705566, "learning_rate": 4.488319170860488e-06, "loss": 0.1039, "step": 487340 }, { "epoch": 2.8969096064340105, "grad_norm": 4.043929100036621, "learning_rate": 4.488112768533766e-06, "loss": 0.1042, "step": 487350 }, { "epoch": 2.896969048510679, "grad_norm": 2.9587862491607666, "learning_rate": 4.4879063670885765e-06, "loss": 0.0816, "step": 487360 }, { "epoch": 2.8970284905873473, "grad_norm": 2.1307644844055176, "learning_rate": 4.487699966525271e-06, "loss": 0.1058, "step": 487370 }, { "epoch": 2.8970879326640153, "grad_norm": 3.1053709983825684, "learning_rate": 4.487493566844207e-06, "loss": 0.1054, "step": 487380 }, { "epoch": 2.897147374740684, "grad_norm": 5.119569778442383, "learning_rate": 4.487287168045742e-06, "loss": 0.1085, "step": 487390 }, { "epoch": 2.897206816817352, "grad_norm": 4.388657093048096, "learning_rate": 4.48708077013023e-06, "loss": 0.1013, "step": 487400 }, { "epoch": 2.8972662588940206, "grad_norm": 3.680842876434326, "learning_rate": 4.486874373098025e-06, "loss": 0.104, "step": 487410 }, { "epoch": 2.897325700970689, "grad_norm": 4.094616413116455, "learning_rate": 4.486667976949485e-06, "loss": 0.0978, "step": 487420 }, { "epoch": 2.8973851430473574, "grad_norm": 4.6702961921691895, "learning_rate": 4.486461581684962e-06, "loss": 0.0965, "step": 487430 }, { "epoch": 2.897444585124026, "grad_norm": 3.9022674560546875, "learning_rate": 4.486255187304814e-06, "loss": 0.1072, "step": 487440 }, { "epoch": 2.897504027200694, "grad_norm": 3.756723642349243, "learning_rate": 4.486048793809397e-06, "loss": 0.1011, "step": 487450 }, { "epoch": 2.8975634692773626, "grad_norm": 3.493945360183716, "learning_rate": 4.485842401199065e-06, "loss": 0.1063, "step": 487460 }, { "epoch": 2.897622911354031, "grad_norm": 3.809061050415039, "learning_rate": 4.485636009474173e-06, "loss": 0.0853, "step": 487470 }, { "epoch": 2.8976823534306995, "grad_norm": 4.053724765777588, "learning_rate": 4.485429618635077e-06, "loss": 0.0839, "step": 487480 }, { "epoch": 2.897741795507368, "grad_norm": 3.38360333442688, "learning_rate": 4.485223228682134e-06, "loss": 0.1164, "step": 487490 }, { "epoch": 2.8978012375840363, "grad_norm": 3.261992931365967, "learning_rate": 4.4850168396156964e-06, "loss": 0.0976, "step": 487500 }, { "epoch": 2.8978606796607047, "grad_norm": 4.875710964202881, "learning_rate": 4.484810451436123e-06, "loss": 0.0935, "step": 487510 }, { "epoch": 2.897920121737373, "grad_norm": 5.588395118713379, "learning_rate": 4.484604064143767e-06, "loss": 0.1175, "step": 487520 }, { "epoch": 2.8979795638140415, "grad_norm": 3.5923633575439453, "learning_rate": 4.484397677738983e-06, "loss": 0.0983, "step": 487530 }, { "epoch": 2.89803900589071, "grad_norm": 5.337133884429932, "learning_rate": 4.484191292222128e-06, "loss": 0.1071, "step": 487540 }, { "epoch": 2.898098447967378, "grad_norm": 3.4133894443511963, "learning_rate": 4.4839849075935585e-06, "loss": 0.0981, "step": 487550 }, { "epoch": 2.898157890044047, "grad_norm": 3.3297085762023926, "learning_rate": 4.4837785238536265e-06, "loss": 0.0956, "step": 487560 }, { "epoch": 2.8982173321207148, "grad_norm": 4.931723117828369, "learning_rate": 4.483572141002691e-06, "loss": 0.1009, "step": 487570 }, { "epoch": 2.8982767741973836, "grad_norm": 4.306403160095215, "learning_rate": 4.483365759041106e-06, "loss": 0.1102, "step": 487580 }, { "epoch": 2.8983362162740516, "grad_norm": 3.433723211288452, "learning_rate": 4.483159377969226e-06, "loss": 0.0956, "step": 487590 }, { "epoch": 2.89839565835072, "grad_norm": 2.768091917037964, "learning_rate": 4.482952997787407e-06, "loss": 0.1171, "step": 487600 }, { "epoch": 2.8984551004273884, "grad_norm": 3.3747241497039795, "learning_rate": 4.4827466184960045e-06, "loss": 0.0957, "step": 487610 }, { "epoch": 2.898514542504057, "grad_norm": 2.9994466304779053, "learning_rate": 4.482540240095375e-06, "loss": 0.1017, "step": 487620 }, { "epoch": 2.8985739845807252, "grad_norm": 5.621023654937744, "learning_rate": 4.482333862585873e-06, "loss": 0.1169, "step": 487630 }, { "epoch": 2.8986334266573937, "grad_norm": 4.0241594314575195, "learning_rate": 4.482127485967853e-06, "loss": 0.0986, "step": 487640 }, { "epoch": 2.898692868734062, "grad_norm": 4.840769290924072, "learning_rate": 4.481921110241672e-06, "loss": 0.1056, "step": 487650 }, { "epoch": 2.8987523108107305, "grad_norm": 3.0484843254089355, "learning_rate": 4.481714735407685e-06, "loss": 0.0995, "step": 487660 }, { "epoch": 2.898811752887399, "grad_norm": 5.158474445343018, "learning_rate": 4.481508361466245e-06, "loss": 0.1124, "step": 487670 }, { "epoch": 2.8988711949640673, "grad_norm": 2.724045515060425, "learning_rate": 4.481301988417712e-06, "loss": 0.1025, "step": 487680 }, { "epoch": 2.8989306370407357, "grad_norm": 4.339982986450195, "learning_rate": 4.481095616262438e-06, "loss": 0.1048, "step": 487690 }, { "epoch": 2.898990079117404, "grad_norm": 2.618255615234375, "learning_rate": 4.480889245000779e-06, "loss": 0.0968, "step": 487700 }, { "epoch": 2.8990495211940726, "grad_norm": 3.3527300357818604, "learning_rate": 4.480682874633091e-06, "loss": 0.1106, "step": 487710 }, { "epoch": 2.899108963270741, "grad_norm": 3.507213592529297, "learning_rate": 4.48047650515973e-06, "loss": 0.111, "step": 487720 }, { "epoch": 2.8991684053474094, "grad_norm": 3.9760513305664062, "learning_rate": 4.480270136581048e-06, "loss": 0.1051, "step": 487730 }, { "epoch": 2.8992278474240774, "grad_norm": 3.566204071044922, "learning_rate": 4.480063768897405e-06, "loss": 0.0901, "step": 487740 }, { "epoch": 2.899287289500746, "grad_norm": 4.919930934906006, "learning_rate": 4.479857402109153e-06, "loss": 0.1102, "step": 487750 }, { "epoch": 2.899346731577414, "grad_norm": 3.846909523010254, "learning_rate": 4.4796510362166485e-06, "loss": 0.1032, "step": 487760 }, { "epoch": 2.899406173654083, "grad_norm": 4.0412678718566895, "learning_rate": 4.479444671220248e-06, "loss": 0.1167, "step": 487770 }, { "epoch": 2.899465615730751, "grad_norm": 4.900057792663574, "learning_rate": 4.479238307120306e-06, "loss": 0.1056, "step": 487780 }, { "epoch": 2.8995250578074194, "grad_norm": 3.8931143283843994, "learning_rate": 4.479031943917177e-06, "loss": 0.1085, "step": 487790 }, { "epoch": 2.899584499884088, "grad_norm": 3.831789970397949, "learning_rate": 4.478825581611217e-06, "loss": 0.109, "step": 487800 }, { "epoch": 2.8996439419607563, "grad_norm": 4.535928726196289, "learning_rate": 4.478619220202783e-06, "loss": 0.0938, "step": 487810 }, { "epoch": 2.8997033840374247, "grad_norm": 4.285600662231445, "learning_rate": 4.478412859692225e-06, "loss": 0.1062, "step": 487820 }, { "epoch": 2.899762826114093, "grad_norm": 3.042792558670044, "learning_rate": 4.478206500079905e-06, "loss": 0.0908, "step": 487830 }, { "epoch": 2.8998222681907615, "grad_norm": 4.185956001281738, "learning_rate": 4.4780001413661754e-06, "loss": 0.1061, "step": 487840 }, { "epoch": 2.89988171026743, "grad_norm": 3.3847501277923584, "learning_rate": 4.477793783551393e-06, "loss": 0.0889, "step": 487850 }, { "epoch": 2.8999411523440983, "grad_norm": 5.450990676879883, "learning_rate": 4.47758742663591e-06, "loss": 0.0999, "step": 487860 }, { "epoch": 2.9000005944207667, "grad_norm": 3.3582828044891357, "learning_rate": 4.4773810706200856e-06, "loss": 0.1046, "step": 487870 }, { "epoch": 2.900060036497435, "grad_norm": 3.5054080486297607, "learning_rate": 4.4771747155042726e-06, "loss": 0.1021, "step": 487880 }, { "epoch": 2.9001194785741036, "grad_norm": 3.2171237468719482, "learning_rate": 4.476968361288827e-06, "loss": 0.1001, "step": 487890 }, { "epoch": 2.900178920650772, "grad_norm": 3.6602602005004883, "learning_rate": 4.476762007974105e-06, "loss": 0.1071, "step": 487900 }, { "epoch": 2.9002383627274404, "grad_norm": 4.234981060028076, "learning_rate": 4.476555655560461e-06, "loss": 0.0988, "step": 487910 }, { "epoch": 2.900297804804109, "grad_norm": 3.440931558609009, "learning_rate": 4.476349304048251e-06, "loss": 0.1005, "step": 487920 }, { "epoch": 2.900357246880777, "grad_norm": 3.722236156463623, "learning_rate": 4.4761429534378284e-06, "loss": 0.1019, "step": 487930 }, { "epoch": 2.9004166889574456, "grad_norm": 4.304406642913818, "learning_rate": 4.475936603729552e-06, "loss": 0.11, "step": 487940 }, { "epoch": 2.9004761310341136, "grad_norm": 3.3014166355133057, "learning_rate": 4.475730254923774e-06, "loss": 0.0928, "step": 487950 }, { "epoch": 2.9005355731107825, "grad_norm": 4.016124725341797, "learning_rate": 4.475523907020851e-06, "loss": 0.1124, "step": 487960 }, { "epoch": 2.9005950151874504, "grad_norm": 4.343491077423096, "learning_rate": 4.475317560021139e-06, "loss": 0.0897, "step": 487970 }, { "epoch": 2.900654457264119, "grad_norm": 4.998457431793213, "learning_rate": 4.475111213924993e-06, "loss": 0.1107, "step": 487980 }, { "epoch": 2.9007138993407873, "grad_norm": 4.076879501342773, "learning_rate": 4.474904868732767e-06, "loss": 0.1008, "step": 487990 }, { "epoch": 2.9007733414174557, "grad_norm": 3.591057300567627, "learning_rate": 4.474698524444819e-06, "loss": 0.0886, "step": 488000 }, { "epoch": 2.900832783494124, "grad_norm": 4.429750919342041, "learning_rate": 4.474492181061502e-06, "loss": 0.0955, "step": 488010 }, { "epoch": 2.9008922255707925, "grad_norm": 4.322207450866699, "learning_rate": 4.474285838583171e-06, "loss": 0.0964, "step": 488020 }, { "epoch": 2.900951667647461, "grad_norm": 3.398568868637085, "learning_rate": 4.4740794970101844e-06, "loss": 0.0987, "step": 488030 }, { "epoch": 2.9010111097241293, "grad_norm": 3.332963228225708, "learning_rate": 4.473873156342894e-06, "loss": 0.1059, "step": 488040 }, { "epoch": 2.9010705518007978, "grad_norm": 4.44729471206665, "learning_rate": 4.4736668165816575e-06, "loss": 0.111, "step": 488050 }, { "epoch": 2.901129993877466, "grad_norm": 4.44741678237915, "learning_rate": 4.47346047772683e-06, "loss": 0.1117, "step": 488060 }, { "epoch": 2.9011894359541346, "grad_norm": 4.44514799118042, "learning_rate": 4.473254139778766e-06, "loss": 0.1188, "step": 488070 }, { "epoch": 2.901248878030803, "grad_norm": 4.2107648849487305, "learning_rate": 4.473047802737822e-06, "loss": 0.1017, "step": 488080 }, { "epoch": 2.9013083201074714, "grad_norm": 5.571341037750244, "learning_rate": 4.472841466604351e-06, "loss": 0.1166, "step": 488090 }, { "epoch": 2.90136776218414, "grad_norm": 4.853302955627441, "learning_rate": 4.472635131378712e-06, "loss": 0.1144, "step": 488100 }, { "epoch": 2.9014272042608082, "grad_norm": 4.275893211364746, "learning_rate": 4.4724287970612565e-06, "loss": 0.109, "step": 488110 }, { "epoch": 2.901486646337476, "grad_norm": 3.9847753047943115, "learning_rate": 4.472222463652342e-06, "loss": 0.0962, "step": 488120 }, { "epoch": 2.901546088414145, "grad_norm": 3.71832013130188, "learning_rate": 4.4720161311523235e-06, "loss": 0.1123, "step": 488130 }, { "epoch": 2.901605530490813, "grad_norm": 4.892675399780273, "learning_rate": 4.471809799561557e-06, "loss": 0.1076, "step": 488140 }, { "epoch": 2.9016649725674815, "grad_norm": 3.0835485458374023, "learning_rate": 4.471603468880396e-06, "loss": 0.1044, "step": 488150 }, { "epoch": 2.90172441464415, "grad_norm": 4.7171502113342285, "learning_rate": 4.471397139109197e-06, "loss": 0.1058, "step": 488160 }, { "epoch": 2.9017838567208183, "grad_norm": 3.239405632019043, "learning_rate": 4.471190810248316e-06, "loss": 0.118, "step": 488170 }, { "epoch": 2.9018432987974867, "grad_norm": 4.410611152648926, "learning_rate": 4.470984482298106e-06, "loss": 0.106, "step": 488180 }, { "epoch": 2.901902740874155, "grad_norm": 4.427322864532471, "learning_rate": 4.470778155258925e-06, "loss": 0.1092, "step": 488190 }, { "epoch": 2.9019621829508235, "grad_norm": 3.0776240825653076, "learning_rate": 4.470571829131128e-06, "loss": 0.0991, "step": 488200 }, { "epoch": 2.902021625027492, "grad_norm": 4.322450160980225, "learning_rate": 4.470365503915067e-06, "loss": 0.1006, "step": 488210 }, { "epoch": 2.9020810671041604, "grad_norm": 3.8710358142852783, "learning_rate": 4.470159179611102e-06, "loss": 0.0947, "step": 488220 }, { "epoch": 2.9021405091808288, "grad_norm": 3.093435049057007, "learning_rate": 4.469952856219586e-06, "loss": 0.0921, "step": 488230 }, { "epoch": 2.902199951257497, "grad_norm": 4.241666793823242, "learning_rate": 4.469746533740873e-06, "loss": 0.1244, "step": 488240 }, { "epoch": 2.9022593933341656, "grad_norm": 3.3442177772521973, "learning_rate": 4.4695402121753205e-06, "loss": 0.0951, "step": 488250 }, { "epoch": 2.902318835410834, "grad_norm": 4.02431058883667, "learning_rate": 4.469333891523282e-06, "loss": 0.1026, "step": 488260 }, { "epoch": 2.9023782774875024, "grad_norm": 2.9070732593536377, "learning_rate": 4.469127571785114e-06, "loss": 0.094, "step": 488270 }, { "epoch": 2.902437719564171, "grad_norm": 3.6092424392700195, "learning_rate": 4.468921252961173e-06, "loss": 0.0993, "step": 488280 }, { "epoch": 2.902497161640839, "grad_norm": 4.041903018951416, "learning_rate": 4.468714935051812e-06, "loss": 0.1035, "step": 488290 }, { "epoch": 2.9025566037175077, "grad_norm": 4.806857585906982, "learning_rate": 4.468508618057388e-06, "loss": 0.0935, "step": 488300 }, { "epoch": 2.9026160457941756, "grad_norm": 3.3757293224334717, "learning_rate": 4.468302301978256e-06, "loss": 0.1032, "step": 488310 }, { "epoch": 2.9026754878708445, "grad_norm": 3.2948453426361084, "learning_rate": 4.4680959868147696e-06, "loss": 0.0842, "step": 488320 }, { "epoch": 2.9027349299475125, "grad_norm": 3.501816749572754, "learning_rate": 4.467889672567287e-06, "loss": 0.1024, "step": 488330 }, { "epoch": 2.902794372024181, "grad_norm": 3.8356986045837402, "learning_rate": 4.46768335923616e-06, "loss": 0.0984, "step": 488340 }, { "epoch": 2.9028538141008493, "grad_norm": 5.869733810424805, "learning_rate": 4.467477046821747e-06, "loss": 0.1048, "step": 488350 }, { "epoch": 2.9029132561775177, "grad_norm": 2.8188390731811523, "learning_rate": 4.467270735324402e-06, "loss": 0.0977, "step": 488360 }, { "epoch": 2.902972698254186, "grad_norm": 2.909494638442993, "learning_rate": 4.467064424744481e-06, "loss": 0.0908, "step": 488370 }, { "epoch": 2.9030321403308545, "grad_norm": 4.061644077301025, "learning_rate": 4.466858115082337e-06, "loss": 0.1171, "step": 488380 }, { "epoch": 2.903091582407523, "grad_norm": 3.4823198318481445, "learning_rate": 4.466651806338328e-06, "loss": 0.1145, "step": 488390 }, { "epoch": 2.9031510244841914, "grad_norm": 3.8212027549743652, "learning_rate": 4.466445498512808e-06, "loss": 0.0955, "step": 488400 }, { "epoch": 2.90321046656086, "grad_norm": 5.625539779663086, "learning_rate": 4.466239191606132e-06, "loss": 0.0996, "step": 488410 }, { "epoch": 2.903269908637528, "grad_norm": 5.414772987365723, "learning_rate": 4.466032885618657e-06, "loss": 0.0975, "step": 488420 }, { "epoch": 2.9033293507141966, "grad_norm": 4.1621222496032715, "learning_rate": 4.4658265805507365e-06, "loss": 0.0959, "step": 488430 }, { "epoch": 2.903388792790865, "grad_norm": 3.676408290863037, "learning_rate": 4.465620276402725e-06, "loss": 0.0986, "step": 488440 }, { "epoch": 2.9034482348675335, "grad_norm": 4.337520122528076, "learning_rate": 4.46541397317498e-06, "loss": 0.1029, "step": 488450 }, { "epoch": 2.903507676944202, "grad_norm": 4.2871270179748535, "learning_rate": 4.465207670867857e-06, "loss": 0.106, "step": 488460 }, { "epoch": 2.9035671190208703, "grad_norm": 4.389179229736328, "learning_rate": 4.465001369481709e-06, "loss": 0.088, "step": 488470 }, { "epoch": 2.9036265610975383, "grad_norm": 4.560174942016602, "learning_rate": 4.464795069016891e-06, "loss": 0.0945, "step": 488480 }, { "epoch": 2.903686003174207, "grad_norm": 4.052540302276611, "learning_rate": 4.464588769473762e-06, "loss": 0.1087, "step": 488490 }, { "epoch": 2.903745445250875, "grad_norm": 4.485495090484619, "learning_rate": 4.464382470852675e-06, "loss": 0.0918, "step": 488500 }, { "epoch": 2.903804887327544, "grad_norm": 3.1555893421173096, "learning_rate": 4.464176173153985e-06, "loss": 0.0989, "step": 488510 }, { "epoch": 2.903864329404212, "grad_norm": 4.095366954803467, "learning_rate": 4.463969876378047e-06, "loss": 0.1089, "step": 488520 }, { "epoch": 2.9039237714808803, "grad_norm": 4.89043664932251, "learning_rate": 4.463763580525218e-06, "loss": 0.0922, "step": 488530 }, { "epoch": 2.9039832135575487, "grad_norm": 4.769223213195801, "learning_rate": 4.463557285595851e-06, "loss": 0.0969, "step": 488540 }, { "epoch": 2.904042655634217, "grad_norm": 4.347667217254639, "learning_rate": 4.4633509915903025e-06, "loss": 0.113, "step": 488550 }, { "epoch": 2.9041020977108856, "grad_norm": 4.557063579559326, "learning_rate": 4.4631446985089286e-06, "loss": 0.1149, "step": 488560 }, { "epoch": 2.904161539787554, "grad_norm": 4.079803943634033, "learning_rate": 4.462938406352083e-06, "loss": 0.1097, "step": 488570 }, { "epoch": 2.9042209818642224, "grad_norm": 4.292788028717041, "learning_rate": 4.462732115120121e-06, "loss": 0.1109, "step": 488580 }, { "epoch": 2.904280423940891, "grad_norm": 3.5255417823791504, "learning_rate": 4.4625258248133995e-06, "loss": 0.0917, "step": 488590 }, { "epoch": 2.9043398660175592, "grad_norm": 3.6776816844940186, "learning_rate": 4.462319535432273e-06, "loss": 0.0915, "step": 488600 }, { "epoch": 2.9043993080942276, "grad_norm": 4.897851467132568, "learning_rate": 4.462113246977095e-06, "loss": 0.1012, "step": 488610 }, { "epoch": 2.904458750170896, "grad_norm": 4.849396228790283, "learning_rate": 4.461906959448223e-06, "loss": 0.102, "step": 488620 }, { "epoch": 2.9045181922475645, "grad_norm": 3.584118366241455, "learning_rate": 4.461700672846011e-06, "loss": 0.1073, "step": 488630 }, { "epoch": 2.904577634324233, "grad_norm": 4.12755012512207, "learning_rate": 4.461494387170814e-06, "loss": 0.0971, "step": 488640 }, { "epoch": 2.9046370764009013, "grad_norm": 3.6661376953125, "learning_rate": 4.461288102422989e-06, "loss": 0.1034, "step": 488650 }, { "epoch": 2.9046965184775697, "grad_norm": 2.8023180961608887, "learning_rate": 4.46108181860289e-06, "loss": 0.09, "step": 488660 }, { "epoch": 2.9047559605542377, "grad_norm": 3.5222856998443604, "learning_rate": 4.460875535710872e-06, "loss": 0.1037, "step": 488670 }, { "epoch": 2.9048154026309065, "grad_norm": 3.2038376331329346, "learning_rate": 4.46066925374729e-06, "loss": 0.1039, "step": 488680 }, { "epoch": 2.9048748447075745, "grad_norm": 3.9790101051330566, "learning_rate": 4.460462972712502e-06, "loss": 0.1083, "step": 488690 }, { "epoch": 2.9049342867842434, "grad_norm": 3.2710227966308594, "learning_rate": 4.460256692606858e-06, "loss": 0.0908, "step": 488700 }, { "epoch": 2.9049937288609113, "grad_norm": 4.16952657699585, "learning_rate": 4.460050413430717e-06, "loss": 0.1034, "step": 488710 }, { "epoch": 2.9050531709375798, "grad_norm": 4.279138088226318, "learning_rate": 4.459844135184436e-06, "loss": 0.0962, "step": 488720 }, { "epoch": 2.905112613014248, "grad_norm": 2.8954570293426514, "learning_rate": 4.459637857868367e-06, "loss": 0.0927, "step": 488730 }, { "epoch": 2.9051720550909166, "grad_norm": 4.4711809158325195, "learning_rate": 4.459431581482866e-06, "loss": 0.0935, "step": 488740 }, { "epoch": 2.905231497167585, "grad_norm": 5.50831937789917, "learning_rate": 4.459225306028288e-06, "loss": 0.1281, "step": 488750 }, { "epoch": 2.9052909392442534, "grad_norm": 3.5156469345092773, "learning_rate": 4.459019031504989e-06, "loss": 0.1134, "step": 488760 }, { "epoch": 2.905350381320922, "grad_norm": 3.2741243839263916, "learning_rate": 4.458812757913323e-06, "loss": 0.0911, "step": 488770 }, { "epoch": 2.9054098233975902, "grad_norm": 3.728782892227173, "learning_rate": 4.458606485253646e-06, "loss": 0.1046, "step": 488780 }, { "epoch": 2.9054692654742587, "grad_norm": 4.380501747131348, "learning_rate": 4.458400213526315e-06, "loss": 0.0925, "step": 488790 }, { "epoch": 2.905528707550927, "grad_norm": 4.148746490478516, "learning_rate": 4.458193942731681e-06, "loss": 0.1123, "step": 488800 }, { "epoch": 2.9055881496275955, "grad_norm": 3.3261899948120117, "learning_rate": 4.457987672870103e-06, "loss": 0.0939, "step": 488810 }, { "epoch": 2.905647591704264, "grad_norm": 4.023305416107178, "learning_rate": 4.457781403941936e-06, "loss": 0.105, "step": 488820 }, { "epoch": 2.9057070337809323, "grad_norm": 3.1877098083496094, "learning_rate": 4.457575135947531e-06, "loss": 0.0921, "step": 488830 }, { "epoch": 2.9057664758576003, "grad_norm": 3.305187225341797, "learning_rate": 4.457368868887249e-06, "loss": 0.1118, "step": 488840 }, { "epoch": 2.905825917934269, "grad_norm": 3.0878543853759766, "learning_rate": 4.457162602761442e-06, "loss": 0.1045, "step": 488850 }, { "epoch": 2.905885360010937, "grad_norm": 4.250781059265137, "learning_rate": 4.456956337570465e-06, "loss": 0.0996, "step": 488860 }, { "epoch": 2.905944802087606, "grad_norm": 2.9432482719421387, "learning_rate": 4.456750073314675e-06, "loss": 0.0897, "step": 488870 }, { "epoch": 2.906004244164274, "grad_norm": 3.875317335128784, "learning_rate": 4.4565438099944264e-06, "loss": 0.0981, "step": 488880 }, { "epoch": 2.9060636862409424, "grad_norm": 4.999629497528076, "learning_rate": 4.456337547610072e-06, "loss": 0.1089, "step": 488890 }, { "epoch": 2.9061231283176108, "grad_norm": 3.5217068195343018, "learning_rate": 4.456131286161972e-06, "loss": 0.0876, "step": 488900 }, { "epoch": 2.906182570394279, "grad_norm": 4.112290859222412, "learning_rate": 4.455925025650478e-06, "loss": 0.1195, "step": 488910 }, { "epoch": 2.9062420124709476, "grad_norm": 3.1163766384124756, "learning_rate": 4.455718766075943e-06, "loss": 0.1183, "step": 488920 }, { "epoch": 2.906301454547616, "grad_norm": 3.1406850814819336, "learning_rate": 4.455512507438728e-06, "loss": 0.0955, "step": 488930 }, { "epoch": 2.9063608966242844, "grad_norm": 3.866255283355713, "learning_rate": 4.455306249739185e-06, "loss": 0.1039, "step": 488940 }, { "epoch": 2.906420338700953, "grad_norm": 3.193760395050049, "learning_rate": 4.45509999297767e-06, "loss": 0.1112, "step": 488950 }, { "epoch": 2.9064797807776213, "grad_norm": 4.560399532318115, "learning_rate": 4.454893737154538e-06, "loss": 0.1257, "step": 488960 }, { "epoch": 2.9065392228542897, "grad_norm": 4.010921955108643, "learning_rate": 4.454687482270143e-06, "loss": 0.0999, "step": 488970 }, { "epoch": 2.906598664930958, "grad_norm": 4.315613746643066, "learning_rate": 4.454481228324843e-06, "loss": 0.1172, "step": 488980 }, { "epoch": 2.9066581070076265, "grad_norm": 3.9299771785736084, "learning_rate": 4.45427497531899e-06, "loss": 0.1028, "step": 488990 }, { "epoch": 2.906717549084295, "grad_norm": 3.747457265853882, "learning_rate": 4.4540687232529405e-06, "loss": 0.1134, "step": 489000 }, { "epoch": 2.9067769911609633, "grad_norm": 3.7743775844573975, "learning_rate": 4.453862472127051e-06, "loss": 0.0892, "step": 489010 }, { "epoch": 2.9068364332376317, "grad_norm": 4.868558406829834, "learning_rate": 4.453656221941674e-06, "loss": 0.0919, "step": 489020 }, { "epoch": 2.9068958753142997, "grad_norm": 4.73479700088501, "learning_rate": 4.4534499726971666e-06, "loss": 0.0951, "step": 489030 }, { "epoch": 2.9069553173909686, "grad_norm": 4.821232795715332, "learning_rate": 4.4532437243938845e-06, "loss": 0.1061, "step": 489040 }, { "epoch": 2.9070147594676365, "grad_norm": 3.5175955295562744, "learning_rate": 4.453037477032181e-06, "loss": 0.0917, "step": 489050 }, { "epoch": 2.9070742015443054, "grad_norm": 3.916149616241455, "learning_rate": 4.452831230612412e-06, "loss": 0.0982, "step": 489060 }, { "epoch": 2.9071336436209734, "grad_norm": 3.615016460418701, "learning_rate": 4.452624985134935e-06, "loss": 0.1049, "step": 489070 }, { "epoch": 2.907193085697642, "grad_norm": 3.131478786468506, "learning_rate": 4.452418740600101e-06, "loss": 0.1089, "step": 489080 }, { "epoch": 2.90725252777431, "grad_norm": 3.966569185256958, "learning_rate": 4.452212497008267e-06, "loss": 0.0878, "step": 489090 }, { "epoch": 2.9073119698509786, "grad_norm": 3.5719640254974365, "learning_rate": 4.45200625435979e-06, "loss": 0.1101, "step": 489100 }, { "epoch": 2.907371411927647, "grad_norm": 4.647253036499023, "learning_rate": 4.451800012655023e-06, "loss": 0.1207, "step": 489110 }, { "epoch": 2.9074308540043154, "grad_norm": 3.1370348930358887, "learning_rate": 4.451593771894321e-06, "loss": 0.0893, "step": 489120 }, { "epoch": 2.907490296080984, "grad_norm": 3.9815518856048584, "learning_rate": 4.451387532078042e-06, "loss": 0.0889, "step": 489130 }, { "epoch": 2.9075497381576523, "grad_norm": 4.299771308898926, "learning_rate": 4.451181293206535e-06, "loss": 0.0908, "step": 489140 }, { "epoch": 2.9076091802343207, "grad_norm": 3.6683292388916016, "learning_rate": 4.450975055280162e-06, "loss": 0.0944, "step": 489150 }, { "epoch": 2.907668622310989, "grad_norm": 2.7340126037597656, "learning_rate": 4.450768818299275e-06, "loss": 0.1262, "step": 489160 }, { "epoch": 2.9077280643876575, "grad_norm": 4.811659336090088, "learning_rate": 4.4505625822642305e-06, "loss": 0.1113, "step": 489170 }, { "epoch": 2.907787506464326, "grad_norm": 4.26657772064209, "learning_rate": 4.450356347175383e-06, "loss": 0.1026, "step": 489180 }, { "epoch": 2.9078469485409943, "grad_norm": 5.2719926834106445, "learning_rate": 4.450150113033086e-06, "loss": 0.1249, "step": 489190 }, { "epoch": 2.9079063906176628, "grad_norm": 4.66494083404541, "learning_rate": 4.449943879837698e-06, "loss": 0.1036, "step": 489200 }, { "epoch": 2.907965832694331, "grad_norm": 3.9385900497436523, "learning_rate": 4.449737647589571e-06, "loss": 0.0969, "step": 489210 }, { "epoch": 2.908025274770999, "grad_norm": 2.9323906898498535, "learning_rate": 4.449531416289061e-06, "loss": 0.1012, "step": 489220 }, { "epoch": 2.908084716847668, "grad_norm": 4.0037617683410645, "learning_rate": 4.449325185936525e-06, "loss": 0.1068, "step": 489230 }, { "epoch": 2.908144158924336, "grad_norm": 2.908104419708252, "learning_rate": 4.449118956532316e-06, "loss": 0.1025, "step": 489240 }, { "epoch": 2.908203601001005, "grad_norm": 2.810540199279785, "learning_rate": 4.448912728076791e-06, "loss": 0.0968, "step": 489250 }, { "epoch": 2.908263043077673, "grad_norm": 5.704996109008789, "learning_rate": 4.448706500570302e-06, "loss": 0.097, "step": 489260 }, { "epoch": 2.908322485154341, "grad_norm": 4.647945880889893, "learning_rate": 4.4485002740132076e-06, "loss": 0.1025, "step": 489270 }, { "epoch": 2.9083819272310096, "grad_norm": 3.422463893890381, "learning_rate": 4.448294048405862e-06, "loss": 0.1027, "step": 489280 }, { "epoch": 2.908441369307678, "grad_norm": 4.087106227874756, "learning_rate": 4.448087823748617e-06, "loss": 0.103, "step": 489290 }, { "epoch": 2.9085008113843465, "grad_norm": 3.5231761932373047, "learning_rate": 4.447881600041833e-06, "loss": 0.0972, "step": 489300 }, { "epoch": 2.908560253461015, "grad_norm": 3.1663177013397217, "learning_rate": 4.447675377285862e-06, "loss": 0.0975, "step": 489310 }, { "epoch": 2.9086196955376833, "grad_norm": 3.3068501949310303, "learning_rate": 4.44746915548106e-06, "loss": 0.1055, "step": 489320 }, { "epoch": 2.9086791376143517, "grad_norm": 5.137150764465332, "learning_rate": 4.447262934627783e-06, "loss": 0.1135, "step": 489330 }, { "epoch": 2.90873857969102, "grad_norm": 2.868058204650879, "learning_rate": 4.447056714726385e-06, "loss": 0.1154, "step": 489340 }, { "epoch": 2.9087980217676885, "grad_norm": 4.02106237411499, "learning_rate": 4.44685049577722e-06, "loss": 0.1057, "step": 489350 }, { "epoch": 2.908857463844357, "grad_norm": 4.292436122894287, "learning_rate": 4.446644277780643e-06, "loss": 0.127, "step": 489360 }, { "epoch": 2.9089169059210254, "grad_norm": 3.9289186000823975, "learning_rate": 4.446438060737013e-06, "loss": 0.1149, "step": 489370 }, { "epoch": 2.908976347997694, "grad_norm": 6.082160949707031, "learning_rate": 4.446231844646683e-06, "loss": 0.0998, "step": 489380 }, { "epoch": 2.909035790074362, "grad_norm": 2.8389077186584473, "learning_rate": 4.446025629510007e-06, "loss": 0.1142, "step": 489390 }, { "epoch": 2.9090952321510306, "grad_norm": 3.134739398956299, "learning_rate": 4.445819415327341e-06, "loss": 0.1033, "step": 489400 }, { "epoch": 2.9091546742276986, "grad_norm": 3.8659327030181885, "learning_rate": 4.4456132020990415e-06, "loss": 0.1039, "step": 489410 }, { "epoch": 2.9092141163043674, "grad_norm": 4.0385589599609375, "learning_rate": 4.4454069898254595e-06, "loss": 0.1158, "step": 489420 }, { "epoch": 2.9092735583810354, "grad_norm": 4.209219932556152, "learning_rate": 4.4452007785069554e-06, "loss": 0.1139, "step": 489430 }, { "epoch": 2.9093330004577043, "grad_norm": 4.062236785888672, "learning_rate": 4.444994568143881e-06, "loss": 0.104, "step": 489440 }, { "epoch": 2.9093924425343722, "grad_norm": 4.350265026092529, "learning_rate": 4.4447883587365905e-06, "loss": 0.0968, "step": 489450 }, { "epoch": 2.9094518846110407, "grad_norm": 3.165620803833008, "learning_rate": 4.444582150285443e-06, "loss": 0.1041, "step": 489460 }, { "epoch": 2.909511326687709, "grad_norm": 4.0502824783325195, "learning_rate": 4.44437594279079e-06, "loss": 0.1032, "step": 489470 }, { "epoch": 2.9095707687643775, "grad_norm": 4.380507469177246, "learning_rate": 4.4441697362529885e-06, "loss": 0.1023, "step": 489480 }, { "epoch": 2.909630210841046, "grad_norm": 4.054347991943359, "learning_rate": 4.443963530672393e-06, "loss": 0.0985, "step": 489490 }, { "epoch": 2.9096896529177143, "grad_norm": 3.1292519569396973, "learning_rate": 4.443757326049359e-06, "loss": 0.1005, "step": 489500 }, { "epoch": 2.9097490949943827, "grad_norm": 3.7321319580078125, "learning_rate": 4.44355112238424e-06, "loss": 0.1199, "step": 489510 }, { "epoch": 2.909808537071051, "grad_norm": 3.9029831886291504, "learning_rate": 4.443344919677394e-06, "loss": 0.0893, "step": 489520 }, { "epoch": 2.9098679791477196, "grad_norm": 3.565213680267334, "learning_rate": 4.443138717929174e-06, "loss": 0.0945, "step": 489530 }, { "epoch": 2.909927421224388, "grad_norm": 3.134580373764038, "learning_rate": 4.442932517139934e-06, "loss": 0.1195, "step": 489540 }, { "epoch": 2.9099868633010564, "grad_norm": 2.842362880706787, "learning_rate": 4.442726317310033e-06, "loss": 0.1185, "step": 489550 }, { "epoch": 2.910046305377725, "grad_norm": 3.76513409614563, "learning_rate": 4.4425201184398224e-06, "loss": 0.1004, "step": 489560 }, { "epoch": 2.910105747454393, "grad_norm": 3.388598680496216, "learning_rate": 4.4423139205296585e-06, "loss": 0.0874, "step": 489570 }, { "epoch": 2.910165189531061, "grad_norm": 4.563853740692139, "learning_rate": 4.442107723579896e-06, "loss": 0.121, "step": 489580 }, { "epoch": 2.91022463160773, "grad_norm": 4.799300670623779, "learning_rate": 4.441901527590891e-06, "loss": 0.097, "step": 489590 }, { "epoch": 2.910284073684398, "grad_norm": 4.494025707244873, "learning_rate": 4.441695332562999e-06, "loss": 0.108, "step": 489600 }, { "epoch": 2.910343515761067, "grad_norm": 3.887117862701416, "learning_rate": 4.441489138496574e-06, "loss": 0.087, "step": 489610 }, { "epoch": 2.910402957837735, "grad_norm": 3.9686827659606934, "learning_rate": 4.441282945391971e-06, "loss": 0.1106, "step": 489620 }, { "epoch": 2.9104623999144033, "grad_norm": 3.082840919494629, "learning_rate": 4.4410767532495465e-06, "loss": 0.0886, "step": 489630 }, { "epoch": 2.9105218419910717, "grad_norm": 5.066973686218262, "learning_rate": 4.440870562069654e-06, "loss": 0.1073, "step": 489640 }, { "epoch": 2.91058128406774, "grad_norm": 4.19071626663208, "learning_rate": 4.440664371852648e-06, "loss": 0.0971, "step": 489650 }, { "epoch": 2.9106407261444085, "grad_norm": 4.069750785827637, "learning_rate": 4.4404581825988856e-06, "loss": 0.0991, "step": 489660 }, { "epoch": 2.910700168221077, "grad_norm": 3.5861599445343018, "learning_rate": 4.440251994308722e-06, "loss": 0.1011, "step": 489670 }, { "epoch": 2.9107596102977453, "grad_norm": 2.6271467208862305, "learning_rate": 4.440045806982509e-06, "loss": 0.1088, "step": 489680 }, { "epoch": 2.9108190523744137, "grad_norm": 5.184016704559326, "learning_rate": 4.439839620620605e-06, "loss": 0.1003, "step": 489690 }, { "epoch": 2.910878494451082, "grad_norm": 5.564103126525879, "learning_rate": 4.439633435223365e-06, "loss": 0.1003, "step": 489700 }, { "epoch": 2.9109379365277506, "grad_norm": 4.832529067993164, "learning_rate": 4.439427250791142e-06, "loss": 0.1072, "step": 489710 }, { "epoch": 2.910997378604419, "grad_norm": 3.498422384262085, "learning_rate": 4.4392210673242926e-06, "loss": 0.0953, "step": 489720 }, { "epoch": 2.9110568206810874, "grad_norm": 4.497518062591553, "learning_rate": 4.439014884823172e-06, "loss": 0.1291, "step": 489730 }, { "epoch": 2.911116262757756, "grad_norm": 4.875765800476074, "learning_rate": 4.438808703288132e-06, "loss": 0.1137, "step": 489740 }, { "epoch": 2.9111757048344242, "grad_norm": 4.077045440673828, "learning_rate": 4.438602522719533e-06, "loss": 0.1037, "step": 489750 }, { "epoch": 2.9112351469110926, "grad_norm": 3.6833457946777344, "learning_rate": 4.438396343117727e-06, "loss": 0.1095, "step": 489760 }, { "epoch": 2.9112945889877606, "grad_norm": 4.663763523101807, "learning_rate": 4.438190164483068e-06, "loss": 0.1052, "step": 489770 }, { "epoch": 2.9113540310644295, "grad_norm": 3.032642364501953, "learning_rate": 4.437983986815915e-06, "loss": 0.1101, "step": 489780 }, { "epoch": 2.9114134731410974, "grad_norm": 5.111413478851318, "learning_rate": 4.43777781011662e-06, "loss": 0.1106, "step": 489790 }, { "epoch": 2.9114729152177663, "grad_norm": 4.440356731414795, "learning_rate": 4.437571634385536e-06, "loss": 0.0936, "step": 489800 }, { "epoch": 2.9115323572944343, "grad_norm": 4.816216945648193, "learning_rate": 4.437365459623023e-06, "loss": 0.091, "step": 489810 }, { "epoch": 2.9115917993711027, "grad_norm": 4.482118129730225, "learning_rate": 4.437159285829433e-06, "loss": 0.1055, "step": 489820 }, { "epoch": 2.911651241447771, "grad_norm": 4.976548194885254, "learning_rate": 4.436953113005123e-06, "loss": 0.0895, "step": 489830 }, { "epoch": 2.9117106835244395, "grad_norm": 3.7447638511657715, "learning_rate": 4.436746941150446e-06, "loss": 0.0949, "step": 489840 }, { "epoch": 2.911770125601108, "grad_norm": 3.770019054412842, "learning_rate": 4.436540770265759e-06, "loss": 0.0986, "step": 489850 }, { "epoch": 2.9118295676777763, "grad_norm": 4.574416160583496, "learning_rate": 4.436334600351416e-06, "loss": 0.0912, "step": 489860 }, { "epoch": 2.9118890097544448, "grad_norm": 4.057918071746826, "learning_rate": 4.436128431407771e-06, "loss": 0.1139, "step": 489870 }, { "epoch": 2.911948451831113, "grad_norm": 4.71612548828125, "learning_rate": 4.43592226343518e-06, "loss": 0.0938, "step": 489880 }, { "epoch": 2.9120078939077816, "grad_norm": 3.717710018157959, "learning_rate": 4.435716096434e-06, "loss": 0.1032, "step": 489890 }, { "epoch": 2.91206733598445, "grad_norm": 4.0050201416015625, "learning_rate": 4.435509930404582e-06, "loss": 0.1073, "step": 489900 }, { "epoch": 2.9121267780611184, "grad_norm": 5.105550765991211, "learning_rate": 4.435303765347285e-06, "loss": 0.1078, "step": 489910 }, { "epoch": 2.912186220137787, "grad_norm": 5.1217546463012695, "learning_rate": 4.435097601262462e-06, "loss": 0.1146, "step": 489920 }, { "epoch": 2.9122456622144552, "grad_norm": 3.7933850288391113, "learning_rate": 4.434891438150468e-06, "loss": 0.1159, "step": 489930 }, { "epoch": 2.9123051042911237, "grad_norm": 3.654193878173828, "learning_rate": 4.434685276011658e-06, "loss": 0.1012, "step": 489940 }, { "epoch": 2.912364546367792, "grad_norm": 3.7309865951538086, "learning_rate": 4.434479114846388e-06, "loss": 0.0927, "step": 489950 }, { "epoch": 2.91242398844446, "grad_norm": 3.9746127128601074, "learning_rate": 4.434272954655013e-06, "loss": 0.1224, "step": 489960 }, { "epoch": 2.912483430521129, "grad_norm": 4.240021705627441, "learning_rate": 4.434066795437886e-06, "loss": 0.111, "step": 489970 }, { "epoch": 2.912542872597797, "grad_norm": 2.568176507949829, "learning_rate": 4.433860637195364e-06, "loss": 0.0993, "step": 489980 }, { "epoch": 2.9126023146744657, "grad_norm": 3.2277815341949463, "learning_rate": 4.433654479927803e-06, "loss": 0.1003, "step": 489990 }, { "epoch": 2.9126617567511337, "grad_norm": 4.595446586608887, "learning_rate": 4.433448323635553e-06, "loss": 0.1056, "step": 490000 }, { "epoch": 2.912721198827802, "grad_norm": 3.920491933822632, "learning_rate": 4.4332421683189755e-06, "loss": 0.1077, "step": 490010 }, { "epoch": 2.9127806409044705, "grad_norm": 3.63496732711792, "learning_rate": 4.43303601397842e-06, "loss": 0.0969, "step": 490020 }, { "epoch": 2.912840082981139, "grad_norm": 4.04688024520874, "learning_rate": 4.432829860614248e-06, "loss": 0.1045, "step": 490030 }, { "epoch": 2.9128995250578074, "grad_norm": 5.598563194274902, "learning_rate": 4.432623708226807e-06, "loss": 0.106, "step": 490040 }, { "epoch": 2.9129589671344758, "grad_norm": 3.7348473072052, "learning_rate": 4.432417556816458e-06, "loss": 0.1001, "step": 490050 }, { "epoch": 2.913018409211144, "grad_norm": 4.331704616546631, "learning_rate": 4.432211406383553e-06, "loss": 0.1075, "step": 490060 }, { "epoch": 2.9130778512878126, "grad_norm": 4.668521404266357, "learning_rate": 4.432005256928447e-06, "loss": 0.092, "step": 490070 }, { "epoch": 2.913137293364481, "grad_norm": 5.87116003036499, "learning_rate": 4.431799108451498e-06, "loss": 0.1111, "step": 490080 }, { "epoch": 2.9131967354411494, "grad_norm": 3.9354870319366455, "learning_rate": 4.431592960953057e-06, "loss": 0.0939, "step": 490090 }, { "epoch": 2.913256177517818, "grad_norm": 3.2037441730499268, "learning_rate": 4.4313868144334796e-06, "loss": 0.1097, "step": 490100 }, { "epoch": 2.9133156195944863, "grad_norm": 4.563952445983887, "learning_rate": 4.431180668893124e-06, "loss": 0.0937, "step": 490110 }, { "epoch": 2.9133750616711547, "grad_norm": 3.543245792388916, "learning_rate": 4.4309745243323435e-06, "loss": 0.0916, "step": 490120 }, { "epoch": 2.913434503747823, "grad_norm": 4.116685390472412, "learning_rate": 4.43076838075149e-06, "loss": 0.097, "step": 490130 }, { "epoch": 2.9134939458244915, "grad_norm": 4.436371803283691, "learning_rate": 4.4305622381509235e-06, "loss": 0.0999, "step": 490140 }, { "epoch": 2.9135533879011595, "grad_norm": 4.339637279510498, "learning_rate": 4.430356096530997e-06, "loss": 0.1157, "step": 490150 }, { "epoch": 2.9136128299778283, "grad_norm": 4.255131721496582, "learning_rate": 4.430149955892064e-06, "loss": 0.0936, "step": 490160 }, { "epoch": 2.9136722720544963, "grad_norm": 3.0732569694519043, "learning_rate": 4.429943816234482e-06, "loss": 0.1097, "step": 490170 }, { "epoch": 2.913731714131165, "grad_norm": 2.801754951477051, "learning_rate": 4.429737677558604e-06, "loss": 0.0947, "step": 490180 }, { "epoch": 2.913791156207833, "grad_norm": 4.453291416168213, "learning_rate": 4.429531539864786e-06, "loss": 0.0932, "step": 490190 }, { "epoch": 2.9138505982845015, "grad_norm": 4.712937355041504, "learning_rate": 4.4293254031533824e-06, "loss": 0.1041, "step": 490200 }, { "epoch": 2.91391004036117, "grad_norm": 3.2125256061553955, "learning_rate": 4.429119267424749e-06, "loss": 0.0977, "step": 490210 }, { "epoch": 2.9139694824378384, "grad_norm": 4.170503616333008, "learning_rate": 4.42891313267924e-06, "loss": 0.0884, "step": 490220 }, { "epoch": 2.914028924514507, "grad_norm": 3.399873971939087, "learning_rate": 4.42870699891721e-06, "loss": 0.1115, "step": 490230 }, { "epoch": 2.914088366591175, "grad_norm": 5.007311820983887, "learning_rate": 4.428500866139015e-06, "loss": 0.0975, "step": 490240 }, { "epoch": 2.9141478086678436, "grad_norm": 3.2518866062164307, "learning_rate": 4.42829473434501e-06, "loss": 0.118, "step": 490250 }, { "epoch": 2.914207250744512, "grad_norm": 2.9703433513641357, "learning_rate": 4.42808860353555e-06, "loss": 0.0825, "step": 490260 }, { "epoch": 2.9142666928211804, "grad_norm": 4.58085823059082, "learning_rate": 4.427882473710989e-06, "loss": 0.1051, "step": 490270 }, { "epoch": 2.914326134897849, "grad_norm": 3.9367246627807617, "learning_rate": 4.427676344871684e-06, "loss": 0.1016, "step": 490280 }, { "epoch": 2.9143855769745173, "grad_norm": 5.105222702026367, "learning_rate": 4.427470217017988e-06, "loss": 0.099, "step": 490290 }, { "epoch": 2.9144450190511857, "grad_norm": 3.3884530067443848, "learning_rate": 4.427264090150256e-06, "loss": 0.1155, "step": 490300 }, { "epoch": 2.914504461127854, "grad_norm": 3.8987839221954346, "learning_rate": 4.427057964268845e-06, "loss": 0.0935, "step": 490310 }, { "epoch": 2.914563903204522, "grad_norm": 3.815113067626953, "learning_rate": 4.426851839374108e-06, "loss": 0.1113, "step": 490320 }, { "epoch": 2.914623345281191, "grad_norm": 4.412670612335205, "learning_rate": 4.426645715466398e-06, "loss": 0.0892, "step": 490330 }, { "epoch": 2.914682787357859, "grad_norm": 4.408903121948242, "learning_rate": 4.4264395925460755e-06, "loss": 0.1106, "step": 490340 }, { "epoch": 2.9147422294345278, "grad_norm": 3.8453328609466553, "learning_rate": 4.426233470613492e-06, "loss": 0.1033, "step": 490350 }, { "epoch": 2.9148016715111957, "grad_norm": 3.1127095222473145, "learning_rate": 4.4260273496690015e-06, "loss": 0.0918, "step": 490360 }, { "epoch": 2.914861113587864, "grad_norm": 3.022836923599243, "learning_rate": 4.425821229712962e-06, "loss": 0.0937, "step": 490370 }, { "epoch": 2.9149205556645326, "grad_norm": 4.289090633392334, "learning_rate": 4.4256151107457265e-06, "loss": 0.1151, "step": 490380 }, { "epoch": 2.914979997741201, "grad_norm": 4.5886359214782715, "learning_rate": 4.4254089927676495e-06, "loss": 0.1057, "step": 490390 }, { "epoch": 2.9150394398178694, "grad_norm": 3.541504383087158, "learning_rate": 4.425202875779087e-06, "loss": 0.1222, "step": 490400 }, { "epoch": 2.915098881894538, "grad_norm": 3.7412827014923096, "learning_rate": 4.424996759780395e-06, "loss": 0.099, "step": 490410 }, { "epoch": 2.9151583239712062, "grad_norm": 3.0880112648010254, "learning_rate": 4.424790644771926e-06, "loss": 0.0983, "step": 490420 }, { "epoch": 2.9152177660478746, "grad_norm": 3.666300058364868, "learning_rate": 4.424584530754037e-06, "loss": 0.1077, "step": 490430 }, { "epoch": 2.915277208124543, "grad_norm": 4.010594844818115, "learning_rate": 4.424378417727081e-06, "loss": 0.1088, "step": 490440 }, { "epoch": 2.9153366502012115, "grad_norm": 3.681047201156616, "learning_rate": 4.424172305691414e-06, "loss": 0.0977, "step": 490450 }, { "epoch": 2.91539609227788, "grad_norm": 4.019844055175781, "learning_rate": 4.423966194647389e-06, "loss": 0.1081, "step": 490460 }, { "epoch": 2.9154555343545483, "grad_norm": 3.757418155670166, "learning_rate": 4.423760084595366e-06, "loss": 0.0895, "step": 490470 }, { "epoch": 2.9155149764312167, "grad_norm": 3.9709205627441406, "learning_rate": 4.423553975535697e-06, "loss": 0.1049, "step": 490480 }, { "epoch": 2.915574418507885, "grad_norm": 3.703125238418579, "learning_rate": 4.423347867468735e-06, "loss": 0.0936, "step": 490490 }, { "epoch": 2.9156338605845535, "grad_norm": 3.658473014831543, "learning_rate": 4.423141760394839e-06, "loss": 0.0937, "step": 490500 }, { "epoch": 2.9156933026612215, "grad_norm": 3.7972214221954346, "learning_rate": 4.422935654314361e-06, "loss": 0.0967, "step": 490510 }, { "epoch": 2.9157527447378904, "grad_norm": 2.9249305725097656, "learning_rate": 4.422729549227656e-06, "loss": 0.1136, "step": 490520 }, { "epoch": 2.9158121868145583, "grad_norm": 4.094358444213867, "learning_rate": 4.4225234451350796e-06, "loss": 0.0994, "step": 490530 }, { "epoch": 2.915871628891227, "grad_norm": 4.071049213409424, "learning_rate": 4.422317342036988e-06, "loss": 0.1172, "step": 490540 }, { "epoch": 2.915931070967895, "grad_norm": 3.2367475032806396, "learning_rate": 4.422111239933733e-06, "loss": 0.0898, "step": 490550 }, { "epoch": 2.9159905130445636, "grad_norm": 5.25339937210083, "learning_rate": 4.421905138825672e-06, "loss": 0.0959, "step": 490560 }, { "epoch": 2.916049955121232, "grad_norm": 4.418443202972412, "learning_rate": 4.421699038713161e-06, "loss": 0.1095, "step": 490570 }, { "epoch": 2.9161093971979004, "grad_norm": 3.0098679065704346, "learning_rate": 4.421492939596551e-06, "loss": 0.1125, "step": 490580 }, { "epoch": 2.916168839274569, "grad_norm": 4.8160600662231445, "learning_rate": 4.4212868414762e-06, "loss": 0.1134, "step": 490590 }, { "epoch": 2.9162282813512372, "grad_norm": 3.8987603187561035, "learning_rate": 4.421080744352463e-06, "loss": 0.0945, "step": 490600 }, { "epoch": 2.9162877234279057, "grad_norm": 3.565474510192871, "learning_rate": 4.4208746482256935e-06, "loss": 0.0849, "step": 490610 }, { "epoch": 2.916347165504574, "grad_norm": 3.5614845752716064, "learning_rate": 4.4206685530962454e-06, "loss": 0.0989, "step": 490620 }, { "epoch": 2.9164066075812425, "grad_norm": 6.636645317077637, "learning_rate": 4.420462458964478e-06, "loss": 0.1165, "step": 490630 }, { "epoch": 2.916466049657911, "grad_norm": 3.365992546081543, "learning_rate": 4.420256365830741e-06, "loss": 0.0992, "step": 490640 }, { "epoch": 2.9165254917345793, "grad_norm": 5.472869873046875, "learning_rate": 4.420050273695392e-06, "loss": 0.1047, "step": 490650 }, { "epoch": 2.9165849338112477, "grad_norm": 3.222851276397705, "learning_rate": 4.419844182558787e-06, "loss": 0.0976, "step": 490660 }, { "epoch": 2.916644375887916, "grad_norm": 4.613945484161377, "learning_rate": 4.419638092421279e-06, "loss": 0.1081, "step": 490670 }, { "epoch": 2.9167038179645846, "grad_norm": 4.05195426940918, "learning_rate": 4.419432003283221e-06, "loss": 0.0857, "step": 490680 }, { "epoch": 2.916763260041253, "grad_norm": 6.99325704574585, "learning_rate": 4.4192259151449714e-06, "loss": 0.1141, "step": 490690 }, { "epoch": 2.916822702117921, "grad_norm": 4.610815525054932, "learning_rate": 4.419019828006886e-06, "loss": 0.1036, "step": 490700 }, { "epoch": 2.91688214419459, "grad_norm": 4.3141889572143555, "learning_rate": 4.418813741869318e-06, "loss": 0.0985, "step": 490710 }, { "epoch": 2.9169415862712578, "grad_norm": 4.89065408706665, "learning_rate": 4.418607656732619e-06, "loss": 0.0893, "step": 490720 }, { "epoch": 2.9170010283479266, "grad_norm": 4.066478729248047, "learning_rate": 4.41840157259715e-06, "loss": 0.1257, "step": 490730 }, { "epoch": 2.9170604704245946, "grad_norm": 5.31968879699707, "learning_rate": 4.418195489463263e-06, "loss": 0.1049, "step": 490740 }, { "epoch": 2.917119912501263, "grad_norm": 4.786845684051514, "learning_rate": 4.41798940733131e-06, "loss": 0.0987, "step": 490750 }, { "epoch": 2.9171793545779314, "grad_norm": 3.7695813179016113, "learning_rate": 4.417783326201652e-06, "loss": 0.0973, "step": 490760 }, { "epoch": 2.9172387966546, "grad_norm": 5.453239440917969, "learning_rate": 4.417577246074639e-06, "loss": 0.1118, "step": 490770 }, { "epoch": 2.9172982387312683, "grad_norm": 3.3496201038360596, "learning_rate": 4.417371166950627e-06, "loss": 0.098, "step": 490780 }, { "epoch": 2.9173576808079367, "grad_norm": 3.1924233436584473, "learning_rate": 4.417165088829971e-06, "loss": 0.0976, "step": 490790 }, { "epoch": 2.917417122884605, "grad_norm": 4.185849666595459, "learning_rate": 4.416959011713029e-06, "loss": 0.1054, "step": 490800 }, { "epoch": 2.9174765649612735, "grad_norm": 3.8496196269989014, "learning_rate": 4.41675293560015e-06, "loss": 0.0974, "step": 490810 }, { "epoch": 2.917536007037942, "grad_norm": 4.687071323394775, "learning_rate": 4.4165468604916934e-06, "loss": 0.0905, "step": 490820 }, { "epoch": 2.9175954491146103, "grad_norm": 3.383413553237915, "learning_rate": 4.416340786388013e-06, "loss": 0.1003, "step": 490830 }, { "epoch": 2.9176548911912787, "grad_norm": 5.299700736999512, "learning_rate": 4.4161347132894625e-06, "loss": 0.0977, "step": 490840 }, { "epoch": 2.917714333267947, "grad_norm": 3.7342653274536133, "learning_rate": 4.4159286411963985e-06, "loss": 0.1009, "step": 490850 }, { "epoch": 2.9177737753446156, "grad_norm": 4.660590648651123, "learning_rate": 4.415722570109175e-06, "loss": 0.1074, "step": 490860 }, { "epoch": 2.917833217421284, "grad_norm": 3.5608456134796143, "learning_rate": 4.4155165000281465e-06, "loss": 0.0954, "step": 490870 }, { "epoch": 2.9178926594979524, "grad_norm": 3.9276328086853027, "learning_rate": 4.415310430953669e-06, "loss": 0.1046, "step": 490880 }, { "epoch": 2.9179521015746204, "grad_norm": 4.425884246826172, "learning_rate": 4.415104362886096e-06, "loss": 0.0899, "step": 490890 }, { "epoch": 2.9180115436512892, "grad_norm": 3.031172513961792, "learning_rate": 4.414898295825782e-06, "loss": 0.1063, "step": 490900 }, { "epoch": 2.918070985727957, "grad_norm": 3.5739550590515137, "learning_rate": 4.414692229773084e-06, "loss": 0.0968, "step": 490910 }, { "epoch": 2.918130427804626, "grad_norm": 3.065948009490967, "learning_rate": 4.414486164728356e-06, "loss": 0.1046, "step": 490920 }, { "epoch": 2.918189869881294, "grad_norm": 3.713542938232422, "learning_rate": 4.414280100691953e-06, "loss": 0.1032, "step": 490930 }, { "epoch": 2.9182493119579624, "grad_norm": 4.131746292114258, "learning_rate": 4.41407403766423e-06, "loss": 0.1123, "step": 490940 }, { "epoch": 2.918308754034631, "grad_norm": 3.750155210494995, "learning_rate": 4.41386797564554e-06, "loss": 0.0875, "step": 490950 }, { "epoch": 2.9183681961112993, "grad_norm": 3.729814052581787, "learning_rate": 4.413661914636241e-06, "loss": 0.102, "step": 490960 }, { "epoch": 2.9184276381879677, "grad_norm": 3.325407028198242, "learning_rate": 4.4134558546366845e-06, "loss": 0.1224, "step": 490970 }, { "epoch": 2.918487080264636, "grad_norm": 5.206515312194824, "learning_rate": 4.413249795647227e-06, "loss": 0.0993, "step": 490980 }, { "epoch": 2.9185465223413045, "grad_norm": 3.916813611984253, "learning_rate": 4.413043737668225e-06, "loss": 0.1065, "step": 490990 }, { "epoch": 2.918605964417973, "grad_norm": 3.824688673019409, "learning_rate": 4.41283768070003e-06, "loss": 0.088, "step": 491000 }, { "epoch": 2.9186654064946413, "grad_norm": 6.122596740722656, "learning_rate": 4.412631624743e-06, "loss": 0.1061, "step": 491010 }, { "epoch": 2.9187248485713098, "grad_norm": 2.8805980682373047, "learning_rate": 4.412425569797488e-06, "loss": 0.1008, "step": 491020 }, { "epoch": 2.918784290647978, "grad_norm": 3.3094112873077393, "learning_rate": 4.4122195158638496e-06, "loss": 0.1155, "step": 491030 }, { "epoch": 2.9188437327246466, "grad_norm": 3.396043062210083, "learning_rate": 4.412013462942437e-06, "loss": 0.0889, "step": 491040 }, { "epoch": 2.918903174801315, "grad_norm": 3.798668622970581, "learning_rate": 4.41180741103361e-06, "loss": 0.0976, "step": 491050 }, { "epoch": 2.918962616877983, "grad_norm": 3.924330711364746, "learning_rate": 4.411601360137721e-06, "loss": 0.1054, "step": 491060 }, { "epoch": 2.919022058954652, "grad_norm": 4.144152641296387, "learning_rate": 4.411395310255122e-06, "loss": 0.1188, "step": 491070 }, { "epoch": 2.91908150103132, "grad_norm": 2.9069557189941406, "learning_rate": 4.411189261386173e-06, "loss": 0.0974, "step": 491080 }, { "epoch": 2.9191409431079887, "grad_norm": 5.126965522766113, "learning_rate": 4.410983213531226e-06, "loss": 0.0998, "step": 491090 }, { "epoch": 2.9192003851846566, "grad_norm": 3.5541045665740967, "learning_rate": 4.410777166690635e-06, "loss": 0.0895, "step": 491100 }, { "epoch": 2.919259827261325, "grad_norm": 2.7708792686462402, "learning_rate": 4.410571120864756e-06, "loss": 0.1077, "step": 491110 }, { "epoch": 2.9193192693379935, "grad_norm": 4.286073684692383, "learning_rate": 4.410365076053943e-06, "loss": 0.1054, "step": 491120 }, { "epoch": 2.919378711414662, "grad_norm": 3.9652888774871826, "learning_rate": 4.4101590322585545e-06, "loss": 0.0868, "step": 491130 }, { "epoch": 2.9194381534913303, "grad_norm": 3.1160314083099365, "learning_rate": 4.40995298947894e-06, "loss": 0.0961, "step": 491140 }, { "epoch": 2.9194975955679987, "grad_norm": 3.619476556777954, "learning_rate": 4.409746947715459e-06, "loss": 0.1094, "step": 491150 }, { "epoch": 2.919557037644667, "grad_norm": 3.573762893676758, "learning_rate": 4.409540906968463e-06, "loss": 0.0974, "step": 491160 }, { "epoch": 2.9196164797213355, "grad_norm": 3.1283302307128906, "learning_rate": 4.409334867238308e-06, "loss": 0.0937, "step": 491170 }, { "epoch": 2.919675921798004, "grad_norm": 3.1707763671875, "learning_rate": 4.409128828525349e-06, "loss": 0.1016, "step": 491180 }, { "epoch": 2.9197353638746724, "grad_norm": 4.588780403137207, "learning_rate": 4.408922790829942e-06, "loss": 0.0968, "step": 491190 }, { "epoch": 2.9197948059513408, "grad_norm": 3.6533098220825195, "learning_rate": 4.408716754152438e-06, "loss": 0.0964, "step": 491200 }, { "epoch": 2.919854248028009, "grad_norm": 4.063662052154541, "learning_rate": 4.408510718493196e-06, "loss": 0.096, "step": 491210 }, { "epoch": 2.9199136901046776, "grad_norm": 4.390064716339111, "learning_rate": 4.408304683852569e-06, "loss": 0.1124, "step": 491220 }, { "epoch": 2.919973132181346, "grad_norm": 2.474472761154175, "learning_rate": 4.408098650230911e-06, "loss": 0.1114, "step": 491230 }, { "epoch": 2.9200325742580144, "grad_norm": 4.8509721755981445, "learning_rate": 4.407892617628579e-06, "loss": 0.1109, "step": 491240 }, { "epoch": 2.9200920163346824, "grad_norm": 4.100446701049805, "learning_rate": 4.4076865860459266e-06, "loss": 0.1035, "step": 491250 }, { "epoch": 2.9201514584113513, "grad_norm": 4.087184429168701, "learning_rate": 4.407480555483308e-06, "loss": 0.1026, "step": 491260 }, { "epoch": 2.9202109004880192, "grad_norm": 3.9947328567504883, "learning_rate": 4.407274525941077e-06, "loss": 0.1012, "step": 491270 }, { "epoch": 2.920270342564688, "grad_norm": 3.9846348762512207, "learning_rate": 4.407068497419592e-06, "loss": 0.0997, "step": 491280 }, { "epoch": 2.920329784641356, "grad_norm": 4.139547348022461, "learning_rate": 4.406862469919206e-06, "loss": 0.1027, "step": 491290 }, { "epoch": 2.9203892267180245, "grad_norm": 4.004457950592041, "learning_rate": 4.406656443440273e-06, "loss": 0.1007, "step": 491300 }, { "epoch": 2.920448668794693, "grad_norm": 3.4505703449249268, "learning_rate": 4.406450417983148e-06, "loss": 0.1021, "step": 491310 }, { "epoch": 2.9205081108713613, "grad_norm": 3.6239559650421143, "learning_rate": 4.406244393548187e-06, "loss": 0.1024, "step": 491320 }, { "epoch": 2.9205675529480297, "grad_norm": 3.7914159297943115, "learning_rate": 4.406038370135743e-06, "loss": 0.1081, "step": 491330 }, { "epoch": 2.920626995024698, "grad_norm": 5.2828593254089355, "learning_rate": 4.40583234774617e-06, "loss": 0.112, "step": 491340 }, { "epoch": 2.9206864371013666, "grad_norm": 3.9733924865722656, "learning_rate": 4.405626326379828e-06, "loss": 0.108, "step": 491350 }, { "epoch": 2.920745879178035, "grad_norm": 2.934218406677246, "learning_rate": 4.405420306037067e-06, "loss": 0.0946, "step": 491360 }, { "epoch": 2.9208053212547034, "grad_norm": 2.784336805343628, "learning_rate": 4.4052142867182426e-06, "loss": 0.0925, "step": 491370 }, { "epoch": 2.920864763331372, "grad_norm": 4.351510524749756, "learning_rate": 4.405008268423711e-06, "loss": 0.1002, "step": 491380 }, { "epoch": 2.92092420540804, "grad_norm": 3.8042032718658447, "learning_rate": 4.4048022511538275e-06, "loss": 0.1064, "step": 491390 }, { "epoch": 2.9209836474847086, "grad_norm": 4.0510358810424805, "learning_rate": 4.404596234908943e-06, "loss": 0.0967, "step": 491400 }, { "epoch": 2.921043089561377, "grad_norm": 4.853939056396484, "learning_rate": 4.404390219689417e-06, "loss": 0.1089, "step": 491410 }, { "epoch": 2.9211025316380455, "grad_norm": 3.1194581985473633, "learning_rate": 4.404184205495601e-06, "loss": 0.1119, "step": 491420 }, { "epoch": 2.921161973714714, "grad_norm": 3.1058156490325928, "learning_rate": 4.403978192327851e-06, "loss": 0.0994, "step": 491430 }, { "epoch": 2.921221415791382, "grad_norm": 2.8983473777770996, "learning_rate": 4.403772180186522e-06, "loss": 0.1026, "step": 491440 }, { "epoch": 2.9212808578680507, "grad_norm": 3.225431203842163, "learning_rate": 4.403566169071968e-06, "loss": 0.1056, "step": 491450 }, { "epoch": 2.9213402999447187, "grad_norm": 4.005008697509766, "learning_rate": 4.403360158984543e-06, "loss": 0.0878, "step": 491460 }, { "epoch": 2.9213997420213875, "grad_norm": 5.453654766082764, "learning_rate": 4.403154149924605e-06, "loss": 0.1024, "step": 491470 }, { "epoch": 2.9214591840980555, "grad_norm": 4.58989143371582, "learning_rate": 4.402948141892507e-06, "loss": 0.1131, "step": 491480 }, { "epoch": 2.921518626174724, "grad_norm": 4.443051338195801, "learning_rate": 4.402742134888602e-06, "loss": 0.1012, "step": 491490 }, { "epoch": 2.9215780682513923, "grad_norm": 4.518207550048828, "learning_rate": 4.402536128913248e-06, "loss": 0.1065, "step": 491500 }, { "epoch": 2.9216375103280607, "grad_norm": 5.1010894775390625, "learning_rate": 4.402330123966797e-06, "loss": 0.0943, "step": 491510 }, { "epoch": 2.921696952404729, "grad_norm": 4.119541645050049, "learning_rate": 4.402124120049604e-06, "loss": 0.1045, "step": 491520 }, { "epoch": 2.9217563944813976, "grad_norm": 4.127871513366699, "learning_rate": 4.401918117162025e-06, "loss": 0.0935, "step": 491530 }, { "epoch": 2.921815836558066, "grad_norm": 3.289672613143921, "learning_rate": 4.401712115304417e-06, "loss": 0.0874, "step": 491540 }, { "epoch": 2.9218752786347344, "grad_norm": 3.619415044784546, "learning_rate": 4.401506114477129e-06, "loss": 0.0938, "step": 491550 }, { "epoch": 2.921934720711403, "grad_norm": 4.486053466796875, "learning_rate": 4.401300114680518e-06, "loss": 0.0934, "step": 491560 }, { "epoch": 2.9219941627880712, "grad_norm": 3.6909828186035156, "learning_rate": 4.401094115914941e-06, "loss": 0.1087, "step": 491570 }, { "epoch": 2.9220536048647396, "grad_norm": 4.8942389488220215, "learning_rate": 4.4008881181807526e-06, "loss": 0.1112, "step": 491580 }, { "epoch": 2.922113046941408, "grad_norm": 2.6916022300720215, "learning_rate": 4.400682121478306e-06, "loss": 0.0919, "step": 491590 }, { "epoch": 2.9221724890180765, "grad_norm": 4.570126056671143, "learning_rate": 4.400476125807955e-06, "loss": 0.1156, "step": 491600 }, { "epoch": 2.922231931094745, "grad_norm": 3.194223642349243, "learning_rate": 4.400270131170057e-06, "loss": 0.0977, "step": 491610 }, { "epoch": 2.9222913731714133, "grad_norm": 2.936096668243408, "learning_rate": 4.400064137564965e-06, "loss": 0.0938, "step": 491620 }, { "epoch": 2.9223508152480813, "grad_norm": 4.390690326690674, "learning_rate": 4.399858144993034e-06, "loss": 0.0977, "step": 491630 }, { "epoch": 2.92241025732475, "grad_norm": 3.256295680999756, "learning_rate": 4.3996521534546195e-06, "loss": 0.0961, "step": 491640 }, { "epoch": 2.922469699401418, "grad_norm": 3.998298168182373, "learning_rate": 4.3994461629500755e-06, "loss": 0.0975, "step": 491650 }, { "epoch": 2.922529141478087, "grad_norm": 3.558237314224243, "learning_rate": 4.399240173479755e-06, "loss": 0.0947, "step": 491660 }, { "epoch": 2.922588583554755, "grad_norm": 3.9719924926757812, "learning_rate": 4.399034185044017e-06, "loss": 0.0949, "step": 491670 }, { "epoch": 2.9226480256314233, "grad_norm": 3.8001973628997803, "learning_rate": 4.398828197643214e-06, "loss": 0.0892, "step": 491680 }, { "epoch": 2.9227074677080918, "grad_norm": 3.1954762935638428, "learning_rate": 4.398622211277698e-06, "loss": 0.1047, "step": 491690 }, { "epoch": 2.92276690978476, "grad_norm": 3.4329514503479004, "learning_rate": 4.398416225947828e-06, "loss": 0.1074, "step": 491700 }, { "epoch": 2.9228263518614286, "grad_norm": 4.048300743103027, "learning_rate": 4.398210241653958e-06, "loss": 0.1095, "step": 491710 }, { "epoch": 2.922885793938097, "grad_norm": 3.0932130813598633, "learning_rate": 4.3980042583964394e-06, "loss": 0.0949, "step": 491720 }, { "epoch": 2.9229452360147654, "grad_norm": 3.711235761642456, "learning_rate": 4.397798276175631e-06, "loss": 0.0953, "step": 491730 }, { "epoch": 2.923004678091434, "grad_norm": 4.254396438598633, "learning_rate": 4.397592294991886e-06, "loss": 0.1027, "step": 491740 }, { "epoch": 2.9230641201681022, "grad_norm": 3.7022042274475098, "learning_rate": 4.397386314845557e-06, "loss": 0.1034, "step": 491750 }, { "epoch": 2.9231235622447707, "grad_norm": 2.3834738731384277, "learning_rate": 4.397180335737002e-06, "loss": 0.1014, "step": 491760 }, { "epoch": 2.923183004321439, "grad_norm": 4.8033928871154785, "learning_rate": 4.396974357666576e-06, "loss": 0.0954, "step": 491770 }, { "epoch": 2.9232424463981075, "grad_norm": 3.5792555809020996, "learning_rate": 4.396768380634628e-06, "loss": 0.1105, "step": 491780 }, { "epoch": 2.923301888474776, "grad_norm": 3.6264545917510986, "learning_rate": 4.396562404641518e-06, "loss": 0.0924, "step": 491790 }, { "epoch": 2.923361330551444, "grad_norm": 2.5099799633026123, "learning_rate": 4.396356429687601e-06, "loss": 0.1025, "step": 491800 }, { "epoch": 2.9234207726281127, "grad_norm": 3.9611594676971436, "learning_rate": 4.396150455773232e-06, "loss": 0.1251, "step": 491810 }, { "epoch": 2.9234802147047807, "grad_norm": 3.4280216693878174, "learning_rate": 4.395944482898761e-06, "loss": 0.0932, "step": 491820 }, { "epoch": 2.9235396567814496, "grad_norm": 3.321293592453003, "learning_rate": 4.395738511064547e-06, "loss": 0.0888, "step": 491830 }, { "epoch": 2.9235990988581175, "grad_norm": 4.264979839324951, "learning_rate": 4.395532540270943e-06, "loss": 0.1076, "step": 491840 }, { "epoch": 2.923658540934786, "grad_norm": 4.070394039154053, "learning_rate": 4.395326570518303e-06, "loss": 0.0988, "step": 491850 }, { "epoch": 2.9237179830114544, "grad_norm": 5.060022830963135, "learning_rate": 4.3951206018069845e-06, "loss": 0.1038, "step": 491860 }, { "epoch": 2.9237774250881228, "grad_norm": 4.0566229820251465, "learning_rate": 4.394914634137341e-06, "loss": 0.0825, "step": 491870 }, { "epoch": 2.923836867164791, "grad_norm": 5.097663879394531, "learning_rate": 4.394708667509725e-06, "loss": 0.1194, "step": 491880 }, { "epoch": 2.9238963092414596, "grad_norm": 3.4240245819091797, "learning_rate": 4.394502701924494e-06, "loss": 0.0931, "step": 491890 }, { "epoch": 2.923955751318128, "grad_norm": 4.120927333831787, "learning_rate": 4.394296737382001e-06, "loss": 0.0959, "step": 491900 }, { "epoch": 2.9240151933947964, "grad_norm": 3.235804557800293, "learning_rate": 4.394090773882601e-06, "loss": 0.1049, "step": 491910 }, { "epoch": 2.924074635471465, "grad_norm": 3.654618263244629, "learning_rate": 4.393884811426649e-06, "loss": 0.0949, "step": 491920 }, { "epoch": 2.9241340775481333, "grad_norm": 3.732431411743164, "learning_rate": 4.393678850014501e-06, "loss": 0.1102, "step": 491930 }, { "epoch": 2.9241935196248017, "grad_norm": 4.570117950439453, "learning_rate": 4.39347288964651e-06, "loss": 0.1162, "step": 491940 }, { "epoch": 2.92425296170147, "grad_norm": 4.637507915496826, "learning_rate": 4.3932669303230305e-06, "loss": 0.1034, "step": 491950 }, { "epoch": 2.9243124037781385, "grad_norm": 3.8426003456115723, "learning_rate": 4.393060972044418e-06, "loss": 0.1349, "step": 491960 }, { "epoch": 2.924371845854807, "grad_norm": 3.6402528285980225, "learning_rate": 4.392855014811027e-06, "loss": 0.0916, "step": 491970 }, { "epoch": 2.9244312879314753, "grad_norm": 4.561824798583984, "learning_rate": 4.39264905862321e-06, "loss": 0.0935, "step": 491980 }, { "epoch": 2.9244907300081433, "grad_norm": 3.5839691162109375, "learning_rate": 4.392443103481327e-06, "loss": 0.1096, "step": 491990 }, { "epoch": 2.924550172084812, "grad_norm": 4.095866680145264, "learning_rate": 4.392237149385726e-06, "loss": 0.1045, "step": 492000 }, { "epoch": 2.92460961416148, "grad_norm": 5.0210113525390625, "learning_rate": 4.392031196336768e-06, "loss": 0.1071, "step": 492010 }, { "epoch": 2.924669056238149, "grad_norm": 4.547645092010498, "learning_rate": 4.391825244334803e-06, "loss": 0.1083, "step": 492020 }, { "epoch": 2.924728498314817, "grad_norm": 4.6724853515625, "learning_rate": 4.391619293380189e-06, "loss": 0.1126, "step": 492030 }, { "epoch": 2.9247879403914854, "grad_norm": 3.816361427307129, "learning_rate": 4.391413343473279e-06, "loss": 0.1151, "step": 492040 }, { "epoch": 2.924847382468154, "grad_norm": 5.810817718505859, "learning_rate": 4.391207394614427e-06, "loss": 0.0963, "step": 492050 }, { "epoch": 2.924906824544822, "grad_norm": 3.4480233192443848, "learning_rate": 4.391001446803989e-06, "loss": 0.1079, "step": 492060 }, { "epoch": 2.9249662666214906, "grad_norm": 4.216585636138916, "learning_rate": 4.39079550004232e-06, "loss": 0.1041, "step": 492070 }, { "epoch": 2.925025708698159, "grad_norm": 3.66943621635437, "learning_rate": 4.390589554329772e-06, "loss": 0.0935, "step": 492080 }, { "epoch": 2.9250851507748274, "grad_norm": 3.752013921737671, "learning_rate": 4.390383609666703e-06, "loss": 0.0961, "step": 492090 }, { "epoch": 2.925144592851496, "grad_norm": 4.1548566818237305, "learning_rate": 4.390177666053466e-06, "loss": 0.1129, "step": 492100 }, { "epoch": 2.9252040349281643, "grad_norm": 3.1644561290740967, "learning_rate": 4.389971723490415e-06, "loss": 0.0906, "step": 492110 }, { "epoch": 2.9252634770048327, "grad_norm": 4.449041366577148, "learning_rate": 4.389765781977906e-06, "loss": 0.1082, "step": 492120 }, { "epoch": 2.925322919081501, "grad_norm": 4.919638633728027, "learning_rate": 4.3895598415162935e-06, "loss": 0.1015, "step": 492130 }, { "epoch": 2.9253823611581695, "grad_norm": 4.036674499511719, "learning_rate": 4.389353902105931e-06, "loss": 0.1012, "step": 492140 }, { "epoch": 2.925441803234838, "grad_norm": 3.569328784942627, "learning_rate": 4.389147963747174e-06, "loss": 0.1048, "step": 492150 }, { "epoch": 2.9255012453115063, "grad_norm": 4.146708965301514, "learning_rate": 4.388942026440379e-06, "loss": 0.1049, "step": 492160 }, { "epoch": 2.9255606873881748, "grad_norm": 2.567652702331543, "learning_rate": 4.388736090185896e-06, "loss": 0.089, "step": 492170 }, { "epoch": 2.9256201294648427, "grad_norm": 2.7708709239959717, "learning_rate": 4.388530154984084e-06, "loss": 0.1026, "step": 492180 }, { "epoch": 2.9256795715415116, "grad_norm": 3.744410514831543, "learning_rate": 4.388324220835296e-06, "loss": 0.0886, "step": 492190 }, { "epoch": 2.9257390136181796, "grad_norm": 3.7800145149230957, "learning_rate": 4.388118287739885e-06, "loss": 0.0975, "step": 492200 }, { "epoch": 2.9257984556948484, "grad_norm": 4.398801326751709, "learning_rate": 4.387912355698209e-06, "loss": 0.0943, "step": 492210 }, { "epoch": 2.9258578977715164, "grad_norm": 3.9356863498687744, "learning_rate": 4.387706424710619e-06, "loss": 0.1094, "step": 492220 }, { "epoch": 2.925917339848185, "grad_norm": 3.520766258239746, "learning_rate": 4.387500494777474e-06, "loss": 0.0984, "step": 492230 }, { "epoch": 2.925976781924853, "grad_norm": 3.753366708755493, "learning_rate": 4.3872945658991255e-06, "loss": 0.0939, "step": 492240 }, { "epoch": 2.9260362240015216, "grad_norm": 4.30546760559082, "learning_rate": 4.3870886380759284e-06, "loss": 0.1082, "step": 492250 }, { "epoch": 2.92609566607819, "grad_norm": 3.764740467071533, "learning_rate": 4.386882711308239e-06, "loss": 0.1135, "step": 492260 }, { "epoch": 2.9261551081548585, "grad_norm": 4.338924884796143, "learning_rate": 4.38667678559641e-06, "loss": 0.0963, "step": 492270 }, { "epoch": 2.926214550231527, "grad_norm": 4.647217273712158, "learning_rate": 4.386470860940796e-06, "loss": 0.1049, "step": 492280 }, { "epoch": 2.9262739923081953, "grad_norm": 3.2727890014648438, "learning_rate": 4.386264937341753e-06, "loss": 0.1058, "step": 492290 }, { "epoch": 2.9263334343848637, "grad_norm": 3.309185266494751, "learning_rate": 4.3860590147996355e-06, "loss": 0.1032, "step": 492300 }, { "epoch": 2.926392876461532, "grad_norm": 3.916933298110962, "learning_rate": 4.385853093314796e-06, "loss": 0.1023, "step": 492310 }, { "epoch": 2.9264523185382005, "grad_norm": 4.12929630279541, "learning_rate": 4.385647172887593e-06, "loss": 0.1057, "step": 492320 }, { "epoch": 2.926511760614869, "grad_norm": 4.312041759490967, "learning_rate": 4.385441253518377e-06, "loss": 0.0885, "step": 492330 }, { "epoch": 2.9265712026915374, "grad_norm": 2.894294261932373, "learning_rate": 4.385235335207505e-06, "loss": 0.0995, "step": 492340 }, { "epoch": 2.926630644768206, "grad_norm": 2.9931833744049072, "learning_rate": 4.385029417955332e-06, "loss": 0.102, "step": 492350 }, { "epoch": 2.926690086844874, "grad_norm": 3.7302043437957764, "learning_rate": 4.3848235017622114e-06, "loss": 0.0926, "step": 492360 }, { "epoch": 2.926749528921542, "grad_norm": 4.110154628753662, "learning_rate": 4.384617586628497e-06, "loss": 0.1146, "step": 492370 }, { "epoch": 2.926808970998211, "grad_norm": 4.483922004699707, "learning_rate": 4.3844116725545464e-06, "loss": 0.0967, "step": 492380 }, { "epoch": 2.926868413074879, "grad_norm": 5.146320819854736, "learning_rate": 4.384205759540712e-06, "loss": 0.1124, "step": 492390 }, { "epoch": 2.9269278551515474, "grad_norm": 3.625777244567871, "learning_rate": 4.383999847587347e-06, "loss": 0.0975, "step": 492400 }, { "epoch": 2.926987297228216, "grad_norm": 5.04506254196167, "learning_rate": 4.383793936694809e-06, "loss": 0.1065, "step": 492410 }, { "epoch": 2.9270467393048842, "grad_norm": 5.409271717071533, "learning_rate": 4.383588026863452e-06, "loss": 0.0952, "step": 492420 }, { "epoch": 2.9271061813815527, "grad_norm": 4.751510143280029, "learning_rate": 4.3833821180936284e-06, "loss": 0.1225, "step": 492430 }, { "epoch": 2.927165623458221, "grad_norm": 3.98856520652771, "learning_rate": 4.383176210385693e-06, "loss": 0.0973, "step": 492440 }, { "epoch": 2.9272250655348895, "grad_norm": 5.124727249145508, "learning_rate": 4.382970303740004e-06, "loss": 0.1082, "step": 492450 }, { "epoch": 2.927284507611558, "grad_norm": 3.168639898300171, "learning_rate": 4.382764398156915e-06, "loss": 0.1074, "step": 492460 }, { "epoch": 2.9273439496882263, "grad_norm": 4.677711486816406, "learning_rate": 4.382558493636777e-06, "loss": 0.1046, "step": 492470 }, { "epoch": 2.9274033917648947, "grad_norm": 3.865607738494873, "learning_rate": 4.382352590179948e-06, "loss": 0.1087, "step": 492480 }, { "epoch": 2.927462833841563, "grad_norm": 2.8611435890197754, "learning_rate": 4.382146687786782e-06, "loss": 0.0899, "step": 492490 }, { "epoch": 2.9275222759182316, "grad_norm": 3.579979181289673, "learning_rate": 4.381940786457632e-06, "loss": 0.1037, "step": 492500 }, { "epoch": 2.9275817179949, "grad_norm": 3.96230149269104, "learning_rate": 4.381734886192855e-06, "loss": 0.1205, "step": 492510 }, { "epoch": 2.9276411600715684, "grad_norm": 3.435396194458008, "learning_rate": 4.381528986992803e-06, "loss": 0.0998, "step": 492520 }, { "epoch": 2.927700602148237, "grad_norm": 4.674050331115723, "learning_rate": 4.381323088857832e-06, "loss": 0.1039, "step": 492530 }, { "epoch": 2.9277600442249048, "grad_norm": 6.582431316375732, "learning_rate": 4.381117191788298e-06, "loss": 0.1119, "step": 492540 }, { "epoch": 2.9278194863015736, "grad_norm": 3.650472402572632, "learning_rate": 4.380911295784553e-06, "loss": 0.1031, "step": 492550 }, { "epoch": 2.9278789283782416, "grad_norm": 4.872618198394775, "learning_rate": 4.380705400846952e-06, "loss": 0.099, "step": 492560 }, { "epoch": 2.9279383704549105, "grad_norm": 2.5775747299194336, "learning_rate": 4.380499506975852e-06, "loss": 0.094, "step": 492570 }, { "epoch": 2.9279978125315784, "grad_norm": 3.8026669025421143, "learning_rate": 4.380293614171605e-06, "loss": 0.0923, "step": 492580 }, { "epoch": 2.928057254608247, "grad_norm": 3.8734207153320312, "learning_rate": 4.380087722434566e-06, "loss": 0.1016, "step": 492590 }, { "epoch": 2.9281166966849153, "grad_norm": 3.6234030723571777, "learning_rate": 4.3798818317650885e-06, "loss": 0.0912, "step": 492600 }, { "epoch": 2.9281761387615837, "grad_norm": 2.63423490524292, "learning_rate": 4.379675942163531e-06, "loss": 0.0918, "step": 492610 }, { "epoch": 2.928235580838252, "grad_norm": 4.514770030975342, "learning_rate": 4.379470053630244e-06, "loss": 0.1027, "step": 492620 }, { "epoch": 2.9282950229149205, "grad_norm": 5.12453556060791, "learning_rate": 4.3792641661655835e-06, "loss": 0.1012, "step": 492630 }, { "epoch": 2.928354464991589, "grad_norm": 4.333282470703125, "learning_rate": 4.379058279769905e-06, "loss": 0.1061, "step": 492640 }, { "epoch": 2.9284139070682573, "grad_norm": 4.960925579071045, "learning_rate": 4.378852394443562e-06, "loss": 0.1002, "step": 492650 }, { "epoch": 2.9284733491449257, "grad_norm": 4.012895584106445, "learning_rate": 4.378646510186907e-06, "loss": 0.1008, "step": 492660 }, { "epoch": 2.928532791221594, "grad_norm": 4.68506383895874, "learning_rate": 4.3784406270002985e-06, "loss": 0.0879, "step": 492670 }, { "epoch": 2.9285922332982626, "grad_norm": 4.447383880615234, "learning_rate": 4.37823474488409e-06, "loss": 0.0851, "step": 492680 }, { "epoch": 2.928651675374931, "grad_norm": 4.848354816436768, "learning_rate": 4.378028863838637e-06, "loss": 0.1056, "step": 492690 }, { "epoch": 2.9287111174515994, "grad_norm": 3.62058687210083, "learning_rate": 4.377822983864289e-06, "loss": 0.0842, "step": 492700 }, { "epoch": 2.928770559528268, "grad_norm": 4.841858863830566, "learning_rate": 4.3776171049614066e-06, "loss": 0.1039, "step": 492710 }, { "epoch": 2.9288300016049362, "grad_norm": 3.9089670181274414, "learning_rate": 4.377411227130342e-06, "loss": 0.0872, "step": 492720 }, { "epoch": 2.928889443681604, "grad_norm": 4.036304950714111, "learning_rate": 4.377205350371448e-06, "loss": 0.0972, "step": 492730 }, { "epoch": 2.928948885758273, "grad_norm": 2.631889581680298, "learning_rate": 4.376999474685082e-06, "loss": 0.0905, "step": 492740 }, { "epoch": 2.929008327834941, "grad_norm": 4.953883171081543, "learning_rate": 4.376793600071597e-06, "loss": 0.0928, "step": 492750 }, { "epoch": 2.92906776991161, "grad_norm": 2.957740068435669, "learning_rate": 4.376587726531346e-06, "loss": 0.0938, "step": 492760 }, { "epoch": 2.929127211988278, "grad_norm": 4.000269889831543, "learning_rate": 4.376381854064688e-06, "loss": 0.1058, "step": 492770 }, { "epoch": 2.9291866540649463, "grad_norm": 4.823218822479248, "learning_rate": 4.376175982671973e-06, "loss": 0.1016, "step": 492780 }, { "epoch": 2.9292460961416147, "grad_norm": 3.4399678707122803, "learning_rate": 4.375970112353558e-06, "loss": 0.1043, "step": 492790 }, { "epoch": 2.929305538218283, "grad_norm": 3.038458824157715, "learning_rate": 4.375764243109797e-06, "loss": 0.0966, "step": 492800 }, { "epoch": 2.9293649802949515, "grad_norm": 3.8385801315307617, "learning_rate": 4.375558374941044e-06, "loss": 0.102, "step": 492810 }, { "epoch": 2.92942442237162, "grad_norm": 5.016143798828125, "learning_rate": 4.375352507847654e-06, "loss": 0.1078, "step": 492820 }, { "epoch": 2.9294838644482883, "grad_norm": 3.83046555519104, "learning_rate": 4.375146641829983e-06, "loss": 0.1106, "step": 492830 }, { "epoch": 2.9295433065249568, "grad_norm": 3.9859588146209717, "learning_rate": 4.3749407768883825e-06, "loss": 0.0915, "step": 492840 }, { "epoch": 2.929602748601625, "grad_norm": 4.290426731109619, "learning_rate": 4.374734913023208e-06, "loss": 0.1085, "step": 492850 }, { "epoch": 2.9296621906782936, "grad_norm": 3.871795892715454, "learning_rate": 4.3745290502348165e-06, "loss": 0.0971, "step": 492860 }, { "epoch": 2.929721632754962, "grad_norm": 4.656642913818359, "learning_rate": 4.37432318852356e-06, "loss": 0.1162, "step": 492870 }, { "epoch": 2.9297810748316304, "grad_norm": 5.054880142211914, "learning_rate": 4.374117327889791e-06, "loss": 0.0852, "step": 492880 }, { "epoch": 2.929840516908299, "grad_norm": 2.662921667098999, "learning_rate": 4.37391146833387e-06, "loss": 0.0972, "step": 492890 }, { "epoch": 2.9298999589849672, "grad_norm": 4.989502429962158, "learning_rate": 4.373705609856146e-06, "loss": 0.1217, "step": 492900 }, { "epoch": 2.9299594010616357, "grad_norm": 4.379284858703613, "learning_rate": 4.373499752456977e-06, "loss": 0.0964, "step": 492910 }, { "epoch": 2.9300188431383036, "grad_norm": 3.9956870079040527, "learning_rate": 4.373293896136716e-06, "loss": 0.0988, "step": 492920 }, { "epoch": 2.9300782852149725, "grad_norm": 4.4293317794799805, "learning_rate": 4.373088040895717e-06, "loss": 0.1077, "step": 492930 }, { "epoch": 2.9301377272916405, "grad_norm": 4.251010417938232, "learning_rate": 4.3728821867343365e-06, "loss": 0.1033, "step": 492940 }, { "epoch": 2.9301971693683093, "grad_norm": 3.75482177734375, "learning_rate": 4.372676333652928e-06, "loss": 0.1105, "step": 492950 }, { "epoch": 2.9302566114449773, "grad_norm": 5.142362594604492, "learning_rate": 4.3724704816518435e-06, "loss": 0.0954, "step": 492960 }, { "epoch": 2.9303160535216457, "grad_norm": 3.572676181793213, "learning_rate": 4.372264630731441e-06, "loss": 0.0962, "step": 492970 }, { "epoch": 2.930375495598314, "grad_norm": 2.959459066390991, "learning_rate": 4.372058780892075e-06, "loss": 0.1155, "step": 492980 }, { "epoch": 2.9304349376749825, "grad_norm": 3.1264894008636475, "learning_rate": 4.371852932134097e-06, "loss": 0.1065, "step": 492990 }, { "epoch": 2.930494379751651, "grad_norm": 3.1993417739868164, "learning_rate": 4.371647084457863e-06, "loss": 0.1097, "step": 493000 }, { "epoch": 2.9305538218283194, "grad_norm": 3.897078275680542, "learning_rate": 4.3714412378637286e-06, "loss": 0.0821, "step": 493010 }, { "epoch": 2.9306132639049878, "grad_norm": 3.879635810852051, "learning_rate": 4.371235392352047e-06, "loss": 0.1107, "step": 493020 }, { "epoch": 2.930672705981656, "grad_norm": 2.7832744121551514, "learning_rate": 4.371029547923173e-06, "loss": 0.1015, "step": 493030 }, { "epoch": 2.9307321480583246, "grad_norm": 3.2089312076568604, "learning_rate": 4.3708237045774615e-06, "loss": 0.0895, "step": 493040 }, { "epoch": 2.930791590134993, "grad_norm": 5.028512954711914, "learning_rate": 4.370617862315266e-06, "loss": 0.1152, "step": 493050 }, { "epoch": 2.9308510322116614, "grad_norm": 3.176565170288086, "learning_rate": 4.370412021136942e-06, "loss": 0.0921, "step": 493060 }, { "epoch": 2.93091047428833, "grad_norm": 5.493259429931641, "learning_rate": 4.370206181042844e-06, "loss": 0.1036, "step": 493070 }, { "epoch": 2.9309699163649983, "grad_norm": 5.4156575202941895, "learning_rate": 4.370000342033325e-06, "loss": 0.1003, "step": 493080 }, { "epoch": 2.9310293584416667, "grad_norm": 3.454766273498535, "learning_rate": 4.369794504108742e-06, "loss": 0.0932, "step": 493090 }, { "epoch": 2.931088800518335, "grad_norm": 4.607604503631592, "learning_rate": 4.3695886672694456e-06, "loss": 0.1028, "step": 493100 }, { "epoch": 2.931148242595003, "grad_norm": 2.898951292037964, "learning_rate": 4.369382831515795e-06, "loss": 0.101, "step": 493110 }, { "epoch": 2.931207684671672, "grad_norm": 4.143335819244385, "learning_rate": 4.369176996848141e-06, "loss": 0.0845, "step": 493120 }, { "epoch": 2.93126712674834, "grad_norm": 4.697909832000732, "learning_rate": 4.3689711632668405e-06, "loss": 0.1064, "step": 493130 }, { "epoch": 2.9313265688250083, "grad_norm": 3.465355634689331, "learning_rate": 4.368765330772247e-06, "loss": 0.0966, "step": 493140 }, { "epoch": 2.9313860109016767, "grad_norm": 3.9144368171691895, "learning_rate": 4.368559499364714e-06, "loss": 0.0976, "step": 493150 }, { "epoch": 2.931445452978345, "grad_norm": 3.752619743347168, "learning_rate": 4.368353669044599e-06, "loss": 0.0954, "step": 493160 }, { "epoch": 2.9315048950550135, "grad_norm": 4.165461540222168, "learning_rate": 4.368147839812253e-06, "loss": 0.1057, "step": 493170 }, { "epoch": 2.931564337131682, "grad_norm": 4.577881813049316, "learning_rate": 4.367942011668031e-06, "loss": 0.0996, "step": 493180 }, { "epoch": 2.9316237792083504, "grad_norm": 2.939117908477783, "learning_rate": 4.367736184612289e-06, "loss": 0.1136, "step": 493190 }, { "epoch": 2.931683221285019, "grad_norm": 4.346700668334961, "learning_rate": 4.367530358645382e-06, "loss": 0.0924, "step": 493200 }, { "epoch": 2.931742663361687, "grad_norm": 4.796242713928223, "learning_rate": 4.367324533767661e-06, "loss": 0.0968, "step": 493210 }, { "epoch": 2.9318021054383556, "grad_norm": 5.815695762634277, "learning_rate": 4.367118709979484e-06, "loss": 0.1025, "step": 493220 }, { "epoch": 2.931861547515024, "grad_norm": 3.318789482116699, "learning_rate": 4.366912887281204e-06, "loss": 0.0871, "step": 493230 }, { "epoch": 2.9319209895916925, "grad_norm": 4.862367630004883, "learning_rate": 4.366707065673175e-06, "loss": 0.0962, "step": 493240 }, { "epoch": 2.931980431668361, "grad_norm": 4.655169486999512, "learning_rate": 4.366501245155752e-06, "loss": 0.0923, "step": 493250 }, { "epoch": 2.9320398737450293, "grad_norm": 3.0437300205230713, "learning_rate": 4.366295425729291e-06, "loss": 0.1077, "step": 493260 }, { "epoch": 2.9320993158216977, "grad_norm": 5.587675094604492, "learning_rate": 4.366089607394144e-06, "loss": 0.1081, "step": 493270 }, { "epoch": 2.9321587578983657, "grad_norm": 4.6757283210754395, "learning_rate": 4.365883790150665e-06, "loss": 0.1151, "step": 493280 }, { "epoch": 2.9322181999750345, "grad_norm": 3.8567638397216797, "learning_rate": 4.365677973999211e-06, "loss": 0.1075, "step": 493290 }, { "epoch": 2.9322776420517025, "grad_norm": 4.763325214385986, "learning_rate": 4.365472158940135e-06, "loss": 0.1128, "step": 493300 }, { "epoch": 2.9323370841283714, "grad_norm": 4.534608364105225, "learning_rate": 4.365266344973792e-06, "loss": 0.0919, "step": 493310 }, { "epoch": 2.9323965262050393, "grad_norm": 4.43383264541626, "learning_rate": 4.365060532100534e-06, "loss": 0.1005, "step": 493320 }, { "epoch": 2.9324559682817077, "grad_norm": 3.598757743835449, "learning_rate": 4.364854720320719e-06, "loss": 0.1249, "step": 493330 }, { "epoch": 2.932515410358376, "grad_norm": 3.8420333862304688, "learning_rate": 4.3646489096347e-06, "loss": 0.0971, "step": 493340 }, { "epoch": 2.9325748524350446, "grad_norm": 3.829695701599121, "learning_rate": 4.364443100042832e-06, "loss": 0.1104, "step": 493350 }, { "epoch": 2.932634294511713, "grad_norm": 3.0662834644317627, "learning_rate": 4.364237291545468e-06, "loss": 0.0862, "step": 493360 }, { "epoch": 2.9326937365883814, "grad_norm": 3.0460731983184814, "learning_rate": 4.364031484142964e-06, "loss": 0.0918, "step": 493370 }, { "epoch": 2.93275317866505, "grad_norm": 4.349151134490967, "learning_rate": 4.363825677835673e-06, "loss": 0.1024, "step": 493380 }, { "epoch": 2.9328126207417182, "grad_norm": 4.769386291503906, "learning_rate": 4.363619872623951e-06, "loss": 0.0937, "step": 493390 }, { "epoch": 2.9328720628183866, "grad_norm": 4.085925579071045, "learning_rate": 4.363414068508151e-06, "loss": 0.1129, "step": 493400 }, { "epoch": 2.932931504895055, "grad_norm": 5.539032936096191, "learning_rate": 4.363208265488627e-06, "loss": 0.1133, "step": 493410 }, { "epoch": 2.9329909469717235, "grad_norm": 4.572971820831299, "learning_rate": 4.3630024635657356e-06, "loss": 0.115, "step": 493420 }, { "epoch": 2.933050389048392, "grad_norm": 4.8098835945129395, "learning_rate": 4.36279666273983e-06, "loss": 0.0951, "step": 493430 }, { "epoch": 2.9331098311250603, "grad_norm": 3.171222686767578, "learning_rate": 4.362590863011264e-06, "loss": 0.1037, "step": 493440 }, { "epoch": 2.9331692732017287, "grad_norm": 3.776252508163452, "learning_rate": 4.362385064380392e-06, "loss": 0.1112, "step": 493450 }, { "epoch": 2.933228715278397, "grad_norm": 4.554840087890625, "learning_rate": 4.36217926684757e-06, "loss": 0.091, "step": 493460 }, { "epoch": 2.933288157355065, "grad_norm": 3.884172201156616, "learning_rate": 4.361973470413151e-06, "loss": 0.1177, "step": 493470 }, { "epoch": 2.933347599431734, "grad_norm": 3.2977349758148193, "learning_rate": 4.36176767507749e-06, "loss": 0.0976, "step": 493480 }, { "epoch": 2.933407041508402, "grad_norm": 4.5951104164123535, "learning_rate": 4.361561880840942e-06, "loss": 0.0956, "step": 493490 }, { "epoch": 2.933466483585071, "grad_norm": 3.6225898265838623, "learning_rate": 4.361356087703859e-06, "loss": 0.1117, "step": 493500 }, { "epoch": 2.9335259256617388, "grad_norm": 4.469265937805176, "learning_rate": 4.361150295666598e-06, "loss": 0.0997, "step": 493510 }, { "epoch": 2.933585367738407, "grad_norm": 4.02496337890625, "learning_rate": 4.360944504729513e-06, "loss": 0.0977, "step": 493520 }, { "epoch": 2.9336448098150756, "grad_norm": 4.983975887298584, "learning_rate": 4.360738714892956e-06, "loss": 0.1071, "step": 493530 }, { "epoch": 2.933704251891744, "grad_norm": 5.573524475097656, "learning_rate": 4.360532926157283e-06, "loss": 0.1137, "step": 493540 }, { "epoch": 2.9337636939684124, "grad_norm": 3.0393176078796387, "learning_rate": 4.360327138522849e-06, "loss": 0.0809, "step": 493550 }, { "epoch": 2.933823136045081, "grad_norm": 3.6349451541900635, "learning_rate": 4.36012135199001e-06, "loss": 0.0874, "step": 493560 }, { "epoch": 2.9338825781217492, "grad_norm": 3.4259932041168213, "learning_rate": 4.359915566559117e-06, "loss": 0.0985, "step": 493570 }, { "epoch": 2.9339420201984177, "grad_norm": 3.628239154815674, "learning_rate": 4.359709782230526e-06, "loss": 0.1038, "step": 493580 }, { "epoch": 2.934001462275086, "grad_norm": 4.021063804626465, "learning_rate": 4.359503999004591e-06, "loss": 0.0885, "step": 493590 }, { "epoch": 2.9340609043517545, "grad_norm": 4.548072338104248, "learning_rate": 4.359298216881667e-06, "loss": 0.0936, "step": 493600 }, { "epoch": 2.934120346428423, "grad_norm": 3.6858980655670166, "learning_rate": 4.359092435862107e-06, "loss": 0.0983, "step": 493610 }, { "epoch": 2.9341797885050913, "grad_norm": 2.4609856605529785, "learning_rate": 4.358886655946267e-06, "loss": 0.129, "step": 493620 }, { "epoch": 2.9342392305817597, "grad_norm": 4.559967517852783, "learning_rate": 4.3586808771345015e-06, "loss": 0.1056, "step": 493630 }, { "epoch": 2.934298672658428, "grad_norm": 4.625845909118652, "learning_rate": 4.3584750994271615e-06, "loss": 0.0907, "step": 493640 }, { "epoch": 2.9343581147350966, "grad_norm": 4.431565761566162, "learning_rate": 4.358269322824607e-06, "loss": 0.1098, "step": 493650 }, { "epoch": 2.9344175568117645, "grad_norm": 3.146207332611084, "learning_rate": 4.358063547327187e-06, "loss": 0.1047, "step": 493660 }, { "epoch": 2.9344769988884334, "grad_norm": 3.1717607975006104, "learning_rate": 4.357857772935259e-06, "loss": 0.0933, "step": 493670 }, { "epoch": 2.9345364409651014, "grad_norm": 3.292379856109619, "learning_rate": 4.357651999649177e-06, "loss": 0.0954, "step": 493680 }, { "epoch": 2.93459588304177, "grad_norm": 3.140944242477417, "learning_rate": 4.3574462274692944e-06, "loss": 0.0992, "step": 493690 }, { "epoch": 2.934655325118438, "grad_norm": 5.215193748474121, "learning_rate": 4.357240456395966e-06, "loss": 0.1121, "step": 493700 }, { "epoch": 2.9347147671951066, "grad_norm": 4.293552398681641, "learning_rate": 4.357034686429546e-06, "loss": 0.1046, "step": 493710 }, { "epoch": 2.934774209271775, "grad_norm": 2.6642372608184814, "learning_rate": 4.3568289175703896e-06, "loss": 0.0976, "step": 493720 }, { "epoch": 2.9348336513484434, "grad_norm": 3.41898250579834, "learning_rate": 4.3566231498188496e-06, "loss": 0.096, "step": 493730 }, { "epoch": 2.934893093425112, "grad_norm": 3.788236141204834, "learning_rate": 4.356417383175282e-06, "loss": 0.0921, "step": 493740 }, { "epoch": 2.9349525355017803, "grad_norm": 3.6705920696258545, "learning_rate": 4.356211617640041e-06, "loss": 0.1127, "step": 493750 }, { "epoch": 2.9350119775784487, "grad_norm": 4.237264633178711, "learning_rate": 4.356005853213478e-06, "loss": 0.1056, "step": 493760 }, { "epoch": 2.935071419655117, "grad_norm": 4.986355304718018, "learning_rate": 4.3558000898959505e-06, "loss": 0.1101, "step": 493770 }, { "epoch": 2.9351308617317855, "grad_norm": 4.600497722625732, "learning_rate": 4.355594327687814e-06, "loss": 0.0976, "step": 493780 }, { "epoch": 2.935190303808454, "grad_norm": 3.7644617557525635, "learning_rate": 4.35538856658942e-06, "loss": 0.0905, "step": 493790 }, { "epoch": 2.9352497458851223, "grad_norm": 4.832856178283691, "learning_rate": 4.355182806601124e-06, "loss": 0.0903, "step": 493800 }, { "epoch": 2.9353091879617907, "grad_norm": 4.157408714294434, "learning_rate": 4.35497704772328e-06, "loss": 0.0845, "step": 493810 }, { "epoch": 2.935368630038459, "grad_norm": 3.5121402740478516, "learning_rate": 4.354771289956243e-06, "loss": 0.0966, "step": 493820 }, { "epoch": 2.9354280721151276, "grad_norm": 3.0891358852386475, "learning_rate": 4.3545655333003655e-06, "loss": 0.1037, "step": 493830 }, { "epoch": 2.935487514191796, "grad_norm": 4.143664360046387, "learning_rate": 4.354359777756005e-06, "loss": 0.0908, "step": 493840 }, { "epoch": 2.935546956268464, "grad_norm": 3.4511420726776123, "learning_rate": 4.354154023323513e-06, "loss": 0.1051, "step": 493850 }, { "epoch": 2.935606398345133, "grad_norm": 4.169545650482178, "learning_rate": 4.353948270003244e-06, "loss": 0.1072, "step": 493860 }, { "epoch": 2.935665840421801, "grad_norm": 3.694728136062622, "learning_rate": 4.353742517795555e-06, "loss": 0.1148, "step": 493870 }, { "epoch": 2.935725282498469, "grad_norm": 4.118868827819824, "learning_rate": 4.3535367667007974e-06, "loss": 0.1154, "step": 493880 }, { "epoch": 2.9357847245751376, "grad_norm": 3.304135799407959, "learning_rate": 4.353331016719327e-06, "loss": 0.1022, "step": 493890 }, { "epoch": 2.935844166651806, "grad_norm": 3.019075870513916, "learning_rate": 4.353125267851497e-06, "loss": 0.0953, "step": 493900 }, { "epoch": 2.9359036087284744, "grad_norm": 2.7379941940307617, "learning_rate": 4.352919520097664e-06, "loss": 0.1063, "step": 493910 }, { "epoch": 2.935963050805143, "grad_norm": 5.074922561645508, "learning_rate": 4.3527137734581785e-06, "loss": 0.1045, "step": 493920 }, { "epoch": 2.9360224928818113, "grad_norm": 4.347270965576172, "learning_rate": 4.352508027933399e-06, "loss": 0.1082, "step": 493930 }, { "epoch": 2.9360819349584797, "grad_norm": 3.8390018939971924, "learning_rate": 4.352302283523678e-06, "loss": 0.0955, "step": 493940 }, { "epoch": 2.936141377035148, "grad_norm": 4.805428504943848, "learning_rate": 4.352096540229369e-06, "loss": 0.1129, "step": 493950 }, { "epoch": 2.9362008191118165, "grad_norm": 3.1391756534576416, "learning_rate": 4.351890798050826e-06, "loss": 0.0918, "step": 493960 }, { "epoch": 2.936260261188485, "grad_norm": 4.50540828704834, "learning_rate": 4.351685056988406e-06, "loss": 0.0971, "step": 493970 }, { "epoch": 2.9363197032651533, "grad_norm": 4.059528350830078, "learning_rate": 4.351479317042459e-06, "loss": 0.0981, "step": 493980 }, { "epoch": 2.9363791453418218, "grad_norm": 3.3752453327178955, "learning_rate": 4.351273578213345e-06, "loss": 0.0909, "step": 493990 }, { "epoch": 2.93643858741849, "grad_norm": 3.930298328399658, "learning_rate": 4.351067840501414e-06, "loss": 0.1007, "step": 494000 }, { "epoch": 2.9364980294951586, "grad_norm": 4.181185245513916, "learning_rate": 4.350862103907023e-06, "loss": 0.1179, "step": 494010 }, { "epoch": 2.9365574715718266, "grad_norm": 4.37532377243042, "learning_rate": 4.350656368430524e-06, "loss": 0.102, "step": 494020 }, { "epoch": 2.9366169136484954, "grad_norm": 4.88315486907959, "learning_rate": 4.350450634072272e-06, "loss": 0.1084, "step": 494030 }, { "epoch": 2.9366763557251634, "grad_norm": 3.2711124420166016, "learning_rate": 4.350244900832622e-06, "loss": 0.0964, "step": 494040 }, { "epoch": 2.9367357978018322, "grad_norm": 4.598088264465332, "learning_rate": 4.3500391687119274e-06, "loss": 0.0977, "step": 494050 }, { "epoch": 2.9367952398785, "grad_norm": 4.184158802032471, "learning_rate": 4.349833437710542e-06, "loss": 0.0989, "step": 494060 }, { "epoch": 2.9368546819551686, "grad_norm": 3.2983405590057373, "learning_rate": 4.349627707828823e-06, "loss": 0.1047, "step": 494070 }, { "epoch": 2.936914124031837, "grad_norm": 2.780599355697632, "learning_rate": 4.349421979067122e-06, "loss": 0.094, "step": 494080 }, { "epoch": 2.9369735661085055, "grad_norm": 4.452364444732666, "learning_rate": 4.349216251425793e-06, "loss": 0.1043, "step": 494090 }, { "epoch": 2.937033008185174, "grad_norm": 3.1453840732574463, "learning_rate": 4.349010524905193e-06, "loss": 0.0959, "step": 494100 }, { "epoch": 2.9370924502618423, "grad_norm": 3.3855128288269043, "learning_rate": 4.3488047995056735e-06, "loss": 0.0994, "step": 494110 }, { "epoch": 2.9371518923385107, "grad_norm": 3.9370439052581787, "learning_rate": 4.34859907522759e-06, "loss": 0.1065, "step": 494120 }, { "epoch": 2.937211334415179, "grad_norm": 4.907443046569824, "learning_rate": 4.348393352071296e-06, "loss": 0.0991, "step": 494130 }, { "epoch": 2.9372707764918475, "grad_norm": 4.2641401290893555, "learning_rate": 4.348187630037147e-06, "loss": 0.0922, "step": 494140 }, { "epoch": 2.937330218568516, "grad_norm": 3.9661872386932373, "learning_rate": 4.347981909125496e-06, "loss": 0.1053, "step": 494150 }, { "epoch": 2.9373896606451844, "grad_norm": 5.294002532958984, "learning_rate": 4.347776189336699e-06, "loss": 0.1018, "step": 494160 }, { "epoch": 2.937449102721853, "grad_norm": 3.8283071517944336, "learning_rate": 4.347570470671109e-06, "loss": 0.1005, "step": 494170 }, { "epoch": 2.937508544798521, "grad_norm": 3.7197372913360596, "learning_rate": 4.34736475312908e-06, "loss": 0.0844, "step": 494180 }, { "epoch": 2.9375679868751896, "grad_norm": 7.377252578735352, "learning_rate": 4.347159036710967e-06, "loss": 0.1031, "step": 494190 }, { "epoch": 2.937627428951858, "grad_norm": 4.931879997253418, "learning_rate": 4.346953321417122e-06, "loss": 0.0987, "step": 494200 }, { "epoch": 2.937686871028526, "grad_norm": 4.517568111419678, "learning_rate": 4.346747607247904e-06, "loss": 0.0956, "step": 494210 }, { "epoch": 2.937746313105195, "grad_norm": 3.117269277572632, "learning_rate": 4.346541894203664e-06, "loss": 0.1005, "step": 494220 }, { "epoch": 2.937805755181863, "grad_norm": 3.566528797149658, "learning_rate": 4.346336182284756e-06, "loss": 0.1039, "step": 494230 }, { "epoch": 2.9378651972585317, "grad_norm": 4.237308979034424, "learning_rate": 4.3461304714915365e-06, "loss": 0.1059, "step": 494240 }, { "epoch": 2.9379246393351997, "grad_norm": 3.8101015090942383, "learning_rate": 4.345924761824358e-06, "loss": 0.0974, "step": 494250 }, { "epoch": 2.937984081411868, "grad_norm": 4.859439849853516, "learning_rate": 4.345719053283574e-06, "loss": 0.1086, "step": 494260 }, { "epoch": 2.9380435234885365, "grad_norm": 3.3219382762908936, "learning_rate": 4.345513345869541e-06, "loss": 0.0937, "step": 494270 }, { "epoch": 2.938102965565205, "grad_norm": 4.232785701751709, "learning_rate": 4.345307639582612e-06, "loss": 0.1033, "step": 494280 }, { "epoch": 2.9381624076418733, "grad_norm": 3.5724077224731445, "learning_rate": 4.34510193442314e-06, "loss": 0.0924, "step": 494290 }, { "epoch": 2.9382218497185417, "grad_norm": 5.046936511993408, "learning_rate": 4.344896230391482e-06, "loss": 0.1067, "step": 494300 }, { "epoch": 2.93828129179521, "grad_norm": 6.671559810638428, "learning_rate": 4.344690527487991e-06, "loss": 0.0997, "step": 494310 }, { "epoch": 2.9383407338718786, "grad_norm": 4.713740825653076, "learning_rate": 4.3444848257130205e-06, "loss": 0.1103, "step": 494320 }, { "epoch": 2.938400175948547, "grad_norm": 2.916663408279419, "learning_rate": 4.344279125066926e-06, "loss": 0.1021, "step": 494330 }, { "epoch": 2.9384596180252154, "grad_norm": 4.666294574737549, "learning_rate": 4.344073425550061e-06, "loss": 0.0937, "step": 494340 }, { "epoch": 2.938519060101884, "grad_norm": 4.0374908447265625, "learning_rate": 4.343867727162779e-06, "loss": 0.0867, "step": 494350 }, { "epoch": 2.938578502178552, "grad_norm": 4.461469650268555, "learning_rate": 4.343662029905436e-06, "loss": 0.093, "step": 494360 }, { "epoch": 2.9386379442552206, "grad_norm": 4.144144535064697, "learning_rate": 4.343456333778385e-06, "loss": 0.1046, "step": 494370 }, { "epoch": 2.938697386331889, "grad_norm": 4.337116241455078, "learning_rate": 4.343250638781979e-06, "loss": 0.096, "step": 494380 }, { "epoch": 2.9387568284085575, "grad_norm": 3.137148380279541, "learning_rate": 4.343044944916575e-06, "loss": 0.0729, "step": 494390 }, { "epoch": 2.9388162704852254, "grad_norm": 4.6748199462890625, "learning_rate": 4.342839252182528e-06, "loss": 0.0916, "step": 494400 }, { "epoch": 2.9388757125618943, "grad_norm": 4.327510356903076, "learning_rate": 4.3426335605801866e-06, "loss": 0.1066, "step": 494410 }, { "epoch": 2.9389351546385623, "grad_norm": 2.54357647895813, "learning_rate": 4.342427870109909e-06, "loss": 0.0924, "step": 494420 }, { "epoch": 2.938994596715231, "grad_norm": 4.452609062194824, "learning_rate": 4.34222218077205e-06, "loss": 0.1136, "step": 494430 }, { "epoch": 2.939054038791899, "grad_norm": 4.9798359870910645, "learning_rate": 4.342016492566964e-06, "loss": 0.1, "step": 494440 }, { "epoch": 2.9391134808685675, "grad_norm": 4.962756156921387, "learning_rate": 4.3418108054950025e-06, "loss": 0.1169, "step": 494450 }, { "epoch": 2.939172922945236, "grad_norm": 4.472126483917236, "learning_rate": 4.341605119556523e-06, "loss": 0.101, "step": 494460 }, { "epoch": 2.9392323650219043, "grad_norm": 3.1999475955963135, "learning_rate": 4.341399434751877e-06, "loss": 0.0946, "step": 494470 }, { "epoch": 2.9392918070985727, "grad_norm": 3.9487709999084473, "learning_rate": 4.34119375108142e-06, "loss": 0.0921, "step": 494480 }, { "epoch": 2.939351249175241, "grad_norm": 3.7583229541778564, "learning_rate": 4.340988068545506e-06, "loss": 0.1121, "step": 494490 }, { "epoch": 2.9394106912519096, "grad_norm": 3.888587713241577, "learning_rate": 4.34078238714449e-06, "loss": 0.095, "step": 494500 }, { "epoch": 2.939470133328578, "grad_norm": 3.8634791374206543, "learning_rate": 4.340576706878723e-06, "loss": 0.1077, "step": 494510 }, { "epoch": 2.9395295754052464, "grad_norm": 2.7505297660827637, "learning_rate": 4.3403710277485645e-06, "loss": 0.1087, "step": 494520 }, { "epoch": 2.939589017481915, "grad_norm": 3.882650375366211, "learning_rate": 4.340165349754364e-06, "loss": 0.1027, "step": 494530 }, { "epoch": 2.9396484595585832, "grad_norm": 4.6003804206848145, "learning_rate": 4.339959672896478e-06, "loss": 0.1028, "step": 494540 }, { "epoch": 2.9397079016352516, "grad_norm": 3.0398306846618652, "learning_rate": 4.33975399717526e-06, "loss": 0.0994, "step": 494550 }, { "epoch": 2.93976734371192, "grad_norm": 4.683925151824951, "learning_rate": 4.339548322591065e-06, "loss": 0.0955, "step": 494560 }, { "epoch": 2.9398267857885885, "grad_norm": 3.7960762977600098, "learning_rate": 4.339342649144246e-06, "loss": 0.0967, "step": 494570 }, { "epoch": 2.939886227865257, "grad_norm": 3.827984571456909, "learning_rate": 4.3391369768351575e-06, "loss": 0.0956, "step": 494580 }, { "epoch": 2.939945669941925, "grad_norm": 2.9678521156311035, "learning_rate": 4.338931305664156e-06, "loss": 0.091, "step": 494590 }, { "epoch": 2.9400051120185937, "grad_norm": 4.693212032318115, "learning_rate": 4.338725635631591e-06, "loss": 0.1066, "step": 494600 }, { "epoch": 2.9400645540952617, "grad_norm": 3.0977463722229004, "learning_rate": 4.338519966737821e-06, "loss": 0.0856, "step": 494610 }, { "epoch": 2.94012399617193, "grad_norm": 3.5772669315338135, "learning_rate": 4.338314298983198e-06, "loss": 0.0952, "step": 494620 }, { "epoch": 2.9401834382485985, "grad_norm": 3.9114773273468018, "learning_rate": 4.3381086323680765e-06, "loss": 0.0931, "step": 494630 }, { "epoch": 2.940242880325267, "grad_norm": 2.9960036277770996, "learning_rate": 4.3379029668928095e-06, "loss": 0.1032, "step": 494640 }, { "epoch": 2.9403023224019353, "grad_norm": 4.281219959259033, "learning_rate": 4.337697302557753e-06, "loss": 0.097, "step": 494650 }, { "epoch": 2.9403617644786038, "grad_norm": 3.069992780685425, "learning_rate": 4.337491639363263e-06, "loss": 0.1112, "step": 494660 }, { "epoch": 2.940421206555272, "grad_norm": 2.8738555908203125, "learning_rate": 4.337285977309691e-06, "loss": 0.1055, "step": 494670 }, { "epoch": 2.9404806486319406, "grad_norm": 3.3067991733551025, "learning_rate": 4.3370803163973894e-06, "loss": 0.096, "step": 494680 }, { "epoch": 2.940540090708609, "grad_norm": 3.622478723526001, "learning_rate": 4.3368746566267175e-06, "loss": 0.1028, "step": 494690 }, { "epoch": 2.9405995327852774, "grad_norm": 3.3251781463623047, "learning_rate": 4.3366689979980255e-06, "loss": 0.1162, "step": 494700 }, { "epoch": 2.940658974861946, "grad_norm": 5.042288780212402, "learning_rate": 4.3364633405116675e-06, "loss": 0.0874, "step": 494710 }, { "epoch": 2.9407184169386142, "grad_norm": 4.938859939575195, "learning_rate": 4.336257684168e-06, "loss": 0.0962, "step": 494720 }, { "epoch": 2.9407778590152827, "grad_norm": 2.9550251960754395, "learning_rate": 4.336052028967376e-06, "loss": 0.1059, "step": 494730 }, { "epoch": 2.940837301091951, "grad_norm": 3.1245644092559814, "learning_rate": 4.335846374910149e-06, "loss": 0.0923, "step": 494740 }, { "epoch": 2.9408967431686195, "grad_norm": 3.7432570457458496, "learning_rate": 4.335640721996674e-06, "loss": 0.1001, "step": 494750 }, { "epoch": 2.9409561852452875, "grad_norm": 3.6593093872070312, "learning_rate": 4.335435070227306e-06, "loss": 0.095, "step": 494760 }, { "epoch": 2.9410156273219563, "grad_norm": 5.132644176483154, "learning_rate": 4.335229419602396e-06, "loss": 0.1073, "step": 494770 }, { "epoch": 2.9410750693986243, "grad_norm": 5.112537860870361, "learning_rate": 4.335023770122302e-06, "loss": 0.0964, "step": 494780 }, { "epoch": 2.941134511475293, "grad_norm": 3.2000174522399902, "learning_rate": 4.334818121787376e-06, "loss": 0.0926, "step": 494790 }, { "epoch": 2.941193953551961, "grad_norm": 3.862852096557617, "learning_rate": 4.3346124745979715e-06, "loss": 0.1, "step": 494800 }, { "epoch": 2.9412533956286295, "grad_norm": 3.8799285888671875, "learning_rate": 4.334406828554445e-06, "loss": 0.0963, "step": 494810 }, { "epoch": 2.941312837705298, "grad_norm": 2.0368492603302, "learning_rate": 4.33420118365715e-06, "loss": 0.0913, "step": 494820 }, { "epoch": 2.9413722797819664, "grad_norm": 3.9686760902404785, "learning_rate": 4.3339955399064374e-06, "loss": 0.0802, "step": 494830 }, { "epoch": 2.9414317218586348, "grad_norm": 4.169111728668213, "learning_rate": 4.333789897302666e-06, "loss": 0.0967, "step": 494840 }, { "epoch": 2.941491163935303, "grad_norm": 3.297659158706665, "learning_rate": 4.333584255846188e-06, "loss": 0.094, "step": 494850 }, { "epoch": 2.9415506060119716, "grad_norm": 3.355799674987793, "learning_rate": 4.333378615537355e-06, "loss": 0.0992, "step": 494860 }, { "epoch": 2.94161004808864, "grad_norm": 2.5071656703948975, "learning_rate": 4.333172976376525e-06, "loss": 0.0907, "step": 494870 }, { "epoch": 2.9416694901653084, "grad_norm": 3.5271708965301514, "learning_rate": 4.332967338364051e-06, "loss": 0.1169, "step": 494880 }, { "epoch": 2.941728932241977, "grad_norm": 2.886746883392334, "learning_rate": 4.3327617015002874e-06, "loss": 0.1074, "step": 494890 }, { "epoch": 2.9417883743186453, "grad_norm": 4.8418660163879395, "learning_rate": 4.3325560657855875e-06, "loss": 0.1004, "step": 494900 }, { "epoch": 2.9418478163953137, "grad_norm": 4.3801140785217285, "learning_rate": 4.3323504312203045e-06, "loss": 0.1101, "step": 494910 }, { "epoch": 2.941907258471982, "grad_norm": 2.660386562347412, "learning_rate": 4.332144797804795e-06, "loss": 0.0849, "step": 494920 }, { "epoch": 2.9419667005486505, "grad_norm": 4.895031452178955, "learning_rate": 4.331939165539412e-06, "loss": 0.1114, "step": 494930 }, { "epoch": 2.942026142625319, "grad_norm": 4.889702320098877, "learning_rate": 4.331733534424509e-06, "loss": 0.0931, "step": 494940 }, { "epoch": 2.942085584701987, "grad_norm": 5.075671195983887, "learning_rate": 4.331527904460441e-06, "loss": 0.1108, "step": 494950 }, { "epoch": 2.9421450267786557, "grad_norm": 4.5568671226501465, "learning_rate": 4.331322275647562e-06, "loss": 0.1053, "step": 494960 }, { "epoch": 2.9422044688553237, "grad_norm": 4.5484724044799805, "learning_rate": 4.331116647986224e-06, "loss": 0.0979, "step": 494970 }, { "epoch": 2.9422639109319926, "grad_norm": 4.361313343048096, "learning_rate": 4.330911021476784e-06, "loss": 0.1102, "step": 494980 }, { "epoch": 2.9423233530086605, "grad_norm": 3.609323024749756, "learning_rate": 4.3307053961195955e-06, "loss": 0.0959, "step": 494990 }, { "epoch": 2.942382795085329, "grad_norm": 4.605201244354248, "learning_rate": 4.330499771915011e-06, "loss": 0.1037, "step": 495000 } ], "logging_steps": 10, "max_steps": 841155, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2.2667066769095524e+19, "train_batch_size": 4, "trial_name": null, "trial_params": null }