{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 7704, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00025960539979231567, "grad_norm": 52.95064163208008, "learning_rate": 0.0, "loss": 0.9218449592590332, "step": 1 }, { "epoch": 0.0005192107995846313, "grad_norm": 43.45841598510742, "learning_rate": 2.1551724137931035e-08, "loss": 0.9805830717086792, "step": 2 }, { "epoch": 0.000778816199376947, "grad_norm": 50.96870422363281, "learning_rate": 4.310344827586207e-08, "loss": 1.044830560684204, "step": 3 }, { "epoch": 0.0010384215991692627, "grad_norm": 54.68854904174805, "learning_rate": 6.465517241379311e-08, "loss": 0.9182177782058716, "step": 4 }, { "epoch": 0.0012980269989615785, "grad_norm": 48.79996109008789, "learning_rate": 8.620689655172414e-08, "loss": 1.0359219312667847, "step": 5 }, { "epoch": 0.001557632398753894, "grad_norm": 39.549034118652344, "learning_rate": 1.0775862068965518e-07, "loss": 0.9573643803596497, "step": 6 }, { "epoch": 0.0018172377985462098, "grad_norm": 61.862083435058594, "learning_rate": 1.2931034482758622e-07, "loss": 1.0588597059249878, "step": 7 }, { "epoch": 0.0020768431983385254, "grad_norm": 48.61808776855469, "learning_rate": 1.5086206896551727e-07, "loss": 0.8744407296180725, "step": 8 }, { "epoch": 0.002336448598130841, "grad_norm": 47.786502838134766, "learning_rate": 1.7241379310344828e-07, "loss": 0.8848466873168945, "step": 9 }, { "epoch": 0.002596053997923157, "grad_norm": 41.55780029296875, "learning_rate": 1.9396551724137932e-07, "loss": 0.9748907089233398, "step": 10 }, { "epoch": 0.0028556593977154725, "grad_norm": 36.76769256591797, "learning_rate": 2.1551724137931036e-07, "loss": 0.9656479954719543, "step": 11 }, { "epoch": 0.003115264797507788, "grad_norm": 46.2722053527832, "learning_rate": 2.3706896551724138e-07, "loss": 0.9733672738075256, "step": 12 }, { "epoch": 0.0033748701973001036, "grad_norm": 51.1312255859375, "learning_rate": 2.5862068965517245e-07, "loss": 0.9227988719940186, "step": 13 }, { "epoch": 0.0036344755970924196, "grad_norm": 48.04316711425781, "learning_rate": 2.801724137931035e-07, "loss": 0.8341588973999023, "step": 14 }, { "epoch": 0.003894080996884735, "grad_norm": 33.93716812133789, "learning_rate": 3.0172413793103453e-07, "loss": 0.9777110815048218, "step": 15 }, { "epoch": 0.004153686396677051, "grad_norm": 43.618099212646484, "learning_rate": 3.2327586206896557e-07, "loss": 0.774552583694458, "step": 16 }, { "epoch": 0.004413291796469367, "grad_norm": 38.67876434326172, "learning_rate": 3.4482758620689656e-07, "loss": 0.9376569986343384, "step": 17 }, { "epoch": 0.004672897196261682, "grad_norm": 28.343490600585938, "learning_rate": 3.663793103448276e-07, "loss": 0.9357712268829346, "step": 18 }, { "epoch": 0.004932502596053998, "grad_norm": 37.590328216552734, "learning_rate": 3.8793103448275865e-07, "loss": 0.9334999322891235, "step": 19 }, { "epoch": 0.005192107995846314, "grad_norm": 22.076416015625, "learning_rate": 4.094827586206897e-07, "loss": 0.7404043674468994, "step": 20 }, { "epoch": 0.005451713395638629, "grad_norm": 18.396305084228516, "learning_rate": 4.3103448275862073e-07, "loss": 0.7013035416603088, "step": 21 }, { "epoch": 0.005711318795430945, "grad_norm": 21.46253204345703, "learning_rate": 4.5258620689655177e-07, "loss": 0.7520222067832947, "step": 22 }, { "epoch": 0.005970924195223261, "grad_norm": 43.764068603515625, "learning_rate": 4.7413793103448276e-07, "loss": 0.8759156465530396, "step": 23 }, { "epoch": 0.006230529595015576, "grad_norm": 21.75173568725586, "learning_rate": 4.956896551724138e-07, "loss": 0.731823205947876, "step": 24 }, { "epoch": 0.006490134994807892, "grad_norm": 28.290224075317383, "learning_rate": 5.172413793103449e-07, "loss": 0.818437933921814, "step": 25 }, { "epoch": 0.006749740394600207, "grad_norm": 26.148454666137695, "learning_rate": 5.387931034482759e-07, "loss": 0.8004028797149658, "step": 26 }, { "epoch": 0.007009345794392523, "grad_norm": 38.599876403808594, "learning_rate": 5.60344827586207e-07, "loss": 0.7293272614479065, "step": 27 }, { "epoch": 0.007268951194184839, "grad_norm": 21.99490737915039, "learning_rate": 5.81896551724138e-07, "loss": 0.7279325723648071, "step": 28 }, { "epoch": 0.007528556593977154, "grad_norm": 28.853933334350586, "learning_rate": 6.034482758620691e-07, "loss": 0.8423474431037903, "step": 29 }, { "epoch": 0.00778816199376947, "grad_norm": 18.938522338867188, "learning_rate": 6.25e-07, "loss": 0.8166996240615845, "step": 30 }, { "epoch": 0.008047767393561786, "grad_norm": 18.036907196044922, "learning_rate": 6.465517241379311e-07, "loss": 0.8423513174057007, "step": 31 }, { "epoch": 0.008307372793354102, "grad_norm": 17.096742630004883, "learning_rate": 6.68103448275862e-07, "loss": 0.7242676019668579, "step": 32 }, { "epoch": 0.008566978193146417, "grad_norm": 14.405272483825684, "learning_rate": 6.896551724137931e-07, "loss": 0.6401216387748718, "step": 33 }, { "epoch": 0.008826583592938734, "grad_norm": 19.49250030517578, "learning_rate": 7.112068965517242e-07, "loss": 0.6172772645950317, "step": 34 }, { "epoch": 0.009086188992731049, "grad_norm": 19.207569122314453, "learning_rate": 7.327586206896552e-07, "loss": 0.7186360359191895, "step": 35 }, { "epoch": 0.009345794392523364, "grad_norm": 17.730302810668945, "learning_rate": 7.543103448275863e-07, "loss": 0.7905684113502502, "step": 36 }, { "epoch": 0.00960539979231568, "grad_norm": 22.74924087524414, "learning_rate": 7.758620689655173e-07, "loss": 0.7959986925125122, "step": 37 }, { "epoch": 0.009865005192107996, "grad_norm": 16.366973876953125, "learning_rate": 7.974137931034484e-07, "loss": 0.7054300308227539, "step": 38 }, { "epoch": 0.010124610591900311, "grad_norm": 14.962441444396973, "learning_rate": 8.189655172413794e-07, "loss": 0.7866121530532837, "step": 39 }, { "epoch": 0.010384215991692628, "grad_norm": 13.327448844909668, "learning_rate": 8.405172413793105e-07, "loss": 0.576513409614563, "step": 40 }, { "epoch": 0.010643821391484943, "grad_norm": 20.14197540283203, "learning_rate": 8.620689655172415e-07, "loss": 0.6791664361953735, "step": 41 }, { "epoch": 0.010903426791277258, "grad_norm": 14.834797859191895, "learning_rate": 8.836206896551724e-07, "loss": 0.695242166519165, "step": 42 }, { "epoch": 0.011163032191069575, "grad_norm": 28.792606353759766, "learning_rate": 9.051724137931035e-07, "loss": 0.784297525882721, "step": 43 }, { "epoch": 0.01142263759086189, "grad_norm": 13.960169792175293, "learning_rate": 9.267241379310346e-07, "loss": 0.6099745631217957, "step": 44 }, { "epoch": 0.011682242990654205, "grad_norm": 13.477916717529297, "learning_rate": 9.482758620689655e-07, "loss": 0.569471538066864, "step": 45 }, { "epoch": 0.011941848390446522, "grad_norm": 14.44013500213623, "learning_rate": 9.698275862068966e-07, "loss": 0.6228048801422119, "step": 46 }, { "epoch": 0.012201453790238837, "grad_norm": 19.150848388671875, "learning_rate": 9.913793103448276e-07, "loss": 0.6284147500991821, "step": 47 }, { "epoch": 0.012461059190031152, "grad_norm": 11.891578674316406, "learning_rate": 1.0129310344827586e-06, "loss": 0.6327741742134094, "step": 48 }, { "epoch": 0.01272066458982347, "grad_norm": 24.986421585083008, "learning_rate": 1.0344827586206898e-06, "loss": 0.6736770868301392, "step": 49 }, { "epoch": 0.012980269989615784, "grad_norm": 11.077199935913086, "learning_rate": 1.0560344827586208e-06, "loss": 0.5445423722267151, "step": 50 }, { "epoch": 0.0132398753894081, "grad_norm": 12.274765968322754, "learning_rate": 1.0775862068965518e-06, "loss": 0.5630475282669067, "step": 51 }, { "epoch": 0.013499480789200415, "grad_norm": 8.067819595336914, "learning_rate": 1.0991379310344828e-06, "loss": 0.5180734395980835, "step": 52 }, { "epoch": 0.013759086188992731, "grad_norm": 16.52487564086914, "learning_rate": 1.120689655172414e-06, "loss": 0.5658445358276367, "step": 53 }, { "epoch": 0.014018691588785047, "grad_norm": 14.336048126220703, "learning_rate": 1.142241379310345e-06, "loss": 0.6525071263313293, "step": 54 }, { "epoch": 0.014278296988577362, "grad_norm": 18.131855010986328, "learning_rate": 1.163793103448276e-06, "loss": 0.6700636744499207, "step": 55 }, { "epoch": 0.014537902388369679, "grad_norm": 11.25307559967041, "learning_rate": 1.185344827586207e-06, "loss": 0.6031025648117065, "step": 56 }, { "epoch": 0.014797507788161994, "grad_norm": 14.610969543457031, "learning_rate": 1.2068965517241381e-06, "loss": 0.7051005363464355, "step": 57 }, { "epoch": 0.015057113187954309, "grad_norm": 26.961383819580078, "learning_rate": 1.2284482758620691e-06, "loss": 0.757234513759613, "step": 58 }, { "epoch": 0.015316718587746626, "grad_norm": 20.935632705688477, "learning_rate": 1.25e-06, "loss": 0.5384839177131653, "step": 59 }, { "epoch": 0.01557632398753894, "grad_norm": 18.386457443237305, "learning_rate": 1.271551724137931e-06, "loss": 0.618147611618042, "step": 60 }, { "epoch": 0.015835929387331256, "grad_norm": 16.571044921875, "learning_rate": 1.2931034482758623e-06, "loss": 0.6291083097457886, "step": 61 }, { "epoch": 0.016095534787123573, "grad_norm": 9.114740371704102, "learning_rate": 1.3146551724137933e-06, "loss": 0.5239481925964355, "step": 62 }, { "epoch": 0.016355140186915886, "grad_norm": 10.30048942565918, "learning_rate": 1.336206896551724e-06, "loss": 0.5930582284927368, "step": 63 }, { "epoch": 0.016614745586708203, "grad_norm": 29.334369659423828, "learning_rate": 1.3577586206896553e-06, "loss": 0.6862934827804565, "step": 64 }, { "epoch": 0.01687435098650052, "grad_norm": 19.739490509033203, "learning_rate": 1.3793103448275862e-06, "loss": 0.6805461049079895, "step": 65 }, { "epoch": 0.017133956386292833, "grad_norm": 9.630888938903809, "learning_rate": 1.4008620689655172e-06, "loss": 0.5202924013137817, "step": 66 }, { "epoch": 0.01739356178608515, "grad_norm": 12.646147727966309, "learning_rate": 1.4224137931034484e-06, "loss": 0.5670164823532104, "step": 67 }, { "epoch": 0.017653167185877467, "grad_norm": 16.810386657714844, "learning_rate": 1.4439655172413794e-06, "loss": 0.7203819751739502, "step": 68 }, { "epoch": 0.01791277258566978, "grad_norm": 9.599488258361816, "learning_rate": 1.4655172413793104e-06, "loss": 0.5293265581130981, "step": 69 }, { "epoch": 0.018172377985462097, "grad_norm": 12.466961860656738, "learning_rate": 1.4870689655172416e-06, "loss": 0.5518414974212646, "step": 70 }, { "epoch": 0.018431983385254414, "grad_norm": 10.040395736694336, "learning_rate": 1.5086206896551726e-06, "loss": 0.5116457939147949, "step": 71 }, { "epoch": 0.018691588785046728, "grad_norm": 7.931884765625, "learning_rate": 1.5301724137931034e-06, "loss": 0.5225841999053955, "step": 72 }, { "epoch": 0.018951194184839044, "grad_norm": 23.140886306762695, "learning_rate": 1.5517241379310346e-06, "loss": 0.6155120134353638, "step": 73 }, { "epoch": 0.01921079958463136, "grad_norm": 13.1940336227417, "learning_rate": 1.5732758620689656e-06, "loss": 0.6251787543296814, "step": 74 }, { "epoch": 0.019470404984423675, "grad_norm": 9.37828254699707, "learning_rate": 1.5948275862068968e-06, "loss": 0.5007927417755127, "step": 75 }, { "epoch": 0.01973001038421599, "grad_norm": 9.512657165527344, "learning_rate": 1.6163793103448278e-06, "loss": 0.5362178087234497, "step": 76 }, { "epoch": 0.01998961578400831, "grad_norm": 13.132498741149902, "learning_rate": 1.6379310344827587e-06, "loss": 0.6391939520835876, "step": 77 }, { "epoch": 0.020249221183800622, "grad_norm": 10.66916561126709, "learning_rate": 1.65948275862069e-06, "loss": 0.5261664986610413, "step": 78 }, { "epoch": 0.02050882658359294, "grad_norm": 9.192667961120605, "learning_rate": 1.681034482758621e-06, "loss": 0.6559566855430603, "step": 79 }, { "epoch": 0.020768431983385256, "grad_norm": 12.455215454101562, "learning_rate": 1.7025862068965517e-06, "loss": 0.6216788291931152, "step": 80 }, { "epoch": 0.02102803738317757, "grad_norm": 7.669570446014404, "learning_rate": 1.724137931034483e-06, "loss": 0.5111876130104065, "step": 81 }, { "epoch": 0.021287642782969886, "grad_norm": 6.602768898010254, "learning_rate": 1.745689655172414e-06, "loss": 0.4953393340110779, "step": 82 }, { "epoch": 0.021547248182762203, "grad_norm": 26.83995819091797, "learning_rate": 1.7672413793103449e-06, "loss": 0.6693631410598755, "step": 83 }, { "epoch": 0.021806853582554516, "grad_norm": 10.578999519348145, "learning_rate": 1.788793103448276e-06, "loss": 0.5690029263496399, "step": 84 }, { "epoch": 0.022066458982346833, "grad_norm": 9.404824256896973, "learning_rate": 1.810344827586207e-06, "loss": 0.6044996976852417, "step": 85 }, { "epoch": 0.02232606438213915, "grad_norm": 13.576065063476562, "learning_rate": 1.831896551724138e-06, "loss": 0.6380812525749207, "step": 86 }, { "epoch": 0.022585669781931463, "grad_norm": 12.766021728515625, "learning_rate": 1.8534482758620693e-06, "loss": 0.5696926712989807, "step": 87 }, { "epoch": 0.02284527518172378, "grad_norm": 16.059598922729492, "learning_rate": 1.8750000000000003e-06, "loss": 0.6084990501403809, "step": 88 }, { "epoch": 0.023104880581516097, "grad_norm": 9.45837116241455, "learning_rate": 1.896551724137931e-06, "loss": 0.5122504830360413, "step": 89 }, { "epoch": 0.02336448598130841, "grad_norm": 9.476510047912598, "learning_rate": 1.9181034482758622e-06, "loss": 0.5505548715591431, "step": 90 }, { "epoch": 0.023624091381100727, "grad_norm": 18.016042709350586, "learning_rate": 1.9396551724137932e-06, "loss": 0.6015290021896362, "step": 91 }, { "epoch": 0.023883696780893044, "grad_norm": 8.81105899810791, "learning_rate": 1.9612068965517242e-06, "loss": 0.5948615074157715, "step": 92 }, { "epoch": 0.024143302180685357, "grad_norm": 7.256336212158203, "learning_rate": 1.982758620689655e-06, "loss": 0.4838152825832367, "step": 93 }, { "epoch": 0.024402907580477674, "grad_norm": 20.724254608154297, "learning_rate": 2.004310344827586e-06, "loss": 0.537036657333374, "step": 94 }, { "epoch": 0.02466251298026999, "grad_norm": 11.5702486038208, "learning_rate": 2.025862068965517e-06, "loss": 0.4926948547363281, "step": 95 }, { "epoch": 0.024922118380062305, "grad_norm": 10.442184448242188, "learning_rate": 2.0474137931034486e-06, "loss": 0.49402886629104614, "step": 96 }, { "epoch": 0.02518172377985462, "grad_norm": 15.714273452758789, "learning_rate": 2.0689655172413796e-06, "loss": 0.5278142094612122, "step": 97 }, { "epoch": 0.02544132917964694, "grad_norm": 17.06800651550293, "learning_rate": 2.0905172413793106e-06, "loss": 0.5932591557502747, "step": 98 }, { "epoch": 0.02570093457943925, "grad_norm": 5.083622932434082, "learning_rate": 2.1120689655172416e-06, "loss": 0.49112480878829956, "step": 99 }, { "epoch": 0.02596053997923157, "grad_norm": 8.93824291229248, "learning_rate": 2.1336206896551725e-06, "loss": 0.4872360825538635, "step": 100 }, { "epoch": 0.026220145379023882, "grad_norm": 14.683554649353027, "learning_rate": 2.1551724137931035e-06, "loss": 0.5032896399497986, "step": 101 }, { "epoch": 0.0264797507788162, "grad_norm": 13.358648300170898, "learning_rate": 2.1767241379310345e-06, "loss": 0.5802744030952454, "step": 102 }, { "epoch": 0.026739356178608516, "grad_norm": 8.697710037231445, "learning_rate": 2.1982758620689655e-06, "loss": 0.5444199442863464, "step": 103 }, { "epoch": 0.02699896157840083, "grad_norm": 8.88721752166748, "learning_rate": 2.219827586206897e-06, "loss": 0.4805337190628052, "step": 104 }, { "epoch": 0.027258566978193146, "grad_norm": 10.682084083557129, "learning_rate": 2.241379310344828e-06, "loss": 0.6105116009712219, "step": 105 }, { "epoch": 0.027518172377985463, "grad_norm": 23.784019470214844, "learning_rate": 2.262931034482759e-06, "loss": 0.5964369773864746, "step": 106 }, { "epoch": 0.027777777777777776, "grad_norm": 9.165786743164062, "learning_rate": 2.28448275862069e-06, "loss": 0.48336073756217957, "step": 107 }, { "epoch": 0.028037383177570093, "grad_norm": 6.773464679718018, "learning_rate": 2.306034482758621e-06, "loss": 0.45280352234840393, "step": 108 }, { "epoch": 0.02829698857736241, "grad_norm": 6.41490364074707, "learning_rate": 2.327586206896552e-06, "loss": 0.47768479585647583, "step": 109 }, { "epoch": 0.028556593977154723, "grad_norm": 10.192892074584961, "learning_rate": 2.349137931034483e-06, "loss": 0.6537889242172241, "step": 110 }, { "epoch": 0.02881619937694704, "grad_norm": 11.992843627929688, "learning_rate": 2.370689655172414e-06, "loss": 0.6832633018493652, "step": 111 }, { "epoch": 0.029075804776739357, "grad_norm": 10.902897834777832, "learning_rate": 2.392241379310345e-06, "loss": 0.5725653171539307, "step": 112 }, { "epoch": 0.02933541017653167, "grad_norm": 11.181191444396973, "learning_rate": 2.4137931034482762e-06, "loss": 0.6211100816726685, "step": 113 }, { "epoch": 0.029595015576323987, "grad_norm": 7.867948532104492, "learning_rate": 2.4353448275862072e-06, "loss": 0.5076699256896973, "step": 114 }, { "epoch": 0.029854620976116304, "grad_norm": 9.150169372558594, "learning_rate": 2.4568965517241382e-06, "loss": 0.5396093726158142, "step": 115 }, { "epoch": 0.030114226375908618, "grad_norm": 8.268501281738281, "learning_rate": 2.4784482758620692e-06, "loss": 0.5824679732322693, "step": 116 }, { "epoch": 0.030373831775700934, "grad_norm": 8.15254020690918, "learning_rate": 2.5e-06, "loss": 0.4682742655277252, "step": 117 }, { "epoch": 0.03063343717549325, "grad_norm": 13.69393539428711, "learning_rate": 2.521551724137931e-06, "loss": 0.6274590492248535, "step": 118 }, { "epoch": 0.030893042575285565, "grad_norm": 12.284512519836426, "learning_rate": 2.543103448275862e-06, "loss": 0.5924288630485535, "step": 119 }, { "epoch": 0.03115264797507788, "grad_norm": 12.697639465332031, "learning_rate": 2.5646551724137936e-06, "loss": 0.464116632938385, "step": 120 }, { "epoch": 0.0314122533748702, "grad_norm": 15.722908973693848, "learning_rate": 2.5862068965517246e-06, "loss": 0.6499549150466919, "step": 121 }, { "epoch": 0.03167185877466251, "grad_norm": 7.660727500915527, "learning_rate": 2.6077586206896556e-06, "loss": 0.5137507915496826, "step": 122 }, { "epoch": 0.031931464174454825, "grad_norm": 13.89177417755127, "learning_rate": 2.6293103448275866e-06, "loss": 0.4974368214607239, "step": 123 }, { "epoch": 0.032191069574247146, "grad_norm": 11.631704330444336, "learning_rate": 2.6508620689655175e-06, "loss": 0.5090399384498596, "step": 124 }, { "epoch": 0.03245067497403946, "grad_norm": 17.99962615966797, "learning_rate": 2.672413793103448e-06, "loss": 0.6659072041511536, "step": 125 }, { "epoch": 0.03271028037383177, "grad_norm": 5.902799606323242, "learning_rate": 2.69396551724138e-06, "loss": 0.4606205224990845, "step": 126 }, { "epoch": 0.03296988577362409, "grad_norm": 16.099905014038086, "learning_rate": 2.7155172413793105e-06, "loss": 0.6000686287879944, "step": 127 }, { "epoch": 0.033229491173416406, "grad_norm": 12.726068496704102, "learning_rate": 2.7370689655172415e-06, "loss": 0.5121291875839233, "step": 128 }, { "epoch": 0.03348909657320872, "grad_norm": 13.02841567993164, "learning_rate": 2.7586206896551725e-06, "loss": 0.563969075679779, "step": 129 }, { "epoch": 0.03374870197300104, "grad_norm": 6.382338523864746, "learning_rate": 2.7801724137931035e-06, "loss": 0.5091010332107544, "step": 130 }, { "epoch": 0.03400830737279335, "grad_norm": 6.360717296600342, "learning_rate": 2.8017241379310345e-06, "loss": 0.474850594997406, "step": 131 }, { "epoch": 0.03426791277258567, "grad_norm": 16.744916915893555, "learning_rate": 2.823275862068966e-06, "loss": 0.5831856727600098, "step": 132 }, { "epoch": 0.03452751817237799, "grad_norm": 14.407731056213379, "learning_rate": 2.844827586206897e-06, "loss": 0.538408637046814, "step": 133 }, { "epoch": 0.0347871235721703, "grad_norm": 6.181216716766357, "learning_rate": 2.866379310344828e-06, "loss": 0.46893221139907837, "step": 134 }, { "epoch": 0.035046728971962614, "grad_norm": 16.212785720825195, "learning_rate": 2.887931034482759e-06, "loss": 0.5305911302566528, "step": 135 }, { "epoch": 0.035306334371754934, "grad_norm": 10.712382316589355, "learning_rate": 2.90948275862069e-06, "loss": 0.5700230002403259, "step": 136 }, { "epoch": 0.03556593977154725, "grad_norm": 9.12829875946045, "learning_rate": 2.931034482758621e-06, "loss": 0.5813370943069458, "step": 137 }, { "epoch": 0.03582554517133956, "grad_norm": 9.42685604095459, "learning_rate": 2.9525862068965522e-06, "loss": 0.5042760968208313, "step": 138 }, { "epoch": 0.03608515057113188, "grad_norm": 8.21872615814209, "learning_rate": 2.9741379310344832e-06, "loss": 0.5089861750602722, "step": 139 }, { "epoch": 0.036344755970924195, "grad_norm": 12.909751892089844, "learning_rate": 2.9956896551724142e-06, "loss": 0.5791746973991394, "step": 140 }, { "epoch": 0.03660436137071651, "grad_norm": 17.688438415527344, "learning_rate": 3.017241379310345e-06, "loss": 0.6827187538146973, "step": 141 }, { "epoch": 0.03686396677050883, "grad_norm": 11.590710639953613, "learning_rate": 3.0387931034482758e-06, "loss": 0.5218712091445923, "step": 142 }, { "epoch": 0.03712357217030114, "grad_norm": 6.30613899230957, "learning_rate": 3.0603448275862068e-06, "loss": 0.4652702808380127, "step": 143 }, { "epoch": 0.037383177570093455, "grad_norm": 14.4529390335083, "learning_rate": 3.081896551724138e-06, "loss": 0.5551283359527588, "step": 144 }, { "epoch": 0.037642782969885775, "grad_norm": 10.011333465576172, "learning_rate": 3.103448275862069e-06, "loss": 0.482838898897171, "step": 145 }, { "epoch": 0.03790238836967809, "grad_norm": 6.831842422485352, "learning_rate": 3.125e-06, "loss": 0.48882636427879333, "step": 146 }, { "epoch": 0.0381619937694704, "grad_norm": 10.033903121948242, "learning_rate": 3.146551724137931e-06, "loss": 0.5958304405212402, "step": 147 }, { "epoch": 0.03842159916926272, "grad_norm": 8.500994682312012, "learning_rate": 3.168103448275862e-06, "loss": 0.6274945139884949, "step": 148 }, { "epoch": 0.038681204569055036, "grad_norm": 10.3060941696167, "learning_rate": 3.1896551724137935e-06, "loss": 0.4621858596801758, "step": 149 }, { "epoch": 0.03894080996884735, "grad_norm": 11.277793884277344, "learning_rate": 3.2112068965517245e-06, "loss": 0.5049821138381958, "step": 150 }, { "epoch": 0.03920041536863967, "grad_norm": 8.109270095825195, "learning_rate": 3.2327586206896555e-06, "loss": 0.5190414190292358, "step": 151 }, { "epoch": 0.03946002076843198, "grad_norm": 13.01602840423584, "learning_rate": 3.2543103448275865e-06, "loss": 0.5926713943481445, "step": 152 }, { "epoch": 0.0397196261682243, "grad_norm": 6.9089741706848145, "learning_rate": 3.2758620689655175e-06, "loss": 0.48134124279022217, "step": 153 }, { "epoch": 0.03997923156801662, "grad_norm": 8.45062255859375, "learning_rate": 3.2974137931034485e-06, "loss": 0.46075814962387085, "step": 154 }, { "epoch": 0.04023883696780893, "grad_norm": 9.49884033203125, "learning_rate": 3.31896551724138e-06, "loss": 0.47138848900794983, "step": 155 }, { "epoch": 0.040498442367601244, "grad_norm": 5.922605037689209, "learning_rate": 3.340517241379311e-06, "loss": 0.4864259958267212, "step": 156 }, { "epoch": 0.040758047767393564, "grad_norm": 12.541130065917969, "learning_rate": 3.362068965517242e-06, "loss": 0.5344440937042236, "step": 157 }, { "epoch": 0.04101765316718588, "grad_norm": 10.93248462677002, "learning_rate": 3.383620689655173e-06, "loss": 0.5731430649757385, "step": 158 }, { "epoch": 0.04127725856697819, "grad_norm": 11.401576042175293, "learning_rate": 3.4051724137931034e-06, "loss": 0.4945701062679291, "step": 159 }, { "epoch": 0.04153686396677051, "grad_norm": 14.718060493469238, "learning_rate": 3.4267241379310344e-06, "loss": 0.5244559645652771, "step": 160 }, { "epoch": 0.041796469366562825, "grad_norm": 8.086901664733887, "learning_rate": 3.448275862068966e-06, "loss": 0.4490375518798828, "step": 161 }, { "epoch": 0.04205607476635514, "grad_norm": 21.52174949645996, "learning_rate": 3.469827586206897e-06, "loss": 0.6390911340713501, "step": 162 }, { "epoch": 0.04231568016614746, "grad_norm": 8.351300239562988, "learning_rate": 3.491379310344828e-06, "loss": 0.47338661551475525, "step": 163 }, { "epoch": 0.04257528556593977, "grad_norm": 5.198214530944824, "learning_rate": 3.512931034482759e-06, "loss": 0.5086630582809448, "step": 164 }, { "epoch": 0.042834890965732085, "grad_norm": 7.649577617645264, "learning_rate": 3.5344827586206898e-06, "loss": 0.6123409867286682, "step": 165 }, { "epoch": 0.043094496365524405, "grad_norm": 8.862589836120605, "learning_rate": 3.5560344827586208e-06, "loss": 0.5774891376495361, "step": 166 }, { "epoch": 0.04335410176531672, "grad_norm": 11.112674713134766, "learning_rate": 3.577586206896552e-06, "loss": 0.571959376335144, "step": 167 }, { "epoch": 0.04361370716510903, "grad_norm": 7.440353870391846, "learning_rate": 3.599137931034483e-06, "loss": 0.5724345445632935, "step": 168 }, { "epoch": 0.04387331256490135, "grad_norm": 8.309920310974121, "learning_rate": 3.620689655172414e-06, "loss": 0.6209840178489685, "step": 169 }, { "epoch": 0.044132917964693666, "grad_norm": 10.579856872558594, "learning_rate": 3.642241379310345e-06, "loss": 0.6188914775848389, "step": 170 }, { "epoch": 0.04439252336448598, "grad_norm": 4.234836101531982, "learning_rate": 3.663793103448276e-06, "loss": 0.5013940930366516, "step": 171 }, { "epoch": 0.0446521287642783, "grad_norm": 10.696198463439941, "learning_rate": 3.685344827586207e-06, "loss": 0.6934300661087036, "step": 172 }, { "epoch": 0.04491173416407061, "grad_norm": 6.392653942108154, "learning_rate": 3.7068965517241385e-06, "loss": 0.4877658486366272, "step": 173 }, { "epoch": 0.045171339563862926, "grad_norm": 10.876198768615723, "learning_rate": 3.7284482758620695e-06, "loss": 0.47988978028297424, "step": 174 }, { "epoch": 0.04543094496365525, "grad_norm": 16.69538116455078, "learning_rate": 3.7500000000000005e-06, "loss": 0.5274117588996887, "step": 175 }, { "epoch": 0.04569055036344756, "grad_norm": 5.2049970626831055, "learning_rate": 3.771551724137931e-06, "loss": 0.46596017479896545, "step": 176 }, { "epoch": 0.045950155763239874, "grad_norm": 12.917200088500977, "learning_rate": 3.793103448275862e-06, "loss": 0.6138955354690552, "step": 177 }, { "epoch": 0.046209761163032194, "grad_norm": 7.281108379364014, "learning_rate": 3.8146551724137935e-06, "loss": 0.48304885625839233, "step": 178 }, { "epoch": 0.04646936656282451, "grad_norm": 6.060185432434082, "learning_rate": 3.8362068965517245e-06, "loss": 0.5063158273696899, "step": 179 }, { "epoch": 0.04672897196261682, "grad_norm": 5.4326653480529785, "learning_rate": 3.857758620689656e-06, "loss": 0.5380522608757019, "step": 180 }, { "epoch": 0.04698857736240914, "grad_norm": 17.01052474975586, "learning_rate": 3.8793103448275865e-06, "loss": 0.6554906964302063, "step": 181 }, { "epoch": 0.047248182762201454, "grad_norm": 9.227376937866211, "learning_rate": 3.900862068965518e-06, "loss": 0.46015793085098267, "step": 182 }, { "epoch": 0.04750778816199377, "grad_norm": 15.383655548095703, "learning_rate": 3.9224137931034484e-06, "loss": 0.5453649163246155, "step": 183 }, { "epoch": 0.04776739356178609, "grad_norm": 8.737911224365234, "learning_rate": 3.94396551724138e-06, "loss": 0.46557313203811646, "step": 184 }, { "epoch": 0.0480269989615784, "grad_norm": 10.104972839355469, "learning_rate": 3.96551724137931e-06, "loss": 0.5587508678436279, "step": 185 }, { "epoch": 0.048286604361370715, "grad_norm": 4.225912570953369, "learning_rate": 3.987068965517242e-06, "loss": 0.4620315134525299, "step": 186 }, { "epoch": 0.048546209761163035, "grad_norm": 4.00620174407959, "learning_rate": 4.008620689655172e-06, "loss": 0.4547384977340698, "step": 187 }, { "epoch": 0.04880581516095535, "grad_norm": 5.045581817626953, "learning_rate": 4.030172413793104e-06, "loss": 0.4791070818901062, "step": 188 }, { "epoch": 0.04906542056074766, "grad_norm": 3.995614528656006, "learning_rate": 4.051724137931034e-06, "loss": 0.4661255478858948, "step": 189 }, { "epoch": 0.04932502596053998, "grad_norm": 6.960451126098633, "learning_rate": 4.073275862068966e-06, "loss": 0.47747206687927246, "step": 190 }, { "epoch": 0.049584631360332296, "grad_norm": 4.307006359100342, "learning_rate": 4.094827586206897e-06, "loss": 0.4339630603790283, "step": 191 }, { "epoch": 0.04984423676012461, "grad_norm": 9.172281265258789, "learning_rate": 4.116379310344828e-06, "loss": 0.5533125400543213, "step": 192 }, { "epoch": 0.05010384215991693, "grad_norm": 10.174232482910156, "learning_rate": 4.137931034482759e-06, "loss": 0.5245087146759033, "step": 193 }, { "epoch": 0.05036344755970924, "grad_norm": 5.538793563842773, "learning_rate": 4.15948275862069e-06, "loss": 0.5096902251243591, "step": 194 }, { "epoch": 0.050623052959501556, "grad_norm": 6.868093967437744, "learning_rate": 4.181034482758621e-06, "loss": 0.46046921610832214, "step": 195 }, { "epoch": 0.05088265835929388, "grad_norm": 5.507999420166016, "learning_rate": 4.2025862068965526e-06, "loss": 0.5360122919082642, "step": 196 }, { "epoch": 0.05114226375908619, "grad_norm": 6.076210021972656, "learning_rate": 4.224137931034483e-06, "loss": 0.4926278293132782, "step": 197 }, { "epoch": 0.0514018691588785, "grad_norm": 6.630780220031738, "learning_rate": 4.2456896551724145e-06, "loss": 0.4619036614894867, "step": 198 }, { "epoch": 0.051661474558670824, "grad_norm": 8.408929824829102, "learning_rate": 4.267241379310345e-06, "loss": 0.5544939637184143, "step": 199 }, { "epoch": 0.05192107995846314, "grad_norm": 4.777322292327881, "learning_rate": 4.288793103448276e-06, "loss": 0.5919787287712097, "step": 200 }, { "epoch": 0.05218068535825545, "grad_norm": 6.099384784698486, "learning_rate": 4.310344827586207e-06, "loss": 0.5260531902313232, "step": 201 }, { "epoch": 0.052440290758047764, "grad_norm": 12.723488807678223, "learning_rate": 4.3318965517241385e-06, "loss": 0.5449131727218628, "step": 202 }, { "epoch": 0.052699896157840084, "grad_norm": 8.124276161193848, "learning_rate": 4.353448275862069e-06, "loss": 0.5110676884651184, "step": 203 }, { "epoch": 0.0529595015576324, "grad_norm": 5.867123603820801, "learning_rate": 4.3750000000000005e-06, "loss": 0.490025132894516, "step": 204 }, { "epoch": 0.05321910695742471, "grad_norm": 11.777213096618652, "learning_rate": 4.396551724137931e-06, "loss": 0.6044182777404785, "step": 205 }, { "epoch": 0.05347871235721703, "grad_norm": 3.479003667831421, "learning_rate": 4.4181034482758624e-06, "loss": 0.43357545137405396, "step": 206 }, { "epoch": 0.053738317757009345, "grad_norm": 10.052297592163086, "learning_rate": 4.439655172413794e-06, "loss": 0.615355372428894, "step": 207 }, { "epoch": 0.05399792315680166, "grad_norm": 8.493797302246094, "learning_rate": 4.461206896551724e-06, "loss": 0.5337498188018799, "step": 208 }, { "epoch": 0.05425752855659398, "grad_norm": 5.92903995513916, "learning_rate": 4.482758620689656e-06, "loss": 0.5364860892295837, "step": 209 }, { "epoch": 0.05451713395638629, "grad_norm": 6.2485175132751465, "learning_rate": 4.504310344827586e-06, "loss": 0.4829055666923523, "step": 210 }, { "epoch": 0.054776739356178605, "grad_norm": 5.983491897583008, "learning_rate": 4.525862068965518e-06, "loss": 0.5921183228492737, "step": 211 }, { "epoch": 0.055036344755970926, "grad_norm": 7.497273921966553, "learning_rate": 4.547413793103448e-06, "loss": 0.5432143211364746, "step": 212 }, { "epoch": 0.05529595015576324, "grad_norm": 7.681201934814453, "learning_rate": 4.56896551724138e-06, "loss": 0.5294414162635803, "step": 213 }, { "epoch": 0.05555555555555555, "grad_norm": 8.961662292480469, "learning_rate": 4.590517241379311e-06, "loss": 0.4524787962436676, "step": 214 }, { "epoch": 0.05581516095534787, "grad_norm": 4.046236038208008, "learning_rate": 4.612068965517242e-06, "loss": 0.4877333641052246, "step": 215 }, { "epoch": 0.056074766355140186, "grad_norm": 8.55899429321289, "learning_rate": 4.633620689655173e-06, "loss": 0.5201913118362427, "step": 216 }, { "epoch": 0.0563343717549325, "grad_norm": 5.082372665405273, "learning_rate": 4.655172413793104e-06, "loss": 0.46447306871414185, "step": 217 }, { "epoch": 0.05659397715472482, "grad_norm": 6.107820510864258, "learning_rate": 4.676724137931034e-06, "loss": 0.45211490988731384, "step": 218 }, { "epoch": 0.05685358255451713, "grad_norm": 10.314708709716797, "learning_rate": 4.698275862068966e-06, "loss": 0.6953151226043701, "step": 219 }, { "epoch": 0.05711318795430945, "grad_norm": 7.427696704864502, "learning_rate": 4.719827586206897e-06, "loss": 0.49990513920783997, "step": 220 }, { "epoch": 0.05737279335410177, "grad_norm": 4.068686485290527, "learning_rate": 4.741379310344828e-06, "loss": 0.44849684834480286, "step": 221 }, { "epoch": 0.05763239875389408, "grad_norm": 5.294517517089844, "learning_rate": 4.762931034482759e-06, "loss": 0.4746742248535156, "step": 222 }, { "epoch": 0.057892004153686394, "grad_norm": 4.703131675720215, "learning_rate": 4.78448275862069e-06, "loss": 0.5142306089401245, "step": 223 }, { "epoch": 0.058151609553478714, "grad_norm": 9.116426467895508, "learning_rate": 4.806034482758621e-06, "loss": 0.4929184317588806, "step": 224 }, { "epoch": 0.05841121495327103, "grad_norm": 8.397038459777832, "learning_rate": 4.8275862068965525e-06, "loss": 0.5004661083221436, "step": 225 }, { "epoch": 0.05867082035306334, "grad_norm": 7.13994026184082, "learning_rate": 4.849137931034483e-06, "loss": 0.6161185503005981, "step": 226 }, { "epoch": 0.05893042575285566, "grad_norm": 10.058401107788086, "learning_rate": 4.8706896551724145e-06, "loss": 0.5449327826499939, "step": 227 }, { "epoch": 0.059190031152647975, "grad_norm": 5.612285614013672, "learning_rate": 4.892241379310345e-06, "loss": 0.5138067007064819, "step": 228 }, { "epoch": 0.05944963655244029, "grad_norm": 4.774786472320557, "learning_rate": 4.9137931034482765e-06, "loss": 0.5136839151382446, "step": 229 }, { "epoch": 0.05970924195223261, "grad_norm": 5.845010757446289, "learning_rate": 4.935344827586207e-06, "loss": 0.43986815214157104, "step": 230 }, { "epoch": 0.05996884735202492, "grad_norm": 4.017227649688721, "learning_rate": 4.9568965517241384e-06, "loss": 0.42265668511390686, "step": 231 }, { "epoch": 0.060228452751817235, "grad_norm": 10.515649795532227, "learning_rate": 4.97844827586207e-06, "loss": 0.5453312993049622, "step": 232 }, { "epoch": 0.060488058151609556, "grad_norm": 3.8743884563446045, "learning_rate": 5e-06, "loss": 0.5020509958267212, "step": 233 }, { "epoch": 0.06074766355140187, "grad_norm": 6.5010247230529785, "learning_rate": 4.99999980112576e-06, "loss": 0.5665720701217651, "step": 234 }, { "epoch": 0.06100726895119418, "grad_norm": 8.6032133102417, "learning_rate": 4.999999204503072e-06, "loss": 0.5249899625778198, "step": 235 }, { "epoch": 0.0612668743509865, "grad_norm": 7.327033519744873, "learning_rate": 4.999998210132044e-06, "loss": 0.47950196266174316, "step": 236 }, { "epoch": 0.061526479750778816, "grad_norm": 7.87631893157959, "learning_rate": 4.999996818012849e-06, "loss": 0.5476998090744019, "step": 237 }, { "epoch": 0.06178608515057113, "grad_norm": 5.554778099060059, "learning_rate": 4.999995028145735e-06, "loss": 0.5058318376541138, "step": 238 }, { "epoch": 0.06204569055036345, "grad_norm": 13.76960563659668, "learning_rate": 4.999992840531019e-06, "loss": 0.6479218602180481, "step": 239 }, { "epoch": 0.06230529595015576, "grad_norm": 7.699481010437012, "learning_rate": 4.999990255169086e-06, "loss": 0.5397629737854004, "step": 240 }, { "epoch": 0.06256490134994808, "grad_norm": 5.185218334197998, "learning_rate": 4.999987272060394e-06, "loss": 0.5415245890617371, "step": 241 }, { "epoch": 0.0628245067497404, "grad_norm": 7.541829586029053, "learning_rate": 4.999983891205471e-06, "loss": 0.48680374026298523, "step": 242 }, { "epoch": 0.0630841121495327, "grad_norm": 11.456315040588379, "learning_rate": 4.999980112604912e-06, "loss": 0.5698228478431702, "step": 243 }, { "epoch": 0.06334371754932502, "grad_norm": 8.231459617614746, "learning_rate": 4.999975936259389e-06, "loss": 0.5328008532524109, "step": 244 }, { "epoch": 0.06360332294911734, "grad_norm": 10.197765350341797, "learning_rate": 4.9999713621696375e-06, "loss": 0.6049075126647949, "step": 245 }, { "epoch": 0.06386292834890965, "grad_norm": 6.161686420440674, "learning_rate": 4.999966390336466e-06, "loss": 0.4953242838382721, "step": 246 }, { "epoch": 0.06412253374870197, "grad_norm": 6.710382461547852, "learning_rate": 4.999961020760754e-06, "loss": 0.5286291241645813, "step": 247 }, { "epoch": 0.06438213914849429, "grad_norm": 7.943606853485107, "learning_rate": 4.999955253443451e-06, "loss": 0.49040576815605164, "step": 248 }, { "epoch": 0.0646417445482866, "grad_norm": 8.535633087158203, "learning_rate": 4.999949088385577e-06, "loss": 0.6623823046684265, "step": 249 }, { "epoch": 0.06490134994807892, "grad_norm": 7.093170642852783, "learning_rate": 4.9999425255882205e-06, "loss": 0.5784268379211426, "step": 250 }, { "epoch": 0.06516095534787124, "grad_norm": 10.855521202087402, "learning_rate": 4.999935565052543e-06, "loss": 0.5411297082901001, "step": 251 }, { "epoch": 0.06542056074766354, "grad_norm": 4.954808235168457, "learning_rate": 4.999928206779774e-06, "loss": 0.5825426578521729, "step": 252 }, { "epoch": 0.06568016614745587, "grad_norm": 7.509947299957275, "learning_rate": 4.999920450771214e-06, "loss": 0.5531846284866333, "step": 253 }, { "epoch": 0.06593977154724819, "grad_norm": 10.406962394714355, "learning_rate": 4.999912297028235e-06, "loss": 0.6578788161277771, "step": 254 }, { "epoch": 0.06619937694704049, "grad_norm": 3.3668336868286133, "learning_rate": 4.999903745552278e-06, "loss": 0.5275566577911377, "step": 255 }, { "epoch": 0.06645898234683281, "grad_norm": 7.11569356918335, "learning_rate": 4.9998947963448554e-06, "loss": 0.6266377568244934, "step": 256 }, { "epoch": 0.06671858774662513, "grad_norm": 7.882741451263428, "learning_rate": 4.999885449407547e-06, "loss": 0.5382826924324036, "step": 257 }, { "epoch": 0.06697819314641744, "grad_norm": 16.64087677001953, "learning_rate": 4.999875704742009e-06, "loss": 0.583878755569458, "step": 258 }, { "epoch": 0.06723779854620976, "grad_norm": 7.322028160095215, "learning_rate": 4.99986556234996e-06, "loss": 0.5618138313293457, "step": 259 }, { "epoch": 0.06749740394600208, "grad_norm": 17.615428924560547, "learning_rate": 4.999855022233195e-06, "loss": 0.5488507747650146, "step": 260 }, { "epoch": 0.06775700934579439, "grad_norm": 13.090457916259766, "learning_rate": 4.999844084393577e-06, "loss": 0.5710142254829407, "step": 261 }, { "epoch": 0.0680166147455867, "grad_norm": 9.71561050415039, "learning_rate": 4.99983274883304e-06, "loss": 0.5062597990036011, "step": 262 }, { "epoch": 0.06827622014537903, "grad_norm": 6.704418659210205, "learning_rate": 4.999821015553586e-06, "loss": 0.4471741318702698, "step": 263 }, { "epoch": 0.06853582554517133, "grad_norm": 10.369550704956055, "learning_rate": 4.999808884557291e-06, "loss": 0.4646396040916443, "step": 264 }, { "epoch": 0.06879543094496365, "grad_norm": 7.30869722366333, "learning_rate": 4.9997963558463e-06, "loss": 0.5072453618049622, "step": 265 }, { "epoch": 0.06905503634475597, "grad_norm": 9.166825294494629, "learning_rate": 4.999783429422826e-06, "loss": 0.4480844736099243, "step": 266 }, { "epoch": 0.06931464174454828, "grad_norm": 8.409547805786133, "learning_rate": 4.999770105289155e-06, "loss": 0.5302656888961792, "step": 267 }, { "epoch": 0.0695742471443406, "grad_norm": 9.011773109436035, "learning_rate": 4.999756383447642e-06, "loss": 0.5670158863067627, "step": 268 }, { "epoch": 0.06983385254413292, "grad_norm": 5.959416389465332, "learning_rate": 4.999742263900714e-06, "loss": 0.5627841949462891, "step": 269 }, { "epoch": 0.07009345794392523, "grad_norm": 7.362491130828857, "learning_rate": 4.9997277466508654e-06, "loss": 0.4489281177520752, "step": 270 }, { "epoch": 0.07035306334371755, "grad_norm": 8.718964576721191, "learning_rate": 4.9997128317006625e-06, "loss": 0.5741689205169678, "step": 271 }, { "epoch": 0.07061266874350987, "grad_norm": 7.236147403717041, "learning_rate": 4.999697519052743e-06, "loss": 0.44992291927337646, "step": 272 }, { "epoch": 0.07087227414330217, "grad_norm": 8.250921249389648, "learning_rate": 4.999681808709814e-06, "loss": 0.5708130598068237, "step": 273 }, { "epoch": 0.0711318795430945, "grad_norm": 5.154395580291748, "learning_rate": 4.999665700674651e-06, "loss": 0.5702844858169556, "step": 274 }, { "epoch": 0.07139148494288682, "grad_norm": 9.365506172180176, "learning_rate": 4.999649194950103e-06, "loss": 0.5958747863769531, "step": 275 }, { "epoch": 0.07165109034267912, "grad_norm": 10.900854110717773, "learning_rate": 4.999632291539088e-06, "loss": 0.5084404945373535, "step": 276 }, { "epoch": 0.07191069574247144, "grad_norm": 7.601486682891846, "learning_rate": 4.999614990444594e-06, "loss": 0.4938811957836151, "step": 277 }, { "epoch": 0.07217030114226376, "grad_norm": 7.692137241363525, "learning_rate": 4.999597291669679e-06, "loss": 0.5636569261550903, "step": 278 }, { "epoch": 0.07242990654205607, "grad_norm": 3.88995623588562, "learning_rate": 4.99957919521747e-06, "loss": 0.46452537178993225, "step": 279 }, { "epoch": 0.07268951194184839, "grad_norm": 5.334096908569336, "learning_rate": 4.9995607010911696e-06, "loss": 0.552187442779541, "step": 280 }, { "epoch": 0.07294911734164071, "grad_norm": 5.218666076660156, "learning_rate": 4.999541809294045e-06, "loss": 0.4343075752258301, "step": 281 }, { "epoch": 0.07320872274143302, "grad_norm": 6.932895660400391, "learning_rate": 4.999522519829435e-06, "loss": 0.4429672360420227, "step": 282 }, { "epoch": 0.07346832814122534, "grad_norm": 3.7598586082458496, "learning_rate": 4.999502832700752e-06, "loss": 0.45471781492233276, "step": 283 }, { "epoch": 0.07372793354101766, "grad_norm": 6.214550495147705, "learning_rate": 4.999482747911475e-06, "loss": 0.4538443684577942, "step": 284 }, { "epoch": 0.07398753894080996, "grad_norm": 4.471278667449951, "learning_rate": 4.999462265465154e-06, "loss": 0.40107691287994385, "step": 285 }, { "epoch": 0.07424714434060228, "grad_norm": 4.884383678436279, "learning_rate": 4.99944138536541e-06, "loss": 0.42283886671066284, "step": 286 }, { "epoch": 0.0745067497403946, "grad_norm": 5.564580917358398, "learning_rate": 4.999420107615935e-06, "loss": 0.45688027143478394, "step": 287 }, { "epoch": 0.07476635514018691, "grad_norm": 4.588374614715576, "learning_rate": 4.9993984322204905e-06, "loss": 0.4642736315727234, "step": 288 }, { "epoch": 0.07502596053997923, "grad_norm": 7.203962326049805, "learning_rate": 4.999376359182906e-06, "loss": 0.4764840602874756, "step": 289 }, { "epoch": 0.07528556593977155, "grad_norm": 3.112377405166626, "learning_rate": 4.999353888507086e-06, "loss": 0.43839478492736816, "step": 290 }, { "epoch": 0.07554517133956386, "grad_norm": 5.527659893035889, "learning_rate": 4.999331020197002e-06, "loss": 0.4698463976383209, "step": 291 }, { "epoch": 0.07580477673935618, "grad_norm": 9.5869140625, "learning_rate": 4.999307754256696e-06, "loss": 0.5794099569320679, "step": 292 }, { "epoch": 0.0760643821391485, "grad_norm": 3.9667794704437256, "learning_rate": 4.999284090690282e-06, "loss": 0.4237849712371826, "step": 293 }, { "epoch": 0.0763239875389408, "grad_norm": 8.535324096679688, "learning_rate": 4.999260029501942e-06, "loss": 0.5948526859283447, "step": 294 }, { "epoch": 0.07658359293873312, "grad_norm": 10.359310150146484, "learning_rate": 4.999235570695931e-06, "loss": 0.44965288043022156, "step": 295 }, { "epoch": 0.07684319833852545, "grad_norm": 3.639894723892212, "learning_rate": 4.9992107142765715e-06, "loss": 0.4234960079193115, "step": 296 }, { "epoch": 0.07710280373831775, "grad_norm": 7.032577037811279, "learning_rate": 4.999185460248257e-06, "loss": 0.5017901659011841, "step": 297 }, { "epoch": 0.07736240913811007, "grad_norm": 4.713806629180908, "learning_rate": 4.999159808615453e-06, "loss": 0.4131354093551636, "step": 298 }, { "epoch": 0.07762201453790239, "grad_norm": 7.453971862792969, "learning_rate": 4.999133759382693e-06, "loss": 0.5879666805267334, "step": 299 }, { "epoch": 0.0778816199376947, "grad_norm": 3.173518180847168, "learning_rate": 4.999107312554583e-06, "loss": 0.43246105313301086, "step": 300 }, { "epoch": 0.07814122533748702, "grad_norm": 5.552595138549805, "learning_rate": 4.9990804681358e-06, "loss": 0.4668937921524048, "step": 301 }, { "epoch": 0.07840083073727934, "grad_norm": 6.580323696136475, "learning_rate": 4.999053226131084e-06, "loss": 0.571910560131073, "step": 302 }, { "epoch": 0.07866043613707165, "grad_norm": 3.822007894515991, "learning_rate": 4.9990255865452565e-06, "loss": 0.4521925151348114, "step": 303 }, { "epoch": 0.07892004153686397, "grad_norm": 5.9042840003967285, "learning_rate": 4.9989975493832005e-06, "loss": 0.44020336866378784, "step": 304 }, { "epoch": 0.07917964693665629, "grad_norm": 10.36135196685791, "learning_rate": 4.998969114649873e-06, "loss": 0.5980026125907898, "step": 305 }, { "epoch": 0.0794392523364486, "grad_norm": 4.468556880950928, "learning_rate": 4.9989402823503006e-06, "loss": 0.5508116483688354, "step": 306 }, { "epoch": 0.07969885773624091, "grad_norm": 8.058670043945312, "learning_rate": 4.9989110524895795e-06, "loss": 0.5024950504302979, "step": 307 }, { "epoch": 0.07995846313603323, "grad_norm": 5.672938346862793, "learning_rate": 4.998881425072879e-06, "loss": 0.5077171325683594, "step": 308 }, { "epoch": 0.08021806853582554, "grad_norm": 2.571035385131836, "learning_rate": 4.998851400105433e-06, "loss": 0.4164579510688782, "step": 309 }, { "epoch": 0.08047767393561786, "grad_norm": 10.903302192687988, "learning_rate": 4.998820977592553e-06, "loss": 0.549788236618042, "step": 310 }, { "epoch": 0.08073727933541018, "grad_norm": 9.955960273742676, "learning_rate": 4.998790157539615e-06, "loss": 0.4851049780845642, "step": 311 }, { "epoch": 0.08099688473520249, "grad_norm": 6.690711498260498, "learning_rate": 4.998758939952068e-06, "loss": 0.6089181900024414, "step": 312 }, { "epoch": 0.08125649013499481, "grad_norm": 5.782426834106445, "learning_rate": 4.998727324835429e-06, "loss": 0.48335862159729004, "step": 313 }, { "epoch": 0.08151609553478713, "grad_norm": 5.348112106323242, "learning_rate": 4.998695312195289e-06, "loss": 0.4709010720252991, "step": 314 }, { "epoch": 0.08177570093457943, "grad_norm": 13.332550048828125, "learning_rate": 4.998662902037306e-06, "loss": 0.49526751041412354, "step": 315 }, { "epoch": 0.08203530633437175, "grad_norm": 7.076578140258789, "learning_rate": 4.998630094367209e-06, "loss": 0.473551869392395, "step": 316 }, { "epoch": 0.08229491173416408, "grad_norm": 4.880993843078613, "learning_rate": 4.998596889190799e-06, "loss": 0.43095633387565613, "step": 317 }, { "epoch": 0.08255451713395638, "grad_norm": 3.536254405975342, "learning_rate": 4.998563286513944e-06, "loss": 0.47599005699157715, "step": 318 }, { "epoch": 0.0828141225337487, "grad_norm": 9.042531967163086, "learning_rate": 4.998529286342585e-06, "loss": 0.5338985323905945, "step": 319 }, { "epoch": 0.08307372793354102, "grad_norm": 5.578803539276123, "learning_rate": 4.998494888682734e-06, "loss": 0.5905638933181763, "step": 320 }, { "epoch": 0.08333333333333333, "grad_norm": 4.310269832611084, "learning_rate": 4.99846009354047e-06, "loss": 0.48624247312545776, "step": 321 }, { "epoch": 0.08359293873312565, "grad_norm": 5.521030902862549, "learning_rate": 4.998424900921944e-06, "loss": 0.5343260765075684, "step": 322 }, { "epoch": 0.08385254413291797, "grad_norm": 4.757368087768555, "learning_rate": 4.998389310833378e-06, "loss": 0.5167557597160339, "step": 323 }, { "epoch": 0.08411214953271028, "grad_norm": 3.5732057094573975, "learning_rate": 4.998353323281063e-06, "loss": 0.43665269017219543, "step": 324 }, { "epoch": 0.0843717549325026, "grad_norm": 5.413257122039795, "learning_rate": 4.998316938271361e-06, "loss": 0.48179805278778076, "step": 325 }, { "epoch": 0.08463136033229492, "grad_norm": 3.103734016418457, "learning_rate": 4.998280155810704e-06, "loss": 0.4912909269332886, "step": 326 }, { "epoch": 0.08489096573208722, "grad_norm": 4.775387287139893, "learning_rate": 4.998242975905593e-06, "loss": 0.5327824950218201, "step": 327 }, { "epoch": 0.08515057113187954, "grad_norm": 7.0986247062683105, "learning_rate": 4.998205398562603e-06, "loss": 0.5249571800231934, "step": 328 }, { "epoch": 0.08541017653167186, "grad_norm": 2.259800672531128, "learning_rate": 4.998167423788375e-06, "loss": 0.43187350034713745, "step": 329 }, { "epoch": 0.08566978193146417, "grad_norm": 6.66581916809082, "learning_rate": 4.998129051589624e-06, "loss": 0.6005333662033081, "step": 330 }, { "epoch": 0.08592938733125649, "grad_norm": 3.3541483879089355, "learning_rate": 4.998090281973131e-06, "loss": 0.45114514231681824, "step": 331 }, { "epoch": 0.08618899273104881, "grad_norm": 5.938751220703125, "learning_rate": 4.99805111494575e-06, "loss": 0.48306483030319214, "step": 332 }, { "epoch": 0.08644859813084112, "grad_norm": 11.194917678833008, "learning_rate": 4.9980115505144065e-06, "loss": 0.5233643651008606, "step": 333 }, { "epoch": 0.08670820353063344, "grad_norm": 3.7290663719177246, "learning_rate": 4.997971588686093e-06, "loss": 0.45942026376724243, "step": 334 }, { "epoch": 0.08696780893042576, "grad_norm": 4.724886894226074, "learning_rate": 4.9979312294678745e-06, "loss": 0.5685032606124878, "step": 335 }, { "epoch": 0.08722741433021806, "grad_norm": 5.4129438400268555, "learning_rate": 4.997890472866885e-06, "loss": 0.5268198251724243, "step": 336 }, { "epoch": 0.08748701973001038, "grad_norm": 5.993208408355713, "learning_rate": 4.99784931889033e-06, "loss": 0.5372881889343262, "step": 337 }, { "epoch": 0.0877466251298027, "grad_norm": 4.5491862297058105, "learning_rate": 4.997807767545485e-06, "loss": 0.4479616582393646, "step": 338 }, { "epoch": 0.08800623052959501, "grad_norm": 5.298781394958496, "learning_rate": 4.9977658188396935e-06, "loss": 0.4607143700122833, "step": 339 }, { "epoch": 0.08826583592938733, "grad_norm": 3.2238364219665527, "learning_rate": 4.997723472780373e-06, "loss": 0.4513218104839325, "step": 340 }, { "epoch": 0.08852544132917965, "grad_norm": 2.754289150238037, "learning_rate": 4.997680729375008e-06, "loss": 0.43238985538482666, "step": 341 }, { "epoch": 0.08878504672897196, "grad_norm": 4.112437725067139, "learning_rate": 4.997637588631156e-06, "loss": 0.5396146774291992, "step": 342 }, { "epoch": 0.08904465212876428, "grad_norm": 3.0439870357513428, "learning_rate": 4.997594050556443e-06, "loss": 0.43001461029052734, "step": 343 }, { "epoch": 0.0893042575285566, "grad_norm": 3.8454055786132812, "learning_rate": 4.9975501151585635e-06, "loss": 0.49437570571899414, "step": 344 }, { "epoch": 0.0895638629283489, "grad_norm": 3.1950199604034424, "learning_rate": 4.997505782445286e-06, "loss": 0.47505438327789307, "step": 345 }, { "epoch": 0.08982346832814123, "grad_norm": 3.699662685394287, "learning_rate": 4.997461052424447e-06, "loss": 0.5156884789466858, "step": 346 }, { "epoch": 0.09008307372793355, "grad_norm": 5.976468563079834, "learning_rate": 4.997415925103955e-06, "loss": 0.5188536047935486, "step": 347 }, { "epoch": 0.09034267912772585, "grad_norm": 4.654469966888428, "learning_rate": 4.997370400491786e-06, "loss": 0.45032215118408203, "step": 348 }, { "epoch": 0.09060228452751817, "grad_norm": 5.446640491485596, "learning_rate": 4.997324478595987e-06, "loss": 0.5050531625747681, "step": 349 }, { "epoch": 0.0908618899273105, "grad_norm": 6.756760597229004, "learning_rate": 4.997278159424678e-06, "loss": 0.5058863759040833, "step": 350 }, { "epoch": 0.0911214953271028, "grad_norm": 7.706319808959961, "learning_rate": 4.997231442986047e-06, "loss": 0.5411859154701233, "step": 351 }, { "epoch": 0.09138110072689512, "grad_norm": 7.829673767089844, "learning_rate": 4.997184329288351e-06, "loss": 0.5713269710540771, "step": 352 }, { "epoch": 0.09164070612668744, "grad_norm": 3.9189045429229736, "learning_rate": 4.99713681833992e-06, "loss": 0.5260486006736755, "step": 353 }, { "epoch": 0.09190031152647975, "grad_norm": 9.120695114135742, "learning_rate": 4.99708891014915e-06, "loss": 0.5304105877876282, "step": 354 }, { "epoch": 0.09215991692627207, "grad_norm": 3.5743606090545654, "learning_rate": 4.997040604724514e-06, "loss": 0.46160268783569336, "step": 355 }, { "epoch": 0.09241952232606439, "grad_norm": 9.025617599487305, "learning_rate": 4.9969919020745485e-06, "loss": 0.43982985615730286, "step": 356 }, { "epoch": 0.0926791277258567, "grad_norm": 3.7944140434265137, "learning_rate": 4.996942802207866e-06, "loss": 0.43497008085250854, "step": 357 }, { "epoch": 0.09293873312564901, "grad_norm": 6.695741176605225, "learning_rate": 4.996893305133142e-06, "loss": 0.5737349987030029, "step": 358 }, { "epoch": 0.09319833852544133, "grad_norm": 3.6104722023010254, "learning_rate": 4.996843410859129e-06, "loss": 0.40333664417266846, "step": 359 }, { "epoch": 0.09345794392523364, "grad_norm": 4.2105584144592285, "learning_rate": 4.996793119394648e-06, "loss": 0.42985421419143677, "step": 360 }, { "epoch": 0.09371754932502596, "grad_norm": 4.6885881423950195, "learning_rate": 4.996742430748587e-06, "loss": 0.45010972023010254, "step": 361 }, { "epoch": 0.09397715472481828, "grad_norm": 5.582444667816162, "learning_rate": 4.996691344929909e-06, "loss": 0.6086344122886658, "step": 362 }, { "epoch": 0.09423676012461059, "grad_norm": 7.952987194061279, "learning_rate": 4.996639861947643e-06, "loss": 0.5015949010848999, "step": 363 }, { "epoch": 0.09449636552440291, "grad_norm": 9.38727855682373, "learning_rate": 4.99658798181089e-06, "loss": 0.5172243118286133, "step": 364 }, { "epoch": 0.09475597092419523, "grad_norm": 7.426234722137451, "learning_rate": 4.996535704528823e-06, "loss": 0.4770270586013794, "step": 365 }, { "epoch": 0.09501557632398754, "grad_norm": 8.253169059753418, "learning_rate": 4.996483030110682e-06, "loss": 0.5547348260879517, "step": 366 }, { "epoch": 0.09527518172377986, "grad_norm": 3.9986071586608887, "learning_rate": 4.996429958565779e-06, "loss": 0.4245326817035675, "step": 367 }, { "epoch": 0.09553478712357218, "grad_norm": 9.927397727966309, "learning_rate": 4.996376489903495e-06, "loss": 0.4980064928531647, "step": 368 }, { "epoch": 0.09579439252336448, "grad_norm": 3.7836358547210693, "learning_rate": 4.996322624133284e-06, "loss": 0.44173377752304077, "step": 369 }, { "epoch": 0.0960539979231568, "grad_norm": 4.113348007202148, "learning_rate": 4.996268361264666e-06, "loss": 0.42230063676834106, "step": 370 }, { "epoch": 0.09631360332294912, "grad_norm": 4.3074846267700195, "learning_rate": 4.996213701307235e-06, "loss": 0.4370242953300476, "step": 371 }, { "epoch": 0.09657320872274143, "grad_norm": 10.87154769897461, "learning_rate": 4.9961586442706525e-06, "loss": 0.6168476343154907, "step": 372 }, { "epoch": 0.09683281412253375, "grad_norm": 5.51374626159668, "learning_rate": 4.9961031901646524e-06, "loss": 0.5474259853363037, "step": 373 }, { "epoch": 0.09709241952232607, "grad_norm": 5.013695240020752, "learning_rate": 4.996047338999037e-06, "loss": 0.5281551480293274, "step": 374 }, { "epoch": 0.09735202492211838, "grad_norm": 3.0454161167144775, "learning_rate": 4.99599109078368e-06, "loss": 0.44523146748542786, "step": 375 }, { "epoch": 0.0976116303219107, "grad_norm": 2.9871373176574707, "learning_rate": 4.995934445528524e-06, "loss": 0.4518771767616272, "step": 376 }, { "epoch": 0.09787123572170302, "grad_norm": 3.356433391571045, "learning_rate": 4.995877403243584e-06, "loss": 0.4490326941013336, "step": 377 }, { "epoch": 0.09813084112149532, "grad_norm": 3.787524461746216, "learning_rate": 4.995819963938942e-06, "loss": 0.43780046701431274, "step": 378 }, { "epoch": 0.09839044652128764, "grad_norm": 2.777096748352051, "learning_rate": 4.995762127624753e-06, "loss": 0.42084258794784546, "step": 379 }, { "epoch": 0.09865005192107996, "grad_norm": 2.7314693927764893, "learning_rate": 4.995703894311242e-06, "loss": 0.43421104550361633, "step": 380 }, { "epoch": 0.09890965732087227, "grad_norm": 4.0690107345581055, "learning_rate": 4.995645264008701e-06, "loss": 0.5226582884788513, "step": 381 }, { "epoch": 0.09916926272066459, "grad_norm": 3.932406187057495, "learning_rate": 4.995586236727496e-06, "loss": 0.48645979166030884, "step": 382 }, { "epoch": 0.09942886812045691, "grad_norm": 4.9222025871276855, "learning_rate": 4.995526812478061e-06, "loss": 0.6094651222229004, "step": 383 }, { "epoch": 0.09968847352024922, "grad_norm": 5.1339874267578125, "learning_rate": 4.995466991270903e-06, "loss": 0.4257265329360962, "step": 384 }, { "epoch": 0.09994807892004154, "grad_norm": 4.116115570068359, "learning_rate": 4.9954067731165945e-06, "loss": 0.43655648827552795, "step": 385 }, { "epoch": 0.10020768431983386, "grad_norm": 2.6905462741851807, "learning_rate": 4.995346158025781e-06, "loss": 0.4047139883041382, "step": 386 }, { "epoch": 0.10046728971962617, "grad_norm": 2.8178060054779053, "learning_rate": 4.995285146009179e-06, "loss": 0.4352670907974243, "step": 387 }, { "epoch": 0.10072689511941849, "grad_norm": 2.3285467624664307, "learning_rate": 4.995223737077573e-06, "loss": 0.5900384187698364, "step": 388 }, { "epoch": 0.1009865005192108, "grad_norm": 1.9967668056488037, "learning_rate": 4.9951619312418196e-06, "loss": 0.41267454624176025, "step": 389 }, { "epoch": 0.10124610591900311, "grad_norm": 3.620739459991455, "learning_rate": 4.995099728512843e-06, "loss": 0.460070937871933, "step": 390 }, { "epoch": 0.10150571131879543, "grad_norm": 4.428513526916504, "learning_rate": 4.995037128901642e-06, "loss": 0.4524936079978943, "step": 391 }, { "epoch": 0.10176531671858775, "grad_norm": 3.3002138137817383, "learning_rate": 4.99497413241928e-06, "loss": 0.43759000301361084, "step": 392 }, { "epoch": 0.10202492211838006, "grad_norm": 7.018954753875732, "learning_rate": 4.994910739076895e-06, "loss": 0.5867871642112732, "step": 393 }, { "epoch": 0.10228452751817238, "grad_norm": 3.6138949394226074, "learning_rate": 4.994846948885693e-06, "loss": 0.4763394594192505, "step": 394 }, { "epoch": 0.1025441329179647, "grad_norm": 6.542708873748779, "learning_rate": 4.99478276185695e-06, "loss": 0.4907902479171753, "step": 395 }, { "epoch": 0.102803738317757, "grad_norm": 3.2386677265167236, "learning_rate": 4.994718178002013e-06, "loss": 0.4002702832221985, "step": 396 }, { "epoch": 0.10306334371754933, "grad_norm": 2.6507439613342285, "learning_rate": 4.9946531973323005e-06, "loss": 0.4229332208633423, "step": 397 }, { "epoch": 0.10332294911734165, "grad_norm": 2.0183277130126953, "learning_rate": 4.9945878198592975e-06, "loss": 0.41824451088905334, "step": 398 }, { "epoch": 0.10358255451713395, "grad_norm": 8.064678192138672, "learning_rate": 4.994522045594563e-06, "loss": 0.527122974395752, "step": 399 }, { "epoch": 0.10384215991692627, "grad_norm": 4.683814525604248, "learning_rate": 4.9944558745497236e-06, "loss": 0.4684903621673584, "step": 400 }, { "epoch": 0.1041017653167186, "grad_norm": 2.506559133529663, "learning_rate": 4.9943893067364765e-06, "loss": 0.469732403755188, "step": 401 }, { "epoch": 0.1043613707165109, "grad_norm": 3.6683189868927, "learning_rate": 4.99432234216659e-06, "loss": 0.49954065680503845, "step": 402 }, { "epoch": 0.10462097611630322, "grad_norm": 4.297175407409668, "learning_rate": 4.994254980851901e-06, "loss": 0.4212227463722229, "step": 403 }, { "epoch": 0.10488058151609553, "grad_norm": 2.808966875076294, "learning_rate": 4.994187222804319e-06, "loss": 0.45423153042793274, "step": 404 }, { "epoch": 0.10514018691588785, "grad_norm": 4.9172844886779785, "learning_rate": 4.99411906803582e-06, "loss": 0.4916982650756836, "step": 405 }, { "epoch": 0.10539979231568017, "grad_norm": 4.545945644378662, "learning_rate": 4.994050516558454e-06, "loss": 0.44368255138397217, "step": 406 }, { "epoch": 0.10565939771547248, "grad_norm": 3.8408596515655518, "learning_rate": 4.993981568384339e-06, "loss": 0.4529244303703308, "step": 407 }, { "epoch": 0.1059190031152648, "grad_norm": 5.591165065765381, "learning_rate": 4.993912223525661e-06, "loss": 0.5229585766792297, "step": 408 }, { "epoch": 0.10617860851505712, "grad_norm": 2.617140531539917, "learning_rate": 4.993842481994683e-06, "loss": 0.5021722316741943, "step": 409 }, { "epoch": 0.10643821391484942, "grad_norm": 6.934810161590576, "learning_rate": 4.99377234380373e-06, "loss": 0.5258035063743591, "step": 410 }, { "epoch": 0.10669781931464174, "grad_norm": 6.363378524780273, "learning_rate": 4.9937018089652024e-06, "loss": 0.5698198080062866, "step": 411 }, { "epoch": 0.10695742471443406, "grad_norm": 3.97837495803833, "learning_rate": 4.99363087749157e-06, "loss": 0.5016721487045288, "step": 412 }, { "epoch": 0.10721703011422637, "grad_norm": 7.996025562286377, "learning_rate": 4.993559549395369e-06, "loss": 0.572613000869751, "step": 413 }, { "epoch": 0.10747663551401869, "grad_norm": 2.2712860107421875, "learning_rate": 4.993487824689211e-06, "loss": 0.44715574383735657, "step": 414 }, { "epoch": 0.10773624091381101, "grad_norm": 3.312512159347534, "learning_rate": 4.993415703385776e-06, "loss": 0.4046105742454529, "step": 415 }, { "epoch": 0.10799584631360332, "grad_norm": 2.6280128955841064, "learning_rate": 4.99334318549781e-06, "loss": 0.4134390950202942, "step": 416 }, { "epoch": 0.10825545171339564, "grad_norm": 3.7079567909240723, "learning_rate": 4.993270271038136e-06, "loss": 0.42517855763435364, "step": 417 }, { "epoch": 0.10851505711318796, "grad_norm": 2.9879846572875977, "learning_rate": 4.993196960019642e-06, "loss": 0.44722041487693787, "step": 418 }, { "epoch": 0.10877466251298026, "grad_norm": 8.007147789001465, "learning_rate": 4.993123252455288e-06, "loss": 0.49636727571487427, "step": 419 }, { "epoch": 0.10903426791277258, "grad_norm": 3.152667999267578, "learning_rate": 4.993049148358103e-06, "loss": 0.43394654989242554, "step": 420 }, { "epoch": 0.1092938733125649, "grad_norm": 3.704678535461426, "learning_rate": 4.992974647741188e-06, "loss": 0.4298904836177826, "step": 421 }, { "epoch": 0.10955347871235721, "grad_norm": 9.398720741271973, "learning_rate": 4.992899750617712e-06, "loss": 0.5480126142501831, "step": 422 }, { "epoch": 0.10981308411214953, "grad_norm": 4.102258205413818, "learning_rate": 4.9928244570009165e-06, "loss": 0.42264246940612793, "step": 423 }, { "epoch": 0.11007268951194185, "grad_norm": 2.1737215518951416, "learning_rate": 4.99274876690411e-06, "loss": 0.41712671518325806, "step": 424 }, { "epoch": 0.11033229491173416, "grad_norm": 3.227278232574463, "learning_rate": 4.992672680340675e-06, "loss": 0.4399089515209198, "step": 425 }, { "epoch": 0.11059190031152648, "grad_norm": 4.1787190437316895, "learning_rate": 4.9925961973240595e-06, "loss": 0.3963736891746521, "step": 426 }, { "epoch": 0.1108515057113188, "grad_norm": 6.366570472717285, "learning_rate": 4.992519317867784e-06, "loss": 0.45751842856407166, "step": 427 }, { "epoch": 0.1111111111111111, "grad_norm": 6.858978748321533, "learning_rate": 4.992442041985442e-06, "loss": 0.4901648759841919, "step": 428 }, { "epoch": 0.11137071651090343, "grad_norm": 3.345062494277954, "learning_rate": 4.9923643696906915e-06, "loss": 0.4155813455581665, "step": 429 }, { "epoch": 0.11163032191069575, "grad_norm": 3.136350393295288, "learning_rate": 4.992286300997263e-06, "loss": 0.446441650390625, "step": 430 }, { "epoch": 0.11188992731048805, "grad_norm": 3.76216197013855, "learning_rate": 4.992207835918959e-06, "loss": 0.517667293548584, "step": 431 }, { "epoch": 0.11214953271028037, "grad_norm": 6.572340965270996, "learning_rate": 4.99212897446965e-06, "loss": 0.43642574548721313, "step": 432 }, { "epoch": 0.11240913811007269, "grad_norm": 2.3010706901550293, "learning_rate": 4.992049716663274e-06, "loss": 0.4290105104446411, "step": 433 }, { "epoch": 0.112668743509865, "grad_norm": 3.0993459224700928, "learning_rate": 4.991970062513845e-06, "loss": 0.425586998462677, "step": 434 }, { "epoch": 0.11292834890965732, "grad_norm": 6.8102216720581055, "learning_rate": 4.991890012035444e-06, "loss": 0.573033332824707, "step": 435 }, { "epoch": 0.11318795430944964, "grad_norm": 7.341329097747803, "learning_rate": 4.991809565242221e-06, "loss": 0.5013463497161865, "step": 436 }, { "epoch": 0.11344755970924195, "grad_norm": 12.923460960388184, "learning_rate": 4.991728722148398e-06, "loss": 0.4693160653114319, "step": 437 }, { "epoch": 0.11370716510903427, "grad_norm": 6.533261775970459, "learning_rate": 4.991647482768265e-06, "loss": 0.5622926950454712, "step": 438 }, { "epoch": 0.11396677050882659, "grad_norm": 2.982571601867676, "learning_rate": 4.991565847116184e-06, "loss": 0.5083297491073608, "step": 439 }, { "epoch": 0.1142263759086189, "grad_norm": 3.930652141571045, "learning_rate": 4.991483815206586e-06, "loss": 0.42100799083709717, "step": 440 }, { "epoch": 0.11448598130841121, "grad_norm": 4.877196788787842, "learning_rate": 4.991401387053973e-06, "loss": 0.4307780861854553, "step": 441 }, { "epoch": 0.11474558670820353, "grad_norm": 4.570183753967285, "learning_rate": 4.991318562672917e-06, "loss": 0.47747594118118286, "step": 442 }, { "epoch": 0.11500519210799584, "grad_norm": 3.483006715774536, "learning_rate": 4.991235342078058e-06, "loss": 0.4655778110027313, "step": 443 }, { "epoch": 0.11526479750778816, "grad_norm": 4.609313488006592, "learning_rate": 4.9911517252841066e-06, "loss": 0.4078787565231323, "step": 444 }, { "epoch": 0.11552440290758048, "grad_norm": 7.447445869445801, "learning_rate": 4.991067712305848e-06, "loss": 0.6317917108535767, "step": 445 }, { "epoch": 0.11578400830737279, "grad_norm": 3.5753345489501953, "learning_rate": 4.9909833031581294e-06, "loss": 0.4478119909763336, "step": 446 }, { "epoch": 0.11604361370716511, "grad_norm": 5.153562068939209, "learning_rate": 4.990898497855876e-06, "loss": 0.5106717944145203, "step": 447 }, { "epoch": 0.11630321910695743, "grad_norm": 8.585794448852539, "learning_rate": 4.990813296414077e-06, "loss": 0.56810462474823, "step": 448 }, { "epoch": 0.11656282450674973, "grad_norm": 6.348191261291504, "learning_rate": 4.990727698847796e-06, "loss": 0.5209312438964844, "step": 449 }, { "epoch": 0.11682242990654206, "grad_norm": 4.275224208831787, "learning_rate": 4.990641705172163e-06, "loss": 0.5013687014579773, "step": 450 }, { "epoch": 0.11708203530633438, "grad_norm": 6.939657211303711, "learning_rate": 4.99055531540238e-06, "loss": 0.5226980447769165, "step": 451 }, { "epoch": 0.11734164070612668, "grad_norm": 6.93046760559082, "learning_rate": 4.99046852955372e-06, "loss": 0.5282785892486572, "step": 452 }, { "epoch": 0.117601246105919, "grad_norm": 5.263741970062256, "learning_rate": 4.990381347641524e-06, "loss": 0.4018937349319458, "step": 453 }, { "epoch": 0.11786085150571132, "grad_norm": 5.587026119232178, "learning_rate": 4.9902937696812034e-06, "loss": 0.38521161675453186, "step": 454 }, { "epoch": 0.11812045690550363, "grad_norm": 4.469263553619385, "learning_rate": 4.99020579568824e-06, "loss": 0.5003210306167603, "step": 455 }, { "epoch": 0.11838006230529595, "grad_norm": 3.5649075508117676, "learning_rate": 4.990117425678186e-06, "loss": 0.4352901875972748, "step": 456 }, { "epoch": 0.11863966770508827, "grad_norm": 2.4407289028167725, "learning_rate": 4.990028659666663e-06, "loss": 0.42774996161460876, "step": 457 }, { "epoch": 0.11889927310488058, "grad_norm": 4.935868740081787, "learning_rate": 4.989939497669363e-06, "loss": 0.4246746003627777, "step": 458 }, { "epoch": 0.1191588785046729, "grad_norm": 5.227277755737305, "learning_rate": 4.989849939702047e-06, "loss": 0.49730032682418823, "step": 459 }, { "epoch": 0.11941848390446522, "grad_norm": 4.616974353790283, "learning_rate": 4.989759985780548e-06, "loss": 0.41689738631248474, "step": 460 }, { "epoch": 0.11967808930425752, "grad_norm": 3.7221338748931885, "learning_rate": 4.989669635920767e-06, "loss": 0.4492464065551758, "step": 461 }, { "epoch": 0.11993769470404984, "grad_norm": 5.724929332733154, "learning_rate": 4.989578890138676e-06, "loss": 0.3806440234184265, "step": 462 }, { "epoch": 0.12019730010384216, "grad_norm": 2.3859333992004395, "learning_rate": 4.989487748450318e-06, "loss": 0.4049297571182251, "step": 463 }, { "epoch": 0.12045690550363447, "grad_norm": 12.756348609924316, "learning_rate": 4.9893962108718015e-06, "loss": 0.661342203617096, "step": 464 }, { "epoch": 0.12071651090342679, "grad_norm": 4.171828269958496, "learning_rate": 4.989304277419311e-06, "loss": 0.5738576650619507, "step": 465 }, { "epoch": 0.12097611630321911, "grad_norm": 7.814642906188965, "learning_rate": 4.989211948109099e-06, "loss": 0.5675133466720581, "step": 466 }, { "epoch": 0.12123572170301142, "grad_norm": 11.11670207977295, "learning_rate": 4.989119222957483e-06, "loss": 0.5627884864807129, "step": 467 }, { "epoch": 0.12149532710280374, "grad_norm": 9.011460304260254, "learning_rate": 4.98902610198086e-06, "loss": 0.577346920967102, "step": 468 }, { "epoch": 0.12175493250259606, "grad_norm": 5.403880596160889, "learning_rate": 4.988932585195688e-06, "loss": 0.6008017063140869, "step": 469 }, { "epoch": 0.12201453790238836, "grad_norm": 4.452714920043945, "learning_rate": 4.988838672618499e-06, "loss": 0.422726571559906, "step": 470 }, { "epoch": 0.12227414330218069, "grad_norm": 12.519052505493164, "learning_rate": 4.988744364265896e-06, "loss": 0.5518972873687744, "step": 471 }, { "epoch": 0.122533748701973, "grad_norm": 6.095191478729248, "learning_rate": 4.988649660154551e-06, "loss": 0.49393531680107117, "step": 472 }, { "epoch": 0.12279335410176531, "grad_norm": 5.1091437339782715, "learning_rate": 4.988554560301203e-06, "loss": 0.48089757561683655, "step": 473 }, { "epoch": 0.12305295950155763, "grad_norm": 6.499190807342529, "learning_rate": 4.988459064722664e-06, "loss": 0.33862394094467163, "step": 474 }, { "epoch": 0.12331256490134995, "grad_norm": 4.4859700202941895, "learning_rate": 4.988363173435818e-06, "loss": 0.48516184091567993, "step": 475 }, { "epoch": 0.12357217030114226, "grad_norm": 6.186678886413574, "learning_rate": 4.9882668864576135e-06, "loss": 0.5202012062072754, "step": 476 }, { "epoch": 0.12383177570093458, "grad_norm": 7.471445083618164, "learning_rate": 4.988170203805074e-06, "loss": 0.4544243812561035, "step": 477 }, { "epoch": 0.1240913811007269, "grad_norm": 5.403469085693359, "learning_rate": 4.9880731254952885e-06, "loss": 0.4028785526752472, "step": 478 }, { "epoch": 0.1243509865005192, "grad_norm": 4.296716690063477, "learning_rate": 4.987975651545421e-06, "loss": 0.39129477739334106, "step": 479 }, { "epoch": 0.12461059190031153, "grad_norm": 9.117839813232422, "learning_rate": 4.9878777819727e-06, "loss": 0.4596603214740753, "step": 480 }, { "epoch": 0.12487019730010385, "grad_norm": 5.348382472991943, "learning_rate": 4.9877795167944285e-06, "loss": 0.43589186668395996, "step": 481 }, { "epoch": 0.12512980269989615, "grad_norm": 5.716213703155518, "learning_rate": 4.987680856027976e-06, "loss": 0.466913640499115, "step": 482 }, { "epoch": 0.12538940809968846, "grad_norm": 4.400861740112305, "learning_rate": 4.987581799690785e-06, "loss": 0.4944489896297455, "step": 483 }, { "epoch": 0.1256490134994808, "grad_norm": 4.425251007080078, "learning_rate": 4.987482347800365e-06, "loss": 0.4016183018684387, "step": 484 }, { "epoch": 0.1259086188992731, "grad_norm": 5.919993877410889, "learning_rate": 4.987382500374298e-06, "loss": 0.5893987417221069, "step": 485 }, { "epoch": 0.1261682242990654, "grad_norm": 9.40504264831543, "learning_rate": 4.987282257430234e-06, "loss": 0.5688784122467041, "step": 486 }, { "epoch": 0.12642782969885774, "grad_norm": 4.663979530334473, "learning_rate": 4.987181618985893e-06, "loss": 0.4982583522796631, "step": 487 }, { "epoch": 0.12668743509865005, "grad_norm": 3.2097506523132324, "learning_rate": 4.987080585059068e-06, "loss": 0.4176246225833893, "step": 488 }, { "epoch": 0.12694704049844235, "grad_norm": 3.2743334770202637, "learning_rate": 4.9869791556676175e-06, "loss": 0.46927589178085327, "step": 489 }, { "epoch": 0.1272066458982347, "grad_norm": 4.509297847747803, "learning_rate": 4.986877330829472e-06, "loss": 0.41915470361709595, "step": 490 }, { "epoch": 0.127466251298027, "grad_norm": 2.6075398921966553, "learning_rate": 4.986775110562632e-06, "loss": 0.43821942806243896, "step": 491 }, { "epoch": 0.1277258566978193, "grad_norm": 3.7064108848571777, "learning_rate": 4.9866724948851685e-06, "loss": 0.5254175662994385, "step": 492 }, { "epoch": 0.12798546209761164, "grad_norm": 5.322484016418457, "learning_rate": 4.98656948381522e-06, "loss": 0.44921252131462097, "step": 493 }, { "epoch": 0.12824506749740394, "grad_norm": 3.01306414604187, "learning_rate": 4.986466077370998e-06, "loss": 0.43925535678863525, "step": 494 }, { "epoch": 0.12850467289719625, "grad_norm": 6.785510540008545, "learning_rate": 4.9863622755707815e-06, "loss": 0.5762823820114136, "step": 495 }, { "epoch": 0.12876427829698858, "grad_norm": 3.759748935699463, "learning_rate": 4.986258078432921e-06, "loss": 0.4532213807106018, "step": 496 }, { "epoch": 0.1290238836967809, "grad_norm": 5.334019184112549, "learning_rate": 4.986153485975835e-06, "loss": 0.5606306791305542, "step": 497 }, { "epoch": 0.1292834890965732, "grad_norm": 2.52231502532959, "learning_rate": 4.986048498218014e-06, "loss": 0.4890502095222473, "step": 498 }, { "epoch": 0.12954309449636553, "grad_norm": 4.943533897399902, "learning_rate": 4.985943115178018e-06, "loss": 0.5909633636474609, "step": 499 }, { "epoch": 0.12980269989615784, "grad_norm": 3.648273468017578, "learning_rate": 4.985837336874475e-06, "loss": 0.4401918351650238, "step": 500 }, { "epoch": 0.13006230529595014, "grad_norm": 3.6909804344177246, "learning_rate": 4.985731163326084e-06, "loss": 0.5764204263687134, "step": 501 }, { "epoch": 0.13032191069574248, "grad_norm": 3.459246873855591, "learning_rate": 4.985624594551616e-06, "loss": 0.4585854411125183, "step": 502 }, { "epoch": 0.13058151609553478, "grad_norm": 2.7474100589752197, "learning_rate": 4.985517630569908e-06, "loss": 0.39290401339530945, "step": 503 }, { "epoch": 0.1308411214953271, "grad_norm": 2.53605580329895, "learning_rate": 4.98541027139987e-06, "loss": 0.4368754029273987, "step": 504 }, { "epoch": 0.13110072689511942, "grad_norm": 4.628731727600098, "learning_rate": 4.98530251706048e-06, "loss": 0.5125380754470825, "step": 505 }, { "epoch": 0.13136033229491173, "grad_norm": 3.658841848373413, "learning_rate": 4.9851943675707864e-06, "loss": 0.4586750566959381, "step": 506 }, { "epoch": 0.13161993769470404, "grad_norm": 3.9156482219696045, "learning_rate": 4.985085822949908e-06, "loss": 0.4401598572731018, "step": 507 }, { "epoch": 0.13187954309449637, "grad_norm": 5.422764778137207, "learning_rate": 4.984976883217032e-06, "loss": 0.49916988611221313, "step": 508 }, { "epoch": 0.13213914849428868, "grad_norm": 4.183960437774658, "learning_rate": 4.984867548391418e-06, "loss": 0.42022567987442017, "step": 509 }, { "epoch": 0.13239875389408098, "grad_norm": 5.972772121429443, "learning_rate": 4.984757818492393e-06, "loss": 0.42354267835617065, "step": 510 }, { "epoch": 0.13265835929387332, "grad_norm": 3.0311946868896484, "learning_rate": 4.984647693539355e-06, "loss": 0.4092777371406555, "step": 511 }, { "epoch": 0.13291796469366562, "grad_norm": 2.5999233722686768, "learning_rate": 4.984537173551772e-06, "loss": 0.4086882472038269, "step": 512 }, { "epoch": 0.13317757009345793, "grad_norm": 4.2184624671936035, "learning_rate": 4.98442625854918e-06, "loss": 0.49779850244522095, "step": 513 }, { "epoch": 0.13343717549325027, "grad_norm": 3.8899524211883545, "learning_rate": 4.984314948551187e-06, "loss": 0.494964063167572, "step": 514 }, { "epoch": 0.13369678089304257, "grad_norm": 7.2834062576293945, "learning_rate": 4.98420324357747e-06, "loss": 0.5084041357040405, "step": 515 }, { "epoch": 0.13395638629283488, "grad_norm": 4.891847133636475, "learning_rate": 4.984091143647777e-06, "loss": 0.5360442399978638, "step": 516 }, { "epoch": 0.1342159916926272, "grad_norm": 2.4334144592285156, "learning_rate": 4.983978648781923e-06, "loss": 0.4584702253341675, "step": 517 }, { "epoch": 0.13447559709241952, "grad_norm": 3.2097818851470947, "learning_rate": 4.983865758999795e-06, "loss": 0.48532330989837646, "step": 518 }, { "epoch": 0.13473520249221183, "grad_norm": 4.330906391143799, "learning_rate": 4.98375247432135e-06, "loss": 0.39475011825561523, "step": 519 }, { "epoch": 0.13499480789200416, "grad_norm": 6.363665580749512, "learning_rate": 4.983638794766613e-06, "loss": 0.4808305501937866, "step": 520 }, { "epoch": 0.13525441329179647, "grad_norm": 2.5443828105926514, "learning_rate": 4.9835247203556815e-06, "loss": 0.5185126066207886, "step": 521 }, { "epoch": 0.13551401869158877, "grad_norm": 3.722109794616699, "learning_rate": 4.9834102511087205e-06, "loss": 0.40339022874832153, "step": 522 }, { "epoch": 0.1357736240913811, "grad_norm": 4.134383678436279, "learning_rate": 4.983295387045965e-06, "loss": 0.5547671914100647, "step": 523 }, { "epoch": 0.1360332294911734, "grad_norm": 6.506190776824951, "learning_rate": 4.98318012818772e-06, "loss": 0.4077463150024414, "step": 524 }, { "epoch": 0.13629283489096572, "grad_norm": 3.749915838241577, "learning_rate": 4.983064474554362e-06, "loss": 0.4277136027812958, "step": 525 }, { "epoch": 0.13655244029075805, "grad_norm": 9.579497337341309, "learning_rate": 4.9829484261663355e-06, "loss": 0.5516588687896729, "step": 526 }, { "epoch": 0.13681204569055036, "grad_norm": 17.138181686401367, "learning_rate": 4.982831983044155e-06, "loss": 0.39875268936157227, "step": 527 }, { "epoch": 0.13707165109034267, "grad_norm": 4.549004077911377, "learning_rate": 4.982715145208405e-06, "loss": 0.4262813329696655, "step": 528 }, { "epoch": 0.137331256490135, "grad_norm": 2.7037975788116455, "learning_rate": 4.982597912679739e-06, "loss": 0.3855251669883728, "step": 529 }, { "epoch": 0.1375908618899273, "grad_norm": 6.085561752319336, "learning_rate": 4.9824802854788825e-06, "loss": 0.5219559669494629, "step": 530 }, { "epoch": 0.1378504672897196, "grad_norm": 4.600220203399658, "learning_rate": 4.982362263626629e-06, "loss": 0.3820894956588745, "step": 531 }, { "epoch": 0.13811007268951195, "grad_norm": 4.9655070304870605, "learning_rate": 4.9822438471438404e-06, "loss": 0.4026579260826111, "step": 532 }, { "epoch": 0.13836967808930425, "grad_norm": 5.353662490844727, "learning_rate": 4.982125036051452e-06, "loss": 0.41213691234588623, "step": 533 }, { "epoch": 0.13862928348909656, "grad_norm": 3.993614673614502, "learning_rate": 4.982005830370466e-06, "loss": 0.5098104476928711, "step": 534 }, { "epoch": 0.1388888888888889, "grad_norm": 6.192975044250488, "learning_rate": 4.981886230121956e-06, "loss": 0.49874958395957947, "step": 535 }, { "epoch": 0.1391484942886812, "grad_norm": 5.07059907913208, "learning_rate": 4.981766235327062e-06, "loss": 0.4440418481826782, "step": 536 }, { "epoch": 0.1394080996884735, "grad_norm": 6.481316566467285, "learning_rate": 4.981645846007e-06, "loss": 0.41379866003990173, "step": 537 }, { "epoch": 0.13966770508826584, "grad_norm": 6.111998558044434, "learning_rate": 4.98152506218305e-06, "loss": 0.52619868516922, "step": 538 }, { "epoch": 0.13992731048805815, "grad_norm": 3.386018991470337, "learning_rate": 4.981403883876564e-06, "loss": 0.5061057806015015, "step": 539 }, { "epoch": 0.14018691588785046, "grad_norm": 2.7899527549743652, "learning_rate": 4.981282311108964e-06, "loss": 0.4079568386077881, "step": 540 }, { "epoch": 0.1404465212876428, "grad_norm": 8.241659164428711, "learning_rate": 4.98116034390174e-06, "loss": 0.5248178243637085, "step": 541 }, { "epoch": 0.1407061266874351, "grad_norm": 4.329916477203369, "learning_rate": 4.981037982276456e-06, "loss": 0.46312451362609863, "step": 542 }, { "epoch": 0.1409657320872274, "grad_norm": 3.1954569816589355, "learning_rate": 4.980915226254739e-06, "loss": 0.4299490451812744, "step": 543 }, { "epoch": 0.14122533748701974, "grad_norm": 3.7241311073303223, "learning_rate": 4.980792075858291e-06, "loss": 0.42715194821357727, "step": 544 }, { "epoch": 0.14148494288681204, "grad_norm": 4.107983589172363, "learning_rate": 4.9806685311088834e-06, "loss": 0.4441114068031311, "step": 545 }, { "epoch": 0.14174454828660435, "grad_norm": 4.320455551147461, "learning_rate": 4.980544592028354e-06, "loss": 0.40989696979522705, "step": 546 }, { "epoch": 0.14200415368639668, "grad_norm": 2.920130968093872, "learning_rate": 4.980420258638615e-06, "loss": 0.3952603340148926, "step": 547 }, { "epoch": 0.142263759086189, "grad_norm": 5.918212890625, "learning_rate": 4.980295530961643e-06, "loss": 0.46289169788360596, "step": 548 }, { "epoch": 0.1425233644859813, "grad_norm": 5.20995569229126, "learning_rate": 4.980170409019488e-06, "loss": 0.428875595331192, "step": 549 }, { "epoch": 0.14278296988577363, "grad_norm": 11.759183883666992, "learning_rate": 4.980044892834269e-06, "loss": 0.4097102880477905, "step": 550 }, { "epoch": 0.14304257528556594, "grad_norm": 5.842040538787842, "learning_rate": 4.979918982428174e-06, "loss": 0.49380311369895935, "step": 551 }, { "epoch": 0.14330218068535824, "grad_norm": 3.4100372791290283, "learning_rate": 4.9797926778234615e-06, "loss": 0.41192519664764404, "step": 552 }, { "epoch": 0.14356178608515058, "grad_norm": 4.203794956207275, "learning_rate": 4.9796659790424595e-06, "loss": 0.41799256205558777, "step": 553 }, { "epoch": 0.14382139148494288, "grad_norm": 3.9997501373291016, "learning_rate": 4.979538886107565e-06, "loss": 0.41496193408966064, "step": 554 }, { "epoch": 0.1440809968847352, "grad_norm": 3.9254534244537354, "learning_rate": 4.979411399041244e-06, "loss": 0.42151781916618347, "step": 555 }, { "epoch": 0.14434060228452752, "grad_norm": 3.4209046363830566, "learning_rate": 4.979283517866036e-06, "loss": 0.424995481967926, "step": 556 }, { "epoch": 0.14460020768431983, "grad_norm": 9.508252143859863, "learning_rate": 4.979155242604545e-06, "loss": 0.650414228439331, "step": 557 }, { "epoch": 0.14485981308411214, "grad_norm": 4.328948497772217, "learning_rate": 4.979026573279447e-06, "loss": 0.5573369860649109, "step": 558 }, { "epoch": 0.14511941848390447, "grad_norm": 6.04700231552124, "learning_rate": 4.97889750991349e-06, "loss": 0.4169745445251465, "step": 559 }, { "epoch": 0.14537902388369678, "grad_norm": 6.606906414031982, "learning_rate": 4.978768052529488e-06, "loss": 0.5362005233764648, "step": 560 }, { "epoch": 0.14563862928348908, "grad_norm": 5.128921985626221, "learning_rate": 4.978638201150327e-06, "loss": 0.4733973741531372, "step": 561 }, { "epoch": 0.14589823468328142, "grad_norm": 3.8689589500427246, "learning_rate": 4.9785079557989605e-06, "loss": 0.4761679768562317, "step": 562 }, { "epoch": 0.14615784008307373, "grad_norm": 4.060021877288818, "learning_rate": 4.978377316498414e-06, "loss": 0.48368531465530396, "step": 563 }, { "epoch": 0.14641744548286603, "grad_norm": 2.960536241531372, "learning_rate": 4.97824628327178e-06, "loss": 0.42662525177001953, "step": 564 }, { "epoch": 0.14667705088265837, "grad_norm": 3.243180274963379, "learning_rate": 4.978114856142224e-06, "loss": 0.4614597260951996, "step": 565 }, { "epoch": 0.14693665628245067, "grad_norm": 3.9971086978912354, "learning_rate": 4.977983035132977e-06, "loss": 0.46408042311668396, "step": 566 }, { "epoch": 0.14719626168224298, "grad_norm": 4.716899394989014, "learning_rate": 4.977850820267346e-06, "loss": 0.47218403220176697, "step": 567 }, { "epoch": 0.1474558670820353, "grad_norm": 2.64581298828125, "learning_rate": 4.9777182115686995e-06, "loss": 0.4388694763183594, "step": 568 }, { "epoch": 0.14771547248182762, "grad_norm": 4.741995334625244, "learning_rate": 4.977585209060481e-06, "loss": 0.49483489990234375, "step": 569 }, { "epoch": 0.14797507788161993, "grad_norm": 5.847671031951904, "learning_rate": 4.977451812766203e-06, "loss": 0.5682700872421265, "step": 570 }, { "epoch": 0.14823468328141226, "grad_norm": 5.8387451171875, "learning_rate": 4.977318022709445e-06, "loss": 0.5723843574523926, "step": 571 }, { "epoch": 0.14849428868120457, "grad_norm": 3.9587085247039795, "learning_rate": 4.977183838913862e-06, "loss": 0.4242345690727234, "step": 572 }, { "epoch": 0.14875389408099687, "grad_norm": 8.61888313293457, "learning_rate": 4.97704926140317e-06, "loss": 0.4598362445831299, "step": 573 }, { "epoch": 0.1490134994807892, "grad_norm": 5.250871181488037, "learning_rate": 4.9769142902011615e-06, "loss": 0.48312264680862427, "step": 574 }, { "epoch": 0.14927310488058151, "grad_norm": 4.567917346954346, "learning_rate": 4.9767789253316964e-06, "loss": 0.47919631004333496, "step": 575 }, { "epoch": 0.14953271028037382, "grad_norm": 4.486226558685303, "learning_rate": 4.976643166818704e-06, "loss": 0.4369913339614868, "step": 576 }, { "epoch": 0.14979231568016615, "grad_norm": 6.5155229568481445, "learning_rate": 4.976507014686183e-06, "loss": 0.577171266078949, "step": 577 }, { "epoch": 0.15005192107995846, "grad_norm": 4.1454386711120605, "learning_rate": 4.976370468958201e-06, "loss": 0.4155636429786682, "step": 578 }, { "epoch": 0.15031152647975077, "grad_norm": 2.3851287364959717, "learning_rate": 4.976233529658898e-06, "loss": 0.4193977117538452, "step": 579 }, { "epoch": 0.1505711318795431, "grad_norm": 4.5558552742004395, "learning_rate": 4.9760961968124815e-06, "loss": 0.46000248193740845, "step": 580 }, { "epoch": 0.1508307372793354, "grad_norm": 3.5343124866485596, "learning_rate": 4.975958470443228e-06, "loss": 0.3972896337509155, "step": 581 }, { "epoch": 0.15109034267912771, "grad_norm": 2.8353583812713623, "learning_rate": 4.9758203505754845e-06, "loss": 0.4954490661621094, "step": 582 }, { "epoch": 0.15134994807892005, "grad_norm": 3.0313079357147217, "learning_rate": 4.975681837233668e-06, "loss": 0.3851563334465027, "step": 583 }, { "epoch": 0.15160955347871236, "grad_norm": 5.1892523765563965, "learning_rate": 4.975542930442263e-06, "loss": 0.4293341040611267, "step": 584 }, { "epoch": 0.15186915887850466, "grad_norm": 5.688177108764648, "learning_rate": 4.975403630225827e-06, "loss": 0.5560200214385986, "step": 585 }, { "epoch": 0.152128764278297, "grad_norm": 3.315228223800659, "learning_rate": 4.975263936608984e-06, "loss": 0.34180986881256104, "step": 586 }, { "epoch": 0.1523883696780893, "grad_norm": 3.361626386642456, "learning_rate": 4.975123849616429e-06, "loss": 0.4074600040912628, "step": 587 }, { "epoch": 0.1526479750778816, "grad_norm": 3.6972103118896484, "learning_rate": 4.974983369272925e-06, "loss": 0.3683452010154724, "step": 588 }, { "epoch": 0.15290758047767394, "grad_norm": 6.698731422424316, "learning_rate": 4.9748424956033076e-06, "loss": 0.45715487003326416, "step": 589 }, { "epoch": 0.15316718587746625, "grad_norm": 3.281827926635742, "learning_rate": 4.9747012286324784e-06, "loss": 0.39563119411468506, "step": 590 }, { "epoch": 0.15342679127725856, "grad_norm": 4.984228610992432, "learning_rate": 4.9745595683854115e-06, "loss": 0.4463680386543274, "step": 591 }, { "epoch": 0.1536863966770509, "grad_norm": 4.068614959716797, "learning_rate": 4.974417514887148e-06, "loss": 0.48462384939193726, "step": 592 }, { "epoch": 0.1539460020768432, "grad_norm": 6.972237586975098, "learning_rate": 4.9742750681628e-06, "loss": 0.503786027431488, "step": 593 }, { "epoch": 0.1542056074766355, "grad_norm": 4.104424953460693, "learning_rate": 4.97413222823755e-06, "loss": 0.41847464442253113, "step": 594 }, { "epoch": 0.15446521287642784, "grad_norm": 2.997044324874878, "learning_rate": 4.973988995136648e-06, "loss": 0.4828353524208069, "step": 595 }, { "epoch": 0.15472481827622014, "grad_norm": 2.6336605548858643, "learning_rate": 4.9738453688854145e-06, "loss": 0.4221630394458771, "step": 596 }, { "epoch": 0.15498442367601245, "grad_norm": 5.9812445640563965, "learning_rate": 4.973701349509238e-06, "loss": 0.4861409664154053, "step": 597 }, { "epoch": 0.15524402907580478, "grad_norm": 5.672513961791992, "learning_rate": 4.973556937033579e-06, "loss": 0.38777315616607666, "step": 598 }, { "epoch": 0.1555036344755971, "grad_norm": 2.4971585273742676, "learning_rate": 4.973412131483966e-06, "loss": 0.4191524088382721, "step": 599 }, { "epoch": 0.1557632398753894, "grad_norm": 3.2055506706237793, "learning_rate": 4.973266932885999e-06, "loss": 0.4037844240665436, "step": 600 }, { "epoch": 0.15602284527518173, "grad_norm": 4.473286151885986, "learning_rate": 4.973121341265343e-06, "loss": 0.48081618547439575, "step": 601 }, { "epoch": 0.15628245067497404, "grad_norm": 5.699620246887207, "learning_rate": 4.9729753566477376e-06, "loss": 0.5168325901031494, "step": 602 }, { "epoch": 0.15654205607476634, "grad_norm": 3.6227400302886963, "learning_rate": 4.972828979058988e-06, "loss": 0.5178072452545166, "step": 603 }, { "epoch": 0.15680166147455868, "grad_norm": 3.4260358810424805, "learning_rate": 4.972682208524971e-06, "loss": 0.4298555254936218, "step": 604 }, { "epoch": 0.15706126687435099, "grad_norm": 4.041790008544922, "learning_rate": 4.972535045071632e-06, "loss": 0.4133217930793762, "step": 605 }, { "epoch": 0.1573208722741433, "grad_norm": 2.5895438194274902, "learning_rate": 4.972387488724986e-06, "loss": 0.4482805132865906, "step": 606 }, { "epoch": 0.15758047767393563, "grad_norm": 3.632769823074341, "learning_rate": 4.972239539511119e-06, "loss": 0.44455835223197937, "step": 607 }, { "epoch": 0.15784008307372793, "grad_norm": 4.348120212554932, "learning_rate": 4.9720911974561835e-06, "loss": 0.4146198034286499, "step": 608 }, { "epoch": 0.15809968847352024, "grad_norm": 8.04554271697998, "learning_rate": 4.971942462586403e-06, "loss": 0.48849353194236755, "step": 609 }, { "epoch": 0.15835929387331257, "grad_norm": 2.885728120803833, "learning_rate": 4.971793334928071e-06, "loss": 0.3866543173789978, "step": 610 }, { "epoch": 0.15861889927310488, "grad_norm": 9.579166412353516, "learning_rate": 4.9716438145075505e-06, "loss": 0.5258530378341675, "step": 611 }, { "epoch": 0.1588785046728972, "grad_norm": 8.94273567199707, "learning_rate": 4.971493901351272e-06, "loss": 0.48555558919906616, "step": 612 }, { "epoch": 0.15913811007268952, "grad_norm": 4.713988304138184, "learning_rate": 4.971343595485736e-06, "loss": 0.5618215203285217, "step": 613 }, { "epoch": 0.15939771547248183, "grad_norm": 5.555334568023682, "learning_rate": 4.971192896937516e-06, "loss": 0.4721204340457916, "step": 614 }, { "epoch": 0.15965732087227413, "grad_norm": 2.9507720470428467, "learning_rate": 4.97104180573325e-06, "loss": 0.39968985319137573, "step": 615 }, { "epoch": 0.15991692627206647, "grad_norm": 9.817140579223633, "learning_rate": 4.970890321899647e-06, "loss": 0.4781028628349304, "step": 616 }, { "epoch": 0.16017653167185877, "grad_norm": 4.3003249168396, "learning_rate": 4.970738445463488e-06, "loss": 0.5167607069015503, "step": 617 }, { "epoch": 0.16043613707165108, "grad_norm": 4.1421966552734375, "learning_rate": 4.9705861764516195e-06, "loss": 0.5050675272941589, "step": 618 }, { "epoch": 0.16069574247144341, "grad_norm": 7.328611850738525, "learning_rate": 4.97043351489096e-06, "loss": 0.4116460382938385, "step": 619 }, { "epoch": 0.16095534787123572, "grad_norm": 6.648682594299316, "learning_rate": 4.970280460808495e-06, "loss": 0.5315380096435547, "step": 620 }, { "epoch": 0.16121495327102803, "grad_norm": 4.4059014320373535, "learning_rate": 4.970127014231283e-06, "loss": 0.3963509500026703, "step": 621 }, { "epoch": 0.16147455867082036, "grad_norm": 4.072173118591309, "learning_rate": 4.969973175186449e-06, "loss": 0.4747138023376465, "step": 622 }, { "epoch": 0.16173416407061267, "grad_norm": 5.105856895446777, "learning_rate": 4.969818943701189e-06, "loss": 0.4656270742416382, "step": 623 }, { "epoch": 0.16199376947040497, "grad_norm": 4.4483442306518555, "learning_rate": 4.969664319802766e-06, "loss": 0.4140931963920593, "step": 624 }, { "epoch": 0.1622533748701973, "grad_norm": 4.603686332702637, "learning_rate": 4.9695093035185154e-06, "loss": 0.4236321449279785, "step": 625 }, { "epoch": 0.16251298026998962, "grad_norm": 3.7857167720794678, "learning_rate": 4.96935389487584e-06, "loss": 0.3685057759284973, "step": 626 }, { "epoch": 0.16277258566978192, "grad_norm": 4.881899833679199, "learning_rate": 4.969198093902212e-06, "loss": 0.4915599226951599, "step": 627 }, { "epoch": 0.16303219106957426, "grad_norm": 3.0970046520233154, "learning_rate": 4.969041900625174e-06, "loss": 0.418434739112854, "step": 628 }, { "epoch": 0.16329179646936656, "grad_norm": 4.180285930633545, "learning_rate": 4.968885315072338e-06, "loss": 0.45569759607315063, "step": 629 }, { "epoch": 0.16355140186915887, "grad_norm": 4.2382683753967285, "learning_rate": 4.968728337271383e-06, "loss": 0.48302268981933594, "step": 630 }, { "epoch": 0.1638110072689512, "grad_norm": 3.7724993228912354, "learning_rate": 4.968570967250061e-06, "loss": 0.39208686351776123, "step": 631 }, { "epoch": 0.1640706126687435, "grad_norm": 4.125081539154053, "learning_rate": 4.9684132050361896e-06, "loss": 0.42455756664276123, "step": 632 }, { "epoch": 0.16433021806853582, "grad_norm": 4.787883281707764, "learning_rate": 4.968255050657658e-06, "loss": 0.44778934121131897, "step": 633 }, { "epoch": 0.16458982346832815, "grad_norm": 2.9254777431488037, "learning_rate": 4.968096504142426e-06, "loss": 0.471075177192688, "step": 634 }, { "epoch": 0.16484942886812046, "grad_norm": 5.288440704345703, "learning_rate": 4.96793756551852e-06, "loss": 0.39557987451553345, "step": 635 }, { "epoch": 0.16510903426791276, "grad_norm": 5.108372688293457, "learning_rate": 4.967778234814035e-06, "loss": 0.40972307324409485, "step": 636 }, { "epoch": 0.1653686396677051, "grad_norm": 5.684891223907471, "learning_rate": 4.96761851205714e-06, "loss": 0.5104650259017944, "step": 637 }, { "epoch": 0.1656282450674974, "grad_norm": 5.955086708068848, "learning_rate": 4.9674583972760676e-06, "loss": 0.4897901713848114, "step": 638 }, { "epoch": 0.1658878504672897, "grad_norm": 5.182025909423828, "learning_rate": 4.967297890499124e-06, "loss": 0.539067268371582, "step": 639 }, { "epoch": 0.16614745586708204, "grad_norm": 4.595883846282959, "learning_rate": 4.967136991754683e-06, "loss": 0.37941861152648926, "step": 640 }, { "epoch": 0.16640706126687435, "grad_norm": 8.570964813232422, "learning_rate": 4.966975701071188e-06, "loss": 0.4100821018218994, "step": 641 }, { "epoch": 0.16666666666666666, "grad_norm": 7.90551233291626, "learning_rate": 4.96681401847715e-06, "loss": 0.48640918731689453, "step": 642 }, { "epoch": 0.166926272066459, "grad_norm": 5.898240089416504, "learning_rate": 4.966651944001153e-06, "loss": 0.5376713275909424, "step": 643 }, { "epoch": 0.1671858774662513, "grad_norm": 5.85093355178833, "learning_rate": 4.966489477671846e-06, "loss": 0.4080977439880371, "step": 644 }, { "epoch": 0.1674454828660436, "grad_norm": 8.510159492492676, "learning_rate": 4.966326619517951e-06, "loss": 0.49403834342956543, "step": 645 }, { "epoch": 0.16770508826583594, "grad_norm": 6.806706428527832, "learning_rate": 4.966163369568256e-06, "loss": 0.38133659958839417, "step": 646 }, { "epoch": 0.16796469366562825, "grad_norm": 7.899182319641113, "learning_rate": 4.965999727851621e-06, "loss": 0.5329399108886719, "step": 647 }, { "epoch": 0.16822429906542055, "grad_norm": 4.421777725219727, "learning_rate": 4.965835694396973e-06, "loss": 0.4213755428791046, "step": 648 }, { "epoch": 0.16848390446521289, "grad_norm": 4.845521450042725, "learning_rate": 4.965671269233312e-06, "loss": 0.5084894299507141, "step": 649 }, { "epoch": 0.1687435098650052, "grad_norm": 10.195366859436035, "learning_rate": 4.9655064523897015e-06, "loss": 0.46885034441947937, "step": 650 }, { "epoch": 0.1690031152647975, "grad_norm": 10.24155330657959, "learning_rate": 4.965341243895279e-06, "loss": 0.6030123233795166, "step": 651 }, { "epoch": 0.16926272066458983, "grad_norm": 7.586025238037109, "learning_rate": 4.9651756437792485e-06, "loss": 0.539675235748291, "step": 652 }, { "epoch": 0.16952232606438214, "grad_norm": 5.464954853057861, "learning_rate": 4.965009652070885e-06, "loss": 0.5394687056541443, "step": 653 }, { "epoch": 0.16978193146417445, "grad_norm": 6.105719089508057, "learning_rate": 4.964843268799533e-06, "loss": 0.41737058758735657, "step": 654 }, { "epoch": 0.17004153686396678, "grad_norm": 6.942319393157959, "learning_rate": 4.964676493994604e-06, "loss": 0.47099947929382324, "step": 655 }, { "epoch": 0.1703011422637591, "grad_norm": 3.616480827331543, "learning_rate": 4.964509327685579e-06, "loss": 0.39057213068008423, "step": 656 }, { "epoch": 0.1705607476635514, "grad_norm": 4.719355583190918, "learning_rate": 4.964341769902012e-06, "loss": 0.5351403951644897, "step": 657 }, { "epoch": 0.17082035306334373, "grad_norm": 4.284090042114258, "learning_rate": 4.964173820673521e-06, "loss": 0.3904067575931549, "step": 658 }, { "epoch": 0.17107995846313603, "grad_norm": 5.574571132659912, "learning_rate": 4.964005480029797e-06, "loss": 0.39478790760040283, "step": 659 }, { "epoch": 0.17133956386292834, "grad_norm": 4.723188400268555, "learning_rate": 4.963836748000597e-06, "loss": 0.4285065531730652, "step": 660 }, { "epoch": 0.17159916926272067, "grad_norm": 4.305122375488281, "learning_rate": 4.963667624615751e-06, "loss": 0.43415457010269165, "step": 661 }, { "epoch": 0.17185877466251298, "grad_norm": 2.810612678527832, "learning_rate": 4.9634981099051545e-06, "loss": 0.43332165479660034, "step": 662 }, { "epoch": 0.1721183800623053, "grad_norm": 4.261164665222168, "learning_rate": 4.963328203898775e-06, "loss": 0.46064701676368713, "step": 663 }, { "epoch": 0.17237798546209762, "grad_norm": 7.224287986755371, "learning_rate": 4.963157906626648e-06, "loss": 0.486758828163147, "step": 664 }, { "epoch": 0.17263759086188993, "grad_norm": 4.987356185913086, "learning_rate": 4.9629872181188774e-06, "loss": 0.4503384828567505, "step": 665 }, { "epoch": 0.17289719626168223, "grad_norm": 3.12707781791687, "learning_rate": 4.962816138405637e-06, "loss": 0.43647223711013794, "step": 666 }, { "epoch": 0.17315680166147457, "grad_norm": 3.582832098007202, "learning_rate": 4.9626446675171704e-06, "loss": 0.3971416652202606, "step": 667 }, { "epoch": 0.17341640706126688, "grad_norm": 6.581991672515869, "learning_rate": 4.962472805483789e-06, "loss": 0.4332820773124695, "step": 668 }, { "epoch": 0.17367601246105918, "grad_norm": 7.125083923339844, "learning_rate": 4.962300552335875e-06, "loss": 0.47022899985313416, "step": 669 }, { "epoch": 0.17393561786085152, "grad_norm": 3.769831657409668, "learning_rate": 4.962127908103878e-06, "loss": 0.4841687083244324, "step": 670 }, { "epoch": 0.17419522326064382, "grad_norm": 3.601754665374756, "learning_rate": 4.961954872818318e-06, "loss": 0.44817817211151123, "step": 671 }, { "epoch": 0.17445482866043613, "grad_norm": 6.185761451721191, "learning_rate": 4.961781446509784e-06, "loss": 0.5474337339401245, "step": 672 }, { "epoch": 0.17471443406022846, "grad_norm": 5.629013538360596, "learning_rate": 4.961607629208933e-06, "loss": 0.3810103237628937, "step": 673 }, { "epoch": 0.17497403946002077, "grad_norm": 4.957672595977783, "learning_rate": 4.961433420946492e-06, "loss": 0.5747833251953125, "step": 674 }, { "epoch": 0.17523364485981308, "grad_norm": 2.552300453186035, "learning_rate": 4.961258821753257e-06, "loss": 0.4126914143562317, "step": 675 }, { "epoch": 0.1754932502596054, "grad_norm": 3.515981912612915, "learning_rate": 4.961083831660095e-06, "loss": 0.4638293981552124, "step": 676 }, { "epoch": 0.17575285565939772, "grad_norm": 4.556919097900391, "learning_rate": 4.960908450697937e-06, "loss": 0.536652684211731, "step": 677 }, { "epoch": 0.17601246105919002, "grad_norm": 7.081160545349121, "learning_rate": 4.960732678897788e-06, "loss": 0.4630212187767029, "step": 678 }, { "epoch": 0.17627206645898236, "grad_norm": 13.346535682678223, "learning_rate": 4.960556516290721e-06, "loss": 0.517835259437561, "step": 679 }, { "epoch": 0.17653167185877466, "grad_norm": 2.24041485786438, "learning_rate": 4.960379962907878e-06, "loss": 0.4379546642303467, "step": 680 }, { "epoch": 0.17679127725856697, "grad_norm": 3.7334814071655273, "learning_rate": 4.960203018780467e-06, "loss": 0.3902384042739868, "step": 681 }, { "epoch": 0.1770508826583593, "grad_norm": 9.108603477478027, "learning_rate": 4.9600256839397695e-06, "loss": 0.4706420600414276, "step": 682 }, { "epoch": 0.1773104880581516, "grad_norm": 8.317928314208984, "learning_rate": 4.959847958417134e-06, "loss": 0.4585955739021301, "step": 683 }, { "epoch": 0.17757009345794392, "grad_norm": 8.815759658813477, "learning_rate": 4.959669842243979e-06, "loss": 0.49471423029899597, "step": 684 }, { "epoch": 0.17782969885773625, "grad_norm": 8.06460952758789, "learning_rate": 4.95949133545179e-06, "loss": 0.5824753046035767, "step": 685 }, { "epoch": 0.17808930425752856, "grad_norm": 5.479262351989746, "learning_rate": 4.959312438072123e-06, "loss": 0.48274680972099304, "step": 686 }, { "epoch": 0.17834890965732086, "grad_norm": 8.478203773498535, "learning_rate": 4.959133150136605e-06, "loss": 0.5851738452911377, "step": 687 }, { "epoch": 0.1786085150571132, "grad_norm": 11.71452522277832, "learning_rate": 4.958953471676927e-06, "loss": 0.47065305709838867, "step": 688 }, { "epoch": 0.1788681204569055, "grad_norm": 2.9635086059570312, "learning_rate": 4.958773402724854e-06, "loss": 0.43936803936958313, "step": 689 }, { "epoch": 0.1791277258566978, "grad_norm": 3.042031764984131, "learning_rate": 4.958592943312218e-06, "loss": 0.4285552501678467, "step": 690 }, { "epoch": 0.17938733125649015, "grad_norm": 8.157258987426758, "learning_rate": 4.958412093470919e-06, "loss": 0.5645010471343994, "step": 691 }, { "epoch": 0.17964693665628245, "grad_norm": 7.892404556274414, "learning_rate": 4.958230853232928e-06, "loss": 0.510260820388794, "step": 692 }, { "epoch": 0.17990654205607476, "grad_norm": 6.4505228996276855, "learning_rate": 4.958049222630285e-06, "loss": 0.5189645290374756, "step": 693 }, { "epoch": 0.1801661474558671, "grad_norm": 5.481898307800293, "learning_rate": 4.957867201695096e-06, "loss": 0.45478177070617676, "step": 694 }, { "epoch": 0.1804257528556594, "grad_norm": 3.9167394638061523, "learning_rate": 4.957684790459539e-06, "loss": 0.43416672945022583, "step": 695 }, { "epoch": 0.1806853582554517, "grad_norm": 7.607226371765137, "learning_rate": 4.957501988955861e-06, "loss": 0.5374035835266113, "step": 696 }, { "epoch": 0.18094496365524404, "grad_norm": 5.927099227905273, "learning_rate": 4.9573187972163765e-06, "loss": 0.4135194718837738, "step": 697 }, { "epoch": 0.18120456905503635, "grad_norm": 3.724628448486328, "learning_rate": 4.9571352152734696e-06, "loss": 0.45288804173469543, "step": 698 }, { "epoch": 0.18146417445482865, "grad_norm": 2.8260936737060547, "learning_rate": 4.956951243159593e-06, "loss": 0.42852991819381714, "step": 699 }, { "epoch": 0.181723779854621, "grad_norm": 2.9753518104553223, "learning_rate": 4.956766880907269e-06, "loss": 0.40890052914619446, "step": 700 }, { "epoch": 0.1819833852544133, "grad_norm": 3.800494909286499, "learning_rate": 4.956582128549089e-06, "loss": 0.3956831097602844, "step": 701 }, { "epoch": 0.1822429906542056, "grad_norm": 4.737961292266846, "learning_rate": 4.9563969861177126e-06, "loss": 0.4923557937145233, "step": 702 }, { "epoch": 0.18250259605399793, "grad_norm": 5.0216965675354, "learning_rate": 4.9562114536458686e-06, "loss": 0.5095490217208862, "step": 703 }, { "epoch": 0.18276220145379024, "grad_norm": 3.786186933517456, "learning_rate": 4.956025531166356e-06, "loss": 0.44273895025253296, "step": 704 }, { "epoch": 0.18302180685358255, "grad_norm": 5.6138410568237305, "learning_rate": 4.955839218712039e-06, "loss": 0.4656902551651001, "step": 705 }, { "epoch": 0.18328141225337488, "grad_norm": 4.000116348266602, "learning_rate": 4.955652516315856e-06, "loss": 0.4976225793361664, "step": 706 }, { "epoch": 0.1835410176531672, "grad_norm": 2.0461161136627197, "learning_rate": 4.955465424010812e-06, "loss": 0.4171741008758545, "step": 707 }, { "epoch": 0.1838006230529595, "grad_norm": 7.56063985824585, "learning_rate": 4.955277941829978e-06, "loss": 0.3963194489479065, "step": 708 }, { "epoch": 0.18406022845275183, "grad_norm": 6.969409465789795, "learning_rate": 4.955090069806499e-06, "loss": 0.45987266302108765, "step": 709 }, { "epoch": 0.18431983385254413, "grad_norm": 3.3605430126190186, "learning_rate": 4.954901807973586e-06, "loss": 0.3482726514339447, "step": 710 }, { "epoch": 0.18457943925233644, "grad_norm": 5.0814900398254395, "learning_rate": 4.954713156364517e-06, "loss": 0.40166574716567993, "step": 711 }, { "epoch": 0.18483904465212878, "grad_norm": 4.4659905433654785, "learning_rate": 4.954524115012645e-06, "loss": 0.41316667199134827, "step": 712 }, { "epoch": 0.18509865005192108, "grad_norm": 3.1704609394073486, "learning_rate": 4.9543346839513856e-06, "loss": 0.39536386728286743, "step": 713 }, { "epoch": 0.1853582554517134, "grad_norm": 2.3061976432800293, "learning_rate": 4.954144863214226e-06, "loss": 0.4178878962993622, "step": 714 }, { "epoch": 0.18561786085150572, "grad_norm": 3.7494099140167236, "learning_rate": 4.953954652834724e-06, "loss": 0.4178115725517273, "step": 715 }, { "epoch": 0.18587746625129803, "grad_norm": 4.510622978210449, "learning_rate": 4.953764052846502e-06, "loss": 0.4486280083656311, "step": 716 }, { "epoch": 0.18613707165109034, "grad_norm": 3.647369146347046, "learning_rate": 4.953573063283257e-06, "loss": 0.4088967442512512, "step": 717 }, { "epoch": 0.18639667705088267, "grad_norm": 3.0176632404327393, "learning_rate": 4.953381684178748e-06, "loss": 0.37879109382629395, "step": 718 }, { "epoch": 0.18665628245067498, "grad_norm": 7.918790817260742, "learning_rate": 4.9531899155668076e-06, "loss": 0.42340534925460815, "step": 719 }, { "epoch": 0.18691588785046728, "grad_norm": 3.502448081970215, "learning_rate": 4.952997757481338e-06, "loss": 0.4850282669067383, "step": 720 }, { "epoch": 0.18717549325025962, "grad_norm": 8.69753360748291, "learning_rate": 4.952805209956306e-06, "loss": 0.5380014181137085, "step": 721 }, { "epoch": 0.18743509865005192, "grad_norm": 4.3966965675354, "learning_rate": 4.95261227302575e-06, "loss": 0.574235200881958, "step": 722 }, { "epoch": 0.18769470404984423, "grad_norm": 3.5433995723724365, "learning_rate": 4.952418946723778e-06, "loss": 0.45772045850753784, "step": 723 }, { "epoch": 0.18795430944963656, "grad_norm": 4.4864068031311035, "learning_rate": 4.952225231084565e-06, "loss": 0.43749865889549255, "step": 724 }, { "epoch": 0.18821391484942887, "grad_norm": 3.328745126724243, "learning_rate": 4.9520311261423556e-06, "loss": 0.4867052733898163, "step": 725 }, { "epoch": 0.18847352024922118, "grad_norm": 3.0809388160705566, "learning_rate": 4.951836631931461e-06, "loss": 0.4378279447555542, "step": 726 }, { "epoch": 0.1887331256490135, "grad_norm": 3.1118595600128174, "learning_rate": 4.951641748486268e-06, "loss": 0.38545888662338257, "step": 727 }, { "epoch": 0.18899273104880582, "grad_norm": 3.37922739982605, "learning_rate": 4.951446475841223e-06, "loss": 0.4769434928894043, "step": 728 }, { "epoch": 0.18925233644859812, "grad_norm": 4.182854652404785, "learning_rate": 4.951250814030847e-06, "loss": 0.5307275056838989, "step": 729 }, { "epoch": 0.18951194184839046, "grad_norm": 2.090557336807251, "learning_rate": 4.951054763089731e-06, "loss": 0.4156108498573303, "step": 730 }, { "epoch": 0.18977154724818276, "grad_norm": 5.872241973876953, "learning_rate": 4.95085832305253e-06, "loss": 0.5703897476196289, "step": 731 }, { "epoch": 0.19003115264797507, "grad_norm": 9.071344375610352, "learning_rate": 4.950661493953969e-06, "loss": 0.5317680835723877, "step": 732 }, { "epoch": 0.1902907580477674, "grad_norm": 3.8356685638427734, "learning_rate": 4.950464275828845e-06, "loss": 0.3938220143318176, "step": 733 }, { "epoch": 0.1905503634475597, "grad_norm": 2.8443355560302734, "learning_rate": 4.9502666687120215e-06, "loss": 0.40824997425079346, "step": 734 }, { "epoch": 0.19080996884735202, "grad_norm": 4.527146339416504, "learning_rate": 4.95006867263843e-06, "loss": 0.4140029549598694, "step": 735 }, { "epoch": 0.19106957424714435, "grad_norm": 4.2836785316467285, "learning_rate": 4.949870287643072e-06, "loss": 0.45423564314842224, "step": 736 }, { "epoch": 0.19132917964693666, "grad_norm": 3.538870334625244, "learning_rate": 4.949671513761018e-06, "loss": 0.43747422099113464, "step": 737 }, { "epoch": 0.19158878504672897, "grad_norm": 2.8819334506988525, "learning_rate": 4.949472351027405e-06, "loss": 0.47545334696769714, "step": 738 }, { "epoch": 0.1918483904465213, "grad_norm": 3.5318076610565186, "learning_rate": 4.949272799477442e-06, "loss": 0.4359532594680786, "step": 739 }, { "epoch": 0.1921079958463136, "grad_norm": 3.863659381866455, "learning_rate": 4.949072859146406e-06, "loss": 0.38639605045318604, "step": 740 }, { "epoch": 0.1923676012461059, "grad_norm": 3.8841335773468018, "learning_rate": 4.948872530069639e-06, "loss": 0.4368569850921631, "step": 741 }, { "epoch": 0.19262720664589825, "grad_norm": 4.807188034057617, "learning_rate": 4.948671812282557e-06, "loss": 0.44798439741134644, "step": 742 }, { "epoch": 0.19288681204569055, "grad_norm": 2.8321621417999268, "learning_rate": 4.948470705820642e-06, "loss": 0.41660308837890625, "step": 743 }, { "epoch": 0.19314641744548286, "grad_norm": 2.581601619720459, "learning_rate": 4.948269210719443e-06, "loss": 0.42458805441856384, "step": 744 }, { "epoch": 0.1934060228452752, "grad_norm": 2.2088348865509033, "learning_rate": 4.948067327014583e-06, "loss": 0.39587146043777466, "step": 745 }, { "epoch": 0.1936656282450675, "grad_norm": 7.185145378112793, "learning_rate": 4.947865054741748e-06, "loss": 0.42627274990081787, "step": 746 }, { "epoch": 0.1939252336448598, "grad_norm": 4.5549774169921875, "learning_rate": 4.947662393936695e-06, "loss": 0.5785468220710754, "step": 747 }, { "epoch": 0.19418483904465214, "grad_norm": 6.0595808029174805, "learning_rate": 4.947459344635251e-06, "loss": 0.4669124186038971, "step": 748 }, { "epoch": 0.19444444444444445, "grad_norm": 3.2883641719818115, "learning_rate": 4.9472559068733104e-06, "loss": 0.4661770164966583, "step": 749 }, { "epoch": 0.19470404984423675, "grad_norm": 3.9111990928649902, "learning_rate": 4.9470520806868356e-06, "loss": 0.4364955425262451, "step": 750 }, { "epoch": 0.1949636552440291, "grad_norm": 3.150069236755371, "learning_rate": 4.946847866111859e-06, "loss": 0.4185783267021179, "step": 751 }, { "epoch": 0.1952232606438214, "grad_norm": 3.2558140754699707, "learning_rate": 4.9466432631844805e-06, "loss": 0.40691065788269043, "step": 752 }, { "epoch": 0.1954828660436137, "grad_norm": 2.6814541816711426, "learning_rate": 4.946438271940869e-06, "loss": 0.4250001311302185, "step": 753 }, { "epoch": 0.19574247144340604, "grad_norm": 4.595742225646973, "learning_rate": 4.946232892417264e-06, "loss": 0.39600804448127747, "step": 754 }, { "epoch": 0.19600207684319834, "grad_norm": 5.85060453414917, "learning_rate": 4.94602712464997e-06, "loss": 0.5552061200141907, "step": 755 }, { "epoch": 0.19626168224299065, "grad_norm": 3.2800722122192383, "learning_rate": 4.945820968675363e-06, "loss": 0.48260900378227234, "step": 756 }, { "epoch": 0.19652128764278298, "grad_norm": 3.6250128746032715, "learning_rate": 4.945614424529886e-06, "loss": 0.405799925327301, "step": 757 }, { "epoch": 0.1967808930425753, "grad_norm": 5.821615219116211, "learning_rate": 4.945407492250052e-06, "loss": 0.5626763701438904, "step": 758 }, { "epoch": 0.1970404984423676, "grad_norm": 2.8049557209014893, "learning_rate": 4.945200171872442e-06, "loss": 0.3546113073825836, "step": 759 }, { "epoch": 0.19730010384215993, "grad_norm": 5.636106491088867, "learning_rate": 4.944992463433704e-06, "loss": 0.43974414467811584, "step": 760 }, { "epoch": 0.19755970924195224, "grad_norm": 4.18052864074707, "learning_rate": 4.944784366970558e-06, "loss": 0.44029513001441956, "step": 761 }, { "epoch": 0.19781931464174454, "grad_norm": 3.7078254222869873, "learning_rate": 4.944575882519789e-06, "loss": 0.4075814485549927, "step": 762 }, { "epoch": 0.19807892004153688, "grad_norm": 6.579445838928223, "learning_rate": 4.944367010118254e-06, "loss": 0.5063996315002441, "step": 763 }, { "epoch": 0.19833852544132918, "grad_norm": 2.9166486263275146, "learning_rate": 4.944157749802876e-06, "loss": 0.4829210937023163, "step": 764 }, { "epoch": 0.1985981308411215, "grad_norm": 6.452652931213379, "learning_rate": 4.9439481016106465e-06, "loss": 0.4835324287414551, "step": 765 }, { "epoch": 0.19885773624091382, "grad_norm": 4.73895263671875, "learning_rate": 4.943738065578628e-06, "loss": 0.572910487651825, "step": 766 }, { "epoch": 0.19911734164070613, "grad_norm": 6.369050979614258, "learning_rate": 4.943527641743949e-06, "loss": 0.47956758737564087, "step": 767 }, { "epoch": 0.19937694704049844, "grad_norm": 5.177425384521484, "learning_rate": 4.9433168301438084e-06, "loss": 0.4568644165992737, "step": 768 }, { "epoch": 0.19963655244029077, "grad_norm": 3.682255744934082, "learning_rate": 4.943105630815472e-06, "loss": 0.5029811859130859, "step": 769 }, { "epoch": 0.19989615784008308, "grad_norm": 6.805792331695557, "learning_rate": 4.942894043796276e-06, "loss": 0.4354338049888611, "step": 770 }, { "epoch": 0.20015576323987538, "grad_norm": 2.5370302200317383, "learning_rate": 4.942682069123623e-06, "loss": 0.3776189088821411, "step": 771 }, { "epoch": 0.20041536863966772, "grad_norm": 2.3517653942108154, "learning_rate": 4.942469706834987e-06, "loss": 0.3810550570487976, "step": 772 }, { "epoch": 0.20067497403946002, "grad_norm": 4.088040828704834, "learning_rate": 4.942256956967907e-06, "loss": 0.4644800126552582, "step": 773 }, { "epoch": 0.20093457943925233, "grad_norm": 9.564146995544434, "learning_rate": 4.942043819559993e-06, "loss": 0.5180612802505493, "step": 774 }, { "epoch": 0.20119418483904467, "grad_norm": 4.242695331573486, "learning_rate": 4.941830294648924e-06, "loss": 0.4185469150543213, "step": 775 }, { "epoch": 0.20145379023883697, "grad_norm": 4.098979473114014, "learning_rate": 4.941616382272444e-06, "loss": 0.35695773363113403, "step": 776 }, { "epoch": 0.20171339563862928, "grad_norm": 4.794043064117432, "learning_rate": 4.94140208246837e-06, "loss": 0.4544667899608612, "step": 777 }, { "epoch": 0.2019730010384216, "grad_norm": 10.121410369873047, "learning_rate": 4.941187395274584e-06, "loss": 0.43399447202682495, "step": 778 }, { "epoch": 0.20223260643821392, "grad_norm": 3.6788909435272217, "learning_rate": 4.940972320729036e-06, "loss": 0.39689624309539795, "step": 779 }, { "epoch": 0.20249221183800623, "grad_norm": 3.532273292541504, "learning_rate": 4.940756858869751e-06, "loss": 0.3911597728729248, "step": 780 }, { "epoch": 0.20275181723779856, "grad_norm": 3.2409403324127197, "learning_rate": 4.940541009734814e-06, "loss": 0.5389816164970398, "step": 781 }, { "epoch": 0.20301142263759087, "grad_norm": 4.212785243988037, "learning_rate": 4.940324773362383e-06, "loss": 0.4396364390850067, "step": 782 }, { "epoch": 0.20327102803738317, "grad_norm": 6.010969161987305, "learning_rate": 4.940108149790684e-06, "loss": 0.5012109875679016, "step": 783 }, { "epoch": 0.2035306334371755, "grad_norm": 3.073944568634033, "learning_rate": 4.939891139058011e-06, "loss": 0.39986830949783325, "step": 784 }, { "epoch": 0.2037902388369678, "grad_norm": 4.393648147583008, "learning_rate": 4.939673741202726e-06, "loss": 0.47505998611450195, "step": 785 }, { "epoch": 0.20404984423676012, "grad_norm": 3.740689277648926, "learning_rate": 4.939455956263262e-06, "loss": 0.37841174006462097, "step": 786 }, { "epoch": 0.20430944963655245, "grad_norm": 3.313401699066162, "learning_rate": 4.9392377842781156e-06, "loss": 0.457416832447052, "step": 787 }, { "epoch": 0.20456905503634476, "grad_norm": 4.56814432144165, "learning_rate": 4.939019225285856e-06, "loss": 0.4697872996330261, "step": 788 }, { "epoch": 0.20482866043613707, "grad_norm": 5.093684673309326, "learning_rate": 4.938800279325119e-06, "loss": 0.4323788285255432, "step": 789 }, { "epoch": 0.2050882658359294, "grad_norm": 3.7235991954803467, "learning_rate": 4.93858094643461e-06, "loss": 0.40387237071990967, "step": 790 }, { "epoch": 0.2053478712357217, "grad_norm": 3.0680787563323975, "learning_rate": 4.938361226653101e-06, "loss": 0.43376779556274414, "step": 791 }, { "epoch": 0.205607476635514, "grad_norm": 2.704881429672241, "learning_rate": 4.938141120019435e-06, "loss": 0.42539921402931213, "step": 792 }, { "epoch": 0.20586708203530635, "grad_norm": 4.872018814086914, "learning_rate": 4.9379206265725196e-06, "loss": 0.4049831032752991, "step": 793 }, { "epoch": 0.20612668743509865, "grad_norm": 8.776473045349121, "learning_rate": 4.937699746351334e-06, "loss": 0.4082080125808716, "step": 794 }, { "epoch": 0.20638629283489096, "grad_norm": 9.26361083984375, "learning_rate": 4.937478479394925e-06, "loss": 0.420032799243927, "step": 795 }, { "epoch": 0.2066458982346833, "grad_norm": 4.910084247589111, "learning_rate": 4.937256825742409e-06, "loss": 0.378171443939209, "step": 796 }, { "epoch": 0.2069055036344756, "grad_norm": 4.926030158996582, "learning_rate": 4.937034785432967e-06, "loss": 0.45541054010391235, "step": 797 }, { "epoch": 0.2071651090342679, "grad_norm": 3.6343228816986084, "learning_rate": 4.936812358505851e-06, "loss": 0.4197157621383667, "step": 798 }, { "epoch": 0.20742471443406024, "grad_norm": 3.3253278732299805, "learning_rate": 4.936589545000381e-06, "loss": 0.40910428762435913, "step": 799 }, { "epoch": 0.20768431983385255, "grad_norm": 6.589433670043945, "learning_rate": 4.936366344955947e-06, "loss": 0.4918232858181, "step": 800 }, { "epoch": 0.20794392523364486, "grad_norm": 2.6862947940826416, "learning_rate": 4.936142758412004e-06, "loss": 0.3828226327896118, "step": 801 }, { "epoch": 0.2082035306334372, "grad_norm": 2.5280797481536865, "learning_rate": 4.935918785408076e-06, "loss": 0.44259923696517944, "step": 802 }, { "epoch": 0.2084631360332295, "grad_norm": 7.965635776519775, "learning_rate": 4.935694425983759e-06, "loss": 0.5296367406845093, "step": 803 }, { "epoch": 0.2087227414330218, "grad_norm": 6.8817138671875, "learning_rate": 4.935469680178713e-06, "loss": 0.5540664196014404, "step": 804 }, { "epoch": 0.2089823468328141, "grad_norm": 5.290346622467041, "learning_rate": 4.9352445480326675e-06, "loss": 0.4693771004676819, "step": 805 }, { "epoch": 0.20924195223260644, "grad_norm": 5.769053936004639, "learning_rate": 4.935019029585421e-06, "loss": 0.49439412355422974, "step": 806 }, { "epoch": 0.20950155763239875, "grad_norm": 4.787761688232422, "learning_rate": 4.934793124876842e-06, "loss": 0.5033883452415466, "step": 807 }, { "epoch": 0.20976116303219106, "grad_norm": 3.69962739944458, "learning_rate": 4.934566833946863e-06, "loss": 0.40145885944366455, "step": 808 }, { "epoch": 0.2100207684319834, "grad_norm": 2.0303256511688232, "learning_rate": 4.934340156835488e-06, "loss": 0.413918137550354, "step": 809 }, { "epoch": 0.2102803738317757, "grad_norm": 3.8855555057525635, "learning_rate": 4.934113093582787e-06, "loss": 0.42865800857543945, "step": 810 }, { "epoch": 0.210539979231568, "grad_norm": 2.6195762157440186, "learning_rate": 4.933885644228902e-06, "loss": 0.3441792130470276, "step": 811 }, { "epoch": 0.21079958463136034, "grad_norm": 4.578952312469482, "learning_rate": 4.933657808814038e-06, "loss": 0.4786851406097412, "step": 812 }, { "epoch": 0.21105919003115264, "grad_norm": 3.0277488231658936, "learning_rate": 4.933429587378473e-06, "loss": 0.3982079327106476, "step": 813 }, { "epoch": 0.21131879543094495, "grad_norm": 4.064517498016357, "learning_rate": 4.933200979962551e-06, "loss": 0.39931100606918335, "step": 814 }, { "epoch": 0.21157840083073728, "grad_norm": 2.902308940887451, "learning_rate": 4.932971986606685e-06, "loss": 0.37909066677093506, "step": 815 }, { "epoch": 0.2118380062305296, "grad_norm": 1.8781629800796509, "learning_rate": 4.9327426073513555e-06, "loss": 0.3758279085159302, "step": 816 }, { "epoch": 0.2120976116303219, "grad_norm": 3.0067691802978516, "learning_rate": 4.9325128422371095e-06, "loss": 0.35012659430503845, "step": 817 }, { "epoch": 0.21235721703011423, "grad_norm": 2.503699779510498, "learning_rate": 4.932282691304567e-06, "loss": 0.35052841901779175, "step": 818 }, { "epoch": 0.21261682242990654, "grad_norm": 4.208228588104248, "learning_rate": 4.932052154594413e-06, "loss": 0.5100893974304199, "step": 819 }, { "epoch": 0.21287642782969884, "grad_norm": 4.673512935638428, "learning_rate": 4.931821232147399e-06, "loss": 0.5078348517417908, "step": 820 }, { "epoch": 0.21313603322949118, "grad_norm": 3.3518431186676025, "learning_rate": 4.931589924004349e-06, "loss": 0.48191189765930176, "step": 821 }, { "epoch": 0.21339563862928349, "grad_norm": 2.7865710258483887, "learning_rate": 4.931358230206152e-06, "loss": 0.36296549439430237, "step": 822 }, { "epoch": 0.2136552440290758, "grad_norm": 3.654707193374634, "learning_rate": 4.931126150793767e-06, "loss": 0.46750515699386597, "step": 823 }, { "epoch": 0.21391484942886813, "grad_norm": 2.3375473022460938, "learning_rate": 4.930893685808219e-06, "loss": 0.3928399085998535, "step": 824 }, { "epoch": 0.21417445482866043, "grad_norm": 2.2822265625, "learning_rate": 4.930660835290603e-06, "loss": 0.41653215885162354, "step": 825 }, { "epoch": 0.21443406022845274, "grad_norm": 3.095013380050659, "learning_rate": 4.930427599282082e-06, "loss": 0.5001860857009888, "step": 826 }, { "epoch": 0.21469366562824507, "grad_norm": 2.5047788619995117, "learning_rate": 4.930193977823887e-06, "loss": 0.4023991823196411, "step": 827 }, { "epoch": 0.21495327102803738, "grad_norm": 2.469675302505493, "learning_rate": 4.929959970957316e-06, "loss": 0.4566177427768707, "step": 828 }, { "epoch": 0.21521287642782969, "grad_norm": 2.5565004348754883, "learning_rate": 4.929725578723738e-06, "loss": 0.4471810758113861, "step": 829 }, { "epoch": 0.21547248182762202, "grad_norm": 3.8389430046081543, "learning_rate": 4.929490801164585e-06, "loss": 0.4492079019546509, "step": 830 }, { "epoch": 0.21573208722741433, "grad_norm": 3.4902963638305664, "learning_rate": 4.929255638321363e-06, "loss": 0.39042142033576965, "step": 831 }, { "epoch": 0.21599169262720663, "grad_norm": 2.491973876953125, "learning_rate": 4.9290200902356424e-06, "loss": 0.37626200914382935, "step": 832 }, { "epoch": 0.21625129802699897, "grad_norm": 2.2083380222320557, "learning_rate": 4.928784156949062e-06, "loss": 0.4150504469871521, "step": 833 }, { "epoch": 0.21651090342679127, "grad_norm": 3.6833255290985107, "learning_rate": 4.928547838503331e-06, "loss": 0.4894189238548279, "step": 834 }, { "epoch": 0.21677050882658358, "grad_norm": 2.927283763885498, "learning_rate": 4.928311134940224e-06, "loss": 0.39915674924850464, "step": 835 }, { "epoch": 0.21703011422637591, "grad_norm": 3.5430009365081787, "learning_rate": 4.928074046301586e-06, "loss": 0.49827995896339417, "step": 836 }, { "epoch": 0.21728971962616822, "grad_norm": 5.070685863494873, "learning_rate": 4.9278365726293274e-06, "loss": 0.46950656175613403, "step": 837 }, { "epoch": 0.21754932502596053, "grad_norm": 4.3277907371521, "learning_rate": 4.927598713965428e-06, "loss": 0.37532347440719604, "step": 838 }, { "epoch": 0.21780893042575286, "grad_norm": 3.058626413345337, "learning_rate": 4.927360470351937e-06, "loss": 0.466197669506073, "step": 839 }, { "epoch": 0.21806853582554517, "grad_norm": 2.2546749114990234, "learning_rate": 4.927121841830969e-06, "loss": 0.3854028284549713, "step": 840 }, { "epoch": 0.21832814122533747, "grad_norm": 2.68621563911438, "learning_rate": 4.926882828444709e-06, "loss": 0.37187495827674866, "step": 841 }, { "epoch": 0.2185877466251298, "grad_norm": 3.3578526973724365, "learning_rate": 4.92664343023541e-06, "loss": 0.4047614634037018, "step": 842 }, { "epoch": 0.21884735202492211, "grad_norm": 4.2502217292785645, "learning_rate": 4.926403647245391e-06, "loss": 0.4275696277618408, "step": 843 }, { "epoch": 0.21910695742471442, "grad_norm": 2.826500415802002, "learning_rate": 4.926163479517039e-06, "loss": 0.40488898754119873, "step": 844 }, { "epoch": 0.21936656282450676, "grad_norm": 9.32996654510498, "learning_rate": 4.9259229270928115e-06, "loss": 0.40265804529190063, "step": 845 }, { "epoch": 0.21962616822429906, "grad_norm": 3.7057766914367676, "learning_rate": 4.925681990015233e-06, "loss": 0.4421318769454956, "step": 846 }, { "epoch": 0.21988577362409137, "grad_norm": 3.8631951808929443, "learning_rate": 4.9254406683268955e-06, "loss": 0.5069433450698853, "step": 847 }, { "epoch": 0.2201453790238837, "grad_norm": 5.437228202819824, "learning_rate": 4.925198962070459e-06, "loss": 0.4963100850582123, "step": 848 }, { "epoch": 0.220404984423676, "grad_norm": 7.205998420715332, "learning_rate": 4.92495687128865e-06, "loss": 0.47295746207237244, "step": 849 }, { "epoch": 0.22066458982346832, "grad_norm": 4.864202499389648, "learning_rate": 4.924714396024267e-06, "loss": 0.5178976058959961, "step": 850 }, { "epoch": 0.22092419522326065, "grad_norm": 6.186012268066406, "learning_rate": 4.9244715363201735e-06, "loss": 0.4879262447357178, "step": 851 }, { "epoch": 0.22118380062305296, "grad_norm": 3.003424644470215, "learning_rate": 4.924228292219301e-06, "loss": 0.4031296372413635, "step": 852 }, { "epoch": 0.22144340602284526, "grad_norm": 2.693387746810913, "learning_rate": 4.923984663764649e-06, "loss": 0.377557635307312, "step": 853 }, { "epoch": 0.2217030114226376, "grad_norm": 2.842175245285034, "learning_rate": 4.923740650999287e-06, "loss": 0.43027931451797485, "step": 854 }, { "epoch": 0.2219626168224299, "grad_norm": 2.217482566833496, "learning_rate": 4.92349625396635e-06, "loss": 0.39449936151504517, "step": 855 }, { "epoch": 0.2222222222222222, "grad_norm": 3.4642598628997803, "learning_rate": 4.923251472709041e-06, "loss": 0.4172500967979431, "step": 856 }, { "epoch": 0.22248182762201454, "grad_norm": 4.940343856811523, "learning_rate": 4.923006307270632e-06, "loss": 0.5066769123077393, "step": 857 }, { "epoch": 0.22274143302180685, "grad_norm": 3.6683382987976074, "learning_rate": 4.922760757694464e-06, "loss": 0.41383904218673706, "step": 858 }, { "epoch": 0.22300103842159916, "grad_norm": 3.3528919219970703, "learning_rate": 4.922514824023944e-06, "loss": 0.38609981536865234, "step": 859 }, { "epoch": 0.2232606438213915, "grad_norm": 3.9533798694610596, "learning_rate": 4.922268506302547e-06, "loss": 0.42491281032562256, "step": 860 }, { "epoch": 0.2235202492211838, "grad_norm": 3.519716501235962, "learning_rate": 4.922021804573815e-06, "loss": 0.5313564538955688, "step": 861 }, { "epoch": 0.2237798546209761, "grad_norm": 3.001084804534912, "learning_rate": 4.921774718881362e-06, "loss": 0.4051316976547241, "step": 862 }, { "epoch": 0.22403946002076844, "grad_norm": 7.437861442565918, "learning_rate": 4.921527249268866e-06, "loss": 0.5142128467559814, "step": 863 }, { "epoch": 0.22429906542056074, "grad_norm": 5.033374309539795, "learning_rate": 4.921279395780073e-06, "loss": 0.45098668336868286, "step": 864 }, { "epoch": 0.22455867082035305, "grad_norm": 2.3308746814727783, "learning_rate": 4.921031158458799e-06, "loss": 0.39067453145980835, "step": 865 }, { "epoch": 0.22481827622014539, "grad_norm": 4.323333263397217, "learning_rate": 4.920782537348926e-06, "loss": 0.43953001499176025, "step": 866 }, { "epoch": 0.2250778816199377, "grad_norm": 3.299778938293457, "learning_rate": 4.9205335324944045e-06, "loss": 0.3922068476676941, "step": 867 }, { "epoch": 0.22533748701973, "grad_norm": 2.3594918251037598, "learning_rate": 4.9202841439392536e-06, "loss": 0.41891422867774963, "step": 868 }, { "epoch": 0.22559709241952233, "grad_norm": 3.2223823070526123, "learning_rate": 4.920034371727559e-06, "loss": 0.42779627442359924, "step": 869 }, { "epoch": 0.22585669781931464, "grad_norm": 3.336909532546997, "learning_rate": 4.919784215903474e-06, "loss": 0.44130122661590576, "step": 870 }, { "epoch": 0.22611630321910695, "grad_norm": 5.903071403503418, "learning_rate": 4.9195336765112215e-06, "loss": 0.49889370799064636, "step": 871 }, { "epoch": 0.22637590861889928, "grad_norm": 3.3405849933624268, "learning_rate": 4.919282753595091e-06, "loss": 0.35571712255477905, "step": 872 }, { "epoch": 0.2266355140186916, "grad_norm": 5.332581043243408, "learning_rate": 4.919031447199439e-06, "loss": 0.49023428559303284, "step": 873 }, { "epoch": 0.2268951194184839, "grad_norm": 2.120410919189453, "learning_rate": 4.918779757368692e-06, "loss": 0.4204685688018799, "step": 874 }, { "epoch": 0.22715472481827623, "grad_norm": 1.5528347492218018, "learning_rate": 4.918527684147342e-06, "loss": 0.3603075444698334, "step": 875 }, { "epoch": 0.22741433021806853, "grad_norm": 1.710693120956421, "learning_rate": 4.918275227579951e-06, "loss": 0.38708239793777466, "step": 876 }, { "epoch": 0.22767393561786084, "grad_norm": 7.00443172454834, "learning_rate": 4.918022387711145e-06, "loss": 0.5356251001358032, "step": 877 }, { "epoch": 0.22793354101765317, "grad_norm": 4.514766216278076, "learning_rate": 4.917769164585623e-06, "loss": 0.3663495182991028, "step": 878 }, { "epoch": 0.22819314641744548, "grad_norm": 3.5822107791900635, "learning_rate": 4.917515558248148e-06, "loss": 0.42339059710502625, "step": 879 }, { "epoch": 0.2284527518172378, "grad_norm": 3.440244436264038, "learning_rate": 4.9172615687435525e-06, "loss": 0.3942910134792328, "step": 880 }, { "epoch": 0.22871235721703012, "grad_norm": 3.481163263320923, "learning_rate": 4.917007196116734e-06, "loss": 0.4020233154296875, "step": 881 }, { "epoch": 0.22897196261682243, "grad_norm": 5.223323822021484, "learning_rate": 4.916752440412661e-06, "loss": 0.5064215660095215, "step": 882 }, { "epoch": 0.22923156801661473, "grad_norm": 3.0745673179626465, "learning_rate": 4.91649730167637e-06, "loss": 0.3944699764251709, "step": 883 }, { "epoch": 0.22949117341640707, "grad_norm": 2.2806572914123535, "learning_rate": 4.916241779952961e-06, "loss": 0.49042296409606934, "step": 884 }, { "epoch": 0.22975077881619937, "grad_norm": 5.2280683517456055, "learning_rate": 4.915985875287607e-06, "loss": 0.37588417530059814, "step": 885 }, { "epoch": 0.23001038421599168, "grad_norm": 6.656860828399658, "learning_rate": 4.915729587725544e-06, "loss": 0.4186626076698303, "step": 886 }, { "epoch": 0.23026998961578402, "grad_norm": 3.4552114009857178, "learning_rate": 4.915472917312079e-06, "loss": 0.4330907464027405, "step": 887 }, { "epoch": 0.23052959501557632, "grad_norm": 2.802380323410034, "learning_rate": 4.915215864092584e-06, "loss": 0.3789641261100769, "step": 888 }, { "epoch": 0.23078920041536863, "grad_norm": 5.640468120574951, "learning_rate": 4.914958428112502e-06, "loss": 0.5140122771263123, "step": 889 }, { "epoch": 0.23104880581516096, "grad_norm": 4.7671308517456055, "learning_rate": 4.91470060941734e-06, "loss": 0.41158539056777954, "step": 890 }, { "epoch": 0.23130841121495327, "grad_norm": 4.760399341583252, "learning_rate": 4.914442408052676e-06, "loss": 0.3823985755443573, "step": 891 }, { "epoch": 0.23156801661474558, "grad_norm": 3.5273964405059814, "learning_rate": 4.9141838240641535e-06, "loss": 0.49648383259773254, "step": 892 }, { "epoch": 0.2318276220145379, "grad_norm": 2.3741774559020996, "learning_rate": 4.913924857497483e-06, "loss": 0.3752386271953583, "step": 893 }, { "epoch": 0.23208722741433022, "grad_norm": 2.5850229263305664, "learning_rate": 4.913665508398447e-06, "loss": 0.3940522074699402, "step": 894 }, { "epoch": 0.23234683281412252, "grad_norm": 3.167173385620117, "learning_rate": 4.913405776812888e-06, "loss": 0.408349871635437, "step": 895 }, { "epoch": 0.23260643821391486, "grad_norm": 2.327085018157959, "learning_rate": 4.913145662786725e-06, "loss": 0.359780490398407, "step": 896 }, { "epoch": 0.23286604361370716, "grad_norm": 6.776957988739014, "learning_rate": 4.912885166365938e-06, "loss": 0.3875972032546997, "step": 897 }, { "epoch": 0.23312564901349947, "grad_norm": 3.206995964050293, "learning_rate": 4.912624287596577e-06, "loss": 0.46197590231895447, "step": 898 }, { "epoch": 0.2333852544132918, "grad_norm": 2.365013599395752, "learning_rate": 4.91236302652476e-06, "loss": 0.3953106105327606, "step": 899 }, { "epoch": 0.2336448598130841, "grad_norm": 5.915037155151367, "learning_rate": 4.9121013831966704e-06, "loss": 0.5043560862541199, "step": 900 }, { "epoch": 0.23390446521287642, "grad_norm": 5.488180637359619, "learning_rate": 4.911839357658562e-06, "loss": 0.3809810280799866, "step": 901 }, { "epoch": 0.23416407061266875, "grad_norm": 8.211989402770996, "learning_rate": 4.911576949956755e-06, "loss": 0.42349258065223694, "step": 902 }, { "epoch": 0.23442367601246106, "grad_norm": 6.595442771911621, "learning_rate": 4.9113141601376365e-06, "loss": 0.4940720498561859, "step": 903 }, { "epoch": 0.23468328141225336, "grad_norm": 3.4310224056243896, "learning_rate": 4.911050988247663e-06, "loss": 0.4031640291213989, "step": 904 }, { "epoch": 0.2349428868120457, "grad_norm": 6.924283504486084, "learning_rate": 4.910787434333355e-06, "loss": 0.40049058198928833, "step": 905 }, { "epoch": 0.235202492211838, "grad_norm": 4.681899547576904, "learning_rate": 4.910523498441304e-06, "loss": 0.3839086890220642, "step": 906 }, { "epoch": 0.2354620976116303, "grad_norm": 3.611400842666626, "learning_rate": 4.91025918061817e-06, "loss": 0.3705865740776062, "step": 907 }, { "epoch": 0.23572170301142265, "grad_norm": 5.3671722412109375, "learning_rate": 4.909994480910674e-06, "loss": 0.39317840337753296, "step": 908 }, { "epoch": 0.23598130841121495, "grad_norm": 6.477071285247803, "learning_rate": 4.909729399365613e-06, "loss": 0.3482658863067627, "step": 909 }, { "epoch": 0.23624091381100726, "grad_norm": 4.2300705909729, "learning_rate": 4.909463936029843e-06, "loss": 0.3934146761894226, "step": 910 }, { "epoch": 0.2365005192107996, "grad_norm": 6.2831830978393555, "learning_rate": 4.909198090950296e-06, "loss": 0.5107008814811707, "step": 911 }, { "epoch": 0.2367601246105919, "grad_norm": 4.533780097961426, "learning_rate": 4.908931864173965e-06, "loss": 0.3901445269584656, "step": 912 }, { "epoch": 0.2370197300103842, "grad_norm": 6.827175140380859, "learning_rate": 4.908665255747914e-06, "loss": 0.413950115442276, "step": 913 }, { "epoch": 0.23727933541017654, "grad_norm": 3.2545387744903564, "learning_rate": 4.908398265719273e-06, "loss": 0.37153077125549316, "step": 914 }, { "epoch": 0.23753894080996885, "grad_norm": 2.916574239730835, "learning_rate": 4.908130894135238e-06, "loss": 0.4212178885936737, "step": 915 }, { "epoch": 0.23779854620976115, "grad_norm": 2.039045572280884, "learning_rate": 4.907863141043076e-06, "loss": 0.37340664863586426, "step": 916 }, { "epoch": 0.2380581516095535, "grad_norm": 3.1100900173187256, "learning_rate": 4.90759500649012e-06, "loss": 0.4387773275375366, "step": 917 }, { "epoch": 0.2383177570093458, "grad_norm": 6.921225547790527, "learning_rate": 4.9073264905237685e-06, "loss": 0.5490912795066833, "step": 918 }, { "epoch": 0.2385773624091381, "grad_norm": 3.1570050716400146, "learning_rate": 4.907057593191489e-06, "loss": 0.41894257068634033, "step": 919 }, { "epoch": 0.23883696780893043, "grad_norm": 2.764375925064087, "learning_rate": 4.906788314540819e-06, "loss": 0.39872226119041443, "step": 920 }, { "epoch": 0.23909657320872274, "grad_norm": 2.91742205619812, "learning_rate": 4.906518654619358e-06, "loss": 0.3808514475822449, "step": 921 }, { "epoch": 0.23935617860851505, "grad_norm": 3.1550023555755615, "learning_rate": 4.906248613474776e-06, "loss": 0.5417710542678833, "step": 922 }, { "epoch": 0.23961578400830738, "grad_norm": 4.776097297668457, "learning_rate": 4.905978191154811e-06, "loss": 0.5184454321861267, "step": 923 }, { "epoch": 0.2398753894080997, "grad_norm": 4.693808555603027, "learning_rate": 4.905707387707267e-06, "loss": 0.4504692256450653, "step": 924 }, { "epoch": 0.240134994807892, "grad_norm": 2.879507541656494, "learning_rate": 4.905436203180016e-06, "loss": 0.4378971457481384, "step": 925 }, { "epoch": 0.24039460020768433, "grad_norm": 3.397453546524048, "learning_rate": 4.9051646376209976e-06, "loss": 0.3791618347167969, "step": 926 }, { "epoch": 0.24065420560747663, "grad_norm": 3.3231165409088135, "learning_rate": 4.904892691078218e-06, "loss": 0.4152478575706482, "step": 927 }, { "epoch": 0.24091381100726894, "grad_norm": 4.8795671463012695, "learning_rate": 4.904620363599752e-06, "loss": 0.4124605059623718, "step": 928 }, { "epoch": 0.24117341640706128, "grad_norm": 3.9175071716308594, "learning_rate": 4.904347655233738e-06, "loss": 0.43178993463516235, "step": 929 }, { "epoch": 0.24143302180685358, "grad_norm": 2.652709722518921, "learning_rate": 4.904074566028388e-06, "loss": 0.37543320655822754, "step": 930 }, { "epoch": 0.2416926272066459, "grad_norm": 7.863239765167236, "learning_rate": 4.903801096031976e-06, "loss": 0.5655639171600342, "step": 931 }, { "epoch": 0.24195223260643822, "grad_norm": 3.1636414527893066, "learning_rate": 4.903527245292847e-06, "loss": 0.4096837043762207, "step": 932 }, { "epoch": 0.24221183800623053, "grad_norm": 3.558210611343384, "learning_rate": 4.903253013859408e-06, "loss": 0.40946120023727417, "step": 933 }, { "epoch": 0.24247144340602284, "grad_norm": 3.6931350231170654, "learning_rate": 4.9029784017801404e-06, "loss": 0.38213226199150085, "step": 934 }, { "epoch": 0.24273104880581517, "grad_norm": 2.3592987060546875, "learning_rate": 4.902703409103588e-06, "loss": 0.3779652416706085, "step": 935 }, { "epoch": 0.24299065420560748, "grad_norm": 4.700354099273682, "learning_rate": 4.902428035878363e-06, "loss": 0.412602961063385, "step": 936 }, { "epoch": 0.24325025960539978, "grad_norm": 9.524249076843262, "learning_rate": 4.902152282153145e-06, "loss": 0.489749550819397, "step": 937 }, { "epoch": 0.24350986500519212, "grad_norm": 4.642603874206543, "learning_rate": 4.901876147976682e-06, "loss": 0.48624423146247864, "step": 938 }, { "epoch": 0.24376947040498442, "grad_norm": 6.325840950012207, "learning_rate": 4.901599633397787e-06, "loss": 0.3598419427871704, "step": 939 }, { "epoch": 0.24402907580477673, "grad_norm": 4.546938896179199, "learning_rate": 4.901322738465341e-06, "loss": 0.5194783210754395, "step": 940 }, { "epoch": 0.24428868120456906, "grad_norm": 5.494564533233643, "learning_rate": 4.901045463228295e-06, "loss": 0.497202068567276, "step": 941 }, { "epoch": 0.24454828660436137, "grad_norm": 3.63159441947937, "learning_rate": 4.900767807735664e-06, "loss": 0.4611629843711853, "step": 942 }, { "epoch": 0.24480789200415368, "grad_norm": 4.937147617340088, "learning_rate": 4.90048977203653e-06, "loss": 0.4745291769504547, "step": 943 }, { "epoch": 0.245067497403946, "grad_norm": 2.567866802215576, "learning_rate": 4.900211356180044e-06, "loss": 0.37760022282600403, "step": 944 }, { "epoch": 0.24532710280373832, "grad_norm": 4.505856513977051, "learning_rate": 4.899932560215423e-06, "loss": 0.4402318000793457, "step": 945 }, { "epoch": 0.24558670820353062, "grad_norm": 2.694492816925049, "learning_rate": 4.899653384191952e-06, "loss": 0.37911802530288696, "step": 946 }, { "epoch": 0.24584631360332296, "grad_norm": 4.53220796585083, "learning_rate": 4.899373828158984e-06, "loss": 0.4850122332572937, "step": 947 }, { "epoch": 0.24610591900311526, "grad_norm": 3.3615779876708984, "learning_rate": 4.899093892165938e-06, "loss": 0.3960675597190857, "step": 948 }, { "epoch": 0.24636552440290757, "grad_norm": 2.2893474102020264, "learning_rate": 4.898813576262299e-06, "loss": 0.3645407557487488, "step": 949 }, { "epoch": 0.2466251298026999, "grad_norm": 10.11630916595459, "learning_rate": 4.8985328804976205e-06, "loss": 0.4777415990829468, "step": 950 }, { "epoch": 0.2468847352024922, "grad_norm": 2.6983978748321533, "learning_rate": 4.898251804921523e-06, "loss": 0.3569599688053131, "step": 951 }, { "epoch": 0.24714434060228452, "grad_norm": 3.0024921894073486, "learning_rate": 4.897970349583697e-06, "loss": 0.3881657123565674, "step": 952 }, { "epoch": 0.24740394600207685, "grad_norm": 3.535332679748535, "learning_rate": 4.8976885145338935e-06, "loss": 0.4275510907173157, "step": 953 }, { "epoch": 0.24766355140186916, "grad_norm": 3.382154941558838, "learning_rate": 4.897406299821936e-06, "loss": 0.4883952736854553, "step": 954 }, { "epoch": 0.24792315680166147, "grad_norm": 5.225388050079346, "learning_rate": 4.897123705497714e-06, "loss": 0.560981035232544, "step": 955 }, { "epoch": 0.2481827622014538, "grad_norm": 3.0710835456848145, "learning_rate": 4.896840731611185e-06, "loss": 0.4281485676765442, "step": 956 }, { "epoch": 0.2484423676012461, "grad_norm": 4.2427897453308105, "learning_rate": 4.896557378212369e-06, "loss": 0.41302770376205444, "step": 957 }, { "epoch": 0.2487019730010384, "grad_norm": 4.138025283813477, "learning_rate": 4.8962736453513595e-06, "loss": 0.45404767990112305, "step": 958 }, { "epoch": 0.24896157840083075, "grad_norm": 4.925053119659424, "learning_rate": 4.895989533078311e-06, "loss": 0.4276583790779114, "step": 959 }, { "epoch": 0.24922118380062305, "grad_norm": 1.6575310230255127, "learning_rate": 4.895705041443452e-06, "loss": 0.39585089683532715, "step": 960 }, { "epoch": 0.24948078920041536, "grad_norm": 3.089151620864868, "learning_rate": 4.89542017049707e-06, "loss": 0.4088520407676697, "step": 961 }, { "epoch": 0.2497403946002077, "grad_norm": 2.6297848224639893, "learning_rate": 4.895134920289526e-06, "loss": 0.36645883321762085, "step": 962 }, { "epoch": 0.25, "grad_norm": 3.4206089973449707, "learning_rate": 4.894849290871245e-06, "loss": 0.4222477674484253, "step": 963 }, { "epoch": 0.2502596053997923, "grad_norm": 4.508742332458496, "learning_rate": 4.89456328229272e-06, "loss": 0.42350977659225464, "step": 964 }, { "epoch": 0.2505192107995846, "grad_norm": 2.7489025592803955, "learning_rate": 4.894276894604511e-06, "loss": 0.3689448833465576, "step": 965 }, { "epoch": 0.2507788161993769, "grad_norm": 7.258790016174316, "learning_rate": 4.893990127857244e-06, "loss": 0.4266553521156311, "step": 966 }, { "epoch": 0.2510384215991693, "grad_norm": 5.562114238739014, "learning_rate": 4.893702982101614e-06, "loss": 0.4139719009399414, "step": 967 }, { "epoch": 0.2512980269989616, "grad_norm": 2.6745388507843018, "learning_rate": 4.89341545738838e-06, "loss": 0.4145331382751465, "step": 968 }, { "epoch": 0.2515576323987539, "grad_norm": 6.2380170822143555, "learning_rate": 4.893127553768372e-06, "loss": 0.46564191579818726, "step": 969 }, { "epoch": 0.2518172377985462, "grad_norm": 3.243204355239868, "learning_rate": 4.892839271292483e-06, "loss": 0.48035985231399536, "step": 970 }, { "epoch": 0.2520768431983385, "grad_norm": 3.432481288909912, "learning_rate": 4.892550610011675e-06, "loss": 0.3477029502391815, "step": 971 }, { "epoch": 0.2523364485981308, "grad_norm": 3.9174046516418457, "learning_rate": 4.8922615699769775e-06, "loss": 0.4063568115234375, "step": 972 }, { "epoch": 0.2525960539979232, "grad_norm": 4.393509387969971, "learning_rate": 4.891972151239486e-06, "loss": 0.4061262011528015, "step": 973 }, { "epoch": 0.2528556593977155, "grad_norm": 3.2908360958099365, "learning_rate": 4.891682353850362e-06, "loss": 0.3907068967819214, "step": 974 }, { "epoch": 0.2531152647975078, "grad_norm": 3.0606300830841064, "learning_rate": 4.8913921778608355e-06, "loss": 0.37891462445259094, "step": 975 }, { "epoch": 0.2533748701973001, "grad_norm": 3.1200287342071533, "learning_rate": 4.891101623322205e-06, "loss": 0.4389794170856476, "step": 976 }, { "epoch": 0.2536344755970924, "grad_norm": 3.6234664916992188, "learning_rate": 4.890810690285831e-06, "loss": 0.3705320954322815, "step": 977 }, { "epoch": 0.2538940809968847, "grad_norm": 5.022310256958008, "learning_rate": 4.8905193788031454e-06, "loss": 0.4095534086227417, "step": 978 }, { "epoch": 0.25415368639667707, "grad_norm": 2.210585117340088, "learning_rate": 4.890227688925645e-06, "loss": 0.42956238985061646, "step": 979 }, { "epoch": 0.2544132917964694, "grad_norm": 2.8937203884124756, "learning_rate": 4.8899356207048945e-06, "loss": 0.4913870096206665, "step": 980 }, { "epoch": 0.2546728971962617, "grad_norm": 2.846088171005249, "learning_rate": 4.889643174192523e-06, "loss": 0.3945484757423401, "step": 981 }, { "epoch": 0.254932502596054, "grad_norm": 4.924194812774658, "learning_rate": 4.8893503494402305e-06, "loss": 0.476923406124115, "step": 982 }, { "epoch": 0.2551921079958463, "grad_norm": 2.7004926204681396, "learning_rate": 4.889057146499781e-06, "loss": 0.5301071405410767, "step": 983 }, { "epoch": 0.2554517133956386, "grad_norm": 3.6404366493225098, "learning_rate": 4.888763565423004e-06, "loss": 0.4550809860229492, "step": 984 }, { "epoch": 0.25571131879543096, "grad_norm": 4.1437811851501465, "learning_rate": 4.888469606261803e-06, "loss": 0.365972638130188, "step": 985 }, { "epoch": 0.25597092419522327, "grad_norm": 6.333739280700684, "learning_rate": 4.888175269068138e-06, "loss": 0.40193304419517517, "step": 986 }, { "epoch": 0.2562305295950156, "grad_norm": 3.9939868450164795, "learning_rate": 4.887880553894044e-06, "loss": 0.35100799798965454, "step": 987 }, { "epoch": 0.2564901349948079, "grad_norm": 4.191832542419434, "learning_rate": 4.887585460791618e-06, "loss": 0.4305158853530884, "step": 988 }, { "epoch": 0.2567497403946002, "grad_norm": 2.0317134857177734, "learning_rate": 4.887289989813029e-06, "loss": 0.3433613181114197, "step": 989 }, { "epoch": 0.2570093457943925, "grad_norm": 3.81493878364563, "learning_rate": 4.886994141010505e-06, "loss": 0.4612756073474884, "step": 990 }, { "epoch": 0.25726895119418486, "grad_norm": 6.513317108154297, "learning_rate": 4.886697914436348e-06, "loss": 0.5002859830856323, "step": 991 }, { "epoch": 0.25752855659397716, "grad_norm": 4.02746057510376, "learning_rate": 4.8864013101429235e-06, "loss": 0.39956986904144287, "step": 992 }, { "epoch": 0.25778816199376947, "grad_norm": 4.34028434753418, "learning_rate": 4.886104328182665e-06, "loss": 0.4005882143974304, "step": 993 }, { "epoch": 0.2580477673935618, "grad_norm": 3.495659351348877, "learning_rate": 4.885806968608072e-06, "loss": 0.4570401906967163, "step": 994 }, { "epoch": 0.2583073727933541, "grad_norm": 4.550365447998047, "learning_rate": 4.8855092314717095e-06, "loss": 0.4063541293144226, "step": 995 }, { "epoch": 0.2585669781931464, "grad_norm": 3.642714738845825, "learning_rate": 4.885211116826212e-06, "loss": 0.38441234827041626, "step": 996 }, { "epoch": 0.25882658359293875, "grad_norm": 2.991595506668091, "learning_rate": 4.884912624724279e-06, "loss": 0.4215107560157776, "step": 997 }, { "epoch": 0.25908618899273106, "grad_norm": 5.8300652503967285, "learning_rate": 4.884613755218677e-06, "loss": 0.48930519819259644, "step": 998 }, { "epoch": 0.25934579439252337, "grad_norm": 2.202361822128296, "learning_rate": 4.884314508362239e-06, "loss": 0.38231778144836426, "step": 999 }, { "epoch": 0.25960539979231567, "grad_norm": 2.0191125869750977, "learning_rate": 4.884014884207865e-06, "loss": 0.42600518465042114, "step": 1000 }, { "epoch": 0.259865005192108, "grad_norm": 4.181741714477539, "learning_rate": 4.8837148828085225e-06, "loss": 0.5063180923461914, "step": 1001 }, { "epoch": 0.2601246105919003, "grad_norm": 2.913489818572998, "learning_rate": 4.883414504217244e-06, "loss": 0.3696708083152771, "step": 1002 }, { "epoch": 0.26038421599169265, "grad_norm": 6.684641361236572, "learning_rate": 4.88311374848713e-06, "loss": 0.502344012260437, "step": 1003 }, { "epoch": 0.26064382139148495, "grad_norm": 1.3189303874969482, "learning_rate": 4.882812615671347e-06, "loss": 0.40379494428634644, "step": 1004 }, { "epoch": 0.26090342679127726, "grad_norm": 3.0635602474212646, "learning_rate": 4.882511105823128e-06, "loss": 0.41840052604675293, "step": 1005 }, { "epoch": 0.26116303219106957, "grad_norm": 4.813144683837891, "learning_rate": 4.882209218995775e-06, "loss": 0.34306854009628296, "step": 1006 }, { "epoch": 0.2614226375908619, "grad_norm": 2.881474494934082, "learning_rate": 4.881906955242652e-06, "loss": 0.40475308895111084, "step": 1007 }, { "epoch": 0.2616822429906542, "grad_norm": 3.45511794090271, "learning_rate": 4.881604314617194e-06, "loss": 0.3786715269088745, "step": 1008 }, { "epoch": 0.26194184839044654, "grad_norm": 6.190754413604736, "learning_rate": 4.8813012971729e-06, "loss": 0.45695236325263977, "step": 1009 }, { "epoch": 0.26220145379023885, "grad_norm": 5.234792709350586, "learning_rate": 4.880997902963337e-06, "loss": 0.4490787386894226, "step": 1010 }, { "epoch": 0.26246105919003115, "grad_norm": 3.11917781829834, "learning_rate": 4.880694132042138e-06, "loss": 0.43977293372154236, "step": 1011 }, { "epoch": 0.26272066458982346, "grad_norm": 2.9668128490448, "learning_rate": 4.8803899844630034e-06, "loss": 0.39455777406692505, "step": 1012 }, { "epoch": 0.26298026998961577, "grad_norm": 3.026217222213745, "learning_rate": 4.880085460279699e-06, "loss": 0.38363298773765564, "step": 1013 }, { "epoch": 0.2632398753894081, "grad_norm": 6.055696964263916, "learning_rate": 4.879780559546058e-06, "loss": 0.33470383286476135, "step": 1014 }, { "epoch": 0.26349948078920044, "grad_norm": 2.4923887252807617, "learning_rate": 4.879475282315978e-06, "loss": 0.3525148034095764, "step": 1015 }, { "epoch": 0.26375908618899274, "grad_norm": 1.7049330472946167, "learning_rate": 4.879169628643428e-06, "loss": 0.40296030044555664, "step": 1016 }, { "epoch": 0.26401869158878505, "grad_norm": 4.216541290283203, "learning_rate": 4.878863598582439e-06, "loss": 0.40770024061203003, "step": 1017 }, { "epoch": 0.26427829698857735, "grad_norm": 2.671154260635376, "learning_rate": 4.87855719218711e-06, "loss": 0.37547868490219116, "step": 1018 }, { "epoch": 0.26453790238836966, "grad_norm": 2.495765447616577, "learning_rate": 4.878250409511608e-06, "loss": 0.38695263862609863, "step": 1019 }, { "epoch": 0.26479750778816197, "grad_norm": 3.683961868286133, "learning_rate": 4.877943250610163e-06, "loss": 0.3976961672306061, "step": 1020 }, { "epoch": 0.26505711318795433, "grad_norm": 4.11492395401001, "learning_rate": 4.8776357155370745e-06, "loss": 0.49908071756362915, "step": 1021 }, { "epoch": 0.26531671858774664, "grad_norm": 5.135095119476318, "learning_rate": 4.877327804346709e-06, "loss": 0.4609183967113495, "step": 1022 }, { "epoch": 0.26557632398753894, "grad_norm": 6.0788493156433105, "learning_rate": 4.877019517093497e-06, "loss": 0.35970449447631836, "step": 1023 }, { "epoch": 0.26583592938733125, "grad_norm": 2.611954927444458, "learning_rate": 4.876710853831935e-06, "loss": 0.36173415184020996, "step": 1024 }, { "epoch": 0.26609553478712356, "grad_norm": 2.1009230613708496, "learning_rate": 4.8764018146165905e-06, "loss": 0.3651844561100006, "step": 1025 }, { "epoch": 0.26635514018691586, "grad_norm": 2.5800726413726807, "learning_rate": 4.876092399502093e-06, "loss": 0.373276948928833, "step": 1026 }, { "epoch": 0.2666147455867082, "grad_norm": 2.0952565670013428, "learning_rate": 4.87578260854314e-06, "loss": 0.35665494203567505, "step": 1027 }, { "epoch": 0.26687435098650053, "grad_norm": 4.3848371505737305, "learning_rate": 4.875472441794496e-06, "loss": 0.4518216550350189, "step": 1028 }, { "epoch": 0.26713395638629284, "grad_norm": 2.0690534114837646, "learning_rate": 4.875161899310992e-06, "loss": 0.4080425500869751, "step": 1029 }, { "epoch": 0.26739356178608514, "grad_norm": 3.087284564971924, "learning_rate": 4.874850981147523e-06, "loss": 0.42382967472076416, "step": 1030 }, { "epoch": 0.26765316718587745, "grad_norm": 4.824130535125732, "learning_rate": 4.874539687359054e-06, "loss": 0.5165126323699951, "step": 1031 }, { "epoch": 0.26791277258566976, "grad_norm": 6.599330902099609, "learning_rate": 4.874228018000613e-06, "loss": 0.4901573061943054, "step": 1032 }, { "epoch": 0.2681723779854621, "grad_norm": 1.3101646900177002, "learning_rate": 4.8739159731272975e-06, "loss": 0.3822336494922638, "step": 1033 }, { "epoch": 0.2684319833852544, "grad_norm": 2.2111082077026367, "learning_rate": 4.873603552794268e-06, "loss": 0.44386062026023865, "step": 1034 }, { "epoch": 0.26869158878504673, "grad_norm": 1.4271750450134277, "learning_rate": 4.873290757056756e-06, "loss": 0.38831305503845215, "step": 1035 }, { "epoch": 0.26895119418483904, "grad_norm": 2.212939500808716, "learning_rate": 4.872977585970054e-06, "loss": 0.38293734192848206, "step": 1036 }, { "epoch": 0.26921079958463134, "grad_norm": 3.6602702140808105, "learning_rate": 4.872664039589525e-06, "loss": 0.5223153829574585, "step": 1037 }, { "epoch": 0.26947040498442365, "grad_norm": 3.0186870098114014, "learning_rate": 4.872350117970596e-06, "loss": 0.44671231508255005, "step": 1038 }, { "epoch": 0.269730010384216, "grad_norm": 4.757496356964111, "learning_rate": 4.8720358211687615e-06, "loss": 0.45835137367248535, "step": 1039 }, { "epoch": 0.2699896157840083, "grad_norm": 4.240511894226074, "learning_rate": 4.871721149239583e-06, "loss": 0.49123311042785645, "step": 1040 }, { "epoch": 0.2702492211838006, "grad_norm": 3.7908973693847656, "learning_rate": 4.8714061022386845e-06, "loss": 0.43522241711616516, "step": 1041 }, { "epoch": 0.27050882658359293, "grad_norm": 3.2279911041259766, "learning_rate": 4.8710906802217624e-06, "loss": 0.5116612911224365, "step": 1042 }, { "epoch": 0.27076843198338524, "grad_norm": 3.6047778129577637, "learning_rate": 4.8707748832445745e-06, "loss": 0.46232491731643677, "step": 1043 }, { "epoch": 0.27102803738317754, "grad_norm": 3.0300192832946777, "learning_rate": 4.870458711362946e-06, "loss": 0.42187464237213135, "step": 1044 }, { "epoch": 0.2712876427829699, "grad_norm": 2.124648094177246, "learning_rate": 4.8701421646327694e-06, "loss": 0.43468523025512695, "step": 1045 }, { "epoch": 0.2715472481827622, "grad_norm": 3.819775104522705, "learning_rate": 4.869825243110003e-06, "loss": 0.5076805353164673, "step": 1046 }, { "epoch": 0.2718068535825545, "grad_norm": 4.879660606384277, "learning_rate": 4.869507946850671e-06, "loss": 0.46949613094329834, "step": 1047 }, { "epoch": 0.2720664589823468, "grad_norm": 3.5254485607147217, "learning_rate": 4.869190275910865e-06, "loss": 0.48839882016181946, "step": 1048 }, { "epoch": 0.27232606438213913, "grad_norm": 2.5345699787139893, "learning_rate": 4.868872230346741e-06, "loss": 0.41200605034828186, "step": 1049 }, { "epoch": 0.27258566978193144, "grad_norm": 2.288473129272461, "learning_rate": 4.8685538102145215e-06, "loss": 0.4348980188369751, "step": 1050 }, { "epoch": 0.2728452751817238, "grad_norm": 2.9936869144439697, "learning_rate": 4.868235015570497e-06, "loss": 0.37443768978118896, "step": 1051 }, { "epoch": 0.2731048805815161, "grad_norm": 2.07033634185791, "learning_rate": 4.867915846471024e-06, "loss": 0.35640114545822144, "step": 1052 }, { "epoch": 0.2733644859813084, "grad_norm": 4.675922393798828, "learning_rate": 4.867596302972523e-06, "loss": 0.38116294145584106, "step": 1053 }, { "epoch": 0.2736240913811007, "grad_norm": 4.482944965362549, "learning_rate": 4.867276385131482e-06, "loss": 0.41187340021133423, "step": 1054 }, { "epoch": 0.273883696780893, "grad_norm": 2.8895962238311768, "learning_rate": 4.866956093004454e-06, "loss": 0.3710104525089264, "step": 1055 }, { "epoch": 0.27414330218068533, "grad_norm": 5.9456095695495605, "learning_rate": 4.866635426648062e-06, "loss": 0.5245624780654907, "step": 1056 }, { "epoch": 0.2744029075804777, "grad_norm": 4.880764961242676, "learning_rate": 4.866314386118991e-06, "loss": 0.41733384132385254, "step": 1057 }, { "epoch": 0.27466251298027, "grad_norm": 3.243873357772827, "learning_rate": 4.865992971473993e-06, "loss": 0.48841094970703125, "step": 1058 }, { "epoch": 0.2749221183800623, "grad_norm": 4.7131171226501465, "learning_rate": 4.865671182769888e-06, "loss": 0.41851645708084106, "step": 1059 }, { "epoch": 0.2751817237798546, "grad_norm": 5.264764308929443, "learning_rate": 4.865349020063561e-06, "loss": 0.47876837849617004, "step": 1060 }, { "epoch": 0.2754413291796469, "grad_norm": 5.289976119995117, "learning_rate": 4.865026483411961e-06, "loss": 0.46170181035995483, "step": 1061 }, { "epoch": 0.2757009345794392, "grad_norm": 5.276914596557617, "learning_rate": 4.864703572872107e-06, "loss": 0.4760853946208954, "step": 1062 }, { "epoch": 0.2759605399792316, "grad_norm": 2.7172391414642334, "learning_rate": 4.864380288501082e-06, "loss": 0.42221254110336304, "step": 1063 }, { "epoch": 0.2762201453790239, "grad_norm": 2.7391276359558105, "learning_rate": 4.864056630356034e-06, "loss": 0.3744608163833618, "step": 1064 }, { "epoch": 0.2764797507788162, "grad_norm": 5.391172409057617, "learning_rate": 4.86373259849418e-06, "loss": 0.40960538387298584, "step": 1065 }, { "epoch": 0.2767393561786085, "grad_norm": 5.216745853424072, "learning_rate": 4.8634081929728e-06, "loss": 0.3591148853302002, "step": 1066 }, { "epoch": 0.2769989615784008, "grad_norm": 3.660759925842285, "learning_rate": 4.863083413849243e-06, "loss": 0.3662911653518677, "step": 1067 }, { "epoch": 0.2772585669781931, "grad_norm": 5.62645959854126, "learning_rate": 4.862758261180921e-06, "loss": 0.49298274517059326, "step": 1068 }, { "epoch": 0.2775181723779855, "grad_norm": 4.178040981292725, "learning_rate": 4.8624327350253145e-06, "loss": 0.45818087458610535, "step": 1069 }, { "epoch": 0.2777777777777778, "grad_norm": 3.444190263748169, "learning_rate": 4.862106835439968e-06, "loss": 0.4213128983974457, "step": 1070 }, { "epoch": 0.2780373831775701, "grad_norm": 2.4038023948669434, "learning_rate": 4.861780562482495e-06, "loss": 0.38811543583869934, "step": 1071 }, { "epoch": 0.2782969885773624, "grad_norm": 8.811697959899902, "learning_rate": 4.861453916210571e-06, "loss": 0.5673283338546753, "step": 1072 }, { "epoch": 0.2785565939771547, "grad_norm": 3.655691146850586, "learning_rate": 4.861126896681941e-06, "loss": 0.43657803535461426, "step": 1073 }, { "epoch": 0.278816199376947, "grad_norm": 1.9915580749511719, "learning_rate": 4.8607995039544135e-06, "loss": 0.34734803438186646, "step": 1074 }, { "epoch": 0.2790758047767394, "grad_norm": 2.0409598350524902, "learning_rate": 4.8604717380858655e-06, "loss": 0.3576924204826355, "step": 1075 }, { "epoch": 0.2793354101765317, "grad_norm": 2.5243008136749268, "learning_rate": 4.8601435991342375e-06, "loss": 0.4182720482349396, "step": 1076 }, { "epoch": 0.279595015576324, "grad_norm": 4.582448959350586, "learning_rate": 4.859815087157536e-06, "loss": 0.4567525386810303, "step": 1077 }, { "epoch": 0.2798546209761163, "grad_norm": 6.13185977935791, "learning_rate": 4.859486202213836e-06, "loss": 0.5188882350921631, "step": 1078 }, { "epoch": 0.2801142263759086, "grad_norm": 7.361220359802246, "learning_rate": 4.859156944361276e-06, "loss": 0.47134220600128174, "step": 1079 }, { "epoch": 0.2803738317757009, "grad_norm": 4.045049667358398, "learning_rate": 4.858827313658062e-06, "loss": 0.3901698589324951, "step": 1080 }, { "epoch": 0.28063343717549327, "grad_norm": 7.565834999084473, "learning_rate": 4.858497310162465e-06, "loss": 0.4007781744003296, "step": 1081 }, { "epoch": 0.2808930425752856, "grad_norm": 5.238163948059082, "learning_rate": 4.858166933932821e-06, "loss": 0.39302825927734375, "step": 1082 }, { "epoch": 0.2811526479750779, "grad_norm": 3.2015838623046875, "learning_rate": 4.857836185027534e-06, "loss": 0.40426522493362427, "step": 1083 }, { "epoch": 0.2814122533748702, "grad_norm": 4.532655239105225, "learning_rate": 4.857505063505073e-06, "loss": 0.5012717247009277, "step": 1084 }, { "epoch": 0.2816718587746625, "grad_norm": 3.0277113914489746, "learning_rate": 4.857173569423971e-06, "loss": 0.4819232225418091, "step": 1085 }, { "epoch": 0.2819314641744548, "grad_norm": 6.517996788024902, "learning_rate": 4.856841702842831e-06, "loss": 0.44555050134658813, "step": 1086 }, { "epoch": 0.28219106957424717, "grad_norm": 6.071752548217773, "learning_rate": 4.856509463820318e-06, "loss": 0.5118427276611328, "step": 1087 }, { "epoch": 0.2824506749740395, "grad_norm": 5.206396102905273, "learning_rate": 4.856176852415164e-06, "loss": 0.3537835478782654, "step": 1088 }, { "epoch": 0.2827102803738318, "grad_norm": 5.086874485015869, "learning_rate": 4.855843868686168e-06, "loss": 0.44068485498428345, "step": 1089 }, { "epoch": 0.2829698857736241, "grad_norm": 3.8357174396514893, "learning_rate": 4.855510512692194e-06, "loss": 0.42647555470466614, "step": 1090 }, { "epoch": 0.2832294911734164, "grad_norm": 6.258233547210693, "learning_rate": 4.8551767844921695e-06, "loss": 0.44124650955200195, "step": 1091 }, { "epoch": 0.2834890965732087, "grad_norm": 3.5335657596588135, "learning_rate": 4.854842684145093e-06, "loss": 0.3431304395198822, "step": 1092 }, { "epoch": 0.28374870197300106, "grad_norm": 2.5280632972717285, "learning_rate": 4.854508211710025e-06, "loss": 0.38710784912109375, "step": 1093 }, { "epoch": 0.28400830737279337, "grad_norm": 3.422869920730591, "learning_rate": 4.85417336724609e-06, "loss": 0.370957612991333, "step": 1094 }, { "epoch": 0.2842679127725857, "grad_norm": 2.1780104637145996, "learning_rate": 4.853838150812485e-06, "loss": 0.3670755624771118, "step": 1095 }, { "epoch": 0.284527518172378, "grad_norm": 4.108975410461426, "learning_rate": 4.853502562468464e-06, "loss": 0.4106486439704895, "step": 1096 }, { "epoch": 0.2847871235721703, "grad_norm": 4.211956024169922, "learning_rate": 4.853166602273356e-06, "loss": 0.44760096073150635, "step": 1097 }, { "epoch": 0.2850467289719626, "grad_norm": 5.072937965393066, "learning_rate": 4.852830270286548e-06, "loss": 0.4807688891887665, "step": 1098 }, { "epoch": 0.28530633437175495, "grad_norm": 10.51195240020752, "learning_rate": 4.852493566567496e-06, "loss": 0.4435202181339264, "step": 1099 }, { "epoch": 0.28556593977154726, "grad_norm": 5.421151161193848, "learning_rate": 4.852156491175724e-06, "loss": 0.3924611806869507, "step": 1100 }, { "epoch": 0.28582554517133957, "grad_norm": 2.562262773513794, "learning_rate": 4.851819044170816e-06, "loss": 0.42349380254745483, "step": 1101 }, { "epoch": 0.2860851505711319, "grad_norm": 4.018048286437988, "learning_rate": 4.851481225612426e-06, "loss": 0.4357547163963318, "step": 1102 }, { "epoch": 0.2863447559709242, "grad_norm": 2.0608632564544678, "learning_rate": 4.851143035560274e-06, "loss": 0.39312267303466797, "step": 1103 }, { "epoch": 0.2866043613707165, "grad_norm": 5.192957401275635, "learning_rate": 4.850804474074143e-06, "loss": 0.3979332149028778, "step": 1104 }, { "epoch": 0.28686396677050885, "grad_norm": 3.0248959064483643, "learning_rate": 4.8504655412138816e-06, "loss": 0.4174812436103821, "step": 1105 }, { "epoch": 0.28712357217030116, "grad_norm": 4.7238688468933105, "learning_rate": 4.850126237039408e-06, "loss": 0.41280871629714966, "step": 1106 }, { "epoch": 0.28738317757009346, "grad_norm": 3.652369737625122, "learning_rate": 4.849786561610702e-06, "loss": 0.380988746881485, "step": 1107 }, { "epoch": 0.28764278296988577, "grad_norm": 3.404042959213257, "learning_rate": 4.84944651498781e-06, "loss": 0.3815971612930298, "step": 1108 }, { "epoch": 0.2879023883696781, "grad_norm": 4.454664707183838, "learning_rate": 4.849106097230845e-06, "loss": 0.4131821393966675, "step": 1109 }, { "epoch": 0.2881619937694704, "grad_norm": 3.486097574234009, "learning_rate": 4.848765308399987e-06, "loss": 0.43772321939468384, "step": 1110 }, { "epoch": 0.28842159916926274, "grad_norm": 5.2171630859375, "learning_rate": 4.848424148555476e-06, "loss": 0.4314087927341461, "step": 1111 }, { "epoch": 0.28868120456905505, "grad_norm": 2.189755916595459, "learning_rate": 4.848082617757624e-06, "loss": 0.37329626083374023, "step": 1112 }, { "epoch": 0.28894080996884736, "grad_norm": 9.372209548950195, "learning_rate": 4.847740716066804e-06, "loss": 0.4440680146217346, "step": 1113 }, { "epoch": 0.28920041536863966, "grad_norm": 2.601062059402466, "learning_rate": 4.847398443543459e-06, "loss": 0.4021087884902954, "step": 1114 }, { "epoch": 0.28946002076843197, "grad_norm": 5.248325824737549, "learning_rate": 4.847055800248092e-06, "loss": 0.46465665102005005, "step": 1115 }, { "epoch": 0.2897196261682243, "grad_norm": 1.9207937717437744, "learning_rate": 4.846712786241275e-06, "loss": 0.3584354519844055, "step": 1116 }, { "epoch": 0.28997923156801664, "grad_norm": 9.060131072998047, "learning_rate": 4.8463694015836465e-06, "loss": 0.419205904006958, "step": 1117 }, { "epoch": 0.29023883696780894, "grad_norm": 2.923635244369507, "learning_rate": 4.846025646335909e-06, "loss": 0.4054134488105774, "step": 1118 }, { "epoch": 0.29049844236760125, "grad_norm": 1.7884540557861328, "learning_rate": 4.845681520558829e-06, "loss": 0.35715335607528687, "step": 1119 }, { "epoch": 0.29075804776739356, "grad_norm": 2.999558448791504, "learning_rate": 4.845337024313242e-06, "loss": 0.4109344482421875, "step": 1120 }, { "epoch": 0.29101765316718586, "grad_norm": 2.9245266914367676, "learning_rate": 4.844992157660044e-06, "loss": 0.38675856590270996, "step": 1121 }, { "epoch": 0.29127725856697817, "grad_norm": 3.817291259765625, "learning_rate": 4.844646920660203e-06, "loss": 0.44459807872772217, "step": 1122 }, { "epoch": 0.29153686396677053, "grad_norm": 2.5742454528808594, "learning_rate": 4.844301313374747e-06, "loss": 0.392677366733551, "step": 1123 }, { "epoch": 0.29179646936656284, "grad_norm": 4.517976760864258, "learning_rate": 4.843955335864772e-06, "loss": 0.3144022226333618, "step": 1124 }, { "epoch": 0.29205607476635514, "grad_norm": 3.1106159687042236, "learning_rate": 4.843608988191439e-06, "loss": 0.41461342573165894, "step": 1125 }, { "epoch": 0.29231568016614745, "grad_norm": 3.0947391986846924, "learning_rate": 4.843262270415974e-06, "loss": 0.410730242729187, "step": 1126 }, { "epoch": 0.29257528556593976, "grad_norm": 5.797959804534912, "learning_rate": 4.842915182599669e-06, "loss": 0.344137966632843, "step": 1127 }, { "epoch": 0.29283489096573206, "grad_norm": 3.1230881214141846, "learning_rate": 4.842567724803881e-06, "loss": 0.3851521611213684, "step": 1128 }, { "epoch": 0.2930944963655244, "grad_norm": 6.663686275482178, "learning_rate": 4.842219897090033e-06, "loss": 0.3442617356777191, "step": 1129 }, { "epoch": 0.29335410176531673, "grad_norm": 5.589675426483154, "learning_rate": 4.8418716995196125e-06, "loss": 0.45583710074424744, "step": 1130 }, { "epoch": 0.29361370716510904, "grad_norm": 4.843136787414551, "learning_rate": 4.841523132154173e-06, "loss": 0.4142068922519684, "step": 1131 }, { "epoch": 0.29387331256490135, "grad_norm": 1.9367215633392334, "learning_rate": 4.841174195055333e-06, "loss": 0.332158625125885, "step": 1132 }, { "epoch": 0.29413291796469365, "grad_norm": 5.769277095794678, "learning_rate": 4.8408248882847775e-06, "loss": 0.46471351385116577, "step": 1133 }, { "epoch": 0.29439252336448596, "grad_norm": 5.212897777557373, "learning_rate": 4.8404752119042556e-06, "loss": 0.38783958554267883, "step": 1134 }, { "epoch": 0.2946521287642783, "grad_norm": 4.84702205657959, "learning_rate": 4.8401251659755805e-06, "loss": 0.5080910921096802, "step": 1135 }, { "epoch": 0.2949117341640706, "grad_norm": 4.3845601081848145, "learning_rate": 4.839774750560635e-06, "loss": 0.4886835813522339, "step": 1136 }, { "epoch": 0.29517133956386293, "grad_norm": 4.661111831665039, "learning_rate": 4.839423965721362e-06, "loss": 0.40490487217903137, "step": 1137 }, { "epoch": 0.29543094496365524, "grad_norm": 4.728646278381348, "learning_rate": 4.839072811519773e-06, "loss": 0.4541248679161072, "step": 1138 }, { "epoch": 0.29569055036344755, "grad_norm": 3.83603572845459, "learning_rate": 4.838721288017945e-06, "loss": 0.38083234429359436, "step": 1139 }, { "epoch": 0.29595015576323985, "grad_norm": 2.3166167736053467, "learning_rate": 4.838369395278019e-06, "loss": 0.3772691488265991, "step": 1140 }, { "epoch": 0.2962097611630322, "grad_norm": 2.426366090774536, "learning_rate": 4.838017133362201e-06, "loss": 0.3274155557155609, "step": 1141 }, { "epoch": 0.2964693665628245, "grad_norm": 1.7363402843475342, "learning_rate": 4.8376645023327625e-06, "loss": 0.383095383644104, "step": 1142 }, { "epoch": 0.2967289719626168, "grad_norm": 4.495004177093506, "learning_rate": 4.837311502252042e-06, "loss": 0.377047598361969, "step": 1143 }, { "epoch": 0.29698857736240913, "grad_norm": 5.841395854949951, "learning_rate": 4.836958133182441e-06, "loss": 0.4877317547798157, "step": 1144 }, { "epoch": 0.29724818276220144, "grad_norm": 2.5423498153686523, "learning_rate": 4.836604395186426e-06, "loss": 0.49169233441352844, "step": 1145 }, { "epoch": 0.29750778816199375, "grad_norm": 4.09756326675415, "learning_rate": 4.836250288326532e-06, "loss": 0.40723538398742676, "step": 1146 }, { "epoch": 0.2977673935617861, "grad_norm": 4.469913482666016, "learning_rate": 4.835895812665356e-06, "loss": 0.5126084089279175, "step": 1147 }, { "epoch": 0.2980269989615784, "grad_norm": 3.8550641536712646, "learning_rate": 4.835540968265559e-06, "loss": 0.3544465899467468, "step": 1148 }, { "epoch": 0.2982866043613707, "grad_norm": 2.690175771713257, "learning_rate": 4.8351857551898734e-06, "loss": 0.37803518772125244, "step": 1149 }, { "epoch": 0.29854620976116303, "grad_norm": 8.541043281555176, "learning_rate": 4.83483017350109e-06, "loss": 0.5390225648880005, "step": 1150 }, { "epoch": 0.29880581516095533, "grad_norm": 6.279774188995361, "learning_rate": 4.834474223262068e-06, "loss": 0.4751748740673065, "step": 1151 }, { "epoch": 0.29906542056074764, "grad_norm": 5.487546920776367, "learning_rate": 4.834117904535732e-06, "loss": 0.49144360423088074, "step": 1152 }, { "epoch": 0.29932502596054, "grad_norm": 2.1328518390655518, "learning_rate": 4.83376121738507e-06, "loss": 0.3725343644618988, "step": 1153 }, { "epoch": 0.2995846313603323, "grad_norm": 2.2010419368743896, "learning_rate": 4.833404161873137e-06, "loss": 0.3650275468826294, "step": 1154 }, { "epoch": 0.2998442367601246, "grad_norm": 4.056833744049072, "learning_rate": 4.8330467380630515e-06, "loss": 0.417880654335022, "step": 1155 }, { "epoch": 0.3001038421599169, "grad_norm": 3.820864200592041, "learning_rate": 4.8326889460179984e-06, "loss": 0.416215717792511, "step": 1156 }, { "epoch": 0.30036344755970923, "grad_norm": 5.6298627853393555, "learning_rate": 4.832330785801227e-06, "loss": 0.43950724601745605, "step": 1157 }, { "epoch": 0.30062305295950154, "grad_norm": 3.782186985015869, "learning_rate": 4.8319722574760504e-06, "loss": 0.43298113346099854, "step": 1158 }, { "epoch": 0.3008826583592939, "grad_norm": 1.5532351732254028, "learning_rate": 4.8316133611058504e-06, "loss": 0.3573913276195526, "step": 1159 }, { "epoch": 0.3011422637590862, "grad_norm": 4.019172668457031, "learning_rate": 4.831254096754072e-06, "loss": 0.4490808844566345, "step": 1160 }, { "epoch": 0.3014018691588785, "grad_norm": 3.5102860927581787, "learning_rate": 4.8308944644842225e-06, "loss": 0.42529481649398804, "step": 1161 }, { "epoch": 0.3016614745586708, "grad_norm": 3.8632819652557373, "learning_rate": 4.8305344643598774e-06, "loss": 0.38810089230537415, "step": 1162 }, { "epoch": 0.3019210799584631, "grad_norm": 4.427507400512695, "learning_rate": 4.830174096444678e-06, "loss": 0.4378880262374878, "step": 1163 }, { "epoch": 0.30218068535825543, "grad_norm": 4.279012680053711, "learning_rate": 4.8298133608023275e-06, "loss": 0.48486924171447754, "step": 1164 }, { "epoch": 0.3024402907580478, "grad_norm": 3.349250316619873, "learning_rate": 4.829452257496596e-06, "loss": 0.3766862154006958, "step": 1165 }, { "epoch": 0.3026998961578401, "grad_norm": 3.4162697792053223, "learning_rate": 4.829090786591319e-06, "loss": 0.3674120306968689, "step": 1166 }, { "epoch": 0.3029595015576324, "grad_norm": 3.2492804527282715, "learning_rate": 4.828728948150395e-06, "loss": 0.3566449284553528, "step": 1167 }, { "epoch": 0.3032191069574247, "grad_norm": 3.6305480003356934, "learning_rate": 4.82836674223779e-06, "loss": 0.3750021457672119, "step": 1168 }, { "epoch": 0.303478712357217, "grad_norm": 2.9532923698425293, "learning_rate": 4.828004168917534e-06, "loss": 0.36699503660202026, "step": 1169 }, { "epoch": 0.3037383177570093, "grad_norm": 4.2946014404296875, "learning_rate": 4.8276412282537205e-06, "loss": 0.45794346928596497, "step": 1170 }, { "epoch": 0.3039979231568017, "grad_norm": 2.385885238647461, "learning_rate": 4.8272779203105095e-06, "loss": 0.3461785316467285, "step": 1171 }, { "epoch": 0.304257528556594, "grad_norm": 2.9831032752990723, "learning_rate": 4.826914245152126e-06, "loss": 0.37087154388427734, "step": 1172 }, { "epoch": 0.3045171339563863, "grad_norm": 2.6601223945617676, "learning_rate": 4.826550202842858e-06, "loss": 0.4186255931854248, "step": 1173 }, { "epoch": 0.3047767393561786, "grad_norm": 5.641952037811279, "learning_rate": 4.826185793447061e-06, "loss": 0.45812469720840454, "step": 1174 }, { "epoch": 0.3050363447559709, "grad_norm": 3.164882183074951, "learning_rate": 4.825821017029154e-06, "loss": 0.4386124610900879, "step": 1175 }, { "epoch": 0.3052959501557632, "grad_norm": 5.304826259613037, "learning_rate": 4.8254558736536216e-06, "loss": 0.38892027735710144, "step": 1176 }, { "epoch": 0.3055555555555556, "grad_norm": 2.0600247383117676, "learning_rate": 4.8250903633850125e-06, "loss": 0.3987712860107422, "step": 1177 }, { "epoch": 0.3058151609553479, "grad_norm": 3.171839475631714, "learning_rate": 4.82472448628794e-06, "loss": 0.3483904004096985, "step": 1178 }, { "epoch": 0.3060747663551402, "grad_norm": 4.922651767730713, "learning_rate": 4.824358242427083e-06, "loss": 0.4447808861732483, "step": 1179 }, { "epoch": 0.3063343717549325, "grad_norm": 3.3155789375305176, "learning_rate": 4.823991631867186e-06, "loss": 0.34440192580223083, "step": 1180 }, { "epoch": 0.3065939771547248, "grad_norm": 3.777911424636841, "learning_rate": 4.8236246546730555e-06, "loss": 0.449526846408844, "step": 1181 }, { "epoch": 0.3068535825545171, "grad_norm": 3.5701894760131836, "learning_rate": 4.823257310909567e-06, "loss": 0.4033127725124359, "step": 1182 }, { "epoch": 0.3071131879543095, "grad_norm": 3.8088934421539307, "learning_rate": 4.822889600641657e-06, "loss": 0.38665828108787537, "step": 1183 }, { "epoch": 0.3073727933541018, "grad_norm": 6.655519485473633, "learning_rate": 4.822521523934328e-06, "loss": 0.4485987722873688, "step": 1184 }, { "epoch": 0.3076323987538941, "grad_norm": 1.6488635540008545, "learning_rate": 4.822153080852648e-06, "loss": 0.32523831725120544, "step": 1185 }, { "epoch": 0.3078920041536864, "grad_norm": 4.803643703460693, "learning_rate": 4.82178427146175e-06, "loss": 0.4737476408481598, "step": 1186 }, { "epoch": 0.3081516095534787, "grad_norm": 2.7367842197418213, "learning_rate": 4.82141509582683e-06, "loss": 0.37398040294647217, "step": 1187 }, { "epoch": 0.308411214953271, "grad_norm": 4.101075649261475, "learning_rate": 4.821045554013151e-06, "loss": 0.4226013422012329, "step": 1188 }, { "epoch": 0.30867082035306337, "grad_norm": 2.4455184936523438, "learning_rate": 4.820675646086037e-06, "loss": 0.35928061604499817, "step": 1189 }, { "epoch": 0.3089304257528557, "grad_norm": 1.9854371547698975, "learning_rate": 4.8203053721108815e-06, "loss": 0.3654870390892029, "step": 1190 }, { "epoch": 0.309190031152648, "grad_norm": 2.1313118934631348, "learning_rate": 4.819934732153141e-06, "loss": 0.3153678774833679, "step": 1191 }, { "epoch": 0.3094496365524403, "grad_norm": 2.0454599857330322, "learning_rate": 4.819563726278334e-06, "loss": 0.3472070097923279, "step": 1192 }, { "epoch": 0.3097092419522326, "grad_norm": 2.112154483795166, "learning_rate": 4.819192354552047e-06, "loss": 0.3532834053039551, "step": 1193 }, { "epoch": 0.3099688473520249, "grad_norm": 5.27289342880249, "learning_rate": 4.81882061703993e-06, "loss": 0.4703049659729004, "step": 1194 }, { "epoch": 0.31022845275181726, "grad_norm": 4.886516571044922, "learning_rate": 4.818448513807698e-06, "loss": 0.464249849319458, "step": 1195 }, { "epoch": 0.31048805815160957, "grad_norm": 2.1395950317382812, "learning_rate": 4.818076044921129e-06, "loss": 0.3465769290924072, "step": 1196 }, { "epoch": 0.3107476635514019, "grad_norm": 4.666955947875977, "learning_rate": 4.817703210446069e-06, "loss": 0.4191746413707733, "step": 1197 }, { "epoch": 0.3110072689511942, "grad_norm": 1.993990421295166, "learning_rate": 4.817330010448426e-06, "loss": 0.31146615743637085, "step": 1198 }, { "epoch": 0.3112668743509865, "grad_norm": 4.47019100189209, "learning_rate": 4.816956444994172e-06, "loss": 0.43672123551368713, "step": 1199 }, { "epoch": 0.3115264797507788, "grad_norm": 2.7343506813049316, "learning_rate": 4.816582514149344e-06, "loss": 0.3652037978172302, "step": 1200 }, { "epoch": 0.31178608515057116, "grad_norm": 2.12104868888855, "learning_rate": 4.816208217980049e-06, "loss": 0.34339672327041626, "step": 1201 }, { "epoch": 0.31204569055036346, "grad_norm": 3.5707929134368896, "learning_rate": 4.815833556552448e-06, "loss": 0.36643171310424805, "step": 1202 }, { "epoch": 0.31230529595015577, "grad_norm": 2.126831531524658, "learning_rate": 4.815458529932778e-06, "loss": 0.34557056427001953, "step": 1203 }, { "epoch": 0.3125649013499481, "grad_norm": 5.493929386138916, "learning_rate": 4.815083138187331e-06, "loss": 0.3080088198184967, "step": 1204 }, { "epoch": 0.3128245067497404, "grad_norm": 2.298093318939209, "learning_rate": 4.8147073813824695e-06, "loss": 0.3957849442958832, "step": 1205 }, { "epoch": 0.3130841121495327, "grad_norm": 3.3866453170776367, "learning_rate": 4.814331259584619e-06, "loss": 0.4062081575393677, "step": 1206 }, { "epoch": 0.31334371754932505, "grad_norm": 3.4661567211151123, "learning_rate": 4.8139547728602685e-06, "loss": 0.47245514392852783, "step": 1207 }, { "epoch": 0.31360332294911736, "grad_norm": 3.5608298778533936, "learning_rate": 4.8135779212759725e-06, "loss": 0.40338069200515747, "step": 1208 }, { "epoch": 0.31386292834890966, "grad_norm": 2.0230367183685303, "learning_rate": 4.81320070489835e-06, "loss": 0.3202235698699951, "step": 1209 }, { "epoch": 0.31412253374870197, "grad_norm": 4.135705947875977, "learning_rate": 4.812823123794084e-06, "loss": 0.42452430725097656, "step": 1210 }, { "epoch": 0.3143821391484943, "grad_norm": 1.7899632453918457, "learning_rate": 4.8124451780299215e-06, "loss": 0.3547184467315674, "step": 1211 }, { "epoch": 0.3146417445482866, "grad_norm": 4.144957065582275, "learning_rate": 4.812066867672676e-06, "loss": 0.4252527952194214, "step": 1212 }, { "epoch": 0.31490134994807895, "grad_norm": 3.448525905609131, "learning_rate": 4.8116881927892225e-06, "loss": 0.4322888255119324, "step": 1213 }, { "epoch": 0.31516095534787125, "grad_norm": 3.139932155609131, "learning_rate": 4.811309153446503e-06, "loss": 0.4797699451446533, "step": 1214 }, { "epoch": 0.31542056074766356, "grad_norm": 3.684122323989868, "learning_rate": 4.810929749711523e-06, "loss": 0.4181937277317047, "step": 1215 }, { "epoch": 0.31568016614745587, "grad_norm": 3.80249285697937, "learning_rate": 4.810549981651353e-06, "loss": 0.4786743223667145, "step": 1216 }, { "epoch": 0.31593977154724817, "grad_norm": 3.558798313140869, "learning_rate": 4.810169849333126e-06, "loss": 0.407772421836853, "step": 1217 }, { "epoch": 0.3161993769470405, "grad_norm": 2.6333165168762207, "learning_rate": 4.8097893528240415e-06, "loss": 0.3659238815307617, "step": 1218 }, { "epoch": 0.31645898234683284, "grad_norm": 3.0893356800079346, "learning_rate": 4.809408492191362e-06, "loss": 0.5031160712242126, "step": 1219 }, { "epoch": 0.31671858774662515, "grad_norm": 2.580040454864502, "learning_rate": 4.809027267502415e-06, "loss": 0.36495986580848694, "step": 1220 }, { "epoch": 0.31697819314641745, "grad_norm": 1.4651529788970947, "learning_rate": 4.808645678824593e-06, "loss": 0.32769912481307983, "step": 1221 }, { "epoch": 0.31723779854620976, "grad_norm": 5.574957847595215, "learning_rate": 4.8082637262253515e-06, "loss": 0.5087754726409912, "step": 1222 }, { "epoch": 0.31749740394600207, "grad_norm": 3.522477626800537, "learning_rate": 4.807881409772211e-06, "loss": 0.34983521699905396, "step": 1223 }, { "epoch": 0.3177570093457944, "grad_norm": 4.84499979019165, "learning_rate": 4.807498729532758e-06, "loss": 0.4910189211368561, "step": 1224 }, { "epoch": 0.31801661474558673, "grad_norm": 2.888317346572876, "learning_rate": 4.807115685574638e-06, "loss": 0.442336767911911, "step": 1225 }, { "epoch": 0.31827622014537904, "grad_norm": 2.3127942085266113, "learning_rate": 4.806732277965569e-06, "loss": 0.3374381363391876, "step": 1226 }, { "epoch": 0.31853582554517135, "grad_norm": 3.927988290786743, "learning_rate": 4.806348506773325e-06, "loss": 0.4836910665035248, "step": 1227 }, { "epoch": 0.31879543094496365, "grad_norm": 2.531118869781494, "learning_rate": 4.805964372065748e-06, "loss": 0.4088473320007324, "step": 1228 }, { "epoch": 0.31905503634475596, "grad_norm": 3.6090424060821533, "learning_rate": 4.805579873910746e-06, "loss": 0.4256136417388916, "step": 1229 }, { "epoch": 0.31931464174454827, "grad_norm": 3.565427303314209, "learning_rate": 4.805195012376289e-06, "loss": 0.4502248167991638, "step": 1230 }, { "epoch": 0.31957424714434063, "grad_norm": 3.7655458450317383, "learning_rate": 4.804809787530411e-06, "loss": 0.45750993490219116, "step": 1231 }, { "epoch": 0.31983385254413293, "grad_norm": 5.239974498748779, "learning_rate": 4.804424199441213e-06, "loss": 0.5453341007232666, "step": 1232 }, { "epoch": 0.32009345794392524, "grad_norm": 2.4360318183898926, "learning_rate": 4.804038248176855e-06, "loss": 0.3653954565525055, "step": 1233 }, { "epoch": 0.32035306334371755, "grad_norm": 2.1006181240081787, "learning_rate": 4.803651933805567e-06, "loss": 0.3937322199344635, "step": 1234 }, { "epoch": 0.32061266874350985, "grad_norm": 3.2716798782348633, "learning_rate": 4.803265256395639e-06, "loss": 0.3926139175891876, "step": 1235 }, { "epoch": 0.32087227414330216, "grad_norm": 1.893674373626709, "learning_rate": 4.802878216015428e-06, "loss": 0.3739561438560486, "step": 1236 }, { "epoch": 0.3211318795430945, "grad_norm": 5.432331085205078, "learning_rate": 4.802490812733352e-06, "loss": 0.4113558530807495, "step": 1237 }, { "epoch": 0.32139148494288683, "grad_norm": 4.903778076171875, "learning_rate": 4.8021030466178965e-06, "loss": 0.4262777864933014, "step": 1238 }, { "epoch": 0.32165109034267914, "grad_norm": 2.2270965576171875, "learning_rate": 4.80171491773761e-06, "loss": 0.38859984278678894, "step": 1239 }, { "epoch": 0.32191069574247144, "grad_norm": 4.63798189163208, "learning_rate": 4.801326426161103e-06, "loss": 0.4436955749988556, "step": 1240 }, { "epoch": 0.32217030114226375, "grad_norm": 4.3915839195251465, "learning_rate": 4.800937571957053e-06, "loss": 0.3685417175292969, "step": 1241 }, { "epoch": 0.32242990654205606, "grad_norm": 5.902676105499268, "learning_rate": 4.800548355194202e-06, "loss": 0.40150386095046997, "step": 1242 }, { "epoch": 0.3226895119418484, "grad_norm": 3.2180895805358887, "learning_rate": 4.800158775941351e-06, "loss": 0.3668874502182007, "step": 1243 }, { "epoch": 0.3229491173416407, "grad_norm": 4.219119548797607, "learning_rate": 4.799768834267372e-06, "loss": 0.3802560865879059, "step": 1244 }, { "epoch": 0.32320872274143303, "grad_norm": 3.042239189147949, "learning_rate": 4.799378530241197e-06, "loss": 0.36789119243621826, "step": 1245 }, { "epoch": 0.32346832814122534, "grad_norm": 5.047704219818115, "learning_rate": 4.7989878639318225e-06, "loss": 0.4148796796798706, "step": 1246 }, { "epoch": 0.32372793354101764, "grad_norm": 4.432123184204102, "learning_rate": 4.798596835408309e-06, "loss": 0.4033219814300537, "step": 1247 }, { "epoch": 0.32398753894080995, "grad_norm": 2.8117783069610596, "learning_rate": 4.79820544473978e-06, "loss": 0.353852778673172, "step": 1248 }, { "epoch": 0.3242471443406023, "grad_norm": 4.234316349029541, "learning_rate": 4.797813691995428e-06, "loss": 0.4051724672317505, "step": 1249 }, { "epoch": 0.3245067497403946, "grad_norm": 4.577305316925049, "learning_rate": 4.7974215772445035e-06, "loss": 0.49979615211486816, "step": 1250 }, { "epoch": 0.3247663551401869, "grad_norm": 2.3394410610198975, "learning_rate": 4.797029100556324e-06, "loss": 0.38848158717155457, "step": 1251 }, { "epoch": 0.32502596053997923, "grad_norm": 3.842571973800659, "learning_rate": 4.796636262000269e-06, "loss": 0.3671519160270691, "step": 1252 }, { "epoch": 0.32528556593977154, "grad_norm": 3.0244579315185547, "learning_rate": 4.796243061645786e-06, "loss": 0.3899475038051605, "step": 1253 }, { "epoch": 0.32554517133956384, "grad_norm": 4.780934810638428, "learning_rate": 4.7958494995623824e-06, "loss": 0.4676362872123718, "step": 1254 }, { "epoch": 0.3258047767393562, "grad_norm": 2.354623794555664, "learning_rate": 4.79545557581963e-06, "loss": 0.38020816445350647, "step": 1255 }, { "epoch": 0.3260643821391485, "grad_norm": 3.9658920764923096, "learning_rate": 4.795061290487168e-06, "loss": 0.4073907136917114, "step": 1256 }, { "epoch": 0.3263239875389408, "grad_norm": 7.202980041503906, "learning_rate": 4.794666643634695e-06, "loss": 0.3562960624694824, "step": 1257 }, { "epoch": 0.3265835929387331, "grad_norm": 4.519219875335693, "learning_rate": 4.794271635331975e-06, "loss": 0.34874439239501953, "step": 1258 }, { "epoch": 0.32684319833852543, "grad_norm": 2.5964887142181396, "learning_rate": 4.793876265648839e-06, "loss": 0.4023156762123108, "step": 1259 }, { "epoch": 0.32710280373831774, "grad_norm": 3.8894665241241455, "learning_rate": 4.793480534655177e-06, "loss": 0.45132777094841003, "step": 1260 }, { "epoch": 0.3273624091381101, "grad_norm": 2.2309446334838867, "learning_rate": 4.793084442420946e-06, "loss": 0.36218416690826416, "step": 1261 }, { "epoch": 0.3276220145379024, "grad_norm": 5.108318328857422, "learning_rate": 4.792687989016166e-06, "loss": 0.4471637010574341, "step": 1262 }, { "epoch": 0.3278816199376947, "grad_norm": 3.543046712875366, "learning_rate": 4.792291174510921e-06, "loss": 0.378878653049469, "step": 1263 }, { "epoch": 0.328141225337487, "grad_norm": 2.2787625789642334, "learning_rate": 4.791893998975359e-06, "loss": 0.35096362233161926, "step": 1264 }, { "epoch": 0.3284008307372793, "grad_norm": 4.851942539215088, "learning_rate": 4.791496462479691e-06, "loss": 0.4131615161895752, "step": 1265 }, { "epoch": 0.32866043613707163, "grad_norm": 5.506999969482422, "learning_rate": 4.791098565094192e-06, "loss": 0.5038992762565613, "step": 1266 }, { "epoch": 0.328920041536864, "grad_norm": 5.480895042419434, "learning_rate": 4.790700306889202e-06, "loss": 0.46284565329551697, "step": 1267 }, { "epoch": 0.3291796469366563, "grad_norm": 6.775750160217285, "learning_rate": 4.790301687935124e-06, "loss": 0.4287629723548889, "step": 1268 }, { "epoch": 0.3294392523364486, "grad_norm": 2.6084632873535156, "learning_rate": 4.789902708302423e-06, "loss": 0.3643956780433655, "step": 1269 }, { "epoch": 0.3296988577362409, "grad_norm": 5.349202632904053, "learning_rate": 4.789503368061632e-06, "loss": 0.472078800201416, "step": 1270 }, { "epoch": 0.3299584631360332, "grad_norm": 5.47688627243042, "learning_rate": 4.789103667283344e-06, "loss": 0.41066956520080566, "step": 1271 }, { "epoch": 0.3302180685358255, "grad_norm": 4.9121503829956055, "learning_rate": 4.788703606038216e-06, "loss": 0.40442419052124023, "step": 1272 }, { "epoch": 0.3304776739356179, "grad_norm": 3.076969623565674, "learning_rate": 4.788303184396971e-06, "loss": 0.4202181398868561, "step": 1273 }, { "epoch": 0.3307372793354102, "grad_norm": 3.0852437019348145, "learning_rate": 4.787902402430395e-06, "loss": 0.3913519084453583, "step": 1274 }, { "epoch": 0.3309968847352025, "grad_norm": 2.777536392211914, "learning_rate": 4.787501260209334e-06, "loss": 0.3924643397331238, "step": 1275 }, { "epoch": 0.3312564901349948, "grad_norm": 4.010172367095947, "learning_rate": 4.7870997578047035e-06, "loss": 0.37224531173706055, "step": 1276 }, { "epoch": 0.3315160955347871, "grad_norm": 5.2934746742248535, "learning_rate": 4.7866978952874795e-06, "loss": 0.42668986320495605, "step": 1277 }, { "epoch": 0.3317757009345794, "grad_norm": 3.638378858566284, "learning_rate": 4.786295672728702e-06, "loss": 0.37634849548339844, "step": 1278 }, { "epoch": 0.3320353063343718, "grad_norm": 3.7913496494293213, "learning_rate": 4.785893090199475e-06, "loss": 0.40522050857543945, "step": 1279 }, { "epoch": 0.3322949117341641, "grad_norm": 3.9789745807647705, "learning_rate": 4.785490147770964e-06, "loss": 0.4130499064922333, "step": 1280 }, { "epoch": 0.3325545171339564, "grad_norm": 3.8654937744140625, "learning_rate": 4.785086845514403e-06, "loss": 0.4392543435096741, "step": 1281 }, { "epoch": 0.3328141225337487, "grad_norm": 4.434556484222412, "learning_rate": 4.784683183501084e-06, "loss": 0.49057623744010925, "step": 1282 }, { "epoch": 0.333073727933541, "grad_norm": 5.466582775115967, "learning_rate": 4.7842791618023666e-06, "loss": 0.4630877375602722, "step": 1283 }, { "epoch": 0.3333333333333333, "grad_norm": 4.6911749839782715, "learning_rate": 4.783874780489673e-06, "loss": 0.3834974765777588, "step": 1284 }, { "epoch": 0.3335929387331256, "grad_norm": 2.3791651725769043, "learning_rate": 4.783470039634486e-06, "loss": 0.42983609437942505, "step": 1285 }, { "epoch": 0.333852544132918, "grad_norm": 5.350069522857666, "learning_rate": 4.783064939308357e-06, "loss": 0.5169476866722107, "step": 1286 }, { "epoch": 0.3341121495327103, "grad_norm": 2.8767788410186768, "learning_rate": 4.782659479582898e-06, "loss": 0.36256143450737, "step": 1287 }, { "epoch": 0.3343717549325026, "grad_norm": 2.40920090675354, "learning_rate": 4.782253660529785e-06, "loss": 0.34863778948783875, "step": 1288 }, { "epoch": 0.3346313603322949, "grad_norm": 4.638552665710449, "learning_rate": 4.781847482220757e-06, "loss": 0.5002865195274353, "step": 1289 }, { "epoch": 0.3348909657320872, "grad_norm": 4.054471015930176, "learning_rate": 4.781440944727617e-06, "loss": 0.42091864347457886, "step": 1290 }, { "epoch": 0.3351505711318795, "grad_norm": 1.9127898216247559, "learning_rate": 4.781034048122232e-06, "loss": 0.3512657880783081, "step": 1291 }, { "epoch": 0.3354101765316719, "grad_norm": 3.112431526184082, "learning_rate": 4.780626792476532e-06, "loss": 0.4782654345035553, "step": 1292 }, { "epoch": 0.3356697819314642, "grad_norm": 5.6733622550964355, "learning_rate": 4.78021917786251e-06, "loss": 0.35993045568466187, "step": 1293 }, { "epoch": 0.3359293873312565, "grad_norm": 2.3762922286987305, "learning_rate": 4.779811204352223e-06, "loss": 0.38956505060195923, "step": 1294 }, { "epoch": 0.3361889927310488, "grad_norm": 2.039839267730713, "learning_rate": 4.779402872017792e-06, "loss": 0.335724800825119, "step": 1295 }, { "epoch": 0.3364485981308411, "grad_norm": 3.080142021179199, "learning_rate": 4.778994180931401e-06, "loss": 0.38729220628738403, "step": 1296 }, { "epoch": 0.3367082035306334, "grad_norm": 3.529047966003418, "learning_rate": 4.778585131165295e-06, "loss": 0.44016414880752563, "step": 1297 }, { "epoch": 0.33696780893042577, "grad_norm": 5.515857696533203, "learning_rate": 4.778175722791788e-06, "loss": 0.264348566532135, "step": 1298 }, { "epoch": 0.3372274143302181, "grad_norm": 2.7280046939849854, "learning_rate": 4.777765955883251e-06, "loss": 0.399355947971344, "step": 1299 }, { "epoch": 0.3374870197300104, "grad_norm": 6.016895771026611, "learning_rate": 4.777355830512122e-06, "loss": 0.540809690952301, "step": 1300 }, { "epoch": 0.3377466251298027, "grad_norm": 5.710633754730225, "learning_rate": 4.776945346750905e-06, "loss": 0.3855063319206238, "step": 1301 }, { "epoch": 0.338006230529595, "grad_norm": 2.5259928703308105, "learning_rate": 4.776534504672159e-06, "loss": 0.3620317578315735, "step": 1302 }, { "epoch": 0.3382658359293873, "grad_norm": 4.5028462409973145, "learning_rate": 4.7761233043485165e-06, "loss": 0.3635250926017761, "step": 1303 }, { "epoch": 0.33852544132917967, "grad_norm": 3.6584720611572266, "learning_rate": 4.7757117458526645e-06, "loss": 0.39182090759277344, "step": 1304 }, { "epoch": 0.338785046728972, "grad_norm": 5.363864421844482, "learning_rate": 4.775299829257358e-06, "loss": 0.4539848566055298, "step": 1305 }, { "epoch": 0.3390446521287643, "grad_norm": 6.479522705078125, "learning_rate": 4.7748875546354155e-06, "loss": 0.5039048194885254, "step": 1306 }, { "epoch": 0.3393042575285566, "grad_norm": 2.4932074546813965, "learning_rate": 4.774474922059718e-06, "loss": 0.3660113215446472, "step": 1307 }, { "epoch": 0.3395638629283489, "grad_norm": 3.315901279449463, "learning_rate": 4.774061931603207e-06, "loss": 0.35473108291625977, "step": 1308 }, { "epoch": 0.3398234683281412, "grad_norm": 1.6852878332138062, "learning_rate": 4.773648583338892e-06, "loss": 0.37655872106552124, "step": 1309 }, { "epoch": 0.34008307372793356, "grad_norm": 1.8215620517730713, "learning_rate": 4.773234877339843e-06, "loss": 0.38200581073760986, "step": 1310 }, { "epoch": 0.34034267912772587, "grad_norm": 1.9248789548873901, "learning_rate": 4.772820813679194e-06, "loss": 0.3833511769771576, "step": 1311 }, { "epoch": 0.3406022845275182, "grad_norm": 3.0497376918792725, "learning_rate": 4.772406392430141e-06, "loss": 0.4564613103866577, "step": 1312 }, { "epoch": 0.3408618899273105, "grad_norm": 3.9933695793151855, "learning_rate": 4.771991613665945e-06, "loss": 0.43841397762298584, "step": 1313 }, { "epoch": 0.3411214953271028, "grad_norm": 2.6727705001831055, "learning_rate": 4.771576477459929e-06, "loss": 0.3675493597984314, "step": 1314 }, { "epoch": 0.3413811007268951, "grad_norm": 2.466693878173828, "learning_rate": 4.77116098388548e-06, "loss": 0.399350106716156, "step": 1315 }, { "epoch": 0.34164070612668745, "grad_norm": 5.687911510467529, "learning_rate": 4.770745133016048e-06, "loss": 0.43281301856040955, "step": 1316 }, { "epoch": 0.34190031152647976, "grad_norm": 3.49582839012146, "learning_rate": 4.770328924925145e-06, "loss": 0.32306599617004395, "step": 1317 }, { "epoch": 0.34215991692627207, "grad_norm": 3.933016061782837, "learning_rate": 4.769912359686346e-06, "loss": 0.395586222410202, "step": 1318 }, { "epoch": 0.3424195223260644, "grad_norm": 2.4106483459472656, "learning_rate": 4.7694954373732935e-06, "loss": 0.36713707447052, "step": 1319 }, { "epoch": 0.3426791277258567, "grad_norm": 3.7252614498138428, "learning_rate": 4.769078158059687e-06, "loss": 0.41179120540618896, "step": 1320 }, { "epoch": 0.342938733125649, "grad_norm": 3.474252223968506, "learning_rate": 4.7686605218192935e-06, "loss": 0.44156384468078613, "step": 1321 }, { "epoch": 0.34319833852544135, "grad_norm": 3.9849905967712402, "learning_rate": 4.768242528725941e-06, "loss": 0.44103914499282837, "step": 1322 }, { "epoch": 0.34345794392523366, "grad_norm": 3.32108736038208, "learning_rate": 4.767824178853521e-06, "loss": 0.37615808844566345, "step": 1323 }, { "epoch": 0.34371754932502596, "grad_norm": 3.654470443725586, "learning_rate": 4.767405472275988e-06, "loss": 0.38174131512641907, "step": 1324 }, { "epoch": 0.34397715472481827, "grad_norm": 2.096447467803955, "learning_rate": 4.76698640906736e-06, "loss": 0.35344815254211426, "step": 1325 }, { "epoch": 0.3442367601246106, "grad_norm": 3.255356550216675, "learning_rate": 4.766566989301718e-06, "loss": 0.4811621606349945, "step": 1326 }, { "epoch": 0.3444963655244029, "grad_norm": 4.579570293426514, "learning_rate": 4.7661472130532056e-06, "loss": 0.43068021535873413, "step": 1327 }, { "epoch": 0.34475597092419524, "grad_norm": 3.2636337280273438, "learning_rate": 4.7657270803960285e-06, "loss": 0.39881962537765503, "step": 1328 }, { "epoch": 0.34501557632398755, "grad_norm": 4.752354621887207, "learning_rate": 4.765306591404459e-06, "loss": 0.4431745409965515, "step": 1329 }, { "epoch": 0.34527518172377986, "grad_norm": 2.0873003005981445, "learning_rate": 4.764885746152828e-06, "loss": 0.33928683400154114, "step": 1330 }, { "epoch": 0.34553478712357216, "grad_norm": 2.355767011642456, "learning_rate": 4.764464544715532e-06, "loss": 0.3888551592826843, "step": 1331 }, { "epoch": 0.34579439252336447, "grad_norm": 4.021733283996582, "learning_rate": 4.764042987167029e-06, "loss": 0.42229339480400085, "step": 1332 }, { "epoch": 0.3460539979231568, "grad_norm": 2.57690691947937, "learning_rate": 4.763621073581842e-06, "loss": 0.3895851969718933, "step": 1333 }, { "epoch": 0.34631360332294914, "grad_norm": 3.667395830154419, "learning_rate": 4.7631988040345554e-06, "loss": 0.37501975893974304, "step": 1334 }, { "epoch": 0.34657320872274144, "grad_norm": 3.5706088542938232, "learning_rate": 4.762776178599815e-06, "loss": 0.35616371035575867, "step": 1335 }, { "epoch": 0.34683281412253375, "grad_norm": 4.296470642089844, "learning_rate": 4.762353197352333e-06, "loss": 0.44964703917503357, "step": 1336 }, { "epoch": 0.34709241952232606, "grad_norm": 3.9419806003570557, "learning_rate": 4.761929860366883e-06, "loss": 0.3913884162902832, "step": 1337 }, { "epoch": 0.34735202492211836, "grad_norm": 2.0837528705596924, "learning_rate": 4.761506167718302e-06, "loss": 0.3283407688140869, "step": 1338 }, { "epoch": 0.34761163032191067, "grad_norm": 2.9477953910827637, "learning_rate": 4.761082119481486e-06, "loss": 0.37797051668167114, "step": 1339 }, { "epoch": 0.34787123572170303, "grad_norm": 6.286281585693359, "learning_rate": 4.7606577157314e-06, "loss": 0.4059382677078247, "step": 1340 }, { "epoch": 0.34813084112149534, "grad_norm": 2.7171342372894287, "learning_rate": 4.760232956543067e-06, "loss": 0.3720853626728058, "step": 1341 }, { "epoch": 0.34839044652128764, "grad_norm": 3.8865175247192383, "learning_rate": 4.759807841991576e-06, "loss": 0.416159451007843, "step": 1342 }, { "epoch": 0.34865005192107995, "grad_norm": 3.6224112510681152, "learning_rate": 4.759382372152077e-06, "loss": 0.4517543315887451, "step": 1343 }, { "epoch": 0.34890965732087226, "grad_norm": 2.555194854736328, "learning_rate": 4.7589565470997836e-06, "loss": 0.38747426867485046, "step": 1344 }, { "epoch": 0.34916926272066456, "grad_norm": 4.285943031311035, "learning_rate": 4.758530366909971e-06, "loss": 0.3432357907295227, "step": 1345 }, { "epoch": 0.3494288681204569, "grad_norm": 4.483672142028809, "learning_rate": 4.758103831657979e-06, "loss": 0.41536498069763184, "step": 1346 }, { "epoch": 0.34968847352024923, "grad_norm": 4.366618633270264, "learning_rate": 4.75767694141921e-06, "loss": 0.47761625051498413, "step": 1347 }, { "epoch": 0.34994807892004154, "grad_norm": 3.987680196762085, "learning_rate": 4.757249696269126e-06, "loss": 0.4404412508010864, "step": 1348 }, { "epoch": 0.35020768431983385, "grad_norm": 7.298227310180664, "learning_rate": 4.756822096283257e-06, "loss": 0.47008079290390015, "step": 1349 }, { "epoch": 0.35046728971962615, "grad_norm": 5.388627529144287, "learning_rate": 4.7563941415371905e-06, "loss": 0.3786904215812683, "step": 1350 }, { "epoch": 0.35072689511941846, "grad_norm": 4.370132923126221, "learning_rate": 4.755965832106581e-06, "loss": 0.494489848613739, "step": 1351 }, { "epoch": 0.3509865005192108, "grad_norm": 4.067026615142822, "learning_rate": 4.755537168067142e-06, "loss": 0.4689337909221649, "step": 1352 }, { "epoch": 0.3512461059190031, "grad_norm": 4.11626672744751, "learning_rate": 4.755108149494653e-06, "loss": 0.3766191005706787, "step": 1353 }, { "epoch": 0.35150571131879543, "grad_norm": 4.544477939605713, "learning_rate": 4.754678776464954e-06, "loss": 0.3962334990501404, "step": 1354 }, { "epoch": 0.35176531671858774, "grad_norm": 4.348957538604736, "learning_rate": 4.754249049053948e-06, "loss": 0.460194855928421, "step": 1355 }, { "epoch": 0.35202492211838005, "grad_norm": 3.5408825874328613, "learning_rate": 4.753818967337602e-06, "loss": 0.41459497809410095, "step": 1356 }, { "epoch": 0.35228452751817235, "grad_norm": 3.2018465995788574, "learning_rate": 4.753388531391943e-06, "loss": 0.4764905571937561, "step": 1357 }, { "epoch": 0.3525441329179647, "grad_norm": 5.132068157196045, "learning_rate": 4.752957741293064e-06, "loss": 0.40732628107070923, "step": 1358 }, { "epoch": 0.352803738317757, "grad_norm": 4.833654403686523, "learning_rate": 4.752526597117117e-06, "loss": 0.39677396416664124, "step": 1359 }, { "epoch": 0.3530633437175493, "grad_norm": 5.96586799621582, "learning_rate": 4.7520950989403205e-06, "loss": 0.44156646728515625, "step": 1360 }, { "epoch": 0.35332294911734163, "grad_norm": 3.6802406311035156, "learning_rate": 4.751663246838953e-06, "loss": 0.4094155430793762, "step": 1361 }, { "epoch": 0.35358255451713394, "grad_norm": 2.9214422702789307, "learning_rate": 4.751231040889354e-06, "loss": 0.36633750796318054, "step": 1362 }, { "epoch": 0.35384215991692625, "grad_norm": 8.139360427856445, "learning_rate": 4.7507984811679296e-06, "loss": 0.4817655086517334, "step": 1363 }, { "epoch": 0.3541017653167186, "grad_norm": 5.7356181144714355, "learning_rate": 4.750365567751146e-06, "loss": 0.4681951701641083, "step": 1364 }, { "epoch": 0.3543613707165109, "grad_norm": 9.341513633728027, "learning_rate": 4.749932300715532e-06, "loss": 0.34770479798316956, "step": 1365 }, { "epoch": 0.3546209761163032, "grad_norm": 4.88552713394165, "learning_rate": 4.74949868013768e-06, "loss": 0.3863942623138428, "step": 1366 }, { "epoch": 0.35488058151609553, "grad_norm": 1.9279803037643433, "learning_rate": 4.749064706094244e-06, "loss": 0.4077291488647461, "step": 1367 }, { "epoch": 0.35514018691588783, "grad_norm": 3.1729037761688232, "learning_rate": 4.74863037866194e-06, "loss": 0.34227314591407776, "step": 1368 }, { "epoch": 0.35539979231568014, "grad_norm": 7.818133354187012, "learning_rate": 4.748195697917547e-06, "loss": 0.453605979681015, "step": 1369 }, { "epoch": 0.3556593977154725, "grad_norm": 8.4013671875, "learning_rate": 4.747760663937908e-06, "loss": 0.44381654262542725, "step": 1370 }, { "epoch": 0.3559190031152648, "grad_norm": 3.007920503616333, "learning_rate": 4.747325276799927e-06, "loss": 0.35992902517318726, "step": 1371 }, { "epoch": 0.3561786085150571, "grad_norm": 5.562985897064209, "learning_rate": 4.746889536580569e-06, "loss": 0.4638137221336365, "step": 1372 }, { "epoch": 0.3564382139148494, "grad_norm": 4.366399765014648, "learning_rate": 4.7464534433568634e-06, "loss": 0.4047280550003052, "step": 1373 }, { "epoch": 0.35669781931464173, "grad_norm": 3.1144044399261475, "learning_rate": 4.7460169972059015e-06, "loss": 0.3550316393375397, "step": 1374 }, { "epoch": 0.35695742471443404, "grad_norm": 7.510344505310059, "learning_rate": 4.7455801982048374e-06, "loss": 0.37526291608810425, "step": 1375 }, { "epoch": 0.3572170301142264, "grad_norm": 2.211824655532837, "learning_rate": 4.7451430464308875e-06, "loss": 0.3402249813079834, "step": 1376 }, { "epoch": 0.3574766355140187, "grad_norm": 4.064290523529053, "learning_rate": 4.74470554196133e-06, "loss": 0.434225857257843, "step": 1377 }, { "epoch": 0.357736240913811, "grad_norm": 4.95591926574707, "learning_rate": 4.744267684873505e-06, "loss": 0.39415520429611206, "step": 1378 }, { "epoch": 0.3579958463136033, "grad_norm": 4.249912261962891, "learning_rate": 4.743829475244816e-06, "loss": 0.3389168381690979, "step": 1379 }, { "epoch": 0.3582554517133956, "grad_norm": 4.749418258666992, "learning_rate": 4.743390913152728e-06, "loss": 0.37502241134643555, "step": 1380 }, { "epoch": 0.35851505711318793, "grad_norm": 3.795386552810669, "learning_rate": 4.74295199867477e-06, "loss": 0.41863375902175903, "step": 1381 }, { "epoch": 0.3587746625129803, "grad_norm": 4.515524864196777, "learning_rate": 4.74251273188853e-06, "loss": 0.4126255512237549, "step": 1382 }, { "epoch": 0.3590342679127726, "grad_norm": 3.2548673152923584, "learning_rate": 4.742073112871663e-06, "loss": 0.3821163773536682, "step": 1383 }, { "epoch": 0.3592938733125649, "grad_norm": 3.786578416824341, "learning_rate": 4.741633141701881e-06, "loss": 0.4547896683216095, "step": 1384 }, { "epoch": 0.3595534787123572, "grad_norm": 3.0654025077819824, "learning_rate": 4.741192818456961e-06, "loss": 0.3486422002315521, "step": 1385 }, { "epoch": 0.3598130841121495, "grad_norm": 5.927062034606934, "learning_rate": 4.740752143214744e-06, "loss": 0.42500990629196167, "step": 1386 }, { "epoch": 0.3600726895119418, "grad_norm": 3.729851007461548, "learning_rate": 4.74031111605313e-06, "loss": 0.4283513128757477, "step": 1387 }, { "epoch": 0.3603322949117342, "grad_norm": 2.4876832962036133, "learning_rate": 4.739869737050084e-06, "loss": 0.3694216310977936, "step": 1388 }, { "epoch": 0.3605919003115265, "grad_norm": 3.3080365657806396, "learning_rate": 4.73942800628363e-06, "loss": 0.39478325843811035, "step": 1389 }, { "epoch": 0.3608515057113188, "grad_norm": 2.3578908443450928, "learning_rate": 4.7389859238318555e-06, "loss": 0.39082735776901245, "step": 1390 }, { "epoch": 0.3611111111111111, "grad_norm": 3.1622490882873535, "learning_rate": 4.738543489772912e-06, "loss": 0.47691577672958374, "step": 1391 }, { "epoch": 0.3613707165109034, "grad_norm": 4.166231155395508, "learning_rate": 4.738100704185011e-06, "loss": 0.4053437411785126, "step": 1392 }, { "epoch": 0.3616303219106957, "grad_norm": 3.2942380905151367, "learning_rate": 4.737657567146427e-06, "loss": 0.3908432126045227, "step": 1393 }, { "epoch": 0.3618899273104881, "grad_norm": 3.9852755069732666, "learning_rate": 4.737214078735496e-06, "loss": 0.40932220220565796, "step": 1394 }, { "epoch": 0.3621495327102804, "grad_norm": 5.771198272705078, "learning_rate": 4.736770239030618e-06, "loss": 0.39308464527130127, "step": 1395 }, { "epoch": 0.3624091381100727, "grad_norm": 3.5019967555999756, "learning_rate": 4.736326048110252e-06, "loss": 0.43020927906036377, "step": 1396 }, { "epoch": 0.362668743509865, "grad_norm": 3.514686346054077, "learning_rate": 4.735881506052922e-06, "loss": 0.46977537870407104, "step": 1397 }, { "epoch": 0.3629283489096573, "grad_norm": 3.0130860805511475, "learning_rate": 4.735436612937211e-06, "loss": 0.352207213640213, "step": 1398 }, { "epoch": 0.3631879543094496, "grad_norm": 3.5510852336883545, "learning_rate": 4.734991368841769e-06, "loss": 0.36544471979141235, "step": 1399 }, { "epoch": 0.363447559709242, "grad_norm": 3.984633207321167, "learning_rate": 4.7345457738453025e-06, "loss": 0.36405685544013977, "step": 1400 }, { "epoch": 0.3637071651090343, "grad_norm": 3.6012725830078125, "learning_rate": 4.734099828026584e-06, "loss": 0.396024614572525, "step": 1401 }, { "epoch": 0.3639667705088266, "grad_norm": 2.9141743183135986, "learning_rate": 4.733653531464445e-06, "loss": 0.38850289583206177, "step": 1402 }, { "epoch": 0.3642263759086189, "grad_norm": 2.888806104660034, "learning_rate": 4.7332068842377815e-06, "loss": 0.3760795593261719, "step": 1403 }, { "epoch": 0.3644859813084112, "grad_norm": 2.9326024055480957, "learning_rate": 4.73275988642555e-06, "loss": 0.4238851070404053, "step": 1404 }, { "epoch": 0.3647455867082035, "grad_norm": 3.5291600227355957, "learning_rate": 4.73231253810677e-06, "loss": 0.3498382568359375, "step": 1405 }, { "epoch": 0.36500519210799587, "grad_norm": 4.858536243438721, "learning_rate": 4.731864839360523e-06, "loss": 0.418373703956604, "step": 1406 }, { "epoch": 0.3652647975077882, "grad_norm": 2.5172882080078125, "learning_rate": 4.73141679026595e-06, "loss": 0.34902647137641907, "step": 1407 }, { "epoch": 0.3655244029075805, "grad_norm": 4.017538070678711, "learning_rate": 4.730968390902257e-06, "loss": 0.45370620489120483, "step": 1408 }, { "epoch": 0.3657840083073728, "grad_norm": 4.392424583435059, "learning_rate": 4.730519641348711e-06, "loss": 0.4809487462043762, "step": 1409 }, { "epoch": 0.3660436137071651, "grad_norm": 3.965660572052002, "learning_rate": 4.73007054168464e-06, "loss": 0.3882036805152893, "step": 1410 }, { "epoch": 0.3663032191069574, "grad_norm": 2.497495412826538, "learning_rate": 4.729621091989434e-06, "loss": 0.35070672631263733, "step": 1411 }, { "epoch": 0.36656282450674976, "grad_norm": 4.439149379730225, "learning_rate": 4.729171292342549e-06, "loss": 0.38203126192092896, "step": 1412 }, { "epoch": 0.36682242990654207, "grad_norm": 1.979597568511963, "learning_rate": 4.728721142823495e-06, "loss": 0.3547241687774658, "step": 1413 }, { "epoch": 0.3670820353063344, "grad_norm": 6.444791793823242, "learning_rate": 4.728270643511849e-06, "loss": 0.4311678409576416, "step": 1414 }, { "epoch": 0.3673416407061267, "grad_norm": 2.2752294540405273, "learning_rate": 4.72781979448725e-06, "loss": 0.35251790285110474, "step": 1415 }, { "epoch": 0.367601246105919, "grad_norm": 4.025384902954102, "learning_rate": 4.727368595829397e-06, "loss": 0.3727911114692688, "step": 1416 }, { "epoch": 0.3678608515057113, "grad_norm": 4.726309299468994, "learning_rate": 4.726917047618053e-06, "loss": 0.4002739191055298, "step": 1417 }, { "epoch": 0.36812045690550366, "grad_norm": 4.147716522216797, "learning_rate": 4.72646514993304e-06, "loss": 0.3451520800590515, "step": 1418 }, { "epoch": 0.36838006230529596, "grad_norm": 2.9126663208007812, "learning_rate": 4.726012902854243e-06, "loss": 0.4124170243740082, "step": 1419 }, { "epoch": 0.36863966770508827, "grad_norm": 4.114672660827637, "learning_rate": 4.72556030646161e-06, "loss": 0.39023151993751526, "step": 1420 }, { "epoch": 0.3688992731048806, "grad_norm": 4.835273742675781, "learning_rate": 4.7251073608351485e-06, "loss": 0.3915468454360962, "step": 1421 }, { "epoch": 0.3691588785046729, "grad_norm": 4.107539653778076, "learning_rate": 4.724654066054931e-06, "loss": 0.3549227714538574, "step": 1422 }, { "epoch": 0.3694184839044652, "grad_norm": 4.9640913009643555, "learning_rate": 4.724200422201087e-06, "loss": 0.44426679611206055, "step": 1423 }, { "epoch": 0.36967808930425755, "grad_norm": 3.4348998069763184, "learning_rate": 4.7237464293538115e-06, "loss": 0.38215547800064087, "step": 1424 }, { "epoch": 0.36993769470404986, "grad_norm": 3.606444835662842, "learning_rate": 4.72329208759336e-06, "loss": 0.44304269552230835, "step": 1425 }, { "epoch": 0.37019730010384216, "grad_norm": 3.0978844165802, "learning_rate": 4.722837397000052e-06, "loss": 0.31680935621261597, "step": 1426 }, { "epoch": 0.37045690550363447, "grad_norm": 3.939771890640259, "learning_rate": 4.722382357654262e-06, "loss": 0.360105037689209, "step": 1427 }, { "epoch": 0.3707165109034268, "grad_norm": 7.46388053894043, "learning_rate": 4.721926969636433e-06, "loss": 0.4809294641017914, "step": 1428 }, { "epoch": 0.3709761163032191, "grad_norm": 3.635774850845337, "learning_rate": 4.721471233027067e-06, "loss": 0.43664807081222534, "step": 1429 }, { "epoch": 0.37123572170301145, "grad_norm": 5.525679111480713, "learning_rate": 4.721015147906727e-06, "loss": 0.3682493567466736, "step": 1430 }, { "epoch": 0.37149532710280375, "grad_norm": 6.047026634216309, "learning_rate": 4.720558714356041e-06, "loss": 0.4257262051105499, "step": 1431 }, { "epoch": 0.37175493250259606, "grad_norm": 3.342740535736084, "learning_rate": 4.720101932455693e-06, "loss": 0.38220325112342834, "step": 1432 }, { "epoch": 0.37201453790238836, "grad_norm": 4.436036109924316, "learning_rate": 4.719644802286433e-06, "loss": 0.48224443197250366, "step": 1433 }, { "epoch": 0.37227414330218067, "grad_norm": 9.427227020263672, "learning_rate": 4.71918732392907e-06, "loss": 0.4275139570236206, "step": 1434 }, { "epoch": 0.372533748701973, "grad_norm": 2.5349535942077637, "learning_rate": 4.718729497464477e-06, "loss": 0.3580266833305359, "step": 1435 }, { "epoch": 0.37279335410176534, "grad_norm": 4.2209858894348145, "learning_rate": 4.7182713229735874e-06, "loss": 0.36336567997932434, "step": 1436 }, { "epoch": 0.37305295950155765, "grad_norm": 5.509407043457031, "learning_rate": 4.717812800537394e-06, "loss": 0.4698270261287689, "step": 1437 }, { "epoch": 0.37331256490134995, "grad_norm": 2.9804975986480713, "learning_rate": 4.717353930236956e-06, "loss": 0.388139009475708, "step": 1438 }, { "epoch": 0.37357217030114226, "grad_norm": 4.61360502243042, "learning_rate": 4.716894712153388e-06, "loss": 0.5549395680427551, "step": 1439 }, { "epoch": 0.37383177570093457, "grad_norm": 5.10478401184082, "learning_rate": 4.716435146367872e-06, "loss": 0.40614053606987, "step": 1440 }, { "epoch": 0.37409138110072687, "grad_norm": 4.582294940948486, "learning_rate": 4.715975232961647e-06, "loss": 0.432392954826355, "step": 1441 }, { "epoch": 0.37435098650051923, "grad_norm": 3.2197794914245605, "learning_rate": 4.715514972016016e-06, "loss": 0.39973506331443787, "step": 1442 }, { "epoch": 0.37461059190031154, "grad_norm": 4.321081161499023, "learning_rate": 4.715054363612343e-06, "loss": 0.4133186936378479, "step": 1443 }, { "epoch": 0.37487019730010385, "grad_norm": 4.441989898681641, "learning_rate": 4.714593407832051e-06, "loss": 0.381430983543396, "step": 1444 }, { "epoch": 0.37512980269989615, "grad_norm": 5.909933567047119, "learning_rate": 4.714132104756628e-06, "loss": 0.39956527948379517, "step": 1445 }, { "epoch": 0.37538940809968846, "grad_norm": 4.015504837036133, "learning_rate": 4.7136704544676215e-06, "loss": 0.43842813372612, "step": 1446 }, { "epoch": 0.37564901349948077, "grad_norm": 2.676190137863159, "learning_rate": 4.713208457046641e-06, "loss": 0.35976797342300415, "step": 1447 }, { "epoch": 0.37590861889927313, "grad_norm": 4.544256687164307, "learning_rate": 4.7127461125753575e-06, "loss": 0.48867860436439514, "step": 1448 }, { "epoch": 0.37616822429906543, "grad_norm": 3.469456434249878, "learning_rate": 4.7122834211355e-06, "loss": 0.3321196436882019, "step": 1449 }, { "epoch": 0.37642782969885774, "grad_norm": 3.8243002891540527, "learning_rate": 4.711820382808866e-06, "loss": 0.41923069953918457, "step": 1450 }, { "epoch": 0.37668743509865005, "grad_norm": 5.575591564178467, "learning_rate": 4.711356997677308e-06, "loss": 0.3859349489212036, "step": 1451 }, { "epoch": 0.37694704049844235, "grad_norm": 3.859673023223877, "learning_rate": 4.710893265822741e-06, "loss": 0.3011387884616852, "step": 1452 }, { "epoch": 0.37720664589823466, "grad_norm": 3.1670846939086914, "learning_rate": 4.710429187327144e-06, "loss": 0.39642179012298584, "step": 1453 }, { "epoch": 0.377466251298027, "grad_norm": 2.9749674797058105, "learning_rate": 4.709964762272554e-06, "loss": 0.3590899407863617, "step": 1454 }, { "epoch": 0.37772585669781933, "grad_norm": 1.7648898363113403, "learning_rate": 4.709499990741071e-06, "loss": 0.3677175045013428, "step": 1455 }, { "epoch": 0.37798546209761164, "grad_norm": 2.137247323989868, "learning_rate": 4.709034872814856e-06, "loss": 0.3212984800338745, "step": 1456 }, { "epoch": 0.37824506749740394, "grad_norm": 5.217474460601807, "learning_rate": 4.708569408576133e-06, "loss": 0.43970221281051636, "step": 1457 }, { "epoch": 0.37850467289719625, "grad_norm": 2.582577705383301, "learning_rate": 4.708103598107182e-06, "loss": 0.33408987522125244, "step": 1458 }, { "epoch": 0.37876427829698855, "grad_norm": 2.99214506149292, "learning_rate": 4.707637441490351e-06, "loss": 0.34589675068855286, "step": 1459 }, { "epoch": 0.3790238836967809, "grad_norm": 9.17647933959961, "learning_rate": 4.707170938808044e-06, "loss": 0.42991411685943604, "step": 1460 }, { "epoch": 0.3792834890965732, "grad_norm": 2.60446834564209, "learning_rate": 4.706704090142728e-06, "loss": 0.3147900700569153, "step": 1461 }, { "epoch": 0.37954309449636553, "grad_norm": 4.32444953918457, "learning_rate": 4.706236895576931e-06, "loss": 0.3738819658756256, "step": 1462 }, { "epoch": 0.37980269989615784, "grad_norm": 3.899545907974243, "learning_rate": 4.705769355193244e-06, "loss": 0.34018734097480774, "step": 1463 }, { "epoch": 0.38006230529595014, "grad_norm": 3.9479362964630127, "learning_rate": 4.705301469074314e-06, "loss": 0.4143322706222534, "step": 1464 }, { "epoch": 0.38032191069574245, "grad_norm": 2.693131446838379, "learning_rate": 4.704833237302857e-06, "loss": 0.3460250496864319, "step": 1465 }, { "epoch": 0.3805815160955348, "grad_norm": 4.598479270935059, "learning_rate": 4.7043646599616425e-06, "loss": 0.34757840633392334, "step": 1466 }, { "epoch": 0.3808411214953271, "grad_norm": 5.219520092010498, "learning_rate": 4.703895737133505e-06, "loss": 0.46826422214508057, "step": 1467 }, { "epoch": 0.3811007268951194, "grad_norm": 6.547023296356201, "learning_rate": 4.703426468901339e-06, "loss": 0.49613797664642334, "step": 1468 }, { "epoch": 0.38136033229491173, "grad_norm": 3.307853937149048, "learning_rate": 4.702956855348102e-06, "loss": 0.3824428915977478, "step": 1469 }, { "epoch": 0.38161993769470404, "grad_norm": 2.3526384830474854, "learning_rate": 4.702486896556809e-06, "loss": 0.3970467448234558, "step": 1470 }, { "epoch": 0.38187954309449634, "grad_norm": 10.44308090209961, "learning_rate": 4.702016592610539e-06, "loss": 0.46182751655578613, "step": 1471 }, { "epoch": 0.3821391484942887, "grad_norm": 4.383131980895996, "learning_rate": 4.70154594359243e-06, "loss": 0.4407491683959961, "step": 1472 }, { "epoch": 0.382398753894081, "grad_norm": 3.8901333808898926, "learning_rate": 4.701074949585684e-06, "loss": 0.4296635389328003, "step": 1473 }, { "epoch": 0.3826583592938733, "grad_norm": 2.5160810947418213, "learning_rate": 4.7006036106735594e-06, "loss": 0.3614394962787628, "step": 1474 }, { "epoch": 0.3829179646936656, "grad_norm": 2.315394639968872, "learning_rate": 4.700131926939379e-06, "loss": 0.38500019907951355, "step": 1475 }, { "epoch": 0.38317757009345793, "grad_norm": 4.1154961585998535, "learning_rate": 4.699659898466527e-06, "loss": 0.4553595781326294, "step": 1476 }, { "epoch": 0.38343717549325024, "grad_norm": 4.313496112823486, "learning_rate": 4.699187525338447e-06, "loss": 0.42193764448165894, "step": 1477 }, { "epoch": 0.3836967808930426, "grad_norm": 3.837676763534546, "learning_rate": 4.698714807638641e-06, "loss": 0.45107051730155945, "step": 1478 }, { "epoch": 0.3839563862928349, "grad_norm": 4.6680908203125, "learning_rate": 4.698241745450678e-06, "loss": 0.43125906586647034, "step": 1479 }, { "epoch": 0.3842159916926272, "grad_norm": 2.786180257797241, "learning_rate": 4.697768338858183e-06, "loss": 0.35294365882873535, "step": 1480 }, { "epoch": 0.3844755970924195, "grad_norm": 4.10017204284668, "learning_rate": 4.697294587944844e-06, "loss": 0.45090076327323914, "step": 1481 }, { "epoch": 0.3847352024922118, "grad_norm": 7.841177940368652, "learning_rate": 4.696820492794408e-06, "loss": 0.3948715925216675, "step": 1482 }, { "epoch": 0.38499480789200413, "grad_norm": 3.7920475006103516, "learning_rate": 4.6963460534906865e-06, "loss": 0.38989323377609253, "step": 1483 }, { "epoch": 0.3852544132917965, "grad_norm": 2.870866298675537, "learning_rate": 4.6958712701175465e-06, "loss": 0.3446637988090515, "step": 1484 }, { "epoch": 0.3855140186915888, "grad_norm": 2.452836275100708, "learning_rate": 4.695396142758922e-06, "loss": 0.38346412777900696, "step": 1485 }, { "epoch": 0.3857736240913811, "grad_norm": 5.149421691894531, "learning_rate": 4.694920671498802e-06, "loss": 0.40095609426498413, "step": 1486 }, { "epoch": 0.3860332294911734, "grad_norm": 4.102245330810547, "learning_rate": 4.694444856421242e-06, "loss": 0.3996424078941345, "step": 1487 }, { "epoch": 0.3862928348909657, "grad_norm": 6.007829666137695, "learning_rate": 4.693968697610351e-06, "loss": 0.4535024166107178, "step": 1488 }, { "epoch": 0.386552440290758, "grad_norm": 4.917811393737793, "learning_rate": 4.693492195150306e-06, "loss": 0.44027602672576904, "step": 1489 }, { "epoch": 0.3868120456905504, "grad_norm": 4.765031337738037, "learning_rate": 4.693015349125341e-06, "loss": 0.38902512192726135, "step": 1490 }, { "epoch": 0.3870716510903427, "grad_norm": 4.8672990798950195, "learning_rate": 4.692538159619751e-06, "loss": 0.4377110004425049, "step": 1491 }, { "epoch": 0.387331256490135, "grad_norm": 4.31627082824707, "learning_rate": 4.692060626717894e-06, "loss": 0.3599108159542084, "step": 1492 }, { "epoch": 0.3875908618899273, "grad_norm": 6.639204025268555, "learning_rate": 4.691582750504184e-06, "loss": 0.3933001756668091, "step": 1493 }, { "epoch": 0.3878504672897196, "grad_norm": 4.0181565284729, "learning_rate": 4.691104531063101e-06, "loss": 0.43919169902801514, "step": 1494 }, { "epoch": 0.3881100726895119, "grad_norm": 2.346186876296997, "learning_rate": 4.6906259684791816e-06, "loss": 0.3554019331932068, "step": 1495 }, { "epoch": 0.3883696780893043, "grad_norm": 2.5610671043395996, "learning_rate": 4.690147062837026e-06, "loss": 0.3677952289581299, "step": 1496 }, { "epoch": 0.3886292834890966, "grad_norm": 4.197483539581299, "learning_rate": 4.689667814221293e-06, "loss": 0.35812050104141235, "step": 1497 }, { "epoch": 0.3888888888888889, "grad_norm": 3.247546911239624, "learning_rate": 4.689188222716703e-06, "loss": 0.39072465896606445, "step": 1498 }, { "epoch": 0.3891484942886812, "grad_norm": 4.379914283752441, "learning_rate": 4.688708288408036e-06, "loss": 0.4460890293121338, "step": 1499 }, { "epoch": 0.3894080996884735, "grad_norm": 3.556874990463257, "learning_rate": 4.688228011380135e-06, "loss": 0.3886861205101013, "step": 1500 }, { "epoch": 0.3896677050882658, "grad_norm": 3.1860241889953613, "learning_rate": 4.687747391717901e-06, "loss": 0.3836607336997986, "step": 1501 }, { "epoch": 0.3899273104880582, "grad_norm": 2.4326415061950684, "learning_rate": 4.687266429506296e-06, "loss": 0.3908586800098419, "step": 1502 }, { "epoch": 0.3901869158878505, "grad_norm": 5.033703327178955, "learning_rate": 4.686785124830345e-06, "loss": 0.3519851267337799, "step": 1503 }, { "epoch": 0.3904465212876428, "grad_norm": 3.589630365371704, "learning_rate": 4.686303477775129e-06, "loss": 0.39320096373558044, "step": 1504 }, { "epoch": 0.3907061266874351, "grad_norm": 3.212836265563965, "learning_rate": 4.685821488425795e-06, "loss": 0.35629191994667053, "step": 1505 }, { "epoch": 0.3909657320872274, "grad_norm": 2.83241868019104, "learning_rate": 4.6853391568675456e-06, "loss": 0.3353641629219055, "step": 1506 }, { "epoch": 0.3912253374870197, "grad_norm": 2.1123735904693604, "learning_rate": 4.684856483185647e-06, "loss": 0.34912949800491333, "step": 1507 }, { "epoch": 0.39148494288681207, "grad_norm": 6.420948028564453, "learning_rate": 4.684373467465424e-06, "loss": 0.3805067241191864, "step": 1508 }, { "epoch": 0.3917445482866044, "grad_norm": 6.211874485015869, "learning_rate": 4.683890109792264e-06, "loss": 0.4783437252044678, "step": 1509 }, { "epoch": 0.3920041536863967, "grad_norm": 5.095607280731201, "learning_rate": 4.683406410251612e-06, "loss": 0.42917531728744507, "step": 1510 }, { "epoch": 0.392263759086189, "grad_norm": 2.867985725402832, "learning_rate": 4.682922368928977e-06, "loss": 0.3364398777484894, "step": 1511 }, { "epoch": 0.3925233644859813, "grad_norm": 3.029184341430664, "learning_rate": 4.682437985909924e-06, "loss": 0.3880491256713867, "step": 1512 }, { "epoch": 0.3927829698857736, "grad_norm": 4.437070369720459, "learning_rate": 4.6819532612800824e-06, "loss": 0.41218504309654236, "step": 1513 }, { "epoch": 0.39304257528556596, "grad_norm": 9.650598526000977, "learning_rate": 4.68146819512514e-06, "loss": 0.4854261875152588, "step": 1514 }, { "epoch": 0.39330218068535827, "grad_norm": 4.164815902709961, "learning_rate": 4.680982787530845e-06, "loss": 0.4384273290634155, "step": 1515 }, { "epoch": 0.3935617860851506, "grad_norm": 4.6420369148254395, "learning_rate": 4.680497038583008e-06, "loss": 0.42645615339279175, "step": 1516 }, { "epoch": 0.3938213914849429, "grad_norm": 3.685027837753296, "learning_rate": 4.680010948367496e-06, "loss": 0.3418661057949066, "step": 1517 }, { "epoch": 0.3940809968847352, "grad_norm": 2.7567176818847656, "learning_rate": 4.67952451697024e-06, "loss": 0.3655220568180084, "step": 1518 }, { "epoch": 0.3943406022845275, "grad_norm": 3.3259634971618652, "learning_rate": 4.67903774447723e-06, "loss": 0.40568873286247253, "step": 1519 }, { "epoch": 0.39460020768431986, "grad_norm": 4.565835952758789, "learning_rate": 4.678550630974515e-06, "loss": 0.5038427710533142, "step": 1520 }, { "epoch": 0.39485981308411217, "grad_norm": 2.4621095657348633, "learning_rate": 4.678063176548209e-06, "loss": 0.346853643655777, "step": 1521 }, { "epoch": 0.39511941848390447, "grad_norm": 2.4309306144714355, "learning_rate": 4.677575381284478e-06, "loss": 0.3610972762107849, "step": 1522 }, { "epoch": 0.3953790238836968, "grad_norm": 5.016209125518799, "learning_rate": 4.6770872452695546e-06, "loss": 0.3655818700790405, "step": 1523 }, { "epoch": 0.3956386292834891, "grad_norm": 4.008982181549072, "learning_rate": 4.6765987685897315e-06, "loss": 0.41599491238594055, "step": 1524 }, { "epoch": 0.3958982346832814, "grad_norm": 7.122842788696289, "learning_rate": 4.6761099513313595e-06, "loss": 0.4202829897403717, "step": 1525 }, { "epoch": 0.39615784008307375, "grad_norm": 5.074874401092529, "learning_rate": 4.67562079358085e-06, "loss": 0.45819541811943054, "step": 1526 }, { "epoch": 0.39641744548286606, "grad_norm": 3.930389642715454, "learning_rate": 4.675131295424675e-06, "loss": 0.37963777780532837, "step": 1527 }, { "epoch": 0.39667705088265837, "grad_norm": 6.071735382080078, "learning_rate": 4.674641456949368e-06, "loss": 0.3810020685195923, "step": 1528 }, { "epoch": 0.3969366562824507, "grad_norm": 4.396778106689453, "learning_rate": 4.674151278241518e-06, "loss": 0.4037214517593384, "step": 1529 }, { "epoch": 0.397196261682243, "grad_norm": 3.682483673095703, "learning_rate": 4.673660759387779e-06, "loss": 0.3990003764629364, "step": 1530 }, { "epoch": 0.3974558670820353, "grad_norm": 4.080988883972168, "learning_rate": 4.673169900474865e-06, "loss": 0.3548598885536194, "step": 1531 }, { "epoch": 0.39771547248182765, "grad_norm": 3.1288583278656006, "learning_rate": 4.672678701589547e-06, "loss": 0.3706014156341553, "step": 1532 }, { "epoch": 0.39797507788161995, "grad_norm": 4.712080955505371, "learning_rate": 4.672187162818658e-06, "loss": 0.32469815015792847, "step": 1533 }, { "epoch": 0.39823468328141226, "grad_norm": 5.372155666351318, "learning_rate": 4.671695284249091e-06, "loss": 0.308037668466568, "step": 1534 }, { "epoch": 0.39849428868120457, "grad_norm": 3.5733654499053955, "learning_rate": 4.671203065967799e-06, "loss": 0.32717210054397583, "step": 1535 }, { "epoch": 0.3987538940809969, "grad_norm": 4.315695762634277, "learning_rate": 4.670710508061794e-06, "loss": 0.4066142439842224, "step": 1536 }, { "epoch": 0.3990134994807892, "grad_norm": 4.187397003173828, "learning_rate": 4.67021761061815e-06, "loss": 0.38229602575302124, "step": 1537 }, { "epoch": 0.39927310488058154, "grad_norm": 5.64918327331543, "learning_rate": 4.669724373724e-06, "loss": 0.4279597997665405, "step": 1538 }, { "epoch": 0.39953271028037385, "grad_norm": 4.220304489135742, "learning_rate": 4.6692307974665355e-06, "loss": 0.43028366565704346, "step": 1539 }, { "epoch": 0.39979231568016615, "grad_norm": 2.9362688064575195, "learning_rate": 4.668736881933012e-06, "loss": 0.3671444058418274, "step": 1540 }, { "epoch": 0.40005192107995846, "grad_norm": 5.003760814666748, "learning_rate": 4.66824262721074e-06, "loss": 0.37233811616897583, "step": 1541 }, { "epoch": 0.40031152647975077, "grad_norm": 4.647136211395264, "learning_rate": 4.6677480333870935e-06, "loss": 0.3342827558517456, "step": 1542 }, { "epoch": 0.4005711318795431, "grad_norm": 3.2683751583099365, "learning_rate": 4.667253100549506e-06, "loss": 0.3973211646080017, "step": 1543 }, { "epoch": 0.40083073727933544, "grad_norm": 2.5042884349823, "learning_rate": 4.666757828785469e-06, "loss": 0.38986051082611084, "step": 1544 }, { "epoch": 0.40109034267912774, "grad_norm": 2.071046829223633, "learning_rate": 4.666262218182535e-06, "loss": 0.39476025104522705, "step": 1545 }, { "epoch": 0.40134994807892005, "grad_norm": 1.719772458076477, "learning_rate": 4.665766268828319e-06, "loss": 0.36153411865234375, "step": 1546 }, { "epoch": 0.40160955347871236, "grad_norm": 3.6209354400634766, "learning_rate": 4.66526998081049e-06, "loss": 0.36774492263793945, "step": 1547 }, { "epoch": 0.40186915887850466, "grad_norm": 1.6512483358383179, "learning_rate": 4.664773354216785e-06, "loss": 0.36284953355789185, "step": 1548 }, { "epoch": 0.40212876427829697, "grad_norm": 4.103269100189209, "learning_rate": 4.664276389134991e-06, "loss": 0.35321810841560364, "step": 1549 }, { "epoch": 0.40238836967808933, "grad_norm": 3.824626922607422, "learning_rate": 4.663779085652964e-06, "loss": 0.41107845306396484, "step": 1550 }, { "epoch": 0.40264797507788164, "grad_norm": 4.473726749420166, "learning_rate": 4.663281443858614e-06, "loss": 0.3773525357246399, "step": 1551 }, { "epoch": 0.40290758047767394, "grad_norm": 3.5404064655303955, "learning_rate": 4.662783463839913e-06, "loss": 0.3497470021247864, "step": 1552 }, { "epoch": 0.40316718587746625, "grad_norm": 4.432277679443359, "learning_rate": 4.662285145684892e-06, "loss": 0.3971443176269531, "step": 1553 }, { "epoch": 0.40342679127725856, "grad_norm": 5.636023998260498, "learning_rate": 4.661786489481644e-06, "loss": 0.48940783739089966, "step": 1554 }, { "epoch": 0.40368639667705086, "grad_norm": 6.763867378234863, "learning_rate": 4.661287495318317e-06, "loss": 0.4086625277996063, "step": 1555 }, { "epoch": 0.4039460020768432, "grad_norm": 6.685881614685059, "learning_rate": 4.660788163283125e-06, "loss": 0.5312143564224243, "step": 1556 }, { "epoch": 0.40420560747663553, "grad_norm": 4.907653331756592, "learning_rate": 4.6602884934643364e-06, "loss": 0.4514213800430298, "step": 1557 }, { "epoch": 0.40446521287642784, "grad_norm": 4.3430023193359375, "learning_rate": 4.659788485950282e-06, "loss": 0.42935067415237427, "step": 1558 }, { "epoch": 0.40472481827622014, "grad_norm": 3.528412103652954, "learning_rate": 4.659288140829351e-06, "loss": 0.3589361608028412, "step": 1559 }, { "epoch": 0.40498442367601245, "grad_norm": 2.224419116973877, "learning_rate": 4.658787458189995e-06, "loss": 0.40833771228790283, "step": 1560 }, { "epoch": 0.40524402907580476, "grad_norm": 4.017250061035156, "learning_rate": 4.658286438120721e-06, "loss": 0.41951784491539, "step": 1561 }, { "epoch": 0.4055036344755971, "grad_norm": 3.846865177154541, "learning_rate": 4.657785080710099e-06, "loss": 0.4147293269634247, "step": 1562 }, { "epoch": 0.4057632398753894, "grad_norm": 1.7491708993911743, "learning_rate": 4.657283386046757e-06, "loss": 0.3466290235519409, "step": 1563 }, { "epoch": 0.40602284527518173, "grad_norm": 3.3357009887695312, "learning_rate": 4.656781354219383e-06, "loss": 0.45655709505081177, "step": 1564 }, { "epoch": 0.40628245067497404, "grad_norm": 3.1078672409057617, "learning_rate": 4.656278985316725e-06, "loss": 0.3558288812637329, "step": 1565 }, { "epoch": 0.40654205607476634, "grad_norm": 4.351127624511719, "learning_rate": 4.655776279427591e-06, "loss": 0.36973679065704346, "step": 1566 }, { "epoch": 0.40680166147455865, "grad_norm": 2.4159252643585205, "learning_rate": 4.655273236640847e-06, "loss": 0.38387396931648254, "step": 1567 }, { "epoch": 0.407061266874351, "grad_norm": 3.3722984790802, "learning_rate": 4.6547698570454206e-06, "loss": 0.40758001804351807, "step": 1568 }, { "epoch": 0.4073208722741433, "grad_norm": 5.327269077301025, "learning_rate": 4.654266140730297e-06, "loss": 0.443672776222229, "step": 1569 }, { "epoch": 0.4075804776739356, "grad_norm": 2.540416955947876, "learning_rate": 4.653762087784521e-06, "loss": 0.33719342947006226, "step": 1570 }, { "epoch": 0.40784008307372793, "grad_norm": 3.6264705657958984, "learning_rate": 4.653257698297198e-06, "loss": 0.349473774433136, "step": 1571 }, { "epoch": 0.40809968847352024, "grad_norm": 4.637056827545166, "learning_rate": 4.652752972357492e-06, "loss": 0.46061939001083374, "step": 1572 }, { "epoch": 0.40835929387331255, "grad_norm": 4.130589008331299, "learning_rate": 4.652247910054629e-06, "loss": 0.3995688259601593, "step": 1573 }, { "epoch": 0.4086188992731049, "grad_norm": 5.594429016113281, "learning_rate": 4.6517425114778905e-06, "loss": 0.41664355993270874, "step": 1574 }, { "epoch": 0.4088785046728972, "grad_norm": 3.2304534912109375, "learning_rate": 4.65123677671662e-06, "loss": 0.3426603674888611, "step": 1575 }, { "epoch": 0.4091381100726895, "grad_norm": 6.020326614379883, "learning_rate": 4.6507307058602205e-06, "loss": 0.38619041442871094, "step": 1576 }, { "epoch": 0.4093977154724818, "grad_norm": 4.388158798217773, "learning_rate": 4.650224298998154e-06, "loss": 0.36263471841812134, "step": 1577 }, { "epoch": 0.40965732087227413, "grad_norm": 4.191479682922363, "learning_rate": 4.649717556219939e-06, "loss": 0.4349496364593506, "step": 1578 }, { "epoch": 0.40991692627206644, "grad_norm": 3.7027721405029297, "learning_rate": 4.649210477615159e-06, "loss": 0.34090813994407654, "step": 1579 }, { "epoch": 0.4101765316718588, "grad_norm": 4.805662631988525, "learning_rate": 4.648703063273452e-06, "loss": 0.3591572344303131, "step": 1580 }, { "epoch": 0.4104361370716511, "grad_norm": 4.8917999267578125, "learning_rate": 4.6481953132845184e-06, "loss": 0.43874698877334595, "step": 1581 }, { "epoch": 0.4106957424714434, "grad_norm": 4.361557483673096, "learning_rate": 4.647687227738116e-06, "loss": 0.4353142976760864, "step": 1582 }, { "epoch": 0.4109553478712357, "grad_norm": 4.4741363525390625, "learning_rate": 4.647178806724064e-06, "loss": 0.3737509250640869, "step": 1583 }, { "epoch": 0.411214953271028, "grad_norm": 3.8286283016204834, "learning_rate": 4.646670050332238e-06, "loss": 0.3512781858444214, "step": 1584 }, { "epoch": 0.41147455867082033, "grad_norm": 8.898958206176758, "learning_rate": 4.646160958652575e-06, "loss": 0.4192643165588379, "step": 1585 }, { "epoch": 0.4117341640706127, "grad_norm": 3.2585513591766357, "learning_rate": 4.645651531775071e-06, "loss": 0.3463243544101715, "step": 1586 }, { "epoch": 0.411993769470405, "grad_norm": 4.152743816375732, "learning_rate": 4.64514176978978e-06, "loss": 0.4240185022354126, "step": 1587 }, { "epoch": 0.4122533748701973, "grad_norm": 3.9685959815979004, "learning_rate": 4.6446316727868175e-06, "loss": 0.48622065782546997, "step": 1588 }, { "epoch": 0.4125129802699896, "grad_norm": 5.280534267425537, "learning_rate": 4.644121240856357e-06, "loss": 0.4014236032962799, "step": 1589 }, { "epoch": 0.4127725856697819, "grad_norm": 6.679940700531006, "learning_rate": 4.6436104740886305e-06, "loss": 0.3324310779571533, "step": 1590 }, { "epoch": 0.41303219106957423, "grad_norm": 4.062171936035156, "learning_rate": 4.64309937257393e-06, "loss": 0.454184889793396, "step": 1591 }, { "epoch": 0.4132917964693666, "grad_norm": 6.1720380783081055, "learning_rate": 4.642587936402607e-06, "loss": 0.4163062572479248, "step": 1592 }, { "epoch": 0.4135514018691589, "grad_norm": 3.2696032524108887, "learning_rate": 4.642076165665071e-06, "loss": 0.3993610739707947, "step": 1593 }, { "epoch": 0.4138110072689512, "grad_norm": 2.6309924125671387, "learning_rate": 4.641564060451792e-06, "loss": 0.408377468585968, "step": 1594 }, { "epoch": 0.4140706126687435, "grad_norm": 2.3140153884887695, "learning_rate": 4.641051620853298e-06, "loss": 0.3863338530063629, "step": 1595 }, { "epoch": 0.4143302180685358, "grad_norm": 5.746891975402832, "learning_rate": 4.640538846960177e-06, "loss": 0.3539913296699524, "step": 1596 }, { "epoch": 0.4145898234683281, "grad_norm": 6.940879821777344, "learning_rate": 4.640025738863076e-06, "loss": 0.42650291323661804, "step": 1597 }, { "epoch": 0.4148494288681205, "grad_norm": 6.198835849761963, "learning_rate": 4.639512296652699e-06, "loss": 0.505724310874939, "step": 1598 }, { "epoch": 0.4151090342679128, "grad_norm": 2.6852030754089355, "learning_rate": 4.638998520419812e-06, "loss": 0.3195785880088806, "step": 1599 }, { "epoch": 0.4153686396677051, "grad_norm": 2.9090723991394043, "learning_rate": 4.63848441025524e-06, "loss": 0.3432796001434326, "step": 1600 }, { "epoch": 0.4156282450674974, "grad_norm": 3.720717430114746, "learning_rate": 4.6379699662498646e-06, "loss": 0.43789732456207275, "step": 1601 }, { "epoch": 0.4158878504672897, "grad_norm": 5.767612457275391, "learning_rate": 4.637455188494627e-06, "loss": 0.465474009513855, "step": 1602 }, { "epoch": 0.416147455867082, "grad_norm": 2.3558478355407715, "learning_rate": 4.636940077080531e-06, "loss": 0.35989272594451904, "step": 1603 }, { "epoch": 0.4164070612668744, "grad_norm": 2.480773448944092, "learning_rate": 4.6364246320986325e-06, "loss": 0.3856356739997864, "step": 1604 }, { "epoch": 0.4166666666666667, "grad_norm": 2.249358892440796, "learning_rate": 4.6359088536400534e-06, "loss": 0.3663512170314789, "step": 1605 }, { "epoch": 0.416926272066459, "grad_norm": 2.6097910404205322, "learning_rate": 4.635392741795971e-06, "loss": 0.4086076021194458, "step": 1606 }, { "epoch": 0.4171858774662513, "grad_norm": 3.968109130859375, "learning_rate": 4.63487629665762e-06, "loss": 0.39690184593200684, "step": 1607 }, { "epoch": 0.4174454828660436, "grad_norm": 8.261850357055664, "learning_rate": 4.634359518316299e-06, "loss": 0.5113265514373779, "step": 1608 }, { "epoch": 0.4177050882658359, "grad_norm": 5.921697616577148, "learning_rate": 4.6338424068633615e-06, "loss": 0.29175472259521484, "step": 1609 }, { "epoch": 0.4179646936656282, "grad_norm": 4.5945892333984375, "learning_rate": 4.6333249623902195e-06, "loss": 0.35813015699386597, "step": 1610 }, { "epoch": 0.4182242990654206, "grad_norm": 7.751162052154541, "learning_rate": 4.632807184988348e-06, "loss": 0.31355470418930054, "step": 1611 }, { "epoch": 0.4184839044652129, "grad_norm": 5.826879501342773, "learning_rate": 4.6322890747492765e-06, "loss": 0.38833341002464294, "step": 1612 }, { "epoch": 0.4187435098650052, "grad_norm": 2.9257960319519043, "learning_rate": 4.631770631764595e-06, "loss": 0.3630880117416382, "step": 1613 }, { "epoch": 0.4190031152647975, "grad_norm": 3.9427130222320557, "learning_rate": 4.631251856125952e-06, "loss": 0.47544121742248535, "step": 1614 }, { "epoch": 0.4192627206645898, "grad_norm": 4.7084479331970215, "learning_rate": 4.630732747925057e-06, "loss": 0.42934760451316833, "step": 1615 }, { "epoch": 0.4195223260643821, "grad_norm": 1.8345955610275269, "learning_rate": 4.630213307253674e-06, "loss": 0.3798452615737915, "step": 1616 }, { "epoch": 0.4197819314641745, "grad_norm": 3.586411476135254, "learning_rate": 4.6296935342036305e-06, "loss": 0.4491296410560608, "step": 1617 }, { "epoch": 0.4200415368639668, "grad_norm": 4.750576019287109, "learning_rate": 4.629173428866808e-06, "loss": 0.3193456530570984, "step": 1618 }, { "epoch": 0.4203011422637591, "grad_norm": 6.175132751464844, "learning_rate": 4.628652991335153e-06, "loss": 0.44570451974868774, "step": 1619 }, { "epoch": 0.4205607476635514, "grad_norm": 3.1944541931152344, "learning_rate": 4.628132221700663e-06, "loss": 0.3653259873390198, "step": 1620 }, { "epoch": 0.4208203530633437, "grad_norm": 2.8532462120056152, "learning_rate": 4.627611120055399e-06, "loss": 0.3420976996421814, "step": 1621 }, { "epoch": 0.421079958463136, "grad_norm": 1.98880136013031, "learning_rate": 4.627089686491482e-06, "loss": 0.33460497856140137, "step": 1622 }, { "epoch": 0.42133956386292837, "grad_norm": 3.168304443359375, "learning_rate": 4.626567921101087e-06, "loss": 0.42136910557746887, "step": 1623 }, { "epoch": 0.4215991692627207, "grad_norm": 2.3423690795898438, "learning_rate": 4.626045823976453e-06, "loss": 0.3476827144622803, "step": 1624 }, { "epoch": 0.421858774662513, "grad_norm": 3.2171363830566406, "learning_rate": 4.625523395209871e-06, "loss": 0.33656859397888184, "step": 1625 }, { "epoch": 0.4221183800623053, "grad_norm": 5.2485833168029785, "learning_rate": 4.625000634893698e-06, "loss": 0.37593328952789307, "step": 1626 }, { "epoch": 0.4223779854620976, "grad_norm": 5.005648136138916, "learning_rate": 4.624477543120344e-06, "loss": 0.4048105478286743, "step": 1627 }, { "epoch": 0.4226375908618899, "grad_norm": 3.778618097305298, "learning_rate": 4.62395411998228e-06, "loss": 0.37053418159484863, "step": 1628 }, { "epoch": 0.42289719626168226, "grad_norm": 3.910529136657715, "learning_rate": 4.623430365572036e-06, "loss": 0.31721770763397217, "step": 1629 }, { "epoch": 0.42315680166147457, "grad_norm": 5.560649871826172, "learning_rate": 4.622906279982199e-06, "loss": 0.5188471078872681, "step": 1630 }, { "epoch": 0.4234164070612669, "grad_norm": 5.422704696655273, "learning_rate": 4.6223818633054155e-06, "loss": 0.3947831690311432, "step": 1631 }, { "epoch": 0.4236760124610592, "grad_norm": 2.7999582290649414, "learning_rate": 4.62185711563439e-06, "loss": 0.3750046491622925, "step": 1632 }, { "epoch": 0.4239356178608515, "grad_norm": 1.9689065217971802, "learning_rate": 4.621332037061887e-06, "loss": 0.3529170751571655, "step": 1633 }, { "epoch": 0.4241952232606438, "grad_norm": 3.968877077102661, "learning_rate": 4.620806627680728e-06, "loss": 0.38767534494400024, "step": 1634 }, { "epoch": 0.42445482866043616, "grad_norm": 5.339788913726807, "learning_rate": 4.6202808875837915e-06, "loss": 0.4412215054035187, "step": 1635 }, { "epoch": 0.42471443406022846, "grad_norm": 5.1270341873168945, "learning_rate": 4.619754816864019e-06, "loss": 0.4681098461151123, "step": 1636 }, { "epoch": 0.42497403946002077, "grad_norm": 3.2309911251068115, "learning_rate": 4.619228415614406e-06, "loss": 0.40662336349487305, "step": 1637 }, { "epoch": 0.4252336448598131, "grad_norm": 3.2429299354553223, "learning_rate": 4.61870168392801e-06, "loss": 0.3684387505054474, "step": 1638 }, { "epoch": 0.4254932502596054, "grad_norm": 2.5975341796875, "learning_rate": 4.6181746218979424e-06, "loss": 0.3385944068431854, "step": 1639 }, { "epoch": 0.4257528556593977, "grad_norm": 5.391345024108887, "learning_rate": 4.6176472296173775e-06, "loss": 0.3664178252220154, "step": 1640 }, { "epoch": 0.42601246105919005, "grad_norm": 4.420018672943115, "learning_rate": 4.617119507179546e-06, "loss": 0.33513718843460083, "step": 1641 }, { "epoch": 0.42627206645898236, "grad_norm": 3.27933931350708, "learning_rate": 4.616591454677737e-06, "loss": 0.3417893052101135, "step": 1642 }, { "epoch": 0.42653167185877466, "grad_norm": 2.319960355758667, "learning_rate": 4.616063072205298e-06, "loss": 0.36018234491348267, "step": 1643 }, { "epoch": 0.42679127725856697, "grad_norm": 7.189662933349609, "learning_rate": 4.615534359855636e-06, "loss": 0.42540639638900757, "step": 1644 }, { "epoch": 0.4270508826583593, "grad_norm": 4.132525444030762, "learning_rate": 4.615005317722213e-06, "loss": 0.35715022683143616, "step": 1645 }, { "epoch": 0.4273104880581516, "grad_norm": 4.535449504852295, "learning_rate": 4.614475945898554e-06, "loss": 0.3155045211315155, "step": 1646 }, { "epoch": 0.42757009345794394, "grad_norm": 4.135591506958008, "learning_rate": 4.613946244478238e-06, "loss": 0.34160706400871277, "step": 1647 }, { "epoch": 0.42782969885773625, "grad_norm": 3.1216206550598145, "learning_rate": 4.613416213554904e-06, "loss": 0.3197169899940491, "step": 1648 }, { "epoch": 0.42808930425752856, "grad_norm": 2.9600396156311035, "learning_rate": 4.61288585322225e-06, "loss": 0.3204689919948578, "step": 1649 }, { "epoch": 0.42834890965732086, "grad_norm": 3.9138355255126953, "learning_rate": 4.6123551635740336e-06, "loss": 0.34769541025161743, "step": 1650 }, { "epoch": 0.42860851505711317, "grad_norm": 3.433037757873535, "learning_rate": 4.611824144704064e-06, "loss": 0.3812066316604614, "step": 1651 }, { "epoch": 0.4288681204569055, "grad_norm": 7.338736534118652, "learning_rate": 4.611292796706218e-06, "loss": 0.3804636597633362, "step": 1652 }, { "epoch": 0.42912772585669784, "grad_norm": 2.5042662620544434, "learning_rate": 4.610761119674422e-06, "loss": 0.3365367352962494, "step": 1653 }, { "epoch": 0.42938733125649015, "grad_norm": 3.01274037361145, "learning_rate": 4.610229113702666e-06, "loss": 0.37772777676582336, "step": 1654 }, { "epoch": 0.42964693665628245, "grad_norm": 2.815861225128174, "learning_rate": 4.609696778884997e-06, "loss": 0.3493812084197998, "step": 1655 }, { "epoch": 0.42990654205607476, "grad_norm": 6.987683296203613, "learning_rate": 4.6091641153155175e-06, "loss": 0.32567858695983887, "step": 1656 }, { "epoch": 0.43016614745586707, "grad_norm": 6.028202056884766, "learning_rate": 4.608631123088393e-06, "loss": 0.35490715503692627, "step": 1657 }, { "epoch": 0.43042575285565937, "grad_norm": 2.9883697032928467, "learning_rate": 4.6080978022978425e-06, "loss": 0.3456190228462219, "step": 1658 }, { "epoch": 0.43068535825545173, "grad_norm": 2.4557931423187256, "learning_rate": 4.607564153038146e-06, "loss": 0.39577484130859375, "step": 1659 }, { "epoch": 0.43094496365524404, "grad_norm": 4.079228401184082, "learning_rate": 4.607030175403638e-06, "loss": 0.38962846994400024, "step": 1660 }, { "epoch": 0.43120456905503635, "grad_norm": 6.174893379211426, "learning_rate": 4.606495869488716e-06, "loss": 0.4259456396102905, "step": 1661 }, { "epoch": 0.43146417445482865, "grad_norm": 3.8982138633728027, "learning_rate": 4.605961235387834e-06, "loss": 0.4157392382621765, "step": 1662 }, { "epoch": 0.43172377985462096, "grad_norm": 8.069034576416016, "learning_rate": 4.605426273195499e-06, "loss": 0.4098549485206604, "step": 1663 }, { "epoch": 0.43198338525441327, "grad_norm": 3.610715389251709, "learning_rate": 4.604890983006285e-06, "loss": 0.3657916784286499, "step": 1664 }, { "epoch": 0.4322429906542056, "grad_norm": 6.658716678619385, "learning_rate": 4.604355364914816e-06, "loss": 0.4265761971473694, "step": 1665 }, { "epoch": 0.43250259605399793, "grad_norm": 4.4559807777404785, "learning_rate": 4.603819419015776e-06, "loss": 0.42124733328819275, "step": 1666 }, { "epoch": 0.43276220145379024, "grad_norm": 4.900829315185547, "learning_rate": 4.603283145403911e-06, "loss": 0.3500504195690155, "step": 1667 }, { "epoch": 0.43302180685358255, "grad_norm": 4.625869274139404, "learning_rate": 4.602746544174021e-06, "loss": 0.355755090713501, "step": 1668 }, { "epoch": 0.43328141225337485, "grad_norm": 5.582276821136475, "learning_rate": 4.602209615420963e-06, "loss": 0.3902735412120819, "step": 1669 }, { "epoch": 0.43354101765316716, "grad_norm": 3.7787458896636963, "learning_rate": 4.601672359239654e-06, "loss": 0.3366892635822296, "step": 1670 }, { "epoch": 0.4338006230529595, "grad_norm": 3.1835620403289795, "learning_rate": 4.6011347757250716e-06, "loss": 0.42439353466033936, "step": 1671 }, { "epoch": 0.43406022845275183, "grad_norm": 7.0221662521362305, "learning_rate": 4.600596864972246e-06, "loss": 0.43897745013237, "step": 1672 }, { "epoch": 0.43431983385254413, "grad_norm": 3.522167205810547, "learning_rate": 4.600058627076266e-06, "loss": 0.343350887298584, "step": 1673 }, { "epoch": 0.43457943925233644, "grad_norm": 5.583951473236084, "learning_rate": 4.599520062132283e-06, "loss": 0.4013487696647644, "step": 1674 }, { "epoch": 0.43483904465212875, "grad_norm": 6.4641313552856445, "learning_rate": 4.598981170235501e-06, "loss": 0.38615623116493225, "step": 1675 }, { "epoch": 0.43509865005192105, "grad_norm": 2.9101810455322266, "learning_rate": 4.598441951481184e-06, "loss": 0.34693586826324463, "step": 1676 }, { "epoch": 0.4353582554517134, "grad_norm": 2.915045738220215, "learning_rate": 4.597902405964654e-06, "loss": 0.34550291299819946, "step": 1677 }, { "epoch": 0.4356178608515057, "grad_norm": 6.062941551208496, "learning_rate": 4.59736253378129e-06, "loss": 0.3526352643966675, "step": 1678 }, { "epoch": 0.43587746625129803, "grad_norm": 2.656069040298462, "learning_rate": 4.596822335026529e-06, "loss": 0.35809484124183655, "step": 1679 }, { "epoch": 0.43613707165109034, "grad_norm": 5.675659656524658, "learning_rate": 4.596281809795866e-06, "loss": 0.40621691942214966, "step": 1680 }, { "epoch": 0.43639667705088264, "grad_norm": 4.800686359405518, "learning_rate": 4.5957409581848535e-06, "loss": 0.3508273959159851, "step": 1681 }, { "epoch": 0.43665628245067495, "grad_norm": 6.278221130371094, "learning_rate": 4.595199780289101e-06, "loss": 0.4678553342819214, "step": 1682 }, { "epoch": 0.4369158878504673, "grad_norm": 2.651620864868164, "learning_rate": 4.5946582762042765e-06, "loss": 0.40634357929229736, "step": 1683 }, { "epoch": 0.4371754932502596, "grad_norm": 5.207724094390869, "learning_rate": 4.594116446026106e-06, "loss": 0.41023194789886475, "step": 1684 }, { "epoch": 0.4374350986500519, "grad_norm": 2.959207057952881, "learning_rate": 4.5935742898503725e-06, "loss": 0.35386383533477783, "step": 1685 }, { "epoch": 0.43769470404984423, "grad_norm": 2.1297566890716553, "learning_rate": 4.5930318077729165e-06, "loss": 0.35180529952049255, "step": 1686 }, { "epoch": 0.43795430944963654, "grad_norm": 2.325718402862549, "learning_rate": 4.592488999889638e-06, "loss": 0.35322895646095276, "step": 1687 }, { "epoch": 0.43821391484942884, "grad_norm": 3.22058367729187, "learning_rate": 4.5919458662964905e-06, "loss": 0.3139047920703888, "step": 1688 }, { "epoch": 0.4384735202492212, "grad_norm": 3.6649892330169678, "learning_rate": 4.591402407089489e-06, "loss": 0.3458176255226135, "step": 1689 }, { "epoch": 0.4387331256490135, "grad_norm": 3.587167263031006, "learning_rate": 4.590858622364705e-06, "loss": 0.34972289204597473, "step": 1690 }, { "epoch": 0.4389927310488058, "grad_norm": 3.394326686859131, "learning_rate": 4.590314512218266e-06, "loss": 0.39800500869750977, "step": 1691 }, { "epoch": 0.4392523364485981, "grad_norm": 2.2707033157348633, "learning_rate": 4.58977007674636e-06, "loss": 0.3649616539478302, "step": 1692 }, { "epoch": 0.43951194184839043, "grad_norm": 3.496913433074951, "learning_rate": 4.589225316045228e-06, "loss": 0.36063283681869507, "step": 1693 }, { "epoch": 0.43977154724818274, "grad_norm": 4.4994096755981445, "learning_rate": 4.588680230211174e-06, "loss": 0.361937940120697, "step": 1694 }, { "epoch": 0.4400311526479751, "grad_norm": 2.2849924564361572, "learning_rate": 4.588134819340554e-06, "loss": 0.3326526880264282, "step": 1695 }, { "epoch": 0.4402907580477674, "grad_norm": 4.615967750549316, "learning_rate": 4.587589083529788e-06, "loss": 0.4700540602207184, "step": 1696 }, { "epoch": 0.4405503634475597, "grad_norm": 5.679474830627441, "learning_rate": 4.587043022875345e-06, "loss": 0.39062291383743286, "step": 1697 }, { "epoch": 0.440809968847352, "grad_norm": 3.954008102416992, "learning_rate": 4.586496637473759e-06, "loss": 0.36689677834510803, "step": 1698 }, { "epoch": 0.4410695742471443, "grad_norm": 4.359582424163818, "learning_rate": 4.585949927421618e-06, "loss": 0.3697752356529236, "step": 1699 }, { "epoch": 0.44132917964693663, "grad_norm": 3.6971311569213867, "learning_rate": 4.5854028928155674e-06, "loss": 0.32051217555999756, "step": 1700 }, { "epoch": 0.441588785046729, "grad_norm": 2.4291152954101562, "learning_rate": 4.584855533752311e-06, "loss": 0.3575421869754791, "step": 1701 }, { "epoch": 0.4418483904465213, "grad_norm": 2.6336255073547363, "learning_rate": 4.584307850328608e-06, "loss": 0.3470489978790283, "step": 1702 }, { "epoch": 0.4421079958463136, "grad_norm": 4.009500026702881, "learning_rate": 4.5837598426412775e-06, "loss": 0.32101187109947205, "step": 1703 }, { "epoch": 0.4423676012461059, "grad_norm": 2.3541951179504395, "learning_rate": 4.583211510787194e-06, "loss": 0.35060107707977295, "step": 1704 }, { "epoch": 0.4426272066458982, "grad_norm": 2.3211028575897217, "learning_rate": 4.582662854863291e-06, "loss": 0.3291245698928833, "step": 1705 }, { "epoch": 0.4428868120456905, "grad_norm": 4.694430351257324, "learning_rate": 4.582113874966558e-06, "loss": 0.5044366121292114, "step": 1706 }, { "epoch": 0.4431464174454829, "grad_norm": 5.9786248207092285, "learning_rate": 4.581564571194041e-06, "loss": 0.3751029670238495, "step": 1707 }, { "epoch": 0.4434060228452752, "grad_norm": 10.735753059387207, "learning_rate": 4.581014943642845e-06, "loss": 0.4448515772819519, "step": 1708 }, { "epoch": 0.4436656282450675, "grad_norm": 3.5449841022491455, "learning_rate": 4.580464992410132e-06, "loss": 0.3909648656845093, "step": 1709 }, { "epoch": 0.4439252336448598, "grad_norm": 8.84955883026123, "learning_rate": 4.57991471759312e-06, "loss": 0.4581793546676636, "step": 1710 }, { "epoch": 0.4441848390446521, "grad_norm": 7.306513786315918, "learning_rate": 4.579364119289086e-06, "loss": 0.45567935705184937, "step": 1711 }, { "epoch": 0.4444444444444444, "grad_norm": 6.727915287017822, "learning_rate": 4.578813197595363e-06, "loss": 0.4656451642513275, "step": 1712 }, { "epoch": 0.4447040498442368, "grad_norm": 4.272744655609131, "learning_rate": 4.578261952609339e-06, "loss": 0.3924146294593811, "step": 1713 }, { "epoch": 0.4449636552440291, "grad_norm": 3.447606325149536, "learning_rate": 4.577710384428466e-06, "loss": 0.3697356879711151, "step": 1714 }, { "epoch": 0.4452232606438214, "grad_norm": 6.617214679718018, "learning_rate": 4.577158493150244e-06, "loss": 0.420681893825531, "step": 1715 }, { "epoch": 0.4454828660436137, "grad_norm": 10.430802345275879, "learning_rate": 4.576606278872238e-06, "loss": 0.41351568698883057, "step": 1716 }, { "epoch": 0.445742471443406, "grad_norm": 6.447225570678711, "learning_rate": 4.576053741692065e-06, "loss": 0.4025519788265228, "step": 1717 }, { "epoch": 0.4460020768431983, "grad_norm": 3.235898017883301, "learning_rate": 4.575500881707402e-06, "loss": 0.4313017725944519, "step": 1718 }, { "epoch": 0.4462616822429907, "grad_norm": 4.762578964233398, "learning_rate": 4.574947699015981e-06, "loss": 0.40701279044151306, "step": 1719 }, { "epoch": 0.446521287642783, "grad_norm": 5.259486198425293, "learning_rate": 4.574394193715593e-06, "loss": 0.4560388922691345, "step": 1720 }, { "epoch": 0.4467808930425753, "grad_norm": 4.045895576477051, "learning_rate": 4.573840365904084e-06, "loss": 0.3671381175518036, "step": 1721 }, { "epoch": 0.4470404984423676, "grad_norm": 6.145009994506836, "learning_rate": 4.57328621567936e-06, "loss": 0.4415567219257355, "step": 1722 }, { "epoch": 0.4473001038421599, "grad_norm": 6.13828706741333, "learning_rate": 4.57273174313938e-06, "loss": 0.3623499870300293, "step": 1723 }, { "epoch": 0.4475597092419522, "grad_norm": 5.580677509307861, "learning_rate": 4.5721769483821625e-06, "loss": 0.5052841305732727, "step": 1724 }, { "epoch": 0.44781931464174457, "grad_norm": 5.31650447845459, "learning_rate": 4.571621831505783e-06, "loss": 0.3783723711967468, "step": 1725 }, { "epoch": 0.4480789200415369, "grad_norm": 7.694154262542725, "learning_rate": 4.571066392608374e-06, "loss": 0.41292834281921387, "step": 1726 }, { "epoch": 0.4483385254413292, "grad_norm": 5.274920463562012, "learning_rate": 4.5705106317881225e-06, "loss": 0.4237174987792969, "step": 1727 }, { "epoch": 0.4485981308411215, "grad_norm": 9.140535354614258, "learning_rate": 4.569954549143276e-06, "loss": 0.5015219449996948, "step": 1728 }, { "epoch": 0.4488577362409138, "grad_norm": 4.809543132781982, "learning_rate": 4.569398144772137e-06, "loss": 0.3582156300544739, "step": 1729 }, { "epoch": 0.4491173416407061, "grad_norm": 5.216885566711426, "learning_rate": 4.568841418773064e-06, "loss": 0.3434184193611145, "step": 1730 }, { "epoch": 0.44937694704049846, "grad_norm": 3.309129476547241, "learning_rate": 4.568284371244475e-06, "loss": 0.388576865196228, "step": 1731 }, { "epoch": 0.44963655244029077, "grad_norm": 5.478052616119385, "learning_rate": 4.567727002284842e-06, "loss": 0.40838271379470825, "step": 1732 }, { "epoch": 0.4498961578400831, "grad_norm": 3.816818952560425, "learning_rate": 4.567169311992696e-06, "loss": 0.3637467324733734, "step": 1733 }, { "epoch": 0.4501557632398754, "grad_norm": 8.458271026611328, "learning_rate": 4.566611300466622e-06, "loss": 0.4394608438014984, "step": 1734 }, { "epoch": 0.4504153686396677, "grad_norm": 1.9028985500335693, "learning_rate": 4.566052967805266e-06, "loss": 0.3463636636734009, "step": 1735 }, { "epoch": 0.45067497403946, "grad_norm": 3.281736373901367, "learning_rate": 4.565494314107327e-06, "loss": 0.3226945996284485, "step": 1736 }, { "epoch": 0.45093457943925236, "grad_norm": 5.164882183074951, "learning_rate": 4.564935339471563e-06, "loss": 0.3627610504627228, "step": 1737 }, { "epoch": 0.45119418483904467, "grad_norm": 3.815917730331421, "learning_rate": 4.564376043996787e-06, "loss": 0.38468098640441895, "step": 1738 }, { "epoch": 0.45145379023883697, "grad_norm": 5.425127029418945, "learning_rate": 4.5638164277818705e-06, "loss": 0.3881641626358032, "step": 1739 }, { "epoch": 0.4517133956386293, "grad_norm": 3.621415138244629, "learning_rate": 4.56325649092574e-06, "loss": 0.4117530286312103, "step": 1740 }, { "epoch": 0.4519730010384216, "grad_norm": 4.319150924682617, "learning_rate": 4.56269623352738e-06, "loss": 0.36806586384773254, "step": 1741 }, { "epoch": 0.4522326064382139, "grad_norm": 4.526022434234619, "learning_rate": 4.562135655685831e-06, "loss": 0.3767552375793457, "step": 1742 }, { "epoch": 0.45249221183800625, "grad_norm": 2.488532304763794, "learning_rate": 4.561574757500192e-06, "loss": 0.3876507878303528, "step": 1743 }, { "epoch": 0.45275181723779856, "grad_norm": 3.6673409938812256, "learning_rate": 4.5610135390696135e-06, "loss": 0.36644864082336426, "step": 1744 }, { "epoch": 0.45301142263759087, "grad_norm": 3.406459331512451, "learning_rate": 4.560452000493309e-06, "loss": 0.31181299686431885, "step": 1745 }, { "epoch": 0.4532710280373832, "grad_norm": 3.6385979652404785, "learning_rate": 4.559890141870545e-06, "loss": 0.4237946569919586, "step": 1746 }, { "epoch": 0.4535306334371755, "grad_norm": 2.0097625255584717, "learning_rate": 4.559327963300643e-06, "loss": 0.3480134904384613, "step": 1747 }, { "epoch": 0.4537902388369678, "grad_norm": 4.525993347167969, "learning_rate": 4.558765464882987e-06, "loss": 0.5407093167304993, "step": 1748 }, { "epoch": 0.45404984423676015, "grad_norm": 3.487093210220337, "learning_rate": 4.558202646717011e-06, "loss": 0.34586089849472046, "step": 1749 }, { "epoch": 0.45430944963655245, "grad_norm": 2.952500581741333, "learning_rate": 4.557639508902211e-06, "loss": 0.34862738847732544, "step": 1750 }, { "epoch": 0.45456905503634476, "grad_norm": 3.227562189102173, "learning_rate": 4.557076051538134e-06, "loss": 0.3347892463207245, "step": 1751 }, { "epoch": 0.45482866043613707, "grad_norm": 5.078027248382568, "learning_rate": 4.556512274724387e-06, "loss": 0.4000248312950134, "step": 1752 }, { "epoch": 0.4550882658359294, "grad_norm": 4.484903812408447, "learning_rate": 4.555948178560635e-06, "loss": 0.28435930609703064, "step": 1753 }, { "epoch": 0.4553478712357217, "grad_norm": 3.0925323963165283, "learning_rate": 4.555383763146596e-06, "loss": 0.3816871643066406, "step": 1754 }, { "epoch": 0.45560747663551404, "grad_norm": 5.595225811004639, "learning_rate": 4.554819028582044e-06, "loss": 0.3390941619873047, "step": 1755 }, { "epoch": 0.45586708203530635, "grad_norm": 3.9433021545410156, "learning_rate": 4.5542539749668134e-06, "loss": 0.3464110493659973, "step": 1756 }, { "epoch": 0.45612668743509865, "grad_norm": 4.402961254119873, "learning_rate": 4.553688602400792e-06, "loss": 0.37300142645835876, "step": 1757 }, { "epoch": 0.45638629283489096, "grad_norm": 5.741177082061768, "learning_rate": 4.5531229109839244e-06, "loss": 0.426721453666687, "step": 1758 }, { "epoch": 0.45664589823468327, "grad_norm": 3.7115869522094727, "learning_rate": 4.552556900816212e-06, "loss": 0.35090190172195435, "step": 1759 }, { "epoch": 0.4569055036344756, "grad_norm": 3.251272678375244, "learning_rate": 4.551990571997713e-06, "loss": 0.35623353719711304, "step": 1760 }, { "epoch": 0.45716510903426794, "grad_norm": 4.2425384521484375, "learning_rate": 4.551423924628541e-06, "loss": 0.33536362648010254, "step": 1761 }, { "epoch": 0.45742471443406024, "grad_norm": 3.8907814025878906, "learning_rate": 4.550856958808867e-06, "loss": 0.41642963886260986, "step": 1762 }, { "epoch": 0.45768431983385255, "grad_norm": 4.8334455490112305, "learning_rate": 4.550289674638915e-06, "loss": 0.424776554107666, "step": 1763 }, { "epoch": 0.45794392523364486, "grad_norm": 3.79714298248291, "learning_rate": 4.549722072218971e-06, "loss": 0.383128821849823, "step": 1764 }, { "epoch": 0.45820353063343716, "grad_norm": 7.391551971435547, "learning_rate": 4.5491541516493725e-06, "loss": 0.3569948971271515, "step": 1765 }, { "epoch": 0.45846313603322947, "grad_norm": 3.5083634853363037, "learning_rate": 4.548585913030515e-06, "loss": 0.3556671440601349, "step": 1766 }, { "epoch": 0.45872274143302183, "grad_norm": 4.7589263916015625, "learning_rate": 4.548017356462851e-06, "loss": 0.39500415325164795, "step": 1767 }, { "epoch": 0.45898234683281414, "grad_norm": 5.290412902832031, "learning_rate": 4.547448482046887e-06, "loss": 0.5073316097259521, "step": 1768 }, { "epoch": 0.45924195223260644, "grad_norm": 5.820164203643799, "learning_rate": 4.546879289883187e-06, "loss": 0.4514744281768799, "step": 1769 }, { "epoch": 0.45950155763239875, "grad_norm": 6.192318439483643, "learning_rate": 4.5463097800723725e-06, "loss": 0.4227742552757263, "step": 1770 }, { "epoch": 0.45976116303219106, "grad_norm": 4.129663944244385, "learning_rate": 4.545739952715118e-06, "loss": 0.33553868532180786, "step": 1771 }, { "epoch": 0.46002076843198336, "grad_norm": 2.4701342582702637, "learning_rate": 4.5451698079121575e-06, "loss": 0.3929893672466278, "step": 1772 }, { "epoch": 0.4602803738317757, "grad_norm": 7.3919291496276855, "learning_rate": 4.544599345764279e-06, "loss": 0.3838600814342499, "step": 1773 }, { "epoch": 0.46053997923156803, "grad_norm": 4.891142845153809, "learning_rate": 4.544028566372326e-06, "loss": 0.3924326002597809, "step": 1774 }, { "epoch": 0.46079958463136034, "grad_norm": 4.8095808029174805, "learning_rate": 4.543457469837202e-06, "loss": 0.390080064535141, "step": 1775 }, { "epoch": 0.46105919003115264, "grad_norm": 5.5108723640441895, "learning_rate": 4.542886056259861e-06, "loss": 0.33026939630508423, "step": 1776 }, { "epoch": 0.46131879543094495, "grad_norm": 3.6463723182678223, "learning_rate": 4.542314325741316e-06, "loss": 0.36580514907836914, "step": 1777 }, { "epoch": 0.46157840083073726, "grad_norm": 3.162839651107788, "learning_rate": 4.541742278382638e-06, "loss": 0.4065691828727722, "step": 1778 }, { "epoch": 0.4618380062305296, "grad_norm": 2.865663766860962, "learning_rate": 4.541169914284951e-06, "loss": 0.3869123160839081, "step": 1779 }, { "epoch": 0.4620976116303219, "grad_norm": 6.792677402496338, "learning_rate": 4.5405972335494345e-06, "loss": 0.355805367231369, "step": 1780 }, { "epoch": 0.46235721703011423, "grad_norm": 3.026488780975342, "learning_rate": 4.540024236277327e-06, "loss": 0.4022318124771118, "step": 1781 }, { "epoch": 0.46261682242990654, "grad_norm": 4.127779006958008, "learning_rate": 4.539450922569921e-06, "loss": 0.4606178402900696, "step": 1782 }, { "epoch": 0.46287642782969884, "grad_norm": 5.5885491371154785, "learning_rate": 4.538877292528564e-06, "loss": 0.4144538938999176, "step": 1783 }, { "epoch": 0.46313603322949115, "grad_norm": 2.654060125350952, "learning_rate": 4.538303346254662e-06, "loss": 0.3273420035839081, "step": 1784 }, { "epoch": 0.4633956386292835, "grad_norm": 3.069155216217041, "learning_rate": 4.537729083849675e-06, "loss": 0.3980654180049896, "step": 1785 }, { "epoch": 0.4636552440290758, "grad_norm": 2.2277872562408447, "learning_rate": 4.53715450541512e-06, "loss": 0.3851422369480133, "step": 1786 }, { "epoch": 0.4639148494288681, "grad_norm": 2.0517537593841553, "learning_rate": 4.5365796110525674e-06, "loss": 0.3844694495201111, "step": 1787 }, { "epoch": 0.46417445482866043, "grad_norm": 8.330156326293945, "learning_rate": 4.5360044008636485e-06, "loss": 0.4335338771343231, "step": 1788 }, { "epoch": 0.46443406022845274, "grad_norm": 3.944681167602539, "learning_rate": 4.535428874950045e-06, "loss": 0.44218945503234863, "step": 1789 }, { "epoch": 0.46469366562824505, "grad_norm": 3.3769991397857666, "learning_rate": 4.5348530334134975e-06, "loss": 0.3804054856300354, "step": 1790 }, { "epoch": 0.4649532710280374, "grad_norm": 4.572920322418213, "learning_rate": 4.534276876355801e-06, "loss": 0.34715110063552856, "step": 1791 }, { "epoch": 0.4652128764278297, "grad_norm": 4.047763824462891, "learning_rate": 4.533700403878806e-06, "loss": 0.45127153396606445, "step": 1792 }, { "epoch": 0.465472481827622, "grad_norm": 3.7131094932556152, "learning_rate": 4.533123616084423e-06, "loss": 0.3575851321220398, "step": 1793 }, { "epoch": 0.4657320872274143, "grad_norm": 5.394829750061035, "learning_rate": 4.5325465130746125e-06, "loss": 0.4332886338233948, "step": 1794 }, { "epoch": 0.46599169262720663, "grad_norm": 3.9892594814300537, "learning_rate": 4.531969094951393e-06, "loss": 0.42527467012405396, "step": 1795 }, { "epoch": 0.46625129802699894, "grad_norm": 3.7733194828033447, "learning_rate": 4.5313913618168394e-06, "loss": 0.3556970953941345, "step": 1796 }, { "epoch": 0.4665109034267913, "grad_norm": 4.272631645202637, "learning_rate": 4.530813313773081e-06, "loss": 0.3502098321914673, "step": 1797 }, { "epoch": 0.4667705088265836, "grad_norm": 4.282476425170898, "learning_rate": 4.530234950922304e-06, "loss": 0.3321155905723572, "step": 1798 }, { "epoch": 0.4670301142263759, "grad_norm": 7.382437229156494, "learning_rate": 4.52965627336675e-06, "loss": 0.40875566005706787, "step": 1799 }, { "epoch": 0.4672897196261682, "grad_norm": 2.951691150665283, "learning_rate": 4.529077281208716e-06, "loss": 0.342987060546875, "step": 1800 }, { "epoch": 0.4675493250259605, "grad_norm": 3.1200919151306152, "learning_rate": 4.528497974550553e-06, "loss": 0.35678914189338684, "step": 1801 }, { "epoch": 0.46780893042575283, "grad_norm": 2.373133897781372, "learning_rate": 4.527918353494672e-06, "loss": 0.33771809935569763, "step": 1802 }, { "epoch": 0.4680685358255452, "grad_norm": 4.9240241050720215, "learning_rate": 4.527338418143533e-06, "loss": 0.41446635127067566, "step": 1803 }, { "epoch": 0.4683281412253375, "grad_norm": 6.025909423828125, "learning_rate": 4.526758168599658e-06, "loss": 0.3358151614665985, "step": 1804 }, { "epoch": 0.4685877466251298, "grad_norm": 4.8260722160339355, "learning_rate": 4.526177604965622e-06, "loss": 0.37694787979125977, "step": 1805 }, { "epoch": 0.4688473520249221, "grad_norm": 2.52244234085083, "learning_rate": 4.525596727344054e-06, "loss": 0.35000813007354736, "step": 1806 }, { "epoch": 0.4691069574247144, "grad_norm": 2.237156629562378, "learning_rate": 4.52501553583764e-06, "loss": 0.3763980269432068, "step": 1807 }, { "epoch": 0.46936656282450673, "grad_norm": 3.0152809619903564, "learning_rate": 4.524434030549122e-06, "loss": 0.3643603026866913, "step": 1808 }, { "epoch": 0.4696261682242991, "grad_norm": 7.381468772888184, "learning_rate": 4.523852211581297e-06, "loss": 0.4034075438976288, "step": 1809 }, { "epoch": 0.4698857736240914, "grad_norm": 3.278655767440796, "learning_rate": 4.523270079037016e-06, "loss": 0.32150381803512573, "step": 1810 }, { "epoch": 0.4701453790238837, "grad_norm": 2.679238796234131, "learning_rate": 4.522687633019189e-06, "loss": 0.343183696269989, "step": 1811 }, { "epoch": 0.470404984423676, "grad_norm": 2.2133750915527344, "learning_rate": 4.522104873630776e-06, "loss": 0.3792586624622345, "step": 1812 }, { "epoch": 0.4706645898234683, "grad_norm": 5.665925979614258, "learning_rate": 4.521521800974798e-06, "loss": 0.45583850145339966, "step": 1813 }, { "epoch": 0.4709241952232606, "grad_norm": 5.107913970947266, "learning_rate": 4.520938415154328e-06, "loss": 0.4348657429218292, "step": 1814 }, { "epoch": 0.471183800623053, "grad_norm": 2.1074750423431396, "learning_rate": 4.520354716272495e-06, "loss": 0.34521275758743286, "step": 1815 }, { "epoch": 0.4714434060228453, "grad_norm": 5.051933765411377, "learning_rate": 4.519770704432484e-06, "loss": 0.3929196298122406, "step": 1816 }, { "epoch": 0.4717030114226376, "grad_norm": 7.559608459472656, "learning_rate": 4.519186379737535e-06, "loss": 0.41350382566452026, "step": 1817 }, { "epoch": 0.4719626168224299, "grad_norm": 4.37528657913208, "learning_rate": 4.518601742290943e-06, "loss": 0.4066176414489746, "step": 1818 }, { "epoch": 0.4722222222222222, "grad_norm": 4.902244567871094, "learning_rate": 4.518016792196059e-06, "loss": 0.4315829277038574, "step": 1819 }, { "epoch": 0.4724818276220145, "grad_norm": 5.471096992492676, "learning_rate": 4.5174315295562885e-06, "loss": 0.46342387795448303, "step": 1820 }, { "epoch": 0.4727414330218069, "grad_norm": 2.478762626647949, "learning_rate": 4.516845954475091e-06, "loss": 0.3672788143157959, "step": 1821 }, { "epoch": 0.4730010384215992, "grad_norm": 5.555480480194092, "learning_rate": 4.516260067055985e-06, "loss": 0.33542558550834656, "step": 1822 }, { "epoch": 0.4732606438213915, "grad_norm": 3.755918502807617, "learning_rate": 4.515673867402541e-06, "loss": 0.36461663246154785, "step": 1823 }, { "epoch": 0.4735202492211838, "grad_norm": 7.301084518432617, "learning_rate": 4.515087355618387e-06, "loss": 0.4610598385334015, "step": 1824 }, { "epoch": 0.4737798546209761, "grad_norm": 4.350727558135986, "learning_rate": 4.514500531807201e-06, "loss": 0.347392737865448, "step": 1825 }, { "epoch": 0.4740394600207684, "grad_norm": 4.683640956878662, "learning_rate": 4.513913396072725e-06, "loss": 0.39674103260040283, "step": 1826 }, { "epoch": 0.4742990654205608, "grad_norm": 4.279356002807617, "learning_rate": 4.513325948518748e-06, "loss": 0.33473169803619385, "step": 1827 }, { "epoch": 0.4745586708203531, "grad_norm": 8.868732452392578, "learning_rate": 4.512738189249119e-06, "loss": 0.4095585346221924, "step": 1828 }, { "epoch": 0.4748182762201454, "grad_norm": 6.379065990447998, "learning_rate": 4.512150118367739e-06, "loss": 0.441131591796875, "step": 1829 }, { "epoch": 0.4750778816199377, "grad_norm": 5.170450687408447, "learning_rate": 4.511561735978564e-06, "loss": 0.3825933337211609, "step": 1830 }, { "epoch": 0.47533748701973, "grad_norm": 3.0270464420318604, "learning_rate": 4.510973042185611e-06, "loss": 0.35686320066452026, "step": 1831 }, { "epoch": 0.4755970924195223, "grad_norm": 3.1416585445404053, "learning_rate": 4.5103840370929446e-06, "loss": 0.37736350297927856, "step": 1832 }, { "epoch": 0.47585669781931467, "grad_norm": 4.659064292907715, "learning_rate": 4.509794720804688e-06, "loss": 0.36517924070358276, "step": 1833 }, { "epoch": 0.476116303219107, "grad_norm": 4.643998146057129, "learning_rate": 4.509205093425018e-06, "loss": 0.3195410370826721, "step": 1834 }, { "epoch": 0.4763759086188993, "grad_norm": 2.9767048358917236, "learning_rate": 4.508615155058168e-06, "loss": 0.3885185718536377, "step": 1835 }, { "epoch": 0.4766355140186916, "grad_norm": 3.3922278881073, "learning_rate": 4.508024905808426e-06, "loss": 0.369036465883255, "step": 1836 }, { "epoch": 0.4768951194184839, "grad_norm": 1.8975310325622559, "learning_rate": 4.507434345780133e-06, "loss": 0.38503944873809814, "step": 1837 }, { "epoch": 0.4771547248182762, "grad_norm": 5.150221347808838, "learning_rate": 4.506843475077689e-06, "loss": 0.41582340002059937, "step": 1838 }, { "epoch": 0.47741433021806856, "grad_norm": 5.609508037567139, "learning_rate": 4.5062522938055444e-06, "loss": 0.45788633823394775, "step": 1839 }, { "epoch": 0.47767393561786087, "grad_norm": 5.128068447113037, "learning_rate": 4.505660802068207e-06, "loss": 0.3718705177307129, "step": 1840 }, { "epoch": 0.4779335410176532, "grad_norm": 4.545754432678223, "learning_rate": 4.50506899997024e-06, "loss": 0.3388887047767639, "step": 1841 }, { "epoch": 0.4781931464174455, "grad_norm": 5.636696815490723, "learning_rate": 4.504476887616258e-06, "loss": 0.43368229269981384, "step": 1842 }, { "epoch": 0.4784527518172378, "grad_norm": 5.231722354888916, "learning_rate": 4.503884465110935e-06, "loss": 0.45447838306427, "step": 1843 }, { "epoch": 0.4787123572170301, "grad_norm": 5.248867511749268, "learning_rate": 4.503291732558998e-06, "loss": 0.39512258768081665, "step": 1844 }, { "epoch": 0.47897196261682246, "grad_norm": 7.612858295440674, "learning_rate": 4.502698690065227e-06, "loss": 0.3543202877044678, "step": 1845 }, { "epoch": 0.47923156801661476, "grad_norm": 2.420684814453125, "learning_rate": 4.5021053377344596e-06, "loss": 0.3818369209766388, "step": 1846 }, { "epoch": 0.47949117341640707, "grad_norm": 2.787482738494873, "learning_rate": 4.501511675671586e-06, "loss": 0.34688127040863037, "step": 1847 }, { "epoch": 0.4797507788161994, "grad_norm": 5.295232772827148, "learning_rate": 4.500917703981553e-06, "loss": 0.46186983585357666, "step": 1848 }, { "epoch": 0.4800103842159917, "grad_norm": 3.633357524871826, "learning_rate": 4.5003234227693596e-06, "loss": 0.3573557436466217, "step": 1849 }, { "epoch": 0.480269989615784, "grad_norm": 3.9488375186920166, "learning_rate": 4.499728832140063e-06, "loss": 0.4114457964897156, "step": 1850 }, { "epoch": 0.48052959501557635, "grad_norm": 3.9603254795074463, "learning_rate": 4.499133932198772e-06, "loss": 0.41363298892974854, "step": 1851 }, { "epoch": 0.48078920041536866, "grad_norm": 4.096459865570068, "learning_rate": 4.498538723050651e-06, "loss": 0.4237934947013855, "step": 1852 }, { "epoch": 0.48104880581516096, "grad_norm": 6.220224380493164, "learning_rate": 4.4979432048009215e-06, "loss": 0.31811556220054626, "step": 1853 }, { "epoch": 0.48130841121495327, "grad_norm": 4.9727373123168945, "learning_rate": 4.497347377554855e-06, "loss": 0.3584413528442383, "step": 1854 }, { "epoch": 0.4815680166147456, "grad_norm": 5.800600528717041, "learning_rate": 4.4967512414177816e-06, "loss": 0.3290262222290039, "step": 1855 }, { "epoch": 0.4818276220145379, "grad_norm": 3.22951340675354, "learning_rate": 4.496154796495083e-06, "loss": 0.3654007613658905, "step": 1856 }, { "epoch": 0.48208722741433024, "grad_norm": 4.021310329437256, "learning_rate": 4.495558042892199e-06, "loss": 0.39334771037101746, "step": 1857 }, { "epoch": 0.48234683281412255, "grad_norm": 2.8593616485595703, "learning_rate": 4.49496098071462e-06, "loss": 0.35648617148399353, "step": 1858 }, { "epoch": 0.48260643821391486, "grad_norm": 3.751338243484497, "learning_rate": 4.494363610067895e-06, "loss": 0.42224258184432983, "step": 1859 }, { "epoch": 0.48286604361370716, "grad_norm": 6.282092094421387, "learning_rate": 4.493765931057624e-06, "loss": 0.2941768765449524, "step": 1860 }, { "epoch": 0.48312564901349947, "grad_norm": 8.594294548034668, "learning_rate": 4.493167943789463e-06, "loss": 0.3870581388473511, "step": 1861 }, { "epoch": 0.4833852544132918, "grad_norm": 2.560415744781494, "learning_rate": 4.492569648369124e-06, "loss": 0.344856858253479, "step": 1862 }, { "epoch": 0.48364485981308414, "grad_norm": 4.044785976409912, "learning_rate": 4.4919710449023695e-06, "loss": 0.3653818964958191, "step": 1863 }, { "epoch": 0.48390446521287644, "grad_norm": 7.055344104766846, "learning_rate": 4.491372133495021e-06, "loss": 0.4607293903827667, "step": 1864 }, { "epoch": 0.48416407061266875, "grad_norm": 7.037286758422852, "learning_rate": 4.49077291425295e-06, "loss": 0.46678242087364197, "step": 1865 }, { "epoch": 0.48442367601246106, "grad_norm": 5.722858428955078, "learning_rate": 4.490173387282087e-06, "loss": 0.3923274874687195, "step": 1866 }, { "epoch": 0.48468328141225336, "grad_norm": 3.7899084091186523, "learning_rate": 4.489573552688414e-06, "loss": 0.29360997676849365, "step": 1867 }, { "epoch": 0.48494288681204567, "grad_norm": 2.6803324222564697, "learning_rate": 4.488973410577968e-06, "loss": 0.3776654303073883, "step": 1868 }, { "epoch": 0.48520249221183803, "grad_norm": 4.9399309158325195, "learning_rate": 4.48837296105684e-06, "loss": 0.3501552641391754, "step": 1869 }, { "epoch": 0.48546209761163034, "grad_norm": 4.721640110015869, "learning_rate": 4.4877722042311765e-06, "loss": 0.37861406803131104, "step": 1870 }, { "epoch": 0.48572170301142265, "grad_norm": 4.537386417388916, "learning_rate": 4.487171140207176e-06, "loss": 0.3811799883842468, "step": 1871 }, { "epoch": 0.48598130841121495, "grad_norm": 5.596259593963623, "learning_rate": 4.4865697690910945e-06, "loss": 0.4072147607803345, "step": 1872 }, { "epoch": 0.48624091381100726, "grad_norm": 4.7397379875183105, "learning_rate": 4.48596809098924e-06, "loss": 0.3917029798030853, "step": 1873 }, { "epoch": 0.48650051921079956, "grad_norm": 3.0772452354431152, "learning_rate": 4.485366106007975e-06, "loss": 0.37481987476348877, "step": 1874 }, { "epoch": 0.4867601246105919, "grad_norm": 5.2757487297058105, "learning_rate": 4.484763814253717e-06, "loss": 0.41819000244140625, "step": 1875 }, { "epoch": 0.48701973001038423, "grad_norm": 3.322463274002075, "learning_rate": 4.484161215832938e-06, "loss": 0.3419565260410309, "step": 1876 }, { "epoch": 0.48727933541017654, "grad_norm": 9.27294921875, "learning_rate": 4.483558310852163e-06, "loss": 0.4135415852069855, "step": 1877 }, { "epoch": 0.48753894080996885, "grad_norm": 7.977225303649902, "learning_rate": 4.482955099417971e-06, "loss": 0.28678616881370544, "step": 1878 }, { "epoch": 0.48779854620976115, "grad_norm": 4.452655792236328, "learning_rate": 4.482351581636998e-06, "loss": 0.23471656441688538, "step": 1879 }, { "epoch": 0.48805815160955346, "grad_norm": 5.115882396697998, "learning_rate": 4.48174775761593e-06, "loss": 0.3474251627922058, "step": 1880 }, { "epoch": 0.4883177570093458, "grad_norm": 5.545967102050781, "learning_rate": 4.48114362746151e-06, "loss": 0.4192138910293579, "step": 1881 }, { "epoch": 0.4885773624091381, "grad_norm": 5.105234146118164, "learning_rate": 4.4805391912805366e-06, "loss": 0.3626374900341034, "step": 1882 }, { "epoch": 0.48883696780893043, "grad_norm": 3.2885046005249023, "learning_rate": 4.4799344491798564e-06, "loss": 0.3751143217086792, "step": 1883 }, { "epoch": 0.48909657320872274, "grad_norm": 8.162425994873047, "learning_rate": 4.4793294012663765e-06, "loss": 0.5013832449913025, "step": 1884 }, { "epoch": 0.48935617860851505, "grad_norm": 5.171310901641846, "learning_rate": 4.478724047647054e-06, "loss": 0.4041452407836914, "step": 1885 }, { "epoch": 0.48961578400830735, "grad_norm": 6.035690784454346, "learning_rate": 4.478118388428904e-06, "loss": 0.3728836178779602, "step": 1886 }, { "epoch": 0.4898753894080997, "grad_norm": 2.745694637298584, "learning_rate": 4.47751242371899e-06, "loss": 0.36866211891174316, "step": 1887 }, { "epoch": 0.490134994807892, "grad_norm": 2.5883545875549316, "learning_rate": 4.476906153624435e-06, "loss": 0.31704646348953247, "step": 1888 }, { "epoch": 0.49039460020768433, "grad_norm": 5.016200542449951, "learning_rate": 4.476299578252414e-06, "loss": 0.4018712639808655, "step": 1889 }, { "epoch": 0.49065420560747663, "grad_norm": 5.522490501403809, "learning_rate": 4.475692697710153e-06, "loss": 0.38290220499038696, "step": 1890 }, { "epoch": 0.49091381100726894, "grad_norm": 6.03836727142334, "learning_rate": 4.475085512104937e-06, "loss": 0.36105644702911377, "step": 1891 }, { "epoch": 0.49117341640706125, "grad_norm": 6.320696830749512, "learning_rate": 4.474478021544102e-06, "loss": 0.4164298176765442, "step": 1892 }, { "epoch": 0.4914330218068536, "grad_norm": 3.110934019088745, "learning_rate": 4.473870226135036e-06, "loss": 0.4142749607563019, "step": 1893 }, { "epoch": 0.4916926272066459, "grad_norm": 4.42419958114624, "learning_rate": 4.473262125985188e-06, "loss": 0.3971281051635742, "step": 1894 }, { "epoch": 0.4919522326064382, "grad_norm": 4.369949817657471, "learning_rate": 4.472653721202052e-06, "loss": 0.376809686422348, "step": 1895 }, { "epoch": 0.49221183800623053, "grad_norm": 6.555181503295898, "learning_rate": 4.472045011893182e-06, "loss": 0.4358724355697632, "step": 1896 }, { "epoch": 0.49247144340602284, "grad_norm": 2.350980043411255, "learning_rate": 4.471435998166185e-06, "loss": 0.36224472522735596, "step": 1897 }, { "epoch": 0.49273104880581514, "grad_norm": 2.333641290664673, "learning_rate": 4.470826680128717e-06, "loss": 0.37753790616989136, "step": 1898 }, { "epoch": 0.4929906542056075, "grad_norm": 4.173916816711426, "learning_rate": 4.470217057888495e-06, "loss": 0.3874945044517517, "step": 1899 }, { "epoch": 0.4932502596053998, "grad_norm": 3.5427651405334473, "learning_rate": 4.469607131553284e-06, "loss": 0.38490378856658936, "step": 1900 }, { "epoch": 0.4935098650051921, "grad_norm": 5.079545974731445, "learning_rate": 4.468996901230907e-06, "loss": 0.32168489694595337, "step": 1901 }, { "epoch": 0.4937694704049844, "grad_norm": 6.1461334228515625, "learning_rate": 4.468386367029236e-06, "loss": 0.4531917870044708, "step": 1902 }, { "epoch": 0.49402907580477673, "grad_norm": 4.588400363922119, "learning_rate": 4.467775529056203e-06, "loss": 0.33901455998420715, "step": 1903 }, { "epoch": 0.49428868120456904, "grad_norm": 5.698703765869141, "learning_rate": 4.467164387419787e-06, "loss": 0.25935372710227966, "step": 1904 }, { "epoch": 0.4945482866043614, "grad_norm": 2.6975419521331787, "learning_rate": 4.466552942228026e-06, "loss": 0.34646010398864746, "step": 1905 }, { "epoch": 0.4948078920041537, "grad_norm": 3.534047842025757, "learning_rate": 4.465941193589008e-06, "loss": 0.3172299265861511, "step": 1906 }, { "epoch": 0.495067497403946, "grad_norm": 8.11964225769043, "learning_rate": 4.465329141610877e-06, "loss": 0.38826605677604675, "step": 1907 }, { "epoch": 0.4953271028037383, "grad_norm": 6.595650672912598, "learning_rate": 4.46471678640183e-06, "loss": 0.3705235719680786, "step": 1908 }, { "epoch": 0.4955867082035306, "grad_norm": 8.60014533996582, "learning_rate": 4.4641041280701164e-06, "loss": 0.35034817457199097, "step": 1909 }, { "epoch": 0.49584631360332293, "grad_norm": 3.767404079437256, "learning_rate": 4.463491166724041e-06, "loss": 0.376486599445343, "step": 1910 }, { "epoch": 0.4961059190031153, "grad_norm": 3.84403920173645, "learning_rate": 4.462877902471961e-06, "loss": 0.3232845366001129, "step": 1911 }, { "epoch": 0.4963655244029076, "grad_norm": 4.229501724243164, "learning_rate": 4.462264335422288e-06, "loss": 0.32502996921539307, "step": 1912 }, { "epoch": 0.4966251298026999, "grad_norm": 4.774477005004883, "learning_rate": 4.4616504656834855e-06, "loss": 0.3366822600364685, "step": 1913 }, { "epoch": 0.4968847352024922, "grad_norm": 4.1695876121521, "learning_rate": 4.461036293364073e-06, "loss": 0.36175981163978577, "step": 1914 }, { "epoch": 0.4971443406022845, "grad_norm": 6.993171691894531, "learning_rate": 4.46042181857262e-06, "loss": 0.3016126751899719, "step": 1915 }, { "epoch": 0.4974039460020768, "grad_norm": 4.364332675933838, "learning_rate": 4.459807041417755e-06, "loss": 0.3636191487312317, "step": 1916 }, { "epoch": 0.4976635514018692, "grad_norm": 4.222325801849365, "learning_rate": 4.4591919620081526e-06, "loss": 0.36347082257270813, "step": 1917 }, { "epoch": 0.4979231568016615, "grad_norm": 5.871955394744873, "learning_rate": 4.458576580452547e-06, "loss": 0.3359036445617676, "step": 1918 }, { "epoch": 0.4981827622014538, "grad_norm": 2.413363218307495, "learning_rate": 4.457960896859724e-06, "loss": 0.3385484516620636, "step": 1919 }, { "epoch": 0.4984423676012461, "grad_norm": 4.9028143882751465, "learning_rate": 4.4573449113385214e-06, "loss": 0.3714197278022766, "step": 1920 }, { "epoch": 0.4987019730010384, "grad_norm": 5.246308326721191, "learning_rate": 4.456728623997831e-06, "loss": 0.40629976987838745, "step": 1921 }, { "epoch": 0.4989615784008307, "grad_norm": 3.06679105758667, "learning_rate": 4.456112034946599e-06, "loss": 0.3637463450431824, "step": 1922 }, { "epoch": 0.4992211838006231, "grad_norm": 3.5820112228393555, "learning_rate": 4.455495144293824e-06, "loss": 0.34824854135513306, "step": 1923 }, { "epoch": 0.4994807892004154, "grad_norm": 5.060879230499268, "learning_rate": 4.454877952148558e-06, "loss": 0.4278174340724945, "step": 1924 }, { "epoch": 0.4997403946002077, "grad_norm": 4.115777015686035, "learning_rate": 4.454260458619907e-06, "loss": 0.3985026776790619, "step": 1925 }, { "epoch": 0.5, "grad_norm": 2.623448133468628, "learning_rate": 4.45364266381703e-06, "loss": 0.3360379934310913, "step": 1926 }, { "epoch": 0.5002596053997923, "grad_norm": 4.8149333000183105, "learning_rate": 4.453024567849136e-06, "loss": 0.3756774663925171, "step": 1927 }, { "epoch": 0.5005192107995846, "grad_norm": 5.344857215881348, "learning_rate": 4.452406170825494e-06, "loss": 0.37852078676223755, "step": 1928 }, { "epoch": 0.5007788161993769, "grad_norm": 3.208264112472534, "learning_rate": 4.451787472855421e-06, "loss": 0.3340098261833191, "step": 1929 }, { "epoch": 0.5010384215991692, "grad_norm": 4.433973789215088, "learning_rate": 4.451168474048288e-06, "loss": 0.418582558631897, "step": 1930 }, { "epoch": 0.5012980269989615, "grad_norm": 5.737292289733887, "learning_rate": 4.450549174513521e-06, "loss": 0.46712368726730347, "step": 1931 }, { "epoch": 0.5015576323987538, "grad_norm": 5.172119140625, "learning_rate": 4.449929574360597e-06, "loss": 0.487331748008728, "step": 1932 }, { "epoch": 0.5018172377985463, "grad_norm": 5.684152126312256, "learning_rate": 4.4493096736990476e-06, "loss": 0.28992515802383423, "step": 1933 }, { "epoch": 0.5020768431983386, "grad_norm": 3.6061580181121826, "learning_rate": 4.448689472638457e-06, "loss": 0.34542644023895264, "step": 1934 }, { "epoch": 0.5023364485981309, "grad_norm": 5.027502059936523, "learning_rate": 4.448068971288462e-06, "loss": 0.3790895640850067, "step": 1935 }, { "epoch": 0.5025960539979232, "grad_norm": 3.3072569370269775, "learning_rate": 4.447448169758754e-06, "loss": 0.3164469599723816, "step": 1936 }, { "epoch": 0.5028556593977155, "grad_norm": 3.6427972316741943, "learning_rate": 4.446827068159076e-06, "loss": 0.32964280247688293, "step": 1937 }, { "epoch": 0.5031152647975078, "grad_norm": 6.848123550415039, "learning_rate": 4.446205666599224e-06, "loss": 0.41940435767173767, "step": 1938 }, { "epoch": 0.5033748701973001, "grad_norm": 5.778529167175293, "learning_rate": 4.445583965189049e-06, "loss": 0.405031681060791, "step": 1939 }, { "epoch": 0.5036344755970924, "grad_norm": 3.086165189743042, "learning_rate": 4.444961964038452e-06, "loss": 0.3429999351501465, "step": 1940 }, { "epoch": 0.5038940809968847, "grad_norm": 7.3324408531188965, "learning_rate": 4.444339663257389e-06, "loss": 0.37677252292633057, "step": 1941 }, { "epoch": 0.504153686396677, "grad_norm": 6.199395179748535, "learning_rate": 4.443717062955869e-06, "loss": 0.4110206663608551, "step": 1942 }, { "epoch": 0.5044132917964693, "grad_norm": 3.1755998134613037, "learning_rate": 4.443094163243954e-06, "loss": 0.3242473006248474, "step": 1943 }, { "epoch": 0.5046728971962616, "grad_norm": 7.988744735717773, "learning_rate": 4.442470964231758e-06, "loss": 0.3642529845237732, "step": 1944 }, { "epoch": 0.504932502596054, "grad_norm": 3.766812801361084, "learning_rate": 4.441847466029447e-06, "loss": 0.33931517601013184, "step": 1945 }, { "epoch": 0.5051921079958464, "grad_norm": 6.374563217163086, "learning_rate": 4.441223668747241e-06, "loss": 0.33477258682250977, "step": 1946 }, { "epoch": 0.5054517133956387, "grad_norm": 2.814096212387085, "learning_rate": 4.440599572495416e-06, "loss": 0.3507235050201416, "step": 1947 }, { "epoch": 0.505711318795431, "grad_norm": 3.810211658477783, "learning_rate": 4.439975177384296e-06, "loss": 0.3468930125236511, "step": 1948 }, { "epoch": 0.5059709241952233, "grad_norm": 3.5133445262908936, "learning_rate": 4.439350483524259e-06, "loss": 0.32374560832977295, "step": 1949 }, { "epoch": 0.5062305295950156, "grad_norm": 4.441192626953125, "learning_rate": 4.4387254910257386e-06, "loss": 0.3208555281162262, "step": 1950 }, { "epoch": 0.5064901349948079, "grad_norm": 5.5488386154174805, "learning_rate": 4.438100199999217e-06, "loss": 0.2910914123058319, "step": 1951 }, { "epoch": 0.5067497403946002, "grad_norm": 5.051970958709717, "learning_rate": 4.437474610555234e-06, "loss": 0.38787543773651123, "step": 1952 }, { "epoch": 0.5070093457943925, "grad_norm": 4.0375471115112305, "learning_rate": 4.436848722804376e-06, "loss": 0.3566349744796753, "step": 1953 }, { "epoch": 0.5072689511941848, "grad_norm": 5.516851425170898, "learning_rate": 4.436222536857289e-06, "loss": 0.3576899766921997, "step": 1954 }, { "epoch": 0.5075285565939771, "grad_norm": 5.088945388793945, "learning_rate": 4.435596052824666e-06, "loss": 0.3113366365432739, "step": 1955 }, { "epoch": 0.5077881619937694, "grad_norm": 6.940811634063721, "learning_rate": 4.434969270817257e-06, "loss": 0.34790146350860596, "step": 1956 }, { "epoch": 0.5080477673935618, "grad_norm": 5.185585021972656, "learning_rate": 4.4343421909458605e-06, "loss": 0.4289481043815613, "step": 1957 }, { "epoch": 0.5083073727933541, "grad_norm": 8.651786804199219, "learning_rate": 4.433714813321331e-06, "loss": 0.43139171600341797, "step": 1958 }, { "epoch": 0.5085669781931464, "grad_norm": 3.256584882736206, "learning_rate": 4.433087138054575e-06, "loss": 0.3026362657546997, "step": 1959 }, { "epoch": 0.5088265835929388, "grad_norm": 6.6610612869262695, "learning_rate": 4.4324591652565505e-06, "loss": 0.4066344201564789, "step": 1960 }, { "epoch": 0.5090861889927311, "grad_norm": 7.335511684417725, "learning_rate": 4.4318308950382685e-06, "loss": 0.42299985885620117, "step": 1961 }, { "epoch": 0.5093457943925234, "grad_norm": 2.9522218704223633, "learning_rate": 4.431202327510793e-06, "loss": 0.3467184901237488, "step": 1962 }, { "epoch": 0.5096053997923157, "grad_norm": 5.220940589904785, "learning_rate": 4.43057346278524e-06, "loss": 0.3487967848777771, "step": 1963 }, { "epoch": 0.509865005192108, "grad_norm": 5.289552211761475, "learning_rate": 4.42994430097278e-06, "loss": 0.3604798913002014, "step": 1964 }, { "epoch": 0.5101246105919003, "grad_norm": 7.000670909881592, "learning_rate": 4.429314842184632e-06, "loss": 0.2700226306915283, "step": 1965 }, { "epoch": 0.5103842159916926, "grad_norm": 5.655209064483643, "learning_rate": 4.428685086532072e-06, "loss": 0.4047335386276245, "step": 1966 }, { "epoch": 0.5106438213914849, "grad_norm": 6.462539196014404, "learning_rate": 4.428055034126426e-06, "loss": 0.37972620129585266, "step": 1967 }, { "epoch": 0.5109034267912772, "grad_norm": 6.999260902404785, "learning_rate": 4.427424685079071e-06, "loss": 0.38072526454925537, "step": 1968 }, { "epoch": 0.5111630321910696, "grad_norm": 6.059019565582275, "learning_rate": 4.42679403950144e-06, "loss": 0.29097050428390503, "step": 1969 }, { "epoch": 0.5114226375908619, "grad_norm": 5.1895341873168945, "learning_rate": 4.426163097505017e-06, "loss": 0.35771432518959045, "step": 1970 }, { "epoch": 0.5116822429906542, "grad_norm": 2.5761687755584717, "learning_rate": 4.425531859201337e-06, "loss": 0.3637140095233917, "step": 1971 }, { "epoch": 0.5119418483904465, "grad_norm": 3.1125457286834717, "learning_rate": 4.424900324701989e-06, "loss": 0.3253420293331146, "step": 1972 }, { "epoch": 0.5122014537902388, "grad_norm": 3.429851770401001, "learning_rate": 4.424268494118613e-06, "loss": 0.35952508449554443, "step": 1973 }, { "epoch": 0.5124610591900312, "grad_norm": 4.395293712615967, "learning_rate": 4.423636367562903e-06, "loss": 0.35921624302864075, "step": 1974 }, { "epoch": 0.5127206645898235, "grad_norm": 4.051858901977539, "learning_rate": 4.423003945146605e-06, "loss": 0.31560760736465454, "step": 1975 }, { "epoch": 0.5129802699896158, "grad_norm": 7.611374855041504, "learning_rate": 4.422371226981517e-06, "loss": 0.3417307734489441, "step": 1976 }, { "epoch": 0.5132398753894081, "grad_norm": 6.370949745178223, "learning_rate": 4.421738213179487e-06, "loss": 0.37608039379119873, "step": 1977 }, { "epoch": 0.5134994807892004, "grad_norm": 4.681211471557617, "learning_rate": 4.421104903852419e-06, "loss": 0.3829312324523926, "step": 1978 }, { "epoch": 0.5137590861889927, "grad_norm": 4.553125858306885, "learning_rate": 4.420471299112267e-06, "loss": 0.368716835975647, "step": 1979 }, { "epoch": 0.514018691588785, "grad_norm": 3.642923593521118, "learning_rate": 4.419837399071038e-06, "loss": 0.32017460465431213, "step": 1980 }, { "epoch": 0.5142782969885774, "grad_norm": 3.672489643096924, "learning_rate": 4.419203203840792e-06, "loss": 0.3221360445022583, "step": 1981 }, { "epoch": 0.5145379023883697, "grad_norm": 4.069151878356934, "learning_rate": 4.418568713533638e-06, "loss": 0.3520399332046509, "step": 1982 }, { "epoch": 0.514797507788162, "grad_norm": 5.1574811935424805, "learning_rate": 4.4179339282617416e-06, "loss": 0.4124201536178589, "step": 1983 }, { "epoch": 0.5150571131879543, "grad_norm": 4.992115020751953, "learning_rate": 4.417298848137317e-06, "loss": 0.2686768174171448, "step": 1984 }, { "epoch": 0.5153167185877466, "grad_norm": 4.311779022216797, "learning_rate": 4.416663473272632e-06, "loss": 0.4003753960132599, "step": 1985 }, { "epoch": 0.5155763239875389, "grad_norm": 7.8158745765686035, "learning_rate": 4.416027803780006e-06, "loss": 0.3805543780326843, "step": 1986 }, { "epoch": 0.5158359293873312, "grad_norm": 4.521412372589111, "learning_rate": 4.415391839771812e-06, "loss": 0.37581950426101685, "step": 1987 }, { "epoch": 0.5160955347871236, "grad_norm": 3.748642683029175, "learning_rate": 4.414755581360473e-06, "loss": 0.36569392681121826, "step": 1988 }, { "epoch": 0.5163551401869159, "grad_norm": 3.998274326324463, "learning_rate": 4.414119028658465e-06, "loss": 0.35954368114471436, "step": 1989 }, { "epoch": 0.5166147455867082, "grad_norm": 6.2244744300842285, "learning_rate": 4.4134821817783155e-06, "loss": 0.35551688075065613, "step": 1990 }, { "epoch": 0.5168743509865005, "grad_norm": 4.754053592681885, "learning_rate": 4.4128450408326065e-06, "loss": 0.40480583906173706, "step": 1991 }, { "epoch": 0.5171339563862928, "grad_norm": 6.2698822021484375, "learning_rate": 4.412207605933967e-06, "loss": 0.3359913229942322, "step": 1992 }, { "epoch": 0.5173935617860852, "grad_norm": 5.507514953613281, "learning_rate": 4.411569877195082e-06, "loss": 0.34133219718933105, "step": 1993 }, { "epoch": 0.5176531671858775, "grad_norm": 2.3714921474456787, "learning_rate": 4.410931854728689e-06, "loss": 0.35017478466033936, "step": 1994 }, { "epoch": 0.5179127725856698, "grad_norm": 4.579190731048584, "learning_rate": 4.410293538647573e-06, "loss": 0.36700913310050964, "step": 1995 }, { "epoch": 0.5181723779854621, "grad_norm": 5.238192081451416, "learning_rate": 4.409654929064575e-06, "loss": 0.33494096994400024, "step": 1996 }, { "epoch": 0.5184319833852544, "grad_norm": 3.3897576332092285, "learning_rate": 4.4090160260925874e-06, "loss": 0.3472450375556946, "step": 1997 }, { "epoch": 0.5186915887850467, "grad_norm": 2.9774553775787354, "learning_rate": 4.408376829844553e-06, "loss": 0.3742300271987915, "step": 1998 }, { "epoch": 0.518951194184839, "grad_norm": 9.018415451049805, "learning_rate": 4.407737340433466e-06, "loss": 0.419670432806015, "step": 1999 }, { "epoch": 0.5192107995846313, "grad_norm": 6.671173095703125, "learning_rate": 4.407097557972375e-06, "loss": 0.3794372081756592, "step": 2000 }, { "epoch": 0.5194704049844237, "grad_norm": 5.294092178344727, "learning_rate": 4.406457482574379e-06, "loss": 0.3789592683315277, "step": 2001 }, { "epoch": 0.519730010384216, "grad_norm": 8.247987747192383, "learning_rate": 4.405817114352627e-06, "loss": 0.4169115424156189, "step": 2002 }, { "epoch": 0.5199896157840083, "grad_norm": 8.301918029785156, "learning_rate": 4.405176453420322e-06, "loss": 0.38702839612960815, "step": 2003 }, { "epoch": 0.5202492211838006, "grad_norm": 5.143083095550537, "learning_rate": 4.4045354998907196e-06, "loss": 0.3735384941101074, "step": 2004 }, { "epoch": 0.520508826583593, "grad_norm": 5.316050052642822, "learning_rate": 4.4038942538771235e-06, "loss": 0.3105137348175049, "step": 2005 }, { "epoch": 0.5207684319833853, "grad_norm": 3.7019553184509277, "learning_rate": 4.403252715492893e-06, "loss": 0.327844500541687, "step": 2006 }, { "epoch": 0.5210280373831776, "grad_norm": 3.4262146949768066, "learning_rate": 4.402610884851437e-06, "loss": 0.31415653228759766, "step": 2007 }, { "epoch": 0.5212876427829699, "grad_norm": 3.81923508644104, "learning_rate": 4.401968762066216e-06, "loss": 0.31928879022598267, "step": 2008 }, { "epoch": 0.5215472481827622, "grad_norm": 6.625582218170166, "learning_rate": 4.4013263472507434e-06, "loss": 0.3208429217338562, "step": 2009 }, { "epoch": 0.5218068535825545, "grad_norm": 4.447213172912598, "learning_rate": 4.400683640518583e-06, "loss": 0.3537136912345886, "step": 2010 }, { "epoch": 0.5220664589823468, "grad_norm": 3.107327699661255, "learning_rate": 4.40004064198335e-06, "loss": 0.34130579233169556, "step": 2011 }, { "epoch": 0.5223260643821391, "grad_norm": 5.664844036102295, "learning_rate": 4.399397351758714e-06, "loss": 0.42261838912963867, "step": 2012 }, { "epoch": 0.5225856697819314, "grad_norm": 7.917862892150879, "learning_rate": 4.39875376995839e-06, "loss": 0.37030094861984253, "step": 2013 }, { "epoch": 0.5228452751817237, "grad_norm": 2.854414939880371, "learning_rate": 4.3981098966961524e-06, "loss": 0.3397887051105499, "step": 2014 }, { "epoch": 0.523104880581516, "grad_norm": 6.465794563293457, "learning_rate": 4.397465732085822e-06, "loss": 0.4268699884414673, "step": 2015 }, { "epoch": 0.5233644859813084, "grad_norm": 7.792341232299805, "learning_rate": 4.396821276241272e-06, "loss": 0.3390604257583618, "step": 2016 }, { "epoch": 0.5236240913811008, "grad_norm": 5.010791778564453, "learning_rate": 4.396176529276426e-06, "loss": 0.39939725399017334, "step": 2017 }, { "epoch": 0.5238836967808931, "grad_norm": 7.621373176574707, "learning_rate": 4.3955314913052636e-06, "loss": 0.312857985496521, "step": 2018 }, { "epoch": 0.5241433021806854, "grad_norm": 8.880678176879883, "learning_rate": 4.394886162441811e-06, "loss": 0.2898547947406769, "step": 2019 }, { "epoch": 0.5244029075804777, "grad_norm": 6.5331549644470215, "learning_rate": 4.394240542800148e-06, "loss": 0.35336941480636597, "step": 2020 }, { "epoch": 0.52466251298027, "grad_norm": 3.147087812423706, "learning_rate": 4.393594632494404e-06, "loss": 0.3359161615371704, "step": 2021 }, { "epoch": 0.5249221183800623, "grad_norm": 3.5783350467681885, "learning_rate": 4.3929484316387636e-06, "loss": 0.37141069769859314, "step": 2022 }, { "epoch": 0.5251817237798546, "grad_norm": 7.482142925262451, "learning_rate": 4.392301940347458e-06, "loss": 0.30202987790107727, "step": 2023 }, { "epoch": 0.5254413291796469, "grad_norm": 5.146938800811768, "learning_rate": 4.391655158734774e-06, "loss": 0.4082491099834442, "step": 2024 }, { "epoch": 0.5257009345794392, "grad_norm": 8.241232872009277, "learning_rate": 4.391008086915046e-06, "loss": 0.4237692356109619, "step": 2025 }, { "epoch": 0.5259605399792315, "grad_norm": 2.2726829051971436, "learning_rate": 4.390360725002663e-06, "loss": 0.3247901201248169, "step": 2026 }, { "epoch": 0.5262201453790238, "grad_norm": 3.204157590866089, "learning_rate": 4.389713073112063e-06, "loss": 0.33690524101257324, "step": 2027 }, { "epoch": 0.5264797507788161, "grad_norm": 7.144014835357666, "learning_rate": 4.389065131357736e-06, "loss": 0.39538395404815674, "step": 2028 }, { "epoch": 0.5267393561786086, "grad_norm": 3.4452903270721436, "learning_rate": 4.388416899854224e-06, "loss": 0.3683183193206787, "step": 2029 }, { "epoch": 0.5269989615784009, "grad_norm": 4.539107322692871, "learning_rate": 4.387768378716117e-06, "loss": 0.37892869114875793, "step": 2030 }, { "epoch": 0.5272585669781932, "grad_norm": 1.825668215751648, "learning_rate": 4.387119568058063e-06, "loss": 0.3573235273361206, "step": 2031 }, { "epoch": 0.5275181723779855, "grad_norm": 7.396895408630371, "learning_rate": 4.386470467994753e-06, "loss": 0.24551689624786377, "step": 2032 }, { "epoch": 0.5277777777777778, "grad_norm": 5.738333225250244, "learning_rate": 4.385821078640935e-06, "loss": 0.3970180153846741, "step": 2033 }, { "epoch": 0.5280373831775701, "grad_norm": 3.1996285915374756, "learning_rate": 4.385171400111405e-06, "loss": 0.31729984283447266, "step": 2034 }, { "epoch": 0.5282969885773624, "grad_norm": 3.5303447246551514, "learning_rate": 4.3845214325210124e-06, "loss": 0.3378658890724182, "step": 2035 }, { "epoch": 0.5285565939771547, "grad_norm": 2.0657169818878174, "learning_rate": 4.383871175984656e-06, "loss": 0.3351707458496094, "step": 2036 }, { "epoch": 0.528816199376947, "grad_norm": 7.338043689727783, "learning_rate": 4.383220630617287e-06, "loss": 0.34959107637405396, "step": 2037 }, { "epoch": 0.5290758047767393, "grad_norm": 4.335491180419922, "learning_rate": 4.3825697965339055e-06, "loss": 0.37863627076148987, "step": 2038 }, { "epoch": 0.5293354101765316, "grad_norm": 4.026844501495361, "learning_rate": 4.3819186738495645e-06, "loss": 0.3731665313243866, "step": 2039 }, { "epoch": 0.5295950155763239, "grad_norm": 2.054842948913574, "learning_rate": 4.381267262679369e-06, "loss": 0.3590086102485657, "step": 2040 }, { "epoch": 0.5298546209761164, "grad_norm": 3.377450942993164, "learning_rate": 4.380615563138472e-06, "loss": 0.36255431175231934, "step": 2041 }, { "epoch": 0.5301142263759087, "grad_norm": 6.5662617683410645, "learning_rate": 4.3799635753420794e-06, "loss": 0.3129930794239044, "step": 2042 }, { "epoch": 0.530373831775701, "grad_norm": 3.7609848976135254, "learning_rate": 4.379311299405449e-06, "loss": 0.3245197832584381, "step": 2043 }, { "epoch": 0.5306334371754933, "grad_norm": 4.317520618438721, "learning_rate": 4.378658735443886e-06, "loss": 0.33559176325798035, "step": 2044 }, { "epoch": 0.5308930425752856, "grad_norm": 7.4778571128845215, "learning_rate": 4.37800588357275e-06, "loss": 0.3777024745941162, "step": 2045 }, { "epoch": 0.5311526479750779, "grad_norm": 4.189903736114502, "learning_rate": 4.37735274390745e-06, "loss": 0.38522714376449585, "step": 2046 }, { "epoch": 0.5314122533748702, "grad_norm": 5.460587024688721, "learning_rate": 4.376699316563447e-06, "loss": 0.296634316444397, "step": 2047 }, { "epoch": 0.5316718587746625, "grad_norm": 5.572330951690674, "learning_rate": 4.3760456016562505e-06, "loss": 0.29773586988449097, "step": 2048 }, { "epoch": 0.5319314641744548, "grad_norm": 3.055250406265259, "learning_rate": 4.375391599301424e-06, "loss": 0.29645705223083496, "step": 2049 }, { "epoch": 0.5321910695742471, "grad_norm": 2.8565495014190674, "learning_rate": 4.374737309614579e-06, "loss": 0.3579908013343811, "step": 2050 }, { "epoch": 0.5324506749740394, "grad_norm": 4.027129173278809, "learning_rate": 4.374082732711379e-06, "loss": 0.34813207387924194, "step": 2051 }, { "epoch": 0.5327102803738317, "grad_norm": 2.695650577545166, "learning_rate": 4.373427868707539e-06, "loss": 0.31385987997055054, "step": 2052 }, { "epoch": 0.5329698857736241, "grad_norm": 6.7079973220825195, "learning_rate": 4.3727727177188226e-06, "loss": 0.30884259939193726, "step": 2053 }, { "epoch": 0.5332294911734164, "grad_norm": 6.3703155517578125, "learning_rate": 4.372117279861047e-06, "loss": 0.26691269874572754, "step": 2054 }, { "epoch": 0.5334890965732088, "grad_norm": 6.7666015625, "learning_rate": 4.371461555250077e-06, "loss": 0.3069170117378235, "step": 2055 }, { "epoch": 0.5337487019730011, "grad_norm": 6.065546989440918, "learning_rate": 4.370805544001831e-06, "loss": 0.31884047389030457, "step": 2056 }, { "epoch": 0.5340083073727934, "grad_norm": 4.595121383666992, "learning_rate": 4.370149246232277e-06, "loss": 0.34332582354545593, "step": 2057 }, { "epoch": 0.5342679127725857, "grad_norm": 4.004138469696045, "learning_rate": 4.3694926620574315e-06, "loss": 0.3581084609031677, "step": 2058 }, { "epoch": 0.534527518172378, "grad_norm": 7.87822151184082, "learning_rate": 4.3688357915933656e-06, "loss": 0.3904057741165161, "step": 2059 }, { "epoch": 0.5347871235721703, "grad_norm": 6.487884998321533, "learning_rate": 4.368178634956199e-06, "loss": 0.41916757822036743, "step": 2060 }, { "epoch": 0.5350467289719626, "grad_norm": 6.906710147857666, "learning_rate": 4.3675211922621e-06, "loss": 0.33651086688041687, "step": 2061 }, { "epoch": 0.5353063343717549, "grad_norm": 6.453043460845947, "learning_rate": 4.36686346362729e-06, "loss": 0.3111308813095093, "step": 2062 }, { "epoch": 0.5355659397715472, "grad_norm": 3.4768033027648926, "learning_rate": 4.366205449168042e-06, "loss": 0.31533631682395935, "step": 2063 }, { "epoch": 0.5358255451713395, "grad_norm": 2.5885977745056152, "learning_rate": 4.3655471490006766e-06, "loss": 0.3089366555213928, "step": 2064 }, { "epoch": 0.5360851505711319, "grad_norm": 2.368610143661499, "learning_rate": 4.364888563241566e-06, "loss": 0.3499771058559418, "step": 2065 }, { "epoch": 0.5363447559709242, "grad_norm": 3.108215570449829, "learning_rate": 4.364229692007134e-06, "loss": 0.3859386444091797, "step": 2066 }, { "epoch": 0.5366043613707165, "grad_norm": 4.666975021362305, "learning_rate": 4.363570535413852e-06, "loss": 0.32247471809387207, "step": 2067 }, { "epoch": 0.5368639667705088, "grad_norm": 7.18953800201416, "learning_rate": 4.362911093578246e-06, "loss": 0.33092522621154785, "step": 2068 }, { "epoch": 0.5371235721703012, "grad_norm": 6.450816631317139, "learning_rate": 4.362251366616891e-06, "loss": 0.44598156213760376, "step": 2069 }, { "epoch": 0.5373831775700935, "grad_norm": 5.850311756134033, "learning_rate": 4.361591354646409e-06, "loss": 0.38961148262023926, "step": 2070 }, { "epoch": 0.5376427829698858, "grad_norm": 6.17826509475708, "learning_rate": 4.360931057783475e-06, "loss": 0.3630654215812683, "step": 2071 }, { "epoch": 0.5379023883696781, "grad_norm": 6.423355579376221, "learning_rate": 4.360270476144817e-06, "loss": 0.31982260942459106, "step": 2072 }, { "epoch": 0.5381619937694704, "grad_norm": 4.479666709899902, "learning_rate": 4.359609609847208e-06, "loss": 0.34807288646698, "step": 2073 }, { "epoch": 0.5384215991692627, "grad_norm": 4.122926712036133, "learning_rate": 4.358948459007475e-06, "loss": 0.33479446172714233, "step": 2074 }, { "epoch": 0.538681204569055, "grad_norm": 8.630376815795898, "learning_rate": 4.358287023742495e-06, "loss": 0.27924689650535583, "step": 2075 }, { "epoch": 0.5389408099688473, "grad_norm": 2.1621532440185547, "learning_rate": 4.357625304169194e-06, "loss": 0.36899030208587646, "step": 2076 }, { "epoch": 0.5392004153686397, "grad_norm": 2.718528985977173, "learning_rate": 4.356963300404549e-06, "loss": 0.30069857835769653, "step": 2077 }, { "epoch": 0.539460020768432, "grad_norm": 2.5299532413482666, "learning_rate": 4.356301012565588e-06, "loss": 0.3681168556213379, "step": 2078 }, { "epoch": 0.5397196261682243, "grad_norm": 6.895898818969727, "learning_rate": 4.355638440769385e-06, "loss": 0.3784013092517853, "step": 2079 }, { "epoch": 0.5399792315680166, "grad_norm": 5.210425853729248, "learning_rate": 4.354975585133072e-06, "loss": 0.33362430334091187, "step": 2080 }, { "epoch": 0.5402388369678089, "grad_norm": 5.35524845123291, "learning_rate": 4.354312445773825e-06, "loss": 0.4174221158027649, "step": 2081 }, { "epoch": 0.5404984423676013, "grad_norm": 7.298679351806641, "learning_rate": 4.353649022808869e-06, "loss": 0.41728803515434265, "step": 2082 }, { "epoch": 0.5407580477673936, "grad_norm": 4.352530479431152, "learning_rate": 4.352985316355487e-06, "loss": 0.3940931558609009, "step": 2083 }, { "epoch": 0.5410176531671859, "grad_norm": 3.459419012069702, "learning_rate": 4.3523213265310036e-06, "loss": 0.3095652461051941, "step": 2084 }, { "epoch": 0.5412772585669782, "grad_norm": 3.0011849403381348, "learning_rate": 4.351657053452798e-06, "loss": 0.3906397819519043, "step": 2085 }, { "epoch": 0.5415368639667705, "grad_norm": 8.389422416687012, "learning_rate": 4.350992497238298e-06, "loss": 0.34871846437454224, "step": 2086 }, { "epoch": 0.5417964693665628, "grad_norm": 6.539154529571533, "learning_rate": 4.350327658004983e-06, "loss": 0.36906808614730835, "step": 2087 }, { "epoch": 0.5420560747663551, "grad_norm": 2.7229115962982178, "learning_rate": 4.349662535870381e-06, "loss": 0.3603833317756653, "step": 2088 }, { "epoch": 0.5423156801661475, "grad_norm": 7.260566711425781, "learning_rate": 4.348997130952069e-06, "loss": 0.3915090560913086, "step": 2089 }, { "epoch": 0.5425752855659398, "grad_norm": 6.4790802001953125, "learning_rate": 4.348331443367677e-06, "loss": 0.41589829325675964, "step": 2090 }, { "epoch": 0.5428348909657321, "grad_norm": 2.779294967651367, "learning_rate": 4.3476654732348826e-06, "loss": 0.310865193605423, "step": 2091 }, { "epoch": 0.5430944963655244, "grad_norm": 5.882518291473389, "learning_rate": 4.346999220671414e-06, "loss": 0.41594773530960083, "step": 2092 }, { "epoch": 0.5433541017653167, "grad_norm": 2.480379343032837, "learning_rate": 4.34633268579505e-06, "loss": 0.32980045676231384, "step": 2093 }, { "epoch": 0.543613707165109, "grad_norm": 4.231016159057617, "learning_rate": 4.345665868723618e-06, "loss": 0.3431246280670166, "step": 2094 }, { "epoch": 0.5438733125649013, "grad_norm": 8.24752426147461, "learning_rate": 4.3449987695749964e-06, "loss": 0.28533393144607544, "step": 2095 }, { "epoch": 0.5441329179646937, "grad_norm": 6.681564807891846, "learning_rate": 4.344331388467113e-06, "loss": 0.4016847610473633, "step": 2096 }, { "epoch": 0.544392523364486, "grad_norm": 2.708123207092285, "learning_rate": 4.343663725517946e-06, "loss": 0.35226720571517944, "step": 2097 }, { "epoch": 0.5446521287642783, "grad_norm": 9.11937141418457, "learning_rate": 4.342995780845522e-06, "loss": 0.4638839662075043, "step": 2098 }, { "epoch": 0.5449117341640706, "grad_norm": 11.837984085083008, "learning_rate": 4.342327554567918e-06, "loss": 0.3973182439804077, "step": 2099 }, { "epoch": 0.5451713395638629, "grad_norm": 6.054419040679932, "learning_rate": 4.341659046803263e-06, "loss": 0.38620424270629883, "step": 2100 }, { "epoch": 0.5454309449636553, "grad_norm": 2.714402198791504, "learning_rate": 4.340990257669732e-06, "loss": 0.36258652806282043, "step": 2101 }, { "epoch": 0.5456905503634476, "grad_norm": 4.4136223793029785, "learning_rate": 4.340321187285553e-06, "loss": 0.34993013739585876, "step": 2102 }, { "epoch": 0.5459501557632399, "grad_norm": 7.191802024841309, "learning_rate": 4.339651835769e-06, "loss": 0.3840875029563904, "step": 2103 }, { "epoch": 0.5462097611630322, "grad_norm": 5.149716854095459, "learning_rate": 4.338982203238403e-06, "loss": 0.3629027307033539, "step": 2104 }, { "epoch": 0.5464693665628245, "grad_norm": 7.543644428253174, "learning_rate": 4.338312289812134e-06, "loss": 0.3907088041305542, "step": 2105 }, { "epoch": 0.5467289719626168, "grad_norm": 4.111990928649902, "learning_rate": 4.33764209560862e-06, "loss": 0.41026222705841064, "step": 2106 }, { "epoch": 0.5469885773624091, "grad_norm": 2.774752140045166, "learning_rate": 4.336971620746334e-06, "loss": 0.3242759108543396, "step": 2107 }, { "epoch": 0.5472481827622014, "grad_norm": 4.904356956481934, "learning_rate": 4.336300865343805e-06, "loss": 0.41408079862594604, "step": 2108 }, { "epoch": 0.5475077881619937, "grad_norm": 4.863967418670654, "learning_rate": 4.335629829519602e-06, "loss": 0.361677885055542, "step": 2109 }, { "epoch": 0.547767393561786, "grad_norm": 4.828758239746094, "learning_rate": 4.334958513392353e-06, "loss": 0.35204845666885376, "step": 2110 }, { "epoch": 0.5480269989615784, "grad_norm": 5.274982929229736, "learning_rate": 4.33428691708073e-06, "loss": 0.35363680124282837, "step": 2111 }, { "epoch": 0.5482866043613707, "grad_norm": 7.042477607727051, "learning_rate": 4.333615040703454e-06, "loss": 0.3294186592102051, "step": 2112 }, { "epoch": 0.5485462097611631, "grad_norm": 3.00858998298645, "learning_rate": 4.332942884379299e-06, "loss": 0.3245515823364258, "step": 2113 }, { "epoch": 0.5488058151609554, "grad_norm": 2.619272470474243, "learning_rate": 4.332270448227087e-06, "loss": 0.3216179609298706, "step": 2114 }, { "epoch": 0.5490654205607477, "grad_norm": 2.5290274620056152, "learning_rate": 4.331597732365689e-06, "loss": 0.3372233808040619, "step": 2115 }, { "epoch": 0.54932502596054, "grad_norm": 6.430972099304199, "learning_rate": 4.330924736914026e-06, "loss": 0.33634594082832336, "step": 2116 }, { "epoch": 0.5495846313603323, "grad_norm": 6.350179672241211, "learning_rate": 4.3302514619910665e-06, "loss": 0.3457720875740051, "step": 2117 }, { "epoch": 0.5498442367601246, "grad_norm": 5.3980393409729, "learning_rate": 4.329577907715833e-06, "loss": 0.3648795485496521, "step": 2118 }, { "epoch": 0.5501038421599169, "grad_norm": 6.002243518829346, "learning_rate": 4.328904074207392e-06, "loss": 0.3277764320373535, "step": 2119 }, { "epoch": 0.5503634475597092, "grad_norm": 11.023887634277344, "learning_rate": 4.328229961584864e-06, "loss": 0.4268181025981903, "step": 2120 }, { "epoch": 0.5506230529595015, "grad_norm": 5.562579154968262, "learning_rate": 4.327555569967414e-06, "loss": 0.3696421980857849, "step": 2121 }, { "epoch": 0.5508826583592938, "grad_norm": 3.512377977371216, "learning_rate": 4.326880899474261e-06, "loss": 0.3845992684364319, "step": 2122 }, { "epoch": 0.5511422637590861, "grad_norm": 2.4954288005828857, "learning_rate": 4.32620595022467e-06, "loss": 0.36362284421920776, "step": 2123 }, { "epoch": 0.5514018691588785, "grad_norm": 5.5855231285095215, "learning_rate": 4.325530722337959e-06, "loss": 0.40860962867736816, "step": 2124 }, { "epoch": 0.5516614745586709, "grad_norm": 3.4408960342407227, "learning_rate": 4.32485521593349e-06, "loss": 0.33914420008659363, "step": 2125 }, { "epoch": 0.5519210799584632, "grad_norm": 2.644801616668701, "learning_rate": 4.324179431130679e-06, "loss": 0.3381247818470001, "step": 2126 }, { "epoch": 0.5521806853582555, "grad_norm": 4.513859748840332, "learning_rate": 4.323503368048987e-06, "loss": 0.3265775442123413, "step": 2127 }, { "epoch": 0.5524402907580478, "grad_norm": 4.295647144317627, "learning_rate": 4.32282702680793e-06, "loss": 0.2603690028190613, "step": 2128 }, { "epoch": 0.5526998961578401, "grad_norm": 6.87967586517334, "learning_rate": 4.322150407527067e-06, "loss": 0.3039935827255249, "step": 2129 }, { "epoch": 0.5529595015576324, "grad_norm": 4.474679470062256, "learning_rate": 4.321473510326009e-06, "loss": 0.3560636043548584, "step": 2130 }, { "epoch": 0.5532191069574247, "grad_norm": 7.703008651733398, "learning_rate": 4.320796335324416e-06, "loss": 0.37769511342048645, "step": 2131 }, { "epoch": 0.553478712357217, "grad_norm": 3.735771417617798, "learning_rate": 4.3201188826419985e-06, "loss": 0.3510289192199707, "step": 2132 }, { "epoch": 0.5537383177570093, "grad_norm": 4.375112533569336, "learning_rate": 4.319441152398513e-06, "loss": 0.3403538465499878, "step": 2133 }, { "epoch": 0.5539979231568016, "grad_norm": 3.740501880645752, "learning_rate": 4.318763144713767e-06, "loss": 0.39455556869506836, "step": 2134 }, { "epoch": 0.5542575285565939, "grad_norm": 7.197619438171387, "learning_rate": 4.318084859707617e-06, "loss": 0.36005640029907227, "step": 2135 }, { "epoch": 0.5545171339563862, "grad_norm": 3.754542589187622, "learning_rate": 4.317406297499968e-06, "loss": 0.3346995413303375, "step": 2136 }, { "epoch": 0.5547767393561787, "grad_norm": 5.968078136444092, "learning_rate": 4.316727458210774e-06, "loss": 0.3014991283416748, "step": 2137 }, { "epoch": 0.555036344755971, "grad_norm": 3.88594913482666, "learning_rate": 4.31604834196004e-06, "loss": 0.34341803193092346, "step": 2138 }, { "epoch": 0.5552959501557633, "grad_norm": 7.026523113250732, "learning_rate": 4.315368948867816e-06, "loss": 0.2917075455188751, "step": 2139 }, { "epoch": 0.5555555555555556, "grad_norm": 8.103325843811035, "learning_rate": 4.3146892790542035e-06, "loss": 0.32114383578300476, "step": 2140 }, { "epoch": 0.5558151609553479, "grad_norm": 6.969364643096924, "learning_rate": 4.314009332639355e-06, "loss": 0.35857149958610535, "step": 2141 }, { "epoch": 0.5560747663551402, "grad_norm": 2.819612741470337, "learning_rate": 4.313329109743466e-06, "loss": 0.35886484384536743, "step": 2142 }, { "epoch": 0.5563343717549325, "grad_norm": 2.9335098266601562, "learning_rate": 4.312648610486786e-06, "loss": 0.3514220118522644, "step": 2143 }, { "epoch": 0.5565939771547248, "grad_norm": 7.875119686126709, "learning_rate": 4.311967834989612e-06, "loss": 0.35498282313346863, "step": 2144 }, { "epoch": 0.5568535825545171, "grad_norm": 4.7939982414245605, "learning_rate": 4.311286783372289e-06, "loss": 0.36690753698349, "step": 2145 }, { "epoch": 0.5571131879543094, "grad_norm": 3.372260093688965, "learning_rate": 4.310605455755211e-06, "loss": 0.3876371383666992, "step": 2146 }, { "epoch": 0.5573727933541017, "grad_norm": 2.1101412773132324, "learning_rate": 4.3099238522588225e-06, "loss": 0.34538692235946655, "step": 2147 }, { "epoch": 0.557632398753894, "grad_norm": 2.717710256576538, "learning_rate": 4.309241973003614e-06, "loss": 0.31424570083618164, "step": 2148 }, { "epoch": 0.5578920041536864, "grad_norm": 6.15447998046875, "learning_rate": 4.3085598181101256e-06, "loss": 0.3695234954357147, "step": 2149 }, { "epoch": 0.5581516095534788, "grad_norm": 5.999569416046143, "learning_rate": 4.307877387698949e-06, "loss": 0.345939576625824, "step": 2150 }, { "epoch": 0.5584112149532711, "grad_norm": 8.569000244140625, "learning_rate": 4.30719468189072e-06, "loss": 0.3354305326938629, "step": 2151 }, { "epoch": 0.5586708203530634, "grad_norm": 3.056173086166382, "learning_rate": 4.306511700806127e-06, "loss": 0.3180522322654724, "step": 2152 }, { "epoch": 0.5589304257528557, "grad_norm": 6.378877639770508, "learning_rate": 4.305828444565904e-06, "loss": 0.283596396446228, "step": 2153 }, { "epoch": 0.559190031152648, "grad_norm": 3.7519829273223877, "learning_rate": 4.305144913290837e-06, "loss": 0.34521883726119995, "step": 2154 }, { "epoch": 0.5594496365524403, "grad_norm": 8.981783866882324, "learning_rate": 4.304461107101756e-06, "loss": 0.45285654067993164, "step": 2155 }, { "epoch": 0.5597092419522326, "grad_norm": 4.592610836029053, "learning_rate": 4.303777026119545e-06, "loss": 0.36344486474990845, "step": 2156 }, { "epoch": 0.5599688473520249, "grad_norm": 6.50792121887207, "learning_rate": 4.3030926704651314e-06, "loss": 0.36307668685913086, "step": 2157 }, { "epoch": 0.5602284527518172, "grad_norm": 3.304655075073242, "learning_rate": 4.302408040259495e-06, "loss": 0.3595450520515442, "step": 2158 }, { "epoch": 0.5604880581516095, "grad_norm": 6.64943265914917, "learning_rate": 4.301723135623662e-06, "loss": 0.44542765617370605, "step": 2159 }, { "epoch": 0.5607476635514018, "grad_norm": 6.762827396392822, "learning_rate": 4.30103795667871e-06, "loss": 0.21134692430496216, "step": 2160 }, { "epoch": 0.5610072689511942, "grad_norm": 4.215898036956787, "learning_rate": 4.300352503545761e-06, "loss": 0.33902981877326965, "step": 2161 }, { "epoch": 0.5612668743509865, "grad_norm": 8.407992362976074, "learning_rate": 4.299666776345987e-06, "loss": 0.38344472646713257, "step": 2162 }, { "epoch": 0.5615264797507789, "grad_norm": 3.495401382446289, "learning_rate": 4.298980775200609e-06, "loss": 0.28690052032470703, "step": 2163 }, { "epoch": 0.5617860851505712, "grad_norm": 2.9659173488616943, "learning_rate": 4.298294500230898e-06, "loss": 0.32998454570770264, "step": 2164 }, { "epoch": 0.5620456905503635, "grad_norm": 3.013561964035034, "learning_rate": 4.29760795155817e-06, "loss": 0.3713639974594116, "step": 2165 }, { "epoch": 0.5623052959501558, "grad_norm": 5.486417770385742, "learning_rate": 4.296921129303792e-06, "loss": 0.3283764123916626, "step": 2166 }, { "epoch": 0.5625649013499481, "grad_norm": 3.2269363403320312, "learning_rate": 4.296234033589178e-06, "loss": 0.35444438457489014, "step": 2167 }, { "epoch": 0.5628245067497404, "grad_norm": 6.374907970428467, "learning_rate": 4.295546664535791e-06, "loss": 0.3429688811302185, "step": 2168 }, { "epoch": 0.5630841121495327, "grad_norm": 3.92932391166687, "learning_rate": 4.2948590222651424e-06, "loss": 0.31565988063812256, "step": 2169 }, { "epoch": 0.563343717549325, "grad_norm": 3.9415626525878906, "learning_rate": 4.294171106898791e-06, "loss": 0.33305543661117554, "step": 2170 }, { "epoch": 0.5636033229491173, "grad_norm": 2.9796149730682373, "learning_rate": 4.293482918558344e-06, "loss": 0.33090537786483765, "step": 2171 }, { "epoch": 0.5638629283489096, "grad_norm": 4.524814605712891, "learning_rate": 4.2927944573654595e-06, "loss": 0.3787199854850769, "step": 2172 }, { "epoch": 0.564122533748702, "grad_norm": 5.619492530822754, "learning_rate": 4.292105723441839e-06, "loss": 0.35291287302970886, "step": 2173 }, { "epoch": 0.5643821391484943, "grad_norm": 10.12498664855957, "learning_rate": 4.291416716909237e-06, "loss": 0.3293813467025757, "step": 2174 }, { "epoch": 0.5646417445482866, "grad_norm": 3.1090781688690186, "learning_rate": 4.290727437889453e-06, "loss": 0.3457280397415161, "step": 2175 }, { "epoch": 0.564901349948079, "grad_norm": 3.015436887741089, "learning_rate": 4.290037886504335e-06, "loss": 0.31429219245910645, "step": 2176 }, { "epoch": 0.5651609553478713, "grad_norm": 5.730237007141113, "learning_rate": 4.289348062875782e-06, "loss": 0.3312947154045105, "step": 2177 }, { "epoch": 0.5654205607476636, "grad_norm": 4.5996928215026855, "learning_rate": 4.288657967125738e-06, "loss": 0.4248770475387573, "step": 2178 }, { "epoch": 0.5656801661474559, "grad_norm": 8.047639846801758, "learning_rate": 4.2879675993761954e-06, "loss": 0.43118494749069214, "step": 2179 }, { "epoch": 0.5659397715472482, "grad_norm": 4.171343803405762, "learning_rate": 4.287276959749196e-06, "loss": 0.32896173000335693, "step": 2180 }, { "epoch": 0.5661993769470405, "grad_norm": 4.436495780944824, "learning_rate": 4.286586048366829e-06, "loss": 0.3079807162284851, "step": 2181 }, { "epoch": 0.5664589823468328, "grad_norm": 7.8710713386535645, "learning_rate": 4.285894865351233e-06, "loss": 0.27976277470588684, "step": 2182 }, { "epoch": 0.5667185877466251, "grad_norm": 6.0785651206970215, "learning_rate": 4.2852034108245895e-06, "loss": 0.3096950650215149, "step": 2183 }, { "epoch": 0.5669781931464174, "grad_norm": 3.052046775817871, "learning_rate": 4.284511684909136e-06, "loss": 0.3371804356575012, "step": 2184 }, { "epoch": 0.5672377985462098, "grad_norm": 4.637426376342773, "learning_rate": 4.2838196877271536e-06, "loss": 0.34612011909484863, "step": 2185 }, { "epoch": 0.5674974039460021, "grad_norm": 3.585468292236328, "learning_rate": 4.283127419400969e-06, "loss": 0.3446285128593445, "step": 2186 }, { "epoch": 0.5677570093457944, "grad_norm": 2.787104845046997, "learning_rate": 4.28243488005296e-06, "loss": 0.3325759470462799, "step": 2187 }, { "epoch": 0.5680166147455867, "grad_norm": 8.964841842651367, "learning_rate": 4.281742069805553e-06, "loss": 0.2507830262184143, "step": 2188 }, { "epoch": 0.568276220145379, "grad_norm": 2.6331958770751953, "learning_rate": 4.281048988781221e-06, "loss": 0.37138622999191284, "step": 2189 }, { "epoch": 0.5685358255451713, "grad_norm": 6.876735210418701, "learning_rate": 4.280355637102483e-06, "loss": 0.192419171333313, "step": 2190 }, { "epoch": 0.5687954309449637, "grad_norm": 3.288271903991699, "learning_rate": 4.279662014891909e-06, "loss": 0.3418262004852295, "step": 2191 }, { "epoch": 0.569055036344756, "grad_norm": 7.031816482543945, "learning_rate": 4.2789681222721155e-06, "loss": 0.38225483894348145, "step": 2192 }, { "epoch": 0.5693146417445483, "grad_norm": 3.2900946140289307, "learning_rate": 4.278273959365768e-06, "loss": 0.3287345767021179, "step": 2193 }, { "epoch": 0.5695742471443406, "grad_norm": 7.576297760009766, "learning_rate": 4.277579526295575e-06, "loss": 0.2907084822654724, "step": 2194 }, { "epoch": 0.5698338525441329, "grad_norm": 5.393574237823486, "learning_rate": 4.2768848231843e-06, "loss": 0.40781310200691223, "step": 2195 }, { "epoch": 0.5700934579439252, "grad_norm": 2.8259994983673096, "learning_rate": 4.27618985015475e-06, "loss": 0.3884434700012207, "step": 2196 }, { "epoch": 0.5703530633437176, "grad_norm": 5.263759613037109, "learning_rate": 4.275494607329778e-06, "loss": 0.34591397643089294, "step": 2197 }, { "epoch": 0.5706126687435099, "grad_norm": 4.33669900894165, "learning_rate": 4.27479909483229e-06, "loss": 0.30562543869018555, "step": 2198 }, { "epoch": 0.5708722741433022, "grad_norm": 9.089154243469238, "learning_rate": 4.274103312785235e-06, "loss": 0.3549862504005432, "step": 2199 }, { "epoch": 0.5711318795430945, "grad_norm": 6.115344047546387, "learning_rate": 4.27340726131161e-06, "loss": 0.34070318937301636, "step": 2200 }, { "epoch": 0.5713914849428868, "grad_norm": 5.291077136993408, "learning_rate": 4.272710940534465e-06, "loss": 0.3781839609146118, "step": 2201 }, { "epoch": 0.5716510903426791, "grad_norm": 3.0940446853637695, "learning_rate": 4.27201435057689e-06, "loss": 0.35681673884391785, "step": 2202 }, { "epoch": 0.5719106957424714, "grad_norm": 3.0993220806121826, "learning_rate": 4.271317491562028e-06, "loss": 0.32215219736099243, "step": 2203 }, { "epoch": 0.5721703011422637, "grad_norm": 2.965254783630371, "learning_rate": 4.270620363613066e-06, "loss": 0.34784483909606934, "step": 2204 }, { "epoch": 0.572429906542056, "grad_norm": 8.426746368408203, "learning_rate": 4.269922966853242e-06, "loss": 0.26382172107696533, "step": 2205 }, { "epoch": 0.5726895119418484, "grad_norm": 3.788700580596924, "learning_rate": 4.269225301405838e-06, "loss": 0.3616098165512085, "step": 2206 }, { "epoch": 0.5729491173416407, "grad_norm": 4.660436630249023, "learning_rate": 4.268527367394188e-06, "loss": 0.39500147104263306, "step": 2207 }, { "epoch": 0.573208722741433, "grad_norm": 6.273392677307129, "learning_rate": 4.267829164941669e-06, "loss": 0.32785165309906006, "step": 2208 }, { "epoch": 0.5734683281412254, "grad_norm": 4.880824565887451, "learning_rate": 4.267130694171706e-06, "loss": 0.35154855251312256, "step": 2209 }, { "epoch": 0.5737279335410177, "grad_norm": 5.9089035987854, "learning_rate": 4.266431955207774e-06, "loss": 0.3917083144187927, "step": 2210 }, { "epoch": 0.57398753894081, "grad_norm": 7.650291919708252, "learning_rate": 4.265732948173395e-06, "loss": 0.37735801935195923, "step": 2211 }, { "epoch": 0.5742471443406023, "grad_norm": 3.881617784500122, "learning_rate": 4.265033673192136e-06, "loss": 0.38190722465515137, "step": 2212 }, { "epoch": 0.5745067497403946, "grad_norm": 7.469627380371094, "learning_rate": 4.264334130387614e-06, "loss": 0.35281234979629517, "step": 2213 }, { "epoch": 0.5747663551401869, "grad_norm": 8.056520462036133, "learning_rate": 4.26363431988349e-06, "loss": 0.43891263008117676, "step": 2214 }, { "epoch": 0.5750259605399792, "grad_norm": 6.965717792510986, "learning_rate": 4.262934241803477e-06, "loss": 0.33873113989830017, "step": 2215 }, { "epoch": 0.5752855659397715, "grad_norm": 3.0642330646514893, "learning_rate": 4.2622338962713315e-06, "loss": 0.3268364667892456, "step": 2216 }, { "epoch": 0.5755451713395638, "grad_norm": 8.566712379455566, "learning_rate": 4.261533283410858e-06, "loss": 0.3615466058254242, "step": 2217 }, { "epoch": 0.5758047767393562, "grad_norm": 3.712982416152954, "learning_rate": 4.26083240334591e-06, "loss": 0.34516534209251404, "step": 2218 }, { "epoch": 0.5760643821391485, "grad_norm": 3.8798158168792725, "learning_rate": 4.260131256200387e-06, "loss": 0.37622952461242676, "step": 2219 }, { "epoch": 0.5763239875389408, "grad_norm": 6.148557186126709, "learning_rate": 4.259429842098235e-06, "loss": 0.3115898370742798, "step": 2220 }, { "epoch": 0.5765835929387332, "grad_norm": 4.742764472961426, "learning_rate": 4.258728161163448e-06, "loss": 0.33848732709884644, "step": 2221 }, { "epoch": 0.5768431983385255, "grad_norm": 5.920379638671875, "learning_rate": 4.258026213520067e-06, "loss": 0.364484965801239, "step": 2222 }, { "epoch": 0.5771028037383178, "grad_norm": 6.053443908691406, "learning_rate": 4.257323999292182e-06, "loss": 0.4224395751953125, "step": 2223 }, { "epoch": 0.5773624091381101, "grad_norm": 3.368074417114258, "learning_rate": 4.256621518603926e-06, "loss": 0.31715893745422363, "step": 2224 }, { "epoch": 0.5776220145379024, "grad_norm": 5.817386627197266, "learning_rate": 4.255918771579482e-06, "loss": 0.3912363648414612, "step": 2225 }, { "epoch": 0.5778816199376947, "grad_norm": 6.843388557434082, "learning_rate": 4.255215758343082e-06, "loss": 0.34753382205963135, "step": 2226 }, { "epoch": 0.578141225337487, "grad_norm": 5.894199371337891, "learning_rate": 4.2545124790189995e-06, "loss": 0.35264334082603455, "step": 2227 }, { "epoch": 0.5784008307372793, "grad_norm": 5.04805326461792, "learning_rate": 4.2538089337315594e-06, "loss": 0.3923669159412384, "step": 2228 }, { "epoch": 0.5786604361370716, "grad_norm": 4.199756622314453, "learning_rate": 4.253105122605134e-06, "loss": 0.3121306598186493, "step": 2229 }, { "epoch": 0.5789200415368639, "grad_norm": 4.79112434387207, "learning_rate": 4.252401045764138e-06, "loss": 0.352910578250885, "step": 2230 }, { "epoch": 0.5791796469366562, "grad_norm": 5.329713821411133, "learning_rate": 4.251696703333037e-06, "loss": 0.3214538097381592, "step": 2231 }, { "epoch": 0.5794392523364486, "grad_norm": 3.3168506622314453, "learning_rate": 4.250992095436345e-06, "loss": 0.3360018730163574, "step": 2232 }, { "epoch": 0.579698857736241, "grad_norm": 5.272871017456055, "learning_rate": 4.250287222198618e-06, "loss": 0.32741689682006836, "step": 2233 }, { "epoch": 0.5799584631360333, "grad_norm": 4.022042274475098, "learning_rate": 4.249582083744461e-06, "loss": 0.3564591407775879, "step": 2234 }, { "epoch": 0.5802180685358256, "grad_norm": 7.535716533660889, "learning_rate": 4.248876680198529e-06, "loss": 0.3239441514015198, "step": 2235 }, { "epoch": 0.5804776739356179, "grad_norm": 3.8775739669799805, "learning_rate": 4.248171011685519e-06, "loss": 0.3492482006549835, "step": 2236 }, { "epoch": 0.5807372793354102, "grad_norm": 4.87652587890625, "learning_rate": 4.247465078330177e-06, "loss": 0.30507272481918335, "step": 2237 }, { "epoch": 0.5809968847352025, "grad_norm": 7.030065536499023, "learning_rate": 4.246758880257299e-06, "loss": 0.33457672595977783, "step": 2238 }, { "epoch": 0.5812564901349948, "grad_norm": 3.7230610847473145, "learning_rate": 4.24605241759172e-06, "loss": 0.35649073123931885, "step": 2239 }, { "epoch": 0.5815160955347871, "grad_norm": 5.31517219543457, "learning_rate": 4.245345690458329e-06, "loss": 0.30957043170928955, "step": 2240 }, { "epoch": 0.5817757009345794, "grad_norm": 5.8204874992370605, "learning_rate": 4.244638698982059e-06, "loss": 0.2956415116786957, "step": 2241 }, { "epoch": 0.5820353063343717, "grad_norm": 3.324918270111084, "learning_rate": 4.243931443287889e-06, "loss": 0.32170921564102173, "step": 2242 }, { "epoch": 0.582294911734164, "grad_norm": 3.111431360244751, "learning_rate": 4.243223923500846e-06, "loss": 0.31812524795532227, "step": 2243 }, { "epoch": 0.5825545171339563, "grad_norm": 2.690580368041992, "learning_rate": 4.2425161397460055e-06, "loss": 0.32823923230171204, "step": 2244 }, { "epoch": 0.5828141225337488, "grad_norm": 5.26724910736084, "learning_rate": 4.241808092148485e-06, "loss": 0.33880096673965454, "step": 2245 }, { "epoch": 0.5830737279335411, "grad_norm": 5.2532243728637695, "learning_rate": 4.241099780833451e-06, "loss": 0.2840079665184021, "step": 2246 }, { "epoch": 0.5833333333333334, "grad_norm": 2.2654058933258057, "learning_rate": 4.240391205926118e-06, "loss": 0.330197811126709, "step": 2247 }, { "epoch": 0.5835929387331257, "grad_norm": 2.407273530960083, "learning_rate": 4.239682367551745e-06, "loss": 0.3611799478530884, "step": 2248 }, { "epoch": 0.583852544132918, "grad_norm": 2.8534345626831055, "learning_rate": 4.238973265835639e-06, "loss": 0.31795862317085266, "step": 2249 }, { "epoch": 0.5841121495327103, "grad_norm": 4.783867835998535, "learning_rate": 4.238263900903152e-06, "loss": 0.33631694316864014, "step": 2250 }, { "epoch": 0.5843717549325026, "grad_norm": 2.1544971466064453, "learning_rate": 4.2375542728796835e-06, "loss": 0.35160669684410095, "step": 2251 }, { "epoch": 0.5846313603322949, "grad_norm": 6.695608139038086, "learning_rate": 4.236844381890681e-06, "loss": 0.30274510383605957, "step": 2252 }, { "epoch": 0.5848909657320872, "grad_norm": 2.4037837982177734, "learning_rate": 4.236134228061636e-06, "loss": 0.3760885000228882, "step": 2253 }, { "epoch": 0.5851505711318795, "grad_norm": 4.395177841186523, "learning_rate": 4.235423811518087e-06, "loss": 0.30226314067840576, "step": 2254 }, { "epoch": 0.5854101765316718, "grad_norm": 11.541665077209473, "learning_rate": 4.2347131323856195e-06, "loss": 0.3470083475112915, "step": 2255 }, { "epoch": 0.5856697819314641, "grad_norm": 6.49381160736084, "learning_rate": 4.234002190789867e-06, "loss": 0.28959032893180847, "step": 2256 }, { "epoch": 0.5859293873312564, "grad_norm": 2.7427186965942383, "learning_rate": 4.233290986856504e-06, "loss": 0.3159981966018677, "step": 2257 }, { "epoch": 0.5861889927310489, "grad_norm": 4.209085941314697, "learning_rate": 4.23257952071126e-06, "loss": 0.32804596424102783, "step": 2258 }, { "epoch": 0.5864485981308412, "grad_norm": 11.267191886901855, "learning_rate": 4.231867792479902e-06, "loss": 0.2952229976654053, "step": 2259 }, { "epoch": 0.5867082035306335, "grad_norm": 2.732192277908325, "learning_rate": 4.2311558022882485e-06, "loss": 0.3435680866241455, "step": 2260 }, { "epoch": 0.5869678089304258, "grad_norm": 4.513068675994873, "learning_rate": 4.2304435502621635e-06, "loss": 0.3186807930469513, "step": 2261 }, { "epoch": 0.5872274143302181, "grad_norm": 3.584254503250122, "learning_rate": 4.229731036527556e-06, "loss": 0.3484313189983368, "step": 2262 }, { "epoch": 0.5874870197300104, "grad_norm": 3.308709144592285, "learning_rate": 4.229018261210383e-06, "loss": 0.35437145829200745, "step": 2263 }, { "epoch": 0.5877466251298027, "grad_norm": 7.427839756011963, "learning_rate": 4.2283052244366465e-06, "loss": 0.3606371283531189, "step": 2264 }, { "epoch": 0.588006230529595, "grad_norm": 7.215373516082764, "learning_rate": 4.227591926332394e-06, "loss": 0.3241083025932312, "step": 2265 }, { "epoch": 0.5882658359293873, "grad_norm": 7.532166957855225, "learning_rate": 4.226878367023724e-06, "loss": 0.3134186267852783, "step": 2266 }, { "epoch": 0.5885254413291796, "grad_norm": 2.489969491958618, "learning_rate": 4.226164546636772e-06, "loss": 0.3627038896083832, "step": 2267 }, { "epoch": 0.5887850467289719, "grad_norm": 3.5724472999572754, "learning_rate": 4.2254504652977285e-06, "loss": 0.3618258535861969, "step": 2268 }, { "epoch": 0.5890446521287642, "grad_norm": 7.43472957611084, "learning_rate": 4.224736123132826e-06, "loss": 0.21938931941986084, "step": 2269 }, { "epoch": 0.5893042575285566, "grad_norm": 9.47447395324707, "learning_rate": 4.224021520268345e-06, "loss": 0.3687649965286255, "step": 2270 }, { "epoch": 0.589563862928349, "grad_norm": 3.682389259338379, "learning_rate": 4.2233066568306084e-06, "loss": 0.35068705677986145, "step": 2271 }, { "epoch": 0.5898234683281413, "grad_norm": 8.456246376037598, "learning_rate": 4.22259153294599e-06, "loss": 0.374894917011261, "step": 2272 }, { "epoch": 0.5900830737279336, "grad_norm": 3.8652656078338623, "learning_rate": 4.221876148740906e-06, "loss": 0.3252931237220764, "step": 2273 }, { "epoch": 0.5903426791277259, "grad_norm": 6.9235029220581055, "learning_rate": 4.221160504341821e-06, "loss": 0.3565118610858917, "step": 2274 }, { "epoch": 0.5906022845275182, "grad_norm": 4.303726673126221, "learning_rate": 4.220444599875243e-06, "loss": 0.32034868001937866, "step": 2275 }, { "epoch": 0.5908618899273105, "grad_norm": 4.398061752319336, "learning_rate": 4.219728435467729e-06, "loss": 0.33272504806518555, "step": 2276 }, { "epoch": 0.5911214953271028, "grad_norm": 5.4370832443237305, "learning_rate": 4.21901201124588e-06, "loss": 0.3688508868217468, "step": 2277 }, { "epoch": 0.5913811007268951, "grad_norm": 8.290021896362305, "learning_rate": 4.2182953273363445e-06, "loss": 0.28751352429389954, "step": 2278 }, { "epoch": 0.5916407061266874, "grad_norm": 7.009812355041504, "learning_rate": 4.217578383865813e-06, "loss": 0.2379995882511139, "step": 2279 }, { "epoch": 0.5919003115264797, "grad_norm": 6.053666591644287, "learning_rate": 4.216861180961026e-06, "loss": 0.3385912775993347, "step": 2280 }, { "epoch": 0.592159916926272, "grad_norm": 5.422316074371338, "learning_rate": 4.21614371874877e-06, "loss": 0.30153360962867737, "step": 2281 }, { "epoch": 0.5924195223260644, "grad_norm": 5.55414342880249, "learning_rate": 4.215425997355875e-06, "loss": 0.29191678762435913, "step": 2282 }, { "epoch": 0.5926791277258567, "grad_norm": 8.487147331237793, "learning_rate": 4.214708016909216e-06, "loss": 0.2101288139820099, "step": 2283 }, { "epoch": 0.592938733125649, "grad_norm": 9.837109565734863, "learning_rate": 4.213989777535719e-06, "loss": 0.2671184539794922, "step": 2284 }, { "epoch": 0.5931983385254413, "grad_norm": 2.8032732009887695, "learning_rate": 4.2132712793623485e-06, "loss": 0.3211594820022583, "step": 2285 }, { "epoch": 0.5934579439252337, "grad_norm": 2.884164571762085, "learning_rate": 4.2125525225161205e-06, "loss": 0.30963587760925293, "step": 2286 }, { "epoch": 0.593717549325026, "grad_norm": 8.28101634979248, "learning_rate": 4.211833507124095e-06, "loss": 0.2902783453464508, "step": 2287 }, { "epoch": 0.5939771547248183, "grad_norm": 9.647309303283691, "learning_rate": 4.211114233313377e-06, "loss": 0.38478976488113403, "step": 2288 }, { "epoch": 0.5942367601246106, "grad_norm": 4.040031909942627, "learning_rate": 4.2103947012111176e-06, "loss": 0.3198563754558563, "step": 2289 }, { "epoch": 0.5944963655244029, "grad_norm": 3.046522617340088, "learning_rate": 4.209674910944513e-06, "loss": 0.3471425771713257, "step": 2290 }, { "epoch": 0.5947559709241952, "grad_norm": 5.816603183746338, "learning_rate": 4.208954862640807e-06, "loss": 0.329393595457077, "step": 2291 }, { "epoch": 0.5950155763239875, "grad_norm": 3.8181569576263428, "learning_rate": 4.208234556427288e-06, "loss": 0.3266708254814148, "step": 2292 }, { "epoch": 0.5952751817237798, "grad_norm": 6.4960150718688965, "learning_rate": 4.207513992431286e-06, "loss": 0.4024621248245239, "step": 2293 }, { "epoch": 0.5955347871235722, "grad_norm": 4.767224311828613, "learning_rate": 4.206793170780185e-06, "loss": 0.28219538927078247, "step": 2294 }, { "epoch": 0.5957943925233645, "grad_norm": 7.685293197631836, "learning_rate": 4.206072091601406e-06, "loss": 0.42250919342041016, "step": 2295 }, { "epoch": 0.5960539979231568, "grad_norm": 5.056921482086182, "learning_rate": 4.2053507550224224e-06, "loss": 0.3592457175254822, "step": 2296 }, { "epoch": 0.5963136033229491, "grad_norm": 5.6799163818359375, "learning_rate": 4.204629161170747e-06, "loss": 0.2882160246372223, "step": 2297 }, { "epoch": 0.5965732087227414, "grad_norm": 4.366357326507568, "learning_rate": 4.2039073101739434e-06, "loss": 0.29288750886917114, "step": 2298 }, { "epoch": 0.5968328141225338, "grad_norm": 5.375147342681885, "learning_rate": 4.203185202159617e-06, "loss": 0.3287704586982727, "step": 2299 }, { "epoch": 0.5970924195223261, "grad_norm": 6.978137016296387, "learning_rate": 4.202462837255421e-06, "loss": 0.3188401460647583, "step": 2300 }, { "epoch": 0.5973520249221184, "grad_norm": 4.232616901397705, "learning_rate": 4.201740215589051e-06, "loss": 0.3129950165748596, "step": 2301 }, { "epoch": 0.5976116303219107, "grad_norm": 8.595711708068848, "learning_rate": 4.201017337288253e-06, "loss": 0.32321876287460327, "step": 2302 }, { "epoch": 0.597871235721703, "grad_norm": 4.435056209564209, "learning_rate": 4.2002942024808125e-06, "loss": 0.3215545117855072, "step": 2303 }, { "epoch": 0.5981308411214953, "grad_norm": 2.971906900405884, "learning_rate": 4.199570811294564e-06, "loss": 0.2835032045841217, "step": 2304 }, { "epoch": 0.5983904465212876, "grad_norm": 2.014267683029175, "learning_rate": 4.198847163857388e-06, "loss": 0.3752943277359009, "step": 2305 }, { "epoch": 0.59865005192108, "grad_norm": 6.33908748626709, "learning_rate": 4.1981232602972075e-06, "loss": 0.29119032621383667, "step": 2306 }, { "epoch": 0.5989096573208723, "grad_norm": 3.434483528137207, "learning_rate": 4.197399100741991e-06, "loss": 0.3275493383407593, "step": 2307 }, { "epoch": 0.5991692627206646, "grad_norm": 7.361067771911621, "learning_rate": 4.196674685319755e-06, "loss": 0.3975467085838318, "step": 2308 }, { "epoch": 0.5994288681204569, "grad_norm": 4.554090976715088, "learning_rate": 4.19595001415856e-06, "loss": 0.32802772521972656, "step": 2309 }, { "epoch": 0.5996884735202492, "grad_norm": 3.4115753173828125, "learning_rate": 4.19522508738651e-06, "loss": 0.36103686690330505, "step": 2310 }, { "epoch": 0.5999480789200415, "grad_norm": 3.318849563598633, "learning_rate": 4.194499905131755e-06, "loss": 0.33581966161727905, "step": 2311 }, { "epoch": 0.6002076843198338, "grad_norm": 3.3846583366394043, "learning_rate": 4.1937744675224925e-06, "loss": 0.3122537136077881, "step": 2312 }, { "epoch": 0.6004672897196262, "grad_norm": 3.741236448287964, "learning_rate": 4.193048774686961e-06, "loss": 0.3043591380119324, "step": 2313 }, { "epoch": 0.6007268951194185, "grad_norm": 7.484060764312744, "learning_rate": 4.192322826753449e-06, "loss": 0.2461654245853424, "step": 2314 }, { "epoch": 0.6009865005192108, "grad_norm": 3.304640293121338, "learning_rate": 4.1915966238502855e-06, "loss": 0.34710025787353516, "step": 2315 }, { "epoch": 0.6012461059190031, "grad_norm": 7.060923099517822, "learning_rate": 4.1908701661058465e-06, "loss": 0.2593671679496765, "step": 2316 }, { "epoch": 0.6015057113187954, "grad_norm": 5.727695941925049, "learning_rate": 4.190143453648554e-06, "loss": 0.30218783020973206, "step": 2317 }, { "epoch": 0.6017653167185878, "grad_norm": 7.201291561126709, "learning_rate": 4.1894164866068745e-06, "loss": 0.27418243885040283, "step": 2318 }, { "epoch": 0.6020249221183801, "grad_norm": 4.580099105834961, "learning_rate": 4.188689265109318e-06, "loss": 0.334612101316452, "step": 2319 }, { "epoch": 0.6022845275181724, "grad_norm": 7.380204677581787, "learning_rate": 4.187961789284441e-06, "loss": 0.37451493740081787, "step": 2320 }, { "epoch": 0.6025441329179647, "grad_norm": 7.824974060058594, "learning_rate": 4.187234059260845e-06, "loss": 0.25994956493377686, "step": 2321 }, { "epoch": 0.602803738317757, "grad_norm": 7.150155067443848, "learning_rate": 4.186506075167174e-06, "loss": 0.4232460856437683, "step": 2322 }, { "epoch": 0.6030633437175493, "grad_norm": 3.865920305252075, "learning_rate": 4.1857778371321225e-06, "loss": 0.3599399924278259, "step": 2323 }, { "epoch": 0.6033229491173416, "grad_norm": 7.677727699279785, "learning_rate": 4.185049345284423e-06, "loss": 0.4069763422012329, "step": 2324 }, { "epoch": 0.6035825545171339, "grad_norm": 3.603090524673462, "learning_rate": 4.184320599752858e-06, "loss": 0.31933414936065674, "step": 2325 }, { "epoch": 0.6038421599169262, "grad_norm": 4.036500453948975, "learning_rate": 4.183591600666253e-06, "loss": 0.29946422576904297, "step": 2326 }, { "epoch": 0.6041017653167186, "grad_norm": 5.699460506439209, "learning_rate": 4.182862348153478e-06, "loss": 0.27231115102767944, "step": 2327 }, { "epoch": 0.6043613707165109, "grad_norm": 7.369551658630371, "learning_rate": 4.182132842343448e-06, "loss": 0.4197086691856384, "step": 2328 }, { "epoch": 0.6046209761163032, "grad_norm": 7.982434272766113, "learning_rate": 4.181403083365122e-06, "loss": 0.24993368983268738, "step": 2329 }, { "epoch": 0.6048805815160956, "grad_norm": 4.974757194519043, "learning_rate": 4.180673071347506e-06, "loss": 0.33658504486083984, "step": 2330 }, { "epoch": 0.6051401869158879, "grad_norm": 9.035775184631348, "learning_rate": 4.17994280641965e-06, "loss": 0.3646499514579773, "step": 2331 }, { "epoch": 0.6053997923156802, "grad_norm": 3.7067513465881348, "learning_rate": 4.179212288710646e-06, "loss": 0.348153680562973, "step": 2332 }, { "epoch": 0.6056593977154725, "grad_norm": 5.625509738922119, "learning_rate": 4.178481518349634e-06, "loss": 0.35469311475753784, "step": 2333 }, { "epoch": 0.6059190031152648, "grad_norm": 2.928762435913086, "learning_rate": 4.1777504954657975e-06, "loss": 0.39556360244750977, "step": 2334 }, { "epoch": 0.6061786085150571, "grad_norm": 8.229840278625488, "learning_rate": 4.1770192201883656e-06, "loss": 0.35999950766563416, "step": 2335 }, { "epoch": 0.6064382139148494, "grad_norm": 8.203455924987793, "learning_rate": 4.17628769264661e-06, "loss": 0.389340877532959, "step": 2336 }, { "epoch": 0.6066978193146417, "grad_norm": 7.929210662841797, "learning_rate": 4.175555912969846e-06, "loss": 0.3959338068962097, "step": 2337 }, { "epoch": 0.606957424714434, "grad_norm": 3.015596389770508, "learning_rate": 4.17482388128744e-06, "loss": 0.28713706135749817, "step": 2338 }, { "epoch": 0.6072170301142263, "grad_norm": 7.752606391906738, "learning_rate": 4.174091597728793e-06, "loss": 0.36024555563926697, "step": 2339 }, { "epoch": 0.6074766355140186, "grad_norm": 6.918606281280518, "learning_rate": 4.173359062423361e-06, "loss": 0.33290934562683105, "step": 2340 }, { "epoch": 0.607736240913811, "grad_norm": 3.1329760551452637, "learning_rate": 4.172626275500637e-06, "loss": 0.34000587463378906, "step": 2341 }, { "epoch": 0.6079958463136034, "grad_norm": 3.363706588745117, "learning_rate": 4.171893237090161e-06, "loss": 0.35152921080589294, "step": 2342 }, { "epoch": 0.6082554517133957, "grad_norm": 7.63456392288208, "learning_rate": 4.171159947321519e-06, "loss": 0.2974911332130432, "step": 2343 }, { "epoch": 0.608515057113188, "grad_norm": 4.15516471862793, "learning_rate": 4.170426406324337e-06, "loss": 0.3135054409503937, "step": 2344 }, { "epoch": 0.6087746625129803, "grad_norm": 3.561732292175293, "learning_rate": 4.16969261422829e-06, "loss": 0.3002326488494873, "step": 2345 }, { "epoch": 0.6090342679127726, "grad_norm": 2.785531520843506, "learning_rate": 4.168958571163097e-06, "loss": 0.3524956703186035, "step": 2346 }, { "epoch": 0.6092938733125649, "grad_norm": 6.120973110198975, "learning_rate": 4.168224277258517e-06, "loss": 0.3166359066963196, "step": 2347 }, { "epoch": 0.6095534787123572, "grad_norm": 8.844202995300293, "learning_rate": 4.167489732644358e-06, "loss": 0.45610305666923523, "step": 2348 }, { "epoch": 0.6098130841121495, "grad_norm": 9.077540397644043, "learning_rate": 4.166754937450471e-06, "loss": 0.34508398175239563, "step": 2349 }, { "epoch": 0.6100726895119418, "grad_norm": 6.303245544433594, "learning_rate": 4.1660198918067504e-06, "loss": 0.28267043828964233, "step": 2350 }, { "epoch": 0.6103322949117341, "grad_norm": 6.125391960144043, "learning_rate": 4.165284595843135e-06, "loss": 0.31310367584228516, "step": 2351 }, { "epoch": 0.6105919003115264, "grad_norm": 5.540392875671387, "learning_rate": 4.1645490496896085e-06, "loss": 0.31425943970680237, "step": 2352 }, { "epoch": 0.6108515057113187, "grad_norm": 8.513740539550781, "learning_rate": 4.1638132534762e-06, "loss": 0.30254799127578735, "step": 2353 }, { "epoch": 0.6111111111111112, "grad_norm": 6.291385650634766, "learning_rate": 4.163077207332979e-06, "loss": 0.37257009744644165, "step": 2354 }, { "epoch": 0.6113707165109035, "grad_norm": 5.6621479988098145, "learning_rate": 4.1623409113900636e-06, "loss": 0.3651920557022095, "step": 2355 }, { "epoch": 0.6116303219106958, "grad_norm": 3.4168612957000732, "learning_rate": 4.161604365777613e-06, "loss": 0.34022825956344604, "step": 2356 }, { "epoch": 0.6118899273104881, "grad_norm": 8.62428092956543, "learning_rate": 4.160867570625833e-06, "loss": 0.28408190608024597, "step": 2357 }, { "epoch": 0.6121495327102804, "grad_norm": 4.020975589752197, "learning_rate": 4.16013052606497e-06, "loss": 0.3365921378135681, "step": 2358 }, { "epoch": 0.6124091381100727, "grad_norm": 4.620813369750977, "learning_rate": 4.159393232225318e-06, "loss": 0.3080781400203705, "step": 2359 }, { "epoch": 0.612668743509865, "grad_norm": 6.034271717071533, "learning_rate": 4.1586556892372135e-06, "loss": 0.3841547966003418, "step": 2360 }, { "epoch": 0.6129283489096573, "grad_norm": 3.6506404876708984, "learning_rate": 4.157917897231037e-06, "loss": 0.3069588243961334, "step": 2361 }, { "epoch": 0.6131879543094496, "grad_norm": 7.007951259613037, "learning_rate": 4.157179856337214e-06, "loss": 0.42148852348327637, "step": 2362 }, { "epoch": 0.6134475597092419, "grad_norm": 6.574019432067871, "learning_rate": 4.156441566686212e-06, "loss": 0.307415246963501, "step": 2363 }, { "epoch": 0.6137071651090342, "grad_norm": 8.040322303771973, "learning_rate": 4.155703028408544e-06, "loss": 0.3865197002887726, "step": 2364 }, { "epoch": 0.6139667705088265, "grad_norm": 5.561257362365723, "learning_rate": 4.1549642416347676e-06, "loss": 0.34851008653640747, "step": 2365 }, { "epoch": 0.614226375908619, "grad_norm": 5.237859725952148, "learning_rate": 4.154225206495482e-06, "loss": 0.3233925402164459, "step": 2366 }, { "epoch": 0.6144859813084113, "grad_norm": 5.337869167327881, "learning_rate": 4.153485923121332e-06, "loss": 0.34487682580947876, "step": 2367 }, { "epoch": 0.6147455867082036, "grad_norm": 8.116100311279297, "learning_rate": 4.152746391643008e-06, "loss": 0.3386959433555603, "step": 2368 }, { "epoch": 0.6150051921079959, "grad_norm": 10.15312385559082, "learning_rate": 4.152006612191239e-06, "loss": 0.2541871666908264, "step": 2369 }, { "epoch": 0.6152647975077882, "grad_norm": 6.535671710968018, "learning_rate": 4.151266584896803e-06, "loss": 0.3309139907360077, "step": 2370 }, { "epoch": 0.6155244029075805, "grad_norm": 2.7469491958618164, "learning_rate": 4.1505263098905196e-06, "loss": 0.3483355641365051, "step": 2371 }, { "epoch": 0.6157840083073728, "grad_norm": 2.7748076915740967, "learning_rate": 4.149785787303253e-06, "loss": 0.3641112446784973, "step": 2372 }, { "epoch": 0.6160436137071651, "grad_norm": 6.263004302978516, "learning_rate": 4.14904501726591e-06, "loss": 0.32614240050315857, "step": 2373 }, { "epoch": 0.6163032191069574, "grad_norm": 7.675942420959473, "learning_rate": 4.148303999909441e-06, "loss": 0.3421233594417572, "step": 2374 }, { "epoch": 0.6165628245067497, "grad_norm": 7.196067810058594, "learning_rate": 4.147562735364842e-06, "loss": 0.31709152460098267, "step": 2375 }, { "epoch": 0.616822429906542, "grad_norm": 4.00227689743042, "learning_rate": 4.146821223763151e-06, "loss": 0.3212851881980896, "step": 2376 }, { "epoch": 0.6170820353063343, "grad_norm": 4.206175804138184, "learning_rate": 4.146079465235452e-06, "loss": 0.2785520553588867, "step": 2377 }, { "epoch": 0.6173416407061267, "grad_norm": 3.2866392135620117, "learning_rate": 4.145337459912868e-06, "loss": 0.3358503580093384, "step": 2378 }, { "epoch": 0.617601246105919, "grad_norm": 3.330146074295044, "learning_rate": 4.144595207926571e-06, "loss": 0.2974590063095093, "step": 2379 }, { "epoch": 0.6178608515057114, "grad_norm": 5.186828136444092, "learning_rate": 4.143852709407773e-06, "loss": 0.2613510191440582, "step": 2380 }, { "epoch": 0.6181204569055037, "grad_norm": 4.257221221923828, "learning_rate": 4.143109964487731e-06, "loss": 0.3143591284751892, "step": 2381 }, { "epoch": 0.618380062305296, "grad_norm": 4.526491165161133, "learning_rate": 4.1423669732977455e-06, "loss": 0.2937508225440979, "step": 2382 }, { "epoch": 0.6186396677050883, "grad_norm": 5.8783793449401855, "learning_rate": 4.1416237359691595e-06, "loss": 0.3058616518974304, "step": 2383 }, { "epoch": 0.6188992731048806, "grad_norm": 8.986563682556152, "learning_rate": 4.140880252633362e-06, "loss": 0.35898706316947937, "step": 2384 }, { "epoch": 0.6191588785046729, "grad_norm": 8.702052116394043, "learning_rate": 4.140136523421782e-06, "loss": 0.3492887616157532, "step": 2385 }, { "epoch": 0.6194184839044652, "grad_norm": 3.0129778385162354, "learning_rate": 4.139392548465895e-06, "loss": 0.35316264629364014, "step": 2386 }, { "epoch": 0.6196780893042575, "grad_norm": 9.094552040100098, "learning_rate": 4.138648327897216e-06, "loss": 0.2675967812538147, "step": 2387 }, { "epoch": 0.6199376947040498, "grad_norm": 3.6110312938690186, "learning_rate": 4.137903861847311e-06, "loss": 0.3257920444011688, "step": 2388 }, { "epoch": 0.6201973001038421, "grad_norm": 2.378373146057129, "learning_rate": 4.137159150447782e-06, "loss": 0.33734560012817383, "step": 2389 }, { "epoch": 0.6204569055036345, "grad_norm": 7.31724739074707, "learning_rate": 4.136414193830276e-06, "loss": 0.32245543599128723, "step": 2390 }, { "epoch": 0.6207165109034268, "grad_norm": 11.072330474853516, "learning_rate": 4.135668992126485e-06, "loss": 0.3123692572116852, "step": 2391 }, { "epoch": 0.6209761163032191, "grad_norm": 7.788872718811035, "learning_rate": 4.134923545468144e-06, "loss": 0.3499039113521576, "step": 2392 }, { "epoch": 0.6212357217030114, "grad_norm": 2.4167320728302, "learning_rate": 4.134177853987032e-06, "loss": 0.3418046534061432, "step": 2393 }, { "epoch": 0.6214953271028038, "grad_norm": 5.378818511962891, "learning_rate": 4.133431917814967e-06, "loss": 0.30939924716949463, "step": 2394 }, { "epoch": 0.6217549325025961, "grad_norm": 4.695295333862305, "learning_rate": 4.132685737083817e-06, "loss": 0.3231920897960663, "step": 2395 }, { "epoch": 0.6220145379023884, "grad_norm": 6.926135540008545, "learning_rate": 4.131939311925486e-06, "loss": 0.23306427896022797, "step": 2396 }, { "epoch": 0.6222741433021807, "grad_norm": 7.283302307128906, "learning_rate": 4.131192642471929e-06, "loss": 0.253856360912323, "step": 2397 }, { "epoch": 0.622533748701973, "grad_norm": 3.0230495929718018, "learning_rate": 4.130445728855137e-06, "loss": 0.34676992893218994, "step": 2398 }, { "epoch": 0.6227933541017653, "grad_norm": 2.794384002685547, "learning_rate": 4.129698571207148e-06, "loss": 0.3615227937698364, "step": 2399 }, { "epoch": 0.6230529595015576, "grad_norm": 7.137810707092285, "learning_rate": 4.128951169660043e-06, "loss": 0.27320706844329834, "step": 2400 }, { "epoch": 0.6233125649013499, "grad_norm": 7.884441375732422, "learning_rate": 4.1282035243459446e-06, "loss": 0.30775243043899536, "step": 2401 }, { "epoch": 0.6235721703011423, "grad_norm": 7.091474533081055, "learning_rate": 4.1274556353970196e-06, "loss": 0.3418984115123749, "step": 2402 }, { "epoch": 0.6238317757009346, "grad_norm": 5.399381637573242, "learning_rate": 4.126707502945478e-06, "loss": 0.32174521684646606, "step": 2403 }, { "epoch": 0.6240913811007269, "grad_norm": 7.031735420227051, "learning_rate": 4.125959127123572e-06, "loss": 0.3163999915122986, "step": 2404 }, { "epoch": 0.6243509865005192, "grad_norm": 2.8326940536499023, "learning_rate": 4.125210508063599e-06, "loss": 0.31750842928886414, "step": 2405 }, { "epoch": 0.6246105919003115, "grad_norm": 3.516976833343506, "learning_rate": 4.1244616458978945e-06, "loss": 0.3036954700946808, "step": 2406 }, { "epoch": 0.6248701973001038, "grad_norm": 3.0394625663757324, "learning_rate": 4.1237125407588434e-06, "loss": 0.30907928943634033, "step": 2407 }, { "epoch": 0.6251298026998962, "grad_norm": 7.219979286193848, "learning_rate": 4.1229631927788684e-06, "loss": 0.3252699375152588, "step": 2408 }, { "epoch": 0.6253894080996885, "grad_norm": 8.680892944335938, "learning_rate": 4.122213602090438e-06, "loss": 0.3091425895690918, "step": 2409 }, { "epoch": 0.6256490134994808, "grad_norm": 2.7270402908325195, "learning_rate": 4.121463768826061e-06, "loss": 0.3201948404312134, "step": 2410 }, { "epoch": 0.6259086188992731, "grad_norm": 9.391181945800781, "learning_rate": 4.120713693118293e-06, "loss": 0.40344977378845215, "step": 2411 }, { "epoch": 0.6261682242990654, "grad_norm": 7.186426162719727, "learning_rate": 4.119963375099729e-06, "loss": 0.3930961787700653, "step": 2412 }, { "epoch": 0.6264278296988577, "grad_norm": 6.967550754547119, "learning_rate": 4.119212814903009e-06, "loss": 0.3696841597557068, "step": 2413 }, { "epoch": 0.6266874350986501, "grad_norm": 3.3719429969787598, "learning_rate": 4.118462012660813e-06, "loss": 0.33474141359329224, "step": 2414 }, { "epoch": 0.6269470404984424, "grad_norm": 6.872894763946533, "learning_rate": 4.117710968505867e-06, "loss": 0.32900747656822205, "step": 2415 }, { "epoch": 0.6272066458982347, "grad_norm": 4.498562335968018, "learning_rate": 4.116959682570938e-06, "loss": 0.3410331904888153, "step": 2416 }, { "epoch": 0.627466251298027, "grad_norm": 4.846643924713135, "learning_rate": 4.1162081549888375e-06, "loss": 0.3383703827857971, "step": 2417 }, { "epoch": 0.6277258566978193, "grad_norm": 5.488988876342773, "learning_rate": 4.1154563858924164e-06, "loss": 0.27328410744667053, "step": 2418 }, { "epoch": 0.6279854620976116, "grad_norm": 9.716874122619629, "learning_rate": 4.114704375414572e-06, "loss": 0.35365986824035645, "step": 2419 }, { "epoch": 0.6282450674974039, "grad_norm": 4.846005439758301, "learning_rate": 4.1139521236882405e-06, "loss": 0.28857770562171936, "step": 2420 }, { "epoch": 0.6285046728971962, "grad_norm": 4.553427219390869, "learning_rate": 4.113199630846405e-06, "loss": 0.34783440828323364, "step": 2421 }, { "epoch": 0.6287642782969886, "grad_norm": 3.370999336242676, "learning_rate": 4.112446897022086e-06, "loss": 0.327309787273407, "step": 2422 }, { "epoch": 0.6290238836967809, "grad_norm": 6.85158109664917, "learning_rate": 4.111693922348353e-06, "loss": 0.29221630096435547, "step": 2423 }, { "epoch": 0.6292834890965732, "grad_norm": 7.48311710357666, "learning_rate": 4.110940706958313e-06, "loss": 0.2945317327976227, "step": 2424 }, { "epoch": 0.6295430944963655, "grad_norm": 3.6228270530700684, "learning_rate": 4.110187250985117e-06, "loss": 0.3377698063850403, "step": 2425 }, { "epoch": 0.6298026998961579, "grad_norm": 4.709264278411865, "learning_rate": 4.10943355456196e-06, "loss": 0.3379358649253845, "step": 2426 }, { "epoch": 0.6300623052959502, "grad_norm": 3.3482165336608887, "learning_rate": 4.108679617822077e-06, "loss": 0.3379407823085785, "step": 2427 }, { "epoch": 0.6303219106957425, "grad_norm": 3.1919970512390137, "learning_rate": 4.107925440898747e-06, "loss": 0.3489181399345398, "step": 2428 }, { "epoch": 0.6305815160955348, "grad_norm": 5.918827533721924, "learning_rate": 4.107171023925292e-06, "loss": 0.3700487017631531, "step": 2429 }, { "epoch": 0.6308411214953271, "grad_norm": 2.7738571166992188, "learning_rate": 4.106416367035075e-06, "loss": 0.3520914912223816, "step": 2430 }, { "epoch": 0.6311007268951194, "grad_norm": 9.367537498474121, "learning_rate": 4.1056614703615015e-06, "loss": 0.32127267122268677, "step": 2431 }, { "epoch": 0.6313603322949117, "grad_norm": 8.913078308105469, "learning_rate": 4.1049063340380205e-06, "loss": 0.22724714875221252, "step": 2432 }, { "epoch": 0.631619937694704, "grad_norm": 5.035462379455566, "learning_rate": 4.104150958198123e-06, "loss": 0.3362656235694885, "step": 2433 }, { "epoch": 0.6318795430944963, "grad_norm": 8.303997039794922, "learning_rate": 4.103395342975343e-06, "loss": 0.32028475403785706, "step": 2434 }, { "epoch": 0.6321391484942886, "grad_norm": 3.5590882301330566, "learning_rate": 4.102639488503254e-06, "loss": 0.31004971265792847, "step": 2435 }, { "epoch": 0.632398753894081, "grad_norm": 8.334657669067383, "learning_rate": 4.101883394915475e-06, "loss": 0.16806399822235107, "step": 2436 }, { "epoch": 0.6326583592938733, "grad_norm": 10.111924171447754, "learning_rate": 4.101127062345666e-06, "loss": 0.3465796709060669, "step": 2437 }, { "epoch": 0.6329179646936657, "grad_norm": 8.868069648742676, "learning_rate": 4.100370490927529e-06, "loss": 0.3317239284515381, "step": 2438 }, { "epoch": 0.633177570093458, "grad_norm": 4.903203964233398, "learning_rate": 4.0996136807948085e-06, "loss": 0.341555655002594, "step": 2439 }, { "epoch": 0.6334371754932503, "grad_norm": 6.041769981384277, "learning_rate": 4.0988566320812915e-06, "loss": 0.3105888366699219, "step": 2440 }, { "epoch": 0.6336967808930426, "grad_norm": 4.107263565063477, "learning_rate": 4.098099344920806e-06, "loss": 0.28081363439559937, "step": 2441 }, { "epoch": 0.6339563862928349, "grad_norm": 6.407242774963379, "learning_rate": 4.097341819447224e-06, "loss": 0.37153977155685425, "step": 2442 }, { "epoch": 0.6342159916926272, "grad_norm": 6.032188892364502, "learning_rate": 4.096584055794459e-06, "loss": 0.2500823140144348, "step": 2443 }, { "epoch": 0.6344755970924195, "grad_norm": 8.089326858520508, "learning_rate": 4.095826054096465e-06, "loss": 0.30524706840515137, "step": 2444 }, { "epoch": 0.6347352024922118, "grad_norm": 9.171630859375, "learning_rate": 4.09506781448724e-06, "loss": 0.37273451685905457, "step": 2445 }, { "epoch": 0.6349948078920041, "grad_norm": 8.716008186340332, "learning_rate": 4.094309337100823e-06, "loss": 0.2916400134563446, "step": 2446 }, { "epoch": 0.6352544132917964, "grad_norm": 3.7781927585601807, "learning_rate": 4.093550622071296e-06, "loss": 0.3007410764694214, "step": 2447 }, { "epoch": 0.6355140186915887, "grad_norm": 8.373933792114258, "learning_rate": 4.092791669532784e-06, "loss": 0.3024917542934418, "step": 2448 }, { "epoch": 0.635773624091381, "grad_norm": 3.144047975540161, "learning_rate": 4.0920324796194485e-06, "loss": 0.3443484902381897, "step": 2449 }, { "epoch": 0.6360332294911735, "grad_norm": 8.694659233093262, "learning_rate": 4.091273052465501e-06, "loss": 0.3435049057006836, "step": 2450 }, { "epoch": 0.6362928348909658, "grad_norm": 4.649786949157715, "learning_rate": 4.090513388205187e-06, "loss": 0.2994406819343567, "step": 2451 }, { "epoch": 0.6365524402907581, "grad_norm": 10.927196502685547, "learning_rate": 4.0897534869728e-06, "loss": 0.29077011346817017, "step": 2452 }, { "epoch": 0.6368120456905504, "grad_norm": 9.057405471801758, "learning_rate": 4.088993348902673e-06, "loss": 0.2989828586578369, "step": 2453 }, { "epoch": 0.6370716510903427, "grad_norm": 9.262954711914062, "learning_rate": 4.0882329741291815e-06, "loss": 0.45649462938308716, "step": 2454 }, { "epoch": 0.637331256490135, "grad_norm": 4.472585678100586, "learning_rate": 4.087472362786741e-06, "loss": 0.3155413269996643, "step": 2455 }, { "epoch": 0.6375908618899273, "grad_norm": 4.180543899536133, "learning_rate": 4.086711515009811e-06, "loss": 0.3457105755805969, "step": 2456 }, { "epoch": 0.6378504672897196, "grad_norm": 5.224422931671143, "learning_rate": 4.085950430932892e-06, "loss": 0.341103196144104, "step": 2457 }, { "epoch": 0.6381100726895119, "grad_norm": 3.7398109436035156, "learning_rate": 4.085189110690526e-06, "loss": 0.3258696496486664, "step": 2458 }, { "epoch": 0.6383696780893042, "grad_norm": 5.977757453918457, "learning_rate": 4.084427554417296e-06, "loss": 0.25709229707717896, "step": 2459 }, { "epoch": 0.6386292834890965, "grad_norm": 3.8640997409820557, "learning_rate": 4.08366576224783e-06, "loss": 0.2750639319419861, "step": 2460 }, { "epoch": 0.6388888888888888, "grad_norm": 6.143558502197266, "learning_rate": 4.082903734316793e-06, "loss": 0.36281976103782654, "step": 2461 }, { "epoch": 0.6391484942886813, "grad_norm": 6.967044830322266, "learning_rate": 4.082141470758896e-06, "loss": 0.33136290311813354, "step": 2462 }, { "epoch": 0.6394080996884736, "grad_norm": 8.287379264831543, "learning_rate": 4.081378971708889e-06, "loss": 0.3272934854030609, "step": 2463 }, { "epoch": 0.6396677050882659, "grad_norm": 9.602275848388672, "learning_rate": 4.080616237301563e-06, "loss": 0.2900780439376831, "step": 2464 }, { "epoch": 0.6399273104880582, "grad_norm": 4.278481483459473, "learning_rate": 4.079853267671755e-06, "loss": 0.3061787188053131, "step": 2465 }, { "epoch": 0.6401869158878505, "grad_norm": 7.690736770629883, "learning_rate": 4.079090062954339e-06, "loss": 0.21737505495548248, "step": 2466 }, { "epoch": 0.6404465212876428, "grad_norm": 3.9776058197021484, "learning_rate": 4.078326623284231e-06, "loss": 0.35016167163848877, "step": 2467 }, { "epoch": 0.6407061266874351, "grad_norm": 9.404581069946289, "learning_rate": 4.077562948796391e-06, "loss": 0.32830166816711426, "step": 2468 }, { "epoch": 0.6409657320872274, "grad_norm": 5.662759304046631, "learning_rate": 4.076799039625819e-06, "loss": 0.180329829454422, "step": 2469 }, { "epoch": 0.6412253374870197, "grad_norm": 7.856602191925049, "learning_rate": 4.076034895907556e-06, "loss": 0.3335166871547699, "step": 2470 }, { "epoch": 0.641484942886812, "grad_norm": 5.126280307769775, "learning_rate": 4.075270517776686e-06, "loss": 0.32404929399490356, "step": 2471 }, { "epoch": 0.6417445482866043, "grad_norm": 6.6893720626831055, "learning_rate": 4.0745059053683325e-06, "loss": 0.2180783450603485, "step": 2472 }, { "epoch": 0.6420041536863966, "grad_norm": 3.5045580863952637, "learning_rate": 4.073741058817663e-06, "loss": 0.3055342435836792, "step": 2473 }, { "epoch": 0.642263759086189, "grad_norm": 4.566664218902588, "learning_rate": 4.072975978259883e-06, "loss": 0.3197007179260254, "step": 2474 }, { "epoch": 0.6425233644859814, "grad_norm": 8.106893539428711, "learning_rate": 4.072210663830243e-06, "loss": 0.1923215389251709, "step": 2475 }, { "epoch": 0.6427829698857737, "grad_norm": 5.382383346557617, "learning_rate": 4.0714451156640314e-06, "loss": 0.370941698551178, "step": 2476 }, { "epoch": 0.643042575285566, "grad_norm": 4.574643135070801, "learning_rate": 4.070679333896582e-06, "loss": 0.3369027078151703, "step": 2477 }, { "epoch": 0.6433021806853583, "grad_norm": 7.018088340759277, "learning_rate": 4.069913318663264e-06, "loss": 0.3384588956832886, "step": 2478 }, { "epoch": 0.6435617860851506, "grad_norm": 4.622626781463623, "learning_rate": 4.069147070099495e-06, "loss": 0.3431566655635834, "step": 2479 }, { "epoch": 0.6438213914849429, "grad_norm": 3.339829921722412, "learning_rate": 4.068380588340728e-06, "loss": 0.32102182507514954, "step": 2480 }, { "epoch": 0.6440809968847352, "grad_norm": 2.695858955383301, "learning_rate": 4.067613873522459e-06, "loss": 0.34502047300338745, "step": 2481 }, { "epoch": 0.6443406022845275, "grad_norm": 10.592076301574707, "learning_rate": 4.066846925780226e-06, "loss": 0.29244136810302734, "step": 2482 }, { "epoch": 0.6446002076843198, "grad_norm": 3.3674933910369873, "learning_rate": 4.06607974524961e-06, "loss": 0.32507383823394775, "step": 2483 }, { "epoch": 0.6448598130841121, "grad_norm": 4.7984161376953125, "learning_rate": 4.065312332066229e-06, "loss": 0.3338886499404907, "step": 2484 }, { "epoch": 0.6451194184839044, "grad_norm": 3.89988112449646, "learning_rate": 4.064544686365744e-06, "loss": 0.3205198347568512, "step": 2485 }, { "epoch": 0.6453790238836968, "grad_norm": 9.635738372802734, "learning_rate": 4.063776808283857e-06, "loss": 0.2861558496952057, "step": 2486 }, { "epoch": 0.6456386292834891, "grad_norm": 3.5264406204223633, "learning_rate": 4.0630086979563125e-06, "loss": 0.3003048300743103, "step": 2487 }, { "epoch": 0.6458982346832814, "grad_norm": 3.9697742462158203, "learning_rate": 4.062240355518895e-06, "loss": 0.326557457447052, "step": 2488 }, { "epoch": 0.6461578400830738, "grad_norm": 2.785243511199951, "learning_rate": 4.061471781107427e-06, "loss": 0.34109199047088623, "step": 2489 }, { "epoch": 0.6464174454828661, "grad_norm": 7.098769664764404, "learning_rate": 4.060702974857778e-06, "loss": 0.4123533368110657, "step": 2490 }, { "epoch": 0.6466770508826584, "grad_norm": 5.338868141174316, "learning_rate": 4.059933936905854e-06, "loss": 0.35716956853866577, "step": 2491 }, { "epoch": 0.6469366562824507, "grad_norm": 2.8436882495880127, "learning_rate": 4.059164667387603e-06, "loss": 0.3389894366264343, "step": 2492 }, { "epoch": 0.647196261682243, "grad_norm": 5.450501441955566, "learning_rate": 4.058395166439015e-06, "loss": 0.296586275100708, "step": 2493 }, { "epoch": 0.6474558670820353, "grad_norm": 5.7974138259887695, "learning_rate": 4.05762543419612e-06, "loss": 0.3884284794330597, "step": 2494 }, { "epoch": 0.6477154724818276, "grad_norm": 2.8332908153533936, "learning_rate": 4.056855470794988e-06, "loss": 0.3618446886539459, "step": 2495 }, { "epoch": 0.6479750778816199, "grad_norm": 2.9956817626953125, "learning_rate": 4.0560852763717335e-06, "loss": 0.31544822454452515, "step": 2496 }, { "epoch": 0.6482346832814122, "grad_norm": 2.9092025756835938, "learning_rate": 4.0553148510625065e-06, "loss": 0.29780346155166626, "step": 2497 }, { "epoch": 0.6484942886812046, "grad_norm": 3.892235279083252, "learning_rate": 4.054544195003502e-06, "loss": 0.30538761615753174, "step": 2498 }, { "epoch": 0.6487538940809969, "grad_norm": 3.2127504348754883, "learning_rate": 4.053773308330953e-06, "loss": 0.3593377470970154, "step": 2499 }, { "epoch": 0.6490134994807892, "grad_norm": 3.4887008666992188, "learning_rate": 4.053002191181137e-06, "loss": 0.32803893089294434, "step": 2500 }, { "epoch": 0.6492731048805815, "grad_norm": 7.865793704986572, "learning_rate": 4.052230843690367e-06, "loss": 0.24265074729919434, "step": 2501 }, { "epoch": 0.6495327102803738, "grad_norm": 6.908817768096924, "learning_rate": 4.051459265995001e-06, "loss": 0.3906949758529663, "step": 2502 }, { "epoch": 0.6497923156801662, "grad_norm": 7.333276271820068, "learning_rate": 4.050687458231437e-06, "loss": 0.2085491120815277, "step": 2503 }, { "epoch": 0.6500519210799585, "grad_norm": 3.8974599838256836, "learning_rate": 4.049915420536112e-06, "loss": 0.3035629987716675, "step": 2504 }, { "epoch": 0.6503115264797508, "grad_norm": 3.284252405166626, "learning_rate": 4.049143153045505e-06, "loss": 0.32041293382644653, "step": 2505 }, { "epoch": 0.6505711318795431, "grad_norm": 5.601222038269043, "learning_rate": 4.048370655896135e-06, "loss": 0.30278074741363525, "step": 2506 }, { "epoch": 0.6508307372793354, "grad_norm": 3.7304623126983643, "learning_rate": 4.047597929224561e-06, "loss": 0.3537360727787018, "step": 2507 }, { "epoch": 0.6510903426791277, "grad_norm": 6.965817451477051, "learning_rate": 4.0468249731673845e-06, "loss": 0.2742987275123596, "step": 2508 }, { "epoch": 0.65134994807892, "grad_norm": 8.422172546386719, "learning_rate": 4.046051787861247e-06, "loss": 0.3747042417526245, "step": 2509 }, { "epoch": 0.6516095534787124, "grad_norm": 3.219167470932007, "learning_rate": 4.045278373442828e-06, "loss": 0.3284864127635956, "step": 2510 }, { "epoch": 0.6518691588785047, "grad_norm": 4.801168441772461, "learning_rate": 4.04450473004885e-06, "loss": 0.3273654878139496, "step": 2511 }, { "epoch": 0.652128764278297, "grad_norm": 9.591716766357422, "learning_rate": 4.043730857816077e-06, "loss": 0.34124258160591125, "step": 2512 }, { "epoch": 0.6523883696780893, "grad_norm": 3.1929047107696533, "learning_rate": 4.042956756881311e-06, "loss": 0.338134229183197, "step": 2513 }, { "epoch": 0.6526479750778816, "grad_norm": 7.402088165283203, "learning_rate": 4.042182427381395e-06, "loss": 0.3234824538230896, "step": 2514 }, { "epoch": 0.6529075804776739, "grad_norm": 6.998046398162842, "learning_rate": 4.041407869453212e-06, "loss": 0.31593865156173706, "step": 2515 }, { "epoch": 0.6531671858774662, "grad_norm": 8.165283203125, "learning_rate": 4.0406330832336885e-06, "loss": 0.3206910789012909, "step": 2516 }, { "epoch": 0.6534267912772586, "grad_norm": 6.9969305992126465, "learning_rate": 4.039858068859787e-06, "loss": 0.35253408551216125, "step": 2517 }, { "epoch": 0.6536863966770509, "grad_norm": 2.745944023132324, "learning_rate": 4.039082826468511e-06, "loss": 0.32967427372932434, "step": 2518 }, { "epoch": 0.6539460020768432, "grad_norm": 2.679488182067871, "learning_rate": 4.03830735619691e-06, "loss": 0.330885112285614, "step": 2519 }, { "epoch": 0.6542056074766355, "grad_norm": 2.3832802772521973, "learning_rate": 4.037531658182065e-06, "loss": 0.3374611437320709, "step": 2520 }, { "epoch": 0.6544652128764278, "grad_norm": 4.58578634262085, "learning_rate": 4.036755732561103e-06, "loss": 0.28350815176963806, "step": 2521 }, { "epoch": 0.6547248182762202, "grad_norm": 3.2061355113983154, "learning_rate": 4.035979579471192e-06, "loss": 0.35349079966545105, "step": 2522 }, { "epoch": 0.6549844236760125, "grad_norm": 3.6441328525543213, "learning_rate": 4.035203199049536e-06, "loss": 0.29380160570144653, "step": 2523 }, { "epoch": 0.6552440290758048, "grad_norm": 3.9329168796539307, "learning_rate": 4.0344265914333805e-06, "loss": 0.2713681161403656, "step": 2524 }, { "epoch": 0.6555036344755971, "grad_norm": 9.146724700927734, "learning_rate": 4.033649756760014e-06, "loss": 0.22689178586006165, "step": 2525 }, { "epoch": 0.6557632398753894, "grad_norm": 7.375767707824707, "learning_rate": 4.032872695166763e-06, "loss": 0.3777696490287781, "step": 2526 }, { "epoch": 0.6560228452751817, "grad_norm": 3.01116681098938, "learning_rate": 4.032095406790992e-06, "loss": 0.3122187852859497, "step": 2527 }, { "epoch": 0.656282450674974, "grad_norm": 9.91795825958252, "learning_rate": 4.031317891770109e-06, "loss": 0.3900604844093323, "step": 2528 }, { "epoch": 0.6565420560747663, "grad_norm": 7.067610263824463, "learning_rate": 4.030540150241563e-06, "loss": 0.3722440004348755, "step": 2529 }, { "epoch": 0.6568016614745587, "grad_norm": 2.7363553047180176, "learning_rate": 4.029762182342836e-06, "loss": 0.3324927091598511, "step": 2530 }, { "epoch": 0.657061266874351, "grad_norm": 2.9659464359283447, "learning_rate": 4.02898398821146e-06, "loss": 0.3256697654724121, "step": 2531 }, { "epoch": 0.6573208722741433, "grad_norm": 8.318479537963867, "learning_rate": 4.028205567984999e-06, "loss": 0.2815779447555542, "step": 2532 }, { "epoch": 0.6575804776739356, "grad_norm": 3.843212842941284, "learning_rate": 4.0274269218010606e-06, "loss": 0.3276960551738739, "step": 2533 }, { "epoch": 0.657840083073728, "grad_norm": 3.375422477722168, "learning_rate": 4.026648049797292e-06, "loss": 0.3206127882003784, "step": 2534 }, { "epoch": 0.6580996884735203, "grad_norm": 6.184537410736084, "learning_rate": 4.025868952111379e-06, "loss": 0.35118210315704346, "step": 2535 }, { "epoch": 0.6583592938733126, "grad_norm": 6.746182918548584, "learning_rate": 4.025089628881049e-06, "loss": 0.33748045563697815, "step": 2536 }, { "epoch": 0.6586188992731049, "grad_norm": 6.37700891494751, "learning_rate": 4.024310080244069e-06, "loss": 0.30687904357910156, "step": 2537 }, { "epoch": 0.6588785046728972, "grad_norm": 7.922694206237793, "learning_rate": 4.023530306338244e-06, "loss": 0.36907297372817993, "step": 2538 }, { "epoch": 0.6591381100726895, "grad_norm": 7.544705867767334, "learning_rate": 4.02275030730142e-06, "loss": 0.34006476402282715, "step": 2539 }, { "epoch": 0.6593977154724818, "grad_norm": 3.439668893814087, "learning_rate": 4.021970083271486e-06, "loss": 0.34405025839805603, "step": 2540 }, { "epoch": 0.6596573208722741, "grad_norm": 5.806586265563965, "learning_rate": 4.021189634386363e-06, "loss": 0.29788342118263245, "step": 2541 }, { "epoch": 0.6599169262720664, "grad_norm": 6.627580165863037, "learning_rate": 4.0204089607840204e-06, "loss": 0.35981908440589905, "step": 2542 }, { "epoch": 0.6601765316718587, "grad_norm": 3.0087060928344727, "learning_rate": 4.019628062602462e-06, "loss": 0.35486260056495667, "step": 2543 }, { "epoch": 0.660436137071651, "grad_norm": 2.82303786277771, "learning_rate": 4.018846939979732e-06, "loss": 0.3134194314479828, "step": 2544 }, { "epoch": 0.6606957424714434, "grad_norm": 4.139949798583984, "learning_rate": 4.018065593053917e-06, "loss": 0.2738379240036011, "step": 2545 }, { "epoch": 0.6609553478712358, "grad_norm": 5.258631229400635, "learning_rate": 4.01728402196314e-06, "loss": 0.3413012623786926, "step": 2546 }, { "epoch": 0.6612149532710281, "grad_norm": 7.496180534362793, "learning_rate": 4.016502226845564e-06, "loss": 0.29255789518356323, "step": 2547 }, { "epoch": 0.6614745586708204, "grad_norm": 4.668758392333984, "learning_rate": 4.015720207839394e-06, "loss": 0.30212754011154175, "step": 2548 }, { "epoch": 0.6617341640706127, "grad_norm": 5.240284442901611, "learning_rate": 4.014937965082871e-06, "loss": 0.3067949414253235, "step": 2549 }, { "epoch": 0.661993769470405, "grad_norm": 2.7900912761688232, "learning_rate": 4.014155498714281e-06, "loss": 0.29921630024909973, "step": 2550 }, { "epoch": 0.6622533748701973, "grad_norm": 6.1406097412109375, "learning_rate": 4.0133728088719425e-06, "loss": 0.30513787269592285, "step": 2551 }, { "epoch": 0.6625129802699896, "grad_norm": 7.153687000274658, "learning_rate": 4.0125898956942195e-06, "loss": 0.28693222999572754, "step": 2552 }, { "epoch": 0.6627725856697819, "grad_norm": 3.721061944961548, "learning_rate": 4.011806759319513e-06, "loss": 0.3303060531616211, "step": 2553 }, { "epoch": 0.6630321910695742, "grad_norm": 8.95779037475586, "learning_rate": 4.011023399886262e-06, "loss": 0.2649017572402954, "step": 2554 }, { "epoch": 0.6632917964693665, "grad_norm": 9.263394355773926, "learning_rate": 4.010239817532947e-06, "loss": 0.34552082419395447, "step": 2555 }, { "epoch": 0.6635514018691588, "grad_norm": 8.268113136291504, "learning_rate": 4.009456012398089e-06, "loss": 0.33056703209877014, "step": 2556 }, { "epoch": 0.6638110072689511, "grad_norm": 8.18498706817627, "learning_rate": 4.008671984620246e-06, "loss": 0.3514813780784607, "step": 2557 }, { "epoch": 0.6640706126687436, "grad_norm": 9.006959915161133, "learning_rate": 4.007887734338016e-06, "loss": 0.3576098382472992, "step": 2558 }, { "epoch": 0.6643302180685359, "grad_norm": 7.639322757720947, "learning_rate": 4.007103261690035e-06, "loss": 0.22330854833126068, "step": 2559 }, { "epoch": 0.6645898234683282, "grad_norm": 3.579862594604492, "learning_rate": 4.006318566814982e-06, "loss": 0.3241422474384308, "step": 2560 }, { "epoch": 0.6648494288681205, "grad_norm": 3.1115682125091553, "learning_rate": 4.005533649851573e-06, "loss": 0.27610743045806885, "step": 2561 }, { "epoch": 0.6651090342679128, "grad_norm": 8.387045860290527, "learning_rate": 4.004748510938562e-06, "loss": 0.38869690895080566, "step": 2562 }, { "epoch": 0.6653686396677051, "grad_norm": 17.258272171020508, "learning_rate": 4.003963150214743e-06, "loss": 0.33016979694366455, "step": 2563 }, { "epoch": 0.6656282450674974, "grad_norm": 2.925114393234253, "learning_rate": 4.003177567818952e-06, "loss": 0.2782752811908722, "step": 2564 }, { "epoch": 0.6658878504672897, "grad_norm": 6.178511142730713, "learning_rate": 4.002391763890062e-06, "loss": 0.33208730816841125, "step": 2565 }, { "epoch": 0.666147455867082, "grad_norm": 9.423944473266602, "learning_rate": 4.001605738566983e-06, "loss": 0.258961021900177, "step": 2566 }, { "epoch": 0.6664070612668743, "grad_norm": 7.7978081703186035, "learning_rate": 4.000819491988667e-06, "loss": 0.26460856199264526, "step": 2567 }, { "epoch": 0.6666666666666666, "grad_norm": 2.87829852104187, "learning_rate": 4.000033024294105e-06, "loss": 0.30964431166648865, "step": 2568 }, { "epoch": 0.6669262720664589, "grad_norm": 4.331821918487549, "learning_rate": 3.999246335622327e-06, "loss": 0.31824159622192383, "step": 2569 }, { "epoch": 0.6671858774662512, "grad_norm": 4.782083034515381, "learning_rate": 3.9984594261124e-06, "loss": 0.308363676071167, "step": 2570 }, { "epoch": 0.6674454828660437, "grad_norm": 3.2512760162353516, "learning_rate": 3.997672295903433e-06, "loss": 0.336921751499176, "step": 2571 }, { "epoch": 0.667705088265836, "grad_norm": 9.953797340393066, "learning_rate": 3.996884945134572e-06, "loss": 0.23030631244182587, "step": 2572 }, { "epoch": 0.6679646936656283, "grad_norm": 8.571348190307617, "learning_rate": 3.996097373945003e-06, "loss": 0.3683072030544281, "step": 2573 }, { "epoch": 0.6682242990654206, "grad_norm": 10.33163833618164, "learning_rate": 3.995309582473949e-06, "loss": 0.26569998264312744, "step": 2574 }, { "epoch": 0.6684839044652129, "grad_norm": 8.660994529724121, "learning_rate": 3.994521570860676e-06, "loss": 0.3903065323829651, "step": 2575 }, { "epoch": 0.6687435098650052, "grad_norm": 3.536771297454834, "learning_rate": 3.993733339244484e-06, "loss": 0.3285478353500366, "step": 2576 }, { "epoch": 0.6690031152647975, "grad_norm": 5.565911293029785, "learning_rate": 3.992944887764715e-06, "loss": 0.3139932155609131, "step": 2577 }, { "epoch": 0.6692627206645898, "grad_norm": 2.8973801136016846, "learning_rate": 3.9921562165607494e-06, "loss": 0.35046592354774475, "step": 2578 }, { "epoch": 0.6695223260643821, "grad_norm": 5.223948001861572, "learning_rate": 3.991367325772007e-06, "loss": 0.3061203956604004, "step": 2579 }, { "epoch": 0.6697819314641744, "grad_norm": 7.257591247558594, "learning_rate": 3.990578215537945e-06, "loss": 0.2752454876899719, "step": 2580 }, { "epoch": 0.6700415368639667, "grad_norm": 8.979470252990723, "learning_rate": 3.98978888599806e-06, "loss": 0.3755706548690796, "step": 2581 }, { "epoch": 0.670301142263759, "grad_norm": 7.031370639801025, "learning_rate": 3.988999337291887e-06, "loss": 0.2902371287345886, "step": 2582 }, { "epoch": 0.6705607476635514, "grad_norm": 7.947518348693848, "learning_rate": 3.988209569559001e-06, "loss": 0.19435758888721466, "step": 2583 }, { "epoch": 0.6708203530633438, "grad_norm": 5.709932327270508, "learning_rate": 3.987419582939014e-06, "loss": 0.3136662244796753, "step": 2584 }, { "epoch": 0.6710799584631361, "grad_norm": 4.787562847137451, "learning_rate": 3.986629377571579e-06, "loss": 0.3652523159980774, "step": 2585 }, { "epoch": 0.6713395638629284, "grad_norm": 7.336483001708984, "learning_rate": 3.985838953596383e-06, "loss": 0.28578007221221924, "step": 2586 }, { "epoch": 0.6715991692627207, "grad_norm": 6.127194881439209, "learning_rate": 3.985048311153158e-06, "loss": 0.39165976643562317, "step": 2587 }, { "epoch": 0.671858774662513, "grad_norm": 9.454923629760742, "learning_rate": 3.98425745038167e-06, "loss": 0.3702031672000885, "step": 2588 }, { "epoch": 0.6721183800623053, "grad_norm": 5.897540092468262, "learning_rate": 3.983466371421727e-06, "loss": 0.26557186245918274, "step": 2589 }, { "epoch": 0.6723779854620976, "grad_norm": 3.2570419311523438, "learning_rate": 3.982675074413171e-06, "loss": 0.28629201650619507, "step": 2590 }, { "epoch": 0.6726375908618899, "grad_norm": 7.969073295593262, "learning_rate": 3.981883559495886e-06, "loss": 0.3327793478965759, "step": 2591 }, { "epoch": 0.6728971962616822, "grad_norm": 7.942237377166748, "learning_rate": 3.9810918268097945e-06, "loss": 0.3276994824409485, "step": 2592 }, { "epoch": 0.6731568016614745, "grad_norm": 11.017038345336914, "learning_rate": 3.980299876494857e-06, "loss": 0.2885117828845978, "step": 2593 }, { "epoch": 0.6734164070612668, "grad_norm": 2.3911938667297363, "learning_rate": 3.979507708691071e-06, "loss": 0.33163297176361084, "step": 2594 }, { "epoch": 0.6736760124610592, "grad_norm": 5.548462867736816, "learning_rate": 3.978715323538474e-06, "loss": 0.2861737310886383, "step": 2595 }, { "epoch": 0.6739356178608515, "grad_norm": 9.046089172363281, "learning_rate": 3.977922721177141e-06, "loss": 0.2583770453929901, "step": 2596 }, { "epoch": 0.6741952232606438, "grad_norm": 7.724869728088379, "learning_rate": 3.977129901747187e-06, "loss": 0.34594523906707764, "step": 2597 }, { "epoch": 0.6744548286604362, "grad_norm": 4.997039794921875, "learning_rate": 3.976336865388765e-06, "loss": 0.37316274642944336, "step": 2598 }, { "epoch": 0.6747144340602285, "grad_norm": 2.82814359664917, "learning_rate": 3.975543612242063e-06, "loss": 0.3530294597148895, "step": 2599 }, { "epoch": 0.6749740394600208, "grad_norm": 3.4931976795196533, "learning_rate": 3.974750142447312e-06, "loss": 0.3226662278175354, "step": 2600 }, { "epoch": 0.6752336448598131, "grad_norm": 4.301272392272949, "learning_rate": 3.97395645614478e-06, "loss": 0.2826727628707886, "step": 2601 }, { "epoch": 0.6754932502596054, "grad_norm": 6.4228034019470215, "learning_rate": 3.97316255347477e-06, "loss": 0.30193454027175903, "step": 2602 }, { "epoch": 0.6757528556593977, "grad_norm": 7.02490758895874, "learning_rate": 3.972368434577628e-06, "loss": 0.3439462184906006, "step": 2603 }, { "epoch": 0.67601246105919, "grad_norm": 3.3402509689331055, "learning_rate": 3.971574099593735e-06, "loss": 0.2903215289115906, "step": 2604 }, { "epoch": 0.6762720664589823, "grad_norm": 3.3531064987182617, "learning_rate": 3.970779548663512e-06, "loss": 0.3200923800468445, "step": 2605 }, { "epoch": 0.6765316718587746, "grad_norm": 8.713602066040039, "learning_rate": 3.969984781927417e-06, "loss": 0.3094954490661621, "step": 2606 }, { "epoch": 0.676791277258567, "grad_norm": 6.391956329345703, "learning_rate": 3.969189799525946e-06, "loss": 0.2991541028022766, "step": 2607 }, { "epoch": 0.6770508826583593, "grad_norm": 10.14437484741211, "learning_rate": 3.9683946015996335e-06, "loss": 0.37318041920661926, "step": 2608 }, { "epoch": 0.6773104880581516, "grad_norm": 5.575343608856201, "learning_rate": 3.967599188289054e-06, "loss": 0.2508164644241333, "step": 2609 }, { "epoch": 0.677570093457944, "grad_norm": 6.0176568031311035, "learning_rate": 3.966803559734818e-06, "loss": 0.33326050639152527, "step": 2610 }, { "epoch": 0.6778296988577363, "grad_norm": 4.249515056610107, "learning_rate": 3.966007716077572e-06, "loss": 0.38006794452667236, "step": 2611 }, { "epoch": 0.6780893042575286, "grad_norm": 8.324031829833984, "learning_rate": 3.965211657458006e-06, "loss": 0.3059914708137512, "step": 2612 }, { "epoch": 0.6783489096573209, "grad_norm": 8.149145126342773, "learning_rate": 3.964415384016843e-06, "loss": 0.30266380310058594, "step": 2613 }, { "epoch": 0.6786085150571132, "grad_norm": 6.1648030281066895, "learning_rate": 3.963618895894847e-06, "loss": 0.3121922016143799, "step": 2614 }, { "epoch": 0.6788681204569055, "grad_norm": 6.222634315490723, "learning_rate": 3.962822193232818e-06, "loss": 0.2908061742782593, "step": 2615 }, { "epoch": 0.6791277258566978, "grad_norm": 13.473384857177734, "learning_rate": 3.9620252761715955e-06, "loss": 0.32155221700668335, "step": 2616 }, { "epoch": 0.6793873312564901, "grad_norm": 5.507289886474609, "learning_rate": 3.961228144852056e-06, "loss": 0.3419838547706604, "step": 2617 }, { "epoch": 0.6796469366562824, "grad_norm": 4.659125804901123, "learning_rate": 3.960430799415114e-06, "loss": 0.35250478982925415, "step": 2618 }, { "epoch": 0.6799065420560748, "grad_norm": 9.123775482177734, "learning_rate": 3.959633240001721e-06, "loss": 0.24225574731826782, "step": 2619 }, { "epoch": 0.6801661474558671, "grad_norm": 4.923583030700684, "learning_rate": 3.958835466752868e-06, "loss": 0.2764846086502075, "step": 2620 }, { "epoch": 0.6804257528556594, "grad_norm": 9.522587776184082, "learning_rate": 3.958037479809583e-06, "loss": 0.3141317367553711, "step": 2621 }, { "epoch": 0.6806853582554517, "grad_norm": 10.470528602600098, "learning_rate": 3.957239279312934e-06, "loss": 0.24403664469718933, "step": 2622 }, { "epoch": 0.680944963655244, "grad_norm": 4.331576347351074, "learning_rate": 3.9564408654040206e-06, "loss": 0.31532052159309387, "step": 2623 }, { "epoch": 0.6812045690550363, "grad_norm": 4.049341201782227, "learning_rate": 3.955642238223987e-06, "loss": 0.3377666473388672, "step": 2624 }, { "epoch": 0.6814641744548287, "grad_norm": 8.445314407348633, "learning_rate": 3.954843397914011e-06, "loss": 0.20472440123558044, "step": 2625 }, { "epoch": 0.681723779854621, "grad_norm": 8.28378677368164, "learning_rate": 3.954044344615309e-06, "loss": 0.2254340946674347, "step": 2626 }, { "epoch": 0.6819833852544133, "grad_norm": 6.560732841491699, "learning_rate": 3.953245078469137e-06, "loss": 0.2881813049316406, "step": 2627 }, { "epoch": 0.6822429906542056, "grad_norm": 4.837647914886475, "learning_rate": 3.952445599616784e-06, "loss": 0.2864934206008911, "step": 2628 }, { "epoch": 0.6825025960539979, "grad_norm": 3.568415403366089, "learning_rate": 3.951645908199583e-06, "loss": 0.3145655393600464, "step": 2629 }, { "epoch": 0.6827622014537902, "grad_norm": 4.120980262756348, "learning_rate": 3.950846004358899e-06, "loss": 0.33282631635665894, "step": 2630 }, { "epoch": 0.6830218068535826, "grad_norm": 5.936924934387207, "learning_rate": 3.950045888236137e-06, "loss": 0.3343369662761688, "step": 2631 }, { "epoch": 0.6832814122533749, "grad_norm": 3.656886577606201, "learning_rate": 3.949245559972739e-06, "loss": 0.3541351556777954, "step": 2632 }, { "epoch": 0.6835410176531672, "grad_norm": 3.9093704223632812, "learning_rate": 3.9484450197101856e-06, "loss": 0.3029097318649292, "step": 2633 }, { "epoch": 0.6838006230529595, "grad_norm": 2.945688009262085, "learning_rate": 3.947644267589993e-06, "loss": 0.3465912938117981, "step": 2634 }, { "epoch": 0.6840602284527518, "grad_norm": 3.257112979888916, "learning_rate": 3.946843303753716e-06, "loss": 0.3215251564979553, "step": 2635 }, { "epoch": 0.6843198338525441, "grad_norm": 6.760339260101318, "learning_rate": 3.946042128342948e-06, "loss": 0.34445610642433167, "step": 2636 }, { "epoch": 0.6845794392523364, "grad_norm": 4.545063495635986, "learning_rate": 3.945240741499317e-06, "loss": 0.3087664246559143, "step": 2637 }, { "epoch": 0.6848390446521287, "grad_norm": 7.343133926391602, "learning_rate": 3.94443914336449e-06, "loss": 0.19247876107692719, "step": 2638 }, { "epoch": 0.685098650051921, "grad_norm": 8.423955917358398, "learning_rate": 3.9436373340801724e-06, "loss": 0.31433308124542236, "step": 2639 }, { "epoch": 0.6853582554517134, "grad_norm": 8.286325454711914, "learning_rate": 3.9428353137881034e-06, "loss": 0.3535882532596588, "step": 2640 }, { "epoch": 0.6856178608515057, "grad_norm": 3.8304831981658936, "learning_rate": 3.942033082630064e-06, "loss": 0.31001633405685425, "step": 2641 }, { "epoch": 0.685877466251298, "grad_norm": 5.165207386016846, "learning_rate": 3.94123064074787e-06, "loss": 0.32429805397987366, "step": 2642 }, { "epoch": 0.6861370716510904, "grad_norm": 11.069270133972168, "learning_rate": 3.940427988283374e-06, "loss": 0.3150339126586914, "step": 2643 }, { "epoch": 0.6863966770508827, "grad_norm": 7.285501480102539, "learning_rate": 3.939625125378467e-06, "loss": 0.2696804404258728, "step": 2644 }, { "epoch": 0.686656282450675, "grad_norm": 8.607057571411133, "learning_rate": 3.938822052175076e-06, "loss": 0.28999149799346924, "step": 2645 }, { "epoch": 0.6869158878504673, "grad_norm": 6.314899444580078, "learning_rate": 3.9380187688151664e-06, "loss": 0.2664242386817932, "step": 2646 }, { "epoch": 0.6871754932502596, "grad_norm": 7.600347518920898, "learning_rate": 3.9372152754407415e-06, "loss": 0.2946661710739136, "step": 2647 }, { "epoch": 0.6874350986500519, "grad_norm": 8.66889476776123, "learning_rate": 3.936411572193839e-06, "loss": 0.2940264344215393, "step": 2648 }, { "epoch": 0.6876947040498442, "grad_norm": 4.630010604858398, "learning_rate": 3.9356076592165355e-06, "loss": 0.3664056062698364, "step": 2649 }, { "epoch": 0.6879543094496365, "grad_norm": 3.578162908554077, "learning_rate": 3.934803536650945e-06, "loss": 0.30085039138793945, "step": 2650 }, { "epoch": 0.6882139148494288, "grad_norm": 11.466419219970703, "learning_rate": 3.933999204639218e-06, "loss": 0.3758038282394409, "step": 2651 }, { "epoch": 0.6884735202492211, "grad_norm": 7.675804615020752, "learning_rate": 3.933194663323541e-06, "loss": 0.26886311173439026, "step": 2652 }, { "epoch": 0.6887331256490135, "grad_norm": 7.5456929206848145, "learning_rate": 3.93238991284614e-06, "loss": 0.28223717212677, "step": 2653 }, { "epoch": 0.6889927310488058, "grad_norm": 12.012738227844238, "learning_rate": 3.931584953349274e-06, "loss": 0.24779832363128662, "step": 2654 }, { "epoch": 0.6892523364485982, "grad_norm": 3.720982789993286, "learning_rate": 3.930779784975244e-06, "loss": 0.2885541319847107, "step": 2655 }, { "epoch": 0.6895119418483905, "grad_norm": 7.172191619873047, "learning_rate": 3.929974407866384e-06, "loss": 0.30253589153289795, "step": 2656 }, { "epoch": 0.6897715472481828, "grad_norm": 8.209142684936523, "learning_rate": 3.929168822165067e-06, "loss": 0.27813494205474854, "step": 2657 }, { "epoch": 0.6900311526479751, "grad_norm": 9.300321578979492, "learning_rate": 3.9283630280137e-06, "loss": 0.23084118962287903, "step": 2658 }, { "epoch": 0.6902907580477674, "grad_norm": 8.026824951171875, "learning_rate": 3.927557025554733e-06, "loss": 0.2540002465248108, "step": 2659 }, { "epoch": 0.6905503634475597, "grad_norm": 8.25452995300293, "learning_rate": 3.926750814930645e-06, "loss": 0.265092670917511, "step": 2660 }, { "epoch": 0.690809968847352, "grad_norm": 4.393087863922119, "learning_rate": 3.925944396283957e-06, "loss": 0.3542754054069519, "step": 2661 }, { "epoch": 0.6910695742471443, "grad_norm": 10.876053810119629, "learning_rate": 3.9251377697572254e-06, "loss": 0.3235320448875427, "step": 2662 }, { "epoch": 0.6913291796469366, "grad_norm": 3.156942367553711, "learning_rate": 3.9243309354930426e-06, "loss": 0.3322370648384094, "step": 2663 }, { "epoch": 0.6915887850467289, "grad_norm": 5.271055698394775, "learning_rate": 3.9235238936340405e-06, "loss": 0.2353605031967163, "step": 2664 }, { "epoch": 0.6918483904465212, "grad_norm": 2.8632683753967285, "learning_rate": 3.922716644322883e-06, "loss": 0.2974582016468048, "step": 2665 }, { "epoch": 0.6921079958463136, "grad_norm": 7.979126453399658, "learning_rate": 3.921909187702275e-06, "loss": 0.2527233958244324, "step": 2666 }, { "epoch": 0.692367601246106, "grad_norm": 9.379979133605957, "learning_rate": 3.921101523914956e-06, "loss": 0.2728230953216553, "step": 2667 }, { "epoch": 0.6926272066458983, "grad_norm": 4.8857035636901855, "learning_rate": 3.920293653103701e-06, "loss": 0.3186866044998169, "step": 2668 }, { "epoch": 0.6928868120456906, "grad_norm": 3.713278293609619, "learning_rate": 3.9194855754113245e-06, "loss": 0.41840678453445435, "step": 2669 }, { "epoch": 0.6931464174454829, "grad_norm": 8.874885559082031, "learning_rate": 3.918677290980678e-06, "loss": 0.34839946031570435, "step": 2670 }, { "epoch": 0.6934060228452752, "grad_norm": 6.650426864624023, "learning_rate": 3.917868799954644e-06, "loss": 0.225361168384552, "step": 2671 }, { "epoch": 0.6936656282450675, "grad_norm": 2.4741079807281494, "learning_rate": 3.9170601024761465e-06, "loss": 0.311686635017395, "step": 2672 }, { "epoch": 0.6939252336448598, "grad_norm": 6.879626750946045, "learning_rate": 3.916251198688145e-06, "loss": 0.26246723532676697, "step": 2673 }, { "epoch": 0.6941848390446521, "grad_norm": 6.567450523376465, "learning_rate": 3.915442088733636e-06, "loss": 0.21155136823654175, "step": 2674 }, { "epoch": 0.6944444444444444, "grad_norm": 10.040538787841797, "learning_rate": 3.9146327727556504e-06, "loss": 0.3335777521133423, "step": 2675 }, { "epoch": 0.6947040498442367, "grad_norm": 6.905935764312744, "learning_rate": 3.913823250897257e-06, "loss": 0.3166741132736206, "step": 2676 }, { "epoch": 0.694963655244029, "grad_norm": 8.304520606994629, "learning_rate": 3.913013523301561e-06, "loss": 0.2930475175380707, "step": 2677 }, { "epoch": 0.6952232606438213, "grad_norm": 8.15971851348877, "learning_rate": 3.912203590111703e-06, "loss": 0.382147878408432, "step": 2678 }, { "epoch": 0.6954828660436138, "grad_norm": 4.200296401977539, "learning_rate": 3.911393451470863e-06, "loss": 0.30312711000442505, "step": 2679 }, { "epoch": 0.6957424714434061, "grad_norm": 5.252500534057617, "learning_rate": 3.910583107522251e-06, "loss": 0.33495932817459106, "step": 2680 }, { "epoch": 0.6960020768431984, "grad_norm": 3.986287832260132, "learning_rate": 3.90977255840912e-06, "loss": 0.3756978213787079, "step": 2681 }, { "epoch": 0.6962616822429907, "grad_norm": 9.850417137145996, "learning_rate": 3.9089618042747564e-06, "loss": 0.33785390853881836, "step": 2682 }, { "epoch": 0.696521287642783, "grad_norm": 8.322352409362793, "learning_rate": 3.908150845262483e-06, "loss": 0.2934481203556061, "step": 2683 }, { "epoch": 0.6967808930425753, "grad_norm": 8.539854049682617, "learning_rate": 3.907339681515657e-06, "loss": 0.2341914027929306, "step": 2684 }, { "epoch": 0.6970404984423676, "grad_norm": 6.0657124519348145, "learning_rate": 3.906528313177676e-06, "loss": 0.32880493998527527, "step": 2685 }, { "epoch": 0.6973001038421599, "grad_norm": 11.768784523010254, "learning_rate": 3.90571674039197e-06, "loss": 0.2105695754289627, "step": 2686 }, { "epoch": 0.6975597092419522, "grad_norm": 5.9075541496276855, "learning_rate": 3.904904963302007e-06, "loss": 0.2979600727558136, "step": 2687 }, { "epoch": 0.6978193146417445, "grad_norm": 11.666950225830078, "learning_rate": 3.904092982051289e-06, "loss": 0.20356276631355286, "step": 2688 }, { "epoch": 0.6980789200415368, "grad_norm": 10.045123100280762, "learning_rate": 3.903280796783358e-06, "loss": 0.29115623235702515, "step": 2689 }, { "epoch": 0.6983385254413291, "grad_norm": 7.240841388702393, "learning_rate": 3.902468407641788e-06, "loss": 0.31849199533462524, "step": 2690 }, { "epoch": 0.6985981308411215, "grad_norm": 8.65452766418457, "learning_rate": 3.901655814770193e-06, "loss": 0.35136139392852783, "step": 2691 }, { "epoch": 0.6988577362409139, "grad_norm": 8.102360725402832, "learning_rate": 3.900843018312218e-06, "loss": 0.236316978931427, "step": 2692 }, { "epoch": 0.6991173416407062, "grad_norm": 5.299955368041992, "learning_rate": 3.90003001841155e-06, "loss": 0.36593949794769287, "step": 2693 }, { "epoch": 0.6993769470404985, "grad_norm": 8.477665901184082, "learning_rate": 3.899216815211905e-06, "loss": 0.33683979511260986, "step": 2694 }, { "epoch": 0.6996365524402908, "grad_norm": 5.476753234863281, "learning_rate": 3.898403408857042e-06, "loss": 0.32021212577819824, "step": 2695 }, { "epoch": 0.6998961578400831, "grad_norm": 5.793542385101318, "learning_rate": 3.897589799490749e-06, "loss": 0.30894735455513, "step": 2696 }, { "epoch": 0.7001557632398754, "grad_norm": 4.821333885192871, "learning_rate": 3.8967759872568584e-06, "loss": 0.26404184103012085, "step": 2697 }, { "epoch": 0.7004153686396677, "grad_norm": 8.330096244812012, "learning_rate": 3.89596197229923e-06, "loss": 0.3084874749183655, "step": 2698 }, { "epoch": 0.70067497403946, "grad_norm": 4.636972427368164, "learning_rate": 3.895147754761763e-06, "loss": 0.29395389556884766, "step": 2699 }, { "epoch": 0.7009345794392523, "grad_norm": 2.37479829788208, "learning_rate": 3.894333334788395e-06, "loss": 0.3480883538722992, "step": 2700 }, { "epoch": 0.7011941848390446, "grad_norm": 8.916874885559082, "learning_rate": 3.893518712523094e-06, "loss": 0.27887773513793945, "step": 2701 }, { "epoch": 0.7014537902388369, "grad_norm": 9.761504173278809, "learning_rate": 3.8927038881098675e-06, "loss": 0.27491211891174316, "step": 2702 }, { "epoch": 0.7017133956386293, "grad_norm": 8.356795310974121, "learning_rate": 3.891888861692759e-06, "loss": 0.259745717048645, "step": 2703 }, { "epoch": 0.7019730010384216, "grad_norm": 3.51949405670166, "learning_rate": 3.891073633415845e-06, "loss": 0.2830735146999359, "step": 2704 }, { "epoch": 0.702232606438214, "grad_norm": 8.174824714660645, "learning_rate": 3.89025820342324e-06, "loss": 0.3992067575454712, "step": 2705 }, { "epoch": 0.7024922118380063, "grad_norm": 7.055792808532715, "learning_rate": 3.889442571859093e-06, "loss": 0.26967787742614746, "step": 2706 }, { "epoch": 0.7027518172377986, "grad_norm": 4.906774044036865, "learning_rate": 3.8886267388675885e-06, "loss": 0.2986184358596802, "step": 2707 }, { "epoch": 0.7030114226375909, "grad_norm": 2.883410930633545, "learning_rate": 3.887810704592949e-06, "loss": 0.3375510573387146, "step": 2708 }, { "epoch": 0.7032710280373832, "grad_norm": 3.4697656631469727, "learning_rate": 3.886994469179429e-06, "loss": 0.33658239245414734, "step": 2709 }, { "epoch": 0.7035306334371755, "grad_norm": 6.982010364532471, "learning_rate": 3.886178032771319e-06, "loss": 0.22460433840751648, "step": 2710 }, { "epoch": 0.7037902388369678, "grad_norm": 3.9143097400665283, "learning_rate": 3.8853613955129495e-06, "loss": 0.28277912735939026, "step": 2711 }, { "epoch": 0.7040498442367601, "grad_norm": 4.098861217498779, "learning_rate": 3.88454455754868e-06, "loss": 0.2894723415374756, "step": 2712 }, { "epoch": 0.7043094496365524, "grad_norm": 3.913747787475586, "learning_rate": 3.883727519022912e-06, "loss": 0.3025659918785095, "step": 2713 }, { "epoch": 0.7045690550363447, "grad_norm": 8.13144588470459, "learning_rate": 3.882910280080077e-06, "loss": 0.2683860957622528, "step": 2714 }, { "epoch": 0.7048286604361371, "grad_norm": 3.9787604808807373, "learning_rate": 3.882092840864645e-06, "loss": 0.27258002758026123, "step": 2715 }, { "epoch": 0.7050882658359294, "grad_norm": 3.057452917098999, "learning_rate": 3.88127520152112e-06, "loss": 0.36959707736968994, "step": 2716 }, { "epoch": 0.7053478712357217, "grad_norm": 12.121042251586914, "learning_rate": 3.880457362194041e-06, "loss": 0.30166375637054443, "step": 2717 }, { "epoch": 0.705607476635514, "grad_norm": 4.567600727081299, "learning_rate": 3.879639323027986e-06, "loss": 0.27250760793685913, "step": 2718 }, { "epoch": 0.7058670820353063, "grad_norm": 6.383082389831543, "learning_rate": 3.878821084167563e-06, "loss": 0.2260727733373642, "step": 2719 }, { "epoch": 0.7061266874350987, "grad_norm": 6.7070817947387695, "learning_rate": 3.8780026457574195e-06, "loss": 0.2714445888996124, "step": 2720 }, { "epoch": 0.706386292834891, "grad_norm": 4.317564010620117, "learning_rate": 3.877184007942236e-06, "loss": 0.29006803035736084, "step": 2721 }, { "epoch": 0.7066458982346833, "grad_norm": 4.067117691040039, "learning_rate": 3.8763651708667285e-06, "loss": 0.31015825271606445, "step": 2722 }, { "epoch": 0.7069055036344756, "grad_norm": 3.306581974029541, "learning_rate": 3.8755461346756505e-06, "loss": 0.3257174789905548, "step": 2723 }, { "epoch": 0.7071651090342679, "grad_norm": 6.605037212371826, "learning_rate": 3.874726899513786e-06, "loss": 0.19364696741104126, "step": 2724 }, { "epoch": 0.7074247144340602, "grad_norm": 5.660243988037109, "learning_rate": 3.873907465525959e-06, "loss": 0.29791155457496643, "step": 2725 }, { "epoch": 0.7076843198338525, "grad_norm": 2.800532817840576, "learning_rate": 3.873087832857026e-06, "loss": 0.2951221466064453, "step": 2726 }, { "epoch": 0.7079439252336449, "grad_norm": 8.609940528869629, "learning_rate": 3.8722680016518796e-06, "loss": 0.29951268434524536, "step": 2727 }, { "epoch": 0.7082035306334372, "grad_norm": 4.885922431945801, "learning_rate": 3.8714479720554475e-06, "loss": 0.2611781358718872, "step": 2728 }, { "epoch": 0.7084631360332295, "grad_norm": 6.957265853881836, "learning_rate": 3.870627744212691e-06, "loss": 0.22737687826156616, "step": 2729 }, { "epoch": 0.7087227414330218, "grad_norm": 3.6713154315948486, "learning_rate": 3.869807318268609e-06, "loss": 0.32382702827453613, "step": 2730 }, { "epoch": 0.7089823468328141, "grad_norm": 4.867636203765869, "learning_rate": 3.868986694368232e-06, "loss": 0.29525789618492126, "step": 2731 }, { "epoch": 0.7092419522326064, "grad_norm": 10.00518798828125, "learning_rate": 3.8681658726566305e-06, "loss": 0.2699679732322693, "step": 2732 }, { "epoch": 0.7095015576323987, "grad_norm": 5.649450778961182, "learning_rate": 3.8673448532789044e-06, "loss": 0.2618623971939087, "step": 2733 }, { "epoch": 0.7097611630321911, "grad_norm": 6.307582855224609, "learning_rate": 3.8665236363801915e-06, "loss": 0.27105867862701416, "step": 2734 }, { "epoch": 0.7100207684319834, "grad_norm": 9.694891929626465, "learning_rate": 3.865702222105666e-06, "loss": 0.18927867710590363, "step": 2735 }, { "epoch": 0.7102803738317757, "grad_norm": 9.020992279052734, "learning_rate": 3.8648806106005335e-06, "loss": 0.3287716805934906, "step": 2736 }, { "epoch": 0.710539979231568, "grad_norm": 7.9627685546875, "learning_rate": 3.864058802010036e-06, "loss": 0.3008835017681122, "step": 2737 }, { "epoch": 0.7107995846313603, "grad_norm": 11.359800338745117, "learning_rate": 3.86323679647945e-06, "loss": 0.26625344157218933, "step": 2738 }, { "epoch": 0.7110591900311527, "grad_norm": 4.246142387390137, "learning_rate": 3.8624145941540896e-06, "loss": 0.2889304757118225, "step": 2739 }, { "epoch": 0.711318795430945, "grad_norm": 6.484511375427246, "learning_rate": 3.861592195179299e-06, "loss": 0.303253710269928, "step": 2740 }, { "epoch": 0.7115784008307373, "grad_norm": 3.132106304168701, "learning_rate": 3.860769599700461e-06, "loss": 0.28891998529434204, "step": 2741 }, { "epoch": 0.7118380062305296, "grad_norm": 9.826004028320312, "learning_rate": 3.859946807862991e-06, "loss": 0.33282288908958435, "step": 2742 }, { "epoch": 0.7120976116303219, "grad_norm": 9.36833667755127, "learning_rate": 3.8591238198123395e-06, "loss": 0.2725912928581238, "step": 2743 }, { "epoch": 0.7123572170301142, "grad_norm": 9.296135902404785, "learning_rate": 3.8583006356939926e-06, "loss": 0.24255633354187012, "step": 2744 }, { "epoch": 0.7126168224299065, "grad_norm": 8.857633590698242, "learning_rate": 3.85747725565347e-06, "loss": 0.2999061644077301, "step": 2745 }, { "epoch": 0.7128764278296988, "grad_norm": 2.7605013847351074, "learning_rate": 3.856653679836326e-06, "loss": 0.351105660200119, "step": 2746 }, { "epoch": 0.7131360332294912, "grad_norm": 3.2493083477020264, "learning_rate": 3.85582990838815e-06, "loss": 0.3495042324066162, "step": 2747 }, { "epoch": 0.7133956386292835, "grad_norm": 10.046037673950195, "learning_rate": 3.855005941454567e-06, "loss": 0.401375949382782, "step": 2748 }, { "epoch": 0.7136552440290758, "grad_norm": 3.468674898147583, "learning_rate": 3.854181779181235e-06, "loss": 0.2961730360984802, "step": 2749 }, { "epoch": 0.7139148494288681, "grad_norm": 9.201087951660156, "learning_rate": 3.853357421713847e-06, "loss": 0.20112046599388123, "step": 2750 }, { "epoch": 0.7141744548286605, "grad_norm": 3.7459986209869385, "learning_rate": 3.852532869198129e-06, "loss": 0.3396592140197754, "step": 2751 }, { "epoch": 0.7144340602284528, "grad_norm": 3.632976770401001, "learning_rate": 3.851708121779846e-06, "loss": 0.30773425102233887, "step": 2752 }, { "epoch": 0.7146936656282451, "grad_norm": 2.628495931625366, "learning_rate": 3.8508831796047925e-06, "loss": 0.33862704038619995, "step": 2753 }, { "epoch": 0.7149532710280374, "grad_norm": 3.5290534496307373, "learning_rate": 3.850058042818799e-06, "loss": 0.30739498138427734, "step": 2754 }, { "epoch": 0.7152128764278297, "grad_norm": 2.776665210723877, "learning_rate": 3.849232711567732e-06, "loss": 0.3204555809497833, "step": 2755 }, { "epoch": 0.715472481827622, "grad_norm": 7.707402229309082, "learning_rate": 3.848407185997491e-06, "loss": 0.3649912476539612, "step": 2756 }, { "epoch": 0.7157320872274143, "grad_norm": 4.32134485244751, "learning_rate": 3.847581466254009e-06, "loss": 0.33103734254837036, "step": 2757 }, { "epoch": 0.7159916926272066, "grad_norm": 8.040523529052734, "learning_rate": 3.846755552483256e-06, "loss": 0.23845230042934418, "step": 2758 }, { "epoch": 0.7162512980269989, "grad_norm": 3.363400459289551, "learning_rate": 3.845929444831234e-06, "loss": 0.3089471459388733, "step": 2759 }, { "epoch": 0.7165109034267912, "grad_norm": 7.3770833015441895, "learning_rate": 3.845103143443978e-06, "loss": 0.25321000814437866, "step": 2760 }, { "epoch": 0.7167705088265836, "grad_norm": 9.292682647705078, "learning_rate": 3.844276648467561e-06, "loss": 0.254925400018692, "step": 2761 }, { "epoch": 0.7170301142263759, "grad_norm": 4.465417861938477, "learning_rate": 3.843449960048089e-06, "loss": 0.34400397539138794, "step": 2762 }, { "epoch": 0.7172897196261683, "grad_norm": 3.9987964630126953, "learning_rate": 3.8426230783317e-06, "loss": 0.29578226804733276, "step": 2763 }, { "epoch": 0.7175493250259606, "grad_norm": 5.397037506103516, "learning_rate": 3.841796003464569e-06, "loss": 0.3244619369506836, "step": 2764 }, { "epoch": 0.7178089304257529, "grad_norm": 9.425292015075684, "learning_rate": 3.8409687355929035e-06, "loss": 0.25552481412887573, "step": 2765 }, { "epoch": 0.7180685358255452, "grad_norm": 7.613983631134033, "learning_rate": 3.840141274862945e-06, "loss": 0.3411557674407959, "step": 2766 }, { "epoch": 0.7183281412253375, "grad_norm": 4.613419055938721, "learning_rate": 3.83931362142097e-06, "loss": 0.2999047040939331, "step": 2767 }, { "epoch": 0.7185877466251298, "grad_norm": 7.623532295227051, "learning_rate": 3.83848577541329e-06, "loss": 0.26299452781677246, "step": 2768 }, { "epoch": 0.7188473520249221, "grad_norm": 8.579442024230957, "learning_rate": 3.837657736986246e-06, "loss": 0.2763642966747284, "step": 2769 }, { "epoch": 0.7191069574247144, "grad_norm": 4.255162715911865, "learning_rate": 3.8368295062862196e-06, "loss": 0.3054724931716919, "step": 2770 }, { "epoch": 0.7193665628245067, "grad_norm": 8.90310001373291, "learning_rate": 3.836001083459621e-06, "loss": 0.3384072780609131, "step": 2771 }, { "epoch": 0.719626168224299, "grad_norm": 10.70047664642334, "learning_rate": 3.835172468652897e-06, "loss": 0.24224156141281128, "step": 2772 }, { "epoch": 0.7198857736240913, "grad_norm": 3.8619346618652344, "learning_rate": 3.834343662012528e-06, "loss": 0.32753312587738037, "step": 2773 }, { "epoch": 0.7201453790238836, "grad_norm": 6.062758445739746, "learning_rate": 3.833514663685027e-06, "loss": 0.34802842140197754, "step": 2774 }, { "epoch": 0.7204049844236761, "grad_norm": 10.959940910339355, "learning_rate": 3.832685473816944e-06, "loss": 0.30702611804008484, "step": 2775 }, { "epoch": 0.7206645898234684, "grad_norm": 5.340280055999756, "learning_rate": 3.831856092554858e-06, "loss": 0.3834133446216583, "step": 2776 }, { "epoch": 0.7209241952232607, "grad_norm": 4.662890911102295, "learning_rate": 3.8310265200453865e-06, "loss": 0.2799415588378906, "step": 2777 }, { "epoch": 0.721183800623053, "grad_norm": 3.0866315364837646, "learning_rate": 3.830196756435179e-06, "loss": 0.31915000081062317, "step": 2778 }, { "epoch": 0.7214434060228453, "grad_norm": 7.382820129394531, "learning_rate": 3.829366801870917e-06, "loss": 0.2656550407409668, "step": 2779 }, { "epoch": 0.7217030114226376, "grad_norm": 3.5346505641937256, "learning_rate": 3.828536656499321e-06, "loss": 0.26150473952293396, "step": 2780 }, { "epoch": 0.7219626168224299, "grad_norm": 4.41226863861084, "learning_rate": 3.827706320467137e-06, "loss": 0.3137522339820862, "step": 2781 }, { "epoch": 0.7222222222222222, "grad_norm": 3.9485762119293213, "learning_rate": 3.826875793921152e-06, "loss": 0.3079371154308319, "step": 2782 }, { "epoch": 0.7224818276220145, "grad_norm": 4.869454860687256, "learning_rate": 3.826045077008185e-06, "loss": 0.30382829904556274, "step": 2783 }, { "epoch": 0.7227414330218068, "grad_norm": 11.829717636108398, "learning_rate": 3.825214169875085e-06, "loss": 0.24948623776435852, "step": 2784 }, { "epoch": 0.7230010384215991, "grad_norm": 9.805453300476074, "learning_rate": 3.82438307266874e-06, "loss": 0.2944403290748596, "step": 2785 }, { "epoch": 0.7232606438213914, "grad_norm": 4.020649433135986, "learning_rate": 3.8235517855360685e-06, "loss": 0.3383059501647949, "step": 2786 }, { "epoch": 0.7235202492211839, "grad_norm": 3.993490695953369, "learning_rate": 3.822720308624021e-06, "loss": 0.31873008608818054, "step": 2787 }, { "epoch": 0.7237798546209762, "grad_norm": 6.6200337409973145, "learning_rate": 3.821888642079586e-06, "loss": 0.20825865864753723, "step": 2788 }, { "epoch": 0.7240394600207685, "grad_norm": 5.947829246520996, "learning_rate": 3.821056786049781e-06, "loss": 0.30268919467926025, "step": 2789 }, { "epoch": 0.7242990654205608, "grad_norm": 8.256492614746094, "learning_rate": 3.8202247406816614e-06, "loss": 0.26798713207244873, "step": 2790 }, { "epoch": 0.7245586708203531, "grad_norm": 8.371309280395508, "learning_rate": 3.819392506122312e-06, "loss": 0.20574559271335602, "step": 2791 }, { "epoch": 0.7248182762201454, "grad_norm": 7.245604515075684, "learning_rate": 3.8185600825188526e-06, "loss": 0.3926126956939697, "step": 2792 }, { "epoch": 0.7250778816199377, "grad_norm": 5.223219394683838, "learning_rate": 3.817727470018439e-06, "loss": 0.33247053623199463, "step": 2793 }, { "epoch": 0.72533748701973, "grad_norm": 3.3409290313720703, "learning_rate": 3.816894668768255e-06, "loss": 0.272184818983078, "step": 2794 }, { "epoch": 0.7255970924195223, "grad_norm": 3.9684364795684814, "learning_rate": 3.816061678915523e-06, "loss": 0.29985934495925903, "step": 2795 }, { "epoch": 0.7258566978193146, "grad_norm": 7.306569576263428, "learning_rate": 3.815228500607495e-06, "loss": 0.2150757610797882, "step": 2796 }, { "epoch": 0.7261163032191069, "grad_norm": 9.067239761352539, "learning_rate": 3.8143951339914596e-06, "loss": 0.3075358271598816, "step": 2797 }, { "epoch": 0.7263759086188992, "grad_norm": 7.151318073272705, "learning_rate": 3.813561579214736e-06, "loss": 0.29046911001205444, "step": 2798 }, { "epoch": 0.7266355140186916, "grad_norm": 9.121228218078613, "learning_rate": 3.8127278364246766e-06, "loss": 0.2339383363723755, "step": 2799 }, { "epoch": 0.726895119418484, "grad_norm": 7.479659080505371, "learning_rate": 3.811893905768669e-06, "loss": 0.24910153448581696, "step": 2800 }, { "epoch": 0.7271547248182763, "grad_norm": 3.8990793228149414, "learning_rate": 3.811059787394133e-06, "loss": 0.31937772035598755, "step": 2801 }, { "epoch": 0.7274143302180686, "grad_norm": 10.787315368652344, "learning_rate": 3.8102254814485225e-06, "loss": 0.25788789987564087, "step": 2802 }, { "epoch": 0.7276739356178609, "grad_norm": 5.1238322257995605, "learning_rate": 3.8093909880793223e-06, "loss": 0.2861466407775879, "step": 2803 }, { "epoch": 0.7279335410176532, "grad_norm": 4.069517135620117, "learning_rate": 3.8085563074340513e-06, "loss": 0.33927053213119507, "step": 2804 }, { "epoch": 0.7281931464174455, "grad_norm": 10.104093551635742, "learning_rate": 3.8077214396602642e-06, "loss": 0.3967769145965576, "step": 2805 }, { "epoch": 0.7284527518172378, "grad_norm": 4.556069374084473, "learning_rate": 3.806886384905545e-06, "loss": 0.331945538520813, "step": 2806 }, { "epoch": 0.7287123572170301, "grad_norm": 11.903525352478027, "learning_rate": 3.806051143317512e-06, "loss": 0.33556294441223145, "step": 2807 }, { "epoch": 0.7289719626168224, "grad_norm": 9.474061965942383, "learning_rate": 3.805215715043818e-06, "loss": 0.21740609407424927, "step": 2808 }, { "epoch": 0.7292315680166147, "grad_norm": 5.7770586013793945, "learning_rate": 3.8043801002321457e-06, "loss": 0.32316985726356506, "step": 2809 }, { "epoch": 0.729491173416407, "grad_norm": 12.733331680297852, "learning_rate": 3.8035442990302145e-06, "loss": 0.3020275831222534, "step": 2810 }, { "epoch": 0.7297507788161994, "grad_norm": 9.655003547668457, "learning_rate": 3.802708311585774e-06, "loss": 0.2512288987636566, "step": 2811 }, { "epoch": 0.7300103842159917, "grad_norm": 11.126626014709473, "learning_rate": 3.801872138046608e-06, "loss": 0.30606377124786377, "step": 2812 }, { "epoch": 0.730269989615784, "grad_norm": 3.9786159992218018, "learning_rate": 3.801035778560532e-06, "loss": 0.3252147436141968, "step": 2813 }, { "epoch": 0.7305295950155763, "grad_norm": 9.391417503356934, "learning_rate": 3.800199233275397e-06, "loss": 0.23602595925331116, "step": 2814 }, { "epoch": 0.7307892004153687, "grad_norm": 10.433959007263184, "learning_rate": 3.7993625023390835e-06, "loss": 0.19523172080516815, "step": 2815 }, { "epoch": 0.731048805815161, "grad_norm": 9.976067543029785, "learning_rate": 3.7985255858995067e-06, "loss": 0.2515241801738739, "step": 2816 }, { "epoch": 0.7313084112149533, "grad_norm": 6.678774356842041, "learning_rate": 3.7976884841046135e-06, "loss": 0.29718124866485596, "step": 2817 }, { "epoch": 0.7315680166147456, "grad_norm": 8.867351531982422, "learning_rate": 3.7968511971023863e-06, "loss": 0.23014330863952637, "step": 2818 }, { "epoch": 0.7318276220145379, "grad_norm": 2.9421908855438232, "learning_rate": 3.7960137250408374e-06, "loss": 0.34495171904563904, "step": 2819 }, { "epoch": 0.7320872274143302, "grad_norm": 6.88255500793457, "learning_rate": 3.795176068068012e-06, "loss": 0.3737315535545349, "step": 2820 }, { "epoch": 0.7323468328141225, "grad_norm": 3.2055470943450928, "learning_rate": 3.794338226331989e-06, "loss": 0.3073786497116089, "step": 2821 }, { "epoch": 0.7326064382139148, "grad_norm": 11.496360778808594, "learning_rate": 3.7935001999808796e-06, "loss": 0.36075854301452637, "step": 2822 }, { "epoch": 0.7328660436137072, "grad_norm": 5.87399435043335, "learning_rate": 3.792661989162828e-06, "loss": 0.2965511679649353, "step": 2823 }, { "epoch": 0.7331256490134995, "grad_norm": 5.405280113220215, "learning_rate": 3.7918235940260108e-06, "loss": 0.3296642303466797, "step": 2824 }, { "epoch": 0.7333852544132918, "grad_norm": 3.6299328804016113, "learning_rate": 3.790985014718636e-06, "loss": 0.3210581839084625, "step": 2825 }, { "epoch": 0.7336448598130841, "grad_norm": 4.188785076141357, "learning_rate": 3.790146251388947e-06, "loss": 0.30883079767227173, "step": 2826 }, { "epoch": 0.7339044652128764, "grad_norm": 10.354411125183105, "learning_rate": 3.789307304185216e-06, "loss": 0.31561505794525146, "step": 2827 }, { "epoch": 0.7341640706126688, "grad_norm": 9.04006290435791, "learning_rate": 3.7884681732557517e-06, "loss": 0.23117098212242126, "step": 2828 }, { "epoch": 0.7344236760124611, "grad_norm": 8.845956802368164, "learning_rate": 3.7876288587488913e-06, "loss": 0.23699481785297394, "step": 2829 }, { "epoch": 0.7346832814122534, "grad_norm": 8.403414726257324, "learning_rate": 3.786789360813007e-06, "loss": 0.37631601095199585, "step": 2830 }, { "epoch": 0.7349428868120457, "grad_norm": 9.573957443237305, "learning_rate": 3.785949679596504e-06, "loss": 0.24593448638916016, "step": 2831 }, { "epoch": 0.735202492211838, "grad_norm": 2.555854082107544, "learning_rate": 3.785109815247817e-06, "loss": 0.32394173741340637, "step": 2832 }, { "epoch": 0.7354620976116303, "grad_norm": 9.381113052368164, "learning_rate": 3.784269767915416e-06, "loss": 0.2685900032520294, "step": 2833 }, { "epoch": 0.7357217030114226, "grad_norm": 3.453284978866577, "learning_rate": 3.7834295377478013e-06, "loss": 0.33096733689308167, "step": 2834 }, { "epoch": 0.735981308411215, "grad_norm": 3.5615785121917725, "learning_rate": 3.7825891248935066e-06, "loss": 0.2724810242652893, "step": 2835 }, { "epoch": 0.7362409138110073, "grad_norm": 4.612658500671387, "learning_rate": 3.7817485295010982e-06, "loss": 0.25722846388816833, "step": 2836 }, { "epoch": 0.7365005192107996, "grad_norm": 9.96161937713623, "learning_rate": 3.7809077517191733e-06, "loss": 0.3323840796947479, "step": 2837 }, { "epoch": 0.7367601246105919, "grad_norm": 4.160588264465332, "learning_rate": 3.780066791696363e-06, "loss": 0.28650885820388794, "step": 2838 }, { "epoch": 0.7370197300103842, "grad_norm": 4.203136920928955, "learning_rate": 3.779225649581329e-06, "loss": 0.37026116251945496, "step": 2839 }, { "epoch": 0.7372793354101765, "grad_norm": 7.200605869293213, "learning_rate": 3.778384325522767e-06, "loss": 0.20781704783439636, "step": 2840 }, { "epoch": 0.7375389408099688, "grad_norm": 3.3183493614196777, "learning_rate": 3.7775428196694023e-06, "loss": 0.30211466550827026, "step": 2841 }, { "epoch": 0.7377985462097612, "grad_norm": 8.837438583374023, "learning_rate": 3.776701132169995e-06, "loss": 0.17130528390407562, "step": 2842 }, { "epoch": 0.7380581516095535, "grad_norm": 7.526297092437744, "learning_rate": 3.7758592631733354e-06, "loss": 0.3272821605205536, "step": 2843 }, { "epoch": 0.7383177570093458, "grad_norm": 6.812796115875244, "learning_rate": 3.775017212828248e-06, "loss": 0.31410276889801025, "step": 2844 }, { "epoch": 0.7385773624091381, "grad_norm": 7.672812461853027, "learning_rate": 3.774174981283587e-06, "loss": 0.36987024545669556, "step": 2845 }, { "epoch": 0.7388369678089304, "grad_norm": 5.394763469696045, "learning_rate": 3.773332568688239e-06, "loss": 0.31638360023498535, "step": 2846 }, { "epoch": 0.7390965732087228, "grad_norm": 5.330357074737549, "learning_rate": 3.7724899751911254e-06, "loss": 0.26625359058380127, "step": 2847 }, { "epoch": 0.7393561786085151, "grad_norm": 4.23008918762207, "learning_rate": 3.7716472009411944e-06, "loss": 0.3036770820617676, "step": 2848 }, { "epoch": 0.7396157840083074, "grad_norm": 4.86529016494751, "learning_rate": 3.7708042460874315e-06, "loss": 0.31768935918807983, "step": 2849 }, { "epoch": 0.7398753894080997, "grad_norm": 3.6981263160705566, "learning_rate": 3.769961110778852e-06, "loss": 0.3316410779953003, "step": 2850 }, { "epoch": 0.740134994807892, "grad_norm": 11.226632118225098, "learning_rate": 3.7691177951645018e-06, "loss": 0.29591527581214905, "step": 2851 }, { "epoch": 0.7403946002076843, "grad_norm": 5.068914413452148, "learning_rate": 3.7682742993934595e-06, "loss": 0.3470991849899292, "step": 2852 }, { "epoch": 0.7406542056074766, "grad_norm": 2.9137866497039795, "learning_rate": 3.7674306236148374e-06, "loss": 0.3286024332046509, "step": 2853 }, { "epoch": 0.7409138110072689, "grad_norm": 5.108968734741211, "learning_rate": 3.7665867679777763e-06, "loss": 0.2775733470916748, "step": 2854 }, { "epoch": 0.7411734164070612, "grad_norm": 7.9017181396484375, "learning_rate": 3.7657427326314523e-06, "loss": 0.2673666775226593, "step": 2855 }, { "epoch": 0.7414330218068536, "grad_norm": 4.704021453857422, "learning_rate": 3.7648985177250697e-06, "loss": 0.3069136142730713, "step": 2856 }, { "epoch": 0.7416926272066459, "grad_norm": 10.400687217712402, "learning_rate": 3.764054123407867e-06, "loss": 0.23728050291538239, "step": 2857 }, { "epoch": 0.7419522326064382, "grad_norm": 6.507105827331543, "learning_rate": 3.763209549829115e-06, "loss": 0.26119470596313477, "step": 2858 }, { "epoch": 0.7422118380062306, "grad_norm": 5.445512294769287, "learning_rate": 3.7623647971381132e-06, "loss": 0.30432868003845215, "step": 2859 }, { "epoch": 0.7424714434060229, "grad_norm": 9.123064994812012, "learning_rate": 3.7615198654841957e-06, "loss": 0.24664106965065002, "step": 2860 }, { "epoch": 0.7427310488058152, "grad_norm": 8.282267570495605, "learning_rate": 3.760674755016727e-06, "loss": 0.342060923576355, "step": 2861 }, { "epoch": 0.7429906542056075, "grad_norm": 5.152033805847168, "learning_rate": 3.7598294658851025e-06, "loss": 0.2581790089607239, "step": 2862 }, { "epoch": 0.7432502596053998, "grad_norm": 9.902706146240234, "learning_rate": 3.758983998238751e-06, "loss": 0.3184623718261719, "step": 2863 }, { "epoch": 0.7435098650051921, "grad_norm": 7.689916133880615, "learning_rate": 3.758138352227131e-06, "loss": 0.2533653974533081, "step": 2864 }, { "epoch": 0.7437694704049844, "grad_norm": 4.233395576477051, "learning_rate": 3.757292527999734e-06, "loss": 0.263846218585968, "step": 2865 }, { "epoch": 0.7440290758047767, "grad_norm": 9.916315078735352, "learning_rate": 3.756446525706081e-06, "loss": 0.23585373163223267, "step": 2866 }, { "epoch": 0.744288681204569, "grad_norm": 8.358806610107422, "learning_rate": 3.7556003454957273e-06, "loss": 0.2354654222726822, "step": 2867 }, { "epoch": 0.7445482866043613, "grad_norm": 4.237387180328369, "learning_rate": 3.754753987518259e-06, "loss": 0.309357225894928, "step": 2868 }, { "epoch": 0.7448078920041536, "grad_norm": 7.979995250701904, "learning_rate": 3.75390745192329e-06, "loss": 0.3482966721057892, "step": 2869 }, { "epoch": 0.745067497403946, "grad_norm": 6.57728385925293, "learning_rate": 3.75306073886047e-06, "loss": 0.22717520594596863, "step": 2870 }, { "epoch": 0.7453271028037384, "grad_norm": 7.637478828430176, "learning_rate": 3.752213848479479e-06, "loss": 0.3459545075893402, "step": 2871 }, { "epoch": 0.7455867082035307, "grad_norm": 6.645857810974121, "learning_rate": 3.751366780930027e-06, "loss": 0.2617373466491699, "step": 2872 }, { "epoch": 0.745846313603323, "grad_norm": 12.929347038269043, "learning_rate": 3.7505195363618563e-06, "loss": 0.34735405445098877, "step": 2873 }, { "epoch": 0.7461059190031153, "grad_norm": 4.8237128257751465, "learning_rate": 3.7496721149247407e-06, "loss": 0.2973061203956604, "step": 2874 }, { "epoch": 0.7463655244029076, "grad_norm": 8.719959259033203, "learning_rate": 3.7488245167684846e-06, "loss": 0.23949924111366272, "step": 2875 }, { "epoch": 0.7466251298026999, "grad_norm": 10.831768035888672, "learning_rate": 3.7479767420429235e-06, "loss": 0.29149383306503296, "step": 2876 }, { "epoch": 0.7468847352024922, "grad_norm": 3.1354777812957764, "learning_rate": 3.7471287908979254e-06, "loss": 0.34027981758117676, "step": 2877 }, { "epoch": 0.7471443406022845, "grad_norm": 9.53782844543457, "learning_rate": 3.746280663483389e-06, "loss": 0.2355024814605713, "step": 2878 }, { "epoch": 0.7474039460020768, "grad_norm": 6.114735126495361, "learning_rate": 3.7454323599492414e-06, "loss": 0.30448365211486816, "step": 2879 }, { "epoch": 0.7476635514018691, "grad_norm": 10.929338455200195, "learning_rate": 3.744583880445446e-06, "loss": 0.24992233514785767, "step": 2880 }, { "epoch": 0.7479231568016614, "grad_norm": 8.11620807647705, "learning_rate": 3.743735225121994e-06, "loss": 0.2211480736732483, "step": 2881 }, { "epoch": 0.7481827622014537, "grad_norm": 6.627674579620361, "learning_rate": 3.7428863941289067e-06, "loss": 0.25804880261421204, "step": 2882 }, { "epoch": 0.7484423676012462, "grad_norm": 9.639720916748047, "learning_rate": 3.742037387616239e-06, "loss": 0.14270900189876556, "step": 2883 }, { "epoch": 0.7487019730010385, "grad_norm": 10.133200645446777, "learning_rate": 3.7411882057340766e-06, "loss": 0.27414071559906006, "step": 2884 }, { "epoch": 0.7489615784008308, "grad_norm": 4.179865837097168, "learning_rate": 3.7403388486325345e-06, "loss": 0.3143153786659241, "step": 2885 }, { "epoch": 0.7492211838006231, "grad_norm": 10.702803611755371, "learning_rate": 3.739489316461759e-06, "loss": 0.2520866394042969, "step": 2886 }, { "epoch": 0.7494807892004154, "grad_norm": 5.94239616394043, "learning_rate": 3.7386396093719297e-06, "loss": 0.3403542637825012, "step": 2887 }, { "epoch": 0.7497403946002077, "grad_norm": 5.233088493347168, "learning_rate": 3.7377897275132534e-06, "loss": 0.3027767539024353, "step": 2888 }, { "epoch": 0.75, "grad_norm": 11.58723258972168, "learning_rate": 3.736939671035971e-06, "loss": 0.30452585220336914, "step": 2889 }, { "epoch": 0.7502596053997923, "grad_norm": 11.053851127624512, "learning_rate": 3.736089440090353e-06, "loss": 0.27406445145606995, "step": 2890 }, { "epoch": 0.7505192107995846, "grad_norm": 6.6120991706848145, "learning_rate": 3.7352390348266997e-06, "loss": 0.38301169872283936, "step": 2891 }, { "epoch": 0.7507788161993769, "grad_norm": 8.6666898727417, "learning_rate": 3.734388455395344e-06, "loss": 0.2971705496311188, "step": 2892 }, { "epoch": 0.7510384215991692, "grad_norm": 10.862812042236328, "learning_rate": 3.7335377019466497e-06, "loss": 0.2438468635082245, "step": 2893 }, { "epoch": 0.7512980269989615, "grad_norm": 11.369403839111328, "learning_rate": 3.73268677463101e-06, "loss": 0.27588117122650146, "step": 2894 }, { "epoch": 0.7515576323987538, "grad_norm": 5.890223026275635, "learning_rate": 3.731835673598848e-06, "loss": 0.2389998584985733, "step": 2895 }, { "epoch": 0.7518172377985463, "grad_norm": 4.263166427612305, "learning_rate": 3.7309843990006207e-06, "loss": 0.28232964873313904, "step": 2896 }, { "epoch": 0.7520768431983386, "grad_norm": 8.293598175048828, "learning_rate": 3.7301329509868124e-06, "loss": 0.21953967213630676, "step": 2897 }, { "epoch": 0.7523364485981309, "grad_norm": 3.1716461181640625, "learning_rate": 3.7292813297079416e-06, "loss": 0.31207600235939026, "step": 2898 }, { "epoch": 0.7525960539979232, "grad_norm": 3.6270129680633545, "learning_rate": 3.728429535314554e-06, "loss": 0.2788572311401367, "step": 2899 }, { "epoch": 0.7528556593977155, "grad_norm": 2.9574923515319824, "learning_rate": 3.727577567957227e-06, "loss": 0.3230104446411133, "step": 2900 }, { "epoch": 0.7531152647975078, "grad_norm": 9.043094635009766, "learning_rate": 3.72672542778657e-06, "loss": 0.28088992834091187, "step": 2901 }, { "epoch": 0.7533748701973001, "grad_norm": 6.989017963409424, "learning_rate": 3.7258731149532207e-06, "loss": 0.19135457277297974, "step": 2902 }, { "epoch": 0.7536344755970924, "grad_norm": 7.770467758178711, "learning_rate": 3.72502062960785e-06, "loss": 0.39563530683517456, "step": 2903 }, { "epoch": 0.7538940809968847, "grad_norm": 4.021442413330078, "learning_rate": 3.724167971901157e-06, "loss": 0.3339120149612427, "step": 2904 }, { "epoch": 0.754153686396677, "grad_norm": 2.5671868324279785, "learning_rate": 3.7233151419838713e-06, "loss": 0.334471732378006, "step": 2905 }, { "epoch": 0.7544132917964693, "grad_norm": 9.103053092956543, "learning_rate": 3.722462140006755e-06, "loss": 0.26436203718185425, "step": 2906 }, { "epoch": 0.7546728971962616, "grad_norm": 10.004110336303711, "learning_rate": 3.721608966120599e-06, "loss": 0.2526721954345703, "step": 2907 }, { "epoch": 0.754932502596054, "grad_norm": 5.233420372009277, "learning_rate": 3.7207556204762248e-06, "loss": 0.357654333114624, "step": 2908 }, { "epoch": 0.7551921079958464, "grad_norm": 4.357045650482178, "learning_rate": 3.7199021032244843e-06, "loss": 0.29576319456100464, "step": 2909 }, { "epoch": 0.7554517133956387, "grad_norm": 7.243122577667236, "learning_rate": 3.7190484145162585e-06, "loss": 0.27677059173583984, "step": 2910 }, { "epoch": 0.755711318795431, "grad_norm": 7.107769966125488, "learning_rate": 3.7181945545024622e-06, "loss": 0.19534403085708618, "step": 2911 }, { "epoch": 0.7559709241952233, "grad_norm": 8.86120891571045, "learning_rate": 3.717340523334037e-06, "loss": 0.26160454750061035, "step": 2912 }, { "epoch": 0.7562305295950156, "grad_norm": 4.739723205566406, "learning_rate": 3.716486321161957e-06, "loss": 0.3147958219051361, "step": 2913 }, { "epoch": 0.7564901349948079, "grad_norm": 3.3252134323120117, "learning_rate": 3.7156319481372247e-06, "loss": 0.3075284957885742, "step": 2914 }, { "epoch": 0.7567497403946002, "grad_norm": 3.076613426208496, "learning_rate": 3.7147774044108743e-06, "loss": 0.32362741231918335, "step": 2915 }, { "epoch": 0.7570093457943925, "grad_norm": 9.08626651763916, "learning_rate": 3.7139226901339685e-06, "loss": 0.3595464825630188, "step": 2916 }, { "epoch": 0.7572689511941848, "grad_norm": 5.956728935241699, "learning_rate": 3.713067805457603e-06, "loss": 0.34389233589172363, "step": 2917 }, { "epoch": 0.7575285565939771, "grad_norm": 4.511954307556152, "learning_rate": 3.7122127505329003e-06, "loss": 0.258809894323349, "step": 2918 }, { "epoch": 0.7577881619937694, "grad_norm": 6.197938442230225, "learning_rate": 3.7113575255110155e-06, "loss": 0.32743722200393677, "step": 2919 }, { "epoch": 0.7580477673935618, "grad_norm": 2.9815335273742676, "learning_rate": 3.7105021305431317e-06, "loss": 0.35030218958854675, "step": 2920 }, { "epoch": 0.7583073727933541, "grad_norm": 2.8093087673187256, "learning_rate": 3.709646565780464e-06, "loss": 0.3489444851875305, "step": 2921 }, { "epoch": 0.7585669781931464, "grad_norm": 8.950501441955566, "learning_rate": 3.708790831374257e-06, "loss": 0.22968809306621552, "step": 2922 }, { "epoch": 0.7588265835929388, "grad_norm": 5.222209930419922, "learning_rate": 3.7079349274757838e-06, "loss": 0.2743053138256073, "step": 2923 }, { "epoch": 0.7590861889927311, "grad_norm": 7.267333984375, "learning_rate": 3.7070788542363495e-06, "loss": 0.3977928161621094, "step": 2924 }, { "epoch": 0.7593457943925234, "grad_norm": 8.90369987487793, "learning_rate": 3.706222611807288e-06, "loss": 0.24200290441513062, "step": 2925 }, { "epoch": 0.7596053997923157, "grad_norm": 7.846198081970215, "learning_rate": 3.705366200339964e-06, "loss": 0.36174333095550537, "step": 2926 }, { "epoch": 0.759865005192108, "grad_norm": 6.397195339202881, "learning_rate": 3.7045096199857694e-06, "loss": 0.22305114567279816, "step": 2927 }, { "epoch": 0.7601246105919003, "grad_norm": 4.297224044799805, "learning_rate": 3.7036528708961297e-06, "loss": 0.28045299649238586, "step": 2928 }, { "epoch": 0.7603842159916926, "grad_norm": 2.896307945251465, "learning_rate": 3.702795953222498e-06, "loss": 0.35179832577705383, "step": 2929 }, { "epoch": 0.7606438213914849, "grad_norm": 3.960496187210083, "learning_rate": 3.7019388671163588e-06, "loss": 0.31775277853012085, "step": 2930 }, { "epoch": 0.7609034267912772, "grad_norm": 2.7537646293640137, "learning_rate": 3.7010816127292245e-06, "loss": 0.31863534450531006, "step": 2931 }, { "epoch": 0.7611630321910696, "grad_norm": 4.801820755004883, "learning_rate": 3.7002241902126366e-06, "loss": 0.22956271469593048, "step": 2932 }, { "epoch": 0.7614226375908619, "grad_norm": 4.605390548706055, "learning_rate": 3.6993665997181698e-06, "loss": 0.2644244432449341, "step": 2933 }, { "epoch": 0.7616822429906542, "grad_norm": 3.7526063919067383, "learning_rate": 3.698508841397426e-06, "loss": 0.3367680609226227, "step": 2934 }, { "epoch": 0.7619418483904465, "grad_norm": 5.889379978179932, "learning_rate": 3.6976509154020375e-06, "loss": 0.26556769013404846, "step": 2935 }, { "epoch": 0.7622014537902388, "grad_norm": 3.3324666023254395, "learning_rate": 3.6967928218836646e-06, "loss": 0.3570541739463806, "step": 2936 }, { "epoch": 0.7624610591900312, "grad_norm": 3.968815803527832, "learning_rate": 3.695934560993999e-06, "loss": 0.2649875283241272, "step": 2937 }, { "epoch": 0.7627206645898235, "grad_norm": 8.837532997131348, "learning_rate": 3.6950761328847634e-06, "loss": 0.2670975923538208, "step": 2938 }, { "epoch": 0.7629802699896158, "grad_norm": 8.166341781616211, "learning_rate": 3.694217537707706e-06, "loss": 0.2326507270336151, "step": 2939 }, { "epoch": 0.7632398753894081, "grad_norm": 8.536922454833984, "learning_rate": 3.6933587756146085e-06, "loss": 0.2934262752532959, "step": 2940 }, { "epoch": 0.7634994807892004, "grad_norm": 6.262457370758057, "learning_rate": 3.6924998467572782e-06, "loss": 0.28421586751937866, "step": 2941 }, { "epoch": 0.7637590861889927, "grad_norm": 2.9335756301879883, "learning_rate": 3.6916407512875567e-06, "loss": 0.364504337310791, "step": 2942 }, { "epoch": 0.764018691588785, "grad_norm": 10.981243133544922, "learning_rate": 3.6907814893573102e-06, "loss": 0.2724956274032593, "step": 2943 }, { "epoch": 0.7642782969885774, "grad_norm": 8.204353332519531, "learning_rate": 3.6899220611184384e-06, "loss": 0.3024114668369293, "step": 2944 }, { "epoch": 0.7645379023883697, "grad_norm": 9.085046768188477, "learning_rate": 3.6890624667228664e-06, "loss": 0.22043608129024506, "step": 2945 }, { "epoch": 0.764797507788162, "grad_norm": 6.296558380126953, "learning_rate": 3.6882027063225527e-06, "loss": 0.2776884138584137, "step": 2946 }, { "epoch": 0.7650571131879543, "grad_norm": 9.069793701171875, "learning_rate": 3.687342780069482e-06, "loss": 0.21632640063762665, "step": 2947 }, { "epoch": 0.7653167185877466, "grad_norm": 5.037213325500488, "learning_rate": 3.68648268811567e-06, "loss": 0.3249487578868866, "step": 2948 }, { "epoch": 0.7655763239875389, "grad_norm": 8.510257720947266, "learning_rate": 3.6856224306131622e-06, "loss": 0.15976175665855408, "step": 2949 }, { "epoch": 0.7658359293873312, "grad_norm": 8.594513893127441, "learning_rate": 3.684762007714031e-06, "loss": 0.3011319041252136, "step": 2950 }, { "epoch": 0.7660955347871236, "grad_norm": 5.202715873718262, "learning_rate": 3.68390141957038e-06, "loss": 0.28166505694389343, "step": 2951 }, { "epoch": 0.7663551401869159, "grad_norm": 2.628394365310669, "learning_rate": 3.683040666334342e-06, "loss": 0.3121095299720764, "step": 2952 }, { "epoch": 0.7666147455867082, "grad_norm": 3.059525728225708, "learning_rate": 3.682179748158078e-06, "loss": 0.2864644527435303, "step": 2953 }, { "epoch": 0.7668743509865005, "grad_norm": 8.916298866271973, "learning_rate": 3.6813186651937775e-06, "loss": 0.21358203887939453, "step": 2954 }, { "epoch": 0.7671339563862928, "grad_norm": 7.761938571929932, "learning_rate": 3.6804574175936623e-06, "loss": 0.21642158925533295, "step": 2955 }, { "epoch": 0.7673935617860852, "grad_norm": 9.540600776672363, "learning_rate": 3.6795960055099804e-06, "loss": 0.2624189555644989, "step": 2956 }, { "epoch": 0.7676531671858775, "grad_norm": 3.811861038208008, "learning_rate": 3.6787344290950094e-06, "loss": 0.31700819730758667, "step": 2957 }, { "epoch": 0.7679127725856698, "grad_norm": 8.57834529876709, "learning_rate": 3.677872688501057e-06, "loss": 0.2625904381275177, "step": 2958 }, { "epoch": 0.7681723779854621, "grad_norm": 7.175212860107422, "learning_rate": 3.6770107838804577e-06, "loss": 0.3180946707725525, "step": 2959 }, { "epoch": 0.7684319833852544, "grad_norm": 4.278269290924072, "learning_rate": 3.676148715385578e-06, "loss": 0.305256724357605, "step": 2960 }, { "epoch": 0.7686915887850467, "grad_norm": 7.878411293029785, "learning_rate": 3.6752864831688124e-06, "loss": 0.27111244201660156, "step": 2961 }, { "epoch": 0.768951194184839, "grad_norm": 10.56968879699707, "learning_rate": 3.6744240873825816e-06, "loss": 0.2993983030319214, "step": 2962 }, { "epoch": 0.7692107995846313, "grad_norm": 5.182278633117676, "learning_rate": 3.673561528179339e-06, "loss": 0.2190246284008026, "step": 2963 }, { "epoch": 0.7694704049844237, "grad_norm": 4.999783992767334, "learning_rate": 3.6726988057115646e-06, "loss": 0.304104208946228, "step": 2964 }, { "epoch": 0.769730010384216, "grad_norm": 4.229818344116211, "learning_rate": 3.6718359201317695e-06, "loss": 0.3566317856311798, "step": 2965 }, { "epoch": 0.7699896157840083, "grad_norm": 11.846697807312012, "learning_rate": 3.67097287159249e-06, "loss": 0.22243216633796692, "step": 2966 }, { "epoch": 0.7702492211838006, "grad_norm": 6.3543620109558105, "learning_rate": 3.6701096602462944e-06, "loss": 0.2891501188278198, "step": 2967 }, { "epoch": 0.770508826583593, "grad_norm": 8.829585075378418, "learning_rate": 3.6692462862457784e-06, "loss": 0.39732804894447327, "step": 2968 }, { "epoch": 0.7707684319833853, "grad_norm": 4.608916282653809, "learning_rate": 3.6683827497435678e-06, "loss": 0.29118746519088745, "step": 2969 }, { "epoch": 0.7710280373831776, "grad_norm": 3.7608468532562256, "learning_rate": 3.667519050892315e-06, "loss": 0.3087479770183563, "step": 2970 }, { "epoch": 0.7712876427829699, "grad_norm": 3.020974636077881, "learning_rate": 3.666655189844701e-06, "loss": 0.2925530970096588, "step": 2971 }, { "epoch": 0.7715472481827622, "grad_norm": 9.077136993408203, "learning_rate": 3.6657911667534397e-06, "loss": 0.24210909008979797, "step": 2972 }, { "epoch": 0.7718068535825545, "grad_norm": 12.18048095703125, "learning_rate": 3.6649269817712686e-06, "loss": 0.22672641277313232, "step": 2973 }, { "epoch": 0.7720664589823468, "grad_norm": 9.356647491455078, "learning_rate": 3.6640626350509557e-06, "loss": 0.1555473655462265, "step": 2974 }, { "epoch": 0.7723260643821391, "grad_norm": 6.373338222503662, "learning_rate": 3.663198126745299e-06, "loss": 0.25508928298950195, "step": 2975 }, { "epoch": 0.7725856697819314, "grad_norm": 9.921378135681152, "learning_rate": 3.6623334570071216e-06, "loss": 0.1709035038948059, "step": 2976 }, { "epoch": 0.7728452751817237, "grad_norm": 5.273703575134277, "learning_rate": 3.6614686259892794e-06, "loss": 0.2912692427635193, "step": 2977 }, { "epoch": 0.773104880581516, "grad_norm": 8.023050308227539, "learning_rate": 3.660603633844654e-06, "loss": 0.1721530258655548, "step": 2978 }, { "epoch": 0.7733644859813084, "grad_norm": 6.6385321617126465, "learning_rate": 3.6597384807261564e-06, "loss": 0.30685263872146606, "step": 2979 }, { "epoch": 0.7736240913811008, "grad_norm": 4.2667107582092285, "learning_rate": 3.658873166786726e-06, "loss": 0.296816349029541, "step": 2980 }, { "epoch": 0.7738836967808931, "grad_norm": 9.276782035827637, "learning_rate": 3.6580076921793295e-06, "loss": 0.191485196352005, "step": 2981 }, { "epoch": 0.7741433021806854, "grad_norm": 9.491331100463867, "learning_rate": 3.6571420570569643e-06, "loss": 0.24277284741401672, "step": 2982 }, { "epoch": 0.7744029075804777, "grad_norm": 3.584057331085205, "learning_rate": 3.6562762615726538e-06, "loss": 0.3179212808609009, "step": 2983 }, { "epoch": 0.77466251298027, "grad_norm": 9.223922729492188, "learning_rate": 3.6554103058794504e-06, "loss": 0.24276643991470337, "step": 2984 }, { "epoch": 0.7749221183800623, "grad_norm": 9.170692443847656, "learning_rate": 3.6545441901304366e-06, "loss": 0.31894630193710327, "step": 2985 }, { "epoch": 0.7751817237798546, "grad_norm": 4.040595054626465, "learning_rate": 3.6536779144787223e-06, "loss": 0.31859099864959717, "step": 2986 }, { "epoch": 0.7754413291796469, "grad_norm": 4.303819179534912, "learning_rate": 3.652811479077443e-06, "loss": 0.2606147229671478, "step": 2987 }, { "epoch": 0.7757009345794392, "grad_norm": 2.9633448123931885, "learning_rate": 3.6519448840797667e-06, "loss": 0.323811411857605, "step": 2988 }, { "epoch": 0.7759605399792315, "grad_norm": 10.752532958984375, "learning_rate": 3.651078129638886e-06, "loss": 0.2623700499534607, "step": 2989 }, { "epoch": 0.7762201453790238, "grad_norm": 16.8436222076416, "learning_rate": 3.6502112159080243e-06, "loss": 0.2346874326467514, "step": 2990 }, { "epoch": 0.7764797507788161, "grad_norm": 5.837913990020752, "learning_rate": 3.6493441430404315e-06, "loss": 0.34203946590423584, "step": 2991 }, { "epoch": 0.7767393561786086, "grad_norm": 13.19857120513916, "learning_rate": 3.648476911189387e-06, "loss": 0.3277285099029541, "step": 2992 }, { "epoch": 0.7769989615784009, "grad_norm": 8.400054931640625, "learning_rate": 3.6476095205081963e-06, "loss": 0.2895665168762207, "step": 2993 }, { "epoch": 0.7772585669781932, "grad_norm": 3.9227042198181152, "learning_rate": 3.646741971150195e-06, "loss": 0.2906827926635742, "step": 2994 }, { "epoch": 0.7775181723779855, "grad_norm": 7.901855945587158, "learning_rate": 3.6458742632687462e-06, "loss": 0.25998008251190186, "step": 2995 }, { "epoch": 0.7777777777777778, "grad_norm": 3.2686915397644043, "learning_rate": 3.64500639701724e-06, "loss": 0.3855349123477936, "step": 2996 }, { "epoch": 0.7780373831775701, "grad_norm": 8.786072731018066, "learning_rate": 3.6441383725490957e-06, "loss": 0.23203882575035095, "step": 2997 }, { "epoch": 0.7782969885773624, "grad_norm": 8.643037796020508, "learning_rate": 3.643270190017761e-06, "loss": 0.3781294822692871, "step": 2998 }, { "epoch": 0.7785565939771547, "grad_norm": 7.848351001739502, "learning_rate": 3.642401849576709e-06, "loss": 0.3375575542449951, "step": 2999 }, { "epoch": 0.778816199376947, "grad_norm": 7.370291709899902, "learning_rate": 3.6415333513794442e-06, "loss": 0.22624953091144562, "step": 3000 }, { "epoch": 0.7790758047767393, "grad_norm": 4.205656051635742, "learning_rate": 3.640664695579496e-06, "loss": 0.3187529444694519, "step": 3001 }, { "epoch": 0.7793354101765316, "grad_norm": 3.9659767150878906, "learning_rate": 3.639795882330423e-06, "loss": 0.352760374546051, "step": 3002 }, { "epoch": 0.7795950155763239, "grad_norm": 3.741715669631958, "learning_rate": 3.638926911785811e-06, "loss": 0.2940973937511444, "step": 3003 }, { "epoch": 0.7798546209761164, "grad_norm": 8.885770797729492, "learning_rate": 3.6380577840992758e-06, "loss": 0.21852387487888336, "step": 3004 }, { "epoch": 0.7801142263759087, "grad_norm": 3.1543567180633545, "learning_rate": 3.637188499424457e-06, "loss": 0.2564847469329834, "step": 3005 }, { "epoch": 0.780373831775701, "grad_norm": 6.937892436981201, "learning_rate": 3.636319057915027e-06, "loss": 0.3365952968597412, "step": 3006 }, { "epoch": 0.7806334371754933, "grad_norm": 3.5086379051208496, "learning_rate": 3.63544945972468e-06, "loss": 0.2640238106250763, "step": 3007 }, { "epoch": 0.7808930425752856, "grad_norm": 8.186923027038574, "learning_rate": 3.634579705007144e-06, "loss": 0.24537482857704163, "step": 3008 }, { "epoch": 0.7811526479750779, "grad_norm": 3.719578266143799, "learning_rate": 3.6337097939161698e-06, "loss": 0.3690008521080017, "step": 3009 }, { "epoch": 0.7814122533748702, "grad_norm": 7.835366725921631, "learning_rate": 3.632839726605538e-06, "loss": 0.15945614874362946, "step": 3010 }, { "epoch": 0.7816718587746625, "grad_norm": 10.940261840820312, "learning_rate": 3.6319695032290565e-06, "loss": 0.2323857545852661, "step": 3011 }, { "epoch": 0.7819314641744548, "grad_norm": 8.498632431030273, "learning_rate": 3.6310991239405625e-06, "loss": 0.251670777797699, "step": 3012 }, { "epoch": 0.7821910695742471, "grad_norm": 7.312407493591309, "learning_rate": 3.630228588893917e-06, "loss": 0.2400745153427124, "step": 3013 }, { "epoch": 0.7824506749740394, "grad_norm": 8.124825477600098, "learning_rate": 3.629357898243011e-06, "loss": 0.32442283630371094, "step": 3014 }, { "epoch": 0.7827102803738317, "grad_norm": 11.661465644836426, "learning_rate": 3.6284870521417646e-06, "loss": 0.21861395239830017, "step": 3015 }, { "epoch": 0.7829698857736241, "grad_norm": 6.203294277191162, "learning_rate": 3.627616050744121e-06, "loss": 0.3159613609313965, "step": 3016 }, { "epoch": 0.7832294911734164, "grad_norm": 8.115625381469727, "learning_rate": 3.6267448942040553e-06, "loss": 0.20243673026561737, "step": 3017 }, { "epoch": 0.7834890965732088, "grad_norm": 9.398262977600098, "learning_rate": 3.6258735826755663e-06, "loss": 0.10417793691158295, "step": 3018 }, { "epoch": 0.7837487019730011, "grad_norm": 8.7615385055542, "learning_rate": 3.625002116312683e-06, "loss": 0.17802459001541138, "step": 3019 }, { "epoch": 0.7840083073727934, "grad_norm": 5.138997554779053, "learning_rate": 3.6241304952694606e-06, "loss": 0.36788859963417053, "step": 3020 }, { "epoch": 0.7842679127725857, "grad_norm": 9.4431734085083, "learning_rate": 3.623258719699982e-06, "loss": 0.330369770526886, "step": 3021 }, { "epoch": 0.784527518172378, "grad_norm": 3.722198724746704, "learning_rate": 3.6223867897583555e-06, "loss": 0.3271309733390808, "step": 3022 }, { "epoch": 0.7847871235721703, "grad_norm": 9.4923677444458, "learning_rate": 3.6215147055987204e-06, "loss": 0.38322949409484863, "step": 3023 }, { "epoch": 0.7850467289719626, "grad_norm": 6.399433612823486, "learning_rate": 3.62064246737524e-06, "loss": 0.15150325000286102, "step": 3024 }, { "epoch": 0.7853063343717549, "grad_norm": 2.970569133758545, "learning_rate": 3.6197700752421066e-06, "loss": 0.32617050409317017, "step": 3025 }, { "epoch": 0.7855659397715472, "grad_norm": 8.240681648254395, "learning_rate": 3.6188975293535393e-06, "loss": 0.2548641562461853, "step": 3026 }, { "epoch": 0.7858255451713395, "grad_norm": 4.87047004699707, "learning_rate": 3.618024829863784e-06, "loss": 0.3304155170917511, "step": 3027 }, { "epoch": 0.7860851505711319, "grad_norm": 8.596366882324219, "learning_rate": 3.617151976927113e-06, "loss": 0.23927102982997894, "step": 3028 }, { "epoch": 0.7863447559709242, "grad_norm": 9.354186058044434, "learning_rate": 3.6162789706978287e-06, "loss": 0.2426697015762329, "step": 3029 }, { "epoch": 0.7866043613707165, "grad_norm": 7.673130989074707, "learning_rate": 3.6154058113302566e-06, "loss": 0.4155598282814026, "step": 3030 }, { "epoch": 0.7868639667705088, "grad_norm": 5.835031032562256, "learning_rate": 3.614532498978753e-06, "loss": 0.2535691261291504, "step": 3031 }, { "epoch": 0.7871235721703012, "grad_norm": 5.047002792358398, "learning_rate": 3.6136590337976985e-06, "loss": 0.2805566191673279, "step": 3032 }, { "epoch": 0.7873831775700935, "grad_norm": 5.184204578399658, "learning_rate": 3.6127854159415014e-06, "loss": 0.29850268363952637, "step": 3033 }, { "epoch": 0.7876427829698858, "grad_norm": 4.024233341217041, "learning_rate": 3.611911645564599e-06, "loss": 0.3198547661304474, "step": 3034 }, { "epoch": 0.7879023883696781, "grad_norm": 7.652870178222656, "learning_rate": 3.611037722821452e-06, "loss": 0.14930790662765503, "step": 3035 }, { "epoch": 0.7881619937694704, "grad_norm": 7.9735517501831055, "learning_rate": 3.610163647866552e-06, "loss": 0.3285595774650574, "step": 3036 }, { "epoch": 0.7884215991692627, "grad_norm": 6.888602256774902, "learning_rate": 3.6092894208544128e-06, "loss": 0.22911660373210907, "step": 3037 }, { "epoch": 0.788681204569055, "grad_norm": 2.896171808242798, "learning_rate": 3.608415041939579e-06, "loss": 0.2972114682197571, "step": 3038 }, { "epoch": 0.7889408099688473, "grad_norm": 3.2688169479370117, "learning_rate": 3.6075405112766213e-06, "loss": 0.3181983530521393, "step": 3039 }, { "epoch": 0.7892004153686397, "grad_norm": 7.79647970199585, "learning_rate": 3.606665829020137e-06, "loss": 0.2684319019317627, "step": 3040 }, { "epoch": 0.789460020768432, "grad_norm": 6.809730052947998, "learning_rate": 3.605790995324749e-06, "loss": 0.31679293513298035, "step": 3041 }, { "epoch": 0.7897196261682243, "grad_norm": 9.937192916870117, "learning_rate": 3.604916010345107e-06, "loss": 0.1740589588880539, "step": 3042 }, { "epoch": 0.7899792315680166, "grad_norm": 4.167820930480957, "learning_rate": 3.60404087423589e-06, "loss": 0.31268712878227234, "step": 3043 }, { "epoch": 0.7902388369678089, "grad_norm": 9.792191505432129, "learning_rate": 3.6031655871518017e-06, "loss": 0.21710051596164703, "step": 3044 }, { "epoch": 0.7904984423676013, "grad_norm": 4.303359508514404, "learning_rate": 3.602290149247572e-06, "loss": 0.283078134059906, "step": 3045 }, { "epoch": 0.7907580477673936, "grad_norm": 4.663645267486572, "learning_rate": 3.6014145606779586e-06, "loss": 0.2702982425689697, "step": 3046 }, { "epoch": 0.7910176531671859, "grad_norm": 8.610651016235352, "learning_rate": 3.600538821597746e-06, "loss": 0.12095634639263153, "step": 3047 }, { "epoch": 0.7912772585669782, "grad_norm": 10.324575424194336, "learning_rate": 3.599662932161745e-06, "loss": 0.2907618582248688, "step": 3048 }, { "epoch": 0.7915368639667705, "grad_norm": 10.766737937927246, "learning_rate": 3.5987868925247916e-06, "loss": 0.23826301097869873, "step": 3049 }, { "epoch": 0.7917964693665628, "grad_norm": 4.265166759490967, "learning_rate": 3.597910702841751e-06, "loss": 0.3296317458152771, "step": 3050 }, { "epoch": 0.7920560747663551, "grad_norm": 11.873173713684082, "learning_rate": 3.5970343632675115e-06, "loss": 0.22056534886360168, "step": 3051 }, { "epoch": 0.7923156801661475, "grad_norm": 8.219057083129883, "learning_rate": 3.5961578739569926e-06, "loss": 0.25679829716682434, "step": 3052 }, { "epoch": 0.7925752855659398, "grad_norm": 12.326690673828125, "learning_rate": 3.5952812350651346e-06, "loss": 0.2512235641479492, "step": 3053 }, { "epoch": 0.7928348909657321, "grad_norm": 5.625826358795166, "learning_rate": 3.5944044467469095e-06, "loss": 0.3047144412994385, "step": 3054 }, { "epoch": 0.7930944963655244, "grad_norm": 4.839621067047119, "learning_rate": 3.5935275091573124e-06, "loss": 0.3120878338813782, "step": 3055 }, { "epoch": 0.7933541017653167, "grad_norm": 4.228823661804199, "learning_rate": 3.5926504224513655e-06, "loss": 0.32988232374191284, "step": 3056 }, { "epoch": 0.793613707165109, "grad_norm": 5.688736915588379, "learning_rate": 3.591773186784118e-06, "loss": 0.3066698908805847, "step": 3057 }, { "epoch": 0.7938733125649013, "grad_norm": 11.687564849853516, "learning_rate": 3.590895802310646e-06, "loss": 0.27124595642089844, "step": 3058 }, { "epoch": 0.7941329179646937, "grad_norm": 6.783256530761719, "learning_rate": 3.590018269186049e-06, "loss": 0.2668912410736084, "step": 3059 }, { "epoch": 0.794392523364486, "grad_norm": 7.5886406898498535, "learning_rate": 3.589140587565456e-06, "loss": 0.16036975383758545, "step": 3060 }, { "epoch": 0.7946521287642783, "grad_norm": 3.293637275695801, "learning_rate": 3.5882627576040212e-06, "loss": 0.2869837284088135, "step": 3061 }, { "epoch": 0.7949117341640706, "grad_norm": 8.229724884033203, "learning_rate": 3.587384779456925e-06, "loss": 0.27439603209495544, "step": 3062 }, { "epoch": 0.7951713395638629, "grad_norm": 2.727992057800293, "learning_rate": 3.5865066532793737e-06, "loss": 0.28610628843307495, "step": 3063 }, { "epoch": 0.7954309449636553, "grad_norm": 8.369645118713379, "learning_rate": 3.5856283792265984e-06, "loss": 0.3264305591583252, "step": 3064 }, { "epoch": 0.7956905503634476, "grad_norm": 5.411226272583008, "learning_rate": 3.5847499574538598e-06, "loss": 0.33459556102752686, "step": 3065 }, { "epoch": 0.7959501557632399, "grad_norm": 7.369969844818115, "learning_rate": 3.5838713881164413e-06, "loss": 0.2929571866989136, "step": 3066 }, { "epoch": 0.7962097611630322, "grad_norm": 2.931649684906006, "learning_rate": 3.582992671369655e-06, "loss": 0.34060388803482056, "step": 3067 }, { "epoch": 0.7964693665628245, "grad_norm": 6.362695693969727, "learning_rate": 3.5821138073688373e-06, "loss": 0.1817409098148346, "step": 3068 }, { "epoch": 0.7967289719626168, "grad_norm": 4.387562274932861, "learning_rate": 3.581234796269351e-06, "loss": 0.26174861192703247, "step": 3069 }, { "epoch": 0.7969885773624091, "grad_norm": 8.183697700500488, "learning_rate": 3.5803556382265854e-06, "loss": 0.19828462600708008, "step": 3070 }, { "epoch": 0.7972481827622014, "grad_norm": 9.441661834716797, "learning_rate": 3.5794763333959564e-06, "loss": 0.27623867988586426, "step": 3071 }, { "epoch": 0.7975077881619937, "grad_norm": 4.354127407073975, "learning_rate": 3.578596881932904e-06, "loss": 0.3532264828681946, "step": 3072 }, { "epoch": 0.797767393561786, "grad_norm": 11.730772018432617, "learning_rate": 3.5777172839928943e-06, "loss": 0.30930936336517334, "step": 3073 }, { "epoch": 0.7980269989615784, "grad_norm": 7.9653120040893555, "learning_rate": 3.5768375397314215e-06, "loss": 0.20769567787647247, "step": 3074 }, { "epoch": 0.7982866043613707, "grad_norm": 7.780672073364258, "learning_rate": 3.5759576493040045e-06, "loss": 0.24608296155929565, "step": 3075 }, { "epoch": 0.7985462097611631, "grad_norm": 3.3253822326660156, "learning_rate": 3.5750776128661865e-06, "loss": 0.3198188543319702, "step": 3076 }, { "epoch": 0.7988058151609554, "grad_norm": 8.398737907409668, "learning_rate": 3.5741974305735377e-06, "loss": 0.31664004921913147, "step": 3077 }, { "epoch": 0.7990654205607477, "grad_norm": 9.252272605895996, "learning_rate": 3.5733171025816547e-06, "loss": 0.2593894600868225, "step": 3078 }, { "epoch": 0.79932502596054, "grad_norm": 4.800086498260498, "learning_rate": 3.5724366290461604e-06, "loss": 0.28947949409484863, "step": 3079 }, { "epoch": 0.7995846313603323, "grad_norm": 8.903545379638672, "learning_rate": 3.5715560101227013e-06, "loss": 0.1881324052810669, "step": 3080 }, { "epoch": 0.7998442367601246, "grad_norm": 5.822025299072266, "learning_rate": 3.5706752459669506e-06, "loss": 0.31707242131233215, "step": 3081 }, { "epoch": 0.8001038421599169, "grad_norm": 6.680737495422363, "learning_rate": 3.5697943367346066e-06, "loss": 0.3351655900478363, "step": 3082 }, { "epoch": 0.8003634475597092, "grad_norm": 2.915198564529419, "learning_rate": 3.5689132825813953e-06, "loss": 0.33159446716308594, "step": 3083 }, { "epoch": 0.8006230529595015, "grad_norm": 9.615392684936523, "learning_rate": 3.5680320836630667e-06, "loss": 0.21910637617111206, "step": 3084 }, { "epoch": 0.8008826583592938, "grad_norm": 6.4244384765625, "learning_rate": 3.567150740135396e-06, "loss": 0.24738040566444397, "step": 3085 }, { "epoch": 0.8011422637590861, "grad_norm": 5.856672763824463, "learning_rate": 3.566269252154184e-06, "loss": 0.25281399488449097, "step": 3086 }, { "epoch": 0.8014018691588785, "grad_norm": 5.193244457244873, "learning_rate": 3.565387619875259e-06, "loss": 0.24976076185703278, "step": 3087 }, { "epoch": 0.8016614745586709, "grad_norm": 9.918301582336426, "learning_rate": 3.564505843454472e-06, "loss": 0.3754706382751465, "step": 3088 }, { "epoch": 0.8019210799584632, "grad_norm": 9.423684120178223, "learning_rate": 3.5636239230477025e-06, "loss": 0.13296633958816528, "step": 3089 }, { "epoch": 0.8021806853582555, "grad_norm": 8.018866539001465, "learning_rate": 3.562741858810852e-06, "loss": 0.19664934277534485, "step": 3090 }, { "epoch": 0.8024402907580478, "grad_norm": 12.341034889221191, "learning_rate": 3.561859650899851e-06, "loss": 0.23259039223194122, "step": 3091 }, { "epoch": 0.8026998961578401, "grad_norm": 13.168891906738281, "learning_rate": 3.560977299470653e-06, "loss": 0.16318917274475098, "step": 3092 }, { "epoch": 0.8029595015576324, "grad_norm": 6.195889949798584, "learning_rate": 3.560094804679237e-06, "loss": 0.30289047956466675, "step": 3093 }, { "epoch": 0.8032191069574247, "grad_norm": 4.352689266204834, "learning_rate": 3.5592121666816083e-06, "loss": 0.3219636380672455, "step": 3094 }, { "epoch": 0.803478712357217, "grad_norm": 5.800823211669922, "learning_rate": 3.5583293856337963e-06, "loss": 0.26448845863342285, "step": 3095 }, { "epoch": 0.8037383177570093, "grad_norm": 6.7027363777160645, "learning_rate": 3.557446461691858e-06, "loss": 0.17830245196819305, "step": 3096 }, { "epoch": 0.8039979231568016, "grad_norm": 6.951898097991943, "learning_rate": 3.5565633950118727e-06, "loss": 0.22238659858703613, "step": 3097 }, { "epoch": 0.8042575285565939, "grad_norm": 8.532066345214844, "learning_rate": 3.5556801857499474e-06, "loss": 0.2626391649246216, "step": 3098 }, { "epoch": 0.8045171339563862, "grad_norm": 3.5948679447174072, "learning_rate": 3.554796834062213e-06, "loss": 0.335022509098053, "step": 3099 }, { "epoch": 0.8047767393561787, "grad_norm": 4.97049617767334, "learning_rate": 3.553913340104826e-06, "loss": 0.26371103525161743, "step": 3100 }, { "epoch": 0.805036344755971, "grad_norm": 13.021405220031738, "learning_rate": 3.5530297040339667e-06, "loss": 0.35438045859336853, "step": 3101 }, { "epoch": 0.8052959501557633, "grad_norm": 10.688467025756836, "learning_rate": 3.5521459260058435e-06, "loss": 0.16045144200325012, "step": 3102 }, { "epoch": 0.8055555555555556, "grad_norm": 3.619112730026245, "learning_rate": 3.5512620061766866e-06, "loss": 0.3186872899532318, "step": 3103 }, { "epoch": 0.8058151609553479, "grad_norm": 5.550841331481934, "learning_rate": 3.550377944702755e-06, "loss": 0.2839139699935913, "step": 3104 }, { "epoch": 0.8060747663551402, "grad_norm": 6.62418794631958, "learning_rate": 3.549493741740327e-06, "loss": 0.2643796503543854, "step": 3105 }, { "epoch": 0.8063343717549325, "grad_norm": 7.328212261199951, "learning_rate": 3.5486093974457133e-06, "loss": 0.27952224016189575, "step": 3106 }, { "epoch": 0.8065939771547248, "grad_norm": 6.129611015319824, "learning_rate": 3.5477249119752426e-06, "loss": 0.3063350319862366, "step": 3107 }, { "epoch": 0.8068535825545171, "grad_norm": 9.160776138305664, "learning_rate": 3.546840285485273e-06, "loss": 0.2903989553451538, "step": 3108 }, { "epoch": 0.8071131879543094, "grad_norm": 5.810596942901611, "learning_rate": 3.5459555181321856e-06, "loss": 0.24227242171764374, "step": 3109 }, { "epoch": 0.8073727933541017, "grad_norm": 4.325039863586426, "learning_rate": 3.545070610072389e-06, "loss": 0.2765347957611084, "step": 3110 }, { "epoch": 0.807632398753894, "grad_norm": 5.148311138153076, "learning_rate": 3.5441855614623126e-06, "loss": 0.3548496961593628, "step": 3111 }, { "epoch": 0.8078920041536864, "grad_norm": 9.458398818969727, "learning_rate": 3.5433003724584143e-06, "loss": 0.29523196816444397, "step": 3112 }, { "epoch": 0.8081516095534788, "grad_norm": 9.068449020385742, "learning_rate": 3.5424150432171727e-06, "loss": 0.2778019309043884, "step": 3113 }, { "epoch": 0.8084112149532711, "grad_norm": 11.962252616882324, "learning_rate": 3.5415295738950965e-06, "loss": 0.2170669138431549, "step": 3114 }, { "epoch": 0.8086708203530634, "grad_norm": 8.462966918945312, "learning_rate": 3.5406439646487144e-06, "loss": 0.25506889820098877, "step": 3115 }, { "epoch": 0.8089304257528557, "grad_norm": 9.453953742980957, "learning_rate": 3.539758215634584e-06, "loss": 0.23954959213733673, "step": 3116 }, { "epoch": 0.809190031152648, "grad_norm": 4.017018795013428, "learning_rate": 3.5388723270092824e-06, "loss": 0.2943011224269867, "step": 3117 }, { "epoch": 0.8094496365524403, "grad_norm": 9.2312650680542, "learning_rate": 3.5379862989294174e-06, "loss": 0.231185644865036, "step": 3118 }, { "epoch": 0.8097092419522326, "grad_norm": 7.598720073699951, "learning_rate": 3.537100131551617e-06, "loss": 0.3197251558303833, "step": 3119 }, { "epoch": 0.8099688473520249, "grad_norm": 9.156719207763672, "learning_rate": 3.536213825032535e-06, "loss": 0.23066867887973785, "step": 3120 }, { "epoch": 0.8102284527518172, "grad_norm": 8.54395580291748, "learning_rate": 3.535327379528851e-06, "loss": 0.23723872005939484, "step": 3121 }, { "epoch": 0.8104880581516095, "grad_norm": 5.879335880279541, "learning_rate": 3.5344407951972687e-06, "loss": 0.24467307329177856, "step": 3122 }, { "epoch": 0.8107476635514018, "grad_norm": 9.062173843383789, "learning_rate": 3.5335540721945145e-06, "loss": 0.3619011640548706, "step": 3123 }, { "epoch": 0.8110072689511942, "grad_norm": 10.422131538391113, "learning_rate": 3.532667210677341e-06, "loss": 0.2624930739402771, "step": 3124 }, { "epoch": 0.8112668743509865, "grad_norm": 12.250530242919922, "learning_rate": 3.531780210802526e-06, "loss": 0.24032308161258698, "step": 3125 }, { "epoch": 0.8115264797507789, "grad_norm": 4.081340789794922, "learning_rate": 3.5308930727268693e-06, "loss": 0.2941242456436157, "step": 3126 }, { "epoch": 0.8117860851505712, "grad_norm": 11.547807693481445, "learning_rate": 3.530005796607198e-06, "loss": 0.3031216859817505, "step": 3127 }, { "epoch": 0.8120456905503635, "grad_norm": 14.047600746154785, "learning_rate": 3.529118382600361e-06, "loss": 0.3454793691635132, "step": 3128 }, { "epoch": 0.8123052959501558, "grad_norm": 4.6110663414001465, "learning_rate": 3.5282308308632348e-06, "loss": 0.2961045801639557, "step": 3129 }, { "epoch": 0.8125649013499481, "grad_norm": 8.673700332641602, "learning_rate": 3.527343141552715e-06, "loss": 0.15867754817008972, "step": 3130 }, { "epoch": 0.8128245067497404, "grad_norm": 5.216850757598877, "learning_rate": 3.526455314825728e-06, "loss": 0.3229261636734009, "step": 3131 }, { "epoch": 0.8130841121495327, "grad_norm": 4.474008560180664, "learning_rate": 3.525567350839219e-06, "loss": 0.29643893241882324, "step": 3132 }, { "epoch": 0.813343717549325, "grad_norm": 7.6437859535217285, "learning_rate": 3.5246792497501615e-06, "loss": 0.3239065408706665, "step": 3133 }, { "epoch": 0.8136033229491173, "grad_norm": 8.252827644348145, "learning_rate": 3.5237910117155494e-06, "loss": 0.2482418417930603, "step": 3134 }, { "epoch": 0.8138629283489096, "grad_norm": 9.238299369812012, "learning_rate": 3.5229026368924043e-06, "loss": 0.22253766655921936, "step": 3135 }, { "epoch": 0.814122533748702, "grad_norm": 6.495654106140137, "learning_rate": 3.5220141254377697e-06, "loss": 0.08273434638977051, "step": 3136 }, { "epoch": 0.8143821391484943, "grad_norm": 4.205256462097168, "learning_rate": 3.521125477508715e-06, "loss": 0.31858161091804504, "step": 3137 }, { "epoch": 0.8146417445482866, "grad_norm": 5.098228454589844, "learning_rate": 3.5202366932623327e-06, "loss": 0.28422969579696655, "step": 3138 }, { "epoch": 0.814901349948079, "grad_norm": 3.7594783306121826, "learning_rate": 3.519347772855738e-06, "loss": 0.3148469924926758, "step": 3139 }, { "epoch": 0.8151609553478713, "grad_norm": 10.39795207977295, "learning_rate": 3.518458716446074e-06, "loss": 0.2413831353187561, "step": 3140 }, { "epoch": 0.8154205607476636, "grad_norm": 5.592272758483887, "learning_rate": 3.517569524190503e-06, "loss": 0.2814023494720459, "step": 3141 }, { "epoch": 0.8156801661474559, "grad_norm": 10.888927459716797, "learning_rate": 3.516680196246216e-06, "loss": 0.2720825672149658, "step": 3142 }, { "epoch": 0.8159397715472482, "grad_norm": 6.154548645019531, "learning_rate": 3.5157907327704244e-06, "loss": 0.3136920630931854, "step": 3143 }, { "epoch": 0.8161993769470405, "grad_norm": 13.755512237548828, "learning_rate": 3.514901133920366e-06, "loss": 0.2612046003341675, "step": 3144 }, { "epoch": 0.8164589823468328, "grad_norm": 3.8403427600860596, "learning_rate": 3.5140113998533015e-06, "loss": 0.32431477308273315, "step": 3145 }, { "epoch": 0.8167185877466251, "grad_norm": 5.71363639831543, "learning_rate": 3.513121530726515e-06, "loss": 0.29211944341659546, "step": 3146 }, { "epoch": 0.8169781931464174, "grad_norm": 4.7591776847839355, "learning_rate": 3.5122315266973146e-06, "loss": 0.3317273259162903, "step": 3147 }, { "epoch": 0.8172377985462098, "grad_norm": 12.026121139526367, "learning_rate": 3.511341387923032e-06, "loss": 0.18648049235343933, "step": 3148 }, { "epoch": 0.8174974039460021, "grad_norm": 11.935651779174805, "learning_rate": 3.5104511145610255e-06, "loss": 0.3621513247489929, "step": 3149 }, { "epoch": 0.8177570093457944, "grad_norm": 11.340683937072754, "learning_rate": 3.509560706768674e-06, "loss": 0.3183686137199402, "step": 3150 }, { "epoch": 0.8180166147455867, "grad_norm": 3.4888293743133545, "learning_rate": 3.508670164703382e-06, "loss": 0.3215169906616211, "step": 3151 }, { "epoch": 0.818276220145379, "grad_norm": 5.935368061065674, "learning_rate": 3.5077794885225747e-06, "loss": 0.27542608976364136, "step": 3152 }, { "epoch": 0.8185358255451713, "grad_norm": 8.039523124694824, "learning_rate": 3.5068886783837047e-06, "loss": 0.2762317955493927, "step": 3153 }, { "epoch": 0.8187954309449637, "grad_norm": 8.37447452545166, "learning_rate": 3.505997734444248e-06, "loss": 0.15809711813926697, "step": 3154 }, { "epoch": 0.819055036344756, "grad_norm": 9.791521072387695, "learning_rate": 3.505106656861701e-06, "loss": 0.23316167294979095, "step": 3155 }, { "epoch": 0.8193146417445483, "grad_norm": 7.699560642242432, "learning_rate": 3.5042154457935867e-06, "loss": 0.27784180641174316, "step": 3156 }, { "epoch": 0.8195742471443406, "grad_norm": 9.228483200073242, "learning_rate": 3.5033241013974512e-06, "loss": 0.20814666152000427, "step": 3157 }, { "epoch": 0.8198338525441329, "grad_norm": 8.328361511230469, "learning_rate": 3.502432623830863e-06, "loss": 0.3013495206832886, "step": 3158 }, { "epoch": 0.8200934579439252, "grad_norm": 7.534794807434082, "learning_rate": 3.5015410132514153e-06, "loss": 0.1858401596546173, "step": 3159 }, { "epoch": 0.8203530633437176, "grad_norm": 3.8596367835998535, "learning_rate": 3.5006492698167256e-06, "loss": 0.32038530707359314, "step": 3160 }, { "epoch": 0.8206126687435099, "grad_norm": 5.735930919647217, "learning_rate": 3.499757393684431e-06, "loss": 0.24721641838550568, "step": 3161 }, { "epoch": 0.8208722741433022, "grad_norm": 3.734884262084961, "learning_rate": 3.4988653850121975e-06, "loss": 0.330757737159729, "step": 3162 }, { "epoch": 0.8211318795430945, "grad_norm": 3.266447067260742, "learning_rate": 3.4979732439577103e-06, "loss": 0.3475398123264313, "step": 3163 }, { "epoch": 0.8213914849428868, "grad_norm": 6.275899887084961, "learning_rate": 3.4970809706786802e-06, "loss": 0.3437226116657257, "step": 3164 }, { "epoch": 0.8216510903426791, "grad_norm": 5.6447577476501465, "learning_rate": 3.49618856533284e-06, "loss": 0.24607449769973755, "step": 3165 }, { "epoch": 0.8219106957424714, "grad_norm": 10.204066276550293, "learning_rate": 3.4952960280779463e-06, "loss": 0.1918037235736847, "step": 3166 }, { "epoch": 0.8221703011422637, "grad_norm": 5.028354167938232, "learning_rate": 3.494403359071781e-06, "loss": 0.3079497218132019, "step": 3167 }, { "epoch": 0.822429906542056, "grad_norm": 10.60645866394043, "learning_rate": 3.4935105584721455e-06, "loss": 0.3080170750617981, "step": 3168 }, { "epoch": 0.8226895119418484, "grad_norm": 6.832054615020752, "learning_rate": 3.4926176264368683e-06, "loss": 0.26904821395874023, "step": 3169 }, { "epoch": 0.8229491173416407, "grad_norm": 8.791253089904785, "learning_rate": 3.491724563123798e-06, "loss": 0.17332080006599426, "step": 3170 }, { "epoch": 0.823208722741433, "grad_norm": 3.215945243835449, "learning_rate": 3.4908313686908074e-06, "loss": 0.3049246668815613, "step": 3171 }, { "epoch": 0.8234683281412254, "grad_norm": 3.0783963203430176, "learning_rate": 3.4899380432957948e-06, "loss": 0.29268956184387207, "step": 3172 }, { "epoch": 0.8237279335410177, "grad_norm": 4.46598482131958, "learning_rate": 3.4890445870966783e-06, "loss": 0.2995077967643738, "step": 3173 }, { "epoch": 0.82398753894081, "grad_norm": 7.9413933753967285, "learning_rate": 3.4881510002514e-06, "loss": 0.1780792474746704, "step": 3174 }, { "epoch": 0.8242471443406023, "grad_norm": 3.271294116973877, "learning_rate": 3.487257282917927e-06, "loss": 0.31028228998184204, "step": 3175 }, { "epoch": 0.8245067497403946, "grad_norm": 3.8511295318603516, "learning_rate": 3.4863634352542465e-06, "loss": 0.2894936203956604, "step": 3176 }, { "epoch": 0.8247663551401869, "grad_norm": 7.207798480987549, "learning_rate": 3.4854694574183716e-06, "loss": 0.2435137927532196, "step": 3177 }, { "epoch": 0.8250259605399792, "grad_norm": 3.1680068969726562, "learning_rate": 3.4845753495683366e-06, "loss": 0.2772786021232605, "step": 3178 }, { "epoch": 0.8252855659397715, "grad_norm": 4.45912504196167, "learning_rate": 3.4836811118621995e-06, "loss": 0.3158871829509735, "step": 3179 }, { "epoch": 0.8255451713395638, "grad_norm": 7.191713809967041, "learning_rate": 3.482786744458041e-06, "loss": 0.154067263007164, "step": 3180 }, { "epoch": 0.8258047767393562, "grad_norm": 5.613157749176025, "learning_rate": 3.4818922475139643e-06, "loss": 0.25114959478378296, "step": 3181 }, { "epoch": 0.8260643821391485, "grad_norm": 10.09434986114502, "learning_rate": 3.4809976211880963e-06, "loss": 0.2734517753124237, "step": 3182 }, { "epoch": 0.8263239875389408, "grad_norm": 4.9061150550842285, "learning_rate": 3.4801028656385867e-06, "loss": 0.25787317752838135, "step": 3183 }, { "epoch": 0.8265835929387332, "grad_norm": 10.661930084228516, "learning_rate": 3.4792079810236078e-06, "loss": 0.20999377965927124, "step": 3184 }, { "epoch": 0.8268431983385255, "grad_norm": 3.989098072052002, "learning_rate": 3.4783129675013545e-06, "loss": 0.28878509998321533, "step": 3185 }, { "epoch": 0.8271028037383178, "grad_norm": 5.669297695159912, "learning_rate": 3.4774178252300445e-06, "loss": 0.3358016908168793, "step": 3186 }, { "epoch": 0.8273624091381101, "grad_norm": 5.181380748748779, "learning_rate": 3.476522554367918e-06, "loss": 0.3153459429740906, "step": 3187 }, { "epoch": 0.8276220145379024, "grad_norm": 7.142282009124756, "learning_rate": 3.4756271550732397e-06, "loss": 0.22381116449832916, "step": 3188 }, { "epoch": 0.8278816199376947, "grad_norm": 5.416299819946289, "learning_rate": 3.474731627504296e-06, "loss": 0.29936307668685913, "step": 3189 }, { "epoch": 0.828141225337487, "grad_norm": 10.251376152038574, "learning_rate": 3.4738359718193932e-06, "loss": 0.22035513818264008, "step": 3190 }, { "epoch": 0.8284008307372793, "grad_norm": 4.543161869049072, "learning_rate": 3.4729401881768655e-06, "loss": 0.2991527318954468, "step": 3191 }, { "epoch": 0.8286604361370716, "grad_norm": 4.911016464233398, "learning_rate": 3.4720442767350637e-06, "loss": 0.2804131805896759, "step": 3192 }, { "epoch": 0.8289200415368639, "grad_norm": 9.85399055480957, "learning_rate": 3.4711482376523687e-06, "loss": 0.24570225179195404, "step": 3193 }, { "epoch": 0.8291796469366562, "grad_norm": 5.985843658447266, "learning_rate": 3.4702520710871757e-06, "loss": 0.2518641948699951, "step": 3194 }, { "epoch": 0.8294392523364486, "grad_norm": 4.98425817489624, "learning_rate": 3.469355777197909e-06, "loss": 0.2965317964553833, "step": 3195 }, { "epoch": 0.829698857736241, "grad_norm": 5.8423686027526855, "learning_rate": 3.468459356143012e-06, "loss": 0.27278932929039, "step": 3196 }, { "epoch": 0.8299584631360333, "grad_norm": 3.638185739517212, "learning_rate": 3.4675628080809508e-06, "loss": 0.3219336271286011, "step": 3197 }, { "epoch": 0.8302180685358256, "grad_norm": 7.986509323120117, "learning_rate": 3.466666133170215e-06, "loss": 0.2655699551105499, "step": 3198 }, { "epoch": 0.8304776739356179, "grad_norm": 9.650290489196777, "learning_rate": 3.4657693315693177e-06, "loss": 0.21696758270263672, "step": 3199 }, { "epoch": 0.8307372793354102, "grad_norm": 9.638733863830566, "learning_rate": 3.4648724034367903e-06, "loss": 0.20372897386550903, "step": 3200 }, { "epoch": 0.8309968847352025, "grad_norm": 11.805191993713379, "learning_rate": 3.4639753489311905e-06, "loss": 0.15478011965751648, "step": 3201 }, { "epoch": 0.8312564901349948, "grad_norm": 11.493110656738281, "learning_rate": 3.4630781682110975e-06, "loss": 0.19551023840904236, "step": 3202 }, { "epoch": 0.8315160955347871, "grad_norm": 9.776763916015625, "learning_rate": 3.462180861435111e-06, "loss": 0.18986192345619202, "step": 3203 }, { "epoch": 0.8317757009345794, "grad_norm": 9.907774925231934, "learning_rate": 3.4612834287618556e-06, "loss": 0.2937457263469696, "step": 3204 }, { "epoch": 0.8320353063343717, "grad_norm": 6.00689697265625, "learning_rate": 3.4603858703499747e-06, "loss": 0.33684444427490234, "step": 3205 }, { "epoch": 0.832294911734164, "grad_norm": 4.152439594268799, "learning_rate": 3.4594881863581397e-06, "loss": 0.3355315923690796, "step": 3206 }, { "epoch": 0.8325545171339563, "grad_norm": 3.633229970932007, "learning_rate": 3.4585903769450372e-06, "loss": 0.30756187438964844, "step": 3207 }, { "epoch": 0.8328141225337488, "grad_norm": 7.990164279937744, "learning_rate": 3.4576924422693813e-06, "loss": 0.2797941565513611, "step": 3208 }, { "epoch": 0.8330737279335411, "grad_norm": 10.89358901977539, "learning_rate": 3.4567943824899055e-06, "loss": 0.15503361821174622, "step": 3209 }, { "epoch": 0.8333333333333334, "grad_norm": 4.606847763061523, "learning_rate": 3.455896197765366e-06, "loss": 0.2842670679092407, "step": 3210 }, { "epoch": 0.8335929387331257, "grad_norm": 9.96165657043457, "learning_rate": 3.454997888254541e-06, "loss": 0.2778182625770569, "step": 3211 }, { "epoch": 0.833852544132918, "grad_norm": 10.640578269958496, "learning_rate": 3.4540994541162333e-06, "loss": 0.19193489849567413, "step": 3212 }, { "epoch": 0.8341121495327103, "grad_norm": 8.806961059570312, "learning_rate": 3.4532008955092627e-06, "loss": 0.1389485001564026, "step": 3213 }, { "epoch": 0.8343717549325026, "grad_norm": 3.4159257411956787, "learning_rate": 3.452302212592475e-06, "loss": 0.320071816444397, "step": 3214 }, { "epoch": 0.8346313603322949, "grad_norm": 6.058373928070068, "learning_rate": 3.4514034055247366e-06, "loss": 0.2717280983924866, "step": 3215 }, { "epoch": 0.8348909657320872, "grad_norm": 7.80876350402832, "learning_rate": 3.450504474464937e-06, "loss": 0.16383127868175507, "step": 3216 }, { "epoch": 0.8351505711318795, "grad_norm": 7.289554595947266, "learning_rate": 3.4496054195719847e-06, "loss": 0.307999849319458, "step": 3217 }, { "epoch": 0.8354101765316718, "grad_norm": 10.615431785583496, "learning_rate": 3.4487062410048135e-06, "loss": 0.2497294545173645, "step": 3218 }, { "epoch": 0.8356697819314641, "grad_norm": 8.08303451538086, "learning_rate": 3.447806938922377e-06, "loss": 0.23419882357120514, "step": 3219 }, { "epoch": 0.8359293873312564, "grad_norm": 8.472848892211914, "learning_rate": 3.4469075134836516e-06, "loss": 0.3486104905605316, "step": 3220 }, { "epoch": 0.8361889927310489, "grad_norm": 9.630253791809082, "learning_rate": 3.4460079648476354e-06, "loss": 0.2634732723236084, "step": 3221 }, { "epoch": 0.8364485981308412, "grad_norm": 8.655433654785156, "learning_rate": 3.4451082931733463e-06, "loss": 0.18337571620941162, "step": 3222 }, { "epoch": 0.8367082035306335, "grad_norm": 7.253250598907471, "learning_rate": 3.444208498619827e-06, "loss": 0.25410133600234985, "step": 3223 }, { "epoch": 0.8369678089304258, "grad_norm": 4.112038612365723, "learning_rate": 3.4433085813461407e-06, "loss": 0.3123020529747009, "step": 3224 }, { "epoch": 0.8372274143302181, "grad_norm": 4.2710981369018555, "learning_rate": 3.4424085415113722e-06, "loss": 0.27601760625839233, "step": 3225 }, { "epoch": 0.8374870197300104, "grad_norm": 3.3932368755340576, "learning_rate": 3.4415083792746284e-06, "loss": 0.2955436706542969, "step": 3226 }, { "epoch": 0.8377466251298027, "grad_norm": 4.905014991760254, "learning_rate": 3.440608094795035e-06, "loss": 0.2825903296470642, "step": 3227 }, { "epoch": 0.838006230529595, "grad_norm": 8.757658004760742, "learning_rate": 3.4397076882317438e-06, "loss": 0.20062163472175598, "step": 3228 }, { "epoch": 0.8382658359293873, "grad_norm": 6.174087047576904, "learning_rate": 3.438807159743926e-06, "loss": 0.21263250708580017, "step": 3229 }, { "epoch": 0.8385254413291796, "grad_norm": 4.035726547241211, "learning_rate": 3.4379065094907734e-06, "loss": 0.3081423044204712, "step": 3230 }, { "epoch": 0.8387850467289719, "grad_norm": 5.9522294998168945, "learning_rate": 3.4370057376315e-06, "loss": 0.34503474831581116, "step": 3231 }, { "epoch": 0.8390446521287642, "grad_norm": 10.832443237304688, "learning_rate": 3.4361048443253443e-06, "loss": 0.22005142271518707, "step": 3232 }, { "epoch": 0.8393042575285566, "grad_norm": 9.581757545471191, "learning_rate": 3.4352038297315616e-06, "loss": 0.24166972935199738, "step": 3233 }, { "epoch": 0.839563862928349, "grad_norm": 7.450894832611084, "learning_rate": 3.4343026940094297e-06, "loss": 0.20262056589126587, "step": 3234 }, { "epoch": 0.8398234683281413, "grad_norm": 11.760103225708008, "learning_rate": 3.433401437318251e-06, "loss": 0.3957524001598358, "step": 3235 }, { "epoch": 0.8400830737279336, "grad_norm": 4.895582675933838, "learning_rate": 3.4325000598173454e-06, "loss": 0.2780182659626007, "step": 3236 }, { "epoch": 0.8403426791277259, "grad_norm": 3.0973143577575684, "learning_rate": 3.4315985616660572e-06, "loss": 0.3257131278514862, "step": 3237 }, { "epoch": 0.8406022845275182, "grad_norm": 9.833398818969727, "learning_rate": 3.430696943023749e-06, "loss": 0.2478906512260437, "step": 3238 }, { "epoch": 0.8408618899273105, "grad_norm": 10.087130546569824, "learning_rate": 3.429795204049808e-06, "loss": 0.2571675181388855, "step": 3239 }, { "epoch": 0.8411214953271028, "grad_norm": 8.393776893615723, "learning_rate": 3.428893344903639e-06, "loss": 0.2074582278728485, "step": 3240 }, { "epoch": 0.8413811007268951, "grad_norm": 9.456521987915039, "learning_rate": 3.427991365744672e-06, "loss": 0.12882588803768158, "step": 3241 }, { "epoch": 0.8416407061266874, "grad_norm": 7.935191631317139, "learning_rate": 3.4270892667323553e-06, "loss": 0.270591676235199, "step": 3242 }, { "epoch": 0.8419003115264797, "grad_norm": 7.75814962387085, "learning_rate": 3.42618704802616e-06, "loss": 0.2548203766345978, "step": 3243 }, { "epoch": 0.842159916926272, "grad_norm": 6.739504337310791, "learning_rate": 3.4252847097855764e-06, "loss": 0.2938738465309143, "step": 3244 }, { "epoch": 0.8424195223260644, "grad_norm": 12.51047134399414, "learning_rate": 3.4243822521701183e-06, "loss": 0.23046249151229858, "step": 3245 }, { "epoch": 0.8426791277258567, "grad_norm": 4.717305660247803, "learning_rate": 3.4234796753393197e-06, "loss": 0.2766285538673401, "step": 3246 }, { "epoch": 0.842938733125649, "grad_norm": 5.749974727630615, "learning_rate": 3.4225769794527354e-06, "loss": 0.2623063325881958, "step": 3247 }, { "epoch": 0.8431983385254413, "grad_norm": 6.2786431312561035, "learning_rate": 3.4216741646699396e-06, "loss": 0.24322110414505005, "step": 3248 }, { "epoch": 0.8434579439252337, "grad_norm": 10.849165916442871, "learning_rate": 3.420771231150532e-06, "loss": 0.15159256756305695, "step": 3249 }, { "epoch": 0.843717549325026, "grad_norm": 7.433477401733398, "learning_rate": 3.4198681790541296e-06, "loss": 0.2174178510904312, "step": 3250 }, { "epoch": 0.8439771547248183, "grad_norm": 10.791385650634766, "learning_rate": 3.418965008540371e-06, "loss": 0.2603294253349304, "step": 3251 }, { "epoch": 0.8442367601246106, "grad_norm": 5.485754489898682, "learning_rate": 3.418061719768916e-06, "loss": 0.2556854784488678, "step": 3252 }, { "epoch": 0.8444963655244029, "grad_norm": 7.549495220184326, "learning_rate": 3.4171583128994453e-06, "loss": 0.21191906929016113, "step": 3253 }, { "epoch": 0.8447559709241952, "grad_norm": 3.5715043544769287, "learning_rate": 3.41625478809166e-06, "loss": 0.32558920979499817, "step": 3254 }, { "epoch": 0.8450155763239875, "grad_norm": 8.787402153015137, "learning_rate": 3.4153511455052844e-06, "loss": 0.3017057776451111, "step": 3255 }, { "epoch": 0.8452751817237798, "grad_norm": 5.063204765319824, "learning_rate": 3.414447385300061e-06, "loss": 0.29634857177734375, "step": 3256 }, { "epoch": 0.8455347871235722, "grad_norm": 12.069185256958008, "learning_rate": 3.4135435076357537e-06, "loss": 0.21503880620002747, "step": 3257 }, { "epoch": 0.8457943925233645, "grad_norm": 8.93328857421875, "learning_rate": 3.412639512672147e-06, "loss": 0.164937824010849, "step": 3258 }, { "epoch": 0.8460539979231568, "grad_norm": 6.869239330291748, "learning_rate": 3.411735400569046e-06, "loss": 0.297943651676178, "step": 3259 }, { "epoch": 0.8463136033229491, "grad_norm": 5.556138038635254, "learning_rate": 3.41083117148628e-06, "loss": 0.32164978981018066, "step": 3260 }, { "epoch": 0.8465732087227414, "grad_norm": 9.744840621948242, "learning_rate": 3.409926825583692e-06, "loss": 0.18327732384204865, "step": 3261 }, { "epoch": 0.8468328141225338, "grad_norm": 9.083122253417969, "learning_rate": 3.4090223630211523e-06, "loss": 0.15861862897872925, "step": 3262 }, { "epoch": 0.8470924195223261, "grad_norm": 4.8032379150390625, "learning_rate": 3.4081177839585485e-06, "loss": 0.31852567195892334, "step": 3263 }, { "epoch": 0.8473520249221184, "grad_norm": 5.398434162139893, "learning_rate": 3.407213088555789e-06, "loss": 0.2772543430328369, "step": 3264 }, { "epoch": 0.8476116303219107, "grad_norm": 6.741178512573242, "learning_rate": 3.4063082769728045e-06, "loss": 0.15584847331047058, "step": 3265 }, { "epoch": 0.847871235721703, "grad_norm": 9.497486114501953, "learning_rate": 3.405403349369544e-06, "loss": 0.21727599203586578, "step": 3266 }, { "epoch": 0.8481308411214953, "grad_norm": 10.432731628417969, "learning_rate": 3.4044983059059766e-06, "loss": 0.22422157227993011, "step": 3267 }, { "epoch": 0.8483904465212876, "grad_norm": 6.462512969970703, "learning_rate": 3.4035931467420964e-06, "loss": 0.3359612822532654, "step": 3268 }, { "epoch": 0.84865005192108, "grad_norm": 7.981855869293213, "learning_rate": 3.402687872037912e-06, "loss": 0.24027451872825623, "step": 3269 }, { "epoch": 0.8489096573208723, "grad_norm": 10.149638175964355, "learning_rate": 3.401782481953457e-06, "loss": 0.12794272601604462, "step": 3270 }, { "epoch": 0.8491692627206646, "grad_norm": 6.328493118286133, "learning_rate": 3.4008769766487826e-06, "loss": 0.2874472737312317, "step": 3271 }, { "epoch": 0.8494288681204569, "grad_norm": 5.472587585449219, "learning_rate": 3.399971356283963e-06, "loss": 0.3184884190559387, "step": 3272 }, { "epoch": 0.8496884735202492, "grad_norm": 11.090744018554688, "learning_rate": 3.399065621019089e-06, "loss": 0.18312811851501465, "step": 3273 }, { "epoch": 0.8499480789200415, "grad_norm": 8.096352577209473, "learning_rate": 3.3981597710142757e-06, "loss": 0.25171712040901184, "step": 3274 }, { "epoch": 0.8502076843198338, "grad_norm": 4.9624152183532715, "learning_rate": 3.3972538064296545e-06, "loss": 0.28479719161987305, "step": 3275 }, { "epoch": 0.8504672897196262, "grad_norm": 4.787832260131836, "learning_rate": 3.396347727425381e-06, "loss": 0.2968963086605072, "step": 3276 }, { "epoch": 0.8507268951194185, "grad_norm": 6.597270965576172, "learning_rate": 3.3954415341616285e-06, "loss": 0.318134605884552, "step": 3277 }, { "epoch": 0.8509865005192108, "grad_norm": 10.046306610107422, "learning_rate": 3.394535226798592e-06, "loss": 0.13054808974266052, "step": 3278 }, { "epoch": 0.8512461059190031, "grad_norm": 10.322465896606445, "learning_rate": 3.393628805496485e-06, "loss": 0.20196473598480225, "step": 3279 }, { "epoch": 0.8515057113187954, "grad_norm": 4.030712127685547, "learning_rate": 3.3927222704155415e-06, "loss": 0.33420199155807495, "step": 3280 }, { "epoch": 0.8517653167185878, "grad_norm": 5.788976669311523, "learning_rate": 3.3918156217160182e-06, "loss": 0.2570119798183441, "step": 3281 }, { "epoch": 0.8520249221183801, "grad_norm": 7.372159004211426, "learning_rate": 3.3909088595581884e-06, "loss": 0.3302896320819855, "step": 3282 }, { "epoch": 0.8522845275181724, "grad_norm": 6.073140621185303, "learning_rate": 3.3900019841023476e-06, "loss": 0.2514299154281616, "step": 3283 }, { "epoch": 0.8525441329179647, "grad_norm": 4.859951496124268, "learning_rate": 3.389094995508809e-06, "loss": 0.2567751109600067, "step": 3284 }, { "epoch": 0.852803738317757, "grad_norm": 12.326886177062988, "learning_rate": 3.3881878939379086e-06, "loss": 0.2012024223804474, "step": 3285 }, { "epoch": 0.8530633437175493, "grad_norm": 10.898907661437988, "learning_rate": 3.3872806795500014e-06, "loss": 0.14584381878376007, "step": 3286 }, { "epoch": 0.8533229491173416, "grad_norm": 9.104905128479004, "learning_rate": 3.386373352505462e-06, "loss": 0.2196689397096634, "step": 3287 }, { "epoch": 0.8535825545171339, "grad_norm": 4.148784160614014, "learning_rate": 3.385465912964685e-06, "loss": 0.32911574840545654, "step": 3288 }, { "epoch": 0.8538421599169262, "grad_norm": 12.397287368774414, "learning_rate": 3.3845583610880844e-06, "loss": 0.20768463611602783, "step": 3289 }, { "epoch": 0.8541017653167186, "grad_norm": 11.405089378356934, "learning_rate": 3.383650697036095e-06, "loss": 0.17635276913642883, "step": 3290 }, { "epoch": 0.8543613707165109, "grad_norm": 3.804802417755127, "learning_rate": 3.3827429209691722e-06, "loss": 0.3046160340309143, "step": 3291 }, { "epoch": 0.8546209761163032, "grad_norm": 6.376018047332764, "learning_rate": 3.3818350330477874e-06, "loss": 0.3042973279953003, "step": 3292 }, { "epoch": 0.8548805815160956, "grad_norm": 6.954339504241943, "learning_rate": 3.3809270334324364e-06, "loss": 0.3168400228023529, "step": 3293 }, { "epoch": 0.8551401869158879, "grad_norm": 6.304434776306152, "learning_rate": 3.3800189222836316e-06, "loss": 0.248386949300766, "step": 3294 }, { "epoch": 0.8553997923156802, "grad_norm": 6.78523588180542, "learning_rate": 3.3791106997619078e-06, "loss": 0.22015540301799774, "step": 3295 }, { "epoch": 0.8556593977154725, "grad_norm": 6.649979114532471, "learning_rate": 3.378202366027817e-06, "loss": 0.31193727254867554, "step": 3296 }, { "epoch": 0.8559190031152648, "grad_norm": 7.3843278884887695, "learning_rate": 3.3772939212419314e-06, "loss": 0.33515310287475586, "step": 3297 }, { "epoch": 0.8561786085150571, "grad_norm": 7.275430679321289, "learning_rate": 3.3763853655648436e-06, "loss": 0.17989321053028107, "step": 3298 }, { "epoch": 0.8564382139148494, "grad_norm": 8.650283813476562, "learning_rate": 3.3754766991571657e-06, "loss": 0.14447438716888428, "step": 3299 }, { "epoch": 0.8566978193146417, "grad_norm": 7.902543544769287, "learning_rate": 3.3745679221795284e-06, "loss": 0.20422831177711487, "step": 3300 }, { "epoch": 0.856957424714434, "grad_norm": 6.044317722320557, "learning_rate": 3.3736590347925842e-06, "loss": 0.29967576265335083, "step": 3301 }, { "epoch": 0.8572170301142263, "grad_norm": 5.543229579925537, "learning_rate": 3.3727500371570014e-06, "loss": 0.25322067737579346, "step": 3302 }, { "epoch": 0.8574766355140186, "grad_norm": 4.037832260131836, "learning_rate": 3.371840929433472e-06, "loss": 0.3856894373893738, "step": 3303 }, { "epoch": 0.857736240913811, "grad_norm": 6.300179481506348, "learning_rate": 3.370931711782704e-06, "loss": 0.2460189014673233, "step": 3304 }, { "epoch": 0.8579958463136034, "grad_norm": 5.394216060638428, "learning_rate": 3.370022384365427e-06, "loss": 0.2787153124809265, "step": 3305 }, { "epoch": 0.8582554517133957, "grad_norm": 4.71046781539917, "learning_rate": 3.3691129473423895e-06, "loss": 0.28374534845352173, "step": 3306 }, { "epoch": 0.858515057113188, "grad_norm": 10.475378036499023, "learning_rate": 3.368203400874358e-06, "loss": 0.23329317569732666, "step": 3307 }, { "epoch": 0.8587746625129803, "grad_norm": 5.652655124664307, "learning_rate": 3.3672937451221206e-06, "loss": 0.25311994552612305, "step": 3308 }, { "epoch": 0.8590342679127726, "grad_norm": 11.223024368286133, "learning_rate": 3.366383980246483e-06, "loss": 0.16330605745315552, "step": 3309 }, { "epoch": 0.8592938733125649, "grad_norm": 12.43634033203125, "learning_rate": 3.3654741064082712e-06, "loss": 0.18303070962429047, "step": 3310 }, { "epoch": 0.8595534787123572, "grad_norm": 4.550843715667725, "learning_rate": 3.3645641237683295e-06, "loss": 0.30283212661743164, "step": 3311 }, { "epoch": 0.8598130841121495, "grad_norm": 8.145953178405762, "learning_rate": 3.363654032487523e-06, "loss": 0.26709219813346863, "step": 3312 }, { "epoch": 0.8600726895119418, "grad_norm": 3.952237606048584, "learning_rate": 3.362743832726735e-06, "loss": 0.27596521377563477, "step": 3313 }, { "epoch": 0.8603322949117341, "grad_norm": 11.35354232788086, "learning_rate": 3.3618335246468657e-06, "loss": 0.15235300362110138, "step": 3314 }, { "epoch": 0.8605919003115264, "grad_norm": 10.719446182250977, "learning_rate": 3.360923108408839e-06, "loss": 0.21500936150550842, "step": 3315 }, { "epoch": 0.8608515057113187, "grad_norm": 3.5190041065216064, "learning_rate": 3.3600125841735955e-06, "loss": 0.32286950945854187, "step": 3316 }, { "epoch": 0.8611111111111112, "grad_norm": 5.558568000793457, "learning_rate": 3.359101952102094e-06, "loss": 0.28670579195022583, "step": 3317 }, { "epoch": 0.8613707165109035, "grad_norm": 8.831124305725098, "learning_rate": 3.3581912123553144e-06, "loss": 0.16150400042533875, "step": 3318 }, { "epoch": 0.8616303219106958, "grad_norm": 8.439031600952148, "learning_rate": 3.357280365094254e-06, "loss": 0.32774263620376587, "step": 3319 }, { "epoch": 0.8618899273104881, "grad_norm": 4.254162788391113, "learning_rate": 3.3563694104799292e-06, "loss": 0.308172345161438, "step": 3320 }, { "epoch": 0.8621495327102804, "grad_norm": 9.970341682434082, "learning_rate": 3.3554583486733776e-06, "loss": 0.2635253667831421, "step": 3321 }, { "epoch": 0.8624091381100727, "grad_norm": 5.412344932556152, "learning_rate": 3.3545471798356526e-06, "loss": 0.228183776140213, "step": 3322 }, { "epoch": 0.862668743509865, "grad_norm": 9.442593574523926, "learning_rate": 3.353635904127829e-06, "loss": 0.1892235428094864, "step": 3323 }, { "epoch": 0.8629283489096573, "grad_norm": 5.245751857757568, "learning_rate": 3.3527245217109986e-06, "loss": 0.28421562910079956, "step": 3324 }, { "epoch": 0.8631879543094496, "grad_norm": 5.351529598236084, "learning_rate": 3.3518130327462734e-06, "loss": 0.3106686472892761, "step": 3325 }, { "epoch": 0.8634475597092419, "grad_norm": 3.636737585067749, "learning_rate": 3.3509014373947834e-06, "loss": 0.3121892809867859, "step": 3326 }, { "epoch": 0.8637071651090342, "grad_norm": 4.759860515594482, "learning_rate": 3.3499897358176793e-06, "loss": 0.2981054186820984, "step": 3327 }, { "epoch": 0.8639667705088265, "grad_norm": 9.191116333007812, "learning_rate": 3.349077928176126e-06, "loss": 0.21949627995491028, "step": 3328 }, { "epoch": 0.864226375908619, "grad_norm": 9.326444625854492, "learning_rate": 3.3481660146313133e-06, "loss": 0.16287292540073395, "step": 3329 }, { "epoch": 0.8644859813084113, "grad_norm": 10.398551940917969, "learning_rate": 3.3472539953444453e-06, "loss": 0.19461597502231598, "step": 3330 }, { "epoch": 0.8647455867082036, "grad_norm": 9.493335723876953, "learning_rate": 3.346341870476746e-06, "loss": 0.10240387916564941, "step": 3331 }, { "epoch": 0.8650051921079959, "grad_norm": 10.085707664489746, "learning_rate": 3.3454296401894585e-06, "loss": 0.1996561586856842, "step": 3332 }, { "epoch": 0.8652647975077882, "grad_norm": 5.939257621765137, "learning_rate": 3.344517304643844e-06, "loss": 0.253200888633728, "step": 3333 }, { "epoch": 0.8655244029075805, "grad_norm": 10.121209144592285, "learning_rate": 3.3436048640011832e-06, "loss": 0.2181432843208313, "step": 3334 }, { "epoch": 0.8657840083073728, "grad_norm": 7.010522365570068, "learning_rate": 3.342692318422773e-06, "loss": 0.3127179443836212, "step": 3335 }, { "epoch": 0.8660436137071651, "grad_norm": 5.254627704620361, "learning_rate": 3.3417796680699334e-06, "loss": 0.3067246973514557, "step": 3336 }, { "epoch": 0.8663032191069574, "grad_norm": 12.96982192993164, "learning_rate": 3.3408669131039972e-06, "loss": 0.24199259281158447, "step": 3337 }, { "epoch": 0.8665628245067497, "grad_norm": 10.228540420532227, "learning_rate": 3.33995405368632e-06, "loss": 0.26661378145217896, "step": 3338 }, { "epoch": 0.866822429906542, "grad_norm": 4.581727981567383, "learning_rate": 3.3390410899782748e-06, "loss": 0.3129448890686035, "step": 3339 }, { "epoch": 0.8670820353063343, "grad_norm": 4.01639461517334, "learning_rate": 3.3381280221412517e-06, "loss": 0.3342529535293579, "step": 3340 }, { "epoch": 0.8673416407061267, "grad_norm": 13.156742095947266, "learning_rate": 3.3372148503366607e-06, "loss": 0.12190891802310944, "step": 3341 }, { "epoch": 0.867601246105919, "grad_norm": 7.000643730163574, "learning_rate": 3.3363015747259294e-06, "loss": 0.294683039188385, "step": 3342 }, { "epoch": 0.8678608515057114, "grad_norm": 7.072605133056641, "learning_rate": 3.3353881954705047e-06, "loss": 0.2445610910654068, "step": 3343 }, { "epoch": 0.8681204569055037, "grad_norm": 6.49428653717041, "learning_rate": 3.3344747127318506e-06, "loss": 0.3024108409881592, "step": 3344 }, { "epoch": 0.868380062305296, "grad_norm": 11.409475326538086, "learning_rate": 3.33356112667145e-06, "loss": 0.20842193067073822, "step": 3345 }, { "epoch": 0.8686396677050883, "grad_norm": 9.54553508758545, "learning_rate": 3.332647437450803e-06, "loss": 0.18619659543037415, "step": 3346 }, { "epoch": 0.8688992731048806, "grad_norm": 9.858890533447266, "learning_rate": 3.3317336452314308e-06, "loss": 0.2734488248825073, "step": 3347 }, { "epoch": 0.8691588785046729, "grad_norm": 3.9519660472869873, "learning_rate": 3.33081975017487e-06, "loss": 0.29538044333457947, "step": 3348 }, { "epoch": 0.8694184839044652, "grad_norm": 3.6449341773986816, "learning_rate": 3.329905752442677e-06, "loss": 0.29278191924095154, "step": 3349 }, { "epoch": 0.8696780893042575, "grad_norm": 6.590338230133057, "learning_rate": 3.328991652196424e-06, "loss": 0.29935044050216675, "step": 3350 }, { "epoch": 0.8699376947040498, "grad_norm": 5.693306922912598, "learning_rate": 3.3280774495977048e-06, "loss": 0.25860708951950073, "step": 3351 }, { "epoch": 0.8701973001038421, "grad_norm": 8.663237571716309, "learning_rate": 3.3271631448081277e-06, "loss": 0.1730923056602478, "step": 3352 }, { "epoch": 0.8704569055036345, "grad_norm": 5.26724100112915, "learning_rate": 3.3262487379893227e-06, "loss": 0.2516552209854126, "step": 3353 }, { "epoch": 0.8707165109034268, "grad_norm": 4.856937885284424, "learning_rate": 3.325334229302935e-06, "loss": 0.2965053915977478, "step": 3354 }, { "epoch": 0.8709761163032191, "grad_norm": 6.856930255889893, "learning_rate": 3.3244196189106287e-06, "loss": 0.27389487624168396, "step": 3355 }, { "epoch": 0.8712357217030114, "grad_norm": 10.323691368103027, "learning_rate": 3.3235049069740864e-06, "loss": 0.18919053673744202, "step": 3356 }, { "epoch": 0.8714953271028038, "grad_norm": 8.418497085571289, "learning_rate": 3.3225900936550094e-06, "loss": 0.19659343361854553, "step": 3357 }, { "epoch": 0.8717549325025961, "grad_norm": 4.103277683258057, "learning_rate": 3.3216751791151124e-06, "loss": 0.2831292748451233, "step": 3358 }, { "epoch": 0.8720145379023884, "grad_norm": 13.385625839233398, "learning_rate": 3.320760163516134e-06, "loss": 0.181162029504776, "step": 3359 }, { "epoch": 0.8722741433021807, "grad_norm": 4.007984161376953, "learning_rate": 3.3198450470198273e-06, "loss": 0.3165947496891022, "step": 3360 }, { "epoch": 0.872533748701973, "grad_norm": 6.351464748382568, "learning_rate": 3.3189298297879653e-06, "loss": 0.25251686573028564, "step": 3361 }, { "epoch": 0.8727933541017653, "grad_norm": 6.752330780029297, "learning_rate": 3.3180145119823347e-06, "loss": 0.2262190282344818, "step": 3362 }, { "epoch": 0.8730529595015576, "grad_norm": 12.711822509765625, "learning_rate": 3.3170990937647445e-06, "loss": 0.24987097084522247, "step": 3363 }, { "epoch": 0.8733125649013499, "grad_norm": 3.9860501289367676, "learning_rate": 3.316183575297019e-06, "loss": 0.28119325637817383, "step": 3364 }, { "epoch": 0.8735721703011423, "grad_norm": 3.6769120693206787, "learning_rate": 3.3152679567410023e-06, "loss": 0.31179678440093994, "step": 3365 }, { "epoch": 0.8738317757009346, "grad_norm": 9.577581405639648, "learning_rate": 3.3143522382585536e-06, "loss": 0.2555857300758362, "step": 3366 }, { "epoch": 0.8740913811007269, "grad_norm": 8.176692008972168, "learning_rate": 3.3134364200115504e-06, "loss": 0.2636450529098511, "step": 3367 }, { "epoch": 0.8743509865005192, "grad_norm": 4.493625164031982, "learning_rate": 3.3125205021618893e-06, "loss": 0.30662429332733154, "step": 3368 }, { "epoch": 0.8746105919003115, "grad_norm": 8.759267807006836, "learning_rate": 3.3116044848714833e-06, "loss": 0.15639325976371765, "step": 3369 }, { "epoch": 0.8748701973001038, "grad_norm": 10.261921882629395, "learning_rate": 3.3106883683022646e-06, "loss": 0.21774499118328094, "step": 3370 }, { "epoch": 0.8751298026998962, "grad_norm": 4.139370441436768, "learning_rate": 3.309772152616179e-06, "loss": 0.3123098313808441, "step": 3371 }, { "epoch": 0.8753894080996885, "grad_norm": 4.167735576629639, "learning_rate": 3.3088558379751945e-06, "loss": 0.3177361488342285, "step": 3372 }, { "epoch": 0.8756490134994808, "grad_norm": 4.0790629386901855, "learning_rate": 3.307939424541294e-06, "loss": 0.2966536283493042, "step": 3373 }, { "epoch": 0.8759086188992731, "grad_norm": 9.396406173706055, "learning_rate": 3.3070229124764784e-06, "loss": 0.17498508095741272, "step": 3374 }, { "epoch": 0.8761682242990654, "grad_norm": 10.222716331481934, "learning_rate": 3.3061063019427653e-06, "loss": 0.3429011106491089, "step": 3375 }, { "epoch": 0.8764278296988577, "grad_norm": 2.9476430416107178, "learning_rate": 3.305189593102192e-06, "loss": 0.30618226528167725, "step": 3376 }, { "epoch": 0.8766874350986501, "grad_norm": 5.6245574951171875, "learning_rate": 3.30427278611681e-06, "loss": 0.2576757073402405, "step": 3377 }, { "epoch": 0.8769470404984424, "grad_norm": 8.772769927978516, "learning_rate": 3.3033558811486915e-06, "loss": 0.2401801198720932, "step": 3378 }, { "epoch": 0.8772066458982347, "grad_norm": 9.77725887298584, "learning_rate": 3.302438878359923e-06, "loss": 0.23374293744564056, "step": 3379 }, { "epoch": 0.877466251298027, "grad_norm": 6.5899248123168945, "learning_rate": 3.30152177791261e-06, "loss": 0.21401748061180115, "step": 3380 }, { "epoch": 0.8777258566978193, "grad_norm": 3.989739418029785, "learning_rate": 3.300604579968875e-06, "loss": 0.2737910747528076, "step": 3381 }, { "epoch": 0.8779854620976116, "grad_norm": 3.498910665512085, "learning_rate": 3.2996872846908574e-06, "loss": 0.28346192836761475, "step": 3382 }, { "epoch": 0.8782450674974039, "grad_norm": 10.510558128356934, "learning_rate": 3.298769892240713e-06, "loss": 0.12136662006378174, "step": 3383 }, { "epoch": 0.8785046728971962, "grad_norm": 14.14472484588623, "learning_rate": 3.2978524027806185e-06, "loss": 0.17256301641464233, "step": 3384 }, { "epoch": 0.8787642782969886, "grad_norm": 4.649110794067383, "learning_rate": 3.2969348164727624e-06, "loss": 0.2557840049266815, "step": 3385 }, { "epoch": 0.8790238836967809, "grad_norm": 8.817009925842285, "learning_rate": 3.296017133479354e-06, "loss": 0.13935139775276184, "step": 3386 }, { "epoch": 0.8792834890965732, "grad_norm": 9.183444023132324, "learning_rate": 3.295099353962618e-06, "loss": 0.2966984510421753, "step": 3387 }, { "epoch": 0.8795430944963655, "grad_norm": 7.609621047973633, "learning_rate": 3.2941814780847987e-06, "loss": 0.28377294540405273, "step": 3388 }, { "epoch": 0.8798026998961579, "grad_norm": 16.57323455810547, "learning_rate": 3.293263506008153e-06, "loss": 0.16071687638759613, "step": 3389 }, { "epoch": 0.8800623052959502, "grad_norm": 10.69848918914795, "learning_rate": 3.2923454378949587e-06, "loss": 0.20429718494415283, "step": 3390 }, { "epoch": 0.8803219106957425, "grad_norm": 6.932797431945801, "learning_rate": 3.291427273907509e-06, "loss": 0.24383991956710815, "step": 3391 }, { "epoch": 0.8805815160955348, "grad_norm": 11.884730339050293, "learning_rate": 3.2905090142081147e-06, "loss": 0.28007936477661133, "step": 3392 }, { "epoch": 0.8808411214953271, "grad_norm": 6.064772129058838, "learning_rate": 3.289590658959103e-06, "loss": 0.24741274118423462, "step": 3393 }, { "epoch": 0.8811007268951194, "grad_norm": 12.543322563171387, "learning_rate": 3.2886722083228177e-06, "loss": 0.16742339730262756, "step": 3394 }, { "epoch": 0.8813603322949117, "grad_norm": 12.306425094604492, "learning_rate": 3.2877536624616198e-06, "loss": 0.31664445996284485, "step": 3395 }, { "epoch": 0.881619937694704, "grad_norm": 9.7003812789917, "learning_rate": 3.286835021537886e-06, "loss": 0.1128140240907669, "step": 3396 }, { "epoch": 0.8818795430944963, "grad_norm": 7.621284008026123, "learning_rate": 3.2859162857140143e-06, "loss": 0.33743828535079956, "step": 3397 }, { "epoch": 0.8821391484942886, "grad_norm": 8.416075706481934, "learning_rate": 3.2849974551524135e-06, "loss": 0.1428036093711853, "step": 3398 }, { "epoch": 0.882398753894081, "grad_norm": 4.171731472015381, "learning_rate": 3.284078530015512e-06, "loss": 0.2950824499130249, "step": 3399 }, { "epoch": 0.8826583592938733, "grad_norm": 6.788780212402344, "learning_rate": 3.2831595104657547e-06, "loss": 0.21215420961380005, "step": 3400 }, { "epoch": 0.8829179646936657, "grad_norm": 15.442902565002441, "learning_rate": 3.2822403966656045e-06, "loss": 0.18612661957740784, "step": 3401 }, { "epoch": 0.883177570093458, "grad_norm": 3.418562650680542, "learning_rate": 3.2813211887775386e-06, "loss": 0.30278855562210083, "step": 3402 }, { "epoch": 0.8834371754932503, "grad_norm": 6.719057559967041, "learning_rate": 3.2804018869640525e-06, "loss": 0.2661706209182739, "step": 3403 }, { "epoch": 0.8836967808930426, "grad_norm": 5.60141134262085, "learning_rate": 3.279482491387657e-06, "loss": 0.29931461811065674, "step": 3404 }, { "epoch": 0.8839563862928349, "grad_norm": 8.572219848632812, "learning_rate": 3.2785630022108804e-06, "loss": 0.30428242683410645, "step": 3405 }, { "epoch": 0.8842159916926272, "grad_norm": 9.248329162597656, "learning_rate": 3.2776434195962682e-06, "loss": 0.1892324686050415, "step": 3406 }, { "epoch": 0.8844755970924195, "grad_norm": 4.600074291229248, "learning_rate": 3.2767237437063803e-06, "loss": 0.3328894078731537, "step": 3407 }, { "epoch": 0.8847352024922118, "grad_norm": 11.009840965270996, "learning_rate": 3.2758039747037944e-06, "loss": 0.22681337594985962, "step": 3408 }, { "epoch": 0.8849948078920041, "grad_norm": 4.412347793579102, "learning_rate": 3.274884112751106e-06, "loss": 0.2932039499282837, "step": 3409 }, { "epoch": 0.8852544132917964, "grad_norm": 11.022082328796387, "learning_rate": 3.2739641580109243e-06, "loss": 0.242986261844635, "step": 3410 }, { "epoch": 0.8855140186915887, "grad_norm": 10.692666053771973, "learning_rate": 3.273044110645878e-06, "loss": 0.31624171137809753, "step": 3411 }, { "epoch": 0.885773624091381, "grad_norm": 7.99951171875, "learning_rate": 3.2721239708186077e-06, "loss": 0.16982346773147583, "step": 3412 }, { "epoch": 0.8860332294911735, "grad_norm": 5.732764720916748, "learning_rate": 3.271203738691774e-06, "loss": 0.23984713852405548, "step": 3413 }, { "epoch": 0.8862928348909658, "grad_norm": 4.330102443695068, "learning_rate": 3.2702834144280536e-06, "loss": 0.3195000886917114, "step": 3414 }, { "epoch": 0.8865524402907581, "grad_norm": 4.57103157043457, "learning_rate": 3.2693629981901392e-06, "loss": 0.3067982792854309, "step": 3415 }, { "epoch": 0.8868120456905504, "grad_norm": 4.531013011932373, "learning_rate": 3.268442490140738e-06, "loss": 0.2858099043369293, "step": 3416 }, { "epoch": 0.8870716510903427, "grad_norm": 3.9553611278533936, "learning_rate": 3.2675218904425748e-06, "loss": 0.28058725595474243, "step": 3417 }, { "epoch": 0.887331256490135, "grad_norm": 6.602977275848389, "learning_rate": 3.266601199258391e-06, "loss": 0.24679650366306305, "step": 3418 }, { "epoch": 0.8875908618899273, "grad_norm": 6.4638543128967285, "learning_rate": 3.2656804167509456e-06, "loss": 0.22083473205566406, "step": 3419 }, { "epoch": 0.8878504672897196, "grad_norm": 3.5561275482177734, "learning_rate": 3.264759543083009e-06, "loss": 0.27768173813819885, "step": 3420 }, { "epoch": 0.8881100726895119, "grad_norm": 7.373794078826904, "learning_rate": 3.2638385784173704e-06, "loss": 0.19776678085327148, "step": 3421 }, { "epoch": 0.8883696780893042, "grad_norm": 4.890158176422119, "learning_rate": 3.262917522916838e-06, "loss": 0.33617618680000305, "step": 3422 }, { "epoch": 0.8886292834890965, "grad_norm": 9.69836139678955, "learning_rate": 3.2619963767442314e-06, "loss": 0.20267321169376373, "step": 3423 }, { "epoch": 0.8888888888888888, "grad_norm": 11.92757511138916, "learning_rate": 3.2610751400623887e-06, "loss": 0.20947468280792236, "step": 3424 }, { "epoch": 0.8891484942886813, "grad_norm": 14.104970932006836, "learning_rate": 3.2601538130341627e-06, "loss": 0.19015204906463623, "step": 3425 }, { "epoch": 0.8894080996884736, "grad_norm": 6.331733226776123, "learning_rate": 3.2592323958224236e-06, "loss": 0.2168535590171814, "step": 3426 }, { "epoch": 0.8896677050882659, "grad_norm": 9.62464714050293, "learning_rate": 3.258310888590058e-06, "loss": 0.12348024547100067, "step": 3427 }, { "epoch": 0.8899273104880582, "grad_norm": 4.199970722198486, "learning_rate": 3.257389291499965e-06, "loss": 0.3062381446361542, "step": 3428 }, { "epoch": 0.8901869158878505, "grad_norm": 7.45574951171875, "learning_rate": 3.256467604715062e-06, "loss": 0.36529988050460815, "step": 3429 }, { "epoch": 0.8904465212876428, "grad_norm": 6.200622081756592, "learning_rate": 3.255545828398285e-06, "loss": 0.24856163561344147, "step": 3430 }, { "epoch": 0.8907061266874351, "grad_norm": 12.722386360168457, "learning_rate": 3.2546239627125796e-06, "loss": 0.30502980947494507, "step": 3431 }, { "epoch": 0.8909657320872274, "grad_norm": 8.976853370666504, "learning_rate": 3.2537020078209126e-06, "loss": 0.16531050205230713, "step": 3432 }, { "epoch": 0.8912253374870197, "grad_norm": 5.098653316497803, "learning_rate": 3.252779963886264e-06, "loss": 0.24928835034370422, "step": 3433 }, { "epoch": 0.891484942886812, "grad_norm": 8.290997505187988, "learning_rate": 3.25185783107163e-06, "loss": 0.18256568908691406, "step": 3434 }, { "epoch": 0.8917445482866043, "grad_norm": 11.709933280944824, "learning_rate": 3.250935609540021e-06, "loss": 0.24479940533638, "step": 3435 }, { "epoch": 0.8920041536863966, "grad_norm": 11.391413688659668, "learning_rate": 3.250013299454468e-06, "loss": 0.20793761312961578, "step": 3436 }, { "epoch": 0.892263759086189, "grad_norm": 3.388547420501709, "learning_rate": 3.2490909009780117e-06, "loss": 0.2956490218639374, "step": 3437 }, { "epoch": 0.8925233644859814, "grad_norm": 4.897642135620117, "learning_rate": 3.248168414273712e-06, "loss": 0.274985134601593, "step": 3438 }, { "epoch": 0.8927829698857737, "grad_norm": 13.152840614318848, "learning_rate": 3.2472458395046423e-06, "loss": 0.21954183280467987, "step": 3439 }, { "epoch": 0.893042575285566, "grad_norm": 11.346435546875, "learning_rate": 3.2463231768338954e-06, "loss": 0.3164845407009125, "step": 3440 }, { "epoch": 0.8933021806853583, "grad_norm": 7.191897869110107, "learning_rate": 3.2454004264245735e-06, "loss": 0.2111642062664032, "step": 3441 }, { "epoch": 0.8935617860851506, "grad_norm": 8.907236099243164, "learning_rate": 3.2444775884398e-06, "loss": 0.18346738815307617, "step": 3442 }, { "epoch": 0.8938213914849429, "grad_norm": 5.494467735290527, "learning_rate": 3.2435546630427105e-06, "loss": 0.2538677155971527, "step": 3443 }, { "epoch": 0.8940809968847352, "grad_norm": 7.104400157928467, "learning_rate": 3.2426316503964583e-06, "loss": 0.19945669174194336, "step": 3444 }, { "epoch": 0.8943406022845275, "grad_norm": 4.586598873138428, "learning_rate": 3.2417085506642095e-06, "loss": 0.3060530126094818, "step": 3445 }, { "epoch": 0.8946002076843198, "grad_norm": 7.829832077026367, "learning_rate": 3.240785364009148e-06, "loss": 0.23820550739765167, "step": 3446 }, { "epoch": 0.8948598130841121, "grad_norm": 6.063501358032227, "learning_rate": 3.239862090594471e-06, "loss": 0.2627893090248108, "step": 3447 }, { "epoch": 0.8951194184839044, "grad_norm": 4.6137213706970215, "learning_rate": 3.2389387305833932e-06, "loss": 0.31496739387512207, "step": 3448 }, { "epoch": 0.8953790238836968, "grad_norm": 7.78245210647583, "learning_rate": 3.238015284139143e-06, "loss": 0.2249600887298584, "step": 3449 }, { "epoch": 0.8956386292834891, "grad_norm": 7.222140312194824, "learning_rate": 3.2370917514249646e-06, "loss": 0.31784629821777344, "step": 3450 }, { "epoch": 0.8958982346832814, "grad_norm": 4.712069511413574, "learning_rate": 3.2361681326041167e-06, "loss": 0.2558526396751404, "step": 3451 }, { "epoch": 0.8961578400830738, "grad_norm": 9.446331024169922, "learning_rate": 3.2352444278398754e-06, "loss": 0.21674571931362152, "step": 3452 }, { "epoch": 0.8964174454828661, "grad_norm": 8.354859352111816, "learning_rate": 3.2343206372955305e-06, "loss": 0.18858137726783752, "step": 3453 }, { "epoch": 0.8966770508826584, "grad_norm": 5.7028350830078125, "learning_rate": 3.2333967611343854e-06, "loss": 0.28787827491760254, "step": 3454 }, { "epoch": 0.8969366562824507, "grad_norm": 7.604372024536133, "learning_rate": 3.232472799519762e-06, "loss": 0.3194512128829956, "step": 3455 }, { "epoch": 0.897196261682243, "grad_norm": 10.336833000183105, "learning_rate": 3.231548752614994e-06, "loss": 0.24964439868927002, "step": 3456 }, { "epoch": 0.8974558670820353, "grad_norm": 11.467708587646484, "learning_rate": 3.2306246205834333e-06, "loss": 0.24544984102249146, "step": 3457 }, { "epoch": 0.8977154724818276, "grad_norm": 5.6297736167907715, "learning_rate": 3.229700403588444e-06, "loss": 0.30678385496139526, "step": 3458 }, { "epoch": 0.8979750778816199, "grad_norm": 9.697653770446777, "learning_rate": 3.2287761017934076e-06, "loss": 0.26650679111480713, "step": 3459 }, { "epoch": 0.8982346832814122, "grad_norm": 13.667064666748047, "learning_rate": 3.2278517153617186e-06, "loss": 0.17806312441825867, "step": 3460 }, { "epoch": 0.8984942886812046, "grad_norm": 9.299569129943848, "learning_rate": 3.226927244456788e-06, "loss": 0.18898740410804749, "step": 3461 }, { "epoch": 0.8987538940809969, "grad_norm": 5.394928455352783, "learning_rate": 3.2260026892420397e-06, "loss": 0.2789182662963867, "step": 3462 }, { "epoch": 0.8990134994807892, "grad_norm": 14.2201509475708, "learning_rate": 3.2250780498809157e-06, "loss": 0.20596453547477722, "step": 3463 }, { "epoch": 0.8992731048805815, "grad_norm": 4.142462730407715, "learning_rate": 3.22415332653687e-06, "loss": 0.2915653586387634, "step": 3464 }, { "epoch": 0.8995327102803738, "grad_norm": 3.8097078800201416, "learning_rate": 3.2232285193733735e-06, "loss": 0.30312180519104004, "step": 3465 }, { "epoch": 0.8997923156801662, "grad_norm": 7.344821453094482, "learning_rate": 3.2223036285539092e-06, "loss": 0.257208913564682, "step": 3466 }, { "epoch": 0.9000519210799585, "grad_norm": 9.195979118347168, "learning_rate": 3.2213786542419796e-06, "loss": 0.180707186460495, "step": 3467 }, { "epoch": 0.9003115264797508, "grad_norm": 4.461888313293457, "learning_rate": 3.220453596601096e-06, "loss": 0.28280237317085266, "step": 3468 }, { "epoch": 0.9005711318795431, "grad_norm": 4.145972728729248, "learning_rate": 3.219528455794788e-06, "loss": 0.28296196460723877, "step": 3469 }, { "epoch": 0.9008307372793354, "grad_norm": 8.663667678833008, "learning_rate": 3.2186032319866e-06, "loss": 0.20018711686134338, "step": 3470 }, { "epoch": 0.9010903426791277, "grad_norm": 10.041707992553711, "learning_rate": 3.217677925340091e-06, "loss": 0.1641007363796234, "step": 3471 }, { "epoch": 0.90134994807892, "grad_norm": 4.050715923309326, "learning_rate": 3.2167525360188317e-06, "loss": 0.2892046570777893, "step": 3472 }, { "epoch": 0.9016095534787124, "grad_norm": 5.496603012084961, "learning_rate": 3.2158270641864126e-06, "loss": 0.2498742938041687, "step": 3473 }, { "epoch": 0.9018691588785047, "grad_norm": 8.121591567993164, "learning_rate": 3.2149015100064333e-06, "loss": 0.2621276378631592, "step": 3474 }, { "epoch": 0.902128764278297, "grad_norm": 10.293593406677246, "learning_rate": 3.213975873642513e-06, "loss": 0.23491531610488892, "step": 3475 }, { "epoch": 0.9023883696780893, "grad_norm": 10.070108413696289, "learning_rate": 3.2130501552582823e-06, "loss": 0.14330598711967468, "step": 3476 }, { "epoch": 0.9026479750778816, "grad_norm": 8.717768669128418, "learning_rate": 3.2121243550173854e-06, "loss": 0.3143349289894104, "step": 3477 }, { "epoch": 0.9029075804776739, "grad_norm": 5.047975063323975, "learning_rate": 3.2111984730834837e-06, "loss": 0.24665260314941406, "step": 3478 }, { "epoch": 0.9031671858774662, "grad_norm": 3.884870767593384, "learning_rate": 3.2102725096202527e-06, "loss": 0.2833096981048584, "step": 3479 }, { "epoch": 0.9034267912772586, "grad_norm": 8.437553405761719, "learning_rate": 3.2093464647913815e-06, "loss": 0.25509101152420044, "step": 3480 }, { "epoch": 0.9036863966770509, "grad_norm": 4.001118183135986, "learning_rate": 3.2084203387605716e-06, "loss": 0.34106001257896423, "step": 3481 }, { "epoch": 0.9039460020768432, "grad_norm": 7.433084487915039, "learning_rate": 3.207494131691542e-06, "loss": 0.2821444571018219, "step": 3482 }, { "epoch": 0.9042056074766355, "grad_norm": 9.198089599609375, "learning_rate": 3.2065678437480265e-06, "loss": 0.26692426204681396, "step": 3483 }, { "epoch": 0.9044652128764278, "grad_norm": 9.031526565551758, "learning_rate": 3.2056414750937696e-06, "loss": 0.16677576303482056, "step": 3484 }, { "epoch": 0.9047248182762202, "grad_norm": 11.662302017211914, "learning_rate": 3.2047150258925324e-06, "loss": 0.1809493750333786, "step": 3485 }, { "epoch": 0.9049844236760125, "grad_norm": 7.9274163246154785, "learning_rate": 3.203788496308091e-06, "loss": 0.23723867535591125, "step": 3486 }, { "epoch": 0.9052440290758048, "grad_norm": 5.7449188232421875, "learning_rate": 3.2028618865042327e-06, "loss": 0.30651092529296875, "step": 3487 }, { "epoch": 0.9055036344755971, "grad_norm": 8.594687461853027, "learning_rate": 3.201935196644763e-06, "loss": 0.17178912460803986, "step": 3488 }, { "epoch": 0.9057632398753894, "grad_norm": 5.2500128746032715, "learning_rate": 3.2010084268934984e-06, "loss": 0.32073235511779785, "step": 3489 }, { "epoch": 0.9060228452751817, "grad_norm": 6.740016937255859, "learning_rate": 3.2000815774142703e-06, "loss": 0.27718719840049744, "step": 3490 }, { "epoch": 0.906282450674974, "grad_norm": 11.484331130981445, "learning_rate": 3.199154648370925e-06, "loss": 0.18331485986709595, "step": 3491 }, { "epoch": 0.9065420560747663, "grad_norm": 8.460870742797852, "learning_rate": 3.198227639927322e-06, "loss": 0.11249206960201263, "step": 3492 }, { "epoch": 0.9068016614745587, "grad_norm": 10.577502250671387, "learning_rate": 3.1973005522473355e-06, "loss": 0.1488223820924759, "step": 3493 }, { "epoch": 0.907061266874351, "grad_norm": 10.31640911102295, "learning_rate": 3.196373385494853e-06, "loss": 0.17926204204559326, "step": 3494 }, { "epoch": 0.9073208722741433, "grad_norm": 4.01501989364624, "learning_rate": 3.1954461398337766e-06, "loss": 0.3376955986022949, "step": 3495 }, { "epoch": 0.9075804776739356, "grad_norm": 5.155045509338379, "learning_rate": 3.194518815428022e-06, "loss": 0.24405407905578613, "step": 3496 }, { "epoch": 0.907840083073728, "grad_norm": 5.375679969787598, "learning_rate": 3.193591412441519e-06, "loss": 0.3139036297798157, "step": 3497 }, { "epoch": 0.9080996884735203, "grad_norm": 3.696629047393799, "learning_rate": 3.1926639310382114e-06, "loss": 0.2596105635166168, "step": 3498 }, { "epoch": 0.9083592938733126, "grad_norm": 8.0321626663208, "learning_rate": 3.1917363713820565e-06, "loss": 0.14058974385261536, "step": 3499 }, { "epoch": 0.9086188992731049, "grad_norm": 3.6637566089630127, "learning_rate": 3.1908087336370245e-06, "loss": 0.3160039782524109, "step": 3500 }, { "epoch": 0.9088785046728972, "grad_norm": 9.54134750366211, "learning_rate": 3.189881017967103e-06, "loss": 0.23356544971466064, "step": 3501 }, { "epoch": 0.9091381100726895, "grad_norm": 9.856812477111816, "learning_rate": 3.188953224536289e-06, "loss": 0.2758694589138031, "step": 3502 }, { "epoch": 0.9093977154724818, "grad_norm": 9.841414451599121, "learning_rate": 3.188025353508595e-06, "loss": 0.17468856275081635, "step": 3503 }, { "epoch": 0.9096573208722741, "grad_norm": 11.405608177185059, "learning_rate": 3.187097405048049e-06, "loss": 0.25739550590515137, "step": 3504 }, { "epoch": 0.9099169262720664, "grad_norm": 10.516032218933105, "learning_rate": 3.18616937931869e-06, "loss": 0.16826125979423523, "step": 3505 }, { "epoch": 0.9101765316718587, "grad_norm": 4.692330360412598, "learning_rate": 3.1852412764845704e-06, "loss": 0.33409029245376587, "step": 3506 }, { "epoch": 0.910436137071651, "grad_norm": 7.971615314483643, "learning_rate": 3.1843130967097596e-06, "loss": 0.1520715057849884, "step": 3507 }, { "epoch": 0.9106957424714434, "grad_norm": 7.648272514343262, "learning_rate": 3.183384840158338e-06, "loss": 0.20789913833141327, "step": 3508 }, { "epoch": 0.9109553478712358, "grad_norm": 10.600997924804688, "learning_rate": 3.1824565069943993e-06, "loss": 0.18215996026992798, "step": 3509 }, { "epoch": 0.9112149532710281, "grad_norm": 4.929108619689941, "learning_rate": 3.181528097382052e-06, "loss": 0.2866085171699524, "step": 3510 }, { "epoch": 0.9114745586708204, "grad_norm": 8.44766616821289, "learning_rate": 3.180599611485418e-06, "loss": 0.174187570810318, "step": 3511 }, { "epoch": 0.9117341640706127, "grad_norm": 4.6898298263549805, "learning_rate": 3.179671049468632e-06, "loss": 0.28209808468818665, "step": 3512 }, { "epoch": 0.911993769470405, "grad_norm": 6.809713363647461, "learning_rate": 3.1787424114958433e-06, "loss": 0.24239276349544525, "step": 3513 }, { "epoch": 0.9122533748701973, "grad_norm": 5.374906539916992, "learning_rate": 3.1778136977312125e-06, "loss": 0.31941160559654236, "step": 3514 }, { "epoch": 0.9125129802699896, "grad_norm": 5.717736721038818, "learning_rate": 3.1768849083389164e-06, "loss": 0.23842309415340424, "step": 3515 }, { "epoch": 0.9127725856697819, "grad_norm": 8.306065559387207, "learning_rate": 3.175956043483142e-06, "loss": 0.24933470785617828, "step": 3516 }, { "epoch": 0.9130321910695742, "grad_norm": 8.231451034545898, "learning_rate": 3.1750271033280925e-06, "loss": 0.3041419982910156, "step": 3517 }, { "epoch": 0.9132917964693665, "grad_norm": 5.617533206939697, "learning_rate": 3.1740980880379823e-06, "loss": 0.23045432567596436, "step": 3518 }, { "epoch": 0.9135514018691588, "grad_norm": 8.629053115844727, "learning_rate": 3.1731689977770414e-06, "loss": 0.22889752686023712, "step": 3519 }, { "epoch": 0.9138110072689511, "grad_norm": 4.285643577575684, "learning_rate": 3.172239832709511e-06, "loss": 0.30302220582962036, "step": 3520 }, { "epoch": 0.9140706126687436, "grad_norm": 5.968740463256836, "learning_rate": 3.171310592999646e-06, "loss": 0.2675471603870392, "step": 3521 }, { "epoch": 0.9143302180685359, "grad_norm": 11.345952033996582, "learning_rate": 3.1703812788117157e-06, "loss": 0.2952604293823242, "step": 3522 }, { "epoch": 0.9145898234683282, "grad_norm": 13.78477954864502, "learning_rate": 3.1694518903099993e-06, "loss": 0.16869224607944489, "step": 3523 }, { "epoch": 0.9148494288681205, "grad_norm": 10.984291076660156, "learning_rate": 3.168522427658794e-06, "loss": 0.1923738718032837, "step": 3524 }, { "epoch": 0.9151090342679128, "grad_norm": 3.867459535598755, "learning_rate": 3.1675928910224063e-06, "loss": 0.2862086892127991, "step": 3525 }, { "epoch": 0.9153686396677051, "grad_norm": 9.80271053314209, "learning_rate": 3.1666632805651564e-06, "loss": 0.22898593544960022, "step": 3526 }, { "epoch": 0.9156282450674974, "grad_norm": 10.370051383972168, "learning_rate": 3.165733596451379e-06, "loss": 0.31665825843811035, "step": 3527 }, { "epoch": 0.9158878504672897, "grad_norm": 6.719732284545898, "learning_rate": 3.164803838845421e-06, "loss": 0.28137099742889404, "step": 3528 }, { "epoch": 0.916147455867082, "grad_norm": 4.280319690704346, "learning_rate": 3.1638740079116427e-06, "loss": 0.30199360847473145, "step": 3529 }, { "epoch": 0.9164070612668743, "grad_norm": 5.516193866729736, "learning_rate": 3.1629441038144152e-06, "loss": 0.279080331325531, "step": 3530 }, { "epoch": 0.9166666666666666, "grad_norm": 9.2513427734375, "learning_rate": 3.1620141267181253e-06, "loss": 0.24574828147888184, "step": 3531 }, { "epoch": 0.9169262720664589, "grad_norm": 10.080924987792969, "learning_rate": 3.1610840767871726e-06, "loss": 0.17210012674331665, "step": 3532 }, { "epoch": 0.9171858774662512, "grad_norm": 4.884981632232666, "learning_rate": 3.160153954185967e-06, "loss": 0.2645752727985382, "step": 3533 }, { "epoch": 0.9174454828660437, "grad_norm": 4.779505729675293, "learning_rate": 3.159223759078934e-06, "loss": 0.279518187046051, "step": 3534 }, { "epoch": 0.917705088265836, "grad_norm": 5.531493186950684, "learning_rate": 3.15829349163051e-06, "loss": 0.102800652384758, "step": 3535 }, { "epoch": 0.9179646936656283, "grad_norm": 8.448500633239746, "learning_rate": 3.157363152005145e-06, "loss": 0.27547383308410645, "step": 3536 }, { "epoch": 0.9182242990654206, "grad_norm": 10.243974685668945, "learning_rate": 3.1564327403673024e-06, "loss": 0.22060325741767883, "step": 3537 }, { "epoch": 0.9184839044652129, "grad_norm": 13.87173080444336, "learning_rate": 3.155502256881458e-06, "loss": 0.1892702430486679, "step": 3538 }, { "epoch": 0.9187435098650052, "grad_norm": 3.677833318710327, "learning_rate": 3.1545717017120993e-06, "loss": 0.2762494683265686, "step": 3539 }, { "epoch": 0.9190031152647975, "grad_norm": 8.854002952575684, "learning_rate": 3.153641075023726e-06, "loss": 0.2083471417427063, "step": 3540 }, { "epoch": 0.9192627206645898, "grad_norm": 9.949603080749512, "learning_rate": 3.152710376980854e-06, "loss": 0.16541428864002228, "step": 3541 }, { "epoch": 0.9195223260643821, "grad_norm": 5.6595282554626465, "learning_rate": 3.151779607748008e-06, "loss": 0.2796385884284973, "step": 3542 }, { "epoch": 0.9197819314641744, "grad_norm": 6.29209566116333, "learning_rate": 3.150848767489726e-06, "loss": 0.299285888671875, "step": 3543 }, { "epoch": 0.9200415368639667, "grad_norm": 4.220917224884033, "learning_rate": 3.1499178563705605e-06, "loss": 0.2859577536582947, "step": 3544 }, { "epoch": 0.920301142263759, "grad_norm": 8.442255973815918, "learning_rate": 3.1489868745550754e-06, "loss": 0.2382063865661621, "step": 3545 }, { "epoch": 0.9205607476635514, "grad_norm": 4.429839611053467, "learning_rate": 3.1480558222078467e-06, "loss": 0.32120922207832336, "step": 3546 }, { "epoch": 0.9208203530633438, "grad_norm": 4.876543045043945, "learning_rate": 3.147124699493462e-06, "loss": 0.2976258397102356, "step": 3547 }, { "epoch": 0.9210799584631361, "grad_norm": 3.704044818878174, "learning_rate": 3.146193506576524e-06, "loss": 0.28423142433166504, "step": 3548 }, { "epoch": 0.9213395638629284, "grad_norm": 8.683226585388184, "learning_rate": 3.1452622436216452e-06, "loss": 0.20908480882644653, "step": 3549 }, { "epoch": 0.9215991692627207, "grad_norm": 3.9152939319610596, "learning_rate": 3.144330910793453e-06, "loss": 0.3224262297153473, "step": 3550 }, { "epoch": 0.921858774662513, "grad_norm": 7.669101715087891, "learning_rate": 3.143399508256584e-06, "loss": 0.14257720112800598, "step": 3551 }, { "epoch": 0.9221183800623053, "grad_norm": 5.871343612670898, "learning_rate": 3.14246803617569e-06, "loss": 0.24146701395511627, "step": 3552 }, { "epoch": 0.9223779854620976, "grad_norm": 4.256019115447998, "learning_rate": 3.1415364947154323e-06, "loss": 0.3212251663208008, "step": 3553 }, { "epoch": 0.9226375908618899, "grad_norm": 4.8379106521606445, "learning_rate": 3.1406048840404886e-06, "loss": 0.26442334055900574, "step": 3554 }, { "epoch": 0.9228971962616822, "grad_norm": 11.34948444366455, "learning_rate": 3.1396732043155447e-06, "loss": 0.07654723525047302, "step": 3555 }, { "epoch": 0.9231568016614745, "grad_norm": 8.66637897491455, "learning_rate": 3.1387414557053013e-06, "loss": 0.16251471638679504, "step": 3556 }, { "epoch": 0.9234164070612668, "grad_norm": 3.6743345260620117, "learning_rate": 3.1378096383744685e-06, "loss": 0.3053237795829773, "step": 3557 }, { "epoch": 0.9236760124610592, "grad_norm": 10.105040550231934, "learning_rate": 3.1368777524877713e-06, "loss": 0.23043055832386017, "step": 3558 }, { "epoch": 0.9239356178608515, "grad_norm": 7.138199806213379, "learning_rate": 3.1359457982099467e-06, "loss": 0.3043307662010193, "step": 3559 }, { "epoch": 0.9241952232606438, "grad_norm": 7.523801803588867, "learning_rate": 3.1350137757057412e-06, "loss": 0.22233596444129944, "step": 3560 }, { "epoch": 0.9244548286604362, "grad_norm": 4.125363349914551, "learning_rate": 3.1340816851399164e-06, "loss": 0.28080517053604126, "step": 3561 }, { "epoch": 0.9247144340602285, "grad_norm": 7.214553356170654, "learning_rate": 3.133149526677243e-06, "loss": 0.28515493869781494, "step": 3562 }, { "epoch": 0.9249740394600208, "grad_norm": 4.336915016174316, "learning_rate": 3.1322173004825076e-06, "loss": 0.3096123933792114, "step": 3563 }, { "epoch": 0.9252336448598131, "grad_norm": 11.948875427246094, "learning_rate": 3.1312850067205036e-06, "loss": 0.2650265097618103, "step": 3564 }, { "epoch": 0.9254932502596054, "grad_norm": 8.468931198120117, "learning_rate": 3.130352645556042e-06, "loss": 0.14358192682266235, "step": 3565 }, { "epoch": 0.9257528556593977, "grad_norm": 4.466760635375977, "learning_rate": 3.1294202171539406e-06, "loss": 0.23952728509902954, "step": 3566 }, { "epoch": 0.92601246105919, "grad_norm": 4.376438617706299, "learning_rate": 3.128487721679033e-06, "loss": 0.30801576375961304, "step": 3567 }, { "epoch": 0.9262720664589823, "grad_norm": 5.005276679992676, "learning_rate": 3.1275551592961617e-06, "loss": 0.22391323745250702, "step": 3568 }, { "epoch": 0.9265316718587746, "grad_norm": 6.335533618927002, "learning_rate": 3.1266225301701842e-06, "loss": 0.24313947558403015, "step": 3569 }, { "epoch": 0.926791277258567, "grad_norm": 17.277284622192383, "learning_rate": 3.1256898344659657e-06, "loss": 0.19432154297828674, "step": 3570 }, { "epoch": 0.9270508826583593, "grad_norm": 9.8506441116333, "learning_rate": 3.124757072348388e-06, "loss": 0.17962010204792023, "step": 3571 }, { "epoch": 0.9273104880581516, "grad_norm": 5.208240032196045, "learning_rate": 3.1238242439823393e-06, "loss": 0.297655314207077, "step": 3572 }, { "epoch": 0.927570093457944, "grad_norm": 9.246395111083984, "learning_rate": 3.1228913495327245e-06, "loss": 0.21343374252319336, "step": 3573 }, { "epoch": 0.9278296988577363, "grad_norm": 9.397062301635742, "learning_rate": 3.1219583891644574e-06, "loss": 0.16973236203193665, "step": 3574 }, { "epoch": 0.9280893042575286, "grad_norm": 6.636998176574707, "learning_rate": 3.121025363042463e-06, "loss": 0.23027366399765015, "step": 3575 }, { "epoch": 0.9283489096573209, "grad_norm": 12.375298500061035, "learning_rate": 3.12009227133168e-06, "loss": 0.24490803480148315, "step": 3576 }, { "epoch": 0.9286085150571132, "grad_norm": 14.403554916381836, "learning_rate": 3.119159114197058e-06, "loss": 0.1511515974998474, "step": 3577 }, { "epoch": 0.9288681204569055, "grad_norm": 12.247858047485352, "learning_rate": 3.118225891803556e-06, "loss": 0.20492017269134521, "step": 3578 }, { "epoch": 0.9291277258566978, "grad_norm": 6.360783100128174, "learning_rate": 3.1172926043161496e-06, "loss": 0.2531173527240753, "step": 3579 }, { "epoch": 0.9293873312564901, "grad_norm": 10.705222129821777, "learning_rate": 3.116359251899819e-06, "loss": 0.20945489406585693, "step": 3580 }, { "epoch": 0.9296469366562824, "grad_norm": 4.711102485656738, "learning_rate": 3.1154258347195614e-06, "loss": 0.31362879276275635, "step": 3581 }, { "epoch": 0.9299065420560748, "grad_norm": 5.592545509338379, "learning_rate": 3.114492352940384e-06, "loss": 0.3005051612854004, "step": 3582 }, { "epoch": 0.9301661474558671, "grad_norm": 11.456665992736816, "learning_rate": 3.1135588067273044e-06, "loss": 0.22887447476387024, "step": 3583 }, { "epoch": 0.9304257528556594, "grad_norm": 7.043931007385254, "learning_rate": 3.1126251962453507e-06, "loss": 0.23108667135238647, "step": 3584 }, { "epoch": 0.9306853582554517, "grad_norm": 6.820188045501709, "learning_rate": 3.111691521659567e-06, "loss": 0.24894922971725464, "step": 3585 }, { "epoch": 0.930944963655244, "grad_norm": 4.480920791625977, "learning_rate": 3.1107577831350033e-06, "loss": 0.2915078401565552, "step": 3586 }, { "epoch": 0.9312045690550363, "grad_norm": 10.988861083984375, "learning_rate": 3.1098239808367237e-06, "loss": 0.15895496308803558, "step": 3587 }, { "epoch": 0.9314641744548287, "grad_norm": 10.75917911529541, "learning_rate": 3.108890114929803e-06, "loss": 0.18750445544719696, "step": 3588 }, { "epoch": 0.931723779854621, "grad_norm": 12.058982849121094, "learning_rate": 3.1079561855793277e-06, "loss": 0.31171831488609314, "step": 3589 }, { "epoch": 0.9319833852544133, "grad_norm": 11.548986434936523, "learning_rate": 3.107022192950395e-06, "loss": 0.07267981022596359, "step": 3590 }, { "epoch": 0.9322429906542056, "grad_norm": 6.573730945587158, "learning_rate": 3.106088137208113e-06, "loss": 0.2315140813589096, "step": 3591 }, { "epoch": 0.9325025960539979, "grad_norm": 9.734476089477539, "learning_rate": 3.105154018517602e-06, "loss": 0.2458646297454834, "step": 3592 }, { "epoch": 0.9327622014537902, "grad_norm": 9.475369453430176, "learning_rate": 3.1042198370439925e-06, "loss": 0.23813778162002563, "step": 3593 }, { "epoch": 0.9330218068535826, "grad_norm": 4.751571178436279, "learning_rate": 3.103285592952427e-06, "loss": 0.3040526807308197, "step": 3594 }, { "epoch": 0.9332814122533749, "grad_norm": 6.42440938949585, "learning_rate": 3.1023512864080563e-06, "loss": 0.20899565517902374, "step": 3595 }, { "epoch": 0.9335410176531672, "grad_norm": 8.164837837219238, "learning_rate": 3.101416917576047e-06, "loss": 0.20449483394622803, "step": 3596 }, { "epoch": 0.9338006230529595, "grad_norm": 4.076730251312256, "learning_rate": 3.1004824866215723e-06, "loss": 0.296752393245697, "step": 3597 }, { "epoch": 0.9340602284527518, "grad_norm": 6.622762203216553, "learning_rate": 3.09954799370982e-06, "loss": 0.20939810574054718, "step": 3598 }, { "epoch": 0.9343198338525441, "grad_norm": 10.608572006225586, "learning_rate": 3.0986134390059847e-06, "loss": 0.17595475912094116, "step": 3599 }, { "epoch": 0.9345794392523364, "grad_norm": 4.767247676849365, "learning_rate": 3.0976788226752767e-06, "loss": 0.2933827042579651, "step": 3600 }, { "epoch": 0.9348390446521287, "grad_norm": 5.563418865203857, "learning_rate": 3.0967441448829132e-06, "loss": 0.30681633949279785, "step": 3601 }, { "epoch": 0.935098650051921, "grad_norm": 6.756685256958008, "learning_rate": 3.0958094057941245e-06, "loss": 0.26349687576293945, "step": 3602 }, { "epoch": 0.9353582554517134, "grad_norm": 3.840869903564453, "learning_rate": 3.09487460557415e-06, "loss": 0.2703828811645508, "step": 3603 }, { "epoch": 0.9356178608515057, "grad_norm": 10.682204246520996, "learning_rate": 3.093939744388243e-06, "loss": 0.16989544034004211, "step": 3604 }, { "epoch": 0.935877466251298, "grad_norm": 9.86925220489502, "learning_rate": 3.093004822401664e-06, "loss": 0.1806529015302658, "step": 3605 }, { "epoch": 0.9361370716510904, "grad_norm": 5.3454999923706055, "learning_rate": 3.092069839779686e-06, "loss": 0.21974629163742065, "step": 3606 }, { "epoch": 0.9363966770508827, "grad_norm": 8.788046836853027, "learning_rate": 3.0911347966875925e-06, "loss": 0.19068771600723267, "step": 3607 }, { "epoch": 0.936656282450675, "grad_norm": 10.970766067504883, "learning_rate": 3.090199693290678e-06, "loss": 0.14845958352088928, "step": 3608 }, { "epoch": 0.9369158878504673, "grad_norm": 12.912609100341797, "learning_rate": 3.0892645297542475e-06, "loss": 0.18506474792957306, "step": 3609 }, { "epoch": 0.9371754932502596, "grad_norm": 4.928340911865234, "learning_rate": 3.088329306243616e-06, "loss": 0.2625715136528015, "step": 3610 }, { "epoch": 0.9374350986500519, "grad_norm": 8.049798011779785, "learning_rate": 3.0873940229241095e-06, "loss": 0.22819820046424866, "step": 3611 }, { "epoch": 0.9376947040498442, "grad_norm": 7.380481243133545, "learning_rate": 3.086458679961066e-06, "loss": 0.07208865135908127, "step": 3612 }, { "epoch": 0.9379543094496365, "grad_norm": 11.502976417541504, "learning_rate": 3.0855232775198317e-06, "loss": 0.13503918051719666, "step": 3613 }, { "epoch": 0.9382139148494288, "grad_norm": 9.03268051147461, "learning_rate": 3.084587815765764e-06, "loss": 0.19793370366096497, "step": 3614 }, { "epoch": 0.9384735202492211, "grad_norm": 11.41735553741455, "learning_rate": 3.0836522948642317e-06, "loss": 0.23313359916210175, "step": 3615 }, { "epoch": 0.9387331256490135, "grad_norm": 6.800013065338135, "learning_rate": 3.0827167149806126e-06, "loss": 0.2619245648384094, "step": 3616 }, { "epoch": 0.9389927310488058, "grad_norm": 5.428073883056641, "learning_rate": 3.0817810762802974e-06, "loss": 0.27094435691833496, "step": 3617 }, { "epoch": 0.9392523364485982, "grad_norm": 4.339400768280029, "learning_rate": 3.0808453789286842e-06, "loss": 0.3400565981864929, "step": 3618 }, { "epoch": 0.9395119418483905, "grad_norm": 6.6809186935424805, "learning_rate": 3.079909623091183e-06, "loss": 0.22195377945899963, "step": 3619 }, { "epoch": 0.9397715472481828, "grad_norm": 11.288467407226562, "learning_rate": 3.078973808933215e-06, "loss": 0.19837340712547302, "step": 3620 }, { "epoch": 0.9400311526479751, "grad_norm": 8.7908353805542, "learning_rate": 3.0780379366202106e-06, "loss": 0.1427241861820221, "step": 3621 }, { "epoch": 0.9402907580477674, "grad_norm": 11.284749031066895, "learning_rate": 3.077102006317609e-06, "loss": 0.16535070538520813, "step": 3622 }, { "epoch": 0.9405503634475597, "grad_norm": 10.265092849731445, "learning_rate": 3.0761660181908624e-06, "loss": 0.2570734918117523, "step": 3623 }, { "epoch": 0.940809968847352, "grad_norm": 9.346059799194336, "learning_rate": 3.0752299724054324e-06, "loss": 0.15669742226600647, "step": 3624 }, { "epoch": 0.9410695742471443, "grad_norm": 7.884377956390381, "learning_rate": 3.0742938691267903e-06, "loss": 0.23066021502017975, "step": 3625 }, { "epoch": 0.9413291796469366, "grad_norm": 13.049266815185547, "learning_rate": 3.073357708520417e-06, "loss": 0.15494868159294128, "step": 3626 }, { "epoch": 0.9415887850467289, "grad_norm": 4.685370922088623, "learning_rate": 3.072421490751805e-06, "loss": 0.2505648136138916, "step": 3627 }, { "epoch": 0.9418483904465212, "grad_norm": 5.597980499267578, "learning_rate": 3.071485215986455e-06, "loss": 0.1865769624710083, "step": 3628 }, { "epoch": 0.9421079958463136, "grad_norm": 10.278467178344727, "learning_rate": 3.0705488843898816e-06, "loss": 0.19406038522720337, "step": 3629 }, { "epoch": 0.942367601246106, "grad_norm": 8.20650577545166, "learning_rate": 3.0696124961276036e-06, "loss": 0.20266783237457275, "step": 3630 }, { "epoch": 0.9426272066458983, "grad_norm": 10.965921401977539, "learning_rate": 3.0686760513651555e-06, "loss": 0.1630948781967163, "step": 3631 }, { "epoch": 0.9428868120456906, "grad_norm": 9.321255683898926, "learning_rate": 3.0677395502680774e-06, "loss": 0.131175696849823, "step": 3632 }, { "epoch": 0.9431464174454829, "grad_norm": 5.49222469329834, "learning_rate": 3.066802993001922e-06, "loss": 0.2182525247335434, "step": 3633 }, { "epoch": 0.9434060228452752, "grad_norm": 9.87180233001709, "learning_rate": 3.0658663797322518e-06, "loss": 0.31294459104537964, "step": 3634 }, { "epoch": 0.9436656282450675, "grad_norm": 8.816058158874512, "learning_rate": 3.0649297106246386e-06, "loss": 0.28987929224967957, "step": 3635 }, { "epoch": 0.9439252336448598, "grad_norm": 5.570260524749756, "learning_rate": 3.0639929858446626e-06, "loss": 0.23383811116218567, "step": 3636 }, { "epoch": 0.9441848390446521, "grad_norm": 4.809844970703125, "learning_rate": 3.0630562055579154e-06, "loss": 0.2725878953933716, "step": 3637 }, { "epoch": 0.9444444444444444, "grad_norm": 5.134171962738037, "learning_rate": 3.0621193699300004e-06, "loss": 0.2774175703525543, "step": 3638 }, { "epoch": 0.9447040498442367, "grad_norm": 6.522680759429932, "learning_rate": 3.0611824791265278e-06, "loss": 0.25364163517951965, "step": 3639 }, { "epoch": 0.944963655244029, "grad_norm": 8.786758422851562, "learning_rate": 3.060245533313117e-06, "loss": 0.2903404235839844, "step": 3640 }, { "epoch": 0.9452232606438213, "grad_norm": 9.700764656066895, "learning_rate": 3.0593085326553995e-06, "loss": 0.21248719096183777, "step": 3641 }, { "epoch": 0.9454828660436138, "grad_norm": 4.492027282714844, "learning_rate": 3.058371477319016e-06, "loss": 0.2797645330429077, "step": 3642 }, { "epoch": 0.9457424714434061, "grad_norm": 9.933292388916016, "learning_rate": 3.0574343674696162e-06, "loss": 0.17987576127052307, "step": 3643 }, { "epoch": 0.9460020768431984, "grad_norm": 10.221786499023438, "learning_rate": 3.05649720327286e-06, "loss": 0.15991047024726868, "step": 3644 }, { "epoch": 0.9462616822429907, "grad_norm": 5.807979106903076, "learning_rate": 3.0555599848944152e-06, "loss": 0.3533617854118347, "step": 3645 }, { "epoch": 0.946521287642783, "grad_norm": 7.300417900085449, "learning_rate": 3.054622712499962e-06, "loss": 0.2654688060283661, "step": 3646 }, { "epoch": 0.9467808930425753, "grad_norm": 6.550504684448242, "learning_rate": 3.0536853862551875e-06, "loss": 0.26675695180892944, "step": 3647 }, { "epoch": 0.9470404984423676, "grad_norm": 8.896138191223145, "learning_rate": 3.0527480063257908e-06, "loss": 0.16034191846847534, "step": 3648 }, { "epoch": 0.9473001038421599, "grad_norm": 6.18784761428833, "learning_rate": 3.0518105728774782e-06, "loss": 0.24609486758708954, "step": 3649 }, { "epoch": 0.9475597092419522, "grad_norm": 11.621676445007324, "learning_rate": 3.0508730860759673e-06, "loss": 0.15389898419380188, "step": 3650 }, { "epoch": 0.9478193146417445, "grad_norm": 5.910560131072998, "learning_rate": 3.0499355460869833e-06, "loss": 0.2522350549697876, "step": 3651 }, { "epoch": 0.9480789200415368, "grad_norm": 11.987192153930664, "learning_rate": 3.048997953076263e-06, "loss": 0.13039185106754303, "step": 3652 }, { "epoch": 0.9483385254413291, "grad_norm": 11.484315872192383, "learning_rate": 3.0480603072095507e-06, "loss": 0.16356179118156433, "step": 3653 }, { "epoch": 0.9485981308411215, "grad_norm": 5.183291435241699, "learning_rate": 3.0471226086526e-06, "loss": 0.269452840089798, "step": 3654 }, { "epoch": 0.9488577362409139, "grad_norm": 13.01155948638916, "learning_rate": 3.046184857571176e-06, "loss": 0.1306058019399643, "step": 3655 }, { "epoch": 0.9491173416407062, "grad_norm": 3.8723480701446533, "learning_rate": 3.0452470541310507e-06, "loss": 0.26257479190826416, "step": 3656 }, { "epoch": 0.9493769470404985, "grad_norm": 11.038515090942383, "learning_rate": 3.0443091984980066e-06, "loss": 0.14872881770133972, "step": 3657 }, { "epoch": 0.9496365524402908, "grad_norm": 7.7423505783081055, "learning_rate": 3.0433712908378356e-06, "loss": 0.22401857376098633, "step": 3658 }, { "epoch": 0.9498961578400831, "grad_norm": 8.785325050354004, "learning_rate": 3.042433331316336e-06, "loss": 0.17215202748775482, "step": 3659 }, { "epoch": 0.9501557632398754, "grad_norm": 8.344087600708008, "learning_rate": 3.04149532009932e-06, "loss": 0.25014033913612366, "step": 3660 }, { "epoch": 0.9504153686396677, "grad_norm": 11.688936233520508, "learning_rate": 3.0405572573526067e-06, "loss": 0.15463969111442566, "step": 3661 }, { "epoch": 0.95067497403946, "grad_norm": 11.261341094970703, "learning_rate": 3.0396191432420225e-06, "loss": 0.19192197918891907, "step": 3662 }, { "epoch": 0.9509345794392523, "grad_norm": 5.784806251525879, "learning_rate": 3.0386809779334055e-06, "loss": 0.24760393798351288, "step": 3663 }, { "epoch": 0.9511941848390446, "grad_norm": 5.120484828948975, "learning_rate": 3.037742761592601e-06, "loss": 0.24572795629501343, "step": 3664 }, { "epoch": 0.9514537902388369, "grad_norm": 10.228177070617676, "learning_rate": 3.0368044943854647e-06, "loss": 0.17057037353515625, "step": 3665 }, { "epoch": 0.9517133956386293, "grad_norm": 10.106581687927246, "learning_rate": 3.0358661764778614e-06, "loss": 0.2740774154663086, "step": 3666 }, { "epoch": 0.9519730010384216, "grad_norm": 6.162112236022949, "learning_rate": 3.0349278080356626e-06, "loss": 0.26313966512680054, "step": 3667 }, { "epoch": 0.952232606438214, "grad_norm": 8.499832153320312, "learning_rate": 3.0339893892247518e-06, "loss": 0.13740548491477966, "step": 3668 }, { "epoch": 0.9524922118380063, "grad_norm": 6.080557823181152, "learning_rate": 3.0330509202110197e-06, "loss": 0.24721869826316833, "step": 3669 }, { "epoch": 0.9527518172377986, "grad_norm": 5.441014289855957, "learning_rate": 3.032112401160366e-06, "loss": 0.23990218341350555, "step": 3670 }, { "epoch": 0.9530114226375909, "grad_norm": 11.029245376586914, "learning_rate": 3.0311738322386996e-06, "loss": 0.17379921674728394, "step": 3671 }, { "epoch": 0.9532710280373832, "grad_norm": 4.253463268280029, "learning_rate": 3.0302352136119364e-06, "loss": 0.34147724509239197, "step": 3672 }, { "epoch": 0.9535306334371755, "grad_norm": 7.407337188720703, "learning_rate": 3.029296545446005e-06, "loss": 0.20519688725471497, "step": 3673 }, { "epoch": 0.9537902388369678, "grad_norm": 7.767226219177246, "learning_rate": 3.0283578279068387e-06, "loss": 0.16390830278396606, "step": 3674 }, { "epoch": 0.9540498442367601, "grad_norm": 11.9354887008667, "learning_rate": 3.027419061160383e-06, "loss": 0.27701807022094727, "step": 3675 }, { "epoch": 0.9543094496365524, "grad_norm": 9.870038032531738, "learning_rate": 3.026480245372588e-06, "loss": 0.19378791749477386, "step": 3676 }, { "epoch": 0.9545690550363447, "grad_norm": 10.645282745361328, "learning_rate": 3.025541380709417e-06, "loss": 0.1947043538093567, "step": 3677 }, { "epoch": 0.9548286604361371, "grad_norm": 11.285296440124512, "learning_rate": 3.024602467336839e-06, "loss": 0.233451709151268, "step": 3678 }, { "epoch": 0.9550882658359294, "grad_norm": 6.443441867828369, "learning_rate": 3.0236635054208322e-06, "loss": 0.2827409505844116, "step": 3679 }, { "epoch": 0.9553478712357217, "grad_norm": 17.202363967895508, "learning_rate": 3.022724495127384e-06, "loss": 0.21658357977867126, "step": 3680 }, { "epoch": 0.955607476635514, "grad_norm": 5.423928737640381, "learning_rate": 3.0217854366224885e-06, "loss": 0.31522536277770996, "step": 3681 }, { "epoch": 0.9558670820353063, "grad_norm": 8.04231071472168, "learning_rate": 3.020846330072152e-06, "loss": 0.16267088055610657, "step": 3682 }, { "epoch": 0.9561266874350987, "grad_norm": 9.964634895324707, "learning_rate": 3.019907175642386e-06, "loss": 0.17595526576042175, "step": 3683 }, { "epoch": 0.956386292834891, "grad_norm": 12.409706115722656, "learning_rate": 3.0189679734992107e-06, "loss": 0.13807392120361328, "step": 3684 }, { "epoch": 0.9566458982346833, "grad_norm": 12.596209526062012, "learning_rate": 3.0180287238086563e-06, "loss": 0.19507266581058502, "step": 3685 }, { "epoch": 0.9569055036344756, "grad_norm": 4.470636367797852, "learning_rate": 3.0170894267367605e-06, "loss": 0.2835842967033386, "step": 3686 }, { "epoch": 0.9571651090342679, "grad_norm": 15.93712043762207, "learning_rate": 3.0161500824495704e-06, "loss": 0.20040594041347504, "step": 3687 }, { "epoch": 0.9574247144340602, "grad_norm": 9.794492721557617, "learning_rate": 3.015210691113139e-06, "loss": 0.11209899187088013, "step": 3688 }, { "epoch": 0.9576843198338525, "grad_norm": 4.258941173553467, "learning_rate": 3.014271252893531e-06, "loss": 0.27787819504737854, "step": 3689 }, { "epoch": 0.9579439252336449, "grad_norm": 10.099874496459961, "learning_rate": 3.0133317679568145e-06, "loss": 0.14953696727752686, "step": 3690 }, { "epoch": 0.9582035306334372, "grad_norm": 5.855003356933594, "learning_rate": 3.012392236469073e-06, "loss": 0.24908708035945892, "step": 3691 }, { "epoch": 0.9584631360332295, "grad_norm": 5.303343772888184, "learning_rate": 3.0114526585963903e-06, "loss": 0.24783757328987122, "step": 3692 }, { "epoch": 0.9587227414330218, "grad_norm": 6.312981128692627, "learning_rate": 3.0105130345048654e-06, "loss": 0.24348017573356628, "step": 3693 }, { "epoch": 0.9589823468328141, "grad_norm": 5.278454303741455, "learning_rate": 3.0095733643606005e-06, "loss": 0.2557886838912964, "step": 3694 }, { "epoch": 0.9592419522326064, "grad_norm": 7.867007732391357, "learning_rate": 3.0086336483297084e-06, "loss": 0.24043816328048706, "step": 3695 }, { "epoch": 0.9595015576323987, "grad_norm": 5.0454511642456055, "learning_rate": 3.007693886578309e-06, "loss": 0.2696075141429901, "step": 3696 }, { "epoch": 0.9597611630321911, "grad_norm": 10.760536193847656, "learning_rate": 3.0067540792725304e-06, "loss": 0.3005066215991974, "step": 3697 }, { "epoch": 0.9600207684319834, "grad_norm": 16.13152313232422, "learning_rate": 3.00581422657851e-06, "loss": 0.21184295415878296, "step": 3698 }, { "epoch": 0.9602803738317757, "grad_norm": 4.332623481750488, "learning_rate": 3.004874328662391e-06, "loss": 0.3282231390476227, "step": 3699 }, { "epoch": 0.960539979231568, "grad_norm": 11.436190605163574, "learning_rate": 3.003934385690328e-06, "loss": 0.11401734501123428, "step": 3700 }, { "epoch": 0.9607995846313603, "grad_norm": 15.031472206115723, "learning_rate": 3.002994397828479e-06, "loss": 0.16049934923648834, "step": 3701 }, { "epoch": 0.9610591900311527, "grad_norm": 11.727775573730469, "learning_rate": 3.002054365243014e-06, "loss": 0.10582850873470306, "step": 3702 }, { "epoch": 0.961318795430945, "grad_norm": 6.470372200012207, "learning_rate": 3.001114288100107e-06, "loss": 0.2495412677526474, "step": 3703 }, { "epoch": 0.9615784008307373, "grad_norm": 10.977858543395996, "learning_rate": 3.0001741665659444e-06, "loss": 0.10086789727210999, "step": 3704 }, { "epoch": 0.9618380062305296, "grad_norm": 6.957880020141602, "learning_rate": 2.9992340008067177e-06, "loss": 0.2181338518857956, "step": 3705 }, { "epoch": 0.9620976116303219, "grad_norm": 6.406105995178223, "learning_rate": 2.9982937909886267e-06, "loss": 0.23413792252540588, "step": 3706 }, { "epoch": 0.9623572170301142, "grad_norm": 8.981218338012695, "learning_rate": 2.997353537277878e-06, "loss": 0.20873211324214935, "step": 3707 }, { "epoch": 0.9626168224299065, "grad_norm": 8.668356895446777, "learning_rate": 2.996413239840687e-06, "loss": 0.25928306579589844, "step": 3708 }, { "epoch": 0.9628764278296988, "grad_norm": 5.158022403717041, "learning_rate": 2.995472898843278e-06, "loss": 0.23330378532409668, "step": 3709 }, { "epoch": 0.9631360332294912, "grad_norm": 9.572197914123535, "learning_rate": 2.994532514451881e-06, "loss": 0.1944384127855301, "step": 3710 }, { "epoch": 0.9633956386292835, "grad_norm": 10.662858009338379, "learning_rate": 2.9935920868327345e-06, "loss": 0.16669121384620667, "step": 3711 }, { "epoch": 0.9636552440290758, "grad_norm": 9.213414192199707, "learning_rate": 2.9926516161520848e-06, "loss": 0.22321225702762604, "step": 3712 }, { "epoch": 0.9639148494288681, "grad_norm": 6.836361885070801, "learning_rate": 2.9917111025761848e-06, "loss": 0.26806801557540894, "step": 3713 }, { "epoch": 0.9641744548286605, "grad_norm": 8.030068397521973, "learning_rate": 2.9907705462712974e-06, "loss": 0.1778888702392578, "step": 3714 }, { "epoch": 0.9644340602284528, "grad_norm": 12.897530555725098, "learning_rate": 2.989829947403689e-06, "loss": 0.1761520802974701, "step": 3715 }, { "epoch": 0.9646936656282451, "grad_norm": 5.027004718780518, "learning_rate": 2.9888893061396375e-06, "loss": 0.29086169600486755, "step": 3716 }, { "epoch": 0.9649532710280374, "grad_norm": 10.916984558105469, "learning_rate": 2.987948622645427e-06, "loss": 0.0874091386795044, "step": 3717 }, { "epoch": 0.9652128764278297, "grad_norm": 5.652656078338623, "learning_rate": 2.9870078970873483e-06, "loss": 0.2714027762413025, "step": 3718 }, { "epoch": 0.965472481827622, "grad_norm": 9.571352005004883, "learning_rate": 2.9860671296317e-06, "loss": 0.24238930642604828, "step": 3719 }, { "epoch": 0.9657320872274143, "grad_norm": 6.070323944091797, "learning_rate": 2.985126320444789e-06, "loss": 0.26399052143096924, "step": 3720 }, { "epoch": 0.9659916926272066, "grad_norm": 6.1683549880981445, "learning_rate": 2.9841854696929266e-06, "loss": 0.29488444328308105, "step": 3721 }, { "epoch": 0.9662512980269989, "grad_norm": 9.890985488891602, "learning_rate": 2.983244577542437e-06, "loss": 0.21043115854263306, "step": 3722 }, { "epoch": 0.9665109034267912, "grad_norm": 11.302054405212402, "learning_rate": 2.9823036441596465e-06, "loss": 0.15550807118415833, "step": 3723 }, { "epoch": 0.9667705088265836, "grad_norm": 6.008785724639893, "learning_rate": 2.98136266971089e-06, "loss": 0.2647494673728943, "step": 3724 }, { "epoch": 0.9670301142263759, "grad_norm": 4.78870964050293, "learning_rate": 2.980421654362511e-06, "loss": 0.3444433808326721, "step": 3725 }, { "epoch": 0.9672897196261683, "grad_norm": 10.963919639587402, "learning_rate": 2.97948059828086e-06, "loss": 0.19832725822925568, "step": 3726 }, { "epoch": 0.9675493250259606, "grad_norm": 8.72403335571289, "learning_rate": 2.978539501632293e-06, "loss": 0.15696671605110168, "step": 3727 }, { "epoch": 0.9678089304257529, "grad_norm": 12.430658340454102, "learning_rate": 2.977598364583176e-06, "loss": 0.1509692519903183, "step": 3728 }, { "epoch": 0.9680685358255452, "grad_norm": 8.430091857910156, "learning_rate": 2.9766571872998777e-06, "loss": 0.22230707108974457, "step": 3729 }, { "epoch": 0.9683281412253375, "grad_norm": 9.754386901855469, "learning_rate": 2.9757159699487798e-06, "loss": 0.1734602302312851, "step": 3730 }, { "epoch": 0.9685877466251298, "grad_norm": 10.21606731414795, "learning_rate": 2.9747747126962666e-06, "loss": 0.1560623049736023, "step": 3731 }, { "epoch": 0.9688473520249221, "grad_norm": 4.87509298324585, "learning_rate": 2.9738334157087307e-06, "loss": 0.28681841492652893, "step": 3732 }, { "epoch": 0.9691069574247144, "grad_norm": 10.34645938873291, "learning_rate": 2.9728920791525724e-06, "loss": 0.2367272675037384, "step": 3733 }, { "epoch": 0.9693665628245067, "grad_norm": 10.480927467346191, "learning_rate": 2.971950703194197e-06, "loss": 0.18840578198432922, "step": 3734 }, { "epoch": 0.969626168224299, "grad_norm": 10.005363464355469, "learning_rate": 2.97100928800002e-06, "loss": 0.1288459300994873, "step": 3735 }, { "epoch": 0.9698857736240913, "grad_norm": 11.55861759185791, "learning_rate": 2.9700678337364615e-06, "loss": 0.2503719925880432, "step": 3736 }, { "epoch": 0.9701453790238836, "grad_norm": 12.102690696716309, "learning_rate": 2.9691263405699485e-06, "loss": 0.14968714118003845, "step": 3737 }, { "epoch": 0.9704049844236761, "grad_norm": 11.989184379577637, "learning_rate": 2.968184808666916e-06, "loss": 0.1855681836605072, "step": 3738 }, { "epoch": 0.9706645898234684, "grad_norm": 13.281675338745117, "learning_rate": 2.967243238193805e-06, "loss": 0.2225312888622284, "step": 3739 }, { "epoch": 0.9709241952232607, "grad_norm": 6.477601528167725, "learning_rate": 2.9663016293170632e-06, "loss": 0.2553830146789551, "step": 3740 }, { "epoch": 0.971183800623053, "grad_norm": 9.54687786102295, "learning_rate": 2.965359982203147e-06, "loss": 0.11166491359472275, "step": 3741 }, { "epoch": 0.9714434060228453, "grad_norm": 8.727293014526367, "learning_rate": 2.9644182970185163e-06, "loss": 0.09113666415214539, "step": 3742 }, { "epoch": 0.9717030114226376, "grad_norm": 8.202333450317383, "learning_rate": 2.96347657392964e-06, "loss": 0.10618865489959717, "step": 3743 }, { "epoch": 0.9719626168224299, "grad_norm": 4.745844841003418, "learning_rate": 2.962534813102994e-06, "loss": 0.3745410740375519, "step": 3744 }, { "epoch": 0.9722222222222222, "grad_norm": 6.293569564819336, "learning_rate": 2.9615930147050597e-06, "loss": 0.25567173957824707, "step": 3745 }, { "epoch": 0.9724818276220145, "grad_norm": 7.263551235198975, "learning_rate": 2.9606511789023247e-06, "loss": 0.22556671500205994, "step": 3746 }, { "epoch": 0.9727414330218068, "grad_norm": 10.50696086883545, "learning_rate": 2.9597093058612843e-06, "loss": 0.14602845907211304, "step": 3747 }, { "epoch": 0.9730010384215991, "grad_norm": 9.240972518920898, "learning_rate": 2.958767395748441e-06, "loss": 0.23615726828575134, "step": 3748 }, { "epoch": 0.9732606438213914, "grad_norm": 10.095008850097656, "learning_rate": 2.957825448730302e-06, "loss": 0.26068204641342163, "step": 3749 }, { "epoch": 0.9735202492211839, "grad_norm": 6.254579544067383, "learning_rate": 2.9568834649733825e-06, "loss": 0.2802491784095764, "step": 3750 }, { "epoch": 0.9737798546209762, "grad_norm": 9.839578628540039, "learning_rate": 2.9559414446442024e-06, "loss": 0.15978971123695374, "step": 3751 }, { "epoch": 0.9740394600207685, "grad_norm": 9.902276992797852, "learning_rate": 2.9549993879092912e-06, "loss": 0.1363983005285263, "step": 3752 }, { "epoch": 0.9742990654205608, "grad_norm": 6.250120639801025, "learning_rate": 2.954057294935182e-06, "loss": 0.2235908806324005, "step": 3753 }, { "epoch": 0.9745586708203531, "grad_norm": 8.513172149658203, "learning_rate": 2.9531151658884156e-06, "loss": 0.24038009345531464, "step": 3754 }, { "epoch": 0.9748182762201454, "grad_norm": 10.216094017028809, "learning_rate": 2.9521730009355383e-06, "loss": 0.20978683233261108, "step": 3755 }, { "epoch": 0.9750778816199377, "grad_norm": 8.913166046142578, "learning_rate": 2.951230800243103e-06, "loss": 0.12926775217056274, "step": 3756 }, { "epoch": 0.97533748701973, "grad_norm": 10.25439167022705, "learning_rate": 2.95028856397767e-06, "loss": 0.20288018882274628, "step": 3757 }, { "epoch": 0.9755970924195223, "grad_norm": 12.086013793945312, "learning_rate": 2.9493462923058057e-06, "loss": 0.1142386645078659, "step": 3758 }, { "epoch": 0.9758566978193146, "grad_norm": 8.662626266479492, "learning_rate": 2.948403985394081e-06, "loss": 0.23088331520557404, "step": 3759 }, { "epoch": 0.9761163032191069, "grad_norm": 5.49579381942749, "learning_rate": 2.9474616434090737e-06, "loss": 0.2493303120136261, "step": 3760 }, { "epoch": 0.9763759086188992, "grad_norm": 7.402132511138916, "learning_rate": 2.9465192665173697e-06, "loss": 0.30092382431030273, "step": 3761 }, { "epoch": 0.9766355140186916, "grad_norm": 8.67586612701416, "learning_rate": 2.9455768548855597e-06, "loss": 0.16089408099651337, "step": 3762 }, { "epoch": 0.976895119418484, "grad_norm": 4.7728166580200195, "learning_rate": 2.944634408680239e-06, "loss": 0.307064950466156, "step": 3763 }, { "epoch": 0.9771547248182763, "grad_norm": 4.598294734954834, "learning_rate": 2.9436919280680115e-06, "loss": 0.30419594049453735, "step": 3764 }, { "epoch": 0.9774143302180686, "grad_norm": 4.222977161407471, "learning_rate": 2.942749413215486e-06, "loss": 0.2805023491382599, "step": 3765 }, { "epoch": 0.9776739356178609, "grad_norm": 3.915311336517334, "learning_rate": 2.941806864289279e-06, "loss": 0.29981470108032227, "step": 3766 }, { "epoch": 0.9779335410176532, "grad_norm": 7.917974948883057, "learning_rate": 2.9408642814560082e-06, "loss": 0.20550782978534698, "step": 3767 }, { "epoch": 0.9781931464174455, "grad_norm": 11.569574356079102, "learning_rate": 2.939921664882304e-06, "loss": 0.13557974994182587, "step": 3768 }, { "epoch": 0.9784527518172378, "grad_norm": 12.011281967163086, "learning_rate": 2.9389790147347973e-06, "loss": 0.21371793746948242, "step": 3769 }, { "epoch": 0.9787123572170301, "grad_norm": 8.806812286376953, "learning_rate": 2.9380363311801286e-06, "loss": 0.1186419129371643, "step": 3770 }, { "epoch": 0.9789719626168224, "grad_norm": 10.14174747467041, "learning_rate": 2.9370936143849415e-06, "loss": 0.16028381884098053, "step": 3771 }, { "epoch": 0.9792315680166147, "grad_norm": 7.176693916320801, "learning_rate": 2.9361508645158875e-06, "loss": 0.2709895372390747, "step": 3772 }, { "epoch": 0.979491173416407, "grad_norm": 9.853363037109375, "learning_rate": 2.9352080817396227e-06, "loss": 0.22328993678092957, "step": 3773 }, { "epoch": 0.9797507788161994, "grad_norm": 10.447724342346191, "learning_rate": 2.93426526622281e-06, "loss": 0.12192144244909286, "step": 3774 }, { "epoch": 0.9800103842159917, "grad_norm": 4.840962886810303, "learning_rate": 2.933322418132117e-06, "loss": 0.3279770612716675, "step": 3775 }, { "epoch": 0.980269989615784, "grad_norm": 6.960728645324707, "learning_rate": 2.932379537634218e-06, "loss": 0.14900845289230347, "step": 3776 }, { "epoch": 0.9805295950155763, "grad_norm": 11.075879096984863, "learning_rate": 2.9314366248957927e-06, "loss": 0.2400478571653366, "step": 3777 }, { "epoch": 0.9807892004153687, "grad_norm": 7.854853630065918, "learning_rate": 2.9304936800835264e-06, "loss": 0.17618775367736816, "step": 3778 }, { "epoch": 0.981048805815161, "grad_norm": 9.353255271911621, "learning_rate": 2.9295507033641105e-06, "loss": 0.15014901757240295, "step": 3779 }, { "epoch": 0.9813084112149533, "grad_norm": 5.621870040893555, "learning_rate": 2.9286076949042415e-06, "loss": 0.2877672612667084, "step": 3780 }, { "epoch": 0.9815680166147456, "grad_norm": 6.340579509735107, "learning_rate": 2.9276646548706222e-06, "loss": 0.27691614627838135, "step": 3781 }, { "epoch": 0.9818276220145379, "grad_norm": 4.198318958282471, "learning_rate": 2.9267215834299585e-06, "loss": 0.29676714539527893, "step": 3782 }, { "epoch": 0.9820872274143302, "grad_norm": 9.682854652404785, "learning_rate": 2.9257784807489663e-06, "loss": 0.09567605704069138, "step": 3783 }, { "epoch": 0.9823468328141225, "grad_norm": 12.97933578491211, "learning_rate": 2.924835346994363e-06, "loss": 0.06095872446894646, "step": 3784 }, { "epoch": 0.9826064382139148, "grad_norm": 4.54567813873291, "learning_rate": 2.9238921823328737e-06, "loss": 0.2923450767993927, "step": 3785 }, { "epoch": 0.9828660436137072, "grad_norm": 4.894484519958496, "learning_rate": 2.9229489869312276e-06, "loss": 0.2650509178638458, "step": 3786 }, { "epoch": 0.9831256490134995, "grad_norm": 6.429374694824219, "learning_rate": 2.9220057609561616e-06, "loss": 0.18929752707481384, "step": 3787 }, { "epoch": 0.9833852544132918, "grad_norm": 11.775213241577148, "learning_rate": 2.9210625045744143e-06, "loss": 0.20634232461452484, "step": 3788 }, { "epoch": 0.9836448598130841, "grad_norm": 4.886599540710449, "learning_rate": 2.920119217952735e-06, "loss": 0.28032386302948, "step": 3789 }, { "epoch": 0.9839044652128764, "grad_norm": 11.255704879760742, "learning_rate": 2.9191759012578712e-06, "loss": 0.14234226942062378, "step": 3790 }, { "epoch": 0.9841640706126688, "grad_norm": 4.5372772216796875, "learning_rate": 2.9182325546565822e-06, "loss": 0.2878374755382538, "step": 3791 }, { "epoch": 0.9844236760124611, "grad_norm": 4.9201812744140625, "learning_rate": 2.91728917831563e-06, "loss": 0.2811893820762634, "step": 3792 }, { "epoch": 0.9846832814122534, "grad_norm": 11.597264289855957, "learning_rate": 2.916345772401781e-06, "loss": 0.2251288890838623, "step": 3793 }, { "epoch": 0.9849428868120457, "grad_norm": 4.087741374969482, "learning_rate": 2.9154023370818085e-06, "loss": 0.3419320583343506, "step": 3794 }, { "epoch": 0.985202492211838, "grad_norm": 8.266716003417969, "learning_rate": 2.91445887252249e-06, "loss": 0.20345281064510345, "step": 3795 }, { "epoch": 0.9854620976116303, "grad_norm": 8.839131355285645, "learning_rate": 2.9135153788906084e-06, "loss": 0.27712181210517883, "step": 3796 }, { "epoch": 0.9857217030114226, "grad_norm": 5.880870342254639, "learning_rate": 2.912571856352952e-06, "loss": 0.2618260979652405, "step": 3797 }, { "epoch": 0.985981308411215, "grad_norm": 10.379395484924316, "learning_rate": 2.9116283050763137e-06, "loss": 0.18689750134944916, "step": 3798 }, { "epoch": 0.9862409138110073, "grad_norm": 8.765254020690918, "learning_rate": 2.910684725227492e-06, "loss": 0.2535206377506256, "step": 3799 }, { "epoch": 0.9865005192107996, "grad_norm": 9.05171012878418, "learning_rate": 2.909741116973289e-06, "loss": 0.24152186512947083, "step": 3800 }, { "epoch": 0.9867601246105919, "grad_norm": 9.577414512634277, "learning_rate": 2.908797480480515e-06, "loss": 0.15984028577804565, "step": 3801 }, { "epoch": 0.9870197300103842, "grad_norm": 11.652802467346191, "learning_rate": 2.9078538159159823e-06, "loss": 0.20533643662929535, "step": 3802 }, { "epoch": 0.9872793354101765, "grad_norm": 11.937936782836914, "learning_rate": 2.90691012344651e-06, "loss": 0.09421533346176147, "step": 3803 }, { "epoch": 0.9875389408099688, "grad_norm": 10.898062705993652, "learning_rate": 2.90596640323892e-06, "loss": 0.22766853868961334, "step": 3804 }, { "epoch": 0.9877985462097612, "grad_norm": 7.693100452423096, "learning_rate": 2.905022655460041e-06, "loss": 0.27573278546333313, "step": 3805 }, { "epoch": 0.9880581516095535, "grad_norm": 6.4537129402160645, "learning_rate": 2.9040788802767065e-06, "loss": 0.23595309257507324, "step": 3806 }, { "epoch": 0.9883177570093458, "grad_norm": 5.2674880027771, "learning_rate": 2.903135077855754e-06, "loss": 0.30004122853279114, "step": 3807 }, { "epoch": 0.9885773624091381, "grad_norm": 9.158122062683105, "learning_rate": 2.902191248364025e-06, "loss": 0.18285490572452545, "step": 3808 }, { "epoch": 0.9888369678089304, "grad_norm": 9.036589622497559, "learning_rate": 2.9012473919683686e-06, "loss": 0.27078932523727417, "step": 3809 }, { "epoch": 0.9890965732087228, "grad_norm": 5.326135158538818, "learning_rate": 2.900303508835637e-06, "loss": 0.2936190366744995, "step": 3810 }, { "epoch": 0.9893561786085151, "grad_norm": 7.6599578857421875, "learning_rate": 2.8993595991326854e-06, "loss": 0.11301890760660172, "step": 3811 }, { "epoch": 0.9896157840083074, "grad_norm": 12.395925521850586, "learning_rate": 2.8984156630263777e-06, "loss": 0.14584508538246155, "step": 3812 }, { "epoch": 0.9898753894080997, "grad_norm": 9.138827323913574, "learning_rate": 2.8974717006835785e-06, "loss": 0.22177229821681976, "step": 3813 }, { "epoch": 0.990134994807892, "grad_norm": 9.555604934692383, "learning_rate": 2.8965277122711593e-06, "loss": 0.19902536273002625, "step": 3814 }, { "epoch": 0.9903946002076843, "grad_norm": 8.944612503051758, "learning_rate": 2.895583697955995e-06, "loss": 0.2568112313747406, "step": 3815 }, { "epoch": 0.9906542056074766, "grad_norm": 8.011981964111328, "learning_rate": 2.8946396579049674e-06, "loss": 0.2631479799747467, "step": 3816 }, { "epoch": 0.9909138110072689, "grad_norm": 4.537193775177002, "learning_rate": 2.8936955922849597e-06, "loss": 0.2743368148803711, "step": 3817 }, { "epoch": 0.9911734164070612, "grad_norm": 11.318621635437012, "learning_rate": 2.8927515012628616e-06, "loss": 0.15930971503257751, "step": 3818 }, { "epoch": 0.9914330218068536, "grad_norm": 9.323302268981934, "learning_rate": 2.8918073850055663e-06, "loss": 0.26028236746788025, "step": 3819 }, { "epoch": 0.9916926272066459, "grad_norm": 6.194754123687744, "learning_rate": 2.8908632436799725e-06, "loss": 0.29713577032089233, "step": 3820 }, { "epoch": 0.9919522326064382, "grad_norm": 10.668627738952637, "learning_rate": 2.8899190774529823e-06, "loss": 0.21862593293190002, "step": 3821 }, { "epoch": 0.9922118380062306, "grad_norm": 11.310778617858887, "learning_rate": 2.888974886491503e-06, "loss": 0.22920984029769897, "step": 3822 }, { "epoch": 0.9924714434060229, "grad_norm": 11.199202537536621, "learning_rate": 2.888030670962446e-06, "loss": 0.1468162089586258, "step": 3823 }, { "epoch": 0.9927310488058152, "grad_norm": 10.047301292419434, "learning_rate": 2.8870864310327267e-06, "loss": 0.09388485550880432, "step": 3824 }, { "epoch": 0.9929906542056075, "grad_norm": 4.571155071258545, "learning_rate": 2.886142166869265e-06, "loss": 0.3037688434123993, "step": 3825 }, { "epoch": 0.9932502596053998, "grad_norm": 7.981799602508545, "learning_rate": 2.885197878638986e-06, "loss": 0.21571409702301025, "step": 3826 }, { "epoch": 0.9935098650051921, "grad_norm": 11.04260540008545, "learning_rate": 2.8842535665088177e-06, "loss": 0.10515999794006348, "step": 3827 }, { "epoch": 0.9937694704049844, "grad_norm": 8.312763214111328, "learning_rate": 2.8833092306456934e-06, "loss": 0.19510892033576965, "step": 3828 }, { "epoch": 0.9940290758047767, "grad_norm": 9.438765525817871, "learning_rate": 2.882364871216548e-06, "loss": 0.17171049118041992, "step": 3829 }, { "epoch": 0.994288681204569, "grad_norm": 7.518713474273682, "learning_rate": 2.881420488388325e-06, "loss": 0.2825802266597748, "step": 3830 }, { "epoch": 0.9945482866043613, "grad_norm": 4.250093936920166, "learning_rate": 2.8804760823279687e-06, "loss": 0.2697317600250244, "step": 3831 }, { "epoch": 0.9948078920041536, "grad_norm": 13.178293228149414, "learning_rate": 2.8795316532024287e-06, "loss": 0.16353783011436462, "step": 3832 }, { "epoch": 0.995067497403946, "grad_norm": 8.209425926208496, "learning_rate": 2.878587201178658e-06, "loss": 0.2784464657306671, "step": 3833 }, { "epoch": 0.9953271028037384, "grad_norm": 11.31003189086914, "learning_rate": 2.8776427264236147e-06, "loss": 0.2358868271112442, "step": 3834 }, { "epoch": 0.9955867082035307, "grad_norm": 10.610757827758789, "learning_rate": 2.8766982291042593e-06, "loss": 0.1244606226682663, "step": 3835 }, { "epoch": 0.995846313603323, "grad_norm": 7.340535640716553, "learning_rate": 2.875753709387559e-06, "loss": 0.24599550664424896, "step": 3836 }, { "epoch": 0.9961059190031153, "grad_norm": 11.80549430847168, "learning_rate": 2.8748091674404816e-06, "loss": 0.18470998108386993, "step": 3837 }, { "epoch": 0.9963655244029076, "grad_norm": 9.56045150756836, "learning_rate": 2.8738646034300015e-06, "loss": 0.11060483753681183, "step": 3838 }, { "epoch": 0.9966251298026999, "grad_norm": 12.281148910522461, "learning_rate": 2.8729200175230955e-06, "loss": 0.2583886384963989, "step": 3839 }, { "epoch": 0.9968847352024922, "grad_norm": 12.062981605529785, "learning_rate": 2.8719754098867446e-06, "loss": 0.11645051836967468, "step": 3840 }, { "epoch": 0.9971443406022845, "grad_norm": 7.79757022857666, "learning_rate": 2.8710307806879343e-06, "loss": 0.2068430483341217, "step": 3841 }, { "epoch": 0.9974039460020768, "grad_norm": 13.399577140808105, "learning_rate": 2.870086130093653e-06, "loss": 0.15093840658664703, "step": 3842 }, { "epoch": 0.9976635514018691, "grad_norm": 12.706191062927246, "learning_rate": 2.8691414582708943e-06, "loss": 0.13252824544906616, "step": 3843 }, { "epoch": 0.9979231568016614, "grad_norm": 11.137466430664062, "learning_rate": 2.8681967653866527e-06, "loss": 0.09236478060483932, "step": 3844 }, { "epoch": 0.9981827622014537, "grad_norm": 5.759500503540039, "learning_rate": 2.86725205160793e-06, "loss": 0.292133092880249, "step": 3845 }, { "epoch": 0.9984423676012462, "grad_norm": 11.412322044372559, "learning_rate": 2.8663073171017284e-06, "loss": 0.13242167234420776, "step": 3846 }, { "epoch": 0.9987019730010385, "grad_norm": 13.150253295898438, "learning_rate": 2.865362562035058e-06, "loss": 0.09821434319019318, "step": 3847 }, { "epoch": 0.9989615784008308, "grad_norm": 12.1273775100708, "learning_rate": 2.8644177865749266e-06, "loss": 0.17346079647541046, "step": 3848 }, { "epoch": 0.9992211838006231, "grad_norm": 11.806007385253906, "learning_rate": 2.8634729908883506e-06, "loss": 0.21854951977729797, "step": 3849 }, { "epoch": 0.9994807892004154, "grad_norm": 12.558850288391113, "learning_rate": 2.8625281751423485e-06, "loss": 0.25483283400535583, "step": 3850 }, { "epoch": 0.9997403946002077, "grad_norm": 8.496223449707031, "learning_rate": 2.861583339503941e-06, "loss": 0.19765958189964294, "step": 3851 }, { "epoch": 1.0, "grad_norm": 10.56491756439209, "learning_rate": 2.8606384841401548e-06, "loss": 0.16779427230358124, "step": 3852 }, { "epoch": 1.0002596053997923, "grad_norm": 9.131593704223633, "learning_rate": 2.8596936092180173e-06, "loss": 0.18227162957191467, "step": 3853 }, { "epoch": 1.0005192107995846, "grad_norm": 11.094890594482422, "learning_rate": 2.858748714904561e-06, "loss": 0.084698885679245, "step": 3854 }, { "epoch": 1.000778816199377, "grad_norm": 6.367124557495117, "learning_rate": 2.857803801366823e-06, "loss": 0.2237202525138855, "step": 3855 }, { "epoch": 1.0010384215991692, "grad_norm": 10.548249244689941, "learning_rate": 2.85685886877184e-06, "loss": 0.10333474725484848, "step": 3856 }, { "epoch": 1.0012980269989615, "grad_norm": 12.454694747924805, "learning_rate": 2.8559139172866563e-06, "loss": 0.05939529463648796, "step": 3857 }, { "epoch": 1.0015576323987538, "grad_norm": 8.855060577392578, "learning_rate": 2.854968947078317e-06, "loss": 0.23075321316719055, "step": 3858 }, { "epoch": 1.0018172377985461, "grad_norm": 10.224270820617676, "learning_rate": 2.854023958313872e-06, "loss": 0.2669062614440918, "step": 3859 }, { "epoch": 1.0020768431983385, "grad_norm": 6.746061325073242, "learning_rate": 2.853078951160373e-06, "loss": 0.06292928755283356, "step": 3860 }, { "epoch": 1.0023364485981308, "grad_norm": 6.4634809494018555, "learning_rate": 2.852133925784875e-06, "loss": 0.2256845235824585, "step": 3861 }, { "epoch": 1.002596053997923, "grad_norm": 5.59658145904541, "learning_rate": 2.8511888823544376e-06, "loss": 0.2333119511604309, "step": 3862 }, { "epoch": 1.0028556593977154, "grad_norm": 13.24404239654541, "learning_rate": 2.850243821036123e-06, "loss": 0.08759263157844543, "step": 3863 }, { "epoch": 1.0031152647975077, "grad_norm": 6.6664886474609375, "learning_rate": 2.849298741996996e-06, "loss": 0.22472776472568512, "step": 3864 }, { "epoch": 1.0033748701973002, "grad_norm": 12.101579666137695, "learning_rate": 2.8483536454041245e-06, "loss": 0.06836866587400436, "step": 3865 }, { "epoch": 1.0036344755970925, "grad_norm": 5.835448265075684, "learning_rate": 2.847408531424581e-06, "loss": 0.20343178510665894, "step": 3866 }, { "epoch": 1.0038940809968848, "grad_norm": 10.339234352111816, "learning_rate": 2.8464634002254387e-06, "loss": 0.06763742119073868, "step": 3867 }, { "epoch": 1.0041536863966771, "grad_norm": 10.696160316467285, "learning_rate": 2.8455182519737774e-06, "loss": 0.1465681791305542, "step": 3868 }, { "epoch": 1.0044132917964694, "grad_norm": 10.9283447265625, "learning_rate": 2.844573086836675e-06, "loss": 0.07883960008621216, "step": 3869 }, { "epoch": 1.0046728971962617, "grad_norm": 9.2667236328125, "learning_rate": 2.8436279049812167e-06, "loss": 0.07324650138616562, "step": 3870 }, { "epoch": 1.004932502596054, "grad_norm": 14.827865600585938, "learning_rate": 2.8426827065744887e-06, "loss": 0.10396046936511993, "step": 3871 }, { "epoch": 1.0051921079958464, "grad_norm": 9.726076126098633, "learning_rate": 2.8417374917835804e-06, "loss": 0.14748665690422058, "step": 3872 }, { "epoch": 1.0054517133956387, "grad_norm": 5.477462291717529, "learning_rate": 2.8407922607755843e-06, "loss": 0.2520378828048706, "step": 3873 }, { "epoch": 1.005711318795431, "grad_norm": 7.0738115310668945, "learning_rate": 2.839847013717595e-06, "loss": 0.2352173626422882, "step": 3874 }, { "epoch": 1.0059709241952233, "grad_norm": 10.727563858032227, "learning_rate": 2.838901750776711e-06, "loss": 0.057371851056814194, "step": 3875 }, { "epoch": 1.0062305295950156, "grad_norm": 8.784355163574219, "learning_rate": 2.8379564721200333e-06, "loss": 0.1160987988114357, "step": 3876 }, { "epoch": 1.0064901349948079, "grad_norm": 5.374886512756348, "learning_rate": 2.8370111779146646e-06, "loss": 0.2875728905200958, "step": 3877 }, { "epoch": 1.0067497403946002, "grad_norm": 6.030477046966553, "learning_rate": 2.8360658683277125e-06, "loss": 0.23473264276981354, "step": 3878 }, { "epoch": 1.0070093457943925, "grad_norm": 8.648138046264648, "learning_rate": 2.835120543526285e-06, "loss": 0.11976520717144012, "step": 3879 }, { "epoch": 1.0072689511941848, "grad_norm": 7.361189365386963, "learning_rate": 2.8341752036774945e-06, "loss": 0.059439320117235184, "step": 3880 }, { "epoch": 1.007528556593977, "grad_norm": 9.425065040588379, "learning_rate": 2.8332298489484555e-06, "loss": 0.1346699595451355, "step": 3881 }, { "epoch": 1.0077881619937694, "grad_norm": 7.262305736541748, "learning_rate": 2.832284479506286e-06, "loss": 0.17152997851371765, "step": 3882 }, { "epoch": 1.0080477673935617, "grad_norm": 9.321390151977539, "learning_rate": 2.8313390955181025e-06, "loss": 0.08638046681880951, "step": 3883 }, { "epoch": 1.008307372793354, "grad_norm": 5.388413429260254, "learning_rate": 2.830393697151031e-06, "loss": 0.2925606667995453, "step": 3884 }, { "epoch": 1.0085669781931463, "grad_norm": 7.696650505065918, "learning_rate": 2.8294482845721934e-06, "loss": 0.14621961116790771, "step": 3885 }, { "epoch": 1.0088265835929386, "grad_norm": 7.362964153289795, "learning_rate": 2.828502857948719e-06, "loss": 0.17893970012664795, "step": 3886 }, { "epoch": 1.009086188992731, "grad_norm": 7.592709541320801, "learning_rate": 2.8275574174477372e-06, "loss": 0.14409233629703522, "step": 3887 }, { "epoch": 1.0093457943925233, "grad_norm": 6.194352626800537, "learning_rate": 2.8266119632363786e-06, "loss": 0.21235346794128418, "step": 3888 }, { "epoch": 1.0096053997923158, "grad_norm": 6.863127708435059, "learning_rate": 2.8256664954817805e-06, "loss": 0.23754817247390747, "step": 3889 }, { "epoch": 1.009865005192108, "grad_norm": 5.696978569030762, "learning_rate": 2.8247210143510774e-06, "loss": 0.22513970732688904, "step": 3890 }, { "epoch": 1.0101246105919004, "grad_norm": 12.110529899597168, "learning_rate": 2.8237755200114105e-06, "loss": 0.11454129219055176, "step": 3891 }, { "epoch": 1.0103842159916927, "grad_norm": 11.496358871459961, "learning_rate": 2.82283001262992e-06, "loss": 0.0733570083975792, "step": 3892 }, { "epoch": 1.010643821391485, "grad_norm": 10.003576278686523, "learning_rate": 2.8218844923737517e-06, "loss": 0.15860450267791748, "step": 3893 }, { "epoch": 1.0109034267912773, "grad_norm": 5.63438606262207, "learning_rate": 2.8209389594100507e-06, "loss": 0.2557522654533386, "step": 3894 }, { "epoch": 1.0111630321910696, "grad_norm": 9.568450927734375, "learning_rate": 2.8199934139059664e-06, "loss": 0.14970636367797852, "step": 3895 }, { "epoch": 1.011422637590862, "grad_norm": 10.078989028930664, "learning_rate": 2.8190478560286488e-06, "loss": 0.10125648975372314, "step": 3896 }, { "epoch": 1.0116822429906542, "grad_norm": 12.61839771270752, "learning_rate": 2.818102285945251e-06, "loss": 0.11070495843887329, "step": 3897 }, { "epoch": 1.0119418483904465, "grad_norm": 7.763114929199219, "learning_rate": 2.8171567038229286e-06, "loss": 0.18016275763511658, "step": 3898 }, { "epoch": 1.0122014537902388, "grad_norm": 15.815547943115234, "learning_rate": 2.8162111098288393e-06, "loss": 0.07817542552947998, "step": 3899 }, { "epoch": 1.0124610591900312, "grad_norm": 12.001087188720703, "learning_rate": 2.8152655041301413e-06, "loss": 0.2549169063568115, "step": 3900 }, { "epoch": 1.0127206645898235, "grad_norm": 12.693999290466309, "learning_rate": 2.8143198868939957e-06, "loss": 0.1408892273902893, "step": 3901 }, { "epoch": 1.0129802699896158, "grad_norm": 8.976357460021973, "learning_rate": 2.8133742582875677e-06, "loss": 0.11770831793546677, "step": 3902 }, { "epoch": 1.013239875389408, "grad_norm": 7.466084003448486, "learning_rate": 2.8124286184780224e-06, "loss": 0.07614398747682571, "step": 3903 }, { "epoch": 1.0134994807892004, "grad_norm": 6.246795654296875, "learning_rate": 2.8114829676325263e-06, "loss": 0.21951204538345337, "step": 3904 }, { "epoch": 1.0137590861889927, "grad_norm": 9.242478370666504, "learning_rate": 2.810537305918249e-06, "loss": 0.1537899225950241, "step": 3905 }, { "epoch": 1.014018691588785, "grad_norm": 7.117823123931885, "learning_rate": 2.809591633502362e-06, "loss": 0.07087501138448715, "step": 3906 }, { "epoch": 1.0142782969885773, "grad_norm": 7.457398414611816, "learning_rate": 2.808645950552039e-06, "loss": 0.1670002043247223, "step": 3907 }, { "epoch": 1.0145379023883696, "grad_norm": 13.37109375, "learning_rate": 2.807700257234455e-06, "loss": 0.11654660850763321, "step": 3908 }, { "epoch": 1.014797507788162, "grad_norm": 10.493232727050781, "learning_rate": 2.8067545537167874e-06, "loss": 0.0687958151102066, "step": 3909 }, { "epoch": 1.0150571131879542, "grad_norm": 10.245232582092285, "learning_rate": 2.805808840166212e-06, "loss": 0.1390615999698639, "step": 3910 }, { "epoch": 1.0153167185877465, "grad_norm": 5.415268421173096, "learning_rate": 2.804863116749913e-06, "loss": 0.2545481324195862, "step": 3911 }, { "epoch": 1.0155763239875388, "grad_norm": 6.919051170349121, "learning_rate": 2.8039173836350714e-06, "loss": 0.08838106691837311, "step": 3912 }, { "epoch": 1.0158359293873314, "grad_norm": 5.23144006729126, "learning_rate": 2.80297164098887e-06, "loss": 0.22278445959091187, "step": 3913 }, { "epoch": 1.0160955347871237, "grad_norm": 11.388863563537598, "learning_rate": 2.802025888978496e-06, "loss": 0.11061202734708786, "step": 3914 }, { "epoch": 1.016355140186916, "grad_norm": 8.819975852966309, "learning_rate": 2.801080127771136e-06, "loss": 0.11104556918144226, "step": 3915 }, { "epoch": 1.0166147455867083, "grad_norm": 6.934135437011719, "learning_rate": 2.800134357533979e-06, "loss": 0.03245261311531067, "step": 3916 }, { "epoch": 1.0168743509865006, "grad_norm": 6.713171482086182, "learning_rate": 2.7991885784342154e-06, "loss": 0.05350356549024582, "step": 3917 }, { "epoch": 1.017133956386293, "grad_norm": 7.965478420257568, "learning_rate": 2.7982427906390374e-06, "loss": 0.07668742537498474, "step": 3918 }, { "epoch": 1.0173935617860852, "grad_norm": 8.672957420349121, "learning_rate": 2.797296994315638e-06, "loss": 0.1937498301267624, "step": 3919 }, { "epoch": 1.0176531671858775, "grad_norm": 9.683975219726562, "learning_rate": 2.796351189631214e-06, "loss": 0.10131754726171494, "step": 3920 }, { "epoch": 1.0179127725856698, "grad_norm": 9.068511962890625, "learning_rate": 2.795405376752961e-06, "loss": 0.126363143324852, "step": 3921 }, { "epoch": 1.0181723779854621, "grad_norm": 6.506666660308838, "learning_rate": 2.7944595558480765e-06, "loss": 0.19278499484062195, "step": 3922 }, { "epoch": 1.0184319833852544, "grad_norm": 7.393968105316162, "learning_rate": 2.7935137270837605e-06, "loss": 0.09701339155435562, "step": 3923 }, { "epoch": 1.0186915887850467, "grad_norm": 6.788854122161865, "learning_rate": 2.7925678906272143e-06, "loss": 0.1817067265510559, "step": 3924 }, { "epoch": 1.018951194184839, "grad_norm": 8.292630195617676, "learning_rate": 2.7916220466456384e-06, "loss": 0.19009748101234436, "step": 3925 }, { "epoch": 1.0192107995846313, "grad_norm": 8.676112174987793, "learning_rate": 2.7906761953062396e-06, "loss": 0.1795847862958908, "step": 3926 }, { "epoch": 1.0194704049844237, "grad_norm": 9.545848846435547, "learning_rate": 2.78973033677622e-06, "loss": 0.10394616425037384, "step": 3927 }, { "epoch": 1.019730010384216, "grad_norm": 11.264042854309082, "learning_rate": 2.788784471222786e-06, "loss": 0.08452427387237549, "step": 3928 }, { "epoch": 1.0199896157840083, "grad_norm": 6.015286922454834, "learning_rate": 2.7878385988131455e-06, "loss": 0.21471865475177765, "step": 3929 }, { "epoch": 1.0202492211838006, "grad_norm": 7.021490573883057, "learning_rate": 2.7868927197145086e-06, "loss": 0.21738234162330627, "step": 3930 }, { "epoch": 1.0205088265835929, "grad_norm": 5.844987869262695, "learning_rate": 2.785946834094082e-06, "loss": 0.012722556479275227, "step": 3931 }, { "epoch": 1.0207684319833852, "grad_norm": 7.465654373168945, "learning_rate": 2.7850009421190787e-06, "loss": 0.17227911949157715, "step": 3932 }, { "epoch": 1.0210280373831775, "grad_norm": 7.150121212005615, "learning_rate": 2.7840550439567104e-06, "loss": 0.04368650168180466, "step": 3933 }, { "epoch": 1.0212876427829698, "grad_norm": 8.433323860168457, "learning_rate": 2.7831091397741905e-06, "loss": 0.12643076479434967, "step": 3934 }, { "epoch": 1.021547248182762, "grad_norm": 10.214330673217773, "learning_rate": 2.782163229738732e-06, "loss": 0.1172037422657013, "step": 3935 }, { "epoch": 1.0218068535825544, "grad_norm": 5.358786106109619, "learning_rate": 2.7812173140175506e-06, "loss": 0.2766493856906891, "step": 3936 }, { "epoch": 1.022066458982347, "grad_norm": 11.011186599731445, "learning_rate": 2.780271392777864e-06, "loss": 0.04254709184169769, "step": 3937 }, { "epoch": 1.0223260643821392, "grad_norm": 10.506444931030273, "learning_rate": 2.7793254661868877e-06, "loss": 0.14989231526851654, "step": 3938 }, { "epoch": 1.0225856697819315, "grad_norm": 10.210741996765137, "learning_rate": 2.778379534411841e-06, "loss": 0.1278911978006363, "step": 3939 }, { "epoch": 1.0228452751817239, "grad_norm": 7.113356113433838, "learning_rate": 2.7774335976199422e-06, "loss": 0.21909970045089722, "step": 3940 }, { "epoch": 1.0231048805815162, "grad_norm": 8.9165620803833, "learning_rate": 2.7764876559784105e-06, "loss": 0.0410575307905674, "step": 3941 }, { "epoch": 1.0233644859813085, "grad_norm": 12.041224479675293, "learning_rate": 2.775541709654469e-06, "loss": 0.17932641506195068, "step": 3942 }, { "epoch": 1.0236240913811008, "grad_norm": 10.610010147094727, "learning_rate": 2.7745957588153376e-06, "loss": 0.04644656926393509, "step": 3943 }, { "epoch": 1.023883696780893, "grad_norm": 8.044418334960938, "learning_rate": 2.7736498036282388e-06, "loss": 0.1980973780155182, "step": 3944 }, { "epoch": 1.0241433021806854, "grad_norm": 15.24914836883545, "learning_rate": 2.7727038442603967e-06, "loss": 0.13633733987808228, "step": 3945 }, { "epoch": 1.0244029075804777, "grad_norm": 5.663825035095215, "learning_rate": 2.7717578808790342e-06, "loss": 0.2779289484024048, "step": 3946 }, { "epoch": 1.02466251298027, "grad_norm": 5.762772560119629, "learning_rate": 2.7708119136513778e-06, "loss": 0.241610586643219, "step": 3947 }, { "epoch": 1.0249221183800623, "grad_norm": 10.890466690063477, "learning_rate": 2.7698659427446507e-06, "loss": 0.08286207914352417, "step": 3948 }, { "epoch": 1.0251817237798546, "grad_norm": 8.006889343261719, "learning_rate": 2.768919968326079e-06, "loss": 0.2438575178384781, "step": 3949 }, { "epoch": 1.025441329179647, "grad_norm": 8.468667984008789, "learning_rate": 2.767973990562891e-06, "loss": 0.17786294221878052, "step": 3950 }, { "epoch": 1.0257009345794392, "grad_norm": 16.083213806152344, "learning_rate": 2.7670280096223136e-06, "loss": 0.12028692662715912, "step": 3951 }, { "epoch": 1.0259605399792315, "grad_norm": 9.250554084777832, "learning_rate": 2.766082025671573e-06, "loss": 0.08617573976516724, "step": 3952 }, { "epoch": 1.0262201453790238, "grad_norm": 10.856694221496582, "learning_rate": 2.7651360388778993e-06, "loss": 0.09347786009311676, "step": 3953 }, { "epoch": 1.0264797507788161, "grad_norm": 5.459696292877197, "learning_rate": 2.7641900494085193e-06, "loss": 0.27738654613494873, "step": 3954 }, { "epoch": 1.0267393561786085, "grad_norm": 6.959506034851074, "learning_rate": 2.763244057430665e-06, "loss": 0.04535338282585144, "step": 3955 }, { "epoch": 1.0269989615784008, "grad_norm": 10.275891304016113, "learning_rate": 2.762298063111563e-06, "loss": 0.06536668539047241, "step": 3956 }, { "epoch": 1.027258566978193, "grad_norm": 13.004080772399902, "learning_rate": 2.7613520666184466e-06, "loss": 0.10967172682285309, "step": 3957 }, { "epoch": 1.0275181723779854, "grad_norm": 8.919858932495117, "learning_rate": 2.7604060681185442e-06, "loss": 0.049047961831092834, "step": 3958 }, { "epoch": 1.0277777777777777, "grad_norm": 11.375747680664062, "learning_rate": 2.7594600677790866e-06, "loss": 0.12593281269073486, "step": 3959 }, { "epoch": 1.02803738317757, "grad_norm": 11.160051345825195, "learning_rate": 2.758514065767306e-06, "loss": 0.07835528254508972, "step": 3960 }, { "epoch": 1.0282969885773625, "grad_norm": 4.868941783905029, "learning_rate": 2.7575680622504342e-06, "loss": 0.2358022928237915, "step": 3961 }, { "epoch": 1.0285565939771548, "grad_norm": 8.437420845031738, "learning_rate": 2.7566220573957015e-06, "loss": 0.129630446434021, "step": 3962 }, { "epoch": 1.0288161993769471, "grad_norm": 8.68986701965332, "learning_rate": 2.755676051370341e-06, "loss": 0.08660091459751129, "step": 3963 }, { "epoch": 1.0290758047767394, "grad_norm": 6.515183925628662, "learning_rate": 2.7547300443415836e-06, "loss": 0.2047739028930664, "step": 3964 }, { "epoch": 1.0293354101765317, "grad_norm": 5.488347053527832, "learning_rate": 2.753784036476664e-06, "loss": 0.2670285999774933, "step": 3965 }, { "epoch": 1.029595015576324, "grad_norm": 8.507019996643066, "learning_rate": 2.752838027942813e-06, "loss": 0.07620327174663544, "step": 3966 }, { "epoch": 1.0298546209761164, "grad_norm": 4.930459499359131, "learning_rate": 2.751892018907263e-06, "loss": 0.25390294194221497, "step": 3967 }, { "epoch": 1.0301142263759087, "grad_norm": 6.84295129776001, "learning_rate": 2.7509460095372477e-06, "loss": 0.25409263372421265, "step": 3968 }, { "epoch": 1.030373831775701, "grad_norm": 4.97076416015625, "learning_rate": 2.7500000000000004e-06, "loss": 0.25694596767425537, "step": 3969 }, { "epoch": 1.0306334371754933, "grad_norm": 5.758492946624756, "learning_rate": 2.749053990462752e-06, "loss": 0.20028872787952423, "step": 3970 }, { "epoch": 1.0308930425752856, "grad_norm": 5.079723358154297, "learning_rate": 2.7481079810927374e-06, "loss": 0.25967469811439514, "step": 3971 }, { "epoch": 1.0311526479750779, "grad_norm": 6.887670993804932, "learning_rate": 2.747161972057188e-06, "loss": 0.2512950301170349, "step": 3972 }, { "epoch": 1.0314122533748702, "grad_norm": 10.525203704833984, "learning_rate": 2.7462159635233372e-06, "loss": 0.07962725311517715, "step": 3973 }, { "epoch": 1.0316718587746625, "grad_norm": 11.030974388122559, "learning_rate": 2.7452699556584167e-06, "loss": 0.09371861815452576, "step": 3974 }, { "epoch": 1.0319314641744548, "grad_norm": 6.236265182495117, "learning_rate": 2.7443239486296603e-06, "loss": 0.10380130261182785, "step": 3975 }, { "epoch": 1.032191069574247, "grad_norm": 11.368236541748047, "learning_rate": 2.7433779426042997e-06, "loss": 0.17161181569099426, "step": 3976 }, { "epoch": 1.0324506749740394, "grad_norm": 5.544776916503906, "learning_rate": 2.742431937749567e-06, "loss": 0.230681911110878, "step": 3977 }, { "epoch": 1.0327102803738317, "grad_norm": 8.964096069335938, "learning_rate": 2.7414859342326943e-06, "loss": 0.09085148572921753, "step": 3978 }, { "epoch": 1.032969885773624, "grad_norm": 5.896623611450195, "learning_rate": 2.740539932220915e-06, "loss": 0.27923518419265747, "step": 3979 }, { "epoch": 1.0332294911734163, "grad_norm": 8.477109909057617, "learning_rate": 2.739593931881457e-06, "loss": 0.08609312027692795, "step": 3980 }, { "epoch": 1.0334890965732086, "grad_norm": 6.812094211578369, "learning_rate": 2.738647933381554e-06, "loss": 0.2361588478088379, "step": 3981 }, { "epoch": 1.033748701973001, "grad_norm": 8.185646057128906, "learning_rate": 2.7377019368884367e-06, "loss": 0.10153618454933167, "step": 3982 }, { "epoch": 1.0340083073727933, "grad_norm": 5.623041152954102, "learning_rate": 2.7367559425693364e-06, "loss": 0.23012790083885193, "step": 3983 }, { "epoch": 1.0342679127725856, "grad_norm": 5.845668315887451, "learning_rate": 2.7358099505914814e-06, "loss": 0.24714884161949158, "step": 3984 }, { "epoch": 1.034527518172378, "grad_norm": 8.547931671142578, "learning_rate": 2.7348639611221014e-06, "loss": 0.0865430235862732, "step": 3985 }, { "epoch": 1.0347871235721704, "grad_norm": 13.360725402832031, "learning_rate": 2.7339179743284273e-06, "loss": 0.1162688285112381, "step": 3986 }, { "epoch": 1.0350467289719627, "grad_norm": 9.311010360717773, "learning_rate": 2.732971990377688e-06, "loss": 0.09336799383163452, "step": 3987 }, { "epoch": 1.035306334371755, "grad_norm": 6.820934772491455, "learning_rate": 2.7320260094371097e-06, "loss": 0.043476786464452744, "step": 3988 }, { "epoch": 1.0355659397715473, "grad_norm": 6.9145379066467285, "learning_rate": 2.7310800316739215e-06, "loss": 0.1055695116519928, "step": 3989 }, { "epoch": 1.0358255451713396, "grad_norm": 10.463375091552734, "learning_rate": 2.7301340572553505e-06, "loss": 0.10934454947710037, "step": 3990 }, { "epoch": 1.036085150571132, "grad_norm": 10.107767105102539, "learning_rate": 2.729188086348624e-06, "loss": 0.12814538180828094, "step": 3991 }, { "epoch": 1.0363447559709242, "grad_norm": 8.593994140625, "learning_rate": 2.728242119120967e-06, "loss": 0.1508564054965973, "step": 3992 }, { "epoch": 1.0366043613707165, "grad_norm": 6.386961460113525, "learning_rate": 2.7272961557396044e-06, "loss": 0.24351055920124054, "step": 3993 }, { "epoch": 1.0368639667705088, "grad_norm": 13.373391151428223, "learning_rate": 2.726350196371762e-06, "loss": 0.07972235977649689, "step": 3994 }, { "epoch": 1.0371235721703012, "grad_norm": 6.877881050109863, "learning_rate": 2.7254042411846636e-06, "loss": 0.07397165894508362, "step": 3995 }, { "epoch": 1.0373831775700935, "grad_norm": 8.465593338012695, "learning_rate": 2.724458290345532e-06, "loss": 0.19045454263687134, "step": 3996 }, { "epoch": 1.0376427829698858, "grad_norm": 10.555658340454102, "learning_rate": 2.7235123440215898e-06, "loss": 0.103238545358181, "step": 3997 }, { "epoch": 1.037902388369678, "grad_norm": 6.070667743682861, "learning_rate": 2.7225664023800597e-06, "loss": 0.21039699018001556, "step": 3998 }, { "epoch": 1.0381619937694704, "grad_norm": 9.50527572631836, "learning_rate": 2.72162046558816e-06, "loss": 0.060239631682634354, "step": 3999 }, { "epoch": 1.0384215991692627, "grad_norm": 5.203536033630371, "learning_rate": 2.720674533813113e-06, "loss": 0.24997198581695557, "step": 4000 }, { "epoch": 1.038681204569055, "grad_norm": 9.942421913146973, "learning_rate": 2.719728607222136e-06, "loss": 0.06570631265640259, "step": 4001 }, { "epoch": 1.0389408099688473, "grad_norm": 5.900951862335205, "learning_rate": 2.7187826859824497e-06, "loss": 0.20146429538726807, "step": 4002 }, { "epoch": 1.0392004153686396, "grad_norm": 7.4872145652771, "learning_rate": 2.717836770261269e-06, "loss": 0.04781235381960869, "step": 4003 }, { "epoch": 1.039460020768432, "grad_norm": 9.484204292297363, "learning_rate": 2.7168908602258106e-06, "loss": 0.07915937900543213, "step": 4004 }, { "epoch": 1.0397196261682242, "grad_norm": 8.42409610748291, "learning_rate": 2.7159449560432903e-06, "loss": 0.08809805661439896, "step": 4005 }, { "epoch": 1.0399792315680165, "grad_norm": 12.039294242858887, "learning_rate": 2.714999057880922e-06, "loss": 0.08498206734657288, "step": 4006 }, { "epoch": 1.0402388369678088, "grad_norm": 9.04325008392334, "learning_rate": 2.714053165905919e-06, "loss": 0.1449560672044754, "step": 4007 }, { "epoch": 1.0404984423676011, "grad_norm": 5.185142993927002, "learning_rate": 2.7131072802854925e-06, "loss": 0.2587963938713074, "step": 4008 }, { "epoch": 1.0407580477673937, "grad_norm": 8.791041374206543, "learning_rate": 2.7121614011868547e-06, "loss": 0.09866102039813995, "step": 4009 }, { "epoch": 1.041017653167186, "grad_norm": 10.104196548461914, "learning_rate": 2.711215528777216e-06, "loss": 0.10491275787353516, "step": 4010 }, { "epoch": 1.0412772585669783, "grad_norm": 9.501018524169922, "learning_rate": 2.7102696632237813e-06, "loss": 0.1924707144498825, "step": 4011 }, { "epoch": 1.0415368639667706, "grad_norm": 11.822763442993164, "learning_rate": 2.7093238046937615e-06, "loss": 0.07076754420995712, "step": 4012 }, { "epoch": 1.041796469366563, "grad_norm": 13.925585746765137, "learning_rate": 2.708377953354362e-06, "loss": 0.10931017249822617, "step": 4013 }, { "epoch": 1.0420560747663552, "grad_norm": 13.144369125366211, "learning_rate": 2.7074321093727877e-06, "loss": 0.06415179371833801, "step": 4014 }, { "epoch": 1.0423156801661475, "grad_norm": 8.174022674560547, "learning_rate": 2.706486272916241e-06, "loss": 0.24634425342082977, "step": 4015 }, { "epoch": 1.0425752855659398, "grad_norm": 6.388430595397949, "learning_rate": 2.7055404441519246e-06, "loss": 0.27330732345581055, "step": 4016 }, { "epoch": 1.0428348909657321, "grad_norm": 11.225699424743652, "learning_rate": 2.70459462324704e-06, "loss": 0.12271934747695923, "step": 4017 }, { "epoch": 1.0430944963655244, "grad_norm": 9.5565824508667, "learning_rate": 2.7036488103687868e-06, "loss": 0.19392339885234833, "step": 4018 }, { "epoch": 1.0433541017653167, "grad_norm": 7.555694580078125, "learning_rate": 2.702703005684363e-06, "loss": 0.21449309587478638, "step": 4019 }, { "epoch": 1.043613707165109, "grad_norm": 7.244806289672852, "learning_rate": 2.7017572093609633e-06, "loss": 0.21515311300754547, "step": 4020 }, { "epoch": 1.0438733125649013, "grad_norm": 4.584173679351807, "learning_rate": 2.700811421565785e-06, "loss": 0.2727484107017517, "step": 4021 }, { "epoch": 1.0441329179646937, "grad_norm": 7.58785343170166, "learning_rate": 2.6998656424660226e-06, "loss": 0.24011382460594177, "step": 4022 }, { "epoch": 1.044392523364486, "grad_norm": 10.16572380065918, "learning_rate": 2.698919872228865e-06, "loss": 0.1564793735742569, "step": 4023 }, { "epoch": 1.0446521287642783, "grad_norm": 10.622035026550293, "learning_rate": 2.6979741110215045e-06, "loss": 0.1104840561747551, "step": 4024 }, { "epoch": 1.0449117341640706, "grad_norm": 10.57458782196045, "learning_rate": 2.6970283590111307e-06, "loss": 0.04935842752456665, "step": 4025 }, { "epoch": 1.0451713395638629, "grad_norm": 5.535445213317871, "learning_rate": 2.6960826163649297e-06, "loss": 0.2553173303604126, "step": 4026 }, { "epoch": 1.0454309449636552, "grad_norm": 10.781182289123535, "learning_rate": 2.695136883250088e-06, "loss": 0.058017194271087646, "step": 4027 }, { "epoch": 1.0456905503634475, "grad_norm": 10.133305549621582, "learning_rate": 2.6941911598337885e-06, "loss": 0.07530763000249863, "step": 4028 }, { "epoch": 1.0459501557632398, "grad_norm": 5.479909420013428, "learning_rate": 2.6932454462832146e-06, "loss": 0.26434817910194397, "step": 4029 }, { "epoch": 1.046209761163032, "grad_norm": 7.780871868133545, "learning_rate": 2.6922997427655456e-06, "loss": 0.06848440319299698, "step": 4030 }, { "epoch": 1.0464693665628244, "grad_norm": 8.301072120666504, "learning_rate": 2.6913540494479613e-06, "loss": 0.1863735020160675, "step": 4031 }, { "epoch": 1.0467289719626167, "grad_norm": 10.890092849731445, "learning_rate": 2.6904083664976384e-06, "loss": 0.13350138068199158, "step": 4032 }, { "epoch": 1.0469885773624092, "grad_norm": 9.477352142333984, "learning_rate": 2.689462694081752e-06, "loss": 0.16499552130699158, "step": 4033 }, { "epoch": 1.0472481827622016, "grad_norm": 9.039000511169434, "learning_rate": 2.6885170323674748e-06, "loss": 0.16121532022953033, "step": 4034 }, { "epoch": 1.0475077881619939, "grad_norm": 7.263554096221924, "learning_rate": 2.6875713815219783e-06, "loss": 0.044220730662345886, "step": 4035 }, { "epoch": 1.0477673935617862, "grad_norm": 7.05935525894165, "learning_rate": 2.6866257417124326e-06, "loss": 0.21825945377349854, "step": 4036 }, { "epoch": 1.0480269989615785, "grad_norm": 6.944103240966797, "learning_rate": 2.6856801131060046e-06, "loss": 0.15635475516319275, "step": 4037 }, { "epoch": 1.0482866043613708, "grad_norm": 8.8873929977417, "learning_rate": 2.6847344958698594e-06, "loss": 0.10456786304712296, "step": 4038 }, { "epoch": 1.048546209761163, "grad_norm": 8.127862930297852, "learning_rate": 2.683788890171162e-06, "loss": 0.05997931584715843, "step": 4039 }, { "epoch": 1.0488058151609554, "grad_norm": 8.335376739501953, "learning_rate": 2.6828432961770717e-06, "loss": 0.18707618117332458, "step": 4040 }, { "epoch": 1.0490654205607477, "grad_norm": 11.838129997253418, "learning_rate": 2.68189771405475e-06, "loss": 0.08480620384216309, "step": 4041 }, { "epoch": 1.04932502596054, "grad_norm": 6.365567684173584, "learning_rate": 2.680952143971352e-06, "loss": 0.19606557488441467, "step": 4042 }, { "epoch": 1.0495846313603323, "grad_norm": 7.481191158294678, "learning_rate": 2.6800065860940343e-06, "loss": 0.2207425832748413, "step": 4043 }, { "epoch": 1.0498442367601246, "grad_norm": 6.650819778442383, "learning_rate": 2.6790610405899496e-06, "loss": 0.022939279675483704, "step": 4044 }, { "epoch": 1.050103842159917, "grad_norm": 10.238801002502441, "learning_rate": 2.6781155076262494e-06, "loss": 0.14184898138046265, "step": 4045 }, { "epoch": 1.0503634475597092, "grad_norm": 8.120224952697754, "learning_rate": 2.6771699873700806e-06, "loss": 0.11642619222402573, "step": 4046 }, { "epoch": 1.0506230529595015, "grad_norm": 7.932507514953613, "learning_rate": 2.6762244799885906e-06, "loss": 0.17172342538833618, "step": 4047 }, { "epoch": 1.0508826583592938, "grad_norm": 9.285436630249023, "learning_rate": 2.675278985648923e-06, "loss": 0.11949510872364044, "step": 4048 }, { "epoch": 1.0511422637590861, "grad_norm": 5.801235198974609, "learning_rate": 2.674333504518221e-06, "loss": 0.24122083187103271, "step": 4049 }, { "epoch": 1.0514018691588785, "grad_norm": 9.096874237060547, "learning_rate": 2.673388036763622e-06, "loss": 0.22967666387557983, "step": 4050 }, { "epoch": 1.0516614745586708, "grad_norm": 10.888863563537598, "learning_rate": 2.672442582552264e-06, "loss": 0.045400168746709824, "step": 4051 }, { "epoch": 1.051921079958463, "grad_norm": 9.477378845214844, "learning_rate": 2.671497142051282e-06, "loss": 0.07630139589309692, "step": 4052 }, { "epoch": 1.0521806853582554, "grad_norm": 8.251884460449219, "learning_rate": 2.6705517154278073e-06, "loss": 0.15469250082969666, "step": 4053 }, { "epoch": 1.0524402907580477, "grad_norm": 13.087596893310547, "learning_rate": 2.66960630284897e-06, "loss": 0.07560717314481735, "step": 4054 }, { "epoch": 1.05269989615784, "grad_norm": 7.436178684234619, "learning_rate": 2.668660904481898e-06, "loss": 0.12587320804595947, "step": 4055 }, { "epoch": 1.0529595015576323, "grad_norm": 6.877731800079346, "learning_rate": 2.667715520493716e-06, "loss": 0.2022167444229126, "step": 4056 }, { "epoch": 1.0532191069574246, "grad_norm": 5.7669901847839355, "learning_rate": 2.666770151051545e-06, "loss": 0.2848864793777466, "step": 4057 }, { "epoch": 1.0534787123572171, "grad_norm": 10.362215995788574, "learning_rate": 2.665824796322506e-06, "loss": 0.07666272670030594, "step": 4058 }, { "epoch": 1.0537383177570094, "grad_norm": 9.762962341308594, "learning_rate": 2.6648794564737156e-06, "loss": 0.09291058778762817, "step": 4059 }, { "epoch": 1.0539979231568017, "grad_norm": 8.841767311096191, "learning_rate": 2.663934131672289e-06, "loss": 0.13387469947338104, "step": 4060 }, { "epoch": 1.054257528556594, "grad_norm": 8.250462532043457, "learning_rate": 2.6629888220853365e-06, "loss": 0.13934624195098877, "step": 4061 }, { "epoch": 1.0545171339563864, "grad_norm": 9.3955717086792, "learning_rate": 2.662043527879968e-06, "loss": 0.1124068945646286, "step": 4062 }, { "epoch": 1.0547767393561787, "grad_norm": 10.023506164550781, "learning_rate": 2.66109824922329e-06, "loss": 0.20886243879795074, "step": 4063 }, { "epoch": 1.055036344755971, "grad_norm": 8.757720947265625, "learning_rate": 2.660152986282406e-06, "loss": 0.24236196279525757, "step": 4064 }, { "epoch": 1.0552959501557633, "grad_norm": 7.92457389831543, "learning_rate": 2.659207739224417e-06, "loss": 0.1650155633687973, "step": 4065 }, { "epoch": 1.0555555555555556, "grad_norm": 9.142913818359375, "learning_rate": 2.65826250821642e-06, "loss": 0.1793181300163269, "step": 4066 }, { "epoch": 1.0558151609553479, "grad_norm": 6.990335941314697, "learning_rate": 2.6573172934255116e-06, "loss": 0.05689683556556702, "step": 4067 }, { "epoch": 1.0560747663551402, "grad_norm": 7.5963850021362305, "learning_rate": 2.656372095018784e-06, "loss": 0.17726582288742065, "step": 4068 }, { "epoch": 1.0563343717549325, "grad_norm": 9.667325019836426, "learning_rate": 2.6554269131633254e-06, "loss": 0.07523904740810394, "step": 4069 }, { "epoch": 1.0565939771547248, "grad_norm": 11.337374687194824, "learning_rate": 2.6544817480262237e-06, "loss": 0.0924278125166893, "step": 4070 }, { "epoch": 1.0568535825545171, "grad_norm": 6.264806747436523, "learning_rate": 2.6535365997745616e-06, "loss": 0.2317771464586258, "step": 4071 }, { "epoch": 1.0571131879543094, "grad_norm": 5.993232250213623, "learning_rate": 2.65259146857542e-06, "loss": 0.2710767388343811, "step": 4072 }, { "epoch": 1.0573727933541017, "grad_norm": 7.042692184448242, "learning_rate": 2.6516463545958766e-06, "loss": 0.18695202469825745, "step": 4073 }, { "epoch": 1.057632398753894, "grad_norm": 13.819015502929688, "learning_rate": 2.650701258003005e-06, "loss": 0.12095899879932404, "step": 4074 }, { "epoch": 1.0578920041536863, "grad_norm": 7.1184983253479, "learning_rate": 2.6497561789638783e-06, "loss": 0.18474870920181274, "step": 4075 }, { "epoch": 1.0581516095534786, "grad_norm": 6.2169365882873535, "learning_rate": 2.648811117645564e-06, "loss": 0.28064364194869995, "step": 4076 }, { "epoch": 1.058411214953271, "grad_norm": 11.074651718139648, "learning_rate": 2.6478660742151257e-06, "loss": 0.1236412525177002, "step": 4077 }, { "epoch": 1.0586708203530633, "grad_norm": 11.396240234375, "learning_rate": 2.646921048839628e-06, "loss": 0.12290622293949127, "step": 4078 }, { "epoch": 1.0589304257528556, "grad_norm": 7.396803379058838, "learning_rate": 2.6459760416861293e-06, "loss": 0.17525255680084229, "step": 4079 }, { "epoch": 1.0591900311526479, "grad_norm": 7.937413215637207, "learning_rate": 2.6450310529216837e-06, "loss": 0.11371427774429321, "step": 4080 }, { "epoch": 1.0594496365524404, "grad_norm": 8.00948715209961, "learning_rate": 2.644086082713345e-06, "loss": 0.16076751053333282, "step": 4081 }, { "epoch": 1.0597092419522327, "grad_norm": 10.780560493469238, "learning_rate": 2.64314113122816e-06, "loss": 0.11223828047513962, "step": 4082 }, { "epoch": 1.059968847352025, "grad_norm": 5.474565505981445, "learning_rate": 2.6421961986331786e-06, "loss": 0.27834242582321167, "step": 4083 }, { "epoch": 1.0602284527518173, "grad_norm": 10.388899803161621, "learning_rate": 2.6412512850954397e-06, "loss": 0.10321524739265442, "step": 4084 }, { "epoch": 1.0604880581516096, "grad_norm": 8.283905029296875, "learning_rate": 2.640306390781984e-06, "loss": 0.09712109714746475, "step": 4085 }, { "epoch": 1.060747663551402, "grad_norm": 8.049455642700195, "learning_rate": 2.6393615158598464e-06, "loss": 0.0750022828578949, "step": 4086 }, { "epoch": 1.0610072689511942, "grad_norm": 11.890026092529297, "learning_rate": 2.6384166604960596e-06, "loss": 0.042885519564151764, "step": 4087 }, { "epoch": 1.0612668743509865, "grad_norm": 8.025299072265625, "learning_rate": 2.6374718248576526e-06, "loss": 0.21355131268501282, "step": 4088 }, { "epoch": 1.0615264797507789, "grad_norm": 7.714563369750977, "learning_rate": 2.6365270091116497e-06, "loss": 0.036126647144556046, "step": 4089 }, { "epoch": 1.0617860851505712, "grad_norm": 5.952432155609131, "learning_rate": 2.635582213425074e-06, "loss": 0.2604477107524872, "step": 4090 }, { "epoch": 1.0620456905503635, "grad_norm": 7.087824821472168, "learning_rate": 2.6346374379649432e-06, "loss": 0.20648181438446045, "step": 4091 }, { "epoch": 1.0623052959501558, "grad_norm": 6.193526744842529, "learning_rate": 2.633692682898272e-06, "loss": 0.24807868897914886, "step": 4092 }, { "epoch": 1.062564901349948, "grad_norm": 8.35940933227539, "learning_rate": 2.632747948392071e-06, "loss": 0.04335904121398926, "step": 4093 }, { "epoch": 1.0628245067497404, "grad_norm": 15.11192798614502, "learning_rate": 2.6318032346133476e-06, "loss": 0.0423147976398468, "step": 4094 }, { "epoch": 1.0630841121495327, "grad_norm": 5.469825267791748, "learning_rate": 2.6308585417291073e-06, "loss": 0.2486531287431717, "step": 4095 }, { "epoch": 1.063343717549325, "grad_norm": 9.758111953735352, "learning_rate": 2.6299138699063475e-06, "loss": 0.06999094784259796, "step": 4096 }, { "epoch": 1.0636033229491173, "grad_norm": 6.672680377960205, "learning_rate": 2.6289692193120664e-06, "loss": 0.29794448614120483, "step": 4097 }, { "epoch": 1.0638629283489096, "grad_norm": 6.821733474731445, "learning_rate": 2.628024590113256e-06, "loss": 0.22310197353363037, "step": 4098 }, { "epoch": 1.064122533748702, "grad_norm": 9.731904029846191, "learning_rate": 2.6270799824769056e-06, "loss": 0.0633440762758255, "step": 4099 }, { "epoch": 1.0643821391484942, "grad_norm": 7.709211826324463, "learning_rate": 2.626135396569999e-06, "loss": 0.19302739202976227, "step": 4100 }, { "epoch": 1.0646417445482865, "grad_norm": 6.967790603637695, "learning_rate": 2.6251908325595187e-06, "loss": 0.22547098994255066, "step": 4101 }, { "epoch": 1.0649013499480788, "grad_norm": 10.375893592834473, "learning_rate": 2.6242462906124415e-06, "loss": 0.04597635939717293, "step": 4102 }, { "epoch": 1.0651609553478711, "grad_norm": 6.816823959350586, "learning_rate": 2.623301770895741e-06, "loss": 0.02975594252347946, "step": 4103 }, { "epoch": 1.0654205607476634, "grad_norm": 8.236679077148438, "learning_rate": 2.6223572735763864e-06, "loss": 0.1900007724761963, "step": 4104 }, { "epoch": 1.0656801661474558, "grad_norm": 13.835140228271484, "learning_rate": 2.621412798821343e-06, "loss": 0.09856177866458893, "step": 4105 }, { "epoch": 1.0659397715472483, "grad_norm": 11.06675910949707, "learning_rate": 2.6204683467975716e-06, "loss": 0.05888855457305908, "step": 4106 }, { "epoch": 1.0661993769470406, "grad_norm": 6.314864158630371, "learning_rate": 2.619523917672033e-06, "loss": 0.24489688873291016, "step": 4107 }, { "epoch": 1.066458982346833, "grad_norm": 9.481042861938477, "learning_rate": 2.6185795116116756e-06, "loss": 0.15412357449531555, "step": 4108 }, { "epoch": 1.0667185877466252, "grad_norm": 11.267463684082031, "learning_rate": 2.617635128783452e-06, "loss": 0.03060322254896164, "step": 4109 }, { "epoch": 1.0669781931464175, "grad_norm": 5.729284286499023, "learning_rate": 2.6166907693543085e-06, "loss": 0.014390120282769203, "step": 4110 }, { "epoch": 1.0672377985462098, "grad_norm": 11.153477668762207, "learning_rate": 2.615746433491183e-06, "loss": 0.09041769802570343, "step": 4111 }, { "epoch": 1.0674974039460021, "grad_norm": 10.631266593933105, "learning_rate": 2.6148021213610147e-06, "loss": 0.0787787213921547, "step": 4112 }, { "epoch": 1.0677570093457944, "grad_norm": 5.335435390472412, "learning_rate": 2.613857833130735e-06, "loss": 0.30631980299949646, "step": 4113 }, { "epoch": 1.0680166147455867, "grad_norm": 6.3630595207214355, "learning_rate": 2.6129135689672745e-06, "loss": 0.27315419912338257, "step": 4114 }, { "epoch": 1.068276220145379, "grad_norm": 5.3564910888671875, "learning_rate": 2.6119693290375555e-06, "loss": 0.2443624883890152, "step": 4115 }, { "epoch": 1.0685358255451713, "grad_norm": 6.049313545227051, "learning_rate": 2.611025113508498e-06, "loss": 0.23884548246860504, "step": 4116 }, { "epoch": 1.0687954309449637, "grad_norm": 6.752605438232422, "learning_rate": 2.610080922547019e-06, "loss": 0.16716215014457703, "step": 4117 }, { "epoch": 1.069055036344756, "grad_norm": 11.615456581115723, "learning_rate": 2.6091367563200294e-06, "loss": 0.13990016281604767, "step": 4118 }, { "epoch": 1.0693146417445483, "grad_norm": 6.3404951095581055, "learning_rate": 2.608192614994435e-06, "loss": 0.262937068939209, "step": 4119 }, { "epoch": 1.0695742471443406, "grad_norm": 5.251070022583008, "learning_rate": 2.6072484987371395e-06, "loss": 0.2745474576950073, "step": 4120 }, { "epoch": 1.0698338525441329, "grad_norm": 10.898355484008789, "learning_rate": 2.6063044077150414e-06, "loss": 0.10833121091127396, "step": 4121 }, { "epoch": 1.0700934579439252, "grad_norm": 10.602837562561035, "learning_rate": 2.6053603420950337e-06, "loss": 0.07129185646772385, "step": 4122 }, { "epoch": 1.0703530633437175, "grad_norm": 9.466150283813477, "learning_rate": 2.6044163020440055e-06, "loss": 0.12273582816123962, "step": 4123 }, { "epoch": 1.0706126687435098, "grad_norm": 11.786832809448242, "learning_rate": 2.6034722877288415e-06, "loss": 0.0241255983710289, "step": 4124 }, { "epoch": 1.070872274143302, "grad_norm": 9.853017807006836, "learning_rate": 2.6025282993164226e-06, "loss": 0.05638467147946358, "step": 4125 }, { "epoch": 1.0711318795430944, "grad_norm": 7.316700458526611, "learning_rate": 2.6015843369736234e-06, "loss": 0.184865340590477, "step": 4126 }, { "epoch": 1.0713914849428867, "grad_norm": 12.155925750732422, "learning_rate": 2.6006404008673153e-06, "loss": 0.13386453688144684, "step": 4127 }, { "epoch": 1.071651090342679, "grad_norm": 15.316765785217285, "learning_rate": 2.599696491164364e-06, "loss": 0.13493075966835022, "step": 4128 }, { "epoch": 1.0719106957424716, "grad_norm": 15.814478874206543, "learning_rate": 2.5987526080316316e-06, "loss": 0.13141828775405884, "step": 4129 }, { "epoch": 1.0721703011422639, "grad_norm": 10.662114143371582, "learning_rate": 2.5978087516359756e-06, "loss": 0.2213275134563446, "step": 4130 }, { "epoch": 1.0724299065420562, "grad_norm": 12.534070014953613, "learning_rate": 2.5968649221442473e-06, "loss": 0.12276066839694977, "step": 4131 }, { "epoch": 1.0726895119418485, "grad_norm": 7.684449672698975, "learning_rate": 2.595921119723294e-06, "loss": 0.08143522590398788, "step": 4132 }, { "epoch": 1.0729491173416408, "grad_norm": 10.970146179199219, "learning_rate": 2.5949773445399595e-06, "loss": 0.050140123814344406, "step": 4133 }, { "epoch": 1.073208722741433, "grad_norm": 7.531533241271973, "learning_rate": 2.5940335967610807e-06, "loss": 0.2138158082962036, "step": 4134 }, { "epoch": 1.0734683281412254, "grad_norm": 9.653477668762207, "learning_rate": 2.5930898765534906e-06, "loss": 0.11646170914173126, "step": 4135 }, { "epoch": 1.0737279335410177, "grad_norm": 9.928112983703613, "learning_rate": 2.592146184084018e-06, "loss": 0.17914068698883057, "step": 4136 }, { "epoch": 1.07398753894081, "grad_norm": 11.08532428741455, "learning_rate": 2.5912025195194855e-06, "loss": 0.20481839776039124, "step": 4137 }, { "epoch": 1.0742471443406023, "grad_norm": 5.267454624176025, "learning_rate": 2.5902588830267116e-06, "loss": 0.21805137395858765, "step": 4138 }, { "epoch": 1.0745067497403946, "grad_norm": 8.733766555786133, "learning_rate": 2.5893152747725094e-06, "loss": 0.1304543912410736, "step": 4139 }, { "epoch": 1.074766355140187, "grad_norm": 9.932709693908691, "learning_rate": 2.588371694923687e-06, "loss": 0.04279470071196556, "step": 4140 }, { "epoch": 1.0750259605399792, "grad_norm": 7.5706400871276855, "learning_rate": 2.5874281436470494e-06, "loss": 0.05389125645160675, "step": 4141 }, { "epoch": 1.0752855659397715, "grad_norm": 6.4072957038879395, "learning_rate": 2.586484621109393e-06, "loss": 0.18943648040294647, "step": 4142 }, { "epoch": 1.0755451713395638, "grad_norm": 8.292046546936035, "learning_rate": 2.585541127477511e-06, "loss": 0.13514277338981628, "step": 4143 }, { "epoch": 1.0758047767393562, "grad_norm": 6.1426682472229, "learning_rate": 2.5845976629181917e-06, "loss": 0.24475765228271484, "step": 4144 }, { "epoch": 1.0760643821391485, "grad_norm": 10.66236400604248, "learning_rate": 2.58365422759822e-06, "loss": 0.08217814564704895, "step": 4145 }, { "epoch": 1.0763239875389408, "grad_norm": 7.256027698516846, "learning_rate": 2.582710821684371e-06, "loss": 0.1934511363506317, "step": 4146 }, { "epoch": 1.076583592938733, "grad_norm": 7.686535358428955, "learning_rate": 2.5817674453434185e-06, "loss": 0.06992717832326889, "step": 4147 }, { "epoch": 1.0768431983385254, "grad_norm": 9.581968307495117, "learning_rate": 2.5808240987421295e-06, "loss": 0.17135657370090485, "step": 4148 }, { "epoch": 1.0771028037383177, "grad_norm": 8.361584663391113, "learning_rate": 2.579880782047267e-06, "loss": 0.10389703512191772, "step": 4149 }, { "epoch": 1.07736240913811, "grad_norm": 10.448714256286621, "learning_rate": 2.5789374954255864e-06, "loss": 0.1564045548439026, "step": 4150 }, { "epoch": 1.0776220145379023, "grad_norm": 10.038352012634277, "learning_rate": 2.5779942390438396e-06, "loss": 0.1309138983488083, "step": 4151 }, { "epoch": 1.0778816199376946, "grad_norm": 10.62409496307373, "learning_rate": 2.5770510130687726e-06, "loss": 0.07591385394334793, "step": 4152 }, { "epoch": 1.078141225337487, "grad_norm": 13.038423538208008, "learning_rate": 2.5761078176671275e-06, "loss": 0.025966666638851166, "step": 4153 }, { "epoch": 1.0784008307372794, "grad_norm": 8.558820724487305, "learning_rate": 2.5751646530056378e-06, "loss": 0.09799499809741974, "step": 4154 }, { "epoch": 1.0786604361370717, "grad_norm": 10.197175979614258, "learning_rate": 2.574221519251035e-06, "loss": 0.10801848769187927, "step": 4155 }, { "epoch": 1.078920041536864, "grad_norm": 13.259835243225098, "learning_rate": 2.5732784165700418e-06, "loss": 0.08215150237083435, "step": 4156 }, { "epoch": 1.0791796469366564, "grad_norm": 11.116984367370605, "learning_rate": 2.5723353451293793e-06, "loss": 0.13615673780441284, "step": 4157 }, { "epoch": 1.0794392523364487, "grad_norm": 8.524550437927246, "learning_rate": 2.571392305095759e-06, "loss": 0.0589294470846653, "step": 4158 }, { "epoch": 1.079698857736241, "grad_norm": 7.539168357849121, "learning_rate": 2.5704492966358897e-06, "loss": 0.2186492681503296, "step": 4159 }, { "epoch": 1.0799584631360333, "grad_norm": 13.100859642028809, "learning_rate": 2.569506319916474e-06, "loss": 0.09095481038093567, "step": 4160 }, { "epoch": 1.0802180685358256, "grad_norm": 10.211967468261719, "learning_rate": 2.5685633751042084e-06, "loss": 0.08670969307422638, "step": 4161 }, { "epoch": 1.0804776739356179, "grad_norm": 6.2189531326293945, "learning_rate": 2.5676204623657824e-06, "loss": 0.23307466506958008, "step": 4162 }, { "epoch": 1.0807372793354102, "grad_norm": 9.593592643737793, "learning_rate": 2.566677581867884e-06, "loss": 0.21393385529518127, "step": 4163 }, { "epoch": 1.0809968847352025, "grad_norm": 13.185276985168457, "learning_rate": 2.565734733777192e-06, "loss": 0.13907688856124878, "step": 4164 }, { "epoch": 1.0812564901349948, "grad_norm": 10.350434303283691, "learning_rate": 2.564791918260378e-06, "loss": 0.11407536268234253, "step": 4165 }, { "epoch": 1.0815160955347871, "grad_norm": 9.780478477478027, "learning_rate": 2.563849135484113e-06, "loss": 0.13765665888786316, "step": 4166 }, { "epoch": 1.0817757009345794, "grad_norm": 8.691566467285156, "learning_rate": 2.562906385615059e-06, "loss": 0.15833012759685516, "step": 4167 }, { "epoch": 1.0820353063343717, "grad_norm": 8.35718059539795, "learning_rate": 2.561963668819873e-06, "loss": 0.09477484226226807, "step": 4168 }, { "epoch": 1.082294911734164, "grad_norm": 8.295453071594238, "learning_rate": 2.5610209852652034e-06, "loss": 0.06068723648786545, "step": 4169 }, { "epoch": 1.0825545171339563, "grad_norm": 7.983356475830078, "learning_rate": 2.5600783351176966e-06, "loss": 0.18511801958084106, "step": 4170 }, { "epoch": 1.0828141225337486, "grad_norm": 7.041274547576904, "learning_rate": 2.559135718543992e-06, "loss": 0.12060848623514175, "step": 4171 }, { "epoch": 1.083073727933541, "grad_norm": 11.463306427001953, "learning_rate": 2.5581931357107226e-06, "loss": 0.08646164834499359, "step": 4172 }, { "epoch": 1.0833333333333333, "grad_norm": 5.802154541015625, "learning_rate": 2.5572505867845145e-06, "loss": 0.2387482076883316, "step": 4173 }, { "epoch": 1.0835929387331256, "grad_norm": 5.935656547546387, "learning_rate": 2.5563080719319892e-06, "loss": 0.23254942893981934, "step": 4174 }, { "epoch": 1.0838525441329179, "grad_norm": 7.249170780181885, "learning_rate": 2.5553655913197612e-06, "loss": 0.14859142899513245, "step": 4175 }, { "epoch": 1.0841121495327102, "grad_norm": 6.570275783538818, "learning_rate": 2.554423145114442e-06, "loss": 0.20737460255622864, "step": 4176 }, { "epoch": 1.0843717549325027, "grad_norm": 7.722807884216309, "learning_rate": 2.553480733482631e-06, "loss": 0.20114843547344208, "step": 4177 }, { "epoch": 1.084631360332295, "grad_norm": 13.359766006469727, "learning_rate": 2.5525383565909274e-06, "loss": 0.08982400596141815, "step": 4178 }, { "epoch": 1.0848909657320873, "grad_norm": 9.987220764160156, "learning_rate": 2.5515960146059204e-06, "loss": 0.07405328005552292, "step": 4179 }, { "epoch": 1.0851505711318796, "grad_norm": 11.553730964660645, "learning_rate": 2.5506537076941955e-06, "loss": 0.05080833286046982, "step": 4180 }, { "epoch": 1.085410176531672, "grad_norm": 11.702961921691895, "learning_rate": 2.5497114360223306e-06, "loss": 0.06781306862831116, "step": 4181 }, { "epoch": 1.0856697819314642, "grad_norm": 6.426751613616943, "learning_rate": 2.548769199756898e-06, "loss": 0.2493470162153244, "step": 4182 }, { "epoch": 1.0859293873312565, "grad_norm": 6.63654899597168, "learning_rate": 2.547826999064463e-06, "loss": 0.20347657799720764, "step": 4183 }, { "epoch": 1.0861889927310489, "grad_norm": 11.024768829345703, "learning_rate": 2.546884834111586e-06, "loss": 0.1481667160987854, "step": 4184 }, { "epoch": 1.0864485981308412, "grad_norm": 9.76480770111084, "learning_rate": 2.545942705064819e-06, "loss": 0.14204274117946625, "step": 4185 }, { "epoch": 1.0867082035306335, "grad_norm": 8.51330852508545, "learning_rate": 2.5450006120907095e-06, "loss": 0.1974559724330902, "step": 4186 }, { "epoch": 1.0869678089304258, "grad_norm": 10.557194709777832, "learning_rate": 2.544058555355798e-06, "loss": 0.0725337415933609, "step": 4187 }, { "epoch": 1.087227414330218, "grad_norm": 10.582982063293457, "learning_rate": 2.543116535026619e-06, "loss": 0.03562099486589432, "step": 4188 }, { "epoch": 1.0874870197300104, "grad_norm": 5.60026216506958, "learning_rate": 2.5421745512696988e-06, "loss": 0.24873726069927216, "step": 4189 }, { "epoch": 1.0877466251298027, "grad_norm": 7.533502101898193, "learning_rate": 2.54123260425156e-06, "loss": 0.23023006319999695, "step": 4190 }, { "epoch": 1.088006230529595, "grad_norm": 7.1524128913879395, "learning_rate": 2.540290694138717e-06, "loss": 0.1471824049949646, "step": 4191 }, { "epoch": 1.0882658359293873, "grad_norm": 6.860157012939453, "learning_rate": 2.5393488210976764e-06, "loss": 0.17802661657333374, "step": 4192 }, { "epoch": 1.0885254413291796, "grad_norm": 9.399867057800293, "learning_rate": 2.5384069852949415e-06, "loss": 0.04538197070360184, "step": 4193 }, { "epoch": 1.088785046728972, "grad_norm": 7.807392120361328, "learning_rate": 2.537465186897006e-06, "loss": 0.09047764539718628, "step": 4194 }, { "epoch": 1.0890446521287642, "grad_norm": 7.481293201446533, "learning_rate": 2.5365234260703607e-06, "loss": 0.11122186481952667, "step": 4195 }, { "epoch": 1.0893042575285565, "grad_norm": 10.07336139678955, "learning_rate": 2.5355817029814844e-06, "loss": 0.10426648706197739, "step": 4196 }, { "epoch": 1.0895638629283488, "grad_norm": 9.229633331298828, "learning_rate": 2.534640017796854e-06, "loss": 0.21400628983974457, "step": 4197 }, { "epoch": 1.0898234683281411, "grad_norm": 9.741889953613281, "learning_rate": 2.533698370682937e-06, "loss": 0.06278694421052933, "step": 4198 }, { "epoch": 1.0900830737279334, "grad_norm": 8.90205192565918, "learning_rate": 2.5327567618061965e-06, "loss": 0.162023663520813, "step": 4199 }, { "epoch": 1.0903426791277258, "grad_norm": 5.7953901290893555, "learning_rate": 2.5318151913330857e-06, "loss": 0.29756593704223633, "step": 4200 }, { "epoch": 1.090602284527518, "grad_norm": 8.908915519714355, "learning_rate": 2.5308736594300522e-06, "loss": 0.1065310537815094, "step": 4201 }, { "epoch": 1.0908618899273106, "grad_norm": 12.195195198059082, "learning_rate": 2.529932166263539e-06, "loss": 0.12353839725255966, "step": 4202 }, { "epoch": 1.091121495327103, "grad_norm": 7.265902042388916, "learning_rate": 2.5289907119999814e-06, "loss": 0.17027312517166138, "step": 4203 }, { "epoch": 1.0913811007268952, "grad_norm": 10.94294548034668, "learning_rate": 2.528049296805804e-06, "loss": 0.1214001327753067, "step": 4204 }, { "epoch": 1.0916407061266875, "grad_norm": 11.471212387084961, "learning_rate": 2.5271079208474288e-06, "loss": 0.20022237300872803, "step": 4205 }, { "epoch": 1.0919003115264798, "grad_norm": 9.435812950134277, "learning_rate": 2.5261665842912696e-06, "loss": 0.038524284958839417, "step": 4206 }, { "epoch": 1.0921599169262721, "grad_norm": 9.607681274414062, "learning_rate": 2.525225287303735e-06, "loss": 0.07973246276378632, "step": 4207 }, { "epoch": 1.0924195223260644, "grad_norm": 8.951681137084961, "learning_rate": 2.5242840300512205e-06, "loss": 0.0738719254732132, "step": 4208 }, { "epoch": 1.0926791277258567, "grad_norm": 8.398626327514648, "learning_rate": 2.5233428127001226e-06, "loss": 0.12113191932439804, "step": 4209 }, { "epoch": 1.092938733125649, "grad_norm": 9.065825462341309, "learning_rate": 2.522401635416825e-06, "loss": 0.07057447731494904, "step": 4210 }, { "epoch": 1.0931983385254413, "grad_norm": 9.00382137298584, "learning_rate": 2.5214604983677084e-06, "loss": 0.16149379312992096, "step": 4211 }, { "epoch": 1.0934579439252337, "grad_norm": 9.466629028320312, "learning_rate": 2.5205194017191414e-06, "loss": 0.15955770015716553, "step": 4212 }, { "epoch": 1.093717549325026, "grad_norm": 9.916325569152832, "learning_rate": 2.5195783456374902e-06, "loss": 0.0827646553516388, "step": 4213 }, { "epoch": 1.0939771547248183, "grad_norm": 11.382824897766113, "learning_rate": 2.518637330289111e-06, "loss": 0.12489672750234604, "step": 4214 }, { "epoch": 1.0942367601246106, "grad_norm": 9.527154922485352, "learning_rate": 2.517696355840355e-06, "loss": 0.0752173364162445, "step": 4215 }, { "epoch": 1.0944963655244029, "grad_norm": 6.148563861846924, "learning_rate": 2.5167554224575643e-06, "loss": 0.21085716784000397, "step": 4216 }, { "epoch": 1.0947559709241952, "grad_norm": 8.28048038482666, "learning_rate": 2.5158145303070737e-06, "loss": 0.15693551301956177, "step": 4217 }, { "epoch": 1.0950155763239875, "grad_norm": 14.447554588317871, "learning_rate": 2.5148736795552125e-06, "loss": 0.07262711226940155, "step": 4218 }, { "epoch": 1.0952751817237798, "grad_norm": 10.720559120178223, "learning_rate": 2.5139328703683007e-06, "loss": 0.18021756410598755, "step": 4219 }, { "epoch": 1.095534787123572, "grad_norm": 8.634256362915039, "learning_rate": 2.5129921029126524e-06, "loss": 0.2165743112564087, "step": 4220 }, { "epoch": 1.0957943925233644, "grad_norm": 8.679244041442871, "learning_rate": 2.5120513773545737e-06, "loss": 0.06513723731040955, "step": 4221 }, { "epoch": 1.0960539979231567, "grad_norm": 8.049880027770996, "learning_rate": 2.511110693860363e-06, "loss": 0.09234391152858734, "step": 4222 }, { "epoch": 1.096313603322949, "grad_norm": 6.1361494064331055, "learning_rate": 2.510170052596312e-06, "loss": 0.06064803898334503, "step": 4223 }, { "epoch": 1.0965732087227413, "grad_norm": 8.657954216003418, "learning_rate": 2.5092294537287038e-06, "loss": 0.171284019947052, "step": 4224 }, { "epoch": 1.0968328141225339, "grad_norm": 6.24765682220459, "learning_rate": 2.5082888974238155e-06, "loss": 0.19365015625953674, "step": 4225 }, { "epoch": 1.0970924195223262, "grad_norm": 9.335380554199219, "learning_rate": 2.5073483838479164e-06, "loss": 0.10238956660032272, "step": 4226 }, { "epoch": 1.0973520249221185, "grad_norm": 8.321731567382812, "learning_rate": 2.5064079131672658e-06, "loss": 0.042816076427698135, "step": 4227 }, { "epoch": 1.0976116303219108, "grad_norm": 3.5317206382751465, "learning_rate": 2.5054674855481198e-06, "loss": 0.024104012176394463, "step": 4228 }, { "epoch": 1.097871235721703, "grad_norm": 8.728548049926758, "learning_rate": 2.5045271011567225e-06, "loss": 0.08279965817928314, "step": 4229 }, { "epoch": 1.0981308411214954, "grad_norm": 10.459108352661133, "learning_rate": 2.5035867601593145e-06, "loss": 0.1781245619058609, "step": 4230 }, { "epoch": 1.0983904465212877, "grad_norm": 12.313777923583984, "learning_rate": 2.5026464627221233e-06, "loss": 0.07065972685813904, "step": 4231 }, { "epoch": 1.09865005192108, "grad_norm": 12.888325691223145, "learning_rate": 2.501706209011374e-06, "loss": 0.05525656417012215, "step": 4232 }, { "epoch": 1.0989096573208723, "grad_norm": 12.000150680541992, "learning_rate": 2.5007659991932826e-06, "loss": 0.05776550620794296, "step": 4233 }, { "epoch": 1.0991692627206646, "grad_norm": 10.100224494934082, "learning_rate": 2.4998258334340563e-06, "loss": 0.06612539291381836, "step": 4234 }, { "epoch": 1.099428868120457, "grad_norm": 7.402202129364014, "learning_rate": 2.498885711899894e-06, "loss": 0.07225066423416138, "step": 4235 }, { "epoch": 1.0996884735202492, "grad_norm": 8.068923950195312, "learning_rate": 2.497945634756987e-06, "loss": 0.18583348393440247, "step": 4236 }, { "epoch": 1.0999480789200415, "grad_norm": 5.293579578399658, "learning_rate": 2.497005602171522e-06, "loss": 0.26564955711364746, "step": 4237 }, { "epoch": 1.1002076843198338, "grad_norm": 10.947559356689453, "learning_rate": 2.4960656143096732e-06, "loss": 0.07907657325267792, "step": 4238 }, { "epoch": 1.1004672897196262, "grad_norm": 7.037770748138428, "learning_rate": 2.4951256713376092e-06, "loss": 0.042508065700531006, "step": 4239 }, { "epoch": 1.1007268951194185, "grad_norm": 5.352993011474609, "learning_rate": 2.494185773421491e-06, "loss": 0.29301917552948, "step": 4240 }, { "epoch": 1.1009865005192108, "grad_norm": 11.185586929321289, "learning_rate": 2.4932459207274694e-06, "loss": 0.07538997381925583, "step": 4241 }, { "epoch": 1.101246105919003, "grad_norm": 8.356466293334961, "learning_rate": 2.4923061134216927e-06, "loss": 0.15886107087135315, "step": 4242 }, { "epoch": 1.1015057113187954, "grad_norm": 10.561235427856445, "learning_rate": 2.4913663516702927e-06, "loss": 0.11078119277954102, "step": 4243 }, { "epoch": 1.1017653167185877, "grad_norm": 9.806394577026367, "learning_rate": 2.4904266356394003e-06, "loss": 0.06968227028846741, "step": 4244 }, { "epoch": 1.10202492211838, "grad_norm": 7.305567264556885, "learning_rate": 2.4894869654951353e-06, "loss": 0.10051193833351135, "step": 4245 }, { "epoch": 1.1022845275181723, "grad_norm": 5.424690246582031, "learning_rate": 2.48854734140361e-06, "loss": 0.05291542410850525, "step": 4246 }, { "epoch": 1.1025441329179646, "grad_norm": 7.187412261962891, "learning_rate": 2.4876077635309283e-06, "loss": 0.13155075907707214, "step": 4247 }, { "epoch": 1.102803738317757, "grad_norm": 9.98573112487793, "learning_rate": 2.4866682320431858e-06, "loss": 0.12894973158836365, "step": 4248 }, { "epoch": 1.1030633437175492, "grad_norm": 5.64347505569458, "learning_rate": 2.4857287471064707e-06, "loss": 0.2385077178478241, "step": 4249 }, { "epoch": 1.1033229491173417, "grad_norm": 8.674264907836914, "learning_rate": 2.484789308886862e-06, "loss": 0.04473172128200531, "step": 4250 }, { "epoch": 1.103582554517134, "grad_norm": 11.691070556640625, "learning_rate": 2.4838499175504303e-06, "loss": 0.09069560468196869, "step": 4251 }, { "epoch": 1.1038421599169264, "grad_norm": 8.823095321655273, "learning_rate": 2.4829105732632397e-06, "loss": 0.16723349690437317, "step": 4252 }, { "epoch": 1.1041017653167187, "grad_norm": 9.571839332580566, "learning_rate": 2.4819712761913444e-06, "loss": 0.11230012029409409, "step": 4253 }, { "epoch": 1.104361370716511, "grad_norm": 11.331351280212402, "learning_rate": 2.48103202650079e-06, "loss": 0.09189844131469727, "step": 4254 }, { "epoch": 1.1046209761163033, "grad_norm": 8.747127532958984, "learning_rate": 2.480092824357615e-06, "loss": 0.06771963834762573, "step": 4255 }, { "epoch": 1.1048805815160956, "grad_norm": 10.37065601348877, "learning_rate": 2.4791536699278487e-06, "loss": 0.097612664103508, "step": 4256 }, { "epoch": 1.105140186915888, "grad_norm": 10.007709503173828, "learning_rate": 2.478214563377512e-06, "loss": 0.09113965928554535, "step": 4257 }, { "epoch": 1.1053997923156802, "grad_norm": 5.877170562744141, "learning_rate": 2.4772755048726172e-06, "loss": 0.2394014149904251, "step": 4258 }, { "epoch": 1.1056593977154725, "grad_norm": 8.636847496032715, "learning_rate": 2.4763364945791685e-06, "loss": 0.16763395071029663, "step": 4259 }, { "epoch": 1.1059190031152648, "grad_norm": 7.955869197845459, "learning_rate": 2.475397532663161e-06, "loss": 0.1228102520108223, "step": 4260 }, { "epoch": 1.1061786085150571, "grad_norm": 9.444487571716309, "learning_rate": 2.474458619290584e-06, "loss": 0.08341038227081299, "step": 4261 }, { "epoch": 1.1064382139148494, "grad_norm": 6.530734062194824, "learning_rate": 2.4735197546274125e-06, "loss": 0.03949883580207825, "step": 4262 }, { "epoch": 1.1066978193146417, "grad_norm": 5.147651195526123, "learning_rate": 2.4725809388396175e-06, "loss": 0.013774847611784935, "step": 4263 }, { "epoch": 1.106957424714434, "grad_norm": 9.624008178710938, "learning_rate": 2.4716421720931616e-06, "loss": 0.07651134580373764, "step": 4264 }, { "epoch": 1.1072170301142263, "grad_norm": 6.081305503845215, "learning_rate": 2.4707034545539963e-06, "loss": 0.20288632810115814, "step": 4265 }, { "epoch": 1.1074766355140186, "grad_norm": 9.064093589782715, "learning_rate": 2.4697647863880648e-06, "loss": 0.17896491289138794, "step": 4266 }, { "epoch": 1.107736240913811, "grad_norm": 7.889888763427734, "learning_rate": 2.468826167761301e-06, "loss": 0.24152301251888275, "step": 4267 }, { "epoch": 1.1079958463136033, "grad_norm": 5.814798831939697, "learning_rate": 2.4678875988396344e-06, "loss": 0.222670778632164, "step": 4268 }, { "epoch": 1.1082554517133956, "grad_norm": 6.066877365112305, "learning_rate": 2.466949079788981e-06, "loss": 0.24618104100227356, "step": 4269 }, { "epoch": 1.1085150571131879, "grad_norm": 8.733928680419922, "learning_rate": 2.4660106107752485e-06, "loss": 0.06078425794839859, "step": 4270 }, { "epoch": 1.1087746625129802, "grad_norm": 15.754413604736328, "learning_rate": 2.4650721919643376e-06, "loss": 0.13983871042728424, "step": 4271 }, { "epoch": 1.1090342679127725, "grad_norm": 9.214346885681152, "learning_rate": 2.46413382352214e-06, "loss": 0.08303932845592499, "step": 4272 }, { "epoch": 1.109293873312565, "grad_norm": 8.16135311126709, "learning_rate": 2.463195505614536e-06, "loss": 0.09740376472473145, "step": 4273 }, { "epoch": 1.1095534787123573, "grad_norm": 10.294439315795898, "learning_rate": 2.4622572384074e-06, "loss": 0.1018574982881546, "step": 4274 }, { "epoch": 1.1098130841121496, "grad_norm": 6.444086074829102, "learning_rate": 2.4613190220665957e-06, "loss": 0.2764744758605957, "step": 4275 }, { "epoch": 1.110072689511942, "grad_norm": 5.595573902130127, "learning_rate": 2.4603808567579787e-06, "loss": 0.2361719012260437, "step": 4276 }, { "epoch": 1.1103322949117342, "grad_norm": 8.131183624267578, "learning_rate": 2.4594427426473944e-06, "loss": 0.1149304211139679, "step": 4277 }, { "epoch": 1.1105919003115265, "grad_norm": 8.566766738891602, "learning_rate": 2.45850467990068e-06, "loss": 0.14416900277137756, "step": 4278 }, { "epoch": 1.1108515057113189, "grad_norm": 6.151986122131348, "learning_rate": 2.457566668683664e-06, "loss": 0.24258631467819214, "step": 4279 }, { "epoch": 1.1111111111111112, "grad_norm": 11.64254093170166, "learning_rate": 2.456628709162166e-06, "loss": 0.06872229278087616, "step": 4280 }, { "epoch": 1.1113707165109035, "grad_norm": 6.8532586097717285, "learning_rate": 2.455690801501994e-06, "loss": 0.2380666434764862, "step": 4281 }, { "epoch": 1.1116303219106958, "grad_norm": 8.717697143554688, "learning_rate": 2.4547529458689496e-06, "loss": 0.05317937955260277, "step": 4282 }, { "epoch": 1.111889927310488, "grad_norm": 7.886569023132324, "learning_rate": 2.4538151424288246e-06, "loss": 0.09778796136379242, "step": 4283 }, { "epoch": 1.1121495327102804, "grad_norm": 8.686994552612305, "learning_rate": 2.452877391347401e-06, "loss": 0.04051807150244713, "step": 4284 }, { "epoch": 1.1124091381100727, "grad_norm": 9.453154563903809, "learning_rate": 2.4519396927904505e-06, "loss": 0.178780198097229, "step": 4285 }, { "epoch": 1.112668743509865, "grad_norm": 8.524458885192871, "learning_rate": 2.4510020469237376e-06, "loss": 0.07344581186771393, "step": 4286 }, { "epoch": 1.1129283489096573, "grad_norm": 7.616153240203857, "learning_rate": 2.450064453913017e-06, "loss": 0.2216108739376068, "step": 4287 }, { "epoch": 1.1131879543094496, "grad_norm": 7.989267826080322, "learning_rate": 2.449126913924034e-06, "loss": 0.19694474339485168, "step": 4288 }, { "epoch": 1.113447559709242, "grad_norm": 14.374603271484375, "learning_rate": 2.4481894271225225e-06, "loss": 0.09107036888599396, "step": 4289 }, { "epoch": 1.1137071651090342, "grad_norm": 13.027379035949707, "learning_rate": 2.44725199367421e-06, "loss": 0.09828582406044006, "step": 4290 }, { "epoch": 1.1139667705088265, "grad_norm": 9.044899940490723, "learning_rate": 2.4463146137448127e-06, "loss": 0.20255717635154724, "step": 4291 }, { "epoch": 1.1142263759086188, "grad_norm": 11.808688163757324, "learning_rate": 2.4453772875000398e-06, "loss": 0.18133631348609924, "step": 4292 }, { "epoch": 1.1144859813084111, "grad_norm": 6.6843719482421875, "learning_rate": 2.444440015105586e-06, "loss": 0.021405421197414398, "step": 4293 }, { "epoch": 1.1147455867082035, "grad_norm": 7.612528324127197, "learning_rate": 2.4435027967271413e-06, "loss": 0.23913758993148804, "step": 4294 }, { "epoch": 1.1150051921079958, "grad_norm": 10.51783561706543, "learning_rate": 2.442565632530384e-06, "loss": 0.10685721784830093, "step": 4295 }, { "epoch": 1.115264797507788, "grad_norm": 9.497872352600098, "learning_rate": 2.441628522680985e-06, "loss": 0.06362536549568176, "step": 4296 }, { "epoch": 1.1155244029075804, "grad_norm": 8.319223403930664, "learning_rate": 2.4406914673446012e-06, "loss": 0.17421936988830566, "step": 4297 }, { "epoch": 1.1157840083073727, "grad_norm": 6.270987033843994, "learning_rate": 2.4397544666868837e-06, "loss": 0.27198338508605957, "step": 4298 }, { "epoch": 1.1160436137071652, "grad_norm": 8.537878036499023, "learning_rate": 2.438817520873474e-06, "loss": 0.06066314876079559, "step": 4299 }, { "epoch": 1.1163032191069575, "grad_norm": 9.283222198486328, "learning_rate": 2.4378806300700003e-06, "loss": 0.12396667897701263, "step": 4300 }, { "epoch": 1.1165628245067498, "grad_norm": 7.053799152374268, "learning_rate": 2.436943794442085e-06, "loss": 0.14471574127674103, "step": 4301 }, { "epoch": 1.1168224299065421, "grad_norm": 9.813641548156738, "learning_rate": 2.436007014155339e-06, "loss": 0.17860060930252075, "step": 4302 }, { "epoch": 1.1170820353063344, "grad_norm": 14.164920806884766, "learning_rate": 2.435070289375363e-06, "loss": 0.05967768654227257, "step": 4303 }, { "epoch": 1.1173416407061267, "grad_norm": 8.110568046569824, "learning_rate": 2.434133620267749e-06, "loss": 0.17829015851020813, "step": 4304 }, { "epoch": 1.117601246105919, "grad_norm": 5.876295566558838, "learning_rate": 2.433197006998078e-06, "loss": 0.22230666875839233, "step": 4305 }, { "epoch": 1.1178608515057114, "grad_norm": 8.037867546081543, "learning_rate": 2.432260449731923e-06, "loss": 0.04618462175130844, "step": 4306 }, { "epoch": 1.1181204569055037, "grad_norm": 8.524476051330566, "learning_rate": 2.431323948634846e-06, "loss": 0.1316252052783966, "step": 4307 }, { "epoch": 1.118380062305296, "grad_norm": 10.477384567260742, "learning_rate": 2.4303875038723975e-06, "loss": 0.035399943590164185, "step": 4308 }, { "epoch": 1.1186396677050883, "grad_norm": 6.632435321807861, "learning_rate": 2.429451115610119e-06, "loss": 0.03649892285466194, "step": 4309 }, { "epoch": 1.1188992731048806, "grad_norm": 6.738088130950928, "learning_rate": 2.428514784013545e-06, "loss": 0.2429817020893097, "step": 4310 }, { "epoch": 1.1191588785046729, "grad_norm": 10.244743347167969, "learning_rate": 2.4275785092481965e-06, "loss": 0.0511336587369442, "step": 4311 }, { "epoch": 1.1194184839044652, "grad_norm": 7.959985733032227, "learning_rate": 2.426642291479584e-06, "loss": 0.09889902174472809, "step": 4312 }, { "epoch": 1.1196780893042575, "grad_norm": 14.48698902130127, "learning_rate": 2.4257061308732104e-06, "loss": 0.1368238478899002, "step": 4313 }, { "epoch": 1.1199376947040498, "grad_norm": 7.3690996170043945, "learning_rate": 2.424770027594568e-06, "loss": 0.10722985118627548, "step": 4314 }, { "epoch": 1.120197300103842, "grad_norm": 10.625116348266602, "learning_rate": 2.4238339818091383e-06, "loss": 0.07901298999786377, "step": 4315 }, { "epoch": 1.1204569055036344, "grad_norm": 9.494133949279785, "learning_rate": 2.422897993682392e-06, "loss": 0.20216763019561768, "step": 4316 }, { "epoch": 1.1207165109034267, "grad_norm": 10.717156410217285, "learning_rate": 2.421962063379791e-06, "loss": 0.1723478138446808, "step": 4317 }, { "epoch": 1.120976116303219, "grad_norm": 12.847150802612305, "learning_rate": 2.421026191066785e-06, "loss": 0.11437337100505829, "step": 4318 }, { "epoch": 1.1212357217030113, "grad_norm": 11.84189224243164, "learning_rate": 2.4200903769088174e-06, "loss": 0.08312978595495224, "step": 4319 }, { "epoch": 1.1214953271028036, "grad_norm": 9.299549102783203, "learning_rate": 2.419154621071317e-06, "loss": 0.10900309681892395, "step": 4320 }, { "epoch": 1.1217549325025962, "grad_norm": 9.01691722869873, "learning_rate": 2.4182189237197033e-06, "loss": 0.1183132529258728, "step": 4321 }, { "epoch": 1.1220145379023885, "grad_norm": 5.340919494628906, "learning_rate": 2.4172832850193877e-06, "loss": 0.23614725470542908, "step": 4322 }, { "epoch": 1.1222741433021808, "grad_norm": 6.664209842681885, "learning_rate": 2.41634770513577e-06, "loss": 0.1681775152683258, "step": 4323 }, { "epoch": 1.122533748701973, "grad_norm": 4.919881820678711, "learning_rate": 2.4154121842342363e-06, "loss": 0.23953941464424133, "step": 4324 }, { "epoch": 1.1227933541017654, "grad_norm": 10.475112915039062, "learning_rate": 2.414476722480169e-06, "loss": 0.08044375479221344, "step": 4325 }, { "epoch": 1.1230529595015577, "grad_norm": 9.613914489746094, "learning_rate": 2.413541320038934e-06, "loss": 0.08207095414400101, "step": 4326 }, { "epoch": 1.12331256490135, "grad_norm": 8.585356712341309, "learning_rate": 2.4126059770758907e-06, "loss": 0.13170596957206726, "step": 4327 }, { "epoch": 1.1235721703011423, "grad_norm": 5.606196880340576, "learning_rate": 2.4116706937563848e-06, "loss": 0.28824204206466675, "step": 4328 }, { "epoch": 1.1238317757009346, "grad_norm": 7.964168071746826, "learning_rate": 2.4107354702457524e-06, "loss": 0.0856998860836029, "step": 4329 }, { "epoch": 1.124091381100727, "grad_norm": 10.90018081665039, "learning_rate": 2.409800306709323e-06, "loss": 0.17014095187187195, "step": 4330 }, { "epoch": 1.1243509865005192, "grad_norm": 8.552375793457031, "learning_rate": 2.4088652033124086e-06, "loss": 0.11898663640022278, "step": 4331 }, { "epoch": 1.1246105919003115, "grad_norm": 5.527297496795654, "learning_rate": 2.407930160220315e-06, "loss": 0.26588624715805054, "step": 4332 }, { "epoch": 1.1248701973001038, "grad_norm": 10.99367618560791, "learning_rate": 2.406995177598337e-06, "loss": 0.06819070130586624, "step": 4333 }, { "epoch": 1.1251298026998962, "grad_norm": 5.424394130706787, "learning_rate": 2.4060602556117578e-06, "loss": 0.24370601773262024, "step": 4334 }, { "epoch": 1.1253894080996885, "grad_norm": 5.944718360900879, "learning_rate": 2.40512539442585e-06, "loss": 0.016544930636882782, "step": 4335 }, { "epoch": 1.1256490134994808, "grad_norm": 6.929652214050293, "learning_rate": 2.404190594205876e-06, "loss": 0.1952010691165924, "step": 4336 }, { "epoch": 1.125908618899273, "grad_norm": 8.201537132263184, "learning_rate": 2.4032558551170875e-06, "loss": 0.20979613065719604, "step": 4337 }, { "epoch": 1.1261682242990654, "grad_norm": 15.150348663330078, "learning_rate": 2.402321177324724e-06, "loss": 0.0468384325504303, "step": 4338 }, { "epoch": 1.1264278296988577, "grad_norm": 12.839938163757324, "learning_rate": 2.4013865609940156e-06, "loss": 0.15668445825576782, "step": 4339 }, { "epoch": 1.12668743509865, "grad_norm": 8.204314231872559, "learning_rate": 2.400452006290181e-06, "loss": 0.1096498966217041, "step": 4340 }, { "epoch": 1.1269470404984423, "grad_norm": 8.363619804382324, "learning_rate": 2.399517513378428e-06, "loss": 0.08391550183296204, "step": 4341 }, { "epoch": 1.1272066458982346, "grad_norm": 10.311180114746094, "learning_rate": 2.398583082423954e-06, "loss": 0.12945066392421722, "step": 4342 }, { "epoch": 1.127466251298027, "grad_norm": 8.064961433410645, "learning_rate": 2.3976487135919444e-06, "loss": 0.12585458159446716, "step": 4343 }, { "epoch": 1.1277258566978192, "grad_norm": 7.194217205047607, "learning_rate": 2.3967144070475746e-06, "loss": 0.062461283057928085, "step": 4344 }, { "epoch": 1.1279854620976115, "grad_norm": 8.690080642700195, "learning_rate": 2.395780162956008e-06, "loss": 0.053551457822322845, "step": 4345 }, { "epoch": 1.1282450674974038, "grad_norm": 10.000402450561523, "learning_rate": 2.3948459814823986e-06, "loss": 0.05871224403381348, "step": 4346 }, { "epoch": 1.1285046728971961, "grad_norm": 10.06474494934082, "learning_rate": 2.3939118627918874e-06, "loss": 0.10566592216491699, "step": 4347 }, { "epoch": 1.1287642782969887, "grad_norm": 8.475969314575195, "learning_rate": 2.3929778070496055e-06, "loss": 0.05419313535094261, "step": 4348 }, { "epoch": 1.129023883696781, "grad_norm": 11.11082935333252, "learning_rate": 2.3920438144206726e-06, "loss": 0.0939454436302185, "step": 4349 }, { "epoch": 1.1292834890965733, "grad_norm": 7.341240882873535, "learning_rate": 2.3911098850701975e-06, "loss": 0.20909926295280457, "step": 4350 }, { "epoch": 1.1295430944963656, "grad_norm": 9.418769836425781, "learning_rate": 2.3901760191632774e-06, "loss": 0.052243687212467194, "step": 4351 }, { "epoch": 1.129802699896158, "grad_norm": 11.080314636230469, "learning_rate": 2.389242216864997e-06, "loss": 0.023488620296120644, "step": 4352 }, { "epoch": 1.1300623052959502, "grad_norm": 8.191865921020508, "learning_rate": 2.3883084783404337e-06, "loss": 0.2817266583442688, "step": 4353 }, { "epoch": 1.1303219106957425, "grad_norm": 6.64168119430542, "learning_rate": 2.38737480375465e-06, "loss": 0.28036320209503174, "step": 4354 }, { "epoch": 1.1305815160955348, "grad_norm": 10.902337074279785, "learning_rate": 2.3864411932726967e-06, "loss": 0.10693906992673874, "step": 4355 }, { "epoch": 1.1308411214953271, "grad_norm": 9.99188232421875, "learning_rate": 2.3855076470596165e-06, "loss": 0.023916330188512802, "step": 4356 }, { "epoch": 1.1311007268951194, "grad_norm": 9.247564315795898, "learning_rate": 2.3845741652804393e-06, "loss": 0.033311646431684494, "step": 4357 }, { "epoch": 1.1313603322949117, "grad_norm": 8.36050796508789, "learning_rate": 2.3836407481001823e-06, "loss": 0.16901762783527374, "step": 4358 }, { "epoch": 1.131619937694704, "grad_norm": 8.828373908996582, "learning_rate": 2.3827073956838515e-06, "loss": 0.014692405238747597, "step": 4359 }, { "epoch": 1.1318795430944963, "grad_norm": 7.87807559967041, "learning_rate": 2.3817741081964433e-06, "loss": 0.21232450008392334, "step": 4360 }, { "epoch": 1.1321391484942886, "grad_norm": 9.278544425964355, "learning_rate": 2.3808408858029437e-06, "loss": 0.17724278569221497, "step": 4361 }, { "epoch": 1.132398753894081, "grad_norm": 5.307327747344971, "learning_rate": 2.379907728668321e-06, "loss": 0.024645280092954636, "step": 4362 }, { "epoch": 1.1326583592938733, "grad_norm": 8.740500450134277, "learning_rate": 2.378974636957538e-06, "loss": 0.06555502116680145, "step": 4363 }, { "epoch": 1.1329179646936656, "grad_norm": 7.714968204498291, "learning_rate": 2.3780416108355433e-06, "loss": 0.2078256607055664, "step": 4364 }, { "epoch": 1.1331775700934579, "grad_norm": 7.582730770111084, "learning_rate": 2.3771086504672762e-06, "loss": 0.11645714193582535, "step": 4365 }, { "epoch": 1.1334371754932502, "grad_norm": 11.310471534729004, "learning_rate": 2.3761757560176614e-06, "loss": 0.03930695727467537, "step": 4366 }, { "epoch": 1.1336967808930425, "grad_norm": 9.924324989318848, "learning_rate": 2.3752429276516132e-06, "loss": 0.13668161630630493, "step": 4367 }, { "epoch": 1.1339563862928348, "grad_norm": 7.968648910522461, "learning_rate": 2.3743101655340346e-06, "loss": 0.21755065023899078, "step": 4368 }, { "epoch": 1.1342159916926273, "grad_norm": 5.961074352264404, "learning_rate": 2.3733774698298173e-06, "loss": 0.26647546887397766, "step": 4369 }, { "epoch": 1.1344755970924196, "grad_norm": 6.483684539794922, "learning_rate": 2.3724448407038386e-06, "loss": 0.022471968084573746, "step": 4370 }, { "epoch": 1.134735202492212, "grad_norm": 10.15463924407959, "learning_rate": 2.371512278320968e-06, "loss": 0.06880344450473785, "step": 4371 }, { "epoch": 1.1349948078920042, "grad_norm": 16.21593475341797, "learning_rate": 2.3705797828460596e-06, "loss": 0.12008152902126312, "step": 4372 }, { "epoch": 1.1352544132917965, "grad_norm": 9.207362174987793, "learning_rate": 2.369647354443959e-06, "loss": 0.14414486289024353, "step": 4373 }, { "epoch": 1.1355140186915889, "grad_norm": 10.362761497497559, "learning_rate": 2.3687149932794967e-06, "loss": 0.09054504334926605, "step": 4374 }, { "epoch": 1.1357736240913812, "grad_norm": 8.738804817199707, "learning_rate": 2.3677826995174935e-06, "loss": 0.19365863502025604, "step": 4375 }, { "epoch": 1.1360332294911735, "grad_norm": 9.522417068481445, "learning_rate": 2.366850473322757e-06, "loss": 0.03507813438773155, "step": 4376 }, { "epoch": 1.1362928348909658, "grad_norm": 9.065218925476074, "learning_rate": 2.3659183148600847e-06, "loss": 0.17934992909431458, "step": 4377 }, { "epoch": 1.136552440290758, "grad_norm": 5.285287857055664, "learning_rate": 2.3649862242942595e-06, "loss": 0.26595255732536316, "step": 4378 }, { "epoch": 1.1368120456905504, "grad_norm": 7.008444786071777, "learning_rate": 2.364054201790054e-06, "loss": 0.18849296867847443, "step": 4379 }, { "epoch": 1.1370716510903427, "grad_norm": 7.006943702697754, "learning_rate": 2.363122247512229e-06, "loss": 0.24363932013511658, "step": 4380 }, { "epoch": 1.137331256490135, "grad_norm": 10.782236099243164, "learning_rate": 2.3621903616255322e-06, "loss": 0.09612654149532318, "step": 4381 }, { "epoch": 1.1375908618899273, "grad_norm": 8.710097312927246, "learning_rate": 2.3612585442946994e-06, "loss": 0.02531168982386589, "step": 4382 }, { "epoch": 1.1378504672897196, "grad_norm": 9.595948219299316, "learning_rate": 2.3603267956844555e-06, "loss": 0.19458431005477905, "step": 4383 }, { "epoch": 1.138110072689512, "grad_norm": 7.824227809906006, "learning_rate": 2.3593951159595125e-06, "loss": 0.16167503595352173, "step": 4384 }, { "epoch": 1.1383696780893042, "grad_norm": 8.441701889038086, "learning_rate": 2.358463505284568e-06, "loss": 0.17968660593032837, "step": 4385 }, { "epoch": 1.1386292834890965, "grad_norm": 10.844616889953613, "learning_rate": 2.3575319638243103e-06, "loss": 0.13258162140846252, "step": 4386 }, { "epoch": 1.1388888888888888, "grad_norm": 13.251023292541504, "learning_rate": 2.3566004917434165e-06, "loss": 0.06761302053928375, "step": 4387 }, { "epoch": 1.1391484942886811, "grad_norm": 11.167089462280273, "learning_rate": 2.3556690892065487e-06, "loss": 0.031022459268569946, "step": 4388 }, { "epoch": 1.1394080996884735, "grad_norm": 6.996865749359131, "learning_rate": 2.354737756378355e-06, "loss": 0.21774913370609283, "step": 4389 }, { "epoch": 1.1396677050882658, "grad_norm": 5.123459815979004, "learning_rate": 2.353806493423476e-06, "loss": 0.23028185963630676, "step": 4390 }, { "epoch": 1.139927310488058, "grad_norm": 8.407901763916016, "learning_rate": 2.352875300506538e-06, "loss": 0.08203453570604324, "step": 4391 }, { "epoch": 1.1401869158878504, "grad_norm": 9.020892143249512, "learning_rate": 2.351944177792155e-06, "loss": 0.16774176061153412, "step": 4392 }, { "epoch": 1.1404465212876427, "grad_norm": 4.859854221343994, "learning_rate": 2.3510131254449253e-06, "loss": 0.24542298913002014, "step": 4393 }, { "epoch": 1.140706126687435, "grad_norm": 5.615849018096924, "learning_rate": 2.35008214362944e-06, "loss": 0.21353858709335327, "step": 4394 }, { "epoch": 1.1409657320872273, "grad_norm": 6.8512372970581055, "learning_rate": 2.349151232510274e-06, "loss": 0.030032681301236153, "step": 4395 }, { "epoch": 1.1412253374870198, "grad_norm": 8.630081176757812, "learning_rate": 2.3482203922519937e-06, "loss": 0.14035499095916748, "step": 4396 }, { "epoch": 1.1414849428868121, "grad_norm": 6.932327747344971, "learning_rate": 2.3472896230191473e-06, "loss": 0.13645242154598236, "step": 4397 }, { "epoch": 1.1417445482866044, "grad_norm": 13.219377517700195, "learning_rate": 2.3463589249762747e-06, "loss": 0.06571807712316513, "step": 4398 }, { "epoch": 1.1420041536863967, "grad_norm": 5.296182155609131, "learning_rate": 2.345428298287902e-06, "loss": 0.26346343755722046, "step": 4399 }, { "epoch": 1.142263759086189, "grad_norm": 6.895456790924072, "learning_rate": 2.3444977431185432e-06, "loss": 0.12642961740493774, "step": 4400 }, { "epoch": 1.1425233644859814, "grad_norm": 9.320816040039062, "learning_rate": 2.3435672596326987e-06, "loss": 0.13703767955303192, "step": 4401 }, { "epoch": 1.1427829698857737, "grad_norm": 8.080148696899414, "learning_rate": 2.3426368479948556e-06, "loss": 0.12298929691314697, "step": 4402 }, { "epoch": 1.143042575285566, "grad_norm": 7.007256507873535, "learning_rate": 2.3417065083694913e-06, "loss": 0.01586330682039261, "step": 4403 }, { "epoch": 1.1433021806853583, "grad_norm": 10.317486763000488, "learning_rate": 2.3407762409210677e-06, "loss": 0.09259939193725586, "step": 4404 }, { "epoch": 1.1435617860851506, "grad_norm": 9.990584373474121, "learning_rate": 2.339846045814034e-06, "loss": 0.033295392990112305, "step": 4405 }, { "epoch": 1.1438213914849429, "grad_norm": 10.806963920593262, "learning_rate": 2.3389159232128285e-06, "loss": 0.11075235903263092, "step": 4406 }, { "epoch": 1.1440809968847352, "grad_norm": 11.801243782043457, "learning_rate": 2.337985873281875e-06, "loss": 0.1476621925830841, "step": 4407 }, { "epoch": 1.1443406022845275, "grad_norm": 6.732293605804443, "learning_rate": 2.337055896185586e-06, "loss": 0.2071196734905243, "step": 4408 }, { "epoch": 1.1446002076843198, "grad_norm": 12.246103286743164, "learning_rate": 2.336125992088359e-06, "loss": 0.0775313749909401, "step": 4409 }, { "epoch": 1.144859813084112, "grad_norm": 8.537839889526367, "learning_rate": 2.3351961611545798e-06, "loss": 0.13509772717952728, "step": 4410 }, { "epoch": 1.1451194184839044, "grad_norm": 9.285588264465332, "learning_rate": 2.3342664035486216e-06, "loss": 0.1504368782043457, "step": 4411 }, { "epoch": 1.1453790238836967, "grad_norm": 6.86322021484375, "learning_rate": 2.3333367194348443e-06, "loss": 0.20424403250217438, "step": 4412 }, { "epoch": 1.145638629283489, "grad_norm": 6.112328052520752, "learning_rate": 2.3324071089775953e-06, "loss": 0.27156955003738403, "step": 4413 }, { "epoch": 1.1458982346832813, "grad_norm": 8.018691062927246, "learning_rate": 2.3314775723412065e-06, "loss": 0.1781541109085083, "step": 4414 }, { "epoch": 1.1461578400830736, "grad_norm": 9.847983360290527, "learning_rate": 2.330548109690002e-06, "loss": 0.11126702278852463, "step": 4415 }, { "epoch": 1.146417445482866, "grad_norm": 9.167607307434082, "learning_rate": 2.3296187211882854e-06, "loss": 0.1311926692724228, "step": 4416 }, { "epoch": 1.1466770508826585, "grad_norm": 10.042624473571777, "learning_rate": 2.328689407000354e-06, "loss": 0.15551598370075226, "step": 4417 }, { "epoch": 1.1469366562824508, "grad_norm": 8.123174667358398, "learning_rate": 2.327760167290489e-06, "loss": 0.04840896278619766, "step": 4418 }, { "epoch": 1.147196261682243, "grad_norm": 14.886967658996582, "learning_rate": 2.3268310022229597e-06, "loss": 0.0754270851612091, "step": 4419 }, { "epoch": 1.1474558670820354, "grad_norm": 9.808018684387207, "learning_rate": 2.3259019119620184e-06, "loss": 0.09932354092597961, "step": 4420 }, { "epoch": 1.1477154724818277, "grad_norm": 6.58099889755249, "learning_rate": 2.324972896671908e-06, "loss": 0.20908385515213013, "step": 4421 }, { "epoch": 1.14797507788162, "grad_norm": 11.195449829101562, "learning_rate": 2.324043956516859e-06, "loss": 0.05366755649447441, "step": 4422 }, { "epoch": 1.1482346832814123, "grad_norm": 8.558728218078613, "learning_rate": 2.323115091661085e-06, "loss": 0.16947263479232788, "step": 4423 }, { "epoch": 1.1484942886812046, "grad_norm": 6.532961845397949, "learning_rate": 2.3221863022687877e-06, "loss": 0.2233770787715912, "step": 4424 }, { "epoch": 1.148753894080997, "grad_norm": 10.245684623718262, "learning_rate": 2.321257588504158e-06, "loss": 0.09466832876205444, "step": 4425 }, { "epoch": 1.1490134994807892, "grad_norm": 6.70489501953125, "learning_rate": 2.3203289505313677e-06, "loss": 0.03951673209667206, "step": 4426 }, { "epoch": 1.1492731048805815, "grad_norm": 11.601266860961914, "learning_rate": 2.3194003885145826e-06, "loss": 0.0808865875005722, "step": 4427 }, { "epoch": 1.1495327102803738, "grad_norm": 8.055121421813965, "learning_rate": 2.3184719026179485e-06, "loss": 0.18769004940986633, "step": 4428 }, { "epoch": 1.1497923156801662, "grad_norm": 10.155405044555664, "learning_rate": 2.317543493005602e-06, "loss": 0.16998113691806793, "step": 4429 }, { "epoch": 1.1500519210799585, "grad_norm": 9.39993953704834, "learning_rate": 2.316615159841663e-06, "loss": 0.06462857127189636, "step": 4430 }, { "epoch": 1.1503115264797508, "grad_norm": 11.73508071899414, "learning_rate": 2.315686903290242e-06, "loss": 0.06265154480934143, "step": 4431 }, { "epoch": 1.150571131879543, "grad_norm": 8.591949462890625, "learning_rate": 2.3147587235154307e-06, "loss": 0.1389555037021637, "step": 4432 }, { "epoch": 1.1508307372793354, "grad_norm": 9.183816909790039, "learning_rate": 2.3138306206813117e-06, "loss": 0.04779946804046631, "step": 4433 }, { "epoch": 1.1510903426791277, "grad_norm": 7.989958763122559, "learning_rate": 2.3129025949519517e-06, "loss": 0.04939097538590431, "step": 4434 }, { "epoch": 1.15134994807892, "grad_norm": 8.326760292053223, "learning_rate": 2.3119746464914055e-06, "loss": 0.16330771148204803, "step": 4435 }, { "epoch": 1.1516095534787123, "grad_norm": 9.124566078186035, "learning_rate": 2.3110467754637115e-06, "loss": 0.032610177993774414, "step": 4436 }, { "epoch": 1.1518691588785046, "grad_norm": 8.709930419921875, "learning_rate": 2.3101189820328977e-06, "loss": 0.2251543402671814, "step": 4437 }, { "epoch": 1.152128764278297, "grad_norm": 7.981034755706787, "learning_rate": 2.3091912663629758e-06, "loss": 0.11287951469421387, "step": 4438 }, { "epoch": 1.1523883696780892, "grad_norm": 13.455442428588867, "learning_rate": 2.3082636286179446e-06, "loss": 0.09731604158878326, "step": 4439 }, { "epoch": 1.1526479750778815, "grad_norm": 8.552781105041504, "learning_rate": 2.3073360689617893e-06, "loss": 0.0760556012392044, "step": 4440 }, { "epoch": 1.1529075804776738, "grad_norm": 8.147024154663086, "learning_rate": 2.3064085875584814e-06, "loss": 0.047995276749134064, "step": 4441 }, { "epoch": 1.1531671858774661, "grad_norm": 14.992701530456543, "learning_rate": 2.3054811845719786e-06, "loss": 0.07888835668563843, "step": 4442 }, { "epoch": 1.1534267912772584, "grad_norm": 8.719889640808105, "learning_rate": 2.304553860166224e-06, "loss": 0.07400467246770859, "step": 4443 }, { "epoch": 1.153686396677051, "grad_norm": 10.592288970947266, "learning_rate": 2.303626614505147e-06, "loss": 0.04355638474225998, "step": 4444 }, { "epoch": 1.1539460020768433, "grad_norm": 5.836801052093506, "learning_rate": 2.302699447752665e-06, "loss": 0.23388078808784485, "step": 4445 }, { "epoch": 1.1542056074766356, "grad_norm": 6.866183280944824, "learning_rate": 2.3017723600726795e-06, "loss": 0.19861219823360443, "step": 4446 }, { "epoch": 1.154465212876428, "grad_norm": 7.142602443695068, "learning_rate": 2.3008453516290756e-06, "loss": 0.19056476652622223, "step": 4447 }, { "epoch": 1.1547248182762202, "grad_norm": 6.535916805267334, "learning_rate": 2.29991842258573e-06, "loss": 0.19399967789649963, "step": 4448 }, { "epoch": 1.1549844236760125, "grad_norm": 6.64884614944458, "learning_rate": 2.2989915731065023e-06, "loss": 0.15153202414512634, "step": 4449 }, { "epoch": 1.1552440290758048, "grad_norm": 7.221959590911865, "learning_rate": 2.2980648033552384e-06, "loss": 0.21204933524131775, "step": 4450 }, { "epoch": 1.1555036344755971, "grad_norm": 9.975869178771973, "learning_rate": 2.297138113495768e-06, "loss": 0.05624089390039444, "step": 4451 }, { "epoch": 1.1557632398753894, "grad_norm": 9.06248950958252, "learning_rate": 2.2962115036919095e-06, "loss": 0.03419981896877289, "step": 4452 }, { "epoch": 1.1560228452751817, "grad_norm": 10.188005447387695, "learning_rate": 2.295284974107468e-06, "loss": 0.11653921008110046, "step": 4453 }, { "epoch": 1.156282450674974, "grad_norm": 7.89450216293335, "learning_rate": 2.2943585249062316e-06, "loss": 0.07355248928070068, "step": 4454 }, { "epoch": 1.1565420560747663, "grad_norm": 5.787784576416016, "learning_rate": 2.2934321562519746e-06, "loss": 0.2176784873008728, "step": 4455 }, { "epoch": 1.1568016614745587, "grad_norm": 9.88270378112793, "learning_rate": 2.2925058683084582e-06, "loss": 0.1860874444246292, "step": 4456 }, { "epoch": 1.157061266874351, "grad_norm": 12.033206939697266, "learning_rate": 2.291579661239429e-06, "loss": 0.07683781534433365, "step": 4457 }, { "epoch": 1.1573208722741433, "grad_norm": 8.176006317138672, "learning_rate": 2.2906535352086205e-06, "loss": 0.11641816794872284, "step": 4458 }, { "epoch": 1.1575804776739356, "grad_norm": 9.272571563720703, "learning_rate": 2.2897274903797484e-06, "loss": 0.07298971712589264, "step": 4459 }, { "epoch": 1.1578400830737279, "grad_norm": 5.390085697174072, "learning_rate": 2.2888015269165166e-06, "loss": 0.23219537734985352, "step": 4460 }, { "epoch": 1.1580996884735202, "grad_norm": 5.938914775848389, "learning_rate": 2.2878756449826157e-06, "loss": 0.2646220922470093, "step": 4461 }, { "epoch": 1.1583592938733125, "grad_norm": 6.956289768218994, "learning_rate": 2.2869498447417193e-06, "loss": 0.05596509948372841, "step": 4462 }, { "epoch": 1.1586188992731048, "grad_norm": 8.089244842529297, "learning_rate": 2.286024126357488e-06, "loss": 0.04171724244952202, "step": 4463 }, { "epoch": 1.158878504672897, "grad_norm": 14.601225852966309, "learning_rate": 2.285098489993567e-06, "loss": 0.10543996840715408, "step": 4464 }, { "epoch": 1.1591381100726896, "grad_norm": 9.692558288574219, "learning_rate": 2.2841729358135885e-06, "loss": 0.08714894950389862, "step": 4465 }, { "epoch": 1.159397715472482, "grad_norm": 5.890231609344482, "learning_rate": 2.2832474639811686e-06, "loss": 0.23097634315490723, "step": 4466 }, { "epoch": 1.1596573208722742, "grad_norm": 7.781374931335449, "learning_rate": 2.28232207465991e-06, "loss": 0.1155756413936615, "step": 4467 }, { "epoch": 1.1599169262720666, "grad_norm": 8.74608325958252, "learning_rate": 2.281396768013401e-06, "loss": 0.03822406008839607, "step": 4468 }, { "epoch": 1.1601765316718589, "grad_norm": 6.443921089172363, "learning_rate": 2.280471544205213e-06, "loss": 0.22985520958900452, "step": 4469 }, { "epoch": 1.1604361370716512, "grad_norm": 7.9918904304504395, "learning_rate": 2.279546403398905e-06, "loss": 0.11092092096805573, "step": 4470 }, { "epoch": 1.1606957424714435, "grad_norm": 7.814604759216309, "learning_rate": 2.2786213457580216e-06, "loss": 0.162992924451828, "step": 4471 }, { "epoch": 1.1609553478712358, "grad_norm": 6.979551792144775, "learning_rate": 2.27769637144609e-06, "loss": 0.21956653892993927, "step": 4472 }, { "epoch": 1.161214953271028, "grad_norm": 11.53706169128418, "learning_rate": 2.276771480626627e-06, "loss": 0.1371975541114807, "step": 4473 }, { "epoch": 1.1614745586708204, "grad_norm": 8.92227840423584, "learning_rate": 2.27584667346313e-06, "loss": 0.20003783702850342, "step": 4474 }, { "epoch": 1.1617341640706127, "grad_norm": 11.372021675109863, "learning_rate": 2.2749219501190846e-06, "loss": 0.11101734638214111, "step": 4475 }, { "epoch": 1.161993769470405, "grad_norm": 7.749009609222412, "learning_rate": 2.2739973107579606e-06, "loss": 0.19688817858695984, "step": 4476 }, { "epoch": 1.1622533748701973, "grad_norm": 10.299751281738281, "learning_rate": 2.2730727555432135e-06, "loss": 0.1234588623046875, "step": 4477 }, { "epoch": 1.1625129802699896, "grad_norm": 8.72927188873291, "learning_rate": 2.272148284638282e-06, "loss": 0.23510685563087463, "step": 4478 }, { "epoch": 1.162772585669782, "grad_norm": 7.65240478515625, "learning_rate": 2.271223898206593e-06, "loss": 0.13261164724826813, "step": 4479 }, { "epoch": 1.1630321910695742, "grad_norm": 6.848535060882568, "learning_rate": 2.270299596411556e-06, "loss": 0.22114315629005432, "step": 4480 }, { "epoch": 1.1632917964693665, "grad_norm": 11.902507781982422, "learning_rate": 2.269375379416568e-06, "loss": 0.13081273436546326, "step": 4481 }, { "epoch": 1.1635514018691588, "grad_norm": 7.137792587280273, "learning_rate": 2.268451247385007e-06, "loss": 0.20521262288093567, "step": 4482 }, { "epoch": 1.1638110072689511, "grad_norm": 8.173017501831055, "learning_rate": 2.2675272004802383e-06, "loss": 0.21546101570129395, "step": 4483 }, { "epoch": 1.1640706126687435, "grad_norm": 9.423613548278809, "learning_rate": 2.2666032388656144e-06, "loss": 0.04355470463633537, "step": 4484 }, { "epoch": 1.1643302180685358, "grad_norm": 10.016979217529297, "learning_rate": 2.265679362704471e-06, "loss": 0.0945904329419136, "step": 4485 }, { "epoch": 1.164589823468328, "grad_norm": 9.869760513305664, "learning_rate": 2.264755572160125e-06, "loss": 0.10162705183029175, "step": 4486 }, { "epoch": 1.1648494288681204, "grad_norm": 8.82520866394043, "learning_rate": 2.2638318673958836e-06, "loss": 0.03675355017185211, "step": 4487 }, { "epoch": 1.1651090342679127, "grad_norm": 9.704703330993652, "learning_rate": 2.262908248575036e-06, "loss": 0.07371166348457336, "step": 4488 }, { "epoch": 1.165368639667705, "grad_norm": 9.952871322631836, "learning_rate": 2.261984715860858e-06, "loss": 0.05760473757982254, "step": 4489 }, { "epoch": 1.1656282450674973, "grad_norm": 8.09604263305664, "learning_rate": 2.261061269416608e-06, "loss": 0.23227010667324066, "step": 4490 }, { "epoch": 1.1658878504672896, "grad_norm": 8.090579986572266, "learning_rate": 2.2601379094055297e-06, "loss": 0.044966984540224075, "step": 4491 }, { "epoch": 1.1661474558670821, "grad_norm": 6.9629011154174805, "learning_rate": 2.2592146359908534e-06, "loss": 0.16985058784484863, "step": 4492 }, { "epoch": 1.1664070612668744, "grad_norm": 7.499349117279053, "learning_rate": 2.2582914493357912e-06, "loss": 0.14119111001491547, "step": 4493 }, { "epoch": 1.1666666666666667, "grad_norm": 8.939409255981445, "learning_rate": 2.2573683496035424e-06, "loss": 0.10472187399864197, "step": 4494 }, { "epoch": 1.166926272066459, "grad_norm": 5.811411380767822, "learning_rate": 2.2564453369572898e-06, "loss": 0.23270386457443237, "step": 4495 }, { "epoch": 1.1671858774662514, "grad_norm": 6.677202224731445, "learning_rate": 2.255522411560201e-06, "loss": 0.18161338567733765, "step": 4496 }, { "epoch": 1.1674454828660437, "grad_norm": 7.218081951141357, "learning_rate": 2.254599573575427e-06, "loss": 0.023701602593064308, "step": 4497 }, { "epoch": 1.167705088265836, "grad_norm": 8.666645050048828, "learning_rate": 2.2536768231661053e-06, "loss": 0.07161670923233032, "step": 4498 }, { "epoch": 1.1679646936656283, "grad_norm": 8.64345645904541, "learning_rate": 2.252754160495357e-06, "loss": 0.09191998839378357, "step": 4499 }, { "epoch": 1.1682242990654206, "grad_norm": 14.033900260925293, "learning_rate": 2.251831585726289e-06, "loss": 0.09093879908323288, "step": 4500 }, { "epoch": 1.1684839044652129, "grad_norm": 6.387760162353516, "learning_rate": 2.250909099021989e-06, "loss": 0.1686096042394638, "step": 4501 }, { "epoch": 1.1687435098650052, "grad_norm": 6.122331142425537, "learning_rate": 2.249986700545533e-06, "loss": 0.2025160789489746, "step": 4502 }, { "epoch": 1.1690031152647975, "grad_norm": 9.794763565063477, "learning_rate": 2.2490643904599787e-06, "loss": 0.12829168140888214, "step": 4503 }, { "epoch": 1.1692627206645898, "grad_norm": 8.543601036071777, "learning_rate": 2.248142168928371e-06, "loss": 0.17271852493286133, "step": 4504 }, { "epoch": 1.1695223260643821, "grad_norm": 11.060996055603027, "learning_rate": 2.247220036113737e-06, "loss": 0.1075911670923233, "step": 4505 }, { "epoch": 1.1697819314641744, "grad_norm": 10.54637336730957, "learning_rate": 2.2462979921790877e-06, "loss": 0.13359591364860535, "step": 4506 }, { "epoch": 1.1700415368639667, "grad_norm": 8.280003547668457, "learning_rate": 2.2453760372874206e-06, "loss": 0.0744035542011261, "step": 4507 }, { "epoch": 1.170301142263759, "grad_norm": 9.21725845336914, "learning_rate": 2.2444541716017167e-06, "loss": 0.029468517750501633, "step": 4508 }, { "epoch": 1.1705607476635513, "grad_norm": 5.556621074676514, "learning_rate": 2.243532395284938e-06, "loss": 0.20181861519813538, "step": 4509 }, { "epoch": 1.1708203530633436, "grad_norm": 8.951839447021484, "learning_rate": 2.242610708500036e-06, "loss": 0.05007117614150047, "step": 4510 }, { "epoch": 1.171079958463136, "grad_norm": 10.470527648925781, "learning_rate": 2.2416891114099433e-06, "loss": 0.14037996530532837, "step": 4511 }, { "epoch": 1.1713395638629283, "grad_norm": 8.99830436706543, "learning_rate": 2.240767604177577e-06, "loss": 0.13611479103565216, "step": 4512 }, { "epoch": 1.1715991692627208, "grad_norm": 7.286121845245361, "learning_rate": 2.2398461869658384e-06, "loss": 0.18397100269794464, "step": 4513 }, { "epoch": 1.171858774662513, "grad_norm": 7.733234405517578, "learning_rate": 2.2389248599376125e-06, "loss": 0.06841910630464554, "step": 4514 }, { "epoch": 1.1721183800623054, "grad_norm": 10.03345775604248, "learning_rate": 2.238003623255769e-06, "loss": 0.10109581053256989, "step": 4515 }, { "epoch": 1.1723779854620977, "grad_norm": 11.058100700378418, "learning_rate": 2.2370824770831634e-06, "loss": 0.06361086666584015, "step": 4516 }, { "epoch": 1.17263759086189, "grad_norm": 9.522730827331543, "learning_rate": 2.23616142158263e-06, "loss": 0.07909208536148071, "step": 4517 }, { "epoch": 1.1728971962616823, "grad_norm": 6.7233195304870605, "learning_rate": 2.2352404569169924e-06, "loss": 0.24525611102581024, "step": 4518 }, { "epoch": 1.1731568016614746, "grad_norm": 7.590155124664307, "learning_rate": 2.234319583249056e-06, "loss": 0.12458554655313492, "step": 4519 }, { "epoch": 1.173416407061267, "grad_norm": 12.144134521484375, "learning_rate": 2.233398800741609e-06, "loss": 0.08453664183616638, "step": 4520 }, { "epoch": 1.1736760124610592, "grad_norm": 8.743653297424316, "learning_rate": 2.2324781095574255e-06, "loss": 0.077365942299366, "step": 4521 }, { "epoch": 1.1739356178608515, "grad_norm": 9.318958282470703, "learning_rate": 2.2315575098592627e-06, "loss": 0.08899369090795517, "step": 4522 }, { "epoch": 1.1741952232606438, "grad_norm": 9.580536842346191, "learning_rate": 2.2306370018098623e-06, "loss": 0.158863365650177, "step": 4523 }, { "epoch": 1.1744548286604362, "grad_norm": 6.639255523681641, "learning_rate": 2.229716585571947e-06, "loss": 0.03822198882699013, "step": 4524 }, { "epoch": 1.1747144340602285, "grad_norm": 8.376765251159668, "learning_rate": 2.228796261308227e-06, "loss": 0.07125811278820038, "step": 4525 }, { "epoch": 1.1749740394600208, "grad_norm": 9.291845321655273, "learning_rate": 2.2278760291813934e-06, "loss": 0.0678824856877327, "step": 4526 }, { "epoch": 1.175233644859813, "grad_norm": 7.227452754974365, "learning_rate": 2.2269558893541237e-06, "loss": 0.059674616903066635, "step": 4527 }, { "epoch": 1.1754932502596054, "grad_norm": 9.64852523803711, "learning_rate": 2.226035841989076e-06, "loss": 0.044412631541490555, "step": 4528 }, { "epoch": 1.1757528556593977, "grad_norm": 11.361336708068848, "learning_rate": 2.225115887248894e-06, "loss": 0.16196680068969727, "step": 4529 }, { "epoch": 1.17601246105919, "grad_norm": 8.892986297607422, "learning_rate": 2.2241960252962054e-06, "loss": 0.18018431961536407, "step": 4530 }, { "epoch": 1.1762720664589823, "grad_norm": 10.271960258483887, "learning_rate": 2.2232762562936204e-06, "loss": 0.10500875115394592, "step": 4531 }, { "epoch": 1.1765316718587746, "grad_norm": 5.907467842102051, "learning_rate": 2.222356580403733e-06, "loss": 0.23132069408893585, "step": 4532 }, { "epoch": 1.176791277258567, "grad_norm": 6.294613361358643, "learning_rate": 2.22143699778912e-06, "loss": 0.2468518167734146, "step": 4533 }, { "epoch": 1.1770508826583592, "grad_norm": 8.192306518554688, "learning_rate": 2.2205175086123436e-06, "loss": 0.15270225703716278, "step": 4534 }, { "epoch": 1.1773104880581515, "grad_norm": 11.383641242980957, "learning_rate": 2.2195981130359482e-06, "loss": 0.14546555280685425, "step": 4535 }, { "epoch": 1.1775700934579438, "grad_norm": 11.795012474060059, "learning_rate": 2.218678811222462e-06, "loss": 0.04582851380109787, "step": 4536 }, { "epoch": 1.1778296988577361, "grad_norm": 9.85705280303955, "learning_rate": 2.217759603334396e-06, "loss": 0.07743993401527405, "step": 4537 }, { "epoch": 1.1780893042575284, "grad_norm": 10.852752685546875, "learning_rate": 2.2168404895342456e-06, "loss": 0.13443396985530853, "step": 4538 }, { "epoch": 1.1783489096573208, "grad_norm": 8.605301856994629, "learning_rate": 2.2159214699844895e-06, "loss": 0.03726775199174881, "step": 4539 }, { "epoch": 1.1786085150571133, "grad_norm": 2.5177884101867676, "learning_rate": 2.2150025448475876e-06, "loss": 0.008913833647966385, "step": 4540 }, { "epoch": 1.1788681204569056, "grad_norm": 8.873114585876465, "learning_rate": 2.214083714285987e-06, "loss": 0.1267782747745514, "step": 4541 }, { "epoch": 1.179127725856698, "grad_norm": 9.507698059082031, "learning_rate": 2.213164978462114e-06, "loss": 0.1465936154127121, "step": 4542 }, { "epoch": 1.1793873312564902, "grad_norm": 8.18509578704834, "learning_rate": 2.212246337538382e-06, "loss": 0.06039224565029144, "step": 4543 }, { "epoch": 1.1796469366562825, "grad_norm": 11.63443374633789, "learning_rate": 2.211327791677183e-06, "loss": 0.1464877724647522, "step": 4544 }, { "epoch": 1.1799065420560748, "grad_norm": 12.382333755493164, "learning_rate": 2.2104093410408972e-06, "loss": 0.1497115194797516, "step": 4545 }, { "epoch": 1.1801661474558671, "grad_norm": 9.064981460571289, "learning_rate": 2.209490985791886e-06, "loss": 0.16076990962028503, "step": 4546 }, { "epoch": 1.1804257528556594, "grad_norm": 9.870169639587402, "learning_rate": 2.2085727260924916e-06, "loss": 0.1804085224866867, "step": 4547 }, { "epoch": 1.1806853582554517, "grad_norm": 11.959528923034668, "learning_rate": 2.2076545621050416e-06, "loss": 0.07983805984258652, "step": 4548 }, { "epoch": 1.180944963655244, "grad_norm": 9.024840354919434, "learning_rate": 2.2067364939918473e-06, "loss": 0.09628047049045563, "step": 4549 }, { "epoch": 1.1812045690550363, "grad_norm": 7.135613918304443, "learning_rate": 2.205818521915203e-06, "loss": 0.22764642536640167, "step": 4550 }, { "epoch": 1.1814641744548287, "grad_norm": 5.764852523803711, "learning_rate": 2.2049006460373824e-06, "loss": 0.27298516035079956, "step": 4551 }, { "epoch": 1.181723779854621, "grad_norm": 12.485897064208984, "learning_rate": 2.203982866520647e-06, "loss": 0.09069493412971497, "step": 4552 }, { "epoch": 1.1819833852544133, "grad_norm": 8.348369598388672, "learning_rate": 2.2030651835272383e-06, "loss": 0.17234724760055542, "step": 4553 }, { "epoch": 1.1822429906542056, "grad_norm": 10.237616539001465, "learning_rate": 2.202147597219383e-06, "loss": 0.09686551988124847, "step": 4554 }, { "epoch": 1.1825025960539979, "grad_norm": 10.49168586730957, "learning_rate": 2.2012301077592874e-06, "loss": 0.04164160043001175, "step": 4555 }, { "epoch": 1.1827622014537902, "grad_norm": 7.2325921058654785, "learning_rate": 2.2003127153091437e-06, "loss": 0.056754156947135925, "step": 4556 }, { "epoch": 1.1830218068535825, "grad_norm": 16.585248947143555, "learning_rate": 2.199395420031126e-06, "loss": 0.07747845351696014, "step": 4557 }, { "epoch": 1.1832814122533748, "grad_norm": 9.85494327545166, "learning_rate": 2.198478222087391e-06, "loss": 0.17782746255397797, "step": 4558 }, { "epoch": 1.183541017653167, "grad_norm": 14.243825912475586, "learning_rate": 2.1975611216400776e-06, "loss": 0.08802425861358643, "step": 4559 }, { "epoch": 1.1838006230529594, "grad_norm": 3.7494871616363525, "learning_rate": 2.196644118851309e-06, "loss": 0.014156688004732132, "step": 4560 }, { "epoch": 1.184060228452752, "grad_norm": 8.32837963104248, "learning_rate": 2.19572721388319e-06, "loss": 0.28112006187438965, "step": 4561 }, { "epoch": 1.1843198338525442, "grad_norm": 8.695653915405273, "learning_rate": 2.194810406897809e-06, "loss": 0.07604488730430603, "step": 4562 }, { "epoch": 1.1845794392523366, "grad_norm": 9.070879936218262, "learning_rate": 2.193893698057235e-06, "loss": 0.08701460063457489, "step": 4563 }, { "epoch": 1.1848390446521289, "grad_norm": 11.482141494750977, "learning_rate": 2.1929770875235227e-06, "loss": 0.15239185094833374, "step": 4564 }, { "epoch": 1.1850986500519212, "grad_norm": 7.562432289123535, "learning_rate": 2.1920605754587073e-06, "loss": 0.04862448200583458, "step": 4565 }, { "epoch": 1.1853582554517135, "grad_norm": 10.461138725280762, "learning_rate": 2.1911441620248066e-06, "loss": 0.09202229231595993, "step": 4566 }, { "epoch": 1.1856178608515058, "grad_norm": 10.153121948242188, "learning_rate": 2.1902278473838217e-06, "loss": 0.0535120815038681, "step": 4567 }, { "epoch": 1.185877466251298, "grad_norm": 8.910053253173828, "learning_rate": 2.1893116316977365e-06, "loss": 0.020480360835790634, "step": 4568 }, { "epoch": 1.1861370716510904, "grad_norm": 6.677167892456055, "learning_rate": 2.188395515128517e-06, "loss": 0.20014938712120056, "step": 4569 }, { "epoch": 1.1863966770508827, "grad_norm": 8.120077133178711, "learning_rate": 2.1874794978381114e-06, "loss": 0.05554784834384918, "step": 4570 }, { "epoch": 1.186656282450675, "grad_norm": 6.088265895843506, "learning_rate": 2.1865635799884507e-06, "loss": 0.18304835259914398, "step": 4571 }, { "epoch": 1.1869158878504673, "grad_norm": 14.57010555267334, "learning_rate": 2.185647761741447e-06, "loss": 0.07630186527967453, "step": 4572 }, { "epoch": 1.1871754932502596, "grad_norm": 8.06767463684082, "learning_rate": 2.184732043258998e-06, "loss": 0.0779389962553978, "step": 4573 }, { "epoch": 1.187435098650052, "grad_norm": 11.600565910339355, "learning_rate": 2.183816424702982e-06, "loss": 0.04551063850522041, "step": 4574 }, { "epoch": 1.1876947040498442, "grad_norm": 7.33604621887207, "learning_rate": 2.1829009062352558e-06, "loss": 0.05113215371966362, "step": 4575 }, { "epoch": 1.1879543094496365, "grad_norm": 10.151537895202637, "learning_rate": 2.181985488017666e-06, "loss": 0.034120824187994, "step": 4576 }, { "epoch": 1.1882139148494288, "grad_norm": 9.294682502746582, "learning_rate": 2.1810701702120367e-06, "loss": 0.061085887253284454, "step": 4577 }, { "epoch": 1.1884735202492211, "grad_norm": 10.856799125671387, "learning_rate": 2.180154952980173e-06, "loss": 0.09013228118419647, "step": 4578 }, { "epoch": 1.1887331256490135, "grad_norm": 9.427392959594727, "learning_rate": 2.179239836483866e-06, "loss": 0.14419826865196228, "step": 4579 }, { "epoch": 1.1889927310488058, "grad_norm": 7.736575126647949, "learning_rate": 2.178324820884888e-06, "loss": 0.047765061259269714, "step": 4580 }, { "epoch": 1.189252336448598, "grad_norm": 10.920706748962402, "learning_rate": 2.177409906344992e-06, "loss": 0.07307035475969315, "step": 4581 }, { "epoch": 1.1895119418483904, "grad_norm": 8.507545471191406, "learning_rate": 2.1764950930259143e-06, "loss": 0.16421791911125183, "step": 4582 }, { "epoch": 1.1897715472481827, "grad_norm": 11.045365333557129, "learning_rate": 2.1755803810893716e-06, "loss": 0.07726481556892395, "step": 4583 }, { "epoch": 1.190031152647975, "grad_norm": 10.397113800048828, "learning_rate": 2.174665770697066e-06, "loss": 0.13596788048744202, "step": 4584 }, { "epoch": 1.1902907580477673, "grad_norm": 10.756622314453125, "learning_rate": 2.1737512620106784e-06, "loss": 0.1443849802017212, "step": 4585 }, { "epoch": 1.1905503634475596, "grad_norm": 7.173614025115967, "learning_rate": 2.1728368551918726e-06, "loss": 0.19947580993175507, "step": 4586 }, { "epoch": 1.190809968847352, "grad_norm": 9.619118690490723, "learning_rate": 2.1719225504022968e-06, "loss": 0.058830857276916504, "step": 4587 }, { "epoch": 1.1910695742471444, "grad_norm": 11.206184387207031, "learning_rate": 2.1710083478035763e-06, "loss": 0.10718287527561188, "step": 4588 }, { "epoch": 1.1913291796469367, "grad_norm": 6.84282112121582, "learning_rate": 2.1700942475573246e-06, "loss": 0.09638364613056183, "step": 4589 }, { "epoch": 1.191588785046729, "grad_norm": 9.405594825744629, "learning_rate": 2.169180249825131e-06, "loss": 0.1638467013835907, "step": 4590 }, { "epoch": 1.1918483904465214, "grad_norm": 7.714014530181885, "learning_rate": 2.1682663547685695e-06, "loss": 0.039885181933641434, "step": 4591 }, { "epoch": 1.1921079958463137, "grad_norm": 8.069873809814453, "learning_rate": 2.167352562549197e-06, "loss": 0.1320694237947464, "step": 4592 }, { "epoch": 1.192367601246106, "grad_norm": 9.377547264099121, "learning_rate": 2.1664388733285514e-06, "loss": 0.06950412690639496, "step": 4593 }, { "epoch": 1.1926272066458983, "grad_norm": 10.007667541503906, "learning_rate": 2.1655252872681505e-06, "loss": 0.06615260243415833, "step": 4594 }, { "epoch": 1.1928868120456906, "grad_norm": 5.80571174621582, "learning_rate": 2.164611804529496e-06, "loss": 0.24025662243366241, "step": 4595 }, { "epoch": 1.1931464174454829, "grad_norm": 10.46866226196289, "learning_rate": 2.1636984252740705e-06, "loss": 0.04360797256231308, "step": 4596 }, { "epoch": 1.1934060228452752, "grad_norm": 8.23196029663086, "learning_rate": 2.16278514966334e-06, "loss": 0.0464339405298233, "step": 4597 }, { "epoch": 1.1936656282450675, "grad_norm": 7.245007038116455, "learning_rate": 2.161871977858749e-06, "loss": 0.16378022730350494, "step": 4598 }, { "epoch": 1.1939252336448598, "grad_norm": 8.2759428024292, "learning_rate": 2.160958910021726e-06, "loss": 0.19243308901786804, "step": 4599 }, { "epoch": 1.1941848390446521, "grad_norm": 5.8783135414123535, "learning_rate": 2.16004594631368e-06, "loss": 0.21533618867397308, "step": 4600 }, { "epoch": 1.1944444444444444, "grad_norm": 10.545944213867188, "learning_rate": 2.1591330868960035e-06, "loss": 0.1587514579296112, "step": 4601 }, { "epoch": 1.1947040498442367, "grad_norm": 7.793755054473877, "learning_rate": 2.1582203319300677e-06, "loss": 0.20422452688217163, "step": 4602 }, { "epoch": 1.194963655244029, "grad_norm": 11.249028205871582, "learning_rate": 2.157307681577227e-06, "loss": 0.07334586977958679, "step": 4603 }, { "epoch": 1.1952232606438213, "grad_norm": 6.0658721923828125, "learning_rate": 2.1563951359988183e-06, "loss": 0.24420958757400513, "step": 4604 }, { "epoch": 1.1954828660436136, "grad_norm": 5.738020896911621, "learning_rate": 2.155482695356157e-06, "loss": 0.2216053009033203, "step": 4605 }, { "epoch": 1.195742471443406, "grad_norm": 9.509855270385742, "learning_rate": 2.154570359810542e-06, "loss": 0.045875728130340576, "step": 4606 }, { "epoch": 1.1960020768431983, "grad_norm": 9.362951278686523, "learning_rate": 2.1536581295232545e-06, "loss": 0.04479648917913437, "step": 4607 }, { "epoch": 1.1962616822429906, "grad_norm": 7.108964443206787, "learning_rate": 2.152746004655556e-06, "loss": 0.15953047573566437, "step": 4608 }, { "epoch": 1.196521287642783, "grad_norm": 12.269108772277832, "learning_rate": 2.1518339853686874e-06, "loss": 0.07666854560375214, "step": 4609 }, { "epoch": 1.1967808930425754, "grad_norm": 7.32312536239624, "learning_rate": 2.1509220718238744e-06, "loss": 0.2535262107849121, "step": 4610 }, { "epoch": 1.1970404984423677, "grad_norm": 8.846782684326172, "learning_rate": 2.150010264182322e-06, "loss": 0.09339043498039246, "step": 4611 }, { "epoch": 1.19730010384216, "grad_norm": 6.067042350769043, "learning_rate": 2.1490985626052173e-06, "loss": 0.27097439765930176, "step": 4612 }, { "epoch": 1.1975597092419523, "grad_norm": 12.132515907287598, "learning_rate": 2.1481869672537277e-06, "loss": 0.03445247560739517, "step": 4613 }, { "epoch": 1.1978193146417446, "grad_norm": 10.67115592956543, "learning_rate": 2.147275478289002e-06, "loss": 0.09137429296970367, "step": 4614 }, { "epoch": 1.198078920041537, "grad_norm": 12.81225872039795, "learning_rate": 2.1463640958721714e-06, "loss": 0.08761078119277954, "step": 4615 }, { "epoch": 1.1983385254413292, "grad_norm": 10.036426544189453, "learning_rate": 2.145452820164348e-06, "loss": 0.06403117626905441, "step": 4616 }, { "epoch": 1.1985981308411215, "grad_norm": 7.9051361083984375, "learning_rate": 2.144541651326623e-06, "loss": 0.12545131146907806, "step": 4617 }, { "epoch": 1.1988577362409139, "grad_norm": 6.8861799240112305, "learning_rate": 2.1436305895200715e-06, "loss": 0.18336278200149536, "step": 4618 }, { "epoch": 1.1991173416407062, "grad_norm": 8.84758472442627, "learning_rate": 2.142719634905747e-06, "loss": 0.10124130547046661, "step": 4619 }, { "epoch": 1.1993769470404985, "grad_norm": 7.45733642578125, "learning_rate": 2.1418087876446867e-06, "loss": 0.2644230127334595, "step": 4620 }, { "epoch": 1.1996365524402908, "grad_norm": 9.132493019104004, "learning_rate": 2.140898047897907e-06, "loss": 0.12344618886709213, "step": 4621 }, { "epoch": 1.199896157840083, "grad_norm": 5.220173358917236, "learning_rate": 2.139987415826405e-06, "loss": 0.21971136331558228, "step": 4622 }, { "epoch": 1.2001557632398754, "grad_norm": 7.5068745613098145, "learning_rate": 2.1390768915911614e-06, "loss": 0.10555446147918701, "step": 4623 }, { "epoch": 1.2004153686396677, "grad_norm": 9.735578536987305, "learning_rate": 2.138166475353135e-06, "loss": 0.10191740095615387, "step": 4624 }, { "epoch": 1.20067497403946, "grad_norm": 7.233607769012451, "learning_rate": 2.137256167273266e-06, "loss": 0.2162037193775177, "step": 4625 }, { "epoch": 1.2009345794392523, "grad_norm": 6.710773468017578, "learning_rate": 2.136345967512477e-06, "loss": 0.18959124386310577, "step": 4626 }, { "epoch": 1.2011941848390446, "grad_norm": 8.168334007263184, "learning_rate": 2.1354358762316703e-06, "loss": 0.15732811391353607, "step": 4627 }, { "epoch": 1.201453790238837, "grad_norm": 8.872641563415527, "learning_rate": 2.134525893591729e-06, "loss": 0.10516583919525146, "step": 4628 }, { "epoch": 1.2017133956386292, "grad_norm": 6.905629634857178, "learning_rate": 2.133616019753517e-06, "loss": 0.21112358570098877, "step": 4629 }, { "epoch": 1.2019730010384215, "grad_norm": 7.424503326416016, "learning_rate": 2.1327062548778797e-06, "loss": 0.16616012156009674, "step": 4630 }, { "epoch": 1.2022326064382138, "grad_norm": 7.223757266998291, "learning_rate": 2.131796599125643e-06, "loss": 0.07065063714981079, "step": 4631 }, { "epoch": 1.2024922118380061, "grad_norm": 10.133325576782227, "learning_rate": 2.1308870526576112e-06, "loss": 0.09368888288736343, "step": 4632 }, { "epoch": 1.2027518172377984, "grad_norm": 9.097468376159668, "learning_rate": 2.129977615634573e-06, "loss": 0.2022324651479721, "step": 4633 }, { "epoch": 1.2030114226375908, "grad_norm": 17.38736915588379, "learning_rate": 2.129068288217296e-06, "loss": 0.11810115724802017, "step": 4634 }, { "epoch": 1.203271028037383, "grad_norm": 10.959100723266602, "learning_rate": 2.128159070566529e-06, "loss": 0.06850038468837738, "step": 4635 }, { "epoch": 1.2035306334371756, "grad_norm": 10.191877365112305, "learning_rate": 2.1272499628429993e-06, "loss": 0.10068267583847046, "step": 4636 }, { "epoch": 1.203790238836968, "grad_norm": 6.646775722503662, "learning_rate": 2.1263409652074165e-06, "loss": 0.20120233297348022, "step": 4637 }, { "epoch": 1.2040498442367602, "grad_norm": 9.6305513381958, "learning_rate": 2.125432077820471e-06, "loss": 0.06347434222698212, "step": 4638 }, { "epoch": 1.2043094496365525, "grad_norm": 6.018986701965332, "learning_rate": 2.1245233008428355e-06, "loss": 0.04700830578804016, "step": 4639 }, { "epoch": 1.2045690550363448, "grad_norm": 7.863824367523193, "learning_rate": 2.123614634435158e-06, "loss": 0.21177151799201965, "step": 4640 }, { "epoch": 1.2048286604361371, "grad_norm": 9.685829162597656, "learning_rate": 2.1227060787580693e-06, "loss": 0.14649444818496704, "step": 4641 }, { "epoch": 1.2050882658359294, "grad_norm": 9.766703605651855, "learning_rate": 2.1217976339721837e-06, "loss": 0.10166727751493454, "step": 4642 }, { "epoch": 1.2053478712357217, "grad_norm": 13.635196685791016, "learning_rate": 2.120889300238093e-06, "loss": 0.06232632324099541, "step": 4643 }, { "epoch": 1.205607476635514, "grad_norm": 8.536247253417969, "learning_rate": 2.1199810777163687e-06, "loss": 0.10480768233537674, "step": 4644 }, { "epoch": 1.2058670820353063, "grad_norm": 9.20021915435791, "learning_rate": 2.1190729665675647e-06, "loss": 0.07108866423368454, "step": 4645 }, { "epoch": 1.2061266874350987, "grad_norm": 6.1320295333862305, "learning_rate": 2.1181649669522138e-06, "loss": 0.22824962437152863, "step": 4646 }, { "epoch": 1.206386292834891, "grad_norm": 13.627962112426758, "learning_rate": 2.1172570790308293e-06, "loss": 0.14469470083713531, "step": 4647 }, { "epoch": 1.2066458982346833, "grad_norm": 13.224226951599121, "learning_rate": 2.1163493029639056e-06, "loss": 0.0959777683019638, "step": 4648 }, { "epoch": 1.2069055036344756, "grad_norm": 10.277782440185547, "learning_rate": 2.1154416389119163e-06, "loss": 0.080791175365448, "step": 4649 }, { "epoch": 1.2071651090342679, "grad_norm": 9.2972412109375, "learning_rate": 2.114534087035316e-06, "loss": 0.09093306958675385, "step": 4650 }, { "epoch": 1.2074247144340602, "grad_norm": 6.952903747558594, "learning_rate": 2.1136266474945387e-06, "loss": 0.2101983278989792, "step": 4651 }, { "epoch": 1.2076843198338525, "grad_norm": 5.294980049133301, "learning_rate": 2.112719320449999e-06, "loss": 0.03627759590744972, "step": 4652 }, { "epoch": 1.2079439252336448, "grad_norm": 8.757675170898438, "learning_rate": 2.111812106062092e-06, "loss": 0.1802167296409607, "step": 4653 }, { "epoch": 1.208203530633437, "grad_norm": 8.756128311157227, "learning_rate": 2.1109050044911922e-06, "loss": 0.10839308053255081, "step": 4654 }, { "epoch": 1.2084631360332294, "grad_norm": 10.662908554077148, "learning_rate": 2.109998015897654e-06, "loss": 0.06850114464759827, "step": 4655 }, { "epoch": 1.2087227414330217, "grad_norm": 9.668084144592285, "learning_rate": 2.1090911404418123e-06, "loss": 0.03356294333934784, "step": 4656 }, { "epoch": 1.208982346832814, "grad_norm": 9.285943031311035, "learning_rate": 2.108184378283982e-06, "loss": 0.02791164629161358, "step": 4657 }, { "epoch": 1.2092419522326066, "grad_norm": 11.137591361999512, "learning_rate": 2.107277729584459e-06, "loss": 0.09694644808769226, "step": 4658 }, { "epoch": 1.2095015576323989, "grad_norm": 5.668270587921143, "learning_rate": 2.106371194503516e-06, "loss": 0.2489633411169052, "step": 4659 }, { "epoch": 1.2097611630321912, "grad_norm": 10.918326377868652, "learning_rate": 2.1054647732014088e-06, "loss": 0.1213553324341774, "step": 4660 }, { "epoch": 1.2100207684319835, "grad_norm": 10.618391036987305, "learning_rate": 2.1045584658383718e-06, "loss": 0.1482020616531372, "step": 4661 }, { "epoch": 1.2102803738317758, "grad_norm": 9.435270309448242, "learning_rate": 2.1036522725746207e-06, "loss": 0.1641891598701477, "step": 4662 }, { "epoch": 1.210539979231568, "grad_norm": 6.27753210067749, "learning_rate": 2.102746193570346e-06, "loss": 0.1738489270210266, "step": 4663 }, { "epoch": 1.2107995846313604, "grad_norm": 11.783909797668457, "learning_rate": 2.1018402289857254e-06, "loss": 0.07629648596048355, "step": 4664 }, { "epoch": 1.2110591900311527, "grad_norm": 9.692817687988281, "learning_rate": 2.1009343789809116e-06, "loss": 0.11456688493490219, "step": 4665 }, { "epoch": 1.211318795430945, "grad_norm": 8.049180030822754, "learning_rate": 2.1000286437160385e-06, "loss": 0.07946246862411499, "step": 4666 }, { "epoch": 1.2115784008307373, "grad_norm": 6.095989227294922, "learning_rate": 2.0991230233512177e-06, "loss": 0.1836269497871399, "step": 4667 }, { "epoch": 1.2118380062305296, "grad_norm": 6.517849922180176, "learning_rate": 2.098217518046543e-06, "loss": 0.022755295038223267, "step": 4668 }, { "epoch": 1.212097611630322, "grad_norm": 8.209275245666504, "learning_rate": 2.097312127962088e-06, "loss": 0.13803459703922272, "step": 4669 }, { "epoch": 1.2123572170301142, "grad_norm": 4.6693267822265625, "learning_rate": 2.0964068532579047e-06, "loss": 0.03546006232500076, "step": 4670 }, { "epoch": 1.2126168224299065, "grad_norm": 6.659671783447266, "learning_rate": 2.095501694094024e-06, "loss": 0.22705766558647156, "step": 4671 }, { "epoch": 1.2128764278296988, "grad_norm": 8.314423561096191, "learning_rate": 2.094596650630457e-06, "loss": 0.1609300673007965, "step": 4672 }, { "epoch": 1.2131360332294912, "grad_norm": 13.84434700012207, "learning_rate": 2.093691723027196e-06, "loss": 0.14961273968219757, "step": 4673 }, { "epoch": 1.2133956386292835, "grad_norm": 11.375476837158203, "learning_rate": 2.0927869114442118e-06, "loss": 0.14643819630146027, "step": 4674 }, { "epoch": 1.2136552440290758, "grad_norm": 15.65027904510498, "learning_rate": 2.091882216041452e-06, "loss": 0.06732474267482758, "step": 4675 }, { "epoch": 1.213914849428868, "grad_norm": 5.673339366912842, "learning_rate": 2.090977636978848e-06, "loss": 0.27278417348861694, "step": 4676 }, { "epoch": 1.2141744548286604, "grad_norm": 9.132843017578125, "learning_rate": 2.090073174416308e-06, "loss": 0.09954053163528442, "step": 4677 }, { "epoch": 1.2144340602284527, "grad_norm": 6.94979190826416, "learning_rate": 2.089168828513722e-06, "loss": 0.13105878233909607, "step": 4678 }, { "epoch": 1.214693665628245, "grad_norm": 8.055228233337402, "learning_rate": 2.0882645994309543e-06, "loss": 0.22684642672538757, "step": 4679 }, { "epoch": 1.2149532710280373, "grad_norm": 8.693262100219727, "learning_rate": 2.0873604873278543e-06, "loss": 0.04940028488636017, "step": 4680 }, { "epoch": 1.2152128764278296, "grad_norm": 7.849094390869141, "learning_rate": 2.086456492364247e-06, "loss": 0.13722871243953705, "step": 4681 }, { "epoch": 1.215472481827622, "grad_norm": 7.0106964111328125, "learning_rate": 2.08555261469994e-06, "loss": 0.029682893306016922, "step": 4682 }, { "epoch": 1.2157320872274142, "grad_norm": 11.777093887329102, "learning_rate": 2.084648854494716e-06, "loss": 0.056632187217473984, "step": 4683 }, { "epoch": 1.2159916926272065, "grad_norm": 6.251913547515869, "learning_rate": 2.08374521190834e-06, "loss": 0.22670790553092957, "step": 4684 }, { "epoch": 1.216251298026999, "grad_norm": 10.019641876220703, "learning_rate": 2.082841687100556e-06, "loss": 0.06841126829385757, "step": 4685 }, { "epoch": 1.2165109034267914, "grad_norm": 6.072206974029541, "learning_rate": 2.0819382802310857e-06, "loss": 0.2303040474653244, "step": 4686 }, { "epoch": 1.2167705088265837, "grad_norm": 6.722197532653809, "learning_rate": 2.08103499145963e-06, "loss": 0.18851003050804138, "step": 4687 }, { "epoch": 1.217030114226376, "grad_norm": 7.652526378631592, "learning_rate": 2.080131820945871e-06, "loss": 0.041697755455970764, "step": 4688 }, { "epoch": 1.2172897196261683, "grad_norm": 9.630241394042969, "learning_rate": 2.0792287688494683e-06, "loss": 0.05835229903459549, "step": 4689 }, { "epoch": 1.2175493250259606, "grad_norm": 7.594051361083984, "learning_rate": 2.0783258353300607e-06, "loss": 0.07319997996091843, "step": 4690 }, { "epoch": 1.217808930425753, "grad_norm": 6.918856620788574, "learning_rate": 2.0774230205472657e-06, "loss": 0.11157875508069992, "step": 4691 }, { "epoch": 1.2180685358255452, "grad_norm": 5.388318061828613, "learning_rate": 2.0765203246606806e-06, "loss": 0.03052261844277382, "step": 4692 }, { "epoch": 1.2183281412253375, "grad_norm": 11.452116012573242, "learning_rate": 2.0756177478298824e-06, "loss": 0.15787121653556824, "step": 4693 }, { "epoch": 1.2185877466251298, "grad_norm": 7.480097770690918, "learning_rate": 2.0747152902144243e-06, "loss": 0.046021778136491776, "step": 4694 }, { "epoch": 1.2188473520249221, "grad_norm": 8.73959732055664, "learning_rate": 2.073812951973841e-06, "loss": 0.1276387721300125, "step": 4695 }, { "epoch": 1.2191069574247144, "grad_norm": 8.396000862121582, "learning_rate": 2.072910733267645e-06, "loss": 0.03275563567876816, "step": 4696 }, { "epoch": 1.2193665628245067, "grad_norm": 8.892261505126953, "learning_rate": 2.072008634255329e-06, "loss": 0.05599111318588257, "step": 4697 }, { "epoch": 1.219626168224299, "grad_norm": 8.904850959777832, "learning_rate": 2.0711066550963615e-06, "loss": 0.09180107712745667, "step": 4698 }, { "epoch": 1.2198857736240913, "grad_norm": 10.296887397766113, "learning_rate": 2.070204795950193e-06, "loss": 0.12035948783159256, "step": 4699 }, { "epoch": 1.2201453790238836, "grad_norm": 9.868876457214355, "learning_rate": 2.069303056976251e-06, "loss": 0.23237933218479156, "step": 4700 }, { "epoch": 1.220404984423676, "grad_norm": 9.863251686096191, "learning_rate": 2.0684014383339447e-06, "loss": 0.04219231754541397, "step": 4701 }, { "epoch": 1.2206645898234683, "grad_norm": 11.67758560180664, "learning_rate": 2.0674999401826558e-06, "loss": 0.08379153907299042, "step": 4702 }, { "epoch": 1.2209241952232606, "grad_norm": 7.435099124908447, "learning_rate": 2.0665985626817496e-06, "loss": 0.24491925537586212, "step": 4703 }, { "epoch": 1.2211838006230529, "grad_norm": 10.27348518371582, "learning_rate": 2.06569730599057e-06, "loss": 0.05682019144296646, "step": 4704 }, { "epoch": 1.2214434060228452, "grad_norm": 7.251338005065918, "learning_rate": 2.06479617026844e-06, "loss": 0.21208405494689941, "step": 4705 }, { "epoch": 1.2217030114226377, "grad_norm": 10.224546432495117, "learning_rate": 2.063895155674657e-06, "loss": 0.1555236130952835, "step": 4706 }, { "epoch": 1.22196261682243, "grad_norm": 7.638967514038086, "learning_rate": 2.0629942623685e-06, "loss": 0.0380333848297596, "step": 4707 }, { "epoch": 1.2222222222222223, "grad_norm": 15.887825012207031, "learning_rate": 2.0620934905092273e-06, "loss": 0.10890902578830719, "step": 4708 }, { "epoch": 1.2224818276220146, "grad_norm": 13.061589241027832, "learning_rate": 2.0611928402560756e-06, "loss": 0.1369403600692749, "step": 4709 }, { "epoch": 1.222741433021807, "grad_norm": 9.545136451721191, "learning_rate": 2.0602923117682573e-06, "loss": 0.1219087541103363, "step": 4710 }, { "epoch": 1.2230010384215992, "grad_norm": 11.813435554504395, "learning_rate": 2.059391905204966e-06, "loss": 0.11139345169067383, "step": 4711 }, { "epoch": 1.2232606438213915, "grad_norm": 8.200335502624512, "learning_rate": 2.0584916207253736e-06, "loss": 0.2191491425037384, "step": 4712 }, { "epoch": 1.2235202492211839, "grad_norm": 8.438422203063965, "learning_rate": 2.0575914584886285e-06, "loss": 0.20346778631210327, "step": 4713 }, { "epoch": 1.2237798546209762, "grad_norm": 9.20616340637207, "learning_rate": 2.0566914186538596e-06, "loss": 0.11287759244441986, "step": 4714 }, { "epoch": 1.2240394600207685, "grad_norm": 10.398887634277344, "learning_rate": 2.0557915013801732e-06, "loss": 0.04146546125411987, "step": 4715 }, { "epoch": 1.2242990654205608, "grad_norm": 7.917276382446289, "learning_rate": 2.054891706826655e-06, "loss": 0.18241488933563232, "step": 4716 }, { "epoch": 1.224558670820353, "grad_norm": 7.051062107086182, "learning_rate": 2.053992035152366e-06, "loss": 0.18877050280570984, "step": 4717 }, { "epoch": 1.2248182762201454, "grad_norm": 6.4709978103637695, "learning_rate": 2.053092486516349e-06, "loss": 0.15174883604049683, "step": 4718 }, { "epoch": 1.2250778816199377, "grad_norm": 7.879971981048584, "learning_rate": 2.0521930610776235e-06, "loss": 0.15810859203338623, "step": 4719 }, { "epoch": 1.22533748701973, "grad_norm": 9.744800567626953, "learning_rate": 2.0512937589951877e-06, "loss": 0.16116021573543549, "step": 4720 }, { "epoch": 1.2255970924195223, "grad_norm": 10.935457229614258, "learning_rate": 2.050394580428016e-06, "loss": 0.043348152190446854, "step": 4721 }, { "epoch": 1.2258566978193146, "grad_norm": 9.236725807189941, "learning_rate": 2.049495525535064e-06, "loss": 0.18442071974277496, "step": 4722 }, { "epoch": 1.226116303219107, "grad_norm": 8.489778518676758, "learning_rate": 2.048596594475264e-06, "loss": 0.10228724032640457, "step": 4723 }, { "epoch": 1.2263759086188992, "grad_norm": 6.254144668579102, "learning_rate": 2.047697787407526e-06, "loss": 0.22755394876003265, "step": 4724 }, { "epoch": 1.2266355140186915, "grad_norm": 12.89907169342041, "learning_rate": 2.046799104490738e-06, "loss": 0.11962635070085526, "step": 4725 }, { "epoch": 1.2268951194184838, "grad_norm": 4.9751105308532715, "learning_rate": 2.045900545883768e-06, "loss": 0.030154822394251823, "step": 4726 }, { "epoch": 1.2271547248182761, "grad_norm": 9.911648750305176, "learning_rate": 2.045002111745459e-06, "loss": 0.06628786027431488, "step": 4727 }, { "epoch": 1.2274143302180685, "grad_norm": 8.436751365661621, "learning_rate": 2.0441038022346354e-06, "loss": 0.0472220815718174, "step": 4728 }, { "epoch": 1.2276739356178608, "grad_norm": 8.640463829040527, "learning_rate": 2.0432056175100957e-06, "loss": 0.08761430531740189, "step": 4729 }, { "epoch": 1.227933541017653, "grad_norm": 8.998905181884766, "learning_rate": 2.0423075577306194e-06, "loss": 0.1201486736536026, "step": 4730 }, { "epoch": 1.2281931464174454, "grad_norm": 7.26038122177124, "learning_rate": 2.041409623054963e-06, "loss": 0.09381077438592911, "step": 4731 }, { "epoch": 1.2284527518172377, "grad_norm": 8.62389850616455, "learning_rate": 2.040511813641862e-06, "loss": 0.22457289695739746, "step": 4732 }, { "epoch": 1.2287123572170302, "grad_norm": 8.048633575439453, "learning_rate": 2.0396141296500256e-06, "loss": 0.06108084321022034, "step": 4733 }, { "epoch": 1.2289719626168225, "grad_norm": 7.738375186920166, "learning_rate": 2.038716571238145e-06, "loss": 0.04403146728873253, "step": 4734 }, { "epoch": 1.2292315680166148, "grad_norm": 6.061878204345703, "learning_rate": 2.037819138564889e-06, "loss": 0.3010534346103668, "step": 4735 }, { "epoch": 1.2294911734164071, "grad_norm": 6.1730828285217285, "learning_rate": 2.036921831788904e-06, "loss": 0.19135156273841858, "step": 4736 }, { "epoch": 1.2297507788161994, "grad_norm": 6.361129283905029, "learning_rate": 2.0360246510688102e-06, "loss": 0.08530541509389877, "step": 4737 }, { "epoch": 1.2300103842159917, "grad_norm": 10.25098705291748, "learning_rate": 2.0351275965632104e-06, "loss": 0.13557402789592743, "step": 4738 }, { "epoch": 1.230269989615784, "grad_norm": 11.008620262145996, "learning_rate": 2.0342306684306834e-06, "loss": 0.07903453707695007, "step": 4739 }, { "epoch": 1.2305295950155763, "grad_norm": 6.74608850479126, "learning_rate": 2.033333866829785e-06, "loss": 0.071754090487957, "step": 4740 }, { "epoch": 1.2307892004153687, "grad_norm": 9.01308536529541, "learning_rate": 2.03243719191905e-06, "loss": 0.027859751135110855, "step": 4741 }, { "epoch": 1.231048805815161, "grad_norm": 9.111356735229492, "learning_rate": 2.031540643856989e-06, "loss": 0.07132696360349655, "step": 4742 }, { "epoch": 1.2313084112149533, "grad_norm": 9.163458824157715, "learning_rate": 2.0306442228020917e-06, "loss": 0.05936414748430252, "step": 4743 }, { "epoch": 1.2315680166147456, "grad_norm": 6.995147705078125, "learning_rate": 2.0297479289128246e-06, "loss": 0.24313081800937653, "step": 4744 }, { "epoch": 1.2318276220145379, "grad_norm": 7.97074556350708, "learning_rate": 2.0288517623476324e-06, "loss": 0.05307861790060997, "step": 4745 }, { "epoch": 1.2320872274143302, "grad_norm": 9.099785804748535, "learning_rate": 2.027955723264936e-06, "loss": 0.23325496912002563, "step": 4746 }, { "epoch": 1.2323468328141225, "grad_norm": 12.0484037399292, "learning_rate": 2.027059811823136e-06, "loss": 0.09666237235069275, "step": 4747 }, { "epoch": 1.2326064382139148, "grad_norm": 7.8925676345825195, "learning_rate": 2.026164028180608e-06, "loss": 0.25719523429870605, "step": 4748 }, { "epoch": 1.232866043613707, "grad_norm": 8.697340965270996, "learning_rate": 2.0252683724957052e-06, "loss": 0.053139325231313705, "step": 4749 }, { "epoch": 1.2331256490134994, "grad_norm": 7.5903191566467285, "learning_rate": 2.02437284492676e-06, "loss": 0.14581775665283203, "step": 4750 }, { "epoch": 1.2333852544132917, "grad_norm": 7.861023426055908, "learning_rate": 2.0234774456320823e-06, "loss": 0.07742588967084885, "step": 4751 }, { "epoch": 1.233644859813084, "grad_norm": 8.060863494873047, "learning_rate": 2.0225821747699566e-06, "loss": 0.11559146642684937, "step": 4752 }, { "epoch": 1.2339044652128763, "grad_norm": 13.21701717376709, "learning_rate": 2.0216870324986466e-06, "loss": 0.10426853597164154, "step": 4753 }, { "epoch": 1.2341640706126689, "grad_norm": 10.966349601745605, "learning_rate": 2.020792018976393e-06, "loss": 0.04227614402770996, "step": 4754 }, { "epoch": 1.2344236760124612, "grad_norm": 9.802338600158691, "learning_rate": 2.0198971343614136e-06, "loss": 0.1604059785604477, "step": 4755 }, { "epoch": 1.2346832814122535, "grad_norm": 7.849728584289551, "learning_rate": 2.0190023788119044e-06, "loss": 0.15245255827903748, "step": 4756 }, { "epoch": 1.2349428868120458, "grad_norm": 7.429351329803467, "learning_rate": 2.018107752486036e-06, "loss": 0.03550054877996445, "step": 4757 }, { "epoch": 1.235202492211838, "grad_norm": 6.086063861846924, "learning_rate": 2.01721325554196e-06, "loss": 0.02796274609863758, "step": 4758 }, { "epoch": 1.2354620976116304, "grad_norm": 6.975172519683838, "learning_rate": 2.0163188881378017e-06, "loss": 0.021380731835961342, "step": 4759 }, { "epoch": 1.2357217030114227, "grad_norm": 7.413137912750244, "learning_rate": 2.0154246504316637e-06, "loss": 0.06784995645284653, "step": 4760 }, { "epoch": 1.235981308411215, "grad_norm": 8.44235610961914, "learning_rate": 2.0145305425816287e-06, "loss": 0.058687638491392136, "step": 4761 }, { "epoch": 1.2362409138110073, "grad_norm": 8.082274436950684, "learning_rate": 2.013636564745754e-06, "loss": 0.062268808484077454, "step": 4762 }, { "epoch": 1.2365005192107996, "grad_norm": 6.859047889709473, "learning_rate": 2.0127427170820746e-06, "loss": 0.17241430282592773, "step": 4763 }, { "epoch": 1.236760124610592, "grad_norm": 7.46274471282959, "learning_rate": 2.0118489997486013e-06, "loss": 0.19457530975341797, "step": 4764 }, { "epoch": 1.2370197300103842, "grad_norm": 6.565465450286865, "learning_rate": 2.0109554129033225e-06, "loss": 0.20891070365905762, "step": 4765 }, { "epoch": 1.2372793354101765, "grad_norm": 10.886513710021973, "learning_rate": 2.0100619567042068e-06, "loss": 0.059502311050891876, "step": 4766 }, { "epoch": 1.2375389408099688, "grad_norm": 5.52951717376709, "learning_rate": 2.0091686313091933e-06, "loss": 0.042083289474248886, "step": 4767 }, { "epoch": 1.2377985462097612, "grad_norm": 7.738126277923584, "learning_rate": 2.0082754368762036e-06, "loss": 0.04065471142530441, "step": 4768 }, { "epoch": 1.2380581516095535, "grad_norm": 5.486522674560547, "learning_rate": 2.0073823735631324e-06, "loss": 0.03413047641515732, "step": 4769 }, { "epoch": 1.2383177570093458, "grad_norm": 9.187861442565918, "learning_rate": 2.006489441527855e-06, "loss": 0.1749497354030609, "step": 4770 }, { "epoch": 1.238577362409138, "grad_norm": 10.286072731018066, "learning_rate": 2.00559664092822e-06, "loss": 0.13421133160591125, "step": 4771 }, { "epoch": 1.2388369678089304, "grad_norm": 9.595965385437012, "learning_rate": 2.004703971922054e-06, "loss": 0.11250531673431396, "step": 4772 }, { "epoch": 1.2390965732087227, "grad_norm": 11.109808921813965, "learning_rate": 2.0038114346671612e-06, "loss": 0.060745395720005035, "step": 4773 }, { "epoch": 1.239356178608515, "grad_norm": 9.304972648620605, "learning_rate": 2.0029190293213213e-06, "loss": 0.1665078103542328, "step": 4774 }, { "epoch": 1.2396157840083073, "grad_norm": 12.735357284545898, "learning_rate": 2.002026756042291e-06, "loss": 0.07528530061244965, "step": 4775 }, { "epoch": 1.2398753894080996, "grad_norm": 8.896705627441406, "learning_rate": 2.0011346149878032e-06, "loss": 0.1234116181731224, "step": 4776 }, { "epoch": 1.240134994807892, "grad_norm": 8.829682350158691, "learning_rate": 2.0002426063155694e-06, "loss": 0.18657377362251282, "step": 4777 }, { "epoch": 1.2403946002076842, "grad_norm": 10.806290626525879, "learning_rate": 1.999350730183276e-06, "loss": 0.05789273977279663, "step": 4778 }, { "epoch": 1.2406542056074765, "grad_norm": 5.986395835876465, "learning_rate": 1.998458986748585e-06, "loss": 0.28730496764183044, "step": 4779 }, { "epoch": 1.2409138110072688, "grad_norm": 11.057390213012695, "learning_rate": 1.997567376169137e-06, "loss": 0.08475841581821442, "step": 4780 }, { "epoch": 1.2411734164070614, "grad_norm": 5.948795795440674, "learning_rate": 1.99667589860255e-06, "loss": 0.043172258883714676, "step": 4781 }, { "epoch": 1.2414330218068537, "grad_norm": 6.572815418243408, "learning_rate": 1.995784554206414e-06, "loss": 0.07523360103368759, "step": 4782 }, { "epoch": 1.241692627206646, "grad_norm": 5.508847236633301, "learning_rate": 1.9948933431383e-06, "loss": 0.041059356182813644, "step": 4783 }, { "epoch": 1.2419522326064383, "grad_norm": 5.985393524169922, "learning_rate": 1.9940022655557527e-06, "loss": 0.05003877729177475, "step": 4784 }, { "epoch": 1.2422118380062306, "grad_norm": 8.279454231262207, "learning_rate": 1.9931113216162956e-06, "loss": 0.08259780704975128, "step": 4785 }, { "epoch": 1.242471443406023, "grad_norm": 9.41423511505127, "learning_rate": 1.992220511477426e-06, "loss": 0.09618361294269562, "step": 4786 }, { "epoch": 1.2427310488058152, "grad_norm": 8.908735275268555, "learning_rate": 1.9913298352966193e-06, "loss": 0.11232073605060577, "step": 4787 }, { "epoch": 1.2429906542056075, "grad_norm": 7.23970890045166, "learning_rate": 1.990439293231326e-06, "loss": 0.10330250859260559, "step": 4788 }, { "epoch": 1.2432502596053998, "grad_norm": 7.976537227630615, "learning_rate": 1.9895488854389744e-06, "loss": 0.07933133840560913, "step": 4789 }, { "epoch": 1.2435098650051921, "grad_norm": 7.09626579284668, "learning_rate": 1.9886586120769685e-06, "loss": 0.04202502593398094, "step": 4790 }, { "epoch": 1.2437694704049844, "grad_norm": 10.220295906066895, "learning_rate": 1.9877684733026865e-06, "loss": 0.2518519163131714, "step": 4791 }, { "epoch": 1.2440290758047767, "grad_norm": 4.179283142089844, "learning_rate": 1.986878469273486e-06, "loss": 0.009675267152488232, "step": 4792 }, { "epoch": 1.244288681204569, "grad_norm": 6.191839218139648, "learning_rate": 1.9859886001466988e-06, "loss": 0.28335055708885193, "step": 4793 }, { "epoch": 1.2445482866043613, "grad_norm": 7.4417405128479, "learning_rate": 1.9850988660796344e-06, "loss": 0.013310054317116737, "step": 4794 }, { "epoch": 1.2448078920041536, "grad_norm": 7.743217468261719, "learning_rate": 1.984209267229576e-06, "loss": 0.24782541394233704, "step": 4795 }, { "epoch": 1.245067497403946, "grad_norm": 10.880047798156738, "learning_rate": 1.9833198037537844e-06, "loss": 0.15025272965431213, "step": 4796 }, { "epoch": 1.2453271028037383, "grad_norm": 9.170848846435547, "learning_rate": 1.982430475809498e-06, "loss": 0.10746560245752335, "step": 4797 }, { "epoch": 1.2455867082035306, "grad_norm": 9.389032363891602, "learning_rate": 1.9815412835539277e-06, "loss": 0.16830305755138397, "step": 4798 }, { "epoch": 1.2458463136033229, "grad_norm": 10.324564933776855, "learning_rate": 1.9806522271442624e-06, "loss": 0.05366497114300728, "step": 4799 }, { "epoch": 1.2461059190031152, "grad_norm": 12.944724082946777, "learning_rate": 1.979763306737668e-06, "loss": 0.020124292001128197, "step": 4800 }, { "epoch": 1.2463655244029075, "grad_norm": 8.674074172973633, "learning_rate": 1.978874522491286e-06, "loss": 0.1547996997833252, "step": 4801 }, { "epoch": 1.2466251298027, "grad_norm": 2.783963680267334, "learning_rate": 1.977985874562231e-06, "loss": 0.018286248669028282, "step": 4802 }, { "epoch": 1.2468847352024923, "grad_norm": 12.909789085388184, "learning_rate": 1.977097363107597e-06, "loss": 0.08975712209939957, "step": 4803 }, { "epoch": 1.2471443406022846, "grad_norm": 9.258929252624512, "learning_rate": 1.9762089882844517e-06, "loss": 0.09066082537174225, "step": 4804 }, { "epoch": 1.247403946002077, "grad_norm": 7.817858695983887, "learning_rate": 1.97532075024984e-06, "loss": 0.25063103437423706, "step": 4805 }, { "epoch": 1.2476635514018692, "grad_norm": 6.9454665184021, "learning_rate": 1.974432649160782e-06, "loss": 0.049297966063022614, "step": 4806 }, { "epoch": 1.2479231568016615, "grad_norm": 7.653895854949951, "learning_rate": 1.973544685174273e-06, "loss": 0.027127522975206375, "step": 4807 }, { "epoch": 1.2481827622014539, "grad_norm": 8.843891143798828, "learning_rate": 1.972656858447285e-06, "loss": 0.08801546692848206, "step": 4808 }, { "epoch": 1.2484423676012462, "grad_norm": 8.109258651733398, "learning_rate": 1.971769169136767e-06, "loss": 0.018560105934739113, "step": 4809 }, { "epoch": 1.2487019730010385, "grad_norm": 6.901128768920898, "learning_rate": 1.9708816173996392e-06, "loss": 0.20227491855621338, "step": 4810 }, { "epoch": 1.2489615784008308, "grad_norm": 8.461516380310059, "learning_rate": 1.969994203392803e-06, "loss": 0.1710452139377594, "step": 4811 }, { "epoch": 1.249221183800623, "grad_norm": 9.930597305297852, "learning_rate": 1.969106927273132e-06, "loss": 0.0870877280831337, "step": 4812 }, { "epoch": 1.2494807892004154, "grad_norm": 8.172057151794434, "learning_rate": 1.9682197891974753e-06, "loss": 0.11783383786678314, "step": 4813 }, { "epoch": 1.2497403946002077, "grad_norm": 9.450833320617676, "learning_rate": 1.9673327893226603e-06, "loss": 0.09628751128911972, "step": 4814 }, { "epoch": 1.25, "grad_norm": 9.251690864562988, "learning_rate": 1.9664459278054866e-06, "loss": 0.06175648421049118, "step": 4815 }, { "epoch": 1.2502596053997923, "grad_norm": 7.475177764892578, "learning_rate": 1.9655592048027324e-06, "loss": 0.03206311911344528, "step": 4816 }, { "epoch": 1.2505192107995846, "grad_norm": 5.752090930938721, "learning_rate": 1.964672620471149e-06, "loss": 0.05155231058597565, "step": 4817 }, { "epoch": 1.250778816199377, "grad_norm": 11.446805953979492, "learning_rate": 1.963786174967465e-06, "loss": 0.032467857003211975, "step": 4818 }, { "epoch": 1.2510384215991692, "grad_norm": 10.591736793518066, "learning_rate": 1.9628998684483835e-06, "loss": 0.07554789632558823, "step": 4819 }, { "epoch": 1.2512980269989615, "grad_norm": 13.9821195602417, "learning_rate": 1.962013701070583e-06, "loss": 0.034749165177345276, "step": 4820 }, { "epoch": 1.2515576323987538, "grad_norm": 11.666523933410645, "learning_rate": 1.9611276729907187e-06, "loss": 0.045703254640102386, "step": 4821 }, { "epoch": 1.2518172377985461, "grad_norm": 10.168021202087402, "learning_rate": 1.960241784365417e-06, "loss": 0.14330258965492249, "step": 4822 }, { "epoch": 1.2520768431983385, "grad_norm": 10.449670791625977, "learning_rate": 1.959356035351286e-06, "loss": 0.12819045782089233, "step": 4823 }, { "epoch": 1.2523364485981308, "grad_norm": 8.201593399047852, "learning_rate": 1.9584704261049047e-06, "loss": 0.03628162667155266, "step": 4824 }, { "epoch": 1.252596053997923, "grad_norm": 9.226067543029785, "learning_rate": 1.957584956782828e-06, "loss": 0.10703593492507935, "step": 4825 }, { "epoch": 1.2528556593977154, "grad_norm": 9.054669380187988, "learning_rate": 1.956699627541587e-06, "loss": 0.15356040000915527, "step": 4826 }, { "epoch": 1.2531152647975077, "grad_norm": 2.1985819339752197, "learning_rate": 1.9558144385376877e-06, "loss": 0.005850640591233969, "step": 4827 }, { "epoch": 1.2533748701973, "grad_norm": 7.577762126922607, "learning_rate": 1.9549293899276115e-06, "loss": 0.04385862126946449, "step": 4828 }, { "epoch": 1.2536344755970923, "grad_norm": 9.380462646484375, "learning_rate": 1.9540444818678146e-06, "loss": 0.15108227729797363, "step": 4829 }, { "epoch": 1.2538940809968846, "grad_norm": 6.860110759735107, "learning_rate": 1.953159714514728e-06, "loss": 0.2313363403081894, "step": 4830 }, { "epoch": 1.2541536863966771, "grad_norm": 10.341517448425293, "learning_rate": 1.952275088024758e-06, "loss": 0.16139882802963257, "step": 4831 }, { "epoch": 1.2544132917964694, "grad_norm": 6.5441484451293945, "learning_rate": 1.9513906025542883e-06, "loss": 0.0863184854388237, "step": 4832 }, { "epoch": 1.2546728971962617, "grad_norm": 6.628525257110596, "learning_rate": 1.9505062582596735e-06, "loss": 0.2150544375181198, "step": 4833 }, { "epoch": 1.254932502596054, "grad_norm": 11.661622047424316, "learning_rate": 1.9496220552972467e-06, "loss": 0.12381114065647125, "step": 4834 }, { "epoch": 1.2551921079958464, "grad_norm": 9.495481491088867, "learning_rate": 1.9487379938233136e-06, "loss": 0.08511920273303986, "step": 4835 }, { "epoch": 1.2554517133956387, "grad_norm": 6.490967273712158, "learning_rate": 1.9478540739941577e-06, "loss": 0.1897190809249878, "step": 4836 }, { "epoch": 1.255711318795431, "grad_norm": 8.05226993560791, "learning_rate": 1.946970295966034e-06, "loss": 0.02977442741394043, "step": 4837 }, { "epoch": 1.2559709241952233, "grad_norm": 14.709362030029297, "learning_rate": 1.9460866598951748e-06, "loss": 0.11283669620752335, "step": 4838 }, { "epoch": 1.2562305295950156, "grad_norm": 8.069502830505371, "learning_rate": 1.9452031659377874e-06, "loss": 0.04885166138410568, "step": 4839 }, { "epoch": 1.2564901349948079, "grad_norm": 9.191778182983398, "learning_rate": 1.9443198142500537e-06, "loss": 0.0732215940952301, "step": 4840 }, { "epoch": 1.2567497403946002, "grad_norm": 7.993277072906494, "learning_rate": 1.943436604988128e-06, "loss": 0.15493369102478027, "step": 4841 }, { "epoch": 1.2570093457943925, "grad_norm": 10.299812316894531, "learning_rate": 1.9425535383081434e-06, "loss": 0.04024548456072807, "step": 4842 }, { "epoch": 1.2572689511941848, "grad_norm": 7.564662456512451, "learning_rate": 1.9416706143662044e-06, "loss": 0.13775454461574554, "step": 4843 }, { "epoch": 1.257528556593977, "grad_norm": 10.179481506347656, "learning_rate": 1.9407878333183933e-06, "loss": 0.12035803496837616, "step": 4844 }, { "epoch": 1.2577881619937694, "grad_norm": 6.472253322601318, "learning_rate": 1.9399051953207643e-06, "loss": 0.23351237177848816, "step": 4845 }, { "epoch": 1.2580477673935617, "grad_norm": 11.524459838867188, "learning_rate": 1.939022700529348e-06, "loss": 0.05193512514233589, "step": 4846 }, { "epoch": 1.258307372793354, "grad_norm": 7.223514080047607, "learning_rate": 1.9381403491001492e-06, "loss": 0.053256481885910034, "step": 4847 }, { "epoch": 1.2585669781931463, "grad_norm": 9.342476844787598, "learning_rate": 1.9372581411891485e-06, "loss": 0.11445850878953934, "step": 4848 }, { "epoch": 1.2588265835929389, "grad_norm": 11.614006996154785, "learning_rate": 1.9363760769522982e-06, "loss": 0.12970836460590363, "step": 4849 }, { "epoch": 1.2590861889927312, "grad_norm": 11.100089073181152, "learning_rate": 1.935494156545528e-06, "loss": 0.1550859659910202, "step": 4850 }, { "epoch": 1.2593457943925235, "grad_norm": 9.787172317504883, "learning_rate": 1.9346123801247422e-06, "loss": 0.062062568962574005, "step": 4851 }, { "epoch": 1.2596053997923158, "grad_norm": 7.699206352233887, "learning_rate": 1.9337307478458167e-06, "loss": 0.04599232226610184, "step": 4852 }, { "epoch": 1.259865005192108, "grad_norm": 7.915972709655762, "learning_rate": 1.9328492598646047e-06, "loss": 0.03606801480054855, "step": 4853 }, { "epoch": 1.2601246105919004, "grad_norm": 11.695398330688477, "learning_rate": 1.9319679163369336e-06, "loss": 0.09504000842571259, "step": 4854 }, { "epoch": 1.2603842159916927, "grad_norm": 8.582366943359375, "learning_rate": 1.9310867174186054e-06, "loss": 0.10691752284765244, "step": 4855 }, { "epoch": 1.260643821391485, "grad_norm": 8.887121200561523, "learning_rate": 1.9302056632653937e-06, "loss": 0.04094665125012398, "step": 4856 }, { "epoch": 1.2609034267912773, "grad_norm": 5.925146579742432, "learning_rate": 1.92932475403305e-06, "loss": 0.015014709904789925, "step": 4857 }, { "epoch": 1.2611630321910696, "grad_norm": 8.713739395141602, "learning_rate": 1.9284439898772994e-06, "loss": 0.13533149659633636, "step": 4858 }, { "epoch": 1.261422637590862, "grad_norm": 9.735359191894531, "learning_rate": 1.9275633709538403e-06, "loss": 0.1312168836593628, "step": 4859 }, { "epoch": 1.2616822429906542, "grad_norm": 9.250904083251953, "learning_rate": 1.9266828974183456e-06, "loss": 0.07816487550735474, "step": 4860 }, { "epoch": 1.2619418483904465, "grad_norm": 13.342611312866211, "learning_rate": 1.925802569426463e-06, "loss": 0.09530492126941681, "step": 4861 }, { "epoch": 1.2622014537902388, "grad_norm": 7.719795227050781, "learning_rate": 1.9249223871338142e-06, "loss": 0.03622391074895859, "step": 4862 }, { "epoch": 1.2624610591900312, "grad_norm": 8.93973159790039, "learning_rate": 1.924042350695997e-06, "loss": 0.05156593769788742, "step": 4863 }, { "epoch": 1.2627206645898235, "grad_norm": 6.182646751403809, "learning_rate": 1.9231624602685787e-06, "loss": 0.2408429980278015, "step": 4864 }, { "epoch": 1.2629802699896158, "grad_norm": 9.9692964553833, "learning_rate": 1.922282716007106e-06, "loss": 0.11096808314323425, "step": 4865 }, { "epoch": 1.263239875389408, "grad_norm": 11.017472267150879, "learning_rate": 1.9214031180670973e-06, "loss": 0.06323234736919403, "step": 4866 }, { "epoch": 1.2634994807892004, "grad_norm": 6.7051873207092285, "learning_rate": 1.9205236666040443e-06, "loss": 0.14300322532653809, "step": 4867 }, { "epoch": 1.2637590861889927, "grad_norm": 9.224350929260254, "learning_rate": 1.919644361773415e-06, "loss": 0.03634585812687874, "step": 4868 }, { "epoch": 1.264018691588785, "grad_norm": 7.690825462341309, "learning_rate": 1.9187652037306496e-06, "loss": 0.234280526638031, "step": 4869 }, { "epoch": 1.2642782969885773, "grad_norm": 9.232169151306152, "learning_rate": 1.917886192631163e-06, "loss": 0.08443933725357056, "step": 4870 }, { "epoch": 1.2645379023883696, "grad_norm": 7.4632062911987305, "learning_rate": 1.9170073286303458e-06, "loss": 0.15728941559791565, "step": 4871 }, { "epoch": 1.264797507788162, "grad_norm": 8.715934753417969, "learning_rate": 1.9161286118835594e-06, "loss": 0.058278828859329224, "step": 4872 }, { "epoch": 1.2650571131879542, "grad_norm": 8.491783142089844, "learning_rate": 1.9152500425461414e-06, "loss": 0.11971044540405273, "step": 4873 }, { "epoch": 1.2653167185877465, "grad_norm": 10.89883804321289, "learning_rate": 1.914371620773402e-06, "loss": 0.038922373205423355, "step": 4874 }, { "epoch": 1.2655763239875388, "grad_norm": 9.875633239746094, "learning_rate": 1.9134933467206274e-06, "loss": 0.17668545246124268, "step": 4875 }, { "epoch": 1.2658359293873311, "grad_norm": 8.587249755859375, "learning_rate": 1.9126152205430754e-06, "loss": 0.16430914402008057, "step": 4876 }, { "epoch": 1.2660955347871234, "grad_norm": 6.652830123901367, "learning_rate": 1.9117372423959786e-06, "loss": 0.24665813148021698, "step": 4877 }, { "epoch": 1.2663551401869158, "grad_norm": 6.237870216369629, "learning_rate": 1.9108594124345444e-06, "loss": 0.20336878299713135, "step": 4878 }, { "epoch": 1.2666147455867083, "grad_norm": 10.730555534362793, "learning_rate": 1.9099817308139516e-06, "loss": 0.0688297376036644, "step": 4879 }, { "epoch": 1.2668743509865006, "grad_norm": 6.053313732147217, "learning_rate": 1.9091041976893547e-06, "loss": 0.2484394758939743, "step": 4880 }, { "epoch": 1.267133956386293, "grad_norm": 10.748517990112305, "learning_rate": 1.908226813215882e-06, "loss": 0.06200583279132843, "step": 4881 }, { "epoch": 1.2673935617860852, "grad_norm": 10.088027000427246, "learning_rate": 1.9073495775486356e-06, "loss": 0.13535699248313904, "step": 4882 }, { "epoch": 1.2676531671858775, "grad_norm": 15.86654281616211, "learning_rate": 1.9064724908426885e-06, "loss": 0.14360004663467407, "step": 4883 }, { "epoch": 1.2679127725856698, "grad_norm": 8.837545394897461, "learning_rate": 1.9055955532530912e-06, "loss": 0.17248260974884033, "step": 4884 }, { "epoch": 1.2681723779854621, "grad_norm": 11.938494682312012, "learning_rate": 1.9047187649348652e-06, "loss": 0.08237352222204208, "step": 4885 }, { "epoch": 1.2684319833852544, "grad_norm": 7.799045562744141, "learning_rate": 1.903842126043009e-06, "loss": 0.0752091333270073, "step": 4886 }, { "epoch": 1.2686915887850467, "grad_norm": 4.18607759475708, "learning_rate": 1.902965636732489e-06, "loss": 0.017041662707924843, "step": 4887 }, { "epoch": 1.268951194184839, "grad_norm": 13.235628128051758, "learning_rate": 1.9020892971582495e-06, "loss": 0.058841168880462646, "step": 4888 }, { "epoch": 1.2692107995846313, "grad_norm": 8.145831108093262, "learning_rate": 1.9012131074752083e-06, "loss": 0.07611238211393356, "step": 4889 }, { "epoch": 1.2694704049844237, "grad_norm": 15.129925727844238, "learning_rate": 1.900337067838256e-06, "loss": 0.1109851524233818, "step": 4890 }, { "epoch": 1.269730010384216, "grad_norm": 9.306279182434082, "learning_rate": 1.8994611784022542e-06, "loss": 0.16501456499099731, "step": 4891 }, { "epoch": 1.2699896157840083, "grad_norm": 9.121024131774902, "learning_rate": 1.8985854393220414e-06, "loss": 0.06349055469036102, "step": 4892 }, { "epoch": 1.2702492211838006, "grad_norm": 10.64552116394043, "learning_rate": 1.8977098507524283e-06, "loss": 0.08079435676336288, "step": 4893 }, { "epoch": 1.2705088265835929, "grad_norm": 10.907910346984863, "learning_rate": 1.8968344128481992e-06, "loss": 0.10263630002737045, "step": 4894 }, { "epoch": 1.2707684319833852, "grad_norm": 10.5340576171875, "learning_rate": 1.8959591257641107e-06, "loss": 0.0935308039188385, "step": 4895 }, { "epoch": 1.2710280373831775, "grad_norm": 7.723674774169922, "learning_rate": 1.8950839896548934e-06, "loss": 0.11675003170967102, "step": 4896 }, { "epoch": 1.27128764278297, "grad_norm": 6.298248291015625, "learning_rate": 1.894209004675252e-06, "loss": 0.1974416971206665, "step": 4897 }, { "epoch": 1.2715472481827623, "grad_norm": 10.320801734924316, "learning_rate": 1.8933341709798642e-06, "loss": 0.12253622710704803, "step": 4898 }, { "epoch": 1.2718068535825546, "grad_norm": 6.170866966247559, "learning_rate": 1.8924594887233787e-06, "loss": 0.2214786410331726, "step": 4899 }, { "epoch": 1.272066458982347, "grad_norm": 6.506800174713135, "learning_rate": 1.8915849580604213e-06, "loss": 0.20645155012607574, "step": 4900 }, { "epoch": 1.2723260643821392, "grad_norm": 7.20465087890625, "learning_rate": 1.8907105791455877e-06, "loss": 0.17612764239311218, "step": 4901 }, { "epoch": 1.2725856697819315, "grad_norm": 8.895004272460938, "learning_rate": 1.8898363521334494e-06, "loss": 0.04658778756856918, "step": 4902 }, { "epoch": 1.2728452751817239, "grad_norm": 6.971678256988525, "learning_rate": 1.888962277178548e-06, "loss": 0.04299928992986679, "step": 4903 }, { "epoch": 1.2731048805815162, "grad_norm": 7.040070533752441, "learning_rate": 1.8880883544354017e-06, "loss": 0.09636914730072021, "step": 4904 }, { "epoch": 1.2733644859813085, "grad_norm": 9.377777099609375, "learning_rate": 1.8872145840584987e-06, "loss": 0.12061747908592224, "step": 4905 }, { "epoch": 1.2736240913811008, "grad_norm": 6.206460952758789, "learning_rate": 1.8863409662023024e-06, "loss": 0.22288942337036133, "step": 4906 }, { "epoch": 1.273883696780893, "grad_norm": 6.11750602722168, "learning_rate": 1.8854675010212476e-06, "loss": 0.22485828399658203, "step": 4907 }, { "epoch": 1.2741433021806854, "grad_norm": 8.279833793640137, "learning_rate": 1.8845941886697432e-06, "loss": 0.09461681544780731, "step": 4908 }, { "epoch": 1.2744029075804777, "grad_norm": 8.3915376663208, "learning_rate": 1.8837210293021724e-06, "loss": 0.12516406178474426, "step": 4909 }, { "epoch": 1.27466251298027, "grad_norm": 7.793252944946289, "learning_rate": 1.8828480230728874e-06, "loss": 0.17711491882801056, "step": 4910 }, { "epoch": 1.2749221183800623, "grad_norm": 8.504938125610352, "learning_rate": 1.8819751701362165e-06, "loss": 0.09320715814828873, "step": 4911 }, { "epoch": 1.2751817237798546, "grad_norm": 7.832852363586426, "learning_rate": 1.8811024706464614e-06, "loss": 0.025413013994693756, "step": 4912 }, { "epoch": 1.275441329179647, "grad_norm": 9.409015655517578, "learning_rate": 1.8802299247578943e-06, "loss": 0.21846193075180054, "step": 4913 }, { "epoch": 1.2757009345794392, "grad_norm": 12.801155090332031, "learning_rate": 1.8793575326247603e-06, "loss": 0.06892281770706177, "step": 4914 }, { "epoch": 1.2759605399792315, "grad_norm": 8.865466117858887, "learning_rate": 1.8784852944012799e-06, "loss": 0.12934273481369019, "step": 4915 }, { "epoch": 1.2762201453790238, "grad_norm": 6.333340167999268, "learning_rate": 1.8776132102416444e-06, "loss": 0.15802989900112152, "step": 4916 }, { "epoch": 1.2764797507788161, "grad_norm": 6.8290605545043945, "learning_rate": 1.8767412803000195e-06, "loss": 0.06289881467819214, "step": 4917 }, { "epoch": 1.2767393561786085, "grad_norm": 6.58758020401001, "learning_rate": 1.875869504730541e-06, "loss": 0.16255192458629608, "step": 4918 }, { "epoch": 1.2769989615784008, "grad_norm": 10.073548316955566, "learning_rate": 1.8749978836873174e-06, "loss": 0.09938692301511765, "step": 4919 }, { "epoch": 1.277258566978193, "grad_norm": 9.979721069335938, "learning_rate": 1.874126417324434e-06, "loss": 0.02508203685283661, "step": 4920 }, { "epoch": 1.2775181723779854, "grad_norm": 5.970702648162842, "learning_rate": 1.8732551057959459e-06, "loss": 0.1840219497680664, "step": 4921 }, { "epoch": 1.2777777777777777, "grad_norm": 8.558868408203125, "learning_rate": 1.8723839492558793e-06, "loss": 0.09769411385059357, "step": 4922 }, { "epoch": 1.27803738317757, "grad_norm": 8.548541069030762, "learning_rate": 1.8715129478582367e-06, "loss": 0.05400571972131729, "step": 4923 }, { "epoch": 1.2782969885773623, "grad_norm": 12.195009231567383, "learning_rate": 1.8706421017569888e-06, "loss": 0.10130687057971954, "step": 4924 }, { "epoch": 1.2785565939771546, "grad_norm": 7.930793762207031, "learning_rate": 1.8697714111060843e-06, "loss": 0.15098389983177185, "step": 4925 }, { "epoch": 1.278816199376947, "grad_norm": 8.375415802001953, "learning_rate": 1.868900876059439e-06, "loss": 0.15161697566509247, "step": 4926 }, { "epoch": 1.2790758047767394, "grad_norm": 6.642594814300537, "learning_rate": 1.868030496770944e-06, "loss": 0.21372807025909424, "step": 4927 }, { "epoch": 1.2793354101765317, "grad_norm": 8.645406723022461, "learning_rate": 1.8671602733944633e-06, "loss": 0.13188417255878448, "step": 4928 }, { "epoch": 1.279595015576324, "grad_norm": 8.383057594299316, "learning_rate": 1.8662902060838318e-06, "loss": 0.06629115343093872, "step": 4929 }, { "epoch": 1.2798546209761164, "grad_norm": 9.73116397857666, "learning_rate": 1.8654202949928574e-06, "loss": 0.15957671403884888, "step": 4930 }, { "epoch": 1.2801142263759087, "grad_norm": 14.265002250671387, "learning_rate": 1.8645505402753205e-06, "loss": 0.0538049191236496, "step": 4931 }, { "epoch": 1.280373831775701, "grad_norm": 7.893801689147949, "learning_rate": 1.8636809420849745e-06, "loss": 0.2021750807762146, "step": 4932 }, { "epoch": 1.2806334371754933, "grad_norm": 8.14280891418457, "learning_rate": 1.8628115005755432e-06, "loss": 0.05939996615052223, "step": 4933 }, { "epoch": 1.2808930425752856, "grad_norm": 10.276741027832031, "learning_rate": 1.861942215900725e-06, "loss": 0.1331016570329666, "step": 4934 }, { "epoch": 1.2811526479750779, "grad_norm": 10.302353858947754, "learning_rate": 1.8610730882141893e-06, "loss": 0.08077593892812729, "step": 4935 }, { "epoch": 1.2814122533748702, "grad_norm": 7.7008867263793945, "learning_rate": 1.8602041176695779e-06, "loss": 0.202869713306427, "step": 4936 }, { "epoch": 1.2816718587746625, "grad_norm": 6.3540425300598145, "learning_rate": 1.8593353044205047e-06, "loss": 0.22186802327632904, "step": 4937 }, { "epoch": 1.2819314641744548, "grad_norm": 8.234813690185547, "learning_rate": 1.8584666486205567e-06, "loss": 0.18554812669754028, "step": 4938 }, { "epoch": 1.282191069574247, "grad_norm": 7.777535438537598, "learning_rate": 1.857598150423291e-06, "loss": 0.040693555027246475, "step": 4939 }, { "epoch": 1.2824506749740394, "grad_norm": 9.575757026672363, "learning_rate": 1.8567298099822395e-06, "loss": 0.050281405448913574, "step": 4940 }, { "epoch": 1.2827102803738317, "grad_norm": 6.4678144454956055, "learning_rate": 1.8558616274509046e-06, "loss": 0.1917494237422943, "step": 4941 }, { "epoch": 1.282969885773624, "grad_norm": 10.553394317626953, "learning_rate": 1.8549936029827603e-06, "loss": 0.12635430693626404, "step": 4942 }, { "epoch": 1.2832294911734163, "grad_norm": 7.883228302001953, "learning_rate": 1.8541257367312543e-06, "loss": 0.1997963786125183, "step": 4943 }, { "epoch": 1.2834890965732086, "grad_norm": 6.210686683654785, "learning_rate": 1.8532580288498065e-06, "loss": 0.17517593502998352, "step": 4944 }, { "epoch": 1.2837487019730012, "grad_norm": 8.756648063659668, "learning_rate": 1.8523904794918046e-06, "loss": 0.1639711558818817, "step": 4945 }, { "epoch": 1.2840083073727935, "grad_norm": 10.906439781188965, "learning_rate": 1.851523088810614e-06, "loss": 0.06340594589710236, "step": 4946 }, { "epoch": 1.2842679127725858, "grad_norm": 15.026391983032227, "learning_rate": 1.850655856959569e-06, "loss": 0.08729594945907593, "step": 4947 }, { "epoch": 1.284527518172378, "grad_norm": 7.071258544921875, "learning_rate": 1.849788784091977e-06, "loss": 0.016533279791474342, "step": 4948 }, { "epoch": 1.2847871235721704, "grad_norm": 8.803971290588379, "learning_rate": 1.848921870361115e-06, "loss": 0.12810173630714417, "step": 4949 }, { "epoch": 1.2850467289719627, "grad_norm": 10.945512771606445, "learning_rate": 1.8480551159202342e-06, "loss": 0.15781326591968536, "step": 4950 }, { "epoch": 1.285306334371755, "grad_norm": 12.922852516174316, "learning_rate": 1.847188520922557e-06, "loss": 0.1133713498711586, "step": 4951 }, { "epoch": 1.2855659397715473, "grad_norm": 8.080702781677246, "learning_rate": 1.8463220855212789e-06, "loss": 0.17725451290607452, "step": 4952 }, { "epoch": 1.2858255451713396, "grad_norm": 11.123588562011719, "learning_rate": 1.845455809869564e-06, "loss": 0.04771007224917412, "step": 4953 }, { "epoch": 1.286085150571132, "grad_norm": 7.827388286590576, "learning_rate": 1.8445896941205503e-06, "loss": 0.10793116688728333, "step": 4954 }, { "epoch": 1.2863447559709242, "grad_norm": 6.935616493225098, "learning_rate": 1.8437237384273471e-06, "loss": 0.04540744051337242, "step": 4955 }, { "epoch": 1.2866043613707165, "grad_norm": 9.094844818115234, "learning_rate": 1.842857942943037e-06, "loss": 0.09866990894079208, "step": 4956 }, { "epoch": 1.2868639667705088, "grad_norm": 9.073453903198242, "learning_rate": 1.8419923078206714e-06, "loss": 0.08016107231378555, "step": 4957 }, { "epoch": 1.2871235721703012, "grad_norm": 9.600443840026855, "learning_rate": 1.8411268332132747e-06, "loss": 0.13114124536514282, "step": 4958 }, { "epoch": 1.2873831775700935, "grad_norm": 7.490073204040527, "learning_rate": 1.8402615192738443e-06, "loss": 0.17866624891757965, "step": 4959 }, { "epoch": 1.2876427829698858, "grad_norm": 4.074695110321045, "learning_rate": 1.8393963661553466e-06, "loss": 0.01575157232582569, "step": 4960 }, { "epoch": 1.287902388369678, "grad_norm": 7.453059196472168, "learning_rate": 1.8385313740107208e-06, "loss": 0.04155116528272629, "step": 4961 }, { "epoch": 1.2881619937694704, "grad_norm": 6.383240222930908, "learning_rate": 1.8376665429928786e-06, "loss": 0.23614154756069183, "step": 4962 }, { "epoch": 1.2884215991692627, "grad_norm": 11.691414833068848, "learning_rate": 1.8368018732547026e-06, "loss": 0.08223221451044083, "step": 4963 }, { "epoch": 1.288681204569055, "grad_norm": 10.74040412902832, "learning_rate": 1.8359373649490452e-06, "loss": 0.07460363954305649, "step": 4964 }, { "epoch": 1.2889408099688473, "grad_norm": 8.27645492553711, "learning_rate": 1.8350730182287323e-06, "loss": 0.10538333654403687, "step": 4965 }, { "epoch": 1.2892004153686396, "grad_norm": 9.011994361877441, "learning_rate": 1.8342088332465612e-06, "loss": 0.0833708643913269, "step": 4966 }, { "epoch": 1.289460020768432, "grad_norm": 10.538110733032227, "learning_rate": 1.8333448101552993e-06, "loss": 0.07357899099588394, "step": 4967 }, { "epoch": 1.2897196261682242, "grad_norm": 5.829265117645264, "learning_rate": 1.8324809491076861e-06, "loss": 0.022876689210534096, "step": 4968 }, { "epoch": 1.2899792315680165, "grad_norm": 8.152443885803223, "learning_rate": 1.8316172502564334e-06, "loss": 0.0974995344877243, "step": 4969 }, { "epoch": 1.2902388369678088, "grad_norm": 5.935791015625, "learning_rate": 1.8307537137542219e-06, "loss": 0.19415590167045593, "step": 4970 }, { "epoch": 1.2904984423676011, "grad_norm": 5.817726135253906, "learning_rate": 1.829890339753706e-06, "loss": 0.01774265617132187, "step": 4971 }, { "epoch": 1.2907580477673934, "grad_norm": 12.267358779907227, "learning_rate": 1.8290271284075106e-06, "loss": 0.10796809196472168, "step": 4972 }, { "epoch": 1.2910176531671858, "grad_norm": 10.601936340332031, "learning_rate": 1.8281640798682316e-06, "loss": 0.07409336417913437, "step": 4973 }, { "epoch": 1.291277258566978, "grad_norm": 8.573994636535645, "learning_rate": 1.8273011942884356e-06, "loss": 0.14339563250541687, "step": 4974 }, { "epoch": 1.2915368639667706, "grad_norm": 7.291093349456787, "learning_rate": 1.8264384718206624e-06, "loss": 0.12118496000766754, "step": 4975 }, { "epoch": 1.291796469366563, "grad_norm": 7.6831183433532715, "learning_rate": 1.8255759126174188e-06, "loss": 0.08033593744039536, "step": 4976 }, { "epoch": 1.2920560747663552, "grad_norm": 8.505566596984863, "learning_rate": 1.8247135168311885e-06, "loss": 0.02735896036028862, "step": 4977 }, { "epoch": 1.2923156801661475, "grad_norm": 10.732410430908203, "learning_rate": 1.823851284614422e-06, "loss": 0.08322754502296448, "step": 4978 }, { "epoch": 1.2925752855659398, "grad_norm": 7.0586371421813965, "learning_rate": 1.8229892161195435e-06, "loss": 0.08981986343860626, "step": 4979 }, { "epoch": 1.2928348909657321, "grad_norm": 6.724460124969482, "learning_rate": 1.8221273114989447e-06, "loss": 0.22608058154582977, "step": 4980 }, { "epoch": 1.2930944963655244, "grad_norm": 6.448352336883545, "learning_rate": 1.8212655709049908e-06, "loss": 0.09059343487024307, "step": 4981 }, { "epoch": 1.2933541017653167, "grad_norm": 8.082812309265137, "learning_rate": 1.8204039944900198e-06, "loss": 0.14690834283828735, "step": 4982 }, { "epoch": 1.293613707165109, "grad_norm": 8.95553207397461, "learning_rate": 1.8195425824063384e-06, "loss": 0.1559666097164154, "step": 4983 }, { "epoch": 1.2938733125649013, "grad_norm": 8.394497871398926, "learning_rate": 1.8186813348062232e-06, "loss": 0.15104016661643982, "step": 4984 }, { "epoch": 1.2941329179646937, "grad_norm": 8.272860527038574, "learning_rate": 1.817820251841923e-06, "loss": 0.04247811809182167, "step": 4985 }, { "epoch": 1.294392523364486, "grad_norm": 6.992300510406494, "learning_rate": 1.8169593336656594e-06, "loss": 0.2290961742401123, "step": 4986 }, { "epoch": 1.2946521287642783, "grad_norm": 11.517629623413086, "learning_rate": 1.816098580429621e-06, "loss": 0.1344020515680313, "step": 4987 }, { "epoch": 1.2949117341640706, "grad_norm": 7.084145545959473, "learning_rate": 1.8152379922859697e-06, "loss": 0.0684615895152092, "step": 4988 }, { "epoch": 1.2951713395638629, "grad_norm": 2.932983875274658, "learning_rate": 1.8143775693868387e-06, "loss": 0.004955197684466839, "step": 4989 }, { "epoch": 1.2954309449636552, "grad_norm": 9.441676139831543, "learning_rate": 1.8135173118843313e-06, "loss": 0.09115180373191833, "step": 4990 }, { "epoch": 1.2956905503634475, "grad_norm": 8.075624465942383, "learning_rate": 1.8126572199305192e-06, "loss": 0.10702337324619293, "step": 4991 }, { "epoch": 1.2959501557632398, "grad_norm": 9.913264274597168, "learning_rate": 1.811797293677448e-06, "loss": 0.14453363418579102, "step": 4992 }, { "epoch": 1.2962097611630323, "grad_norm": 6.8566765785217285, "learning_rate": 1.8109375332771346e-06, "loss": 0.028561461716890335, "step": 4993 }, { "epoch": 1.2964693665628246, "grad_norm": 10.11131477355957, "learning_rate": 1.8100779388815631e-06, "loss": 0.14616113901138306, "step": 4994 }, { "epoch": 1.296728971962617, "grad_norm": 10.51610279083252, "learning_rate": 1.8092185106426913e-06, "loss": 0.18169352412223816, "step": 4995 }, { "epoch": 1.2969885773624092, "grad_norm": 7.95993709564209, "learning_rate": 1.808359248712444e-06, "loss": 0.14207154512405396, "step": 4996 }, { "epoch": 1.2972481827622016, "grad_norm": 9.625641822814941, "learning_rate": 1.8075001532427216e-06, "loss": 0.17391341924667358, "step": 4997 }, { "epoch": 1.2975077881619939, "grad_norm": 8.641576766967773, "learning_rate": 1.806641224385393e-06, "loss": 0.19215042889118195, "step": 4998 }, { "epoch": 1.2977673935617862, "grad_norm": 14.03900146484375, "learning_rate": 1.8057824622922948e-06, "loss": 0.04986556991934776, "step": 4999 }, { "epoch": 1.2980269989615785, "grad_norm": 14.079048156738281, "learning_rate": 1.8049238671152381e-06, "loss": 0.07384788990020752, "step": 5000 }, { "epoch": 1.2982866043613708, "grad_norm": 5.763216018676758, "learning_rate": 1.804065439006001e-06, "loss": 0.051405202597379684, "step": 5001 }, { "epoch": 1.298546209761163, "grad_norm": 11.278416633605957, "learning_rate": 1.8032071781163363e-06, "loss": 0.07413344085216522, "step": 5002 }, { "epoch": 1.2988058151609554, "grad_norm": 6.931161880493164, "learning_rate": 1.802349084597964e-06, "loss": 0.04502430930733681, "step": 5003 }, { "epoch": 1.2990654205607477, "grad_norm": 7.084031581878662, "learning_rate": 1.8014911586025747e-06, "loss": 0.13965682685375214, "step": 5004 }, { "epoch": 1.29932502596054, "grad_norm": 11.011415481567383, "learning_rate": 1.800633400281831e-06, "loss": 0.12098953872919083, "step": 5005 }, { "epoch": 1.2995846313603323, "grad_norm": 7.62074089050293, "learning_rate": 1.7997758097873647e-06, "loss": 0.040040522813797, "step": 5006 }, { "epoch": 1.2998442367601246, "grad_norm": 13.447028160095215, "learning_rate": 1.7989183872707767e-06, "loss": 0.07564105838537216, "step": 5007 }, { "epoch": 1.300103842159917, "grad_norm": 8.851777076721191, "learning_rate": 1.7980611328836422e-06, "loss": 0.06040051579475403, "step": 5008 }, { "epoch": 1.3003634475597092, "grad_norm": 10.24958324432373, "learning_rate": 1.7972040467775021e-06, "loss": 0.09534578770399094, "step": 5009 }, { "epoch": 1.3006230529595015, "grad_norm": 11.460532188415527, "learning_rate": 1.7963471291038708e-06, "loss": 0.12624883651733398, "step": 5010 }, { "epoch": 1.3008826583592938, "grad_norm": 9.463903427124023, "learning_rate": 1.7954903800142321e-06, "loss": 0.06559178233146667, "step": 5011 }, { "epoch": 1.3011422637590861, "grad_norm": 12.293988227844238, "learning_rate": 1.7946337996600371e-06, "loss": 0.08620107918977737, "step": 5012 }, { "epoch": 1.3014018691588785, "grad_norm": 12.296661376953125, "learning_rate": 1.793777388192713e-06, "loss": 0.11435138434171677, "step": 5013 }, { "epoch": 1.3016614745586708, "grad_norm": 9.725610733032227, "learning_rate": 1.7929211457636514e-06, "loss": 0.14060908555984497, "step": 5014 }, { "epoch": 1.301921079958463, "grad_norm": 6.491941928863525, "learning_rate": 1.7920650725242167e-06, "loss": 0.20938870310783386, "step": 5015 }, { "epoch": 1.3021806853582554, "grad_norm": 7.690974235534668, "learning_rate": 1.7912091686257438e-06, "loss": 0.2007063776254654, "step": 5016 }, { "epoch": 1.3024402907580477, "grad_norm": 7.723694324493408, "learning_rate": 1.7903534342195366e-06, "loss": 0.08565766364336014, "step": 5017 }, { "epoch": 1.30269989615784, "grad_norm": 11.774528503417969, "learning_rate": 1.7894978694568688e-06, "loss": 0.04111583158373833, "step": 5018 }, { "epoch": 1.3029595015576323, "grad_norm": 7.789734363555908, "learning_rate": 1.7886424744889852e-06, "loss": 0.04848656430840492, "step": 5019 }, { "epoch": 1.3032191069574246, "grad_norm": 7.852505207061768, "learning_rate": 1.7877872494670996e-06, "loss": 0.059248752892017365, "step": 5020 }, { "epoch": 1.303478712357217, "grad_norm": 9.709324836730957, "learning_rate": 1.7869321945423985e-06, "loss": 0.03029918484389782, "step": 5021 }, { "epoch": 1.3037383177570092, "grad_norm": 12.158089637756348, "learning_rate": 1.7860773098660316e-06, "loss": 0.0655878335237503, "step": 5022 }, { "epoch": 1.3039979231568017, "grad_norm": 8.42043685913086, "learning_rate": 1.7852225955891256e-06, "loss": 0.12546806037425995, "step": 5023 }, { "epoch": 1.304257528556594, "grad_norm": 9.801237106323242, "learning_rate": 1.7843680518627753e-06, "loss": 0.04323320835828781, "step": 5024 }, { "epoch": 1.3045171339563864, "grad_norm": 8.737695693969727, "learning_rate": 1.7835136788380436e-06, "loss": 0.18473735451698303, "step": 5025 }, { "epoch": 1.3047767393561787, "grad_norm": 13.514850616455078, "learning_rate": 1.7826594766659638e-06, "loss": 0.11707282066345215, "step": 5026 }, { "epoch": 1.305036344755971, "grad_norm": 12.082964897155762, "learning_rate": 1.7818054454975387e-06, "loss": 0.05260620266199112, "step": 5027 }, { "epoch": 1.3052959501557633, "grad_norm": 9.94282054901123, "learning_rate": 1.7809515854837418e-06, "loss": 0.07011671364307404, "step": 5028 }, { "epoch": 1.3055555555555556, "grad_norm": 8.15792465209961, "learning_rate": 1.7800978967755179e-06, "loss": 0.08238360285758972, "step": 5029 }, { "epoch": 1.3058151609553479, "grad_norm": 6.698310852050781, "learning_rate": 1.7792443795237764e-06, "loss": 0.18862192332744598, "step": 5030 }, { "epoch": 1.3060747663551402, "grad_norm": 11.000999450683594, "learning_rate": 1.7783910338794019e-06, "loss": 0.17862087488174438, "step": 5031 }, { "epoch": 1.3063343717549325, "grad_norm": 9.270679473876953, "learning_rate": 1.7775378599932452e-06, "loss": 0.09873242676258087, "step": 5032 }, { "epoch": 1.3065939771547248, "grad_norm": 10.051019668579102, "learning_rate": 1.776684858016129e-06, "loss": 0.03778012841939926, "step": 5033 }, { "epoch": 1.3068535825545171, "grad_norm": 8.815133094787598, "learning_rate": 1.7758320280988444e-06, "loss": 0.11318247020244598, "step": 5034 }, { "epoch": 1.3071131879543094, "grad_norm": 6.241446495056152, "learning_rate": 1.774979370392151e-06, "loss": 0.01979094371199608, "step": 5035 }, { "epoch": 1.3073727933541017, "grad_norm": 7.3754143714904785, "learning_rate": 1.7741268850467796e-06, "loss": 0.23049476742744446, "step": 5036 }, { "epoch": 1.307632398753894, "grad_norm": 6.776282787322998, "learning_rate": 1.7732745722134315e-06, "loss": 0.03805714100599289, "step": 5037 }, { "epoch": 1.3078920041536863, "grad_norm": 7.739318370819092, "learning_rate": 1.7724224320427741e-06, "loss": 0.1800370216369629, "step": 5038 }, { "epoch": 1.3081516095534786, "grad_norm": 8.829008102416992, "learning_rate": 1.7715704646854476e-06, "loss": 0.09550593793392181, "step": 5039 }, { "epoch": 1.308411214953271, "grad_norm": 17.023916244506836, "learning_rate": 1.7707186702920587e-06, "loss": 0.04383058845996857, "step": 5040 }, { "epoch": 1.3086708203530635, "grad_norm": 9.891764640808105, "learning_rate": 1.7698670490131875e-06, "loss": 0.0742998868227005, "step": 5041 }, { "epoch": 1.3089304257528558, "grad_norm": 10.148579597473145, "learning_rate": 1.7690156009993803e-06, "loss": 0.03301534056663513, "step": 5042 }, { "epoch": 1.309190031152648, "grad_norm": 12.694999694824219, "learning_rate": 1.7681643264011523e-06, "loss": 0.0587938018143177, "step": 5043 }, { "epoch": 1.3094496365524404, "grad_norm": 10.23303508758545, "learning_rate": 1.7673132253689913e-06, "loss": 0.046751610934734344, "step": 5044 }, { "epoch": 1.3097092419522327, "grad_norm": 9.87772274017334, "learning_rate": 1.7664622980533508e-06, "loss": 0.14398202300071716, "step": 5045 }, { "epoch": 1.309968847352025, "grad_norm": 8.503164291381836, "learning_rate": 1.7656115446046558e-06, "loss": 0.042014770209789276, "step": 5046 }, { "epoch": 1.3102284527518173, "grad_norm": 9.91667652130127, "learning_rate": 1.764760965173301e-06, "loss": 0.1042451485991478, "step": 5047 }, { "epoch": 1.3104880581516096, "grad_norm": 10.577165603637695, "learning_rate": 1.7639105599096484e-06, "loss": 0.09986422955989838, "step": 5048 }, { "epoch": 1.310747663551402, "grad_norm": 15.277294158935547, "learning_rate": 1.7630603289640298e-06, "loss": 0.05097540467977524, "step": 5049 }, { "epoch": 1.3110072689511942, "grad_norm": 11.808074951171875, "learning_rate": 1.7622102724867473e-06, "loss": 0.04061664640903473, "step": 5050 }, { "epoch": 1.3112668743509865, "grad_norm": 9.786896705627441, "learning_rate": 1.7613603906280708e-06, "loss": 0.08402934670448303, "step": 5051 }, { "epoch": 1.3115264797507789, "grad_norm": 12.063836097717285, "learning_rate": 1.7605106835382424e-06, "loss": 0.07795663177967072, "step": 5052 }, { "epoch": 1.3117860851505712, "grad_norm": 11.951482772827148, "learning_rate": 1.7596611513674667e-06, "loss": 0.03694445267319679, "step": 5053 }, { "epoch": 1.3120456905503635, "grad_norm": 9.572701454162598, "learning_rate": 1.7588117942659239e-06, "loss": 0.15965966880321503, "step": 5054 }, { "epoch": 1.3123052959501558, "grad_norm": 9.155969619750977, "learning_rate": 1.7579626123837612e-06, "loss": 0.1667167693376541, "step": 5055 }, { "epoch": 1.312564901349948, "grad_norm": 6.610975742340088, "learning_rate": 1.7571136058710942e-06, "loss": 0.2010769248008728, "step": 5056 }, { "epoch": 1.3128245067497404, "grad_norm": 5.168154239654541, "learning_rate": 1.7562647748780076e-06, "loss": 0.26270222663879395, "step": 5057 }, { "epoch": 1.3130841121495327, "grad_norm": 9.028136253356934, "learning_rate": 1.7554161195545545e-06, "loss": 0.10737016797065735, "step": 5058 }, { "epoch": 1.313343717549325, "grad_norm": 7.509494781494141, "learning_rate": 1.754567640050759e-06, "loss": 0.02868192084133625, "step": 5059 }, { "epoch": 1.3136033229491173, "grad_norm": 5.663483142852783, "learning_rate": 1.7537193365166133e-06, "loss": 0.23521605134010315, "step": 5060 }, { "epoch": 1.3138629283489096, "grad_norm": 7.041374683380127, "learning_rate": 1.7528712091020756e-06, "loss": 0.03254295885562897, "step": 5061 }, { "epoch": 1.314122533748702, "grad_norm": 7.866463661193848, "learning_rate": 1.7520232579570768e-06, "loss": 0.1053183525800705, "step": 5062 }, { "epoch": 1.3143821391484942, "grad_norm": 7.643865585327148, "learning_rate": 1.7511754832315165e-06, "loss": 0.13752663135528564, "step": 5063 }, { "epoch": 1.3146417445482865, "grad_norm": 8.137459754943848, "learning_rate": 1.7503278850752604e-06, "loss": 0.05750657618045807, "step": 5064 }, { "epoch": 1.3149013499480788, "grad_norm": 5.446472644805908, "learning_rate": 1.7494804636381446e-06, "loss": 0.20443280041217804, "step": 5065 }, { "epoch": 1.3151609553478711, "grad_norm": 8.836065292358398, "learning_rate": 1.748633219069974e-06, "loss": 0.06259655952453613, "step": 5066 }, { "epoch": 1.3154205607476634, "grad_norm": 8.354536056518555, "learning_rate": 1.7477861515205213e-06, "loss": 0.1594141125679016, "step": 5067 }, { "epoch": 1.3156801661474558, "grad_norm": 8.491137504577637, "learning_rate": 1.7469392611395309e-06, "loss": 0.05310414731502533, "step": 5068 }, { "epoch": 1.315939771547248, "grad_norm": 7.167979717254639, "learning_rate": 1.7460925480767107e-06, "loss": 0.04378432780504227, "step": 5069 }, { "epoch": 1.3161993769470404, "grad_norm": 9.09409236907959, "learning_rate": 1.7452460124817424e-06, "loss": 0.11066807061433792, "step": 5070 }, { "epoch": 1.316458982346833, "grad_norm": 10.02896785736084, "learning_rate": 1.7443996545042734e-06, "loss": 0.17682957649230957, "step": 5071 }, { "epoch": 1.3167185877466252, "grad_norm": 5.42388391494751, "learning_rate": 1.7435534742939193e-06, "loss": 0.05258038640022278, "step": 5072 }, { "epoch": 1.3169781931464175, "grad_norm": 7.267324924468994, "learning_rate": 1.7427074720002673e-06, "loss": 0.15397688746452332, "step": 5073 }, { "epoch": 1.3172377985462098, "grad_norm": 10.580714225769043, "learning_rate": 1.7418616477728694e-06, "loss": 0.11978138238191605, "step": 5074 }, { "epoch": 1.3174974039460021, "grad_norm": 10.22170352935791, "learning_rate": 1.74101600176125e-06, "loss": 0.11468330025672913, "step": 5075 }, { "epoch": 1.3177570093457944, "grad_norm": 8.541668891906738, "learning_rate": 1.740170534114898e-06, "loss": 0.055235356092453, "step": 5076 }, { "epoch": 1.3180166147455867, "grad_norm": 9.02411937713623, "learning_rate": 1.7393252449832734e-06, "loss": 0.049169160425662994, "step": 5077 }, { "epoch": 1.318276220145379, "grad_norm": 7.71360445022583, "learning_rate": 1.7384801345158048e-06, "loss": 0.10683267563581467, "step": 5078 }, { "epoch": 1.3185358255451713, "grad_norm": 7.735487937927246, "learning_rate": 1.7376352028618877e-06, "loss": 0.042763762176036835, "step": 5079 }, { "epoch": 1.3187954309449637, "grad_norm": 6.025306224822998, "learning_rate": 1.7367904501708856e-06, "loss": 0.19189319014549255, "step": 5080 }, { "epoch": 1.319055036344756, "grad_norm": 10.761621475219727, "learning_rate": 1.7359458765921334e-06, "loss": 0.05924215167760849, "step": 5081 }, { "epoch": 1.3193146417445483, "grad_norm": 7.477258682250977, "learning_rate": 1.7351014822749308e-06, "loss": 0.1187213882803917, "step": 5082 }, { "epoch": 1.3195742471443406, "grad_norm": 11.070180892944336, "learning_rate": 1.734257267368549e-06, "loss": 0.03151771426200867, "step": 5083 }, { "epoch": 1.3198338525441329, "grad_norm": 14.523330688476562, "learning_rate": 1.7334132320222244e-06, "loss": 0.08716709166765213, "step": 5084 }, { "epoch": 1.3200934579439252, "grad_norm": 9.40825080871582, "learning_rate": 1.732569376385163e-06, "loss": 0.10498577356338501, "step": 5085 }, { "epoch": 1.3203530633437175, "grad_norm": 8.768832206726074, "learning_rate": 1.7317257006065407e-06, "loss": 0.11904551833868027, "step": 5086 }, { "epoch": 1.3206126687435098, "grad_norm": 8.33776569366455, "learning_rate": 1.7308822048354996e-06, "loss": 0.08284201472997665, "step": 5087 }, { "epoch": 1.320872274143302, "grad_norm": 6.145062446594238, "learning_rate": 1.7300388892211483e-06, "loss": 0.26750698685646057, "step": 5088 }, { "epoch": 1.3211318795430946, "grad_norm": 7.220580577850342, "learning_rate": 1.7291957539125686e-06, "loss": 0.20376890897750854, "step": 5089 }, { "epoch": 1.321391484942887, "grad_norm": 8.881848335266113, "learning_rate": 1.7283527990588055e-06, "loss": 0.11922052502632141, "step": 5090 }, { "epoch": 1.3216510903426792, "grad_norm": 9.522796630859375, "learning_rate": 1.7275100248088766e-06, "loss": 0.03333437442779541, "step": 5091 }, { "epoch": 1.3219106957424716, "grad_norm": 8.21663761138916, "learning_rate": 1.7266674313117615e-06, "loss": 0.03540441766381264, "step": 5092 }, { "epoch": 1.3221703011422639, "grad_norm": 6.407963275909424, "learning_rate": 1.7258250187164139e-06, "loss": 0.0703364685177803, "step": 5093 }, { "epoch": 1.3224299065420562, "grad_norm": 8.966442108154297, "learning_rate": 1.7249827871717526e-06, "loss": 0.1024395152926445, "step": 5094 }, { "epoch": 1.3226895119418485, "grad_norm": 6.870159149169922, "learning_rate": 1.7241407368266649e-06, "loss": 0.041402898728847504, "step": 5095 }, { "epoch": 1.3229491173416408, "grad_norm": 5.880430698394775, "learning_rate": 1.7232988678300062e-06, "loss": 0.21481287479400635, "step": 5096 }, { "epoch": 1.323208722741433, "grad_norm": 8.298185348510742, "learning_rate": 1.7224571803305984e-06, "loss": 0.10555292665958405, "step": 5097 }, { "epoch": 1.3234683281412254, "grad_norm": 6.481558322906494, "learning_rate": 1.721615674477234e-06, "loss": 0.20228563249111176, "step": 5098 }, { "epoch": 1.3237279335410177, "grad_norm": 6.425837516784668, "learning_rate": 1.720774350418672e-06, "loss": 0.1610969603061676, "step": 5099 }, { "epoch": 1.32398753894081, "grad_norm": 8.389187812805176, "learning_rate": 1.7199332083036374e-06, "loss": 0.12709622085094452, "step": 5100 }, { "epoch": 1.3242471443406023, "grad_norm": 9.38548469543457, "learning_rate": 1.719092248280827e-06, "loss": 0.01415332593023777, "step": 5101 }, { "epoch": 1.3245067497403946, "grad_norm": 9.203843116760254, "learning_rate": 1.7182514704989029e-06, "loss": 0.1492745280265808, "step": 5102 }, { "epoch": 1.324766355140187, "grad_norm": 8.80053997039795, "learning_rate": 1.7174108751064939e-06, "loss": 0.035425227135419846, "step": 5103 }, { "epoch": 1.3250259605399792, "grad_norm": 7.503564834594727, "learning_rate": 1.7165704622521994e-06, "loss": 0.19007819890975952, "step": 5104 }, { "epoch": 1.3252855659397715, "grad_norm": 7.282296180725098, "learning_rate": 1.7157302320845848e-06, "loss": 0.1700199842453003, "step": 5105 }, { "epoch": 1.3255451713395638, "grad_norm": 8.877081871032715, "learning_rate": 1.7148901847521837e-06, "loss": 0.05325988307595253, "step": 5106 }, { "epoch": 1.3258047767393562, "grad_norm": 7.434116840362549, "learning_rate": 1.7140503204034973e-06, "loss": 0.20247763395309448, "step": 5107 }, { "epoch": 1.3260643821391485, "grad_norm": 9.173623085021973, "learning_rate": 1.713210639186993e-06, "loss": 0.15207353234291077, "step": 5108 }, { "epoch": 1.3263239875389408, "grad_norm": 7.937605381011963, "learning_rate": 1.7123711412511096e-06, "loss": 0.07604565471410751, "step": 5109 }, { "epoch": 1.326583592938733, "grad_norm": 8.068218231201172, "learning_rate": 1.7115318267442496e-06, "loss": 0.1517193615436554, "step": 5110 }, { "epoch": 1.3268431983385254, "grad_norm": 6.483710765838623, "learning_rate": 1.7106926958147841e-06, "loss": 0.0419585183262825, "step": 5111 }, { "epoch": 1.3271028037383177, "grad_norm": 6.49209451675415, "learning_rate": 1.7098537486110539e-06, "loss": 0.2105715423822403, "step": 5112 }, { "epoch": 1.32736240913811, "grad_norm": 10.396184921264648, "learning_rate": 1.709014985281364e-06, "loss": 0.05601097270846367, "step": 5113 }, { "epoch": 1.3276220145379023, "grad_norm": 8.030893325805664, "learning_rate": 1.70817640597399e-06, "loss": 0.19609509408473969, "step": 5114 }, { "epoch": 1.3278816199376946, "grad_norm": 9.622479438781738, "learning_rate": 1.7073380108371728e-06, "loss": 0.14350177347660065, "step": 5115 }, { "epoch": 1.328141225337487, "grad_norm": 13.601211547851562, "learning_rate": 1.7064998000191207e-06, "loss": 0.06898333132266998, "step": 5116 }, { "epoch": 1.3284008307372792, "grad_norm": 9.250457763671875, "learning_rate": 1.705661773668012e-06, "loss": 0.11451362818479538, "step": 5117 }, { "epoch": 1.3286604361370715, "grad_norm": 10.787129402160645, "learning_rate": 1.7048239319319894e-06, "loss": 0.05617126077413559, "step": 5118 }, { "epoch": 1.328920041536864, "grad_norm": 7.713017463684082, "learning_rate": 1.7039862749591635e-06, "loss": 0.0430007241666317, "step": 5119 }, { "epoch": 1.3291796469366564, "grad_norm": 11.17284107208252, "learning_rate": 1.703148802897614e-06, "loss": 0.19740742444992065, "step": 5120 }, { "epoch": 1.3294392523364487, "grad_norm": 12.153351783752441, "learning_rate": 1.7023115158953862e-06, "loss": 0.13009324669837952, "step": 5121 }, { "epoch": 1.329698857736241, "grad_norm": 11.892632484436035, "learning_rate": 1.7014744141004948e-06, "loss": 0.03735268488526344, "step": 5122 }, { "epoch": 1.3299584631360333, "grad_norm": 10.821698188781738, "learning_rate": 1.7006374976609174e-06, "loss": 0.06088895723223686, "step": 5123 }, { "epoch": 1.3302180685358256, "grad_norm": 7.27818489074707, "learning_rate": 1.6998007667246037e-06, "loss": 0.21501800417900085, "step": 5124 }, { "epoch": 1.3304776739356179, "grad_norm": 8.484064102172852, "learning_rate": 1.698964221439469e-06, "loss": 0.15863071382045746, "step": 5125 }, { "epoch": 1.3307372793354102, "grad_norm": 10.785920143127441, "learning_rate": 1.698127861953393e-06, "loss": 0.13781321048736572, "step": 5126 }, { "epoch": 1.3309968847352025, "grad_norm": 11.759261131286621, "learning_rate": 1.697291688414227e-06, "loss": 0.11665994673967361, "step": 5127 }, { "epoch": 1.3312564901349948, "grad_norm": 9.926136016845703, "learning_rate": 1.6964557009697858e-06, "loss": 0.03918846696615219, "step": 5128 }, { "epoch": 1.3315160955347871, "grad_norm": 8.661161422729492, "learning_rate": 1.6956198997678546e-06, "loss": 0.10110421478748322, "step": 5129 }, { "epoch": 1.3317757009345794, "grad_norm": 10.22033405303955, "learning_rate": 1.6947842849561835e-06, "loss": 0.059873104095458984, "step": 5130 }, { "epoch": 1.3320353063343717, "grad_norm": 12.475257873535156, "learning_rate": 1.6939488566824885e-06, "loss": 0.12407398223876953, "step": 5131 }, { "epoch": 1.332294911734164, "grad_norm": 8.068260192871094, "learning_rate": 1.6931136150944561e-06, "loss": 0.014555069617927074, "step": 5132 }, { "epoch": 1.3325545171339563, "grad_norm": 15.021374702453613, "learning_rate": 1.692278560339737e-06, "loss": 0.05351170152425766, "step": 5133 }, { "epoch": 1.3328141225337486, "grad_norm": 11.429421424865723, "learning_rate": 1.6914436925659488e-06, "loss": 0.03892616927623749, "step": 5134 }, { "epoch": 1.333073727933541, "grad_norm": 7.838219165802002, "learning_rate": 1.6906090119206792e-06, "loss": 0.18256288766860962, "step": 5135 }, { "epoch": 1.3333333333333333, "grad_norm": 9.343498229980469, "learning_rate": 1.689774518551478e-06, "loss": 0.11523465067148209, "step": 5136 }, { "epoch": 1.3335929387331256, "grad_norm": 7.798018455505371, "learning_rate": 1.6889402126058674e-06, "loss": 0.1483953297138214, "step": 5137 }, { "epoch": 1.333852544132918, "grad_norm": 5.901391506195068, "learning_rate": 1.6881060942313322e-06, "loss": 0.03527364507317543, "step": 5138 }, { "epoch": 1.3341121495327104, "grad_norm": 9.92304515838623, "learning_rate": 1.687272163575324e-06, "loss": 0.15988343954086304, "step": 5139 }, { "epoch": 1.3343717549325027, "grad_norm": 10.061573028564453, "learning_rate": 1.6864384207852655e-06, "loss": 0.13167613744735718, "step": 5140 }, { "epoch": 1.334631360332295, "grad_norm": 9.802764892578125, "learning_rate": 1.6856048660085418e-06, "loss": 0.11986713111400604, "step": 5141 }, { "epoch": 1.3348909657320873, "grad_norm": 8.335078239440918, "learning_rate": 1.6847714993925051e-06, "loss": 0.04059702903032303, "step": 5142 }, { "epoch": 1.3351505711318796, "grad_norm": 10.043451309204102, "learning_rate": 1.6839383210844779e-06, "loss": 0.10464279353618622, "step": 5143 }, { "epoch": 1.335410176531672, "grad_norm": 7.348189830780029, "learning_rate": 1.683105331231745e-06, "loss": 0.127277210354805, "step": 5144 }, { "epoch": 1.3356697819314642, "grad_norm": 9.026698112487793, "learning_rate": 1.6822725299815618e-06, "loss": 0.1354837864637375, "step": 5145 }, { "epoch": 1.3359293873312565, "grad_norm": 10.242551803588867, "learning_rate": 1.6814399174811475e-06, "loss": 0.018624383956193924, "step": 5146 }, { "epoch": 1.3361889927310489, "grad_norm": 6.5287184715271, "learning_rate": 1.6806074938776884e-06, "loss": 0.2203342765569687, "step": 5147 }, { "epoch": 1.3364485981308412, "grad_norm": 9.415583610534668, "learning_rate": 1.6797752593183393e-06, "loss": 0.049748148769140244, "step": 5148 }, { "epoch": 1.3367082035306335, "grad_norm": 3.162950277328491, "learning_rate": 1.6789432139502192e-06, "loss": 0.007413007318973541, "step": 5149 }, { "epoch": 1.3369678089304258, "grad_norm": 11.884135246276855, "learning_rate": 1.6781113579204145e-06, "loss": 0.20324605703353882, "step": 5150 }, { "epoch": 1.337227414330218, "grad_norm": 10.876842498779297, "learning_rate": 1.6772796913759792e-06, "loss": 0.06270156800746918, "step": 5151 }, { "epoch": 1.3374870197300104, "grad_norm": 3.0815911293029785, "learning_rate": 1.6764482144639326e-06, "loss": 0.006542264483869076, "step": 5152 }, { "epoch": 1.3377466251298027, "grad_norm": 12.568303108215332, "learning_rate": 1.6756169273312606e-06, "loss": 0.049364592880010605, "step": 5153 }, { "epoch": 1.338006230529595, "grad_norm": 13.289052963256836, "learning_rate": 1.6747858301249148e-06, "loss": 0.06753618270158768, "step": 5154 }, { "epoch": 1.3382658359293873, "grad_norm": 8.272306442260742, "learning_rate": 1.6739549229918154e-06, "loss": 0.1808578073978424, "step": 5155 }, { "epoch": 1.3385254413291796, "grad_norm": 12.92064094543457, "learning_rate": 1.6731242060788489e-06, "loss": 0.03721708059310913, "step": 5156 }, { "epoch": 1.338785046728972, "grad_norm": 9.839875221252441, "learning_rate": 1.6722936795328637e-06, "loss": 0.08408258855342865, "step": 5157 }, { "epoch": 1.3390446521287642, "grad_norm": 15.377281188964844, "learning_rate": 1.671463343500681e-06, "loss": 0.07011891156435013, "step": 5158 }, { "epoch": 1.3393042575285565, "grad_norm": 7.400469779968262, "learning_rate": 1.670633198129083e-06, "loss": 0.2405165582895279, "step": 5159 }, { "epoch": 1.3395638629283488, "grad_norm": 9.94312858581543, "learning_rate": 1.669803243564822e-06, "loss": 0.03974202275276184, "step": 5160 }, { "epoch": 1.3398234683281411, "grad_norm": 9.35326862335205, "learning_rate": 1.6689734799546145e-06, "loss": 0.054171718657016754, "step": 5161 }, { "epoch": 1.3400830737279334, "grad_norm": 9.866500854492188, "learning_rate": 1.6681439074451424e-06, "loss": 0.0648047998547554, "step": 5162 }, { "epoch": 1.3403426791277258, "grad_norm": 8.586215019226074, "learning_rate": 1.6673145261830577e-06, "loss": 0.06802234053611755, "step": 5163 }, { "epoch": 1.340602284527518, "grad_norm": 5.837095737457275, "learning_rate": 1.6664853363149739e-06, "loss": 0.021430175751447678, "step": 5164 }, { "epoch": 1.3408618899273104, "grad_norm": 5.3848700523376465, "learning_rate": 1.6656563379874724e-06, "loss": 0.01038355939090252, "step": 5165 }, { "epoch": 1.3411214953271027, "grad_norm": 5.626173973083496, "learning_rate": 1.6648275313471039e-06, "loss": 0.02162257954478264, "step": 5166 }, { "epoch": 1.341381100726895, "grad_norm": 7.780850410461426, "learning_rate": 1.6639989165403794e-06, "loss": 0.13717949390411377, "step": 5167 }, { "epoch": 1.3416407061266875, "grad_norm": 7.689326763153076, "learning_rate": 1.6631704937137811e-06, "loss": 0.0768977552652359, "step": 5168 }, { "epoch": 1.3419003115264798, "grad_norm": 10.239666938781738, "learning_rate": 1.6623422630137542e-06, "loss": 0.0384475402534008, "step": 5169 }, { "epoch": 1.3421599169262721, "grad_norm": 6.386974811553955, "learning_rate": 1.6615142245867107e-06, "loss": 0.20224496722221375, "step": 5170 }, { "epoch": 1.3424195223260644, "grad_norm": 8.318122863769531, "learning_rate": 1.66068637857903e-06, "loss": 0.1421758085489273, "step": 5171 }, { "epoch": 1.3426791277258567, "grad_norm": 7.4352922439575195, "learning_rate": 1.6598587251370557e-06, "loss": 0.12133767455816269, "step": 5172 }, { "epoch": 1.342938733125649, "grad_norm": 7.2520833015441895, "learning_rate": 1.659031264407097e-06, "loss": 0.02945343777537346, "step": 5173 }, { "epoch": 1.3431983385254413, "grad_norm": 6.852450370788574, "learning_rate": 1.6582039965354313e-06, "loss": 0.0307542085647583, "step": 5174 }, { "epoch": 1.3434579439252337, "grad_norm": 10.679596900939941, "learning_rate": 1.6573769216683e-06, "loss": 0.08197537064552307, "step": 5175 }, { "epoch": 1.343717549325026, "grad_norm": 7.1876678466796875, "learning_rate": 1.6565500399519116e-06, "loss": 0.0551590658724308, "step": 5176 }, { "epoch": 1.3439771547248183, "grad_norm": 7.727220058441162, "learning_rate": 1.6557233515324398e-06, "loss": 0.07184228301048279, "step": 5177 }, { "epoch": 1.3442367601246106, "grad_norm": 8.486368179321289, "learning_rate": 1.6548968565560226e-06, "loss": 0.19753551483154297, "step": 5178 }, { "epoch": 1.3444963655244029, "grad_norm": 8.319323539733887, "learning_rate": 1.6540705551687686e-06, "loss": 0.1604302078485489, "step": 5179 }, { "epoch": 1.3447559709241952, "grad_norm": 9.001075744628906, "learning_rate": 1.653244447516745e-06, "loss": 0.0740472674369812, "step": 5180 }, { "epoch": 1.3450155763239875, "grad_norm": 10.580072402954102, "learning_rate": 1.6524185337459909e-06, "loss": 0.04185495153069496, "step": 5181 }, { "epoch": 1.3452751817237798, "grad_norm": 7.624772548675537, "learning_rate": 1.6515928140025095e-06, "loss": 0.1396847814321518, "step": 5182 }, { "epoch": 1.345534787123572, "grad_norm": 10.146327018737793, "learning_rate": 1.6507672884322685e-06, "loss": 0.10222851485013962, "step": 5183 }, { "epoch": 1.3457943925233644, "grad_norm": 7.121346473693848, "learning_rate": 1.649941957181202e-06, "loss": 0.13583247363567352, "step": 5184 }, { "epoch": 1.3460539979231567, "grad_norm": 9.355398178100586, "learning_rate": 1.6491168203952085e-06, "loss": 0.08897607773542404, "step": 5185 }, { "epoch": 1.3463136033229492, "grad_norm": 6.841733455657959, "learning_rate": 1.6482918782201537e-06, "loss": 0.17453914880752563, "step": 5186 }, { "epoch": 1.3465732087227416, "grad_norm": 6.471242427825928, "learning_rate": 1.6474671308018714e-06, "loss": 0.1816803514957428, "step": 5187 }, { "epoch": 1.3468328141225339, "grad_norm": 15.229243278503418, "learning_rate": 1.646642578286154e-06, "loss": 0.0521467924118042, "step": 5188 }, { "epoch": 1.3470924195223262, "grad_norm": 5.194127082824707, "learning_rate": 1.645818220818766e-06, "loss": 0.02352919429540634, "step": 5189 }, { "epoch": 1.3473520249221185, "grad_norm": 9.700956344604492, "learning_rate": 1.644994058545433e-06, "loss": 0.1336277425289154, "step": 5190 }, { "epoch": 1.3476116303219108, "grad_norm": 7.5865478515625, "learning_rate": 1.6441700916118505e-06, "loss": 0.054430097341537476, "step": 5191 }, { "epoch": 1.347871235721703, "grad_norm": 1.9194656610488892, "learning_rate": 1.6433463201636755e-06, "loss": 0.004519879352301359, "step": 5192 }, { "epoch": 1.3481308411214954, "grad_norm": 10.727429389953613, "learning_rate": 1.642522744346531e-06, "loss": 0.0803331583738327, "step": 5193 }, { "epoch": 1.3483904465212877, "grad_norm": 10.4699068069458, "learning_rate": 1.6416993643060081e-06, "loss": 0.05586669221520424, "step": 5194 }, { "epoch": 1.34865005192108, "grad_norm": 9.105958938598633, "learning_rate": 1.6408761801876612e-06, "loss": 0.10800224542617798, "step": 5195 }, { "epoch": 1.3489096573208723, "grad_norm": 13.311152458190918, "learning_rate": 1.6400531921370095e-06, "loss": 0.05191632732748985, "step": 5196 }, { "epoch": 1.3491692627206646, "grad_norm": 13.809236526489258, "learning_rate": 1.6392304002995397e-06, "loss": 0.032348617911338806, "step": 5197 }, { "epoch": 1.349428868120457, "grad_norm": 8.604084968566895, "learning_rate": 1.6384078048207008e-06, "loss": 0.18733376264572144, "step": 5198 }, { "epoch": 1.3496884735202492, "grad_norm": 12.777754783630371, "learning_rate": 1.6375854058459107e-06, "loss": 0.11822602152824402, "step": 5199 }, { "epoch": 1.3499480789200415, "grad_norm": 9.606423377990723, "learning_rate": 1.63676320352055e-06, "loss": 0.09421989321708679, "step": 5200 }, { "epoch": 1.3502076843198338, "grad_norm": 9.173744201660156, "learning_rate": 1.6359411979899648e-06, "loss": 0.1526297926902771, "step": 5201 }, { "epoch": 1.3504672897196262, "grad_norm": 9.815403938293457, "learning_rate": 1.6351193893994675e-06, "loss": 0.088615283370018, "step": 5202 }, { "epoch": 1.3507268951194185, "grad_norm": 9.410345077514648, "learning_rate": 1.6342977778943353e-06, "loss": 0.09285296499729156, "step": 5203 }, { "epoch": 1.3509865005192108, "grad_norm": 10.195036888122559, "learning_rate": 1.6334763636198083e-06, "loss": 0.07538335025310516, "step": 5204 }, { "epoch": 1.351246105919003, "grad_norm": 9.440836906433105, "learning_rate": 1.6326551467210965e-06, "loss": 0.12676993012428284, "step": 5205 }, { "epoch": 1.3515057113187954, "grad_norm": 12.050540924072266, "learning_rate": 1.6318341273433704e-06, "loss": 0.0476008802652359, "step": 5206 }, { "epoch": 1.3517653167185877, "grad_norm": 8.63272476196289, "learning_rate": 1.6310133056317678e-06, "loss": 0.0590418204665184, "step": 5207 }, { "epoch": 1.35202492211838, "grad_norm": 1.674432635307312, "learning_rate": 1.6301926817313923e-06, "loss": 0.0033628754317760468, "step": 5208 }, { "epoch": 1.3522845275181723, "grad_norm": 10.45157527923584, "learning_rate": 1.629372255787309e-06, "loss": 0.10940997302532196, "step": 5209 }, { "epoch": 1.3525441329179646, "grad_norm": 8.447126388549805, "learning_rate": 1.6285520279445539e-06, "loss": 0.11793992668390274, "step": 5210 }, { "epoch": 1.352803738317757, "grad_norm": 10.150683403015137, "learning_rate": 1.627731998348121e-06, "loss": 0.07574226707220078, "step": 5211 }, { "epoch": 1.3530633437175492, "grad_norm": 12.225767135620117, "learning_rate": 1.626912167142974e-06, "loss": 0.10933159291744232, "step": 5212 }, { "epoch": 1.3533229491173415, "grad_norm": 7.3607258796691895, "learning_rate": 1.6260925344740414e-06, "loss": 0.01603514328598976, "step": 5213 }, { "epoch": 1.3535825545171338, "grad_norm": 7.494224548339844, "learning_rate": 1.6252731004862149e-06, "loss": 0.08965447545051575, "step": 5214 }, { "epoch": 1.3538421599169261, "grad_norm": 7.784119129180908, "learning_rate": 1.6244538653243508e-06, "loss": 0.02308533899486065, "step": 5215 }, { "epoch": 1.3541017653167187, "grad_norm": 6.84290075302124, "learning_rate": 1.6236348291332716e-06, "loss": 0.02787342667579651, "step": 5216 }, { "epoch": 1.354361370716511, "grad_norm": 7.348395347595215, "learning_rate": 1.6228159920577638e-06, "loss": 0.17950907349586487, "step": 5217 }, { "epoch": 1.3546209761163033, "grad_norm": 8.249752044677734, "learning_rate": 1.6219973542425816e-06, "loss": 0.08874104171991348, "step": 5218 }, { "epoch": 1.3548805815160956, "grad_norm": 7.965944766998291, "learning_rate": 1.621178915832437e-06, "loss": 0.06383498758077621, "step": 5219 }, { "epoch": 1.355140186915888, "grad_norm": 7.220761299133301, "learning_rate": 1.6203606769720148e-06, "loss": 0.19469420611858368, "step": 5220 }, { "epoch": 1.3553997923156802, "grad_norm": 10.690885543823242, "learning_rate": 1.6195426378059587e-06, "loss": 0.21548597514629364, "step": 5221 }, { "epoch": 1.3556593977154725, "grad_norm": 9.81281566619873, "learning_rate": 1.6187247984788811e-06, "loss": 0.16158843040466309, "step": 5222 }, { "epoch": 1.3559190031152648, "grad_norm": 9.345661163330078, "learning_rate": 1.6179071591353563e-06, "loss": 0.06471845507621765, "step": 5223 }, { "epoch": 1.3561786085150571, "grad_norm": 14.679018020629883, "learning_rate": 1.6170897199199231e-06, "loss": 0.014690934680402279, "step": 5224 }, { "epoch": 1.3564382139148494, "grad_norm": 8.824769973754883, "learning_rate": 1.6162724809770885e-06, "loss": 0.1285553276538849, "step": 5225 }, { "epoch": 1.3566978193146417, "grad_norm": 8.613593101501465, "learning_rate": 1.6154554424513203e-06, "loss": 0.08056342601776123, "step": 5226 }, { "epoch": 1.356957424714434, "grad_norm": 6.576373100280762, "learning_rate": 1.6146386044870514e-06, "loss": 0.029751069843769073, "step": 5227 }, { "epoch": 1.3572170301142263, "grad_norm": 9.441704750061035, "learning_rate": 1.6138219672286814e-06, "loss": 0.07603519409894943, "step": 5228 }, { "epoch": 1.3574766355140186, "grad_norm": 4.349368095397949, "learning_rate": 1.6130055308205723e-06, "loss": 0.008365530520677567, "step": 5229 }, { "epoch": 1.357736240913811, "grad_norm": 9.2703857421875, "learning_rate": 1.612189295407052e-06, "loss": 0.1423547863960266, "step": 5230 }, { "epoch": 1.3579958463136033, "grad_norm": 8.542278289794922, "learning_rate": 1.6113732611324118e-06, "loss": 0.17902886867523193, "step": 5231 }, { "epoch": 1.3582554517133956, "grad_norm": 4.983769416809082, "learning_rate": 1.6105574281409073e-06, "loss": 0.0160038061439991, "step": 5232 }, { "epoch": 1.3585150571131879, "grad_norm": 8.117551803588867, "learning_rate": 1.6097417965767608e-06, "loss": 0.12475956976413727, "step": 5233 }, { "epoch": 1.3587746625129804, "grad_norm": 7.208653450012207, "learning_rate": 1.608926366584156e-06, "loss": 0.17483694851398468, "step": 5234 }, { "epoch": 1.3590342679127727, "grad_norm": 11.321831703186035, "learning_rate": 1.6081111383072414e-06, "loss": 0.024931058287620544, "step": 5235 }, { "epoch": 1.359293873312565, "grad_norm": 8.649020195007324, "learning_rate": 1.6072961118901328e-06, "loss": 0.16739490628242493, "step": 5236 }, { "epoch": 1.3595534787123573, "grad_norm": 7.241736888885498, "learning_rate": 1.6064812874769073e-06, "loss": 0.2176782786846161, "step": 5237 }, { "epoch": 1.3598130841121496, "grad_norm": 10.284845352172852, "learning_rate": 1.605666665211606e-06, "loss": 0.05460171401500702, "step": 5238 }, { "epoch": 1.360072689511942, "grad_norm": 9.412002563476562, "learning_rate": 1.6048522452382375e-06, "loss": 0.08386191725730896, "step": 5239 }, { "epoch": 1.3603322949117342, "grad_norm": 9.09163761138916, "learning_rate": 1.604038027700771e-06, "loss": 0.11804920434951782, "step": 5240 }, { "epoch": 1.3605919003115265, "grad_norm": 10.921448707580566, "learning_rate": 1.6032240127431433e-06, "loss": 0.14430123567581177, "step": 5241 }, { "epoch": 1.3608515057113189, "grad_norm": 12.51972484588623, "learning_rate": 1.6024102005092513e-06, "loss": 0.1305694282054901, "step": 5242 }, { "epoch": 1.3611111111111112, "grad_norm": 19.023427963256836, "learning_rate": 1.6015965911429593e-06, "loss": 0.05387154594063759, "step": 5243 }, { "epoch": 1.3613707165109035, "grad_norm": 8.148754119873047, "learning_rate": 1.600783184788096e-06, "loss": 0.2236768901348114, "step": 5244 }, { "epoch": 1.3616303219106958, "grad_norm": 8.148299217224121, "learning_rate": 1.5999699815884518e-06, "loss": 0.16461166739463806, "step": 5245 }, { "epoch": 1.361889927310488, "grad_norm": 9.54062557220459, "learning_rate": 1.5991569816877827e-06, "loss": 0.06494037061929703, "step": 5246 }, { "epoch": 1.3621495327102804, "grad_norm": 7.838174343109131, "learning_rate": 1.5983441852298075e-06, "loss": 0.10932430624961853, "step": 5247 }, { "epoch": 1.3624091381100727, "grad_norm": 8.791908264160156, "learning_rate": 1.5975315923582113e-06, "loss": 0.0406758151948452, "step": 5248 }, { "epoch": 1.362668743509865, "grad_norm": 9.457147598266602, "learning_rate": 1.5967192032166429e-06, "loss": 0.15325817465782166, "step": 5249 }, { "epoch": 1.3629283489096573, "grad_norm": 3.0335912704467773, "learning_rate": 1.5959070179487112e-06, "loss": 0.005747363902628422, "step": 5250 }, { "epoch": 1.3631879543094496, "grad_norm": 8.013182640075684, "learning_rate": 1.5950950366979943e-06, "loss": 0.06558997929096222, "step": 5251 }, { "epoch": 1.363447559709242, "grad_norm": 6.155940055847168, "learning_rate": 1.5942832596080304e-06, "loss": 0.024707630276679993, "step": 5252 }, { "epoch": 1.3637071651090342, "grad_norm": 10.31406307220459, "learning_rate": 1.5934716868223244e-06, "loss": 0.08428341895341873, "step": 5253 }, { "epoch": 1.3639667705088265, "grad_norm": 10.370220184326172, "learning_rate": 1.592660318484343e-06, "loss": 0.058933552354574203, "step": 5254 }, { "epoch": 1.3642263759086188, "grad_norm": 10.480037689208984, "learning_rate": 1.5918491547375175e-06, "loss": 0.03869984298944473, "step": 5255 }, { "epoch": 1.3644859813084111, "grad_norm": 14.270220756530762, "learning_rate": 1.591038195725244e-06, "loss": 0.047969043254852295, "step": 5256 }, { "epoch": 1.3647455867082035, "grad_norm": 6.548439979553223, "learning_rate": 1.5902274415908802e-06, "loss": 0.21653807163238525, "step": 5257 }, { "epoch": 1.3650051921079958, "grad_norm": 8.362281799316406, "learning_rate": 1.5894168924777493e-06, "loss": 0.22756138443946838, "step": 5258 }, { "epoch": 1.365264797507788, "grad_norm": 6.904840469360352, "learning_rate": 1.5886065485291385e-06, "loss": 0.19442984461784363, "step": 5259 }, { "epoch": 1.3655244029075804, "grad_norm": 9.046541213989258, "learning_rate": 1.587796409888297e-06, "loss": 0.12066245824098587, "step": 5260 }, { "epoch": 1.3657840083073727, "grad_norm": 8.518424034118652, "learning_rate": 1.5869864766984397e-06, "loss": 0.15605545043945312, "step": 5261 }, { "epoch": 1.366043613707165, "grad_norm": 9.593670845031738, "learning_rate": 1.586176749102744e-06, "loss": 0.12308257818222046, "step": 5262 }, { "epoch": 1.3663032191069573, "grad_norm": 10.357213020324707, "learning_rate": 1.5853672272443499e-06, "loss": 0.14344024658203125, "step": 5263 }, { "epoch": 1.3665628245067498, "grad_norm": 9.706165313720703, "learning_rate": 1.5845579112663651e-06, "loss": 0.1733681857585907, "step": 5264 }, { "epoch": 1.3668224299065421, "grad_norm": 8.47900390625, "learning_rate": 1.5837488013118558e-06, "loss": 0.03213094547390938, "step": 5265 }, { "epoch": 1.3670820353063344, "grad_norm": 8.994719505310059, "learning_rate": 1.5829398975238542e-06, "loss": 0.11337041854858398, "step": 5266 }, { "epoch": 1.3673416407061267, "grad_norm": 6.198131561279297, "learning_rate": 1.5821312000453575e-06, "loss": 0.06472205370664597, "step": 5267 }, { "epoch": 1.367601246105919, "grad_norm": 7.8998870849609375, "learning_rate": 1.581322709019324e-06, "loss": 0.04410821199417114, "step": 5268 }, { "epoch": 1.3678608515057114, "grad_norm": 5.805971145629883, "learning_rate": 1.580514424588675e-06, "loss": 0.019943930208683014, "step": 5269 }, { "epoch": 1.3681204569055037, "grad_norm": 5.622299671173096, "learning_rate": 1.5797063468962998e-06, "loss": 0.01461485680192709, "step": 5270 }, { "epoch": 1.368380062305296, "grad_norm": 6.661832332611084, "learning_rate": 1.5788984760850445e-06, "loss": 0.033220358192920685, "step": 5271 }, { "epoch": 1.3686396677050883, "grad_norm": 8.14207935333252, "learning_rate": 1.5780908122977265e-06, "loss": 0.1909622997045517, "step": 5272 }, { "epoch": 1.3688992731048806, "grad_norm": 8.281014442443848, "learning_rate": 1.5772833556771177e-06, "loss": 0.030044574290513992, "step": 5273 }, { "epoch": 1.3691588785046729, "grad_norm": 5.856735706329346, "learning_rate": 1.57647610636596e-06, "loss": 0.17217840254306793, "step": 5274 }, { "epoch": 1.3694184839044652, "grad_norm": 7.520462512969971, "learning_rate": 1.5756690645069573e-06, "loss": 0.013339750468730927, "step": 5275 }, { "epoch": 1.3696780893042575, "grad_norm": 10.026015281677246, "learning_rate": 1.5748622302427755e-06, "loss": 0.08660167455673218, "step": 5276 }, { "epoch": 1.3699376947040498, "grad_norm": 12.48084831237793, "learning_rate": 1.5740556037160443e-06, "loss": 0.14101043343544006, "step": 5277 }, { "epoch": 1.370197300103842, "grad_norm": 7.46137809753418, "learning_rate": 1.5732491850693557e-06, "loss": 0.02854165807366371, "step": 5278 }, { "epoch": 1.3704569055036344, "grad_norm": 9.602002143859863, "learning_rate": 1.5724429744452674e-06, "loss": 0.11180879920721054, "step": 5279 }, { "epoch": 1.3707165109034267, "grad_norm": 11.161517143249512, "learning_rate": 1.5716369719863003e-06, "loss": 0.10203209519386292, "step": 5280 }, { "epoch": 1.370976116303219, "grad_norm": 8.904410362243652, "learning_rate": 1.5708311778349341e-06, "loss": 0.07448653876781464, "step": 5281 }, { "epoch": 1.3712357217030116, "grad_norm": 8.884866714477539, "learning_rate": 1.5700255921336168e-06, "loss": 0.08257421106100082, "step": 5282 }, { "epoch": 1.3714953271028039, "grad_norm": 9.148530960083008, "learning_rate": 1.5692202150247566e-06, "loss": 0.060226790606975555, "step": 5283 }, { "epoch": 1.3717549325025962, "grad_norm": 6.044318199157715, "learning_rate": 1.5684150466507263e-06, "loss": 0.20680345594882965, "step": 5284 }, { "epoch": 1.3720145379023885, "grad_norm": 8.460076332092285, "learning_rate": 1.567610087153862e-06, "loss": 0.141519695520401, "step": 5285 }, { "epoch": 1.3722741433021808, "grad_norm": 8.381101608276367, "learning_rate": 1.5668053366764596e-06, "loss": 0.11331392824649811, "step": 5286 }, { "epoch": 1.372533748701973, "grad_norm": 5.393473148345947, "learning_rate": 1.566000795360783e-06, "loss": 0.03384567052125931, "step": 5287 }, { "epoch": 1.3727933541017654, "grad_norm": 8.096317291259766, "learning_rate": 1.565196463349056e-06, "loss": 0.14367149770259857, "step": 5288 }, { "epoch": 1.3730529595015577, "grad_norm": 16.909440994262695, "learning_rate": 1.564392340783465e-06, "loss": 0.08842761814594269, "step": 5289 }, { "epoch": 1.37331256490135, "grad_norm": 9.950118064880371, "learning_rate": 1.563588427806162e-06, "loss": 0.051566772162914276, "step": 5290 }, { "epoch": 1.3735721703011423, "grad_norm": 8.22456169128418, "learning_rate": 1.5627847245592598e-06, "loss": 0.16636207699775696, "step": 5291 }, { "epoch": 1.3738317757009346, "grad_norm": 9.408929824829102, "learning_rate": 1.5619812311848336e-06, "loss": 0.18220221996307373, "step": 5292 }, { "epoch": 1.374091381100727, "grad_norm": 10.088114738464355, "learning_rate": 1.561177947824925e-06, "loss": 0.1928592026233673, "step": 5293 }, { "epoch": 1.3743509865005192, "grad_norm": 7.632709980010986, "learning_rate": 1.5603748746215338e-06, "loss": 0.020429152995347977, "step": 5294 }, { "epoch": 1.3746105919003115, "grad_norm": 7.470269203186035, "learning_rate": 1.5595720117166268e-06, "loss": 0.18035756051540375, "step": 5295 }, { "epoch": 1.3748701973001038, "grad_norm": 8.690511703491211, "learning_rate": 1.5587693592521307e-06, "loss": 0.054715581238269806, "step": 5296 }, { "epoch": 1.3751298026998962, "grad_norm": 8.026701927185059, "learning_rate": 1.557966917369936e-06, "loss": 0.04179704189300537, "step": 5297 }, { "epoch": 1.3753894080996885, "grad_norm": 13.43422794342041, "learning_rate": 1.5571646862118968e-06, "loss": 0.054211318492889404, "step": 5298 }, { "epoch": 1.3756490134994808, "grad_norm": 10.917057037353516, "learning_rate": 1.5563626659198289e-06, "loss": 0.044636018574237823, "step": 5299 }, { "epoch": 1.375908618899273, "grad_norm": 8.86841106414795, "learning_rate": 1.55556085663551e-06, "loss": 0.15180428326129913, "step": 5300 }, { "epoch": 1.3761682242990654, "grad_norm": 10.804094314575195, "learning_rate": 1.5547592585006839e-06, "loss": 0.12474159151315689, "step": 5301 }, { "epoch": 1.3764278296988577, "grad_norm": 8.325804710388184, "learning_rate": 1.5539578716570524e-06, "loss": 0.1227065920829773, "step": 5302 }, { "epoch": 1.37668743509865, "grad_norm": 7.52871036529541, "learning_rate": 1.5531566962462853e-06, "loss": 0.17033666372299194, "step": 5303 }, { "epoch": 1.3769470404984423, "grad_norm": 14.065980911254883, "learning_rate": 1.552355732410008e-06, "loss": 0.05927558243274689, "step": 5304 }, { "epoch": 1.3772066458982346, "grad_norm": 12.959402084350586, "learning_rate": 1.551554980289815e-06, "loss": 0.10607878118753433, "step": 5305 }, { "epoch": 1.377466251298027, "grad_norm": 9.758914947509766, "learning_rate": 1.550754440027262e-06, "loss": 0.21411636471748352, "step": 5306 }, { "epoch": 1.3777258566978192, "grad_norm": 6.805299282073975, "learning_rate": 1.5499541117638645e-06, "loss": 0.03370396047830582, "step": 5307 }, { "epoch": 1.3779854620976115, "grad_norm": 7.227850437164307, "learning_rate": 1.5491539956411027e-06, "loss": 0.2050306499004364, "step": 5308 }, { "epoch": 1.3782450674974038, "grad_norm": 7.619629383087158, "learning_rate": 1.548354091800418e-06, "loss": 0.02267354726791382, "step": 5309 }, { "epoch": 1.3785046728971961, "grad_norm": 8.850096702575684, "learning_rate": 1.5475544003832161e-06, "loss": 0.12214121222496033, "step": 5310 }, { "epoch": 1.3787642782969884, "grad_norm": 9.15484619140625, "learning_rate": 1.546754921530865e-06, "loss": 0.09223726391792297, "step": 5311 }, { "epoch": 1.379023883696781, "grad_norm": 11.827319145202637, "learning_rate": 1.5459556553846915e-06, "loss": 0.05400405079126358, "step": 5312 }, { "epoch": 1.3792834890965733, "grad_norm": 10.003668785095215, "learning_rate": 1.5451566020859903e-06, "loss": 0.13391339778900146, "step": 5313 }, { "epoch": 1.3795430944963656, "grad_norm": 9.117853164672852, "learning_rate": 1.5443577617760137e-06, "loss": 0.05200058966875076, "step": 5314 }, { "epoch": 1.379802699896158, "grad_norm": 8.19187068939209, "learning_rate": 1.54355913459598e-06, "loss": 0.1531682312488556, "step": 5315 }, { "epoch": 1.3800623052959502, "grad_norm": 10.720846176147461, "learning_rate": 1.5427607206870677e-06, "loss": 0.032250985503196716, "step": 5316 }, { "epoch": 1.3803219106957425, "grad_norm": 10.5056734085083, "learning_rate": 1.5419625201904164e-06, "loss": 0.07047098875045776, "step": 5317 }, { "epoch": 1.3805815160955348, "grad_norm": 9.303312301635742, "learning_rate": 1.5411645332471326e-06, "loss": 0.13421307504177094, "step": 5318 }, { "epoch": 1.3808411214953271, "grad_norm": 11.590692520141602, "learning_rate": 1.5403667599982808e-06, "loss": 0.09847286343574524, "step": 5319 }, { "epoch": 1.3811007268951194, "grad_norm": 14.697831153869629, "learning_rate": 1.5395692005848876e-06, "loss": 0.054825302213430405, "step": 5320 }, { "epoch": 1.3813603322949117, "grad_norm": 10.849261283874512, "learning_rate": 1.5387718551479452e-06, "loss": 0.11825378984212875, "step": 5321 }, { "epoch": 1.381619937694704, "grad_norm": 12.877946853637695, "learning_rate": 1.5379747238284059e-06, "loss": 0.05562260001897812, "step": 5322 }, { "epoch": 1.3818795430944963, "grad_norm": 5.776100158691406, "learning_rate": 1.5371778067671826e-06, "loss": 0.021966252475976944, "step": 5323 }, { "epoch": 1.3821391484942886, "grad_norm": 2.149083375930786, "learning_rate": 1.5363811041051541e-06, "loss": 0.007162698544561863, "step": 5324 }, { "epoch": 1.382398753894081, "grad_norm": 6.555510520935059, "learning_rate": 1.5355846159831572e-06, "loss": 0.20564523339271545, "step": 5325 }, { "epoch": 1.3826583592938733, "grad_norm": 8.856579780578613, "learning_rate": 1.5347883425419945e-06, "loss": 0.017815038561820984, "step": 5326 }, { "epoch": 1.3829179646936656, "grad_norm": 9.706877708435059, "learning_rate": 1.5339922839224285e-06, "loss": 0.04868682101368904, "step": 5327 }, { "epoch": 1.3831775700934579, "grad_norm": 10.05773639678955, "learning_rate": 1.5331964402651827e-06, "loss": 0.12053798139095306, "step": 5328 }, { "epoch": 1.3834371754932502, "grad_norm": 7.88345193862915, "learning_rate": 1.5324008117109463e-06, "loss": 0.04070255905389786, "step": 5329 }, { "epoch": 1.3836967808930427, "grad_norm": 10.354352951049805, "learning_rate": 1.531605398400367e-06, "loss": 0.12602679431438446, "step": 5330 }, { "epoch": 1.383956386292835, "grad_norm": 7.360202312469482, "learning_rate": 1.5308102004740549e-06, "loss": 0.04332605004310608, "step": 5331 }, { "epoch": 1.3842159916926273, "grad_norm": 7.193620204925537, "learning_rate": 1.530015218072584e-06, "loss": 0.16601242125034332, "step": 5332 }, { "epoch": 1.3844755970924196, "grad_norm": 7.118607997894287, "learning_rate": 1.5292204513364884e-06, "loss": 0.05176633596420288, "step": 5333 }, { "epoch": 1.384735202492212, "grad_norm": 8.68138313293457, "learning_rate": 1.528425900406266e-06, "loss": 0.150282621383667, "step": 5334 }, { "epoch": 1.3849948078920042, "grad_norm": 7.3462677001953125, "learning_rate": 1.5276315654223728e-06, "loss": 0.06396454572677612, "step": 5335 }, { "epoch": 1.3852544132917965, "grad_norm": 6.467790603637695, "learning_rate": 1.5268374465252301e-06, "loss": 0.16677965223789215, "step": 5336 }, { "epoch": 1.3855140186915889, "grad_norm": 7.863952159881592, "learning_rate": 1.5260435438552208e-06, "loss": 0.1488179862499237, "step": 5337 }, { "epoch": 1.3857736240913812, "grad_norm": 7.149718284606934, "learning_rate": 1.5252498575526887e-06, "loss": 0.09056651592254639, "step": 5338 }, { "epoch": 1.3860332294911735, "grad_norm": 8.085183143615723, "learning_rate": 1.524456387757938e-06, "loss": 0.13286370038986206, "step": 5339 }, { "epoch": 1.3862928348909658, "grad_norm": 6.03314733505249, "learning_rate": 1.5236631346112364e-06, "loss": 0.01072664838284254, "step": 5340 }, { "epoch": 1.386552440290758, "grad_norm": 4.2853593826293945, "learning_rate": 1.5228700982528127e-06, "loss": 0.01578601263463497, "step": 5341 }, { "epoch": 1.3868120456905504, "grad_norm": 8.430670738220215, "learning_rate": 1.5220772788228599e-06, "loss": 0.10357480496168137, "step": 5342 }, { "epoch": 1.3870716510903427, "grad_norm": 9.056607246398926, "learning_rate": 1.5212846764615271e-06, "loss": 0.08256644755601883, "step": 5343 }, { "epoch": 1.387331256490135, "grad_norm": 10.663201332092285, "learning_rate": 1.5204922913089305e-06, "loss": 0.11451196670532227, "step": 5344 }, { "epoch": 1.3875908618899273, "grad_norm": 6.693849086761475, "learning_rate": 1.5197001235051446e-06, "loss": 0.009781203232705593, "step": 5345 }, { "epoch": 1.3878504672897196, "grad_norm": 9.67573070526123, "learning_rate": 1.5189081731902062e-06, "loss": 0.13351260125637054, "step": 5346 }, { "epoch": 1.388110072689512, "grad_norm": 8.919293403625488, "learning_rate": 1.5181164405041149e-06, "loss": 0.14652124047279358, "step": 5347 }, { "epoch": 1.3883696780893042, "grad_norm": 7.132058143615723, "learning_rate": 1.5173249255868299e-06, "loss": 0.13838274776935577, "step": 5348 }, { "epoch": 1.3886292834890965, "grad_norm": 9.126842498779297, "learning_rate": 1.5165336285782739e-06, "loss": 0.09343217313289642, "step": 5349 }, { "epoch": 1.3888888888888888, "grad_norm": 17.679244995117188, "learning_rate": 1.5157425496183303e-06, "loss": 0.04692264646291733, "step": 5350 }, { "epoch": 1.3891484942886811, "grad_norm": 3.570707082748413, "learning_rate": 1.5149516888468423e-06, "loss": 0.017445804551243782, "step": 5351 }, { "epoch": 1.3894080996884735, "grad_norm": 6.2944560050964355, "learning_rate": 1.5141610464036177e-06, "loss": 0.035670384764671326, "step": 5352 }, { "epoch": 1.3896677050882658, "grad_norm": 8.892047882080078, "learning_rate": 1.513370622428423e-06, "loss": 0.09737996757030487, "step": 5353 }, { "epoch": 1.389927310488058, "grad_norm": 10.367972373962402, "learning_rate": 1.5125804170609865e-06, "loss": 0.07727379351854324, "step": 5354 }, { "epoch": 1.3901869158878504, "grad_norm": 7.892663955688477, "learning_rate": 1.5117904304409997e-06, "loss": 0.10850843787193298, "step": 5355 }, { "epoch": 1.3904465212876427, "grad_norm": 7.144579887390137, "learning_rate": 1.511000662708113e-06, "loss": 0.028065800666809082, "step": 5356 }, { "epoch": 1.390706126687435, "grad_norm": 8.735821723937988, "learning_rate": 1.5102111140019404e-06, "loss": 0.08132467418909073, "step": 5357 }, { "epoch": 1.3909657320872273, "grad_norm": 9.58808708190918, "learning_rate": 1.5094217844620558e-06, "loss": 0.05975838750600815, "step": 5358 }, { "epoch": 1.3912253374870196, "grad_norm": 9.882769584655762, "learning_rate": 1.508632674227993e-06, "loss": 0.1653544306755066, "step": 5359 }, { "epoch": 1.3914849428868121, "grad_norm": 7.506853103637695, "learning_rate": 1.5078437834392508e-06, "loss": 0.11746055632829666, "step": 5360 }, { "epoch": 1.3917445482866044, "grad_norm": 9.702200889587402, "learning_rate": 1.507055112235286e-06, "loss": 0.04288087785243988, "step": 5361 }, { "epoch": 1.3920041536863967, "grad_norm": 6.890796661376953, "learning_rate": 1.5062666607555175e-06, "loss": 0.14084389805793762, "step": 5362 }, { "epoch": 1.392263759086189, "grad_norm": 8.806206703186035, "learning_rate": 1.505478429139326e-06, "loss": 0.15963885188102722, "step": 5363 }, { "epoch": 1.3925233644859814, "grad_norm": 6.032581329345703, "learning_rate": 1.5046904175260513e-06, "loss": 0.048994775861501694, "step": 5364 }, { "epoch": 1.3927829698857737, "grad_norm": 6.245964527130127, "learning_rate": 1.5039026260549988e-06, "loss": 0.027610884979367256, "step": 5365 }, { "epoch": 1.393042575285566, "grad_norm": 6.616786956787109, "learning_rate": 1.5031150548654288e-06, "loss": 0.1747896522283554, "step": 5366 }, { "epoch": 1.3933021806853583, "grad_norm": 7.87692403793335, "learning_rate": 1.502327704096567e-06, "loss": 0.21042989194393158, "step": 5367 }, { "epoch": 1.3935617860851506, "grad_norm": 4.483992099761963, "learning_rate": 1.5015405738876002e-06, "loss": 0.008552069775760174, "step": 5368 }, { "epoch": 1.3938213914849429, "grad_norm": 8.798362731933594, "learning_rate": 1.5007536643776737e-06, "loss": 0.13940337300300598, "step": 5369 }, { "epoch": 1.3940809968847352, "grad_norm": 7.997049808502197, "learning_rate": 1.4999669757058956e-06, "loss": 0.017419686540961266, "step": 5370 }, { "epoch": 1.3943406022845275, "grad_norm": 6.796347618103027, "learning_rate": 1.4991805080113337e-06, "loss": 0.17205534875392914, "step": 5371 }, { "epoch": 1.3946002076843198, "grad_norm": 11.499645233154297, "learning_rate": 1.4983942614330182e-06, "loss": 0.07573007047176361, "step": 5372 }, { "epoch": 1.394859813084112, "grad_norm": 7.926067352294922, "learning_rate": 1.4976082361099397e-06, "loss": 0.12032503634691238, "step": 5373 }, { "epoch": 1.3951194184839044, "grad_norm": 8.44056510925293, "learning_rate": 1.496822432181048e-06, "loss": 0.029989011585712433, "step": 5374 }, { "epoch": 1.3953790238836967, "grad_norm": 8.099782943725586, "learning_rate": 1.4960368497852568e-06, "loss": 0.15238139033317566, "step": 5375 }, { "epoch": 1.395638629283489, "grad_norm": 8.969976425170898, "learning_rate": 1.49525148906144e-06, "loss": 0.12035514414310455, "step": 5376 }, { "epoch": 1.3958982346832813, "grad_norm": 8.387063980102539, "learning_rate": 1.4944663501484285e-06, "loss": 0.17881159484386444, "step": 5377 }, { "epoch": 1.3961578400830739, "grad_norm": 12.220314025878906, "learning_rate": 1.4936814331850188e-06, "loss": 0.08692950010299683, "step": 5378 }, { "epoch": 1.3964174454828662, "grad_norm": 8.883055686950684, "learning_rate": 1.4928967383099655e-06, "loss": 0.09551399201154709, "step": 5379 }, { "epoch": 1.3966770508826585, "grad_norm": 9.232622146606445, "learning_rate": 1.4921122656619855e-06, "loss": 0.10842718929052353, "step": 5380 }, { "epoch": 1.3969366562824508, "grad_norm": 9.184113502502441, "learning_rate": 1.4913280153797553e-06, "loss": 0.12682031095027924, "step": 5381 }, { "epoch": 1.397196261682243, "grad_norm": 8.072134971618652, "learning_rate": 1.4905439876019113e-06, "loss": 0.17845173180103302, "step": 5382 }, { "epoch": 1.3974558670820354, "grad_norm": 7.605972766876221, "learning_rate": 1.4897601824670534e-06, "loss": 0.05304066091775894, "step": 5383 }, { "epoch": 1.3977154724818277, "grad_norm": 11.899151802062988, "learning_rate": 1.4889766001137395e-06, "loss": 0.10782185196876526, "step": 5384 }, { "epoch": 1.39797507788162, "grad_norm": 8.42362117767334, "learning_rate": 1.4881932406804883e-06, "loss": 0.14015069603919983, "step": 5385 }, { "epoch": 1.3982346832814123, "grad_norm": 7.537042140960693, "learning_rate": 1.4874101043057814e-06, "loss": 0.14129288494586945, "step": 5386 }, { "epoch": 1.3984942886812046, "grad_norm": 11.042187690734863, "learning_rate": 1.4866271911280578e-06, "loss": 0.0343618243932724, "step": 5387 }, { "epoch": 1.398753894080997, "grad_norm": 10.936522483825684, "learning_rate": 1.4858445012857203e-06, "loss": 0.09179249405860901, "step": 5388 }, { "epoch": 1.3990134994807892, "grad_norm": 9.719653129577637, "learning_rate": 1.4850620349171297e-06, "loss": 0.13715241849422455, "step": 5389 }, { "epoch": 1.3992731048805815, "grad_norm": 8.414788246154785, "learning_rate": 1.4842797921606073e-06, "loss": 0.1300780326128006, "step": 5390 }, { "epoch": 1.3995327102803738, "grad_norm": 10.166313171386719, "learning_rate": 1.483497773154437e-06, "loss": 0.015457394532859325, "step": 5391 }, { "epoch": 1.3997923156801662, "grad_norm": 10.733803749084473, "learning_rate": 1.4827159780368616e-06, "loss": 0.06030305474996567, "step": 5392 }, { "epoch": 1.4000519210799585, "grad_norm": 7.1749653816223145, "learning_rate": 1.4819344069460833e-06, "loss": 0.03126300871372223, "step": 5393 }, { "epoch": 1.4003115264797508, "grad_norm": 10.036773681640625, "learning_rate": 1.4811530600202683e-06, "loss": 0.0451558455824852, "step": 5394 }, { "epoch": 1.400571131879543, "grad_norm": 10.702322959899902, "learning_rate": 1.4803719373975382e-06, "loss": 0.04759054630994797, "step": 5395 }, { "epoch": 1.4008307372793354, "grad_norm": 2.5858356952667236, "learning_rate": 1.4795910392159798e-06, "loss": 0.005709134042263031, "step": 5396 }, { "epoch": 1.4010903426791277, "grad_norm": 6.807803630828857, "learning_rate": 1.4788103656136372e-06, "loss": 0.03853100538253784, "step": 5397 }, { "epoch": 1.40134994807892, "grad_norm": 6.213100910186768, "learning_rate": 1.478029916728515e-06, "loss": 0.11857811361551285, "step": 5398 }, { "epoch": 1.4016095534787123, "grad_norm": 8.716022491455078, "learning_rate": 1.4772496926985808e-06, "loss": 0.017758766189217567, "step": 5399 }, { "epoch": 1.4018691588785046, "grad_norm": 5.167316913604736, "learning_rate": 1.476469693661757e-06, "loss": 0.021155619993805885, "step": 5400 }, { "epoch": 1.402128764278297, "grad_norm": 6.020216464996338, "learning_rate": 1.4756899197559317e-06, "loss": 0.03655087947845459, "step": 5401 }, { "epoch": 1.4023883696780892, "grad_norm": 9.1631441116333, "learning_rate": 1.4749103711189517e-06, "loss": 0.0942498967051506, "step": 5402 }, { "epoch": 1.4026479750778815, "grad_norm": 10.560129165649414, "learning_rate": 1.4741310478886217e-06, "loss": 0.08774174749851227, "step": 5403 }, { "epoch": 1.4029075804776738, "grad_norm": 7.172115802764893, "learning_rate": 1.4733519502027093e-06, "loss": 0.14546307921409607, "step": 5404 }, { "epoch": 1.4031671858774661, "grad_norm": 9.235494613647461, "learning_rate": 1.47257307819894e-06, "loss": 0.05090084299445152, "step": 5405 }, { "epoch": 1.4034267912772584, "grad_norm": 9.960723876953125, "learning_rate": 1.4717944320150013e-06, "loss": 0.06292320787906647, "step": 5406 }, { "epoch": 1.4036863966770508, "grad_norm": 10.391134262084961, "learning_rate": 1.4710160117885414e-06, "loss": 0.13285666704177856, "step": 5407 }, { "epoch": 1.4039460020768433, "grad_norm": 13.463119506835938, "learning_rate": 1.4702378176571641e-06, "loss": 0.07182904332876205, "step": 5408 }, { "epoch": 1.4042056074766356, "grad_norm": 12.036457061767578, "learning_rate": 1.4694598497584392e-06, "loss": 0.09067290276288986, "step": 5409 }, { "epoch": 1.404465212876428, "grad_norm": 7.4433274269104, "learning_rate": 1.4686821082298914e-06, "loss": 0.12292876839637756, "step": 5410 }, { "epoch": 1.4047248182762202, "grad_norm": 9.253717422485352, "learning_rate": 1.4679045932090092e-06, "loss": 0.08283568918704987, "step": 5411 }, { "epoch": 1.4049844236760125, "grad_norm": 14.65174674987793, "learning_rate": 1.4671273048332389e-06, "loss": 0.03201444447040558, "step": 5412 }, { "epoch": 1.4052440290758048, "grad_norm": 6.602550506591797, "learning_rate": 1.4663502432399861e-06, "loss": 0.17940783500671387, "step": 5413 }, { "epoch": 1.4055036344755971, "grad_norm": 9.750904083251953, "learning_rate": 1.4655734085666198e-06, "loss": 0.15938055515289307, "step": 5414 }, { "epoch": 1.4057632398753894, "grad_norm": 4.503278732299805, "learning_rate": 1.4647968009504654e-06, "loss": 0.010241085663437843, "step": 5415 }, { "epoch": 1.4060228452751817, "grad_norm": 10.524885177612305, "learning_rate": 1.4640204205288084e-06, "loss": 0.09287513047456741, "step": 5416 }, { "epoch": 1.406282450674974, "grad_norm": 10.00966739654541, "learning_rate": 1.4632442674388969e-06, "loss": 0.11114563792943954, "step": 5417 }, { "epoch": 1.4065420560747663, "grad_norm": 6.720124244689941, "learning_rate": 1.4624683418179353e-06, "loss": 0.038833245635032654, "step": 5418 }, { "epoch": 1.4068016614745587, "grad_norm": 11.145310401916504, "learning_rate": 1.461692643803091e-06, "loss": 0.051349714398384094, "step": 5419 }, { "epoch": 1.407061266874351, "grad_norm": 10.43587589263916, "learning_rate": 1.4609171735314892e-06, "loss": 0.07348815351724625, "step": 5420 }, { "epoch": 1.4073208722741433, "grad_norm": 10.316786766052246, "learning_rate": 1.4601419311402142e-06, "loss": 0.06999535858631134, "step": 5421 }, { "epoch": 1.4075804776739356, "grad_norm": 11.16226577758789, "learning_rate": 1.4593669167663126e-06, "loss": 0.05055171251296997, "step": 5422 }, { "epoch": 1.4078400830737279, "grad_norm": 9.063199996948242, "learning_rate": 1.4585921305467887e-06, "loss": 0.054242685437202454, "step": 5423 }, { "epoch": 1.4080996884735202, "grad_norm": 9.987250328063965, "learning_rate": 1.4578175726186056e-06, "loss": 0.039093926548957825, "step": 5424 }, { "epoch": 1.4083592938733125, "grad_norm": 8.125736236572266, "learning_rate": 1.45704324311869e-06, "loss": 0.17931416630744934, "step": 5425 }, { "epoch": 1.408618899273105, "grad_norm": 8.252802848815918, "learning_rate": 1.4562691421839237e-06, "loss": 0.05592896044254303, "step": 5426 }, { "epoch": 1.4088785046728973, "grad_norm": 10.950543403625488, "learning_rate": 1.4554952699511498e-06, "loss": 0.06914839148521423, "step": 5427 }, { "epoch": 1.4091381100726896, "grad_norm": 8.969706535339355, "learning_rate": 1.454721626557173e-06, "loss": 0.15010908246040344, "step": 5428 }, { "epoch": 1.409397715472482, "grad_norm": 14.585598945617676, "learning_rate": 1.4539482121387539e-06, "loss": 0.13510823249816895, "step": 5429 }, { "epoch": 1.4096573208722742, "grad_norm": 11.158748626708984, "learning_rate": 1.4531750268326166e-06, "loss": 0.10123436152935028, "step": 5430 }, { "epoch": 1.4099169262720666, "grad_norm": 7.461811542510986, "learning_rate": 1.45240207077544e-06, "loss": 0.04184667766094208, "step": 5431 }, { "epoch": 1.4101765316718589, "grad_norm": 5.902101993560791, "learning_rate": 1.4516293441038659e-06, "loss": 0.04307031258940697, "step": 5432 }, { "epoch": 1.4104361370716512, "grad_norm": 25.110980987548828, "learning_rate": 1.450856846954496e-06, "loss": 0.05353805050253868, "step": 5433 }, { "epoch": 1.4106957424714435, "grad_norm": 10.783242225646973, "learning_rate": 1.4500845794638886e-06, "loss": 0.14034998416900635, "step": 5434 }, { "epoch": 1.4109553478712358, "grad_norm": 10.6550931930542, "learning_rate": 1.449312541768564e-06, "loss": 0.03117496520280838, "step": 5435 }, { "epoch": 1.411214953271028, "grad_norm": 7.729600429534912, "learning_rate": 1.4485407340049991e-06, "loss": 0.028398843482136726, "step": 5436 }, { "epoch": 1.4114745586708204, "grad_norm": 8.226722717285156, "learning_rate": 1.447769156309633e-06, "loss": 0.14346517622470856, "step": 5437 }, { "epoch": 1.4117341640706127, "grad_norm": 8.343647003173828, "learning_rate": 1.4469978088188646e-06, "loss": 0.06709058582782745, "step": 5438 }, { "epoch": 1.411993769470405, "grad_norm": 8.135261535644531, "learning_rate": 1.4462266916690474e-06, "loss": 0.03873954713344574, "step": 5439 }, { "epoch": 1.4122533748701973, "grad_norm": 7.6041107177734375, "learning_rate": 1.4454558049964993e-06, "loss": 0.05153337121009827, "step": 5440 }, { "epoch": 1.4125129802699896, "grad_norm": 8.616138458251953, "learning_rate": 1.4446851489374942e-06, "loss": 0.06288588047027588, "step": 5441 }, { "epoch": 1.412772585669782, "grad_norm": 6.79640531539917, "learning_rate": 1.4439147236282674e-06, "loss": 0.07325562834739685, "step": 5442 }, { "epoch": 1.4130321910695742, "grad_norm": 8.36706256866455, "learning_rate": 1.4431445292050123e-06, "loss": 0.13495925068855286, "step": 5443 }, { "epoch": 1.4132917964693665, "grad_norm": 8.72175407409668, "learning_rate": 1.4423745658038808e-06, "loss": 0.1460288017988205, "step": 5444 }, { "epoch": 1.4135514018691588, "grad_norm": 9.03812026977539, "learning_rate": 1.4416048335609856e-06, "loss": 0.04085960611701012, "step": 5445 }, { "epoch": 1.4138110072689511, "grad_norm": 7.971168041229248, "learning_rate": 1.4408353326123981e-06, "loss": 0.0434628389775753, "step": 5446 }, { "epoch": 1.4140706126687435, "grad_norm": 8.785202026367188, "learning_rate": 1.4400660630941469e-06, "loss": 0.07542167603969574, "step": 5447 }, { "epoch": 1.4143302180685358, "grad_norm": 8.351974487304688, "learning_rate": 1.439297025142223e-06, "loss": 0.061148740351200104, "step": 5448 }, { "epoch": 1.414589823468328, "grad_norm": 16.194425582885742, "learning_rate": 1.4385282188925732e-06, "loss": 0.09208741784095764, "step": 5449 }, { "epoch": 1.4148494288681204, "grad_norm": 9.784061431884766, "learning_rate": 1.4377596444811064e-06, "loss": 0.06124281510710716, "step": 5450 }, { "epoch": 1.4151090342679127, "grad_norm": 8.147010803222656, "learning_rate": 1.4369913020436882e-06, "loss": 0.08103228360414505, "step": 5451 }, { "epoch": 1.415368639667705, "grad_norm": 9.830822944641113, "learning_rate": 1.436223191716143e-06, "loss": 0.049915388226509094, "step": 5452 }, { "epoch": 1.4156282450674973, "grad_norm": 8.362489700317383, "learning_rate": 1.4354553136342569e-06, "loss": 0.03752352297306061, "step": 5453 }, { "epoch": 1.4158878504672896, "grad_norm": 11.7392578125, "learning_rate": 1.4346876679337721e-06, "loss": 0.12013392895460129, "step": 5454 }, { "epoch": 1.416147455867082, "grad_norm": 8.735631942749023, "learning_rate": 1.43392025475039e-06, "loss": 0.17804798483848572, "step": 5455 }, { "epoch": 1.4164070612668744, "grad_norm": 9.710807800292969, "learning_rate": 1.4331530742197738e-06, "loss": 0.09606719762086868, "step": 5456 }, { "epoch": 1.4166666666666667, "grad_norm": 11.012744903564453, "learning_rate": 1.432386126477542e-06, "loss": 0.09769608080387115, "step": 5457 }, { "epoch": 1.416926272066459, "grad_norm": 2.8724167346954346, "learning_rate": 1.431619411659273e-06, "loss": 0.014337925240397453, "step": 5458 }, { "epoch": 1.4171858774662514, "grad_norm": 6.192224502563477, "learning_rate": 1.4308529299005059e-06, "loss": 0.018254488706588745, "step": 5459 }, { "epoch": 1.4174454828660437, "grad_norm": 8.713011741638184, "learning_rate": 1.4300866813367356e-06, "loss": 0.061370402574539185, "step": 5460 }, { "epoch": 1.417705088265836, "grad_norm": 12.058089256286621, "learning_rate": 1.4293206661034198e-06, "loss": 0.007859325036406517, "step": 5461 }, { "epoch": 1.4179646936656283, "grad_norm": 9.296378135681152, "learning_rate": 1.4285548843359686e-06, "loss": 0.049078915268182755, "step": 5462 }, { "epoch": 1.4182242990654206, "grad_norm": 8.916112899780273, "learning_rate": 1.427789336169757e-06, "loss": 0.06036514416337013, "step": 5463 }, { "epoch": 1.4184839044652129, "grad_norm": 11.995770454406738, "learning_rate": 1.4270240217401171e-06, "loss": 0.03259224817156792, "step": 5464 }, { "epoch": 1.4187435098650052, "grad_norm": 15.196318626403809, "learning_rate": 1.426258941182338e-06, "loss": 0.08492852002382278, "step": 5465 }, { "epoch": 1.4190031152647975, "grad_norm": 9.035319328308105, "learning_rate": 1.4254940946316684e-06, "loss": 0.06069473177194595, "step": 5466 }, { "epoch": 1.4192627206645898, "grad_norm": 9.207514762878418, "learning_rate": 1.4247294822233146e-06, "loss": 0.07225818932056427, "step": 5467 }, { "epoch": 1.4195223260643821, "grad_norm": 5.105385780334473, "learning_rate": 1.423965104092444e-06, "loss": 0.028282083570957184, "step": 5468 }, { "epoch": 1.4197819314641744, "grad_norm": 10.913613319396973, "learning_rate": 1.4232009603741822e-06, "loss": 0.12714383006095886, "step": 5469 }, { "epoch": 1.4200415368639667, "grad_norm": 4.629530429840088, "learning_rate": 1.4224370512036095e-06, "loss": 0.007707742042839527, "step": 5470 }, { "epoch": 1.420301142263759, "grad_norm": 9.686724662780762, "learning_rate": 1.4216733767157698e-06, "loss": 0.05693420022726059, "step": 5471 }, { "epoch": 1.4205607476635513, "grad_norm": 11.236577987670898, "learning_rate": 1.420909937045662e-06, "loss": 0.08058443665504456, "step": 5472 }, { "epoch": 1.4208203530633436, "grad_norm": 8.3109712600708, "learning_rate": 1.4201467323282453e-06, "loss": 0.1821669042110443, "step": 5473 }, { "epoch": 1.421079958463136, "grad_norm": 10.888689994812012, "learning_rate": 1.419383762698437e-06, "loss": 0.13587667047977448, "step": 5474 }, { "epoch": 1.4213395638629285, "grad_norm": 10.295233726501465, "learning_rate": 1.4186210282911118e-06, "loss": 0.08230781555175781, "step": 5475 }, { "epoch": 1.4215991692627208, "grad_norm": 8.530892372131348, "learning_rate": 1.4178585292411046e-06, "loss": 0.10154558718204498, "step": 5476 }, { "epoch": 1.421858774662513, "grad_norm": 9.072016716003418, "learning_rate": 1.4170962656832077e-06, "loss": 0.04135313630104065, "step": 5477 }, { "epoch": 1.4221183800623054, "grad_norm": 8.29041862487793, "learning_rate": 1.416334237752171e-06, "loss": 0.08240097016096115, "step": 5478 }, { "epoch": 1.4223779854620977, "grad_norm": 8.041120529174805, "learning_rate": 1.4155724455827046e-06, "loss": 0.14509421586990356, "step": 5479 }, { "epoch": 1.42263759086189, "grad_norm": 10.2243070602417, "learning_rate": 1.4148108893094756e-06, "loss": 0.18781423568725586, "step": 5480 }, { "epoch": 1.4228971962616823, "grad_norm": 5.918367862701416, "learning_rate": 1.414049569067109e-06, "loss": 0.027340654283761978, "step": 5481 }, { "epoch": 1.4231568016614746, "grad_norm": 7.257382392883301, "learning_rate": 1.41328848499019e-06, "loss": 0.1925169825553894, "step": 5482 }, { "epoch": 1.423416407061267, "grad_norm": 8.336073875427246, "learning_rate": 1.4125276372132594e-06, "loss": 0.13884489238262177, "step": 5483 }, { "epoch": 1.4236760124610592, "grad_norm": 7.356685638427734, "learning_rate": 1.4117670258708194e-06, "loss": 0.08991085737943649, "step": 5484 }, { "epoch": 1.4239356178608515, "grad_norm": 6.9830641746521, "learning_rate": 1.4110066510973275e-06, "loss": 0.1428246796131134, "step": 5485 }, { "epoch": 1.4241952232606438, "grad_norm": 11.064277648925781, "learning_rate": 1.4102465130272003e-06, "loss": 0.07882662117481232, "step": 5486 }, { "epoch": 1.4244548286604362, "grad_norm": 9.657548904418945, "learning_rate": 1.4094866117948136e-06, "loss": 0.07697556167840958, "step": 5487 }, { "epoch": 1.4247144340602285, "grad_norm": 9.568977355957031, "learning_rate": 1.4087269475345009e-06, "loss": 0.0968623012304306, "step": 5488 }, { "epoch": 1.4249740394600208, "grad_norm": 9.116116523742676, "learning_rate": 1.4079675203805516e-06, "loss": 0.0218490157276392, "step": 5489 }, { "epoch": 1.425233644859813, "grad_norm": 8.300312995910645, "learning_rate": 1.4072083304672174e-06, "loss": 0.045041535049676895, "step": 5490 }, { "epoch": 1.4254932502596054, "grad_norm": 6.393424987792969, "learning_rate": 1.4064493779287033e-06, "loss": 0.0467003732919693, "step": 5491 }, { "epoch": 1.4257528556593977, "grad_norm": 8.270915031433105, "learning_rate": 1.4056906628991775e-06, "loss": 0.034246157854795456, "step": 5492 }, { "epoch": 1.42601246105919, "grad_norm": 7.205489635467529, "learning_rate": 1.4049321855127608e-06, "loss": 0.06770449876785278, "step": 5493 }, { "epoch": 1.4262720664589823, "grad_norm": 3.9192721843719482, "learning_rate": 1.4041739459035352e-06, "loss": 0.011141277849674225, "step": 5494 }, { "epoch": 1.4265316718587746, "grad_norm": 7.567033767700195, "learning_rate": 1.4034159442055417e-06, "loss": 0.02764318883419037, "step": 5495 }, { "epoch": 1.426791277258567, "grad_norm": 9.06408405303955, "learning_rate": 1.4026581805527767e-06, "loss": 0.0928252637386322, "step": 5496 }, { "epoch": 1.4270508826583592, "grad_norm": 7.411526679992676, "learning_rate": 1.4019006550791953e-06, "loss": 0.1933298259973526, "step": 5497 }, { "epoch": 1.4273104880581515, "grad_norm": 8.743227005004883, "learning_rate": 1.4011433679187098e-06, "loss": 0.06659477204084396, "step": 5498 }, { "epoch": 1.4275700934579438, "grad_norm": 3.761518716812134, "learning_rate": 1.400386319205192e-06, "loss": 0.006581766530871391, "step": 5499 }, { "epoch": 1.4278296988577361, "grad_norm": 6.695815086364746, "learning_rate": 1.3996295090724723e-06, "loss": 0.21066001057624817, "step": 5500 }, { "epoch": 1.4280893042575284, "grad_norm": 8.883511543273926, "learning_rate": 1.3988729376543347e-06, "loss": 0.11076942086219788, "step": 5501 }, { "epoch": 1.4283489096573208, "grad_norm": 6.999568939208984, "learning_rate": 1.3981166050845258e-06, "loss": 0.2123865783214569, "step": 5502 }, { "epoch": 1.428608515057113, "grad_norm": 10.134419441223145, "learning_rate": 1.3973605114967465e-06, "loss": 0.07908232510089874, "step": 5503 }, { "epoch": 1.4288681204569054, "grad_norm": 8.155759811401367, "learning_rate": 1.396604657024658e-06, "loss": 0.13719286024570465, "step": 5504 }, { "epoch": 1.429127725856698, "grad_norm": 7.358661651611328, "learning_rate": 1.3958490418018778e-06, "loss": 0.17427396774291992, "step": 5505 }, { "epoch": 1.4293873312564902, "grad_norm": 9.07320499420166, "learning_rate": 1.3950936659619795e-06, "loss": 0.07197403907775879, "step": 5506 }, { "epoch": 1.4296469366562825, "grad_norm": 6.08734655380249, "learning_rate": 1.3943385296384996e-06, "loss": 0.012898236513137817, "step": 5507 }, { "epoch": 1.4299065420560748, "grad_norm": 10.217681884765625, "learning_rate": 1.3935836329649266e-06, "loss": 0.029554467648267746, "step": 5508 }, { "epoch": 1.4301661474558671, "grad_norm": 8.669442176818848, "learning_rate": 1.3928289760747088e-06, "loss": 0.04973556101322174, "step": 5509 }, { "epoch": 1.4304257528556594, "grad_norm": 8.098166465759277, "learning_rate": 1.3920745591012536e-06, "loss": 0.21559447050094604, "step": 5510 }, { "epoch": 1.4306853582554517, "grad_norm": 7.639484882354736, "learning_rate": 1.3913203821779239e-06, "loss": 0.20260116457939148, "step": 5511 }, { "epoch": 1.430944963655244, "grad_norm": 8.853425025939941, "learning_rate": 1.3905664454380401e-06, "loss": 0.11697506904602051, "step": 5512 }, { "epoch": 1.4312045690550363, "grad_norm": 5.055756568908691, "learning_rate": 1.3898127490148832e-06, "loss": 0.029127182438969612, "step": 5513 }, { "epoch": 1.4314641744548287, "grad_norm": 6.417606353759766, "learning_rate": 1.389059293041687e-06, "loss": 0.0272840429097414, "step": 5514 }, { "epoch": 1.431723779854621, "grad_norm": 10.908087730407715, "learning_rate": 1.3883060776516473e-06, "loss": 0.12207172065973282, "step": 5515 }, { "epoch": 1.4319833852544133, "grad_norm": 7.571567058563232, "learning_rate": 1.3875531029779137e-06, "loss": 0.22365248203277588, "step": 5516 }, { "epoch": 1.4322429906542056, "grad_norm": 8.467215538024902, "learning_rate": 1.3868003691535958e-06, "loss": 0.06550659984350204, "step": 5517 }, { "epoch": 1.4325025960539979, "grad_norm": 7.484626293182373, "learning_rate": 1.3860478763117596e-06, "loss": 0.14394409954547882, "step": 5518 }, { "epoch": 1.4327622014537902, "grad_norm": 10.714242935180664, "learning_rate": 1.3852956245854288e-06, "loss": 0.11600548028945923, "step": 5519 }, { "epoch": 1.4330218068535825, "grad_norm": 6.745232582092285, "learning_rate": 1.3845436141075832e-06, "loss": 0.03571578115224838, "step": 5520 }, { "epoch": 1.4332814122533748, "grad_norm": 8.647963523864746, "learning_rate": 1.3837918450111626e-06, "loss": 0.04425131529569626, "step": 5521 }, { "epoch": 1.433541017653167, "grad_norm": 13.347002029418945, "learning_rate": 1.3830403174290611e-06, "loss": 0.06325769424438477, "step": 5522 }, { "epoch": 1.4338006230529596, "grad_norm": 9.645773887634277, "learning_rate": 1.382289031494134e-06, "loss": 0.05542172119021416, "step": 5523 }, { "epoch": 1.434060228452752, "grad_norm": 11.333439826965332, "learning_rate": 1.3815379873391876e-06, "loss": 0.10472623258829117, "step": 5524 }, { "epoch": 1.4343198338525442, "grad_norm": 2.775134563446045, "learning_rate": 1.3807871850969918e-06, "loss": 0.04285810515284538, "step": 5525 }, { "epoch": 1.4345794392523366, "grad_norm": 7.257162570953369, "learning_rate": 1.3800366249002715e-06, "loss": 0.10357730090618134, "step": 5526 }, { "epoch": 1.4348390446521289, "grad_norm": 9.13148021697998, "learning_rate": 1.3792863068817079e-06, "loss": 0.058844633400440216, "step": 5527 }, { "epoch": 1.4350986500519212, "grad_norm": 6.4059157371521, "learning_rate": 1.3785362311739397e-06, "loss": 0.018201161175966263, "step": 5528 }, { "epoch": 1.4353582554517135, "grad_norm": 9.739400863647461, "learning_rate": 1.377786397909563e-06, "loss": 0.0787728875875473, "step": 5529 }, { "epoch": 1.4356178608515058, "grad_norm": 11.902823448181152, "learning_rate": 1.377036807221132e-06, "loss": 0.11045321822166443, "step": 5530 }, { "epoch": 1.435877466251298, "grad_norm": 8.960169792175293, "learning_rate": 1.376287459241158e-06, "loss": 0.11632558703422546, "step": 5531 }, { "epoch": 1.4361370716510904, "grad_norm": 7.043107032775879, "learning_rate": 1.3755383541021056e-06, "loss": 0.10975479334592819, "step": 5532 }, { "epoch": 1.4363966770508827, "grad_norm": 7.964547157287598, "learning_rate": 1.3747894919364024e-06, "loss": 0.031609468162059784, "step": 5533 }, { "epoch": 1.436656282450675, "grad_norm": 7.102853775024414, "learning_rate": 1.3740408728764277e-06, "loss": 0.1174854189157486, "step": 5534 }, { "epoch": 1.4369158878504673, "grad_norm": 10.169414520263672, "learning_rate": 1.3732924970545225e-06, "loss": 0.08245725929737091, "step": 5535 }, { "epoch": 1.4371754932502596, "grad_norm": 8.798051834106445, "learning_rate": 1.3725443646029811e-06, "loss": 0.10186495631933212, "step": 5536 }, { "epoch": 1.437435098650052, "grad_norm": 10.498743057250977, "learning_rate": 1.3717964756540557e-06, "loss": 0.15006694197654724, "step": 5537 }, { "epoch": 1.4376947040498442, "grad_norm": 18.132429122924805, "learning_rate": 1.3710488303399577e-06, "loss": 0.07299554347991943, "step": 5538 }, { "epoch": 1.4379543094496365, "grad_norm": 7.79577112197876, "learning_rate": 1.3703014287928528e-06, "loss": 0.1595393717288971, "step": 5539 }, { "epoch": 1.4382139148494288, "grad_norm": 7.8560004234313965, "learning_rate": 1.3695542711448636e-06, "loss": 0.041511718183755875, "step": 5540 }, { "epoch": 1.4384735202492211, "grad_norm": 8.695724487304688, "learning_rate": 1.368807357528072e-06, "loss": 0.03846478462219238, "step": 5541 }, { "epoch": 1.4387331256490135, "grad_norm": 6.73705530166626, "learning_rate": 1.368060688074514e-06, "loss": 0.041303642094135284, "step": 5542 }, { "epoch": 1.4389927310488058, "grad_norm": 8.390012741088867, "learning_rate": 1.367314262916184e-06, "loss": 0.11529628932476044, "step": 5543 }, { "epoch": 1.439252336448598, "grad_norm": 9.748218536376953, "learning_rate": 1.3665680821850335e-06, "loss": 0.08525236696004868, "step": 5544 }, { "epoch": 1.4395119418483904, "grad_norm": 11.863451957702637, "learning_rate": 1.365822146012969e-06, "loss": 0.1456001102924347, "step": 5545 }, { "epoch": 1.4397715472481827, "grad_norm": 9.492399215698242, "learning_rate": 1.3650764545318562e-06, "loss": 0.15326395630836487, "step": 5546 }, { "epoch": 1.440031152647975, "grad_norm": 8.517308235168457, "learning_rate": 1.3643310078735156e-06, "loss": 0.06141847372055054, "step": 5547 }, { "epoch": 1.4402907580477673, "grad_norm": 7.785722732543945, "learning_rate": 1.3635858061697246e-06, "loss": 0.029229024425148964, "step": 5548 }, { "epoch": 1.4405503634475596, "grad_norm": 9.445257186889648, "learning_rate": 1.3628408495522195e-06, "loss": 0.07818537950515747, "step": 5549 }, { "epoch": 1.440809968847352, "grad_norm": 9.39675235748291, "learning_rate": 1.36209613815269e-06, "loss": 0.0212102048099041, "step": 5550 }, { "epoch": 1.4410695742471442, "grad_norm": 11.415602684020996, "learning_rate": 1.3613516721027837e-06, "loss": 0.10630223155021667, "step": 5551 }, { "epoch": 1.4413291796469365, "grad_norm": 8.335192680358887, "learning_rate": 1.360607451534107e-06, "loss": 0.1765817403793335, "step": 5552 }, { "epoch": 1.441588785046729, "grad_norm": 7.9767680168151855, "learning_rate": 1.3598634765782192e-06, "loss": 0.05590464174747467, "step": 5553 }, { "epoch": 1.4418483904465214, "grad_norm": 5.666673183441162, "learning_rate": 1.3591197473666401e-06, "loss": 0.03340861201286316, "step": 5554 }, { "epoch": 1.4421079958463137, "grad_norm": 10.137964248657227, "learning_rate": 1.3583762640308412e-06, "loss": 0.0739956945180893, "step": 5555 }, { "epoch": 1.442367601246106, "grad_norm": 8.311525344848633, "learning_rate": 1.3576330267022552e-06, "loss": 0.07572207599878311, "step": 5556 }, { "epoch": 1.4426272066458983, "grad_norm": 4.9235663414001465, "learning_rate": 1.3568900355122697e-06, "loss": 0.01848798245191574, "step": 5557 }, { "epoch": 1.4428868120456906, "grad_norm": 8.12116527557373, "learning_rate": 1.356147290592228e-06, "loss": 0.042016856372356415, "step": 5558 }, { "epoch": 1.4431464174454829, "grad_norm": 6.6484375, "learning_rate": 1.3554047920734301e-06, "loss": 0.037708550691604614, "step": 5559 }, { "epoch": 1.4434060228452752, "grad_norm": 9.880377769470215, "learning_rate": 1.3546625400871321e-06, "loss": 0.036305349320173264, "step": 5560 }, { "epoch": 1.4436656282450675, "grad_norm": 10.018362998962402, "learning_rate": 1.3539205347645485e-06, "loss": 0.1285654753446579, "step": 5561 }, { "epoch": 1.4439252336448598, "grad_norm": 10.16372013092041, "learning_rate": 1.3531787762368498e-06, "loss": 0.1026754304766655, "step": 5562 }, { "epoch": 1.4441848390446521, "grad_norm": 12.226672172546387, "learning_rate": 1.3524372646351585e-06, "loss": 0.09064523875713348, "step": 5563 }, { "epoch": 1.4444444444444444, "grad_norm": 10.866791725158691, "learning_rate": 1.3516960000905601e-06, "loss": 0.014739839360117912, "step": 5564 }, { "epoch": 1.4447040498442367, "grad_norm": 15.40916633605957, "learning_rate": 1.3509549827340917e-06, "loss": 0.02076820284128189, "step": 5565 }, { "epoch": 1.444963655244029, "grad_norm": 10.688849449157715, "learning_rate": 1.350214212696748e-06, "loss": 0.041159264743328094, "step": 5566 }, { "epoch": 1.4452232606438213, "grad_norm": 9.128345489501953, "learning_rate": 1.3494736901094814e-06, "loss": 0.027440346777439117, "step": 5567 }, { "epoch": 1.4454828660436136, "grad_norm": 7.866311073303223, "learning_rate": 1.3487334151031975e-06, "loss": 0.03785569965839386, "step": 5568 }, { "epoch": 1.445742471443406, "grad_norm": 9.803665161132812, "learning_rate": 1.347993387808762e-06, "loss": 0.0439428947865963, "step": 5569 }, { "epoch": 1.4460020768431983, "grad_norm": 8.922355651855469, "learning_rate": 1.3472536083569937e-06, "loss": 0.0430746003985405, "step": 5570 }, { "epoch": 1.4462616822429908, "grad_norm": 6.359393119812012, "learning_rate": 1.3465140768786683e-06, "loss": 0.039617400616407394, "step": 5571 }, { "epoch": 1.446521287642783, "grad_norm": 5.655131816864014, "learning_rate": 1.3457747935045193e-06, "loss": 0.06419433653354645, "step": 5572 }, { "epoch": 1.4467808930425754, "grad_norm": 7.463356971740723, "learning_rate": 1.345035758365234e-06, "loss": 0.18141916394233704, "step": 5573 }, { "epoch": 1.4470404984423677, "grad_norm": 7.623383522033691, "learning_rate": 1.3442969715914568e-06, "loss": 0.13386860489845276, "step": 5574 }, { "epoch": 1.44730010384216, "grad_norm": 11.785513877868652, "learning_rate": 1.343558433313789e-06, "loss": 0.027221493422985077, "step": 5575 }, { "epoch": 1.4475597092419523, "grad_norm": 7.076478958129883, "learning_rate": 1.3428201436627863e-06, "loss": 0.06725606322288513, "step": 5576 }, { "epoch": 1.4478193146417446, "grad_norm": 8.577349662780762, "learning_rate": 1.342082102768963e-06, "loss": 0.1532900482416153, "step": 5577 }, { "epoch": 1.448078920041537, "grad_norm": 12.177986145019531, "learning_rate": 1.3413443107627872e-06, "loss": 0.021980546414852142, "step": 5578 }, { "epoch": 1.4483385254413292, "grad_norm": 9.571271896362305, "learning_rate": 1.340606767774682e-06, "loss": 0.09267392754554749, "step": 5579 }, { "epoch": 1.4485981308411215, "grad_norm": 7.489499568939209, "learning_rate": 1.3398694739350303e-06, "loss": 0.06436525285243988, "step": 5580 }, { "epoch": 1.4488577362409139, "grad_norm": 6.600432872772217, "learning_rate": 1.3391324293741681e-06, "loss": 0.1892806440591812, "step": 5581 }, { "epoch": 1.4491173416407062, "grad_norm": 5.254380226135254, "learning_rate": 1.3383956342223872e-06, "loss": 0.03763451427221298, "step": 5582 }, { "epoch": 1.4493769470404985, "grad_norm": 10.059388160705566, "learning_rate": 1.3376590886099372e-06, "loss": 0.09129363298416138, "step": 5583 }, { "epoch": 1.4496365524402908, "grad_norm": 10.721118927001953, "learning_rate": 1.3369227926670215e-06, "loss": 0.04215380549430847, "step": 5584 }, { "epoch": 1.449896157840083, "grad_norm": 8.81942367553711, "learning_rate": 1.336186746523802e-06, "loss": 0.040052380412817, "step": 5585 }, { "epoch": 1.4501557632398754, "grad_norm": 9.584114074707031, "learning_rate": 1.3354509503103922e-06, "loss": 0.09901133179664612, "step": 5586 }, { "epoch": 1.4504153686396677, "grad_norm": 8.745201110839844, "learning_rate": 1.3347154041568655e-06, "loss": 0.0654657781124115, "step": 5587 }, { "epoch": 1.45067497403946, "grad_norm": 9.396105766296387, "learning_rate": 1.3339801081932507e-06, "loss": 0.09439204633235931, "step": 5588 }, { "epoch": 1.4509345794392523, "grad_norm": 7.252870082855225, "learning_rate": 1.3332450625495298e-06, "loss": 0.03905784711241722, "step": 5589 }, { "epoch": 1.4511941848390446, "grad_norm": 10.735020637512207, "learning_rate": 1.332510267355643e-06, "loss": 0.04670993611216545, "step": 5590 }, { "epoch": 1.451453790238837, "grad_norm": 8.219460487365723, "learning_rate": 1.3317757227414835e-06, "loss": 0.1174047440290451, "step": 5591 }, { "epoch": 1.4517133956386292, "grad_norm": 8.52341079711914, "learning_rate": 1.331041428836904e-06, "loss": 0.025820357725024223, "step": 5592 }, { "epoch": 1.4519730010384215, "grad_norm": 8.516939163208008, "learning_rate": 1.3303073857717103e-06, "loss": 0.08343521505594254, "step": 5593 }, { "epoch": 1.4522326064382138, "grad_norm": 8.290135383605957, "learning_rate": 1.3295735936756631e-06, "loss": 0.07734886556863785, "step": 5594 }, { "epoch": 1.4524922118380061, "grad_norm": 10.74474048614502, "learning_rate": 1.328840052678482e-06, "loss": 0.060471631586551666, "step": 5595 }, { "epoch": 1.4527518172377984, "grad_norm": 8.896937370300293, "learning_rate": 1.3281067629098394e-06, "loss": 0.05427916720509529, "step": 5596 }, { "epoch": 1.4530114226375908, "grad_norm": 9.009980201721191, "learning_rate": 1.3273737244993632e-06, "loss": 0.18581563234329224, "step": 5597 }, { "epoch": 1.453271028037383, "grad_norm": 10.483063697814941, "learning_rate": 1.3266409375766392e-06, "loss": 0.020212529227137566, "step": 5598 }, { "epoch": 1.4535306334371754, "grad_norm": 5.324757099151611, "learning_rate": 1.3259084022712065e-06, "loss": 0.03656933456659317, "step": 5599 }, { "epoch": 1.4537902388369677, "grad_norm": 13.063553810119629, "learning_rate": 1.3251761187125614e-06, "loss": 0.029813673347234726, "step": 5600 }, { "epoch": 1.4540498442367602, "grad_norm": 8.740616798400879, "learning_rate": 1.3244440870301545e-06, "loss": 0.07033288478851318, "step": 5601 }, { "epoch": 1.4543094496365525, "grad_norm": 7.588616847991943, "learning_rate": 1.3237123073533915e-06, "loss": 0.03219248354434967, "step": 5602 }, { "epoch": 1.4545690550363448, "grad_norm": 10.64168643951416, "learning_rate": 1.3229807798116351e-06, "loss": 0.15015751123428345, "step": 5603 }, { "epoch": 1.4548286604361371, "grad_norm": 10.688577651977539, "learning_rate": 1.3222495045342032e-06, "loss": 0.04408622533082962, "step": 5604 }, { "epoch": 1.4550882658359294, "grad_norm": 7.94398832321167, "learning_rate": 1.3215184816503663e-06, "loss": 0.09706312417984009, "step": 5605 }, { "epoch": 1.4553478712357217, "grad_norm": 3.72884202003479, "learning_rate": 1.3207877112893553e-06, "loss": 0.020952431485056877, "step": 5606 }, { "epoch": 1.455607476635514, "grad_norm": 10.16704273223877, "learning_rate": 1.3200571935803513e-06, "loss": 0.06729302555322647, "step": 5607 }, { "epoch": 1.4558670820353063, "grad_norm": 6.85423469543457, "learning_rate": 1.3193269286524945e-06, "loss": 0.01474146731197834, "step": 5608 }, { "epoch": 1.4561266874350987, "grad_norm": 9.538947105407715, "learning_rate": 1.318596916634879e-06, "loss": 0.14007720351219177, "step": 5609 }, { "epoch": 1.456386292834891, "grad_norm": 7.409256458282471, "learning_rate": 1.3178671576565533e-06, "loss": 0.04080543667078018, "step": 5610 }, { "epoch": 1.4566458982346833, "grad_norm": 10.925999641418457, "learning_rate": 1.3171376518465228e-06, "loss": 0.042086753994226456, "step": 5611 }, { "epoch": 1.4569055036344756, "grad_norm": 5.6233673095703125, "learning_rate": 1.3164083993337478e-06, "loss": 0.03387753665447235, "step": 5612 }, { "epoch": 1.4571651090342679, "grad_norm": 7.065145492553711, "learning_rate": 1.3156794002471417e-06, "loss": 0.22273504734039307, "step": 5613 }, { "epoch": 1.4574247144340602, "grad_norm": 7.461042404174805, "learning_rate": 1.314950654715577e-06, "loss": 0.15931391716003418, "step": 5614 }, { "epoch": 1.4576843198338525, "grad_norm": 9.376483917236328, "learning_rate": 1.3142221628678778e-06, "loss": 0.07363161444664001, "step": 5615 }, { "epoch": 1.4579439252336448, "grad_norm": 9.476765632629395, "learning_rate": 1.3134939248328265e-06, "loss": 0.1422986388206482, "step": 5616 }, { "epoch": 1.458203530633437, "grad_norm": 7.736110210418701, "learning_rate": 1.3127659407391564e-06, "loss": 0.06049273908138275, "step": 5617 }, { "epoch": 1.4584631360332294, "grad_norm": 7.019824028015137, "learning_rate": 1.3120382107155595e-06, "loss": 0.13570542633533478, "step": 5618 }, { "epoch": 1.458722741433022, "grad_norm": 6.551684856414795, "learning_rate": 1.3113107348906833e-06, "loss": 0.05592062324285507, "step": 5619 }, { "epoch": 1.4589823468328142, "grad_norm": 4.7880940437316895, "learning_rate": 1.3105835133931264e-06, "loss": 0.03539074584841728, "step": 5620 }, { "epoch": 1.4592419522326066, "grad_norm": 8.05263614654541, "learning_rate": 1.3098565463514467e-06, "loss": 0.06263624131679535, "step": 5621 }, { "epoch": 1.4595015576323989, "grad_norm": 7.86428165435791, "learning_rate": 1.3091298338941538e-06, "loss": 0.062073834240436554, "step": 5622 }, { "epoch": 1.4597611630321912, "grad_norm": 9.331265449523926, "learning_rate": 1.3084033761497156e-06, "loss": 0.02080014906823635, "step": 5623 }, { "epoch": 1.4600207684319835, "grad_norm": 8.09192943572998, "learning_rate": 1.3076771732465521e-06, "loss": 0.04983188211917877, "step": 5624 }, { "epoch": 1.4602803738317758, "grad_norm": 8.175018310546875, "learning_rate": 1.306951225313039e-06, "loss": 0.16332487761974335, "step": 5625 }, { "epoch": 1.460539979231568, "grad_norm": 5.466986179351807, "learning_rate": 1.3062255324775086e-06, "loss": 0.009959761053323746, "step": 5626 }, { "epoch": 1.4607995846313604, "grad_norm": 13.56248664855957, "learning_rate": 1.3055000948682458e-06, "loss": 0.046404577791690826, "step": 5627 }, { "epoch": 1.4610591900311527, "grad_norm": 8.991293907165527, "learning_rate": 1.3047749126134912e-06, "loss": 0.046309251338243484, "step": 5628 }, { "epoch": 1.461318795430945, "grad_norm": 6.532393932342529, "learning_rate": 1.304049985841441e-06, "loss": 0.04923570528626442, "step": 5629 }, { "epoch": 1.4615784008307373, "grad_norm": 8.962593078613281, "learning_rate": 1.303325314680245e-06, "loss": 0.015350721776485443, "step": 5630 }, { "epoch": 1.4618380062305296, "grad_norm": 8.358607292175293, "learning_rate": 1.3026008992580096e-06, "loss": 0.06638162583112717, "step": 5631 }, { "epoch": 1.462097611630322, "grad_norm": 2.640552043914795, "learning_rate": 1.3018767397027942e-06, "loss": 0.008720946498215199, "step": 5632 }, { "epoch": 1.4623572170301142, "grad_norm": 10.591498374938965, "learning_rate": 1.301152836142613e-06, "loss": 0.08466355502605438, "step": 5633 }, { "epoch": 1.4626168224299065, "grad_norm": 11.763611793518066, "learning_rate": 1.3004291887054366e-06, "loss": 0.09886270761489868, "step": 5634 }, { "epoch": 1.4628764278296988, "grad_norm": 8.067373275756836, "learning_rate": 1.299705797519189e-06, "loss": 0.1739262044429779, "step": 5635 }, { "epoch": 1.4631360332294912, "grad_norm": 9.156147956848145, "learning_rate": 1.2989826627117482e-06, "loss": 0.09310568869113922, "step": 5636 }, { "epoch": 1.4633956386292835, "grad_norm": 8.469603538513184, "learning_rate": 1.2982597844109498e-06, "loss": 0.04082649201154709, "step": 5637 }, { "epoch": 1.4636552440290758, "grad_norm": 9.312158584594727, "learning_rate": 1.29753716274458e-06, "loss": 0.017269890755414963, "step": 5638 }, { "epoch": 1.463914849428868, "grad_norm": 10.284122467041016, "learning_rate": 1.2968147978403835e-06, "loss": 0.04176195710897446, "step": 5639 }, { "epoch": 1.4641744548286604, "grad_norm": 6.980477333068848, "learning_rate": 1.2960926898260575e-06, "loss": 0.1963951289653778, "step": 5640 }, { "epoch": 1.4644340602284527, "grad_norm": 17.006399154663086, "learning_rate": 1.2953708388292533e-06, "loss": 0.06377553939819336, "step": 5641 }, { "epoch": 1.464693665628245, "grad_norm": 10.39399242401123, "learning_rate": 1.294649244977579e-06, "loss": 0.11619904637336731, "step": 5642 }, { "epoch": 1.4649532710280373, "grad_norm": 8.17374038696289, "learning_rate": 1.2939279083985945e-06, "loss": 0.06347209215164185, "step": 5643 }, { "epoch": 1.4652128764278296, "grad_norm": 8.399392127990723, "learning_rate": 1.2932068292198157e-06, "loss": 0.16615813970565796, "step": 5644 }, { "epoch": 1.465472481827622, "grad_norm": 9.350573539733887, "learning_rate": 1.292486007568714e-06, "loss": 0.12675625085830688, "step": 5645 }, { "epoch": 1.4657320872274142, "grad_norm": 9.378758430480957, "learning_rate": 1.2917654435727137e-06, "loss": 0.11098232865333557, "step": 5646 }, { "epoch": 1.4659916926272065, "grad_norm": 8.385417938232422, "learning_rate": 1.2910451373591936e-06, "loss": 0.12357058376073837, "step": 5647 }, { "epoch": 1.4662512980269988, "grad_norm": 9.138087272644043, "learning_rate": 1.290325089055487e-06, "loss": 0.05260051041841507, "step": 5648 }, { "epoch": 1.4665109034267914, "grad_norm": 11.841137886047363, "learning_rate": 1.2896052987888825e-06, "loss": 0.08412881195545197, "step": 5649 }, { "epoch": 1.4667705088265837, "grad_norm": 20.489561080932617, "learning_rate": 1.2888857666866243e-06, "loss": 0.0420319028198719, "step": 5650 }, { "epoch": 1.467030114226376, "grad_norm": 10.368449211120605, "learning_rate": 1.2881664928759051e-06, "loss": 0.1323782503604889, "step": 5651 }, { "epoch": 1.4672897196261683, "grad_norm": 6.991710186004639, "learning_rate": 1.2874474774838802e-06, "loss": 0.16537544131278992, "step": 5652 }, { "epoch": 1.4675493250259606, "grad_norm": 8.330705642700195, "learning_rate": 1.2867287206376522e-06, "loss": 0.07795198261737823, "step": 5653 }, { "epoch": 1.467808930425753, "grad_norm": 7.110814571380615, "learning_rate": 1.2860102224642823e-06, "loss": 0.16497880220413208, "step": 5654 }, { "epoch": 1.4680685358255452, "grad_norm": 8.872294425964355, "learning_rate": 1.2852919830907846e-06, "loss": 0.13485008478164673, "step": 5655 }, { "epoch": 1.4683281412253375, "grad_norm": 16.501049041748047, "learning_rate": 1.284574002644126e-06, "loss": 0.028490174561738968, "step": 5656 }, { "epoch": 1.4685877466251298, "grad_norm": 7.256619453430176, "learning_rate": 1.2838562812512306e-06, "loss": 0.04833918809890747, "step": 5657 }, { "epoch": 1.4688473520249221, "grad_norm": 9.696182250976562, "learning_rate": 1.2831388190389747e-06, "loss": 0.10409028828144073, "step": 5658 }, { "epoch": 1.4691069574247144, "grad_norm": 7.878911018371582, "learning_rate": 1.2824216161341879e-06, "loss": 0.1463499665260315, "step": 5659 }, { "epoch": 1.4693665628245067, "grad_norm": 7.004404544830322, "learning_rate": 1.2817046726636573e-06, "loss": 0.06937211751937866, "step": 5660 }, { "epoch": 1.469626168224299, "grad_norm": 9.085766792297363, "learning_rate": 1.28098798875412e-06, "loss": 0.14488406479358673, "step": 5661 }, { "epoch": 1.4698857736240913, "grad_norm": 9.355705261230469, "learning_rate": 1.280271564532271e-06, "loss": 0.09708565473556519, "step": 5662 }, { "epoch": 1.4701453790238836, "grad_norm": 8.140201568603516, "learning_rate": 1.2795554001247574e-06, "loss": 0.051280248910188675, "step": 5663 }, { "epoch": 1.470404984423676, "grad_norm": 9.604181289672852, "learning_rate": 1.2788394956581795e-06, "loss": 0.18569205701351166, "step": 5664 }, { "epoch": 1.4706645898234683, "grad_norm": 7.39485502243042, "learning_rate": 1.2781238512590944e-06, "loss": 0.13375675678253174, "step": 5665 }, { "epoch": 1.4709241952232606, "grad_norm": 9.522624015808105, "learning_rate": 1.277408467054011e-06, "loss": 0.040921650826931, "step": 5666 }, { "epoch": 1.471183800623053, "grad_norm": 7.1907501220703125, "learning_rate": 1.2766933431693919e-06, "loss": 0.03837442398071289, "step": 5667 }, { "epoch": 1.4714434060228454, "grad_norm": 6.378300189971924, "learning_rate": 1.275978479731656e-06, "loss": 0.012433560565114021, "step": 5668 }, { "epoch": 1.4717030114226377, "grad_norm": 8.019015312194824, "learning_rate": 1.2752638768671738e-06, "loss": 0.078182153403759, "step": 5669 }, { "epoch": 1.47196261682243, "grad_norm": 10.622651100158691, "learning_rate": 1.2745495347022722e-06, "loss": 0.11137887835502625, "step": 5670 }, { "epoch": 1.4722222222222223, "grad_norm": 6.919636249542236, "learning_rate": 1.273835453363229e-06, "loss": 0.02333010733127594, "step": 5671 }, { "epoch": 1.4724818276220146, "grad_norm": 9.264680862426758, "learning_rate": 1.2731216329762775e-06, "loss": 0.07343105971813202, "step": 5672 }, { "epoch": 1.472741433021807, "grad_norm": 11.430480003356934, "learning_rate": 1.2724080736676064e-06, "loss": 0.03997465595602989, "step": 5673 }, { "epoch": 1.4730010384215992, "grad_norm": 15.101462364196777, "learning_rate": 1.2716947755633547e-06, "loss": 0.05957283452153206, "step": 5674 }, { "epoch": 1.4732606438213915, "grad_norm": 7.724887847900391, "learning_rate": 1.2709817387896173e-06, "loss": 0.01632322371006012, "step": 5675 }, { "epoch": 1.4735202492211839, "grad_norm": 10.889435768127441, "learning_rate": 1.2702689634724446e-06, "loss": 0.1069873571395874, "step": 5676 }, { "epoch": 1.4737798546209762, "grad_norm": 10.662954330444336, "learning_rate": 1.2695564497378377e-06, "loss": 0.03558206930756569, "step": 5677 }, { "epoch": 1.4740394600207685, "grad_norm": 8.732804298400879, "learning_rate": 1.2688441977117526e-06, "loss": 0.08665340393781662, "step": 5678 }, { "epoch": 1.4742990654205608, "grad_norm": 8.390684127807617, "learning_rate": 1.2681322075200988e-06, "loss": 0.21138399839401245, "step": 5679 }, { "epoch": 1.474558670820353, "grad_norm": 8.636568069458008, "learning_rate": 1.2674204792887406e-06, "loss": 0.11615695804357529, "step": 5680 }, { "epoch": 1.4748182762201454, "grad_norm": 5.887744426727295, "learning_rate": 1.2667090131434961e-06, "loss": 0.011156267486512661, "step": 5681 }, { "epoch": 1.4750778816199377, "grad_norm": 3.256464719772339, "learning_rate": 1.2659978092101343e-06, "loss": 0.011518513783812523, "step": 5682 }, { "epoch": 1.47533748701973, "grad_norm": 4.322808742523193, "learning_rate": 1.2652868676143806e-06, "loss": 0.023729942739009857, "step": 5683 }, { "epoch": 1.4755970924195223, "grad_norm": 9.159924507141113, "learning_rate": 1.2645761884819136e-06, "loss": 0.07182110846042633, "step": 5684 }, { "epoch": 1.4758566978193146, "grad_norm": 8.31926441192627, "learning_rate": 1.263865771938365e-06, "loss": 0.15412956476211548, "step": 5685 }, { "epoch": 1.476116303219107, "grad_norm": 9.229022979736328, "learning_rate": 1.2631556181093202e-06, "loss": 0.1020444929599762, "step": 5686 }, { "epoch": 1.4763759086188992, "grad_norm": 10.238409042358398, "learning_rate": 1.2624457271203172e-06, "loss": 0.049752168357372284, "step": 5687 }, { "epoch": 1.4766355140186915, "grad_norm": 0.7785980105400085, "learning_rate": 1.2617360990968486e-06, "loss": 0.0022170408628880978, "step": 5688 }, { "epoch": 1.4768951194184838, "grad_norm": 8.043182373046875, "learning_rate": 1.2610267341643628e-06, "loss": 0.06127530336380005, "step": 5689 }, { "epoch": 1.4771547248182761, "grad_norm": 8.836763381958008, "learning_rate": 1.260317632448256e-06, "loss": 0.14367596805095673, "step": 5690 }, { "epoch": 1.4774143302180685, "grad_norm": 8.8645601272583, "learning_rate": 1.2596087940738832e-06, "loss": 0.14072617888450623, "step": 5691 }, { "epoch": 1.4776739356178608, "grad_norm": 7.332346439361572, "learning_rate": 1.2589002191665495e-06, "loss": 0.15935319662094116, "step": 5692 }, { "epoch": 1.477933541017653, "grad_norm": 9.511393547058105, "learning_rate": 1.2581919078515161e-06, "loss": 0.04814625903964043, "step": 5693 }, { "epoch": 1.4781931464174454, "grad_norm": 9.032256126403809, "learning_rate": 1.2574838602539955e-06, "loss": 0.10581433027982712, "step": 5694 }, { "epoch": 1.4784527518172377, "grad_norm": 9.689663887023926, "learning_rate": 1.2567760764991536e-06, "loss": 0.13088542222976685, "step": 5695 }, { "epoch": 1.47871235721703, "grad_norm": 6.858417987823486, "learning_rate": 1.2560685567121116e-06, "loss": 0.027578409761190414, "step": 5696 }, { "epoch": 1.4789719626168225, "grad_norm": 5.957778453826904, "learning_rate": 1.2553613010179427e-06, "loss": 0.03608587384223938, "step": 5697 }, { "epoch": 1.4792315680166148, "grad_norm": 7.719024181365967, "learning_rate": 1.2546543095416718e-06, "loss": 0.03727800399065018, "step": 5698 }, { "epoch": 1.4794911734164071, "grad_norm": 6.331921577453613, "learning_rate": 1.2539475824082813e-06, "loss": 0.02608262188732624, "step": 5699 }, { "epoch": 1.4797507788161994, "grad_norm": 7.5468339920043945, "learning_rate": 1.2532411197427034e-06, "loss": 0.015193245373666286, "step": 5700 }, { "epoch": 1.4800103842159917, "grad_norm": 8.501947402954102, "learning_rate": 1.2525349216698229e-06, "loss": 0.14444418251514435, "step": 5701 }, { "epoch": 1.480269989615784, "grad_norm": 7.750917911529541, "learning_rate": 1.2518289883144819e-06, "loss": 0.178831547498703, "step": 5702 }, { "epoch": 1.4805295950155763, "grad_norm": 6.6258111000061035, "learning_rate": 1.2511233198014716e-06, "loss": 0.01271783746778965, "step": 5703 }, { "epoch": 1.4807892004153687, "grad_norm": 8.456064224243164, "learning_rate": 1.2504179162555392e-06, "loss": 0.06693121045827866, "step": 5704 }, { "epoch": 1.481048805815161, "grad_norm": 8.630645751953125, "learning_rate": 1.2497127778013833e-06, "loss": 0.12159736454486847, "step": 5705 }, { "epoch": 1.4813084112149533, "grad_norm": 10.128578186035156, "learning_rate": 1.2490079045636554e-06, "loss": 0.017209943383932114, "step": 5706 }, { "epoch": 1.4815680166147456, "grad_norm": 3.6480190753936768, "learning_rate": 1.248303296666963e-06, "loss": 0.009149383753538132, "step": 5707 }, { "epoch": 1.4818276220145379, "grad_norm": 8.647954940795898, "learning_rate": 1.247598954235863e-06, "loss": 0.062247514724731445, "step": 5708 }, { "epoch": 1.4820872274143302, "grad_norm": 6.992454528808594, "learning_rate": 1.2468948773948669e-06, "loss": 0.03025323711335659, "step": 5709 }, { "epoch": 1.4823468328141225, "grad_norm": 8.059597969055176, "learning_rate": 1.2461910662684404e-06, "loss": 0.02132660523056984, "step": 5710 }, { "epoch": 1.4826064382139148, "grad_norm": 10.261658668518066, "learning_rate": 1.2454875209810005e-06, "loss": 0.16484934091567993, "step": 5711 }, { "epoch": 1.482866043613707, "grad_norm": 12.579419136047363, "learning_rate": 1.2447842416569192e-06, "loss": 0.11485376954078674, "step": 5712 }, { "epoch": 1.4831256490134994, "grad_norm": 11.824892044067383, "learning_rate": 1.244081228420518e-06, "loss": 0.01989266462624073, "step": 5713 }, { "epoch": 1.4833852544132917, "grad_norm": 8.956391334533691, "learning_rate": 1.2433784813960743e-06, "loss": 0.033492326736450195, "step": 5714 }, { "epoch": 1.4836448598130842, "grad_norm": 8.612380027770996, "learning_rate": 1.2426760007078188e-06, "loss": 0.014069180935621262, "step": 5715 }, { "epoch": 1.4839044652128766, "grad_norm": 9.743985176086426, "learning_rate": 1.2419737864799334e-06, "loss": 0.11153620481491089, "step": 5716 }, { "epoch": 1.4841640706126689, "grad_norm": 10.671978950500488, "learning_rate": 1.2412718388365532e-06, "loss": 0.05786152556538582, "step": 5717 }, { "epoch": 1.4844236760124612, "grad_norm": 14.520308494567871, "learning_rate": 1.2405701579017658e-06, "loss": 0.051628630608320236, "step": 5718 }, { "epoch": 1.4846832814122535, "grad_norm": 4.55833625793457, "learning_rate": 1.2398687437996133e-06, "loss": 0.0167633518576622, "step": 5719 }, { "epoch": 1.4849428868120458, "grad_norm": 8.654436111450195, "learning_rate": 1.239167596654091e-06, "loss": 0.06383093446493149, "step": 5720 }, { "epoch": 1.485202492211838, "grad_norm": 7.282694339752197, "learning_rate": 1.2384667165891424e-06, "loss": 0.12018869817256927, "step": 5721 }, { "epoch": 1.4854620976116304, "grad_norm": 10.541799545288086, "learning_rate": 1.2377661037286698e-06, "loss": 0.039129145443439484, "step": 5722 }, { "epoch": 1.4857217030114227, "grad_norm": 11.795473098754883, "learning_rate": 1.2370657581965236e-06, "loss": 0.08727850764989853, "step": 5723 }, { "epoch": 1.485981308411215, "grad_norm": 7.831371307373047, "learning_rate": 1.2363656801165104e-06, "loss": 0.02823648601770401, "step": 5724 }, { "epoch": 1.4862409138110073, "grad_norm": 7.837916374206543, "learning_rate": 1.2356658696123873e-06, "loss": 0.029692577198147774, "step": 5725 }, { "epoch": 1.4865005192107996, "grad_norm": 15.15390682220459, "learning_rate": 1.234966326807864e-06, "loss": 0.05259297788143158, "step": 5726 }, { "epoch": 1.486760124610592, "grad_norm": 11.464186668395996, "learning_rate": 1.2342670518266057e-06, "loss": 0.03440677374601364, "step": 5727 }, { "epoch": 1.4870197300103842, "grad_norm": 6.40576171875, "learning_rate": 1.2335680447922266e-06, "loss": 0.01524268090724945, "step": 5728 }, { "epoch": 1.4872793354101765, "grad_norm": 10.148011207580566, "learning_rate": 1.2328693058282945e-06, "loss": 0.11436069756746292, "step": 5729 }, { "epoch": 1.4875389408099688, "grad_norm": 7.52514123916626, "learning_rate": 1.2321708350583324e-06, "loss": 0.04289883375167847, "step": 5730 }, { "epoch": 1.4877985462097612, "grad_norm": 8.87476634979248, "learning_rate": 1.231472632605813e-06, "loss": 0.05746039003133774, "step": 5731 }, { "epoch": 1.4880581516095535, "grad_norm": 10.609723091125488, "learning_rate": 1.230774698594162e-06, "loss": 0.10234105587005615, "step": 5732 }, { "epoch": 1.4883177570093458, "grad_norm": 10.3270845413208, "learning_rate": 1.230077033146759e-06, "loss": 0.10442738234996796, "step": 5733 }, { "epoch": 1.488577362409138, "grad_norm": 8.921080589294434, "learning_rate": 1.2293796363869345e-06, "loss": 0.1698606163263321, "step": 5734 }, { "epoch": 1.4888369678089304, "grad_norm": 9.552383422851562, "learning_rate": 1.2286825084379733e-06, "loss": 0.1419951617717743, "step": 5735 }, { "epoch": 1.4890965732087227, "grad_norm": 10.65824031829834, "learning_rate": 1.227985649423111e-06, "loss": 0.13226677477359772, "step": 5736 }, { "epoch": 1.489356178608515, "grad_norm": 9.012055397033691, "learning_rate": 1.2272890594655356e-06, "loss": 0.027720604091882706, "step": 5737 }, { "epoch": 1.4896157840083073, "grad_norm": 10.851712226867676, "learning_rate": 1.2265927386883898e-06, "loss": 0.05136270076036453, "step": 5738 }, { "epoch": 1.4898753894080996, "grad_norm": 10.765798568725586, "learning_rate": 1.2258966872147664e-06, "loss": 0.10329780727624893, "step": 5739 }, { "epoch": 1.490134994807892, "grad_norm": 8.952117919921875, "learning_rate": 1.2252009051677106e-06, "loss": 0.17895397543907166, "step": 5740 }, { "epoch": 1.4903946002076842, "grad_norm": 7.711213111877441, "learning_rate": 1.2245053926702224e-06, "loss": 0.016536692157387733, "step": 5741 }, { "epoch": 1.4906542056074765, "grad_norm": 7.065972328186035, "learning_rate": 1.2238101498452507e-06, "loss": 0.15280935168266296, "step": 5742 }, { "epoch": 1.4909138110072688, "grad_norm": 7.990512847900391, "learning_rate": 1.2231151768157008e-06, "loss": 0.1571306735277176, "step": 5743 }, { "epoch": 1.4911734164070611, "grad_norm": 5.380511283874512, "learning_rate": 1.2224204737044252e-06, "loss": 0.012038303539156914, "step": 5744 }, { "epoch": 1.4914330218068537, "grad_norm": 7.599693775177002, "learning_rate": 1.221726040634233e-06, "loss": 0.04260185360908508, "step": 5745 }, { "epoch": 1.491692627206646, "grad_norm": 8.109792709350586, "learning_rate": 1.2210318777278844e-06, "loss": 0.03867543488740921, "step": 5746 }, { "epoch": 1.4919522326064383, "grad_norm": 8.629276275634766, "learning_rate": 1.2203379851080914e-06, "loss": 0.14876282215118408, "step": 5747 }, { "epoch": 1.4922118380062306, "grad_norm": 6.1686015129089355, "learning_rate": 1.219644362897518e-06, "loss": 0.016308164224028587, "step": 5748 }, { "epoch": 1.492471443406023, "grad_norm": 8.583176612854004, "learning_rate": 1.21895101121878e-06, "loss": 0.11320577561855316, "step": 5749 }, { "epoch": 1.4927310488058152, "grad_norm": 9.244345664978027, "learning_rate": 1.218257930194447e-06, "loss": 0.05010352283716202, "step": 5750 }, { "epoch": 1.4929906542056075, "grad_norm": 7.454180717468262, "learning_rate": 1.2175651199470408e-06, "loss": 0.059247568249702454, "step": 5751 }, { "epoch": 1.4932502596053998, "grad_norm": 10.94264030456543, "learning_rate": 1.2168725805990319e-06, "loss": 0.04822733625769615, "step": 5752 }, { "epoch": 1.4935098650051921, "grad_norm": 8.332820892333984, "learning_rate": 1.2161803122728476e-06, "loss": 0.018987631425261497, "step": 5753 }, { "epoch": 1.4937694704049844, "grad_norm": 9.128106117248535, "learning_rate": 1.2154883150908635e-06, "loss": 0.10998895019292831, "step": 5754 }, { "epoch": 1.4940290758047767, "grad_norm": 2.9980628490448, "learning_rate": 1.2147965891754104e-06, "loss": 0.004805648233741522, "step": 5755 }, { "epoch": 1.494288681204569, "grad_norm": 7.124837398529053, "learning_rate": 1.2141051346487692e-06, "loss": 0.03910297155380249, "step": 5756 }, { "epoch": 1.4945482866043613, "grad_norm": 10.439627647399902, "learning_rate": 1.2134139516331715e-06, "loss": 0.13987527787685394, "step": 5757 }, { "epoch": 1.4948078920041536, "grad_norm": 10.388832092285156, "learning_rate": 1.212723040250805e-06, "loss": 0.11192416399717331, "step": 5758 }, { "epoch": 1.495067497403946, "grad_norm": 24.928476333618164, "learning_rate": 1.212032400623806e-06, "loss": 0.09281487762928009, "step": 5759 }, { "epoch": 1.4953271028037383, "grad_norm": 9.918700218200684, "learning_rate": 1.2113420328742629e-06, "loss": 0.09660350531339645, "step": 5760 }, { "epoch": 1.4955867082035306, "grad_norm": 8.22436809539795, "learning_rate": 1.2106519371242188e-06, "loss": 0.011784165166318417, "step": 5761 }, { "epoch": 1.4958463136033229, "grad_norm": 7.828329563140869, "learning_rate": 1.2099621134956656e-06, "loss": 0.054784152656793594, "step": 5762 }, { "epoch": 1.4961059190031154, "grad_norm": 5.726986408233643, "learning_rate": 1.209272562110548e-06, "loss": 0.006517247762531042, "step": 5763 }, { "epoch": 1.4963655244029077, "grad_norm": 5.080677509307861, "learning_rate": 1.2085832830907642e-06, "loss": 0.023854417726397514, "step": 5764 }, { "epoch": 1.4966251298027, "grad_norm": 7.946144104003906, "learning_rate": 1.2078942765581611e-06, "loss": 0.04399146884679794, "step": 5765 }, { "epoch": 1.4968847352024923, "grad_norm": 8.047101020812988, "learning_rate": 1.2072055426345414e-06, "loss": 0.038245782256126404, "step": 5766 }, { "epoch": 1.4971443406022846, "grad_norm": 6.166354179382324, "learning_rate": 1.2065170814416564e-06, "loss": 0.030224818736314774, "step": 5767 }, { "epoch": 1.497403946002077, "grad_norm": 10.357839584350586, "learning_rate": 1.2058288931012095e-06, "loss": 0.1284853219985962, "step": 5768 }, { "epoch": 1.4976635514018692, "grad_norm": 8.207843780517578, "learning_rate": 1.205140977734858e-06, "loss": 0.21866638958454132, "step": 5769 }, { "epoch": 1.4979231568016615, "grad_norm": 5.332629203796387, "learning_rate": 1.2044533354642095e-06, "loss": 0.028272416442632675, "step": 5770 }, { "epoch": 1.4981827622014539, "grad_norm": 10.1871919631958, "learning_rate": 1.2037659664108222e-06, "loss": 0.10551749169826508, "step": 5771 }, { "epoch": 1.4984423676012462, "grad_norm": 10.882970809936523, "learning_rate": 1.2030788706962085e-06, "loss": 0.01921144127845764, "step": 5772 }, { "epoch": 1.4987019730010385, "grad_norm": 7.484201908111572, "learning_rate": 1.20239204844183e-06, "loss": 0.1659565269947052, "step": 5773 }, { "epoch": 1.4989615784008308, "grad_norm": 12.25341510772705, "learning_rate": 1.2017054997691032e-06, "loss": 0.06533786654472351, "step": 5774 }, { "epoch": 1.499221183800623, "grad_norm": 8.8429536819458, "learning_rate": 1.2010192247993915e-06, "loss": 0.059217363595962524, "step": 5775 }, { "epoch": 1.4994807892004154, "grad_norm": 7.479935646057129, "learning_rate": 1.200333223654014e-06, "loss": 0.15197119116783142, "step": 5776 }, { "epoch": 1.4997403946002077, "grad_norm": 8.37545108795166, "learning_rate": 1.19964749645424e-06, "loss": 0.01579427719116211, "step": 5777 }, { "epoch": 1.5, "grad_norm": 7.802292346954346, "learning_rate": 1.1989620433212908e-06, "loss": 0.050098225474357605, "step": 5778 }, { "epoch": 1.5002596053997923, "grad_norm": 8.70941162109375, "learning_rate": 1.1982768643763382e-06, "loss": 0.10547631978988647, "step": 5779 }, { "epoch": 1.5005192107995846, "grad_norm": 8.61688232421875, "learning_rate": 1.1975919597405054e-06, "loss": 0.113170325756073, "step": 5780 }, { "epoch": 1.500778816199377, "grad_norm": 9.811720848083496, "learning_rate": 1.1969073295348686e-06, "loss": 0.11099991202354431, "step": 5781 }, { "epoch": 1.5010384215991692, "grad_norm": 9.126008987426758, "learning_rate": 1.1962229738804565e-06, "loss": 0.06862494349479675, "step": 5782 }, { "epoch": 1.5012980269989615, "grad_norm": 6.635739326477051, "learning_rate": 1.1955388928982444e-06, "loss": 0.07086203247308731, "step": 5783 }, { "epoch": 1.5015576323987538, "grad_norm": 12.33934211730957, "learning_rate": 1.1948550867091643e-06, "loss": 0.07311221212148666, "step": 5784 }, { "epoch": 1.5018172377985461, "grad_norm": 7.007626056671143, "learning_rate": 1.1941715554340965e-06, "loss": 0.04961729422211647, "step": 5785 }, { "epoch": 1.5020768431983385, "grad_norm": 7.5299973487854, "learning_rate": 1.1934882991938737e-06, "loss": 0.059329599142074585, "step": 5786 }, { "epoch": 1.5023364485981308, "grad_norm": 8.14100456237793, "learning_rate": 1.1928053181092804e-06, "loss": 0.17115892469882965, "step": 5787 }, { "epoch": 1.502596053997923, "grad_norm": 6.300399303436279, "learning_rate": 1.1921226123010515e-06, "loss": 0.019285667687654495, "step": 5788 }, { "epoch": 1.5028556593977154, "grad_norm": 13.724431991577148, "learning_rate": 1.1914401818898745e-06, "loss": 0.11568114161491394, "step": 5789 }, { "epoch": 1.5031152647975077, "grad_norm": 6.296074867248535, "learning_rate": 1.1907580269963874e-06, "loss": 0.03467927128076553, "step": 5790 }, { "epoch": 1.5033748701973, "grad_norm": 11.475769996643066, "learning_rate": 1.1900761477411782e-06, "loss": 0.07027753442525864, "step": 5791 }, { "epoch": 1.5036344755970923, "grad_norm": 9.140806198120117, "learning_rate": 1.1893945442447892e-06, "loss": 0.08768278360366821, "step": 5792 }, { "epoch": 1.5038940809968846, "grad_norm": 8.545520782470703, "learning_rate": 1.188713216627712e-06, "loss": 0.11396737396717072, "step": 5793 }, { "epoch": 1.504153686396677, "grad_norm": 11.929117202758789, "learning_rate": 1.1880321650103884e-06, "loss": 0.12350651621818542, "step": 5794 }, { "epoch": 1.5044132917964692, "grad_norm": 9.625204086303711, "learning_rate": 1.1873513895132145e-06, "loss": 0.10281671583652496, "step": 5795 }, { "epoch": 1.5046728971962615, "grad_norm": 10.245569229125977, "learning_rate": 1.1866708902565346e-06, "loss": 0.077400341629982, "step": 5796 }, { "epoch": 1.504932502596054, "grad_norm": 9.882364273071289, "learning_rate": 1.1859906673606462e-06, "loss": 0.07903631031513214, "step": 5797 }, { "epoch": 1.5051921079958464, "grad_norm": 8.227690696716309, "learning_rate": 1.1853107209457966e-06, "loss": 0.12337833642959595, "step": 5798 }, { "epoch": 1.5054517133956387, "grad_norm": 11.837031364440918, "learning_rate": 1.1846310511321845e-06, "loss": 0.16303426027297974, "step": 5799 }, { "epoch": 1.505711318795431, "grad_norm": 5.136192798614502, "learning_rate": 1.1839516580399607e-06, "loss": 0.015141976997256279, "step": 5800 }, { "epoch": 1.5059709241952233, "grad_norm": 10.45075511932373, "learning_rate": 1.1832725417892263e-06, "loss": 0.021097034215927124, "step": 5801 }, { "epoch": 1.5062305295950156, "grad_norm": 7.678901195526123, "learning_rate": 1.1825937025000325e-06, "loss": 0.10263844579458237, "step": 5802 }, { "epoch": 1.5064901349948079, "grad_norm": 9.67095947265625, "learning_rate": 1.181915140292384e-06, "loss": 0.05388014018535614, "step": 5803 }, { "epoch": 1.5067497403946002, "grad_norm": 9.618996620178223, "learning_rate": 1.1812368552862336e-06, "loss": 0.07548820972442627, "step": 5804 }, { "epoch": 1.5070093457943925, "grad_norm": 12.646187782287598, "learning_rate": 1.1805588476014886e-06, "loss": 0.059664659202098846, "step": 5805 }, { "epoch": 1.5072689511941848, "grad_norm": 8.629432678222656, "learning_rate": 1.1798811173580024e-06, "loss": 0.09278733283281326, "step": 5806 }, { "epoch": 1.507528556593977, "grad_norm": 7.82720422744751, "learning_rate": 1.1792036646755838e-06, "loss": 0.03146244212985039, "step": 5807 }, { "epoch": 1.5077881619937694, "grad_norm": 10.883487701416016, "learning_rate": 1.1785264896739914e-06, "loss": 0.09911772608757019, "step": 5808 }, { "epoch": 1.508047767393562, "grad_norm": 9.080597877502441, "learning_rate": 1.177849592472934e-06, "loss": 0.04780552163720131, "step": 5809 }, { "epoch": 1.5083073727933543, "grad_norm": 7.1512861251831055, "learning_rate": 1.1771729731920707e-06, "loss": 0.15206846594810486, "step": 5810 }, { "epoch": 1.5085669781931466, "grad_norm": 8.966167449951172, "learning_rate": 1.1764966319510124e-06, "loss": 0.17441226541996002, "step": 5811 }, { "epoch": 1.5088265835929389, "grad_norm": 7.983825206756592, "learning_rate": 1.1758205688693219e-06, "loss": 0.17949479818344116, "step": 5812 }, { "epoch": 1.5090861889927312, "grad_norm": 9.202092170715332, "learning_rate": 1.1751447840665105e-06, "loss": 0.04275961220264435, "step": 5813 }, { "epoch": 1.5093457943925235, "grad_norm": 10.334101676940918, "learning_rate": 1.1744692776620414e-06, "loss": 0.07132946699857712, "step": 5814 }, { "epoch": 1.5096053997923158, "grad_norm": 6.197861194610596, "learning_rate": 1.17379404977533e-06, "loss": 0.03695110231637955, "step": 5815 }, { "epoch": 1.509865005192108, "grad_norm": 5.624989986419678, "learning_rate": 1.1731191005257399e-06, "loss": 0.028841635212302208, "step": 5816 }, { "epoch": 1.5101246105919004, "grad_norm": 5.5411763191223145, "learning_rate": 1.1724444300325864e-06, "loss": 0.01188135240226984, "step": 5817 }, { "epoch": 1.5103842159916927, "grad_norm": 9.516247749328613, "learning_rate": 1.1717700384151375e-06, "loss": 0.08552783727645874, "step": 5818 }, { "epoch": 1.510643821391485, "grad_norm": 8.204642295837402, "learning_rate": 1.1710959257926084e-06, "loss": 0.17577603459358215, "step": 5819 }, { "epoch": 1.5109034267912773, "grad_norm": 7.644372940063477, "learning_rate": 1.1704220922841678e-06, "loss": 0.044053107500076294, "step": 5820 }, { "epoch": 1.5111630321910696, "grad_norm": 8.349360466003418, "learning_rate": 1.169748538008934e-06, "loss": 0.11179672181606293, "step": 5821 }, { "epoch": 1.511422637590862, "grad_norm": 8.159433364868164, "learning_rate": 1.1690752630859748e-06, "loss": 0.05161948502063751, "step": 5822 }, { "epoch": 1.5116822429906542, "grad_norm": 8.27098274230957, "learning_rate": 1.1684022676343118e-06, "loss": 0.09017281979322433, "step": 5823 }, { "epoch": 1.5119418483904465, "grad_norm": 9.059157371520996, "learning_rate": 1.1677295517729138e-06, "loss": 0.0766349732875824, "step": 5824 }, { "epoch": 1.5122014537902388, "grad_norm": 6.761657238006592, "learning_rate": 1.1670571156207013e-06, "loss": 0.03915657848119736, "step": 5825 }, { "epoch": 1.5124610591900312, "grad_norm": 10.686118125915527, "learning_rate": 1.1663849592965466e-06, "loss": 0.07127004861831665, "step": 5826 }, { "epoch": 1.5127206645898235, "grad_norm": 8.242500305175781, "learning_rate": 1.1657130829192708e-06, "loss": 0.09905347228050232, "step": 5827 }, { "epoch": 1.5129802699896158, "grad_norm": 10.641853332519531, "learning_rate": 1.1650414866076472e-06, "loss": 0.11169019341468811, "step": 5828 }, { "epoch": 1.513239875389408, "grad_norm": 11.245284080505371, "learning_rate": 1.1643701704803977e-06, "loss": 0.07904261350631714, "step": 5829 }, { "epoch": 1.5134994807892004, "grad_norm": 11.905596733093262, "learning_rate": 1.1636991346561956e-06, "loss": 0.06020492687821388, "step": 5830 }, { "epoch": 1.5137590861889927, "grad_norm": 9.401069641113281, "learning_rate": 1.1630283792536657e-06, "loss": 0.043653909116983414, "step": 5831 }, { "epoch": 1.514018691588785, "grad_norm": 9.908562660217285, "learning_rate": 1.1623579043913814e-06, "loss": 0.04216467961668968, "step": 5832 }, { "epoch": 1.5142782969885773, "grad_norm": 9.436690330505371, "learning_rate": 1.1616877101878665e-06, "loss": 0.06488692760467529, "step": 5833 }, { "epoch": 1.5145379023883696, "grad_norm": 8.734103202819824, "learning_rate": 1.161017796761598e-06, "loss": 0.12070488184690475, "step": 5834 }, { "epoch": 1.514797507788162, "grad_norm": 9.184377670288086, "learning_rate": 1.1603481642309992e-06, "loss": 0.044374655932188034, "step": 5835 }, { "epoch": 1.5150571131879542, "grad_norm": 9.707904815673828, "learning_rate": 1.1596788127144485e-06, "loss": 0.09054949134588242, "step": 5836 }, { "epoch": 1.5153167185877465, "grad_norm": 10.317488670349121, "learning_rate": 1.1590097423302683e-06, "loss": 0.034190427511930466, "step": 5837 }, { "epoch": 1.5155763239875388, "grad_norm": 7.959134578704834, "learning_rate": 1.1583409531967372e-06, "loss": 0.1408415287733078, "step": 5838 }, { "epoch": 1.5158359293873311, "grad_norm": 13.8001070022583, "learning_rate": 1.1576724454320828e-06, "loss": 0.04946261644363403, "step": 5839 }, { "epoch": 1.5160955347871234, "grad_norm": 7.637941360473633, "learning_rate": 1.1570042191544787e-06, "loss": 0.18978086113929749, "step": 5840 }, { "epoch": 1.5163551401869158, "grad_norm": 13.039626121520996, "learning_rate": 1.156336274482055e-06, "loss": 0.03185822069644928, "step": 5841 }, { "epoch": 1.516614745586708, "grad_norm": 6.207785129547119, "learning_rate": 1.1556686115328872e-06, "loss": 0.022139426320791245, "step": 5842 }, { "epoch": 1.5168743509865004, "grad_norm": 5.655002117156982, "learning_rate": 1.1550012304250043e-06, "loss": 0.01586577296257019, "step": 5843 }, { "epoch": 1.5171339563862927, "grad_norm": 5.290867805480957, "learning_rate": 1.154334131276383e-06, "loss": 0.028855830430984497, "step": 5844 }, { "epoch": 1.5173935617860852, "grad_norm": 9.830732345581055, "learning_rate": 1.1536673142049507e-06, "loss": 0.056870438158512115, "step": 5845 }, { "epoch": 1.5176531671858775, "grad_norm": 7.955554962158203, "learning_rate": 1.153000779328587e-06, "loss": 0.07728267461061478, "step": 5846 }, { "epoch": 1.5179127725856698, "grad_norm": 4.224413871765137, "learning_rate": 1.1523345267651188e-06, "loss": 0.026266280561685562, "step": 5847 }, { "epoch": 1.5181723779854621, "grad_norm": 8.33614444732666, "learning_rate": 1.1516685566323243e-06, "loss": 0.0645027607679367, "step": 5848 }, { "epoch": 1.5184319833852544, "grad_norm": 7.7362189292907715, "learning_rate": 1.1510028690479323e-06, "loss": 0.05565435439348221, "step": 5849 }, { "epoch": 1.5186915887850467, "grad_norm": 7.8294148445129395, "learning_rate": 1.1503374641296204e-06, "loss": 0.05024033784866333, "step": 5850 }, { "epoch": 1.518951194184839, "grad_norm": 8.292490005493164, "learning_rate": 1.1496723419950178e-06, "loss": 0.15578410029411316, "step": 5851 }, { "epoch": 1.5192107995846313, "grad_norm": 7.944540500640869, "learning_rate": 1.149007502761703e-06, "loss": 0.09614276885986328, "step": 5852 }, { "epoch": 1.5194704049844237, "grad_norm": 9.75826358795166, "learning_rate": 1.1483429465472026e-06, "loss": 0.12138377875089645, "step": 5853 }, { "epoch": 1.519730010384216, "grad_norm": 7.627353668212891, "learning_rate": 1.1476786734689973e-06, "loss": 0.03141598403453827, "step": 5854 }, { "epoch": 1.5199896157840083, "grad_norm": 9.124534606933594, "learning_rate": 1.1470146836445141e-06, "loss": 0.10105372965335846, "step": 5855 }, { "epoch": 1.5202492211838006, "grad_norm": 7.269939422607422, "learning_rate": 1.1463509771911305e-06, "loss": 0.2275669276714325, "step": 5856 }, { "epoch": 1.520508826583593, "grad_norm": 11.056641578674316, "learning_rate": 1.1456875542261765e-06, "loss": 0.106590136885643, "step": 5857 }, { "epoch": 1.5207684319833854, "grad_norm": 9.000641822814941, "learning_rate": 1.145024414866928e-06, "loss": 0.09357558190822601, "step": 5858 }, { "epoch": 1.5210280373831777, "grad_norm": 7.587728977203369, "learning_rate": 1.1443615592306147e-06, "loss": 0.028333857655525208, "step": 5859 }, { "epoch": 1.52128764278297, "grad_norm": 7.091004371643066, "learning_rate": 1.1436989874344135e-06, "loss": 0.036933690309524536, "step": 5860 }, { "epoch": 1.5215472481827623, "grad_norm": 6.602540969848633, "learning_rate": 1.143036699595451e-06, "loss": 0.01759195141494274, "step": 5861 }, { "epoch": 1.5218068535825546, "grad_norm": 7.490098476409912, "learning_rate": 1.1423746958308066e-06, "loss": 0.12545208632946014, "step": 5862 }, { "epoch": 1.522066458982347, "grad_norm": 7.781574249267578, "learning_rate": 1.1417129762575057e-06, "loss": 0.04420243576169014, "step": 5863 }, { "epoch": 1.5223260643821392, "grad_norm": 8.65044116973877, "learning_rate": 1.1410515409925252e-06, "loss": 0.13827933371067047, "step": 5864 }, { "epoch": 1.5225856697819315, "grad_norm": 9.422290802001953, "learning_rate": 1.1403903901527929e-06, "loss": 0.10827584564685822, "step": 5865 }, { "epoch": 1.5228452751817239, "grad_norm": 8.086088180541992, "learning_rate": 1.1397295238551847e-06, "loss": 0.14702507853507996, "step": 5866 }, { "epoch": 1.5231048805815162, "grad_norm": 5.762803077697754, "learning_rate": 1.1390689422165262e-06, "loss": 0.02816094271838665, "step": 5867 }, { "epoch": 1.5233644859813085, "grad_norm": 7.629810810089111, "learning_rate": 1.1384086453535925e-06, "loss": 0.10389938950538635, "step": 5868 }, { "epoch": 1.5236240913811008, "grad_norm": 5.691707134246826, "learning_rate": 1.1377486333831099e-06, "loss": 0.03459566831588745, "step": 5869 }, { "epoch": 1.523883696780893, "grad_norm": 10.254682540893555, "learning_rate": 1.1370889064217545e-06, "loss": 0.03802446648478508, "step": 5870 }, { "epoch": 1.5241433021806854, "grad_norm": 7.668889045715332, "learning_rate": 1.1364294645861483e-06, "loss": 0.05673383176326752, "step": 5871 }, { "epoch": 1.5244029075804777, "grad_norm": 5.1334123611450195, "learning_rate": 1.1357703079928676e-06, "loss": 0.023950152099132538, "step": 5872 }, { "epoch": 1.52466251298027, "grad_norm": 9.09573745727539, "learning_rate": 1.1351114367584347e-06, "loss": 0.13859757781028748, "step": 5873 }, { "epoch": 1.5249221183800623, "grad_norm": 8.453714370727539, "learning_rate": 1.1344528509993246e-06, "loss": 0.048240549862384796, "step": 5874 }, { "epoch": 1.5251817237798546, "grad_norm": 11.361966133117676, "learning_rate": 1.1337945508319593e-06, "loss": 0.10233083367347717, "step": 5875 }, { "epoch": 1.525441329179647, "grad_norm": 4.893131256103516, "learning_rate": 1.1331365363727106e-06, "loss": 0.01907382719218731, "step": 5876 }, { "epoch": 1.5257009345794392, "grad_norm": 6.378259181976318, "learning_rate": 1.1324788077379015e-06, "loss": 0.01025522779673338, "step": 5877 }, { "epoch": 1.5259605399792315, "grad_norm": 10.84532642364502, "learning_rate": 1.1318213650438028e-06, "loss": 0.07020480930805206, "step": 5878 }, { "epoch": 1.5262201453790238, "grad_norm": 9.743852615356445, "learning_rate": 1.131164208406635e-06, "loss": 0.07965472340583801, "step": 5879 }, { "epoch": 1.5264797507788161, "grad_norm": 7.1938581466674805, "learning_rate": 1.130507337942569e-06, "loss": 0.05270298197865486, "step": 5880 }, { "epoch": 1.5267393561786085, "grad_norm": 8.858832359313965, "learning_rate": 1.129850753767724e-06, "loss": 0.06956121325492859, "step": 5881 }, { "epoch": 1.5269989615784008, "grad_norm": 7.787688255310059, "learning_rate": 1.1291944559981697e-06, "loss": 0.04321955516934395, "step": 5882 }, { "epoch": 1.527258566978193, "grad_norm": 7.8947343826293945, "learning_rate": 1.128538444749924e-06, "loss": 0.024820378050208092, "step": 5883 }, { "epoch": 1.5275181723779854, "grad_norm": 12.805058479309082, "learning_rate": 1.1278827201389539e-06, "loss": 0.06654703617095947, "step": 5884 }, { "epoch": 1.5277777777777777, "grad_norm": 7.980788230895996, "learning_rate": 1.1272272822811784e-06, "loss": 0.027185633778572083, "step": 5885 }, { "epoch": 1.52803738317757, "grad_norm": 7.796864986419678, "learning_rate": 1.1265721312924624e-06, "loss": 0.04422502964735031, "step": 5886 }, { "epoch": 1.5282969885773623, "grad_norm": 6.903666019439697, "learning_rate": 1.1259172672886216e-06, "loss": 0.09065064787864685, "step": 5887 }, { "epoch": 1.5285565939771546, "grad_norm": 4.919293403625488, "learning_rate": 1.1252626903854218e-06, "loss": 0.034952886402606964, "step": 5888 }, { "epoch": 1.528816199376947, "grad_norm": 8.115833282470703, "learning_rate": 1.1246084006985764e-06, "loss": 0.1254139244556427, "step": 5889 }, { "epoch": 1.5290758047767392, "grad_norm": 8.667130470275879, "learning_rate": 1.1239543983437498e-06, "loss": 0.09702448546886444, "step": 5890 }, { "epoch": 1.5293354101765315, "grad_norm": 8.061119079589844, "learning_rate": 1.1233006834365542e-06, "loss": 0.1360209584236145, "step": 5891 }, { "epoch": 1.5295950155763238, "grad_norm": 7.802938461303711, "learning_rate": 1.1226472560925502e-06, "loss": 0.20970231294631958, "step": 5892 }, { "epoch": 1.5298546209761164, "grad_norm": 7.2730865478515625, "learning_rate": 1.1219941164272515e-06, "loss": 0.02750738337635994, "step": 5893 }, { "epoch": 1.5301142263759087, "grad_norm": 6.659880638122559, "learning_rate": 1.1213412645561154e-06, "loss": 0.01514490507543087, "step": 5894 }, { "epoch": 1.530373831775701, "grad_norm": 8.508879661560059, "learning_rate": 1.1206887005945521e-06, "loss": 0.057580992579460144, "step": 5895 }, { "epoch": 1.5306334371754933, "grad_norm": 9.47340202331543, "learning_rate": 1.1200364246579213e-06, "loss": 0.05235327035188675, "step": 5896 }, { "epoch": 1.5308930425752856, "grad_norm": 8.217972755432129, "learning_rate": 1.119384436861529e-06, "loss": 0.06893043965101242, "step": 5897 }, { "epoch": 1.5311526479750779, "grad_norm": 5.83732271194458, "learning_rate": 1.1187327373206323e-06, "loss": 0.013733320869505405, "step": 5898 }, { "epoch": 1.5314122533748702, "grad_norm": 7.728915691375732, "learning_rate": 1.118081326150436e-06, "loss": 0.09374114871025085, "step": 5899 }, { "epoch": 1.5316718587746625, "grad_norm": 9.125643730163574, "learning_rate": 1.117430203466095e-06, "loss": 0.04840253293514252, "step": 5900 }, { "epoch": 1.5319314641744548, "grad_norm": 11.77644157409668, "learning_rate": 1.1167793693827145e-06, "loss": 0.07459475100040436, "step": 5901 }, { "epoch": 1.532191069574247, "grad_norm": 8.072978019714355, "learning_rate": 1.1161288240153446e-06, "loss": 0.04817308485507965, "step": 5902 }, { "epoch": 1.5324506749740394, "grad_norm": 8.928130149841309, "learning_rate": 1.1154785674789883e-06, "loss": 0.05942017212510109, "step": 5903 }, { "epoch": 1.5327102803738317, "grad_norm": 7.087179183959961, "learning_rate": 1.1148285998885956e-06, "loss": 0.012676045298576355, "step": 5904 }, { "epoch": 1.5329698857736243, "grad_norm": 7.896318435668945, "learning_rate": 1.114178921359066e-06, "loss": 0.059369634836912155, "step": 5905 }, { "epoch": 1.5332294911734166, "grad_norm": 8.741944313049316, "learning_rate": 1.113529532005248e-06, "loss": 0.09048023819923401, "step": 5906 }, { "epoch": 1.5334890965732089, "grad_norm": 8.992340087890625, "learning_rate": 1.112880431941938e-06, "loss": 0.1014999970793724, "step": 5907 }, { "epoch": 1.5337487019730012, "grad_norm": 8.010420799255371, "learning_rate": 1.112231621283883e-06, "loss": 0.0788959339261055, "step": 5908 }, { "epoch": 1.5340083073727935, "grad_norm": 7.9431233406066895, "learning_rate": 1.1115831001457775e-06, "loss": 0.09708497673273087, "step": 5909 }, { "epoch": 1.5342679127725858, "grad_norm": 10.434443473815918, "learning_rate": 1.1109348686422643e-06, "loss": 0.055450934916734695, "step": 5910 }, { "epoch": 1.534527518172378, "grad_norm": 10.463534355163574, "learning_rate": 1.1102869268879379e-06, "loss": 0.04681078717112541, "step": 5911 }, { "epoch": 1.5347871235721704, "grad_norm": 7.605714321136475, "learning_rate": 1.1096392749973373e-06, "loss": 0.13834863901138306, "step": 5912 }, { "epoch": 1.5350467289719627, "grad_norm": 9.032453536987305, "learning_rate": 1.1089919130849543e-06, "loss": 0.029766235500574112, "step": 5913 }, { "epoch": 1.535306334371755, "grad_norm": 7.705545902252197, "learning_rate": 1.108344841265227e-06, "loss": 0.02428252063691616, "step": 5914 }, { "epoch": 1.5355659397715473, "grad_norm": 4.619174957275391, "learning_rate": 1.1076980596525422e-06, "loss": 0.011296030133962631, "step": 5915 }, { "epoch": 1.5358255451713396, "grad_norm": 3.5738818645477295, "learning_rate": 1.1070515683612373e-06, "loss": 0.005128685850650072, "step": 5916 }, { "epoch": 1.536085150571132, "grad_norm": 12.471135139465332, "learning_rate": 1.1064053675055967e-06, "loss": 0.020771916955709457, "step": 5917 }, { "epoch": 1.5363447559709242, "grad_norm": 11.35791015625, "learning_rate": 1.1057594571998528e-06, "loss": 0.05562891438603401, "step": 5918 }, { "epoch": 1.5366043613707165, "grad_norm": 9.441903114318848, "learning_rate": 1.10511383755819e-06, "loss": 0.036404818296432495, "step": 5919 }, { "epoch": 1.5368639667705088, "grad_norm": 7.455719470977783, "learning_rate": 1.1044685086947376e-06, "loss": 0.1198417991399765, "step": 5920 }, { "epoch": 1.5371235721703012, "grad_norm": 7.605189800262451, "learning_rate": 1.1038234707235742e-06, "loss": 0.050978198647499084, "step": 5921 }, { "epoch": 1.5373831775700935, "grad_norm": 11.67216682434082, "learning_rate": 1.1031787237587296e-06, "loss": 0.0867185965180397, "step": 5922 }, { "epoch": 1.5376427829698858, "grad_norm": 7.337251663208008, "learning_rate": 1.102534267914179e-06, "loss": 0.02527565136551857, "step": 5923 }, { "epoch": 1.537902388369678, "grad_norm": 12.830378532409668, "learning_rate": 1.101890103303849e-06, "loss": 0.08995413035154343, "step": 5924 }, { "epoch": 1.5381619937694704, "grad_norm": 5.926882266998291, "learning_rate": 1.1012462300416104e-06, "loss": 0.011190211400389671, "step": 5925 }, { "epoch": 1.5384215991692627, "grad_norm": 12.578588485717773, "learning_rate": 1.100602648241287e-06, "loss": 0.03473443165421486, "step": 5926 }, { "epoch": 1.538681204569055, "grad_norm": 11.432430267333984, "learning_rate": 1.0999593580166501e-06, "loss": 0.09372437000274658, "step": 5927 }, { "epoch": 1.5389408099688473, "grad_norm": 7.561873912811279, "learning_rate": 1.099316359481418e-06, "loss": 0.028631016612052917, "step": 5928 }, { "epoch": 1.5392004153686396, "grad_norm": 10.343709945678711, "learning_rate": 1.0986736527492573e-06, "loss": 0.17201462388038635, "step": 5929 }, { "epoch": 1.539460020768432, "grad_norm": 10.775518417358398, "learning_rate": 1.0980312379337844e-06, "loss": 0.11275715380907059, "step": 5930 }, { "epoch": 1.5397196261682242, "grad_norm": 8.459372520446777, "learning_rate": 1.097389115148563e-06, "loss": 0.03756383806467056, "step": 5931 }, { "epoch": 1.5399792315680165, "grad_norm": 12.799583435058594, "learning_rate": 1.0967472845071078e-06, "loss": 0.050829485058784485, "step": 5932 }, { "epoch": 1.5402388369678088, "grad_norm": 9.169228553771973, "learning_rate": 1.0961057461228768e-06, "loss": 0.06707822531461716, "step": 5933 }, { "epoch": 1.5404984423676011, "grad_norm": 6.8319783210754395, "learning_rate": 1.0954645001092818e-06, "loss": 0.022552702575922012, "step": 5934 }, { "epoch": 1.5407580477673934, "grad_norm": 8.542713165283203, "learning_rate": 1.0948235465796784e-06, "loss": 0.0874059870839119, "step": 5935 }, { "epoch": 1.5410176531671858, "grad_norm": 10.112587928771973, "learning_rate": 1.0941828856473738e-06, "loss": 0.04207956790924072, "step": 5936 }, { "epoch": 1.541277258566978, "grad_norm": 7.628046035766602, "learning_rate": 1.0935425174256224e-06, "loss": 0.054257459938526154, "step": 5937 }, { "epoch": 1.5415368639667704, "grad_norm": 8.373537063598633, "learning_rate": 1.092902442027625e-06, "loss": 0.028006400913000107, "step": 5938 }, { "epoch": 1.5417964693665627, "grad_norm": 7.9853925704956055, "learning_rate": 1.0922626595665343e-06, "loss": 0.03925977647304535, "step": 5939 }, { "epoch": 1.542056074766355, "grad_norm": 8.379556655883789, "learning_rate": 1.091623170155448e-06, "loss": 0.08936459571123123, "step": 5940 }, { "epoch": 1.5423156801661475, "grad_norm": 8.569311141967773, "learning_rate": 1.0909839739074126e-06, "loss": 0.03328118845820427, "step": 5941 }, { "epoch": 1.5425752855659398, "grad_norm": 5.662975788116455, "learning_rate": 1.0903450709354253e-06, "loss": 0.027532806620001793, "step": 5942 }, { "epoch": 1.5428348909657321, "grad_norm": 6.005722522735596, "learning_rate": 1.0897064613524273e-06, "loss": 0.021045878529548645, "step": 5943 }, { "epoch": 1.5430944963655244, "grad_norm": 5.088267803192139, "learning_rate": 1.0890681452713123e-06, "loss": 0.014563779346644878, "step": 5944 }, { "epoch": 1.5433541017653167, "grad_norm": 8.343155860900879, "learning_rate": 1.0884301228049187e-06, "loss": 0.07366197556257248, "step": 5945 }, { "epoch": 1.543613707165109, "grad_norm": 7.819498538970947, "learning_rate": 1.0877923940660338e-06, "loss": 0.0366583988070488, "step": 5946 }, { "epoch": 1.5438733125649013, "grad_norm": 8.986598014831543, "learning_rate": 1.087154959167395e-06, "loss": 0.06624975800514221, "step": 5947 }, { "epoch": 1.5441329179646937, "grad_norm": 5.624297618865967, "learning_rate": 1.0865178182216852e-06, "loss": 0.016504865139722824, "step": 5948 }, { "epoch": 1.544392523364486, "grad_norm": 7.627315044403076, "learning_rate": 1.0858809713415355e-06, "loss": 0.01891571655869484, "step": 5949 }, { "epoch": 1.5446521287642783, "grad_norm": 5.5259904861450195, "learning_rate": 1.0852444186395279e-06, "loss": 0.02881617471575737, "step": 5950 }, { "epoch": 1.5449117341640706, "grad_norm": 9.266963005065918, "learning_rate": 1.0846081602281889e-06, "loss": 0.07474929094314575, "step": 5951 }, { "epoch": 1.5451713395638629, "grad_norm": 7.825357913970947, "learning_rate": 1.0839721962199942e-06, "loss": 0.03533705323934555, "step": 5952 }, { "epoch": 1.5454309449636554, "grad_norm": 8.012664794921875, "learning_rate": 1.083336526727369e-06, "loss": 0.1331843137741089, "step": 5953 }, { "epoch": 1.5456905503634477, "grad_norm": 10.332134246826172, "learning_rate": 1.0827011518626836e-06, "loss": 0.054601699113845825, "step": 5954 }, { "epoch": 1.54595015576324, "grad_norm": 7.802980422973633, "learning_rate": 1.0820660717382598e-06, "loss": 0.029086189344525337, "step": 5955 }, { "epoch": 1.5462097611630323, "grad_norm": 10.192930221557617, "learning_rate": 1.0814312864663625e-06, "loss": 0.0534515380859375, "step": 5956 }, { "epoch": 1.5464693665628246, "grad_norm": 9.69723892211914, "learning_rate": 1.0807967961592086e-06, "loss": 0.02351166494190693, "step": 5957 }, { "epoch": 1.546728971962617, "grad_norm": 10.250658988952637, "learning_rate": 1.0801626009289621e-06, "loss": 0.1787284016609192, "step": 5958 }, { "epoch": 1.5469885773624092, "grad_norm": 7.68472146987915, "learning_rate": 1.0795287008877334e-06, "loss": 0.02713199146091938, "step": 5959 }, { "epoch": 1.5472481827622016, "grad_norm": 12.910090446472168, "learning_rate": 1.0788950961475819e-06, "loss": 0.11340336501598358, "step": 5960 }, { "epoch": 1.5475077881619939, "grad_norm": 7.589601516723633, "learning_rate": 1.0782617868205138e-06, "loss": 0.00929606519639492, "step": 5961 }, { "epoch": 1.5477673935617862, "grad_norm": 10.378885269165039, "learning_rate": 1.0776287730184837e-06, "loss": 0.1561138927936554, "step": 5962 }, { "epoch": 1.5480269989615785, "grad_norm": 7.547937870025635, "learning_rate": 1.0769960548533955e-06, "loss": 0.012487681582570076, "step": 5963 }, { "epoch": 1.5482866043613708, "grad_norm": 11.323131561279297, "learning_rate": 1.076363632437097e-06, "loss": 0.1228455901145935, "step": 5964 }, { "epoch": 1.548546209761163, "grad_norm": 7.985038757324219, "learning_rate": 1.0757315058813877e-06, "loss": 0.053999222815036774, "step": 5965 }, { "epoch": 1.5488058151609554, "grad_norm": 12.064689636230469, "learning_rate": 1.0750996752980117e-06, "loss": 0.12322713434696198, "step": 5966 }, { "epoch": 1.5490654205607477, "grad_norm": 7.051385879516602, "learning_rate": 1.0744681407986636e-06, "loss": 0.23608562350273132, "step": 5967 }, { "epoch": 1.54932502596054, "grad_norm": 8.729743957519531, "learning_rate": 1.073836902494984e-06, "loss": 0.11085677891969681, "step": 5968 }, { "epoch": 1.5495846313603323, "grad_norm": 8.704968452453613, "learning_rate": 1.0732059604985602e-06, "loss": 0.12278259545564651, "step": 5969 }, { "epoch": 1.5498442367601246, "grad_norm": 7.904305458068848, "learning_rate": 1.0725753149209295e-06, "loss": 0.05817509442567825, "step": 5970 }, { "epoch": 1.550103842159917, "grad_norm": 8.694740295410156, "learning_rate": 1.0719449658735754e-06, "loss": 0.023976048454642296, "step": 5971 }, { "epoch": 1.5503634475597092, "grad_norm": 18.289043426513672, "learning_rate": 1.0713149134679281e-06, "loss": 0.060090214014053345, "step": 5972 }, { "epoch": 1.5506230529595015, "grad_norm": 5.942843437194824, "learning_rate": 1.0706851578153681e-06, "loss": 0.03537706658244133, "step": 5973 }, { "epoch": 1.5508826583592938, "grad_norm": 8.322661399841309, "learning_rate": 1.0700556990272203e-06, "loss": 0.12496218830347061, "step": 5974 }, { "epoch": 1.5511422637590861, "grad_norm": 6.657193183898926, "learning_rate": 1.06942653721476e-06, "loss": 0.02325068600475788, "step": 5975 }, { "epoch": 1.5514018691588785, "grad_norm": 7.652291774749756, "learning_rate": 1.0687976724892078e-06, "loss": 0.10565607249736786, "step": 5976 }, { "epoch": 1.5516614745586708, "grad_norm": 8.174856185913086, "learning_rate": 1.0681691049617322e-06, "loss": 0.04905067756772041, "step": 5977 }, { "epoch": 1.551921079958463, "grad_norm": 8.821608543395996, "learning_rate": 1.0675408347434504e-06, "loss": 0.07513866573572159, "step": 5978 }, { "epoch": 1.5521806853582554, "grad_norm": 6.222255229949951, "learning_rate": 1.066912861945426e-06, "loss": 0.018293600529432297, "step": 5979 }, { "epoch": 1.5524402907580477, "grad_norm": 12.06058406829834, "learning_rate": 1.0662851866786694e-06, "loss": 0.06636215001344681, "step": 5980 }, { "epoch": 1.55269989615784, "grad_norm": 9.862005233764648, "learning_rate": 1.0656578090541402e-06, "loss": 0.09295117855072021, "step": 5981 }, { "epoch": 1.5529595015576323, "grad_norm": 7.58448600769043, "learning_rate": 1.0650307291827443e-06, "loss": 0.14930838346481323, "step": 5982 }, { "epoch": 1.5532191069574246, "grad_norm": 9.555429458618164, "learning_rate": 1.0644039471753343e-06, "loss": 0.09617993980646133, "step": 5983 }, { "epoch": 1.553478712357217, "grad_norm": 8.6415433883667, "learning_rate": 1.0637774631427117e-06, "loss": 0.01313193328678608, "step": 5984 }, { "epoch": 1.5537383177570092, "grad_norm": 3.904897451400757, "learning_rate": 1.0631512771956238e-06, "loss": 0.006648501381278038, "step": 5985 }, { "epoch": 1.5539979231568015, "grad_norm": 10.197158813476562, "learning_rate": 1.0625253894447676e-06, "loss": 0.0951983705163002, "step": 5986 }, { "epoch": 1.5542575285565938, "grad_norm": 8.987442970275879, "learning_rate": 1.0618998000007832e-06, "loss": 0.022194813936948776, "step": 5987 }, { "epoch": 1.5545171339563861, "grad_norm": 4.833334445953369, "learning_rate": 1.061274508974262e-06, "loss": 0.009047091007232666, "step": 5988 }, { "epoch": 1.5547767393561787, "grad_norm": 10.517287254333496, "learning_rate": 1.060649516475741e-06, "loss": 0.11835397034883499, "step": 5989 }, { "epoch": 1.555036344755971, "grad_norm": 4.848659038543701, "learning_rate": 1.0600248226157051e-06, "loss": 0.012370058335363865, "step": 5990 }, { "epoch": 1.5552959501557633, "grad_norm": 7.705470085144043, "learning_rate": 1.0594004275045849e-06, "loss": 0.021491186693310738, "step": 5991 }, { "epoch": 1.5555555555555556, "grad_norm": 7.9341840744018555, "learning_rate": 1.058776331252759e-06, "loss": 0.02852461114525795, "step": 5992 }, { "epoch": 1.5558151609553479, "grad_norm": 9.601608276367188, "learning_rate": 1.058152533970554e-06, "loss": 0.026814548298716545, "step": 5993 }, { "epoch": 1.5560747663551402, "grad_norm": 8.922667503356934, "learning_rate": 1.0575290357682439e-06, "loss": 0.08205500990152359, "step": 5994 }, { "epoch": 1.5563343717549325, "grad_norm": 7.173849582672119, "learning_rate": 1.0569058367560468e-06, "loss": 0.030129875987768173, "step": 5995 }, { "epoch": 1.5565939771547248, "grad_norm": 8.085023880004883, "learning_rate": 1.0562829370441304e-06, "loss": 0.06542669981718063, "step": 5996 }, { "epoch": 1.5568535825545171, "grad_norm": 7.3755412101745605, "learning_rate": 1.055660336742611e-06, "loss": 0.028363093733787537, "step": 5997 }, { "epoch": 1.5571131879543094, "grad_norm": 8.596912384033203, "learning_rate": 1.0550380359615487e-06, "loss": 0.14994260668754578, "step": 5998 }, { "epoch": 1.5573727933541017, "grad_norm": 3.1947550773620605, "learning_rate": 1.054416034810952e-06, "loss": 0.009325413033366203, "step": 5999 }, { "epoch": 1.557632398753894, "grad_norm": 6.963706016540527, "learning_rate": 1.0537943334007762e-06, "loss": 0.04157648980617523, "step": 6000 }, { "epoch": 1.5578920041536866, "grad_norm": 3.177189350128174, "learning_rate": 1.0531729318409242e-06, "loss": 0.003834634320810437, "step": 6001 }, { "epoch": 1.5581516095534789, "grad_norm": 10.088044166564941, "learning_rate": 1.052551830241247e-06, "loss": 0.12620852887630463, "step": 6002 }, { "epoch": 1.5584112149532712, "grad_norm": 5.816816329956055, "learning_rate": 1.0519310287115383e-06, "loss": 0.029491767287254333, "step": 6003 }, { "epoch": 1.5586708203530635, "grad_norm": 10.70497989654541, "learning_rate": 1.051310527361544e-06, "loss": 0.061945825815200806, "step": 6004 }, { "epoch": 1.5589304257528558, "grad_norm": 8.421204566955566, "learning_rate": 1.0506903263009536e-06, "loss": 0.039792533963918686, "step": 6005 }, { "epoch": 1.559190031152648, "grad_norm": 10.249558448791504, "learning_rate": 1.0500704256394037e-06, "loss": 0.11274218559265137, "step": 6006 }, { "epoch": 1.5594496365524404, "grad_norm": 6.7820024490356445, "learning_rate": 1.04945082548648e-06, "loss": 0.026818975806236267, "step": 6007 }, { "epoch": 1.5597092419522327, "grad_norm": 7.685001850128174, "learning_rate": 1.0488315259517124e-06, "loss": 0.15076890587806702, "step": 6008 }, { "epoch": 1.559968847352025, "grad_norm": 4.263107776641846, "learning_rate": 1.0482125271445798e-06, "loss": 0.01839839294552803, "step": 6009 }, { "epoch": 1.5602284527518173, "grad_norm": 3.67643141746521, "learning_rate": 1.0475938291745069e-06, "loss": 0.012418217957019806, "step": 6010 }, { "epoch": 1.5604880581516096, "grad_norm": 9.097334861755371, "learning_rate": 1.0469754321508641e-06, "loss": 0.09132860600948334, "step": 6011 }, { "epoch": 1.560747663551402, "grad_norm": 9.055914878845215, "learning_rate": 1.046357336182972e-06, "loss": 0.21876084804534912, "step": 6012 }, { "epoch": 1.5610072689511942, "grad_norm": 11.836400032043457, "learning_rate": 1.045739541380094e-06, "loss": 0.050880081951618195, "step": 6013 }, { "epoch": 1.5612668743509865, "grad_norm": 7.7440595626831055, "learning_rate": 1.0451220478514424e-06, "loss": 0.07103997468948364, "step": 6014 }, { "epoch": 1.5615264797507789, "grad_norm": 11.047102928161621, "learning_rate": 1.044504855706177e-06, "loss": 0.07360802590847015, "step": 6015 }, { "epoch": 1.5617860851505712, "grad_norm": 11.345026016235352, "learning_rate": 1.0438879650534016e-06, "loss": 0.02834843099117279, "step": 6016 }, { "epoch": 1.5620456905503635, "grad_norm": 7.854557991027832, "learning_rate": 1.0432713760021696e-06, "loss": 0.028221815824508667, "step": 6017 }, { "epoch": 1.5623052959501558, "grad_norm": 9.885053634643555, "learning_rate": 1.0426550886614797e-06, "loss": 0.057519447058439255, "step": 6018 }, { "epoch": 1.562564901349948, "grad_norm": 9.825019836425781, "learning_rate": 1.0420391031402763e-06, "loss": 0.04182117432355881, "step": 6019 }, { "epoch": 1.5628245067497404, "grad_norm": 10.11793041229248, "learning_rate": 1.041423419547453e-06, "loss": 0.11496046185493469, "step": 6020 }, { "epoch": 1.5630841121495327, "grad_norm": 9.023759841918945, "learning_rate": 1.0408080379918481e-06, "loss": 0.08055828511714935, "step": 6021 }, { "epoch": 1.563343717549325, "grad_norm": 13.863476753234863, "learning_rate": 1.0401929585822459e-06, "loss": 0.08706381171941757, "step": 6022 }, { "epoch": 1.5636033229491173, "grad_norm": 8.948551177978516, "learning_rate": 1.0395781814273801e-06, "loss": 0.04944559931755066, "step": 6023 }, { "epoch": 1.5638629283489096, "grad_norm": 8.061125755310059, "learning_rate": 1.0389637066359278e-06, "loss": 0.04117746278643608, "step": 6024 }, { "epoch": 1.564122533748702, "grad_norm": 7.026515960693359, "learning_rate": 1.0383495343165154e-06, "loss": 0.03323396295309067, "step": 6025 }, { "epoch": 1.5643821391484942, "grad_norm": 12.790764808654785, "learning_rate": 1.037735664577713e-06, "loss": 0.033725570887327194, "step": 6026 }, { "epoch": 1.5646417445482865, "grad_norm": 10.135710716247559, "learning_rate": 1.0371220975280393e-06, "loss": 0.053717322647571564, "step": 6027 }, { "epoch": 1.5649013499480788, "grad_norm": 3.7415194511413574, "learning_rate": 1.0365088332759596e-06, "loss": 0.018743440508842468, "step": 6028 }, { "epoch": 1.5651609553478711, "grad_norm": 4.679855823516846, "learning_rate": 1.0358958719298845e-06, "loss": 0.010580906644463539, "step": 6029 }, { "epoch": 1.5654205607476634, "grad_norm": 5.479997158050537, "learning_rate": 1.0352832135981711e-06, "loss": 0.01029722485691309, "step": 6030 }, { "epoch": 1.5656801661474558, "grad_norm": 9.112139701843262, "learning_rate": 1.0346708583891237e-06, "loss": 0.07504169642925262, "step": 6031 }, { "epoch": 1.565939771547248, "grad_norm": 11.367140769958496, "learning_rate": 1.034058806410993e-06, "loss": 0.10997497290372849, "step": 6032 }, { "epoch": 1.5661993769470404, "grad_norm": 9.545903205871582, "learning_rate": 1.0334470577719755e-06, "loss": 0.056213460862636566, "step": 6033 }, { "epoch": 1.5664589823468327, "grad_norm": 9.004844665527344, "learning_rate": 1.0328356125802136e-06, "loss": 0.15563902258872986, "step": 6034 }, { "epoch": 1.566718587746625, "grad_norm": 8.864649772644043, "learning_rate": 1.0322244709437983e-06, "loss": 0.058059170842170715, "step": 6035 }, { "epoch": 1.5669781931464173, "grad_norm": 10.206201553344727, "learning_rate": 1.0316136329707649e-06, "loss": 0.04410235956311226, "step": 6036 }, { "epoch": 1.5672377985462098, "grad_norm": 10.641823768615723, "learning_rate": 1.0310030987690945e-06, "loss": 0.048485029488801956, "step": 6037 }, { "epoch": 1.5674974039460021, "grad_norm": 10.459261894226074, "learning_rate": 1.030392868446717e-06, "loss": 0.06202954798936844, "step": 6038 }, { "epoch": 1.5677570093457944, "grad_norm": 8.211485862731934, "learning_rate": 1.029782942111506e-06, "loss": 0.053531307727098465, "step": 6039 }, { "epoch": 1.5680166147455867, "grad_norm": 9.015928268432617, "learning_rate": 1.0291733198712838e-06, "loss": 0.0490473210811615, "step": 6040 }, { "epoch": 1.568276220145379, "grad_norm": 9.640584945678711, "learning_rate": 1.0285640018338166e-06, "loss": 0.10454653203487396, "step": 6041 }, { "epoch": 1.5685358255451713, "grad_norm": 12.232954025268555, "learning_rate": 1.027954988106818e-06, "loss": 0.03137259930372238, "step": 6042 }, { "epoch": 1.5687954309449637, "grad_norm": 7.359123229980469, "learning_rate": 1.0273462787979485e-06, "loss": 0.05013256147503853, "step": 6043 }, { "epoch": 1.569055036344756, "grad_norm": 11.152789115905762, "learning_rate": 1.0267378740148131e-06, "loss": 0.15934371948242188, "step": 6044 }, { "epoch": 1.5693146417445483, "grad_norm": 5.429010391235352, "learning_rate": 1.0261297738649637e-06, "loss": 0.010710546746850014, "step": 6045 }, { "epoch": 1.5695742471443406, "grad_norm": 12.616474151611328, "learning_rate": 1.0255219784558992e-06, "loss": 0.086412213742733, "step": 6046 }, { "epoch": 1.5698338525441329, "grad_norm": 4.592020034790039, "learning_rate": 1.0249144878950634e-06, "loss": 0.008831611834466457, "step": 6047 }, { "epoch": 1.5700934579439252, "grad_norm": 7.709641933441162, "learning_rate": 1.0243073022898472e-06, "loss": 0.026250142604112625, "step": 6048 }, { "epoch": 1.5703530633437177, "grad_norm": 13.01848316192627, "learning_rate": 1.023700421747587e-06, "loss": 0.03830840066075325, "step": 6049 }, { "epoch": 1.57061266874351, "grad_norm": 7.839964389801025, "learning_rate": 1.0230938463755648e-06, "loss": 0.047436028718948364, "step": 6050 }, { "epoch": 1.5708722741433023, "grad_norm": 8.007784843444824, "learning_rate": 1.0224875762810102e-06, "loss": 0.18756914138793945, "step": 6051 }, { "epoch": 1.5711318795430946, "grad_norm": 9.401654243469238, "learning_rate": 1.021881611571097e-06, "loss": 0.03898317739367485, "step": 6052 }, { "epoch": 1.571391484942887, "grad_norm": 8.986214637756348, "learning_rate": 1.0212759523529456e-06, "loss": 0.06554725766181946, "step": 6053 }, { "epoch": 1.5716510903426792, "grad_norm": 11.018774032592773, "learning_rate": 1.020670598733624e-06, "loss": 0.11802354454994202, "step": 6054 }, { "epoch": 1.5719106957424716, "grad_norm": 11.568116188049316, "learning_rate": 1.0200655508201438e-06, "loss": 0.018697025254368782, "step": 6055 }, { "epoch": 1.5721703011422639, "grad_norm": 9.841056823730469, "learning_rate": 1.019460808719465e-06, "loss": 0.1245393231511116, "step": 6056 }, { "epoch": 1.5724299065420562, "grad_norm": 9.947080612182617, "learning_rate": 1.0188563725384898e-06, "loss": 0.14191484451293945, "step": 6057 }, { "epoch": 1.5726895119418485, "grad_norm": 10.059103965759277, "learning_rate": 1.01825224238407e-06, "loss": 0.09415354579687119, "step": 6058 }, { "epoch": 1.5729491173416408, "grad_norm": 8.086653709411621, "learning_rate": 1.0176484183630035e-06, "loss": 0.03864789009094238, "step": 6059 }, { "epoch": 1.573208722741433, "grad_norm": 7.190443992614746, "learning_rate": 1.0170449005820296e-06, "loss": 0.17388126254081726, "step": 6060 }, { "epoch": 1.5734683281412254, "grad_norm": 8.681221008300781, "learning_rate": 1.0164416891478382e-06, "loss": 0.011515956372022629, "step": 6061 }, { "epoch": 1.5737279335410177, "grad_norm": 7.964816093444824, "learning_rate": 1.0158387841670626e-06, "loss": 0.014502759091556072, "step": 6062 }, { "epoch": 1.57398753894081, "grad_norm": 9.044486999511719, "learning_rate": 1.0152361857462836e-06, "loss": 0.04447879642248154, "step": 6063 }, { "epoch": 1.5742471443406023, "grad_norm": 10.099874496459961, "learning_rate": 1.0146338939920262e-06, "loss": 0.09599380195140839, "step": 6064 }, { "epoch": 1.5745067497403946, "grad_norm": 11.752754211425781, "learning_rate": 1.014031909010761e-06, "loss": 0.05280284583568573, "step": 6065 }, { "epoch": 1.574766355140187, "grad_norm": 8.28384780883789, "learning_rate": 1.0134302309089065e-06, "loss": 0.08568839728832245, "step": 6066 }, { "epoch": 1.5750259605399792, "grad_norm": 9.302923202514648, "learning_rate": 1.0128288597928252e-06, "loss": 0.06186448037624359, "step": 6067 }, { "epoch": 1.5752855659397715, "grad_norm": 7.964133262634277, "learning_rate": 1.0122277957688244e-06, "loss": 0.0328059196472168, "step": 6068 }, { "epoch": 1.5755451713395638, "grad_norm": 9.521063804626465, "learning_rate": 1.0116270389431606e-06, "loss": 0.06040489673614502, "step": 6069 }, { "epoch": 1.5758047767393562, "grad_norm": 8.224623680114746, "learning_rate": 1.0110265894220322e-06, "loss": 0.03032253310084343, "step": 6070 }, { "epoch": 1.5760643821391485, "grad_norm": 8.370471954345703, "learning_rate": 1.010426447311586e-06, "loss": 0.09667657315731049, "step": 6071 }, { "epoch": 1.5763239875389408, "grad_norm": 10.876726150512695, "learning_rate": 1.0098266127179132e-06, "loss": 0.09286346286535263, "step": 6072 }, { "epoch": 1.576583592938733, "grad_norm": 13.012537956237793, "learning_rate": 1.00922708574705e-06, "loss": 0.02492939867079258, "step": 6073 }, { "epoch": 1.5768431983385254, "grad_norm": 7.59501314163208, "learning_rate": 1.0086278665049801e-06, "loss": 0.05458587408065796, "step": 6074 }, { "epoch": 1.5771028037383177, "grad_norm": 4.812619686126709, "learning_rate": 1.0080289550976314e-06, "loss": 0.02186523750424385, "step": 6075 }, { "epoch": 1.57736240913811, "grad_norm": 9.049494743347168, "learning_rate": 1.0074303516308767e-06, "loss": 0.07743342220783234, "step": 6076 }, { "epoch": 1.5776220145379023, "grad_norm": 9.198593139648438, "learning_rate": 1.0068320562105369e-06, "loss": 0.10067857801914215, "step": 6077 }, { "epoch": 1.5778816199376946, "grad_norm": 3.734281063079834, "learning_rate": 1.0062340689423762e-06, "loss": 0.008868107572197914, "step": 6078 }, { "epoch": 1.578141225337487, "grad_norm": 7.6446213722229, "learning_rate": 1.0056363899321053e-06, "loss": 0.06809450685977936, "step": 6079 }, { "epoch": 1.5784008307372792, "grad_norm": 9.616958618164062, "learning_rate": 1.0050390192853801e-06, "loss": 0.03545167297124863, "step": 6080 }, { "epoch": 1.5786604361370715, "grad_norm": 7.420277118682861, "learning_rate": 1.0044419571078016e-06, "loss": 0.016159910708665848, "step": 6081 }, { "epoch": 1.5789200415368638, "grad_norm": 9.816426277160645, "learning_rate": 1.0038452035049174e-06, "loss": 0.0864492803812027, "step": 6082 }, { "epoch": 1.5791796469366561, "grad_norm": 10.705350875854492, "learning_rate": 1.0032487585822196e-06, "loss": 0.06971655040979385, "step": 6083 }, { "epoch": 1.5794392523364484, "grad_norm": 8.529905319213867, "learning_rate": 1.0026526224451455e-06, "loss": 0.03745666891336441, "step": 6084 }, { "epoch": 1.579698857736241, "grad_norm": 9.177329063415527, "learning_rate": 1.0020567951990794e-06, "loss": 0.08434998244047165, "step": 6085 }, { "epoch": 1.5799584631360333, "grad_norm": 7.039719581604004, "learning_rate": 1.0014612769493494e-06, "loss": 0.06286708265542984, "step": 6086 }, { "epoch": 1.5802180685358256, "grad_norm": 7.251510143280029, "learning_rate": 1.000866067801229e-06, "loss": 0.031312815845012665, "step": 6087 }, { "epoch": 1.5804776739356179, "grad_norm": 13.196393013000488, "learning_rate": 1.0002711678599378e-06, "loss": 0.032029420137405396, "step": 6088 }, { "epoch": 1.5807372793354102, "grad_norm": 11.662070274353027, "learning_rate": 9.996765772306405e-07, "loss": 0.07861031591892242, "step": 6089 }, { "epoch": 1.5809968847352025, "grad_norm": 6.8793511390686035, "learning_rate": 9.990822960184488e-07, "loss": 0.017641134560108185, "step": 6090 }, { "epoch": 1.5812564901349948, "grad_norm": 8.32076358795166, "learning_rate": 9.984883243284146e-07, "loss": 0.04260701686143875, "step": 6091 }, { "epoch": 1.5815160955347871, "grad_norm": 12.5129976272583, "learning_rate": 9.978946622655414e-07, "loss": 0.06424976140260696, "step": 6092 }, { "epoch": 1.5817757009345794, "grad_norm": 5.750008583068848, "learning_rate": 9.973013099347734e-07, "loss": 0.018043240532279015, "step": 6093 }, { "epoch": 1.5820353063343717, "grad_norm": 10.86890697479248, "learning_rate": 9.967082674410028e-07, "loss": 0.10417626798152924, "step": 6094 }, { "epoch": 1.582294911734164, "grad_norm": 8.899286270141602, "learning_rate": 9.961155348890654e-07, "loss": 0.07899390906095505, "step": 6095 }, { "epoch": 1.5825545171339563, "grad_norm": 9.55163860321045, "learning_rate": 9.955231123837422e-07, "loss": 0.05946134775876999, "step": 6096 }, { "epoch": 1.5828141225337489, "grad_norm": 8.457242965698242, "learning_rate": 9.94931000029761e-07, "loss": 0.08967159688472748, "step": 6097 }, { "epoch": 1.5830737279335412, "grad_norm": 9.280034065246582, "learning_rate": 9.943391979317938e-07, "loss": 0.10545799881219864, "step": 6098 }, { "epoch": 1.5833333333333335, "grad_norm": 4.692337989807129, "learning_rate": 9.93747706194456e-07, "loss": 0.004244961775839329, "step": 6099 }, { "epoch": 1.5835929387331258, "grad_norm": 5.253089427947998, "learning_rate": 9.931565249223116e-07, "loss": 0.021034402772784233, "step": 6100 }, { "epoch": 1.583852544132918, "grad_norm": 8.671971321105957, "learning_rate": 9.925656542198666e-07, "loss": 0.060935989022254944, "step": 6101 }, { "epoch": 1.5841121495327104, "grad_norm": 9.929414749145508, "learning_rate": 9.919750941915748e-07, "loss": 0.08141940087080002, "step": 6102 }, { "epoch": 1.5843717549325027, "grad_norm": 10.367295265197754, "learning_rate": 9.91384844941833e-07, "loss": 0.06933117657899857, "step": 6103 }, { "epoch": 1.584631360332295, "grad_norm": 14.888291358947754, "learning_rate": 9.907949065749827e-07, "loss": 0.046403344720602036, "step": 6104 }, { "epoch": 1.5848909657320873, "grad_norm": 7.225255012512207, "learning_rate": 9.902052791953131e-07, "loss": 0.09299860894680023, "step": 6105 }, { "epoch": 1.5851505711318796, "grad_norm": 6.4888715744018555, "learning_rate": 9.896159629070564e-07, "loss": 0.03824766352772713, "step": 6106 }, { "epoch": 1.585410176531672, "grad_norm": 9.263890266418457, "learning_rate": 9.890269578143894e-07, "loss": 0.13239075243473053, "step": 6107 }, { "epoch": 1.5856697819314642, "grad_norm": 9.272712707519531, "learning_rate": 9.884382640214357e-07, "loss": 0.066036157310009, "step": 6108 }, { "epoch": 1.5859293873312565, "grad_norm": 10.417691230773926, "learning_rate": 9.878498816322621e-07, "loss": 0.054780520498752594, "step": 6109 }, { "epoch": 1.5861889927310489, "grad_norm": 7.44378662109375, "learning_rate": 9.87261810750882e-07, "loss": 0.07051566988229752, "step": 6110 }, { "epoch": 1.5864485981308412, "grad_norm": 9.156224250793457, "learning_rate": 9.866740514812524e-07, "loss": 0.1046803742647171, "step": 6111 }, { "epoch": 1.5867082035306335, "grad_norm": 10.254530906677246, "learning_rate": 9.86086603927275e-07, "loss": 0.03629626706242561, "step": 6112 }, { "epoch": 1.5869678089304258, "grad_norm": 11.239745140075684, "learning_rate": 9.854994681927992e-07, "loss": 0.052477557212114334, "step": 6113 }, { "epoch": 1.587227414330218, "grad_norm": 13.91186237335205, "learning_rate": 9.849126443816146e-07, "loss": 0.0191471129655838, "step": 6114 }, { "epoch": 1.5874870197300104, "grad_norm": 1.4698494672775269, "learning_rate": 9.843261325974591e-07, "loss": 0.007015420123934746, "step": 6115 }, { "epoch": 1.5877466251298027, "grad_norm": 8.317206382751465, "learning_rate": 9.837399329440155e-07, "loss": 0.1621614396572113, "step": 6116 }, { "epoch": 1.588006230529595, "grad_norm": 8.01662540435791, "learning_rate": 9.831540455249097e-07, "loss": 0.1350264996290207, "step": 6117 }, { "epoch": 1.5882658359293873, "grad_norm": 5.457774639129639, "learning_rate": 9.825684704437132e-07, "loss": 0.017926640808582306, "step": 6118 }, { "epoch": 1.5885254413291796, "grad_norm": 10.503756523132324, "learning_rate": 9.819832078039419e-07, "loss": 0.16522441804409027, "step": 6119 }, { "epoch": 1.588785046728972, "grad_norm": 9.326226234436035, "learning_rate": 9.813982577090572e-07, "loss": 0.06314161419868469, "step": 6120 }, { "epoch": 1.5890446521287642, "grad_norm": 12.965301513671875, "learning_rate": 9.808136202624657e-07, "loss": 0.13358405232429504, "step": 6121 }, { "epoch": 1.5893042575285565, "grad_norm": 8.553083419799805, "learning_rate": 9.802292955675163e-07, "loss": 0.01863318867981434, "step": 6122 }, { "epoch": 1.5895638629283488, "grad_norm": 8.427129745483398, "learning_rate": 9.796452837275055e-07, "loss": 0.03610028326511383, "step": 6123 }, { "epoch": 1.5898234683281411, "grad_norm": 10.044571876525879, "learning_rate": 9.790615848456725e-07, "loss": 0.10881271958351135, "step": 6124 }, { "epoch": 1.5900830737279334, "grad_norm": 10.420720100402832, "learning_rate": 9.784781990252027e-07, "loss": 0.05496913194656372, "step": 6125 }, { "epoch": 1.5903426791277258, "grad_norm": 10.173528671264648, "learning_rate": 9.778951263692247e-07, "loss": 0.14078503847122192, "step": 6126 }, { "epoch": 1.590602284527518, "grad_norm": 8.897722244262695, "learning_rate": 9.773123669808118e-07, "loss": 0.04403966665267944, "step": 6127 }, { "epoch": 1.5908618899273104, "grad_norm": 9.373709678649902, "learning_rate": 9.767299209629841e-07, "loss": 0.11869382113218307, "step": 6128 }, { "epoch": 1.5911214953271027, "grad_norm": 3.385064125061035, "learning_rate": 9.761477884187038e-07, "loss": 0.020000234246253967, "step": 6129 }, { "epoch": 1.591381100726895, "grad_norm": 13.062518119812012, "learning_rate": 9.755659694508781e-07, "loss": 0.06982442736625671, "step": 6130 }, { "epoch": 1.5916407061266873, "grad_norm": 7.849478721618652, "learning_rate": 9.749844641623605e-07, "loss": 0.057762838900089264, "step": 6131 }, { "epoch": 1.5919003115264796, "grad_norm": 9.096354484558105, "learning_rate": 9.744032726559465e-07, "loss": 0.10011710971593857, "step": 6132 }, { "epoch": 1.592159916926272, "grad_norm": 6.7319817543029785, "learning_rate": 9.738223950343789e-07, "loss": 0.020991556346416473, "step": 6133 }, { "epoch": 1.5924195223260644, "grad_norm": 8.857818603515625, "learning_rate": 9.732418314003422e-07, "loss": 0.08705062419176102, "step": 6134 }, { "epoch": 1.5926791277258567, "grad_norm": 9.53032398223877, "learning_rate": 9.726615818564675e-07, "loss": 0.07804296910762787, "step": 6135 }, { "epoch": 1.592938733125649, "grad_norm": 3.1068098545074463, "learning_rate": 9.720816465053296e-07, "loss": 0.0036798533983528614, "step": 6136 }, { "epoch": 1.5931983385254413, "grad_norm": 11.253424644470215, "learning_rate": 9.715020254494475e-07, "loss": 0.07225307822227478, "step": 6137 }, { "epoch": 1.5934579439252337, "grad_norm": 10.149560928344727, "learning_rate": 9.709227187912852e-07, "loss": 0.15687985718250275, "step": 6138 }, { "epoch": 1.593717549325026, "grad_norm": 8.519047737121582, "learning_rate": 9.703437266332506e-07, "loss": 0.048995986580848694, "step": 6139 }, { "epoch": 1.5939771547248183, "grad_norm": 9.032483100891113, "learning_rate": 9.697650490776968e-07, "loss": 0.11123410612344742, "step": 6140 }, { "epoch": 1.5942367601246106, "grad_norm": 6.597506999969482, "learning_rate": 9.691866862269197e-07, "loss": 0.08979952335357666, "step": 6141 }, { "epoch": 1.5944963655244029, "grad_norm": 6.89504337310791, "learning_rate": 9.686086381831617e-07, "loss": 0.015477234497666359, "step": 6142 }, { "epoch": 1.5947559709241952, "grad_norm": 7.740943431854248, "learning_rate": 9.680309050486075e-07, "loss": 0.05902833119034767, "step": 6143 }, { "epoch": 1.5950155763239875, "grad_norm": 5.880603313446045, "learning_rate": 9.674534869253887e-07, "loss": 0.012908351607620716, "step": 6144 }, { "epoch": 1.5952751817237798, "grad_norm": 2.9993033409118652, "learning_rate": 9.668763839155776e-07, "loss": 0.006176204886287451, "step": 6145 }, { "epoch": 1.5955347871235723, "grad_norm": 10.620271682739258, "learning_rate": 9.662995961211935e-07, "loss": 0.06142057478427887, "step": 6146 }, { "epoch": 1.5957943925233646, "grad_norm": 2.755467653274536, "learning_rate": 9.657231236442002e-07, "loss": 0.016284819692373276, "step": 6147 }, { "epoch": 1.596053997923157, "grad_norm": 10.142965316772461, "learning_rate": 9.65146966586504e-07, "loss": 0.09166675060987473, "step": 6148 }, { "epoch": 1.5963136033229492, "grad_norm": 7.630058288574219, "learning_rate": 9.645711250499565e-07, "loss": 0.07710204273462296, "step": 6149 }, { "epoch": 1.5965732087227416, "grad_norm": 8.876147270202637, "learning_rate": 9.639955991363526e-07, "loss": 0.15919777750968933, "step": 6150 }, { "epoch": 1.5968328141225339, "grad_norm": 8.457542419433594, "learning_rate": 9.634203889474324e-07, "loss": 0.10678166151046753, "step": 6151 }, { "epoch": 1.5970924195223262, "grad_norm": 9.74612808227539, "learning_rate": 9.628454945848815e-07, "loss": 0.15899010002613068, "step": 6152 }, { "epoch": 1.5973520249221185, "grad_norm": 4.039417743682861, "learning_rate": 9.622709161503257e-07, "loss": 0.016996685415506363, "step": 6153 }, { "epoch": 1.5976116303219108, "grad_norm": 8.624626159667969, "learning_rate": 9.616966537453389e-07, "loss": 0.03163427859544754, "step": 6154 }, { "epoch": 1.597871235721703, "grad_norm": 7.384050369262695, "learning_rate": 9.611227074714364e-07, "loss": 0.020606406033039093, "step": 6155 }, { "epoch": 1.5981308411214954, "grad_norm": 9.727676391601562, "learning_rate": 9.6054907743008e-07, "loss": 0.10426939278841019, "step": 6156 }, { "epoch": 1.5983904465212877, "grad_norm": 10.003988265991211, "learning_rate": 9.599757637226739e-07, "loss": 0.013690972700715065, "step": 6157 }, { "epoch": 1.59865005192108, "grad_norm": 8.298256874084473, "learning_rate": 9.594027664505656e-07, "loss": 0.10182187706232071, "step": 6158 }, { "epoch": 1.5989096573208723, "grad_norm": 1.388411283493042, "learning_rate": 9.588300857150498e-07, "loss": 0.003653549123555422, "step": 6159 }, { "epoch": 1.5991692627206646, "grad_norm": 11.95708179473877, "learning_rate": 9.582577216173626e-07, "loss": 0.08068227022886276, "step": 6160 }, { "epoch": 1.599428868120457, "grad_norm": 11.07988166809082, "learning_rate": 9.576856742586837e-07, "loss": 0.05319377779960632, "step": 6161 }, { "epoch": 1.5996884735202492, "grad_norm": 0.6743687391281128, "learning_rate": 9.5711394374014e-07, "loss": 0.0013814246049150825, "step": 6162 }, { "epoch": 1.5999480789200415, "grad_norm": 11.162513732910156, "learning_rate": 9.565425301627987e-07, "loss": 0.06811297684907913, "step": 6163 }, { "epoch": 1.6002076843198338, "grad_norm": 9.419539451599121, "learning_rate": 9.55971433627674e-07, "loss": 0.13465332984924316, "step": 6164 }, { "epoch": 1.6004672897196262, "grad_norm": 11.562515258789062, "learning_rate": 9.554006542357219e-07, "loss": 0.0663033202290535, "step": 6165 }, { "epoch": 1.6007268951194185, "grad_norm": 7.96680212020874, "learning_rate": 9.548301920878428e-07, "loss": 0.019513973966240883, "step": 6166 }, { "epoch": 1.6009865005192108, "grad_norm": 11.70079517364502, "learning_rate": 9.542600472848825e-07, "loss": 0.0436982661485672, "step": 6167 }, { "epoch": 1.601246105919003, "grad_norm": 8.850266456604004, "learning_rate": 9.536902199276284e-07, "loss": 0.12928059697151184, "step": 6168 }, { "epoch": 1.6015057113187954, "grad_norm": 10.35810661315918, "learning_rate": 9.531207101168132e-07, "loss": 0.05125388875603676, "step": 6169 }, { "epoch": 1.6017653167185877, "grad_norm": 9.422423362731934, "learning_rate": 9.525515179531139e-07, "loss": 0.10099310427904129, "step": 6170 }, { "epoch": 1.60202492211838, "grad_norm": 8.999065399169922, "learning_rate": 9.519826435371502e-07, "loss": 0.050004951655864716, "step": 6171 }, { "epoch": 1.6022845275181723, "grad_norm": 13.063153266906738, "learning_rate": 9.514140869694852e-07, "loss": 0.048017751425504684, "step": 6172 }, { "epoch": 1.6025441329179646, "grad_norm": 5.526363372802734, "learning_rate": 9.508458483506281e-07, "loss": 0.01564898155629635, "step": 6173 }, { "epoch": 1.602803738317757, "grad_norm": 9.503007888793945, "learning_rate": 9.502779277810292e-07, "loss": 0.038023173809051514, "step": 6174 }, { "epoch": 1.6030633437175492, "grad_norm": 9.164512634277344, "learning_rate": 9.497103253610857e-07, "loss": 0.012909095734357834, "step": 6175 }, { "epoch": 1.6033229491173415, "grad_norm": 5.818684101104736, "learning_rate": 9.491430411911343e-07, "loss": 0.021845050156116486, "step": 6176 }, { "epoch": 1.6035825545171338, "grad_norm": 10.596431732177734, "learning_rate": 9.485760753714592e-07, "loss": 0.02215868979692459, "step": 6177 }, { "epoch": 1.6038421599169261, "grad_norm": 8.68700122833252, "learning_rate": 9.480094280022873e-07, "loss": 0.11449287831783295, "step": 6178 }, { "epoch": 1.6041017653167184, "grad_norm": 11.032129287719727, "learning_rate": 9.474430991837886e-07, "loss": 0.06032365933060646, "step": 6179 }, { "epoch": 1.6043613707165107, "grad_norm": 6.855289936065674, "learning_rate": 9.468770890160767e-07, "loss": 0.032382551580667496, "step": 6180 }, { "epoch": 1.604620976116303, "grad_norm": 7.806724548339844, "learning_rate": 9.463113975992086e-07, "loss": 0.06722113490104675, "step": 6181 }, { "epoch": 1.6048805815160956, "grad_norm": 2.4470596313476562, "learning_rate": 9.457460250331868e-07, "loss": 0.005184976849704981, "step": 6182 }, { "epoch": 1.605140186915888, "grad_norm": 10.67555046081543, "learning_rate": 9.451809714179569e-07, "loss": 0.07444718480110168, "step": 6183 }, { "epoch": 1.6053997923156802, "grad_norm": 9.655664443969727, "learning_rate": 9.446162368534051e-07, "loss": 0.043021999299526215, "step": 6184 }, { "epoch": 1.6056593977154725, "grad_norm": 7.868814945220947, "learning_rate": 9.440518214393657e-07, "loss": 0.12157639116048813, "step": 6185 }, { "epoch": 1.6059190031152648, "grad_norm": 8.105634689331055, "learning_rate": 9.434877252756125e-07, "loss": 0.03622312843799591, "step": 6186 }, { "epoch": 1.6061786085150571, "grad_norm": 11.387063026428223, "learning_rate": 9.429239484618669e-07, "loss": 0.04622707515954971, "step": 6187 }, { "epoch": 1.6064382139148494, "grad_norm": 9.568228721618652, "learning_rate": 9.423604910977904e-07, "loss": 0.0569285973906517, "step": 6188 }, { "epoch": 1.6066978193146417, "grad_norm": 9.119587898254395, "learning_rate": 9.41797353282989e-07, "loss": 0.09545683860778809, "step": 6189 }, { "epoch": 1.606957424714434, "grad_norm": 7.651573181152344, "learning_rate": 9.412345351170138e-07, "loss": 0.03780031576752663, "step": 6190 }, { "epoch": 1.6072170301142263, "grad_norm": 10.074515342712402, "learning_rate": 9.406720366993575e-07, "loss": 0.012586007826030254, "step": 6191 }, { "epoch": 1.6074766355140186, "grad_norm": 8.527278900146484, "learning_rate": 9.401098581294563e-07, "loss": 0.08941332250833511, "step": 6192 }, { "epoch": 1.607736240913811, "grad_norm": 9.095743179321289, "learning_rate": 9.395479995066919e-07, "loss": 0.10397651791572571, "step": 6193 }, { "epoch": 1.6079958463136035, "grad_norm": 5.413567066192627, "learning_rate": 9.38986460930387e-07, "loss": 0.010098562575876713, "step": 6194 }, { "epoch": 1.6082554517133958, "grad_norm": 8.718454360961914, "learning_rate": 9.384252424998094e-07, "loss": 0.12734976410865784, "step": 6195 }, { "epoch": 1.608515057113188, "grad_norm": 8.4729642868042, "learning_rate": 9.378643443141694e-07, "loss": 0.12403763830661774, "step": 6196 }, { "epoch": 1.6087746625129804, "grad_norm": 9.81765079498291, "learning_rate": 9.373037664726204e-07, "loss": 0.1272698938846588, "step": 6197 }, { "epoch": 1.6090342679127727, "grad_norm": 7.696983337402344, "learning_rate": 9.367435090742608e-07, "loss": 0.02382618747651577, "step": 6198 }, { "epoch": 1.609293873312565, "grad_norm": 5.727336883544922, "learning_rate": 9.361835722181306e-07, "loss": 0.03359556943178177, "step": 6199 }, { "epoch": 1.6095534787123573, "grad_norm": 9.332430839538574, "learning_rate": 9.356239560032135e-07, "loss": 0.09968965500593185, "step": 6200 }, { "epoch": 1.6098130841121496, "grad_norm": 7.382543563842773, "learning_rate": 9.350646605284378e-07, "loss": 0.024613432586193085, "step": 6201 }, { "epoch": 1.610072689511942, "grad_norm": 8.221385955810547, "learning_rate": 9.345056858926735e-07, "loss": 0.1561950147151947, "step": 6202 }, { "epoch": 1.6103322949117342, "grad_norm": 2.347644329071045, "learning_rate": 9.339470321947341e-07, "loss": 0.005057732108980417, "step": 6203 }, { "epoch": 1.6105919003115265, "grad_norm": 7.103420734405518, "learning_rate": 9.333886995333782e-07, "loss": 0.021521808579564095, "step": 6204 }, { "epoch": 1.6108515057113189, "grad_norm": 6.343746185302734, "learning_rate": 9.328306880073046e-07, "loss": 0.030701428651809692, "step": 6205 }, { "epoch": 1.6111111111111112, "grad_norm": 9.324624061584473, "learning_rate": 9.322729977151587e-07, "loss": 0.04913279041647911, "step": 6206 }, { "epoch": 1.6113707165109035, "grad_norm": 7.009439468383789, "learning_rate": 9.317156287555253e-07, "loss": 0.07372012734413147, "step": 6207 }, { "epoch": 1.6116303219106958, "grad_norm": 12.083925247192383, "learning_rate": 9.311585812269356e-07, "loss": 0.057325828820466995, "step": 6208 }, { "epoch": 1.611889927310488, "grad_norm": 7.646029949188232, "learning_rate": 9.306018552278631e-07, "loss": 0.03283817321062088, "step": 6209 }, { "epoch": 1.6121495327102804, "grad_norm": 7.8551926612854, "learning_rate": 9.300454508567242e-07, "loss": 0.11687206476926804, "step": 6210 }, { "epoch": 1.6124091381100727, "grad_norm": 10.775976181030273, "learning_rate": 9.294893682118783e-07, "loss": 0.008729199878871441, "step": 6211 }, { "epoch": 1.612668743509865, "grad_norm": 6.1034417152404785, "learning_rate": 9.28933607391627e-07, "loss": 0.013755295425653458, "step": 6212 }, { "epoch": 1.6129283489096573, "grad_norm": 7.2426958084106445, "learning_rate": 9.28378168494217e-07, "loss": 0.04603176563978195, "step": 6213 }, { "epoch": 1.6131879543094496, "grad_norm": 7.9199981689453125, "learning_rate": 9.278230516178385e-07, "loss": 0.020451154559850693, "step": 6214 }, { "epoch": 1.613447559709242, "grad_norm": 10.01712417602539, "learning_rate": 9.272682568606209e-07, "loss": 0.10529930144548416, "step": 6215 }, { "epoch": 1.6137071651090342, "grad_norm": 9.477547645568848, "learning_rate": 9.267137843206411e-07, "loss": 0.01729734241962433, "step": 6216 }, { "epoch": 1.6139667705088265, "grad_norm": 9.473709106445312, "learning_rate": 9.261596340959161e-07, "loss": 0.17430119216442108, "step": 6217 }, { "epoch": 1.6142263759086188, "grad_norm": 11.604022026062012, "learning_rate": 9.256058062844078e-07, "loss": 0.03862488269805908, "step": 6218 }, { "epoch": 1.6144859813084111, "grad_norm": 7.4017486572265625, "learning_rate": 9.250523009840201e-07, "loss": 0.05286489054560661, "step": 6219 }, { "epoch": 1.6147455867082035, "grad_norm": 3.199949264526367, "learning_rate": 9.244991182925987e-07, "loss": 0.012024137191474438, "step": 6220 }, { "epoch": 1.6150051921079958, "grad_norm": 11.263750076293945, "learning_rate": 9.239462583079359e-07, "loss": 0.08563786745071411, "step": 6221 }, { "epoch": 1.615264797507788, "grad_norm": 7.367594242095947, "learning_rate": 9.233937211277633e-07, "loss": 0.020950783044099808, "step": 6222 }, { "epoch": 1.6155244029075804, "grad_norm": 7.67721700668335, "learning_rate": 9.228415068497565e-07, "loss": 0.1669628620147705, "step": 6223 }, { "epoch": 1.6157840083073727, "grad_norm": 8.104241371154785, "learning_rate": 9.222896155715352e-07, "loss": 0.13018646836280823, "step": 6224 }, { "epoch": 1.616043613707165, "grad_norm": 3.5088655948638916, "learning_rate": 9.217380473906612e-07, "loss": 0.027853520587086678, "step": 6225 }, { "epoch": 1.6163032191069573, "grad_norm": 2.7014262676239014, "learning_rate": 9.211868024046381e-07, "loss": 0.008463934995234013, "step": 6226 }, { "epoch": 1.6165628245067496, "grad_norm": 8.979504585266113, "learning_rate": 9.206358807109147e-07, "loss": 0.08831919729709625, "step": 6227 }, { "epoch": 1.616822429906542, "grad_norm": 8.127654075622559, "learning_rate": 9.200852824068801e-07, "loss": 0.02712080627679825, "step": 6228 }, { "epoch": 1.6170820353063342, "grad_norm": 7.232674598693848, "learning_rate": 9.195350075898684e-07, "loss": 0.13373906910419464, "step": 6229 }, { "epoch": 1.6173416407061267, "grad_norm": 7.259256362915039, "learning_rate": 9.189850563571556e-07, "loss": 0.025109028443694115, "step": 6230 }, { "epoch": 1.617601246105919, "grad_norm": 7.446611404418945, "learning_rate": 9.184354288059596e-07, "loss": 0.059726618230342865, "step": 6231 }, { "epoch": 1.6178608515057114, "grad_norm": 6.806866645812988, "learning_rate": 9.178861250334429e-07, "loss": 0.013347459957003593, "step": 6232 }, { "epoch": 1.6181204569055037, "grad_norm": 7.755645275115967, "learning_rate": 9.173371451367097e-07, "loss": 0.11339033395051956, "step": 6233 }, { "epoch": 1.618380062305296, "grad_norm": 10.886655807495117, "learning_rate": 9.167884892128059e-07, "loss": 0.1304093301296234, "step": 6234 }, { "epoch": 1.6186396677050883, "grad_norm": 10.723713874816895, "learning_rate": 9.162401573587229e-07, "loss": 0.08812753856182098, "step": 6235 }, { "epoch": 1.6188992731048806, "grad_norm": 9.922018051147461, "learning_rate": 9.156921496713922e-07, "loss": 0.02863203175365925, "step": 6236 }, { "epoch": 1.6191588785046729, "grad_norm": 8.08179759979248, "learning_rate": 9.151444662476902e-07, "loss": 0.048183467239141464, "step": 6237 }, { "epoch": 1.6194184839044652, "grad_norm": 9.974342346191406, "learning_rate": 9.145971071844332e-07, "loss": 0.03631168231368065, "step": 6238 }, { "epoch": 1.6196780893042575, "grad_norm": 5.173995494842529, "learning_rate": 9.140500725783818e-07, "loss": 0.04061884433031082, "step": 6239 }, { "epoch": 1.6199376947040498, "grad_norm": 8.455676078796387, "learning_rate": 9.135033625262412e-07, "loss": 0.02271174266934395, "step": 6240 }, { "epoch": 1.620197300103842, "grad_norm": 5.09301233291626, "learning_rate": 9.129569771246555e-07, "loss": 0.05830760300159454, "step": 6241 }, { "epoch": 1.6204569055036346, "grad_norm": 7.954090118408203, "learning_rate": 9.124109164702135e-07, "loss": 0.13396155834197998, "step": 6242 }, { "epoch": 1.620716510903427, "grad_norm": 7.434292793273926, "learning_rate": 9.118651806594459e-07, "loss": 0.1352381706237793, "step": 6243 }, { "epoch": 1.6209761163032192, "grad_norm": 8.311488151550293, "learning_rate": 9.113197697888265e-07, "loss": 0.165963277220726, "step": 6244 }, { "epoch": 1.6212357217030116, "grad_norm": 11.422502517700195, "learning_rate": 9.107746839547729e-07, "loss": 0.11931384354829788, "step": 6245 }, { "epoch": 1.6214953271028039, "grad_norm": 10.782086372375488, "learning_rate": 9.102299232536413e-07, "loss": 0.10526114702224731, "step": 6246 }, { "epoch": 1.6217549325025962, "grad_norm": 9.673149108886719, "learning_rate": 9.096854877817346e-07, "loss": 0.09701535105705261, "step": 6247 }, { "epoch": 1.6220145379023885, "grad_norm": 8.672794342041016, "learning_rate": 9.091413776352954e-07, "loss": 0.05153723061084747, "step": 6248 }, { "epoch": 1.6222741433021808, "grad_norm": 6.87314510345459, "learning_rate": 9.085975929105113e-07, "loss": 0.026655394583940506, "step": 6249 }, { "epoch": 1.622533748701973, "grad_norm": 10.35488510131836, "learning_rate": 9.080541337035102e-07, "loss": 0.07054802030324936, "step": 6250 }, { "epoch": 1.6227933541017654, "grad_norm": 9.313549041748047, "learning_rate": 9.075110001103627e-07, "loss": 0.05104581266641617, "step": 6251 }, { "epoch": 1.6230529595015577, "grad_norm": 2.267854690551758, "learning_rate": 9.069681922270837e-07, "loss": 0.004325231537222862, "step": 6252 }, { "epoch": 1.62331256490135, "grad_norm": 10.288649559020996, "learning_rate": 9.064257101496285e-07, "loss": 0.029910625889897346, "step": 6253 }, { "epoch": 1.6235721703011423, "grad_norm": 7.296132564544678, "learning_rate": 9.058835539738947e-07, "loss": 0.03561069816350937, "step": 6254 }, { "epoch": 1.6238317757009346, "grad_norm": 7.821628093719482, "learning_rate": 9.053417237957243e-07, "loss": 0.032739341259002686, "step": 6255 }, { "epoch": 1.624091381100727, "grad_norm": 11.455401420593262, "learning_rate": 9.048002197109004e-07, "loss": 0.07999362051486969, "step": 6256 }, { "epoch": 1.6243509865005192, "grad_norm": 9.561942100524902, "learning_rate": 9.042590418151474e-07, "loss": 0.05037909001111984, "step": 6257 }, { "epoch": 1.6246105919003115, "grad_norm": 9.696890830993652, "learning_rate": 9.037181902041348e-07, "loss": 0.015959257259964943, "step": 6258 }, { "epoch": 1.6248701973001038, "grad_norm": 4.141871929168701, "learning_rate": 9.031776649734708e-07, "loss": 0.008598823100328445, "step": 6259 }, { "epoch": 1.6251298026998962, "grad_norm": 5.579647064208984, "learning_rate": 9.026374662187102e-07, "loss": 0.02126101776957512, "step": 6260 }, { "epoch": 1.6253894080996885, "grad_norm": 6.562705993652344, "learning_rate": 9.020975940353463e-07, "loss": 0.03328230604529381, "step": 6261 }, { "epoch": 1.6256490134994808, "grad_norm": 5.989737510681152, "learning_rate": 9.015580485188158e-07, "loss": 0.01922638528048992, "step": 6262 }, { "epoch": 1.625908618899273, "grad_norm": 8.972261428833008, "learning_rate": 9.010188297644994e-07, "loss": 0.027773700654506683, "step": 6263 }, { "epoch": 1.6261682242990654, "grad_norm": 11.58440113067627, "learning_rate": 9.004799378677176e-07, "loss": 0.027070965617895126, "step": 6264 }, { "epoch": 1.6264278296988577, "grad_norm": 8.761272430419922, "learning_rate": 8.999413729237339e-07, "loss": 0.036557938903570175, "step": 6265 }, { "epoch": 1.62668743509865, "grad_norm": 11.724414825439453, "learning_rate": 8.994031350277552e-07, "loss": 0.12788382172584534, "step": 6266 }, { "epoch": 1.6269470404984423, "grad_norm": 8.608908653259277, "learning_rate": 8.988652242749288e-07, "loss": 0.08293183147907257, "step": 6267 }, { "epoch": 1.6272066458982346, "grad_norm": 2.30881404876709, "learning_rate": 8.983276407603464e-07, "loss": 0.004012567922472954, "step": 6268 }, { "epoch": 1.627466251298027, "grad_norm": 9.126639366149902, "learning_rate": 8.977903845790384e-07, "loss": 0.07289385795593262, "step": 6269 }, { "epoch": 1.6277258566978192, "grad_norm": 10.6666898727417, "learning_rate": 8.972534558259803e-07, "loss": 0.08026017248630524, "step": 6270 }, { "epoch": 1.6279854620976115, "grad_norm": 8.492986679077148, "learning_rate": 8.967168545960897e-07, "loss": 0.03932422399520874, "step": 6271 }, { "epoch": 1.6282450674974038, "grad_norm": 9.279993057250977, "learning_rate": 8.961805809842244e-07, "loss": 0.0326918289065361, "step": 6272 }, { "epoch": 1.6285046728971961, "grad_norm": 7.925037860870361, "learning_rate": 8.956446350851855e-07, "loss": 0.015611731447279453, "step": 6273 }, { "epoch": 1.6287642782969884, "grad_norm": 8.881474494934082, "learning_rate": 8.951090169937158e-07, "loss": 0.02231115847826004, "step": 6274 }, { "epoch": 1.6290238836967808, "grad_norm": 4.798060894012451, "learning_rate": 8.945737268045004e-07, "loss": 0.038999997079372406, "step": 6275 }, { "epoch": 1.629283489096573, "grad_norm": 9.528767585754395, "learning_rate": 8.940387646121673e-07, "loss": 0.023243308067321777, "step": 6276 }, { "epoch": 1.6295430944963654, "grad_norm": 9.767080307006836, "learning_rate": 8.935041305112838e-07, "loss": 0.05199260264635086, "step": 6277 }, { "epoch": 1.629802699896158, "grad_norm": 9.59459400177002, "learning_rate": 8.929698245963625e-07, "loss": 0.04593446105718613, "step": 6278 }, { "epoch": 1.6300623052959502, "grad_norm": 10.097428321838379, "learning_rate": 8.92435846961856e-07, "loss": 0.015174699015915394, "step": 6279 }, { "epoch": 1.6303219106957425, "grad_norm": 9.7376708984375, "learning_rate": 8.919021977021584e-07, "loss": 0.03209744766354561, "step": 6280 }, { "epoch": 1.6305815160955348, "grad_norm": 9.04373550415039, "learning_rate": 8.91368876911608e-07, "loss": 0.08894692361354828, "step": 6281 }, { "epoch": 1.6308411214953271, "grad_norm": 14.047399520874023, "learning_rate": 8.908358846844828e-07, "loss": 0.02670646645128727, "step": 6282 }, { "epoch": 1.6311007268951194, "grad_norm": 8.83419132232666, "learning_rate": 8.903032211150042e-07, "loss": 0.060881949961185455, "step": 6283 }, { "epoch": 1.6313603322949117, "grad_norm": 1.5343372821807861, "learning_rate": 8.89770886297335e-07, "loss": 0.008763588033616543, "step": 6284 }, { "epoch": 1.631619937694704, "grad_norm": 6.333771705627441, "learning_rate": 8.892388803255788e-07, "loss": 0.013840735889971256, "step": 6285 }, { "epoch": 1.6318795430944963, "grad_norm": 9.818028450012207, "learning_rate": 8.887072032937833e-07, "loss": 0.04347773268818855, "step": 6286 }, { "epoch": 1.6321391484942886, "grad_norm": 9.089714050292969, "learning_rate": 8.881758552959366e-07, "loss": 0.08453921973705292, "step": 6287 }, { "epoch": 1.632398753894081, "grad_norm": 6.928920269012451, "learning_rate": 8.876448364259677e-07, "loss": 0.023415053263306618, "step": 6288 }, { "epoch": 1.6326583592938733, "grad_norm": 7.027194023132324, "learning_rate": 8.871141467777501e-07, "loss": 0.029384618625044823, "step": 6289 }, { "epoch": 1.6329179646936658, "grad_norm": 11.008216857910156, "learning_rate": 8.865837864450962e-07, "loss": 0.09745979309082031, "step": 6290 }, { "epoch": 1.633177570093458, "grad_norm": 12.837447166442871, "learning_rate": 8.86053755521763e-07, "loss": 0.0829092338681221, "step": 6291 }, { "epoch": 1.6334371754932504, "grad_norm": 7.951898574829102, "learning_rate": 8.855240541014471e-07, "loss": 0.045630816370248795, "step": 6292 }, { "epoch": 1.6336967808930427, "grad_norm": 6.900551795959473, "learning_rate": 8.849946822777871e-07, "loss": 0.02310135029256344, "step": 6293 }, { "epoch": 1.633956386292835, "grad_norm": 9.210805892944336, "learning_rate": 8.844656401443646e-07, "loss": 0.01302409078925848, "step": 6294 }, { "epoch": 1.6342159916926273, "grad_norm": 8.113181114196777, "learning_rate": 8.839369277947021e-07, "loss": 0.04903629794716835, "step": 6295 }, { "epoch": 1.6344755970924196, "grad_norm": 10.978915214538574, "learning_rate": 8.83408545322263e-07, "loss": 0.04056038334965706, "step": 6296 }, { "epoch": 1.634735202492212, "grad_norm": 8.490053176879883, "learning_rate": 8.828804928204543e-07, "loss": 0.04741067439317703, "step": 6297 }, { "epoch": 1.6349948078920042, "grad_norm": 10.247552871704102, "learning_rate": 8.823527703826227e-07, "loss": 0.040934231132268906, "step": 6298 }, { "epoch": 1.6352544132917965, "grad_norm": 11.389487266540527, "learning_rate": 8.818253781020586e-07, "loss": 0.020982984453439713, "step": 6299 }, { "epoch": 1.6355140186915889, "grad_norm": 11.039714813232422, "learning_rate": 8.812983160719912e-07, "loss": 0.14435173571109772, "step": 6300 }, { "epoch": 1.6357736240913812, "grad_norm": 9.769349098205566, "learning_rate": 8.807715843855941e-07, "loss": 0.053201280534267426, "step": 6301 }, { "epoch": 1.6360332294911735, "grad_norm": 9.949394226074219, "learning_rate": 8.802451831359815e-07, "loss": 0.04631898179650307, "step": 6302 }, { "epoch": 1.6362928348909658, "grad_norm": 10.367444038391113, "learning_rate": 8.797191124162091e-07, "loss": 0.09751928597688675, "step": 6303 }, { "epoch": 1.636552440290758, "grad_norm": 7.786436557769775, "learning_rate": 8.791933723192731e-07, "loss": 0.0441097728908062, "step": 6304 }, { "epoch": 1.6368120456905504, "grad_norm": 3.472489356994629, "learning_rate": 8.786679629381136e-07, "loss": 0.006085654720664024, "step": 6305 }, { "epoch": 1.6370716510903427, "grad_norm": 11.703312873840332, "learning_rate": 8.781428843656106e-07, "loss": 0.12350304424762726, "step": 6306 }, { "epoch": 1.637331256490135, "grad_norm": 1.3657039403915405, "learning_rate": 8.776181366945858e-07, "loss": 0.007052162662148476, "step": 6307 }, { "epoch": 1.6375908618899273, "grad_norm": 1.6536731719970703, "learning_rate": 8.77093720017802e-07, "loss": 0.007499328814446926, "step": 6308 }, { "epoch": 1.6378504672897196, "grad_norm": 2.2198524475097656, "learning_rate": 8.765696344279645e-07, "loss": 0.002245538169518113, "step": 6309 }, { "epoch": 1.638110072689512, "grad_norm": 9.140088081359863, "learning_rate": 8.76045880017721e-07, "loss": 0.060904502868652344, "step": 6310 }, { "epoch": 1.6383696780893042, "grad_norm": 7.940468788146973, "learning_rate": 8.755224568796569e-07, "loss": 0.01810513809323311, "step": 6311 }, { "epoch": 1.6386292834890965, "grad_norm": 12.30627155303955, "learning_rate": 8.749993651063033e-07, "loss": 0.09417606145143509, "step": 6312 }, { "epoch": 1.6388888888888888, "grad_norm": 6.427719593048096, "learning_rate": 8.744766047901291e-07, "loss": 0.036482274532318115, "step": 6313 }, { "epoch": 1.6391484942886811, "grad_norm": 1.344321608543396, "learning_rate": 8.739541760235484e-07, "loss": 0.007029153406620026, "step": 6314 }, { "epoch": 1.6394080996884735, "grad_norm": 11.129658699035645, "learning_rate": 8.734320788989133e-07, "loss": 0.058340683579444885, "step": 6315 }, { "epoch": 1.6396677050882658, "grad_norm": 3.96219801902771, "learning_rate": 8.729103135085184e-07, "loss": 0.02252412959933281, "step": 6316 }, { "epoch": 1.639927310488058, "grad_norm": 6.639028072357178, "learning_rate": 8.723888799446012e-07, "loss": 0.018890563398599625, "step": 6317 }, { "epoch": 1.6401869158878504, "grad_norm": 9.883068084716797, "learning_rate": 8.718677782993383e-07, "loss": 0.06331166625022888, "step": 6318 }, { "epoch": 1.6404465212876427, "grad_norm": 11.278589248657227, "learning_rate": 8.713470086648482e-07, "loss": 0.12535923719406128, "step": 6319 }, { "epoch": 1.640706126687435, "grad_norm": 14.185550689697266, "learning_rate": 8.70826571133192e-07, "loss": 0.02722443826496601, "step": 6320 }, { "epoch": 1.6409657320872273, "grad_norm": 10.03127670288086, "learning_rate": 8.703064657963703e-07, "loss": 0.06811089813709259, "step": 6321 }, { "epoch": 1.6412253374870196, "grad_norm": 6.4258036613464355, "learning_rate": 8.697866927463264e-07, "loss": 0.01759495586156845, "step": 6322 }, { "epoch": 1.641484942886812, "grad_norm": 8.392895698547363, "learning_rate": 8.692672520749443e-07, "loss": 0.029677918180823326, "step": 6323 }, { "epoch": 1.6417445482866042, "grad_norm": 2.731243848800659, "learning_rate": 8.687481438740481e-07, "loss": 0.020842215046286583, "step": 6324 }, { "epoch": 1.6420041536863965, "grad_norm": 7.079140663146973, "learning_rate": 8.682293682354059e-07, "loss": 0.007673859596252441, "step": 6325 }, { "epoch": 1.642263759086189, "grad_norm": 4.972203254699707, "learning_rate": 8.677109252507246e-07, "loss": 0.009236319921910763, "step": 6326 }, { "epoch": 1.6425233644859814, "grad_norm": 8.825058937072754, "learning_rate": 8.671928150116523e-07, "loss": 0.11433467268943787, "step": 6327 }, { "epoch": 1.6427829698857737, "grad_norm": 10.946760177612305, "learning_rate": 8.666750376097805e-07, "loss": 0.10546694695949554, "step": 6328 }, { "epoch": 1.643042575285566, "grad_norm": 11.251607894897461, "learning_rate": 8.661575931366387e-07, "loss": 0.09313636273145676, "step": 6329 }, { "epoch": 1.6433021806853583, "grad_norm": 8.51339340209961, "learning_rate": 8.656404816837011e-07, "loss": 0.033892083913087845, "step": 6330 }, { "epoch": 1.6435617860851506, "grad_norm": 10.383890151977539, "learning_rate": 8.651237033423801e-07, "loss": 0.025453075766563416, "step": 6331 }, { "epoch": 1.6438213914849429, "grad_norm": 10.615754127502441, "learning_rate": 8.646072582040296e-07, "loss": 0.10832260549068451, "step": 6332 }, { "epoch": 1.6440809968847352, "grad_norm": 9.459778785705566, "learning_rate": 8.640911463599475e-07, "loss": 0.040392570197582245, "step": 6333 }, { "epoch": 1.6443406022845275, "grad_norm": 10.364725112915039, "learning_rate": 8.635753679013681e-07, "loss": 0.0764712393283844, "step": 6334 }, { "epoch": 1.6446002076843198, "grad_norm": 3.1380844116210938, "learning_rate": 8.6305992291947e-07, "loss": 0.009346948936581612, "step": 6335 }, { "epoch": 1.644859813084112, "grad_norm": 11.290587425231934, "learning_rate": 8.62544811505373e-07, "loss": 0.027631627395749092, "step": 6336 }, { "epoch": 1.6451194184839044, "grad_norm": 10.374869346618652, "learning_rate": 8.620300337501361e-07, "loss": 0.10384257137775421, "step": 6337 }, { "epoch": 1.645379023883697, "grad_norm": 2.936314105987549, "learning_rate": 8.615155897447606e-07, "loss": 0.008885920979082584, "step": 6338 }, { "epoch": 1.6456386292834893, "grad_norm": 13.517950057983398, "learning_rate": 8.610014795801879e-07, "loss": 0.029106078669428825, "step": 6339 }, { "epoch": 1.6458982346832816, "grad_norm": 3.100353717803955, "learning_rate": 8.604877033473011e-07, "loss": 0.0167132206261158, "step": 6340 }, { "epoch": 1.6461578400830739, "grad_norm": 8.776116371154785, "learning_rate": 8.599742611369255e-07, "loss": 0.07651011645793915, "step": 6341 }, { "epoch": 1.6464174454828662, "grad_norm": 10.970436096191406, "learning_rate": 8.594611530398235e-07, "loss": 0.0075821708887815475, "step": 6342 }, { "epoch": 1.6466770508826585, "grad_norm": 6.625573635101318, "learning_rate": 8.589483791467024e-07, "loss": 0.055692389607429504, "step": 6343 }, { "epoch": 1.6469366562824508, "grad_norm": 7.964571952819824, "learning_rate": 8.584359395482081e-07, "loss": 0.13699871301651, "step": 6344 }, { "epoch": 1.647196261682243, "grad_norm": 8.518203735351562, "learning_rate": 8.579238343349295e-07, "loss": 0.04966232180595398, "step": 6345 }, { "epoch": 1.6474558670820354, "grad_norm": 7.733097076416016, "learning_rate": 8.574120635973937e-07, "loss": 0.12030670046806335, "step": 6346 }, { "epoch": 1.6477154724818277, "grad_norm": 7.618414878845215, "learning_rate": 8.569006274260702e-07, "loss": 0.0446920320391655, "step": 6347 }, { "epoch": 1.64797507788162, "grad_norm": 8.62810230255127, "learning_rate": 8.563895259113703e-07, "loss": 0.06438873708248138, "step": 6348 }, { "epoch": 1.6482346832814123, "grad_norm": 10.184386253356934, "learning_rate": 8.558787591436437e-07, "loss": 0.021961526945233345, "step": 6349 }, { "epoch": 1.6484942886812046, "grad_norm": 3.455333948135376, "learning_rate": 8.553683272131827e-07, "loss": 0.0101807015016675, "step": 6350 }, { "epoch": 1.648753894080997, "grad_norm": 9.315178871154785, "learning_rate": 8.548582302102207e-07, "loss": 0.10206104815006256, "step": 6351 }, { "epoch": 1.6490134994807892, "grad_norm": 8.004886627197266, "learning_rate": 8.543484682249301e-07, "loss": 0.06079729646444321, "step": 6352 }, { "epoch": 1.6492731048805815, "grad_norm": 9.454710006713867, "learning_rate": 8.53839041347426e-07, "loss": 0.08007680624723434, "step": 6353 }, { "epoch": 1.6495327102803738, "grad_norm": 4.408962249755859, "learning_rate": 8.53329949667763e-07, "loss": 0.023715466260910034, "step": 6354 }, { "epoch": 1.6497923156801662, "grad_norm": 10.729987144470215, "learning_rate": 8.528211932759367e-07, "loss": 0.025933358818292618, "step": 6355 }, { "epoch": 1.6500519210799585, "grad_norm": 8.43139934539795, "learning_rate": 8.52312772261884e-07, "loss": 0.02401052415370941, "step": 6356 }, { "epoch": 1.6503115264797508, "grad_norm": 5.750206470489502, "learning_rate": 8.518046867154823e-07, "loss": 0.02945600263774395, "step": 6357 }, { "epoch": 1.650571131879543, "grad_norm": 7.91591739654541, "learning_rate": 8.512969367265483e-07, "loss": 0.13742490112781525, "step": 6358 }, { "epoch": 1.6508307372793354, "grad_norm": 7.961919784545898, "learning_rate": 8.507895223848417e-07, "loss": 0.043364107608795166, "step": 6359 }, { "epoch": 1.6510903426791277, "grad_norm": 11.448613166809082, "learning_rate": 8.502824437800615e-07, "loss": 0.06217917054891586, "step": 6360 }, { "epoch": 1.65134994807892, "grad_norm": 11.303199768066406, "learning_rate": 8.49775701001847e-07, "loss": 0.052019231021404266, "step": 6361 }, { "epoch": 1.6516095534787123, "grad_norm": 10.185041427612305, "learning_rate": 8.492692941397798e-07, "loss": 0.08211716264486313, "step": 6362 }, { "epoch": 1.6518691588785046, "grad_norm": 9.29188060760498, "learning_rate": 8.487632232833798e-07, "loss": 0.08832710981369019, "step": 6363 }, { "epoch": 1.652128764278297, "grad_norm": 9.7089204788208, "learning_rate": 8.482574885221106e-07, "loss": 0.09308703243732452, "step": 6364 }, { "epoch": 1.6523883696780892, "grad_norm": 11.856532096862793, "learning_rate": 8.477520899453719e-07, "loss": 0.033536333590745926, "step": 6365 }, { "epoch": 1.6526479750778815, "grad_norm": 7.322755813598633, "learning_rate": 8.472470276425082e-07, "loss": 0.021297289058566093, "step": 6366 }, { "epoch": 1.6529075804776738, "grad_norm": 6.2468976974487305, "learning_rate": 8.467423017028035e-07, "loss": 0.05009131133556366, "step": 6367 }, { "epoch": 1.6531671858774661, "grad_norm": 10.055206298828125, "learning_rate": 8.462379122154807e-07, "loss": 0.10447120666503906, "step": 6368 }, { "epoch": 1.6534267912772584, "grad_norm": 1.5370404720306396, "learning_rate": 8.457338592697046e-07, "loss": 0.0031402655877172947, "step": 6369 }, { "epoch": 1.6536863966770508, "grad_norm": 3.5212674140930176, "learning_rate": 8.452301429545798e-07, "loss": 0.01562456600368023, "step": 6370 }, { "epoch": 1.653946002076843, "grad_norm": 10.491328239440918, "learning_rate": 8.447267633591525e-07, "loss": 0.047422394156455994, "step": 6371 }, { "epoch": 1.6542056074766354, "grad_norm": 10.861556053161621, "learning_rate": 8.442237205724094e-07, "loss": 0.027298515662550926, "step": 6372 }, { "epoch": 1.6544652128764277, "grad_norm": 5.717190742492676, "learning_rate": 8.437210146832749e-07, "loss": 0.016389526426792145, "step": 6373 }, { "epoch": 1.6547248182762202, "grad_norm": 9.564976692199707, "learning_rate": 8.432186457806175e-07, "loss": 0.04902117699384689, "step": 6374 }, { "epoch": 1.6549844236760125, "grad_norm": 10.579845428466797, "learning_rate": 8.427166139532436e-07, "loss": 0.05926200747489929, "step": 6375 }, { "epoch": 1.6552440290758048, "grad_norm": 6.966303825378418, "learning_rate": 8.422149192899018e-07, "loss": 0.04584728181362152, "step": 6376 }, { "epoch": 1.6555036344755971, "grad_norm": 10.965907096862793, "learning_rate": 8.417135618792799e-07, "loss": 0.04598246142268181, "step": 6377 }, { "epoch": 1.6557632398753894, "grad_norm": 13.57130241394043, "learning_rate": 8.412125418100055e-07, "loss": 0.025046516209840775, "step": 6378 }, { "epoch": 1.6560228452751817, "grad_norm": 9.348356246948242, "learning_rate": 8.407118591706493e-07, "loss": 0.026629116386175156, "step": 6379 }, { "epoch": 1.656282450674974, "grad_norm": 9.335158348083496, "learning_rate": 8.402115140497189e-07, "loss": 0.04002499580383301, "step": 6380 }, { "epoch": 1.6565420560747663, "grad_norm": 9.663758277893066, "learning_rate": 8.397115065356641e-07, "loss": 0.1653650850057602, "step": 6381 }, { "epoch": 1.6568016614745587, "grad_norm": 8.925962448120117, "learning_rate": 8.392118367168757e-07, "loss": 0.08361174911260605, "step": 6382 }, { "epoch": 1.657061266874351, "grad_norm": 7.926258087158203, "learning_rate": 8.38712504681683e-07, "loss": 0.01976502127945423, "step": 6383 }, { "epoch": 1.6573208722741433, "grad_norm": 9.298202514648438, "learning_rate": 8.38213510518357e-07, "loss": 0.06531906127929688, "step": 6384 }, { "epoch": 1.6575804776739356, "grad_norm": 8.685004234313965, "learning_rate": 8.377148543151084e-07, "loss": 0.045951806008815765, "step": 6385 }, { "epoch": 1.657840083073728, "grad_norm": 9.597166061401367, "learning_rate": 8.372165361600876e-07, "loss": 0.042575009167194366, "step": 6386 }, { "epoch": 1.6580996884735204, "grad_norm": 13.6602201461792, "learning_rate": 8.367185561413866e-07, "loss": 0.051644615828990936, "step": 6387 }, { "epoch": 1.6583592938733127, "grad_norm": 10.630000114440918, "learning_rate": 8.362209143470368e-07, "loss": 0.022054096683859825, "step": 6388 }, { "epoch": 1.658618899273105, "grad_norm": 2.350844621658325, "learning_rate": 8.357236108650091e-07, "loss": 0.008244817145168781, "step": 6389 }, { "epoch": 1.6588785046728973, "grad_norm": 6.922889709472656, "learning_rate": 8.352266457832158e-07, "loss": 0.016592107713222504, "step": 6390 }, { "epoch": 1.6591381100726896, "grad_norm": 8.533327102661133, "learning_rate": 8.347300191895097e-07, "loss": 0.03769344836473465, "step": 6391 }, { "epoch": 1.659397715472482, "grad_norm": 10.676796913146973, "learning_rate": 8.342337311716817e-07, "loss": 0.07451440393924713, "step": 6392 }, { "epoch": 1.6596573208722742, "grad_norm": 9.410832405090332, "learning_rate": 8.337377818174651e-07, "loss": 0.11444898694753647, "step": 6393 }, { "epoch": 1.6599169262720666, "grad_norm": 5.993988990783691, "learning_rate": 8.332421712145316e-07, "loss": 0.006396078504621983, "step": 6394 }, { "epoch": 1.6601765316718589, "grad_norm": 9.663595199584961, "learning_rate": 8.327468994504953e-07, "loss": 0.07152866572141647, "step": 6395 }, { "epoch": 1.6604361370716512, "grad_norm": 10.514664649963379, "learning_rate": 8.32251966612907e-07, "loss": 0.042582083493471146, "step": 6396 }, { "epoch": 1.6606957424714435, "grad_norm": 9.944818496704102, "learning_rate": 8.317573727892603e-07, "loss": 0.1650967001914978, "step": 6397 }, { "epoch": 1.6609553478712358, "grad_norm": 8.29255485534668, "learning_rate": 8.312631180669889e-07, "loss": 0.09854674339294434, "step": 6398 }, { "epoch": 1.661214953271028, "grad_norm": 9.367019653320312, "learning_rate": 8.307692025334648e-07, "loss": 0.04552021250128746, "step": 6399 }, { "epoch": 1.6614745586708204, "grad_norm": 8.839824676513672, "learning_rate": 8.302756262760009e-07, "loss": 0.19764269888401031, "step": 6400 }, { "epoch": 1.6617341640706127, "grad_norm": 5.638975620269775, "learning_rate": 8.297823893818502e-07, "loss": 0.01176772452890873, "step": 6401 }, { "epoch": 1.661993769470405, "grad_norm": 6.946890354156494, "learning_rate": 8.292894919382058e-07, "loss": 0.014926988631486893, "step": 6402 }, { "epoch": 1.6622533748701973, "grad_norm": 10.057928085327148, "learning_rate": 8.287969340322017e-07, "loss": 0.12198372185230255, "step": 6403 }, { "epoch": 1.6625129802699896, "grad_norm": 16.043834686279297, "learning_rate": 8.283047157509091e-07, "loss": 0.019415641203522682, "step": 6404 }, { "epoch": 1.662772585669782, "grad_norm": 11.74693775177002, "learning_rate": 8.278128371813423e-07, "loss": 0.0655883178114891, "step": 6405 }, { "epoch": 1.6630321910695742, "grad_norm": 11.028200149536133, "learning_rate": 8.273212984104531e-07, "loss": 0.107967808842659, "step": 6406 }, { "epoch": 1.6632917964693665, "grad_norm": 10.305356979370117, "learning_rate": 8.268300995251353e-07, "loss": 0.021988270804286003, "step": 6407 }, { "epoch": 1.6635514018691588, "grad_norm": 9.845529556274414, "learning_rate": 8.263392406122212e-07, "loss": 0.0660293772816658, "step": 6408 }, { "epoch": 1.6638110072689511, "grad_norm": 8.385414123535156, "learning_rate": 8.258487217584827e-07, "loss": 0.043763309717178345, "step": 6409 }, { "epoch": 1.6640706126687435, "grad_norm": 13.28118896484375, "learning_rate": 8.253585430506333e-07, "loss": 0.03512280434370041, "step": 6410 }, { "epoch": 1.6643302180685358, "grad_norm": 8.420056343078613, "learning_rate": 8.248687045753256e-07, "loss": 0.025157619267702103, "step": 6411 }, { "epoch": 1.664589823468328, "grad_norm": 8.537565231323242, "learning_rate": 8.243792064191503e-07, "loss": 0.1182793602347374, "step": 6412 }, { "epoch": 1.6648494288681204, "grad_norm": 8.722381591796875, "learning_rate": 8.238900486686413e-07, "loss": 0.09691765159368515, "step": 6413 }, { "epoch": 1.6651090342679127, "grad_norm": 10.01906967163086, "learning_rate": 8.234012314102695e-07, "loss": 0.11996135860681534, "step": 6414 }, { "epoch": 1.665368639667705, "grad_norm": 10.15494155883789, "learning_rate": 8.22912754730446e-07, "loss": 0.049347132444381714, "step": 6415 }, { "epoch": 1.6656282450674973, "grad_norm": 9.644288063049316, "learning_rate": 8.224246187155238e-07, "loss": 0.022467797622084618, "step": 6416 }, { "epoch": 1.6658878504672896, "grad_norm": 10.555082321166992, "learning_rate": 8.219368234517927e-07, "loss": 0.03788985311985016, "step": 6417 }, { "epoch": 1.666147455867082, "grad_norm": 10.912786483764648, "learning_rate": 8.21449369025485e-07, "loss": 0.08255480974912643, "step": 6418 }, { "epoch": 1.6664070612668742, "grad_norm": 6.192792892456055, "learning_rate": 8.209622555227709e-07, "loss": 0.008066914044320583, "step": 6419 }, { "epoch": 1.6666666666666665, "grad_norm": 9.471332550048828, "learning_rate": 8.204754830297602e-07, "loss": 0.09623923897743225, "step": 6420 }, { "epoch": 1.6669262720664588, "grad_norm": 6.613889694213867, "learning_rate": 8.199890516325046e-07, "loss": 0.017078761011362076, "step": 6421 }, { "epoch": 1.6671858774662511, "grad_norm": 10.858194351196289, "learning_rate": 8.195029614169934e-07, "loss": 0.046564094722270966, "step": 6422 }, { "epoch": 1.6674454828660437, "grad_norm": 10.83379077911377, "learning_rate": 8.190172124691553e-07, "loss": 0.10509449988603592, "step": 6423 }, { "epoch": 1.667705088265836, "grad_norm": 9.634726524353027, "learning_rate": 8.185318048748611e-07, "loss": 0.03425140678882599, "step": 6424 }, { "epoch": 1.6679646936656283, "grad_norm": 9.813173294067383, "learning_rate": 8.180467387199184e-07, "loss": 0.16654619574546814, "step": 6425 }, { "epoch": 1.6682242990654206, "grad_norm": 11.19595718383789, "learning_rate": 8.175620140900774e-07, "loss": 0.056436579674482346, "step": 6426 }, { "epoch": 1.6684839044652129, "grad_norm": 4.956009387969971, "learning_rate": 8.170776310710246e-07, "loss": 0.01203225553035736, "step": 6427 }, { "epoch": 1.6687435098650052, "grad_norm": 4.540051460266113, "learning_rate": 8.165935897483881e-07, "loss": 0.00664316164329648, "step": 6428 }, { "epoch": 1.6690031152647975, "grad_norm": 11.417351722717285, "learning_rate": 8.161098902077366e-07, "loss": 0.05267181247472763, "step": 6429 }, { "epoch": 1.6692627206645898, "grad_norm": 10.912347793579102, "learning_rate": 8.156265325345764e-07, "loss": 0.04838843643665314, "step": 6430 }, { "epoch": 1.6695223260643821, "grad_norm": 11.619688987731934, "learning_rate": 8.151435168143537e-07, "loss": 0.10308708250522614, "step": 6431 }, { "epoch": 1.6697819314641744, "grad_norm": 10.115438461303711, "learning_rate": 8.146608431324548e-07, "loss": 0.020872291177511215, "step": 6432 }, { "epoch": 1.6700415368639667, "grad_norm": 8.547294616699219, "learning_rate": 8.141785115742049e-07, "loss": 0.16471654176712036, "step": 6433 }, { "epoch": 1.670301142263759, "grad_norm": 9.026678085327148, "learning_rate": 8.136965222248713e-07, "loss": 0.02545803412795067, "step": 6434 }, { "epoch": 1.6705607476635516, "grad_norm": 10.086118698120117, "learning_rate": 8.132148751696556e-07, "loss": 0.07432136684656143, "step": 6435 }, { "epoch": 1.6708203530633439, "grad_norm": 9.232229232788086, "learning_rate": 8.127335704937042e-07, "loss": 0.09757234156131744, "step": 6436 }, { "epoch": 1.6710799584631362, "grad_norm": 10.347338676452637, "learning_rate": 8.122526082820994e-07, "loss": 0.12523533403873444, "step": 6437 }, { "epoch": 1.6713395638629285, "grad_norm": 11.047740936279297, "learning_rate": 8.117719886198655e-07, "loss": 0.07034695148468018, "step": 6438 }, { "epoch": 1.6715991692627208, "grad_norm": 19.087677001953125, "learning_rate": 8.112917115919644e-07, "loss": 0.0972512811422348, "step": 6439 }, { "epoch": 1.671858774662513, "grad_norm": 7.077968120574951, "learning_rate": 8.108117772832977e-07, "loss": 0.056568585336208344, "step": 6440 }, { "epoch": 1.6721183800623054, "grad_norm": 12.017054557800293, "learning_rate": 8.103321857787077e-07, "loss": 0.08811589330434799, "step": 6441 }, { "epoch": 1.6723779854620977, "grad_norm": 9.645620346069336, "learning_rate": 8.09852937162975e-07, "loss": 0.055608563125133514, "step": 6442 }, { "epoch": 1.67263759086189, "grad_norm": 11.509795188903809, "learning_rate": 8.093740315208188e-07, "loss": 0.09919033944606781, "step": 6443 }, { "epoch": 1.6728971962616823, "grad_norm": 9.355026245117188, "learning_rate": 8.088954689368999e-07, "loss": 0.0527348592877388, "step": 6444 }, { "epoch": 1.6731568016614746, "grad_norm": 8.510951042175293, "learning_rate": 8.084172494958168e-07, "loss": 0.019670061767101288, "step": 6445 }, { "epoch": 1.673416407061267, "grad_norm": 11.527682304382324, "learning_rate": 8.07939373282107e-07, "loss": 0.054198410362005234, "step": 6446 }, { "epoch": 1.6736760124610592, "grad_norm": 8.720733642578125, "learning_rate": 8.074618403802494e-07, "loss": 0.010057179257273674, "step": 6447 }, { "epoch": 1.6739356178608515, "grad_norm": 9.310404777526855, "learning_rate": 8.069846508746594e-07, "loss": 0.0918484479188919, "step": 6448 }, { "epoch": 1.6741952232606438, "grad_norm": 9.136397361755371, "learning_rate": 8.065078048496946e-07, "loss": 0.01562462653964758, "step": 6449 }, { "epoch": 1.6744548286604362, "grad_norm": 6.4177632331848145, "learning_rate": 8.060313023896499e-07, "loss": 0.021630942821502686, "step": 6450 }, { "epoch": 1.6747144340602285, "grad_norm": 8.849235534667969, "learning_rate": 8.055551435787595e-07, "loss": 0.06347554922103882, "step": 6451 }, { "epoch": 1.6749740394600208, "grad_norm": 3.7188658714294434, "learning_rate": 8.050793285011983e-07, "loss": 0.019215591251850128, "step": 6452 }, { "epoch": 1.675233644859813, "grad_norm": 2.806198835372925, "learning_rate": 8.04603857241079e-07, "loss": 0.008162938058376312, "step": 6453 }, { "epoch": 1.6754932502596054, "grad_norm": 4.599464416503906, "learning_rate": 8.041287298824535e-07, "loss": 0.018435342237353325, "step": 6454 }, { "epoch": 1.6757528556593977, "grad_norm": 8.630075454711914, "learning_rate": 8.036539465093146e-07, "loss": 0.028402039781212807, "step": 6455 }, { "epoch": 1.67601246105919, "grad_norm": 6.559454917907715, "learning_rate": 8.031795072055921e-07, "loss": 0.024577546864748, "step": 6456 }, { "epoch": 1.6762720664589823, "grad_norm": 10.895296096801758, "learning_rate": 8.027054120551572e-07, "loss": 0.023629143834114075, "step": 6457 }, { "epoch": 1.6765316718587746, "grad_norm": 11.539310455322266, "learning_rate": 8.022316611418176e-07, "loss": 0.06327514350414276, "step": 6458 }, { "epoch": 1.676791277258567, "grad_norm": 8.902460098266602, "learning_rate": 8.017582545493221e-07, "loss": 0.026141518726944923, "step": 6459 }, { "epoch": 1.6770508826583592, "grad_norm": 8.710428237915039, "learning_rate": 8.01285192361359e-07, "loss": 0.06807292252779007, "step": 6460 }, { "epoch": 1.6773104880581515, "grad_norm": 8.78219223022461, "learning_rate": 8.008124746615542e-07, "loss": 0.02353627234697342, "step": 6461 }, { "epoch": 1.6775700934579438, "grad_norm": 8.525876998901367, "learning_rate": 8.003401015334734e-07, "loss": 0.023408222943544388, "step": 6462 }, { "epoch": 1.6778296988577361, "grad_norm": 9.908795356750488, "learning_rate": 7.99868073060621e-07, "loss": 0.015866750851273537, "step": 6463 }, { "epoch": 1.6780893042575284, "grad_norm": 9.253023147583008, "learning_rate": 7.99396389326441e-07, "loss": 0.03387821838259697, "step": 6464 }, { "epoch": 1.6783489096573208, "grad_norm": 10.215862274169922, "learning_rate": 7.989250504143174e-07, "loss": 0.11169233918190002, "step": 6465 }, { "epoch": 1.678608515057113, "grad_norm": 6.679493427276611, "learning_rate": 7.984540564075702e-07, "loss": 0.018459388986229897, "step": 6466 }, { "epoch": 1.6788681204569054, "grad_norm": 11.74686050415039, "learning_rate": 7.979834073894621e-07, "loss": 0.0454525351524353, "step": 6467 }, { "epoch": 1.6791277258566977, "grad_norm": 9.04555606842041, "learning_rate": 7.975131034431917e-07, "loss": 0.05650131031870842, "step": 6468 }, { "epoch": 1.67938733125649, "grad_norm": 9.916043281555176, "learning_rate": 7.970431446518991e-07, "loss": 0.09812243282794952, "step": 6469 }, { "epoch": 1.6796469366562823, "grad_norm": 12.250697135925293, "learning_rate": 7.965735310986615e-07, "loss": 0.035225193947553635, "step": 6470 }, { "epoch": 1.6799065420560748, "grad_norm": 9.995577812194824, "learning_rate": 7.961042628664958e-07, "loss": 0.04578356444835663, "step": 6471 }, { "epoch": 1.6801661474558671, "grad_norm": 12.815237998962402, "learning_rate": 7.956353400383586e-07, "loss": 0.07435629516839981, "step": 6472 }, { "epoch": 1.6804257528556594, "grad_norm": 8.756601333618164, "learning_rate": 7.951667626971443e-07, "loss": 0.02569476142525673, "step": 6473 }, { "epoch": 1.6806853582554517, "grad_norm": 9.53547477722168, "learning_rate": 7.94698530925686e-07, "loss": 0.057232581079006195, "step": 6474 }, { "epoch": 1.680944963655244, "grad_norm": 8.92676067352295, "learning_rate": 7.942306448067574e-07, "loss": 0.08436176925897598, "step": 6475 }, { "epoch": 1.6812045690550363, "grad_norm": 8.961762428283691, "learning_rate": 7.937631044230699e-07, "loss": 0.0320679247379303, "step": 6476 }, { "epoch": 1.6814641744548287, "grad_norm": 11.366193771362305, "learning_rate": 7.932959098572731e-07, "loss": 0.06691768020391464, "step": 6477 }, { "epoch": 1.681723779854621, "grad_norm": 6.258442401885986, "learning_rate": 7.928290611919573e-07, "loss": 0.0184018611907959, "step": 6478 }, { "epoch": 1.6819833852544133, "grad_norm": 8.11243724822998, "learning_rate": 7.923625585096496e-07, "loss": 0.04778815805912018, "step": 6479 }, { "epoch": 1.6822429906542056, "grad_norm": 6.000070571899414, "learning_rate": 7.91896401892818e-07, "loss": 0.02608497068285942, "step": 6480 }, { "epoch": 1.6825025960539979, "grad_norm": 8.52530574798584, "learning_rate": 7.914305914238682e-07, "loss": 0.020748328417539597, "step": 6481 }, { "epoch": 1.6827622014537902, "grad_norm": 7.473196506500244, "learning_rate": 7.909651271851438e-07, "loss": 0.048779428005218506, "step": 6482 }, { "epoch": 1.6830218068535827, "grad_norm": 12.119928359985352, "learning_rate": 7.905000092589296e-07, "loss": 0.0577440969645977, "step": 6483 }, { "epoch": 1.683281412253375, "grad_norm": 15.71175479888916, "learning_rate": 7.900352377274471e-07, "loss": 0.04611203446984291, "step": 6484 }, { "epoch": 1.6835410176531673, "grad_norm": 3.556260347366333, "learning_rate": 7.895708126728569e-07, "loss": 0.006605756469070911, "step": 6485 }, { "epoch": 1.6838006230529596, "grad_norm": 8.963858604431152, "learning_rate": 7.891067341772596e-07, "loss": 0.03527802228927612, "step": 6486 }, { "epoch": 1.684060228452752, "grad_norm": 8.126330375671387, "learning_rate": 7.886430023226927e-07, "loss": 0.008430455811321735, "step": 6487 }, { "epoch": 1.6843198338525442, "grad_norm": 3.2811269760131836, "learning_rate": 7.881796171911349e-07, "loss": 0.020177442580461502, "step": 6488 }, { "epoch": 1.6845794392523366, "grad_norm": 13.084159851074219, "learning_rate": 7.877165788644998e-07, "loss": 0.01895056664943695, "step": 6489 }, { "epoch": 1.6848390446521289, "grad_norm": 5.581074237823486, "learning_rate": 7.872538874246436e-07, "loss": 0.036392103880643845, "step": 6490 }, { "epoch": 1.6850986500519212, "grad_norm": 6.386736869812012, "learning_rate": 7.867915429533596e-07, "loss": 0.024605553597211838, "step": 6491 }, { "epoch": 1.6853582554517135, "grad_norm": 8.183507919311523, "learning_rate": 7.863295455323791e-07, "loss": 0.1885516345500946, "step": 6492 }, { "epoch": 1.6856178608515058, "grad_norm": 11.438322067260742, "learning_rate": 7.85867895243373e-07, "loss": 0.09086543321609497, "step": 6493 }, { "epoch": 1.685877466251298, "grad_norm": 7.9869608879089355, "learning_rate": 7.854065921679499e-07, "loss": 0.028608785942196846, "step": 6494 }, { "epoch": 1.6861370716510904, "grad_norm": 7.5426554679870605, "learning_rate": 7.849456363876579e-07, "loss": 0.07718035578727722, "step": 6495 }, { "epoch": 1.6863966770508827, "grad_norm": 7.864658832550049, "learning_rate": 7.844850279839847e-07, "loss": 0.12962420284748077, "step": 6496 }, { "epoch": 1.686656282450675, "grad_norm": 9.022557258605957, "learning_rate": 7.84024767038353e-07, "loss": 0.0776449516415596, "step": 6497 }, { "epoch": 1.6869158878504673, "grad_norm": 9.536027908325195, "learning_rate": 7.835648536321285e-07, "loss": 0.05162174999713898, "step": 6498 }, { "epoch": 1.6871754932502596, "grad_norm": 10.13976764678955, "learning_rate": 7.831052878466124e-07, "loss": 0.07791057974100113, "step": 6499 }, { "epoch": 1.687435098650052, "grad_norm": 4.9045090675354, "learning_rate": 7.826460697630449e-07, "loss": 0.031435705721378326, "step": 6500 }, { "epoch": 1.6876947040498442, "grad_norm": 7.238372325897217, "learning_rate": 7.821871994626062e-07, "loss": 0.025324080139398575, "step": 6501 }, { "epoch": 1.6879543094496365, "grad_norm": 6.5977864265441895, "learning_rate": 7.817286770264134e-07, "loss": 0.018745213747024536, "step": 6502 }, { "epoch": 1.6882139148494288, "grad_norm": 8.167784690856934, "learning_rate": 7.812705025355234e-07, "loss": 0.11253560334444046, "step": 6503 }, { "epoch": 1.6884735202492211, "grad_norm": 9.938932418823242, "learning_rate": 7.808126760709309e-07, "loss": 0.012636656872928143, "step": 6504 }, { "epoch": 1.6887331256490135, "grad_norm": 7.457326889038086, "learning_rate": 7.803551977135681e-07, "loss": 0.01431664265692234, "step": 6505 }, { "epoch": 1.6889927310488058, "grad_norm": 8.094405174255371, "learning_rate": 7.798980675443079e-07, "loss": 0.033312007784843445, "step": 6506 }, { "epoch": 1.689252336448598, "grad_norm": 5.253124713897705, "learning_rate": 7.794412856439602e-07, "loss": 0.02153775840997696, "step": 6507 }, { "epoch": 1.6895119418483904, "grad_norm": 5.8709893226623535, "learning_rate": 7.789848520932729e-07, "loss": 0.03855925798416138, "step": 6508 }, { "epoch": 1.6897715472481827, "grad_norm": 5.172524929046631, "learning_rate": 7.785287669729338e-07, "loss": 0.023166341707110405, "step": 6509 }, { "epoch": 1.690031152647975, "grad_norm": 11.329113960266113, "learning_rate": 7.780730303635675e-07, "loss": 0.03909459337592125, "step": 6510 }, { "epoch": 1.6902907580477673, "grad_norm": 6.929095268249512, "learning_rate": 7.776176423457391e-07, "loss": 0.006320637185126543, "step": 6511 }, { "epoch": 1.6905503634475596, "grad_norm": 10.172262191772461, "learning_rate": 7.771626029999496e-07, "loss": 0.05292468145489693, "step": 6512 }, { "epoch": 1.690809968847352, "grad_norm": 7.210566520690918, "learning_rate": 7.767079124066397e-07, "loss": 0.015520143322646618, "step": 6513 }, { "epoch": 1.6910695742471442, "grad_norm": 8.204598426818848, "learning_rate": 7.762535706461887e-07, "loss": 0.02883993089199066, "step": 6514 }, { "epoch": 1.6913291796469365, "grad_norm": 6.753733158111572, "learning_rate": 7.757995777989139e-07, "loss": 0.009151961654424667, "step": 6515 }, { "epoch": 1.6915887850467288, "grad_norm": 9.307780265808105, "learning_rate": 7.753459339450699e-07, "loss": 0.06927160918712616, "step": 6516 }, { "epoch": 1.6918483904465211, "grad_norm": 9.813838958740234, "learning_rate": 7.748926391648516e-07, "loss": 0.061301156878471375, "step": 6517 }, { "epoch": 1.6921079958463134, "grad_norm": 4.104682445526123, "learning_rate": 7.744396935383904e-07, "loss": 0.010946821421384811, "step": 6518 }, { "epoch": 1.692367601246106, "grad_norm": 0.42658862471580505, "learning_rate": 7.739870971457581e-07, "loss": 0.0015253007877618074, "step": 6519 }, { "epoch": 1.6926272066458983, "grad_norm": 7.670013427734375, "learning_rate": 7.735348500669611e-07, "loss": 0.02704353630542755, "step": 6520 }, { "epoch": 1.6928868120456906, "grad_norm": 5.7877702713012695, "learning_rate": 7.730829523819477e-07, "loss": 0.01903851144015789, "step": 6521 }, { "epoch": 1.6931464174454829, "grad_norm": 11.422205924987793, "learning_rate": 7.726314041706031e-07, "loss": 0.052768148481845856, "step": 6522 }, { "epoch": 1.6934060228452752, "grad_norm": 4.324800491333008, "learning_rate": 7.721802055127509e-07, "loss": 0.02001103200018406, "step": 6523 }, { "epoch": 1.6936656282450675, "grad_norm": 2.665938377380371, "learning_rate": 7.717293564881521e-07, "loss": 0.005276505835354328, "step": 6524 }, { "epoch": 1.6939252336448598, "grad_norm": 9.929649353027344, "learning_rate": 7.712788571765065e-07, "loss": 0.11879859119653702, "step": 6525 }, { "epoch": 1.6941848390446521, "grad_norm": 10.705199241638184, "learning_rate": 7.708287076574523e-07, "loss": 0.0263671875, "step": 6526 }, { "epoch": 1.6944444444444444, "grad_norm": 5.437097072601318, "learning_rate": 7.703789080105657e-07, "loss": 0.03100660629570484, "step": 6527 }, { "epoch": 1.6947040498442367, "grad_norm": 7.963646411895752, "learning_rate": 7.699294583153605e-07, "loss": 0.07692263275384903, "step": 6528 }, { "epoch": 1.694963655244029, "grad_norm": 8.230506896972656, "learning_rate": 7.694803586512899e-07, "loss": 0.057095762342214584, "step": 6529 }, { "epoch": 1.6952232606438213, "grad_norm": 8.118553161621094, "learning_rate": 7.690316090977437e-07, "loss": 0.048698000609874725, "step": 6530 }, { "epoch": 1.6954828660436139, "grad_norm": 6.859965801239014, "learning_rate": 7.685832097340508e-07, "loss": 0.018812604248523712, "step": 6531 }, { "epoch": 1.6957424714434062, "grad_norm": 9.883479118347168, "learning_rate": 7.681351606394784e-07, "loss": 0.06032857298851013, "step": 6532 }, { "epoch": 1.6960020768431985, "grad_norm": 8.062353134155273, "learning_rate": 7.676874618932302e-07, "loss": 0.06990055739879608, "step": 6533 }, { "epoch": 1.6962616822429908, "grad_norm": 8.027473449707031, "learning_rate": 7.672401135744503e-07, "loss": 0.06777503341436386, "step": 6534 }, { "epoch": 1.696521287642783, "grad_norm": 6.974035263061523, "learning_rate": 7.667931157622192e-07, "loss": 0.030880700796842575, "step": 6535 }, { "epoch": 1.6967808930425754, "grad_norm": 7.507722854614258, "learning_rate": 7.663464685355555e-07, "loss": 0.056970592588186264, "step": 6536 }, { "epoch": 1.6970404984423677, "grad_norm": 6.214605808258057, "learning_rate": 7.65900171973417e-07, "loss": 0.016381099820137024, "step": 6537 }, { "epoch": 1.69730010384216, "grad_norm": 8.564210891723633, "learning_rate": 7.65454226154698e-07, "loss": 0.055662523955106735, "step": 6538 }, { "epoch": 1.6975597092419523, "grad_norm": 5.7254109382629395, "learning_rate": 7.650086311582314e-07, "loss": 0.00720871239900589, "step": 6539 }, { "epoch": 1.6978193146417446, "grad_norm": 9.734319686889648, "learning_rate": 7.645633870627889e-07, "loss": 0.08002924919128418, "step": 6540 }, { "epoch": 1.698078920041537, "grad_norm": 5.794570446014404, "learning_rate": 7.641184939470788e-07, "loss": 0.02031293325126171, "step": 6541 }, { "epoch": 1.6983385254413292, "grad_norm": 6.37791633605957, "learning_rate": 7.636739518897488e-07, "loss": 0.028835248202085495, "step": 6542 }, { "epoch": 1.6985981308411215, "grad_norm": 8.483884811401367, "learning_rate": 7.632297609693828e-07, "loss": 0.04254892095923424, "step": 6543 }, { "epoch": 1.6988577362409139, "grad_norm": 7.521839618682861, "learning_rate": 7.627859212645041e-07, "loss": 0.024735601618885994, "step": 6544 }, { "epoch": 1.6991173416407062, "grad_norm": 7.9251861572265625, "learning_rate": 7.623424328535738e-07, "loss": 0.03667890653014183, "step": 6545 }, { "epoch": 1.6993769470404985, "grad_norm": 8.90410327911377, "learning_rate": 7.618992958149897e-07, "loss": 0.02582428976893425, "step": 6546 }, { "epoch": 1.6996365524402908, "grad_norm": 10.103979110717773, "learning_rate": 7.614565102270885e-07, "loss": 0.04351779818534851, "step": 6547 }, { "epoch": 1.699896157840083, "grad_norm": 4.5724663734436035, "learning_rate": 7.610140761681449e-07, "loss": 0.03477779030799866, "step": 6548 }, { "epoch": 1.7001557632398754, "grad_norm": 11.109112739562988, "learning_rate": 7.605719937163705e-07, "loss": 0.028484124690294266, "step": 6549 }, { "epoch": 1.7004153686396677, "grad_norm": 9.240252494812012, "learning_rate": 7.601302629499168e-07, "loss": 0.021944211795926094, "step": 6550 }, { "epoch": 1.70067497403946, "grad_norm": 6.808456897735596, "learning_rate": 7.596888839468696e-07, "loss": 0.01682794652879238, "step": 6551 }, { "epoch": 1.7009345794392523, "grad_norm": 6.59945011138916, "learning_rate": 7.592478567852557e-07, "loss": 0.03842554986476898, "step": 6552 }, { "epoch": 1.7011941848390446, "grad_norm": 11.907785415649414, "learning_rate": 7.588071815430393e-07, "loss": 0.03220716118812561, "step": 6553 }, { "epoch": 1.701453790238837, "grad_norm": 12.448650360107422, "learning_rate": 7.583668582981202e-07, "loss": 0.0643838495016098, "step": 6554 }, { "epoch": 1.7017133956386292, "grad_norm": 8.913719177246094, "learning_rate": 7.579268871283385e-07, "loss": 0.09904658794403076, "step": 6555 }, { "epoch": 1.7019730010384215, "grad_norm": 9.127758026123047, "learning_rate": 7.574872681114705e-07, "loss": 0.020373811945319176, "step": 6556 }, { "epoch": 1.7022326064382138, "grad_norm": 8.792866706848145, "learning_rate": 7.570480013252313e-07, "loss": 0.03824666142463684, "step": 6557 }, { "epoch": 1.7024922118380061, "grad_norm": 11.75577163696289, "learning_rate": 7.566090868472728e-07, "loss": 0.023326056078076363, "step": 6558 }, { "epoch": 1.7027518172377984, "grad_norm": 3.2877964973449707, "learning_rate": 7.56170524755185e-07, "loss": 0.013785608112812042, "step": 6559 }, { "epoch": 1.7030114226375908, "grad_norm": 6.541566371917725, "learning_rate": 7.557323151264958e-07, "loss": 0.024725334718823433, "step": 6560 }, { "epoch": 1.703271028037383, "grad_norm": 7.450356483459473, "learning_rate": 7.552944580386709e-07, "loss": 0.034017160534858704, "step": 6561 }, { "epoch": 1.7035306334371754, "grad_norm": 0.632963240146637, "learning_rate": 7.548569535691127e-07, "loss": 0.0009375577792525291, "step": 6562 }, { "epoch": 1.7037902388369677, "grad_norm": 4.422078609466553, "learning_rate": 7.544198017951626e-07, "loss": 0.0060905287973582745, "step": 6563 }, { "epoch": 1.70404984423676, "grad_norm": 5.4742560386657715, "learning_rate": 7.539830027940986e-07, "loss": 0.007475641556084156, "step": 6564 }, { "epoch": 1.7043094496365523, "grad_norm": 2.016422986984253, "learning_rate": 7.535465566431374e-07, "loss": 0.0029909536242485046, "step": 6565 }, { "epoch": 1.7045690550363446, "grad_norm": 8.887380599975586, "learning_rate": 7.531104634194323e-07, "loss": 0.1416856050491333, "step": 6566 }, { "epoch": 1.7048286604361371, "grad_norm": 8.738395690917969, "learning_rate": 7.526747232000737e-07, "loss": 0.14311537146568298, "step": 6567 }, { "epoch": 1.7050882658359294, "grad_norm": 6.825820446014404, "learning_rate": 7.522393360620922e-07, "loss": 0.014771008864045143, "step": 6568 }, { "epoch": 1.7053478712357217, "grad_norm": 6.568090438842773, "learning_rate": 7.518043020824535e-07, "loss": 0.03621537238359451, "step": 6569 }, { "epoch": 1.705607476635514, "grad_norm": 10.201072692871094, "learning_rate": 7.513696213380608e-07, "loss": 0.02870437130331993, "step": 6570 }, { "epoch": 1.7058670820353063, "grad_norm": 10.508028984069824, "learning_rate": 7.509352939057573e-07, "loss": 0.08603546023368835, "step": 6571 }, { "epoch": 1.7061266874350987, "grad_norm": 9.75034236907959, "learning_rate": 7.505013198623207e-07, "loss": 0.05481555685400963, "step": 6572 }, { "epoch": 1.706386292834891, "grad_norm": 5.130714416503906, "learning_rate": 7.500676992844686e-07, "loss": 0.013835100457072258, "step": 6573 }, { "epoch": 1.7066458982346833, "grad_norm": 4.844119548797607, "learning_rate": 7.49634432248855e-07, "loss": 0.01300264336168766, "step": 6574 }, { "epoch": 1.7069055036344756, "grad_norm": 13.252559661865234, "learning_rate": 7.492015188320711e-07, "loss": 0.07643651217222214, "step": 6575 }, { "epoch": 1.7071651090342679, "grad_norm": 7.730420112609863, "learning_rate": 7.487689591106467e-07, "loss": 0.043731726706027985, "step": 6576 }, { "epoch": 1.7074247144340602, "grad_norm": 10.21704387664795, "learning_rate": 7.483367531610483e-07, "loss": 0.04798579216003418, "step": 6577 }, { "epoch": 1.7076843198338525, "grad_norm": 9.2091646194458, "learning_rate": 7.479049010596795e-07, "loss": 0.10644272714853287, "step": 6578 }, { "epoch": 1.707943925233645, "grad_norm": 11.254587173461914, "learning_rate": 7.474734028828828e-07, "loss": 0.17949238419532776, "step": 6579 }, { "epoch": 1.7082035306334373, "grad_norm": 10.834129333496094, "learning_rate": 7.470422587069368e-07, "loss": 0.14419235289096832, "step": 6580 }, { "epoch": 1.7084631360332296, "grad_norm": 8.002863883972168, "learning_rate": 7.466114686080576e-07, "loss": 0.042989011853933334, "step": 6581 }, { "epoch": 1.708722741433022, "grad_norm": 10.41833209991455, "learning_rate": 7.461810326623988e-07, "loss": 0.03026139736175537, "step": 6582 }, { "epoch": 1.7089823468328142, "grad_norm": 12.262764930725098, "learning_rate": 7.457509509460522e-07, "loss": 0.026164043694734573, "step": 6583 }, { "epoch": 1.7092419522326066, "grad_norm": 10.318960189819336, "learning_rate": 7.453212235350471e-07, "loss": 0.03486372530460358, "step": 6584 }, { "epoch": 1.7095015576323989, "grad_norm": 7.336367130279541, "learning_rate": 7.448918505053476e-07, "loss": 0.012027577497065067, "step": 6585 }, { "epoch": 1.7097611630321912, "grad_norm": 7.173542499542236, "learning_rate": 7.444628319328586e-07, "loss": 0.012487221509218216, "step": 6586 }, { "epoch": 1.7100207684319835, "grad_norm": 12.297802925109863, "learning_rate": 7.440341678934197e-07, "loss": 0.020007189363241196, "step": 6587 }, { "epoch": 1.7102803738317758, "grad_norm": 10.850003242492676, "learning_rate": 7.436058584628098e-07, "loss": 0.05752135068178177, "step": 6588 }, { "epoch": 1.710539979231568, "grad_norm": 7.098777770996094, "learning_rate": 7.431779037167437e-07, "loss": 0.012069507502019405, "step": 6589 }, { "epoch": 1.7107995846313604, "grad_norm": 6.404893398284912, "learning_rate": 7.42750303730874e-07, "loss": 0.028123609721660614, "step": 6590 }, { "epoch": 1.7110591900311527, "grad_norm": 7.376404285430908, "learning_rate": 7.423230585807907e-07, "loss": 0.06037630885839462, "step": 6591 }, { "epoch": 1.711318795430945, "grad_norm": 8.587696075439453, "learning_rate": 7.418961683420211e-07, "loss": 0.014219307340681553, "step": 6592 }, { "epoch": 1.7115784008307373, "grad_norm": 5.82539701461792, "learning_rate": 7.414696330900291e-07, "loss": 0.008495084010064602, "step": 6593 }, { "epoch": 1.7118380062305296, "grad_norm": 9.916136741638184, "learning_rate": 7.410434529002172e-07, "loss": 0.11476971954107285, "step": 6594 }, { "epoch": 1.712097611630322, "grad_norm": 5.7161383628845215, "learning_rate": 7.406176278479232e-07, "loss": 0.01697319559752941, "step": 6595 }, { "epoch": 1.7123572170301142, "grad_norm": 9.433913230895996, "learning_rate": 7.401921580084244e-07, "loss": 0.06432973593473434, "step": 6596 }, { "epoch": 1.7126168224299065, "grad_norm": 8.355850219726562, "learning_rate": 7.397670434569335e-07, "loss": 0.0465003065764904, "step": 6597 }, { "epoch": 1.7128764278296988, "grad_norm": 5.076743125915527, "learning_rate": 7.393422842686008e-07, "loss": 0.010578572750091553, "step": 6598 }, { "epoch": 1.7131360332294912, "grad_norm": 6.634745121002197, "learning_rate": 7.389178805185145e-07, "loss": 0.03502010181546211, "step": 6599 }, { "epoch": 1.7133956386292835, "grad_norm": 7.818234920501709, "learning_rate": 7.384938322816995e-07, "loss": 0.13184696435928345, "step": 6600 }, { "epoch": 1.7136552440290758, "grad_norm": 9.248495101928711, "learning_rate": 7.380701396331168e-07, "loss": 0.17774415016174316, "step": 6601 }, { "epoch": 1.713914849428868, "grad_norm": 8.379435539245605, "learning_rate": 7.376468026476669e-07, "loss": 0.03655649721622467, "step": 6602 }, { "epoch": 1.7141744548286604, "grad_norm": 9.767821311950684, "learning_rate": 7.372238214001852e-07, "loss": 0.011488907970488071, "step": 6603 }, { "epoch": 1.7144340602284527, "grad_norm": 8.193958282470703, "learning_rate": 7.368011959654456e-07, "loss": 0.05205681174993515, "step": 6604 }, { "epoch": 1.714693665628245, "grad_norm": 4.476260185241699, "learning_rate": 7.363789264181586e-07, "loss": 0.008355260826647282, "step": 6605 }, { "epoch": 1.7149532710280373, "grad_norm": 7.0706939697265625, "learning_rate": 7.359570128329711e-07, "loss": 0.014445215463638306, "step": 6606 }, { "epoch": 1.7152128764278296, "grad_norm": 10.220410346984863, "learning_rate": 7.355354552844693e-07, "loss": 0.030016206204891205, "step": 6607 }, { "epoch": 1.715472481827622, "grad_norm": 9.275341033935547, "learning_rate": 7.351142538471728e-07, "loss": 0.09139207750558853, "step": 6608 }, { "epoch": 1.7157320872274142, "grad_norm": 3.663374423980713, "learning_rate": 7.346934085955416e-07, "loss": 0.012564465403556824, "step": 6609 }, { "epoch": 1.7159916926272065, "grad_norm": 8.500539779663086, "learning_rate": 7.342729196039716e-07, "loss": 0.01713993214070797, "step": 6610 }, { "epoch": 1.7162512980269988, "grad_norm": 10.124252319335938, "learning_rate": 7.338527869467954e-07, "loss": 0.1386171281337738, "step": 6611 }, { "epoch": 1.7165109034267911, "grad_norm": 7.429091453552246, "learning_rate": 7.33433010698283e-07, "loss": 0.034698259085416794, "step": 6612 }, { "epoch": 1.7167705088265834, "grad_norm": 8.723939895629883, "learning_rate": 7.330135909326405e-07, "loss": 0.09832842648029327, "step": 6613 }, { "epoch": 1.7170301142263757, "grad_norm": 7.455139636993408, "learning_rate": 7.325945277240124e-07, "loss": 0.022775650024414062, "step": 6614 }, { "epoch": 1.7172897196261683, "grad_norm": 10.234095573425293, "learning_rate": 7.3217582114648e-07, "loss": 0.0510353222489357, "step": 6615 }, { "epoch": 1.7175493250259606, "grad_norm": 9.796673774719238, "learning_rate": 7.317574712740595e-07, "loss": 0.06040492281317711, "step": 6616 }, { "epoch": 1.717808930425753, "grad_norm": 10.112713813781738, "learning_rate": 7.313394781807066e-07, "loss": 0.18004944920539856, "step": 6617 }, { "epoch": 1.7180685358255452, "grad_norm": 7.859908103942871, "learning_rate": 7.309218419403132e-07, "loss": 0.006309324875473976, "step": 6618 }, { "epoch": 1.7183281412253375, "grad_norm": 8.058234214782715, "learning_rate": 7.305045626267074e-07, "loss": 0.015686994418501854, "step": 6619 }, { "epoch": 1.7185877466251298, "grad_norm": 5.382007598876953, "learning_rate": 7.300876403136544e-07, "loss": 0.01290139276534319, "step": 6620 }, { "epoch": 1.7188473520249221, "grad_norm": 10.672730445861816, "learning_rate": 7.296710750748563e-07, "loss": 0.14282722771167755, "step": 6621 }, { "epoch": 1.7191069574247144, "grad_norm": 8.729373931884766, "learning_rate": 7.292548669839531e-07, "loss": 0.02578362450003624, "step": 6622 }, { "epoch": 1.7193665628245067, "grad_norm": 3.7515532970428467, "learning_rate": 7.288390161145209e-07, "loss": 0.0117377620190382, "step": 6623 }, { "epoch": 1.719626168224299, "grad_norm": 9.41771411895752, "learning_rate": 7.284235225400716e-07, "loss": 0.05066775903105736, "step": 6624 }, { "epoch": 1.7198857736240913, "grad_norm": 2.1050031185150146, "learning_rate": 7.280083863340559e-07, "loss": 0.005827879533171654, "step": 6625 }, { "epoch": 1.7201453790238836, "grad_norm": 8.87158489227295, "learning_rate": 7.275936075698597e-07, "loss": 0.024216709658503532, "step": 6626 }, { "epoch": 1.7204049844236762, "grad_norm": 1.9508862495422363, "learning_rate": 7.271791863208067e-07, "loss": 0.02565173991024494, "step": 6627 }, { "epoch": 1.7206645898234685, "grad_norm": 10.735548973083496, "learning_rate": 7.267651226601577e-07, "loss": 0.1227492019534111, "step": 6628 }, { "epoch": 1.7209241952232608, "grad_norm": 3.9258220195770264, "learning_rate": 7.263514166611083e-07, "loss": 0.03063666820526123, "step": 6629 }, { "epoch": 1.721183800623053, "grad_norm": 9.323589324951172, "learning_rate": 7.259380683967936e-07, "loss": 0.17547297477722168, "step": 6630 }, { "epoch": 1.7214434060228454, "grad_norm": 10.096756935119629, "learning_rate": 7.255250779402835e-07, "loss": 0.023840801790356636, "step": 6631 }, { "epoch": 1.7217030114226377, "grad_norm": 6.285518169403076, "learning_rate": 7.251124453645849e-07, "loss": 0.011835440061986446, "step": 6632 }, { "epoch": 1.72196261682243, "grad_norm": 8.491545677185059, "learning_rate": 7.247001707426424e-07, "loss": 0.05765689164400101, "step": 6633 }, { "epoch": 1.7222222222222223, "grad_norm": 9.12039566040039, "learning_rate": 7.242882541473367e-07, "loss": 0.036857970058918, "step": 6634 }, { "epoch": 1.7224818276220146, "grad_norm": 4.221169948577881, "learning_rate": 7.238766956514844e-07, "loss": 0.007214819081127644, "step": 6635 }, { "epoch": 1.722741433021807, "grad_norm": 2.912334680557251, "learning_rate": 7.23465495327841e-07, "loss": 0.011132135055959225, "step": 6636 }, { "epoch": 1.7230010384215992, "grad_norm": 12.907434463500977, "learning_rate": 7.230546532490958e-07, "loss": 0.04464991018176079, "step": 6637 }, { "epoch": 1.7232606438213915, "grad_norm": 8.201859474182129, "learning_rate": 7.226441694878774e-07, "loss": 0.09596754610538483, "step": 6638 }, { "epoch": 1.7235202492211839, "grad_norm": 10.898249626159668, "learning_rate": 7.222340441167498e-07, "loss": 0.05941317602992058, "step": 6639 }, { "epoch": 1.7237798546209762, "grad_norm": 9.405794143676758, "learning_rate": 7.218242772082131e-07, "loss": 0.02688544988632202, "step": 6640 }, { "epoch": 1.7240394600207685, "grad_norm": 2.9458634853363037, "learning_rate": 7.214148688347055e-07, "loss": 0.01895914599299431, "step": 6641 }, { "epoch": 1.7242990654205608, "grad_norm": 8.776471138000488, "learning_rate": 7.210058190686003e-07, "loss": 0.03672731667757034, "step": 6642 }, { "epoch": 1.724558670820353, "grad_norm": 10.878572463989258, "learning_rate": 7.205971279822084e-07, "loss": 0.04106653481721878, "step": 6643 }, { "epoch": 1.7248182762201454, "grad_norm": 9.467714309692383, "learning_rate": 7.201887956477774e-07, "loss": 0.10857640206813812, "step": 6644 }, { "epoch": 1.7250778816199377, "grad_norm": 8.043272972106934, "learning_rate": 7.197808221374904e-07, "loss": 0.016815517097711563, "step": 6645 }, { "epoch": 1.72533748701973, "grad_norm": 3.0287024974823, "learning_rate": 7.193732075234693e-07, "loss": 0.006367554888129234, "step": 6646 }, { "epoch": 1.7255970924195223, "grad_norm": 3.5218076705932617, "learning_rate": 7.189659518777687e-07, "loss": 0.01975153759121895, "step": 6647 }, { "epoch": 1.7258566978193146, "grad_norm": 2.856391429901123, "learning_rate": 7.185590552723834e-07, "loss": 0.005067793652415276, "step": 6648 }, { "epoch": 1.726116303219107, "grad_norm": 1.522311806678772, "learning_rate": 7.181525177792436e-07, "loss": 0.002822712529450655, "step": 6649 }, { "epoch": 1.7263759086188992, "grad_norm": 9.443867683410645, "learning_rate": 7.177463394702157e-07, "loss": 0.03712867945432663, "step": 6650 }, { "epoch": 1.7266355140186915, "grad_norm": 8.622591972351074, "learning_rate": 7.173405204171028e-07, "loss": 0.011869215406477451, "step": 6651 }, { "epoch": 1.7268951194184838, "grad_norm": 1.0037040710449219, "learning_rate": 7.169350606916434e-07, "loss": 0.00411259476095438, "step": 6652 }, { "epoch": 1.7271547248182761, "grad_norm": 7.759876728057861, "learning_rate": 7.165299603655141e-07, "loss": 0.06158362329006195, "step": 6653 }, { "epoch": 1.7274143302180685, "grad_norm": 4.575164318084717, "learning_rate": 7.161252195103286e-07, "loss": 0.015322655439376831, "step": 6654 }, { "epoch": 1.7276739356178608, "grad_norm": 1.6559621095657349, "learning_rate": 7.157208381976338e-07, "loss": 0.004113007336854935, "step": 6655 }, { "epoch": 1.727933541017653, "grad_norm": 10.249251365661621, "learning_rate": 7.153168164989166e-07, "loss": 0.18315823376178741, "step": 6656 }, { "epoch": 1.7281931464174454, "grad_norm": 9.545114517211914, "learning_rate": 7.149131544855976e-07, "loss": 0.022993680089712143, "step": 6657 }, { "epoch": 1.7284527518172377, "grad_norm": 6.398290157318115, "learning_rate": 7.145098522290362e-07, "loss": 0.03128475695848465, "step": 6658 }, { "epoch": 1.72871235721703, "grad_norm": 12.622420310974121, "learning_rate": 7.141069098005259e-07, "loss": 0.06309698522090912, "step": 6659 }, { "epoch": 1.7289719626168223, "grad_norm": 8.561059951782227, "learning_rate": 7.137043272712981e-07, "loss": 0.015709195286035538, "step": 6660 }, { "epoch": 1.7292315680166146, "grad_norm": 2.7943553924560547, "learning_rate": 7.133021047125206e-07, "loss": 0.009826021268963814, "step": 6661 }, { "epoch": 1.729491173416407, "grad_norm": 5.725277900695801, "learning_rate": 7.129002421952968e-07, "loss": 0.006046530324965715, "step": 6662 }, { "epoch": 1.7297507788161994, "grad_norm": 1.627911925315857, "learning_rate": 7.124987397906661e-07, "loss": 0.0030093486420810223, "step": 6663 }, { "epoch": 1.7300103842159917, "grad_norm": 9.680037498474121, "learning_rate": 7.120975975696064e-07, "loss": 0.03213911131024361, "step": 6664 }, { "epoch": 1.730269989615784, "grad_norm": 10.530749320983887, "learning_rate": 7.116968156030297e-07, "loss": 0.08042044937610626, "step": 6665 }, { "epoch": 1.7305295950155763, "grad_norm": 2.5434250831604004, "learning_rate": 7.112963939617845e-07, "loss": 0.0074696289375424385, "step": 6666 }, { "epoch": 1.7307892004153687, "grad_norm": 5.622500896453857, "learning_rate": 7.108963327166571e-07, "loss": 0.022808009758591652, "step": 6667 }, { "epoch": 1.731048805815161, "grad_norm": 7.8421502113342285, "learning_rate": 7.104966319383684e-07, "loss": 0.025042539462447166, "step": 6668 }, { "epoch": 1.7313084112149533, "grad_norm": 7.458043575286865, "learning_rate": 7.100972916975771e-07, "loss": 0.040508270263671875, "step": 6669 }, { "epoch": 1.7315680166147456, "grad_norm": 10.968070030212402, "learning_rate": 7.096983120648771e-07, "loss": 0.02352207340300083, "step": 6670 }, { "epoch": 1.7318276220145379, "grad_norm": 9.323155403137207, "learning_rate": 7.092996931107983e-07, "loss": 0.04825378209352493, "step": 6671 }, { "epoch": 1.7320872274143302, "grad_norm": 0.5841009616851807, "learning_rate": 7.089014349058085e-07, "loss": 0.0007846658118069172, "step": 6672 }, { "epoch": 1.7323468328141225, "grad_norm": 8.691361427307129, "learning_rate": 7.085035375203098e-07, "loss": 0.0270432997494936, "step": 6673 }, { "epoch": 1.7326064382139148, "grad_norm": 8.868074417114258, "learning_rate": 7.081060010246415e-07, "loss": 0.17304854094982147, "step": 6674 }, { "epoch": 1.7328660436137073, "grad_norm": 9.073651313781738, "learning_rate": 7.077088254890792e-07, "loss": 0.1284867823123932, "step": 6675 }, { "epoch": 1.7331256490134996, "grad_norm": 11.575915336608887, "learning_rate": 7.07312010983834e-07, "loss": 0.050415076315402985, "step": 6676 }, { "epoch": 1.733385254413292, "grad_norm": 8.128658294677734, "learning_rate": 7.069155575790547e-07, "loss": 0.024159131571650505, "step": 6677 }, { "epoch": 1.7336448598130842, "grad_norm": 7.1078948974609375, "learning_rate": 7.065194653448234e-07, "loss": 0.03067217953503132, "step": 6678 }, { "epoch": 1.7339044652128766, "grad_norm": 1.0711331367492676, "learning_rate": 7.061237343511613e-07, "loss": 0.0035485720727592707, "step": 6679 }, { "epoch": 1.7341640706126689, "grad_norm": 10.078063011169434, "learning_rate": 7.057283646680249e-07, "loss": 0.19058577716350555, "step": 6680 }, { "epoch": 1.7344236760124612, "grad_norm": 8.206942558288574, "learning_rate": 7.05333356365306e-07, "loss": 0.021431993693113327, "step": 6681 }, { "epoch": 1.7346832814122535, "grad_norm": 10.875646591186523, "learning_rate": 7.04938709512833e-07, "loss": 0.12603133916854858, "step": 6682 }, { "epoch": 1.7349428868120458, "grad_norm": 10.833586692810059, "learning_rate": 7.045444241803699e-07, "loss": 0.07486749440431595, "step": 6683 }, { "epoch": 1.735202492211838, "grad_norm": 8.89519214630127, "learning_rate": 7.04150500437618e-07, "loss": 0.07996072620153427, "step": 6684 }, { "epoch": 1.7354620976116304, "grad_norm": 10.912105560302734, "learning_rate": 7.037569383542147e-07, "loss": 0.08864985406398773, "step": 6685 }, { "epoch": 1.7357217030114227, "grad_norm": 9.931708335876465, "learning_rate": 7.033637379997308e-07, "loss": 0.04473397880792618, "step": 6686 }, { "epoch": 1.735981308411215, "grad_norm": 7.206912040710449, "learning_rate": 7.029708994436771e-07, "loss": 0.01596539095044136, "step": 6687 }, { "epoch": 1.7362409138110073, "grad_norm": 2.2255759239196777, "learning_rate": 7.02578422755497e-07, "loss": 0.005534895695745945, "step": 6688 }, { "epoch": 1.7365005192107996, "grad_norm": 10.27485179901123, "learning_rate": 7.021863080045726e-07, "loss": 0.028454605489969254, "step": 6689 }, { "epoch": 1.736760124610592, "grad_norm": 4.865207195281982, "learning_rate": 7.017945552602201e-07, "loss": 0.002695126924663782, "step": 6690 }, { "epoch": 1.7370197300103842, "grad_norm": 8.960564613342285, "learning_rate": 7.014031645916923e-07, "loss": 0.0596202127635479, "step": 6691 }, { "epoch": 1.7372793354101765, "grad_norm": 4.630766868591309, "learning_rate": 7.010121360681787e-07, "loss": 0.029869772493839264, "step": 6692 }, { "epoch": 1.7375389408099688, "grad_norm": 8.305368423461914, "learning_rate": 7.006214697588036e-07, "loss": 0.023400796577334404, "step": 6693 }, { "epoch": 1.7377985462097612, "grad_norm": 5.613466739654541, "learning_rate": 7.002311657326279e-07, "loss": 0.01230460312217474, "step": 6694 }, { "epoch": 1.7380581516095535, "grad_norm": 10.836331367492676, "learning_rate": 6.99841224058649e-07, "loss": 0.08291156589984894, "step": 6695 }, { "epoch": 1.7383177570093458, "grad_norm": 8.936193466186523, "learning_rate": 6.994516448057993e-07, "loss": 0.03386245295405388, "step": 6696 }, { "epoch": 1.738577362409138, "grad_norm": 10.328633308410645, "learning_rate": 6.99062428042947e-07, "loss": 0.0868699848651886, "step": 6697 }, { "epoch": 1.7388369678089304, "grad_norm": 11.313105583190918, "learning_rate": 6.986735738388976e-07, "loss": 0.03428545221686363, "step": 6698 }, { "epoch": 1.7390965732087227, "grad_norm": 6.991525650024414, "learning_rate": 6.982850822623907e-07, "loss": 0.028305863961577415, "step": 6699 }, { "epoch": 1.739356178608515, "grad_norm": 7.271103858947754, "learning_rate": 6.978969533821036e-07, "loss": 0.028140434995293617, "step": 6700 }, { "epoch": 1.7396157840083073, "grad_norm": 14.637694358825684, "learning_rate": 6.975091872666484e-07, "loss": 0.020305337384343147, "step": 6701 }, { "epoch": 1.7398753894080996, "grad_norm": 11.8953275680542, "learning_rate": 6.971217839845726e-07, "loss": 0.14546507596969604, "step": 6702 }, { "epoch": 1.740134994807892, "grad_norm": 6.594169616699219, "learning_rate": 6.96734743604361e-07, "loss": 0.011761746369302273, "step": 6703 }, { "epoch": 1.7403946002076842, "grad_norm": 6.3018622398376465, "learning_rate": 6.963480661944335e-07, "loss": 0.004683314822614193, "step": 6704 }, { "epoch": 1.7406542056074765, "grad_norm": 9.778101921081543, "learning_rate": 6.959617518231448e-07, "loss": 0.04109895974397659, "step": 6705 }, { "epoch": 1.7409138110072688, "grad_norm": 11.027759552001953, "learning_rate": 6.955758005587876e-07, "loss": 0.08535721153020859, "step": 6706 }, { "epoch": 1.7411734164070611, "grad_norm": 14.724403381347656, "learning_rate": 6.951902124695885e-07, "loss": 0.02140619605779648, "step": 6707 }, { "epoch": 1.7414330218068534, "grad_norm": 10.19485855102539, "learning_rate": 6.948049876237116e-07, "loss": 0.029411684721708298, "step": 6708 }, { "epoch": 1.7416926272066457, "grad_norm": 4.264031410217285, "learning_rate": 6.944201260892544e-07, "loss": 0.017892764881253242, "step": 6709 }, { "epoch": 1.741952232606438, "grad_norm": 10.347553253173828, "learning_rate": 6.940356279342524e-07, "loss": 0.11435019969940186, "step": 6710 }, { "epoch": 1.7422118380062306, "grad_norm": 11.932656288146973, "learning_rate": 6.936514932266763e-07, "loss": 0.13602441549301147, "step": 6711 }, { "epoch": 1.742471443406023, "grad_norm": 7.34426212310791, "learning_rate": 6.932677220344321e-07, "loss": 0.011537805199623108, "step": 6712 }, { "epoch": 1.7427310488058152, "grad_norm": 6.989626884460449, "learning_rate": 6.928843144253619e-07, "loss": 0.021662738174200058, "step": 6713 }, { "epoch": 1.7429906542056075, "grad_norm": 14.656341552734375, "learning_rate": 6.925012704672426e-07, "loss": 0.08796384930610657, "step": 6714 }, { "epoch": 1.7432502596053998, "grad_norm": 9.268608093261719, "learning_rate": 6.921185902277882e-07, "loss": 0.03043203428387642, "step": 6715 }, { "epoch": 1.7435098650051921, "grad_norm": 12.877426147460938, "learning_rate": 6.917362737746487e-07, "loss": 0.029292050749063492, "step": 6716 }, { "epoch": 1.7437694704049844, "grad_norm": 7.645228385925293, "learning_rate": 6.913543211754075e-07, "loss": 0.02196357026696205, "step": 6717 }, { "epoch": 1.7440290758047767, "grad_norm": 10.139452934265137, "learning_rate": 6.909727324975854e-07, "loss": 0.025441022589802742, "step": 6718 }, { "epoch": 1.744288681204569, "grad_norm": 8.940617561340332, "learning_rate": 6.905915078086392e-07, "loss": 0.10345250368118286, "step": 6719 }, { "epoch": 1.7445482866043613, "grad_norm": 10.355334281921387, "learning_rate": 6.902106471759595e-07, "loss": 0.060853540897369385, "step": 6720 }, { "epoch": 1.7448078920041536, "grad_norm": 4.642154693603516, "learning_rate": 6.898301506668749e-07, "loss": 0.012259932234883308, "step": 6721 }, { "epoch": 1.745067497403946, "grad_norm": 0.9064867496490479, "learning_rate": 6.894500183486478e-07, "loss": 0.0014167891349643469, "step": 6722 }, { "epoch": 1.7453271028037385, "grad_norm": 12.825403213500977, "learning_rate": 6.890702502884775e-07, "loss": 0.04356827959418297, "step": 6723 }, { "epoch": 1.7455867082035308, "grad_norm": 6.602018356323242, "learning_rate": 6.886908465534975e-07, "loss": 0.01841430924832821, "step": 6724 }, { "epoch": 1.745846313603323, "grad_norm": 9.634625434875488, "learning_rate": 6.883118072107783e-07, "loss": 0.05469636619091034, "step": 6725 }, { "epoch": 1.7461059190031154, "grad_norm": 3.605433225631714, "learning_rate": 6.879331323273253e-07, "loss": 0.006652013398706913, "step": 6726 }, { "epoch": 1.7463655244029077, "grad_norm": 3.3264875411987305, "learning_rate": 6.875548219700792e-07, "loss": 0.003920349758118391, "step": 6727 }, { "epoch": 1.7466251298027, "grad_norm": 2.2438766956329346, "learning_rate": 6.871768762059167e-07, "loss": 0.0028676954098045826, "step": 6728 }, { "epoch": 1.7468847352024923, "grad_norm": 7.195053577423096, "learning_rate": 6.867992951016506e-07, "loss": 0.07662229239940643, "step": 6729 }, { "epoch": 1.7471443406022846, "grad_norm": 4.703885555267334, "learning_rate": 6.864220787240275e-07, "loss": 0.04803704470396042, "step": 6730 }, { "epoch": 1.747403946002077, "grad_norm": 9.551641464233398, "learning_rate": 6.860452271397317e-07, "loss": 0.10349799692630768, "step": 6731 }, { "epoch": 1.7476635514018692, "grad_norm": 11.338561058044434, "learning_rate": 6.856687404153814e-07, "loss": 0.0825815349817276, "step": 6732 }, { "epoch": 1.7479231568016615, "grad_norm": 8.469058990478516, "learning_rate": 6.852926186175305e-07, "loss": 0.12354665994644165, "step": 6733 }, { "epoch": 1.7481827622014539, "grad_norm": 6.515504837036133, "learning_rate": 6.849168618126695e-07, "loss": 0.02541513741016388, "step": 6734 }, { "epoch": 1.7484423676012462, "grad_norm": 8.081735610961914, "learning_rate": 6.845414700672231e-07, "loss": 0.03687663748860359, "step": 6735 }, { "epoch": 1.7487019730010385, "grad_norm": 6.138477802276611, "learning_rate": 6.841664434475518e-07, "loss": 0.008457152172923088, "step": 6736 }, { "epoch": 1.7489615784008308, "grad_norm": 6.449219703674316, "learning_rate": 6.837917820199525e-07, "loss": 0.011555083096027374, "step": 6737 }, { "epoch": 1.749221183800623, "grad_norm": 1.2174735069274902, "learning_rate": 6.834174858506555e-07, "loss": 0.002184624318033457, "step": 6738 }, { "epoch": 1.7494807892004154, "grad_norm": 9.147669792175293, "learning_rate": 6.830435550058297e-07, "loss": 0.11038103699684143, "step": 6739 }, { "epoch": 1.7497403946002077, "grad_norm": 8.765205383300781, "learning_rate": 6.826699895515751e-07, "loss": 0.021205544471740723, "step": 6740 }, { "epoch": 1.75, "grad_norm": 9.492851257324219, "learning_rate": 6.822967895539311e-07, "loss": 0.07289920747280121, "step": 6741 }, { "epoch": 1.7502596053997923, "grad_norm": 3.7255494594573975, "learning_rate": 6.81923955078871e-07, "loss": 0.013537835329771042, "step": 6742 }, { "epoch": 1.7505192107995846, "grad_norm": 8.26984977722168, "learning_rate": 6.815514861923028e-07, "loss": 0.01593608595430851, "step": 6743 }, { "epoch": 1.750778816199377, "grad_norm": 7.211132049560547, "learning_rate": 6.811793829600707e-07, "loss": 0.04243237152695656, "step": 6744 }, { "epoch": 1.7510384215991692, "grad_norm": 8.678642272949219, "learning_rate": 6.808076454479534e-07, "loss": 0.04365893080830574, "step": 6745 }, { "epoch": 1.7512980269989615, "grad_norm": 6.961361885070801, "learning_rate": 6.80436273721667e-07, "loss": 0.09117812663316727, "step": 6746 }, { "epoch": 1.7515576323987538, "grad_norm": 9.331140518188477, "learning_rate": 6.800652678468604e-07, "loss": 0.055098775774240494, "step": 6747 }, { "epoch": 1.7518172377985461, "grad_norm": 6.0023040771484375, "learning_rate": 6.79694627889119e-07, "loss": 0.008991449140012264, "step": 6748 }, { "epoch": 1.7520768431983385, "grad_norm": 8.736807823181152, "learning_rate": 6.793243539139636e-07, "loss": 0.15472033619880676, "step": 6749 }, { "epoch": 1.7523364485981308, "grad_norm": 7.007387161254883, "learning_rate": 6.789544459868508e-07, "loss": 0.0375603586435318, "step": 6750 }, { "epoch": 1.752596053997923, "grad_norm": 8.248247146606445, "learning_rate": 6.785849041731705e-07, "loss": 0.05053162947297096, "step": 6751 }, { "epoch": 1.7528556593977154, "grad_norm": 8.14639949798584, "learning_rate": 6.782157285382508e-07, "loss": 0.03580544516444206, "step": 6752 }, { "epoch": 1.7531152647975077, "grad_norm": 7.120941162109375, "learning_rate": 6.778469191473519e-07, "loss": 0.0647820234298706, "step": 6753 }, { "epoch": 1.7533748701973, "grad_norm": 8.625426292419434, "learning_rate": 6.774784760656725e-07, "loss": 0.17257221043109894, "step": 6754 }, { "epoch": 1.7536344755970923, "grad_norm": 2.044353485107422, "learning_rate": 6.771103993583437e-07, "loss": 0.009980998001992702, "step": 6755 }, { "epoch": 1.7538940809968846, "grad_norm": 10.940380096435547, "learning_rate": 6.767426890904332e-07, "loss": 0.014704287052154541, "step": 6756 }, { "epoch": 1.754153686396677, "grad_norm": 12.04219913482666, "learning_rate": 6.763753453269445e-07, "loss": 0.04568265378475189, "step": 6757 }, { "epoch": 1.7544132917964692, "grad_norm": 8.609794616699219, "learning_rate": 6.760083681328147e-07, "loss": 0.10416260361671448, "step": 6758 }, { "epoch": 1.7546728971962615, "grad_norm": 10.60714054107666, "learning_rate": 6.756417575729171e-07, "loss": 0.06880050152540207, "step": 6759 }, { "epoch": 1.754932502596054, "grad_norm": 8.327618598937988, "learning_rate": 6.752755137120606e-07, "loss": 0.04564318805932999, "step": 6760 }, { "epoch": 1.7551921079958464, "grad_norm": 9.354100227355957, "learning_rate": 6.749096366149881e-07, "loss": 0.05430010333657265, "step": 6761 }, { "epoch": 1.7554517133956387, "grad_norm": 7.513314723968506, "learning_rate": 6.745441263463791e-07, "loss": 0.017729055136442184, "step": 6762 }, { "epoch": 1.755711318795431, "grad_norm": 7.595766544342041, "learning_rate": 6.741789829708467e-07, "loss": 0.01141815073788166, "step": 6763 }, { "epoch": 1.7559709241952233, "grad_norm": 7.578171253204346, "learning_rate": 6.738142065529396e-07, "loss": 0.019593534991145134, "step": 6764 }, { "epoch": 1.7562305295950156, "grad_norm": 11.732694625854492, "learning_rate": 6.73449797157143e-07, "loss": 0.06655814498662949, "step": 6765 }, { "epoch": 1.7564901349948079, "grad_norm": 11.710673332214355, "learning_rate": 6.730857548478753e-07, "loss": 0.028597254306077957, "step": 6766 }, { "epoch": 1.7567497403946002, "grad_norm": 8.137646675109863, "learning_rate": 6.727220796894913e-07, "loss": 0.08648999780416489, "step": 6767 }, { "epoch": 1.7570093457943925, "grad_norm": 8.909019470214844, "learning_rate": 6.723587717462801e-07, "loss": 0.025973141193389893, "step": 6768 }, { "epoch": 1.7572689511941848, "grad_norm": 6.880206108093262, "learning_rate": 6.719958310824662e-07, "loss": 0.011946765705943108, "step": 6769 }, { "epoch": 1.757528556593977, "grad_norm": 7.193524360656738, "learning_rate": 6.7163325776221e-07, "loss": 0.03980551287531853, "step": 6770 }, { "epoch": 1.7577881619937694, "grad_norm": 10.16041088104248, "learning_rate": 6.712710518496049e-07, "loss": 0.025929071009159088, "step": 6771 }, { "epoch": 1.758047767393562, "grad_norm": 7.637630939483643, "learning_rate": 6.709092134086813e-07, "loss": 0.012979650869965553, "step": 6772 }, { "epoch": 1.7583073727933543, "grad_norm": 13.928009986877441, "learning_rate": 6.705477425034046e-07, "loss": 0.12448467314243317, "step": 6773 }, { "epoch": 1.7585669781931466, "grad_norm": 9.530085563659668, "learning_rate": 6.701866391976733e-07, "loss": 0.1413583755493164, "step": 6774 }, { "epoch": 1.7588265835929389, "grad_norm": 9.39040756225586, "learning_rate": 6.698259035553228e-07, "loss": 0.028380723670125008, "step": 6775 }, { "epoch": 1.7590861889927312, "grad_norm": 12.336506843566895, "learning_rate": 6.694655356401226e-07, "loss": 0.03842750936746597, "step": 6776 }, { "epoch": 1.7593457943925235, "grad_norm": 8.753865242004395, "learning_rate": 6.691055355157783e-07, "loss": 0.07837261259555817, "step": 6777 }, { "epoch": 1.7596053997923158, "grad_norm": 7.99043083190918, "learning_rate": 6.687459032459289e-07, "loss": 0.04124715179204941, "step": 6778 }, { "epoch": 1.759865005192108, "grad_norm": 2.9438931941986084, "learning_rate": 6.683866388941495e-07, "loss": 0.010511758737266064, "step": 6779 }, { "epoch": 1.7601246105919004, "grad_norm": 11.994930267333984, "learning_rate": 6.680277425239496e-07, "loss": 0.027145039290189743, "step": 6780 }, { "epoch": 1.7603842159916927, "grad_norm": 6.507628917694092, "learning_rate": 6.676692141987744e-07, "loss": 0.023085199296474457, "step": 6781 }, { "epoch": 1.760643821391485, "grad_norm": 9.587218284606934, "learning_rate": 6.673110539820023e-07, "loss": 0.047896333038806915, "step": 6782 }, { "epoch": 1.7609034267912773, "grad_norm": 7.873696327209473, "learning_rate": 6.669532619369493e-07, "loss": 0.05233946070075035, "step": 6783 }, { "epoch": 1.7611630321910696, "grad_norm": 9.11800765991211, "learning_rate": 6.665958381268634e-07, "loss": 0.12373586744070053, "step": 6784 }, { "epoch": 1.761422637590862, "grad_norm": 12.99471664428711, "learning_rate": 6.662387826149303e-07, "loss": 0.041225746273994446, "step": 6785 }, { "epoch": 1.7616822429906542, "grad_norm": 7.6290082931518555, "learning_rate": 6.658820954642687e-07, "loss": 0.04925667494535446, "step": 6786 }, { "epoch": 1.7619418483904465, "grad_norm": 8.494758605957031, "learning_rate": 6.655257767379321e-07, "loss": 0.10950806736946106, "step": 6787 }, { "epoch": 1.7622014537902388, "grad_norm": 4.888763904571533, "learning_rate": 6.651698264989105e-07, "loss": 0.021036311984062195, "step": 6788 }, { "epoch": 1.7624610591900312, "grad_norm": 8.770198822021484, "learning_rate": 6.648142448101274e-07, "loss": 0.09604746848344803, "step": 6789 }, { "epoch": 1.7627206645898235, "grad_norm": 2.0042836666107178, "learning_rate": 6.644590317344409e-07, "loss": 0.007549067959189415, "step": 6790 }, { "epoch": 1.7629802699896158, "grad_norm": 8.24477767944336, "learning_rate": 6.641041873346453e-07, "loss": 0.029888510704040527, "step": 6791 }, { "epoch": 1.763239875389408, "grad_norm": 4.250118255615234, "learning_rate": 6.637497116734686e-07, "loss": 0.016108045354485512, "step": 6792 }, { "epoch": 1.7634994807892004, "grad_norm": 8.457086563110352, "learning_rate": 6.633956048135741e-07, "loss": 0.04759783297777176, "step": 6793 }, { "epoch": 1.7637590861889927, "grad_norm": 6.521376609802246, "learning_rate": 6.630418668175598e-07, "loss": 0.03196081519126892, "step": 6794 }, { "epoch": 1.764018691588785, "grad_norm": 3.8276238441467285, "learning_rate": 6.626884977479582e-07, "loss": 0.022518783807754517, "step": 6795 }, { "epoch": 1.7642782969885773, "grad_norm": 1.7579431533813477, "learning_rate": 6.623354976672376e-07, "loss": 0.00223011733032763, "step": 6796 }, { "epoch": 1.7645379023883696, "grad_norm": 9.842527389526367, "learning_rate": 6.619828666377998e-07, "loss": 0.03428056091070175, "step": 6797 }, { "epoch": 1.764797507788162, "grad_norm": 9.583616256713867, "learning_rate": 6.616306047219813e-07, "loss": 0.11503492295742035, "step": 6798 }, { "epoch": 1.7650571131879542, "grad_norm": 12.889507293701172, "learning_rate": 6.612787119820552e-07, "loss": 0.05633416026830673, "step": 6799 }, { "epoch": 1.7653167185877465, "grad_norm": 8.667671203613281, "learning_rate": 6.609271884802272e-07, "loss": 0.0157071053981781, "step": 6800 }, { "epoch": 1.7655763239875388, "grad_norm": 8.201737403869629, "learning_rate": 6.605760342786391e-07, "loss": 0.02641553059220314, "step": 6801 }, { "epoch": 1.7658359293873311, "grad_norm": 9.409200668334961, "learning_rate": 6.602252494393663e-07, "loss": 0.020564185455441475, "step": 6802 }, { "epoch": 1.7660955347871234, "grad_norm": 0.9473312497138977, "learning_rate": 6.598748340244198e-07, "loss": 0.002162142191082239, "step": 6803 }, { "epoch": 1.7663551401869158, "grad_norm": 6.740763187408447, "learning_rate": 6.595247880957459e-07, "loss": 0.021590568125247955, "step": 6804 }, { "epoch": 1.766614745586708, "grad_norm": 11.40386962890625, "learning_rate": 6.59175111715223e-07, "loss": 0.0870349109172821, "step": 6805 }, { "epoch": 1.7668743509865004, "grad_norm": 7.709743499755859, "learning_rate": 6.588258049446673e-07, "loss": 0.037978462874889374, "step": 6806 }, { "epoch": 1.7671339563862927, "grad_norm": 6.166854381561279, "learning_rate": 6.584768678458274e-07, "loss": 0.02091815695166588, "step": 6807 }, { "epoch": 1.7673935617860852, "grad_norm": 8.409905433654785, "learning_rate": 6.58128300480388e-07, "loss": 0.12224027514457703, "step": 6808 }, { "epoch": 1.7676531671858775, "grad_norm": 9.55855941772461, "learning_rate": 6.577801029099676e-07, "loss": 0.05254790931940079, "step": 6809 }, { "epoch": 1.7679127725856698, "grad_norm": 7.337765216827393, "learning_rate": 6.574322751961193e-07, "loss": 0.012360326945781708, "step": 6810 }, { "epoch": 1.7681723779854621, "grad_norm": 10.358094215393066, "learning_rate": 6.570848174003316e-07, "loss": 0.020433837547898293, "step": 6811 }, { "epoch": 1.7684319833852544, "grad_norm": 12.429496765136719, "learning_rate": 6.567377295840267e-07, "loss": 0.04679771512746811, "step": 6812 }, { "epoch": 1.7686915887850467, "grad_norm": 6.813800811767578, "learning_rate": 6.563910118085616e-07, "loss": 0.05291353166103363, "step": 6813 }, { "epoch": 1.768951194184839, "grad_norm": 9.017754554748535, "learning_rate": 6.560446641352288e-07, "loss": 0.027160532772541046, "step": 6814 }, { "epoch": 1.7692107995846313, "grad_norm": 13.551855087280273, "learning_rate": 6.556986866252535e-07, "loss": 0.04152347147464752, "step": 6815 }, { "epoch": 1.7694704049844237, "grad_norm": 8.659775733947754, "learning_rate": 6.553530793397975e-07, "loss": 0.036592476069927216, "step": 6816 }, { "epoch": 1.769730010384216, "grad_norm": 9.165627479553223, "learning_rate": 6.550078423399565e-07, "loss": 0.01632096990942955, "step": 6817 }, { "epoch": 1.7699896157840083, "grad_norm": 11.984518051147461, "learning_rate": 6.546629756867594e-07, "loss": 0.10879036784172058, "step": 6818 }, { "epoch": 1.7702492211838006, "grad_norm": 2.33320689201355, "learning_rate": 6.543184794411715e-07, "loss": 0.004169302526861429, "step": 6819 }, { "epoch": 1.770508826583593, "grad_norm": 9.798614501953125, "learning_rate": 6.539743536640921e-07, "loss": 0.012771292589604855, "step": 6820 }, { "epoch": 1.7707684319833854, "grad_norm": 3.5419788360595703, "learning_rate": 6.536305984163538e-07, "loss": 0.0039089517667889595, "step": 6821 }, { "epoch": 1.7710280373831777, "grad_norm": 6.4815897941589355, "learning_rate": 6.532872137587254e-07, "loss": 0.017465723678469658, "step": 6822 }, { "epoch": 1.77128764278297, "grad_norm": 9.004140853881836, "learning_rate": 6.529441997519091e-07, "loss": 0.04184328019618988, "step": 6823 }, { "epoch": 1.7715472481827623, "grad_norm": 4.593098163604736, "learning_rate": 6.526015564565423e-07, "loss": 0.01737888529896736, "step": 6824 }, { "epoch": 1.7718068535825546, "grad_norm": 8.572574615478516, "learning_rate": 6.522592839331962e-07, "loss": 0.15166549384593964, "step": 6825 }, { "epoch": 1.772066458982347, "grad_norm": 11.4613037109375, "learning_rate": 6.519173822423768e-07, "loss": 0.05335605889558792, "step": 6826 }, { "epoch": 1.7723260643821392, "grad_norm": 8.65926742553711, "learning_rate": 6.51575851444525e-07, "loss": 0.048705171793699265, "step": 6827 }, { "epoch": 1.7725856697819315, "grad_norm": 2.414638042449951, "learning_rate": 6.512346916000144e-07, "loss": 0.006444437429308891, "step": 6828 }, { "epoch": 1.7728452751817239, "grad_norm": 6.0370306968688965, "learning_rate": 6.508939027691548e-07, "loss": 0.012964744120836258, "step": 6829 }, { "epoch": 1.7731048805815162, "grad_norm": 10.6043701171875, "learning_rate": 6.505534850121904e-07, "loss": 0.02287272736430168, "step": 6830 }, { "epoch": 1.7733644859813085, "grad_norm": 10.025681495666504, "learning_rate": 6.502134383892993e-07, "loss": 0.1526455134153366, "step": 6831 }, { "epoch": 1.7736240913811008, "grad_norm": 8.978684425354004, "learning_rate": 6.498737629605933e-07, "loss": 0.02536601573228836, "step": 6832 }, { "epoch": 1.773883696780893, "grad_norm": 8.432783126831055, "learning_rate": 6.49534458786119e-07, "loss": 0.044428423047065735, "step": 6833 }, { "epoch": 1.7741433021806854, "grad_norm": 10.10982894897461, "learning_rate": 6.491955259258584e-07, "loss": 0.057555343955755234, "step": 6834 }, { "epoch": 1.7744029075804777, "grad_norm": 6.745957851409912, "learning_rate": 6.488569644397272e-07, "loss": 0.030647775158286095, "step": 6835 }, { "epoch": 1.77466251298027, "grad_norm": 9.658977508544922, "learning_rate": 6.485187743875743e-07, "loss": 0.030133869498968124, "step": 6836 }, { "epoch": 1.7749221183800623, "grad_norm": 11.867449760437012, "learning_rate": 6.481809558291848e-07, "loss": 0.04220227152109146, "step": 6837 }, { "epoch": 1.7751817237798546, "grad_norm": 7.96382999420166, "learning_rate": 6.478435088242768e-07, "loss": 0.07653261721134186, "step": 6838 }, { "epoch": 1.775441329179647, "grad_norm": 8.582989692687988, "learning_rate": 6.475064334325039e-07, "loss": 0.1396826207637787, "step": 6839 }, { "epoch": 1.7757009345794392, "grad_norm": 2.2882091999053955, "learning_rate": 6.471697297134526e-07, "loss": 0.011851094663143158, "step": 6840 }, { "epoch": 1.7759605399792315, "grad_norm": 8.629960060119629, "learning_rate": 6.468333977266446e-07, "loss": 0.05675417184829712, "step": 6841 }, { "epoch": 1.7762201453790238, "grad_norm": 7.535496711730957, "learning_rate": 6.464974375315357e-07, "loss": 0.026493936777114868, "step": 6842 }, { "epoch": 1.7764797507788161, "grad_norm": 6.327040672302246, "learning_rate": 6.461618491875163e-07, "loss": 0.01743108034133911, "step": 6843 }, { "epoch": 1.7767393561786085, "grad_norm": 13.110689163208008, "learning_rate": 6.4582663275391e-07, "loss": 0.03345615044236183, "step": 6844 }, { "epoch": 1.7769989615784008, "grad_norm": 9.270087242126465, "learning_rate": 6.454917882899764e-07, "loss": 0.11013076454401016, "step": 6845 }, { "epoch": 1.777258566978193, "grad_norm": 5.0019612312316895, "learning_rate": 6.451573158549071e-07, "loss": 0.014261877164244652, "step": 6846 }, { "epoch": 1.7775181723779854, "grad_norm": 5.723528861999512, "learning_rate": 6.448232155078303e-07, "loss": 0.014226913452148438, "step": 6847 }, { "epoch": 1.7777777777777777, "grad_norm": 10.175668716430664, "learning_rate": 6.44489487307807e-07, "loss": 0.05509531497955322, "step": 6848 }, { "epoch": 1.77803738317757, "grad_norm": 9.60272216796875, "learning_rate": 6.441561313138321e-07, "loss": 0.0638195127248764, "step": 6849 }, { "epoch": 1.7782969885773623, "grad_norm": 6.675018787384033, "learning_rate": 6.438231475848361e-07, "loss": 0.02731926739215851, "step": 6850 }, { "epoch": 1.7785565939771546, "grad_norm": 9.192619323730469, "learning_rate": 6.434905361796825e-07, "loss": 0.08366333693265915, "step": 6851 }, { "epoch": 1.778816199376947, "grad_norm": 9.026644706726074, "learning_rate": 6.431582971571693e-07, "loss": 0.016550805419683456, "step": 6852 }, { "epoch": 1.7790758047767392, "grad_norm": 9.557668685913086, "learning_rate": 6.428264305760288e-07, "loss": 0.03352257236838341, "step": 6853 }, { "epoch": 1.7793354101765315, "grad_norm": 4.390439987182617, "learning_rate": 6.424949364949279e-07, "loss": 0.014719588682055473, "step": 6854 }, { "epoch": 1.7795950155763238, "grad_norm": 1.0387159585952759, "learning_rate": 6.421638149724661e-07, "loss": 0.0062141213566064835, "step": 6855 }, { "epoch": 1.7798546209761164, "grad_norm": 9.220613479614258, "learning_rate": 6.418330660671794e-07, "loss": 0.12481597065925598, "step": 6856 }, { "epoch": 1.7801142263759087, "grad_norm": 5.414656639099121, "learning_rate": 6.415026898375355e-07, "loss": 0.009267131797969341, "step": 6857 }, { "epoch": 1.780373831775701, "grad_norm": 10.958989143371582, "learning_rate": 6.411726863419386e-07, "loss": 0.04506605118513107, "step": 6858 }, { "epoch": 1.7806334371754933, "grad_norm": 9.027633666992188, "learning_rate": 6.408430556387243e-07, "loss": 0.023178935050964355, "step": 6859 }, { "epoch": 1.7808930425752856, "grad_norm": 5.634317874908447, "learning_rate": 6.405137977861643e-07, "loss": 0.008015005849301815, "step": 6860 }, { "epoch": 1.7811526479750779, "grad_norm": 8.930949211120605, "learning_rate": 6.401849128424645e-07, "loss": 0.010537983849644661, "step": 6861 }, { "epoch": 1.7814122533748702, "grad_norm": 22.348033905029297, "learning_rate": 6.398564008657638e-07, "loss": 0.016449276357889175, "step": 6862 }, { "epoch": 1.7816718587746625, "grad_norm": 9.095417976379395, "learning_rate": 6.395282619141354e-07, "loss": 0.08285261690616608, "step": 6863 }, { "epoch": 1.7819314641744548, "grad_norm": 8.898979187011719, "learning_rate": 6.392004960455867e-07, "loss": 0.1032545268535614, "step": 6864 }, { "epoch": 1.782191069574247, "grad_norm": 3.1103427410125732, "learning_rate": 6.388731033180594e-07, "loss": 0.025489985942840576, "step": 6865 }, { "epoch": 1.7824506749740394, "grad_norm": 8.316673278808594, "learning_rate": 6.385460837894296e-07, "loss": 0.008004422299563885, "step": 6866 }, { "epoch": 1.7827102803738317, "grad_norm": 7.146642208099365, "learning_rate": 6.382194375175058e-07, "loss": 0.05623910203576088, "step": 6867 }, { "epoch": 1.7829698857736243, "grad_norm": 8.44965648651123, "learning_rate": 6.378931645600321e-07, "loss": 0.09339198470115662, "step": 6868 }, { "epoch": 1.7832294911734166, "grad_norm": 3.354769229888916, "learning_rate": 6.375672649746861e-07, "loss": 0.03042376972734928, "step": 6869 }, { "epoch": 1.7834890965732089, "grad_norm": 2.404928207397461, "learning_rate": 6.372417388190796e-07, "loss": 0.005997427273541689, "step": 6870 }, { "epoch": 1.7837487019730012, "grad_norm": 9.134212493896484, "learning_rate": 6.369165861507577e-07, "loss": 0.05439869314432144, "step": 6871 }, { "epoch": 1.7840083073727935, "grad_norm": 7.513163089752197, "learning_rate": 6.365918070271999e-07, "loss": 0.024287788197398186, "step": 6872 }, { "epoch": 1.7842679127725858, "grad_norm": 1.8528497219085693, "learning_rate": 6.362674015058207e-07, "loss": 0.0024812398478388786, "step": 6873 }, { "epoch": 1.784527518172378, "grad_norm": 10.560469627380371, "learning_rate": 6.359433696439665e-07, "loss": 0.014849337749183178, "step": 6874 }, { "epoch": 1.7847871235721704, "grad_norm": 9.991327285766602, "learning_rate": 6.356197114989187e-07, "loss": 0.035330332815647125, "step": 6875 }, { "epoch": 1.7850467289719627, "grad_norm": 8.750171661376953, "learning_rate": 6.352964271278934e-07, "loss": 0.0699618011713028, "step": 6876 }, { "epoch": 1.785306334371755, "grad_norm": 9.635566711425781, "learning_rate": 6.349735165880393e-07, "loss": 0.06066139414906502, "step": 6877 }, { "epoch": 1.7855659397715473, "grad_norm": 9.25105094909668, "learning_rate": 6.346509799364402e-07, "loss": 0.06357167661190033, "step": 6878 }, { "epoch": 1.7858255451713396, "grad_norm": 9.8679838180542, "learning_rate": 6.343288172301125e-07, "loss": 0.04316157102584839, "step": 6879 }, { "epoch": 1.786085150571132, "grad_norm": 6.772732734680176, "learning_rate": 6.340070285260071e-07, "loss": 0.10303318500518799, "step": 6880 }, { "epoch": 1.7863447559709242, "grad_norm": 2.2329514026641846, "learning_rate": 6.3368561388101e-07, "loss": 0.008335107006132603, "step": 6881 }, { "epoch": 1.7866043613707165, "grad_norm": 2.987840414047241, "learning_rate": 6.333645733519387e-07, "loss": 0.0048692249692976475, "step": 6882 }, { "epoch": 1.7868639667705088, "grad_norm": 5.264216423034668, "learning_rate": 6.330439069955461e-07, "loss": 0.02696913667023182, "step": 6883 }, { "epoch": 1.7871235721703012, "grad_norm": 15.623023986816406, "learning_rate": 6.327236148685192e-07, "loss": 0.054666951298713684, "step": 6884 }, { "epoch": 1.7873831775700935, "grad_norm": 6.346808910369873, "learning_rate": 6.32403697027478e-07, "loss": 0.020584655925631523, "step": 6885 }, { "epoch": 1.7876427829698858, "grad_norm": 6.217933654785156, "learning_rate": 6.320841535289765e-07, "loss": 0.025346072390675545, "step": 6886 }, { "epoch": 1.787902388369678, "grad_norm": 3.597949266433716, "learning_rate": 6.317649844295029e-07, "loss": 0.005989714525640011, "step": 6887 }, { "epoch": 1.7881619937694704, "grad_norm": 1.1953316926956177, "learning_rate": 6.314461897854787e-07, "loss": 0.001504240557551384, "step": 6888 }, { "epoch": 1.7884215991692627, "grad_norm": 9.47928524017334, "learning_rate": 6.311277696532603e-07, "loss": 0.02813812904059887, "step": 6889 }, { "epoch": 1.788681204569055, "grad_norm": 5.830350875854492, "learning_rate": 6.308097240891359e-07, "loss": 0.006128310691565275, "step": 6890 }, { "epoch": 1.7889408099688473, "grad_norm": 10.900840759277344, "learning_rate": 6.304920531493292e-07, "loss": 0.029261328279972076, "step": 6891 }, { "epoch": 1.7892004153686396, "grad_norm": 9.635966300964355, "learning_rate": 6.301747568899975e-07, "loss": 0.0653105080127716, "step": 6892 }, { "epoch": 1.789460020768432, "grad_norm": 9.61002254486084, "learning_rate": 6.298578353672312e-07, "loss": 0.028454069048166275, "step": 6893 }, { "epoch": 1.7897196261682242, "grad_norm": 3.054976224899292, "learning_rate": 6.29541288637055e-07, "loss": 0.022023387253284454, "step": 6894 }, { "epoch": 1.7899792315680165, "grad_norm": 7.570322513580322, "learning_rate": 6.292251167554264e-07, "loss": 0.03281480818986893, "step": 6895 }, { "epoch": 1.7902388369678088, "grad_norm": 9.808753967285156, "learning_rate": 6.289093197782378e-07, "loss": 0.0973612368106842, "step": 6896 }, { "epoch": 1.7904984423676011, "grad_norm": 9.116852760314941, "learning_rate": 6.285938977613156e-07, "loss": 0.03649105131626129, "step": 6897 }, { "epoch": 1.7907580477673934, "grad_norm": 9.805302619934082, "learning_rate": 6.282788507604179e-07, "loss": 0.03987520560622215, "step": 6898 }, { "epoch": 1.7910176531671858, "grad_norm": 9.408486366271973, "learning_rate": 6.279641788312388e-07, "loss": 0.04413342848420143, "step": 6899 }, { "epoch": 1.791277258566978, "grad_norm": 3.4481201171875, "learning_rate": 6.276498820294043e-07, "loss": 0.014646448194980621, "step": 6900 }, { "epoch": 1.7915368639667704, "grad_norm": 4.452564239501953, "learning_rate": 6.273359604104756e-07, "loss": 0.016422029584646225, "step": 6901 }, { "epoch": 1.7917964693665627, "grad_norm": 8.133672714233398, "learning_rate": 6.270224140299466e-07, "loss": 0.020477142184972763, "step": 6902 }, { "epoch": 1.792056074766355, "grad_norm": 4.81505823135376, "learning_rate": 6.267092429432446e-07, "loss": 0.006005551666021347, "step": 6903 }, { "epoch": 1.7923156801661475, "grad_norm": 8.452354431152344, "learning_rate": 6.26396447205732e-07, "loss": 0.03000275418162346, "step": 6904 }, { "epoch": 1.7925752855659398, "grad_norm": 0.32014259696006775, "learning_rate": 6.260840268727032e-07, "loss": 0.0010263846488669515, "step": 6905 }, { "epoch": 1.7928348909657321, "grad_norm": 5.601585388183594, "learning_rate": 6.257719819993873e-07, "loss": 0.01883697509765625, "step": 6906 }, { "epoch": 1.7930944963655244, "grad_norm": 10.403563499450684, "learning_rate": 6.254603126409466e-07, "loss": 0.04729340225458145, "step": 6907 }, { "epoch": 1.7933541017653167, "grad_norm": 8.46908187866211, "learning_rate": 6.251490188524768e-07, "loss": 0.09393171966075897, "step": 6908 }, { "epoch": 1.793613707165109, "grad_norm": 13.279379844665527, "learning_rate": 6.248381006890083e-07, "loss": 0.01119104865938425, "step": 6909 }, { "epoch": 1.7938733125649013, "grad_norm": 9.182371139526367, "learning_rate": 6.24527558205504e-07, "loss": 0.03136829286813736, "step": 6910 }, { "epoch": 1.7941329179646937, "grad_norm": 3.0467846393585205, "learning_rate": 6.2421739145686e-07, "loss": 0.00395551510155201, "step": 6911 }, { "epoch": 1.794392523364486, "grad_norm": 6.638899326324463, "learning_rate": 6.239076004979075e-07, "loss": 0.0414857380092144, "step": 6912 }, { "epoch": 1.7946521287642783, "grad_norm": 6.248005390167236, "learning_rate": 6.235981853834102e-07, "loss": 0.025743691250681877, "step": 6913 }, { "epoch": 1.7949117341640706, "grad_norm": 2.2858378887176514, "learning_rate": 6.232891461680653e-07, "loss": 0.011762918904423714, "step": 6914 }, { "epoch": 1.7951713395638629, "grad_norm": 11.978527069091797, "learning_rate": 6.229804829065044e-07, "loss": 0.029197020456194878, "step": 6915 }, { "epoch": 1.7954309449636554, "grad_norm": 7.521058559417725, "learning_rate": 6.226721956532921e-07, "loss": 0.04479368031024933, "step": 6916 }, { "epoch": 1.7956905503634477, "grad_norm": 2.9010910987854004, "learning_rate": 6.223642844629255e-07, "loss": 0.009794218465685844, "step": 6917 }, { "epoch": 1.79595015576324, "grad_norm": 7.004780292510986, "learning_rate": 6.220567493898376e-07, "loss": 0.03377984091639519, "step": 6918 }, { "epoch": 1.7962097611630323, "grad_norm": 11.217182159423828, "learning_rate": 6.217495904883928e-07, "loss": 0.008128381334245205, "step": 6919 }, { "epoch": 1.7964693665628246, "grad_norm": 3.6729843616485596, "learning_rate": 6.214428078128902e-07, "loss": 0.007908156141638756, "step": 6920 }, { "epoch": 1.796728971962617, "grad_norm": 11.018760681152344, "learning_rate": 6.211364014175613e-07, "loss": 0.08347916603088379, "step": 6921 }, { "epoch": 1.7969885773624092, "grad_norm": 0.3992184102535248, "learning_rate": 6.208303713565721e-07, "loss": 0.0009868599008768797, "step": 6922 }, { "epoch": 1.7972481827622016, "grad_norm": 3.3789291381835938, "learning_rate": 6.205247176840217e-07, "loss": 0.0058874343521893024, "step": 6923 }, { "epoch": 1.7975077881619939, "grad_norm": 0.2812126874923706, "learning_rate": 6.202194404539431e-07, "loss": 0.0006316349608823657, "step": 6924 }, { "epoch": 1.7977673935617862, "grad_norm": 9.812289237976074, "learning_rate": 6.199145397203017e-07, "loss": 0.048982005566358566, "step": 6925 }, { "epoch": 1.7980269989615785, "grad_norm": 8.270833015441895, "learning_rate": 6.19610015536997e-07, "loss": 0.012831389904022217, "step": 6926 }, { "epoch": 1.7982866043613708, "grad_norm": 3.1197335720062256, "learning_rate": 6.193058679578619e-07, "loss": 0.006482498254626989, "step": 6927 }, { "epoch": 1.798546209761163, "grad_norm": 8.88103199005127, "learning_rate": 6.190020970366636e-07, "loss": 0.08992139995098114, "step": 6928 }, { "epoch": 1.7988058151609554, "grad_norm": 10.987506866455078, "learning_rate": 6.186987028271007e-07, "loss": 0.06177586689591408, "step": 6929 }, { "epoch": 1.7990654205607477, "grad_norm": 8.2612886428833, "learning_rate": 6.183956853828069e-07, "loss": 0.02503361739218235, "step": 6930 }, { "epoch": 1.79932502596054, "grad_norm": 1.639367938041687, "learning_rate": 6.180930447573486e-07, "loss": 0.0031979666091501713, "step": 6931 }, { "epoch": 1.7995846313603323, "grad_norm": 6.011653900146484, "learning_rate": 6.177907810042259e-07, "loss": 0.004878082312643528, "step": 6932 }, { "epoch": 1.7998442367601246, "grad_norm": 7.31426477432251, "learning_rate": 6.174888941768721e-07, "loss": 0.03807417303323746, "step": 6933 }, { "epoch": 1.800103842159917, "grad_norm": 10.115386962890625, "learning_rate": 6.171873843286534e-07, "loss": 0.061031196266412735, "step": 6934 }, { "epoch": 1.8003634475597092, "grad_norm": 10.09533405303955, "learning_rate": 6.168862515128703e-07, "loss": 0.028336435556411743, "step": 6935 }, { "epoch": 1.8006230529595015, "grad_norm": 3.6773829460144043, "learning_rate": 6.165854957827565e-07, "loss": 0.011742286384105682, "step": 6936 }, { "epoch": 1.8008826583592938, "grad_norm": 0.703057050704956, "learning_rate": 6.16285117191478e-07, "loss": 0.0013607931323349476, "step": 6937 }, { "epoch": 1.8011422637590861, "grad_norm": 5.620474338531494, "learning_rate": 6.159851157921354e-07, "loss": 0.018946707248687744, "step": 6938 }, { "epoch": 1.8014018691588785, "grad_norm": 9.89026927947998, "learning_rate": 6.156854916377618e-07, "loss": 0.02216997742652893, "step": 6939 }, { "epoch": 1.8016614745586708, "grad_norm": 9.636061668395996, "learning_rate": 6.153862447813236e-07, "loss": 0.1109783872961998, "step": 6940 }, { "epoch": 1.801921079958463, "grad_norm": 12.390007019042969, "learning_rate": 6.150873752757217e-07, "loss": 0.023537663742899895, "step": 6941 }, { "epoch": 1.8021806853582554, "grad_norm": 10.694045066833496, "learning_rate": 6.147888831737882e-07, "loss": 0.021035941317677498, "step": 6942 }, { "epoch": 1.8024402907580477, "grad_norm": 2.1221768856048584, "learning_rate": 6.144907685282909e-07, "loss": 0.006173310335725546, "step": 6943 }, { "epoch": 1.80269989615784, "grad_norm": 4.822834491729736, "learning_rate": 6.14193031391929e-07, "loss": 0.010607559233903885, "step": 6944 }, { "epoch": 1.8029595015576323, "grad_norm": 9.762336730957031, "learning_rate": 6.13895671817335e-07, "loss": 0.08699218183755875, "step": 6945 }, { "epoch": 1.8032191069574246, "grad_norm": 10.290810585021973, "learning_rate": 6.135986898570765e-07, "loss": 0.06700006872415543, "step": 6946 }, { "epoch": 1.803478712357217, "grad_norm": 8.607769012451172, "learning_rate": 6.133020855636526e-07, "loss": 0.03244719281792641, "step": 6947 }, { "epoch": 1.8037383177570092, "grad_norm": 7.034428596496582, "learning_rate": 6.130058589894958e-07, "loss": 0.0053398581221699715, "step": 6948 }, { "epoch": 1.8039979231568015, "grad_norm": 6.687631607055664, "learning_rate": 6.127100101869725e-07, "loss": 0.016244791448116302, "step": 6949 }, { "epoch": 1.8042575285565938, "grad_norm": 8.309552192687988, "learning_rate": 6.124145392083817e-07, "loss": 0.00873376801609993, "step": 6950 }, { "epoch": 1.8045171339563861, "grad_norm": 8.419578552246094, "learning_rate": 6.121194461059566e-07, "loss": 0.00893104076385498, "step": 6951 }, { "epoch": 1.8047767393561787, "grad_norm": 8.790657997131348, "learning_rate": 6.118247309318625e-07, "loss": 0.07814355939626694, "step": 6952 }, { "epoch": 1.805036344755971, "grad_norm": 10.56247329711914, "learning_rate": 6.115303937381976e-07, "loss": 0.0522480346262455, "step": 6953 }, { "epoch": 1.8052959501557633, "grad_norm": 2.0722033977508545, "learning_rate": 6.112364345769953e-07, "loss": 0.022485824301838875, "step": 6954 }, { "epoch": 1.8055555555555556, "grad_norm": 10.401487350463867, "learning_rate": 6.1094285350022e-07, "loss": 0.07150711119174957, "step": 6955 }, { "epoch": 1.8058151609553479, "grad_norm": 4.899384021759033, "learning_rate": 6.1064965055977e-07, "loss": 0.015711985528469086, "step": 6956 }, { "epoch": 1.8060747663551402, "grad_norm": 6.135985374450684, "learning_rate": 6.103568258074773e-07, "loss": 0.018938610330224037, "step": 6957 }, { "epoch": 1.8063343717549325, "grad_norm": 4.850893497467041, "learning_rate": 6.100643792951065e-07, "loss": 0.025099219754338264, "step": 6958 }, { "epoch": 1.8065939771547248, "grad_norm": 8.26452350616455, "learning_rate": 6.097723110743556e-07, "loss": 0.012266355566680431, "step": 6959 }, { "epoch": 1.8068535825545171, "grad_norm": 8.757819175720215, "learning_rate": 6.094806211968551e-07, "loss": 0.012962844222784042, "step": 6960 }, { "epoch": 1.8071131879543094, "grad_norm": 8.190850257873535, "learning_rate": 6.091893097141695e-07, "loss": 0.02995712123811245, "step": 6961 }, { "epoch": 1.8073727933541017, "grad_norm": 2.3040359020233154, "learning_rate": 6.088983766777959e-07, "loss": 0.0029566960874944925, "step": 6962 }, { "epoch": 1.807632398753894, "grad_norm": 9.298532485961914, "learning_rate": 6.086078221391644e-07, "loss": 0.04894959181547165, "step": 6963 }, { "epoch": 1.8078920041536866, "grad_norm": 9.300383567810059, "learning_rate": 6.083176461496389e-07, "loss": 0.008220667950809002, "step": 6964 }, { "epoch": 1.8081516095534789, "grad_norm": 9.785250663757324, "learning_rate": 6.08027848760515e-07, "loss": 0.03720194473862648, "step": 6965 }, { "epoch": 1.8084112149532712, "grad_norm": 10.403316497802734, "learning_rate": 6.077384300230233e-07, "loss": 0.14141370356082916, "step": 6966 }, { "epoch": 1.8086708203530635, "grad_norm": 9.27656078338623, "learning_rate": 6.074493899883259e-07, "loss": 0.02469533123075962, "step": 6967 }, { "epoch": 1.8089304257528558, "grad_norm": 10.055436134338379, "learning_rate": 6.07160728707518e-07, "loss": 0.06988561153411865, "step": 6968 }, { "epoch": 1.809190031152648, "grad_norm": 11.640408515930176, "learning_rate": 6.068724462316291e-07, "loss": 0.013249313458800316, "step": 6969 }, { "epoch": 1.8094496365524404, "grad_norm": 4.977053165435791, "learning_rate": 6.065845426116207e-07, "loss": 0.007877876050770283, "step": 6970 }, { "epoch": 1.8097092419522327, "grad_norm": 4.889413833618164, "learning_rate": 6.062970178983869e-07, "loss": 0.0037462380714714527, "step": 6971 }, { "epoch": 1.809968847352025, "grad_norm": 6.657378673553467, "learning_rate": 6.060098721427566e-07, "loss": 0.014752604067325592, "step": 6972 }, { "epoch": 1.8102284527518173, "grad_norm": 1.3713631629943848, "learning_rate": 6.057231053954895e-07, "loss": 0.0031246282160282135, "step": 6973 }, { "epoch": 1.8104880581516096, "grad_norm": 8.260441780090332, "learning_rate": 6.054367177072803e-07, "loss": 0.08222299814224243, "step": 6974 }, { "epoch": 1.810747663551402, "grad_norm": 6.388847827911377, "learning_rate": 6.051507091287554e-07, "loss": 0.02898695133626461, "step": 6975 }, { "epoch": 1.8110072689511942, "grad_norm": 9.118659973144531, "learning_rate": 6.048650797104746e-07, "loss": 0.101046621799469, "step": 6976 }, { "epoch": 1.8112668743509865, "grad_norm": 6.368597507476807, "learning_rate": 6.045798295029305e-07, "loss": 0.017099525779485703, "step": 6977 }, { "epoch": 1.8115264797507789, "grad_norm": 5.347561836242676, "learning_rate": 6.042949585565491e-07, "loss": 0.01634054444730282, "step": 6978 }, { "epoch": 1.8117860851505712, "grad_norm": 2.9142396450042725, "learning_rate": 6.040104669216889e-07, "loss": 0.0042061153799295425, "step": 6979 }, { "epoch": 1.8120456905503635, "grad_norm": 6.9239501953125, "learning_rate": 6.037263546486413e-07, "loss": 0.01240929402410984, "step": 6980 }, { "epoch": 1.8123052959501558, "grad_norm": 12.032729148864746, "learning_rate": 6.03442621787631e-07, "loss": 0.027045229449868202, "step": 6981 }, { "epoch": 1.812564901349948, "grad_norm": 2.540969133377075, "learning_rate": 6.031592683888158e-07, "loss": 0.014227376319468021, "step": 6982 }, { "epoch": 1.8128245067497404, "grad_norm": 3.956817388534546, "learning_rate": 6.028762945022857e-07, "loss": 0.01712971180677414, "step": 6983 }, { "epoch": 1.8130841121495327, "grad_norm": 8.472990989685059, "learning_rate": 6.02593700178064e-07, "loss": 0.025772301480174065, "step": 6984 }, { "epoch": 1.813343717549325, "grad_norm": 9.46380615234375, "learning_rate": 6.023114854661073e-07, "loss": 0.14395782351493835, "step": 6985 }, { "epoch": 1.8136033229491173, "grad_norm": 9.843769073486328, "learning_rate": 6.020296504163043e-07, "loss": 0.08136820793151855, "step": 6986 }, { "epoch": 1.8138629283489096, "grad_norm": 5.092779159545898, "learning_rate": 6.017481950784767e-07, "loss": 0.007152100093662739, "step": 6987 }, { "epoch": 1.814122533748702, "grad_norm": 11.064294815063477, "learning_rate": 6.014671195023805e-07, "loss": 0.031952887773513794, "step": 6988 }, { "epoch": 1.8143821391484942, "grad_norm": 9.893150329589844, "learning_rate": 6.01186423737702e-07, "loss": 0.042765840888023376, "step": 6989 }, { "epoch": 1.8146417445482865, "grad_norm": 9.483115196228027, "learning_rate": 6.009061078340631e-07, "loss": 0.03235968202352524, "step": 6990 }, { "epoch": 1.8149013499480788, "grad_norm": 10.177200317382812, "learning_rate": 6.00626171841016e-07, "loss": 0.01768338307738304, "step": 6991 }, { "epoch": 1.8151609553478711, "grad_norm": 9.326446533203125, "learning_rate": 6.003466158080478e-07, "loss": 0.020783431828022003, "step": 6992 }, { "epoch": 1.8154205607476634, "grad_norm": 2.424657106399536, "learning_rate": 6.000674397845777e-07, "loss": 0.013541575521230698, "step": 6993 }, { "epoch": 1.8156801661474558, "grad_norm": 3.495759963989258, "learning_rate": 5.997886438199571e-07, "loss": 0.006027591414749622, "step": 6994 }, { "epoch": 1.815939771547248, "grad_norm": 11.909066200256348, "learning_rate": 5.995102279634708e-07, "loss": 0.11273613572120667, "step": 6995 }, { "epoch": 1.8161993769470404, "grad_norm": 3.071225881576538, "learning_rate": 5.992321922643364e-07, "loss": 0.016541825607419014, "step": 6996 }, { "epoch": 1.8164589823468327, "grad_norm": 8.145153999328613, "learning_rate": 5.98954536771705e-07, "loss": 0.012987663969397545, "step": 6997 }, { "epoch": 1.816718587746625, "grad_norm": 7.287134170532227, "learning_rate": 5.986772615346586e-07, "loss": 0.011793967336416245, "step": 6998 }, { "epoch": 1.8169781931464173, "grad_norm": 5.965941905975342, "learning_rate": 5.984003666022135e-07, "loss": 0.03827587887644768, "step": 6999 }, { "epoch": 1.8172377985462098, "grad_norm": 8.304347038269043, "learning_rate": 5.981238520233188e-07, "loss": 0.038202106952667236, "step": 7000 }, { "epoch": 1.8174974039460021, "grad_norm": 7.120350360870361, "learning_rate": 5.978477178468556e-07, "loss": 0.01011229120194912, "step": 7001 }, { "epoch": 1.8177570093457944, "grad_norm": 0.8236815929412842, "learning_rate": 5.975719641216379e-07, "loss": 0.0012287532445043325, "step": 7002 }, { "epoch": 1.8180166147455867, "grad_norm": 8.526314735412598, "learning_rate": 5.972965908964129e-07, "loss": 0.060406483709812164, "step": 7003 }, { "epoch": 1.818276220145379, "grad_norm": 8.32077693939209, "learning_rate": 5.970215982198602e-07, "loss": 0.0325218066573143, "step": 7004 }, { "epoch": 1.8185358255451713, "grad_norm": 10.628438949584961, "learning_rate": 5.967469861405927e-07, "loss": 0.09726157039403915, "step": 7005 }, { "epoch": 1.8187954309449637, "grad_norm": 9.217697143554688, "learning_rate": 5.964727547071548e-07, "loss": 0.0555657334625721, "step": 7006 }, { "epoch": 1.819055036344756, "grad_norm": 1.3345104455947876, "learning_rate": 5.961989039680243e-07, "loss": 0.005997347645461559, "step": 7007 }, { "epoch": 1.8193146417445483, "grad_norm": 3.11525297164917, "learning_rate": 5.959254339716127e-07, "loss": 0.01548727322369814, "step": 7008 }, { "epoch": 1.8195742471443406, "grad_norm": 3.571136236190796, "learning_rate": 5.956523447662624e-07, "loss": 0.0024633242283016443, "step": 7009 }, { "epoch": 1.8198338525441329, "grad_norm": 6.89959716796875, "learning_rate": 5.953796364002491e-07, "loss": 0.005365974269807339, "step": 7010 }, { "epoch": 1.8200934579439252, "grad_norm": 6.861233234405518, "learning_rate": 5.951073089217822e-07, "loss": 0.0068832156248390675, "step": 7011 }, { "epoch": 1.8203530633437177, "grad_norm": 10.413665771484375, "learning_rate": 5.948353623790024e-07, "loss": 0.04352939873933792, "step": 7012 }, { "epoch": 1.82061266874351, "grad_norm": 9.547194480895996, "learning_rate": 5.94563796819984e-07, "loss": 0.0284085962921381, "step": 7013 }, { "epoch": 1.8208722741433023, "grad_norm": 1.9859970808029175, "learning_rate": 5.942926122927334e-07, "loss": 0.0043208845891058445, "step": 7014 }, { "epoch": 1.8211318795430946, "grad_norm": 9.199363708496094, "learning_rate": 5.940218088451894e-07, "loss": 0.013374499045312405, "step": 7015 }, { "epoch": 1.821391484942887, "grad_norm": 6.740625858306885, "learning_rate": 5.937513865252247e-07, "loss": 0.02082831785082817, "step": 7016 }, { "epoch": 1.8216510903426792, "grad_norm": 9.60734748840332, "learning_rate": 5.934813453806434e-07, "loss": 0.018606819212436676, "step": 7017 }, { "epoch": 1.8219106957424716, "grad_norm": 8.6329927444458, "learning_rate": 5.932116854591819e-07, "loss": 0.07708913832902908, "step": 7018 }, { "epoch": 1.8221703011422639, "grad_norm": 10.89633846282959, "learning_rate": 5.929424068085109e-07, "loss": 0.029683228582143784, "step": 7019 }, { "epoch": 1.8224299065420562, "grad_norm": 12.394777297973633, "learning_rate": 5.926735094762325e-07, "loss": 0.03278720751404762, "step": 7020 }, { "epoch": 1.8226895119418485, "grad_norm": 10.110406875610352, "learning_rate": 5.924049935098812e-07, "loss": 0.08387445658445358, "step": 7021 }, { "epoch": 1.8229491173416408, "grad_norm": 11.550761222839355, "learning_rate": 5.921368589569246e-07, "loss": 0.043170858174562454, "step": 7022 }, { "epoch": 1.823208722741433, "grad_norm": 4.486028671264648, "learning_rate": 5.918691058647626e-07, "loss": 0.03240898624062538, "step": 7023 }, { "epoch": 1.8234683281412254, "grad_norm": 3.477335214614868, "learning_rate": 5.916017342807287e-07, "loss": 0.018168803304433823, "step": 7024 }, { "epoch": 1.8237279335410177, "grad_norm": 7.855131149291992, "learning_rate": 5.913347442520865e-07, "loss": 0.009004930034279823, "step": 7025 }, { "epoch": 1.82398753894081, "grad_norm": 10.384000778198242, "learning_rate": 5.910681358260355e-07, "loss": 0.0334426611661911, "step": 7026 }, { "epoch": 1.8242471443406023, "grad_norm": 12.055850982666016, "learning_rate": 5.908019090497045e-07, "loss": 0.06286431849002838, "step": 7027 }, { "epoch": 1.8245067497403946, "grad_norm": 8.802350997924805, "learning_rate": 5.905360639701571e-07, "loss": 0.026965994387865067, "step": 7028 }, { "epoch": 1.824766355140187, "grad_norm": 8.43641471862793, "learning_rate": 5.902706006343887e-07, "loss": 0.05900491401553154, "step": 7029 }, { "epoch": 1.8250259605399792, "grad_norm": 10.490011215209961, "learning_rate": 5.900055190893262e-07, "loss": 0.02845947816967964, "step": 7030 }, { "epoch": 1.8252855659397715, "grad_norm": 6.654792785644531, "learning_rate": 5.897408193818311e-07, "loss": 0.014752104878425598, "step": 7031 }, { "epoch": 1.8255451713395638, "grad_norm": 9.88711166381836, "learning_rate": 5.894765015586959e-07, "loss": 0.056192368268966675, "step": 7032 }, { "epoch": 1.8258047767393562, "grad_norm": 3.537806987762451, "learning_rate": 5.892125656666454e-07, "loss": 0.00874654296785593, "step": 7033 }, { "epoch": 1.8260643821391485, "grad_norm": 9.079551696777344, "learning_rate": 5.889490117523381e-07, "loss": 0.07682154327630997, "step": 7034 }, { "epoch": 1.8263239875389408, "grad_norm": 7.941117286682129, "learning_rate": 5.886858398623635e-07, "loss": 0.05196930468082428, "step": 7035 }, { "epoch": 1.826583592938733, "grad_norm": 7.236630916595459, "learning_rate": 5.884230500432455e-07, "loss": 0.018729086965322495, "step": 7036 }, { "epoch": 1.8268431983385254, "grad_norm": 9.950838088989258, "learning_rate": 5.881606423414383e-07, "loss": 0.05464792996644974, "step": 7037 }, { "epoch": 1.8271028037383177, "grad_norm": 4.1221923828125, "learning_rate": 5.878986168033301e-07, "loss": 0.015750302001833916, "step": 7038 }, { "epoch": 1.82736240913811, "grad_norm": 9.81890869140625, "learning_rate": 5.876369734752411e-07, "loss": 0.03524380549788475, "step": 7039 }, { "epoch": 1.8276220145379023, "grad_norm": 7.8537278175354, "learning_rate": 5.873757124034234e-07, "loss": 0.07690339535474777, "step": 7040 }, { "epoch": 1.8278816199376946, "grad_norm": 6.2707672119140625, "learning_rate": 5.871148336340623e-07, "loss": 0.020152747631072998, "step": 7041 }, { "epoch": 1.828141225337487, "grad_norm": 8.137767791748047, "learning_rate": 5.868543372132751e-07, "loss": 0.028489643707871437, "step": 7042 }, { "epoch": 1.8284008307372792, "grad_norm": 10.847209930419922, "learning_rate": 5.865942231871113e-07, "loss": 0.09178946912288666, "step": 7043 }, { "epoch": 1.8286604361370715, "grad_norm": 4.637927055358887, "learning_rate": 5.863344916015538e-07, "loss": 0.02979729138314724, "step": 7044 }, { "epoch": 1.8289200415368638, "grad_norm": 11.008584022521973, "learning_rate": 5.86075142502517e-07, "loss": 0.031533509492874146, "step": 7045 }, { "epoch": 1.8291796469366561, "grad_norm": 8.408496856689453, "learning_rate": 5.858161759358472e-07, "loss": 0.06926422566175461, "step": 7046 }, { "epoch": 1.8294392523364484, "grad_norm": 4.899702072143555, "learning_rate": 5.855575919473248e-07, "loss": 0.023001650348305702, "step": 7047 }, { "epoch": 1.829698857736241, "grad_norm": 8.840087890625, "learning_rate": 5.852993905826606e-07, "loss": 0.06040545552968979, "step": 7048 }, { "epoch": 1.8299584631360333, "grad_norm": 8.049409866333008, "learning_rate": 5.850415718874988e-07, "loss": 0.01554460171610117, "step": 7049 }, { "epoch": 1.8302180685358256, "grad_norm": 9.168421745300293, "learning_rate": 5.847841359074165e-07, "loss": 0.05763794481754303, "step": 7050 }, { "epoch": 1.8304776739356179, "grad_norm": 10.416366577148438, "learning_rate": 5.845270826879221e-07, "loss": 0.10731260478496552, "step": 7051 }, { "epoch": 1.8307372793354102, "grad_norm": 12.518858909606934, "learning_rate": 5.842704122744569e-07, "loss": 0.034153204411268234, "step": 7052 }, { "epoch": 1.8309968847352025, "grad_norm": 11.636221885681152, "learning_rate": 5.840141247123938e-07, "loss": 0.07911023497581482, "step": 7053 }, { "epoch": 1.8312564901349948, "grad_norm": 7.168910026550293, "learning_rate": 5.837582200470388e-07, "loss": 0.04227122291922569, "step": 7054 }, { "epoch": 1.8315160955347871, "grad_norm": 9.20552921295166, "learning_rate": 5.835026983236308e-07, "loss": 0.02098730579018593, "step": 7055 }, { "epoch": 1.8317757009345794, "grad_norm": 10.47717571258545, "learning_rate": 5.832475595873389e-07, "loss": 0.09740473330020905, "step": 7056 }, { "epoch": 1.8320353063343717, "grad_norm": 8.421854019165039, "learning_rate": 5.829928038832668e-07, "loss": 0.0457952581346035, "step": 7057 }, { "epoch": 1.832294911734164, "grad_norm": 2.9756197929382324, "learning_rate": 5.827384312564488e-07, "loss": 0.012999461963772774, "step": 7058 }, { "epoch": 1.8325545171339563, "grad_norm": 7.147493839263916, "learning_rate": 5.824844417518527e-07, "loss": 0.01582597754895687, "step": 7059 }, { "epoch": 1.8328141225337489, "grad_norm": 1.29714834690094, "learning_rate": 5.822308354143776e-07, "loss": 0.0033699499908834696, "step": 7060 }, { "epoch": 1.8330737279335412, "grad_norm": 9.184773445129395, "learning_rate": 5.819776122888553e-07, "loss": 0.02755962312221527, "step": 7061 }, { "epoch": 1.8333333333333335, "grad_norm": 9.270790100097656, "learning_rate": 5.817247724200503e-07, "loss": 0.047803837805986404, "step": 7062 }, { "epoch": 1.8335929387331258, "grad_norm": 10.189233779907227, "learning_rate": 5.814723158526586e-07, "loss": 0.030412498861551285, "step": 7063 }, { "epoch": 1.833852544132918, "grad_norm": 10.541325569152832, "learning_rate": 5.812202426313087e-07, "loss": 0.046001747250556946, "step": 7064 }, { "epoch": 1.8341121495327104, "grad_norm": 13.31861400604248, "learning_rate": 5.809685528005614e-07, "loss": 0.006997935939580202, "step": 7065 }, { "epoch": 1.8343717549325027, "grad_norm": 11.04265022277832, "learning_rate": 5.807172464049096e-07, "loss": 0.0196666456758976, "step": 7066 }, { "epoch": 1.834631360332295, "grad_norm": 11.55837345123291, "learning_rate": 5.80466323488779e-07, "loss": 0.0828792154788971, "step": 7067 }, { "epoch": 1.8348909657320873, "grad_norm": 6.334250450134277, "learning_rate": 5.802157840965264e-07, "loss": 0.013970816507935524, "step": 7068 }, { "epoch": 1.8351505711318796, "grad_norm": 9.921738624572754, "learning_rate": 5.799656282724417e-07, "loss": 0.025834564119577408, "step": 7069 }, { "epoch": 1.835410176531672, "grad_norm": 2.8857812881469727, "learning_rate": 5.797158560607467e-07, "loss": 0.016830625012516975, "step": 7070 }, { "epoch": 1.8356697819314642, "grad_norm": 1.729339361190796, "learning_rate": 5.794664675055956e-07, "loss": 0.00388575391843915, "step": 7071 }, { "epoch": 1.8359293873312565, "grad_norm": 0.4572497010231018, "learning_rate": 5.792174626510742e-07, "loss": 0.0009030423825606704, "step": 7072 }, { "epoch": 1.8361889927310489, "grad_norm": 8.847635269165039, "learning_rate": 5.789688415412015e-07, "loss": 0.006922398693859577, "step": 7073 }, { "epoch": 1.8364485981308412, "grad_norm": 8.302247047424316, "learning_rate": 5.787206042199273e-07, "loss": 0.04884713888168335, "step": 7074 }, { "epoch": 1.8367082035306335, "grad_norm": 1.5249654054641724, "learning_rate": 5.784727507311344e-07, "loss": 0.0016657992964610457, "step": 7075 }, { "epoch": 1.8369678089304258, "grad_norm": 1.3707866668701172, "learning_rate": 5.78225281118638e-07, "loss": 0.002170937368646264, "step": 7076 }, { "epoch": 1.837227414330218, "grad_norm": 14.452722549438477, "learning_rate": 5.779781954261845e-07, "loss": 0.039724335074424744, "step": 7077 }, { "epoch": 1.8374870197300104, "grad_norm": 6.525069236755371, "learning_rate": 5.777314936974541e-07, "loss": 0.039313994348049164, "step": 7078 }, { "epoch": 1.8377466251298027, "grad_norm": 6.97569465637207, "learning_rate": 5.774851759760566e-07, "loss": 0.023251503705978394, "step": 7079 }, { "epoch": 1.838006230529595, "grad_norm": 5.9677228927612305, "learning_rate": 5.77239242305536e-07, "loss": 0.0029078680090606213, "step": 7080 }, { "epoch": 1.8382658359293873, "grad_norm": 7.644233703613281, "learning_rate": 5.769936927293679e-07, "loss": 0.01901204325258732, "step": 7081 }, { "epoch": 1.8385254413291796, "grad_norm": 7.120748519897461, "learning_rate": 5.767485272909598e-07, "loss": 0.00980173796415329, "step": 7082 }, { "epoch": 1.838785046728972, "grad_norm": 6.04267692565918, "learning_rate": 5.765037460336512e-07, "loss": 0.013684432953596115, "step": 7083 }, { "epoch": 1.8390446521287642, "grad_norm": 1.686445951461792, "learning_rate": 5.762593490007135e-07, "loss": 0.008787917904555798, "step": 7084 }, { "epoch": 1.8393042575285565, "grad_norm": 10.677783966064453, "learning_rate": 5.76015336235351e-07, "loss": 0.1340746283531189, "step": 7085 }, { "epoch": 1.8395638629283488, "grad_norm": 10.577898979187012, "learning_rate": 5.757717077807e-07, "loss": 0.09797898679971695, "step": 7086 }, { "epoch": 1.8398234683281411, "grad_norm": 12.307374000549316, "learning_rate": 5.75528463679827e-07, "loss": 0.04110163077712059, "step": 7087 }, { "epoch": 1.8400830737279334, "grad_norm": 9.579166412353516, "learning_rate": 5.752856039757334e-07, "loss": 0.05349595099687576, "step": 7088 }, { "epoch": 1.8403426791277258, "grad_norm": 11.73398494720459, "learning_rate": 5.750431287113501e-07, "loss": 0.03140203654766083, "step": 7089 }, { "epoch": 1.840602284527518, "grad_norm": 7.282037734985352, "learning_rate": 5.74801037929542e-07, "loss": 0.011492948979139328, "step": 7090 }, { "epoch": 1.8408618899273104, "grad_norm": 1.414275050163269, "learning_rate": 5.745593316731051e-07, "loss": 0.004638227634131908, "step": 7091 }, { "epoch": 1.8411214953271027, "grad_norm": 9.843428611755371, "learning_rate": 5.74318009984767e-07, "loss": 0.03294308856129646, "step": 7092 }, { "epoch": 1.841381100726895, "grad_norm": 15.437151908874512, "learning_rate": 5.740770729071887e-07, "loss": 0.035484664142131805, "step": 7093 }, { "epoch": 1.8416407061266873, "grad_norm": 9.786811828613281, "learning_rate": 5.738365204829617e-07, "loss": 0.056815121322870255, "step": 7094 }, { "epoch": 1.8419003115264796, "grad_norm": 3.553903579711914, "learning_rate": 5.735963527546102e-07, "loss": 0.02357841283082962, "step": 7095 }, { "epoch": 1.842159916926272, "grad_norm": 11.555122375488281, "learning_rate": 5.733565697645906e-07, "loss": 0.048775333911180496, "step": 7096 }, { "epoch": 1.8424195223260644, "grad_norm": 9.513813018798828, "learning_rate": 5.731171715552908e-07, "loss": 0.030569633468985558, "step": 7097 }, { "epoch": 1.8426791277258567, "grad_norm": 1.55464768409729, "learning_rate": 5.728781581690312e-07, "loss": 0.0025847123470157385, "step": 7098 }, { "epoch": 1.842938733125649, "grad_norm": 7.917464733123779, "learning_rate": 5.726395296480637e-07, "loss": 0.01846424862742424, "step": 7099 }, { "epoch": 1.8431983385254413, "grad_norm": 7.190680503845215, "learning_rate": 5.724012860345723e-07, "loss": 0.012623647227883339, "step": 7100 }, { "epoch": 1.8434579439252337, "grad_norm": 1.5482510328292847, "learning_rate": 5.721634273706735e-07, "loss": 0.00266761495731771, "step": 7101 }, { "epoch": 1.843717549325026, "grad_norm": 5.341789722442627, "learning_rate": 5.719259536984147e-07, "loss": 0.016963662579655647, "step": 7102 }, { "epoch": 1.8439771547248183, "grad_norm": 10.320176124572754, "learning_rate": 5.716888650597758e-07, "loss": 0.06074162945151329, "step": 7103 }, { "epoch": 1.8442367601246106, "grad_norm": 5.5775980949401855, "learning_rate": 5.714521614966689e-07, "loss": 0.008885013870894909, "step": 7104 }, { "epoch": 1.8444963655244029, "grad_norm": 6.082468509674072, "learning_rate": 5.71215843050938e-07, "loss": 0.016167812049388885, "step": 7105 }, { "epoch": 1.8447559709241952, "grad_norm": 6.982146739959717, "learning_rate": 5.709799097643583e-07, "loss": 0.028267376124858856, "step": 7106 }, { "epoch": 1.8450155763239875, "grad_norm": 9.515826225280762, "learning_rate": 5.707443616786376e-07, "loss": 0.07062938809394836, "step": 7107 }, { "epoch": 1.8452751817237798, "grad_norm": 7.927002906799316, "learning_rate": 5.705091988354152e-07, "loss": 0.03168899565935135, "step": 7108 }, { "epoch": 1.8455347871235723, "grad_norm": 6.653871059417725, "learning_rate": 5.702744212762634e-07, "loss": 0.010490147396922112, "step": 7109 }, { "epoch": 1.8457943925233646, "grad_norm": 6.111510276794434, "learning_rate": 5.700400290426841e-07, "loss": 0.004136575385928154, "step": 7110 }, { "epoch": 1.846053997923157, "grad_norm": 7.660833358764648, "learning_rate": 5.698060221761133e-07, "loss": 0.028860479593276978, "step": 7111 }, { "epoch": 1.8463136033229492, "grad_norm": 8.453070640563965, "learning_rate": 5.695724007179182e-07, "loss": 0.008315572515130043, "step": 7112 }, { "epoch": 1.8465732087227416, "grad_norm": 5.500887393951416, "learning_rate": 5.693391647093975e-07, "loss": 0.008316153660416603, "step": 7113 }, { "epoch": 1.8468328141225339, "grad_norm": 3.0014517307281494, "learning_rate": 5.69106314191782e-07, "loss": 0.012168933637440205, "step": 7114 }, { "epoch": 1.8470924195223262, "grad_norm": 4.771364212036133, "learning_rate": 5.688738492062342e-07, "loss": 0.009310727007687092, "step": 7115 }, { "epoch": 1.8473520249221185, "grad_norm": 6.233847618103027, "learning_rate": 5.686417697938483e-07, "loss": 0.020600277930498123, "step": 7116 }, { "epoch": 1.8476116303219108, "grad_norm": 2.9867501258850098, "learning_rate": 5.684100759956516e-07, "loss": 0.0065556601621210575, "step": 7117 }, { "epoch": 1.847871235721703, "grad_norm": 6.842892169952393, "learning_rate": 5.681787678526015e-07, "loss": 0.023744281381368637, "step": 7118 }, { "epoch": 1.8481308411214954, "grad_norm": 9.462162017822266, "learning_rate": 5.679478454055882e-07, "loss": 0.05869996175169945, "step": 7119 }, { "epoch": 1.8483904465212877, "grad_norm": 9.974279403686523, "learning_rate": 5.677173086954331e-07, "loss": 0.037172190845012665, "step": 7120 }, { "epoch": 1.84865005192108, "grad_norm": 9.58400821685791, "learning_rate": 5.674871577628907e-07, "loss": 0.017366617918014526, "step": 7121 }, { "epoch": 1.8489096573208723, "grad_norm": 9.977479934692383, "learning_rate": 5.672573926486457e-07, "loss": 0.08748944848775864, "step": 7122 }, { "epoch": 1.8491692627206646, "grad_norm": 5.016042709350586, "learning_rate": 5.670280133933152e-07, "loss": 0.007311730179935694, "step": 7123 }, { "epoch": 1.849428868120457, "grad_norm": 4.424811840057373, "learning_rate": 5.66799020037449e-07, "loss": 0.003711764933541417, "step": 7124 }, { "epoch": 1.8496884735202492, "grad_norm": 4.17465353012085, "learning_rate": 5.66570412621527e-07, "loss": 0.004782531410455704, "step": 7125 }, { "epoch": 1.8499480789200415, "grad_norm": 6.549159049987793, "learning_rate": 5.663421911859622e-07, "loss": 0.008740774355828762, "step": 7126 }, { "epoch": 1.8502076843198338, "grad_norm": 13.068856239318848, "learning_rate": 5.661143557710988e-07, "loss": 0.07260838150978088, "step": 7127 }, { "epoch": 1.8504672897196262, "grad_norm": 10.06566333770752, "learning_rate": 5.658869064172132e-07, "loss": 0.10511235892772675, "step": 7128 }, { "epoch": 1.8507268951194185, "grad_norm": 5.519456386566162, "learning_rate": 5.656598431645127e-07, "loss": 0.009374242275953293, "step": 7129 }, { "epoch": 1.8509865005192108, "grad_norm": 7.8293633460998535, "learning_rate": 5.654331660531374e-07, "loss": 0.014943500980734825, "step": 7130 }, { "epoch": 1.851246105919003, "grad_norm": 8.422245025634766, "learning_rate": 5.652068751231583e-07, "loss": 0.012371067889034748, "step": 7131 }, { "epoch": 1.8515057113187954, "grad_norm": 13.830862998962402, "learning_rate": 5.649809704145786e-07, "loss": 0.016288984566926956, "step": 7132 }, { "epoch": 1.8517653167185877, "grad_norm": 2.5884830951690674, "learning_rate": 5.64755451967333e-07, "loss": 0.011993791908025742, "step": 7133 }, { "epoch": 1.85202492211838, "grad_norm": 5.544191837310791, "learning_rate": 5.645303198212878e-07, "loss": 0.006724104750901461, "step": 7134 }, { "epoch": 1.8522845275181723, "grad_norm": 3.5221900939941406, "learning_rate": 5.643055740162418e-07, "loss": 0.026850871741771698, "step": 7135 }, { "epoch": 1.8525441329179646, "grad_norm": 8.111618995666504, "learning_rate": 5.640812145919245e-07, "loss": 0.07809922099113464, "step": 7136 }, { "epoch": 1.852803738317757, "grad_norm": 7.69135046005249, "learning_rate": 5.638572415879972e-07, "loss": 0.014455877244472504, "step": 7137 }, { "epoch": 1.8530633437175492, "grad_norm": 0.43883514404296875, "learning_rate": 5.63633655044054e-07, "loss": 0.0014796615578234196, "step": 7138 }, { "epoch": 1.8533229491173415, "grad_norm": 10.281201362609863, "learning_rate": 5.63410454999619e-07, "loss": 0.03169949725270271, "step": 7139 }, { "epoch": 1.8535825545171338, "grad_norm": 9.856832504272461, "learning_rate": 5.6318764149415e-07, "loss": 0.08959655463695526, "step": 7140 }, { "epoch": 1.8538421599169261, "grad_norm": 1.799835205078125, "learning_rate": 5.629652145670338e-07, "loss": 0.004534983541816473, "step": 7141 }, { "epoch": 1.8541017653167184, "grad_norm": 6.235176086425781, "learning_rate": 5.627431742575914e-07, "loss": 0.02182781882584095, "step": 7142 }, { "epoch": 1.8543613707165107, "grad_norm": 8.107626914978027, "learning_rate": 5.625215206050745e-07, "loss": 0.015551939606666565, "step": 7143 }, { "epoch": 1.854620976116303, "grad_norm": 10.377684593200684, "learning_rate": 5.623002536486661e-07, "loss": 0.04508105292916298, "step": 7144 }, { "epoch": 1.8548805815160956, "grad_norm": 10.230069160461426, "learning_rate": 5.620793734274812e-07, "loss": 0.05690186098217964, "step": 7145 }, { "epoch": 1.855140186915888, "grad_norm": 8.617100715637207, "learning_rate": 5.618588799805662e-07, "loss": 0.08083365112543106, "step": 7146 }, { "epoch": 1.8553997923156802, "grad_norm": 8.91873550415039, "learning_rate": 5.616387733468992e-07, "loss": 0.10409849137067795, "step": 7147 }, { "epoch": 1.8556593977154725, "grad_norm": 3.116891622543335, "learning_rate": 5.614190535653909e-07, "loss": 0.014779515564441681, "step": 7148 }, { "epoch": 1.8559190031152648, "grad_norm": 10.723101615905762, "learning_rate": 5.611997206748815e-07, "loss": 0.014233250170946121, "step": 7149 }, { "epoch": 1.8561786085150571, "grad_norm": 9.946467399597168, "learning_rate": 5.60980774714145e-07, "loss": 0.01609407551586628, "step": 7150 }, { "epoch": 1.8564382139148494, "grad_norm": 2.037278175354004, "learning_rate": 5.607622157218851e-07, "loss": 0.004086499102413654, "step": 7151 }, { "epoch": 1.8566978193146417, "grad_norm": 8.43525505065918, "learning_rate": 5.60544043736739e-07, "loss": 0.07602342218160629, "step": 7152 }, { "epoch": 1.856957424714434, "grad_norm": 3.4446864128112793, "learning_rate": 5.60326258797274e-07, "loss": 0.003793173935264349, "step": 7153 }, { "epoch": 1.8572170301142263, "grad_norm": 8.198193550109863, "learning_rate": 5.601088609419893e-07, "loss": 0.008590596728026867, "step": 7154 }, { "epoch": 1.8574766355140186, "grad_norm": 6.772740840911865, "learning_rate": 5.598918502093165e-07, "loss": 0.015754075720906258, "step": 7155 }, { "epoch": 1.857736240913811, "grad_norm": 3.7576990127563477, "learning_rate": 5.596752266376175e-07, "loss": 0.004835526924580336, "step": 7156 }, { "epoch": 1.8579958463136035, "grad_norm": 8.787276268005371, "learning_rate": 5.594589902651866e-07, "loss": 0.1117585152387619, "step": 7157 }, { "epoch": 1.8582554517133958, "grad_norm": 3.0623207092285156, "learning_rate": 5.592431411302498e-07, "loss": 0.005607916973531246, "step": 7158 }, { "epoch": 1.858515057113188, "grad_norm": 5.935207366943359, "learning_rate": 5.590276792709639e-07, "loss": 0.004343576729297638, "step": 7159 }, { "epoch": 1.8587746625129804, "grad_norm": 7.292799949645996, "learning_rate": 5.588126047254173e-07, "loss": 0.0315997451543808, "step": 7160 }, { "epoch": 1.8590342679127727, "grad_norm": 7.377762317657471, "learning_rate": 5.58597917531631e-07, "loss": 0.02903793193399906, "step": 7161 }, { "epoch": 1.859293873312565, "grad_norm": 4.192690849304199, "learning_rate": 5.583836177275561e-07, "loss": 0.010311871767044067, "step": 7162 }, { "epoch": 1.8595534787123573, "grad_norm": 8.68257999420166, "learning_rate": 5.581697053510768e-07, "loss": 0.02377125434577465, "step": 7163 }, { "epoch": 1.8598130841121496, "grad_norm": 2.1126744747161865, "learning_rate": 5.579561804400068e-07, "loss": 0.0027141273021698, "step": 7164 }, { "epoch": 1.860072689511942, "grad_norm": 4.439840793609619, "learning_rate": 5.577430430320932e-07, "loss": 0.02185070514678955, "step": 7165 }, { "epoch": 1.8603322949117342, "grad_norm": 7.237804412841797, "learning_rate": 5.575302931650135e-07, "loss": 0.023341089487075806, "step": 7166 }, { "epoch": 1.8605919003115265, "grad_norm": 8.557365417480469, "learning_rate": 5.573179308763772e-07, "loss": 0.076737180352211, "step": 7167 }, { "epoch": 1.8608515057113189, "grad_norm": 1.31730318069458, "learning_rate": 5.571059562037244e-07, "loss": 0.004120787605643272, "step": 7168 }, { "epoch": 1.8611111111111112, "grad_norm": 3.5305960178375244, "learning_rate": 5.568943691845285e-07, "loss": 0.006626635789871216, "step": 7169 }, { "epoch": 1.8613707165109035, "grad_norm": 0.4139617085456848, "learning_rate": 5.566831698561925e-07, "loss": 0.0007430604891851544, "step": 7170 }, { "epoch": 1.8616303219106958, "grad_norm": 8.46349811553955, "learning_rate": 5.56472358256052e-07, "loss": 0.08038397133350372, "step": 7171 }, { "epoch": 1.861889927310488, "grad_norm": 4.5858845710754395, "learning_rate": 5.56261934421373e-07, "loss": 0.020679300650954247, "step": 7172 }, { "epoch": 1.8621495327102804, "grad_norm": 8.376826286315918, "learning_rate": 5.560518983893542e-07, "loss": 0.05598915368318558, "step": 7173 }, { "epoch": 1.8624091381100727, "grad_norm": 10.383721351623535, "learning_rate": 5.558422501971251e-07, "loss": 0.07141001522541046, "step": 7174 }, { "epoch": 1.862668743509865, "grad_norm": 2.6250157356262207, "learning_rate": 5.556329898817467e-07, "loss": 0.012875113636255264, "step": 7175 }, { "epoch": 1.8629283489096573, "grad_norm": 3.8429887294769287, "learning_rate": 5.554241174802112e-07, "loss": 0.0033517847768962383, "step": 7176 }, { "epoch": 1.8631879543094496, "grad_norm": 3.4764201641082764, "learning_rate": 5.552156330294427e-07, "loss": 0.003162545384839177, "step": 7177 }, { "epoch": 1.863447559709242, "grad_norm": 9.065021514892578, "learning_rate": 5.55007536566296e-07, "loss": 0.02354620024561882, "step": 7178 }, { "epoch": 1.8637071651090342, "grad_norm": 2.581683874130249, "learning_rate": 5.547998281275589e-07, "loss": 0.01254834420979023, "step": 7179 }, { "epoch": 1.8639667705088265, "grad_norm": 2.3743138313293457, "learning_rate": 5.545925077499481e-07, "loss": 0.009074247442185879, "step": 7180 }, { "epoch": 1.8642263759086188, "grad_norm": 12.95626449584961, "learning_rate": 5.543855754701142e-07, "loss": 0.02354501560330391, "step": 7181 }, { "epoch": 1.8644859813084111, "grad_norm": 11.125388145446777, "learning_rate": 5.541790313246371e-07, "loss": 0.011617941781878471, "step": 7182 }, { "epoch": 1.8647455867082035, "grad_norm": 5.471608638763428, "learning_rate": 5.539728753500302e-07, "loss": 0.01201359461992979, "step": 7183 }, { "epoch": 1.8650051921079958, "grad_norm": 7.5956597328186035, "learning_rate": 5.537671075827364e-07, "loss": 0.013095404952764511, "step": 7184 }, { "epoch": 1.865264797507788, "grad_norm": 7.762704849243164, "learning_rate": 5.535617280591308e-07, "loss": 0.005629516206681728, "step": 7185 }, { "epoch": 1.8655244029075804, "grad_norm": 1.0082937479019165, "learning_rate": 5.5335673681552e-07, "loss": 0.00137049681507051, "step": 7186 }, { "epoch": 1.8657840083073727, "grad_norm": 10.588264465332031, "learning_rate": 5.531521338881417e-07, "loss": 0.05092274397611618, "step": 7187 }, { "epoch": 1.866043613707165, "grad_norm": 11.327463150024414, "learning_rate": 5.529479193131649e-07, "loss": 0.03240056335926056, "step": 7188 }, { "epoch": 1.8663032191069573, "grad_norm": 4.6938018798828125, "learning_rate": 5.527440931266902e-07, "loss": 0.02075437270104885, "step": 7189 }, { "epoch": 1.8665628245067496, "grad_norm": 8.783570289611816, "learning_rate": 5.525406553647495e-07, "loss": 0.019071325659751892, "step": 7190 }, { "epoch": 1.866822429906542, "grad_norm": 6.438575267791748, "learning_rate": 5.523376060633054e-07, "loss": 0.014284491539001465, "step": 7191 }, { "epoch": 1.8670820353063342, "grad_norm": 2.346233367919922, "learning_rate": 5.52134945258253e-07, "loss": 0.004122845828533173, "step": 7192 }, { "epoch": 1.8673416407061267, "grad_norm": 3.1009929180145264, "learning_rate": 5.519326729854176e-07, "loss": 0.0051169563084840775, "step": 7193 }, { "epoch": 1.867601246105919, "grad_norm": 2.964980125427246, "learning_rate": 5.517307892805569e-07, "loss": 0.007458471227437258, "step": 7194 }, { "epoch": 1.8678608515057114, "grad_norm": 9.795879364013672, "learning_rate": 5.515292941793587e-07, "loss": 0.01772841438651085, "step": 7195 }, { "epoch": 1.8681204569055037, "grad_norm": 7.777874946594238, "learning_rate": 5.513281877174431e-07, "loss": 0.02392151765525341, "step": 7196 }, { "epoch": 1.868380062305296, "grad_norm": 0.5813645124435425, "learning_rate": 5.51127469930361e-07, "loss": 0.0007308547501452267, "step": 7197 }, { "epoch": 1.8686396677050883, "grad_norm": 6.809978485107422, "learning_rate": 5.509271408535949e-07, "loss": 0.020752444863319397, "step": 7198 }, { "epoch": 1.8688992731048806, "grad_norm": 10.019400596618652, "learning_rate": 5.507272005225578e-07, "loss": 0.010109984315931797, "step": 7199 }, { "epoch": 1.8691588785046729, "grad_norm": 3.9806158542633057, "learning_rate": 5.505276489725951e-07, "loss": 0.0037283606361597776, "step": 7200 }, { "epoch": 1.8694184839044652, "grad_norm": 6.162172317504883, "learning_rate": 5.503284862389828e-07, "loss": 0.019977226853370667, "step": 7201 }, { "epoch": 1.8696780893042575, "grad_norm": 22.34674072265625, "learning_rate": 5.501297123569287e-07, "loss": 0.014470446854829788, "step": 7202 }, { "epoch": 1.8699376947040498, "grad_norm": 9.049626350402832, "learning_rate": 5.499313273615706e-07, "loss": 0.03630336374044418, "step": 7203 }, { "epoch": 1.870197300103842, "grad_norm": 2.2015221118927, "learning_rate": 5.49733331287979e-07, "loss": 0.006387186702340841, "step": 7204 }, { "epoch": 1.8704569055036346, "grad_norm": 7.0657830238342285, "learning_rate": 5.495357241711554e-07, "loss": 0.015405626967549324, "step": 7205 }, { "epoch": 1.870716510903427, "grad_norm": 10.518815994262695, "learning_rate": 5.493385060460316e-07, "loss": 0.055950410664081573, "step": 7206 }, { "epoch": 1.8709761163032192, "grad_norm": 11.21801471710205, "learning_rate": 5.491416769474714e-07, "loss": 0.024675315245985985, "step": 7207 }, { "epoch": 1.8712357217030116, "grad_norm": 11.891866683959961, "learning_rate": 5.489452369102696e-07, "loss": 0.0664600133895874, "step": 7208 }, { "epoch": 1.8714953271028039, "grad_norm": 12.026609420776367, "learning_rate": 5.487491859691525e-07, "loss": 0.1029699370265007, "step": 7209 }, { "epoch": 1.8717549325025962, "grad_norm": 10.295184135437012, "learning_rate": 5.485535241587777e-07, "loss": 0.012056661769747734, "step": 7210 }, { "epoch": 1.8720145379023885, "grad_norm": 10.108992576599121, "learning_rate": 5.483582515137331e-07, "loss": 0.02436414733529091, "step": 7211 }, { "epoch": 1.8722741433021808, "grad_norm": 13.325572967529297, "learning_rate": 5.481633680685388e-07, "loss": 0.00966585986316204, "step": 7212 }, { "epoch": 1.872533748701973, "grad_norm": 9.92042350769043, "learning_rate": 5.479688738576457e-07, "loss": 0.08482495695352554, "step": 7213 }, { "epoch": 1.8727933541017654, "grad_norm": 11.537996292114258, "learning_rate": 5.477747689154355e-07, "loss": 0.04293980076909065, "step": 7214 }, { "epoch": 1.8730529595015577, "grad_norm": 0.7159776091575623, "learning_rate": 5.475810532762226e-07, "loss": 0.000871505937539041, "step": 7215 }, { "epoch": 1.87331256490135, "grad_norm": 8.517121315002441, "learning_rate": 5.473877269742502e-07, "loss": 0.012077638879418373, "step": 7216 }, { "epoch": 1.8735721703011423, "grad_norm": 0.3611367344856262, "learning_rate": 5.471947900436947e-07, "loss": 0.001126578776165843, "step": 7217 }, { "epoch": 1.8738317757009346, "grad_norm": 6.420989513397217, "learning_rate": 5.470022425186627e-07, "loss": 0.009680964052677155, "step": 7218 }, { "epoch": 1.874091381100727, "grad_norm": 6.8307294845581055, "learning_rate": 5.468100844331922e-07, "loss": 0.013386614620685577, "step": 7219 }, { "epoch": 1.8743509865005192, "grad_norm": 4.254208564758301, "learning_rate": 5.466183158212525e-07, "loss": 0.0045409975573420525, "step": 7220 }, { "epoch": 1.8746105919003115, "grad_norm": 8.775280952453613, "learning_rate": 5.464269367167439e-07, "loss": 0.015333663672208786, "step": 7221 }, { "epoch": 1.8748701973001038, "grad_norm": 8.829682350158691, "learning_rate": 5.462359471534976e-07, "loss": 0.052134670317173004, "step": 7222 }, { "epoch": 1.8751298026998962, "grad_norm": 3.8885185718536377, "learning_rate": 5.460453471652765e-07, "loss": 0.008704937994480133, "step": 7223 }, { "epoch": 1.8753894080996885, "grad_norm": 10.756003379821777, "learning_rate": 5.45855136785774e-07, "loss": 0.0649644210934639, "step": 7224 }, { "epoch": 1.8756490134994808, "grad_norm": 8.614141464233398, "learning_rate": 5.45665316048615e-07, "loss": 0.02633027732372284, "step": 7225 }, { "epoch": 1.875908618899273, "grad_norm": 6.309566497802734, "learning_rate": 5.454758849873559e-07, "loss": 0.011807255446910858, "step": 7226 }, { "epoch": 1.8761682242990654, "grad_norm": 9.701569557189941, "learning_rate": 5.45286843635483e-07, "loss": 0.06686176359653473, "step": 7227 }, { "epoch": 1.8764278296988577, "grad_norm": 8.005964279174805, "learning_rate": 5.450981920264152e-07, "loss": 0.08914056420326233, "step": 7228 }, { "epoch": 1.87668743509865, "grad_norm": 7.54556941986084, "learning_rate": 5.449099301935015e-07, "loss": 0.030752962455153465, "step": 7229 }, { "epoch": 1.8769470404984423, "grad_norm": 10.97547721862793, "learning_rate": 5.447220581700222e-07, "loss": 0.012002737261354923, "step": 7230 }, { "epoch": 1.8772066458982346, "grad_norm": 5.430563449859619, "learning_rate": 5.445345759891889e-07, "loss": 0.02811732515692711, "step": 7231 }, { "epoch": 1.877466251298027, "grad_norm": 6.847679138183594, "learning_rate": 5.44347483684144e-07, "loss": 0.01055968925356865, "step": 7232 }, { "epoch": 1.8777258566978192, "grad_norm": 6.587201118469238, "learning_rate": 5.441607812879614e-07, "loss": 0.015051428228616714, "step": 7233 }, { "epoch": 1.8779854620976115, "grad_norm": 3.57827091217041, "learning_rate": 5.439744688336453e-07, "loss": 0.003231981536373496, "step": 7234 }, { "epoch": 1.8782450674974038, "grad_norm": 8.459187507629395, "learning_rate": 5.43788546354132e-07, "loss": 0.035574011504650116, "step": 7235 }, { "epoch": 1.8785046728971961, "grad_norm": 11.366127967834473, "learning_rate": 5.436030138822881e-07, "loss": 0.018507763743400574, "step": 7236 }, { "epoch": 1.8787642782969884, "grad_norm": 9.804183006286621, "learning_rate": 5.434178714509117e-07, "loss": 0.007110102102160454, "step": 7237 }, { "epoch": 1.8790238836967808, "grad_norm": 7.855343818664551, "learning_rate": 5.432331190927316e-07, "loss": 0.014399961568415165, "step": 7238 }, { "epoch": 1.879283489096573, "grad_norm": 10.068663597106934, "learning_rate": 5.430487568404078e-07, "loss": 0.02312997542321682, "step": 7239 }, { "epoch": 1.8795430944963654, "grad_norm": 10.487146377563477, "learning_rate": 5.428647847265313e-07, "loss": 0.03308796137571335, "step": 7240 }, { "epoch": 1.879802699896158, "grad_norm": 10.825746536254883, "learning_rate": 5.426812027836241e-07, "loss": 0.036497436463832855, "step": 7241 }, { "epoch": 1.8800623052959502, "grad_norm": 1.7352104187011719, "learning_rate": 5.424980110441392e-07, "loss": 0.0014633041573688388, "step": 7242 }, { "epoch": 1.8803219106957425, "grad_norm": 11.075231552124023, "learning_rate": 5.423152095404608e-07, "loss": 0.10453122109174728, "step": 7243 }, { "epoch": 1.8805815160955348, "grad_norm": 8.615315437316895, "learning_rate": 5.421327983049046e-07, "loss": 0.032353661954402924, "step": 7244 }, { "epoch": 1.8808411214953271, "grad_norm": 4.670989513397217, "learning_rate": 5.419507773697157e-07, "loss": 0.01042455155402422, "step": 7245 }, { "epoch": 1.8811007268951194, "grad_norm": 9.960973739624023, "learning_rate": 5.417691467670719e-07, "loss": 0.03062054142355919, "step": 7246 }, { "epoch": 1.8813603322949117, "grad_norm": 8.370984077453613, "learning_rate": 5.415879065290811e-07, "loss": 0.029554979875683784, "step": 7247 }, { "epoch": 1.881619937694704, "grad_norm": 8.134401321411133, "learning_rate": 5.414070566877826e-07, "loss": 0.09825462102890015, "step": 7248 }, { "epoch": 1.8818795430944963, "grad_norm": 11.478996276855469, "learning_rate": 5.412265972751465e-07, "loss": 0.07499741017818451, "step": 7249 }, { "epoch": 1.8821391484942886, "grad_norm": 0.39544209837913513, "learning_rate": 5.410465283230735e-07, "loss": 0.0007949169958010316, "step": 7250 }, { "epoch": 1.882398753894081, "grad_norm": 11.62515640258789, "learning_rate": 5.408668498633959e-07, "loss": 0.03762082755565643, "step": 7251 }, { "epoch": 1.8826583592938733, "grad_norm": 10.69772720336914, "learning_rate": 5.406875619278772e-07, "loss": 0.0252072736620903, "step": 7252 }, { "epoch": 1.8829179646936658, "grad_norm": 8.584653854370117, "learning_rate": 5.405086645482108e-07, "loss": 0.009935565292835236, "step": 7253 }, { "epoch": 1.883177570093458, "grad_norm": 8.221753120422363, "learning_rate": 5.40330157756022e-07, "loss": 0.03710831329226494, "step": 7254 }, { "epoch": 1.8834371754932504, "grad_norm": 14.68126106262207, "learning_rate": 5.401520415828664e-07, "loss": 0.031569384038448334, "step": 7255 }, { "epoch": 1.8836967808930427, "grad_norm": 11.623587608337402, "learning_rate": 5.399743160602311e-07, "loss": 0.03409642353653908, "step": 7256 }, { "epoch": 1.883956386292835, "grad_norm": 5.405086517333984, "learning_rate": 5.397969812195336e-07, "loss": 0.008438830263912678, "step": 7257 }, { "epoch": 1.8842159916926273, "grad_norm": 11.434508323669434, "learning_rate": 5.396200370921232e-07, "loss": 0.17255014181137085, "step": 7258 }, { "epoch": 1.8844755970924196, "grad_norm": 5.037031650543213, "learning_rate": 5.394434837092792e-07, "loss": 0.004880443215370178, "step": 7259 }, { "epoch": 1.884735202492212, "grad_norm": 7.90067720413208, "learning_rate": 5.392673211022122e-07, "loss": 0.014777997508645058, "step": 7260 }, { "epoch": 1.8849948078920042, "grad_norm": 6.708584785461426, "learning_rate": 5.390915493020638e-07, "loss": 0.009817367419600487, "step": 7261 }, { "epoch": 1.8852544132917965, "grad_norm": 5.393206596374512, "learning_rate": 5.389161683399063e-07, "loss": 0.015083534643054008, "step": 7262 }, { "epoch": 1.8855140186915889, "grad_norm": 4.5810136795043945, "learning_rate": 5.387411782467429e-07, "loss": 0.00960176158696413, "step": 7263 }, { "epoch": 1.8857736240913812, "grad_norm": 6.158790588378906, "learning_rate": 5.385665790535087e-07, "loss": 0.009826011955738068, "step": 7264 }, { "epoch": 1.8860332294911735, "grad_norm": 12.673584938049316, "learning_rate": 5.383923707910677e-07, "loss": 0.06462248414754868, "step": 7265 }, { "epoch": 1.8862928348909658, "grad_norm": 17.44279670715332, "learning_rate": 5.382185534902165e-07, "loss": 0.05656801164150238, "step": 7266 }, { "epoch": 1.886552440290758, "grad_norm": 10.771771430969238, "learning_rate": 5.380451271816824e-07, "loss": 0.08571799099445343, "step": 7267 }, { "epoch": 1.8868120456905504, "grad_norm": 8.644801139831543, "learning_rate": 5.378720918961223e-07, "loss": 0.11796686053276062, "step": 7268 }, { "epoch": 1.8870716510903427, "grad_norm": 8.776901245117188, "learning_rate": 5.376994476641252e-07, "loss": 0.016763176769018173, "step": 7269 }, { "epoch": 1.887331256490135, "grad_norm": 2.4689955711364746, "learning_rate": 5.375271945162114e-07, "loss": 0.005161553621292114, "step": 7270 }, { "epoch": 1.8875908618899273, "grad_norm": 13.756218910217285, "learning_rate": 5.373553324828303e-07, "loss": 0.031542375683784485, "step": 7271 }, { "epoch": 1.8878504672897196, "grad_norm": 3.3641421794891357, "learning_rate": 5.371838615943637e-07, "loss": 0.009431380778551102, "step": 7272 }, { "epoch": 1.888110072689512, "grad_norm": 5.304780960083008, "learning_rate": 5.370127818811234e-07, "loss": 0.006115619093179703, "step": 7273 }, { "epoch": 1.8883696780893042, "grad_norm": 1.5805619955062866, "learning_rate": 5.368420933733525e-07, "loss": 0.0017558375839143991, "step": 7274 }, { "epoch": 1.8886292834890965, "grad_norm": 2.2791764736175537, "learning_rate": 5.366717961012253e-07, "loss": 0.0027552288956940174, "step": 7275 }, { "epoch": 1.8888888888888888, "grad_norm": 6.993620872497559, "learning_rate": 5.365018900948458e-07, "loss": 0.014996248297393322, "step": 7276 }, { "epoch": 1.8891484942886811, "grad_norm": 10.095281600952148, "learning_rate": 5.363323753842498e-07, "loss": 0.06953120976686478, "step": 7277 }, { "epoch": 1.8894080996884735, "grad_norm": 0.2565213441848755, "learning_rate": 5.361632519994034e-07, "loss": 0.000640166224911809, "step": 7278 }, { "epoch": 1.8896677050882658, "grad_norm": 11.567520141601562, "learning_rate": 5.359945199702042e-07, "loss": 0.028869664296507835, "step": 7279 }, { "epoch": 1.889927310488058, "grad_norm": 10.40505599975586, "learning_rate": 5.358261793264796e-07, "loss": 0.09454206377267838, "step": 7280 }, { "epoch": 1.8901869158878504, "grad_norm": 4.954315185546875, "learning_rate": 5.356582300979887e-07, "loss": 0.020430810749530792, "step": 7281 }, { "epoch": 1.8904465212876427, "grad_norm": 8.427783012390137, "learning_rate": 5.354906723144211e-07, "loss": 0.07319118827581406, "step": 7282 }, { "epoch": 1.890706126687435, "grad_norm": 2.090116024017334, "learning_rate": 5.353235060053971e-07, "loss": 0.003489566734060645, "step": 7283 }, { "epoch": 1.8909657320872273, "grad_norm": 13.337984085083008, "learning_rate": 5.351567312004675e-07, "loss": 0.021599464118480682, "step": 7284 }, { "epoch": 1.8912253374870196, "grad_norm": 1.4312821626663208, "learning_rate": 5.349903479291153e-07, "loss": 0.0025334437377750874, "step": 7285 }, { "epoch": 1.891484942886812, "grad_norm": 11.01418399810791, "learning_rate": 5.348243562207519e-07, "loss": 0.03912799432873726, "step": 7286 }, { "epoch": 1.8917445482866042, "grad_norm": 9.545766830444336, "learning_rate": 5.34658756104722e-07, "loss": 0.03312349319458008, "step": 7287 }, { "epoch": 1.8920041536863965, "grad_norm": 12.205389976501465, "learning_rate": 5.344935476102992e-07, "loss": 0.06628121435642242, "step": 7288 }, { "epoch": 1.892263759086189, "grad_norm": 6.194303035736084, "learning_rate": 5.34328730766689e-07, "loss": 0.032524559646844864, "step": 7289 }, { "epoch": 1.8925233644859814, "grad_norm": 0.3728868365287781, "learning_rate": 5.341643056030269e-07, "loss": 0.001504775369539857, "step": 7290 }, { "epoch": 1.8927829698857737, "grad_norm": 2.233046293258667, "learning_rate": 5.340002721483798e-07, "loss": 0.011307060718536377, "step": 7291 }, { "epoch": 1.893042575285566, "grad_norm": 4.194411277770996, "learning_rate": 5.338366304317445e-07, "loss": 0.022449638694524765, "step": 7292 }, { "epoch": 1.8933021806853583, "grad_norm": 8.17348861694336, "learning_rate": 5.336733804820501e-07, "loss": 0.028642263263463974, "step": 7293 }, { "epoch": 1.8935617860851506, "grad_norm": 14.816712379455566, "learning_rate": 5.335105223281544e-07, "loss": 0.06441959738731384, "step": 7294 }, { "epoch": 1.8938213914849429, "grad_norm": 8.641690254211426, "learning_rate": 5.333480559988477e-07, "loss": 0.08198487013578415, "step": 7295 }, { "epoch": 1.8940809968847352, "grad_norm": 11.076306343078613, "learning_rate": 5.331859815228501e-07, "loss": 0.02933013066649437, "step": 7296 }, { "epoch": 1.8943406022845275, "grad_norm": 7.3815016746521, "learning_rate": 5.330242989288127e-07, "loss": 0.03924811631441116, "step": 7297 }, { "epoch": 1.8946002076843198, "grad_norm": 6.673245906829834, "learning_rate": 5.328630082453173e-07, "loss": 0.019174883142113686, "step": 7298 }, { "epoch": 1.894859813084112, "grad_norm": 8.357784271240234, "learning_rate": 5.327021095008762e-07, "loss": 0.016412101686000824, "step": 7299 }, { "epoch": 1.8951194184839044, "grad_norm": 2.201221227645874, "learning_rate": 5.325416027239327e-07, "loss": 0.003111095167696476, "step": 7300 }, { "epoch": 1.895379023883697, "grad_norm": 8.672255516052246, "learning_rate": 5.323814879428608e-07, "loss": 0.031592439860105515, "step": 7301 }, { "epoch": 1.8956386292834893, "grad_norm": 6.18038272857666, "learning_rate": 5.322217651859652e-07, "loss": 0.01917736604809761, "step": 7302 }, { "epoch": 1.8958982346832816, "grad_norm": 7.553554534912109, "learning_rate": 5.320624344814812e-07, "loss": 0.017651967704296112, "step": 7303 }, { "epoch": 1.8961578400830739, "grad_norm": 8.097372055053711, "learning_rate": 5.319034958575744e-07, "loss": 0.030285723507404327, "step": 7304 }, { "epoch": 1.8964174454828662, "grad_norm": 4.673190116882324, "learning_rate": 5.317449493423419e-07, "loss": 0.021794287487864494, "step": 7305 }, { "epoch": 1.8966770508826585, "grad_norm": 5.316408157348633, "learning_rate": 5.315867949638114e-07, "loss": 0.014419801533222198, "step": 7306 }, { "epoch": 1.8969366562824508, "grad_norm": 6.958665370941162, "learning_rate": 5.314290327499404e-07, "loss": 0.025527454912662506, "step": 7307 }, { "epoch": 1.897196261682243, "grad_norm": 9.957477569580078, "learning_rate": 5.312716627286179e-07, "loss": 0.09885281324386597, "step": 7308 }, { "epoch": 1.8974558670820354, "grad_norm": 7.662487030029297, "learning_rate": 5.311146849276632e-07, "loss": 0.034545838832855225, "step": 7309 }, { "epoch": 1.8977154724818277, "grad_norm": 1.3770956993103027, "learning_rate": 5.309580993748266e-07, "loss": 0.0029969639144837856, "step": 7310 }, { "epoch": 1.89797507788162, "grad_norm": 9.15853500366211, "learning_rate": 5.308019060977887e-07, "loss": 0.0771867036819458, "step": 7311 }, { "epoch": 1.8982346832814123, "grad_norm": 6.056488513946533, "learning_rate": 5.306461051241607e-07, "loss": 0.03974892571568489, "step": 7312 }, { "epoch": 1.8984942886812046, "grad_norm": 8.877811431884766, "learning_rate": 5.304906964814849e-07, "loss": 0.12084728479385376, "step": 7313 }, { "epoch": 1.898753894080997, "grad_norm": 9.361786842346191, "learning_rate": 5.303356801972342e-07, "loss": 0.10059309005737305, "step": 7314 }, { "epoch": 1.8990134994807892, "grad_norm": 10.39819622039795, "learning_rate": 5.301810562988113e-07, "loss": 0.028478560969233513, "step": 7315 }, { "epoch": 1.8992731048805815, "grad_norm": 9.563990592956543, "learning_rate": 5.300268248135509e-07, "loss": 0.07973825931549072, "step": 7316 }, { "epoch": 1.8995327102803738, "grad_norm": 3.7522635459899902, "learning_rate": 5.29872985768717e-07, "loss": 0.0050821187905967236, "step": 7317 }, { "epoch": 1.8997923156801662, "grad_norm": 6.445851802825928, "learning_rate": 5.297195391915051e-07, "loss": 0.005763563793152571, "step": 7318 }, { "epoch": 1.9000519210799585, "grad_norm": 8.565982818603516, "learning_rate": 5.295664851090409e-07, "loss": 0.008121812716126442, "step": 7319 }, { "epoch": 1.9003115264797508, "grad_norm": 8.85189151763916, "learning_rate": 5.29413823548381e-07, "loss": 0.028581375256180763, "step": 7320 }, { "epoch": 1.900571131879543, "grad_norm": 7.149714469909668, "learning_rate": 5.292615545365124e-07, "loss": 0.024139078333973885, "step": 7321 }, { "epoch": 1.9008307372793354, "grad_norm": 9.828056335449219, "learning_rate": 5.29109678100353e-07, "loss": 0.011425860226154327, "step": 7322 }, { "epoch": 1.9010903426791277, "grad_norm": 12.147915840148926, "learning_rate": 5.289581942667505e-07, "loss": 0.061869874596595764, "step": 7323 }, { "epoch": 1.90134994807892, "grad_norm": 7.811540603637695, "learning_rate": 5.288071030624846e-07, "loss": 0.019188925623893738, "step": 7324 }, { "epoch": 1.9016095534787123, "grad_norm": 10.445918083190918, "learning_rate": 5.286564045142638e-07, "loss": 0.12395688891410828, "step": 7325 }, { "epoch": 1.9018691588785046, "grad_norm": 11.326139450073242, "learning_rate": 5.28506098648729e-07, "loss": 0.015964988619089127, "step": 7326 }, { "epoch": 1.902128764278297, "grad_norm": 13.009010314941406, "learning_rate": 5.283561854924504e-07, "loss": 0.0963481217622757, "step": 7327 }, { "epoch": 1.9023883696780892, "grad_norm": 7.542107582092285, "learning_rate": 5.282066650719291e-07, "loss": 0.020931174978613853, "step": 7328 }, { "epoch": 1.9026479750778815, "grad_norm": 8.169641494750977, "learning_rate": 5.280575374135975e-07, "loss": 0.015980618074536324, "step": 7329 }, { "epoch": 1.9029075804776738, "grad_norm": 7.862338066101074, "learning_rate": 5.279088025438173e-07, "loss": 0.018213512375950813, "step": 7330 }, { "epoch": 1.9031671858774661, "grad_norm": 4.114855766296387, "learning_rate": 5.277604604888816e-07, "loss": 0.008830499835312366, "step": 7331 }, { "epoch": 1.9034267912772584, "grad_norm": 5.770373821258545, "learning_rate": 5.27612511275014e-07, "loss": 0.00870046578347683, "step": 7332 }, { "epoch": 1.9036863966770508, "grad_norm": 5.819675922393799, "learning_rate": 5.274649549283685e-07, "loss": 0.011874553747475147, "step": 7333 }, { "epoch": 1.903946002076843, "grad_norm": 5.061110973358154, "learning_rate": 5.273177914750298e-07, "loss": 0.019832640886306763, "step": 7334 }, { "epoch": 1.9042056074766354, "grad_norm": 1.8927397727966309, "learning_rate": 5.271710209410127e-07, "loss": 0.004865230526775122, "step": 7335 }, { "epoch": 1.9044652128764277, "grad_norm": 9.607576370239258, "learning_rate": 5.270246433522629e-07, "loss": 0.07238902896642685, "step": 7336 }, { "epoch": 1.9047248182762202, "grad_norm": 6.899377822875977, "learning_rate": 5.268786587346573e-07, "loss": 0.01296391524374485, "step": 7337 }, { "epoch": 1.9049844236760125, "grad_norm": 15.325356483459473, "learning_rate": 5.267330671140016e-07, "loss": 0.039074596017599106, "step": 7338 }, { "epoch": 1.9052440290758048, "grad_norm": 5.416893005371094, "learning_rate": 5.265878685160339e-07, "loss": 0.0185802411288023, "step": 7339 }, { "epoch": 1.9055036344755971, "grad_norm": 4.4730448722839355, "learning_rate": 5.264430629664214e-07, "loss": 0.013905603438615799, "step": 7340 }, { "epoch": 1.9057632398753894, "grad_norm": 12.739498138427734, "learning_rate": 5.262986504907629e-07, "loss": 0.017654646188020706, "step": 7341 }, { "epoch": 1.9060228452751817, "grad_norm": 11.119919776916504, "learning_rate": 5.261546311145868e-07, "loss": 0.0742577314376831, "step": 7342 }, { "epoch": 1.906282450674974, "grad_norm": 6.579029083251953, "learning_rate": 5.260110048633527e-07, "loss": 0.011604154482483864, "step": 7343 }, { "epoch": 1.9065420560747663, "grad_norm": 5.230285167694092, "learning_rate": 5.258677717624502e-07, "loss": 0.010117171332240105, "step": 7344 }, { "epoch": 1.9068016614745587, "grad_norm": 6.161332607269287, "learning_rate": 5.257249318372001e-07, "loss": 0.014329606667160988, "step": 7345 }, { "epoch": 1.907061266874351, "grad_norm": 11.359046936035156, "learning_rate": 5.255824851128525e-07, "loss": 0.02634650282561779, "step": 7346 }, { "epoch": 1.9073208722741433, "grad_norm": 9.181132316589355, "learning_rate": 5.254404316145894e-07, "loss": 0.0254644975066185, "step": 7347 }, { "epoch": 1.9075804776739356, "grad_norm": 10.217137336730957, "learning_rate": 5.252987713675222e-07, "loss": 0.07472413778305054, "step": 7348 }, { "epoch": 1.907840083073728, "grad_norm": 9.887078285217285, "learning_rate": 5.251575043966932e-07, "loss": 0.0646752268075943, "step": 7349 }, { "epoch": 1.9080996884735204, "grad_norm": 8.249054908752441, "learning_rate": 5.250166307270754e-07, "loss": 0.03444390371441841, "step": 7350 }, { "epoch": 1.9083592938733127, "grad_norm": 9.567713737487793, "learning_rate": 5.24876150383572e-07, "loss": 0.08497333526611328, "step": 7351 }, { "epoch": 1.908618899273105, "grad_norm": 8.762981414794922, "learning_rate": 5.247360633910168e-07, "loss": 0.05606355518102646, "step": 7352 }, { "epoch": 1.9088785046728973, "grad_norm": 11.421062469482422, "learning_rate": 5.245963697741734e-07, "loss": 0.028492996469140053, "step": 7353 }, { "epoch": 1.9091381100726896, "grad_norm": 3.810089588165283, "learning_rate": 5.244570695577371e-07, "loss": 0.005373557098209858, "step": 7354 }, { "epoch": 1.909397715472482, "grad_norm": 3.9538848400115967, "learning_rate": 5.243181627663325e-07, "loss": 0.004060490522533655, "step": 7355 }, { "epoch": 1.9096573208722742, "grad_norm": 3.3277182579040527, "learning_rate": 5.241796494245157e-07, "loss": 0.010871443897485733, "step": 7356 }, { "epoch": 1.9099169262720666, "grad_norm": 0.3214355409145355, "learning_rate": 5.240415295567719e-07, "loss": 0.0010680307168513536, "step": 7357 }, { "epoch": 1.9101765316718589, "grad_norm": 10.78282356262207, "learning_rate": 5.239038031875184e-07, "loss": 0.0787239596247673, "step": 7358 }, { "epoch": 1.9104361370716512, "grad_norm": 10.383243560791016, "learning_rate": 5.237664703411014e-07, "loss": 0.022636666893959045, "step": 7359 }, { "epoch": 1.9106957424714435, "grad_norm": 4.234218597412109, "learning_rate": 5.236295310417988e-07, "loss": 0.010493671521544456, "step": 7360 }, { "epoch": 1.9109553478712358, "grad_norm": 6.592552661895752, "learning_rate": 5.234929853138177e-07, "loss": 0.007390880025923252, "step": 7361 }, { "epoch": 1.911214953271028, "grad_norm": 6.874414920806885, "learning_rate": 5.233568331812964e-07, "loss": 0.02142544649541378, "step": 7362 }, { "epoch": 1.9114745586708204, "grad_norm": 5.231846332550049, "learning_rate": 5.232210746683039e-07, "loss": 0.008582457900047302, "step": 7363 }, { "epoch": 1.9117341640706127, "grad_norm": 1.005347728729248, "learning_rate": 5.230857097988388e-07, "loss": 0.002960112178698182, "step": 7364 }, { "epoch": 1.911993769470405, "grad_norm": 3.5618109703063965, "learning_rate": 5.229507385968308e-07, "loss": 0.003430020296946168, "step": 7365 }, { "epoch": 1.9122533748701973, "grad_norm": 4.496954917907715, "learning_rate": 5.228161610861392e-07, "loss": 0.007432994432747364, "step": 7366 }, { "epoch": 1.9125129802699896, "grad_norm": 9.972973823547363, "learning_rate": 5.226819772905546e-07, "loss": 0.06860870122909546, "step": 7367 }, { "epoch": 1.912772585669782, "grad_norm": 16.94474983215332, "learning_rate": 5.22548187233798e-07, "loss": 0.036361515522003174, "step": 7368 }, { "epoch": 1.9130321910695742, "grad_norm": 8.242147445678711, "learning_rate": 5.224147909395197e-07, "loss": 0.00625105295330286, "step": 7369 }, { "epoch": 1.9132917964693665, "grad_norm": 1.5883433818817139, "learning_rate": 5.222817884313015e-07, "loss": 0.0024071442894637585, "step": 7370 }, { "epoch": 1.9135514018691588, "grad_norm": 11.648534774780273, "learning_rate": 5.22149179732655e-07, "loss": 0.019575107842683792, "step": 7371 }, { "epoch": 1.9138110072689511, "grad_norm": 11.06873893737793, "learning_rate": 5.220169648670227e-07, "loss": 0.06843249499797821, "step": 7372 }, { "epoch": 1.9140706126687435, "grad_norm": 1.0708234310150146, "learning_rate": 5.21885143857777e-07, "loss": 0.001622096635401249, "step": 7373 }, { "epoch": 1.9143302180685358, "grad_norm": 10.347220420837402, "learning_rate": 5.217537167282206e-07, "loss": 0.047438375651836395, "step": 7374 }, { "epoch": 1.914589823468328, "grad_norm": 2.8950164318084717, "learning_rate": 5.21622683501587e-07, "loss": 0.021763579919934273, "step": 7375 }, { "epoch": 1.9148494288681204, "grad_norm": 10.287393569946289, "learning_rate": 5.214920442010399e-07, "loss": 0.011165741831064224, "step": 7376 }, { "epoch": 1.9151090342679127, "grad_norm": 12.127157211303711, "learning_rate": 5.213617988496733e-07, "loss": 0.07013245671987534, "step": 7377 }, { "epoch": 1.915368639667705, "grad_norm": 15.164905548095703, "learning_rate": 5.212319474705119e-07, "loss": 0.045649413019418716, "step": 7378 }, { "epoch": 1.9156282450674973, "grad_norm": 15.002545356750488, "learning_rate": 5.211024900865099e-07, "loss": 0.03177668899297714, "step": 7379 }, { "epoch": 1.9158878504672896, "grad_norm": 1.5308934450149536, "learning_rate": 5.209734267205526e-07, "loss": 0.007482070941478014, "step": 7380 }, { "epoch": 1.916147455867082, "grad_norm": 9.417211532592773, "learning_rate": 5.208447573954557e-07, "loss": 0.009202428162097931, "step": 7381 }, { "epoch": 1.9164070612668742, "grad_norm": 3.725273370742798, "learning_rate": 5.207164821339647e-07, "loss": 0.013826441019773483, "step": 7382 }, { "epoch": 1.9166666666666665, "grad_norm": 11.063006401062012, "learning_rate": 5.205886009587559e-07, "loss": 0.08916640281677246, "step": 7383 }, { "epoch": 1.9169262720664588, "grad_norm": 2.625898838043213, "learning_rate": 5.204611138924358e-07, "loss": 0.012010165490210056, "step": 7384 }, { "epoch": 1.9171858774662511, "grad_norm": 10.577807426452637, "learning_rate": 5.203340209575409e-07, "loss": 0.012121258303523064, "step": 7385 }, { "epoch": 1.9174454828660437, "grad_norm": 9.460308074951172, "learning_rate": 5.202073221765384e-07, "loss": 0.05252283439040184, "step": 7386 }, { "epoch": 1.917705088265836, "grad_norm": 8.703475952148438, "learning_rate": 5.20081017571826e-07, "loss": 0.01567825675010681, "step": 7387 }, { "epoch": 1.9179646936656283, "grad_norm": 7.116260051727295, "learning_rate": 5.199551071657315e-07, "loss": 0.018638746812939644, "step": 7388 }, { "epoch": 1.9182242990654206, "grad_norm": 12.008977890014648, "learning_rate": 5.198295909805126e-07, "loss": 0.03159257397055626, "step": 7389 }, { "epoch": 1.9184839044652129, "grad_norm": 11.037032127380371, "learning_rate": 5.197044690383577e-07, "loss": 0.01786426641047001, "step": 7390 }, { "epoch": 1.9187435098650052, "grad_norm": 9.571077346801758, "learning_rate": 5.195797413613861e-07, "loss": 0.014724219217896461, "step": 7391 }, { "epoch": 1.9190031152647975, "grad_norm": 10.561264038085938, "learning_rate": 5.194554079716461e-07, "loss": 0.027973836287856102, "step": 7392 }, { "epoch": 1.9192627206645898, "grad_norm": 6.957898139953613, "learning_rate": 5.19331468891117e-07, "loss": 0.020144429057836533, "step": 7393 }, { "epoch": 1.9195223260643821, "grad_norm": 9.224384307861328, "learning_rate": 5.192079241417092e-07, "loss": 0.07069496065378189, "step": 7394 }, { "epoch": 1.9197819314641744, "grad_norm": 8.4942045211792, "learning_rate": 5.190847737452617e-07, "loss": 0.07795488834381104, "step": 7395 }, { "epoch": 1.9200415368639667, "grad_norm": 10.011496543884277, "learning_rate": 5.189620177235454e-07, "loss": 0.07353836297988892, "step": 7396 }, { "epoch": 1.920301142263759, "grad_norm": 8.658334732055664, "learning_rate": 5.1883965609826e-07, "loss": 0.018760625272989273, "step": 7397 }, { "epoch": 1.9205607476635516, "grad_norm": 8.019011497497559, "learning_rate": 5.187176888910366e-07, "loss": 0.019706545397639275, "step": 7398 }, { "epoch": 1.9208203530633439, "grad_norm": 1.0864900350570679, "learning_rate": 5.185961161234364e-07, "loss": 0.0019865273497998714, "step": 7399 }, { "epoch": 1.9210799584631362, "grad_norm": 9.235721588134766, "learning_rate": 5.184749378169505e-07, "loss": 0.04266104847192764, "step": 7400 }, { "epoch": 1.9213395638629285, "grad_norm": 4.18696403503418, "learning_rate": 5.183541539930002e-07, "loss": 0.02351249009370804, "step": 7401 }, { "epoch": 1.9215991692627208, "grad_norm": 1.6928502321243286, "learning_rate": 5.182337646729378e-07, "loss": 0.003235733835026622, "step": 7402 }, { "epoch": 1.921858774662513, "grad_norm": 3.845367431640625, "learning_rate": 5.18113769878045e-07, "loss": 0.007677214685827494, "step": 7403 }, { "epoch": 1.9221183800623054, "grad_norm": 7.1230669021606445, "learning_rate": 5.179941696295345e-07, "loss": 0.013374442234635353, "step": 7404 }, { "epoch": 1.9223779854620977, "grad_norm": 9.548635482788086, "learning_rate": 5.178749639485482e-07, "loss": 0.0389157310128212, "step": 7405 }, { "epoch": 1.92263759086189, "grad_norm": 0.9804825782775879, "learning_rate": 5.177561528561597e-07, "loss": 0.0014445674605667591, "step": 7406 }, { "epoch": 1.9228971962616823, "grad_norm": 7.8699822425842285, "learning_rate": 5.176377363733718e-07, "loss": 0.019839603453874588, "step": 7407 }, { "epoch": 1.9231568016614746, "grad_norm": 10.922478675842285, "learning_rate": 5.175197145211176e-07, "loss": 0.02804388478398323, "step": 7408 }, { "epoch": 1.923416407061267, "grad_norm": 1.5009067058563232, "learning_rate": 5.174020873202611e-07, "loss": 0.007097845431417227, "step": 7409 }, { "epoch": 1.9236760124610592, "grad_norm": 8.073363304138184, "learning_rate": 5.172848547915956e-07, "loss": 0.013665586709976196, "step": 7410 }, { "epoch": 1.9239356178608515, "grad_norm": 7.162308692932129, "learning_rate": 5.171680169558456e-07, "loss": 0.025746462866663933, "step": 7411 }, { "epoch": 1.9241952232606438, "grad_norm": 3.1944258213043213, "learning_rate": 5.170515738336647e-07, "loss": 0.0265057310461998, "step": 7412 }, { "epoch": 1.9244548286604362, "grad_norm": 9.086647033691406, "learning_rate": 5.169355254456381e-07, "loss": 0.007077313959598541, "step": 7413 }, { "epoch": 1.9247144340602285, "grad_norm": 2.731858968734741, "learning_rate": 5.168198718122804e-07, "loss": 0.0027144961059093475, "step": 7414 }, { "epoch": 1.9249740394600208, "grad_norm": 8.143909454345703, "learning_rate": 5.167046129540361e-07, "loss": 0.04865093529224396, "step": 7415 }, { "epoch": 1.925233644859813, "grad_norm": 5.707154273986816, "learning_rate": 5.165897488912805e-07, "loss": 0.008169371634721756, "step": 7416 }, { "epoch": 1.9254932502596054, "grad_norm": 8.49951457977295, "learning_rate": 5.164752796443191e-07, "loss": 0.02382161095738411, "step": 7417 }, { "epoch": 1.9257528556593977, "grad_norm": 7.978644847869873, "learning_rate": 5.163612052333871e-07, "loss": 0.04162494093179703, "step": 7418 }, { "epoch": 1.92601246105919, "grad_norm": 5.217052936553955, "learning_rate": 5.162475256786508e-07, "loss": 0.008980544283986092, "step": 7419 }, { "epoch": 1.9262720664589823, "grad_norm": 8.366711616516113, "learning_rate": 5.161342410002055e-07, "loss": 0.1004570946097374, "step": 7420 }, { "epoch": 1.9265316718587746, "grad_norm": 10.783598899841309, "learning_rate": 5.160213512180778e-07, "loss": 0.03464876115322113, "step": 7421 }, { "epoch": 1.926791277258567, "grad_norm": 10.469861030578613, "learning_rate": 5.159088563522239e-07, "loss": 0.07379812002182007, "step": 7422 }, { "epoch": 1.9270508826583592, "grad_norm": 3.3489959239959717, "learning_rate": 5.157967564225303e-07, "loss": 0.003425073344260454, "step": 7423 }, { "epoch": 1.9273104880581515, "grad_norm": 5.9055328369140625, "learning_rate": 5.156850514488136e-07, "loss": 0.02680336870253086, "step": 7424 }, { "epoch": 1.9275700934579438, "grad_norm": 6.14055061340332, "learning_rate": 5.155737414508208e-07, "loss": 0.010184386745095253, "step": 7425 }, { "epoch": 1.9278296988577361, "grad_norm": 8.328892707824707, "learning_rate": 5.154628264482289e-07, "loss": 0.01695800945162773, "step": 7426 }, { "epoch": 1.9280893042575284, "grad_norm": 8.587568283081055, "learning_rate": 5.153523064606452e-07, "loss": 0.06383142620325089, "step": 7427 }, { "epoch": 1.9283489096573208, "grad_norm": 11.285179138183594, "learning_rate": 5.15242181507607e-07, "loss": 0.04520455747842789, "step": 7428 }, { "epoch": 1.928608515057113, "grad_norm": 9.285404205322266, "learning_rate": 5.151324516085819e-07, "loss": 0.022553198039531708, "step": 7429 }, { "epoch": 1.9288681204569054, "grad_norm": 10.861345291137695, "learning_rate": 5.15023116782968e-07, "loss": 0.07559776306152344, "step": 7430 }, { "epoch": 1.9291277258566977, "grad_norm": 12.630661964416504, "learning_rate": 5.149141770500926e-07, "loss": 0.021985245868563652, "step": 7431 }, { "epoch": 1.92938733125649, "grad_norm": 9.119088172912598, "learning_rate": 5.148056324292142e-07, "loss": 0.019820604473352432, "step": 7432 }, { "epoch": 1.9296469366562823, "grad_norm": 3.2648119926452637, "learning_rate": 5.146974829395207e-07, "loss": 0.004322517663240433, "step": 7433 }, { "epoch": 1.9299065420560748, "grad_norm": 10.031188011169434, "learning_rate": 5.145897286001304e-07, "loss": 0.028920432552695274, "step": 7434 }, { "epoch": 1.9301661474558671, "grad_norm": 9.661847114562988, "learning_rate": 5.144823694300921e-07, "loss": 0.07830162346363068, "step": 7435 }, { "epoch": 1.9304257528556594, "grad_norm": 2.316873788833618, "learning_rate": 5.143754054483844e-07, "loss": 0.010419361293315887, "step": 7436 }, { "epoch": 1.9306853582554517, "grad_norm": 12.849039077758789, "learning_rate": 5.14268836673916e-07, "loss": 0.010689022950828075, "step": 7437 }, { "epoch": 1.930944963655244, "grad_norm": 5.452453136444092, "learning_rate": 5.141626631255257e-07, "loss": 0.0035574110224843025, "step": 7438 }, { "epoch": 1.9312045690550363, "grad_norm": 3.52419114112854, "learning_rate": 5.140568848219826e-07, "loss": 0.013061629608273506, "step": 7439 }, { "epoch": 1.9314641744548287, "grad_norm": 5.048742771148682, "learning_rate": 5.139515017819862e-07, "loss": 0.014116866514086723, "step": 7440 }, { "epoch": 1.931723779854621, "grad_norm": 6.92241907119751, "learning_rate": 5.138465140241657e-07, "loss": 0.012530080042779446, "step": 7441 }, { "epoch": 1.9319833852544133, "grad_norm": 11.699714660644531, "learning_rate": 5.137419215670798e-07, "loss": 0.034509699791669846, "step": 7442 }, { "epoch": 1.9322429906542056, "grad_norm": 7.954527378082275, "learning_rate": 5.136377244292192e-07, "loss": 0.03691547363996506, "step": 7443 }, { "epoch": 1.9325025960539979, "grad_norm": 3.9509902000427246, "learning_rate": 5.135339226290027e-07, "loss": 0.00907796248793602, "step": 7444 }, { "epoch": 1.9327622014537902, "grad_norm": 7.930732727050781, "learning_rate": 5.134305161847805e-07, "loss": 0.023360643535852432, "step": 7445 }, { "epoch": 1.9330218068535827, "grad_norm": 1.5199419260025024, "learning_rate": 5.133275051148322e-07, "loss": 0.004260748624801636, "step": 7446 }, { "epoch": 1.933281412253375, "grad_norm": 14.550076484680176, "learning_rate": 5.132248894373682e-07, "loss": 0.04614456743001938, "step": 7447 }, { "epoch": 1.9335410176531673, "grad_norm": 7.641897678375244, "learning_rate": 5.131226691705285e-07, "loss": 0.01851726695895195, "step": 7448 }, { "epoch": 1.9338006230529596, "grad_norm": 11.802581787109375, "learning_rate": 5.130208443323829e-07, "loss": 0.10999603569507599, "step": 7449 }, { "epoch": 1.934060228452752, "grad_norm": 2.318636894226074, "learning_rate": 5.129194149409321e-07, "loss": 0.01835775375366211, "step": 7450 }, { "epoch": 1.9343198338525442, "grad_norm": 9.532533645629883, "learning_rate": 5.128183810141066e-07, "loss": 0.047083064913749695, "step": 7451 }, { "epoch": 1.9345794392523366, "grad_norm": 3.7716124057769775, "learning_rate": 5.127177425697662e-07, "loss": 0.016639122739434242, "step": 7452 }, { "epoch": 1.9348390446521289, "grad_norm": 7.2491374015808105, "learning_rate": 5.126174996257024e-07, "loss": 0.0345093309879303, "step": 7453 }, { "epoch": 1.9350986500519212, "grad_norm": 12.392905235290527, "learning_rate": 5.125176521996353e-07, "loss": 0.02676999196410179, "step": 7454 }, { "epoch": 1.9353582554517135, "grad_norm": 8.945816040039062, "learning_rate": 5.124182003092153e-07, "loss": 0.05024545639753342, "step": 7455 }, { "epoch": 1.9356178608515058, "grad_norm": 7.6390533447265625, "learning_rate": 5.123191439720241e-07, "loss": 0.039568718522787094, "step": 7456 }, { "epoch": 1.935877466251298, "grad_norm": 2.6683897972106934, "learning_rate": 5.122204832055723e-07, "loss": 0.005082236602902412, "step": 7457 }, { "epoch": 1.9361370716510904, "grad_norm": 10.267523765563965, "learning_rate": 5.121222180273004e-07, "loss": 0.10089840739965439, "step": 7458 }, { "epoch": 1.9363966770508827, "grad_norm": 7.608743667602539, "learning_rate": 5.120243484545798e-07, "loss": 0.02420196495950222, "step": 7459 }, { "epoch": 1.936656282450675, "grad_norm": 2.9190902709960938, "learning_rate": 5.119268745047115e-07, "loss": 0.007565495558083057, "step": 7460 }, { "epoch": 1.9369158878504673, "grad_norm": 11.347016334533691, "learning_rate": 5.118297961949268e-07, "loss": 0.026130201295018196, "step": 7461 }, { "epoch": 1.9371754932502596, "grad_norm": 7.647984027862549, "learning_rate": 5.117331135423866e-07, "loss": 0.024760928004980087, "step": 7462 }, { "epoch": 1.937435098650052, "grad_norm": 10.781556129455566, "learning_rate": 5.116368265641828e-07, "loss": 0.06240004301071167, "step": 7463 }, { "epoch": 1.9376947040498442, "grad_norm": 8.650053024291992, "learning_rate": 5.115409352773361e-07, "loss": 0.06213708221912384, "step": 7464 }, { "epoch": 1.9379543094496365, "grad_norm": 1.8341598510742188, "learning_rate": 5.11445439698798e-07, "loss": 0.002282980363816023, "step": 7465 }, { "epoch": 1.9382139148494288, "grad_norm": 9.902975082397461, "learning_rate": 5.113503398454503e-07, "loss": 0.05607590451836586, "step": 7466 }, { "epoch": 1.9384735202492211, "grad_norm": 9.891023635864258, "learning_rate": 5.11255635734104e-07, "loss": 0.060768552124500275, "step": 7467 }, { "epoch": 1.9387331256490135, "grad_norm": 2.4403035640716553, "learning_rate": 5.11161327381501e-07, "loss": 0.002605265937745571, "step": 7468 }, { "epoch": 1.9389927310488058, "grad_norm": 9.963329315185547, "learning_rate": 5.110674148043129e-07, "loss": 0.035748280584812164, "step": 7469 }, { "epoch": 1.939252336448598, "grad_norm": 2.8222365379333496, "learning_rate": 5.109738980191408e-07, "loss": 0.018881941214203835, "step": 7470 }, { "epoch": 1.9395119418483904, "grad_norm": 8.387494087219238, "learning_rate": 5.108807770425167e-07, "loss": 0.04040813446044922, "step": 7471 }, { "epoch": 1.9397715472481827, "grad_norm": 5.369485855102539, "learning_rate": 5.107880518909023e-07, "loss": 0.006396141834557056, "step": 7472 }, { "epoch": 1.940031152647975, "grad_norm": 9.629406929016113, "learning_rate": 5.106957225806889e-07, "loss": 0.03892231360077858, "step": 7473 }, { "epoch": 1.9402907580477673, "grad_norm": 5.780135154724121, "learning_rate": 5.106037891281988e-07, "loss": 0.007900848984718323, "step": 7474 }, { "epoch": 1.9405503634475596, "grad_norm": 3.8177101612091064, "learning_rate": 5.105122515496832e-07, "loss": 0.004129031673073769, "step": 7475 }, { "epoch": 1.940809968847352, "grad_norm": 2.548088788986206, "learning_rate": 5.10421109861324e-07, "loss": 0.011961519718170166, "step": 7476 }, { "epoch": 1.9410695742471442, "grad_norm": 6.973703861236572, "learning_rate": 5.103303640792333e-07, "loss": 0.010623801499605179, "step": 7477 }, { "epoch": 1.9413291796469365, "grad_norm": 11.701687812805176, "learning_rate": 5.102400142194524e-07, "loss": 0.03171839565038681, "step": 7478 }, { "epoch": 1.9415887850467288, "grad_norm": 10.320889472961426, "learning_rate": 5.101500602979533e-07, "loss": 0.030964255332946777, "step": 7479 }, { "epoch": 1.9418483904465211, "grad_norm": 7.223510265350342, "learning_rate": 5.100605023306377e-07, "loss": 0.017352081835269928, "step": 7480 }, { "epoch": 1.9421079958463134, "grad_norm": 18.164173126220703, "learning_rate": 5.099713403333375e-07, "loss": 0.02242162451148033, "step": 7481 }, { "epoch": 1.942367601246106, "grad_norm": 9.398011207580566, "learning_rate": 5.098825743218146e-07, "loss": 0.01847102679312229, "step": 7482 }, { "epoch": 1.9426272066458983, "grad_norm": 10.793610572814941, "learning_rate": 5.097942043117604e-07, "loss": 0.022989705204963684, "step": 7483 }, { "epoch": 1.9428868120456906, "grad_norm": 6.193488597869873, "learning_rate": 5.097062303187973e-07, "loss": 0.016466880217194557, "step": 7484 }, { "epoch": 1.9431464174454829, "grad_norm": 9.7996244430542, "learning_rate": 5.096186523584765e-07, "loss": 0.01872747391462326, "step": 7485 }, { "epoch": 1.9434060228452752, "grad_norm": 2.004023551940918, "learning_rate": 5.095314704462803e-07, "loss": 0.0053059193305671215, "step": 7486 }, { "epoch": 1.9436656282450675, "grad_norm": 8.446779251098633, "learning_rate": 5.0944468459762e-07, "loss": 0.04117114841938019, "step": 7487 }, { "epoch": 1.9439252336448598, "grad_norm": 5.4548540115356445, "learning_rate": 5.093582948278375e-07, "loss": 0.014396166428923607, "step": 7488 }, { "epoch": 1.9441848390446521, "grad_norm": 9.073540687561035, "learning_rate": 5.092723011522047e-07, "loss": 0.09812489151954651, "step": 7489 }, { "epoch": 1.9444444444444444, "grad_norm": 3.5611510276794434, "learning_rate": 5.091867035859232e-07, "loss": 0.00884288176894188, "step": 7490 }, { "epoch": 1.9447040498442367, "grad_norm": 7.501927375793457, "learning_rate": 5.091015021441246e-07, "loss": 0.021138925105333328, "step": 7491 }, { "epoch": 1.944963655244029, "grad_norm": 9.287389755249023, "learning_rate": 5.090166968418707e-07, "loss": 0.014253780245780945, "step": 7492 }, { "epoch": 1.9452232606438213, "grad_norm": 0.5132268667221069, "learning_rate": 5.08932287694153e-07, "loss": 0.0011753638973459601, "step": 7493 }, { "epoch": 1.9454828660436139, "grad_norm": 2.693070411682129, "learning_rate": 5.088482747158933e-07, "loss": 0.006458566524088383, "step": 7494 }, { "epoch": 1.9457424714434062, "grad_norm": 7.007188320159912, "learning_rate": 5.087646579219432e-07, "loss": 0.020116552710533142, "step": 7495 }, { "epoch": 1.9460020768431985, "grad_norm": 5.893444538116455, "learning_rate": 5.086814373270836e-07, "loss": 0.0025565852411091328, "step": 7496 }, { "epoch": 1.9462616822429908, "grad_norm": 5.287834644317627, "learning_rate": 5.085986129460268e-07, "loss": 0.014512911438941956, "step": 7497 }, { "epoch": 1.946521287642783, "grad_norm": 0.5230802297592163, "learning_rate": 5.085161847934141e-07, "loss": 0.0011044007260352373, "step": 7498 }, { "epoch": 1.9467808930425754, "grad_norm": 8.779706954956055, "learning_rate": 5.084341528838165e-07, "loss": 0.028482921421527863, "step": 7499 }, { "epoch": 1.9470404984423677, "grad_norm": 1.6857248544692993, "learning_rate": 5.083525172317356e-07, "loss": 0.006917332764714956, "step": 7500 }, { "epoch": 1.94730010384216, "grad_norm": 10.315027236938477, "learning_rate": 5.082712778516029e-07, "loss": 0.004405372776091099, "step": 7501 }, { "epoch": 1.9475597092419523, "grad_norm": 9.555110931396484, "learning_rate": 5.081904347577796e-07, "loss": 0.026509964838624, "step": 7502 }, { "epoch": 1.9478193146417446, "grad_norm": 10.354889869689941, "learning_rate": 5.081099879645564e-07, "loss": 0.01732524484395981, "step": 7503 }, { "epoch": 1.948078920041537, "grad_norm": 8.669515609741211, "learning_rate": 5.080299374861551e-07, "loss": 0.015656406059861183, "step": 7504 }, { "epoch": 1.9483385254413292, "grad_norm": 9.961729049682617, "learning_rate": 5.079502833367265e-07, "loss": 0.05789396911859512, "step": 7505 }, { "epoch": 1.9485981308411215, "grad_norm": 9.180944442749023, "learning_rate": 5.078710255303515e-07, "loss": 0.03877844661474228, "step": 7506 }, { "epoch": 1.9488577362409139, "grad_norm": 10.469200134277344, "learning_rate": 5.077921640810416e-07, "loss": 0.041342563927173615, "step": 7507 }, { "epoch": 1.9491173416407062, "grad_norm": 9.094799995422363, "learning_rate": 5.077136990027372e-07, "loss": 0.021323319524526596, "step": 7508 }, { "epoch": 1.9493769470404985, "grad_norm": 7.922214984893799, "learning_rate": 5.076356303093091e-07, "loss": 0.02465881034731865, "step": 7509 }, { "epoch": 1.9496365524402908, "grad_norm": 4.37409782409668, "learning_rate": 5.075579580145585e-07, "loss": 0.005192209500819445, "step": 7510 }, { "epoch": 1.949896157840083, "grad_norm": 5.152479648590088, "learning_rate": 5.074806821322155e-07, "loss": 0.005789751186966896, "step": 7511 }, { "epoch": 1.9501557632398754, "grad_norm": 11.250014305114746, "learning_rate": 5.074038026759412e-07, "loss": 0.08078449219465256, "step": 7512 }, { "epoch": 1.9504153686396677, "grad_norm": 9.35805892944336, "learning_rate": 5.07327319659326e-07, "loss": 0.00655389903113246, "step": 7513 }, { "epoch": 1.95067497403946, "grad_norm": 3.989957571029663, "learning_rate": 5.072512330958902e-07, "loss": 0.002378251403570175, "step": 7514 }, { "epoch": 1.9509345794392523, "grad_norm": 12.038792610168457, "learning_rate": 5.071755429990844e-07, "loss": 0.06325703859329224, "step": 7515 }, { "epoch": 1.9511941848390446, "grad_norm": 8.277644157409668, "learning_rate": 5.071002493822885e-07, "loss": 0.014680690132081509, "step": 7516 }, { "epoch": 1.951453790238837, "grad_norm": 11.019142150878906, "learning_rate": 5.070253522588128e-07, "loss": 0.011959047988057137, "step": 7517 }, { "epoch": 1.9517133956386292, "grad_norm": 2.3907220363616943, "learning_rate": 5.06950851641898e-07, "loss": 0.009355799295008183, "step": 7518 }, { "epoch": 1.9519730010384215, "grad_norm": 2.499084234237671, "learning_rate": 5.068767475447131e-07, "loss": 0.013641257770359516, "step": 7519 }, { "epoch": 1.9522326064382138, "grad_norm": 7.644372463226318, "learning_rate": 5.068030399803587e-07, "loss": 0.0220772884786129, "step": 7520 }, { "epoch": 1.9524922118380061, "grad_norm": 11.30446720123291, "learning_rate": 5.067297289618643e-07, "loss": 0.03414041921496391, "step": 7521 }, { "epoch": 1.9527518172377984, "grad_norm": 11.87026596069336, "learning_rate": 5.0665681450219e-07, "loss": 0.09603564441204071, "step": 7522 }, { "epoch": 1.9530114226375908, "grad_norm": 10.719764709472656, "learning_rate": 5.065842966142251e-07, "loss": 0.023219872266054153, "step": 7523 }, { "epoch": 1.953271028037383, "grad_norm": 3.7357237339019775, "learning_rate": 5.065121753107889e-07, "loss": 0.034213587641716, "step": 7524 }, { "epoch": 1.9535306334371754, "grad_norm": 12.02769660949707, "learning_rate": 5.064404506046314e-07, "loss": 0.07042588293552399, "step": 7525 }, { "epoch": 1.9537902388369677, "grad_norm": 6.8067307472229, "learning_rate": 5.063691225084313e-07, "loss": 0.012840994633734226, "step": 7526 }, { "epoch": 1.95404984423676, "grad_norm": 3.443970203399658, "learning_rate": 5.062981910347979e-07, "loss": 0.02721451036632061, "step": 7527 }, { "epoch": 1.9543094496365523, "grad_norm": 8.970043182373047, "learning_rate": 5.062276561962705e-07, "loss": 0.024823680520057678, "step": 7528 }, { "epoch": 1.9545690550363446, "grad_norm": 12.809823989868164, "learning_rate": 5.06157518005318e-07, "loss": 0.032085567712783813, "step": 7529 }, { "epoch": 1.9548286604361371, "grad_norm": 0.5955641269683838, "learning_rate": 5.060877764743391e-07, "loss": 0.0013360065640881658, "step": 7530 }, { "epoch": 1.9550882658359294, "grad_norm": 11.550591468811035, "learning_rate": 5.060184316156627e-07, "loss": 0.034798260778188705, "step": 7531 }, { "epoch": 1.9553478712357217, "grad_norm": 1.5036516189575195, "learning_rate": 5.059494834415468e-07, "loss": 0.0024601295590400696, "step": 7532 }, { "epoch": 1.955607476635514, "grad_norm": 6.654494762420654, "learning_rate": 5.058809319641804e-07, "loss": 0.011769833043217659, "step": 7533 }, { "epoch": 1.9558670820353063, "grad_norm": 3.766103744506836, "learning_rate": 5.05812777195682e-07, "loss": 0.0026427684351801872, "step": 7534 }, { "epoch": 1.9561266874350987, "grad_norm": 7.286386013031006, "learning_rate": 5.057450191480994e-07, "loss": 0.009164316579699516, "step": 7535 }, { "epoch": 1.956386292834891, "grad_norm": 4.251327037811279, "learning_rate": 5.056776578334107e-07, "loss": 0.011928138323128223, "step": 7536 }, { "epoch": 1.9566458982346833, "grad_norm": 12.072914123535156, "learning_rate": 5.056106932635236e-07, "loss": 0.047320667654275894, "step": 7537 }, { "epoch": 1.9569055036344756, "grad_norm": 10.24957275390625, "learning_rate": 5.055441254502768e-07, "loss": 0.027331054210662842, "step": 7538 }, { "epoch": 1.9571651090342679, "grad_norm": 8.948193550109863, "learning_rate": 5.054779544054372e-07, "loss": 0.00848731305450201, "step": 7539 }, { "epoch": 1.9574247144340602, "grad_norm": 6.3193840980529785, "learning_rate": 5.054121801407024e-07, "loss": 0.014087097719311714, "step": 7540 }, { "epoch": 1.9576843198338525, "grad_norm": 11.796732902526855, "learning_rate": 5.053468026677003e-07, "loss": 0.04169861972332001, "step": 7541 }, { "epoch": 1.957943925233645, "grad_norm": 6.231082439422607, "learning_rate": 5.052818219979871e-07, "loss": 0.021416760981082916, "step": 7542 }, { "epoch": 1.9582035306334373, "grad_norm": 9.526700973510742, "learning_rate": 5.05217238143051e-07, "loss": 0.05479741841554642, "step": 7543 }, { "epoch": 1.9584631360332296, "grad_norm": 2.325418710708618, "learning_rate": 5.051530511143083e-07, "loss": 0.0048791454173624516, "step": 7544 }, { "epoch": 1.958722741433022, "grad_norm": 10.248977661132812, "learning_rate": 5.050892609231061e-07, "loss": 0.04461248964071274, "step": 7545 }, { "epoch": 1.9589823468328142, "grad_norm": 4.789544582366943, "learning_rate": 5.050258675807208e-07, "loss": 0.002359706209972501, "step": 7546 }, { "epoch": 1.9592419522326066, "grad_norm": 0.21312595903873444, "learning_rate": 5.049628710983592e-07, "loss": 0.0007439752807840705, "step": 7547 }, { "epoch": 1.9595015576323989, "grad_norm": 4.259063720703125, "learning_rate": 5.049002714871572e-07, "loss": 0.007699835579842329, "step": 7548 }, { "epoch": 1.9597611630321912, "grad_norm": 12.00948715209961, "learning_rate": 5.048380687581814e-07, "loss": 0.02870498038828373, "step": 7549 }, { "epoch": 1.9600207684319835, "grad_norm": 10.079366683959961, "learning_rate": 5.047762629224276e-07, "loss": 0.048893969506025314, "step": 7550 }, { "epoch": 1.9602803738317758, "grad_norm": 7.341607570648193, "learning_rate": 5.047148539908217e-07, "loss": 0.008506621234118938, "step": 7551 }, { "epoch": 1.960539979231568, "grad_norm": 3.832420587539673, "learning_rate": 5.046538419742194e-07, "loss": 0.007399942725896835, "step": 7552 }, { "epoch": 1.9607995846313604, "grad_norm": 1.5543478727340698, "learning_rate": 5.045932268834061e-07, "loss": 0.004054334480315447, "step": 7553 }, { "epoch": 1.9610591900311527, "grad_norm": 8.911617279052734, "learning_rate": 5.045330087290976e-07, "loss": 0.0764215886592865, "step": 7554 }, { "epoch": 1.961318795430945, "grad_norm": 10.57158088684082, "learning_rate": 5.044731875219385e-07, "loss": 0.06446009874343872, "step": 7555 }, { "epoch": 1.9615784008307373, "grad_norm": 4.149320125579834, "learning_rate": 5.044137632725041e-07, "loss": 0.01089179515838623, "step": 7556 }, { "epoch": 1.9618380062305296, "grad_norm": 3.553199291229248, "learning_rate": 5.043547359912995e-07, "loss": 0.0047592357732355595, "step": 7557 }, { "epoch": 1.962097611630322, "grad_norm": 7.192654609680176, "learning_rate": 5.042961056887591e-07, "loss": 0.014037643559277058, "step": 7558 }, { "epoch": 1.9623572170301142, "grad_norm": 11.099822044372559, "learning_rate": 5.042378723752473e-07, "loss": 0.07883147895336151, "step": 7559 }, { "epoch": 1.9626168224299065, "grad_norm": 6.6428914070129395, "learning_rate": 5.041800360610583e-07, "loss": 0.009077288210391998, "step": 7560 }, { "epoch": 1.9628764278296988, "grad_norm": 3.3822927474975586, "learning_rate": 5.041225967564167e-07, "loss": 0.00349415629170835, "step": 7561 }, { "epoch": 1.9631360332294912, "grad_norm": 4.257452487945557, "learning_rate": 5.040655544714762e-07, "loss": 0.013107996433973312, "step": 7562 }, { "epoch": 1.9633956386292835, "grad_norm": 10.620783805847168, "learning_rate": 5.040089092163204e-07, "loss": 0.028872665017843246, "step": 7563 }, { "epoch": 1.9636552440290758, "grad_norm": 7.501871109008789, "learning_rate": 5.039526610009634e-07, "loss": 0.039245449006557465, "step": 7564 }, { "epoch": 1.963914849428868, "grad_norm": 10.436403274536133, "learning_rate": 5.038968098353482e-07, "loss": 0.07602811604738235, "step": 7565 }, { "epoch": 1.9641744548286604, "grad_norm": 10.666337966918945, "learning_rate": 5.038413557293478e-07, "loss": 0.041572172194719315, "step": 7566 }, { "epoch": 1.9644340602284527, "grad_norm": 14.161417007446289, "learning_rate": 5.037862986927657e-07, "loss": 0.021413762122392654, "step": 7567 }, { "epoch": 1.964693665628245, "grad_norm": 10.996366500854492, "learning_rate": 5.037316387353347e-07, "loss": 0.1044808030128479, "step": 7568 }, { "epoch": 1.9649532710280373, "grad_norm": 5.2703986167907715, "learning_rate": 5.036773758667168e-07, "loss": 0.008959300816059113, "step": 7569 }, { "epoch": 1.9652128764278296, "grad_norm": 10.965862274169922, "learning_rate": 5.036235100965053e-07, "loss": 0.04649119824171066, "step": 7570 }, { "epoch": 1.965472481827622, "grad_norm": 9.587687492370605, "learning_rate": 5.035700414342218e-07, "loss": 0.051666028797626495, "step": 7571 }, { "epoch": 1.9657320872274142, "grad_norm": 11.07901668548584, "learning_rate": 5.035169698893185e-07, "loss": 0.04470149055123329, "step": 7572 }, { "epoch": 1.9659916926272065, "grad_norm": 5.614193439483643, "learning_rate": 5.034642954711773e-07, "loss": 0.0046605076640844345, "step": 7573 }, { "epoch": 1.9662512980269988, "grad_norm": 6.599521160125732, "learning_rate": 5.034120181891097e-07, "loss": 0.027404483407735825, "step": 7574 }, { "epoch": 1.9665109034267911, "grad_norm": 10.410292625427246, "learning_rate": 5.033601380523576e-07, "loss": 0.08740299940109253, "step": 7575 }, { "epoch": 1.9667705088265834, "grad_norm": 6.503312587738037, "learning_rate": 5.033086550700915e-07, "loss": 0.007610802538692951, "step": 7576 }, { "epoch": 1.9670301142263757, "grad_norm": 9.865730285644531, "learning_rate": 5.03257569251413e-07, "loss": 0.06636501848697662, "step": 7577 }, { "epoch": 1.9672897196261683, "grad_norm": 4.900853157043457, "learning_rate": 5.032068806053528e-07, "loss": 0.016925828531384468, "step": 7578 }, { "epoch": 1.9675493250259606, "grad_norm": 11.808980941772461, "learning_rate": 5.031565891408709e-07, "loss": 0.06024260073900223, "step": 7579 }, { "epoch": 1.967808930425753, "grad_norm": 6.242331504821777, "learning_rate": 5.031066948668585e-07, "loss": 0.011485740542411804, "step": 7580 }, { "epoch": 1.9680685358255452, "grad_norm": 2.2228310108184814, "learning_rate": 5.030571977921354e-07, "loss": 0.00345442071557045, "step": 7581 }, { "epoch": 1.9683281412253375, "grad_norm": 8.49876594543457, "learning_rate": 5.030080979254515e-07, "loss": 0.02582971379160881, "step": 7582 }, { "epoch": 1.9685877466251298, "grad_norm": 5.386411190032959, "learning_rate": 5.029593952754865e-07, "loss": 0.03091803751885891, "step": 7583 }, { "epoch": 1.9688473520249221, "grad_norm": 9.139192581176758, "learning_rate": 5.029110898508502e-07, "loss": 0.011524084955453873, "step": 7584 }, { "epoch": 1.9691069574247144, "grad_norm": 11.165170669555664, "learning_rate": 5.028631816600815e-07, "loss": 0.03692919760942459, "step": 7585 }, { "epoch": 1.9693665628245067, "grad_norm": 6.904069423675537, "learning_rate": 5.028156707116497e-07, "loss": 0.013876549899578094, "step": 7586 }, { "epoch": 1.969626168224299, "grad_norm": 8.542262077331543, "learning_rate": 5.027685570139535e-07, "loss": 0.013549924828112125, "step": 7587 }, { "epoch": 1.9698857736240913, "grad_norm": 8.216272354125977, "learning_rate": 5.02721840575322e-07, "loss": 0.02296566218137741, "step": 7588 }, { "epoch": 1.9701453790238836, "grad_norm": 8.64220142364502, "learning_rate": 5.02675521404013e-07, "loss": 0.016235336661338806, "step": 7589 }, { "epoch": 1.9704049844236762, "grad_norm": 12.582184791564941, "learning_rate": 5.026295995082151e-07, "loss": 0.06819169968366623, "step": 7590 }, { "epoch": 1.9706645898234685, "grad_norm": 6.222652435302734, "learning_rate": 5.025840748960458e-07, "loss": 0.01552064623683691, "step": 7591 }, { "epoch": 1.9709241952232608, "grad_norm": 1.8920170068740845, "learning_rate": 5.025389475755532e-07, "loss": 0.0031140646897256374, "step": 7592 }, { "epoch": 1.971183800623053, "grad_norm": 7.39307165145874, "learning_rate": 5.024942175547146e-07, "loss": 0.027815237641334534, "step": 7593 }, { "epoch": 1.9714434060228454, "grad_norm": 5.295709133148193, "learning_rate": 5.024498848414372e-07, "loss": 0.012943332083523273, "step": 7594 }, { "epoch": 1.9717030114226377, "grad_norm": 10.034997940063477, "learning_rate": 5.024059494435582e-07, "loss": 0.04786300286650658, "step": 7595 }, { "epoch": 1.97196261682243, "grad_norm": 7.400404453277588, "learning_rate": 5.023624113688442e-07, "loss": 0.030325060710310936, "step": 7596 }, { "epoch": 1.9722222222222223, "grad_norm": 12.339344024658203, "learning_rate": 5.023192706249917e-07, "loss": 0.06385044753551483, "step": 7597 }, { "epoch": 1.9724818276220146, "grad_norm": 10.471773147583008, "learning_rate": 5.022765272196273e-07, "loss": 0.008618921972811222, "step": 7598 }, { "epoch": 1.972741433021807, "grad_norm": 9.910747528076172, "learning_rate": 5.022341811603066e-07, "loss": 0.04892151057720184, "step": 7599 }, { "epoch": 1.9730010384215992, "grad_norm": 1.430881381034851, "learning_rate": 5.021922324545157e-07, "loss": 0.004705469589680433, "step": 7600 }, { "epoch": 1.9732606438213915, "grad_norm": 9.5062255859375, "learning_rate": 5.021506811096703e-07, "loss": 0.020000256597995758, "step": 7601 }, { "epoch": 1.9735202492211839, "grad_norm": 7.224993705749512, "learning_rate": 5.021095271331153e-07, "loss": 0.01673758588731289, "step": 7602 }, { "epoch": 1.9737798546209762, "grad_norm": 10.970293045043945, "learning_rate": 5.020687705321261e-07, "loss": 0.019323348999023438, "step": 7603 }, { "epoch": 1.9740394600207685, "grad_norm": 9.6807279586792, "learning_rate": 5.020284113139077e-07, "loss": 0.020209725946187973, "step": 7604 }, { "epoch": 1.9742990654205608, "grad_norm": 11.260957717895508, "learning_rate": 5.019884494855942e-07, "loss": 0.014204494655132294, "step": 7605 }, { "epoch": 1.974558670820353, "grad_norm": 2.415844202041626, "learning_rate": 5.019488850542504e-07, "loss": 0.004903980065137148, "step": 7606 }, { "epoch": 1.9748182762201454, "grad_norm": 8.045358657836914, "learning_rate": 5.0190971802687e-07, "loss": 0.02810421586036682, "step": 7607 }, { "epoch": 1.9750778816199377, "grad_norm": 8.27931022644043, "learning_rate": 5.018709484103771e-07, "loss": 0.03755154460668564, "step": 7608 }, { "epoch": 1.97533748701973, "grad_norm": 6.867565631866455, "learning_rate": 5.018325762116251e-07, "loss": 0.024377383291721344, "step": 7609 }, { "epoch": 1.9755970924195223, "grad_norm": 3.099580764770508, "learning_rate": 5.017946014373977e-07, "loss": 0.0029338947497308254, "step": 7610 }, { "epoch": 1.9758566978193146, "grad_norm": 4.2926130294799805, "learning_rate": 5.017570240944074e-07, "loss": 0.029386207461357117, "step": 7611 }, { "epoch": 1.976116303219107, "grad_norm": 7.238816738128662, "learning_rate": 5.017198441892972e-07, "loss": 0.007685491815209389, "step": 7612 }, { "epoch": 1.9763759086188992, "grad_norm": 9.12541389465332, "learning_rate": 5.016830617286399e-07, "loss": 0.011205941438674927, "step": 7613 }, { "epoch": 1.9766355140186915, "grad_norm": 6.021729469299316, "learning_rate": 5.016466767189378e-07, "loss": 0.010919584892690182, "step": 7614 }, { "epoch": 1.9768951194184838, "grad_norm": 15.00564956665039, "learning_rate": 5.016106891666227e-07, "loss": 0.015665002167224884, "step": 7615 }, { "epoch": 1.9771547248182761, "grad_norm": 3.143521547317505, "learning_rate": 5.015750990780564e-07, "loss": 0.003777734935283661, "step": 7616 }, { "epoch": 1.9774143302180685, "grad_norm": 12.58506965637207, "learning_rate": 5.015399064595305e-07, "loss": 0.016891056671738625, "step": 7617 }, { "epoch": 1.9776739356178608, "grad_norm": 10.480782508850098, "learning_rate": 5.01505111317266e-07, "loss": 0.05803773179650307, "step": 7618 }, { "epoch": 1.977933541017653, "grad_norm": 7.254306793212891, "learning_rate": 5.014707136574146e-07, "loss": 0.016921989619731903, "step": 7619 }, { "epoch": 1.9781931464174454, "grad_norm": 8.920049667358398, "learning_rate": 5.014367134860563e-07, "loss": 0.016793008893728256, "step": 7620 }, { "epoch": 1.9784527518172377, "grad_norm": 2.3159968852996826, "learning_rate": 5.014031108092017e-07, "loss": 0.003077826462686062, "step": 7621 }, { "epoch": 1.97871235721703, "grad_norm": 2.4546408653259277, "learning_rate": 5.01369905632791e-07, "loss": 0.0081168282777071, "step": 7622 }, { "epoch": 1.9789719626168223, "grad_norm": 8.22233772277832, "learning_rate": 5.013370979626944e-07, "loss": 0.0074889035895466805, "step": 7623 }, { "epoch": 1.9792315680166146, "grad_norm": 0.3990163505077362, "learning_rate": 5.013046878047113e-07, "loss": 0.001227271044626832, "step": 7624 }, { "epoch": 1.979491173416407, "grad_norm": 3.5767929553985596, "learning_rate": 5.01272675164571e-07, "loss": 0.015839558094739914, "step": 7625 }, { "epoch": 1.9797507788161994, "grad_norm": 9.19272232055664, "learning_rate": 5.012410600479326e-07, "loss": 0.02052055299282074, "step": 7626 }, { "epoch": 1.9800103842159917, "grad_norm": 9.000655174255371, "learning_rate": 5.012098424603852e-07, "loss": 0.041025012731552124, "step": 7627 }, { "epoch": 1.980269989615784, "grad_norm": 10.375683784484863, "learning_rate": 5.011790224074471e-07, "loss": 0.025555016472935677, "step": 7628 }, { "epoch": 1.9805295950155763, "grad_norm": 9.880080223083496, "learning_rate": 5.011485998945668e-07, "loss": 0.037740595638751984, "step": 7629 }, { "epoch": 1.9807892004153687, "grad_norm": 0.6621754765510559, "learning_rate": 5.01118574927122e-07, "loss": 0.0016839629970490932, "step": 7630 }, { "epoch": 1.981048805815161, "grad_norm": 11.242833137512207, "learning_rate": 5.010889475104205e-07, "loss": 0.04888027533888817, "step": 7631 }, { "epoch": 1.9813084112149533, "grad_norm": 5.031106472015381, "learning_rate": 5.010597176497002e-07, "loss": 0.008711814880371094, "step": 7632 }, { "epoch": 1.9815680166147456, "grad_norm": 13.163233757019043, "learning_rate": 5.010308853501275e-07, "loss": 0.011099754832684994, "step": 7633 }, { "epoch": 1.9818276220145379, "grad_norm": 10.341577529907227, "learning_rate": 5.010024506168001e-07, "loss": 0.06796656548976898, "step": 7634 }, { "epoch": 1.9820872274143302, "grad_norm": 9.795126914978027, "learning_rate": 5.009744134547438e-07, "loss": 0.015824006870388985, "step": 7635 }, { "epoch": 1.9823468328141225, "grad_norm": 11.129071235656738, "learning_rate": 5.009467738689157e-07, "loss": 0.06190549582242966, "step": 7636 }, { "epoch": 1.9826064382139148, "grad_norm": 8.701565742492676, "learning_rate": 5.009195318642012e-07, "loss": 0.04596366733312607, "step": 7637 }, { "epoch": 1.9828660436137073, "grad_norm": 8.60280990600586, "learning_rate": 5.008926874454166e-07, "loss": 0.04841221868991852, "step": 7638 }, { "epoch": 1.9831256490134996, "grad_norm": 9.100397109985352, "learning_rate": 5.008662406173071e-07, "loss": 0.03000802919268608, "step": 7639 }, { "epoch": 1.983385254413292, "grad_norm": 2.3092305660247803, "learning_rate": 5.008401913845478e-07, "loss": 0.009376275353133678, "step": 7640 }, { "epoch": 1.9836448598130842, "grad_norm": 4.760688781738281, "learning_rate": 5.008145397517439e-07, "loss": 0.013692403212189674, "step": 7641 }, { "epoch": 1.9839044652128766, "grad_norm": 6.739892959594727, "learning_rate": 5.007892857234296e-07, "loss": 0.020573876798152924, "step": 7642 }, { "epoch": 1.9841640706126689, "grad_norm": 8.573616027832031, "learning_rate": 5.007644293040695e-07, "loss": 0.02212066948413849, "step": 7643 }, { "epoch": 1.9844236760124612, "grad_norm": 6.7440409660339355, "learning_rate": 5.007399704980578e-07, "loss": 0.013411030173301697, "step": 7644 }, { "epoch": 1.9846832814122535, "grad_norm": 2.9381909370422363, "learning_rate": 5.007159093097181e-07, "loss": 0.0013026073575019836, "step": 7645 }, { "epoch": 1.9849428868120458, "grad_norm": 0.5071078538894653, "learning_rate": 5.006922457433039e-07, "loss": 0.0011263432679697871, "step": 7646 }, { "epoch": 1.985202492211838, "grad_norm": 1.257077693939209, "learning_rate": 5.006689798029981e-07, "loss": 0.0040954118594527245, "step": 7647 }, { "epoch": 1.9854620976116304, "grad_norm": 1.4348503351211548, "learning_rate": 5.00646111492914e-07, "loss": 0.006140862591564655, "step": 7648 }, { "epoch": 1.9857217030114227, "grad_norm": 6.589706897735596, "learning_rate": 5.006236408170939e-07, "loss": 0.007632429711520672, "step": 7649 }, { "epoch": 1.985981308411215, "grad_norm": 9.936112403869629, "learning_rate": 5.006015677795102e-07, "loss": 0.019601672887802124, "step": 7650 }, { "epoch": 1.9862409138110073, "grad_norm": 0.9056838154792786, "learning_rate": 5.005798923840652e-07, "loss": 0.0034139107447117567, "step": 7651 }, { "epoch": 1.9865005192107996, "grad_norm": 7.830855369567871, "learning_rate": 5.005586146345901e-07, "loss": 0.015933897346258163, "step": 7652 }, { "epoch": 1.986760124610592, "grad_norm": 8.500604629516602, "learning_rate": 5.005377345348463e-07, "loss": 0.008460069075226784, "step": 7653 }, { "epoch": 1.9870197300103842, "grad_norm": 8.420544624328613, "learning_rate": 5.005172520885257e-07, "loss": 0.05018593370914459, "step": 7654 }, { "epoch": 1.9872793354101765, "grad_norm": 11.155835151672363, "learning_rate": 5.004971672992484e-07, "loss": 0.025657741352915764, "step": 7655 }, { "epoch": 1.9875389408099688, "grad_norm": 6.103438854217529, "learning_rate": 5.004774801705649e-07, "loss": 0.007379727438092232, "step": 7656 }, { "epoch": 1.9877985462097612, "grad_norm": 1.6075485944747925, "learning_rate": 5.00458190705956e-07, "loss": 0.003658323548734188, "step": 7657 }, { "epoch": 1.9880581516095535, "grad_norm": 3.922168731689453, "learning_rate": 5.00439298908831e-07, "loss": 0.011705269105732441, "step": 7658 }, { "epoch": 1.9883177570093458, "grad_norm": 2.7638094425201416, "learning_rate": 5.004208047825299e-07, "loss": 0.006952987052500248, "step": 7659 }, { "epoch": 1.988577362409138, "grad_norm": 1.6299192905426025, "learning_rate": 5.004027083303222e-07, "loss": 0.0036116091068834066, "step": 7660 }, { "epoch": 1.9888369678089304, "grad_norm": 4.963471412658691, "learning_rate": 5.003850095554065e-07, "loss": 0.010644745081663132, "step": 7661 }, { "epoch": 1.9890965732087227, "grad_norm": 2.55281662940979, "learning_rate": 5.00367708460912e-07, "loss": 0.006089954636991024, "step": 7662 }, { "epoch": 1.989356178608515, "grad_norm": 10.426007270812988, "learning_rate": 5.003508050498967e-07, "loss": 0.05073416233062744, "step": 7663 }, { "epoch": 1.9896157840083073, "grad_norm": 11.833382606506348, "learning_rate": 5.00334299325349e-07, "loss": 0.006852129008620977, "step": 7664 }, { "epoch": 1.9898753894080996, "grad_norm": 10.124542236328125, "learning_rate": 5.003181912901865e-07, "loss": 0.016259128227829933, "step": 7665 }, { "epoch": 1.990134994807892, "grad_norm": 4.942392826080322, "learning_rate": 5.003024809472572e-07, "loss": 0.004286845214664936, "step": 7666 }, { "epoch": 1.9903946002076842, "grad_norm": 9.954922676086426, "learning_rate": 5.002871682993378e-07, "loss": 0.012840712442994118, "step": 7667 }, { "epoch": 1.9906542056074765, "grad_norm": 1.701145052909851, "learning_rate": 5.002722533491354e-07, "loss": 0.0014269589446485043, "step": 7668 }, { "epoch": 1.9909138110072688, "grad_norm": 9.113811492919922, "learning_rate": 5.002577360992869e-07, "loss": 0.01481900829821825, "step": 7669 }, { "epoch": 1.9911734164070611, "grad_norm": 8.087076187133789, "learning_rate": 5.002436165523583e-07, "loss": 0.02321913279592991, "step": 7670 }, { "epoch": 1.9914330218068534, "grad_norm": 6.769175052642822, "learning_rate": 5.002298947108454e-07, "loss": 0.01274887565523386, "step": 7671 }, { "epoch": 1.9916926272066457, "grad_norm": 13.943981170654297, "learning_rate": 5.002165705771746e-07, "loss": 0.06220895051956177, "step": 7672 }, { "epoch": 1.991952232606438, "grad_norm": 11.565264701843262, "learning_rate": 5.002036441537007e-07, "loss": 0.058290403336286545, "step": 7673 }, { "epoch": 1.9922118380062306, "grad_norm": 1.9547795057296753, "learning_rate": 5.00191115442709e-07, "loss": 0.0026502246037125587, "step": 7674 }, { "epoch": 1.992471443406023, "grad_norm": 6.175225257873535, "learning_rate": 5.001789844464145e-07, "loss": 0.005648806691169739, "step": 7675 }, { "epoch": 1.9927310488058152, "grad_norm": 9.526251792907715, "learning_rate": 5.001672511669613e-07, "loss": 0.02012992650270462, "step": 7676 }, { "epoch": 1.9929906542056075, "grad_norm": 9.77379322052002, "learning_rate": 5.001559156064238e-07, "loss": 0.017868822440505028, "step": 7677 }, { "epoch": 1.9932502596053998, "grad_norm": 6.299620628356934, "learning_rate": 5.00144977766806e-07, "loss": 0.005701158661395311, "step": 7678 }, { "epoch": 1.9935098650051921, "grad_norm": 8.628693580627441, "learning_rate": 5.001344376500408e-07, "loss": 0.03894973173737526, "step": 7679 }, { "epoch": 1.9937694704049844, "grad_norm": 4.77823543548584, "learning_rate": 5.001242952579924e-07, "loss": 0.006036761216819286, "step": 7680 }, { "epoch": 1.9940290758047767, "grad_norm": 9.561266899108887, "learning_rate": 5.001145505924532e-07, "loss": 0.010454826056957245, "step": 7681 }, { "epoch": 1.994288681204569, "grad_norm": 11.117560386657715, "learning_rate": 5.001052036551458e-07, "loss": 0.08117702603340149, "step": 7682 }, { "epoch": 1.9945482866043613, "grad_norm": 3.1651768684387207, "learning_rate": 5.000962544477227e-07, "loss": 0.012161842547357082, "step": 7683 }, { "epoch": 1.9948078920041536, "grad_norm": 6.2542219161987305, "learning_rate": 5.000877029717655e-07, "loss": 0.00960729643702507, "step": 7684 }, { "epoch": 1.995067497403946, "grad_norm": 18.77297019958496, "learning_rate": 5.000795492287867e-07, "loss": 0.04306270554661751, "step": 7685 }, { "epoch": 1.9953271028037385, "grad_norm": 0.6838592290878296, "learning_rate": 5.000717932202271e-07, "loss": 0.0008837068453431129, "step": 7686 }, { "epoch": 1.9955867082035308, "grad_norm": 9.338550567626953, "learning_rate": 5.000644349474577e-07, "loss": 0.030749527737498283, "step": 7687 }, { "epoch": 1.995846313603323, "grad_norm": 7.6919050216674805, "learning_rate": 5.000574744117799e-07, "loss": 0.009659857489168644, "step": 7688 }, { "epoch": 1.9961059190031154, "grad_norm": 15.112417221069336, "learning_rate": 5.000509116144236e-07, "loss": 0.03414037078619003, "step": 7689 }, { "epoch": 1.9963655244029077, "grad_norm": 8.833207130432129, "learning_rate": 5.000447465565491e-07, "loss": 0.020902708172798157, "step": 7690 }, { "epoch": 1.9966251298027, "grad_norm": 9.50918197631836, "learning_rate": 5.000389792392462e-07, "loss": 0.060631174594163895, "step": 7691 }, { "epoch": 1.9968847352024923, "grad_norm": 6.893176555633545, "learning_rate": 5.000336096635346e-07, "loss": 0.010877227410674095, "step": 7692 }, { "epoch": 1.9971443406022846, "grad_norm": 5.50828742980957, "learning_rate": 5.000286378303634e-07, "loss": 0.014891192317008972, "step": 7693 }, { "epoch": 1.997403946002077, "grad_norm": 11.726415634155273, "learning_rate": 5.000240637406114e-07, "loss": 0.0798947736620903, "step": 7694 }, { "epoch": 1.9976635514018692, "grad_norm": 3.7947516441345215, "learning_rate": 5.000198873950875e-07, "loss": 0.007636896800249815, "step": 7695 }, { "epoch": 1.9979231568016615, "grad_norm": 5.301407814025879, "learning_rate": 5.000161087945296e-07, "loss": 0.010741552338004112, "step": 7696 }, { "epoch": 1.9981827622014539, "grad_norm": 9.25462532043457, "learning_rate": 5.000127279396061e-07, "loss": 0.10137039422988892, "step": 7697 }, { "epoch": 1.9984423676012462, "grad_norm": 4.103989124298096, "learning_rate": 5.000097448309143e-07, "loss": 0.021232040598988533, "step": 7698 }, { "epoch": 1.9987019730010385, "grad_norm": 5.729522228240967, "learning_rate": 5.000071594689815e-07, "loss": 0.012826499529182911, "step": 7699 }, { "epoch": 1.9989615784008308, "grad_norm": 8.516284942626953, "learning_rate": 5.000049718542651e-07, "loss": 0.05655009299516678, "step": 7700 }, { "epoch": 1.999221183800623, "grad_norm": 9.368715286254883, "learning_rate": 5.000031819871517e-07, "loss": 0.02057873085141182, "step": 7701 }, { "epoch": 1.9994807892004154, "grad_norm": 10.116219520568848, "learning_rate": 5.000017898679574e-07, "loss": 0.026697248220443726, "step": 7702 }, { "epoch": 1.9997403946002077, "grad_norm": 8.104308128356934, "learning_rate": 5.000007954969287e-07, "loss": 0.018273232504725456, "step": 7703 }, { "epoch": 2.0, "grad_norm": 0.5357872247695923, "learning_rate": 5.000001988742409e-07, "loss": 0.001505000051110983, "step": 7704 } ], "logging_steps": 1, "max_steps": 7704, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }