{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 3852, "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 } ], "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": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }